buffer.c

grow_dev_page(struct block_device *bdev, sector_t block,
		pgoff_t index, int size)
{
	struct inode *inode = bdev->bd_inode;
	struct page *page;
	struct buffer_head *bh;

	page = find_or_create_page(inode->i_mapping, index,
		(mapping_gfp_mask(inode->i_mapping) & ~__GFP_FS)|__GFP_MOVABLE);
	if (!page)
		return NULL;

	BUG_ON(!PageLocked(page));

	if (page_has_buffers(page)) {
		bh = page_buffers(page);
		if (bh->b_size == size) {
			init_page_buffers(page, bdev, block, size);
			return page;
		}
		if (!try_to_free_buffers(page))
			goto failed;
	}

	/*
	 * Allocate some buffers for this page
	 */
	bh = alloc_page_buffers(page, size, 0);
	if (!bh)
		goto failed;

	/*
	 * Link the page to the buffers and initialise them.  Take the
	 * lock to be atomic wrt __find_get_block(), which does not
	 * run under the page lock.
	 */
	spin_lock(&inode->i_mapping->private_lock);
	link_dev_buffers(page, bh);
	init_page_buffers(page, bdev, block, size);
	spin_unlock(&inode->i_mapping->private_lock);
	return page;

failed:
	BUG();
	unlock_page(page);
	page_cache_release(page);
	return NULL;
}

/*
 * Create buffers for the specified block device block's page.  If
 * that page was dirty, the buffers are set dirty also.
 */
static int
grow_buffers(struct block_device *bdev, sector_t block, int size)
{
	struct page *page;
	pgoff_t index;
	int sizebits;

	sizebits = -1;
	do {
		sizebits++;
	} while ((size << sizebits) < PAGE_SIZE);

	index = block >> sizebits;

	/*
	 * Check for a block which wants to lie outside our maximum possible
	 * pagecache index.  (this comparison is done using sector_t types).
	 */
	if (unlikely(index != block >> sizebits)) {
		char b[BDEVNAME_SIZE];

		printk(KERN_ERR "%s: requested out-of-range block %llu for "
			"device %s\n",
			__func__, (unsigned long long)block,
			bdevname(bdev, b));
		return -EIO;
	}
	block = index << sizebits;
	/* Create a page with the proper size buffers.. */
	page = grow_dev_page(bdev, block, index, size);
	if (!page)
		return 0;
	unlock_page(page);
	page_cache_release(page);
	return 1;
}

static struct buffer_head *
__getblk_slow(struct block_device *bdev, sector_t block, int size)
{
	/* Size must be multiple of hard sectorsize */
	if (unlikely(size & (bdev_logical_block_size(bdev)-1) ||
			(size < 512 || size > PAGE_SIZE))) {
		printk(KERN_ERR "getblk(): invalid block size %d requested\n",
					size);
		printk(KERN_ERR "logical block size: %d\n",
					bdev_logical_block_size(bdev));

		dump_stack();
		return NULL;
	}

	for (;;) {
		struct buffer_head * bh;
		int ret;

		bh = __find_get_block(bdev, block, size);
		if (bh)
			return bh;

		ret = grow_buffers(bdev, block, size);
		if (ret < 0)
			return NULL;
		if (ret == 0)
			free_more_memory();
	}
}

/*
 * The relationship between dirty buffers and dirty pages:
 *
 * Whenever a page has any dirty buffers, the page's dirty bit is set, and
 * the page is tagged dirty in its radix tree.
 *
 * At all times, the dirtiness of the buffers represents the dirtiness of
 * subsections of the page.  If the page has buffers, the page dirty bit is
 * merely a hint about the true dirty state.
 *
 * When a page is set dirty in its entirety, all its buffers are marked dirty
 * (if the page has buffers).
 *
 * When a buffer is marked dirty, its page is dirtied, but the page's other
 * buffers are not.
 *
 * Also.  When blockdev buffers are explicitly read with bread(), they
 * individually become uptodate.  But their backing page remains not
 * uptodate - even if all of its buffers are uptodate.  A subsequent
 * block_read_full_page() against that page will discover all the uptodate
 * buffers, will set the page uptodate and will perform no I/O.
 */

