Linux-2.6.12-rc2v2.6.12-rc2

Initial git repository build. I'm not bothering with the full history,
even though we have it. We can create a separate "historical" git
archive of that later if we want to, and in the meantime it's about
3.2GB when imported into git - space that would just make the early
git days unnecessarily complicated, when we don't have a lot of good
infrastructure for it.

Let it rip!

1 files changed, 3132 insertions, 0 deletions

diff --git a/fs/ext3/inode.c b/fs/ext3/inode.c
new file mode 100644
index 00000000000..040eb288bb1
--- /dev/null
+++ b/fs/ext3/inode.c
@@ -0,0 +1,3132 @@
+/*
+ *  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/smp_lock.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 "xattr.h"
+#include "acl.h"
+
+static int ext3_writepage_trans_blocks(struct inode *inode);
+
+/*
+ * Test whether an inode is a fast symlink.
+ */
+static inline 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,
+		       int blocknr)
+{
+	int err;
+
+	might_sleep();
+
+	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, __FUNCTION__,
+			   "error %d when attempting revoke", err);
+	BUFFER_TRACE(bh, "exit");
+	return err;
+}
+
+/*
+ * Work out how many blocks we need to progress 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 + 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 ext3_journal_test_restart(handle_t *handle, struct inode *inode)
+{
+	jbd_debug(2, "restarting handle %p\n", handle);
+	return ext3_journal_restart(handle, blocks_for_truncate(inode));
+}
+
+/*
+ * Called at the last iput() if i_nlink is zero.
+ */
+void ext3_delete_inode (struct inode * inode)
+{
+	handle_t *handle;
+
+	if (is_bad_inode(inode))
+		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 which ext3_truncate created.
+	 * AKPM: I think this can be inside the above `if'.
+	 * Note that ext3_orphan_del() has to be able to cope with the
+	 * deletion of a non-existent orphan - this is because we don't
+	 * know if ext3_truncate() actually created an orphan record.
+	 * (Well, we could do this if we need to, but heck - it works)
+	 */
+	ext3_orphan_del(handle, inode);
+	EXT3_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 (ext3_mark_inode_dirty(handle, inode))
+		/* If that failed, just do the required in-core inode clear. */
+		clear_inode(inode);
+	else
+		ext3_free_inode(handle, inode);
+	ext3_journal_stop(handle);
+	return;
+no_delete:
+	clear_inode(inode);	/* We must guarantee clearing of inode... */
+}
+
+static int ext3_alloc_block (handle_t *handle,
+			struct inode * inode, unsigned long goal, int *err)
+{
+	unsigned long result;
+
+	result = ext3_new_block(handle, inode, goal, err);
+	return result;
+}
+
+
+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 inline 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 = (i_block & (ptrs - 1)) == (final - 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 prefered 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 unsigned long 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;
+	unsigned long bg_start;
+	unsigned long 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 refered from inode itself? OK, just put it into
+	 * the same cylinder group then.
+	 */
+	bg_start = (ei->i_block_group * EXT3_BLOCKS_PER_GROUP(inode->i_sb)) +
+		le32_to_cpu(EXT3_SB(inode->i_sb)->s_es->s_first_data_block);
+	colour = (current->pid % 16) *
+			(EXT3_BLOCKS_PER_GROUP(inode->i_sb) / 16);
+	return bg_start + colour;
+}
+
+/**
+ *	ext3_find_goal - find a prefered place for allocation.
+ *	@inode: owner
+ *	@block:  block we want
+ *	@chain:  chain of indirect blocks
+ *	@partial: pointer to the last triple within a chain
+ *	@goal:	place to store the result.
+ *
+ *	Normally this function find the prefered place for block allocation,
+ *	stores it in *@goal and returns zero. If the branch had been changed
+ *	under us we return -EAGAIN.
+ */
+
+static int ext3_find_goal(struct inode *inode, long block, Indirect chain[4],
+			  Indirect *partial, unsigned long *goal)
+{
+	struct ext3_block_alloc_info *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)) {
+		*goal = block_i->last_alloc_physical_block + 1;
+		return 0;
+	}
+
+	if (verify_chain(chain, partial)) {
+		*goal = ext3_find_near(inode, partial);
+		return 0;
+	}
+	return -EAGAIN;
+}
+
+/**
+ *	ext3_alloc_branch - allocate and set up a chain of blocks.
