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

40 files changed, 606 insertions, 468 deletions

diff --git a/fs/bio.c b/fs/bio.c
index 242e409dab4..3312fcc3c09 100644
--- a/fs/bio.c
+++ b/fs/bio.c
@@ -903,7 +903,7 @@ void bio_set_pages_dirty(struct bio *bio)
 	}
 }
 
-void bio_release_pages(struct bio *bio)
+static void bio_release_pages(struct bio *bio)
 {
 	struct bio_vec *bvec = bio->bi_io_vec;
 	int i;
diff --git a/fs/block_dev.c b/fs/block_dev.c
index 67fe72ce6ac..7d822fae776 100644
--- a/fs/block_dev.c
+++ b/fs/block_dev.c
@@ -31,6 +31,8 @@ struct bdev_inode {
 	struct inode vfs_inode;
 };
 
+static const struct address_space_operations def_blk_aops;
+
 static inline struct bdev_inode *BDEV_I(struct inode *inode)
 {
 	return container_of(inode, struct bdev_inode, vfs_inode);
@@ -171,203 +173,6 @@ blkdev_direct_IO(int rw, struct kiocb *iocb, const struct iovec *iov,
 				iov, offset, nr_segs, blkdev_get_blocks, NULL);
 }
 
-#if 0
-static void blk_end_aio(struct bio *bio, int error)
-{
-	struct kiocb *iocb = bio->bi_private;
-	atomic_t *bio_count = &iocb->ki_bio_count;
-
-	if (bio_data_dir(bio) == READ)
-		bio_check_pages_dirty(bio);
-	else {
-		bio_release_pages(bio);
-		bio_put(bio);
-	}
-
-	/* iocb->ki_nbytes stores error code from LLDD */
-	if (error)
-		iocb->ki_nbytes = -EIO;
-
-	if (atomic_dec_and_test(bio_count)) {
-		if ((long)iocb->ki_nbytes < 0)
-			aio_complete(iocb, iocb->ki_nbytes, 0);
-		else
-			aio_complete(iocb, iocb->ki_left, 0);
-	}
-
-	return 0;
-}
-
-#define VEC_SIZE	16
-struct pvec {
-	unsigned short nr;
-	unsigned short idx;
-	struct page *page[VEC_SIZE];
-};
-
-#define PAGES_SPANNED(addr, len)	\
-	(DIV_ROUND_UP((addr) + (len), PAGE_SIZE) - (addr) / PAGE_SIZE);
-
-/*
- * get page pointer for user addr, we internally cache struct page array for
- * (addr, count) range in pvec to avoid frequent call to get_user_pages.  If
- * internal page list is exhausted, a batch count of up to VEC_SIZE is used
- * to get next set of page struct.
- */
-static struct page *blk_get_page(unsigned long addr, size_t count, int rw,
-				 struct pvec *pvec)
-{
-	int ret, nr_pages;
-	if (pvec->idx == pvec->nr) {
-		nr_pages = PAGES_SPANNED(addr, count);
-		nr_pages = min(nr_pages, VEC_SIZE);
-		down_read(&current->mm->mmap_sem);
-		ret = get_user_pages(current, current->mm, addr, nr_pages,
-				     rw == READ, 0, pvec->page, NULL);
-		up_read(&current->mm->mmap_sem);
-		if (ret < 0)
-			return ERR_PTR(ret);
-		pvec->nr = ret;
-		pvec->idx = 0;
-	}
-	return pvec->page[pvec->idx++];
-}
-
-/* return a page back to pvec array */
-static void blk_unget_page(struct page *page, struct pvec *pvec)
-{
-	pvec->page[--pvec->idx] = page;
-}
-
-static ssize_t
-blkdev_direct_IO(int rw, struct kiocb *iocb, const struct iovec *iov,
-		 loff_t pos, unsigned long nr_segs)
-{
-	struct inode *inode = iocb->ki_filp->f_mapping->host;
-	unsigned blkbits = blksize_bits(bdev_hardsect_size(I_BDEV(inode)));
-	unsigned blocksize_mask = (1 << blkbits) - 1;
-	unsigned long seg = 0;	/* iov segment iterator */
-	unsigned long nvec;	/* number of bio vec needed */
-	unsigned long cur_off;	/* offset into current page */
-	unsigned long cur_len;	/* I/O len of current page, up to PAGE_SIZE */
