1/* SPDX-License-Identifier: GPL-2.0 */ 2/* 3 * Operations on the network namespace 4 */ 5#ifndef __NET_NET_NAMESPACE_H 6#define __NET_NET_NAMESPACE_H 7 8#include <linux/atomic.h> 9#include <linux/refcount.h> 10#include <linux/workqueue.h> 11#include <linux/list.h> 12#include <linux/sysctl.h> 13#include <linux/uidgid.h> 14 15#include <net/flow.h> 16#include <net/netns/core.h> 17#include <net/netns/mib.h> 18#include <net/netns/unix.h> 19#include <net/netns/packet.h> 20#include <net/netns/ipv4.h> 21#include <net/netns/ipv6.h> 22#include <net/netns/nexthop.h> 23#include <net/netns/ieee802154_6lowpan.h> 24#include <net/netns/sctp.h> 25#include <net/netns/netfilter.h> 26#if defined(CONFIG_NF_CONNTRACK) || defined(CONFIG_NF_CONNTRACK_MODULE) 27#include <net/netns/conntrack.h> 28#endif 29#if IS_ENABLED(CONFIG_NF_FLOW_TABLE) 30#include <net/netns/flow_table.h> 31#endif 32#include <net/netns/nftables.h> 33#include <net/netns/xfrm.h> 34#include <net/netns/mpls.h> 35#include <net/netns/can.h> 36#include <net/netns/xdp.h> 37#include <net/netns/smc.h> 38#include <net/netns/bpf.h> 39#include <net/netns/mctp.h> 40#include <net/net_trackers.h> 41#include <linux/ns_common.h> 42#include <linux/idr.h> 43#include <linux/skbuff.h> 44#include <linux/notifier.h> 45#include <linux/xarray.h> 46 47struct user_namespace; 48struct proc_dir_entry; 49struct net_device; 50struct sock; 51struct ctl_table_header; 52struct net_generic; 53struct uevent_sock; 54struct netns_ipvs; 55struct bpf_prog; 56 57 58#define NETDEV_HASHBITS 8 59#define NETDEV_HASHENTRIES (1 << NETDEV_HASHBITS) 60 61struct net { 62 /* First cache line can be often dirtied. 63 * Do not place here read-mostly fields. 64 */ 65 refcount_t passive; /* To decide when the network 66 * namespace should be freed. 67 */ 68 spinlock_t rules_mod_lock; 69 70 atomic_t dev_unreg_count; 71 72 unsigned int dev_base_seq; /* protected by rtnl_mutex */ 73 u32 ifindex; 74 75 spinlock_t nsid_lock; 76 atomic_t fnhe_genid; 77 78 struct list_head list; /* list of network namespaces */ 79 struct list_head exit_list; /* To linked to call pernet exit 80 * methods on dead net ( 81 * pernet_ops_rwsem read locked), 82 * or to unregister pernet ops 83 * (pernet_ops_rwsem write locked). 84 */ 85 struct llist_node cleanup_list; /* namespaces on death row */ 86 87#ifdef CONFIG_KEYS 88 struct key_tag *key_domain; /* Key domain of operation tag */ 89#endif 90 struct user_namespace *user_ns; /* Owning user namespace */ 91 struct ucounts *ucounts; 92 struct idr netns_ids; 93 94 struct ns_common ns; 95 struct ref_tracker_dir refcnt_tracker; 96 struct ref_tracker_dir notrefcnt_tracker; /* tracker for objects not 97 * refcounted against netns 98 */ 99 struct list_head dev_base_head; 100 struct proc_dir_entry *proc_net; 101 struct proc_dir_entry *proc_net_stat; 102 103#ifdef CONFIG_SYSCTL 104 struct ctl_table_set sysctls; 105#endif 106 107 struct sock *rtnl; /* rtnetlink socket */ 108 struct sock *genl_sock; 109 110 struct uevent_sock *uevent_sock; /* uevent socket */ 111 112 struct hlist_head *dev_name_head; 113 struct hlist_head *dev_index_head; 114 struct xarray dev_by_index; 115 struct raw_notifier_head netdev_chain; 116 117 /* Note that @hash_mix can be read millions times per second, 118 * it is critical that it is on a read_mostly cache line. 119 */ 120 u32 hash_mix; 121 122 struct net_device *loopback_dev; /* The loopback */ 123 124 /* core fib_rules */ 125 struct list_head rules_ops; 126 127 struct netns_core core; 128 struct netns_mib mib; 129 struct netns_packet packet; 130#if IS_ENABLED(CONFIG_UNIX) 131 struct netns_unix unx; 132#endif 133 struct netns_nexthop nexthop; 134 struct netns_ipv4 ipv4; 135#if IS_ENABLED(CONFIG_IPV6) 136 struct netns_ipv6 ipv6; 137#endif 138#if IS_ENABLED(CONFIG_IEEE802154_6LOWPAN) 139 struct