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: (47 commits)
ext4: Fix potential fiemap deadlock (mmap_sem vs. i_data_sem)
ext4: Do not override ext2 or ext3 if built they are built as modules
jbd2: Export jbd2_log_start_commit to fix ext4 build
ext4: Fix insufficient checks in EXT4_IOC_MOVE_EXT
ext4: Wait for proper transaction commit on fsync
ext4: fix incorrect block reservation on quota transfer.
ext4: quota macros cleanup
ext4: ext4_get_reserved_space() must return bytes instead of blocks
ext4: remove blocks from inode prealloc list on failure
ext4: wait for log to commit when umounting
ext4: Avoid data / filesystem corruption when write fails to copy data
ext4: Use ext4 file system driver for ext2/ext3 file system mounts
ext4: Return the PTR_ERR of the correct pointer in setup_new_group_blocks()
jbd2: Add ENOMEM checking in and for jbd2_journal_write_metadata_buffer()
ext4: remove unused parameter wbc from __ext4_journalled_writepage()
ext4: remove encountered_congestion trace
ext4: move_extent_per_page() cleanup
ext4: initialize moved_len before calling ext4_move_extents()
ext4: Fix double-free of blocks with EXT4_IOC_MOVE_EXT
ext4: use ext4_data_block_valid() in ext4_free_blocks()
...

Documentation/filesystems/ext4.txt

···
 			identified through its new major/minor numbers encoded
 			in devnum.
 
-noload			Don't load the journal on mounting.  Note that
-                     	if the filesystem was not unmounted cleanly,
+norecovery		Don't load the journal on mounting.  Note that
+noload			if the filesystem was not unmounted cleanly,
                      	skipping the journal replay will lead to the
                      	filesystem containing inconsistencies that can
                      	lead to any number of problems.
···
 			"zero-length" problem that can happen when a
 			system crashes before the delayed allocation
 			blocks are forced to disk.
+
+discard		Controls whether ext4 should issue discard/TRIM
+nodiscard(*)		commands to the underlying block device when
+			blocks are freed.  This is useful for SSD devices
+			and sparse/thinly-provisioned LUNs, but it is off
+			by default until sufficient testing has been done.
 
 Data Mode
 =========

fs/ext4/Kconfig

···
 
 	  If unsure, say N.
 
+config EXT4_USE_FOR_EXT23
+	bool "Use ext4 for ext2/ext3 file systems"
+	depends on EXT3_FS=n || EXT2_FS=n
+	default y
+	help
+	  Allow the ext4 file system driver code to be used for ext2 or
+	  ext3 file system mounts.  This allows users to reduce their
+	  compiled kernel size by using one file system driver for
+	  ext2, ext3, and ext4 file systems.
+
 config EXT4_FS_XATTR
 	bool "Ext4 extended attributes"
 	depends on EXT4_FS

fs/ext4/balloc.c

···
 }
 
 /**
- * ext4_free_blocks() -- Free given blocks and update quota
- * @handle:		handle for this transaction
- * @inode:		inode
- * @block:		start physical block to free
- * @count:		number of blocks to count
- * @metadata: 		Are these metadata blocks
- */
-void ext4_free_blocks(handle_t *handle, struct inode *inode,
-			ext4_fsblk_t block, unsigned long count,
-			int metadata)
-{
-	struct super_block *sb;
-	unsigned long dquot_freed_blocks;
-
-	/* this isn't the right place to decide whether block is metadata
-	 * inode.c/extents.c knows better, but for safety ... */
-	if (S_ISDIR(inode->i_mode) || S_ISLNK(inode->i_mode))
-		metadata = 1;
-
-	/* We need to make sure we don't reuse
-	 * block released untill the transaction commit.
-	 * writeback mode have weak data consistency so
-	 * don't force data as metadata when freeing block
-	 * for writeback mode.
-	 */
-	if (metadata == 0 && !ext4_should_writeback_data(inode))
-		metadata = 1;
-
-	sb = inode->i_sb;
-
-	ext4_mb_free_blocks(handle, inode, block, count,
-			    metadata, &dquot_freed_blocks);
-	if (dquot_freed_blocks)
-		vfs_dq_free_block(inode, dquot_freed_blocks);
-	return;
-}
-
-/**
  * ext4_has_free_blocks()
  * @sbi:	in-core super block structure.
  * @nblocks:	number of needed blocks
···
 static unsigned long ext4_bg_num_gdb_nometa(struct super_block *sb,
 					ext4_group_t group)
 {
-	return ext4_bg_has_super(sb, group) ? EXT4_SB(sb)->s_gdb_count : 0;
+	if (!ext4_bg_has_super(sb, group))
+		return 0;
+
+	if (EXT4_HAS_INCOMPAT_FEATURE(sb,EXT4_FEATURE_INCOMPAT_META_BG))
+		return le32_to_cpu(EXT4_SB(sb)->s_es->s_first_meta_bg);
+	else
+		return EXT4_SB(sb)->s_gdb_count;
 }
 
 /**

fs/ext4/block_validity.c

···
 		if (ext4_bg_has_super(sb, i) &&
 		    ((i < 5) || ((i % flex_size) == 0)))
 			add_system_zone(sbi, ext4_group_first_block_no(sb, i),
-					sbi->s_gdb_count + 1);
+					ext4_bg_num_gdb(sb, i) + 1);
 		gdp = ext4_get_group_desc(sb, i, NULL);
 		ret = add_system_zone(sbi, ext4_block_bitmap(sb, gdp), 1);
 		if (ret)
···
 	struct rb_node *n = sbi->system_blks.rb_node;
 
 	if ((start_blk <= le32_to_cpu(sbi->s_es->s_first_data_block)) ||
+	    (start_blk + count < start_blk) ||
 	    (start_blk + count > ext4_blocks_count(sbi->s_es)))
 		return 0;
 	while (n) {

fs/ext4/ext4.h

···
 					 EXT4_GET_BLOCKS_DIO_CREATE_EXT)
 
 /*
+ * Flags used by ext4_free_blocks
+ */
+#define EXT4_FREE_BLOCKS_METADATA	0x0001
+#define EXT4_FREE_BLOCKS_FORGET		0x0002
+
+/*
  * ioctl commands
  */
 #define	EXT4_IOC_GETFLAGS		FS_IOC_GETFLAGS
···
 	struct list_head i_aio_dio_complete_list;
 	/* current io_end structure for async DIO write*/
 	ext4_io_end_t *cur_aio_dio;
+
+	/*
+	 * Transactions that contain inode's metadata needed to complete
+	 * fsync and fdatasync, respectively.
+	 */
+	tid_t i_sync_tid;
+	tid_t i_datasync_tid;
 };
 
 /*
···
 #define EXT4_MOUNT_DELALLOC		0x8000000 /* Delalloc support */
 #define EXT4_MOUNT_DATA_ERR_ABORT	0x10000000 /* Abort on file data write */
 #define EXT4_MOUNT_BLOCK_VALIDITY	0x20000000 /* Block validity checking */
+#define EXT4_MOUNT_DISCARD		0x40000000 /* Issue DISCARD requests */
 
 #define clear_opt(o, opt)		o &= ~EXT4_MOUNT_##opt
 #define set_opt(o, opt)			o |= EXT4_MOUNT_##opt
···
 			ext4_fsblk_t goal, unsigned long *count, int *errp);
 extern int ext4_claim_free_blocks(struct ext4_sb_info *sbi, s64 nblocks);
 extern int ext4_has_free_blocks(struct ext4_sb_info *sbi, s64 nblocks);
-extern void ext4_free_blocks(handle_t *handle, struct inode *inode,
-			ext4_fsblk_t block, unsigned long count, int metadata);
 extern void ext4_add_groupblocks(handle_t *handle, struct super_block *sb,
 				ext4_fsblk_t block, unsigned long count);
 extern ext4_fsblk_t ext4_count_free_blocks(struct super_block *);
···
 extern void ext4_discard_preallocations(struct inode *);
 extern int __init init_ext4_mballoc(void);
 extern void exit_ext4_mballoc(void);
-extern void ext4_mb_free_blocks(handle_t *, struct inode *,
-		ext4_fsblk_t, unsigned long, int, unsigned long *);
+extern void ext4_free_blocks(handle_t *handle, struct inode *inode,
+			     struct buffer_head *bh, ext4_fsblk_t block,
+			     unsigned long count, int flags);
 extern int ext4_mb_add_groupinfo(struct super_block *sb,
 		ext4_group_t i, struct ext4_group_desc *desc);
 extern int ext4_mb_get_buddy_cache_lock(struct super_block *, ext4_group_t);
 extern void ext4_mb_put_buddy_cache_lock(struct super_block *,
 						ext4_group_t, int);
 /* inode.c */
-int ext4_forget(handle_t *handle, int is_metadata, struct inode *inode,
-		struct buffer_head *bh, ext4_fsblk_t blocknr);
 struct buffer_head *ext4_getblk(handle_t *, struct inode *,
 						ext4_lblk_t, int, int *);
 struct buffer_head *ext4_bread(handle_t *, struct inode *,

fs/ext4/ext4_jbd2.c

···
 
 #include "ext4_jbd2.h"
 
+#include <trace/events/ext4.h>
+
 int __ext4_journal_get_undo_access(const char *where, handle_t *handle,
 				struct buffer_head *bh)
 {
···
 	return err;
 }
 
-int __ext4_journal_forget(const char *where, handle_t *handle,
-				struct buffer_head *bh)
+/*
+ * The ext4 forget function must perform a revoke if we are freeing data
+ * which has been journaled.  Metadata (eg. indirect blocks) must be
+ * revoked in all cases.
+ *
+ * "bh" may be NULL: a metadata block may have been freed from memory
+ * but there may still be a record of it in the journal, and that record
+ * still needs to be revoked.
+ *
+ * If the handle isn't valid we're not journaling, but we still need to
+ * call into ext4_journal_revoke() to put the buffer head.
+ */
+int __ext4_forget(const char *where, handle_t *handle, int is_metadata,
+		  struct inode *inode, struct buffer_head *bh,
+		  ext4_fsblk_t blocknr)
 {
-	int err = 0;
+	int err;
 
-	if (ext4_handle_valid(handle)) {
-		err = jbd2_journal_forget(handle, bh);
-		if (err)
-			ext4_journal_abort_handle(where, __func__, bh,
-						  handle, err);
-	}
-	else
+	might_sleep();
+
+	trace_ext4_forget(inode, is_metadata, blocknr);
+	BUFFER_TRACE(bh, "enter");
+
+	jbd_debug(4, "forgetting bh %p: is_metadata = %d, mode %o, "
+		  "data mode %x\n",
+		  bh, is_metadata, inode->i_mode,
+		  test_opt(inode->i_sb, DATA_FLAGS));
+
+	/* In the no journal case, we can just do a bforget and return */
+	if (!ext4_handle_valid(handle)) {
 		bforget(bh);
-	return err;
-}
-
-int __ext4_journal_revoke(const char *where, handle_t *handle,
-				ext4_fsblk_t blocknr, struct buffer_head *bh)
-{
-	int err = 0;
-
-	if (ext4_handle_valid(handle)) {
-		err = jbd2_journal_revoke(handle, blocknr, bh);
-		if (err)
-			ext4_journal_abort_handle(where, __func__, bh,
-						  handle, err);
+		return 0;
 	}
-	else
-		bforget(bh);
+
+	/* Never use the revoke function if we are doing full data
+	 * journaling: there is no need to, and a V1 superblock won't
+	 * support it.  Otherwise, only skip the revoke on un-journaled
+	 * data blocks. */
+
+	if (test_opt(inode->i_sb, DATA_FLAGS) == EXT4_MOUNT_JOURNAL_DATA ||
+	    (!is_metadata && !ext4_should_journal_data(inode))) {
+		if (bh) {
+			BUFFER_TRACE(bh, "call jbd2_journal_forget");
+			err = jbd2_journal_forget(handle, bh);
+			if (err)
+				ext4_journal_abort_handle(where, __func__, bh,
+							  handle, err);
+			return err;
+		}
+		return 0;
+	}
+
+	/*
+	 * data!=journal && (is_metadata || should_journal_data(inode))
+	 */
+	BUFFER_TRACE(bh, "call jbd2_journal_revoke");
+	err = jbd2_journal_revoke(handle, blocknr, bh);
+	if (err) {
+		ext4_journal_abort_handle(where, __func__, bh, handle, err);
+		ext4_abort(inode->i_sb, __func__,
+			   "error %d when attempting revoke", err);
+	}
+	BUFFER_TRACE(bh, "exit");
 	return err;
 }
 

fs/ext4/ext4_jbd2.h

···
 
 #define EXT4_DATA_TRANS_BLOCKS(sb)	(EXT4_SINGLEDATA_TRANS_BLOCKS(sb) + \
 					 EXT4_XATTR_TRANS_BLOCKS - 2 + \
-					 2*EXT4_QUOTA_TRANS_BLOCKS(sb))
+					 EXT4_MAXQUOTAS_TRANS_BLOCKS(sb))
 
