Merge branch 'master' into for-next

Fast-forward merge with Linus to be able to merge patches
based on more recent version of the tree.

36 files changed, 4634 insertions, 575 deletions

diff --git a/fs/nfs/Kconfig b/fs/nfs/Kconfig
index 81515545ba75..dbcd82126aed 100644
--- a/fs/nfs/Kconfig
+++ b/fs/nfs/Kconfig
@@ -77,6 +77,7 @@ config NFS_V4
 config NFS_V4_1
 	bool "NFS client support for NFSv4.1 (EXPERIMENTAL)"
 	depends on NFS_FS && NFS_V4 && EXPERIMENTAL
+	select SUNRPC_BACKCHANNEL
 	select PNFS_FILE_LAYOUT
 	help
 	  This option enables support for minor version 1 of the NFSv4 protocol
@@ -87,15 +88,15 @@ config NFS_V4_1
 config PNFS_FILE_LAYOUT
 	tristate
 
+config PNFS_BLOCK
+	tristate
+	depends on NFS_FS && NFS_V4_1 && BLK_DEV_DM
+	default m
+
 config PNFS_OBJLAYOUT
-	tristate "Provide support for the pNFS Objects Layout Driver for NFSv4.1 pNFS (EXPERIMENTAL)"
+	tristate
 	depends on NFS_FS && NFS_V4_1 && SCSI_OSD_ULD
-	help
-	  Say M here if you want your pNFS client to support the Objects Layout Driver.
-	  Requires the SCSI osd initiator library (SCSI_OSD_INITIATOR) and
-	  upper level driver (SCSI_OSD_ULD).
-
-	  If unsure, say N.
+	default m
 
 config ROOT_NFS
 	bool "Root file system on NFS"
diff --git a/fs/nfs/Makefile b/fs/nfs/Makefile
index 6a34f7dd0e6f..b58613d0abb3 100644
--- a/fs/nfs/Makefile
+++ b/fs/nfs/Makefile
@@ -23,3 +23,4 @@ obj-$(CONFIG_PNFS_FILE_LAYOUT) += nfs_layout_nfsv41_files.o
 nfs_layout_nfsv41_files-y := nfs4filelayout.o nfs4filelayoutdev.o
 
