raid5.c

来自「Linux Kernel 2.6.9 for OMAP1710」· C语言 代码 · 共 1,920 行 · 第 1/4 页

/*
 * raid5.c : Multiple Devices driver for Linux
 *	   Copyright (C) 1996, 1997 Ingo Molnar, Miguel de Icaza, Gadi Oxman
 *	   Copyright (C) 1999, 2000 Ingo Molnar
 *
 * RAID-5 management functions.
 *
 * This program is free software; you can redistribute it and/or modify
 * it under the terms of the GNU General Public License as published by
 * the Free Software Foundation; either version 2, or (at your option)
 * any later version.
 *
 * You should have received a copy of the GNU General Public License
 * (for example /usr/src/linux/COPYING); if not, write to the Free
 * Software Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
 */


#include <linux/config.h>
#include <linux/module.h>
#include <linux/slab.h>
#include <linux/raid/raid5.h>
#include <linux/highmem.h>
#include <asm/bitops.h>
#include <asm/atomic.h>

/*
 * Stripe cache
 */

#define NR_STRIPES		256
#define STRIPE_SIZE		PAGE_SIZE
#define STRIPE_SHIFT		(PAGE_SHIFT - 9)
#define STRIPE_SECTORS		(STRIPE_SIZE>>9)
#define	IO_THRESHOLD		1
#define HASH_PAGES		1
#define HASH_PAGES_ORDER	0
#define NR_HASH			(HASH_PAGES * PAGE_SIZE / sizeof(struct stripe_head *))
#define HASH_MASK		(NR_HASH - 1)

#define stripe_hash(conf, sect)	((conf)->stripe_hashtbl[((sect) >> STRIPE_SHIFT) & HASH_MASK])

/* bio's attached to a stripe+device for I/O are linked together in bi_sector
 * order without overlap.  There may be several bio's per stripe+device, and
 * a bio could span several devices.
 * When walking this list for a particular stripe+device, we must never proceed
 * beyond a bio that extends past this device, as the next bio might no longer
 * be valid.
 * This macro is used to determine the 'next' bio in the list, given the sector
 * of the current stripe+device
 */
#define r5_next_bio(bio, sect) ( ( bio->bi_sector + (bio->bi_size>>9) < sect + STRIPE_SECTORS) ? bio->bi_next : NULL)
/*
 * The following can be used to debug the driver
 */
#define RAID5_DEBUG	0
#define RAID5_PARANOIA	1
#if RAID5_PARANOIA && defined(CONFIG_SMP)
# define CHECK_DEVLOCK() if (!spin_is_locked(&conf->device_lock)) BUG()
#else
# define CHECK_DEVLOCK()
#endif

#define PRINTK(x...) ((void)(RAID5_DEBUG && printk(x)))
#if RAID5_DEBUG
#define inline
#define __inline__
#endif

static void print_raid5_conf (raid5_conf_t *conf);

static inline void __release_stripe(raid5_conf_t *conf, struct stripe_head *sh)
{
	if (atomic_dec_and_test(&sh->count)) {
		if (!list_empty(&sh->lru))
			BUG();
		if (atomic_read(&conf->active_stripes)==0)
			BUG();
		if (test_bit(STRIPE_HANDLE, &sh->state)) {
			if (test_bit(STRIPE_DELAYED, &sh->state))
				list_add_tail(&sh->lru, &conf->delayed_list);
			else
				list_add_tail(&sh->lru, &conf->handle_list);
			md_wakeup_thread(conf->mddev->thread);
		} else {
			if (test_and_clear_bit(STRIPE_PREREAD_ACTIVE, &sh->state)) {
				atomic_dec(&conf->preread_active_stripes);
				if (atomic_read(&conf->preread_active_stripes) < IO_THRESHOLD)
					md_wakeup_thread(conf->mddev->thread);
			}
			list_add_tail(&sh->lru, &conf->inactive_list);
			atomic_dec(&conf->active_stripes);
			if (!conf->inactive_blocked ||
			    atomic_read(&conf->active_stripes) < (NR_STRIPES*3/4))
				wake_up(&conf->wait_for_stripe);
		}
	}
}
static void release_stripe(struct stripe_head *sh)
{
	raid5_conf_t *conf = sh->raid_conf;
	unsigned long flags;
	
