Merge branch 'akpm/master'

32 files changed, 1536 insertions, 296 deletions

diff --git a/fs/Kconfig b/fs/Kconfig
index 664991afe0c0..560971c20f12 100644
--- a/fs/Kconfig
+++ b/fs/Kconfig
@@ -13,13 +13,6 @@ if BLOCK
 source "fs/ext2/Kconfig"
 source "fs/ext3/Kconfig"
 source "fs/ext4/Kconfig"
-
-config FS_XIP
-# execute in place
-	bool
-	depends on EXT2_FS_XIP
-	default y
-
 source "fs/jbd/Kconfig"
 source "fs/jbd2/Kconfig"
 
@@ -40,6 +33,20 @@ source "fs/ocfs2/Kconfig"
 source "fs/btrfs/Kconfig"
 source "fs/nilfs2/Kconfig"
 
+config FS_DAX
+	bool "Direct Access (DAX) support"
+	depends on MMU
+	help
+	  Direct Access (DAX) can be used on memory-backed block devices.
+	  If the block device supports DAX and the filesystem supports DAX,
+	  then you can avoid using the pagecache to buffer I/Os.  Turning
+	  on this option will compile in support for DAX; you will need to
+	  mount the filesystem using the -o dax option.
+
+	  If you do not have a block device that is capable of using this,
+	  or if unsure, say N.  Saying Y will increase the size of the kernel
+	  by about 5kB.
+
 endif # BLOCK
 
 # Posix ACL utility routines
diff --git a/fs/Makefile b/fs/Makefile
index bedff48e8fdc..0f4635f7c49c 100644
--- a/fs/Makefile
+++ b/fs/Makefile
@@ -28,6 +28,7 @@ obj-$(CONFIG_SIGNALFD)		+= signalfd.o
 obj-$(CONFIG_TIMERFD)		+= timerfd.o
 obj-$(CONFIG_EVENTFD)		+= eventfd.o
 obj-$(CONFIG_AIO)               += aio.o
+obj-$(CONFIG_FS_DAX)		+= dax.o
 obj-$(CONFIG_FILE_LOCKING)      += locks.o
 obj-$(CONFIG_COMPAT)		+= compat.o compat_ioctl.o
 obj-$(CONFIG_BINFMT_AOUT)	+= binfmt_aout.o
diff --git a/fs/dax.c b/fs/dax.c
new file mode 100644
index 000000000000..ed1619ec6537
--- /dev/null
+++ b/fs/dax.c
@@ -0,0 +1,534 @@
+/*
+ * fs/dax.c - Direct Access filesystem code
+ * Copyright (c) 2013-2014 Intel Corporation
+ * Author: Matthew Wilcox <matthew.r.wilcox@intel.com>
+ * Author: Ross Zwisler <ross.zwisler@linux.intel.com>
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
+ * more details.
+ */
+
+#include <linux/atomic.h>
+#include <linux/blkdev.h>
+#include <linux/buffer_head.h>
+#include <linux/fs.h>
+#include <linux/genhd.h>
+#include <linux/highmem.h>
+#include <linux/memcontrol.h>
+#include <linux/mm.h>
+#include <linux/mutex.h>
+#include <linux/sched.h>
+#include <linux/uio.h>
+#include <linux/vmstat.h>
+
+int dax_clear_blocks(struct inode *inode, sector_t block, long size)
+{
+	struct block_device *bdev = inode->i_sb->s_bdev;
+	sector_t sector = block << (inode->i_blkbits - 9);
+
+	might_sleep();
+	do {
+		void *addr;
+		unsigned long pfn;
+		long count;
+
+		count = bdev_direct_access(bdev, sector, &addr, &pfn, size);
+		if (count < 0)
+			return count;
+		BUG_ON(size < count);
+		while (count > 0) {
+			unsigned pgsz = PAGE_SIZE - offset_in_page(addr);
+			if (pgsz > count)
+				pgsz = count;
+			if (pgsz < PAGE_SIZE)
+				memset(addr, 0, pgsz);
+			else
+				clear_page(addr);
+			addr += pgsz;
+			size -= pgsz;
+			count -= pgsz;
+			BUG_ON(pgsz & 511);
+			sector += pgsz / 512;
+			cond_resched();
+		}
+	} while (size);
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(dax_clear_blocks);
+
+static long dax_get_addr(struct buffer_head *bh, void **addr, unsigned blkbits)
+{
+	unsigned long pfn;
+	sector_t sector = bh->b_blocknr << (blkbits - 9);
+	return bdev_direct_access(bh->b_bdev, sector, addr, &pfn, bh->b_size);
+}
+
+static void dax_new_buf(void *addr, unsigned size, unsigned first, loff_t pos,
+			loff_t end)
+{
+	loff_t final = end - pos + first; /* The final byte of the buffer */
+
+	if (first > 0)
+		memset(addr, 0, first);
+	if (final < size)
+		memset(addr + final, 0, size - final);
+}
+
+static bool buffer_written(struct buffer_head *bh)
+{
+	return buffer_mapped(bh) && !buffer_unwritten(bh);
+}
+
+/*
+ * When ext4 encounters a hole, it returns without modifying the buffer_head
+ * which means that we can't trust b_size.  To cope with this, we set b_state
+ * to 0 before calling get_block and, if any bit is set, we know we can trust
+ * b_size.  Unfortunate, really, since ext4 knows precisely how long a hole is
+ * and would save us time calling get_block repeatedly.
+ */
+static bool buffer_size_valid(struct buffer_head *bh)
+{
+	return bh->b_state != 0;
+}
+
+static ssize_t dax_io(int rw, struct inode *inode, struct iov_iter *iter,
+			loff_t start, loff_t end, get_block_t get_block,
+			struct buffer_head *bh)
+{
+	ssize_t retval = 0;
+	loff_t pos = start;
+	loff_t max = start;
+	loff_t bh_max = start;
+	void *addr;
+	bool hole = false;
+
+	if (rw != WRITE)
+		end = min(end, i_size_read(inode));
+
+	while (pos < end) {
+		unsigned len;
+		if (pos == max) {
+			unsigned blkbits = inode->i_blkbits;
+			sector_t block = pos >> blkbits;
+			unsigned first = pos - (block << blkbits);
+			long size;
+
+			if (pos == bh_max) {
+				bh->b_size = PAGE_ALIGN(end - pos);
+				bh->b_state = 0;
+				retval = get_block(inode, block, bh,
+								rw == WRITE);
+				if (retval)
+					break;
+				if (!buffer_size_valid(bh))
+					bh->b_size = 1 << blkbits;
+				bh_max = pos - first + bh->b_size;
+			} else {
+				unsigned done = bh->b_size -
+						(bh_max - (pos - first));
+				bh->b_blocknr += done >> blkbits;
+				bh->b_size -= done;
+			}
+
+			hole = (rw != WRITE) && !buffer_written(bh);
+			if (hole) {
+				addr = NULL;
+				size = bh->b_size - first;
+			} else {
+				retval = dax_get_addr(bh, &addr, blkbits);
+				if (retval < 0)
+					break;
+				if (buffer_unwritten(bh) || buffer_new(bh))
+					dax_new_buf(addr, retval, first, pos,
+									end);
+				addr += first;
+				size = retval - first;
+			}
+			max = min(pos + size, end);
+		}
+
+		if (rw == WRITE)
+			len = copy_from_iter(addr, max - pos, iter);
+		else if (!hole)
+			len = copy_to_iter(addr, max - pos, iter);
+		else
+			len = iov_iter_zero(max - pos, iter);
+
+		if (!len)
+			break;
+
+		pos += len;
+		addr += len;
+	}
+
+	return (pos == start) ? retval : pos - start;
+}
+
+/**
+ * dax_do_io - Perform I/O to a DAX file
+ * @rw: READ to read or WRITE to write
+ * @iocb: The control block for this I/O
+ * @inode: The file which the I/O is directed at
+ * @iter: The addresses to do I/O from or to
+ * @pos: The file offset where the I/O starts
+ * @get_block: The filesystem method used to translate file offsets to blocks
+ * @end_io: A filesystem callback for I/O completion
+ * @flags: See below
+ *
+ * This function uses the same locking scheme as do_blockdev_direct_IO:
+ * If @flags has DIO_LOCKING set, we assume that the i_mutex is held by the
+ * caller for writes.  For reads, we take and release the i_mutex ourselves.
+ * If DIO_LOCKING is not set, the filesystem takes care of its own locking.
+ * As with do_blockdev_direct_IO(), we increment i_dio_count while the I/O
+ * is in progress.
+ */
+ssize_t dax_do_io(int rw, struct kiocb *iocb, struct inode *inode,
+			struct iov_iter *iter, loff_t pos,
+			get_block_t get_block, dio_iodone_t end_io, int flags)
+{
+	struct buffer_head bh;
+	ssize_t retval = -EINVAL;
+	loff_t end = pos + iov_iter_count(iter);
+
+	memset(&bh, 0, sizeof(bh));
+
+	if ((flags & DIO_LOCKING) && (rw == READ)) {
+		struct address_space *mapping = inode->i_mapping;
+		mutex_lock(&inode->i_mutex);
+		retval = filemap_write_and_wait_range(mapping, pos, end - 1);
+		if (retval) {
+			mutex_unlock(&inode->i_mutex);
+			goto out;
+		}
+	}
+
+	/* Protects against truncate */
+	atomic_inc(&inode->i_dio_count);
+
+	retval = dax_io(rw, inode, iter, pos, end, get_block, &bh);
+
+	if ((flags & DIO_LOCKING) && (rw == READ))
+		mutex_unlock(&inode->i_mutex);
+
+	if ((retval > 0) && end_io)
+		end_io(iocb, pos, retval, bh.b_private);
+
+	inode_dio_done(inode);
+ out:
+	return retval;
+}
+EXPORT_SYMBOL_GPL(dax_do_io);
+
+/*
+ * The user has performed a load from a hole in the file.  Allocating
+ * a new page in the file would cause excessive storage usage for
+ * workloads with sparse files.  We allocate a page cache page instead.
+ * We'll kick it out of the page cache if it's ever written to,
+ * otherwise it will simply fall out of the page cache under memory
+ * pressure without ever having been dirtied.
+ */
+static int dax_load_hole(struct address_space *mapping, struct page *page,
+							struct vm_fault *vmf)
+{
+	unsigned long size;
+	struct inode *inode = mapping->host;
+	if (!page)
+		page = find_or_create_page(mapping, vmf->pgoff,
+						GFP_KERNEL | __GFP_ZERO);
+	if (!page)
+		return VM_FAULT_OOM;
+	/* Recheck i_size under page lock to avoid truncate race */
+	size = (i_size_read(inode) + PAGE_SIZE - 1) >> PAGE_SHIFT;
+	if (vmf->pgoff >= size) {
+		unlock_page(page);
+		page_cache_release(page);
+		return VM_FAULT_SIGBUS;
+	}
+
+	vmf->page = page;
+	return VM_FAULT_LOCKED;
+}
+
+static int copy_user_bh(struct page *to, struct buffer_head *bh,
+			unsigned blkbits, unsigned long vaddr)
+{
+	void *vfrom, *vto;
+	if (dax_get_addr(bh, &vfrom, blkbits) < 0)
+		return -EIO;
+	vto = kmap_atomic(to);
+	copy_user_page(vto, vfrom, vaddr, to);
+	kunmap_atomic(vto);
+	return 0;
+}
+
+static int dax_insert_mapping(struct inode *inode, struct buffer_head *bh,
+			struct vm_area_struct *vma, struct vm_fault *vmf)
+{
+	struct address_space *mapping = inode->i_mapping;
+	sector_t sector = bh->b_blocknr << (inode->i_blkbits - 9);
+	unsigned long vaddr = (unsigned long)vmf->virtual_address;
+	void *addr;
+	unsigned long pfn;
+	pgoff_t size;
+	int error;
+
+	i_mmap_lock_read(mapping);
+
+	/*
+	 * Check truncate didn't happen while we were allocating a block.
+	 * If it did, this block may or may not be still allocated to the
+	 * file.  We can't tell the filesystem to free it because we can't
+	 * take i_mutex here.  In the worst case, the file still has blocks
+	 * allocated past the end of the file.
+	 */
+	size = (i_size_read(inode) + PAGE_SIZE - 1) >> PAGE_SHIFT;
+	if (unlikely(vmf->pgoff >= size)) {
+		error = -EIO;
+		goto out;
+	}
+
+	error = bdev_direct_access(bh->b_bdev, sector, &addr, &pfn, bh->b_size);
+	if (error < 0)
+		goto out;
+	if (error < PAGE_SIZE) {
+		error = -EIO;
+		goto out;
+	}
+
+	if (buffer_unwritten(bh) || buffer_new(bh))
+		clear_page(addr);
+
+	error = vm_insert_mixed(vma, vaddr, pfn);
+
+ out:
+	i_mmap_unlock_read(mapping);
+
+	if (bh->b_end_io)
+		bh->b_end_io(bh, 1);
+
+	return error;
+}
+
+static int do_dax_fault(struct vm_area_struct *vma, struct vm_fault *vmf,
+			get_block_t get_block)
+{
+	struct file *file = vma->vm_file;
+	struct address_space *mapping = file->f_mapping;
+	struct inode *inode = mapping->host;
+	struct page *page;
+	struct buffer_head bh;
+	unsigned long vaddr = (unsigned long)vmf->virtual_address;
+	unsigned blkbits = inode->i_blkbits;
+	sector_t block;
+	pgoff_t size;
+	int error;
+	int major = 0;
+
+	size = (i_size_read(inode) + PAGE_SIZE - 1) >> PAGE_SHIFT;
+	if (vmf->pgoff >= size)
+		return VM_FAULT_SIGBUS;
+
+	memset(&bh, 0, sizeof(bh));
+	block = (sector_t)vmf->pgoff << (PAGE_SHIFT - blkbits);
+	bh.b_size = PAGE_SIZE;
+
+ repeat:
+	page = find_get_page(mapping, vmf->pgoff);
+	if (page) {
+		if (!lock_page_or_retry(page, vma->vm_mm, vmf->flags)) {
+			page_cache_release(page);
+			return VM_FAULT_RETRY;
+		}
+		if (unlikely(page->mapping != mapping)) {
+			unlock_page(page);
+			page_cache_release(page);
+			goto repeat;
+		}
+		size = (i_size_read(inode) + PAGE_SIZE - 1) >> PAGE_SHIFT;
+		if (unlikely(vmf->pgoff >= size)) {
+			/*
+			 * We have a struct page covering a hole in the file
+			 * from a read fault and we've raced with a truncate
+			 */
+			error = -EIO;
+			goto unlock_page;
+		}
+	}
+
+	error = get_block(inode, block, &bh, 0);
+	if (!error && (bh.b_size < PAGE_SIZE))
+		error = -EIO;		/* fs corruption? */
+	if (error)
+		goto unlock_page;
+
+	if (!buffer_mapped(&bh) && !buffer_unwritten(&bh) && !vmf->cow_page) {
+		if (vmf->flags & FAULT_FLAG_WRITE) {
+			error = get_block(inode, block, &bh, 1);
+			count_vm_event(PGMAJFAULT);
+			mem_cgroup_count_vm_event(vma->vm_mm, PGMAJFAULT);
+			major = VM_FAULT_MAJOR;
+			if (!error && (bh.b_size < PAGE_SIZE))
+				error = -EIO;
+			if (error)
+				goto unlock_page;
+		} else {
+			return dax_load_hole(mapping, page, vmf);
+		}
+	}
+
+	if (vmf->cow_page) {
+		struct page *new_page = vmf->cow_page;
+		if (buffer_written(&bh))
+			error = copy_user_bh(new_page, &bh, blkbits, vaddr);
+		else
+			clear_user_highpage(new_page, vaddr);
+		if (error)
+			goto unlock_page;
+		vmf->page = page;
+		if (!page) {
+			i_mmap_lock_read(mapping);
+			/* Check we didn't race with truncate */
+			size = (i_size_read(inode) + PAGE_SIZE - 1) >>
+								PAGE_SHIFT;
+			if (vmf->pgoff >= size) {
+				i_mmap_unlock_read(mapping);
+				error = -EIO;
+				goto out;
+			}
+		}
+		return VM_FAULT_LOCKED;
+	}
+
+	/* Check we didn't race with a read fault installing a new page */
+	if (!page && major)
+		page = find_lock_page(mapping, vmf->pgoff);
+
+	if (page) {
+		unmap_mapping_range(mapping, vmf->pgoff << PAGE_SHIFT,
+							PAGE_CACHE_SIZE, 0);
+		delete_from_page_cache(page);
+		unlock_page(page);
+		page_cache_release(page);
+	}
+
+	error = dax_insert_mapping(inode, &bh, vma, vmf);
+
+ out:
+	if (error == -ENOMEM)
+		return VM_FAULT_OOM | major;
+	/* -EBUSY is fine, somebody else faulted on the same PTE */
+	if ((error < 0) && (error != -EBUSY))
+		return VM_FAULT_SIGBUS | major;
+	return VM_FAULT_NOPAGE | major;
+
+ unlock_page:
+	if (page) {
+		unlock_page(page);
+		page_cache_release(page);
+	}
+	goto out;
+}
+
+/**
+ * dax_fault - handle a page fault on a DAX file
+ * @vma: The virtual memory area where the fault occurred
+ * @vmf: The description of the fault
+ * @get_block: The filesystem method used to translate file offsets to blocks
+ *
+ * When a page fault occurs, filesystems may call this helper in their
+ * fault handler for DAX files.
+ */
+int dax_fault(struct vm_area_struct *vma, struct vm_fault *vmf,
+			get_block_t get_block)
+{
+	int result;
+	struct super_block *sb = file_inode(vma->vm_file)->i_sb;
+
+	if (vmf->flags & FAULT_FLAG_WRITE) {
+		sb_start_pagefault(sb);
+		file_update_time(vma->vm_file);
+	}
+	result = do_dax_fault(vma, vmf, get_block);
+	if (vmf->flags & FAULT_FLAG_WRITE)
+		sb_end_pagefault(sb);
+
+	return result;
+}
+EXPORT_SYMBOL_GPL(dax_fault);
+
+/**
+ * dax_zero_page_range - zero a range within a page of a DAX file
+ * @inode: The file being truncated
+ * @from: The file offset that is being truncated to
+ * @length: The number of bytes to zero
+ * @get_block: The filesystem method used to translate file offsets to blocks
+ *
+ * This function can be called by a filesystem when it is zeroing part of a
+ * page in a DAX file.  This is intended for hole-punch operations.  If
+ * you are truncating a file, the helper function dax_truncate_page() may be
+ * more convenient.
+ *
+ * We work in terms of PAGE_CACHE_SIZE here for commonality with
+ * block_truncate_page(), but we could go down to PAGE_SIZE if the filesystem
+ * took care of disposing of the unnecessary blocks.  Even if the filesystem
+ * block size is smaller than PAGE_SIZE, we have to zero the rest of the page
+ * since the file might be mmapped.
+ */
+int dax_zero_page_range(struct inode *inode, loff_t from, unsigned length,
+							get_block_t get_block)
+{
+	struct buffer_head bh;
+	pgoff_t index = from >> PAGE_CACHE_SHIFT;
+	unsigned offset = from & (PAGE_CACHE_SIZE-1);
+	int err;
+
+	/* Block boundary? Nothing to do */
+	if (!length)
+		return 0;
+	BUG_ON((offset + length) > PAGE_CACHE_SIZE);
+
+	memset(&bh, 0, sizeof(bh));
+	bh.b_size = PAGE_CACHE_SIZE;
+	err = get_block(inode, index, &bh, 0);
+	if (err < 0)
+		return err;
+	if (buffer_written(&bh)) {
+		void *addr;
+		err = dax_get_addr(&bh, &addr, inode->i_blkbits);
+		if (err < 0)
+			return err;
+		memset(addr + offset, 0, length);
+	}
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(dax_zero_page_range);
+
+/**
+ * dax_truncate_page - handle a partial page being truncated in a DAX file
+ * @inode: The file being truncated
+ * @from: The file offset that is being truncated to
+ * @get_block: The filesystem method used to translate file offsets to blocks
+ *
+ * Similar to block_truncate_page(), this function can be called by a
+ * filesystem when it is truncating a DAX file to handle the partial page.
+ *
+ * We work in terms of PAGE_CACHE_SIZE here for commonality with
+ * block_truncate_page(), but we could go down to PAGE_SIZE if the filesystem
+ * took care of disposing of the unnecessary blocks.  Even if the filesystem
+ * block size is smaller than PAGE_SIZE, we have to zero the rest of the page
+ * since the file might be mmapped.
+ */
+int dax_truncate_page(struct inode *inode, loff_t from, get_block_t get_block)
+{
+	unsigned length = PAGE_CACHE_ALIGN(from) - from;
+	return dax_zero_page_range(inode, from, length, get_block);
+}
+EXPORT_SYMBOL_GPL(dax_truncate_page);
diff --git a/fs/exofs/inode.c b/fs/exofs/inode.c
index 6fc91df99ff8..a198e94813fe 100644
--- a/fs/exofs/inode.c
+++ b/fs/exofs/inode.c
@@ -985,7 +985,6 @@ const struct address_space_operations exofs_aops = {
 	.direct_IO	= exofs_direct_IO,
 
