Merge branch 'for_linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tytso/ext4

* 'for_linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tytso/ext4: (48 commits) ext4: fix hot spins in mballoc after err_freebuddy and err_freemeta ext4: fix test ext_generic_write_end() copied return value ext3: fix test ext_generic_write_end() copied return value ext4: Move mballoc headers/structures to a seperate header file mballoc.h ext4: cleanup for compiling mballoc with verification and debugging #defines ext4: don't use ext4_error in ext4_check_descriptors ext4: mark inode dirty after initializing the extent tree ext4: update ctime and mtime for truncate with extents. ext4: Don't do GFP_NOFS allocations after taking ext4_lock_group ext4: move headers out of include/linux ext4: fix wrong gfp type under transaction ext4: Fix hang on umount with quotas when journal is aborted ext4: Fix update of mtime and ctime on rename jdb2: replace remaining __FUNCTION__ occurrences ext4: replace remaining __FUNCTION__ occurrences jbd2: only create debugfs and stats entries if init is successful jbd2: fix kernel-doc notation jbd2: replace potentially false assertion with if block jbd2: eliminate duplicated code in revocation table init/destroy functions jbd2: tidy up revoke cache initialisation and destruction ...
2026-05-01 15:00:59 -07:00 · 2008-04-29 20:34:49 -07:00
parent c15a2434ed f1fa3342e2
commit c4755d16fc
38 changed files with 1090 additions and 841 deletions
@@ -1261,10 +1261,11 @@ static int ext3_ordered_write_end(struct file *file,
 		new_i_size = pos + copied;
 		if (new_i_size > EXT3_I(inode)->i_disksize)
 			EXT3_I(inode)->i_disksize = new_i_size;
-		copied = ext3_generic_write_end(file, mapping, pos, len, copied,
+		ret2 = ext3_generic_write_end(file, mapping, pos, len, copied,
 							page, fsdata);
-		if (copied < 0)
-			ret = copied;
+		copied = ret2;
+		if (ret2 < 0)
+			ret = ret2;
 	}
 	ret2 = ext3_journal_stop(handle);
 	if (!ret)
@@ -1289,10 +1290,11 @@ static int ext3_writeback_write_end(struct file *file,
 	if (new_i_size > EXT3_I(inode)->i_disksize)
 		EXT3_I(inode)->i_disksize = new_i_size;

-	copied = ext3_generic_write_end(file, mapping, pos, len, copied,
+	ret2 = ext3_generic_write_end(file, mapping, pos, len, copied,
 							page, fsdata);
-	if (copied < 0)
-		ret = copied;
+	copied = ret2;
+	if (ret2 < 0)
+		ret = ret2;

 	ret2 = ext3_journal_stop(handle);
 	if (!ret)
@@ -9,8 +9,8 @@
 #include <linux/slab.h>
 #include <linux/capability.h>
 #include <linux/fs.h>
-#include <linux/ext4_jbd2.h>
-#include <linux/ext4_fs.h>
+#include "ext4_jbd2.h"
+#include "ext4.h"
 #include "xattr.h"
 #include "acl.h"

@@ -37,7 +37,7 @@ ext4_acl_from_disk(const void *value, size_t size)
 		return ERR_PTR(-EINVAL);
 	if (count == 0)
 		return NULL;
-	acl = posix_acl_alloc(count, GFP_KERNEL);
+	acl = posix_acl_alloc(count, GFP_NOFS);
 	if (!acl)
 		return ERR_PTR(-ENOMEM);
 	for (n=0; n < count; n++) {
@@ -91,7 +91,7 @@ ext4_acl_to_disk(const struct posix_acl *acl, size_t *size)

 	*size = ext4_acl_size(acl->a_count);
 	ext_acl = kmalloc(sizeof(ext4_acl_header) + acl->a_count *
-			sizeof(ext4_acl_entry), GFP_KERNEL);
+			sizeof(ext4_acl_entry), GFP_NOFS);
 	if (!ext_acl)
 		return ERR_PTR(-ENOMEM);
 	ext_acl->a_version = cpu_to_le32(EXT4_ACL_VERSION);
@@ -187,7 +187,7 @@ ext4_get_acl(struct inode *inode, int type)
 	}
 	retval = ext4_xattr_get(inode, name_index, "", NULL, 0);
 	if (retval > 0) {
-		value = kmalloc(retval, GFP_KERNEL);
+		value = kmalloc(retval, GFP_NOFS);
 		if (!value)
 			return ERR_PTR(-ENOMEM);
 		retval = ext4_xattr_get(inode, name_index, "", value, retval);
@@ -335,7 +335,7 @@ ext4_init_acl(handle_t *handle, struct inode *inode, struct inode *dir)
 			if (error)
 				goto cleanup;
 		}
-		clone = posix_acl_clone(acl, GFP_KERNEL);
+		clone = posix_acl_clone(acl, GFP_NOFS);
 		error = -ENOMEM;
 		if (!clone)
 			goto cleanup;
@@ -15,12 +15,12 @@
 #include <linux/capability.h>
 #include <linux/fs.h>
 #include <linux/jbd2.h>
-#include <linux/ext4_fs.h>
-#include <linux/ext4_jbd2.h>
 #include <linux/quotaops.h>
 #include <linux/buffer_head.h>
-
+#include "ext4.h"
+#include "ext4_jbd2.h"
 #include "group.h"
+
 /*
 * balloc.c contains the blocks allocation and deallocation routines
 */
@@ -48,7 +48,6 @@ void ext4_get_group_no_and_offset(struct super_block *sb, ext4_fsblk_t blocknr,
 unsigned ext4_init_block_bitmap(struct super_block *sb, struct buffer_head *bh,
 		 ext4_group_t block_group, struct ext4_group_desc *gdp)
 {
-	unsigned long start;
 	int bit, bit_max;
 	unsigned free_blocks, group_blocks;
 	struct ext4_sb_info *sbi = EXT4_SB(sb);
@@ -59,7 +58,7 @@ unsigned ext4_init_block_bitmap(struct super_block *sb, struct buffer_head *bh,
 		/* If checksum is bad mark all blocks used to prevent allocation
 		 * essentially implementing a per-group read-only flag. */
 		if (!ext4_group_desc_csum_verify(sbi, block_group, gdp)) {
-			ext4_error(sb, __FUNCTION__,
+			ext4_error(sb, __func__,
 				  "Checksum bad for group %lu\n", block_group);
 			gdp->bg_free_blocks_count = 0;
 			gdp->bg_free_inodes_count = 0;
@@ -106,11 +105,12 @@ unsigned ext4_init_block_bitmap(struct super_block *sb, struct buffer_head *bh,
 	free_blocks = group_blocks - bit_max;

 	if (bh) {
+		ext4_fsblk_t start;
+
 		for (bit = 0; bit < bit_max; bit++)
 			ext4_set_bit(bit, bh->b_data);

-		start = block_group * EXT4_BLOCKS_PER_GROUP(sb) +
-			le32_to_cpu(sbi->s_es->s_first_data_block);
+		start = ext4_group_first_block_no(sb, block_group);

 		/* Set bits for block and inode bitmaps, and inode table */
 		ext4_set_bit(ext4_block_bitmap(sb, gdp) - start, bh->b_data);
@@ -235,7 +235,7 @@ static int ext4_valid_block_bitmap(struct super_block *sb,
 		return 1;

 err_out:
-	ext4_error(sb, __FUNCTION__,
+	ext4_error(sb, __func__,
 			"Invalid block bitmap - "
 			"block_group = %d, block = %llu",
 			block_group, bitmap_blk);
@@ -264,7 +264,7 @@ read_block_bitmap(struct super_block *sb, ext4_group_t block_group)
 	bitmap_blk = ext4_block_bitmap(sb, desc);
 	bh = sb_getblk(sb, bitmap_blk);
 	if (unlikely(!bh)) {
-		ext4_error(sb, __FUNCTION__,
+		ext4_error(sb, __func__,
 			    "Cannot read block bitmap - "
 			    "block_group = %d, block_bitmap = %llu",
 			    (int)block_group, (unsigned long long)bitmap_blk);
@@ -281,7 +281,7 @@ read_block_bitmap(struct super_block *sb, ext4_group_t block_group)
 	}
 	if (bh_submit_read(bh) < 0) {
 		put_bh(bh);
-		ext4_error(sb, __FUNCTION__,
+		ext4_error(sb, __func__,
 			    "Cannot read block bitmap - "
 			    "block_group = %d, block_bitmap = %llu",
 			    (int)block_group, (unsigned long long)bitmap_blk);
@@ -360,7 +360,7 @@ restart:
 		BUG();
 }
 #define rsv_window_dump(root, verbose) \
-	__rsv_window_dump((root), (verbose), __FUNCTION__)
+	__rsv_window_dump((root), (verbose), __func__)
 #else
 #define rsv_window_dump(root, verbose) do {} while (0)
 #endif
@@ -740,7 +740,7 @@ do_more:
 		if (!ext4_clear_bit_atomic(sb_bgl_lock(sbi, block_group),
 						bit + i, bitmap_bh->b_data)) {
 			jbd_unlock_bh_state(bitmap_bh);
-			ext4_error(sb, __FUNCTION__,
+			ext4_error(sb, __func__,
 				   "bit already cleared for block %llu",
 				   (ext4_fsblk_t)(block + i));
 			jbd_lock_bh_state(bitmap_bh);
@@ -752,9 +752,7 @@ do_more:
 	jbd_unlock_bh_state(bitmap_bh);