/**
 * mark_buffer_dirty - mark a buffer_head as needing writeout
 * @bh: the buffer_head to mark dirty
 *
 * mark_buffer_dirty() will set the dirty bit against the buffer, then set its
 * backing page dirty, then tag the page as dirty in its address_space's radix
 * tree and then attach the address_space's inode to its superblock's dirty
 * inode list.
 *
 * mark_buffer_dirty() is atomic.  It takes bh->b_page->mapping->private_lock,
 * mapping->tree_lock and the global inode_lock.
 */
void mark_buffer_dirty(struct buffer_head *bh)
{
	WARN_ON_ONCE(!buffer_uptodate(bh));

	/*
	 * Very *carefully* optimize the it-is-already-dirty case.
	 *
	 * Don't let the final "is it dirty" escape to before we
	 * perhaps modified the buffer.
	 */
	if (buffer_dirty(bh)) {
		smp_mb();
		if (buffer_dirty(bh))
			return;
	}

	if (!test_set_buffer_dirty(bh)) {
		struct page *page = bh->b_page;
		if (!TestSetPageDirty(page)) {
			struct address_space *mapping = page_mapping(page);
			if (mapping)
				__set_page_dirty(page, mapping, 0);
		}
	}
}
EXPORT_SYMBOL(mark_buffer_dirty);

/*
 * Decrement a buffer_head's reference count.  If all buffers against a page
 * have zero reference count, are clean and unlocked, and if the page is clean
 * and unlocked then try_to_free_buffers() may strip the buffers from the page
 * in preparation for freeing it (sometimes, rarely, buffers are removed from
 * a page but it ends up not being freed, and buffers may later be reattached).
 */
void __brelse(struct buffer_head * buf)
{
	if (atomic_read(&buf->b_count)) {
		put_bh(buf);
		return;
	}
	WARN(1, KERN_ERR "VFS: brelse: Trying to free free buffer\n");
}
EXPORT_SYMBOL(__brelse);

/*
 * bforget() is like brelse(), except it discards any
 * potentially dirty data.
 */
void __bforget(struct buffer_head *bh)
{
	clear_buffer_dirty(bh);
	if (bh->b_assoc_map) {
		struct address_space *buffer_mapping = bh->b_page->mapping;

		spin_lock(&buffer_mapping->private_lock);
		list_del_init(&bh->b_assoc_buffers);
		bh->b_assoc_map = NULL;
		spin_unlock(&buffer_mapping->private_lock);
	}
	__brelse(bh);
}
EXPORT_SYMBOL(__bforget);

static struct buffer_head *__bread_slow(struct buffer_head *bh)
{
	lock_buffer(bh);
	if (buffer_uptodate(bh)) {
		unlock_buffer(bh);
		return bh;
	} else {
		get_bh(bh);
		bh->b_end_io = end_buffer_read_sync;
		submit_bh(READ, bh);
		wait_on_buffer(bh);
		if (buffer_uptodate(bh))
			return bh;
	}
	brelse(bh);
	return NULL;
}

/*
 * Per-cpu buffer LRU implementation.  To reduce the cost of __find_get_block().
 * The bhs[] array is sorted - newest buffer is at bhs[0].  Buffers have their
 * refcount elevated by one when they're in an LRU.  A buffer can only appear
 * once in a particular CPU's LRU.  A single buffer can be present in multiple
 * CPU's LRUs at the same time.
 *
 * This is a transparent caching front-end to sb_bread(), sb_getblk() and
 * sb_find_get_block().
 *
 * The LRUs themselves only need locking against invalidate_bh_lrus.  We use
 * a local interrupt disable for that.
 */