	spin_lock_irqsave(&conf->device_lock, flags);
	__release_stripe(conf, sh);
	spin_unlock_irqrestore(&conf->device_lock, flags);
}

static void remove_hash(struct stripe_head *sh)
{
	PRINTK("remove_hash(), stripe %llu\n", (unsigned long long)sh->sector);

	if (sh->hash_pprev) {
		if (sh->hash_next)
			sh->hash_next->hash_pprev = sh->hash_pprev;
		*sh->hash_pprev = sh->hash_next;
		sh->hash_pprev = NULL;
	}
}

static __inline__ void insert_hash(raid5_conf_t *conf, struct stripe_head *sh)
{
	struct stripe_head **shp = &stripe_hash(conf, sh->sector);

	PRINTK("insert_hash(), stripe %llu\n", (unsigned long long)sh->sector);

	CHECK_DEVLOCK();
	if ((sh->hash_next = *shp) != NULL)
		(*shp)->hash_pprev = &sh->hash_next;
	*shp = sh;
	sh->hash_pprev = shp;
}


/* find an idle stripe, make sure it is unhashed, and return it. */
static struct stripe_head *get_free_stripe(raid5_conf_t *conf)
{
	struct stripe_head *sh = NULL;
	struct list_head *first;

	CHECK_DEVLOCK();
	if (list_empty(&conf->inactive_list))
		goto out;
	first = conf->inactive_list.next;
	sh = list_entry(first, struct stripe_head, lru);
	list_del_init(first);
	remove_hash(sh);
	atomic_inc(&conf->active_stripes);
out:
	return sh;
}

static void shrink_buffers(struct stripe_head *sh, int num)
{
	struct page *p;
	int i;

	for (i=0; i<num ; i++) {
		p = sh->dev[i].page;
		if (!p)
			continue;
		sh->dev[i].page = NULL;
		page_cache_release(p);
	}
}

static int grow_buffers(struct stripe_head *sh, int num)
{
	int i;

	for (i=0; i<num; i++) {
		struct page *page;

		if (!(page = alloc_page(GFP_KERNEL))) {
			return 1;
		}
		sh->dev[i].page = page;
	}
	return 0;
}

static void raid5_build_block (struct stripe_head *sh, int i);

static inline void init_stripe(struct stripe_head *sh, sector_t sector, int pd_idx)
{
	raid5_conf_t *conf = sh->raid_conf;
	int disks = conf->raid_disks, i;

	if (atomic_read(&sh->count) != 0)
		BUG();
	if (test_bit(STRIPE_HANDLE, &sh->state))
		BUG();
	
	CHECK_DEVLOCK();
	PRINTK("init_stripe called, stripe %llu\n", 
		(unsigned long long)sh->sector);

	remove_hash(sh);
	
	sh->sector = sector;
	sh->pd_idx = pd_idx;
	sh->state = 0;

	for (i=disks; i--; ) {
		struct r5dev *dev = &sh->dev[i];

		if (dev->toread || dev->towrite || dev->written ||
		    test_bit(R5_LOCKED, &dev->flags)) {
			printk("sector=%llx i=%d %p %p %p %d\n",
			       (unsigned long long)sh->sector, i, dev->toread,
			       dev->towrite, dev->written,
			       test_bit(R5_LOCKED, &dev->flags));
			BUG();
		}
		dev->flags = 0;
		raid5_build_block(sh, i);
	}
	insert_hash(conf, sh);
}

static struct stripe_head *__find_stripe(raid5_conf_t *conf, sector_t sector)
{
	struct stripe_head *sh;

	CHECK_DEVLOCK();
	PRINTK("__find_stripe, sector %llu\n", (unsigned long long)sector);
	for (sh = stripe_hash(conf, sector); sh; sh = sh->hash_next)
		if (sh->sector == sector)
			return sh;
	PRINTK("__stripe %llu not in cache\n", (unsigned long long)sector);
	return NULL;
}

static void unplug_slaves(mddev_t *mddev);

static struct stripe_head *get_active_stripe(raid5_conf_t *conf, sector_t sector,
					     int pd_idx, int noblock) 
{
	struct stripe_head *sh;