 obj-$(CONFIG_PNFS_OBJLAYOUT) += objlayout/
+obj-$(CONFIG_PNFS_BLOCK) += blocklayout/
diff --git a/fs/nfs/blocklayout/Makefile b/fs/nfs/blocklayout/Makefile
new file mode 100644
index 000000000000..d5815505c020
--- /dev/null
+++ b/fs/nfs/blocklayout/Makefile
@@ -0,0 +1,5 @@
+#
+# Makefile for the pNFS block layout driver kernel module
+#
+obj-$(CONFIG_PNFS_BLOCK) += blocklayoutdriver.o
+blocklayoutdriver-objs := blocklayout.o extents.o blocklayoutdev.o blocklayoutdm.o
diff --git a/fs/nfs/blocklayout/blocklayout.c b/fs/nfs/blocklayout/blocklayout.c
new file mode 100644
index 000000000000..9561c8fc8bdb
--- /dev/null
+++ b/fs/nfs/blocklayout/blocklayout.c
@@ -0,0 +1,1020 @@
+/*
+ *  linux/fs/nfs/blocklayout/blocklayout.c
+ *
+ *  Module for the NFSv4.1 pNFS block layout driver.
+ *
+ *  Copyright (c) 2006 The Regents of the University of Michigan.
+ *  All rights reserved.
+ *
+ *  Andy Adamson <andros@citi.umich.edu>
+ *  Fred Isaman <iisaman@umich.edu>
+ *
+ * permission is granted to use, copy, create derivative works and
+ * redistribute this software and such derivative works for any purpose,
+ * so long as the name of the university of michigan is not used in
+ * any advertising or publicity pertaining to the use or distribution
+ * of this software without specific, written prior authorization.  if
+ * the above copyright notice or any other identification of the
+ * university of michigan is included in any copy of any portion of
+ * this software, then the disclaimer below must also be included.
+ *
+ * this software is provided as is, without representation from the
+ * university of michigan as to its fitness for any purpose, and without
+ * warranty by the university of michigan of any kind, either express
+ * or implied, including without limitation the implied warranties of
+ * merchantability and fitness for a particular purpose.  the regents
+ * of the university of michigan shall not be liable for any damages,
+ * including special, indirect, incidental, or consequential damages,
+ * with respect to any claim arising out or in connection with the use
+ * of the software, even if it has been or is hereafter advised of the
+ * possibility of such damages.
+ */
+
+#include <linux/module.h>
+#include <linux/init.h>
+#include <linux/mount.h>
+#include <linux/namei.h>
+#include <linux/bio.h>		/* struct bio */
+#include <linux/buffer_head.h>	/* various write calls */
+#include <linux/prefetch.h>
+
+#include "blocklayout.h"
+
+#define NFSDBG_FACILITY	NFSDBG_PNFS_LD
+
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Andy Adamson <andros@citi.umich.edu>");
+MODULE_DESCRIPTION("The NFSv4.1 pNFS Block layout driver");
+
+struct dentry *bl_device_pipe;
+wait_queue_head_t bl_wq;
+
+static void print_page(struct page *page)
+{
+	dprintk("PRINTPAGE page %p\n", page);
+	dprintk("	PagePrivate %d\n", PagePrivate(page));
+	dprintk("	PageUptodate %d\n", PageUptodate(page));
+	dprintk("	PageError %d\n", PageError(page));
+	dprintk("	PageDirty %d\n", PageDirty(page));
+	dprintk("	PageReferenced %d\n", PageReferenced(page));
+	dprintk("	PageLocked %d\n", PageLocked(page));
+	dprintk("	PageWriteback %d\n", PageWriteback(page));
+	dprintk("	PageMappedToDisk %d\n", PageMappedToDisk(page));
+	dprintk("\n");
+}
+
+/* Given the be associated with isect, determine if page data needs to be
+ * initialized.
+ */
+static int is_hole(struct pnfs_block_extent *be, sector_t isect)
+{
+	if (be->be_state == PNFS_BLOCK_NONE_DATA)
+		return 1;
+	else if (be->be_state != PNFS_BLOCK_INVALID_DATA)
+		return 0;
+	else
+		return !bl_is_sector_init(be->be_inval, isect);
+}
+
+/* Given the be associated with isect, determine if page data can be
+ * written to disk.
+ */
+static int is_writable(struct pnfs_block_extent *be, sector_t isect)
+{
+	return (be->be_state == PNFS_BLOCK_READWRITE_DATA ||
+		be->be_state == PNFS_BLOCK_INVALID_DATA);
+}
+
+/* The data we are handed might be spread across several bios.  We need
+ * to track when the last one is finished.
+ */
+struct parallel_io {
+	struct kref refcnt;
+	struct rpc_call_ops call_ops;
+	void (*pnfs_callback) (void *data);
+	void *data;
+};
+
+static inline struct parallel_io *alloc_parallel(void *data)
+{
+	struct parallel_io *rv;
+
+	rv  = kmalloc(sizeof(*rv), GFP_NOFS);
+	if (rv) {
+		rv->data = data;
+		kref_init(&rv->refcnt);
+	}
+	return rv;
+}
+
+static inline void get_parallel(struct parallel_io *p)
+{
+	kref_get(&p->refcnt);
+}
+
+static void destroy_parallel(struct kref *kref)
+{
+	struct parallel_io *p = container_of(kref, struct parallel_io, refcnt);
+
+	dprintk("%s enter\n", __func__);
+	p->pnfs_callback(p->data);
+	kfree(p);
+}
+
+static inline void put_parallel(struct parallel_io *p)
+{
+	kref_put(&p->refcnt, destroy_parallel);
+}
+
+static struct bio *
+bl_submit_bio(int rw, struct bio *bio)
+{
+	if (bio) {
+		get_parallel(bio->bi_private);
+		dprintk("%s submitting %s bio %u@%llu\n", __func__,
+			rw == READ ? "read" : "write",
+			bio->bi_size, (unsigned long long)bio->bi_sector);
+		submit_bio(rw, bio);
+	}
+	return NULL;
+}
+
+static struct bio *bl_alloc_init_bio(int npg, sector_t isect,
+				     struct pnfs_block_extent *be,
+				     void (*end_io)(struct bio *, int err),
+				     struct parallel_io *par)
+{
+	struct bio *bio;
+
+	bio = bio_alloc(GFP_NOIO, npg);
+	if (!bio)
+		return NULL;
+
+	bio->bi_sector = isect - be->be_f_offset + be->be_v_offset;
+	bio->bi_bdev = be->be_mdev;
+	bio->bi_end_io = end_io;
+	bio->bi_private = par;
+	return bio;
+}
+
+static struct bio *bl_add_page_to_bio(struct bio *bio, int npg, int rw,
+				      sector_t isect, struct page *page,
+				      struct pnfs_block_extent *be,
+				      void (*end_io)(struct bio *, int err),
+				      struct parallel_io *par)
+{
+retry:
+	if (!bio) {
+		bio = bl_alloc_init_bio(npg, isect, be, end_io, par);
+		if (!bio)
+			return ERR_PTR(-ENOMEM);
+	}
+	if (bio_add_page(bio, page, PAGE_CACHE_SIZE, 0) < PAGE_CACHE_SIZE) {
+		bio = bl_submit_bio(rw, bio);
+		goto retry;
+	}
+	return bio;
+}
+
+static void bl_set_lo_fail(struct pnfs_layout_segment *lseg)
+{
+	if (lseg->pls_range.iomode == IOMODE_RW) {
+		dprintk("%s Setting layout IOMODE_RW fail bit\n", __func__);
+		set_bit(lo_fail_bit(IOMODE_RW), &lseg->pls_layout->plh_flags);
+	} else {
+		dprintk("%s Setting layout IOMODE_READ fail bit\n", __func__);
+		set_bit(lo_fail_bit(IOMODE_READ), &lseg->pls_layout->plh_flags);
+	}
+}
+
+/* This is basically copied from mpage_end_io_read */
+static void bl_end_io_read(struct bio *bio, int err)
+{
+	struct parallel_io *par = bio->bi_private;
+	const int uptodate = test_bit(BIO_UPTODATE, &bio->bi_flags);
+	struct bio_vec *bvec = bio->bi_io_vec + bio->bi_vcnt - 1;
+	struct nfs_read_data *rdata = (struct nfs_read_data *)par->data;
+
+	do {
+		struct page *page = bvec->bv_page;
+
+		if (--bvec >= bio->bi_io_vec)
+			prefetchw(&bvec->bv_page->flags);
+		if (uptodate)
+			SetPageUptodate(page);
+	} while (bvec >= bio->bi_io_vec);
+	if (!uptodate) {
+		if (!rdata->pnfs_error)
+			rdata->pnfs_error = -EIO;
+		bl_set_lo_fail(rdata->lseg);
+	}
+	bio_put(bio);
+	put_parallel(par);
+}
+
+static void bl_read_cleanup(struct work_struct *work)
+{
+	struct rpc_task *task;
+	struct nfs_read_data *rdata;
+	dprintk("%s enter\n", __func__);
+	task = container_of(work, struct rpc_task, u.tk_work);
+	rdata = container_of(task, struct nfs_read_data, task);
+	pnfs_ld_read_done(rdata);
+}
+
+static void
+bl_end_par_io_read(void *data)
+{
+	struct nfs_read_data *rdata = data;
+
+	INIT_WORK(&rdata->task.u.tk_work, bl_read_cleanup);
+	schedule_work(&rdata->task.u.tk_work);
+}
+
+/* We don't want normal .rpc_call_done callback used, so we replace it
+ * with this stub.
+ */
+static void bl_rpc_do_nothing(struct rpc_task *task, void *calldata)
+{
+	return;
+}
+
+static enum pnfs_try_status
+bl_read_pagelist(struct nfs_read_data *rdata)
+{
+	int i, hole;
+	struct bio *bio = NULL;
+	struct pnfs_block_extent *be = NULL, *cow_read = NULL;
+	sector_t isect, extent_length = 0;
+	struct parallel_io *par;
+	loff_t f_offset = rdata->args.offset;
+	size_t count = rdata->args.count;
+	struct page **pages = rdata->args.pages;
+	int pg_index = rdata->args.pgbase >> PAGE_CACHE_SHIFT;
+
+	dprintk("%s enter nr_pages %u offset %lld count %Zd\n", __func__,
+	       rdata->npages, f_offset, count);
+
+	par = alloc_parallel(rdata);
+	if (!par)
+		goto use_mds;
+	par->call_ops = *rdata->mds_ops;
+	par->call_ops.rpc_call_done = bl_rpc_do_nothing;
+	par->pnfs_callback = bl_end_par_io_read;
+	/* At this point, we can no longer jump to use_mds */
+
+	isect = (sector_t) (f_offset >> SECTOR_SHIFT);
+	/* Code assumes extents are page-aligned */
+	for (i = pg_index; i < rdata->npages; i++) {
+		if (!extent_length) {
+			/* We've used up the previous extent */
+			bl_put_extent(be);
+			bl_put_extent(cow_read);
+			bio = bl_submit_bio(READ, bio);
+			/* Get the next one */
+			be = bl_find_get_extent(BLK_LSEG2EXT(rdata->lseg),
+					     isect, &cow_read);
+			if (!be) {
+				rdata->pnfs_error = -EIO;
+				goto out;
+			}
+			extent_length = be->be_length -
+				(isect - be->be_f_offset);
+			if (cow_read) {
+				sector_t cow_length = cow_read->be_length -
+					(isect - cow_read->be_f_offset);
+				extent_length = min(extent_length, cow_length);
+			}
+		}
+		hole = is_hole(be, isect);
+		if (hole && !cow_read) {
+			bio = bl_submit_bio(READ, bio);
+			/* Fill hole w/ zeroes w/o accessing device */
+			dprintk("%s Zeroing page for hole\n", __func__);
+			zero_user_segment(pages[i], 0, PAGE_CACHE_SIZE);
+			print_page(pages[i]);
+			SetPageUptodate(pages[i]);
+		} else {
+			struct pnfs_block_extent *be_read;
+
+			be_read = (hole && cow_read) ? cow_read : be;
+			bio = bl_add_page_to_bio(bio, rdata->npages - i, READ,
+						 isect, pages[i], be_read,
+						 bl_end_io_read, par);
+			if (IS_ERR(bio)) {
+				rdata->pnfs_error = PTR_ERR(bio);
+				goto out;
+			}
+		}
+		isect += PAGE_CACHE_SECTORS;
+		extent_length -= PAGE_CACHE_SECTORS;
+	}
+	if ((isect << SECTOR_SHIFT) >= rdata->inode->i_size) {
+		rdata->res.eof = 1;
+		rdata->res.count = rdata->inode->i_size - f_offset;
+	} else {
+		rdata->res.count = (isect << SECTOR_SHIFT) - f_offset;
+	}
+out:
+	bl_put_extent(be);
+	bl_put_extent(cow_read);
+	bl_submit_bio(READ, bio);
+	put_parallel(par);
+	return PNFS_ATTEMPTED;
+
+ use_mds:
+	dprintk("Giving up and using normal NFS\n");
+	return PNFS_NOT_ATTEMPTED;
+}
+
+static void mark_extents_written(struct pnfs_block_layout *bl,
+				 __u64 offset, __u32 count)
+{
+	sector_t isect, end;
+	struct pnfs_block_extent *be;
+
+	dprintk("%s(%llu, %u)\n", __func__, offset, count);
+	if (count == 0)
+		return;
+	isect = (offset & (long)(PAGE_CACHE_MASK)) >> SECTOR_SHIFT;
+	end = (offset + count + PAGE_CACHE_SIZE - 1) & (long)(PAGE_CACHE_MASK);
+	end >>= SECTOR_SHIFT;
+	while (isect < end) {
+		sector_t len;
+		be = bl_find_get_extent(bl, isect, NULL);
+		BUG_ON(!be); /* FIXME */
+		len = min(end, be->be_f_offset + be->be_length) - isect;
+		if (be->be_state == PNFS_BLOCK_INVALID_DATA)
+			bl_mark_for_commit(be, isect, len); /* What if fails? */
+		isect += len;
+		bl_put_extent(be);
+	}
+}
+
+static void bl_end_io_write_zero(struct bio *bio, int err)
+{
+	struct parallel_io *par = bio->bi_private;
+	const int uptodate = test_bit(BIO_UPTODATE, &bio->bi_flags);
+	struct bio_vec *bvec = bio->bi_io_vec + bio->bi_vcnt - 1;
+	struct nfs_write_data *wdata = (struct nfs_write_data *)par->data;
+
+	do {
+		struct page *page = bvec->bv_page;
+
+		if (--bvec >= bio->bi_io_vec)
+			prefetchw(&bvec->bv_page->flags);
+		/* This is the zeroing page we added */
+		end_page_writeback(page);
+		page_cache_release(page);
+	} while (bvec >= bio->bi_io_vec);
+	if (!uptodate) {
+		if (!wdata->pnfs_error)
+			wdata->pnfs_error = -EIO;
+		bl_set_lo_fail(wdata->lseg);
+	}
+	bio_put(bio);
+	put_parallel(par);
+}
+
+/* This is basically copied from mpage_end_io_read */
+static void bl_end_io_write(struct bio *bio, int err)
+{
+	struct parallel_io *par = bio->bi_private;
+	const int uptodate = test_bit(BIO_UPTODATE, &bio->bi_flags);
+	struct nfs_write_data *wdata = (struct nfs_write_data *)par->data;
+
+	if (!uptodate) {
+		if (!wdata->pnfs_error)
+			wdata->pnfs_error = -EIO;
+		bl_set_lo_fail(wdata->lseg);
+	}
+	bio_put(bio);
+	put_parallel(par);
+}
+
+/* Function scheduled for call during bl_end_par_io_write,
+ * it marks sectors as written and extends the commitlist.
+ */
+static void bl_write_cleanup(struct work_struct *work)
+{
+	struct rpc_task *task;
+	struct nfs_write_data *wdata;
+	dprintk("%s enter\n", __func__);
+	task = container_of(work, struct rpc_task, u.tk_work);
+	wdata = container_of(task, struct nfs_write_data, task);
+	if (!wdata->pnfs_error) {
+		/* Marks for LAYOUTCOMMIT */
+		mark_extents_written(BLK_LSEG2EXT(wdata->lseg),
+				     wdata->args.offset, wdata->args.count);
+	}
+	pnfs_ld_write_done(wdata);
+}
+
+/* Called when last of bios associated with a bl_write_pagelist call finishes */
+static void bl_end_par_io_write(void *data)
+{
+	struct nfs_write_data *wdata = data;
+
+	wdata->task.tk_status = 0;
+	wdata->verf.committed = NFS_FILE_SYNC;
+	INIT_WORK(&wdata->task.u.tk_work, bl_write_cleanup);
+	schedule_work(&wdata->task.u.tk_work);
+}
+
+/* FIXME STUB - mark intersection of layout and page as bad, so is not
+ * used again.
+ */
+static void mark_bad_read(void)
+{
+	return;
+}
+
+/*
+ * map_block:  map a requested I/0 block (isect) into an offset in the LVM
+ * block_device
+ */
+static void
+map_block(struct buffer_head *bh, sector_t isect, struct pnfs_block_extent *be)
+{
+	dprintk("%s enter be=%p\n", __func__, be);
+
+	set_buffer_mapped(bh);
+	bh->b_bdev = be->be_mdev;
+	bh->b_blocknr = (isect - be->be_f_offset + be->be_v_offset) >>
+	    (be->be_mdev->bd_inode->i_blkbits - SECTOR_SHIFT);
+
+	dprintk("%s isect %llu, bh->b_blocknr %ld, using bsize %Zd\n",
+		__func__, (unsigned long long)isect, (long)bh->b_blocknr,
+		bh->b_size);
+	return;
+}
+
+/* Given an unmapped page, zero it or read in page for COW, page is locked
+ * by caller.
+ */
+static int
+init_page_for_write(struct page *page, struct pnfs_block_extent *cow_read)
+{
+	struct buffer_head *bh = NULL;
+	int ret = 0;
+	sector_t isect;
+
+	dprintk("%s enter, %p\n", __func__, page);
+	BUG_ON(PageUptodate(page));
+	if (!cow_read) {
+		zero_user_segment(page, 0, PAGE_SIZE);
+		SetPageUptodate(page);
+		goto cleanup;
+	}
+
+	bh = alloc_page_buffers(page, PAGE_CACHE_SIZE, 0);
+	if (!bh) {
+		ret = -ENOMEM;
+		goto cleanup;
+	}
+
+	isect = (sector_t) page->index << PAGE_CACHE_SECTOR_SHIFT;
+	map_block(bh, isect, cow_read);
+	if (!bh_uptodate_or_lock(bh))
+		ret = bh_submit_read(bh);
+	if (ret)
+		goto cleanup;
+	SetPageUptodate(page);
+
+cleanup:
+	bl_put_extent(cow_read);
+	if (bh)
+		free_buffer_head(bh);
+	if (ret) {
+		/* Need to mark layout with bad read...should now
+		 * just use nfs4 for reads and writes.
+		 */
+		mark_bad_read();
+	}
+	return ret;
+}
+
+static enum pnfs_try_status
+bl_write_pagelist(struct nfs_write_data *wdata, int sync)
+{
+	int i, ret, npg_zero, pg_index, last = 0;
+	struct bio *bio = NULL;
+	struct pnfs_block_extent *be = NULL, *cow_read = NULL;
+	sector_t isect, last_isect = 0, extent_length = 0;
+	struct parallel_io *par;
+	loff_t offset = wdata->args.offset;
+	size_t count = wdata->args.count;
+	struct page **pages = wdata->args.pages;
+	struct page *page;
+	pgoff_t index;
+	u64 temp;
+	int npg_per_block =
+	    NFS_SERVER(wdata->inode)->pnfs_blksize >> PAGE_CACHE_SHIFT;
+
+	dprintk("%s enter, %Zu@%lld\n", __func__, count, offset);
+	/* At this point, wdata->pages is a (sequential) list of nfs_pages.
+	 * We want to write each, and if there is an error set pnfs_error
+	 * to have it redone using nfs.
+	 */
+	par = alloc_parallel(wdata);
+	if (!par)
+		return PNFS_NOT_ATTEMPTED;
+	par->call_ops = *wdata->mds_ops;
+	par->call_ops.rpc_call_done = bl_rpc_do_nothing;
+	par->pnfs_callback = bl_end_par_io_write;
+	/* At this point, have to be more careful with error handling */
+
+	isect = (sector_t) ((offset & (long)PAGE_CACHE_MASK) >> SECTOR_SHIFT);
+	be = bl_find_get_extent(BLK_LSEG2EXT(wdata->lseg), isect, &cow_read);
+	if (!be || !is_writable(be, isect)) {
+		dprintk("%s no matching extents!\n", __func__);
+		wdata->pnfs_error = -EINVAL;
+		goto out;
+	}
+
+	/* First page inside INVALID extent */
+	if (be->be_state == PNFS_BLOCK_INVALID_DATA) {
+		temp = offset >> PAGE_CACHE_SHIFT;
+		npg_zero = do_div(temp, npg_per_block);
+		isect = (sector_t) (((offset - npg_zero * PAGE_CACHE_SIZE) &
+				     (long)PAGE_CACHE_MASK) >> SECTOR_SHIFT);
+		extent_length = be->be_length - (isect - be->be_f_offset);
+
+fill_invalid_ext:
+		dprintk("%s need to zero %d pages\n", __func__, npg_zero);
+		for (;npg_zero > 0; npg_zero--) {
+			/* page ref released in bl_end_io_write_zero */
+			index = isect >> PAGE_CACHE_SECTOR_SHIFT;
+			dprintk("%s zero %dth page: index %lu isect %llu\n",
+				__func__, npg_zero, index,
+				(unsigned long long)isect);
+			page =
+			    find_or_create_page(wdata->inode->i_mapping, index,
+						GFP_NOFS);
+			if (!page) {
+				dprintk("%s oom\n", __func__);
+				wdata->pnfs_error = -ENOMEM;
+				goto out;
+			}
+
+			/* PageDirty: Other will write this out
+			 * PageWriteback: Other is writing this out
+			 * PageUptodate: It was read before
+			 * sector_initialized: already written out
+			 */
+			if (PageDirty(page) || PageWriteback(page) ||
+			    bl_is_sector_init(be->be_inval, isect)) {
+				print_page(page);
+				unlock_page(page);
+				page_cache_release(page);
+				goto next_page;
+			}
+			if (!PageUptodate(page)) {
+				/* New page, readin or zero it */
+				init_page_for_write(page, cow_read);
+			}
+			set_page_writeback(page);
+			unlock_page(page);
+
+			ret = bl_mark_sectors_init(be->be_inval, isect,
+						       PAGE_CACHE_SECTORS,
+						       NULL);
+			if (unlikely(ret)) {
+				dprintk("%s bl_mark_sectors_init fail %d\n",
+					__func__, ret);
+				end_page_writeback(page);
+				page_cache_release(page);
+				wdata->pnfs_error = ret;
+				goto out;
+			}
+			bio = bl_add_page_to_bio(bio, npg_zero, WRITE,
+						 isect, page, be,
+						 bl_end_io_write_zero, par);
+			if (IS_ERR(bio)) {
+				wdata->pnfs_error = PTR_ERR(bio);
+				goto out;
+			}
+			/* FIXME: This should be done in bi_end_io */
+			mark_extents_written(BLK_LSEG2EXT(wdata->lseg),
+					     page->index << PAGE_CACHE_SHIFT,
+					     PAGE_CACHE_SIZE);
+next_page:
+			isect += PAGE_CACHE_SECTORS;
+			extent_length -= PAGE_CACHE_SECTORS;
+		}
+		if (last)
+			goto write_done;
+	}
+	bio = bl_submit_bio(WRITE, bio);
+
+	/* Middle pages */
+	pg_index = wdata->args.pgbase >> PAGE_CACHE_SHIFT;
+	for (i = pg_index; i < wdata->npages; i++) {
+		if (!extent_length) {
+			/* We've used up the previous extent */
+			bl_put_extent(be);
+			bio = bl_submit_bio(WRITE, bio);
+			/* Get the next one */
+			be = bl_find_get_extent(BLK_LSEG2EXT(wdata->lseg),
+					     isect, NULL);
+			if (!be || !is_writable(be, isect)) {
+				wdata->pnfs_error = -EINVAL;
+				goto out;
+			}
+			extent_length = be->be_length -
+			    (isect - be->be_f_offset);
+		}
+		if (be->be_state == PNFS_BLOCK_INVALID_DATA) {
+			ret = bl_mark_sectors_init(be->be_inval, isect,
+						       PAGE_CACHE_SECTORS,
+						       NULL);
+			if (unlikely(ret)) {
+				dprintk("%s bl_mark_sectors_init fail %d\n",
+					__func__, ret);
+				wdata->pnfs_error = ret;
+				goto out;
+			}
+		}
+		bio = bl_add_page_to_bio(bio, wdata->npages - i, WRITE,
+					 isect, pages[i], be,
+					 bl_end_io_write, par);
+		if (IS_ERR(bio)) {
+			wdata->pnfs_error = PTR_ERR(bio);
+			goto out;
+		}
+		isect += PAGE_CACHE_SECTORS;
+		last_isect = isect;
+		extent_length -= PAGE_CACHE_SECTORS;
+	}
+
+	/* Last page inside INVALID extent */
+	if (be->be_state == PNFS_BLOCK_INVALID_DATA) {
+		bio = bl_submit_bio(WRITE, bio);
+		temp = last_isect >> PAGE_CACHE_SECTOR_SHIFT;
+		npg_zero = npg_per_block - do_div(temp, npg_per_block);
+		if (npg_zero < npg_per_block) {
+			last = 1;
+			goto fill_invalid_ext;
+		}
+	}
+
+write_done:
+	wdata->res.count = (last_isect << SECTOR_SHIFT) - (offset);
+	if (count < wdata->res.count) {
+		wdata->res.count = count;
+	}
+out:
+	bl_put_extent(be);
+	bl_submit_bio(WRITE, bio);
+	put_parallel(par);
+	return PNFS_ATTEMPTED;
+}
+
+/* FIXME - range ignored */
+static void
+release_extents(struct pnfs_block_layout *bl, struct pnfs_layout_range *range)
+{
+	int i;
+	struct pnfs_block_extent *be;
+
+	spin_lock(&bl->bl_ext_lock);
+	for (i = 0; i < EXTENT_LISTS; i++) {
+		while (!list_empty(&bl->bl_extents[i])) {
+			be = list_first_entry(&bl->bl_extents[i],
+					      struct pnfs_block_extent,
+					      be_node);
+			list_del(&be->be_node);
+			bl_put_extent(be);
+		}
+	}
+	spin_unlock(&bl->bl_ext_lock);
+}
+
+static void
+release_inval_marks(struct pnfs_inval_markings *marks)
+{
+	struct pnfs_inval_tracking *pos, *temp;
+
+	list_for_each_entry_safe(pos, temp, &marks->im_tree.mtt_stub, it_link) {
+		list_del(&pos->it_link);
+		kfree(pos);
+	}
+	return;
+}
+
+static void bl_free_layout_hdr(struct pnfs_layout_hdr *lo)
+{
+	struct pnfs_block_layout *bl = BLK_LO2EXT(lo);
+
+	dprintk("%s enter\n", __func__);
+	release_extents(bl, NULL);
+	release_inval_marks(&bl->bl_inval);
+	kfree(bl);
+}
+
+static struct pnfs_layout_hdr *bl_alloc_layout_hdr(struct inode *inode,
+						   gfp_t gfp_flags)
+{
+	struct pnfs_block_layout *bl;
+
+	dprintk("%s enter\n", __func__);
+	bl = kzalloc(sizeof(*bl), gfp_flags);
+	if (!bl)
+		return NULL;
+	spin_lock_init(&bl->bl_ext_lock);
+	INIT_LIST_HEAD(&bl->bl_extents[0]);
+	INIT_LIST_HEAD(&bl->bl_extents[1]);
+	INIT_LIST_HEAD(&bl->bl_commit);
+	INIT_LIST_HEAD(&bl->bl_committing);
+	bl->bl_count = 0;
+	bl->bl_blocksize = NFS_SERVER(inode)->pnfs_blksize >> SECTOR_SHIFT;
+	BL_INIT_INVAL_MARKS(&bl->bl_inval, bl->bl_blocksize);
+	return &bl->bl_layout;
+}
+
+static void bl_free_lseg(struct pnfs_layout_segment *lseg)
+{
+	dprintk("%s enter\n", __func__);
+	kfree(lseg);
+}
+
+/* We pretty much ignore lseg, and store all data layout wide, so we
+ * can correctly merge.
+ */
+static struct pnfs_layout_segment *bl_alloc_lseg(struct pnfs_layout_hdr *lo,
+						 struct nfs4_layoutget_res *lgr,
+						 gfp_t gfp_flags)
+{
+	struct pnfs_layout_segment *lseg;
+	int status;
+
+	dprintk("%s enter\n", __func__);
+	lseg = kzalloc(sizeof(*lseg), gfp_flags);
+	if (!lseg)
+		return ERR_PTR(-ENOMEM);
+	status = nfs4_blk_process_layoutget(lo, lgr, gfp_flags);
+	if (status) {
+		/* We don't want to call the full-blown bl_free_lseg,
+		 * since on error extents were not touched.
+		 */
+		kfree(lseg);
+		return ERR_PTR(status);
+	}
+	return lseg;
+}
+
+static void
+bl_encode_layoutcommit(struct pnfs_layout_hdr *lo, struct xdr_stream *xdr,
+		       const struct nfs4_layoutcommit_args *arg)
+{
+	dprintk("%s enter\n", __func__);
+	encode_pnfs_block_layoutupdate(BLK_LO2EXT(lo), xdr, arg);
+}
+
+static void
+bl_cleanup_layoutcommit(struct nfs4_layoutcommit_data *lcdata)
+{
+	struct pnfs_layout_hdr *lo = NFS_I(lcdata->args.inode)->layout;
+
+	dprintk("%s enter\n", __func__);
+	clean_pnfs_block_layoutupdate(BLK_LO2EXT(lo), &lcdata->args, lcdata->res.status);
+}
+
+static void free_blk_mountid(struct block_mount_id *mid)
+{
+	if (mid) {
+		struct pnfs_block_dev *dev;
+		spin_lock(&mid->bm_lock);
+		while (!list_empty(&mid->bm_devlist)) {
+			dev = list_first_entry(&mid->bm_devlist,
+					       struct pnfs_block_dev,
+					       bm_node);
+			list_del(&dev->bm_node);
+			bl_free_block_dev(dev);
+		}
+		spin_unlock(&mid->bm_lock);
+		kfree(mid);
+	}
+}
+
+/* This is mostly copied from the filelayout's get_device_info function.
+ * It seems much of this should be at the generic pnfs level.
+ */
+static struct pnfs_block_dev *
+nfs4_blk_get_deviceinfo(struct nfs_server *server, const struct nfs_fh *fh,
+			struct nfs4_deviceid *d_id)
+{
+	struct pnfs_device *dev;
+	struct pnfs_block_dev *rv = NULL;
+	u32 max_resp_sz;
+	int max_pages;
+	struct page **pages = NULL;
+	int i, rc;
+
+	/*
+	 * Use the session max response size as the basis for setting
+	 * GETDEVICEINFO's maxcount
+	 */
+	max_resp_sz = server->nfs_client->cl_session->fc_attrs.max_resp_sz;
+	max_pages = max_resp_sz >> PAGE_SHIFT;
+	dprintk("%s max_resp_sz %u max_pages %d\n",
+		__func__, max_resp_sz, max_pages);
+
+	dev = kmalloc(sizeof(*dev), GFP_NOFS);
+	if (!dev) {
+		dprintk("%s kmalloc failed\n", __func__);
+		return NULL;
+	}
+
+	pages = kzalloc(max_pages * sizeof(struct page *), GFP_NOFS);
+	if (pages == NULL) {
+		kfree(dev);
+		return NULL;
+	}
+	for (i = 0; i < max_pages; i++) {
+		pages[i] = alloc_page(GFP_NOFS);
+		if (!pages[i])
+			goto out_free;
+	}
+
+	memcpy(&dev->dev_id, d_id, sizeof(*d_id));
+	dev->layout_type = LAYOUT_BLOCK_VOLUME;
+	dev->pages = pages;
+	dev->pgbase = 0;
+	dev->pglen = PAGE_SIZE * max_pages;
+	dev->mincount = 0;
+
+	dprintk("%s: dev_id: %s\n", __func__, dev->dev_id.data);
+	rc = nfs4_proc_getdeviceinfo(server, dev);
+	dprintk("%s getdevice info returns %d\n", __func__, rc);
+	if (rc)
+		goto out_free;
+
+	rv = nfs4_blk_decode_device(server, dev);
+ out_free:
+	for (i = 0; i < max_pages; i++)
+		__free_page(pages[i]);
+	kfree(pages);
+	kfree(dev);
+	return rv;
+}
+
+static int
+bl_set_layoutdriver(struct nfs_server *server, const struct nfs_fh *fh)
+{
+	struct block_mount_id *b_mt_id = NULL;
+	struct pnfs_devicelist *dlist = NULL;
+	struct pnfs_block_dev *bdev;
+	LIST_HEAD(block_disklist);
+	int status = 0, i;
+
+	dprintk("%s enter\n", __func__);
+
+	if (server->pnfs_blksize == 0) {
+		dprintk("%s Server did not return blksize\n", __func__);
+		return -EINVAL;
+	}
+	b_mt_id = kzalloc(sizeof(struct block_mount_id), GFP_NOFS);
+	if (!b_mt_id) {
+		status = -ENOMEM;
+		goto out_error;
+	}
+	/* Initialize nfs4 block layout mount id */
+	spin_lock_init(&b_mt_id->bm_lock);
+	INIT_LIST_HEAD(&b_mt_id->bm_devlist);
+
+	dlist = kmalloc(sizeof(struct pnfs_devicelist), GFP_NOFS);
+	if (!dlist) {
+		status = -ENOMEM;
+		goto out_error;
+	}
+	dlist->eof = 0;
+	while (!dlist->eof) {
+		status = nfs4_proc_getdevicelist(server, fh, dlist);
+		if (status)
+			goto out_error;
+		dprintk("%s GETDEVICELIST numdevs=%i, eof=%i\n",
+			__func__, dlist->num_devs, dlist->eof);
+		for (i = 0; i < dlist->num_devs; i++) {
+			bdev = nfs4_blk_get_deviceinfo(server, fh,
+						       &dlist->dev_id[i]);
+			if (!bdev) {
+				status = -ENODEV;
+				goto out_error;
+			}
+			spin_lock(&b_mt_id->bm_lock);
+			list_add(&bdev->bm_node, &b_mt_id->bm_devlist);
+			spin_unlock(&b_mt_id->bm_lock);
+		}
+	}
+	dprintk("%s SUCCESS\n", __func__);
+	server->pnfs_ld_data = b_mt_id;
+
+ out_return:
+	kfree(dlist);
+	return status;
+
+ out_error:
+	free_blk_mountid(b_mt_id);
+	goto out_return;
+}
+
+static int
+bl_clear_layoutdriver(struct nfs_server *server)
+{
+	struct block_mount_id *b_mt_id = server->pnfs_ld_data;
+
+	dprintk("%s enter\n", __func__);
+	free_blk_mountid(b_mt_id);
+	dprintk("%s RETURNS\n", __func__);
+	return 0;
+}
+
+static const struct nfs_pageio_ops bl_pg_read_ops = {
+	.pg_init = pnfs_generic_pg_init_read,
+	.pg_test = pnfs_generic_pg_test,
+	.pg_doio = pnfs_generic_pg_readpages,
+};
+
+static const struct nfs_pageio_ops bl_pg_write_ops = {
+	.pg_init = pnfs_generic_pg_init_write,
+	.pg_test = pnfs_generic_pg_test,
+	.pg_doio = pnfs_generic_pg_writepages,
+};
+
+static struct pnfs_layoutdriver_type blocklayout_type = {
+	.id				= LAYOUT_BLOCK_VOLUME,
+	.name				= "LAYOUT_BLOCK_VOLUME",
+	.read_pagelist			= bl_read_pagelist,
+	.write_pagelist			= bl_write_pagelist,
+	.alloc_layout_hdr		= bl_alloc_layout_hdr,
+	.free_layout_hdr		= bl_free_layout_hdr,
+	.alloc_lseg			= bl_alloc_lseg,
+	.free_lseg			= bl_free_lseg,
+	.encode_layoutcommit		= bl_encode_layoutcommit,
+	.cleanup_layoutcommit		= bl_cleanup_layoutcommit,
+	.set_layoutdriver		= bl_set_layoutdriver,
+	.clear_layoutdriver		= bl_clear_layoutdriver,
+	.pg_read_ops			= &bl_pg_read_ops,
+	.pg_write_ops			= &bl_pg_write_ops,
+};
+
+static const struct rpc_pipe_ops bl_upcall_ops = {
+	.upcall		= bl_pipe_upcall,
+	.downcall	= bl_pipe_downcall,
+	.destroy_msg	= bl_pipe_destroy_msg,
+};
+
+static int __init nfs4blocklayout_init(void)
+{
+	struct vfsmount *mnt;
+	struct path path;
+	int ret;
+
+	dprintk("%s: NFSv4 Block Layout Driver Registering...\n", __func__);
+
+	ret = pnfs_register_layoutdriver(&blocklayout_type);
+	if (ret)
+		goto out;
+
+	init_waitqueue_head(&bl_wq);
+
+	mnt = rpc_get_mount();
+	if (IS_ERR(mnt)) {
+		ret = PTR_ERR(mnt);
+		goto out_remove;
+	}
+
+	ret = vfs_path_lookup(mnt->mnt_root,
+			      mnt,
+			      NFS_PIPE_DIRNAME, 0, &path);
+	if (ret)
+		goto out_remove;
+
+	bl_device_pipe = rpc_mkpipe(path.dentry, "blocklayout", NULL,
+				    &bl_upcall_ops, 0);
+	if (IS_ERR(bl_device_pipe)) {
+		ret = PTR_ERR(bl_device_pipe);
+		goto out_remove;
+	}
+out:
+	return ret;
+
+out_remove:
+	pnfs_unregister_layoutdriver(&blocklayout_type);
+	return ret;
+}
+
+static void __exit nfs4blocklayout_exit(void)
+{
+	dprintk("%s: NFSv4 Block Layout Driver Unregistering...\n",
+	       __func__);
+
+	pnfs_unregister_layoutdriver(&blocklayout_type);
+	rpc_unlink(bl_device_pipe);
+}
+
+MODULE_ALIAS("nfs-layouttype4-3");
+
+module_init(nfs4blocklayout_init);
+module_exit(nfs4blocklayout_exit);
diff --git a/fs/nfs/blocklayout/blocklayout.h b/fs/nfs/blocklayout/blocklayout.h
new file mode 100644
index 000000000000..f27d827960a3
--- /dev/null
+++ b/fs/nfs/blocklayout/blocklayout.h
@@ -0,0 +1,207 @@
+/*
+ *  linux/fs/nfs/blocklayout/blocklayout.h
+ *
+ *  Module for the NFSv4.1 pNFS block layout driver.
+ *
+ *  Copyright (c) 2006 The Regents of the University of Michigan.
+ *  All rights reserved.
+ *
+ *  Andy Adamson <andros@citi.umich.edu>
+ *  Fred Isaman <iisaman@umich.edu>
+ *
+ * permission is granted to use, copy, create derivative works and
+ * redistribute this software and such derivative works for any purpose,
+ * so long as the name of the university of michigan is not used in
+ * any advertising or publicity pertaining to the use or distribution
+ * of this software without specific, written prior authorization.  if
+ * the above copyright notice or any other identification of the
+ * university of michigan is included in any copy of any portion of
+ * this software, then the disclaimer below must also be included.
+ *
+ * this software is provided as is, without representation from the
+ * university of michigan as to its fitness for any purpose, and without
+ * warranty by the university of michigan of any kind, either express
+ * or implied, including without limitation the implied warranties of
+ * merchantability and fitness for a particular purpose.  the regents
+ * of the university of michigan shall not be liable for any damages,
+ * including special, indirect, incidental, or consequential damages,
+ * with respect to any claim arising out or in connection with the use
+ * of the software, even if it has been or is hereafter advised of the
+ * possibility of such damages.
+ */
+#ifndef FS_NFS_NFS4BLOCKLAYOUT_H
+#define FS_NFS_NFS4BLOCKLAYOUT_H
+
+#include <linux/device-mapper.h>
+#include <linux/nfs_fs.h>
+#include <linux/sunrpc/rpc_pipe_fs.h>
+
+#include "../pnfs.h"
+
+#define PAGE_CACHE_SECTORS (PAGE_CACHE_SIZE >> SECTOR_SHIFT)
+#define PAGE_CACHE_SECTOR_SHIFT (PAGE_CACHE_SHIFT - SECTOR_SHIFT)
+
+struct block_mount_id {
+	spinlock_t			bm_lock;    /* protects list */
+	struct list_head		bm_devlist; /* holds pnfs_block_dev */
+};
+
+struct pnfs_block_dev {
+	struct list_head		bm_node;
+	struct nfs4_deviceid		bm_mdevid;    /* associated devid */
+	struct block_device		*bm_mdev;     /* meta device itself */
+};
+
+enum exstate4 {
+	PNFS_BLOCK_READWRITE_DATA	= 0,
+	PNFS_BLOCK_READ_DATA		= 1,
+	PNFS_BLOCK_INVALID_DATA		= 2, /* mapped, but data is invalid */
+	PNFS_BLOCK_NONE_DATA		= 3  /* unmapped, it's a hole */
+};
+
+#define MY_MAX_TAGS (15) /* tag bitnums used must be less than this */
+
+struct my_tree {
+	sector_t		mtt_step_size;	/* Internal sector alignment */
+	struct list_head	mtt_stub; /* Should be a radix tree */
+};
+
+struct pnfs_inval_markings {
+	spinlock_t	im_lock;
+	struct my_tree	im_tree;	/* Sectors that need LAYOUTCOMMIT */
+	sector_t	im_block_size;	/* Server blocksize in sectors */
+};
+
+struct pnfs_inval_tracking {
+	struct list_head it_link;
+	int		 it_sector;
+	int		 it_tags;
+};
+
+/* sector_t fields are all in 512-byte sectors */
+struct pnfs_block_extent {
+	struct kref	be_refcnt;
+	struct list_head be_node;	/* link into lseg list */
+	struct nfs4_deviceid be_devid;  /* FIXME: could use device cache instead */
+	struct block_device *be_mdev;
+	sector_t	be_f_offset;	/* the starting offset in the file */
+	sector_t	be_length;	/* the size of the extent */
+	sector_t	be_v_offset;	/* the starting offset in the volume */
+	enum exstate4	be_state;	/* the state of this extent */
+	struct pnfs_inval_markings *be_inval; /* tracks INVAL->RW transition */
+};
+
+/* Shortened extent used by LAYOUTCOMMIT */
+struct pnfs_block_short_extent {
+	struct list_head bse_node;
+	struct nfs4_deviceid bse_devid;
+	struct block_device *bse_mdev;
+	sector_t	bse_f_offset;	/* the starting offset in the file */
+	sector_t	bse_length;	/* the size of the extent */
+};
+
+static inline void
+BL_INIT_INVAL_MARKS(struct pnfs_inval_markings *marks, sector_t blocksize)
+{
+	spin_lock_init(&marks->im_lock);
+	INIT_LIST_HEAD(&marks->im_tree.mtt_stub);
+	marks->im_block_size = blocksize;
+	marks->im_tree.mtt_step_size = min((sector_t)PAGE_CACHE_SECTORS,
+					   blocksize);
+}
+
+enum extentclass4 {
+	RW_EXTENT       = 0, /* READWRTE and INVAL */
+	RO_EXTENT       = 1, /* READ and NONE */
+	EXTENT_LISTS    = 2,
+};
+
+static inline int bl_choose_list(enum exstate4 state)
+{
+	if (state == PNFS_BLOCK_READ_DATA || state == PNFS_BLOCK_NONE_DATA)
+		return RO_EXTENT;
+	else
+		return RW_EXTENT;
+}
+
+struct pnfs_block_layout {
+	struct pnfs_layout_hdr bl_layout;
+	struct pnfs_inval_markings bl_inval; /* tracks INVAL->RW transition */
+	spinlock_t		bl_ext_lock;   /* Protects list manipulation */
+	struct list_head	bl_extents[EXTENT_LISTS]; /* R and RW extents */
+	struct list_head	bl_commit;	/* Needs layout commit */
+	struct list_head	bl_committing;	/* Layout committing */
+	unsigned int		bl_count;	/* entries in bl_commit */
+	sector_t		bl_blocksize;  /* Server blocksize in sectors */
+};
+
+#define BLK_ID(lo) ((struct block_mount_id *)(NFS_SERVER(lo->plh_inode)->pnfs_ld_data))
+
+static inline struct pnfs_block_layout *
+BLK_LO2EXT(struct pnfs_layout_hdr *lo)
+{
+	return container_of(lo, struct pnfs_block_layout, bl_layout);
+}
+
+static inline struct pnfs_block_layout *
+BLK_LSEG2EXT(struct pnfs_layout_segment *lseg)
+{
+	return BLK_LO2EXT(lseg->pls_layout);
+}
+
+struct bl_dev_msg {
+	int status;
+	uint32_t major, minor;
+};
+
+struct bl_msg_hdr {
+	u8  type;
+	u16 totallen; /* length of entire message, including hdr itself */
+};
+
+extern struct dentry *bl_device_pipe;
+extern wait_queue_head_t bl_wq;
+
+#define BL_DEVICE_UMOUNT               0x0 /* Umount--delete devices */
+#define BL_DEVICE_MOUNT                0x1 /* Mount--create devices*/
+#define BL_DEVICE_REQUEST_INIT         0x0 /* Start request */
+#define BL_DEVICE_REQUEST_PROC         0x1 /* User level process succeeds */
+#define BL_DEVICE_REQUEST_ERR          0x2 /* User level process fails */
+
+/* blocklayoutdev.c */
+ssize_t bl_pipe_upcall(struct file *, struct rpc_pipe_msg *,
+		       char __user *, size_t);
+ssize_t bl_pipe_downcall(struct file *, const char __user *, size_t);
+void bl_pipe_destroy_msg(struct rpc_pipe_msg *);
+struct block_device *nfs4_blkdev_get(dev_t dev);
+int nfs4_blkdev_put(struct block_device *bdev);
+struct pnfs_block_dev *nfs4_blk_decode_device(struct nfs_server *server,
+						struct pnfs_device *dev);
+int nfs4_blk_process_layoutget(struct pnfs_layout_hdr *lo,
+				struct nfs4_layoutget_res *lgr, gfp_t gfp_flags);
+
+/* blocklayoutdm.c */
+void bl_free_block_dev(struct pnfs_block_dev *bdev);
+
+/* extents.c */
+struct pnfs_block_extent *
+bl_find_get_extent(struct pnfs_block_layout *bl, sector_t isect,
+		struct pnfs_block_extent **cow_read);
+int bl_mark_sectors_init(struct pnfs_inval_markings *marks,
+			     sector_t offset, sector_t length,
+			     sector_t **pages);
+void bl_put_extent(struct pnfs_block_extent *be);
+struct pnfs_block_extent *bl_alloc_extent(void);
+int bl_is_sector_init(struct pnfs_inval_markings *marks, sector_t isect);
+int encode_pnfs_block_layoutupdate(struct pnfs_block_layout *bl,
+				   struct xdr_stream *xdr,
+				   const struct nfs4_layoutcommit_args *arg);
+void clean_pnfs_block_layoutupdate(struct pnfs_block_layout *bl,
+				   const struct nfs4_layoutcommit_args *arg,
+				   int status);
+int bl_add_merge_extent(struct pnfs_block_layout *bl,
+			 struct pnfs_block_extent *new);
+int bl_mark_for_commit(struct pnfs_block_extent *be,
+			sector_t offset, sector_t length);
+
+#endif /* FS_NFS_NFS4BLOCKLAYOUT_H */
diff --git a/fs/nfs/blocklayout/blocklayoutdev.c b/fs/nfs/blocklayout/blocklayoutdev.c
new file mode 100644
index 000000000000..a83b393fb01c
--- /dev/null
+++ b/fs/nfs/blocklayout/blocklayoutdev.c
@@ -0,0 +1,410 @@
+/*
+ *  linux/fs/nfs/blocklayout/blocklayoutdev.c
+ *
+ *  Device operations for the pnfs nfs4 file layout driver.
+ *
+ *  Copyright (c) 2006 The Regents of the University of Michigan.
+ *  All rights reserved.
+ *
+ *  Andy Adamson <andros@citi.umich.edu>
+ *  Fred Isaman <iisaman@umich.edu>
+ *
+ * permission is granted to use, copy, create derivative works and
+ * redistribute this software and such derivative works for any purpose,
+ * so long as the name of the university of michigan is not used in
+ * any advertising or publicity pertaining to the use or distribution
+ * of this software without specific, written prior authorization.  if
+ * the above copyright notice or any other identification of the
+ * university of michigan is included in any copy of any portion of
+ * this software, then the disclaimer below must also be included.
+ *
+ * this software is provided as is, without representation from the
+ * university of michigan as to its fitness for any purpose, and without
+ * warranty by the university of michigan of any kind, either express
+ * or implied, including without limitation the implied warranties of
+ * merchantability and fitness for a particular purpose.  the regents
+ * of the university of michigan shall not be liable for any damages,
+ * including special, indirect, incidental, or consequential damages,
+ * with respect to any claim arising out or in connection with the use
+ * of the software, even if it has been or is hereafter advised of the
+ * possibility of such damages.
+ */
+#include <linux/module.h>
+#include <linux/buffer_head.h> /* __bread */
+
+#include <linux/genhd.h>
+#include <linux/blkdev.h>
+#include <linux/hash.h>
+
+#include "blocklayout.h"
+
+#define NFSDBG_FACILITY         NFSDBG_PNFS_LD
+
+static int decode_sector_number(__be32 **rp, sector_t *sp)
+{
+	uint64_t s;
+
+	*rp = xdr_decode_hyper(*rp, &s);
+	if (s & 0x1ff) {
+		printk(KERN_WARNING "%s: sector not aligned\n", __func__);
+		return -1;
+	}
+	*sp = s >> SECTOR_SHIFT;
+	return 0;
+}
+
+/* Open a block_device by device number. */
+struct block_device *nfs4_blkdev_get(dev_t dev)
+{
+	struct block_device *bd;
+
+	dprintk("%s enter\n", __func__);
+	bd = blkdev_get_by_dev(dev, FMODE_READ, NULL);
+	if (IS_ERR(bd))
+		goto fail;
+	return bd;
+fail:
+	dprintk("%s failed to open device : %ld\n",
+			__func__, PTR_ERR(bd));
+	return NULL;
+}
+
+/*
+ * Release the block device
+ */
+int nfs4_blkdev_put(struct block_device *bdev)
+{
+	dprintk("%s for device %d:%d\n", __func__, MAJOR(bdev->bd_dev),
+			MINOR(bdev->bd_dev));
+	return blkdev_put(bdev, FMODE_READ);
+}
+
+/*
+ * Shouldn't there be a rpc_generic_upcall() to do this for us?
+ */
+ssize_t bl_pipe_upcall(struct file *filp, struct rpc_pipe_msg *msg,
+		       char __user *dst, size_t buflen)