-
-	unsigned long addr;	/* user iovec address */
-	size_t count;		/* user iovec len */
-	size_t nbytes = iocb->ki_nbytes = iocb->ki_left; /* total xfer size */
-	loff_t size;		/* size of block device */
-	struct bio *bio;
-	atomic_t *bio_count = &iocb->ki_bio_count;
-	struct page *page;
-	struct pvec pvec;
-
-	pvec.nr = 0;
-	pvec.idx = 0;
-
-	if (pos & blocksize_mask)
-		return -EINVAL;
-
-	size = i_size_read(inode);
-	if (pos + nbytes > size) {
-		nbytes = size - pos;
-		iocb->ki_left = nbytes;
-	}
-
-	/*
-	 * check first non-zero iov alignment, the remaining
-	 * iov alignment is checked inside bio loop below.
-	 */
-	do {
-		addr = (unsigned long) iov[seg].iov_base;
-		count = min(iov[seg].iov_len, nbytes);
-		if (addr & blocksize_mask || count & blocksize_mask)
-			return -EINVAL;
-	} while (!count && ++seg < nr_segs);
-	atomic_set(bio_count, 1);
-
-	while (nbytes) {
-		/* roughly estimate number of bio vec needed */
-		nvec = (nbytes + PAGE_SIZE - 1) / PAGE_SIZE;
-		nvec = max(nvec, nr_segs - seg);
-		nvec = min(nvec, (unsigned long) BIO_MAX_PAGES);
-
-		/* bio_alloc should not fail with GFP_KERNEL flag */
-		bio = bio_alloc(GFP_KERNEL, nvec);
-		bio->bi_bdev = I_BDEV(inode);
-		bio->bi_end_io = blk_end_aio;
-		bio->bi_private = iocb;
-		bio->bi_sector = pos >> blkbits;
-same_bio:
-		cur_off = addr & ~PAGE_MASK;
-		cur_len = PAGE_SIZE - cur_off;
-		if (count < cur_len)
-			cur_len = count;
-
-		page = blk_get_page(addr, count, rw, &pvec);
-		if (unlikely(IS_ERR(page)))
-			goto backout;
-
-		if (bio_add_page(bio, page, cur_len, cur_off)) {
-			pos += cur_len;
-			addr += cur_len;
-			count -= cur_len;
-			nbytes -= cur_len;
-
-			if (count)
-				goto same_bio;
-			while (++seg < nr_segs) {
-				addr = (unsigned long) iov[seg].iov_base;
-				count = iov[seg].iov_len;
-				if (!count)
-					continue;
-				if (unlikely(addr & blocksize_mask ||
-					     count & blocksize_mask)) {
-					page = ERR_PTR(-EINVAL);
-					goto backout;
-				}
-				count = min(count, nbytes);
-				goto same_bio;
-			}
-		} else {
-			blk_unget_page(page, &pvec);
-		}
-
-		/* bio is ready, submit it */
-		if (rw == READ)
-			bio_set_pages_dirty(bio);
-		atomic_inc(bio_count);
-		submit_bio(rw, bio);
-	}
-
-completion:
-	iocb->ki_left -= nbytes;
-	nbytes = iocb->ki_left;
-	iocb->ki_pos += nbytes;
-
-	blk_run_address_space(inode->i_mapping);
-	if (atomic_dec_and_test(bio_count))
-		aio_complete(iocb, nbytes, 0);
-
-	return -EIOCBQUEUED;
-
-backout:
-	/*
-	 * back out nbytes count constructed so far for this bio,
-	 * we will throw away current bio.
-	 */
-	nbytes += bio->bi_size;
-	bio_release_pages(bio);
-	bio_put(bio);
-
-	/*
-	 * if no bio was submmitted, return the error code.
-	 * otherwise, proceed with pending I/O completion.
-	 */
-	if (atomic_read(bio_count) == 1)
-		return PTR_ERR(page);
-	goto completion;
-}
-#endif
-
 static int blkdev_writepage(struct page *page, struct writeback_control *wbc)
 {
 	return block_write_full_page(page, blkdev_get_block, wbc);
@@ -1334,7 +1139,7 @@ static long block_ioctl(struct file *file, unsigned cmd, unsigned long arg)
 	return blkdev_ioctl(file->f_mapping->host, file, cmd, arg);
 }
 