	PRINTK("get_stripe, sector %llu\n", (unsigned long long)sector);

	spin_lock_irq(&conf->device_lock);

	do {
		sh = __find_stripe(conf, sector);
		if (!sh) {
			if (!conf->inactive_blocked)
				sh = get_free_stripe(conf);
			if (noblock && sh == NULL)
				break;
			if (!sh) {
				conf->inactive_blocked = 1;
				wait_event_lock_irq(conf->wait_for_stripe,
						    !list_empty(&conf->inactive_list) &&
						    (atomic_read(&conf->active_stripes) < (NR_STRIPES *3/4)
						     || !conf->inactive_blocked),
						    conf->device_lock,
						    unplug_slaves(conf->mddev);
					);
				conf->inactive_blocked = 0;
			} else
				init_stripe(sh, sector, pd_idx);
		} else {
			if (atomic_read(&sh->count)) {
				if (!list_empty(&sh->lru))
					BUG();
			} else {
				if (!test_bit(STRIPE_HANDLE, &sh->state))
					atomic_inc(&conf->active_stripes);
				if (list_empty(&sh->lru))
					BUG();
				list_del_init(&sh->lru);
			}
		}
	} while (sh == NULL);

	if (sh)
		atomic_inc(&sh->count);

	spin_unlock_irq(&conf->device_lock);
	return sh;
}

static int grow_stripes(raid5_conf_t *conf, int num)
{
	struct stripe_head *sh;
	kmem_cache_t *sc;
	int devs = conf->raid_disks;

	sprintf(conf->cache_name, "raid5/%s", mdname(conf->mddev));

	sc = kmem_cache_create(conf->cache_name, 
			       sizeof(struct stripe_head)+(devs-1)*sizeof(struct r5dev),
			       0, 0, NULL, NULL);
	if (!sc)
		return 1;
	conf->slab_cache = sc;
	while (num--) {
		sh = kmem_cache_alloc(sc, GFP_KERNEL);
		if (!sh)
			return 1;
		memset(sh, 0, sizeof(*sh) + (devs-1)*sizeof(struct r5dev));
		sh->raid_conf = conf;
		sh->lock = SPIN_LOCK_UNLOCKED;

		if (grow_buffers(sh, conf->raid_disks)) {
			shrink_buffers(sh, conf->raid_disks);
			kmem_cache_free(sc, sh);
			return 1;
		}
		/* we just created an active stripe so... */
		atomic_set(&sh->count, 1);
		atomic_inc(&conf->active_stripes);
		INIT_LIST_HEAD(&sh->lru);
		release_stripe(sh);
	}
	return 0;
}

static void shrink_stripes(raid5_conf_t *conf)
{
	struct stripe_head *sh;

	while (1) {
		spin_lock_irq(&conf->device_lock);
		sh = get_free_stripe(conf);
		spin_unlock_irq(&conf->device_lock);
		if (!sh)
			break;
		if (atomic_read(&sh->count))
			BUG();
		shrink_buffers(sh, conf->raid_disks);
		kmem_cache_free(conf->slab_cache, sh);
		atomic_dec(&conf->active_stripes);
	}
	kmem_cache_destroy(conf->slab_cache);
	conf->slab_cache = NULL;
}

static int raid5_end_read_request (struct bio * bi, unsigned int bytes_done,
				   int error)
{
 	struct stripe_head *sh = bi->bi_private;
	raid5_conf_t *conf = sh->raid_conf;
	int disks = conf->raid_disks, i;
	int uptodate = test_bit(BIO_UPTODATE, &bi->bi_flags);

	if (bi->bi_size)
		return 1;

	for (i=0 ; i<disks; i++)
		if (bi == &sh->dev[i].req)
			break;

