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: (61 commits)
  ext4: Documention update for new ordered mode and delayed allocation
  ext4: do not set extents feature from the kernel
  ext4: Don't allow nonextenst mount option for large filesystem
  ext4: Enable delalloc by default.
  ext4: delayed allocation i_blocks fix for stat
  ext4: fix delalloc i_disksize early update issue
  ext4: Handle page without buffers in ext4_*_writepage()
  ext4: Add ordered mode support for delalloc
  ext4: Invert lock ordering of page_lock and transaction start in delalloc
  mm: Add range_cont mode for writeback
  ext4: delayed allocation ENOSPC handling
  percpu_counter: new function percpu_counter_sum_and_set
  ext4: Add delayed allocation support in data=writeback mode
  vfs: add hooks for ext4's delayed allocation support
  jbd2: Remove data=ordered mode support using jbd buffer heads
  ext4: Use new framework for data=ordered mode in JBD2
  jbd2: Implement data=ordered mode handling via inodes
  vfs: export filemap_fdatawrite_range()
  ext4: Fix lock inversion in ext4_ext_truncate()
  ext4: Invert the locking order of page_lock and transaction start
  ...

Documentation/filesystems/ext4.txt

@@ -13,72 +13,93 @@ Mailing list: linux-ext4@vger.kernel.org
 1. Quick usage instructions:
 ===========================
 
-  - Grab updated e2fsprogs from
-    ftp://ftp.kernel.org/pub/linux/kernel/people/tytso/e2fsprogs-interim/
-    This is a patchset on top of e2fsprogs-1.39, which can be found at
+  - Compile and install the latest version of e2fsprogs (as of this
+    writing version 1.41) from:
+
+    http://sourceforge.net/project/showfiles.php?group_id=2406
+	
+	or
+
     ftp://ftp.kernel.org/pub/linux/kernel/people/tytso/e2fsprogs/
 
-  - It's still mke2fs -j /dev/hda1
+	or grab the latest git repository from:
+
+    git://git.kernel.org/pub/scm/fs/ext2/e2fsprogs.git
+
+  - Create a new filesystem using the ext4dev filesystem type:
+
+    	# mke2fs -t ext4dev /dev/hda1
+
+    Or configure an existing ext3 filesystem to support extents and set
+    the test_fs flag to indicate that it's ok for an in-development
+    filesystem to touch this filesystem:
 
-  - mount /dev/hda1 /wherever -t ext4dev
+	# tune2fs -O extents -E test_fs /dev/hda1
 
-  - To enable extents,
+    If the filesystem was created with 128 byte inodes, it can be
+    converted to use 256 byte for greater efficiency via:
 
-	mount /dev/hda1 /wherever -t ext4dev -o extents
+        # tune2fs -I 256 /dev/hda1
 
-  - The filesystem is compatible with the ext3 driver until you add a file
-    which has extents (ie: `mount -o extents', then create a file).
+    (Note: we currently do not have tools to convert an ext4dev
+    filesystem back to ext3; so please do not do try this on production
+    filesystems.)
 
-    NOTE: The "extents" mount flag is temporary.  It will soon go away and
-    extents will be enabled by the "-o extents" flag to mke2fs or tune2fs
+  - Mounting:
+
+	# mount -t ext4dev /dev/hda1 /wherever
 
   - When comparing performance with other filesystems, remember that
-    ext3/4 by default offers higher data integrity guarantees than most.  So
-    when comparing with a metadata-only journalling filesystem, use `mount -o
-    data=writeback'.  And you might as well use `mount -o nobh' too along
-    with it.  Making the journal larger than the mke2fs default often helps
-    performance with metadata-intensive workloads.
+    ext3/4 by default offers higher data integrity guarantees than most.
+    So when comparing with a metadata-only journalling filesystem, such
+    as ext3, use `mount -o data=writeback'.  And you might as well use
+    `mount -o nobh' too along with it.  Making the journal larger than
+    the mke2fs default often helps performance with metadata-intensive
+    workloads.
 
 2. Features
 ===========
 
 2.1 Currently available
 
-* ability to use filesystems > 16TB
+* ability to use filesystems > 16TB (e2fsprogs support not available yet)
 * extent format reduces metadata overhead (RAM, IO for access, transactions)
 * extent format more robust in face of on-disk corruption due to magics,
 * internal redunancy in tree
-
-2.1 Previously available, soon to be enabled by default by "mkefs.ext4":
-
-* dir_index and resize inode will be on by default
-* large inodes will be used by default for fast EAs, nsec timestamps, etc
+* improved file allocation (multi-block alloc)
+* fix 32000 subdirectory limit
+* nsec timestamps for mtime, atime, ctime, create time
+* inode version field on disk (NFSv4, Lustre)
+* reduced e2fsck time via uninit_bg feature
+* journal checksumming for robustness, performance
+* persistent file preallocation (e.g for streaming media, databases)
+* ability to pack bitmaps and inode tables into larger virtual groups via the
+  flex_bg feature
+* large file support
+* Inode allocation using large virtual block groups via flex_bg
+* delayed allocation
+* large block (up to pagesize) support
+* efficent new ordered mode in JBD2 and ext4(avoid using buffer head to force
+  the ordering)
 
 2.2 Candidate features for future inclusion
 
-There are several under discussion, whether they all make it in is
-partly a function of how much time everyone has to work on them:
+* Online defrag (patches available but not well tested)
+* reduced mke2fs time via lazy itable initialization in conjuction with
+  the uninit_bg feature (capability to do this is available in e2fsprogs
+  but a kernel thread to do lazy zeroing of unused inode table blocks
+  after filesystem is first mounted is required for safety)
 
-* improved file allocation (multi-block alloc, delayed alloc; basically done)
-* fix 32000 subdirectory limit (patch exists, needs some e2fsck work)
-* nsec timestamps for mtime, atime, ctime, create time (patch exists,
-  needs some e2fsck work)
-* inode version field on disk (NFSv4, Lustre; prototype exists)
-* reduced mke2fs/e2fsck time via uninitialized groups (prototype exists)
-* journal checksumming for robustness, performance (prototype exists)
-* persistent file preallocation (e.g for streaming media, databases)
+There are several others under discussion, whether they all make it in is
+partly a function of how much time everyone has to work on them. Features like
+metadata checksumming have been discussed and planned for a bit but no patches
+exist yet so I'm not sure they're in the near-term roadmap.
 
-Features like metadata checksumming have been discussed and planned for
-a bit but no patches exist yet so I'm not sure they're in the near-term
-roadmap.
+The big performance win will come with mballoc, delalloc and flex_bg
+grouping of bitmaps and inode tables.  Some test results available here:
 
-The big performance win will come with mballoc and delalloc.  CFS has
-been using mballoc for a few years already with Lustre, and IBM + Bull
-did a lot of benchmarking on it.  The reason it isn't in the first set of
-patches is partly a manageability issue, and partly because it doesn't
-directly affect the on-disk format (outside of much better allocation)
-so it isn't critical to get into the first round of changes.  I believe
-Alex is working on a new set of patches right now.
+ - http://www.bullopensource.org/ext4/20080530/ffsb-write-2.6.26-rc2.html
+ - http://www.bullopensource.org/ext4/20080530/ffsb-readwrite-2.6.26-rc2.html
 
 3. Options
 ==========
@@ -222,9 +243,11 @@ stripe=n		Number of filesystem blocks that mballoc will try
 			to use for allocation size and alignment. For RAID5/6
 			systems this should be the number of data
 			disks *  RAID chunk size in file system blocks.
-
+delalloc	(*)	Deferring block allocation until write-out time.
+nodelalloc		Disable delayed allocation. Blocks are allocation
+			when data is copied from user to page cache.
 Data Mode
----------
+=========
 There are 3 different data modes:
 
 * writeback mode
@@ -236,10 +259,10 @@ typically provide the best ext4 performance.
 
 * ordered mode
 In data=ordered mode, ext4 only officially journals metadata, but it logically
-groups metadata and data blocks into a single unit called a transaction.  When
-it's time to write the new metadata out to disk, the associated data blocks
-are written first.  In general, this mode performs slightly slower than
-writeback but significantly faster than journal mode.
+groups metadata information related to data changes with the data blocks into a
+single unit called a transaction.  When it's time to write the new metadata
+out to disk, the associated data blocks are written first.  In general,
+this mode performs slightly slower than writeback but significantly faster than journal mode.
 
 * journal mode
 data=journal mode provides full data and metadata journaling.  All new data is
@@ -247,7 +270,8 @@ written to the journal first, and then to its final location.
 In the event of a crash, the journal can be replayed, bringing both data and
 metadata into a consistent state.  This mode is the slowest except when data
 needs to be read from and written to disk at the same time where it
-outperforms all others modes.
+outperforms all others modes.  Curently ext4 does not have delayed
+allocation support if this data journalling mode is selected.
 
 References
 ==========
@@ -256,7 +280,8 @@ kernel source:	<file:fs/ext4/>
 		<file:fs/jbd2/>
 
 programs:	http://e2fsprogs.sourceforge.net/
-		http://ext2resize.sourceforge.net
 
 useful links:	http://fedoraproject.org/wiki/ext3-devel
 		http://www.bullopensource.org/ext4/
+		http://ext4.wiki.kernel.org/index.php/Main_Page
+		http://fedoraproject.org/wiki/Features/Ext4

fs/buffer.c

@@ -1691,11 +1691,13 @@ static int __block_write_full_page(struct inode *inode, struct page *page,
 			 */
 			clear_buffer_dirty(bh);
 			set_buffer_uptodate(bh);
-		} else if (!buffer_mapped(bh) && buffer_dirty(bh)) {
+		} else if ((!buffer_mapped(bh) || buffer_delay(bh)) &&
+			   buffer_dirty(bh)) {
 			WARN_ON(bh->b_size != blocksize);
 			err = get_block(inode, block, bh, 1);
 			if (err)
 				goto recover;
+			clear_buffer_delay(bh);
 			if (buffer_new(bh)) {
 				/* blockdev mappings never come here */
 				clear_buffer_new(bh);
@@ -1774,7 +1776,8 @@ static int __block_write_full_page(struct inode *inode, struct page *page,
 	bh = head;
 	/* Recovery: lock and submit the mapped buffers */
 	do {
-		if (buffer_mapped(bh) && buffer_dirty(bh)) {
+		if (buffer_mapped(bh) && buffer_dirty(bh) &&
+		    !buffer_delay(bh)) {
 			lock_buffer(bh);
 			mark_buffer_async_write(bh);
 		} else {
@@ -2061,6 +2064,7 @@ int generic_write_end(struct file *file, struct address_space *mapping,
 			struct page *page, void *fsdata)
 {
 	struct inode *inode = mapping->host;
+	int i_size_changed = 0;
 
 	copied = block_write_end(file, mapping, pos, len, copied, page, fsdata);
 