#define BH_LRU_SIZE	8

struct bh_lru {
	struct buffer_head *bhs[BH_LRU_SIZE];
};

static DEFINE_PER_CPU(struct bh_lru, bh_lrus) = {{ NULL }};

#ifdef CONFIG_SMP
#define bh_lru_lock()	local_irq_disable()
#define bh_lru_unlock()	local_irq_enable()
#else
#define bh_lru_lock()	preempt_disable()
#define bh_lru_unlock()	preempt_enable()
#endif

static inline void check_irqs_on(void)
{
#ifdef irqs_disabled
	BUG_ON(irqs_disabled());
#endif
}

/*
 * The LRU management algorithm is dopey-but-simple.  Sorry.
 */
static void bh_lru_install(struct buffer_head *bh)
{
	struct buffer_head *evictee = NULL;
	struct bh_lru *lru;

	check_irqs_on();
	bh_lru_lock();
	lru = &__get_cpu_var(bh_lrus);
	if (lru->bhs[0] != bh) {
		struct buffer_head *bhs[BH_LRU_SIZE];
		int in;
		int out = 0;

		get_bh(bh);
		bhs[out++] = bh;
		for (in = 0; in < BH_LRU_SIZE; in++) {
			struct buffer_head *bh2 = lru->bhs[in];

			if (bh2 == bh) {
				__brelse(bh2);
			} else {
				if (out >= BH_LRU_SIZE) {
					BUG_ON(evictee != NULL);
					evictee = bh2;
				} else {
					bhs[out++] = bh2;
				}
			}
		}
		while (out < BH_LRU_SIZE)
			bhs[out++] = NULL;
		memcpy(lru->bhs, bhs, sizeof(bhs));
	}
	bh_lru_unlock();

	if (evictee)
		__brelse(evictee);
}

/*
 * Look up the bh in this cpu's LRU.  If it's there, move it to the head.
 */
static struct buffer_head *
lookup_bh_lru(struct block_device *bdev, sector_t block, unsigned size)
{
	struct buffer_head *ret = NULL;
	struct bh_lru *lru;
	unsigned int i;

	check_irqs_on();
	bh_lru_lock();
	lru = &__get_cpu_var(bh_lrus);
	for (i = 0; i < BH_LRU_SIZE; i++) {
		struct buffer_head *bh = lru->bhs[i];

		if (bh && bh->b_bdev == bdev &&
				bh->b_blocknr == block && bh->b_size == size) {
			if (i) {
				while (i) {
					lru->bhs[i] = lru->bhs[i - 1];
					i--;
				}
				lru->bhs[0] = bh;
			}
			get_bh(bh);
			ret = bh;
			break;
		}
	}
	bh_lru_unlock();
	return ret;
}

/*
 * Perform a pagecache lookup for the matching buffer.  If it's there, refresh
 * it in the LRU and mark it as accessed.  If it is not present then return
 * NULL
 */
struct buffer_head *
__find_get_block(struct block_device *bdev, sector_t block, unsigned size)
{
	struct buffer_head *bh = lookup_bh_lru(bdev, block, size);

	if (bh == NULL) {
		bh = __find_get_block_slow(bdev, block);
		if (bh)
			bh_lru_install(bh);
	}
	if (bh)
		touch_buffer(bh);
	return bh;
}
EXPORT_SYMBOL(__find_get_block);

/*
 * __getblk will locate (and, if necessary, create) the buffer_head
 * which corresponds to the passed block_device, block and size. The
 * returned buffer has its reference count incremented.
 *
 * __getblk() cannot fail - it just keeps trying.  If you pass it an
 * illegal block number, __getblk() will happily return a buffer_head
 * which represents the non-existent block.  Very weird.
 *
 * __getblk() will lock up the machine if grow_dev_page's try_to_free_buffers()
 * attempt is failing.  FIXME, perhaps?
 */
struct buffer_head *
__getblk(struct block_device *bdev, sector_t block, unsigned size)
{
	struct buffer_head *bh = __find_get_block(bdev, block, size);

	might_sleep();
	if (bh == NULL)
		bh = __getblk_slow(bdev, block, size);
	return bh;
}
EXPORT_SYMBOL(__getblk);