netns_ieee802154_lowpan ieee802154_lowpan; 140#endif 141#if defined(CONFIG_IP_SCTP) || defined(CONFIG_IP_SCTP_MODULE) 142 struct netns_sctp sctp; 143#endif 144#ifdef CONFIG_NETFILTER 145 struct netns_nf nf; 146#if defined(CONFIG_NF_CONNTRACK) || defined(CONFIG_NF_CONNTRACK_MODULE) 147 struct netns_ct ct; 148#endif 149#if defined(CONFIG_NF_TABLES) || defined(CONFIG_NF_TABLES_MODULE) 150 struct netns_nftables nft; 151#endif 152#if IS_ENABLED(CONFIG_NF_FLOW_TABLE) 153 struct netns_ft ft; 154#endif 155#endif 156#ifdef CONFIG_WEXT_CORE 157 struct sk_buff_head wext_nlevents; 158#endif 159 struct net_generic __rcu *gen; 160 161 /* Used to store attached BPF programs */ 162 struct netns_bpf bpf; 163 164 /* Note : following structs are cache line aligned */ 165#ifdef CONFIG_XFRM 166 struct netns_xfrm xfrm; 167#endif 168 169 u64 net_cookie; /* written once */ 170 171#if IS_ENABLED(CONFIG_IP_VS) 172 struct netns_ipvs *ipvs; 173#endif 174#if IS_ENABLED(CONFIG_MPLS) 175 struct netns_mpls mpls; 176#endif 177#if IS_ENABLED(CONFIG_CAN) 178 struct netns_can can; 179#endif 180#ifdef CONFIG_XDP_SOCKETS 181 struct netns_xdp xdp; 182#endif 183#if IS_ENABLED(CONFIG_MCTP) 184 struct netns_mctp mctp; 185#endif 186#if IS_ENABLED(CONFIG_CRYPTO_USER) 187 struct sock *crypto_nlsk; 188#endif 189 struct sock *diag_nlsk; 190#if IS_ENABLED(CONFIG_SMC) 191 struct netns_smc smc; 192#endif 193} __randomize_layout; 194 195#include <linux/seq_file_net.h> 196 197/* Init's network namespace */ 198extern struct net init_net; 199 200#ifdef CONFIG_NET_NS 201struct net *copy_net_ns(unsigned long flags, struct user_namespace *user_ns, 202 struct net *old_net); 203 204void net_ns_get_ownership(const struct net *net, kuid_t *uid, kgid_t *gid); 205 206void net_ns_barrier(void); 207 208struct ns_common *get_net_ns(struct ns_common *ns); 209struct net *get_net_ns_by_fd(int fd); 210#else /* CONFIG_NET_NS */ 211#include <linux/sched.h> 212#include <linux/nsproxy.h> 213static inline struct net *copy_net_ns(unsigned long flags, 214 struct user_namespace *user_ns, struct net *old_net) 215{ 216 if (flags & CLONE_NEWNET) 217 return ERR_PTR(-EINVAL); 218 return old_net; 219} 220 221static inline void net_ns_get_ownership(const struct net *net, 222 kuid_t *uid, kgid_t *gid) 223{ 224 *uid = GLOBAL_ROOT_UID; 225 *gid = GLOBAL_ROOT_GID; 226} 227 228static inline void net_ns_barrier(void) {} 229 230static inline struct ns_common *get_net_ns(struct ns_common *ns) 231{ 232 return ERR_PTR(-EINVAL); 233} 234 235static inline struct net *get_net_ns_by_fd(int fd) 236{ 237 return ERR_PTR(-EINVAL); 238} 239#endif /* CONFIG_NET_NS */ 240 241 242extern struct list_head net_namespace_list; 243 244struct net *get_net_ns_by_pid(pid_t pid); 245 246#ifdef CONFIG_SYSCTL 247void ipx_register_sysctl(void); 248void ipx_unregister_sysctl(void); 249#else 250#define ipx_register_sysctl() 251#define ipx_unregister_sysctl() 252#endif 253 254#ifdef CONFIG_NET_NS 255void __put_net(struct net *net); 256 257/* Try using get_net_track() instead */ 258static inline struct net *get_net(struct net *net) 259{ 260 refcount_inc(&net->ns.count); 261 return net; 262} 263 264static inline struct net *maybe_get_net(struct net *net) 265{ 266 /* Used when we know struct net exists but we 267 * aren't guaranteed a previous reference count 268 * exists. If the reference count is zero this 269 * function fails and returns NULL. 270 */ 271 if (!refcount_inc_not_zero(&net->ns.count)) 272 net = NULL; 273 return net; 274} 275 276/* Try using put_net_track() instead */ 277static inline void put_net(struct net *net) 278{ 279 if (refcount_dec_and_test(&net->ns.count)) 280 __put_net(net); 281} 282 283static inline 284int net_eq(const struct net *net1, const struct net *net2) 285{ 286 return net1 == net2; 287} 288 289static inline int check_net(const struct