 	/* With these NULL has special meaning or default is not exported */
-	.get_xip_mem	= NULL,
 	.migratepage	= NULL,
 	.launder_page	= NULL,
 	.is_partially_uptodate = NULL,
diff --git a/fs/ext2/Kconfig b/fs/ext2/Kconfig
index 14a6780fd034..c634874e12d9 100644
--- a/fs/ext2/Kconfig
+++ b/fs/ext2/Kconfig
@@ -42,14 +42,3 @@ config EXT2_FS_SECURITY
 
 	  If you are not using a security module that requires using
 	  extended attributes for file security labels, say N.
-
-config EXT2_FS_XIP
-	bool "Ext2 execute in place support"
-	depends on EXT2_FS && MMU
-	help
-	  Execute in place can be used on memory-backed block devices. If you
-	  enable this option, you can select to mount block devices which are
-	  capable of this feature without using the page cache.
-
-	  If you do not use a block device that is capable of using this,
-	  or if unsure, say N.
diff --git a/fs/ext2/Makefile b/fs/ext2/Makefile
index f42af45cfd88..445b0e996a12 100644
--- a/fs/ext2/Makefile
+++ b/fs/ext2/Makefile
@@ -10,4 +10,3 @@ ext2-y := balloc.o dir.o file.o ialloc.o inode.o \
 ext2-$(CONFIG_EXT2_FS_XATTR)	 += xattr.o xattr_user.o xattr_trusted.o
 ext2-$(CONFIG_EXT2_FS_POSIX_ACL) += acl.o
 ext2-$(CONFIG_EXT2_FS_SECURITY)	 += xattr_security.o
-ext2-$(CONFIG_EXT2_FS_XIP)	 += xip.o
diff --git a/fs/ext2/ext2.h b/fs/ext2/ext2.h
index e4279ead4a05..678f9ab08c48 100644
--- a/fs/ext2/ext2.h
+++ b/fs/ext2/ext2.h
@@ -380,10 +380,15 @@ struct ext2_inode {
 #define EXT2_MOUNT_NO_UID32		0x000200  /* Disable 32-bit UIDs */
 #define EXT2_MOUNT_XATTR_USER		0x004000  /* Extended user attributes */
 #define EXT2_MOUNT_POSIX_ACL		0x008000  /* POSIX Access Control Lists */
-#define EXT2_MOUNT_XIP			0x010000  /* Execute in place */
+#define EXT2_MOUNT_XIP			0x010000  /* Obsolete, use DAX */
 #define EXT2_MOUNT_USRQUOTA		0x020000  /* user quota */
 #define EXT2_MOUNT_GRPQUOTA		0x040000  /* group quota */
 #define EXT2_MOUNT_RESERVATION		0x080000  /* Preallocation */
+#ifdef CONFIG_FS_DAX
+#define EXT2_MOUNT_DAX			0x100000  /* Direct Access */
+#else
+#define EXT2_MOUNT_DAX			0
+#endif
 
 
 #define clear_opt(o, opt)		o &= ~EXT2_MOUNT_##opt
@@ -788,11 +793,10 @@ extern int ext2_fsync(struct file *file, loff_t start, loff_t end,
 		      int datasync);
 extern const struct inode_operations ext2_file_inode_operations;
 extern const struct file_operations ext2_file_operations;
-extern const struct file_operations ext2_xip_file_operations;
+extern const struct file_operations ext2_dax_file_operations;
 
 /* inode.c */
 extern const struct address_space_operations ext2_aops;
-extern const struct address_space_operations ext2_aops_xip;
 extern const struct address_space_operations ext2_nobh_aops;
 
 /* namei.c */
diff --git a/fs/ext2/file.c b/fs/ext2/file.c
index 7c87b22a7228..e31701713516 100644
--- a/fs/ext2/file.c
+++ b/fs/ext2/file.c
@@ -25,6 +25,36 @@
 #include "xattr.h"
 #include "acl.h"
 
+#ifdef CONFIG_FS_DAX
+static int ext2_dax_fault(struct vm_area_struct *vma, struct vm_fault *vmf)
+{
+	return dax_fault(vma, vmf, ext2_get_block);
+}
+
+static int ext2_dax_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf)
+{
+	return dax_mkwrite(vma, vmf, ext2_get_block);
+}
+
+static const struct vm_operations_struct ext2_dax_vm_ops = {
+	.fault		= ext2_dax_fault,
+	.page_mkwrite	= ext2_dax_mkwrite,
+};
+
+static int ext2_file_mmap(struct file *file, struct vm_area_struct *vma)
+{
+	if (!IS_DAX(file_inode(file)))
+		return generic_file_mmap(file, vma);
+
+	file_accessed(file);
+	vma->vm_ops = &ext2_dax_vm_ops;
+	vma->vm_flags |= VM_MIXEDMAP;
+	return 0;
+}
+#else
+#define ext2_file_mmap	generic_file_mmap
+#endif
+
 /*
  * Called when filp is released. This happens when all file descriptors
  * for a single struct file are closed. Note that different open() calls
@@ -70,7 +100,7 @@ const struct file_operations ext2_file_operations = {
 #ifdef CONFIG_COMPAT
 	.compat_ioctl	= ext2_compat_ioctl,
 #endif
-	.mmap		= generic_file_mmap,
+	.mmap		= ext2_file_mmap,
 	.open		= dquot_file_open,
 	.release	= ext2_release_file,
 	.fsync		= ext2_fsync,
@@ -78,16 +108,18 @@ const struct file_operations ext2_file_operations = {
 	.splice_write	= iter_file_splice_write,
 };
 
-#ifdef CONFIG_EXT2_FS_XIP
-const struct file_operations ext2_xip_file_operations = {
+#ifdef CONFIG_FS_DAX
+const struct file_operations ext2_dax_file_operations = {
 	.llseek		= generic_file_llseek,
-	.read		= xip_file_read,
-	.write		= xip_file_write,
+	.read		= new_sync_read,
+	.write		= new_sync_write,
+	.read_iter	= generic_file_read_iter,
+	.write_iter	= generic_file_write_iter,
 	.unlocked_ioctl = ext2_ioctl,
 #ifdef CONFIG_COMPAT
 	.compat_ioctl	= ext2_compat_ioctl,
 #endif
-	.mmap		= xip_file_mmap,
+	.mmap		= ext2_file_mmap,
 	.open		= dquot_file_open,
 	.release	= ext2_release_file,
 	.fsync		= ext2_fsync,
diff --git a/fs/ext2/inode.c b/fs/ext2/inode.c
index 36d35c36311d..6434bc000125 100644
--- a/fs/ext2/inode.c
+++ b/fs/ext2/inode.c
@@ -34,7 +34,6 @@
 #include <linux/aio.h>
 #include "ext2.h"
 #include "acl.h"
-#include "xip.h"
 #include "xattr.h"
 
 static int __ext2_write_inode(struct inode *inode, int do_sync);
@@ -731,12 +730,14 @@ static int ext2_get_blocks(struct inode *inode,
 		goto cleanup;
 	}
 
-	if (ext2_use_xip(inode->i_sb)) {
+	if (IS_DAX(inode)) {
 		/*
-		 * we need to clear the block
+		 * block must be initialised before we put it in the tree
+		 * so that it's not found by another thread before it's
+		 * initialised
 		 */
-		err = ext2_clear_xip_target (inode,
-			le32_to_cpu(chain[depth-1].key));
+		err = dax_clear_blocks(inode, le32_to_cpu(chain[depth-1].key),
+						1 << inode->i_blkbits);
 		if (err) {
 			mutex_unlock(&ei->truncate_mutex);
 			goto cleanup;
@@ -859,7 +860,12 @@ ext2_direct_IO(int rw, struct kiocb *iocb, struct iov_iter *iter,
 	size_t count = iov_iter_count(iter);
 	ssize_t ret;
 
-	ret = blockdev_direct_IO(rw, iocb, inode, iter, offset, ext2_get_block);
+	if (IS_DAX(inode))
+		ret = dax_do_io(rw, iocb, inode, iter, offset, ext2_get_block,
+				NULL, DIO_LOCKING);
+	else
+		ret = blockdev_direct_IO(rw, iocb, inode, iter, offset,
+					 ext2_get_block);
 	if (ret < 0 && (rw & WRITE))
 		ext2_write_failed(mapping, offset + count);
 	return ret;
@@ -885,11 +891,6 @@ const struct address_space_operations ext2_aops = {
 	.error_remove_page	= generic_error_remove_page,
 };
 
-const struct address_space_operations ext2_aops_xip = {
-	.bmap			= ext2_bmap,
-	.get_xip_mem		= ext2_get_xip_mem,
-};
-
 const struct address_space_operations ext2_nobh_aops = {
 	.readpage		= ext2_readpage,
 	.readpages		= ext2_readpages,
@@ -1201,8 +1202,8 @@ static int ext2_setsize(struct inode *inode, loff_t newsize)
 
 	inode_dio_wait(inode);
 
-	if (mapping_is_xip(inode->i_mapping))
-		error = xip_truncate_page(inode->i_mapping, newsize);
+	if (IS_DAX(inode))
+		error = dax_truncate_page(inode, newsize, ext2_get_block);
 	else if (test_opt(inode->i_sb, NOBH))
 		error = nobh_truncate_page(inode->i_mapping,
 				newsize, ext2_get_block);
@@ -1273,7 +1274,8 @@ void ext2_set_inode_flags(struct inode *inode)
 {
 	unsigned int flags = EXT2_I(inode)->i_flags;
 