 	spin_lock(sb_bgl_lock(sbi, block_group));
-	desc->bg_free_blocks_count =
-		cpu_to_le16(le16_to_cpu(desc->bg_free_blocks_count) +
-			group_freed);
+	le16_add_cpu(&desc->bg_free_blocks_count, group_freed);
 	desc->bg_checksum = ext4_group_desc_csum(sbi, block_group, desc);
 	spin_unlock(sb_bgl_lock(sbi, block_group));
 	percpu_counter_add(&sbi->s_freeblocks_counter, count);
@@ -1798,7 +1796,7 @@ allocated:
 			if (ext4_test_bit(grp_alloc_blk+i,
 					bh2jh(bitmap_bh)->b_committed_data)) {
 				printk("%s: block was unexpectedly set in "
-					"b_committed_data\n", __FUNCTION__);
+					"b_committed_data\n", __func__);
 			}
 		}
 	}
@@ -1823,8 +1821,7 @@ allocated:
 	spin_lock(sb_bgl_lock(sbi, group_no));
 	if (gdp->bg_flags & cpu_to_le16(EXT4_BG_BLOCK_UNINIT))
 		gdp->bg_flags &= cpu_to_le16(~EXT4_BG_BLOCK_UNINIT);
-	gdp->bg_free_blocks_count =
-			cpu_to_le16(le16_to_cpu(gdp->bg_free_blocks_count)-num);
+	le16_add_cpu(&gdp->bg_free_blocks_count, -num);
 	gdp->bg_checksum = ext4_group_desc_csum(sbi, group_no, gdp);
 	spin_unlock(sb_bgl_lock(sbi, group_no));
 	percpu_counter_sub(&sbi->s_freeblocks_counter, num);
@@ -9,7 +9,7 @@

 #include <linux/buffer_head.h>
 #include <linux/jbd2.h>
-#include <linux/ext4_fs.h>
+#include "ext4.h"

 #ifdef EXT4FS_DEBUG

@@ -23,10 +23,10 @@

 #include <linux/fs.h>
 #include <linux/jbd2.h>
-#include <linux/ext4_fs.h>
 #include <linux/buffer_head.h>
 #include <linux/slab.h>
 #include <linux/rbtree.h>
+#include "ext4.h"

