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
|
/* SPDX-License-Identifier: GPL-2.0 */
/*
* Operations on the network namespace
*/
#ifndef __NET_NET_NAMESPACE_H
#define __NET_NET_NAMESPACE_H
#include <linux/atomic.h>
#include <linux/refcount.h>
#include <linux/workqueue.h>
#include <linux/list.h>
#include <linux/sysctl.h>
#include <linux/uidgid.h>
#include <net/flow.h>
#include <net/netns/core.h>
#include <net/netns/mib.h>
#include <net/netns/unix.h>
#include <net/netns/packet.h>
#include <net/netns/ipv4.h>
#include <net/netns/ipv6.h>
#include <net/netns/nexthop.h>
#include <net/netns/ieee802154_6lowpan.h>
#include <net/netns/sctp.h>
#include <net/netns/dccp.h>
#include <net/netns/netfilter.h>
#include <net/netns/x_tables.h>
#if defined(CONFIG_NF_CONNTRACK) || defined(CONFIG_NF_CONNTRACK_MODULE)
#include <net/netns/conntrack.h>
#endif
#include <net/netns/nftables.h>
#include <net/netns/xfrm.h>
#include <net/netns/mpls.h>
#include <net/netns/can.h>
#include <net/netns/xdp.h>
#include <net/netns/bpf.h>
#include <linux/ns_common.h>
#include <linux/idr.h>
#include <linux/skbuff.h>
#include <linux/notifier.h>
struct user_namespace;
struct proc_dir_entry;
struct net_device;
struct sock;
struct ctl_table_header;
struct net_generic;
struct uevent_sock;
struct netns_ipvs;
struct bpf_prog;
#define NETDEV_HASHBITS 8
#define NETDEV_HASHENTRIES (1 << NETDEV_HASHBITS)
struct net {
/* First cache line can be often dirtied.
* Do not place here read-mostly fields.
*/
refcount_t passive; /* To decide when the network
* namespace should be freed.
*/
spinlock_t rules_mod_lock;
unsigned int dev_unreg_count;
unsigned int dev_base_seq; /* protected by rtnl_mutex */
int ifindex;
spinlock_t nsid_lock;
atomic_t fnhe_genid;
struct list_head list; /* list of network namespaces */
struct list_head exit_list; /* To linked to call pernet exit
* methods on dead net (
* pernet_ops_rwsem read locked),
* or to unregister pernet ops
* (pernet_ops_rwsem write locked).
*/
struct llist_node cleanup_list; /* namespaces on death row */
#ifdef CONFIG_KEYS
struct key_tag *key_domain; /* Key domain of operation tag */
#endif
struct user_namespace *user_ns; /* Owning user namespace */
struct ucounts *ucounts;
struct idr netns_ids;
struct ns_common ns;
struct list_head dev_base_head;
struct proc_dir_entry *proc_net;
struct proc_dir_entry *proc_net_stat;
#ifdef CONFIG_SYSCTL
struct ctl_table_set sysctls;
#endif
struct sock *rtnl; /* rtnetlink socket */
struct sock *genl_sock;
struct uevent_sock *uevent_sock; /* uevent socket */
struct hlist_head *dev_name_head;
struct hlist_head *dev_index_head;
struct raw_notifier_head netdev_chain;
/* Note that @hash_mix can be read millions times per second,
* it is critical that it is on a read_mostly cache line.
