inode.c

/*
 *  linux/fs/ext4/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 ext4_get_block() by Al Viro, 2000
 */

#include <linux/module.h>
#include <linux/fs.h>
#include <linux/time.h>
#include <linux/jbd2.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/pagevec.h>
#include <linux/mpage.h>
#include <linux/namei.h>
#include <linux/uio.h>
#include <linux/bio.h>
#include <linux/workqueue.h>

#include "ext4_jbd2.h"
#include "xattr.h"
#include "acl.h"
#include "ext4_extents.h"

#include <trace/events/ext4.h>

#define MPAGE_DA_EXTENT_TAIL 0x01

static inline int ext4_begin_ordered_truncate(struct inode *inode,
					      loff_t new_size)
{
	return jbd2_journal_begin_ordered_truncate(
					EXT4_SB(inode->i_sb)->s_journal,
					&EXT4_I(inode)->jinode,
					new_size);
}

static void ext4_invalidatepage(struct page *page, unsigned long offset);

/*
 * Test whether an inode is a fast symlink.
 */
static int ext4_inode_is_fast_symlink(struct inode *inode)
{
	int ea_blocks = EXT4_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 ext4 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.
 *
 * If the handle isn't valid we're not journaling, but we still need to
 * call into ext4_journal_revoke() to put the buffer head.
 */
int ext4_forget(handle_t *handle, int is_metadata, struct inode *inode,
		struct buffer_head *bh, ext4_fsblk_t blocknr)
{
	int err;

	might_sleep();

	BUFFER_TRACE(bh, "enter");

	jbd_debug(4, "forgetting bh %p: is_metadata = %d, mode %o, "
		  "data mode %x\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) == EXT4_MOUNT_JOURNAL_DATA ||
	    (!is_metadata && !ext4_should_journal_data(inode))) {
		if (bh) {
			BUFFER_TRACE(bh, "call jbd2_journal_forget");
			return ext4_journal_forget(handle, bh);
		}
		return 0;
	}

	/*
	 * data!=journal && (is_metadata || should_journal_data(inode))
	 */
	BUFFER_TRACE(bh, "call ext4_journal_revoke");
	err = ext4_journal_revoke(handle, blocknr, bh);
	if (err)
		ext4_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)
{
	ext4_lblk_t 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 ext4 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 > EXT4_MAX_TRANS_DATA)
		needed = EXT4_MAX_TRANS_DATA;

	return EXT4_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 = ext4_journal_start(inode, blocks_for_truncate(inode));
	if (!IS_ERR(result))
		return result;

	ext4_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 (!ext4_handle_valid(handle))
		return 0;
	if (ext4_handle_has_enough_credits(handle, EXT4_RESERVE_TRANS_BLOCKS+1))
		return 0;
	if (!ext4_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.
 */
int ext4_truncate_restart_trans(handle_t *handle, struct inode *inode,
				 int nblocks)
{
	int ret;

	/*
	 * Drop i_data_sem to avoid deadlock with ext4_get_blocks 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 i_data_sem here.
	 */
	BUG_ON(EXT4_JOURNAL(inode) == NULL);
	jbd_debug(2, "restarting handle %p\n", handle);
	up_write(&EXT4_I(inode)->i_data_sem);
	ret = ext4_journal_restart(handle, blocks_for_truncate(inode));
	down_write(&EXT4_I(inode)->i_data_sem);
	ext4_discard_preallocations(inode);

	return ret;
}

/*
 * Called at the last iput() if i_nlink is zero.
 */
void ext4_delete_inode(struct inode *inode)
{
	handle_t *handle;
	int err;

	if (ext4_should_order_data(inode))
		ext4_begin_ordered_truncate(inode, 0);
	truncate_inode_pages(&inode->i_data, 0);

	if (is_bad_inode(inode))
		goto no_delete;

	handle = ext4_journal_start(inode, blocks_for_truncate(inode)+3);
	if (IS_ERR(handle)) {
		ext4_std_error(inode->i_sb, PTR_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.
		 */
		ext4_orphan_del(NULL, inode);
		goto no_delete;
	}

	if (IS_SYNC(inode))
		ext4_handle_sync(handle);
	inode->i_size = 0;
	err = ext4_mark_inode_dirty(handle, inode);
	if (err) {
		ext4_warning(inode->i_sb, __func__,
			     "couldn't mark inode dirty (err %d)", err);
		goto stop_handle;
	}
	if (inode->i_blocks)
		ext4_truncate(inode);

