loop.c

来自「linux 内核源代码」· C语言 代码 · 共 1,565 行 · 第 1/3 页

/*
 *  linux/drivers/block/loop.c
 *
 *  Written by Theodore Ts'o, 3/29/93
 *
 * Copyright 1993 by Theodore Ts'o.  Redistribution of this file is
 * permitted under the GNU General Public License.
 *
 * DES encryption plus some minor changes by Werner Almesberger, 30-MAY-1993
 * more DES encryption plus IDEA encryption by Nicholas J. Leon, June 20, 1996
 *
 * Modularized and updated for 1.1.16 kernel - Mitch Dsouza 28th May 1994
 * Adapted for 1.3.59 kernel - Andries Brouwer, 1 Feb 1996
 *
 * Fixed do_loop_request() re-entrancy - [e-mail] Mar 20, 1997
 *
 * Added devfs support - Richard Gooch <[e-mail]> 16-Jan-1998
 *
 * Handle sparse backing files correctly - Kenn Humborg, Jun 28, 1998
 *
 * Loadable modules and other fixes by AK, 1998
 *
 * Make real block number available to downstream transfer functions, enables
 * CBC (and relatives) mode encryption requiring unique IVs per data block.
 * Reed H. Petty, [e-mail]
 *
 * Maximum number of loop devices now dynamic via max_loop module parameter.
 * Russell Kroll <[e-mail]> 19990701
 *
 * Maximum number of loop devices when compiled-in now selectable by passing
 * max_loop=<1-255> to the kernel on boot.
 * Erik I. Bolsø, <[e-mail]>, Oct 31, 1999
 *
 * Completely rewrite request handling to be make_request_fn style and
 * non blocking, pushing work to a helper thread. Lots of fixes from
 * Al Viro too.
 * Jens Axboe <[e-mail]>, Nov 2000
 *
 * Support up to 256 loop devices
 * Heinz Mauelshagen <[e-mail]>, Feb 2002
 *
 * Support for falling back on the write file operation when the address space
 * operations prepare_write and/or commit_write are not available on the
 * backing filesystem.
 * Anton Altaparmakov, 16 Feb 2005
 *
 * Still To Fix:
 * - Advisory locking is ignored here.
 * - Should use an own CAP_* category instead of CAP_SYS_ADMIN
 *
 */

#include <linux/module.h>
#include <linux/moduleparam.h>
#include <linux/sched.h>
#include <linux/fs.h>
#include <linux/file.h>
#include <linux/stat.h>
#include <linux/errno.h>
#include <linux/major.h>
#include <linux/wait.h>
#include <linux/blkdev.h>
#include <linux/blkpg.h>
#include <linux/init.h>
#include <linux/smp_lock.h>
#include <linux/swap.h>
#include <linux/slab.h>
#include <linux/loop.h>
#include <linux/compat.h>
#include <linux/suspend.h>
#include <linux/freezer.h>
#include <linux/writeback.h>
#include <linux/buffer_head.h>		/* for invalidate_bdev() */
#include <linux/completion.h>
#include <linux/highmem.h>
#include <linux/gfp.h>
#include <linux/kthread.h>
#include <linux/splice.h>

#include <asm/uaccess.h>

static LIST_HEAD(loop_devices);
static DEFINE_MUTEX(loop_devices_mutex);

/*
 * Transfer functions
 */
static int transfer_none(struct loop_device *lo, int cmd,
			 struct page *raw_page, unsigned raw_off,
			 struct page *loop_page, unsigned loop_off,
			 int size, sector_t real_block)
{
	char *raw_buf = kmap_atomic(raw_page, KM_USER0) + raw_off;
	char *loop_buf = kmap_atomic(loop_page, KM_USER1) + loop_off;

	if (cmd == READ)
		memcpy(loop_buf, raw_buf, size);
	else
		memcpy(raw_buf, loop_buf, size);

	kunmap_atomic(raw_buf, KM_USER0);
	kunmap_atomic(loop_buf, KM_USER1);
	cond_resched();
	return 0;
}