+ *	@inode: owner
+ *	@num: depth of the chain (number of blocks to allocate)
+ *	@offsets: offsets (in the blocks) to store the pointers to next.
+ *	@branch: place to store the chain in.
+ *
+ *	This function allocates @num 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(), excpet 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 num,
+			     unsigned long goal,
+			     int *offsets,
+			     Indirect *branch)
+{
+	int blocksize = inode->i_sb->s_blocksize;
+	int n = 0, keys = 0;
+	int err = 0;
+	int i;
+	int parent = ext3_alloc_block(handle, inode, goal, &err);
+
+	branch[0].key = cpu_to_le32(parent);
+	if (parent) {
+		for (n = 1; n < num; n++) {
+			struct buffer_head *bh;
+			/* Allocate the next block */
+			int nr = ext3_alloc_block(handle, inode, parent, &err);
+			if (!nr)
+				break;
+			branch[n].key = cpu_to_le32(nr);
+			keys = n+1;
+
+			/*
+			 * 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, parent);
+			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);
+				break;
+			}
+
+			memset(bh->b_data, 0, blocksize);
+			branch[n].p = (__le32*) bh->b_data + offsets[n];
+			*branch[n].p = branch[n].key;
+			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)
+				break;
+
+			parent = nr;
+		}
+	}
+	if (n == num)
+		return 0;
+
+	/* Allocation failed, free what we already allocated */
+	for (i = 1; i < keys; i++) {
+		BUFFER_TRACE(branch[i].bh, "call journal_forget");
+		ext3_journal_forget(handle, branch[i].bh);
+	}
+	for (i = 0; i < keys; i++)
+		ext3_free_blocks(handle, inode, le32_to_cpu(branch[i].key), 1);
+	return err;
+}
+
+/**
+ *	ext3_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
+ *		ext3_alloc_branch)
+ *	@where: location of missing link
+ *	@num:   number of blocks we are adding
+ *
+ *	This function verifies that chain (up to the missing link) had not
+ *	changed, 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. Otherwise (== chain had been changed)
+ *	we free the new blocks (forgetting their buffer_heads, indeed) and
+ *	return -EAGAIN.
+ */
+
+static int ext3_splice_branch(handle_t *handle, struct inode *inode, long block,
+			      Indirect chain[4], Indirect *where, int num)
+{
+	int i;
+	int err = 0;
+	struct ext3_block_alloc_info *block_i = EXT3_I(inode)->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;
+	}
+	/* Verify that place we are splicing to is still there and vacant */
+
+	if (!verify_chain(chain, where-1) || *where->p)
+		/* Writer: end */
+		goto changed;
+
+	/* That's it */
+
+	*where->p = where->key;
+
+	/*
+	 * 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;
+		block_i->last_alloc_physical_block = le32_to_cpu(where[num-1].key);
+	}
+
+	/* We are done with atomic stuff, now do the rest of housekeeping */
+
+	inode->i_ctime = CURRENT_TIME_SEC;
+	ext3_mark_inode_dirty(handle, inode);
+
+	/* had we spliced it onto indirect block? */
+	if (where->bh) {
+		/*
+		 * akpm: 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;
+
+changed:
+	/*
+	 * AKPM: if where[i].bh isn't part of the current updating
+	 * transaction then we explode nastily.  Test this code path.
+	 */
+	jbd_debug(1, "the chain changed: try again\n");
+	err = -EAGAIN;
+
+err_out:
+	for (i = 1; i < num; i++) {
+		BUFFER_TRACE(where[i].bh, "call journal_forget");
+		ext3_journal_forget(handle, where[i].bh);
+	}
+	/* For the normal collision cleanup case, we free up the blocks.
+	 * On genuine filesystem errors we don't even think about doing
+	 * that. */
+	if (err == -EAGAIN)
+		for (i = 0; i < num; i++)
+			ext3_free_blocks(handle, inode, 
+					 le32_to_cpu(where[i].key), 1);
+	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.
