summaryrefslogtreecommitdiffstats
path: root/drivers/block/brd.c
blob: 95694113e38eb9ab35cbe14a189fa851219ffd60 (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
// SPDX-License-Identifier: GPL-2.0-only
/*
 * Ram backed block device driver.
 *
 * Copyright (C) 2007 Nick Piggin
 * Copyright (C) 2007 Novell Inc.
 *
 * Parts derived from drivers/block/rd.c, and drivers/block/loop.c, copyright
 * of their respective owners.
 */

#include <linux/init.h>
#include <linux/initrd.h>
#include <linux/module.h>
#include <linux/moduleparam.h>
#include <linux/major.h>
#include <linux/blkdev.h>
#include <linux/bio.h>
#include <linux/highmem.h>
#include <linux/mutex.h>
#include <linux/pagemap.h>
#include <linux/radix-tree.h>
#include <linux/fs.h>
#include <linux/slab.h>
#include <linux/backing-dev.h>
#include <linux/debugfs.h>

#include <linux/uaccess.h>

#define PAGE_SECTORS_SHIFT	(PAGE_SHIFT - SECTOR_SHIFT)
#define PAGE_SECTORS		(1 << PAGE_SECTORS_SHIFT)

/*
 * Each block ramdisk device has a radix_tree brd_pages of pages that stores
 * the pages containing the block device's contents. A brd page's ->index is
 * its offset in PAGE_SIZE units. This is similar to, but in no way connected
 * with, the kernel's pagecache or buffer cache (which sit above our block
 * device).
 */
struct brd_device {
	int			brd_number;
	struct gendisk		*brd_disk;
	struct list_head	brd_list;

	/*
	 * Backing store of pages and lock to protect it. This is the contents
	 * of the block device.
	 */
	spinlock_t		brd_lock;
	struct radix_tree_root	brd_pages;
	u64			brd_nr_pages;
};

/*
 * Look up and return a brd's page for a given sector.
 */
static struct page *brd_lookup_page(struct brd_device *brd, sector_t sector)
{
	pgoff_t idx;
	struct page *page;

	/*
	 * The page lifetime is protected by the fact that we have opened the
	 * device node -- brd pages will never be deleted under us, so we
	 * don't need any further locking or refcounting.
	 *
	 * This is strictly true for the radix-tree nodes as well (ie. we
	 * don't actually need the rcu_read_lock()), however that is not a
	 * documented feature of the radix-tree API so it is better to be
	 * safe here (we don't have total exclusion from radix tree updates
	 * here, only deletes).
	 */
	rcu_read_lock();
	idx = sector >> PAGE_SECTORS_SHIFT; /* sector to page index */
	page = radix_tree_lookup(&brd->brd_pages, idx);
	rcu_read_unlock();

	BUG_ON(page && page->index != idx);

	return page;
}

/*
 * Look up and return a brd's page for a given sector.
 * If one does not exist, allocate an empty page, and insert that. Then
 * return it.
 */
static struct page *brd_insert_page(struct brd_device *brd, sector_t sector)
{
	pgoff_t idx;
	struct page *page;
	gfp_t gfp_flags;

	page = brd_lookup_page(brd, sector);
	if (page)
		return page;

	/*
	 * Must use NOIO because we don't want to recurse back into the
	 * block or filesystem layers from page reclaim.
	 */
	gfp_flags = GFP_NOIO | __GFP_ZERO | __GFP_HIGHMEM;
	page = alloc_page(gfp_flags);
	if (!page)
		return NULL;

	if (radix_tree_preload(GFP_NOIO)) {
		__free_page(page);
		return NULL;
	}

	spin_lock(&brd->brd_lock);
	idx = sector >> PAGE_SECTORS_SHIFT;
	page->index = idx;
	if (radix_tree_insert(&brd->brd_pages, idx, page)) {
		__free_page(page);
		page = radix_tree_lookup(&brd->brd_pages, idx);
		BUG_ON(!page);
		BUG_ON(page->index != idx);
	} else {
		brd->brd_nr_pages++;
	}
	spin_unlock(&brd->brd_lock);

	radix_tree_preload_end();

	return page;
}

/*
 * Free all backing store pages and radix tree. This must only be called when
 * there are no other users of the device.
 */
#define FREE_BATCH 16
static void brd_free_pages(struct brd_device *brd)
{
	unsigned long pos = 0;
	struct page *pages[FREE_BATCH];
	int nr_pages;

	do {
		int i;

		nr_pages = radix_tree_gang_lookup(&brd->brd_pages,
				(void **)pages, pos, FREE_BATCH);

		for (i = 0; i < nr_pages; i++) {
			void *ret;

