summaryrefslogtreecommitdiff
path: root/fs/pidfs.c
blob: dbb9d854d1c57c94ec17f1fd2d332c076b2d8228 (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
302
303
// SPDX-License-Identifier: GPL-2.0
#include <linux/anon_inodes.h>
#include <linux/file.h>
#include <linux/fs.h>
#include <linux/magic.h>
#include <linux/mount.h>
#include <linux/pid.h>
#include <linux/pidfs.h>
#include <linux/pid_namespace.h>
#include <linux/poll.h>
#include <linux/proc_fs.h>
#include <linux/proc_ns.h>
#include <linux/pseudo_fs.h>
#include <linux/seq_file.h>
#include <uapi/linux/pidfd.h>

#include "internal.h"

#ifdef CONFIG_PROC_FS
/**
 * pidfd_show_fdinfo - print information about a pidfd
 * @m: proc fdinfo file
 * @f: file referencing a pidfd
 *
 * Pid:
 * This function will print the pid that a given pidfd refers to in the
 * pid namespace of the procfs instance.
 * If the pid namespace of the process is not a descendant of the pid
 * namespace of the procfs instance 0 will be shown as its pid. This is
 * similar to calling getppid() on a process whose parent is outside of
 * its pid namespace.
 *
 * NSpid:
 * If pid namespaces are supported then this function will also print
 * the pid of a given pidfd refers to for all descendant pid namespaces
 * starting from the current pid namespace of the instance, i.e. the
 * Pid field and the first entry in the NSpid field will be identical.
 * If the pid namespace of the process is not a descendant of the pid
 * namespace of the procfs instance 0 will be shown as its first NSpid
 * entry and no others will be shown.
 * Note that this differs from the Pid and NSpid fields in
 * /proc/<pid>/status where Pid and NSpid are always shown relative to
 * the  pid namespace of the procfs instance. The difference becomes
 * obvious when sending around a pidfd between pid namespaces from a
 * different branch of the tree, i.e. where no ancestral relation is
 * present between the pid namespaces:
 * - create two new pid namespaces ns1 and ns2 in the initial pid
 *   namespace (also take care to create new mount namespaces in the
 *   new pid namespace and mount procfs)
 * - create a process with a pidfd in ns1
 * - send pidfd from ns1 to ns2
 * - read /proc/self/fdinfo/<pidfd> and observe that both Pid and NSpid
 *   have exactly one entry, which is 0
 */
static void pidfd_show_fdinfo(struct seq_file *m, struct file *f)
{
	struct pid *pid = pidfd_pid(f);
	struct pid_namespace *ns;
	pid_t nr = -1;

	if (likely(pid_has_task(pid, PIDTYPE_PID))) {
		ns = proc_pid_ns(file_inode(m->file)->i_sb);
		nr = pid_nr_ns(pid, ns);
	}

	seq_put_decimal_ll(m, "Pid:\t", nr);

#ifdef CONFIG_PID_NS
	seq_put_decimal_ll(m, "\nNSpid:\t", nr);
	if (nr > 0) {
		int i;

		/* If nr is non-zero it means that 'pid' is valid and that
		 * ns, i.e. the pid namespace associated with the procfs
		 * instance, is in the pid namespace hierarchy of pid.
		 * Start at one below the already printed level.
		 */
		for (i = ns->level + 1; i <= pid->level; i++)
			seq_put_decimal_ll(m, "\t", pid->numbers[i].nr);
	}
#endif
	seq_putc(m, '\n');
}
#endif

/*
 * Poll support for process exit notification.
 */
static __poll_t pidfd_poll(struct file *file, struct poll_table_struct *pts)
{
	struct pid *pid = pidfd_pid(file);
	bool thread = file->f_flags & PIDFD_THREAD;
	struct task_struct *task;
	__poll_t poll_flags = 0;

	poll_wait(file, &pid->wait_pidfd, pts);
	/*
	 * Depending on PIDFD_THREAD, inform pollers when the thread
	 * or the whole thread-group exits.
	 */
	guard(rcu)();
	task = pid_task(pid, PIDTYPE_PID);
	if (!task)
		poll_flags = EPOLLIN | EPOLLRDNORM | EPOLLHUP;
	else if (task->exit_state && (thread || thread_group_empty(task)))
		poll_flags = EPOLLIN | EPOLLRDNORM;

	return poll_flags;
}

static const struct file_operations pidfs_file_operations = {
	.poll		= pidfd_poll,
#ifdef CONFIG_PROC_FS
	.show_fdinfo	= pidfd_show_fdinfo,
#endif
};

struct pid *pidfd_pid(const struct file *file)
{
	if (file->f_op != &pidfs_file_operations)
		return ERR_PTR(-EBADF);
	return file_inode(file)->i_private;
}

static struct vfsmount *pidfs_mnt __ro_after_init;