-const struct address_space_operations def_blk_aops = {
+static const struct address_space_operations def_blk_aops = {
 	.readpage	= blkdev_readpage,
 	.writepage	= blkdev_writepage,
 	.sync_page	= block_sync_page,
diff --git a/fs/dlm/rcom.c b/fs/dlm/rcom.c
index 035e6f9990b..67522c268c1 100644
--- a/fs/dlm/rcom.c
+++ b/fs/dlm/rcom.c
@@ -215,6 +215,8 @@ int dlm_rcom_names(struct dlm_ls *ls, int nodeid, char *last_name, int last_len)
 	ls->ls_recover_nodeid = nodeid;
 
 	if (nodeid == dlm_our_nodeid()) {
+		ls->ls_recover_buf->rc_header.h_length =
+			dlm_config.ci_buffer_size;
 		dlm_copy_master_names(ls, last_name, last_len,
 		                      ls->ls_recover_buf->rc_buf,
 		                      max_size, nodeid);
diff --git a/fs/efs/dir.c b/fs/efs/dir.c
index dfb5cb40021..49308a29798 100644
--- a/fs/efs/dir.c
+++ b/fs/efs/dir.c
@@ -5,8 +5,8 @@
  */
 
 #include <linux/buffer_head.h>
-#include <linux/efs_fs.h>
 #include <linux/smp_lock.h>
+#include "efs.h"
 
 static int efs_readdir(struct file *, void *, filldir_t);
 