			BUG_ON(pages[i]->index < pos);
			pos = pages[i]->index;
			ret = radix_tree_delete(&brd->brd_pages, pos);
			BUG_ON(!ret || ret != pages[i]);
			__free_page(pages[i]);
		}

		pos++;

		/*
		 * It takes 3.4 seconds to remove 80GiB ramdisk.
		 * So, we need cond_resched to avoid stalling the CPU.
		 */
		cond_resched();

		/*
		 * This assumes radix_tree_gang_lookup always returns as
		 * many pages as possible. If the radix-tree code changes,
		 * so will this have to.
		 */
	} while (nr_pages == FREE_BATCH);
}

/*
 * copy_to_brd_setup must be called before copy_to_brd. It may sleep.
 */
static int copy_to_brd_setup(struct brd_device *brd, sector_t sector, size_t n)
{
	unsigned int offset = (sector & (PAGE_SECTORS-1)) << SECTOR_SHIFT;
	size_t copy;

	copy = min_t(size_t, n, PAGE_SIZE - offset);
	if (!brd_insert_page(brd, sector))
		return -ENOSPC;
	if (copy < n) {
		sector += copy >> SECTOR_SHIFT;
		if (!brd_insert_page(brd, sector))
			return -ENOSPC;
	}
	return 0;
}

/*
 * Copy n bytes from src to the brd starting at sector. Does not sleep.
 */
static void copy_to_brd(struct brd_device *brd, const void *src,
			sector_t sector, size_t n)
{
	struct page *page;
	void *dst;
	unsigned int offset = (sector & (PAGE_SECTORS-1)) << SECTOR_SHIFT;
	size_t copy;

	copy = min_t(size_t, n, PAGE_SIZE - offset);
	page = brd_lookup_page(brd, sector);
	BUG_ON(!page);

	dst = kmap_atomic(page);
	memcpy(dst + offset, src, copy);
	kunmap_atomic(dst);

	if (copy < n) {
		src += copy;
		sector += copy >> SECTOR_SHIFT;
		copy = n - copy;
		page = brd_lookup_page(brd, sector);
		BUG_ON(!page);

		dst = kmap_atomic(page);
		memcpy(dst, src, copy);
		kunmap_atomic(dst);
	}
}

/*
 * Copy n bytes to dst from the brd starting at sector. Does not sleep.
 */
static void copy_from_brd(void *dst, struct brd_device *brd,
			sector_t sector, size_t n)
{
	struct page *page;
	void *src;
	unsigned int offset = (sector & (PAGE_SECTORS-1)) << SECTOR_SHIFT;
	size_t copy;

	copy = min_t(size_t, n, PAGE_SIZE - offset);
	page = brd_lookup_page(brd, sector);
	if (page) {
		src = kmap_atomic(page);
		memcpy(dst, src + offset, copy);
		kunmap_atomic(src);
	} else
		memset(dst, 0, copy);

	if (copy < n) {
		dst += copy;
		sector += copy >> SECTOR_SHIFT;
		copy = n - copy;
		page = brd_lookup_page(brd, sector);
		if (page) {
			src = kmap_atomic(page);
			memcpy(dst, src, copy);
			kunmap_atomic(src);
		} else
			memset(dst, 0, copy);
	}
}

/*
 * Process a single bvec of a bio.
 */
static int brd_do_bvec(struct brd_device *brd, struct page *page,
			unsigned int len, unsigned int off, unsigned int op,
			sector_t sector)
{
	void *mem;
	int err = 0;

	if (op_is_write(op)) {
		err = copy_to_brd_setup(brd, sector, len);
		if (err)
			goto out;
	}

	mem = kmap_atomic(page);
	if (!op_is_write(op)) {
		copy_from_brd(mem + off, brd, sector, len);
		flush_dcache_page(page);
	} else {
		flush_dcache_page(page);
		copy_to_brd(brd, mem + off, sector, len);
	}
	kunmap_atomic(mem);

out:
	return err;
}

static blk_qc_t brd_submit_bio(struct bio *bio)
{
	struct brd_device *brd = bio->bi_bdev->bd_disk->private_data;
	sector_t sector = bio->bi_iter.bi_sector;
	struct bio_vec bvec;
	struct bvec_iter iter;

	bio_for_each_segment(bvec, bio, iter) {
		unsigned int len = bvec.bv_len;
		int err;

