summaryrefslogtreecommitdiffstats
path: root/fs/proc/root.c
blob: ac823a85cf6e5675b6ff3318784c6c8f9ea176ef (plain)
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
/*
 *  linux/fs/proc/root.c
 *
 *  Copyright (C) 1991, 1992 Linus Torvalds
 *
 *  proc root directory handling functions
 */

#include <asm/uaccess.h>

#include <linux/errno.h>
#include <linux/time.h>
#include <linux/proc_fs.h>
#include <linux/stat.h>
#include <linux/init.h>
#include <linux/sched.h>
#include <linux/module.h>
#include <linux/bitops.h>
#include <linux/user_namespace.h>
#include <linux/mount.h>
#include <linux/pid_namespace.h>
#include <linux/parser.h>

#include "internal.h"

static int proc_test_super(struct super_block *sb, void *data)
{
	return sb->s_fs_info == data;
}

static int proc_set_super(struct super_block *sb, void *data)
{
	int err = set_anon_super(sb, NULL);
	if (!err) {
		struct pid_namespace *ns = (struct pid_namespace *)data;
		sb->s_fs_info = get_pid_ns(ns);
	}
	return err;
}

enum {
	Opt_gid, Opt_hidepid, Opt_err,
};

static const match_table_t tokens = {
	{Opt_hidepid, "hidepid=%u"},
	{Opt_gid, "gid=%u"},
	{Opt_err, NULL},
};

static int proc_parse_options(char *options, struct pid_namespace *pid)
{
	char *p;
	substring_t args[MAX_OPT_ARGS];
	int option;

	if (!options)
		return 1;

	while ((p = strsep(&options, ",")) != NULL) {
		int token;
		if (!*p)
			continue;

		args[0].to = args[0].from = NULL;
		token = match_token(p, tokens, args);
		switch (token) {
		case Opt_gid:
			if (match_int(&args[0], &option))
				return 0;
			pid->pid_gid = make_kgid(current_user_ns(), option);
			break;
		case Opt_hidepid:
			if (match_int(&args[0], &option))
				return 0;
			if (option < 0 || option > 2) {
				pr_err("proc: hidepid value must be between 0 and 2.\n");
				return 0;
			}
			pid->hide_pid = option;
			break;
		default:
			pr_err("proc: unrecognized mount option \"%s\" "
			       "or missing value\n", p);
			return 0;
		}
	}

	return 1;
}

int proc_remount(struct super_block *sb, int *flags, char *data)
{
	struct pid_namespace *pid = sb->s_fs_info;

	sync_filesystem(sb);
	return !proc_parse_options(data, pid);
}

static struct dentry *proc_mount(struct file_system_type *fs_type,
	int flags, const char *dev_name, void *data)
{
	int err;
	struct super_block *sb;
	struct pid_namespace *ns;
	char *options;

	if (flags & MS_KERNMOUNT) {
		ns = (struct pid_namespace *)data;
		options = NULL;
	} else {
		ns = task_active_pid_ns(current);
		options = data;

		if (!capable(CAP_SYS_ADMIN) && !fs_fully_visible(fs_type))
			return ERR_PTR(-EPERM);

		/* Does the mounter have privilege over the pid namespace? */
		if (!ns_capable(ns->user_ns, CAP_SYS_ADMIN))
			return ERR_PTR(-EPERM);
	}

	sb = sget(fs_type, proc_test_super, proc_set_super, flags, ns);
	if (IS_ERR(sb))
		return ERR_CAST(sb);

	if (!proc_parse_options(options, ns)) {
		deactivate_locked_super(sb);
		return ERR_PTR(-EINVAL);
	}

	if (!sb->s_root) {
		err = proc_fill_super(sb);
		if (err) {
			deactivate_locked_super(sb);
			return ERR_PTR(err);
		}

		sb->s_flags |= MS_ACTIVE;
	}

	return dget(sb->s_root);
}

static void proc_kill_sb(struct super_block *sb)
{
	struct pid_namespace *ns;

	ns = (struct pid_namespace *)sb->s_fs_info;
	if (ns->proc_self)
		dput(ns->proc_self);
	kill_anon_super(sb);
	put_pid_ns(ns);
}

static struct file_system_type proc_fs_type = {
	.name		= "proc",
	.mount		= proc_mount,
	.kill_sb	= proc_kill_sb,
	.fs_flags	= FS_USERNS_MOUNT,
};

void __init proc_root_init(void)
{
	int err;

	proc_init_inodecache();
	err = register_filesystem(&proc_fs_type);
	if (err)
		return;

	proc_self_init();
	proc_symlink("mounts", NULL, "self/mounts");

	proc_net_init();

#ifdef CONFIG_SYSVIPC
	proc_mkdir("sysvipc", NULL);
#endif
	proc_mkdir("fs", NULL);
	proc_mkdir("driver", NULL);
	proc_mkdir("fs/nfsd", NULL); /* somewhere for the nfsd filesystem to be mounted */
#if defined(CONFIG_SUN_OPENPROMFS) || defined(CONFIG_SUN_OPENPROMFS_MODULE)
	/* just give it a mountpoint */
	proc_mkdir("openprom", NULL);
#endif
	proc_tty_init();
#ifdef CONFIG_PROC_DEVICETREE
	proc_device_tree_init();
#endif
	proc_mkdir("bus", NULL);
	proc_sys_init();
}

static int proc_root_getattr(struct vfsmount *mnt, struct dentry *dentry, struct kstat *stat
)
{
	generic_fillattr(dentry->d_inode, stat);
	stat->nlink = proc_root.nlink + nr_processes();
	return 0;
}

static struct dentry *proc_root_lookup(struct inode * dir, struct dentry * dentry, unsigned int flags)
{
	if (!proc_lookup(dir, dentry, flags))
		return NULL;
	
	return proc_pid_lookup(dir, dentry, flags);
}

static int proc_root_readdir(struct file *file, struct dir_context *ctx)
{
	if (ctx->pos < FIRST_PROCESS_ENTRY) {
		int error = proc_readdir(file, ctx);
		if (unlikely(error <= 0))
			return error;
		ctx->pos = FIRST_PROCESS_ENTRY;
	}

	return proc_pid_readdir(file, ctx);
}

/*
 * The root /proc directory is special, as it has the
 * <pid> directories. Thus we don't use the generic
 * directory handling functions for that..
 */
static const struct file_operations proc_root_operations = {
	.read		 = generic_read_dir,
	.iterate	 = proc_root_readdir,
	.llseek		= default_llseek,
};

/*
 * proc root can do almost nothing..
 */
static const struct inode_operations proc_root_inode_operations = {
	.lookup		= proc_root_lookup,
	.getattr	= proc_root_getattr,
};

/*
 * This is the root "inode" in the /proc tree..
 */
struct proc_dir_entry proc_root = {
	.low_ino	= PROC_ROOT_INO, 
	.namelen	= 5, 
	.mode		= S_IFDIR | S_IRUGO | S_IXUGO, 
	.nlink		= 2, 
	.count		= ATOMIC_INIT(1),
	.proc_iops	= &proc_root_inode_operations, 
	.proc_fops	= &proc_root_operations,
	.parent		= &proc_root,
	.name		= "/proc",
};

int pid_ns_prepare_proc(struct pid_namespace *ns)
{
	struct vfsmount *mnt;

	mnt = kern_mount_data(&proc_fs_type, ns);
	if (IS_ERR(mnt))
		return PTR_ERR(mnt);

	ns->proc_mnt = mnt;
	return 0;
}

void pid_ns_release_proc(struct pid_namespace *ns)
{
	kern_unmount(ns->proc_mnt);
}