@@ -2073,12 +2077,21 @@ int generic_write_end(struct file *file, struct address_space *mapping,
 	 */
 	if (pos+copied > inode->i_size) {
 		i_size_write(inode, pos+copied);
-		mark_inode_dirty(inode);
+		i_size_changed = 1;
 	}
 
 	unlock_page(page);
 	page_cache_release(page);
 
+	/*
+	 * Don't mark the inode dirty under page lock. First, it unnecessarily
+	 * makes the holding time of page lock longer. Second, it forces lock
+	 * ordering of page lock and transaction start for journaling
+	 * filesystems.
+	 */
+	if (i_size_changed)
+		mark_inode_dirty(inode);
+
 	return copied;
 }
 EXPORT_SYMBOL(generic_write_end);

fs/ext4/dir.c

@@ -129,7 +129,8 @@ static int ext4_readdir(struct file * filp,
 		struct buffer_head *bh = NULL;
 
 		map_bh.b_state = 0;
-		err = ext4_get_blocks_wrap(NULL, inode, blk, 1, &map_bh, 0, 0);
+		err = ext4_get_blocks_wrap(NULL, inode, blk, 1, &map_bh,
+						0, 0, 0);
 		if (err > 0) {
 			pgoff_t index = map_bh.b_blocknr >>
 					(PAGE_CACHE_SHIFT - inode->i_blkbits);
@@ -272,7 +273,7 @@ static void free_rb_tree_fname(struct rb_root *root)
 
 	while (n) {
 		/* Do the node's children first */
-		if ((n)->rb_left) {
+		if (n->rb_left) {
 			n = n->rb_left;
 			continue;
 		}
@@ -301,24 +302,18 @@ static void free_rb_tree_fname(struct rb_root *root)
 			parent->rb_right = NULL;
 		n = parent;
 	}
-	root->rb_node = NULL;
 }
 
 
-static struct dir_private_info *create_dir_info(loff_t pos)
+static struct dir_private_info *ext4_htree_create_dir_info(loff_t pos)
 {
 	struct dir_private_info *p;
 
-	p = kmalloc(sizeof(struct dir_private_info), GFP_KERNEL);
+	p = kzalloc(sizeof(struct dir_private_info), GFP_KERNEL);
 	if (!p)
 		return NULL;
-	p->root.rb_node = NULL;
-	p->curr_node = NULL;
-	p->extra_fname = NULL;
-	p->last_pos = 0;
 	p->curr_hash = pos2maj_hash(pos);
 	p->curr_minor_hash = pos2min_hash(pos);
-	p->next_hash = 0;
 	return p;
 }
 
@@ -433,7 +428,7 @@ static int ext4_dx_readdir(struct file * filp,
 	int	ret;
 
 	if (!info) {
-		info = create_dir_info(filp->f_pos);
+		info = ext4_htree_create_dir_info(filp->f_pos);
 		if (!info)
 			return -ENOMEM;
 		filp->private_data = info;

fs/ext4/ext4.h

@@ -22,7 +22,7 @@
 #include "ext4_i.h"
 
 /*
- * The second extended filesystem constants/structures
+ * The fourth extended filesystem constants/structures
  */
 
 /*
@@ -45,7 +45,7 @@
 #define ext4_debug(f, a...)						\
 	do {								\
 		printk (KERN_DEBUG "EXT4-fs DEBUG (%s, %d): %s:",	\
-			__FILE__, __LINE__, __FUNCTION__);		\
+			__FILE__, __LINE__, __func__);			\
 		printk (KERN_DEBUG f, ## a);				\
 	} while (0)
 #else
@@ -74,6 +74,9 @@
 #define EXT4_MB_HINT_GOAL_ONLY		256
 /* goal is meaningful */
 #define EXT4_MB_HINT_TRY_GOAL		512
+/* blocks already pre-reserved by delayed allocation */
+#define EXT4_MB_DELALLOC_RESERVED      1024
+
 
 struct ext4_allocation_request {
 	/* target inode for block we're allocating */
@@ -170,6 +173,15 @@ struct ext4_group_desc
 	__u32	bg_reserved2[3];
 };
 
+/*
+ * Structure of a flex block group info
+ */
+
+struct flex_groups {
+	__u32 free_inodes;
+	__u32 free_blocks;
+};
+
 #define EXT4_BG_INODE_UNINIT	0x0001 /* Inode table/bitmap not in use */
 #define EXT4_BG_BLOCK_UNINIT	0x0002 /* Block bitmap not in use */
 #define EXT4_BG_INODE_ZEROED	0x0004 /* On-disk itable initialized to zero */
@@ -527,6 +539,7 @@ do {									       \
 #define EXT4_MOUNT_JOURNAL_ASYNC_COMMIT	0x1000000 /* Journal Async Commit */
 #define EXT4_MOUNT_I_VERSION            0x2000000 /* i_version support */
 #define EXT4_MOUNT_MBALLOC		0x4000000 /* Buddy allocation support */
+#define EXT4_MOUNT_DELALLOC		0x8000000 /* Delalloc support */
 /* Compatibility, for having both ext2_fs.h and ext4_fs.h included at once */
 #ifndef _LINUX_EXT2_FS_H
 #define clear_opt(o, opt)		o &= ~EXT4_MOUNT_##opt
@@ -647,7 +660,10 @@ struct ext4_super_block {
 	__le16  s_mmp_interval;         /* # seconds to wait in MMP checking */
 	__le64  s_mmp_block;            /* Block for multi-mount protection */
 	__le32  s_raid_stripe_width;    /* blocks on all data disks (N*stride)*/
-	__u32   s_reserved[163];        /* Padding to the end of the block */
+	__u8	s_log_groups_per_flex;  /* FLEX_BG group size */
+	__u8	s_reserved_char_pad2;
+	__le16  s_reserved_pad;
+	__u32   s_reserved[162];        /* Padding to the end of the block */
 };
 
 #ifdef __KERNEL__
@@ -958,12 +974,17 @@ extern ext4_grpblk_t ext4_block_group_offset(struct super_block *sb,
 extern int ext4_bg_has_super(struct super_block *sb, ext4_group_t group);
 extern unsigned long ext4_bg_num_gdb(struct super_block *sb,
 			ext4_group_t group);
-extern ext4_fsblk_t ext4_new_block (handle_t *handle, struct inode *inode,
+extern ext4_fsblk_t ext4_new_meta_block(handle_t *handle, struct inode *inode,
 			ext4_fsblk_t goal, int *errp);
-extern ext4_fsblk_t ext4_new_blocks (handle_t *handle, struct inode *inode,
+extern ext4_fsblk_t ext4_new_meta_blocks(handle_t *handle, struct inode *inode,
 			ext4_fsblk_t goal, unsigned long *count, int *errp);
-extern ext4_fsblk_t ext4_new_blocks_old(handle_t *handle, struct inode *inode,
+extern ext4_fsblk_t ext4_new_blocks(handle_t *handle, struct inode *inode,
+					ext4_lblk_t iblock, ext4_fsblk_t goal,
+					unsigned long *count, int *errp);
+extern ext4_fsblk_t ext4_old_new_blocks(handle_t *handle, struct inode *inode,
 			ext4_fsblk_t goal, unsigned long *count, int *errp);
+extern ext4_fsblk_t ext4_has_free_blocks(struct ext4_sb_info *sbi,
+						ext4_fsblk_t nblocks);
 extern void ext4_free_blocks (handle_t *handle, struct inode *inode,
 			ext4_fsblk_t block, unsigned long count, int metadata);
 extern void ext4_free_blocks_sb (handle_t *handle, struct super_block *sb,
@@ -1016,9 +1037,14 @@ extern int __init init_ext4_mballoc(void);
 extern void exit_ext4_mballoc(void);
 extern void ext4_mb_free_blocks(handle_t *, struct inode *,
 		unsigned long, unsigned long, int, unsigned long *);
+extern int ext4_mb_add_more_groupinfo(struct super_block *sb,
+		ext4_group_t i, struct ext4_group_desc *desc);
+extern void ext4_mb_update_group_info(struct ext4_group_info *grp,
+		ext4_grpblk_t add);
 
 
 /* inode.c */
+void ext4_da_release_space(struct inode *inode, int used, int to_free);
 int ext4_forget(handle_t *handle, int is_metadata, struct inode *inode,
 		struct buffer_head *bh, ext4_fsblk_t blocknr);
 struct buffer_head *ext4_getblk(handle_t *, struct inode *,
@@ -1033,19 +1059,23 @@ int ext4_get_blocks_handle(handle_t *handle, struct inode *inode,
 extern struct inode *ext4_iget(struct super_block *, unsigned long);
 extern int  ext4_write_inode (struct inode *, int);
 extern int  ext4_setattr (struct dentry *, struct iattr *);
+extern int  ext4_getattr(struct vfsmount *mnt, struct dentry *dentry,
+				struct kstat *stat);
 extern void ext4_delete_inode (struct inode *);
 extern int  ext4_sync_inode (handle_t *, struct inode *);
 extern void ext4_discard_reservation (struct inode *);
 extern void ext4_dirty_inode(struct inode *);
 extern int ext4_change_inode_journal_flag(struct inode *, int);
 extern int ext4_get_inode_loc(struct inode *, struct ext4_iloc *);
+extern int ext4_can_truncate(struct inode *inode);
 extern void ext4_truncate (struct inode *);
 extern void ext4_set_inode_flags(struct inode *);
 extern void ext4_get_inode_flags(struct ext4_inode_info *);
 extern void ext4_set_aops(struct inode *inode);
 extern int ext4_writepage_trans_blocks(struct inode *);
-extern int ext4_block_truncate_page(handle_t *handle, struct page *page,
+extern int ext4_block_truncate_page(handle_t *handle,
 		struct address_space *mapping, loff_t from);
+extern int ext4_page_mkwrite(struct vm_area_struct *vma, struct page *page);
 
 /* ioctl.c */
 extern long ext4_ioctl(struct file *, unsigned int, unsigned long);
@@ -1159,10 +1189,21 @@ struct ext4_group_info *ext4_get_group_info(struct super_block *sb,
 }
 
 
+static inline ext4_group_t ext4_flex_group(struct ext4_sb_info *sbi,
+					     ext4_group_t block_group)
+{
+	return block_group >> sbi->s_log_groups_per_flex;
+}
+
+static inline unsigned int ext4_flex_bg_size(struct ext4_sb_info *sbi)
+{
+	return 1 << sbi->s_log_groups_per_flex;
+}
+
 #define ext4_std_error(sb, errno)				\
 do {								\
 	if ((errno))						\
-		__ext4_std_error((sb), __FUNCTION__, (errno));	\
+		__ext4_std_error((sb), __func__, (errno));	\
 } while (0)
 
