summaryrefslogtreecommitdiff
path: root/fs/proc/root.c
blob: cdbe9293ea55148d284d8990a563702a9f6f7a55 (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
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
// SPDX-License-Identifier: GPL-2.0
/*
 *  linux/fs/proc/root.c
 *
 *  Copyright (C) 1991, 1992 Linus Torvalds
 *
 *  proc root directory handling functions
 */

#include <linux/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/sched/stat.h>
#include <linux/module.h>
#include <linux/bitops.h>
#include <linux/user_namespace.h>
#include <linux/fs_context.h>
#include <linux/mount.h>
#include <linux/pid_namespace.h>
#include <linux/fs_parser.h>
#include <linux/cred.h>
#include <linux/magic.h>
#include <linux/slab.h>

#include "internal.h"

struct proc_fs_context {
	struct pid_namespace	*pid_ns;
	unsigned int		mask;
	int			hidepid;
	int			gid;
};

enum proc_param {
	Opt_gid,
	Opt_hidepid,
};

static const struct fs_parameter_spec proc_fs_parameters[] = {
	fsparam_u32("gid",	Opt_gid),
	fsparam_u32("hidepid",	Opt_hidepid),
	{}
};

static int proc_parse_param(struct fs_context *fc, struct fs_parameter *param)
{
	struct proc_fs_context *ctx = fc->fs_private;
	struct fs_parse_result result;
	int opt;

	opt = fs_parse(fc, proc_fs_parameters, param, &result);
	if (opt < 0)
		return opt;

	switch (opt) {
	case Opt_gid:
		ctx->gid = result.uint_32;
		break;

	case Opt_hidepid:
		ctx->hidepid = result.uint_32;
		if (ctx->hidepid < HIDEPID_OFF ||
		    ctx->hidepid > HIDEPID_INVISIBLE)
			return invalfc(fc, "hidepid value must be between 0 and 2.\n");
		break;

	default:
		return -EINVAL;
	}

	ctx->mask |= 1 << opt;
	return 0;
}

static void proc_apply_options(struct super_block *s,
			       struct fs_context *fc,
			       struct pid_namespace *pid_ns,
			       struct user_namespace *user_ns)
{
	struct proc_fs_context *ctx = fc->fs_private;

	if (ctx->mask & (1 << Opt_gid))
		pid_ns->pid_gid = make_kgid(user_ns, ctx->gid);
	if (ctx->mask & (1 << Opt_hidepid))
		pid_ns->hide_pid = ctx->hidepid;
}

static int proc_fill_super(struct super_block *s, struct fs_context *fc)
{
	struct pid_namespace *pid_ns = get_pid_ns(s->s_fs_info);
	struct inode *root_inode;
	int ret;

	proc_apply_options(s, fc, pid_ns, current_user_ns());

	/* User space would break if executables or devices appear on proc */
	s->s_iflags |= SB_I_USERNS_VISIBLE | SB_I_NOEXEC | SB_I_NODEV;
	s->s_flags |= SB_NODIRATIME | SB_NOSUID | SB_NOEXEC;
	s->s_blocksize = 1024;
	s->s_blocksize_bits = 10;
	s->s_magic = PROC_SUPER_MAGIC;
	s->s_op = &proc_sops;
	s->s_time_gran = 1;

	/*
	 * procfs isn't actually a stacking filesystem; however, there is
	 * too much magic going on inside it to permit stacking things on
	 * top of it
	 */
	s->s_stack_depth = FILESYSTEM_MAX_STACK_DEPTH;
	
	/* procfs dentries and inodes don't require IO to create */
	s->s_shrink.seeks = 0;

	pde_get(&proc_root);
	root_inode = proc_get_inode(s, &proc_root);
	if (!root_inode) {
		pr_err("proc_fill_super: get root inode failed\n");
		return -ENOMEM;
	}

	s->s_root = d_make_root(root_inode);
	if (!s->s_root) {
		pr_err("proc_fill_super: allocate dentry failed\n");
		return -ENOMEM;
	}

	ret = proc_setup_self(s);
	if (ret) {
		return ret;
	}
	return proc_setup_thread_self(s);
}

static int proc_reconfigure(struct fs_context *fc)
{
	struct super_block *sb = fc->root->d_sb;
	struct pid_namespace *pid = sb->s_fs_info;

	sync_filesystem(sb);

	proc_apply_options(sb, fc, pid, current_user_ns());
	return 0;
}

static int proc_get_tree(struct fs_context *fc)
{
	struct proc_fs_context *ctx = fc->fs_private;

	return get_tree_keyed(fc, proc_fill_super, ctx->pid_ns);
}

static void proc_fs_context_free(struct fs_context *fc)
{
	struct proc_fs_context *ctx = fc->fs_private;

	put_pid_ns(ctx->pid_ns);
	kfree(ctx);
}

static const struct fs_context_operations proc_fs_context_ops = {
	.free		= proc_fs_context_free,
	.parse_param	= proc_parse_param,
	.get_tree	= proc_get_tree,
	.reconfigure	= proc_reconfigure,
};

static int proc_init_fs_context(struct fs_context *fc)
{
	struct proc_fs_context *ctx;

	ctx = kzalloc(sizeof(struct proc_fs_context), GFP_KERNEL);
	if (!ctx)
		return -ENOMEM;

	ctx->pid_ns = get_pid_ns(task_active_pid_ns(current));
	put_user_ns(fc->user_ns);
	fc->user_ns = get_user_ns(ctx->pid_ns->user_ns);
	fc->fs_private = ctx;
	fc->ops = &proc_fs_context_ops;
	return 0;
}

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);
	if (ns->proc_thread_self)
		dput(ns->proc_thread_self);
	kill_anon_super(sb);

	/* Make the pid namespace safe for the next mount of proc */
	ns->proc_self = NULL;
	ns->proc_thread_self = NULL;
	ns->pid_gid = GLOBAL_ROOT_GID;
	ns->hide_pid = 0;

	put_pid_ns(ns);
}

static struct file_system_type proc_fs_type = {
	.name			= "proc",
	.init_fs_context	= proc_init_fs_context,
	.parameters		= proc_fs_parameters,
	.kill_sb		= proc_kill_sb,
	.fs_flags		= FS_USERNS_MOUNT | FS_DISALLOW_NOTIFY_PERM,
};

void __init proc_root_init(void)
{
	proc_init_kmemcache();
	set_proc_pid_nlink();
	proc_self_init();
	proc_thread_self_init();
	proc_symlink("mounts", NULL, "self/mounts");

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

	register_filesystem(&proc_fs_type);
}

static int proc_root_getattr(const struct path *path, struct kstat *stat,
			     u32 request_mask, unsigned int query_flags)
{
	generic_fillattr(d_inode(path->dentry), 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_pid_lookup(dentry, flags))
		return NULL;

	return proc_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_shared	 = proc_root_readdir,
	.llseek		= generic_file_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, 
	.refcnt		= REFCOUNT_INIT(1),
	.proc_iops	= &proc_root_inode_operations, 
	.proc_dir_ops	= &proc_root_operations,
	.parent		= &proc_root,
	.subdir		= RB_ROOT,
	.name		= "/proc",
};