 /*
  * Define the number of metadata blocks we need to account to modify data.
···
  * This include super block, inode block, quota blocks and xattr blocks
  */
 #define EXT4_META_TRANS_BLOCKS(sb)	(EXT4_XATTR_TRANS_BLOCKS + \
-					2*EXT4_QUOTA_TRANS_BLOCKS(sb))
+					EXT4_MAXQUOTAS_TRANS_BLOCKS(sb))
 
 /* Delete operations potentially hit one directory's namespace plus an
  * entire inode, plus arbitrary amounts of bitmap/indirection data.  Be
···
  * but inode, sb and group updates are done only once */
 #define EXT4_QUOTA_INIT_BLOCKS(sb) (test_opt(sb, QUOTA) ? (DQUOT_INIT_ALLOC*\
 		(EXT4_SINGLEDATA_TRANS_BLOCKS(sb)-3)+3+DQUOT_INIT_REWRITE) : 0)
+
 #define EXT4_QUOTA_DEL_BLOCKS(sb) (test_opt(sb, QUOTA) ? (DQUOT_DEL_ALLOC*\
 		(EXT4_SINGLEDATA_TRANS_BLOCKS(sb)-3)+3+DQUOT_DEL_REWRITE) : 0)
 #else
···
 #define EXT4_QUOTA_INIT_BLOCKS(sb) 0
 #define EXT4_QUOTA_DEL_BLOCKS(sb) 0
 #endif
+#define EXT4_MAXQUOTAS_TRANS_BLOCKS(sb) (MAXQUOTAS*EXT4_QUOTA_TRANS_BLOCKS(sb))
+#define EXT4_MAXQUOTAS_INIT_BLOCKS(sb) (MAXQUOTAS*EXT4_QUOTA_INIT_BLOCKS(sb))
+#define EXT4_MAXQUOTAS_DEL_BLOCKS(sb) (MAXQUOTAS*EXT4_QUOTA_DEL_BLOCKS(sb))
 
 int
 ext4_mark_iloc_dirty(handle_t *handle,
···
 int ext4_mark_inode_dirty(handle_t *handle, struct inode *inode);
 
 /*
- * Wrapper functions with which ext4 calls into JBD.  The intent here is
- * to allow these to be turned into appropriate stubs so ext4 can control
- * ext2 filesystems, so ext2+ext4 systems only nee one fs.  This work hasn't
- * been done yet.
+ * Wrapper functions with which ext4 calls into JBD.
  */
-
 void ext4_journal_abort_handle(const char *caller, const char *err_fn,
 		struct buffer_head *bh, handle_t *handle, int err);
 
···
 int __ext4_journal_get_write_access(const char *where, handle_t *handle,
 				struct buffer_head *bh);
 
-/* When called with an invalid handle, this will still do a put on the BH */
-int __ext4_journal_forget(const char *where, handle_t *handle,
-				struct buffer_head *bh);
-
-/* When called with an invalid handle, this will still do a put on the BH */
-int __ext4_journal_revoke(const char *where, handle_t *handle,
-				ext4_fsblk_t blocknr, struct buffer_head *bh);
+int __ext4_forget(const char *where, handle_t *handle, int is_metadata,
+		  struct inode *inode, struct buffer_head *bh,
+		  ext4_fsblk_t blocknr);
 
 int __ext4_journal_get_create_access(const char *where,
 				handle_t *handle, struct buffer_head *bh);
···
 	__ext4_journal_get_undo_access(__func__, (handle), (bh))
 #define ext4_journal_get_write_access(handle, bh) \
 	__ext4_journal_get_write_access(__func__, (handle), (bh))
-#define ext4_journal_revoke(handle, blocknr, bh) \
-	__ext4_journal_revoke(__func__, (handle), (blocknr), (bh))
+#define ext4_forget(handle, is_metadata, inode, bh, block_nr) \
+	__ext4_forget(__func__, (handle), (is_metadata), (inode), (bh),\
+		      (block_nr))
 #define ext4_journal_get_create_access(handle, bh) \
 	__ext4_journal_get_create_access(__func__, (handle), (bh))
-#define ext4_journal_forget(handle, bh) \
-	__ext4_journal_forget(__func__, (handle), (bh))
 #define ext4_handle_dirty_metadata(handle, inode, bh) \
 	__ext4_handle_dirty_metadata(__func__, (handle), (inode), (bh))
 
···
 	if (ext4_handle_valid(handle))
 		return jbd2_journal_file_inode(handle, &EXT4_I(inode)->jinode);
 	return 0;
+}
+
+static inline void ext4_update_inode_fsync_trans(handle_t *handle,
+						 struct inode *inode,
+						 int datasync)
+{
+	struct ext4_inode_info *ei = EXT4_I(inode);
+
+	if (ext4_handle_valid(handle)) {
+		ei->i_sync_tid = handle->h_transaction->t_tid;
+		if (datasync)
+			ei->i_datasync_tid = handle->h_transaction->t_tid;
+	}
 }
 
 /* super.c */

fs/ext4/extents.c

···
 		for (i = 0; i < depth; i++) {
 			if (!ablocks[i])
 				continue;
-			ext4_free_blocks(handle, inode, ablocks[i], 1, 1);
+			ext4_free_blocks(handle, inode, 0, ablocks[i], 1,
+					 EXT4_FREE_BLOCKS_METADATA);
 		}
 	}
 	kfree(ablocks);
···
 	while (block < last && block != EXT_MAX_BLOCK) {
 		num = last - block;
 		/* find extent for this block */
+		down_read(&EXT4_I(inode)->i_data_sem);
 		path = ext4_ext_find_extent(inode, block, path);
+		up_read(&EXT4_I(inode)->i_data_sem);
 		if (IS_ERR(path)) {
 			err = PTR_ERR(path);
 			path = NULL;
···
 static int ext4_ext_rm_idx(handle_t *handle, struct inode *inode,
 			struct ext4_ext_path *path)
 {
-	struct buffer_head *bh;
 	int err;
 	ext4_fsblk_t leaf;
 
···
 	if (err)
 		return err;
 	ext_debug("index is empty, remove it, free block %llu\n", leaf);
-	bh = sb_find_get_block(inode->i_sb, leaf);
-	ext4_forget(handle, 1, inode, bh, leaf);
-	ext4_free_blocks(handle, inode, leaf, 1, 1);
+	ext4_free_blocks(handle, inode, 0, leaf, 1,
+			 EXT4_FREE_BLOCKS_METADATA | EXT4_FREE_BLOCKS_FORGET);
 	return err;
 }
 
···
 				struct ext4_extent *ex,
 				ext4_lblk_t from, ext4_lblk_t to)
 {
-	struct buffer_head *bh;
 	unsigned short ee_len =  ext4_ext_get_actual_len(ex);
-	int i, metadata = 0;
+	int flags = EXT4_FREE_BLOCKS_FORGET;
 
 	if (S_ISDIR(inode->i_mode) || S_ISLNK(inode->i_mode))
-		metadata = 1;
+		flags |= EXT4_FREE_BLOCKS_METADATA;
 #ifdef EXTENTS_STATS
 	{
 		struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb);
···
 		num = le32_to_cpu(ex->ee_block) + ee_len - from;
 		start = ext_pblock(ex) + ee_len - num;
 		ext_debug("free last %u blocks starting %llu\n", num, start);
-		for (i = 0; i < num; i++) {
-			bh = sb_find_get_block(inode->i_sb, start + i);
-			ext4_forget(handle, 0, inode, bh, start + i);
-		}
-		ext4_free_blocks(handle, inode, start, num, metadata);
+		ext4_free_blocks(handle, inode, 0, start, num, flags);
 	} else if (from == le32_to_cpu(ex->ee_block)
 		   && to <= le32_to_cpu(ex->ee_block) + ee_len - 1) {
 		printk(KERN_INFO "strange request: removal %u-%u from %u:%u\n",
···
 			correct_index = 1;
 			credits += (ext_depth(inode)) + 1;
 		}
-		credits += 2 * EXT4_QUOTA_TRANS_BLOCKS(inode->i_sb);
+		credits += EXT4_MAXQUOTAS_TRANS_BLOCKS(inode->i_sb);
 
 		err = ext4_ext_truncate_extend_restart(handle, inode, credits);
 		if (err)
···
 	if (flags == EXT4_GET_BLOCKS_DIO_CONVERT_EXT) {
 		ret = ext4_convert_unwritten_extents_dio(handle, inode,
 							path);
+		if (ret >= 0)
+			ext4_update_inode_fsync_trans(handle, inode, 1);
 		goto out2;
 	}
 	/* buffered IO case */
···
 	ret = ext4_ext_convert_to_initialized(handle, inode,
 						path, iblock,
 						max_blocks);
+	if (ret >= 0)
+		ext4_update_inode_fsync_trans(handle, inode, 1);
 out:
 	if (ret <= 0) {
 		err = ret;
···
 		/* not a good idea to call discard here directly,
 		 * but otherwise we'd need to call it every free() */
 		ext4_discard_preallocations(inode);
-		ext4_free_blocks(handle, inode, ext_pblock(&newex),
-					ext4_ext_get_actual_len(&newex), 0);
+		ext4_free_blocks(handle, inode, 0, ext_pblock(&newex),
+				 ext4_ext_get_actual_len(&newex), 0);
 		goto out2;
 	}
 
···
 	allocated = ext4_ext_get_actual_len(&newex);
 	set_buffer_new(bh_result);
 
-	/* Cache only when it is _not_ an uninitialized extent */
-	if ((flags & EXT4_GET_BLOCKS_UNINIT_EXT) == 0)
+	/*
+	 * Cache the extent and update transaction to commit on fdatasync only
+	 * 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_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;
···
 		 * Walk the extent tree gathering extent information.
 		 * ext4_ext_fiemap_cb will push extents back to user.
 		 */
-		down_read(&EXT4_I(inode)->i_data_sem);
 		error = ext4_ext_walk_space(inode, start_blk, len_blks,
 					  ext4_ext_fiemap_cb, fieinfo);
-		up_read(&EXT4_I(inode)->i_data_sem);
 	}
 
 	return error;

fs/ext4/fsync.c

···
 int ext4_sync_file(struct file *file, struct dentry *dentry, int datasync)
 {
 	struct inode *inode = dentry->d_inode;
+	struct ext4_inode_info *ei = EXT4_I(inode);
 	journal_t *journal = EXT4_SB(inode->i_sb)->s_journal;
-	int err, ret = 0;
+	int ret;
+	tid_t commit_tid;
 
 	J_ASSERT(ext4_journal_current_handle() == NULL);
 
 	trace_ext4_sync_file(file, dentry, datasync);
 