+ *
+ * akpm: `handle' can be NULL if create == 0.
+ *
+ * The BKL may not be held on entry here.  Be sure to take it early.
+ */
+
+static int
+ext3_get_block_handle(handle_t *handle, struct inode *inode, sector_t iblock,
+		struct buffer_head *bh_result, int create, int extend_disksize)
+{
+	int err = -EIO;
+	int offsets[4];
+	Indirect chain[4];
+	Indirect *partial;
+	unsigned long goal;
+	int left;
+	int boundary = 0;
+	int depth = ext3_block_to_path(inode, iblock, offsets, &boundary);
+	struct ext3_inode_info *ei = EXT3_I(inode);
+
+	J_ASSERT(handle != NULL || create == 0);
+
+	if (depth == 0)
+		goto out;
+
+reread:
+	partial = ext3_get_branch(inode, depth, offsets, chain, &err);
+
+	/* Simplest case - block found, no allocation needed */
+	if (!partial) {
+		clear_buffer_new(bh_result);
+got_it:
+		map_bh(bh_result, inode->i_sb, le32_to_cpu(chain[depth-1].key));
+		if (boundary)
+			set_buffer_boundary(bh_result);
+		/* Clean up and exit */
+		partial = chain+depth-1; /* the whole chain */
+		goto cleanup;
+	}
+
+	/* Next simple case - plain lookup or failed read of indirect block */
+	if (!create || err == -EIO) {
+cleanup:
+		while (partial > chain) {
+			BUFFER_TRACE(partial->bh, "call brelse");
+			brelse(partial->bh);
+			partial--;
+		}
+		BUFFER_TRACE(bh_result, "returned");
+out:
+		return err;
+	}
+
+	/*
+	 * Indirect block might be removed by truncate while we were
+	 * reading it. Handling of that case (forget what we've got and
+	 * reread) is taken out of the main path.
+	 */
+	if (err == -EAGAIN)
+		goto changed;
+
+	goal = 0;
+	down(&ei->truncate_sem);
+
+	/* lazy 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);
+	}
+
+	if (ext3_find_goal(inode, iblock, chain, partial, &goal) < 0) {
+		up(&ei->truncate_sem);
+		goto changed;
+	}
+
+	left = (chain + depth) - partial;
+
+	/*
+	 * Block out ext3_truncate while we alter the tree
+	 */
+	err = ext3_alloc_branch(handle, inode, left, 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, chain,
+					 partial, left);
+	/* i_disksize growing is protected by truncate_sem
+	 * don't forget to protect it if you're about to implement
+	 * concurrent ext3_get_block() -bzzz */
+	if (!err && extend_disksize && inode->i_size > ei->i_disksize)
+		ei->i_disksize = inode->i_size;
+	up(&ei->truncate_sem);
+	if (err == -EAGAIN)
+		goto changed;
+	if (err)
+		goto cleanup;
+
+	set_buffer_new(bh_result);
+	goto got_it;
+
+changed:
+	while (partial > chain) {
+		jbd_debug(1, "buffer chain changed, retrying\n");
+		BUFFER_TRACE(partial->bh, "brelsing");
+		brelse(partial->bh);
+		partial--;
+	}
+	goto reread;
+}
+
+static int ext3_get_block(struct inode *inode, sector_t iblock,
+			struct buffer_head *bh_result, int create)
+{
+	handle_t *handle = NULL;
+	int ret;
+
+	if (create) {
+		handle = ext3_journal_current_handle();
+		J_ASSERT(handle != 0);
+	}
+	ret = ext3_get_block_handle(handle, inode, iblock,
+				bh_result, create, 1);
+	return ret;
+}
+
+#define DIO_CREDITS (EXT3_RESERVE_TRANS_BLOCKS + 32)
+
+static int
+ext3_direct_io_get_blocks(struct inode *inode, sector_t iblock,
+		unsigned long max_blocks, struct buffer_head *bh_result,
+		int create)
+{
+	handle_t *handle = journal_current_handle();
+	int ret = 0;
+
+	if (!handle)
+		goto get_block;		/* A read */
+
+	if (handle->h_transaction->t_state == T_LOCKED) {
+		/*
+		 * Huge direct-io writes can hold off commits for long
+		 * periods of time.  Let this commit run.
