Merge branch 'master' of /pub/scm/linux/kernel/git/torvalds/linux-2.6

21 files changed, 508 insertions, 304 deletions

diff --git a/fs/binfmt_flat.c b/fs/binfmt_flat.c
index 56372ecf1690..dfc0197905ca 100644
--- a/fs/binfmt_flat.c
+++ b/fs/binfmt_flat.c
@@ -914,7 +914,9 @@ static int load_flat_binary(struct linux_binprm * bprm, struct pt_regs * regs)
 	/* Stash our initial stack pointer into the mm structure */
 	current->mm->start_stack = (unsigned long )sp;
 
-	
+#ifdef FLAT_PLAT_INIT
+	FLAT_PLAT_INIT(regs);
+#endif
 	DBG_FLT("start_thread(regs=0x%x, entry=0x%x, start_stack=0x%x)\n",
 		(int)regs, (int)start_addr, (int)current->mm->start_stack);
 	
diff --git a/fs/binfmt_misc.c b/fs/binfmt_misc.c
index 756205314c24..8d7e88e02e0f 100644
--- a/fs/binfmt_misc.c
+++ b/fs/binfmt_misc.c
@@ -120,8 +120,6 @@ static int load_misc_binary(struct linux_binprm *bprm, struct pt_regs *regs)
 	if (bprm->misc_bang)
 		goto _ret;
 
-	bprm->misc_bang = 1;
-
 	/* to keep locking time low, we copy the interpreter string */
 	read_lock(&entries_lock);
 	fmt = check_file(bprm);
@@ -199,6 +197,8 @@ static int load_misc_binary(struct linux_binprm *bprm, struct pt_regs *regs)
 	if (retval < 0)
 		goto _error;
 
+	bprm->misc_bang = 1;
+
 	retval = search_binary_handler (bprm, regs);
 	if (retval < 0)
 		goto _error;
diff --git a/fs/cramfs/inode.c b/fs/cramfs/inode.c
index 0c3b618c15b3..f40423eb1a14 100644
--- a/fs/cramfs/inode.c
+++ b/fs/cramfs/inode.c
@@ -43,58 +43,13 @@ static DEFINE_MUTEX(read_mutex);
 static int cramfs_iget5_test(struct inode *inode, void *opaque)
 {
 	struct cramfs_inode *cramfs_inode = opaque;
-
-	if (inode->i_ino != CRAMINO(cramfs_inode))
-		return 0; /* does not match */
-
-	if (inode->i_ino != 1)
-		return 1;
-
-	/* all empty directories, char, block, pipe, and sock, share inode #1 */
-
-	if ((inode->i_mode != cramfs_inode->mode) ||
-	    (inode->i_gid != cramfs_inode->gid) ||
-	    (inode->i_uid != cramfs_inode->uid))
-		return 0; /* does not match */
-
-	if ((S_ISCHR(inode->i_mode) || S_ISBLK(inode->i_mode)) &&
-	    (inode->i_rdev != old_decode_dev(cramfs_inode->size)))
-		return 0; /* does not match */
-
-	return 1; /* matches */
+	return inode->i_ino == CRAMINO(cramfs_inode) && inode->i_ino != 1;
 }
 
 static int cramfs_iget5_set(struct inode *inode, void *opaque)
 {
-	static struct timespec zerotime;
 	struct cramfs_inode *cramfs_inode = opaque;
-	inode->i_mode = cramfs_inode->mode;
-	inode->i_uid = cramfs_inode->uid;
-	inode->i_size = cramfs_inode->size;
-	inode->i_blocks = (cramfs_inode->size - 1) / 512 + 1;
-	inode->i_gid = cramfs_inode->gid;
-	/* Struct copy intentional */
-	inode->i_mtime = inode->i_atime = inode->i_ctime = zerotime;
 	inode->i_ino = CRAMINO(cramfs_inode);
-	/* inode->i_nlink is left 1 - arguably wrong for directories,
-	   but it's the best we can do without reading the directory
-           contents.  1 yields the right result in GNU find, even
-	   without -noleaf option. */
-	if (S_ISREG(inode->i_mode)) {
-		inode->i_fop = &generic_ro_fops;
-		inode->i_data.a_ops = &cramfs_aops;
-	} else if (S_ISDIR(inode->i_mode)) {
-		inode->i_op = &cramfs_dir_inode_operations;
-		inode->i_fop = &cramfs_directory_operations;
-	} else if (S_ISLNK(inode->i_mode)) {
-		inode->i_op = &page_symlink_inode_operations;
-		inode->i_data.a_ops = &cramfs_aops;
-	} else {
-		inode->i_size = 0;
-		inode->i_blocks = 0;
-		init_special_inode(inode, inode->i_mode,
-			old_decode_dev(cramfs_inode->size));
-	}
 	return 0;
 }
 
