/fs/ext3/inode.c

/*
 *  linux/fs/ext3/inode.c
 *
 * Copyright (C) 1992, 1993, 1994, 1995
 * Remy Card (card@masi.ibp.fr)
 * Laboratoire MASI - Institut Blaise Pascal
 * Universite Pierre et Marie Curie (Paris VI)
 *
 *  from
 *
 *  linux/fs/minix/inode.c
 *
 *  Copyright (C) 1991, 1992  Linus Torvalds
 *
 *  Goal-directed block allocation by Stephen Tweedie
 *	(sct@redhat.com), 1993, 1998
 *  Big-endian to little-endian byte-swapping/bitmaps by
 *        David S. Miller (davem@caip.rutgers.edu), 1995
 *  64-bit file support on 64-bit platforms by Jakub Jelinek
 *	(jj@sunsite.ms.mff.cuni.cz)
 *
 *  Assorted race fixes, rewrite of ext3_get_block() by Al Viro, 2000
 */

#include <linux/module.h>
#include <linux/fs.h>
#include <linux/time.h>
#include <linux/ext3_jbd.h>
#include <linux/jbd.h>
#include <linux/highuid.h>
#include <linux/pagemap.h>
#include <linux/quotaops.h>
#include <linux/string.h>
#include <linux/buffer_head.h>
#include <linux/writeback.h>
#include <linux/mpage.h>
#include <linux/uio.h>
#include <linux/bio.h>
#include <linux/fiemap.h>
#include <linux/namei.h>
#include <trace/events/ext3.h>
#include "xattr.h"
#include "acl.h"

static int ext3_writepage_trans_blocks(struct inode *inode);
static int ext3_block_truncate_page(struct inode *inode, loff_t from);

/*
 * Test whether an inode is a fast symlink.
 */
static int ext3_inode_is_fast_symlink(struct inode *inode)
{
	int ea_blocks = EXT3_I(inode)->i_file_acl ?
		(inode->i_sb->s_blocksize >> 9) : 0;

	return (S_ISLNK(inode->i_mode) && inode->i_blocks - ea_blocks == 0);
}

/*
 * The ext3 forget function must perform a revoke if we are freeing data
 * which has been journaled.  Metadata (eg. indirect blocks) must be
 * revoked in all cases.
 *
 * "bh" may be NULL: a metadata block may have been freed from memory
 * but there may still be a record of it in the journal, and that record
 * still needs to be revoked.
 */
int ext3_forget(handle_t *handle, int is_metadata, struct inode *inode,
			struct buffer_head *bh, ext3_fsblk_t blocknr)
{
	int err;

	might_sleep();

	trace_ext3_forget(inode, is_metadata, blocknr);
	BUFFER_TRACE(bh, "enter");

	jbd_debug(4, "forgetting bh %p: is_metadata = %d, mode %o, "
		  "data mode %lx\n",
		  bh, is_metadata, inode->i_mode,
		  test_opt(inode->i_sb, DATA_FLAGS));

	/* Never use the revoke function if we are doing full data
	 * journaling: there is no need to, and a V1 superblock won't
	 * support it.  Otherwise, only skip the revoke on un-journaled
	 * data blocks. */

	if (test_opt(inode->i_sb, DATA_FLAGS) == EXT3_MOUNT_JOURNAL_DATA ||
	    (!is_metadata && !ext3_should_journal_data(inode))) {
		if (bh) {
			BUFFER_TRACE(bh, "call journal_forget");
			return ext3_journal_forget(handle, bh);
		}
		return 0;
	}

	/*
	 * data!=journal && (is_metadata || should_journal_data(inode))
	 */
	BUFFER_TRACE(bh, "call ext3_journal_revoke");
	err = ext3_journal_revoke(handle, blocknr, bh);
	if (err)
		ext3_abort(inode->i_sb, __func__,
			   "error %d when attempting revoke", err);
	BUFFER_TRACE(bh, "exit");
	return err;
}

/*
 * Work out how many blocks we need to proceed with the next chunk of a
 * truncate transaction.
 */
static unsigned long blocks_for_truncate(struct inode *inode)
{
	unsigned long needed;

	needed = inode->i_blocks >> (inode->i_sb->s_blocksize_bits - 9);

	/* Give ourselves just enough room to cope with inodes in which
	 * i_blocks is corrupt: we've seen disk corruptions in the past
	 * which resulted in random data in an inode which looked enough
	 * like a regular file for ext3 to try to delete it.  Things
	 * will go a bit crazy if that happens, but at least we should
	 * try not to panic the whole kernel. */
	if (needed < 2)
		needed = 2;

	/* But we need to bound the transaction so we don't overflow the
	 * journal. */
	if (needed > EXT3_MAX_TRANS_DATA)
		needed = EXT3_MAX_TRANS_DATA;

	return EXT3_DATA_TRANS_BLOCKS(inode->i_sb) + needed;
}

/*
 * Truncate transactions can be complex and absolutely huge.  So we need to
 * be able to restart the transaction at a conventient checkpoint to make
 * sure we don't overflow the journal.
 *
 * start_transaction gets us a new handle for a truncate transaction,
 * and extend_transaction tries to extend the existing one a bit.  If
 * extend fails, we need to propagate the failure up and restart the
 * transaction in the top-level truncate loop. --sct
 */
static handle_t *start_transaction(struct inode *inode)
{
	handle_t *result;

	result = ext3_journal_start(inode, blocks_for_truncate(inode));
	if (!IS_ERR(result))
		return result;

	ext3_std_error(inode->i_sb, PTR_ERR(result));
	return result;
}

/*
 * Try to extend this transaction for the purposes of truncation.
 *
 * Returns 0 if we managed to create more room.  If we can't create more
 * room, and the transaction must be restarted we return 1.
 */
static int try_to_extend_transaction(handle_t *handle, struct inode *inode)
{
	if (handle->h_buffer_credits > EXT3_RESERVE_TRANS_BLOCKS)
		return 0;
	if (!ext3_journal_extend(handle, blocks_for_truncate(inode)))
		return 0;
	return 1;
}

/*
 * Restart the transaction associated with *handle.  This does a commit,
 * so before we call here everything must be consistently dirtied against
 * this transaction.
 */
static int truncate_restart_transaction(handle_t *handle, struct inode *inode)
{
	int ret;

	jbd_debug(2, "restarting handle %p\n", handle);
	/*
	 * Drop truncate_mutex to avoid deadlock with ext3_get_blocks_handle
	 * At this moment, get_block can be called only for blocks inside
	 * i_size since page cache has been already dropped and writes are
	 * blocked by i_mutex. So we can safely drop the truncate_mutex.
	 */
	mutex_unlock(&EXT3_I(inode)->truncate_mutex);
	ret = ext3_journal_restart(handle, blocks_for_truncate(inode));
	mutex_lock(&EXT3_I(inode)->truncate_mutex);
	return ret;
}

