brd.c 14.9 KB
Newer Older
N
Nick Piggin 已提交
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17
/*
 * 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/module.h>
#include <linux/moduleparam.h>
#include <linux/major.h>
#include <linux/blkdev.h>
#include <linux/bio.h>
#include <linux/highmem.h>
18
#include <linux/mutex.h>
N
Nick Piggin 已提交
19 20
#include <linux/radix-tree.h>
#include <linux/buffer_head.h> /* invalidate_bh_lrus() */
21
#include <linux/slab.h>
N
Nick Piggin 已提交
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

#include <asm/uaccess.h>

#define SECTOR_SHIFT		9
#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 request_queue	*brd_queue;
	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;
};

/*
 * Look up and return a brd's page for a given sector.
 */
54
static DEFINE_MUTEX(brd_mutex);
N
Nick Piggin 已提交
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
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;
N
Nick Piggin 已提交
90
	gfp_t gfp_flags;
N
Nick Piggin 已提交
91 92 93 94 95 96 97 98

	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.
N
Nick Piggin 已提交
99 100 101 102 103
	 *
	 * Cannot support XIP and highmem, because our ->direct_access
	 * routine for XIP must return memory that is always addressable.
	 * If XIP was reworked to use pfns and kmap throughout, this
	 * restriction might be able to be lifted.
N
Nick Piggin 已提交
104
	 */
N
Nick Piggin 已提交
105 106 107 108
	gfp_flags = GFP_NOIO | __GFP_ZERO;
#ifndef CONFIG_BLK_DEV_XIP
	gfp_flags |= __GFP_HIGHMEM;
#endif
P
Petr Tesarik 已提交
109
	page = alloc_page(gfp_flags);
N
Nick Piggin 已提交
110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133
	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;
	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
		page->index = idx;
	spin_unlock(&brd->brd_lock);

	radix_tree_preload_end();

	return page;
}

N
Nick Piggin 已提交
134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155
static void brd_free_page(struct brd_device *brd, sector_t sector)
{
	struct page *page;
	pgoff_t idx;

	spin_lock(&brd->brd_lock);
	idx = sector >> PAGE_SECTORS_SHIFT;
	page = radix_tree_delete(&brd->brd_pages, idx);
	spin_unlock(&brd->brd_lock);
	if (page)
		__free_page(page);
}

static void brd_zero_page(struct brd_device *brd, sector_t sector)
{
	struct page *page;

	page = brd_lookup_page(brd, sector);
	if (page)
		clear_highpage(page);
}

N
Nick Piggin 已提交
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
/*
 * 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++;

		/*
		 * 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 -ENOMEM;
	if (copy < n) {
		sector += copy >> SECTOR_SHIFT;
		if (!brd_insert_page(brd, sector))
			return -ENOMEM;
	}
	return 0;
}

N
Nick Piggin 已提交
212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229
static void discard_from_brd(struct brd_device *brd,
			sector_t sector, size_t n)
{
	while (n >= PAGE_SIZE) {
		/*
		 * Don't want to actually discard pages here because
		 * re-allocating the pages can result in writeback
		 * deadlocks under heavy load.
		 */
		if (0)
			brd_free_page(brd, sector);
		else
			brd_zero_page(brd, sector);
		sector += PAGE_SIZE >> SECTOR_SHIFT;
		n -= PAGE_SIZE;
	}
}

N
Nick Piggin 已提交
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
/*
 * 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, KM_USER1);
	memcpy(dst + offset, src, copy);
	kunmap_atomic(dst, KM_USER1);

	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, KM_USER1);
		memcpy(dst, src, copy);
		kunmap_atomic(dst, KM_USER1);
	}
}

/*
 * 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, KM_USER1);
		memcpy(dst, src + offset, copy);
		kunmap_atomic(src, KM_USER1);
	} 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, KM_USER1);
			memcpy(dst, src, copy);
			kunmap_atomic(src, KM_USER1);
		} 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, int rw,
			sector_t sector)
{
	void *mem;
	int err = 0;

	if (rw != READ) {
		err = copy_to_brd_setup(brd, sector, len);
		if (err)
			goto out;
	}

	mem = kmap_atomic(page, KM_USER0);
	if (rw == READ) {
		copy_from_brd(mem + off, brd, sector, len);
		flush_dcache_page(page);
N
Nick Piggin 已提交
316 317
	} else {
		flush_dcache_page(page);
N
Nick Piggin 已提交
318
		copy_to_brd(brd, mem + off, sector, len);
N
Nick Piggin 已提交
319
	}
N
Nick Piggin 已提交
320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340
	kunmap_atomic(mem, KM_USER0);

out:
	return err;
}

static int brd_make_request(struct request_queue *q, struct bio *bio)
{
	struct block_device *bdev = bio->bi_bdev;
	struct brd_device *brd = bdev->bd_disk->private_data;
	int rw;
	struct bio_vec *bvec;
	sector_t sector;
	int i;
	int err = -EIO;

	sector = bio->bi_sector;
	if (sector + (bio->bi_size >> SECTOR_SHIFT) >
						get_capacity(bdev->bd_disk))
		goto out;