@@ -104,12 +59,48 @@ static struct inode *get_cramfs_inode(struct super_block *sb,
 	struct inode *inode = iget5_locked(sb, CRAMINO(cramfs_inode),
 					    cramfs_iget5_test, cramfs_iget5_set,
 					    cramfs_inode);
+	static struct timespec zerotime;
+
 	if (inode && (inode->i_state & I_NEW)) {
+		inode->i_mode = cramfs_inode->mode;
+		inode->i_uid = cramfs_inode->uid;
+		inode->i_size = cramfs_inode->size;
+		inode->i_blocks = (cramfs_inode->size - 1) / 512 + 1;
+		inode->i_gid = cramfs_inode->gid;
+		/* Struct copy intentional */
+		inode->i_mtime = inode->i_atime = inode->i_ctime = zerotime;
+		/* inode->i_nlink is left 1 - arguably wrong for directories,
+		   but it's the best we can do without reading the directory
+		   contents.  1 yields the right result in GNU find, even
+		   without -noleaf option. */
+		if (S_ISREG(inode->i_mode)) {
+			inode->i_fop = &generic_ro_fops;
+			inode->i_data.a_ops = &cramfs_aops;
+		} else if (S_ISDIR(inode->i_mode)) {
+			inode->i_op = &cramfs_dir_inode_operations;
+			inode->i_fop = &cramfs_directory_operations;
+		} else if (S_ISLNK(inode->i_mode)) {
+			inode->i_op = &page_symlink_inode_operations;
+			inode->i_data.a_ops = &cramfs_aops;
+		} else {
+			inode->i_size = 0;
+			inode->i_blocks = 0;
+			init_special_inode(inode, inode->i_mode,
+				old_decode_dev(cramfs_inode->size));
+		}
 		unlock_new_inode(inode);
 	}
 	return inode;
 }
 
+static void cramfs_drop_inode(struct inode *inode)
+{
+	if (inode->i_ino == 1)
+		generic_delete_inode(inode);
+	else
+		generic_drop_inode(inode);
+}
+
 /*
  * We have our own block cache: don't fill up the buffer cache
  * with the rom-image, because the way the filesystem is set
@@ -534,6 +525,7 @@ static const struct super_operations cramfs_ops = {
 	.put_super	= cramfs_put_super,
 	.remount_fs	= cramfs_remount,
 	.statfs		= cramfs_statfs,
+	.drop_inode	= cramfs_drop_inode,
 };
 
 static int cramfs_get_sb(struct file_system_type *fs_type,
diff --git a/fs/ext4/balloc.c b/fs/ext4/balloc.c
index 1ae5004e93fc..e9fa960ba6da 100644
--- a/fs/ext4/balloc.c
+++ b/fs/ext4/balloc.c
@@ -1626,6 +1626,9 @@ ext4_fsblk_t ext4_has_free_blocks(struct ext4_sb_info *sbi,
 		free_blocks =
 			percpu_counter_sum_and_set(&sbi->s_freeblocks_counter);
 #endif
+	if (free_blocks <= root_blocks)
+		/* we don't have free space */
+		return 0;
 	if (free_blocks - root_blocks < nblocks)
 		return free_blocks - root_blocks;
 	return nblocks;
diff --git a/fs/ext4/dir.c b/fs/ext4/dir.c
index d3d23d73c08b..ec8e33b45219 100644
--- a/fs/ext4/dir.c
+++ b/fs/ext4/dir.c
@@ -411,7 +411,7 @@ static int call_filldir(struct file * filp, void * dirent,
 				get_dtype(sb, fname->file_type));
 		if (error) {
 			filp->f_pos = curr_pos;
-			info->extra_fname = fname->next;
+			info->extra_fname = fname;
 			return error;
 		}
 		fname = fname->next;
@@ -450,11 +450,21 @@ static int ext4_dx_readdir(struct file * filp,
 	 * If there are any leftover names on the hash collision
 	 * chain, return them first.
 	 */
-	if (info->extra_fname &&
-	    call_filldir(filp, dirent, filldir, info->extra_fname))
-		goto finished;
+	if (info->extra_fname) {
+		if (call_filldir(filp, dirent, filldir, info->extra_fname))
+			goto finished;
 