+{
+	char *data = (char *)msg->data + msg->copied;
+	size_t mlen = min(msg->len - msg->copied, buflen);
+	unsigned long left;
+
+	left = copy_to_user(dst, data, mlen);
+	if (left == mlen) {
+		msg->errno = -EFAULT;
+		return -EFAULT;
+	}
+
+	mlen -= left;
+	msg->copied += mlen;
+	msg->errno = 0;
+	return mlen;
+}
+
+static struct bl_dev_msg bl_mount_reply;
+
+ssize_t bl_pipe_downcall(struct file *filp, const char __user *src,
+			 size_t mlen)
+{
+	if (mlen != sizeof (struct bl_dev_msg))
+		return -EINVAL;
+
+	if (copy_from_user(&bl_mount_reply, src, mlen) != 0)
+		return -EFAULT;
+
+	wake_up(&bl_wq);
+
+	return mlen;
+}
+
+void bl_pipe_destroy_msg(struct rpc_pipe_msg *msg)
+{
+	if (msg->errno >= 0)
+		return;
+	wake_up(&bl_wq);
+}
+
+/*
+ * Decodes pnfs_block_deviceaddr4 which is XDR encoded in dev->dev_addr_buf.
+ */
+struct pnfs_block_dev *
+nfs4_blk_decode_device(struct nfs_server *server,
+		       struct pnfs_device *dev)
+{
+	struct pnfs_block_dev *rv = NULL;
+	struct block_device *bd = NULL;
+	struct rpc_pipe_msg msg;
+	struct bl_msg_hdr bl_msg = {
+		.type = BL_DEVICE_MOUNT,
+		.totallen = dev->mincount,
+	};
+	uint8_t *dataptr;
+	DECLARE_WAITQUEUE(wq, current);
+	struct bl_dev_msg *reply = &bl_mount_reply;
+	int offset, len, i;
+
+	dprintk("%s CREATING PIPEFS MESSAGE\n", __func__);
+	dprintk("%s: deviceid: %s, mincount: %d\n", __func__, dev->dev_id.data,
+		dev->mincount);
+
+	memset(&msg, 0, sizeof(msg));
+	msg.data = kzalloc(sizeof(bl_msg) + dev->mincount, GFP_NOFS);
+	if (!msg.data) {
+		rv = ERR_PTR(-ENOMEM);
+		goto out;
+	}
+
+	memcpy(msg.data, &bl_msg, sizeof(bl_msg));
+	dataptr = (uint8_t *) msg.data;
+	len = dev->mincount;
+	offset = sizeof(bl_msg);
+	for (i = 0; len > 0; i++) {
+		memcpy(&dataptr[offset], page_address(dev->pages[i]),
+				len < PAGE_CACHE_SIZE ? len : PAGE_CACHE_SIZE);
+		len -= PAGE_CACHE_SIZE;
+		offset += PAGE_CACHE_SIZE;
+	}
+	msg.len = sizeof(bl_msg) + dev->mincount;
+
+	dprintk("%s CALLING USERSPACE DAEMON\n", __func__);
+	add_wait_queue(&bl_wq, &wq);
+	if (rpc_queue_upcall(bl_device_pipe->d_inode, &msg) < 0) {
+		remove_wait_queue(&bl_wq, &wq);
+		goto out;
+	}
+
+	set_current_state(TASK_UNINTERRUPTIBLE);
+	schedule();
+	__set_current_state(TASK_RUNNING);
+	remove_wait_queue(&bl_wq, &wq);
+
+	if (reply->status != BL_DEVICE_REQUEST_PROC) {
+		dprintk("%s failed to open device: %d\n",
+			__func__, reply->status);
+		rv = ERR_PTR(-EINVAL);
+		goto out;
+	}
+
+	bd = nfs4_blkdev_get(MKDEV(reply->major, reply->minor));
+	if (IS_ERR(bd)) {
+		dprintk("%s failed to open device : %ld\n",
+			__func__, PTR_ERR(bd));
+		goto out;
+	}
+
+	rv = kzalloc(sizeof(*rv), GFP_NOFS);
+	if (!rv) {
+		rv = ERR_PTR(-ENOMEM);
+		goto out;
+	}
+
+	rv->bm_mdev = bd;
+	memcpy(&rv->bm_mdevid, &dev->dev_id, sizeof(struct nfs4_deviceid));
+	dprintk("%s Created device %s with bd_block_size %u\n",
+		__func__,
+		bd->bd_disk->disk_name,
+		bd->bd_block_size);
+
+out:
+	kfree(msg.data);
+	return rv;
+}
+
+/* Map deviceid returned by the server to constructed block_device */
+static struct block_device *translate_devid(struct pnfs_layout_hdr *lo,
+					    struct nfs4_deviceid *id)
+{
+	struct block_device *rv = NULL;
+	struct block_mount_id *mid;
+	struct pnfs_block_dev *dev;
+
+	dprintk("%s enter, lo=%p, id=%p\n", __func__, lo, id);
+	mid = BLK_ID(lo);
+	spin_lock(&mid->bm_lock);
+	list_for_each_entry(dev, &mid->bm_devlist, bm_node) {
+		if (memcmp(id->data, dev->bm_mdevid.data,
+			   NFS4_DEVICEID4_SIZE) == 0) {
+			rv = dev->bm_mdev;
+			goto out;
+		}
+	}
+ out:
+	spin_unlock(&mid->bm_lock);
+	dprintk("%s returning %p\n", __func__, rv);
+	return rv;
+}
+
+/* Tracks info needed to ensure extents in layout obey constraints of spec */
+struct layout_verification {
+	u32 mode;	/* R or RW */
+	u64 start;	/* Expected start of next non-COW extent */
+	u64 inval;	/* Start of INVAL coverage */
+	u64 cowread;	/* End of COW read coverage */
+};
+
+/* Verify the extent meets the layout requirements of the pnfs-block draft,
+ * section 2.3.1.
+ */
+static int verify_extent(struct pnfs_block_extent *be,
+			 struct layout_verification *lv)
+{
+	if (lv->mode == IOMODE_READ) {
+		if (be->be_state == PNFS_BLOCK_READWRITE_DATA ||
+		    be->be_state == PNFS_BLOCK_INVALID_DATA)
+			return -EIO;
+		if (be->be_f_offset != lv->start)
+			return -EIO;
+		lv->start += be->be_length;
+		return 0;
+	}
+	/* lv->mode == IOMODE_RW */
+	if (be->be_state == PNFS_BLOCK_READWRITE_DATA) {
+		if (be->be_f_offset != lv->start)
+			return -EIO;
+		if (lv->cowread > lv->start)
+			return -EIO;
+		lv->start += be->be_length;
+		lv->inval = lv->start;
+		return 0;
+	} else if (be->be_state == PNFS_BLOCK_INVALID_DATA) {
+		if (be->be_f_offset != lv->start)
+			return -EIO;
+		lv->start += be->be_length;
+		return 0;
+	} else if (be->be_state == PNFS_BLOCK_READ_DATA) {
+		if (be->be_f_offset > lv->start)
+			return -EIO;
+		if (be->be_f_offset < lv->inval)
+			return -EIO;
+		if (be->be_f_offset < lv->cowread)
+			return -EIO;
+		/* It looks like you might want to min this with lv->start,
+		 * but you really don't.
+		 */
+		lv->inval = lv->inval + be->be_length;
+		lv->cowread = be->be_f_offset + be->be_length;
+		return 0;
+	} else
+		return -EIO;
+}
+
+/* XDR decode pnfs_block_layout4 structure */
+int
+nfs4_blk_process_layoutget(struct pnfs_layout_hdr *lo,
+			   struct nfs4_layoutget_res *lgr, gfp_t gfp_flags)
+{
+	struct pnfs_block_layout *bl = BLK_LO2EXT(lo);
+	int i, status = -EIO;
+	uint32_t count;
+	struct pnfs_block_extent *be = NULL, *save;
+	struct xdr_stream stream;
+	struct xdr_buf buf;
+	struct page *scratch;
+	__be32 *p;
+	struct layout_verification lv = {
+		.mode = lgr->range.iomode,
+		.start = lgr->range.offset >> SECTOR_SHIFT,
+		.inval = lgr->range.offset >> SECTOR_SHIFT,
+		.cowread = lgr->range.offset >> SECTOR_SHIFT,
+	};
+	LIST_HEAD(extents);
+
+	dprintk("---> %s\n", __func__);
+
+	scratch = alloc_page(gfp_flags);
+	if (!scratch)
+		return -ENOMEM;
+
+	xdr_init_decode_pages(&stream, &buf, lgr->layoutp->pages, lgr->layoutp->len);
+	xdr_set_scratch_buffer(&stream, page_address(scratch), PAGE_SIZE);
+
+	p = xdr_inline_decode(&stream, 4);
+	if (unlikely(!p))
+		goto out_err;
+
+	count = be32_to_cpup(p++);
+
+	dprintk("%s enter, number of extents %i\n", __func__, count);
+	p = xdr_inline_decode(&stream, (28 + NFS4_DEVICEID4_SIZE) * count);
+	if (unlikely(!p))
+		goto out_err;
+
+	/* Decode individual extents, putting them in temporary
+	 * staging area until whole layout is decoded to make error
+	 * recovery easier.
+	 */
+	for (i = 0; i < count; i++) {
+		be = bl_alloc_extent();
+		if (!be) {
+			status = -ENOMEM;
+			goto out_err;
+		}
+		memcpy(&be->be_devid, p, NFS4_DEVICEID4_SIZE);
+		p += XDR_QUADLEN(NFS4_DEVICEID4_SIZE);
+		be->be_mdev = translate_devid(lo, &be->be_devid);
+		if (!be->be_mdev)
+			goto out_err;
+
+		/* The next three values are read in as bytes,
+		 * but stored as 512-byte sector lengths
+		 */
+		if (decode_sector_number(&p, &be->be_f_offset) < 0)
+			goto out_err;
+		if (decode_sector_number(&p, &be->be_length) < 0)
+			goto out_err;
+		if (decode_sector_number(&p, &be->be_v_offset) < 0)
+			goto out_err;
+		be->be_state = be32_to_cpup(p++);
+		if (be->be_state == PNFS_BLOCK_INVALID_DATA)
+			be->be_inval = &bl->bl_inval;
+		if (verify_extent(be, &lv)) {
+			dprintk("%s verify failed\n", __func__);
+			goto out_err;
+		}
+		list_add_tail(&be->be_node, &extents);
+	}
+	if (lgr->range.offset + lgr->range.length !=
+			lv.start << SECTOR_SHIFT) {
+		dprintk("%s Final length mismatch\n", __func__);
+		be = NULL;
+		goto out_err;
+	}
+	if (lv.start < lv.cowread) {
+		dprintk("%s Final uncovered COW extent\n", __func__);
+		be = NULL;
+		goto out_err;
+	}
+	/* Extents decoded properly, now try to merge them in to
+	 * existing layout extents.
+	 */
+	spin_lock(&bl->bl_ext_lock);
+	list_for_each_entry_safe(be, save, &extents, be_node) {
+		list_del(&be->be_node);
+		status = bl_add_merge_extent(bl, be);
+		if (status) {
+			spin_unlock(&bl->bl_ext_lock);
+			/* This is a fairly catastrophic error, as the
+			 * entire layout extent lists are now corrupted.
+			 * We should have some way to distinguish this.
+			 */
+			be = NULL;
+			goto out_err;
+		}
+	}
+	spin_unlock(&bl->bl_ext_lock);
+	status = 0;
+ out:
+	__free_page(scratch);
+	dprintk("%s returns %i\n", __func__, status);
+	return status;
+
+ out_err:
+	bl_put_extent(be);
+	while (!list_empty(&extents)) {
+		be = list_first_entry(&extents, struct pnfs_block_extent,
+				      be_node);
+		list_del(&be->be_node);
+		bl_put_extent(be);
+	}
+	goto out;
+}
diff --git a/fs/nfs/blocklayout/blocklayoutdm.c b/fs/nfs/blocklayout/blocklayoutdm.c
new file mode 100644
index 000000000000..d055c7558073
--- /dev/null
+++ b/fs/nfs/blocklayout/blocklayoutdm.c
@@ -0,0 +1,111 @@
+/*
+ *  linux/fs/nfs/blocklayout/blocklayoutdm.c
+ *
+ *  Module for the NFSv4.1 pNFS block layout driver.
+ *
+ *  Copyright (c) 2007 The Regents of the University of Michigan.
+ *  All rights reserved.
+ *
+ *  Fred Isaman <iisaman@umich.edu>
+ *  Andy Adamson <andros@citi.umich.edu>
+ *
+ * permission is granted to use, copy, create derivative works and
+ * redistribute this software and such derivative works for any purpose,
+ * so long as the name of the university of michigan is not used in
+ * any advertising or publicity pertaining to the use or distribution
+ * of this software without specific, written prior authorization.  if
+ * the above copyright notice or any other identification of the
+ * university of michigan is included in any copy of any portion of
+ * this software, then the disclaimer below must also be included.
+ *
+ * this software is provided as is, without representation from the
+ * university of michigan as to its fitness for any purpose, and without
+ * warranty by the university of michigan of any kind, either express
+ * or implied, including without limitation the implied warranties of
+ * merchantability and fitness for a particular purpose.  the regents
+ * of the university of michigan shall not be liable for any damages,
+ * including special, indirect, incidental, or consequential damages,
+ * with respect to any claim arising out or in connection with the use
+ * of the software, even if it has been or is hereafter advised of the
+ * possibility of such damages.
+ */
+
+#include <linux/genhd.h> /* gendisk - used in a dprintk*/
+#include <linux/sched.h>
+#include <linux/hash.h>
+
+#include "blocklayout.h"
+
+#define NFSDBG_FACILITY         NFSDBG_PNFS_LD
+
+static void dev_remove(dev_t dev)
+{
+	struct rpc_pipe_msg msg;
+	struct bl_dev_msg bl_umount_request;
+	struct bl_msg_hdr bl_msg = {
+		.type = BL_DEVICE_UMOUNT,
+		.totallen = sizeof(bl_umount_request),
+	};
+	uint8_t *dataptr;
+	DECLARE_WAITQUEUE(wq, current);
+
+	dprintk("Entering %s\n", __func__);
+
+	memset(&msg, 0, sizeof(msg));
+	msg.data = kzalloc(1 + sizeof(bl_umount_request), GFP_NOFS);
+	if (!msg.data)
+		goto out;
+
+	memset(&bl_umount_request, 0, sizeof(bl_umount_request));
+	bl_umount_request.major = MAJOR(dev);
+	bl_umount_request.minor = MINOR(dev);
+
+	memcpy(msg.data, &bl_msg, sizeof(bl_msg));
+	dataptr = (uint8_t *) msg.data;
+	memcpy(&dataptr[sizeof(bl_msg)], &bl_umount_request, sizeof(bl_umount_request));
+	msg.len = sizeof(bl_msg) + bl_msg.totallen;
+
+	add_wait_queue(&bl_wq, &wq);
+	if (rpc_queue_upcall(bl_device_pipe->d_inode, &msg) < 0) {
+		remove_wait_queue(&bl_wq, &wq);
+		goto out;
+	}
+
+	set_current_state(TASK_UNINTERRUPTIBLE);
+	schedule();
+	__set_current_state(TASK_RUNNING);
+	remove_wait_queue(&bl_wq, &wq);
+
+out:
+	kfree(msg.data);
+}
+
+/*
+ * Release meta device
+ */
+static void nfs4_blk_metadev_release(struct pnfs_block_dev *bdev)
+{
+	int rv;
+
+	dprintk("%s Releasing\n", __func__);
+	rv = nfs4_blkdev_put(bdev->bm_mdev);
+	if (rv)
+		printk(KERN_ERR "%s nfs4_blkdev_put returns %d\n",
+				__func__, rv);
+
+	dev_remove(bdev->bm_mdev->bd_dev);
+}
+
+void bl_free_block_dev(struct pnfs_block_dev *bdev)
+{
+	if (bdev) {
+		if (bdev->bm_mdev) {
+			dprintk("%s Removing DM device: %d:%d\n",
+				__func__,
+				MAJOR(bdev->bm_mdev->bd_dev),
+				MINOR(bdev->bm_mdev->bd_dev));
+			nfs4_blk_metadev_release(bdev);
+		}
+		kfree(bdev);
+	}
+}
diff --git a/fs/nfs/blocklayout/extents.c b/fs/nfs/blocklayout/extents.c
new file mode 100644
index 000000000000..19fa7b0b8c00
--- /dev/null
+++ b/fs/nfs/blocklayout/extents.c
@@ -0,0 +1,935 @@
+/*
+ *  linux/fs/nfs/blocklayout/blocklayout.h
+ *
+ *  Module for the NFSv4.1 pNFS block layout driver.
+ *
+ *  Copyright (c) 2006 The Regents of the University of Michigan.
+ *  All rights reserved.
+ *
+ *  Andy Adamson <andros@citi.umich.edu>
+ *  Fred Isaman <iisaman@umich.edu>
+ *
+ * permission is granted to use, copy, create derivative works and
+ * redistribute this software and such derivative works for any purpose,
+ * so long as the name of the university of michigan is not used in
+ * any advertising or publicity pertaining to the use or distribution
+ * of this software without specific, written prior authorization.  if
+ * the above copyright notice or any other identification of the
+ * university of michigan is included in any copy of any portion of
+ * this software, then the disclaimer below must also be included.
+ *
+ * this software is provided as is, without representation from the
+ * university of michigan as to its fitness for any purpose, and without
+ * warranty by the university of michigan of any kind, either express
+ * or implied, including without limitation the implied warranties of
+ * merchantability and fitness for a particular purpose.  the regents
+ * of the university of michigan shall not be liable for any damages,
+ * including special, indirect, incidental, or consequential damages,
+ * with respect to any claim arising out or in connection with the use
+ * of the software, even if it has been or is hereafter advised of the
+ * possibility of such damages.
+ */
+
+#include "blocklayout.h"
+#define NFSDBG_FACILITY         NFSDBG_PNFS_LD
+
+/* Bit numbers */
+#define EXTENT_INITIALIZED 0
+#define EXTENT_WRITTEN     1
+#define EXTENT_IN_COMMIT   2
+#define INTERNAL_EXISTS    MY_MAX_TAGS
+#define INTERNAL_MASK      ((1 << INTERNAL_EXISTS) - 1)
+
+/* Returns largest t<=s s.t. t%base==0 */
+static inline sector_t normalize(sector_t s, int base)
+{
+	sector_t tmp = s; /* Since do_div modifies its argument */
+	return s - do_div(tmp, base);
+}
+
+static inline sector_t normalize_up(sector_t s, int base)
+{
+	return normalize(s + base - 1, base);
+}
+
+/* Complete stub using list while determine API wanted */
+
+/* Returns tags, or negative */
+static int32_t _find_entry(struct my_tree *tree, u64 s)
+{
+	struct pnfs_inval_tracking *pos;
+
+	dprintk("%s(%llu) enter\n", __func__, s);
+	list_for_each_entry_reverse(pos, &tree->mtt_stub, it_link) {
+		if (pos->it_sector > s)
+			continue;
+		else if (pos->it_sector == s)
+			return pos->it_tags & INTERNAL_MASK;
+		else
+			break;
+	}
+	return -ENOENT;
+}
+
+static inline
+int _has_tag(struct my_tree *tree, u64 s, int32_t tag)
+{
+	int32_t tags;
+
+	dprintk("%s(%llu, %i) enter\n", __func__, s, tag);
+	s = normalize(s, tree->mtt_step_size);
+	tags = _find_entry(tree, s);
+	if ((tags < 0) || !(tags & (1 << tag)))
+		return 0;
+	else
+		return 1;
+}
+
+/* Creates entry with tag, or if entry already exists, unions tag to it.
+ * If storage is not NULL, newly created entry will use it.
+ * Returns number of entries added, or negative on error.
+ */
+static int _add_entry(struct my_tree *tree, u64 s, int32_t tag,
+		      struct pnfs_inval_tracking *storage)
+{
+	int found = 0;
+	struct pnfs_inval_tracking *pos;
+
+	dprintk("%s(%llu, %i, %p) enter\n", __func__, s, tag, storage);
+	list_for_each_entry_reverse(pos, &tree->mtt_stub, it_link) {
+		if (pos->it_sector > s)
+			continue;
+		else if (pos->it_sector == s) {
+			found = 1;
+			break;
+		} else
+			break;
+	}
+	if (found) {
+		pos->it_tags |= (1 << tag);
+		return 0;
+	} else {
+		struct pnfs_inval_tracking *new;
+		if (storage)
+			new = storage;
+		else {
+			new = kmalloc(sizeof(*new), GFP_NOFS);
+			if (!new)
+				return -ENOMEM;
+		}
+		new->it_sector = s;
+		new->it_tags = (1 << tag);
+		list_add(&new->it_link, &pos->it_link);
+		return 1;
+	}
+}
+
+/* XXXX Really want option to not create */
+/* Over range, unions tag with existing entries, else creates entry with tag */
+static int _set_range(struct my_tree *tree, int32_t tag, u64 s, u64 length)
+{
+	u64 i;
+
+	dprintk("%s(%i, %llu, %llu) enter\n", __func__, tag, s, length);
+	for (i = normalize(s, tree->mtt_step_size); i < s + length;
+	     i += tree->mtt_step_size)
+		if (_add_entry(tree, i, tag, NULL))
+			return -ENOMEM;
+	return 0;
+}
+
+/* Ensure that future operations on given range of tree will not malloc */
+static int _preload_range(struct my_tree *tree, u64 offset, u64 length)
+{
+	u64 start, end, s;
+	int count, i, used = 0, status = -ENOMEM;
+	struct pnfs_inval_tracking **storage;
+
+	dprintk("%s(%llu, %llu) enter\n", __func__, offset, length);
+	start = normalize(offset, tree->mtt_step_size);
+	end = normalize_up(offset + length, tree->mtt_step_size);
+	count = (int)(end - start) / (int)tree->mtt_step_size;
+
+	/* Pre-malloc what memory we might need */
+	storage = kmalloc(sizeof(*storage) * count, GFP_NOFS);
+	if (!storage)
+		return -ENOMEM;
+	for (i = 0; i < count; i++) {
+		storage[i] = kmalloc(sizeof(struct pnfs_inval_tracking),
+				     GFP_NOFS);
+		if (!storage[i])
+			goto out_cleanup;
+	}
+
+	/* Now need lock - HOW??? */
+
+	for (s = start; s < end; s += tree->mtt_step_size)
+		used += _add_entry(tree, s, INTERNAL_EXISTS, storage[used]);
+
+	/* Unlock - HOW??? */
+	status = 0;
+
+ out_cleanup:
+	for (i = used; i < count; i++) {
+		if (!storage[i])
+			break;
+		kfree(storage[i]);
+	}
+	kfree(storage);
+	return status;
+}
+
+static void set_needs_init(sector_t *array, sector_t offset)
+{
+	sector_t *p = array;
+
+	dprintk("%s enter\n", __func__);
+	if (!p)
+		return;
+	while (*p < offset)
+		p++;
+	if (*p == offset)
+		return;
+	else if (*p == ~0) {
+		*p++ = offset;
+		*p = ~0;
+		return;
+	} else {
+		sector_t *save = p;
+		dprintk("%s Adding %llu\n", __func__, (u64)offset);
+		while (*p != ~0)
+			p++;
+		p++;
+		memmove(save + 1, save, (char *)p - (char *)save);
+		*save = offset;
+		return;
+	}
+}
+
+/* We are relying on page lock to serialize this */
+int bl_is_sector_init(struct pnfs_inval_markings *marks, sector_t isect)
+{
+	int rv;
+
+	spin_lock(&marks->im_lock);
+	rv = _has_tag(&marks->im_tree, isect, EXTENT_INITIALIZED);
+	spin_unlock(&marks->im_lock);
+	return rv;
+}
+
+/* Assume start, end already sector aligned */
+static int
+_range_has_tag(struct my_tree *tree, u64 start, u64 end, int32_t tag)
+{
+	struct pnfs_inval_tracking *pos;
+	u64 expect = 0;
+
+	dprintk("%s(%llu, %llu, %i) enter\n", __func__, start, end, tag);
+	list_for_each_entry_reverse(pos, &tree->mtt_stub, it_link) {
+		if (pos->it_sector >= end)
+			continue;
+		if (!expect) {
+			if ((pos->it_sector == end - tree->mtt_step_size) &&
+			    (pos->it_tags & (1 << tag))) {
+				expect = pos->it_sector - tree->mtt_step_size;
+				if (pos->it_sector < tree->mtt_step_size || expect < start)
+					return 1;
+				continue;
+			} else {
+				return 0;
+			}
+		}
+		if (pos->it_sector != expect || !(pos->it_tags & (1 << tag)))
+			return 0;
+		expect -= tree->mtt_step_size;
+		if (expect < start)
+			return 1;
+	}
+	return 0;
+}
+
+static int is_range_written(struct pnfs_inval_markings *marks,
+			    sector_t start, sector_t end)
+{
+	int rv;
+
+	spin_lock(&marks->im_lock);
+	rv = _range_has_tag(&marks->im_tree, start, end, EXTENT_WRITTEN);
+	spin_unlock(&marks->im_lock);
+	return rv;
+}
+
+/* Marks sectors in [offest, offset_length) as having been initialized.
+ * All lengths are step-aligned, where step is min(pagesize, blocksize).
+ * Notes where partial block is initialized, and helps prepare it for
+ * complete initialization later.
+ */
+/* Currently assumes offset is page-aligned */
+int bl_mark_sectors_init(struct pnfs_inval_markings *marks,
+			     sector_t offset, sector_t length,
+			     sector_t **pages)
+{
+	sector_t s, start, end;
+	sector_t *array = NULL; /* Pages to mark */
+
+	dprintk("%s(offset=%llu,len=%llu) enter\n",
+		__func__, (u64)offset, (u64)length);
+	s = max((sector_t) 3,
+		2 * (marks->im_block_size / (PAGE_CACHE_SECTORS)));
+	dprintk("%s set max=%llu\n", __func__, (u64)s);
+	if (pages) {
+		array = kmalloc(s * sizeof(sector_t), GFP_NOFS);
+		if (!array)
+			goto outerr;
+		array[0] = ~0;
+	}
+
+	start = normalize(offset, marks->im_block_size);
+	end = normalize_up(offset + length, marks->im_block_size);
+	if (_preload_range(&marks->im_tree, start, end - start))
+		goto outerr;
+
+	spin_lock(&marks->im_lock);
+
+	for (s = normalize_up(start, PAGE_CACHE_SECTORS);
+	     s < offset; s += PAGE_CACHE_SECTORS) {
+		dprintk("%s pre-area pages\n", __func__);
+		/* Portion of used block is not initialized */
+		if (!_has_tag(&marks->im_tree, s, EXTENT_INITIALIZED))
+			set_needs_init(array, s);
+	}
+	if (_set_range(&marks->im_tree, EXTENT_INITIALIZED, offset, length))
+		goto out_unlock;
+	for (s = normalize_up(offset + length, PAGE_CACHE_SECTORS);
+	     s < end; s += PAGE_CACHE_SECTORS) {
+		dprintk("%s post-area pages\n", __func__);
+		if (!_has_tag(&marks->im_tree, s, EXTENT_INITIALIZED))
+			set_needs_init(array, s);
+	}
+
+	spin_unlock(&marks->im_lock);
+
+	if (pages) {
+		if (array[0] == ~0) {
+			kfree(array);
+			*pages = NULL;
+		} else
+			*pages = array;
+	}
+	return 0;
+
+ out_unlock:
+	spin_unlock(&marks->im_lock);
+ outerr:
+	if (pages) {
+		kfree(array);
+		*pages = NULL;
+	}
+	return -ENOMEM;
+}
+
+/* Marks sectors in [offest, offset+length) as having been written to disk.
+ * All lengths should be block aligned.
+ */
+static int mark_written_sectors(struct pnfs_inval_markings *marks,
+				sector_t offset, sector_t length)
+{
+	int status;
+
+	dprintk("%s(offset=%llu,len=%llu) enter\n", __func__,
+		(u64)offset, (u64)length);
+	spin_lock(&marks->im_lock);
+	status = _set_range(&marks->im_tree, EXTENT_WRITTEN, offset, length);
+	spin_unlock(&marks->im_lock);
+	return status;
+}
+
+static void print_short_extent(struct pnfs_block_short_extent *be)
+{
+	dprintk("PRINT SHORT EXTENT extent %p\n", be);
+	if (be) {
+		dprintk("        be_f_offset %llu\n", (u64)be->bse_f_offset);
+		dprintk("        be_length   %llu\n", (u64)be->bse_length);
+	}
+}
+
+static void print_clist(struct list_head *list, unsigned int count)
+{
+	struct pnfs_block_short_extent *be;
+	unsigned int i = 0;
+
+	ifdebug(FACILITY) {
+		printk(KERN_DEBUG "****************\n");
+		printk(KERN_DEBUG "Extent list looks like:\n");
+		list_for_each_entry(be, list, bse_node) {
+			i++;
+			print_short_extent(be);
+		}
+		if (i != count)
+			printk(KERN_DEBUG "\n\nExpected %u entries\n\n\n", count);
+		printk(KERN_DEBUG "****************\n");
+	}
+}
+
+/* Note: In theory, we should do more checking that devid's match between
+ * old and new, but if they don't, the lists are too corrupt to salvage anyway.
+ */
+/* Note this is very similar to bl_add_merge_extent */
+static void add_to_commitlist(struct pnfs_block_layout *bl,
+			      struct pnfs_block_short_extent *new)
+{
+	struct list_head *clist = &bl->bl_commit;
+	struct pnfs_block_short_extent *old, *save;
+	sector_t end = new->bse_f_offset + new->bse_length;
+
+	dprintk("%s enter\n", __func__);
+	print_short_extent(new);
+	print_clist(clist, bl->bl_count);
+	bl->bl_count++;
+	/* Scan for proper place to insert, extending new to the left
+	 * as much as possible.
+	 */
+	list_for_each_entry_safe(old, save, clist, bse_node) {
+		if (new->bse_f_offset < old->bse_f_offset)
+			break;
+		if (end <= old->bse_f_offset + old->bse_length) {
+			/* Range is already in list */
+			bl->bl_count--;
+			kfree(new);
+			return;
+		} else if (new->bse_f_offset <=
+				old->bse_f_offset + old->bse_length) {
+			/* new overlaps or abuts existing be */
+			if (new->bse_mdev == old->bse_mdev) {
+				/* extend new to fully replace old */
+				new->bse_length += new->bse_f_offset -
+						old->bse_f_offset;
+				new->bse_f_offset = old->bse_f_offset;
+				list_del(&old->bse_node);
+				bl->bl_count--;
+				kfree(old);
+			}
+		}
+	}
+	/* Note that if we never hit the above break, old will not point to a
+	 * valid extent.  However, in that case &old->bse_node==list.
+	 */
+	list_add_tail(&new->bse_node, &old->bse_node);
+	/* Scan forward for overlaps.  If we find any, extend new and
+	 * remove the overlapped extent.
+	 */
+	old = list_prepare_entry(new, clist, bse_node);
+	list_for_each_entry_safe_continue(old, save, clist, bse_node) {
+		if (end < old->bse_f_offset)
+			break;
+		/* new overlaps or abuts old */
+		if (new->bse_mdev == old->bse_mdev) {
+			if (end < old->bse_f_offset + old->bse_length) {
+				/* extend new to fully cover old */
+				end = old->bse_f_offset + old->bse_length;
+				new->bse_length = end - new->bse_f_offset;
+			}
+			list_del(&old->bse_node);
+			bl->bl_count--;
+			kfree(old);
+		}
+	}
+	dprintk("%s: after merging\n", __func__);
+	print_clist(clist, bl->bl_count);
+}
+
+/* Note the range described by offset, length is guaranteed to be contained
+ * within be.
+ */
+int bl_mark_for_commit(struct pnfs_block_extent *be,
+		    sector_t offset, sector_t length)
+{
+	sector_t new_end, end = offset + length;
+	struct pnfs_block_short_extent *new;
+	struct pnfs_block_layout *bl = container_of(be->be_inval,
+						    struct pnfs_block_layout,
+						    bl_inval);
+
+	new = kmalloc(sizeof(*new), GFP_NOFS);
+	if (!new)
+		return -ENOMEM;
+
+	mark_written_sectors(be->be_inval, offset, length);
+	/* We want to add the range to commit list, but it must be
+	 * block-normalized, and verified that the normalized range has
+	 * been entirely written to disk.
+	 */
+	new->bse_f_offset = offset;
+	offset = normalize(offset, bl->bl_blocksize);
+	if (offset < new->bse_f_offset) {
+		if (is_range_written(be->be_inval, offset, new->bse_f_offset))
+			new->bse_f_offset = offset;
+		else
+			new->bse_f_offset = offset + bl->bl_blocksize;
+	}
+	new_end = normalize_up(end, bl->bl_blocksize);
+	if (end < new_end) {
+		if (is_range_written(be->be_inval, end, new_end))
+			end = new_end;
+		else
+			end = new_end - bl->bl_blocksize;
+	}
+	if (end <= new->bse_f_offset) {
+		kfree(new);
+		return 0;
+	}
+	new->bse_length = end - new->bse_f_offset;
+	new->bse_devid = be->be_devid;
+	new->bse_mdev = be->be_mdev;
+
+	spin_lock(&bl->bl_ext_lock);
+	/* new will be freed, either by add_to_commitlist if it decides not
+	 * to use it, or after LAYOUTCOMMIT uses it in the commitlist.
+	 */
+	add_to_commitlist(bl, new);
+	spin_unlock(&bl->bl_ext_lock);
+	return 0;
+}
+
+static void print_bl_extent(struct pnfs_block_extent *be)
+{
+	dprintk("PRINT EXTENT extent %p\n", be);
+	if (be) {
+		dprintk("        be_f_offset %llu\n", (u64)be->be_f_offset);
+		dprintk("        be_length   %llu\n", (u64)be->be_length);
+		dprintk("        be_v_offset %llu\n", (u64)be->be_v_offset);
+		dprintk("        be_state    %d\n", be->be_state);
+	}
+}
+
+static void
+destroy_extent(struct kref *kref)
+{
+	struct pnfs_block_extent *be;
+
+	be = container_of(kref, struct pnfs_block_extent, be_refcnt);
+	dprintk("%s be=%p\n", __func__, be);
+	kfree(be);
+}
+
+void
+bl_put_extent(struct pnfs_block_extent *be)
+{
+	if (be) {
+		dprintk("%s enter %p (%i)\n", __func__, be,
+			atomic_read(&be->be_refcnt.refcount));
+		kref_put(&be->be_refcnt, destroy_extent);
+	}
+}
+
+struct pnfs_block_extent *bl_alloc_extent(void)
+{
+	struct pnfs_block_extent *be;
+
+	be = kmalloc(sizeof(struct pnfs_block_extent), GFP_NOFS);
+	if (!be)
+		return NULL;
+	INIT_LIST_HEAD(&be->be_node);
+	kref_init(&be->be_refcnt);
+	be->be_inval = NULL;
+	return be;
+}
+
+static void print_elist(struct list_head *list)
+{
+	struct pnfs_block_extent *be;
+	dprintk("****************\n");
+	dprintk("Extent list looks like:\n");
+	list_for_each_entry(be, list, be_node) {
+		print_bl_extent(be);
+	}
+	dprintk("****************\n");
+}
+
+static inline int
+extents_consistent(struct pnfs_block_extent *old, struct pnfs_block_extent *new)
+{
+	/* Note this assumes new->be_f_offset >= old->be_f_offset */
+	return (new->be_state == old->be_state) &&
+		((new->be_state == PNFS_BLOCK_NONE_DATA) ||
+		 ((new->be_v_offset - old->be_v_offset ==
+		   new->be_f_offset - old->be_f_offset) &&
+		  new->be_mdev == old->be_mdev));
+}
+
+/* Adds new to appropriate list in bl, modifying new and removing existing
+ * extents as appropriate to deal with overlaps.
+ *
+ * See bl_find_get_extent for list constraints.
+ *
+ * Refcount on new is already set.  If end up not using it, or error out,
+ * need to put the reference.
+ *
+ * bl->bl_ext_lock is held by caller.
+ */
+int
+bl_add_merge_extent(struct pnfs_block_layout *bl,
+		     struct pnfs_block_extent *new)
+{
+	struct pnfs_block_extent *be, *tmp;
+	sector_t end = new->be_f_offset + new->be_length;
+	struct list_head *list;
+
+	dprintk("%s enter with be=%p\n", __func__, new);
+	print_bl_extent(new);
+	list = &bl->bl_extents[bl_choose_list(new->be_state)];
+	print_elist(list);
+
+	/* Scan for proper place to insert, extending new to the left
+	 * as much as possible.
+	 */
+	list_for_each_entry_safe_reverse(be, tmp, list, be_node) {
+		if (new->be_f_offset >= be->be_f_offset + be->be_length)
+			break;
+		if (new->be_f_offset >= be->be_f_offset) {
+			if (end <= be->be_f_offset + be->be_length) {
+				/* new is a subset of existing be*/
+				if (extents_consistent(be, new)) {
+					dprintk("%s: new is subset, ignoring\n",
+						__func__);
+					bl_put_extent(new);
+					return 0;
+				} else {
+					goto out_err;
+				}
+			} else {
+				/* |<--   be   -->|
+				 *          |<--   new   -->| */
+				if (extents_consistent(be, new)) {
+					/* extend new to fully replace be */
+					new->be_length += new->be_f_offset -
+						be->be_f_offset;
+					new->be_f_offset = be->be_f_offset;
+					new->be_v_offset = be->be_v_offset;
+					dprintk("%s: removing %p\n", __func__, be);
+					list_del(&be->be_node);
+					bl_put_extent(be);
+				} else {
+					goto out_err;
+				}
+			}
+		} else if (end >= be->be_f_offset + be->be_length) {
+			/* new extent overlap existing be */
+			if (extents_consistent(be, new)) {
+				/* extend new to fully replace be */
+				dprintk("%s: removing %p\n", __func__, be);
+				list_del(&be->be_node);
+				bl_put_extent(be);
+			} else {
+				goto out_err;
+			}
+		} else if (end > be->be_f_offset) {
+			/*           |<--   be   -->|
+			 *|<--   new   -->| */
+			if (extents_consistent(new, be)) {
+				/* extend new to fully replace be */
+				new->be_length += be->be_f_offset + be->be_length -
+					new->be_f_offset - new->be_length;
+				dprintk("%s: removing %p\n", __func__, be);
+				list_del(&be->be_node);
+				bl_put_extent(be);
+			} else {
+				goto out_err;
+			}
+		}
+	}
+	/* Note that if we never hit the above break, be will not point to a
+	 * valid extent.  However, in that case &be->be_node==list.
+	 */
+	list_add(&new->be_node, &be->be_node);
+	dprintk("%s: inserting new\n", __func__);
+	print_elist(list);
+	/* FIXME - The per-list consistency checks have all been done,
+	 * should now check cross-list consistency.
+	 */
+	return 0;
+
+ out_err:
+	bl_put_extent(new);
+	return -EIO;
+}
+
+/* Returns extent, or NULL.  If a second READ extent exists, it is returned
+ * in cow_read, if given.
+ *
+ * The extents are kept in two seperate ordered lists, one for READ and NONE,
+ * one for READWRITE and INVALID.  Within each list, we assume:
+ * 1. Extents are ordered by file offset.
+ * 2. For any given isect, there is at most one extents that matches.
+ */
+struct pnfs_block_extent *
+bl_find_get_extent(struct pnfs_block_layout *bl, sector_t isect,
+	    struct pnfs_block_extent **cow_read)
+{
+	struct pnfs_block_extent *be, *cow, *ret;
+	int i;
+
+	dprintk("%s enter with isect %llu\n", __func__, (u64)isect);
+	cow = ret = NULL;
+	spin_lock(&bl->bl_ext_lock);
+	for (i = 0; i < EXTENT_LISTS; i++) {
+		list_for_each_entry_reverse(be, &bl->bl_extents[i], be_node) {
+			if (isect >= be->be_f_offset + be->be_length)
+				break;
+			if (isect >= be->be_f_offset) {
+				/* We have found an extent */
+				dprintk("%s Get %p (%i)\n", __func__, be,
+					atomic_read(&be->be_refcnt.refcount));
+				kref_get(&be->be_refcnt);
+				if (!ret)
+					ret = be;
+				else if (be->be_state != PNFS_BLOCK_READ_DATA)
+					bl_put_extent(be);
+				else
+					cow = be;
+				break;
+			}
+		}
+		if (ret &&
+		    (!cow_read || ret->be_state != PNFS_BLOCK_INVALID_DATA))
+			break;
+	}
+	spin_unlock(&bl->bl_ext_lock);
+	if (cow_read)
+		*cow_read = cow;
+	print_bl_extent(ret);
+	return ret;
+}
+
+/* Similar to bl_find_get_extent, but called with lock held, and ignores cow */
+static struct pnfs_block_extent *
+bl_find_get_extent_locked(struct pnfs_block_layout *bl, sector_t isect)
+{
+	struct pnfs_block_extent *be, *ret = NULL;
+	int i;
+
+	dprintk("%s enter with isect %llu\n", __func__, (u64)isect);
+	for (i = 0; i < EXTENT_LISTS; i++) {
+		if (ret)
+			break;
+		list_for_each_entry_reverse(be, &bl->bl_extents[i], be_node) {
+			if (isect >= be->be_f_offset + be->be_length)
+				break;
+			if (isect >= be->be_f_offset) {
+				/* We have found an extent */
+				dprintk("%s Get %p (%i)\n", __func__, be,
+					atomic_read(&be->be_refcnt.refcount));
+				kref_get(&be->be_refcnt);
+				ret = be;
+				break;
+			}
+		}
+	}
+	print_bl_extent(ret);
+	return ret;
+}
+
+int
+encode_pnfs_block_layoutupdate(struct pnfs_block_layout *bl,
+			       struct xdr_stream *xdr,
+			       const struct nfs4_layoutcommit_args *arg)
+{
+	struct pnfs_block_short_extent *lce, *save;
+	unsigned int count = 0;
+	__be32 *p, *xdr_start;
+
+	dprintk("%s enter\n", __func__);
+	/* BUG - creation of bl_commit is buggy - need to wait for
+	 * entire block to be marked WRITTEN before it can be added.
+	 */
+	spin_lock(&bl->bl_ext_lock);
+	/* Want to adjust for possible truncate */
+	/* We now want to adjust argument range */
+
+	/* XDR encode the ranges found */
+	xdr_start = xdr_reserve_space(xdr, 8);
+	if (!xdr_start)
+		goto out;
+	list_for_each_entry_safe(lce, save, &bl->bl_commit, bse_node) {
+		p = xdr_reserve_space(xdr, 7 * 4 + sizeof(lce->bse_devid.data));
+		if (!p)
+			break;
+		p = xdr_encode_opaque_fixed(p, lce->bse_devid.data, NFS4_DEVICEID4_SIZE);
+		p = xdr_encode_hyper(p, lce->bse_f_offset << SECTOR_SHIFT);
+		p = xdr_encode_hyper(p, lce->bse_length << SECTOR_SHIFT);
+		p = xdr_encode_hyper(p, 0LL);
+		*p++ = cpu_to_be32(PNFS_BLOCK_READWRITE_DATA);
+		list_del(&lce->bse_node);
+		list_add_tail(&lce->bse_node, &bl->bl_committing);
+		bl->bl_count--;
+		count++;
+	}
+	xdr_start[0] = cpu_to_be32((xdr->p - xdr_start - 1) * 4);
+	xdr_start[1] = cpu_to_be32(count);
+out:
+	spin_unlock(&bl->bl_ext_lock);
+	dprintk("%s found %i ranges\n", __func__, count);
+	return 0;
+}
+
+/* Helper function to set_to_rw that initialize a new extent */
+static void
+_prep_new_extent(struct pnfs_block_extent *new,
+		 struct pnfs_block_extent *orig,
+		 sector_t offset, sector_t length, int state)
+{
+	kref_init(&new->be_refcnt);
+	/* don't need to INIT_LIST_HEAD(&new->be_node) */
+	memcpy(&new->be_devid, &orig->be_devid, sizeof(struct nfs4_deviceid));
+	new->be_mdev = orig->be_mdev;
+	new->be_f_offset = offset;
+	new->be_length = length;
+	new->be_v_offset = orig->be_v_offset - orig->be_f_offset + offset;
+	new->be_state = state;
+	new->be_inval = orig->be_inval;
+}
+
+/* Tries to merge be with extent in front of it in list.
+ * Frees storage if not used.
+ */
+static struct pnfs_block_extent *
+_front_merge(struct pnfs_block_extent *be, struct list_head *head,
+	     struct pnfs_block_extent *storage)
+{
+	struct pnfs_block_extent *prev;
+
+	if (!storage)
+		goto no_merge;
+	if (&be->be_node == head || be->be_node.prev == head)
+		goto no_merge;
+	prev = list_entry(be->be_node.prev, struct pnfs_block_extent, be_node);
+	if ((prev->be_f_offset + prev->be_length != be->be_f_offset) ||
+	    !extents_consistent(prev, be))
+		goto no_merge;
+	_prep_new_extent(storage, prev, prev->be_f_offset,
+			 prev->be_length + be->be_length, prev->be_state);
+	list_replace(&prev->be_node, &storage->be_node);
+	bl_put_extent(prev);
+	list_del(&be->be_node);
+	bl_put_extent(be);
+	return storage;
+
+ no_merge:
+	kfree(storage);
+	return be;
+}
+
+static u64
+set_to_rw(struct pnfs_block_layout *bl, u64 offset, u64 length)
+{
+	u64 rv = offset + length;
+	struct pnfs_block_extent *be, *e1, *e2, *e3, *new, *old;
+	struct pnfs_block_extent *children[3];
+	struct pnfs_block_extent *merge1 = NULL, *merge2 = NULL;
+	int i = 0, j;
+
+	dprintk("%s(%llu, %llu)\n", __func__, offset, length);
+	/* Create storage for up to three new extents e1, e2, e3 */
+	e1 = kmalloc(sizeof(*e1), GFP_ATOMIC);
+	e2 = kmalloc(sizeof(*e2), GFP_ATOMIC);
+	e3 = kmalloc(sizeof(*e3), GFP_ATOMIC);
+	/* BUG - we are ignoring any failure */
+	if (!e1 || !e2 || !e3)
+		goto out_nosplit;
+
+	spin_lock(&bl->bl_ext_lock);
+	be = bl_find_get_extent_locked(bl, offset);
+	rv = be->be_f_offset + be->be_length;
+	if (be->be_state != PNFS_BLOCK_INVALID_DATA) {
+		spin_unlock(&bl->bl_ext_lock);
+		goto out_nosplit;
+	}
+	/* Add e* to children, bumping e*'s krefs */
+	if (be->be_f_offset != offset) {
+		_prep_new_extent(e1, be, be->be_f_offset,
+				 offset - be->be_f_offset,
+				 PNFS_BLOCK_INVALID_DATA);
+		children[i++] = e1;
+		print_bl_extent(e1);
+	} else
+		merge1 = e1;
+	_prep_new_extent(e2, be, offset,
+			 min(length, be->be_f_offset + be->be_length - offset),
+			 PNFS_BLOCK_READWRITE_DATA);
+	children[i++] = e2;
+	print_bl_extent(e2);
+	if (offset + length < be->be_f_offset + be->be_length) {
+		_prep_new_extent(e3, be, e2->be_f_offset + e2->be_length,
+				 be->be_f_offset + be->be_length -
+				 offset - length,
+				 PNFS_BLOCK_INVALID_DATA);
+		children[i++] = e3;
+		print_bl_extent(e3);
+	} else
+		merge2 = e3;
+
+	/* Remove be from list, and insert the e* */
+	/* We don't get refs on e*, since this list is the base reference
+	 * set when init'ed.
+	 */
+	if (i < 3)
+		children[i] = NULL;
+	new = children[0];
+	list_replace(&be->be_node, &new->be_node);
+	bl_put_extent(be);
+	new = _front_merge(new, &bl->bl_extents[RW_EXTENT], merge1);
+	for (j = 1; j < i; j++) {
+		old = new;
+		new = children[j];
+		list_add(&new->be_node, &old->be_node);
+	}
+	if (merge2) {
+		/* This is a HACK, should just create a _back_merge function */
+		new = list_entry(new->be_node.next,
+				 struct pnfs_block_extent, be_node);
+		new = _front_merge(new, &bl->bl_extents[RW_EXTENT], merge2);
+	}
+	spin_unlock(&bl->bl_ext_lock);
+
+	/* Since we removed the base reference above, be is now scheduled for
+	 * destruction.
+	 */
+	bl_put_extent(be);
+	dprintk("%s returns %llu after split\n", __func__, rv);
+	return rv;
+
+ out_nosplit:
+	kfree(e1);
+	kfree(e2);
+	kfree(e3);
+	dprintk("%s returns %llu without splitting\n", __func__, rv);
+	return rv;
+}
+
+void
+clean_pnfs_block_layoutupdate(struct pnfs_block_layout *bl,
+			      const struct nfs4_layoutcommit_args *arg,
+			      int status)
+{
+	struct pnfs_block_short_extent *lce, *save;
+
+	dprintk("%s status %d\n", __func__, status);
+	list_for_each_entry_safe(lce, save, &bl->bl_committing, bse_node) {
+		if (likely(!status)) {
+			u64 offset = lce->bse_f_offset;
+			u64 end = offset + lce->bse_length;
+
+			do {
+				offset = set_to_rw(bl, offset, end - offset);
+			} while (offset < end);
+			list_del(&lce->bse_node);
+
+			kfree(lce);
+		} else {
+			list_del(&lce->bse_node);
+			spin_lock(&bl->bl_ext_lock);
+			add_to_commitlist(bl, lce);
+			spin_unlock(&bl->bl_ext_lock);
+		}
+	}
+}
diff --git a/fs/nfs/cache_lib.h b/fs/nfs/cache_lib.h
index 76f856e284e4..7cf6cafcc007 100644
--- a/fs/nfs/cache_lib.h
+++ b/fs/nfs/cache_lib.h
@@ -6,7 +6,7 @@
 