diff --git a/fs/efs/efs.h b/fs/efs/efs.h
new file mode 100644
index 00000000000..d8305b582ab
--- /dev/null
+++ b/fs/efs/efs.h
@@ -0,0 +1,140 @@
+/*
+ * Copyright (c) 1999 Al Smith
+ *
+ * Portions derived from work (c) 1995,1996 Christian Vogelgsang.
+ * Portions derived from IRIX header files (c) 1988 Silicon Graphics
+ */
+#ifndef _EFS_EFS_H_
+#define _EFS_EFS_H_
+
+#include <linux/fs.h>
+#include <asm/uaccess.h>
+
+#define EFS_VERSION "1.0a"
+
+static const char cprt[] = "EFS: "EFS_VERSION" - (c) 1999 Al Smith <Al.Smith@aeschi.ch.eu.org>";
+
+
+/* 1 block is 512 bytes */
+#define	EFS_BLOCKSIZE_BITS	9
+#define	EFS_BLOCKSIZE		(1 << EFS_BLOCKSIZE_BITS)
+
+typedef	int32_t		efs_block_t;
+typedef uint32_t	efs_ino_t;
+
+#define	EFS_DIRECTEXTENTS	12
+
+/*
+ * layout of an extent, in memory and on disk. 8 bytes exactly.
+ */
+typedef union extent_u {
+	unsigned char raw[8];
+	struct extent_s {
+		unsigned int	ex_magic:8;	/* magic # (zero) */
+		unsigned int	ex_bn:24;	/* basic block */
+		unsigned int	ex_length:8;	/* numblocks in this extent */
+		unsigned int	ex_offset:24;	/* logical offset into file */
+	} cooked;
+} efs_extent;
+
+typedef struct edevs {
+	__be16		odev;
+	__be32		ndev;
+} efs_devs;
+
+/*
+ * extent based filesystem inode as it appears on disk.  The efs inode
+ * is exactly 128 bytes long.
+ */
+struct	efs_dinode {
+	__be16		di_mode;	/* mode and type of file */
+	__be16		di_nlink;	/* number of links to file */
+	__be16		di_uid;		/* owner's user id */
+	__be16		di_gid;		/* owner's group id */
+	__be32		di_size;	/* number of bytes in file */
+	__be32		di_atime;	/* time last accessed */
+	__be32		di_mtime;	/* time last modified */
+	__be32		di_ctime;	/* time created */
+	__be32		di_gen;		/* generation number */
+	__be16		di_numextents;	/* # of extents */
+	u_char		di_version;	/* version of inode */
+	u_char		di_spare;	/* spare - used by AFS */
+	union di_addr {
+		efs_extent	di_extents[EFS_DIRECTEXTENTS];
+		efs_devs	di_dev;	/* device for IFCHR/IFBLK */
+	} di_u;
+};
+
+/* efs inode storage in memory */
+struct efs_inode_info {
+	int		numextents;
+	int		lastextent;
+
+	efs_extent	extents[EFS_DIRECTEXTENTS];
+	struct inode	vfs_inode;
+};
+
+#include <linux/efs_fs_sb.h>
+
+#define EFS_DIRBSIZE_BITS	EFS_BLOCKSIZE_BITS
+#define EFS_DIRBSIZE		(1 << EFS_DIRBSIZE_BITS)
+
+struct efs_dentry {
+	__be32		inode;
+	unsigned char	namelen;
+	char		name[3];
+};
+
+#define EFS_DENTSIZE	(sizeof(struct efs_dentry) - 3 + 1)
+#define EFS_MAXNAMELEN  ((1 << (sizeof(char) * 8)) - 1)
+
+#define EFS_DIRBLK_HEADERSIZE	4
+#define EFS_DIRBLK_MAGIC	0xbeef	/* moo */
+
+struct efs_dir {
+	__be16	magic;
+	unsigned char	firstused;
+	unsigned char	slots;
+
+	unsigned char	space[EFS_DIRBSIZE - EFS_DIRBLK_HEADERSIZE];
+};
+
+#define EFS_MAXENTS \
+	((EFS_DIRBSIZE - EFS_DIRBLK_HEADERSIZE) / \
+	 (EFS_DENTSIZE + sizeof(char)))
+
+#define EFS_SLOTAT(dir, slot) EFS_REALOFF((dir)->space[slot])
+
+#define EFS_REALOFF(offset) ((offset << 1))
+
+
+static inline struct efs_inode_info *INODE_INFO(struct inode *inode)
+{
+	return container_of(inode, struct efs_inode_info, vfs_inode);
+}
+
+static inline struct efs_sb_info *SUPER_INFO(struct super_block *sb)
+{
+	return sb->s_fs_info;
+}
+
+struct statfs;
+struct fid;
+
+extern const struct inode_operations efs_dir_inode_operations;
+extern const struct file_operations efs_dir_operations;
+extern const struct address_space_operations efs_symlink_aops;
+
+extern struct inode *efs_iget(struct super_block *, unsigned long);
+extern efs_block_t efs_map_block(struct inode *, efs_block_t);
+extern int efs_get_block(struct inode *, sector_t, struct buffer_head *, int);
+
+extern struct dentry *efs_lookup(struct inode *, struct dentry *, struct nameidata *);
+extern struct dentry *efs_fh_to_dentry(struct super_block *sb, struct fid *fid,
+		int fh_len, int fh_type);
+extern struct dentry *efs_fh_to_parent(struct super_block *sb, struct fid *fid,
+		int fh_len, int fh_type);
+extern struct dentry *efs_get_parent(struct dentry *);
+extern int efs_bmap(struct inode *, int);
+
+#endif /* _EFS_EFS_H_ */
diff --git a/fs/efs/file.c b/fs/efs/file.c
index 5db20129681..1ccb364ffa6 100644
--- a/fs/efs/file.c
+++ b/fs/efs/file.c
@@ -7,7 +7,7 @@
  */
 