static int transfer_xor(struct loop_device *lo, int cmd,
			struct page *raw_page, unsigned raw_off,
			struct page *loop_page, unsigned loop_off,
			int size, sector_t real_block)
{
	char *raw_buf = kmap_atomic(raw_page, KM_USER0) + raw_off;
	char *loop_buf = kmap_atomic(loop_page, KM_USER1) + loop_off;
	char *in, *out, *key;
	int i, keysize;

	if (cmd == READ) {
		in = raw_buf;
		out = loop_buf;
	} else {
		in = loop_buf;
		out = raw_buf;
	}

	key = lo->lo_encrypt_key;
	keysize = lo->lo_encrypt_key_size;
	for (i = 0; i < size; i++)
		*out++ = *in++ ^ key[(i & 511) % keysize];

	kunmap_atomic(raw_buf, KM_USER0);
	kunmap_atomic(loop_buf, KM_USER1);
	cond_resched();
	return 0;
}

static int xor_init(struct loop_device *lo, const struct loop_info64 *info)
{
	if (unlikely(info->lo_encrypt_key_size <= 0))
		return -EINVAL;
	return 0;
}

static struct loop_func_table none_funcs = {
	.number = LO_CRYPT_NONE,
	.transfer = transfer_none,
}; 	

static struct loop_func_table xor_funcs = {
	.number = LO_CRYPT_XOR,
	.transfer = transfer_xor,
	.init = xor_init
}; 	

/* xfer_funcs[0] is special - its release function is never called */
static struct loop_func_table *xfer_funcs[MAX_LO_CRYPT] = {
	&none_funcs,
	&xor_funcs
};

static loff_t get_loop_size(struct loop_device *lo, struct file *file)
{
	loff_t size, offset, loopsize;

	/* Compute loopsize in bytes */
	size = i_size_read(file->f_mapping->host);
	offset = lo->lo_offset;
	loopsize = size - offset;
	if (lo->lo_sizelimit > 0 && lo->lo_sizelimit < loopsize)
		loopsize = lo->lo_sizelimit;

	/*
	 * Unfortunately, if we want to do I/O on the device,
	 * the number of 512-byte sectors has to fit into a sector_t.
	 */
	return loopsize >> 9;
}

static int
figure_loop_size(struct loop_device *lo)
{
	loff_t size = get_loop_size(lo, lo->lo_backing_file);
	sector_t x = (sector_t)size;

	if (unlikely((loff_t)x != size))
		return -EFBIG;

	set_capacity(lo->lo_disk, x);
	return 0;					
}

static inline int
lo_do_transfer(struct loop_device *lo, int cmd,
	       struct page *rpage, unsigned roffs,
	       struct page *lpage, unsigned loffs,
	       int size, sector_t rblock)
{
	if (unlikely(!lo->transfer))
		return 0;

	return lo->transfer(lo, cmd, rpage, roffs, lpage, loffs, size, rblock);
}

/**
 * do_lo_send_aops - helper for writing data to a loop device
 *
 * This is the fast version for backing filesystems which implement the address
 * space operations write_begin and write_end.
 */
static int do_lo_send_aops(struct loop_device *lo, struct bio_vec *bvec,
		int bsize, loff_t pos, struct page *unused)
{
	struct file *file = lo->lo_backing_file; /* kudos to NFsckingS */
	struct address_space *mapping = file->f_mapping;
	pgoff_t index;
	unsigned offset, bv_offs;
	int len, ret;

	mutex_lock(&mapping->host->i_mutex);
	index = pos >> PAGE_CACHE_SHIFT;
	offset = pos & ((pgoff_t)PAGE_CACHE_SIZE - 1);
	bv_offs = bvec->bv_offset;
	len = bvec->bv_len;
	while (len > 0) {
		sector_t IV;
		unsigned size, copied;
		int transfer_result;
		struct page *page;
		void *fsdata;

