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: (40 commits)
ext4: Make fsync sync new parent directories in no-journal mode
ext4: Drop whitespace at end of lines
ext4: Fix compat EXT4_IOC_ADD_GROUP
ext4: Conditionally define compat ioctl numbers
tracing: Convert more ext4 events to DEFINE_EVENT
ext4: Add new tracepoints to track mballoc's buddy bitmap loads
ext4: Add a missing trace hook
ext4: restart ext4_ext_remove_space() after transaction restart
ext4: Clear the EXT4_EOFBLOCKS_FL flag only when warranted
ext4: Avoid crashing on NULL ptr dereference on a filesystem error
ext4: Use bitops to read/modify i_flags in struct ext4_inode_info
ext4: Convert calls of ext4_error() to EXT4_ERROR_INODE()
ext4: Convert callers of ext4_get_blocks() to use ext4_map_blocks()
ext4: Add new abstraction ext4_map_blocks() underneath ext4_get_blocks()
ext4: Use our own write_cache_pages()
ext4: Show journal_checksum option
ext4: Fix for ext4_mb_collect_stats()
ext4: check for a good block group before loading buddy pages
ext4: Prevent creation of files larger than RLIMIT_FSIZE using fallocate
ext4: Remove extraneous newlines in ext4_msg() calls
...

Fixed up trivial conflict in fs/ext4/fsync.c

fs/ext4/balloc.c

···
 	ret = ext4_mb_new_blocks(handle, &ar, errp);
 	if (count)
 		*count = ar.len;
-
 	/*
-	 * Account for the allocated meta blocks
+	 * Account for the allocated meta blocks.  We will never
+	 * fail EDQUOT for metdata, but we do account for it.
 	 */
 	if (!(*errp) && EXT4_I(inode)->i_delalloc_reserved_flag) {
 		spin_lock(&EXT4_I(inode)->i_block_reservation_lock);
 		EXT4_I(inode)->i_allocated_meta_blocks += ar.len;
 		spin_unlock(&EXT4_I(inode)->i_block_reservation_lock);
+		dquot_alloc_block_nofail(inode, ar.len);
 	}
 	return ret;
 }

fs/ext4/block_validity.c

···
 		else if (start_blk >= (entry->start_blk + entry->count))
 			n = &(*n)->rb_right;
 		else {
-			if (start_blk + count > (entry->start_blk + 
+			if (start_blk + count > (entry->start_blk +
 						 entry->count))
-				entry->count = (start_blk + count - 
+				entry->count = (start_blk + count -
 						entry->start_blk);
 			new_node = *n;
 			new_entry = rb_entry(new_node, struct ext4_system_zone,

fs/ext4/dir.c

···
 		error_msg = "inode out of bounds";
 
 	if (error_msg != NULL)
-		__ext4_error(dir->i_sb, function,
-			"bad entry in directory #%lu: %s - block=%llu"
+		ext4_error_inode(function, dir,
+			"bad entry in directory: %s - block=%llu"
 			"offset=%u(%u), inode=%u, rec_len=%d, name_len=%d",
-			dir->i_ino, error_msg, 
-			(unsigned long long) bh->b_blocknr,     
+			error_msg, (unsigned long long) bh->b_blocknr,
 			(unsigned) (offset%bh->b_size), offset,
 			le32_to_cpu(de->inode),
 			rlen, de->name_len);
···
 
 	if (EXT4_HAS_COMPAT_FEATURE(inode->i_sb,
 				    EXT4_FEATURE_COMPAT_DIR_INDEX) &&
-	    ((EXT4_I(inode)->i_flags & EXT4_INDEX_FL) ||
+	    ((ext4_test_inode_flag(inode, EXT4_INODE_INDEX)) ||
 	     ((inode->i_size >> sb->s_blocksize_bits) == 1))) {
 		err = ext4_dx_readdir(filp, dirent, filldir);
 		if (err != ERR_BAD_DX_DIR) {
···
 		 * We don't set the inode dirty flag since it's not
 		 * critical that it get flushed back to the disk.
 		 */
-		EXT4_I(filp->f_path.dentry->d_inode)->i_flags &= ~EXT4_INDEX_FL;
+		ext4_clear_inode_flag(filp->f_path.dentry->d_inode, EXT4_INODE_INDEX);
 	}
 	stored = 0;
 	offset = filp->f_pos & (sb->s_blocksize - 1);
 
 	while (!error && !stored && filp->f_pos < inode->i_size) {
-		ext4_lblk_t blk = filp->f_pos >> EXT4_BLOCK_SIZE_BITS(sb);
-		struct buffer_head map_bh;
+		struct ext4_map_blocks map;
 		struct buffer_head *bh = NULL;
 
-		map_bh.b_state = 0;
-		err = ext4_get_blocks(NULL, inode, blk, 1, &map_bh, 0);
+		map.m_lblk = filp->f_pos >> EXT4_BLOCK_SIZE_BITS(sb);
+		map.m_len = 1;
+		err = ext4_map_blocks(NULL, inode, &map, 0);
 		if (err > 0) {
-			pgoff_t index = map_bh.b_blocknr >>
+			pgoff_t index = map.m_pblk >>
 					(PAGE_CACHE_SHIFT - inode->i_blkbits);
 			if (!ra_has_index(&filp->f_ra, index))
 				page_cache_sync_readahead(
···
 					&filp->f_ra, filp,
 					index, 1);
 			filp->f_ra.prev_pos = (loff_t)index << PAGE_CACHE_SHIFT;
-			bh = ext4_bread(NULL, inode, blk, 0, &err);
+			bh = ext4_bread(NULL, inode, map.m_lblk, 0, &err);
 		}
 
 		/*
···
 		 */
 		if (!bh) {
 			if (!dir_has_error) {
-				ext4_error(sb, "directory #%lu "
+				EXT4_ERROR_INODE(inode, "directory "
 					   "contains a hole at offset %Lu",
-					   inode->i_ino,
 					   (unsigned long long) filp->f_pos);
 				dir_has_error = 1;
 			}

fs/ext4/ext4.h

···
 #include <linux/wait.h>
 #include <linux/blockgroup_lock.h>
 #include <linux/percpu_counter.h>
+#ifdef __KERNEL__
+#include <linux/compat.h>
+#endif
 
 /*
  * The fourth extended filesystem constants/structures
···
 #endif
 
 #define EXT4_ERROR_INODE(inode, fmt, a...) \
-	ext4_error_inode(__func__, (inode), (fmt), ## a);
+	ext4_error_inode(__func__, (inode), (fmt), ## a)
 
 #define EXT4_ERROR_FILE(file, fmt, a...)	\
-	ext4_error_file(__func__, (file), (fmt), ## a);
+	ext4_error_file(__func__, (file), (fmt), ## a)
 
 /* data type for block offset of block group */
 typedef int ext4_grpblk_t;
···
 typedef unsigned int ext4_group_t;
 
 /*
- * Flags used in mballoc's allocation_context flags field.  
+ * Flags used in mballoc's allocation_context flags field.
  *
  * Also used to show what's going on for debugging purposes when the
  * flag field is exported via the traceport interface
···
 	ext4_fsblk_t pright;
 	/* flags. see above EXT4_MB_HINT_* */
 	unsigned int flags;
+};
+
+/*
+ * Logical to physical block mapping, used by ext4_map_blocks()
+ *
+ * This structure is used to pass requests into ext4_map_blocks() as
+ * well as to store the information returned by ext4_map_blocks().  It
+ * takes less room on the stack than a struct buffer_head.
+ */
+#define EXT4_MAP_NEW		(1 << BH_New)
+#define EXT4_MAP_MAPPED		(1 << BH_Mapped)
+#define EXT4_MAP_UNWRITTEN	(1 << BH_Unwritten)
+#define EXT4_MAP_BOUNDARY	(1 << BH_Boundary)
+#define EXT4_MAP_UNINIT		(1 << BH_Uninit)
+#define EXT4_MAP_FLAGS		(EXT4_MAP_NEW | EXT4_MAP_MAPPED |\
+				 EXT4_MAP_UNWRITTEN | EXT4_MAP_BOUNDARY |\
+				 EXT4_MAP_UNINIT)
+
+struct ext4_map_blocks {
+	ext4_fsblk_t m_pblk;
+	ext4_lblk_t m_lblk;
+	unsigned int m_len;
+	unsigned int m_flags;
 };
 
 /*
···
 		return flags & EXT4_OTHER_FLMASK;
 }
 
+/*
+ * Inode flags used for atomic set/get
+ */
+enum {
+	EXT4_INODE_SECRM	= 0,	/* Secure deletion */
+	EXT4_INODE_UNRM		= 1,	/* Undelete */
+	EXT4_INODE_COMPR	= 2,	/* Compress file */
+	EXT4_INODE_SYNC		= 3,	/* Synchronous updates */
+	EXT4_INODE_IMMUTABLE	= 4,	/* Immutable file */
+	EXT4_INODE_APPEND	= 5,	/* writes to file may only append */
+	EXT4_INODE_NODUMP	= 6,	/* do not dump file */
+	EXT4_INODE_NOATIME	= 7,	/* do not update atime */
+/* Reserved for compression usage... */
+	EXT4_INODE_DIRTY	= 8,
+	EXT4_INODE_COMPRBLK	= 9,	/* One or more compressed clusters */
+	EXT4_INODE_NOCOMPR	= 10,	/* Don't compress */
+	EXT4_INODE_ECOMPR	= 11,	/* Compression error */
+/* End compression flags --- maybe not all used */
+	EXT4_INODE_INDEX	= 12,	/* hash-indexed directory */
+	EXT4_INODE_IMAGIC	= 13,	/* AFS directory */
+	EXT4_INODE_JOURNAL_DATA	= 14,	/* file data should be journaled */
+	EXT4_INODE_NOTAIL	= 15,	/* file tail should not be merged */
+	EXT4_INODE_DIRSYNC	= 16,	/* dirsync behaviour (directories only) */
+	EXT4_INODE_TOPDIR	= 17,	/* Top of directory hierarchies*/
+	EXT4_INODE_HUGE_FILE	= 18,	/* Set to each huge file */
+	EXT4_INODE_EXTENTS	= 19,	/* Inode uses extents */
+	EXT4_INODE_EA_INODE	= 21,	/* Inode used for large EA */
+	EXT4_INODE_EOFBLOCKS	= 22,	/* Blocks allocated beyond EOF */
+	EXT4_INODE_RESERVED	= 31,	/* reserved for ext4 lib */
+};
+
+#define TEST_FLAG_VALUE(FLAG) (EXT4_##FLAG##_FL == (1 << EXT4_INODE_##FLAG))
+#define CHECK_FLAG_VALUE(FLAG) if (!TEST_FLAG_VALUE(FLAG)) { \
+	printk(KERN_EMERG "EXT4 flag fail: " #FLAG ": %d %d\n", \
+		EXT4_##FLAG##_FL, EXT4_INODE_##FLAG); BUG_ON(1); }
+
+/*
+ * Since it's pretty easy to mix up bit numbers and hex values, and we
+ * can't do a compile-time test for ENUM values, we use a run-time
+ * test to make sure that EXT4_XXX_FL is consistent with respect to
+ * EXT4_INODE_XXX.  If all is well the printk and BUG_ON will all drop
+ * out so it won't cost any extra space in the compiled kernel image.
+ * But it's important that these values are the same, since we are
+ * using EXT4_INODE_XXX to test for the flag values, but EXT4_XX_FL
+ * must be consistent with the values of FS_XXX_FL defined in
+ * include/linux/fs.h and the on-disk values found in ext2, ext3, and
+ * ext4 filesystems, and of course the values defined in e2fsprogs.
+ *
+ * It's not paranoia if the Murphy's Law really *is* out to get you.  :-)
+ */
+static inline void ext4_check_flag_values(void)
+{
+	CHECK_FLAG_VALUE(SECRM);
+	CHECK_FLAG_VALUE(UNRM);
+	CHECK_FLAG_VALUE(COMPR);
+	CHECK_FLAG_VALUE(SYNC);
+	CHECK_FLAG_VALUE(IMMUTABLE);
+	CHECK_FLAG_VALUE(APPEND);
+	CHECK_FLAG_VALUE(NODUMP);
+	CHECK_FLAG_VALUE(NOATIME);
+	CHECK_FLAG_VALUE(DIRTY);
+	CHECK_FLAG_VALUE(COMPRBLK);
+	CHECK_FLAG_VALUE(NOCOMPR);
+	CHECK_FLAG_VALUE(ECOMPR);
+	CHECK_FLAG_VALUE(INDEX);
+	CHECK_FLAG_VALUE(IMAGIC);
+	CHECK_FLAG_VALUE(JOURNAL_DATA);
+	CHECK_FLAG_VALUE(NOTAIL);
+	CHECK_FLAG_VALUE(DIRSYNC);
+	CHECK_FLAG_VALUE(TOPDIR);
+	CHECK_FLAG_VALUE(HUGE_FILE);
+	CHECK_FLAG_VALUE(EXTENTS);
+	CHECK_FLAG_VALUE(EA_INODE);
+	CHECK_FLAG_VALUE(EOFBLOCKS);
+	CHECK_FLAG_VALUE(RESERVED);
+}
+
 /* Used to pass group descriptor data when online resize is done */
 struct ext4_new_group_input {
 	__u32 group;		/* Group number for this data */
···
 	__u16 reserved_blocks;	/* Number of reserved blocks in this group */
 	__u16 unused;
 };
+
+#if defined(__KERNEL__) && defined(CONFIG_COMPAT)
+struct compat_ext4_new_group_input {
+	u32 group;
+	compat_u64 block_bitmap;
+	compat_u64 inode_bitmap;
+	compat_u64 inode_table;
+	u32 blocks_count;
+	u16 reserved_blocks;
+	u16 unused;
+};
+#endif
 
 /* The struct ext4_new_group_input in kernel space, with free_blocks_count */
 struct ext4_new_group_data {
···
 #define EXT4_GET_BLOCKS_CREATE_UNINIT_EXT	(EXT4_GET_BLOCKS_UNINIT_EXT|\
 						 EXT4_GET_BLOCKS_CREATE)
 	/* Caller is from the delayed allocation writeout path,
-	   so set the magic i_delalloc_reserve_flag after taking the 
+	   so set the magic i_delalloc_reserve_flag after taking the
 	   inode allocation semaphore for */
 #define EXT4_GET_BLOCKS_DELALLOC_RESERVE	0x0004
 	/* caller is from the direct IO path, request to creation of an
···
 #define EXT4_IOC_ALLOC_DA_BLKS		_IO('f', 12)
 #define EXT4_IOC_MOVE_EXT		_IOWR('f', 15, struct move_extent)
 
+#if defined(__KERNEL__) && defined(CONFIG_COMPAT)
 /*
  * ioctl commands in 32 bit emulation
  */
···
 #define EXT4_IOC32_GETRSVSZ		_IOR('f', 5, int)
 #define EXT4_IOC32_SETRSVSZ		_IOW('f', 6, int)
 #define EXT4_IOC32_GROUP_EXTEND		_IOW('f', 7, unsigned int)
+#define EXT4_IOC32_GROUP_ADD		_IOW('f', 8, struct compat_ext4_new_group_input)
 #ifdef CONFIG_JBD2_DEBUG
 #define EXT4_IOC32_WAIT_FOR_READONLY	_IOR('f', 99, int)
 #endif
 #define EXT4_IOC32_GETVERSION_OLD	FS_IOC32_GETVERSION
 #define EXT4_IOC32_SETVERSION_OLD	FS_IOC32_SETVERSION
+#endif
 
 
 /*
···
  */
 struct ext4_inode_info {
 	__le32	i_data[15];	/* unconverted */
-	__u32	i_flags;
-	ext4_fsblk_t	i_file_acl;
 	__u32	i_dtime;
+	ext4_fsblk_t	i_file_acl;
 
 	/*
 	 * i_block_group is the number of the block group which contains
···
 	 */
 	ext4_group_t	i_block_group;
 	unsigned long	i_state_flags;		/* Dynamic state flags */
+	unsigned long	i_flags;
 
 	ext4_lblk_t		i_dir_start_lookup;
 #ifdef CONFIG_EXT4_FS_XATTR
···
 	EXT4_STATE_DA_ALLOC_CLOSE,	/* Alloc DA blks on close */
 	EXT4_STATE_EXT_MIGRATE,		/* Inode is migrating */
 	EXT4_STATE_DIO_UNWRITTEN,	/* need convert on dio done*/
+	EXT4_STATE_NEWENTRY,		/* File just added to dir */
 };
 
-static inline int ext4_test_inode_state(struct inode *inode, int bit)
-{
-	return test_bit(bit, &EXT4_I(inode)->i_state_flags);
+#define EXT4_INODE_BIT_FNS(name, field)					\
+static inline int ext4_test_inode_##name(struct inode *inode, int bit)	\
+{									\
+	return test_bit(bit, &EXT4_I(inode)->i_##field);		\
+}									\
+static inline void ext4_set_inode_##name(struct inode *inode, int bit)	\
+{									\
+	set_bit(bit, &EXT4_I(inode)->i_##field);			\
+}									\
+static inline void ext4_clear_inode_##name(struct inode *inode, int bit) \
+{									\
+	clear_bit(bit, &EXT4_I(inode)->i_##field);			\
 }
 
-static inline void ext4_set_inode_state(struct inode *inode, int bit)
-{
-	set_bit(bit, &EXT4_I(inode)->i_state_flags);
-}
-
-static inline void ext4_clear_inode_state(struct inode *inode, int bit)
-{
-	clear_bit(bit, &EXT4_I(inode)->i_state_flags);
-}
+EXT4_INODE_BIT_FNS(flag, flags)
+EXT4_INODE_BIT_FNS(state, state_flags)
 #else
 /* Assume that user mode programs are passing in an ext4fs superblock, not
  * a kernel struct super_block.  This will allow us to call the feature-test
···
 
 #define is_dx(dir) (EXT4_HAS_COMPAT_FEATURE(dir->i_sb, \
 				      EXT4_FEATURE_COMPAT_DIR_INDEX) && \
-		      (EXT4_I(dir)->i_flags & EXT4_INDEX_FL))
+		    ext4_test_inode_flag((dir), EXT4_INODE_INDEX))
 #define EXT4_DIR_LINK_MAX(dir) (!is_dx(dir) && (dir)->i_nlink >= EXT4_LINK_MAX)
 #define EXT4_DIR_LINK_EMPTY(dir) ((dir)->i_nlink == 2 || (dir)->i_nlink == 1)
 
···
 	ext4_grpblk_t	bb_first_free;	/* first free block */
 	ext4_grpblk_t	bb_free;	/* total free blocks */
 	ext4_grpblk_t	bb_fragments;	/* nr of freespace fragments */
+	ext4_grpblk_t	bb_largest_free_order;/* order of largest frag in BG */
 	struct          list_head bb_prealloc_list;
 #ifdef DOUBLE_CHECK
 	void            *bb_bitmap;
···
 extern int ext4_ext_writepage_trans_blocks(struct inode *, int);
 extern int ext4_ext_index_trans_blocks(struct inode *inode, int nrblocks,
 				       int chunk);
-extern int ext4_ext_get_blocks(handle_t *handle, struct inode *inode,
-			       ext4_lblk_t iblock, unsigned int max_blocks,
-			       struct buffer_head *bh_result, int flags);
+extern int ext4_ext_map_blocks(handle_t *handle, struct inode *inode,
+			       struct ext4_map_blocks *map, int flags);
 extern void ext4_ext_truncate(struct inode *);
 extern void ext4_ext_init(struct super_block *);
 extern void ext4_ext_release(struct super_block *);
···
 			  loff_t len);
 extern int ext4_convert_unwritten_extents(struct inode *inode, loff_t offset,
 			  ssize_t len);
+extern int ext4_map_blocks(handle_t *handle, struct inode *inode,
+			   struct ext4_map_blocks *map, int flags);
 extern int ext4_get_blocks(handle_t *handle, struct inode *inode,
 			   sector_t block, unsigned int max_blocks,
 			   struct buffer_head *bh, int flags);

fs/ext4/ext4_jbd2.h

···
 		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)
+	if (ext4_test_inode_flag(inode, EXT4_INODE_JOURNAL_DATA))
 		return 1;
 	return 0;
 }
···
 		return 0;
 	if (!S_ISREG(inode->i_mode))
 		return 0;
-	if (EXT4_I(inode)->i_flags & EXT4_JOURNAL_DATA_FL)
+	if (ext4_test_inode_flag(inode, EXT4_INODE_JOURNAL_DATA))
 		return 0;
 	if (test_opt(inode->i_sb, DATA_FLAGS) == EXT4_MOUNT_ORDERED_DATA)
 		return 1;
···
 		return 0;
 	if (EXT4_JOURNAL(inode) == NULL)
 		return 1;
-	if (EXT4_I(inode)->i_flags & EXT4_JOURNAL_DATA_FL)
+	if (ext4_test_inode_flag(inode, EXT4_INODE_JOURNAL_DATA))
 		return 0;
 	if (test_opt(inode->i_sb, DATA_FLAGS) == EXT4_MOUNT_WRITEBACK_DATA)
 		return 1;
···
 		return 0;
 	if (!S_ISREG(inode->i_mode))
 		return 0;
-	if (!(EXT4_I(inode)->i_flags & EXT4_EXTENTS_FL))
+	if (!(ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS)))
 		return 0;
 	if (ext4_should_journal_data(inode))
 		return 0;

fs/ext4/extents.c

···
 	if (err <= 0)
 		return err;
 	err = ext4_truncate_restart_trans(handle, inode, needed);
-	/*
-	 * We have dropped i_data_sem so someone might have cached again
-	 * an extent we are going to truncate.
-	 */
-	ext4_ext_invalidate_cache(inode);
+	if (err == 0)
+		err = -EAGAIN;
 
 	return err;
 }
···
 	if (flex_size >= EXT4_FLEX_SIZE_DIR_ALLOC_SCHEME) {
 		/*
 		 * If there are at least EXT4_FLEX_SIZE_DIR_ALLOC_SCHEME
-		 * block groups per flexgroup, reserve the first block 
-		 * group for directories and special files.  Regular 
+		 * block groups per flexgroup, reserve the first block
+		 * group for directories and special files.  Regular
 		 * files will start at the second block group.  This
-		 * tends to speed up directory access and improves 
+		 * tends to speed up directory access and improves
 		 * fsck times.
 		 */
 		block_group &= ~(flex_size-1);
···
 	return 0;
 
 corrupted:
-	__ext4_error(inode->i_sb, function,
-			"bad header/extent in inode #%lu: %s - magic %x, "
+	ext4_error_inode(function, inode,
+			"bad header/extent: %s - magic %x, "
 			"entries %u, max %u(%u), depth %u(%u)",
-			inode->i_ino, error_msg, le16_to_cpu(eh->eh_magic),
+			error_msg, le16_to_cpu(eh->eh_magic),
 			le16_to_cpu(eh->eh_entries), le16_to_cpu(eh->eh_max),
 			max, le16_to_cpu(eh->eh_depth), depth);
 
