17 files changed, 704 insertions, 592 deletions

diff --git a/fs/ext4/Kconfig b/fs/ext4/Kconfig
index d5c0ea2e8f2d..9acf7e808139 100644
--- a/fs/ext4/Kconfig
+++ b/fs/ext4/Kconfig
@@ -26,19 +26,15 @@ config EXT4_FS
 
           If unsure, say N.
 
-config EXT4DEV_COMPAT
-        bool "Enable ext4dev compatibility"
-        depends on EXT4_FS
+config EXT4_USE_FOR_EXT23
+        bool "Use ext4 for ext2/ext3 file systems"
+        depends on EXT3_FS=n || EXT2_FS=n
+        default y
         help
-          Starting with 2.6.28, the name of the ext4 filesystem was
-          renamed from ext4dev to ext4.  Unfortunately there are some
-          legacy userspace programs (such as klibc's fstype) have
-          "ext4dev" hardcoded.
-
-          To enable backwards compatibility so that systems that are
-          still expecting to mount ext4 filesystems using ext4dev,
-          choose Y here.   This feature will go away by 2.6.31, so
-          please arrange to get your userspace programs fixed!
+          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"
diff --git a/fs/ext4/balloc.c b/fs/ext4/balloc.c
index 1d0418980f8d..22bc7435d913 100644
--- a/fs/ext4/balloc.c
+++ b/fs/ext4/balloc.c
@@ -499,44 +499,6 @@ error_return:
 }
 
 /**
- * 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
@@ -761,7 +723,13 @@ static unsigned long ext4_bg_num_gdb_meta(struct super_block *sb,
 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;
 }
 
 /**
diff --git a/fs/ext4/block_validity.c b/fs/ext4/block_validity.c
index 50784ef07563..4df8621ec31c 100644
--- a/fs/ext4/block_validity.c
+++ b/fs/ext4/block_validity.c
@@ -160,7 +160,7 @@ int ext4_setup_system_zone(struct super_block *sb)
                 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)
@@ -228,6 +228,7 @@ int ext4_data_block_valid(struct ext4_sb_info *sbi, ext4_fsblk_t start_blk,
         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) {
diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h
index 984ca0cb38c3..ab31e65d46d0 100644
--- a/fs/ext4/ext4.h
+++ b/fs/ext4/ext4.h
@@ -322,6 +322,7 @@ static inline __u32 ext4_mask_flags(umode_t mode, __u32 flags)
 #define EXT4_STATE_NO_EXPAND            0x00000008 /* No space for expansion */
 #define EXT4_STATE_DA_ALLOC_CLOSE       0x00000010 /* Alloc DA blks on close */
 #define EXT4_STATE_EXT_MIGRATE          0x00000020 /* Inode is migrating */
+#define EXT4_STATE_DIO_UNWRITTEN        0x00000040 /* need convert on dio done*/
 
 /* Used to pass group descriptor data when online resize is done */
 struct ext4_new_group_input {
@@ -375,6 +376,12 @@ struct ext4_new_group_data {
                                          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
@@ -702,6 +709,13 @@ struct ext4_inode_info {
         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;
 };
 
 /*
@@ -743,11 +757,13 @@ struct ext4_inode_info {
 #define EXT4_MOUNT_QUOTA                0x80000 /* Some quota option set */
 #define EXT4_MOUNT_USRQUOTA             0x100000 /* "old" user quota */
 #define EXT4_MOUNT_GRPQUOTA             0x200000 /* "old" group quota */
+#define EXT4_MOUNT_JOURNAL_CHECKSUM     0x800000 /* Journal checksums */
 #define EXT4_MOUNT_JOURNAL_ASYNC_COMMIT 0x1000000 /* Journal Async Commit */
 #define EXT4_MOUNT_I_VERSION            0x2000000 /* i_version support */
 #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
@@ -1322,8 +1338,6 @@ extern ext4_fsblk_t ext4_new_meta_blocks(handle_t *handle, struct inode *inode,
                         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 *);
@@ -1382,16 +1396,15 @@ extern int ext4_mb_reserve_blocks(struct super_block *, int);
 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 *,
diff --git a/fs/ext4/ext4_jbd2.c b/fs/ext4/ext4_jbd2.c
index 6a9409920dee..b57e5c711b6d 100644
--- a/fs/ext4/ext4_jbd2.c
+++ b/fs/ext4/ext4_jbd2.c
@@ -4,6 +4,8 @@
 
 #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)
 {
@@ -32,35 +34,69 @@ int __ext4_journal_get_write_access(const char *where, handle_t *handle,
         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;
-}
+                return 0;
+        }
 
-int __ext4_journal_revoke(const char *where, handle_t *handle,
-                                ext4_fsblk_t blocknr, struct buffer_head *bh)
-{
-        int err = 0;
+        /* 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 (ext4_handle_valid(handle)) {
-                err = jbd2_journal_revoke(handle, blocknr, bh);
-                if (err)
-                        ext4_journal_abort_handle(where, __func__, bh,
-                                                  handle, err);
+        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;
         }
-        else
-                bforget(bh);
+
+        /*
+         * 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;
 }
 
diff --git a/fs/ext4/ext4_jbd2.h b/fs/ext4/ext4_jbd2.h
index a2865980342f..05eca817d704 100644
--- a/fs/ext4/ext4_jbd2.h
+++ b/fs/ext4/ext4_jbd2.h
@@ -49,7 +49,7 @@
 
 #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.
@@ -57,7 +57,7 @@
  * 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
@@ -92,6 +92,7 @@
  * 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
@@ -99,6 +100,9 @@
 #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,
@@ -116,12 +120,8 @@ int ext4_reserve_inode_write(handle_t *handle, struct inode *inode,
 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);
 