 /*
@@ -1191,7 +1232,7 @@ extern int ext4_ext_get_blocks(handle_t *handle, struct inode *inode,
 			ext4_lblk_t iblock,
 			unsigned long max_blocks, struct buffer_head *bh_result,
 			int create, int extend_disksize);
-extern void ext4_ext_truncate(struct inode *, struct page *);
+extern void ext4_ext_truncate(struct inode *);
 extern void ext4_ext_init(struct super_block *);
 extern void ext4_ext_release(struct super_block *);
 extern long ext4_fallocate(struct inode *inode, int mode, loff_t offset,
@@ -1199,7 +1240,7 @@ extern long ext4_fallocate(struct inode *inode, int mode, loff_t offset,
 extern int ext4_get_blocks_wrap(handle_t *handle, struct inode *inode,
 			sector_t block, unsigned long max_blocks,
 			struct buffer_head *bh, int create,
-			int extend_disksize);
+			int extend_disksize, int flag);
 #endif	/* __KERNEL__ */
 
 #endif	/* _EXT4_H */

fs/ext4/ext4_extents.h

@@ -212,6 +212,7 @@ static inline int ext4_ext_get_actual_len(struct ext4_extent *ext)
 		(le16_to_cpu(ext->ee_len) - EXT_INIT_MAX_LEN));
 }
 
+extern int ext4_ext_calc_metadata_amount(struct inode *inode, int blocks);
 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 *);

fs/ext4/ext4_i.h

@@ -79,7 +79,7 @@ struct ext4_ext_cache {
 };
 
 /*
- * third extended file system inode data in memory
+ * fourth extended file system inode data in memory
  */
 struct ext4_inode_info {
 	__le32	i_data[15];	/* unconverted */
@@ -150,6 +150,7 @@ struct ext4_inode_info {
 	 */
 	struct rw_semaphore i_data_sem;
 	struct inode vfs_inode;
+	struct jbd2_inode jinode;
 
 	unsigned long i_ext_generation;
 	struct ext4_ext_cache i_cached_extent;
@@ -162,6 +163,13 @@ struct ext4_inode_info {
 	/* mballoc */
 	struct list_head i_prealloc_list;
 	spinlock_t i_prealloc_lock;
+
+	/* allocation reservation info for delalloc */
+	unsigned long i_reserved_data_blocks;
+	unsigned long i_reserved_meta_blocks;
+	unsigned long i_allocated_meta_blocks;
+	unsigned short i_delalloc_reserved_flag;
+	spinlock_t i_block_reservation_lock;
 };
 
 #endif	/* _EXT4_I */

fs/ext4/ext4_jbd2.h

@@ -142,19 +142,17 @@ 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))
+	__ext4_journal_get_undo_access(__func__, (handle), (bh))
 #define ext4_journal_get_write_access(handle, bh) \
-	__ext4_journal_get_write_access(__FUNCTION__, (handle), (bh))
+	__ext4_journal_get_write_access(__func__, (handle), (bh))
 #define ext4_journal_revoke(handle, blocknr, bh) \
-	__ext4_journal_revoke(__FUNCTION__, (handle), (blocknr), (bh))
+	__ext4_journal_revoke(__func__, (handle), (blocknr), (bh))
 #define ext4_journal_get_create_access(handle, bh) \
-	__ext4_journal_get_create_access(__FUNCTION__, (handle), (bh))
+	__ext4_journal_get_create_access(__func__, (handle), (bh))
 #define ext4_journal_dirty_metadata(handle, bh) \
-	__ext4_journal_dirty_metadata(__FUNCTION__, (handle), (bh))
+	__ext4_journal_dirty_metadata(__func__, (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);
+	__ext4_journal_forget(__func__, (handle), (bh))
 
 handle_t *ext4_journal_start_sb(struct super_block *sb, int nblocks);
 int __ext4_journal_stop(const char *where, handle_t *handle);
@@ -165,7 +163,7 @@ static inline handle_t *ext4_journal_start(struct inode *inode, int nblocks)
 }
 
 #define ext4_journal_stop(handle) \
-	__ext4_journal_stop(__FUNCTION__, (handle))
+	__ext4_journal_stop(__func__, (handle))
 
 static inline handle_t *ext4_journal_current_handle(void)
 {
@@ -192,6 +190,11 @@ static inline int ext4_journal_force_commit(journal_t *journal)
 	return jbd2_journal_force_commit(journal);
 }
 
+static inline int ext4_jbd2_file_inode(handle_t *handle, struct inode *inode)
+{
+	return jbd2_journal_file_inode(handle, &EXT4_I(inode)->jinode);
+}
+
 /* super.c */
 int ext4_force_commit(struct super_block *sb);
 

fs/ext4/ext4_sb.h

@@ -25,7 +25,7 @@
 #include <linux/rbtree.h>
 
 /*
- * third extended-fs super-block data in memory
+ * fourth extended-fs super-block data in memory
  */
 struct ext4_sb_info {
 	unsigned long s_desc_size;	/* Size of a group descriptor in bytes */
@@ -143,6 +143,9 @@ struct ext4_sb_info {
 
 	/* locality groups */
 	struct ext4_locality_group *s_locality_groups;
+
+	unsigned int s_log_groups_per_flex;
+	struct flex_groups *s_flex_groups;
 };
 
 #endif	/* _EXT4_SB */

fs/ext4/extents.c

@@ -92,17 +92,16 @@ static void ext4_idx_store_pblock(struct ext4_extent_idx *ix, ext4_fsblk_t pb)
 	ix->ei_leaf_hi = cpu_to_le16((unsigned long) ((pb >> 31) >> 1) & 0xffff);
 }
 
-static handle_t *ext4_ext_journal_restart(handle_t *handle, int needed)
+static int ext4_ext_journal_restart(handle_t *handle, int needed)
 {
 	int err;
 
 	if (handle->h_buffer_credits > needed)
-		return handle;
-	if (!ext4_journal_extend(handle, needed))
-		return handle;
-	err = ext4_journal_restart(handle, needed);
-
-	return handle;
+		return 0;
+	err = ext4_journal_extend(handle, needed);
+	if (err)
+		return err;
+	return ext4_journal_restart(handle, needed);
 }
 
 /*
@@ -180,15 +179,18 @@ static ext4_fsblk_t ext4_ext_find_goal(struct inode *inode,
 	return bg_start + colour + block;
 }
 
+/*
+ * Allocation for a meta data block
+ */
 static ext4_fsblk_t
-ext4_ext_new_block(handle_t *handle, struct inode *inode,
+ext4_ext_new_meta_block(handle_t *handle, struct inode *inode,
 			struct ext4_ext_path *path,
 			struct ext4_extent *ex, int *err)
 {
 	ext4_fsblk_t goal, newblock;
 
 	goal = ext4_ext_find_goal(inode, path, le32_to_cpu(ex->ee_block));
-	newblock = ext4_new_block(handle, inode, goal, err);
+	newblock = ext4_new_meta_block(handle, inode, goal, err);
 	return newblock;
 }
 
@@ -246,6 +248,36 @@ static int ext4_ext_space_root_idx(struct inode *inode)
 	return size;
 }
 
+/*
+ * Calculate the number of metadata blocks needed
+ * to allocate @blocks
+ * Worse case is one block per extent
+ */
+int ext4_ext_calc_metadata_amount(struct inode *inode, int blocks)
+{
+	int lcap, icap, rcap, leafs, idxs, num;
+	int newextents = blocks;
+
+	rcap = ext4_ext_space_root_idx(inode);
+	lcap = ext4_ext_space_block(inode);
+	icap = ext4_ext_space_block_idx(inode);
+
+	/* number of new leaf blocks needed */
+	num = leafs = (newextents + lcap - 1) / lcap;
+
+	/*
+	 * Worse case, we need separate index block(s)
+	 * to link all new leaf blocks
+	 */
+	idxs = (leafs + icap - 1) / icap;
+	do {
+		num += idxs;
+		idxs = (idxs + icap - 1) / icap;
+	} while (idxs > rcap);
+
+	return num;
+}
+
 static int
 ext4_ext_max_entries(struct inode *inode, int depth)
 {
@@ -524,6 +556,7 @@ ext4_ext_find_extent(struct inode *inode, ext4_lblk_t block,
 		alloc = 1;
 	}
 	path[0].p_hdr = eh;
+	path[0].p_bh = NULL;
 
 	i = depth;
 	/* walk through the tree */
@@ -552,12 +585,14 @@ ext4_ext_find_extent(struct inode *inode, ext4_lblk_t block,
 	}
 
 	path[ppos].p_depth = i;
-	path[ppos].p_hdr = eh;
 	path[ppos].p_ext = NULL;
 	path[ppos].p_idx = NULL;
 
 	/* find extent */
 	ext4_ext_binsearch(inode, path + ppos, block);
+	/* if not an empty leaf */
+	if (path[ppos].p_ext)
+		path[ppos].p_block = ext_pblock(path[ppos].p_ext);
 
 	ext4_ext_show_path(inode, path);
 
@@ -688,7 +723,8 @@ static int ext4_ext_split(handle_t *handle, struct inode *inode,
 	/* allocate all needed blocks */
 	ext_debug("allocate %d blocks for indexes/leaf\n", depth - at);
 	for (a = 0; a < depth - at; a++) {
-		newblock = ext4_ext_new_block(handle, inode, path, newext, &err);
+		newblock = ext4_ext_new_meta_block(handle, inode, path,
+						   newext, &err);
 		if (newblock == 0)
 			goto cleanup;
 		ablocks[a] = newblock;
@@ -884,7 +920,7 @@ static int ext4_ext_grow_indepth(handle_t *handle, struct inode *inode,
 	ext4_fsblk_t newblock;
 	int err = 0;
 
-	newblock = ext4_ext_new_block(handle, inode, path, newext, &err);
+	newblock = ext4_ext_new_meta_block(handle, inode, path, newext, &err);
 	if (newblock == 0)
 		return err;
 
@@ -981,6 +1017,8 @@ static int ext4_ext_create_new_leaf(handle_t *handle, struct inode *inode,
 		/* if we found index with free entry, then use that
 		 * entry: create all needed subtree and add new leaf */
 		err = ext4_ext_split(handle, inode, path, newext, i);
+		if (err)
+			goto out;
 
 		/* refill path */
 		ext4_ext_drop_refs(path);
@@ -1883,11 +1921,9 @@ ext4_ext_rm_leaf(handle_t *handle, struct inode *inode,
 		credits += 2 * EXT4_QUOTA_TRANS_BLOCKS(inode->i_sb);
 #endif
 
-		handle = ext4_ext_journal_restart(handle, credits);
-		if (IS_ERR(handle)) {
-			err = PTR_ERR(handle);
+		err = ext4_ext_journal_restart(handle, credits);
+		if (err)
 			goto out;
-		}
 
 		err = ext4_ext_get_access(handle, inode, path + depth);
 		if (err)
@@ -2529,6 +2565,7 @@ int ext4_ext_get_blocks(handle_t *handle, struct inode *inode,
 	int err = 0, depth, ret;
 	unsigned long allocated = 0;
 	struct ext4_allocation_request ar;
+	loff_t disksize;
 
 	__clear_bit(BH_New, &bh_result->b_state);
 	ext_debug("blocks %u/%lu requested for inode %u\n",
@@ -2616,8 +2653,7 @@ int ext4_ext_get_blocks(handle_t *handle, struct inode *inode,
 				 */
 				if (allocated > max_blocks)
 					allocated = max_blocks;
-				/* mark the buffer unwritten */
-				__set_bit(BH_Unwritten, &bh_result->b_state);
+				set_buffer_unwritten(bh_result);
 				goto out2;
 			}
 