 static unsigned char ext4_filetype_table[] = {
 	DT_UNKNOWN, DT_REG, DT_DIR, DT_CHR, DT_BLK, DT_FIFO, DT_SOCK, DT_LNK
@@ -42,7 +42,7 @@ const struct file_operations ext4_dir_operations = {
 	.llseek		= generic_file_llseek,
 	.read		= generic_read_dir,
 	.readdir	= ext4_readdir,		/* we take BKL. needed?*/
-	.ioctl		= ext4_ioctl,		/* BKL held */
+	.unlocked_ioctl = ext4_ioctl,
 #ifdef CONFIG_COMPAT
 	.compat_ioctl	= ext4_compat_ioctl,
 #endif
@@ -0,0 +1,232 @@
+/*
+ * Copyright (c) 2003-2006, Cluster File Systems, Inc, info@clusterfs.com
+ * Written by Alex Tomas <alex@clusterfs.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public Licens
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-
+ */
+
+#ifndef _EXT4_EXTENTS
+#define _EXT4_EXTENTS
+
+#include "ext4.h"
+
+/*
+ * With AGGRESSIVE_TEST defined, the capacity of index/leaf blocks
+ * becomes very small, so index split, in-depth growing and
+ * other hard changes happen much more often.
+ * This is for debug purposes only.
+ */
+#define AGGRESSIVE_TEST_
+
+/*
+ * With EXTENTS_STATS defined, the number of blocks and extents
+ * are collected in the truncate path. They'll be shown at
+ * umount time.
+ */
+#define EXTENTS_STATS__
+
+/*
+ * If CHECK_BINSEARCH is defined, then the results of the binary search
+ * will also be checked by linear search.
+ */
+#define CHECK_BINSEARCH__
+
+/*
+ * If EXT_DEBUG is defined you can use the 'extdebug' mount option
+ * to get lots of info about what's going on.
+ */
+#define EXT_DEBUG__
+#ifdef EXT_DEBUG
+#define ext_debug(a...)		printk(a)
+#else
+#define ext_debug(a...)
+#endif
+
+/*
+ * If EXT_STATS is defined then stats numbers are collected.
+ * These number will be displayed at umount time.
+ */
+#define EXT_STATS_
+
+
+/*
+ * ext4_inode has i_block array (60 bytes total).
+ * The first 12 bytes store ext4_extent_header;
+ * the remainder stores an array of ext4_extent.
+ */
+
+/*
+ * This is the extent on-disk structure.
+ * It's used at the bottom of the tree.
+ */
+struct ext4_extent {
+	__le32	ee_block;	/* first logical block extent covers */
+	__le16	ee_len;		/* number of blocks covered by extent */
+	__le16	ee_start_hi;	/* high 16 bits of physical block */
+	__le32	ee_start_lo;	/* low 32 bits of physical block */
+};
+
+/*
+ * This is index on-disk structure.
+ * It's used at all the levels except the bottom.
+ */
+struct ext4_extent_idx {
+	__le32	ei_block;	/* index covers logical blocks from 'block' */
+	__le32	ei_leaf_lo;	/* pointer to the physical block of the next *
+				 * level. leaf or next index could be there */
+	__le16	ei_leaf_hi;	/* high 16 bits of physical block */
+	__u16	ei_unused;
+};
+
+/*
+ * Each block (leaves and indexes), even inode-stored has header.
+ */
+struct ext4_extent_header {
+	__le16	eh_magic;	/* probably will support different formats */
+	__le16	eh_entries;	/* number of valid entries */
+	__le16	eh_max;		/* capacity of store in entries */
+	__le16	eh_depth;	/* has tree real underlying blocks? */
+	__le32	eh_generation;	/* generation of the tree */
+};
+
+#define EXT4_EXT_MAGIC		cpu_to_le16(0xf30a)
+
+/*
+ * Array of ext4_ext_path contains path to some extent.
+ * Creation/lookup routines use it for traversal/splitting/etc.
+ * Truncate uses it to simulate recursive walking.
+ */
+struct ext4_ext_path {
+	ext4_fsblk_t			p_block;
+	__u16				p_depth;
+	struct ext4_extent		*p_ext;
+	struct ext4_extent_idx		*p_idx;
+	struct ext4_extent_header	*p_hdr;
+	struct buffer_head		*p_bh;
+};
+
+/*
+ * structure for external API
+ */
+
+#define EXT4_EXT_CACHE_NO	0
+#define EXT4_EXT_CACHE_GAP	1
+#define EXT4_EXT_CACHE_EXTENT	2
+
+
+#define EXT_MAX_BLOCK	0xffffffff
+
+/*
+ * EXT_INIT_MAX_LEN is the maximum number of blocks we can have in an
+ * initialized extent. This is 2^15 and not (2^16 - 1), since we use the
+ * MSB of ee_len field in the extent datastructure to signify if this
+ * particular extent is an initialized extent or an uninitialized (i.e.
+ * preallocated).
+ * EXT_UNINIT_MAX_LEN is the maximum number of blocks we can have in an
+ * uninitialized extent.
+ * If ee_len is <= 0x8000, it is an initialized extent. Otherwise, it is an
+ * uninitialized one. In other words, if MSB of ee_len is set, it is an
+ * uninitialized extent with only one special scenario when ee_len = 0x8000.
+ * In this case we can not have an uninitialized extent of zero length and
+ * thus we make it as a special case of initialized extent with 0x8000 length.
+ * This way we get better extent-to-group alignment for initialized extents.
+ * Hence, the maximum number of blocks we can have in an *initialized*
+ * extent is 2^15 (32768) and in an *uninitialized* extent is 2^15-1 (32767).
+ */
+#define EXT_INIT_MAX_LEN	(1UL << 15)
+#define EXT_UNINIT_MAX_LEN	(EXT_INIT_MAX_LEN - 1)
+
+
+#define EXT_FIRST_EXTENT(__hdr__) \
+	((struct ext4_extent *) (((char *) (__hdr__)) +		\
+				 sizeof(struct ext4_extent_header)))
+#define EXT_FIRST_INDEX(__hdr__) \
+	((struct ext4_extent_idx *) (((char *) (__hdr__)) +	\
+				     sizeof(struct ext4_extent_header)))
+#define EXT_HAS_FREE_INDEX(__path__) \
+	(le16_to_cpu((__path__)->p_hdr->eh_entries) \
+				     < le16_to_cpu((__path__)->p_hdr->eh_max))
+#define EXT_LAST_EXTENT(__hdr__) \
+	(EXT_FIRST_EXTENT((__hdr__)) + le16_to_cpu((__hdr__)->eh_entries) - 1)
+#define EXT_LAST_INDEX(__hdr__) \
+	(EXT_FIRST_INDEX((__hdr__)) + le16_to_cpu((__hdr__)->eh_entries) - 1)
+#define EXT_MAX_EXTENT(__hdr__) \
+	(EXT_FIRST_EXTENT((__hdr__)) + le16_to_cpu((__hdr__)->eh_max) - 1)
+#define EXT_MAX_INDEX(__hdr__) \
+	(EXT_FIRST_INDEX((__hdr__)) + le16_to_cpu((__hdr__)->eh_max) - 1)
+
+static inline struct ext4_extent_header *ext_inode_hdr(struct inode *inode)
+{
+	return (struct ext4_extent_header *) EXT4_I(inode)->i_data;
+}
+
+static inline struct ext4_extent_header *ext_block_hdr(struct buffer_head *bh)
+{
+	return (struct ext4_extent_header *) bh->b_data;
+}
+
+static inline unsigned short ext_depth(struct inode *inode)
+{
+	return le16_to_cpu(ext_inode_hdr(inode)->eh_depth);
+}
+
+static inline void ext4_ext_tree_changed(struct inode *inode)
+{
+	EXT4_I(inode)->i_ext_generation++;
+}
+
+static inline void
+ext4_ext_invalidate_cache(struct inode *inode)
+{
+	EXT4_I(inode)->i_cached_extent.ec_type = EXT4_EXT_CACHE_NO;
+}
+
+static inline void ext4_ext_mark_uninitialized(struct ext4_extent *ext)
+{
+	/* We can not have an uninitialized extent of zero length! */
+	BUG_ON((le16_to_cpu(ext->ee_len) & ~EXT_INIT_MAX_LEN) == 0);
+	ext->ee_len |= cpu_to_le16(EXT_INIT_MAX_LEN);
+}
+
+static inline int ext4_ext_is_uninitialized(struct ext4_extent *ext)
+{
+	/* Extent with ee_len of 0x8000 is treated as an initialized extent */
+	return (le16_to_cpu(ext->ee_len) > EXT_INIT_MAX_LEN);
+}
+
+static inline int ext4_ext_get_actual_len(struct ext4_extent *ext)
+{
+	return (le16_to_cpu(ext->ee_len) <= EXT_INIT_MAX_LEN ?
+		le16_to_cpu(ext->ee_len) :
+		(le16_to_cpu(ext->ee_len) - EXT_INIT_MAX_LEN));
+}
+
+extern ext4_fsblk_t idx_pblock(struct ext4_extent_idx *);
+extern void ext4_ext_store_pblock(struct ext4_extent *, ext4_fsblk_t);
+extern int ext4_extent_tree_init(handle_t *, struct inode *);
+extern int ext4_ext_calc_credits_for_insert(struct inode *, struct ext4_ext_path *);
+extern int ext4_ext_try_to_merge(struct inode *inode,
+				 struct ext4_ext_path *path,
+				 struct ext4_extent *);
+extern unsigned int ext4_ext_check_overlap(struct inode *, struct ext4_extent *, struct ext4_ext_path *);
+extern int ext4_ext_insert_extent(handle_t *, struct inode *, struct ext4_ext_path *, struct ext4_extent *);
+extern struct ext4_ext_path *ext4_ext_find_extent(struct inode *, ext4_lblk_t,
+							struct ext4_ext_path *);
+extern int ext4_ext_search_left(struct inode *, struct ext4_ext_path *,
+						ext4_lblk_t *, ext4_fsblk_t *);
+extern int ext4_ext_search_right(struct inode *, struct ext4_ext_path *,
+						ext4_lblk_t *, ext4_fsblk_t *);
+extern void ext4_ext_drop_refs(struct ext4_ext_path *);
+#endif /* _EXT4_EXTENTS */
+
@@ -0,0 +1,167 @@
+/*
+ *  ext4_i.h
+ *
+ * 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/include/linux/minix_fs_i.h
+ *
+ *  Copyright (C) 1991, 1992  Linus Torvalds
+ */
+
+#ifndef _EXT4_I
+#define _EXT4_I
+
+#include <linux/rwsem.h>
+#include <linux/rbtree.h>
+#include <linux/seqlock.h>
+#include <linux/mutex.h>
+
+/* data type for block offset of block group */
+typedef int ext4_grpblk_t;
+
+/* data type for filesystem-wide blocks number */
+typedef unsigned long long ext4_fsblk_t;
+
+/* data type for file logical block number */
+typedef __u32 ext4_lblk_t;
+
+/* data type for block group number */
+typedef unsigned long ext4_group_t;
+
+struct ext4_reserve_window {
+	ext4_fsblk_t	_rsv_start;	/* First byte reserved */
+	ext4_fsblk_t	_rsv_end;	/* Last byte reserved or 0 */
+};
+
+struct ext4_reserve_window_node {
+	struct rb_node		rsv_node;
+	__u32			rsv_goal_size;
+	__u32			rsv_alloc_hit;
+	struct ext4_reserve_window	rsv_window;
+};
+
+struct ext4_block_alloc_info {
+	/* information about reservation window */
+	struct ext4_reserve_window_node rsv_window_node;
+	/*
+	 * was i_next_alloc_block in ext4_inode_info
+	 * is the logical (file-relative) number of the
+	 * most-recently-allocated block in this file.
+	 * We use this for detecting linearly ascending allocation requests.
+	 */
+	ext4_lblk_t last_alloc_logical_block;
+	/*
+	 * Was i_next_alloc_goal in ext4_inode_info
+	 * is the *physical* companion to i_next_alloc_block.
+	 * it the physical block number of the block which was most-recentl
+	 * allocated to this file.  This give us the goal (target) for the next
+	 * allocation when we detect linearly ascending requests.
+	 */
+	ext4_fsblk_t last_alloc_physical_block;
+};
+
+#define rsv_start rsv_window._rsv_start
+#define rsv_end rsv_window._rsv_end
+
+/*
+ * storage for cached extent
+ */
+struct ext4_ext_cache {
+	ext4_fsblk_t	ec_start;
+	ext4_lblk_t	ec_block;
+	__u32		ec_len; /* must be 32bit to return holes */
+	__u32		ec_type;
+};
+
+/*
+ * third extended file system inode data in memory
+ */
+struct ext4_inode_info {
+	__le32	i_data[15];	/* unconverted */
+	__u32	i_flags;
+	ext4_fsblk_t	i_file_acl;
+	__u32	i_dtime;
+
+	/*
+	 * i_block_group is the number of the block group which contains
+	 * this file's inode.  Constant across the lifetime of the inode,
+	 * it is ued for making block allocation decisions - we try to
+	 * place a file's data blocks near its inode block, and new inodes
+	 * near to their parent directory's inode.
+	 */
+	ext4_group_t	i_block_group;
+	__u32	i_state;		/* Dynamic state flags for ext4 */
+
+	/* block reservation info */
+	struct ext4_block_alloc_info *i_block_alloc_info;
+
+	ext4_lblk_t		i_dir_start_lookup;
+#ifdef CONFIG_EXT4DEV_FS_XATTR
+	/*
+	 * Extended attributes can be read independently of the main file
+	 * data. Taking i_mutex even when reading would cause contention
+	 * between readers of EAs and writers of regular file data, so
+	 * instead we synchronize on xattr_sem when reading or changing
+	 * EAs.
+	 */
+	struct rw_semaphore xattr_sem;
+#endif
+#ifdef CONFIG_EXT4DEV_FS_POSIX_ACL
+	struct posix_acl	*i_acl;
+	struct posix_acl	*i_default_acl;
+#endif
+
+	struct list_head i_orphan;	/* unlinked but open inodes */
+
+	/*
+	 * i_disksize keeps track of what the inode size is ON DISK, not
+	 * in memory.  During truncate, i_size is set to the new size by
+	 * the VFS prior to calling ext4_truncate(), but the filesystem won't
+	 * set i_disksize to 0 until the truncate is actually under way.
+	 *
+	 * The intent is that i_disksize always represents the blocks which
+	 * are used by this file.  This allows recovery to restart truncate
+	 * on orphans if we crash during truncate.  We actually write i_disksize
+	 * into the on-disk inode when writing inodes out, instead of i_size.
+	 *
+	 * The only time when i_disksize and i_size may be different is when
+	 * a truncate is in progress.  The only things which change i_disksize
+	 * are ext4_get_block (growth) and ext4_truncate (shrinkth).
+	 */
+	loff_t	i_disksize;
+
+	/* on-disk additional length */
+	__u16 i_extra_isize;
+
+	/*
+	 * i_data_sem is for serialising ext4_truncate() against
+	 * ext4_getblock().  In the 2.4 ext2 design, great chunks of inode's
+	 * data tree are chopped off during truncate. We can't do that in
+	 * ext4 because whenever we perform intermediate commits during
+	 * truncate, the inode and all the metadata blocks *must* be in a
+	 * consistent state which allows truncation of the orphans to restart
+	 * during recovery.  Hence we must fix the get_block-vs-truncate race
+	 * by other means, so we have i_data_sem.
+	 */
+	struct rw_semaphore i_data_sem;
+	struct inode vfs_inode;
+
+	unsigned long i_ext_generation;
+	struct ext4_ext_cache i_cached_extent;
+	/*
+	 * File creation time. Its function is same as that of
+	 * struct timespec i_{a,c,m}time in the generic inode.
+	 */
+	struct timespec i_crtime;
+
+	/* mballoc */
+	struct list_head i_prealloc_list;
+	spinlock_t i_prealloc_lock;
+};
+
+#endif	/* _EXT4_I */
@@ -2,14 +2,14 @@
 * Interface between ext4 and JBD
 */