+	if (inode->i_sb->s_flags & MS_RDONLY)
+		return 0;
+
 	ret = flush_aio_dio_completed_IO(inode);
 	if (ret < 0)
-		goto out;
+		return ret;
+	
+	if (!journal)
+		return simple_fsync(file, dentry, datasync);
+
 	/*
-	 * data=writeback:
+	 * data=writeback,ordered:
 	 *  The caller's filemap_fdatawrite()/wait will sync the data.
-	 *  sync_inode() will sync the metadata
-	 *
-	 * data=ordered:
-	 *  The caller's filemap_fdatawrite() will write the data and
-	 *  sync_inode() will write the inode if it is dirty.  Then the caller's
-	 *  filemap_fdatawait() will wait on the pages.
+	 *  Metadata is in the journal, we wait for proper transaction to
+	 *  commit here.
 	 *
 	 * data=journal:
 	 *  filemap_fdatawrite won't do anything (the buffers are clean).
···
 	 *  (they were dirtied by commit).  But that's OK - the blocks are
 	 *  safe in-journal, which is all fsync() needs to ensure.
 	 */
-	if (ext4_should_journal_data(inode)) {
-		ret = ext4_force_commit(inode->i_sb);
-		goto out;
-	}
+	if (ext4_should_journal_data(inode))
+		return ext4_force_commit(inode->i_sb);
 
-	if (!journal)
-		ret = sync_mapping_buffers(inode->i_mapping);
-
-	if (datasync && !(inode->i_state & I_DIRTY_DATASYNC))
-		goto out;
-
-	/*
-	 * The VFS has written the file data.  If the inode is unaltered
-	 * then we need not start a commit.
-	 */
-	if (inode->i_state & (I_DIRTY_SYNC|I_DIRTY_DATASYNC)) {
-		struct writeback_control wbc = {
-			.sync_mode = WB_SYNC_ALL,
-			.nr_to_write = 0, /* sys_fsync did this */
-		};
-		err = sync_inode(inode, &wbc);
-		if (ret == 0)
-			ret = err;
-	}
-out:
-	if (journal && (journal->j_flags & JBD2_BARRIER))
+	commit_tid = datasync ? ei->i_datasync_tid : ei->i_sync_tid;
+	if (jbd2_log_start_commit(journal, commit_tid))
+		jbd2_log_wait_commit(journal, commit_tid);
+	else if (journal->j_flags & JBD2_BARRIER)
 		blkdev_issue_flush(inode->i_sb->s_bdev, NULL);
 	return ret;
 }

fs/ext4/inode.c

···
 }
 
 /*
- * The ext4 forget function must perform a revoke if we are freeing data
- * which has been journaled.  Metadata (eg. indirect blocks) must be
- * revoked in all cases.
- *
- * "bh" may be NULL: a metadata block may have been freed from memory
- * but there may still be a record of it in the journal, and that record
- * still needs to be revoked.
- *
- * If the handle isn't valid we're not journaling, but we still need to
- * call into ext4_journal_revoke() to put the buffer head.
- */
-int ext4_forget(handle_t *handle, int is_metadata, struct inode *inode,
-		struct buffer_head *bh, ext4_fsblk_t blocknr)
-{
-	int err;
-
-	might_sleep();
-
-	BUFFER_TRACE(bh, "enter");
-
-	jbd_debug(4, "forgetting bh %p: is_metadata = %d, mode %o, "
-		  "data mode %x\n",
-		  bh, is_metadata, inode->i_mode,
-		  test_opt(inode->i_sb, DATA_FLAGS));
-
-	/* Never use the revoke function if we are doing full data
-	 * journaling: there is no need to, and a V1 superblock won't
-	 * support it.  Otherwise, only skip the revoke on un-journaled
-	 * data blocks. */
-
-	if (test_opt(inode->i_sb, DATA_FLAGS) == EXT4_MOUNT_JOURNAL_DATA ||
-	    (!is_metadata && !ext4_should_journal_data(inode))) {
-		if (bh) {
-			BUFFER_TRACE(bh, "call jbd2_journal_forget");
-			return ext4_journal_forget(handle, bh);
-		}
-		return 0;
-	}
-
-	/*
-	 * data!=journal && (is_metadata || should_journal_data(inode))
-	 */
-	BUFFER_TRACE(bh, "call ext4_journal_revoke");
-	err = ext4_journal_revoke(handle, blocknr, bh);
-	if (err)
-		ext4_abort(inode->i_sb, __func__,
-			   "error %d when attempting revoke", err);
-	BUFFER_TRACE(bh, "exit");
-	return err;
-}
-
-/*
  * Work out how many blocks we need to proceed with the next chunk of a
  * truncate transaction.
  */
···
 	return ret;
 failed_out:
 	for (i = 0; i < index; i++)
-		ext4_free_blocks(handle, inode, new_blocks[i], 1, 0);
+		ext4_free_blocks(handle, inode, 0, new_blocks[i], 1, 0);
 	return ret;
 }
 
···
 	return err;
 failed:
 	/* Allocation failed, free what we already allocated */
+	ext4_free_blocks(handle, inode, 0, new_blocks[0], 1, 0);
 	for (i = 1; i <= n ; i++) {
-		BUFFER_TRACE(branch[i].bh, "call jbd2_journal_forget");
-		ext4_journal_forget(handle, branch[i].bh);
+		/* 
+		 * 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.
+		 */
+		ext4_free_blocks(handle, inode, 0, new_blocks[i], 1,
+				 EXT4_FREE_BLOCKS_FORGET);
 	}
-	for (i = 0; i < indirect_blks; i++)
-		ext4_free_blocks(handle, inode, new_blocks[i], 1, 0);
+	for (i = n+1; i < indirect_blks; i++)
+		ext4_free_blocks(handle, inode, 0, new_blocks[i], 1, 0);
 
-	ext4_free_blocks(handle, inode, new_blocks[i], num, 0);
+	ext4_free_blocks(handle, inode, 0, new_blocks[i], num, 0);
 
 	return err;
 }
···
 
 err_out:
 	for (i = 1; i <= num; i++) {
-		BUFFER_TRACE(where[i].bh, "call jbd2_journal_forget");
-		ext4_journal_forget(handle, where[i].bh);
-		ext4_free_blocks(handle, inode,
-					le32_to_cpu(where[i-1].key), 1, 0);
+		/* 
+		 * 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.
+		 */
+		ext4_free_blocks(handle, inode, where[i].bh, 0, 1,
+				 EXT4_FREE_BLOCKS_FORGET);
 	}
-	ext4_free_blocks(handle, inode, le32_to_cpu(where[num].key), blks, 0);
+	ext4_free_blocks(handle, inode, 0, le32_to_cpu(where[num].key),
+			 blks, 0);
 
 	return err;
 }
···
 	if (!err)
 		err = ext4_splice_branch(handle, inode, iblock,
 					 partial, indirect_blks, count);
-	else
+	if (err)
 		goto cleanup;
 
 	set_buffer_new(bh_result);
+
+	ext4_update_inode_fsync_trans(handle, inode, 1);
 got_it:
 	map_bh(bh_result, inode->i_sb, le32_to_cpu(chain[depth-1].key));
 	if (count > blocks_to_boundary)
···
 		EXT4_I(inode)->i_reserved_meta_blocks;
 	spin_unlock(&EXT4_I(inode)->i_block_reservation_lock);
 
-	return total;
+	return (total << inode->i_blkbits);
 }
 /*
  * Calculate the number of metadata blocks need to reserve
···
 	return ext4_journal_get_write_access(handle, bh);
 }
 
+/*
+ * Truncate blocks that were not used by write. We have to truncate the
+ * pagecache as well so that corresponding buffers get properly unmapped.
+ */
+static void ext4_truncate_failed_write(struct inode *inode)
+{
+	truncate_inode_pages(inode->i_mapping, inode->i_size);
+	ext4_truncate(inode);
+}
+
 static int ext4_write_begin(struct file *file, struct address_space *mapping,
 			    loff_t pos, unsigned len, unsigned flags,
 			    struct page **pagep, void **fsdata)
···
 
 		ext4_journal_stop(handle);
 		if (pos + len > inode->i_size) {
-			ext4_truncate(inode);
+			ext4_truncate_failed_write(inode);
 			/*
 			 * If truncate failed early the inode might
 			 * still be on the orphan list; we need to
···
 		ret = ret2;
 
 	if (pos + len > inode->i_size) {
-		ext4_truncate(inode);
+		ext4_truncate_failed_write(inode);
 		/*
 		 * If truncate failed early the inode might still be
 		 * on the orphan list; we need to make sure the inode
···
 		ret = ret2;
 
 	if (pos + len > inode->i_size) {
-		ext4_truncate(inode);
+		ext4_truncate_failed_write(inode);
 		/*
 		 * If truncate failed early the inode might still be
 		 * on the orphan list; we need to make sure the inode
···
 	if (!ret)
 		ret = ret2;
 	if (pos + len > inode->i_size) {
-		ext4_truncate(inode);
+		ext4_truncate_failed_write(inode);
 		/*
 		 * If truncate failed early the inode might still be
 		 * on the orphan list; we need to make sure the inode
···
 }
 
 static int __ext4_journalled_writepage(struct page *page,
-				       struct writeback_control *wbc,
 				       unsigned int len)
 {
 	struct address_space *mapping = page->mapping;
···
 		 * doesn't seem much point in redirtying the page here.
 		 */
 		ClearPageChecked(page);
-		return __ext4_journalled_writepage(page, wbc, len);
+		return __ext4_journalled_writepage(page, len);
 	}
 
 	if (test_opt(inode->i_sb, NOBH) && ext4_should_writeback_data(inode))
···
 	 * number of contiguous block. So we will limit
 	 * number of contiguous block to a sane value
 	 */
-	if (!(inode->i_flags & EXT4_EXTENTS_FL) &&
+	if (!(EXT4_I(inode)->i_flags & EXT4_EXTENTS_FL) &&
 	    (max_blocks > EXT4_MAX_TRANS_DATA))
 		max_blocks = EXT4_MAX_TRANS_DATA;
 
···
 		 * i_size_read because we hold i_mutex.
 		 */
 		if (pos + len > inode->i_size)
-			ext4_truncate(inode);
+			ext4_truncate_failed_write(inode);
 	}
 
 	if (ret == -ENOSPC && ext4_should_retry_alloc(inode->i_sb, &retries))
···
 			      __le32 *last)
 {
 	__le32 *p;
+	int	flags = EXT4_FREE_BLOCKS_FORGET;
+
+	if (S_ISDIR(inode->i_mode) || S_ISLNK(inode->i_mode))
+		flags |= EXT4_FREE_BLOCKS_METADATA;
+
 	if (try_to_extend_transaction(handle, inode)) {
 		if (bh) {
 			BUFFER_TRACE(bh, "call ext4_handle_dirty_metadata");
···
 		}
 	}
 
-	/*
-	 * Any buffers which are on the journal will be in memory. We
-	 * find them on the hash table so jbd2_journal_revoke() will
-	 * run jbd2_journal_forget() on them.  We've already detached
-	 * each block from the file, so bforget() in
-	 * jbd2_journal_forget() should be safe.
-	 *
-	 * AKPM: turn on bforget in jbd2_journal_forget()!!!
-	 */
-	for (p = first; p < last; p++) {
-		u32 nr = le32_to_cpu(*p);
-		if (nr) {
-			struct buffer_head *tbh;
+	for (p = first; p < last; p++)
+		*p = 0;
 
-			*p = 0;
-			tbh = sb_find_get_block(inode->i_sb, nr);
-			ext4_forget(handle, 0, inode, tbh, nr);
-		}
-	}
-
-	ext4_free_blocks(handle, inode, block_to_free, count, 0);
+	ext4_free_blocks(handle, inode, 0, block_to_free, count, flags);
 }
 
 /**
···
 					    blocks_for_truncate(inode));
 			}
 
-			ext4_free_blocks(handle, inode, nr, 1, 1);
+			ext4_free_blocks(handle, inode, 0, nr, 1,
+					 EXT4_FREE_BLOCKS_METADATA);
 
 			if (parent_bh) {
 				/*
···
 	struct ext4_iloc iloc;
 	struct ext4_inode *raw_inode;
 	struct ext4_inode_info *ei;
-	struct buffer_head *bh;
 	struct inode *inode;
+	journal_t *journal = EXT4_SB(sb)->s_journal;
 	long ret;
 	int block;
 