/*
 * Do async read-ahead on a buffer..
 */
void __breadahead(struct block_device *bdev, sector_t block, unsigned size)
{
	struct buffer_head *bh = __getblk(bdev, block, size);
	if (likely(bh)) {
		ll_rw_block(READA, 1, &bh);
		brelse(bh);
	}
}
EXPORT_SYMBOL(__breadahead);

/**
 *  __bread() - reads a specified block and returns the bh
 *  @bdev: the block_device to read from
 *  @block: number of block
 *  @size: size (in bytes) to read
 * 
 *  Reads a specified block, and returns buffer head that contains it.
 *  It returns NULL if the block was unreadable.
 */
struct buffer_head *
__bread(struct block_device *bdev, sector_t block, unsigned size)
{
	struct buffer_head *bh = __getblk(bdev, block, size);

	if (likely(bh) && !buffer_uptodate(bh))
		bh = __bread_slow(bh);
	return bh;
}
EXPORT_SYMBOL(__bread);

/*
 * invalidate_bh_lrus() is called rarely - but not only at unmount.
 * This doesn't race because it runs in each cpu either in irq
 * or with preempt disabled.
 */
static void invalidate_bh_lru(void *arg)
{
	struct bh_lru *b = &get_cpu_var(bh_lrus);
	int i;

	for (i = 0; i < BH_LRU_SIZE; i++) {
		brelse(b->bhs[i]);
		b->bhs[i] = NULL;
	}
	put_cpu_var(bh_lrus);
}
	
void invalidate_bh_lrus(void)
{
	on_each_cpu(invalidate_bh_lru, NULL, 1);
}
EXPORT_SYMBOL_GPL(invalidate_bh_lrus);

void set_bh_page(struct buffer_head *bh,
		struct page *page, unsigned long offset)
{
	bh->b_page = page;
	BUG_ON(offset >= PAGE_SIZE);
	if (PageHighMem(page))
		/*
		 * This catches illegal uses and preserves the offset:
		 */
		bh->b_data = (char *)(0 + offset);
	else
		bh->b_data = page_address(page) + offset;
}
EXPORT_SYMBOL(set_bh_page);

/*
 * Called when truncating a buffer on a page completely.
 */
static void discard_buffer(struct buffer_head * bh)
{
	lock_buffer(bh);
	clear_buffer_dirty(bh);
	bh->b_bdev = NULL;
	clear_buffer_mapped(bh);
	clear_buffer_req(bh);
	clear_buffer_new(bh);
	clear_buffer_delay(bh);
	clear_buffer_unwritten(bh);
	unlock_buffer(bh);
}

/**
 * block_invalidatepage - invalidate part of all of a buffer-backed page
 *
 * @page: the page which is affected
 * @offset: the index of the truncation point
 *
 * block_invalidatepage() is called when all or part of the page has become
 * invalidatedby a truncate operation.
 *
 * block_invalidatepage() does not have to release all buffers, but it must
 * ensure that no dirty buffer is left outside @offset and that no I/O
 * is underway against any of the blocks which are outside the truncation
 * point.  Because the caller is about to free (and possibly reuse) those
 * blocks on-disk.
 */
void block_invalidatepage(struct page *page, unsigned long offset)
{
	struct buffer_head *head, *bh, *next;
	unsigned int curr_off = 0;

	BUG_ON(!PageLocked(page));
	if (!page_has_buffers(page))
		goto out;

	head = page_buffers(page);
	bh = head;
	do {
		unsigned int next_off = curr_off + bh->b_size;
		next = bh->b_this_page;