-#include <linux/ext4_jbd2.h>
+#include "ext4_jbd2.h"

 int __ext4_journal_get_undo_access(const char *where, handle_t *handle,
 				struct buffer_head *bh)
 {
 	int err = jbd2_journal_get_undo_access(handle, bh);
 	if (err)
-		ext4_journal_abort_handle(where, __FUNCTION__, bh, handle,err);
+		ext4_journal_abort_handle(where, __func__, bh, handle, err);
 	return err;
 }

@@ -18,7 +18,7 @@ int __ext4_journal_get_write_access(const char *where, handle_t *handle,
 {
 	int err = jbd2_journal_get_write_access(handle, bh);
 	if (err)
-		ext4_journal_abort_handle(where, __FUNCTION__, bh, handle,err);
+		ext4_journal_abort_handle(where, __func__, bh, handle, err);
 	return err;
 }

@@ -27,7 +27,7 @@ int __ext4_journal_forget(const char *where, handle_t *handle,
 {
 	int err = jbd2_journal_forget(handle, bh);
 	if (err)
-		ext4_journal_abort_handle(where, __FUNCTION__, bh, handle,err);
+		ext4_journal_abort_handle(where, __func__, bh, handle, err);
 	return err;
 }

@@ -36,7 +36,7 @@ int __ext4_journal_revoke(const char *where, handle_t *handle,
 {
 	int err = jbd2_journal_revoke(handle, blocknr, bh);
 	if (err)
-		ext4_journal_abort_handle(where, __FUNCTION__, bh, handle,err);
+		ext4_journal_abort_handle(where, __func__, bh, handle, err);
 	return err;
 }

@@ -45,7 +45,7 @@ int __ext4_journal_get_create_access(const char *where,
 {
 	int err = jbd2_journal_get_create_access(handle, bh);
 	if (err)
-		ext4_journal_abort_handle(where, __FUNCTION__, bh, handle,err);
+		ext4_journal_abort_handle(where, __func__, bh, handle, err);
 	return err;
 }

