Merge branch 'xfs-4.8-buf-fixes' into for-next
diff --git a/fs/Kconfig b/fs/Kconfig
index b8fcb41..4524916 100644
--- a/fs/Kconfig
+++ b/fs/Kconfig
@@ -10,6 +10,9 @@
 
 if BLOCK
 
+config FS_IOMAP
+	bool
+
 source "fs/ext2/Kconfig"
 source "fs/ext4/Kconfig"
 source "fs/jbd2/Kconfig"
diff --git a/fs/Makefile b/fs/Makefile
index 85b6e13..ed2b632 100644
--- a/fs/Makefile
+++ b/fs/Makefile
@@ -49,6 +49,7 @@
 obj-$(CONFIG_SYSCTL)		+= drop_caches.o
 
 obj-$(CONFIG_FHANDLE)		+= fhandle.o
+obj-$(CONFIG_FS_IOMAP)		+= iomap.o
 
 obj-y				+= quota/
 
diff --git a/fs/buffer.c b/fs/buffer.c
index 754813a..228288a 100644
--- a/fs/buffer.c
+++ b/fs/buffer.c
@@ -21,6 +21,7 @@
 #include <linux/kernel.h>
 #include <linux/syscalls.h>
 #include <linux/fs.h>
+#include <linux/iomap.h>
 #include <linux/mm.h>
 #include <linux/percpu.h>
 #include <linux/slab.h>
@@ -1891,8 +1892,62 @@
 }
 EXPORT_SYMBOL(page_zero_new_buffers);
 
-int __block_write_begin(struct page *page, loff_t pos, unsigned len,
-		get_block_t *get_block)
+static void
+iomap_to_bh(struct inode *inode, sector_t block, struct buffer_head *bh,
+		struct iomap *iomap)
+{
+	loff_t offset = block << inode->i_blkbits;
+
+	bh->b_bdev = iomap->bdev;
+
+	/*
+	 * Block points to offset in file we need to map, iomap contains
+	 * the offset at which the map starts. If the map ends before the
+	 * current block, then do not map the buffer and let the caller
+	 * handle it.
+	 */
+	BUG_ON(offset >= iomap->offset + iomap->length);
+
+	switch (iomap->type) {
+	case IOMAP_HOLE:
+		/*
+		 * If the buffer is not up to date or beyond the current EOF,
+		 * we need to mark it as new to ensure sub-block zeroing is
+		 * executed if necessary.
+		 */
+		if (!buffer_uptodate(bh) ||
+		    (offset >= i_size_read(inode)))
+			set_buffer_new(bh);
+		break;
+	case IOMAP_DELALLOC:
+		if (!buffer_uptodate(bh) ||
+		    (offset >= i_size_read(inode)))
+			set_buffer_new(bh);
+		set_buffer_uptodate(bh);
+		set_buffer_mapped(bh);
+		set_buffer_delay(bh);
+		break;
+	case IOMAP_UNWRITTEN:
+		/*
+		 * For unwritten regions, we always need to ensure that
+		 * sub-block writes cause the regions in the block we are not
+		 * writing to are zeroed. Set the buffer as new to ensure this.
+		 */
+		set_buffer_new(bh);
+		set_buffer_unwritten(bh);
+		/* FALLTHRU */
+	case IOMAP_MAPPED:
+		if (offset >= i_size_read(inode))
+			set_buffer_new(bh);
+		bh->b_blocknr = (iomap->blkno >> (inode->i_blkbits - 9)) +
+				((offset - iomap->offset) >> inode->i_blkbits);
+		set_buffer_mapped(bh);
+		break;
+	}
+}
+
+int __block_write_begin_int(struct page *page, loff_t pos, unsigned len,
+		get_block_t *get_block, struct iomap *iomap)
 {
 	unsigned from = pos & (PAGE_SIZE - 1);
 	unsigned to = from + len;
@@ -1928,9 +1983,14 @@
 			clear_buffer_new(bh);
 		if (!buffer_mapped(bh)) {
 			WARN_ON(bh->b_size != blocksize);
-			err = get_block(inode, block, bh, 1);
-			if (err)
-				break;
+			if (get_block) {
+				err = get_block(inode, block, bh, 1);
+				if (err)
+					break;
+			} else {
+				iomap_to_bh(inode, block, bh, iomap);
+			}
+
 			if (buffer_new(bh)) {
 				unmap_underlying_metadata(bh->b_bdev,
 							bh->b_blocknr);
@@ -1971,6 +2031,12 @@
 		page_zero_new_buffers(page, from, to);
 	return err;
 }
+
+int __block_write_begin(struct page *page, loff_t pos, unsigned len,
+		get_block_t *get_block)
+{
+	return __block_write_begin_int(page, pos, len, get_block, NULL);
+}
 EXPORT_SYMBOL(__block_write_begin);
 
 static int __block_commit_write(struct inode *inode, struct page *page,
diff --git a/fs/internal.h b/fs/internal.h
index b71deee..c0c6f49 100644
--- a/fs/internal.h
+++ b/fs/internal.h
@@ -11,6 +11,7 @@
 
 struct super_block;
 struct file_system_type;
+struct iomap;
 struct linux_binprm;
 struct path;
 struct mount;
@@ -39,6 +40,8 @@
  * buffer.c
  */
 extern void guard_bio_eod(int rw, struct bio *bio);
+extern int __block_write_begin_int(struct page *page, loff_t pos, unsigned len,
+		get_block_t *get_block, struct iomap *iomap);
 
 /*
  * char_dev.c
diff --git a/fs/iomap.c b/fs/iomap.c
new file mode 100644
index 0000000..48141b8
--- /dev/null
+++ b/fs/iomap.c
@@ -0,0 +1,497 @@
+/*
+ * Copyright (C) 2010 Red Hat, Inc.
+ * Copyright (c) 2016 Christoph Hellwig.
+ *
+ * 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/module.h>
+#include <linux/compiler.h>
+#include <linux/fs.h>
+#include <linux/iomap.h>
+#include <linux/uaccess.h>
+#include <linux/gfp.h>
+#include <linux/mm.h>
+#include <linux/swap.h>
+#include <linux/pagemap.h>
+#include <linux/file.h>
+#include <linux/uio.h>
+#include <linux/backing-dev.h>
+#include <linux/buffer_head.h>
+#include <linux/dax.h>
+#include "internal.h"
+
+typedef loff_t (*iomap_actor_t)(struct inode *inode, loff_t pos, loff_t len,
+		void *data, struct iomap *iomap);
+
+/*
+ * Execute a iomap write on a segment of the mapping that spans a
+ * contiguous range of pages that have identical block mapping state.
+ *
+ * This avoids the need to map pages individually, do individual allocations
+ * for each page and most importantly avoid the need for filesystem specific
+ * locking per page. Instead, all the operations are amortised over the entire
+ * range of pages. It is assumed that the filesystems will lock whatever
+ * resources they require in the iomap_begin call, and release them in the
+ * iomap_end call.
+ */
+static loff_t
+iomap_apply(struct inode *inode, loff_t pos, loff_t length, unsigned flags,
+		struct iomap_ops *ops, void *data, iomap_actor_t actor)
+{
+	struct iomap iomap = { 0 };
+	loff_t written = 0, ret;
+
+	/*
+	 * Need to map a range from start position for length bytes. This can
+	 * span multiple pages - it is only guaranteed to return a range of a
+	 * single type of pages (e.g. all into a hole, all mapped or all
+	 * unwritten). Failure at this point has nothing to undo.
+	 *
+	 * If allocation is required for this range, reserve the space now so
+	 * that the allocation is guaranteed to succeed later on. Once we copy
+	 * the data into the page cache pages, then we cannot fail otherwise we
+	 * expose transient stale data. If the reserve fails, we can safely
+	 * back out at this point as there is nothing to undo.
+	 */
+	ret = ops->iomap_begin(inode, pos, length, flags, &iomap);
+	if (ret)
+		return ret;
+	if (WARN_ON(iomap.offset > pos))
+		return -EIO;
+
+	/*
+	 * Cut down the length to the one actually provided by the filesystem,
+	 * as it might not be able to give us the whole size that we requested.
+	 */
+	if (iomap.offset + iomap.length < pos + length)
+		length = iomap.offset + iomap.length - pos;
+
+	/*
+	 * Now that we have guaranteed that the space allocation will succeed.
+	 * we can do the copy-in page by page without having to worry about
+	 * failures exposing transient data.
+	 */
+	written = actor(inode, pos, length, data, &iomap);
+
+	/*
+	 * Now the data has been copied, commit the range we've copied.  This
+	 * should not fail unless the filesystem has had a fatal error.
+	 */
+	ret = ops->iomap_end(inode, pos, length, written > 0 ? written : 0,
+			flags, &iomap);
+
+	return written ? written : ret;
+}
+
+static void
+iomap_write_failed(struct inode *inode, loff_t pos, unsigned len)
+{
+	loff_t i_size = i_size_read(inode);
+
+	/*
+	 * Only truncate newly allocated pages beyoned EOF, even if the
+	 * write started inside the existing inode size.
+	 */
+	if (pos + len > i_size)
+		truncate_pagecache_range(inode, max(pos, i_size), pos + len);
+}
+
+static int
+iomap_write_begin(struct inode *inode, loff_t pos, unsigned len, unsigned flags,
+		struct page **pagep, struct iomap *iomap)
+{
+	pgoff_t index = pos >> PAGE_SHIFT;
+	struct page *page;
+	int status = 0;
+
+	BUG_ON(pos + len > iomap->offset + iomap->length);
+
+	page = grab_cache_page_write_begin(inode->i_mapping, index, flags);
+	if (!page)
+		return -ENOMEM;
+
+	status = __block_write_begin_int(page, pos, len, NULL, iomap);
+	if (unlikely(status)) {
+		unlock_page(page);
+		put_page(page);
+		page = NULL;
+
+		iomap_write_failed(inode, pos, len);
+	}
+
+	*pagep = page;
+	return status;
+}
+
+static int
+iomap_write_end(struct inode *inode, loff_t pos, unsigned len,
+		unsigned copied, struct page *page)
+{
+	int ret;
+
+	ret = generic_write_end(NULL, inode->i_mapping, pos, len,
+			copied, page, NULL);
+	if (ret < len)
+		iomap_write_failed(inode, pos, len);
+	return ret;
+}
+
+static loff_t
+iomap_write_actor(struct inode *inode, loff_t pos, loff_t length, void *data,
+		struct iomap *iomap)
+{
+	struct iov_iter *i = data;
+	long status = 0;
+	ssize_t written = 0;
+	unsigned int flags = AOP_FLAG_NOFS;
+
+	/*
+	 * Copies from kernel address space cannot fail (NFSD is a big user).
+	 */
+	if (!iter_is_iovec(i))
+		flags |= AOP_FLAG_UNINTERRUPTIBLE;
+
+	do {
+		struct page *page;
+		unsigned long offset;	/* Offset into pagecache page */
+		unsigned long bytes;	/* Bytes to write to page */
+		size_t copied;		/* Bytes copied from user */
+
+		offset = (pos & (PAGE_SIZE - 1));
+		bytes = min_t(unsigned long, PAGE_SIZE - offset,
+						iov_iter_count(i));
+again:
+		if (bytes > length)
+			bytes = length;
+
+		/*
+		 * Bring in the user page that we will copy from _first_.
+		 * Otherwise there's a nasty deadlock on copying from the
+		 * same page as we're writing to, without it being marked
+		 * up-to-date.
+		 *
+		 * Not only is this an optimisation, but it is also required
+		 * to check that the address is actually valid, when atomic
+		 * usercopies are used, below.
+		 */
+		if (unlikely(iov_iter_fault_in_readable(i, bytes))) {
+			status = -EFAULT;
+			break;
+		}
+
+		status = iomap_write_begin(inode, pos, bytes, flags, &page,
+				iomap);
+		if (unlikely(status))
+			break;
+
+		if (mapping_writably_mapped(inode->i_mapping))
+			flush_dcache_page(page);
+
+		pagefault_disable();
+		copied = iov_iter_copy_from_user_atomic(page, i, offset, bytes);
+		pagefault_enable();
+
+		flush_dcache_page(page);
+		mark_page_accessed(page);
+
+		status = iomap_write_end(inode, pos, bytes, copied, page);
+		if (unlikely(status < 0))
+			break;
+		copied = status;
+
+		cond_resched();
+
+		iov_iter_advance(i, copied);
+		if (unlikely(copied == 0)) {
+			/*
+			 * If we were unable to copy any data at all, we must
+			 * fall back to a single segment length write.
+			 *
+			 * If we didn't fallback here, we could livelock
+			 * because not all segments in the iov can be copied at
+			 * once without a pagefault.
+			 */
+			bytes = min_t(unsigned long, PAGE_SIZE - offset,
+						iov_iter_single_seg_count(i));
+			goto again;
+		}
+		pos += copied;
+		written += copied;
+		length -= copied;
+
+		balance_dirty_pages_ratelimited(inode->i_mapping);
+	} while (iov_iter_count(i) && length);
+
+	return written ? written : status;
+}
+
+ssize_t
+iomap_file_buffered_write(struct kiocb *iocb, struct iov_iter *iter,
+		struct iomap_ops *ops)
+{
+	struct inode *inode = iocb->ki_filp->f_mapping->host;
+	loff_t pos = iocb->ki_pos, ret = 0, written = 0;
+
+	while (iov_iter_count(iter)) {
+		ret = iomap_apply(inode, pos, iov_iter_count(iter),
+				IOMAP_WRITE, ops, iter, iomap_write_actor);
+		if (ret <= 0)
+			break;
+		pos += ret;
+		written += ret;
+	}
+
+	return written ? written : ret;
+}
+EXPORT_SYMBOL_GPL(iomap_file_buffered_write);
+
+static int iomap_zero(struct inode *inode, loff_t pos, unsigned offset,
+		unsigned bytes, struct iomap *iomap)
+{
+	struct page *page;
+	int status;
+
+	status = iomap_write_begin(inode, pos, bytes,
+			AOP_FLAG_UNINTERRUPTIBLE | AOP_FLAG_NOFS, &page, iomap);
+	if (status)
+		return status;
+
+	zero_user(page, offset, bytes);
+	mark_page_accessed(page);
+
+	return iomap_write_end(inode, pos, bytes, bytes, page);
+}
+
+static int iomap_dax_zero(loff_t pos, unsigned offset, unsigned bytes,
+		struct iomap *iomap)
+{
+	sector_t sector = iomap->blkno +
+		(((pos & ~(PAGE_SIZE - 1)) - iomap->offset) >> 9);
+
+	return __dax_zero_page_range(iomap->bdev, sector, offset, bytes);
+}
+
+static loff_t
+iomap_zero_range_actor(struct inode *inode, loff_t pos, loff_t count,
+		void *data, struct iomap *iomap)
+{
+	bool *did_zero = data;
+	loff_t written = 0;
+	int status;
+
+	/* already zeroed?  we're done. */
+	if (iomap->type == IOMAP_HOLE || iomap->type == IOMAP_UNWRITTEN)
+	    	return count;
+
+	do {
+		unsigned offset, bytes;
+
+		offset = pos & (PAGE_SIZE - 1); /* Within page */
+		bytes = min_t(unsigned, PAGE_SIZE - offset, count);
+
+		if (IS_DAX(inode))
+			status = iomap_dax_zero(pos, offset, bytes, iomap);
+		else
+			status = iomap_zero(inode, pos, offset, bytes, iomap);
+		if (status < 0)
+			return status;
+
+		pos += bytes;
+		count -= bytes;
+		written += bytes;
+		if (did_zero)
+			*did_zero = true;
+	} while (count > 0);
+
+	return written;
+}
+
+int
+iomap_zero_range(struct inode *inode, loff_t pos, loff_t len, bool *did_zero,
+		struct iomap_ops *ops)
+{
+	loff_t ret;
+
+	while (len > 0) {
+		ret = iomap_apply(inode, pos, len, IOMAP_ZERO,
+				ops, did_zero, iomap_zero_range_actor);
+		if (ret <= 0)
+			return ret;
+
+		pos += ret;
+		len -= ret;
+	}
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(iomap_zero_range);
+
+int
+iomap_truncate_page(struct inode *inode, loff_t pos, bool *did_zero,
+		struct iomap_ops *ops)
+{
+	unsigned blocksize = (1 << inode->i_blkbits);
+	unsigned off = pos & (blocksize - 1);
+
+	/* Block boundary? Nothing to do */
+	if (!off)
+		return 0;
+	return iomap_zero_range(inode, pos, blocksize - off, did_zero, ops);
+}
+EXPORT_SYMBOL_GPL(iomap_truncate_page);
+
+static loff_t
+iomap_page_mkwrite_actor(struct inode *inode, loff_t pos, loff_t length,
+		void *data, struct iomap *iomap)
+{
+	struct page *page = data;
+	int ret;
+
+	ret = __block_write_begin_int(page, pos & ~PAGE_MASK, length,
+			NULL, iomap);
+	if (ret)
+		return ret;
+
+	block_commit_write(page, 0, length);
+	return length;
+}
+
+int iomap_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf,
+		struct iomap_ops *ops)
+{
+	struct page *page = vmf->page;
+	struct inode *inode = file_inode(vma->vm_file);
+	unsigned long length;
+	loff_t offset, size;
+	ssize_t ret;
+
+	lock_page(page);
+	size = i_size_read(inode);
+	if ((page->mapping != inode->i_mapping) ||
+	    (page_offset(page) > size)) {
+		/* We overload EFAULT to mean page got truncated */
+		ret = -EFAULT;
+		goto out_unlock;
+	}
+
+	/* page is wholly or partially inside EOF */
+	if (((page->index + 1) << PAGE_SHIFT) > size)
+		length = size & ~PAGE_MASK;
+	else
+		length = PAGE_SIZE;
+
+	offset = page_offset(page);
+	while (length > 0) {
+		ret = iomap_apply(inode, offset, length, IOMAP_WRITE,
+				ops, page, iomap_page_mkwrite_actor);
+		if (unlikely(ret <= 0))
+			goto out_unlock;
+		offset += ret;
+		length -= ret;
+	}
+
+	set_page_dirty(page);
+	wait_for_stable_page(page);
+	return 0;
+out_unlock:
+	unlock_page(page);
+	return ret;
+}
+EXPORT_SYMBOL_GPL(iomap_page_mkwrite);
+
+struct fiemap_ctx {
+	struct fiemap_extent_info *fi;
+	struct iomap prev;
+};
+
+static int iomap_to_fiemap(struct fiemap_extent_info *fi,
+		struct iomap *iomap, u32 flags)
+{
+	switch (iomap->type) {
+	case IOMAP_HOLE:
+		/* skip holes */
+		return 0;
+	case IOMAP_DELALLOC:
+		flags |= FIEMAP_EXTENT_DELALLOC | FIEMAP_EXTENT_UNKNOWN;
+		break;
+	case IOMAP_UNWRITTEN:
+		flags |= FIEMAP_EXTENT_UNWRITTEN;
+		break;
+	case IOMAP_MAPPED:
+		break;
+	}
+
+	return fiemap_fill_next_extent(fi, iomap->offset,
+			iomap->blkno != IOMAP_NULL_BLOCK ? iomap->blkno << 9: 0,
+			iomap->length, flags | FIEMAP_EXTENT_MERGED);
+
+}
+
+static loff_t
+iomap_fiemap_actor(struct inode *inode, loff_t pos, loff_t length, void *data,
+		struct iomap *iomap)
+{
+	struct fiemap_ctx *ctx = data;
+	loff_t ret = length;
+
+	if (iomap->type == IOMAP_HOLE)
+		return length;
+
+	ret = iomap_to_fiemap(ctx->fi, &ctx->prev, 0);
+	ctx->prev = *iomap;
+	switch (ret) {
+	case 0:		/* success */
+		return length;
+	case 1:		/* extent array full */
+		return 0;
+	default:
+		return ret;
+	}
+}
+
+int iomap_fiemap(struct inode *inode, struct fiemap_extent_info *fi,
+		loff_t start, loff_t len, struct iomap_ops *ops)
+{
+	struct fiemap_ctx ctx;
+	loff_t ret;
+
+	memset(&ctx, 0, sizeof(ctx));
+	ctx.fi = fi;
+	ctx.prev.type = IOMAP_HOLE;
+
+	ret = fiemap_check_flags(fi, FIEMAP_FLAG_SYNC);
+	if (ret)
+		return ret;
+
+	ret = filemap_write_and_wait(inode->i_mapping);
+	if (ret)
+		return ret;
+
+	while (len > 0) {
+		ret = iomap_apply(inode, start, len, 0, ops, &ctx,
+				iomap_fiemap_actor);
+		if (ret < 0)
+			return ret;
+		if (ret == 0)
+			break;
+
+		start += ret;
+		len -= ret;
+	}
+
+	if (ctx.prev.type != IOMAP_HOLE) {
+		ret = iomap_to_fiemap(fi, &ctx.prev, FIEMAP_EXTENT_LAST);
+		if (ret < 0)
+			return ret;
+	}
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(iomap_fiemap);
diff --git a/fs/nfsd/blocklayout.c b/fs/nfsd/blocklayout.c
index e55b524..4df16ae 100644
--- a/fs/nfsd/blocklayout.c
+++ b/fs/nfsd/blocklayout.c
@@ -2,6 +2,7 @@
  * Copyright (c) 2014-2016 Christoph Hellwig.
  */
 #include <linux/exportfs.h>
+#include <linux/iomap.h>
 #include <linux/genhd.h>
 #include <linux/slab.h>
 #include <linux/pr.h>
diff --git a/fs/nfsd/blocklayoutxdr.c b/fs/nfsd/blocklayoutxdr.c
index 6c3b316..4ebaaf4 100644
--- a/fs/nfsd/blocklayoutxdr.c
+++ b/fs/nfsd/blocklayoutxdr.c
@@ -3,6 +3,7 @@
  */
 #include <linux/sunrpc/svc.h>
 #include <linux/exportfs.h>
+#include <linux/iomap.h>
 #include <linux/nfs4.h>
 
