summaryrefslogtreecommitdiffstats
path: root/block/ioctl.c
blob: 6b785181344fe197d1b72f94367e319bfe320ed1 (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
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
// SPDX-License-Identifier: GPL-2.0
#include <linux/capability.h>
#include <linux/compat.h>
#include <linux/blkdev.h>
#include <linux/export.h>
#include <linux/gfp.h>
#include <linux/blkpg.h>
#include <linux/hdreg.h>
#include <linux/backing-dev.h>
#include <linux/fs.h>
#include <linux/blktrace_api.h>
#include <linux/pr.h>
#include <linux/uaccess.h>
#include "blk.h"

static int blkpg_do_ioctl(struct block_device *bdev,
			  struct blkpg_partition __user *upart, int op)
{
	struct blkpg_partition p;
	long long start, length;

	if (!capable(CAP_SYS_ADMIN))
		return -EACCES;
	if (copy_from_user(&p, upart, sizeof(struct blkpg_partition)))
		return -EFAULT;
	if (bdev_is_partition(bdev))
		return -EINVAL;

	if (p.pno <= 0)
		return -EINVAL;

	if (op == BLKPG_DEL_PARTITION)
		return bdev_del_partition(bdev, p.pno);

	start = p.start >> SECTOR_SHIFT;
	length = p.length >> SECTOR_SHIFT;

	/* check for fit in a hd_struct */
	if (sizeof(sector_t) < sizeof(long long)) {
		long pstart = start, plength = length;

		if (pstart != start || plength != length || pstart < 0 ||
		    plength < 0 || p.pno > 65535)
			return -EINVAL;
	}

	switch (op) {
	case BLKPG_ADD_PARTITION:
		/* check if partition is aligned to blocksize */
		if (p.start & (bdev_logical_block_size(bdev) - 1))
			return -EINVAL;
		return bdev_add_partition(bdev, p.pno, start, length);
	case BLKPG_RESIZE_PARTITION:
		return bdev_resize_partition(bdev, p.pno, start, length);
	default:
		return -EINVAL;
	}
}

static int blkpg_ioctl(struct block_device *bdev,
		       struct blkpg_ioctl_arg __user *arg)
{
	struct blkpg_partition __user *udata;
	int op;

	if (get_user(op, &arg->op) || get_user(udata, &arg->data))
		return -EFAULT;

	return blkpg_do_ioctl(bdev, udata, op);
}

#ifdef CONFIG_COMPAT
struct compat_blkpg_ioctl_arg {
	compat_int_t op;
	compat_int_t flags;
	compat_int_t datalen;
	compat_caddr_t data;
};

static int compat_blkpg_ioctl(struct block_device *bdev,
			      struct compat_blkpg_ioctl_arg __user *arg)
{
	compat_caddr_t udata;
	int op;

	if (get_user(op, &arg->op) || get_user(udata, &arg->data))
		return -EFAULT;

	return blkpg_do_ioctl(bdev, compat_ptr(udata), op);
}
#endif

static int blkdev_reread_part(struct block_device *bdev)
{
	int ret;

	if (!disk_part_scan_enabled(bdev->bd_disk) || bdev_is_partition(bdev))
		return -EINVAL;
	if (!capable(CAP_SYS_ADMIN))
		return -EACCES;

	mutex_lock(&bdev->bd_mutex);
	ret = bdev_disk_changed(bdev, false);
	mutex_unlock(&bdev->bd_mutex);

	return ret;
}

static int blk_ioctl_discard(struct block_device *bdev, fmode_t mode,
		unsigned long arg, unsigned long flags)
{
	uint64_t range[2];
	uint64_t start, len;
	struct request_queue *q = bdev_get_queue(bdev);
	int err;

	if (!(mode & FMODE_WRITE))
		return -EBADF;

	if (!blk_queue_discard(q))
		return -EOPNOTSUPP;

	if (copy_from_user(range, (void __user *)arg, sizeof(range)))
		return -EFAULT;

	start = range[0];
	len = range[1];

	if (start & 511)
		return -EINVAL;
	if (len & 511)
		return -EINVAL;

	if (start + len > i_size_read(bdev->bd_inode))
		return -EINVAL;

	err = truncate_bdev_range(bdev, mode, start, start + len - 1);
	if (err)
		return err;

	return blkdev_issue_discard(bdev, start >> 9, len >> 9,
				    GFP_KERNEL, flags);
}