	/*
	 * ext4_ext_truncate() doesn't reserve any slop when it
	 * restarts journal transactions; therefore there may not be
	 * enough credits left in the handle to remove the inode from
	 * the orphan list and set the dtime field.
	 */
	if (!ext4_handle_has_enough_credits(handle, 3)) {
		err = ext4_journal_extend(handle, 3);
		if (err > 0)
			err = ext4_journal_restart(handle, 3);
		if (err != 0) {
			ext4_warning(inode->i_sb, __func__,
				     "couldn't extend journal (err %d)", err);
		stop_handle:
			ext4_journal_stop(handle);
			goto no_delete;
		}
	}

	/*
	 * Kill off the orphan record which ext4_truncate created.
	 * AKPM: I think this can be inside the above `if'.
	 * Note that ext4_orphan_del() has to be able to cope with the
	 * deletion of a non-existent orphan - this is because we don't
	 * know if ext4_truncate() actually created an orphan record.
	 * (Well, we could do this if we need to, but heck - it works)
	 */
	ext4_orphan_del(handle, inode);
	EXT4_I(inode)->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 (ext4_mark_inode_dirty(handle, inode))
		/* If that failed, just do the required in-core inode clear. */
		clear_inode(inode);
	else
		ext4_free_inode(handle, inode);
	ext4_journal_stop(handle);
	return;
no_delete:
	clear_inode(inode);	/* We must guarantee clearing of 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;
}

/**
 *	ext4_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 ext4 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 ext4_block_to_path(struct inode *inode,
			      ext4_lblk_t i_block,
			      ext4_lblk_t offsets[4], int *boundary)
{
	int ptrs = EXT4_ADDR_PER_BLOCK(inode->i_sb);
	int ptrs_bits = EXT4_ADDR_PER_BLOCK_BITS(inode->i_sb);
	const long direct_blocks = EXT4_NDIR_BLOCKS,
		indirect_blocks = ptrs,
		double_blocks = (1 << (ptrs_bits * 2));
	int n = 0;
	int final = 0;

	if (i_block < direct_blocks) {
		offsets[n++] = i_block;
		final = direct_blocks;
	} else if ((i_block -= direct_blocks) < indirect_blocks) {
		offsets[n++] = EXT4_IND_BLOCK;
		offsets[n++] = i_block;
		final = ptrs;
	} else if ((i_block -= indirect_blocks) < double_blocks) {
		offsets[n++] = EXT4_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++] = EXT4_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 {
		ext4_warning(inode->i_sb, "ext4_block_to_path",
			     "block %lu > max in inode %lu",
			     i_block + direct_blocks +
			     indirect_blocks + double_blocks, inode->i_ino);
	}
	if (boundary)
		*boundary = final - 1 - (i_block & (ptrs - 1));
	return n;
}

static int __ext4_check_blockref(const char *function, struct inode *inode,
				 __le32 *p, unsigned int max)
{
	__le32 *bref = p;
	unsigned int blk;

	while (bref < p+max) {
		blk = le32_to_cpu(*bref++);
		if (blk &&
		    unlikely(!ext4_data_block_valid(EXT4_SB(inode->i_sb),
						    blk, 1))) {
			ext4_error(inode->i_sb, function,
				   "invalid block reference %u "
				   "in inode #%lu", blk, inode->i_ino);
			return -EIO;
		}
	}
	return 0;
}