		/*
		 * is this block fully invalidated?
		 */
		if (offset <= curr_off)
			discard_buffer(bh);
		curr_off = next_off;
		bh = next;
	} while (bh != head);

	/*
	 * We release buffers only if the entire page is being invalidated.
	 * The get_block cached value has been unconditionally invalidated,
	 * so real IO is not possible anymore.
	 */
	if (offset == 0)
		try_to_release_page(page, 0);
out:
	return;
}
EXPORT_SYMBOL(block_invalidatepage);

/*
 * We attach and possibly dirty the buffers atomically wrt
 * __set_page_dirty_buffers() via private_lock.  try_to_free_buffers
 * is already excluded via the page lock.
 */
void create_empty_buffers(struct page *page,
			unsigned long blocksize, unsigned long b_state)
{
	struct buffer_head *bh, *head, *tail;

	head = alloc_page_buffers(page, blocksize, 1);
	bh = head;
	do {
		bh->b_state |= b_state;
		tail = bh;
		bh = bh->b_this_page;
	} while (bh);
	tail->b_this_page = head;

	spin_lock(&page->mapping->private_lock);
	if (PageUptodate(page) || PageDirty(page)) {
		bh = head;
		do {
			if (PageDirty(page))
				set_buffer_dirty(bh);
			if (PageUptodate(page))
				set_buffer_uptodate(bh);
			bh = bh->b_this_page;
		} while (bh != head);
	}
	attach_page_buffers(page, head);
	spin_unlock(&page->mapping->private_lock);
}
EXPORT_SYMBOL(create_empty_buffers);

/*
 * We are taking a block for data and we don't want any output from any
 * buffer-cache aliases starting from return from that function and
 * until the moment when something will explicitly mark the buffer
 * dirty (hopefully that will not happen until we will free that block ;-)
 * We don't even need to mark it not-uptodate - nobody can expect
 * anything from a newly allocated buffer anyway. We used to used
 * unmap_buffer() for such invalidation, but that was wrong. We definitely
 * don't want to mark the alias unmapped, for example - it would confuse
 * anyone who might pick it with bread() afterwards...
 *
 * Also..  Note that bforget() doesn't lock the buffer.  So there can
 * be writeout I/O going on against recently-freed buffers.  We don't
 * wait on that I/O in bforget() - it's more efficient to wait on the I/O
 * only if we really need to.  That happens here.
 */
void unmap_underlying_metadata(struct block_device *bdev, sector_t block)
{
	struct buffer_head *old_bh;

	might_sleep();

	old_bh = __find_get_block_slow(bdev, block);
	if (old_bh) {
		clear_buffer_dirty(old_bh);
		wait_on_buffer(old_bh);
		clear_buffer_req(old_bh);
		__brelse(old_bh);
	}
}
EXPORT_SYMBOL(unmap_underlying_metadata);

/*
 * NOTE! All mapped/uptodate combinations are valid:
 *
 *	Mapped	Uptodate	Meaning
 *
 *	No	No		"unknown" - must do get_block()
 *	No	Yes		"hole" - zero-filled
 *	Yes	No		"allocated" - allocated on disk, not read in
 *	Yes	Yes		"valid" - allocated and up-to-date in memory.
 *
 * "Dirty" is valid only with the last case (mapped+uptodate).
 */