		IV = ((sector_t)index << (PAGE_CACHE_SHIFT - 9))+(offset >> 9);
		size = PAGE_CACHE_SIZE - offset;
		if (size > len)
			size = len;

		ret = pagecache_write_begin(file, mapping, pos, size, 0,
							&page, &fsdata);
		if (ret)
			goto fail;

		transfer_result = lo_do_transfer(lo, WRITE, page, offset,
				bvec->bv_page, bv_offs, size, IV);
		copied = size;
		if (unlikely(transfer_result))
			copied = 0;

		ret = pagecache_write_end(file, mapping, pos, size, copied,
							page, fsdata);
		if (ret < 0 || ret != copied)
			goto fail;

		if (unlikely(transfer_result))
			goto fail;

		bv_offs += copied;
		len -= copied;
		offset = 0;
		index++;
		pos += copied;
	}
	ret = 0;
out:
	mutex_unlock(&mapping->host->i_mutex);
	return ret;
fail:
	ret = -1;
	goto out;
}

/**
 * __do_lo_send_write - helper for writing data to a loop device
 *
 * This helper just factors out common code between do_lo_send_direct_write()
 * and do_lo_send_write().
 */
static int __do_lo_send_write(struct file *file,
		u8 *buf, const int len, loff_t pos)
{
	ssize_t bw;
	mm_segment_t old_fs = get_fs();

	set_fs(get_ds());
	bw = file->f_op->write(file, buf, len, &pos);
	set_fs(old_fs);
	if (likely(bw == len))
		return 0;
	printk(KERN_ERR "loop: Write error at byte offset %llu, length %i.\n",
			(unsigned long long)pos, len);
	if (bw >= 0)
		bw = -EIO;
	return bw;
}

/**
 * do_lo_send_direct_write - helper for writing data to a loop device
 *
 * This is the fast, non-transforming version for backing filesystems which do
 * not implement the address space operations write_begin and write_end.
 * It uses the write file operation which should be present on all writeable
 * filesystems.
 */
static int do_lo_send_direct_write(struct loop_device *lo,
		struct bio_vec *bvec, int bsize, loff_t pos, struct page *page)
{
	ssize_t bw = __do_lo_send_write(lo->lo_backing_file,
			kmap(bvec->bv_page) + bvec->bv_offset,
			bvec->bv_len, pos);
	kunmap(bvec->bv_page);
	cond_resched();
	return bw;
}

/**
 * do_lo_send_write - helper for writing data to a loop device
 *
 * This is the slow, transforming version for filesystems which do not
 * implement the address space operations write_begin and write_end.  It
 * uses the write file operation which should be present on all writeable
 * filesystems.
 *
 * Using fops->write is slower than using aops->{prepare,commit}_write in the
 * transforming case because we need to double buffer the data as we cannot do
 * the transformations in place as we do not have direct access to the
 * destination pages of the backing file.
 */
static int do_lo_send_write(struct loop_device *lo, struct bio_vec *bvec,
		int bsize, loff_t pos, struct page *page)
{
	int ret = lo_do_transfer(lo, WRITE, page, 0, bvec->bv_page,
			bvec->bv_offset, bvec->bv_len, pos >> 9);
	if (likely(!ret))
		return __do_lo_send_write(lo->lo_backing_file,
				page_address(page), bvec->bv_len,
				pos);
	printk(KERN_ERR "loop: Transfer error at byte offset %llu, "
			"length %i.\n", (unsigned long long)pos, bvec->bv_len);
	if (ret > 0)
		ret = -EIO;
	return ret;
}

static int lo_send(struct loop_device *lo, struct bio *bio, int bsize,
		loff_t pos)
{
	int (*do_lo_send)(struct loop_device *, struct bio_vec *, int, loff_t,
			struct page *page);
	struct bio_vec *bvec;
	struct page *page = NULL;
	int i, ret = 0;

	do_lo_send = do_lo_send_aops;
	if (!(lo->lo_flags & LO_FLAGS_USE_AOPS)) {
		do_lo_send = do_lo_send_direct_write;
		if (lo->transfer != transfer_none) {
			page = alloc_page(GFP_NOIO | __GFP_HIGHMEM);
			if (unlikely(!page))
				goto fail;
			kmap(page);
			do_lo_send = do_lo_send_write;
		}
	}
	bio_for_each_segment(bvec, bio, i) {
		ret = do_lo_send(lo, bvec, bsize, pos, page);
		if (ret < 0)
			break;
		pos += bvec->bv_len;
	}
	if (page) {
		kunmap(page);
		__free_page(page);
	}
out:
	return ret;
fail:
	printk(KERN_ERR "loop: Failed to allocate temporary page for write.\n");
	ret = -ENOMEM;
	goto out;
}