 #include "nfsd.h"
diff --git a/fs/xfs/Kconfig b/fs/xfs/Kconfig
index 5d47b4d..35faf12 100644
--- a/fs/xfs/Kconfig
+++ b/fs/xfs/Kconfig
@@ -4,6 +4,7 @@
 	depends on (64BIT || LBDAF)
 	select EXPORTFS
 	select LIBCRC32C
+	select FS_IOMAP
 	help
 	  XFS is a high performance journaling filesystem which originated
 	  on the SGI IRIX platform.  It is completely multi-threaded, can
diff --git a/fs/xfs/libxfs/xfs_alloc.c b/fs/xfs/libxfs/xfs_alloc.c
index a708e38..88c26b8 100644
--- a/fs/xfs/libxfs/xfs_alloc.c
+++ b/fs/xfs/libxfs/xfs_alloc.c
@@ -84,7 +84,7 @@
  * Lookup the first record less than or equal to [bno, len]
  * in the btree given by cur.
  */
-int					/* error */
+static int				/* error */
 xfs_alloc_lookup_le(
 	struct xfs_btree_cur	*cur,	/* btree cursor */
 	xfs_agblock_t		bno,	/* starting block of extent */
@@ -1839,19 +1839,8 @@
 xfs_alloc_compute_maxlevels(
 	xfs_mount_t	*mp)	/* file system mount structure */
 {
-	int		level;
-	uint		maxblocks;
-	uint		maxleafents;
-	int		minleafrecs;
-	int		minnoderecs;
-
-	maxleafents = (mp->m_sb.sb_agblocks + 1) / 2;
-	minleafrecs = mp->m_alloc_mnr[0];
-	minnoderecs = mp->m_alloc_mnr[1];
-	maxblocks = (maxleafents + minleafrecs - 1) / minleafrecs;
-	for (level = 1; maxblocks > 1; level++)
-		maxblocks = (maxblocks + minnoderecs - 1) / minnoderecs;
-	mp->m_ag_maxlevels = level;
+	mp->m_ag_maxlevels = xfs_btree_compute_maxlevels(mp, mp->m_alloc_mnr,
+			(mp->m_sb.sb_agblocks + 1) / 2);
 }
 
 /*
@@ -2658,55 +2647,79 @@
 	return error;
 }
 
-/*
- * Free an extent.
- * Just break up the extent address and hand off to xfs_free_ag_extent
- * after fixing up the freelist.
- */
-int				/* error */
-xfs_free_extent(
-	xfs_trans_t	*tp,	/* transaction pointer */
-	xfs_fsblock_t	bno,	/* starting block number of extent */
-	xfs_extlen_t	len)	/* length of extent */
+/* Ensure that the freelist is at full capacity. */
+int
+xfs_free_extent_fix_freelist(
+	struct xfs_trans	*tp,
+	xfs_agnumber_t		agno,
+	struct xfs_buf		**agbp)
 {
-	xfs_alloc_arg_t	args;
-	int		error;
+	struct xfs_alloc_arg	args;
+	int			error;
 
-	ASSERT(len != 0);
-	memset(&args, 0, sizeof(xfs_alloc_arg_t));
+	memset(&args, 0, sizeof(struct xfs_alloc_arg));
 	args.tp = tp;
 	args.mp = tp->t_mountp;
+	args.agno = agno;
 
 	/*
 	 * validate that the block number is legal - the enables us to detect
 	 * and handle a silent filesystem corruption rather than crashing.
 	 */
-	args.agno = XFS_FSB_TO_AGNO(args.mp, bno);
 	if (args.agno >= args.mp->m_sb.sb_agcount)
 		return -EFSCORRUPTED;
 
-	args.agbno = XFS_FSB_TO_AGBNO(args.mp, bno);
-	if (args.agbno >= args.mp->m_sb.sb_agblocks)
-		return -EFSCORRUPTED;
-
 	args.pag = xfs_perag_get(args.mp, args.agno);
 	ASSERT(args.pag);
 
 	error = xfs_alloc_fix_freelist(&args, XFS_ALLOC_FLAG_FREEING);
 	if (error)
-		goto error0;
+		goto out;
+
+	*agbp = args.agbp;
+out:
+	xfs_perag_put(args.pag);
+	return error;
+}
+
+/*
+ * Free an extent.
+ * Just break up the extent address and hand off to xfs_free_ag_extent
+ * after fixing up the freelist.
+ */
+int				/* error */
+xfs_free_extent(
+	struct xfs_trans	*tp,	/* transaction pointer */
+	xfs_fsblock_t		bno,	/* starting block number of extent */
+	xfs_extlen_t		len)	/* length of extent */
+{
+	struct xfs_mount	*mp = tp->t_mountp;
+	struct xfs_buf		*agbp;
+	xfs_agnumber_t		agno = XFS_FSB_TO_AGNO(mp, bno);
+	xfs_agblock_t		agbno = XFS_FSB_TO_AGBNO(mp, bno);
+	int			error;
+
+	ASSERT(len != 0);
+
+	error = xfs_free_extent_fix_freelist(tp, agno, &agbp);
+	if (error)
+		return error;
+
+	XFS_WANT_CORRUPTED_GOTO(mp, agbno < mp->m_sb.sb_agblocks, err);
 
 	/* validate the extent size is legal now we have the agf locked */
-	if (args.agbno + len >
-			be32_to_cpu(XFS_BUF_TO_AGF(args.agbp)->agf_length)) {
-		error = -EFSCORRUPTED;
-		goto error0;
-	}
+	XFS_WANT_CORRUPTED_GOTO(mp,
+		agbno + len <= be32_to_cpu(XFS_BUF_TO_AGF(agbp)->agf_length),
+				err);
 
-	error = xfs_free_ag_extent(tp, args.agbp, args.agno, args.agbno, len, 0);
-	if (!error)
-		xfs_extent_busy_insert(tp, args.agno, args.agbno, len, 0);
-error0:
-	xfs_perag_put(args.pag);
+	error = xfs_free_ag_extent(tp, agbp, agno, agbno, len, 0);
+	if (error)
+		goto err;
+
+	xfs_extent_busy_insert(tp, agno, agbno, len, 0);
+	return 0;
+
+err:
+	xfs_trans_brelse(tp, agbp);
 	return error;
 }
diff --git a/fs/xfs/libxfs/xfs_alloc.h b/fs/xfs/libxfs/xfs_alloc.h
index 135eb3d..cf268b2 100644
--- a/fs/xfs/libxfs/xfs_alloc.h
+++ b/fs/xfs/libxfs/xfs_alloc.h
@@ -212,13 +212,6 @@
 	xfs_fsblock_t	bno,	/* starting block number of extent */
 	xfs_extlen_t	len);	/* length of extent */
 
-int					/* error */
-xfs_alloc_lookup_le(
-	struct xfs_btree_cur	*cur,	/* btree cursor */
-	xfs_agblock_t		bno,	/* starting block of extent */
-	xfs_extlen_t		len,	/* length of extent */
-	int			*stat);	/* success/failure */
-
 int				/* error */
 xfs_alloc_lookup_ge(
 	struct xfs_btree_cur	*cur,	/* btree cursor */
@@ -236,5 +229,7 @@
 int xfs_read_agf(struct xfs_mount *mp, struct xfs_trans *tp,
 			xfs_agnumber_t agno, int flags, struct xfs_buf **bpp);
 int xfs_alloc_fix_freelist(struct xfs_alloc_arg *args, int flags);
+int xfs_free_extent_fix_freelist(struct xfs_trans *tp, xfs_agnumber_t agno,
+		struct xfs_buf **agbp);
 
 #endif	/* __XFS_ALLOC_H__ */
diff --git a/fs/xfs/libxfs/xfs_attr_leaf.h b/fs/xfs/libxfs/xfs_attr_leaf.h
index 882c8d3..4f2aed0 100644
--- a/fs/xfs/libxfs/xfs_attr_leaf.h
+++ b/fs/xfs/libxfs/xfs_attr_leaf.h
@@ -50,7 +50,6 @@
 int	xfs_attr_shortform_getvalue(struct xfs_da_args *args);
 int	xfs_attr_shortform_to_leaf(struct xfs_da_args *args);
 int	xfs_attr_shortform_remove(struct xfs_da_args *args);
-int	xfs_attr_shortform_list(struct xfs_attr_list_context *context);
 int	xfs_attr_shortform_allfit(struct xfs_buf *bp, struct xfs_inode *dp);
 int	xfs_attr_shortform_bytesfit(xfs_inode_t *dp, int bytes);
 void	xfs_attr_fork_remove(struct xfs_inode *ip, struct xfs_trans *tp);
@@ -88,8 +87,6 @@
 void	xfs_attr3_leaf_unbalance(struct xfs_da_state *state,
 				       struct xfs_da_state_blk *drop_blk,
 				       struct xfs_da_state_blk *save_blk);
-int	xfs_attr3_root_inactive(struct xfs_trans **trans, struct xfs_inode *dp);
-
 /*
  * Utility routines.
  */
diff --git a/fs/xfs/libxfs/xfs_bmap.c b/fs/xfs/libxfs/xfs_bmap.c
index 932381c..2f2c85c 100644
--- a/fs/xfs/libxfs/xfs_bmap.c
+++ b/fs/xfs/libxfs/xfs_bmap.c
@@ -570,14 +570,12 @@
  */
 void
 xfs_bmap_add_free(
+	struct xfs_mount	*mp,		/* mount point structure */
+	struct xfs_bmap_free	*flist,		/* list of extents */
 	xfs_fsblock_t		bno,		/* fs block number of extent */
-	xfs_filblks_t		len,		/* length of extent */
-	xfs_bmap_free_t		*flist,		/* list of extents */
-	xfs_mount_t		*mp)		/* mount point structure */
+	xfs_filblks_t		len)		/* length of extent */
 {
-	xfs_bmap_free_item_t	*cur;		/* current (next) element */
-	xfs_bmap_free_item_t	*new;		/* new element */
-	xfs_bmap_free_item_t	*prev;		/* previous element */
+	struct xfs_bmap_free_item	*new;		/* new element */
 #ifdef DEBUG
 	xfs_agnumber_t		agno;
 	xfs_agblock_t		agbno;
@@ -597,17 +595,7 @@
 	new = kmem_zone_alloc(xfs_bmap_free_item_zone, KM_SLEEP);
 	new->xbfi_startblock = bno;
 	new->xbfi_blockcount = (xfs_extlen_t)len;
-	for (prev = NULL, cur = flist->xbf_first;
-	     cur != NULL;
-	     prev = cur, cur = cur->xbfi_next) {
-		if (cur->xbfi_startblock >= bno)
-			break;
-	}
-	if (prev)
-		prev->xbfi_next = new;
-	else
-		flist->xbf_first = new;
-	new->xbfi_next = cur;
+	list_add(&new->xbfi_list, &flist->xbf_flist);
 	flist->xbf_count++;
 }
 
@@ -617,14 +605,10 @@
  */
 void
 xfs_bmap_del_free(
-	xfs_bmap_free_t		*flist,	/* free item list header */
-	xfs_bmap_free_item_t	*prev,	/* previous item on list, if any */
-	xfs_bmap_free_item_t	*free)	/* list item to be freed */
+	struct xfs_bmap_free		*flist,	/* free item list header */
+	struct xfs_bmap_free_item	*free)	/* list item to be freed */
 {
-	if (prev)
-		prev->xbfi_next = free->xbfi_next;
-	else
-		flist->xbf_first = free->xbfi_next;
+	list_del(&free->xbfi_list);
 	flist->xbf_count--;
 	kmem_zone_free(xfs_bmap_free_item_zone, free);
 }
@@ -634,17 +618,16 @@
  */
 void
 xfs_bmap_cancel(
-	xfs_bmap_free_t		*flist)	/* list of bmap_free_items */
+	struct xfs_bmap_free		*flist)	/* list of bmap_free_items */
 {
-	xfs_bmap_free_item_t	*free;	/* free list item */
-	xfs_bmap_free_item_t	*next;
+	struct xfs_bmap_free_item	*free;	/* free list item */
 
 	if (flist->xbf_count == 0)
 		return;
-	ASSERT(flist->xbf_first != NULL);
-	for (free = flist->xbf_first; free; free = next) {
-		next = free->xbfi_next;
-		xfs_bmap_del_free(flist, NULL, free);
+	while (!list_empty(&flist->xbf_flist)) {
+		free = list_first_entry(&flist->xbf_flist,
+				struct xfs_bmap_free_item, xbfi_list);
+		xfs_bmap_del_free(flist, free);
 	}
 	ASSERT(flist->xbf_count == 0);
 }
@@ -699,7 +682,7 @@
 	cblock = XFS_BUF_TO_BLOCK(cbp);
 	if ((error = xfs_btree_check_block(cur, cblock, 0, cbp)))
 		return error;
-	xfs_bmap_add_free(cbno, 1, cur->bc_private.b.flist, mp);
+	xfs_bmap_add_free(mp, cur->bc_private.b.flist, cbno, 1);
 	ip->i_d.di_nblocks--;
 	xfs_trans_mod_dquot_byino(tp, ip, XFS_TRANS_DQ_BCOUNT, -1L);
 	xfs_trans_binval(tp, cbp);
@@ -5073,8 +5056,8 @@
 	 * If we need to, add to list of extents to delete.
 	 */
 	if (do_fx)
-		xfs_bmap_add_free(del->br_startblock, del->br_blockcount, flist,
-			mp);
+		xfs_bmap_add_free(mp, flist, del->br_startblock,
+			del->br_blockcount);
 	/*
 	 * Adjust inode # blocks in the file.
 	 */
diff --git a/fs/xfs/libxfs/xfs_bmap.h b/fs/xfs/libxfs/xfs_bmap.h
index 423a34e..f1f3ae6 100644
--- a/fs/xfs/libxfs/xfs_bmap.h
+++ b/fs/xfs/libxfs/xfs_bmap.h
@@ -62,12 +62,12 @@
  * List of extents to be free "later".
  * The list is kept sorted on xbf_startblock.
  */
-typedef struct xfs_bmap_free_item
+struct xfs_bmap_free_item
 {
 	xfs_fsblock_t		xbfi_startblock;/* starting fs block number */
 	xfs_extlen_t		xbfi_blockcount;/* number of blocks in extent */
-	struct xfs_bmap_free_item *xbfi_next;	/* link to next entry */
-} xfs_bmap_free_item_t;
+	struct list_head	xbfi_list;
+};
 