@@ -54,6 +54,6 @@ int __ext4_journal_dirty_metadata(const char *where,
 {
 	int err = jbd2_journal_dirty_metadata(handle, bh);
 	if (err)
-		ext4_journal_abort_handle(where, __FUNCTION__, bh, handle,err);
+		ext4_journal_abort_handle(where, __func__, bh, handle, err);
 	return err;
 }
@@ -0,0 +1,231 @@
+/*
+ * ext4_jbd2.h
+ *
+ * Written by Stephen C. Tweedie <sct@redhat.com>, 1999
+ *
+ * Copyright 1998--1999 Red Hat corp --- All Rights Reserved
+ *
+ * This file is part of the Linux kernel and is made available under
+ * the terms of the GNU General Public License, version 2, or at your
+ * option, any later version, incorporated herein by reference.
+ *
+ * Ext4-specific journaling extensions.
+ */
+
+#ifndef _EXT4_JBD2_H
+#define _EXT4_JBD2_H
+
+#include <linux/fs.h>
+#include <linux/jbd2.h>
+#include "ext4.h"
+
+#define EXT4_JOURNAL(inode)	(EXT4_SB((inode)->i_sb)->s_journal)
+
+/* Define the number of blocks we need to account to a transaction to
+ * modify one block of data.
+ *
+ * We may have to touch one inode, one bitmap buffer, up to three
+ * indirection blocks, the group and superblock summaries, and the data
+ * block to complete the transaction.
+ *
+ * For extents-enabled fs we may have to allocate and modify up to
+ * 5 levels of tree + root which are stored in the inode. */
+
+#define EXT4_SINGLEDATA_TRANS_BLOCKS(sb)				\
+	(EXT4_HAS_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_EXTENTS)	\
+		|| test_opt(sb, EXTENTS) ? 27U : 8U)
+
+/* Extended attribute operations touch at most two data buffers,
+ * two bitmap buffers, and two group summaries, in addition to the inode
+ * and the superblock, which are already accounted for. */
+
+#define EXT4_XATTR_TRANS_BLOCKS		6U
+
+/* Define the minimum size for a transaction which modifies data.  This
+ * needs to take into account the fact that we may end up modifying two
+ * quota files too (one for the group, one for the user quota).  The
+ * superblock only gets updated once, of course, so don't bother
+ * counting that again for the quota updates. */
+
+#define EXT4_DATA_TRANS_BLOCKS(sb)	(EXT4_SINGLEDATA_TRANS_BLOCKS(sb) + \
+					 EXT4_XATTR_TRANS_BLOCKS - 2 + \
+					 2*EXT4_QUOTA_TRANS_BLOCKS(sb))
+
+/* Delete operations potentially hit one directory's namespace plus an
+ * entire inode, plus arbitrary amounts of bitmap/indirection data.  Be
+ * generous.  We can grow the delete transaction later if necessary. */
+
+#define EXT4_DELETE_TRANS_BLOCKS(sb)	(2 * EXT4_DATA_TRANS_BLOCKS(sb) + 64)
+
+/* Define an arbitrary limit for the amount of data we will anticipate
+ * writing to any given transaction.  For unbounded transactions such as
+ * write(2) and truncate(2) we can write more than this, but we always
+ * start off at the maximum transaction size and grow the transaction
+ * optimistically as we go. */
+
+#define EXT4_MAX_TRANS_DATA		64U
+
+/* We break up a large truncate or write transaction once the handle's
+ * buffer credits gets this low, we need either to extend the
+ * transaction or to start a new one.  Reserve enough space here for
+ * inode, bitmap, superblock, group and indirection updates for at least
+ * one block, plus two quota updates.  Quota allocations are not
+ * needed. */
+
+#define EXT4_RESERVE_TRANS_BLOCKS	12U
+
+#define EXT4_INDEX_EXTRA_TRANS_BLOCKS	8
+
+#ifdef CONFIG_QUOTA
+/* Amount of blocks needed for quota update - we know that the structure was
+ * allocated so we need to update only inode+data */
+#define EXT4_QUOTA_TRANS_BLOCKS(sb) (test_opt(sb, QUOTA) ? 2 : 0)
+/* Amount of blocks needed for quota insert/delete - we do some block writes
+ * but inode, sb and group updates are done only once */
+#define EXT4_QUOTA_INIT_BLOCKS(sb) (test_opt(sb, QUOTA) ? (DQUOT_INIT_ALLOC*\
+		(EXT4_SINGLEDATA_TRANS_BLOCKS(sb)-3)+3+DQUOT_INIT_REWRITE) : 0)
+#define EXT4_QUOTA_DEL_BLOCKS(sb) (test_opt(sb, QUOTA) ? (DQUOT_DEL_ALLOC*\
+		(EXT4_SINGLEDATA_TRANS_BLOCKS(sb)-3)+3+DQUOT_DEL_REWRITE) : 0)
+#else
+#define EXT4_QUOTA_TRANS_BLOCKS(sb) 0
+#define EXT4_QUOTA_INIT_BLOCKS(sb) 0
+#define EXT4_QUOTA_DEL_BLOCKS(sb) 0
+#endif
+
+int
+ext4_mark_iloc_dirty(handle_t *handle,
+		     struct inode *inode,
+		     struct ext4_iloc *iloc);
+
+/*
+ * On success, We end up with an outstanding reference count against
+ * iloc->bh.  This _must_ be cleaned up later.
+ */
+
+int ext4_reserve_inode_write(handle_t *handle, struct inode *inode,
+			struct ext4_iloc *iloc);
+
+int ext4_mark_inode_dirty(handle_t *handle, struct inode *inode);
+
+/*
+ * Wrapper functions with which ext4 calls into JBD.  The intent here is
+ * to allow these to be turned into appropriate stubs so ext4 can control
+ * ext2 filesystems, so ext2+ext4 systems only nee one fs.  This work hasn't
+ * been done yet.
+ */
+
+static inline void ext4_journal_release_buffer(handle_t *handle,
+						struct buffer_head *bh)
+{
+	jbd2_journal_release_buffer(handle, bh);
+}
+
+void ext4_journal_abort_handle(const char *caller, const char *err_fn,
+		struct buffer_head *bh, handle_t *handle, int err);
+
+int __ext4_journal_get_undo_access(const char *where, handle_t *handle,
+				struct buffer_head *bh);
+
+int __ext4_journal_get_write_access(const char *where, handle_t *handle,
+				struct buffer_head *bh);
+
+int __ext4_journal_forget(const char *where, handle_t *handle,
+				struct buffer_head *bh);
+
+int __ext4_journal_revoke(const char *where, handle_t *handle,
+				ext4_fsblk_t blocknr, struct buffer_head *bh);
+
+int __ext4_journal_get_create_access(const char *where,
+				handle_t *handle, struct buffer_head *bh);
+
+int __ext4_journal_dirty_metadata(const char *where,
+				handle_t *handle, struct buffer_head *bh);
+
+#define ext4_journal_get_undo_access(handle, bh) \
+	__ext4_journal_get_undo_access(__FUNCTION__, (handle), (bh))
+#define ext4_journal_get_write_access(handle, bh) \
+	__ext4_journal_get_write_access(__FUNCTION__, (handle), (bh))
+#define ext4_journal_revoke(handle, blocknr, bh) \
+	__ext4_journal_revoke(__FUNCTION__, (handle), (blocknr), (bh))
+#define ext4_journal_get_create_access(handle, bh) \
+	__ext4_journal_get_create_access(__FUNCTION__, (handle), (bh))
+#define ext4_journal_dirty_metadata(handle, bh) \
+	__ext4_journal_dirty_metadata(__FUNCTION__, (handle), (bh))
+#define ext4_journal_forget(handle, bh) \
+	__ext4_journal_forget(__FUNCTION__, (handle), (bh))
+
+int ext4_journal_dirty_data(handle_t *handle, struct buffer_head *bh);
+
+handle_t *ext4_journal_start_sb(struct super_block *sb, int nblocks);
+int __ext4_journal_stop(const char *where, handle_t *handle);
+
+static inline handle_t *ext4_journal_start(struct inode *inode, int nblocks)
+{
+	return ext4_journal_start_sb(inode->i_sb, nblocks);
+}
+
+#define ext4_journal_stop(handle) \
+	__ext4_journal_stop(__FUNCTION__, (handle))
+
+static inline handle_t *ext4_journal_current_handle(void)
+{
+	return journal_current_handle();
+}
+
+static inline int ext4_journal_extend(handle_t *handle, int nblocks)
+{
+	return jbd2_journal_extend(handle, nblocks);
+}
+
+static inline int ext4_journal_restart(handle_t *handle, int nblocks)
+{
+	return jbd2_journal_restart(handle, nblocks);
+}
+
+static inline int ext4_journal_blocks_per_page(struct inode *inode)
+{
+	return jbd2_journal_blocks_per_page(inode);
+}
+
+static inline int ext4_journal_force_commit(journal_t *journal)
+{
+	return jbd2_journal_force_commit(journal);
+}
+
+/* super.c */
+int ext4_force_commit(struct super_block *sb);
+
+static inline int ext4_should_journal_data(struct inode *inode)
+{
+	if (!S_ISREG(inode->i_mode))
+		return 1;
+	if (test_opt(inode->i_sb, DATA_FLAGS) == EXT4_MOUNT_JOURNAL_DATA)
+		return 1;
+	if (EXT4_I(inode)->i_flags & EXT4_JOURNAL_DATA_FL)
+		return 1;
+	return 0;
+}
+
+static inline int ext4_should_order_data(struct inode *inode)
+{
+	if (!S_ISREG(inode->i_mode))
+		return 0;
+	if (EXT4_I(inode)->i_flags & EXT4_JOURNAL_DATA_FL)
+		return 0;
+	if (test_opt(inode->i_sb, DATA_FLAGS) == EXT4_MOUNT_ORDERED_DATA)
+		return 1;
+	return 0;
+}
+
+static inline int ext4_should_writeback_data(struct inode *inode)
+{
+	if (!S_ISREG(inode->i_mode))
+		return 0;
+	if (EXT4_I(inode)->i_flags & EXT4_JOURNAL_DATA_FL)
+		return 0;
+	if (test_opt(inode->i_sb, DATA_FLAGS) == EXT4_MOUNT_WRITEBACK_DATA)
+		return 1;
+	return 0;
+}
+
+#endif	/* _EXT4_JBD2_H */
@@ -0,0 +1,148 @@
+/*
+ *  ext4_sb.h
+ *
+ * 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/include/linux/minix_fs_sb.h
+ *
+ *  Copyright (C) 1991, 1992  Linus Torvalds
+ */
+
+#ifndef _EXT4_SB
+#define _EXT4_SB
+
+#ifdef __KERNEL__
+#include <linux/timer.h>
+#include <linux/wait.h>
+#include <linux/blockgroup_lock.h>
+#include <linux/percpu_counter.h>
+#endif
+#include <linux/rbtree.h>
+
+/*
+ * third extended-fs super-block data in memory
+ */
+struct ext4_sb_info {
+	unsigned long s_desc_size;	/* Size of a group descriptor in bytes */
+	unsigned long s_inodes_per_block;/* Number of inodes per block */
+	unsigned long s_blocks_per_group;/* Number of blocks in a group */
+	unsigned long s_inodes_per_group;/* Number of inodes in a group */
+	unsigned long s_itb_per_group;	/* Number of inode table blocks per group */
+	unsigned long s_gdb_count;	/* Number of group descriptor blocks */
+	unsigned long s_desc_per_block;	/* Number of group descriptors per block */
+	ext4_group_t s_groups_count;	/* Number of groups in the fs */
+	unsigned long s_overhead_last;  /* Last calculated overhead */
+	unsigned long s_blocks_last;    /* Last seen block count */
+	loff_t s_bitmap_maxbytes;	/* max bytes for bitmap files */
+	struct buffer_head * s_sbh;	/* Buffer containing the super block */
+	struct ext4_super_block * s_es;	/* Pointer to the super block in the buffer */
+	struct buffer_head ** s_group_desc;
+	unsigned long  s_mount_opt;
+	ext4_fsblk_t s_sb_block;
+	uid_t s_resuid;
+	gid_t s_resgid;
+	unsigned short s_mount_state;
+	unsigned short s_pad;
+	int s_addr_per_block_bits;
+	int s_desc_per_block_bits;
+	int s_inode_size;
+	int s_first_ino;
+	spinlock_t s_next_gen_lock;
+	u32 s_next_generation;
+	u32 s_hash_seed[4];
+	int s_def_hash_version;
+	struct percpu_counter s_freeblocks_counter;
+	struct percpu_counter s_freeinodes_counter;
+	struct percpu_counter s_dirs_counter;
+	struct blockgroup_lock s_blockgroup_lock;
+
+	/* root of the per fs reservation window tree */
+	spinlock_t s_rsv_window_lock;
+	struct rb_root s_rsv_window_root;
+	struct ext4_reserve_window_node s_rsv_window_head;
+
+	/* Journaling */
+	struct inode * s_journal_inode;
+	struct journal_s * s_journal;
+	struct list_head s_orphan;
+	unsigned long s_commit_interval;
+	struct block_device *journal_bdev;
+#ifdef CONFIG_JBD2_DEBUG
+	struct timer_list turn_ro_timer;	/* For turning read-only (crash simulation) */
+	wait_queue_head_t ro_wait_queue;	/* For people waiting for the fs to go read-only */
+#endif
+#ifdef CONFIG_QUOTA
+	char *s_qf_names[MAXQUOTAS];		/* Names of quota files with journalled quota */
+	int s_jquota_fmt;			/* Format of quota to use */
+#endif
+	unsigned int s_want_extra_isize; /* New inodes should reserve # bytes */
+
+#ifdef EXTENTS_STATS
+	/* ext4 extents stats */
+	unsigned long s_ext_min;
+	unsigned long s_ext_max;
+	unsigned long s_depth_max;
+	spinlock_t s_ext_stats_lock;
+	unsigned long s_ext_blocks;
+	unsigned long s_ext_extents;
+#endif
+
+	/* for buddy allocator */
+	struct ext4_group_info ***s_group_info;
+	struct inode *s_buddy_cache;
+	long s_blocks_reserved;
+	spinlock_t s_reserve_lock;
+	struct list_head s_active_transaction;
+	struct list_head s_closed_transaction;
+	struct list_head s_committed_transaction;
+	spinlock_t s_md_lock;
+	tid_t s_last_transaction;
+	unsigned short *s_mb_offsets, *s_mb_maxs;
+
+	/* tunables */
+	unsigned long s_stripe;
+	unsigned long s_mb_stream_request;
+	unsigned long s_mb_max_to_scan;
+	unsigned long s_mb_min_to_scan;
+	unsigned long s_mb_stats;
+	unsigned long s_mb_order2_reqs;
+	unsigned long s_mb_group_prealloc;
+	/* where last allocation was done - for stream allocation */
+	unsigned long s_mb_last_group;
+	unsigned long s_mb_last_start;
+
+	/* history to debug policy */
+	struct ext4_mb_history *s_mb_history;
+	int s_mb_history_cur;
+	int s_mb_history_max;
+	int s_mb_history_num;
+	struct proc_dir_entry *s_mb_proc;
+	spinlock_t s_mb_history_lock;
+	int s_mb_history_filter;
+
+	/* stats for buddy allocator */
+	spinlock_t s_mb_pa_lock;
+	atomic_t s_bal_reqs;	/* number of reqs with len > 1 */
+	atomic_t s_bal_success;	/* we found long enough chunks */
+	atomic_t s_bal_allocated;	/* in blocks */
+	atomic_t s_bal_ex_scanned;	/* total extents scanned */
+	atomic_t s_bal_goals;	/* goal hits */
+	atomic_t s_bal_breaks;	/* too long searches */
+	atomic_t s_bal_2orders;	/* 2^order hits */
+	spinlock_t s_bal_lock;
+	unsigned long s_mb_buddies_generated;
+	unsigned long long s_mb_generation_time;
+	atomic_t s_mb_lost_chunks;
+	atomic_t s_mb_preallocated;
+	atomic_t s_mb_discarded;
+
+	/* locality groups */
+	struct ext4_locality_group *s_locality_groups;
+};
+
+#endif	/* _EXT4_SB */
@@ -21,8 +21,8 @@
 #include <linux/time.h>
 #include <linux/fs.h>
 #include <linux/jbd2.h>
-#include <linux/ext4_fs.h>
-#include <linux/ext4_jbd2.h>
+#include "ext4.h"
+#include "ext4_jbd2.h"
 #include "xattr.h"
 #include "acl.h"