/*
 * While block_write_full_page is writing back the dirty buffers under
 * the page lock, whoever dirtied the buffers may decide to clean them
 * again at any time.  We handle that by only looking at the buffer
 * state inside lock_buffer().
 *
 * If block_write_full_page() is called for regular writeback
 * (wbc->sync_mode == WB_SYNC_NONE) then it will redirty a page which has a
 * locked buffer.   This only can happen if someone has written the buffer
 * directly, with submit_bh().  At the address_space level PageWriteback
 * prevents this contention from occurring.
 *
 * If block_write_full_page() is called with wbc->sync_mode ==
 * WB_SYNC_ALL, the writes are posted using WRITE_SYNC_PLUG; this
 * causes the writes to be flagged as synchronous writes, but the
 * block device queue will NOT be unplugged, since usually many pages
 * will be pushed to the out before the higher-level caller actually
 * waits for the writes to be completed.  The various wait functions,
 * such as wait_on_writeback_range() will ultimately call sync_page()
 * which will ultimately call blk_run_backing_dev(), which will end up
 * unplugging the device queue.
 */
static int __block_write_full_page(struct inode *inode, struct page *page,
			get_block_t *get_block, struct writeback_control *wbc,
			bh_end_io_t *handler)
{
	int err;
	sector_t block;
	sector_t last_block;
	struct buffer_head *bh, *head;
	const unsigned blocksize = 1 << inode->i_blkbits;
	int nr_underway = 0;
	int write_op = (wbc->sync_mode == WB_SYNC_ALL ?
			WRITE_SYNC_PLUG : WRITE);

	BUG_ON(!PageLocked(page));

	last_block = (i_size_read(inode) - 1) >> inode->i_blkbits;

	if (!page_has_buffers(page)) {
		create_empty_buffers(page, blocksize,
					(1 << BH_Dirty)|(1 << BH_Uptodate));
	}

	/*
	 * Be very careful.  We have no exclusion from __set_page_dirty_buffers
	 * here, and the (potentially unmapped) buffers may become dirty at
	 * any time.  If a buffer becomes dirty here after we've inspected it
	 * then we just miss that fact, and the page stays dirty.
	 *
	 * Buffers outside i_size may be dirtied by __set_page_dirty_buffers;
	 * handle that here by just cleaning them.
	 */

	block = (sector_t)page->index << (PAGE_CACHE_SHIFT - inode->i_blkbits);
	head = page_buffers(page);
	bh = head;

	/*
	 * Get all the dirty buffers mapped to disk addresses and
	 * handle any aliases from the underlying blockdev's mapping.
	 */
	do {
		if (block > last_block) {
			/*
			 * mapped buffers outside i_size will occur, because
			 * this page can be outside i_size when there is a
			 * truncate in progress.
			 */
			/*
			 * The buffer was zeroed by block_write_full_page()
			 */
			clear_buffer_dirty(bh);
			set_buffer_uptodate(bh);
		} else if ((!buffer_mapped(bh) || buffer_delay(bh)) &&
			   buffer_dirty(bh)) {
			WARN_ON(bh->b_size != blocksize);
			err = get_block(inode, block, bh, 1);
			if (err)
				goto recover;
			clear_buffer_delay(bh);
			if (buffer_new(bh)) {
				/* blockdev mappings never come here */
				clear_buffer_new(bh);
				unmap_underlying_metadata(bh->b_bdev,
							bh->b_blocknr);
			}
		}
		bh = bh->b_this_page;
		block++;
	} while (bh != head);

	do {
		if (!buffer_mapped(bh))
			continue;
		/*
		 * If it's a fully non-blocking write attempt and we cannot
		 * lock the buffer then redirty the page.  Note that this can
		 * potentially cause a busy-wait loop from writeback threads
		 * and kswapd activity, but those code paths have their own
		 * higher-level throttling.
		 */
		if (wbc->sync_mode != WB_SYNC_NONE || !wbc->nonblocking) {
			lock_buffer(bh);
		} else if (!trylock_buffer(bh)) {
			redirty_page_for_writepage(wbc, page);
			continue;
		}
		if (test_clear_buffer_dirty(bh)) {
			mark_buffer_async_write_endio(bh, handler);
		} else {
			unlock_buffer(bh);
		}
	} while ((bh = bh->b_this_page) != head);

