Linux preempt-rt

Check our new training course

Real-Time Linux with PREEMPT_RT

Check our new training course
with Creative Commons CC-BY-SA
lecture and lab materials

Bootlin logo

Elixir Cross Referencer

  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
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
/*
 *  linux/fs/super.c
 *
 *  Copyright (C) 1991, 1992  Linus Torvalds
 */

/*
 * super.c contains code to handle the super-block tables.
 */
#include <stdarg.h>

#include <linux/config.h>
#include <linux/sched.h>
#include <linux/kernel.h>
#include <linux/major.h>
#include <linux/stat.h>
#include <linux/errno.h>
#include <linux/string.h>
#include <linux/locks.h>
#include <linux/mm.h>

#include <asm/system.h>
#include <asm/segment.h>
#include <asm/bitops.h>
 
extern struct file_operations * get_blkfops(unsigned int);
extern struct file_operations * get_chrfops(unsigned int);

extern void wait_for_keypress(void);

extern int root_mountflags;

struct super_block super_blocks[NR_SUPER];

static int do_remount_sb(struct super_block *sb, int flags, char * data);

/* this is initialized in init/main.c */
dev_t ROOT_DEV = 0;

static struct file_system_type * file_systems = NULL;

int register_filesystem(struct file_system_type * fs)
{
	struct file_system_type ** tmp;

	if (!fs)
		return -EINVAL;
	if (fs->next)
		return -EBUSY;
	tmp = &file_systems;
	while (*tmp) {
		if (strcmp((*tmp)->name, fs->name) == 0)
			return -EBUSY;
		tmp = &(*tmp)->next;
	}
	*tmp = fs;
	return 0;
}

int unregister_filesystem(struct file_system_type * fs)
{
	struct file_system_type ** tmp;

	tmp = &file_systems;
	while (*tmp) {
		if (fs == *tmp) {
			*tmp = fs->next;
			fs->next = NULL;
			return 0;
		}
		tmp = &(*tmp)->next;
	}
	return -EINVAL;
}

static int fs_index(const char * __name)
{
	struct file_system_type * tmp;
	char * name;
	int err, index;

	err = getname(__name, &name);
	if (err)
		return err;
	index = 0;
	for (tmp = file_systems ; tmp ; tmp = tmp->next) {
		if (strcmp(tmp->name, name) == 0) {
			putname(name);
			return index;
		}
		index++;
	}
	putname(name);
	return -EINVAL;
}

static int fs_name(unsigned int index, char * buf)
{
	struct file_system_type * tmp;
	int err, len;

	tmp = file_systems;
	while (tmp && index > 0) {
		tmp = tmp->next;
		index--;
	}
	if (!tmp)
		return -EINVAL;
	len = strlen(tmp->name) + 1;
	err = verify_area(VERIFY_WRITE, buf, len);
	if (err)
		return err;
	memcpy_tofs(buf, tmp->name, len);
	return 0;
}

static int fs_maxindex(void)
{
	struct file_system_type * tmp;
	int index;

	index = 0;
	for (tmp = file_systems ; tmp ; tmp = tmp->next)
		index++;
	return index;
}

/*
 * Whee.. Weird sysv syscall. 
 */
asmlinkage int sys_sysfs(int option, ...)
{
	va_list args;
	int retval = -EINVAL;
	unsigned int index;

	va_start(args, option);
	switch (option) {
		case 1:
			retval = fs_index(va_arg(args, const char *));
			break;

		case 2:
			index = va_arg(args, unsigned int);
			retval = fs_name(index, va_arg(args, char *));
			break;

		case 3:
			retval = fs_maxindex();
			break;
	}
	va_end(args);
	return retval;
}

int get_filesystem_list(char * buf)
{
	int len = 0;
	struct file_system_type * tmp;

	tmp = file_systems;
	while (tmp && len < PAGE_SIZE - 80) {
		len += sprintf(buf+len, "%s\t%s\n",
			tmp->requires_dev ? "" : "nodev",
			tmp->name);
		tmp = tmp->next;
	}
	return len;
}