*/
u32 hash_mix;
struct net_device *loopback_dev; /* The loopback */
/* core fib_rules */
struct list_head rules_ops;
struct netns_core core;
struct netns_mib mib;
struct netns_packet packet;
struct netns_unix unx;
struct netns_nexthop nexthop;
struct netns_ipv4 ipv4;
#if IS_ENABLED(CONFIG_IPV6)
struct netns_ipv6 ipv6;
#endif
#if IS_ENABLED(CONFIG_IEEE802154_6LOWPAN)
struct netns_ieee802154_lowpan ieee802154_lowpan;
#endif
#if defined(CONFIG_IP_SCTP) || defined(CONFIG_IP_SCTP_MODULE)
struct netns_sctp sctp;
#endif
#if defined(CONFIG_IP_DCCP) || defined(CONFIG_IP_DCCP_MODULE)
struct netns_dccp dccp;
#endif
#ifdef CONFIG_NETFILTER
struct netns_nf nf;
struct netns_xt xt;
#if defined(CONFIG_NF_CONNTRACK) || defined(CONFIG_NF_CONNTRACK_MODULE)
struct netns_ct ct;
#endif
#if defined(CONFIG_NF_TABLES) || defined(CONFIG_NF_TABLES_MODULE)
struct netns_nftables nft;
#endif
#if IS_ENABLED(CONFIG_NF_DEFRAG_IPV6)
struct netns_nf_frag nf_frag;
struct ctl_table_header *nf_frag_frags_hdr;
#endif
struct sock *nfnl;
struct sock *nfnl_stash;
#if IS_ENABLED(CONFIG_NETFILTER_NETLINK_ACCT)
struct list_head nfnl_acct_list;
#endif
#if IS_ENABLED(CONFIG_NF_CT_NETLINK_TIMEOUT)
struct list_head nfct_timeout_list;
#endif
#endif
#ifdef CONFIG_WEXT_CORE
struct sk_buff_head wext_nlevents;
#endif
struct net_generic __rcu *gen;
/* Used to store attached BPF programs */
struct netns_bpf bpf;
/* Note : following structs are cache line aligned */
#ifdef CONFIG_XFRM
struct netns_xfrm xfrm;
#endif
atomic64_t net_cookie; /* written once */
#if IS_ENABLED(CONFIG_IP_VS)
struct netns_ipvs *ipvs;
#endif
#if IS_ENABLED(CONFIG_MPLS)
struct netns_mpls mpls;
#endif
#if IS_ENABLED(CONFIG_CAN)
struct netns_can can;
#endif
#ifdef CONFIG_XDP_SOCKETS
struct netns_xdp xdp;
#endif
#if IS_ENABLED(CONFIG_CRYPTO_USER)
struct sock *crypto_nlsk;
#endif
struct sock *diag_nlsk;
} __randomize_layout;
#include <linux/seq_file_net.h>
/* Init's network namespace */
extern struct net init_net;
#ifdef CONFIG_NET_NS
struct net *copy_net_ns(unsigned long flags, struct user_namespace *user_ns,
struct net *old_net);
void net_ns_get_ownership(const struct net *net, kuid_t *uid, kgid_t *gid);
void net_ns_barrier(void);
#else /* CONFIG_NET_NS */
#include <linux/sched.h>
#include <linux/nsproxy.h>
static inline struct net *copy_net_ns(unsigned long flags,
struct user_namespace *user_ns, struct net *old_net)
{
if (flags & CLONE_NEWNET)
return ERR_PTR(-EINVAL);
return old_net;
}
static inline void net_ns_get_ownership(const struct net *net,
kuid_t *uid, kgid_t *gid)
{
*uid = GLOBAL_ROOT_UID;
*gid = GLOBAL_ROOT_GID;
}
static inline void net_ns_barrier(void) {}
#endif /* CONFIG_NET_NS */
extern struct list_head net_namespace_list;
struct net *get_net_ns_by_pid(pid_t pid);
struct net *get_net_ns_by_fd(int fd);
u64 net_gen_cookie(struct net *net);
#ifdef CONFIG_SYSCTL
void ipx_register_sysctl(void);
void ipx_unregister_sysctl(void);
#else
#define ipx_register_sysctl()
#define ipx_unregister_sysctl()
#endif
#ifdef CONFIG_NET_NS
void __put_net(struct net *net);
static inline struct net *get_net(struct net *net)
{
refcount_inc(&net->ns.count);
return net;
}
static inline struct net *maybe_get_net(struct net *net)
{
/* Used when we know struct net exists but we
* aren't guaranteed a previous reference count
* exists. If the reference count is zero this
* function fails and returns NULL.
*/
if (!refcount_inc_not_zero(&net->ns.count))
net = NULL;
return net;
}
static inline void put_net(struct net *net)
{
if (refcount_dec_and_test(&net->ns.count))
__put_net(net);
}
static inline
int net_eq(const struct net *net1, const struct net *net2)
{
return net1 == net2;
}
static inline int check_net(const struct net *net)
{
return refcount_read(&net->ns.count) != 0;
}
void net_drop_ns(void *);
#else
static inline struct net *get_net(struct net *net)
{
return net;
}
static inline void put_net(struct net *net)
{
}
static inline struct net *maybe_get_net(struct net *net)
{
return net;
}
static inline
int net_eq(const struct net *net1, const struct net *net2)
{
return 1;
}
static inline int check_net(const struct net *net)
{
return 1;
}
#define net_drop_ns NULL
#endif
typedef struct {
#ifdef CONFIG_NET_NS
struct net *net;
#endif
} possible_net_t;
static inline void write_pnet(possible_net_t *pnet, struct net *net)
{
#ifdef CONFIG_NET_NS
pnet->net = net;
#endif
}
static inline struct net *read_pnet(const possible_net_t *pnet)
{
#ifdef CONFIG_NET_NS
return pnet->net;
#else
return &init_net;
#endif
}
/* Protected by net_rwsem */
#define for_each_net(VAR) \
list_for_each_entry(VAR, &net_namespace_list, list)
#define for_each_net_continue_reverse(VAR) \
list_for_each_entry_continue_reverse(VAR, &net_namespace_list, list)
#define for_each_net_rcu(VAR) \
list_for_each_entry_rcu(VAR, &net_namespace_list, list)
#ifdef CONFIG_NET_NS
#define __net_init
#define __net_exit
#define __net_initdata
#define __net_initconst
#else
#define __net_init __init
#define __net_exit __ref
#define __net_initdata __initdata
#define __net_initconst __initconst
#endif
int peernet2id_alloc(struct net *net, struct net *peer, gfp_t gfp);
int peernet2id(const struct net *net, struct net *peer);
bool peernet_has_id(const struct net *net, struct net *peer);
struct net *get_net_ns_by_id(const struct net *net, int id);
struct pernet_operations {
struct list_head list;
/*
* Below methods are called without any exclusive locks.