	/*
	 * The page and its buffers are protected by PageWriteback(), so we can
	 * drop the bh refcounts early.
	 */
	BUG_ON(PageWriteback(page));
	set_page_writeback(page);

	do {
		struct buffer_head *next = bh->b_this_page;
		if (buffer_async_write(bh)) {
			submit_bh(write_op, bh);
			nr_underway++;
		}
		bh = next;
	} while (bh != head);
	unlock_page(page);

	err = 0;
done:
	if (nr_underway == 0) {
		/*
		 * The page was marked dirty, but the buffers were
		 * clean.  Someone wrote them back by hand with
		 * ll_rw_block/submit_bh.  A rare case.
		 */
		end_page_writeback(page);

		/*
		 * The page and buffer_heads can be released at any time from
		 * here on.
		 */
	}
	return err;

recover:
	/*
	 * ENOSPC, or some other error.  We may already have added some
	 * blocks to the file, so we need to write these out to avoid
	 * exposing stale data.
	 * The page is currently locked and not marked for writeback
	 */
	bh = head;
	/* Recovery: lock and submit the mapped buffers */
	do {
		if (buffer_mapped(bh) && buffer_dirty(bh) &&
		    !buffer_delay(bh)) {
			lock_buffer(bh);
			mark_buffer_async_write_endio(bh, handler);
		} else {
			/*
			 * The buffer may have been set dirty during
			 * attachment to a dirty page.
			 */
			clear_buffer_dirty(bh);
		}
	} while ((bh = bh->b_this_page) != head);
	SetPageError(page);
	BUG_ON(PageWriteback(page));
	mapping_set_error(page->mapping, err);
	set_page_writeback(page);
	do {
		struct buffer_head *next = bh->b_this_page;
		if (buffer_async_write(bh)) {
			clear_buffer_dirty(bh);
			submit_bh(write_op, bh);
			nr_underway++;
		}
		bh = next;
	} while (bh != head);
	unlock_page(page);
	goto done;
}

/*
 * If a page has any new buffers, zero them out here, and mark them uptodate
 * and dirty so they'll be written out (in order to prevent uninitialised
 * block data from leaking). And clear the new bit.
 */
void page_zero_new_buffers(struct page *page, unsigned from, unsigned to)
{
	unsigned int block_start, block_end;
	struct buffer_head *head, *bh;

	BUG_ON(!PageLocked(page));
	if (!page_has_buffers(page))
		return;

	bh = head = page_buffers(page);
	block_start = 0;
	do {
		block_end = block_start + bh->b_size;

		if (buffer_new(bh)) {
			if (block_end > from && block_start < to) {
				if (!PageUptodate(page)) {
					unsigned start, size;

					start = max(from, block_start);
					size = min(to, block_end) - start;

					zero_user(page, start, size);
					set_buffer_uptodate(bh);
				}

				clear_buffer_new(bh);
				mark_buffer_dirty(bh);
			}
		}

		block_start = block_end;
		bh = bh->b_this_page;
	} while (bh != head);
}
EXPORT_SYMBOL(page_zero_new_buffers);

static int __block_prepare_write(struct inode *inode, struct page *page,
		unsigned from, unsigned to, get_block_t *get_block)
{
	unsigned block_start, block_end;
	sector_t block;
	int err = 0;
	unsigned blocksize, bbits;
	struct buffer_head *bh, *head, *wait[2], **wait_bh=wait;

	BUG_ON(!PageLocked(page));
	BUG_ON(from > PAGE_CACHE_SIZE);
	BUG_ON(to > PAGE_CACHE_SIZE);
	BUG_ON(from > to);

	blocksize = 1 << inode->i_blkbits;
	if (!page_has_buffers(page))
		create_empty_buffers(page, blocksize, 0);
	head = page_buffers(page);

	bbits = inode->i_blkbits;
	block = (sector_t)page->index << (PAGE_CACHE_SHIFT - bbits);