···
 		return inode;
 
 	ei = EXT4_I(inode);
+	iloc.bh = 0;
 
 	ret = __ext4_get_inode_loc(inode, &iloc, 0);
 	if (ret < 0)
 		goto bad_inode;
-	bh = iloc.bh;
 	raw_inode = ext4_raw_inode(&iloc);
 	inode->i_mode = le16_to_cpu(raw_inode->i_mode);
 	inode->i_uid = (uid_t)le16_to_cpu(raw_inode->i_uid_low);
···
 		if (inode->i_mode == 0 ||
 		    !(EXT4_SB(inode->i_sb)->s_mount_state & EXT4_ORPHAN_FS)) {
 			/* this inode is deleted */
-			brelse(bh);
 			ret = -ESTALE;
 			goto bad_inode;
 		}
···
 		ei->i_data[block] = raw_inode->i_block[block];
 	INIT_LIST_HEAD(&ei->i_orphan);
 
+	/*
+	 * Set transaction id's of transactions that have to be committed
+	 * to finish f[data]sync. We set them to currently running transaction
+	 * as we cannot be sure that the inode or some of its metadata isn't
+	 * part of the transaction - the inode could have been reclaimed and
+	 * now it is reread from disk.
+	 */
+	if (journal) {
+		transaction_t *transaction;
+		tid_t tid;
+
+		spin_lock(&journal->j_state_lock);
+		if (journal->j_running_transaction)
+			transaction = journal->j_running_transaction;
+		else
+			transaction = journal->j_committing_transaction;
+		if (transaction)
+			tid = transaction->t_tid;
+		else
+			tid = journal->j_commit_sequence;
+		spin_unlock(&journal->j_state_lock);
+		ei->i_sync_tid = tid;
+		ei->i_datasync_tid = tid;
+	}
+
 	if (EXT4_INODE_SIZE(inode->i_sb) > EXT4_GOOD_OLD_INODE_SIZE) {
 		ei->i_extra_isize = le16_to_cpu(raw_inode->i_extra_isize);
 		if (EXT4_GOOD_OLD_INODE_SIZE + ei->i_extra_isize >
 		    EXT4_INODE_SIZE(inode->i_sb)) {
-			brelse(bh);
 			ret = -EIO;
 			goto bad_inode;
 		}
···
 
 	ret = 0;
 	if (ei->i_file_acl &&
-	    ((ei->i_file_acl <
-	      (le32_to_cpu(EXT4_SB(sb)->s_es->s_first_data_block) +
-	       EXT4_SB(sb)->s_gdb_count)) ||
-	     (ei->i_file_acl >= ext4_blocks_count(EXT4_SB(sb)->s_es)))) {
+	    !ext4_data_block_valid(EXT4_SB(sb), ei->i_file_acl, 1)) {
 		ext4_error(sb, __func__,
 			   "bad extended attribute block %llu in inode #%lu",
 			   ei->i_file_acl, inode->i_ino);
···
 		/* Validate block references which are part of inode */
 		ret = ext4_check_inode_blockref(inode);
 	}
-	if (ret) {
-		brelse(bh);
+	if (ret)
 		goto bad_inode;
-	}
 
 	if (S_ISREG(inode->i_mode)) {
 		inode->i_op = &ext4_file_inode_operations;
···
 			init_special_inode(inode, inode->i_mode,
 			   new_decode_dev(le32_to_cpu(raw_inode->i_block[1])));
 	} else {
-		brelse(bh);
 		ret = -EIO;
 		ext4_error(inode->i_sb, __func__,
 			   "bogus i_mode (%o) for inode=%lu",
···
 	return inode;
 
 bad_inode:
+	brelse(iloc.bh);
 	iget_failed(inode);
 	return ERR_PTR(ret);
 }
···
 		err = rc;
 	ei->i_state &= ~EXT4_STATE_NEW;
 
+	ext4_update_inode_fsync_trans(handle, inode, 0);
 out_brelse:
 	brelse(bh);
 	ext4_std_error(inode->i_sb, err);
···
 
 		/* (user+group)*(old+new) structure, inode write (sb,
 		 * inode block, ? - but truncate inode update has it) */
-		handle = ext4_journal_start(inode, 2*(EXT4_QUOTA_INIT_BLOCKS(inode->i_sb)+
-					EXT4_QUOTA_DEL_BLOCKS(inode->i_sb))+3);
+		handle = ext4_journal_start(inode, (EXT4_MAXQUOTAS_INIT_BLOCKS(inode->i_sb)+
+					EXT4_MAXQUOTAS_DEL_BLOCKS(inode->i_sb))+3);
 		if (IS_ERR(handle)) {
 			error = PTR_ERR(handle);
 			goto err_out;

fs/ext4/ioctl.c

···
 		struct file *donor_filp;
 		int err;
 
+		if (!(filp->f_mode & FMODE_READ) ||
+		    !(filp->f_mode & FMODE_WRITE))
+			return -EBADF;
+
 		if (copy_from_user(&me,
 			(struct move_extent __user *)arg, sizeof(me)))
 			return -EFAULT;
+		me.moved_len = 0;
 
 		donor_filp = fget(me.donor_fd);
 		if (!donor_filp)
 			return -EBADF;
 
-		if (!capable(CAP_DAC_OVERRIDE)) {
-			if ((current->real_cred->fsuid != inode->i_uid) ||
-				!(inode->i_mode & S_IRUSR) ||
-				!(donor_filp->f_dentry->d_inode->i_mode &
-				S_IRUSR)) {
-				fput(donor_filp);
-				return -EACCES;
-			}
+		if (!(donor_filp->f_mode & FMODE_WRITE)) {
+			err = -EBADF;
+			goto mext_out;
 		}
+
+		err = mnt_want_write(filp->f_path.mnt);
+		if (err)
+			goto mext_out;
 
 		err = ext4_move_extents(filp, donor_filp, me.orig_start,
 					me.donor_start, me.len, &me.moved_len);
-		fput(donor_filp);
+		mnt_drop_write(filp->f_path.mnt);
+		if (me.moved_len > 0)
+			file_remove_suid(donor_filp);
 
 		if (copy_to_user((struct move_extent *)arg, &me, sizeof(me)))
-			return -EFAULT;
-
+			err = -EFAULT;
+mext_out:
+		fput(donor_filp);
 		return err;
 	}
 

fs/ext4/mballoc.c

···
 	struct ext4_group_info *db;
 	int err, count = 0, count2 = 0;
 	struct ext4_free_data *entry;
-	ext4_fsblk_t discard_block;
 	struct list_head *l, *ltmp;
 
 	list_for_each_safe(l, ltmp, &txn->t_private_list) {
···
 			page_cache_release(e4b.bd_bitmap_page);
 		}
 		ext4_unlock_group(sb, entry->group);
-		discard_block = (ext4_fsblk_t) entry->group * EXT4_BLOCKS_PER_GROUP(sb)
-			+ entry->start_blk
-			+ le32_to_cpu(EXT4_SB(sb)->s_es->s_first_data_block);
-		trace_ext4_discard_blocks(sb, (unsigned long long)discard_block,
-					  entry->count);
-		sb_issue_discard(sb, discard_block, entry->count);
+		if (test_opt(sb, DISCARD)) {
+			ext4_fsblk_t discard_block;
+			struct ext4_super_block *es = EXT4_SB(sb)->s_es;
 
+			discard_block = (ext4_fsblk_t)entry->group *
+						EXT4_BLOCKS_PER_GROUP(sb)
+					+ entry->start_blk
+					+ le32_to_cpu(es->s_first_data_block);
+			trace_ext4_discard_blocks(sb,
+					(unsigned long long)discard_block,
+					entry->count);
+			sb_issue_discard(sb, discard_block, entry->count);
+		}
 		kmem_cache_free(ext4_free_ext_cachep, entry);
 		ext4_mb_release_desc(&e4b);
 	}
···
 		trace_ext4_mballoc_alloc(ac);
 	else
 		trace_ext4_mballoc_prealloc(ac);
+}
+
+/*
+ * Called on failure; free up any blocks from the inode PA for this
+ * context.  We don't need this for MB_GROUP_PA because we only change
+ * pa_free in ext4_mb_release_context(), but on failure, we've already
+ * zeroed out ac->ac_b_ex.fe_len, so group_pa->pa_free is not changed.
+ */
+static void ext4_discard_allocated_blocks(struct ext4_allocation_context *ac)
+{
+	struct ext4_prealloc_space *pa = ac->ac_pa;
+	int len;
+
+	if (pa && pa->pa_type == MB_INODE_PA) {
+		len = ac->ac_b_ex.fe_len;
+		pa->pa_free += len;
+	}
+
 }
 
 /*
···
 			ac->ac_status = AC_STATUS_CONTINUE;
 			goto repeat;
 		} else if (*errp) {
+			ext4_discard_allocated_blocks(ac);
 			ac->ac_b_ex.fe_len = 0;
 			ar->len = 0;
 			ext4_mb_show_ac(ac);
···
 	return 0;
 }
 
-/*
- * Main entry point into mballoc to free blocks
+/**
+ * ext4_free_blocks() -- Free given blocks and update quota
+ * @handle:		handle for this transaction
+ * @inode:		inode
+ * @block:		start physical block to free
+ * @count:		number of blocks to count
+ * @metadata: 		Are these metadata blocks
  */
-void ext4_mb_free_blocks(handle_t *handle, struct inode *inode,
-			ext4_fsblk_t block, unsigned long count,
-			int metadata, unsigned long *freed)
+void ext4_free_blocks(handle_t *handle, struct inode *inode,
+		      struct buffer_head *bh, ext4_fsblk_t block,
+		      unsigned long count, int flags)
 {
 	struct buffer_head *bitmap_bh = NULL;
 	struct super_block *sb = inode->i_sb;
 	struct ext4_allocation_context *ac = NULL;
 	struct ext4_group_desc *gdp;
 	struct ext4_super_block *es;
+	unsigned long freed = 0;
 	unsigned int overflow;
 	ext4_grpblk_t bit;
 	struct buffer_head *gd_bh;
···
 	int err = 0;
 	int ret;
 
-	*freed = 0;
+	if (bh) {
+		if (block)
+			BUG_ON(block != bh->b_blocknr);
+		else
+			block = bh->b_blocknr;
+	}
 
 	sbi = EXT4_SB(sb);
 	es = EXT4_SB(sb)->s_es;
-	if (block < le32_to_cpu(es->s_first_data_block) ||
-	    block + count < block ||
-	    block + count > ext4_blocks_count(es)) {
+	if (!ext4_data_block_valid(sbi, block, count)) {
 		ext4_error(sb, __func__,
 			    "Freeing blocks not in datazone - "
 			    "block = %llu, count = %lu", block, count);
···
 	}
 
 	ext4_debug("freeing block %llu\n", block);
-	trace_ext4_free_blocks(inode, block, count, metadata);
+	trace_ext4_free_blocks(inode, block, count, flags);
+
+	if (flags & EXT4_FREE_BLOCKS_FORGET) {
+		struct buffer_head *tbh = bh;
+		int i;
+
+		BUG_ON(bh && (count > 1));
+
+		for (i = 0; i < count; i++) {
+			if (!bh)
+				tbh = sb_find_get_block(inode->i_sb,
+							block + i);
+			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
+	 * exception if the inode is to be written in writeback mode
+	 * since writeback mode has weak data consistency guarantees.
+	 */
+	if (!ext4_should_writeback_data(inode))
+		flags |= EXT4_FREE_BLOCKS_METADATA;
 
 	ac = kmem_cache_alloc(ext4_ac_cachep, GFP_NOFS);
 	if (ac) {
···
 	err = ext4_mb_load_buddy(sb, block_group, &e4b);
 	if (err)
 		goto error_return;
-	if (metadata && ext4_handle_valid(handle)) {
+
+	if ((flags & EXT4_FREE_BLOCKS_METADATA) && ext4_handle_valid(handle)) {
 		struct ext4_free_data *new_entry;
 		/*
 		 * blocks being freed are metadata. these blocks shouldn't
···
 
 	ext4_mb_release_desc(&e4b);
 
-	*freed += count;
+	freed += count;
 