 #include <linux/completion.h>
 #include <linux/sunrpc/cache.h>
-#include <asm/atomic.h>
+#include <linux/atomic.h>
 
 /*
  * Deferred request handling
diff --git a/fs/nfs/callback.h b/fs/nfs/callback.h
index b257383bb565..07df5f1d85e5 100644
--- a/fs/nfs/callback.h
+++ b/fs/nfs/callback.h
@@ -38,6 +38,7 @@ enum nfs4_callback_opnum {
 struct cb_process_state {
 	__be32			drc_status;
 	struct nfs_client	*clp;
+	int			slotid;
 };
 
 struct cb_compound_hdr_arg {
@@ -166,7 +167,6 @@ extern unsigned nfs4_callback_layoutrecall(
 	void *dummy, struct cb_process_state *cps);
 
 extern void nfs4_check_drain_bc_complete(struct nfs4_session *ses);
-extern void nfs4_cb_take_slot(struct nfs_client *clp);
 
 struct cb_devicenotifyitem {
 	uint32_t		cbd_notify_type;
diff --git a/fs/nfs/callback_proc.c b/fs/nfs/callback_proc.c
index d4d1954e9bb9..43926add945b 100644
--- a/fs/nfs/callback_proc.c
+++ b/fs/nfs/callback_proc.c
@@ -111,6 +111,7 @@ int nfs4_validate_delegation_stateid(struct nfs_delegation *delegation, const nf
 static u32 initiate_file_draining(struct nfs_client *clp,
 				  struct cb_layoutrecallargs *args)
 {
+	struct nfs_server *server;
 	struct pnfs_layout_hdr *lo;
 	struct inode *ino;
 	bool found = false;
@@ -118,21 +119,28 @@ static u32 initiate_file_draining(struct nfs_client *clp,
 	LIST_HEAD(free_me_list);
 
 	spin_lock(&clp->cl_lock);
-	list_for_each_entry(lo, &clp->cl_layouts, plh_layouts) {
-		if (nfs_compare_fh(&args->cbl_fh,
-				   &NFS_I(lo->plh_inode)->fh))
-			continue;
-		ino = igrab(lo->plh_inode);
-		if (!ino)
-			continue;
-		found = true;
-		/* Without this, layout can be freed as soon
-		 * as we release cl_lock.
-		 */
-		get_layout_hdr(lo);
-		break;
+	rcu_read_lock();
+	list_for_each_entry_rcu(server, &clp->cl_superblocks, client_link) {
+		list_for_each_entry(lo, &server->layouts, plh_layouts) {
+			if (nfs_compare_fh(&args->cbl_fh,
+					   &NFS_I(lo->plh_inode)->fh))
+				continue;
+			ino = igrab(lo->plh_inode);
+			if (!ino)
+				continue;
+			found = true;
+			/* Without this, layout can be freed as soon
+			 * as we release cl_lock.
+			 */
+			get_layout_hdr(lo);
+			break;
+		}
+		if (found)
+			break;
 	}
+	rcu_read_unlock();
 	spin_unlock(&clp->cl_lock);
+
 	if (!found)
 		return NFS4ERR_NOMATCHING_LAYOUT;
 
@@ -154,6 +162,7 @@ static u32 initiate_file_draining(struct nfs_client *clp,
 static u32 initiate_bulk_draining(struct nfs_client *clp,
 				  struct cb_layoutrecallargs *args)
 {
+	struct nfs_server *server;
 	struct pnfs_layout_hdr *lo;
 	struct inode *ino;
 	u32 rv = NFS4ERR_NOMATCHING_LAYOUT;
@@ -167,18 +176,24 @@ static u32 initiate_bulk_draining(struct nfs_client *clp,
 	};
 
 	spin_lock(&clp->cl_lock);
-	list_for_each_entry(lo, &clp->cl_layouts, plh_layouts) {
+	rcu_read_lock();
+	list_for_each_entry_rcu(server, &clp->cl_superblocks, client_link) {
 		if ((args->cbl_recall_type == RETURN_FSID) &&
-		    memcmp(&NFS_SERVER(lo->plh_inode)->fsid,
-			   &args->cbl_fsid, sizeof(struct nfs_fsid)))
-			continue;
-		if (!igrab(lo->plh_inode))
+		    memcmp(&server->fsid, &args->cbl_fsid,
+			   sizeof(struct nfs_fsid)))
 			continue;
-		get_layout_hdr(lo);
-		BUG_ON(!list_empty(&lo->plh_bulk_recall));
-		list_add(&lo->plh_bulk_recall, &recall_list);
+
+		list_for_each_entry(lo, &server->layouts, plh_layouts) {
+			if (!igrab(lo->plh_inode))
+				continue;
+			get_layout_hdr(lo);
+			BUG_ON(!list_empty(&lo->plh_bulk_recall));
+			list_add(&lo->plh_bulk_recall, &recall_list);
+		}
 	}
+	rcu_read_unlock();
 	spin_unlock(&clp->cl_lock);
+
 	list_for_each_entry_safe(lo, tmp,
 				 &recall_list, plh_bulk_recall) {
 		ino = lo->plh_inode;
@@ -333,7 +348,7 @@ validate_seqid(struct nfs4_slot_table *tbl, struct cb_sequenceargs * args)
 	/* Normal */
 	if (likely(args->csa_sequenceid == slot->seq_nr + 1)) {
 		slot->seq_nr++;
-		return htonl(NFS4_OK);
+		goto out_ok;
 	}
 
 	/* Replay */
@@ -352,11 +367,14 @@ validate_seqid(struct nfs4_slot_table *tbl, struct cb_sequenceargs * args)
 	/* Wraparound */
 	if (args->csa_sequenceid == 1 && (slot->seq_nr + 1) == 0) {
 		slot->seq_nr = 1;
-		return htonl(NFS4_OK);
+		goto out_ok;
 	}
 
 	/* Misordered request */
 	return htonl(NFS4ERR_SEQ_MISORDERED);
+out_ok:
+	tbl->highest_used_slotid = args->csa_slotid;
+	return htonl(NFS4_OK);
 }
 
 /*
@@ -418,26 +436,37 @@ __be32 nfs4_callback_sequence(struct cb_sequenceargs *args,
 			      struct cb_sequenceres *res,
 			      struct cb_process_state *cps)
 {
+	struct nfs4_slot_table *tbl;
 	struct nfs_client *clp;
 	int i;
 	__be32 status = htonl(NFS4ERR_BADSESSION);
 
-	cps->clp = NULL;
-
 	clp = nfs4_find_client_sessionid(args->csa_addr, &args->csa_sessionid);
 	if (clp == NULL)
 		goto out;
 
+	tbl = &clp->cl_session->bc_slot_table;
+
+	spin_lock(&tbl->slot_tbl_lock);
 	/* state manager is resetting the session */
 	if (test_bit(NFS4_SESSION_DRAINING, &clp->cl_session->session_state)) {
-		status = NFS4ERR_DELAY;
+		spin_unlock(&tbl->slot_tbl_lock);
+		status = htonl(NFS4ERR_DELAY);
+		/* Return NFS4ERR_BADSESSION if we're draining the session
+		 * in order to reset it.
+		 */
+		if (test_bit(NFS4CLNT_SESSION_RESET, &clp->cl_state))
+			status = htonl(NFS4ERR_BADSESSION);
 		goto out;
 	}
 
 	status = validate_seqid(&clp->cl_session->bc_slot_table, args);
+	spin_unlock(&tbl->slot_tbl_lock);
 	if (status)
 		goto out;
 
