dm.c

linux 内核源代码

/*
 * Copyright (C) 2001, 2002 Sistina Software (UK) Limited.
 * Copyright (C) 2004-2006 Red Hat, Inc. All rights reserved.
 *
 * This file is released under the GPL.
 */

#include "dm.h"
#include "dm-bio-list.h"
#include "dm-uevent.h"

#include <linux/init.h>
#include <linux/module.h>
#include <linux/mutex.h>
#include <linux/moduleparam.h>
#include <linux/blkpg.h>
#include <linux/bio.h>
#include <linux/buffer_head.h>
#include <linux/mempool.h>
#include <linux/slab.h>
#include <linux/idr.h>
#include <linux/hdreg.h>
#include <linux/blktrace_api.h>
#include <linux/smp_lock.h>

#define DM_MSG_PREFIX "core"

static const char *_name = DM_NAME;

static unsigned int major = 0;
static unsigned int _major = 0;

static DEFINE_SPINLOCK(_minor_lock);
/*
 * One of these is allocated per bio.
 */
struct dm_io {
	struct mapped_device *md;
	int error;
	struct bio *bio;
	atomic_t io_count;
	unsigned long start_time;
};

/*
 * One of these is allocated per target within a bio.  Hopefully
 * this will be simplified out one day.
 */
struct dm_target_io {
	struct dm_io *io;
	struct dm_target *ti;
	union map_info info;
};

union map_info *dm_get_mapinfo(struct bio *bio)
{
	if (bio && bio->bi_private)
		return &((struct dm_target_io *)bio->bi_private)->info;
	return NULL;
}

#define MINOR_ALLOCED ((void *)-1)

/*
 * Bits for the md->flags field.
 */
#define DMF_BLOCK_IO 0
#define DMF_SUSPENDED 1
#define DMF_FROZEN 2
#define DMF_FREEING 3
#define DMF_DELETING 4
#define DMF_NOFLUSH_SUSPENDING 5

struct mapped_device {
	struct rw_semaphore io_lock;
	struct semaphore suspend_lock;
	spinlock_t pushback_lock;
	rwlock_t map_lock;
	atomic_t holders;
	atomic_t open_count;

	unsigned long flags;

	struct request_queue *queue;
	struct gendisk *disk;
	char name[16];

	void *interface_ptr;

	/*
	 * A list of ios that arrived while we were suspended.
	 */
	atomic_t pending;
	wait_queue_head_t wait;
	struct bio_list deferred;
	struct bio_list pushback;

	/*
	 * The current mapping.
	 */
	struct dm_table *map;

	/*
	 * io objects are allocated from here.
	 */
	mempool_t *io_pool;
	mempool_t *tio_pool;

	struct bio_set *bs;

	/*
	 * Event handling.
	 */
	atomic_t event_nr;
	wait_queue_head_t eventq;
	atomic_t uevent_seq;
	struct list_head uevent_list;
	spinlock_t uevent_lock; /* Protect access to uevent_list */

	/*
	 * freeze/thaw support require holding onto a super block
	 */
	struct super_block *frozen_sb;
	struct block_device *suspended_bdev;

	/* forced geometry settings */
	struct hd_geometry geometry;
};

#define MIN_IOS 256
static struct kmem_cache *_io_cache;
static struct kmem_cache *_tio_cache;

static int __init local_init(void)
{
	int r;

	/* allocate a slab for the dm_ios */
	_io_cache = KMEM_CACHE(dm_io, 0);
	if (!_io_cache)
		return -ENOMEM;

	/* allocate a slab for the target ios */
	_tio_cache = KMEM_CACHE(dm_target_io, 0);
	if (!_tio_cache) {
		kmem_cache_destroy(_io_cache);
		return -ENOMEM;
	}

	r = dm_uevent_init();
	if (r) {
		kmem_cache_destroy(_tio_cache);
		kmem_cache_destroy(_io_cache);
		return r;
	}

	_major = major;
	r = register_blkdev(_major, _name);
	if (r < 0) {
		kmem_cache_destroy(_tio_cache);
		kmem_cache_destroy(_io_cache);
		dm_uevent_exit();
		return r;
	}

	if (!_major)
		_major = r;

	return 0;
}

static void local_exit(void)
{
	kmem_cache_destroy(_tio_cache);
	kmem_cache_destroy(_io_cache);
	unregister_blkdev(_major, _name);
	dm_uevent_exit();

