bitmap.c

来自「linux 内核源代码」· C语言 代码 · 共 1,568 行 · 第 1/3 页

	struct page *page = NULL, *lastpage = NULL;
	int blocks;
	void *paddr;

	if (bitmap == NULL)
		return;
	if (time_before(jiffies, bitmap->daemon_lastrun + bitmap->daemon_sleep*HZ))
		return;
	bitmap->daemon_lastrun = jiffies;

	for (j = 0; j < bitmap->chunks; j++) {
		bitmap_counter_t *bmc;
		spin_lock_irqsave(&bitmap->lock, flags);
		if (!bitmap->filemap) {
			/* error or shutdown */
			spin_unlock_irqrestore(&bitmap->lock, flags);
			break;
		}

		page = filemap_get_page(bitmap, j);

		if (page != lastpage) {
			/* skip this page unless it's marked as needing cleaning */
			if (!test_page_attr(bitmap, page, BITMAP_PAGE_CLEAN)) {
				int need_write = test_page_attr(bitmap, page,
								BITMAP_PAGE_NEEDWRITE);
				if (need_write)
					clear_page_attr(bitmap, page, BITMAP_PAGE_NEEDWRITE);

				spin_unlock_irqrestore(&bitmap->lock, flags);
				if (need_write)
					write_page(bitmap, page, 0);
				continue;
			}

			/* grab the new page, sync and release the old */
			if (lastpage != NULL) {
				if (test_page_attr(bitmap, lastpage, BITMAP_PAGE_NEEDWRITE)) {
					clear_page_attr(bitmap, lastpage, BITMAP_PAGE_NEEDWRITE);
					spin_unlock_irqrestore(&bitmap->lock, flags);
					write_page(bitmap, lastpage, 0);
				} else {
					set_page_attr(bitmap, lastpage, BITMAP_PAGE_NEEDWRITE);
					spin_unlock_irqrestore(&bitmap->lock, flags);
				}
			} else
				spin_unlock_irqrestore(&bitmap->lock, flags);
			lastpage = page;
/*
			printk("bitmap clean at page %lu\n", j);
*/
			spin_lock_irqsave(&bitmap->lock, flags);
			clear_page_attr(bitmap, page, BITMAP_PAGE_CLEAN);
		}
		bmc = bitmap_get_counter(bitmap, j << CHUNK_BLOCK_SHIFT(bitmap),
					&blocks, 0);
		if (bmc) {
/*
  if (j < 100) printk("bitmap: j=%lu, *bmc = 0x%x\n", j, *bmc);
*/
			if (*bmc == 2) {
				*bmc=1; /* maybe clear the bit next time */
				set_page_attr(bitmap, page, BITMAP_PAGE_CLEAN);
			} else if (*bmc == 1) {
				/* we can clear the bit */
				*bmc = 0;
				bitmap_count_page(bitmap, j << CHUNK_BLOCK_SHIFT(bitmap),
						  -1);

				/* clear the bit */
				paddr = kmap_atomic(page, KM_USER0);
				if (bitmap->flags & BITMAP_HOSTENDIAN)
					clear_bit(file_page_offset(j), paddr);
				else
					ext2_clear_bit(file_page_offset(j), paddr);
				kunmap_atomic(paddr, KM_USER0);
			}
		}
		spin_unlock_irqrestore(&bitmap->lock, flags);
	}

	/* now sync the final page */
	if (lastpage != NULL) {
		spin_lock_irqsave(&bitmap->lock, flags);
		if (test_page_attr(bitmap, lastpage, BITMAP_PAGE_NEEDWRITE)) {
			clear_page_attr(bitmap, lastpage, BITMAP_PAGE_NEEDWRITE);
			spin_unlock_irqrestore(&bitmap->lock, flags);
			write_page(bitmap, lastpage, 0);
		} else {
			set_page_attr(bitmap, lastpage, BITMAP_PAGE_NEEDWRITE);
			spin_unlock_irqrestore(&bitmap->lock, flags);
		}
	}