+	cps->slotid = args->csa_slotid;
+
 	/*
 	 * Check for pending referring calls.  If a match is found, a
 	 * related callback was received before the response to the original
@@ -454,7 +483,6 @@ __be32 nfs4_callback_sequence(struct cb_sequenceargs *args,
 	res->csr_slotid = args->csa_slotid;
 	res->csr_highestslotid = NFS41_BC_MAX_CALLBACKS - 1;
 	res->csr_target_highestslotid = NFS41_BC_MAX_CALLBACKS - 1;
-	nfs4_cb_take_slot(clp);
 
 out:
 	cps->clp = clp; /* put in nfs4_callback_compound */
diff --git a/fs/nfs/callback_xdr.c b/fs/nfs/callback_xdr.c
index c6c86a77e043..918ad647afea 100644
--- a/fs/nfs/callback_xdr.c
+++ b/fs/nfs/callback_xdr.c
@@ -754,26 +754,15 @@ static void nfs4_callback_free_slot(struct nfs4_session *session)
 	 * Let the state manager know callback processing done.
 	 * A single slot, so highest used slotid is either 0 or -1
 	 */
-	tbl->highest_used_slotid--;
+	tbl->highest_used_slotid = -1;
 	nfs4_check_drain_bc_complete(session);
 	spin_unlock(&tbl->slot_tbl_lock);
 }
 
-static void nfs4_cb_free_slot(struct nfs_client *clp)
+static void nfs4_cb_free_slot(struct cb_process_state *cps)
 {
-	if (clp && clp->cl_session)
-		nfs4_callback_free_slot(clp->cl_session);
-}
-
-/* A single slot, so highest used slotid is either 0 or -1 */
-void nfs4_cb_take_slot(struct nfs_client *clp)
-{
-	struct nfs4_slot_table *tbl = &clp->cl_session->bc_slot_table;
-
-	spin_lock(&tbl->slot_tbl_lock);
-	tbl->highest_used_slotid++;
-	BUG_ON(tbl->highest_used_slotid != 0);
-	spin_unlock(&tbl->slot_tbl_lock);
+	if (cps->slotid != -1)
+		nfs4_callback_free_slot(cps->clp->cl_session);
 }
 
 #else /* CONFIG_NFS_V4_1 */
@@ -784,7 +773,7 @@ preprocess_nfs41_op(int nop, unsigned int op_nr, struct callback_op **op)
 	return htonl(NFS4ERR_MINOR_VERS_MISMATCH);
 }
 
-static void nfs4_cb_free_slot(struct nfs_client *clp)
+static void nfs4_cb_free_slot(struct cb_process_state *cps)
 {
 }
 #endif /* CONFIG_NFS_V4_1 */
@@ -866,6 +855,7 @@ static __be32 nfs4_callback_compound(struct svc_rqst *rqstp, void *argp, void *r
 	struct cb_process_state cps = {
 		.drc_status = 0,
 		.clp = NULL,
+		.slotid = -1,
 	};
 	unsigned int nops = 0;
 
@@ -906,7 +896,7 @@ static __be32 nfs4_callback_compound(struct svc_rqst *rqstp, void *argp, void *r
 
 	*hdr_res.status = status;
 	*hdr_res.nops = htonl(nops);
-	nfs4_cb_free_slot(cps.clp);
+	nfs4_cb_free_slot(&cps);
 	nfs_put_client(cps.clp);
 	dprintk("%s: done, status = %u\n", __func__, ntohl(status));
 	return rpc_success;
diff --git a/fs/nfs/client.c b/fs/nfs/client.c
index b3dc2b88b65b..5833fbbf59b0 100644
--- a/fs/nfs/client.c
+++ b/fs/nfs/client.c
@@ -105,7 +105,7 @@ struct rpc_program nfs_program = {
 	.nrvers			= ARRAY_SIZE(nfs_version),
 	.version		= nfs_version,
 	.stats			= &nfs_rpcstat,
-	.pipe_dir_name		= "/nfs",
+	.pipe_dir_name		= NFS_PIPE_DIRNAME,
 };
 
 struct rpc_stat nfs_rpcstat = {
@@ -188,9 +188,6 @@ static struct nfs_client *nfs_alloc_client(const struct nfs_client_initdata *cl_
 	cred = rpc_lookup_machine_cred();
 	if (!IS_ERR(cred))
 		clp->cl_machine_cred = cred;
-#if defined(CONFIG_NFS_V4_1)
-	INIT_LIST_HEAD(&clp->cl_layouts);
-#endif
 	nfs_fscache_get_client_cookie(clp);
 
 	return clp;
@@ -293,6 +290,7 @@ static void nfs_free_client(struct nfs_client *clp)
 	nfs4_deviceid_purge_client(clp);
 
 	kfree(clp->cl_hostname);
+	kfree(clp->server_scope);
 	kfree(clp);
 
 	dprintk("<-- nfs_free_client()\n");
@@ -906,7 +904,9 @@ error:
 /*
  * Load up the server record from information gained in an fsinfo record
  */
-static void nfs_server_set_fsinfo(struct nfs_server *server, struct nfs_fsinfo *fsinfo)
+static void nfs_server_set_fsinfo(struct nfs_server *server,
+				  struct nfs_fh *mntfh,
+				  struct nfs_fsinfo *fsinfo)
 {
 	unsigned long max_rpc_payload;
 
@@ -936,7 +936,8 @@ static void nfs_server_set_fsinfo(struct nfs_server *server, struct nfs_fsinfo *
 	if (server->wsize > NFS_MAX_FILE_IO_SIZE)
 		server->wsize = NFS_MAX_FILE_IO_SIZE;
 	server->wpages = (server->wsize + PAGE_CACHE_SIZE - 1) >> PAGE_CACHE_SHIFT;
-	set_pnfs_layoutdriver(server, fsinfo->layouttype);
+	server->pnfs_blksize = fsinfo->blksize;
+	set_pnfs_layoutdriver(server, mntfh, fsinfo->layouttype);
 
 	server->wtmult = nfs_block_bits(fsinfo->wtmult, NULL);
 
@@ -982,7 +983,7 @@ static int nfs_probe_fsinfo(struct nfs_server *server, struct nfs_fh *mntfh, str
 	if (error < 0)
 		goto out_error;
 
-	nfs_server_set_fsinfo(server, &fsinfo);
+	nfs_server_set_fsinfo(server, mntfh, &fsinfo);
 
 	/* Get some general file system info */
 	if (server->namelen == 0) {
@@ -1062,6 +1063,7 @@ static struct nfs_server *nfs_alloc_server(void)
 	INIT_LIST_HEAD(&server->client_link);
 	INIT_LIST_HEAD(&server->master_link);
 	INIT_LIST_HEAD(&server->delegations);
+	INIT_LIST_HEAD(&server->layouts);
 
 	atomic_set(&server->active, 0);
 
@@ -1464,7 +1466,7 @@ struct nfs_client *nfs4_set_ds_client(struct nfs_client* mds_clp,
 	dprintk("<-- %s %p\n", __func__, clp);
 	return clp;
 }
-EXPORT_SYMBOL(nfs4_set_ds_client);
+EXPORT_SYMBOL_GPL(nfs4_set_ds_client);
 
 /*
  * Session has been established, and the client marked ready.
diff --git a/fs/nfs/delegation.c b/fs/nfs/delegation.c
index dd25c2aec375..321a66bc3846 100644
--- a/fs/nfs/delegation.c
+++ b/fs/nfs/delegation.c
@@ -398,12 +398,11 @@ int nfs_inode_return_delegation(struct inode *inode)
 	return err;
 }
 
-static void nfs_mark_return_delegation(struct nfs_delegation *delegation)
+static void nfs_mark_return_delegation(struct nfs_server *server,
+		struct nfs_delegation *delegation)
 {
-	struct nfs_client *clp = NFS_SERVER(delegation->inode)->nfs_client;
-
 	set_bit(NFS_DELEGATION_RETURN, &delegation->flags);
-	set_bit(NFS4CLNT_DELEGRETURN, &clp->cl_state);
+	set_bit(NFS4CLNT_DELEGRETURN, &server->nfs_client->cl_state);
 }
 
 /**
@@ -441,7 +440,7 @@ static void nfs_mark_return_all_delegation_types(struct nfs_server *server,
 		if ((delegation->type == (FMODE_READ|FMODE_WRITE)) && !(flags & FMODE_WRITE))
 			continue;
 		if (delegation->type & flags)
-			nfs_mark_return_delegation(delegation);
+			nfs_mark_return_delegation(server, delegation);
 	}
 }
 
@@ -508,7 +507,7 @@ static void nfs_mark_return_unreferenced_delegations(struct nfs_server *server)
 	list_for_each_entry_rcu(delegation, &server->delegations, super_list) {
 		if (test_and_clear_bit(NFS_DELEGATION_REFERENCED, &delegation->flags))
 			continue;
-		nfs_mark_return_delegation(delegation);
+		nfs_mark_return_delegation(server, delegation);
 	}
 }
 
@@ -539,7 +538,8 @@ void nfs_expire_unreferenced_delegations(struct nfs_client *clp)
 int nfs_async_inode_return_delegation(struct inode *inode,
 				      const nfs4_stateid *stateid)
 {
-	struct nfs_client *clp = NFS_SERVER(inode)->nfs_client;
+	struct nfs_server *server = NFS_SERVER(inode);
+	struct nfs_client *clp = server->nfs_client;
 	struct nfs_delegation *delegation;
 
 	rcu_read_lock();
@@ -549,7 +549,7 @@ int nfs_async_inode_return_delegation(struct inode *inode,
 		rcu_read_unlock();
 		return -ENOENT;
 	}
-	nfs_mark_return_delegation(delegation);
+	nfs_mark_return_delegation(server, delegation);
 	rcu_read_unlock();
 
 	nfs_delegation_run_state_manager(clp);
diff --git a/fs/nfs/dir.c b/fs/nfs/dir.c
index 57f578e2560a..b238d95ac48c 100644
--- a/fs/nfs/dir.c
+++ b/fs/nfs/dir.c
@@ -134,18 +134,19 @@ const struct inode_operations nfs4_dir_inode_operations = {
 
 #endif /* CONFIG_NFS_V4 */
 
-static struct nfs_open_dir_context *alloc_nfs_open_dir_context(struct rpc_cred *cred)
+static struct nfs_open_dir_context *alloc_nfs_open_dir_context(struct inode *dir, struct rpc_cred *cred)
 {
 	struct nfs_open_dir_context *ctx;
 	ctx = kmalloc(sizeof(*ctx), GFP_KERNEL);
 	if (ctx != NULL) {
 		ctx->duped = 0;
+		ctx->attr_gencount = NFS_I(dir)->attr_gencount;
 		ctx->dir_cookie = 0;
 		ctx->dup_cookie = 0;
 		ctx->cred = get_rpccred(cred);
-	} else
-		ctx = ERR_PTR(-ENOMEM);
-	return ctx;
+		return ctx;
+	}
+	return  ERR_PTR(-ENOMEM);
 }
 
 static void put_nfs_open_dir_context(struct nfs_open_dir_context *ctx)
@@ -173,7 +174,7 @@ nfs_opendir(struct inode *inode, struct file *filp)
 	cred = rpc_lookup_cred();
 	if (IS_ERR(cred))
 		return PTR_ERR(cred);
-	ctx = alloc_nfs_open_dir_context(cred);
+	ctx = alloc_nfs_open_dir_context(inode, cred);
 	if (IS_ERR(ctx)) {
 		res = PTR_ERR(ctx);
 		goto out;
@@ -323,7 +324,6 @@ int nfs_readdir_search_for_pos(struct nfs_cache_array *array, nfs_readdir_descri
 {
 	loff_t diff = desc->file->f_pos - desc->current_index;
 	unsigned int index;
-	struct nfs_open_dir_context *ctx = desc->file->private_data;
 
 	if (diff < 0)
 		goto out_eof;
@@ -336,7 +336,6 @@ int nfs_readdir_search_for_pos(struct nfs_cache_array *array, nfs_readdir_descri
 	index = (unsigned int)diff;
 	*desc->dir_cookie = array->array[index].cookie;
 	desc->cache_entry_index = index;
-	ctx->duped = 0;
 	return 0;
 out_eof:
 	desc->eof = 1;
@@ -349,14 +348,34 @@ int nfs_readdir_search_for_cookie(struct nfs_cache_array *array, nfs_readdir_des
 	int i;
 	loff_t new_pos;
 	int status = -EAGAIN;
-	struct nfs_open_dir_context *ctx = desc->file->private_data;
 
 	for (i = 0; i < array->size; i++) {
 		if (array->array[i].cookie == *desc->dir_cookie) {
+			struct nfs_inode *nfsi = NFS_I(desc->file->f_path.dentry->d_inode);
+			struct nfs_open_dir_context *ctx = desc->file->private_data;
+
 			new_pos = desc->current_index + i;
-			if (new_pos < desc->file->f_pos) {
+			if (ctx->attr_gencount != nfsi->attr_gencount
+			    || (nfsi->cache_validity & (NFS_INO_INVALID_ATTR|NFS_INO_INVALID_DATA))) {
+				ctx->duped = 0;
+				ctx->attr_gencount = nfsi->attr_gencount;
+			} else if (new_pos < desc->file->f_pos) {
+				if (ctx->duped > 0
+				    && ctx->dup_cookie == *desc->dir_cookie) {
+					if (printk_ratelimit()) {
+						pr_notice("NFS: directory %s/%s contains a readdir loop."
+								"Please contact your server vendor.  "
+								"The file: %s has duplicate cookie %llu\n",
+								desc->file->f_dentry->d_parent->d_name.name,
+								desc->file->f_dentry->d_name.name,
+								array->array[i].string.name,
+								*desc->dir_cookie);
+					}
+					status = -ELOOP;
+					goto out;
+				}
 				ctx->dup_cookie = *desc->dir_cookie;
-				ctx->duped = 1;
+				ctx->duped = -1;
 			}
 			desc->file->f_pos = new_pos;
 			desc->cache_entry_index = i;
@@ -368,6 +387,7 @@ int nfs_readdir_search_for_cookie(struct nfs_cache_array *array, nfs_readdir_des
 		if (*desc->dir_cookie == array->last_cookie)
 			desc->eof = 1;
 	}
+out:
 	return status;
 }
 
@@ -740,19 +760,6 @@ int nfs_do_filldir(nfs_readdir_descriptor_t *desc, void *dirent,
 	struct nfs_cache_array *array = NULL;
 	struct nfs_open_dir_context *ctx = file->private_data;
 
-	if (ctx->duped != 0 && ctx->dup_cookie == *desc->dir_cookie) {
-		if (printk_ratelimit()) {
-			pr_notice("NFS: directory %s/%s contains a readdir loop.  "
-				"Please contact your server vendor.  "
-				"Offending cookie: %llu\n",
-				file->f_dentry->d_parent->d_name.name,
-				file->f_dentry->d_name.name,
-				*desc->dir_cookie);
-		}
-		res = -ELOOP;
-		goto out;
-	}
-
 	array = nfs_readdir_get_array(desc->page);
 	if (IS_ERR(array)) {
 		res = PTR_ERR(array);
@@ -774,6 +781,8 @@ int nfs_do_filldir(nfs_readdir_descriptor_t *desc, void *dirent,
 			*desc->dir_cookie = array->array[i+1].cookie;
 		else
 			*desc->dir_cookie = array->last_cookie;
+		if (ctx->duped != 0)
+			ctx->duped = 1;
 	}
 	if (array->eof_index >= 0)
 		desc->eof = 1;
@@ -805,6 +814,7 @@ int uncached_readdir(nfs_readdir_descriptor_t *desc, void *dirent,
 	struct page	*page = NULL;
 	int		status;
 	struct inode *inode = desc->file->f_path.dentry->d_inode;
+	struct nfs_open_dir_context *ctx = desc->file->private_data;
 
 	dfprintk(DIRCACHE, "NFS: uncached_readdir() searching for cookie %Lu\n",
 			(unsigned long long)*desc->dir_cookie);
@@ -818,6 +828,7 @@ int uncached_readdir(nfs_readdir_descriptor_t *desc, void *dirent,
 	desc->page_index = 0;
 	desc->last_cookie = *desc->dir_cookie;
 	desc->page = page;
+	ctx->duped = 0;
 
 	status = nfs_readdir_xdr_to_array(desc, page, inode);
 	if (status < 0)
diff --git a/fs/nfs/direct.c b/fs/nfs/direct.c
index b35d25b98da6..1940f1a56a5f 100644
--- a/fs/nfs/direct.c
+++ b/fs/nfs/direct.c
@@ -53,7 +53,7 @@
 
 #include <asm/system.h>
 #include <asm/uaccess.h>
-#include <asm/atomic.h>
+#include <linux/atomic.h>
 
 #include "internal.h"
 #include "iostat.h"
diff --git a/fs/nfs/internal.h b/fs/nfs/internal.h
index 2a55347a2daa..ab12913dd473 100644
--- a/fs/nfs/internal.h
+++ b/fs/nfs/internal.h
@@ -277,6 +277,9 @@ extern void nfs_sb_deactive(struct super_block *sb);
 extern char *nfs_path(char **p, struct dentry *dentry,
 		      char *buffer, ssize_t buflen);
 extern struct vfsmount *nfs_d_automount(struct path *path);
+#ifdef CONFIG_NFS_V4
+rpc_authflavor_t nfs_find_best_sec(struct nfs4_secinfo_flavors *);
+#endif
 
 /* getroot.c */
 extern struct dentry *nfs_get_root(struct super_block *, struct nfs_fh *,
@@ -288,12 +291,22 @@ extern struct dentry *nfs4_get_root(struct super_block *, struct nfs_fh *,
 extern int nfs4_get_rootfh(struct nfs_server *server, struct nfs_fh *mntfh);
 #endif
 
+struct nfs_pageio_descriptor;
 /* read.c */
 extern int nfs_initiate_read(struct nfs_read_data *data, struct rpc_clnt *clnt,
 			     const struct rpc_call_ops *call_ops);
 extern void nfs_read_prepare(struct rpc_task *task, void *calldata);
+extern int nfs_generic_pagein(struct nfs_pageio_descriptor *desc,
+		struct list_head *head);
+
+extern void nfs_pageio_reset_read_mds(struct nfs_pageio_descriptor *pgio);
+extern void nfs_readdata_release(struct nfs_read_data *rdata);
 
 /* write.c */
+extern int nfs_generic_flush(struct nfs_pageio_descriptor *desc,
+		struct list_head *head);
+extern void nfs_pageio_reset_write_mds(struct nfs_pageio_descriptor *pgio);
+extern void nfs_writedata_release(struct nfs_write_data *wdata);
 extern void nfs_commit_free(struct nfs_write_data *p);
 extern int nfs_initiate_write(struct nfs_write_data *data,
 			      struct rpc_clnt *clnt,
diff --git a/fs/nfs/namespace.c b/fs/nfs/namespace.c
index 1f063bacd285..8102391bb374 100644
--- a/fs/nfs/namespace.c
+++ b/fs/nfs/namespace.c
@@ -119,7 +119,7 @@ Elong:
 }
 
 #ifdef CONFIG_NFS_V4
-static rpc_authflavor_t nfs_find_best_sec(struct nfs4_secinfo_flavors *flavors)
+rpc_authflavor_t nfs_find_best_sec(struct nfs4_secinfo_flavors *flavors)
 {
 	struct gss_api_mech *mech;
 	struct xdr_netobj oid;
diff --git a/fs/nfs/nfs3acl.c b/fs/nfs/nfs3acl.c
index e49e73107e62..7ef23979896d 100644
--- a/fs/nfs/nfs3acl.c
+++ b/fs/nfs/nfs3acl.c
@@ -415,7 +415,7 @@ fail:
 }
 
 int nfs3_proc_set_default_acl(struct inode *dir, struct inode *inode,
-		mode_t mode)
+		umode_t mode)
 {
 	struct posix_acl *dfacl, *acl;
 	int error = 0;
diff --git a/fs/nfs/nfs3proc.c b/fs/nfs/nfs3proc.c
index 38053d823eb0..85f1690ca08c 100644
--- a/fs/nfs/nfs3proc.c
+++ b/fs/nfs/nfs3proc.c
@@ -316,7 +316,7 @@ nfs3_proc_create(struct inode *dir, struct dentry *dentry, struct iattr *sattr,
 		 int flags, struct nfs_open_context *ctx)
 {
 	struct nfs3_createdata *data;
-	mode_t mode = sattr->ia_mode;
+	umode_t mode = sattr->ia_mode;
 	int status = -ENOMEM;
 
 	dprintk("NFS call  create %s\n", dentry->d_name.name);
@@ -562,7 +562,7 @@ static int
 nfs3_proc_mkdir(struct inode *dir, struct dentry *dentry, struct iattr *sattr)
 {
 	struct nfs3_createdata *data;
-	int mode = sattr->ia_mode;
+	umode_t mode = sattr->ia_mode;
 	int status = -ENOMEM;
 
 	dprintk("NFS call  mkdir %s\n", dentry->d_name.name);
@@ -681,7 +681,7 @@ nfs3_proc_mknod(struct inode *dir, struct dentry *dentry, struct iattr *sattr,
 		dev_t rdev)
 {
 	struct nfs3_createdata *data;
-	mode_t mode = sattr->ia_mode;
+	umode_t mode = sattr->ia_mode;
 	int status = -ENOMEM;
 
 	dprintk("NFS call  mknod %s %u:%u\n", dentry->d_name.name,
diff --git a/fs/nfs/nfs4_fs.h b/fs/nfs/nfs4_fs.h
index b788f2eb1ba0..1ec1a85fa71c 100644
--- a/fs/nfs/nfs4_fs.h
+++ b/fs/nfs/nfs4_fs.h
@@ -48,6 +48,7 @@ enum nfs4_client_state {
 	NFS4CLNT_SESSION_RESET,
 	NFS4CLNT_RECALL_SLOT,
 	NFS4CLNT_LEASE_CONFIRM,
+	NFS4CLNT_SERVER_SCOPE_MISMATCH,
 };
 
 enum nfs4_session_state {
@@ -66,6 +67,8 @@ struct nfs4_minor_version_ops {
 			int cache_reply);
 	int	(*validate_stateid)(struct nfs_delegation *,
 			const nfs4_stateid *);
+	int	(*find_root_sec)(struct nfs_server *, struct nfs_fh *,
+			struct nfs_fsinfo *);
 	const struct nfs4_state_recovery_ops *reboot_recovery_ops;
 	const struct nfs4_state_recovery_ops *nograce_recovery_ops;
 	const struct nfs4_state_maintenance_ops *state_renewal_ops;
@@ -315,7 +318,7 @@ extern const struct nfs4_minor_version_ops *nfs_v4_minor_ops[];
 extern const u32 nfs4_fattr_bitmap[2];
 extern const u32 nfs4_statfs_bitmap[2];
 extern const u32 nfs4_pathconf_bitmap[2];
-extern const u32 nfs4_fsinfo_bitmap[2];
+extern const u32 nfs4_fsinfo_bitmap[3];
 extern const u32 nfs4_fs_locations_bitmap[2];
 
 /* nfs4renewd.c */
@@ -349,6 +352,8 @@ extern void nfs4_schedule_state_manager(struct nfs_client *);
 extern void nfs4_schedule_stateid_recovery(const struct nfs_server *, struct nfs4_state *);
 extern void nfs41_handle_sequence_flag_errors(struct nfs_client *clp, u32 flags);
 extern void nfs41_handle_recall_slot(struct nfs_client *clp);
+extern void nfs41_handle_server_scope(struct nfs_client *,
+				      struct server_scope **);
 extern void nfs4_put_lock_state(struct nfs4_lock_state *lsp);
 extern int nfs4_set_lock_state(struct nfs4_state *state, struct file_lock *fl);
 extern void nfs4_copy_stateid(nfs4_stateid *, struct nfs4_state *, fl_owner_t, pid_t);
diff --git a/fs/nfs/nfs4filelayout.c b/fs/nfs/nfs4filelayout.c
index f9d03abcd04c..e8915d4840ad 100644
--- a/fs/nfs/nfs4filelayout.c
+++ b/fs/nfs/nfs4filelayout.c
@@ -170,7 +170,7 @@ filelayout_set_layoutcommit(struct nfs_write_data *wdata)
 
 	pnfs_set_layoutcommit(wdata);
 	dprintk("%s ionde %lu pls_end_pos %lu\n", __func__, wdata->inode->i_ino,
-		(unsigned long) wdata->lseg->pls_end_pos);
+		(unsigned long) NFS_I(wdata->inode)->layout->plh_lwb);
 }
 
 /*
@@ -334,6 +334,9 @@ filelayout_read_pagelist(struct nfs_read_data *data)
 		__func__, data->inode->i_ino,
 		data->args.pgbase, (size_t)data->args.count, offset);
 
+	if (test_bit(NFS_DEVICEID_INVALID, &FILELAYOUT_DEVID_NODE(lseg)->flags))
+		return PNFS_NOT_ATTEMPTED;
+
 	/* Retrieve the correct rpc_client for the byte range */
 	j = nfs4_fl_calc_j_index(lseg, offset);
 	idx = nfs4_fl_calc_ds_index(lseg, j);
@@ -344,8 +347,7 @@ filelayout_read_pagelist(struct nfs_read_data *data)
 		set_bit(lo_fail_bit(IOMODE_READ), &lseg->pls_layout->plh_flags);
 		return PNFS_NOT_ATTEMPTED;
 	}
-	dprintk("%s USE DS:ip %x %hu\n", __func__,
-		ntohl(ds->ds_ip_addr), ntohs(ds->ds_port));
+	dprintk("%s USE DS: %s\n", __func__, ds->ds_remotestr);
 
 	/* No multipath support. Use first DS */
 	data->ds_clp = ds->ds_clp;
@@ -374,6 +376,9 @@ filelayout_write_pagelist(struct nfs_write_data *data, int sync)
 	struct nfs_fh *fh;
 	int status;
 
+	if (test_bit(NFS_DEVICEID_INVALID, &FILELAYOUT_DEVID_NODE(lseg)->flags))
+		return PNFS_NOT_ATTEMPTED;
+
 	/* Retrieve the correct rpc_client for the byte range */
 	j = nfs4_fl_calc_j_index(lseg, offset);
 	idx = nfs4_fl_calc_ds_index(lseg, j);
@@ -384,9 +389,9 @@ filelayout_write_pagelist(struct nfs_write_data *data, int sync)
 		set_bit(lo_fail_bit(IOMODE_READ), &lseg->pls_layout->plh_flags);
 		return PNFS_NOT_ATTEMPTED;
 	}
-	dprintk("%s ino %lu sync %d req %Zu@%llu DS:%x:%hu\n", __func__,
+	dprintk("%s ino %lu sync %d req %Zu@%llu DS: %s\n", __func__,
 		data->inode->i_ino, sync, (size_t) data->args.count, offset,
-		ntohl(ds->ds_ip_addr), ntohs(ds->ds_port));
+		ds->ds_remotestr);
 
 	data->write_done_cb = filelayout_write_done_cb;
 	data->ds_clp = ds->ds_clp;
@@ -428,6 +433,14 @@ filelayout_check_layout(struct pnfs_layout_hdr *lo,
 
 	dprintk("--> %s\n", __func__);
 
+	/* FIXME: remove this check when layout segment support is added */
+	if (lgr->range.offset != 0 ||
+	    lgr->range.length != NFS4_MAX_UINT64) {
+		dprintk("%s Only whole file layouts supported. Use MDS i/o\n",
+			__func__);
+		goto out;
+	}
+
 	if (fl->pattern_offset > lgr->range.offset) {
 		dprintk("%s pattern_offset %lld too large\n",
 				__func__, fl->pattern_offset);
@@ -449,6 +462,10 @@ filelayout_check_layout(struct pnfs_layout_hdr *lo,
 			goto out;
 	} else
 		dsaddr = container_of(d, struct nfs4_file_layout_dsaddr, id_node);
+	/* Found deviceid is being reaped */
+	if (test_bit(NFS_DEVICEID_INVALID, &dsaddr->id_node.flags))
+			goto out_put;
+
 	fl->dsaddr = dsaddr;
 
 	if (fl->first_stripe_index < 0 ||
@@ -659,7 +676,7 @@ filelayout_alloc_lseg(struct pnfs_layout_hdr *layoutid,
  * return true  : coalesce page
  * return false : don't coalesce page
  */
-bool
+static bool
 filelayout_pg_test(struct nfs_pageio_descriptor *pgio, struct nfs_page *prev,
 		   struct nfs_page *req)
 {
@@ -670,8 +687,6 @@ filelayout_pg_test(struct nfs_pageio_descriptor *pgio, struct nfs_page *prev,
 	    !nfs_generic_pg_test(pgio, prev, req))
 		return false;
 