/*
 * Called at inode eviction from icache
 */
void ext3_evict_inode (struct inode *inode)
{
	struct ext3_inode_info *ei = EXT3_I(inode);
	struct ext3_block_alloc_info *rsv;
	handle_t *handle;
	int want_delete = 0;

	trace_ext3_evict_inode(inode);
	if (!inode->i_nlink && !is_bad_inode(inode)) {
		dquot_initialize(inode);
		want_delete = 1;
	}

	/*
	 * When journalling data dirty buffers are tracked only in the journal.
	 * So although mm thinks everything is clean and ready for reaping the
	 * inode might still have some pages to write in the running
	 * transaction or waiting to be checkpointed. Thus calling
	 * journal_invalidatepage() (via truncate_inode_pages()) to discard
	 * these buffers can cause data loss. Also even if we did not discard
	 * these buffers, we would have no way to find them after the inode
	 * is reaped and thus user could see stale data if he tries to read
	 * them before the transaction is checkpointed. So be careful and
	 * force everything to disk here... We use ei->i_datasync_tid to
	 * store the newest transaction containing inode's data.
	 *
	 * Note that directories do not have this problem because they don't
	 * use page cache.
	 */
	if (inode->i_nlink && ext3_should_journal_data(inode) &&
	    (S_ISLNK(inode->i_mode) || S_ISREG(inode->i_mode))) {
		tid_t commit_tid = atomic_read(&ei->i_datasync_tid);
		journal_t *journal = EXT3_SB(inode->i_sb)->s_journal;

		log_start_commit(journal, commit_tid);
		log_wait_commit(journal, commit_tid);
		filemap_write_and_wait(&inode->i_data);
	}
	truncate_inode_pages(&inode->i_data, 0);

	ext3_discard_reservation(inode);
	rsv = ei->i_block_alloc_info;
	ei->i_block_alloc_info = NULL;
	if (unlikely(rsv))
		kfree(rsv);

	if (!want_delete)
		goto no_delete;

	handle = start_transaction(inode);
	if (IS_ERR(handle)) {
		/*
		 * If we're going to skip the normal cleanup, we still need to
		 * make sure that the in-core orphan linked list is properly
		 * cleaned up.
		 */
		ext3_orphan_del(NULL, inode);
		goto no_delete;
	}

	if (IS_SYNC(inode))
		handle->h_sync = 1;
	inode->i_size = 0;
	if (inode->i_blocks)
		ext3_truncate(inode);
	/*
	 * Kill off the orphan record created when the inode lost the last
	 * link.  Note that ext3_orphan_del() has to be able to cope with the
	 * deletion of a non-existent orphan - ext3_truncate() could
	 * have removed the record.
	 */
	ext3_orphan_del(handle, inode);
	ei->i_dtime = get_seconds();

	/*
	 * One subtle ordering requirement: if anything has gone wrong
	 * (transaction abort, IO errors, whatever), then we can still
	 * do these next steps (the fs will already have been marked as
	 * having errors), but we can't free the inode if the mark_dirty
	 * fails.
	 */
	if (ext3_mark_inode_dirty(handle, inode)) {
		/* If that failed, just dquot_drop() and be done with that */
		dquot_drop(inode);
		end_writeback(inode);
	} else {
		ext3_xattr_delete_inode(handle, inode);
		dquot_free_inode(inode);
		dquot_drop(inode);
		end_writeback(inode);
		ext3_free_inode(handle, inode);
	}
	ext3_journal_stop(handle);
	return;
no_delete:
	end_writeback(inode);
	dquot_drop(inode);
}

typedef struct {
	__le32	*p;
	__le32	key;
	struct buffer_head *bh;
} Indirect;

static inline void add_chain(Indirect *p, struct buffer_head *bh, __le32 *v)
{
	p->key = *(p->p = v);
	p->bh = bh;
}

static int verify_chain(Indirect *from, Indirect *to)
{
	while (from <= to && from->key == *from->p)
		from++;
	return (from > to);
}

/**
 *	ext3_block_to_path - parse the block number into array of offsets
 *	@inode: inode in question (we are only interested in its superblock)
 *	@i_block: block number to be parsed
 *	@offsets: array to store the offsets in
 *      @boundary: set this non-zero if the referred-to block is likely to be
 *             followed (on disk) by an indirect block.
 *
 *	To store the locations of file's data ext3 uses a data structure common
 *	for UNIX filesystems - tree of pointers anchored in the inode, with
 *	data blocks at leaves and indirect blocks in intermediate nodes.
 *	This function translates the block number into path in that tree -
 *	return value is the path length and @offsets[n] is the offset of
 *	pointer to (n+1)th node in the nth one. If @block is out of range
 *	(negative or too large) warning is printed and zero returned.
 *
 *	Note: function doesn't find node addresses, so no IO is needed. All
 *	we need to know is the capacity of indirect blocks (taken from the
 *	inode->i_sb).
 */

/*
 * Portability note: the last comparison (check that we fit into triple
 * indirect block) is spelled differently, because otherwise on an
 * architecture with 32-bit longs and 8Kb pages we might get into trouble
 * if our filesystem had 8Kb blocks. We might use long long, but that would
 * kill us on x86. Oh, well, at least the sign propagation does not matter -
 * i_block would have to be negative in the very beginning, so we would not
 * get there at all.
 */

static int ext3_block_to_path(struct inode *inode,
			long i_block, int offsets[4], int *boundary)
{
	int ptrs = EXT3_ADDR_PER_BLOCK(inode->i_sb);
	int ptrs_bits = EXT3_ADDR_PER_BLOCK_BITS(inode->i_sb);
	const long direct_blocks = EXT3_NDIR_BLOCKS,
		indirect_blocks = ptrs,
		double_blocks = (1 << (ptrs_bits * 2));
	int n = 0;
	int final = 0;

	if (i_block < 0) {
		ext3_warning (inode->i_sb, "ext3_block_to_path", "block < 0");
	} else if (i_block < direct_blocks) {
		offsets[n++] = i_block;
		final = direct_blocks;
	} else if ( (i_block -= direct_blocks) < indirect_blocks) {
		offsets[n++] = EXT3_IND_BLOCK;
		offsets[n++] = i_block;
		final = ptrs;
	} else if ((i_block -= indirect_blocks) < double_blocks) {
		offsets[n++] = EXT3_DIND_BLOCK;
		offsets[n++] = i_block >> ptrs_bits;
		offsets[n++] = i_block & (ptrs - 1);
		final = ptrs;
	} else if (((i_block -= double_blocks) >> (ptrs_bits * 2)) < ptrs) {
		offsets[n++] = EXT3_TIND_BLOCK;
		offsets[n++] = i_block >> (ptrs_bits * 2);
		offsets[n++] = (i_block >> ptrs_bits) & (ptrs - 1);
		offsets[n++] = i_block & (ptrs - 1);
		final = ptrs;
	} else {
		ext3_warning(inode->i_sb, "ext3_block_to_path", "block > big");
	}
	if (boundary)
		*boundary = final - 1 - (i_block & (ptrs - 1));
	return n;
}