net *net) 290{ 291 return refcount_read(&net->ns.count) != 0; 292} 293 294void net_drop_ns(void *); 295 296#else 297 298static inline struct net *get_net(struct net *net) 299{ 300 return net; 301} 302 303static inline void put_net(struct net *net) 304{ 305} 306 307static inline struct net *maybe_get_net(struct net *net) 308{ 309 return net; 310} 311 312static inline 313int net_eq(const struct net *net1, const struct net *net2) 314{ 315 return 1; 316} 317 318static inline int check_net(const struct net *net) 319{ 320 return 1; 321} 322 323#define net_drop_ns NULL 324#endif 325 326 327static inline void __netns_tracker_alloc(struct net *net, 328 netns_tracker *tracker, 329 bool refcounted, 330 gfp_t gfp) 331{ 332#ifdef CONFIG_NET_NS_REFCNT_TRACKER 333 ref_tracker_alloc(refcounted ? &net->refcnt_tracker : 334 &net->notrefcnt_tracker, 335 tracker, gfp); 336#endif 337} 338 339static inline void netns_tracker_alloc(struct net *net, netns_tracker *tracker, 340 gfp_t gfp) 341{ 342 __netns_tracker_alloc(net, tracker, true, gfp); 343} 344 345static inline void __netns_tracker_free(struct net *net, 346 netns_tracker *tracker, 347 bool refcounted) 348{ 349#ifdef CONFIG_NET_NS_REFCNT_TRACKER 350 ref_tracker_free(refcounted ? &net->refcnt_tracker : 351 &net->notrefcnt_tracker, tracker); 352#endif 353} 354 355static inline struct net *get_net_track(struct net *net, 356 netns_tracker *tracker, gfp_t gfp) 357{ 358 get_net(net); 359 netns_tracker_alloc(net, tracker, gfp); 360 return net; 361} 362 363static inline void put_net_track(struct net *net, netns_tracker *tracker) 364{ 365 __netns_tracker_free(net, tracker, true); 366 put_net(net); 367} 368 369typedef struct { 370#ifdef CONFIG_NET_NS 371 struct net *net; 372#endif 373} possible_net_t; 374 375static inline void write_pnet(possible_net_t *pnet, struct net *net) 376{ 377#ifdef CONFIG_NET_NS 378 pnet->net = net; 379#endif 380} 381 382static inline struct net *read_pnet(const possible_net_t *pnet) 383{ 384#ifdef CONFIG_NET_NS 385 return pnet->net; 386#else 387 return &init_net; 388#endif 389} 390 391/* Protected by net_rwsem */ 392#define for_each_net(VAR) \ 393 list_for_each_entry(VAR, &net_namespace_list, list) 394#define for_each_net_continue_reverse(VAR) \ 395 list_for_each_entry_continue_reverse(VAR, &net_namespace_list, list) 396#define for_each_net_rcu(VAR) \ 397 list_for_each_entry_rcu(VAR, &net_namespace_list, list) 398 399#ifdef CONFIG_NET_NS 400#define __net_init 401#define __net_exit 402#define __net_initdata 403#define __net_initconst 404#else 405#define __net_init __init 406#define __net_exit __ref 407#define __net_initdata __initdata 408#define __net_initconst __initconst 409#endif 410 411int peernet2id_alloc(struct net *net, struct net *peer, gfp_t gfp); 412int peernet2id(const struct net *net, struct net *peer); 413bool peernet_has_id(const struct net *net, struct net *peer); 414struct net *get_net_ns_by_id(const struct net *net, int id); 415 416struct pernet_operations { 417 struct list_head list; 418 /* 419 * Below methods are called without any exclusive locks. 420 * More than one net may be constructed and destructed 421 * in parallel on several cpus. Every pernet_operations 422 * have to keep in mind all other pernet_operations and 423 * to introduce a locking, if they share common resources. 424 * 425 * The only time they are called with exclusive lock is 426 * from register_pernet_subsys(), unregister_pernet_subsys() 427 * register_pernet_device() and unregister_pernet_device(). 428 * 429 * Exit methods using blocking RCU primitives, such as 430 * synchronize_rcu(), should be implemented via exit_batch. 431 * Then, destruction of a group of net requires single 432 * synchronize_rcu() related to these pernet_operations, 433 * instead of separate synchronize_rcu() for every net. 434 * Please, avoid synchronize_rcu() at all, where it's possible. 