struct file_system_type *get_fs_type(char *name)
{
	struct file_system_type * fs = file_systems;
	
	if (!name)
		return fs;
	while (fs) {
		if (!strcmp(name,fs->name))
			break;
		fs = fs->next;
	}
	return fs;
}

void __wait_on_super(struct super_block * sb)
{
	struct wait_queue wait = { current, NULL };

	add_wait_queue(&sb->s_wait, &wait);
repeat:
	current->state = TASK_UNINTERRUPTIBLE;
	if (sb->s_lock) {
		schedule();
		goto repeat;
	}
	remove_wait_queue(&sb->s_wait, &wait);
	current->state = TASK_RUNNING;
}

void sync_supers(dev_t dev)
{
	struct super_block * sb;

	for (sb = super_blocks + 0 ; sb < super_blocks + NR_SUPER ; sb++) {
		if (!sb->s_dev)
			continue;
		if (dev && sb->s_dev != dev)
			continue;
		wait_on_super(sb);
		if (!sb->s_dev || !sb->s_dirt)
			continue;
		if (dev && (dev != sb->s_dev))
			continue;
		if (sb->s_op && sb->s_op->write_super)
			sb->s_op->write_super(sb);
	}
}

static struct super_block * get_super(dev_t dev)
{
	struct super_block * s;

	if (!dev)
		return NULL;
	s = 0+super_blocks;
	while (s < NR_SUPER+super_blocks)
		if (s->s_dev == dev) {
			wait_on_super(s);
			if (s->s_dev == dev)
				return s;
			s = 0+super_blocks;
		} else
			s++;
	return NULL;
}

void put_super(dev_t dev)
{
	struct super_block * sb;

	if (dev == ROOT_DEV) {
		printk("VFS: Root device %d/%d: prepare for armageddon\n",
							MAJOR(dev), MINOR(dev));
		return;
	}
	if (!(sb = get_super(dev)))
		return;
	if (sb->s_covered) {
		printk("VFS: Mounted device %d/%d - tssk, tssk\n",
						MAJOR(dev), MINOR(dev));
		return;
	}
	if (sb->s_op && sb->s_op->put_super)
		sb->s_op->put_super(sb);
}

static struct super_block * read_super(dev_t dev,char *name,int flags,
				       void *data, int silent)
{
	struct super_block * s;
	struct file_system_type *type;

	if (!dev)
		return NULL;
	check_disk_change(dev);
	s = get_super(dev);
	if (s)
		return s;
	if (!(type = get_fs_type(name))) {
		printk("VFS: on device %d/%d: get_fs_type(%s) failed\n",
						MAJOR(dev), MINOR(dev), name);
		return NULL;
	}
	for (s = 0+super_blocks ;; s++) {
		if (s >= NR_SUPER+super_blocks)
			return NULL;
		if (!s->s_dev)
			break;
	}
	s->s_dev = dev;
	s->s_flags = flags;
	if (!type->read_super(s,data, silent)) {
		s->s_dev = 0;
		return NULL;
	}
	s->s_dev = dev;
	s->s_covered = NULL;
	s->s_rd_only = 0;
	s->s_dirt = 0;
	s->s_type = type;
	return s;
}

/*
 * Unnamed block devices are dummy devices used by virtual
 * filesystems which don't use real block-devices.  -- jrs
 */

static char unnamed_dev_in_use[256/8] = { 0, };

static dev_t get_unnamed_dev(void)
{
	int i;

	for (i = 1; i < 256; i++) {
		if (!set_bit(i,unnamed_dev_in_use))
			return (UNNAMED_MAJOR << 8) | i;
	}
	return 0;
}

static void put_unnamed_dev(dev_t dev)
{
	if (!dev)
		return;
	if (MAJOR(dev) == UNNAMED_MAJOR &&
	    clear_bit(MINOR(dev), unnamed_dev_in_use))
		return;
	printk("VFS: put_unnamed_dev: freeing unused device %d/%d\n",
			MAJOR(dev), MINOR(dev));
}