···
 		merge_done = 1;
 		WARN_ON(eh->eh_entries == 0);
 		if (!eh->eh_entries)
-			ext4_error(inode->i_sb,
-				   "inode#%lu, eh->eh_entries = 0!",
-				   inode->i_ino);
+			EXT4_ERROR_INODE(inode, "eh->eh_entries = 0!");
 	}
 
 	return merge_done;
···
 	struct ext4_ext_cache *cex;
 	int ret = EXT4_EXT_CACHE_NO;
 
-	/* 
+	/*
 	 * We borrow i_block_reservation_lock to protect i_cached_extent
 	 */
 	spin_lock(&EXT4_I(inode)->i_block_reservation_lock);
···
 	int depth = ext_depth(inode);
 	struct ext4_ext_path *path;
 	handle_t *handle;
-	int i = 0, err = 0;
+	int i, err;
 
 	ext_debug("truncate since %u\n", start);
 
···
 	if (IS_ERR(handle))
 		return PTR_ERR(handle);
 
+again:
 	ext4_ext_invalidate_cache(inode);
 
 	/*
 	 * We start scanning from right side, freeing all the blocks
 	 * after i_size and walking into the tree depth-wise.
 	 */
+	depth = ext_depth(inode);
 	path = kzalloc(sizeof(struct ext4_ext_path) * (depth + 1), GFP_NOFS);
 	if (path == NULL) {
 		ext4_journal_stop(handle);
 		return -ENOMEM;
 	}
+	path[0].p_depth = depth;
 	path[0].p_hdr = ext_inode_hdr(inode);
 	if (ext4_ext_check(inode, path[0].p_hdr, depth)) {
 		err = -EIO;
 		goto out;
 	}
-	path[0].p_depth = depth;
+	i = err = 0;
 
 	while (i >= 0 && err == 0) {
 		if (i == depth) {
···
 out:
 	ext4_ext_drop_refs(path);
 	kfree(path);
+	if (err == -EAGAIN)
+		goto again;
 	ext4_journal_stop(handle);
 
 	return err;
···
 /* FIXME!! we need to try to merge to left or right after zero-out  */
 static int ext4_ext_zeroout(struct inode *inode, struct ext4_extent *ex)
 {
-	int ret = -EIO;
+	int ret;
 	struct bio *bio;
 	int blkbits, blocksize;
 	sector_t ee_pblock;
···
 			len = ee_len;
 
 		bio = bio_alloc(GFP_NOIO, len);
+		if (!bio)
+			return -ENOMEM;
+
 		bio->bi_sector = ee_pblock;
 		bio->bi_bdev   = inode->i_sb->s_bdev;
 
···
 		submit_bio(WRITE, bio);
 		wait_for_completion(&event);
 
-		if (test_bit(BIO_UPTODATE, &bio->bi_flags))
-			ret = 0;
-		else {
-			ret = -EIO;
-			break;
+		if (!test_bit(BIO_UPTODATE, &bio->bi_flags)) {
+			bio_put(bio);
+			return -EIO;
 		}
 		bio_put(bio);
 		ee_len    -= done;
 		ee_pblock += done  << (blkbits - 9);
 	}
-	return ret;
+	return 0;
 }
 
 #define EXT4_EXT_ZERO_LEN 7
 /*
- * This function is called by ext4_ext_get_blocks() if someone tries to write
+ * This function is called by ext4_ext_map_blocks() if someone tries to write
  * to an uninitialized extent. It may result in splitting the uninitialized
  * extent into multiple extents (upto three - one initialized and two
  * uninitialized).
···
  *   c> Splits in three extents: Somone is writing in middle of the extent
  */
 static int ext4_ext_convert_to_initialized(handle_t *handle,
-						struct inode *inode,
-						struct ext4_ext_path *path,
-						ext4_lblk_t iblock,
-						unsigned int max_blocks)
+					   struct inode *inode,
+					   struct ext4_map_blocks *map,
+					   struct ext4_ext_path *path)
 {
 	struct ext4_extent *ex, newex, orig_ex;
 	struct ext4_extent *ex1 = NULL;
 	struct ext4_extent *ex2 = NULL;
 	struct ext4_extent *ex3 = NULL;
 	struct ext4_extent_header *eh;
-	ext4_lblk_t ee_block;
+	ext4_lblk_t ee_block, eof_block;
 	unsigned int allocated, ee_len, depth;
 	ext4_fsblk_t newblock;
 	int err = 0;
 	int ret = 0;
+	int may_zeroout;
+
+	ext_debug("ext4_ext_convert_to_initialized: inode %lu, logical"
+		"block %llu, max_blocks %u\n", inode->i_ino,
+		(unsigned long long)map->m_lblk, map->m_len);
+
+	eof_block = (inode->i_size + inode->i_sb->s_blocksize - 1) >>
+		inode->i_sb->s_blocksize_bits;
+	if (eof_block < map->m_lblk + map->m_len)
+		eof_block = map->m_lblk + map->m_len;
 
 	depth = ext_depth(inode);
 	eh = path[depth].p_hdr;
 	ex = path[depth].p_ext;
 	ee_block = le32_to_cpu(ex->ee_block);
 	ee_len = ext4_ext_get_actual_len(ex);
-	allocated = ee_len - (iblock - ee_block);
-	newblock = iblock - ee_block + ext_pblock(ex);
+	allocated = ee_len - (map->m_lblk - ee_block);
+	newblock = map->m_lblk - ee_block + ext_pblock(ex);
+
 	ex2 = ex;
 	orig_ex.ee_block = ex->ee_block;
 	orig_ex.ee_len   = cpu_to_le16(ee_len);
 	ext4_ext_store_pblock(&orig_ex, ext_pblock(ex));
 
+	/*
+	 * It is safe to convert extent to initialized via explicit
+	 * zeroout only if extent is fully insde i_size or new_size.
+	 */
+	may_zeroout = ee_block + ee_len <= eof_block;
+
 	err = ext4_ext_get_access(handle, inode, path + depth);
 	if (err)
 		goto out;
 	/* If extent has less than 2*EXT4_EXT_ZERO_LEN zerout directly */
-	if (ee_len <= 2*EXT4_EXT_ZERO_LEN) {
+	if (ee_len <= 2*EXT4_EXT_ZERO_LEN && may_zeroout) {
 		err =  ext4_ext_zeroout(inode, &orig_ex);
 		if (err)
 			goto fix_extent_len;
···
 		return allocated;
 	}
 
-	/* ex1: ee_block to iblock - 1 : uninitialized */
-	if (iblock > ee_block) {
+	/* ex1: ee_block to map->m_lblk - 1 : uninitialized */
+	if (map->m_lblk > ee_block) {
 		ex1 = ex;
-		ex1->ee_len = cpu_to_le16(iblock - ee_block);
+		ex1->ee_len = cpu_to_le16(map->m_lblk - ee_block);
 		ext4_ext_mark_uninitialized(ex1);
 		ex2 = &newex;
 	}
···
 	 * we insert ex3, if ex1 is NULL. This is to avoid temporary
 	 * overlap of blocks.
 	 */
-	if (!ex1 && allocated > max_blocks)
-		ex2->ee_len = cpu_to_le16(max_blocks);
+	if (!ex1 && allocated > map->m_len)
+		ex2->ee_len = cpu_to_le16(map->m_len);
 	/* ex3: to ee_block + ee_len : uninitialised */
-	if (allocated > max_blocks) {
+	if (allocated > map->m_len) {
 		unsigned int newdepth;
 		/* If extent has less than EXT4_EXT_ZERO_LEN zerout directly */
-		if (allocated <= EXT4_EXT_ZERO_LEN) {
+		if (allocated <= EXT4_EXT_ZERO_LEN && may_zeroout) {
 			/*
-			 * iblock == ee_block is handled by the zerouout
+			 * map->m_lblk == ee_block is handled by the zerouout
 			 * at the beginning.
 			 * Mark first half uninitialized.
 			 * Mark second half initialized and zero out the
···
 			ext4_ext_dirty(handle, inode, path + depth);
 
 			ex3 = &newex;
-			ex3->ee_block = cpu_to_le32(iblock);
+			ex3->ee_block = cpu_to_le32(map->m_lblk);
 			ext4_ext_store_pblock(ex3, newblock);
 			ex3->ee_len = cpu_to_le16(allocated);
 			err = ext4_ext_insert_extent(handle, inode, path,
···
 				ex->ee_len   = orig_ex.ee_len;
 				ext4_ext_store_pblock(ex, ext_pblock(&orig_ex));
 				ext4_ext_dirty(handle, inode, path + depth);
-				/* blocks available from iblock */
+				/* blocks available from map->m_lblk */
 				return allocated;
 
 			} else if (err)
···
 				 */
 				depth = ext_depth(inode);
 				ext4_ext_drop_refs(path);
-				path = ext4_ext_find_extent(inode,
-								iblock, path);
+				path = ext4_ext_find_extent(inode, map->m_lblk,
+							    path);
 				if (IS_ERR(path)) {
 					err = PTR_ERR(path);
 					return err;
···
 			return allocated;
 		}
 		ex3 = &newex;
-		ex3->ee_block = cpu_to_le32(iblock + max_blocks);
-		ext4_ext_store_pblock(ex3, newblock + max_blocks);
-		ex3->ee_len = cpu_to_le16(allocated - max_blocks);
+		ex3->ee_block = cpu_to_le32(map->m_lblk + map->m_len);
+		ext4_ext_store_pblock(ex3, newblock + map->m_len);
+		ex3->ee_len = cpu_to_le16(allocated - map->m_len);
 		ext4_ext_mark_uninitialized(ex3);
 		err = ext4_ext_insert_extent(handle, inode, path, ex3, 0);
-		if (err == -ENOSPC) {
+		if (err == -ENOSPC && may_zeroout) {
 			err =  ext4_ext_zeroout(inode, &orig_ex);
 			if (err)
 				goto fix_extent_len;
···
 			ext4_ext_store_pblock(ex, ext_pblock(&orig_ex));
 			ext4_ext_dirty(handle, inode, path + depth);
 			/* zeroed the full extent */
-			/* blocks available from iblock */
+			/* blocks available from map->m_lblk */
 			return allocated;
 
 		} else if (err)
···
 		 * update the extent length after successful insert of the
 		 * split extent
 		 */
-		orig_ex.ee_len = cpu_to_le16(ee_len -
-						ext4_ext_get_actual_len(ex3));
+		ee_len -= ext4_ext_get_actual_len(ex3);
+		orig_ex.ee_len = cpu_to_le16(ee_len);
+		may_zeroout = ee_block + ee_len <= eof_block;
+
 		depth = newdepth;
 		ext4_ext_drop_refs(path);
-		path = ext4_ext_find_extent(inode, iblock, path);
+		path = ext4_ext_find_extent(inode, map->m_lblk, path);
 		if (IS_ERR(path)) {
 			err = PTR_ERR(path);
 			goto out;
···
 		if (err)
 			goto out;
 
-		allocated = max_blocks;
+		allocated = map->m_len;
 
 		/* If extent has less than EXT4_EXT_ZERO_LEN and we are trying
 		 * to insert a extent in the middle zerout directly
 		 * otherwise give the extent a chance to merge to left
 		 */
 		if (le16_to_cpu(orig_ex.ee_len) <= EXT4_EXT_ZERO_LEN &&
-							iblock != ee_block) {
+			map->m_lblk != ee_block && may_zeroout) {
 			err =  ext4_ext_zeroout(inode, &orig_ex);
 			if (err)
 				goto fix_extent_len;
···
 			ext4_ext_store_pblock(ex, ext_pblock(&orig_ex));
 			ext4_ext_dirty(handle, inode, path + depth);
 			/* zero out the first half */
-			/* blocks available from iblock */
+			/* blocks available from map->m_lblk */
 			return allocated;
 		}
 	}
···
 	 */
 	if (ex1 && ex1 != ex) {
 		ex1 = ex;
-		ex1->ee_len = cpu_to_le16(iblock - ee_block);
+		ex1->ee_len = cpu_to_le16(map->m_lblk - ee_block);
 		ext4_ext_mark_uninitialized(ex1);
 		ex2 = &newex;
 	}
-	/* ex2: iblock to iblock + maxblocks-1 : initialised */
-	ex2->ee_block = cpu_to_le32(iblock);
+	/* ex2: map->m_lblk to map->m_lblk + maxblocks-1 : initialised */
+	ex2->ee_block = cpu_to_le32(map->m_lblk);
 	ext4_ext_store_pblock(ex2, newblock);
 	ex2->ee_len = cpu_to_le16(allocated);
 	if (ex2 != ex)
···
 	goto out;
 insert:
 	err = ext4_ext_insert_extent(handle, inode, path, &newex, 0);
-	if (err == -ENOSPC) {
+	if (err == -ENOSPC && may_zeroout) {
 		err =  ext4_ext_zeroout(inode, &orig_ex);
 		if (err)
 			goto fix_extent_len;
···
 }
 
 /*
- * This function is called by ext4_ext_get_blocks() from
+ * This function is called by ext4_ext_map_blocks() from
  * ext4_get_blocks_dio_write() when DIO to write
  * to an uninitialized extent.
  *
···
  */
 static int ext4_split_unwritten_extents(handle_t *handle,
 					struct inode *inode,
+					struct ext4_map_blocks *map,
 					struct ext4_ext_path *path,
-					ext4_lblk_t iblock,
-					unsigned int max_blocks,
 					int flags)
 {
 	struct ext4_extent *ex, newex, orig_ex;
···
 	struct ext4_extent *ex2 = NULL;
 	struct ext4_extent *ex3 = NULL;
 	struct ext4_extent_header *eh;
-	ext4_lblk_t ee_block;
+	ext4_lblk_t ee_block, eof_block;
 	unsigned int allocated, ee_len, depth;
 	ext4_fsblk_t newblock;
 	int err = 0;
+	int may_zeroout;
 
-	ext_debug("ext4_split_unwritten_extents: inode %lu,"
-		  "iblock %llu, max_blocks %u\n", inode->i_ino,
-		  (unsigned long long)iblock, max_blocks);
+	ext_debug("ext4_split_unwritten_extents: inode %lu, logical"
+		"block %llu, max_blocks %u\n", inode->i_ino,
+		(unsigned long long)map->m_lblk, map->m_len);
+
+	eof_block = (inode->i_size + inode->i_sb->s_blocksize - 1) >>
+		inode->i_sb->s_blocksize_bits;
+	if (eof_block < map->m_lblk + map->m_len)
+		eof_block = map->m_lblk + map->m_len;
+
 	depth = ext_depth(inode);
 	eh = path[depth].p_hdr;
 	ex = path[depth].p_ext;
 	ee_block = le32_to_cpu(ex->ee_block);
 	ee_len = ext4_ext_get_actual_len(ex);
-	allocated = ee_len - (iblock - ee_block);
-	newblock = iblock - ee_block + ext_pblock(ex);
+	allocated = ee_len - (map->m_lblk - ee_block);
+	newblock = map->m_lblk - ee_block + ext_pblock(ex);
+
 	ex2 = ex;
 	orig_ex.ee_block = ex->ee_block;
 	orig_ex.ee_len   = cpu_to_le16(ee_len);
 	ext4_ext_store_pblock(&orig_ex, ext_pblock(ex));
 
 	/*
+	 * It is safe to convert extent to initialized via explicit
+	 * zeroout only if extent is fully insde i_size or new_size.
+	 */
+	may_zeroout = ee_block + ee_len <= eof_block;
+
+	/*
  	 * If the uninitialized extent begins at the same logical
  	 * block where the write begins, and the write completely
  	 * covers the extent, then we don't need to split it.
  	 */
-	if ((iblock == ee_block) && (allocated <= max_blocks))
+	if ((map->m_lblk == ee_block) && (allocated <= map->m_len))
 		return allocated;
 
 	err = ext4_ext_get_access(handle, inode, path + depth);
 	if (err)
 		goto out;
-	/* ex1: ee_block to iblock - 1 : uninitialized */
-	if (iblock > ee_block) {
+	/* ex1: ee_block to map->m_lblk - 1 : uninitialized */
+	if (map->m_lblk > ee_block) {
 		ex1 = ex;
-		ex1->ee_len = cpu_to_le16(iblock - ee_block);
+		ex1->ee_len = cpu_to_le16(map->m_lblk - ee_block);
 		ext4_ext_mark_uninitialized(ex1);
 		ex2 = &newex;
 	}
···
 	 * we insert ex3, if ex1 is NULL. This is to avoid temporary
 	 * overlap of blocks.
 	 */
-	if (!ex1 && allocated > max_blocks)
-		ex2->ee_len = cpu_to_le16(max_blocks);
+	if (!ex1 && allocated > map->m_len)
+		ex2->ee_len = cpu_to_le16(map->m_len);
 	/* ex3: to ee_block + ee_len : uninitialised */
-	if (allocated > max_blocks) {
+	if (allocated > map->m_len) {
 		unsigned int newdepth;
 		ex3 = &newex;
-		ex3->ee_block = cpu_to_le32(iblock + max_blocks);
-		ext4_ext_store_pblock(ex3, newblock + max_blocks);
-		ex3->ee_len = cpu_to_le16(allocated - max_blocks);
+		ex3->ee_block = cpu_to_le32(map->m_lblk + map->m_len);
+		ext4_ext_store_pblock(ex3, newblock + map->m_len);
+		ex3->ee_len = cpu_to_le16(allocated - map->m_len);
 		ext4_ext_mark_uninitialized(ex3);
 		err = ext4_ext_insert_extent(handle, inode, path, ex3, flags);
-		if (err == -ENOSPC) {
+		if (err == -ENOSPC && may_zeroout) {
 			err =  ext4_ext_zeroout(inode, &orig_ex);
 			if (err)
 				goto fix_extent_len;
···
 			ext4_ext_store_pblock(ex, ext_pblock(&orig_ex));
 			ext4_ext_dirty(handle, inode, path + depth);
 			/* zeroed the full extent */
-			/* blocks available from iblock */
+			/* blocks available from map->m_lblk */
 			return allocated;
 
 		} else if (err)
···
 		 * update the extent length after successful insert of the
 		 * split extent
 		 */
-		orig_ex.ee_len = cpu_to_le16(ee_len -
-						ext4_ext_get_actual_len(ex3));
+		ee_len -= ext4_ext_get_actual_len(ex3);
+		orig_ex.ee_len = cpu_to_le16(ee_len);
+		may_zeroout = ee_block + ee_len <= eof_block;
+
 		depth = newdepth;
 		ext4_ext_drop_refs(path);
-		path = ext4_ext_find_extent(inode, iblock, path);
+		path = ext4_ext_find_extent(inode, map->m_lblk, path);
 		if (IS_ERR(path)) {
 			err = PTR_ERR(path);
 			goto out;
···
 		if (err)
 			goto out;
 