}

static bitmap_counter_t *bitmap_get_counter(struct bitmap *bitmap,
					    sector_t offset, int *blocks,
					    int create)
{
	/* If 'create', we might release the lock and reclaim it.
	 * The lock must have been taken with interrupts enabled.
	 * If !create, we don't release the lock.
	 */
	sector_t chunk = offset >> CHUNK_BLOCK_SHIFT(bitmap);
	unsigned long page = chunk >> PAGE_COUNTER_SHIFT;
	unsigned long pageoff = (chunk & PAGE_COUNTER_MASK) << COUNTER_BYTE_SHIFT;
	sector_t csize;

	if (bitmap_checkpage(bitmap, page, create) < 0) {
		csize = ((sector_t)1) << (CHUNK_BLOCK_SHIFT(bitmap));
		*blocks = csize - (offset & (csize- 1));
		return NULL;
	}
	/* now locked ... */

	if (bitmap->bp[page].hijacked) { /* hijacked pointer */
		/* should we use the first or second counter field
		 * of the hijacked pointer? */
		int hi = (pageoff > PAGE_COUNTER_MASK);
		csize = ((sector_t)1) << (CHUNK_BLOCK_SHIFT(bitmap) +
					  PAGE_COUNTER_SHIFT - 1);
		*blocks = csize - (offset & (csize- 1));
		return  &((bitmap_counter_t *)
			  &bitmap->bp[page].map)[hi];
	} else { /* page is allocated */
		csize = ((sector_t)1) << (CHUNK_BLOCK_SHIFT(bitmap));
		*blocks = csize - (offset & (csize- 1));
		return (bitmap_counter_t *)
			&(bitmap->bp[page].map[pageoff]);
	}
}

int bitmap_startwrite(struct bitmap *bitmap, sector_t offset, unsigned long sectors, int behind)
{
	if (!bitmap) return 0;

	if (behind) {
		atomic_inc(&bitmap->behind_writes);
		PRINTK(KERN_DEBUG "inc write-behind count %d/%d\n",
		  atomic_read(&bitmap->behind_writes), bitmap->max_write_behind);
	}

	while (sectors) {
		int blocks;
		bitmap_counter_t *bmc;

		spin_lock_irq(&bitmap->lock);
		bmc = bitmap_get_counter(bitmap, offset, &blocks, 1);
		if (!bmc) {
			spin_unlock_irq(&bitmap->lock);
			return 0;
		}

		if (unlikely((*bmc & COUNTER_MAX) == COUNTER_MAX)) {
			DEFINE_WAIT(__wait);
			/* note that it is safe to do the prepare_to_wait
			 * after the test as long as we do it before dropping
			 * the spinlock.
			 */
			prepare_to_wait(&bitmap->overflow_wait, &__wait,
					TASK_UNINTERRUPTIBLE);
			spin_unlock_irq(&bitmap->lock);
			blk_unplug(bitmap->mddev->queue);
			schedule();
			finish_wait(&bitmap->overflow_wait, &__wait);
			continue;
		}

		switch(*bmc) {
		case 0:
			bitmap_file_set_bit(bitmap, offset);
			bitmap_count_page(bitmap,offset, 1);
			blk_plug_device(bitmap->mddev->queue);
			/* fall through */
		case 1:
			*bmc = 2;
		}

		(*bmc)++;

		spin_unlock_irq(&bitmap->lock);

		offset += blocks;
		if (sectors > blocks)
			sectors -= blocks;
		else sectors = 0;
	}
	return 0;
}

void bitmap_endwrite(struct bitmap *bitmap, sector_t offset, unsigned long sectors,
		     int success, int behind)
{
	if (!bitmap) return;
	if (behind) {
		atomic_dec(&bitmap->behind_writes);
		PRINTK(KERN_DEBUG "dec write-behind count %d/%d\n",
		  atomic_read(&bitmap->behind_writes), bitmap->max_write_behind);
	}

	while (sectors) {
		int blocks;
		unsigned long flags;
		bitmap_counter_t *bmc;

		spin_lock_irqsave(&bitmap->lock, flags);
		bmc = bitmap_get_counter(bitmap, offset, &blocks, 0);
		if (!bmc) {
			spin_unlock_irqrestore(&bitmap->lock, flags);
			return;
		}

		if (!success && ! (*bmc & NEEDED_MASK))
			*bmc |= NEEDED_MASK;

		if ((*bmc & COUNTER_MAX) == COUNTER_MAX)
			wake_up(&bitmap->overflow_wait);

		(*bmc)--;
		if (*bmc <= 2) {
			set_page_attr(bitmap,
				      filemap_get_page(bitmap, offset >> CHUNK_BLOCK_SHIFT(bitmap)),
				      BITMAP_PAGE_CLEAN);
		}
		spin_unlock_irqrestore(&bitmap->lock, flags);
		offset += blocks;
		if (sectors > blocks)
			sectors -= blocks;
		else sectors = 0;
	}
}