-	if (!info->curr_node)
+		info->extra_fname = NULL;
+		info->curr_node = rb_next(info->curr_node);
+		if (!info->curr_node) {
+			if (info->next_hash == ~0) {
+				filp->f_pos = EXT4_HTREE_EOF;
+				goto finished;
+			}
+			info->curr_hash = info->next_hash;
+			info->curr_minor_hash = 0;
+		}
+	} else if (!info->curr_node)
 		info->curr_node = rb_first(&info->root);
 
 	while (1) {
diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h
index 6c7924d9e358..295003241d3d 100644
--- a/fs/ext4/ext4.h
+++ b/fs/ext4/ext4.h
@@ -1072,6 +1072,8 @@ extern void ext4_set_inode_flags(struct inode *);
 extern void ext4_get_inode_flags(struct ext4_inode_info *);
 extern void ext4_set_aops(struct inode *inode);
 extern int ext4_writepage_trans_blocks(struct inode *);
+extern int ext4_meta_trans_blocks(struct inode *, int nrblocks, int idxblocks);
+extern int ext4_chunk_trans_blocks(struct inode *, int nrblocks);
 extern int ext4_block_truncate_page(handle_t *handle,
 		struct address_space *mapping, loff_t from);
 extern int ext4_page_mkwrite(struct vm_area_struct *vma, struct page *page);
@@ -1227,6 +1229,8 @@ extern const struct inode_operations ext4_fast_symlink_inode_operations;
 /* extents.c */
 extern int ext4_ext_tree_init(handle_t *handle, struct inode *);
 extern int ext4_ext_writepage_trans_blocks(struct inode *, int);
+extern int ext4_ext_index_trans_blocks(struct inode *inode, int nrblocks,
+				       int chunk);
 extern int ext4_ext_get_blocks(handle_t *handle, struct inode *inode,
 			ext4_lblk_t iblock,
 			unsigned long max_blocks, struct buffer_head *bh_result,
diff --git a/fs/ext4/ext4_extents.h b/fs/ext4/ext4_extents.h
index 6c166c0a54b7..d33dc56d6986 100644
--- a/fs/ext4/ext4_extents.h
+++ b/fs/ext4/ext4_extents.h
@@ -216,7 +216,9 @@ extern int ext4_ext_calc_metadata_amount(struct inode *inode, int blocks);
 extern ext4_fsblk_t idx_pblock(struct ext4_extent_idx *);
 extern void ext4_ext_store_pblock(struct ext4_extent *, ext4_fsblk_t);
 extern int ext4_extent_tree_init(handle_t *, struct inode *);
-extern int ext4_ext_calc_credits_for_insert(struct inode *, struct ext4_ext_path *);
+extern int ext4_ext_calc_credits_for_single_extent(struct inode *inode,
+						   int num,
+						   struct ext4_ext_path *path);
 extern int ext4_ext_try_to_merge(struct inode *inode,
 				 struct ext4_ext_path *path,
 				 struct ext4_extent *);
diff --git a/fs/ext4/ext4_jbd2.h b/fs/ext4/ext4_jbd2.h
index eb8bc3afe6e9..b455c685a98b 100644
--- a/fs/ext4/ext4_jbd2.h
+++ b/fs/ext4/ext4_jbd2.h
@@ -51,6 +51,14 @@
 					 EXT4_XATTR_TRANS_BLOCKS - 2 + \
 					 2*EXT4_QUOTA_TRANS_BLOCKS(sb))
 
+/*
+ * Define the number of metadata blocks we need to account to modify data.
+ *
+ * This include super block, inode block, quota blocks and xattr blocks
+ */
+#define EXT4_META_TRANS_BLOCKS(sb)	(EXT4_XATTR_TRANS_BLOCKS + \
+					2*EXT4_QUOTA_TRANS_BLOCKS(sb))
+
 /* Delete operations potentially hit one directory's namespace plus an
  * entire inode, plus arbitrary amounts of bitmap/indirection data.  Be
  * generous.  We can grow the delete transaction later if necessary. */
diff --git a/fs/ext4/extents.c b/fs/ext4/extents.c
index 612c3d2c3824..b24d3c53f20c 100644
--- a/fs/ext4/extents.c
+++ b/fs/ext4/extents.c
@@ -1747,54 +1747,61 @@ static int ext4_ext_rm_idx(handle_t *handle, struct inode *inode,
 }
 
 /*
- * ext4_ext_calc_credits_for_insert:
- * This routine returns max. credits that the extent tree can consume.
- * It should be OK for low-performance paths like ->writepage()
- * To allow many writing processes to fit into a single transaction,
- * the caller should calculate credits under i_data_sem and
- * pass the actual path.
+ * ext4_ext_calc_credits_for_single_extent:
+ * This routine returns max. credits that needed to insert an extent
+ * to the extent tree.
+ * When pass the actual path, the caller should calculate credits
+ * under i_data_sem.
  */
-int ext4_ext_calc_credits_for_insert(struct inode *inode,
+int ext4_ext_calc_credits_for_single_extent(struct inode *inode, int nrblocks,
 						struct ext4_ext_path *path)
 {
-	int depth, needed;
-
 	if (path) {
+		int depth = ext_depth(inode);
+		int ret = 0;
+
 		/* probably there is space in leaf? */
-		depth = ext_depth(inode);
 		if (le16_to_cpu(path[depth].p_hdr->eh_entries)
-				< le16_to_cpu(path[depth].p_hdr->eh_max))
-			return 1;
-	}
+				< le16_to_cpu(path[depth].p_hdr->eh_max)) {
 