	for(bh = head, block_start = 0; bh != head || !block_start;
	    block++, block_start=block_end, bh = bh->b_this_page) {
		block_end = block_start + blocksize;
		if (block_end <= from || block_start >= to) {
			if (PageUptodate(page)) {
				if (!buffer_uptodate(bh))
					set_buffer_uptodate(bh);
			}
			continue;
		}
		if (buffer_new(bh))
			clear_buffer_new(bh);
		if (!buffer_mapped(bh)) {
			WARN_ON(bh->b_size != blocksize);
			err = get_block(inode, block, bh, 1);
			if (err)
				break;
			if (buffer_new(bh)) {
				unmap_underlying_metadata(bh->b_bdev,
							bh->b_blocknr);
				if (PageUptodate(page)) {
					clear_buffer_new(bh);
					set_buffer_uptodate(bh);
					mark_buffer_dirty(bh);
					continue;
				}
				if (block_end > to || block_start < from)
					zero_user_segments(page,
						to, block_end,
						block_start, from);
				continue;
			}
		}
		if (PageUptodate(page)) {
			if (!buffer_uptodate(bh))
				set_buffer_uptodate(bh);
			continue; 
		}
		if (!buffer_uptodate(bh) && !buffer_delay(bh) &&
		    !buffer_unwritten(bh) &&
		     (block_start < from || block_end > to)) {
			ll_rw_block(READ, 1, &bh);
			*wait_bh++=bh;
		}
	}
	/*
	 * If we issued read requests - let them complete.
	 */
	while(wait_bh > wait) {
		wait_on_buffer(*--wait_bh);
		if (!buffer_uptodate(*wait_bh))
			err = -EIO;
	}
	if (unlikely(err))
		page_zero_new_buffers(page, from, to);
	return err;
}

static int __block_commit_write(struct inode *inode, struct page *page,
		unsigned from, unsigned to)
{
	unsigned block_start, block_end;
	int partial = 0;
	unsigned blocksize;
	struct buffer_head *bh, *head;

	blocksize = 1 << inode->i_blkbits;

	for(bh = head = page_buffers(page), block_start = 0;
	    bh != head || !block_start;
	    block_start=block_end, bh = bh->b_this_page) {
		block_end = block_start + blocksize;
		if (block_end <= from || block_start >= to) {
			if (!buffer_uptodate(bh))
				partial = 1;
		} else {
			set_buffer_uptodate(bh);
			mark_buffer_dirty(bh);
		}
		clear_buffer_new(bh);
	}

	/*
	 * If this is a partial write which happened to make all buffers
	 * uptodate then we can optimize away a bogus readpage() for
	 * the next read(). Here we 'discover' whether the page went
	 * uptodate as a result of this (potentially partial) write.
	 */
	if (!partial)
		SetPageUptodate(page);
	return 0;
}

/*
 * block_write_begin takes care of the basic task of block allocation and
 * bringing partial write blocks uptodate first.
 *
 * If *pagep is not NULL, then block_write_begin uses the locked page
 * at *pagep rather than allocating its own. In this case, the page will
 * not be unlocked or deallocated on failure.
 */
int block_write_begin(struct file *file, struct address_space *mapping,
			loff_t pos, unsigned len, unsigned flags,
			struct page **pagep, void **fsdata,
			get_block_t *get_block)
{
	struct inode *inode = mapping->host;
	int status = 0;
	struct page *page;
	pgoff_t index;
	unsigned start, end;
	int ownpage = 0;

	index = pos >> PAGE_CACHE_SHIFT;
	start = pos & (PAGE_CACHE_SIZE - 1);
	end = start + len;

	page = *pagep;
	if (page == NULL) {
		ownpage = 1;
		page = grab_cache_page_write_begin(mapping, index, flags);
		if (!page) {
			status = -ENOMEM;
			goto out;
		}
		*pagep = page;
	} else
		BUG_ON(!PageLocked(page));

	status = __block_prepare_write(inode, page, start, end, get_block);
	if (unlikely(status)) {
		ClearPageUptodate(page);

		if (ownpage) {
			unlock_page(page);