static int do_umount(dev_t dev)
{
	struct super_block * sb;
	int retval;
	
	if (dev==ROOT_DEV) {
		/* Special case for "unmounting" root.  We just try to remount
		   it readonly, and sync() the device. */
		if (!(sb=get_super(dev)))
			return -ENOENT;
		if (!(sb->s_flags & MS_RDONLY)) {
			fsync_dev(dev);
			retval = do_remount_sb(sb, MS_RDONLY, 0);
			if (retval)
				return retval;
		}
		return 0;
	}
	if (!(sb=get_super(dev)) || !(sb->s_covered))
		return -ENOENT;
	if (!sb->s_covered->i_mount)
		printk("VFS: umount(%d/%d): mounted inode has i_mount=NULL\n",
							MAJOR(dev), MINOR(dev));
	if (!fs_may_umount(dev, sb->s_mounted))
		return -EBUSY;
	sb->s_covered->i_mount = NULL;
	iput(sb->s_covered);
	sb->s_covered = NULL;
	iput(sb->s_mounted);
	sb->s_mounted = NULL;
	if (sb->s_op && sb->s_op->write_super && sb->s_dirt)
		sb->s_op->write_super(sb);
	put_super(dev);
	return 0;
}

/*
 * Now umount can handle mount points as well as block devices.
 * This is important for filesystems which use unnamed block devices.
 *
 * There is a little kludge here with the dummy_inode.  The current
 * vfs release functions only use the r_dev field in the inode so
 * we give them the info they need without using a real inode.
 * If any other fields are ever needed by any block device release
 * functions, they should be faked here.  -- jrs
 */

asmlinkage int sys_umount(char * name)
{
	struct inode * inode;
	dev_t dev;
	int retval;
	struct inode dummy_inode;
	struct file_operations * fops;

	if (!suser())
		return -EPERM;
	retval = namei(name,&inode);
	if (retval) {
		retval = lnamei(name,&inode);
		if (retval)
			return retval;
	}
	if (S_ISBLK(inode->i_mode)) {
		dev = inode->i_rdev;
		if (IS_NODEV(inode)) {
			iput(inode);
			return -EACCES;
		}
	} else {
		if (!inode->i_sb || inode != inode->i_sb->s_mounted) {
			iput(inode);
			return -EINVAL;
		}
		dev = inode->i_sb->s_dev;
		iput(inode);
		memset(&dummy_inode, 0, sizeof(dummy_inode));
		dummy_inode.i_rdev = dev;
		inode = &dummy_inode;
	}
	if (MAJOR(dev) >= MAX_BLKDEV) {
		iput(inode);
		return -ENXIO;
	}
	if (!(retval = do_umount(dev)) && dev != ROOT_DEV) {
		fops = get_blkfops(MAJOR(dev));
		if (fops && fops->release)
			fops->release(inode,NULL);
		if (MAJOR(dev) == UNNAMED_MAJOR)
			put_unnamed_dev(dev);
	}
	if (inode != &dummy_inode)
		iput(inode);
	if (retval)
		return retval;
	fsync_dev(dev);
	return 0;
}

/*
 * do_mount() does the actual mounting after sys_mount has done the ugly
 * parameter parsing. When enough time has gone by, and everything uses the
 * new mount() parameters, sys_mount() can then be cleaned up.
 *
 * We cannot mount a filesystem if it has active, used, or dirty inodes.
 * We also have to flush all inode-data for this device, as the new mount
 * might need new info.
 */
static int do_mount(dev_t dev, const char * dir, char * type, int flags, void * data)
{
	struct inode * dir_i;
	struct super_block * sb;
	int error;

	error = namei(dir,&dir_i);
	if (error)
		return error;
	if (dir_i->i_count != 1 || dir_i->i_mount) {
		iput(dir_i);
		return -EBUSY;
	}
	if (!S_ISDIR(dir_i->i_mode)) {
		iput(dir_i);
		return -ENOTDIR;
	}
	if (!fs_may_mount(dev)) {
		iput(dir_i);
		return -EBUSY;
	}
	sb = read_super(dev,type,flags,data,0);
	if (!sb) {
		iput(dir_i);
		return -EINVAL;
	}
	if (sb->s_covered) {
		iput(dir_i);
		return -EBUSY;
	}
	sb->s_covered = dir_i;
	dir_i->i_mount = sb->s_mounted;
	return 0;		/* we don't iput(dir_i) - see umount */
}