-	/*
-	 * given 32-bit logical block (4294967296 blocks), max. tree
-	 * can be 4 levels in depth -- 4 * 340^4 == 53453440000.
-	 * Let's also add one more level for imbalance.
-	 */
-	depth = 5;
-
-	/* allocation of new data block(s) */
-	needed = 2;
+			/*
+			 *  There are some space in the leaf tree, no
+			 *  need to account for leaf block credit
+			 *
+			 *  bitmaps and block group descriptor blocks
+			 *  and other metadat blocks still need to be
+			 *  accounted.
+			 */
+			/* 1 bitmap, 1 block group descriptor */
+			ret = 2 + EXT4_META_TRANS_BLOCKS(inode->i_sb);
+		}
+	}
 
-	/*
-	 * tree can be full, so it would need to grow in depth:
-	 * we need one credit to modify old root, credits for
-	 * new root will be added in split accounting
-	 */
-	needed += 1;
+	return ext4_chunk_trans_blocks(inode, nrblocks);
+}
 
-	/*
-	 * Index split can happen, we would need:
-	 *    allocate intermediate indexes (bitmap + group)
-	 *  + change two blocks at each level, but root (already included)
-	 */
-	needed += (depth * 2) + (depth * 2);
+/*
+ * How many index/leaf blocks need to change/allocate to modify nrblocks?
+ *
+ * if nrblocks are fit in a single extent (chunk flag is 1), then
+ * in the worse case, each tree level index/leaf need to be changed
+ * if the tree split due to insert a new extent, then the old tree
+ * index/leaf need to be updated too
+ *
+ * If the nrblocks are discontiguous, they could cause
+ * the whole tree split more than once, but this is really rare.
+ */
+int ext4_ext_index_trans_blocks(struct inode *inode, int nrblocks, int chunk)
+{
+	int index;
+	int depth = ext_depth(inode);
 
-	/* any allocation modifies superblock */
-	needed += 1;
+	if (chunk)
+		index = depth * 2;
+	else
+		index = depth * 3;
 
-	return needed;
+	return index;
 }
 
 static int ext4_remove_blocks(handle_t *handle, struct inode *inode,
@@ -1921,9 +1928,7 @@ ext4_ext_rm_leaf(handle_t *handle, struct inode *inode,
 			correct_index = 1;
 			credits += (ext_depth(inode)) + 1;
 		}
-#ifdef CONFIG_QUOTA
 		credits += 2 * EXT4_QUOTA_TRANS_BLOCKS(inode->i_sb);
-#endif
 
 		err = ext4_ext_journal_restart(handle, credits);
 		if (err)
@@ -2805,7 +2810,7 @@ void ext4_ext_truncate(struct inode *inode)
 	/*
 	 * probably first extent we're gonna free will be last in block
 	 */
-	err = ext4_writepage_trans_blocks(inode) + 3;
+	err = ext4_writepage_trans_blocks(inode);
 	handle = ext4_journal_start(inode, err);
 	if (IS_ERR(handle))
 		return;
@@ -2819,7 +2824,7 @@ void ext4_ext_truncate(struct inode *inode)
 	down_write(&EXT4_I(inode)->i_data_sem);
 	ext4_ext_invalidate_cache(inode);
 
-	ext4_mb_discard_inode_preallocations(inode);
+	ext4_discard_reservation(inode);
 
 	/*
 	 * TODO: optimization is possible here.
@@ -2858,27 +2863,6 @@ out_stop:
 	ext4_journal_stop(handle);
 }
 
