652 lines · 15.0 KB · C
RawDownload
/* * 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>#include <linux/mutex.h>#include <linux/radix-tree.h>#include <linux/fs.h>#include <linux/slab.h> #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. */static DEFINE_MUTEX(brd_mutex);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.	 *	 * 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.	 */	gfp_flags = GFP_NOIO | __GFP_ZERO;#ifndef CONFIG_BLK_DEV_XIP	gfp_flags |= __GFP_HIGHMEM;#endif	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);	}	spin_unlock(&brd->brd_lock); 	radix_tree_preload_end(); 	return page;} 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);} /* * 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 16static 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;} 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;	}} /* * 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, 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);	if (rw == READ) {		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 void 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 (bio_end_sector(bio) > get_capacity(bdev->bd_disk))		goto out; 	if (unlikely(bio->bi_rw & REQ_DISCARD)) {		err = 0;		discard_from_brd(brd, sector, bio->bi_size);		goto out;	} 	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);} #ifdef CONFIG_BLK_DEV_XIPstatic int brd_direct_access(struct block_device *bdev, sector_t sector,			void **kaddr, unsigned long *pfn){	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;	*kaddr = page_address(page);	*pfn = page_to_pfn(page); 	return 0;}#endif static int brd_ioctl(struct block_device *bdev, fmode_t mode,			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.	 */	mutex_lock(&brd_mutex);	mutex_lock(&bdev->bd_mutex);	error = -EBUSY;	if (bdev->bd_openers <= 1) {		/*		 * Kill 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.		 */		kill_bdev(bdev);		brd_free_pages(brd);		error = 0;	}	mutex_unlock(&bdev->bd_mutex);	mutex_unlock(&brd_mutex); 	return error;} static const struct block_device_operations brd_fops = {	.owner =		THIS_MODULE,	.ioctl =		brd_ioctl,#ifdef CONFIG_BLK_DEV_XIP	.direct_access =	brd_direct_access,#endif}; /* * And now the modules code and kernel interface. */static int rd_nr;int rd_size = CONFIG_BLK_DEV_RAM_SIZE;static int max_part;static int part_shift;module_param(rd_nr, int, S_IRUGO);MODULE_PARM_DESC(rd_nr, "Maximum number of brd devices");module_param(rd_size, int, S_IRUGO);MODULE_PARM_DESC(rd_size, "Size of each RAM disk in kbytes.");module_param(max_part, int, S_IRUGO);MODULE_PARM_DESC(max_part, "Maximum number of partitions per RAM disk");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 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);	blk_queue_max_hw_sectors(brd->brd_queue, 1024);	blk_queue_bounce_limit(brd->brd_queue, BLK_BOUNCE_ANY); 	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); 	disk = brd->brd_disk = alloc_disk(1 << part_shift);	if (!disk)		goto out_free_queue;	disk->major		= RAMDISK_MAJOR;	disk->first_minor	= i << part_shift;	disk->fops		= &brd_fops;	disk->private_data	= brd;	disk->queue		= brd->brd_queue;	disk->flags |= GENHD_FL_SUPPRESS_PARTITION_INFO;	sprintf(disk->disk_name, "ram%d", i);	set_capacity(disk, rd_size * 2); 	return brd; out_free_queue:

Lines 1–500 of 652.