@@ -131,13 +131,9 @@ int __ext4_journal_get_undo_access(const char *where, handle_t *handle,
 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);
@@ -149,12 +145,11 @@ int __ext4_handle_dirty_metadata(const char *where, handle_t *handle,
         __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))
 
@@ -254,6 +249,19 @@ static inline int ext4_jbd2_file_inode(handle_t *handle, struct inode *inode)
         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 */
 int ext4_force_commit(struct super_block *sb);
 
diff --git a/fs/ext4/extents.c b/fs/ext4/extents.c
index 10539e364283..3a7928f825e4 100644
--- a/fs/ext4/extents.c
+++ b/fs/ext4/extents.c
@@ -1007,7 +1007,8 @@ cleanup:
                 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);
@@ -1761,7 +1762,9 @@ int ext4_ext_walk_space(struct inode *inode, ext4_lblk_t block,
         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;
@@ -1957,7 +1960,6 @@ errout:
 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;
 
@@ -1973,9 +1975,8 @@ static int ext4_ext_rm_idx(handle_t *handle, struct inode *inode,
         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;
 }
 
@@ -2042,12 +2043,11 @@ static int ext4_remove_blocks(handle_t *handle, struct inode *inode,
                                 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);
@@ -2072,11 +2072,7 @@ static int ext4_remove_blocks(handle_t *handle, struct inode *inode,
                 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",
@@ -2167,7 +2163,7 @@ ext4_ext_rm_leaf(handle_t *handle, struct inode *inode,
                         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)
@@ -2807,6 +2803,8 @@ fix_extent_len:
  * into three uninitialized extent(at most). After IO complete, the part
  * being filled will be convert to initialized by the end_io callback function
  * via ext4_convert_unwritten_extents().
+ *
+ * Returns the size of uninitialized extent to be written on success.
  */
 static int ext4_split_unwritten_extents(handle_t *handle,
                                         struct inode *inode,
@@ -2824,7 +2822,6 @@ static int ext4_split_unwritten_extents(handle_t *handle,
         unsigned int allocated, ee_len, depth;
         ext4_fsblk_t newblock;
         int err = 0;
-        int ret = 0;
 
         ext_debug("ext4_split_unwritten_extents: inode %lu,"
                   "iblock %llu, max_blocks %u\n", inode->i_ino,
@@ -2842,12 +2839,12 @@ static int ext4_split_unwritten_extents(handle_t *handle,
         ext4_ext_store_pblock(&orig_ex, ext_pblock(ex));
 
         /*
-         * if the entire unintialized extent length less than
-         * the size of extent to write, there is no need to split
-         * uninitialized extent
+         * 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 (allocated <= max_blocks)
-                return ret;
+        if ((iblock == ee_block) && (allocated <= max_blocks))
+                return allocated;
 
         err = ext4_ext_get_access(handle, inode, path + depth);
         if (err)
@@ -3048,15 +3045,23 @@ ext4_ext_handle_uninitialized_extents(handle_t *handle, struct inode *inode,
                 ret = ext4_split_unwritten_extents(handle,
                                                 inode, path, iblock,
                                                 max_blocks, flags);
-                /* flag the io_end struct that we need convert when IO done */
+                /*
+                 * Flag the inode(non aio case) or end_io struct (aio case)
+                 * that this IO needs to convertion to written when IO is
+                 * completed
+                 */
                 if (io)
                         io->flag = DIO_AIO_UNWRITTEN;
+                else
+                        EXT4_I(inode)->i_state |= EXT4_STATE_DIO_UNWRITTEN;
                 goto out;
         }
-        /* DIO end_io complete, convert the filled extent to written */
+        /* async DIO end_io complete, convert the filled extent to written */
         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 */
@@ -3084,6 +3089,8 @@ ext4_ext_handle_uninitialized_extents(handle_t *handle, struct inode *inode,
         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;
@@ -3295,10 +3302,16 @@ int ext4_ext_get_blocks(handle_t *handle, struct inode *inode,
                  * To avoid unecessary convertion for every aio dio rewrite
                  * to the mid of file, here we flag the IO that is really
                  * need the convertion.
-                 *
+                 * For non asycn direct IO case, flag the inode state
+                 * that we need to perform convertion when IO is done.
                  */
-                if (io && flags == EXT4_GET_BLOCKS_DIO_CREATE_EXT)
-                        io->flag = DIO_AIO_UNWRITTEN;
+                if (flags == EXT4_GET_BLOCKS_DIO_CREATE_EXT) {
+                        if (io)
+                                io->flag = DIO_AIO_UNWRITTEN;
+                        else
+                                EXT4_I(inode)->i_state |=
+                                        EXT4_STATE_DIO_UNWRITTEN;;
+                }
         }
         err = ext4_ext_insert_extent(handle, inode, path, &newex, flags);
         if (err) {
@@ -3306,8 +3319,8 @@ int ext4_ext_get_blocks(handle_t *handle, struct inode *inode,
                 /* 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;
         }
 
@@ -3316,10 +3329,16 @@ int ext4_ext_get_blocks(handle_t *handle, struct inode *inode,
         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;
@@ -3519,6 +3538,7 @@ retry:
  *
  * This function is called from the direct IO end io call back
  * function, to convert the fallocated extents after IO is completed.
+ * Returns 0 on success.
  */
 int ext4_convert_unwritten_extents(struct inode *inode, loff_t offset,
                                     loff_t len)
@@ -3706,10 +3726,8 @@ int ext4_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo,
                  * 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;
diff --git a/fs/ext4/fsync.c b/fs/ext4/fsync.c
index 2b1531266ee2..0b22497d92e1 100644
--- a/fs/ext4/fsync.c
+++ b/fs/ext4/fsync.c
@@ -51,25 +51,30 @@
 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).
@@ -79,32 +84,13 @@ int ext4_sync_file(struct file *file, struct dentry *dentry, int datasync)
          *  (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;
 }
diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
index ec367bce7215..5352db1a3086 100644
--- a/fs/ext4/inode.c
+++ b/fs/ext4/inode.c
@@ -71,58 +71,6 @@ static int ext4_inode_is_fast_symlink(struct inode *inode)
 }
 