	PRINTK("end_read_request %llu/%d, count: %d, uptodate %d.\n", 
		(unsigned long long)sh->sector, i, atomic_read(&sh->count), 
		uptodate);
	if (i == disks) {
		BUG();
		return 0;
	}

	if (uptodate) {
#if 0
		struct bio *bio;
		unsigned long flags;
		spin_lock_irqsave(&conf->device_lock, flags);
		/* we can return a buffer if we bypassed the cache or
		 * if the top buffer is not in highmem.  If there are
		 * multiple buffers, leave the extra work to
		 * handle_stripe
		 */
		buffer = sh->bh_read[i];
		if (buffer &&
		    (!PageHighMem(buffer->b_page)
		     || buffer->b_page == bh->b_page )
			) {
			sh->bh_read[i] = buffer->b_reqnext;
			buffer->b_reqnext = NULL;
		} else
			buffer = NULL;
		spin_unlock_irqrestore(&conf->device_lock, flags);
		if (sh->bh_page[i]==bh->b_page)
			set_buffer_uptodate(bh);
		if (buffer) {
			if (buffer->b_page != bh->b_page)
				memcpy(buffer->b_data, bh->b_data, bh->b_size);
			buffer->b_end_io(buffer, 1);
		}
#else
		set_bit(R5_UPTODATE, &sh->dev[i].flags);
#endif		
	} else {
		md_error(conf->mddev, conf->disks[i].rdev);
		clear_bit(R5_UPTODATE, &sh->dev[i].flags);
	}
	rdev_dec_pending(conf->disks[i].rdev, conf->mddev);
#if 0
	/* must restore b_page before unlocking buffer... */
	if (sh->bh_page[i] != bh->b_page) {
		bh->b_page = sh->bh_page[i];
		bh->b_data = page_address(bh->b_page);
		clear_buffer_uptodate(bh);
	}
#endif
	clear_bit(R5_LOCKED, &sh->dev[i].flags);
	set_bit(STRIPE_HANDLE, &sh->state);
	release_stripe(sh);
	return 0;
}

static int raid5_end_write_request (struct bio *bi, unsigned int bytes_done,
				    int error)
{
 	struct stripe_head *sh = bi->bi_private;
	raid5_conf_t *conf = sh->raid_conf;
	int disks = conf->raid_disks, i;
	unsigned long flags;
	int uptodate = test_bit(BIO_UPTODATE, &bi->bi_flags);

	if (bi->bi_size)
		return 1;

	for (i=0 ; i<disks; i++)
		if (bi == &sh->dev[i].req)
			break;

	PRINTK("end_write_request %llu/%d, count %d, uptodate: %d.\n", 
		(unsigned long long)sh->sector, i, atomic_read(&sh->count),
		uptodate);
	if (i == disks) {
		BUG();
		return 0;
	}

	spin_lock_irqsave(&conf->device_lock, flags);
	if (!uptodate)
		md_error(conf->mddev, conf->disks[i].rdev);

	rdev_dec_pending(conf->disks[i].rdev, conf->mddev);
	
	clear_bit(R5_LOCKED, &sh->dev[i].flags);
	set_bit(STRIPE_HANDLE, &sh->state);
	__release_stripe(conf, sh);
	spin_unlock_irqrestore(&conf->device_lock, flags);
	return 0;
}


static sector_t compute_blocknr(struct stripe_head *sh, int i);
	
static void raid5_build_block (struct stripe_head *sh, int i)
{
	struct r5dev *dev = &sh->dev[i];

	bio_init(&dev->req);
	dev->req.bi_io_vec = &dev->vec;
	dev->req.bi_vcnt++;
	dev->vec.bv_page = dev->page;
	dev->vec.bv_len = STRIPE_SIZE;
	dev->vec.bv_offset = 0;

	dev->req.bi_sector = sh->sector;
	dev->req.bi_private = sh;

	dev->flags = 0;
	if (i != sh->pd_idx)
		dev->sector = compute_blocknr(sh, i);
}

static void error(mddev_t *mddev, mdk_rdev_t *rdev)
{
	char b[BDEVNAME_SIZE];
	raid5_conf_t *conf = (raid5_conf_t *) mddev->private;
	PRINTK("raid5: error called\n");

	if (!rdev->faulty) {
		mddev->sb_dirty = 1;
		if (rdev->in_sync) {