summaryrefslogtreecommitdiff
path: root/fs/anon_inodes.c
blob: 1dd96d4406c09dde60b038a0eb5900606d59e18c (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
/*
 *  fs/anon_inodes.c
 *
 *  Copyright (C) 2007  Davide Libenzi <davidel@xmailserver.org>
 *
 *  Thanks to Arnd Bergmann for code review and suggestions.
 *  More changes for Thomas Gleixner suggestions.
 *
 */

#include <linux/file.h>
#include <linux/poll.h>
#include <linux/slab.h>
#include <linux/init.h>
#include <linux/fs.h>
#include <linux/mount.h>
#include <linux/module.h>
#include <linux/kernel.h>
#include <linux/magic.h>
#include <linux/anon_inodes.h>

#include <asm/uaccess.h>

static struct vfsmount *anon_inode_mnt __read_mostly;
static struct inode *anon_inode_inode;
static const struct file_operations anon_inode_fops;

static int anon_inodefs_get_sb(struct file_system_type *fs_type, int flags,
			       const char *dev_name, void *data,
			       struct vfsmount *mnt)
{
	return get_sb_pseudo(fs_type, "anon_inode:", NULL, ANON_INODE_FS_MAGIC,
			     mnt);
}

static int anon_inodefs_delete_dentry(struct dentry *dentry)
{
	/*
	 * We faked vfs to believe the dentry was hashed when we created it.
	 * Now we restore the flag so that dput() will work correctly.
	 */
	dentry->d_flags |= DCACHE_UNHASHED;
	return 1;
}

static struct file_system_type anon_inode_fs_type = {
	.name		= "anon_inodefs",
	.get_sb		= anon_inodefs_get_sb,
	.kill_sb	= kill_anon_super,
};
static const struct dentry_operations anon_inodefs_dentry_operations = {
	.d_delete	= anon_inodefs_delete_dentry,
};

/**
 * anon_inode_getfd - creates a new file instance by hooking it up to an
 *                    anonymous inode, and a dentry that describe the "class"
 *                    of the file
 *
 * @name:    [in]    name of the "class" of the new file
 * @fops:    [in]    file operations for the new file
 * @priv:    [in]    private data for the new file (will be file's private_data)
 * @flags:   [in]    flags
 *
 * Creates a new file by hooking it on a single inode. This is useful for files
 * that do not need to have a full-fledged inode in order to operate correctly.
 * All the files created with anon_inode_getfd() will share a single inode,
 * hence saving memory and avoiding code duplication for the file/inode/dentry
 * setup.  Returns new descriptor or -error.
 */
int anon_inode_getfd(const char *name, const struct file_operations *fops,
		     void *priv, int flags)
{
	struct qstr this;
	struct dentry *dentry;
	struct file *file;
	int error, fd;

	if (IS_ERR(anon_inode_inode))
		return -ENODEV;

	if (fops->owner && !try_module_get(fops->owner))
		return -ENOENT;

	error = get_unused_fd_flags(flags);
	if (error < 0)
		goto err_module;
	fd = error;

	/*
	 * Link the inode to a directory entry by creating a unique name
	 * using the inode sequence number.
	 */
	error = -ENOMEM;
	this.name = name;
	this.len = strlen(name);
	this.hash = 0;
	dentry = d_alloc(anon_inode_mnt->mnt_sb->s_root, &this);
	if (!dentry)
		goto err_put_unused_fd;

	/*
	 * We know the anon_inode inode count is always greater than zero,
	 * so we can avoid doing an igrab() and we can use an open-coded
	 * atomic_inc().
	 */
	atomic_inc(&anon_inode_inode->i_count);

	dentry->d_op = &anon_inodefs_dentry_operations;
	/* Do not publish this dentry inside the global dentry hash table */
	dentry->d_flags &= ~DCACHE_UNHASHED;
	d_instantiate(dentry, anon_inode_inode);

	error = -ENFILE;
	file = alloc_file(anon_inode_mnt, dentry,
			  FMODE_READ | FMODE_WRITE, fops);
	if (!file)
		goto err_dput;
	file->f_mapping = anon_inode_inode->i_mapping;

	file->f_pos = 0;
	file->f_flags = O_RDWR | (flags & O_NONBLOCK);
	file->f_version = 0;
	file->private_data = priv;

	fd_install(fd, file);

	return fd;

err_dput:
	dput(dentry);
err_put_unused_fd:
	put_unused_fd(fd);
err_module:
	module_put(fops->owner);
	return error;
}
EXPORT_SYMBOL_GPL(anon_inode_getfd);

/*
 * A single inode exists for all anon_inode files. Contrary to pipes,
 * anon_inode inodes have no associated per-instance data, so we need
 * only allocate one of them.
 */
static struct inode *anon_inode_mkinode(void)
{
	struct inode *inode = new_inode(anon_inode_mnt->mnt_sb);

	if (!inode)
		return ERR_PTR(-ENOMEM);

	inode->i_fop = &anon_inode_fops;

	/*
	 * Mark the inode dirty from the very beginning,
	 * that way it will never be moved to the dirty
	 * list because mark_inode_dirty() will think
	 * that it already _is_ on the dirty list.
	 */
	inode->i_state = I_DIRTY;
	inode->i_mode = S_IRUSR | S_IWUSR;
	inode->i_uid = current_fsuid();
	inode->i_gid = current_fsgid();
	inode->i_atime = inode->i_mtime = inode->i_ctime = CURRENT_TIME;
	return inode;
}

static int __init anon_inode_init(void)
{
	int error;

	error = register_filesystem(&anon_inode_fs_type);
	if (error)
		goto err_exit;
	anon_inode_mnt = kern_mount(&anon_inode_fs_type);
	if (IS_ERR(anon_inode_mnt)) {
		error = PTR_ERR(anon_inode_mnt);
		goto err_unregister_filesystem;
	}
	anon_inode_inode = anon_inode_mkinode();
	if (IS_ERR(anon_inode_inode)) {
		error = PTR_ERR(anon_inode_inode);
		goto err_mntput;
	}

	return 0;

err_mntput:
	mntput(anon_inode_mnt);
err_unregister_filesystem:
	unregister_filesystem(&anon_inode_fs_type);
err_exit:
	panic(KERN_ERR "anon_inode_init() failed (%d)\n", error);
}

fs_initcall(anon_inode_init);