/**
 *	ext3_get_branch - read the chain of indirect blocks leading to data
 *	@inode: inode in question
 *	@depth: depth of the chain (1 - direct pointer, etc.)
 *	@offsets: offsets of pointers in inode/indirect blocks
 *	@chain: place to store the result
 *	@err: here we store the error value
 *
 *	Function fills the array of triples <key, p, bh> and returns %NULL
 *	if everything went OK or the pointer to the last filled triple
 *	(incomplete one) otherwise. Upon the return chain[i].key contains
 *	the number of (i+1)-th block in the chain (as it is stored in memory,
 *	i.e. little-endian 32-bit), chain[i].p contains the address of that
 *	number (it points into struct inode for i==0 and into the bh->b_data
 *	for i>0) and chain[i].bh points to the buffer_head of i-th indirect
 *	block for i>0 and NULL for i==0. In other words, it holds the block
 *	numbers of the chain, addresses they were taken from (and where we can
 *	verify that chain did not change) and buffer_heads hosting these
 *	numbers.
 *
 *	Function stops when it stumbles upon zero pointer (absent block)
 *		(pointer to last triple returned, *@err == 0)
 *	or when it gets an IO error reading an indirect block
 *		(ditto, *@err == -EIO)
 *	or when it notices that chain had been changed while it was reading
 *		(ditto, *@err == -EAGAIN)
 *	or when it reads all @depth-1 indirect blocks successfully and finds
 *	the whole chain, all way to the data (returns %NULL, *err == 0).
 */
static Indirect *ext3_get_branch(struct inode *inode, int depth, int *offsets,
				 Indirect chain[4], int *err)
{
	struct super_block *sb = inode->i_sb;
	Indirect *p = chain;
	struct buffer_head *bh;

	*err = 0;
	/* i_data is not going away, no lock needed */
	add_chain (chain, NULL, EXT3_I(inode)->i_data + *offsets);
	if (!p->key)
		goto no_block;
	while (--depth) {
		bh = sb_bread(sb, le32_to_cpu(p->key));
		if (!bh)
			goto failure;
		/* Reader: pointers */
		if (!verify_chain(chain, p))
			goto changed;
		add_chain(++p, bh, (__le32*)bh->b_data + *++offsets);
		/* Reader: end */
		if (!p->key)
			goto no_block;
	}
	return NULL;

changed:
	brelse(bh);
	*err = -EAGAIN;
	goto no_block;
failure:
	*err = -EIO;
no_block:
	return p;
}

/**
 *	ext3_find_near - find a place for allocation with sufficient locality
 *	@inode: owner
 *	@ind: descriptor of indirect block.
 *
 *	This function returns the preferred place for block allocation.
 *	It is used when heuristic for sequential allocation fails.
 *	Rules are:
 *	  + if there is a block to the left of our position - allocate near it.
 *	  + if pointer will live in indirect block - allocate near that block.
 *	  + if pointer will live in inode - allocate in the same
 *	    cylinder group.
 *
 * In the latter case we colour the starting block by the callers PID to
 * prevent it from clashing with concurrent allocations for a different inode
 * in the same block group.   The PID is used here so that functionally related
 * files will be close-by on-disk.
 *
 *	Caller must make sure that @ind is valid and will stay that way.
 */
static ext3_fsblk_t ext3_find_near(struct inode *inode, Indirect *ind)
{
	struct ext3_inode_info *ei = EXT3_I(inode);
	__le32 *start = ind->bh ? (__le32*) ind->bh->b_data : ei->i_data;
	__le32 *p;
	ext3_fsblk_t bg_start;
	ext3_grpblk_t colour;

	/* Try to find previous block */
	for (p = ind->p - 1; p >= start; p--) {
		if (*p)
			return le32_to_cpu(*p);
	}

	/* No such thing, so let's try location of indirect block */
	if (ind->bh)
		return ind->bh->b_blocknr;

	/*
	 * It is going to be referred to from the inode itself? OK, just put it
	 * into the same cylinder group then.
	 */
	bg_start = ext3_group_first_block_no(inode->i_sb, ei->i_block_group);
	colour = (current->pid % 16) *
			(EXT3_BLOCKS_PER_GROUP(inode->i_sb) / 16);
	return bg_start + colour;
}

/**
 *	ext3_find_goal - find a preferred place for allocation.
 *	@inode: owner
 *	@block:  block we want
 *	@partial: pointer to the last triple within a chain
 *
 *	Normally this function find the preferred place for block allocation,
 *	returns it.
 */

static ext3_fsblk_t ext3_find_goal(struct inode *inode, long block,
				   Indirect *partial)
{
	struct ext3_block_alloc_info *block_i;

	block_i =  EXT3_I(inode)->i_block_alloc_info;

	/*
	 * try the heuristic for sequential allocation,
	 * failing that at least try to get decent locality.
	 */
	if (block_i && (block == block_i->last_alloc_logical_block + 1)
		&& (block_i->last_alloc_physical_block != 0)) {
		return block_i->last_alloc_physical_block + 1;
	}

	return ext3_find_near(inode, partial);
}

/**
 *	ext3_blks_to_allocate - Look up the block map and count the number
 *	of direct blocks need to be allocated for the given branch.
 *
 *	@branch: chain of indirect blocks
 *	@k: number of blocks need for indirect blocks
 *	@blks: number of data blocks to be mapped.
 *	@blocks_to_boundary:  the offset in the indirect block
 *
 *	return the total number of blocks to be allocate, including the
 *	direct and indirect blocks.
 */
static int ext3_blks_to_allocate(Indirect *branch, int k, unsigned long blks,
		int blocks_to_boundary)
{
	unsigned long count = 0;

	/*
	 * Simple case, [t,d]Indirect block(s) has not allocated yet
	 * then it's clear blocks on that path have not allocated
	 */
	if (k > 0) {
		/* right now we don't handle cross boundary allocation */
		if (blks < blocks_to_boundary + 1)
			count += blks;
		else
			count += blocks_to_boundary + 1;
		return count;
	}

	count++;
	while (count < blks && count <= blocks_to_boundary &&
		le32_to_cpu(*(branch[0].p + count)) == 0) {
		count++;
	}
	return count;
}

/**
 *	ext3_alloc_blocks - multiple allocate blocks needed for a branch
 *	@handle: handle for this transaction
 *	@inode: owner
 *	@goal: preferred place for allocation
 *	@indirect_blks: the number of blocks need to allocate for indirect
 *			blocks
 *	@blks:	number of blocks need to allocated for direct blocks
 *	@new_blocks: on return it will store the new block numbers for
 *	the indirect blocks(if needed) and the first direct block,
 *	@err: here we store the error value
 *
 *	return the number of direct blocks allocated
 */
static int ext3_alloc_blocks(handle_t *handle, struct inode *inode,
			ext3_fsblk_t goal, int indirect_blks, int blks,
			ext3_fsblk_t new_blocks[4], int *err)
{
	int target, i;
	unsigned long count = 0;
	int index = 0;
	ext3_fsblk_t current_block = 0;
	int ret = 0;