 #include <linux/buffer_head.h>
-#include <linux/efs_fs.h>
+#include "efs.h"
 
 int efs_get_block(struct inode *inode, sector_t iblock,
 		  struct buffer_head *bh_result, int create)
diff --git a/fs/efs/inode.c b/fs/efs/inode.c
index 627c3026946..79e19e5958e 100644
--- a/fs/efs/inode.c
+++ b/fs/efs/inode.c
@@ -7,11 +7,11 @@
  *              and from work (c) 1998 Mike Shaver.
  */
 
-#include <linux/efs_fs.h>
-#include <linux/efs_fs_sb.h>
 #include <linux/buffer_head.h>
 #include <linux/module.h>
 #include <linux/fs.h>
+#include "efs.h"
+#include <linux/efs_fs_sb.h>
 
 static int efs_readpage(struct file *file, struct page *page)
 {
diff --git a/fs/efs/namei.c b/fs/efs/namei.c
index e26704742d4..3a404e7fad5 100644
--- a/fs/efs/namei.c
+++ b/fs/efs/namei.c
@@ -8,9 +8,9 @@
 
 #include <linux/buffer_head.h>
 #include <linux/string.h>
-#include <linux/efs_fs.h>
 #include <linux/smp_lock.h>
 #include <linux/exportfs.h>
+#include "efs.h"
 
 
 static efs_ino_t efs_find_entry(struct inode *inode, const char *name, int len) {
diff --git a/fs/efs/super.c b/fs/efs/super.c
index 14082405cdd..d733531b55e 100644
--- a/fs/efs/super.c
+++ b/fs/efs/super.c
@@ -8,14 +8,15 @@
 
 #include <linux/init.h>
 #include <linux/module.h>
-#include <linux/efs_fs.h>
-#include <linux/efs_vh.h>
-#include <linux/efs_fs_sb.h>
 #include <linux/exportfs.h>
 #include <linux/slab.h>
 #include <linux/buffer_head.h>
 #include <linux/vfs.h>
 
+#include "efs.h"
+#include <linux/efs_vh.h>
+#include <linux/efs_fs_sb.h>
+
 static int efs_statfs(struct dentry *dentry, struct kstatfs *buf);
 static int efs_fill_super(struct super_block *s, void *d, int silent);
 
diff --git a/fs/efs/symlink.c b/fs/efs/symlink.c
index 1d30d2ff440..41911ec83aa 100644
--- a/fs/efs/symlink.c
+++ b/fs/efs/symlink.c
@@ -7,10 +7,10 @@
  */
 
 #include <linux/string.h>
-#include <linux/efs_fs.h>
 #include <linux/pagemap.h>
 #include <linux/buffer_head.h>
 #include <linux/smp_lock.h>
+#include "efs.h"
 
 static int efs_symlink_readpage(struct file *file, struct page *page)
 {
diff --git a/fs/ext4/dir.c b/fs/ext4/dir.c
index 33888bb5814..2c23bade9aa 100644
--- a/fs/ext4/dir.c
+++ b/fs/ext4/dir.c
@@ -46,7 +46,7 @@ const struct file_operations ext4_dir_operations = {
 #ifdef CONFIG_COMPAT
 	.compat_ioctl	= ext4_compat_ioctl,
 #endif
-	.fsync		= ext4_sync_file,	/* BKL held */
+	.fsync		= ext4_sync_file,
 	.release	= ext4_release_dir,
 };
 
diff --git a/fs/ext4/extents.c b/fs/ext4/extents.c
index bc7081f1fbe..9ae6e67090c 100644
--- a/fs/ext4/extents.c
+++ b/fs/ext4/extents.c
@@ -148,6 +148,7 @@ static ext4_fsblk_t ext4_ext_find_goal(struct inode *inode,
 {
 	struct ext4_inode_info *ei = EXT4_I(inode);
 	ext4_fsblk_t bg_start;
+	ext4_fsblk_t last_block;
 	ext4_grpblk_t colour;
 	int depth;
 