#define ext4_check_indirect_blockref(inode, bh)                         \
	__ext4_check_blockref(__func__, inode, (__le32 *)(bh)->b_data,  \
			      EXT4_ADDR_PER_BLOCK((inode)->i_sb))

#define ext4_check_inode_blockref(inode)                                \
	__ext4_check_blockref(__func__, inode, EXT4_I(inode)->i_data,   \
			      EXT4_NDIR_BLOCKS)

/**
 *	ext4_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 reads all @depth-1 indirect blocks successfully and finds
 *	the whole chain, all way to the data (returns %NULL, *err == 0).
 *
 *      Need to be called with
 *      down_read(&EXT4_I(inode)->i_data_sem)
 */
static Indirect *ext4_get_branch(struct inode *inode, int depth,
				 ext4_lblk_t  *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, EXT4_I(inode)->i_data + *offsets);
	if (!p->key)
		goto no_block;
	while (--depth) {
		bh = sb_getblk(sb, le32_to_cpu(p->key));
		if (unlikely(!bh))
			goto failure;

		if (!bh_uptodate_or_lock(bh)) {
			if (bh_submit_read(bh) < 0) {
				put_bh(bh);
				goto failure;
			}
			/* validate block references */
			if (ext4_check_indirect_blockref(inode, bh)) {
				put_bh(bh);
				goto failure;
			}
		}

		add_chain(++p, bh, (__le32 *)bh->b_data + *++offsets);
		/* Reader: end */
		if (!p->key)
			goto no_block;
	}
	return NULL;

failure:
	*err = -EIO;
no_block:
	return p;
}

/**
 *	ext4_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 ext4_fsblk_t ext4_find_near(struct inode *inode, Indirect *ind)
{
	struct ext4_inode_info *ei = EXT4_I(inode);
	__le32 *start = ind->bh ? (__le32 *) ind->bh->b_data : ei->i_data;
	__le32 *p;
	ext4_fsblk_t bg_start;
	ext4_fsblk_t last_block;
	ext4_grpblk_t colour;
	ext4_group_t block_group;
	int flex_size = ext4_flex_bg_size(EXT4_SB(inode->i_sb));

	/* 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.
	 */
	block_group = ei->i_block_group;
	if (flex_size >= EXT4_FLEX_SIZE_DIR_ALLOC_SCHEME) {
		block_group &= ~(flex_size-1);
		if (S_ISREG(inode->i_mode))
			block_group++;
	}
	bg_start = ext4_group_first_block_no(inode->i_sb, block_group);
	last_block = ext4_blocks_count(EXT4_SB(inode->i_sb)->s_es) - 1;

	/*
	 * If we are doing delayed allocation, we don't need take
	 * colour into account.
	 */
	if (test_opt(inode->i_sb, DELALLOC))
		return bg_start;

	if (bg_start + EXT4_BLOCKS_PER_GROUP(inode->i_sb) <= last_block)
		colour = (current->pid % 16) *
			(EXT4_BLOCKS_PER_GROUP(inode->i_sb) / 16);
	else
		colour = (current->pid % 16) * ((last_block - bg_start) / 16);
	return bg_start + colour;
}

/**
 *	ext4_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.
 *	Because this is only used for non-extent files, we limit the block nr
 *	to 32 bits.
 */
static ext4_fsblk_t ext4_find_goal(struct inode *inode, ext4_lblk_t block,
				   Indirect *partial)
{
	ext4_fsblk_t goal;

	/*
	 * XXX need to get goal block from mballoc's data structures
	 */

	goal = ext4_find_near(inode, partial);
	goal = goal & EXT4_MAX_BLOCK_FILE_PHYS;
	return goal;
}

/**
 *	ext4_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 ext4_blks_to_allocate(Indirect *branch, int k, unsigned int blks,
				 int blocks_to_boundary)
{
	unsigned int 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;
}