341
	if (unlikely(bio->bi_rw & REQ_DISCARD)) {
N
Nick Piggin 已提交
342 343 344 345 346
		err = 0;
		discard_from_brd(brd, sector, bio->bi_size);
		goto out;
	}

N
Nick Piggin 已提交
347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365
	rw = bio_rw(bio);
	if (rw == READA)
		rw = READ;

	bio_for_each_segment(bvec, bio, i) {
		unsigned int len = bvec->bv_len;
		err = brd_do_bvec(brd, bvec->bv_page, len,
					bvec->bv_offset, rw, sector);
		if (err)
			break;
		sector += len >> SECTOR_SHIFT;
	}

out:
	bio_endio(bio, err);

	return 0;
}

N
Nick Piggin 已提交
366
#ifdef CONFIG_BLK_DEV_XIP
N
Nick Piggin 已提交
367
static int brd_direct_access(struct block_device *bdev, sector_t sector,
368
			void **kaddr, unsigned long *pfn)
N
Nick Piggin 已提交
369 370 371 372 373 374 375 376 377 378 379 380 381
{
	struct brd_device *brd = bdev->bd_disk->private_data;
	struct page *page;

	if (!brd)
		return -ENODEV;
	if (sector & (PAGE_SECTORS-1))
		return -EINVAL;
	if (sector + PAGE_SECTORS > get_capacity(bdev->bd_disk))
		return -ERANGE;
	page = brd_insert_page(brd, sector);
	if (!page)
		return -ENOMEM;
382 383
	*kaddr = page_address(page);
	*pfn = page_to_pfn(page);
N
Nick Piggin 已提交
384 385 386 387 388

	return 0;
}
#endif

A
Al Viro 已提交
389
static int brd_ioctl(struct block_device *bdev, fmode_t mode,
N
Nick Piggin 已提交
390 391 392 393 394 395 396 397 398 399 400 401
			unsigned int cmd, unsigned long arg)
{
	int error;
	struct brd_device *brd = bdev->bd_disk->private_data;

	if (cmd != BLKFLSBUF)
		return -ENOTTY;

	/*
	 * ram device BLKFLSBUF has special semantics, we want to actually
	 * release and destroy the ramdisk data.
	 */
402
	mutex_lock(&brd_mutex);
N
Nick Piggin 已提交
403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418
	mutex_lock(&bdev->bd_mutex);
	error = -EBUSY;
	if (bdev->bd_openers <= 1) {
		/*
		 * Invalidate the cache first, so it isn't written
		 * back to the device.
		 *
		 * Another thread might instantiate more buffercache here,
		 * but there is not much we can do to close that race.
		 */
		invalidate_bh_lrus();
		truncate_inode_pages(bdev->bd_inode->i_mapping, 0);
		brd_free_pages(brd);
		error = 0;
	}
	mutex_unlock(&bdev->bd_mutex);
419
	mutex_unlock(&brd_mutex);
N
Nick Piggin 已提交
420 421 422 423

	return error;
}

424
static const struct block_device_operations brd_fops = {
N
Nick Piggin 已提交
425
	.owner =		THIS_MODULE,
426
	.ioctl =		brd_ioctl,
N
Nick Piggin 已提交
427 428 429
#ifdef CONFIG_BLK_DEV_XIP
	.direct_access =	brd_direct_access,
#endif
N
Nick Piggin 已提交
430 431 432 433 434 435 436
};

/*
 * And now the modules code and kernel interface.
 */
static int rd_nr;
int rd_size = CONFIG_BLK_DEV_RAM_SIZE;
437 438
static int max_part;
static int part_shift;
N
Nick Piggin 已提交
439 440 441 442
module_param(rd_nr, int, 0);
MODULE_PARM_DESC(rd_nr, "Maximum number of brd devices");
module_param(rd_size, int, 0);
MODULE_PARM_DESC(rd_size, "Size of each RAM disk in kbytes.");
443 444
module_param(max_part, int, 0);
MODULE_PARM_DESC(max_part, "Maximum number of partitions per RAM disk");
N
Nick Piggin 已提交
445 446
MODULE_LICENSE("GPL");
MODULE_ALIAS_BLOCKDEV_MAJOR(RAMDISK_MAJOR);
447
MODULE_ALIAS("rd");
N
Nick Piggin 已提交
448 449 450 451 452 453 454 455

#ifndef MODULE
/* Legacy boot options - nonmodular */
static int __init ramdisk_size(char *str)
{
	rd_size = simple_strtol(str, NULL, 0);
	return 1;
}
456
__setup("ramdisk_size=", ramdisk_size);
N
Nick Piggin 已提交
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
#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 brd_device *brd_alloc(int i)
{
	struct brd_device *brd;
	struct gendisk *disk;

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

	brd->brd_queue = blk_alloc_queue(GFP_KERNEL);
	if (!brd->brd_queue)
		goto out_free_dev;
	blk_queue_make_request(brd->brd_queue, brd_make_request);
482
	blk_queue_max_hw_sectors(brd->brd_queue, 1024);
N
Nick Piggin 已提交
483 484
	blk_queue_bounce_limit(brd->brd_queue, BLK_BOUNCE_ANY);