struct lo_read_data {
	struct loop_device *lo;
	struct page *page;
	unsigned offset;
	int bsize;
};

static int
lo_splice_actor(struct pipe_inode_info *pipe, struct pipe_buffer *buf,
		struct splice_desc *sd)
{
	struct lo_read_data *p = sd->u.data;
	struct loop_device *lo = p->lo;
	struct page *page = buf->page;
	sector_t IV;
	size_t size;
	int ret;

	ret = buf->ops->confirm(pipe, buf);
	if (unlikely(ret))
		return ret;

	IV = ((sector_t) page->index << (PAGE_CACHE_SHIFT - 9)) +
							(buf->offset >> 9);
	size = sd->len;
	if (size > p->bsize)
		size = p->bsize;

	if (lo_do_transfer(lo, READ, page, buf->offset, p->page, p->offset, size, IV)) {
		printk(KERN_ERR "loop: transfer error block %ld\n",
		       page->index);
		size = -EINVAL;
	}

	flush_dcache_page(p->page);

	if (size > 0)
		p->offset += size;

	return size;
}

static int
lo_direct_splice_actor(struct pipe_inode_info *pipe, struct splice_desc *sd)
{
	return __splice_from_pipe(pipe, sd, lo_splice_actor);
}

static int
do_lo_receive(struct loop_device *lo,
	      struct bio_vec *bvec, int bsize, loff_t pos)
{
	struct lo_read_data cookie;
	struct splice_desc sd;
	struct file *file;
	long retval;

	cookie.lo = lo;
	cookie.page = bvec->bv_page;
	cookie.offset = bvec->bv_offset;
	cookie.bsize = bsize;

	sd.len = 0;
	sd.total_len = bvec->bv_len;
	sd.flags = 0;
	sd.pos = pos;
	sd.u.data = &cookie;

	file = lo->lo_backing_file;
	retval = splice_direct_to_actor(file, &sd, lo_direct_splice_actor);

	if (retval < 0)
		return retval;

	return 0;
}

static int
lo_receive(struct loop_device *lo, struct bio *bio, int bsize, loff_t pos)
{
	struct bio_vec *bvec;
	int i, ret = 0;

	bio_for_each_segment(bvec, bio, i) {
		ret = do_lo_receive(lo, bvec, bsize, pos);
		if (ret < 0)
			break;
		pos += bvec->bv_len;
	}
	return ret;
}

static int do_bio_filebacked(struct loop_device *lo, struct bio *bio)
{
	loff_t pos;
	int ret;

	pos = ((loff_t) bio->bi_sector << 9) + lo->lo_offset;
	if (bio_rw(bio) == WRITE)
		ret = lo_send(lo, bio, lo->lo_blocksize, pos);
	else
		ret = lo_receive(lo, bio, lo->lo_blocksize, pos);
	return ret;
}

/*
 * Add bio to back of pending list
 */
static void loop_add_bio(struct loop_device *lo, struct bio *bio)
{
	if (lo->lo_biotail) {
		lo->lo_biotail->bi_next = bio;
		lo->lo_biotail = bio;
	} else
		lo->lo_bio = lo->lo_biotail = bio;
}

/*
 * Grab first pending buffer
 */
static struct bio *loop_get_bio(struct loop_device *lo)
{
	struct bio *bio;

	if ((bio = lo->lo_bio)) {
		if (bio == lo->lo_biotail)
			lo->lo_biotail = NULL;
		lo->lo_bio = bio->bi_next;
		bio->bi_next = NULL;
	}

	return bio;
}

static int loop_make_request(struct request_queue *q, struct bio *old_bio)
{
	struct loop_device *lo = q->queuedata;
	int rw = bio_rw(old_bio);

	if (rw == READA)
		rw = READ;

	BUG_ON(!lo || (rw != READ && rw != WRITE));