* More than one net may be constructed and destructed
* in parallel on several cpus. Every pernet_operations
* have to keep in mind all other pernet_operations and
* to introduce a locking, if they share common resources.
*
* The only time they are called with exclusive lock is
* from register_pernet_subsys(), unregister_pernet_subsys()
* register_pernet_device() and unregister_pernet_device().
*
* Exit methods using blocking RCU primitives, such as
* synchronize_rcu(), should be implemented via exit_batch.
* Then, destruction of a group of net requires single
* synchronize_rcu() related to these pernet_operations,
* instead of separate synchronize_rcu() for every net.
* Please, avoid synchronize_rcu() at all, where it's possible.
*
* Note that a combination of pre_exit() and exit() can
* be used, since a synchronize_rcu() is guaranteed between
* the calls.
*/
int (*init)(struct net *net);
void (*pre_exit)(struct net *net);
void (*exit)(struct net *net);
void (*exit_batch)(struct list_head *net_exit_list);
unsigned int *id;
size_t size;
};
/*
* Use these carefully. If you implement a network device and it
* needs per network namespace operations use device pernet operations,
* otherwise use pernet subsys operations.
*
* Network interfaces need to be removed from a dying netns _before_
* subsys notifiers can be called, as most of the network code cleanup
* (which is done from subsys notifiers) runs with the assumption that
* dev_remove_pack has been called so no new packets will arrive during
* and after the cleanup functions have been called. dev_remove_pack
* is not per namespace so instead the guarantee of no more packets
* arriving in a network namespace is provided by ensuring that all
* network devices and all sockets have left the network namespace
* before the cleanup methods are called.
*
* For the longest time the ipv4 icmp code was registered as a pernet
* device which caused kernel oops, and panics during network
* namespace cleanup. So please don't get this wrong.
*/
int register_pernet_subsys(struct pernet_operations *);
void unregister_pernet_subsys(struct pernet_operations *);
int register_pernet_device(struct pernet_operations *);
void unregister_pernet_device(struct pernet_operations *);
struct ctl_table;
struct ctl_table_header;
#ifdef CONFIG_SYSCTL
int net_sysctl_init(void);
struct ctl_table_header *register_net_sysctl(struct net *net, const char *path,
struct ctl_table *table);
void unregister_net_sysctl_table(struct ctl_table_header *header);
#else
static inline int net_sysctl_init(void) { return 0; }
static inline struct ctl_table_header *register_net_sysctl(struct net *net,
const char *path, struct ctl_table *table)
{
return NULL;
}
static inline void unregister_net_sysctl_table(struct ctl_table_header *header)
{
}
#endif
static inline int rt_genid_ipv4(const struct net *net)
{
return atomic_read(&net->ipv4.rt_genid);
}
#if IS_ENABLED(CONFIG_IPV6)
static inline int rt_genid_ipv6(const struct net *net)
{
return atomic_read(&net->ipv6.fib6_sernum);
}
#endif
static inline void rt_genid_bump_ipv4(struct net *net)
{
atomic_inc(&net->ipv4.rt_genid);
}
extern void (*__fib6_flush_trees)(struct net *net);
static inline void rt_genid_bump_ipv6(struct net *net)
{
if (__fib6_flush_trees)
__fib6_flush_trees(net);
}
#if IS_ENABLED(CONFIG_IEEE802154_6LOWPAN)
static inline struct netns_ieee802154_lowpan *
net_ieee802154_lowpan(struct net *net)
{
return &net->ieee802154_lowpan;
}
#endif
/* For callers who don't really care about whether it's IPv4 or IPv6 */
static inline void rt_genid_bump_all(struct net *net)
{
rt_genid_bump_ipv4(net);
rt_genid_bump_ipv6(net);
}
static inline int fnhe_genid(const struct net *net)
{
return atomic_read(&net->fnhe_genid);
}
static inline void fnhe_genid_bump(struct net *net)
{
atomic_inc(&net->fnhe_genid);
}
#endif /* __NET_NET_NAMESPACE_H */
|