/**
 *	ext4_alloc_blocks: multiple allocate blocks needed for a branch
 *	@indirect_blks: the number of blocks need to allocate for indirect
 *			blocks
 *
 *	@new_blocks: on return it will store the new block numbers for
 *	the indirect blocks(if needed) and the first direct block,
 *	@blks:	on return it will store the total number of allocated
 *		direct blocks
 */
static int ext4_alloc_blocks(handle_t *handle, struct inode *inode,
			     ext4_lblk_t iblock, ext4_fsblk_t goal,
			     int indirect_blks, int blks,
			     ext4_fsblk_t new_blocks[4], int *err)
{
	struct ext4_allocation_request ar;
	int target, i;
	unsigned long count = 0, blk_allocated = 0;
	int index = 0;
	ext4_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)
	 */
	/* first we try to allocate the indirect blocks */
	target = indirect_blks;
	while (target > 0) {
		count = target;
		/* allocating blocks for indirect blocks and direct blocks */
		current_block = ext4_new_meta_blocks(handle, inode,
							goal, &count, err);
		if (*err)
			goto failed_out;

		BUG_ON(current_block + count > EXT4_MAX_BLOCK_FILE_PHYS);

		target -= count;
		/* allocate blocks for indirect blocks */
		while (index < indirect_blks && count) {
			new_blocks[index++] = current_block++;
			count--;
		}
		if (count > 0) {
			/*
			 * save the new block number
			 * for the first direct block
			 */
			new_blocks[index] = current_block;
			printk(KERN_INFO "%s returned more blocks than "
						"requested\n", __func__);
			WARN_ON(1);
			break;
		}
	}

	target = blks - count ;
	blk_allocated = count;
	if (!target)
		goto allocated;
	/* Now allocate data blocks */
	memset(&ar, 0, sizeof(ar));
	ar.inode = inode;
	ar.goal = goal;
	ar.len = target;
	ar.logical = iblock;
	if (S_ISREG(inode->i_mode))
		/* enable in-core preallocation only for regular files */
		ar.flags = EXT4_MB_HINT_DATA;

	current_block = ext4_mb_new_blocks(handle, &ar, err);
	BUG_ON(current_block + ar.len > EXT4_MAX_BLOCK_FILE_PHYS);

	if (*err && (target == blks)) {
		/*
		 * if the allocation failed and we didn't allocate
		 * any blocks before
		 */
		goto failed_out;
	}
	if (!*err) {
		if (target == blks) {
			/*
			 * save the new block number
			 * for the first direct block
			 */
			new_blocks[index] = current_block;
		}
		blk_allocated += ar.len;
	}
allocated:
	/* total number of blocks allocated for direct blocks */
	ret = blk_allocated;
	*err = 0;
	return ret;
failed_out:
	for (i = 0; i < index; i++)
		ext4_free_blocks(handle, inode, new_blocks[i], 1, 0);
	return ret;
}

/**
 *	ext4_alloc_branch - allocate and set up a chain of blocks.
 *	@inode: owner
 *	@indirect_blks: number of allocated indirect blocks
 *	@blks: number of allocated direct blocks
 *	@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 ext4_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 ext4_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
 *	ext4_alloc_block() (normally -ENOSPC). Otherwise we set the chain
 *	as described above and return 0.
 */
static int ext4_alloc_branch(handle_t *handle, struct inode *inode,
			     ext4_lblk_t iblock, int indirect_blks,
			     int *blks, ext4_fsblk_t goal,
			     ext4_lblk_t *offsets, Indirect *branch)
{
	int blocksize = inode->i_sb->s_blocksize;
	int i, n = 0;
	int err = 0;
	struct buffer_head *bh;
	int num;
	ext4_fsblk_t new_blocks[4];
	ext4_fsblk_t current_block;

	num = ext4_alloc_blocks(handle, inode, iblock, 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 = ext4_journal_get_create_access(handle, bh);
		if (err) {
			/* Don't brelse(bh) here; it's done in
			 * ext4_journal_forget() below */
			unlock_buffer(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 ext4_handle_dirty_metadata");
		err = ext4_handle_dirty_metadata(handle, inode, 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 jbd2_journal_forget");
		ext4_journal_forget(handle, branch[i].bh);
	}
	for (i = 0; i < indirect_blks; i++)
		ext4_free_blocks(handle, inode, new_blocks[i], 1, 0);