@@ -129,7 +129,7 @@ const struct file_operations ext4_file_operations = {
 	.write		= do_sync_write,
 	.aio_read	= generic_file_aio_read,
 	.aio_write	= ext4_file_write,
-	.ioctl		= ext4_ioctl,
+	.unlocked_ioctl = ext4_ioctl,
 #ifdef CONFIG_COMPAT
 	.compat_ioctl	= ext4_compat_ioctl,
 #endif
@@ -27,8 +27,8 @@
 #include <linux/sched.h>
 #include <linux/writeback.h>
 #include <linux/jbd2.h>
-#include <linux/ext4_fs.h>
-#include <linux/ext4_jbd2.h>
+#include "ext4.h"
+#include "ext4_jbd2.h"

 /*
 * akpm: A new design for ext4_sync_file().
@@ -72,6 +72,9 @@ int ext4_sync_file(struct file * file, struct dentry *dentry, int datasync)
 		goto out;
 	}

+	if (datasync && !(inode->i_state & I_DIRTY_DATASYNC))
+		goto out;
+
 	/*
 	 * The VFS has written the file data.  If the inode is unaltered
 	 * then we need not start a commit.
@@ -11,8 +11,8 @@

 #include <linux/fs.h>
 #include <linux/jbd2.h>
-#include <linux/ext4_fs.h>
 #include <linux/cryptohash.h>
+#include "ext4.h"

 #define DELTA 0x9E3779B9

@@ -15,8 +15,6 @@
 #include <linux/time.h>
 #include <linux/fs.h>
 #include <linux/jbd2.h>
-#include <linux/ext4_fs.h>
-#include <linux/ext4_jbd2.h>
 #include <linux/stat.h>
 #include <linux/string.h>
 #include <linux/quotaops.h>
@@ -25,7 +23,8 @@
 #include <linux/bitops.h>
 #include <linux/blkdev.h>
 #include <asm/byteorder.h>
-
+#include "ext4.h"
+#include "ext4_jbd2.h"
 #include "xattr.h"
 #include "acl.h"
 #include "group.h"
@@ -75,7 +74,7 @@ unsigned ext4_init_inode_bitmap(struct super_block *sb, struct buffer_head *bh,
 	/* If checksum is bad mark all blocks and inodes use to prevent
 	 * allocation, essentially implementing a per-group read-only flag. */
 	if (!ext4_group_desc_csum_verify(sbi, block_group, gdp)) {
-		ext4_error(sb, __FUNCTION__, "Checksum bad for group %lu\n",
+		ext4_error(sb, __func__, "Checksum bad for group %lu\n",
 			   block_group);
 		gdp->bg_free_blocks_count = 0;
 		gdp->bg_free_inodes_count = 0;
@@ -223,11 +222,9 @@ void ext4_free_inode (handle_t *handle, struct inode * inode)

 		if (gdp) {
 			spin_lock(sb_bgl_lock(sbi, block_group));
-			gdp->bg_free_inodes_count = cpu_to_le16(
-				le16_to_cpu(gdp->bg_free_inodes_count) + 1);
+			le16_add_cpu(&gdp->bg_free_inodes_count, 1);
 			if (is_directory)
-				gdp->bg_used_dirs_count = cpu_to_le16(
-				  le16_to_cpu(gdp->bg_used_dirs_count) - 1);
+				le16_add_cpu(&gdp->bg_used_dirs_count, -1);
 			gdp->bg_checksum = ext4_group_desc_csum(sbi,
 							block_group, gdp);
 			spin_unlock(sb_bgl_lock(sbi, block_group));
@@ -588,7 +585,7 @@ got:
 	ino++;
 	if ((group == 0 && ino < EXT4_FIRST_INO(sb)) ||
 	    ino > EXT4_INODES_PER_GROUP(sb)) {
-		ext4_error(sb, __FUNCTION__,
+		ext4_error(sb, __func__,
 			   "reserved inode or inode > inodes count - "
 			   "block_group = %lu, inode=%lu", group,
 			   ino + group * EXT4_INODES_PER_GROUP(sb));
@@ -664,11 +661,9 @@ got:
 				cpu_to_le16(EXT4_INODES_PER_GROUP(sb) - ino);
 	}

-	gdp->bg_free_inodes_count =
-		cpu_to_le16(le16_to_cpu(gdp->bg_free_inodes_count) - 1);
+	le16_add_cpu(&gdp->bg_free_inodes_count, -1);
 	if (S_ISDIR(mode)) {
-		gdp->bg_used_dirs_count =
-			cpu_to_le16(le16_to_cpu(gdp->bg_used_dirs_count) + 1);
+		le16_add_cpu(&gdp->bg_used_dirs_count, 1);
 	}
 	gdp->bg_checksum = ext4_group_desc_csum(sbi, group, gdp);
 	spin_unlock(sb_bgl_lock(sbi, group));
@@ -744,23 +739,24 @@ got:
 	if (err)
 		goto fail_free_drop;

-	err = ext4_mark_inode_dirty(handle, inode);
-	if (err) {
-		ext4_std_error(sb, err);
-		goto fail_free_drop;
-	}
 	if (test_opt(sb, EXTENTS)) {
-		/* set extent flag only for directory and file */
-		if (S_ISDIR(mode) || S_ISREG(mode)) {
+		/* set extent flag only for diretory, file and normal symlink*/
+		if (S_ISDIR(mode) || S_ISREG(mode) || S_ISLNK(mode)) {
 			EXT4_I(inode)->i_flags |= EXT4_EXTENTS_FL;
 			ext4_ext_tree_init(handle, inode);
 			err = ext4_update_incompat_feature(handle, sb,
 					EXT4_FEATURE_INCOMPAT_EXTENTS);
 			if (err)
-				goto fail;
+				goto fail_free_drop;
 		}
 	}

+	err = ext4_mark_inode_dirty(handle, inode);
+	if (err) {
+		ext4_std_error(sb, err);
+		goto fail_free_drop;
+	}
+
 	ext4_debug("allocating inode %lu\n", inode->i_ino);
 	goto really_out;
 fail:
@@ -796,7 +792,7 @@ struct inode *ext4_orphan_get(struct super_block *sb, unsigned long ino)

 	/* Error cases - e2fsck has already cleaned up for us */
 	if (ino > max_ino) {
-		ext4_warning(sb, __FUNCTION__,
+		ext4_warning(sb, __func__,
 			     "bad orphan ino %lu!  e2fsck was run?", ino);
 		goto error;
 	}
@@ -805,7 +801,7 @@ struct inode *ext4_orphan_get(struct super_block *sb, unsigned long ino)
 	bit = (ino - 1) % EXT4_INODES_PER_GROUP(sb);
 	bitmap_bh = read_inode_bitmap(sb, block_group);
 	if (!bitmap_bh) {
-		ext4_warning(sb, __FUNCTION__,
+		ext4_warning(sb, __func__,
 			     "inode bitmap error for orphan %lu", ino);
 		goto error;
 	}
@@ -830,7 +826,7 @@ iget_failed:
 	err = PTR_ERR(inode);
 	inode = NULL;
 bad_orphan:
-	ext4_warning(sb, __FUNCTION__,
+	ext4_warning(sb, __func__,
 		     "bad orphan inode %lu!  e2fsck was run?", ino);
 	printk(KERN_NOTICE "ext4_test_bit(bit=%d, block=%llu) = %d\n",
 	       bit, (unsigned long long)bitmap_bh->b_blocknr,
@@ -25,7 +25,6 @@
 #include <linux/module.h>
 #include <linux/fs.h>
 #include <linux/time.h>
-#include <linux/ext4_jbd2.h>
 #include <linux/jbd2.h>
 #include <linux/highuid.h>
 #include <linux/pagemap.h>
@@ -36,6 +35,7 @@
 #include <linux/mpage.h>
 #include <linux/uio.h>
 #include <linux/bio.h>
+#include "ext4_jbd2.h"
 #include "xattr.h"
 #include "acl.h"