 /*
  * Header for free extent list.
@@ -85,7 +85,7 @@
  */
 typedef	struct xfs_bmap_free
 {
-	xfs_bmap_free_item_t	*xbf_first;	/* list of to-be-free extents */
+	struct list_head	xbf_flist;	/* list of to-be-free extents */
 	int			xbf_count;	/* count of items on list */
 	int			xbf_low;	/* alloc in low mode */
 } xfs_bmap_free_t;
@@ -141,8 +141,10 @@
 
 static inline void xfs_bmap_init(xfs_bmap_free_t *flp, xfs_fsblock_t *fbp)
 {
-	((flp)->xbf_first = NULL, (flp)->xbf_count = 0, \
-		(flp)->xbf_low = 0, *(fbp) = NULLFSBLOCK);
+	INIT_LIST_HEAD(&flp->xbf_flist);
+	flp->xbf_count = 0;
+	flp->xbf_low = 0;
+	*fbp = NULLFSBLOCK;
 }
 
 /*
@@ -191,8 +193,8 @@
 
 int	xfs_bmap_add_attrfork(struct xfs_inode *ip, int size, int rsvd);
 void	xfs_bmap_local_to_extents_empty(struct xfs_inode *ip, int whichfork);
-void	xfs_bmap_add_free(xfs_fsblock_t bno, xfs_filblks_t len,
-		struct xfs_bmap_free *flist, struct xfs_mount *mp);
+void	xfs_bmap_add_free(struct xfs_mount *mp, struct xfs_bmap_free *flist,
+			  xfs_fsblock_t bno, xfs_filblks_t len);
 void	xfs_bmap_cancel(struct xfs_bmap_free *flist);
 int	xfs_bmap_finish(struct xfs_trans **tp, struct xfs_bmap_free *flist,
 			struct xfs_inode *ip);
diff --git a/fs/xfs/libxfs/xfs_bmap_btree.c b/fs/xfs/libxfs/xfs_bmap_btree.c
index 6282f6e..db0c71e 100644
--- a/fs/xfs/libxfs/xfs_bmap_btree.c
+++ b/fs/xfs/libxfs/xfs_bmap_btree.c
@@ -526,7 +526,7 @@
 	struct xfs_trans	*tp = cur->bc_tp;
 	xfs_fsblock_t		fsbno = XFS_DADDR_TO_FSB(mp, XFS_BUF_ADDR(bp));
 
-	xfs_bmap_add_free(fsbno, 1, cur->bc_private.b.flist, mp);
+	xfs_bmap_add_free(mp, cur->bc_private.b.flist, fsbno, 1);
 	ip->i_d.di_nblocks--;
 
 	xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE);
diff --git a/fs/xfs/libxfs/xfs_btree.c b/fs/xfs/libxfs/xfs_btree.c
index 1f88e1c..07eeb0b 100644
--- a/fs/xfs/libxfs/xfs_btree.c
+++ b/fs/xfs/libxfs/xfs_btree.c
@@ -543,12 +543,12 @@
  */
 STATIC struct xfs_btree_block *
 xfs_btree_get_iroot(
-       struct xfs_btree_cur    *cur)
+	struct xfs_btree_cur	*cur)
 {
-       struct xfs_ifork        *ifp;
+	struct xfs_ifork	*ifp;
 
-       ifp = XFS_IFORK_PTR(cur->bc_private.b.ip, cur->bc_private.b.whichfork);
-       return (struct xfs_btree_block *)ifp->if_broot;
+	ifp = XFS_IFORK_PTR(cur->bc_private.b.ip, cur->bc_private.b.whichfork);
+	return (struct xfs_btree_block *)ifp->if_broot;
 }
 
 /*
@@ -4152,3 +4152,22 @@
 
 	return true;
 }
+
+/*
+ * Calculate the number of btree levels needed to store a given number of
+ * records in a short-format btree.
+ */
+uint
+xfs_btree_compute_maxlevels(
+	struct xfs_mount	*mp,
+	uint			*limits,
+	unsigned long		len)
+{
+	uint			level;
+	unsigned long		maxblocks;
+
+	maxblocks = (len + limits[0] - 1) / limits[0];
+	for (level = 1; maxblocks > 1; level++)
+		maxblocks = (maxblocks + limits[1] - 1) / limits[1];
+	return level;
+}
diff --git a/fs/xfs/libxfs/xfs_btree.h b/fs/xfs/libxfs/xfs_btree.h
index 2e874be..785a996 100644
--- a/fs/xfs/libxfs/xfs_btree.h
+++ b/fs/xfs/libxfs/xfs_btree.h
@@ -474,5 +474,7 @@
 
 bool xfs_btree_sblock_v5hdr_verify(struct xfs_buf *bp);
 bool xfs_btree_sblock_verify(struct xfs_buf *bp, unsigned int max_recs);
+uint xfs_btree_compute_maxlevels(struct xfs_mount *mp, uint *limits,
+				 unsigned long len);
 
 #endif	/* __XFS_BTREE_H__ */
diff --git a/fs/xfs/libxfs/xfs_format.h b/fs/xfs/libxfs/xfs_format.h
index dc97eb21..adb204d 100644
--- a/fs/xfs/libxfs/xfs_format.h
+++ b/fs/xfs/libxfs/xfs_format.h
@@ -1435,41 +1435,57 @@
  * with the crc feature bit, and all accesses to them must be conditional on
  * that flag.
  */
+/* short form block header */
+struct xfs_btree_block_shdr {
+	__be32		bb_leftsib;
+	__be32		bb_rightsib;
+
+	__be64		bb_blkno;
+	__be64		bb_lsn;
+	uuid_t		bb_uuid;
+	__be32		bb_owner;
+	__le32		bb_crc;
+};
+
+/* long form block header */
+struct xfs_btree_block_lhdr {
+	__be64		bb_leftsib;
+	__be64		bb_rightsib;
+
+	__be64		bb_blkno;
+	__be64		bb_lsn;
+	uuid_t		bb_uuid;
+	__be64		bb_owner;
+	__le32		bb_crc;
+	__be32		bb_pad; /* padding for alignment */
+};
+
 struct xfs_btree_block {
 	__be32		bb_magic;	/* magic number for block type */
 	__be16		bb_level;	/* 0 is a leaf */
 	__be16		bb_numrecs;	/* current # of data records */
 	union {
-		struct {
-			__be32		bb_leftsib;
-			__be32		bb_rightsib;
-
-			__be64		bb_blkno;
-			__be64		bb_lsn;
-			uuid_t		bb_uuid;
-			__be32		bb_owner;
-			__le32		bb_crc;
-		} s;			/* short form pointers */
-		struct	{
-			__be64		bb_leftsib;
-			__be64		bb_rightsib;
-
-			__be64		bb_blkno;
-			__be64		bb_lsn;
-			uuid_t		bb_uuid;
-			__be64		bb_owner;
-			__le32		bb_crc;
-			__be32		bb_pad; /* padding for alignment */
-		} l;			/* long form pointers */
+		struct xfs_btree_block_shdr s;
+		struct xfs_btree_block_lhdr l;
 	} bb_u;				/* rest */
 };
 
-#define XFS_BTREE_SBLOCK_LEN	16	/* size of a short form block */
-#define XFS_BTREE_LBLOCK_LEN	24	/* size of a long form block */
+/* size of a short form block */
+#define XFS_BTREE_SBLOCK_LEN \
+	(offsetof(struct xfs_btree_block, bb_u) + \
+	 offsetof(struct xfs_btree_block_shdr, bb_blkno))
+/* size of a long form block */
+#define XFS_BTREE_LBLOCK_LEN \
+	(offsetof(struct xfs_btree_block, bb_u) + \
+	 offsetof(struct xfs_btree_block_lhdr, bb_blkno))
 
 /* sizes of CRC enabled btree blocks */
-#define XFS_BTREE_SBLOCK_CRC_LEN	(XFS_BTREE_SBLOCK_LEN + 40)
-#define XFS_BTREE_LBLOCK_CRC_LEN	(XFS_BTREE_LBLOCK_LEN + 48)
+#define XFS_BTREE_SBLOCK_CRC_LEN \
+	(offsetof(struct xfs_btree_block, bb_u) + \
+	 sizeof(struct xfs_btree_block_shdr))
+#define XFS_BTREE_LBLOCK_CRC_LEN \
+	(offsetof(struct xfs_btree_block, bb_u) + \
+	 sizeof(struct xfs_btree_block_lhdr))
 
 #define XFS_BTREE_SBLOCK_CRC_OFF \
 	offsetof(struct xfs_btree_block, bb_u.s.bb_crc)
diff --git a/fs/xfs/libxfs/xfs_fs.h b/fs/xfs/libxfs/xfs_fs.h
index fffe3d0..f5ec9c5 100644
--- a/fs/xfs/libxfs/xfs_fs.h
+++ b/fs/xfs/libxfs/xfs_fs.h
@@ -521,12 +521,8 @@
 #define XFS_IOC_ERROR_CLEARALL	     _IOW ('X', 117, struct xfs_error_injection)
 /*	XFS_IOC_ATTRCTL_BY_HANDLE -- deprecated 118	 */
 
-/*	XFS_IOC_FREEZE		  -- FIFREEZE   119	 */
-/*	XFS_IOC_THAW		  -- FITHAW     120	 */
-#ifndef FIFREEZE
-#define XFS_IOC_FREEZE		     _IOWR('X', 119, int)
-#define XFS_IOC_THAW		     _IOWR('X', 120, int)
-#endif
+#define XFS_IOC_FREEZE		     _IOWR('X', 119, int)	/* aka FIFREEZE */
+#define XFS_IOC_THAW		     _IOWR('X', 120, int)	/* aka FITHAW */
 
 #define XFS_IOC_FSSETDM_BY_HANDLE    _IOW ('X', 121, struct xfs_fsop_setdm_handlereq)
 #define XFS_IOC_ATTRLIST_BY_HANDLE   _IOW ('X', 122, struct xfs_fsop_attrlist_handlereq)
diff --git a/fs/xfs/libxfs/xfs_ialloc.c b/fs/xfs/libxfs/xfs_ialloc.c
index 22297f9..4b1e408 100644
--- a/fs/xfs/libxfs/xfs_ialloc.c
+++ b/fs/xfs/libxfs/xfs_ialloc.c
@@ -1828,9 +1828,8 @@
 
 	if (!xfs_inobt_issparse(rec->ir_holemask)) {
 		/* not sparse, calculate extent info directly */
-		xfs_bmap_add_free(XFS_AGB_TO_FSB(mp, agno,
-				  XFS_AGINO_TO_AGBNO(mp, rec->ir_startino)),
-				  mp->m_ialloc_blks, flist, mp);
+		xfs_bmap_add_free(mp, flist, XFS_AGB_TO_FSB(mp, agno, sagbno),
+				  mp->m_ialloc_blks);
 		return;
 	}
 
@@ -1873,8 +1872,8 @@
 
 		ASSERT(agbno % mp->m_sb.sb_spino_align == 0);
 		ASSERT(contigblk % mp->m_sb.sb_spino_align == 0);
-		xfs_bmap_add_free(XFS_AGB_TO_FSB(mp, agno, agbno), contigblk,
-				  flist, mp);
+		xfs_bmap_add_free(mp, flist, XFS_AGB_TO_FSB(mp, agno, agbno),
+				  contigblk);
 
 		/* reset range to current bit and carry on... */
 		startidx = endidx = nextbit;
@@ -2395,20 +2394,11 @@
 xfs_ialloc_compute_maxlevels(
 	xfs_mount_t	*mp)		/* file system mount structure */
 {
-	int		level;
-	uint		maxblocks;
-	uint		maxleafents;
-	int		minleafrecs;
-	int		minnoderecs;
+	uint		inodes;
 
-	maxleafents = (1LL << XFS_INO_AGINO_BITS(mp)) >>
-		XFS_INODES_PER_CHUNK_LOG;
-	minleafrecs = mp->m_inobt_mnr[0];
-	minnoderecs = mp->m_inobt_mnr[1];
-	maxblocks = (maxleafents + minleafrecs - 1) / minleafrecs;
-	for (level = 1; maxblocks > 1; level++)
-		maxblocks = (maxblocks + minnoderecs - 1) / minnoderecs;
-	mp->m_in_maxlevels = level;
+	inodes = (1LL << XFS_INO_AGINO_BITS(mp)) >> XFS_INODES_PER_CHUNK_LOG;
+	mp->m_in_maxlevels = xfs_btree_compute_maxlevels(mp, mp->m_inobt_mnr,
+							 inodes);
 }
 
 /*
diff --git a/fs/xfs/libxfs/xfs_rtbitmap.c b/fs/xfs/libxfs/xfs_rtbitmap.c
index 951c044..e2e1106 100644
--- a/fs/xfs/libxfs/xfs_rtbitmap.c
+++ b/fs/xfs/libxfs/xfs_rtbitmap.c
@@ -70,7 +70,7 @@
  * Get a buffer for the bitmap or summary file block specified.
  * The buffer is returned read and locked.
  */
-int
+static int
 xfs_rtbuf_get(
 	xfs_mount_t	*mp,		/* file system mount structure */
 	xfs_trans_t	*tp,		/* transaction pointer */
diff --git a/fs/xfs/xfs_aops.c b/fs/xfs/xfs_aops.c
index 4c463b9..80714eb 100644
--- a/fs/xfs/xfs_aops.c
+++ b/fs/xfs/xfs_aops.c
@@ -1143,6 +1143,8 @@
 	ssize_t			size;
 	int			new = 0;
 
+	BUG_ON(create && !direct);
+
 	if (XFS_FORCED_SHUTDOWN(mp))
 		return -EIO;
 
@@ -1150,22 +1152,14 @@
 	ASSERT(bh_result->b_size >= (1 << inode->i_blkbits));
 	size = bh_result->b_size;
 
-	if (!create && direct && offset >= i_size_read(inode))
+	if (!create && offset >= i_size_read(inode))
 		return 0;
 
 	/*
 	 * Direct I/O is usually done on preallocated files, so try getting
-	 * a block mapping without an exclusive lock first.  For buffered
-	 * writes we already have the exclusive iolock anyway, so avoiding
-	 * a lock roundtrip here by taking the ilock exclusive from the
-	 * beginning is a useful micro optimization.
+	 * a block mapping without an exclusive lock first.
 	 */
-	if (create && !direct) {
-		lockmode = XFS_ILOCK_EXCL;
-		xfs_ilock(ip, lockmode);
-	} else {
-		lockmode = xfs_ilock_data_map_shared(ip);
-	}
+	lockmode = xfs_ilock_data_map_shared(ip);
 
 	ASSERT(offset <= mp->m_super->s_maxbytes);
 	if (offset + size > mp->m_super->s_maxbytes)
@@ -1184,37 +1178,19 @@
 	     (imap.br_startblock == HOLESTARTBLOCK ||
 	      imap.br_startblock == DELAYSTARTBLOCK) ||
 	     (IS_DAX(inode) && ISUNWRITTEN(&imap)))) {
-		if (direct || xfs_get_extsz_hint(ip)) {
-			/*
-			 * xfs_iomap_write_direct() expects the shared lock. It
-			 * is unlocked on return.
-			 */
-			if (lockmode == XFS_ILOCK_EXCL)
-				xfs_ilock_demote(ip, lockmode);
+		/*
+		 * xfs_iomap_write_direct() expects the shared lock. It
+		 * is unlocked on return.
+		 */
+		if (lockmode == XFS_ILOCK_EXCL)
+			xfs_ilock_demote(ip, lockmode);
 
-			error = xfs_iomap_write_direct(ip, offset, size,
-						       &imap, nimaps);
-			if (error)
-				return error;
-			new = 1;
+		error = xfs_iomap_write_direct(ip, offset, size,
+					       &imap, nimaps);
+		if (error)
+			return error;
+		new = 1;
 
-		} else {
-			/*
-			 * Delalloc reservations do not require a transaction,
-			 * we can go on without dropping the lock here. If we
-			 * are allocating a new delalloc block, make sure that
-			 * we set the new flag so that we mark the buffer new so
-			 * that we know that it is newly allocated if the write
-			 * fails.
-			 */
-			if (nimaps && imap.br_startblock == HOLESTARTBLOCK)
-				new = 1;
-			error = xfs_iomap_write_delay(ip, offset, size, &imap);
-			if (error)
-				goto out_unlock;
-
-			xfs_iunlock(ip, lockmode);
-		}
 		trace_xfs_get_blocks_alloc(ip, offset, size,
 				ISUNWRITTEN(&imap) ? XFS_IO_UNWRITTEN
 						   : XFS_IO_DELALLOC, &imap);
@@ -1235,9 +1211,7 @@
 	}
 
 	/* trim mapping down to size requested */
-	if (direct || size > (1 << inode->i_blkbits))
-		xfs_map_trim_size(inode, iblock, bh_result,
-				  &imap, offset, size);
+	xfs_map_trim_size(inode, iblock, bh_result, &imap, offset, size);
 
 	/*
 	 * For unwritten extents do not report a disk address in the buffered
@@ -1250,7 +1224,7 @@
 		if (ISUNWRITTEN(&imap))
 			set_buffer_unwritten(bh_result);
 		/* direct IO needs special help */
-		if (create && direct) {
+		if (create) {
 			if (dax_fault)
 				ASSERT(!ISUNWRITTEN(&imap));
 			else
@@ -1279,14 +1253,7 @@
 	     (new || ISUNWRITTEN(&imap))))
 		set_buffer_new(bh_result);
 
-	if (imap.br_startblock == DELAYSTARTBLOCK) {
-		BUG_ON(direct);
-		if (create) {
-			set_buffer_uptodate(bh_result);
-			set_buffer_mapped(bh_result);
-			set_buffer_delay(bh_result);
-		}
-	}
+	BUG_ON(direct && imap.br_startblock == DELAYSTARTBLOCK);
 
 	return 0;
 