	ext4_free_blocks(handle, inode, new_blocks[i], num, 0);

	return err;
}

/**
 * ext4_splice_branch - splice the allocated branch onto inode.
 * @inode: owner
 * @block: (logical) number of block we are adding
 * @chain: chain of indirect blocks (with a missing link - see
 *	ext4_alloc_branch)
 * @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 ext4_splice_branch(handle_t *handle, struct inode *inode,
			      ext4_lblk_t block, Indirect *where, int num,
			      int blks)
{
	int i;
	int err = 0;
	ext4_fsblk_t current_block;

	/*
	 * 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 = ext4_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++);
	}

	/* We are done with atomic stuff, now do the rest of housekeeping */
	/* 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->ext4_dirty_inode.
		 */
		jbd_debug(5, "splicing indirect only\n");
		BUFFER_TRACE(where->bh, "call ext4_handle_dirty_metadata");
		err = ext4_handle_dirty_metadata(handle, inode, where->bh);
		if (err)
			goto err_out;
	} else {
		/*
		 * OK, we spliced it into the inode itself on a direct block.
		 */
		ext4_mark_inode_dirty(handle, inode);
		jbd_debug(5, "splicing direct\n");
	}
	return err;

err_out:
	for (i = 1; i <= num; i++) {
		BUFFER_TRACE(where[i].bh, "call jbd2_journal_forget");
		ext4_journal_forget(handle, where[i].bh);
		ext4_free_blocks(handle, inode,
					le32_to_cpu(where[i-1].key), 1, 0);
	}
	ext4_free_blocks(handle, inode, le32_to_cpu(where[num].key), blks, 0);

	return err;
}

/*
 * The ext4_ind_get_blocks() function handles non-extents inodes
 * (i.e., using the traditional indirect/double-indirect i_blocks
 * scheme) for ext4_get_blocks().
 *
 * 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.
 *
 * return > 0, # of blocks mapped or allocated.
 * return = 0, if plain lookup failed.
 * return < 0, error case.
 *
 * The ext4_ind_get_blocks() function should be called with
 * down_write(&EXT4_I(inode)->i_data_sem) if allocating filesystem
 * blocks (i.e., flags has EXT4_GET_BLOCKS_CREATE set) or
 * down_read(&EXT4_I(inode)->i_data_sem) if not allocating file system
 * blocks.
 */
static int ext4_ind_get_blocks(handle_t *handle, struct inode *inode,
			       ext4_lblk_t iblock, unsigned int maxblocks,
			       struct buffer_head *bh_result,
			       int flags)
{
	int err = -EIO;
	ext4_lblk_t offsets[4];
	Indirect chain[4];
	Indirect *partial;
	ext4_fsblk_t goal;
	int indirect_blks;
	int blocks_to_boundary = 0;
	int depth;
	int count = 0;
	ext4_fsblk_t first_block = 0;

	J_ASSERT(!(EXT4_I(inode)->i_flags & EXT4_EXTENTS_FL));
	J_ASSERT(handle != NULL || (flags & EXT4_GET_BLOCKS_CREATE) == 0);
	depth = ext4_block_to_path(inode, iblock, offsets,
				   &blocks_to_boundary);

	if (depth == 0)
		goto out;

	partial = ext4_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) {
			ext4_fsblk_t blk;

			blk = le32_to_cpu(*(chain[depth-1].p + count));

			if (blk == first_block + count)
				count++;
			else
				break;
		}
		goto got_it;
	}

	/* Next simple case - plain lookup or failed read of indirect block */
	if ((flags & EXT4_GET_BLOCKS_CREATE) == 0 || err == -EIO)
		goto cleanup;

	/*
	 * Okay, we need to do block allocation.
	*/
	goal = ext4_find_goal(inode, iblock, partial);

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