1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _NDISC_H #define _NDISC_H #include <net/ipv6_stubs.h> /* * ICMP codes for neighbour discovery messages */ #define NDISC_ROUTER_SOLICITATION 133 #define NDISC_ROUTER_ADVERTISEMENT 134 #define NDISC_NEIGHBOUR_SOLICITATION 135 #define NDISC_NEIGHBOUR_ADVERTISEMENT 136 #define NDISC_REDIRECT 137 /* * Router type: cross-layer information from link-layer to * IPv6 layer reported by certain link types (e.g., RFC4214). */ #define NDISC_NODETYPE_UNSPEC 0 /* unspecified (default) */ #define NDISC_NODETYPE_HOST 1 /* host or unauthorized router */ #define NDISC_NODETYPE_NODEFAULT 2 /* non-default router */ #define NDISC_NODETYPE_DEFAULT 3 /* default router */ /* * ndisc options */ enum { __ND_OPT_PREFIX_INFO_END = 0, ND_OPT_SOURCE_LL_ADDR = 1, /* RFC2461 */ ND_OPT_TARGET_LL_ADDR = 2, /* RFC2461 */ ND_OPT_PREFIX_INFO = 3, /* RFC2461 */ ND_OPT_REDIRECT_HDR = 4, /* RFC2461 */ ND_OPT_MTU = 5, /* RFC2461 */ ND_OPT_NONCE = 14, /* RFC7527 */ __ND_OPT_ARRAY_MAX, ND_OPT_ROUTE_INFO = 24, /* RFC4191 */ ND_OPT_RDNSS = 25, /* RFC5006 */ ND_OPT_DNSSL = 31, /* RFC6106 */ ND_OPT_6CO = 34, /* RFC6775 */ ND_OPT_CAPTIVE_PORTAL = 37, /* RFC7710 */ ND_OPT_PREF64 = 38, /* RFC8781 */ __ND_OPT_MAX }; #define MAX_RTR_SOLICITATION_DELAY HZ #define ND_REACHABLE_TIME (30*HZ) #define ND_RETRANS_TIMER HZ #include <linux/compiler.h> #include <linux/icmpv6.h> #include <linux/in6.h> #include <linux/types.h> #include <linux/if_arp.h> #include <linux/netdevice.h> #include <linux/hash.h> #include <net/neighbour.h> /* Set to 3 to get tracing... */ #define ND_DEBUG 1 #define ND_PRINTK(val, level, fmt, ...) \ do { \ if (val <= ND_DEBUG) \ net_##level##_ratelimited(fmt, ##__VA_ARGS__); \ } while (0) struct ctl_table; struct inet6_dev; struct net_device; struct net_proto_family; struct sk_buff; struct prefix_info; extern struct neigh_table nd_tbl; struct nd_msg { struct icmp6hdr icmph; struct in6_addr target; __u8 opt[]; }; struct rs_msg { struct icmp6hdr icmph; __u8 opt[]; }; struct ra_msg { struct icmp6hdr icmph; __be32 reachable_time; __be32 retrans_timer; }; struct rd_msg { struct icmp6hdr icmph; struct in6_addr target; struct in6_addr dest; __u8 opt[]; }; struct nd_opt_hdr { __u8 nd_opt_type; __u8 nd_opt_len; } __packed; /* ND options */ struct ndisc_options { struct nd_opt_hdr *nd_opt_array[__ND_OPT_ARRAY_MAX]; #ifdef CONFIG_IPV6_ROUTE_INFO struct nd_opt_hdr *nd_opts_ri; struct nd_opt_hdr *nd_opts_ri_end; #endif struct nd_opt_hdr *nd_useropts; struct nd_opt_hdr *nd_useropts_end; #if IS_ENABLED(CONFIG_IEEE802154_6LOWPAN) struct nd_opt_hdr *nd_802154_opt_array[ND_OPT_TARGET_LL_ADDR + 1]; #endif }; #define nd_opts_src_lladdr nd_opt_array[ND_OPT_SOURCE_LL_ADDR] #define nd_opts_tgt_lladdr nd_opt_array[ND_OPT_TARGET_LL_ADDR] #define nd_opts_pi nd_opt_array[ND_OPT_PREFIX_INFO] #define nd_opts_pi_end nd_opt_array[__ND_OPT_PREFIX_INFO_END] #define nd_opts_rh nd_opt_array[ND_OPT_REDIRECT_HDR] #define nd_opts_mtu nd_opt_array[ND_OPT_MTU] #define nd_opts_nonce nd_opt_array[ND_OPT_NONCE] #define nd_802154_opts_src_lladdr nd_802154_opt_array[ND_OPT_SOURCE_LL_ADDR] #define nd_802154_opts_tgt_lladdr nd_802154_opt_array[ND_OPT_TARGET_LL_ADDR] #define NDISC_OPT_SPACE(len) (((len)+2+7)&~7) struct ndisc_options *ndisc_parse_options(const struct net_device *dev, u8 *opt, int opt_len, struct ndisc_options *ndopts); void __ndisc_fill_addr_option(struct sk_buff *skb, int type, void *data, int data_len, int pad); #define NDISC_OPS_REDIRECT_DATA_SPACE 2 /* * This structure defines the hooks for IPv6 neighbour discovery. * The following hooks can be defined; unless noted otherwise, they are * optional and can be filled with a null pointer. * * int (*is_useropt)(u8 nd_opt_type): * This function is called when IPv6 decide RA userspace options. if * this function returns 1 then the option given by nd_opt_type will * be handled as userspace option additional to the IPv6 options. * * int (*parse_options)(const struct net_device *dev, * struct nd_opt_hdr *nd_opt, * struct ndisc_options *ndopts): * This function is called while parsing ndisc ops and put each position * as pointer into ndopts. If this function return unequal 0, then this * function took care about the ndisc option, if 0 then the IPv6 ndisc * option parser will take care about that option. * * void (*update)(const struct net_device *dev, struct neighbour *n, * u32 flags, u8 icmp6_type, * const struct ndisc_options *ndopts): * This function is called when IPv6 ndisc updates the neighbour cache * entry. Additional options which can be updated may be previously * parsed by parse_opts callback and accessible over ndopts parameter. * * int (*opt_addr_space)(const struct net_device *dev, u8 icmp6_type, * struct neighbour *neigh, u8 *ha_buf, * u8 **ha): * This function is called when the necessary option space will be * calculated before allocating a skb. The parameters neigh, ha_buf * abd ha are available on NDISC_REDIRECT messages only. * * void (*fill_addr_option)(const struct net_device *dev, * struct sk_buff *skb, u8 icmp6_type, * const u8 *ha): * This function is called when the skb will finally fill the option * fields inside skb. NOTE: this callback should fill the option * fields to the skb which are previously indicated by opt_space * parameter. That means the decision to add such option should * not lost between these two callbacks, e.g. protected by interface * up state. * * void (*prefix_rcv_add_addr)(struct net *net, struct net_device *dev, * const struct prefix_info *pinfo, * struct inet6_dev *in6_dev, * struct in6_addr *addr, * int addr_type, u32 addr_flags, * bool sllao, bool tokenized, * __u32 valid_lft, u32 prefered_lft, * bool dev_addr_generated): * This function is called when a RA messages is received with valid * PIO option fields and an IPv6 address will be added to the interface * for autoconfiguration. The parameter dev_addr_generated reports about * if the address was based on dev->dev_addr or not. This can be used * to add a second address if link-layer operates with two link layer * addresses. E.g. 802.15.4 6LoWPAN. */ struct ndisc_ops { int (*is_useropt)(u8 nd_opt_type); int (*parse_options)(const struct net_device *dev, struct nd_opt_hdr *nd_opt, struct ndisc_options *ndopts); void (*update)(const struct net_device *dev, struct neighbour *n, u32 flags, u8 icmp6_type, const struct ndisc_options *ndopts); int (*opt_addr_space)(const struct net_device *dev, u8 icmp6_type, struct neighbour *neigh, u8 *ha_buf, u8 **ha); void (*fill_addr_option)(const struct net_device *dev, struct sk_buff *skb, u8 icmp6_type, const u8 *ha); void (*prefix_rcv_add_addr)(struct net *net, struct net_device *dev, const struct prefix_info *pinfo, struct inet6_dev *in6_dev, struct in6_addr *addr, int addr_type, u32 addr_flags, bool sllao, bool tokenized, __u32 valid_lft, u32 prefered_lft, bool dev_addr_generated); }; #if IS_ENABLED(CONFIG_IPV6) static inline int ndisc_ops_is_useropt(const struct net_device *dev, u8 nd_opt_type) { if (dev->ndisc_ops && dev->ndisc_ops->is_useropt) return dev->ndisc_ops->is_useropt(nd_opt_type); else return 0; } static inline int ndisc_ops_parse_options(const struct net_device *dev, struct nd_opt_hdr *nd_opt, struct ndisc_options *ndopts) { if (dev->ndisc_ops && dev->ndisc_ops->parse_options) return dev->ndisc_ops->parse_options(dev, nd_opt, ndopts); else return 0; } static inline void ndisc_ops_update(const struct net_device *dev, struct neighbour *n, u32 flags, u8 icmp6_type, const struct ndisc_options *ndopts) { if (dev->ndisc_ops && dev->ndisc_ops->update) dev->ndisc_ops->update(dev, n, flags, icmp6_type, ndopts); } static inline int ndisc_ops_opt_addr_space(const struct net_device *dev, u8 icmp6_type) { if (dev->ndisc_ops && dev->ndisc_ops->opt_addr_space && icmp6_type != NDISC_REDIRECT) return dev->ndisc_ops->opt_addr_space(dev, icmp6_type, NULL, NULL, NULL); else return 0; } static inline int ndisc_ops_redirect_opt_addr_space(const struct net_device *dev, struct neighbour *neigh, u8 *ha_buf, u8 **ha) { if (dev->ndisc_ops && dev->ndisc_ops->opt_addr_space) return dev->ndisc_ops->opt_addr_space(dev, NDISC_REDIRECT, neigh, ha_buf, ha); else return 0; } static inline void ndisc_ops_fill_addr_option(const struct net_device *dev, struct sk_buff *skb, u8 icmp6_type) { if (dev->ndisc_ops && dev->ndisc_ops->fill_addr_option && icmp6_type != NDISC_REDIRECT) dev->ndisc_ops->fill_addr_option(dev, skb, icmp6_type, NULL); } static inline void ndisc_ops_fill_redirect_addr_option(const struct net_device *dev, struct sk_buff *skb, const u8 *ha) { if (dev->ndisc_ops && dev->ndisc_ops->fill_addr_option) dev->ndisc_ops->fill_addr_option(dev, skb, NDISC_REDIRECT, ha); } static inline void ndisc_ops_prefix_rcv_add_addr(struct net *net, struct net_device *dev, const struct prefix_info *pinfo, struct inet6_dev *in6_dev, struct in6_addr *addr, int addr_type, u32 addr_flags, bool sllao, bool tokenized, __u32 valid_lft, u32 prefered_lft, bool dev_addr_generated) { if (dev->ndisc_ops && dev->ndisc_ops->prefix_rcv_add_addr) dev->ndisc_ops->prefix_rcv_add_addr(net, dev, pinfo, in6_dev, addr, addr_type, addr_flags, sllao, tokenized, valid_lft, prefered_lft, dev_addr_generated); } #endif /* * Return the padding between the option length and the start of the * link addr. Currently only IP-over-InfiniBand needs this, although * if RFC 3831 IPv6-over-Fibre Channel is ever implemented it may * also need a pad of 2. */ static inline int ndisc_addr_option_pad(unsigned short type) { switch (type) { case ARPHRD_INFINIBAND: return 2; default: return 0; } } static inline int __ndisc_opt_addr_space(unsigned char addr_len, int pad) { return NDISC_OPT_SPACE(addr_len + pad); } #if IS_ENABLED(CONFIG_IPV6) static inline int ndisc_opt_addr_space(struct net_device *dev, u8 icmp6_type) { return __ndisc_opt_addr_space(dev->addr_len, ndisc_addr_option_pad(dev->type)) + ndisc_ops_opt_addr_space(dev, icmp6_type); } static inline int ndisc_redirect_opt_addr_space(struct net_device *dev, struct neighbour *neigh, u8 *ops_data_buf, u8 **ops_data) { return __ndisc_opt_addr_space(dev->addr_len, ndisc_addr_option_pad(dev->type)) + ndisc_ops_redirect_opt_addr_space(dev, neigh, ops_data_buf, ops_data); } #endif static inline u8 *__ndisc_opt_addr_data(struct nd_opt_hdr *p, unsigned char addr_len, int prepad) { u8 *lladdr = (u8 *)(p + 1); int lladdrlen = p->nd_opt_len << 3; if (lladdrlen != __ndisc_opt_addr_space(addr_len, prepad)) return NULL; return lladdr + prepad; } static inline u8 *ndisc_opt_addr_data(struct nd_opt_hdr *p, struct net_device *dev) { return __ndisc_opt_addr_data(p, dev->addr_len, ndisc_addr_option_pad(dev->type)); } static inline u32 ndisc_hashfn(const void *pkey, const struct net_device *dev, __u32 *hash_rnd) { const u32 *p32 = pkey; return (((p32[0] ^ hash32_ptr(dev)) * hash_rnd[0]) + (p32[1] * hash_rnd[1]) + (p32[2] * hash_rnd[2]) + (p32[3] * hash_rnd[3])); } static inline struct neighbour *__ipv6_neigh_lookup_noref(struct net_device *dev, const void *pkey) { return ___neigh_lookup_noref(&nd_tbl, neigh_key_eq128, ndisc_hashfn, pkey, dev); } static inline struct neighbour *__ipv6_neigh_lookup_noref_stub(struct net_device *dev, const void *pkey) { return ___neigh_lookup_noref(ipv6_stub->nd_tbl, neigh_key_eq128, ndisc_hashfn, pkey, dev); } static inline struct neighbour *__ipv6_neigh_lookup(struct net_device *dev, const void *pkey) { struct neighbour *n; rcu_read_lock_bh(); n = __ipv6_neigh_lookup_noref(dev, pkey); if (n && !refcount_inc_not_zero(&n->refcnt)) n = NULL; rcu_read_unlock_bh(); return n; } static inline void __ipv6_confirm_neigh(struct net_device *dev, const void *pkey) { struct neighbour *n; rcu_read_lock_bh(); n = __ipv6_neigh_lookup_noref(dev, pkey); if (n) { unsigned long now = jiffies; /* avoid dirtying neighbour */ if (READ_ONCE(n->confirmed) != now) WRITE_ONCE(n->confirmed, now); } rcu_read_unlock_bh(); } static inline void __ipv6_confirm_neigh_stub(struct net_device *dev, const void *pkey) { struct neighbour *n; rcu_read_lock_bh(); n = __ipv6_neigh_lookup_noref_stub(dev, pkey); if (n) { unsigned long now = jiffies; /* avoid dirtying neighbour */ if (READ_ONCE(n->confirmed) != now) WRITE_ONCE(n->confirmed, now); } rcu_read_unlock_bh(); } /* uses ipv6_stub and is meant for use outside of IPv6 core */ static inline struct neighbour *ip_neigh_gw6(struct net_device *dev, const void *addr) { struct neighbour *neigh; neigh = __ipv6_neigh_lookup_noref_stub(dev, addr); if (unlikely(!neigh)) neigh = __neigh_create(ipv6_stub->nd_tbl, addr, dev, false); return neigh; } int ndisc_init(void); int ndisc_late_init(void); void ndisc_late_cleanup(void); void ndisc_cleanup(void); int ndisc_rcv(struct sk_buff *skb); void ndisc_send_ns(struct net_device *dev, const struct in6_addr *solicit, const struct in6_addr *daddr, const struct in6_addr *saddr, u64 nonce); void ndisc_send_rs(struct net_device *dev, const struct in6_addr *saddr, const struct in6_addr *daddr); void ndisc_send_na(struct net_device *dev, const struct in6_addr *daddr, const struct in6_addr *solicited_addr, bool router, bool solicited, bool override, bool inc_opt); void ndisc_send_redirect(struct sk_buff *skb, const struct in6_addr *target); int ndisc_mc_map(const struct in6_addr *addr, char *buf, struct net_device *dev, int dir); void ndisc_update(const struct net_device *dev, struct neighbour *neigh, const u8 *lladdr, u8 new, u32 flags, u8 icmp6_type, struct ndisc_options *ndopts); /* * IGMP */ int igmp6_init(void); int igmp6_late_init(void); void igmp6_cleanup(void); void igmp6_late_cleanup(void); int igmp6_event_query(struct sk_buff *skb); int igmp6_event_report(struct sk_buff *skb); #ifdef CONFIG_SYSCTL int ndisc_ifinfo_sysctl_change(struct ctl_table *ctl, int write, void *buffer, size_t *lenp, loff_t *ppos); int ndisc_ifinfo_sysctl_strategy(struct ctl_table *ctl, void __user *oldval, size_t __user *oldlenp, void __user *newval, size_t newlen); #endif void inet6_ifinfo_notify(int event, struct inet6_dev *idev); #endif
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 /* SPDX-License-Identifier: GPL-2.0-or-later */ /* Filesystem parameter description and parser * * Copyright (C) 2018 Red Hat, Inc. All Rights Reserved. * Written by David Howells (dhowells@redhat.com) */ #ifndef _LINUX_FS_PARSER_H #define _LINUX_FS_PARSER_H #include <linux/fs_context.h> struct path; struct constant_table { const char *name; int value; }; struct fs_parameter_spec; struct fs_parse_result; typedef int fs_param_type(struct p_log *, const struct fs_parameter_spec *, struct fs_parameter *, struct fs_parse_result *); /* * The type of parameter expected. */ fs_param_type fs_param_is_bool, fs_param_is_u32, fs_param_is_s32, fs_param_is_u64, fs_param_is_enum, fs_param_is_string, fs_param_is_blob, fs_param_is_blockdev, fs_param_is_path, fs_param_is_fd; /* * Specification of the type of value a parameter wants. * * Note that the fsparam_flag(), fsparam_string(), fsparam_u32(), ... macros * should be used to generate elements of this type. */ struct fs_parameter_spec { const char *name; fs_param_type *type; /* The desired parameter type */ u8 opt; /* Option number (returned by fs_parse()) */ unsigned short flags; #define fs_param_neg_with_no 0x0002 /* "noxxx" is negative param */ #define fs_param_neg_with_empty 0x0004 /* "xxx=" is negative param */ #define fs_param_deprecated 0x0008 /* The param is deprecated */ const void *data; }; /* * Result of parse. */ struct fs_parse_result { bool negated; /* T if param was "noxxx" */ union { bool boolean; /* For spec_bool */ int int_32; /* For spec_s32/spec_enum */ unsigned int uint_32; /* For spec_u32{,_octal,_hex}/spec_enum */ u64 uint_64; /* For spec_u64 */ }; }; extern int __fs_parse(struct p_log *log, const struct fs_parameter_spec *desc, struct fs_parameter *value, struct fs_parse_result *result); static inline int fs_parse(struct fs_context *fc, const struct fs_parameter_spec *desc, struct fs_parameter *param, struct fs_parse_result *result) { return __fs_parse(&fc->log, desc, param, result); } extern int fs_lookup_param(struct fs_context *fc, struct fs_parameter *param, bool want_bdev, struct path *_path); extern int lookup_constant(const struct constant_table tbl[], const char *name, int not_found); #ifdef CONFIG_VALIDATE_FS_PARSER extern bool validate_constant_table(const struct constant_table *tbl, size_t tbl_size, int low, int high, int special); extern bool fs_validate_description(const char *name, const struct fs_parameter_spec *desc); #else static inline bool validate_constant_table(const struct constant_table *tbl, size_t tbl_size, int low, int high, int special) { return true; } static inline bool fs_validate_description(const char *name, const struct fs_parameter_spec *desc) { return true; } #endif /* * Parameter type, name, index and flags element constructors. Use as: * * fsparam_xxxx("foo", Opt_foo) * * If existing helpers are not enough, direct use of __fsparam() would * work, but any such case is probably a sign that new helper is needed. * Helpers will remain stable; low-level implementation may change. */ #define __fsparam(TYPE, NAME, OPT, FLAGS, DATA) \ { \ .name = NAME, \ .opt = OPT, \ .type = TYPE, \ .flags = FLAGS, \ .data = DATA \ } #define fsparam_flag(NAME, OPT) __fsparam(NULL, NAME, OPT, 0, NULL) #define fsparam_flag_no(NAME, OPT) \ __fsparam(NULL, NAME, OPT, fs_param_neg_with_no, NULL) #define fsparam_bool(NAME, OPT) __fsparam(fs_param_is_bool, NAME, OPT, 0, NULL) #define fsparam_u32(NAME, OPT) __fsparam(fs_param_is_u32, NAME, OPT, 0, NULL) #define fsparam_u32oct(NAME, OPT) \ __fsparam(fs_param_is_u32, NAME, OPT, 0, (void *)8) #define fsparam_u32hex(NAME, OPT) \ __fsparam(fs_param_is_u32_hex, NAME, OPT, 0, (void *)16) #define fsparam_s32(NAME, OPT) __fsparam(fs_param_is_s32, NAME, OPT, 0, NULL) #define fsparam_u64(NAME, OPT) __fsparam(fs_param_is_u64, NAME, OPT, 0, NULL) #define fsparam_enum(NAME, OPT, array) __fsparam(fs_param_is_enum, NAME, OPT, 0, array) #define fsparam_string(NAME, OPT) \ __fsparam(fs_param_is_string, NAME, OPT, 0, NULL) #define fsparam_blob(NAME, OPT) __fsparam(fs_param_is_blob, NAME, OPT, 0, NULL) #define fsparam_bdev(NAME, OPT) __fsparam(fs_param_is_blockdev, NAME, OPT, 0, NULL) #define fsparam_path(NAME, OPT) __fsparam(fs_param_is_path, NAME, OPT, 0, NULL) #define fsparam_fd(NAME, OPT) __fsparam(fs_param_is_fd, NAME, OPT, 0, NULL) #endif /* _LINUX_FS_PARSER_H */
230 231 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 // SPDX-License-Identifier: GPL-2.0 #include <linux/memblock.h> #include <linux/mmdebug.h> #include <linux/export.h> #include <linux/mm.h> #include <asm/page.h> #include <linux/vmalloc.h> #include "physaddr.h" #ifdef CONFIG_X86_64 #ifdef CONFIG_DEBUG_VIRTUAL unsigned long __phys_addr(unsigned long x) { unsigned long y = x - __START_KERNEL_map; /* use the carry flag to determine if x was < __START_KERNEL_map */ if (unlikely(x > y)) { x = y + phys_base; VIRTUAL_BUG_ON(y >= KERNEL_IMAGE_SIZE); } else { x = y + (__START_KERNEL_map - PAGE_OFFSET); /* carry flag will be set if starting x was >= PAGE_OFFSET */ VIRTUAL_BUG_ON((x > y) || !phys_addr_valid(x)); } return x; } EXPORT_SYMBOL(__phys_addr); unsigned long __phys_addr_symbol(unsigned long x) { unsigned long y = x - __START_KERNEL_map; /* only check upper bounds since lower bounds will trigger carry */ VIRTUAL_BUG_ON(y >= KERNEL_IMAGE_SIZE); return y + phys_base; } EXPORT_SYMBOL(__phys_addr_symbol); #endif bool __virt_addr_valid(unsigned long x) { unsigned long y = x - __START_KERNEL_map; /* use the carry flag to determine if x was < __START_KERNEL_map */ if (unlikely(x > y)) { x = y + phys_base; if (y >= KERNEL_IMAGE_SIZE) return false; } else { x = y + (__START_KERNEL_map - PAGE_OFFSET); /* carry flag will be set if starting x was >= PAGE_OFFSET */ if ((x > y) || !phys_addr_valid(x)) return false; } return pfn_valid(x >> PAGE_SHIFT); } EXPORT_SYMBOL(__virt_addr_valid); #else #ifdef CONFIG_DEBUG_VIRTUAL unsigned long __phys_addr(unsigned long x) { unsigned long phys_addr = x - PAGE_OFFSET; /* VMALLOC_* aren't constants */ VIRTUAL_BUG_ON(x < PAGE_OFFSET); VIRTUAL_BUG_ON(__vmalloc_start_set && is_vmalloc_addr((void *) x)); /* max_low_pfn is set early, but not _that_ early */ if (max_low_pfn) { VIRTUAL_BUG_ON((phys_addr >> PAGE_SHIFT) > max_low_pfn); BUG_ON(slow_virt_to_phys((void *)x) != phys_addr); } return phys_addr; } EXPORT_SYMBOL(__phys_addr); #endif bool __virt_addr_valid(unsigned long x) { if (x < PAGE_OFFSET) return false; if (__vmalloc_start_set && is_vmalloc_addr((void *) x)) return false; if (x >= FIXADDR_START) return false; return pfn_valid((x - PAGE_OFFSET) >> PAGE_SHIFT); } EXPORT_SYMBOL(__virt_addr_valid); #endif /* CONFIG_X86_64 */
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 /* SPDX-License-Identifier: GPL-2.0 */ #ifndef __LINUX_NODEMASK_H #define __LINUX_NODEMASK_H /* * Nodemasks provide a bitmap suitable for representing the * set of Node's in a system, one bit position per Node number. * * See detailed comments in the file linux/bitmap.h describing the * data type on which these nodemasks are based. * * For details of nodemask_parse_user(), see bitmap_parse_user() in * lib/bitmap.c. For details of nodelist_parse(), see bitmap_parselist(), * also in bitmap.c. For details of node_remap(), see bitmap_bitremap in * lib/bitmap.c. For details of nodes_remap(), see bitmap_remap in * lib/bitmap.c. For details of nodes_onto(), see bitmap_onto in * lib/bitmap.c. For details of nodes_fold(), see bitmap_fold in * lib/bitmap.c. * * The available nodemask operations are: * * void node_set(node, mask) turn on bit 'node' in mask * void node_clear(node, mask) turn off bit 'node' in mask * void nodes_setall(mask) set all bits * void nodes_clear(mask) clear all bits * int node_isset(node, mask) true iff bit 'node' set in mask * int node_test_and_set(node, mask) test and set bit 'node' in mask * * void nodes_and(dst, src1, src2) dst = src1 & src2 [intersection] * void nodes_or(dst, src1, src2) dst = src1 | src2 [union] * void nodes_xor(dst, src1, src2) dst = src1 ^ src2 * void nodes_andnot(dst, src1, src2) dst = src1 & ~src2 * void nodes_complement(dst, src) dst = ~src * * int nodes_equal(mask1, mask2) Does mask1 == mask2? * int nodes_intersects(mask1, mask2) Do mask1 and mask2 intersect? * int nodes_subset(mask1, mask2) Is mask1 a subset of mask2? * int nodes_empty(mask) Is mask empty (no bits sets)? * int nodes_full(mask) Is mask full (all bits sets)? * int nodes_weight(mask) Hamming weight - number of set bits * * void nodes_shift_right(dst, src, n) Shift right * void nodes_shift_left(dst, src, n) Shift left * * int first_node(mask) Number lowest set bit, or MAX_NUMNODES * int next_node(node, mask) Next node past 'node', or MAX_NUMNODES * int next_node_in(node, mask) Next node past 'node', or wrap to first, * or MAX_NUMNODES * int first_unset_node(mask) First node not set in mask, or * MAX_NUMNODES * * nodemask_t nodemask_of_node(node) Return nodemask with bit 'node' set * NODE_MASK_ALL Initializer - all bits set * NODE_MASK_NONE Initializer - no bits set * unsigned long *nodes_addr(mask) Array of unsigned long's in mask * * int nodemask_parse_user(ubuf, ulen, mask) Parse ascii string as nodemask * int nodelist_parse(buf, map) Parse ascii string as nodelist * int node_remap(oldbit, old, new) newbit = map(old, new)(oldbit) * void nodes_remap(dst, src, old, new) *dst = map(old, new)(src) * void nodes_onto(dst, orig, relmap) *dst = orig relative to relmap * void nodes_fold(dst, orig, sz) dst bits = orig bits mod sz * * for_each_node_mask(node, mask) for-loop node over mask * * int num_online_nodes() Number of online Nodes * int num_possible_nodes() Number of all possible Nodes * * int node_random(mask) Random node with set bit in mask * * int node_online(node) Is some node online? * int node_possible(node) Is some node possible? * * node_set_online(node) set bit 'node' in node_online_map * node_set_offline(node) clear bit 'node' in node_online_map * * for_each_node(node) for-loop node over node_possible_map * for_each_online_node(node) for-loop node over node_online_map * * Subtlety: * 1) The 'type-checked' form of node_isset() causes gcc (3.3.2, anyway) * to generate slightly worse code. So use a simple one-line #define * for node_isset(), instead of wrapping an inline inside a macro, the * way we do the other calls. * * NODEMASK_SCRATCH * When doing above logical AND, OR, XOR, Remap operations the callers tend to * need temporary nodemask_t's on the stack. But if NODES_SHIFT is large, * nodemask_t's consume too much stack space. NODEMASK_SCRATCH is a helper * for such situations. See below and CPUMASK_ALLOC also. */ #include <linux/threads.h> #include <linux/bitmap.h> #include <linux/minmax.h> #include <linux/numa.h> typedef struct { DECLARE_BITMAP(bits, MAX_NUMNODES); } nodemask_t; extern nodemask_t _unused_nodemask_arg_; /** * nodemask_pr_args - printf args to output a nodemask * @maskp: nodemask to be printed * * Can be used to provide arguments for '%*pb[l]' when printing a nodemask. */ #define nodemask_pr_args(maskp) __nodemask_pr_numnodes(maskp), \ __nodemask_pr_bits(maskp) static inline unsigned int __nodemask_pr_numnodes(const nodemask_t *m) { return m ? MAX_NUMNODES : 0; } static inline const unsigned long *__nodemask_pr_bits(const nodemask_t *m) { return m ? m->bits : NULL; } /* * The inline keyword gives the compiler room to decide to inline, or * not inline a function as it sees best. However, as these functions * are called in both __init and non-__init functions, if they are not * inlined we will end up with a section mis-match error (of the type of * freeable items not being freed). So we must use __always_inline here * to fix the problem. If other functions in the future also end up in * this situation they will also need to be annotated as __always_inline */ #define node_set(node, dst) __node_set((node), &(dst)) static __always_inline void __node_set(int node, volatile nodemask_t *dstp) { set_bit(node, dstp->bits); } #define node_clear(node, dst) __node_clear((node), &(dst)) static inline void __node_clear(int node, volatile nodemask_t *dstp) { clear_bit(node, dstp->bits); } #define nodes_setall(dst) __nodes_setall(&(dst), MAX_NUMNODES) static inline void __nodes_setall(nodemask_t *dstp, unsigned int nbits) { bitmap_fill(dstp->bits, nbits); } #define nodes_clear(dst) __nodes_clear(&(dst), MAX_NUMNODES) static inline void __nodes_clear(nodemask_t *dstp, unsigned int nbits) { bitmap_zero(dstp->bits, nbits); } /* No static inline type checking - see Subtlety (1) above. */ #define node_isset(node, nodemask) test_bit((node), (nodemask).bits) #define node_test_and_set(node, nodemask) \ __node_test_and_set((node), &(nodemask)) static inline int __node_test_and_set(int node, nodemask_t *addr) { return test_and_set_bit(node, addr->bits); } #define nodes_and(dst, src1, src2) \ __nodes_and(&(dst), &(src1), &(src2), MAX_NUMNODES) static inline void __nodes_and(nodemask_t *dstp, const nodemask_t *src1p, const nodemask_t *src2p, unsigned int nbits) { bitmap_and(dstp->bits, src1p->bits, src2p->bits, nbits); } #define nodes_or(dst, src1, src2) \ __nodes_or(&(dst), &(src1), &(src2), MAX_NUMNODES) static inline void __nodes_or(nodemask_t *dstp, const nodemask_t *src1p, const nodemask_t *src2p, unsigned int nbits) { bitmap_or(dstp->bits, src1p->bits, src2p->bits, nbits); } #define nodes_xor(dst, src1, src2) \ __nodes_xor(&(dst), &(src1), &(src2), MAX_NUMNODES) static inline void __nodes_xor(nodemask_t *dstp, const nodemask_t *src1p, const nodemask_t *src2p, unsigned int nbits) { bitmap_xor(dstp->bits, src1p->bits, src2p->bits, nbits); } #define nodes_andnot(dst, src1, src2) \ __nodes_andnot(&(dst), &(src1), &(src2), MAX_NUMNODES) static inline void __nodes_andnot(nodemask_t *dstp, const nodemask_t *src1p, const nodemask_t *src2p, unsigned int nbits) { bitmap_andnot(dstp->bits, src1p->bits, src2p->bits, nbits); } #define nodes_complement(dst, src) \ __nodes_complement(&(dst), &(src), MAX_NUMNODES) static inline void __nodes_complement(nodemask_t *dstp, const nodemask_t *srcp, unsigned int nbits) { bitmap_complement(dstp->bits, srcp->bits, nbits); } #define nodes_equal(src1, src2) \ __nodes_equal(&(src1), &(src2), MAX_NUMNODES) static inline int __nodes_equal(const nodemask_t *src1p, const nodemask_t *src2p, unsigned int nbits) { return bitmap_equal(src1p->bits, src2p->bits, nbits); } #define nodes_intersects(src1, src2) \ __nodes_intersects(&(src1), &(src2), MAX_NUMNODES) static inline int __nodes_intersects(const nodemask_t *src1p, const nodemask_t *src2p, unsigned int nbits) { return bitmap_intersects(src1p->bits, src2p->bits, nbits); } #define nodes_subset(src1, src2) \ __nodes_subset(&(src1), &(src2), MAX_NUMNODES) static inline int __nodes_subset(const nodemask_t *src1p, const nodemask_t *src2p, unsigned int nbits) { return bitmap_subset(src1p->bits, src2p->bits, nbits); } #define nodes_empty(src) __nodes_empty(&(src), MAX_NUMNODES) static inline int __nodes_empty(const nodemask_t *srcp, unsigned int nbits) { return bitmap_empty(srcp->bits, nbits); } #define nodes_full(nodemask) __nodes_full(&(nodemask), MAX_NUMNODES) static inline int __nodes_full(const nodemask_t *srcp, unsigned int nbits) { return bitmap_full(srcp->bits, nbits); } #define nodes_weight(nodemask) __nodes_weight(&(nodemask), MAX_NUMNODES) static inline int __nodes_weight(const nodemask_t *srcp, unsigned int nbits) { return bitmap_weight(srcp->bits, nbits); } #define nodes_shift_right(dst, src, n) \ __nodes_shift_right(&(dst), &(src), (n), MAX_NUMNODES) static inline void __nodes_shift_right(nodemask_t *dstp, const nodemask_t *srcp, int n, int nbits) { bitmap_shift_right(dstp->bits, srcp->bits, n, nbits); } #define nodes_shift_left(dst, src, n) \ __nodes_shift_left(&(dst), &(src), (n), MAX_NUMNODES) static inline void __nodes_shift_left(nodemask_t *dstp, const nodemask_t *srcp, int n, int nbits) { bitmap_shift_left(dstp->bits, srcp->bits, n, nbits); } /* FIXME: better would be to fix all architectures to never return > MAX_NUMNODES, then the silly min_ts could be dropped. */ #define first_node(src) __first_node(&(src)) static inline int __first_node(const nodemask_t *srcp) { return min_t(int, MAX_NUMNODES, find_first_bit(srcp->bits, MAX_NUMNODES)); } #define next_node(n, src) __next_node((n), &(src)) static inline int __next_node(int n, const nodemask_t *srcp) { return min_t(int,MAX_NUMNODES,find_next_bit(srcp->bits, MAX_NUMNODES, n+1)); } /* * Find the next present node in src, starting after node n, wrapping around to * the first node in src if needed. Returns MAX_NUMNODES if src is empty. */ #define next_node_in(n, src) __next_node_in((n), &(src)) int __next_node_in(int node, const nodemask_t *srcp); static inline void init_nodemask_of_node(nodemask_t *mask, int node) { nodes_clear(*mask); node_set(node, *mask); } #define nodemask_of_node(node) \ ({ \ typeof(_unused_nodemask_arg_) m; \ if (sizeof(m) == sizeof(unsigned long)) { \ m.bits[0] = 1UL << (node); \ } else { \ init_nodemask_of_node(&m, (node)); \ } \ m; \ }) #define first_unset_node(mask) __first_unset_node(&(mask)) static inline int __first_unset_node(const nodemask_t *maskp) { return min_t(int,MAX_NUMNODES, find_first_zero_bit(maskp->bits, MAX_NUMNODES)); } #define NODE_MASK_LAST_WORD BITMAP_LAST_WORD_MASK(MAX_NUMNODES) #if MAX_NUMNODES <= BITS_PER_LONG #define NODE_MASK_ALL \ ((nodemask_t) { { \ [BITS_TO_LONGS(MAX_NUMNODES)-1] = NODE_MASK_LAST_WORD \ } }) #else #define NODE_MASK_ALL \ ((nodemask_t) { { \ [0 ... BITS_TO_LONGS(MAX_NUMNODES)-2] = ~0UL, \ [BITS_TO_LONGS(MAX_NUMNODES)-1] = NODE_MASK_LAST_WORD \ } }) #endif #define NODE_MASK_NONE \ ((nodemask_t) { { \ [0 ... BITS_TO_LONGS(MAX_NUMNODES)-1] = 0UL \ } }) #define nodes_addr(src) ((src).bits) #define nodemask_parse_user(ubuf, ulen, dst) \ __nodemask_parse_user((ubuf), (ulen), &(dst), MAX_NUMNODES) static inline int __nodemask_parse_user(const char __user *buf, int len, nodemask_t *dstp, int nbits) { return bitmap_parse_user(buf, len, dstp->bits, nbits); } #define nodelist_parse(buf, dst) __nodelist_parse((buf), &(dst), MAX_NUMNODES) static inline int __nodelist_parse(const char *buf, nodemask_t *dstp, int nbits) { return bitmap_parselist(buf, dstp->bits, nbits); } #define node_remap(oldbit, old, new) \ __node_remap((oldbit), &(old), &(new), MAX_NUMNODES) static inline int __node_remap(int oldbit, const nodemask_t *oldp, const nodemask_t *newp, int nbits) { return bitmap_bitremap(oldbit, oldp->bits, newp->bits, nbits); } #define nodes_remap(dst, src, old, new) \ __nodes_remap(&(dst), &(src), &(old), &(new), MAX_NUMNODES) static inline void __nodes_remap(nodemask_t *dstp, const nodemask_t *srcp, const nodemask_t *oldp, const nodemask_t *newp, int nbits) { bitmap_remap(dstp->bits, srcp->bits, oldp->bits, newp->bits, nbits); } #define nodes_onto(dst, orig, relmap) \ __nodes_onto(&(dst), &(orig), &(relmap), MAX_NUMNODES) static inline void __nodes_onto(nodemask_t *dstp, const nodemask_t *origp, const nodemask_t *relmapp, int nbits) { bitmap_onto(dstp->bits, origp->bits, relmapp->bits, nbits); } #define nodes_fold(dst, orig, sz) \ __nodes_fold(&(dst), &(orig), sz, MAX_NUMNODES) static inline void __nodes_fold(nodemask_t *dstp, const nodemask_t *origp, int sz, int nbits) { bitmap_fold(dstp->bits, origp->bits, sz, nbits); } #if MAX_NUMNODES > 1 #define for_each_node_mask(node, mask) \ for ((node) = first_node(mask); \ (node) < MAX_NUMNODES; \ (node) = next_node((node), (mask))) #else /* MAX_NUMNODES == 1 */ #define for_each_node_mask(node, mask) \ if (!nodes_empty(mask)) \ for ((node) = 0; (node) < 1; (node)++) #endif /* MAX_NUMNODES */ /* * Bitmasks that are kept for all the nodes. */ enum node_states { N_POSSIBLE, /* The node could become online at some point */ N_ONLINE, /* The node is online */ N_NORMAL_MEMORY, /* The node has regular memory */ #ifdef CONFIG_HIGHMEM N_HIGH_MEMORY, /* The node has regular or high memory */ #else N_HIGH_MEMORY = N_NORMAL_MEMORY, #endif N_MEMORY, /* The node has memory(regular, high, movable) */ N_CPU, /* The node has one or more cpus */ N_GENERIC_INITIATOR, /* The node has one or more Generic Initiators */ NR_NODE_STATES }; /* * The following particular system nodemasks and operations * on them manage all possible and online nodes. */ extern nodemask_t node_states[NR_NODE_STATES]; #if MAX_NUMNODES > 1 static inline int node_state(int node, enum node_states state) { return node_isset(node, node_states[state]); } static inline void node_set_state(int node, enum node_states state) { __node_set(node, &node_states[state]); } static inline void node_clear_state(int node, enum node_states state) { __node_clear(node, &node_states[state]); } static inline int num_node_state(enum node_states state) { return nodes_weight(node_states[state]); } #define for_each_node_state(__node, __state) \ for_each_node_mask((__node), node_states[__state]) #define first_online_node first_node(node_states[N_ONLINE]) #define first_memory_node first_node(node_states[N_MEMORY]) static inline int next_online_node(int nid) { return next_node(nid, node_states[N_ONLINE]); } static inline int next_memory_node(int nid) { return next_node(nid, node_states[N_MEMORY]); } extern unsigned int nr_node_ids; extern unsigned int nr_online_nodes; static inline void node_set_online(int nid) { node_set_state(nid, N_ONLINE); nr_online_nodes = num_node_state(N_ONLINE); } static inline void node_set_offline(int nid) { node_clear_state(nid, N_ONLINE); nr_online_nodes = num_node_state(N_ONLINE); } #else static inline int node_state(int node, enum node_states state) { return node == 0; } static inline void node_set_state(int node, enum node_states state) { } static inline void node_clear_state(int node, enum node_states state) { } static inline int num_node_state(enum node_states state) { return 1; } #define for_each_node_state(node, __state) \ for ( (node) = 0; (node) == 0; (node) = 1) #define first_online_node 0 #define first_memory_node 0 #define next_online_node(nid) (MAX_NUMNODES) #define nr_node_ids 1U #define nr_online_nodes 1U #define node_set_online(node) node_set_state((node), N_ONLINE) #define node_set_offline(node) node_clear_state((node), N_ONLINE) #endif #if defined(CONFIG_NUMA) && (MAX_NUMNODES > 1) extern int node_random(const nodemask_t *maskp); #else static inline int node_random(const nodemask_t *mask) { return 0; } #endif #define node_online_map node_states[N_ONLINE] #define node_possible_map node_states[N_POSSIBLE] #define num_online_nodes() num_node_state(N_ONLINE) #define num_possible_nodes() num_node_state(N_POSSIBLE) #define node_online(node) node_state((node), N_ONLINE) #define node_possible(node) node_state((node), N_POSSIBLE) #define for_each_node(node) for_each_node_state(node, N_POSSIBLE) #define for_each_online_node(node) for_each_node_state(node, N_ONLINE) /* * For nodemask scrach area. * NODEMASK_ALLOC(type, name) allocates an object with a specified type and * name. */ #if NODES_SHIFT > 8 /* nodemask_t > 32 bytes */ #define NODEMASK_ALLOC(type, name, gfp_flags) \ type *name = kmalloc(sizeof(*name), gfp_flags) #define NODEMASK_FREE(m) kfree(m) #else #define NODEMASK_ALLOC(type, name, gfp_flags) type _##name, *name = &_##name #define NODEMASK_FREE(m) do {} while (0) #endif /* A example struture for using NODEMASK_ALLOC, used in mempolicy. */ struct nodemask_scratch { nodemask_t mask1; nodemask_t mask2; }; #define NODEMASK_SCRATCH(x) \ NODEMASK_ALLOC(struct nodemask_scratch, x, \ GFP_KERNEL | __GFP_NORETRY) #define NODEMASK_SCRATCH_FREE(x) NODEMASK_FREE(x) #endif /* __LINUX_NODEMASK_H */