-/*
- * ext4_ext_writepage_trans_blocks:
- * calculate max number of blocks we could modify
- * in order to allocate new block for an inode
- */
-int ext4_ext_writepage_trans_blocks(struct inode *inode, int num)
-{
-	int needed;
-
-	needed = ext4_ext_calc_credits_for_insert(inode, NULL);
-
-	/* caller wants to allocate num blocks, but note it includes sb */
-	needed = needed * num - (num - 1);
-
-#ifdef CONFIG_QUOTA
-	needed += 2 * EXT4_QUOTA_TRANS_BLOCKS(inode->i_sb);
-#endif
-
-	return needed;
-}
-
 static void ext4_falloc_update_inode(struct inode *inode,
 				int mode, loff_t new_size, int update_ctime)
 {
@@ -2939,10 +2923,9 @@ long ext4_fallocate(struct inode *inode, int mode, loff_t offset, loff_t len)
 	max_blocks = (EXT4_BLOCK_ALIGN(len + offset, blkbits) >> blkbits)
 							- block;
 	/*
-	 * credits to insert 1 extent into extent tree + buffers to be able to
-	 * modify 1 super block, 1 block bitmap and 1 group descriptor.
+	 * credits to insert 1 extent into extent tree
 	 */
-	credits = EXT4_DATA_TRANS_BLOCKS(inode->i_sb) + 3;
+	credits = ext4_chunk_trans_blocks(inode, max_blocks);
 	mutex_lock(&inode->i_mutex);
 retry:
 	while (ret >= 0 && ret < max_blocks) {
diff --git a/fs/ext4/ialloc.c b/fs/ext4/ialloc.c
index 655e760212b8..f344834bbf58 100644
--- a/fs/ext4/ialloc.c
+++ b/fs/ext4/ialloc.c
@@ -351,7 +351,7 @@ find_close_to_parent:
 			goto found_flexbg;
 		}
 
-		if (best_flex < 0 ||
+		if (flex_group[best_flex].free_inodes == 0 ||
 		    (flex_group[i].free_blocks >
 		     flex_group[best_flex].free_blocks &&
 		     flex_group[i].free_inodes))
diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
index 59fbbe899acc..7e91913e325b 100644
--- a/fs/ext4/inode.c
+++ b/fs/ext4/inode.c
@@ -41,6 +41,8 @@
 #include "acl.h"
 #include "ext4_extents.h"
 
+#define MPAGE_DA_EXTENT_TAIL 0x01
+
 static inline int ext4_begin_ordered_truncate(struct inode *inode,
 					      loff_t new_size)
 {
@@ -1005,6 +1007,9 @@ static int ext4_indirect_calc_metadata_amount(struct inode *inode, int blocks)
  */
 static int ext4_calc_metadata_amount(struct inode *inode, int blocks)
 {
+	if (!blocks)
+		return 0;
+
 	if (EXT4_I(inode)->i_flags & EXT4_EXTENTS_FL)
 		return ext4_ext_calc_metadata_amount(inode, blocks);
 
@@ -1041,18 +1046,6 @@ static void ext4_da_update_reserve_space(struct inode *inode, int used)
 	spin_unlock(&EXT4_I(inode)->i_block_reservation_lock);
 }
 
-/* Maximum number of blocks we map for direct IO at once. */
-#define DIO_MAX_BLOCKS 4096
-/*
- * Number of credits we need for writing DIO_MAX_BLOCKS:
- * We need sb + group descriptor + bitmap + inode -> 4
- * For B blocks with A block pointers per block we need:
- * 1 (triple ind.) + (B/A/A + 2) (doubly ind.) + (B/A + 2) (indirect).
- * If we plug in 4096 for B and 256 for A (for 1KB block size), we get 25.
- */
-#define DIO_CREDITS 25
-
-
 /*
  * The ext4_get_blocks_wrap() function try to look up the requested blocks,
  * and returns if the blocks are already mapped.
@@ -1164,19 +1157,23 @@ int ext4_get_blocks_wrap(handle_t *handle, struct inode *inode, sector_t block,
 	return retval;
 }
 
+/* Maximum number of blocks we map for direct IO at once. */
+#define DIO_MAX_BLOCKS 4096
+
 static int ext4_get_block(struct inode *inode, sector_t iblock,
 			struct buffer_head *bh_result, int create)
 {
 	handle_t *handle = ext4_journal_current_handle();
 	int ret = 0, started = 0;
 	unsigned max_blocks = bh_result->b_size >> inode->i_blkbits;
+	int dio_credits;
 
 	if (create && !handle) {
 		/* Direct IO write... */
 		if (max_blocks > DIO_MAX_BLOCKS)
 			max_blocks = DIO_MAX_BLOCKS;
-		handle = ext4_journal_start(inode, DIO_CREDITS +
-			      2 * EXT4_QUOTA_TRANS_BLOCKS(inode->i_sb));
+		dio_credits = ext4_chunk_trans_blocks(inode, max_blocks);
+		handle = ext4_journal_start(inode, dio_credits);
 		if (IS_ERR(handle)) {
 			ret = PTR_ERR(handle);
 			goto out;
@@ -1559,7 +1556,25 @@ static void ext4_da_release_space(struct inode *inode, int to_free)
 	struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb);
 	int total, mdb, mdb_free, release;
 