	/*
	 * Here we try to allocate the requested multiple blocks at once,
	 * on a best-effort basis.
	 * To build a branch, we should allocate blocks for
	 * the indirect blocks(if not allocated yet), and at least
	 * the first direct block of this branch.  That's the
	 * minimum number of blocks need to allocate(required)
	 */
	target = blks + indirect_blks;

	while (1) {
		count = target;
		/* allocating blocks for indirect blocks and direct blocks */
		current_block = ext3_new_blocks(handle,inode,goal,&count,err);
		if (*err)
			goto failed_out;

		target -= count;
		/* allocate blocks for indirect blocks */
		while (index < indirect_blks && count) {
			new_blocks[index++] = current_block++;
			count--;
		}

		if (count > 0)
			break;
	}

	/* save the new block number for the first direct block */
	new_blocks[index] = current_block;

	/* total number of blocks allocated for direct blocks */
	ret = count;
	*err = 0;
	return ret;
failed_out:
	for (i = 0; i <index; i++)
		ext3_free_blocks(handle, inode, new_blocks[i], 1);
	return ret;
}

/**
 *	ext3_alloc_branch - allocate and set up a chain of blocks.
 *	@handle: handle for this transaction
 *	@inode: owner
 *	@indirect_blks: number of allocated indirect blocks
 *	@blks: number of allocated direct blocks
 *	@goal: preferred place for allocation
 *	@offsets: offsets (in the blocks) to store the pointers to next.
 *	@branch: place to store the chain in.
 *
 *	This function allocates blocks, zeroes out all but the last one,
 *	links them into chain and (if we are synchronous) writes them to disk.
 *	In other words, it prepares a branch that can be spliced onto the
 *	inode. It stores the information about that chain in the branch[], in
 *	the same format as ext3_get_branch() would do. We are calling it after
 *	we had read the existing part of chain and partial points to the last
 *	triple of that (one with zero ->key). Upon the exit we have the same
 *	picture as after the successful ext3_get_block(), except that in one
 *	place chain is disconnected - *branch->p is still zero (we did not
 *	set the last link), but branch->key contains the number that should
 *	be placed into *branch->p to fill that gap.
 *
 *	If allocation fails we free all blocks we've allocated (and forget
 *	their buffer_heads) and return the error value the from failed
 *	ext3_alloc_block() (normally -ENOSPC). Otherwise we set the chain
 *	as described above and return 0.
 */
static int ext3_alloc_branch(handle_t *handle, struct inode *inode,
			int indirect_blks, int *blks, ext3_fsblk_t goal,
			int *offsets, Indirect *branch)
{
	int blocksize = inode->i_sb->s_blocksize;
	int i, n = 0;
	int err = 0;
	struct buffer_head *bh;
	int num;
	ext3_fsblk_t new_blocks[4];
	ext3_fsblk_t current_block;

	num = ext3_alloc_blocks(handle, inode, goal, indirect_blks,
				*blks, new_blocks, &err);
	if (err)
		return err;

	branch[0].key = cpu_to_le32(new_blocks[0]);
	/*
	 * metadata blocks and data blocks are allocated.
	 */
	for (n = 1; n <= indirect_blks;  n++) {
		/*
		 * Get buffer_head for parent block, zero it out
		 * and set the pointer to new one, then send
		 * parent to disk.
		 */
		bh = sb_getblk(inode->i_sb, new_blocks[n-1]);
		branch[n].bh = bh;
		lock_buffer(bh);
		BUFFER_TRACE(bh, "call get_create_access");
		err = ext3_journal_get_create_access(handle, bh);
		if (err) {
			unlock_buffer(bh);
			brelse(bh);
			goto failed;
		}

		memset(bh->b_data, 0, blocksize);
		branch[n].p = (__le32 *) bh->b_data + offsets[n];
		branch[n].key = cpu_to_le32(new_blocks[n]);
		*branch[n].p = branch[n].key;
		if ( n == indirect_blks) {
			current_block = new_blocks[n];
			/*
			 * End of chain, update the last new metablock of
			 * the chain to point to the new allocated
			 * data blocks numbers
			 */
			for (i=1; i < num; i++)
				*(branch[n].p + i) = cpu_to_le32(++current_block);
		}
		BUFFER_TRACE(bh, "marking uptodate");
		set_buffer_uptodate(bh);
		unlock_buffer(bh);

		BUFFER_TRACE(bh, "call ext3_journal_dirty_metadata");
		err = ext3_journal_dirty_metadata(handle, bh);
		if (err)
			goto failed;
	}
	*blks = num;
	return err;
failed:
	/* Allocation failed, free what we already allocated */
	for (i = 1; i <= n ; i++) {
		BUFFER_TRACE(branch[i].bh, "call journal_forget");
		ext3_journal_forget(handle, branch[i].bh);
	}
	for (i = 0; i <indirect_blks; i++)
		ext3_free_blocks(handle, inode, new_blocks[i], 1);

	ext3_free_blocks(handle, inode, new_blocks[i], num);

	return err;
}

/**
 * ext3_splice_branch - splice the allocated branch onto inode.
 * @handle: handle for this transaction
 * @inode: owner
 * @block: (logical) number of block we are adding
 * @where: location of missing link
 * @num:   number of indirect blocks we are adding
 * @blks:  number of direct blocks we are adding
 *
 * This function fills the missing link and does all housekeeping needed in
 * inode (->i_blocks, etc.). In case of success we end up with the full
 * chain to new block and return 0.
 */
static int ext3_splice_branch(handle_t *handle, struct inode *inode,
			long block, Indirect *where, int num, int blks)
{
	int i;
	int err = 0;
	struct ext3_block_alloc_info *block_i;
	ext3_fsblk_t current_block;
	struct ext3_inode_info *ei = EXT3_I(inode);

	block_i = ei->i_block_alloc_info;
	/*
	 * If we're splicing into a [td]indirect block (as opposed to the
	 * inode) then we need to get write access to the [td]indirect block
	 * before the splice.
	 */
	if (where->bh) {
		BUFFER_TRACE(where->bh, "get_write_access");
		err = ext3_journal_get_write_access(handle, where->bh);
		if (err)
			goto err_out;
	}
	/* That's it */

	*where->p = where->key;

	/*
	 * Update the host buffer_head or inode to point to more just allocated
	 * direct blocks blocks
	 */
	if (num == 0 && blks > 1) {
		current_block = le32_to_cpu(where->key) + 1;
		for (i = 1; i < blks; i++)
			*(where->p + i ) = cpu_to_le32(current_block++);
	}

	/*
	 * update the most recently allocated logical & physical block
	 * in i_block_alloc_info, to assist find the proper goal block for next
	 * allocation
	 */
	if (block_i) {
		block_i->last_alloc_logical_block = block + blks - 1;
		block_i->last_alloc_physical_block =
				le32_to_cpu(where[num].key) + blks - 1;
	}

	/* We are done with atomic stuff, now do the rest of housekeeping */

	inode->i_ctime = CURRENT_TIME_SEC;
	ext3_mark_inode_dirty(handle, inode);
	/* ext3_mark_inode_dirty already updated i_sync_tid */
	atomic_set(&ei->i_datasync_tid, handle->h_transaction->t_tid);

