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
|
/* SPDX-License-Identifier: GPL-2.0 */
/*
* sysctl.h: General linux system control interface
*
* Begun 24 March 1995, Stephen Tweedie
*
****************************************************************
****************************************************************
**
** WARNING:
** The values in this file are exported to user space via
** the sysctl() binary interface. Do *NOT* change the
** numbering of any existing values here, and do not change
** any numbers within any one set of values. If you have to
** redefine an existing interface, use a new number for it.
** The kernel will then return -ENOTDIR to any application using
** the old binary interface.
**
****************************************************************
****************************************************************
*/
#ifndef _LINUX_SYSCTL_H
#define _LINUX_SYSCTL_H
#include <linux/list.h>
#include <linux/rcupdate.h>
#include <linux/wait.h>
#include <linux/rbtree.h>
#include <linux/uidgid.h>
#include <uapi/linux/sysctl.h>
/* For the /proc/sys support */
struct completion;
struct ctl_table;
struct nsproxy;
struct ctl_table_root;
struct ctl_table_header;
struct ctl_dir;
/* Keep the same order as in fs/proc/proc_sysctl.c */
#define SYSCTL_ZERO ((void *)&sysctl_vals[0])
#define SYSCTL_ONE ((void *)&sysctl_vals[1])
#define SYSCTL_TWO ((void *)&sysctl_vals[2])
#define SYSCTL_THREE ((void *)&sysctl_vals[3])
#define SYSCTL_FOUR ((void *)&sysctl_vals[4])
#define SYSCTL_ONE_HUNDRED ((void *)&sysctl_vals[5])
#define SYSCTL_TWO_HUNDRED ((void *)&sysctl_vals[6])
#define SYSCTL_ONE_THOUSAND ((void *)&sysctl_vals[7])
#define SYSCTL_THREE_THOUSAND ((void *)&sysctl_vals[8])
#define SYSCTL_INT_MAX ((void *)&sysctl_vals[9])
/* this is needed for the proc_dointvec_minmax for [fs_]overflow UID and GID */
#define SYSCTL_MAXOLDUID ((void *)&sysctl_vals[10])
#define SYSCTL_NEG_ONE ((void *)&sysctl_vals[11])
extern const int sysctl_vals[];
#define SYSCTL_LONG_ZERO ((void *)&sysctl_long_vals[0])
#define SYSCTL_LONG_ONE ((void *)&sysctl_long_vals[1])
#define SYSCTL_LONG_MAX ((void *)&sysctl_long_vals[2])
#define SYSCTL_CONV_IDENTITY(val) (val)
/**
*
* "dir" originates from read_iter (dir = 0) or write_iter (dir = 1)
* in the file_operations struct at proc/proc_sysctl.c. Its value means
* one of two things for sysctl:
* 1. SYSCTL_USER_TO_KERN(dir) Writing to an internal kernel variable from user
* space (dir > 0)
* 2. SYSCTL_KERN_TO_USER(dir) Writing to a user space buffer from a kernel
* variable (dir == 0).
*/
#define SYSCTL_USER_TO_KERN(dir) (!!(dir))
#define SYSCTL_KERN_TO_USER(dir) (!dir)
#define SYSCTL_USER_TO_KERN_INT_CONV(name, u_ptr_op) \
int sysctl_user_to_kern_int_conv##name(const bool *negp, \
const unsigned long *u_ptr,\
int *k_ptr) \
{ \
unsigned long u = u_ptr_op(*u_ptr); \
if (*negp) { \
if (u > (unsigned long) INT_MAX + 1) \
return -EINVAL; \
WRITE_ONCE(*k_ptr, -u); \
} else { \
if (u > (unsigned long) INT_MAX) \
return -EINVAL; \
WRITE_ONCE(*k_ptr, u); \
} \
return 0; \
}
#define SYSCTL_KERN_TO_USER_INT_CONV(name, k_ptr_op) \
int sysctl_kern_to_user_int_conv##name(bool *negp, \
unsigned long *u_ptr, \
const int *k_ptr) \
{ \
int val = READ_ONCE(*k_ptr); \
if (val < 0) { \
*negp = true; \
*u_ptr = -k_ptr_op((unsigned long)val); \
} else { \
*negp = false; \
*u_ptr = k_ptr_op((unsigned long)val); \
} \
return 0; \
}
/**
* To range check on a converted value, use a temp k_ptr
* When checking range, value should be within (tbl->extra1, tbl->extra2)
*/
#define SYSCTL_INT_CONV_CUSTOM(name, user_to_kern, kern_to_user, \
k_ptr_range_check) \
int do_proc_int_conv##name(bool *negp, unsigned long *u_ptr, int *k_ptr,\
int dir, const struct ctl_table *tbl) \
{ \
if (SYSCTL_KERN_TO_USER(dir)) \
return kern_to_user(negp, u_ptr, k_ptr); \
\
if (k_ptr_range_check) { \
int tmp_k, ret; \