-		allocated = max_blocks;
+		allocated = map->m_len;
 	}
 	/*
 	 * If there was a change of depth as part of the
···
 	 */
 	if (ex1 && ex1 != ex) {
 		ex1 = ex;
-		ex1->ee_len = cpu_to_le16(iblock - ee_block);
+		ex1->ee_len = cpu_to_le16(map->m_lblk - ee_block);
 		ext4_ext_mark_uninitialized(ex1);
 		ex2 = &newex;
 	}
 	/*
-	 * ex2: iblock to iblock + maxblocks-1 : to be direct IO written,
-	 * uninitialised still.
+	 * ex2: map->m_lblk to map->m_lblk + map->m_len-1 : to be written
+	 * using direct I/O, uninitialised still.
 	 */
-	ex2->ee_block = cpu_to_le32(iblock);
+	ex2->ee_block = cpu_to_le32(map->m_lblk);
 	ext4_ext_store_pblock(ex2, newblock);
 	ex2->ee_len = cpu_to_le16(allocated);
 	ext4_ext_mark_uninitialized(ex2);
···
 	goto out;
 insert:
 	err = ext4_ext_insert_extent(handle, inode, path, &newex, flags);
-	if (err == -ENOSPC) {
+	if (err == -ENOSPC && may_zeroout) {
 		err =  ext4_ext_zeroout(inode, &orig_ex);
 		if (err)
 			goto fix_extent_len;
···
 
 static int
 ext4_ext_handle_uninitialized_extents(handle_t *handle, struct inode *inode,
-			ext4_lblk_t iblock, unsigned int max_blocks,
+			struct ext4_map_blocks *map,
 			struct ext4_ext_path *path, int flags,
-			unsigned int allocated, struct buffer_head *bh_result,
-			ext4_fsblk_t newblock)
+			unsigned int allocated, ext4_fsblk_t newblock)
 {
 	int ret = 0;
 	int err = 0;
···
 
 	ext_debug("ext4_ext_handle_uninitialized_extents: inode %lu, logical"
 		  "block %llu, max_blocks %u, flags %d, allocated %u",
-		  inode->i_ino, (unsigned long long)iblock, max_blocks,
+		  inode->i_ino, (unsigned long long)map->m_lblk, map->m_len,
 		  flags, allocated);
 	ext4_ext_show_leaf(inode, path);
 
 	/* get_block() before submit the IO, split the extent */
 	if ((flags & EXT4_GET_BLOCKS_PRE_IO)) {
-		ret = ext4_split_unwritten_extents(handle,
-						inode, path, iblock,
-						max_blocks, flags);
+		ret = ext4_split_unwritten_extents(handle, inode, map,
+						   path, flags);
 		/*
 		 * Flag the inode(non aio case) or end_io struct (aio case)
 		 * that this IO needs to convertion to written when IO is
···
 		else
 			ext4_set_inode_state(inode, EXT4_STATE_DIO_UNWRITTEN);
 		if (ext4_should_dioread_nolock(inode))
-			set_buffer_uninit(bh_result);
+			map->m_flags |= EXT4_MAP_UNINIT;
 		goto out;
 	}
 	/* IO end_io complete, convert the filled extent to written */
···
 		 * the buffer head will be unmapped so that
 		 * a read from the block returns 0s.
 		 */
-		set_buffer_unwritten(bh_result);
+		map->m_flags |= EXT4_MAP_UNWRITTEN;
 		goto out1;
 	}
 
 	/* buffered write, writepage time, convert*/
-	ret = ext4_ext_convert_to_initialized(handle, inode,
-						path, iblock,
-						max_blocks);
+	ret = ext4_ext_convert_to_initialized(handle, inode, map, path);
 	if (ret >= 0)
 		ext4_update_inode_fsync_trans(handle, inode, 1);
 out:
···
 		goto out2;
 	} else
 		allocated = ret;
-	set_buffer_new(bh_result);
+	map->m_flags |= EXT4_MAP_NEW;
 	/*
 	 * if we allocated more blocks than requested
 	 * we need to make sure we unmap the extra block
···
 	 * unmapped later when we find the buffer_head marked
 	 * new.
 	 */
-	if (allocated > max_blocks) {
+	if (allocated > map->m_len) {
 		unmap_underlying_metadata_blocks(inode->i_sb->s_bdev,
-					newblock + max_blocks,
-					allocated - max_blocks);
-		allocated = max_blocks;
+					newblock + map->m_len,
+					allocated - map->m_len);
+		allocated = map->m_len;
 	}
 
 	/*
···
 		ext4_da_update_reserve_space(inode, allocated, 0);
 
 map_out:
-	set_buffer_mapped(bh_result);
+	map->m_flags |= EXT4_MAP_MAPPED;
 out1:
-	if (allocated > max_blocks)
-		allocated = max_blocks;
+	if (allocated > map->m_len)
+		allocated = map->m_len;
 	ext4_ext_show_leaf(inode, path);
-	bh_result->b_bdev = inode->i_sb->s_bdev;
-	bh_result->b_blocknr = newblock;
+	map->m_pblk = newblock;
+	map->m_len = allocated;
 out2:
 	if (path) {
 		ext4_ext_drop_refs(path);
···
  *
  * return < 0, error case.
  */
-int ext4_ext_get_blocks(handle_t *handle, struct inode *inode,
-			ext4_lblk_t iblock,
-			unsigned int max_blocks, struct buffer_head *bh_result,
-			int flags)
+int ext4_ext_map_blocks(handle_t *handle, struct inode *inode,
+			struct ext4_map_blocks *map, int flags)
 {
 	struct ext4_ext_path *path = NULL;
 	struct ext4_extent_header *eh;
 	struct ext4_extent newex, *ex, *last_ex;
 	ext4_fsblk_t newblock;
-	int err = 0, depth, ret, cache_type;
+	int i, err = 0, depth, ret, cache_type;
 	unsigned int allocated = 0;
 	struct ext4_allocation_request ar;
 	ext4_io_end_t *io = EXT4_I(inode)->cur_aio_dio;
 
-	__clear_bit(BH_New, &bh_result->b_state);
 	ext_debug("blocks %u/%u requested for inode %lu\n",
-			iblock, max_blocks, inode->i_ino);
+		  map->m_lblk, map->m_len, inode->i_ino);
 
 	/* check in cache */
-	cache_type = ext4_ext_in_cache(inode, iblock, &newex);
+	cache_type = ext4_ext_in_cache(inode, map->m_lblk, &newex);
 	if (cache_type) {
 		if (cache_type == EXT4_EXT_CACHE_GAP) {
 			if ((flags & EXT4_GET_BLOCKS_CREATE) == 0) {
···
 			/* we should allocate requested block */
 		} else if (cache_type == EXT4_EXT_CACHE_EXTENT) {
 			/* block is already allocated */
-			newblock = iblock
+			newblock = map->m_lblk
 				   - le32_to_cpu(newex.ee_block)
 				   + ext_pblock(&newex);
 			/* number of remaining blocks in the extent */
 			allocated = ext4_ext_get_actual_len(&newex) -
-					(iblock - le32_to_cpu(newex.ee_block));
+				(map->m_lblk - le32_to_cpu(newex.ee_block));
 			goto out;
 		} else {
 			BUG();
···
 	}
 
 	/* find extent for this block */
-	path = ext4_ext_find_extent(inode, iblock, NULL);
+	path = ext4_ext_find_extent(inode, map->m_lblk, NULL);
 	if (IS_ERR(path)) {
 		err = PTR_ERR(path);
 		path = NULL;
···
 	 */
 	if (unlikely(path[depth].p_ext == NULL && depth != 0)) {
 		EXT4_ERROR_INODE(inode, "bad extent address "
-				 "iblock: %d, depth: %d pblock %lld",
-				 iblock, depth, path[depth].p_block);
+				 "lblock: %lu, depth: %d pblock %lld",
+				 (unsigned long) map->m_lblk, depth,
+				 path[depth].p_block);
 		err = -EIO;
 		goto out2;
 	}
···
 		 */
 		ee_len = ext4_ext_get_actual_len(ex);
 		/* if found extent covers block, simply return it */
-		if (in_range(iblock, ee_block, ee_len)) {
-			newblock = iblock - ee_block + ee_start;
+		if (in_range(map->m_lblk, ee_block, ee_len)) {
+			newblock = map->m_lblk - ee_block + ee_start;
 			/* number of remaining blocks in the extent */
-			allocated = ee_len - (iblock - ee_block);
-			ext_debug("%u fit into %u:%d -> %llu\n", iblock,
-					ee_block, ee_len, newblock);
+			allocated = ee_len - (map->m_lblk - ee_block);
+			ext_debug("%u fit into %u:%d -> %llu\n", map->m_lblk,
+				  ee_block, ee_len, newblock);
 
 			/* Do not put uninitialized extent in the cache */
 			if (!ext4_ext_is_uninitialized(ex)) {
···
 				goto out;
 			}
 			ret = ext4_ext_handle_uninitialized_extents(handle,
-					inode, iblock, max_blocks, path,
-					flags, allocated, bh_result, newblock);
+					inode, map, path, flags, allocated,
+					newblock);
 			return ret;
 		}
 	}
···
 		 * put just found gap into cache to speed up
 		 * subsequent requests
 		 */
-		ext4_ext_put_gap_in_cache(inode, path, iblock);
+		ext4_ext_put_gap_in_cache(inode, path, map->m_lblk);
 		goto out2;
 	}
 	/*
···
 	 */
 
 	/* find neighbour allocated blocks */
-	ar.lleft = iblock;
+	ar.lleft = map->m_lblk;
 	err = ext4_ext_search_left(inode, path, &ar.lleft, &ar.pleft);
 	if (err)
 		goto out2;
-	ar.lright = iblock;
+	ar.lright = map->m_lblk;
 	err = ext4_ext_search_right(inode, path, &ar.lright, &ar.pright);
 	if (err)
 		goto out2;
···
 	 * EXT_INIT_MAX_LEN and for an uninitialized extent this limit is
 	 * EXT_UNINIT_MAX_LEN.
 	 */
-	if (max_blocks > EXT_INIT_MAX_LEN &&
+	if (map->m_len > EXT_INIT_MAX_LEN &&
 	    !(flags & EXT4_GET_BLOCKS_UNINIT_EXT))
-		max_blocks = EXT_INIT_MAX_LEN;
-	else if (max_blocks > EXT_UNINIT_MAX_LEN &&
+		map->m_len = EXT_INIT_MAX_LEN;
+	else if (map->m_len > EXT_UNINIT_MAX_LEN &&
 		 (flags & EXT4_GET_BLOCKS_UNINIT_EXT))
-		max_blocks = EXT_UNINIT_MAX_LEN;
+		map->m_len = EXT_UNINIT_MAX_LEN;
 
-	/* Check if we can really insert (iblock)::(iblock+max_blocks) extent */
-	newex.ee_block = cpu_to_le32(iblock);
-	newex.ee_len = cpu_to_le16(max_blocks);
+	/* Check if we can really insert (m_lblk)::(m_lblk + m_len) extent */
+	newex.ee_block = cpu_to_le32(map->m_lblk);
+	newex.ee_len = cpu_to_le16(map->m_len);
 	err = ext4_ext_check_overlap(inode, &newex, path);
 	if (err)
 		allocated = ext4_ext_get_actual_len(&newex);
 	else
-		allocated = max_blocks;
+		allocated = map->m_len;
 
 	/* allocate new block */
 	ar.inode = inode;
-	ar.goal = ext4_ext_find_goal(inode, path, iblock);
-	ar.logical = iblock;
+	ar.goal = ext4_ext_find_goal(inode, path, map->m_lblk);
+	ar.logical = map->m_lblk;
 	ar.len = allocated;
 	if (S_ISREG(inode->i_mode))
 		ar.flags = EXT4_MB_HINT_DATA;
···
 						     EXT4_STATE_DIO_UNWRITTEN);
 		}
 		if (ext4_should_dioread_nolock(inode))
-			set_buffer_uninit(bh_result);
+			map->m_flags |= EXT4_MAP_UNINIT;
 	}
 
-	if (unlikely(EXT4_I(inode)->i_flags & EXT4_EOFBLOCKS_FL)) {
+	if (unlikely(ext4_test_inode_flag(inode, EXT4_INODE_EOFBLOCKS))) {
 		if (unlikely(!eh->eh_entries)) {
 			EXT4_ERROR_INODE(inode,
-					 "eh->eh_entries == 0 ee_block %d",
-					 ex->ee_block);
+					 "eh->eh_entries == 0 and "
+					 "EOFBLOCKS_FL set");
 			err = -EIO;
 			goto out2;
 		}
 		last_ex = EXT_LAST_EXTENT(eh);
-		if (iblock + ar.len > le32_to_cpu(last_ex->ee_block)
-		    + ext4_ext_get_actual_len(last_ex))
-			EXT4_I(inode)->i_flags &= ~EXT4_EOFBLOCKS_FL;
+		/*
+		 * If the current leaf block was reached by looking at
+		 * the last index block all the way down the tree, and
+		 * we are extending the inode beyond the last extent
+		 * in the current leaf block, then clear the
+		 * EOFBLOCKS_FL flag.
+		 */
+		for (i = depth-1; i >= 0; i--) {
+			if (path[i].p_idx != EXT_LAST_INDEX(path[i].p_hdr))
+				break;
+		}
+		if ((i < 0) &&
+		    (map->m_lblk + ar.len > le32_to_cpu(last_ex->ee_block) +
+		     ext4_ext_get_actual_len(last_ex)))
+			ext4_clear_inode_flag(inode, EXT4_INODE_EOFBLOCKS);
 	}
 	err = ext4_ext_insert_extent(handle, inode, path, &newex, flags);
 	if (err) {
···
 	/* previous routine could use block we allocated */
 	newblock = ext_pblock(&newex);
 	allocated = ext4_ext_get_actual_len(&newex);
-	if (allocated > max_blocks)
-		allocated = max_blocks;
-	set_buffer_new(bh_result);
+	if (allocated > map->m_len)
+		allocated = map->m_len;
+	map->m_flags |= EXT4_MAP_NEW;
 
 	/*
 	 * Update reserved blocks/metadata blocks after successful
···
 	 * when it is _not_ an uninitialized extent.
 	 */
 	if ((flags & EXT4_GET_BLOCKS_UNINIT_EXT) == 0) {
-		ext4_ext_put_in_cache(inode, iblock, allocated, newblock,
+		ext4_ext_put_in_cache(inode, map->m_lblk, allocated, newblock,
 						EXT4_EXT_CACHE_EXTENT);
 		ext4_update_inode_fsync_trans(handle, inode, 1);
 	} else
 		ext4_update_inode_fsync_trans(handle, inode, 0);
 out:
-	if (allocated > max_blocks)
-		allocated = max_blocks;
+	if (allocated > map->m_len)
+		allocated = map->m_len;
 	ext4_ext_show_leaf(inode, path);
-	set_buffer_mapped(bh_result);
-	bh_result->b_bdev = inode->i_sb->s_bdev;
-	bh_result->b_blocknr = newblock;
+	map->m_flags |= EXT4_MAP_MAPPED;
+	map->m_pblk = newblock;
+	map->m_len = allocated;
 out2:
 	if (path) {
 		ext4_ext_drop_refs(path);
···
 		 * can proceed even if the new size is the same as i_size.
 		 */
 		if (new_size > i_size_read(inode))
-			EXT4_I(inode)->i_flags |= EXT4_EOFBLOCKS_FL;
+			ext4_set_inode_flag(inode, EXT4_INODE_EOFBLOCKS);
 	}
 
 }
···
 long ext4_fallocate(struct inode *inode, int mode, loff_t offset, loff_t len)
 {
 	handle_t *handle;
-	ext4_lblk_t block;
 	loff_t new_size;
 	unsigned int max_blocks;
 	int ret = 0;
 	int ret2 = 0;
 	int retries = 0;
-	struct buffer_head map_bh;
+	struct ext4_map_blocks map;
 	unsigned int credits, blkbits = inode->i_blkbits;
 
 	/*
 	 * currently supporting (pre)allocate mode for extent-based
 	 * files _only_
 	 */
-	if (!(EXT4_I(inode)->i_flags & EXT4_EXTENTS_FL))
+	if (!(ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS)))
 		return -EOPNOTSUPP;
 
 	/* preallocation to directories is currently not supported */
 	if (S_ISDIR(inode->i_mode))
 		return -ENODEV;
 
-	block = offset >> blkbits;
+	map.m_lblk = offset >> blkbits;
 	/*
 	 * We can't just convert len to max_blocks because
 	 * If blocksize = 4096 offset = 3072 and len = 2048
 	 */
 	max_blocks = (EXT4_BLOCK_ALIGN(len + offset, blkbits) >> blkbits)
-							- block;
+		- map.m_lblk;
 	/*
 	 * credits to insert 1 extent into extent tree
 	 */
 	credits = ext4_chunk_trans_blocks(inode, max_blocks);
 	mutex_lock(&inode->i_mutex);
+	ret = inode_newsize_ok(inode, (len + offset));
+	if (ret) {
+		mutex_unlock(&inode->i_mutex);
+		return ret;
+	}
 retry:
 	while (ret >= 0 && ret < max_blocks) {
-		block = block + ret;
-		max_blocks = max_blocks - ret;
+		map.m_lblk = map.m_lblk + ret;
+		map.m_len = max_blocks = max_blocks - ret;
 		handle = ext4_journal_start(inode, credits);
 		if (IS_ERR(handle)) {
 			ret = PTR_ERR(handle);
 			break;
 		}
-		map_bh.b_state = 0;
-		ret = ext4_get_blocks(handle, inode, block,
-				      max_blocks, &map_bh,
+		ret = ext4_map_blocks(handle, inode, &map,
 				      EXT4_GET_BLOCKS_CREATE_UNINIT_EXT);
 		if (ret <= 0) {
 #ifdef EXT4FS_DEBUG
 			WARN_ON(ret <= 0);
-			printk(KERN_ERR "%s: ext4_ext_get_blocks "
+			printk(KERN_ERR "%s: ext4_ext_map_blocks "
 				    "returned error inode#%lu, block=%u, "
 				    "max_blocks=%u", __func__,
 				    inode->i_ino, block, max_blocks);
···
 			ret2 = ext4_journal_stop(handle);
 			break;
 		}
-		if ((block + ret) >= (EXT4_BLOCK_ALIGN(offset + len,
+		if ((map.m_lblk + ret) >= (EXT4_BLOCK_ALIGN(offset + len,
 						blkbits) >> blkbits))
 			new_size = offset + len;
 		else
-			new_size = (block + ret) << blkbits;
+			new_size = (map.m_lblk + ret) << blkbits;
 
 		ext4_falloc_update_inode(inode, mode, new_size,
-						buffer_new(&map_bh));
+					 (map.m_flags & EXT4_MAP_NEW));
 		ext4_mark_inode_dirty(handle, inode);
 		ret2 = ext4_journal_stop(handle);
 		if (ret2)
···
 				    ssize_t len)
 {
 	handle_t *handle;
-	ext4_lblk_t block;
 	unsigned int max_blocks;
 	int ret = 0;
 	int ret2 = 0;
-	struct buffer_head map_bh;
+	struct ext4_map_blocks map;
 	unsigned int credits, blkbits = inode->i_blkbits;
 
-	block = offset >> blkbits;
+	map.m_lblk = offset >> blkbits;
 	/*
 	 * We can't just convert len to max_blocks because
 	 * If blocksize = 4096 offset = 3072 and len = 2048
 	 */
-	max_blocks = (EXT4_BLOCK_ALIGN(len + offset, blkbits) >> blkbits)
-							- block;
+	max_blocks = ((EXT4_BLOCK_ALIGN(len + offset, blkbits) >> blkbits) -
+		      map.m_lblk);
 	/*
 	 * credits to insert 1 extent into extent tree
 	 */
 	credits = ext4_chunk_trans_blocks(inode, max_blocks);
 	while (ret >= 0 && ret < max_blocks) {
-		block = block + ret;
-		max_blocks = max_blocks - ret;
+		map.m_lblk += ret;
+		map.m_len = (max_blocks -= ret);
 		handle = ext4_journal_start(inode, credits);
 		if (IS_ERR(handle)) {
 			ret = PTR_ERR(handle);
 			break;
 		}
-		map_bh.b_state = 0;
-		ret = ext4_get_blocks(handle, inode, block,
-				      max_blocks, &map_bh,
+		ret = ext4_map_blocks(handle, inode, &map,
 				      EXT4_GET_BLOCKS_IO_CONVERT_EXT);
 		if (ret <= 0) {
 			WARN_ON(ret <= 0);
-			printk(KERN_ERR "%s: ext4_ext_get_blocks "
+			printk(KERN_ERR "%s: ext4_ext_map_blocks "
 				    "returned error inode#%lu, block=%u, "
 				    "max_blocks=%u", __func__,
-				    inode->i_ino, block, max_blocks);
+				    inode->i_ino, map.m_lblk, map.m_len);
 		}
 		ext4_mark_inode_dirty(handle, inode);
 		ret2 = ext4_journal_stop(handle);
···
 	int error = 0;
 
 	/* fallback to generic here if not in extents fmt */
-	if (!(EXT4_I(inode)->i_flags & EXT4_EXTENTS_FL))
+	if (!(ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS)))
 		return generic_block_fiemap(inode, fieinfo, start, len,
 			ext4_get_block);
 

fs/ext4/file.c

···
 	 * is smaller than s_maxbytes, which is for extent-mapped files.
 	 */
 
-	if (!(EXT4_I(inode)->i_flags & EXT4_EXTENTS_FL)) {
+	if (!(ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS))) {
 		struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb);
 		size_t length = iov_length(iov, nr_segs);
 

fs/ext4/fsync.c

···
 #include <trace/events/ext4.h>
 
 /*
+ * If we're not journaling and this is a just-created file, we have to
+ * sync our parent directory (if it was freshly created) since
+ * otherwise it will only be written by writeback, leaving a huge
+ * window during which a crash may lose the file.  This may apply for
+ * the parent directory's parent as well, and so on recursively, if
+ * they are also freshly created.
+ */
+static void ext4_sync_parent(struct inode *inode)
+{
+	struct dentry *dentry = NULL;
+
+	while (inode && ext4_test_inode_state(inode, EXT4_STATE_NEWENTRY)) {
+		ext4_clear_inode_state(inode, EXT4_STATE_NEWENTRY);
+		dentry = list_entry(inode->i_dentry.next,
+				    struct dentry, d_alias);
+		if (!dentry || !dentry->d_parent || !dentry->d_parent->d_inode)
+			break;
+		inode = dentry->d_parent->d_inode;
+		sync_mapping_buffers(inode->i_mapping);
+	}
+}
+
+/*
  * akpm: A new design for ext4_sync_file().
  *
  * This is only called from sys_fsync(), sys_fdatasync() and sys_msync().
···
 	ret = flush_completed_IO(inode);
 	if (ret < 0)
 		return ret;
-	
-	if (!journal)
-		return simple_fsync(file, dentry, datasync);
+
+	if (!journal) {
+		ret = simple_fsync(file, dentry, datasync);
+		if (!ret && !list_empty(&inode->i_dentry))
+			ext4_sync_parent(inode);
+		return ret;
+	}
 