 /*
- * 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.
  */
@@ -193,7 +141,7 @@ static int try_to_extend_transaction(handle_t *handle, struct inode *inode)
  * so before we call here everything must be consistently dirtied against
  * this transaction.
  */
- int ext4_truncate_restart_trans(handle_t *handle, struct inode *inode,
+int ext4_truncate_restart_trans(handle_t *handle, struct inode *inode,
                                  int nblocks)
 {
         int ret;
@@ -209,6 +157,7 @@ static int try_to_extend_transaction(handle_t *handle, struct inode *inode)
         up_write(&EXT4_I(inode)->i_data_sem);
         ret = ext4_journal_restart(handle, blocks_for_truncate(inode));
         down_write(&EXT4_I(inode)->i_data_sem);
+        ext4_discard_preallocations(inode);
 
         return ret;
 }
@@ -720,7 +669,7 @@ allocated:
         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;
 }
 
@@ -816,14 +765,20 @@ static int ext4_alloc_branch(handle_t *handle, struct inode *inode,
         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;
 }
@@ -902,12 +857,16 @@ static int ext4_splice_branch(handle_t *handle, struct inode *inode,
 
 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;
 }
@@ -1020,10 +979,12 @@ static int ext4_ind_get_blocks(handle_t *handle, struct inode *inode,
         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)
@@ -1051,7 +1012,7 @@ qsize_t ext4_get_reserved_space(struct inode *inode)
                 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
@@ -1146,8 +1107,8 @@ static int check_block_validity(struct inode *inode, const char *msg,
 }
 
 /*
- * Return the number of dirty pages in the given inode starting at
- * page frame idx.
+ * Return the number of contiguous dirty pages in a given inode
+ * starting at page frame idx.
  */
 static pgoff_t ext4_num_dirty_pages(struct inode *inode, pgoff_t idx,
                                     unsigned int max_pages)
@@ -1181,15 +1142,15 @@ static pgoff_t ext4_num_dirty_pages(struct inode *inode, pgoff_t idx,
                                 unlock_page(page);
                                 break;
                         }
-                        head = page_buffers(page);
-                        bh = head;
-                        do {
-                                if (!buffer_delay(bh) &&
-                                    !buffer_unwritten(bh)) {
-                                        done = 1;
-                                        break;
-                                }
-                        } while ((bh = bh->b_this_page) != head);
+                        if (page_has_buffers(page)) {
+                                bh = head = page_buffers(page);
+                                do {
+                                        if (!buffer_delay(bh) &&
+                                            !buffer_unwritten(bh))
+                                                done = 1;
+                                        bh = bh->b_this_page;
+                                } while (!done && (bh != head));
+                        }
                         unlock_page(page);
                         if (done)
                                 break;
@@ -1533,6 +1494,16 @@ static int do_journal_get_write_access(handle_t *handle,
         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)
@@ -1598,7 +1569,7 @@ retry:
 
                 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
@@ -1708,7 +1679,7 @@ static int ext4_ordered_write_end(struct file *file,
                 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
@@ -1750,7 +1721,7 @@ static int ext4_writeback_write_end(struct file *file,
                 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
@@ -1813,7 +1784,7 @@ static int ext4_journalled_write_end(struct file *file,
         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
@@ -2599,7 +2570,6 @@ static int bput_one(handle_t *handle, struct buffer_head *bh)
 }
 
 static int __ext4_journalled_writepage(struct page *page,
-                                       struct writeback_control *wbc,
                                        unsigned int len)
 {
         struct address_space *mapping = page->mapping;
@@ -2757,7 +2727,7 @@ static int ext4_writepage(struct page *page,
                  * 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))
@@ -2787,7 +2757,7 @@ static int ext4_da_writepages_trans_blocks(struct inode *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;
 
@@ -2932,7 +2902,7 @@ retry:
                 ret = write_cache_pages(mapping, wbc, __mpage_da_writepage,
                                         &mpd);
                 /*
-                 * If we have a contigous extent of pages and we
+                 * If we have a contiguous extent of pages and we
                  * haven't done the I/O yet, map the blocks and submit
                  * them for I/O.
                  */
@@ -3090,7 +3060,7 @@ retry:
                  * 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))
@@ -3378,6 +3348,7 @@ static ssize_t ext4_ind_direct_IO(int rw, struct kiocb *iocb,
         ssize_t ret;
         int orphan = 0;
         size_t count = iov_length(iov, nr_segs);
+        int retries = 0;
 
         if (rw == WRITE) {
                 loff_t final_size = offset + count;
@@ -3400,9 +3371,12 @@ static ssize_t ext4_ind_direct_IO(int rw, struct kiocb *iocb,
                 }
         }
 
+retry:
         ret = blockdev_direct_IO(rw, iocb, inode, inode->i_sb->s_bdev, iov,
                                  offset, nr_segs,
                                  ext4_get_block, NULL);
+        if (ret == -ENOSPC && ext4_should_retry_alloc(inode->i_sb, &retries))
+                goto retry;
 
         if (orphan) {
                 int err;
@@ -3441,8 +3415,6 @@ out:
         return ret;
 }
 