+	if (!to_free)
+		return;		/* Nothing to release, exit */
+
 	spin_lock(&EXT4_I(inode)->i_block_reservation_lock);
+
+	if (!EXT4_I(inode)->i_reserved_data_blocks) {
+		/*
+		 * if there is no reserved blocks, but we try to free some
+		 * then the counter is messed up somewhere.
+		 * but since this function is called from invalidate
+		 * page, it's harmless to return without any action
+		 */
+		printk(KERN_INFO "ext4 delalloc try to release %d reserved "
+			    "blocks for inode %lu, but there is no reserved "
+			    "data blocks\n", to_free, inode->i_ino);
+		spin_unlock(&EXT4_I(inode)->i_block_reservation_lock);
+		return;
+	}
+
 	/* recalculate the number of metablocks still need to be reserved */
 	total = EXT4_I(inode)->i_reserved_data_blocks - to_free;
 	mdb = ext4_calc_metadata_amount(inode, total);
@@ -1613,11 +1628,13 @@ struct mpage_da_data {
 	unsigned long first_page, next_page;	/* extent of pages */
 	get_block_t *get_block;
 	struct writeback_control *wbc;
+	int io_done;
+	long pages_written;
 };
 
 /*
  * mpage_da_submit_io - walks through extent of pages and try to write
- * them with __mpage_writepage()
+ * them with writepage() call back
  *
  * @mpd->inode: inode
  * @mpd->first_page: first page of the extent
@@ -1632,18 +1649,11 @@ struct mpage_da_data {
 static int mpage_da_submit_io(struct mpage_da_data *mpd)
 {
 	struct address_space *mapping = mpd->inode->i_mapping;
-	struct mpage_data mpd_pp = {
-		.bio = NULL,
-		.last_block_in_bio = 0,
-		.get_block = mpd->get_block,
-		.use_writepage = 1,
-	};
 	int ret = 0, err, nr_pages, i;
 	unsigned long index, end;
 	struct pagevec pvec;
 
 	BUG_ON(mpd->next_page <= mpd->first_page);
-
 	pagevec_init(&pvec, 0);
 	index = mpd->first_page;
 	end = mpd->next_page - 1;
@@ -1661,8 +1671,9 @@ static int mpage_da_submit_io(struct mpage_da_data *mpd)
 				break;
 			index++;
 
-			err = __mpage_writepage(page, mpd->wbc, &mpd_pp);
-
+			err = mapping->a_ops->writepage(page, mpd->wbc);
+			if (!err)
+				mpd->pages_written++;
 			/*
 			 * In error case, we have to continue because
 			 * remaining pages are still locked
@@ -1673,9 +1684,6 @@ static int mpage_da_submit_io(struct mpage_da_data *mpd)
 		}
 		pagevec_release(&pvec);
 	}
-	if (mpd_pp.bio)
-		mpage_bio_submit(WRITE, mpd_pp.bio);
-
 	return ret;
 }
 
@@ -1698,7 +1706,7 @@ static void mpage_put_bnr_to_bhs(struct mpage_da_data *mpd, sector_t logical,
 	int blocks = exbh->b_size >> inode->i_blkbits;
 	sector_t pblock = exbh->b_blocknr, cur_logical;
 	struct buffer_head *head, *bh;
-	unsigned long index, end;
+	pgoff_t index, end;
 	struct pagevec pvec;
 	int nr_pages, i;
 
@@ -1741,6 +1749,13 @@ static void mpage_put_bnr_to_bhs(struct mpage_da_data *mpd, sector_t logical,
 				if (buffer_delay(bh)) {
 					bh->b_blocknr = pblock;
 					clear_buffer_delay(bh);
+					bh->b_bdev = inode->i_sb->s_bdev;
+				} else if (buffer_unwritten(bh)) {
+					bh->b_blocknr = pblock;
+					clear_buffer_unwritten(bh);
+					set_buffer_mapped(bh);
+					set_buffer_new(bh);
+					bh->b_bdev = inode->i_sb->s_bdev;
 				} else if (buffer_mapped(bh))
 					BUG_ON(bh->b_blocknr != pblock);
 
@@ -1776,13 +1791,11 @@ static inline void __unmap_underlying_blocks(struct inode *inode,
  *
  * The function skips space we know is already mapped to disk blocks.
  *
- * The function ignores errors ->get_block() returns, thus real
- * error handling is postponed to __mpage_writepage()
  */
 static void mpage_da_map_blocks(struct mpage_da_data *mpd)
 {
+	int err = 0;
 	struct buffer_head *lbh = &mpd->lbh;
-	int err = 0, remain = lbh->b_size;
 	sector_t next = lbh->b_blocknr;
 	struct buffer_head new;
 
@@ -1792,38 +1805,36 @@ static void mpage_da_map_blocks(struct mpage_da_data *mpd)
 	if (buffer_mapped(lbh) && !buffer_delay(lbh))
 		return;
 