164 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 /* SPDX-License-Identifier: GPL-2.0 */ #undef TRACE_SYSTEM #define TRACE_SYSTEM random #if !defined(_TRACE_RANDOM_H) || defined(TRACE_HEADER_MULTI_READ) #define _TRACE_RANDOM_H #include <linux/writeback.h> #include <linux/tracepoint.h> TRACE_EVENT(add_device_randomness, TP_PROTO(int bytes, unsigned long IP), TP_ARGS(bytes, IP), TP_STRUCT__entry( __field( int, bytes ) __field(unsigned long, IP ) ), TP_fast_assign( __entry->bytes = bytes; __entry->IP = IP; ), TP_printk("bytes %d caller %pS", __entry->bytes, (void *)__entry->IP) ); DECLARE_EVENT_CLASS(random__mix_pool_bytes, TP_PROTO(const char *pool_name, int bytes, unsigned long IP), TP_ARGS(pool_name, bytes, IP), TP_STRUCT__entry( __field( const char *, pool_name ) __field( int, bytes ) __field(unsigned long, IP ) ), TP_fast_assign( __entry->pool_name = pool_name; __entry->bytes = bytes; __entry->IP = IP; ), TP_printk("%s pool: bytes %d caller %pS", __entry->pool_name, __entry->bytes, (void *)__entry->IP) ); DEFINE_EVENT(random__mix_pool_bytes, mix_pool_bytes, TP_PROTO(const char *pool_name, int bytes, unsigned long IP), TP_ARGS(pool_name, bytes, IP) ); DEFINE_EVENT(random__mix_pool_bytes, mix_pool_bytes_nolock, TP_PROTO(const char *pool_name, int bytes, unsigned long IP), TP_ARGS(pool_name, bytes, IP) ); TRACE_EVENT(credit_entropy_bits, TP_PROTO(const char *pool_name, int bits, int entropy_count, unsigned long IP), TP_ARGS(pool_name, bits, entropy_count, IP), TP_STRUCT__entry( __field( const char *, pool_name ) __field( int, bits ) __field( int, entropy_count ) __field(unsigned long, IP ) ), TP_fast_assign( __entry->pool_name = pool_name; __entry->bits = bits; __entry->entropy_count = entropy_count; __entry->IP = IP; ), TP_printk("%s pool: bits %d entropy_count %d caller %pS", __entry->pool_name, __entry->bits, __entry->entropy_count, (void *)__entry->IP) ); TRACE_EVENT(push_to_pool, TP_PROTO(const char *pool_name, int pool_bits, int input_bits), TP_ARGS(pool_name, pool_bits, input_bits), TP_STRUCT__entry( __field( const char *, pool_name ) __field( int, pool_bits ) __field( int, input_bits ) ), TP_fast_assign( __entry->pool_name = pool_name; __entry->pool_bits = pool_bits; __entry->input_bits = input_bits; ), TP_printk("%s: pool_bits %d input_pool_bits %d", __entry->pool_name, __entry->pool_bits, __entry->input_bits) ); TRACE_EVENT(debit_entropy, TP_PROTO(const char *pool_name, int debit_bits), TP_ARGS(pool_name, debit_bits), TP_STRUCT__entry( __field( const char *, pool_name ) __field( int, debit_bits ) ), TP_fast_assign( __entry->pool_name = pool_name; __entry->debit_bits = debit_bits; ), TP_printk("%s: debit_bits %d", __entry->pool_name, __entry->debit_bits) ); TRACE_EVENT(add_input_randomness, TP_PROTO(int input_bits), TP_ARGS(input_bits), TP_STRUCT__entry( __field( int, input_bits ) ), TP_fast_assign( __entry->input_bits = input_bits; ), TP_printk("input_pool_bits %d", __entry->input_bits) ); TRACE_EVENT(add_disk_randomness, TP_PROTO(dev_t dev, int input_bits), TP_ARGS(dev, input_bits), TP_STRUCT__entry( __field( dev_t, dev ) __field( int, input_bits ) ), TP_fast_assign( __entry->dev = dev; __entry->input_bits = input_bits; ), TP_printk("dev %d,%d input_pool_bits %d", MAJOR(__entry->dev), MINOR(__entry->dev), __entry->input_bits) ); TRACE_EVENT(xfer_secondary_pool, TP_PROTO(const char *pool_name, int xfer_bits, int request_bits, int pool_entropy, int input_entropy), TP_ARGS(pool_name, xfer_bits, request_bits, pool_entropy, input_entropy), TP_STRUCT__entry( __field( const char *, pool_name ) __field( int, xfer_bits ) __field( int, request_bits ) __field( int, pool_entropy ) __field( int, input_entropy ) ), TP_fast_assign( __entry->pool_name = pool_name; __entry->xfer_bits = xfer_bits; __entry->request_bits = request_bits; __entry->pool_entropy = pool_entropy; __entry->input_entropy = input_entropy; ), TP_printk("pool %s xfer_bits %d request_bits %d pool_entropy %d " "input_entropy %d", __entry->pool_name, __entry->xfer_bits, __entry->request_bits, __entry->pool_entropy, __entry->input_entropy) ); DECLARE_EVENT_CLASS(random__get_random_bytes, TP_PROTO(int nbytes, unsigned long IP), TP_ARGS(nbytes, IP), TP_STRUCT__entry( __field( int, nbytes ) __field(unsigned long, IP ) ), TP_fast_assign( __entry->nbytes = nbytes; __entry->IP = IP; ), TP_printk("nbytes %d caller %pS", __entry->nbytes, (void *)__entry->IP) ); DEFINE_EVENT(random__get_random_bytes, get_random_bytes, TP_PROTO(int nbytes, unsigned long IP), TP_ARGS(nbytes, IP) ); DEFINE_EVENT(random__get_random_bytes, get_random_bytes_arch, TP_PROTO(int nbytes, unsigned long IP), TP_ARGS(nbytes, IP) ); DECLARE_EVENT_CLASS(random__extract_entropy, TP_PROTO(const char *pool_name, int nbytes, int entropy_count, unsigned long IP), TP_ARGS(pool_name, nbytes, entropy_count, IP), TP_STRUCT__entry( __field( const char *, pool_name ) __field( int, nbytes ) __field( int, entropy_count ) __field(unsigned long, IP ) ), TP_fast_assign( __entry->pool_name = pool_name; __entry->nbytes = nbytes; __entry->entropy_count = entropy_count; __entry->IP = IP; ), TP_printk("%s pool: nbytes %d entropy_count %d caller %pS", __entry->pool_name, __entry->nbytes, __entry->entropy_count, (void *)__entry->IP) ); DEFINE_EVENT(random__extract_entropy, extract_entropy, TP_PROTO(const char *pool_name, int nbytes, int entropy_count, unsigned long IP), TP_ARGS(pool_name, nbytes, entropy_count, IP) ); DEFINE_EVENT(random__extract_entropy, extract_entropy_user, TP_PROTO(const char *pool_name, int nbytes, int entropy_count, unsigned long IP), TP_ARGS(pool_name, nbytes, entropy_count, IP) ); TRACE_EVENT(random_read, TP_PROTO(int got_bits, int need_bits, int pool_left, int input_left), TP_ARGS(got_bits, need_bits, pool_left, input_left), TP_STRUCT__entry( __field( int, got_bits ) __field( int, need_bits ) __field( int, pool_left ) __field( int, input_left ) ), TP_fast_assign( __entry->got_bits = got_bits; __entry->need_bits = need_bits; __entry->pool_left = pool_left; __entry->input_left = input_left; ), TP_printk("got_bits %d still_needed_bits %d " "blocking_pool_entropy_left %d input_entropy_left %d", __entry->got_bits, __entry->got_bits, __entry->pool_left, __entry->input_left) ); TRACE_EVENT(urandom_read, TP_PROTO(int got_bits, int pool_left, int input_left), TP_ARGS(got_bits, pool_left, input_left), TP_STRUCT__entry( __field( int, got_bits ) __field( int, pool_left ) __field( int, input_left ) ), TP_fast_assign( __entry->got_bits = got_bits; __entry->pool_left = pool_left; __entry->input_left = input_left; ), TP_printk("got_bits %d nonblocking_pool_entropy_left %d " "input_entropy_left %d", __entry->got_bits, __entry->pool_left, __entry->input_left) ); TRACE_EVENT(prandom_u32, TP_PROTO(unsigned int ret), TP_ARGS(ret), TP_STRUCT__entry( __field( unsigned int, ret) ), TP_fast_assign( __entry->ret = ret; ), TP_printk("ret=%u" , __entry->ret) ); #endif /* _TRACE_RANDOM_H */ /* This part must be outside protection */ #include <trace/define_trace.h>
19 19 19 19 19 19 9 9 9 1 9 19 19 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 // SPDX-License-Identifier: GPL-2.0 /* * Lockless hierarchical page accounting & limiting * * Copyright (C) 2014 Red Hat, Inc., Johannes Weiner */ #include <linux/page_counter.h> #include <linux/atomic.h> #include <linux/kernel.h> #include <linux/string.h> #include <linux/sched.h> #include <linux/bug.h> #include <asm/page.h> static void propagate_protected_usage(struct page_counter *c, unsigned long usage) { unsigned long protected, old_protected; unsigned long low, min; long delta; if (!c->parent) return; min = READ_ONCE(c->min); if (min || atomic_long_read(&c->min_usage)) { protected = min(usage, min); old_protected = atomic_long_xchg(&c->min_usage, protected); delta = protected - old_protected; if (delta) atomic_long_add(delta, &c->parent->children_min_usage); } low = READ_ONCE(c->low); if (low || atomic_long_read(&c->low_usage)) { protected = min(usage, low); old_protected = atomic_long_xchg(&c->low_usage, protected); delta = protected - old_protected; if (delta) atomic_long_add(delta, &c->parent->children_low_usage); } } /** * page_counter_cancel - take pages out of the local counter * @counter: counter * @nr_pages: number of pages to cancel */ void page_counter_cancel(struct page_counter *counter, unsigned long nr_pages) { long new; new = atomic_long_sub_return(nr_pages, &counter->usage); propagate_protected_usage(counter, new); /* More uncharges than charges? */ WARN_ON_ONCE(new < 0); } /** * page_counter_charge - hierarchically charge pages * @counter: counter * @nr_pages: number of pages to charge * * NOTE: This does not consider any configured counter limits. */ void page_counter_charge(struct page_counter *counter, unsigned long nr_pages) { struct page_counter *c; for (c = counter; c; c = c->parent) { long new; new = atomic_long_add_return(nr_pages, &c->usage); propagate_protected_usage(c, new); /* * This is indeed racy, but we can live with some * inaccuracy in the watermark. */ if (new > READ_ONCE(c->watermark)) WRITE_ONCE(c->watermark, new); } } /** * page_counter_try_charge - try to hierarchically charge pages * @counter: counter * @nr_pages: number of pages to charge * @fail: points first counter to hit its limit, if any * * Returns %true on success, or %false and @fail if the counter or one * of its ancestors has hit its configured limit. */ bool page_counter_try_charge(struct page_counter *counter, unsigned long nr_pages, struct page_counter **fail) { struct page_counter *c; for (c = counter; c; c = c->parent) { long new; /* * Charge speculatively to avoid an expensive CAS. If * a bigger charge fails, it might falsely lock out a * racing smaller charge and send it into reclaim * early, but the error is limited to the difference * between the two sizes, which is less than 2M/4M in * case of a THP locking out a regular page charge. * * The atomic_long_add_return() implies a full memory * barrier between incrementing the count and reading * the limit. When racing with page_counter_set_max(), * we either see the new limit or the setter sees the * counter has changed and retries. */ new = atomic_long_add_return(nr_pages, &c->usage); if (new > c->max) { atomic_long_sub(nr_pages, &c->usage); propagate_protected_usage(c, new); /* * This is racy, but we can live with some * inaccuracy in the failcnt which is only used * to report stats. */ data_race(c->failcnt++); *fail = c; goto failed; } propagate_protected_usage(c, new); /* * Just like with failcnt, we can live with some * inaccuracy in the watermark. */ if (new > READ_ONCE(c->watermark)) WRITE_ONCE(c->watermark, new); } return true; failed: for (c = counter; c != *fail; c = c->parent) page_counter_cancel(c, nr_pages); return false; } /** * page_counter_uncharge - hierarchically uncharge pages * @counter: counter * @nr_pages: number of pages to uncharge */ void page_counter_uncharge(struct page_counter *counter, unsigned long nr_pages) { struct page_counter *c; for (c = counter; c; c = c->parent) page_counter_cancel(c, nr_pages); } /** * page_counter_set_max - set the maximum number of pages allowed * @counter: counter * @nr_pages: limit to set * * Returns 0 on success, -EBUSY if the current number of pages on the * counter already exceeds the specified limit. * * The caller must serialize invocations on the same counter. */ int page_counter_set_max(struct page_counter *counter, unsigned long nr_pages) { for (;;) { unsigned long old; long usage; /* * Update the limit while making sure that it's not * below the concurrently-changing counter value. * * The xchg implies two full memory barriers before * and after, so the read-swap-read is ordered and * ensures coherency with page_counter_try_charge(): * that function modifies the count before checking * the limit, so if it sees the old limit, we see the * modified counter and retry. */ usage = atomic_long_read(&counter->usage); if (usage > nr_pages) return -EBUSY; old = xchg(&counter->max, nr_pages); if (atomic_long_read(&counter->usage) <= usage) return 0; counter->max = old; cond_resched(); } } /** * page_counter_set_min - set the amount of protected memory * @counter: counter * @nr_pages: value to set * * The caller must serialize invocations on the same counter. */ void page_counter_set_min(struct page_counter *counter, unsigned long nr_pages) { struct page_counter *c; WRITE_ONCE(counter->min, nr_pages); for (c = counter; c; c = c->parent) propagate_protected_usage(c, atomic_long_read(&c->usage)); } /** * page_counter_set_low - set the amount of protected memory * @counter: counter * @nr_pages: value to set * * The caller must serialize invocations on the same counter. */ void page_counter_set_low(struct page_counter *counter, unsigned long nr_pages) { struct page_counter *c; WRITE_ONCE(counter->low, nr_pages); for (c = counter; c; c = c->parent) propagate_protected_usage(c, atomic_long_read(&c->usage)); } /** * page_counter_memparse - memparse() for page counter limits * @buf: string to parse * @max: string meaning maximum possible value * @nr_pages: returns the result in number of pages * * Returns -EINVAL, or 0 and @nr_pages on success. @nr_pages will be * limited to %PAGE_COUNTER_MAX. */ int page_counter_memparse(const char *buf, const char *max, unsigned long *nr_pages) { char *end; u64 bytes; if (!strcmp(buf, max)) { *nr_pages = PAGE_COUNTER_MAX; return 0; } bytes = memparse(buf, &end); if (*end != '\0') return -EINVAL; *nr_pages = min(bytes / PAGE_SIZE, (u64)PAGE_COUNTER_MAX); return 0; }
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 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 /* SPDX-License-Identifier: GPL-2.0-or-later */ /* * Copyright (C) 2001 Momchil Velikov * Portions Copyright (C) 2001 Christoph Hellwig * Copyright (C) 2006 Nick Piggin * Copyright (C) 2012 Konstantin Khlebnikov */ #ifndef _LINUX_RADIX_TREE_H #define _LINUX_RADIX_TREE_H #include <linux/bitops.h> #include <linux/kernel.h> #include <linux/list.h> #include <linux/percpu.h> #include <linux/preempt.h> #include <linux/rcupdate.h> #include <linux/spinlock.h> #include <linux/types.h> #include <linux/xarray.h> #include <linux/local_lock.h> /* Keep unconverted code working */ #define radix_tree_root xarray #define radix_tree_node xa_node struct radix_tree_preload { local_lock_t lock; unsigned nr; /* nodes->parent points to next preallocated node */ struct radix_tree_node *nodes; }; DECLARE_PER_CPU(struct radix_tree_preload, radix_tree_preloads); /* * The bottom two bits of the slot determine how the remaining bits in the * slot are interpreted: * * 00 - data pointer * 10 - internal entry * x1 - value entry * * The internal entry may be a pointer to the next level in the tree, a * sibling entry, or an indicator that the entry in this slot has been moved * to another location in the tree and the lookup should be restarted. While * NULL fits the 'data pointer' pattern, it means that there is no entry in * the tree for this index (no matter what level of the tree it is found at). * This means that storing a NULL entry in the tree is the same as deleting * the entry from the tree. */ #define RADIX_TREE_ENTRY_MASK 3UL #define RADIX_TREE_INTERNAL_NODE 2UL static inline bool radix_tree_is_internal_node(void *ptr) { return ((unsigned long)ptr & RADIX_TREE_ENTRY_MASK) == RADIX_TREE_INTERNAL_NODE; } /*** radix-tree API starts here ***/ #define RADIX_TREE_MAP_SHIFT XA_CHUNK_SHIFT #define RADIX_TREE_MAP_SIZE (1UL << RADIX_TREE_MAP_SHIFT) #define RADIX_TREE_MAP_MASK (RADIX_TREE_MAP_SIZE-1) #define RADIX_TREE_MAX_TAGS XA_MAX_MARKS #define RADIX_TREE_TAG_LONGS XA_MARK_LONGS #define RADIX_TREE_INDEX_BITS (8 /* CHAR_BIT */ * sizeof(unsigned long)) #define RADIX_TREE_MAX_PATH (DIV_ROUND_UP(RADIX_TREE_INDEX_BITS, \ RADIX_TREE_MAP_SHIFT)) /* The IDR tag is stored in the low bits of xa_flags */ #define ROOT_IS_IDR ((__force gfp_t)4) /* The top bits of xa_flags are used to store the root tags */ #define ROOT_TAG_SHIFT (__GFP_BITS_SHIFT) #define RADIX_TREE_INIT(name, mask) XARRAY_INIT(name, mask) #define RADIX_TREE(name, mask) \ struct radix_tree_root name = RADIX_TREE_INIT(name, mask) #define INIT_RADIX_TREE(root, mask) xa_init_flags(root, mask) static inline bool radix_tree_empty(const struct radix_tree_root *root) { return root->xa_head == NULL; } /** * struct radix_tree_iter - radix tree iterator state * * @index: index of current slot * @next_index: one beyond the last index for this chunk * @tags: bit-mask for tag-iterating * @node: node that contains current slot * * This radix tree iterator works in terms of "chunks" of slots. A chunk is a * subinterval of slots contained within one radix tree leaf node. It is * described by a pointer to its first slot and a struct radix_tree_iter * which holds the chunk's position in the tree and its size. For tagged * iteration radix_tree_iter also holds the slots' bit-mask for one chosen * radix tree tag. */ struct radix_tree_iter { unsigned long index; unsigned long next_index; unsigned long tags; struct radix_tree_node *node; }; /** * Radix-tree synchronization * * The radix-tree API requires that users provide all synchronisation (with * specific exceptions, noted below). * * Synchronization of access to the data items being stored in the tree, and * management of their lifetimes must be completely managed by API users. * * For API usage, in general, * - any function _modifying_ the tree or tags (inserting or deleting * items, setting or clearing tags) must exclude other modifications, and * exclude any functions reading the tree. * - any function _reading_ the tree or tags (looking up items or tags, * gang lookups) must exclude modifications to the tree, but may occur * concurrently with other readers. * * The notable exceptions to this rule are the following functions: * __radix_tree_lookup * radix_tree_lookup * radix_tree_lookup_slot * radix_tree_tag_get * radix_tree_gang_lookup * radix_tree_gang_lookup_tag * radix_tree_gang_lookup_tag_slot * radix_tree_tagged * * The first 7 functions are able to be called locklessly, using RCU. The * caller must ensure calls to these functions are made within rcu_read_lock() * regions. Other readers (lock-free or otherwise) and modifications may be * running concurrently. * * It is still required that the caller manage the synchronization and lifetimes * of the items. So if RCU lock-free lookups are used, typically this would mean * that the items have their own locks, or are amenable to lock-free access; and * that the items are freed by RCU (or only freed after having been deleted from * the radix tree *and* a synchronize_rcu() grace period). * * (Note, rcu_assign_pointer and rcu_dereference are not needed to control * access to data items when inserting into or looking up from the radix tree) * * Note that the value returned by radix_tree_tag_get() may not be relied upon * if only the RCU read lock is held. Functions to set/clear tags and to * delete nodes running concurrently with it may affect its result such that * two consecutive reads in the same locked section may return different * values. If reliability is required, modification functions must also be * excluded from concurrency. * * radix_tree_tagged is able to be called without locking or RCU. */ /** * radix_tree_deref_slot - dereference a slot * @slot: slot pointer, returned by radix_tree_lookup_slot * * For use with radix_tree_lookup_slot(). Caller must hold tree at least read * locked across slot lookup and dereference. Not required if write lock is * held (ie. items cannot be concurrently inserted). * * radix_tree_deref_retry must be used to confirm validity of the pointer if * only the read lock is held. * * Return: entry stored in that slot. */ static inline void *radix_tree_deref_slot(void __rcu **slot) { return rcu_dereference(*slot); } /** * radix_tree_deref_slot_protected - dereference a slot with tree lock held * @slot: slot pointer, returned by radix_tree_lookup_slot * * Similar to radix_tree_deref_slot. The caller does not hold the RCU read * lock but it must hold the tree lock to prevent parallel updates. * * Return: entry stored in that slot. */ static inline void *radix_tree_deref_slot_protected(void __rcu **slot, spinlock_t *treelock) { return rcu_dereference_protected(*slot, lockdep_is_held(treelock)); } /** * radix_tree_deref_retry - check radix_tree_deref_slot * @arg: pointer returned by radix_tree_deref_slot * Returns: 0 if retry is not required, otherwise retry is required * * radix_tree_deref_retry must be used with radix_tree_deref_slot. */ static inline int radix_tree_deref_retry(void *arg) { return unlikely(radix_tree_is_internal_node(arg)); } /** * radix_tree_exception - radix_tree_deref_slot returned either exception? * @arg: value returned by radix_tree_deref_slot * Returns: 0 if well-aligned pointer, non-0 if either kind of exception. */ static inline int radix_tree_exception(void *arg) { return unlikely((unsigned long)arg & RADIX_TREE_ENTRY_MASK); } int radix_tree_insert(struct radix_tree_root *, unsigned long index, void *); void *__radix_tree_lookup(const struct radix_tree_root *, unsigned long index, struct radix_tree_node **nodep, void __rcu ***slotp); void *radix_tree_lookup(const struct radix_tree_root *, unsigned long); void __rcu **radix_tree_lookup_slot(const struct radix_tree_root *, unsigned long index); void __radix_tree_replace(struct radix_tree_root *, struct radix_tree_node *, void __rcu **slot, void *entry); void radix_tree_iter_replace(struct radix_tree_root *, const struct radix_tree_iter *, void __rcu **slot, void *entry); void radix_tree_replace_slot(struct radix_tree_root *, void __rcu **slot, void *entry); void radix_tree_iter_delete(struct radix_tree_root *, struct radix_tree_iter *iter, void __rcu **slot); void *radix_tree_delete_item(struct radix_tree_root *, unsigned long, void *); void *radix_tree_delete(struct radix_tree_root *, unsigned long); unsigned int radix_tree_gang_lookup(const struct radix_tree_root *, void **results, unsigned long first_index, unsigned int max_items); int radix_tree_preload(gfp_t gfp_mask); int radix_tree_maybe_preload(gfp_t gfp_mask); void radix_tree_init(void); void *radix_tree_tag_set(struct radix_tree_root *, unsigned long index, unsigned int tag); void *radix_tree_tag_clear(struct radix_tree_root *, unsigned long index, unsigned int tag); int radix_tree_tag_get(const struct radix_tree_root *, unsigned long index, unsigned int tag); void radix_tree_iter_tag_clear(struct radix_tree_root *, const struct radix_tree_iter *iter, unsigned int tag); unsigned int radix_tree_gang_lookup_tag(const struct radix_tree_root *, void **results, unsigned long first_index, unsigned int max_items, unsigned int tag); unsigned int radix_tree_gang_lookup_tag_slot(const struct radix_tree_root *, void __rcu ***results, unsigned long first_index, unsigned int max_items, unsigned int tag); int radix_tree_tagged(const struct radix_tree_root *, unsigned int tag); static inline void radix_tree_preload_end(void) { local_unlock(&radix_tree_preloads.lock); } void __rcu **idr_get_free(struct radix_tree_root *root, struct radix_tree_iter *iter, gfp_t gfp, unsigned long max); enum { RADIX_TREE_ITER_TAG_MASK = 0x0f, /* tag index in lower nybble */ RADIX_TREE_ITER_TAGGED = 0x10, /* lookup tagged slots */ RADIX_TREE_ITER_CONTIG = 0x20, /* stop at first hole */ }; /** * radix_tree_iter_init - initialize radix tree iterator * * @iter: pointer to iterator state * @start: iteration starting index * Returns: NULL */ static __always_inline void __rcu ** radix_tree_iter_init(struct radix_tree_iter *iter, unsigned long start) { /* * Leave iter->tags uninitialized. radix_tree_next_chunk() will fill it * in the case of a successful tagged chunk lookup. If the lookup was * unsuccessful or non-tagged then nobody cares about ->tags. * * Set index to zero to bypass next_index overflow protection. * See the comment in radix_tree_next_chunk() for details. */ iter->index = 0; iter->next_index = start; return NULL; } /** * radix_tree_next_chunk - find next chunk of slots for iteration * * @root: radix tree root * @iter: iterator state * @flags: RADIX_TREE_ITER_* flags and tag index * Returns: pointer to chunk first slot, or NULL if there no more left * * This function looks up the next chunk in the radix tree starting from * @iter->next_index. It returns a pointer to the chunk's first slot. * Also it fills @iter with data about chunk: position in the tree (index), * its end (next_index), and constructs a bit mask for tagged iterating (tags). */ void __rcu **radix_tree_next_chunk(const struct radix_tree_root *, struct radix_tree_iter *iter, unsigned flags); /** * radix_tree_iter_lookup - look up an index in the radix tree * @root: radix tree root * @iter: iterator state * @index: key to look up * * If @index is present in the radix tree, this function returns the slot * containing it and updates @iter to describe the entry. If @index is not * present, it returns NULL. */ static inline void __rcu ** radix_tree_iter_lookup(const struct radix_tree_root *root, struct radix_tree_iter *iter, unsigned long index) { radix_tree_iter_init(iter, index); return radix_tree_next_chunk(root, iter, RADIX_TREE_ITER_CONTIG); } /** * radix_tree_iter_retry - retry this chunk of the iteration * @iter: iterator state * * If we iterate over a tree protected only by the RCU lock, a race * against deletion or creation may result in seeing a slot for which * radix_tree_deref_retry() returns true. If so, call this function * and continue the iteration. */ static inline __must_check void __rcu **radix_tree_iter_retry(struct radix_tree_iter *iter) { iter->next_index = iter->index; iter->tags = 0; return NULL; } static inline unsigned long __radix_tree_iter_add(struct radix_tree_iter *iter, unsigned long slots) { return iter->index + slots; } /** * radix_tree_iter_resume - resume iterating when the chunk may be invalid * @slot: pointer to current slot * @iter: iterator state * Returns: New slot pointer * * If the iterator needs to release then reacquire a lock, the chunk may * have been invalidated by an insertion or deletion. Call this function * before releasing the lock to continue the iteration from the next index. */ void __rcu **__must_check radix_tree_iter_resume(void __rcu **slot, struct radix_tree_iter *iter); /** * radix_tree_chunk_size - get current chunk size * * @iter: pointer to radix tree iterator * Returns: current chunk size */ static __always_inline long radix_tree_chunk_size(struct radix_tree_iter *iter) { return iter->next_index - iter->index; } /** * radix_tree_next_slot - find next slot in chunk * * @slot: pointer to current slot * @iter: pointer to iterator state * @flags: RADIX_TREE_ITER_*, should be constant * Returns: pointer to next slot, or NULL if there no more left * * This function updates @iter->index in the case of a successful lookup. * For tagged lookup it also eats @iter->tags. * * There are several cases where 'slot' can be passed in as NULL to this * function. These cases result from the use of radix_tree_iter_resume() or * radix_tree_iter_retry(). In these cases we don't end up dereferencing * 'slot' because either: * a) we are doing tagged iteration and iter->tags has been set to 0, or * b) we are doing non-tagged iteration, and iter->index and iter->next_index * have been set up so that radix_tree_chunk_size() returns 1 or 0. */ static __always_inline void __rcu **radix_tree_next_slot(void __rcu **slot, struct radix_tree_iter *iter, unsigned flags) { if (flags & RADIX_TREE_ITER_TAGGED) { iter->tags >>= 1; if (unlikely(!iter->tags)) return NULL; if (likely(iter->tags & 1ul)) { iter->index = __radix_tree_iter_add(iter, 1); slot++; goto found; } if (!(flags & RADIX_TREE_ITER_CONTIG)) { unsigned offset = __ffs(iter->tags); iter->tags >>= offset++; iter->index = __radix_tree_iter_add(iter, offset); slot += offset; goto found; } } else { long count = radix_tree_chunk_size(iter); while (--count > 0) { slot++; iter->index = __radix_tree_iter_add(iter, 1); if (likely(*slot)) goto found; if (flags & RADIX_TREE_ITER_CONTIG) { /* forbid switching to the next chunk */ iter->next_index = 0; break; } } } return NULL; found: return slot; } /** * radix_tree_for_each_slot - iterate over non-empty slots * * @slot: the void** variable for pointer to slot * @root: the struct radix_tree_root pointer * @iter: the struct radix_tree_iter pointer * @start: iteration starting index * * @slot points to radix tree slot, @iter->index contains its index. */ #define radix_tree_for_each_slot(slot, root, iter, start) \ for (slot = radix_tree_iter_init(iter, start) ; \ slot || (slot = radix_tree_next_chunk(root, iter, 0)) ; \ slot = radix_tree_next_slot(slot, iter, 0)) /** * radix_tree_for_each_tagged - iterate over tagged slots * * @slot: the void** variable for pointer to slot * @root: the struct radix_tree_root pointer * @iter: the struct radix_tree_iter pointer * @start: iteration starting index * @tag: tag index * * @slot points to radix tree slot, @iter->index contains its index. */ #define radix_tree_for_each_tagged(slot, root, iter, start, tag) \ for (slot = radix_tree_iter_init(iter, start) ; \ slot || (slot = radix_tree_next_chunk(root, iter, \ RADIX_TREE_ITER_TAGGED | tag)) ; \ slot = radix_tree_next_slot(slot, iter, \ RADIX_TREE_ITER_TAGGED | tag)) #endif /* _LINUX_RADIX_TREE_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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _linux_POSIX_TIMERS_H #define _linux_POSIX_TIMERS_H #include <linux/spinlock.h> #include <linux/list.h> #include <linux/alarmtimer.h> #include <linux/timerqueue.h> #include <linux/task_work.h> struct kernel_siginfo; struct task_struct; /* * Bit fields within a clockid: * * The most significant 29 bits hold either a pid or a file descriptor. * * Bit 2 indicates whether a cpu clock refers to a thread or a process. * * Bits 1 and 0 give the type: PROF=0, VIRT=1, SCHED=2, or FD=3. * * A clockid is invalid if bits 2, 1, and 0 are all set. */ #define CPUCLOCK_PID(clock) ((pid_t) ~((clock) >> 3)) #define CPUCLOCK_PERTHREAD(clock) \ (((clock) & (clockid_t) CPUCLOCK_PERTHREAD_MASK) != 0) #define CPUCLOCK_PERTHREAD_MASK 4 #define CPUCLOCK_WHICH(clock) ((clock) & (clockid_t) CPUCLOCK_CLOCK_MASK) #define CPUCLOCK_CLOCK_MASK 3 #define CPUCLOCK_PROF 0 #define CPUCLOCK_VIRT 1 #define CPUCLOCK_SCHED 2 #define CPUCLOCK_MAX 3 #define CLOCKFD CPUCLOCK_MAX #define CLOCKFD_MASK (CPUCLOCK_PERTHREAD_MASK|CPUCLOCK_CLOCK_MASK) static inline clockid_t make_process_cpuclock(const unsigned int pid, const clockid_t clock) { return ((~pid) << 3) | clock; } static inline clockid_t make_thread_cpuclock(const unsigned int tid, const clockid_t clock) { return make_process_cpuclock(tid, clock | CPUCLOCK_PERTHREAD_MASK); } static inline clockid_t fd_to_clockid(const int fd) { return make_process_cpuclock((unsigned int) fd, CLOCKFD); } static inline int clockid_to_fd(const clockid_t clk) { return ~(clk >> 3); } #ifdef CONFIG_POSIX_TIMERS /** * cpu_timer - Posix CPU timer representation for k_itimer * @node: timerqueue node to queue in the task/sig * @head: timerqueue head on which this timer is queued * @task: Pointer to target task * @elist: List head for the expiry list * @firing: Timer is currently firing */ struct cpu_timer { struct timerqueue_node node; struct timerqueue_head *head; struct pid *pid; struct list_head elist; int firing; }; static inline bool cpu_timer_enqueue(struct timerqueue_head *head, struct cpu_timer *ctmr) { ctmr->head = head; return timerqueue_add(head, &ctmr->node); } static inline void cpu_timer_dequeue(struct cpu_timer *ctmr) { if (ctmr->head) { timerqueue_del(ctmr->head, &ctmr->node); ctmr->head = NULL; } } static inline u64 cpu_timer_getexpires(struct cpu_timer *ctmr) { return ctmr->node.expires; } static inline void cpu_timer_setexpires(struct cpu_timer *ctmr, u64 exp) { ctmr->node.expires = exp; } /** * posix_cputimer_base - Container per posix CPU clock * @nextevt: Earliest-expiration cache * @tqhead: timerqueue head for cpu_timers */ struct posix_cputimer_base { u64 nextevt; struct timerqueue_head tqhead; }; /** * posix_cputimers - Container for posix CPU timer related data * @bases: Base container for posix CPU clocks * @timers_active: Timers are queued. * @expiry_active: Timer expiry is active. Used for * process wide timers to avoid multiple * task trying to handle expiry concurrently * * Used in task_struct and signal_struct */ struct posix_cputimers { struct posix_cputimer_base bases[CPUCLOCK_MAX]; unsigned int timers_active; unsigned int expiry_active; }; /** * posix_cputimers_work - Container for task work based posix CPU timer expiry * @work: The task work to be scheduled * @scheduled: @work has been scheduled already, no further processing */ struct posix_cputimers_work { struct callback_head work; unsigned int scheduled; }; static inline void posix_cputimers_init(struct posix_cputimers *pct) { memset(pct, 0, sizeof(*pct)); pct->bases[0].nextevt = U64_MAX; pct->bases[1].nextevt = U64_MAX; pct->bases[2].nextevt = U64_MAX; } void posix_cputimers_group_init(struct posix_cputimers *pct, u64 cpu_limit); static inline void posix_cputimers_rt_watchdog(struct posix_cputimers *pct, u64 runtime) { pct->bases[CPUCLOCK_SCHED].nextevt = runtime; } /* Init task static initializer */ #define INIT_CPU_TIMERBASE(b) { \ .nextevt = U64_MAX, \ } #define INIT_CPU_TIMERBASES(b) { \ INIT_CPU_TIMERBASE(b[0]), \ INIT_CPU_TIMERBASE(b[1]), \ INIT_CPU_TIMERBASE(b[2]), \ } #define INIT_CPU_TIMERS(s) \ .posix_cputimers = { \ .bases = INIT_CPU_TIMERBASES(s.posix_cputimers.bases), \ }, #else struct posix_cputimers { }; struct cpu_timer { }; #define INIT_CPU_TIMERS(s) static inline void posix_cputimers_init(struct posix_cputimers *pct) { } static inline void posix_cputimers_group_init(struct posix_cputimers *pct, u64 cpu_limit) { } #endif #ifdef CONFIG_POSIX_CPU_TIMERS_TASK_WORK void posix_cputimers_init_work(void); #else static inline void posix_cputimers_init_work(void) { } #endif #define REQUEUE_PENDING 1 /** * struct k_itimer - POSIX.1b interval timer structure. * @list: List head for binding the timer to signals->posix_timers * @t_hash: Entry in the posix timer hash table * @it_lock: Lock protecting the timer * @kclock: Pointer to the k_clock struct handling this timer * @it_clock: The posix timer clock id * @it_id: The posix timer id for identifying the timer * @it_active: Marker that timer is active * @it_overrun: The overrun counter for pending signals * @it_overrun_last: The overrun at the time of the last delivered signal * @it_requeue_pending: Indicator that timer waits for being requeued on * signal delivery * @it_sigev_notify: The notify word of sigevent struct for signal delivery * @it_interval: The interval for periodic timers * @it_signal: Pointer to the creators signal struct * @it_pid: The pid of the process/task targeted by the signal * @it_process: The task to wakeup on clock_nanosleep (CPU timers) * @sigq: Pointer to preallocated sigqueue * @it: Union representing the various posix timer type * internals. * @rcu: RCU head for freeing the timer. */ struct k_itimer { struct list_head list; struct hlist_node t_hash; spinlock_t it_lock; const struct k_clock *kclock; clockid_t it_clock; timer_t it_id; int it_active; s64 it_overrun; s64 it_overrun_last; int it_requeue_pending; int it_sigev_notify; ktime_t it_interval; struct signal_struct *it_signal; union { struct pid *it_pid; struct task_struct *it_process; }; struct sigqueue *sigq; union { struct { struct hrtimer timer; } real; struct cpu_timer cpu; struct { struct alarm alarmtimer; } alarm; } it; struct rcu_head rcu; }; void run_posix_cpu_timers(void); void posix_cpu_timers_exit(struct task_struct *task); void posix_cpu_timers_exit_group(struct task_struct *task); void set_process_cpu_timer(struct task_struct *task, unsigned int clock_idx, u64 *newval, u64 *oldval); void update_rlimit_cpu(struct task_struct *task, unsigned long rlim_new); void posixtimer_rearm(struct kernel_siginfo *info); #endif