		/* Don't support un-aligned buffer */
		WARN_ON_ONCE((bvec.bv_offset & (SECTOR_SIZE - 1)) ||
				(len & (SECTOR_SIZE - 1)));

		err = brd_do_bvec(brd, bvec.bv_page, len, bvec.bv_offset,
				  bio_op(bio), sector);
		if (err)
			goto io_error;
		sector += len >> SECTOR_SHIFT;
	}

	bio_endio(bio);
	return BLK_QC_T_NONE;
io_error:
	bio_io_error(bio);
	return BLK_QC_T_NONE;
}

static int brd_rw_page(struct block_device *bdev, sector_t sector,
		       struct page *page, unsigned int op)
{
	struct brd_device *brd = bdev->bd_disk->private_data;
	int err;

	if (PageTransHuge(page))
		return -ENOTSUPP;
	err = brd_do_bvec(brd, page, PAGE_SIZE, 0, op, sector);
	page_endio(page, op_is_write(op), err);
	return err;
}

static const struct block_device_operations brd_fops = {
	.owner =		THIS_MODULE,
	.submit_bio =		brd_submit_bio,
	.rw_page =		brd_rw_page,
};

/*
 * And now the modules code and kernel interface.
 */
static int rd_nr = CONFIG_BLK_DEV_RAM_COUNT;
module_param(rd_nr, int, 0444);
MODULE_PARM_DESC(rd_nr, "Maximum number of brd devices");

unsigned long rd_size = CONFIG_BLK_DEV_RAM_SIZE;
module_param(rd_size, ulong, 0444);
MODULE_PARM_DESC(rd_size, "Size of each RAM disk in kbytes.");

static int max_part = 1;
module_param(max_part, int, 0444);
MODULE_PARM_DESC(max_part, "Num Minors to reserve between devices");

MODULE_LICENSE("GPL");
MODULE_ALIAS_BLOCKDEV_MAJOR(RAMDISK_MAJOR);
MODULE_ALIAS("rd");

#ifndef MODULE
/* Legacy boot options - nonmodular */
static int __init ramdisk_size(char *str)
{
	rd_size = simple_strtol(str, NULL, 0);
	return 1;
}
__setup("ramdisk_size=", ramdisk_size);
#endif

/*
 * The device scheme is derived from loop.c. Keep them in synch where possible
 * (should share code eventually).
 */
static LIST_HEAD(brd_devices);
static DEFINE_MUTEX(brd_devices_mutex);
static struct dentry *brd_debugfs_dir;

static int brd_alloc(int i)
{
	struct brd_device *brd;
	struct gendisk *disk;
	char buf[DISK_NAME_LEN];

	brd = kzalloc(sizeof(*brd), GFP_KERNEL);
	if (!brd)
		return -ENOMEM;
	brd->brd_number		= i;
	spin_lock_init(&brd->brd_lock);
	INIT_RADIX_TREE(&brd->brd_pages, GFP_ATOMIC);

	snprintf(buf, DISK_NAME_LEN, "ram%d", i);
	if (!IS_ERR_OR_NULL(brd_debugfs_dir))
		debugfs_create_u64(buf, 0444, brd_debugfs_dir,
				&brd->brd_nr_pages);

	disk = brd->brd_disk = blk_alloc_disk(NUMA_NO_NODE);
	if (!disk)
		goto out_free_dev;

	disk->major		= RAMDISK_MAJOR;
	disk->first_minor	= i * max_part;
	disk->minors		= max_part;
	disk->fops		= &brd_fops;
	disk->private_data	= brd;
	disk->flags		= GENHD_FL_EXT_DEVT;
	strlcpy(disk->disk_name, buf, DISK_NAME_LEN);
	set_capacity(disk, rd_size * 2);
	