-	inode->i_flags &= ~(S_SYNC|S_APPEND|S_IMMUTABLE|S_NOATIME|S_DIRSYNC);
+	inode->i_flags &= ~(S_SYNC | S_APPEND | S_IMMUTABLE | S_NOATIME |
+				S_DIRSYNC | S_DAX);
 	if (flags & EXT2_SYNC_FL)
 		inode->i_flags |= S_SYNC;
 	if (flags & EXT2_APPEND_FL)
@@ -1284,6 +1286,8 @@ void ext2_set_inode_flags(struct inode *inode)
 		inode->i_flags |= S_NOATIME;
 	if (flags & EXT2_DIRSYNC_FL)
 		inode->i_flags |= S_DIRSYNC;
+	if (test_opt(inode->i_sb, DAX))
+		inode->i_flags |= S_DAX;
 }
 
 /* Propagate flags from i_flags to EXT2_I(inode)->i_flags */
@@ -1384,9 +1388,9 @@ struct inode *ext2_iget (struct super_block *sb, unsigned long ino)
 
 	if (S_ISREG(inode->i_mode)) {
 		inode->i_op = &ext2_file_inode_operations;
-		if (ext2_use_xip(inode->i_sb)) {
-			inode->i_mapping->a_ops = &ext2_aops_xip;
-			inode->i_fop = &ext2_xip_file_operations;
+		if (test_opt(inode->i_sb, DAX)) {
+			inode->i_mapping->a_ops = &ext2_aops;
+			inode->i_fop = &ext2_dax_file_operations;
 		} else if (test_opt(inode->i_sb, NOBH)) {
 			inode->i_mapping->a_ops = &ext2_nobh_aops;
 			inode->i_fop = &ext2_file_operations;
diff --git a/fs/ext2/namei.c b/fs/ext2/namei.c
index c268d0af1db9..148f6e3789ea 100644
--- a/fs/ext2/namei.c
+++ b/fs/ext2/namei.c
@@ -35,7 +35,6 @@
 #include "ext2.h"
 #include "xattr.h"
 #include "acl.h"
-#include "xip.h"
 
 static inline int ext2_add_nondir(struct dentry *dentry, struct inode *inode)
 {
@@ -105,9 +104,9 @@ static int ext2_create (struct inode * dir, struct dentry * dentry, umode_t mode
 		return PTR_ERR(inode);
 
 	inode->i_op = &ext2_file_inode_operations;
-	if (ext2_use_xip(inode->i_sb)) {
-		inode->i_mapping->a_ops = &ext2_aops_xip;
-		inode->i_fop = &ext2_xip_file_operations;
+	if (test_opt(inode->i_sb, DAX)) {
+		inode->i_mapping->a_ops = &ext2_aops;
+		inode->i_fop = &ext2_dax_file_operations;
 	} else if (test_opt(inode->i_sb, NOBH)) {
 		inode->i_mapping->a_ops = &ext2_nobh_aops;
 		inode->i_fop = &ext2_file_operations;
@@ -126,9 +125,9 @@ static int ext2_tmpfile(struct inode *dir, struct dentry *dentry, umode_t mode)
 		return PTR_ERR(inode);
 
 	inode->i_op = &ext2_file_inode_operations;
-	if (ext2_use_xip(inode->i_sb)) {
-		inode->i_mapping->a_ops = &ext2_aops_xip;
-		inode->i_fop = &ext2_xip_file_operations;
+	if (test_opt(inode->i_sb, DAX)) {
+		inode->i_mapping->a_ops = &ext2_aops;
+		inode->i_fop = &ext2_dax_file_operations;
 	} else if (test_opt(inode->i_sb, NOBH)) {
 		inode->i_mapping->a_ops = &ext2_nobh_aops;
 		inode->i_fop = &ext2_file_operations;
diff --git a/fs/ext2/super.c b/fs/ext2/super.c
index ae55fddc26a9..d0e746e96511 100644
--- a/fs/ext2/super.c
+++ b/fs/ext2/super.c
@@ -35,7 +35,6 @@
 #include "ext2.h"
 #include "xattr.h"
 #include "acl.h"
-#include "xip.h"
 
 static void ext2_sync_super(struct super_block *sb,
 			    struct ext2_super_block *es, int wait);
@@ -292,9 +291,11 @@ static int ext2_show_options(struct seq_file *seq, struct dentry *root)
 		seq_puts(seq, ",grpquota");
 #endif
 
-#if defined(CONFIG_EXT2_FS_XIP)
+#ifdef CONFIG_FS_DAX
 	if (sbi->s_mount_opt & EXT2_MOUNT_XIP)
 		seq_puts(seq, ",xip");
+	if (sbi->s_mount_opt & EXT2_MOUNT_DAX)
+		seq_puts(seq, ",dax");
 #endif
 
 	if (!test_opt(sb, RESERVATION))
@@ -403,7 +404,7 @@ enum {
 	Opt_resgid, Opt_resuid, Opt_sb, Opt_err_cont, Opt_err_panic,
 	Opt_err_ro, Opt_nouid32, Opt_nocheck, Opt_debug,
 	Opt_oldalloc, Opt_orlov, Opt_nobh, Opt_user_xattr, Opt_nouser_xattr,
-	Opt_acl, Opt_noacl, Opt_xip, Opt_ignore, Opt_err, Opt_quota,
+	Opt_acl, Opt_noacl, Opt_xip, Opt_dax, Opt_ignore, Opt_err, Opt_quota,
 	Opt_usrquota, Opt_grpquota, Opt_reservation, Opt_noreservation
 };
 
@@ -432,6 +433,7 @@ static const match_table_t tokens = {
 	{Opt_acl, "acl"},
 	{Opt_noacl, "noacl"},
 	{Opt_xip, "xip"},
+	{Opt_dax, "dax"},
 	{Opt_grpquota, "grpquota"},
 	{Opt_ignore, "noquota"},
 	{Opt_quota, "quota"},
@@ -559,10 +561,14 @@ static int parse_options(char *options, struct super_block *sb)
 			break;
 #endif
 		case Opt_xip:
-#ifdef CONFIG_EXT2_FS_XIP
-			set_opt (sbi->s_mount_opt, XIP);
+			ext2_msg(sb, KERN_INFO, "use dax instead of xip");
+			set_opt(sbi->s_mount_opt, XIP);
+			/* Fall through */
+		case Opt_dax:
+#ifdef CONFIG_FS_DAX
+			set_opt(sbi->s_mount_opt, DAX);
 #else
-			ext2_msg(sb, KERN_INFO, "xip option not supported");
+			ext2_msg(sb, KERN_INFO, "dax option not supported");
 #endif
 			break;
 
@@ -877,9 +883,6 @@ static int ext2_fill_super(struct super_block *sb, void *data, int silent)
 		((EXT2_SB(sb)->s_mount_opt & EXT2_MOUNT_POSIX_ACL) ?
 		 MS_POSIXACL : 0);
 
-	ext2_xip_verify_sb(sb); /* see if bdev supports xip, unset
-				    EXT2_MOUNT_XIP if not */
-
 	if (le32_to_cpu(es->s_rev_level) == EXT2_GOOD_OLD_REV &&
 	    (EXT2_HAS_COMPAT_FEATURE(sb, ~0U) ||
 	     EXT2_HAS_RO_COMPAT_FEATURE(sb, ~0U) ||
@@ -909,11 +912,17 @@ static int ext2_fill_super(struct super_block *sb, void *data, int silent)
 
 	blocksize = BLOCK_SIZE << le32_to_cpu(sbi->s_es->s_log_block_size);
 
-	if (ext2_use_xip(sb) && blocksize != PAGE_SIZE) {
-		if (!silent)
+	if (sbi->s_mount_opt & EXT2_MOUNT_DAX) {
+		if (blocksize != PAGE_SIZE) {
 			ext2_msg(sb, KERN_ERR,
-				"error: unsupported blocksize for xip");
-		goto failed_mount;
+					"error: unsupported blocksize for dax");
+			goto failed_mount;
+		}
+		if (!sb->s_bdev->bd_disk->fops->direct_access) {
+			ext2_msg(sb, KERN_ERR,
+					"error: device does not support dax");
+			goto failed_mount;
+		}
 	}
 
 	/* If the blocksize doesn't match, re-read the thing.. */
@@ -1259,7 +1268,6 @@ static int ext2_remount (struct super_block * sb, int * flags, char * data)
 {
 	struct ext2_sb_info * sbi = EXT2_SB(sb);
 	struct ext2_super_block * es;
-	unsigned long old_mount_opt = sbi->s_mount_opt;
 	struct ext2_mount_options old_opts;
 	unsigned long old_sb_flags;
 	int err;
@@ -1284,22 +1292,11 @@ static int ext2_remount (struct super_block * sb, int * flags, char * data)
 	sb->s_flags = (sb->s_flags & ~MS_POSIXACL) |
 		((sbi->s_mount_opt & EXT2_MOUNT_POSIX_ACL) ? MS_POSIXACL : 0);
 
-	ext2_xip_verify_sb(sb); /* see if bdev supports xip, unset
-				    EXT2_MOUNT_XIP if not */
-
-	if ((ext2_use_xip(sb)) && (sb->s_blocksize != PAGE_SIZE)) {
-		ext2_msg(sb, KERN_WARNING,
-			"warning: unsupported blocksize for xip");
-		err = -EINVAL;
-		goto restore_opts;
-	}
-
 	es = sbi->s_es;
-	if ((sbi->s_mount_opt ^ old_mount_opt) & EXT2_MOUNT_XIP) {
+	if ((sbi->s_mount_opt ^ old_opts.s_mount_opt) & EXT2_MOUNT_DAX) {
 		ext2_msg(sb, KERN_WARNING, "warning: refusing change of "
-			 "xip flag with busy inodes while remounting");
-		sbi->s_mount_opt &= ~EXT2_MOUNT_XIP;
-		sbi->s_mount_opt |= old_mount_opt & EXT2_MOUNT_XIP;
+			 "dax flag with busy inodes while remounting");
+		sbi->s_mount_opt ^= EXT2_MOUNT_DAX;
 	}
 	if ((*flags & MS_RDONLY) == (sb->s_flags & MS_RDONLY)) {
 		spin_unlock(&sbi->s_lock);
diff --git a/fs/ext2/xip.c b/fs/ext2/xip.c
deleted file mode 100644
index bbc5fec6ff7f..000000000000
--- a/fs/ext2/xip.c
+++ /dev/null
@@ -1,86 +0,0 @@
-/*
- *  linux/fs/ext2/xip.c
- *
- * Copyright (C) 2005 IBM Corporation
- * Author: Carsten Otte (cotte@de.ibm.com)
- */
-
-#include <linux/mm.h>
-#include <linux/fs.h>
-#include <linux/genhd.h>
-#include <linux/buffer_head.h>
-#include <linux/blkdev.h>
-#include "ext2.h"
-#include "xip.h"
-
-static inline long __inode_direct_access(struct inode *inode, sector_t block,
-				void **kaddr, unsigned long *pfn, long size)
-{
-	struct block_device *bdev = inode->i_sb->s_bdev;
-	sector_t sector = block * (PAGE_SIZE / 512);
-	return bdev_direct_access(bdev, sector, kaddr, pfn, size);
-}
-
-static inline int
-__ext2_get_block(struct inode *inode, pgoff_t pgoff, int create,
-		   sector_t *result)
-{
-	struct buffer_head tmp;
-	int rc;
-
-	memset(&tmp, 0, sizeof(struct buffer_head));
-	tmp.b_size = 1 << inode->i_blkbits;
-	rc = ext2_get_block(inode, pgoff, &tmp, create);
-	*result = tmp.b_blocknr;
-
-	/* did we get a sparse block (hole in the file)? */
-	if (!tmp.b_blocknr && !rc) {
-		BUG_ON(create);
-		rc = -ENODATA;
-	}
-
-	return rc;
-}
-
-int
-ext2_clear_xip_target(struct inode *inode, sector_t block)
-{
-	void *kaddr;
-	unsigned long pfn;
-	long size;
-
-	size = __inode_direct_access(inode, block, &kaddr, &pfn, PAGE_SIZE);
-	if (size < 0)
-		return size;
-	clear_page(kaddr);
-	return 0;
-}
-
-void ext2_xip_verify_sb(struct super_block *sb)
-{
-	struct ext2_sb_info *sbi = EXT2_SB(sb);
-
-	if ((sbi->s_mount_opt & EXT2_MOUNT_XIP) &&
-	    !sb->s_bdev->bd_disk->fops->direct_access) {
-		sbi->s_mount_opt &= (~EXT2_MOUNT_XIP);
-		ext2_msg(sb, KERN_WARNING,
-			     "warning: ignoring xip option - "
-			     "not supported by bdev");
-	}
-}
-
-int ext2_get_xip_mem(struct address_space *mapping, pgoff_t pgoff, int create,
-				void **kmem, unsigned long *pfn)
-{
-	long rc;
-	sector_t block;
-
-	/* first, retrieve the sector number */
-	rc = __ext2_get_block(mapping->host, pgoff, create, &block);
-	if (rc)
-		return rc;
-
-	/* retrieve address of the target data */
-	rc = __inode_direct_access(mapping->host, block, kmem, pfn, PAGE_SIZE);
-	return (rc < 0) ? rc : 0;
-}
diff --git a/fs/ext2/xip.h b/fs/ext2/xip.h
deleted file mode 100644
index 18b34d2f31b3..000000000000
--- a/fs/ext2/xip.h
+++ /dev/null
@@ -1,26 +0,0 @@
-/*
- *  linux/fs/ext2/xip.h
- *
- * Copyright (C) 2005 IBM Corporation
- * Author: Carsten Otte (cotte@de.ibm.com)
- */
-
-#ifdef CONFIG_EXT2_FS_XIP
-extern void ext2_xip_verify_sb (struct super_block *);
-extern int ext2_clear_xip_target (struct inode *, sector_t);
-
-static inline int ext2_use_xip (struct super_block *sb)
-{
-	struct ext2_sb_info *sbi = EXT2_SB(sb);
-	return (sbi->s_mount_opt & EXT2_MOUNT_XIP);
-}
-int ext2_get_xip_mem(struct address_space *, pgoff_t, int,
-				void **, unsigned long *);
-#define mapping_is_xip(map) unlikely(map->a_ops->get_xip_mem)
-#else
-#define mapping_is_xip(map)			0
-#define ext2_xip_verify_sb(sb)			do { } while (0)
-#define ext2_use_xip(sb)			0
-#define ext2_clear_xip_target(inode, chain)	0
-#define ext2_get_xip_mem			NULL
-#endif
diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h
index b7f393df2e4c..98ee89cef0ad 100644
--- a/fs/ext4/ext4.h
+++ b/fs/ext4/ext4.h
@@ -966,6 +966,11 @@ struct ext4_inode_info {
 #define EXT4_MOUNT_ERRORS_MASK		0x00070
 #define EXT4_MOUNT_MINIX_DF		0x00080	/* Mimics the Minix statfs */
 #define EXT4_MOUNT_NOLOAD		0x00100	/* Don't use existing journal*/
+#ifdef CONFIG_FS_DAX
+#define EXT4_MOUNT_DAX			0x00200	/* Direct Access */
+#else
+#define EXT4_MOUNT_DAX			0
+#endif
 #define EXT4_MOUNT_DATA_FLAGS		0x00C00	/* Mode for data writes: */
 #define EXT4_MOUNT_JOURNAL_DATA		0x00400	/* Write data to journal */
 #define EXT4_MOUNT_ORDERED_DATA		0x00800	/* Flush data before commit */
@@ -2587,6 +2592,7 @@ extern const struct file_operations ext4_dir_operations;
 /* file.c */
 extern const struct inode_operations ext4_file_inode_operations;
 extern const struct file_operations ext4_file_operations;
+extern const struct file_operations ext4_dax_file_operations;
 extern loff_t ext4_llseek(struct file *file, loff_t offset, int origin);
 