 	/*
 	 * data=writeback,ordered:
···
 		    (journal->j_flags & JBD2_BARRIER))
 			blkdev_issue_flush(inode->i_sb->s_bdev, GFP_KERNEL,
 					NULL, BLKDEV_IFL_WAIT);
-		jbd2_log_wait_commit(journal, commit_tid);
+		ret = jbd2_log_wait_commit(journal, commit_tid);
 	} else if (journal->j_flags & JBD2_BARRIER)
 		blkdev_issue_flush(inode->i_sb->s_bdev, GFP_KERNEL, NULL,
 			BLKDEV_IFL_WAIT);

fs/ext4/ialloc.c

···
 	if (fatal)
 		goto error_return;
 
-	/* Ok, now we can actually update the inode bitmaps.. */
-	cleared = ext4_clear_bit_atomic(ext4_group_lock_ptr(sb, block_group),
-					bit, bitmap_bh->b_data);
-	if (!cleared)
-		ext4_error(sb, "bit already cleared for inode %lu", ino);
-	else {
-		gdp = ext4_get_group_desc(sb, block_group, &bh2);
-
+	fatal = -ESRCH;
+	gdp = ext4_get_group_desc(sb, block_group, &bh2);
+	if (gdp) {
 		BUFFER_TRACE(bh2, "get_write_access");
 		fatal = ext4_journal_get_write_access(handle, bh2);
-		if (fatal) goto error_return;
-
-		if (gdp) {
-			ext4_lock_group(sb, block_group);
-			count = ext4_free_inodes_count(sb, gdp) + 1;
-			ext4_free_inodes_set(sb, gdp, count);
-			if (is_directory) {
-				count = ext4_used_dirs_count(sb, gdp) - 1;
-				ext4_used_dirs_set(sb, gdp, count);
-				if (sbi->s_log_groups_per_flex) {
-					ext4_group_t f;
-
-					f = ext4_flex_group(sbi, block_group);
-					atomic_dec(&sbi->s_flex_groups[f].used_dirs);
-				}
-
-			}
-			gdp->bg_checksum = ext4_group_desc_csum(sbi,
-							block_group, gdp);
-			ext4_unlock_group(sb, block_group);
-			percpu_counter_inc(&sbi->s_freeinodes_counter);
-			if (is_directory)
-				percpu_counter_dec(&sbi->s_dirs_counter);
-
-			if (sbi->s_log_groups_per_flex) {
-				ext4_group_t f;
-
-				f = ext4_flex_group(sbi, block_group);
-				atomic_inc(&sbi->s_flex_groups[f].free_inodes);
-			}
-		}
-		BUFFER_TRACE(bh2, "call ext4_handle_dirty_metadata");
-		err = ext4_handle_dirty_metadata(handle, NULL, bh2);
-		if (!fatal) fatal = err;
 	}
-	BUFFER_TRACE(bitmap_bh, "call ext4_handle_dirty_metadata");
-	err = ext4_handle_dirty_metadata(handle, NULL, bitmap_bh);
-	if (!fatal)
-		fatal = err;
-	sb->s_dirt = 1;
+	ext4_lock_group(sb, block_group);
+	cleared = ext4_clear_bit(bit, bitmap_bh->b_data);
+	if (fatal || !cleared) {
+		ext4_unlock_group(sb, block_group);
+		goto out;
+	}
+
+	count = ext4_free_inodes_count(sb, gdp) + 1;
+	ext4_free_inodes_set(sb, gdp, count);
+	if (is_directory) {
+		count = ext4_used_dirs_count(sb, gdp) - 1;
+		ext4_used_dirs_set(sb, gdp, count);
+		percpu_counter_dec(&sbi->s_dirs_counter);
+	}
+	gdp->bg_checksum = ext4_group_desc_csum(sbi, block_group, gdp);
+	ext4_unlock_group(sb, block_group);
+
+	percpu_counter_inc(&sbi->s_freeinodes_counter);
+	if (sbi->s_log_groups_per_flex) {
+		ext4_group_t f = ext4_flex_group(sbi, block_group);
+
+		atomic_inc(&sbi->s_flex_groups[f].free_inodes);
+		if (is_directory)
+			atomic_dec(&sbi->s_flex_groups[f].used_dirs);
+	}
+	BUFFER_TRACE(bh2, "call ext4_handle_dirty_metadata");
+	fatal = ext4_handle_dirty_metadata(handle, NULL, bh2);
+out:
+	if (cleared) {
+		BUFFER_TRACE(bitmap_bh, "call ext4_handle_dirty_metadata");
+		err = ext4_handle_dirty_metadata(handle, NULL, bitmap_bh);
+		if (!fatal)
+			fatal = err;
+		sb->s_dirt = 1;
+	} else
+		ext4_error(sb, "bit already cleared for inode %lu", ino);
+
 error_return:
 	brelse(bitmap_bh);
 	ext4_std_error(sb, fatal);
···
 
 	if (S_ISDIR(mode) &&
 	    ((parent == sb->s_root->d_inode) ||
-	     (EXT4_I(parent)->i_flags & EXT4_TOPDIR_FL))) {
+	     (ext4_test_inode_flag(parent, EXT4_INODE_TOPDIR)))) {
 		int best_ndir = inodes_per_group;
 		int ret = -1;
 
···
 	if (EXT4_HAS_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_EXTENTS)) {
 		/* 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_set_inode_flag(inode, EXT4_INODE_EXTENTS);
 			ext4_ext_tree_init(handle, inode);
 		}
 	}

fs/ext4/inode.c

···
 	int ret;
 
 	/*
-	 * Drop i_data_sem to avoid deadlock with ext4_get_blocks At this
+	 * Drop i_data_sem to avoid deadlock with ext4_map_blocks.  At this
 	 * moment, get_block can be called only for blocks inside i_size since
 	 * page cache has been already dropped and writes are blocked by
 	 * i_mutex. So we can safely drop the i_data_sem here.
···
 		if (blk &&
 		    unlikely(!ext4_data_block_valid(EXT4_SB(inode->i_sb),
 						    blk, 1))) {
-			__ext4_error(inode->i_sb, function,
-				   "invalid block reference %u "
-				   "in inode #%lu", blk, inode->i_ino);
+			ext4_error_inode(function, inode,
+					 "invalid block reference %u", blk);
 			return -EIO;
 		}
 	}
···
 	/* Allocation failed, free what we already allocated */
 	ext4_free_blocks(handle, inode, 0, new_blocks[0], 1, 0);
 	for (i = 1; i <= n ; i++) {
-		/* 
+		/*
 		 * branch[i].bh is newly allocated, so there is no
 		 * need to revoke the block, which is why we don't
 		 * need to set EXT4_FREE_BLOCKS_METADATA.
···
 
 err_out:
 	for (i = 1; i <= num; i++) {
-		/* 
+		/*
 		 * branch[i].bh is newly allocated, so there is no
 		 * need to revoke the block, which is why we don't
 		 * need to set EXT4_FREE_BLOCKS_METADATA.
···
 }
 
 /*
- * The ext4_ind_get_blocks() function handles non-extents inodes
+ * The ext4_ind_map_blocks() function handles non-extents inodes
  * (i.e., using the traditional indirect/double-indirect i_blocks
- * scheme) for ext4_get_blocks().
+ * scheme) for ext4_map_blocks().
  *
  * Allocation strategy is simple: if we have to allocate something, we will
  * have to go the whole way to leaf. So let's do it before attaching anything
···
  * down_read(&EXT4_I(inode)->i_data_sem) if not allocating file system
  * blocks.
  */
-static int ext4_ind_get_blocks(handle_t *handle, struct inode *inode,
-			       ext4_lblk_t iblock, unsigned int maxblocks,
-			       struct buffer_head *bh_result,
+static int ext4_ind_map_blocks(handle_t *handle, struct inode *inode,
+			       struct ext4_map_blocks *map,
 			       int flags)
 {
 	int err = -EIO;
···
 	int count = 0;
 	ext4_fsblk_t first_block = 0;
 
-	J_ASSERT(!(EXT4_I(inode)->i_flags & EXT4_EXTENTS_FL));
+	J_ASSERT(!(ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS)));
 	J_ASSERT(handle != NULL || (flags & EXT4_GET_BLOCKS_CREATE) == 0);
-	depth = ext4_block_to_path(inode, iblock, offsets,
+	depth = ext4_block_to_path(inode, map->m_lblk, offsets,
 				   &blocks_to_boundary);
 
 	if (depth == 0)
···
 	/* Simplest case - block found, no allocation needed */
 	if (!partial) {
 		first_block = le32_to_cpu(chain[depth - 1].key);
-		clear_buffer_new(bh_result);
 		count++;
 		/*map more blocks*/
-		while (count < maxblocks && count <= blocks_to_boundary) {
+		while (count < map->m_len && count <= blocks_to_boundary) {
 			ext4_fsblk_t blk;
 
 			blk = le32_to_cpu(*(chain[depth-1].p + count));
···
 	/*
 	 * Okay, we need to do block allocation.
 	*/
-	goal = ext4_find_goal(inode, iblock, partial);
+	goal = ext4_find_goal(inode, map->m_lblk, partial);
 
 	/* the number of blocks need to allocate for [d,t]indirect blocks */
 	indirect_blks = (chain + depth) - partial - 1;
···
 	 * direct blocks to allocate for this branch.
 	 */
 	count = ext4_blks_to_allocate(partial, indirect_blks,
-					maxblocks, blocks_to_boundary);
+				      map->m_len, blocks_to_boundary);
 	/*
 	 * Block out ext4_truncate while we alter the tree
 	 */
-	err = ext4_alloc_branch(handle, inode, iblock, indirect_blks,
+	err = ext4_alloc_branch(handle, inode, map->m_lblk, indirect_blks,
 				&count, goal,
 				offsets + (partial - chain), partial);
 
···
 	 * may need to return -EAGAIN upwards in the worst case.  --sct
 	 */
 	if (!err)
-		err = ext4_splice_branch(handle, inode, iblock,
+		err = ext4_splice_branch(handle, inode, map->m_lblk,
 					 partial, indirect_blks, count);
 	if (err)
 		goto cleanup;
 
-	set_buffer_new(bh_result);
+	map->m_flags |= EXT4_MAP_NEW;
 
 	ext4_update_inode_fsync_trans(handle, inode, 1);
 got_it:
-	map_bh(bh_result, inode->i_sb, le32_to_cpu(chain[depth-1].key));
+	map->m_flags |= EXT4_MAP_MAPPED;
+	map->m_pblk = le32_to_cpu(chain[depth-1].key);
+	map->m_len = count;
 	if (count > blocks_to_boundary)
-		set_buffer_boundary(bh_result);
+		map->m_flags |= EXT4_MAP_BOUNDARY;
 	err = count;
 	/* Clean up and exit */
 	partial = chain + depth - 1;	/* the whole chain */
···
 		brelse(partial->bh);
 		partial--;
 	}
-	BUFFER_TRACE(bh_result, "returned");
 out:
 	return err;
 }
···
  */
 static int ext4_calc_metadata_amount(struct inode *inode, sector_t lblock)
 {
-	if (EXT4_I(inode)->i_flags & EXT4_EXTENTS_FL)
+	if (ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS))
 		return ext4_ext_calc_metadata_amount(inode, lblock);
 
 	return ext4_indirect_calc_metadata_amount(inode, lblock);
···
 {
 	struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb);
 	struct ext4_inode_info *ei = EXT4_I(inode);
-	int mdb_free = 0, allocated_meta_blocks = 0;
 
 	spin_lock(&ei->i_block_reservation_lock);
 	trace_ext4_da_update_reserve_space(inode, used);
···
 
 	/* Update per-inode reservations */
 	ei->i_reserved_data_blocks -= used;
-	used += ei->i_allocated_meta_blocks;
 	ei->i_reserved_meta_blocks -= ei->i_allocated_meta_blocks;
-	allocated_meta_blocks = ei->i_allocated_meta_blocks;
+	percpu_counter_sub(&sbi->s_dirtyblocks_counter,
+			   used + ei->i_allocated_meta_blocks);
 	ei->i_allocated_meta_blocks = 0;
-	percpu_counter_sub(&sbi->s_dirtyblocks_counter, used);
 
 	if (ei->i_reserved_data_blocks == 0) {
 		/*
···
 		 * only when we have written all of the delayed
 		 * allocation blocks.
 		 */
-		mdb_free = ei->i_reserved_meta_blocks;
+		percpu_counter_sub(&sbi->s_dirtyblocks_counter,
+				   ei->i_reserved_meta_blocks);
 		ei->i_reserved_meta_blocks = 0;
 		ei->i_da_metadata_calc_len = 0;
-		percpu_counter_sub(&sbi->s_dirtyblocks_counter, mdb_free);
 	}
 	spin_unlock(&EXT4_I(inode)->i_block_reservation_lock);
 
-	/* Update quota subsystem */
-	if (quota_claim) {
+	/* Update quota subsystem for data blocks */
+	if (quota_claim)
 		dquot_claim_block(inode, used);
-		if (mdb_free)
-			dquot_release_reservation_block(inode, mdb_free);
-	} else {
+	else {
 		/*
 		 * We did fallocate with an offset that is already delayed
 		 * allocated. So on delayed allocated writeback we should
-		 * not update the quota for allocated blocks. But then
-		 * converting an fallocate region to initialized region would
-		 * have caused a metadata allocation. So claim quota for
-		 * that
+		 * not re-claim the quota for fallocated blocks.
 		 */
-		if (allocated_meta_blocks)
-			dquot_claim_block(inode, allocated_meta_blocks);
-		dquot_release_reservation_block(inode, mdb_free + used);
+		dquot_release_reservation_block(inode, used);
 	}
 
 	/*
···
 		ext4_discard_preallocations(inode);
 }
 
-static int check_block_validity(struct inode *inode, const char *msg,
-				sector_t logical, sector_t phys, int len)
+static int check_block_validity(struct inode *inode, const char *func,
+				struct ext4_map_blocks *map)
 {
-	if (!ext4_data_block_valid(EXT4_SB(inode->i_sb), phys, len)) {
-		__ext4_error(inode->i_sb, msg,
-			   "inode #%lu logical block %llu mapped to %llu "
-			   "(size %d)", inode->i_ino,
-			   (unsigned long long) logical,
-			   (unsigned long long) phys, len);
+	if (!ext4_data_block_valid(EXT4_SB(inode->i_sb), map->m_pblk,
+				   map->m_len)) {
+		ext4_error_inode(func, inode,
+			   "lblock %lu mapped to illegal pblock %llu "
+			   "(length %d)", (unsigned long) map->m_lblk,
+				 map->m_pblk, map->m_len);
 		return -EIO;
 	}
 	return 0;
···
 }
 
 /*
- * The ext4_get_blocks() function tries to look up the requested blocks,
+ * The ext4_map_blocks() function tries to look up the requested blocks,
  * and returns if the blocks are already mapped.
  *
  * Otherwise it takes the write lock of the i_data_sem and allocate blocks
  * and store the allocated blocks in the result buffer head and mark it
  * mapped.
  *
- * If file type is extents based, it will call ext4_ext_get_blocks(),
- * Otherwise, call with ext4_ind_get_blocks() to handle indirect mapping
+ * If file type is extents based, it will call ext4_ext_map_blocks(),
+ * Otherwise, call with ext4_ind_map_blocks() to handle indirect mapping
  * based files
  *
  * On success, it returns the number of blocks being mapped or allocate.
···
  *
  * It returns the error in case of allocation failure.
  */
-int ext4_get_blocks(handle_t *handle, struct inode *inode, sector_t block,
-		    unsigned int max_blocks, struct buffer_head *bh,
-		    int flags)
+int ext4_map_blocks(handle_t *handle, struct inode *inode,
+		    struct ext4_map_blocks *map, int flags)
 {
 	int retval;
 
-	clear_buffer_mapped(bh);
-	clear_buffer_unwritten(bh);
-
-	ext_debug("ext4_get_blocks(): inode %lu, flag %d, max_blocks %u,"
-		  "logical block %lu\n", inode->i_ino, flags, max_blocks,
-		  (unsigned long)block);
+	map->m_flags = 0;
+	ext_debug("ext4_map_blocks(): inode %lu, flag %d, max_blocks %u,"
+		  "logical block %lu\n", inode->i_ino, flags, map->m_len,
+		  (unsigned long) map->m_lblk);
 	/*
 	 * Try to see if we can get the block without requesting a new
 	 * file system block.
 	 */
 	down_read((&EXT4_I(inode)->i_data_sem));
-	if (EXT4_I(inode)->i_flags & EXT4_EXTENTS_FL) {
-		retval =  ext4_ext_get_blocks(handle, inode, block, max_blocks,
-				bh, 0);
+	if (ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS)) {
+		retval = ext4_ext_map_blocks(handle, inode, map, 0);
 	} else {
-		retval = ext4_ind_get_blocks(handle, inode, block, max_blocks,
-					     bh, 0);
+		retval = ext4_ind_map_blocks(handle, inode, map, 0);
 	}
 	up_read((&EXT4_I(inode)->i_data_sem));
 
-	if (retval > 0 && buffer_mapped(bh)) {
-		int ret = check_block_validity(inode, "file system corruption",
-					       block, bh->b_blocknr, retval);
+	if (retval > 0 && map->m_flags & EXT4_MAP_MAPPED) {
+		int ret = check_block_validity(inode, __func__, map);
 		if (ret != 0)
 			return ret;
 	}
···
 	 * ext4_ext_get_block() returns th create = 0
 	 * with buffer head unmapped.
 	 */
-	if (retval > 0 && buffer_mapped(bh))
+	if (retval > 0 && map->m_flags & EXT4_MAP_MAPPED)
 		return retval;
 
 	/*
···
 	 * of BH_Unwritten and BH_Mapped flags being simultaneously
 	 * set on the buffer_head.
 	 */
-	clear_buffer_unwritten(bh);
+	map->m_flags &= ~EXT4_MAP_UNWRITTEN;
 
 	/*
 	 * New blocks allocate and/or writing to uninitialized extent
···
 	 * We need to check for EXT4 here because migrate
 	 * could have changed the inode type in between
 	 */
-	if (EXT4_I(inode)->i_flags & EXT4_EXTENTS_FL) {
-		retval =  ext4_ext_get_blocks(handle, inode, block, max_blocks,
-					      bh, flags);
+	if (ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS)) {
+		retval = ext4_ext_map_blocks(handle, inode, map, flags);
 	} else {
-		retval = ext4_ind_get_blocks(handle, inode, block,
-					     max_blocks, bh, flags);
+		retval = ext4_ind_map_blocks(handle, inode, map, flags);
 
-		if (retval > 0 && buffer_new(bh)) {
+		if (retval > 0 && map->m_flags & EXT4_MAP_NEW) {
 			/*
 			 * We allocated new blocks which will result in
 			 * i_data's format changing.  Force the migrate
···
 		EXT4_I(inode)->i_delalloc_reserved_flag = 0;
 
 	up_write((&EXT4_I(inode)->i_data_sem));
-	if (retval > 0 && buffer_mapped(bh)) {
-		int ret = check_block_validity(inode, "file system "
-					       "corruption after allocation",
-					       block, bh->b_blocknr, retval);
+	if (retval > 0 && map->m_flags & EXT4_MAP_MAPPED) {
+		int ret = check_block_validity(inode,
+					       "ext4_map_blocks_after_alloc",
+					       map);
 		if (ret != 0)
 			return ret;
 	}
···
 /* Maximum number of blocks we map for direct IO at once. */
 #define DIO_MAX_BLOCKS 4096
 
-int ext4_get_block(struct inode *inode, sector_t iblock,
-		   struct buffer_head *bh_result, int create)
+static int _ext4_get_block(struct inode *inode, sector_t iblock,
+			   struct buffer_head *bh, int flags)
 {
 	handle_t *handle = ext4_journal_current_handle();
+	struct ext4_map_blocks map;
 	int ret = 0, started = 0;
-	unsigned max_blocks = bh_result->b_size >> inode->i_blkbits;
 	int dio_credits;
 
-	if (create && !handle) {
+	map.m_lblk = iblock;
+	map.m_len = bh->b_size >> inode->i_blkbits;
+
+	if (flags && !handle) {
 		/* Direct IO write... */
-		if (max_blocks > DIO_MAX_BLOCKS)
-			max_blocks = DIO_MAX_BLOCKS;
-		dio_credits = ext4_chunk_trans_blocks(inode, max_blocks);
+		if (map.m_len > DIO_MAX_BLOCKS)
+			map.m_len = DIO_MAX_BLOCKS;
+		dio_credits = ext4_chunk_trans_blocks(inode, map.m_len);
 		handle = ext4_journal_start(inode, dio_credits);
 		if (IS_ERR(handle)) {
 			ret = PTR_ERR(handle);
-			goto out;
+			return ret;
 		}
 		started = 1;
 	}
 