	/*
	 * This is so fdisk will align partitions on 4k, because of
	 * direct_access API needing 4k alignment, returning a PFN
	 * (This is only a problem on very small devices <= 4M,
	 *  otherwise fdisk will align on 1M. Regardless this call
	 *  is harmless)
	 */
	blk_queue_physical_block_size(disk->queue, PAGE_SIZE);

	/* Tell the block layer that this is not a rotational device */
	blk_queue_flag_set(QUEUE_FLAG_NONROT, disk->queue);
	blk_queue_flag_clear(QUEUE_FLAG_ADD_RANDOM, disk->queue);
	add_disk(disk);
	list_add_tail(&brd->brd_list, &brd_devices);

	return 0;

out_free_dev:
	kfree(brd);
	return -ENOMEM;
}

static void brd_probe(dev_t dev)
{
	int i = MINOR(dev) / max_part;
	struct brd_device *brd;

	mutex_lock(&brd_devices_mutex);
	list_for_each_entry(brd, &brd_devices, brd_list) {
		if (brd->brd_number == i)
			goto out_unlock;
	}

	brd_alloc(i);
out_unlock:
	mutex_unlock(&brd_devices_mutex);
}

static void brd_del_one(struct brd_device *brd)
{
	list_del(&brd->brd_list);
	del_gendisk(brd->brd_disk);
	blk_cleanup_disk(brd->brd_disk);
	brd_free_pages(brd);
	kfree(brd);
}

static inline void brd_check_and_reset_par(void)
{
	if (unlikely(!max_part))
		max_part = 1;

	/*
	 * make sure 'max_part' can be divided exactly by (1U << MINORBITS),
	 * otherwise, it is possiable to get same dev_t when adding partitions.
	 */
	if ((1U << MINORBITS) % max_part != 0)
		max_part = 1UL << fls(max_part);

	if (max_part > DISK_MAX_PARTS) {
		pr_info("brd: max_part can't be larger than %d, reset max_part = %d.\n",
			DISK_MAX_PARTS, DISK_MAX_PARTS);
		max_part = DISK_MAX_PARTS;
	}
}

static int __init brd_init(void)
{
	struct brd_device *brd, *next;
	int err, i;

	/*
	 * brd module now has a feature to instantiate underlying device
	 * structure on-demand, provided that there is an access dev node.
	 *
	 * (1) if rd_nr is specified, create that many upfront. else
	 *     it defaults to CONFIG_BLK_DEV_RAM_COUNT
	 * (2) User can further extend brd devices by create dev node themselves
	 *     and have kernel automatically instantiate actual device
	 *     on-demand. Example:
	 *		mknod /path/devnod_name b 1 X	# 1 is the rd major
	 *		fdisk -l /path/devnod_name
	 *	If (X / max_part) was not already created it will be created
	 *	dynamically.
	 */

	if (__register_blkdev(RAMDISK_MAJOR, "ramdisk", brd_probe))
		return -EIO;

	brd_check_and_reset_par();

	brd_debugfs_dir = debugfs_create_dir("ramdisk_pages", NULL);

	mutex_lock(&brd_devices_mutex);
	for (i = 0; i < rd_nr; i++) {
		err = brd_alloc(i);
		if (err)
			goto out_free;
	}

	mutex_unlock(&brd_devices_mutex);

	pr_info("brd: module loaded\n");
	return 0;

out_free:
	debugfs_remove_recursive(brd_debugfs_dir);

	list_for_each_entry_safe(brd, next, &brd_devices, brd_list)
		brd_del_one(brd);
	mutex_unlock(&brd_devices_mutex);
	unregister_blkdev(RAMDISK_MAJOR, "ramdisk");

	pr_info("brd: module NOT loaded !!!\n");
	return err;
}

static void __exit brd_exit(void)
{
	struct brd_device *brd, *next;

	debugfs_remove_recursive(brd_debugfs_dir);

	list_for_each_entry_safe(brd, next, &brd_devices, brd_list)
		brd_del_one(brd);

	unregister_blkdev(RAMDISK_MAJOR, "ramdisk");

	pr_info("brd: module unloaded\n");
}

module_init(brd_init);
module_exit(brd_exit);