static int blk_ioctl_zeroout(struct block_device *bdev, fmode_t mode,
		unsigned long arg)
{
	uint64_t range[2];
	uint64_t start, end, len;
	int err;

	if (!(mode & FMODE_WRITE))
		return -EBADF;

	if (copy_from_user(range, (void __user *)arg, sizeof(range)))
		return -EFAULT;

	start = range[0];
	len = range[1];
	end = start + len - 1;

	if (start & 511)
		return -EINVAL;
	if (len & 511)
		return -EINVAL;
	if (end >= (uint64_t)i_size_read(bdev->bd_inode))
		return -EINVAL;
	if (end < start)
		return -EINVAL;

	/* Invalidate the page cache, including dirty pages */
	err = truncate_bdev_range(bdev, mode, start, end);
	if (err)
		return err;

	return blkdev_issue_zeroout(bdev, start >> 9, len >> 9, GFP_KERNEL,
			BLKDEV_ZERO_NOUNMAP);
}

static int put_ushort(unsigned short __user *argp, unsigned short val)
{
	return put_user(val, argp);
}

static int put_int(int __user *argp, int val)
{
	return put_user(val, argp);
}

static int put_uint(unsigned int __user *argp, unsigned int val)
{
	return put_user(val, argp);
}

static int put_long(long __user *argp, long val)
{
	return put_user(val, argp);
}

static int put_ulong(unsigned long __user *argp, unsigned long val)
{
	return put_user(val, argp);
}

static int put_u64(u64 __user *argp, u64 val)
{
	return put_user(val, argp);
}

#ifdef CONFIG_COMPAT
static int compat_put_long(compat_long_t __user *argp, long val)
{
	return put_user(val, argp);
}

static int compat_put_ulong(compat_ulong_t __user *argp, compat_ulong_t val)
{
	return put_user(val, argp);
}
#endif

#ifdef CONFIG_COMPAT
/*
 * This is the equivalent of compat_ptr_ioctl(), to be used by block
 * drivers that implement only commands that are completely compatible
 * between 32-bit and 64-bit user space
 */
int blkdev_compat_ptr_ioctl(struct block_device *bdev, fmode_t mode,
			unsigned cmd, unsigned long arg)
{
	struct gendisk *disk = bdev->bd_disk;

	if (disk->fops->ioctl)
		return disk->fops->ioctl(bdev, mode, cmd,
					 (unsigned long)compat_ptr(arg));

	return -ENOIOCTLCMD;
}
EXPORT_SYMBOL(blkdev_compat_ptr_ioctl);
#endif

static int blkdev_pr_register(struct block_device *bdev,
		struct pr_registration __user *arg)
{
	const struct pr_ops *ops = bdev->bd_disk->fops->pr_ops;
	struct pr_registration reg;

	if (!capable(CAP_SYS_ADMIN))
		return -EPERM;
	if (!ops || !ops->pr_register)
		return -EOPNOTSUPP;
	if (copy_from_user(&reg, arg, sizeof(reg)))
		return -EFAULT;

	if (reg.flags & ~PR_FL_IGNORE_KEY)
		return -EOPNOTSUPP;
	return ops->pr_register(bdev, reg.old_key, reg.new_key, reg.flags);
}

static int blkdev_pr_reserve(struct block_device *bdev,
		struct pr_reservation __user *arg)
{
	const struct pr_ops *ops = bdev->bd_disk->fops->pr_ops;
	struct pr_reservation rsv;

	if (!capable(CAP_SYS_ADMIN))
		return -EPERM;
	if (!ops || !ops->pr_reserve)
		return -EOPNOTSUPP;
	if (copy_from_user(&rsv, arg, sizeof(rsv)))
		return -EFAULT;

	if (rsv.flags & ~PR_FL_IGNORE_KEY)
		return -EOPNOTSUPP;
	return ops->pr_reserve(bdev, rsv.key, rsv.type, rsv.flags);
}

static int blkdev_pr_release(struct block_device *bdev,
		struct pr_reservation __user *arg)
{
	const struct pr_ops *ops = bdev->bd_disk->fops->pr_ops;
	struct pr_reservation rsv;

	if (!capable(CAP_SYS_ADMIN))
		return -EPERM;
	if (!ops || !ops->pr_release)
		return -EOPNOTSUPP;
	if (copy_from_user(&rsv, arg, sizeof(rsv)))
		return -EFAULT;