@@ -169,8 +170,13 @@ static ext4_fsblk_t ext4_ext_find_goal(struct inode *inode,
 	/* OK. use inode's group */
 	bg_start = (ei->i_block_group * EXT4_BLOCKS_PER_GROUP(inode->i_sb)) +
 		le32_to_cpu(EXT4_SB(inode->i_sb)->s_es->s_first_data_block);
-	colour = (current->pid % 16) *
+	last_block = ext4_blocks_count(EXT4_SB(inode->i_sb)->s_es) - 1;
+
+	if (bg_start + EXT4_BLOCKS_PER_GROUP(inode->i_sb) <= last_block)
+		colour = (current->pid % 16) *
 			(EXT4_BLOCKS_PER_GROUP(inode->i_sb) / 16);
+	else
+		colour = (current->pid % 16) * ((last_block - bg_start) / 16);
 	return bg_start + colour + block;
 }
 
@@ -349,7 +355,7 @@ static void ext4_ext_show_leaf(struct inode *inode, struct ext4_ext_path *path)
 #define ext4_ext_show_leaf(inode,path)
 #endif
 
-static void ext4_ext_drop_refs(struct ext4_ext_path *path)
+void ext4_ext_drop_refs(struct ext4_ext_path *path)
 {
 	int depth = path->p_depth;
 	int i;
@@ -2168,6 +2174,10 @@ static int ext4_ext_convert_to_initialized(handle_t *handle,
 	newblock = iblock - ee_block + ext_pblock(ex);
 	ex2 = ex;
 
+	err = ext4_ext_get_access(handle, inode, path + depth);
+	if (err)
+		goto out;
+
 	/* ex1: ee_block to iblock - 1 : uninitialized */
 	if (iblock > ee_block) {
 		ex1 = ex;
@@ -2200,16 +2210,20 @@ static int ext4_ext_convert_to_initialized(handle_t *handle,
 		newdepth = ext_depth(inode);
 		if (newdepth != depth) {
 			depth = newdepth;
-			path = ext4_ext_find_extent(inode, iblock, NULL);
+			ext4_ext_drop_refs(path);
+			path = ext4_ext_find_extent(inode, iblock, path);
 			if (IS_ERR(path)) {
 				err = PTR_ERR(path);
-				path = NULL;
 				goto out;
 			}
 			eh = path[depth].p_hdr;
 			ex = path[depth].p_ext;
 			if (ex2 != &newex)
 				ex2 = ex;
+
+			err = ext4_ext_get_access(handle, inode, path + depth);
+			if (err)
+				goto out;
 		}
 		allocated = max_blocks;
 	}
@@ -2230,9 +2244,6 @@ static int ext4_ext_convert_to_initialized(handle_t *handle,
 	ex2->ee_len = cpu_to_le16(allocated);
 	if (ex2 != ex)
 		goto insert;
-	err = ext4_ext_get_access(handle, inode, path + depth);
-	if (err)
-		goto out;
 	/*
 	 * New (initialized) extent starts from the first block
 	 * in the current extent. i.e., ex2 == ex
@@ -2276,9 +2287,22 @@ out:
 }
 
 /*
+ * Block allocation/map/preallocation routine for extents based files
+ *
+ *
  * Need to be called with
  * down_read(&EXT4_I(inode)->i_data_sem) if not allocating file system block
  * (ie, create is zero). Otherwise down_write(&EXT4_I(inode)->i_data_sem)
+ *
+ * return > 0, number of of blocks already mapped/allocated
+ *          if create == 0 and these are pre-allocated blocks
+ *          	buffer head is unmapped
+ *          otherwise blocks are mapped
+ *
+ * return = 0, if plain look up failed (blocks have not been allocated)
+ *          buffer head is unmapped
+ *
+ * return < 0, error case.
  */
 int ext4_ext_get_blocks(handle_t *handle, struct inode *inode,
 			ext4_lblk_t iblock,
@@ -2623,7 +2647,7 @@ long ext4_fallocate(struct inode *inode, int mode, loff_t offset, loff_t len)
 	 * modify 1 super block, 1 block bitmap and 1 group descriptor.
 	 */
 	credits = EXT4_DATA_TRANS_BLOCKS(inode->i_sb) + 3;
-	down_write((&EXT4_I(inode)->i_data_sem));
+	mutex_lock(&inode->i_mutex);
 retry:
 	while (ret >= 0 && ret < max_blocks) {
 		block = block + ret;
@@ -2634,16 +2658,17 @@ retry:
 			break;
 		}
 