if (!tbl) \
return -EINVAL; \
ret = user_to_kern(negp, u_ptr, &tmp_k); \
if (ret) \
return ret; \
if ((tbl->extra1 && *(int *)tbl->extra1 > tmp_k) || \
(tbl->extra2 && *(int *)tbl->extra2 < tmp_k)) \
return -EINVAL; \
WRITE_ONCE(*k_ptr, tmp_k); \
} else \
return user_to_kern(negp, u_ptr, k_ptr); \
return 0; \
}
#define SYSCTL_USER_TO_KERN_UINT_CONV(name, u_ptr_op) \
int sysctl_user_to_kern_uint_conv##name(const unsigned long *u_ptr,\
unsigned int *k_ptr) \
{ \
unsigned long u = u_ptr_op(*u_ptr); \
if (u > UINT_MAX) \
return -EINVAL; \
WRITE_ONCE(*k_ptr, u); \
return 0; \
}
#define SYSCTL_UINT_CONV_CUSTOM(name, user_to_kern, kern_to_user, \
k_ptr_range_check) \
int do_proc_uint_conv##name(unsigned long *u_ptr, unsigned int *k_ptr, \
int dir, const struct ctl_table *tbl) \
{ \
if (SYSCTL_KERN_TO_USER(dir)) \
return kern_to_user(u_ptr, k_ptr); \
\
if (k_ptr_range_check) { \
unsigned int tmp_k; \
int ret; \
if (!tbl) \
return -EINVAL; \
ret = user_to_kern(u_ptr, &tmp_k); \
if (ret) \
return ret; \
if ((tbl->extra1 && \
*(unsigned int *)tbl->extra1 > tmp_k) || \
(tbl->extra2 && \
*(unsigned int *)tbl->extra2 < tmp_k)) \
return -ERANGE; \
WRITE_ONCE(*k_ptr, tmp_k); \
} else \
return user_to_kern(u_ptr, k_ptr); \
return 0; \
}
extern const unsigned long sysctl_long_vals[];
typedef int proc_handler(const struct ctl_table *ctl, int write, void *buffer,
size_t *lenp, loff_t *ppos);
int proc_dostring(const struct ctl_table *, int, void *, size_t *, loff_t *);
int proc_dobool(const struct ctl_table *table, int write, void *buffer,
size_t *lenp, loff_t *ppos);
int proc_dointvec(const struct ctl_table *, int, void *, size_t *, loff_t *);
int proc_dointvec_minmax(const struct ctl_table *table, int dir, void *buffer,
size_t *lenp, loff_t *ppos);
int proc_dointvec_conv(const struct ctl_table *table, int dir, void *buffer,
size_t *lenp, loff_t *ppos,
int (*conv)(bool *negp, unsigned long *u_ptr, int *k_ptr,
int dir, const struct ctl_table *table));
int proc_douintvec(const struct ctl_table *, int, void *, size_t *, loff_t *);
int proc_douintvec_minmax(const struct ctl_table *table, int write, void *buffer,
size_t *lenp, loff_t *ppos);
int proc_douintvec_conv(const struct ctl_table *table, int write, void *buffer,
size_t *lenp, loff_t *ppos,
int (*conv)(unsigned long *lvalp, unsigned int *valp,
int write, const struct ctl_table *table));
int proc_dou8vec_minmax(const struct ctl_table *table, int write, void *buffer,
size_t *lenp, loff_t *ppos);
int proc_doulongvec_minmax(const struct ctl_table *, int, void *, size_t *, loff_t *);
int proc_doulongvec_minmax_conv(const struct ctl_table *table, int dir,
void *buffer, size_t *lenp, loff_t *ppos,
unsigned long convmul, unsigned long convdiv);
int proc_do_large_bitmap(const struct ctl_table *, int, void *, size_t *, loff_t *);
int proc_do_static_key(const struct ctl_table *table, int write, void *buffer,
size_t *lenp, loff_t *ppos);
int sysctl_kern_to_user_uint_conv(unsigned long *u_ptr, const unsigned int *k_ptr);
/*
* Register a set of sysctl names by calling register_sysctl
* with an initialised array of struct ctl_table's.
*
* sysctl names can be mirrored automatically under /proc/sys. The
* procname supplied controls /proc naming.
*
* The table's mode will be honoured for proc-fs access.
*
* Leaf nodes in the sysctl tree will be represented by a single file
* under /proc; non-leaf nodes will be represented by directories. A
* null procname disables /proc mirroring at this node.
*
* The data and maxlen fields of the ctl_table
* struct enable minimal validation of the values being written to be
* performed, and the mode field allows minimal authentication.
*
* There must be a proc_handler routine for any terminal nodes
* mirrored under /proc/sys (non-terminals are handled by a built-in
* directory handler). Several default handlers are available to
* cover common cases.