int bitmap_start_sync(struct bitmap *bitmap, sector_t offset, int *blocks,
			int degraded)
{
	bitmap_counter_t *bmc;
	int rv;
	if (bitmap == NULL) {/* FIXME or bitmap set as 'failed' */
		*blocks = 1024;
		return 1; /* always resync if no bitmap */
	}
	spin_lock_irq(&bitmap->lock);
	bmc = bitmap_get_counter(bitmap, offset, blocks, 0);
	rv = 0;
	if (bmc) {
		/* locked */
		if (RESYNC(*bmc))
			rv = 1;
		else if (NEEDED(*bmc)) {
			rv = 1;
			if (!degraded) { /* don't set/clear bits if degraded */
				*bmc |= RESYNC_MASK;
				*bmc &= ~NEEDED_MASK;
			}
		}
	}
	spin_unlock_irq(&bitmap->lock);
	return rv;
}

void bitmap_end_sync(struct bitmap *bitmap, sector_t offset, int *blocks, int aborted)
{
	bitmap_counter_t *bmc;
	unsigned long flags;
/*
	if (offset == 0) printk("bitmap_end_sync 0 (%d)\n", aborted);
*/	if (bitmap == NULL) {
		*blocks = 1024;
		return;
	}
	spin_lock_irqsave(&bitmap->lock, flags);
	bmc = bitmap_get_counter(bitmap, offset, blocks, 0);
	if (bmc == NULL)
		goto unlock;
	/* locked */
/*
	if (offset == 0) printk("bitmap_end sync found 0x%x, blocks %d\n", *bmc, *blocks);
*/
	if (RESYNC(*bmc)) {
		*bmc &= ~RESYNC_MASK;

		if (!NEEDED(*bmc) && aborted)
			*bmc |= NEEDED_MASK;
		else {
			if (*bmc <= 2) {
				set_page_attr(bitmap,
					      filemap_get_page(bitmap, offset >> CHUNK_BLOCK_SHIFT(bitmap)),
					      BITMAP_PAGE_CLEAN);
			}
		}
	}
 unlock:
	spin_unlock_irqrestore(&bitmap->lock, flags);
}

void bitmap_close_sync(struct bitmap *bitmap)
{
	/* Sync has finished, and any bitmap chunks that weren't synced
	 * properly have been aborted.  It remains to us to clear the
	 * RESYNC bit wherever it is still on
	 */
	sector_t sector = 0;
	int blocks;
	if (!bitmap) return;
	while (sector < bitmap->mddev->resync_max_sectors) {
		bitmap_end_sync(bitmap, sector, &blocks, 0);
/*
		if (sector < 500) printk("bitmap_close_sync: sec %llu blks %d\n",
					 (unsigned long long)sector, blocks);
*/		sector += blocks;
	}
}

static void bitmap_set_memory_bits(struct bitmap *bitmap, sector_t offset, int needed)
{
	/* For each chunk covered by any of these sectors, set the
	 * counter to 1 and set resync_needed.  They should all
	 * be 0 at this point
	 */

	int secs;
	bitmap_counter_t *bmc;
	spin_lock_irq(&bitmap->lock);
	bmc = bitmap_get_counter(bitmap, offset, &secs, 1);
	if (!bmc) {
		spin_unlock_irq(&bitmap->lock);
		return;
	}
	if (! *bmc) {
		struct page *page;
		*bmc = 1 | (needed?NEEDED_MASK:0);
		bitmap_count_page(bitmap, offset, 1);
		page = filemap_get_page(bitmap, offset >> CHUNK_BLOCK_SHIFT(bitmap));
		set_page_attr(bitmap, page, BITMAP_PAGE_CLEAN);
	}
	spin_unlock_irq(&bitmap->lock);

}

/* dirty the memory and file bits for bitmap chunks "s" to "e" */
void bitmap_dirty_bits(struct bitmap *bitmap, unsigned long s, unsigned long e)
{
	unsigned long chunk;

	for (chunk = s; chunk <= e; chunk++) {
		sector_t sec = chunk << CHUNK_BLOCK_SHIFT(bitmap);
		bitmap_set_memory_bits(bitmap, sec, 1);
		bitmap_file_set_bit(bitmap, sec);
	}
}

/*
 * flush out any pending updates
 */
void bitmap_flush(mddev_t *mddev)
{
	struct bitmap *bitmap = mddev->bitmap;
	int sleep;

	if (!bitmap) /* there was no bitmap */
		return;

	/* run the daemon_work three time to ensure everything is flushed
	 * that can be
	 */
	sleep = bitmap->daemon_sleep;
	bitmap->daemon_sleep = 0;
	bitmap_daemon_work(bitmap);
	bitmap_daemon_work(bitmap);
	bitmap_daemon_work(bitmap);
	bitmap->daemon_sleep = sleep;
	bitmap_update_sb(bitmap);
}

/*
 * free memory that was allocated
 */
static void bitmap_free(struct bitmap *bitmap)
{
	unsigned long k, pages;
	struct bitmap_page *bp;

	if (!bitmap) /* there was no bitmap */
		return;