@@ -1427,216 +1394,6 @@
 			xfs_get_blocks_direct, endio, NULL, flags);
 }
 
-/*
- * Punch out the delalloc blocks we have already allocated.
- *
- * Don't bother with xfs_setattr given that nothing can have made it to disk yet
- * as the page is still locked at this point.
- */
-STATIC void
-xfs_vm_kill_delalloc_range(
-	struct inode		*inode,
-	loff_t			start,
-	loff_t			end)
-{
-	struct xfs_inode	*ip = XFS_I(inode);
-	xfs_fileoff_t		start_fsb;
-	xfs_fileoff_t		end_fsb;
-	int			error;
-
-	start_fsb = XFS_B_TO_FSB(ip->i_mount, start);
-	end_fsb = XFS_B_TO_FSB(ip->i_mount, end);
-	if (end_fsb <= start_fsb)
-		return;
-
-	xfs_ilock(ip, XFS_ILOCK_EXCL);
-	error = xfs_bmap_punch_delalloc_range(ip, start_fsb,
-						end_fsb - start_fsb);
-	if (error) {
-		/* something screwed, just bail */
-		if (!XFS_FORCED_SHUTDOWN(ip->i_mount)) {
-			xfs_alert(ip->i_mount,
-		"xfs_vm_write_failed: unable to clean up ino %lld",
-					ip->i_ino);
-		}
-	}
-	xfs_iunlock(ip, XFS_ILOCK_EXCL);
-}
-
-STATIC void
-xfs_vm_write_failed(
-	struct inode		*inode,
-	struct page		*page,
-	loff_t			pos,
-	unsigned		len)
-{
-	loff_t			block_offset;
-	loff_t			block_start;
-	loff_t			block_end;
-	loff_t			from = pos & (PAGE_SIZE - 1);
-	loff_t			to = from + len;
-	struct buffer_head	*bh, *head;
-	struct xfs_mount	*mp = XFS_I(inode)->i_mount;
-
-	/*
-	 * The request pos offset might be 32 or 64 bit, this is all fine
-	 * on 64-bit platform.  However, for 64-bit pos request on 32-bit
-	 * platform, the high 32-bit will be masked off if we evaluate the
-	 * block_offset via (pos & PAGE_MASK) because the PAGE_MASK is
-	 * 0xfffff000 as an unsigned long, hence the result is incorrect
-	 * which could cause the following ASSERT failed in most cases.
-	 * In order to avoid this, we can evaluate the block_offset of the
-	 * start of the page by using shifts rather than masks the mismatch
-	 * problem.
-	 */
-	block_offset = (pos >> PAGE_SHIFT) << PAGE_SHIFT;
-
-	ASSERT(block_offset + from == pos);
-
-	head = page_buffers(page);
-	block_start = 0;
-	for (bh = head; bh != head || !block_start;
-	     bh = bh->b_this_page, block_start = block_end,
-				   block_offset += bh->b_size) {
-		block_end = block_start + bh->b_size;
-
-		/* skip buffers before the write */
-		if (block_end <= from)
-			continue;
-
-		/* if the buffer is after the write, we're done */
-		if (block_start >= to)
-			break;
-
-		/*
-		 * Process delalloc and unwritten buffers beyond EOF. We can
-		 * encounter unwritten buffers in the event that a file has
-		 * post-EOF unwritten extents and an extending write happens to
-		 * fail (e.g., an unaligned write that also involves a delalloc
-		 * to the same page).
-		 */
-		if (!buffer_delay(bh) && !buffer_unwritten(bh))
-			continue;
-
-		if (!xfs_mp_fail_writes(mp) && !buffer_new(bh) &&
-		    block_offset < i_size_read(inode))
-			continue;
-
-		if (buffer_delay(bh))
-			xfs_vm_kill_delalloc_range(inode, block_offset,
-						   block_offset + bh->b_size);
-
-		/*
-		 * This buffer does not contain data anymore. make sure anyone
-		 * who finds it knows that for certain.
-		 */
-		clear_buffer_delay(bh);
-		clear_buffer_uptodate(bh);
-		clear_buffer_mapped(bh);
-		clear_buffer_new(bh);
-		clear_buffer_dirty(bh);
-		clear_buffer_unwritten(bh);
-	}
-
-}
-
-/*
- * This used to call block_write_begin(), but it unlocks and releases the page
- * on error, and we need that page to be able to punch stale delalloc blocks out
- * on failure. hence we copy-n-waste it here and call xfs_vm_write_failed() at
- * the appropriate point.
- */
-STATIC int
-xfs_vm_write_begin(
-	struct file		*file,
-	struct address_space	*mapping,
-	loff_t			pos,
-	unsigned		len,
-	unsigned		flags,
-	struct page		**pagep,
-	void			**fsdata)
-{
-	pgoff_t			index = pos >> PAGE_SHIFT;
-	struct page		*page;
-	int			status;
-	struct xfs_mount	*mp = XFS_I(mapping->host)->i_mount;
-
-	ASSERT(len <= PAGE_SIZE);
-
-	page = grab_cache_page_write_begin(mapping, index, flags);
-	if (!page)
-		return -ENOMEM;
-
-	status = __block_write_begin(page, pos, len, xfs_get_blocks);
-	if (xfs_mp_fail_writes(mp))
-		status = -EIO;
-	if (unlikely(status)) {
-		struct inode	*inode = mapping->host;
-		size_t		isize = i_size_read(inode);
-
-		xfs_vm_write_failed(inode, page, pos, len);
-		unlock_page(page);
-
-		/*
-		 * If the write is beyond EOF, we only want to kill blocks
-		 * allocated in this write, not blocks that were previously
-		 * written successfully.
-		 */
-		if (xfs_mp_fail_writes(mp))
-			isize = 0;
-		if (pos + len > isize) {
-			ssize_t start = max_t(ssize_t, pos, isize);
-
-			truncate_pagecache_range(inode, start, pos + len);
-		}
-
-		put_page(page);
-		page = NULL;
-	}
-
-	*pagep = page;
-	return status;
-}
-
-/*
- * On failure, we only need to kill delalloc blocks beyond EOF in the range of
- * this specific write because they will never be written. Previous writes
- * beyond EOF where block allocation succeeded do not need to be trashed, so
- * only new blocks from this write should be trashed. For blocks within
- * EOF, generic_write_end() zeros them so they are safe to leave alone and be
- * written with all the other valid data.
- */
-STATIC int
-xfs_vm_write_end(
-	struct file		*file,
-	struct address_space	*mapping,
-	loff_t			pos,
-	unsigned		len,
-	unsigned		copied,
-	struct page		*page,
-	void			*fsdata)
-{
-	int			ret;
-
-	ASSERT(len <= PAGE_SIZE);
-
-	ret = generic_write_end(file, mapping, pos, len, copied, page, fsdata);
-	if (unlikely(ret < len)) {
-		struct inode	*inode = mapping->host;
-		size_t		isize = i_size_read(inode);
-		loff_t		to = pos + len;
-
-		if (to > isize) {
-			/* only kill blocks in this write beyond EOF */
-			if (pos > isize)
-				isize = pos;
-			xfs_vm_kill_delalloc_range(inode, isize, to);
-			truncate_pagecache_range(inode, isize, to);
-		}
-	}
-	return ret;
-}
-
 STATIC sector_t
 xfs_vm_bmap(
 	struct address_space	*mapping,
@@ -1747,8 +1504,6 @@
 	.set_page_dirty		= xfs_vm_set_page_dirty,
 	.releasepage		= xfs_vm_releasepage,
 	.invalidatepage		= xfs_vm_invalidatepage,
-	.write_begin		= xfs_vm_write_begin,
-	.write_end		= xfs_vm_write_end,
 	.bmap			= xfs_vm_bmap,
 	.direct_IO		= xfs_vm_direct_IO,
 	.migratepage		= buffer_migrate_page,
diff --git a/fs/xfs/xfs_attr_inactive.c b/fs/xfs/xfs_attr_inactive.c
index 55d2149..be0b79d 100644
--- a/fs/xfs/xfs_attr_inactive.c
+++ b/fs/xfs/xfs_attr_inactive.c
@@ -322,7 +322,7 @@
  * Recurse (gasp!) through the attribute nodes until we find leaves.
  * We're doing a depth-first traversal in order to invalidate everything.
  */
-int
+static int
 xfs_attr3_root_inactive(
 	struct xfs_trans	**trans,
 	struct xfs_inode	*dp)
diff --git a/fs/xfs/xfs_attr_list.c b/fs/xfs/xfs_attr_list.c
index d25f26b..25e76cd 100644
--- a/fs/xfs/xfs_attr_list.c
+++ b/fs/xfs/xfs_attr_list.c
@@ -65,7 +65,7 @@
  * we have to calculate each entries' hashvalue and sort them before
  * we can begin returning them to the user.
  */
-int
+static int
 xfs_attr_shortform_list(xfs_attr_list_context_t *context)
 {
 	attrlist_cursor_kern_t *cursor;
diff --git a/fs/xfs/xfs_bmap_util.c b/fs/xfs/xfs_bmap_util.c
index 586bb64..cd4a850 100644
--- a/fs/xfs/xfs_bmap_util.c
+++ b/fs/xfs/xfs_bmap_util.c
@@ -79,6 +79,23 @@
 		GFP_NOFS, true);
 }
 
+/* Sort bmap items by AG. */
+static int
+xfs_bmap_free_list_cmp(
+	void			*priv,
+	struct list_head	*a,
+	struct list_head	*b)
+{
+	struct xfs_mount	*mp = priv;
+	struct xfs_bmap_free_item	*ra;
+	struct xfs_bmap_free_item	*rb;
+
+	ra = container_of(a, struct xfs_bmap_free_item, xbfi_list);
+	rb = container_of(b, struct xfs_bmap_free_item, xbfi_list);
+	return  XFS_FSB_TO_AGNO(mp, ra->xbfi_startblock) -
+		XFS_FSB_TO_AGNO(mp, rb->xbfi_startblock);
+}
+
 /*
  * Routine to be called at transaction's end by xfs_bmapi, xfs_bunmapi
  * caller.  Frees all the extents that need freeing, which must be done
@@ -99,14 +116,15 @@
 	int				error;	/* error return value */
 	int				committed;/* xact committed or not */
 	struct xfs_bmap_free_item	*free;	/* free extent item */
-	struct xfs_bmap_free_item	*next;	/* next item on free list */
 
 	ASSERT((*tp)->t_flags & XFS_TRANS_PERM_LOG_RES);
 	if (flist->xbf_count == 0)
 		return 0;
 
+	list_sort((*tp)->t_mountp, &flist->xbf_flist, xfs_bmap_free_list_cmp);
+
 	efi = xfs_trans_get_efi(*tp, flist->xbf_count);
-	for (free = flist->xbf_first; free; free = free->xbfi_next)
+	list_for_each_entry(free, &flist->xbf_flist, xbfi_list)
 		xfs_trans_log_efi_extent(*tp, efi, free->xbfi_startblock,
 			free->xbfi_blockcount);
 
@@ -125,9 +143,7 @@
 		if (committed) {
 			xfs_efi_release(efi);
 			xfs_force_shutdown((*tp)->t_mountp,
-				(error == -EFSCORRUPTED) ?
-					SHUTDOWN_CORRUPT_INCORE :
-					SHUTDOWN_META_IO_ERROR);
+					   SHUTDOWN_META_IO_ERROR);
 		}
 		return error;
 	}
@@ -138,15 +154,15 @@
 	 * on error.
 	 */
 	efd = xfs_trans_get_efd(*tp, efi, flist->xbf_count);
-	for (free = flist->xbf_first; free != NULL; free = next) {
-		next = free->xbfi_next;
-
+	while (!list_empty(&flist->xbf_flist)) {
+		free = list_first_entry(&flist->xbf_flist,
+				struct xfs_bmap_free_item, xbfi_list);
 		error = xfs_trans_free_extent(*tp, efd, free->xbfi_startblock,
 					      free->xbfi_blockcount);
 		if (error)
 			return error;
 
-		xfs_bmap_del_free(flist, NULL, free);
+		xfs_bmap_del_free(flist, free);
 	}
 
 	return 0;
@@ -409,7 +425,7 @@
 /*
  * Count fsblocks of the given fork.
  */
-int						/* error */
+static int					/* error */
 xfs_bmap_count_blocks(
 	xfs_trans_t		*tp,		/* transaction pointer */
 	xfs_inode_t		*ip,		/* incore inode */
@@ -799,7 +815,7 @@
 		if (error)
 			break;
 
-		ASSERT(!flist.xbf_count && !flist.xbf_first);
+		ASSERT(!flist.xbf_count && list_empty(&flist.xbf_flist));
 next_block:
 		start_fsb++;
 		remaining--;
@@ -1089,99 +1105,120 @@
 	return error;
 }
 
-/*
- * Zero file bytes between startoff and endoff inclusive.
- * The iolock is held exclusive and no blocks are buffered.
- *
- * This function is used by xfs_free_file_space() to zero
- * partial blocks when the range to free is not block aligned.
- * When unreserving space with boundaries that are not block
- * aligned we round up the start and round down the end
- * boundaries and then use this function to zero the parts of
- * the blocks that got dropped during the rounding.
- */
-STATIC int
-xfs_zero_remaining_bytes(
-	xfs_inode_t		*ip,
-	xfs_off_t		startoff,
-	xfs_off_t		endoff)
+static int
+xfs_unmap_extent(
+	struct xfs_inode	*ip,
+	xfs_fileoff_t		startoffset_fsb,
+	xfs_filblks_t		len_fsb,
+	int			*done)
 {
-	xfs_bmbt_irec_t		imap;
-	xfs_fileoff_t		offset_fsb;
-	xfs_off_t		lastoffset;
-	xfs_off_t		offset;
-	xfs_buf_t		*bp;
-	xfs_mount_t		*mp = ip->i_mount;
-	int			nimap;
-	int			error = 0;
+	struct xfs_mount	*mp = ip->i_mount;
+	struct xfs_trans	*tp;
+	struct xfs_bmap_free	free_list;
+	xfs_fsblock_t		firstfsb;
+	uint			resblks = XFS_DIOSTRAT_SPACE_RES(mp, 0);
+	int			error;
 
-	/*
-	 * Avoid doing I/O beyond eof - it's not necessary
-	 * since nothing can read beyond eof.  The space will
-	 * be zeroed when the file is extended anyway.
-	 */
-	if (startoff >= XFS_ISIZE(ip))
-		return 0;
-
-	if (endoff > XFS_ISIZE(ip))
-		endoff = XFS_ISIZE(ip);
-
-	for (offset = startoff; offset <= endoff; offset = lastoffset + 1) {
-		uint lock_mode;
-
-		offset_fsb = XFS_B_TO_FSBT(mp, offset);
-		nimap = 1;
-
-		lock_mode = xfs_ilock_data_map_shared(ip);
-		error = xfs_bmapi_read(ip, offset_fsb, 1, &imap, &nimap, 0);
-		xfs_iunlock(ip, lock_mode);
-
-		if (error || nimap < 1)
-			break;
-		ASSERT(imap.br_blockcount >= 1);
-		ASSERT(imap.br_startoff == offset_fsb);
-		ASSERT(imap.br_startblock != DELAYSTARTBLOCK);
-
-		if (imap.br_startblock == HOLESTARTBLOCK ||
-		    imap.br_state == XFS_EXT_UNWRITTEN) {
-			/* skip the entire extent */
-			lastoffset = XFS_FSB_TO_B(mp, imap.br_startoff +
-						      imap.br_blockcount) - 1;
-			continue;
-		}
-
-		lastoffset = XFS_FSB_TO_B(mp, imap.br_startoff + 1) - 1;
-		if (lastoffset > endoff)
-			lastoffset = endoff;
-
-		/* DAX can just zero the backing device directly */
-		if (IS_DAX(VFS_I(ip))) {
-			error = dax_zero_page_range(VFS_I(ip), offset,
-						    lastoffset - offset + 1,
-						    xfs_get_blocks_direct);
-			if (error)
-				return error;
-			continue;
-		}
-
-		error = xfs_buf_read_uncached(XFS_IS_REALTIME_INODE(ip) ?
-				mp->m_rtdev_targp : mp->m_ddev_targp,
-				xfs_fsb_to_db(ip, imap.br_startblock),
-				BTOBB(mp->m_sb.sb_blocksize),
-				0, &bp, NULL);
-		if (error)
-			return error;
-
-		memset(bp->b_addr +
-				(offset - XFS_FSB_TO_B(mp, imap.br_startoff)),
-		       0, lastoffset - offset + 1);
-
-		error = xfs_bwrite(bp);
-		xfs_buf_relse(bp);
-		if (error)
-			return error;
+	error = xfs_trans_alloc(mp, &M_RES(mp)->tr_write, resblks, 0, 0, &tp);
+	if (error) {
+		ASSERT(error == -ENOSPC || XFS_FORCED_SHUTDOWN(mp));
+		return error;
 	}
+
+	xfs_ilock(ip, XFS_ILOCK_EXCL);
+	error = xfs_trans_reserve_quota(tp, mp, ip->i_udquot, ip->i_gdquot,
+			ip->i_pdquot, resblks, 0, XFS_QMOPT_RES_REGBLKS);
+	if (error)
+		goto out_trans_cancel;
+
+	xfs_trans_ijoin(tp, ip, 0);
+
+	xfs_bmap_init(&free_list, &firstfsb);
+	error = xfs_bunmapi(tp, ip, startoffset_fsb, len_fsb, 0, 2, &firstfsb,
+			&free_list, done);
+	if (error)
+		goto out_bmap_cancel;
+
+	error = xfs_bmap_finish(&tp, &free_list, NULL);
+	if (error)
+		goto out_bmap_cancel;
+
+	error = xfs_trans_commit(tp);
+out_unlock:
+	xfs_iunlock(ip, XFS_ILOCK_EXCL);
 	return error;
+
+out_bmap_cancel:
+	xfs_bmap_cancel(&free_list);
+out_trans_cancel:
+	xfs_trans_cancel(tp);
+	goto out_unlock;
+}
+
+static int
+xfs_adjust_extent_unmap_boundaries(
+	struct xfs_inode	*ip,
+	xfs_fileoff_t		*startoffset_fsb,
+	xfs_fileoff_t		*endoffset_fsb)
+{
+	struct xfs_mount	*mp = ip->i_mount;
+	struct xfs_bmbt_irec	imap;
+	int			nimap, error;
+	xfs_extlen_t		mod = 0;
+
+	nimap = 1;
+	error = xfs_bmapi_read(ip, *startoffset_fsb, 1, &imap, &nimap, 0);
+	if (error)
+		return error;
+
+	if (nimap && imap.br_startblock != HOLESTARTBLOCK) {
+		xfs_daddr_t	block;
+
+		ASSERT(imap.br_startblock != DELAYSTARTBLOCK);
+		block = imap.br_startblock;
+		mod = do_div(block, mp->m_sb.sb_rextsize);
+		if (mod)
+			*startoffset_fsb += mp->m_sb.sb_rextsize - mod;
+	}
+
+	nimap = 1;
+	error = xfs_bmapi_read(ip, *endoffset_fsb - 1, 1, &imap, &nimap, 0);
+	if (error)
+		return error;
+
+	if (nimap && imap.br_startblock != HOLESTARTBLOCK) {
+		ASSERT(imap.br_startblock != DELAYSTARTBLOCK);
+		mod++;
+		if (mod && mod != mp->m_sb.sb_rextsize)
+			*endoffset_fsb -= mod;
+	}
+
+	return 0;
+}
+
+static int
+xfs_flush_unmap_range(
+	struct xfs_inode	*ip,
+	xfs_off_t		offset,
+	xfs_off_t		len)
+{
+	struct xfs_mount	*mp = ip->i_mount;
+	struct inode		*inode = VFS_I(ip);
+	xfs_off_t		rounding, start, end;
+	int			error;
+
+	/* wait for the completion of any pending DIOs */
+	inode_dio_wait(inode);
+
+	rounding = max_t(xfs_off_t, 1 << mp->m_sb.sb_blocklog, PAGE_SIZE);
+	start = round_down(offset, rounding);
+	end = round_up(offset + len, rounding) - 1;
+
+	error = filemap_write_and_wait_range(inode->i_mapping, start, end);
+	if (error)
+		return error;
+	truncate_pagecache_range(inode, start, end);
+	return 0;
 }
 
 int
@@ -1190,24 +1227,10 @@
 	xfs_off_t		offset,
 	xfs_off_t		len)
 {
-	int			done;
-	xfs_fileoff_t		endoffset_fsb;
-	int			error;
-	xfs_fsblock_t		firstfsb;
-	xfs_bmap_free_t		free_list;
-	xfs_bmbt_irec_t		imap;
-	xfs_off_t		ioffset;
-	xfs_off_t		iendoffset;
-	xfs_extlen_t		mod=0;
-	xfs_mount_t		*mp;
-	int			nimap;
-	uint			resblks;
-	xfs_off_t		rounding;
-	int			rt;
+	struct xfs_mount	*mp = ip->i_mount;
 	xfs_fileoff_t		startoffset_fsb;
-	xfs_trans_t		*tp;
-
-	mp = ip->i_mount;
+	xfs_fileoff_t		endoffset_fsb;
+	int			done = 0, error;
 
 	trace_xfs_free_file_space(ip);
 