-	ret = ext4_get_blocks(handle, inode, iblock, max_blocks, bh_result,
-			      create ? EXT4_GET_BLOCKS_CREATE : 0);
+	ret = ext4_map_blocks(handle, inode, &map, flags);
 	if (ret > 0) {
-		bh_result->b_size = (ret << inode->i_blkbits);
+		map_bh(bh, inode->i_sb, map.m_pblk);
+		bh->b_state = (bh->b_state & ~EXT4_MAP_FLAGS) | map.m_flags;
+		bh->b_size = inode->i_sb->s_blocksize * map.m_len;
 		ret = 0;
 	}
 	if (started)
 		ext4_journal_stop(handle);
-out:
 	return ret;
+}
+
+int ext4_get_block(struct inode *inode, sector_t iblock,
+		   struct buffer_head *bh, int create)
+{
+	return _ext4_get_block(inode, iblock, bh,
+			       create ? EXT4_GET_BLOCKS_CREATE : 0);
 }
 
 /*
···
 struct buffer_head *ext4_getblk(handle_t *handle, struct inode *inode,
 				ext4_lblk_t block, int create, int *errp)
 {
-	struct buffer_head dummy;
+	struct ext4_map_blocks map;
+	struct buffer_head *bh;
 	int fatal = 0, err;
-	int flags = 0;
 
 	J_ASSERT(handle != NULL || create == 0);
 
-	dummy.b_state = 0;
-	dummy.b_blocknr = -1000;
-	buffer_trace_init(&dummy.b_history);
-	if (create)
-		flags |= EXT4_GET_BLOCKS_CREATE;
-	err = ext4_get_blocks(handle, inode, block, 1, &dummy, flags);
-	/*
-	 * ext4_get_blocks() returns number of blocks mapped. 0 in
-	 * case of a HOLE.
-	 */
-	if (err > 0) {
-		if (err > 1)
-			WARN_ON(1);
-		err = 0;
-	}
-	*errp = err;
-	if (!err && buffer_mapped(&dummy)) {
-		struct buffer_head *bh;
-		bh = sb_getblk(inode->i_sb, dummy.b_blocknr);
-		if (!bh) {
-			*errp = -EIO;
-			goto err;
-		}
-		if (buffer_new(&dummy)) {
-			J_ASSERT(create != 0);
-			J_ASSERT(handle != NULL);
+	map.m_lblk = block;
+	map.m_len = 1;
+	err = ext4_map_blocks(handle, inode, &map,
+			      create ? EXT4_GET_BLOCKS_CREATE : 0);
 
-			/*
-			 * Now that we do not always journal data, we should
-			 * keep in mind whether this should always journal the
-			 * new buffer as metadata.  For now, regular file
-			 * writes use ext4_get_block instead, so it's not a
-			 * problem.
-			 */
-			lock_buffer(bh);
-			BUFFER_TRACE(bh, "call get_create_access");
-			fatal = ext4_journal_get_create_access(handle, bh);
-			if (!fatal && !buffer_uptodate(bh)) {
-				memset(bh->b_data, 0, inode->i_sb->s_blocksize);
-				set_buffer_uptodate(bh);
-			}
-			unlock_buffer(bh);
-			BUFFER_TRACE(bh, "call ext4_handle_dirty_metadata");
-			err = ext4_handle_dirty_metadata(handle, inode, bh);
-			if (!fatal)
-				fatal = err;
-		} else {
-			BUFFER_TRACE(bh, "not a new buffer");
-		}
-		if (fatal) {
-			*errp = fatal;
-			brelse(bh);
-			bh = NULL;
-		}
-		return bh;
+	if (err < 0)
+		*errp = err;
+	if (err <= 0)
+		return NULL;
+	*errp = 0;
+
+	bh = sb_getblk(inode->i_sb, map.m_pblk);
+	if (!bh) {
+		*errp = -EIO;
+		return NULL;
 	}
-err:
-	return NULL;
+	if (map.m_flags & EXT4_MAP_NEW) {
+		J_ASSERT(create != 0);
+		J_ASSERT(handle != NULL);
+
+		/*
+		 * Now that we do not always journal data, we should
+		 * keep in mind whether this should always journal the
+		 * new buffer as metadata.  For now, regular file
+		 * writes use ext4_get_block instead, so it's not a
+		 * problem.
+		 */
+		lock_buffer(bh);
+		BUFFER_TRACE(bh, "call get_create_access");
+		fatal = ext4_journal_get_create_access(handle, bh);
+		if (!fatal && !buffer_uptodate(bh)) {
+			memset(bh->b_data, 0, inode->i_sb->s_blocksize);
+			set_buffer_uptodate(bh);
+		}
+		unlock_buffer(bh);
+		BUFFER_TRACE(bh, "call ext4_handle_dirty_metadata");
+		err = ext4_handle_dirty_metadata(handle, inode, bh);
+		if (!fatal)
+			fatal = err;
+	} else {
+		BUFFER_TRACE(bh, "not a new buffer");
+	}
+	if (fatal) {
+		*errp = fatal;
+		brelse(bh);
+		bh = NULL;
+	}
+	return bh;
 }
 
 struct buffer_head *ext4_bread(handle_t *handle, struct inode *inode,
···
 	int retries = 0;
 	struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb);
 	struct ext4_inode_info *ei = EXT4_I(inode);
-	unsigned long md_needed, md_reserved;
+	unsigned long md_needed;
 	int ret;
 
 	/*
···
 	 */
 repeat:
 	spin_lock(&ei->i_block_reservation_lock);
-	md_reserved = ei->i_reserved_meta_blocks;
 	md_needed = ext4_calc_metadata_amount(inode, lblock);
 	trace_ext4_da_reserve_space(inode, md_needed);
 	spin_unlock(&ei->i_block_reservation_lock);
 
 	/*
-	 * Make quota reservation here to prevent quota overflow
-	 * later. Real quota accounting is done at pages writeout
-	 * time.
+	 * We will charge metadata quota at writeout time; this saves
+	 * us from metadata over-estimation, though we may go over by
+	 * a small amount in the end.  Here we just reserve for data.
 	 */
-	ret = dquot_reserve_block(inode, md_needed + 1);
+	ret = dquot_reserve_block(inode, 1);
 	if (ret)
 		return ret;
-
+	/*
+	 * We do still charge estimated metadata to the sb though;
+	 * we cannot afford to run out of free blocks.
+	 */
 	if (ext4_claim_free_blocks(sbi, md_needed + 1)) {
-		dquot_release_reservation_block(inode, md_needed + 1);
+		dquot_release_reservation_block(inode, 1);
 		if (ext4_should_retry_alloc(inode->i_sb, &retries)) {
 			yield();
 			goto repeat;
···
 
 	spin_lock(&EXT4_I(inode)->i_block_reservation_lock);
 
+	trace_ext4_da_release_space(inode, to_free);
 	if (unlikely(to_free > ei->i_reserved_data_blocks)) {
 		/*
 		 * if there aren't enough reserved blocks, then the
···
 		 * only when we have written all of the delayed
 		 * allocation blocks.
 		 */
-		to_free += ei->i_reserved_meta_blocks;
+		percpu_counter_sub(&sbi->s_dirtyblocks_counter,
+				   ei->i_reserved_meta_blocks);
 		ei->i_reserved_meta_blocks = 0;
 		ei->i_da_metadata_calc_len = 0;
 	}
 
-	/* update fs dirty blocks counter */
+	/* update fs dirty data blocks counter */
 	percpu_counter_sub(&sbi->s_dirtyblocks_counter, to_free);
 
 	spin_unlock(&EXT4_I(inode)->i_block_reservation_lock);
···
 /*
  * mpage_put_bnr_to_bhs - walk blocks and assign them actual numbers
  *
- * @mpd->inode - inode to walk through
- * @exbh->b_blocknr - first block on a disk
- * @exbh->b_size - amount of space in bytes
- * @logical - first logical block to start assignment with
- *
  * the function goes through all passed space and put actual disk
  * block numbers into buffer heads, dropping BH_Delay and BH_Unwritten
  */
-static void mpage_put_bnr_to_bhs(struct mpage_da_data *mpd, sector_t logical,
-				 struct buffer_head *exbh)
+static void mpage_put_bnr_to_bhs(struct mpage_da_data *mpd,
+				 struct ext4_map_blocks *map)
 {
 	struct inode *inode = mpd->inode;
 	struct address_space *mapping = inode->i_mapping;
-	int blocks = exbh->b_size >> inode->i_blkbits;
-	sector_t pblock = exbh->b_blocknr, cur_logical;
+	int blocks = map->m_len;
+	sector_t pblock = map->m_pblk, cur_logical;
 	struct buffer_head *head, *bh;
 	pgoff_t index, end;
 	struct pagevec pvec;
 	int nr_pages, i;
 
-	index = logical >> (PAGE_CACHE_SHIFT - inode->i_blkbits);
-	end = (logical + blocks - 1) >> (PAGE_CACHE_SHIFT - inode->i_blkbits);
+	index = map->m_lblk >> (PAGE_CACHE_SHIFT - inode->i_blkbits);
+	end = (map->m_lblk + blocks - 1) >> (PAGE_CACHE_SHIFT - inode->i_blkbits);
 	cur_logical = index << (PAGE_CACHE_SHIFT - inode->i_blkbits);
 
 	pagevec_init(&pvec, 0);
···
 
 			/* skip blocks out of the range */
 			do {
-				if (cur_logical >= logical)
+				if (cur_logical >= map->m_lblk)
 					break;
 				cur_logical++;
 			} while ((bh = bh->b_this_page) != head);
 
 			do {
-				if (cur_logical >= logical + blocks)
+				if (cur_logical >= map->m_lblk + blocks)
 					break;
 
-				if (buffer_delay(bh) ||
-						buffer_unwritten(bh)) {
+				if (buffer_delay(bh) || buffer_unwritten(bh)) {
 
 					BUG_ON(bh->b_bdev != inode->i_sb->s_bdev);
 
···
 				} else if (buffer_mapped(bh))
 					BUG_ON(bh->b_blocknr != pblock);
 
-				if (buffer_uninit(exbh))
+				if (map->m_flags & EXT4_MAP_UNINIT)
 					set_buffer_uninit(bh);
 				cur_logical++;
 				pblock++;
···
 	}
 }
 
-
-/*
- * __unmap_underlying_blocks - just a helper function to unmap
- * set of blocks described by @bh
- */
-static inline void __unmap_underlying_blocks(struct inode *inode,
-					     struct buffer_head *bh)
-{
-	struct block_device *bdev = inode->i_sb->s_bdev;
-	int blocks, i;
-
-	blocks = bh->b_size >> inode->i_blkbits;
-	for (i = 0; i < blocks; i++)
-		unmap_underlying_metadata(bdev, bh->b_blocknr + i);
-}
 
 static void ext4_da_block_invalidatepages(struct mpage_da_data *mpd,
 					sector_t logical, long blk_cnt)
···
 static int mpage_da_map_blocks(struct mpage_da_data *mpd)
 {
 	int err, blks, get_blocks_flags;
-	struct buffer_head new;
+	struct ext4_map_blocks map;
 	sector_t next = mpd->b_blocknr;
 	unsigned max_blocks = mpd->b_size >> mpd->inode->i_blkbits;
 	loff_t disksize = EXT4_I(mpd->inode)->i_disksize;
···
 	 * EXT4_GET_BLOCKS_DELALLOC_RESERVE so the delalloc accounting
 	 * variables are updated after the blocks have been allocated.
 	 */
-	new.b_state = 0;
+	map.m_lblk = next;
+	map.m_len = max_blocks;
 	get_blocks_flags = EXT4_GET_BLOCKS_CREATE;
 	if (ext4_should_dioread_nolock(mpd->inode))
 		get_blocks_flags |= EXT4_GET_BLOCKS_IO_CREATE_EXT;
 	if (mpd->b_state & (1 << BH_Delay))
 		get_blocks_flags |= EXT4_GET_BLOCKS_DELALLOC_RESERVE;
 
-	blks = ext4_get_blocks(handle, mpd->inode, next, max_blocks,
-			       &new, get_blocks_flags);
+	blks = ext4_map_blocks(handle, mpd->inode, &map, get_blocks_flags);
 	if (blks < 0) {
 		err = blks;
 		/*
···
 		ext4_msg(mpd->inode->i_sb, KERN_CRIT,
 			 "delayed block allocation failed for inode %lu at "
 			 "logical offset %llu with max blocks %zd with "
-			 "error %d\n", mpd->inode->i_ino,
+			 "error %d", mpd->inode->i_ino,
 			 (unsigned long long) next,
 			 mpd->b_size >> mpd->inode->i_blkbits, err);
 		printk(KERN_CRIT "This should not happen!!  "
···
 	}
 	BUG_ON(blks == 0);
 
-	new.b_size = (blks << mpd->inode->i_blkbits);
+	if (map.m_flags & EXT4_MAP_NEW) {
+		struct block_device *bdev = mpd->inode->i_sb->s_bdev;
+		int i;
 
-	if (buffer_new(&new))
-		__unmap_underlying_blocks(mpd->inode, &new);
+		for (i = 0; i < map.m_len; i++)
+			unmap_underlying_metadata(bdev, map.m_pblk + i);
+	}
 
 	/*
 	 * If blocks are delayed marked, we need to
···
 	 */
 	if ((mpd->b_state & (1 << BH_Delay)) ||
 	    (mpd->b_state & (1 << BH_Unwritten)))
-		mpage_put_bnr_to_bhs(mpd, next, &new);
+		mpage_put_bnr_to_bhs(mpd, &map);
 
 	if (ext4_should_order_data(mpd->inode)) {
 		err = ext4_jbd2_file_inode(handle, mpd->inode);
···
 	sector_t next;
 	int nrblocks = mpd->b_size >> mpd->inode->i_blkbits;
 
+	/*
+	 * XXX Don't go larger than mballoc is willing to allocate
+	 * This is a stopgap solution.  We eventually need to fold
+	 * mpage_da_submit_io() into this function and then call
+	 * ext4_get_blocks() multiple times in a loop
+	 */
+	if (nrblocks >= 8*1024*1024/mpd->inode->i_sb->s_blocksize)
+		goto flush_it;
+
 	/* check if thereserved journal credits might overflow */
-	if (!(EXT4_I(mpd->inode)->i_flags & EXT4_EXTENTS_FL)) {
+	if (!(ext4_test_inode_flag(mpd->inode, EXT4_INODE_EXTENTS))) {
 		if (nrblocks >= EXT4_MAX_TRANS_DATA) {
 			/*
 			 * With non-extent format we are limited by the journal
···
 	struct buffer_head *bh, *head;
 	sector_t logical;
 
-	if (mpd->io_done) {
-		/*
-		 * Rest of the page in the page_vec
-		 * redirty then and skip then. We will
-		 * try to write them again after
-		 * starting a new transaction
-		 */
-		redirty_page_for_writepage(wbc, page);
-		unlock_page(page);
-		return MPAGE_DA_EXTENT_TAIL;
-	}
 	/*
 	 * Can we merge this page to current extent?
 	 */
···
  * initialized properly.
  */
 static int ext4_da_get_block_prep(struct inode *inode, sector_t iblock,
-				  struct buffer_head *bh_result, int create)
+				  struct buffer_head *bh, int create)
 {
+	struct ext4_map_blocks map;
 	int ret = 0;
 	sector_t invalid_block = ~((sector_t) 0xffff);
 
···
 		invalid_block = ~0;
 
 	BUG_ON(create == 0);
-	BUG_ON(bh_result->b_size != inode->i_sb->s_blocksize);
+	BUG_ON(bh->b_size != inode->i_sb->s_blocksize);
+
+	map.m_lblk = iblock;
+	map.m_len = 1;
 
 	/*
 	 * first, we need to know whether the block is allocated already
 	 * preallocated blocks are unmapped but should treated
 	 * the same as allocated blocks.
 	 */
-	ret = ext4_get_blocks(NULL, inode, iblock, 1,  bh_result, 0);
-	if ((ret == 0) && !buffer_delay(bh_result)) {
-		/* the block isn't (pre)allocated yet, let's reserve space */
+	ret = ext4_map_blocks(NULL, inode, &map, 0);
+	if (ret < 0)
+		return ret;
+	if (ret == 0) {
+		if (buffer_delay(bh))
+			return 0; /* Not sure this could or should happen */
 		/*
 		 * XXX: __block_prepare_write() unmaps passed block,
 		 * is it OK?
···
 			/* not enough space to reserve */
 			return ret;
 
-		map_bh(bh_result, inode->i_sb, invalid_block);
-		set_buffer_new(bh_result);
-		set_buffer_delay(bh_result);
-	} else if (ret > 0) {
-		bh_result->b_size = (ret << inode->i_blkbits);
-		if (buffer_unwritten(bh_result)) {
-			/* A delayed write to unwritten bh should
-			 * be marked new and mapped.  Mapped ensures
-			 * that we don't do get_block multiple times
-			 * when we write to the same offset and new
-			 * ensures that we do proper zero out for
-			 * partial write.
-			 */
-			set_buffer_new(bh_result);
-			set_buffer_mapped(bh_result);
-		}
-		ret = 0;
+		map_bh(bh, inode->i_sb, invalid_block);
+		set_buffer_new(bh);
+		set_buffer_delay(bh);
+		return 0;
 	}
 
-	return ret;
+	map_bh(bh, inode->i_sb, map.m_pblk);
+	bh->b_state = (bh->b_state & ~EXT4_MAP_FLAGS) | map.m_flags;
+
+	if (buffer_unwritten(bh)) {
+		/* A delayed write to unwritten bh should be marked
+		 * new and mapped.  Mapped ensures that we don't do
+		 * get_block multiple times when we write to the same
+		 * offset and new ensures that we do proper zero out
+		 * for partial write.
+		 */
+		set_buffer_new(bh);
+		set_buffer_mapped(bh);
+	}
+	return 0;
 }
 
 /*
···
 static int noalloc_get_block_write(struct inode *inode, sector_t iblock,
 				   struct buffer_head *bh_result, int create)
 {
-	int ret = 0;
-	unsigned max_blocks = bh_result->b_size >> inode->i_blkbits;
-
 	BUG_ON(bh_result->b_size != inode->i_sb->s_blocksize);
-
-	/*
-	 * we don't want to do block allocation in writepage
-	 * so call get_block_wrap with create = 0
-	 */
-	ret = ext4_get_blocks(NULL, inode, iblock, max_blocks, bh_result, 0);
-	if (ret > 0) {
-		bh_result->b_size = (ret << inode->i_blkbits);
-		ret = 0;
-	}
-	return ret;
+	return _ext4_get_block(inode, iblock, bh_result, 0);
 }
 
 static int bget_one(handle_t *handle, struct buffer_head *bh)
···
 	 * number of contiguous block. So we will limit
 	 * number of contiguous block to a sane value
 	 */
-	if (!(EXT4_I(inode)->i_flags & EXT4_EXTENTS_FL) &&
+	if (!(ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS)) &&
 	    (max_blocks > EXT4_MAX_TRANS_DATA))
 		max_blocks = EXT4_MAX_TRANS_DATA;
 
 	return ext4_chunk_trans_blocks(inode, max_blocks);
 }
+
+/*
+ * write_cache_pages_da - walk the list of dirty pages of the given
+ * address space and call the callback function (which usually writes
+ * the pages).
+ *
+ * This is a forked version of write_cache_pages().  Differences:
+ *	Range cyclic is ignored.
+ *	no_nrwrite_index_update is always presumed true
+ */
+static int write_cache_pages_da(struct address_space *mapping,
+				struct writeback_control *wbc,
+				struct mpage_da_data *mpd)
+{
+	int ret = 0;
+	int done = 0;
+	struct pagevec pvec;
+	int nr_pages;
+	pgoff_t index;
+	pgoff_t end;		/* Inclusive */
+	long nr_to_write = wbc->nr_to_write;
+
+	pagevec_init(&pvec, 0);
+	index = wbc->range_start >> PAGE_CACHE_SHIFT;
+	end = wbc->range_end >> PAGE_CACHE_SHIFT;
+
+	while (!done && (index <= end)) {
+		int i;
+
+		nr_pages = pagevec_lookup_tag(&pvec, mapping, &index,
+			      PAGECACHE_TAG_DIRTY,
+			      min(end - index, (pgoff_t)PAGEVEC_SIZE-1) + 1);
+		if (nr_pages == 0)
+			break;
+
+		for (i = 0; i < nr_pages; i++) {
+			struct page *page = pvec.pages[i];
+
+			/*
+			 * At this point, the page may be truncated or
+			 * invalidated (changing page->mapping to NULL), or
+			 * even swizzled back from swapper_space to tmpfs file
+			 * mapping. However, page->index will not change
+			 * because we have a reference on the page.
+			 */
+			if (page->index > end) {
+				done = 1;
+				break;
+			}
+
+			lock_page(page);
+
+			/*
+			 * Page truncated or invalidated. We can freely skip it
+			 * then, even for data integrity operations: the page
+			 * has disappeared concurrently, so there could be no
+			 * real expectation of this data interity operation
+			 * even if there is now a new, dirty page at the same
+			 * pagecache address.
+			 */
+			if (unlikely(page->mapping != mapping)) {
+continue_unlock:
+				unlock_page(page);
+				continue;
+			}
+
+			if (!PageDirty(page)) {
+				/* someone wrote it for us */
+				goto continue_unlock;
+			}
+
+			if (PageWriteback(page)) {
+				if (wbc->sync_mode != WB_SYNC_NONE)
+					wait_on_page_writeback(page);
+				else
+					goto continue_unlock;
+			}
+
+			BUG_ON(PageWriteback(page));
+			if (!clear_page_dirty_for_io(page))
+				goto continue_unlock;
+
+			ret = __mpage_da_writepage(page, wbc, mpd);
+			if (unlikely(ret)) {
+				if (ret == AOP_WRITEPAGE_ACTIVATE) {
+					unlock_page(page);
+					ret = 0;
+				} else {
+					done = 1;
+					break;
+				}
+			}
+
+			if (nr_to_write > 0) {
+				nr_to_write--;
+				if (nr_to_write == 0 &&
+				    wbc->sync_mode == WB_SYNC_NONE) {
+					/*
+					 * We stop writing back only if we are
+					 * not doing integrity sync. In case of
+					 * integrity sync we have to keep going
+					 * because someone may be concurrently
+					 * dirtying pages, and we might have
+					 * synced a lot of newly appeared dirty
+					 * pages, but have not synced all of the
+					 * old dirty pages.
+					 */
+					done = 1;
+					break;
+				}
+			}
+		}
+		pagevec_release(&pvec);
+		cond_resched();
+	}
+	return ret;
+}
+
 
 static int ext4_da_writepages(struct address_space *mapping,
 			      struct writeback_control *wbc)
···
 	handle_t *handle = NULL;
 	struct mpage_da_data mpd;
 	struct inode *inode = mapping->host;
-	int no_nrwrite_index_update;
 	int pages_written = 0;
 	long pages_skipped;
 	unsigned int max_pages;
···
 	mpd.wbc = wbc;
 	mpd.inode = mapping->host;
 