-/* Maximum number of blocks we map for direct IO at once. */
-
 static int ext4_get_block_dio_write(struct inode *inode, sector_t iblock,
                    struct buffer_head *bh_result, int create)
 {
@@ -3650,13 +3622,14 @@ static void ext4_end_io_dio(struct kiocb *iocb, loff_t offset,
         ext4_io_end_t *io_end = iocb->private;
         struct workqueue_struct *wq;
 
+        /* if not async direct IO or dio with 0 bytes write, just return */
+        if (!io_end || !size)
+                return;
+
         ext_debug("ext4_end_io_dio(): io_end 0x%p"
                   "for inode %lu, iocb 0x%p, offset %llu, size %llu\n",
                   iocb->private, io_end->inode->i_ino, iocb, offset,
                   size);
-        /* if not async direct IO or dio with 0 bytes write, just return */
-        if (!io_end || !size)
-                return;
 
         /* if not aio dio with unwritten extents, just free io and return */
         if (io_end->flag != DIO_AIO_UNWRITTEN){
@@ -3767,13 +3740,19 @@ static ssize_t ext4_ext_direct_IO(int rw, struct kiocb *iocb,
                 if (ret != -EIOCBQUEUED && ret <= 0 && iocb->private) {
                         ext4_free_io_end(iocb->private);
                         iocb->private = NULL;
-                } else if (ret > 0)
+                } else if (ret > 0 && (EXT4_I(inode)->i_state &
+                                       EXT4_STATE_DIO_UNWRITTEN)) {
+                        int err;
                         /*
                          * for non AIO case, since the IO is already
                          * completed, we could do the convertion right here
                          */
-                        ret = ext4_convert_unwritten_extents(inode,
-                                                                offset, ret);
+                        err = ext4_convert_unwritten_extents(inode,
+                                                             offset, ret);
+                        if (err < 0)
+                                ret = err;
+                        EXT4_I(inode)->i_state &= ~EXT4_STATE_DIO_UNWRITTEN;
+                }
                 return ret;
         }
 
@@ -4054,7 +4033,7 @@ static Indirect *ext4_find_shared(struct inode *inode, int depth,
         int k, err;
 
         *top = 0;
-        /* Make k index the deepest non-null offest + 1 */
+        /* Make k index the deepest non-null offset + 1 */
         for (k = depth; k > 1 && !offsets[k-1]; k--)
                 ;
         partial = ext4_get_branch(inode, k, offsets, chain, &err);
@@ -4110,6 +4089,11 @@ static void ext4_clear_blocks(handle_t *handle, struct inode *inode,
                               __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");
@@ -4124,27 +4108,10 @@ static void ext4_clear_blocks(handle_t *handle, struct inode *inode,
                 }
         }
 
-        /*
-         * 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;
-
-                        *p = 0;
-                        tbh = sb_find_get_block(inode->i_sb, nr);
-                        ext4_forget(handle, 0, inode, tbh, nr);
-                }
-        }
+        for (p = first; p < last; p++)
+                *p = 0;
 
-        ext4_free_blocks(handle, inode, block_to_free, count, 0);
+        ext4_free_blocks(handle, inode, 0, block_to_free, count, flags);
 }
 
 /**
@@ -4332,7 +4299,8 @@ static void ext4_free_branches(handle_t *handle, struct inode *inode,
                                             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) {
                                 /*
@@ -4771,8 +4739,8 @@ struct inode *ext4_iget(struct super_block *sb, unsigned long ino)
         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;
 
@@ -4783,11 +4751,11 @@ struct inode *ext4_iget(struct super_block *sb, unsigned long ino)
                 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);
@@ -4810,7 +4778,6 @@ struct inode *ext4_iget(struct super_block *sb, unsigned long ino)
                 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;
                 }
@@ -4838,11 +4805,35 @@ struct inode *ext4_iget(struct super_block *sb, unsigned long ino)
                 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;
                 }
@@ -4874,10 +4865,7 @@ struct inode *ext4_iget(struct super_block *sb, unsigned long ino)
 
         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);
@@ -4895,10 +4883,8 @@ struct inode *ext4_iget(struct super_block *sb, unsigned long 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;
@@ -4926,7 +4912,6 @@ struct inode *ext4_iget(struct super_block *sb, unsigned long ino)
                         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",
@@ -4939,6 +4924,7 @@ struct inode *ext4_iget(struct super_block *sb, unsigned long ino)
         return inode;
 
 bad_inode:
+        brelse(iloc.bh);
         iget_failed(inode);
         return ERR_PTR(ret);
 }
@@ -5098,6 +5084,7 @@ static int ext4_do_update_inode(handle_t *handle,
                 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);
@@ -5217,8 +5204,8 @@ int ext4_setattr(struct dentry *dentry, struct iattr *attr)
 
                 /* (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;
@@ -5366,7 +5353,7 @@ static int ext4_index_trans_blocks(struct inode *inode, int nrblocks, int chunk)
  * worse case, the indexs blocks spread over different block groups
  *
  * If datablocks are discontiguous, they are possible to spread over
- * different block groups too. If they are contiugous, with flexbg,
+ * different block groups too. If they are contiuguous, with flexbg,
  * they could still across block group boundary.
  *
  * Also account for superblock, inode, quota and xattr blocks
@@ -5442,7 +5429,7 @@ int ext4_writepage_trans_blocks(struct inode *inode)
  * Calculate the journal credits for a chunk of data modification.
  *
  * This is called from DIO, fallocate or whoever calling
- * ext4_get_blocks() to map/allocate a chunk of contigous disk blocks.
+ * ext4_get_blocks() to map/allocate a chunk of contiguous disk blocks.
  *
  * journal buffers for data blocks are not included here, as DIO
  * and fallocate do no need to journal data buffers.
@@ -5612,14 +5599,12 @@ int ext4_mark_inode_dirty(handle_t *handle, struct inode *inode)
  */
 void ext4_dirty_inode(struct inode *inode)
 {
-        handle_t *current_handle = ext4_journal_current_handle();
         handle_t *handle;
 
         handle = ext4_journal_start(inode, 2);
         if (IS_ERR(handle))
                 goto out;
 