1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 2 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 // SPDX-License-Identifier: GPL-2.0+ /* * linux/fs/jbd2/journal.c * * Written by Stephen C. Tweedie <sct@redhat.com>, 1998 * * Copyright 1998 Red Hat corp --- All Rights Reserved * * Generic filesystem journal-writing code; part of the ext2fs * journaling system. * * This file manages journals: areas of disk reserved for logging * transactional updates. This includes the kernel journaling thread * which is responsible for scheduling updates to the log. * * We do not actually manage the physical storage of the journal in this * file: that is left to a per-journal policy function, which allows us * to store the journal within a filesystem-specified area for ext2 * journaling (ext2 can use a reserved inode for storing the log). */ #include <linux/module.h> #include <linux/time.h> #include <linux/fs.h> #include <linux/jbd2.h> #include <linux/errno.h> #include <linux/slab.h> #include <linux/init.h> #include <linux/mm.h> #include <linux/freezer.h> #include <linux/pagemap.h> #include <linux/kthread.h> #include <linux/poison.h> #include <linux/proc_fs.h> #include <linux/seq_file.h> #include <linux/math64.h> #include <linux/hash.h> #include <linux/log2.h> #include <linux/vmalloc.h> #include <linux/backing-dev.h> #include <linux/bitops.h> #include <linux/ratelimit.h> #include <linux/sched/mm.h> #define CREATE_TRACE_POINTS #include <trace/events/jbd2.h> #include <linux/uaccess.h> #include <asm/page.h> #ifdef CONFIG_JBD2_DEBUG ushort jbd2_journal_enable_debug __read_mostly; EXPORT_SYMBOL(jbd2_journal_enable_debug); module_param_named(jbd2_debug, jbd2_journal_enable_debug, ushort, 0644); MODULE_PARM_DESC(jbd2_debug, "Debugging level for jbd2"); #endif EXPORT_SYMBOL(jbd2_journal_extend); EXPORT_SYMBOL(jbd2_journal_stop); EXPORT_SYMBOL(jbd2_journal_lock_updates); EXPORT_SYMBOL(jbd2_journal_unlock_updates); EXPORT_SYMBOL(jbd2_journal_get_write_access); EXPORT_SYMBOL(jbd2_journal_get_create_access); EXPORT_SYMBOL(jbd2_journal_get_undo_access); EXPORT_SYMBOL(jbd2_journal_set_triggers); EXPORT_SYMBOL(jbd2_journal_dirty_metadata); EXPORT_SYMBOL(jbd2_journal_forget); EXPORT_SYMBOL(jbd2_journal_flush); EXPORT_SYMBOL(jbd2_journal_revoke); EXPORT_SYMBOL(jbd2_journal_init_dev); EXPORT_SYMBOL(jbd2_journal_init_inode); EXPORT_SYMBOL(jbd2_journal_check_used_features); EXPORT_SYMBOL(jbd2_journal_check_available_features); EXPORT_SYMBOL(jbd2_journal_set_features); EXPORT_SYMBOL(jbd2_journal_load); EXPORT_SYMBOL(jbd2_journal_destroy); EXPORT_SYMBOL(jbd2_journal_abort); EXPORT_SYMBOL(jbd2_journal_errno); EXPORT_SYMBOL(jbd2_journal_ack_err); EXPORT_SYMBOL(jbd2_journal_clear_err); EXPORT_SYMBOL(jbd2_log_wait_commit); EXPORT_SYMBOL(jbd2_log_start_commit); EXPORT_SYMBOL(jbd2_journal_start_commit); EXPORT_SYMBOL(jbd2_journal_force_commit_nested); EXPORT_SYMBOL(jbd2_journal_wipe); EXPORT_SYMBOL(jbd2_journal_blocks_per_page); EXPORT_SYMBOL(jbd2_journal_invalidatepage); EXPORT_SYMBOL(jbd2_journal_try_to_free_buffers); EXPORT_SYMBOL(jbd2_journal_force_commit); EXPORT_SYMBOL(jbd2_journal_inode_ranged_write); EXPORT_SYMBOL(jbd2_journal_inode_ranged_wait); EXPORT_SYMBOL(jbd2_journal_submit_inode_data_buffers); EXPORT_SYMBOL(jbd2_journal_finish_inode_data_buffers); EXPORT_SYMBOL(jbd2_journal_init_jbd_inode); EXPORT_SYMBOL(jbd2_journal_release_jbd_inode); EXPORT_SYMBOL(jbd2_journal_begin_ordered_truncate); EXPORT_SYMBOL(jbd2_inode_cache); static int jbd2_journal_create_slab(size_t slab_size); #ifdef CONFIG_JBD2_DEBUG void __jbd2_debug(int level, const char *file, const char *func, unsigned int line, const char *fmt, ...) { struct va_format vaf; va_list args; if (level > jbd2_journal_enable_debug) return; va_start(args, fmt); vaf.fmt = fmt; vaf.va = &args; printk(KERN_DEBUG "%s: (%s, %u): %pV", file, func, line, &vaf); va_end(args); } EXPORT_SYMBOL(__jbd2_debug); #endif /* Checksumming functions */ static int jbd2_verify_csum_type(journal_t *j, journal_superblock_t *sb) { if (!jbd2_journal_has_csum_v2or3_feature(j)) return 1; return sb->s_checksum_type == JBD2_CRC32C_CHKSUM; } static __be32 jbd2_superblock_csum(journal_t *j, journal_superblock_t *sb) { __u32 csum; __be32 old_csum; old_csum = sb->s_checksum; sb->s_checksum = 0; csum = jbd2_chksum(j, ~0, (char *)sb, sizeof(journal_superblock_t)); sb->s_checksum = old_csum; return cpu_to_be32(csum); } /* * Helper function used to manage commit timeouts */ static void commit_timeout(struct timer_list *t) { journal_t *journal = from_timer(journal, t, j_commit_timer); wake_up_process(journal->j_task); } /* * kjournald2: The main thread function used to manage a logging device * journal. * * This kernel thread is responsible for two things: * * 1) COMMIT: Every so often we need to commit the current state of the * filesystem to disk. The journal thread is responsible for writing * all of the metadata buffers to disk. If a fast commit is ongoing * journal thread waits until it's done and then continues from * there on. * * 2) CHECKPOINT: We cannot reuse a used section of the log file until all * of the data in that part of the log has been rewritten elsewhere on * the disk. Flushing these old buffers to reclaim space in the log is * known as checkpointing, and this thread is responsible for that job. */ static int kjournald2(void *arg) { journal_t *journal = arg; transaction_t *transaction; /* * Set up an interval timer which can be used to trigger a commit wakeup * after the commit interval expires */ timer_setup(&journal->j_commit_timer, commit_timeout, 0); set_freezable(); /* Record that the journal thread is running */ journal->j_task = current; wake_up(&journal->j_wait_done_commit); /* * Make sure that no allocations from this kernel thread will ever * recurse to the fs layer because we are responsible for the * transaction commit and any fs involvement might get stuck waiting for * the trasn. commit. */ memalloc_nofs_save(); /* * And now, wait forever for commit wakeup events. */ write_lock(&journal->j_state_lock); loop: if (journal->j_flags & JBD2_UNMOUNT) goto end_loop; jbd_debug(1, "commit_sequence=%u, commit_request=%u\n", journal->j_commit_sequence, journal->j_commit_request); if (journal->j_commit_sequence != journal->j_commit_request) { jbd_debug(1, "OK, requests differ\n"); write_unlock(&journal->j_state_lock); del_timer_sync(&journal->j_commit_timer); jbd2_journal_commit_transaction(journal); write_lock(&journal->j_state_lock); goto loop; } wake_up(&journal->j_wait_done_commit); if (freezing(current)) { /* * The simpler the better. Flushing journal isn't a * good idea, because that depends on threads that may * be already stopped. */ jbd_debug(1, "Now suspending kjournald2\n"); write_unlock(&journal->j_state_lock); try_to_freeze(); write_lock(&journal->j_state_lock); } else { /* * We assume on resume that commits are already there, * so we don't sleep */ DEFINE_WAIT(wait); int should_sleep = 1; prepare_to_wait(&journal->j_wait_commit, &wait, TASK_INTERRUPTIBLE); if (journal->j_commit_sequence != journal->j_commit_request) should_sleep = 0; transaction = journal->j_running_transaction; if (transaction && time_after_eq(jiffies, transaction->t_expires)) should_sleep = 0; if (journal->j_flags & JBD2_UNMOUNT) should_sleep = 0; if (should_sleep) { write_unlock(&journal->j_state_lock); schedule(); write_lock(&journal->j_state_lock); } finish_wait(&journal->j_wait_commit, &wait); } jbd_debug(1, "kjournald2 wakes\n"); /* * Were we woken up by a commit wakeup event? */ transaction = journal->j_running_transaction; if (transaction && time_after_eq(jiffies, transaction->t_expires)) { journal->j_commit_request = transaction->t_tid; jbd_debug(1, "woke because of timeout\n"); } goto loop; end_loop: del_timer_sync(&journal->j_commit_timer); journal->j_task = NULL; wake_up(&journal->j_wait_done_commit); jbd_debug(1, "Journal thread exiting.\n"); write_unlock(&journal->j_state_lock); return 0; } static int jbd2_journal_start_thread(journal_t *journal) { struct task_struct *t; t = kthread_run(kjournald2, journal, "jbd2/%s", journal->j_devname); if (IS_ERR(t)) return PTR_ERR(t); wait_event(journal->j_wait_done_commit, journal->j_task != NULL); return 0; } static void journal_kill_thread(journal_t *journal) { write_lock(&journal->j_state_lock); journal->j_flags |= JBD2_UNMOUNT; while (journal->j_task) { write_unlock(&journal->j_state_lock); wake_up(&journal->j_wait_commit); wait_event(journal->j_wait_done_commit, journal->j_task == NULL); write_lock(&journal->j_state_lock); } write_unlock(&journal->j_state_lock); } /* * jbd2_journal_write_metadata_buffer: write a metadata buffer to the journal. * * Writes a metadata buffer to a given disk block. The actual IO is not * performed but a new buffer_head is constructed which labels the data * to be written with the correct destination disk block. * * Any magic-number escaping which needs to be done will cause a * copy-out here. If the buffer happens to start with the * JBD2_MAGIC_NUMBER, then we can't write it to the log directly: the * magic number is only written to the log for descripter blocks. In * this case, we copy the data and replace the first word with 0, and we * return a result code which indicates that this buffer needs to be * marked as an escaped buffer in the corresponding log descriptor * block. The missing word can then be restored when the block is read * during recovery. * * If the source buffer has already been modified by a new transaction * since we took the last commit snapshot, we use the frozen copy of * that data for IO. If we end up using the existing buffer_head's data * for the write, then we have to make sure nobody modifies it while the * IO is in progress. do_get_write_access() handles this. * * The function returns a pointer to the buffer_head to be used for IO. * * * Return value: * <0: Error * >=0: Finished OK * * On success: * Bit 0 set == escape performed on the data * Bit 1 set == buffer copy-out performed (kfree the data after IO) */ int jbd2_journal_write_metadata_buffer(transaction_t *transaction, struct journal_head *jh_in, struct buffer_head **bh_out, sector_t blocknr) { int need_copy_out = 0; int done_copy_out = 0; int do_escape = 0; char *mapped_data; struct buffer_head *new_bh; struct page *new_page; unsigned int new_offset; struct buffer_head *bh_in = jh2bh(jh_in); journal_t *journal = transaction->t_journal; /* * The buffer really shouldn't be locked: only the current committing * transaction is allowed to write it, so nobody else is allowed * to do any IO. * * akpm: except if we're journalling data, and write() output is * also part of a shared mapping, and another thread has * decided to launch a writepage() against this buffer. */ J_ASSERT_BH(bh_in, buffer_jbddirty(bh_in)); new_bh = alloc_buffer_head(GFP_NOFS|__GFP_NOFAIL); /* keep subsequent assertions sane */ atomic_set(&new_bh->b_count, 1); spin_lock(&jh_in->b_state_lock); repeat: /* * If a new transaction has already done a buffer copy-out, then * we use that version of the data for the commit. */ if (jh_in->b_frozen_data) { done_copy_out = 1; new_page = virt_to_page(jh_in->b_frozen_data); new_offset = offset_in_page(jh_in->b_frozen_data); } else { new_page = jh2bh(jh_in)->b_page; new_offset = offset_in_page(jh2bh(jh_in)->b_data); } mapped_data = kmap_atomic(new_page); /* * Fire data frozen trigger if data already wasn't frozen. Do this * before checking for escaping, as the trigger may modify the magic * offset. If a copy-out happens afterwards, it will have the correct * data in the buffer. */ if (!done_copy_out) jbd2_buffer_frozen_trigger(jh_in, mapped_data + new_offset, jh_in->b_triggers); /* * Check for escaping */ if (*((__be32 *)(mapped_data + new_offset)) == cpu_to_be32(JBD2_MAGIC_NUMBER)) { need_copy_out = 1; do_escape = 1; } kunmap_atomic(mapped_data); /* * Do we need to do a data copy? */ if (need_copy_out && !done_copy_out) { char *tmp; spin_unlock(&jh_in->b_state_lock); tmp = jbd2_alloc(bh_in->b_size, GFP_NOFS); if (!tmp) { brelse(new_bh); return -ENOMEM; } spin_lock(&jh_in->b_state_lock); if (jh_in->b_frozen_data) { jbd2_free(tmp, bh_in->b_size); goto repeat; } jh_in->b_frozen_data = tmp; mapped_data = kmap_atomic(new_page); memcpy(tmp, mapped_data + new_offset, bh_in->b_size); kunmap_atomic(mapped_data); new_page = virt_to_page(tmp); new_offset = offset_in_page(tmp); done_copy_out = 1; /* * This isn't strictly necessary, as we're using frozen * data for the escaping, but it keeps consistency with * b_frozen_data usage. */ jh_in->b_frozen_triggers = jh_in->b_triggers; } /* * Did we need to do an escaping? Now we've done all the * copying, we can finally do so. */ if (do_escape) { mapped_data = kmap_atomic(new_page); *((unsigned int *)(mapped_data + new_offset)) = 0; kunmap_atomic(mapped_data); } set_bh_page(new_bh, new_page, new_offset); new_bh->b_size = bh_in->b_size; new_bh->b_bdev = journal->j_dev; new_bh->b_blocknr = blocknr; new_bh->b_private = bh_in; set_buffer_mapped(new_bh); set_buffer_dirty(new_bh); *bh_out = new_bh; /* * The to-be-written buffer needs to get moved to the io queue, * and the original buffer whose contents we are shadowing or * copying is moved to the transaction's shadow queue. */ JBUFFER_TRACE(jh_in, "file as BJ_Shadow"); spin_lock(&journal->j_list_lock); __jbd2_journal_file_buffer(jh_in, transaction, BJ_Shadow); spin_unlock(&journal->j_list_lock); set_buffer_shadow(bh_in); spin_unlock(&jh_in->b_state_lock); return do_escape | (done_copy_out << 1); } /* * Allocation code for the journal file. Manage the space left in the * journal, so that we can begin checkpointing when appropriate. */ /* * Called with j_state_lock locked for writing. * Returns true if a transaction commit was started. */ int __jbd2_log_start_commit(journal_t *journal, tid_t target) { /* Return if the txn has already requested to be committed */ if (journal->j_commit_request == target) return 0; /* * The only transaction we can possibly wait upon is the * currently running transaction (if it exists). Otherwise, * the target tid must be an old one. */ if (journal->j_running_transaction && journal->j_running_transaction->t_tid == target) { /* * We want a new commit: OK, mark the request and wakeup the * commit thread. We do _not_ do the commit ourselves. */ journal->j_commit_request = target; jbd_debug(1, "JBD2: requesting commit %u/%u\n", journal->j_commit_request, journal->j_commit_sequence); journal->j_running_transaction->t_requested = jiffies; wake_up(&journal->j_wait_commit); return 1; } else if (!tid_geq(journal->j_commit_request, target)) /* This should never happen, but if it does, preserve the evidence before kjournald goes into a loop and increments j_commit_sequence beyond all recognition. */ WARN_ONCE(1, "JBD2: bad log_start_commit: %u %u %u %u\n", journal->j_commit_request, journal->j_commit_sequence, target, journal->j_running_transaction ? journal->j_running_transaction->t_tid : 0); return 0; } int jbd2_log_start_commit(journal_t *journal, tid_t tid) { int ret; write_lock(&journal->j_state_lock); ret = __jbd2_log_start_commit(journal, tid); write_unlock(&journal->j_state_lock); return ret; } /* * Force and wait any uncommitted transactions. We can only force the running * transaction if we don't have an active handle, otherwise, we will deadlock. * Returns: <0 in case of error, * 0 if nothing to commit, * 1 if transaction was successfully committed. */ static int __jbd2_journal_force_commit(journal_t *journal) { transaction_t *transaction = NULL; tid_t tid; int need_to_start = 0, ret = 0; read_lock(&journal->j_state_lock); if (journal->j_running_transaction && !current->journal_info) { transaction = journal->j_running_transaction; if (!tid_geq(journal->j_commit_request, transaction->t_tid)) need_to_start = 1; } else if (journal->j_committing_transaction) transaction = journal->j_committing_transaction; if (!transaction) { /* Nothing to commit */ read_unlock(&journal->j_state_lock); return 0; } tid = transaction->t_tid; read_unlock(&journal->j_state_lock); if (need_to_start) jbd2_log_start_commit(journal, tid); ret = jbd2_log_wait_commit(journal, tid); if (!ret) ret = 1; return ret; } /** * jbd2_journal_force_commit_nested - Force and wait upon a commit if the * calling process is not within transaction. * * @journal: journal to force * Returns true if progress was made. * * This is used for forcing out undo-protected data which contains * bitmaps, when the fs is running out of space. */ int jbd2_journal_force_commit_nested(journal_t *journal) { int ret; ret = __jbd2_journal_force_commit(journal); return ret > 0; } /** * jbd2_journal_force_commit() - force any uncommitted transactions * @journal: journal to force * * Caller want unconditional commit. We can only force the running transaction * if we don't have an active handle, otherwise, we will deadlock. */ int jbd2_journal_force_commit(journal_t *journal) { int ret; J_ASSERT(!current->journal_info); ret = __jbd2_journal_force_commit(journal); if (ret > 0) ret = 0; return ret; } /* * Start a commit of the current running transaction (if any). Returns true * if a transaction is going to be committed (or is currently already * committing), and fills its tid in at *ptid */ int jbd2_journal_start_commit(journal_t *journal, tid_t *ptid) { int ret = 0; write_lock(&journal->j_state_lock); if (journal->j_running_transaction) { tid_t tid = journal->j_running_transaction->t_tid; __jbd2_log_start_commit(journal, tid); /* There's a running transaction and we've just made sure * it's commit has been scheduled. */ if (ptid) *ptid = tid; ret = 1; } else if (journal->j_committing_transaction) { /* * If commit has been started, then we have to wait for * completion of that transaction. */ if (ptid) *ptid = journal->j_committing_transaction->t_tid; ret = 1; } write_unlock(&journal->j_state_lock); return ret; } /* * Return 1 if a given transaction has not yet sent barrier request * connected with a transaction commit. If 0 is returned, transaction * may or may not have sent the barrier. Used to avoid sending barrier * twice in common cases. */ int jbd2_trans_will_send_data_barrier(journal_t *journal, tid_t tid) { int ret = 0; transaction_t *commit_trans; if (!(journal->j_flags & JBD2_BARRIER)) return 0; read_lock(&journal->j_state_lock); /* Transaction already committed? */ if (tid_geq(journal->j_commit_sequence, tid)) goto out; commit_trans = journal->j_committing_transaction; if (!commit_trans || commit_trans->t_tid != tid) { ret = 1; goto out; } /* * Transaction is being committed and we already proceeded to * submitting a flush to fs partition? */ if (journal->j_fs_dev != journal->j_dev) { if (!commit_trans->t_need_data_flush || commit_trans->t_state >= T_COMMIT_DFLUSH) goto out; } else { if (commit_trans->t_state >= T_COMMIT_JFLUSH) goto out; } ret = 1; out: read_unlock(&journal->j_state_lock); return ret; } EXPORT_SYMBOL(jbd2_trans_will_send_data_barrier); /* * Wait for a specified commit to complete. * The caller may not hold the journal lock. */ int jbd2_log_wait_commit(journal_t *journal, tid_t tid) { int err = 0; read_lock(&journal->j_state_lock); #ifdef CONFIG_PROVE_LOCKING /* * Some callers make sure transaction is already committing and in that * case we cannot block on open handles anymore. So don't warn in that * case. */ if (tid_gt(tid, journal->j_commit_sequence) && (!journal->j_committing_transaction || journal->j_committing_transaction->t_tid != tid)) { read_unlock(&journal->j_state_lock); jbd2_might_wait_for_commit(journal); read_lock(&journal->j_state_lock); } #endif #ifdef CONFIG_JBD2_DEBUG if (!tid_geq(journal->j_commit_request, tid)) { printk(KERN_ERR "%s: error: j_commit_request=%u, tid=%u\n", __func__, journal->j_commit_request, tid); } #endif while (tid_gt(tid, journal->j_commit_sequence)) { jbd_debug(1, "JBD2: want %u, j_commit_sequence=%u\n", tid, journal->j_commit_sequence); read_unlock(&journal->j_state_lock); wake_up(&journal->j_wait_commit); wait_event(journal->j_wait_done_commit, !tid_gt(tid, journal->j_commit_sequence)); read_lock(&journal->j_state_lock); } read_unlock(&journal->j_state_lock); if (unlikely(is_journal_aborted(journal))) err = -EIO; return err; } /* * Start a fast commit. If there's an ongoing fast or full commit wait for * it to complete. Returns 0 if a new fast commit was started. Returns -EALREADY * if a fast commit is not needed, either because there's an already a commit * going on or this tid has already been committed. Returns -EINVAL if no jbd2 * commit has yet been performed. */ int jbd2_fc_begin_commit(journal_t *journal, tid_t tid) { if (unlikely(is_journal_aborted(journal))) return -EIO; /* * Fast commits only allowed if at least one full commit has * been processed. */ if (!journal->j_stats.ts_tid) return -EINVAL; write_lock(&journal->j_state_lock); if (tid <= journal->j_commit_sequence) { write_unlock(&journal->j_state_lock); return -EALREADY; } if (journal->j_flags & JBD2_FULL_COMMIT_ONGOING || (journal->j_flags & JBD2_FAST_COMMIT_ONGOING)) { DEFINE_WAIT(wait); prepare_to_wait(&journal->j_fc_wait, &wait, TASK_UNINTERRUPTIBLE); write_unlock(&journal->j_state_lock); schedule(); finish_wait(&journal->j_fc_wait, &wait); return -EALREADY; } journal->j_flags |= JBD2_FAST_COMMIT_ONGOING; write_unlock(&journal->j_state_lock); return 0; } EXPORT_SYMBOL(jbd2_fc_begin_commit); /* * Stop a fast commit. If fallback is set, this function starts commit of * TID tid before any other fast commit can start. */ static int __jbd2_fc_end_commit(journal_t *journal, tid_t tid, bool fallback) { if (journal->j_fc_cleanup_callback) journal->j_fc_cleanup_callback(journal, 0); write_lock(&journal->j_state_lock); journal->j_flags &= ~JBD2_FAST_COMMIT_ONGOING; if (fallback) journal->j_flags |= JBD2_FULL_COMMIT_ONGOING; write_unlock(&journal->j_state_lock); wake_up(&journal->j_fc_wait); if (fallback) return jbd2_complete_transaction(journal, tid); return 0; } int jbd2_fc_end_commit(journal_t *journal) { return __jbd2_fc_end_commit(journal, 0, false); } EXPORT_SYMBOL(jbd2_fc_end_commit); int jbd2_fc_end_commit_fallback(journal_t *journal) { tid_t tid; read_lock(&journal->j_state_lock); tid = journal->j_running_transaction ? journal->j_running_transaction->t_tid : 0; read_unlock(&journal->j_state_lock); return __jbd2_fc_end_commit(journal, tid, true); } EXPORT_SYMBOL(jbd2_fc_end_commit_fallback); /* Return 1 when transaction with given tid has already committed. */ int jbd2_transaction_committed(journal_t *journal, tid_t tid) { int ret = 1; read_lock(&journal->j_state_lock); if (journal->j_running_transaction && journal->j_running_transaction->t_tid == tid) ret = 0; if (journal->j_committing_transaction && journal->j_committing_transaction->t_tid == tid) ret = 0; read_unlock(&journal->j_state_lock); return ret; } EXPORT_SYMBOL(jbd2_transaction_committed); /* * When this function returns the transaction corresponding to tid * will be completed. If the transaction has currently running, start * committing that transaction before waiting for it to complete. If * the transaction id is stale, it is by definition already completed, * so just return SUCCESS. */ int jbd2_complete_transaction(journal_t *journal, tid_t tid) { int need_to_wait = 1; read_lock(&journal->j_state_lock); if (journal->j_running_transaction && journal->j_running_transaction->t_tid == tid) { if (journal->j_commit_request != tid) { /* transaction not yet started, so request it */ read_unlock(&journal->j_state_lock); jbd2_log_start_commit(journal, tid); goto wait_commit; } } else if (!(journal->j_committing_transaction && journal->j_committing_transaction->t_tid == tid)) need_to_wait = 0; read_unlock(&journal->j_state_lock); if (!need_to_wait) return 0; wait_commit: return jbd2_log_wait_commit(journal, tid); } EXPORT_SYMBOL(jbd2_complete_transaction); /* * Log buffer allocation routines: */ int jbd2_journal_next_log_block(journal_t *journal, unsigned long long *retp) { unsigned long blocknr; write_lock(&journal->j_state_lock); J_ASSERT(journal->j_free > 1); blocknr = journal->j_head; journal->j_head++; journal->j_free--; if (journal->j_head == journal->j_last) journal->j_head = journal->j_first; write_unlock(&journal->j_state_lock); return jbd2_journal_bmap(journal, blocknr, retp); } /* Map one fast commit buffer for use by the file system */ int jbd2_fc_get_buf(journal_t *journal, struct buffer_head **bh_out) { unsigned long long pblock; unsigned long blocknr; int ret = 0; struct buffer_head *bh; int fc_off; *bh_out = NULL; if (journal->j_fc_off + journal->j_fc_first < journal->j_fc_last) { fc_off = journal->j_fc_off; blocknr = journal->j_fc_first + fc_off; journal->j_fc_off++; } else { ret = -EINVAL; } if (ret) return ret; ret = jbd2_journal_bmap(journal, blocknr, &pblock); if (ret) return ret; bh = __getblk(journal->j_dev, pblock, journal->j_blocksize); if (!bh) return -ENOMEM; journal->j_fc_wbuf[fc_off] = bh; *bh_out = bh; return 0; } EXPORT_SYMBOL(jbd2_fc_get_buf); /* * Wait on fast commit buffers that were allocated by jbd2_fc_get_buf * for completion. */ int jbd2_fc_wait_bufs(journal_t *journal, int num_blks) { struct buffer_head *bh; int i, j_fc_off; j_fc_off = journal->j_fc_off; /* * Wait in reverse order to minimize chances of us being woken up before * all IOs have completed */ for (i = j_fc_off - 1; i >= j_fc_off - num_blks; i--) { bh = journal->j_fc_wbuf[i]; wait_on_buffer(bh); put_bh(bh); journal->j_fc_wbuf[i] = NULL; if (unlikely(!buffer_uptodate(bh))) return -EIO; } return 0; } EXPORT_SYMBOL(jbd2_fc_wait_bufs); /* * Wait on fast commit buffers that were allocated by jbd2_fc_get_buf * for completion. */ int jbd2_fc_release_bufs(journal_t *journal) { struct buffer_head *bh; int i, j_fc_off; j_fc_off = journal->j_fc_off; /* * Wait in reverse order to minimize chances of us being woken up before * all IOs have completed */ for (i = j_fc_off - 1; i >= 0; i--) { bh = journal->j_fc_wbuf[i]; if (!bh) break; put_bh(bh); journal->j_fc_wbuf[i] = NULL; } return 0; } EXPORT_SYMBOL(jbd2_fc_release_bufs); /* * Conversion of logical to physical block numbers for the journal * * On external journals the journal blocks are identity-mapped, so * this is a no-op. If needed, we can use j_blk_offset - everything is * ready. */ int jbd2_journal_bmap(journal_t *journal, unsigned long blocknr, unsigned long long *retp) { int err = 0; unsigned long long ret; sector_t block = 0; if (journal->j_inode) { block = blocknr; ret = bmap(journal->j_inode, &block); if (ret || !block) { printk(KERN_ALERT "%s: journal block not found " "at offset %lu on %s\n", __func__, blocknr, journal->j_devname); err = -EIO; jbd2_journal_abort(journal, err); } else { *retp = block; } } else { *retp = blocknr; /* +journal->j_blk_offset */ } return err; } /* * We play buffer_head aliasing tricks to write data/metadata blocks to * the journal without copying their contents, but for journal * descriptor blocks we do need to generate bona fide buffers. * * After the caller of jbd2_journal_get_descriptor_buffer() has finished modifying * the buffer's contents they really should run flush_dcache_page(bh->b_page). * But we don't bother doing that, so there will be coherency problems with * mmaps of blockdevs which hold live JBD-controlled filesystems. */ struct buffer_head * jbd2_journal_get_descriptor_buffer(transaction_t *transaction, int type) { journal_t *journal = transaction->t_journal; struct buffer_head *bh; unsigned long long blocknr; journal_header_t *header; int err; err = jbd2_journal_next_log_block(journal, &blocknr); if (err) return NULL; bh = __getblk(journal->j_dev, blocknr, journal->j_blocksize); if (!bh) return NULL; atomic_dec(&transaction->t_outstanding_credits); lock_buffer(bh); memset(bh->b_data, 0, journal->j_blocksize); header = (journal_header_t *)bh->b_data; header->h_magic = cpu_to_be32(JBD2_MAGIC_NUMBER); header->h_blocktype = cpu_to_be32(type); header->h_sequence = cpu_to_be32(transaction->t_tid); set_buffer_uptodate(bh); unlock_buffer(bh); BUFFER_TRACE(bh, "return this buffer"); return bh; } void jbd2_descriptor_block_csum_set(journal_t *j, struct buffer_head *bh) { struct jbd2_journal_block_tail *tail; __u32 csum; if (!jbd2_journal_has_csum_v2or3(j)) return; tail = (struct jbd2_journal_block_tail *)(bh->b_data + j->j_blocksize - sizeof(struct jbd2_journal_block_tail)); tail->t_checksum = 0; csum = jbd2_chksum(j, j->j_csum_seed, bh->b_data, j->j_blocksize); tail->t_checksum = cpu_to_be32(csum); } /* * Return tid of the oldest transaction in the journal and block in the journal * where the transaction starts. * * If the journal is now empty, return which will be the next transaction ID * we will write and where will that transaction start. * * The return value is 0 if journal tail cannot be pushed any further, 1 if * it can. */ int jbd2_journal_get_log_tail(journal_t *journal, tid_t *tid, unsigned long *block) { transaction_t *transaction; int ret; read_lock(&journal->j_state_lock); spin_lock(&journal->j_list_lock); transaction = journal->j_checkpoint_transactions; if (transaction) { *tid = transaction->t_tid; *block = transaction->t_log_start; } else if ((transaction = journal->j_committing_transaction) != NULL) { *tid = transaction->t_tid; *block = transaction->t_log_start; } else if ((transaction = journal->j_running_transaction) != NULL) { *tid = transaction->t_tid; *block = journal->j_head; } else { *tid = journal->j_transaction_sequence; *block = journal->j_head; } ret = tid_gt(*tid, journal->j_tail_sequence); spin_unlock(&journal->j_list_lock); read_unlock(&journal->j_state_lock); return ret; } /* * Update information in journal structure and in on disk journal superblock * about log tail. This function does not check whether information passed in * really pushes log tail further. It's responsibility of the caller to make * sure provided log tail information is valid (e.g. by holding * j_checkpoint_mutex all the time between computing log tail and calling this * function as is the case with jbd2_cleanup_journal_tail()). * * Requires j_checkpoint_mutex */ int __jbd2_update_log_tail(journal_t *journal, tid_t tid, unsigned long block) { unsigned long freed; int ret; BUG_ON(!mutex_is_locked(&journal->j_checkpoint_mutex)); /* * We cannot afford for write to remain in drive's caches since as * soon as we update j_tail, next transaction can start reusing journal * space and if we lose sb update during power failure we'd replay * old transaction with possibly newly overwritten data. */ ret = jbd2_journal_update_sb_log_tail(journal, tid, block, REQ_SYNC | REQ_FUA); if (ret) goto out; write_lock(&journal->j_state_lock); freed = block - journal->j_tail; if (block < journal->j_tail) freed += journal->j_last - journal->j_first; trace_jbd2_update_log_tail(journal, tid, block, freed); jbd_debug(1, "Cleaning journal tail from %u to %u (offset %lu), " "freeing %lu\n", journal->j_tail_sequence, tid, block, freed); journal->j_free += freed; journal->j_tail_sequence = tid; journal->j_tail = block; write_unlock(&journal->j_state_lock); out: return ret; } /* * This is a variation of __jbd2_update_log_tail which checks for validity of * provided log tail and locks j_checkpoint_mutex. So it is safe against races * with other threads updating log tail. */ void jbd2_update_log_tail(journal_t *journal, tid_t tid, unsigned long block) { mutex_lock_io(&journal->j_checkpoint_mutex); if (tid_gt(tid, journal->j_tail_sequence)) __jbd2_update_log_tail(journal, tid, block); mutex_unlock(&journal->j_checkpoint_mutex); } struct jbd2_stats_proc_session { journal_t *journal; struct transaction_stats_s *stats; int start; int max; }; static void *jbd2_seq_info_start(struct seq_file *seq, loff_t *pos) { return *pos ? NULL : SEQ_START_TOKEN; } static void *jbd2_seq_info_next(struct seq_file *seq, void *v, loff_t *pos) { (*pos)++; return NULL; } static int jbd2_seq_info_show(struct seq_file *seq, void *v) { struct jbd2_stats_proc_session *s = seq->private; if (v != SEQ_START_TOKEN) return 0; seq_printf(seq, "%lu transactions (%lu requested), " "each up to %u blocks\n", s->stats->ts_tid, s->stats->ts_requested, s->journal->j_max_transaction_buffers); if (s->stats->ts_tid == 0) return 0; seq_printf(seq, "average: \n %ums waiting for transaction\n", jiffies_to_msecs(s->stats->run.rs_wait / s->stats->ts_tid)); seq_printf(seq, " %ums request delay\n", (s->stats->ts_requested == 0) ? 