-	/*
-	 * we don't want write_cache_pages to update
-	 * nr_to_write and writeback_index
-	 */
-	no_nrwrite_index_update = wbc->no_nrwrite_index_update;
-	wbc->no_nrwrite_index_update = 1;
 	pages_skipped = wbc->pages_skipped;
 
 retry:
···
 		if (IS_ERR(handle)) {
 			ret = PTR_ERR(handle);
 			ext4_msg(inode->i_sb, KERN_CRIT, "%s: jbd2_start: "
-			       "%ld pages, ino %lu; err %d\n", __func__,
+			       "%ld pages, ino %lu; err %d", __func__,
 				wbc->nr_to_write, inode->i_ino, ret);
 			goto out_writepages;
 		}
···
 		mpd.io_done = 0;
 		mpd.pages_written = 0;
 		mpd.retval = 0;
-		ret = write_cache_pages(mapping, wbc, __mpage_da_writepage,
-					&mpd);
+		ret = write_cache_pages_da(mapping, wbc, &mpd);
 		/*
 		 * If we have a contiguous extent of pages and we
 		 * haven't done the I/O yet, map the blocks and submit
···
 	if (pages_skipped != wbc->pages_skipped)
 		ext4_msg(inode->i_sb, KERN_CRIT,
 			 "This should not happen leaving %s "
-			 "with nr_to_write = %ld ret = %d\n",
+			 "with nr_to_write = %ld ret = %d",
 			 __func__, wbc->nr_to_write, ret);
 
 	/* Update index */
···
 		mapping->writeback_index = index;
 
 out_writepages:
-	if (!no_nrwrite_index_update)
-		wbc->no_nrwrite_index_update = 0;
 	wbc->nr_to_write -= nr_to_writebump;
 	wbc->range_start = range_start;
 	trace_ext4_da_writepages_result(inode, wbc, ret, pages_written);
···
 			       loff_t pos, unsigned len, unsigned flags,
 			       struct page **pagep, void **fsdata)
 {
-	int ret, retries = 0, quota_retries = 0;
+	int ret, retries = 0;
 	struct page *page;
 	pgoff_t index;
 	unsigned from, to;
···
 
 	if (ret == -ENOSPC && ext4_should_retry_alloc(inode->i_sb, &retries))
 		goto retry;
-
-	if ((ret == -EDQUOT) &&
-	    EXT4_I(inode)->i_reserved_meta_blocks &&
-	    (quota_retries++ < 3)) {
-		/*
-		 * Since we often over-estimate the number of meta
-		 * data blocks required, we may sometimes get a
-		 * spurios out of quota error even though there would
-		 * be enough space once we write the data blocks and
-		 * find out how many meta data blocks were _really_
-		 * required.  So try forcing the inode write to see if
-		 * that helps.
-		 */
-		write_inode_now(inode, (quota_retries == 3));
-		goto retry;
-	}
 out:
 	return ret;
 }
···
 	return ret;
 }
 
+/*
+ * ext4_get_block used when preparing for a DIO write or buffer write.
+ * We allocate an uinitialized extent if blocks haven't been allocated.
+ * The extent will be converted to initialized after the IO is complete.
+ */
 static int ext4_get_block_write(struct inode *inode, sector_t iblock,
 		   struct buffer_head *bh_result, int create)
 {
-	handle_t *handle = ext4_journal_current_handle();
-	int ret = 0;
-	unsigned max_blocks = bh_result->b_size >> inode->i_blkbits;
-	int dio_credits;
-	int started = 0;
-
 	ext4_debug("ext4_get_block_write: inode %lu, create flag %d\n",
 		   inode->i_ino, create);
-	/*
-	 * ext4_get_block in prepare for a DIO write or buffer write.
-	 * We allocate an uinitialized extent if blocks haven't been allocated.
-	 * The extent will be converted to initialized after IO complete.
-	 */
-	create = EXT4_GET_BLOCKS_IO_CREATE_EXT;
-
-	if (!handle) {
-		if (max_blocks > DIO_MAX_BLOCKS)
-			max_blocks = DIO_MAX_BLOCKS;
-		dio_credits = ext4_chunk_trans_blocks(inode, max_blocks);
-		handle = ext4_journal_start(inode, dio_credits);
-		if (IS_ERR(handle)) {
-			ret = PTR_ERR(handle);
-			goto out;
-		}
-		started = 1;
-	}
-
-	ret = ext4_get_blocks(handle, inode, iblock, max_blocks, bh_result,
-			      create);
-	if (ret > 0) {
-		bh_result->b_size = (ret << inode->i_blkbits);
-		ret = 0;
-	}
-	if (started)
-		ext4_journal_stop(handle);
-out:
-	return ret;
+	return _ext4_get_block(inode, iblock, bh_result,
+			       EXT4_GET_BLOCKS_IO_CREATE_EXT);
 }
 
 static void dump_completed_IO(struct inode * inode)
···
 	struct file *file = iocb->ki_filp;
 	struct inode *inode = file->f_mapping->host;
 
-	if (EXT4_I(inode)->i_flags & EXT4_EXTENTS_FL)
+	if (ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS))
 		return ext4_ext_direct_IO(rw, iocb, iov, offset, nr_segs);
 
 	return ext4_ind_direct_IO(rw, iocb, iov, offset, nr_segs);
···
 
 	if (!ext4_data_block_valid(EXT4_SB(inode->i_sb), block_to_free,
 				   count)) {
-		ext4_error(inode->i_sb, "inode #%lu: "
-			   "attempt to clear blocks %llu len %lu, invalid",
-			   inode->i_ino, (unsigned long long) block_to_free,
-			   count);
+		EXT4_ERROR_INODE(inode, "attempt to clear invalid "
+				 "blocks %llu len %lu",
+				 (unsigned long long) block_to_free, count);
 		return 1;
 	}
 
···
 		if ((EXT4_JOURNAL(inode) == NULL) || bh2jh(this_bh))
 			ext4_handle_dirty_metadata(handle, inode, this_bh);
 		else
-			ext4_error(inode->i_sb,
-				   "circular indirect block detected, "
-				   "inode=%lu, block=%llu",
-				   inode->i_ino,
-				   (unsigned long long) this_bh->b_blocknr);
+			EXT4_ERROR_INODE(inode,
+					 "circular indirect block detected at "
+					 "block %llu",
+				(unsigned long long) this_bh->b_blocknr);
 	}
 }
 
···
 
 			if (!ext4_data_block_valid(EXT4_SB(inode->i_sb),
 						   nr, 1)) {
-				ext4_error(inode->i_sb,
-					   "indirect mapped block in inode "
-					   "#%lu invalid (level %d, blk #%lu)",
-					   inode->i_ino, depth,
-					   (unsigned long) nr);
+				EXT4_ERROR_INODE(inode,
+						 "invalid indirect mapped "
+						 "block %lu (level %d)",
+						 (unsigned long) nr, depth);
 				break;
 			}
 
···
 			 * (should be rare).
 			 */
 			if (!bh) {
-				ext4_error(inode->i_sb,
-					   "Read failure, inode=%lu, block=%llu",
-					   inode->i_ino, nr);
+				EXT4_ERROR_INODE(inode,
+						 "Read failure block=%llu",
+						 (unsigned long long) nr);
 				continue;
 			}
 
···
 	if (!ext4_can_truncate(inode))
 		return;
 
-	EXT4_I(inode)->i_flags &= ~EXT4_EOFBLOCKS_FL;
+	ext4_clear_inode_flag(inode, EXT4_INODE_EOFBLOCKS);
 
 	if (inode->i_size == 0 && !test_opt(inode->i_sb, NO_AUTO_DA_ALLOC))
 		ext4_set_inode_state(inode, EXT4_STATE_DA_ALLOC_CLOSE);
 
-	if (EXT4_I(inode)->i_flags & EXT4_EXTENTS_FL) {
+	if (ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS)) {
 		ext4_ext_truncate(inode);
 		return;
 	}
···
 
 	bh = sb_getblk(sb, block);
 	if (!bh) {
-		ext4_error(sb, "unable to read inode block - "
-			   "inode=%lu, block=%llu", inode->i_ino, block);
+		EXT4_ERROR_INODE(inode, "unable to read inode block - "
+				 "block %llu", block);
 		return -EIO;
 	}
 	if (!buffer_uptodate(bh)) {
···
 		submit_bh(READ_META, bh);
 		wait_on_buffer(bh);
 		if (!buffer_uptodate(bh)) {
-			ext4_error(sb, "unable to read inode block - inode=%lu,"
-				   " block=%llu", inode->i_ino, block);
+			EXT4_ERROR_INODE(inode, "unable to read inode "
+					 "block %llu", block);
 			brelse(bh);
 			return -EIO;
 		}
···
 	ret = 0;
 	if (ei->i_file_acl &&
 	    !ext4_data_block_valid(EXT4_SB(sb), ei->i_file_acl, 1)) {
-		ext4_error(sb, "bad extended attribute block %llu inode #%lu",
-			   ei->i_file_acl, inode->i_ino);
+		EXT4_ERROR_INODE(inode, "bad extended attribute block %llu",
+				 ei->i_file_acl);
 		ret = -EIO;
 		goto bad_inode;
 	} else if (ei->i_flags & EXT4_EXTENTS_FL) {
···
 			   new_decode_dev(le32_to_cpu(raw_inode->i_block[1])));
 	} else {
 		ret = -EIO;
-		ext4_error(inode->i_sb, "bogus i_mode (%o) for inode=%lu",
-			   inode->i_mode, inode->i_ino);
+		EXT4_ERROR_INODE(inode, "bogus i_mode (%o)", inode->i_mode);
 		goto bad_inode;
 	}
 	brelse(iloc.bh);
···
 		if (wbc->sync_mode == WB_SYNC_ALL)
 			sync_dirty_buffer(iloc.bh);
 		if (buffer_req(iloc.bh) && !buffer_uptodate(iloc.bh)) {
-			ext4_error(inode->i_sb, "IO error syncing inode, "
-				   "inode=%lu, block=%llu", inode->i_ino,
-				   (unsigned long long)iloc.bh->b_blocknr);
+			EXT4_ERROR_INODE(inode,
+				"IO error syncing inode (block=%llu)",
+				(unsigned long long) iloc.bh->b_blocknr);
 			err = -EIO;
 		}
 		brelse(iloc.bh);
···
 	}
 
 	if (attr->ia_valid & ATTR_SIZE) {
-		if (!(EXT4_I(inode)->i_flags & EXT4_EXTENTS_FL)) {
+		if (!(ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS))) {
 			struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb);
 
 			if (attr->ia_size > sbi->s_bitmap_maxbytes) {
···
 	if (S_ISREG(inode->i_mode) &&
 	    attr->ia_valid & ATTR_SIZE &&
 	    (attr->ia_size < inode->i_size ||
-	     (EXT4_I(inode)->i_flags & EXT4_EOFBLOCKS_FL))) {
+	     (ext4_test_inode_flag(inode, EXT4_INODE_EOFBLOCKS)))) {
 		handle_t *handle;
 
 		handle = ext4_journal_start(inode, 3);
···
 			}
 		}
 		/* ext4_truncate will clear the flag */
-		if ((EXT4_I(inode)->i_flags & EXT4_EOFBLOCKS_FL))
+		if ((ext4_test_inode_flag(inode, EXT4_INODE_EOFBLOCKS)))
 			ext4_truncate(inode);
 	}
 
···
 
 static int ext4_index_trans_blocks(struct inode *inode, int nrblocks, int chunk)
 {
-	if (!(EXT4_I(inode)->i_flags & EXT4_EXTENTS_FL))
+	if (!(ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS)))
 		return ext4_indirect_trans_blocks(inode, nrblocks, chunk);
 	return ext4_ext_index_trans_blocks(inode, nrblocks, chunk);
 }
···
 	 */
 
 	if (val)
-		EXT4_I(inode)->i_flags |= EXT4_JOURNAL_DATA_FL;
+		ext4_set_inode_flag(inode, EXT4_INODE_JOURNAL_DATA);
 	else
-		EXT4_I(inode)->i_flags &= ~EXT4_JOURNAL_DATA_FL;
+		ext4_clear_inode_flag(inode, EXT4_INODE_JOURNAL_DATA);
 	ext4_set_aops(inode);
 
 	jbd2_journal_unlock_updates(journal);

fs/ext4/ioctl.c

···
 		if (me.moved_len > 0)
 			file_remove_suid(donor_filp);
 
-		if (copy_to_user((struct move_extent __user *)arg, 
+		if (copy_to_user((struct move_extent __user *)arg,
 				 &me, sizeof(me)))
 			err = -EFAULT;
 mext_out:
···
 	case EXT4_IOC32_SETRSVSZ:
 		cmd = EXT4_IOC_SETRSVSZ;
 		break;
-	case EXT4_IOC_GROUP_ADD:
+	case EXT4_IOC32_GROUP_ADD: {
+		struct compat_ext4_new_group_input __user *uinput;
+		struct ext4_new_group_input input;
+		mm_segment_t old_fs;
+		int err;
+
+		uinput = compat_ptr(arg);
+		err = get_user(input.group, &uinput->group);
+		err |= get_user(input.block_bitmap, &uinput->block_bitmap);
+		err |= get_user(input.inode_bitmap, &uinput->inode_bitmap);
+		err |= get_user(input.inode_table, &uinput->inode_table);
+		err |= get_user(input.blocks_count, &uinput->blocks_count);
+		err |= get_user(input.reserved_blocks,
+				&uinput->reserved_blocks);
+		if (err)
+			return -EFAULT;
+		old_fs = get_fs();
+		set_fs(KERNEL_DS);
+		err = ext4_ioctl(file, EXT4_IOC_GROUP_ADD,
+				 (unsigned long) &input);
+		set_fs(old_fs);
+		return err;
+	}
+	case EXT4_IOC_MOVE_EXT:
 		break;
 	default:
 		return -ENOIOCTLCMD;

fs/ext4/mballoc.c

···
 	}
 }
 
+/*
+ * Cache the order of the largest free extent we have available in this block
+ * group.
+ */
+static void
+mb_set_largest_free_order(struct super_block *sb, struct ext4_group_info *grp)
+{
+	int i;
+	int bits;
+
+	grp->bb_largest_free_order = -1; /* uninit */
+
+	bits = sb->s_blocksize_bits + 1;
+	for (i = bits; i >= 0; i--) {
+		if (grp->bb_counters[i] > 0) {
+			grp->bb_largest_free_order = i;
+			break;
+		}
+	}
+}
+
 static noinline_for_stack
 void ext4_mb_generate_buddy(struct super_block *sb,
 				void *buddy, void *bitmap, ext4_group_t group)
···
 		 */
 		grp->bb_free = free;
 	}
+	mb_set_largest_free_order(sb, grp);
 
 	clear_bit(EXT4_GROUP_INFO_NEED_INIT_BIT, &(grp->bb_state));
 
···
  * contain blocks_per_page (PAGE_CACHE_SIZE / blocksize)  blocks.
  * So it can have information regarding groups_per_page which
  * is blocks_per_page/2
+ *
+ * Locking note:  This routine takes the block group lock of all groups
+ * for this page; do not hold this lock when calling this routine!
  */
 
 static int ext4_mb_init_cache(struct page *page, char *incore)
···
 			BUG_ON(incore == NULL);
 			mb_debug(1, "put buddy for group %u in page %lu/%x\n",
 				group, page->index, i * blocksize);
+			trace_ext4_mb_buddy_bitmap_load(sb, group);
 			grinfo = ext4_get_group_info(sb, group);
 			grinfo->bb_fragments = 0;
 			memset(grinfo->bb_counters, 0,
···
 			BUG_ON(incore != NULL);
 			mb_debug(1, "put bitmap for group %u in page %lu/%x\n",
 				group, page->index, i * blocksize);
+			trace_ext4_mb_bitmap_load(sb, group);
 
 			/* see comments in ext4_mb_put_pa() */
 			ext4_lock_group(sb, group);
···
 	return err;
 }
 
+/*
+ * Locking note:  This routine calls ext4_mb_init_cache(), which takes the
+ * block group lock of all groups for this page; do not hold the BG lock when
+ * calling this routine!
+ */
 static noinline_for_stack
 int ext4_mb_init_group(struct super_block *sb, ext4_group_t group)
 {
···
 	return ret;
 }
 
+/*
+ * Locking note:  This routine calls ext4_mb_init_cache(), which takes the
+ * block group lock of all groups for this page; do not hold the BG lock when
+ * calling this routine!
+ */
 static noinline_for_stack int
 ext4_mb_load_buddy(struct super_block *sb, ext4_group_t group,
 					struct ext4_buddy *e4b)
···
 	return ret;
 }
 
-static void ext4_mb_release_desc(struct ext4_buddy *e4b)
+static void ext4_mb_unload_buddy(struct ext4_buddy *e4b)
 {
 	if (e4b->bd_bitmap_page)
 		page_cache_release(e4b->bd_bitmap_page);
···
 			buddy = buddy2;
 		} while (1);
 	}
+	mb_set_largest_free_order(sb, e4b->bd_info);
 	mb_check_buddy(e4b);
 }
 
···
 		e4b->bd_info->bb_counters[ord]++;
 		e4b->bd_info->bb_counters[ord]++;
 	}
+	mb_set_largest_free_order(e4b->bd_sb, e4b->bd_info);
 
 	mb_set_bits(EXT4_MB_BITMAP(e4b), ex->fe_start, len0);
 	mb_check_buddy(e4b);
···
 	}
 
 	ext4_unlock_group(ac->ac_sb, group);
-	ext4_mb_release_desc(e4b);
+	ext4_mb_unload_buddy(e4b);
 
 	return 0;
 }
···
 		ext4_mb_use_best_found(ac, e4b);
 	}
 	ext4_unlock_group(ac->ac_sb, group);
-	ext4_mb_release_desc(e4b);
+	ext4_mb_unload_buddy(e4b);
 
 	return 0;
 }
···
 	}
 }
 
+/* This is now called BEFORE we load the buddy bitmap. */
 static int ext4_mb_good_group(struct ext4_allocation_context *ac,
 				ext4_group_t group, int cr)
 {
 	unsigned free, fragments;
-	unsigned i, bits;
 	int flex_size = ext4_flex_bg_size(EXT4_SB(ac->ac_sb));
 	struct ext4_group_info *grp = ext4_get_group_info(ac->ac_sb, group);
 
 	BUG_ON(cr < 0 || cr >= 4);
-	BUG_ON(EXT4_MB_GRP_NEED_INIT(grp));
+
+	/* We only do this if the grp has never been initialized */
+	if (unlikely(EXT4_MB_GRP_NEED_INIT(grp))) {
+		int ret = ext4_mb_init_group(ac->ac_sb, group);
+		if (ret)
+			return 0;
+	}
 
 	free = grp->bb_free;
 	fragments = grp->bb_fragments;
···
 	case 0:
 		BUG_ON(ac->ac_2order == 0);
 
+		if (grp->bb_largest_free_order < ac->ac_2order)
+			return 0;
+
 		/* Avoid using the first bg of a flexgroup for data files */
 		if ((ac->ac_flags & EXT4_MB_HINT_DATA) &&
 		    (flex_size >= EXT4_FLEX_SIZE_DIR_ALLOC_SCHEME) &&
 		    ((group % flex_size) == 0))
 			return 0;
 