-	if (!pgio->pg_lseg)
-		return 1;
 	p_stripe = (u64)prev->wb_index << PAGE_CACHE_SHIFT;
 	r_stripe = (u64)req->wb_index << PAGE_CACHE_SHIFT;
 	stripe_unit = FILELAYOUT_LSEG(pgio->pg_lseg)->stripe_unit;
@@ -682,6 +697,52 @@ filelayout_pg_test(struct nfs_pageio_descriptor *pgio, struct nfs_page *prev,
 	return (p_stripe == r_stripe);
 }
 
+void
+filelayout_pg_init_read(struct nfs_pageio_descriptor *pgio,
+			struct nfs_page *req)
+{
+	BUG_ON(pgio->pg_lseg != NULL);
+
+	pgio->pg_lseg = pnfs_update_layout(pgio->pg_inode,
+					   req->wb_context,
+					   0,
+					   NFS4_MAX_UINT64,
+					   IOMODE_READ,
+					   GFP_KERNEL);
+	/* If no lseg, fall back to read through mds */
+	if (pgio->pg_lseg == NULL)
+		nfs_pageio_reset_read_mds(pgio);
+}
+
+void
+filelayout_pg_init_write(struct nfs_pageio_descriptor *pgio,
+			 struct nfs_page *req)
+{
+	BUG_ON(pgio->pg_lseg != NULL);
+
+	pgio->pg_lseg = pnfs_update_layout(pgio->pg_inode,
+					   req->wb_context,
+					   0,
+					   NFS4_MAX_UINT64,
+					   IOMODE_RW,
+					   GFP_NOFS);
+	/* If no lseg, fall back to write through mds */
+	if (pgio->pg_lseg == NULL)
+		nfs_pageio_reset_write_mds(pgio);
+}
+
+static const struct nfs_pageio_ops filelayout_pg_read_ops = {
+	.pg_init = filelayout_pg_init_read,
+	.pg_test = filelayout_pg_test,
+	.pg_doio = pnfs_generic_pg_readpages,
+};
+
+static const struct nfs_pageio_ops filelayout_pg_write_ops = {
+	.pg_init = filelayout_pg_init_write,
+	.pg_test = filelayout_pg_test,
+	.pg_doio = pnfs_generic_pg_writepages,
+};
+
 static bool filelayout_mark_pnfs_commit(struct pnfs_layout_segment *lseg)
 {
 	return !FILELAYOUT_LSEG(lseg)->commit_through_mds;
@@ -879,7 +940,8 @@ static struct pnfs_layoutdriver_type filelayout_type = {
 	.owner			= THIS_MODULE,
 	.alloc_lseg		= filelayout_alloc_lseg,
 	.free_lseg		= filelayout_free_lseg,
-	.pg_test		= filelayout_pg_test,
+	.pg_read_ops		= &filelayout_pg_read_ops,
+	.pg_write_ops		= &filelayout_pg_write_ops,
 	.mark_pnfs_commit	= filelayout_mark_pnfs_commit,
 	.choose_commit_list	= filelayout_choose_commit_list,
 	.commit_pagelist	= filelayout_commit_pagelist,
@@ -902,5 +964,7 @@ static void __exit nfs4filelayout_exit(void)
 	pnfs_unregister_layoutdriver(&filelayout_type);
 }
 
+MODULE_ALIAS("nfs-layouttype4-1");
+
 module_init(nfs4filelayout_init);
 module_exit(nfs4filelayout_exit);
diff --git a/fs/nfs/nfs4filelayout.h b/fs/nfs/nfs4filelayout.h
index cebe01e3795e..2e42284253fa 100644
--- a/fs/nfs/nfs4filelayout.h
+++ b/fs/nfs/nfs4filelayout.h
@@ -47,10 +47,17 @@ enum stripetype4 {
 };
 
 /* Individual ip address */
+struct nfs4_pnfs_ds_addr {
+	struct sockaddr_storage	da_addr;
+	size_t			da_addrlen;
+	struct list_head	da_node;  /* nfs4_pnfs_dev_hlist dev_dslist */
+	char			*da_remotestr;	/* human readable addr+port */
+};
+
 struct nfs4_pnfs_ds {
 	struct list_head	ds_node;  /* nfs4_pnfs_dev_hlist dev_dslist */
-	u32			ds_ip_addr;
-	u32			ds_port;
+	char			*ds_remotestr;	/* comma sep list of addrs */
+	struct list_head	ds_addrs;
 	struct nfs_client	*ds_clp;
 	atomic_t		ds_count;
 };
@@ -89,6 +96,12 @@ FILELAYOUT_LSEG(struct pnfs_layout_segment *lseg)
 			    generic_hdr);
 }
 
+static inline struct nfs4_deviceid_node *
+FILELAYOUT_DEVID_NODE(struct pnfs_layout_segment *lseg)
+{
+	return &FILELAYOUT_LSEG(lseg)->dsaddr->id_node;
+}
+
 extern struct nfs_fh *
 nfs4_fl_select_ds_fh(struct pnfs_layout_segment *lseg, u32 j);
 
diff --git a/fs/nfs/nfs4filelayoutdev.c b/fs/nfs/nfs4filelayoutdev.c
index 3b7bf1377264..ed388aae9689 100644
--- a/fs/nfs/nfs4filelayoutdev.c
+++ b/fs/nfs/nfs4filelayoutdev.c
@@ -56,54 +56,139 @@ print_ds(struct nfs4_pnfs_ds *ds)
 		printk("%s NULL device\n", __func__);
 		return;
 	}
-	printk("        ip_addr %x port %hu\n"
+	printk("        ds %s\n"
 		"        ref count %d\n"
 		"        client %p\n"
 		"        cl_exchange_flags %x\n",
-		ntohl(ds->ds_ip_addr), ntohs(ds->ds_port),
+		ds->ds_remotestr,
 		atomic_read(&ds->ds_count), ds->ds_clp,
 		ds->ds_clp ? ds->ds_clp->cl_exchange_flags : 0);
 }
 
-/* nfs4_ds_cache_lock is held */
-static struct nfs4_pnfs_ds *
-_data_server_lookup_locked(u32 ip_addr, u32 port)
+static bool
+same_sockaddr(struct sockaddr *addr1, struct sockaddr *addr2)
 {
-	struct nfs4_pnfs_ds *ds;
+	struct sockaddr_in *a, *b;
+	struct sockaddr_in6 *a6, *b6;
+
+	if (addr1->sa_family != addr2->sa_family)
+		return false;
+
+	switch (addr1->sa_family) {
+	case AF_INET:
+		a = (struct sockaddr_in *)addr1;
+		b = (struct sockaddr_in *)addr2;
+
+		if (a->sin_addr.s_addr == b->sin_addr.s_addr &&
+		    a->sin_port == b->sin_port)
+			return true;
+		break;
+
+	case AF_INET6:
+		a6 = (struct sockaddr_in6 *)addr1;
+		b6 = (struct sockaddr_in6 *)addr2;
+
+		/* LINKLOCAL addresses must have matching scope_id */
+		if (ipv6_addr_scope(&a6->sin6_addr) ==
+		    IPV6_ADDR_SCOPE_LINKLOCAL &&
+		    a6->sin6_scope_id != b6->sin6_scope_id)
+			return false;
+
+		if (ipv6_addr_equal(&a6->sin6_addr, &b6->sin6_addr) &&
+		    a6->sin6_port == b6->sin6_port)
+			return true;
+		break;
+
+	default:
+		dprintk("%s: unhandled address family: %u\n",
+			__func__, addr1->sa_family);
+		return false;
+	}
 
-	dprintk("_data_server_lookup: ip_addr=%x port=%hu\n",
-			ntohl(ip_addr), ntohs(port));
+	return false;
+}
 
-	list_for_each_entry(ds, &nfs4_data_server_cache, ds_node) {
-		if (ds->ds_ip_addr == ip_addr &&
-		    ds->ds_port == port) {
-			return ds;
+/*
+ * Lookup DS by addresses.  The first matching address returns true.
+ * nfs4_ds_cache_lock is held
+ */
+static struct nfs4_pnfs_ds *
+_data_server_lookup_locked(struct list_head *dsaddrs)
+{
+	struct nfs4_pnfs_ds *ds;
+	struct nfs4_pnfs_ds_addr *da1, *da2;
+
+	list_for_each_entry(da1, dsaddrs, da_node) {
+		list_for_each_entry(ds, &nfs4_data_server_cache, ds_node) {
+			list_for_each_entry(da2, &ds->ds_addrs, da_node) {
+				if (same_sockaddr(
+					(struct sockaddr *)&da1->da_addr,
+					(struct sockaddr *)&da2->da_addr))
+					return ds;
+			}
 		}
 	}
 	return NULL;
 }
 
 /*
+ * Compare two lists of addresses.
+ */
+static bool
+_data_server_match_all_addrs_locked(struct list_head *dsaddrs1,
+				    struct list_head *dsaddrs2)
+{
+	struct nfs4_pnfs_ds_addr *da1, *da2;
+	size_t count1 = 0,
+	       count2 = 0;
+
+	list_for_each_entry(da1, dsaddrs1, da_node)
+		count1++;
+
+	list_for_each_entry(da2, dsaddrs2, da_node) {
+		bool found = false;
+		count2++;
+		list_for_each_entry(da1, dsaddrs1, da_node) {
+			if (same_sockaddr((struct sockaddr *)&da1->da_addr,
+				(struct sockaddr *)&da2->da_addr)) {
+				found = true;
+				break;
+			}
+		}
+		if (!found)
+			return false;
+	}
+
+	return (count1 == count2);
+}
+
+/*
  * Create an rpc connection to the nfs4_pnfs_ds data server
- * Currently only support IPv4
+ * Currently only supports IPv4 and IPv6 addresses
  */
 static int
 nfs4_ds_connect(struct nfs_server *mds_srv, struct nfs4_pnfs_ds *ds)
 {
-	struct nfs_client *clp;
-	struct sockaddr_in sin;
+	struct nfs_client *clp = ERR_PTR(-EIO);
+	struct nfs4_pnfs_ds_addr *da;
 	int status = 0;
 
-	dprintk("--> %s ip:port %x:%hu au_flavor %d\n", __func__,
-		ntohl(ds->ds_ip_addr), ntohs(ds->ds_port),
+	dprintk("--> %s DS %s au_flavor %d\n", __func__, ds->ds_remotestr,
 		mds_srv->nfs_client->cl_rpcclient->cl_auth->au_flavor);
 
-	sin.sin_family = AF_INET;
-	sin.sin_addr.s_addr = ds->ds_ip_addr;
-	sin.sin_port = ds->ds_port;
+	BUG_ON(list_empty(&ds->ds_addrs));
+
+	list_for_each_entry(da, &ds->ds_addrs, da_node) {
+		dprintk("%s: DS %s: trying address %s\n",
+			__func__, ds->ds_remotestr, da->da_remotestr);
+
+		clp = nfs4_set_ds_client(mds_srv->nfs_client,
+				 (struct sockaddr *)&da->da_addr,
+				 da->da_addrlen, IPPROTO_TCP);
+		if (!IS_ERR(clp))
+			break;
+	}
 
-	clp = nfs4_set_ds_client(mds_srv->nfs_client, (struct sockaddr *)&sin,
-				 sizeof(sin), IPPROTO_TCP);
 	if (IS_ERR(clp)) {
 		status = PTR_ERR(clp);
 		goto out;
@@ -115,8 +200,8 @@ nfs4_ds_connect(struct nfs_server *mds_srv, struct nfs4_pnfs_ds *ds)
 			goto out_put;
 		}
 		ds->ds_clp = clp;
-		dprintk("%s [existing] ip=%x, port=%hu\n", __func__,
-			ntohl(ds->ds_ip_addr), ntohs(ds->ds_port));
+		dprintk("%s [existing] server=%s\n", __func__,
+			ds->ds_remotestr);
 		goto out;
 	}
 
@@ -135,8 +220,7 @@ nfs4_ds_connect(struct nfs_server *mds_srv, struct nfs4_pnfs_ds *ds)
 		goto out_put;
 
 	ds->ds_clp = clp;
-	dprintk("%s [new] ip=%x, port=%hu\n", __func__, ntohl(ds->ds_ip_addr),
-		ntohs(ds->ds_port));
+	dprintk("%s [new] addr: %s\n", __func__, ds->ds_remotestr);
 out:
 	return status;
 out_put:
@@ -147,12 +231,25 @@ out_put:
 static void
 destroy_ds(struct nfs4_pnfs_ds *ds)
 {
+	struct nfs4_pnfs_ds_addr *da;
+
 	dprintk("--> %s\n", __func__);
 	ifdebug(FACILITY)
 		print_ds(ds);
 
 	if (ds->ds_clp)
 		nfs_put_client(ds->ds_clp);
+
+	while (!list_empty(&ds->ds_addrs)) {
+		da = list_first_entry(&ds->ds_addrs,
+				      struct nfs4_pnfs_ds_addr,
+				      da_node);
+		list_del_init(&da->da_node);
+		kfree(da->da_remotestr);
+		kfree(da);
+	}
+
+	kfree(ds->ds_remotestr);
 	kfree(ds);
 }
 
@@ -179,31 +276,96 @@ nfs4_fl_free_deviceid(struct nfs4_file_layout_dsaddr *dsaddr)
 	kfree(dsaddr);
 }
 
+/*
+ * Create a string with a human readable address and port to avoid
+ * complicated setup around many dprinks.
+ */
+static char *
+nfs4_pnfs_remotestr(struct list_head *dsaddrs, gfp_t gfp_flags)
+{
+	struct nfs4_pnfs_ds_addr *da;
+	char *remotestr;
+	size_t len;
+	char *p;
+
+	len = 3;        /* '{', '}' and eol */
+	list_for_each_entry(da, dsaddrs, da_node) {
+		len += strlen(da->da_remotestr) + 1;    /* string plus comma */
+	}
+
+	remotestr = kzalloc(len, gfp_flags);
+	if (!remotestr)
+		return NULL;
+
+	p = remotestr;
+	*(p++) = '{';
+	len--;
+	list_for_each_entry(da, dsaddrs, da_node) {
+		size_t ll = strlen(da->da_remotestr);
+
+		if (ll > len)
+			goto out_err;
+
+		memcpy(p, da->da_remotestr, ll);
+		p += ll;
+		len -= ll;
+
+		if (len < 1)
+			goto out_err;
+		(*p++) = ',';
+		len--;
+	}
+	if (len < 2)
+		goto out_err;
+	*(p++) = '}';
+	*p = '\0';
+	return remotestr;
+out_err:
+	kfree(remotestr);
+	return NULL;
+}
+
 static struct nfs4_pnfs_ds *
-nfs4_pnfs_ds_add(struct inode *inode, u32 ip_addr, u32 port, gfp_t gfp_flags)
+nfs4_pnfs_ds_add(struct list_head *dsaddrs, gfp_t gfp_flags)
 {
-	struct nfs4_pnfs_ds *tmp_ds, *ds;
+	struct nfs4_pnfs_ds *tmp_ds, *ds = NULL;
+	char *remotestr;
 
-	ds = kzalloc(sizeof(*tmp_ds), gfp_flags);
+	if (list_empty(dsaddrs)) {
+		dprintk("%s: no addresses defined\n", __func__);
+		goto out;
+	}
+
+	ds = kzalloc(sizeof(*ds), gfp_flags);
 	if (!ds)
 		goto out;
 
+	/* this is only used for debugging, so it's ok if its NULL */
+	remotestr = nfs4_pnfs_remotestr(dsaddrs, gfp_flags);
+
 	spin_lock(&nfs4_ds_cache_lock);
-	tmp_ds = _data_server_lookup_locked(ip_addr, port);
+	tmp_ds = _data_server_lookup_locked(dsaddrs);
 	if (tmp_ds == NULL) {
-		ds->ds_ip_addr = ip_addr;
-		ds->ds_port = port;
+		INIT_LIST_HEAD(&ds->ds_addrs);
+		list_splice_init(dsaddrs, &ds->ds_addrs);
+		ds->ds_remotestr = remotestr;
 		atomic_set(&ds->ds_count, 1);
 		INIT_LIST_HEAD(&ds->ds_node);
 		ds->ds_clp = NULL;
 		list_add(&ds->ds_node, &nfs4_data_server_cache);
-		dprintk("%s add new data server ip 0x%x\n", __func__,
-			ds->ds_ip_addr);
+		dprintk("%s add new data server %s\n", __func__,
+			ds->ds_remotestr);
 	} else {
+		if (!_data_server_match_all_addrs_locked(&tmp_ds->ds_addrs,
+							 dsaddrs)) {
+			dprintk("%s:  multipath address mismatch: %s != %s",
+				__func__, tmp_ds->ds_remotestr, remotestr);
+		}
+		kfree(remotestr);
 		kfree(ds);
 		atomic_inc(&tmp_ds->ds_count);
-		dprintk("%s data server found ip 0x%x, inc'ed ds_count to %d\n",
-			__func__, tmp_ds->ds_ip_addr,
+		dprintk("%s data server %s found, inc'ed ds_count to %d\n",
+			__func__, tmp_ds->ds_remotestr,
 			atomic_read(&tmp_ds->ds_count));
 		ds = tmp_ds;
 	}
@@ -213,18 +375,22 @@ out:
 }
 
 /*
- * Currently only support ipv4, and one multi-path address.
+ * Currently only supports ipv4, ipv6 and one multi-path address.
  */
-static struct nfs4_pnfs_ds *
-decode_and_add_ds(struct xdr_stream *streamp, struct inode *inode, gfp_t gfp_flags)
+static struct nfs4_pnfs_ds_addr *
+decode_ds_addr(struct xdr_stream *streamp, gfp_t gfp_flags)
 {
-	struct nfs4_pnfs_ds *ds = NULL;
-	char *buf;
-	const char *ipend, *pstr;
-	u32 ip_addr, port;
-	int nlen, rlen, i;
+	struct nfs4_pnfs_ds_addr *da = NULL;
+	char *buf, *portstr;
+	u32 port;
+	int nlen, rlen;
 	int tmp[2];
 	__be32 *p;
+	char *netid, *match_netid;
+	size_t len, match_netid_len;
+	char *startsep = "";
+	char *endsep = "";
+
 
 	/* r_netid */
 	p = xdr_inline_decode(streamp, 4);
@@ -236,64 +402,123 @@ decode_and_add_ds(struct xdr_stream *streamp, struct inode *inode, gfp_t gfp_fla
 	if (unlikely(!p))
 		goto out_err;
 
-	/* Check that netid is "tcp" */
-	if (nlen != 3 ||  memcmp((char *)p, "tcp", 3)) {
-		dprintk("%s: ERROR: non ipv4 TCP r_netid\n", __func__);
+	netid = kmalloc(nlen+1, gfp_flags);
+	if (unlikely(!netid))
 		goto out_err;
-	}
 
-	/* r_addr */
+	netid[nlen] = '\0';
+	memcpy(netid, p, nlen);
+
+	/* r_addr: ip/ip6addr with port in dec octets - see RFC 5665 */
 	p = xdr_inline_decode(streamp, 4);
 	if (unlikely(!p))
-		goto out_err;
+		goto out_free_netid;
 	rlen = be32_to_cpup(p);
 
 	p = xdr_inline_decode(streamp, rlen);
 	if (unlikely(!p))
-		goto out_err;
+		goto out_free_netid;
 
-	/* ipv6 length plus port is legal */
-	if (rlen > INET6_ADDRSTRLEN + 8) {
+	/* port is ".ABC.DEF", 8 chars max */
+	if (rlen > INET6_ADDRSTRLEN + IPV6_SCOPE_ID_LEN + 8) {
 		dprintk("%s: Invalid address, length %d\n", __func__,
 			rlen);
-		goto out_err;
+		goto out_free_netid;
 	}
 	buf = kmalloc(rlen + 1, gfp_flags);
 	if (!buf) {
 		dprintk("%s: Not enough memory\n", __func__);
-		goto out_err;
+		goto out_free_netid;
 	}
 	buf[rlen] = '\0';
 	memcpy(buf, p, rlen);
 
-	/* replace the port dots with dashes for the in4_pton() delimiter*/
-	for (i = 0; i < 2; i++) {
-		char *res = strrchr(buf, '.');
-		if (!res) {
-			dprintk("%s: Failed finding expected dots in port\n",
-				__func__);
-			goto out_free;
-		}
-		*res = '-';
+	/* replace port '.' with '-' */
+	portstr = strrchr(buf, '.');
+	if (!portstr) {
+		dprintk("%s: Failed finding expected dot in port\n",
+			__func__);
+		goto out_free_buf;
+	}
+	*portstr = '-';
+
+	/* find '.' between address and port */
+	portstr = strrchr(buf, '.');
+	if (!portstr) {
+		dprintk("%s: Failed finding expected dot between address and "
+			"port\n", __func__);
+		goto out_free_buf;
 	}
+	*portstr = '\0';
 
-	/* Currently only support ipv4 address */
-	if (in4_pton(buf, rlen, (u8 *)&ip_addr, '-', &ipend) == 0) {
-		dprintk("%s: Only ipv4 addresses supported\n", __func__);
-		goto out_free;
+	da = kzalloc(sizeof(*da), gfp_flags);
+	if (unlikely(!da))
+		goto out_free_buf;
+
+	INIT_LIST_HEAD(&da->da_node);
+
+	if (!rpc_pton(buf, portstr-buf, (struct sockaddr *)&da->da_addr,
+		      sizeof(da->da_addr))) {
+		dprintk("%s: error parsing address %s\n", __func__, buf);
+		goto out_free_da;
 	}
 
-	/* port */
-	pstr = ipend;
-	sscanf(pstr, "-%d-%d", &tmp[0], &tmp[1]);
+	portstr++;
+	sscanf(portstr, "%d-%d", &tmp[0], &tmp[1]);
 	port = htons((tmp[0] << 8) | (tmp[1]));
 
-	ds = nfs4_pnfs_ds_add(inode, ip_addr, port, gfp_flags);
-	dprintk("%s: Decoded address and port %s\n", __func__, buf);
-out_free:
+	switch (da->da_addr.ss_family) {
+	case AF_INET:
+		((struct sockaddr_in *)&da->da_addr)->sin_port = port;
+		da->da_addrlen = sizeof(struct sockaddr_in);
+		match_netid = "tcp";
+		match_netid_len = 3;
+		break;
+
+	case AF_INET6:
+		((struct sockaddr_in6 *)&da->da_addr)->sin6_port = port;
+		da->da_addrlen = sizeof(struct sockaddr_in6);
+		match_netid = "tcp6";
+		match_netid_len = 4;
+		startsep = "[";
+		endsep = "]";
+		break;
+
+	default:
+		dprintk("%s: unsupported address family: %u\n",
+			__func__, da->da_addr.ss_family);
+		goto out_free_da;
+	}
+
+	if (nlen != match_netid_len || strncmp(netid, match_netid, nlen)) {
+		dprintk("%s: ERROR: r_netid \"%s\" != \"%s\"\n",
+			__func__, netid, match_netid);
+		goto out_free_da;
+	}
+
+	/* save human readable address */
+	len = strlen(startsep) + strlen(buf) + strlen(endsep) + 7;
+	da->da_remotestr = kzalloc(len, gfp_flags);
+
+	/* NULL is ok, only used for dprintk */
+	if (da->da_remotestr)
+		snprintf(da->da_remotestr, len, "%s%s%s:%u", startsep,
+			 buf, endsep, ntohs(port));
+
+	dprintk("%s: Parsed DS addr %s\n", __func__, da->da_remotestr);
 	kfree(buf);
+	kfree(netid);
+	return da;
+
+out_free_da:
+	kfree(da);
+out_free_buf:
+	dprintk("%s: Error parsing DS addr: %s\n", __func__, buf);
+	kfree(buf);
+out_free_netid:
+	kfree(netid);
 out_err:
-	return ds;
+	return NULL;
 }
 
 /* Decode opaque device data and return the result */
@@ -310,6 +535,8 @@ decode_device(struct inode *ino, struct pnfs_device *pdev, gfp_t gfp_flags)
 	struct xdr_stream stream;
 	struct xdr_buf buf;
 	struct page *scratch;
+	struct list_head dsaddrs;
+	struct nfs4_pnfs_ds_addr *da;
 
 	/* set up xdr stream */
 	scratch = alloc_page(gfp_flags);
@@ -386,6 +613,8 @@ decode_device(struct inode *ino, struct pnfs_device *pdev, gfp_t gfp_flags)
 				NFS_SERVER(ino)->nfs_client,
 				&pdev->dev_id);
 
+	INIT_LIST_HEAD(&dsaddrs);
+
 	for (i = 0; i < dsaddr->ds_num; i++) {
 		int j;
 		u32 mp_count;
@@ -395,48 +624,43 @@ decode_device(struct inode *ino, struct pnfs_device *pdev, gfp_t gfp_flags)
 			goto out_err_free_deviceid;
 
 		mp_count = be32_to_cpup(p); /* multipath count */
-		if (mp_count > 1) {
-			printk(KERN_WARNING
-			       "%s: Multipath count %d not supported, "
-			       "skipping all greater than 1\n", __func__,
-				mp_count);
-		}
 		for (j = 0; j < mp_count; j++) {
-			if (j == 0) {
-				dsaddr->ds_list[i] = decode_and_add_ds(&stream,
-					ino, gfp_flags);
-				if (dsaddr->ds_list[i] == NULL)
-					goto out_err_free_deviceid;
-			} else {
-				u32 len;
-				/* skip extra multipath */
-
-				/* read len, skip */
-				p = xdr_inline_decode(&stream, 4);
-				if (unlikely(!p))
-					goto out_err_free_deviceid;
-				len = be32_to_cpup(p);
-
-				p = xdr_inline_decode(&stream, len);
-				if (unlikely(!p))
-					goto out_err_free_deviceid;
-
-				/* read len, skip */
-				p = xdr_inline_decode(&stream, 4);
-				if (unlikely(!p))
-					goto out_err_free_deviceid;
-				len = be32_to_cpup(p);
-
-				p = xdr_inline_decode(&stream, len);
-				if (unlikely(!p))
-					goto out_err_free_deviceid;
-			}
+			da = decode_ds_addr(&stream, gfp_flags);
+			if (da)
+				list_add_tail(&da->da_node, &dsaddrs);
+		}
+		if (list_empty(&dsaddrs)) {
+			dprintk("%s: no suitable DS addresses found\n",
+				__func__);
+			goto out_err_free_deviceid;
+		}
+
+		dsaddr->ds_list[i] = nfs4_pnfs_ds_add(&dsaddrs, gfp_flags);
+		if (!dsaddr->ds_list[i])
+			goto out_err_drain_dsaddrs;
+
+		/* If DS was already in cache, free ds addrs */
+		while (!list_empty(&dsaddrs)) {
+			da = list_first_entry(&dsaddrs,
+					      struct nfs4_pnfs_ds_addr,
+					      da_node);
+			list_del_init(&da->da_node);
+			kfree(da->da_remotestr);
+			kfree(da);
 		}
 	}
 