@@ -1215,135 +1238,45 @@
 	if (error)
 		return error;
 
-	error = 0;
 	if (len <= 0)	/* if nothing being freed */
+		return 0;
+
+	error = xfs_flush_unmap_range(ip, offset, len);
+	if (error)
 		return error;
-	rt = XFS_IS_REALTIME_INODE(ip);
-	startoffset_fsb	= XFS_B_TO_FSB(mp, offset);
+
+	startoffset_fsb = XFS_B_TO_FSB(mp, offset);
 	endoffset_fsb = XFS_B_TO_FSBT(mp, offset + len);
 
-	/* wait for the completion of any pending DIOs */
-	inode_dio_wait(VFS_I(ip));
-
-	rounding = max_t(xfs_off_t, 1 << mp->m_sb.sb_blocklog, PAGE_SIZE);
-	ioffset = round_down(offset, rounding);
-	iendoffset = round_up(offset + len, rounding) - 1;
-	error = filemap_write_and_wait_range(VFS_I(ip)->i_mapping, ioffset,
-					     iendoffset);
-	if (error)
-		goto out;
-	truncate_pagecache_range(VFS_I(ip), ioffset, iendoffset);
-
 	/*
-	 * Need to zero the stuff we're not freeing, on disk.
-	 * If it's a realtime file & can't use unwritten extents then we
-	 * actually need to zero the extent edges.  Otherwise xfs_bunmapi
-	 * will take care of it for us.
+	 * Need to zero the stuff we're not freeing, on disk.  If it's a RT file
+	 * and we can't use unwritten extents then we actually need to ensure
+	 * to zero the whole extent, otherwise we just need to take of block
+	 * boundaries, and xfs_bunmapi will handle the rest.
 	 */
-	if (rt && !xfs_sb_version_hasextflgbit(&mp->m_sb)) {
-		nimap = 1;
-		error = xfs_bmapi_read(ip, startoffset_fsb, 1,
-					&imap, &nimap, 0);
+	if (XFS_IS_REALTIME_INODE(ip) &&
+	    !xfs_sb_version_hasextflgbit(&mp->m_sb)) {
+		error = xfs_adjust_extent_unmap_boundaries(ip, &startoffset_fsb,
+				&endoffset_fsb);
 		if (error)
-			goto out;
-		ASSERT(nimap == 0 || nimap == 1);
-		if (nimap && imap.br_startblock != HOLESTARTBLOCK) {
-			xfs_daddr_t	block;
-
-			ASSERT(imap.br_startblock != DELAYSTARTBLOCK);
-			block = imap.br_startblock;
-			mod = do_div(block, mp->m_sb.sb_rextsize);
-			if (mod)
-				startoffset_fsb += mp->m_sb.sb_rextsize - mod;
-		}
-		nimap = 1;
-		error = xfs_bmapi_read(ip, endoffset_fsb - 1, 1,
-					&imap, &nimap, 0);
-		if (error)
-			goto out;
-		ASSERT(nimap == 0 || nimap == 1);
-		if (nimap && imap.br_startblock != HOLESTARTBLOCK) {
-			ASSERT(imap.br_startblock != DELAYSTARTBLOCK);
-			mod++;
-			if (mod && (mod != mp->m_sb.sb_rextsize))
-				endoffset_fsb -= mod;
-		}
+			return error;
 	}
-	if ((done = (endoffset_fsb <= startoffset_fsb)))
-		/*
-		 * One contiguous piece to clear
-		 */
-		error = xfs_zero_remaining_bytes(ip, offset, offset + len - 1);
-	else {
-		/*
-		 * Some full blocks, possibly two pieces to clear
-		 */
-		if (offset < XFS_FSB_TO_B(mp, startoffset_fsb))
-			error = xfs_zero_remaining_bytes(ip, offset,
-				XFS_FSB_TO_B(mp, startoffset_fsb) - 1);
-		if (!error &&
-		    XFS_FSB_TO_B(mp, endoffset_fsb) < offset + len)
-			error = xfs_zero_remaining_bytes(ip,
-				XFS_FSB_TO_B(mp, endoffset_fsb),
-				offset + len - 1);
+
+	if (endoffset_fsb > startoffset_fsb) {
+		while (!done) {
+			error = xfs_unmap_extent(ip, startoffset_fsb,
+					endoffset_fsb - startoffset_fsb, &done);
+			if (error)
+				return error;
+		}
 	}
 
 	/*
-	 * free file space until done or until there is an error
+	 * Now that we've unmap all full blocks we'll have to zero out any
+	 * partial block at the beginning and/or end.  xfs_zero_range is
+	 * smart enough to skip any holes, including those we just created.
 	 */
-	resblks = XFS_DIOSTRAT_SPACE_RES(mp, 0);
-	while (!error && !done) {
-
-		/*
-		 * allocate and setup the transaction. Allow this
-		 * transaction to dip into the reserve blocks to ensure
-		 * the freeing of the space succeeds at ENOSPC.
-		 */
-		error = xfs_trans_alloc(mp, &M_RES(mp)->tr_write, resblks, 0, 0,
-				&tp);
-		if (error) {
-			ASSERT(error == -ENOSPC || XFS_FORCED_SHUTDOWN(mp));
-			break;
-		}
-		xfs_ilock(ip, XFS_ILOCK_EXCL);
-		error = xfs_trans_reserve_quota(tp, mp,
-				ip->i_udquot, ip->i_gdquot, ip->i_pdquot,
-				resblks, 0, XFS_QMOPT_RES_REGBLKS);
-		if (error)
-			goto error1;
-
-		xfs_trans_ijoin(tp, ip, 0);
-
-		/*
-		 * issue the bunmapi() call to free the blocks
-		 */
-		xfs_bmap_init(&free_list, &firstfsb);
-		error = xfs_bunmapi(tp, ip, startoffset_fsb,
-				  endoffset_fsb - startoffset_fsb,
-				  0, 2, &firstfsb, &free_list, &done);
-		if (error)
-			goto error0;
-
-		/*
-		 * complete the transaction
-		 */
-		error = xfs_bmap_finish(&tp, &free_list, NULL);
-		if (error)
-			goto error0;
-
-		error = xfs_trans_commit(tp);
-		xfs_iunlock(ip, XFS_ILOCK_EXCL);
-	}
-
- out:
-	return error;
-
- error0:
-	xfs_bmap_cancel(&free_list);
- error1:
-	xfs_trans_cancel(tp);
-	xfs_iunlock(ip, XFS_ILOCK_EXCL);
-	goto out;
+	return xfs_zero_range(ip, offset, len, NULL);
 }
 
 /*
diff --git a/fs/xfs/xfs_bmap_util.h b/fs/xfs/xfs_bmap_util.h
index af97d9a..f200714 100644
--- a/fs/xfs/xfs_bmap_util.h
+++ b/fs/xfs/xfs_bmap_util.h
@@ -31,8 +31,6 @@
 int	xfs_bmap_rtalloc(struct xfs_bmalloca *ap);
 int	xfs_bmap_eof(struct xfs_inode *ip, xfs_fileoff_t endoff,
 		     int whichfork, int *eof);
-int	xfs_bmap_count_blocks(struct xfs_trans *tp, struct xfs_inode *ip,
-			      int whichfork, int *count);
 int	xfs_bmap_punch_delalloc_range(struct xfs_inode *ip,
 		xfs_fileoff_t start_fsb, xfs_fileoff_t length);
 
@@ -43,7 +41,6 @@
 
 /* functions in xfs_bmap.c that are only needed by xfs_bmap_util.c */
 void	xfs_bmap_del_free(struct xfs_bmap_free *flist,
-			  struct xfs_bmap_free_item *prev,
 			  struct xfs_bmap_free_item *free);
 int	xfs_bmap_extsize_align(struct xfs_mount *mp, struct xfs_bmbt_irec *gotp,
 			       struct xfs_bmbt_irec *prevp, xfs_extlen_t extsz,
diff --git a/fs/xfs/xfs_buf.c b/fs/xfs/xfs_buf.c
index 2722cb4..32fc540 100644
--- a/fs/xfs/xfs_buf.c
+++ b/fs/xfs/xfs_buf.c
@@ -1016,10 +1016,12 @@
 	int			locked;
 
 	locked = down_trylock(&bp->b_sema) == 0;
-	if (locked)
+	if (locked) {
 		XB_SET_OWNER(bp);
-
-	trace_xfs_buf_trylock(bp, _RET_IP_);
+		trace_xfs_buf_trylock(bp, _RET_IP_);
+	} else {
+		trace_xfs_buf_trylock_fail(bp, _RET_IP_);
+	}
 	return locked;
 }
 
@@ -1858,18 +1860,33 @@
 	return 0;
 }
 
+/*
+ * submit buffers for write.
+ *
+ * When we have a large buffer list, we do not want to hold all the buffers
+ * locked while we block on the request queue waiting for IO dispatch. To avoid
+ * this problem, we lock and submit buffers in groups of 50, thereby minimising
+ * the lock hold times for lists which may contain thousands of objects.
+ *
+ * To do this, we sort the buffer list before we walk the list to lock and
+ * submit buffers, and we plug and unplug around each group of buffers we
+ * submit.
+ */
 static int
-__xfs_buf_delwri_submit(
+xfs_buf_delwri_submit_buffers(
 	struct list_head	*buffer_list,
-	struct list_head	*io_list,
-	bool			wait)
+	struct list_head	*wait_list)
 {
-	struct blk_plug		plug;
 	struct xfs_buf		*bp, *n;
+	LIST_HEAD		(submit_list);
 	int			pinned = 0;
+	struct blk_plug		plug;
 
+	list_sort(NULL, buffer_list, xfs_buf_cmp);
+
+	blk_start_plug(&plug);
 	list_for_each_entry_safe(bp, n, buffer_list, b_list) {
-		if (!wait) {
+		if (!wait_list) {
 			if (xfs_buf_ispinned(bp)) {
 				pinned++;
 				continue;
@@ -1892,25 +1909,21 @@
 			continue;
 		}
 
-		list_move_tail(&bp->b_list, io_list);
 		trace_xfs_buf_delwri_split(bp, _RET_IP_);
-	}
-
-	list_sort(NULL, io_list, xfs_buf_cmp);
-
-	blk_start_plug(&plug);
-	list_for_each_entry_safe(bp, n, io_list, b_list) {
-		bp->b_flags &= ~(_XBF_DELWRI_Q | XBF_WRITE_FAIL);
-		bp->b_flags |= XBF_WRITE | XBF_ASYNC;
 
 		/*
-		 * we do all Io submission async. This means if we need to wait
-		 * for IO completion we need to take an extra reference so the
-		 * buffer is still valid on the other side.
+		 * We do all IO submission async. This means if we need
+		 * to wait for IO completion we need to take an extra
+		 * reference so the buffer is still valid on the other
+		 * side. We need to move the buffer onto the io_list
+		 * at this point so the caller can still access it.
 		 */
-		if (wait)
+		bp->b_flags &= ~(_XBF_DELWRI_Q | XBF_WRITE_FAIL);
+		bp->b_flags |= XBF_WRITE | XBF_ASYNC;
+		if (wait_list) {
 			xfs_buf_hold(bp);
-		else
+			list_move_tail(&bp->b_list, wait_list);
+		} else
 			list_del_init(&bp->b_list);
 
 		xfs_buf_submit(bp);
@@ -1933,8 +1946,7 @@
 xfs_buf_delwri_submit_nowait(
 	struct list_head	*buffer_list)
 {
-	LIST_HEAD		(io_list);
-	return __xfs_buf_delwri_submit(buffer_list, &io_list, false);
+	return xfs_buf_delwri_submit_buffers(buffer_list, NULL);
 }
 
 /*
@@ -1949,15 +1961,15 @@
 xfs_buf_delwri_submit(
 	struct list_head	*buffer_list)
 {
-	LIST_HEAD		(io_list);
+	LIST_HEAD		(wait_list);
 	int			error = 0, error2;
 	struct xfs_buf		*bp;
 
-	__xfs_buf_delwri_submit(buffer_list, &io_list, true);
+	xfs_buf_delwri_submit_buffers(buffer_list, &wait_list);
 
 	/* Wait for IO to complete. */
-	while (!list_empty(&io_list)) {
-		bp = list_first_entry(&io_list, struct xfs_buf, b_list);
+	while (!list_empty(&wait_list)) {
+		bp = list_first_entry(&wait_list, struct xfs_buf, b_list);
 
 		list_del_init(&bp->b_list);
 
diff --git a/fs/xfs/xfs_buf_item.c b/fs/xfs/xfs_buf_item.c
index 3b19e52..0337690 100644
--- a/fs/xfs/xfs_buf_item.c
+++ b/fs/xfs/xfs_buf_item.c
@@ -359,7 +359,7 @@
 	for (i = 0; i < bip->bli_format_count; i++) {
 		xfs_buf_item_format_segment(bip, lv, &vecp, offset,
 					    &bip->bli_formats[i]);
-		offset += bp->b_maps[i].bm_len;
+		offset += BBTOB(bp->b_maps[i].bm_len);
 	}
 
 	/*
@@ -915,20 +915,28 @@
 	for (i = 0; i < bip->bli_format_count; i++) {
 		if (start > last)
 			break;
-		end = start + BBTOB(bp->b_maps[i].bm_len);
+		end = start + BBTOB(bp->b_maps[i].bm_len) - 1;
+
+		/* skip to the map that includes the first byte to log */
 		if (first > end) {
 			start += BBTOB(bp->b_maps[i].bm_len);
 			continue;
 		}
+
+		/*
+		 * Trim the range to this segment and mark it in the bitmap.
+		 * Note that we must convert buffer offsets to segment relative
+		 * offsets (e.g., the first byte of each segment is byte 0 of
+		 * that segment).
+		 */
 		if (first < start)
 			first = start;
 		if (end > last)
 			end = last;
-
-		xfs_buf_item_log_segment(first, end,
+		xfs_buf_item_log_segment(first - start, end - start,
 					 &bip->bli_formats[i].blf_data_map[0]);
 
-		start += bp->b_maps[i].bm_len;
+		start += BBTOB(bp->b_maps[i].bm_len);
 	}
 }
 
diff --git a/fs/xfs/xfs_error.c b/fs/xfs/xfs_error.c
index 88693a9..ed7ee4e 100644
--- a/fs/xfs/xfs_error.c
+++ b/fs/xfs/xfs_error.c
@@ -55,12 +55,15 @@
 }
 
 int
-xfs_errortag_add(int error_tag, xfs_mount_t *mp)
+xfs_errortag_add(unsigned int error_tag, xfs_mount_t *mp)
 {
 	int i;
 	int len;
 	int64_t fsid;
 
+	if (error_tag >= XFS_ERRTAG_MAX)
+		return -EINVAL;
+
 	memcpy(&fsid, mp->m_fixedfsid, sizeof(xfs_fsid_t));
 
 	for (i = 0; i < XFS_NUM_INJECT_ERROR; i++)  {
diff --git a/fs/xfs/xfs_error.h b/fs/xfs/xfs_error.h
index 4ed3042..2e4f67f 100644
--- a/fs/xfs/xfs_error.h
+++ b/fs/xfs/xfs_error.h
@@ -128,7 +128,7 @@
 	 xfs_error_test((tag), (mp)->m_fixedfsid, "expr", __LINE__, __FILE__, \
 			(rf))))
 
-extern int xfs_errortag_add(int error_tag, struct xfs_mount *mp);
+extern int xfs_errortag_add(unsigned int error_tag, struct xfs_mount *mp);
 extern int xfs_errortag_clearall(struct xfs_mount *mp, int loud);
 #else
 #define XFS_TEST_ERROR(expr, mp, tag, rf)	(expr)
diff --git a/fs/xfs/xfs_file.c b/fs/xfs/xfs_file.c
index 47fc632..713991c 100644
--- a/fs/xfs/xfs_file.c
+++ b/fs/xfs/xfs_file.c
@@ -37,6 +37,7 @@
 #include "xfs_log.h"
 #include "xfs_icache.h"
 #include "xfs_pnfs.h"
+#include "xfs_iomap.h"
 