0 : jiffies_to_msecs(s->stats->run.rs_request_delay / s->stats->ts_requested)); seq_printf(seq, " %ums running transaction\n", jiffies_to_msecs(s->stats->run.rs_running / s->stats->ts_tid)); seq_printf(seq, " %ums transaction was being locked\n", jiffies_to_msecs(s->stats->run.rs_locked / s->stats->ts_tid)); seq_printf(seq, " %ums flushing data (in ordered mode)\n", jiffies_to_msecs(s->stats->run.rs_flushing / s->stats->ts_tid)); seq_printf(seq, " %ums logging transaction\n", jiffies_to_msecs(s->stats->run.rs_logging / s->stats->ts_tid)); seq_printf(seq, " %lluus average transaction commit time\n", div_u64(s->journal->j_average_commit_time, 1000)); seq_printf(seq, " %lu handles per transaction\n", s->stats->run.rs_handle_count / s->stats->ts_tid); seq_printf(seq, " %lu blocks per transaction\n", s->stats->run.rs_blocks / s->stats->ts_tid); seq_printf(seq, " %lu logged blocks per transaction\n", s->stats->run.rs_blocks_logged / s->stats->ts_tid); return 0; } static void jbd2_seq_info_stop(struct seq_file *seq, void *v) { } static const struct seq_operations jbd2_seq_info_ops = { .start = jbd2_seq_info_start, .next = jbd2_seq_info_next, .stop = jbd2_seq_info_stop, .show = jbd2_seq_info_show, }; static int jbd2_seq_info_open(struct inode *inode, struct file *file) { journal_t *journal = PDE_DATA(inode); struct jbd2_stats_proc_session *s; int rc, size; s = kmalloc(sizeof(*s), GFP_KERNEL); if (s == NULL) return -ENOMEM; size = sizeof(struct transaction_stats_s); s->stats = kmalloc(size, GFP_KERNEL); if (s->stats == NULL) { kfree(s); return -ENOMEM; } spin_lock(&journal->j_history_lock); memcpy(s->stats, &journal->j_stats, size); s->journal = journal; spin_unlock(&journal->j_history_lock); rc = seq_open(file, &jbd2_seq_info_ops); if (rc == 0) { struct seq_file *m = file->private_data; m->private = s; } else { kfree(s->stats); kfree(s); } return rc; } static int jbd2_seq_info_release(struct inode *inode, struct file *file) { struct seq_file *seq = file->private_data; struct jbd2_stats_proc_session *s = seq->private; kfree(s->stats); kfree(s); return seq_release(inode, file); } static const struct proc_ops jbd2_info_proc_ops = { .proc_open = jbd2_seq_info_open, .proc_read = seq_read, .proc_lseek = seq_lseek, .proc_release = jbd2_seq_info_release, }; static struct proc_dir_entry *proc_jbd2_stats; static void jbd2_stats_proc_init(journal_t *journal) { journal->j_proc_entry = proc_mkdir(journal->j_devname, proc_jbd2_stats); if (journal->j_proc_entry) { proc_create_data("info", S_IRUGO, journal->j_proc_entry, &jbd2_info_proc_ops, journal); } } static void jbd2_stats_proc_exit(journal_t *journal) { remove_proc_entry("info", journal->j_proc_entry); remove_proc_entry(journal->j_devname, proc_jbd2_stats); } /* Minimum size of descriptor tag */ static int jbd2_min_tag_size(void) { /* * Tag with 32-bit block numbers does not use last four bytes of the * structure */ return sizeof(journal_block_tag_t) - 4; } /* * Management for journal control blocks: functions to create and * destroy journal_t structures, and to initialise and read existing * journal blocks from disk. */ /* First: create and setup a journal_t object in memory. We initialise * very few fields yet: that has to wait until we have created the * journal structures from from scratch, or loaded them from disk. */ static journal_t *journal_init_common(struct block_device *bdev, struct block_device *fs_dev, unsigned long long start, int len, int blocksize) { static struct lock_class_key jbd2_trans_commit_key; journal_t *journal; int err; struct buffer_head *bh; int n; journal = kzalloc(sizeof(*journal), GFP_KERNEL); if (!journal) return NULL; init_waitqueue_head(&journal->j_wait_transaction_locked); init_waitqueue_head(&journal->j_wait_done_commit); init_waitqueue_head(&journal->j_wait_commit); init_waitqueue_head(&journal->j_wait_updates); init_waitqueue_head(&journal->j_wait_reserved); init_waitqueue_head(&journal->j_fc_wait); mutex_init(&journal->j_abort_mutex); mutex_init(&journal->j_barrier); mutex_init(&journal->j_checkpoint_mutex); spin_lock_init(&journal->j_revoke_lock); spin_lock_init(&journal->j_list_lock); rwlock_init(&journal->j_state_lock); journal->j_commit_interval = (HZ * JBD2_DEFAULT_MAX_COMMIT_AGE); journal->j_min_batch_time = 0; journal->j_max_batch_time = 15000; /* 15ms */ atomic_set(&journal->j_reserved_credits, 0); /* The journal is marked for error until we succeed with recovery! */ journal->j_flags = JBD2_ABORT; /* Set up a default-sized revoke table for the new mount. */ err = jbd2_journal_init_revoke(journal, JOURNAL_REVOKE_DEFAULT_HASH); if (err) goto err_cleanup; spin_lock_init(&journal->j_history_lock); lockdep_init_map(&journal->j_trans_commit_map, "jbd2_handle", &jbd2_trans_commit_key, 0); /* journal descriptor can store up to n blocks -bzzz */ journal->j_blocksize = blocksize; journal->j_dev = bdev; journal->j_fs_dev = fs_dev; journal->j_blk_offset = start; journal->j_total_len = len; /* We need enough buffers to write out full descriptor block. */ n = journal->j_blocksize / jbd2_min_tag_size(); journal->j_wbufsize = n; journal->j_fc_wbuf = NULL; journal->j_wbuf = kmalloc_array(n, sizeof(struct buffer_head *), GFP_KERNEL); if (!journal->j_wbuf) goto err_cleanup; bh = getblk_unmovable(journal->j_dev, start, journal->j_blocksize); if (!bh) { pr_err("%s: Cannot get buffer for journal superblock\n", __func__); goto err_cleanup; } journal->j_sb_buffer = bh; journal->j_superblock = (journal_superblock_t *)bh->b_data; return journal; err_cleanup: kfree(journal->j_wbuf); jbd2_journal_destroy_revoke(journal); kfree(journal); return NULL; } /* jbd2_journal_init_dev and jbd2_journal_init_inode: * * Create a journal structure assigned some fixed set of disk blocks to * the journal. We don't actually touch those disk blocks yet, but we * need to set up all of the mapping information to tell the journaling * system where the journal blocks are. * */ /** * journal_t * jbd2_journal_init_dev() - creates and initialises a journal structure * @bdev: Block device on which to create the journal * @fs_dev: Device which hold journalled filesystem for this journal. * @start: Block nr Start of journal. * @len: Length of the journal in blocks. * @blocksize: blocksize of journalling device * * Returns: a newly created journal_t * * * jbd2_journal_init_dev creates a journal which maps a fixed contiguous * range of blocks on an arbitrary block device. * */ journal_t *jbd2_journal_init_dev(struct block_device *bdev, struct block_device *fs_dev, unsigned long long start, int len, int blocksize) { journal_t *journal; journal = journal_init_common(bdev, fs_dev, start, len, blocksize); if (!journal) return NULL; bdevname(journal->j_dev, journal->j_devname); strreplace(journal->j_devname, '/', '!'); jbd2_stats_proc_init(journal); return journal; } /** * journal_t * jbd2_journal_init_inode () - creates a journal which maps to a inode. * @inode: An inode to create the journal in * * jbd2_journal_init_inode creates a journal which maps an on-disk inode as * the journal. The inode must exist already, must support bmap() and * must have all data blocks preallocated. */ journal_t *jbd2_journal_init_inode(struct inode *inode) { journal_t *journal; sector_t blocknr; char *p; int err = 0; blocknr = 0; err = bmap(inode, &blocknr); if (err || !blocknr) { pr_err("%s: Cannot locate journal superblock\n", __func__); return NULL; } jbd_debug(1, "JBD2: inode %s/%ld, size %lld, bits %d, blksize %ld\n", inode->i_sb->s_id, inode->i_ino, (long long) inode->i_size, inode->i_sb->s_blocksize_bits, inode->i_sb->s_blocksize); journal = journal_init_common(inode->i_sb->s_bdev, inode->i_sb->s_bdev, blocknr, inode->i_size >> inode->i_sb->s_blocksize_bits, inode->i_sb->s_blocksize); if (!journal) return NULL; journal->j_inode = inode; bdevname(journal->j_dev, journal->j_devname); p = strreplace(journal->j_devname, '/', '!'); sprintf(p, "-%lu", journal->j_inode->i_ino); jbd2_stats_proc_init(journal); return journal; } /* * If the journal init or create aborts, we need to mark the journal * superblock as being NULL to prevent the journal destroy from writing * back a bogus superblock. */ static void journal_fail_superblock(journal_t *journal) { struct buffer_head *bh = journal->j_sb_buffer; brelse(bh); journal->j_sb_buffer = NULL; } /* * Given a journal_t structure, initialise the various fields for * startup of a new journaling session. We use this both when creating * a journal, and after recovering an old journal to reset it for * subsequent use. */ static int journal_reset(journal_t *journal) { journal_superblock_t *sb = journal->j_superblock; unsigned long long first, last; first = be32_to_cpu(sb->s_first); last = be32_to_cpu(sb->s_maxlen); if (first + JBD2_MIN_JOURNAL_BLOCKS > last + 1) { printk(KERN_ERR "JBD2: Journal too short (blocks %llu-%llu).\n", first, last); journal_fail_superblock(journal); return -EINVAL; } journal->j_first = first; journal->j_last = last; journal->j_head = journal->j_first; journal->j_tail = journal->j_first; journal->j_free = journal->j_last - journal->j_first; journal->j_tail_sequence = journal->j_transaction_sequence; journal->j_commit_sequence = journal->j_transaction_sequence - 1; journal->j_commit_request = journal->j_commit_sequence; journal->j_max_transaction_buffers = jbd2_journal_get_max_txn_bufs(journal); /* * Now that journal recovery is done, turn fast commits off here. This * way, if fast commit was enabled before the crash but if now FS has * disabled it, we don't enable fast commits. */ jbd2_clear_feature_fast_commit(journal); /* * As a special case, if the on-disk copy is already marked as needing * no recovery (s_start == 0), then we can safely defer the superblock * update until the next commit by setting JBD2_FLUSHED. This avoids * attempting a write to a potential-readonly device. */ if (sb->s_start == 0) { jbd_debug(1, "JBD2: Skipping superblock update on recovered sb " "(start %ld, seq %u, errno %d)\n", journal->j_tail, journal->j_tail_sequence, journal->j_errno); journal->j_flags |= JBD2_FLUSHED; } else { /* Lock here to make assertions happy... */ mutex_lock_io(&journal->j_checkpoint_mutex); /* * Update log tail information. We use REQ_FUA since new * transaction will start reusing journal space and so we * must make sure information about current log tail is on * disk before that. */ jbd2_journal_update_sb_log_tail(journal, journal->j_tail_sequence, journal->j_tail, REQ_SYNC | REQ_FUA); mutex_unlock(&journal->j_checkpoint_mutex); } return jbd2_journal_start_thread(journal); } /* * This function expects that the caller will have locked the journal * buffer head, and will return with it unlocked */ static int jbd2_write_superblock(journal_t *journal, int write_flags) { struct buffer_head *bh = journal->j_sb_buffer; journal_superblock_t *sb = journal->j_superblock; int ret; /* Buffer got discarded which means block device got invalidated */ if (!buffer_mapped(bh)) { unlock_buffer(bh); return -EIO; } trace_jbd2_write_superblock(journal, write_flags); if (!(journal->j_flags & JBD2_BARRIER)) write_flags &= ~(REQ_FUA | REQ_PREFLUSH); if (buffer_write_io_error(bh)) { /* * Oh, dear. A previous attempt to write the journal * superblock failed. This could happen because the * USB device was yanked out. Or it could happen to * be a transient write error and maybe the block will * be remapped. Nothing we can do but to retry the * write and hope for the best. */ printk(KERN_ERR "JBD2: previous I/O error detected " "for journal superblock update for %s.\n", journal->j_devname); clear_buffer_write_io_error(bh); set_buffer_uptodate(bh); } if (jbd2_journal_has_csum_v2or3(journal)) sb->s_checksum = jbd2_superblock_csum(journal, sb); get_bh(bh); bh->b_end_io = end_buffer_write_sync; ret = submit_bh(REQ_OP_WRITE, write_flags, bh); wait_on_buffer(bh); if (buffer_write_io_error(bh)) { clear_buffer_write_io_error(bh); set_buffer_uptodate(bh); ret = -EIO; } if (ret) { printk(KERN_ERR "JBD2: Error %d detected when updating " "journal superblock for %s.\n", ret, journal->j_devname); if (!is_journal_aborted(journal)) jbd2_journal_abort(journal, ret); } return ret; } /** * jbd2_journal_update_sb_log_tail() - Update log tail in journal sb on disk. * @journal: The journal to update. * @tail_tid: TID of the new transaction at the tail of the log * @tail_block: The first block of the transaction at the tail of the log * @write_op: With which operation should we write the journal sb * * Update a journal's superblock information about log tail and write it to * disk, waiting for the IO to complete. */ int jbd2_journal_update_sb_log_tail(journal_t *journal, tid_t tail_tid, unsigned long tail_block, int write_op) { journal_superblock_t *sb = journal->j_superblock; int ret; if (is_journal_aborted(journal)) return -EIO; BUG_ON(!mutex_is_locked(&journal->j_checkpoint_mutex)); jbd_debug(1, "JBD2: updating superblock (start %lu, seq %u)\n", tail_block, tail_tid); lock_buffer(journal->j_sb_buffer); sb->s_sequence = cpu_to_be32(tail_tid); sb->s_start = cpu_to_be32(tail_block); ret = jbd2_write_superblock(journal, write_op); if (ret) goto out; /* Log is no longer empty */ write_lock(&journal->j_state_lock); WARN_ON(!sb->s_sequence); journal->j_flags &= ~JBD2_FLUSHED; write_unlock(&journal->j_state_lock); out: return ret; } /** * jbd2_mark_journal_empty() - Mark on disk journal as empty. * @journal: The journal to update. * @write_op: With which operation should we write the journal sb * * Update a journal's dynamic superblock fields to show that journal is empty. * Write updated superblock to disk waiting for IO to complete. */ static void jbd2_mark_journal_empty(journal_t *journal, int write_op) { journal_superblock_t *sb = journal->j_superblock; bool had_fast_commit = false; BUG_ON(!mutex_is_locked(&journal->j_checkpoint_mutex)); lock_buffer(journal->j_sb_buffer); if (sb->s_start == 0) { /* Is it already empty? */ unlock_buffer(journal->j_sb_buffer); return; } jbd_debug(1, "JBD2: Marking journal as empty (seq %u)\n", journal->j_tail_sequence); sb->s_sequence = cpu_to_be32(journal->j_tail_sequence); sb->s_start = cpu_to_be32(0); if (jbd2_has_feature_fast_commit(journal)) { /* * When journal is clean, no need to commit fast commit flag and * make file system incompatible with older kernels. */ jbd2_clear_feature_fast_commit(journal); had_fast_commit = true; } jbd2_write_superblock(journal, write_op); if (had_fast_commit) jbd2_set_feature_fast_commit(journal); /* Log is no longer empty */ write_lock(&journal->j_state_lock); journal->j_flags |= JBD2_FLUSHED; write_unlock(&journal->j_state_lock); } /** * jbd2_journal_update_sb_errno() - Update error in the journal. * @journal: The journal to update. * * Update a journal's errno. Write updated superblock to disk waiting for IO * to complete. */ void jbd2_journal_update_sb_errno(journal_t *journal) { journal_superblock_t *sb = journal->j_superblock; int errcode; lock_buffer(journal->j_sb_buffer); errcode = journal->j_errno; if (errcode == -ESHUTDOWN) errcode = 0; jbd_debug(1, "JBD2: updating superblock error (errno %d)\n", errcode); sb->s_errno = cpu_to_be32(errcode); jbd2_write_superblock(journal, REQ_SYNC | REQ_FUA); } EXPORT_SYMBOL(jbd2_journal_update_sb_errno); static int journal_revoke_records_per_block(journal_t *journal) { int record_size; int space = journal->j_blocksize - sizeof(jbd2_journal_revoke_header_t); if (jbd2_has_feature_64bit(journal)) record_size = 8; else record_size = 4; if (jbd2_journal_has_csum_v2or3(journal)) space -= sizeof(struct jbd2_journal_block_tail); return space / record_size; } /* * Read the superblock for a given journal, performing initial * validation of the format. */ static int journal_get_superblock(journal_t *journal) { struct buffer_head *bh; journal_superblock_t *sb; int err = -EIO; bh = journal->j_sb_buffer; J_ASSERT(bh != NULL); if (!buffer_uptodate(bh)) { ll_rw_block(REQ_OP_READ, 0, 1, &bh); wait_on_buffer(bh); if (!buffer_uptodate(bh)) { printk(KERN_ERR "JBD2: IO error reading journal superblock\n"); goto out; } } if (buffer_verified(bh)) return 0; sb = journal->j_superblock; err = -EINVAL; if (sb->s_header.h_magic != cpu_to_be32(JBD2_MAGIC_NUMBER) || sb->s_blocksize != cpu_to_be32(journal->j_blocksize)) { printk(KERN_WARNING "JBD2: no valid journal superblock found\n"); goto out; } switch(be32_to_cpu(sb->s_header.h_blocktype)) { case JBD2_SUPERBLOCK_V1: journal->j_format_version = 1; break; case JBD2_SUPERBLOCK_V2: journal->j_format_version = 2; break; default: printk(KERN_WARNING "JBD2: unrecognised superblock format ID\n"); goto out; } if (be32_to_cpu(sb->s_maxlen) < journal->j_total_len) journal->j_total_len = be32_to_cpu(sb->s_maxlen); else if (be32_to_cpu(sb->s_maxlen) > journal->j_total_len) { printk(KERN_WARNING "JBD2: journal file too short\n"); goto out; } if (be32_to_cpu(sb->s_first) == 0 || be32_to_cpu(sb->s_first) >= journal->j_total_len) { printk(KERN_WARNING "JBD2: Invalid start block of journal: %u\n", be32_to_cpu(sb->s_first)); goto out; } if (jbd2_has_feature_csum2(journal) && jbd2_has_feature_csum3(journal)) { /* Can't have checksum v2 and v3 at the same time! */ printk(KERN_ERR "JBD2: Can't enable checksumming v2 and v3 " "at the same time!\n"); goto out; } if (jbd2_journal_has_csum_v2or3_feature(journal) && jbd2_has_feature_checksum(journal)) { /* Can't have checksum v1 and v2 on at the same time! */ printk(KERN_ERR "JBD2: Can't enable checksumming v1 and v2/3 " "at the same time!\n"); goto out; } if (!jbd2_verify_csum_type(journal, sb)) { printk(KERN_ERR "JBD2: Unknown checksum type\n"); goto out; } /* Load the checksum driver */ if (jbd2_journal_has_csum_v2or3_feature(journal)) { journal->j_chksum_driver = crypto_alloc_shash("crc32c", 0, 0); if (IS_ERR(journal->j_chksum_driver)) { printk(KERN_ERR "JBD2: Cannot load crc32c driver.\n"); err = PTR_ERR(journal->j_chksum_driver); journal->j_chksum_driver = NULL; goto out; } } if (jbd2_journal_has_csum_v2or3(journal)) { /* Check superblock checksum */ if (sb->s_checksum != jbd2_superblock_csum(journal, sb)) { printk(KERN_ERR "JBD2: journal checksum error\n"); err = -EFSBADCRC; goto out; } /* Precompute checksum seed for all metadata */ journal->j_csum_seed = jbd2_chksum(journal, ~0, sb->s_uuid, sizeof(sb->s_uuid)); } journal->j_revoke_records_per_block = journal_revoke_records_per_block(journal); set_buffer_verified(bh); return 0; out: journal_fail_superblock(journal); return err; } /* * Load the on-disk journal superblock and read the key fields into the * journal_t. */ static int load_superblock(journal_t *journal) { int err; journal_superblock_t *sb; int num_fc_blocks; err = journal_get_superblock(journal); if (err) return err; sb = journal->j_superblock; journal->j_tail_sequence = be32_to_cpu(sb->s_sequence); journal->j_tail = be32_to_cpu(sb->s_start); journal->j_first = be32_to_cpu(sb->s_first); journal->j_errno = be32_to_cpu(sb->s_errno); journal->j_last = be32_to_cpu(sb->s_maxlen); if (jbd2_has_feature_fast_commit(journal)) { journal->j_fc_last = be32_to_cpu(sb->s_maxlen); num_fc_blocks = be32_to_cpu(sb->s_num_fc_blks); if (!num_fc_blocks) num_fc_blocks = JBD2_MIN_FC_BLOCKS; if (journal->j_last - num_fc_blocks >= JBD2_MIN_JOURNAL_BLOCKS) journal->j_last = journal->j_fc_last - num_fc_blocks; journal->j_fc_first = journal->j_last + 1; journal->j_fc_off = 0; } return 0; } /** * jbd2_journal_load() - Read journal from disk. * @journal: Journal to act on. * * Given a journal_t structure which tells us which disk blocks contain * a journal, read the journal from disk to initialise the in-memory * structures. */ int jbd2_journal_load(journal_t *journal) { int err; journal_superblock_t *sb; err = load_superblock(journal); if (err) return err; sb = journal->j_superblock; /* If this is a V2 superblock, then we have to check the * features flags on it. */ if (journal->j_format_version >= 2) { if ((sb->s_feature_ro_compat & ~cpu_to_be32(JBD2_KNOWN_ROCOMPAT_FEATURES)) || (sb->s_feature_incompat & ~cpu_to_be32(JBD2_KNOWN_INCOMPAT_FEATURES))) { printk(KERN_WARNING "JBD2: Unrecognised features on journal\n"); return -EINVAL; } } /* * Create a slab for this blocksize */ err = jbd2_journal_create_slab(be32_to_cpu(sb->s_blocksize)); if (err) return err; /* Let the recovery code check whether it needs to recover any * data from the journal. */ if (jbd2_journal_recover(journal)) goto recovery_error; if (journal->j_failed_commit) { printk(KERN_ERR "JBD2: journal transaction %u on %s " "is corrupt.\n", journal->j_failed_commit, journal->j_devname); return -EFSCORRUPTED; } /* * clear JBD2_ABORT flag initialized in journal_init_common * here to update log tail information with the newest seq. */ journal->j_flags &= ~JBD2_ABORT; /* OK, we've finished with the dynamic journal bits: * reinitialise the dynamic contents of the superblock in memory * and reset them on disk. */ if (journal_reset(journal)) goto recovery_error; journal->j_flags |= JBD2_LOADED; return 0; recovery_error: printk(KERN_WARNING "JBD2: recovery failed\n"); return -EIO; } /** * jbd2_journal_destroy() - Release a journal_t structure. * @journal: Journal to act on. * * Release a journal_t structure once it is no longer in use by the * journaled object. * Return <0 if we couldn't clean up the journal. */ int jbd2_journal_destroy(journal_t *journal) { int err = 0; /* Wait for the commit thread to wake up and die. */ journal_kill_thread(journal); /* Force a final log commit */ if (journal->j_running_transaction) jbd2_journal_commit_transaction(journal); /* Force any old transactions to disk */ /* Totally anal locking here... */ spin_lock(&journal->j_list_lock); while (journal->j_checkpoint_transactions != NULL) { spin_unlock(&journal->j_list_lock); mutex_lock_io(&journal->j_checkpoint_mutex); err = jbd2_log_do_checkpoint(journal); mutex_unlock(&journal->j_checkpoint_mutex); /* * If checkpointing failed, just free the buffers to avoid * looping forever */ if (err) { jbd2_journal_destroy_checkpoint(journal); spin_lock(&journal->j_list_lock); break; } spin_lock(&journal->j_list_lock); } J_ASSERT(journal->j_running_transaction == NULL); J_ASSERT(journal->j_committing_transaction == NULL); J_ASSERT(journal->j_checkpoint_transactions == NULL); spin_unlock(&journal->j_list_lock); if (journal->j_sb_buffer) { if (!is_journal_aborted(journal)) { mutex_lock_io(&journal->j_checkpoint_mutex); write_lock(&journal->j_state_lock); journal->j_tail_sequence = ++journal->j_transaction_sequence; write_unlock(&journal->j_state_lock); jbd2_mark_journal_empty(journal, REQ_SYNC | REQ_PREFLUSH | REQ_FUA); mutex_unlock(&journal->j_checkpoint_mutex); } else err = -EIO; brelse(journal->j_sb_buffer); } if (journal->j_proc_entry) jbd2_stats_proc_exit(journal); iput(journal->j_inode); if (journal->j_revoke) jbd2_journal_destroy_revoke(journal); if (journal->j_chksum_driver) crypto_free_shash(journal->j_chksum_driver); kfree(journal->j_fc_wbuf); kfree(journal->j_wbuf); kfree(journal); return err; } /** * jbd2_journal_check_used_features() - Check if features specified are used. * @journal: Journal to check. * @compat: bitmask of compatible features * @ro: bitmask of features that force read-only mount * @incompat: bitmask of incompatible features * * Check whether the journal uses all of a given set of * features. Return true (non-zero) if it does. **/ int jbd2_journal_check_used_features(journal_t *journal, unsigned long compat, unsigned long ro, unsigned long incompat) { journal_superblock_t *sb; if (!compat && !ro && !incompat) return 1; /* Load journal superblock if it is not loaded yet. */ if (journal->j_format_version == 0 && journal_get_superblock(journal) != 0) return 0; if (journal->j_format_version == 1) return 0; sb = journal->j_superblock; if (((be32_to_cpu(sb->s_feature_compat) & compat) == compat) && ((be32_to_cpu(sb->s_feature_ro_compat) & ro) == ro) && ((be32_to_cpu(sb->s_feature_incompat) & incompat) == incompat)) return 1; return 0; } /** * jbd2_journal_check_available_features() - Check feature set in journalling layer * @journal: Journal to check. * @compat: bitmask of compatible features * @ro: bitmask of features that force read-only mount * @incompat: bitmask of incompatible features * * Check whether the journaling code supports the use of * all of a given set of features on this journal. Return true * (non-zero) if it can. */ int jbd2_journal_check_available_features(journal_t *journal, unsigned long compat, unsigned long ro, unsigned long incompat) { if (!compat && !ro && !incompat) return 1; /* We can support any known requested features iff the * superblock is in version 2. Otherwise we fail to support any * extended sb features. */ if (journal->j_format_version != 2) return 0; if ((compat & JBD2_KNOWN_COMPAT_FEATURES) == compat && (ro & JBD2_KNOWN_ROCOMPAT_FEATURES) == ro && (incompat & JBD2_KNOWN_INCOMPAT_FEATURES) == incompat) return 1; return 0; } static int jbd2_journal_initialize_fast_commit(journal_t *journal) { journal_superblock_t *sb = journal->j_superblock; unsigned long long num_fc_blks; num_fc_blks = be32_to_cpu(sb->s_num_fc_blks); if (num_fc_blks == 0) num_fc_blks = JBD2_MIN_FC_BLOCKS; if (journal->j_last - num_fc_blks < JBD2_MIN_JOURNAL_BLOCKS) return -ENOSPC; /* Are we called twice? */ WARN_ON(journal->j_fc_wbuf != NULL); journal->j_fc_wbuf = kmalloc_array(num_fc_blks, sizeof(struct buffer_head *), GFP_KERNEL); if (!journal->j_fc_wbuf) return -ENOMEM; journal->j_fc_wbufsize = num_fc_blks; journal->j_fc_last = journal->j_last; journal->j_last = journal->j_fc_last - num_fc_blks; journal->j_fc_first = journal->j_last + 1; journal->j_fc_off = 0; journal->j_free = journal->j_last - journal->j_first; journal->j_max_transaction_buffers = jbd2_journal_get_max_txn_bufs(journal); return 0; } /** * jbd2_journal_set_features() - Mark a given journal feature in the superblock * @journal: Journal to act on. * @compat: bitmask of compatible features * @ro: bitmask of features that force read-only mount * @incompat: bitmask of incompatible features * * Mark a given journal feature as present on the * superblock. Returns true if the requested features could be set. * */ int jbd2_journal_set_features(journal_t *journal, unsigned long compat, unsigned long ro, unsigned long incompat) { #define INCOMPAT_FEATURE_ON(f) \ ((incompat & (f)) && !(sb->s_feature_incompat & cpu_to_be32(f))) #define COMPAT_FEATURE_ON(f) \ ((compat & (f)) && !(sb->s_feature_compat & cpu_to_be32(f))) journal_superblock_t *sb; if (jbd2_journal_check_used_features(journal, compat, ro, incompat)) return 1; if (!jbd2_journal_check_available_features(journal, compat, ro, incompat)) return 0; /* If enabling v2 checksums, turn on v3 instead */ if (incompat & JBD2_FEATURE_INCOMPAT_CSUM_V2) { incompat &= ~JBD2_FEATURE_INCOMPAT_CSUM_V2; incompat |= JBD2_FEATURE_INCOMPAT_CSUM_V3; } /* Asking for checksumming v3 and v1? Only give them v3. */ if (incompat & JBD2_FEATURE_INCOMPAT_CSUM_V3 && compat & JBD2_FEATURE_COMPAT_CHECKSUM) compat &= ~JBD2_FEATURE_COMPAT_CHECKSUM; jbd_debug(1, "Setting new features 0x%lx/0x%lx/0x%lx\n", compat, ro, incompat); sb = journal->j_superblock; if (incompat & JBD2_FEATURE_INCOMPAT_FAST_COMMIT) { if (jbd2_journal_initialize_fast_commit(journal)) { pr_err("JBD2: Cannot enable fast commits.\n"); return 0; } } /* Load the checksum driver if necessary */ if ((journal->j_chksum_driver == NULL) && INCOMPAT_FEATURE_ON(JBD2_FEATURE_INCOMPAT_CSUM_V3)) { journal->j_chksum_driver = crypto_alloc_shash("crc32c", 0, 0); if (IS_ERR(journal->j_chksum_driver)) { printk(KERN_ERR "JBD2: Cannot load crc32c driver.\n"); journal->j_chksum_driver = NULL; return 0; } /* Precompute checksum seed for all metadata */ journal->j_csum_seed = jbd2_chksum(journal, ~0, sb->s_uuid, sizeof(sb->s_uuid)); } lock_buffer(journal->j_sb_buffer); /* If enabling v3 checksums, update superblock */ if (INCOMPAT_FEATURE_ON(JBD2_FEATURE_INCOMPAT_CSUM_V3)) { sb->s_checksum_type = JBD2_CRC32C_CHKSUM; sb->s_feature_compat &= ~cpu_to_be32(JBD2_FEATURE_COMPAT_CHECKSUM); } /* If enabling v1 checksums, downgrade superblock */ if (COMPAT_FEATURE_ON(JBD2_FEATURE_COMPAT_CHECKSUM)) sb->s_feature_incompat &= ~cpu_to_be32(JBD2_FEATURE_INCOMPAT_CSUM_V2 | JBD2_FEATURE_INCOMPAT_CSUM_V3); sb->s_feature_compat |= cpu_to_be32(compat); sb->s_feature_ro_compat |= cpu_to_be32(ro); sb->s_feature_incompat |= cpu_to_be32(incompat); unlock_buffer(journal->j_sb_buffer); journal->j_revoke_records_per_block = journal_revoke_records_per_block(journal); return 1; #undef COMPAT_FEATURE_ON #undef INCOMPAT_FEATURE_ON } /* * jbd2_journal_clear_features() - Clear a given journal feature in the * superblock * @journal: Journal to act on. * @compat: bitmask of compatible features * @ro: bitmask of features that force read-only mount * @incompat: bitmask of incompatible features * * Clear a given journal feature as present on the * superblock. */ void jbd2_journal_clear_features(journal_t *journal, unsigned long compat, unsigned long ro, unsigned long incompat) { journal_superblock_t *sb; jbd_debug(1, "Clear features 0x%lx/0x%lx/0x%lx\n", compat, ro, incompat); sb = journal->j_superblock; sb->s_feature_compat &= ~cpu_to_be32(compat); sb->s_feature_ro_compat &= ~cpu_to_be32(ro); sb->s_feature_incompat &= ~cpu_to_be32(incompat); journal->j_revoke_records_per_block = journal_revoke_records_per_block(journal); } EXPORT_SYMBOL(jbd2_journal_clear_features); /** * jbd2_journal_flush() - Flush journal * @journal: Journal to act on. * * Flush all data for a given journal to disk and empty the journal. * Filesystems can use this when remounting readonly to ensure that * recovery does not need to happen on remount. */ int jbd2_journal_flush(journal_t *journal) { int err = 0; transaction_t *transaction = NULL; write_lock(&journal->j_state_lock); /* Force everything buffered to the log... */ if (journal->j_running_transaction) { transaction = journal->j_running_transaction; __jbd2_log_start_commit(journal, transaction->t_tid); } else if (journal->j_committing_transaction) transaction = journal->j_committing_transaction; /* Wait for the log commit to complete... */ if (transaction) { tid_t tid = transaction->t_tid; write_unlock(&journal->j_state_lock); jbd2_log_wait_commit(journal, tid); } else { write_unlock(&journal->j_state_lock); } /* ...and flush everything in the log out to disk. */ spin_lock(&journal->j_list_lock); while (!err && journal->j_checkpoint_transactions != NULL) { spin_unlock(&journal->j_list_lock); mutex_lock_io(&journal->j_checkpoint_mutex); err = jbd2_log_do_checkpoint(journal); mutex_unlock(&journal->j_checkpoint_mutex); spin_lock(&journal->j_list_lock); } spin_unlock(&journal->j_list_lock); if (is_journal_aborted(journal)) return -EIO; mutex_lock_io(&journal->j_checkpoint_mutex); if (!err) { err = jbd2_cleanup_journal_tail(journal); if (err < 0) { mutex_unlock(&journal->j_checkpoint_mutex); goto out; } err = 0; } /* Finally, mark the journal as really needing no recovery. * This sets s_start==0 in the underlying superblock, which is * the magic code for a fully-recovered superblock. Any future * commits of data to the journal will restore the current * s_start value. */ jbd2_mark_journal_empty(journal, REQ_SYNC | REQ_FUA); mutex_unlock(&journal->j_checkpoint_mutex); write_lock(&journal->j_state_lock); J_ASSERT(!journal->j_running_transaction); J_ASSERT(!journal->j_committing_transaction); J_ASSERT(!journal->j_checkpoint_transactions); J_ASSERT(journal->j_head == journal->j_tail); J_ASSERT(journal->j_tail_sequence == journal->j_transaction_sequence); write_unlock(&journal->j_state_lock); out: return err; } /** * jbd2_journal_wipe() - Wipe journal contents * @journal: Journal to act on. * @write: flag (see below) * * Wipe out all of the contents of a journal, safely. This will produce * a warning if the journal contains any valid recovery information. * Must be called between journal_init_*() and jbd2_journal_load(). * * If 'write' is non-zero, then we wipe out the journal on disk; otherwise * we merely suppress recovery. */ int jbd2_journal_wipe(journal_t *journal, int write) { int err = 0; J_ASSERT (!(journal->j_flags & JBD2_LOADED)); err = load_superblock(journal); if (err) return err; if (!journal->j_tail) goto no_recovery; printk(KERN_WARNING "JBD2: %s recovery information on journal\n", write ? "Clearing" : "Ignoring"); err = jbd2_journal_skip_recovery(journal); if (write) { /* Lock to make assertions happy... */ mutex_lock_io(&journal->j_checkpoint_mutex); jbd2_mark_journal_empty(journal, REQ_SYNC | REQ_FUA); mutex_unlock(&journal->j_checkpoint_mutex); } no_recovery: return err; } /** * jbd2_journal_abort () - Shutdown the journal immediately. * @journal: the journal to shutdown. * @errno: an error number to record in the journal indicating * the reason for the shutdown. * * Perform a complete, immediate shutdown of the ENTIRE * journal (not of a single transaction). This operation cannot be * undone without closing and reopening the journal. * * The jbd2_journal_abort function is intended to support higher level error * recovery mechanisms such as the ext2/ext3 remount-readonly error * mode. * * Journal abort has very specific semantics. Any existing dirty, * unjournaled buffers in the main filesystem will still be written to * disk by bdflush, but the journaling mechanism will be suspended * immediately and no further transaction commits will be honoured. * * Any dirty, journaled buffers will be written back to disk without * hitting the journal. Atomicity cannot be guaranteed on an aborted * filesystem, but we _do_ attempt to leave as much data as possible * behind for fsck to use for cleanup. * * Any attempt to get a new transaction handle on a journal which is in * ABORT state will just result in an -EROFS error return. A * jbd2_journal_stop on an existing handle will return -EIO if we have * entered abort state during the update. * * Recursive transactions are not disturbed by journal abort until the * final jbd2_journal_stop, which will receive the -EIO error. * * Finally, the jbd2_journal_abort call allows the caller to supply an errno * which will be recorded (if possible) in the journal superblock. This * allows a client to record failure conditions in the middle of a * transaction without having to complete the transaction to record the * failure to disk. ext3_error, for example, now uses this * functionality. * */ void jbd2_journal_abort(journal_t *journal, int errno) { transaction_t *transaction; /* * Lock the aborting procedure until everything is done, this avoid * races between filesystem's error handling flow (e.g. ext4_abort()), * ensure panic after the error info is written into journal's * superblock. */ mutex_lock(&journal->j_abort_mutex); /* * ESHUTDOWN always takes precedence because a file system check * caused by any other journal abort error is not required after * a shutdown triggered. */ write_lock(&journal->j_state_lock); if (journal->j_flags & JBD2_ABORT) { int old_errno = journal->j_errno; write_unlock(&journal->j_state_lock); if (old_errno != -ESHUTDOWN && errno == -ESHUTDOWN) { journal->j_errno = errno; jbd2_journal_update_sb_errno(journal); } mutex_unlock(&journal->j_abort_mutex); return; } /* * Mark the abort as occurred and start current running transaction * to release all journaled buffer. */ pr_err("Aborting journal on device %s.