@@ -2716,14 +2752,19 @@ int ext4_ext_get_blocks(handle_t *handle, struct inode *inode,
 		goto out2;
 	}
 
-	if (extend_disksize && inode->i_size > EXT4_I(inode)->i_disksize)
-		EXT4_I(inode)->i_disksize = inode->i_size;
-
 	/* previous routine could use block we allocated */
 	newblock = ext_pblock(&newex);
 	allocated = ext4_ext_get_actual_len(&newex);
 outnew:
-	__set_bit(BH_New, &bh_result->b_state);
+	if (extend_disksize) {
+		disksize = ((loff_t) iblock + ar.len) << inode->i_blkbits;
+		if (disksize > i_size_read(inode))
+			disksize = i_size_read(inode);
+		if (disksize > EXT4_I(inode)->i_disksize)
+			EXT4_I(inode)->i_disksize = disksize;
+	}
+
+	set_buffer_new(bh_result);
 
 	/* Cache only when it is _not_ an uninitialized extent */
 	if (create != EXT4_CREATE_UNINITIALIZED_EXT)
@@ -2733,7 +2774,7 @@ int ext4_ext_get_blocks(handle_t *handle, struct inode *inode,
 	if (allocated > max_blocks)
 		allocated = max_blocks;
 	ext4_ext_show_leaf(inode, path);
-	__set_bit(BH_Mapped, &bh_result->b_state);
+	set_buffer_mapped(bh_result);
 	bh_result->b_bdev = inode->i_sb->s_bdev;
 	bh_result->b_blocknr = newblock;
 out2:
@@ -2744,7 +2785,7 @@ int ext4_ext_get_blocks(handle_t *handle, struct inode *inode,
 	return err ? err : allocated;
 }
 
-void ext4_ext_truncate(struct inode * inode, struct page *page)
+void ext4_ext_truncate(struct inode *inode)
 {
 	struct address_space *mapping = inode->i_mapping;
 	struct super_block *sb = inode->i_sb;
@@ -2757,18 +2798,14 @@ void ext4_ext_truncate(struct inode * inode, struct page *page)
 	 */
 	err = ext4_writepage_trans_blocks(inode) + 3;
 	handle = ext4_journal_start(inode, err);
-	if (IS_ERR(handle)) {
-		if (page) {
-			clear_highpage(page);
-			flush_dcache_page(page);
-			unlock_page(page);
-			page_cache_release(page);
-		}
+	if (IS_ERR(handle))
 		return;
-	}
 
-	if (page)
-		ext4_block_truncate_page(handle, page, mapping, inode->i_size);
+	if (inode->i_size & (sb->s_blocksize - 1))
+		ext4_block_truncate_page(handle, mapping, inode->i_size);
+
+	if (ext4_orphan_add(handle, inode))
+		goto out_stop;
 
 	down_write(&EXT4_I(inode)->i_data_sem);
 	ext4_ext_invalidate_cache(inode);
@@ -2780,8 +2817,6 @@ void ext4_ext_truncate(struct inode * inode, struct page *page)
 	 * Probably we need not scan at all,
 	 * because page truncation is enough.
 	 */
-	if (ext4_orphan_add(handle, inode))
-		goto out_stop;
 
 	/* we have to know where to truncate from in crash case */
 	EXT4_I(inode)->i_disksize = inode->i_size;
@@ -2798,6 +2833,7 @@ void ext4_ext_truncate(struct inode * inode, struct page *page)
 		handle->h_sync = 1;
 
 out_stop:
+	up_write(&EXT4_I(inode)->i_data_sem);
 	/*
 	 * If this was a simple ftruncate() and the file will remain alive,
 	 * then we need to clear up the orphan record which we created above.
@@ -2808,7 +2844,6 @@ void ext4_ext_truncate(struct inode * inode, struct page *page)
 	if (inode->i_nlink)
 		ext4_orphan_del(handle, inode);
 
-	up_write(&EXT4_I(inode)->i_data_sem);
 	inode->i_mtime = inode->i_ctime = ext4_current_time(inode);
 	ext4_mark_inode_dirty(handle, inode);
 	ext4_journal_stop(handle);
@@ -2911,7 +2946,7 @@ long ext4_fallocate(struct inode *inode, int mode, loff_t offset, loff_t len)
 		}
 		ret = ext4_get_blocks_wrap(handle, inode, block,
 					  max_blocks, &map_bh,
-					  EXT4_CREATE_UNINITIALIZED_EXT, 0);
+					  EXT4_CREATE_UNINITIALIZED_EXT, 0, 0);
 		if (ret <= 0) {
 #ifdef EXT4FS_DEBUG
 			WARN_ON(ret <= 0);

fs/ext4/file.c

@@ -123,6 +123,23 @@ ext4_file_write(struct kiocb *iocb, const struct iovec *iov,
 	return ret;
 }
 
+static struct vm_operations_struct ext4_file_vm_ops = {
+	.fault		= filemap_fault,
+	.page_mkwrite   = ext4_page_mkwrite,
+};
+
+static int ext4_file_mmap(struct file *file, struct vm_area_struct *vma)
+{
+	struct address_space *mapping = file->f_mapping;
+
+	if (!mapping->a_ops->readpage)
+		return -ENOEXEC;
+	file_accessed(file);
+	vma->vm_ops = &ext4_file_vm_ops;
+	vma->vm_flags |= VM_CAN_NONLINEAR;
+	return 0;
+}
+
 const struct file_operations ext4_file_operations = {
 	.llseek		= generic_file_llseek,
 	.read		= do_sync_read,
@@ -133,7 +150,7 @@ const struct file_operations ext4_file_operations = {
 #ifdef CONFIG_COMPAT
 	.compat_ioctl	= ext4_compat_ioctl,
 #endif
-	.mmap		= generic_file_mmap,
+	.mmap		= ext4_file_mmap,
 	.open		= generic_file_open,
 	.release	= ext4_release_file,
 	.fsync		= ext4_sync_file,
@@ -144,6 +161,7 @@ const struct file_operations ext4_file_operations = {
 const struct inode_operations ext4_file_inode_operations = {
 	.truncate	= ext4_truncate,
 	.setattr	= ext4_setattr,
+	.getattr	= ext4_getattr,
 #ifdef CONFIG_EXT4DEV_FS_XATTR
 	.setxattr	= generic_setxattr,
 	.getxattr	= generic_getxattr,

fs/ext4/fsync.c

@@ -27,6 +27,7 @@
 #include <linux/sched.h>
 #include <linux/writeback.h>
 #include <linux/jbd2.h>
+#include <linux/blkdev.h>
 #include "ext4.h"
 #include "ext4_jbd2.h"
 
@@ -45,6 +46,7 @@
 int ext4_sync_file(struct file * file, struct dentry *dentry, int datasync)
 {
 	struct inode *inode = dentry->d_inode;
+	journal_t *journal = EXT4_SB(inode->i_sb)->s_journal;
 	int ret = 0;
 
 	J_ASSERT(ext4_journal_current_handle() == NULL);
@@ -85,6 +87,8 @@ int ext4_sync_file(struct file * file, struct dentry *dentry, int datasync)
 			.nr_to_write = 0, /* sys_fsync did this */
 		};
 		ret = sync_inode(inode, &wbc);
+		if (journal && (journal->j_flags & JBD2_BARRIER))
+			blkdev_issue_flush(inode->i_sb->s_bdev, NULL);
 	}
 out:
 	return ret;

fs/ext4/group.h

@@ -13,7 +13,7 @@ extern __le16 ext4_group_desc_csum(struct ext4_sb_info *sbi, __u32 group,
 				   struct ext4_group_desc *gdp);
 extern int ext4_group_desc_csum_verify(struct ext4_sb_info *sbi, __u32 group,
 				       struct ext4_group_desc *gdp);
-struct buffer_head *read_block_bitmap(struct super_block *sb,
+struct buffer_head *ext4_read_block_bitmap(struct super_block *sb,
 				      ext4_group_t block_group);
 extern unsigned ext4_init_block_bitmap(struct super_block *sb,
 				       struct buffer_head *bh,

fs/ext4/ialloc.c

@@ -157,6 +157,7 @@ void ext4_free_inode (handle_t *handle, struct inode * inode)
 	struct ext4_super_block * es;
 	struct ext4_sb_info *sbi;
 	int fatal = 0, err;
+	ext4_group_t flex_group;
 
 	if (atomic_read(&inode->i_count) > 1) {
 		printk ("ext4_free_inode: inode has count=%d\n",
@@ -232,6 +233,12 @@ void ext4_free_inode (handle_t *handle, struct inode * inode)
 			if (is_directory)
 				percpu_counter_dec(&sbi->s_dirs_counter);
 
+			if (sbi->s_log_groups_per_flex) {
+				flex_group = ext4_flex_group(sbi, block_group);
+				spin_lock(sb_bgl_lock(sbi, flex_group));
+				sbi->s_flex_groups[flex_group].free_inodes++;
+				spin_unlock(sb_bgl_lock(sbi, flex_group));
+			}
 		}
 		BUFFER_TRACE(bh2, "call ext4_journal_dirty_metadata");
 		err = ext4_journal_dirty_metadata(handle, bh2);
@@ -286,6 +293,80 @@ static int find_group_dir(struct super_block *sb, struct inode *parent,
 	return ret;
 }
 