-        jbd_debug(5, "marking dirty.  outer handle=%p\n", current_handle);
         ext4_mark_inode_dirty(handle, inode);
 
         ext4_journal_stop(handle);
diff --git a/fs/ext4/ioctl.c b/fs/ext4/ioctl.c
index c1cdf613e725..b63d193126db 100644
--- a/fs/ext4/ioctl.c
+++ b/fs/ext4/ioctl.c
@@ -221,31 +221,38 @@ setversion_out:
                 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;
         }
 
diff --git a/fs/ext4/mballoc.c b/fs/ext4/mballoc.c
index d527fd384582..b1fd3daadc9c 100644
--- a/fs/ext4/mballoc.c
+++ b/fs/ext4/mballoc.c
@@ -142,7 +142,7 @@
  * 2 blocks and the order of allocation is >= sbi->s_mb_order2_reqs. The
  * value of s_mb_order2_reqs can be tuned via
  * /sys/fs/ext4/<partition>/mb_order2_req.  If the request len is equal to
- * stripe size (sbi->s_stripe), we try to search for contigous block in
+ * stripe size (sbi->s_stripe), we try to search for contiguous block in
  * stripe size. This should result in better allocation on RAID setups. If
  * not, we search in the specific group using bitmap for best extents. The
  * tunable min_to_scan and max_to_scan control the behaviour here.
@@ -2529,7 +2529,6 @@ static void release_blocks_on_commit(journal_t *journal, transaction_t *txn)
         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) {
@@ -2559,13 +2558,19 @@ static void release_blocks_on_commit(journal_t *journal, transaction_t *txn)
                         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);
         }
@@ -3006,6 +3011,24 @@ static void ext4_mb_collect_stats(struct ext4_allocation_context *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;
+        }
+
+}
+
+/*
  * use blocks preallocated to inode
  */
 static void ext4_mb_use_inode_pa(struct ext4_allocation_context *ac,
@@ -4290,6 +4313,7 @@ repeat:
                         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);
@@ -4422,18 +4446,24 @@ ext4_mb_free_metadata(handle_t *handle, struct ext4_buddy *e4b,
         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;
@@ -4443,13 +4473,16 @@ void ext4_mb_free_blocks(handle_t *handle, struct inode *inode,
         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);
@@ -4457,7 +4490,32 @@ void ext4_mb_free_blocks(handle_t *handle, struct inode *inode,
         }
 
         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) {
@@ -4533,7 +4591,8 @@ do_more:
         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
@@ -4572,7 +4631,7 @@ do_more:
 
         ext4_mb_release_desc(&e4b);
 
-        *freed += count;
+        freed += count;
 
         /* We dirtied the bitmap block */
         BUFFER_TRACE(bitmap_bh, "dirtied bitmap block");
@@ -4592,6 +4651,8 @@ do_more:
         }
         sb->s_dirt = 1;
 error_return:
+        if (freed)
+                vfs_dq_free_block(inode, freed);
         brelse(bitmap_bh);
         ext4_std_error(sb, err);
         if (ac)
diff --git a/fs/ext4/migrate.c b/fs/ext4/migrate.c
index a93d5b80f3e2..81415814b00b 100644
--- a/fs/ext4/migrate.c
+++ b/fs/ext4/migrate.c
@@ -238,7 +238,7 @@ static int extend_credit_for_blkdel(handle_t *handle, struct inode *inode)
          * 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);
@@ -262,13 +262,17 @@ static int free_dind_blocks(handle_t *handle,
         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;
 }
 
@@ -297,7 +301,9 @@ static int free_tind_blocks(handle_t *handle,
         }
         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;
 }
 
@@ -308,8 +314,10 @@ static int free_ind_block(handle_t *handle, struct inode *inode, __le32 *i_data)
         /* 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] */
@@ -419,7 +427,8 @@ static int free_ext_idx(handle_t *handle, struct inode *inode,
         }
         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;
 }
 
@@ -477,7 +486,7 @@ int ext4_ext_migrate(struct inode *inode)
         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);
diff --git a/fs/ext4/move_extent.c b/fs/ext4/move_extent.c
index 25b6b1457360..82c415be87a4 100644
--- a/fs/ext4/move_extent.c
+++ b/fs/ext4/move_extent.c
@@ -77,12 +77,14 @@ static int
 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;
         }
 
@@ -119,9 +121,18 @@ mext_next_extent(struct inode *inode, struct ext4_ext_path *path,
                                         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;
                 }
         }
@@ -155,40 +166,15 @@ mext_check_null_inode(struct inode *inode1, struct inode *inode2,
 }
 
 /**
- * mext_double_down_read - Acquire two inodes' read semaphore
- *
- * @orig_inode:         original inode structure
- * @donor_inode:        donor inode structure
- * Acquire read semaphore 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
+ * 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 write 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_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;
 
@@ -203,32 +189,18 @@ mext_double_down_write(struct inode *orig_inode, struct inode *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);
@@ -596,7 +568,7 @@ out:
  * @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.
  */
@@ -661,6 +633,7 @@ mext_calc_swap_extents(struct ext4_extent *tmp_dext,
  * @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:
@@ -671,33 +644,33 @@ mext_calc_swap_extents(struct ext4_extent *tmp_dext,
  * 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;
@@ -707,9 +680,9 @@ mext_replace_branches(handle_t *handle, struct inode *orig_inode,
         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 */
@@ -718,7 +691,7 @@ mext_replace_branches(handle_t *handle, struct inode *orig_inode,
                 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__,
@@ -726,20 +699,20 @@ mext_replace_branches(handle_t *handle, struct inode *orig_inode,
                                 "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);
@@ -753,35 +726,25 @@ mext_replace_branches(handle_t *handle, struct inode *orig_inode,
 