 #include <linux/dcache.h>
 #include <linux/falloc.h>
@@ -80,61 +81,17 @@
 }
 
 /*
- * xfs_iozero clears the specified range supplied via the page cache (except in
- * the DAX case). Writes through the page cache will allocate blocks over holes,
- * though the callers usually map the holes first and avoid them. If a block is
- * not completely zeroed, then it will be read from disk before being partially
- * zeroed.
- *
- * In the DAX case, we can just directly write to the underlying pages. This
- * will not allocate blocks, but will avoid holes and unwritten extents and so
- * not do unnecessary work.
+ * Clear the specified ranges to zero through either the pagecache or DAX.
+ * Holes and unwritten extents will be left as-is as they already are zeroed.
  */
 int
-xfs_iozero(
-	struct xfs_inode	*ip,	/* inode			*/
-	loff_t			pos,	/* offset in file		*/
-	size_t			count)	/* size of data to zero		*/
+xfs_zero_range(
+	struct xfs_inode	*ip,
+	xfs_off_t		pos,
+	xfs_off_t		count,
+	bool			*did_zero)
 {
-	struct page		*page;
-	struct address_space	*mapping;
-	int			status = 0;
-
-
-	mapping = VFS_I(ip)->i_mapping;
-	do {
-		unsigned offset, bytes;
-		void *fsdata;
-
-		offset = (pos & (PAGE_SIZE -1)); /* Within page */
-		bytes = PAGE_SIZE - offset;
-		if (bytes > count)
-			bytes = count;
-
-		if (IS_DAX(VFS_I(ip))) {
-			status = dax_zero_page_range(VFS_I(ip), pos, bytes,
-						     xfs_get_blocks_direct);
-			if (status)
-				break;
-		} else {
-			status = pagecache_write_begin(NULL, mapping, pos, bytes,
-						AOP_FLAG_UNINTERRUPTIBLE,
-						&page, &fsdata);
-			if (status)
-				break;
-
-			zero_user(page, offset, bytes);
-
-			status = pagecache_write_end(NULL, mapping, pos, bytes,
-						bytes, page, fsdata);
-			WARN_ON(status <= 0); /* can't return less than zero! */
-			status = 0;
-		}
-		pos += bytes;
-		count -= bytes;
-	} while (count);
-
-	return status;
+	return iomap_zero_range(VFS_I(ip), pos, count, NULL, &xfs_iomap_ops);
 }
 
 int
@@ -424,49 +381,6 @@
 }
 
 /*
- * This routine is called to handle zeroing any space in the last block of the
- * file that is beyond the EOF.  We do this since the size is being increased
- * without writing anything to that block and we don't want to read the
- * garbage on the disk.
- */
-STATIC int				/* error (positive) */
-xfs_zero_last_block(
-	struct xfs_inode	*ip,
-	xfs_fsize_t		offset,
-	xfs_fsize_t		isize,
-	bool			*did_zeroing)
-{
-	struct xfs_mount	*mp = ip->i_mount;
-	xfs_fileoff_t		last_fsb = XFS_B_TO_FSBT(mp, isize);
-	int			zero_offset = XFS_B_FSB_OFFSET(mp, isize);
-	int			zero_len;
-	int			nimaps = 1;
-	int			error = 0;
-	struct xfs_bmbt_irec	imap;
-
-	xfs_ilock(ip, XFS_ILOCK_EXCL);
-	error = xfs_bmapi_read(ip, last_fsb, 1, &imap, &nimaps, 0);
-	xfs_iunlock(ip, XFS_ILOCK_EXCL);
-	if (error)
-		return error;
-
-	ASSERT(nimaps > 0);
-
-	/*
-	 * If the block underlying isize is just a hole, then there
-	 * is nothing to zero.
-	 */
-	if (imap.br_startblock == HOLESTARTBLOCK)
-		return 0;
-
-	zero_len = mp->m_sb.sb_blocksize - zero_offset;
-	if (isize + zero_len > offset)
-		zero_len = offset - isize;
-	*did_zeroing = true;
-	return xfs_iozero(ip, isize, zero_len);
-}
-
-/*
  * Zero any on disk space between the current EOF and the new, larger EOF.
  *
  * This handles the normal case of zeroing the remainder of the last block in
@@ -484,94 +398,11 @@
 	xfs_fsize_t		isize,		/* current inode size */
 	bool			*did_zeroing)
 {
-	struct xfs_mount	*mp = ip->i_mount;
-	xfs_fileoff_t		start_zero_fsb;
-	xfs_fileoff_t		end_zero_fsb;
-	xfs_fileoff_t		zero_count_fsb;
-	xfs_fileoff_t		last_fsb;
-	xfs_fileoff_t		zero_off;
-	xfs_fsize_t		zero_len;
-	int			nimaps;
-	int			error = 0;
-	struct xfs_bmbt_irec	imap;
-
 	ASSERT(xfs_isilocked(ip, XFS_IOLOCK_EXCL));
 	ASSERT(offset > isize);
 
 	trace_xfs_zero_eof(ip, isize, offset - isize);
-
-	/*
-	 * First handle zeroing the block on which isize resides.
-	 *
-	 * We only zero a part of that block so it is handled specially.
-	 */
-	if (XFS_B_FSB_OFFSET(mp, isize) != 0) {
-		error = xfs_zero_last_block(ip, offset, isize, did_zeroing);
-		if (error)
-			return error;
-	}
-
-	/*
-	 * Calculate the range between the new size and the old where blocks
-	 * needing to be zeroed may exist.
-	 *
-	 * To get the block where the last byte in the file currently resides,
-	 * we need to subtract one from the size and truncate back to a block
-	 * boundary.  We subtract 1 in case the size is exactly on a block
-	 * boundary.
-	 */
-	last_fsb = isize ? XFS_B_TO_FSBT(mp, isize - 1) : (xfs_fileoff_t)-1;
-	start_zero_fsb = XFS_B_TO_FSB(mp, (xfs_ufsize_t)isize);
-	end_zero_fsb = XFS_B_TO_FSBT(mp, offset - 1);
-	ASSERT((xfs_sfiloff_t)last_fsb < (xfs_sfiloff_t)start_zero_fsb);
-	if (last_fsb == end_zero_fsb) {
-		/*
-		 * The size was only incremented on its last block.
-		 * We took care of that above, so just return.
-		 */
-		return 0;
-	}
-
-	ASSERT(start_zero_fsb <= end_zero_fsb);
-	while (start_zero_fsb <= end_zero_fsb) {
-		nimaps = 1;
-		zero_count_fsb = end_zero_fsb - start_zero_fsb + 1;
-
-		xfs_ilock(ip, XFS_ILOCK_EXCL);
-		error = xfs_bmapi_read(ip, start_zero_fsb, zero_count_fsb,
-					  &imap, &nimaps, 0);
-		xfs_iunlock(ip, XFS_ILOCK_EXCL);
-		if (error)
-			return error;
-
-		ASSERT(nimaps > 0);
-
-		if (imap.br_state == XFS_EXT_UNWRITTEN ||
-		    imap.br_startblock == HOLESTARTBLOCK) {
-			start_zero_fsb = imap.br_startoff + imap.br_blockcount;
-			ASSERT(start_zero_fsb <= (end_zero_fsb + 1));
-			continue;
-		}
-
-		/*
-		 * There are blocks we need to zero.
-		 */
-		zero_off = XFS_FSB_TO_B(mp, start_zero_fsb);
-		zero_len = XFS_FSB_TO_B(mp, imap.br_blockcount);
-
-		if ((zero_off + zero_len) > offset)
-			zero_len = offset - zero_off;
-
-		error = xfs_iozero(ip, zero_off, zero_len);
-		if (error)
-			return error;
-
-		*did_zeroing = true;
-		start_zero_fsb = imap.br_startoff + imap.br_blockcount;
-		ASSERT(start_zero_fsb <= (end_zero_fsb + 1));
-	}
-
-	return 0;
+	return xfs_zero_range(ip, isize, offset - isize, did_zeroing);
 }
 
 /*
@@ -841,7 +672,7 @@
 write_retry:
 	trace_xfs_file_buffered_write(ip, iov_iter_count(from),
 				      iocb->ki_pos, 0);
-	ret = generic_perform_write(file, from, iocb->ki_pos);
+	ret = iomap_file_buffered_write(iocb, from, &xfs_iomap_ops);
 	if (likely(ret >= 0))
 		iocb->ki_pos += ret;
 
@@ -1553,7 +1384,7 @@
 	if (IS_DAX(inode)) {
 		ret = __dax_mkwrite(vma, vmf, xfs_get_blocks_dax_fault);
 	} else {
-		ret = block_page_mkwrite(vma, vmf, xfs_get_blocks);
+		ret = iomap_page_mkwrite(vma, vmf, &xfs_iomap_ops);
 		ret = block_page_mkwrite_return(ret);
 	}
 
diff --git a/fs/xfs/xfs_fsops.c b/fs/xfs/xfs_fsops.c
index b4d7582..7191c38 100644
--- a/fs/xfs/xfs_fsops.c
+++ b/fs/xfs/xfs_fsops.c
@@ -667,8 +667,11 @@
 	__uint64_t              *inval,
 	xfs_fsop_resblks_t      *outval)
 {
-	__int64_t		lcounter, delta, fdblks_delta;
+	__int64_t		lcounter, delta;
+	__int64_t		fdblks_delta = 0;
 	__uint64_t		request;
+	__int64_t		free;
+	int			error = 0;
 
 	/* If inval is null, report current values and return */
 	if (inval == (__uint64_t *)NULL) {
@@ -682,24 +685,23 @@
 	request = *inval;
 
 	/*
-	 * With per-cpu counters, this becomes an interesting
-	 * problem. we needto work out if we are freeing or allocation
-	 * blocks first, then we can do the modification as necessary.
+	 * With per-cpu counters, this becomes an interesting problem. we need
+	 * to work out if we are freeing or allocation blocks first, then we can
+	 * do the modification as necessary.
 	 *
-	 * We do this under the m_sb_lock so that if we are near
-	 * ENOSPC, we will hold out any changes while we work out
-	 * what to do. This means that the amount of free space can
-	 * change while we do this, so we need to retry if we end up
-	 * trying to reserve more space than is available.
+	 * We do this under the m_sb_lock so that if we are near ENOSPC, we will
+	 * hold out any changes while we work out what to do. This means that
+	 * the amount of free space can change while we do this, so we need to
+	 * retry if we end up trying to reserve more space than is available.
 	 */
-retry:
 	spin_lock(&mp->m_sb_lock);
 
 	/*
 	 * If our previous reservation was larger than the current value,
-	 * then move any unused blocks back to the free pool.
+	 * then move any unused blocks back to the free pool. Modify the resblks
+	 * counters directly since we shouldn't have any problems unreserving
+	 * space.
 	 */
-	fdblks_delta = 0;
 	if (mp->m_resblks > request) {
 		lcounter = mp->m_resblks_avail - request;
 		if (lcounter  > 0) {		/* release unused blocks */
@@ -707,54 +709,67 @@
 			mp->m_resblks_avail -= lcounter;
 		}
 		mp->m_resblks = request;
-	} else {
-		__int64_t	free;
+		if (fdblks_delta) {
+			spin_unlock(&mp->m_sb_lock);
+			error = xfs_mod_fdblocks(mp, fdblks_delta, 0);
+			spin_lock(&mp->m_sb_lock);
+		}
 
+		goto out;
+	}
+
+	/*
+	 * If the request is larger than the current reservation, reserve the
+	 * blocks before we update the reserve counters. Sample m_fdblocks and
+	 * perform a partial reservation if the request exceeds free space.
+	 */
+	error = -ENOSPC;
+	do {
 		free = percpu_counter_sum(&mp->m_fdblocks) -
 							XFS_ALLOC_SET_ASIDE(mp);
 		if (!free)
-			goto out; /* ENOSPC and fdblks_delta = 0 */
+			break;
 
 		delta = request - mp->m_resblks;
 		lcounter = free - delta;
-		if (lcounter < 0) {
+		if (lcounter < 0)
 			/* We can't satisfy the request, just get what we can */
-			mp->m_resblks += free;
-			mp->m_resblks_avail += free;
-			fdblks_delta = -free;
-		} else {
-			fdblks_delta = -delta;
-			mp->m_resblks = request;
-			mp->m_resblks_avail += delta;
-		}
+			fdblks_delta = free;
+		else
+			fdblks_delta = delta;
+
+		/*
+		 * We'll either succeed in getting space from the free block
+		 * count or we'll get an ENOSPC. If we get a ENOSPC, it means
+		 * things changed while we were calculating fdblks_delta and so
+		 * we should try again to see if there is anything left to
+		 * reserve.
+		 *
+		 * Don't set the reserved flag here - we don't want to reserve
+		 * the extra reserve blocks from the reserve.....
+		 */
+		spin_unlock(&mp->m_sb_lock);
+		error = xfs_mod_fdblocks(mp, -fdblks_delta, 0);
+		spin_lock(&mp->m_sb_lock);
+	} while (error == -ENOSPC);
+
+	/*
+	 * Update the reserve counters if blocks have been successfully
+	 * allocated.
+	 */
+	if (!error && fdblks_delta) {
+		mp->m_resblks += fdblks_delta;
+		mp->m_resblks_avail += fdblks_delta;
 	}
+
 out:
 	if (outval) {
 		outval->resblks = mp->m_resblks;
 		outval->resblks_avail = mp->m_resblks_avail;
 	}
-	spin_unlock(&mp->m_sb_lock);
 
-	if (fdblks_delta) {
-		/*
-		 * If we are putting blocks back here, m_resblks_avail is
-		 * already at its max so this will put it in the free pool.
-		 *
-		 * If we need space, we'll either succeed in getting it
-		 * from the free block count or we'll get an enospc. If
-		 * we get a ENOSPC, it means things changed while we were
-		 * calculating fdblks_delta and so we should try again to
-		 * see if there is anything left to reserve.
-		 *
-		 * Don't set the reserved flag here - we don't want to reserve
-		 * the extra reserve blocks from the reserve.....
-		 */
-		int error;
-		error = xfs_mod_fdblocks(mp, fdblks_delta, 0);
-		if (error == -ENOSPC)
-			goto retry;
-	}
-	return 0;
+	spin_unlock(&mp->m_sb_lock);
+	return error;
 }
 
 int
diff --git a/fs/xfs/xfs_icache.c b/fs/xfs/xfs_icache.c
index 99ee6eee..fb39a66 100644
--- a/fs/xfs/xfs_icache.c
+++ b/fs/xfs/xfs_icache.c
@@ -765,7 +765,7 @@
  * Background scanning to trim post-EOF preallocated space. This is queued
  * based on the 'speculative_prealloc_lifetime' tunable (5m by default).
  */
-STATIC void
+void
 xfs_queue_eofblocks(
 	struct xfs_mount *mp)
 {
diff --git a/fs/xfs/xfs_icache.h b/fs/xfs/xfs_icache.h
index 62f1f91..05bac99 100644
--- a/fs/xfs/xfs_icache.h
+++ b/fs/xfs/xfs_icache.h
@@ -68,6 +68,7 @@
 int xfs_icache_free_eofblocks(struct xfs_mount *, struct xfs_eofblocks *);
 int xfs_inode_free_quota_eofblocks(struct xfs_inode *ip);
 void xfs_eofblocks_worker(struct work_struct *);
+void xfs_queue_eofblocks(struct xfs_mount *);
 
 int xfs_inode_ag_iterator(struct xfs_mount *mp,
 	int (*execute)(struct xfs_inode *ip, int flags, void *args),
diff --git a/fs/xfs/xfs_inode.c b/fs/xfs/xfs_inode.c
index ee6799e..8825bcf 100644
--- a/fs/xfs/xfs_inode.c
+++ b/fs/xfs/xfs_inode.c
@@ -431,7 +431,7 @@
  * lock more than one at a time, lockdep will report false positives saying we
  * have violated locking orders.
  */
-void
+static void
 xfs_lock_inodes(
 	xfs_inode_t	**ips,
 	int		inodes,
@@ -667,14 +667,6 @@
 	return _xfs_dic2xflags(dic->di_flags, dic->di_flags2, XFS_IFORK_Q(ip));
 }
 
-uint
-xfs_dic2xflags(
-	struct xfs_dinode	*dip)
-{
-	return _xfs_dic2xflags(be16_to_cpu(dip->di_flags),
-				be64_to_cpu(dip->di_flags2), XFS_DFORK_Q(dip));
-}
-
 /*
  * Lookups up an inode from "name". If ci_name is not NULL, then a CI match
  * is allowed, otherwise it has to be an exact match. If a CI match is found,
@@ -748,7 +740,7 @@
  * are not linked into the directory structure - they are attached
  * directly to the superblock - and so have no parent.
  */
-int
+static int
 xfs_ialloc(
 	xfs_trans_t	*tp,
 	xfs_inode_t	*pip,
@@ -1085,7 +1077,7 @@
  * link count to go to zero, move the inode to AGI unlinked list so that it can
  * be freed when the last active reference goes away via xfs_inactive().
  */
-int				/* error */
+static int			/* error */
 xfs_droplink(
 	xfs_trans_t *tp,
 	xfs_inode_t *ip)
@@ -1104,7 +1096,7 @@
 /*
  * Increment the link count on an inode & log the change.
  */
-int
+static int
 xfs_bumplink(
 	xfs_trans_t *tp,
 	xfs_inode_t *ip)
diff --git a/fs/xfs/xfs_inode.h b/fs/xfs/xfs_inode.h
index e52d7c7..0c19d3d 100644
--- a/fs/xfs/xfs_inode.h
+++ b/fs/xfs/xfs_inode.h
@@ -395,12 +395,8 @@
 int		xfs_isilocked(xfs_inode_t *, uint);
 uint		xfs_ilock_data_map_shared(struct xfs_inode *);
 uint		xfs_ilock_attr_map_shared(struct xfs_inode *);
-int		xfs_ialloc(struct xfs_trans *, xfs_inode_t *, umode_t,
-			   xfs_nlink_t, xfs_dev_t, prid_t, int,
-			   struct xfs_buf **, xfs_inode_t **);
 
 uint		xfs_ip2xflags(struct xfs_inode *);
-uint		xfs_dic2xflags(struct xfs_dinode *);
 int		xfs_ifree(struct xfs_trans *, xfs_inode_t *,
 			   struct xfs_bmap_free *);
 int		xfs_itruncate_extents(struct xfs_trans **, struct xfs_inode *,
@@ -411,7 +407,6 @@
 #define xfs_ipincount(ip)	((unsigned int) atomic_read(&ip->i_pincount))
 
 int		xfs_iflush(struct xfs_inode *, struct xfs_buf **);
-void		xfs_lock_inodes(xfs_inode_t **, int, uint);
 void		xfs_lock_two_inodes(xfs_inode_t *, xfs_inode_t *, uint);
 
 xfs_extlen_t	xfs_get_extsz_hint(struct xfs_inode *ip);
@@ -419,8 +414,6 @@
 int		xfs_dir_ialloc(struct xfs_trans **, struct xfs_inode *, umode_t,
 			       xfs_nlink_t, xfs_dev_t, prid_t, int,
 			       struct xfs_inode **, int *);
-int		xfs_droplink(struct xfs_trans *, struct xfs_inode *);
-int		xfs_bumplink(struct xfs_trans *, struct xfs_inode *);
 