/*
 * Alters the mount flags of a mounted file system. Only the mount point
 * is used as a reference - file system type and the device are ignored.
 * FS-specific mount options can't be altered by remounting.
 */

static int do_remount_sb(struct super_block *sb, int flags, char *data)
{
	int retval;
	
	if (!(flags & MS_RDONLY ) && sb->s_dev && is_read_only(sb->s_dev))
		return -EACCES;
		/*flags |= MS_RDONLY;*/
	/* If we are remounting RDONLY, make sure there are no rw files open */
	if ((flags & MS_RDONLY) && !(sb->s_flags & MS_RDONLY))
		if (!fs_may_remount_ro(sb->s_dev))
			return -EBUSY;
	if (sb->s_op && sb->s_op->remount_fs) {
		retval = sb->s_op->remount_fs(sb, &flags, data);
		if (retval)
			return retval;
	}
	sb->s_flags = (sb->s_flags & ~MS_RMT_MASK) |
		(flags & MS_RMT_MASK);
	return 0;
}

static int do_remount(const char *dir,int flags,char *data)
{
	struct inode *dir_i;
	int retval;

	retval = namei(dir,&dir_i);
	if (retval)
		return retval;
	if (dir_i != dir_i->i_sb->s_mounted) {
		iput(dir_i);
		return -EINVAL;
	}
	retval = do_remount_sb(dir_i->i_sb, flags, data);
	iput(dir_i);
	return retval;
}

static int copy_mount_options (const void * data, unsigned long *where)
{
	int i;
	unsigned long page;
	struct vm_area_struct * vma;

	*where = 0;
	if (!data)
		return 0;

	vma = find_vma(current, (unsigned long) data);
	if (!vma || (unsigned long) data < vma->vm_start)
		return -EFAULT;
	i = vma->vm_end - (unsigned long) data;
	if (PAGE_SIZE <= (unsigned long) i)
		i = PAGE_SIZE-1;
	if (!(page = __get_free_page(GFP_KERNEL))) {
		return -ENOMEM;
	}
	memcpy_fromfs((void *) page,data,i);
	*where = page;
	return 0;
}

/*
 * Flags is a 16-bit value that allows up to 16 non-fs dependent flags to
 * be given to the mount() call (ie: read-only, no-dev, no-suid etc).
 *
 * data is a (void *) that can point to any structure up to
 * PAGE_SIZE-1 bytes, which can contain arbitrary fs-dependent
 * information (or be NULL).
 *
 * NOTE! As old versions of mount() didn't use this setup, the flags
 * has to have a special 16-bit magic number in the hight word:
 * 0xC0ED. If this magic word isn't present, the flags and data info
 * isn't used, as the syscall assumes we are talking to an older
 * version that didn't understand them.
 */
asmlinkage int sys_mount(char * dev_name, char * dir_name, char * type,
	unsigned long new_flags, void * data)
{
	struct file_system_type * fstype;
	struct inode * inode;
	struct file_operations * fops;
	dev_t dev;
	int retval;
	char * t;
	unsigned long flags = 0;
	unsigned long page = 0;