                 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;
         }
 
@@ -795,8 +758,12 @@ 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;
 }
 
 /**
@@ -808,16 +775,17 @@ out:
  * @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;
@@ -829,9 +797,11 @@ move_extent_per_page(struct file *o_filp, struct inode *donor_inode,
         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;
 
         /*
@@ -841,8 +811,8 @@ move_extent_per_page(struct file *o_filp, struct inode *donor_inode,
         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))
@@ -858,39 +828,36 @@ move_extent_per_page(struct file *o_filp, struct inode *donor_inode,
          * 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;
+
+        replaced_size = data_size;
 
-        ret = a_ops->write_begin(o_filp, mapping, offs, data_len, w_flags,
+        *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)) {
@@ -911,14 +878,17 @@ move_extent_per_page(struct file *o_filp, struct inode *donor_inode,
         /* 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);
@@ -928,16 +898,16 @@ move_extent_per_page(struct file *o_filp, struct inode *donor_inode,
                 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;
 
@@ -951,7 +921,10 @@ out:
 out2:
         ext4_journal_stop(handle);
 
-        return ret < 0 ? ret : 0;
+        if (err2)
+                *err = err2;
+
+        return replaced_count;
 }
 
 /**
@@ -962,7 +935,6 @@ out2:
  * @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.
@@ -970,8 +942,8 @@ out2:
  */
 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;
@@ -985,6 +957,13 @@ mext_check_arguments(struct inode *orig_inode,
                 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 move extent does not support swapfile */
         if (IS_SWAPFILE(orig_inode) || IS_SWAPFILE(donor_inode)) {
                 ext4_debug("ext4 move extent: The argument files should "
@@ -1025,13 +1004,6 @@ mext_check_arguments(struct inode *orig_inode,
                 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 ((orig_start > EXT_MAX_BLOCK) ||
             (donor_start > EXT_MAX_BLOCK) ||
             (*len > EXT_MAX_BLOCK) ||
@@ -1088,7 +1060,7 @@ mext_check_arguments(struct inode *orig_inode,
         }
 
         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;
@@ -1232,16 +1204,16 @@ ext4_move_extents(struct file *o_filp, struct file *d_filp,
                 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;
 
@@ -1355,36 +1327,39 @@ ext4_move_extents(struct file *o_filp, struct file *d_filp,
                 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)
@@ -1393,6 +1368,10 @@ ext4_move_extents(struct file *o_filp, struct file *d_filp,
                                 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)
                         ext4_ext_drop_refs(holecheck_path);
@@ -1414,6 +1393,11 @@ ext4_move_extents(struct file *o_filp, struct file *d_filp,
 
         }
 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);
@@ -1422,7 +1406,7 @@ out:
                 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)
diff --git a/fs/ext4/namei.c b/fs/ext4/namei.c
index 7c8fe80bacdd..17a17e10dd60 100644
--- a/fs/ext4/namei.c
+++ b/fs/ext4/namei.c
@@ -1292,9 +1292,6 @@ errout:
  * 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,
@@ -1315,14 +1312,10 @@ static int add_dirent_to_buf(handle_t *handle, struct dentry *dentry,
                 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)
@@ -1337,7 +1330,6 @@ static int add_dirent_to_buf(handle_t *handle, struct dentry *dentry,
         err = ext4_journal_get_write_access(handle, bh);
         if (err) {
                 ext4_std_error(dir->i_sb, err);
-                brelse(bh);
                 return err;
         }
 
@@ -1377,7 +1369,6 @@ static int add_dirent_to_buf(handle_t *handle, struct dentry *dentry,
         err = ext4_handle_dirty_metadata(handle, dir, bh);
         if (err)
                 ext4_std_error(dir->i_sb, err);
-        brelse(bh);
         return 0;
 }
 
@@ -1471,7 +1462,9 @@ static int make_indexed_dir(handle_t *handle, struct dentry *dentry,
         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;
 }
 
 /*
@@ -1514,16 +1507,14 @@ static int ext4_add_entry(handle_t *handle, struct dentry *dentry,
                 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)) {
-                        retval = make_indexed_dir(handle, dentry, inode, bh);
-                        if (retval == -ENOSPC)
-                                brelse(bh);
-                        return retval;
-                }
+                    EXT4_HAS_COMPAT_FEATURE(sb, EXT4_FEATURE_COMPAT_DIR_INDEX))
+                        return make_indexed_dir(handle, dentry, inode, bh);
                 brelse(bh);
         }
         bh = ext4_append(handle, dir, &block, &retval);
@@ -1533,8 +1524,7 @@ static int ext4_add_entry(handle_t *handle, struct dentry *dentry,
         de->inode = 0;
         de->rec_len = ext4_rec_len_to_disk(blocksize, blocksize);
         retval = add_dirent_to_buf(handle, dentry, inode, de, bh);
-        if (retval == -ENOSPC)
-                brelse(bh);
+        brelse(bh);
         return retval;
 }
 
@@ -1568,10 +1558,8 @@ static int ext4_dx_add_entry(handle_t *handle, struct dentry *dentry,
                 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",
@@ -1664,8 +1652,6 @@ static int ext4_dx_add_entry(handle_t *handle, struct dentry *dentry,
         if (!de)
                 goto cleanup;
         err = add_dirent_to_buf(handle, dentry, inode, de, bh);
-        if (err != -ENOSPC)
-                bh = NULL;
         goto cleanup;
 
 journal_error:
@@ -1783,7 +1769,7 @@ static int ext4_create(struct inode *dir, struct dentry *dentry, int mode,
 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);
 