#if BITS_PER_LONG == 32
/*
 * Provide a fallback mechanism for 32-bit systems so processes remain
 * reliably comparable by inode number even on those systems.
 */
static DEFINE_IDA(pidfd_inum_ida);

static int pidfs_inum(struct pid *pid, unsigned long *ino)
{
	int ret;

	ret = ida_alloc_range(&pidfd_inum_ida, RESERVED_PIDS + 1,
			      UINT_MAX, GFP_ATOMIC);
	if (ret < 0)
		return -ENOSPC;

	*ino = ret;
	return 0;
}

static inline void pidfs_free_inum(unsigned long ino)
{
	if (ino > 0)
		ida_free(&pidfd_inum_ida, ino);
}
#else
static inline int pidfs_inum(struct pid *pid, unsigned long *ino)
{
	*ino = pid->ino;
	return 0;
}
#define pidfs_free_inum(ino) ((void)(ino))
#endif

/*
 * The vfs falls back to simple_setattr() if i_op->setattr() isn't
 * implemented. Let's reject it completely until we have a clean
 * permission concept for pidfds.
 */
static int pidfs_setattr(struct mnt_idmap *idmap, struct dentry *dentry,
			 struct iattr *attr)
{
	return -EOPNOTSUPP;
}


/*
 * User space expects pidfs inodes to have no file type in st_mode.
 *
 * In particular, 'lsof' has this legacy logic:
 *
 *	type = s->st_mode & S_IFMT;
 *	switch (type) {
 *	  ...
 *	case 0:
 *		if (!strcmp(p, "anon_inode"))
 *			Lf->ntype = Ntype = N_ANON_INODE;
 *
 * to detect our old anon_inode logic.
 *
 * Rather than mess with our internal sane inode data, just fix it
 * up here in getattr() by masking off the format bits.
 */
static int pidfs_getattr(struct mnt_idmap *idmap, const struct path *path,
			 struct kstat *stat, u32 request_mask,
			 unsigned int query_flags)
{
	struct inode *inode = d_inode(path->dentry);

	generic_fillattr(&nop_mnt_idmap, request_mask, inode, stat);
	stat->mode &= ~S_IFMT;
	return 0;
}

static const struct inode_operations pidfs_inode_operations = {
	.getattr = pidfs_getattr,
	.setattr = pidfs_setattr,
};

static void pidfs_evict_inode(struct inode *inode)
{
	struct pid *pid = inode->i_private;

	clear_inode(inode);
	put_pid(pid);
	pidfs_free_inum(inode->i_ino);
}

static const struct super_operations pidfs_sops = {
	.drop_inode	= generic_delete_inode,
	.evict_inode	= pidfs_evict_inode,
	.statfs		= simple_statfs,
};

/*
 * 'lsof' has knowledge of out historical anon_inode use, and expects
 * the pidfs dentry name to start with 'anon_inode'.
 */
static char *pidfs_dname(struct dentry *dentry, char *buffer, int buflen)
{
	return dynamic_dname(buffer, buflen, "anon_inode:[pidfd]");
}

static const struct dentry_operations pidfs_dentry_operations = {
	.d_delete	= always_delete_dentry,
	.d_dname	= pidfs_dname,
	.d_prune	= stashed_dentry_prune,
};

static int pidfs_init_inode(struct inode *inode, void *data)
{
	inode->i_private = data;
	inode->i_flags |= S_PRIVATE;
	inode->i_mode |= S_IRWXU;
	inode->i_op = &pidfs_inode_operations;
	inode->i_fop = &pidfs_file_operations;
	/*
	 * Inode numbering for pidfs start at RESERVED_PIDS + 1. This
	 * avoids collisions with the root inode which is 1 for pseudo
	 * filesystems.
	 */
	return pidfs_inum(data, &inode->i_ino);
}

static void pidfs_put_data(void *data)
{
	struct pid *pid = data;
	put_pid(pid);
}

static const struct stashed_operations pidfs_stashed_ops = {
	.init_inode = pidfs_init_inode,
	.put_data = pidfs_put_data,
};

static int pidfs_init_fs_context(struct fs_context *fc)
{
	struct pseudo_fs_context *ctx;

	ctx = init_pseudo(fc, PID_FS_MAGIC);
	if (!ctx)
		return -ENOMEM;

	ctx->ops = &pidfs_sops;
	ctx->dops = &pidfs_dentry_operations;
	fc->s_fs_info = (void *)&pidfs_stashed_ops;
	return 0;
}

static struct file_system_type pidfs_type = {
	.name			= "pidfs",
	.init_fs_context	= pidfs_init_fs_context,
	.kill_sb		= kill_anon_super,
};

struct file *pidfs_alloc_file(struct pid *pid, unsigned int flags)
{

	struct file *pidfd_file;
	struct path path;
	int ret;

	ret = path_from_stashed(&pid->stashed, pidfs_mnt, get_pid(pid), &path);
	if (ret < 0)
		return ERR_PTR(ret);

	pidfd_file = dentry_open(&path, flags, current_cred());
	path_put(&path);
	return pidfd_file;
}

void __init pidfs_init(void)
{
	pidfs_mnt = kern_mount(&pidfs_type);
	if (IS_ERR(pidfs_mnt))
		panic("Failed to mount pidfs pseudo filesystem");
}