+#define free_block_ratio 10
+
+static int find_group_flex(struct super_block *sb, struct inode *parent,
+			   ext4_group_t *best_group)
+{
+	struct ext4_sb_info *sbi = EXT4_SB(sb);
+	struct ext4_group_desc *desc;
+	struct buffer_head *bh;
+	struct flex_groups *flex_group = sbi->s_flex_groups;
+	ext4_group_t parent_group = EXT4_I(parent)->i_block_group;
+	ext4_group_t parent_fbg_group = ext4_flex_group(sbi, parent_group);
+	ext4_group_t ngroups = sbi->s_groups_count;
+	int flex_size = ext4_flex_bg_size(sbi);
+	ext4_group_t best_flex = parent_fbg_group;
+	int blocks_per_flex = sbi->s_blocks_per_group * flex_size;
+	int flexbg_free_blocks;
+	int flex_freeb_ratio;
+	ext4_group_t n_fbg_groups;
+	ext4_group_t i;
+
+	n_fbg_groups = (sbi->s_groups_count + flex_size - 1) >>
+		sbi->s_log_groups_per_flex;
+
+find_close_to_parent:
+	flexbg_free_blocks = flex_group[best_flex].free_blocks;
+	flex_freeb_ratio = flexbg_free_blocks * 100 / blocks_per_flex;
+	if (flex_group[best_flex].free_inodes &&
+	    flex_freeb_ratio > free_block_ratio)
+		goto found_flexbg;
+
+	if (best_flex && best_flex == parent_fbg_group) {
+		best_flex--;
+		goto find_close_to_parent;
+	}
+
+	for (i = 0; i < n_fbg_groups; i++) {
+		if (i == parent_fbg_group || i == parent_fbg_group - 1)
+			continue;
+
+		flexbg_free_blocks = flex_group[i].free_blocks;
+		flex_freeb_ratio = flexbg_free_blocks * 100 / blocks_per_flex;
+
+		if (flex_freeb_ratio > free_block_ratio &&
+		    flex_group[i].free_inodes) {
+			best_flex = i;
+			goto found_flexbg;
+		}
+
+		if (best_flex < 0 ||
+		    (flex_group[i].free_blocks >
+		     flex_group[best_flex].free_blocks &&
+		     flex_group[i].free_inodes))
+			best_flex = i;
+	}
+
+	if (!flex_group[best_flex].free_inodes ||
+	    !flex_group[best_flex].free_blocks)
+		return -1;
+
+found_flexbg:
+	for (i = best_flex * flex_size; i < ngroups &&
+		     i < (best_flex + 1) * flex_size; i++) {
+		desc = ext4_get_group_desc(sb, i, &bh);
+		if (le16_to_cpu(desc->bg_free_inodes_count)) {
+			*best_group = i;
+			goto out;
+		}
+	}
+
+	return -1;
+out:
+	return 0;
+}
+
 /*
  * Orlov's allocator for directories.
  *
@@ -501,6 +582,7 @@ struct inode *ext4_new_inode(handle_t *handle, struct inode * dir, int mode)
 	struct inode *ret;
 	ext4_group_t i;
 	int free = 0;
+	ext4_group_t flex_group;
 
 	/* Cannot create files in a deleted directory */
 	if (!dir || !dir->i_nlink)
@@ -514,6 +596,12 @@ struct inode *ext4_new_inode(handle_t *handle, struct inode * dir, int mode)
 
 	sbi = EXT4_SB(sb);
 	es = sbi->s_es;
+
+	if (sbi->s_log_groups_per_flex) {
+		ret2 = find_group_flex(sb, dir, &group);
+		goto got_group;
+	}
+
 	if (S_ISDIR(mode)) {
 		if (test_opt (sb, OLDALLOC))
 			ret2 = find_group_dir(sb, dir, &group);
@@ -522,6 +610,7 @@ struct inode *ext4_new_inode(handle_t *handle, struct inode * dir, int mode)
 	} else
 		ret2 = find_group_other(sb, dir, &group);
 
+got_group:
 	err = -ENOSPC;
 	if (ret2 == -1)
 		goto out;
@@ -600,7 +689,7 @@ struct inode *ext4_new_inode(handle_t *handle, struct inode * dir, int mode)
 	/* We may have to initialize the block bitmap if it isn't already */
 	if (EXT4_HAS_RO_COMPAT_FEATURE(sb, EXT4_FEATURE_RO_COMPAT_GDT_CSUM) &&
 	    gdp->bg_flags & cpu_to_le16(EXT4_BG_BLOCK_UNINIT)) {
-		struct buffer_head *block_bh = read_block_bitmap(sb, group);
+		struct buffer_head *block_bh = ext4_read_block_bitmap(sb, group);
 
 		BUFFER_TRACE(block_bh, "get block bitmap access");
 		err = ext4_journal_get_write_access(handle, block_bh);
@@ -676,6 +765,13 @@ struct inode *ext4_new_inode(handle_t *handle, struct inode * dir, int mode)
 		percpu_counter_inc(&sbi->s_dirs_counter);
 	sb->s_dirt = 1;
 
+	if (sbi->s_log_groups_per_flex) {
+		flex_group = ext4_flex_group(sbi, group);
+		spin_lock(sb_bgl_lock(sbi, flex_group));
+		sbi->s_flex_groups[flex_group].free_inodes--;
+		spin_unlock(sb_bgl_lock(sbi, flex_group));
+	}
+
 	inode->i_uid = current->fsuid;
 	if (test_opt (sb, GRPID))
 		inode->i_gid = dir->i_gid;
@@ -740,14 +836,10 @@ struct inode *ext4_new_inode(handle_t *handle, struct inode * dir, int mode)
 		goto fail_free_drop;
 
 	if (test_opt(sb, EXTENTS)) {
-		/* set extent flag only for diretory, file and normal symlink*/
+		/* set extent flag only for directory, 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_free_drop;
 		}
 	}
 
@@ -817,6 +909,14 @@ struct inode *ext4_orphan_get(struct super_block *sb, unsigned long ino)
 	if (IS_ERR(inode))
 		goto iget_failed;
 
+	/*
+	 * If the orphans has i_nlinks > 0 then it should be able to be
+	 * truncated, otherwise it won't be removed from the orphan list
+	 * during processing and an infinite loop will result.
+	 */
+	if (inode->i_nlink && !ext4_can_truncate(inode))
+		goto bad_orphan;
+
 	if (NEXT_ORPHAN(inode) > max_ino)
 		goto bad_orphan;
 	brelse(bitmap_bh);
@@ -838,6 +938,7 @@ struct inode *ext4_orphan_get(struct super_block *sb, unsigned long ino)
 		printk(KERN_NOTICE "NEXT_ORPHAN(inode)=%u\n",
 		       NEXT_ORPHAN(inode));
 		printk(KERN_NOTICE "max_ino=%lu\n", max_ino);
+		printk(KERN_NOTICE "i_nlink=%u\n", inode->i_nlink);
 		/* Avoid freeing blocks if we got a bad deleted inode */
 		if (inode->i_nlink == 0)
 			inode->i_blocks = 0;

fs/ext4/namei.c

@@ -182,6 +182,16 @@ static struct buffer_head * ext4_dx_find_entry(struct dentry *dentry,
 static int ext4_dx_add_entry(handle_t *handle, struct dentry *dentry,
 			     struct inode *inode);
 
+/*
+ * p is at least 6 bytes before the end of page
+ */
+static inline struct ext4_dir_entry_2 *
+ext4_next_entry(struct ext4_dir_entry_2 *p)
+{
+	return (struct ext4_dir_entry_2 *)((char *)p +
+		ext4_rec_len_from_disk(p->rec_len));
+}
+
 /*
  * Future: use high four bits of block for coalesce-on-delete flags
  * Mask them off for now.
@@ -231,13 +241,13 @@ static inline unsigned dx_root_limit (struct inode *dir, unsigned infosize)
 {
 	unsigned entry_space = dir->i_sb->s_blocksize - EXT4_DIR_REC_LEN(1) -
 		EXT4_DIR_REC_LEN(2) - infosize;
-	return 0? 20: entry_space / sizeof(struct dx_entry);
+	return entry_space / sizeof(struct dx_entry);
 }
 
 static inline unsigned dx_node_limit (struct inode *dir)
 {
 	unsigned entry_space = dir->i_sb->s_blocksize - EXT4_DIR_REC_LEN(0);
-	return 0? 22: entry_space / sizeof(struct dx_entry);
+	return entry_space / sizeof(struct dx_entry);
 }
 
 /*
@@ -553,15 +563,6 @@ static int ext4_htree_next_block(struct inode *dir, __u32 hash,
 }
 
 
-/*
- * p is at least 6 bytes before the end of page
- */
-static inline struct ext4_dir_entry_2 *ext4_next_entry(struct ext4_dir_entry_2 *p)
-{
-	return (struct ext4_dir_entry_2 *)((char *)p +
-		ext4_rec_len_from_disk(p->rec_len));
-}
-
 /*
  * This function fills a red-black tree with information from a
  * directory block.  It returns the number directory entries loaded
@@ -993,19 +994,21 @@ static struct buffer_head * ext4_dx_find_entry(struct dentry *dentry,
 		de = (struct ext4_dir_entry_2 *) bh->b_data;
 		top = (struct ext4_dir_entry_2 *) ((char *) de + sb->s_blocksize -
 				       EXT4_DIR_REC_LEN(0));
-		for (; de < top; de = ext4_next_entry(de))
-		if (ext4_match (namelen, name, de)) {
-			if (!ext4_check_dir_entry("ext4_find_entry",
-						  dir, de, bh,
-				  (block<<EXT4_BLOCK_SIZE_BITS(sb))
-					  +((char *)de - bh->b_data))) {
-				brelse (bh);
+		for (; de < top; de = ext4_next_entry(de)) {
+			int off = (block << EXT4_BLOCK_SIZE_BITS(sb))
+				  + ((char *) de - bh->b_data);
+
+			if (!ext4_check_dir_entry(__func__, dir, de, bh, off)) {
+				brelse(bh);
 				*err = ERR_BAD_DX_DIR;
 				goto errout;
 			}
-			*res_dir = de;
-			dx_release (frames);
-			return bh;
+
+			if (ext4_match(namelen, name, de)) {
+				*res_dir = de;
+				dx_release(frames);
+				return bh;
+			}
 		}
 		brelse (bh);
 		/* Check to see if we should continue to search */

fs/ext4/resize.c

@@ -865,6 +865,15 @@ int ext4_group_add(struct super_block *sb, struct ext4_new_group_data *input)
 	gdp->bg_free_inodes_count = cpu_to_le16(EXT4_INODES_PER_GROUP(sb));
 	gdp->bg_checksum = ext4_group_desc_csum(sbi, input->group, gdp);
 
+	/*
+	 * We can allocate memory for mb_alloc based on the new group
+	 * descriptor
+	 */
+	if (test_opt(sb, MBALLOC)) {
+		err = ext4_mb_add_more_groupinfo(sb, input->group, gdp);
+		if (err)
+			goto exit_journal;
+	}
 	/*
 	 * Make the new blocks and inodes valid next.  We do this before
 	 * increasing the group count so that once the group is enabled,
@@ -957,6 +966,8 @@ int ext4_group_extend(struct super_block *sb, struct ext4_super_block *es,
 	handle_t *handle;
 	int err;
 	unsigned long freed_blocks;
+	ext4_group_t group;
+	struct ext4_group_info *grp;
 
 	/* We don't need to worry about locking wrt other resizers just
 	 * yet: we're going to revalidate es->s_blocks_count after
@@ -988,7 +999,7 @@ int ext4_group_extend(struct super_block *sb, struct ext4_super_block *es,
 	}
 