	_major = 0;

	DMINFO("cleaned up");
}

int (*_inits[])(void) __initdata = {
	local_init,
	dm_target_init,
	dm_linear_init,
	dm_stripe_init,
	dm_interface_init,
};

void (*_exits[])(void) = {
	local_exit,
	dm_target_exit,
	dm_linear_exit,
	dm_stripe_exit,
	dm_interface_exit,
};

static int __init dm_init(void)
{
	const int count = ARRAY_SIZE(_inits);

	int r, i;

	for (i = 0; i < count; i++) {
		r = _inits[i]();
		if (r)
			goto bad;
	}

	return 0;

      bad:
	while (i--)
		_exits[i]();

	return r;
}

static void __exit dm_exit(void)
{
	int i = ARRAY_SIZE(_exits);

	while (i--)
		_exits[i]();
}

/*
 * Block device functions
 */
static int dm_blk_open(struct inode *inode, struct file *file)
{
	struct mapped_device *md;

	spin_lock(&_minor_lock);

	md = inode->i_bdev->bd_disk->private_data;
	if (!md)
		goto out;

	if (test_bit(DMF_FREEING, &md->flags) ||
	    test_bit(DMF_DELETING, &md->flags)) {
		md = NULL;
		goto out;
	}

	dm_get(md);
	atomic_inc(&md->open_count);

out:
	spin_unlock(&_minor_lock);

	return md ? 0 : -ENXIO;
}

static int dm_blk_close(struct inode *inode, struct file *file)
{
	struct mapped_device *md;

	md = inode->i_bdev->bd_disk->private_data;
	atomic_dec(&md->open_count);
	dm_put(md);
	return 0;
}

int dm_open_count(struct mapped_device *md)
{
	return atomic_read(&md->open_count);
}

/*
 * Guarantees nothing is using the device before it's deleted.
 */
int dm_lock_for_deletion(struct mapped_device *md)
{
	int r = 0;

	spin_lock(&_minor_lock);

	if (dm_open_count(md))
		r = -EBUSY;
	else
		set_bit(DMF_DELETING, &md->flags);

	spin_unlock(&_minor_lock);

	return r;
}

static int dm_blk_getgeo(struct block_device *bdev, struct hd_geometry *geo)
{
	struct mapped_device *md = bdev->bd_disk->private_data;

	return dm_get_geometry(md, geo);
}

static int dm_blk_ioctl(struct inode *inode, struct file *file,
			unsigned int cmd, unsigned long arg)
{
	struct mapped_device *md;
	struct dm_table *map;
	struct dm_target *tgt;
	int r = -ENOTTY;

	/* We don't really need this lock, but we do need 'inode'. */
	unlock_kernel();

	md = inode->i_bdev->bd_disk->private_data;

	map = dm_get_table(md);

	if (!map || !dm_table_get_size(map))
		goto out;

	/* We only support devices that have a single target */
	if (dm_table_get_num_targets(map) != 1)
		goto out;

	tgt = dm_table_get_target(map, 0);

	if (dm_suspended(md)) {
		r = -EAGAIN;
		goto out;
	}

	if (tgt->type->ioctl)
		r = tgt->type->ioctl(tgt, inode, file, cmd, arg);

out:
	dm_table_put(map);

	lock_kernel();
	return r;
}

static struct dm_io *alloc_io(struct mapped_device *md)
{
	return mempool_alloc(md->io_pool, GFP_NOIO);
}

static void free_io(struct mapped_device *md, struct dm_io *io)
{
	mempool_free(io, md->io_pool);
}

static struct dm_target_io *alloc_tio(struct mapped_device *md)
{
	return mempool_alloc(md->tio_pool, GFP_NOIO);
}

static void free_tio(struct mapped_device *md, struct dm_target_io *tio)
{
	mempool_free(tio, md->tio_pool);
}

static void start_io_acct(struct dm_io *io)
{
	struct mapped_device *md = io->md;

	io->start_time = jiffies;

	preempt_disable();
	disk_round_stats(dm_disk(md));
	preempt_enable();
	dm_disk(md)->in_flight = atomic_inc_return(&md->pending);
}

static int end_io_acct(struct dm_io *io)
{
	struct mapped_device *md = io->md;
	struct bio *bio = io->bio;
	unsigned long duration = jiffies - io->start_time;
	int pending;
	int rw = bio_data_dir(bio);