+		 */
+		ext3_journal_stop(handle);
+		handle = ext3_journal_start(inode, DIO_CREDITS);
+		if (IS_ERR(handle))
+			ret = PTR_ERR(handle);
+		goto get_block;
+	}
+
+	if (handle->h_buffer_credits <= EXT3_RESERVE_TRANS_BLOCKS) {
+		/*
+		 * Getting low on buffer credits...
+		 */
+		ret = ext3_journal_extend(handle, DIO_CREDITS);
+		if (ret > 0) {
+			/*
+			 * Couldn't extend the transaction.  Start a new one.
+			 */
+			ret = ext3_journal_restart(handle, DIO_CREDITS);
+		}
+	}
+
+get_block:
+	if (ret == 0)
+		ret = ext3_get_block_handle(handle, inode, iblock,
+					bh_result, create, 0);
+	bh_result->b_size = (1 << inode->i_blkbits);
+	return ret;
+}
+
+static int ext3_writepages_get_block(struct inode *inode, sector_t iblock,
+			struct buffer_head *bh, int create)
+{
+	return ext3_direct_io_get_blocks(inode, iblock, 1, bh, create);
+}
+
+/*
+ * `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);
+	*errp = ext3_get_block_handle(handle, inode, block, &dummy, create, 1);
+	if (!*errp && buffer_mapped(&dummy)) {
+		struct buffer_head *bh;
+		bh = sb_getblk(inode->i_sb, dummy.b_blocknr);
+		if (buffer_new(&dummy)) {
+			J_ASSERT(create != 0);
+			J_ASSERT(handle != 0);
+
+			/* 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;
+	}
+	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, 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)
+{
+	if (!buffer_mapped(bh) || buffer_freed(bh))
+		return 0;
+	return ext3_journal_get_write_access(handle, bh);
+}
+
+static int ext3_prepare_write(struct file *file, struct page *page,
+			      unsigned from, unsigned to)
+{
+	struct inode *inode = page->mapping->host;
+	int ret, needed_blocks = ext3_writepage_trans_blocks(inode);
+	handle_t *handle;
+	int retries = 0;
+
+retry:
+	handle = ext3_journal_start(inode, needed_blocks);
+	if (IS_ERR(handle)) {
+		ret = PTR_ERR(handle);
+		goto out;
+	}
+	if (test_opt(inode->i_sb, NOBH))
+		ret = nobh_prepare_write(page, from, to, ext3_get_block);
+	else
+		ret = block_prepare_write(page, from, to, ext3_get_block);
+	if (ret)
+		goto prepare_write_failed;
+
+	if (ext3_should_journal_data(inode)) {
+		ret = walk_page_buffers(handle, page_buffers(page),
+				from, to, NULL, do_journal_get_write_access);
+	}
+prepare_write_failed:
+	if (ret)
+		ext3_journal_stop(handle);
+	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(__FUNCTION__, __FUNCTION__,
+						bh, handle,err);
+	return err;
+}
+
+/* For commit_write() in data=journal mode */
+static int commit_write_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);
+}
+
+/*
+ * 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_commit_write(struct file *file, struct page *page,
+			     unsigned from, unsigned to)
+{
+	handle_t *handle = ext3_journal_current_handle();
+	struct inode *inode = page->mapping->host;
+	int ret = 0, ret2;
+
+	ret = walk_page_buffers(handle, page_buffers(page),
+		from, to, NULL, ext3_journal_dirty_data);
+
+	if (ret == 0) {
+		/*
+		 * generic_commit_write() will run mark_inode_dirty() if i_size
+		 * changes.  So let's piggyback the i_disksize mark_inode_dirty
+		 * into that.
+		 */
+		loff_t new_i_size;
+
+		new_i_size = ((loff_t)page->index << PAGE_CACHE_SHIFT) + to;