*/
/* Support for userspace poll() to watch for changes */
struct ctl_table_poll {
atomic_t event;
wait_queue_head_t wait;
};
static inline void *proc_sys_poll_event(struct ctl_table_poll *poll)
{
return (void *)(unsigned long)atomic_read(&poll->event);
}
#define __CTL_TABLE_POLL_INITIALIZER(name) { \
.event = ATOMIC_INIT(0), \
.wait = __WAIT_QUEUE_HEAD_INITIALIZER(name.wait) }
#define DEFINE_CTL_TABLE_POLL(name) \
struct ctl_table_poll name = __CTL_TABLE_POLL_INITIALIZER(name)
/* A sysctl table is an array of struct ctl_table: */
struct ctl_table {
const char *procname; /* Text ID for /proc/sys */
void *data;
int maxlen;
umode_t mode;
proc_handler *proc_handler; /* Callback for text formatting */
struct ctl_table_poll *poll;
void *extra1;
void *extra2;
} __randomize_layout;
struct ctl_node {
struct rb_node node;
struct ctl_table_header *header;
};
/**
* struct ctl_table_header - maintains dynamic lists of struct ctl_table trees
* @ctl_table: pointer to the first element in ctl_table array
* @ctl_table_size: number of elements pointed by @ctl_table
* @used: The entry will never be touched when equal to 0.
* @count: Upped every time something is added to @inodes and downed every time
* something is removed from inodes
* @nreg: When nreg drops to 0 the ctl_table_header will be unregistered.
* @rcu: Delays the freeing of the inode. Introduced with "unfuck proc_sysctl ->d_compare()"
*
* @type: Enumeration to differentiate between ctl target types
* @type.SYSCTL_TABLE_TYPE_DEFAULT: ctl target with no special considerations
* @type.SYSCTL_TABLE_TYPE_PERMANENTLY_EMPTY: Identifies a permanently empty dir
* target to serve as a mount point
*/
struct ctl_table_header {
union {
struct {
const struct ctl_table *ctl_table;
int ctl_table_size;
int used;
int count;
int nreg;
};
struct rcu_head rcu;
};
struct completion *unregistering;
const struct ctl_table *ctl_table_arg;
struct ctl_table_root *root;
struct ctl_table_set *set;
struct ctl_dir *parent;
struct ctl_node *node;
struct hlist_head inodes; /* head for proc_inode->sysctl_inodes */
enum {
SYSCTL_TABLE_TYPE_DEFAULT,
SYSCTL_TABLE_TYPE_PERMANENTLY_EMPTY,
} type;
};
struct ctl_dir {
/* Header must be at the start of ctl_dir */
struct ctl_table_header header;
struct rb_root root;
};
struct ctl_table_set {
int (*is_seen)(struct ctl_table_set *);
struct ctl_dir dir;
};
struct ctl_table_root {
struct ctl_table_set default_set;
struct ctl_table_set *(*lookup)(struct ctl_table_root *root);
void (*set_ownership)(struct ctl_table_header *head,
kuid_t *uid, kgid_t *gid);
int (*permissions)(struct ctl_table_header *head, const struct ctl_table *table);
};
#define register_sysctl(path, table) \
register_sysctl_sz(path, table, ARRAY_SIZE(table))
#ifdef CONFIG_SYSCTL
void proc_sys_poll_notify(struct ctl_table_poll *poll);
extern void setup_sysctl_set(struct ctl_table_set *p,
struct ctl_table_root *root,
int (*is_seen)(struct ctl_table_set *));
extern void retire_sysctl_set(struct ctl_table_set *set);
struct ctl_table_header *__register_sysctl_table(
struct ctl_table_set *set,
const char *path, const struct ctl_table *table, size_t table_size);
struct ctl_table_header *register_sysctl_sz(const char *path, const struct ctl_table *table,
size_t table_size);
void unregister_sysctl_table(struct ctl_table_header * table);
extern int sysctl_init_bases(void);
extern void __register_sysctl_init(const char *path, const struct ctl_table *table,
const char *table_name, size_t table_size);
#define register_sysctl_init(path, table) \
__register_sysctl_init(path, table, #table, ARRAY_SIZE(table))
extern struct ctl_table_header *register_sysctl_mount_point(const char *path);
void do_sysctl_args(void);
bool sysctl_is_alias(char *param);
extern int unaligned_enabled;
extern int no_unaligned_warning;
#else /* CONFIG_SYSCTL */
static inline void register_sysctl_init(const char *path, const struct ctl_table *table)
{
}
static inline struct ctl_table_header *register_sysctl_mount_point(const char *path)
{
return NULL;
}
static inline struct ctl_table_header *register_sysctl_sz(const char *path,
const struct ctl_table *table,
size_t table_size)
{
return NULL;
}
static inline void unregister_sysctl_table(struct ctl_table_header * table)
{
}
static inline void setup_sysctl_set(struct ctl_table_set *p,
struct ctl_table_root *root,
int (*is_seen)(struct ctl_table_set *))
{
}
static inline void do_sysctl_args(void)
{
}
static inline bool sysctl_is_alias(char *param)
{
return false;
}
#endif /* CONFIG_SYSCTL */
#endif /* _LINUX_SYSCTL_H */
|