	if (!suser())
		return -EPERM;
	if ((new_flags &
	     (MS_MGC_MSK | MS_REMOUNT)) == (MS_MGC_VAL | MS_REMOUNT)) {
		retval = copy_mount_options (data, &page);
		if (retval < 0)
			return retval;
		retval = do_remount(dir_name,
				    new_flags & ~MS_MGC_MSK & ~MS_REMOUNT,
				    (char *) page);
		free_page(page);
		return retval;
	}
	retval = copy_mount_options (type, &page);
	if (retval < 0)
		return retval;
	fstype = get_fs_type((char *) page);
	free_page(page);
	if (!fstype)		
		return -ENODEV;
	t = fstype->name;
	fops = NULL;
	if (fstype->requires_dev) {
		retval = namei(dev_name,&inode);
		if (retval)
			return retval;
		if (!S_ISBLK(inode->i_mode)) {
			iput(inode);
			return -ENOTBLK;
		}
		if (IS_NODEV(inode)) {
			iput(inode);
			return -EACCES;
		}
		dev = inode->i_rdev;
		if (MAJOR(dev) >= MAX_BLKDEV) {
			iput(inode);
			return -ENXIO;
		}
		fops = get_blkfops(MAJOR(dev));
		if (!fops) {
			iput(inode);
			return -ENOTBLK;
		}
		if (fops->open) {
			struct file dummy;	/* allows read-write or read-only flag */
			memset(&dummy, 0, sizeof(dummy));
			dummy.f_inode = inode;
			dummy.f_mode = (new_flags & MS_RDONLY) ? 1 : 3;
			retval = fops->open(inode, &dummy);
			if (retval) {
				iput(inode);
				return retval;
			}
		}

	} else {
		if (!(dev = get_unnamed_dev()))
			return -EMFILE;
		inode = NULL;
	}
	page = 0;
	if ((new_flags & MS_MGC_MSK) == MS_MGC_VAL) {
		flags = new_flags & ~MS_MGC_MSK;
		retval = copy_mount_options(data, &page);
		if (retval < 0) {
			iput(inode);
			return retval;
		}
	}
	retval = do_mount(dev,dir_name,t,flags,(void *) page);
	free_page(page);
	if (retval && fops && fops->release)
		fops->release(inode, NULL);
	iput(inode);
	return retval;
}

void mount_root(void)
{
	struct file_system_type * fs_type;
	struct super_block * sb;
	struct inode * inode, d_inode;
	struct file filp;
	int retval;

	memset(super_blocks, 0, sizeof(super_blocks));
#ifdef CONFIG_BLK_DEV_FD
	if (MAJOR(ROOT_DEV) == FLOPPY_MAJOR) {
		printk(KERN_NOTICE "VFS: Insert root floppy and press ENTER\n");
		wait_for_keypress();
	}
#endif

	memset(&filp, 0, sizeof(filp));
	memset(&d_inode, 0, sizeof(d_inode));
	d_inode.i_rdev = ROOT_DEV;
	filp.f_inode = &d_inode;
	if ( root_mountflags & MS_RDONLY)
		filp.f_mode = 1; /* read only */
	else
		filp.f_mode = 3; /* read write */
	retval = blkdev_open(&d_inode, &filp);
	if(retval == -EROFS){
		root_mountflags |= MS_RDONLY;
		filp.f_mode = 1;
		retval = blkdev_open(&d_inode, &filp);
	}

	for (fs_type = file_systems ; fs_type ; fs_type = fs_type->next) {
		if(retval)
			break;
		if (!fs_type->requires_dev)
			continue;
		sb = read_super(ROOT_DEV,fs_type->name,root_mountflags,NULL,1);
		if (sb) {
			inode = sb->s_mounted;
			inode->i_count += 3 ;	/* NOTE! it is logically used 4 times, not 1 */
			sb->s_covered = inode;
			sb->s_flags = root_mountflags;
			current->fs->pwd = inode;
			current->fs->root = inode;
			printk ("VFS: Mounted root (%s filesystem)%s.\n",
				fs_type->name,
				(sb->s_flags & MS_RDONLY) ? " readonly" : "");
			return;
		}
	}
	panic("VFS: Unable to mount root fs on %02x:%02x",
		MAJOR(ROOT_DEV), MINOR(ROOT_DEV));
}