 /* inline.c */
diff --git a/fs/ext4/file.c b/fs/ext4/file.c
index 7cb592386121..33a09da16c9c 100644
--- a/fs/ext4/file.c
+++ b/fs/ext4/file.c
@@ -95,7 +95,7 @@ ext4_file_write_iter(struct kiocb *iocb, struct iov_iter *from)
 	struct inode *inode = file_inode(iocb->ki_filp);
 	struct mutex *aio_mutex = NULL;
 	struct blk_plug plug;
-	int o_direct = file->f_flags & O_DIRECT;
+	int o_direct = io_is_direct(file);
 	int overwrite = 0;
 	size_t length = iov_iter_count(from);
 	ssize_t ret;
@@ -191,6 +191,26 @@ errout:
 	return ret;
 }
 
+#ifdef CONFIG_FS_DAX
+static int ext4_dax_fault(struct vm_area_struct *vma, struct vm_fault *vmf)
+{
+	return dax_fault(vma, vmf, ext4_get_block);
+					/* Is this the right get_block? */
+}
+
+static int ext4_dax_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf)
+{
+	return dax_mkwrite(vma, vmf, ext4_get_block);
+}
+
+static const struct vm_operations_struct ext4_dax_vm_ops = {
+	.fault		= ext4_dax_fault,
+	.page_mkwrite	= ext4_dax_mkwrite,
+};
+#else
+#define ext4_dax_vm_ops	ext4_file_vm_ops
+#endif
+
 static const struct vm_operations_struct ext4_file_vm_ops = {
 	.fault		= filemap_fault,
 	.map_pages	= filemap_map_pages,
@@ -200,7 +220,12 @@ static const struct vm_operations_struct ext4_file_vm_ops = {
 static int ext4_file_mmap(struct file *file, struct vm_area_struct *vma)
 {
 	file_accessed(file);
-	vma->vm_ops = &ext4_file_vm_ops;
+	if (IS_DAX(file_inode(file))) {
+		vma->vm_ops = &ext4_dax_vm_ops;
+		vma->vm_flags |= VM_MIXEDMAP;
+	} else {
+		vma->vm_ops = &ext4_file_vm_ops;
+	}
 	return 0;
 }
 
@@ -599,6 +624,26 @@ const struct file_operations ext4_file_operations = {
 	.fallocate	= ext4_fallocate,
 };
 
+#ifdef CONFIG_FS_DAX
+const struct file_operations ext4_dax_file_operations = {
+	.llseek		= ext4_llseek,
+	.read		= new_sync_read,
+	.write		= new_sync_write,
+	.read_iter	= generic_file_read_iter,
+	.write_iter	= ext4_file_write_iter,
+	.unlocked_ioctl = ext4_ioctl,
+#ifdef CONFIG_COMPAT
+	.compat_ioctl	= ext4_compat_ioctl,
+#endif
+	.mmap		= ext4_file_mmap,
+	.open		= ext4_file_open,
+	.release	= ext4_release_file,
+	.fsync		= ext4_sync_file,
+	/* Splice not yet supported with DAX */
+	.fallocate	= ext4_fallocate,
+};
+#endif
+
 const struct inode_operations ext4_file_inode_operations = {
 	.setattr	= ext4_setattr,
 	.getattr	= ext4_getattr,
diff --git a/fs/ext4/indirect.c b/fs/ext4/indirect.c
index 36b369697a13..6b9878a24182 100644
--- a/fs/ext4/indirect.c
+++ b/fs/ext4/indirect.c
@@ -689,14 +689,22 @@ retry:
 			inode_dio_done(inode);
 			goto locked;
 		}
-		ret = __blockdev_direct_IO(rw, iocb, inode,
-				 inode->i_sb->s_bdev, iter, offset,
-				 ext4_get_block, NULL, NULL, 0);
+		if (IS_DAX(inode))
+			ret = dax_do_io(rw, iocb, inode, iter, offset,
+					ext4_get_block, NULL, 0);
+		else
+			ret = __blockdev_direct_IO(rw, iocb, inode,
+					inode->i_sb->s_bdev, iter, offset,
+					ext4_get_block, NULL, NULL, 0);
 		inode_dio_done(inode);
 	} else {
 locked:
-		ret = blockdev_direct_IO(rw, iocb, inode, iter,
-				 offset, ext4_get_block);
+		if (IS_DAX(inode))
+			ret = dax_do_io(rw, iocb, inode, iter, offset,
+					ext4_get_block, NULL, DIO_LOCKING);
+		else
+			ret = blockdev_direct_IO(rw, iocb, inode, iter,
+					offset, ext4_get_block);
 
 		if (unlikely((rw & WRITE) && ret < 0)) {
 			loff_t isize = i_size_read(inode);
diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
index 9193ea130dcb..85404f15e53a 100644
--- a/fs/ext4/inode.c
+++ b/fs/ext4/inode.c
@@ -657,6 +657,18 @@ has_zeroout:
 	return retval;
 }
 
+static void ext4_end_io_unwritten(struct buffer_head *bh, int uptodate)
+{
+	struct inode *inode = bh->b_assoc_map->host;
+	/* XXX: breaks on 32-bit > 16GB. Is that even supported? */
+	loff_t offset = (loff_t)(uintptr_t)bh->b_private << inode->i_blkbits;
+	int err;
+	if (!uptodate)
+		return;
+	WARN_ON(!buffer_unwritten(bh));
+	err = ext4_convert_unwritten_extents(NULL, inode, offset, bh->b_size);
+}
+
 /* Maximum number of blocks we map for direct IO at once. */
 #define DIO_MAX_BLOCKS 4096
 
@@ -694,6 +706,11 @@ static int _ext4_get_block(struct inode *inode, sector_t iblock,
 
 		map_bh(bh, inode->i_sb, map.m_pblk);
 		bh->b_state = (bh->b_state & ~EXT4_MAP_FLAGS) | map.m_flags;
+		if (IS_DAX(inode) && buffer_unwritten(bh) && !io_end) {
+			bh->b_assoc_map = inode->i_mapping;
+			bh->b_private = (void *)(unsigned long)iblock;
+			bh->b_end_io = ext4_end_io_unwritten;
+		}
 		if (io_end && io_end->flag & EXT4_IO_END_UNWRITTEN)
 			set_buffer_defer_completion(bh);
 		bh->b_size = inode->i_sb->s_blocksize * map.m_len;
@@ -3010,13 +3027,14 @@ static ssize_t ext4_ext_direct_IO(int rw, struct kiocb *iocb,
 		get_block_func = ext4_get_block_write;
 		dio_flags = DIO_LOCKING;
 	}
-	ret = __blockdev_direct_IO(rw, iocb, inode,
-				   inode->i_sb->s_bdev, iter,
-				   offset,
-				   get_block_func,
-				   ext4_end_io_dio,
-				   NULL,
-				   dio_flags);
+	if (IS_DAX(inode))
+		ret = dax_do_io(rw, iocb, inode, iter, offset, get_block_func,
+				ext4_end_io_dio, dio_flags);
+	else
+		ret = __blockdev_direct_IO(rw, iocb, inode,
+					   inode->i_sb->s_bdev, iter, offset,
+					   get_block_func,
+					   ext4_end_io_dio, NULL, dio_flags);
 
 	/*
 	 * Put our reference to io_end. This can free the io_end structure e.g.
@@ -3180,19 +3198,12 @@ void ext4_set_aops(struct inode *inode)
 		inode->i_mapping->a_ops = &ext4_aops;
 }
 
-/*
- * ext4_block_zero_page_range() zeros out a mapping of length 'length'
- * starting from file offset 'from'.  The range to be zero'd must
- * be contained with in one block.  If the specified range exceeds
- * the end of the block it will be shortened to end of the block
- * that cooresponds to 'from'
- */
-static int ext4_block_zero_page_range(handle_t *handle,
+static int __ext4_block_zero_page_range(handle_t *handle,
 		struct address_space *mapping, loff_t from, loff_t length)
 {
 	ext4_fsblk_t index = from >> PAGE_CACHE_SHIFT;
 	unsigned offset = from & (PAGE_CACHE_SIZE-1);
-	unsigned blocksize, max, pos;
+	unsigned blocksize, pos;
 	ext4_lblk_t iblock;
 	struct inode *inode = mapping->host;
 	struct buffer_head *bh;
@@ -3205,14 +3216,6 @@ static int ext4_block_zero_page_range(handle_t *handle,
 		return -ENOMEM;
 
 	blocksize = inode->i_sb->s_blocksize;
-	max = blocksize - (offset & (blocksize - 1));
-
-	/*
-	 * correct length if it does not fall between
-	 * 'from' and the end of the block
-	 */
-	if (length > max || length < 0)
-		length = max;
 
 	iblock = index << (PAGE_CACHE_SHIFT - inode->i_sb->s_blocksize_bits);
 
@@ -3278,6 +3281,33 @@ unlock:
 }
 
 /*
+ * ext4_block_zero_page_range() zeros out a mapping of length 'length'
+ * starting from file offset 'from'.  The range to be zero'd must
+ * be contained with in one block.  If the specified range exceeds
+ * the end of the block it will be shortened to end of the block
+ * that cooresponds to 'from'
+ */
+static int ext4_block_zero_page_range(handle_t *handle,
+		struct address_space *mapping, loff_t from, loff_t length)
+{
+	struct inode *inode = mapping->host;
+	unsigned offset = from & (PAGE_CACHE_SIZE-1);
+	unsigned blocksize = inode->i_sb->s_blocksize;
+	unsigned max = blocksize - (offset & (blocksize - 1));
+
+	/*
+	 * correct length if it does not fall between
+	 * 'from' and the end of the block
+	 */
+	if (length > max || length < 0)
+		length = max;
+
+	if (IS_DAX(inode))
+		return dax_zero_page_range(inode, from, length, ext4_get_block);
+	return __ext4_block_zero_page_range(handle, mapping, from, length);
+}
+
+/*
  * ext4_block_truncate_page() zeroes out a mapping from file offset `from'
  * up to the end of the block which corresponds to `from'.
  * This required during truncate. We need to physically zero the tail end
@@ -3798,8 +3828,10 @@ void ext4_set_inode_flags(struct inode *inode)
 		new_fl |= S_NOATIME;
 	if (flags & EXT4_DIRSYNC_FL)
 		new_fl |= S_DIRSYNC;
+	if (test_opt(inode->i_sb, DAX))
+		new_fl |= S_DAX;
 	inode_set_flags(inode, new_fl,
-			S_SYNC|S_APPEND|S_IMMUTABLE|S_NOATIME|S_DIRSYNC);
+			S_SYNC|S_APPEND|S_IMMUTABLE|S_NOATIME|S_DIRSYNC|S_DAX);
 }
 
 /* Propagate flags from i_flags to EXT4_I(inode)->i_flags */
@@ -4052,7 +4084,10 @@ struct inode *ext4_iget(struct super_block *sb, unsigned long ino)
 
 	if (S_ISREG(inode->i_mode)) {
 		inode->i_op = &ext4_file_inode_operations;
-		inode->i_fop = &ext4_file_operations;
+		if (test_opt(inode->i_sb, DAX))
+			inode->i_fop = &ext4_dax_file_operations;
+		else
+			inode->i_fop = &ext4_file_operations;
 		ext4_set_aops(inode);
 	} else if (S_ISDIR(inode->i_mode)) {
 		inode->i_op = &ext4_dir_inode_operations;
@@ -4594,7 +4629,7 @@ int ext4_setattr(struct dentry *dentry, struct iattr *attr)
 		 * Truncate pagecache after we've waited for commit
 		 * in data=journal mode to make pages freeable.
 		 */
-			truncate_pagecache(inode, inode->i_size);
+		truncate_pagecache(inode, inode->i_size);
 	}
 	/*
 	 * We want to call ext4_truncate() even if attr->ia_size ==
diff --git a/fs/ext4/namei.c b/fs/ext4/namei.c
index 2291923dae4e..28fe71a2904c 100644
--- a/fs/ext4/namei.c
+++ b/fs/ext4/namei.c
@@ -2235,7 +2235,10 @@ retry:
 	err = PTR_ERR(inode);
 	if (!IS_ERR(inode)) {
 		inode->i_op = &ext4_file_inode_operations;
-		inode->i_fop = &ext4_file_operations;
+		if (test_opt(inode->i_sb, DAX))
+			inode->i_fop = &ext4_dax_file_operations;
+		else
+			inode->i_fop = &ext4_file_operations;
 		ext4_set_aops(inode);
 		err = ext4_add_nondir(handle, dentry, inode);
 		if (!err && IS_DIRSYNC(dir))
@@ -2299,7 +2302,10 @@ retry:
 	err = PTR_ERR(inode);
 	if (!IS_ERR(inode)) {
 		inode->i_op = &ext4_file_inode_operations;
-		inode->i_fop = &ext4_file_operations;
+		if (test_opt(inode->i_sb, DAX))
+			inode->i_fop = &ext4_dax_file_operations;
+		else
+			inode->i_fop = &ext4_file_operations;
 		ext4_set_aops(inode);
 		d_tmpfile(dentry, inode);
 		err = ext4_orphan_add(handle, inode);
diff --git a/fs/ext4/super.c b/fs/ext4/super.c
index 9fcd99748f18..3450ce4f3250 100644
--- a/fs/ext4/super.c
+++ b/fs/ext4/super.c
@@ -1124,7 +1124,7 @@ enum {
 	Opt_usrjquota, Opt_grpjquota, Opt_offusrjquota, Opt_offgrpjquota,
 	Opt_jqfmt_vfsold, Opt_jqfmt_vfsv0, Opt_jqfmt_vfsv1, Opt_quota,
 	Opt_noquota, Opt_barrier, Opt_nobarrier, Opt_err,
-	Opt_usrquota, Opt_grpquota, Opt_i_version,
+	Opt_usrquota, Opt_grpquota, Opt_i_version, Opt_dax,
 	Opt_stripe, Opt_delalloc, Opt_nodelalloc, Opt_mblk_io_submit,
 	Opt_lazytime, Opt_nolazytime,
 	Opt_nomblk_io_submit, Opt_block_validity, Opt_noblock_validity,
@@ -1188,6 +1188,7 @@ static const match_table_t tokens = {
 	{Opt_barrier, "barrier"},
 	{Opt_nobarrier, "nobarrier"},
 	{Opt_i_version, "i_version"},
+	{Opt_dax, "dax"},
 	{Opt_stripe, "stripe=%u"},
 	{Opt_delalloc, "delalloc"},
 	{Opt_lazytime, "lazytime"},
@@ -1374,6 +1375,7 @@ static const struct mount_opts {
 	{Opt_min_batch_time, 0, MOPT_GTE0},
 	{Opt_inode_readahead_blks, 0, MOPT_GTE0},
 	{Opt_init_itable, 0, MOPT_GTE0},
+	{Opt_dax, EXT4_MOUNT_DAX, MOPT_SET},
 	{Opt_stripe, 0, MOPT_GTE0},
 	{Opt_resuid, 0, MOPT_GTE0},
 	{Opt_resgid, 0, MOPT_GTE0},
@@ -1616,6 +1618,11 @@ static int handle_mount_opt(struct super_block *sb, char *opt, int token,
 		}
 		sbi->s_jquota_fmt = m->mount_opt;
 #endif
+#ifndef CONFIG_FS_DAX
+	} else if (token == Opt_dax) {
+		ext4_msg(sb, KERN_INFO, "dax option not supported");
+		return -1;
+#endif
 	} else {
 		if (!args->from)
 			arg = 1;
@@ -3598,6 +3605,11 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
 				 "both data=journal and dioread_nolock");
 			goto failed_mount;
 		}
+		if (test_opt(sb, DAX)) {
+			ext4_msg(sb, KERN_ERR, "can't mount with "
+				 "both data=journal and dax");
+			goto failed_mount;
+		}
 		if (test_opt(sb, DELALLOC))
 			clear_opt(sb, DELALLOC);
 	}
@@ -3661,6 +3673,19 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
 		goto failed_mount;
 	}
 