 	/* Handle the remaining blocks in the last group only. */
-	ext4_get_group_no_and_offset(sb, o_blocks_count, NULL, &last);
+	ext4_get_group_no_and_offset(sb, o_blocks_count, &group, &last);
 
 	if (last == 0) {
 		ext4_warning(sb, __func__,
@@ -1060,6 +1071,45 @@ int ext4_group_extend(struct super_block *sb, struct ext4_super_block *es,
 		   o_blocks_count + add);
 	if ((err = ext4_journal_stop(handle)))
 		goto exit_put;
+
+	/*
+	 * Mark mballoc pages as not up to date so that they will be updated
+	 * next time they are loaded by ext4_mb_load_buddy.
+	 */
+	if (test_opt(sb, MBALLOC)) {
+		struct ext4_sb_info *sbi = EXT4_SB(sb);
+		struct inode *inode = sbi->s_buddy_cache;
+		int blocks_per_page;
+		int block;
+		int pnum;
+		struct page *page;
+
+		/* Set buddy page as not up to date */
+		blocks_per_page = PAGE_CACHE_SIZE / sb->s_blocksize;
+		block = group * 2;
+		pnum = block / blocks_per_page;
+		page = find_get_page(inode->i_mapping, pnum);
+		if (page != NULL) {
+			ClearPageUptodate(page);
+			page_cache_release(page);
+		}
+
+		/* Set bitmap page as not up to date */
+		block++;
+		pnum = block / blocks_per_page;
+		page = find_get_page(inode->i_mapping, pnum);
+		if (page != NULL) {
+			ClearPageUptodate(page);
+			page_cache_release(page);
+		}
+
+		/* Get the info on the last group */
+		grp = ext4_get_group_info(sb, group);
+
+		/* Update free blocks in group info */
+		ext4_mb_update_group_info(grp, add);
+	}
+
 	if (test_opt(sb, DEBUG))
 		printk(KERN_DEBUG "EXT4-fs: extended group to %llu blocks\n",
 		       ext4_blocks_count(es));

fs/ext4/super.c

@@ -506,6 +506,7 @@ static void ext4_put_super (struct super_block * sb)
 	ext4_ext_release(sb);
 	ext4_xattr_put_super(sb);
 	jbd2_journal_destroy(sbi->s_journal);
+	sbi->s_journal = NULL;
 	if (!(sb->s_flags & MS_RDONLY)) {
 		EXT4_CLEAR_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_RECOVER);
 		es->s_state = cpu_to_le16(sbi->s_mount_state);
@@ -517,6 +518,7 @@ static void ext4_put_super (struct super_block * sb)
 	for (i = 0; i < sbi->s_gdb_count; i++)
 		brelse(sbi->s_group_desc[i]);
 	kfree(sbi->s_group_desc);
+	kfree(sbi->s_flex_groups);
 	percpu_counter_destroy(&sbi->s_freeblocks_counter);
 	percpu_counter_destroy(&sbi->s_freeinodes_counter);
 	percpu_counter_destroy(&sbi->s_dirs_counter);
@@ -571,6 +573,12 @@ static struct inode *ext4_alloc_inode(struct super_block *sb)
 	memset(&ei->i_cached_extent, 0, sizeof(struct ext4_ext_cache));
 	INIT_LIST_HEAD(&ei->i_prealloc_list);
 	spin_lock_init(&ei->i_prealloc_lock);
+	jbd2_journal_init_jbd_inode(&ei->jinode, &ei->vfs_inode);
+	ei->i_reserved_data_blocks = 0;
+	ei->i_reserved_meta_blocks = 0;
+	ei->i_allocated_meta_blocks = 0;
+	ei->i_delalloc_reserved_flag = 0;
+	spin_lock_init(&(ei->i_block_reservation_lock));
 	return &ei->vfs_inode;
 }
 
@@ -635,6 +643,8 @@ static void ext4_clear_inode(struct inode *inode)
 	EXT4_I(inode)->i_block_alloc_info = NULL;
 	if (unlikely(rsv))
 		kfree(rsv);
+	jbd2_journal_release_jbd_inode(EXT4_SB(inode->i_sb)->s_journal,
+				       &EXT4_I(inode)->jinode);
 }
 
 static inline void ext4_show_quota_options(struct seq_file *seq, struct super_block *sb)
@@ -671,7 +681,6 @@ static int ext4_show_options(struct seq_file *seq, struct vfsmount *vfs)
 	unsigned long def_mount_opts;
 	struct super_block *sb = vfs->mnt_sb;
 	struct ext4_sb_info *sbi = EXT4_SB(sb);
-	journal_t *journal = sbi->s_journal;
 	struct ext4_super_block *es = sbi->s_es;
 
 	def_mount_opts = le32_to_cpu(es->s_default_mount_opts);
@@ -747,6 +756,9 @@ static int ext4_show_options(struct seq_file *seq, struct vfsmount *vfs)
 		seq_puts(seq, ",nomballoc");
 	if (test_opt(sb, I_VERSION))
 		seq_puts(seq, ",i_version");
+	if (!test_opt(sb, DELALLOC))
+		seq_puts(seq, ",nodelalloc");
+
 
 	if (sbi->s_stripe)
 		seq_printf(seq, ",stripe=%lu", sbi->s_stripe);
@@ -894,7 +906,7 @@ enum {
 	Opt_jqfmt_vfsold, Opt_jqfmt_vfsv0, Opt_quota, Opt_noquota,
 	Opt_ignore, Opt_barrier, Opt_err, Opt_resize, Opt_usrquota,
 	Opt_grpquota, Opt_extents, Opt_noextents, Opt_i_version,
-	Opt_mballoc, Opt_nomballoc, Opt_stripe,
+	Opt_mballoc, Opt_nomballoc, Opt_stripe, Opt_delalloc, Opt_nodelalloc,
 };
 
 static match_table_t tokens = {
@@ -953,6 +965,8 @@ static match_table_t tokens = {
 	{Opt_nomballoc, "nomballoc"},
 	{Opt_stripe, "stripe=%u"},
 	{Opt_resize, "resize"},
+	{Opt_delalloc, "delalloc"},
+	{Opt_nodelalloc, "nodelalloc"},
 	{Opt_err, NULL},
 };
 
@@ -990,6 +1004,7 @@ static int parse_options (char *options, struct super_block *sb,
 	int qtype, qfmt;
 	char *qname;
 #endif
+	ext4_fsblk_t last_block;
 
 	if (!options)
 		return 1;
@@ -1309,15 +1324,39 @@ static int parse_options (char *options, struct super_block *sb,
 			clear_opt(sbi->s_mount_opt, NOBH);
 			break;
 		case Opt_extents:
+			if (!EXT4_HAS_INCOMPAT_FEATURE(sb,
+					EXT4_FEATURE_INCOMPAT_EXTENTS)) {
+				ext4_warning(sb, __func__,
+					"extents feature not enabled "
+					"on this filesystem, use tune2fs\n");
+				return 0;
+			}
 			set_opt (sbi->s_mount_opt, EXTENTS);
 			break;
 		case Opt_noextents:
+			/*
+			 * When e2fsprogs support resizing an already existing
+			 * ext3 file system to greater than 2**32 we need to
+			 * add support to block allocator to handle growing
+			 * already existing block  mapped inode so that blocks
+			 * allocated for them fall within 2**32
+			 */
+			last_block = ext4_blocks_count(sbi->s_es) - 1;
+			if (last_block  > 0xffffffffULL) {
+				printk(KERN_ERR "EXT4-fs: Filesystem too "
+						"large to mount with "
+						"-o noextents options\n");
+				return 0;
+			}
 			clear_opt (sbi->s_mount_opt, EXTENTS);
 			break;
 		case Opt_i_version:
 			set_opt(sbi->s_mount_opt, I_VERSION);
 			sb->s_flags |= MS_I_VERSION;
 			break;
+		case Opt_nodelalloc:
+			clear_opt(sbi->s_mount_opt, DELALLOC);
+			break;
 		case Opt_mballoc:
 			set_opt(sbi->s_mount_opt, MBALLOC);
 			break;
@@ -1331,6 +1370,9 @@ static int parse_options (char *options, struct super_block *sb,
 				return 0;
 			sbi->s_stripe = option;
 			break;
+		case Opt_delalloc:
+			set_opt(sbi->s_mount_opt, DELALLOC);
+			break;
 		default:
 			printk (KERN_ERR
 				"EXT4-fs: Unrecognized mount option \"%s\" "
@@ -1443,6 +1485,54 @@ static int ext4_setup_super(struct super_block *sb, struct ext4_super_block *es,
 	return res;
 }
 
+static int ext4_fill_flex_info(struct super_block *sb)
+{
+	struct ext4_sb_info *sbi = EXT4_SB(sb);
+	struct ext4_group_desc *gdp = NULL;
+	struct buffer_head *bh;
+	ext4_group_t flex_group_count;
+	ext4_group_t flex_group;
+	int groups_per_flex = 0;
+	__u64 block_bitmap = 0;
+	int i;
+
+	if (!sbi->s_es->s_log_groups_per_flex) {
+		sbi->s_log_groups_per_flex = 0;
+		return 1;
+	}
+
+	sbi->s_log_groups_per_flex = sbi->s_es->s_log_groups_per_flex;
+	groups_per_flex = 1 << sbi->s_log_groups_per_flex;
+
+	flex_group_count = (sbi->s_groups_count + groups_per_flex - 1) /
+		groups_per_flex;
+	sbi->s_flex_groups = kmalloc(flex_group_count *
+				     sizeof(struct flex_groups), GFP_KERNEL);
+	if (sbi->s_flex_groups == NULL) {
+		printk(KERN_ERR "EXT4-fs: not enough memory\n");
+		goto failed;
+	}
+	memset(sbi->s_flex_groups, 0, flex_group_count *
+	       sizeof(struct flex_groups));
+
+	gdp = ext4_get_group_desc(sb, 1, &bh);
+	block_bitmap = ext4_block_bitmap(sb, gdp) - 1;
+
+	for (i = 0; i < sbi->s_groups_count; i++) {
+		gdp = ext4_get_group_desc(sb, i, &bh);
+
+		flex_group = ext4_flex_group(sbi, i);
+		sbi->s_flex_groups[flex_group].free_inodes +=
+			le16_to_cpu(gdp->bg_free_inodes_count);
+		sbi->s_flex_groups[flex_group].free_blocks +=
+			le16_to_cpu(gdp->bg_free_blocks_count);
+	}
+
+	return 1;
+failed:
+	return 0;
+}
+
 __le16 ext4_group_desc_csum(struct ext4_sb_info *sbi, __u32 block_group,
 			    struct ext4_group_desc *gdp)
 {
@@ -1810,8 +1900,8 @@ static unsigned long ext4_get_stripe_size(struct ext4_sb_info *sbi)
 }
 
 static int ext4_fill_super (struct super_block *sb, void *data, int silent)
-				__releases(kernel_sem)
-				__acquires(kernel_sem)
+				__releases(kernel_lock)
+				__acquires(kernel_lock)
 
 {
 	struct buffer_head * bh;
@@ -1851,11 +1941,6 @@ static int ext4_fill_super (struct super_block *sb, void *data, int silent)
 		goto out_fail;
 	}
 
-	if (!sb_set_blocksize(sb, blocksize)) {
-		printk(KERN_ERR "EXT4-fs: bad blocksize %d.\n", blocksize);
-		goto out_fail;
-	}
-
 	/*
 	 * The ext4 superblock will not be buffer aligned for other than 1kB
 	 * block sizes.  We need to calculate the offset from buffer start.
@@ -1919,15 +2004,28 @@ static int ext4_fill_super (struct super_block *sb, void *data, int silent)
 
