summaryrefslogtreecommitdiffstats
path: root/fs/file_table.c
blob: 0131ba06e1ee48bc9714805efa8b15a11a21edcc (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
/*
 *  linux/fs/file_table.c
 *
 *  Copyright (C) 1991, 1992  Linus Torvalds
 *  Copyright (C) 1997 David S. Miller (davem@caip.rutgers.edu)
 */

#include <linux/string.h>
#include <linux/slab.h>
#include <linux/file.h>
#include <linux/init.h>
#include <linux/module.h>
#include <linux/smp_lock.h>
#include <linux/fs.h>
#include <linux/security.h>
#include <linux/eventpoll.h>
#include <linux/rcupdate.h>
#include <linux/mount.h>
#include <linux/capability.h>
#include <linux/cdev.h>
#include <linux/fsnotify.h>
#include <linux/sysctl.h>
#include <linux/percpu_counter.h>

#include <asm/atomic.h>

/* sysctl tunables... */
struct files_stat_struct files_stat = {
	.max_files = NR_FILE
};

/* public. Not pretty! */
__cacheline_aligned_in_smp DEFINE_SPINLOCK(files_lock);

static struct percpu_counter nr_files __cacheline_aligned_in_smp;

static inline void file_free_rcu(struct rcu_head *head)
{
	struct file *f =  container_of(head, struct file, f_u.fu_rcuhead);
	kmem_cache_free(filp_cachep, f);
}

static inline void file_free(struct file *f)
{
	percpu_counter_dec(&nr_files);
	call_rcu(&f->f_u.fu_rcuhead, file_free_rcu);
}

/*
 * Return the total number of open files in the system
 */
static int get_nr_files(void)
{
	return percpu_counter_read_positive(&nr_files);
}

/*
 * Return the maximum number of open files in the system
 */
int get_max_files(void)
{
	return files_stat.max_files;
}
EXPORT_SYMBOL_GPL(get_max_files);

/*
 * Handle nr_files sysctl
 */
#if defined(CONFIG_SYSCTL) && defined(CONFIG_PROC_FS)
int proc_nr_files(ctl_table *table, int write, struct file *filp,
                     void __user *buffer, size_t *lenp, loff_t *ppos)
{
	files_stat.nr_files = get_nr_files();
	return proc_dointvec(table, write, filp, buffer, lenp, ppos);
}
#else
int proc_nr_files(ctl_table *table, int write, struct file *filp,
                     void __user *buffer, size_t *lenp, loff_t *ppos)
{
	return -ENOSYS;
}
#endif

/* Find an unused file structure and return a pointer to it.
 * Returns NULL, if there are no more free file structures or
 * we run out of memory.
 */
struct file *get_empty_filp(void)
{
	struct task_struct *tsk;
	static int old_max;
	struct file * f;

	/*
	 * Privileged users can go above max_files
	 */
	if (get_nr_files() >= files_stat.max_files && !capable(CAP_SYS_ADMIN)) {
		/*
		 * percpu_counters are inaccurate.  Do an expensive check before
		 * we go and fail.
		 */
		if (percpu_counter_sum(&nr_files) >= files_stat.max_files)
			goto over;
	}

	f = kmem_cache_alloc(filp_cachep, GFP_KERNEL);
	if (f == NULL)
		goto fail;

	percpu_counter_inc(&nr_files);
	memset(f, 0, sizeof(*f));
	if (security_file_alloc(f))
		goto fail_sec;

	tsk = current;
	INIT_LIST_HEAD(&f->f_u.fu_list);
	atomic_set(&f->f_count, 1);
	rwlock_init(&f->f_owner.lock);
	f->f_uid = tsk->fsuid;
	f->f_gid = tsk->fsgid;
	eventpoll_init_file(f);
	/* f->f_version: 0 */
	return f;

over:
	/* Ran out of filps - report that */
	if (get_nr_files() > old_max) {
		printk(KERN_INFO "VFS: file-max limit %d reached\n",
					get_max_files());
		old_max = get_nr_files();
	}
	goto fail;

fail_sec:
	file_free(f);
fail:
	return NULL;
}

EXPORT_SYMBOL(get_empty_filp);

void fastcall fput(struct file *file)
{
	if (atomic_dec_and_test(&file->f_count))
		__fput(file);
}