N
Nick Piggin 已提交
485 486 487 488 489
	brd->brd_queue->limits.discard_granularity = PAGE_SIZE;
	brd->brd_queue->limits.max_discard_sectors = UINT_MAX;
	brd->brd_queue->limits.discard_zeroes_data = 1;
	queue_flag_set_unlocked(QUEUE_FLAG_DISCARD, brd->brd_queue);

490
	disk = brd->brd_disk = alloc_disk(1 << part_shift);
N
Nick Piggin 已提交
491 492 493
	if (!disk)
		goto out_free_queue;
	disk->major		= RAMDISK_MAJOR;
494
	disk->first_minor	= i << part_shift;
N
Nick Piggin 已提交
495 496 497
	disk->fops		= &brd_fops;
	disk->private_data	= brd;
	disk->queue		= brd->brd_queue;
498
	disk->flags |= GENHD_FL_SUPPRESS_PARTITION_INFO;
N
Nick Piggin 已提交
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
	sprintf(disk->disk_name, "ram%d", i);
	set_capacity(disk, rd_size * 2);

	return brd;

out_free_queue:
	blk_cleanup_queue(brd->brd_queue);
out_free_dev:
	kfree(brd);
out:
	return NULL;
}

static void brd_free(struct brd_device *brd)
{
	put_disk(brd->brd_disk);
	blk_cleanup_queue(brd->brd_queue);
	brd_free_pages(brd);
	kfree(brd);
}

static struct brd_device *brd_init_one(int i)
{
	struct brd_device *brd;

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

	brd = brd_alloc(i);
	if (brd) {
		add_disk(brd->brd_disk);
		list_add_tail(&brd->brd_list, &brd_devices);
	}
out:
	return brd;
}

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

static struct kobject *brd_probe(dev_t dev, int *part, void *data)
{
	struct brd_device *brd;
	struct kobject *kobj;

	mutex_lock(&brd_devices_mutex);
	brd = brd_init_one(dev & MINORMASK);
	kobj = brd ? get_disk(brd->brd_disk) : ERR_PTR(-ENOMEM);
	mutex_unlock(&brd_devices_mutex);

	*part = 0;
	return kobj;
}

static int __init brd_init(void)
{
	int i, nr;
	unsigned long range;
	struct brd_device *brd, *next;

	/*
	 * brd module now has a feature to instantiate underlying device
	 * structure on-demand, provided that there is an access dev node.
	 * However, this will not work well with user space tool that doesn't
	 * know about such "feature".  In order to not break any existing
	 * tool, we do the following:
	 *
	 * (1) if rd_nr is specified, create that many upfront, and this
	 *     also becomes a hard limit.
	 * (2) if rd_nr is not specified, create 1 rd device on module
	 *     load, user can further extend brd device by create dev node
	 *     themselves and have kernel automatically instantiate actual
	 *     device on-demand.
	 */
579 580 581 582 583

	part_shift = 0;
	if (max_part > 0)
		part_shift = fls(max_part);

584 585 586
	if ((1UL << part_shift) > DISK_MAX_PARTS)
		return -EINVAL;

587
	if (rd_nr > 1UL << (MINORBITS - part_shift))
N
Nick Piggin 已提交
588 589 590 591 592 593 594
		return -EINVAL;

	if (rd_nr) {
		nr = rd_nr;
		range = rd_nr;
	} else {
		nr = CONFIG_BLK_DEV_RAM_COUNT;
595
		range = 1UL << (MINORBITS - part_shift);
N
Nick Piggin 已提交
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
	}

	if (register_blkdev(RAMDISK_MAJOR, "ramdisk"))
		return -EIO;

	for (i = 0; i < nr; i++) {
		brd = brd_alloc(i);
		if (!brd)
			goto out_free;
		list_add_tail(&brd->brd_list, &brd_devices);
	}

	/* point of no return */

	list_for_each_entry(brd, &brd_devices, brd_list)
		add_disk(brd->brd_disk);

	blk_register_region(MKDEV(RAMDISK_MAJOR, 0), range,
				  THIS_MODULE, brd_probe, NULL, NULL);

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

out_free:
	list_for_each_entry_safe(brd, next, &brd_devices, brd_list) {
		list_del(&brd->brd_list);
		brd_free(brd);
	}
624
	unregister_blkdev(RAMDISK_MAJOR, "ramdisk");
N
Nick Piggin 已提交
625 626 627 628 629 630 631 632 633

	return -ENOMEM;
}

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

634
	range = rd_nr ? rd_nr :  1UL << (MINORBITS - part_shift);
N
Nick Piggin 已提交
635 636 637 638 639 640 641 642 643 644 645

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

	blk_unregister_region(MKDEV(RAMDISK_MAJOR, 0), range);
	unregister_blkdev(RAMDISK_MAJOR, "ramdisk");
}

module_init(brd_init);
module_exit(brd_exit);