-		ret = ext4_ext_get_blocks(handle, inode, block,
+		ret = ext4_get_blocks_wrap(handle, inode, block,
 					  max_blocks, &map_bh,
 					  EXT4_CREATE_UNINITIALIZED_EXT, 0);
-		WARN_ON(ret <= 0);
 		if (ret <= 0) {
-			ext4_error(inode->i_sb, "ext4_fallocate",
-				    "ext4_ext_get_blocks returned error: "
-				    "inode#%lu, block=%u, max_blocks=%lu",
+#ifdef EXT4FS_DEBUG
+			WARN_ON(ret <= 0);
+			printk(KERN_ERR "%s: ext4_ext_get_blocks "
+				    "returned error inode#%lu, block=%u, "
+				    "max_blocks=%lu", __func__,
 				    inode->i_ino, block, max_blocks);
-			ret = -EIO;
+#endif
 			ext4_mark_inode_dirty(handle, inode);
 			ret2 = ext4_journal_stop(handle);
 			break;
@@ -2680,7 +2705,6 @@ retry:
 	if (ret == -ENOSPC && ext4_should_retry_alloc(inode->i_sb, &retries))
 		goto retry;
 
-	up_write((&EXT4_I(inode)->i_data_sem));
 	/*
 	 * Time to update the file size.
 	 * Update only when preallocation was requested beyond the file size.
@@ -2692,21 +2716,18 @@ retry:
 			 * if no error, we assume preallocation succeeded
 			 * completely
 			 */
-			mutex_lock(&inode->i_mutex);
 			i_size_write(inode, offset + len);
 			EXT4_I(inode)->i_disksize = i_size_read(inode);
-			mutex_unlock(&inode->i_mutex);
 		} else if (ret < 0 && nblocks) {
 			/* Handle partial allocation scenario */
 			loff_t newsize;
 
-			mutex_lock(&inode->i_mutex);
 			newsize  = (nblocks << blkbits) + i_size_read(inode);
 			i_size_write(inode, EXT4_BLOCK_ALIGN(newsize, blkbits));
 			EXT4_I(inode)->i_disksize = i_size_read(inode);
-			mutex_unlock(&inode->i_mutex);
 		}
 	}
 
+	mutex_unlock(&inode->i_mutex);
 	return ret > 0 ? ret2 : ret;
 }
diff --git a/fs/ext4/ialloc.c b/fs/ext4/ialloc.c
index da18a74b966..8036b9b5376 100644
--- a/fs/ext4/ialloc.c
+++ b/fs/ext4/ialloc.c
@@ -702,7 +702,12 @@ got:
 	ei->i_dir_start_lookup = 0;
 	ei->i_disksize = 0;
 
-	ei->i_flags = EXT4_I(dir)->i_flags & ~EXT4_INDEX_FL;
+	/*
+	 * Don't inherit extent flag from directory. We set extent flag on
+	 * newly created directory and file only if -o extent mount option is
+	 * specified
+	 */
+	ei->i_flags = EXT4_I(dir)->i_flags & ~(EXT4_INDEX_FL|EXT4_EXTENTS_FL);
 	if (S_ISLNK(mode))
 		ei->i_flags &= ~(EXT4_IMMUTABLE_FL|EXT4_APPEND_FL);
 	/* dirsync only applies to directories */
@@ -745,12 +750,15 @@ got:
 		goto fail_free_drop;
 	}
 	if (test_opt(sb, EXTENTS)) {
-		EXT4_I(inode)->i_flags |= EXT4_EXTENTS_FL;
-		ext4_ext_tree_init(handle, inode);
-		err = ext4_update_incompat_feature(handle, sb,
-						EXT4_FEATURE_INCOMPAT_EXTENTS);
-		if (err)
-			goto fail;
+		/* set extent flag only for directory and file */
+		if (S_ISDIR(mode) || S_ISREG(mode)) {
+			EXT4_I(inode)->i_flags |= EXT4_EXTENTS_FL;
+			ext4_ext_tree_init(handle, inode);
+			err = ext4_update_incompat_feature(handle, sb,
+					EXT4_FEATURE_INCOMPAT_EXTENTS);
+			if (err)
+				goto fail;
+		}
 	}
 