 	/* We dirtied the bitmap block */
 	BUFFER_TRACE(bitmap_bh, "dirtied bitmap block");
···
 	}
 	sb->s_dirt = 1;
 error_return:
+	if (freed)
+		vfs_dq_free_block(inode, freed);
 	brelse(bitmap_bh);
 	ext4_std_error(sb, err);
 	if (ac)

fs/ext4/migrate.c

···
 	 * So allocate a credit of 3. We may update
 	 * quota (user and group).
 	 */
-	needed = 3 + 2*EXT4_QUOTA_TRANS_BLOCKS(inode->i_sb);
+	needed = 3 + EXT4_MAXQUOTAS_TRANS_BLOCKS(inode->i_sb);
 
 	if (ext4_journal_extend(handle, needed) != 0)
 		retval = ext4_journal_restart(handle, needed);
···
 	for (i = 0; i < max_entries; i++) {
 		if (tmp_idata[i]) {
 			extend_credit_for_blkdel(handle, inode);
-			ext4_free_blocks(handle, inode,
-					le32_to_cpu(tmp_idata[i]), 1, 1);
+			ext4_free_blocks(handle, inode, 0,
+					 le32_to_cpu(tmp_idata[i]), 1,
+					 EXT4_FREE_BLOCKS_METADATA |
+					 EXT4_FREE_BLOCKS_FORGET);
 		}
 	}
 	put_bh(bh);
 	extend_credit_for_blkdel(handle, inode);
-	ext4_free_blocks(handle, inode, le32_to_cpu(i_data), 1, 1);
+	ext4_free_blocks(handle, inode, 0, le32_to_cpu(i_data), 1,
+			 EXT4_FREE_BLOCKS_METADATA |
+			 EXT4_FREE_BLOCKS_FORGET);
 	return 0;
 }
 
···
 	}
 	put_bh(bh);
 	extend_credit_for_blkdel(handle, inode);
-	ext4_free_blocks(handle, inode, le32_to_cpu(i_data), 1, 1);
+	ext4_free_blocks(handle, inode, 0, le32_to_cpu(i_data), 1,
+			 EXT4_FREE_BLOCKS_METADATA |
+			 EXT4_FREE_BLOCKS_FORGET);
 	return 0;
 }
 
···
 	/* ei->i_data[EXT4_IND_BLOCK] */
 	if (i_data[0]) {
 		extend_credit_for_blkdel(handle, inode);
-		ext4_free_blocks(handle, inode,
-				le32_to_cpu(i_data[0]), 1, 1);
+		ext4_free_blocks(handle, inode, 0,
+				le32_to_cpu(i_data[0]), 1,
+				 EXT4_FREE_BLOCKS_METADATA |
+				 EXT4_FREE_BLOCKS_FORGET);
 	}
 
 	/* ei->i_data[EXT4_DIND_BLOCK] */
···
 	}
 	put_bh(bh);
 	extend_credit_for_blkdel(handle, inode);
-	ext4_free_blocks(handle, inode, block, 1, 1);
+	ext4_free_blocks(handle, inode, 0, block, 1,
+			 EXT4_FREE_BLOCKS_METADATA | EXT4_FREE_BLOCKS_FORGET);
 	return retval;
 }
 
···
 	handle = ext4_journal_start(inode,
 					EXT4_DATA_TRANS_BLOCKS(inode->i_sb) +
 					EXT4_INDEX_EXTRA_TRANS_BLOCKS + 3 +
-					2 * EXT4_QUOTA_INIT_BLOCKS(inode->i_sb)
+					EXT4_MAXQUOTAS_INIT_BLOCKS(inode->i_sb)
 					+ 1);
 	if (IS_ERR(handle)) {
 		retval = PTR_ERR(handle);

fs/ext4/move_extent.c

···
 mext_next_extent(struct inode *inode, struct ext4_ext_path *path,
 		      struct ext4_extent **extent)
 {
+	struct ext4_extent_header *eh;
 	int ppos, leaf_ppos = path->p_depth;
 
 	ppos = leaf_ppos;
 	if (EXT_LAST_EXTENT(path[ppos].p_hdr) > path[ppos].p_ext) {
 		/* leaf block */
 		*extent = ++path[ppos].p_ext;
+		path[ppos].p_block = ext_pblock(path[ppos].p_ext);
 		return 0;
 	}
 
···
 					ext_block_hdr(path[cur_ppos+1].p_bh);
 			}
 
+			path[leaf_ppos].p_ext = *extent = NULL;
+
+			eh = path[leaf_ppos].p_hdr;
+			if (le16_to_cpu(eh->eh_entries) == 0)
+				/* empty leaf is found */
+				return -ENODATA;
+
 			/* leaf block */
 			path[leaf_ppos].p_ext = *extent =
 				EXT_FIRST_EXTENT(path[leaf_ppos].p_hdr);
+			path[leaf_ppos].p_block =
+					ext_pblock(path[leaf_ppos].p_ext);
 			return 0;
 		}
 	}
···
 }
 
 /**
- * mext_double_down_read - Acquire two inodes' read semaphore
+ * double_down_write_data_sem - Acquire two inodes' write lock of i_data_sem
  *
  * @orig_inode:		original inode structure
  * @donor_inode:	donor inode structure
- * Acquire read semaphore of the two inodes (orig and donor) by i_ino order.
+ * Acquire write lock of i_data_sem of the two inodes (orig and donor) by
+ * i_ino order.
  */
 static void
-mext_double_down_read(struct inode *orig_inode, struct inode *donor_inode)
-{
-	struct inode *first = orig_inode, *second = donor_inode;
-
-	/*
-	 * Use the inode number to provide the stable locking order instead
-	 * of its address, because the C language doesn't guarantee you can
-	 * compare pointers that don't come from the same array.
-	 */
-	if (donor_inode->i_ino < orig_inode->i_ino) {
-		first = donor_inode;
-		second = orig_inode;
-	}
-
-	down_read(&EXT4_I(first)->i_data_sem);
-	down_read(&EXT4_I(second)->i_data_sem);
-}
-
-/**
- * mext_double_down_write - Acquire two inodes' write semaphore
- *
- * @orig_inode:		original inode structure
- * @donor_inode:	donor inode structure
- * Acquire write semaphore of the two inodes (orig and donor) by i_ino order.
- */
-static void
-mext_double_down_write(struct inode *orig_inode, struct inode *donor_inode)
+double_down_write_data_sem(struct inode *orig_inode, struct inode *donor_inode)
 {
 	struct inode *first = orig_inode, *second = donor_inode;
 
···
 	}
 
 	down_write(&EXT4_I(first)->i_data_sem);
-	down_write(&EXT4_I(second)->i_data_sem);
+	down_write_nested(&EXT4_I(second)->i_data_sem, SINGLE_DEPTH_NESTING);
 }
 
 /**
- * mext_double_up_read - Release two inodes' read semaphore
+ * double_up_write_data_sem - Release two inodes' write lock of i_data_sem
  *
  * @orig_inode:		original inode structure to be released its lock first
  * @donor_inode:	donor inode structure to be released its lock second
- * Release read semaphore of two inodes (orig and donor).
+ * Release write lock of i_data_sem of two inodes (orig and donor).
  */
 static void
-mext_double_up_read(struct inode *orig_inode, struct inode *donor_inode)
-{
-	up_read(&EXT4_I(orig_inode)->i_data_sem);
-	up_read(&EXT4_I(donor_inode)->i_data_sem);
-}
-
-/**
- * mext_double_up_write - Release two inodes' write semaphore
- *
- * @orig_inode:		original inode structure to be released its lock first
- * @donor_inode:	donor inode structure to be released its lock second
- * Release write semaphore of two inodes (orig and donor).
- */
-static void
-mext_double_up_write(struct inode *orig_inode, struct inode *donor_inode)
+double_up_write_data_sem(struct inode *orig_inode, struct inode *donor_inode)
 {
 	up_write(&EXT4_I(orig_inode)->i_data_sem);
 	up_write(&EXT4_I(donor_inode)->i_data_sem);
···
  * @tmp_oext:		the extent that will belong to the donor inode
  * @orig_off:		block offset of original inode
  * @donor_off:		block offset of donor inode
- * @max_count:		the maximun length of extents
+ * @max_count:		the maximum length of extents
  *
  * Return 0 on success, or a negative error value on failure.
  */
···
  * @donor_inode:	donor inode
  * @from:		block offset of orig_inode
  * @count:		block count to be replaced
+ * @err:		pointer to save return value
  *
  * Replace original inode extents and donor inode extents page by page.
  * We implement this replacement in the following three steps:
···
  * 3. Change the block information of donor inode to point at the saved
  *    original inode blocks in the dummy extents.
  *
- * Return 0 on success, or a negative error value on failure.
+ * Return replaced block count.
  */
 static int
 mext_replace_branches(handle_t *handle, struct inode *orig_inode,
 			   struct inode *donor_inode, ext4_lblk_t from,
-			   ext4_lblk_t count)
+			   ext4_lblk_t count, int *err)
 {
 	struct ext4_ext_path *orig_path = NULL;
 	struct ext4_ext_path *donor_path = NULL;
 	struct ext4_extent *oext, *dext;
 	struct ext4_extent tmp_dext, tmp_oext;
 	ext4_lblk_t orig_off = from, donor_off = from;
-	int err = 0;
 	int depth;
 	int replaced_count = 0;
 	int dext_alen;
 
-	mext_double_down_write(orig_inode, donor_inode);
+	/* Protect extent trees against block allocations via delalloc */
+	double_down_write_data_sem(orig_inode, donor_inode);
 
 	/* Get the original extent for the block "orig_off" */
-	err = get_ext_path(orig_inode, orig_off, &orig_path);
-	if (err)
+	*err = get_ext_path(orig_inode, orig_off, &orig_path);
+	if (*err)
 		goto out;
 
 	/* Get the donor extent for the head */
-	err = get_ext_path(donor_inode, donor_off, &donor_path);
-	if (err)
+	*err = get_ext_path(donor_inode, donor_off, &donor_path);
+	if (*err)
 		goto out;
 	depth = ext_depth(orig_inode);
 	oext = orig_path[depth].p_ext;
···
 	dext = donor_path[depth].p_ext;
 	tmp_dext = *dext;
 
-	err = mext_calc_swap_extents(&tmp_dext, &tmp_oext, orig_off,
+	*err = mext_calc_swap_extents(&tmp_dext, &tmp_oext, orig_off,
 				      donor_off, count);
-	if (err)
+	if (*err)
 		goto out;
 
 	/* Loop for the donor extents */
···
 		if (!dext) {
 			ext4_error(donor_inode->i_sb, __func__,
 				   "The extent for donor must be found");
-			err = -EIO;
+			*err = -EIO;
 			goto out;
 		} else if (donor_off != le32_to_cpu(tmp_dext.ee_block)) {
 			ext4_error(donor_inode->i_sb, __func__,
···
 				"extent(%u) should be equal",
 				donor_off,
 				le32_to_cpu(tmp_dext.ee_block));
-			err = -EIO;
+			*err = -EIO;
 			goto out;
 		}
 
 		/* Set donor extent to orig extent */
-		err = mext_leaf_block(handle, orig_inode,
+		*err = mext_leaf_block(handle, orig_inode,
 					   orig_path, &tmp_dext, &orig_off);
-		if (err < 0)
+		if (*err)
 			goto out;
 
 		/* Set orig extent to donor extent */
-		err = mext_leaf_block(handle, donor_inode,
+		*err = mext_leaf_block(handle, donor_inode,
 					   donor_path, &tmp_oext, &donor_off);
-		if (err < 0)
+		if (*err)
 			goto out;
 
 		dext_alen = ext4_ext_get_actual_len(&tmp_dext);
···
 
 		if (orig_path)
 			ext4_ext_drop_refs(orig_path);
-		err = get_ext_path(orig_inode, orig_off, &orig_path);
-		if (err)
+		*err = get_ext_path(orig_inode, orig_off, &orig_path);
+		if (*err)
 			goto out;
 		depth = ext_depth(orig_inode);
 		oext = orig_path[depth].p_ext;
-		if (le32_to_cpu(oext->ee_block) +
-				ext4_ext_get_actual_len(oext) <= orig_off) {
-			err = 0;
-			goto out;
-		}
 		tmp_oext = *oext;
 
 		if (donor_path)
 			ext4_ext_drop_refs(donor_path);
-		err = get_ext_path(donor_inode, donor_off, &donor_path);
-		if (err)
+		*err = get_ext_path(donor_inode, donor_off, &donor_path);
+		if (*err)
 			goto out;
 		depth = ext_depth(donor_inode);
 		dext = donor_path[depth].p_ext;
-		if (le32_to_cpu(dext->ee_block) +
-				ext4_ext_get_actual_len(dext) <= donor_off) {
-			err = 0;
-			goto out;
-		}
 		tmp_dext = *dext;
 