-	while (remain) {
-		new.b_state = lbh->b_state;
-		new.b_blocknr = 0;
-		new.b_size = remain;
-		err = mpd->get_block(mpd->inode, next, &new, 1);
-		if (err) {
-			/*
-			 * Rather than implement own error handling
-			 * here, we just leave remaining blocks
-			 * unallocated and try again with ->writepage()
-			 */
-			break;
-		}
-		BUG_ON(new.b_size == 0);
+	new.b_state = lbh->b_state;
+	new.b_blocknr = 0;
+	new.b_size = lbh->b_size;
 
-		if (buffer_new(&new))
-			__unmap_underlying_blocks(mpd->inode, &new);
+	/*
+	 * If we didn't accumulate anything
+	 * to write simply return
+	 */
+	if (!new.b_size)
+		return;
+	err = mpd->get_block(mpd->inode, next, &new, 1);
+	if (err)
+		return;
+	BUG_ON(new.b_size == 0);
 
-		/*
-		 * If blocks are delayed marked, we need to
-		 * put actual blocknr and drop delayed bit
-		 */
-		if (buffer_delay(lbh))
-			mpage_put_bnr_to_bhs(mpd, next, &new);
+	if (buffer_new(&new))
+		__unmap_underlying_blocks(mpd->inode, &new);
 
-		/* go for the remaining blocks */
-		next += new.b_size >> mpd->inode->i_blkbits;
-		remain -= new.b_size;
-	}
+	/*
+	 * If blocks are delayed marked, we need to
+	 * put actual blocknr and drop delayed bit
+	 */
+	if (buffer_delay(lbh) || buffer_unwritten(lbh))
+		mpage_put_bnr_to_bhs(mpd, next, &new);
+
+	return;
 }
 
-#define BH_FLAGS ((1 << BH_Uptodate) | (1 << BH_Mapped) | (1 << BH_Delay))
+#define BH_FLAGS ((1 << BH_Uptodate) | (1 << BH_Mapped) | \
+		(1 << BH_Delay) | (1 << BH_Unwritten))
 
 /*
  * mpage_add_bh_to_extent - try to add one more block to extent of blocks
@@ -1837,41 +1848,61 @@ static void mpage_da_map_blocks(struct mpage_da_data *mpd)
 static void mpage_add_bh_to_extent(struct mpage_da_data *mpd,
 				   sector_t logical, struct buffer_head *bh)
 {
-	struct buffer_head *lbh = &mpd->lbh;
 	sector_t next;
+	size_t b_size = bh->b_size;
+	struct buffer_head *lbh = &mpd->lbh;
+	int nrblocks = lbh->b_size >> mpd->inode->i_blkbits;
 
-	next = lbh->b_blocknr + (lbh->b_size >> mpd->inode->i_blkbits);
-
+	/* check if thereserved journal credits might overflow */
+	if (!(EXT4_I(mpd->inode)->i_flags & EXT4_EXTENTS_FL)) {
+		if (nrblocks >= EXT4_MAX_TRANS_DATA) {
+			/*
+			 * With non-extent format we are limited by the journal
+			 * credit available.  Total credit needed to insert
+			 * nrblocks contiguous blocks is dependent on the
+			 * nrblocks.  So limit nrblocks.
+			 */
+			goto flush_it;
+		} else if ((nrblocks + (b_size >> mpd->inode->i_blkbits)) >
+				EXT4_MAX_TRANS_DATA) {
+			/*
+			 * Adding the new buffer_head would make it cross the
+			 * allowed limit for which we have journal credit
+			 * reserved. So limit the new bh->b_size
+			 */
+			b_size = (EXT4_MAX_TRANS_DATA - nrblocks) <<
+						mpd->inode->i_blkbits;
+			/* we will do mpage_da_submit_io in the next loop */
+		}
+	}
 	/*
 	 * First block in the extent
 	 */
 	if (lbh->b_size == 0) {
 		lbh->b_blocknr = logical;
-		lbh->b_size = bh->b_size;
+		lbh->b_size = b_size;
 		lbh->b_state = bh->b_state & BH_FLAGS;
 		return;
 	}
 
+	next = lbh->b_blocknr + nrblocks;
 	/*
 	 * Can we merge the block to our big extent?
 	 */
 	if (logical == next && (bh->b_state & BH_FLAGS) == lbh->b_state) {
-		lbh->b_size += bh->b_size;
+		lbh->b_size += b_size;
 		return;
 	}
 
+flush_it:
 	/*
 	 * We couldn't merge the block to our extent, so we
 	 * need to flush current  extent and start new one
 	 */
 	mpage_da_map_blocks(mpd);
-
-	/*
-	 * Now start a new extent
-	 */
-	lbh->b_size = bh->b_size;
-	lbh->b_state = bh->b_state & BH_FLAGS;
-	lbh->b_blocknr = logical;
+	mpage_da_submit_io(mpd);
+	mpd->io_done = 1;
+	return;
 }
 