 	ext4_debug("allocating inode %lu\n", inode->i_ino);
diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
index 7dd9b50d5eb..945cbf6cb1f 100644
--- a/fs/ext4/inode.c
+++ b/fs/ext4/inode.c
@@ -403,6 +403,7 @@ static ext4_fsblk_t ext4_find_near(struct inode *inode, Indirect *ind)
 	__le32 *start = ind->bh ? (__le32*) ind->bh->b_data : ei->i_data;
 	__le32 *p;
 	ext4_fsblk_t bg_start;
+	ext4_fsblk_t last_block;
 	ext4_grpblk_t colour;
 
 	/* Try to find previous block */
@@ -420,8 +421,13 @@ static ext4_fsblk_t ext4_find_near(struct inode *inode, Indirect *ind)
 	 * into the same cylinder group then.
 	 */
 	bg_start = ext4_group_first_block_no(inode->i_sb, ei->i_block_group);
-	colour = (current->pid % 16) *
+	last_block = ext4_blocks_count(EXT4_SB(inode->i_sb)->s_es) - 1;
+
+	if (bg_start + EXT4_BLOCKS_PER_GROUP(inode->i_sb) <= last_block)
+		colour = (current->pid % 16) *
 			(EXT4_BLOCKS_PER_GROUP(inode->i_sb) / 16);
+	else
+		colour = (current->pid % 16) * ((last_block - bg_start) / 16);
 	return bg_start + colour;
 }
 
@@ -768,7 +774,6 @@ err_out:
  *
  * `handle' can be NULL if create == 0.
  *
- * The BKL may not be held on entry here.  Be sure to take it early.
  * return > 0, # of blocks mapped or allocated.
  * return = 0, if plain lookup failed.
  * return < 0, error case.
@@ -903,11 +908,38 @@ out:
  */
 #define DIO_CREDITS 25
 
+
+/*
+ *
+ *
+ * ext4_ext4 get_block() wrapper function
+ * It will do a look up first, and returns if the blocks already mapped.
+ * Otherwise it takes the write lock of the i_data_sem and allocate blocks
+ * and store the allocated blocks in the result buffer head and mark it
+ * mapped.
+ *
+ * If file type is extents based, it will call ext4_ext_get_blocks(),
+ * Otherwise, call with ext4_get_blocks_handle() to handle indirect mapping
+ * based files
+ *
+ * On success, it returns the number of blocks being mapped or allocate.
+ * if create==0 and the blocks are pre-allocated and uninitialized block,
+ * the result buffer head is unmapped. If the create ==1, it will make sure
+ * the buffer head is mapped.
+ *
+ * It returns 0 if plain look up failed (blocks have not been allocated), in
+ * that casem, buffer head is unmapped
+ *
+ * It returns the error in case of allocation failure.
+ */
 int ext4_get_blocks_wrap(handle_t *handle, struct inode *inode, sector_t block,
 			unsigned long max_blocks, struct buffer_head *bh,
 			int create, int extend_disksize)
 {
 	int retval;
+
+	clear_buffer_mapped(bh);
+
 	/*
 	 * Try to see if we can get  the block without requesting
 	 * for new file system block.
@@ -921,12 +953,26 @@ int ext4_get_blocks_wrap(handle_t *handle, struct inode *inode, sector_t block,
 				inode, block, max_blocks, bh, 0, 0);