@@ -1817,7 +1803,7 @@ static int ext4_mknod(struct inode *dir, struct dentry *dentry,
 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);
 
@@ -1854,7 +1840,7 @@ static int ext4_mkdir(struct inode *dir, struct dentry *dentry, int mode)
 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);
 
@@ -2267,7 +2253,7 @@ static int ext4_symlink(struct inode *dir,
 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);
 
diff --git a/fs/ext4/resize.c b/fs/ext4/resize.c
index 3cfc343c41b5..3b2c5541d8a6 100644
--- a/fs/ext4/resize.c
+++ b/fs/ext4/resize.c
@@ -247,7 +247,7 @@ static int setup_new_group_blocks(struct super_block *sb,
                         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);
diff --git a/fs/ext4/super.c b/fs/ext4/super.c
index 12e726a7073f..768c111a77ec 100644
--- a/fs/ext4/super.c
+++ b/fs/ext4/super.c
@@ -603,10 +603,6 @@ static void ext4_put_super(struct super_block *sb)
         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;
@@ -614,6 +610,12 @@ static void ext4_put_super(struct super_block *sb)
                         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);
@@ -704,6 +706,8 @@ static struct inode *ext4_alloc_inode(struct super_block *sb)
         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;
 }
@@ -765,9 +769,22 @@ static inline void ext4_show_quota_options(struct seq_file *seq,
 #if defined(CONFIG_QUOTA)
         struct ext4_sb_info *sbi = EXT4_SB(sb);
 
-        if (sbi->s_jquota_fmt)
-                seq_printf(seq, ",jqfmt=%s",
-                (sbi->s_jquota_fmt == QFMT_VFS_OLD) ? "vfsold" : "vfsv0");
+        if (sbi->s_jquota_fmt) {
+                char *fmtname = "";
+
+                switch (sbi->s_jquota_fmt) {
+                case QFMT_VFS_OLD:
+                        fmtname = "vfsold";
+                        break;
+                case QFMT_VFS_V0:
+                        fmtname = "vfsv0";
+                        break;
+                case QFMT_VFS_V1:
+                        fmtname = "vfsv1";
+                        break;
+                }
+                seq_printf(seq, ",jqfmt=%s", fmtname);
+        }
 
         if (sbi->s_qf_names[USRQUOTA])
                 seq_printf(seq, ",usrjquota=%s", sbi->s_qf_names[USRQUOTA]);
@@ -899,6 +916,12 @@ static int ext4_show_options(struct seq_file *seq, struct vfsmount *vfs)
         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;
@@ -1074,12 +1097,13 @@ enum {
         Opt_abort, Opt_data_journal, Opt_data_ordered, Opt_data_writeback,
         Opt_data_err_abort, Opt_data_err_ignore,
         Opt_usrjquota, Opt_grpjquota, Opt_offusrjquota, Opt_offgrpjquota,
-        Opt_jqfmt_vfsold, Opt_jqfmt_vfsv0, Opt_quota, Opt_noquota,
-        Opt_ignore, Opt_barrier, Opt_nobarrier, Opt_err, Opt_resize,
-        Opt_usrquota, Opt_grpquota, Opt_i_version,
+        Opt_jqfmt_vfsold, Opt_jqfmt_vfsv0, Opt_jqfmt_vfsv1, Opt_quota,
+        Opt_noquota, Opt_ignore, Opt_barrier, Opt_nobarrier, Opt_err,
+        Opt_resize, 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 = {
@@ -1104,6 +1128,7 @@ 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"},
@@ -1125,6 +1150,7 @@ static const match_table_t tokens = {
         {Opt_grpjquota, "grpjquota=%s"},
         {Opt_jqfmt_vfsold, "jqfmt=vfsold"},
         {Opt_jqfmt_vfsv0, "jqfmt=vfsv0"},
+        {Opt_jqfmt_vfsv1, "jqfmt=vfsv1"},
         {Opt_grpquota, "grpquota"},
         {Opt_noquota, "noquota"},
         {Opt_quota, "quota"},
@@ -1144,6 +1170,8 @@ static const match_table_t tokens = {
         {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},
 };
 
@@ -1300,9 +1328,11 @@ static int parse_options(char *options, struct super_block *sb,
                         *journal_devnum = option;
                         break;
                 case Opt_journal_checksum:
-                        break;  /* Kept for backwards compatibility */
+                        set_opt(sbi->s_mount_opt, JOURNAL_CHECKSUM);
+                        break;
                 case Opt_journal_async_commit:
                         set_opt(sbi->s_mount_opt, JOURNAL_ASYNC_COMMIT);
+                        set_opt(sbi->s_mount_opt, JOURNAL_CHECKSUM);
                         break;
                 case Opt_noload:
                         set_opt(sbi->s_mount_opt, NOLOAD);
@@ -1423,6 +1453,9 @@ clear_qf_name:
                         goto set_qf_format;
                 case Opt_jqfmt_vfsv0:
                         qfmt = QFMT_VFS_V0;
+                        goto set_qf_format;
+                case Opt_jqfmt_vfsv1:
+                        qfmt = QFMT_VFS_V1;
 set_qf_format:
                         if (sb_any_quota_loaded(sb) &&
                             sbi->s_jquota_fmt != qfmt) {
@@ -1465,6 +1498,7 @@ set_qf_format:
                 case Opt_offgrpjquota:
                 case Opt_jqfmt_vfsold:
                 case Opt_jqfmt_vfsv0:
+                case Opt_jqfmt_vfsv1:
                         ext4_msg(sb, KERN_ERR,
                                 "journaled quota options not supported");
                         break;
@@ -1563,6 +1597,12 @@ set_qf_format:
                         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\" "
@@ -1671,14 +1711,14 @@ static int ext4_fill_flex_info(struct super_block *sb)
         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) +
                         ((le16_to_cpu(sbi->s_es->s_reserved_gdt_blocks) + 1) <<
@@ -2719,26 +2759,6 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
             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 "
@@ -2759,14 +2779,20 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
                 goto failed_mount4;
         }
 