 	__free_page(scratch);
 	return dsaddr;
 
+out_err_drain_dsaddrs:
+	while (!list_empty(&dsaddrs)) {
+		da = list_first_entry(&dsaddrs, struct nfs4_pnfs_ds_addr,
+				      da_node);
+		list_del_init(&da->da_node);
+		kfree(da->da_remotestr);
+		kfree(da);
+	}
 out_err_free_deviceid:
 	nfs4_fl_free_deviceid(dsaddr);
 	/* stripe_indicies was part of dsaddr */
@@ -591,13 +815,13 @@ nfs4_fl_select_ds_fh(struct pnfs_layout_segment *lseg, u32 j)
 
 static void
 filelayout_mark_devid_negative(struct nfs4_file_layout_dsaddr *dsaddr,
-			       int err, u32 ds_addr)
+			       int err, const char *ds_remotestr)
 {
 	u32 *p = (u32 *)&dsaddr->id_node.deviceid;
 
-	printk(KERN_ERR "NFS: data server %x connection error %d."
+	printk(KERN_ERR "NFS: data server %s connection error %d."
 		" Deviceid [%x%x%x%x] marked out of use.\n",
-		ds_addr, err, p[0], p[1], p[2], p[3]);
+		ds_remotestr, err, p[0], p[1], p[2], p[3]);
 
 	spin_lock(&nfs4_ds_cache_lock);
 	dsaddr->flags |= NFS4_DEVICE_ID_NEG_ENTRY;
@@ -628,7 +852,7 @@ nfs4_fl_prepare_ds(struct pnfs_layout_segment *lseg, u32 ds_idx)
 		err = nfs4_ds_connect(s, ds);
 		if (err) {
 			filelayout_mark_devid_negative(dsaddr, err,
-						       ntohl(ds->ds_ip_addr));
+						       ds->ds_remotestr);
 			return NULL;
 		}
 	}
diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c
index 26bece8f3083..8c77039e7a81 100644
--- a/fs/nfs/nfs4proc.c
+++ b/fs/nfs/nfs4proc.c
@@ -80,7 +80,10 @@ static int _nfs4_proc_getattr(struct nfs_server *server, struct nfs_fh *fhandle,
 static int nfs4_do_setattr(struct inode *inode, struct rpc_cred *cred,
 			    struct nfs_fattr *fattr, struct iattr *sattr,
 			    struct nfs4_state *state);
-
+#ifdef CONFIG_NFS_V4_1
+static int nfs41_test_stateid(struct nfs_server *, struct nfs4_state *);
+static int nfs41_free_stateid(struct nfs_server *, struct nfs4_state *);
+#endif
 /* Prevent leaks of NFSv4 errors into userland */
 static int nfs4_map_errors(int err)
 {
@@ -137,12 +140,13 @@ const u32 nfs4_pathconf_bitmap[2] = {
 	0
 };
 
-const u32 nfs4_fsinfo_bitmap[2] = { FATTR4_WORD0_MAXFILESIZE
+const u32 nfs4_fsinfo_bitmap[3] = { FATTR4_WORD0_MAXFILESIZE
 			| FATTR4_WORD0_MAXREAD
 			| FATTR4_WORD0_MAXWRITE
 			| FATTR4_WORD0_LEASE_TIME,
 			FATTR4_WORD1_TIME_DELTA
-			| FATTR4_WORD1_FS_LAYOUT_TYPES
+			| FATTR4_WORD1_FS_LAYOUT_TYPES,
+			FATTR4_WORD2_LAYOUT_BLKSIZE
 };
 
 const u32 nfs4_fs_locations_bitmap[2] = {
@@ -1689,6 +1693,20 @@ static int nfs4_open_expired(struct nfs4_state_owner *sp, struct nfs4_state *sta
 	return ret;
 }
 
+#if defined(CONFIG_NFS_V4_1)
+static int nfs41_open_expired(struct nfs4_state_owner *sp, struct nfs4_state *state)
+{
+	int status;
+	struct nfs_server *server = NFS_SERVER(state->inode);
+
+	status = nfs41_test_stateid(server, state);
+	if (status == NFS_OK)
+		return 0;
+	nfs41_free_stateid(server, state);
+	return nfs4_open_expired(sp, state);
+}
+#endif
+
 /*
  * on an EXCLUSIVE create, the server should send back a bitmask with FATTR4-*
  * fields corresponding to attributes that were used to store the verifier.
@@ -2252,13 +2270,14 @@ static int nfs4_find_root_sec(struct nfs_server *server, struct nfs_fh *fhandle,
 static int nfs4_proc_get_root(struct nfs_server *server, struct nfs_fh *fhandle,
 			      struct nfs_fsinfo *info)
 {
+	int minor_version = server->nfs_client->cl_minorversion;
 	int status = nfs4_lookup_root(server, fhandle, info);
 	if ((status == -NFS4ERR_WRONGSEC) && !(server->flags & NFS_MOUNT_SECFLAVOUR))
 		/*
 		 * A status of -NFS4ERR_WRONGSEC will be mapped to -EPERM
 		 * by nfs4_map_errors() as this function exits.
 		 */
-		status = nfs4_find_root_sec(server, fhandle, info);
+		status = nfs_v4_minor_ops[minor_version]->find_root_sec(server, fhandle, info);
 	if (status == 0)
 		status = nfs4_server_capabilities(server, fhandle);
 	if (status == 0)
@@ -4441,6 +4460,20 @@ out:
 	return err;
 }
 
+#if defined(CONFIG_NFS_V4_1)
+static int nfs41_lock_expired(struct nfs4_state *state, struct file_lock *request)
+{
+	int status;
+	struct nfs_server *server = NFS_SERVER(state->inode);
+
+	status = nfs41_test_stateid(server, state);
+	if (status == NFS_OK)
+		return 0;
+	nfs41_free_stateid(server, state);
+	return nfs4_lock_expired(state, request);
+}
+#endif
+
 static int _nfs4_proc_setlk(struct nfs4_state *state, int cmd, struct file_lock *request)
 {
 	struct nfs_inode *nfsi = NFS_I(state->inode);
@@ -4779,6 +4812,16 @@ out_inval:
 	return -NFS4ERR_INVAL;
 }
 
+static bool
+nfs41_same_server_scope(struct server_scope *a, struct server_scope *b)
+{
+	if (a->server_scope_sz == b->server_scope_sz &&
+	    memcmp(a->server_scope, b->server_scope, a->server_scope_sz) == 0)
+		return true;
+
+	return false;
+}
+
 /*
  * nfs4_proc_exchange_id()
  *
@@ -4821,9 +4864,31 @@ int nfs4_proc_exchange_id(struct nfs_client *clp, struct rpc_cred *cred)
 				init_utsname()->domainname,
 				clp->cl_rpcclient->cl_auth->au_flavor);
 
+	res.server_scope = kzalloc(sizeof(struct server_scope), GFP_KERNEL);
+	if (unlikely(!res.server_scope))
+		return -ENOMEM;
+
 	status = rpc_call_sync(clp->cl_rpcclient, &msg, RPC_TASK_TIMEOUT);
 	if (!status)
 		status = nfs4_check_cl_exchange_flags(clp->cl_exchange_flags);
+
+	if (!status) {
+		if (clp->server_scope &&
+		    !nfs41_same_server_scope(clp->server_scope,
+					     res.server_scope)) {
+			dprintk("%s: server_scope mismatch detected\n",
+				__func__);
+			set_bit(NFS4CLNT_SERVER_SCOPE_MISMATCH, &clp->cl_state);
+			kfree(clp->server_scope);
+			clp->server_scope = NULL;
+		}
+
+		if (!clp->server_scope)
+			clp->server_scope = res.server_scope;
+		else
+			kfree(res.server_scope);
+	}
+
 	dprintk("<-- %s status= %d\n", __func__, status);
 	return status;
 }
@@ -5704,7 +5769,7 @@ static void nfs4_layoutreturn_done(struct rpc_task *task, void *calldata)
 {
 	struct nfs4_layoutreturn *lrp = calldata;
 	struct nfs_server *server;
-	struct pnfs_layout_hdr *lo = NFS_I(lrp->args.inode)->layout;
+	struct pnfs_layout_hdr *lo = lrp->args.layout;
 
 	dprintk("--> %s\n", __func__);
 
@@ -5733,7 +5798,7 @@ static void nfs4_layoutreturn_release(void *calldata)
 	struct nfs4_layoutreturn *lrp = calldata;
 
 	dprintk("--> %s\n", __func__);
-	put_layout_hdr(NFS_I(lrp->args.inode)->layout);
+	put_layout_hdr(lrp->args.layout);
 	kfree(calldata);
 	dprintk("<-- %s\n", __func__);
 }
@@ -5770,6 +5835,54 @@ int nfs4_proc_layoutreturn(struct nfs4_layoutreturn *lrp)
 	return status;
 }
 
+/*
+ * Retrieve the list of Data Server devices from the MDS.
+ */
+static int _nfs4_getdevicelist(struct nfs_server *server,
+				    const struct nfs_fh *fh,
+				    struct pnfs_devicelist *devlist)
+{
+	struct nfs4_getdevicelist_args args = {
+		.fh = fh,
+		.layoutclass = server->pnfs_curr_ld->id,
+	};
+	struct nfs4_getdevicelist_res res = {
+		.devlist = devlist,
+	};
+	struct rpc_message msg = {
+		.rpc_proc = &nfs4_procedures[NFSPROC4_CLNT_GETDEVICELIST],
+		.rpc_argp = &args,
+		.rpc_resp = &res,
+	};
+	int status;
+
+	dprintk("--> %s\n", __func__);
+	status = nfs4_call_sync(server->client, server, &msg, &args.seq_args,
+				&res.seq_res, 0);
+	dprintk("<-- %s status=%d\n", __func__, status);
+	return status;
+}
+
+int nfs4_proc_getdevicelist(struct nfs_server *server,
+			    const struct nfs_fh *fh,
+			    struct pnfs_devicelist *devlist)
+{
+	struct nfs4_exception exception = { };
+	int err;
+
+	do {
+		err = nfs4_handle_exception(server,
+				_nfs4_getdevicelist(server, fh, devlist),
+				&exception);
+	} while (exception.retry);
+
+	dprintk("%s: err=%d, num_devs=%u\n", __func__,
+		err, devlist->num_devs);
+
+	return err;
+}
+EXPORT_SYMBOL_GPL(nfs4_proc_getdevicelist);
+
 static int
 _nfs4_proc_getdeviceinfo(struct nfs_server *server, struct pnfs_device *pdev)
 {
@@ -5848,9 +5961,16 @@ nfs4_layoutcommit_done(struct rpc_task *task, void *calldata)
 static void nfs4_layoutcommit_release(void *calldata)
 {
 	struct nfs4_layoutcommit_data *data = calldata;
+	struct pnfs_layout_segment *lseg, *tmp;
 
+	pnfs_cleanup_layoutcommit(data);
 	/* Matched by references in pnfs_set_layoutcommit */
-	put_lseg(data->lseg);
+	list_for_each_entry_safe(lseg, tmp, &data->lseg_list, pls_lc_list) {
+		list_del_init(&lseg->pls_lc_list);
+		if (test_and_clear_bit(NFS_LSEG_LAYOUTCOMMIT,
+				       &lseg->pls_flags))
+			put_lseg(lseg);
+	}
 	put_rpccred(data->cred);
 	kfree(data);
 }
@@ -5901,6 +6021,143 @@ out:
 	rpc_put_task(task);
 	return status;
 }
+
+static int
+_nfs41_proc_secinfo_no_name(struct nfs_server *server, struct nfs_fh *fhandle,
+		    struct nfs_fsinfo *info, struct nfs4_secinfo_flavors *flavors)
+{
+	struct nfs41_secinfo_no_name_args args = {
+		.style = SECINFO_STYLE_CURRENT_FH,
+	};
+	struct nfs4_secinfo_res res = {
+		.flavors = flavors,
+	};
+	struct rpc_message msg = {
+		.rpc_proc = &nfs4_procedures[NFSPROC4_CLNT_SECINFO_NO_NAME],
+		.rpc_argp = &args,
+		.rpc_resp = &res,
+	};
+	return nfs4_call_sync(server->client, server, &msg, &args.seq_args, &res.seq_res, 0);
+}
+
+static int
+nfs41_proc_secinfo_no_name(struct nfs_server *server, struct nfs_fh *fhandle,
+			   struct nfs_fsinfo *info, struct nfs4_secinfo_flavors *flavors)
+{
+	struct nfs4_exception exception = { };
+	int err;
+	do {
+		err = _nfs41_proc_secinfo_no_name(server, fhandle, info, flavors);
+		switch (err) {
+		case 0:
+		case -NFS4ERR_WRONGSEC:
+		case -NFS4ERR_NOTSUPP:
+			break;
+		default:
+			err = nfs4_handle_exception(server, err, &exception);
+		}
+	} while (exception.retry);
+	return err;
+}
+
+static int
+nfs41_find_root_sec(struct nfs_server *server, struct nfs_fh *fhandle,
+		    struct nfs_fsinfo *info)
+{
+	int err;
+	struct page *page;
+	rpc_authflavor_t flavor;
+	struct nfs4_secinfo_flavors *flavors;
+
+	page = alloc_page(GFP_KERNEL);
+	if (!page) {
+		err = -ENOMEM;
+		goto out;
+	}
+
+	flavors = page_address(page);
+	err = nfs41_proc_secinfo_no_name(server, fhandle, info, flavors);
+
+	/*
+	 * Fall back on "guess and check" method if
+	 * the server doesn't support SECINFO_NO_NAME
+	 */
+	if (err == -NFS4ERR_WRONGSEC || err == -NFS4ERR_NOTSUPP) {
+		err = nfs4_find_root_sec(server, fhandle, info);
+		goto out_freepage;
+	}
+	if (err)
+		goto out_freepage;
+
+	flavor = nfs_find_best_sec(flavors);
+	if (err == 0)
+		err = nfs4_lookup_root_sec(server, fhandle, info, flavor);
+
+out_freepage:
+	put_page(page);
+	if (err == -EACCES)
+		return -EPERM;
+out:
+	return err;
+}
+static int _nfs41_test_stateid(struct nfs_server *server, struct nfs4_state *state)
+{
+	int status;
+	struct nfs41_test_stateid_args args = {
+		.stateid = &state->stateid,
+	};
+	struct nfs41_test_stateid_res res;
+	struct rpc_message msg = {
+		.rpc_proc = &nfs4_procedures[NFSPROC4_CLNT_TEST_STATEID],
+		.rpc_argp = &args,
+		.rpc_resp = &res,
+	};
+	args.seq_args.sa_session = res.seq_res.sr_session = NULL;
+	status = nfs4_call_sync_sequence(server->client, server, &msg, &args.seq_args, &res.seq_res, 0, 1);
+	return status;
+}
+
+static int nfs41_test_stateid(struct nfs_server *server, struct nfs4_state *state)
+{
+	struct nfs4_exception exception = { };
+	int err;
+	do {
+		err = nfs4_handle_exception(server,
+				_nfs41_test_stateid(server, state),
+				&exception);
+	} while (exception.retry);
+	return err;
+}
+
+static int _nfs4_free_stateid(struct nfs_server *server, struct nfs4_state *state)
+{
+	int status;
+	struct nfs41_free_stateid_args args = {
+		.stateid = &state->stateid,
+	};
+	struct nfs41_free_stateid_res res;
+	struct rpc_message msg = {
+		.rpc_proc = &nfs4_procedures[NFSPROC4_CLNT_FREE_STATEID],
+		.rpc_argp = &args,
+		.rpc_resp = &res,
+	};
+
+	args.seq_args.sa_session = res.seq_res.sr_session = NULL;
+	status = nfs4_call_sync_sequence(server->client, server, &msg, &args.seq_args, &res.seq_res, 0, 1);
+	return status;
+}
+
+static int nfs41_free_stateid(struct nfs_server *server, struct nfs4_state *state)
+{
+	struct nfs4_exception exception = { };
+	int err;
+	do {
+		err = nfs4_handle_exception(server,
+				_nfs4_free_stateid(server, state),
+				&exception);
+	} while (exception.retry);
+	return err;
+}
 #endif /* CONFIG_NFS_V4_1 */
 
 struct nfs4_state_recovery_ops nfs40_reboot_recovery_ops = {
@@ -5937,8 +6194,8 @@ struct nfs4_state_recovery_ops nfs40_nograce_recovery_ops = {
 struct nfs4_state_recovery_ops nfs41_nograce_recovery_ops = {
 	.owner_flag_bit = NFS_OWNER_RECLAIM_NOGRACE,
 	.state_flag_bit	= NFS_STATE_RECLAIM_NOGRACE,
-	.recover_open	= nfs4_open_expired,
-	.recover_lock	= nfs4_lock_expired,
+	.recover_open	= nfs41_open_expired,
+	.recover_lock	= nfs41_lock_expired,
 	.establish_clid = nfs41_init_clientid,
 	.get_clid_cred	= nfs4_get_exchange_id_cred,
 };
@@ -5962,6 +6219,7 @@ static const struct nfs4_minor_version_ops nfs_v4_0_minor_ops = {
 	.minor_version = 0,
 	.call_sync = _nfs4_call_sync,
 	.validate_stateid = nfs4_validate_delegation_stateid,
+	.find_root_sec = nfs4_find_root_sec,
 	.reboot_recovery_ops = &nfs40_reboot_recovery_ops,
 	.nograce_recovery_ops = &nfs40_nograce_recovery_ops,
 	.state_renewal_ops = &nfs40_state_renewal_ops,
@@ -5972,6 +6230,7 @@ static const struct nfs4_minor_version_ops nfs_v4_1_minor_ops = {
 	.minor_version = 1,
 	.call_sync = _nfs4_call_sync_session,
 	.validate_stateid = nfs41_validate_delegation_stateid,
+	.find_root_sec = nfs41_find_root_sec,
 	.reboot_recovery_ops = &nfs41_reboot_recovery_ops,
 	.nograce_recovery_ops = &nfs41_nograce_recovery_ops,
 	.state_renewal_ops = &nfs41_state_renewal_ops,
diff --git a/fs/nfs/nfs4state.c b/fs/nfs/nfs4state.c
index 7acfe8843626..72ab97ef3d61 100644
--- a/fs/nfs/nfs4state.c
+++ b/fs/nfs/nfs4state.c
@@ -1643,7 +1643,14 @@ static void nfs4_state_manager(struct nfs_client *clp)
 				goto out_error;
 			}
 			clear_bit(NFS4CLNT_CHECK_LEASE, &clp->cl_state);
-			set_bit(NFS4CLNT_RECLAIM_REBOOT, &clp->cl_state);
+
+			if (test_and_clear_bit(NFS4CLNT_SERVER_SCOPE_MISMATCH,
+					       &clp->cl_state))
+				nfs4_state_start_reclaim_nograce(clp);
+			else
+				set_bit(NFS4CLNT_RECLAIM_REBOOT,
+					&clp->cl_state);
+
 			pnfs_destroy_all_layouts(clp);
 		}
 
diff --git a/fs/nfs/nfs4xdr.c b/fs/nfs/nfs4xdr.c
index e6e8f3b9a1de..1dce12f41a4f 100644
--- a/fs/nfs/nfs4xdr.c
+++ b/fs/nfs/nfs4xdr.c
@@ -113,7 +113,11 @@ static int nfs4_stat_to_errno(int);
 #define encode_restorefh_maxsz  (op_encode_hdr_maxsz)
 #define decode_restorefh_maxsz  (op_decode_hdr_maxsz)
 #define encode_fsinfo_maxsz	(encode_getattr_maxsz)
-#define decode_fsinfo_maxsz	(op_decode_hdr_maxsz + 15)
+/* The 5 accounts for the PNFS attributes, and assumes that at most three
+ * layout types will be returned.
+ */
+#define decode_fsinfo_maxsz	(op_decode_hdr_maxsz + \
+				 nfs4_fattr_bitmap_maxsz + 4 + 8 + 5)
 #define encode_renew_maxsz	(op_encode_hdr_maxsz + 3)
 #define decode_renew_maxsz	(op_decode_hdr_maxsz)
 #define encode_setclientid_maxsz \
@@ -314,6 +318,17 @@ static int nfs4_stat_to_errno(int);
 				XDR_QUADLEN(NFS4_MAX_SESSIONID_LEN) + 5)
 #define encode_reclaim_complete_maxsz	(op_encode_hdr_maxsz + 4)
 #define decode_reclaim_complete_maxsz	(op_decode_hdr_maxsz + 4)
+#define encode_getdevicelist_maxsz (op_encode_hdr_maxsz + 4 + \
+				encode_verifier_maxsz)
+#define decode_getdevicelist_maxsz (op_decode_hdr_maxsz + \
+				2 /* nfs_cookie4 gdlr_cookie */ + \
+				decode_verifier_maxsz \
+				  /* verifier4 gdlr_verifier */ + \
+				1 /* gdlr_deviceid_list count */ + \
+				XDR_QUADLEN(NFS4_PNFS_GETDEVLIST_MAXNUM * \
+					    NFS4_DEVICEID4_SIZE) \
+				  /* gdlr_deviceid_list */ + \
+				1 /* bool gdlr_eof */)
 #define encode_getdeviceinfo_maxsz (op_encode_hdr_maxsz + 4 + \
 				XDR_QUADLEN(NFS4_DEVICEID4_SIZE))
 #define decode_getdeviceinfo_maxsz (op_decode_hdr_maxsz + \
@@ -343,6 +358,14 @@ static int nfs4_stat_to_errno(int);
 				1 /* FIXME: opaque lrf_body always empty at the moment */)
 #define decode_layoutreturn_maxsz (op_decode_hdr_maxsz + \
 				1 + decode_stateid_maxsz)
+#define encode_secinfo_no_name_maxsz (op_encode_hdr_maxsz + 1)
+#define decode_secinfo_no_name_maxsz decode_secinfo_maxsz
+#define encode_test_stateid_maxsz	(op_encode_hdr_maxsz + 2 + \
+					 XDR_QUADLEN(NFS4_STATEID_SIZE))
+#define decode_test_stateid_maxsz	(op_decode_hdr_maxsz + 2 + 1)
+#define encode_free_stateid_maxsz	(op_encode_hdr_maxsz + 1 + \
+					 XDR_QUADLEN(NFS4_STATEID_SIZE))
+#define decode_free_stateid_maxsz	(op_decode_hdr_maxsz + 1)
 #else /* CONFIG_NFS_V4_1 */
 #define encode_sequence_maxsz	0
 #define decode_sequence_maxsz	0
@@ -740,6 +763,14 @@ static int nfs4_stat_to_errno(int);
 #define NFS4_dec_reclaim_complete_sz	(compound_decode_hdr_maxsz + \
 					 decode_sequence_maxsz + \
 					 decode_reclaim_complete_maxsz)
+#define NFS4_enc_getdevicelist_sz (compound_encode_hdr_maxsz + \
+				encode_sequence_maxsz + \
+				encode_putfh_maxsz + \
+				encode_getdevicelist_maxsz)
+#define NFS4_dec_getdevicelist_sz (compound_decode_hdr_maxsz + \
+				decode_sequence_maxsz + \
+				decode_putfh_maxsz + \
+				decode_getdevicelist_maxsz)
 #define NFS4_enc_getdeviceinfo_sz (compound_encode_hdr_maxsz +    \
 				encode_sequence_maxsz +\
 				encode_getdeviceinfo_maxsz)
@@ -772,6 +803,26 @@ static int nfs4_stat_to_errno(int);
 				decode_sequence_maxsz + \
 				decode_putfh_maxsz + \
 				decode_layoutreturn_maxsz)
+#define NFS4_enc_secinfo_no_name_sz	(compound_encode_hdr_maxsz + \
+					encode_sequence_maxsz + \
+					encode_putrootfh_maxsz +\
+					encode_secinfo_no_name_maxsz)
+#define NFS4_dec_secinfo_no_name_sz	(compound_decode_hdr_maxsz + \
+					decode_sequence_maxsz + \
+					decode_putrootfh_maxsz + \
+					decode_secinfo_no_name_maxsz)
+#define NFS4_enc_test_stateid_sz	(compound_encode_hdr_maxsz + \
+					 encode_sequence_maxsz + \
+					 encode_test_stateid_maxsz)
+#define NFS4_dec_test_stateid_sz	(compound_decode_hdr_maxsz + \
+					 decode_sequence_maxsz + \
+					 decode_test_stateid_maxsz)
+#define NFS4_enc_free_stateid_sz	(compound_encode_hdr_maxsz + \
+					 encode_sequence_maxsz + \
+					 encode_free_stateid_maxsz)
+#define NFS4_dec_free_stateid_sz	(compound_decode_hdr_maxsz + \
+					 decode_sequence_maxsz + \
+					 decode_free_stateid_maxsz)
 
 const u32 nfs41_maxwrite_overhead = ((RPC_MAX_HEADER_WITH_AUTH +
 				      compound_encode_hdr_maxsz +
@@ -1076,6 +1127,35 @@ static void encode_getattr_two(struct xdr_stream *xdr, uint32_t bm0, uint32_t bm
 	hdr->replen += decode_getattr_maxsz;
 }
 
+static void
+encode_getattr_three(struct xdr_stream *xdr,
+		     uint32_t bm0, uint32_t bm1, uint32_t bm2,
+		     struct compound_hdr *hdr)
+{
+	__be32 *p;
+
+	p = reserve_space(xdr, 4);
+	*p = cpu_to_be32(OP_GETATTR);
+	if (bm2) {
+		p = reserve_space(xdr, 16);
+		*p++ = cpu_to_be32(3);
+		*p++ = cpu_to_be32(bm0);
+		*p++ = cpu_to_be32(bm1);
+		*p = cpu_to_be32(bm2);
+	} else if (bm1) {
+		p = reserve_space(xdr, 12);
+		*p++ = cpu_to_be32(2);
+		*p++ = cpu_to_be32(bm0);
+		*p = cpu_to_be32(bm1);
+	} else {
+		p = reserve_space(xdr, 8);
+		*p++ = cpu_to_be32(1);
+		*p = cpu_to_be32(bm0);
+	}
+	hdr->nops++;
+	hdr->replen += decode_getattr_maxsz;
+}
+
 static void encode_getfattr(struct xdr_stream *xdr, const u32* bitmask, struct compound_hdr *hdr)
 {
 	encode_getattr_two(xdr, bitmask[0] & nfs4_fattr_bitmap[0],
@@ -1084,8 +1164,11 @@ static void encode_getfattr(struct xdr_stream *xdr, const u32* bitmask, struct c
 
 static void encode_fsinfo(struct xdr_stream *xdr, const u32* bitmask, struct compound_hdr *hdr)
 {
-	encode_getattr_two(xdr, bitmask[0] & nfs4_fsinfo_bitmap[0],
-			   bitmask[1] & nfs4_fsinfo_bitmap[1], hdr);
+	encode_getattr_three(xdr,
+			     bitmask[0] & nfs4_fsinfo_bitmap[0],
+			     bitmask[1] & nfs4_fsinfo_bitmap[1],
+			     bitmask[2] & nfs4_fsinfo_bitmap[2],
+			     hdr);
 }
 
 static void encode_fs_locations(struct xdr_stream *xdr, const u32* bitmask, struct compound_hdr *hdr)
@@ -1827,6 +1910,26 @@ static void encode_sequence(struct xdr_stream *xdr,
 