@@ -93,7 +93,7 @@ int ext4_forget(handle_t *handle, int is_metadata, struct inode *inode,
 	BUFFER_TRACE(bh, "call ext4_journal_revoke");
 	err = ext4_journal_revoke(handle, blocknr, bh);
 	if (err)
-		ext4_abort(inode->i_sb, __FUNCTION__,
+		ext4_abort(inode->i_sb, __func__,
 			   "error %d when attempting revoke", err);
 	BUFFER_TRACE(bh, "exit");
 	return err;
@@ -985,6 +985,16 @@ int ext4_get_blocks_wrap(handle_t *handle, struct inode *inode, sector_t block,
 	} else {
 		retval = ext4_get_blocks_handle(handle, inode, block,
 				max_blocks, bh, create, extend_disksize);
+
+		if (retval > 0 && buffer_new(bh)) {
+			/*
+			 * We allocated new blocks which will result in
+			 * i_data's format changing.  Force the migrate
+			 * to fail by clearing migrate flags
+			 */
+			EXT4_I(inode)->i_flags = EXT4_I(inode)->i_flags &
+							~EXT4_EXT_MIGRATE;
+		}
 	}
 	up_write((&EXT4_I(inode)->i_data_sem));
 	return retval;
@@ -1230,7 +1240,7 @@ int ext4_journal_dirty_data(handle_t *handle, struct buffer_head *bh)
 {
 	int err = jbd2_journal_dirty_data(handle, bh);
 	if (err)
-		ext4_journal_abort_handle(__FUNCTION__, __FUNCTION__,
+		ext4_journal_abort_handle(__func__, __func__,
 						bh, handle, err);
 	return err;
 }
@@ -1301,10 +1311,11 @@ static int ext4_ordered_write_end(struct file *file,
 		new_i_size = pos + copied;
 		if (new_i_size > EXT4_I(inode)->i_disksize)
 			EXT4_I(inode)->i_disksize = new_i_size;
-		copied = ext4_generic_write_end(file, mapping, pos, len, copied,
+		ret2 = ext4_generic_write_end(file, mapping, pos, len, copied,
 							page, fsdata);
-		if (copied < 0)
-			ret = copied;
+		copied = ret2;
+		if (ret2 < 0)
+			ret = ret2;
 	}
 	ret2 = ext4_journal_stop(handle);
 	if (!ret)
@@ -1329,10 +1340,11 @@ static int ext4_writeback_write_end(struct file *file,
 	if (new_i_size > EXT4_I(inode)->i_disksize)
 		EXT4_I(inode)->i_disksize = new_i_size;

-	copied = ext4_generic_write_end(file, mapping, pos, len, copied,
+	ret2 = ext4_generic_write_end(file, mapping, pos, len, copied,
 							page, fsdata);
-	if (copied < 0)
-		ret = copied;
+	copied = ret2;
+	if (ret2 < 0)
+		ret = ret2;

 	ret2 = ext4_journal_stop(handle);
 	if (!ret)
@@ -2501,12 +2513,10 @@ out_stop:
 static ext4_fsblk_t ext4_get_inode_block(struct super_block *sb,
 		unsigned long ino, struct ext4_iloc *iloc)
 {
-	unsigned long desc, group_desc;
 	ext4_group_t block_group;
 	unsigned long offset;
 	ext4_fsblk_t block;
-	struct buffer_head *bh;
-	struct ext4_group_desc * gdp;
+	struct ext4_group_desc *gdp;

 	if (!ext4_valid_inum(sb, ino)) {
 		/*
@@ -2518,22 +2528,10 @@ static ext4_fsblk_t ext4_get_inode_block(struct super_block *sb,
 	}

 	block_group = (ino - 1) / EXT4_INODES_PER_GROUP(sb);
-	if (block_group >= EXT4_SB(sb)->s_groups_count) {
-		ext4_error(sb,"ext4_get_inode_block","group >= groups count");
+	gdp = ext4_get_group_desc(sb, block_group, NULL);
+	if (!gdp)
 		return 0;
-	}
-	smp_rmb();
-	group_desc = block_group >> EXT4_DESC_PER_BLOCK_BITS(sb);
-	desc = block_group & (EXT4_DESC_PER_BLOCK(sb) - 1);
-	bh = EXT4_SB(sb)->s_group_desc[group_desc];
-	if (!bh) {
-		ext4_error (sb, "ext4_get_inode_block",
-			    "Descriptor not loaded");
-		return 0;
-	}

-	gdp = (struct ext4_group_desc *)((__u8 *)bh->b_data +
-		desc * EXT4_DESC_SIZE(sb));
 	/*
 	 * Figure out the offset within the block group inode table
 	 */
@@ -2976,7 +2974,8 @@ static int ext4_do_update_inode(handle_t *handle,
 	if (ext4_inode_blocks_set(handle, raw_inode, ei))
 		goto out_brelse;
 	raw_inode->i_dtime = cpu_to_le32(ei->i_dtime);
-	raw_inode->i_flags = cpu_to_le32(ei->i_flags);
+	/* clear the migrate flag in the raw_inode */
+	raw_inode->i_flags = cpu_to_le32(ei->i_flags & ~EXT4_EXT_MIGRATE);
 	if (EXT4_SB(inode->i_sb)->s_es->s_creator_os !=
 	    cpu_to_le32(EXT4_OS_HURD))
 		raw_inode->i_file_acl_high =
@@ -3374,7 +3373,7 @@ int ext4_mark_inode_dirty(handle_t *handle, struct inode *inode)
 				EXT4_I(inode)->i_state |= EXT4_STATE_NO_EXPAND;
 				if (mnt_count !=
 					le16_to_cpu(sbi->s_es->s_mnt_count)) {
-					ext4_warning(inode->i_sb, __FUNCTION__,
+					ext4_warning(inode->i_sb, __func__,
 					"Unable to expand inode %lu. Delete"
 					" some EAs or run e2fsck.",
 					inode->i_ino);
@@ -3415,7 +3414,7 @@ void ext4_dirty_inode(struct inode *inode)
 		current_handle->h_transaction != handle->h_transaction) {
 		/* This task has a transaction open against a different fs */
 		printk(KERN_EMERG "%s: transactions do not match!\n",
-		       __FUNCTION__);
+		       __func__);
 	} else {
 		jbd_debug(5, "marking dirty.  outer handle=%p\n",
 				current_handle);
@@ -10,17 +10,17 @@
 #include <linux/fs.h>
 #include <linux/jbd2.h>
 #include <linux/capability.h>
-#include <linux/ext4_fs.h>
-#include <linux/ext4_jbd2.h>
 #include <linux/time.h>
 #include <linux/compat.h>
 #include <linux/smp_lock.h>
 #include <linux/mount.h>
 #include <asm/uaccess.h>
+#include "ext4_jbd2.h"
+#include "ext4.h"