\n", journal->j_devname); journal->j_flags |= JBD2_ABORT; journal->j_errno = errno; transaction = journal->j_running_transaction; if (transaction) __jbd2_log_start_commit(journal, transaction->t_tid); write_unlock(&journal->j_state_lock); /* * Record errno to the journal super block, so that fsck and jbd2 * layer could realise that a filesystem check is needed. */ jbd2_journal_update_sb_errno(journal); mutex_unlock(&journal->j_abort_mutex); } /** * jbd2_journal_errno() - returns the journal's error state. * @journal: journal to examine. * * This is the errno number set with jbd2_journal_abort(), the last * time the journal was mounted - if the journal was stopped * without calling abort this will be 0. * * If the journal has been aborted on this mount time -EROFS will * be returned. */ int jbd2_journal_errno(journal_t *journal) { int err; read_lock(&journal->j_state_lock); if (journal->j_flags & JBD2_ABORT) err = -EROFS; else err = journal->j_errno; read_unlock(&journal->j_state_lock); return err; } /** * jbd2_journal_clear_err() - clears the journal's error state * @journal: journal to act on. * * An error must be cleared or acked to take a FS out of readonly * mode. */ int jbd2_journal_clear_err(journal_t *journal) { int err = 0; write_lock(&journal->j_state_lock); if (journal->j_flags & JBD2_ABORT) err = -EROFS; else journal->j_errno = 0; write_unlock(&journal->j_state_lock); return err; } /** * jbd2_journal_ack_err() - Ack journal err. * @journal: journal to act on. * * An error must be cleared or acked to take a FS out of readonly * mode. */ void jbd2_journal_ack_err(journal_t *journal) { write_lock(&journal->j_state_lock); if (journal->j_errno) journal->j_flags |= JBD2_ACK_ERR; write_unlock(&journal->j_state_lock); } int jbd2_journal_blocks_per_page(struct inode *inode) { return 1 << (PAGE_SHIFT - inode->i_sb->s_blocksize_bits); } /* * helper functions to deal with 32 or 64bit block numbers. */ size_t journal_tag_bytes(journal_t *journal) { size_t sz; if (jbd2_has_feature_csum3(journal)) return sizeof(journal_block_tag3_t); sz = sizeof(journal_block_tag_t); if (jbd2_has_feature_csum2(journal)) sz += sizeof(__u16); if (jbd2_has_feature_64bit(journal)) return sz; else return sz - sizeof(__u32); } /* * JBD memory management * * These functions are used to allocate block-sized chunks of memory * used for making copies of buffer_head data. Very often it will be * page-sized chunks of data, but sometimes it will be in * sub-page-size chunks. (For example, 16k pages on Power systems * with a 4k block file system.) For blocks smaller than a page, we * use a SLAB allocator. There are slab caches for each block size, * which are allocated at mount time, if necessary, and we only free * (all of) the slab caches when/if the jbd2 module is unloaded. For * this reason we don't need to a mutex to protect access to * jbd2_slab[] allocating or releasing memory; only in * jbd2_journal_create_slab(). */ #define JBD2_MAX_SLABS 8 static struct kmem_cache *jbd2_slab[JBD2_MAX_SLABS]; static const char *jbd2_slab_names[JBD2_MAX_SLABS] = { "jbd2_1k", "jbd2_2k", "jbd2_4k", "jbd2_8k", "jbd2_16k", "jbd2_32k", "jbd2_64k", "jbd2_128k" }; static void jbd2_journal_destroy_slabs(void) { int i; for (i = 0; i < JBD2_MAX_SLABS; i++) { kmem_cache_destroy(jbd2_slab[i]); jbd2_slab[i] = NULL; } } static int jbd2_journal_create_slab(size_t size) { static DEFINE_MUTEX(jbd2_slab_create_mutex); int i = order_base_2(size) - 10; size_t slab_size; if (size == PAGE_SIZE) return 0; if (i >= JBD2_MAX_SLABS) return -EINVAL; if (unlikely(i < 0)) i = 0; mutex_lock(&jbd2_slab_create_mutex); if (jbd2_slab[i]) { mutex_unlock(&jbd2_slab_create_mutex); return 0; /* Already created */ } slab_size = 1 << (i+10); jbd2_slab[i] = kmem_cache_create(jbd2_slab_names[i], slab_size, slab_size, 0, NULL); mutex_unlock(&jbd2_slab_create_mutex); if (!jbd2_slab[i]) { printk(KERN_EMERG "JBD2: no memory for jbd2_slab cache\n"); return -ENOMEM; } return 0; } static struct kmem_cache *get_slab(size_t size) { int i = order_base_2(size) - 10; BUG_ON(i >= JBD2_MAX_SLABS); if (unlikely(i < 0)) i = 0; BUG_ON(jbd2_slab[i] == NULL); return jbd2_slab[i]; } void *jbd2_alloc(size_t size, gfp_t flags) { void *ptr; BUG_ON(size & (size-1)); /* Must be a power of 2 */ if (size < PAGE_SIZE) ptr = kmem_cache_alloc(get_slab(size), flags); else ptr = (void *)__get_free_pages(flags, get_order(size)); /* Check alignment; SLUB has gotten this wrong in the past, * and this can lead to user data corruption! */ BUG_ON(((unsigned long) ptr) & (size-1)); return ptr; } void jbd2_free(void *ptr, size_t size) { if (size < PAGE_SIZE) kmem_cache_free(get_slab(size), ptr); else free_pages((unsigned long)ptr, get_order(size)); }; /* * Journal_head storage management */ static struct kmem_cache *jbd2_journal_head_cache; #ifdef CONFIG_JBD2_DEBUG static atomic_t nr_journal_heads = ATOMIC_INIT(0); #endif static int __init jbd2_journal_init_journal_head_cache(void) { J_ASSERT(!jbd2_journal_head_cache); jbd2_journal_head_cache = kmem_cache_create("jbd2_journal_head", sizeof(struct journal_head), 0, /* offset */ SLAB_TEMPORARY | SLAB_TYPESAFE_BY_RCU, NULL); /* ctor */ if (!jbd2_journal_head_cache) { printk(KERN_EMERG "JBD2: no memory for journal_head cache\n"); return -ENOMEM; } return 0; } static void jbd2_journal_destroy_journal_head_cache(void) { kmem_cache_destroy(jbd2_journal_head_cache); jbd2_journal_head_cache = NULL; } /* * journal_head splicing and dicing */ static struct journal_head *journal_alloc_journal_head(void) { struct journal_head *ret; #ifdef CONFIG_JBD2_DEBUG atomic_inc(&nr_journal_heads); #endif ret = kmem_cache_zalloc(jbd2_journal_head_cache, GFP_NOFS); if (!ret) { jbd_debug(1, "out of memory for journal_head\n"); pr_notice_ratelimited("ENOMEM in %s, retrying.\n", __func__); ret = kmem_cache_zalloc(jbd2_journal_head_cache, GFP_NOFS | __GFP_NOFAIL); } if (ret) spin_lock_init(&ret->b_state_lock); return ret; } static void journal_free_journal_head(struct journal_head *jh) { #ifdef CONFIG_JBD2_DEBUG atomic_dec(&nr_journal_heads); memset(jh, JBD2_POISON_FREE, sizeof(*jh)); #endif kmem_cache_free(jbd2_journal_head_cache, jh); } /* * A journal_head is attached to a buffer_head whenever JBD has an * interest in the buffer. * * Whenever a buffer has an attached journal_head, its ->b_state:BH_JBD bit * is set. This bit is tested in core kernel code where we need to take * JBD-specific actions. Testing the zeroness of ->b_private is not reliable * there. * * When a buffer has its BH_JBD bit set, its ->b_count is elevated by one. * * When a buffer has its BH_JBD bit set it is immune from being released by * core kernel code, mainly via ->b_count. * * A journal_head is detached from its buffer_head when the journal_head's * b_jcount reaches zero. Running transaction (b_transaction) and checkpoint * transaction (b_cp_transaction) hold their references to b_jcount. * * Various places in the kernel want to attach a journal_head to a buffer_head * _before_ attaching the journal_head to a transaction. To protect the * journal_head in this situation, jbd2_journal_add_journal_head elevates the * journal_head's b_jcount refcount by one. The caller must call * jbd2_journal_put_journal_head() to undo this. * * So the typical usage would be: * * (Attach a journal_head if needed. Increments b_jcount) * struct journal_head *jh = jbd2_journal_add_journal_head(bh); * ... * (Get another reference for transaction) * jbd2_journal_grab_journal_head(bh); * jh->b_transaction = xxx; * (Put original reference) * jbd2_journal_put_journal_head(jh); */ /* * Give a buffer_head a journal_head. * * May sleep. */ struct journal_head *jbd2_journal_add_journal_head(struct buffer_head *bh) { struct journal_head *jh; struct journal_head *new_jh = NULL; repeat: if (!buffer_jbd(bh)) new_jh = journal_alloc_journal_head(); jbd_lock_bh_journal_head(bh); if (buffer_jbd(bh)) { jh = bh2jh(bh); } else { J_ASSERT_BH(bh, (atomic_read(&bh->b_count) > 0) || (bh->b_page && bh->b_page->mapping)); if (!new_jh) { jbd_unlock_bh_journal_head(bh); goto repeat; } jh = new_jh; new_jh = NULL; /* We consumed it */ set_buffer_jbd(bh); bh->b_private = jh; jh->b_bh = bh; get_bh(bh); BUFFER_TRACE(bh, "added journal_head"); } jh->b_jcount++; jbd_unlock_bh_journal_head(bh); if (new_jh) journal_free_journal_head(new_jh); return bh->b_private; } /* * Grab a ref against this buffer_head's journal_head. If it ended up not * having a journal_head, return NULL */ struct journal_head *jbd2_journal_grab_journal_head(struct buffer_head *bh) { struct journal_head *jh = NULL; jbd_lock_bh_journal_head(bh); if (buffer_jbd(bh)) { jh = bh2jh(bh); jh->b_jcount++; } jbd_unlock_bh_journal_head(bh); return jh; } static void __journal_remove_journal_head(struct buffer_head *bh) { struct journal_head *jh = bh2jh(bh); J_ASSERT_JH(jh, jh->b_transaction == NULL); J_ASSERT_JH(jh, jh->b_next_transaction == NULL); J_ASSERT_JH(jh, jh->b_cp_transaction == NULL); J_ASSERT_JH(jh, jh->b_jlist == BJ_None); J_ASSERT_BH(bh, buffer_jbd(bh)); J_ASSERT_BH(bh, jh2bh(jh) == bh); BUFFER_TRACE(bh, "remove journal_head"); /* Unlink before dropping the lock */ bh->b_private = NULL; jh->b_bh = NULL; /* debug, really */ clear_buffer_jbd(bh); } static void journal_release_journal_head(struct journal_head *jh, size_t b_size) { if (jh->b_frozen_data) { printk(KERN_WARNING "%s: freeing b_frozen_data\n", __func__); jbd2_free(jh->b_frozen_data, b_size); } if (jh->b_committed_data) { printk(KERN_WARNING "%s: freeing b_committed_data\n", __func__); jbd2_free(jh->b_committed_data, b_size); } journal_free_journal_head(jh); } /* * Drop a reference on the passed journal_head. If it fell to zero then * release the journal_head from the buffer_head. */ void jbd2_journal_put_journal_head(struct journal_head *jh) { struct buffer_head *bh = jh2bh(jh); jbd_lock_bh_journal_head(bh); J_ASSERT_JH(jh, jh->b_jcount > 0); --jh->b_jcount; if (!jh->b_jcount) { __journal_remove_journal_head(bh); jbd_unlock_bh_journal_head(bh); journal_release_journal_head(jh, bh->b_size); __brelse(bh); } else { jbd_unlock_bh_journal_head(bh); } } /* * Initialize jbd inode head */ void jbd2_journal_init_jbd_inode(struct jbd2_inode *jinode, struct inode *inode) { jinode->i_transaction = NULL; jinode->i_next_transaction = NULL; jinode->i_vfs_inode = inode; jinode->i_flags = 0; jinode->i_dirty_start = 0; jinode->i_dirty_end = 0; INIT_LIST_HEAD(&jinode->i_list); } /* * Function to be called before we start removing inode from memory (i.e., * clear_inode() is a fine place to be called from). It removes inode from * transaction's lists. */ void jbd2_journal_release_jbd_inode(journal_t *journal, struct jbd2_inode *jinode) { if (!journal) return; restart: spin_lock(&journal->j_list_lock); /* Is commit writing out inode - we have to wait */ if (jinode->i_flags & JI_COMMIT_RUNNING) { wait_queue_head_t *wq; DEFINE_WAIT_BIT(wait, &jinode->i_flags, __JI_COMMIT_RUNNING); wq = bit_waitqueue(&jinode->i_flags, __JI_COMMIT_RUNNING); prepare_to_wait(wq, &wait.wq_entry, TASK_UNINTERRUPTIBLE); spin_unlock(&journal->j_list_lock); schedule(); finish_wait(wq, &wait.wq_entry); goto restart; } if (jinode->i_transaction) { list_del(&jinode->i_list); jinode->i_transaction = NULL; } spin_unlock(&journal->j_list_lock); } #ifdef CONFIG_PROC_FS #define JBD2_STATS_PROC_NAME "fs/jbd2" static void __init jbd2_create_jbd_stats_proc_entry(void) { proc_jbd2_stats = proc_mkdir(JBD2_STATS_PROC_NAME, NULL); } static void __exit jbd2_remove_jbd_stats_proc_entry(void) { if (proc_jbd2_stats) remove_proc_entry(JBD2_STATS_PROC_NAME, NULL); } #else #define jbd2_create_jbd_stats_proc_entry() do {} while (0) #define jbd2_remove_jbd_stats_proc_entry() do {} while (0) #endif struct kmem_cache *jbd2_handle_cache, *jbd2_inode_cache; static int __init jbd2_journal_init_inode_cache(void) { J_ASSERT(!jbd2_inode_cache); jbd2_inode_cache = KMEM_CACHE(jbd2_inode, 0); if (!jbd2_inode_cache) { pr_emerg("JBD2: failed to create inode cache\n"); return -ENOMEM; } return 0; } static int __init jbd2_journal_init_handle_cache(void) { J_ASSERT(!jbd2_handle_cache); jbd2_handle_cache = KMEM_CACHE(jbd2_journal_handle, SLAB_TEMPORARY); if (!jbd2_handle_cache) { printk(KERN_EMERG "JBD2: failed to create handle cache\n"); return -ENOMEM; } return 0; } static void jbd2_journal_destroy_inode_cache(void) { kmem_cache_destroy(jbd2_inode_cache); jbd2_inode_cache = NULL; } static void jbd2_journal_destroy_handle_cache(void) { kmem_cache_destroy(jbd2_handle_cache); jbd2_handle_cache = NULL; } /* * Module startup and shutdown */ static int __init journal_init_caches(void) { int ret; ret = jbd2_journal_init_revoke_record_cache(); if (ret == 0) ret = jbd2_journal_init_revoke_table_cache(); if (ret == 0) ret = jbd2_journal_init_journal_head_cache(); if (ret == 0) ret = jbd2_journal_init_handle_cache(); if (ret == 0) ret = jbd2_journal_init_inode_cache(); if (ret == 0) ret = jbd2_journal_init_transaction_cache(); return ret; } static void jbd2_journal_destroy_caches(void) { jbd2_journal_destroy_revoke_record_cache(); jbd2_journal_destroy_revoke_table_cache(); jbd2_journal_destroy_journal_head_cache(); jbd2_journal_destroy_handle_cache(); jbd2_journal_destroy_inode_cache(); jbd2_journal_destroy_transaction_cache(); jbd2_journal_destroy_slabs(); } static int __init journal_init(void) { int ret; BUILD_BUG_ON(sizeof(struct journal_superblock_s) != 1024); ret = journal_init_caches(); if (ret == 0) { jbd2_create_jbd_stats_proc_entry(); } else { jbd2_journal_destroy_caches(); } return ret; } static void __exit journal_exit(void) { #ifdef CONFIG_JBD2_DEBUG int n = atomic_read(&nr_journal_heads); if (n) printk(KERN_ERR "JBD2: leaked %d journal_heads!\n", n); #endif jbd2_remove_jbd_stats_proc_entry(); jbd2_journal_destroy_caches(); } MODULE_LICENSE("GPL"); module_init(journal_init); module_exit(journal_exit);
109 36 24 69 20 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 /* SPDX-License-Identifier: GPL-2.0 */ #undef TRACE_SYSTEM #define TRACE_SYSTEM timer #if !defined(_TRACE_TIMER_H) || defined(TRACE_HEADER_MULTI_READ) #define _TRACE_TIMER_H #include <linux/tracepoint.h> #include <linux/hrtimer.h> #include <linux/timer.h> DECLARE_EVENT_CLASS(timer_class, TP_PROTO(struct timer_list *timer), TP_ARGS(timer), TP_STRUCT__entry( __field( void *, timer ) ), TP_fast_assign( __entry->timer = timer; ), TP_printk("timer=%p", __entry->timer) ); /** * timer_init - called when the timer is initialized * @timer: pointer to struct timer_list */ DEFINE_EVENT(timer_class, timer_init, TP_PROTO(struct timer_list *timer), TP_ARGS(timer) ); #define decode_timer_flags(flags) \ __print_flags(flags, "|", \ { TIMER_MIGRATING, "M" }, \ { TIMER_DEFERRABLE, "D" }, \ { TIMER_PINNED, "P" }, \ { TIMER_IRQSAFE, "I" }) /** * timer_start - called when the timer is started * @timer: pointer to struct timer_list * @expires: the timers expiry time */ TRACE_EVENT(timer_start, TP_PROTO(struct timer_list *timer, unsigned long expires, unsigned int flags), TP_ARGS(timer, expires, flags), TP_STRUCT__entry( __field( void *, timer ) __field( void *, function ) __field( unsigned long, expires ) __field( unsigned long, now ) __field( unsigned int, flags ) ), TP_fast_assign( __entry->timer = timer; __entry->function = timer->function; __entry->expires = expires; __entry->now = jiffies; __entry->flags = flags; ), TP_printk("timer=%p function=%ps expires=%lu [timeout=%ld] cpu=%u idx=%u flags=%s", __entry->timer, __entry->function, __entry->expires, (long)__entry->expires - __entry->now, __entry->flags & TIMER_CPUMASK, __entry->flags >> TIMER_ARRAYSHIFT, decode_timer_flags(__entry->flags & TIMER_TRACE_FLAGMASK)) ); /** * timer_expire_entry - called immediately before the timer callback * @timer: pointer to struct timer_list * * Allows to determine the timer latency. */ TRACE_EVENT(timer_expire_entry, TP_PROTO(struct timer_list *timer, unsigned long baseclk), TP_ARGS(timer, baseclk), TP_STRUCT__entry( __field( void *, timer ) __field( unsigned long, now ) __field( void *, function) __field( unsigned long, baseclk ) ), TP_fast_assign( __entry->timer = timer; __entry->now = jiffies; __entry->function = timer->function; __entry->baseclk = baseclk; ), TP_printk("timer=%p function=%ps now=%lu baseclk=%lu", __entry->timer, __entry->function, __entry->now, __entry->baseclk) ); /** * timer_expire_exit - called immediately after the timer callback returns * @timer: pointer to struct timer_list * * When used in combination with the timer_expire_entry tracepoint we can * determine the runtime of the timer callback function. * * NOTE: Do NOT derefernce timer in TP_fast_assign. The pointer might * be invalid. We solely track the pointer. */ DEFINE_EVENT(timer_class, timer_expire_exit, TP_PROTO(struct timer_list *timer), TP_ARGS(timer) ); /** * timer_cancel - called when the timer is canceled * @timer: pointer to struct timer_list */ DEFINE_EVENT(timer_class, timer_cancel, TP_PROTO(struct timer_list *timer), TP_ARGS(timer) ); #define decode_clockid(type) \ __print_symbolic(type, \ { CLOCK_REALTIME, "CLOCK_REALTIME" }, \ { CLOCK_MONOTONIC, "CLOCK_MONOTONIC" }, \ { CLOCK_BOOTTIME, "CLOCK_BOOTTIME" }, \ { CLOCK_TAI, "CLOCK_TAI" }) #define decode_hrtimer_mode(mode) \ __print_symbolic(mode, \ { HRTIMER_MODE_ABS, "ABS" }, \ { HRTIMER_MODE_REL, "REL" }, \ { HRTIMER_MODE_ABS_PINNED, "ABS|PINNED" }, \ { HRTIMER_MODE_REL_PINNED, "REL|PINNED" }, \ { HRTIMER_MODE_ABS_SOFT, "ABS|SOFT" }, \ { HRTIMER_MODE_REL_SOFT, "REL|SOFT" }, \ { HRTIMER_MODE_ABS_PINNED_SOFT, "ABS|PINNED|SOFT" }, \ { HRTIMER_MODE_REL_PINNED_SOFT, "REL|PINNED|SOFT" }) /** * hrtimer_init - called when the hrtimer is initialized * @hrtimer: pointer to struct hrtimer * @clockid: the hrtimers clock * @mode: the hrtimers mode */ TRACE_EVENT(hrtimer_init, TP_PROTO(struct hrtimer *hrtimer, clockid_t clockid, enum hrtimer_mode mode), TP_ARGS(hrtimer, clockid, mode), TP_STRUCT__entry( __field( void *, hrtimer ) __field( clockid_t, clockid ) __field( enum hrtimer_mode, mode ) ), TP_fast_assign( __entry->hrtimer = hrtimer; __entry->clockid = clockid; __entry->mode = mode; ), TP_printk("hrtimer=%p clockid=%s mode=%s", __entry->hrtimer, decode_clockid(__entry->clockid), decode_hrtimer_mode(__entry->mode)) ); /** * hrtimer_start - called when the hrtimer is started * @hrtimer: pointer to struct hrtimer */ TRACE_EVENT(hrtimer_start, TP_PROTO(struct hrtimer *hrtimer, enum hrtimer_mode mode), TP_ARGS(hrtimer, mode), TP_STRUCT__entry( __field( void *, hrtimer ) __field( void *, function ) __field( s64, expires ) __field( s64, softexpires ) __field( enum hrtimer_mode, mode ) ), TP_fast_assign( __entry->hrtimer = hrtimer; __entry->function = hrtimer->function; __entry->expires = hrtimer_get_expires(hrtimer); __entry->softexpires = hrtimer_get_softexpires(hrtimer); __entry->mode = mode; ), TP_printk("hrtimer=%p function=%ps expires=%llu softexpires=%llu " "mode=%s", __entry->hrtimer, __entry->function, (unsigned long long) __entry->expires, (unsigned long long) __entry->softexpires, decode_hrtimer_mode(__entry->mode)) ); /** * hrtimer_expire_entry - called immediately before the hrtimer callback * @hrtimer: pointer to struct hrtimer * @now: pointer to variable which contains current time of the * timers base. * * Allows to determine the timer latency. */ TRACE_EVENT(hrtimer_expire_entry, TP_PROTO(struct hrtimer *hrtimer, ktime_t *now), TP_ARGS(hrtimer, now), TP_STRUCT__entry( __field( void *, hrtimer ) __field( s64, now ) __field( void *, function) ), TP_fast_assign( __entry->hrtimer = hrtimer; __entry->now = *now; __entry->function = hrtimer->function; ), TP_printk("hrtimer=%p function=%ps now=%llu", __entry->hrtimer, __entry->function, (unsigned long long) __entry->now) ); DECLARE_EVENT_CLASS(hrtimer_class, TP_PROTO(struct hrtimer *hrtimer), TP_ARGS(hrtimer), TP_STRUCT__entry( __field( void *, hrtimer ) ), TP_fast_assign( __entry->hrtimer = hrtimer; ), TP_printk("hrtimer=%p", __entry->hrtimer) ); /** * hrtimer_expire_exit - called immediately after the hrtimer callback returns * @hrtimer: pointer to struct hrtimer * * When used in combination with the hrtimer_expire_entry tracepoint we can * determine the runtime of the callback function. */ DEFINE_EVENT(hrtimer_class, hrtimer_expire_exit, TP_PROTO(struct hrtimer *hrtimer), TP_ARGS(hrtimer) ); /** * hrtimer_cancel - called when the hrtimer is canceled * @hrtimer: pointer to struct hrtimer */ DEFINE_EVENT(hrtimer_class, hrtimer_cancel, TP_PROTO(struct hrtimer *hrtimer), TP_ARGS(hrtimer) ); /** * itimer_state - called when itimer is started or canceled * @which: name of the interval timer * @value: the itimers value, itimer is canceled if value->it_value is * zero, otherwise it is started * @expires: the itimers expiry time */ TRACE_EVENT(itimer_state, TP_PROTO(int which, const struct itimerspec64 *const value, unsigned long long expires), TP_ARGS(which, value, expires), TP_STRUCT__entry( __field( int, which ) __field( unsigned long long, expires ) __field( long, value_sec ) __field( long, value_nsec ) __field( long, interval_sec ) __field( long, interval_nsec ) ), TP_fast_assign( __entry->which = which; __entry->expires = expires; __entry->value_sec = value->it_value.tv_sec; __entry->value_nsec = value->it_value.tv_nsec; __entry->interval_sec = value->it_interval.tv_sec; __entry->interval_nsec = value->it_interval.tv_nsec; ), TP_printk("which=%d expires=%llu it_value=%ld.%06ld it_interval=%ld.%06ld", __entry->which, __entry->expires, __entry->value_sec, __entry->value_nsec / NSEC_PER_USEC, __entry->interval_sec, __entry->interval_nsec / NSEC_PER_USEC) ); /** * itimer_expire - called when itimer expires * @which: type of the interval timer * @pid: pid of the process which owns the timer * @now: current time, used to calculate the latency of itimer */ TRACE_EVENT(itimer_expire, TP_PROTO(int which, struct pid *pid, unsigned long long now), TP_ARGS(which, pid, now), TP_STRUCT__entry( __field( int , which ) __field( pid_t, pid ) __field( unsigned long long, now ) ), TP_fast_assign( __entry->which = which; __entry->now = now; __entry->pid = pid_nr(pid); ), TP_printk("which=%d pid=%d now=%llu", __entry->which, (int) __entry->pid, __entry->now) ); #ifdef CONFIG_NO_HZ_COMMON #define TICK_DEP_NAMES \ tick_dep_mask_name(NONE) \ tick_dep_name(POSIX_TIMER) \ tick_dep_name(PERF_EVENTS) \ tick_dep_name(SCHED) \ tick_dep_name(CLOCK_UNSTABLE) \ tick_dep_name_end(RCU) #undef tick_dep_name #undef tick_dep_mask_name #undef tick_dep_name_end /* The MASK will convert to their bits and they need to be processed too */ #define tick_dep_name(sdep) TRACE_DEFINE_ENUM(TICK_DEP_BIT_##sdep); \ TRACE_DEFINE_ENUM(TICK_DEP_MASK_##sdep); #define tick_dep_name_end(sdep) TRACE_DEFINE_ENUM(TICK_DEP_BIT_##sdep); \ TRACE_DEFINE_ENUM(TICK_DEP_MASK_##sdep); /* NONE only has a mask defined for it */ #define tick_dep_mask_name(sdep) TRACE_DEFINE_ENUM(TICK_DEP_MASK_##sdep); TICK_DEP_NAMES #undef tick_dep_name #undef tick_dep_mask_name #undef tick_dep_name_end #define tick_dep_name(sdep) { TICK_DEP_MASK_##sdep, #sdep }, #define tick_dep_mask_name(sdep) { TICK_DEP_MASK_##sdep, #sdep }, #define tick_dep_name_end(sdep) { TICK_DEP_MASK_##sdep, #sdep } #define show_tick_dep_name(val) \ __print_symbolic(val, TICK_DEP_NAMES) TRACE_EVENT(tick_stop, TP_PROTO(int success, int dependency), TP_ARGS(success, dependency), TP_STRUCT__entry( __field( int , success ) __field( int , dependency ) ), TP_fast_assign( __entry->success = success; __entry->dependency = dependency; ), TP_printk("success=%d dependency=%s", __entry->success, \ show_tick_dep_name(__entry->dependency)) ); #endif #endif /* _TRACE_TIMER_H */ /* This part must be outside protection */ #include <trace/define_trace.h>
225 226 4 218 220 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 // SPDX-License-Identifier: GPL-2.0 /* * linux/kernel/capability.c * * Copyright (C) 1997 Andrew Main <zefram@fysh.org> * * Integrated into 2.1.97+, Andrew G. Morgan <morgan@kernel.org> * 30 May 2002: Cleanup, Robert M. Love <rml@tech9.net> */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/audit.h> #include <linux/capability.h> #include <linux/mm.h> #include <linux/export.h> #include <linux/security.h> #include <linux/syscalls.h> #include <linux/pid_namespace.h> #include <linux/user_namespace.h> #include <linux/uaccess.h> /* * Leveraged for setting/resetting capabilities */ const kernel_cap_t __cap_empty_set = CAP_EMPTY_SET; EXPORT_SYMBOL(__cap_empty_set); int file_caps_enabled = 1; static int __init file_caps_disable(char *str) { file_caps_enabled = 0; return 1; } __setup("no_file_caps", file_caps_disable); #ifdef CONFIG_MULTIUSER /* * More recent versions of libcap are available from: * * http://www.kernel.org/pub/linux/libs/security/linux-privs/ */ static void warn_legacy_capability_use(void) { char name[sizeof(current->comm)]; pr_info_once("warning: `%s' uses 32-bit capabilities (legacy support in use)\n", get_task_comm(name, current)); } /* * Version 2 capabilities worked fine, but the linux/capability.h file * that accompanied their introduction encouraged their use without * the necessary user-space source code changes. As such, we have * created a version 3 with equivalent functionality to version 2, but * with a header change to protect legacy source code from using * version 2 when it wanted to use version 1. If your system has code * that trips the following warning, it is using version 2 specific * capabilities and may be doing so insecurely. * * The remedy is to either upgrade your version of libcap (to 2.10+, * if the application is linked against it), or recompile your * application with modern kernel headers and this warning will go * away. */ static void warn_deprecated_v2(void) { char name[sizeof(current->comm)]; pr_info_once("warning: `%s' uses deprecated v2 capabilities in a way that may be insecure\n", get_task_comm(name, current)); } /* * Version check. Return the number of u32s in each capability flag * array, or a negative value on error. */ static int cap_validate_magic(cap_user_header_t header, unsigned *tocopy) { __u32 version; if (get_user(version, &header->version)) return -EFAULT; switch (version) { case _LINUX_CAPABILITY_VERSION_1: warn_legacy_capability_use(); *tocopy = _LINUX_CAPABILITY_U32S_1; break; case _LINUX_CAPABILITY_VERSION_2: warn_deprecated_v2(); fallthrough; /* v3 is otherwise equivalent to v2 */ case _LINUX_CAPABILITY_VERSION_3: *tocopy = _LINUX_CAPABILITY_U32S_3; break; default: if (put_user((u32)_KERNEL_CAPABILITY_VERSION, &header->version)) return -EFAULT; return -EINVAL; } return 0; } /* * The only thing that can change the capabilities of the current * process is the current process. As such, we can't be in this code * at the same time as we are in the process of setting capabilities * in this process. The net result is that we can limit our use of * locks to when we are reading the caps of another process. */ static inline int cap_get_target_pid(pid_t pid, kernel_cap_t *pEp, kernel_cap_t *pIp, kernel_cap_t *pPp) { int ret; if (pid && (pid != task_pid_vnr(current))) { struct task_struct *target; rcu_read_lock(); target = find_task_by_vpid(pid); if (!target) ret = -ESRCH; else ret = security_capget(target, pEp, pIp, pPp); rcu_read_unlock(); } else ret = security_capget(current, pEp, pIp, pPp); return ret; } /** * sys_capget - get the capabilities of a given process. * @header: pointer to struct that contains capability version and * target pid data * @dataptr: pointer to struct that contains the effective, permitted, * and inheritable capabilities that are returned * * Returns 0 on success and < 0 on error. */ SYSCALL_DEFINE2(capget, cap_user_header_t, header, cap_user_data_t, dataptr) { int ret = 0; pid_t pid; unsigned tocopy; kernel_cap_t pE, pI, pP; ret = cap_validate_magic(header, &tocopy); if ((dataptr == NULL) || (ret != 0)) return ((dataptr == NULL) && (ret == -EINVAL)) ? 0 : ret; if (get_user(pid, &header->pid)) return -EFAULT; if (pid < 0) return -EINVAL; ret = cap_get_target_pid(pid, &pE, &pI, &pP); if (!ret) { struct __user_cap_data_struct kdata[_KERNEL_CAPABILITY_U32S]; unsigned i; for (i = 0; i < tocopy; i++) { kdata[i].effective = pE.cap[i]; kdata[i].permitted = pP.cap[i]; kdata[i].inheritable = pI.cap[i]; } /* * Note, in the case, tocopy < _KERNEL_CAPABILITY_U32S, * we silently drop the upper capabilities here. This * has the effect of making older libcap * implementations implicitly drop upper capability * bits when they perform a: capget/modify/capset * sequence. * * This behavior is considered fail-safe * behavior. Upgrading the application to a newer * version of libcap will enable access to the newer * capabilities. * * An alternative would be to return an error here * (-ERANGE), but that causes legacy applications to * unexpectedly fail; the capget/modify/capset aborts * before modification is attempted and the application * fails. */ if (copy_to_user(dataptr, kdata, tocopy * sizeof(struct __user_cap_data_struct))) { return -EFAULT; } } return ret; } /** * sys_capset - set capabilities for a process or (*) a group of processes * @header: pointer to struct that contains capability version and * target pid data * @data: pointer to struct that contains the effective, permitted, * and inheritable capabilities * * Set capabilities for the current process only. The ability to any other * process(es) has been deprecated and removed. * * The restrictions on setting capabilities are specified as: * * I: any raised capabilities must be a subset of the old permitted * P: any raised capabilities must be a subset of the old permitted * E: must be set to a subset of new permitted * * Returns 0 on success and < 0 on error. */ SYSCALL_DEFINE2(capset, cap_user_header_t, header, const cap_user_data_t, data) { struct __user_cap_data_struct kdata[_KERNEL_CAPABILITY_U32S]; unsigned i, tocopy, copybytes; kernel_cap_t inheritable, permitted, effective; struct cred *new; int ret; pid_t pid; ret = cap_validate_magic(header, &tocopy); if (ret != 0) return ret; if (get_user(pid, &header->pid)) return -EFAULT; /* may only affect current now */ if (pid != 0 && pid != task_pid_vnr(current)) return -EPERM; copybytes = tocopy * sizeof(struct __user_cap_data_struct); if (copybytes > sizeof(kdata)) return -EFAULT; if (copy_from_user(&kdata, data, copybytes)) return -EFAULT; for (i = 0; i < tocopy; i++) { effective.cap[i] = kdata[i].effective; permitted.cap[i] = kdata[i].permitted; inheritable.cap[i] = kdata[i].inheritable; } while (i < _KERNEL_CAPABILITY_U32S) { effective.cap[i] = 0; permitted.cap[i] = 0; inheritable.cap[i] = 0; i++; } effective.cap[CAP_LAST_U32] &= CAP_LAST_U32_VALID_MASK; permitted.cap[CAP_LAST_U32] &= CAP_LAST_U32_VALID_MASK; inheritable.cap[CAP_LAST_U32] &= CAP_LAST_U32_VALID_MASK; new = prepare_creds(); if (!new) return -ENOMEM; ret = security_capset(new, current_cred(), &effective, &inheritable, &permitted); if (ret < 0) goto error; audit_log_capset(new, current_cred()); return commit_creds(new); error: abort_creds(new); return ret; } /** * has_ns_capability - Does a task have a capability in a specific user ns * @t: The task in question * @ns: target user namespace * @cap: The capability to be tested for * * Return true if the specified task has the given superior capability * currently in effect to the specified user namespace, false if not. * * Note that this does not set PF_SUPERPRIV on the task. */ bool has_ns_capability(struct task_struct *t, struct user_namespace *ns, int cap) { int ret; rcu_read_lock(); ret = security_capable(__task_cred(t), ns, cap, CAP_OPT_NONE); rcu_read_unlock(); return (ret == 0); } /** * has_capability - Does a task have a capability in init_user_ns * @t: The task in question * @cap: The capability to be tested for * * Return true if the specified task has the given superior capability * currently in effect to the initial user namespace, false if not. * * Note that this does not set PF_SUPERPRIV on the task. */ bool has_capability(struct task_struct *t, int cap) { return has_ns_capability(t, &init_user_ns, cap); } EXPORT_SYMBOL(has_capability); /** * has_ns_capability_noaudit - Does a task have a capability (unaudited) * in a specific user ns. * @t: The task in question * @ns: target user namespace * @cap: The capability to be tested for * * Return true if the specified task has the given superior capability * currently in effect to the specified user namespace, false if not. * Do not write an audit message for the check. * * Note that this does not set PF_SUPERPRIV on the task. */ bool has_ns_capability_noaudit(struct task_struct *t, struct user_namespace *ns, int cap) { int ret; rcu_read_lock(); ret = security_capable(__task_cred(t), ns, cap, CAP_OPT_NOAUDIT); rcu_read_unlock(); return (ret == 0); } /** * has_capability_noaudit - Does a task have a capability (unaudited) in the * initial user ns * @t: The task in question * @cap: The capability to be tested for * * Return true if the specified task has the given superior capability * currently in effect to init_user_ns, false if not. Don't write an * audit message for the check. * * Note that this does not set PF_SUPERPRIV on the task. */ bool has_capability_noaudit(struct task_struct *t, int cap) { return has_ns_capability_noaudit(t, &init_user_ns, cap); } static bool ns_capable_common(struct user_namespace *ns, int cap, unsigned int opts) { int capable; if (unlikely(!cap_valid(cap))) { pr_crit("capable() called with invalid cap=%u\n", cap); BUG(); } capable = security_capable(current_cred(), ns, cap, opts); if (capable == 0) { current->flags |= PF_SUPERPRIV; return true; } return false; } /** * ns_capable - Determine if the current task has a superior capability in effect * @ns: The usernamespace we want the capability in * @cap: The capability to be tested for * * Return true if the current task has the given superior capability currently * available for use, false if not. * * This sets PF_SUPERPRIV on the task if the capability is available on the * assumption that it's about to be used. */ bool ns_capable(struct user_namespace *ns, int cap) { return ns_capable_common(ns, cap, CAP_OPT_NONE); } EXPORT_SYMBOL(ns_capable); /** * ns_capable_noaudit - Determine if the current task has a superior capability * (unaudited) in effect * @ns: The usernamespace we want the capability in * @cap: The capability to be tested for * * Return true if the current task has the given superior capability currently * available for use, false if not. * * This sets PF_SUPERPRIV on the task if the capability is available on the * assumption that it's about to be used. */ bool ns_capable_noaudit(struct user_namespace *ns, int cap) { return ns_capable_common(ns, cap, CAP_OPT_NOAUDIT); } EXPORT_SYMBOL(ns_capable_noaudit); /** * ns_capable_setid - Determine if the current task has a superior capability * in effect, while signalling that this check is being done from within a * setid or setgroups syscall. * @ns: The usernamespace we want the capability in * @cap: The capability to be tested for * * Return true if the current task has the given superior capability currently * available for use, false if not. * * This sets PF_SUPERPRIV on the task if the capability is available on the * assumption that it's about to be used. */ bool ns_capable_setid(struct user_namespace *ns, int cap) { return ns_capable_common(ns, cap, CAP_OPT_INSETID); } EXPORT_SYMBOL(ns_capable_setid); /** * capable - Determine if the current task has a superior capability in effect * @cap: The capability to be tested for * * Return true if the current task has the given superior capability currently * available for use, false if not. * * This sets PF_SUPERPRIV on the task if the capability is available on the * assumption that it's about to be used. */ bool capable(int cap) { return ns_capable(&init_user_ns, cap); } EXPORT_SYMBOL(capable); #endif /* CONFIG_MULTIUSER */ /** * file_ns_capable - Determine if the file's opener had a capability in effect * @file: The file we want to check * @ns: The usernamespace we want the capability in * @cap: The capability to be tested for * * Return true if task that opened the file had a capability in effect * when the file was opened. * * This does not set PF_SUPERPRIV because the caller may not * actually be privileged. */ bool file_ns_capable(const struct file *file, struct user_namespace *ns, int cap) { if (WARN_ON_ONCE(!cap_valid(cap))) return false; if (security_capable(file->f_cred, ns, cap, CAP_OPT_NONE) == 0) return true; return false; } EXPORT_SYMBOL(file_ns_capable); /** * privileged_wrt_inode_uidgid - Do capabilities in the namespace work over the inode? * @ns: The user namespace in question * @inode: The inode in question * * Return true if the inode uid and gid are within the namespace. */ bool privileged_wrt_inode_uidgid(struct user_namespace *ns, const struct inode *inode) { return kuid_has_mapping(ns, inode->i_uid) && kgid_has_mapping(ns, inode->i_gid); } /** * capable_wrt_inode_uidgid - Check nsown_capable and uid and gid mapped * @inode: The inode in question * @cap: The capability in question * * Return true if the current task has the given capability targeted at * its own user namespace and that the given inode's uid and gid are * mapped into the current user namespace. */ bool capable_wrt_inode_uidgid(const struct inode *inode, int cap) { struct user_namespace *ns = current_user_ns(); return ns_capable(ns, cap) && privileged_wrt_inode_uidgid(ns, inode); } EXPORT_SYMBOL(capable_wrt_inode_uidgid); /** * ptracer_capable - Determine if the ptracer holds CAP_SYS_PTRACE in the namespace * @tsk: The task that may be ptraced * @ns: The user namespace to search for CAP_SYS_PTRACE in * * Return true if the task that is ptracing the current task had CAP_SYS_PTRACE * in the specified user namespace. */ bool ptracer_capable(struct task_struct *tsk, struct user_namespace *ns) { int ret = 0; /* An absent tracer adds no restrictions */ const struct cred *cred; rcu_read_lock(); cred = rcu_dereference(tsk->ptracer_cred); if (cred) ret = security_capable(cred, ns, CAP_SYS_PTRACE, CAP_OPT_NOAUDIT); rcu_read_unlock(); return (ret == 0); }
