summaryrefslogtreecommitdiff
path: root/fs/proc/namespaces.c
blob: 89026095f2b51a081ab37098c4b8f3f1da762519 (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
#include <linux/proc_fs.h>
#include <linux/nsproxy.h>
#include <linux/sched.h>
#include <linux/ptrace.h>
#include <linux/fs_struct.h>
#include <linux/mount.h>
#include <linux/path.h>
#include <linux/namei.h>
#include <linux/file.h>
#include <linux/utsname.h>
#include <net/net_namespace.h>
#include <linux/ipc_namespace.h>
#include <linux/pid_namespace.h>
#include <linux/user_namespace.h>
#include "internal.h"


static const struct proc_ns_operations *ns_entries[] = {
#ifdef CONFIG_NET_NS
	&netns_operations,
#endif
#ifdef CONFIG_UTS_NS
	&utsns_operations,
#endif
#ifdef CONFIG_IPC_NS
	&ipcns_operations,
#endif
#ifdef CONFIG_PID_NS
	&pidns_operations,
#endif
#ifdef CONFIG_USER_NS
	&userns_operations,
#endif
	&mntns_operations,
};

static const struct file_operations ns_file_operations = {
	.llseek		= no_llseek,
};

static const struct inode_operations ns_inode_operations = {
	.setattr	= proc_setattr,
};

static char *ns_dname(struct dentry *dentry, char *buffer, int buflen)
{
	struct inode *inode = dentry->d_inode;
	const struct proc_ns_operations *ns_ops = PROC_I(inode)->ns.ns_ops;

	return dynamic_dname(dentry, buffer, buflen, "%s:[%lu]",
		ns_ops->name, inode->i_ino);
}

const struct dentry_operations ns_dentry_operations =
{
	.d_delete	= always_delete_dentry,
	.d_dname	= ns_dname,
};

static struct dentry *proc_ns_get_dentry(struct super_block *sb,
	struct task_struct *task, const struct proc_ns_operations *ns_ops)
{
	struct dentry *dentry, *result;
	struct inode *inode;
	struct proc_inode *ei;
	struct qstr qname = { .name = "", };
	void *ns;

	ns = ns_ops->get(task);
	if (!ns)
		return ERR_PTR(-ENOENT);

	dentry = d_alloc_pseudo(sb, &qname);
	if (!dentry) {
		ns_ops->put(ns);
		return ERR_PTR(-ENOMEM);
	}

	inode = iget_locked(sb, ns_ops->inum(ns));
	if (!inode) {
		dput(dentry);
		ns_ops->put(ns);
		return ERR_PTR(-ENOMEM);
	}

	ei = PROC_I(inode);
	if (inode->i_state & I_NEW) {
		inode->i_mtime = inode->i_atime = inode->i_ctime = CURRENT_TIME;
		inode->i_op = &ns_inode_operations;
		inode->i_mode = S_IFREG | S_IRUGO;
		inode->i_fop = &ns_file_operations;
		ei->ns.ns_ops = ns_ops;
		ei->ns.ns = ns;
		unlock_new_inode(inode);
	} else {
		ns_ops->put(ns);
	}

	d_set_d_op(dentry, &ns_dentry_operations);
	result = d_instantiate_unique(dentry, inode);
	if (result) {
		dput(dentry);
		dentry = result;
	}

	return dentry;
}

static void *proc_ns_follow_link(struct dentry *dentry, struct nameidata *nd)
{
	struct inode *inode = dentry->d_inode;
	struct super_block *sb = inode->i_sb;
	struct proc_inode *ei = PROC_I(inode);
	struct task_struct *task;
	struct path ns_path;
	void *error = ERR_PTR(-EACCES);

	task = get_proc_task(inode);
	if (!task)
		goto out;

	if (!ptrace_may_access(task, PTRACE_MODE_READ))
		goto out_put_task;

	ns_path.dentry = proc_ns_get_dentry(sb, task, ei->ns.ns_ops);
	if (IS_ERR(ns_path.dentry)) {
		error = ERR_CAST(ns_path.dentry);
		goto out_put_task;
	}

	ns_path.mnt = mntget(nd->path.mnt);
	nd_jump_link(nd, &ns_path);
	error = NULL;