-		err = mext_calc_swap_extents(&tmp_dext, &tmp_oext, orig_off,
+		*err = mext_calc_swap_extents(&tmp_dext, &tmp_oext, orig_off,
 					   donor_off, count - replaced_count);
-		if (err)
+		if (*err)
 			goto out;
 	}
 
···
 		kfree(donor_path);
 	}
 
-	mext_double_up_write(orig_inode, donor_inode);
-	return err;
+	ext4_ext_invalidate_cache(orig_inode);
+	ext4_ext_invalidate_cache(donor_inode);
+
+	double_up_write_data_sem(orig_inode, donor_inode);
+
+	return replaced_count;
 }
 
 /**
···
  * @data_offset_in_page:	block index where data swapping starts
  * @block_len_in_page:		the number of blocks to be swapped
  * @uninit:			orig extent is uninitialized or not
+ * @err:			pointer to save return value
  *
  * Save the data in original inode blocks and replace original inode extents
  * with donor inode extents by calling mext_replace_branches().
- * Finally, write out the saved data in new original inode blocks. Return 0
- * on success, or a negative error value on failure.
+ * Finally, write out the saved data in new original inode blocks. Return
+ * replaced block count.
  */
 static int
 move_extent_per_page(struct file *o_filp, struct inode *donor_inode,
 		  pgoff_t orig_page_offset, int data_offset_in_page,
-		  int block_len_in_page, int uninit)
+		  int block_len_in_page, int uninit, int *err)
 {
 	struct inode *orig_inode = o_filp->f_dentry->d_inode;
 	struct address_space *mapping = orig_inode->i_mapping;
···
 	long long offs = orig_page_offset << PAGE_CACHE_SHIFT;
 	unsigned long blocksize = orig_inode->i_sb->s_blocksize;
 	unsigned int w_flags = 0;
-	unsigned int tmp_data_len, data_len;
+	unsigned int tmp_data_size, data_size, replaced_size;
 	void *fsdata;
-	int ret, i, jblocks;
+	int i, jblocks;
+	int err2 = 0;
+	int replaced_count = 0;
 	int blocks_per_page = PAGE_CACHE_SIZE >> orig_inode->i_blkbits;
 
 	/*
···
 	jblocks = ext4_writepage_trans_blocks(orig_inode) * 2;
 	handle = ext4_journal_start(orig_inode, jblocks);
 	if (IS_ERR(handle)) {
-		ret = PTR_ERR(handle);
-		return ret;
+		*err = PTR_ERR(handle);
+		return 0;
 	}
 
 	if (segment_eq(get_fs(), KERNEL_DS))
···
 	 * Just swap data blocks between orig and donor.
 	 */
 	if (uninit) {
-		ret = mext_replace_branches(handle, orig_inode,
-						 donor_inode, orig_blk_offset,
-						 block_len_in_page);
-
-		/* Clear the inode cache not to refer to the old data */
-		ext4_ext_invalidate_cache(orig_inode);
-		ext4_ext_invalidate_cache(donor_inode);
+		replaced_count = mext_replace_branches(handle, orig_inode,
+						donor_inode, orig_blk_offset,
+						block_len_in_page, err);
 		goto out2;
 	}
 
 	offs = (long long)orig_blk_offset << orig_inode->i_blkbits;
 
-	/* Calculate data_len */
+	/* Calculate data_size */
 	if ((orig_blk_offset + block_len_in_page - 1) ==
 	    ((orig_inode->i_size - 1) >> orig_inode->i_blkbits)) {
 		/* Replace the last block */
-		tmp_data_len = orig_inode->i_size & (blocksize - 1);
+		tmp_data_size = orig_inode->i_size & (blocksize - 1);
 		/*
-		 * If data_len equal zero, it shows data_len is multiples of
+		 * If data_size equal zero, it shows data_size is multiples of
 		 * blocksize. So we set appropriate value.
 		 */
-		if (tmp_data_len == 0)
-			tmp_data_len = blocksize;
+		if (tmp_data_size == 0)
+			tmp_data_size = blocksize;
 
-		data_len = tmp_data_len +
+		data_size = tmp_data_size +
 			((block_len_in_page - 1) << orig_inode->i_blkbits);
-	} else {
-		data_len = block_len_in_page << orig_inode->i_blkbits;
-	}
+	} else
+		data_size = block_len_in_page << orig_inode->i_blkbits;
 
-	ret = a_ops->write_begin(o_filp, mapping, offs, data_len, w_flags,
+	replaced_size = data_size;
+
+	*err = a_ops->write_begin(o_filp, mapping, offs, data_size, w_flags,
 				 &page, &fsdata);
-	if (unlikely(ret < 0))
+	if (unlikely(*err < 0))
 		goto out;
 
 	if (!PageUptodate(page)) {
···
 	/* Release old bh and drop refs */
 	try_to_release_page(page, 0);
 
-	ret = mext_replace_branches(handle, orig_inode, donor_inode,
-					 orig_blk_offset, block_len_in_page);
-	if (ret < 0)
-		goto out;
-
-	/* Clear the inode cache not to refer to the old data */
-	ext4_ext_invalidate_cache(orig_inode);
-	ext4_ext_invalidate_cache(donor_inode);
+	replaced_count = mext_replace_branches(handle, orig_inode, donor_inode,
+					orig_blk_offset, block_len_in_page,
+					&err2);
+	if (err2) {
+		if (replaced_count) {
+			block_len_in_page = replaced_count;
+			replaced_size =
+				block_len_in_page << orig_inode->i_blkbits;
+		} else
+			goto out;
+	}
 
 	if (!page_has_buffers(page))
 		create_empty_buffers(page, 1 << orig_inode->i_blkbits, 0);
···
 		bh = bh->b_this_page;
 
 	for (i = 0; i < block_len_in_page; i++) {
-		ret = ext4_get_block(orig_inode,
+		*err = ext4_get_block(orig_inode,
 				(sector_t)(orig_blk_offset + i), bh, 0);
-		if (ret < 0)
+		if (*err < 0)
 			goto out;
 
 		if (bh->b_this_page != NULL)
 			bh = bh->b_this_page;
 	}
 
-	ret = a_ops->write_end(o_filp, mapping, offs, data_len, data_len,
+	*err = a_ops->write_end(o_filp, mapping, offs, data_size, replaced_size,
 			       page, fsdata);
 	page = NULL;
 
···
 out2:
 	ext4_journal_stop(handle);
 
-	return ret < 0 ? ret : 0;
+	if (err2)
+		*err = err2;
+
+	return replaced_count;
 }
 
 /**
···
  * @orig_start:		logical start offset in block for orig
  * @donor_start:	logical start offset in block for donor
  * @len:		the number of blocks to be moved
- * @moved_len:		moved block length
  *
  * Check the arguments of ext4_move_extents() whether the files can be
  * exchanged with each other.
···
  */
 static int
 mext_check_arguments(struct inode *orig_inode,
-			  struct inode *donor_inode, __u64 orig_start,
-			  __u64 donor_start, __u64 *len, __u64 moved_len)
+		     struct inode *donor_inode, __u64 orig_start,
+		     __u64 donor_start, __u64 *len)
 {
 	ext4_lblk_t orig_blocks, donor_blocks;
 	unsigned int blkbits = orig_inode->i_blkbits;
···
 		ext4_debug("ext4 move extent: The argument files should be "
 			"regular file [ino:orig %lu, donor %lu]\n",
 			orig_inode->i_ino, donor_inode->i_ino);
+		return -EINVAL;
+	}
+
+	if (donor_inode->i_mode & (S_ISUID|S_ISGID)) {
+		ext4_debug("ext4 move extent: suid or sgid is set"
+			   " to donor file [ino:orig %lu, donor %lu]\n",
+			   orig_inode->i_ino, donor_inode->i_ino);
 		return -EINVAL;
 	}
 
···
 		ext4_debug("ext4 move extent: orig and donor's start "
 			"offset are not same [ino:orig %lu, donor %lu]\n",
 			orig_inode->i_ino, donor_inode->i_ino);
-		return -EINVAL;
-	}
-
-	if (moved_len) {
-		ext4_debug("ext4 move extent: moved_len should be 0 "
-			"[ino:orig %lu, donor %lu]\n", orig_inode->i_ino,
-			donor_inode->i_ino);
 		return -EINVAL;
 	}
 
···
 	}
 
 	if (!*len) {
-		ext4_debug("ext4 move extent: len shoudld not be 0 "
+		ext4_debug("ext4 move extent: len should not be 0 "
 			"[ino:orig %lu, donor %lu]\n", orig_inode->i_ino,
 			donor_inode->i_ino);
 		return -EINVAL;
···
 		return -EINVAL;
 	}
 
-	/* protect orig and donor against a truncate */
+	/* Protect orig and donor inodes against a truncate */
 	ret1 = mext_inode_double_lock(orig_inode, donor_inode);
 	if (ret1 < 0)
 		return ret1;
 
-	mext_double_down_read(orig_inode, donor_inode);
+	/* Protect extent tree against block allocations via delalloc */
+	double_down_write_data_sem(orig_inode, donor_inode);
 	/* Check the filesystem environment whether move_extent can be done */
 	ret1 = mext_check_arguments(orig_inode, donor_inode, orig_start,
-					donor_start, &len, *moved_len);
-	mext_double_up_read(orig_inode, donor_inode);
+				    donor_start, &len);
 	if (ret1)
 		goto out;
 
···
 		seq_start = le32_to_cpu(ext_cur->ee_block);
 		rest_blocks = seq_blocks;
 
-		/* Discard preallocations of two inodes */
-		down_write(&EXT4_I(orig_inode)->i_data_sem);
-		ext4_discard_preallocations(orig_inode);
-		up_write(&EXT4_I(orig_inode)->i_data_sem);
-
-		down_write(&EXT4_I(donor_inode)->i_data_sem);
-		ext4_discard_preallocations(donor_inode);
-		up_write(&EXT4_I(donor_inode)->i_data_sem);
+		/*
+		 * Up semaphore to avoid following problems:
+		 * a. transaction deadlock among ext4_journal_start,
+		 *    ->write_begin via pagefault, and jbd2_journal_commit
+		 * b. racing with ->readpage, ->write_begin, and ext4_get_block
+		 *    in move_extent_per_page
+		 */
+		double_up_write_data_sem(orig_inode, donor_inode);
 
 		while (orig_page_offset <= seq_end_page) {
 
 			/* Swap original branches with new branches */
-			ret1 = move_extent_per_page(o_filp, donor_inode,
+			block_len_in_page = move_extent_per_page(
+						o_filp, donor_inode,
 						orig_page_offset,
 						data_offset_in_page,
-						block_len_in_page, uninit);
-			if (ret1 < 0)
-				goto out;
-			orig_page_offset++;
+						block_len_in_page, uninit,
+						&ret1);
+
 			/* Count how many blocks we have exchanged */
 			*moved_len += block_len_in_page;
+			if (ret1 < 0)
+				break;
 			if (*moved_len > len) {
 				ext4_error(orig_inode->i_sb, __func__,
 					"We replaced blocks too much! "
 					"sum of replaced: %llu requested: %llu",
 					*moved_len, len);
 				ret1 = -EIO;
-				goto out;
+				break;
 			}
 
+			orig_page_offset++;
 			data_offset_in_page = 0;
 			rest_blocks -= block_len_in_page;
 			if (rest_blocks > blocks_per_page)
···
 			else
 				block_len_in_page = rest_blocks;
 		}
+
+		double_down_write_data_sem(orig_inode, donor_inode);
+		if (ret1 < 0)
+			break;
 