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 /* SPDX-License-Identifier: GPL-2.0-or-later */ /* * inet6 interface/address list definitions * Linux INET6 implementation * * Authors: * Pedro Roque <roque@di.fc.ul.pt> */ #ifndef _NET_IF_INET6_H #define _NET_IF_INET6_H #include <net/snmp.h> #include <linux/ipv6.h> #include <linux/refcount.h> /* inet6_dev.if_flags */ #define IF_RA_OTHERCONF 0x80 #define IF_RA_MANAGED 0x40 #define IF_RA_RCVD 0x20 #define IF_RS_SENT 0x10 #define IF_READY 0x80000000 /* prefix flags */ #define IF_PREFIX_ONLINK 0x01 #define IF_PREFIX_AUTOCONF 0x02 enum { INET6_IFADDR_STATE_PREDAD, INET6_IFADDR_STATE_DAD, INET6_IFADDR_STATE_POSTDAD, INET6_IFADDR_STATE_ERRDAD, INET6_IFADDR_STATE_DEAD, }; struct inet6_ifaddr { struct in6_addr addr; __u32 prefix_len; __u32 rt_priority; /* In seconds, relative to tstamp. Expiry is at tstamp + HZ * lft. */ __u32 valid_lft; __u32 prefered_lft; refcount_t refcnt; spinlock_t lock; int state; __u32 flags; __u8 dad_probes; __u8 stable_privacy_retry; __u16 scope; __u64 dad_nonce; unsigned long cstamp; /* created timestamp */ unsigned long tstamp; /* updated timestamp */ struct delayed_work dad_work; struct inet6_dev *idev; struct fib6_info *rt; struct hlist_node addr_lst; struct list_head if_list; struct list_head tmp_list; struct inet6_ifaddr *ifpub; int regen_count; bool tokenized; struct rcu_head rcu; struct in6_addr peer_addr; }; struct ip6_sf_socklist { unsigned int sl_max; unsigned int sl_count; struct in6_addr sl_addr[]; }; #define IP6_SFLSIZE(count) (sizeof(struct ip6_sf_socklist) + \ (count) * sizeof(struct in6_addr)) #define IP6_SFBLOCK 10 /* allocate this many at once */ struct ipv6_mc_socklist { struct in6_addr addr; int ifindex; unsigned int sfmode; /* MCAST_{INCLUDE,EXCLUDE} */ struct ipv6_mc_socklist __rcu *next; rwlock_t sflock; struct ip6_sf_socklist *sflist; struct rcu_head rcu; }; struct ip6_sf_list { struct ip6_sf_list *sf_next; struct in6_addr sf_addr; unsigned long sf_count[2]; /* include/exclude counts */ unsigned char sf_gsresp; /* include in g & s response? */ unsigned char sf_oldin; /* change state */ unsigned char sf_crcount; /* retrans. left to send */ }; #define MAF_TIMER_RUNNING 0x01 #define MAF_LAST_REPORTER 0x02 #define MAF_LOADED 0x04 #define MAF_NOREPORT 0x08 #define MAF_GSQUERY 0x10 struct ifmcaddr6 { struct in6_addr mca_addr; struct inet6_dev *idev; struct ifmcaddr6 *next; struct ip6_sf_list *mca_sources; struct ip6_sf_list *mca_tomb; unsigned int mca_sfmode; unsigned char mca_crcount; unsigned long mca_sfcount[2]; struct timer_list mca_timer; unsigned int mca_flags; int mca_users; refcount_t mca_refcnt; spinlock_t mca_lock; unsigned long mca_cstamp; unsigned long mca_tstamp; }; /* Anycast stuff */ struct ipv6_ac_socklist { struct in6_addr acl_addr; int acl_ifindex; struct ipv6_ac_socklist *acl_next; }; struct ifacaddr6 { struct in6_addr aca_addr; struct fib6_info *aca_rt; struct ifacaddr6 *aca_next; struct hlist_node aca_addr_lst; int aca_users; refcount_t aca_refcnt; unsigned long aca_cstamp; unsigned long aca_tstamp; struct rcu_head rcu; }; #define IFA_HOST IPV6_ADDR_LOOPBACK #define IFA_LINK IPV6_ADDR_LINKLOCAL #define IFA_SITE IPV6_ADDR_SITELOCAL struct ipv6_devstat { struct proc_dir_entry *proc_dir_entry; DEFINE_SNMP_STAT(struct ipstats_mib, ipv6); DEFINE_SNMP_STAT_ATOMIC(struct icmpv6_mib_device, icmpv6dev); DEFINE_SNMP_STAT_ATOMIC(struct icmpv6msg_mib_device, icmpv6msgdev); }; struct inet6_dev { struct net_device *dev; struct list_head addr_list; struct ifmcaddr6 *mc_list; struct ifmcaddr6 *mc_tomb; spinlock_t mc_lock; unsigned char mc_qrv; /* Query Robustness Variable */ unsigned char mc_gq_running; unsigned char mc_ifc_count; unsigned char mc_dad_count; unsigned long mc_v1_seen; /* Max time we stay in MLDv1 mode */ unsigned long mc_qi; /* Query Interval */ unsigned long mc_qri; /* Query Response Interval */ unsigned long mc_maxdelay; struct timer_list mc_gq_timer; /* general query timer */ struct timer_list mc_ifc_timer; /* interface change timer */ struct timer_list mc_dad_timer; /* dad complete mc timer */ struct ifacaddr6 *ac_list; rwlock_t lock; refcount_t refcnt; __u32 if_flags; int dead; u32 desync_factor; struct list_head tempaddr_list; struct in6_addr token; struct neigh_parms *nd_parms; struct ipv6_devconf cnf; struct ipv6_devstat stats; struct timer_list rs_timer; __s32 rs_interval; /* in jiffies */ __u8 rs_probes; unsigned long tstamp; /* ipv6InterfaceTable update timestamp */ struct rcu_head rcu; }; static inline void ipv6_eth_mc_map(const struct in6_addr *addr, char *buf) { /* * +-------+-------+-------+-------+-------+-------+ * | 33 | 33 | DST13 | DST14 | DST15 | DST16 | * +-------+-------+-------+-------+-------+-------+ */ buf[0]= 0x33; buf[1]= 0x33; memcpy(buf + 2, &addr->s6_addr32[3], sizeof(__u32)); } static inline void ipv6_arcnet_mc_map(const struct in6_addr *addr, char *buf) { buf[0] = 0x00; } static inline void ipv6_ib_mc_map(const struct in6_addr *addr, const unsigned char *broadcast, char *buf) { unsigned char scope = broadcast[5] & 0xF; buf[0] = 0; /* Reserved */ buf[1] = 0xff; /* Multicast QPN */ buf[2] = 0xff; buf[3] = 0xff; buf[4] = 0xff; buf[5] = 0x10 | scope; /* scope from broadcast address */ buf[6] = 0x60; /* IPv6 signature */ buf[7] = 0x1b; buf[8] = broadcast[8]; /* P_Key */ buf[9] = broadcast[9]; memcpy(buf + 10, addr->s6_addr + 6, 10); } static inline int ipv6_ipgre_mc_map(const struct in6_addr *addr, const unsigned char *broadcast, char *buf) { if ((broadcast[0] | broadcast[1] | broadcast[2] | broadcast[3]) != 0) { memcpy(buf, broadcast, 4); } else { /* v4mapped? */ if ((addr->s6_addr32[0] | addr->s6_addr32[1] | (addr->s6_addr32[2] ^ htonl(0x0000ffff))) != 0) return -EINVAL; memcpy(buf, &addr->s6_addr32[3], 4); } return 0; } #endif
38 28 28 28 23 22 24 14 45 4 10 10 45 11 11 1 29 28 29 7 7 29 29 17 29 19 3 15 5 15 5 10 6 10 10 11 15 4 14 14 14 14 1 3 4 1 1 3 15 32 17 17 8 16 1 21 25 7 7 8 8 7 29 29 9 15 29 29 29 29 23 11 20 29 3 11 11 5 5 11 26 29 13 12 28 35 7 33 28 27 27 33 20 14 14 14 12 12 10 10 14 20 19 30 24 24 24 24 24 13 5 13 20 2 29 21 21 13 21 30 12 12 12 4 4 4 15 7 3 4 4 4 2 8 2 2 15 1 2 1 1 3 10 9 9 8 8 10 8 1 1 1 1 1 1 1 1 1 1 1 1 4 1 1 4 4 3 1 1 4 1 4 7 7 23 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 2209 2210 2211 2212 2213 2214 2215 2216 2217 2218 2219 2220 2221 2222 2223 2224 2225 2226 2227 2228 2229 2230 2231 2232 2233 2234 2235 2236 2237 2238 2239 2240 2241 2242 2243 2244 2245 2246 2247 2248 2249 2250 2251 2252 2253 2254 2255 2256 2257 2258 2259 2260 2261 2262 2263 2264 2265 2266 2267 2268 2269 2270 2271 2272 2273 2274 2275 2276 2277 2278 2279 2280 2281 2282 2283 2284 2285 2286 2287 2288 2289 2290 2291 2292 2293 2294 2295 2296 2297 2298 2299 2300 2301 2302 2303 2304 2305 2306 2307 2308 2309 2310 2311 2312 2313 2314 2315 2316 2317 2318 2319 2320 2321 2322 2323 2324 2325 2326 2327 2328 2329 2330 2331 2332 2333 2334 2335 2336 2337 2338 2339 2340 2341 2342 2343 2344 2345 2346 2347 2348 2349 2350 2351 2352 2353 2354 2355 2356 2357 2358 2359 2360 2361 2362 2363 2364 2365 2366 2367 2368 2369 2370 2371 2372 2373 2374 2375 2376 2377 2378 2379 2380 2381 2382 2383 2384 2385 2386 2387 2388 2389 2390 2391 2392 2393 2394 2395 2396 2397 2398 2399 2400 2401 2402 2403 2404 2405 2406 2407 2408 2409 2410 2411 2412 2413 2414 2415 2416 2417 2418 2419 2420 2421 2422 2423 2424 2425 2426 2427 2428 2429 2430 2431 2432 2433 2434 2435 2436 2437 2438 2439 2440 2441 2442 2443 2444 2445 2446 2447 2448 2449 2450 2451 2452 2453 2454 2455 2456 2457 2458 2459 2460 2461 2462 2463 2464 2465 2466 2467 2468 2469 2470 2471 2472 2473 2474 2475 2476 2477 2478 2479 2480 2481 2482 2483 2484 2485 2486 2487 2488 2489 2490 2491 2492 2493 2494 2495 2496 2497 2498 2499 2500 2501 2502 2503 2504 2505 2506 2507 2508 2509 2510 2511 2512 2513 2514 2515 2516 2517 2518 2519 2520 2521 2522 2523 2524 2525 2526 2527 2528 2529 2530 2531 2532 2533 2534 2535 2536 2537 2538 2539 2540 2541 2542 2543 2544 2545 2546 2547 2548 2549 2550 2551 2552 2553 2554 2555 2556 2557 2558 2559 2560 2561 2562 2563 2564 2565 2566 2567 2568 2569 2570 2571 2572 2573 2574 2575 2576 2577 2578 2579 2580 2581 2582 2583 2584 2585 2586 2587 2588 2589 2590 2591 2592 2593 2594 2595 2596 2597 2598 2599 2600 2601 2602 2603 2604 2605 2606 2607 2608 2609 2610 2611 2612 2613 2614 2615 2616 2617 2618 2619 2620 2621 2622 2623 2624 2625 2626 2627 2628 2629 2630 2631 2632 2633 2634 2635 2636 2637 2638 2639 2640 2641 2642 2643 2644 2645 2646 2647 2648 2649 2650 2651 2652 2653 2654 2655 2656 2657 2658 2659 2660 2661 2662 2663 2664 2665 2666 2667 2668 2669 2670 2671 2672 2673 2674 2675 2676 2677 2678 2679 2680 2681 2682 2683 2684 2685 2686 2687 2688 2689 2690 2691 2692 2693 2694 2695 2696 2697 2698 2699 2700 2701 2702 2703 2704 2705 2706 2707 2708 2709 2710 2711 2712 2713 2714 2715 2716 2717 2718 2719 2720 2721 2722 2723 2724 2725 2726 2727 2728 2729 2730 2731 2732 2733 2734 2735 2736 2737 2738 2739 2740 2741 2742 2743 2744 2745 2746 2747 2748 2749 2750 2751 2752 2753 2754 2755 2756 2757 2758 2759 2760 2761 2762 2763 2764 2765 2766 2767 2768 2769 2770 2771 2772 2773 2774 2775 2776 2777 2778 2779 2780 2781 2782 2783 2784 2785 2786 2787 2788 2789 2790 2791 2792 2793 2794 2795 2796 2797 2798 2799 2800 2801 2802 2803 2804 2805 2806 2807 2808 2809 2810 2811 2812 2813 2814 2815 2816 2817 2818 2819 2820 2821 2822 2823 2824 2825 2826 2827 2828 2829 2830 2831 2832 2833 2834 2835 2836 2837 2838 2839 2840 2841 2842 2843 2844 2845 2846 2847 2848 2849 2850 2851 2852 2853 2854 2855 2856 2857 2858 2859 2860 2861 2862 2863 2864 2865 2866 2867 2868 2869 2870 2871 2872 2873 2874 2875 2876 2877 2878 2879 2880 2881 2882 2883 2884 2885 2886 2887 2888 2889 2890 2891 2892 2893 2894 2895 2896 2897 2898 2899 2900 2901 2902 2903 2904 2905 2906 2907 2908 2909 2910 2911 2912 2913 2914 2915 2916 2917 2918 2919 2920 2921 2922 2923 2924 2925 2926 2927 2928 2929 2930 2931 2932 2933 2934 2935 2936 2937 2938 2939 2940 2941 2942 2943 2944 2945 2946 2947 2948 2949 2950 2951 2952 2953 2954 2955 2956 2957 2958 2959 2960 2961 2962 2963 2964 2965 2966 2967 2968 2969 2970 2971 2972 2973 2974 2975 2976 2977 2978 2979 2980 2981 2982 2983 2984 2985 2986 2987 2988 2989 2990 2991 2992 2993 2994 2995 2996 2997 2998 2999 3000 3001 3002 3003 3004 3005 3006 3007 3008 3009 3010 3011 3012 3013 3014 3015 3016 3017 3018 3019 3020 3021 3022 3023 3024 3025 3026 3027 3028 3029 3030 3031 3032 3033 3034 3035 3036 3037 3038 3039 3040 3041 3042 3043 3044 3045 3046 3047 3048 3049 3050 3051 3052 3053 3054 3055 3056 3057 3058 3059 3060 3061 3062 3063 3064 3065 3066 3067 3068 3069 3070 3071 3072 3073 3074 3075 3076 3077 3078 3079 3080 3081 3082 3083 3084 3085 3086 3087 3088 3089 3090 3091 3092 3093 3094 3095 3096 3097 3098 3099 3100 3101 3102 3103 3104 3105 3106 3107 3108 3109 3110 3111 3112 3113 3114 3115 3116 3117 3118 3119 3120 3121 3122 3123 3124 3125 3126 3127 3128 3129 3130 3131 3132 3133 3134 3135 3136 3137 3138 3139 3140 3141 3142 3143 3144 3145 3146 3147 3148 3149 3150 3151 3152 3153 3154 3155 3156 3157 3158 3159 3160 3161 3162 3163 3164 3165 3166 3167 3168 3169 3170 3171 3172 3173 3174 3175 3176 3177 3178 3179 3180 3181 3182 3183 3184 3185 3186 3187 3188 3189 3190 3191 3192 3193 3194 3195 3196 3197 3198 3199 3200 3201 3202 3203 3204 3205 3206 3207 3208 3209 3210 3211 3212 3213 3214 3215 3216 3217 3218 3219 3220 3221 3222 3223 3224 3225 3226 3227 3228 3229 3230 3231 3232 3233 3234 3235 3236 3237 3238 3239 3240 3241 3242 3243 3244 3245 3246 3247 3248 3249 3250 3251 3252 3253 3254 3255 3256 3257 3258 3259 3260 3261 3262 3263 3264 3265 3266 3267 3268 3269 3270 3271 3272 3273 3274 3275 3276 3277 3278 3279 3280 3281 3282 3283 3284 3285 3286 3287 3288 3289 3290 3291 3292 3293 3294 3295 3296 3297 3298 3299 3300 3301 3302 3303 3304 3305 3306 3307 3308 3309 3310 3311 3312 3313 3314 3315 3316 3317 3318 3319 3320 3321 3322 3323 3324 3325 3326 3327 3328 3329 3330 3331 3332 3333 3334 3335 3336 3337 3338 3339 3340 3341 3342 3343 3344 3345 3346 3347 3348 3349 3350 3351 3352 3353 3354 3355 3356 3357 3358 3359 3360 3361 3362 3363 3364 3365 3366 3367 3368 3369 3370 3371 3372 3373 3374 3375 3376 3377 3378 3379 3380 3381 3382 3383 3384 3385 3386 3387 3388 3389 3390 3391 3392 3393 3394 3395 3396 3397 3398 3399 3400 3401 3402 3403 3404 3405 3406 3407 3408 3409 3410 3411 3412 3413 3414 3415 3416 3417 3418 3419 3420 3421 3422 3423 3424 3425 3426 3427 3428 3429 3430 3431 3432 3433 3434 3435 3436 3437 3438 3439 3440 3441 3442 3443 3444 3445 3446 3447 3448 3449 3450 3451 3452 3453 3454 3455 3456 3457 3458 3459 3460 3461 3462 3463 3464 3465 3466 3467 3468 3469 3470 3471 3472 3473 3474 3475 3476 3477 3478 3479 3480 3481 3482 3483 3484 3485 3486 3487 3488 3489 3490 3491 3492 3493 3494 3495 3496 3497 3498 3499 3500 3501 3502 3503 3504 3505 3506 3507 3508 3509 3510 3511 3512 3513 3514 3515 3516 3517 3518 3519 3520 3521 3522 3523 3524 3525 3526 3527 3528 3529 3530 3531 3532 3533 3534 3535 3536 3537 3538 3539 3540 3541 3542 3543 3544 3545 3546 3547 3548 3549 3550 3551 3552 3553 3554 3555 3556 3557 3558 3559 3560 3561 3562 3563 3564 3565 3566 3567 3568 3569 3570 3571 3572 3573 3574 3575 3576 3577 3578 3579 3580 3581 3582 3583 3584 3585 3586 3587 3588 3589 3590 3591 3592 3593 3594 3595 3596 3597 3598 3599 3600 3601 3602 3603 3604 3605 3606 3607 3608 3609 3610 3611 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 // SPDX-License-Identifier: GPL-2.0-only /* * xfrm_policy.c * * Changes: * Mitsuru KANDA @USAGI * Kazunori MIYAZAWA @USAGI * Kunihiro Ishiguro <kunihiro@ipinfusion.com> * IPv6 support * Kazunori MIYAZAWA @USAGI * YOSHIFUJI Hideaki * Split up af-specific portion * Derek Atkins <derek@ihtfp.com> Add the post_input processor * */ #include <linux/err.h> #include <linux/slab.h> #include <linux/kmod.h> #include <linux/list.h> #include <linux/spinlock.h> #include <linux/workqueue.h> #include <linux/notifier.h> #include <linux/netdevice.h> #include <linux/netfilter.h> #include <linux/module.h> #include <linux/cache.h> #include <linux/cpu.h> #include <linux/audit.h> #include <linux/rhashtable.h> #include <linux/if_tunnel.h> #include <net/dst.h> #include <net/flow.h> #include <net/xfrm.h> #include <net/ip.h> #if IS_ENABLED(CONFIG_IPV6_MIP6) #include <net/mip6.h> #endif #ifdef CONFIG_XFRM_STATISTICS #include <net/snmp.h> #endif #ifdef CONFIG_XFRM_ESPINTCP #include <net/espintcp.h> #endif #include "xfrm_hash.h" #define XFRM_QUEUE_TMO_MIN ((unsigned)(HZ/10)) #define XFRM_QUEUE_TMO_MAX ((unsigned)(60*HZ)) #define XFRM_MAX_QUEUE_LEN 100 struct xfrm_flo { struct dst_entry *dst_orig; u8 flags; }; /* prefixes smaller than this are stored in lists, not trees. */ #define INEXACT_PREFIXLEN_IPV4 16 #define INEXACT_PREFIXLEN_IPV6 48 struct xfrm_pol_inexact_node { struct rb_node node; union { xfrm_address_t addr; struct rcu_head rcu; }; u8 prefixlen; struct rb_root root; /* the policies matching this node, can be empty list */ struct hlist_head hhead; }; /* xfrm inexact policy search tree: * xfrm_pol_inexact_bin = hash(dir,type,family,if_id); * | * +---- root_d: sorted by daddr:prefix * | | * | xfrm_pol_inexact_node * | | * | +- root: sorted by saddr/prefix * | | | * | | xfrm_pol_inexact_node * | | | * | | + root: unused * | | | * | | + hhead: saddr:daddr policies * | | * | +- coarse policies and all any:daddr policies * | * +---- root_s: sorted by saddr:prefix * | | * | xfrm_pol_inexact_node * | | * | + root: unused * | | * | + hhead: saddr:any policies * | * +---- coarse policies and all any:any policies * * Lookups return four candidate lists: * 1. any:any list from top-level xfrm_pol_inexact_bin * 2. any:daddr list from daddr tree * 3. saddr:daddr list from 2nd level daddr tree * 4. saddr:any list from saddr tree * * This result set then needs to be searched for the policy with * the lowest priority. If two results have same prio, youngest one wins. */ struct xfrm_pol_inexact_key { possible_net_t net; u32 if_id; u16 family; u8 dir, type; }; struct xfrm_pol_inexact_bin { struct xfrm_pol_inexact_key k; struct rhash_head head; /* list containing '*:*' policies */ struct hlist_head hhead; seqcount_spinlock_t count; /* tree sorted by daddr/prefix */ struct rb_root root_d; /* tree sorted by saddr/prefix */ struct rb_root root_s; /* slow path below */ struct list_head inexact_bins; struct rcu_head rcu; }; enum xfrm_pol_inexact_candidate_type { XFRM_POL_CAND_BOTH, XFRM_POL_CAND_SADDR, XFRM_POL_CAND_DADDR, XFRM_POL_CAND_ANY, XFRM_POL_CAND_MAX, }; struct xfrm_pol_inexact_candidates { struct hlist_head *res[XFRM_POL_CAND_MAX]; }; static DEFINE_SPINLOCK(xfrm_if_cb_lock); static struct xfrm_if_cb const __rcu *xfrm_if_cb __read_mostly; static DEFINE_SPINLOCK(xfrm_policy_afinfo_lock); static struct xfrm_policy_afinfo const __rcu *xfrm_policy_afinfo[AF_INET6 + 1] __read_mostly; static struct kmem_cache *xfrm_dst_cache __ro_after_init; static struct rhashtable xfrm_policy_inexact_table; static const struct rhashtable_params xfrm_pol_inexact_params; static void xfrm_init_pmtu(struct xfrm_dst **bundle, int nr); static int stale_bundle(struct dst_entry *dst); static int xfrm_bundle_ok(struct xfrm_dst *xdst); static void xfrm_policy_queue_process(struct timer_list *t); static void __xfrm_policy_link(struct xfrm_policy *pol, int dir); static struct xfrm_policy *__xfrm_policy_unlink(struct xfrm_policy *pol, int dir); static struct xfrm_pol_inexact_bin * xfrm_policy_inexact_lookup(struct net *net, u8 type, u16 family, u8 dir, u32 if_id); static struct xfrm_pol_inexact_bin * xfrm_policy_inexact_lookup_rcu(struct net *net, u8 type, u16 family, u8 dir, u32 if_id); static struct xfrm_policy * xfrm_policy_insert_list(struct hlist_head *chain, struct xfrm_policy *policy, bool excl); static void xfrm_policy_insert_inexact_list(struct hlist_head *chain, struct xfrm_policy *policy); static bool xfrm_policy_find_inexact_candidates(struct xfrm_pol_inexact_candidates *cand, struct xfrm_pol_inexact_bin *b, const xfrm_address_t *saddr, const xfrm_address_t *daddr); static inline bool xfrm_pol_hold_rcu(struct xfrm_policy *policy) { return refcount_inc_not_zero(&policy->refcnt); } static inline bool __xfrm4_selector_match(const struct xfrm_selector *sel, const struct flowi *fl) { const struct flowi4 *fl4 = &fl->u.ip4; return addr4_match(fl4->daddr, sel->daddr.a4, sel->prefixlen_d) && addr4_match(fl4->saddr, sel->saddr.a4, sel->prefixlen_s) && !((xfrm_flowi_dport(fl, &fl4->uli) ^ sel->dport) & sel->dport_mask) && !((xfrm_flowi_sport(fl, &fl4->uli) ^ sel->sport) & sel->sport_mask) && (fl4->flowi4_proto == sel->proto || !sel->proto) && (fl4->flowi4_oif == sel->ifindex || !sel->ifindex); } static inline bool __xfrm6_selector_match(const struct xfrm_selector *sel, const struct flowi *fl) { const struct flowi6 *fl6 = &fl->u.ip6; return addr_match(&fl6->daddr, &sel->daddr, sel->prefixlen_d) && addr_match(&fl6->saddr, &sel->saddr, sel->prefixlen_s) && !((xfrm_flowi_dport(fl, &fl6->uli) ^ sel->dport) & sel->dport_mask) && !((xfrm_flowi_sport(fl, &fl6->uli) ^ sel->sport) & sel->sport_mask) && (fl6->flowi6_proto == sel->proto || !sel->proto) && (fl6->flowi6_oif == sel->ifindex || !sel->ifindex); } bool xfrm_selector_match(const struct xfrm_selector *sel, const struct flowi *fl, unsigned short family) { switch (family) { case AF_INET: return __xfrm4_selector_match(sel, fl); case AF_INET6: return __xfrm6_selector_match(sel, fl); } return false; } static const struct xfrm_policy_afinfo *xfrm_policy_get_afinfo(unsigned short family) { const struct xfrm_policy_afinfo *afinfo; if (unlikely(family >= ARRAY_SIZE(xfrm_policy_afinfo))) return NULL; rcu_read_lock(); afinfo = rcu_dereference(xfrm_policy_afinfo[family]); if (unlikely(!afinfo)) rcu_read_unlock(); return afinfo; } /* Called with rcu_read_lock(). */ static const struct xfrm_if_cb *xfrm_if_get_cb(void) { return rcu_dereference(xfrm_if_cb); } struct dst_entry *__xfrm_dst_lookup(struct net *net, int tos, int oif, const xfrm_address_t *saddr, const xfrm_address_t *daddr, int family, u32 mark) { const struct xfrm_policy_afinfo *afinfo; struct dst_entry *dst; afinfo = xfrm_policy_get_afinfo(family); if (unlikely(afinfo == NULL)) return ERR_PTR(-EAFNOSUPPORT); dst = afinfo->dst_lookup(net, tos, oif, saddr, daddr, mark); rcu_read_unlock(); return dst; } EXPORT_SYMBOL(__xfrm_dst_lookup); static inline struct dst_entry *xfrm_dst_lookup(struct xfrm_state *x, int tos, int oif, xfrm_address_t *prev_saddr, xfrm_address_t *prev_daddr, int family, u32 mark) { struct net *net = xs_net(x); xfrm_address_t *saddr = &x->props.saddr; xfrm_address_t *daddr = &x->id.daddr; struct dst_entry *dst; if (x->type->flags & XFRM_TYPE_LOCAL_COADDR) { saddr = x->coaddr; daddr = prev_daddr; } if (x->type->flags & XFRM_TYPE_REMOTE_COADDR) { saddr = prev_saddr; daddr = x->coaddr; } dst = __xfrm_dst_lookup(net, tos, oif, saddr, daddr, family, mark); if (!IS_ERR(dst)) { if (prev_saddr != saddr) memcpy(prev_saddr, saddr, sizeof(*prev_saddr)); if (prev_daddr != daddr) memcpy(prev_daddr, daddr, sizeof(*prev_daddr)); } return dst; } static inline unsigned long make_jiffies(long secs) { if (secs >= (MAX_SCHEDULE_TIMEOUT-1)/HZ) return MAX_SCHEDULE_TIMEOUT-1; else return secs*HZ; } static void xfrm_policy_timer(struct timer_list *t) { struct xfrm_policy *xp = from_timer(xp, t, timer); time64_t now = ktime_get_real_seconds(); time64_t next = TIME64_MAX; int warn = 0; int dir; read_lock(&xp->lock); if (unlikely(xp->walk.dead)) goto out; dir = xfrm_policy_id2dir(xp->index); if (xp->lft.hard_add_expires_seconds) { time64_t tmo = xp->lft.hard_add_expires_seconds + xp->curlft.add_time - now; if (tmo <= 0) goto expired; if (tmo < next) next = tmo; } if (xp->lft.hard_use_expires_seconds) { time64_t tmo = xp->lft.hard_use_expires_seconds + (xp->curlft.use_time ? : xp->curlft.add_time) - now; if (tmo <= 0) goto expired; if (tmo < next) next = tmo; } if (xp->lft.soft_add_expires_seconds) { time64_t tmo = xp->lft.soft_add_expires_seconds + xp->curlft.add_time - now; if (tmo <= 0) { warn = 1; tmo = XFRM_KM_TIMEOUT; } if (tmo < next) next = tmo; } if (xp->lft.soft_use_expires_seconds) { time64_t tmo = xp->lft.soft_use_expires_seconds + (xp->curlft.use_time ? : xp->curlft.add_time) - now; if (tmo <= 0) { warn = 1; tmo = XFRM_KM_TIMEOUT; } if (tmo < next) next = tmo; } if (warn) km_policy_expired(xp, dir, 0, 0); if (next != TIME64_MAX && !mod_timer(&xp->timer, jiffies + make_jiffies(next))) xfrm_pol_hold(xp); out: read_unlock(&xp->lock); xfrm_pol_put(xp); return; expired: read_unlock(&xp->lock); if (!xfrm_policy_delete(xp, dir)) km_policy_expired(xp, dir, 1, 0); xfrm_pol_put(xp); } /* Allocate xfrm_policy. Not used here, it is supposed to be used by pfkeyv2 * SPD calls. */ struct xfrm_policy *xfrm_policy_alloc(struct net *net, gfp_t gfp) { struct xfrm_policy *policy; policy = kzalloc(sizeof(struct xfrm_policy), gfp); if (policy) { write_pnet(&policy->xp_net, net); INIT_LIST_HEAD(&policy->walk.all); INIT_HLIST_NODE(&policy->bydst_inexact_list); INIT_HLIST_NODE(&policy->bydst); INIT_HLIST_NODE(&policy->byidx); rwlock_init(&policy->lock); refcount_set(&policy->refcnt, 1); skb_queue_head_init(&policy->polq.hold_queue); timer_setup(&policy->timer, xfrm_policy_timer, 0); timer_setup(&policy->polq.hold_timer, xfrm_policy_queue_process, 0); } return policy; } EXPORT_SYMBOL(xfrm_policy_alloc); static void xfrm_policy_destroy_rcu(struct rcu_head *head) { struct xfrm_policy *policy = container_of(head, struct xfrm_policy, rcu); security_xfrm_policy_free(policy->security); kfree(policy); } /* Destroy xfrm_policy: descendant resources must be released to this moment. */ void xfrm_policy_destroy(struct xfrm_policy *policy) { BUG_ON(!policy->walk.dead); if (del_timer(&policy->timer) || del_timer(&policy->polq.hold_timer)) BUG(); call_rcu(&policy->rcu, xfrm_policy_destroy_rcu); } EXPORT_SYMBOL(xfrm_policy_destroy); /* Rule must be locked. Release descendant resources, announce * entry dead. The rule must be unlinked from lists to the moment. */ static void xfrm_policy_kill(struct xfrm_policy *policy) { write_lock_bh(&policy->lock); policy->walk.dead = 1; write_unlock_bh(&policy->lock); atomic_inc(&policy->genid); if (del_timer(&policy->polq.hold_timer)) xfrm_pol_put(policy); skb_queue_purge(&policy->polq.hold_queue); if (del_timer(&policy->timer)) xfrm_pol_put(policy); xfrm_pol_put(policy); } static unsigned int xfrm_policy_hashmax __read_mostly = 1 * 1024 * 1024; static inline unsigned int idx_hash(struct net *net, u32 index) { return __idx_hash(index, net->xfrm.policy_idx_hmask); } /* calculate policy hash thresholds */ static void __get_hash_thresh(struct net *net, unsigned short family, int dir, u8 *dbits, u8 *sbits) { switch (family) { case AF_INET: *dbits = net->xfrm.policy_bydst[dir].dbits4; *sbits = net->xfrm.policy_bydst[dir].sbits4; break; case AF_INET6: *dbits = net->xfrm.policy_bydst[dir].dbits6; *sbits = net->xfrm.policy_bydst[dir].sbits6; break; default: *dbits = 0; *sbits = 0; } } static struct hlist_head *policy_hash_bysel(struct net *net, const struct xfrm_selector *sel, unsigned short family, int dir) { unsigned int hmask = net->xfrm.policy_bydst[dir].hmask; unsigned int hash; u8 dbits; u8 sbits; __get_hash_thresh(net, family, dir, &dbits, &sbits); hash = __sel_hash(sel, family, hmask, dbits, sbits); if (hash == hmask + 1) return NULL; return rcu_dereference_check(net->xfrm.policy_bydst[dir].table, lockdep_is_held(&net->xfrm.xfrm_policy_lock)) + hash; } static struct hlist_head *policy_hash_direct(struct net *net, const xfrm_address_t *daddr, const xfrm_address_t *saddr, unsigned short family, int dir) { unsigned int hmask = net->xfrm.policy_bydst[dir].hmask; unsigned int hash; u8 dbits; u8 sbits; __get_hash_thresh(net, family, dir, &dbits, &sbits); hash = __addr_hash(daddr, saddr, family, hmask, dbits, sbits); return rcu_dereference_check(net->xfrm.policy_bydst[dir].table, lockdep_is_held(&net->xfrm.xfrm_policy_lock)) + hash; } static void xfrm_dst_hash_transfer(struct net *net, struct hlist_head *list, struct hlist_head *ndsttable, unsigned int nhashmask, int dir) { struct hlist_node *tmp, *entry0 = NULL; struct xfrm_policy *pol; unsigned int h0 = 0; u8 dbits; u8 sbits; redo: hlist_for_each_entry_safe(pol, tmp, list, bydst) { unsigned int h; __get_hash_thresh(net, pol->family, dir, &dbits, &sbits); h = __addr_hash(&pol->selector.daddr, &pol->selector.saddr, pol->family, nhashmask, dbits, sbits); if (!entry0) { hlist_del_rcu(&pol->bydst); hlist_add_head_rcu(&pol->bydst, ndsttable + h); h0 = h; } else { if (h != h0) continue; hlist_del_rcu(&pol->bydst); hlist_add_behind_rcu(&pol->bydst, entry0); } entry0 = &pol->bydst; } if (!hlist_empty(list)) { entry0 = NULL; goto redo; } } static void xfrm_idx_hash_transfer(struct hlist_head *list, struct hlist_head *nidxtable, unsigned int nhashmask) { struct hlist_node *tmp; struct xfrm_policy *pol; hlist_for_each_entry_safe(pol, tmp, list, byidx) { unsigned int h; h = __idx_hash(pol->index, nhashmask); hlist_add_head(&pol->byidx, nidxtable+h); } } static unsigned long xfrm_new_hash_mask(unsigned int old_hmask) { return ((old_hmask + 1) << 1) - 1; } static void xfrm_bydst_resize(struct net *net, int dir) { unsigned int hmask = net->xfrm.policy_bydst[dir].hmask; unsigned int nhashmask = xfrm_new_hash_mask(hmask); unsigned int nsize = (nhashmask + 1) * sizeof(struct hlist_head); struct hlist_head *ndst = xfrm_hash_alloc(nsize); struct hlist_head *odst; int i; if (!ndst) return; spin_lock_bh(&net->xfrm.xfrm_policy_lock); write_seqcount_begin(&net->xfrm.xfrm_policy_hash_generation); odst = rcu_dereference_protected(net->xfrm.policy_bydst[dir].table, lockdep_is_held(&net->xfrm.xfrm_policy_lock)); for (i = hmask; i >= 0; i--) xfrm_dst_hash_transfer(net, odst + i, ndst, nhashmask, dir); rcu_assign_pointer(net->xfrm.policy_bydst[dir].table, ndst); net->xfrm.policy_bydst[dir].hmask = nhashmask; write_seqcount_end(&net->xfrm.xfrm_policy_hash_generation); spin_unlock_bh(&net->xfrm.xfrm_policy_lock); synchronize_rcu(); xfrm_hash_free(odst, (hmask + 1) * sizeof(struct hlist_head)); } static void xfrm_byidx_resize(struct net *net, int total) { unsigned int hmask = net->xfrm.policy_idx_hmask; unsigned int nhashmask = xfrm_new_hash_mask(hmask); unsigned int nsize = (nhashmask + 1) * sizeof(struct hlist_head); struct hlist_head *oidx = net->xfrm.policy_byidx; struct hlist_head *nidx = xfrm_hash_alloc(nsize); int i; if (!nidx) return; spin_lock_bh(&net->xfrm.xfrm_policy_lock); for (i = hmask; i >= 0; i--) xfrm_idx_hash_transfer(oidx + i, nidx, nhashmask); net->xfrm.policy_byidx = nidx; net->xfrm.policy_idx_hmask = nhashmask; spin_unlock_bh(&net->xfrm.xfrm_policy_lock); xfrm_hash_free(oidx, (hmask + 1) * sizeof(struct hlist_head)); } static inline int xfrm_bydst_should_resize(struct net *net, int dir, int *total) { unsigned int cnt = net->xfrm.policy_count[dir]; unsigned int hmask = net->xfrm.policy_bydst[dir].hmask; if (total) *total += cnt; if ((hmask + 1) < xfrm_policy_hashmax && cnt > hmask) return 1; return 0; } static inline int xfrm_byidx_should_resize(struct net *net, int total) { unsigned int hmask = net->xfrm.policy_idx_hmask; if ((hmask + 1) < xfrm_policy_hashmax && total > hmask) return 1; return 0; } void xfrm_spd_getinfo(struct net *net, struct xfrmk_spdinfo *si) { si->incnt = net->xfrm.policy_count[XFRM_POLICY_IN]; si->outcnt = net->xfrm.policy_count[XFRM_POLICY_OUT]; si->fwdcnt = net->xfrm.policy_count[XFRM_POLICY_FWD]; si->inscnt = net->xfrm.policy_count[XFRM_POLICY_IN+XFRM_POLICY_MAX]; si->outscnt = net->xfrm.policy_count[XFRM_POLICY_OUT+XFRM_POLICY_MAX]; si->fwdscnt = net->xfrm.policy_count[XFRM_POLICY_FWD+XFRM_POLICY_MAX]; si->spdhcnt = net->xfrm.policy_idx_hmask; si->spdhmcnt = xfrm_policy_hashmax; } EXPORT_SYMBOL(xfrm_spd_getinfo); static DEFINE_MUTEX(hash_resize_mutex); static void xfrm_hash_resize(struct work_struct *work) { struct net *net = container_of(work, struct net, xfrm.policy_hash_work); int dir, total; mutex_lock(&hash_resize_mutex); total = 0; for (dir = 0; dir < XFRM_POLICY_MAX; dir++) { if (xfrm_bydst_should_resize(net, dir, &total)) xfrm_bydst_resize(net, dir); } if (xfrm_byidx_should_resize(net, total)) xfrm_byidx_resize(net, total); mutex_unlock(&hash_resize_mutex); } /* Make sure *pol can be inserted into fastbin. * Useful to check that later insert requests will be sucessful * (provided xfrm_policy_lock is held throughout). */ static struct xfrm_pol_inexact_bin * xfrm_policy_inexact_alloc_bin(const struct xfrm_policy *pol, u8 dir) { struct xfrm_pol_inexact_bin *bin, *prev; struct xfrm_pol_inexact_key k = { .family = pol->family, .type = pol->type, .dir = dir, .if_id = pol->if_id, }; struct net *net = xp_net(pol); lockdep_assert_held(&net->xfrm.xfrm_policy_lock); write_pnet(&k.net, net); bin = rhashtable_lookup_fast(&xfrm_policy_inexact_table, &k, xfrm_pol_inexact_params); if (bin) return bin; bin = kzalloc(sizeof(*bin), GFP_ATOMIC); if (!bin) return NULL; bin->k = k; INIT_HLIST_HEAD(&bin->hhead); bin->root_d = RB_ROOT; bin->root_s = RB_ROOT; seqcount_spinlock_init(&bin->count, &net->xfrm.xfrm_policy_lock); prev = rhashtable_lookup_get_insert_key(&xfrm_policy_inexact_table, &bin->k, &bin->head, xfrm_pol_inexact_params); if (!prev) { list_add(&bin->inexact_bins, &net->xfrm.inexact_bins); return bin; } kfree(bin); return IS_ERR(prev) ? NULL : prev; } static bool xfrm_pol_inexact_addr_use_any_list(const xfrm_address_t *addr, int family, u8 prefixlen) { if (xfrm_addr_any(addr, family)) return true; if (family == AF_INET6 && prefixlen < INEXACT_PREFIXLEN_IPV6) return true; if (family == AF_INET && prefixlen < INEXACT_PREFIXLEN_IPV4) return true; return false; } static bool xfrm_policy_inexact_insert_use_any_list(const struct xfrm_policy *policy) { const xfrm_address_t *addr; bool saddr_any, daddr_any; u8 prefixlen; addr = &policy->selector.saddr; prefixlen = policy->selector.prefixlen_s; saddr_any = xfrm_pol_inexact_addr_use_any_list(addr, policy->family, prefixlen); addr = &policy->selector.daddr; prefixlen = policy->selector.prefixlen_d; daddr_any = xfrm_pol_inexact_addr_use_any_list(addr, policy->family, prefixlen); return saddr_any && daddr_any; } static void xfrm_pol_inexact_node_init(struct xfrm_pol_inexact_node *node, const xfrm_address_t *addr, u8 prefixlen) { node->addr = *addr; node->prefixlen = prefixlen; } static struct xfrm_pol_inexact_node * xfrm_pol_inexact_node_alloc(const xfrm_address_t *addr, u8 prefixlen) { struct xfrm_pol_inexact_node *node; node = kzalloc(sizeof(*node), GFP_ATOMIC); if (node) xfrm_pol_inexact_node_init(node, addr, prefixlen); return node; } static int xfrm_policy_addr_delta(const xfrm_address_t *a, const xfrm_address_t *b, u8 prefixlen, u16 family) { u32 ma, mb, mask; unsigned int pdw, pbi; int delta = 0; switch (family) { case AF_INET: if (prefixlen == 0) return 0; mask = ~0U << (32 - prefixlen); ma = ntohl(a->a4) & mask; mb = ntohl(b->a4) & mask; if (ma < mb) delta = -1; else if (ma > mb) delta = 1; break; case AF_INET6: pdw = prefixlen >> 5; pbi = prefixlen & 0x1f; if (pdw) { delta = memcmp(a->a6, b->a6, pdw << 2); if (delta) return delta; } if (pbi) { mask = ~0U << (32 - pbi); ma = ntohl(a->a6[pdw]) & mask; mb = ntohl(b->a6[pdw]) & mask; if (ma < mb) delta = -1; else if (ma > mb) delta = 1; } break; default: break; } return delta; } static void xfrm_policy_inexact_list_reinsert(struct net *net, struct xfrm_pol_inexact_node *n, u16 family) { unsigned int matched_s, matched_d; struct xfrm_policy *policy, *p; matched_s = 0; matched_d = 0; list_for_each_entry_reverse(policy, &net->xfrm.policy_all, walk.all) { struct hlist_node *newpos = NULL; bool matches_s, matches_d; if (!policy->bydst_reinsert) continue; WARN_ON_ONCE(policy->family != family); policy->bydst_reinsert = false; hlist_for_each_entry(p, &n->hhead, bydst) { if (policy->priority > p->priority) newpos = &p->bydst; else if (policy->priority == p->priority && policy->pos > p->pos) newpos = &p->bydst; else break; } if (newpos) hlist_add_behind_rcu(&policy->bydst, newpos); else hlist_add_head_rcu(&policy->bydst, &n->hhead); /* paranoia checks follow. * Check that the reinserted policy matches at least * saddr or daddr for current node prefix. * * Matching both is fine, matching saddr in one policy * (but not daddr) and then matching only daddr in another * is a bug. */ matches_s = xfrm_policy_addr_delta(&policy->selector.saddr, &n->addr, n->prefixlen, family) == 0; matches_d = xfrm_policy_addr_delta(&policy->selector.daddr, &n->addr, n->prefixlen, family) == 0; if (matches_s && matches_d) continue; WARN_ON_ONCE(!matches_s && !matches_d); if (matches_s) matched_s++; if (matches_d) matched_d++; WARN_ON_ONCE(matched_s && matched_d); } } static void xfrm_policy_inexact_node_reinsert(struct net *net, struct xfrm_pol_inexact_node *n, struct rb_root *new, u16 family) { struct xfrm_pol_inexact_node *node; struct rb_node **p, *parent; /* we should not have another subtree here */ WARN_ON_ONCE(!RB_EMPTY_ROOT(&n->root)); restart: parent = NULL; p = &new->rb_node; while (*p) { u8 prefixlen; int delta; parent = *p; node = rb_entry(*p, struct xfrm_pol_inexact_node, node); prefixlen = min(node->prefixlen, n->prefixlen); delta = xfrm_policy_addr_delta(&n->addr, &node->addr, prefixlen, family); if (delta < 0) { p = &parent->rb_left; } else if (delta > 0) { p = &parent->rb_right; } else { bool same_prefixlen = node->prefixlen == n->prefixlen; struct xfrm_policy *tmp; hlist_for_each_entry(tmp, &n->hhead, bydst) { tmp->bydst_reinsert = true; hlist_del_rcu(&tmp->bydst); } node->prefixlen = prefixlen; xfrm_policy_inexact_list_reinsert(net, node, family); if (same_prefixlen) { kfree_rcu(n, rcu); return; } rb_erase(*p, new); kfree_rcu(n, rcu); n = node; goto restart; } } rb_link_node_rcu(&n->node, parent, p); rb_insert_color(&n->node, new); } /* merge nodes v and n */ static void xfrm_policy_inexact_node_merge(struct net *net, struct xfrm_pol_inexact_node *v, struct xfrm_pol_inexact_node *n, u16 family) { struct xfrm_pol_inexact_node *node; struct xfrm_policy *tmp; struct rb_node *rnode; /* To-be-merged node v has a subtree. * * Dismantle it and insert its nodes to n->root. */ while ((rnode = rb_first(&v->root)) != NULL) { node = rb_entry(rnode, struct xfrm_pol_inexact_node, node); rb_erase(&node->node, &v->root); xfrm_policy_inexact_node_reinsert(net, node, &n->root, family); } hlist_for_each_entry(tmp, &v->hhead, bydst) { tmp->bydst_reinsert = true; hlist_del_rcu(&tmp->bydst); } xfrm_policy_inexact_list_reinsert(net, n, family); } static struct xfrm_pol_inexact_node * xfrm_policy_inexact_insert_node(struct net *net, struct rb_root *root, xfrm_address_t *addr, u16 family, u8 prefixlen, u8 dir) { struct xfrm_pol_inexact_node *cached = NULL; struct rb_node **p, *parent = NULL; struct xfrm_pol_inexact_node *node; p = &root->rb_node; while (*p) { int delta; parent = *p; node = rb_entry(*p, struct xfrm_pol_inexact_node, node); delta = xfrm_policy_addr_delta(addr, &node->addr, node->prefixlen, family); if (delta == 0 && prefixlen >= node->prefixlen) { WARN_ON_ONCE(cached); /* ipsec policies got lost */ return node; } if (delta < 0) p = &parent->rb_left; else p = &parent->rb_right; if (prefixlen < node->prefixlen) { delta = xfrm_policy_addr_delta(addr, &node->addr, prefixlen, family); if (delta) continue; /* This node is a subnet of the new prefix. It needs * to be removed and re-inserted with the smaller * prefix and all nodes that are now also covered * by the reduced prefixlen. */ rb_erase(&node->node, root); if (!cached) { xfrm_pol_inexact_node_init(node, addr, prefixlen); cached = node; } else { /* This node also falls within the new * prefixlen. Merge the to-be-reinserted * node and this one. */ xfrm_policy_inexact_node_merge(net, node, cached, family); kfree_rcu(node, rcu); } /* restart */ p = &root->rb_node; parent = NULL; } } node = cached; if (!node) { node = xfrm_pol_inexact_node_alloc(addr, prefixlen); if (!node) return NULL; } rb_link_node_rcu(&node->node, parent, p); rb_insert_color(&node->node, root); return node; } static void xfrm_policy_inexact_gc_tree(struct rb_root *r, bool rm) { struct xfrm_pol_inexact_node *node; struct rb_node *rn = rb_first(r); while (rn) { node = rb_entry(rn, struct xfrm_pol_inexact_node, node); xfrm_policy_inexact_gc_tree(&node->root, rm); rn = rb_next(rn); if (!hlist_empty(&node->hhead) || !RB_EMPTY_ROOT(&node->root)) { WARN_ON_ONCE(rm); continue; } rb_erase(&node->node, r); kfree_rcu(node, rcu); } } static void __xfrm_policy_inexact_prune_bin(struct xfrm_pol_inexact_bin *b, bool net_exit) { write_seqcount_begin(&b->count); xfrm_policy_inexact_gc_tree(&b->root_d, net_exit); xfrm_policy_inexact_gc_tree(&b->root_s, net_exit); write_seqcount_end(&b->count); if (!RB_EMPTY_ROOT(&b->root_d) || !RB_EMPTY_ROOT(&b->root_s) || !hlist_empty(&b->hhead)) { WARN_ON_ONCE(net_exit); return; } if (rhashtable_remove_fast(&xfrm_policy_inexact_table, &b->head, xfrm_pol_inexact_params) == 0) { list_del(&b->inexact_bins); kfree_rcu(b, rcu); } } static void xfrm_policy_inexact_prune_bin(struct xfrm_pol_inexact_bin *b) { struct net *net = read_pnet(&b->k.net); spin_lock_bh(&net->xfrm.xfrm_policy_lock); __xfrm_policy_inexact_prune_bin(b, false); spin_unlock_bh(&net->xfrm.xfrm_policy_lock); } static void __xfrm_policy_inexact_flush(struct net *net) { struct xfrm_pol_inexact_bin *bin, *t; lockdep_assert_held(&net->xfrm.xfrm_policy_lock); list_for_each_entry_safe(bin, t, &net->xfrm.inexact_bins, inexact_bins) __xfrm_policy_inexact_prune_bin(bin, false); } static struct hlist_head * xfrm_policy_inexact_alloc_chain(struct xfrm_pol_inexact_bin *bin, struct xfrm_policy *policy, u8 dir) { struct xfrm_pol_inexact_node *n; struct net *net; net = xp_net(policy); lockdep_assert_held(&net->xfrm.xfrm_policy_lock); if (xfrm_policy_inexact_insert_use_any_list(policy)) return &bin->hhead; if (xfrm_pol_inexact_addr_use_any_list(&policy->selector.daddr, policy->family, policy->selector.prefixlen_d)) { write_seqcount_begin(&bin->count); n = xfrm_policy_inexact_insert_node(net, &bin->root_s, &policy->selector.saddr, policy->family, policy->selector.prefixlen_s, dir); write_seqcount_end(&bin->count); if (!n) return NULL; return &n->hhead; } /* daddr is fixed */ write_seqcount_begin(&bin->count); n = xfrm_policy_inexact_insert_node(net, &bin->root_d, &policy->selector.daddr, policy->family, policy->selector.prefixlen_d, dir); write_seqcount_end(&bin->count); if (!n) return NULL; /* saddr is wildcard */ if (xfrm_pol_inexact_addr_use_any_list(&policy->selector.saddr, policy->family, policy->selector.prefixlen_s)) return &n->hhead; write_seqcount_begin(&bin->count); n = xfrm_policy_inexact_insert_node(net, &n->root, &policy->selector.saddr, policy->family, policy->selector.prefixlen_s, dir); write_seqcount_end(&bin->count); if (!n) return NULL; return &n->hhead; } static struct xfrm_policy * xfrm_policy_inexact_insert(struct xfrm_policy *policy, u8 dir, int excl) { struct xfrm_pol_inexact_bin *bin; struct xfrm_policy *delpol; struct hlist_head *chain; struct net *net; bin = xfrm_policy_inexact_alloc_bin(policy, dir); if (!bin) return ERR_PTR(-ENOMEM); net = xp_net(policy); lockdep_assert_held(&net->xfrm.xfrm_policy_lock); chain = xfrm_policy_inexact_alloc_chain(bin, policy, dir); if (!chain) { __xfrm_policy_inexact_prune_bin(bin, false); return ERR_PTR(-ENOMEM); } delpol = xfrm_policy_insert_list(chain, policy, excl); if (delpol && excl) { __xfrm_policy_inexact_prune_bin(bin, false); return ERR_PTR(-EEXIST); } chain = &net->xfrm.policy_inexact[dir]; xfrm_policy_insert_inexact_list(chain, policy); if (delpol) __xfrm_policy_inexact_prune_bin(bin, false); return delpol; } static void xfrm_hash_rebuild(struct work_struct *work) { struct net *net = container_of(work, struct net, xfrm.policy_hthresh.work); unsigned int hmask; struct xfrm_policy *pol; struct xfrm_policy *policy; struct hlist_head *chain; struct hlist_head *odst; struct hlist_node *newpos; int i; int dir; unsigned seq; u8 lbits4, rbits4, lbits6, rbits6; mutex_lock(&hash_resize_mutex); /* read selector prefixlen thresholds */ do { seq = read_seqbegin(&net->xfrm.policy_hthresh.lock); lbits4 = net->xfrm.policy_hthresh.lbits4; rbits4 = net->xfrm.policy_hthresh.rbits4; lbits6 = net->xfrm.policy_hthresh.lbits6; rbits6 = net->xfrm.policy_hthresh.rbits6; } while (read_seqretry(&net->xfrm.policy_hthresh.lock, seq)); spin_lock_bh(&net->xfrm.xfrm_policy_lock); write_seqcount_begin(&net->xfrm.xfrm_policy_hash_generation); /* make sure that we can insert the indirect policies again before * we start with destructive action. */ list_for_each_entry(policy, &net->xfrm.policy_all, walk.all) { struct xfrm_pol_inexact_bin *bin; u8 dbits, sbits; dir = xfrm_policy_id2dir(policy->index); if (policy->walk.dead || dir >= XFRM_POLICY_MAX) continue; if ((dir & XFRM_POLICY_MASK) == XFRM_POLICY_OUT) { if (policy->family == AF_INET) { dbits = rbits4; sbits = lbits4; } else { dbits = rbits6; sbits = lbits6; } } else { if (policy->family == AF_INET) { dbits = lbits4; sbits = rbits4; } else { dbits = lbits6; sbits = rbits6; } } if (policy->selector.prefixlen_d < dbits || policy->selector.prefixlen_s < sbits) continue; bin = xfrm_policy_inexact_alloc_bin(policy, dir); if (!bin) goto out_unlock; if (!xfrm_policy_inexact_alloc_chain(bin, policy, dir)) goto out_unlock; } /* reset the bydst and inexact table in all directions */ for (dir = 0; dir < XFRM_POLICY_MAX; dir++) { struct hlist_node *n; hlist_for_each_entry_safe(policy, n, &net->xfrm.policy_inexact[dir], bydst_inexact_list) { hlist_del_rcu(&policy->bydst); hlist_del_init(&policy->bydst_inexact_list); } hmask = net->xfrm.policy_bydst[dir].hmask; odst = net->xfrm.policy_bydst[dir].table; for (i = hmask; i >= 0; i--) { hlist_for_each_entry_safe(policy, n, odst + i, bydst) hlist_del_rcu(&policy->bydst); } if ((dir & XFRM_POLICY_MASK) == XFRM_POLICY_OUT) { /* dir out => dst = remote, src = local */ net->xfrm.policy_bydst[dir].dbits4 = rbits4; net->xfrm.policy_bydst[dir].sbits4 = lbits4; net->xfrm.policy_bydst[dir].dbits6 = rbits6; net->xfrm.policy_bydst[dir].sbits6 = lbits6; } else { /* dir in/fwd => dst = local, src = remote */ net->xfrm.policy_bydst[dir].dbits4 = lbits4; net->xfrm.policy_bydst[dir].sbits4 = rbits4; net->xfrm.policy_bydst[dir].dbits6 = lbits6; net->xfrm.policy_bydst[dir].sbits6 = rbits6; } } /* re-insert all policies by order of creation */ list_for_each_entry_reverse(policy, &net->xfrm.policy_all, walk.all) { if (policy->walk.dead) continue; dir = xfrm_policy_id2dir(policy->index); if (dir >= XFRM_POLICY_MAX) { /* skip socket policies */ continue; } newpos = NULL; chain = policy_hash_bysel(net, &policy->selector, policy->family, dir); if (!chain) { void *p = xfrm_policy_inexact_insert(policy, dir, 0); WARN_ONCE(IS_ERR(p), "reinsert: %ld\n", PTR_ERR(p)); continue; } hlist_for_each_entry(pol, chain, bydst) { if (policy->priority >= pol->priority) newpos = &pol->bydst; else break; } if (newpos) hlist_add_behind_rcu(&policy->bydst, newpos); else hlist_add_head_rcu(&policy->bydst, chain); } out_unlock: __xfrm_policy_inexact_flush(net); write_seqcount_end(&net->xfrm.xfrm_policy_hash_generation); spin_unlock_bh(&net->xfrm.xfrm_policy_lock); mutex_unlock(&hash_resize_mutex); } void xfrm_policy_hash_rebuild(struct net *net) { schedule_work(&net->xfrm.policy_hthresh.work); } EXPORT_SYMBOL(xfrm_policy_hash_rebuild); /* Generate new index... KAME seems to generate them ordered by cost * of an absolute inpredictability of ordering of rules. This will not pass. */ static u32 xfrm_gen_index(struct net *net, int dir, u32 index) { static u32 idx_generator; for (;;) { struct hlist_head *list; struct xfrm_policy *p; u32 idx; int found; if (!index) { idx = (idx_generator | dir); idx_generator += 8; } else { idx = index; index = 0; } if (idx == 0) idx = 8; list = net->xfrm.policy_byidx + idx_hash(net, idx); found = 0; hlist_for_each_entry(p, list, byidx) { if (p->index == idx) { found = 1; break; } } if (!found) return idx; } } static inline int selector_cmp(struct xfrm_selector *s1, struct xfrm_selector *s2) { u32 *p1 = (u32 *) s1; u32 *p2 = (u32 *) s2; int len = sizeof(struct xfrm_selector) / sizeof(u32); int i; for (i = 0; i < len; i++) { if (p1[i] != p2[i]) return 1; } return 0; } static void xfrm_policy_requeue(struct xfrm_policy *old, struct xfrm_policy *new) { struct xfrm_policy_queue *pq = &old->polq; struct sk_buff_head list; if (skb_queue_empty(&pq->hold_queue)) return; __skb_queue_head_init(&list); spin_lock_bh(&pq->hold_queue.lock); skb_queue_splice_init(&pq->hold_queue, &list); if (del_timer(&pq->hold_timer)) xfrm_pol_put(old); spin_unlock_bh(&pq->hold_queue.lock); pq = &new->polq; spin_lock_bh(&pq->hold_queue.lock); skb_queue_splice(&list, &pq->hold_queue); pq->timeout = XFRM_QUEUE_TMO_MIN; if (!mod_timer(&pq->hold_timer, jiffies)) xfrm_pol_hold(new); spin_unlock_bh(&pq->hold_queue.lock); } static inline bool xfrm_policy_mark_match(const struct xfrm_mark *mark, struct xfrm_policy *pol) { return mark->v == pol->mark.v && mark->m == pol->mark.m; } static u32 xfrm_pol_bin_key(const void *data, u32 len, u32 seed) { const struct xfrm_pol_inexact_key *k = data; u32 a = k->type << 24 | k->dir << 16 | k->family; return jhash_3words(a, k->if_id, net_hash_mix(read_pnet(&k->net)), seed); } static u32 xfrm_pol_bin_obj(const void *data, u32 len, u32 seed) { const struct xfrm_pol_inexact_bin *b = data; return xfrm_pol_bin_key(&b->k, 0, seed); } static int xfrm_pol_bin_cmp(struct rhashtable_compare_arg *arg, const void *ptr) { const struct xfrm_pol_inexact_key *key = arg->key; const struct xfrm_pol_inexact_bin *b = ptr; int ret; if (!net_eq(read_pnet(&b->k.net), read_pnet(&key->net))) return -1; ret = b->k.dir ^ key->dir; if (ret) return ret; ret = b->k.type ^ key->type; if (ret) return ret; ret = b->k.family ^ key->family; if (ret) return ret; return b->k.if_id ^ key->if_id; } static const struct rhashtable_params xfrm_pol_inexact_params = { .head_offset = offsetof(struct xfrm_pol_inexact_bin, head), .hashfn = xfrm_pol_bin_key, .obj_hashfn = xfrm_pol_bin_obj, .obj_cmpfn = xfrm_pol_bin_cmp, .automatic_shrinking = true, }; static void xfrm_policy_insert_inexact_list(struct hlist_head *chain, struct xfrm_policy *policy) { struct xfrm_policy *pol, *delpol = NULL; struct hlist_node *newpos = NULL; int i = 0; hlist_for_each_entry(pol, chain, bydst_inexact_list) { if (pol->type == policy->type && pol->if_id == policy->if_id && !selector_cmp(&pol->selector, &policy->selector) && xfrm_policy_mark_match(&policy->mark, pol) && xfrm_sec_ctx_match(pol->security, policy->security) && !WARN_ON(delpol)) { delpol = pol; if (policy->priority > pol->priority) continue; } else if (policy->priority >= pol->priority) { newpos = &pol->bydst_inexact_list; continue; } if (delpol) break; } if (newpos) hlist_add_behind_rcu(&policy->bydst_inexact_list, newpos); else hlist_add_head_rcu(&policy->bydst_inexact_list, chain); hlist_for_each_entry(pol, chain, bydst_inexact_list) { pol->pos = i; i++; } } static struct xfrm_policy *xfrm_policy_insert_list(struct hlist_head *chain, struct xfrm_policy *policy, bool excl) { struct xfrm_policy *pol, *newpos = NULL, *delpol = NULL; hlist_for_each_entry(pol, chain, bydst) { if (pol->type == policy->type && pol->if_id == policy->if_id && !selector_cmp(&pol->selector, &policy->selector) && xfrm_policy_mark_match(&policy->mark, pol) && xfrm_sec_ctx_match(pol->security, policy->security) && !WARN_ON(delpol)) { if (excl) return ERR_PTR(-EEXIST); delpol = pol; if (policy->priority > pol->priority) continue; } else if (policy->priority >= pol->priority) { newpos = pol; continue; } if (delpol) break; } if (newpos) hlist_add_behind_rcu(&policy->bydst, &newpos->bydst); else hlist_add_head_rcu(&policy->bydst, chain); return delpol; } int xfrm_policy_insert(int dir, struct xfrm_policy *policy, int excl) { struct net *net = xp_net(policy); struct xfrm_policy *delpol; struct hlist_head *chain; spin_lock_bh(&net->xfrm.xfrm_policy_lock); chain = policy_hash_bysel(net, &policy->selector, policy->family, dir); if (chain) delpol = xfrm_policy_insert_list(chain, policy, excl); else delpol = xfrm_policy_inexact_insert(policy, dir, excl); if (IS_ERR(delpol)) { spin_unlock_bh(&net->xfrm.xfrm_policy_lock); return PTR_ERR(delpol); } __xfrm_policy_link(policy, dir); /* After previous checking, family can either be AF_INET or AF_INET6 */ if (policy->family == AF_INET) rt_genid_bump_ipv4(net); else rt_genid_bump_ipv6(net); if (delpol) { xfrm_policy_requeue(delpol, policy); __xfrm_policy_unlink(delpol, dir); } policy->index = delpol ? delpol->index : xfrm_gen_index(net, dir, policy->index); hlist_add_head(&policy->byidx, net->xfrm.policy_byidx+idx_hash(net, policy->index)); policy->curlft.add_time = ktime_get_real_seconds(); policy->curlft.use_time = 0; if (!mod_timer(&policy->timer, jiffies + HZ)) xfrm_pol_hold(policy); spin_unlock_bh(&net->xfrm.xfrm_policy_lock); if (delpol) xfrm_policy_kill(delpol); else if (xfrm_bydst_should_resize(net, dir, NULL)) schedule_work(&net->xfrm.policy_hash_work); return 0; } EXPORT_SYMBOL(xfrm_policy_insert); static struct xfrm_policy * __xfrm_policy_bysel_ctx(struct hlist_head *chain, const struct xfrm_mark *mark, u32 if_id, u8 type, int dir, struct xfrm_selector *sel, struct xfrm_sec_ctx *ctx) { struct xfrm_policy *pol; if (!chain) return NULL; hlist_for_each_entry(pol, chain, bydst) { if (pol->type == type && pol->if_id == if_id && xfrm_policy_mark_match(mark, pol) && !selector_cmp(sel, &pol->selector) && xfrm_sec_ctx_match(ctx, pol->security)) return pol; } return NULL; } struct xfrm_policy * xfrm_policy_bysel_ctx(struct net *net, const struct xfrm_mark *mark, u32 if_id, u8 type, int dir, struct xfrm_selector *sel, struct xfrm_sec_ctx *ctx, int delete, int *err) { struct xfrm_pol_inexact_bin *bin = NULL; struct xfrm_policy *pol, *ret = NULL; struct hlist_head *chain; *err = 0; spin_lock_bh(&net->xfrm.xfrm_policy_lock); chain = policy_hash_bysel(net, sel, sel->family, dir); if (!chain) { struct xfrm_pol_inexact_candidates cand; int i; bin = xfrm_policy_inexact_lookup(net, type, sel->family, dir, if_id); if (!bin) { spin_unlock_bh(&net->xfrm.xfrm_policy_lock); return NULL; } if (!xfrm_policy_find_inexact_candidates(&cand, bin, &sel->saddr, &sel->daddr)) { spin_unlock_bh(&net->xfrm.xfrm_policy_lock); return NULL; } pol = NULL; for (i = 0; i < ARRAY_SIZE(cand.res); i++) { struct xfrm_policy *tmp; tmp = __xfrm_policy_bysel_ctx(cand.res[i], mark, if_id, type, dir, sel, ctx); if (!tmp) continue; if (!pol || tmp->pos < pol->pos) pol = tmp; } } else { pol = __xfrm_policy_bysel_ctx(chain, mark, if_id, type, dir, sel, ctx); } if (pol) { xfrm_pol_hold(pol); if (delete) { *err = security_xfrm_policy_delete(pol->security); if (*err) { spin_unlock_bh(&net->xfrm.xfrm_policy_lock); return pol; } __xfrm_policy_unlink(pol, dir); } ret = pol; } spin_unlock_bh(&net->xfrm.xfrm_policy_lock); if (ret && delete) xfrm_policy_kill(ret); if (bin && delete) xfrm_policy_inexact_prune_bin(bin); return ret; } EXPORT_SYMBOL(xfrm_policy_bysel_ctx); struct xfrm_policy * xfrm_policy_byid(struct net *net, const struct xfrm_mark *mark, u32 if_id, u8 type, int dir, u32 id, int delete, int *err) { struct xfrm_policy *pol, *ret; struct hlist_head *chain; *err = -ENOENT; if (xfrm_policy_id2dir(id) != dir) return NULL; *err = 0; spin_lock_bh(&net->xfrm.xfrm_policy_lock); chain = net->xfrm.policy_byidx + idx_hash(net, id); ret = NULL; hlist_for_each_entry(pol, chain, byidx) { if (pol->type == type && pol->index == id && pol->if_id == if_id && xfrm_policy_mark_match(mark, pol)) { xfrm_pol_hold(pol); if (delete) { *err = security_xfrm_policy_delete( pol->security); if (*err) { spin_unlock_bh(&net->xfrm.xfrm_policy_lock); return pol; } __xfrm_policy_unlink(pol, dir); } ret = pol; break; } } spin_unlock_bh(&net->xfrm.xfrm_policy_lock); if (ret && delete) xfrm_policy_kill(ret); return ret; } EXPORT_SYMBOL(xfrm_policy_byid); #ifdef CONFIG_SECURITY_NETWORK_XFRM static inline int xfrm_policy_flush_secctx_check(struct net *net, u8 type, bool task_valid) { struct xfrm_policy *pol; int err = 0; list_for_each_entry(pol, &net->xfrm.policy_all, walk.all) { if (pol->walk.dead || xfrm_policy_id2dir(pol->index) >= XFRM_POLICY_MAX || pol->type != type) continue; err = security_xfrm_policy_delete(pol->security); if (err) { xfrm_audit_policy_delete(pol, 0, task_valid); return err; } } return err; } #else static inline int xfrm_policy_flush_secctx_check(struct net *net, u8 type, bool task_valid) { return 0; } #endif int xfrm_policy_flush(struct net *net, u8 type, bool task_valid) { int dir, err = 0, cnt = 0; struct xfrm_policy *pol; spin_lock_bh(&net->xfrm.xfrm_policy_lock); err = xfrm_policy_flush_secctx_check(net, type, task_valid); if (err) goto out; again: list_for_each_entry(pol, &net->xfrm.policy_all, walk.all) { dir = xfrm_policy_id2dir(pol->index); if (pol->walk.dead || dir >= XFRM_POLICY_MAX || pol->type != type) continue; __xfrm_policy_unlink(pol, dir); spin_unlock_bh(&net->xfrm.xfrm_policy_lock); cnt++; xfrm_audit_policy_delete(pol, 1, task_valid); xfrm_policy_kill(pol); spin_lock_bh(&net->xfrm.xfrm_policy_lock); goto again; } if (cnt) __xfrm_policy_inexact_flush(net); else err = -ESRCH; out: spin_unlock_bh(&net->xfrm.xfrm_policy_lock); return err; } EXPORT_SYMBOL(xfrm_policy_flush); int xfrm_policy_walk(struct net *net, struct xfrm_policy_walk *walk, int (*func)(struct xfrm_policy *, int, int, void*), void *data) { struct xfrm_policy *pol; struct xfrm_policy_walk_entry *x; int error = 0; if (walk->type >= XFRM_POLICY_TYPE_MAX && walk->type != XFRM_POLICY_TYPE_ANY) return -EINVAL; if (list_empty(&walk->walk.all) && walk->seq != 0) return 0; spin_lock_bh(&net->xfrm.xfrm_policy_lock); if (list_empty(&walk->walk.all)) x = list_first_entry(&net->xfrm.policy_all, struct xfrm_policy_walk_entry, all); else x = list_first_entry(&walk->walk.all, struct xfrm_policy_walk_entry, all); list_for_each_entry_from(x, &net->xfrm.policy_all, all) { if (x->dead) continue; pol = container_of(x, struct xfrm_policy, walk); if (walk->type != XFRM_POLICY_TYPE_ANY && walk->type != pol->type) continue; error = func(pol, xfrm_policy_id2dir(pol->index), walk->seq, data); if (error) { list_move_tail(&walk->walk.all, &x->all); goto out; } walk->seq++; } if (walk->seq == 0) { error = -ENOENT; goto out; } list_del_init(&walk->walk.all); out: spin_unlock_bh(&net->xfrm.xfrm_policy_lock); return error; } EXPORT_SYMBOL(xfrm_policy_walk); void xfrm_policy_walk_init(struct xfrm_policy_walk *walk, u8 type) { INIT_LIST_HEAD(&walk->walk.all); walk->walk.dead = 1; walk->type = type; walk->seq = 0; } EXPORT_SYMBOL(xfrm_policy_walk_init); void xfrm_policy_walk_done(struct xfrm_policy_walk *walk, struct net *net) { if (list_empty(&walk->walk.all)) return; spin_lock_bh(&net->xfrm.xfrm_policy_lock); /*FIXME where is net? */ list_del(&walk->walk.all); spin_unlock_bh(&net->xfrm.xfrm_policy_lock); } EXPORT_SYMBOL(xfrm_policy_walk_done); /* * Find policy to apply to this flow. * * Returns 0 if policy found, else an -errno. */ static int xfrm_policy_match(const struct xfrm_policy *pol, const struct flowi *fl, u8 type, u16 family, int dir, u32 if_id) { const struct xfrm_selector *sel = &pol->selector; int ret = -ESRCH; bool match; if (pol->family != family || pol->if_id != if_id || (fl->flowi_mark & pol->mark.m) != pol->mark.v || pol->type != type) return ret; match = xfrm_selector_match(sel, fl, family); if (match) ret = security_xfrm_policy_lookup(pol->security, fl->flowi_secid, dir); return ret; } static struct xfrm_pol_inexact_node * xfrm_policy_lookup_inexact_addr(const struct rb_root *r, seqcount_spinlock_t *count, const xfrm_address_t *addr, u16 family) { const struct rb_node *parent; int seq; again: seq = read_seqcount_begin(count); parent = rcu_dereference_raw(r->rb_node); while (parent) { struct xfrm_pol_inexact_node *node; int delta; node = rb_entry(parent, struct xfrm_pol_inexact_node, node); delta = xfrm_policy_addr_delta(addr, &node->addr, node->prefixlen, family); if (delta < 0) { parent = rcu_dereference_raw(parent->rb_left); continue; } else if (delta > 0) { parent = rcu_dereference_raw(parent->rb_right); continue; } return node; } if (read_seqcount_retry(count, seq)) goto again; return NULL; } static bool xfrm_policy_find_inexact_candidates(struct xfrm_pol_inexact_candidates *cand, struct xfrm_pol_inexact_bin *b, const xfrm_address_t *saddr, const xfrm_address_t *daddr) { struct xfrm_pol_inexact_node *n; u16 family; if (!b) return false; family = b->k.family; memset(cand, 0, sizeof(*cand)); cand->res[XFRM_POL_CAND_ANY] = &b->hhead; n = xfrm_policy_lookup_inexact_addr(&b->root_d, &b->count, daddr, family); if (n) { cand->res[XFRM_POL_CAND_DADDR] = &n->hhead; n = xfrm_policy_lookup_inexact_addr(&n->root, &b->count, saddr, family); if (n) cand->res[XFRM_POL_CAND_BOTH] = &n->hhead; } n = xfrm_policy_lookup_inexact_addr(&b->root_s, &b->count, saddr, family); if (n) cand->res[XFRM_POL_CAND_SADDR] = &n->hhead; return true; } static struct xfrm_pol_inexact_bin * xfrm_policy_inexact_lookup_rcu(struct net *net, u8 type, u16 family, u8 dir, u32 if_id) { struct xfrm_pol_inexact_key k = { .family = family, .type = type, .dir = dir, .if_id = if_id, }; write_pnet(&k.net, net); return rhashtable_lookup(&xfrm_policy_inexact_table, &k, xfrm_pol_inexact_params); } static struct xfrm_pol_inexact_bin * xfrm_policy_inexact_lookup(struct net *net, u8 type, u16 family, u8 dir, u32 if_id) { struct xfrm_pol_inexact_bin *bin; lockdep_assert_held(&net->xfrm.xfrm_policy_lock); rcu_read_lock(); bin = xfrm_policy_inexact_lookup_rcu(net, type, family, dir, if_id); rcu_read_unlock(); return bin; } static struct xfrm_policy * __xfrm_policy_eval_candidates(struct hlist_head *chain, struct xfrm_policy *prefer, const struct flowi *fl, u8 type, u16 family, int dir, u32 if_id) { u32 priority = prefer ? prefer->priority : ~0u; struct xfrm_policy *pol; if (!chain) return NULL; hlist_for_each_entry_rcu(pol, chain, bydst) { int err; if (pol->priority > priority) break; err = xfrm_policy_match(pol, fl, type, family, dir, if_id); if (err) { if (err != -ESRCH) return ERR_PTR(err); continue; } if (prefer) { /* matches. Is it older than *prefer? */ if (pol->priority == priority && prefer->pos < pol->pos) return prefer; } return pol; } return NULL; } static struct xfrm_policy * xfrm_policy_eval_candidates(struct xfrm_pol_inexact_candidates *cand, struct xfrm_policy *prefer, const struct flowi *fl, u8 type, u16 family, int dir, u32 if_id) { struct xfrm_policy *tmp; int i; for (i = 0; i < ARRAY_SIZE(cand->res); i++) { tmp = __xfrm_policy_eval_candidates(cand->res[i], prefer, fl, type, family, dir, if_id); if (!tmp) continue; if (IS_ERR(tmp)) return tmp; prefer = tmp; } return prefer; } static struct xfrm_policy *xfrm_policy_lookup_bytype(struct net *net, u8 type, const struct flowi *fl, u16 family, u8 dir, u32 if_id) { struct xfrm_pol_inexact_candidates cand; const xfrm_address_t *daddr, *saddr; struct xfrm_pol_inexact_bin *bin; struct xfrm_policy *pol, *ret; struct hlist_head *chain; unsigned int sequence; int err; daddr = xfrm_flowi_daddr(fl, family); saddr = xfrm_flowi_saddr(fl, family); if (unlikely(!daddr || !saddr)) return NULL; rcu_read_lock(); retry: do { sequence = read_seqcount_begin(&net->xfrm.xfrm_policy_hash_generation); chain = policy_hash_direct(net, daddr, saddr, family, dir); } while (read_seqcount_retry(&net->xfrm.xfrm_policy_hash_generation, sequence)); ret = NULL; hlist_for_each_entry_rcu(pol, chain, bydst) { err = xfrm_policy_match(pol, fl, type, family, dir, if_id); if (err) { if (err == -ESRCH) continue; else { ret = ERR_PTR(err); goto fail; } } else { ret = pol; break; } } bin = xfrm_policy_inexact_lookup_rcu(net, type, family, dir, if_id); if (!bin || !xfrm_policy_find_inexact_candidates(&cand, bin, saddr, daddr)) goto skip_inexact; pol = xfrm_policy_eval_candidates(&cand, ret, fl, type, family, dir, if_id); if (pol) { ret = pol; if (IS_ERR(pol)) goto fail; } skip_inexact: if (read_seqcount_retry(&net->xfrm.xfrm_policy_hash_generation, sequence)) goto retry; if (ret && !xfrm_pol_hold_rcu(ret)) goto retry; fail: rcu_read_unlock(); return ret; } static struct xfrm_policy *xfrm_policy_lookup(struct net *net, const struct flowi *fl, u16 family, u8 dir, u32 if_id) { #ifdef CONFIG_XFRM_SUB_POLICY struct xfrm_policy *pol; pol = xfrm_policy_lookup_bytype(net, XFRM_POLICY_TYPE_SUB, fl, family, dir, if_id); if (pol != NULL) return pol; #endif return xfrm_policy_lookup_bytype(net, XFRM_POLICY_TYPE_MAIN, fl, family, dir, if_id); } static struct xfrm_policy *xfrm_sk_policy_lookup(const struct sock *sk, int dir, const struct flowi *fl, u16 family, u32 if_id) { struct xfrm_policy *pol; rcu_read_lock(); again: pol = rcu_dereference(sk->sk_policy[dir]); if (pol != NULL) { bool match; int err = 0; if (pol->family != family) { pol = NULL; goto out; } match = xfrm_selector_match(&pol->selector, fl, family); if (match) { if ((sk->sk_mark & pol->mark.m) != pol->mark.v || pol->if_id != if_id) { pol = NULL; goto out; } err = security_xfrm_policy_lookup(pol->security, fl->flowi_secid, dir); if (!err) { if (!xfrm_pol_hold_rcu(pol)) goto again; } else if (err == -ESRCH) { pol = NULL; } else { pol = ERR_PTR(err); } } else pol = NULL; } out: rcu_read_unlock(); return pol; } static void __xfrm_policy_link(struct xfrm_policy *pol, int dir) { struct net *net = xp_net(pol); list_add(&pol->walk.all, &net->xfrm.policy_all); net->xfrm.policy_count[dir]++; xfrm_pol_hold(pol); } static struct xfrm_policy *__xfrm_policy_unlink(struct xfrm_policy *pol, int dir) { struct net *net = xp_net(pol); if (list_empty(&pol->walk.all)) return NULL; /* Socket policies are not hashed. */ if (!hlist_unhashed(&pol->bydst)) { hlist_del_rcu(&pol->bydst); hlist_del_init(&pol->bydst_inexact_list); hlist_del(&pol->byidx); } list_del_init(&pol->walk.all); net->xfrm.policy_count[dir]--; return pol; } static void xfrm_sk_policy_link(struct xfrm_policy *pol, int dir) { __xfrm_policy_link(pol, XFRM_POLICY_MAX + dir); } static void xfrm_sk_policy_unlink(struct xfrm_policy *pol, int dir) { __xfrm_policy_unlink(pol, XFRM_POLICY_MAX + dir); } int xfrm_policy_delete(struct xfrm_policy *pol, int dir) { struct net *net = xp_net(pol); spin_lock_bh(&net->xfrm.xfrm_policy_lock); pol = __xfrm_policy_unlink(pol, dir); spin_unlock_bh(&net->xfrm.xfrm_policy_lock); if (pol) { xfrm_policy_kill(pol); return 0; } return -ENOENT; } EXPORT_SYMBOL(xfrm_policy_delete); int xfrm_sk_policy_insert(struct sock *sk, int dir, struct xfrm_policy *pol) { struct net *net = sock_net(sk); struct xfrm_policy *old_pol; #ifdef CONFIG_XFRM_SUB_POLICY if (pol && pol->type != XFRM_POLICY_TYPE_MAIN) return -EINVAL; #endif spin_lock_bh(&net->xfrm.xfrm_policy_lock); old_pol = rcu_dereference_protected(sk->sk_policy[dir], lockdep_is_held(&net->xfrm.xfrm_policy_lock)); if (pol) { pol->curlft.add_time = ktime_get_real_seconds(); pol->index = xfrm_gen_index(net, XFRM_POLICY_MAX+dir, 0); xfrm_sk_policy_link(pol, dir); } rcu_assign_pointer(sk->sk_policy[dir], pol); if (old_pol) { if (pol) xfrm_policy_requeue(old_pol, pol); /* Unlinking succeeds always. This is the only function * allowed to delete or replace socket policy. */ xfrm_sk_policy_unlink(old_pol, dir); } spin_unlock_bh(&net->xfrm.xfrm_policy_lock); if (old_pol) { xfrm_policy_kill(old_pol); } return 0; } static struct xfrm_policy *clone_policy(const struct xfrm_policy *old, int dir) { struct xfrm_policy *newp = xfrm_policy_alloc(xp_net(old), GFP_ATOMIC); struct net *net = xp_net(old); if (newp) { newp->selector = old->selector; if (security_xfrm_policy_clone(old->security, &newp->security)) { kfree(newp); return NULL; /* ENOMEM */ } newp->lft = old->lft; newp->curlft = old->curlft; newp->mark = old->mark; newp->if_id = old->if_id; newp->action = old->action; newp->flags = old->flags; newp->xfrm_nr = old->xfrm_nr; newp->index = old->index; newp->type = old->type; newp->family = old->family; memcpy(newp->xfrm_vec, old->xfrm_vec, newp->xfrm_nr*sizeof(struct xfrm_tmpl)); spin_lock_bh(&net->xfrm.xfrm_policy_lock); xfrm_sk_policy_link(newp, dir); spin_unlock_bh(&net->xfrm.xfrm_policy_lock); xfrm_pol_put(newp); } return newp; } int __xfrm_sk_clone_policy(struct sock *sk, const struct sock *osk) { const struct xfrm_policy *p; struct xfrm_policy *np; int i, ret = 0; rcu_read_lock(); for (i = 0; i < 2; i++) { p = rcu_dereference(osk->sk_policy[i]); if (p) { np = clone_policy(p, i); if (unlikely(!np)) { ret = -ENOMEM; break; } rcu_assign_pointer(sk->sk_policy[i], np); } } rcu_read_unlock(); return ret; } static int xfrm_get_saddr(struct net *net, int oif, xfrm_address_t *local, xfrm_address_t *remote, unsigned short family, u32 mark) { int err; const struct xfrm_policy_afinfo *afinfo = xfrm_policy_get_afinfo(family); if (unlikely(afinfo == NULL)) return -EINVAL; err = afinfo->get_saddr(net, oif, local, remote, mark); rcu_read_unlock(); return err; } /* Resolve list of templates for the flow, given policy. */ static int xfrm_tmpl_resolve_one(struct xfrm_policy *policy, const struct flowi *fl, struct xfrm_state **xfrm, unsigned short family) { struct net *net = xp_net(policy); int nx; int i, error; xfrm_address_t *daddr = xfrm_flowi_daddr(fl, family); xfrm_address_t *saddr = xfrm_flowi_saddr(fl, family); xfrm_address_t tmp; for (nx = 0, i = 0; i < policy->xfrm_nr; i++) { struct xfrm_state *x; xfrm_address_t *remote = daddr; xfrm_address_t *local = saddr; struct xfrm_tmpl *tmpl = &policy->xfrm_vec[i]; if (tmpl->mode == XFRM_MODE_TUNNEL || tmpl->mode == XFRM_MODE_BEET) { remote = &tmpl->id.daddr; local = &tmpl->saddr; if (xfrm_addr_any(local, tmpl->encap_family)) { error = xfrm_get_saddr(net, fl->flowi_oif, &tmp, remote, tmpl->encap_family, 0); if (error) goto fail; local = &tmp; } } x = xfrm_state_find(remote, local, fl, tmpl, policy, &error, family, policy->if_id); if (x && x->km.state == XFRM_STATE_VALID) { xfrm[nx++] = x; daddr = remote; saddr = local; continue; } if (x) { error = (x->km.state == XFRM_STATE_ERROR ? -EINVAL : -EAGAIN); xfrm_state_put(x); } else if (error == -ESRCH) { error = -EAGAIN; } if (!tmpl->optional) goto fail; } return nx; fail: for (nx--; nx >= 0; nx--) xfrm_state_put(xfrm[nx]); return error; } static int xfrm_tmpl_resolve(struct xfrm_policy **pols, int npols, const struct flowi *fl, struct xfrm_state **xfrm, unsigned short family) { struct xfrm_state *tp[XFRM_MAX_DEPTH]; struct xfrm_state **tpp = (npols > 1) ? tp : xfrm; int cnx = 0; int error; int ret; int i; for (i = 0; i < npols; i++) { if (cnx + pols[i]->xfrm_nr >= XFRM_MAX_DEPTH) { error = -ENOBUFS; goto fail; } ret = xfrm_tmpl_resolve_one(pols[i], fl, &tpp[cnx], family); if (ret < 0) { error = ret; goto fail; } else cnx += ret; } /* found states are sorted for outbound processing */ if (npols > 1) xfrm_state_sort(xfrm, tpp, cnx, family); return cnx; fail: for (cnx--; cnx >= 0; cnx--) xfrm_state_put(tpp[cnx]); return error; } static int xfrm_get_tos(const struct flowi *fl, int family) { if (family == AF_INET) return IPTOS_RT_MASK & fl->u.ip4.flowi4_tos; return 0; } static inline struct xfrm_dst *xfrm_alloc_dst(struct net *net, int family) { const struct xfrm_policy_afinfo *afinfo = xfrm_policy_get_afinfo(family); struct dst_ops *dst_ops; struct xfrm_dst *xdst; if (!afinfo) return ERR_PTR(-EINVAL); switch (family) { case AF_INET: dst_ops = &net->xfrm.xfrm4_dst_ops; break; #if IS_ENABLED(CONFIG_IPV6) case AF_INET6: dst_ops = &net->xfrm.xfrm6_dst_ops; break; #endif default: BUG(); } xdst = dst_alloc(dst_ops, NULL, 1, DST_OBSOLETE_NONE, 0); if (likely(xdst)) { struct dst_entry *dst = &xdst->u.dst; memset(dst + 1, 0, sizeof(*xdst) - sizeof(*dst)); } else xdst = ERR_PTR(-ENOBUFS); rcu_read_unlock(); return xdst; } static void xfrm_init_path(struct xfrm_dst *path, struct dst_entry *dst, int nfheader_len) { if (dst->ops->family == AF_INET6) { struct rt6_info *rt = (struct rt6_info *)dst; path->path_cookie = rt6_get_cookie(rt); path->u.rt6.rt6i_nfheader_len = nfheader_len; } } static inline int xfrm_fill_dst(struct xfrm_dst *xdst, struct net_device *dev, const struct flowi *fl) { const struct xfrm_policy_afinfo *afinfo = xfrm_policy_get_afinfo(xdst->u.dst.ops->family); int err; if (!afinfo) return -EINVAL; err = afinfo->fill_dst(xdst, dev, fl); rcu_read_unlock(); return err; } /* Allocate chain of dst_entry's, attach known xfrm's, calculate * all the metrics... Shortly, bundle a bundle. */ static struct dst_entry *xfrm_bundle_create(struct xfrm_policy *policy, struct xfrm_state **xfrm, struct xfrm_dst **bundle, int nx, const struct flowi *fl, struct dst_entry *dst) { const struct xfrm_state_afinfo *afinfo; const struct xfrm_mode *inner_mode; struct net *net = xp_net(policy); unsigned long now = jiffies; struct net_device *dev; struct xfrm_dst *xdst_prev = NULL; struct xfrm_dst *xdst0 = NULL; int i = 0; int err; int header_len = 0; int nfheader_len = 0; int trailer_len = 0; int tos; int family = policy->selector.family; xfrm_address_t saddr, daddr; xfrm_flowi_addr_get(fl, &saddr, &daddr, family); tos = xfrm_get_tos(fl, family); dst_hold(dst); for (; i < nx; i++) { struct xfrm_dst *xdst = xfrm_alloc_dst(net, family); struct