+	if (sbi->s_mount_opt & EXT4_MOUNT_DAX) {
+		if (blocksize != PAGE_SIZE) {
+			ext4_msg(sb, KERN_ERR,
+					"error: unsupported blocksize for dax");
+			goto failed_mount;
+		}
+		if (!sb->s_bdev->bd_disk->fops->direct_access) {
+			ext4_msg(sb, KERN_ERR,
+					"error: device does not support dax");
+			goto failed_mount;
+		}
+	}
+
 	if (sb->s_blocksize != blocksize) {
 		/* Validate the filesystem blocksize */
 		if (!sb_set_blocksize(sb, blocksize)) {
@@ -4877,6 +4902,18 @@ static int ext4_remount(struct super_block *sb, int *flags, char *data)
 			err = -EINVAL;
 			goto restore_opts;
 		}
+		if (test_opt(sb, DAX)) {
+			ext4_msg(sb, KERN_ERR, "can't mount with "
+				 "both data=journal and dax");
+			err = -EINVAL;
+			goto restore_opts;
+		}
+	}
+
+	if ((sbi->s_mount_opt ^ old_opts.s_mount_opt) & EXT4_MOUNT_DAX) {
+		ext4_msg(sb, KERN_WARNING, "warning: refusing change of "
+			"dax flag with busy inodes while remounting");
+		sbi->s_mount_opt ^= EXT4_MOUNT_DAX;
 	}
 
 	if (sbi->s_mount_flags & EXT4_MF_FS_ABORTED)
diff --git a/fs/ocfs2/aops.c b/fs/ocfs2/aops.c
index 125b749f5a18..174aa9e41bc3 100644
--- a/fs/ocfs2/aops.c
+++ b/fs/ocfs2/aops.c
@@ -28,6 +28,7 @@
 #include <linux/pipe_fs_i.h>
 #include <linux/mpage.h>
 #include <linux/quotaops.h>
+#include <linux/blkdev.h>
 
 #include <cluster/masklog.h>
 
@@ -47,6 +48,9 @@
 #include "ocfs2_trace.h"
 
 #include "buffer_head_io.h"
+#include "dir.h"
+#include "namei.h"
+#include "sysfile.h"
 
 static int ocfs2_symlink_get_block(struct inode *inode, sector_t iblock,
 				   struct buffer_head *bh_result, int create)
@@ -506,18 +510,21 @@ bail:
  *
  * called like this: dio->get_blocks(dio->inode, fs_startblk,
  * 					fs_count, map_bh, dio->rw == WRITE);
- *
- * Note that we never bother to allocate blocks here, and thus ignore the
- * create argument.
  */
 static int ocfs2_direct_IO_get_blocks(struct inode *inode, sector_t iblock,
 				     struct buffer_head *bh_result, int create)
 {
 	int ret;
+	u32 cpos = 0;
+	int alloc_locked = 0;
 	u64 p_blkno, inode_blocks, contig_blocks;
 	unsigned int ext_flags;
 	unsigned char blocksize_bits = inode->i_sb->s_blocksize_bits;
 	unsigned long max_blocks = bh_result->b_size >> inode->i_blkbits;
+	unsigned long len = bh_result->b_size;
+	unsigned int clusters_to_alloc = 0;
+
+	cpos = ocfs2_blocks_to_clusters(inode->i_sb, iblock);
 
 	/* This function won't even be called if the request isn't all
 	 * nicely aligned and of the right size, so there's no need
@@ -539,6 +546,40 @@ static int ocfs2_direct_IO_get_blocks(struct inode *inode, sector_t iblock,
 	/* We should already CoW the refcounted extent in case of create. */
 	BUG_ON(create && (ext_flags & OCFS2_EXT_REFCOUNTED));
 
+	/* allocate blocks if no p_blkno is found, and create == 1 */
+	if (!p_blkno && create) {
+		ret = ocfs2_inode_lock(inode, NULL, 1);
+		if (ret < 0) {
+			mlog_errno(ret);
+			goto bail;
+		}
+
+		alloc_locked = 1;
+
+		/* fill hole, allocate blocks can't be larger than the size
+		 * of the hole */
+		clusters_to_alloc = ocfs2_clusters_for_bytes(inode->i_sb, len);
+		if (clusters_to_alloc > contig_blocks)
+			clusters_to_alloc = contig_blocks;
+
+		/* allocate extent and insert them into the extent tree */
+		ret = ocfs2_extend_allocation(inode, cpos,
+				clusters_to_alloc, 0);
+		if (ret < 0) {
+			mlog_errno(ret);
+			goto bail;
+		}
+
+		ret = ocfs2_extent_map_get_blocks(inode, iblock, &p_blkno,
+				&contig_blocks, &ext_flags);
+		if (ret < 0) {
+			mlog(ML_ERROR, "get_blocks() failed iblock=%llu\n",
+					(unsigned long long)iblock);
+			ret = -EIO;
+			goto bail;
+		}
+	}
+
 	/*
 	 * get_more_blocks() expects us to describe a hole by clearing
 	 * the mapped bit on bh_result().
@@ -556,6 +597,8 @@ static int ocfs2_direct_IO_get_blocks(struct inode *inode, sector_t iblock,
 		contig_blocks = max_blocks;
 	bh_result->b_size = contig_blocks << blocksize_bits;
 bail:
+	if (alloc_locked)
+		ocfs2_inode_unlock(inode, 1);
 	return ret;
 }
 
@@ -597,6 +640,184 @@ static int ocfs2_releasepage(struct page *page, gfp_t wait)
 	return try_to_free_buffers(page);
 }
 
+static int ocfs2_is_overwrite(struct ocfs2_super *osb,
+		struct inode *inode, loff_t offset)
+{
+	int ret = 0;
+	u32 v_cpos = 0;
+	u32 p_cpos = 0;
+	unsigned int num_clusters = 0;
+	unsigned int ext_flags = 0;
+
+	v_cpos = ocfs2_bytes_to_clusters(osb->sb, offset);
+	ret = ocfs2_get_clusters(inode, v_cpos, &p_cpos,
+			&num_clusters, &ext_flags);
+	if (ret < 0) {
+		mlog_errno(ret);
+		return ret;
+	}
+
+	if (p_cpos && !(ext_flags & OCFS2_EXT_UNWRITTEN))
+		return 1;
+
+	return 0;
+}
+
+static ssize_t ocfs2_direct_IO_write(struct kiocb *iocb,
+		struct iov_iter *iter,
+		loff_t offset)
+{
+	ssize_t ret = 0;
+	ssize_t written = 0;
+	bool orphaned = false;
+	int is_overwrite = 0;
+	struct file *file = iocb->ki_filp;
+	struct inode *inode = file_inode(file)->i_mapping->host;
+	struct ocfs2_super *osb = OCFS2_SB(inode->i_sb);
+	struct buffer_head *di_bh = NULL;
+	size_t count = iter->count;
+	journal_t *journal = osb->journal->j_journal;
+	u32 zero_len;
+	int cluster_align;
+	loff_t final_size = offset + count;
+	int append_write = offset >= i_size_read(inode) ? 1 : 0;
+	unsigned int num_clusters = 0;
+	unsigned int ext_flags = 0;
+
+	{
+		u64 o = offset;
+
+		zero_len = do_div(o, 1 << osb->s_clustersize_bits);
+		cluster_align = !zero_len;
+	}
+
+	/*
+	 * when final_size > inode->i_size, inode->i_size will be
+	 * updated after direct write, so add the inode to orphan
+	 * dir first.
+	 */
+	if (final_size > i_size_read(inode)) {
+		ret = ocfs2_add_inode_to_orphan(osb, inode);
+		if (ret < 0) {
+			mlog_errno(ret);
+			goto out;
+		}
+		orphaned = true;
+	}
+
+	if (append_write) {
+		ret = ocfs2_inode_lock(inode, &di_bh, 1);
+		if (ret < 0) {
+			mlog_errno(ret);
+			goto clean_orphan;
+		}
+
+		if (ocfs2_sparse_alloc(OCFS2_SB(inode->i_sb)))
+			ret = ocfs2_zero_extend(inode, di_bh, offset);
+		else
+			ret = ocfs2_extend_no_holes(inode, di_bh, offset,
+					offset);
+		if (ret < 0) {
+			mlog_errno(ret);
+			ocfs2_inode_unlock(inode, 1);
+			brelse(di_bh);
+			goto clean_orphan;
+		}
+
+		is_overwrite = ocfs2_is_overwrite(osb, inode, offset);
+		if (is_overwrite < 0) {
+			mlog_errno(is_overwrite);
+			ocfs2_inode_unlock(inode, 1);
+			brelse(di_bh);
+			goto clean_orphan;
+		}
+
+		ocfs2_inode_unlock(inode, 1);
+		brelse(di_bh);
+		di_bh = NULL;
+	}
+
+	written = __blockdev_direct_IO(WRITE, iocb, inode, inode->i_sb->s_bdev,
+			iter, offset,
+			ocfs2_direct_IO_get_blocks,
+			ocfs2_dio_end_io, NULL, 0);
+	if (unlikely(written < 0)) {
+		loff_t i_size = i_size_read(inode);
+
+		if (offset + count > i_size) {
+			ret = ocfs2_inode_lock(inode, &di_bh, 1);
+			if (ret < 0) {
+				mlog_errno(ret);
+				goto clean_orphan;
+			}
+
+			if (i_size == i_size_read(inode)) {
+				ret = ocfs2_truncate_file(inode, di_bh,
+						i_size);
+				if (ret < 0) {
+					if (ret != -ENOSPC)
+						mlog_errno(ret);
+
+					ocfs2_inode_unlock(inode, 1);
+					brelse(di_bh);
+					goto clean_orphan;
+				}
+			}
+
+			ocfs2_inode_unlock(inode, 1);
+			brelse(di_bh);
+
+			ret = jbd2_journal_force_commit(journal);
+			if (ret < 0)
+				mlog_errno(ret);
+		}
+	} else if (written < 0 && append_write && !is_overwrite &&
+			!cluster_align) {
+		u32 p_cpos = 0;
+		u32 v_cpos = ocfs2_bytes_to_clusters(osb->sb, offset);
+
+		ret = ocfs2_get_clusters(inode, v_cpos, &p_cpos,
+				&num_clusters, &ext_flags);
+		if (ret < 0) {
+			mlog_errno(ret);
+			goto clean_orphan;
+		}
+
+		BUG_ON(!p_cpos || (ext_flags & OCFS2_EXT_UNWRITTEN));
+
+		ret = blkdev_issue_zeroout(osb->sb->s_bdev,
+				p_cpos << (osb->s_clustersize_bits - 9),
+				zero_len >> 9, GFP_KERNEL, false);
+		if (ret < 0)
+			mlog_errno(ret);
+	}
+
+clean_orphan:
+	if (orphaned) {
+		int tmp_ret;
+		int update_isize = written > 0 ? 1 : 0;
+		loff_t end = update_isize ? offset + written : 0;
+
+		tmp_ret = ocfs2_del_inode_from_orphan(osb, inode,
+				update_isize, end);
+		if (tmp_ret < 0) {
+			ret = tmp_ret;
+			goto out;
+		}
+
+		tmp_ret = jbd2_journal_force_commit(journal);
+		if (tmp_ret < 0) {
+			ret = tmp_ret;
+			mlog_errno(tmp_ret);
+		}
+	}
+
+out:
+	if (ret >= 0)
+		ret = written;
+	return ret;
+}
+
 static ssize_t ocfs2_direct_IO(int rw,
 			       struct kiocb *iocb,
 			       struct iov_iter *iter,
@@ -604,6 +825,9 @@ static ssize_t ocfs2_direct_IO(int rw,
 {
 	struct file *file = iocb->ki_filp;
 	struct inode *inode = file_inode(file)->i_mapping->host;
+	struct ocfs2_super *osb = OCFS2_SB(inode->i_sb);
+	int full_coherency = !(osb->s_mount_opt &
+			OCFS2_MOUNT_COHERENCY_BUFFERED);
 
 	/*
 	 * Fallback to buffered I/O if we see an inode without
@@ -612,14 +836,20 @@ static ssize_t ocfs2_direct_IO(int rw,
 	if (OCFS2_I(inode)->ip_dyn_features & OCFS2_INLINE_DATA_FL)
 		return 0;
 
-	/* Fallback to buffered I/O if we are appending. */
-	if (i_size_read(inode) <= offset)
+	/* Fallback to buffered I/O if we are appending and
+	 * concurrent O_DIRECT writes are allowed.
+	 */
+	if (i_size_read(inode) <= offset && !full_coherency)
 		return 0;
 
-	return __blockdev_direct_IO(rw, iocb, inode, inode->i_sb->s_bdev,
+	if (rw == READ)
+		return __blockdev_direct_IO(rw, iocb, inode,
+				    inode->i_sb->s_bdev,
 				    iter, offset,
 				    ocfs2_direct_IO_get_blocks,
 				    ocfs2_dio_end_io, NULL, 0);
+	else
+		return ocfs2_direct_IO_write(iocb, iter, offset);
 }
 
 static void ocfs2_figure_cluster_boundaries(struct ocfs2_super *osb,
diff --git a/fs/ocfs2/file.c b/fs/ocfs2/file.c
index e0f04d55fd05..46e0d4e857c7 100644
--- a/fs/ocfs2/file.c
+++ b/fs/ocfs2/file.c
@@ -295,7 +295,7 @@ out:
 	return ret;
 }
 
-static int ocfs2_set_inode_size(handle_t *handle,
+int ocfs2_set_inode_size(handle_t *handle,
 				struct inode *inode,
 				struct buffer_head *fe_bh,
 				u64 new_i_size)
@@ -441,7 +441,7 @@ out:
 	return status;
 }
 
-static int ocfs2_truncate_file(struct inode *inode,
+int ocfs2_truncate_file(struct inode *inode,
 			       struct buffer_head *di_bh,
 			       u64 new_i_size)
 {
@@ -709,6 +709,13 @@ leave:
 	return status;
 }
 