 		/* Decrease buffer counter */
 		if (holecheck_path)
···
 
 	}
 out:
+	if (*moved_len) {
+		ext4_discard_preallocations(orig_inode);
+		ext4_discard_preallocations(donor_inode);
+	}
+
 	if (orig_path) {
 		ext4_ext_drop_refs(orig_path);
 		kfree(orig_path);
···
 		ext4_ext_drop_refs(holecheck_path);
 		kfree(holecheck_path);
 	}
-
+	double_up_write_data_sem(orig_inode, donor_inode);
 	ret2 = mext_inode_double_unlock(orig_inode, donor_inode);
 
 	if (ret1)

fs/ext4/namei.c

···
  * add_dirent_to_buf will attempt search the directory block for
  * space.  It will return -ENOSPC if no space is available, and -EIO
  * and -EEXIST if directory entry already exists.
- *
- * NOTE!  bh is NOT released in the case where ENOSPC is returned.  In
- * all other cases bh is released.
  */
 static int add_dirent_to_buf(handle_t *handle, struct dentry *dentry,
 			     struct inode *inode, struct ext4_dir_entry_2 *de,
···
 		top = bh->b_data + blocksize - reclen;
 		while ((char *) de <= top) {
 			if (!ext4_check_dir_entry("ext4_add_entry", dir, de,
-						  bh, offset)) {
-				brelse(bh);
+						  bh, offset))
 				return -EIO;
-			}
-			if (ext4_match(namelen, name, de)) {
-				brelse(bh);
+			if (ext4_match(namelen, name, de))
 				return -EEXIST;
-			}
 			nlen = EXT4_DIR_REC_LEN(de->name_len);
 			rlen = ext4_rec_len_from_disk(de->rec_len, blocksize);
 			if ((de->inode? rlen - nlen: rlen) >= reclen)
···
 	err = ext4_journal_get_write_access(handle, bh);
 	if (err) {
 		ext4_std_error(dir->i_sb, err);
-		brelse(bh);
 		return err;
 	}
 
···
 	err = ext4_handle_dirty_metadata(handle, dir, bh);
 	if (err)
 		ext4_std_error(dir->i_sb, err);
-	brelse(bh);
 	return 0;
 }
 
···
 	if (!(de))
 		return retval;
 
-	return add_dirent_to_buf(handle, dentry, inode, de, bh);
+	retval = add_dirent_to_buf(handle, dentry, inode, de, bh);
+	brelse(bh);
+	return retval;
 }
 
 /*
···
 		if(!bh)
 			return retval;
 		retval = add_dirent_to_buf(handle, dentry, inode, NULL, bh);
-		if (retval != -ENOSPC)
+		if (retval != -ENOSPC) {
+			brelse(bh);
 			return retval;
+		}
 
 		if (blocks == 1 && !dx_fallback &&
 		    EXT4_HAS_COMPAT_FEATURE(sb, EXT4_FEATURE_COMPAT_DIR_INDEX))
···
 	de = (struct ext4_dir_entry_2 *) bh->b_data;
 	de->inode = 0;
 	de->rec_len = ext4_rec_len_to_disk(blocksize, blocksize);
-	return add_dirent_to_buf(handle, dentry, inode, de, bh);
+	retval = add_dirent_to_buf(handle, dentry, inode, de, bh);
+	brelse(bh);
+	return retval;
 }
 
 /*
···
 		goto journal_error;
 
 	err = add_dirent_to_buf(handle, dentry, inode, NULL, bh);
-	if (err != -ENOSPC) {
-		bh = NULL;
+	if (err != -ENOSPC)
 		goto cleanup;
-	}
 
 	/* Block full, should compress but for now just split */
 	dxtrace(printk(KERN_DEBUG "using %u of %u node entries\n",
···
 	if (!de)
 		goto cleanup;
 	err = add_dirent_to_buf(handle, dentry, inode, de, bh);
-	bh = NULL;
 	goto cleanup;
 
 journal_error:
···
 retry:
 	handle = ext4_journal_start(dir, EXT4_DATA_TRANS_BLOCKS(dir->i_sb) +
 					EXT4_INDEX_EXTRA_TRANS_BLOCKS + 3 +
-					2*EXT4_QUOTA_INIT_BLOCKS(dir->i_sb));
+					EXT4_MAXQUOTAS_INIT_BLOCKS(dir->i_sb));
 	if (IS_ERR(handle))
 		return PTR_ERR(handle);
 
···
 retry:
 	handle = ext4_journal_start(dir, EXT4_DATA_TRANS_BLOCKS(dir->i_sb) +
 					EXT4_INDEX_EXTRA_TRANS_BLOCKS + 3 +
-					2*EXT4_QUOTA_INIT_BLOCKS(dir->i_sb));
+					EXT4_MAXQUOTAS_INIT_BLOCKS(dir->i_sb));
 	if (IS_ERR(handle))
 		return PTR_ERR(handle);
 
···
 retry:
 	handle = ext4_journal_start(dir, EXT4_DATA_TRANS_BLOCKS(dir->i_sb) +
 					EXT4_INDEX_EXTRA_TRANS_BLOCKS + 3 +
-					2*EXT4_QUOTA_INIT_BLOCKS(dir->i_sb));
+					EXT4_MAXQUOTAS_INIT_BLOCKS(dir->i_sb));
 	if (IS_ERR(handle))
 		return PTR_ERR(handle);
 
···
 retry:
 	handle = ext4_journal_start(dir, EXT4_DATA_TRANS_BLOCKS(dir->i_sb) +
 					EXT4_INDEX_EXTRA_TRANS_BLOCKS + 5 +
-					2*EXT4_QUOTA_INIT_BLOCKS(dir->i_sb));
+					EXT4_MAXQUOTAS_INIT_BLOCKS(dir->i_sb));
 	if (IS_ERR(handle))
 		return PTR_ERR(handle);
 

fs/ext4/resize.c

···
 			goto exit_bh;
 
 		if (IS_ERR(gdb = bclean(handle, sb, block))) {
-			err = PTR_ERR(bh);
+			err = PTR_ERR(gdb);
 			goto exit_bh;
 		}
 		ext4_handle_dirty_metadata(handle, NULL, gdb);

fs/ext4/super.c

···
 	if (sb->s_dirt)
 		ext4_commit_super(sb, 1);
 
-	ext4_release_system_zone(sb);
-	ext4_mb_release(sb);
-	ext4_ext_release(sb);
-	ext4_xattr_put_super(sb);
 	if (sbi->s_journal) {
 		err = jbd2_journal_destroy(sbi->s_journal);
 		sbi->s_journal = NULL;
···
 			ext4_abort(sb, __func__,
 				   "Couldn't clean up the journal");
 	}
+
+	ext4_release_system_zone(sb);
+	ext4_mb_release(sb);
+	ext4_ext_release(sb);
+	ext4_xattr_put_super(sb);
+
 	if (!(sb->s_flags & MS_RDONLY)) {
 		EXT4_CLEAR_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_RECOVER);
 		es->s_state = cpu_to_le16(sbi->s_mount_state);
···
 	spin_lock_init(&(ei->i_block_reservation_lock));
 	INIT_LIST_HEAD(&ei->i_aio_dio_complete_list);
 	ei->cur_aio_dio = NULL;
+	ei->i_sync_tid = 0;
+	ei->i_datasync_tid = 0;
 
 	return &ei->vfs_inode;
 }
···
 	if (test_opt(sb, NO_AUTO_DA_ALLOC))
 		seq_puts(seq, ",noauto_da_alloc");
 
+	if (test_opt(sb, DISCARD))
+		seq_puts(seq, ",discard");
+
+	if (test_opt(sb, NOLOAD))
+		seq_puts(seq, ",norecovery");
+
 	ext4_show_quota_options(seq, sb);
 
 	return 0;
···
 	Opt_usrquota, Opt_grpquota, Opt_i_version,
 	Opt_stripe, Opt_delalloc, Opt_nodelalloc,
 	Opt_block_validity, Opt_noblock_validity,
-	Opt_inode_readahead_blks, Opt_journal_ioprio
+	Opt_inode_readahead_blks, Opt_journal_ioprio,
+	Opt_discard, Opt_nodiscard,
 };
 
 static const match_table_t tokens = {
···
 	{Opt_acl, "acl"},
 	{Opt_noacl, "noacl"},
 	{Opt_noload, "noload"},
+	{Opt_noload, "norecovery"},
 	{Opt_nobh, "nobh"},
 	{Opt_bh, "bh"},
 	{Opt_commit, "commit=%u"},
···
 	{Opt_auto_da_alloc, "auto_da_alloc=%u"},
 	{Opt_auto_da_alloc, "auto_da_alloc"},
 	{Opt_noauto_da_alloc, "noauto_da_alloc"},
+	{Opt_discard, "discard"},
+	{Opt_nodiscard, "nodiscard"},
 	{Opt_err, NULL},
 };
 
···
 			else
 				set_opt(sbi->s_mount_opt,NO_AUTO_DA_ALLOC);
 			break;
+		case Opt_discard:
+			set_opt(sbi->s_mount_opt, DISCARD);
+			break;
+		case Opt_nodiscard:
+			clear_opt(sbi->s_mount_opt, DISCARD);
+			break;
 		default:
 			ext4_msg(sb, KERN_ERR,
 			       "Unrecognized mount option \"%s\" "
···
 	size_t size;
 	int i;
 
-	if (!sbi->s_es->s_log_groups_per_flex) {
+	sbi->s_log_groups_per_flex = sbi->s_es->s_log_groups_per_flex;
+	groups_per_flex = 1 << sbi->s_log_groups_per_flex;
+
+	if (groups_per_flex < 2) {
 		sbi->s_log_groups_per_flex = 0;
 		return 1;
 	}
-
-	sbi->s_log_groups_per_flex = sbi->s_es->s_log_groups_per_flex;
-	groups_per_flex = 1 << sbi->s_log_groups_per_flex;
 
 	/* We allocate both existing and potentially added groups */
 	flex_group_count = ((sbi->s_groups_count + groups_per_flex - 1) +
···
 	    EXT4_HAS_COMPAT_FEATURE(sb, EXT4_FEATURE_COMPAT_HAS_JOURNAL)) {
 		if (ext4_load_journal(sb, es, journal_devnum))
 			goto failed_mount3;
-		if (!(sb->s_flags & MS_RDONLY) &&
-		    EXT4_SB(sb)->s_journal->j_failed_commit) {
-			ext4_msg(sb, KERN_CRIT, "error: "
-			       "ext4_fill_super: Journal transaction "
-			       "%u is corrupt",
-			       EXT4_SB(sb)->s_journal->j_failed_commit);
-			if (test_opt(sb, ERRORS_RO)) {
-				ext4_msg(sb, KERN_CRIT,
-				       "Mounting filesystem read-only");
-				sb->s_flags |= MS_RDONLY;
-				EXT4_SB(sb)->s_mount_state |= EXT4_ERROR_FS;
-				es->s_state |= cpu_to_le16(EXT4_ERROR_FS);
-			}
-			if (test_opt(sb, ERRORS_PANIC)) {
-				EXT4_SB(sb)->s_mount_state |= EXT4_ERROR_FS;
-				es->s_state |= cpu_to_le16(EXT4_ERROR_FS);
-				ext4_commit_super(sb, 1);
-				goto failed_mount4;
-			}
-		}
 	} else if (test_opt(sb, NOLOAD) && !(sb->s_flags & MS_RDONLY) &&
 	      EXT4_HAS_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_RECOVER)) {
 		ext4_msg(sb, KERN_ERR, "required journal recovery "
···
 	buf->f_blocks = ext4_blocks_count(es) - sbi->s_overhead_last;
 	buf->f_bfree = percpu_counter_sum_positive(&sbi->s_freeblocks_counter) -
 		       percpu_counter_sum_positive(&sbi->s_dirtyblocks_counter);
-	ext4_free_blocks_count_set(es, buf->f_bfree);
 	buf->f_bavail = buf->f_bfree - ext4_r_blocks_count(es);
 	if (buf->f_bfree < ext4_r_blocks_count(es))
 		buf->f_bavail = 0;
 	buf->f_files = le32_to_cpu(es->s_inodes_count);
 	buf->f_ffree = percpu_counter_sum_positive(&sbi->s_freeinodes_counter);
-	es->s_free_inodes_count = cpu_to_le32(buf->f_ffree);
 	buf->f_namelen = EXT4_NAME_LEN;
 	fsid = le64_to_cpup((void *)es->s_uuid) ^
 	       le64_to_cpup((void *)es->s_uuid + sizeof(u64));
···
 	return get_sb_bdev(fs_type, flags, dev_name, data, ext4_fill_super,mnt);
 }
 