	if (rsv.flags)
		return -EOPNOTSUPP;
	return ops->pr_release(bdev, rsv.key, rsv.type);
}

static int blkdev_pr_preempt(struct block_device *bdev,
		struct pr_preempt __user *arg, bool abort)
{
	const struct pr_ops *ops = bdev->bd_disk->fops->pr_ops;
	struct pr_preempt p;

	if (!capable(CAP_SYS_ADMIN))
		return -EPERM;
	if (!ops || !ops->pr_preempt)
		return -EOPNOTSUPP;
	if (copy_from_user(&p, arg, sizeof(p)))
		return -EFAULT;

	if (p.flags)
		return -EOPNOTSUPP;
	return ops->pr_preempt(bdev, p.old_key, p.new_key, p.type, abort);
}

static int blkdev_pr_clear(struct block_device *bdev,
		struct pr_clear __user *arg)
{
	const struct pr_ops *ops = bdev->bd_disk->fops->pr_ops;
	struct pr_clear c;

	if (!capable(CAP_SYS_ADMIN))
		return -EPERM;
	if (!ops || !ops->pr_clear)
		return -EOPNOTSUPP;
	if (copy_from_user(&c, arg, sizeof(c)))
		return -EFAULT;

	if (c.flags)
		return -EOPNOTSUPP;
	return ops->pr_clear(bdev, c.key);
}

static int blkdev_flushbuf(struct block_device *bdev, fmode_t mode,
		unsigned cmd, unsigned long arg)
{
	if (!capable(CAP_SYS_ADMIN))
		return -EACCES;
	fsync_bdev(bdev);
	invalidate_bdev(bdev);
	return 0;
}

static int blkdev_roset(struct block_device *bdev, fmode_t mode,
		unsigned cmd, unsigned long arg)
{
	int ret, n;

	if (!capable(CAP_SYS_ADMIN))
		return -EACCES;

	if (get_user(n, (int __user *)arg))
		return -EFAULT;
	if (bdev->bd_disk->fops->set_read_only) {
		ret = bdev->bd_disk->fops->set_read_only(bdev, n);
		if (ret)
			return ret;
	}
	bdev->bd_part->policy = n;
	return 0;
}

static int blkdev_getgeo(struct block_device *bdev,
		struct hd_geometry __user *argp)
{
	struct gendisk *disk = bdev->bd_disk;
	struct hd_geometry geo;
	int ret;

	if (!argp)
		return -EINVAL;
	if (!disk->fops->getgeo)
		return -ENOTTY;

	/*
	 * We need to set the startsect first, the driver may
	 * want to override it.
	 */
	memset(&geo, 0, sizeof(geo));
	geo.start = get_start_sect(bdev);
	ret = disk->fops->getgeo(bdev, &geo);
	if (ret)
		return ret;
	if (copy_to_user(argp, &geo, sizeof(geo)))
		return -EFAULT;
	return 0;
}

#ifdef CONFIG_COMPAT
struct compat_hd_geometry {
	unsigned char heads;
	unsigned char sectors;
	unsigned short cylinders;
	u32 start;
};

static int compat_hdio_getgeo(struct block_device *bdev,
			      struct compat_hd_geometry __user *ugeo)
{
	struct gendisk *disk = bdev->bd_disk;
	struct hd_geometry geo;
	int ret;

	if (!ugeo)
		return -EINVAL;
	if (!disk->fops->getgeo)
		return -ENOTTY;

	memset(&geo, 0, sizeof(geo));
	/*
	 * We need to set the startsect first, the driver may
	 * want to override it.
	 */
	geo.start = get_start_sect(bdev);
	ret = disk->fops->getgeo(bdev, &geo);
	if (ret)
		return ret;

	ret = copy_to_user(ugeo, &geo, 4);
	ret |= put_user(geo.start, &ugeo->start);
	if (ret)
		ret = -EFAULT;

	return ret;
}
#endif

/* set the logical block size */
static int blkdev_bszset(struct block_device *bdev, fmode_t mode,
		int __user *argp)
{
	int ret, n;

	if (!capable(CAP_SYS_ADMIN))
		return -EACCES;
	if (!argp)
		return -EINVAL;
	if (get_user(n, argp))
		return -EFAULT;

	if (mode & FMODE_EXCL)
		return set_blocksize(bdev, n);