-        jbd2_journal_set_features(sbi->s_journal,
-                                  JBD2_FEATURE_COMPAT_CHECKSUM, 0, 0);
-        if (test_opt(sb, JOURNAL_ASYNC_COMMIT))
-                jbd2_journal_set_features(sbi->s_journal, 0, 0,
+        if (test_opt(sb, JOURNAL_ASYNC_COMMIT)) {
+                jbd2_journal_set_features(sbi->s_journal,
+                                JBD2_FEATURE_COMPAT_CHECKSUM, 0,
                                 JBD2_FEATURE_INCOMPAT_ASYNC_COMMIT);
-        else
+        } else if (test_opt(sb, JOURNAL_CHECKSUM)) {
+                jbd2_journal_set_features(sbi->s_journal,
+                                JBD2_FEATURE_COMPAT_CHECKSUM, 0, 0);
                 jbd2_journal_clear_features(sbi->s_journal, 0, 0,
                                 JBD2_FEATURE_INCOMPAT_ASYNC_COMMIT);
+        } else {
+                jbd2_journal_clear_features(sbi->s_journal,
+                                JBD2_FEATURE_COMPAT_CHECKSUM, 0,
+                                JBD2_FEATURE_INCOMPAT_ASYNC_COMMIT);
+        }
 
         /* We have now updated the journal if required, so we can
          * validate the data journaling mode. */
@@ -3660,13 +3686,11 @@ static int ext4_statfs(struct dentry *dentry, struct kstatfs *buf)
         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));
@@ -3958,35 +3982,66 @@ static int ext4_get_sb(struct file_system_type *fs_type, int flags,
         return get_sb_bdev(fs_type, flags, dev_name, data, ext4_fill_super,mnt);
 }
 
-static struct file_system_type ext4_fs_type = {
+#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           = "ext4",
+        .name           = "ext2",
         .get_sb         = ext4_get_sb,
         .kill_sb        = kill_block_super,
         .fs_flags       = FS_REQUIRES_DEV,
 };
 
-#ifdef CONFIG_EXT4DEV_COMPAT
-static int ext4dev_get_sb(struct file_system_type *fs_type, int flags,
-                          const char *dev_name, void *data,struct vfsmount *mnt)
+static inline void register_as_ext2(void)
 {
-        printk(KERN_WARNING "EXT4-fs (%s): Update your userspace programs "
-               "to mount using ext4\n", dev_name);
-        printk(KERN_WARNING "EXT4-fs (%s): ext4dev backwards compatibility "
-               "will go away by 2.6.31\n", dev_name);
-        return get_sb_bdev(fs_type, flags, dev_name, data, ext4_fill_super,mnt);
+        int err = register_filesystem(&ext2_fs_type);
+        if (err)
+                printk(KERN_WARNING
+                       "EXT4-fs: Unable to register as ext2 (%d)\n", err);
 }
 
-static struct file_system_type ext4dev_fs_type = {
+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           = "ext4dev",
-        .get_sb         = ext4dev_get_sb,
+        .name           = "ext3",
+        .get_sb         = ext4_get_sb,
         .kill_sb        = kill_block_super,
         .fs_flags       = FS_REQUIRES_DEV,
 };
-MODULE_ALIAS("ext4dev");
+
+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",
+        .get_sb         = ext4_get_sb,
+        .kill_sb        = kill_block_super,
+        .fs_flags       = FS_REQUIRES_DEV,
+};
+
 static int __init init_ext4_fs(void)
 {
         int err;
@@ -4008,18 +4063,15 @@ static int __init init_ext4_fs(void)
         err = init_inodecache();
         if (err)
                 goto out1;
+        register_as_ext2();
+        register_as_ext3();
         err = register_filesystem(&ext4_fs_type);
         if (err)
                 goto out;
-#ifdef CONFIG_EXT4DEV_COMPAT
-        err = register_filesystem(&ext4dev_fs_type);
-        if (err) {
-                unregister_filesystem(&ext4_fs_type);
-                goto out;
-        }
-#endif
         return 0;
 out:
+        unregister_as_ext2();
+        unregister_as_ext3();
         destroy_inodecache();
 out1:
         exit_ext4_xattr();
@@ -4035,10 +4087,9 @@ out4:
 
 static void __exit exit_ext4_fs(void)
 {
+        unregister_as_ext2();
+        unregister_as_ext3();
         unregister_filesystem(&ext4_fs_type);
-#ifdef CONFIG_EXT4DEV_COMPAT
-        unregister_filesystem(&ext4dev_fs_type);
-#endif
         destroy_inodecache();
         exit_ext4_xattr();
         exit_ext4_mballoc();
diff --git a/fs/ext4/xattr.c b/fs/ext4/xattr.c
index fed5b01d7a8d..910bf9a59cb3 100644
--- a/fs/ext4/xattr.c
+++ b/fs/ext4/xattr.c
@@ -482,9 +482,10 @@ ext4_xattr_release_block(handle_t *handle, struct inode *inode,
                 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);
@@ -832,7 +833,8 @@ inserted:
                         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;
                         }
@@ -988,6 +990,10 @@ ext4_xattr_set_handle(handle_t *handle, struct inode *inode, int name_index,
         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);
@@ -1013,9 +1019,6 @@ ext4_xattr_set_handle(handle_t *handle, struct inode *inode, int name_index,
                 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);