dst_entry *dst1 = &xdst->u.dst; err = PTR_ERR(xdst); if (IS_ERR(xdst)) { dst_release(dst); goto put_states; } bundle[i] = xdst; if (!xdst_prev) xdst0 = xdst; else /* Ref count is taken during xfrm_alloc_dst() * No need to do dst_clone() on dst1 */ xfrm_dst_set_child(xdst_prev, &xdst->u.dst); if (xfrm[i]->sel.family == AF_UNSPEC) { inner_mode = xfrm_ip2inner_mode(xfrm[i], xfrm_af2proto(family)); if (!inner_mode) { err = -EAFNOSUPPORT; dst_release(dst); goto put_states; } } else inner_mode = &xfrm[i]->inner_mode; xdst->route = dst; dst_copy_metrics(dst1, dst); if (xfrm[i]->props.mode != XFRM_MODE_TRANSPORT) { __u32 mark = 0; if (xfrm[i]->props.smark.v || xfrm[i]->props.smark.m) mark = xfrm_smark_get(fl->flowi_mark, xfrm[i]); family = xfrm[i]->props.family; dst = xfrm_dst_lookup(xfrm[i], tos, fl->flowi_oif, &saddr, &daddr, family, mark); err = PTR_ERR(dst); if (IS_ERR(dst)) goto put_states; } else dst_hold(dst); dst1->xfrm = xfrm[i]; xdst->xfrm_genid = xfrm[i]->genid; dst1->obsolete = DST_OBSOLETE_FORCE_CHK; dst1->lastuse = now; dst1->input = dst_discard; rcu_read_lock(); afinfo = xfrm_state_afinfo_get_rcu(inner_mode->family); if (likely(afinfo)) dst1->output = afinfo->output; else dst1->output = dst_discard_out; rcu_read_unlock(); xdst_prev = xdst; header_len += xfrm[i]->props.header_len; if (xfrm[i]->type->flags & XFRM_TYPE_NON_FRAGMENT) nfheader_len += xfrm[i]->props.header_len; trailer_len += xfrm[i]->props.trailer_len; } xfrm_dst_set_child(xdst_prev, dst); xdst0->path = dst; err = -ENODEV; dev = dst->dev; if (!dev) goto free_dst; xfrm_init_path(xdst0, dst, nfheader_len); xfrm_init_pmtu(bundle, nx); for (xdst_prev = xdst0; xdst_prev != (struct xfrm_dst *)dst; xdst_prev = (struct xfrm_dst *) xfrm_dst_child(&xdst_prev->u.dst)) { err = xfrm_fill_dst(xdst_prev, dev, fl); if (err) goto free_dst; xdst_prev->u.dst.header_len = header_len; xdst_prev->u.dst.trailer_len = trailer_len; header_len -= xdst_prev->u.dst.xfrm->props.header_len; trailer_len -= xdst_prev->u.dst.xfrm->props.trailer_len; } return &xdst0->u.dst; put_states: for (; i < nx; i++) xfrm_state_put(xfrm[i]); free_dst: if (xdst0) dst_release_immediate(&xdst0->u.dst); return ERR_PTR(err); } static int xfrm_expand_policies(const struct flowi *fl, u16 family, struct xfrm_policy **pols, int *num_pols, int *num_xfrms) { int i; if (*num_pols == 0 || !pols[0]) { *num_pols = 0; *num_xfrms = 0; return 0; } if (IS_ERR(pols[0])) return PTR_ERR(pols[0]); *num_xfrms = pols[0]->xfrm_nr; #ifdef CONFIG_XFRM_SUB_POLICY if (pols[0] && pols[0]->action == XFRM_POLICY_ALLOW && pols[0]->type != XFRM_POLICY_TYPE_MAIN) { pols[1] = xfrm_policy_lookup_bytype(xp_net(pols[0]), XFRM_POLICY_TYPE_MAIN, fl, family, XFRM_POLICY_OUT, pols[0]->if_id); if (pols[1]) { if (IS_ERR(pols[1])) { xfrm_pols_put(pols, *num_pols); return PTR_ERR(pols[1]); } (*num_pols)++; (*num_xfrms) += pols[1]->xfrm_nr; } } #endif for (i = 0; i < *num_pols; i++) { if (pols[i]->action != XFRM_POLICY_ALLOW) { *num_xfrms = -1; break; } } return 0; } static struct xfrm_dst * xfrm_resolve_and_create_bundle(struct xfrm_policy **pols, int num_pols, const struct flowi *fl, u16 family, struct dst_entry *dst_orig) { struct net *net = xp_net(pols[0]); struct xfrm_state *xfrm[XFRM_MAX_DEPTH]; struct xfrm_dst *bundle[XFRM_MAX_DEPTH]; struct xfrm_dst *xdst; struct dst_entry *dst; int err; /* Try to instantiate a bundle */ err = xfrm_tmpl_resolve(pols, num_pols, fl, xfrm, family); if (err <= 0) { if (err == 0) return NULL; if (err != -EAGAIN) XFRM_INC_STATS(net, LINUX_MIB_XFRMOUTPOLERROR); return ERR_PTR(err); } dst = xfrm_bundle_create(pols[0], xfrm, bundle, err, fl, dst_orig); if (IS_ERR(dst)) { XFRM_INC_STATS(net, LINUX_MIB_XFRMOUTBUNDLEGENERROR); return ERR_CAST(dst); } xdst = (struct xfrm_dst *)dst; xdst->num_xfrms = err; xdst->num_pols = num_pols; memcpy(xdst->pols, pols, sizeof(struct xfrm_policy *) * num_pols); xdst->policy_genid = atomic_read(&pols[0]->genid); return xdst; } static void xfrm_policy_queue_process(struct timer_list *t) { struct sk_buff *skb; struct sock *sk; struct dst_entry *dst; struct xfrm_policy *pol = from_timer(pol, t, polq.hold_timer); struct net *net = xp_net(pol); struct xfrm_policy_queue *pq = &pol->polq; struct flowi fl; struct sk_buff_head list; __u32 skb_mark; spin_lock(&pq->hold_queue.lock); skb = skb_peek(&pq->hold_queue); if (!skb) { spin_unlock(&pq->hold_queue.lock); goto out; } dst = skb_dst(skb); sk = skb->sk; /* Fixup the mark to support VTI. */ skb_mark = skb->mark; skb->mark = pol->mark.v; xfrm_decode_session(skb, &fl, dst->ops->family); skb->mark = skb_mark; spin_unlock(&pq->hold_queue.lock); dst_hold(xfrm_dst_path(dst)); dst = xfrm_lookup(net, xfrm_dst_path(dst), &fl, sk, XFRM_LOOKUP_QUEUE); if (IS_ERR(dst)) goto purge_queue; if (dst->flags & DST_XFRM_QUEUE) { dst_release(dst); if (pq->timeout >= XFRM_QUEUE_TMO_MAX) goto purge_queue; pq->timeout = pq->timeout << 1; if (!mod_timer(&pq->hold_timer, jiffies + pq->timeout)) xfrm_pol_hold(pol); goto out; } dst_release(dst); __skb_queue_head_init(&list); spin_lock(&pq->hold_queue.lock); pq->timeout = 0; skb_queue_splice_init(&pq->hold_queue, &list); spin_unlock(&pq->hold_queue.lock); while (!skb_queue_empty(&list)) { skb = __skb_dequeue(&list); /* Fixup the mark to support VTI. */ skb_mark = skb->mark; skb->mark = pol->mark.v; xfrm_decode_session(skb, &fl, skb_dst(skb)->ops->family); skb->mark = skb_mark; dst_hold(xfrm_dst_path(skb_dst(skb))); dst = xfrm_lookup(net, xfrm_dst_path(skb_dst(skb)), &fl, skb->sk, 0); if (IS_ERR(dst)) { kfree_skb(skb); continue; } nf_reset_ct(skb); skb_dst_drop(skb); skb_dst_set(skb, dst); dst_output(net, skb->sk, skb); } out: xfrm_pol_put(pol); return; purge_queue: pq->timeout = 0; skb_queue_purge(&pq->hold_queue); xfrm_pol_put(pol); } static int xdst_queue_output(struct net *net, struct sock *sk, struct sk_buff *skb) { unsigned long sched_next; struct dst_entry *dst = skb_dst(skb); struct xfrm_dst *xdst = (struct xfrm_dst *) dst; struct xfrm_policy *pol = xdst->pols[0]; struct xfrm_policy_queue *pq = &pol->polq; if (unlikely(skb_fclone_busy(sk, skb))) { kfree_skb(skb); return 0; } if (pq->hold_queue.qlen > XFRM_MAX_QUEUE_LEN) { kfree_skb(skb); return -EAGAIN; } skb_dst_force(skb); spin_lock_bh(&pq->hold_queue.lock); if (!pq->timeout) pq->timeout = XFRM_QUEUE_TMO_MIN; sched_next = jiffies + pq->timeout; if (del_timer(&pq->hold_timer)) { if (time_before(pq->hold_timer.expires, sched_next)) sched_next = pq->hold_timer.expires; xfrm_pol_put(pol); } __skb_queue_tail(&pq->hold_queue, skb); if (!mod_timer(&pq->hold_timer, sched_next)) xfrm_pol_hold(pol); spin_unlock_bh(&pq->hold_queue.lock); return 0; } static struct xfrm_dst *xfrm_create_dummy_bundle(struct net *net, struct xfrm_flo *xflo, const struct flowi *fl, int num_xfrms, u16 family) { int err; struct net_device *dev; struct dst_entry *dst; struct dst_entry *dst1; struct xfrm_dst *xdst; xdst = xfrm_alloc_dst(net, family); if (IS_ERR(xdst)) return xdst; if (!(xflo->flags & XFRM_LOOKUP_QUEUE) || net->xfrm.sysctl_larval_drop || num_xfrms <= 0) return xdst; dst = xflo->dst_orig; dst1 = &xdst->u.dst; dst_hold(dst); xdst->route = dst; dst_copy_metrics(dst1, dst); dst1->obsolete = DST_OBSOLETE_FORCE_CHK; dst1->flags |= DST_XFRM_QUEUE; dst1->lastuse = jiffies; dst1->input = dst_discard; dst1->output = xdst_queue_output; dst_hold(dst); xfrm_dst_set_child(xdst, dst); xdst->path = dst; xfrm_init_path((struct xfrm_dst *)dst1, dst, 0); err = -ENODEV; dev = dst->dev; if (!dev) goto free_dst; err = xfrm_fill_dst(xdst, dev, fl); if (err) goto free_dst; out: return xdst; free_dst: dst_release(dst1); xdst = ERR_PTR(err); goto out; } static struct xfrm_dst *xfrm_bundle_lookup(struct net *net, const struct flowi *fl, u16 family, u8 dir, struct xfrm_flo *xflo, u32 if_id) { struct xfrm_policy *pols[XFRM_POLICY_TYPE_MAX]; int num_pols = 0, num_xfrms = 0, err; struct xfrm_dst *xdst; /* Resolve policies to use if we couldn't get them from * previous cache entry */ num_pols = 1; pols[0] = xfrm_policy_lookup(net, fl, family, dir, if_id); err = xfrm_expand_policies(fl, family, pols, &num_pols, &num_xfrms); if (err < 0) goto inc_error; if (num_pols == 0) return NULL; if (num_xfrms <= 0) goto make_dummy_bundle; xdst = xfrm_resolve_and_create_bundle(pols, num_pols, fl, family, xflo->dst_orig); if (IS_ERR(xdst)) { err = PTR_ERR(xdst); if (err == -EREMOTE) { xfrm_pols_put(pols, num_pols); return NULL; } if (err != -EAGAIN) goto error; goto make_dummy_bundle; } else if (xdst == NULL) { num_xfrms = 0; goto make_dummy_bundle; } return xdst; make_dummy_bundle: /* We found policies, but there's no bundles to instantiate: * either because the policy blocks, has no transformations or * we could not build template (no xfrm_states).*/ xdst = xfrm_create_dummy_bundle(net, xflo, fl, num_xfrms, family); if (IS_ERR(xdst)) { xfrm_pols_put(pols, num_pols); return ERR_CAST(xdst); } xdst->num_pols = num_pols; xdst->num_xfrms = num_xfrms; memcpy(xdst->pols, pols, sizeof(struct xfrm_policy *) * num_pols); return xdst; inc_error: XFRM_INC_STATS(net, LINUX_MIB_XFRMOUTPOLERROR); error: xfrm_pols_put(pols, num_pols); return ERR_PTR(err); } static struct dst_entry *make_blackhole(struct net *net, u16 family, struct dst_entry *dst_orig) { const struct xfrm_policy_afinfo *afinfo = xfrm_policy_get_afinfo(family); struct dst_entry *ret; if (!afinfo) { dst_release(dst_orig); return ERR_PTR(-EINVAL); } else { ret = afinfo->blackhole_route(net, dst_orig); } rcu_read_unlock(); return ret; } /* Finds/creates a bundle for given flow and if_id * * At the moment we eat a raw IP route. Mostly to speed up lookups * on interfaces with disabled IPsec. * * xfrm_lookup uses an if_id of 0 by default, and is provided for * compatibility */ struct dst_entry *xfrm_lookup_with_ifid(struct net *net, struct dst_entry *dst_orig, const struct flowi *fl, const struct sock *sk, int flags, u32 if_id) { struct xfrm_policy *pols[XFRM_POLICY_TYPE_MAX]; struct xfrm_dst *xdst; struct dst_entry *dst, *route; u16 family = dst_orig->ops->family; u8 dir = XFRM_POLICY_OUT; int i, err, num_pols, num_xfrms = 0, drop_pols = 0; dst = NULL; xdst = NULL; route = NULL; sk = sk_const_to_full_sk(sk); if (sk && sk->sk_policy[XFRM_POLICY_OUT]) { num_pols = 1; pols[0] = xfrm_sk_policy_lookup(sk, XFRM_POLICY_OUT, fl, family, if_id); err = xfrm_expand_policies(fl, family, pols, &num_pols, &num_xfrms); if (err < 0) goto dropdst; if (num_pols) { if (num_xfrms <= 0) { drop_pols = num_pols; goto no_transform; } xdst = xfrm_resolve_and_create_bundle( pols, num_pols, fl, family, dst_orig); if (IS_ERR(xdst)) { xfrm_pols_put(pols, num_pols); err = PTR_ERR(xdst); if (err == -EREMOTE) goto nopol; goto dropdst; } else if (xdst == NULL) { num_xfrms = 0; drop_pols = num_pols; goto no_transform; } route = xdst->route; } } if (xdst == NULL) { struct xfrm_flo xflo; xflo.dst_orig = dst_orig; xflo.flags = flags; /* To accelerate a bit... */ if (!if_id && ((dst_orig->flags & DST_NOXFRM) || !net->xfrm.policy_count[XFRM_POLICY_OUT])) goto nopol; xdst = xfrm_bundle_lookup(net, fl, family, dir, &xflo, if_id); if (xdst == NULL) goto nopol; if (IS_ERR(xdst)) { err = PTR_ERR(xdst); goto dropdst; } num_pols = xdst->num_pols; num_xfrms = xdst->num_xfrms; memcpy(pols, xdst->pols, sizeof(struct xfrm_policy *) * num_pols); route = xdst->route; } dst = &xdst->u.dst; if (route == NULL && num_xfrms > 0) { /* The only case when xfrm_bundle_lookup() returns a * bundle with null route, is when the template could * not be resolved. It means policies are there, but * bundle could not be created, since we don't yet * have the xfrm_state's. We need to wait for KM to * negotiate new SA's or bail out with error.*/ if (net->xfrm.sysctl_larval_drop) { XFRM_INC_STATS(net, LINUX_MIB_XFRMOUTNOSTATES); err = -EREMOTE; goto error; } err = -EAGAIN; XFRM_INC_STATS(net, LINUX_MIB_XFRMOUTNOSTATES); goto error; } no_transform: if (num_pols == 0) goto nopol; if ((flags & XFRM_LOOKUP_ICMP) && !(pols[0]->flags & XFRM_POLICY_ICMP)) { err = -ENOENT; goto error; } for (i = 0; i < num_pols; i++) pols[i]->curlft.use_time = ktime_get_real_seconds(); if (num_xfrms < 0) { /* Prohibit the flow */ XFRM_INC_STATS(net, LINUX_MIB_XFRMOUTPOLBLOCK); err = -EPERM; goto error; } else if (num_xfrms > 0) { /* Flow transformed */ dst_release(dst_orig); } else { /* Flow passes untransformed */ dst_release(dst); dst = dst_orig; } ok: xfrm_pols_put(pols, drop_pols); if (dst && dst->xfrm && dst->xfrm->props.mode == XFRM_MODE_TUNNEL) dst->flags |= DST_XFRM_TUNNEL; return dst; nopol: if (!(flags & XFRM_LOOKUP_ICMP)) { dst = dst_orig; goto ok; } err = -ENOENT; error: dst_release(dst); dropdst: if (!(flags & XFRM_LOOKUP_KEEP_DST_REF)) dst_release(dst_orig); xfrm_pols_put(pols, drop_pols); return ERR_PTR(err); } EXPORT_SYMBOL(xfrm_lookup_with_ifid); /* Main function: finds/creates a bundle for given flow. * * At the moment we eat a raw IP route. Mostly to speed up lookups * on interfaces with disabled IPsec. */ struct dst_entry *xfrm_lookup(struct net *net, struct dst_entry *dst_orig, const struct flowi *fl, const struct sock *sk, int flags) { return xfrm_lookup_with_ifid(net, dst_orig, fl, sk, flags, 0); } EXPORT_SYMBOL(xfrm_lookup); /* Callers of xfrm_lookup_route() must ensure a call to dst_output(). * Otherwise we may send out blackholed packets. */ struct dst_entry *xfrm_lookup_route(struct net *net, struct dst_entry *dst_orig, const struct flowi *fl, const struct sock *sk, int flags) { struct dst_entry *dst = xfrm_lookup(net, dst_orig, fl, sk, flags | XFRM_LOOKUP_QUEUE | XFRM_LOOKUP_KEEP_DST_REF); if (PTR_ERR(dst) == -EREMOTE) return make_blackhole(net, dst_orig->ops->family, dst_orig); if (IS_ERR(dst)) dst_release(dst_orig); return dst; } EXPORT_SYMBOL(xfrm_lookup_route); static inline int xfrm_secpath_reject(int idx, struct sk_buff *skb, const struct flowi *fl) { struct sec_path *sp = skb_sec_path(skb); struct xfrm_state *x; if (!sp || idx < 0 || idx >= sp->len) return 0; x = sp->xvec[idx]; if (!x->type->reject) return 0; return x->type->reject(x, skb, fl); } /* When skb is transformed back to its "native" form, we have to * check policy restrictions. At the moment we make this in maximally * stupid way. Shame on me. :-) Of course, connected sockets must * have policy cached at them. */ static inline int xfrm_state_ok(const struct xfrm_tmpl *tmpl, const struct xfrm_state *x, unsigned short family) { if (xfrm_state_kern(x)) return tmpl->optional && !xfrm_state_addr_cmp(tmpl, x, tmpl->encap_family); return x->id.proto == tmpl->id.proto && (x->id.spi == tmpl->id.spi || !tmpl->id.spi) && (x->props.reqid == tmpl->reqid || !tmpl->reqid) && x->props.mode == tmpl->mode && (tmpl->allalgs || (tmpl->aalgos & (1<<x->props.aalgo)) || !(xfrm_id_proto_match(tmpl->id.proto, IPSEC_PROTO_ANY))) && !(x->props.mode != XFRM_MODE_TRANSPORT && xfrm_state_addr_cmp(tmpl, x, family)); } /* * 0 or more than 0 is returned when validation is succeeded (either bypass * because of optional transport mode, or next index of the mathced secpath * state with the template. * -1 is returned when no matching template is found. * Otherwise "-2 - errored_index" is returned. */ static inline int xfrm_policy_ok(const struct xfrm_tmpl *tmpl, const struct sec_path *sp, int start, unsigned short family) { int idx = start; if (tmpl->optional) { if (tmpl->mode == XFRM_MODE_TRANSPORT) return start; } else start = -1; for (; idx < sp->len; idx++) { if (xfrm_state_ok(tmpl, sp->xvec[idx], family)) return ++idx; if (sp->xvec[idx]->props.mode != XFRM_MODE_TRANSPORT) { if (start == -1) start = -2-idx; break; } } return start; } static void decode_session4(struct sk_buff *skb, struct flowi *fl, bool reverse) { const struct iphdr *iph = ip_hdr(skb); int ihl = iph->ihl; u8 *xprth = skb_network_header(skb) + ihl * 4; struct flowi4 *fl4 = &fl->u.ip4; int oif = 0; if (skb_dst(skb) && skb_dst(skb)->dev) oif = skb_dst(skb)->dev->ifindex; memset(fl4, 0, sizeof(struct flowi4)); fl4->flowi4_mark = skb->mark; fl4->flowi4_oif = reverse ? skb->skb_iif : oif; fl4->flowi4_proto = iph->protocol; fl4->daddr = reverse ? iph->saddr : iph->daddr; fl4->saddr = reverse ? iph->daddr : iph->saddr; fl4->flowi4_tos = iph->tos; if (!ip_is_fragment(iph)) { switch (iph->protocol) { case IPPROTO_UDP: case IPPROTO_UDPLITE: case IPPROTO_TCP: case IPPROTO_SCTP: case IPPROTO_DCCP: if (xprth + 4 < skb->data || pskb_may_pull(skb, xprth + 4 - skb->data)) { __be16 *ports; xprth = skb_network_header(skb) + ihl * 4; ports = (__be16 *)xprth; fl4->fl4_sport = ports[!!reverse]; fl4->fl4_dport = ports[!reverse]; } break; case IPPROTO_ICMP: if (xprth + 2 < skb->data || pskb_may_pull(skb, xprth + 2 - skb->data)) { u8 *icmp; xprth = skb_network_header(skb) + ihl * 4; icmp = xprth; fl4->fl4_icmp_type = icmp[0]; fl4->fl4_icmp_code = icmp[1]; } break; case IPPROTO_ESP: if (xprth + 4 < skb->data || pskb_may_pull(skb, xprth + 4 - skb->data)) { __be32 *ehdr; xprth = skb_network_header(skb) + ihl * 4; ehdr = (__be32 *)xprth; fl4->fl4_ipsec_spi = ehdr[0]; } break; case IPPROTO_AH: if (xprth + 8 < skb->data || pskb_may_pull(skb, xprth + 8 - skb->data)) { __be32 *ah_hdr; xprth = skb_network_header(skb) + ihl * 4; ah_hdr = (__be32 *)xprth; fl4->fl4_ipsec_spi = ah_hdr[1]; } break; case IPPROTO_COMP: if (xprth + 4 < skb->data || pskb_may_pull(skb, xprth + 4 - skb->data)) { __be16 *ipcomp_hdr; xprth = skb_network_header(skb) + ihl * 4; ipcomp_hdr = (__be16 *)xprth; fl4->fl4_ipsec_spi = htonl(ntohs(ipcomp_hdr[1])); } break; case IPPROTO_GRE: if (xprth + 12 < skb->data || pskb_may_pull(skb, xprth + 12 - skb->data)) { __be16 *greflags; __be32 *gre_hdr; xprth = skb_network_header(skb) + ihl * 4; greflags = (__be16 *)xprth; gre_hdr = (__be32 *)xprth; if (greflags[0] & GRE_KEY) { if (greflags[0] & GRE_CSUM) gre_hdr++; fl4->fl4_gre_key = gre_hdr[1]; } } break; default: fl4->fl4_ipsec_spi = 0; break; } } } #if IS_ENABLED(CONFIG_IPV6) static void decode_session6(struct sk_buff *skb, struct flowi *fl, bool reverse) { struct flowi6 *fl6 = &fl->u.ip6; int onlyproto = 0; const struct ipv6hdr *hdr = ipv6_hdr(skb); u32 offset = sizeof(*hdr); struct ipv6_opt_hdr *exthdr; const unsigned char *nh = skb_network_header(skb); u16 nhoff = IP6CB(skb)->nhoff; int oif = 0; u8 nexthdr; if (!nhoff) nhoff = offsetof(struct ipv6hdr, nexthdr); nexthdr = nh[nhoff]; if (skb_dst(skb) && skb_dst(skb)->dev) oif = skb_dst(skb)->dev->ifindex; memset(fl6, 0, sizeof(struct flowi6)); fl6->flowi6_mark = skb->mark; fl6->flowi6_oif = reverse ? skb->skb_iif : oif; fl6->daddr = reverse ? hdr->saddr : hdr->daddr; fl6->saddr = reverse ? hdr->daddr : hdr->saddr; while (nh + offset + sizeof(*exthdr) < skb->data || pskb_may_pull(skb, nh + offset + sizeof(*exthdr) - skb->data)) { nh = skb_network_header(skb); exthdr = (struct ipv6_opt_hdr *)(nh + offset); switch (nexthdr) { case NEXTHDR_FRAGMENT: onlyproto = 1; fallthrough; case NEXTHDR_ROUTING: case NEXTHDR_HOP: case NEXTHDR_DEST: offset += ipv6_optlen(exthdr); nexthdr = exthdr->nexthdr; exthdr = (struct ipv6_opt_hdr *)(nh + offset); break; case IPPROTO_UDP: case IPPROTO_UDPLITE: case IPPROTO_TCP: case IPPROTO_SCTP: case IPPROTO_DCCP: if (!onlyproto && (nh + offset + 4 < skb->data || pskb_may_pull(skb, nh + offset + 4 - skb->data))) { __be16 *ports; nh = skb_network_header(skb); ports = (__be16 *)(nh + offset); fl6->fl6_sport = ports[!!reverse]; fl6->fl6_dport = ports[!reverse]; } fl6->flowi6_proto = nexthdr; return; case IPPROTO_ICMPV6: if (!onlyproto && (nh + offset + 2 < skb->data || pskb_may_pull(skb, nh + offset + 2 - skb->data))) { u8 *icmp; nh = skb_network_header(skb); icmp = (u8 *)(nh + offset); fl6->fl6_icmp_type = icmp[0]; fl6->fl6_icmp_code = icmp[1]; } fl6->flowi6_proto = nexthdr; return; #if IS_ENABLED(CONFIG_IPV6_MIP6) case IPPROTO_MH: offset += ipv6_optlen(exthdr); if (!onlyproto && (nh + offset + 3 < skb->data || pskb_may_pull(skb, nh + offset + 3 - skb->data))) { struct ip6_mh *mh; nh = skb_network_header(skb); mh = (struct ip6_mh *)(nh + offset); fl6->fl6_mh_type = mh->ip6mh_type; } fl6->flowi6_proto = nexthdr; return; #endif /* XXX Why are there these headers? */ case IPPROTO_AH: case IPPROTO_ESP: case IPPROTO_COMP: default: fl6->fl6_ipsec_spi = 0; fl6->flowi6_proto = nexthdr; return; } } } #endif int __xfrm_decode_session(struct sk_buff *skb, struct flowi *fl, unsigned int family, int reverse) { switch (family) { case AF_INET: decode_session4(skb, fl, reverse); break; #if IS_ENABLED(CONFIG_IPV6) case AF_INET6: decode_session6(skb, fl, reverse); break; #endif default: return -EAFNOSUPPORT; } return security_xfrm_decode_session(skb, &fl->flowi_secid); } EXPORT_SYMBOL(__xfrm_decode_session); static inline int secpath_has_nontransport(const struct sec_path *sp, int k, int *idxp) { for (; k < sp->len; k++) { if (sp->xvec[k]->props.mode != XFRM_MODE_TRANSPORT) { *idxp = k; return 1; } } return 0; } int __xfrm_policy_check(struct sock *sk, int dir, struct sk_buff *skb, unsigned short family) { struct net *net = dev_net(skb->dev); struct xfrm_policy *pol; struct xfrm_policy *pols[XFRM_POLICY_TYPE_MAX]; int npols = 0; int xfrm_nr; int pi; int reverse; struct flowi fl; int xerr_idx = -1; const struct xfrm_if_cb *ifcb; struct sec_path *sp; struct xfrm_if *xi; u32 if_id = 0; rcu_read_lock(); ifcb = xfrm_if_get_cb(); if (ifcb) { xi = ifcb->decode_session(skb, family); if (xi) { if_id = xi->p.if_id; net = xi->net; } } rcu_read_unlock(); reverse = dir & ~XFRM_POLICY_MASK; dir &= XFRM_POLICY_MASK; if (__xfrm_decode_session(skb, &fl, family, reverse) < 0) { XFRM_INC_STATS(net, LINUX_MIB_XFRMINHDRERROR); return 0; } nf_nat_decode_session(skb, &fl, family); /* First, check used SA against their selectors. */ sp = skb_sec_path(skb); if (sp) { int i; for (i = sp->len - 1; i >= 0; i--) { struct xfrm_state *x = sp->xvec[i]; if (!xfrm_selector_match(&x->sel, &fl, family)) { XFRM_INC_STATS(net, LINUX_MIB_XFRMINSTATEMISMATCH); return 0; } } } pol = NULL; sk = sk_to_full_sk(sk); if (sk && sk->sk_policy[dir]) { pol = xfrm_sk_policy_lookup(sk, dir, &fl, family, if_id); if (IS_ERR(pol)) { XFRM_INC_STATS(net, LINUX_MIB_XFRMINPOLERROR); return 0; } } if (!pol) pol = xfrm_policy_lookup(net, &fl, family, dir, if_id); if (IS_ERR(pol)) { XFRM_INC_STATS(net, LINUX_MIB_XFRMINPOLERROR); return 0; } if (!pol) { if (sp && secpath_has_nontransport(sp, 0, &xerr_idx)) { xfrm_secpath_reject(xerr_idx, skb, &fl); XFRM_INC_STATS(net, LINUX_MIB_XFRMINNOPOLS); return 0; } return 1; } pol->curlft.use_time = ktime_get_real_seconds(); pols[0] = pol; npols++; #ifdef CONFIG_XFRM_SUB_POLICY if (pols[0]->type != XFRM_POLICY_TYPE_MAIN) { pols[1] = xfrm_policy_lookup_bytype(net, XFRM_POLICY_TYPE_MAIN, &fl, family, XFRM_POLICY_IN, if_id); if (pols[1]) { if (IS_ERR(pols[1])) { XFRM_INC_STATS(net, LINUX_MIB_XFRMINPOLERROR); return 0; } pols[1]->curlft.use_time = ktime_get_real_seconds(); npols++; } } #endif if (pol->action == XFRM_POLICY_ALLOW) { static struct sec_path dummy; struct xfrm_tmpl *tp[XFRM_MAX_DEPTH]; struct xfrm_tmpl *stp[XFRM_MAX_DEPTH]; struct xfrm_tmpl **tpp = tp; int ti = 0; int i, k; sp = skb_sec_path(skb); if (!sp) sp = &dummy; for (pi = 0; pi < npols; pi++) { if (pols[pi] != pol && pols[pi]->action != XFRM_POLICY_ALLOW) { XFRM_INC_STATS(net, LINUX_MIB_XFRMINPOLBLOCK); goto reject; } if (ti + pols[pi]->xfrm_nr >= XFRM_MAX_DEPTH) { XFRM_INC_STATS(net, LINUX_MIB_XFRMINBUFFERERROR); goto reject_error; } for (i = 0; i < pols[pi]->xfrm_nr; i++) tpp[ti++] = &pols[pi]->xfrm_vec[i]; } xfrm_nr = ti; if (npols > 1) { xfrm_tmpl_sort(stp, tpp, xfrm_nr, family); tpp = stp; } /* For each tunnel xfrm, find the first matching tmpl. * For each tmpl before that, find corresponding xfrm. * Order is _important_. Later we will implement * some barriers, but at the moment barriers * are implied between each two transformations. */ for (i = xfrm_nr-1, k = 0; i >= 0; i--) { k = xfrm_policy_ok(tpp[i], sp, k, family); if (k < 0) { if (k < -1) /* "-2 - errored_index" returned */ xerr_idx = -(2+k); XFRM_INC_STATS(net, LINUX_MIB_XFRMINTMPLMISMATCH); goto reject; } } if (secpath_has_nontransport(sp, k, &xerr_idx)) { XFRM_INC_STATS(net, LINUX_MIB_XFRMINTMPLMISMATCH); goto reject; } xfrm_pols_put(pols, npols); return 1; } XFRM_INC_STATS(net, LINUX_MIB_XFRMINPOLBLOCK); reject: xfrm_secpath_reject(xerr_idx, skb, &fl); reject_error: xfrm_pols_put(pols, npols); return 0; } EXPORT_SYMBOL(__xfrm_policy_check); int __xfrm_route_forward(struct sk_buff *skb, unsigned short family) { struct net *net = dev_net(skb->dev); struct flowi fl; struct dst_entry *dst; int res = 1; if (xfrm_decode_session(skb, &fl, family) < 0) { XFRM_INC_STATS(net, LINUX_MIB_XFRMFWDHDRERROR); return 0; } skb_dst_force(skb); if (!skb_dst(skb)) { XFRM_INC_STATS(net, LINUX_MIB_XFRMFWDHDRERROR); return 0; } dst = xfrm_lookup(net, skb_dst(skb), &fl, NULL, XFRM_LOOKUP_QUEUE); if (IS_ERR(dst)) { res = 0; dst = NULL; } skb_dst_set(skb, dst); return res; } EXPORT_SYMBOL(__xfrm_route_forward); /* Optimize later using cookies and generation ids. */ static struct dst_entry *xfrm_dst_check(struct dst_entry *dst, u32 cookie) { /* Code (such as __xfrm4_bundle_create()) sets dst->obsolete * to DST_OBSOLETE_FORCE_CHK to force all XFRM destinations to * get validated by dst_ops->check on every use. We do this * because when a normal route referenced by an XFRM dst is * obsoleted we do not go looking around for all parent * referencing XFRM dsts so that we can invalidate them. It * is just too much work. Instead we make the checks here on * every use. For example: * * XFRM dst A --> IPv4 dst X * * X is the "xdst->route" of A (X is also the "dst->path" of A * in this example). If X is marked obsolete, "A" will not * notice. That's what we are validating here via the * stale_bundle() check. * * When a dst is removed from the fib tree, DST_OBSOLETE_DEAD will * be marked on it. * This will force stale_bundle() to fail on any xdst bundle with * this dst linked in it. */ if (dst->obsolete < 0 && !stale_bundle(dst)) return dst; return NULL; } static int stale_bundle(struct dst_entry *dst) { return !xfrm_bundle_ok((struct xfrm_dst *)dst); } void xfrm_dst_ifdown(struct dst_entry *dst, struct net_device *dev) { while ((dst = xfrm_dst_child(dst)) && dst->xfrm && dst->dev == dev) { dst->dev = dev_net(dev)->loopback_dev; dev_hold(dst->dev); dev_put(dev); } } EXPORT_SYMBOL(xfrm_dst_ifdown); static void xfrm_link_failure(struct sk_buff *skb) { /* Impossible. Such dst must be popped before reaches point of failure. */ } static struct dst_entry *xfrm_negative_advice(struct dst_entry *dst) { if (dst) { if (dst->obsolete) { dst_release(dst); dst = NULL; } } return dst; } static void xfrm_init_pmtu(struct xfrm_dst **bundle, int nr) { while (nr--) { struct xfrm_dst *xdst = bundle[nr]; u32 pmtu, route_mtu_cached; struct dst_entry *dst; dst = &xdst->u.dst; pmtu = dst_mtu(xfrm_dst_child(dst)); xdst->child_mtu_cached = pmtu; pmtu = xfrm_state_mtu(dst->xfrm, pmtu); route_mtu_cached = dst_mtu(xdst->route); xdst->route_mtu_cached = route_mtu_cached; if (pmtu > route_mtu_cached) pmtu = route_mtu_cached; dst_metric_set(dst, RTAX_MTU, pmtu); } } /* Check that the bundle accepts the flow and its components are * still valid. */ static int xfrm_bundle_ok(struct xfrm_dst *first) { struct xfrm_dst *bundle[XFRM_MAX_DEPTH]; struct dst_entry *dst = &first->u.dst; struct xfrm_dst *xdst; int start_from, nr; u32 mtu; if (!dst_check(xfrm_dst_path(dst), ((struct xfrm_dst *)dst)->path_cookie) || (dst->dev && !netif_running(dst->dev))) return 0; if (dst->flags & DST_XFRM_QUEUE) return 1; start_from = nr = 0; do { struct xfrm_dst *xdst = (struct xfrm_dst *)dst; if (dst->xfrm->km.state != XFRM_STATE_VALID) return 0; if (xdst->xfrm_genid != dst->xfrm->genid) return 0; if (xdst->num_pols > 0 && xdst->policy_genid != atomic_read(&xdst->pols[0]->genid)) return 0; bundle[nr++] = xdst; mtu = dst_mtu(xfrm_dst_child(dst)); if (xdst->child_mtu_cached != mtu) { start_from = nr; xdst->child_mtu_cached = mtu; } if (!dst_check(xdst->route, xdst->route_cookie)) return 0; mtu = dst_mtu(xdst->route); if (xdst->route_mtu_cached != mtu) { start_from = nr; xdst->route_mtu_cached = mtu; } dst = xfrm_dst_child(dst); } while (dst->xfrm); if (likely(!start_from)) return 1; xdst = bundle[start_from - 1]; mtu = xdst->child_mtu_cached; while (start_from--) { dst = &xdst->u.dst; mtu = xfrm_state_mtu(dst->xfrm, mtu); if (mtu > xdst->route_mtu_cached) mtu = xdst->route_mtu_cached; dst_metric_set(dst, RTAX_MTU, mtu); if (!start_from) break; xdst = bundle[start_from - 1]; xdst->child_mtu_cached = mtu; } return 1; } static unsigned int xfrm_default_advmss(const struct dst_entry *dst) { return dst_metric_advmss(xfrm_dst_path(dst)); } static unsigned int xfrm_mtu(const struct dst_entry *dst) { unsigned int mtu = dst_metric_raw(dst, RTAX_MTU); return mtu ? : dst_mtu(xfrm_dst_path(dst)); } static const void *xfrm_get_dst_nexthop(const struct dst_entry *dst, const void *daddr) { while (dst->xfrm) { const struct xfrm_state *xfrm = dst->xfrm; dst = xfrm_dst_child(dst); if (xfrm->props.mode == XFRM_MODE_TRANSPORT) continue; if (xfrm->type->flags & XFRM_TYPE_REMOTE_COADDR) daddr = xfrm->coaddr; else if (!(xfrm->type->flags & XFRM_TYPE_LOCAL_COADDR)) daddr = &xfrm->id.daddr; } return daddr; } static struct neighbour *xfrm_neigh_lookup(const struct dst_entry *dst, struct sk_buff *skb, const void *daddr) { const struct dst_entry *path = xfrm_dst_path(dst); if (!skb) daddr = xfrm_get_dst_nexthop(dst, daddr); return path->ops->neigh_lookup(path, skb, daddr); } static void xfrm_confirm_neigh(const struct dst_entry *dst, const void *daddr) { const struct dst_entry *path = xfrm_dst_path(dst); daddr = xfrm_get_dst_nexthop(dst, daddr); path->ops->confirm_neigh(path, daddr); } int xfrm_policy_register_afinfo(const struct xfrm_policy_afinfo *afinfo, int family) { int err = 0; if (WARN_ON(family >= ARRAY_SIZE(xfrm_policy_afinfo))) return -EAFNOSUPPORT; spin_lock(&xfrm_policy_afinfo_lock); if (unlikely(xfrm_policy_afinfo[family] != NULL)) err = -EEXIST; else { struct dst_ops *dst_ops = afinfo->dst_ops; if (likely(dst_ops->kmem_cachep == NULL)) dst_ops->kmem_cachep = xfrm_dst_cache; if (likely(dst_ops->check == NULL)) dst_ops->check = xfrm_dst_check; if (likely(dst_ops->default_advmss == NULL)) dst_ops->default_advmss = xfrm_default_advmss; if (likely(dst_ops->mtu == NULL)) dst_ops->mtu = xfrm_mtu; if (likely(dst_ops->negative_advice == NULL)) dst_ops->negative_advice = xfrm_negative_advice; if (likely(dst_ops->link_failure == NULL)) dst_ops->link_failure = xfrm_link_failure; if (likely(dst_ops->neigh_lookup == NULL)) dst_ops->neigh_lookup = xfrm_neigh_lookup; if (likely(!dst_ops->confirm_neigh)) dst_ops->confirm_neigh = xfrm_confirm_neigh; rcu_assign_pointer(xfrm_policy_afinfo[family], afinfo); } spin_unlock(&xfrm_policy_afinfo_lock); return err; } EXPORT_SYMBOL(xfrm_policy_register_afinfo); void xfrm_policy_unregister_afinfo(const struct xfrm_policy_afinfo *afinfo) { struct dst_ops *dst_ops = afinfo->dst_ops; int i; for (i = 0; i < ARRAY_SIZE(xfrm_policy_afinfo); i++) { if (xfrm_policy_afinfo[i] != afinfo) continue; RCU_INIT_POINTER(xfrm_policy_afinfo[i], NULL); break; } synchronize_rcu(); dst_ops->kmem_cachep = NULL; dst_ops->check = NULL; dst_ops->negative_advice = NULL; dst_ops->link_failure = NULL; } EXPORT_SYMBOL(xfrm_policy_unregister_afinfo); void xfrm_if_register_cb(const struct xfrm_if_cb *ifcb) { spin_lock(&xfrm_if_cb_lock); rcu_assign_pointer(xfrm_if_cb, ifcb); spin_unlock(&xfrm_if_cb_lock); } EXPORT_SYMBOL(xfrm_if_register_cb); void xfrm_if_unregister_cb(void) { RCU_INIT_POINTER(xfrm_if_cb, NULL); synchronize_rcu(); } EXPORT_SYMBOL(xfrm_if_unregister_cb); #ifdef CONFIG_XFRM_STATISTICS static int __net_init xfrm_statistics_init(struct net *net) { int rv; net->mib.xfrm_statistics = alloc_percpu(struct linux_xfrm_mib); if (!net->mib.xfrm_statistics) return -ENOMEM; rv = xfrm_proc_init(net); if (rv < 0) free_percpu(net->mib.xfrm_statistics); return rv; } static void xfrm_statistics_fini(struct net *net) { xfrm_proc_fini(net); free_percpu(net->mib.xfrm_statistics); } #else static int __net_init xfrm_statistics_init(struct net *net) { return 0; } static void xfrm_statistics_fini(struct net *net) { } #endif static int __net_init xfrm_policy_init(struct net *net) { unsigned int hmask, sz; int dir, err; if (net_eq(net, &init_net)) { xfrm_dst_cache = kmem_cache_create("xfrm_dst_cache", sizeof(struct xfrm_dst), 0, SLAB_HWCACHE_ALIGN|SLAB_PANIC, NULL); err = rhashtable_init(&xfrm_policy_inexact_table, &xfrm_pol_inexact_params); BUG_ON(err); } hmask = 8 - 1; sz = (hmask+1) * sizeof(struct hlist_head); net->xfrm.policy_byidx = xfrm_hash_alloc(sz); if (!net->xfrm.policy_byidx) goto out_byidx; net->xfrm.policy_idx_hmask = hmask; for (dir = 0; dir < XFRM_POLICY_MAX; dir++) { struct xfrm_policy_hash *htab; net->xfrm.policy_count[dir] = 0; net->xfrm.policy_count[XFRM_POLICY_MAX + dir] = 0; INIT_HLIST_HEAD(&net->xfrm.policy_inexact[dir]); htab = &net->xfrm.policy_bydst[dir]; htab->table = xfrm_hash_alloc(sz); if (!htab->table) goto out_bydst; htab->hmask = hmask; htab->dbits4 = 32; htab->sbits4 = 32; htab->dbits6 = 128; htab->sbits6 = 128; } net->xfrm.policy_hthresh.lbits4 = 32; net->xfrm.policy_hthresh.rbits4 = 32; net->xfrm.policy_hthresh.lbits6 = 128; net->xfrm.policy_hthresh.rbits6 = 128; seqlock_init(&net->xfrm.policy_hthresh.lock); INIT_LIST_HEAD(&net->xfrm.policy_all); INIT_LIST_HEAD(&net->xfrm.inexact_bins); INIT_WORK(&net->xfrm.policy_hash_work, xfrm_hash_resize); INIT_WORK(&net->xfrm.policy_hthresh.work, xfrm_hash_rebuild); return 0; out_bydst: for (dir--; dir >= 0; dir--) { struct xfrm_policy_hash *htab; htab = &net->xfrm.policy_bydst[dir]; xfrm_hash_free(htab->table, sz); } xfrm_hash_free(net->xfrm.policy_byidx, sz); out_byidx: return -ENOMEM; } static void xfrm_policy_fini(struct net *net) { struct xfrm_pol_inexact_bin *b, *t; unsigned int sz; int dir; flush_work(&net->xfrm.policy_hash_work); #ifdef CONFIG_XFRM_SUB_POLICY xfrm_policy_flush(net, XFRM_POLICY_TYPE_SUB, false); #endif xfrm_policy_flush(net, XFRM_POLICY_TYPE_MAIN, false); WARN_ON(!list_empty(&net->xfrm.policy_all)); for (dir = 0; dir < XFRM_POLICY_MAX; dir++) { struct xfrm_policy_hash *htab; WARN_ON(!hlist_empty(&net->xfrm.policy_inexact[dir])); htab = &net->xfrm.policy_bydst[dir]; sz = (htab->hmask + 1) * sizeof(struct hlist_head); WARN_ON(!hlist_empty(htab->table)); xfrm_hash_free(htab->table, sz); } sz = (net->xfrm.policy_idx_hmask + 1) * sizeof(struct hlist_head); WARN_ON(!hlist_empty(net->xfrm.policy_byidx)); xfrm_hash_free(net->xfrm.policy_byidx, sz); spin_lock_bh(&net->xfrm.xfrm_policy_lock); list_for_each_entry_safe(b, t, &net->xfrm.inexact_bins, inexact_bins) __xfrm_policy_inexact_prune_bin(b, true); spin_unlock_bh(&net->xfrm.xfrm_policy_lock); } static int __net_init xfrm_net_init(struct net *net) { int rv; /* Initialize the per-net locks here */ spin_lock_init(&net->xfrm.xfrm_state_lock); spin_lock_init(&net->xfrm.xfrm_policy_lock); seqcount_spinlock_init(&net->xfrm.xfrm_policy_hash_generation, &net->xfrm.xfrm_policy_lock); mutex_init(&net->xfrm.xfrm_cfg_mutex); rv = xfrm_statistics_init(net); if (rv < 0) goto out_statistics; rv = xfrm_state_init(net); if (rv < 0) goto out_state; rv = xfrm_policy_init(net); if (rv < 0) goto out_policy; rv = xfrm_sysctl_init(net); if (rv < 0) goto out_sysctl; return 0; out_sysctl: xfrm_policy_fini(net); out_policy: xfrm_state_fini(net); out_state: xfrm_statistics_fini(net); out_statistics: return rv; } static void __net_exit xfrm_net_exit(struct net *net) { xfrm_sysctl_fini(net); xfrm_policy_fini(net); xfrm_state_fini(net); xfrm_statistics_fini(net); } static struct pernet_operations __net_initdata xfrm_net_ops = { .init = xfrm_net_init, .exit = xfrm_net_exit, }; void __init xfrm_init(void) { register_pernet_subsys(&xfrm_net_ops); xfrm_dev_init(); xfrm_input_init(); #ifdef CONFIG_XFRM_ESPIN