	if (IS_ERR(blkdev_get_by_dev(bdev->bd_dev, mode | FMODE_EXCL, &bdev)))
		return -EBUSY;
	ret = set_blocksize(bdev, n);
	blkdev_put(bdev, mode | FMODE_EXCL);

	return ret;
}

/*
 * Common commands that are handled the same way on native and compat
 * user space. Note the separate arg/argp parameters that are needed
 * to deal with the compat_ptr() conversion.
 */
static int blkdev_common_ioctl(struct block_device *bdev, fmode_t mode,
				unsigned cmd, unsigned long arg, void __user *argp)
{
	unsigned int max_sectors;

	switch (cmd) {
	case BLKFLSBUF:
		return blkdev_flushbuf(bdev, mode, cmd, arg);
	case BLKROSET:
		return blkdev_roset(bdev, mode, cmd, arg);
	case BLKDISCARD:
		return blk_ioctl_discard(bdev, mode, arg, 0);
	case BLKSECDISCARD:
		return blk_ioctl_discard(bdev, mode, arg,
				BLKDEV_DISCARD_SECURE);
	case BLKZEROOUT:
		return blk_ioctl_zeroout(bdev, mode, arg);
	case BLKREPORTZONE:
		return blkdev_report_zones_ioctl(bdev, mode, cmd, arg);
	case BLKRESETZONE:
	case BLKOPENZONE:
	case BLKCLOSEZONE:
	case BLKFINISHZONE:
		return blkdev_zone_mgmt_ioctl(bdev, mode, cmd, arg);
	case BLKGETZONESZ:
		return put_uint(argp, bdev_zone_sectors(bdev));
	case BLKGETNRZONES:
		return put_uint(argp, blkdev_nr_zones(bdev->bd_disk));
	case BLKROGET:
		return put_int(argp, bdev_read_only(bdev) != 0);
	case BLKSSZGET: /* get block device logical block size */
		return put_int(argp, bdev_logical_block_size(bdev));
	case BLKPBSZGET: /* get block device physical block size */
		return put_uint(argp, bdev_physical_block_size(bdev));
	case BLKIOMIN:
		return put_uint(argp, bdev_io_min(bdev));
	case BLKIOOPT:
		return put_uint(argp, bdev_io_opt(bdev));
	case BLKALIGNOFF:
		return put_int(argp, bdev_alignment_offset(bdev));
	case BLKDISCARDZEROES:
		return put_uint(argp, 0);
	case BLKSECTGET:
		max_sectors = min_t(unsigned int, USHRT_MAX,
				    queue_max_sectors(bdev_get_queue(bdev)));
		return put_ushort(argp, max_sectors);
	case BLKROTATIONAL:
		return put_ushort(argp, !blk_queue_nonrot(bdev_get_queue(bdev)));
	case BLKRASET:
	case BLKFRASET:
		if(!capable(CAP_SYS_ADMIN))
			return -EACCES;
		bdev->bd_bdi->ra_pages = (arg * 512) / PAGE_SIZE;
		return 0;
	case BLKRRPART:
		return blkdev_reread_part(bdev);
	case BLKTRACESTART:
	case BLKTRACESTOP:
	case BLKTRACETEARDOWN:
		return blk_trace_ioctl(bdev, cmd, argp);
	case IOC_PR_REGISTER:
		return blkdev_pr_register(bdev, argp);
	case IOC_PR_RESERVE:
		return blkdev_pr_reserve(bdev, argp);
	case IOC_PR_RELEASE:
		return blkdev_pr_release(bdev, argp);
	case IOC_PR_PREEMPT:
		return blkdev_pr_preempt(bdev, argp, false);
	case IOC_PR_PREEMPT_ABORT:
		return blkdev_pr_preempt(bdev, argp, true);
	case IOC_PR_CLEAR:
		return blkdev_pr_clear(bdev, argp);
	default:
		return -ENOIOCTLCMD;
	}
}

/*
 * Always keep this in sync with compat_blkdev_ioctl()
 * to handle all incompatible commands in both functions.
 *
 * New commands must be compatible and go into blkdev_common_ioctl
 */
int blkdev_ioctl(struct block_device *bdev, fmode_t mode, unsigned cmd,
			unsigned long arg)
{
	int ret;
	loff_t size;
	void __user *argp = (void __user *)arg;

	switch (cmd) {
	/* These need separate implementations for the data structure */
	case HDIO_GETGEO:
		return blkdev_getgeo(bdev, argp);
	case BLKPG:
		return blkpg_ioctl(bdev, argp);