-int ext4_ioctl (struct inode * inode, struct file * filp, unsigned int cmd,
-		unsigned long arg)
+long ext4_ioctl(struct file *filp, unsigned int cmd, unsigned long arg)
 {
+	struct inode *inode = filp->f_dentry->d_inode;
 	struct ext4_inode_info *ei = EXT4_I(inode);
 	unsigned int flags;
 	unsigned short rsv_window_size;
@@ -277,9 +277,6 @@ setversion_out:
 #ifdef CONFIG_COMPAT
 long ext4_compat_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
 {
-	struct inode *inode = file->f_path.dentry->d_inode;
-	int ret;
-
 	/* These are just misnamed, they actually get/put from/to user an int */
 	switch (cmd) {
 	case EXT4_IOC32_GETFLAGS:
@@ -319,9 +316,6 @@ long ext4_compat_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
 	default:
 		return -ENOIOCTLCMD;
 	}
-	lock_kernel();
-	ret = ext4_ioctl(inode, file, cmd, (unsigned long) compat_ptr(arg));
-	unlock_kernel();
-	return ret;
+	return ext4_ioctl(file, cmd, (unsigned long) compat_ptr(arg));
 }
 #endif
@@ -0,0 +1,304 @@
+/*
+ *  fs/ext4/mballoc.h
+ *
+ *  Written by: Alex Tomas <alex@clusterfs.com>
+ *
+ */
+#ifndef _EXT4_MBALLOC_H
+#define _EXT4_MBALLOC_H
+
+#include <linux/time.h>
+#include <linux/fs.h>
+#include <linux/namei.h>
+#include <linux/quotaops.h>
+#include <linux/buffer_head.h>
+#include <linux/module.h>
+#include <linux/swap.h>
+#include <linux/proc_fs.h>
+#include <linux/pagemap.h>
+#include <linux/seq_file.h>
+#include <linux/version.h>
+#include "ext4_jbd2.h"
+#include "ext4.h"
+#include "group.h"
+
+/*
+ * with AGGRESSIVE_CHECK allocator runs consistency checks over
+ * structures. these checks slow things down a lot
+ */
+#define AGGRESSIVE_CHECK__
+
+/*
+ * with DOUBLE_CHECK defined mballoc creates persistent in-core
+ * bitmaps, maintains and uses them to check for double allocations
+ */
+#define DOUBLE_CHECK__
+
+/*
+ */
+#define MB_DEBUG__
+#ifdef MB_DEBUG
+#define mb_debug(fmt, a...)	printk(fmt, ##a)
+#else
+#define mb_debug(fmt, a...)
+#endif
+
+/*
+ * with EXT4_MB_HISTORY mballoc stores last N allocations in memory
+ * and you can monitor it in /proc/fs/ext4/<dev>/mb_history
+ */
+#define EXT4_MB_HISTORY
+#define EXT4_MB_HISTORY_ALLOC		1	/* allocation */
+#define EXT4_MB_HISTORY_PREALLOC	2	/* preallocated blocks used */
+#define EXT4_MB_HISTORY_DISCARD		4	/* preallocation discarded */
+#define EXT4_MB_HISTORY_FREE		8	/* free */
+
+#define EXT4_MB_HISTORY_DEFAULT		(EXT4_MB_HISTORY_ALLOC | \
+					 EXT4_MB_HISTORY_PREALLOC)
+
+/*
+ * How long mballoc can look for a best extent (in found extents)
+ */
+#define MB_DEFAULT_MAX_TO_SCAN		200
+
+/*
+ * How long mballoc must look for a best extent
+ */
+#define MB_DEFAULT_MIN_TO_SCAN		10
+
+/*
+ * How many groups mballoc will scan looking for the best chunk
+ */
+#define MB_DEFAULT_MAX_GROUPS_TO_SCAN	5
+
+/*
+ * with 'ext4_mb_stats' allocator will collect stats that will be
+ * shown at umount. The collecting costs though!
+ */
+#define MB_DEFAULT_STATS		1
+
+/*
+ * files smaller than MB_DEFAULT_STREAM_THRESHOLD are served
+ * by the stream allocator, which purpose is to pack requests
+ * as close each to other as possible to produce smooth I/O traffic
+ * We use locality group prealloc space for stream request.
+ * We can tune the same via /proc/fs/ext4/<parition>/stream_req
+ */
+#define MB_DEFAULT_STREAM_THRESHOLD	16	/* 64K */
+
+/*
+ * for which requests use 2^N search using buddies
+ */
+#define MB_DEFAULT_ORDER2_REQS		2
+
+/*
+ * default group prealloc size 512 blocks
+ */
+#define MB_DEFAULT_GROUP_PREALLOC	512
+
+static struct kmem_cache *ext4_pspace_cachep;
+static struct kmem_cache *ext4_ac_cachep;
+
+#ifdef EXT4_BB_MAX_BLOCKS
+#undef EXT4_BB_MAX_BLOCKS
+#endif
+#define EXT4_BB_MAX_BLOCKS	30
+
+struct ext4_free_metadata {
+	ext4_group_t group;
+	unsigned short num;
+	ext4_grpblk_t  blocks[EXT4_BB_MAX_BLOCKS];
+	struct list_head list;
+};
+
+struct ext4_group_info {
+	unsigned long	bb_state;
+	unsigned long	bb_tid;
+	struct ext4_free_metadata *bb_md_cur;
+	unsigned short	bb_first_free;
+	unsigned short	bb_free;
+	unsigned short	bb_fragments;
+	struct		list_head bb_prealloc_list;
+#ifdef DOUBLE_CHECK
+	void		*bb_bitmap;
+#endif
+	unsigned short	bb_counters[];
+};
+
+#define EXT4_GROUP_INFO_NEED_INIT_BIT	0
+#define EXT4_GROUP_INFO_LOCKED_BIT	1
+
+#define EXT4_MB_GRP_NEED_INIT(grp)	\
+	(test_bit(EXT4_GROUP_INFO_NEED_INIT_BIT, &((grp)->bb_state)))
+
+
+struct ext4_prealloc_space {
+	struct list_head	pa_inode_list;
+	struct list_head	pa_group_list;
+	union {
+		struct list_head pa_tmp_list;
+		struct rcu_head	pa_rcu;
+	} u;
+	spinlock_t		pa_lock;
+	atomic_t		pa_count;
+	unsigned		pa_deleted;
+	ext4_fsblk_t		pa_pstart;	/* phys. block */
+	ext4_lblk_t		pa_lstart;	/* log. block */
+	unsigned short		pa_len;		/* len of preallocated chunk */
+	unsigned short		pa_free;	/* how many blocks are free */
+	unsigned short		pa_linear;	/* consumed in one direction
+						 * strictly, for grp prealloc */
+	spinlock_t		*pa_obj_lock;
+	struct inode		*pa_inode;	/* hack, for history only */
+};
+
+
+struct ext4_free_extent {
+	ext4_lblk_t fe_logical;
+	ext4_grpblk_t fe_start;
+	ext4_group_t fe_group;
+	int fe_len;
+};
+
+/*
+ * Locality group:
+ *   we try to group all related changes together
+ *   so that writeback can flush/allocate them together as well
+ */
+struct ext4_locality_group {
+	/* for allocator */
+	struct mutex		lg_mutex;	/* to serialize allocates */
+	struct list_head	lg_prealloc_list;/* list of preallocations */
+	spinlock_t		lg_prealloc_lock;
+};
+
+struct ext4_allocation_context {
+	struct inode *ac_inode;
+	struct super_block *ac_sb;
+
+	/* original request */
+	struct ext4_free_extent ac_o_ex;
+
+	/* goal request (after normalization) */
+	struct ext4_free_extent ac_g_ex;
+
+	/* the best found extent */
+	struct ext4_free_extent ac_b_ex;
+
+	/* copy of the bext found extent taken before preallocation efforts */
+	struct ext4_free_extent ac_f_ex;
+
+	/* number of iterations done. we have to track to limit searching */
+	unsigned long ac_ex_scanned;
+	__u16 ac_groups_scanned;
+	__u16 ac_found;
+	__u16 ac_tail;
+	__u16 ac_buddy;
+	__u16 ac_flags;		/* allocation hints */
+	__u8 ac_status;
+	__u8 ac_criteria;
+	__u8 ac_repeats;
+	__u8 ac_2order;		/* if request is to allocate 2^N blocks and
+				 * N > 0, the field stores N, otherwise 0 */
+	__u8 ac_op;		/* operation, for history only */
+	struct page *ac_bitmap_page;
+	struct page *ac_buddy_page;
+	struct ext4_prealloc_space *ac_pa;
+	struct ext4_locality_group *ac_lg;
+};
+
+#define AC_STATUS_CONTINUE	1
+#define AC_STATUS_FOUND		2
+#define AC_STATUS_BREAK		3
+
+struct ext4_mb_history {
+	struct ext4_free_extent orig;	/* orig allocation */
+	struct ext4_free_extent goal;	/* goal allocation */
+	struct ext4_free_extent result;	/* result allocation */
+	unsigned pid;
+	unsigned ino;
+	__u16 found;	/* how many extents have been found */
+	__u16 groups;	/* how many groups have been scanned */
+	__u16 tail;	/* what tail broke some buddy */
+	__u16 buddy;	/* buddy the tail ^^^ broke */
+	__u16 flags;
+	__u8 cr:3;	/* which phase the result extent was found at */
+	__u8 op:4;
+	__u8 merged:1;
+};
+
+struct ext4_buddy {
+	struct page *bd_buddy_page;
+	void *bd_buddy;
+	struct page *bd_bitmap_page;
+	void *bd_bitmap;
+	struct ext4_group_info *bd_info;
+	struct super_block *bd_sb;
+	__u16 bd_blkbits;
+	ext4_group_t bd_group;
+};
+#define EXT4_MB_BITMAP(e4b)	((e4b)->bd_bitmap)
+#define EXT4_MB_BUDDY(e4b)	((e4b)->bd_buddy)
+
+#ifndef EXT4_MB_HISTORY
+static inline void ext4_mb_store_history(struct ext4_allocation_context *ac)
+{
+	return;
+}
+#else
+static void ext4_mb_store_history(struct ext4_allocation_context *ac);
+#endif
+
+#define in_range(b, first, len)	((b) >= (first) && (b) <= (first) + (len) - 1)
+
+static struct proc_dir_entry *proc_root_ext4;
+struct buffer_head *read_block_bitmap(struct super_block *, ext4_group_t);
+
+static void ext4_mb_generate_from_pa(struct super_block *sb, void *bitmap,
+					ext4_group_t group);
+static void ext4_mb_poll_new_transaction(struct super_block *, handle_t *);
+static void ext4_mb_free_committed_blocks(struct super_block *);
+static void ext4_mb_return_to_preallocation(struct inode *inode,
+					struct ext4_buddy *e4b, sector_t block,
+					int count);
+static void ext4_mb_put_pa(struct ext4_allocation_context *,
+			struct super_block *, struct ext4_prealloc_space *pa);
+static int ext4_mb_init_per_dev_proc(struct super_block *sb);
+static int ext4_mb_destroy_per_dev_proc(struct super_block *sb);
+
+
+static inline void ext4_lock_group(struct super_block *sb, ext4_group_t group)
+{
+	struct ext4_group_info *grinfo = ext4_get_group_info(sb, group);
+
+	bit_spin_lock(EXT4_GROUP_INFO_LOCKED_BIT, &(grinfo->bb_state));
+}
+
+static inline void ext4_unlock_group(struct super_block *sb,
+					ext4_group_t group)
+{
+	struct ext4_group_info *grinfo = ext4_get_group_info(sb, group);
+
+	bit_spin_unlock(EXT4_GROUP_INFO_LOCKED_BIT, &(grinfo->bb_state));
+}
+
+static inline int ext4_is_group_locked(struct super_block *sb,
+					ext4_group_t group)
+{
+	struct ext4_group_info *grinfo = ext4_get_group_info(sb, group);
+
+	return bit_spin_is_locked(EXT4_GROUP_INFO_LOCKED_BIT,
+						&(grinfo->bb_state));
+}
+
+static ext4_fsblk_t ext4_grp_offs_to_block(struct super_block *sb,
+					struct ext4_free_extent *fex)
+{
+	ext4_fsblk_t block;
+
+	block = (ext4_fsblk_t) fex->fe_group * EXT4_BLOCKS_PER_GROUP(sb)
+			+ fex->fe_start
+			+ le32_to_cpu(EXT4_SB(sb)->s_es->s_first_data_block);
+	return block;
+}
+#endif
--- a/Show More
+++ b/Show More