	/* had we spliced it onto indirect block? */
	if (where->bh) {
		/*
		 * If we spliced it onto an indirect block, we haven't
		 * altered the inode.  Note however that if it is being spliced
		 * onto an indirect block at the very end of the file (the
		 * file is growing) then we *will* alter the inode to reflect
		 * the new i_size.  But that is not done here - it is done in
		 * generic_commit_write->__mark_inode_dirty->ext3_dirty_inode.
		 */
		jbd_debug(5, "splicing indirect only\n");
		BUFFER_TRACE(where->bh, "call ext3_journal_dirty_metadata");
		err = ext3_journal_dirty_metadata(handle, where->bh);
		if (err)
			goto err_out;
	} else {
		/*
		 * OK, we spliced it into the inode itself on a direct block.
		 * Inode was dirtied above.
		 */
		jbd_debug(5, "splicing direct\n");
	}
	return err;

err_out:
	for (i = 1; i <= num; i++) {
		BUFFER_TRACE(where[i].bh, "call journal_forget");
		ext3_journal_forget(handle, where[i].bh);
		ext3_free_blocks(handle,inode,le32_to_cpu(where[i-1].key),1);
	}
	ext3_free_blocks(handle, inode, le32_to_cpu(where[num].key), blks);

	return err;
}

/*
 * Allocation strategy is simple: if we have to allocate something, we will
 * have to go the whole way to leaf. So let's do it before attaching anything
 * to tree, set linkage between the newborn blocks, write them if sync is
 * required, recheck the path, free and repeat if check fails, otherwise
 * set the last missing link (that will protect us from any truncate-generated
 * removals - all blocks on the path are immune now) and possibly force the
 * write on the parent block.
 * That has a nice additional property: no special recovery from the failed
 * allocations is needed - we simply release blocks and do not touch anything
 * reachable from inode.
 *
 * `handle' can be NULL if create == 0.
 *
 * The BKL may not be held on entry here.  Be sure to take it early.
 * return > 0, # of blocks mapped or allocated.
 * return = 0, if plain lookup failed.
 * return < 0, error case.
 */
int ext3_get_blocks_handle(handle_t *handle, struct inode *inode,
		sector_t iblock, unsigned long maxblocks,
		struct buffer_head *bh_result,
		int create)
{
	int err = -EIO;
	int offsets[4];
	Indirect chain[4];
	Indirect *partial;
	ext3_fsblk_t goal;
	int indirect_blks;
	int blocks_to_boundary = 0;
	int depth;
	struct ext3_inode_info *ei = EXT3_I(inode);
	int count = 0;
	ext3_fsblk_t first_block = 0;


	trace_ext3_get_blocks_enter(inode, iblock, maxblocks, create);
	J_ASSERT(handle != NULL || create == 0);
	depth = ext3_block_to_path(inode,iblock,offsets,&blocks_to_boundary);

	if (depth == 0)
		goto out;

	partial = ext3_get_branch(inode, depth, offsets, chain, &err);

	/* Simplest case - block found, no allocation needed */
	if (!partial) {
		first_block = le32_to_cpu(chain[depth - 1].key);
		clear_buffer_new(bh_result);
		count++;
		/*map more blocks*/
		while (count < maxblocks && count <= blocks_to_boundary) {
			ext3_fsblk_t blk;

			if (!verify_chain(chain, chain + depth - 1)) {
				/*
				 * Indirect block might be removed by
				 * truncate while we were reading it.
				 * Handling of that case: forget what we've
				 * got now. Flag the err as EAGAIN, so it
				 * will reread.
				 */
				err = -EAGAIN;
				count = 0;
				break;
			}
			blk = le32_to_cpu(*(chain[depth-1].p + count));

			if (blk == first_block + count)
				count++;
			else
				break;
		}
		if (err != -EAGAIN)
			goto got_it;
	}

	/* Next simple case - plain lookup or failed read of indirect block */
	if (!create || err == -EIO)
		goto cleanup;

	/*
	 * Block out ext3_truncate while we alter the tree
	 */
	mutex_lock(&ei->truncate_mutex);

	/*
	 * If the indirect block is missing while we are reading
	 * the chain(ext3_get_branch() returns -EAGAIN err), or
	 * if the chain has been changed after we grab the semaphore,
	 * (either because another process truncated this branch, or
	 * another get_block allocated this branch) re-grab the chain to see if
	 * the request block has been allocated or not.
	 *
	 * Since we already block the truncate/other get_block
	 * at this point, we will have the current copy of the chain when we
	 * splice the branch into the tree.
	 */
	if (err == -EAGAIN || !verify_chain(chain, partial)) {
		while (partial > chain) {
			brelse(partial->bh);
			partial--;
		}
		partial = ext3_get_branch(inode, depth, offsets, chain, &err);
		if (!partial) {
			count++;
			mutex_unlock(&ei->truncate_mutex);
			if (err)
				goto cleanup;
			clear_buffer_new(bh_result);
			goto got_it;
		}
	}

	/*
	 * Okay, we need to do block allocation.  Lazily initialize the block
	 * allocation info here if necessary
	*/
	if (S_ISREG(inode->i_mode) && (!ei->i_block_alloc_info))
		ext3_init_block_alloc_info(inode);

	goal = ext3_find_goal(inode, iblock, partial);

	/* the number of blocks need to allocate for [d,t]indirect blocks */
	indirect_blks = (chain + depth) - partial - 1;

	/*
	 * Next look up the indirect map to count the totoal number of
	 * direct blocks to allocate for this branch.
	 */
	count = ext3_blks_to_allocate(partial, indirect_blks,
					maxblocks, blocks_to_boundary);
	err = ext3_alloc_branch(handle, inode, indirect_blks, &count, goal,
				offsets + (partial - chain), partial);

	/*
	 * The ext3_splice_branch call will free and forget any buffers
	 * on the new chain if there is a failure, but that risks using
	 * up transaction credits, especially for bitmaps where the
	 * credits cannot be returned.  Can we handle this somehow?  We
	 * may need to return -EAGAIN upwards in the worst case.  --sct
	 */
	if (!err)
		err = ext3_splice_branch(handle, inode, iblock,
					partial, indirect_blks, count);
	mutex_unlock(&ei->truncate_mutex);
	if (err)
		goto cleanup;

	set_buffer_new(bh_result);
got_it:
	map_bh(bh_result, inode->i_sb, le32_to_cpu(chain[depth-1].key));
	if (count > blocks_to_boundary)
		set_buffer_boundary(bh_result);
	err = count;
	/* Clean up and exit */
	partial = chain + depth - 1;	/* the whole chain */
cleanup:
	while (partial > chain) {
		BUFFER_TRACE(partial->bh, "call brelse");
		brelse(partial->bh);
		partial--;
	}
	BUFFER_TRACE(bh_result, "returned");
out:
	trace_ext3_get_blocks_exit(inode, iblock,
				   depth ? le32_to_cpu(chain[depth-1].key) : 0,
				   count, err);
	return err;
}