 /* from xfs_file.c */
 enum xfs_prealloc_flags {
@@ -434,7 +427,8 @@
 				  enum xfs_prealloc_flags flags);
 int	xfs_zero_eof(struct xfs_inode *ip, xfs_off_t offset,
 		     xfs_fsize_t isize, bool *did_zeroing);
-int	xfs_iozero(struct xfs_inode *ip, loff_t pos, size_t count);
+int	xfs_zero_range(struct xfs_inode *ip, xfs_off_t pos, xfs_off_t count,
+		bool *did_zero);
 loff_t	__xfs_seek_hole_data(struct inode *inode, loff_t start,
 			     loff_t eof, int whence);
 
diff --git a/fs/xfs/xfs_ioctl.c b/fs/xfs/xfs_ioctl.c
index dbca737..408f3ad 100644
--- a/fs/xfs/xfs_ioctl.c
+++ b/fs/xfs/xfs_ioctl.c
@@ -1575,6 +1575,17 @@
 		goto out_put_tmp_file;
 	}
 
+	/*
+	 * We need to ensure that the fds passed in point to XFS inodes
+	 * before we cast and access them as XFS structures as we have no
+	 * control over what the user passes us here.
+	 */
+	if (f.file->f_op != &xfs_file_operations ||
+	    tmp.file->f_op != &xfs_file_operations) {
+		error = -EINVAL;
+		goto out_put_tmp_file;
+	}
+
 	ip = XFS_I(file_inode(f.file));
 	tip = XFS_I(file_inode(tmp.file));
 
diff --git a/fs/xfs/xfs_iomap.c b/fs/xfs/xfs_iomap.c
index 5839135..620fc91 100644
--- a/fs/xfs/xfs_iomap.c
+++ b/fs/xfs/xfs_iomap.c
@@ -15,6 +15,7 @@
  * along with this program; if not, write the Free Software Foundation,
  * Inc.,  51 Franklin St, Fifth Floor, Boston, MA  02110-1301  USA
  */
+#include <linux/iomap.h>
 #include "xfs.h"
 #include "xfs_fs.h"
 #include "xfs_shared.h"
@@ -940,3 +941,173 @@
 	xfs_iunlock(ip, XFS_ILOCK_EXCL);
 	return error;
 }
+
+void
+xfs_bmbt_to_iomap(
+	struct xfs_inode	*ip,
+	struct iomap		*iomap,
+	struct xfs_bmbt_irec	*imap)
+{
+	struct xfs_mount	*mp = ip->i_mount;
+
+	if (imap->br_startblock == HOLESTARTBLOCK) {
+		iomap->blkno = IOMAP_NULL_BLOCK;
+		iomap->type = IOMAP_HOLE;
+	} else if (imap->br_startblock == DELAYSTARTBLOCK) {
+		iomap->blkno = IOMAP_NULL_BLOCK;
+		iomap->type = IOMAP_DELALLOC;
+	} else {
+		iomap->blkno = xfs_fsb_to_db(ip, imap->br_startblock);
+		if (imap->br_state == XFS_EXT_UNWRITTEN)
+			iomap->type = IOMAP_UNWRITTEN;
+		else
+			iomap->type = IOMAP_MAPPED;
+	}
+	iomap->offset = XFS_FSB_TO_B(mp, imap->br_startoff);
+	iomap->length = XFS_FSB_TO_B(mp, imap->br_blockcount);
+	iomap->bdev = xfs_find_bdev_for_inode(VFS_I(ip));
+}
+
+static inline bool imap_needs_alloc(struct xfs_bmbt_irec *imap, int nimaps)
+{
+	return !nimaps ||
+		imap->br_startblock == HOLESTARTBLOCK ||
+		imap->br_startblock == DELAYSTARTBLOCK;
+}
+
+static int
+xfs_file_iomap_begin(
+	struct inode		*inode,
+	loff_t			offset,
+	loff_t			length,
+	unsigned		flags,
+	struct iomap		*iomap)
+{
+	struct xfs_inode	*ip = XFS_I(inode);
+	struct xfs_mount	*mp = ip->i_mount;
+	struct xfs_bmbt_irec	imap;
+	xfs_fileoff_t		offset_fsb, end_fsb;
+	int			nimaps = 1, error = 0;
+
+	if (XFS_FORCED_SHUTDOWN(mp))
+		return -EIO;
+
+	xfs_ilock(ip, XFS_ILOCK_EXCL);
+
+	ASSERT(offset <= mp->m_super->s_maxbytes);
+	if ((xfs_fsize_t)offset + length > mp->m_super->s_maxbytes)
+		length = mp->m_super->s_maxbytes - offset;
+	offset_fsb = XFS_B_TO_FSBT(mp, offset);
+	end_fsb = XFS_B_TO_FSB(mp, offset + length);
+
+	error = xfs_bmapi_read(ip, offset_fsb, end_fsb - offset_fsb, &imap,
+			       &nimaps, XFS_BMAPI_ENTIRE);
+	if (error) {
+		xfs_iunlock(ip, XFS_ILOCK_EXCL);
+		return error;
+	}
+
+	if ((flags & IOMAP_WRITE) && imap_needs_alloc(&imap, nimaps)) {
+		/*
+		 * We cap the maximum length we map here to MAX_WRITEBACK_PAGES
+		 * pages to keep the chunks of work done where somewhat symmetric
+		 * with the work writeback does. This is a completely arbitrary
+		 * number pulled out of thin air as a best guess for initial
+		 * testing.
+		 *
+		 * Note that the values needs to be less than 32-bits wide until
+		 * the lower level functions are updated.
+		 */
+		length = min_t(loff_t, length, 1024 * PAGE_SIZE);
+		if (xfs_get_extsz_hint(ip)) {
+			/*
+			 * xfs_iomap_write_direct() expects the shared lock. It
+			 * is unlocked on return.
+			 */
+			xfs_ilock_demote(ip, XFS_ILOCK_EXCL);
+			error = xfs_iomap_write_direct(ip, offset, length, &imap,
+					nimaps);
+		} else {
+			error = xfs_iomap_write_delay(ip, offset, length, &imap);
+			xfs_iunlock(ip, XFS_ILOCK_EXCL);
+		}
+
+		if (error)
+			return error;
+
+		trace_xfs_iomap_alloc(ip, offset, length, 0, &imap);
+		xfs_bmbt_to_iomap(ip, iomap, &imap);
+	} else if (nimaps) {
+		xfs_iunlock(ip, XFS_ILOCK_EXCL);
+		trace_xfs_iomap_found(ip, offset, length, 0, &imap);
+		xfs_bmbt_to_iomap(ip, iomap, &imap);
+	} else {
+		xfs_iunlock(ip, XFS_ILOCK_EXCL);
+		trace_xfs_iomap_not_found(ip, offset, length, 0, &imap);
+		iomap->blkno = IOMAP_NULL_BLOCK;
+		iomap->type = IOMAP_HOLE;
+		iomap->offset = offset;
+		iomap->length = length;
+	}
+
+	return 0;
+}
+
+static int
+xfs_file_iomap_end_delalloc(
+	struct xfs_inode	*ip,
+	loff_t			offset,
+	loff_t			length,
+	ssize_t			written)
+{
+	struct xfs_mount	*mp = ip->i_mount;
+	xfs_fileoff_t		start_fsb;
+	xfs_fileoff_t		end_fsb;
+	int			error = 0;
+
+	start_fsb = XFS_B_TO_FSB(mp, offset + written);
+	end_fsb = XFS_B_TO_FSB(mp, offset + length);
+
+	/*
+	 * Trim back delalloc blocks if we didn't manage to write the whole
+	 * range reserved.
+	 *
+	 * We don't need to care about racing delalloc as we hold i_mutex
+	 * across the reserve/allocate/unreserve calls. If there are delalloc
+	 * blocks in the range, they are ours.
+	 */
+	if (start_fsb < end_fsb) {
+		xfs_ilock(ip, XFS_ILOCK_EXCL);
+		error = xfs_bmap_punch_delalloc_range(ip, start_fsb,
+					       end_fsb - start_fsb);
+		xfs_iunlock(ip, XFS_ILOCK_EXCL);
+
+		if (error && !XFS_FORCED_SHUTDOWN(mp)) {
+			xfs_alert(mp, "%s: unable to clean up ino %lld",
+				__func__, ip->i_ino);
+			return error;
+		}
+	}
+
+	return 0;
+}
+
+static int
+xfs_file_iomap_end(
+	struct inode		*inode,
+	loff_t			offset,
+	loff_t			length,
+	ssize_t			written,
+	unsigned		flags,
+	struct iomap		*iomap)
+{
+	if ((flags & IOMAP_WRITE) && iomap->type == IOMAP_DELALLOC)
+		return xfs_file_iomap_end_delalloc(XFS_I(inode), offset,
+				length, written);
+	return 0;
+}
+
+struct iomap_ops xfs_iomap_ops = {
+	.iomap_begin		= xfs_file_iomap_begin,
+	.iomap_end		= xfs_file_iomap_end,
+};
diff --git a/fs/xfs/xfs_iomap.h b/fs/xfs/xfs_iomap.h
index 8688e66..e066d04 100644
--- a/fs/xfs/xfs_iomap.h
+++ b/fs/xfs/xfs_iomap.h
@@ -18,6 +18,8 @@
 #ifndef __XFS_IOMAP_H__
 #define __XFS_IOMAP_H__
 
+#include <linux/iomap.h>
+
 struct xfs_inode;
 struct xfs_bmbt_irec;
 
@@ -29,4 +31,9 @@
 			struct xfs_bmbt_irec *);
 int xfs_iomap_write_unwritten(struct xfs_inode *, xfs_off_t, xfs_off_t);
 
+void xfs_bmbt_to_iomap(struct xfs_inode *, struct iomap *,
+		struct xfs_bmbt_irec *);
+
+extern struct iomap_ops xfs_iomap_ops;
+
 #endif /* __XFS_IOMAP_H__*/
diff --git a/fs/xfs/xfs_iops.c b/fs/xfs/xfs_iops.c
index c5d4eba..ab820f8 100644
--- a/fs/xfs/xfs_iops.c
+++ b/fs/xfs/xfs_iops.c
@@ -38,12 +38,13 @@
 #include "xfs_dir2.h"
 #include "xfs_trans_space.h"
 #include "xfs_pnfs.h"
+#include "xfs_iomap.h"
 
 #include <linux/capability.h>
 #include <linux/xattr.h>
 #include <linux/posix_acl.h>
 #include <linux/security.h>
-#include <linux/fiemap.h>
+#include <linux/iomap.h>
 #include <linux/slab.h>
 
 /*
@@ -801,20 +802,30 @@
 		return error;
 
 	/*
+	 * Wait for all direct I/O to complete.
+	 */
+	inode_dio_wait(inode);
+
+	/*
 	 * File data changes must be complete before we start the transaction to
 	 * modify the inode.  This needs to be done before joining the inode to
 	 * the transaction because the inode cannot be unlocked once it is a
 	 * part of the transaction.
 	 *
-	 * Start with zeroing any data block beyond EOF that we may expose on
-	 * file extension.
+	 * Start with zeroing any data beyond EOF that we may expose on file
+	 * extension, or zeroing out the rest of the block on a downward
+	 * truncate.
 	 */
 	if (newsize > oldsize) {
 		error = xfs_zero_eof(ip, newsize, oldsize, &did_zeroing);
-		if (error)
-			return error;
+	} else {
+		error = iomap_truncate_page(inode, newsize, &did_zeroing,
+				&xfs_iomap_ops);
 	}
 
+	if (error)
+		return error;
+
 	/*
 	 * We are going to log the inode size change in this transaction so
 	 * any previous writes that are beyond the on disk EOF and the new
@@ -823,17 +834,14 @@
 	 * problem. Note that this includes any block zeroing we did above;
 	 * otherwise those blocks may not be zeroed after a crash.
 	 */
-	if (newsize > ip->i_d.di_size &&
-	    (oldsize != ip->i_d.di_size || did_zeroing)) {
+	if (did_zeroing ||
+	    (newsize > ip->i_d.di_size && oldsize != ip->i_d.di_size)) {
 		error = filemap_write_and_wait_range(VFS_I(ip)->i_mapping,
 						      ip->i_d.di_size, newsize);
 		if (error)
 			return error;
 	}
 
-	/* Now wait for all direct I/O to complete. */
-	inode_dio_wait(inode);
-
 	/*
 	 * We've already locked out new page faults, so now we can safely remove
 	 * pages from the page cache knowing they won't get refaulted until we
@@ -851,13 +859,6 @@
 	 * to hope that the caller sees ENOMEM and retries the truncate
 	 * operation.
 	 */
-	if (IS_DAX(inode))
-		error = dax_truncate_page(inode, newsize, xfs_get_blocks_direct);
-	else
-		error = block_truncate_page(inode->i_mapping, newsize,
-					    xfs_get_blocks);
-	if (error)
-		return error;
 	truncate_setsize(inode, newsize);
 
 	error = xfs_trans_alloc(mp, &M_RES(mp)->tr_itruncate, 0, 0, 0, &tp);
@@ -998,51 +999,6 @@
 	return xfs_trans_commit(tp);
 }
 
-#define XFS_FIEMAP_FLAGS	(FIEMAP_FLAG_SYNC|FIEMAP_FLAG_XATTR)
-
-/*
- * Call fiemap helper to fill in user data.
- * Returns positive errors to xfs_getbmap.
- */
-STATIC int
-xfs_fiemap_format(
-	void			**arg,
-	struct getbmapx		*bmv,
-	int			*full)
-{
-	int			error;
-	struct fiemap_extent_info *fieinfo = *arg;
-	u32			fiemap_flags = 0;
-	u64			logical, physical, length;
-
-	/* Do nothing for a hole */
-	if (bmv->bmv_block == -1LL)
-		return 0;
-
-	logical = BBTOB(bmv->bmv_offset);
-	physical = BBTOB(bmv->bmv_block);
-	length = BBTOB(bmv->bmv_length);
-
-	if (bmv->bmv_oflags & BMV_OF_PREALLOC)
-		fiemap_flags |= FIEMAP_EXTENT_UNWRITTEN;
-	else if (bmv->bmv_oflags & BMV_OF_DELALLOC) {
-		fiemap_flags |= (FIEMAP_EXTENT_DELALLOC |
-				 FIEMAP_EXTENT_UNKNOWN);
-		physical = 0;   /* no block yet */
-	}
-	if (bmv->bmv_oflags & BMV_OF_LAST)
-		fiemap_flags |= FIEMAP_EXTENT_LAST;
-
-	error = fiemap_fill_next_extent(fieinfo, logical, physical,
-					length, fiemap_flags);
-	if (error > 0) {
-		error = 0;
-		*full = 1;	/* user array now full */
-	}
-
-	return error;
-}
-
 STATIC int
 xfs_vn_fiemap(
 	struct inode		*inode,
@@ -1050,38 +1006,13 @@
 	u64			start,
 	u64			length)
 {
-	xfs_inode_t		*ip = XFS_I(inode);
-	struct getbmapx		bm;
 	int			error;
 
-	error = fiemap_check_flags(fieinfo, XFS_FIEMAP_FLAGS);
-	if (error)
-		return error;
+	xfs_ilock(XFS_I(inode), XFS_IOLOCK_SHARED);
+	error = iomap_fiemap(inode, fieinfo, start, length, &xfs_iomap_ops);
+	xfs_iunlock(XFS_I(inode), XFS_IOLOCK_SHARED);
 
-	/* Set up bmap header for xfs internal routine */
-	bm.bmv_offset = BTOBBT(start);
-	/* Special case for whole file */
-	if (length == FIEMAP_MAX_OFFSET)
-		bm.bmv_length = -1LL;
-	else
-		bm.bmv_length = BTOBB(start + length) - bm.bmv_offset;
-
-	/* We add one because in getbmap world count includes the header */
-	bm.bmv_count = !fieinfo->fi_extents_max ? MAXEXTNUM :
-					fieinfo->fi_extents_max + 1;
-	bm.bmv_count = min_t(__s32, bm.bmv_count,
-			     (PAGE_SIZE * 16 / sizeof(struct getbmapx)));
-	bm.bmv_iflags = BMV_IF_PREALLOC | BMV_IF_NO_HOLES;
-	if (fieinfo->fi_flags & FIEMAP_FLAG_XATTR)
-		bm.bmv_iflags |= BMV_IF_ATTRFORK;
-	if (!(fieinfo->fi_flags & FIEMAP_FLAG_SYNC))
-		bm.bmv_iflags |= BMV_IF_DELALLOC;
-
-	error = xfs_getbmap(ip, &bm, xfs_fiemap_format, fieinfo);
-	if (error)
-		return error;
-
-	return 0;
+	return error;
 }
 
 STATIC int
diff --git a/fs/xfs/xfs_log.c b/fs/xfs/xfs_log.c
index 216aaa2..3b74fa0 100644
--- a/fs/xfs/xfs_log.c
+++ b/fs/xfs/xfs_log.c
@@ -788,7 +788,7 @@
  * As far as I know, there weren't any dependencies on the old behaviour.
  */
 