-		bits = ac->ac_sb->s_blocksize_bits + 1;
-		for (i = ac->ac_2order; i <= bits; i++)
-			if (grp->bb_counters[i] > 0)
-				return 1;
-		break;
+		return 1;
 	case 1:
 		if ((free / fragments) >= ac->ac_g_ex.fe_len)
 			return 1;
···
 	sbi = EXT4_SB(sb);
 	ngroups = ext4_get_groups_count(sb);
 	/* non-extent files are limited to low blocks/groups */
-	if (!(EXT4_I(ac->ac_inode)->i_flags & EXT4_EXTENTS_FL))
+	if (!(ext4_test_inode_flag(ac->ac_inode, EXT4_INODE_EXTENTS)))
 		ngroups = sbi->s_blockfile_groups;
 
 	BUG_ON(ac->ac_status == AC_STATUS_FOUND);
···
 		group = ac->ac_g_ex.fe_group;
 
 		for (i = 0; i < ngroups; group++, i++) {
-			struct ext4_group_info *grp;
-			struct ext4_group_desc *desc;
-
 			if (group == ngroups)
 				group = 0;
 
-			/* quick check to skip empty groups */
-			grp = ext4_get_group_info(sb, group);
-			if (grp->bb_free == 0)
+			/* This now checks without needing the buddy page */
+			if (!ext4_mb_good_group(ac, group, cr))
 				continue;
 
 			err = ext4_mb_load_buddy(sb, group, &e4b);
···
 				goto out;
 
 			ext4_lock_group(sb, group);
+
+			/*
+			 * We need to check again after locking the
+			 * block group
+			 */
 			if (!ext4_mb_good_group(ac, group, cr)) {
-				/* someone did allocation from this group */
 				ext4_unlock_group(sb, group);
-				ext4_mb_release_desc(&e4b);
+				ext4_mb_unload_buddy(&e4b);
 				continue;
 			}
 
 			ac->ac_groups_scanned++;
-			desc = ext4_get_group_desc(sb, group, NULL);
 			if (cr == 0)
 				ext4_mb_simple_scan_group(ac, &e4b);
 			else if (cr == 1 &&
···
 				ext4_mb_complex_scan_group(ac, &e4b);
 
 			ext4_unlock_group(sb, group);
-			ext4_mb_release_desc(&e4b);
+			ext4_mb_unload_buddy(&e4b);
 
 			if (ac->ac_status != AC_STATUS_CONTINUE)
 				break;
···
 	ext4_lock_group(sb, group);
 	memcpy(&sg, ext4_get_group_info(sb, group), i);
 	ext4_unlock_group(sb, group);
-	ext4_mb_release_desc(&e4b);
+	ext4_mb_unload_buddy(&e4b);
 
 	seq_printf(seq, "#%-5u: %-5u %-5u %-5u [", group, sg.info.bb_free,
 			sg.info.bb_fragments, sg.info.bb_first_free);
···
 	INIT_LIST_HEAD(&meta_group_info[i]->bb_prealloc_list);
 	init_rwsem(&meta_group_info[i]->alloc_sem);
 	meta_group_info[i]->bb_free_root = RB_ROOT;
+	meta_group_info[i]->bb_largest_free_order = -1;  /* uninit */
 
 #ifdef DOUBLE_CHECK
 	{
···
 			 entry->count, entry->group, entry);
 
 		if (test_opt(sb, DISCARD)) {
+			int ret;
 			ext4_fsblk_t discard_block;
 
 			discard_block = entry->start_blk +
···
 			trace_ext4_discard_blocks(sb,
 					(unsigned long long)discard_block,
 					entry->count);
-			sb_issue_discard(sb, discard_block, entry->count);
+			ret = sb_issue_discard(sb, discard_block, entry->count);
+			if (ret == EOPNOTSUPP) {
+				ext4_warning(sb,
+					"discard not supported, disabling");
+				clear_opt(EXT4_SB(sb)->s_mount_opt, DISCARD);
+			}
 		}
 
 		err = ext4_mb_load_buddy(sb, entry->group, &e4b);
···
 		}
 		ext4_unlock_group(sb, entry->group);
 		kmem_cache_free(ext4_free_ext_cachep, entry);
-		ext4_mb_release_desc(&e4b);
+		ext4_mb_unload_buddy(&e4b);
 	}
 
 	mb_debug(1, "freed %u blocks in %u structures\n", count, count2);
···
 
 void exit_ext4_mballoc(void)
 {
-	/* 
+	/*
 	 * Wait for completion of call_rcu()'s on ext4_pspace_cachep
 	 * before destroying the slab cache.
 	 */
···
 	if (sbi->s_mb_stats && ac->ac_g_ex.fe_len > 1) {
 		atomic_inc(&sbi->s_bal_reqs);
 		atomic_add(ac->ac_b_ex.fe_len, &sbi->s_bal_allocated);
-		if (ac->ac_o_ex.fe_len >= ac->ac_g_ex.fe_len)
+		if (ac->ac_b_ex.fe_len >= ac->ac_o_ex.fe_len)
 			atomic_inc(&sbi->s_bal_success);
 		atomic_add(ac->ac_found, &sbi->s_bal_ex_scanned);
 		if (ac->ac_g_ex.fe_start == ac->ac_b_ex.fe_start &&
···
 			continue;
 
 		/* non-extent files can't have physical blocks past 2^32 */
-		if (!(EXT4_I(ac->ac_inode)->i_flags & EXT4_EXTENTS_FL) &&
+		if (!(ext4_test_inode_flag(ac->ac_inode, EXT4_INODE_EXTENTS)) &&
 			pa->pa_pstart + pa->pa_len > EXT4_MAX_BLOCK_FILE_PHYS)
 			continue;
 
···
 	spin_unlock(&pa->pa_lock);
 
 	grp_blk = pa->pa_pstart;
-	/* 
+	/*
 	 * If doing group-based preallocation, pa_pstart may be in the
 	 * next group when pa is used up
 	 */
···
 	ext4_unlock_group(sb, group);
 	if (ac)
 		kmem_cache_free(ext4_ac_cachep, ac);
-	ext4_mb_release_desc(&e4b);
+	ext4_mb_unload_buddy(&e4b);
 	put_bh(bitmap_bh);
 	return free;
 }
···
 		if (bitmap_bh == NULL) {
 			ext4_error(sb, "Error reading block bitmap for %u",
 					group);
-			ext4_mb_release_desc(&e4b);
+			ext4_mb_unload_buddy(&e4b);
 			continue;
 		}
 
···
 		ext4_mb_release_inode_pa(&e4b, bitmap_bh, pa, ac);
 		ext4_unlock_group(sb, group);
 
-		ext4_mb_release_desc(&e4b);
+		ext4_mb_unload_buddy(&e4b);
 		put_bh(bitmap_bh);
 
 		list_del(&pa->u.pa_tmp_list);
···
 		ext4_mb_release_group_pa(&e4b, pa, ac);
 		ext4_unlock_group(sb, group);
 
-		ext4_mb_release_desc(&e4b);
+		ext4_mb_unload_buddy(&e4b);
 		list_del(&pa->u.pa_tmp_list);
 		call_rcu(&(pa)->u.pa_rcu, ext4_mb_pa_callback);
 	}
···
 			if (!bh)
 				tbh = sb_find_get_block(inode->i_sb,
 							block + i);
-			ext4_forget(handle, flags & EXT4_FREE_BLOCKS_METADATA, 
+			ext4_forget(handle, flags & EXT4_FREE_BLOCKS_METADATA,
 				    inode, tbh, block + i);
 		}
 	}
 
-	/* 
+	/*
 	 * We need to make sure we don't reuse the freed block until
 	 * after the transaction is committed, which we can do by
 	 * treating the block as metadata, below.  We make an
···
 		atomic_add(count, &sbi->s_flex_groups[flex_group].free_blocks);
 	}
 
-	ext4_mb_release_desc(&e4b);
+	ext4_mb_unload_buddy(&e4b);
 
 	freed += count;
 

fs/ext4/migrate.c

···
 	 */
 	if (!EXT4_HAS_INCOMPAT_FEATURE(inode->i_sb,
 				       EXT4_FEATURE_INCOMPAT_EXTENTS) ||
-	    (EXT4_I(inode)->i_flags & EXT4_EXTENTS_FL))
+	    (ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS)))
 		return -EINVAL;
 
 	if (S_ISLNK(inode->i_mode) && inode->i_blocks == 0)

fs/ext4/move_extent.c

···
 	int depth = ext_depth(orig_inode);
 	int ret;
 
+	start_ext.ee_block = end_ext.ee_block = 0;
 	o_start = o_end = oext = orig_path[depth].p_ext;
 	oext_alen = ext4_ext_get_actual_len(oext);
 	start_ext.ee_len = end_ext.ee_len = 0;
···
 	 * new_ext       |-------|
 	 */
 	if (le32_to_cpu(oext->ee_block) + oext_alen - 1 < new_ext_end) {
-		ext4_error(orig_inode->i_sb,
+		EXT4_ERROR_INODE(orig_inode,
 			"new_ext_end(%u) should be less than or equal to "
 			"oext->ee_block(%u) + oext_alen(%d) - 1",
 			new_ext_end, le32_to_cpu(oext->ee_block),
···
 	while (1) {
 		/* The extent for donor must be found. */
 		if (!dext) {
-			ext4_error(donor_inode->i_sb,
+			EXT4_ERROR_INODE(donor_inode,
 				   "The extent for donor must be found");
 			*err = -EIO;
 			goto out;
 		} else if (donor_off != le32_to_cpu(tmp_dext.ee_block)) {
-			ext4_error(donor_inode->i_sb,
+			EXT4_ERROR_INODE(donor_inode,
 				"Donor offset(%u) and the first block of donor "
 				"extent(%u) should be equal",
 				donor_off,
···
 	}
 
 	/* Ext4 move extent supports only extent based file */
-	if (!(EXT4_I(orig_inode)->i_flags & EXT4_EXTENTS_FL)) {
+	if (!(ext4_test_inode_flag(orig_inode, EXT4_INODE_EXTENTS))) {
 		ext4_debug("ext4 move extent: orig file is not extents "
 			"based file [ino:orig %lu]\n", orig_inode->i_ino);
 		return -EOPNOTSUPP;
-	} else if (!(EXT4_I(donor_inode)->i_flags & EXT4_EXTENTS_FL)) {
+	} else if (!(ext4_test_inode_flag(donor_inode, EXT4_INODE_EXTENTS))) {
 		ext4_debug("ext4 move extent: donor file is not extents "
 			"based file [ino:donor %lu]\n", donor_inode->i_ino);
 		return -EOPNOTSUPP;
···
 			if (ret1 < 0)
 				break;
 			if (*moved_len > len) {
-				ext4_error(orig_inode->i_sb,
+				EXT4_ERROR_INODE(orig_inode,
 					"We replaced blocks too much! "
 					"sum of replaced: %llu requested: %llu",
 					*moved_len, len);

fs/ext4/namei.c

···
 		return blocksize;
 	return (len & 65532) | ((len & 3) << 16);
 }
-  
+
 __le16 ext4_rec_len_to_disk(unsigned len, unsigned blocksize)
 {
 	if ((len > blocksize) || (blocksize > (1 << 18)) || (len & 3))
···
 	if (len == blocksize) {
 		if (blocksize == 65536)
 			return cpu_to_le16(EXT4_MAX_REC_LEN);
-		else 
+		else
 			return cpu_to_le16(0);
 	}
 	return cpu_to_le16((len & 65532) | ((len >> 16) & 3));
···
 		brelse(bh);
 	}
 	if (bcount)
-		printk(KERN_DEBUG "%snames %u, fullness %u (%u%%)\n", 
+		printk(KERN_DEBUG "%snames %u, fullness %u (%u%%)\n",
 		       levels ? "" : "   ", names, space/bcount,
 		       (space/bcount)*100/blocksize);
 	return (struct stats) { names, space, bcount};
···
 	int ret, err;
 	__u32 hashval;
 
-	dxtrace(printk(KERN_DEBUG "In htree_fill_tree, start hash: %x:%x\n", 
+	dxtrace(printk(KERN_DEBUG "In htree_fill_tree, start hash: %x:%x\n",
 		       start_hash, start_minor_hash));
 	dir = dir_file->f_path.dentry->d_inode;
-	if (!(EXT4_I(dir)->i_flags & EXT4_INDEX_FL)) {
+	if (!(ext4_test_inode_flag(dir, EXT4_INODE_INDEX))) {
 		hinfo.hash_version = EXT4_SB(dir->i_sb)->s_def_hash_version;
 		if (hinfo.hash_version <= DX_HASH_TEA)
 			hinfo.hash_version +=
···
 {
 	if (!EXT4_HAS_COMPAT_FEATURE(inode->i_sb,
 				     EXT4_FEATURE_COMPAT_DIR_INDEX))
-		EXT4_I(inode)->i_flags &= ~EXT4_INDEX_FL;
+		ext4_clear_inode_flag(inode, EXT4_INODE_INDEX);
 }
 
 /*
···
 		wait_on_buffer(bh);
 		if (!buffer_uptodate(bh)) {
 			/* read error, skip block & hope for the best */
-			ext4_error(sb, "reading directory #%lu offset %lu",
-				   dir->i_ino, (unsigned long)block);
+			EXT4_ERROR_INODE(dir, "reading directory lblock %lu",
+					 (unsigned long) block);
 			brelse(bh);
 			goto next;
 		}
···
 		__u32 ino = le32_to_cpu(de->inode);
 		brelse(bh);
 		if (!ext4_valid_inum(dir->i_sb, ino)) {
-			ext4_error(dir->i_sb, "bad inode number: %u", ino);
+			EXT4_ERROR_INODE(dir, "bad inode number: %u", ino);
 			return ERR_PTR(-EIO);
 		}
 		inode = ext4_iget(dir->i_sb, ino);
 		if (unlikely(IS_ERR(inode))) {
 			if (PTR_ERR(inode) == -ESTALE) {
-				ext4_error(dir->i_sb,
-						"deleted inode referenced: %u",
-						ino);
+				EXT4_ERROR_INODE(dir,
+						 "deleted inode referenced: %u",
+						 ino);
 				return ERR_PTR(-EIO);
 			} else {
 				return ERR_CAST(inode);
···
 	brelse(bh);
 
 	if (!ext4_valid_inum(child->d_inode->i_sb, ino)) {
-		ext4_error(child->d_inode->i_sb,
-			   "bad inode number: %u", ino);
+		EXT4_ERROR_INODE(child->d_inode,
+				 "bad parent inode number: %u", ino);
 		return ERR_PTR(-EIO);
 	}
 
···
 	unsigned rec_len = 0;
 
 	while (count--) {
-		struct ext4_dir_entry_2 *de = (struct ext4_dir_entry_2 *) 
+		struct ext4_dir_entry_2 *de = (struct ext4_dir_entry_2 *)
 						(from + (map->offs<<2));
 		rec_len = EXT4_DIR_REC_LEN(de->name_len);
 		memcpy (to, de, rec_len);
···
 	de = (struct ext4_dir_entry_2 *)((char *)fde +
 		ext4_rec_len_from_disk(fde->rec_len, blocksize));
 	if ((char *) de >= (((char *) root) + blocksize)) {
-		ext4_error(dir->i_sb,
-			   "invalid rec_len for '..' in inode %lu",
-			   dir->i_ino);
+		EXT4_ERROR_INODE(dir, "invalid rec_len for '..'");
 		brelse(bh);
 		return -EIO;
 	}
···
 		brelse(bh);
 		return retval;
 	}
-	EXT4_I(dir)->i_flags |= EXT4_INDEX_FL;
+	ext4_set_inode_flag(dir, EXT4_INODE_INDEX);
 	data1 = bh2->b_data;
 
 	memcpy (data1, de, len);
···
 		retval = ext4_dx_add_entry(handle, dentry, inode);
 		if (!retval || (retval != ERR_BAD_DX_DIR))
 			return retval;
-		EXT4_I(dir)->i_flags &= ~EXT4_INDEX_FL;
+		ext4_clear_inode_flag(dir, EXT4_INODE_INDEX);
 		dx_fallback++;
 		ext4_mark_inode_dirty(handle, dir);
 	}
···
 	de->rec_len = ext4_rec_len_to_disk(blocksize, blocksize);
 	retval = add_dirent_to_buf(handle, dentry, inode, de, bh);
 	brelse(bh);
+	if (retval == 0)
+		ext4_set_inode_state(inode, EXT4_STATE_NEWENTRY);
 	return retval;
 }
 
···
 	if (inode->i_size < EXT4_DIR_REC_LEN(1) + EXT4_DIR_REC_LEN(2) ||
 	    !(bh = ext4_bread(NULL, inode, 0, 0, &err))) {
 		if (err)
-			ext4_error(inode->i_sb,
-				   "error %d reading directory #%lu offset 0",
-				   err, inode->i_ino);
+			EXT4_ERROR_INODE(inode,
+				"error %d reading directory lblock 0", err);
 		else
 			ext4_warning(inode->i_sb,
 				     "bad directory (dir #%lu) - no data block",
···
 	de = ext4_next_entry(de1, sb->s_blocksize);
 	while (offset < inode->i_size) {
 		if (!bh ||
-			(void *) de >= (void *) (bh->b_data+sb->s_blocksize)) {
+		    (void *) de >= (void *) (bh->b_data+sb->s_blocksize)) {
+			unsigned int lblock;
 			err = 0;
 			brelse(bh);
-			bh = ext4_bread(NULL, inode,
-				offset >> EXT4_BLOCK_SIZE_BITS(sb), 0, &err);
+			lblock = offset >> EXT4_BLOCK_SIZE_BITS(sb);
+			bh = ext4_bread(NULL, inode, lblock, 0, &err);
 			if (!bh) {
 				if (err)
-					ext4_error(sb,
-						   "error %d reading directory"
-						   " #%lu offset %u",
-						   err, inode->i_ino, offset);
+					EXT4_ERROR_INODE(inode,
+						"error %d reading directory "
+						"lblock %u", err, lblock);
 				offset += sb->s_blocksize;
 				continue;
 			}
···
 		}
 	} else {
 		/* clear the extent format for fast symlink */
-		EXT4_I(inode)->i_flags &= ~EXT4_EXTENTS_FL;
+		ext4_clear_inode_flag(inode, EXT4_INODE_EXTENTS);
 		inode->i_op = &ext4_fast_symlink_inode_operations;
 		memcpy((char *)&EXT4_I(inode)->i_data, symname, l);
 		inode->i_size = l-1;

fs/ext4/resize.c

···
 	percpu_counter_add(&sbi->s_freeinodes_counter,
 			   EXT4_INODES_PER_GROUP(sb));
 
-	if (EXT4_HAS_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_FLEX_BG)) {
+	if (EXT4_HAS_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_FLEX_BG) &&
+	    sbi->s_log_groups_per_flex) {
 		ext4_group_t flex_group;
 		flex_group = ext4_flex_group(sbi, input->group);
 		atomic_add(input->free_blocks_count,

fs/ext4/super.c

···
 	if (sb->s_flags & MS_RDONLY)
 		return ERR_PTR(-EROFS);
 
+	vfs_check_frozen(sb, SB_FREEZE_WRITE);
 	/* Special case here: if the journal has aborted behind our
 	 * backs (eg. EIO in the commit thread), then we still need to
 	 * take the FS itself readonly cleanly. */
···
 	seq_puts(seq, test_opt(sb, BARRIER) ? "1" : "0");
 	if (test_opt(sb, JOURNAL_ASYNC_COMMIT))
 		seq_puts(seq, ",journal_async_commit");
+	else if (test_opt(sb, JOURNAL_CHECKSUM))
+		seq_puts(seq, ",journal_checksum");
 	if (test_opt(sb, NOBH))
 		seq_puts(seq, ",nobh");
 	if (test_opt(sb, I_VERSION))
···
 struct ext4_attr {
 	struct attribute attr;
 	ssize_t (*show)(struct ext4_attr *, struct ext4_sb_info *, char *);
-	ssize_t (*store)(struct ext4_attr *, struct ext4_sb_info *, 
+	ssize_t (*store)(struct ext4_attr *, struct ext4_sb_info *,
 			 const char *, size_t);
 	int offset;
 };
···
 				__releases(kernel_lock)
 				__acquires(kernel_lock)
 {
+	char *orig_data = kstrdup(data, GFP_KERNEL);
 	struct buffer_head *bh;
 	struct ext4_super_block *es = NULL;
 	struct ext4_sb_info *sbi;
···
 	get_random_bytes(&sbi->s_next_generation, sizeof(u32));
 	spin_lock_init(&sbi->s_next_gen_lock);
 
-	err = percpu_counter_init(&sbi->s_freeblocks_counter,
-			ext4_count_free_blocks(sb));
-	if (!err) {
-		err = percpu_counter_init(&sbi->s_freeinodes_counter,
-				ext4_count_free_inodes(sb));
-	}
-	if (!err) {
-		err = percpu_counter_init(&sbi->s_dirs_counter,
-				ext4_count_dirs(sb));
-	}
-	if (!err) {
-		err = percpu_counter_init(&sbi->s_dirtyblocks_counter, 0);
-	}
-	if (err) {
-		ext4_msg(sb, KERN_ERR, "insufficient memory");
-		goto failed_mount3;
-	}
-
 	sbi->s_stripe = ext4_get_stripe_size(sbi);
 	sbi->s_max_writeback_mb_bump = 128;
 