+#if !defined(CONTIG_EXT2_FS) && !defined(CONFIG_EXT2_FS_MODULE) && defined(CONFIG_EXT4_USE_FOR_EXT23)
+static struct file_system_type ext2_fs_type = {
+	.owner		= THIS_MODULE,
+	.name		= "ext2",
+	.get_sb		= ext4_get_sb,
+	.kill_sb	= kill_block_super,
+	.fs_flags	= FS_REQUIRES_DEV,
+};
+
+static inline void register_as_ext2(void)
+{
+	int err = register_filesystem(&ext2_fs_type);
+	if (err)
+		printk(KERN_WARNING
+		       "EXT4-fs: Unable to register as ext2 (%d)\n", err);
+}
+
+static inline void unregister_as_ext2(void)
+{
+	unregister_filesystem(&ext2_fs_type);
+}
+#else
+static inline void register_as_ext2(void) { }
+static inline void unregister_as_ext2(void) { }
+#endif
+
+#if !defined(CONTIG_EXT3_FS) && !defined(CONFIG_EXT3_FS_MODULE) && defined(CONFIG_EXT4_USE_FOR_EXT23)
+static struct file_system_type ext3_fs_type = {
+	.owner		= THIS_MODULE,
+	.name		= "ext3",
+	.get_sb		= ext4_get_sb,
+	.kill_sb	= kill_block_super,
+	.fs_flags	= FS_REQUIRES_DEV,
+};
+
+static inline void register_as_ext3(void)
+{
+	int err = register_filesystem(&ext3_fs_type);
+	if (err)
+		printk(KERN_WARNING
+		       "EXT4-fs: Unable to register as ext3 (%d)\n", err);
+}
+
+static inline void unregister_as_ext3(void)
+{
+	unregister_filesystem(&ext3_fs_type);
+}
+#else
+static inline void register_as_ext3(void) { }
+static inline void unregister_as_ext3(void) { }
+#endif
+
 static struct file_system_type ext4_fs_type = {
 	.owner		= THIS_MODULE,
 	.name		= "ext4",
···
 	err = init_inodecache();
 	if (err)
 		goto out1;
+	register_as_ext2();
+	register_as_ext3();
 	err = register_filesystem(&ext4_fs_type);
 	if (err)
 		goto out;
 	return 0;
 out:
+	unregister_as_ext2();
+	unregister_as_ext3();
 	destroy_inodecache();
 out1:
 	exit_ext4_xattr();
···
 
 static void __exit exit_ext4_fs(void)
 {
+	unregister_as_ext2();
+	unregister_as_ext3();
 	unregister_filesystem(&ext4_fs_type);
 	destroy_inodecache();
 	exit_ext4_xattr();

fs/ext4/xattr.c

···
 		ea_bdebug(bh, "refcount now=0; freeing");
 		if (ce)
 			mb_cache_entry_free(ce);
-		ext4_free_blocks(handle, inode, bh->b_blocknr, 1, 1);
 		get_bh(bh);
-		ext4_forget(handle, 1, inode, bh, bh->b_blocknr);
+		ext4_free_blocks(handle, inode, bh, 0, 1,
+				 EXT4_FREE_BLOCKS_METADATA |
+				 EXT4_FREE_BLOCKS_FORGET);
 	} else {
 		le32_add_cpu(&BHDR(bh)->h_refcount, -1);
 		error = ext4_handle_dirty_metadata(handle, inode, bh);
···
 			new_bh = sb_getblk(sb, block);
 			if (!new_bh) {
 getblk_failed:
-				ext4_free_blocks(handle, inode, block, 1, 1);
+				ext4_free_blocks(handle, inode, 0, block, 1,
+						 EXT4_FREE_BLOCKS_METADATA);
 				error = -EIO;
 				goto cleanup;
 			}
···
 	if (error)
 		goto cleanup;
 
+	error = ext4_journal_get_write_access(handle, is.iloc.bh);
+	if (error)
+		goto cleanup;
+
 	if (EXT4_I(inode)->i_state & EXT4_STATE_NEW) {
 		struct ext4_inode *raw_inode = ext4_raw_inode(&is.iloc);
 		memset(raw_inode, 0, EXT4_SB(inode->i_sb)->s_inode_size);
···
 		if (flags & XATTR_CREATE)
 			goto cleanup;
 	}
-	error = ext4_journal_get_write_access(handle, is.iloc.bh);
-	if (error)
-		goto cleanup;
 	if (!value) {
 		if (!is.s.not_found)
 			error = ext4_xattr_ibody_set(handle, inode, &i, &is);

fs/jbd2/commit.c

···
 		JBUFFER_TRACE(jh, "ph3: write metadata");
 		flags = jbd2_journal_write_metadata_buffer(commit_transaction,
 						      jh, &new_jh, blocknr);
+		if (flags < 0) {
+			jbd2_journal_abort(journal, flags);
+			continue;
+		}
 		set_bit(BH_JWrite, &jh2bh(new_jh)->b_state);
 		wbuf[bufs++] = jh2bh(new_jh);
 

fs/jbd2/journal.c

···
 EXPORT_SYMBOL(jbd2_journal_ack_err);
 EXPORT_SYMBOL(jbd2_journal_clear_err);
 EXPORT_SYMBOL(jbd2_log_wait_commit);
+EXPORT_SYMBOL(jbd2_log_start_commit);
 EXPORT_SYMBOL(jbd2_journal_start_commit);
 EXPORT_SYMBOL(jbd2_journal_force_commit_nested);
 EXPORT_SYMBOL(jbd2_journal_wipe);
···
 
 		jbd_unlock_bh_state(bh_in);
 		tmp = jbd2_alloc(bh_in->b_size, GFP_NOFS);
+		if (!tmp) {
+			jbd2_journal_put_journal_head(new_jh);
+			return -ENOMEM;
+		}
 		jbd_lock_bh_state(bh_in);
 		if (jh_in->b_frozen_data) {
 			jbd2_free(tmp, bh_in->b_size);
···
 	 * data from the journal. */
 	if (jbd2_journal_recover(journal))
 		goto recovery_error;
+
+	if (journal->j_failed_commit) {
+		printk(KERN_ERR "JBD2: journal transaction %u on %s "
+		       "is corrupt.\n", journal->j_failed_commit,
+		       journal->j_devname);
+		return -EIO;
+	}
 
 	/* OK, we've finished with the dynamic journal bits:
 	 * reinitialise the dynamic contents of the superblock in memory

include/trace/events/ext4.h

···
 		__entry->blocks	= inode->i_blocks;
 	),
 
-	TP_printk("dev %s ino %lu mode %d uid %u gid %u blocks %llu",
+	TP_printk("dev %s ino %lu mode 0%o uid %u gid %u blocks %llu",
 		  jbd2_dev_to_name(__entry->dev), (unsigned long) __entry->ino,
 		  __entry->mode, __entry->uid, __entry->gid,
 		  (unsigned long long) __entry->blocks)
···
 		__entry->mode	= mode;
 	),
 
-	TP_printk("dev %s dir %lu mode %d",
+	TP_printk("dev %s dir %lu mode 0%o",
 		  jbd2_dev_to_name(__entry->dev), (unsigned long) __entry->dir,
 		  __entry->mode)
 );
···
 		__entry->mode	= mode;
 	),
 
-	TP_printk("dev %s ino %lu dir %lu mode %d",
+	TP_printk("dev %s ino %lu dir %lu mode 0%o",
 		  jbd2_dev_to_name(__entry->dev), (unsigned long) __entry->ino,
 		  (unsigned long) __entry->dir, __entry->mode)
 );
···
 		__field(	int,	ret			)
 		__field(	int,	pages_written		)
 		__field(	long,	pages_skipped		)
-		__field(	char,	encountered_congestion	)
 		__field(	char,	more_io			)	
 		__field(	char,	no_nrwrite_index_update )
 		__field(       pgoff_t,	writeback_index		)
···
 		__entry->ret		= ret;
 		__entry->pages_written	= pages_written;
 		__entry->pages_skipped	= wbc->pages_skipped;
-		__entry->encountered_congestion	= wbc->encountered_congestion;
 		__entry->more_io	= wbc->more_io;
 		__entry->no_nrwrite_index_update = wbc->no_nrwrite_index_update;
 		__entry->writeback_index = inode->i_mapping->writeback_index;
 	),
 
-	TP_printk("dev %s ino %lu ret %d pages_written %d pages_skipped %ld congestion %d more_io %d no_nrwrite_index_update %d writeback_index %lu",
+	TP_printk("dev %s ino %lu ret %d pages_written %d pages_skipped %ld more_io %d no_nrwrite_index_update %d writeback_index %lu",
 		  jbd2_dev_to_name(__entry->dev),
 		  (unsigned long) __entry->ino, __entry->ret,
 		  __entry->pages_written, __entry->pages_skipped,
-		  __entry->encountered_congestion, __entry->more_io,
+		  __entry->more_io,
 		  __entry->no_nrwrite_index_update,
 		  (unsigned long) __entry->writeback_index)
 );
···
 
 TRACE_EVENT(ext4_free_blocks,
 	TP_PROTO(struct inode *inode, __u64 block, unsigned long count,
-			int metadata),
+		 int flags),
 
-	TP_ARGS(inode, block, count, metadata),
+	TP_ARGS(inode, block, count, flags),
 
 	TP_STRUCT__entry(
 		__field(	dev_t,	dev			)
 		__field(	ino_t,	ino			)
+		__field(      umode_t, mode			)
 		__field(	__u64,	block			)
 		__field(	unsigned long,	count		)
-		__field(	int,	metadata		)
-
+		__field(	 int,	flags			)
 	),
 
 	TP_fast_assign(
 		__entry->dev		= inode->i_sb->s_dev;
 		__entry->ino		= inode->i_ino;
+		__entry->mode		= inode->i_mode;
 		__entry->block		= block;
 		__entry->count		= count;
-		__entry->metadata	= metadata;
+		__entry->flags		= flags;
 	),
 
-	TP_printk("dev %s ino %lu block %llu count %lu metadata %d",
+	TP_printk("dev %s ino %lu mode 0%o block %llu count %lu flags %d",
 		  jbd2_dev_to_name(__entry->dev), (unsigned long) __entry->ino,
-		  __entry->block, __entry->count, __entry->metadata)
+		  __entry->mode, __entry->block, __entry->count,
+		  __entry->flags)
 );
 
 TRACE_EVENT(ext4_sync_file,
···
 		  jbd2_dev_to_name(__entry->dev), (unsigned long) __entry->ino,
 		  __entry->result_group, __entry->result_start,
 		  __entry->result_len, __entry->result_logical)
+);
+
+TRACE_EVENT(ext4_forget,
+	TP_PROTO(struct inode *inode, int is_metadata, __u64 block),
+
+	TP_ARGS(inode, is_metadata, block),
+
+	TP_STRUCT__entry(
+		__field(	dev_t,	dev			)
+		__field(	ino_t,	ino			)
+		__field(	umode_t, mode			)
+		__field(	int,	is_metadata		)
+		__field(	__u64,	block			)
+	),
+
+	TP_fast_assign(
+		__entry->dev	= inode->i_sb->s_dev;
+		__entry->ino	= inode->i_ino;
+		__entry->mode	= inode->i_mode;
+		__entry->is_metadata = is_metadata;
+		__entry->block	= block;
+	),
+
+	TP_printk("dev %s ino %lu mode 0%o is_metadata %d block %llu",
+		  jbd2_dev_to_name(__entry->dev), (unsigned long) __entry->ino,
+		  __entry->mode, __entry->is_metadata, __entry->block)
 );
 
 #endif /* _TRACE_EXT4_H */