/* Maximum number of blocks we map for direct IO at once. */
#define DIO_MAX_BLOCKS 4096
/*
 * Number of credits we need for writing DIO_MAX_BLOCKS:
 * We need sb + group descriptor + bitmap + inode -> 4
 * For B blocks with A block pointers per block we need:
 * 1 (triple ind.) + (B/A/A + 2) (doubly ind.) + (B/A + 2) (indirect).
 * If we plug in 4096 for B and 256 for A (for 1KB block size), we get 25.
 */
#define DIO_CREDITS 25

static int ext3_get_block(struct inode *inode, sector_t iblock,
			struct buffer_head *bh_result, int create)
{
	handle_t *handle = ext3_journal_current_handle();
	int ret = 0, started = 0;
	unsigned max_blocks = bh_result->b_size >> inode->i_blkbits;

	if (create && !handle) {	/* Direct IO write... */
		if (max_blocks > DIO_MAX_BLOCKS)
			max_blocks = DIO_MAX_BLOCKS;
		handle = ext3_journal_start(inode, DIO_CREDITS +
				EXT3_MAXQUOTAS_TRANS_BLOCKS(inode->i_sb));
		if (IS_ERR(handle)) {
			ret = PTR_ERR(handle);
			goto out;
		}
		started = 1;
	}

	ret = ext3_get_blocks_handle(handle, inode, iblock,
					max_blocks, bh_result, create);
	if (ret > 0) {
		bh_result->b_size = (ret << inode->i_blkbits);
		ret = 0;
	}
	if (started)
		ext3_journal_stop(handle);
out:
	return ret;
}

int ext3_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo,
		u64 start, u64 len)
{
	return generic_block_fiemap(inode, fieinfo, start, len,
				    ext3_get_block);
}

/*
 * `handle' can be NULL if create is zero
 */
struct buffer_head *ext3_getblk(handle_t *handle, struct inode *inode,
				long block, int create, int *errp)
{
	struct buffer_head dummy;
	int fatal = 0, err;

	J_ASSERT(handle != NULL || create == 0);

	dummy.b_state = 0;
	dummy.b_blocknr = -1000;
	buffer_trace_init(&dummy.b_history);
	err = ext3_get_blocks_handle(handle, inode, block, 1,
					&dummy, create);
	/*
	 * ext3_get_blocks_handle() returns number of blocks
	 * mapped. 0 in case of a HOLE.
	 */
	if (err > 0) {
		if (err > 1)
			WARN_ON(1);
		err = 0;
	}
	*errp = err;
	if (!err && buffer_mapped(&dummy)) {
		struct buffer_head *bh;
		bh = sb_getblk(inode->i_sb, dummy.b_blocknr);
		if (!bh) {
			*errp = -EIO;
			goto err;
		}
		if (buffer_new(&dummy)) {
			J_ASSERT(create != 0);
			J_ASSERT(handle != NULL);

			/*
			 * Now that we do not always journal data, we should
			 * keep in mind whether this should always journal the
			 * new buffer as metadata.  For now, regular file
			 * writes use ext3_get_block instead, so it's not a
			 * problem.
			 */
			lock_buffer(bh);
			BUFFER_TRACE(bh, "call get_create_access");
			fatal = ext3_journal_get_create_access(handle, bh);
			if (!fatal && !buffer_uptodate(bh)) {
				memset(bh->b_data,0,inode->i_sb->s_blocksize);
				set_buffer_uptodate(bh);
			}
			unlock_buffer(bh);
			BUFFER_TRACE(bh, "call ext3_journal_dirty_metadata");
			err = ext3_journal_dirty_metadata(handle, bh);
			if (!fatal)
				fatal = err;
		} else {
			BUFFER_TRACE(bh, "not a new buffer");
		}
		if (fatal) {
			*errp = fatal;
			brelse(bh);
			bh = NULL;
		}
		return bh;
	}
err:
	return NULL;
}

struct buffer_head *ext3_bread(handle_t *handle, struct inode *inode,
			       int block, int create, int *err)
{
	struct buffer_head * bh;

	bh = ext3_getblk(handle, inode, block, create, err);
	if (!bh)
		return bh;
	if (buffer_uptodate(bh))
		return bh;
	ll_rw_block(READ_META, 1, &bh);
	wait_on_buffer(bh);
	if (buffer_uptodate(bh))
		return bh;
	put_bh(bh);
	*err = -EIO;
	return NULL;
}

static int walk_page_buffers(	handle_t *handle,
				struct buffer_head *head,
				unsigned from,
				unsigned to,
				int *partial,
				int (*fn)(	handle_t *handle,
						struct buffer_head *bh))
{
	struct buffer_head *bh;
	unsigned block_start, block_end;
	unsigned blocksize = head->b_size;
	int err, ret = 0;
	struct buffer_head *next;

	for (	bh = head, block_start = 0;
		ret == 0 && (bh != head || !block_start);
		block_start = block_end, bh = next)
	{
		next = bh->b_this_page;
		block_end = block_start + blocksize;
		if (block_end <= from || block_start >= to) {
			if (partial && !buffer_uptodate(bh))
				*partial = 1;
			continue;
		}
		err = (*fn)(handle, bh);
		if (!ret)
			ret = err;
	}
	return ret;
}

/*
 * To preserve ordering, it is essential that the hole instantiation and
 * the data write be encapsulated in a single transaction.  We cannot
 * close off a transaction and start a new one between the ext3_get_block()
 * and the commit_write().  So doing the journal_start at the start of
 * prepare_write() is the right place.
 *
 * Also, this function can nest inside ext3_writepage() ->
 * block_write_full_page(). In that case, we *know* that ext3_writepage()
 * has generated enough buffer credits to do the whole page.  So we won't
 * block on the journal in that case, which is good, because the caller may
 * be PF_MEMALLOC.
 *
 * By accident, ext3 can be reentered when a transaction is open via
 * quota file writes.  If we were to commit the transaction while thus
 * reentered, there can be a deadlock - we would be holding a quota
 * lock, and the commit would never complete if another thread had a
 * transaction open and was blocking on the quota lock - a ranking
 * violation.
 *
 * So what we do is to rely on the fact that journal_stop/journal_start
 * will _not_ run commit under these circumstances because handle->h_ref
 * is elevated.  We'll still have enough credits for the tiny quotafile
 * write.
 */
static int do_journal_get_write_access(handle_t *handle,
					struct buffer_head *bh)
{
	int dirty = buffer_dirty(bh);
	int ret;

	if (!buffer_mapped(bh) || buffer_freed(bh))
		return 0;
	/*
	 * __block_prepare_write() could have dirtied some buffers. Clean
	 * the dirty bit as jbd2_journal_get_write_access() could complain
	 * otherwise about fs integrity issues. Setting of the dirty bit
	 * by __block_prepare_write() isn't a real problem here as we clear
	 * the bit before releasing a page lock and thus writeback cannot
	 * ever write the buffer.
	 */
	if (dirty)
		clear_buffer_dirty(bh);
	ret = ext3_journal_get_write_access(handle, bh);
	if (!ret && dirty)
		ret = ext3_journal_dirty_metadata(handle, bh);
	return ret;
}