EXPORT_SYMBOL(fput);

/* __fput is called from task context when aio completion releases the last
 * last use of a struct file *.  Do not use otherwise.
 */
void fastcall __fput(struct file *file)
{
	struct dentry *dentry = file->f_dentry;
	struct vfsmount *mnt = file->f_vfsmnt;
	struct inode *inode = dentry->d_inode;

	might_sleep();

	fsnotify_close(file);
	/*
	 * The function eventpoll_release() should be the first called
	 * in the file cleanup chain.
	 */
	eventpoll_release(file);
	locks_remove_flock(file);

	if (file->f_op && file->f_op->release)
		file->f_op->release(inode, file);
	security_file_free(file);
	if (unlikely(inode->i_cdev != NULL))
		cdev_put(inode->i_cdev);
	fops_put(file->f_op);
	if (file->f_mode & FMODE_WRITE)
		put_write_access(inode);
	file_kill(file);
	file->f_dentry = NULL;
	file->f_vfsmnt = NULL;
	file_free(file);
	dput(dentry);
	mntput(mnt);
}

struct file fastcall *fget(unsigned int fd)
{
	struct file *file;
	struct files_struct *files = current->files;

	rcu_read_lock();
	file = fcheck_files(files, fd);
	if (file) {
		if (!atomic_inc_not_zero(&file->f_count)) {
			/* File object ref couldn't be taken */
			rcu_read_unlock();
			return NULL;
		}
	}
	rcu_read_unlock();

	return file;
}

EXPORT_SYMBOL(fget);

/*
 * Lightweight file lookup - no refcnt increment if fd table isn't shared. 
 * You can use this only if it is guranteed that the current task already 
 * holds a refcnt to that file. That check has to be done at fget() only
 * and a flag is returned to be passed to the corresponding fput_light().
 * There must not be a cloning between an fget_light/fput_light pair.
 */
struct file fastcall *fget_light(unsigned int fd, int *fput_needed)
{
	struct file *file;
	struct files_struct *files = current->files;

	*fput_needed = 0;
	if (likely((atomic_read(&files->count) == 1))) {
		file = fcheck_files(files, fd);
	} else {
		rcu_read_lock();
		file = fcheck_files(files, fd);
		if (file) {
			if (atomic_inc_not_zero(&file->f_count))
				*fput_needed = 1;
			else
				/* Didn't get the reference, someone's freed */
				file = NULL;
		}
		rcu_read_unlock();
	}

	return file;
}


void put_filp(struct file *file)
{
	if (atomic_dec_and_test(&file->f_count)) {
		security_file_free(file);
		file_kill(file);
		file_free(file);
	}
}

void file_move(struct file *file, struct list_head *list)
{
	if (!list)
		return;
	file_list_lock();
	list_move(&file->f_u.fu_list, list);
	file_list_unlock();
}

void file_kill(struct file *file)
{
	if (!list_empty(&file->f_u.fu_list)) {
		file_list_lock();
		list_del_init(&file->f_u.fu_list);
		file_list_unlock();
	}
}

int fs_may_remount_ro(struct super_block *sb)
{
	struct list_head *p;

	/* Check that no files are currently opened for writing. */
	file_list_lock();
	list_for_each(p, &sb->s_files) {
		struct file *file = list_entry(p, struct file, f_u.fu_list);
		struct inode *inode = file->f_dentry->d_inode;

		/* File with pending delete? */
		if (inode->i_nlink == 0)
			goto too_bad;

		/* Writeable file? */
		if (S_ISREG(inode->i_mode) && (file->f_mode & FMODE_WRITE))
			goto too_bad;
	}
	file_list_unlock();
	return 1; /* Tis' cool bro. */
too_bad:
	file_list_unlock();
	return 0;
}

void __init files_init(unsigned long mempages)
{ 
	int n; 
	/* One file with associated inode and dcache is very roughly 1K. 
	 * Per default don't use more than 10% of our memory for files. 
	 */ 

	n = (mempages * (PAGE_SIZE / 1024)) / 10;
	files_stat.max_files = n; 
	if (files_stat.max_files < NR_FILE)
		files_stat.max_files = NR_FILE;
	files_defer_init();
	percpu_counter_init(&nr_files, 0);
}