 	/*
 	 * turn on extents feature by default in ext4 filesystem
-	 * User -o noextents to turn it off
+	 * only if feature flag already set by mkfs or tune2fs.
+	 * Use -o noextents to turn it off
 	 */
-	set_opt(sbi->s_mount_opt, EXTENTS);
+	if (EXT4_HAS_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_EXTENTS))
+		set_opt(sbi->s_mount_opt, EXTENTS);
+	else
+		ext4_warning(sb, __func__,
+			"extents feature not enabled on this filesystem, "
+			"use tune2fs.\n");
 	/*
-	 * turn on mballoc feature by default in ext4 filesystem
-	 * User -o nomballoc to turn it off
+	 * turn on mballoc code by default in ext4 filesystem
+	 * Use -o nomballoc to turn it off
 	 */
 	set_opt(sbi->s_mount_opt, MBALLOC);
 
+	/*
+	 * enable delayed allocation by default
+	 * Use -o nodelalloc to turn it off
+	 */
+	set_opt(sbi->s_mount_opt, DELALLOC);
+
+
 	if (!parse_options ((char *) data, sb, &journal_inum, &journal_devnum,
 			    NULL, 0))
 		goto failed_mount;
@@ -2138,6 +2236,14 @@ static int ext4_fill_super (struct super_block *sb, void *data, int silent)
 		printk(KERN_ERR "EXT4-fs: group descriptors corrupted!\n");
 		goto failed_mount2;
 	}
+	if (EXT4_HAS_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_FLEX_BG))
+		if (!ext4_fill_flex_info(sb)) {
+			printk(KERN_ERR
+			       "EXT4-fs: unable to initialize "
+			       "flex_bg meta info!\n");
+			goto failed_mount2;
+		}
+
 	sbi->s_gdb_count = db_count;
 	get_random_bytes(&sbi->s_next_generation, sizeof(u32));
 	spin_lock_init(&sbi->s_next_gen_lock);
@@ -2358,6 +2464,13 @@ static int ext4_fill_super (struct super_block *sb, void *data, int silent)
 		test_opt(sb,DATA_FLAGS) == EXT4_MOUNT_ORDERED_DATA ? "ordered":
 		"writeback");
 
+	if (test_opt(sb, DATA_FLAGS) == EXT4_MOUNT_JOURNAL_DATA) {
+		printk(KERN_WARNING "EXT4-fs: Ignoring delalloc option - "
+				"requested data journaling mode\n");
+		clear_opt(sbi->s_mount_opt, DELALLOC);
+	} else if (test_opt(sb, DELALLOC))
+		printk(KERN_INFO "EXT4-fs: delayed allocation enabled\n");
+
 	ext4_ext_init(sb);
 	ext4_mb_init(sb, needs_recovery);
 
@@ -2372,6 +2485,7 @@ static int ext4_fill_super (struct super_block *sb, void *data, int silent)
 
 failed_mount4:
 	jbd2_journal_destroy(sbi->s_journal);
+	sbi->s_journal = NULL;
 failed_mount3:
 	percpu_counter_destroy(&sbi->s_freeblocks_counter);
 	percpu_counter_destroy(&sbi->s_freeinodes_counter);
@@ -3325,7 +3439,7 @@ static ssize_t ext4_quota_write(struct super_block *sb, int type,
 			err = ext4_journal_dirty_metadata(handle, bh);
 		else {
 			/* Always do at least ordered writes for quotas */
-			err = ext4_journal_dirty_data(handle, bh);
+			err = ext4_jbd2_file_inode(handle, inode);
 			mark_buffer_dirty(bh);
 		}
 		brelse(bh);

fs/ext4/xattr.c

@@ -810,7 +810,7 @@ ext4_xattr_block_set(handle_t *handle, struct inode *inode,
 			/* We need to allocate a new block */
 			ext4_fsblk_t goal = ext4_group_first_block_no(sb,
 						EXT4_I(inode)->i_block_group);
-			ext4_fsblk_t block = ext4_new_block(handle, inode,
+			ext4_fsblk_t block = ext4_new_meta_block(handle, inode,
 							goal, &error);
 			if (error)
 				goto cleanup;

fs/ext4/xattr_trusted.c

@@ -13,13 +13,11 @@
 #include "ext4.h"
 #include "xattr.h"
 
-#define XATTR_TRUSTED_PREFIX "trusted."
-
 static size_t
 ext4_xattr_trusted_list(struct inode *inode, char *list, size_t list_size,
 			const char *name, size_t name_len)
 {
-	const size_t prefix_len = sizeof(XATTR_TRUSTED_PREFIX)-1;
+	const size_t prefix_len = XATTR_TRUSTED_PREFIX_LEN;
 	const size_t total_len = prefix_len + name_len + 1;
 
 	if (!capable(CAP_SYS_ADMIN))

fs/ext4/xattr_user.c

@@ -12,13 +12,11 @@
 #include "ext4.h"
 #include "xattr.h"
 
-#define XATTR_USER_PREFIX "user."
-
 static size_t
 ext4_xattr_user_list(struct inode *inode, char *list, size_t list_size,
 		     const char *name, size_t name_len)
 {
-	const size_t prefix_len = sizeof(XATTR_USER_PREFIX)-1;
+	const size_t prefix_len = XATTR_USER_PREFIX_LEN;
 	const size_t total_len = prefix_len + name_len + 1;
 
 	if (!test_opt(inode->i_sb, XATTR_USER))

fs/jbd2/checkpoint.c

@@ -688,7 +688,6 @@ void __jbd2_journal_drop_transaction(journal_t *journal, transaction_t *transact
 
 	J_ASSERT(transaction->t_state == T_FINISHED);
 	J_ASSERT(transaction->t_buffers == NULL);
-	J_ASSERT(transaction->t_sync_datalist == NULL);
 	J_ASSERT(transaction->t_forget == NULL);
 	J_ASSERT(transaction->t_iobuf_list == NULL);
 	J_ASSERT(transaction->t_shadow_list == NULL);

fs/jbd2/journal.c

@@ -50,7 +50,6 @@ EXPORT_SYMBOL(jbd2_journal_unlock_updates);
 EXPORT_SYMBOL(jbd2_journal_get_write_access);
 EXPORT_SYMBOL(jbd2_journal_get_create_access);
 EXPORT_SYMBOL(jbd2_journal_get_undo_access);
-EXPORT_SYMBOL(jbd2_journal_dirty_data);
 EXPORT_SYMBOL(jbd2_journal_dirty_metadata);
 EXPORT_SYMBOL(jbd2_journal_release_buffer);
 EXPORT_SYMBOL(jbd2_journal_forget);
@@ -82,6 +81,10 @@ EXPORT_SYMBOL(jbd2_journal_blocks_per_page);
 EXPORT_SYMBOL(jbd2_journal_invalidatepage);
 EXPORT_SYMBOL(jbd2_journal_try_to_free_buffers);
 EXPORT_SYMBOL(jbd2_journal_force_commit);
+EXPORT_SYMBOL(jbd2_journal_file_inode);
+EXPORT_SYMBOL(jbd2_journal_init_jbd_inode);
+EXPORT_SYMBOL(jbd2_journal_release_jbd_inode);
+EXPORT_SYMBOL(jbd2_journal_begin_ordered_truncate);
 
 static int journal_convert_superblock_v1(journal_t *, journal_superblock_t *);
 static void __journal_abort_soft (journal_t *journal, int errno);
@@ -2194,6 +2197,54 @@ void jbd2_journal_put_journal_head(struct journal_head *jh)
 	jbd_unlock_bh_journal_head(bh);
 }
 
+/*
+ * Initialize jbd inode head
+ */
+void jbd2_journal_init_jbd_inode(struct jbd2_inode *jinode, struct inode *inode)
+{
+	jinode->i_transaction = NULL;
+	jinode->i_next_transaction = NULL;
+	jinode->i_vfs_inode = inode;
+	jinode->i_flags = 0;
+	INIT_LIST_HEAD(&jinode->i_list);
+}
+
+/*
+ * Function to be called before we start removing inode from memory (i.e.,
+ * clear_inode() is a fine place to be called from). It removes inode from
+ * transaction's lists.
+ */
+void jbd2_journal_release_jbd_inode(journal_t *journal,
+				    struct jbd2_inode *jinode)
+{
+	int writeout = 0;
+
+	if (!journal)
+		return;
+restart:
+	spin_lock(&journal->j_list_lock);
+	/* Is commit writing out inode - we have to wait */
+	if (jinode->i_flags & JI_COMMIT_RUNNING) {
+		wait_queue_head_t *wq;
+		DEFINE_WAIT_BIT(wait, &jinode->i_flags, __JI_COMMIT_RUNNING);
+		wq = bit_waitqueue(&jinode->i_flags, __JI_COMMIT_RUNNING);
+		prepare_to_wait(wq, &wait.wait, TASK_UNINTERRUPTIBLE);
+		spin_unlock(&journal->j_list_lock);
+		schedule();
+		finish_wait(wq, &wait.wait);
+		goto restart;
+	}
+
+	/* Do we need to wait for data writeback? */
+	if (journal->j_committing_transaction == jinode->i_transaction)
+		writeout = 1;
+	if (jinode->i_transaction) {
+		list_del(&jinode->i_list);
+		jinode->i_transaction = NULL;
+	}
+	spin_unlock(&journal->j_list_lock);
+}
+
 /*
  * debugfs tunables
  */

fs/mpage.c

@@ -82,7 +82,7 @@ static void mpage_end_io_write(struct bio *bio, int err)
 	bio_put(bio);
 }
 
-static struct bio *mpage_bio_submit(int rw, struct bio *bio)
+struct bio *mpage_bio_submit(int rw, struct bio *bio)
 {
 	bio->bi_end_io = mpage_end_io_read;
 	if (rw == WRITE)
@@ -90,6 +90,7 @@ static struct bio *mpage_bio_submit(int rw, struct bio *bio)
 	submit_bio(rw, bio);
 	return NULL;
 }
+EXPORT_SYMBOL(mpage_bio_submit);
 
 static struct bio *
 mpage_alloc(struct block_device *bdev,
@@ -435,15 +436,9 @@ EXPORT_SYMBOL(mpage_readpage);
  * written, so it can intelligently allocate a suitably-sized BIO.  For now,
  * just allocate full-size (16-page) BIOs.
  */
-struct mpage_data {
-	struct bio *bio;
-	sector_t last_block_in_bio;
-	get_block_t *get_block;
-	unsigned use_writepage;
-};
 
-static int __mpage_writepage(struct page *page, struct writeback_control *wbc,
-			     void *data)
+int __mpage_writepage(struct page *page, struct writeback_control *wbc,
+		      void *data)
 {
 	struct mpage_data *mpd = data;
 	struct bio *bio = mpd->bio;
@@ -651,6 +646,7 @@ static int __mpage_writepage(struct page *page, struct writeback_control *wbc,
 	mpd->bio = bio;
 	return ret;
 }
+EXPORT_SYMBOL(__mpage_writepage);
 