	/* Compat mode returns 32-bit data instead of 'long' */
	case BLKRAGET:
	case BLKFRAGET:
		if (!argp)
			return -EINVAL;
		return put_long(argp, (bdev->bd_bdi->ra_pages*PAGE_SIZE) / 512);
	case BLKGETSIZE:
		size = i_size_read(bdev->bd_inode);
		if ((size >> 9) > ~0UL)
			return -EFBIG;
		return put_ulong(argp, size >> 9);

	/* The data is compatible, but the command number is different */
	case BLKBSZGET: /* get block device soft block size (cf. BLKSSZGET) */
		return put_int(argp, block_size(bdev));
	case BLKBSZSET:
		return blkdev_bszset(bdev, mode, argp);
	case BLKGETSIZE64:
		return put_u64(argp, i_size_read(bdev->bd_inode));

	/* Incompatible alignment on i386 */
	case BLKTRACESETUP:
		return blk_trace_ioctl(bdev, cmd, argp);
	default:
		break;
	}

	ret = blkdev_common_ioctl(bdev, mode, cmd, arg, argp);
	if (ret != -ENOIOCTLCMD)
		return ret;

	if (!bdev->bd_disk->fops->ioctl)
		return -ENOTTY;
	return bdev->bd_disk->fops->ioctl(bdev, mode, cmd, arg);
}
EXPORT_SYMBOL_GPL(blkdev_ioctl); /* for /dev/raw */

#ifdef CONFIG_COMPAT

#define BLKBSZGET_32		_IOR(0x12, 112, int)
#define BLKBSZSET_32		_IOW(0x12, 113, int)
#define BLKGETSIZE64_32		_IOR(0x12, 114, int)

/* Most of the generic ioctls are handled in the normal fallback path.
   This assumes the blkdev's low level compat_ioctl always returns
   ENOIOCTLCMD for unknown ioctls. */
long compat_blkdev_ioctl(struct file *file, unsigned cmd, unsigned long arg)
{
	int ret;
	void __user *argp = compat_ptr(arg);
	struct inode *inode = file->f_mapping->host;
	struct block_device *bdev = inode->i_bdev;
	struct gendisk *disk = bdev->bd_disk;
	fmode_t mode = file->f_mode;
	loff_t size;

	/*
	 * O_NDELAY can be altered using fcntl(.., F_SETFL, ..), so we have
	 * to updated it before every ioctl.
	 */
	if (file->f_flags & O_NDELAY)
		mode |= FMODE_NDELAY;
	else
		mode &= ~FMODE_NDELAY;

	switch (cmd) {
	/* These need separate implementations for the data structure */
	case HDIO_GETGEO:
		return compat_hdio_getgeo(bdev, argp);
	case BLKPG:
		return compat_blkpg_ioctl(bdev, argp);

	/* Compat mode returns 32-bit data instead of 'long' */
	case BLKRAGET:
	case BLKFRAGET:
		if (!argp)
			return -EINVAL;
		return compat_put_long(argp,
			       (bdev->bd_bdi->ra_pages * PAGE_SIZE) / 512);
	case BLKGETSIZE:
		size = i_size_read(bdev->bd_inode);
		if ((size >> 9) > ~0UL)
			return -EFBIG;
		return compat_put_ulong(argp, size >> 9);

	/* The data is compatible, but the command number is different */
	case BLKBSZGET_32: /* get the logical block size (cf. BLKSSZGET) */
		return put_int(argp, bdev_logical_block_size(bdev));
	case BLKBSZSET_32:
		return blkdev_bszset(bdev, mode, argp);
	case BLKGETSIZE64_32:
		return put_u64(argp, i_size_read(bdev->bd_inode));

	/* Incompatible alignment on i386 */
	case BLKTRACESETUP32:
		return blk_trace_ioctl(bdev, cmd, argp);
	default:
		break;
	}

	ret = blkdev_common_ioctl(bdev, mode, cmd, arg, argp);
	if (ret == -ENOIOCTLCMD && disk->fops->compat_ioctl)
		ret = disk->fops->compat_ioctl(bdev, mode, cmd, arg);

	return ret;
}
#endif