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