out_put_task:
	put_task_struct(task);
out:
	return error;
}

static int proc_ns_readlink(struct dentry *dentry, char __user *buffer, int buflen)
{
	struct inode *inode = dentry->d_inode;
	struct proc_inode *ei = PROC_I(inode);
	const struct proc_ns_operations *ns_ops = ei->ns.ns_ops;
	struct task_struct *task;
	void *ns;
	char name[50];
	int res = -EACCES;

	task = get_proc_task(inode);
	if (!task)
		goto out;

	if (!ptrace_may_access(task, PTRACE_MODE_READ))
		goto out_put_task;

	res = -ENOENT;
	ns = ns_ops->get(task);
	if (!ns)
		goto out_put_task;

	snprintf(name, sizeof(name), "%s:[%u]", ns_ops->name, ns_ops->inum(ns));
	res = readlink_copy(buffer, buflen, name);
	ns_ops->put(ns);
out_put_task:
	put_task_struct(task);
out:
	return res;
}

static const struct inode_operations proc_ns_link_inode_operations = {
	.readlink	= proc_ns_readlink,
	.follow_link	= proc_ns_follow_link,
	.setattr	= proc_setattr,
};

static int proc_ns_instantiate(struct inode *dir,
	struct dentry *dentry, struct task_struct *task, const void *ptr)
{
	const struct proc_ns_operations *ns_ops = ptr;
	struct inode *inode;
	struct proc_inode *ei;

	inode = proc_pid_make_inode(dir->i_sb, task);
	if (!inode)
		goto out;

	ei = PROC_I(inode);
	inode->i_mode = S_IFLNK|S_IRWXUGO;
	inode->i_op = &proc_ns_link_inode_operations;
	ei->ns.ns_ops = ns_ops;

	d_set_d_op(dentry, &pid_dentry_operations);
	d_add(dentry, inode);
	/* Close the race of the process dying before we return the dentry */
	if (pid_revalidate(dentry, 0))
		return 0;
out:
	return -ENOENT;
}

static int proc_ns_dir_readdir(struct file *file, struct dir_context *ctx)
{
	struct task_struct *task = get_proc_task(file_inode(file));
	const struct proc_ns_operations **entry, **last;

	if (!task)
		return -ENOENT;

	if (!dir_emit_dots(file, ctx))
		goto out;
	if (ctx->pos >= 2 + ARRAY_SIZE(ns_entries))
		goto out;
	entry = ns_entries + (ctx->pos - 2);
	last = &ns_entries[ARRAY_SIZE(ns_entries) - 1];
	while (entry <= last) {
		const struct proc_ns_operations *ops = *entry;
		if (!proc_fill_cache(file, ctx, ops->name, strlen(ops->name),
				     proc_ns_instantiate, task, ops))
			break;
		ctx->pos++;
		entry++;
	}
out:
	put_task_struct(task);
	return 0;
}

const struct file_operations proc_ns_dir_operations = {
	.read		= generic_read_dir,
	.iterate	= proc_ns_dir_readdir,
};

static struct dentry *proc_ns_dir_lookup(struct inode *dir,
				struct dentry *dentry, unsigned int flags)
{
	int error;
	struct task_struct *task = get_proc_task(dir);
	const struct proc_ns_operations **entry, **last;
	unsigned int len = dentry->d_name.len;

	error = -ENOENT;

	if (!task)
		goto out_no_task;

	last = &ns_entries[ARRAY_SIZE(ns_entries)];
	for (entry = ns_entries; entry < last; entry++) {
		if (strlen((*entry)->name) != len)
			continue;
		if (!memcmp(dentry->d_name.name, (*entry)->name, len))
			break;
	}
	if (entry == last)
		goto out;

	error = proc_ns_instantiate(dir, dentry, task, *entry);
out:
	put_task_struct(task);
out_no_task:
	return ERR_PTR(error);
}

const struct inode_operations proc_ns_dir_inode_operations = {
	.lookup		= proc_ns_dir_lookup,
	.getattr	= pid_getattr,
	.setattr	= proc_setattr,
};

struct file *proc_ns_fget(int fd)
{
	struct file *file;

	file = fget(fd);
	if (!file)
		return ERR_PTR(-EBADF);

	if (file->f_op != &ns_file_operations)
		goto out_invalid;

	return file;

out_invalid:
	fput(file);
	return ERR_PTR(-EINVAL);
}

struct proc_ns *get_proc_ns(struct inode *inode)
{
	return &PROC_I(inode)->ns;
}

bool proc_ns_inode(struct inode *inode)
{
	return inode->i_fop == &ns_file_operations;
}