 /*
@@ -1891,17 +1922,35 @@ static int __mpage_da_writepage(struct page *page,
 	struct buffer_head *bh, *head, fake;
 	sector_t logical;
 
+	if (mpd->io_done) {
+		/*
+		 * Rest of the page in the page_vec
+		 * redirty then and skip then. We will
+		 * try to to write them again after
+		 * starting a new transaction
+		 */
+		redirty_page_for_writepage(wbc, page);
+		unlock_page(page);
+		return MPAGE_DA_EXTENT_TAIL;
+	}
 	/*
 	 * Can we merge this page to current extent?
 	 */
 	if (mpd->next_page != page->index) {
 		/*
 		 * Nope, we can't. So, we map non-allocated blocks
-		 * and start IO on them using __mpage_writepage()
+		 * and start IO on them using writepage()
 		 */
 		if (mpd->next_page != mpd->first_page) {
 			mpage_da_map_blocks(mpd);
 			mpage_da_submit_io(mpd);
+			/*
+			 * skip rest of the page in the page_vec
+			 */
+			mpd->io_done = 1;
+			redirty_page_for_writepage(wbc, page);
+			unlock_page(page);
+			return MPAGE_DA_EXTENT_TAIL;
 		}
 
 		/*
@@ -1932,6 +1981,8 @@ static int __mpage_da_writepage(struct page *page,
 		set_buffer_dirty(bh);
 		set_buffer_uptodate(bh);
 		mpage_add_bh_to_extent(mpd, logical, bh);
+		if (mpd->io_done)
+			return MPAGE_DA_EXTENT_TAIL;
 	} else {
 		/*
 		 * Page with regular buffer heads, just add all dirty ones
@@ -1940,8 +1991,12 @@ static int __mpage_da_writepage(struct page *page,
 		bh = head;
 		do {
 			BUG_ON(buffer_locked(bh));
-			if (buffer_dirty(bh))
+			if (buffer_dirty(bh) &&
+				(!buffer_mapped(bh) || buffer_delay(bh))) {
 				mpage_add_bh_to_extent(mpd, logical, bh);
+				if (mpd->io_done)
+					return MPAGE_DA_EXTENT_TAIL;
+			}
 			logical++;
 		} while ((bh = bh->b_this_page) != head);
 	}
@@ -1960,22 +2015,13 @@ static int __mpage_da_writepage(struct page *page,
  *
  * This is a library function, which implements the writepages()
  * address_space_operation.
- *
- * In order to avoid duplication of logic that deals with partial pages,
- * multiple bio per page, etc, we find non-allocated blocks, allocate
- * them with minimal calls to ->get_block() and re-use __mpage_writepage()
- *
- * It's important that we call __mpage_writepage() only once for each
- * involved page, otherwise we'd have to implement more complicated logic
- * to deal with pages w/o PG_lock or w/ PG_writeback and so on.
- *
- * See comments to mpage_writepages()
  */
 static int mpage_da_writepages(struct address_space *mapping,
 			       struct writeback_control *wbc,
 			       get_block_t get_block)
 {
 	struct mpage_da_data mpd;
+	long to_write;
 	int ret;
 
 	if (!get_block)
@@ -1989,17 +2035,22 @@ static int mpage_da_writepages(struct address_space *mapping,
 	mpd.first_page = 0;
 	mpd.next_page = 0;
 	mpd.get_block = get_block;
+	mpd.io_done = 0;
+	mpd.pages_written = 0;
+
+	to_write = wbc->nr_to_write;
 
 	ret = write_cache_pages(mapping, wbc, __mpage_da_writepage, &mpd);
 
 	/*
 	 * Handle last extent of pages
 	 */
-	if (mpd.next_page != mpd.first_page) {
+	if (!mpd.io_done && mpd.next_page != mpd.first_page) {
 		mpage_da_map_blocks(&mpd);
 		mpage_da_submit_io(&mpd);
 	}
 
+	wbc->nr_to_write = to_write - mpd.pages_written;
 	return ret;
 }
 
@@ -2204,63 +2255,95 @@ static int ext4_da_writepage(struct page *page,
 }
 
 /*
- * For now just follow the DIO way to estimate the max credits
- * needed to write out EXT4_MAX_WRITEBACK_PAGES.
- * todo: need to calculate the max credits need for
- * extent based files, currently the DIO credits is based on
- * indirect-blocks mapping way.
- *
- * Probably should have a generic way to calculate credits
- * for DIO, writepages, and truncate
+ * This is called via ext4_da_writepages() to
+ * calulate the total number of credits to reserve to fit
+ * a single extent allocation into a single transaction,
+ * ext4_da_writpeages() will loop