+int ocfs2_extend_allocation(struct inode *inode, u32 logical_start,
+		u32 clusters_to_add, int mark_unwritten)
+{
+	return __ocfs2_extend_allocation(inode, logical_start,
+			clusters_to_add, mark_unwritten);
+}
+
 /*
  * While a write will already be ordering the data, a truncate will not.
  * Thus, we need to explicitly order the zeroed pages.
@@ -2109,6 +2116,9 @@ static int ocfs2_prepare_inode_for_write(struct file *file,
 	struct dentry *dentry = file->f_path.dentry;
 	struct inode *inode = dentry->d_inode;
 	loff_t saved_pos = 0, end;
+	struct ocfs2_super *osb = OCFS2_SB(inode->i_sb);
+	int full_coherency = !(osb->s_mount_opt &
+		OCFS2_MOUNT_COHERENCY_BUFFERED);
 
 	/*
 	 * We start with a read level meta lock and only jump to an ex
@@ -2197,7 +2207,16 @@ static int ocfs2_prepare_inode_for_write(struct file *file,
 		 * one node could wind up truncating another
 		 * nodes writes.
 		 */
-		if (end > i_size_read(inode)) {
+		if (end > i_size_read(inode) && !full_coherency) {
+			*direct_io = 0;
+			break;
+		}
+
+		/*
+		 * Fallback to old way if the feature bit is not set.
+		 */
+		if (end > i_size_read(inode) &&
+				!ocfs2_supports_append_dio(osb)) {
 			*direct_io = 0;
 			break;
 		}
@@ -2210,7 +2229,13 @@ static int ocfs2_prepare_inode_for_write(struct file *file,
 		 */
 		ret = ocfs2_check_range_for_holes(inode, saved_pos, count);
 		if (ret == 1) {
-			*direct_io = 0;
+			/*
+			 * Fallback to old way if the feature bit is not set.
+			 * Otherwise try dio first and then complete the rest
+			 * request through buffer io.
+			 */
+			if (!ocfs2_supports_append_dio(osb))
+				*direct_io = 0;
 			ret = 0;
 		} else if (ret < 0)
 			mlog_errno(ret);
@@ -2243,6 +2268,7 @@ static ssize_t ocfs2_file_write_iter(struct kiocb *iocb,
 	u32 old_clusters;
 	struct file *file = iocb->ki_filp;
 	struct inode *inode = file_inode(file);
+	struct address_space *mapping = file->f_mapping;
 	struct ocfs2_super *osb = OCFS2_SB(inode->i_sb);
 	int full_coherency = !(osb->s_mount_opt &
 			       OCFS2_MOUNT_COHERENCY_BUFFERED);
@@ -2357,11 +2383,51 @@ relock:
 
 	iov_iter_truncate(from, count);
 	if (direct_io) {
+		loff_t endbyte;
+		ssize_t written_buffered;
 		written = generic_file_direct_write(iocb, from, *ppos);
-		if (written < 0) {
+		if (written < 0 || written == count) {
 			ret = written;
 			goto out_dio;
 		}
+
+		/*
+		 * for completing the rest of the request.
+		 */
+		*ppos += written;
+		count -= written;
+		written_buffered = generic_perform_write(file, from, *ppos);
+		/*
+		 * If generic_file_buffered_write() returned a synchronous error
+		 * then we want to return the number of bytes which were
+		 * direct-written, or the error code if that was zero. Note
+		 * that this differs from normal direct-io semantics, which
+		 * will return -EFOO even if some bytes were written.
+		 */
+		if (written_buffered < 0) {
+			ret = written_buffered;
+			goto out_dio;
+		}
+
+		iocb->ki_pos = *ppos + written_buffered;
+		/* We need to ensure that the page cache pages are written to
+		 * disk and invalidated to preserve the expected O_DIRECT
+		 * semantics.
+		 */
+		endbyte = *ppos + written_buffered - 1;
+		ret = filemap_write_and_wait_range(file->f_mapping, *ppos,
+				endbyte);
+		if (ret == 0) {
+			written += written_buffered;
+			invalidate_mapping_pages(mapping,
+					*ppos >> PAGE_CACHE_SHIFT,
+					endbyte >> PAGE_CACHE_SHIFT);
+		} else {
+			/*
+			 * We don't know how much we wrote, so just return
+			 * the number of bytes which were direct-written
+			 */
+		}
 	} else {
 		current->backing_dev_info = inode_to_bdi(inode);
 		written = generic_perform_write(file, from, *ppos);
diff --git a/fs/ocfs2/file.h b/fs/ocfs2/file.h
index 97bf761c9e7c..e8c62f22215c 100644
--- a/fs/ocfs2/file.h
+++ b/fs/ocfs2/file.h
@@ -51,13 +51,22 @@ int ocfs2_add_inode_data(struct ocfs2_super *osb,
 			 struct ocfs2_alloc_context *data_ac,
 			 struct ocfs2_alloc_context *meta_ac,
 			 enum ocfs2_alloc_restarted *reason_ret);
+int ocfs2_set_inode_size(handle_t *handle,
+		struct inode *inode,
+		struct buffer_head *fe_bh,
+		u64 new_i_size);
 int ocfs2_simple_size_update(struct inode *inode,
 			     struct buffer_head *di_bh,
 			     u64 new_i_size);
+int ocfs2_truncate_file(struct inode *inode,
+		struct buffer_head *di_bh,
+		u64 new_i_size);
 int ocfs2_extend_no_holes(struct inode *inode, struct buffer_head *di_bh,
 			  u64 new_i_size, u64 zero_to);
 int ocfs2_zero_extend(struct inode *inode, struct buffer_head *di_bh,
 		      loff_t zero_to);
+int ocfs2_extend_allocation(struct inode *inode, u32 logical_start,
+		u32 clusters_to_add, int mark_unwritten);
 int ocfs2_setattr(struct dentry *dentry, struct iattr *attr);
 int ocfs2_getattr(struct vfsmount *mnt, struct dentry *dentry,
 		  struct kstat *stat);
diff --git a/fs/ocfs2/inode.c b/fs/ocfs2/inode.c
index c8b25de9efbb..3025c0da6b8a 100644
--- a/fs/ocfs2/inode.c
+++ b/fs/ocfs2/inode.c
@@ -648,7 +648,7 @@ static int ocfs2_remove_inode(struct inode *inode,
 
 	if (!(OCFS2_I(inode)->ip_flags & OCFS2_INODE_SKIP_ORPHAN_DIR)) {
 		status = ocfs2_orphan_del(osb, handle, orphan_dir_inode, inode,
-					  orphan_dir_bh);
+					  orphan_dir_bh, false);
 		if (status < 0) {
 			mlog_errno(status);
 			goto bail_commit;
diff --git a/fs/ocfs2/inode.h b/fs/ocfs2/inode.h
index ca3431ee7f24..5e86b247c821 100644
--- a/fs/ocfs2/inode.h
+++ b/fs/ocfs2/inode.h
@@ -81,6 +81,8 @@ struct ocfs2_inode_info
 	tid_t i_sync_tid;
 	tid_t i_datasync_tid;
 
+	wait_queue_head_t append_dio_wq;
+
 	struct dquot *i_dquot[MAXQUOTAS];
 };
 
diff --git a/fs/ocfs2/journal.c b/fs/ocfs2/journal.c
index d10860fde165..ff531928269e 100644
--- a/fs/ocfs2/journal.c
+++ b/fs/ocfs2/journal.c
@@ -50,6 +50,8 @@
 #include "sysfile.h"
 #include "uptodate.h"
 #include "quota.h"
+#include "file.h"
+#include "namei.h"
 
 #include "buffer_head_io.h"
 #include "ocfs2_trace.h"
@@ -69,13 +71,15 @@ static int ocfs2_journal_toggle_dirty(struct ocfs2_super *osb,
 static int ocfs2_trylock_journal(struct ocfs2_super *osb,
 				 int slot_num);
 static int ocfs2_recover_orphans(struct ocfs2_super *osb,
-				 int slot);
+				 int slot,
+				 enum ocfs2_orphan_reco_type orphan_reco_type);
 static int ocfs2_commit_thread(void *arg);
 static void ocfs2_queue_recovery_completion(struct ocfs2_journal *journal,
 					    int slot_num,
 					    struct ocfs2_dinode *la_dinode,
 					    struct ocfs2_dinode *tl_dinode,
-					    struct ocfs2_quota_recovery *qrec);
+					    struct ocfs2_quota_recovery *qrec,
+					    enum ocfs2_orphan_reco_type orphan_reco_type);
 
 static inline int ocfs2_wait_on_mount(struct ocfs2_super *osb)
 {
@@ -149,7 +153,8 @@ int ocfs2_compute_replay_slots(struct ocfs2_super *osb)
 	return 0;
 }
 
-void ocfs2_queue_replay_slots(struct ocfs2_super *osb)
+void ocfs2_queue_replay_slots(struct ocfs2_super *osb,
+		enum ocfs2_orphan_reco_type orphan_reco_type)
 {
 	struct ocfs2_replay_map *replay_map = osb->replay_map;
 	int i;
@@ -163,7 +168,8 @@ void ocfs2_queue_replay_slots(struct ocfs2_super *osb)
 	for (i = 0; i < replay_map->rm_slots; i++)
 		if (replay_map->rm_replay_slots[i])
 			ocfs2_queue_recovery_completion(osb->journal, i, NULL,
-							NULL, NULL);
+							NULL, NULL,
+							orphan_reco_type);
 	replay_map->rm_state = REPLAY_DONE;
 }
 
@@ -1174,6 +1180,7 @@ struct ocfs2_la_recovery_item {
 	struct ocfs2_dinode	*lri_la_dinode;
 	struct ocfs2_dinode	*lri_tl_dinode;
 	struct ocfs2_quota_recovery *lri_qrec;
+	enum ocfs2_orphan_reco_type  lri_orphan_reco_type;
 };
 
 /* Does the second half of the recovery process. By this point, the
@@ -1195,6 +1202,7 @@ void ocfs2_complete_recovery(struct work_struct *work)
 	struct ocfs2_dinode *la_dinode, *tl_dinode;
 	struct ocfs2_la_recovery_item *item, *n;
 	struct ocfs2_quota_recovery *qrec;
+	enum ocfs2_orphan_reco_type orphan_reco_type;
 	LIST_HEAD(tmp_la_list);
 
 	trace_ocfs2_complete_recovery(
@@ -1212,6 +1220,7 @@ void ocfs2_complete_recovery(struct work_struct *work)
 		la_dinode = item->lri_la_dinode;
 		tl_dinode = item->lri_tl_dinode;
 		qrec = item->lri_qrec;
+		orphan_reco_type = item->lri_orphan_reco_type;
 
 		trace_ocfs2_complete_recovery_slot(item->lri_slot,
 			la_dinode ? le64_to_cpu(la_dinode->i_blkno) : 0,
@@ -1236,7 +1245,8 @@ void ocfs2_complete_recovery(struct work_struct *work)
 			kfree(tl_dinode);
 		}
 
-		ret = ocfs2_recover_orphans(osb, item->lri_slot);
+		ret = ocfs2_recover_orphans(osb, item->lri_slot,
+				orphan_reco_type);
 		if (ret < 0)
 			mlog_errno(ret);
 
@@ -1261,7 +1271,8 @@ static void ocfs2_queue_recovery_completion(struct ocfs2_journal *journal,
 					    int slot_num,
 					    struct ocfs2_dinode *la_dinode,
 					    struct ocfs2_dinode *tl_dinode,
-					    struct ocfs2_quota_recovery *qrec)
+					    struct ocfs2_quota_recovery *qrec,
+					    enum ocfs2_orphan_reco_type orphan_reco_type)
 {
 	struct ocfs2_la_recovery_item *item;
 
@@ -1285,6 +1296,7 @@ static void ocfs2_queue_recovery_completion(struct ocfs2_journal *journal,
 	item->lri_slot = slot_num;
 	item->lri_tl_dinode = tl_dinode;
 	item->lri_qrec = qrec;
+	item->lri_orphan_reco_type = orphan_reco_type;
 
 	spin_lock(&journal->j_lock);
 	list_add_tail(&item->lri_list, &journal->j_la_cleanups);
@@ -1304,7 +1316,8 @@ void ocfs2_complete_mount_recovery(struct ocfs2_super *osb)
 	/* No need to queue up our truncate_log as regular cleanup will catch
 	 * that */
 	ocfs2_queue_recovery_completion(journal, osb->slot_num,
-					osb->local_alloc_copy, NULL, NULL);
+					osb->local_alloc_copy, NULL, NULL,
+					ORPHAN_NEED_TRUNCATE);
 	ocfs2_schedule_truncate_log_flush(osb, 0);
 
 	osb->local_alloc_copy = NULL;
@@ -1312,7 +1325,7 @@ void ocfs2_complete_mount_recovery(struct ocfs2_super *osb)
 
 	/* queue to recover orphan slots for all offline slots */
 	ocfs2_replay_map_set_state(osb, REPLAY_NEEDED);
-	ocfs2_queue_replay_slots(osb);
+	ocfs2_queue_replay_slots(osb, ORPHAN_NEED_TRUNCATE);
 	ocfs2_free_replay_slots(osb);
 }
 
@@ -1323,7 +1336,8 @@ void ocfs2_complete_quota_recovery(struct ocfs2_super *osb)
 						osb->slot_num,
 						NULL,
 						NULL,
-						osb->quota_rec);
+						osb->quota_rec,
+						ORPHAN_NEED_TRUNCATE);
 		osb->quota_rec = NULL;
 	}
 }
@@ -1360,7 +1374,7 @@ restart:
 
 	/* queue recovery for our own slot */
 	ocfs2_queue_recovery_completion(osb->journal, osb->slot_num, NULL,
-					NULL, NULL);
+					NULL, NULL, ORPHAN_NO_NEED_TRUNCATE);
 
 	spin_lock(&osb->osb_lock);
 	while (rm->rm_used) {
@@ -1419,13 +1433,14 @@ skip_recovery:
 			continue;
 		}
 		ocfs2_queue_recovery_completion(osb->journal, rm_quota[i],
-						NULL, NULL, qrec);
+						NULL, NULL, qrec,
+						ORPHAN_NEED_TRUNCATE);
 	}
 
 	ocfs2_super_unlock(osb, 1);
 
 	/* queue recovery for offline slots */
-	ocfs2_queue_replay_slots(osb);
+	ocfs2_queue_replay_slots(osb, ORPHAN_NEED_TRUNCATE);
 
 bail:
 	mutex_lock(&osb->recovery_lock);
@@ -1711,7 +1726,7 @@ static int ocfs2_recover_node(struct ocfs2_super *osb,
 
 	/* This will kfree the memory pointed to by la_copy and tl_copy */
 	ocfs2_queue_recovery_completion(osb->journal, slot_num, la_copy,
-					tl_copy, NULL);
+					tl_copy, NULL, ORPHAN_NEED_TRUNCATE);
 
 	status = 0;
 done:
@@ -1901,7 +1916,7 @@ void ocfs2_queue_orphan_scan(struct ocfs2_super *osb)
 
 	for (i = 0; i < osb->max_slots; i++)
 		ocfs2_queue_recovery_completion(osb->journal, i, NULL, NULL,
-						NULL);
+						NULL, ORPHAN_NO_NEED_TRUNCATE);
 	/*
 	 * We queued a recovery on orphan slots, increment the sequence
 	 * number and update LVB so other node will skip the scan for a while
@@ -2000,6 +2015,13 @@ static int ocfs2_orphan_filldir(struct dir_context *ctx, const char *name,
 	if (IS_ERR(iter))
 		return 0;
 