	preempt_disable();
	disk_round_stats(dm_disk(md));
	preempt_enable();
	dm_disk(md)->in_flight = pending = atomic_dec_return(&md->pending);

	disk_stat_add(dm_disk(md), ticks[rw], duration);

	return !pending;
}

/*
 * Add the bio to the list of deferred io.
 */
static int queue_io(struct mapped_device *md, struct bio *bio)
{
	down_write(&md->io_lock);

	if (!test_bit(DMF_BLOCK_IO, &md->flags)) {
		up_write(&md->io_lock);
		return 1;
	}

	bio_list_add(&md->deferred, bio);

	up_write(&md->io_lock);
	return 0;		/* deferred successfully */
}

/*
 * Everyone (including functions in this file), should use this
 * function to access the md->map field, and make sure they call
 * dm_table_put() when finished.
 */
struct dm_table *dm_get_table(struct mapped_device *md)
{
	struct dm_table *t;

	read_lock(&md->map_lock);
	t = md->map;
	if (t)
		dm_table_get(t);
	read_unlock(&md->map_lock);

	return t;
}

/*
 * Get the geometry associated with a dm device
 */
int dm_get_geometry(struct mapped_device *md, struct hd_geometry *geo)
{
	*geo = md->geometry;

	return 0;
}

/*
 * Set the geometry of a device.
 */
int dm_set_geometry(struct mapped_device *md, struct hd_geometry *geo)
{
	sector_t sz = (sector_t)geo->cylinders * geo->heads * geo->sectors;

	if (geo->start > sz) {
		DMWARN("Start sector is beyond the geometry limits.");
		return -EINVAL;
	}

	md->geometry = *geo;

	return 0;
}

/*-----------------------------------------------------------------
 * CRUD START:
 *   A more elegant soln is in the works that uses the queue
 *   merge fn, unfortunately there are a couple of changes to
 *   the block layer that I want to make for this.  So in the
 *   interests of getting something for people to use I give
 *   you this clearly demarcated crap.
 *---------------------------------------------------------------*/

static int __noflush_suspending(struct mapped_device *md)
{
	return test_bit(DMF_NOFLUSH_SUSPENDING, &md->flags);
}

/*
 * Decrements the number of outstanding ios that a bio has been
 * cloned into, completing the original io if necc.
 */
static void dec_pending(struct dm_io *io, int error)
{
	unsigned long flags;

	/* Push-back supersedes any I/O errors */
	if (error && !(io->error > 0 && __noflush_suspending(io->md)))
		io->error = error;

	if (atomic_dec_and_test(&io->io_count)) {
		if (io->error == DM_ENDIO_REQUEUE) {
			/*
			 * Target requested pushing back the I/O.
			 * This must be handled before the sleeper on
			 * suspend queue merges the pushback list.
			 */
			spin_lock_irqsave(&io->md->pushback_lock, flags);
			if (__noflush_suspending(io->md))
				bio_list_add(&io->md->pushback, io->bio);
			else
				/* noflush suspend was interrupted. */
				io->error = -EIO;
			spin_unlock_irqrestore(&io->md->pushback_lock, flags);
		}

		if (end_io_acct(io))
			/* nudge anyone waiting on suspend queue */
			wake_up(&io->md->wait);

		if (io->error != DM_ENDIO_REQUEUE) {
			blk_add_trace_bio(io->md->queue, io->bio,
					  BLK_TA_COMPLETE);

			bio_endio(io->bio, io->error);
		}

		free_io(io->md, io);
	}
}

static void clone_endio(struct bio *bio, int error)
{
	int r = 0;
	struct dm_target_io *tio = bio->bi_private;
	struct mapped_device *md = tio->io->md;
	dm_endio_fn endio = tio->ti->type->end_io;

	if (!bio_flagged(bio, BIO_UPTODATE) && !error)
		error = -EIO;

	if (endio) {
		r = endio(tio->ti, bio, error, &tio->info);
		if (r < 0 || r == DM_ENDIO_REQUEUE)
			/*
			 * error and requeue request are handled
			 * in dec_pending().
			 */
			error = r;
		else if (r == DM_ENDIO_INCOMPLETE)
			/* The target will handle the io */
			return;
		else if (r) {
			DMWARN("unimplemented target endio return value: %d", r);
			BUG();
		}
	}

	dec_pending(tio->io, error);

	/*