	/* release the bitmap file and kill the daemon */
	bitmap_file_put(bitmap);

	bp = bitmap->bp;
	pages = bitmap->pages;

	/* free all allocated memory */

	if (bp) /* deallocate the page memory */
		for (k = 0; k < pages; k++)
			if (bp[k].map && !bp[k].hijacked)
				kfree(bp[k].map);
	kfree(bp);
	kfree(bitmap);
}
void bitmap_destroy(mddev_t *mddev)
{
	struct bitmap *bitmap = mddev->bitmap;

	if (!bitmap) /* there was no bitmap */
		return;

	mddev->bitmap = NULL; /* disconnect from the md device */
	if (mddev->thread)
		mddev->thread->timeout = MAX_SCHEDULE_TIMEOUT;

	bitmap_free(bitmap);
}

/*
 * initialize the bitmap structure
 * if this returns an error, bitmap_destroy must be called to do clean up
 */
int bitmap_create(mddev_t *mddev)
{
	struct bitmap *bitmap;
	unsigned long blocks = mddev->resync_max_sectors;
	unsigned long chunks;
	unsigned long pages;
	struct file *file = mddev->bitmap_file;
	int err;
	sector_t start;

	BUILD_BUG_ON(sizeof(bitmap_super_t) != 256);

	if (!file && !mddev->bitmap_offset) /* bitmap disabled, nothing to do */
		return 0;

	BUG_ON(file && mddev->bitmap_offset);

	bitmap = kzalloc(sizeof(*bitmap), GFP_KERNEL);
	if (!bitmap)
		return -ENOMEM;

	spin_lock_init(&bitmap->lock);
	atomic_set(&bitmap->pending_writes, 0);
	init_waitqueue_head(&bitmap->write_wait);
	init_waitqueue_head(&bitmap->overflow_wait);

	bitmap->mddev = mddev;

	bitmap->file = file;
	bitmap->offset = mddev->bitmap_offset;
	if (file) {
		get_file(file);
		do_sync_mapping_range(file->f_mapping, 0, LLONG_MAX,
				      SYNC_FILE_RANGE_WAIT_BEFORE |
				      SYNC_FILE_RANGE_WRITE |
				      SYNC_FILE_RANGE_WAIT_AFTER);
	}
	/* read superblock from bitmap file (this sets bitmap->chunksize) */
	err = bitmap_read_sb(bitmap);
	if (err)
		goto error;

	bitmap->chunkshift = ffz(~bitmap->chunksize);

	/* now that chunksize and chunkshift are set, we can use these macros */
 	chunks = (blocks + CHUNK_BLOCK_RATIO(bitmap) - 1) /
			CHUNK_BLOCK_RATIO(bitmap);
 	pages = (chunks + PAGE_COUNTER_RATIO - 1) / PAGE_COUNTER_RATIO;

	BUG_ON(!pages);

	bitmap->chunks = chunks;
	bitmap->pages = pages;
	bitmap->missing_pages = pages;
	bitmap->counter_bits = COUNTER_BITS;

	bitmap->syncchunk = ~0UL;

#ifdef INJECT_FATAL_FAULT_1
	bitmap->bp = NULL;
#else
	bitmap->bp = kzalloc(pages * sizeof(*bitmap->bp), GFP_KERNEL);
#endif
	err = -ENOMEM;
	if (!bitmap->bp)
		goto error;

	/* now that we have some pages available, initialize the in-memory
	 * bitmap from the on-disk bitmap */
	start = 0;
	if (mddev->degraded == 0
	    || bitmap->events_cleared == mddev->events)
		/* no need to keep dirty bits to optimise a re-add of a missing device */
		start = mddev->recovery_cp;
	err = bitmap_init_from_disk(bitmap, start);

	if (err)
		goto error;

	printk(KERN_INFO "created bitmap (%lu pages) for device %s\n",
		pages, bmname(bitmap));

	mddev->bitmap = bitmap;

	mddev->thread->timeout = bitmap->daemon_sleep * HZ;

	bitmap_update_sb(bitmap);

	return (bitmap->flags & BITMAP_WRITE_ERROR) ? -EIO : 0;

 error:
	bitmap_free(bitmap);
	return err;
}

/* the bitmap API -- for raid personalities */
EXPORT_SYMBOL(bitmap_startwrite);
EXPORT_SYMBOL(bitmap_endwrite);
EXPORT_SYMBOL(bitmap_start_sync);
EXPORT_SYMBOL(bitmap_end_sync);
EXPORT_SYMBOL(bitmap_unplug);
EXPORT_SYMBOL(bitmap_close_sync);