+	/* Skip inodes which are already added to recover list, since dio may
+	 * happen concurrently with unlink/rename */
+	if (OCFS2_I(iter)->ip_next_orphan) {
+		iput(iter);
+		return 0;
+	}
+
 	trace_ocfs2_orphan_filldir((unsigned long long)OCFS2_I(iter)->ip_blkno);
 	/* No locking is required for the next_orphan queue as there
 	 * is only ever a single process doing orphan recovery. */
@@ -2108,7 +2130,8 @@ static void ocfs2_clear_recovering_orphan_dir(struct ocfs2_super *osb,
  *   advertising our state to ocfs2_delete_inode().
  */
 static int ocfs2_recover_orphans(struct ocfs2_super *osb,
-				 int slot)
+				 int slot,
+				 enum ocfs2_orphan_reco_type orphan_reco_type)
 {
 	int ret = 0;
 	struct inode *inode = NULL;
@@ -2132,13 +2155,60 @@ static int ocfs2_recover_orphans(struct ocfs2_super *osb,
 					(unsigned long long)oi->ip_blkno);
 
 		iter = oi->ip_next_orphan;
+		oi->ip_next_orphan = NULL;
+
+		/*
+		 * We need to take and drop the inode lock to
+		 * force read inode from disk.
+		 */
+		ret = ocfs2_inode_lock(inode, NULL, 0);
+		if (ret) {
+			mlog_errno(ret);
+			goto next;
+		}
+		ocfs2_inode_unlock(inode, 0);
+
+		if (inode->i_nlink == 0) {
+			spin_lock(&oi->ip_lock);
+			/* Set the proper information to get us going into
+			 * ocfs2_delete_inode. */
+			oi->ip_flags |= OCFS2_INODE_MAYBE_ORPHANED;
+			spin_unlock(&oi->ip_lock);
+		} else if (orphan_reco_type == ORPHAN_NEED_TRUNCATE) {
+			struct buffer_head *di_bh = NULL;
+
+			ret = ocfs2_rw_lock(inode, 1);
+			if (ret) {
+				mlog_errno(ret);
+				goto next;
+			}
+
+			ret = ocfs2_inode_lock(inode, &di_bh, 1);
+			if (ret < 0) {
+				ocfs2_rw_unlock(inode, 1);
+				mlog_errno(ret);
+				goto next;
+			}
+
+			ret = ocfs2_truncate_file(inode, di_bh,
+					i_size_read(inode));
+			ocfs2_inode_unlock(inode, 1);
+			ocfs2_rw_unlock(inode, 1);
+			brelse(di_bh);
+			if (ret < 0) {
+				if (ret != -ENOSPC)
+					mlog_errno(ret);
+				goto next;
+			}
+
+			ret = ocfs2_del_inode_from_orphan(osb, inode, 0, 0);
+			if (ret)
+				mlog_errno(ret);
 
-		spin_lock(&oi->ip_lock);
-		/* Set the proper information to get us going into
-		 * ocfs2_delete_inode. */
-		oi->ip_flags |= OCFS2_INODE_MAYBE_ORPHANED;
-		spin_unlock(&oi->ip_lock);
+			wake_up(&OCFS2_I(inode)->append_dio_wq);
+		} /* else if ORPHAN_NO_NEED_TRUNCATE, do nothing */
 
+next:
 		iput(inode);
 
 		inode = iter;
diff --git a/fs/ocfs2/journal.h b/fs/ocfs2/journal.h
index 7f8cde94abfe..f4cd3c3e9fb7 100644
--- a/fs/ocfs2/journal.h
+++ b/fs/ocfs2/journal.h
@@ -472,6 +472,11 @@ static inline int ocfs2_unlink_credits(struct super_block *sb)
  * orphan dir index leaf */
 #define OCFS2_DELETE_INODE_CREDITS (3 * OCFS2_INODE_UPDATE_CREDITS + 4)
 
+/* dinode + orphan dir dinode + extent tree leaf block + orphan dir entry +
+ * orphan dir index root + orphan dir index leaf */
+#define OCFS2_INODE_ADD_TO_ORPHAN_CREDITS  (2 * OCFS2_INODE_UPDATE_CREDITS + 4)
+#define OCFS2_INODE_DEL_FROM_ORPHAN_CREDITS  OCFS2_INODE_ADD_TO_ORPHAN_CREDITS
+
 /* dinode update, old dir dinode update, new dir dinode update, old
  * dir dir entry, new dir dir entry, dir entry update for renaming
  * directory + target unlink + 3 x dir index leaves */
diff --git a/fs/ocfs2/namei.c b/fs/ocfs2/namei.c
index 914c121ec890..b5c3a5ea3ee6 100644
--- a/fs/ocfs2/namei.c
+++ b/fs/ocfs2/namei.c
@@ -79,7 +79,8 @@ static int ocfs2_prepare_orphan_dir(struct ocfs2_super *osb,
 				    struct inode **ret_orphan_dir,
 				    u64 blkno,
 				    char *name,
-				    struct ocfs2_dir_lookup_result *lookup);
+				    struct ocfs2_dir_lookup_result *lookup,
+				    bool dio);
 
 static int ocfs2_orphan_add(struct ocfs2_super *osb,
 			    handle_t *handle,
@@ -87,7 +88,8 @@ static int ocfs2_orphan_add(struct ocfs2_super *osb,
 			    struct buffer_head *fe_bh,
 			    char *name,
 			    struct ocfs2_dir_lookup_result *lookup,
-			    struct inode *orphan_dir_inode);
+			    struct inode *orphan_dir_inode,
+			    bool dio);
 
 static int ocfs2_create_symlink_data(struct ocfs2_super *osb,
 				     handle_t *handle,
@@ -104,6 +106,8 @@ static int ocfs2_double_lock(struct ocfs2_super *osb,
 static void ocfs2_double_unlock(struct inode *inode1, struct inode *inode2);
 /* An orphan dir name is an 8 byte value, printed as a hex string */
 #define OCFS2_ORPHAN_NAMELEN ((int)(2 * sizeof(u64)))
+#define OCFS2_DIO_ORPHAN_PREFIX "dio-"
+#define OCFS2_DIO_ORPHAN_PREFIX_LEN 4
 
 static struct dentry *ocfs2_lookup(struct inode *dir, struct dentry *dentry,
 				   unsigned int flags)
@@ -952,7 +956,8 @@ static int ocfs2_unlink(struct inode *dir,
 	if (ocfs2_inode_is_unlinkable(inode)) {
 		status = ocfs2_prepare_orphan_dir(osb, &orphan_dir,
 						  OCFS2_I(inode)->ip_blkno,
-						  orphan_name, &orphan_insert);
+						  orphan_name, &orphan_insert,
+						  false);
 		if (status < 0) {
 			mlog_errno(status);
 			goto leave;
@@ -1004,7 +1009,7 @@ static int ocfs2_unlink(struct inode *dir,
 
 	if (is_unlinkable) {
 		status = ocfs2_orphan_add(osb, handle, inode, fe_bh,
-				orphan_name, &orphan_insert, orphan_dir);
+				orphan_name, &orphan_insert, orphan_dir, false);
 		if (status < 0)
 			mlog_errno(status);
 	}
@@ -1440,7 +1445,8 @@ static int ocfs2_rename(struct inode *old_dir,
 		if (S_ISDIR(new_inode->i_mode) || (new_inode->i_nlink == 1)) {
 			status = ocfs2_prepare_orphan_dir(osb, &orphan_dir,
 						OCFS2_I(new_inode)->ip_blkno,
-						orphan_name, &orphan_insert);
+						orphan_name, &orphan_insert,
+						false);
 			if (status < 0) {
 				mlog_errno(status);
 				goto bail;
@@ -1507,7 +1513,7 @@ static int ocfs2_rename(struct inode *old_dir,
 		if (should_add_orphan) {
 			status = ocfs2_orphan_add(osb, handle, new_inode,
 					newfe_bh, orphan_name,
-					&orphan_insert, orphan_dir);
+					&orphan_insert, orphan_dir, false);
 			if (status < 0) {
 				mlog_errno(status);
 				goto bail;
@@ -2088,12 +2094,28 @@ static int __ocfs2_prepare_orphan_dir(struct inode *orphan_dir_inode,
 				      struct buffer_head *orphan_dir_bh,
 				      u64 blkno,
 				      char *name,
-				      struct ocfs2_dir_lookup_result *lookup)
+				      struct ocfs2_dir_lookup_result *lookup,
+				      bool dio)
 {
 	int ret;
 	struct ocfs2_super *osb = OCFS2_SB(orphan_dir_inode->i_sb);
+	int namelen = dio ?
+			(OCFS2_DIO_ORPHAN_PREFIX_LEN + OCFS2_ORPHAN_NAMELEN) :
+			OCFS2_ORPHAN_NAMELEN;
+
+	if (dio) {
+		ret = snprintf(name, OCFS2_DIO_ORPHAN_PREFIX_LEN + 1, "%s",
+				OCFS2_DIO_ORPHAN_PREFIX);
+		if (ret != OCFS2_DIO_ORPHAN_PREFIX_LEN) {
+			ret = -EINVAL;
+			mlog_errno(ret);
+			return ret;
+		}
 
-	ret = ocfs2_blkno_stringify(blkno, name);
+		ret = ocfs2_blkno_stringify(blkno,
+				name + OCFS2_DIO_ORPHAN_PREFIX_LEN);
+	} else
+		ret = ocfs2_blkno_stringify(blkno, name);
 	if (ret < 0) {
 		mlog_errno(ret);
 		return ret;
@@ -2101,7 +2123,7 @@ static int __ocfs2_prepare_orphan_dir(struct inode *orphan_dir_inode,
 
 	ret = ocfs2_prepare_dir_for_insert(osb, orphan_dir_inode,
 					   orphan_dir_bh, name,
-					   OCFS2_ORPHAN_NAMELEN, lookup);
+					   namelen, lookup);
 	if (ret < 0) {
 		mlog_errno(ret);
 		return ret;
@@ -2128,7 +2150,8 @@ static int ocfs2_prepare_orphan_dir(struct ocfs2_super *osb,
 				    struct inode **ret_orphan_dir,
 				    u64 blkno,
 				    char *name,
-				    struct ocfs2_dir_lookup_result *lookup)
+				    struct ocfs2_dir_lookup_result *lookup,
+				    bool dio)
 {
 	struct inode *orphan_dir_inode = NULL;
 	struct buffer_head *orphan_dir_bh = NULL;
@@ -2142,7 +2165,7 @@ static int ocfs2_prepare_orphan_dir(struct ocfs2_super *osb,
 	}
 
 	ret = __ocfs2_prepare_orphan_dir(orphan_dir_inode, orphan_dir_bh,
-					 blkno, name, lookup);
+					 blkno, name, lookup, dio);
 	if (ret < 0) {
 		mlog_errno(ret);
 		goto out;
@@ -2170,12 +2193,16 @@ static int ocfs2_orphan_add(struct ocfs2_super *osb,
 			    struct buffer_head *fe_bh,
 			    char *name,
 			    struct ocfs2_dir_lookup_result *lookup,
-			    struct inode *orphan_dir_inode)
+			    struct inode *orphan_dir_inode,
+			    bool dio)
 {
 	struct buffer_head *orphan_dir_bh = NULL;
 	int status = 0;
 	struct ocfs2_dinode *orphan_fe;
 	struct ocfs2_dinode *fe = (struct ocfs2_dinode *) fe_bh->b_data;
+	int namelen = dio ?
+			(OCFS2_DIO_ORPHAN_PREFIX_LEN + OCFS2_ORPHAN_NAMELEN) :
+			OCFS2_ORPHAN_NAMELEN;
 
 	trace_ocfs2_orphan_add_begin(
 				(unsigned long long)OCFS2_I(inode)->ip_blkno);
@@ -2219,7 +2246,7 @@ static int ocfs2_orphan_add(struct ocfs2_super *osb,
 	ocfs2_journal_dirty(handle, orphan_dir_bh);
 
 	status = __ocfs2_add_entry(handle, orphan_dir_inode, name,
-				   OCFS2_ORPHAN_NAMELEN, inode,
+				   namelen, inode,
 				   OCFS2_I(inode)->ip_blkno,
 				   orphan_dir_bh, lookup);
 	if (status < 0) {
@@ -2227,13 +2254,21 @@ static int ocfs2_orphan_add(struct ocfs2_super *osb,
 		goto rollback;
 	}
 
-	fe->i_flags |= cpu_to_le32(OCFS2_ORPHANED_FL);
-	OCFS2_I(inode)->ip_flags &= ~OCFS2_INODE_SKIP_ORPHAN_DIR;
+	if (dio) {
+		/* Update flag OCFS2_DIO_ORPHANED_FL and record the orphan
+		 * slot.
+		 */
+		fe->i_flags |= cpu_to_le32(OCFS2_DIO_ORPHANED_FL);
+		fe->i_dio_orphaned_slot = cpu_to_le16(osb->slot_num);
+	} else {
+		fe->i_flags |= cpu_to_le32(OCFS2_ORPHANED_FL);
+		OCFS2_I(inode)->ip_flags &= ~OCFS2_INODE_SKIP_ORPHAN_DIR;
 
-	/* Record which orphan dir our inode now resides
-	 * in. delete_inode will use this to determine which orphan
-	 * dir to lock. */
-	fe->i_orphaned_slot = cpu_to_le16(osb->slot_num);
+		/* Record which orphan dir our inode now resides
+		 * in. delete_inode will use this to determine which orphan
+		 * dir to lock. */
+		fe->i_orphaned_slot = cpu_to_le16(osb->slot_num);
+	}
 
 	ocfs2_journal_dirty(handle, fe_bh);
 
@@ -2258,14 +2293,28 @@ int ocfs2_orphan_del(struct ocfs2_super *osb,
 		     handle_t *handle,
 		     struct inode *orphan_dir_inode,
 		     struct inode *inode,
-		     struct buffer_head *orphan_dir_bh)
+		     struct buffer_head *orphan_dir_bh,
+		     bool dio)
 {
-	char name[OCFS2_ORPHAN_NAMELEN + 1];
+	const int namelen = OCFS2_DIO_ORPHAN_PREFIX_LEN + OCFS2_ORPHAN_NAMELEN;
+	char name[namelen + 1];
 	struct ocfs2_dinode *orphan_fe;
 	int status = 0;
 	struct ocfs2_dir_lookup_result lookup = { NULL, };
 
-	status = ocfs2_blkno_stringify(OCFS2_I(inode)->ip_blkno, name);
+	if (dio) {
+		status = snprintf(name, OCFS2_DIO_ORPHAN_PREFIX_LEN + 1, "%s",
+				OCFS2_DIO_ORPHAN_PREFIX);
+		if (status != OCFS2_DIO_ORPHAN_PREFIX_LEN) {
+			status = -EINVAL;
+			mlog_errno(status);
+			return status;
+		}
+
+		status = ocfs2_blkno_stringify(OCFS2_I(inode)->ip_blkno,
+				name + OCFS2_DIO_ORPHAN_PREFIX_LEN);
+	} else
+		status = ocfs2_blkno_stringify(OCFS2_I(inode)->ip_blkno, name);
 	if (status < 0) {
 		mlog_errno(status);
 		goto leave;
@@ -2273,10 +2322,10 @@ int ocfs2_orphan_del(struct ocfs2_super *osb,
 
 	trace_ocfs2_orphan_del(
 	     (unsigned long long)OCFS2_I(orphan_dir_inode)->ip_blkno,
-	     name, OCFS2_ORPHAN_NAMELEN);
+	     name, namelen);
 