/*
 * Truncate blocks that were not used by write. We have to truncate the
 * pagecache as well so that corresponding buffers get properly unmapped.
 */
static void ext3_truncate_failed_write(struct inode *inode)
{
	truncate_inode_pages(inode->i_mapping, inode->i_size);
	ext3_truncate(inode);
}

/*
 * Truncate blocks that were not used by direct IO write. We have to zero out
 * the last file block as well because direct IO might have written to it.
 */
static void ext3_truncate_failed_direct_write(struct inode *inode)
{
	ext3_block_truncate_page(inode, inode->i_size);
	ext3_truncate(inode);
}

static int ext3_write_begin(struct file *file, struct address_space *mapping,
				loff_t pos, unsigned len, unsigned flags,
				struct page **pagep, void **fsdata)
{
	struct inode *inode = mapping->host;
	int ret;
	handle_t *handle;
	int retries = 0;
	struct page *page;
	pgoff_t index;
	unsigned from, to;
	/* Reserve one block more for addition to orphan list in case
	 * we allocate blocks but write fails for some reason */
	int needed_blocks = ext3_writepage_trans_blocks(inode) + 1;

	trace_ext3_write_begin(inode, pos, len, flags);

	index = pos >> PAGE_CACHE_SHIFT;
	from = pos & (PAGE_CACHE_SIZE - 1);
	to = from + len;

retry:
	page = grab_cache_page_write_begin(mapping, index, flags);
	if (!page)
		return -ENOMEM;
	*pagep = page;

	handle = ext3_journal_start(inode, needed_blocks);
	if (IS_ERR(handle)) {
		unlock_page(page);
		page_cache_release(page);
		ret = PTR_ERR(handle);
		goto out;
	}
	ret = __block_write_begin(page, pos, len, ext3_get_block);
	if (ret)
		goto write_begin_failed;

	if (ext3_should_journal_data(inode)) {
		ret = walk_page_buffers(handle, page_buffers(page),
				from, to, NULL, do_journal_get_write_access);
	}
write_begin_failed:
	if (ret) {
		/*
		 * block_write_begin may have instantiated a few blocks
		 * outside i_size.  Trim these off again. Don't need
		 * i_size_read because we hold i_mutex.
		 *
		 * Add inode to orphan list in case we crash before truncate
		 * finishes. Do this only if ext3_can_truncate() agrees so
		 * that orphan processing code is happy.
		 */
		if (pos + len > inode->i_size && ext3_can_truncate(inode))
			ext3_orphan_add(handle, inode);
		ext3_journal_stop(handle);
		unlock_page(page);
		page_cache_release(page);
		if (pos + len > inode->i_size)
			ext3_truncate_failed_write(inode);
	}
	if (ret == -ENOSPC && ext3_should_retry_alloc(inode->i_sb, &retries))
		goto retry;
out:
	return ret;
}


int ext3_journal_dirty_data(handle_t *handle, struct buffer_head *bh)
{
	int err = journal_dirty_data(handle, bh);
	if (err)
		ext3_journal_abort_handle(__func__, __func__,
						bh, handle, err);
	return err;
}

/* For ordered writepage and write_end functions */
static int journal_dirty_data_fn(handle_t *handle, struct buffer_head *bh)
{
	/*
	 * Write could have mapped the buffer but it didn't copy the data in
	 * yet. So avoid filing such buffer into a transaction.
	 */
	if (buffer_mapped(bh) && buffer_uptodate(bh))
		return ext3_journal_dirty_data(handle, bh);
	return 0;
}

/* For write_end() in data=journal mode */
static int write_end_fn(handle_t *handle, struct buffer_head *bh)
{
	if (!buffer_mapped(bh) || buffer_freed(bh))
		return 0;
	set_buffer_uptodate(bh);
	return ext3_journal_dirty_metadata(handle, bh);
}

/*
 * This is nasty and subtle: ext3_write_begin() could have allocated blocks
 * for the whole page but later we failed to copy the data in. Update inode
 * size according to what we managed to copy. The rest is going to be
 * truncated in write_end function.
 */
static void update_file_sizes(struct inode *inode, loff_t pos, unsigned copied)
{
	/* What matters to us is i_disksize. We don't write i_size anywhere */
	if (pos + copied > inode->i_size)
		i_size_write(inode, pos + copied);
	if (pos + copied > EXT3_I(inode)->i_disksize) {
		EXT3_I(inode)->i_disksize = pos + copied;
		mark_inode_dirty(inode);
	}
}

/*
 * We need to pick up the new inode size which generic_commit_write gave us
 * `file' can be NULL - eg, when called from page_symlink().
 *
 * ext3 never places buffers on inode->i_mapping->private_list.  metadata
 * buffers are managed internally.
 */
static int ext3_ordered_write_end(struct file *file,
				struct address_space *mapping,
				loff_t pos, unsigned len, unsigned copied,
				struct page *page, void *fsdata)
{
	handle_t *handle = ext3_journal_current_handle();
	struct inode *inode = file->f_mapping->host;
	unsigned from, to;
	int ret = 0, ret2;

	trace_ext3_ordered_write_end(inode, pos, len, copied);
	copied = block_write_end(file, mapping, pos, len, copied, page, fsdata);

	from = pos & (PAGE_CACHE_SIZE - 1);
	to = from + copied;
	ret = walk_page_buffers(handle, page_buffers(page),
		from, to, NULL, journal_dirty_data_fn);

	if (ret == 0)
		update_file_sizes(inode, pos, copied);
	/*
	 * There may be allocated blocks outside of i_size because
	 * we failed to copy some data. Prepare for truncate.
	 */
	if (pos + len > inode->i_size && ext3_can_truncate(inode))
		ext3_orphan_add(handle, inode);
	ret2 = ext3_journal_stop(handle);
	if (!ret)
		ret = ret2;
	unlock_page(page);
	page_cache_release(page);

	if (pos + len > inode->i_size)
		ext3_truncate_failed_write(inode);
	return ret ? ret : copied;
}

static int ext3_writeback_write_end(struct file *file,
				struct address_space *mapping,
				loff_t pos, unsigned len, unsigned copied,
				struct page *page, void *fsdata)
{
	handle_t *handle = ext3_journal_current_handle();
	struct inode *inode = file->f_mapping->host;
	int ret;

	trace_ext3_writeback_write_end(inode, pos, len, copied);
	copied = block_write_end(file, mapping, pos, len, copied, page, fsdata);
	update_file_sizes(inode, pos, copied);
	/*
	 * There may be allocated blocks outside of i_size because
	 * we failed to copy some data. Prepare for truncate.
	 */
	if (pos + len > inode->i_size && ext3_can_truncate(inode))
		ext3_orphan_add(handle, inode);
	ret = ext3_journal_stop(handle);
	unlock_page(page);
	page_cache_release(page);

	if (pos + len > inode->i_size)
		ext3_truncate_failed_write(inode);
	return ret ? ret : copied;
}