···
 	set_task_ioprio(sbi->s_journal->j_task, journal_ioprio);
 
 no_journal:
+	err = percpu_counter_init(&sbi->s_freeblocks_counter,
+				  ext4_count_free_blocks(sb));
+	if (!err)
+		err = percpu_counter_init(&sbi->s_freeinodes_counter,
+					  ext4_count_free_inodes(sb));
+	if (!err)
+		err = percpu_counter_init(&sbi->s_dirs_counter,
+					  ext4_count_dirs(sb));
+	if (!err)
+		err = percpu_counter_init(&sbi->s_dirtyblocks_counter, 0);
+	if (err) {
+		ext4_msg(sb, KERN_ERR, "insufficient memory");
+		goto failed_mount_wq;
+	}
 	if (test_opt(sb, NOBH)) {
 		if (!(test_opt(sb, DATA_FLAGS) == EXT4_MOUNT_WRITEBACK_DATA)) {
 			ext4_msg(sb, KERN_WARNING, "Ignoring nobh option - "
···
 	err = ext4_setup_system_zone(sb);
 	if (err) {
 		ext4_msg(sb, KERN_ERR, "failed to initialize system "
-			 "zone (%d)\n", err);
+			 "zone (%d)", err);
 		goto failed_mount4;
 	}
 
···
 	} else
 		descr = "out journal";
 
-	ext4_msg(sb, KERN_INFO, "mounted filesystem with%s", descr);
+	ext4_msg(sb, KERN_INFO, "mounted filesystem with%s. "
+		"Opts: %s", descr, orig_data);
 
 	lock_kernel();
+	kfree(orig_data);
 	return 0;
 
 cantfind_ext4:
···
 		jbd2_journal_destroy(sbi->s_journal);
 		sbi->s_journal = NULL;
 	}
+	percpu_counter_destroy(&sbi->s_freeblocks_counter);
+	percpu_counter_destroy(&sbi->s_freeinodes_counter);
+	percpu_counter_destroy(&sbi->s_dirs_counter);
+	percpu_counter_destroy(&sbi->s_dirtyblocks_counter);
 failed_mount3:
 	if (sbi->s_flex_groups) {
 		if (is_vmalloc_addr(sbi->s_flex_groups))
···
 		else
 			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);
-	percpu_counter_destroy(&sbi->s_dirtyblocks_counter);
 failed_mount2:
 	for (i = 0; i < db_count; i++)
 		brelse(sbi->s_group_desc[i]);
···
 	kfree(sbi->s_blockgroup_lock);
 	kfree(sbi);
 	lock_kernel();
+	kfree(orig_data);
 	return ret;
 }
 
···
 	if (!(sb->s_flags & MS_RDONLY))
 		es->s_wtime = cpu_to_le32(get_seconds());
 	es->s_kbytes_written =
-		cpu_to_le64(EXT4_SB(sb)->s_kbytes_written + 
+		cpu_to_le64(EXT4_SB(sb)->s_kbytes_written +
 			    ((part_stat_read(sb->s_bdev->bd_part, sectors[1]) -
 			      EXT4_SB(sb)->s_sectors_written_start) >> 1));
 	ext4_free_blocks_count_set(es, percpu_counter_sum_positive(
···
 		return 0;
 
 	journal = EXT4_SB(sb)->s_journal;
-	if (journal)
+	if (journal) {
+		vfs_check_frozen(sb, SB_FREEZE_WRITE);
 		ret = ext4_journal_force_commit(journal);
+	}
 
 	return ret;
 }
···
 	 * the journal.
 	 */
 	error = jbd2_journal_flush(journal);
-	if (error < 0) {
-	out:
-		jbd2_journal_unlock_updates(journal);
-		return error;
-	}
+	if (error < 0)
+		goto out;
 
 	/* Journal blocked and flushed, clear needs_recovery flag. */
 	EXT4_CLEAR_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_RECOVER);
 	error = ext4_commit_super(sb, 1);
-	if (error)
-		goto out;
-	return 0;
+out:
+	/* we rely on s_frozen to stop further updates */
+	jbd2_journal_unlock_updates(EXT4_SB(sb)->s_journal);
+	return error;
 }
 
 /*
···
 	EXT4_SET_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_RECOVER);
 	ext4_commit_super(sb, 1);
 	unlock_super(sb);
-	jbd2_journal_unlock_updates(EXT4_SB(sb)->s_journal);
 	return 0;
 }
 
···
 #ifdef CONFIG_QUOTA
 	int i;
 #endif
+	char *orig_data = kstrdup(data, GFP_KERNEL);
 
 	lock_kernel();
 
···
 #endif
 	unlock_super(sb);
 	unlock_kernel();
+
+	ext4_msg(sb, KERN_INFO, "re-mounted. Opts: %s", orig_data);
+	kfree(orig_data);
 	return 0;
 
 restore_opts:
···
 #endif
 	unlock_super(sb);
 	unlock_kernel();
+	kfree(orig_data);
 	return err;
 }
 
···
 {
 	int err;
 
+	ext4_check_flag_values();
 	err = init_ext4_system_zone();
 	if (err)
 		return err;

fs/ext4/symlink.c

···
 	.readlink	= generic_readlink,
 	.follow_link	= page_follow_link_light,
 	.put_link	= page_put_link,
+	.setattr	= ext4_setattr,
 #ifdef CONFIG_EXT4_FS_XATTR
 	.setxattr	= generic_setxattr,
 	.getxattr	= generic_getxattr,
···
 const struct inode_operations ext4_fast_symlink_inode_operations = {
 	.readlink	= generic_readlink,
 	.follow_link	= ext4_follow_link,
+	.setattr	= ext4_setattr,
 #ifdef CONFIG_EXT4_FS_XATTR
 	.setxattr	= generic_setxattr,
 	.getxattr	= generic_getxattr,

fs/ext4/xattr.c

···
 		atomic_read(&(bh->b_count)), le32_to_cpu(BHDR(bh)->h_refcount));
 	if (ext4_xattr_check_block(bh)) {
 bad_block:
-		ext4_error(inode->i_sb,
-			   "inode %lu: bad block %llu", inode->i_ino,
-			   EXT4_I(inode)->i_file_acl);
+		EXT4_ERROR_INODE(inode, "bad block %llu",
+				 EXT4_I(inode)->i_file_acl);
 		error = -EIO;
 		goto cleanup;
 	}
···
 	ea_bdebug(bh, "b_count=%d, refcount=%d",
 		atomic_read(&(bh->b_count)), le32_to_cpu(BHDR(bh)->h_refcount));
 	if (ext4_xattr_check_block(bh)) {
-		ext4_error(inode->i_sb,
-			   "inode %lu: bad block %llu", inode->i_ino,
-			   EXT4_I(inode)->i_file_acl);
+		EXT4_ERROR_INODE(inode, "bad block %llu",
+				 EXT4_I(inode)->i_file_acl);
 		error = -EIO;
 		goto cleanup;
 	}
···
 			atomic_read(&(bs->bh->b_count)),
 			le32_to_cpu(BHDR(bs->bh)->h_refcount));
 		if (ext4_xattr_check_block(bs->bh)) {
-			ext4_error(sb, "inode %lu: bad block %llu",
-				   inode->i_ino, EXT4_I(inode)->i_file_acl);
+			EXT4_ERROR_INODE(inode, "bad block %llu",
+					 EXT4_I(inode)->i_file_acl);
 			error = -EIO;
 			goto cleanup;
 		}
···
 						EXT4_I(inode)->i_block_group);
 
 			/* non-extent files can't have physical blocks past 2^32 */
-			if (!(EXT4_I(inode)->i_flags & EXT4_EXTENTS_FL))
+			if (!(ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS)))
 				goal = goal & EXT4_MAX_BLOCK_FILE_PHYS;
 
 			block = ext4_new_meta_blocks(handle, inode,
···
 			if (error)
 				goto cleanup;
 
-			if (!(EXT4_I(inode)->i_flags & EXT4_EXTENTS_FL))
+			if (!(ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS)))
 				BUG_ON(block > EXT4_MAX_BLOCK_FILE_PHYS);
 
 			ea_idebug(inode, "creating block %d", block);
···
 	goto cleanup;
 
 bad_block:
-	ext4_error(inode->i_sb, "inode %lu: bad block %llu",
-		   inode->i_ino, EXT4_I(inode)->i_file_acl);
+	EXT4_ERROR_INODE(inode, "bad block %llu",
+			 EXT4_I(inode)->i_file_acl);
 	goto cleanup;
 
 #undef header
···
 		if (!bh)
 			goto cleanup;
 		if (ext4_xattr_check_block(bh)) {
-			ext4_error(inode->i_sb, "inode %lu: bad block %llu",
-				   inode->i_ino, EXT4_I(inode)->i_file_acl);
+			EXT4_ERROR_INODE(inode, "bad block %llu",
+					 EXT4_I(inode)->i_file_acl);
 			error = -EIO;
 			goto cleanup;
 		}
···
 		goto cleanup;
 	bh = sb_bread(inode->i_sb, EXT4_I(inode)->i_file_acl);
 	if (!bh) {
-		ext4_error(inode->i_sb, "inode %lu: block %llu read error",
-			   inode->i_ino, EXT4_I(inode)->i_file_acl);
+		EXT4_ERROR_INODE(inode, "block %llu read error",
+				 EXT4_I(inode)->i_file_acl);
 		goto cleanup;
 	}
 	if (BHDR(bh)->h_magic != cpu_to_le32(EXT4_XATTR_MAGIC) ||
 	    BHDR(bh)->h_blocks != cpu_to_le32(1)) {
-		ext4_error(inode->i_sb, "inode %lu: bad block %llu",
-			   inode->i_ino, EXT4_I(inode)->i_file_acl);
+		EXT4_ERROR_INODE(inode, "bad block %llu",
+				 EXT4_I(inode)->i_file_acl);
 		goto cleanup;
 	}
 	ext4_xattr_release_block(handle, inode, bh);
···
 		}
 		bh = sb_bread(inode->i_sb, ce->e_block);
 		if (!bh) {
-			ext4_error(inode->i_sb,
-				"inode %lu: block %lu read error",
-				inode->i_ino, (unsigned long) ce->e_block);
+			EXT4_ERROR_INODE(inode, "block %lu read error",
+					 (unsigned long) ce->e_block);
 		} else if (le32_to_cpu(BHDR(bh)->h_refcount) >=
 				EXT4_XATTR_REFCOUNT_MAX) {
 			ea_idebug(inode, "block %lu refcount %d>=%d",

fs/jbd2/transaction.c

···
 	if (handle->h_sync)
 		transaction->t_synchronous_commit = 1;
 	current->journal_info = NULL;
-	spin_lock(&journal->j_state_lock);
 	spin_lock(&transaction->t_handle_lock);
 	transaction->t_outstanding_credits -= handle->h_buffer_credits;
 	transaction->t_updates--;
···
 		jbd_debug(2, "transaction too old, requesting commit for "
 					"handle %p\n", handle);
 		/* This is non-blocking */
-		__jbd2_log_start_commit(journal, transaction->t_tid);
-		spin_unlock(&journal->j_state_lock);
+		jbd2_log_start_commit(journal, transaction->t_tid);
 
 		/*
 		 * Special case: JBD2_SYNC synchronous updates require us
···
 			err = jbd2_log_wait_commit(journal, tid);
 	} else {
 		spin_unlock(&transaction->t_handle_lock);
-		spin_unlock(&journal->j_state_lock);
 	}
 
 	lock_map_release(&handle->h_lockdep_map);

fs/quota/dquot.c

···
 /*
  * This operation can block, but only after everything is updated
  */
-int __dquot_alloc_space(struct inode *inode, qsize_t number,
-		int warn, int reserve)
+int __dquot_alloc_space(struct inode *inode, qsize_t number, int flags)
 {
 	int cnt, ret = 0;
 	char warntype[MAXQUOTAS];
+	int warn = flags & DQUOT_SPACE_WARN;
+	int reserve = flags & DQUOT_SPACE_RESERVE;
+	int nofail = flags & DQUOT_SPACE_NOFAIL;
 
 	/*
 	 * First test before acquiring mutex - solves deadlocks when we
···
 			continue;
 		ret = check_bdq(inode->i_dquot[cnt], number, !warn,
 				warntype+cnt);
-		if (ret) {
+		if (ret && !nofail) {
 			spin_unlock(&dq_data_lock);
 			goto out_flush_warn;
 		}
···
 /*
  * This operation can block, but only after everything is updated
  */
-void __dquot_free_space(struct inode *inode, qsize_t number, int reserve)
+void __dquot_free_space(struct inode *inode, qsize_t number, int flags)
 {
 	unsigned int cnt;
 	char warntype[MAXQUOTAS];
+	int reserve = flags & DQUOT_SPACE_RESERVE;
 
 	/* First test before acquiring mutex - solves deadlocks when we
          * re-enter the quota code and are already holding the mutex */

include/linux/quotaops.h

···
 
 #include <linux/fs.h>
 
+#define DQUOT_SPACE_WARN	0x1
+#define DQUOT_SPACE_RESERVE	0x2
+#define DQUOT_SPACE_NOFAIL	0x4
+
 static inline struct quota_info *sb_dqopt(struct super_block *sb)
 {
 	return &sb->s_dquot;
···
 struct dquot *dquot_alloc(struct super_block *sb, int type);
 void dquot_destroy(struct dquot *dquot);
 
-int __dquot_alloc_space(struct inode *inode, qsize_t number,
-		int warn, int reserve);
-void __dquot_free_space(struct inode *inode, qsize_t number, int reserve);
+int __dquot_alloc_space(struct inode *inode, qsize_t number, int flags);
+void __dquot_free_space(struct inode *inode, qsize_t number, int flags);
 
 int dquot_alloc_inode(const struct inode *inode);
 
···
 }
 
 static inline int __dquot_alloc_space(struct inode *inode, qsize_t number,
-		int warn, int reserve)
+		int flags)
 {
-	if (!reserve)
+	if (!(flags & DQUOT_SPACE_RESERVE))
 		inode_add_bytes(inode, number);
 	return 0;
 }
 
 static inline void __dquot_free_space(struct inode *inode, qsize_t number,
-		int reserve)
+		int flags)
 {
-	if (!reserve)
+	if (!(flags & DQUOT_SPACE_RESERVE))
 		inode_sub_bytes(inode, number);
 }
 
···
 
 static inline int dquot_alloc_space_nodirty(struct inode *inode, qsize_t nr)
 {
-	return __dquot_alloc_space(inode, nr, 1, 0);
+	return __dquot_alloc_space(inode, nr, DQUOT_SPACE_WARN);
+}
+
+static inline void dquot_alloc_space_nofail(struct inode *inode, qsize_t nr)
+{
+	__dquot_alloc_space(inode, nr, DQUOT_SPACE_WARN|DQUOT_SPACE_NOFAIL);
+	mark_inode_dirty(inode);
 }
 
 static inline int dquot_alloc_space(struct inode *inode, qsize_t nr)
···
 	return dquot_alloc_space_nodirty(inode, nr << inode->i_blkbits);
 }
 
+static inline void dquot_alloc_block_nofail(struct inode *inode, qsize_t nr)
+{
+	dquot_alloc_space_nofail(inode, nr << inode->i_blkbits);
+}
+
 static inline int dquot_alloc_block(struct inode *inode, qsize_t nr)
 {
 	return dquot_alloc_space(inode, nr << inode->i_blkbits);
···
 
 static inline int dquot_prealloc_block_nodirty(struct inode *inode, qsize_t nr)
 {
-	return __dquot_alloc_space(inode, nr << inode->i_blkbits, 0, 0);
+	return __dquot_alloc_space(inode, nr << inode->i_blkbits, 0);
 }
 
 static inline int dquot_prealloc_block(struct inode *inode, qsize_t nr)
···
 
 static inline int dquot_reserve_block(struct inode *inode, qsize_t nr)
 {
-	return __dquot_alloc_space(inode, nr << inode->i_blkbits, 1, 1);
+	return __dquot_alloc_space(inode, nr << inode->i_blkbits,
+				DQUOT_SPACE_WARN|DQUOT_SPACE_RESERVE);
 }
 
 static inline int dquot_claim_block(struct inode *inode, qsize_t nr)
···
 static inline void dquot_release_reservation_block(struct inode *inode,
 		qsize_t nr)
 {
-	__dquot_free_space(inode, nr << inode->i_blkbits, 1);
+	__dquot_free_space(inode, nr << inode->i_blkbits, DQUOT_SPACE_RESERVE);
 }
 
 #endif /* _LINUX_QUOTAOPS_ */

include/trace/events/ext4.h

···
 		  jbd2_dev_to_name(__entry->dev), __entry->blk, __entry->count)
 );
 
-TRACE_EVENT(ext4_mb_new_inode_pa,
+DECLARE_EVENT_CLASS(ext4__mb_new_pa,
 	TP_PROTO(struct ext4_allocation_context *ac,
 		 struct ext4_prealloc_space *pa),
 
···
 		  __entry->pa_pstart, __entry->pa_len, __entry->pa_lstart)
 );
 
-TRACE_EVENT(ext4_mb_new_group_pa,
+DEFINE_EVENT(ext4__mb_new_pa, ext4_mb_new_inode_pa,
+
 	TP_PROTO(struct ext4_allocation_context *ac,
 		 struct ext4_prealloc_space *pa),
 
-	TP_ARGS(ac, pa),
+	TP_ARGS(ac, pa)
+);
 
-	TP_STRUCT__entry(
-		__field(	dev_t,	dev			)
-		__field(	ino_t,	ino			)
-		__field(	__u64,	pa_pstart		)
-		__field(	__u32,	pa_len			)
-		__field(	__u64,	pa_lstart		)
+DEFINE_EVENT(ext4__mb_new_pa, ext4_mb_new_group_pa,
 
-	),
+	TP_PROTO(struct ext4_allocation_context *ac,
+		 struct ext4_prealloc_space *pa),
 
-	TP_fast_assign(
-		__entry->dev		= ac->ac_sb->s_dev;
-		__entry->ino		= ac->ac_inode->i_ino;
-		__entry->pa_pstart	= pa->pa_pstart;
-		__entry->pa_len		= pa->pa_len;
-		__entry->pa_lstart	= pa->pa_lstart;
-	),
-
-	TP_printk("dev %s ino %lu pstart %llu len %u lstart %llu",
-		  jbd2_dev_to_name(__entry->dev), (unsigned long) __entry->ino,
-		  __entry->pa_pstart, __entry->pa_len, __entry->pa_lstart)
+	TP_ARGS(ac, pa)
 );
 
 TRACE_EVENT(ext4_mb_release_inode_pa,
···
 		  __entry->result_len, __entry->result_logical)
 );
 
-TRACE_EVENT(ext4_mballoc_discard,
+DECLARE_EVENT_CLASS(ext4__mballoc,
 	TP_PROTO(struct ext4_allocation_context *ac),
 
 	TP_ARGS(ac),
···
 		  __entry->result_len, __entry->result_logical)
 );
 
-TRACE_EVENT(ext4_mballoc_free,
+DEFINE_EVENT(ext4__mballoc, ext4_mballoc_discard,
+
 	TP_PROTO(struct ext4_allocation_context *ac),
 
-	TP_ARGS(ac),
+	TP_ARGS(ac)
+);
 
-	TP_STRUCT__entry(
-		__field(	dev_t,	dev			)
-		__field(	ino_t,	ino			)
-		__field(	__u32, 	result_logical		)
-		__field(	  int,	result_start		)
-		__field(	__u32, 	result_group		)
-		__field(	  int,	result_len		)
-	),
+DEFINE_EVENT(ext4__mballoc, ext4_mballoc_free,
 
-	TP_fast_assign(
-		__entry->dev		= ac->ac_inode->i_sb->s_dev;
-		__entry->ino		= ac->ac_inode->i_ino;
-		__entry->result_logical	= ac->ac_b_ex.fe_logical;
-		__entry->result_start	= ac->ac_b_ex.fe_start;
-		__entry->result_group	= ac->ac_b_ex.fe_group;
-		__entry->result_len	= ac->ac_b_ex.fe_len;
-	),
+	TP_PROTO(struct ext4_allocation_context *ac),
 
-	TP_printk("dev %s inode %lu extent %u/%d/%u@%u ",
-		  jbd2_dev_to_name(__entry->dev), (unsigned long) __entry->ino,
-		  __entry->result_group, __entry->result_start,
-		  __entry->result_len, __entry->result_logical)
+	TP_ARGS(ac)
 );
 
 TRACE_EVENT(ext4_forget,
···
 		  __entry->reserved_meta_blocks, __entry->allocated_meta_blocks)
 );
 
+DECLARE_EVENT_CLASS(ext4__bitmap_load,
+	TP_PROTO(struct super_block *sb, unsigned long group),
+
+	TP_ARGS(sb, group),
+
+	TP_STRUCT__entry(
+		__field(	dev_t,	dev			)
+		__field(	__u32,	group			)
+
+	),
+
+	TP_fast_assign(
+		__entry->dev	= sb->s_dev;
+		__entry->group	= group;
+	),
+
+	TP_printk("dev %s group %u",
+		  jbd2_dev_to_name(__entry->dev), __entry->group)
+);
+
+DEFINE_EVENT(ext4__bitmap_load, ext4_mb_bitmap_load,
+
+	TP_PROTO(struct super_block *sb, unsigned long group),
+
+	TP_ARGS(sb, group)
+);
+
+DEFINE_EVENT(ext4__bitmap_load, ext4_mb_buddy_bitmap_load,
+
+	TP_PROTO(struct super_block *sb, unsigned long group),
+
+	TP_ARGS(sb, group)
+);
 
 #endif /* _TRACE_EXT4_H */