 	/* find it's spot in the orphan directory */
-	status = ocfs2_find_entry(name, OCFS2_ORPHAN_NAMELEN, orphan_dir_inode,
+	status = ocfs2_find_entry(name, namelen, orphan_dir_inode,
 				  &lookup);
 	if (status) {
 		mlog_errno(status);
@@ -2376,7 +2425,8 @@ static int ocfs2_prep_new_orphaned_file(struct inode *dir,
 	}
 
 	ret = __ocfs2_prepare_orphan_dir(orphan_dir, orphan_dir_bh,
-					 di_blkno, orphan_name, orphan_insert);
+					 di_blkno, orphan_name, orphan_insert,
+					 false);
 	if (ret < 0) {
 		mlog_errno(ret);
 		goto out;
@@ -2482,7 +2532,7 @@ int ocfs2_create_inode_in_orphan(struct inode *dir,
 
 	di = (struct ocfs2_dinode *)new_di_bh->b_data;
 	status = ocfs2_orphan_add(osb, handle, inode, new_di_bh, orphan_name,
-				  &orphan_insert, orphan_dir);
+				  &orphan_insert, orphan_dir, false);
 	if (status < 0) {
 		mlog_errno(status);
 		goto leave;
@@ -2527,6 +2577,186 @@ leave:
 	return status;
 }
 
+static int ocfs2_dio_orphan_recovered(struct inode *inode)
+{
+	int ret;
+	struct buffer_head *di_bh = NULL;
+	struct ocfs2_dinode *di = NULL;
+
+	ret = ocfs2_inode_lock(inode, &di_bh, 1);
+	if (ret < 0) {
+		mlog_errno(ret);
+		return 0;
+	}
+
+	di = (struct ocfs2_dinode *) di_bh->b_data;
+	ret = !(di->i_flags & cpu_to_le32(OCFS2_DIO_ORPHANED_FL));
+	ocfs2_inode_unlock(inode, 1);
+	brelse(di_bh);
+
+	return ret;
+}
+
+#define OCFS2_DIO_ORPHANED_FL_CHECK_INTERVAL 10000
+int ocfs2_add_inode_to_orphan(struct ocfs2_super *osb,
+	struct inode *inode)
+{
+	char orphan_name[OCFS2_DIO_ORPHAN_PREFIX_LEN + OCFS2_ORPHAN_NAMELEN + 1];
+	struct inode *orphan_dir_inode = NULL;
+	struct ocfs2_dir_lookup_result orphan_insert = { NULL, };
+	struct buffer_head *di_bh = NULL;
+	int status = 0;
+	handle_t *handle = NULL;
+	struct ocfs2_dinode *di = NULL;
+
+restart:
+	status = ocfs2_inode_lock(inode, &di_bh, 1);
+	if (status < 0) {
+		mlog_errno(status);
+		goto bail;
+	}
+
+	di = (struct ocfs2_dinode *) di_bh->b_data;
+	/*
+	 * Another append dio crashed?
+	 * If so, wait for recovery first.
+	 */
+	if (unlikely(di->i_flags & cpu_to_le32(OCFS2_DIO_ORPHANED_FL))) {
+		ocfs2_inode_unlock(inode, 1);
+		brelse(di_bh);
+		wait_event_interruptible_timeout(OCFS2_I(inode)->append_dio_wq,
+				ocfs2_dio_orphan_recovered(inode),
+				msecs_to_jiffies(OCFS2_DIO_ORPHANED_FL_CHECK_INTERVAL));
+		goto restart;
+	}
+
+	status = ocfs2_prepare_orphan_dir(osb, &orphan_dir_inode,
+			OCFS2_I(inode)->ip_blkno,
+			orphan_name,
+			&orphan_insert,
+			true);
+	if (status < 0) {
+		mlog_errno(status);
+		goto bail_unlock_inode;
+	}
+
+	handle = ocfs2_start_trans(osb,
+			OCFS2_INODE_ADD_TO_ORPHAN_CREDITS);
+	if (IS_ERR(handle)) {
+		status = PTR_ERR(handle);
+		goto bail_unlock_orphan;
+	}
+
+	status = ocfs2_orphan_add(osb, handle, inode, di_bh, orphan_name,
+			&orphan_insert, orphan_dir_inode, true);
+	if (status)
+		mlog_errno(status);
+
+	ocfs2_commit_trans(osb, handle);
+
+bail_unlock_orphan:
+	ocfs2_inode_unlock(orphan_dir_inode, 1);
+	mutex_unlock(&orphan_dir_inode->i_mutex);
+	iput(orphan_dir_inode);
+
+	ocfs2_free_dir_lookup_result(&orphan_insert);
+
+bail_unlock_inode:
+	ocfs2_inode_unlock(inode, 1);
+	brelse(di_bh);
+
+bail:
+	return status;
+}
+
+int ocfs2_del_inode_from_orphan(struct ocfs2_super *osb,
+		struct inode *inode, int update_isize,
+		loff_t end)
+{
+	struct inode *orphan_dir_inode = NULL;
+	struct buffer_head *orphan_dir_bh = NULL;
+	struct buffer_head *di_bh = NULL;
+	struct ocfs2_dinode *di = NULL;
+	handle_t *handle = NULL;
+	int status = 0;
+
+	status = ocfs2_inode_lock(inode, &di_bh, 1);
+	if (status < 0) {
+		mlog_errno(status);
+		goto bail;
+	}
+	di = (struct ocfs2_dinode *) di_bh->b_data;
+
+	orphan_dir_inode = ocfs2_get_system_file_inode(osb,
+			ORPHAN_DIR_SYSTEM_INODE,
+			le16_to_cpu(di->i_dio_orphaned_slot));
+	if (!orphan_dir_inode) {
+		status = -ENOENT;
+		mlog_errno(status);
+		goto bail_unlock_inode;
+	}
+
+	mutex_lock(&orphan_dir_inode->i_mutex);
+	status = ocfs2_inode_lock(orphan_dir_inode, &orphan_dir_bh, 1);
+	if (status < 0) {
+		mutex_unlock(&orphan_dir_inode->i_mutex);
+		iput(orphan_dir_inode);
+		mlog_errno(status);
+		goto bail_unlock_inode;
+	}
+
+	handle = ocfs2_start_trans(osb,
+			OCFS2_INODE_DEL_FROM_ORPHAN_CREDITS);
+	if (IS_ERR(handle)) {
+		status = PTR_ERR(handle);
+		goto bail_unlock_orphan;
+	}
+
+	BUG_ON(!(di->i_flags & cpu_to_le32(OCFS2_DIO_ORPHANED_FL)));
+
+	status = ocfs2_orphan_del(osb, handle, orphan_dir_inode,
+				inode, orphan_dir_bh, true);
+	if (status < 0) {
+		mlog_errno(status);
+		goto bail_commit;
+	}
+
+	status = ocfs2_journal_access_di(handle,
+			INODE_CACHE(inode),
+			di_bh,
+			OCFS2_JOURNAL_ACCESS_WRITE);
+	if (status < 0) {
+		mlog_errno(status);
+		goto bail_commit;
+	}
+
+	di->i_flags &= ~cpu_to_le32(OCFS2_DIO_ORPHANED_FL);
+	di->i_dio_orphaned_slot = 0;
+
+	if (update_isize) {
+		status = ocfs2_set_inode_size(handle, inode, di_bh, end);
+		if (status)
+			mlog_errno(status);
+	} else
+		ocfs2_journal_dirty(handle, di_bh);
+
+bail_commit:
+	ocfs2_commit_trans(osb, handle);
+
+bail_unlock_orphan:
+	ocfs2_inode_unlock(orphan_dir_inode, 1);
+	mutex_unlock(&orphan_dir_inode->i_mutex);
+	brelse(orphan_dir_bh);
+	iput(orphan_dir_inode);
+
+bail_unlock_inode:
+	ocfs2_inode_unlock(inode, 1);
+	brelse(di_bh);
+
+bail:
+	return status;
+}
+
 int ocfs2_mv_orphaned_inode_to_new(struct inode *dir,
 				   struct inode *inode,
 				   struct dentry *dentry)
@@ -2615,7 +2845,7 @@ int ocfs2_mv_orphaned_inode_to_new(struct inode *dir,
 	}
 
 	status = ocfs2_orphan_del(osb, handle, orphan_dir_inode, inode,
-				  orphan_dir_bh);
+				  orphan_dir_bh, false);
 	if (status < 0) {
 		mlog_errno(status);
 		goto out_commit;
diff --git a/fs/ocfs2/namei.h b/fs/ocfs2/namei.h
index e5d059d4f115..5ddecce172fa 100644
--- a/fs/ocfs2/namei.h
+++ b/fs/ocfs2/namei.h
@@ -34,10 +34,16 @@ int ocfs2_orphan_del(struct ocfs2_super *osb,
 		     handle_t *handle,
 		     struct inode *orphan_dir_inode,
 		     struct inode *inode,
-		     struct buffer_head *orphan_dir_bh);
+		     struct buffer_head *orphan_dir_bh,
+		     bool dio);
 int ocfs2_create_inode_in_orphan(struct inode *dir,
 				 int mode,
 				 struct inode **new_inode);
+int ocfs2_add_inode_to_orphan(struct ocfs2_super *osb,
+		struct inode *inode);
+int ocfs2_del_inode_from_orphan(struct ocfs2_super *osb,
+		struct inode *inode, int update_isize,
+		loff_t end);
 int ocfs2_mv_orphaned_inode_to_new(struct inode *dir,
 				   struct inode *new_inode,
 				   struct dentry *new_dentry);
diff --git a/fs/ocfs2/ocfs2.h b/fs/ocfs2/ocfs2.h
index fdbcbfed529e..8490c64d34fe 100644
--- a/fs/ocfs2/ocfs2.h
+++ b/fs/ocfs2/ocfs2.h
@@ -209,6 +209,11 @@ struct ocfs2_lock_res {
 #endif
 };
 
+enum ocfs2_orphan_reco_type {
+	ORPHAN_NO_NEED_TRUNCATE = 0,
+	ORPHAN_NEED_TRUNCATE,
+};
+
 enum ocfs2_orphan_scan_state {
 	ORPHAN_SCAN_ACTIVE,
 	ORPHAN_SCAN_INACTIVE
@@ -495,6 +500,14 @@ static inline int ocfs2_writes_unwritten_extents(struct ocfs2_super *osb)
 	return 0;
 }
 
+static inline int ocfs2_supports_append_dio(struct ocfs2_super *osb)
+{
+	if (osb->s_feature_ro_compat & OCFS2_FEATURE_RO_COMPAT_APPEND_DIO)
+		return 1;
+	return 0;
+}
+
+
 static inline int ocfs2_supports_inline_data(struct ocfs2_super *osb)
 {
 	if (osb->s_feature_incompat & OCFS2_FEATURE_INCOMPAT_INLINE_DATA)
@@ -726,6 +739,16 @@ static inline unsigned int ocfs2_clusters_for_bytes(struct super_block *sb,
 	return clusters;
 }
 
+static inline unsigned int ocfs2_bytes_to_clusters(struct super_block *sb,
+		u64 bytes)
+{
+	int cl_bits = OCFS2_SB(sb)->s_clustersize_bits;
+	unsigned int clusters;
+
+	clusters = (unsigned int)(bytes >> cl_bits);
+	return clusters;
+}
+
 static inline u64 ocfs2_blocks_for_bytes(struct super_block *sb,
 					 u64 bytes)
 {
diff --git a/fs/ocfs2/ocfs2_fs.h b/fs/ocfs2/ocfs2_fs.h
index 938387a10d5d..20e37a3ed26f 100644
--- a/fs/ocfs2/ocfs2_fs.h
+++ b/fs/ocfs2/ocfs2_fs.h
@@ -105,7 +105,8 @@
 					 | OCFS2_FEATURE_INCOMPAT_CLUSTERINFO)
 #define OCFS2_FEATURE_RO_COMPAT_SUPP	(OCFS2_FEATURE_RO_COMPAT_UNWRITTEN \
 					 | OCFS2_FEATURE_RO_COMPAT_USRQUOTA \
-					 | OCFS2_FEATURE_RO_COMPAT_GRPQUOTA)
+					 | OCFS2_FEATURE_RO_COMPAT_GRPQUOTA \
+					 | OCFS2_FEATURE_RO_COMPAT_APPEND_DIO)
 
 /*
  * Heartbeat-only devices are missing journals and other files.  The
@@ -199,6 +200,11 @@
 #define OCFS2_FEATURE_RO_COMPAT_USRQUOTA	0x0002
 #define OCFS2_FEATURE_RO_COMPAT_GRPQUOTA	0x0004
 
+/*
+ * Append Direct IO support
+ */
+#define OCFS2_FEATURE_RO_COMPAT_APPEND_DIO	0x0008
+
 /* The byte offset of the first backup block will be 1G.
  * The following will be 4G, 16G, 64G, 256G and 1T.
  */
@@ -229,6 +235,8 @@
 #define OCFS2_CHAIN_FL		(0x00000400)	/* Chain allocator */
 #define OCFS2_DEALLOC_FL	(0x00000800)	/* Truncate log */
 #define OCFS2_QUOTA_FL		(0x00001000)	/* Quota file */
+#define OCFS2_DIO_ORPHANED_FL	(0X00002000)	/* On the orphan list especially
+						 * for dio */
 
 /*
  * Flags on ocfs2_dinode.i_dyn_features
@@ -729,7 +737,9 @@ struct ocfs2_dinode {
 					   inode belongs to.  Only valid
 					   if allocated from a
 					   discontiguous block group */
-/*A0*/	__le64 i_reserved2[3];
+/*A0*/	__le16 i_dio_orphaned_slot;	/* only used for append dio write */
+	__le16 i_reserved1[3];
+	__le64 i_reserved2[2];
 /*B8*/	union {
 		__le64 i_pad1;		/* Generic way to refer to this
 					   64bit union */
diff --git a/fs/ocfs2/super.c b/fs/ocfs2/super.c
index 87a1f7679d9b..26675185b886 100644
--- a/fs/ocfs2/super.c
+++ b/fs/ocfs2/super.c
@@ -1746,6 +1746,8 @@ static void ocfs2_inode_init_once(void *data)
 	ocfs2_lock_res_init_once(&oi->ip_inode_lockres);
 	ocfs2_lock_res_init_once(&oi->ip_open_lockres);
 
+	init_waitqueue_head(&oi->append_dio_wq);
+
 	ocfs2_metadata_cache_init(INODE_CACHE(&oi->vfs_inode),
 				  &ocfs2_inode_caching_ops);
 
diff --git a/fs/open.c b/fs/open.c
index d36c42ff019d..33f9cbf2610b 100644
--- a/fs/open.c
+++ b/fs/open.c
@@ -667,11 +667,8 @@ int open_check_o_direct(struct file *f)
 {
 	/* NB: we're sure to have correct a_ops only after f_op->open */
 	if (f->f_flags & O_DIRECT) {
-		if (!f->f_mapping->a_ops ||
-		    ((!f->f_mapping->a_ops->direct_IO) &&
-		    (!f->f_mapping->a_ops->get_xip_mem))) {
+		if (!f->f_mapping->a_ops || !f->f_mapping->a_ops->direct_IO)
 			return -EINVAL;
-		}
 	}
 	return 0;
 }