-int
+static int
 xfs_log_unmount_write(xfs_mount_t *mp)
 {
 	struct xlog	 *log = mp->m_log;
@@ -1036,7 +1036,7 @@
  * there's no point in running a dummy transaction at this point because we
  * can't start trying to idle the log until both the CIL and AIL are empty.
  */
-int
+static int
 xfs_log_need_covered(xfs_mount_t *mp)
 {
 	struct xlog	*log = mp->m_log;
@@ -1177,7 +1177,7 @@
  * The log manager needs its own routine, in order to control what
  * happens with the buffer after the write completes.
  */
-void
+static void
 xlog_iodone(xfs_buf_t *bp)
 {
 	struct xlog_in_core	*iclog = bp->b_fspriv;
@@ -1302,7 +1302,7 @@
  * disk. If there is nothing dirty, then we might need to cover the log to
  * indicate that the filesystem is idle.
  */
-void
+static void
 xfs_log_worker(
 	struct work_struct	*work)
 {
diff --git a/fs/xfs/xfs_log.h b/fs/xfs/xfs_log.h
index 80ba0c0..b5e7107 100644
--- a/fs/xfs/xfs_log.h
+++ b/fs/xfs/xfs_log.h
@@ -163,12 +163,8 @@
 			  __uint8_t	   clientid,
 			  bool		   permanent);
 int	  xfs_log_regrant(struct xfs_mount *mp, struct xlog_ticket *tic);
-int	  xfs_log_unmount_write(struct xfs_mount *mp);
 void      xfs_log_unmount(struct xfs_mount *mp);
 int	  xfs_log_force_umount(struct xfs_mount *mp, int logerror);
-int	  xfs_log_need_covered(struct xfs_mount *mp);
-
-void	  xlog_iodone(struct xfs_buf *);
 
 struct xlog_ticket *xfs_log_ticket_get(struct xlog_ticket *ticket);
 void	  xfs_log_ticket_put(struct xlog_ticket *ticket);
@@ -178,7 +174,6 @@
 bool	xfs_log_item_in_current_chkpt(struct xfs_log_item *lip);
 
 void	xfs_log_work_queue(struct xfs_mount *mp);
-void	xfs_log_worker(struct work_struct *work);
 void	xfs_log_quiesce(struct xfs_mount *mp);
 bool	xfs_log_check_lsn(struct xfs_mount *, xfs_lsn_t);
 
diff --git a/fs/xfs/xfs_ondisk.h b/fs/xfs/xfs_ondisk.h
index 184c44e..17ec024 100644
--- a/fs/xfs/xfs_ondisk.h
+++ b/fs/xfs/xfs_ondisk.h
@@ -22,6 +22,11 @@
 	BUILD_BUG_ON_MSG(sizeof(structname) != (size), "XFS: sizeof(" \
 		#structname ") is wrong, expected " #size)
 
+#define XFS_CHECK_OFFSET(structname, member, off) \
+	BUILD_BUG_ON_MSG(offsetof(structname, member) != (off), \
+		"XFS: offsetof(" #structname ", " #member ") is wrong, " \
+		"expected " #off)
+
 static inline void __init
 xfs_check_ondisk_structs(void)
 {
@@ -34,6 +39,8 @@
 	XFS_CHECK_STRUCT_SIZE(struct xfs_bmbt_key,		8);
 	XFS_CHECK_STRUCT_SIZE(struct xfs_bmbt_rec,		16);
 	XFS_CHECK_STRUCT_SIZE(struct xfs_bmdr_block,		4);
+	XFS_CHECK_STRUCT_SIZE(struct xfs_btree_block_shdr,	48);
+	XFS_CHECK_STRUCT_SIZE(struct xfs_btree_block_lhdr,	64);
 	XFS_CHECK_STRUCT_SIZE(struct xfs_btree_block,		72);
 	XFS_CHECK_STRUCT_SIZE(struct xfs_dinode,		176);
 	XFS_CHECK_STRUCT_SIZE(struct xfs_disk_dquot,		104);
@@ -75,15 +82,28 @@
 	XFS_CHECK_STRUCT_SIZE(xfs_attr_leaf_name_remote_t,	12);
 	 */
 
+	XFS_CHECK_OFFSET(xfs_attr_leaf_name_local_t, valuelen,	0);
+	XFS_CHECK_OFFSET(xfs_attr_leaf_name_local_t, namelen,	2);
+	XFS_CHECK_OFFSET(xfs_attr_leaf_name_local_t, nameval,	3);
+	XFS_CHECK_OFFSET(xfs_attr_leaf_name_remote_t, valueblk,	0);
+	XFS_CHECK_OFFSET(xfs_attr_leaf_name_remote_t, valuelen,	4);
+	XFS_CHECK_OFFSET(xfs_attr_leaf_name_remote_t, namelen,	8);
+	XFS_CHECK_OFFSET(xfs_attr_leaf_name_remote_t, name,	9);
 	XFS_CHECK_STRUCT_SIZE(xfs_attr_leafblock_t,		40);
-	XFS_CHECK_STRUCT_SIZE(xfs_attr_shortform_t,		8);
+	XFS_CHECK_OFFSET(xfs_attr_shortform_t, hdr.totsize,	0);
+	XFS_CHECK_OFFSET(xfs_attr_shortform_t, hdr.count,	2);
+	XFS_CHECK_OFFSET(xfs_attr_shortform_t, list[0].namelen,	4);
+	XFS_CHECK_OFFSET(xfs_attr_shortform_t, list[0].valuelen, 5);
+	XFS_CHECK_OFFSET(xfs_attr_shortform_t, list[0].flags,	6);
+	XFS_CHECK_OFFSET(xfs_attr_shortform_t, list[0].nameval,	7);
 	XFS_CHECK_STRUCT_SIZE(xfs_da_blkinfo_t,			12);
 	XFS_CHECK_STRUCT_SIZE(xfs_da_intnode_t,			16);
 	XFS_CHECK_STRUCT_SIZE(xfs_da_node_entry_t,		8);
 	XFS_CHECK_STRUCT_SIZE(xfs_da_node_hdr_t,		16);
 	XFS_CHECK_STRUCT_SIZE(xfs_dir2_data_free_t,		4);
 	XFS_CHECK_STRUCT_SIZE(xfs_dir2_data_hdr_t,		16);
-	XFS_CHECK_STRUCT_SIZE(xfs_dir2_data_unused_t,		6);
+	XFS_CHECK_OFFSET(xfs_dir2_data_unused_t, freetag,	0);
+	XFS_CHECK_OFFSET(xfs_dir2_data_unused_t, length,	2);
 	XFS_CHECK_STRUCT_SIZE(xfs_dir2_free_hdr_t,		16);
 	XFS_CHECK_STRUCT_SIZE(xfs_dir2_free_t,			16);
 	XFS_CHECK_STRUCT_SIZE(xfs_dir2_ino4_t,			4);
@@ -94,6 +114,9 @@
 	XFS_CHECK_STRUCT_SIZE(xfs_dir2_leaf_t,			16);
 	XFS_CHECK_STRUCT_SIZE(xfs_dir2_leaf_tail_t,		4);
 	XFS_CHECK_STRUCT_SIZE(xfs_dir2_sf_entry_t,		3);
+	XFS_CHECK_OFFSET(xfs_dir2_sf_entry_t, namelen,		0);
+	XFS_CHECK_OFFSET(xfs_dir2_sf_entry_t, offset,		1);
+	XFS_CHECK_OFFSET(xfs_dir2_sf_entry_t, name,		3);
 	XFS_CHECK_STRUCT_SIZE(xfs_dir2_sf_hdr_t,		10);
 	XFS_CHECK_STRUCT_SIZE(xfs_dir2_sf_off_t,		2);
 
diff --git a/fs/xfs/xfs_pnfs.c b/fs/xfs/xfs_pnfs.c
index d5b7566..0f14b2e 100644
--- a/fs/xfs/xfs_pnfs.c
+++ b/fs/xfs/xfs_pnfs.c
@@ -1,6 +1,7 @@
 /*
  * Copyright (c) 2014 Christoph Hellwig.
  */
+#include <linux/iomap.h>
 #include "xfs.h"
 #include "xfs_format.h"
 #include "xfs_log_format.h"
@@ -79,32 +80,6 @@
 	return 0;
 }
 
-static void
-xfs_bmbt_to_iomap(
-	struct xfs_inode	*ip,
-	struct iomap		*iomap,
-	struct xfs_bmbt_irec	*imap)
-{
-	struct xfs_mount	*mp = ip->i_mount;
-
-	if (imap->br_startblock == HOLESTARTBLOCK) {
-		iomap->blkno = IOMAP_NULL_BLOCK;
-		iomap->type = IOMAP_HOLE;
-	} else if (imap->br_startblock == DELAYSTARTBLOCK) {
-		iomap->blkno = IOMAP_NULL_BLOCK;
-		iomap->type = IOMAP_DELALLOC;
-	} else {
-		iomap->blkno =
-			XFS_FSB_TO_DADDR(ip->i_mount, imap->br_startblock);
-		if (imap->br_state == XFS_EXT_UNWRITTEN)
-			iomap->type = IOMAP_UNWRITTEN;
-		else
-			iomap->type = IOMAP_MAPPED;
-	}
-	iomap->offset = XFS_FSB_TO_B(mp, imap->br_startoff);
-	iomap->length = XFS_FSB_TO_B(mp, imap->br_blockcount);
-}
-
 /*
  * Get a layout for the pNFS client.
  */
diff --git a/fs/xfs/xfs_rtalloc.h b/fs/xfs/xfs_rtalloc.h
index 76c0a4a..355dd9e 100644
--- a/fs/xfs/xfs_rtalloc.h
+++ b/fs/xfs/xfs_rtalloc.h
@@ -98,8 +98,6 @@
 /*
  * From xfs_rtbitmap.c
  */
-int xfs_rtbuf_get(struct xfs_mount *mp, struct xfs_trans *tp,
-		  xfs_rtblock_t block, int issum, struct xfs_buf **bpp);
 int xfs_rtcheck_range(struct xfs_mount *mp, struct xfs_trans *tp,
 		      xfs_rtblock_t start, xfs_extlen_t len, int val,
 		      xfs_rtblock_t *new, int *stat);
diff --git a/fs/xfs/xfs_super.c b/fs/xfs/xfs_super.c
index 11ea5d5..258b594 100644
--- a/fs/xfs/xfs_super.c
+++ b/fs/xfs/xfs_super.c
@@ -546,7 +546,7 @@
 
 	return 0;
 }
-__uint64_t
+static __uint64_t
 xfs_max_file_offset(
 	unsigned int		blockshift)
 {
@@ -1294,6 +1294,7 @@
 		 */
 		xfs_restore_resvblks(mp);
 		xfs_log_work_queue(mp);
+		xfs_queue_eofblocks(mp);
 	}
 
 	/* rw -> ro */
@@ -1306,6 +1307,13 @@
 		 * return it to the same size.
 		 */
 		xfs_save_resvblks(mp);
+
+		/*
+		 * Cancel background eofb scanning so it cannot race with the
+		 * final log force+buftarg wait and deadlock the remount.
+		 */
+		cancel_delayed_work_sync(&mp->m_eofblocks_work);
+
 		xfs_quiesce_attr(mp);
 		mp->m_flags |= XFS_MOUNT_RDONLY;
 	}
@@ -1692,8 +1700,9 @@
 	if (!xfs_log_ticket_zone)
 		goto out_free_ioend_bioset;
 
-	xfs_bmap_free_item_zone = kmem_zone_init(sizeof(xfs_bmap_free_item_t),
-						"xfs_bmap_free_item");
+	xfs_bmap_free_item_zone = kmem_zone_init(
+			sizeof(struct xfs_bmap_free_item),
+			"xfs_bmap_free_item");
 	if (!xfs_bmap_free_item_zone)
 		goto out_destroy_log_ticket_zone;
 
diff --git a/fs/xfs/xfs_super.h b/fs/xfs/xfs_super.h
index 2dfb1ce..529bce9 100644
--- a/fs/xfs/xfs_super.h
+++ b/fs/xfs/xfs_super.h
@@ -61,8 +61,6 @@
 struct xfs_buftarg;
 struct block_device;
 
-extern __uint64_t xfs_max_file_offset(unsigned int);
-
 extern void xfs_flush_inodes(struct xfs_mount *mp);
 extern void xfs_blkdev_issue_flush(struct xfs_buftarg *);
 extern xfs_agnumber_t xfs_set_inode_alloc(struct xfs_mount *,
diff --git a/fs/xfs/xfs_trace.h b/fs/xfs/xfs_trace.h
index ea94ee0..6787a9f 100644
--- a/fs/xfs/xfs_trace.h
+++ b/fs/xfs/xfs_trace.h
@@ -354,6 +354,7 @@
 DEFINE_BUF_EVENT(xfs_buf_bawrite);
 DEFINE_BUF_EVENT(xfs_buf_lock);
 DEFINE_BUF_EVENT(xfs_buf_lock_done);
+DEFINE_BUF_EVENT(xfs_buf_trylock_fail);
 DEFINE_BUF_EVENT(xfs_buf_trylock);
 DEFINE_BUF_EVENT(xfs_buf_unlock);
 DEFINE_BUF_EVENT(xfs_buf_iowait);
@@ -1295,6 +1296,9 @@
 DEFINE_IOMAP_EVENT(xfs_get_blocks_found);
 DEFINE_IOMAP_EVENT(xfs_get_blocks_alloc);
 DEFINE_IOMAP_EVENT(xfs_get_blocks_map_direct);
+DEFINE_IOMAP_EVENT(xfs_iomap_alloc);
+DEFINE_IOMAP_EVENT(xfs_iomap_found);
+DEFINE_IOMAP_EVENT(xfs_iomap_not_found);
 
 DECLARE_EVENT_CLASS(xfs_simple_io_class,
 	TP_PROTO(struct xfs_inode *ip, xfs_off_t offset, ssize_t count),
diff --git a/include/linux/exportfs.h b/include/linux/exportfs.h
index d841450..b03c062 100644
--- a/include/linux/exportfs.h
+++ b/include/linux/exportfs.h
@@ -6,6 +6,7 @@
 struct dentry;
 struct iattr;
 struct inode;
+struct iomap;
 struct super_block;
 struct vfsmount;
 
@@ -187,21 +188,6 @@
  *    get_name is not (which is possibly inconsistent)
  */
 
-/* types of block ranges for multipage write mappings. */
-#define IOMAP_HOLE	0x01	/* no blocks allocated, need allocation */
-#define IOMAP_DELALLOC	0x02	/* delayed allocation blocks */
-#define IOMAP_MAPPED	0x03	/* blocks allocated @blkno */
-#define IOMAP_UNWRITTEN	0x04	/* blocks allocated @blkno in unwritten state */
-
-#define IOMAP_NULL_BLOCK -1LL	/* blkno is not valid */
-
-struct iomap {
-	sector_t	blkno;	/* first sector of mapping */
-	loff_t		offset;	/* file offset of mapping, bytes */
-	u64		length;	/* length of mapping, bytes */
-	int		type;	/* type of mapping */
-};
-
 struct export_operations {
 	int (*encode_fh)(struct inode *inode, __u32 *fh, int *max_len,
 			struct inode *parent);
diff --git a/include/linux/iomap.h b/include/linux/iomap.h
new file mode 100644
index 0000000..3267df4
--- /dev/null
+++ b/include/linux/iomap.h
@@ -0,0 +1,70 @@
+#ifndef LINUX_IOMAP_H
+#define LINUX_IOMAP_H 1
+
+#include <linux/types.h>
+
+struct fiemap_extent_info;
+struct inode;
+struct iov_iter;
+struct kiocb;
+struct vm_area_struct;
+struct vm_fault;
+
+/*
+ * Types of block ranges for iomap mappings:
+ */
+#define IOMAP_HOLE	0x01	/* no blocks allocated, need allocation */
+#define IOMAP_DELALLOC	0x02	/* delayed allocation blocks */
+#define IOMAP_MAPPED	0x03	/* blocks allocated @blkno */
+#define IOMAP_UNWRITTEN	0x04	/* blocks allocated @blkno in unwritten state */
+
+/*
+ * Magic value for blkno:
+ */
+#define IOMAP_NULL_BLOCK -1LL	/* blkno is not valid */
+
+struct iomap {
+	sector_t		blkno;	/* 1st sector of mapping, 512b units */
+	loff_t			offset;	/* file offset of mapping, bytes */
+	u64			length;	/* length of mapping, bytes */
+	int			type;	/* type of mapping */
+	struct block_device	*bdev;	/* block device for I/O */
+};
+
+/*
+ * Flags for iomap_begin / iomap_end.  No flag implies a read.
+ */
+#define IOMAP_WRITE		(1 << 0)
+#define IOMAP_ZERO		(1 << 1)
+
+struct iomap_ops {
+	/*
+	 * Return the existing mapping at pos, or reserve space starting at
+	 * pos for up to length, as long as we can do it as a single mapping.
+	 * The actual length is returned in iomap->length.
+	 */
+	int (*iomap_begin)(struct inode *inode, loff_t pos, loff_t length,
+			unsigned flags, struct iomap *iomap);
+
+	/*
+	 * Commit and/or unreserve space previous allocated using iomap_begin.
+	 * Written indicates the length of the successful write operation which
+	 * needs to be commited, while the rest needs to be unreserved.
+	 * Written might be zero if no data was written.
+	 */
+	int (*iomap_end)(struct inode *inode, loff_t pos, loff_t length,
+			ssize_t written, unsigned flags, struct iomap *iomap);
+};
+
+ssize_t iomap_file_buffered_write(struct kiocb *iocb, struct iov_iter *from,
+		struct iomap_ops *ops);
+int iomap_zero_range(struct inode *inode, loff_t pos, loff_t len,
+		bool *did_zero, struct iomap_ops *ops);
+int iomap_truncate_page(struct inode *inode, loff_t pos, bool *did_zero,
+		struct iomap_ops *ops);
+int iomap_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf,
+		struct iomap_ops *ops);
+int iomap_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo,
+		loff_t start, loff_t len, struct iomap_ops *ops);
+
+#endif /* LINUX_IOMAP_H */