static int ext3_journalled_write_end(struct file *file,
				struct address_space *mapping,
				loff_t pos, unsigned len, unsigned copied,
				struct page *page, void *fsdata)
{
	handle_t *handle = ext3_journal_current_handle();
	struct inode *inode = mapping->host;
	struct ext3_inode_info *ei = EXT3_I(inode);
	int ret = 0, ret2;
	int partial = 0;
	unsigned from, to;

	trace_ext3_journalled_write_end(inode, pos, len, copied);
	from = pos & (PAGE_CACHE_SIZE - 1);
	to = from + len;

	if (copied < len) {
		if (!PageUptodate(page))
			copied = 0;
		page_zero_new_buffers(page, from + copied, to);
		to = from + copied;
	}

	ret = walk_page_buffers(handle, page_buffers(page), from,
				to, &partial, write_end_fn);
	if (!partial)
		SetPageUptodate(page);

	if (pos + copied > inode->i_size)
		i_size_write(inode, pos + copied);
	/*
	 * There may be allocated blocks outside of i_size because
	 * we failed to copy some data. Prepare for truncate.
	 */
	if (pos + len > inode->i_size && ext3_can_truncate(inode))
		ext3_orphan_add(handle, inode);
	ext3_set_inode_state(inode, EXT3_STATE_JDATA);
	atomic_set(&ei->i_datasync_tid, handle->h_transaction->t_tid);
	if (inode->i_size > ei->i_disksize) {
		ei->i_disksize = inode->i_size;
		ret2 = ext3_mark_inode_dirty(handle, inode);
		if (!ret)
			ret = ret2;
	}

	ret2 = ext3_journal_stop(handle);
	if (!ret)
		ret = ret2;
	unlock_page(page);
	page_cache_release(page);

	if (pos + len > inode->i_size)
		ext3_truncate_failed_write(inode);
	return ret ? ret : copied;
}

/*
 * bmap() is special.  It gets used by applications such as lilo and by
 * the swapper to find the on-disk block of a specific piece of data.
 *
 * Naturally, this is dangerous if the block concerned is still in the
 * journal.  If somebody makes a swapfile on an ext3 data-journaling
 * filesystem and enables swap, then they may get a nasty shock when the
 * data getting swapped to that swapfile suddenly gets overwritten by
 * the original zero's written out previously to the journal and
 * awaiting writeback in the kernel's buffer cache.
 *
 * So, if we see any bmap calls here on a modified, data-journaled file,
 * take extra steps to flush any blocks which might be in the cache.
 */
static sector_t ext3_bmap(struct address_space *mapping, sector_t block)
{
	struct inode *inode = mapping->host;
	journal_t *journal;
	int err;

	if (ext3_test_inode_state(inode, EXT3_STATE_JDATA)) {
		/*
		 * This is a REALLY heavyweight approach, but the use of
		 * bmap on dirty files is expected to be extremely rare:
		 * only if we run lilo or swapon on a freshly made file
		 * do we expect this to happen.
		 *
		 * (bmap requires CAP_SYS_RAWIO so this does not
		 * represent an unprivileged user DOS attack --- we'd be
		 * in trouble if mortal users could trigger this path at
		 * will.)
		 *
		 * NB. EXT3_STATE_JDATA is not set on files other than
		 * regular files.  If somebody wants to bmap a directory
		 * or symlink and gets confused because the buffer
		 * hasn't yet been flushed to disk, they deserve
		 * everything they get.
		 */

		ext3_clear_inode_state(inode, EXT3_STATE_JDATA);
		journal = EXT3_JOURNAL(inode);
		journal_lock_updates(journal);
		err = journal_flush(journal);
		journal_unlock_updates(journal);

		if (err)
			return 0;
	}

	return generic_block_bmap(mapping,block,ext3_get_block);
}

static int bget_one(handle_t *handle, struct buffer_head *bh)
{
	get_bh(bh);
	return 0;
}

static int bput_one(handle_t *handle, struct buffer_head *bh)
{
	put_bh(bh);
	return 0;
}

static int buffer_unmapped(handle_t *handle, struct buffer_head *bh)
{
	return !buffer_mapped(bh);
}

/*
 * Note that we always start a transaction even if we're not journalling
 * data.  This is to preserve ordering: any hole instantiation within
 * __block_write_full_page -> ext3_get_block() should be journalled
 * along with the data so we don't crash and then get metadata which
 * refers to old data.
 *
 * In all journalling modes block_write_full_page() will start the I/O.
 *
 * Problem:
 *
 *	ext3_writepage() -> kmalloc() -> __alloc_pages() -> page_launder() ->
 *		ext3_writepage()
 *
 * Similar for:
 *
 *	ext3_file_write() -> generic_file_write() -> __alloc_pages() -> ...
 *
 * Same applies to ext3_get_block().  We will deadlock on various things like
 * lock_journal and i_truncate_mutex.
 *
 * Setting PF_MEMALLOC here doesn't work - too many internal memory
 * allocations fail.
 *
 * 16May01: If we're reentered then journal_current_handle() will be
 *	    non-zero. We simply *return*.
 *
 * 1 July 2001: @@@ FIXME:
 *   In journalled data mode, a data buffer may be metadata against the
 *   current transaction.  But the same file is part of a shared mapping
 *   and someone does a writepage() on it.
 *
 *   We will move the buffer onto the async_data list, but *after* it has
 *   been dirtied. So there's a small window where we have dirty data on
 *   BJ_Metadata.
 *
 *   Note that this only applies to the last partial page in the file.  The
 *   bit which block_write_full_page() uses prepare/commit for.  (That's
 *   broken code anyway: it's wrong for msync()).
 *
 *   It's a rare case: affects the final partial page, for journalled data
 *   where the file is subject to bith write() and writepage() in the same
 *   transction.  To fix it we'll need a custom block_write_full_page().
 *   We'll probably need that anyway for journalling writepage() output.
 *
 * We don't honour synchronous mounts for writepage().  That would be
 * disastrous.  Any write() or metadata operation will sync the fs for
 * us.
 *
 * AKPM2: if all the page's buffers are mapped to disk and !data=journal,
 * we don't need to open a transaction here.
 */
static int ext3_ordered_writepage(struct page *page,
				struct writeback_control *wbc)
{
	struct inode *inode = page->mapping->host;
	struct buffer_head *page_bufs;
	handle_t *handle = NULL;
	int ret = 0;
	int err;

	J_ASSERT(PageLocked(page));
	WARN_ON_ONCE(IS_RDONLY(inode));

	/*
	 * We give up here if we're reentered, because it might be for a
	 * different filesystem.
	 */
	if (ext3_journal_current_handle())
		goto out_fail;

	trace_ext3_ordered_writepage(page);
	if (!page_has_buffers(page)) {
		create_empty_buffers(page, inode->i_sb->s_blocksize,
				(1 << BH_Dirty)|(1 << BH_Uptodate));
		page_bufs = page_buffers(page);
	} else {
		page_bufs = page_buffers(page);
		if (!walk_page_buffers(NULL, page_bufs, 0, PAGE_CACHE_SIZE,
				       NULL, buffer_unmapped)) {
			/* Provide NULL get_block() to