 /**
  * mpage_writepages - walk the list of dirty pages of the given address space & writepage() all of them

include/linux/fs.h

@@ -1740,6 +1740,8 @@ extern int wait_on_page_writeback_range(struct address_space *mapping,
 				pgoff_t start, pgoff_t end);
 extern int __filemap_fdatawrite_range(struct address_space *mapping,
 				loff_t start, loff_t end, int sync_mode);
+extern int filemap_fdatawrite_range(struct address_space *mapping,
+				loff_t start, loff_t end);
 
 extern long do_fsync(struct file *file, int datasync);
 extern void sync_supers(void);

include/linux/jbd2.h

@@ -168,6 +168,8 @@ struct commit_header {
 	unsigned char   h_chksum_size;
 	unsigned char 	h_padding[2];
 	__be32 		h_chksum[JBD2_CHECKSUM_BYTES];
+	__be64		h_commit_sec;
+	__be32		h_commit_nsec;
 };
 
 /*
@@ -379,6 +381,38 @@ static inline void jbd_unlock_bh_journal_head(struct buffer_head *bh)
 	bit_spin_unlock(BH_JournalHead, &bh->b_state);
 }
 
+/* Flags in jbd_inode->i_flags */
+#define __JI_COMMIT_RUNNING 0
+/* Commit of the inode data in progress. We use this flag to protect us from
+ * concurrent deletion of inode. We cannot use reference to inode for this
+ * since we cannot afford doing last iput() on behalf of kjournald
+ */
+#define JI_COMMIT_RUNNING (1 << __JI_COMMIT_RUNNING)
+
+/**
+ * struct jbd_inode is the structure linking inodes in ordered mode
+ *   present in a transaction so that we can sync them during commit.
+ */
+struct jbd2_inode {
+	/* Which transaction does this inode belong to? Either the running
+	 * transaction or the committing one. [j_list_lock] */
+	transaction_t *i_transaction;
+
+	/* Pointer to the running transaction modifying inode's data in case
+	 * there is already a committing transaction touching it. [j_list_lock] */
+	transaction_t *i_next_transaction;
+
+	/* List of inodes in the i_transaction [j_list_lock] */
+	struct list_head i_list;
+
+	/* VFS inode this inode belongs to [constant during the lifetime
+	 * of the structure] */
+	struct inode *i_vfs_inode;
+
+	/* Flags of inode [j_list_lock] */
+	unsigned int i_flags;
+};
+
 struct jbd2_revoke_table_s;
 
 /**
@@ -508,24 +542,12 @@ struct transaction_s
 	 */
 	struct journal_head	*t_reserved_list;
 
-	/*
-	 * Doubly-linked circular list of all buffers under writeout during
-	 * commit [j_list_lock]
-	 */
-	struct journal_head	*t_locked_list;
-
 	/*
 	 * Doubly-linked circular list of all metadata buffers owned by this
 	 * transaction [j_list_lock]
 	 */
 	struct journal_head	*t_buffers;
 
-	/*
-	 * Doubly-linked circular list of all data buffers still to be
-	 * flushed before this transaction can be committed [j_list_lock]
-	 */
-	struct journal_head	*t_sync_datalist;
-
 	/*
 	 * Doubly-linked circular list of all forget buffers (superseded
 	 * buffers which we can un-checkpoint once this transaction commits)
@@ -564,6 +586,12 @@ struct transaction_s
 	 */
 	struct journal_head	*t_log_list;
 
+	/*
+	 * List of inodes whose data we've modified in data=ordered mode.
+	 * [j_list_lock]
+	 */
+	struct list_head	t_inode_list;
+
 	/*
 	 * Protects info related to handles
 	 */
@@ -1004,7 +1032,6 @@ extern int	 jbd2_journal_extend (handle_t *, int nblocks);
 extern int	 jbd2_journal_get_write_access(handle_t *, struct buffer_head *);
 extern int	 jbd2_journal_get_create_access (handle_t *, struct buffer_head *);
 extern int	 jbd2_journal_get_undo_access(handle_t *, struct buffer_head *);
-extern int	 jbd2_journal_dirty_data (handle_t *, struct buffer_head *);
 extern int	 jbd2_journal_dirty_metadata (handle_t *, struct buffer_head *);
 extern void	 jbd2_journal_release_buffer (handle_t *, struct buffer_head *);
 extern int	 jbd2_journal_forget (handle_t *, struct buffer_head *);
@@ -1044,6 +1071,10 @@ extern void	   jbd2_journal_ack_err    (journal_t *);
 extern int	   jbd2_journal_clear_err  (journal_t *);
 extern int	   jbd2_journal_bmap(journal_t *, unsigned long, unsigned long long *);
 extern int	   jbd2_journal_force_commit(journal_t *);
+extern int	   jbd2_journal_file_inode(handle_t *handle, struct jbd2_inode *inode);
+extern int	   jbd2_journal_begin_ordered_truncate(struct jbd2_inode *inode, loff_t new_size);
+extern void	   jbd2_journal_init_jbd_inode(struct jbd2_inode *jinode, struct inode *inode);
+extern void	   jbd2_journal_release_jbd_inode(journal_t *journal, struct jbd2_inode *jinode);
 
 /*
  * journal_head management
@@ -1179,15 +1210,13 @@ static inline int jbd_space_needed(journal_t *journal)
 
 /* journaling buffer types */
 #define BJ_None		0	/* Not journaled */
-#define BJ_SyncData	1	/* Normal data: flush before commit */
-#define BJ_Metadata	2	/* Normal journaled metadata */
-#define BJ_Forget	3	/* Buffer superseded by this transaction */
-#define BJ_IO		4	/* Buffer is for temporary IO use */
-#define BJ_Shadow	5	/* Buffer contents being shadowed to the log */
-#define BJ_LogCtl	6	/* Buffer contains log descriptors */
-#define BJ_Reserved	7	/* Buffer is reserved for access by journal */
-#define BJ_Locked	8	/* Locked for I/O during commit */
-#define BJ_Types	9
+#define BJ_Metadata	1	/* Normal journaled metadata */
+#define BJ_Forget	2	/* Buffer superseded by this transaction */
+#define BJ_IO		3	/* Buffer is for temporary IO use */
+#define BJ_Shadow	4	/* Buffer contents being shadowed to the log */
+#define BJ_LogCtl	5	/* Buffer contains log descriptors */
+#define BJ_Reserved	6	/* Buffer is reserved for access by journal */
+#define BJ_Types	7
 
 extern int jbd_blocks_per_page(struct inode *inode);
 

include/linux/mpage.h

@@ -11,11 +11,21 @@
  */
 #ifdef CONFIG_BLOCK
 
+struct mpage_data {
+	struct bio *bio;
+	sector_t last_block_in_bio;
+	get_block_t *get_block;
+	unsigned use_writepage;
+};
+
 struct writeback_control;
 
+struct bio *mpage_bio_submit(int rw, struct bio *bio);
 int mpage_readpages(struct address_space *mapping, struct list_head *pages,
 				unsigned nr_pages, get_block_t get_block);
 int mpage_readpage(struct page *page, get_block_t get_block);
+int __mpage_writepage(struct page *page, struct writeback_control *wbc,
+		      void *data);
 int mpage_writepages(struct address_space *mapping,
 		struct writeback_control *wbc, get_block_t get_block);
 int mpage_writepage(struct page *page, get_block_t *get_block,

include/linux/percpu_counter.h

@@ -35,7 +35,7 @@ int percpu_counter_init_irq(struct percpu_counter *fbc, s64 amount);
 void percpu_counter_destroy(struct percpu_counter *fbc);
 void percpu_counter_set(struct percpu_counter *fbc, s64 amount);
 void __percpu_counter_add(struct percpu_counter *fbc, s64 amount, s32 batch);
-s64 __percpu_counter_sum(struct percpu_counter *fbc);
+s64 __percpu_counter_sum(struct percpu_counter *fbc, int set);
 
 static inline void percpu_counter_add(struct percpu_counter *fbc, s64 amount)
 {
@@ -44,13 +44,19 @@ static inline void percpu_counter_add(struct percpu_counter *fbc, s64 amount)
 
 static inline s64 percpu_counter_sum_positive(struct percpu_counter *fbc)
 {
-	s64 ret = __percpu_counter_sum(fbc);
+	s64 ret = __percpu_counter_sum(fbc, 0);
 	return ret < 0 ? 0 : ret;
 }
 
+static inline s64 percpu_counter_sum_and_set(struct percpu_counter *fbc)
+{
+	return __percpu_counter_sum(fbc, 1);
+}
+
+
 static inline s64 percpu_counter_sum(struct percpu_counter *fbc)
 {
-	return __percpu_counter_sum(fbc);
+	return __percpu_counter_sum(fbc, 0);
 }
 
 static inline s64 percpu_counter_read(struct percpu_counter *fbc)

include/linux/writeback.h

@@ -63,6 +63,7 @@ struct writeback_control {
 	unsigned for_writepages:1;	/* This is a writepages() call */
 	unsigned range_cyclic:1;	/* range_start is cyclic */
 	unsigned more_io:1;		/* more io to be dispatched */
+	unsigned range_cont:1;
 };
 
 /*

lib/percpu_counter.c

@@ -52,7 +52,7 @@ EXPORT_SYMBOL(__percpu_counter_add);
  * Add up all the per-cpu counts, return the result.  This is a more accurate
  * but much slower version of percpu_counter_read_positive()
  */
-s64 __percpu_counter_sum(struct percpu_counter *fbc)
+s64 __percpu_counter_sum(struct percpu_counter *fbc, int set)
 {
 	s64 ret;
 	int cpu;
@@ -62,7 +62,12 @@ s64 __percpu_counter_sum(struct percpu_counter *fbc)
 	for_each_online_cpu(cpu) {
 		s32 *pcount = per_cpu_ptr(fbc->counters, cpu);
 		ret += *pcount;
+		if (set)
+			*pcount = 0;
 	}
+	if (set)
+		fbc->count = ret;
+
 	spin_unlock(&fbc->lock);
 	return ret;
 }

mm/filemap.c

@@ -236,11 +236,12 @@ int filemap_fdatawrite(struct address_space *mapping)
 }
 EXPORT_SYMBOL(filemap_fdatawrite);
 
-static int filemap_fdatawrite_range(struct address_space *mapping, loff_t start,
+int filemap_fdatawrite_range(struct address_space *mapping, loff_t start,
 				loff_t end)
 {
 	return __filemap_fdatawrite_range(mapping, start, end, WB_SYNC_ALL);
 }
+EXPORT_SYMBOL(filemap_fdatawrite_range);
 
 /**
  * filemap_flush - mostly a non-blocking flush

mm/page-writeback.c

@@ -960,6 +960,9 @@ int write_cache_pages(struct address_space *mapping,
 	}
 	if (wbc->range_cyclic || (range_whole && wbc->nr_to_write > 0))
 		mapping->writeback_index = index;
+
+	if (wbc->range_cont)
+		wbc->range_start = index << PAGE_CACHE_SHIFT;
 	return ret;
 }
 EXPORT_SYMBOL(write_cache_pages);