435 * 436 * Note that a combination of pre_exit() and exit() can 437 * be used, since a synchronize_rcu() is guaranteed between 438 * the calls. 439 */ 440 int (*init)(struct net *net); 441 void (*pre_exit)(struct net *net); 442 void (*exit)(struct net *net); 443 void (*exit_batch)(struct list_head *net_exit_list); 444 unsigned int *id; 445 size_t size; 446}; 447 448/* 449 * Use these carefully. If you implement a network device and it 450 * needs per network namespace operations use device pernet operations, 451 * otherwise use pernet subsys operations. 452 * 453 * Network interfaces need to be removed from a dying netns _before_ 454 * subsys notifiers can be called, as most of the network code cleanup 455 * (which is done from subsys notifiers) runs with the assumption that 456 * dev_remove_pack has been called so no new packets will arrive during 457 * and after the cleanup functions have been called. dev_remove_pack 458 * is not per namespace so instead the guarantee of no more packets 459 * arriving in a network namespace is provided by ensuring that all 460 * network devices and all sockets have left the network namespace 461 * before the cleanup methods are called. 462 * 463 * For the longest time the ipv4 icmp code was registered as a pernet 464 * device which caused kernel oops, and panics during network 465 * namespace cleanup. So please don't get this wrong. 466 */ 467int register_pernet_subsys(struct pernet_operations *); 468void unregister_pernet_subsys(struct pernet_operations *); 469int register_pernet_device(struct pernet_operations *); 470void unregister_pernet_device(struct pernet_operations *); 471 472struct ctl_table; 473 474#define register_net_sysctl(net, path, table) \ 475 register_net_sysctl_sz(net, path, table, ARRAY_SIZE(table)) 476#ifdef CONFIG_SYSCTL 477int net_sysctl_init(void); 478struct ctl_table_header *register_net_sysctl_sz(struct net *net, const char *path, 479 struct ctl_table *table, size_t table_size); 480void unregister_net_sysctl_table(struct ctl_table_header *header); 481#else 482static inline int net_sysctl_init(void) { return 0; } 483static inline struct ctl_table_header *register_net_sysctl_sz(struct net *net, 484 const char *path, struct ctl_table *table, size_t table_size) 485{ 486 return NULL; 487} 488static inline void unregister_net_sysctl_table(struct ctl_table_header *header) 489{ 490} 491#endif 492 493static inline int rt_genid_ipv4(const struct net *net) 494{ 495 return atomic_read(&net->ipv4.rt_genid); 496} 497 498#if IS_ENABLED(CONFIG_IPV6) 499static inline int rt_genid_ipv6(const struct net *net) 500{ 501 return atomic_read(&net->ipv6.fib6_sernum); 502} 503#endif 504 505static inline void rt_genid_bump_ipv4(struct net *net) 506{ 507 atomic_inc(&net->ipv4.rt_genid); 508} 509 510extern void (*__fib6_flush_trees)(struct net *net); 511static inline void rt_genid_bump_ipv6(struct net *net) 512{ 513 if (__fib6_flush_trees) 514 __fib6_flush_trees(net); 515} 516 517#if IS_ENABLED(CONFIG_IEEE802154_6LOWPAN) 518static inline struct netns_ieee802154_lowpan * 519net_ieee802154_lowpan(struct net *net) 520{ 521 return &net->ieee802154_lowpan; 522} 523#endif 524 525/* For callers who don't really care about whether it's IPv4 or IPv6 */ 526static inline void rt_genid_bump_all(struct net *net) 527{ 528 rt_genid_bump_ipv4(net); 529 rt_genid_bump_ipv6(net); 530} 531 532static inline int fnhe_genid(const struct net *net) 533{ 534 return atomic_read(&net->fnhe_genid); 535} 536 537static inline void fnhe_genid_bump(struct net *net) 538{ 539 atomic_inc(&net->fnhe_genid); 540} 541 542#ifdef CONFIG_NET 543void net_ns_init(void); 544#else 545static inline void net_ns_init(void) {} 546#endif 547 548#endif /* __NET_NET_NAMESPACE_H */ 549