 #ifdef CONFIG_NFS_V4_1
 static void
+encode_getdevicelist(struct xdr_stream *xdr,
+		     const struct nfs4_getdevicelist_args *args,
+		     struct compound_hdr *hdr)
+{
+	__be32 *p;
+	nfs4_verifier dummy = {
+		.data = "dummmmmy",
+	};
+
+	p = reserve_space(xdr, 20);
+	*p++ = cpu_to_be32(OP_GETDEVICELIST);
+	*p++ = cpu_to_be32(args->layoutclass);
+	*p++ = cpu_to_be32(NFS4_PNFS_GETDEVLIST_MAXNUM);
+	xdr_encode_hyper(p, 0ULL);                          /* cookie */
+	encode_nfs4_verifier(xdr, &dummy);
+	hdr->nops++;
+	hdr->replen += decode_getdevicelist_maxsz;
+}
+
+static void
 encode_getdeviceinfo(struct xdr_stream *xdr,
 		     const struct nfs4_getdeviceinfo_args *args,
 		     struct compound_hdr *hdr)
@@ -1888,7 +1991,7 @@ encode_layoutcommit(struct xdr_stream *xdr,
 	*p++ = cpu_to_be32(OP_LAYOUTCOMMIT);
 	/* Only whole file layouts */
 	p = xdr_encode_hyper(p, 0); /* offset */
-	p = xdr_encode_hyper(p, NFS4_MAX_UINT64); /* length */
+	p = xdr_encode_hyper(p, args->lastbytewritten + 1);	/* length */
 	*p++ = cpu_to_be32(0); /* reclaim */
 	p = xdr_encode_opaque_fixed(p, args->stateid.data, NFS4_STATEID_SIZE);
 	*p++ = cpu_to_be32(1); /* newoffset = TRUE */
@@ -1938,6 +2041,46 @@ encode_layoutreturn(struct xdr_stream *xdr,
 	hdr->nops++;
 	hdr->replen += decode_layoutreturn_maxsz;
 }
+
+static int
+encode_secinfo_no_name(struct xdr_stream *xdr,
+		       const struct nfs41_secinfo_no_name_args *args,
+		       struct compound_hdr *hdr)
+{
+	__be32 *p;
+	p = reserve_space(xdr, 8);
+	*p++ = cpu_to_be32(OP_SECINFO_NO_NAME);
+	*p++ = cpu_to_be32(args->style);
+	hdr->nops++;
+	hdr->replen += decode_secinfo_no_name_maxsz;
+	return 0;
+}
+
+static void encode_test_stateid(struct xdr_stream *xdr,
+				struct nfs41_test_stateid_args *args,
+				struct compound_hdr *hdr)
+{
+	__be32 *p;
+
+	p = reserve_space(xdr, 8 + NFS4_STATEID_SIZE);
+	*p++ = cpu_to_be32(OP_TEST_STATEID);
+	*p++ = cpu_to_be32(1);
+	xdr_encode_opaque_fixed(p, args->stateid->data, NFS4_STATEID_SIZE);
+	hdr->nops++;
+	hdr->replen += decode_test_stateid_maxsz;
+}
+
+static void encode_free_stateid(struct xdr_stream *xdr,
+				struct nfs41_free_stateid_args *args,
+				struct compound_hdr *hdr)
+{
+	__be32 *p;
+	p = reserve_space(xdr, 4 + NFS4_STATEID_SIZE);
+	*p++ = cpu_to_be32(OP_FREE_STATEID);
+	xdr_encode_opaque_fixed(p, args->stateid->data, NFS4_STATEID_SIZE);
+	hdr->nops++;
+	hdr->replen += decode_free_stateid_maxsz;
+}
 #endif /* CONFIG_NFS_V4_1 */
 
 /*
@@ -2536,7 +2679,7 @@ static void nfs4_xdr_enc_setclientid_confirm(struct rpc_rqst *req,
 	struct compound_hdr hdr = {
 		.nops	= 0,
 	};
-	const u32 lease_bitmap[2] = { FATTR4_WORD0_LEASE_TIME, 0 };
+	const u32 lease_bitmap[3] = { FATTR4_WORD0_LEASE_TIME };
 
 	encode_compound_hdr(xdr, req, &hdr);
 	encode_setclientid_confirm(xdr, arg, &hdr);
@@ -2680,7 +2823,7 @@ static void nfs4_xdr_enc_get_lease_time(struct rpc_rqst *req,
 	struct compound_hdr hdr = {
 		.minorversion = nfs4_xdr_minorversion(&args->la_seq_args),
 	};
-	const u32 lease_bitmap[2] = { FATTR4_WORD0_LEASE_TIME, 0 };
+	const u32 lease_bitmap[3] = { FATTR4_WORD0_LEASE_TIME };
 
 	encode_compound_hdr(xdr, req, &hdr);
 	encode_sequence(xdr, &args->la_seq_args, &hdr);
@@ -2707,6 +2850,24 @@ static void nfs4_xdr_enc_reclaim_complete(struct rpc_rqst *req,
 }
 
 /*
+ * Encode GETDEVICELIST request
+ */
+static void nfs4_xdr_enc_getdevicelist(struct rpc_rqst *req,
+				       struct xdr_stream *xdr,
+				       struct nfs4_getdevicelist_args *args)
+{
+	struct compound_hdr hdr = {
+		.minorversion = nfs4_xdr_minorversion(&args->seq_args),
+	};
+
+	encode_compound_hdr(xdr, req, &hdr);
+	encode_sequence(xdr, &args->seq_args, &hdr);
+	encode_putfh(xdr, args->fh, &hdr);
+	encode_getdevicelist(xdr, args, &hdr);
+	encode_nops(&hdr);
+}
+
+/*
  * Encode GETDEVICEINFO request
  */
 static void nfs4_xdr_enc_getdeviceinfo(struct rpc_rqst *req,
@@ -2790,6 +2951,59 @@ static void nfs4_xdr_enc_layoutreturn(struct rpc_rqst *req,
 	encode_layoutreturn(xdr, args, &hdr);
 	encode_nops(&hdr);
 }
+
+/*
+ * Encode SECINFO_NO_NAME request
+ */
+static int nfs4_xdr_enc_secinfo_no_name(struct rpc_rqst *req,
+					struct xdr_stream *xdr,
+					struct nfs41_secinfo_no_name_args *args)
+{
+	struct compound_hdr hdr = {
+		.minorversion = nfs4_xdr_minorversion(&args->seq_args),
+	};
+
+	encode_compound_hdr(xdr, req, &hdr);
+	encode_sequence(xdr, &args->seq_args, &hdr);
+	encode_putrootfh(xdr, &hdr);
+	encode_secinfo_no_name(xdr, args, &hdr);
+	encode_nops(&hdr);
+	return 0;
+}
+
+/*
+ *  Encode TEST_STATEID request
+ */
+static void nfs4_xdr_enc_test_stateid(struct rpc_rqst *req,
+				      struct xdr_stream *xdr,
+				      struct nfs41_test_stateid_args *args)
+{
+	struct compound_hdr hdr = {
+		.minorversion = nfs4_xdr_minorversion(&args->seq_args),
+	};
+
+	encode_compound_hdr(xdr, req, &hdr);
+	encode_sequence(xdr, &args->seq_args, &hdr);
+	encode_test_stateid(xdr, args, &hdr);
+	encode_nops(&hdr);
+}
+
+/*
+ *  Encode FREE_STATEID request
+ */
+static void nfs4_xdr_enc_free_stateid(struct rpc_rqst *req,
+				     struct xdr_stream *xdr,
+				     struct nfs41_free_stateid_args *args)
+{
+	struct compound_hdr hdr = {
+		.minorversion = nfs4_xdr_minorversion(&args->seq_args),
+	};
+
+	encode_compound_hdr(xdr, req, &hdr);
+	encode_sequence(xdr, &args->seq_args, &hdr);
+	encode_free_stateid(xdr, args, &hdr);
+	encode_nops(&hdr);
+}
 #endif /* CONFIG_NFS_V4_1 */
 
 static void print_overflow_msg(const char *func, const struct xdr_stream *xdr)
@@ -2890,14 +3104,17 @@ static int decode_attr_bitmap(struct xdr_stream *xdr, uint32_t *bitmap)
 		goto out_overflow;
 	bmlen = be32_to_cpup(p);
 
-	bitmap[0] = bitmap[1] = 0;
+	bitmap[0] = bitmap[1] = bitmap[2] = 0;
 	p = xdr_inline_decode(xdr, (bmlen << 2));
 	if (unlikely(!p))
 		goto out_overflow;
 	if (bmlen > 0) {
 		bitmap[0] = be32_to_cpup(p++);
-		if (bmlen > 1)
-			bitmap[1] = be32_to_cpup(p);
+		if (bmlen > 1) {
+			bitmap[1] = be32_to_cpup(p++);
+			if (bmlen > 2)
+				bitmap[2] = be32_to_cpup(p);
+		}
 	}
 	return 0;
 out_overflow:
@@ -2929,8 +3146,9 @@ static int decode_attr_supported(struct xdr_stream *xdr, uint32_t *bitmap, uint3
 			return ret;
 		bitmap[0] &= ~FATTR4_WORD0_SUPPORTED_ATTRS;
 	} else
-		bitmask[0] = bitmask[1] = 0;
-	dprintk("%s: bitmask=%08x:%08x\n", __func__, bitmask[0], bitmask[1]);
+		bitmask[0] = bitmask[1] = bitmask[2] = 0;
+	dprintk("%s: bitmask=%08x:%08x:%08x\n", __func__,
+		bitmask[0], bitmask[1], bitmask[2]);
 	return 0;
 }
 
@@ -3984,7 +4202,7 @@ out_overflow:
 static int decode_server_caps(struct xdr_stream *xdr, struct nfs4_server_caps_res *res)
 {
 	__be32 *savep;
-	uint32_t attrlen, bitmap[2] = {0};
+	uint32_t attrlen, bitmap[3] = {0};
 	int status;
 
 	if ((status = decode_op_hdr(xdr, OP_GETATTR)) != 0)
@@ -4010,7 +4228,7 @@ xdr_error:
 static int decode_statfs(struct xdr_stream *xdr, struct nfs_fsstat *fsstat)
 {
 	__be32 *savep;
-	uint32_t attrlen, bitmap[2] = {0};
+	uint32_t attrlen, bitmap[3] = {0};
 	int status;
 
 	if ((status = decode_op_hdr(xdr, OP_GETATTR)) != 0)
@@ -4042,7 +4260,7 @@ xdr_error:
 static int decode_pathconf(struct xdr_stream *xdr, struct nfs_pathconf *pathconf)
 {
 	__be32 *savep;
-	uint32_t attrlen, bitmap[2] = {0};
+	uint32_t attrlen, bitmap[3] = {0};
 	int status;
 
 	if ((status = decode_op_hdr(xdr, OP_GETATTR)) != 0)
@@ -4182,7 +4400,7 @@ static int decode_getfattr_generic(struct xdr_stream *xdr, struct nfs_fattr *fat
 {
 	__be32 *savep;
 	uint32_t attrlen,
-		 bitmap[2] = {0};
+		 bitmap[3] = {0};
 	int status;
 
 	status = decode_op_hdr(xdr, OP_GETATTR);
@@ -4268,10 +4486,32 @@ static int decode_attr_pnfstype(struct xdr_stream *xdr, uint32_t *bitmap,
 	return status;
 }
 
+/*
+ * The prefered block size for layout directed io
+ */
+static int decode_attr_layout_blksize(struct xdr_stream *xdr, uint32_t *bitmap,
+				      uint32_t *res)
+{
+	__be32 *p;
+
+	dprintk("%s: bitmap is %x\n", __func__, bitmap[2]);
+	*res = 0;
+	if (bitmap[2] & FATTR4_WORD2_LAYOUT_BLKSIZE) {
+		p = xdr_inline_decode(xdr, 4);
+		if (unlikely(!p)) {
+			print_overflow_msg(__func__, xdr);
+			return -EIO;
+		}
+		*res = be32_to_cpup(p);
+		bitmap[2] &= ~FATTR4_WORD2_LAYOUT_BLKSIZE;
+	}
+	return 0;
+}
+
 static int decode_fsinfo(struct xdr_stream *xdr, struct nfs_fsinfo *fsinfo)
 {
 	__be32 *savep;
-	uint32_t attrlen, bitmap[2];
+	uint32_t attrlen, bitmap[3];
 	int status;
 
 	if ((status = decode_op_hdr(xdr, OP_GETATTR)) != 0)
@@ -4299,6 +4539,9 @@ static int decode_fsinfo(struct xdr_stream *xdr, struct nfs_fsinfo *fsinfo)
 	status = decode_attr_pnfstype(xdr, bitmap, &fsinfo->layouttype);
 	if (status != 0)
 		goto xdr_error;
+	status = decode_attr_layout_blksize(xdr, bitmap, &fsinfo->blksize);
+	if (status)
+		goto xdr_error;
 
 	status = verify_attr_len(xdr, savep, attrlen);
 xdr_error:
@@ -4718,7 +4961,7 @@ static int decode_getacl(struct xdr_stream *xdr, struct rpc_rqst *req,
 {
 	__be32 *savep;
 	uint32_t attrlen,
-		 bitmap[2] = {0};
+		 bitmap[3] = {0};
 	struct kvec *iov = req->rq_rcv_buf.head;
 	int status;
 
@@ -4977,11 +5220,17 @@ static int decode_exchange_id(struct xdr_stream *xdr,
 	if (unlikely(status))
 		return status;
 
-	/* Throw away server_scope */
+	/* Save server_scope */
 	status = decode_opaque_inline(xdr, &dummy, &dummy_str);
 	if (unlikely(status))
 		return status;
 
+	if (unlikely(dummy > NFS4_OPAQUE_LIMIT))
+		return -EIO;
+
+	memcpy(res->server_scope->server_scope, dummy_str, dummy);
+	res->server_scope->server_scope_sz = dummy;
+
 	/* Throw away Implementation id array */
 	status = decode_opaque_inline(xdr, &dummy, &dummy_str);
 	if (unlikely(status))
@@ -5141,6 +5390,53 @@ out_overflow:
 }
 
 #if defined(CONFIG_NFS_V4_1)
+/*
+ * TODO: Need to handle case when EOF != true;
+ */
+static int decode_getdevicelist(struct xdr_stream *xdr,
+				struct pnfs_devicelist *res)
+{
+	__be32 *p;
+	int status, i;
+	struct nfs_writeverf verftemp;
+
+	status = decode_op_hdr(xdr, OP_GETDEVICELIST);
+	if (status)
+		return status;
+
+	p = xdr_inline_decode(xdr, 8 + 8 + 4);
+	if (unlikely(!p))
+		goto out_overflow;
+
+	/* TODO: Skip cookie for now */
+	p += 2;
+
+	/* Read verifier */
+	p = xdr_decode_opaque_fixed(p, verftemp.verifier, 8);
+
+	res->num_devs = be32_to_cpup(p);
+
+	dprintk("%s: num_dev %d\n", __func__, res->num_devs);
+
+	if (res->num_devs > NFS4_PNFS_GETDEVLIST_MAXNUM) {
+		printk(KERN_ERR "%s too many result dev_num %u\n",
+				__func__, res->num_devs);
+		return -EIO;
+	}
+
+	p = xdr_inline_decode(xdr,
+			      res->num_devs * NFS4_DEVICEID4_SIZE + 4);
+	if (unlikely(!p))
+		goto out_overflow;
+	for (i = 0; i < res->num_devs; i++)
+		p = xdr_decode_opaque_fixed(p, res->dev_id[i].data,
+					    NFS4_DEVICEID4_SIZE);
+	res->eof = be32_to_cpup(p);
+	return 0;
+out_overflow:
+	print_overflow_msg(__func__, xdr);
+	return -EIO;
+}
 
 static int decode_getdeviceinfo(struct xdr_stream *xdr,
 				struct pnfs_device *pdev)
@@ -5303,6 +5599,7 @@ static int decode_layoutcommit(struct xdr_stream *xdr,
 	int status;
 
 	status = decode_op_hdr(xdr, OP_LAYOUTCOMMIT);
+	res->status = status;
 	if (status)
 		return status;
 
@@ -5322,6 +5619,55 @@ out_overflow:
 	print_overflow_msg(__func__, xdr);
 	return -EIO;
 }
+
+static int decode_test_stateid(struct xdr_stream *xdr,
+			       struct nfs41_test_stateid_res *res)
+{
+	__be32 *p;
+	int status;
+	int num_res;
+
+	status = decode_op_hdr(xdr, OP_TEST_STATEID);
+	if (status)
+		return status;
+
+	p = xdr_inline_decode(xdr, 4);
+	if (unlikely(!p))
+		goto out_overflow;
+	num_res = be32_to_cpup(p++);
+	if (num_res != 1)
+		goto out;
+
+	p = xdr_inline_decode(xdr, 4);
+	if (unlikely(!p))
+		goto out_overflow;
+	res->status = be32_to_cpup(p++);
+	return res->status;
+out_overflow:
+	print_overflow_msg(__func__, xdr);
+out:
+	return -EIO;
+}
+
+static int decode_free_stateid(struct xdr_stream *xdr,
+			       struct nfs41_free_stateid_res *res)
+{
+	__be32 *p;
+	int status;
+
+	status = decode_op_hdr(xdr, OP_FREE_STATEID);
+	if (status)
+		return status;
+
+	p = xdr_inline_decode(xdr, 4);
+	if (unlikely(!p))
+		goto out_overflow;
+	res->status = be32_to_cpup(p++);
+	return res->status;
+out_overflow:
+	print_overflow_msg(__func__, xdr);
+	return -EIO;
+}
 #endif /* CONFIG_NFS_V4_1 */
 
 /*
@@ -6366,6 +6712,32 @@ static int nfs4_xdr_dec_reclaim_complete(struct rpc_rqst *rqstp,
 }
 
 /*
+ * Decode GETDEVICELIST response
+ */
+static int nfs4_xdr_dec_getdevicelist(struct rpc_rqst *rqstp,
+				      struct xdr_stream *xdr,
+				      struct nfs4_getdevicelist_res *res)
+{
+	struct compound_hdr hdr;
+	int status;
+
+	dprintk("encoding getdevicelist!\n");
+
+	status = decode_compound_hdr(xdr, &hdr);
+	if (status != 0)
+		goto out;
+	status = decode_sequence(xdr, &res->seq_res, rqstp);
+	if (status != 0)
+		goto out;
+	status = decode_putfh(xdr);
+	if (status != 0)
+		goto out;
+	status = decode_getdevicelist(xdr, res->devlist);
+out:
+	return status;
+}
+
+/*
  * Decode GETDEVINFO response
  */
 static int nfs4_xdr_dec_getdeviceinfo(struct rpc_rqst *rqstp,
@@ -6461,6 +6833,72 @@ static int nfs4_xdr_dec_layoutcommit(struct rpc_rqst *rqstp,
 out:
 	return status;
 }
+
+/*
+ * Decode SECINFO_NO_NAME response
+ */
+static int nfs4_xdr_dec_secinfo_no_name(struct rpc_rqst *rqstp,
+					struct xdr_stream *xdr,
+					struct nfs4_secinfo_res *res)
+{
+	struct compound_hdr hdr;
+	int status;
+
+	status = decode_compound_hdr(xdr, &hdr);
+	if (status)
+		goto out;
+	status = decode_sequence(xdr, &res->seq_res, rqstp);
+	if (status)
+		goto out;
+	status = decode_putrootfh(xdr);
+	if (status)
+		goto out;
+	status = decode_secinfo(xdr, res);
+out:
+	return status;
+}
+
+/*
+ * Decode TEST_STATEID response
+ */
+static int nfs4_xdr_dec_test_stateid(struct rpc_rqst *rqstp,
+				     struct xdr_stream *xdr,
+				     struct nfs41_test_stateid_res *res)
+{
+	struct compound_hdr hdr;
+	int status;
+
+	status = decode_compound_hdr(xdr, &hdr);
+	if (status)
+		goto out;
+	status = decode_sequence(xdr, &res->seq_res, rqstp);
+	if (status)
+		goto out;
+	status = decode_test_stateid(xdr, res);
+out:
+	return status;
+}
+
+/*
+ * Decode FREE_STATEID response
+ */
+static int nfs4_xdr_dec_free_stateid(struct rpc_rqst *rqstp,
+				     struct xdr_stream *xdr,
+				     struct nfs41_free_stateid_res *res)
+{
+	struct compound_hdr hdr;
+	int status;
+
+	status = decode_compound_hdr(xdr, &hdr);
+	if (status)
+		goto out;
+	status = decode_sequence(xdr, &res->seq_res, rqstp);
+	if (status)
+		goto out;
+	status = decode_free_stateid(xdr, res);
+out:
+	return status;
+}
 #endif /* CONFIG_NFS_V4_1 */
 
 /**
@@ -6480,7 +6918,7 @@ out:
 int nfs4_decode_dirent(struct xdr_stream *xdr, struct nfs_entry *entry,
 		       int plus)
 {
-	uint32_t bitmap[2] = {0};
+	uint32_t bitmap[3] = {0};
 	uint32_t len;
 	__be32 *p = xdr_inline_decode(xdr, 4);
 	if (unlikely(!p))
@@ -6663,6 +7101,10 @@ struct rpc_procinfo	nfs4_procedures[] = {
 	PROC(LAYOUTGET,		enc_layoutget,		dec_layoutget),
 	PROC(LAYOUTCOMMIT,	enc_layoutcommit,	dec_layoutcommit),
 	PROC(LAYOUTRETURN,	enc_layoutreturn,	dec_layoutreturn),
+	PROC(SECINFO_NO_NAME,	enc_secinfo_no_name,	dec_secinfo_no_name),
+	PROC(TEST_STATEID,	enc_test_stateid,	dec_test_stateid),
+	PROC(FREE_STATEID,	enc_free_stateid,	dec_free_stateid),
+	PROC(GETDEVICELIST,	enc_getdevicelist,	dec_getdevicelist),
 #endif /* CONFIG_NFS_V4_1 */
 };
 
diff --git a/fs/nfs/objlayout/objio_osd.c b/fs/nfs/objlayout/objio_osd.c
index 8ff2ea3f10ef..d0cda12fddc3 100644
--- a/fs/nfs/objlayout/objio_osd.c
+++ b/fs/nfs/objlayout/objio_osd.c
@@ -479,7 +479,6 @@ static int _io_check(struct objio_state *ios, bool is_write)
 	for (i = 0; i <  ios->numdevs; i++) {
 		struct osd_sense_info osi;
 		struct osd_request *or = ios->per_dev[i].or;
-		unsigned dev;
 		int ret;
 
 		if (!or)
@@ -500,9 +499,8 @@ static int _io_check(struct objio_state *ios, bool is_write)
 
 			continue; /* we recovered */
 		}
-		dev = ios->per_dev[i].dev;
-		objlayout_io_set_result(&ios->ol_state, dev,
-					&ios->layout->comps[dev].oc_object_id,
+		objlayout_io_set_result(&ios->ol_state, i,
+					&ios->layout->comps[i].oc_object_id,
 					osd_pri_2_pnfs_err(osi.osd_err_pri),
 					ios->per_dev[i].offset,
 					ios->per_dev[i].length,
@@ -589,22 +587,19 @@ static void _calc_stripe_info(struct objio_state *ios, u64 file_offset,
 }
 
 static int _add_stripe_unit(struct objio_state *ios,  unsigned *cur_pg,
-		unsigned pgbase, struct _objio_per_comp *per_dev, int cur_len,
+		unsigned pgbase, struct _objio_per_comp *per_dev, int len,
 		gfp_t gfp_flags)
 {
 	unsigned pg = *cur_pg;
+	int cur_len = len;
 	struct request_queue *q =
 			osd_request_queue(_io_od(ios, per_dev->dev));
 
-	per_dev->length += cur_len;
-
 	if (per_dev->bio == NULL) {
-		unsigned stripes = ios->layout->num_comps /
-						     ios->layout->mirrors_p1;
-		unsigned pages_in_stripe = stripes *
+		unsigned pages_in_stripe = ios->layout->group_width *
 				      (ios->layout->stripe_unit / PAGE_SIZE);
 		unsigned bio_size = (ios->ol_state.nr_pages + pages_in_stripe) /
-				    stripes;
+				    ios->layout->group_width;
 
 		if (BIO_MAX_PAGES_KMALLOC < bio_size)
 			bio_size = BIO_MAX_PAGES_KMALLOC;
@@ -632,6 +627,7 @@ static int _add_stripe_unit(struct objio_state *ios,  unsigned *cur_pg,
 	}
 	BUG_ON(cur_len);
 
+	per_dev->length += len;
 	*cur_pg = pg;
 	return 0;
 }
@@ -650,7 +646,7 @@ static int _prepare_one_group(struct objio_state *ios, u64 length,
 	int ret = 0;
 
 	while (length) {
-		struct _objio_per_comp *per_dev = &ios->per_dev[dev];
+		struct _objio_per_comp *per_dev = &ios->per_dev[dev - first_dev];
 		unsigned cur_len, page_off = 0;
 
 		if (!per_dev->length) {
@@ -670,8 +666,8 @@ static int _prepare_one_group(struct objio_state *ios, u64 length,
 				cur_len = stripe_unit;
 			}
 
-			if (max_comp < dev)
-				max_comp = dev;
+			if (max_comp < dev - first_dev)
+				max_comp = dev - first_dev;
 		} else {
 			cur_len = stripe_unit;
 		}
@@ -806,7 +802,7 @@ static int _read_mirrors(struct objio_state *ios, unsigned cur_comp)
 	struct _objio_per_comp *per_dev = &ios->per_dev[cur_comp];
 	unsigned dev = per_dev->dev;
 	struct pnfs_osd_object_cred *cred =
-			&ios->layout->comps[dev];
+			&ios->layout->comps[cur_comp];
 	struct osd_obj_id obj = {
 		.partition = cred->oc_object_id.oid_partition_id,
 		.id = cred->oc_object_id.oid_object_id,
@@ -904,7 +900,7 @@ static int _write_mirrors(struct objio_state *ios, unsigned cur_comp)
 	for (; cur_comp < last_comp; ++cur_comp, ++dev) {
 		struct osd_request *or = NULL;
 		struct pnfs_osd_object_cred *cred =
-					&ios->layout->comps[dev];
+					&ios->layout->comps[cur_comp];
 		struct osd_obj_id obj = {
 			.partition = cred->oc_object_id.oid_partition_id,
 			.id = cred->oc_object_id.oid_object_id,
@@ -1000,13 +996,22 @@ static bool objio_pg_test(struct nfs_pageio_descriptor *pgio,
 	if (!pnfs_generic_pg_test(pgio, prev, req))
 		return false;
 
-	if (pgio->pg_lseg == NULL)
-		return true;
-
 	return pgio->pg_count + req->wb_bytes <=
 			OBJIO_LSEG(pgio->pg_lseg)->max_io_size;
 }
 
+static const struct nfs_pageio_ops objio_pg_read_ops = {
+	.pg_init = pnfs_generic_pg_init_read,
+	.pg_test = objio_pg_test,
+	.pg_doio = pnfs_generic_pg_readpages,
+};
+
+static const struct nfs_pageio_ops objio_pg_write_ops = {
+	.pg_init = pnfs_generic_pg_init_write,
+	.pg_test = objio_pg_test,
+	.pg_doio = pnfs_generic_pg_writepages,
+};
+
 static struct pnfs_layoutdriver_type objlayout_type = {
 	.id = LAYOUT_OSD2_OBJECTS,
 	.name = "LAYOUT_OSD2_OBJECTS",
@@ -1020,7 +1025,8 @@ static struct pnfs_layoutdriver_type objlayout_type = {
 
 	.read_pagelist           = objlayout_read_pagelist,
 	.write_pagelist          = objlayout_write_pagelist,
-	.pg_test                 = objio_pg_test,
+	.pg_read_ops             = &objio_pg_read_ops,
+	.pg_write_ops            = &objio_pg_write_ops,
 
 	.free_deviceid_node	 = objio_free_deviceid_node,
 
@@ -1055,5 +1061,7 @@ objlayout_exit(void)
 	       __func__);
 }
 
+MODULE_ALIAS("nfs-layouttype4-2");
+
 module_init(objlayout_init);
 module_exit(objlayout_exit);
diff --git a/fs/nfs/objlayout/pnfs_osd_xdr_cli.c b/fs/nfs/objlayout/pnfs_osd_xdr_cli.c
index 16fc758e9123..b3918f7ac34d 100644
--- a/fs/nfs/objlayout/pnfs_osd_xdr_cli.c
+++ b/fs/nfs/objlayout/pnfs_osd_xdr_cli.c
@@ -170,6 +170,9 @@ int pnfs_osd_xdr_decode_layout_map(struct pnfs_osd_layout *layout,
 	p = _osd_xdr_decode_data_map(p, &layout->olo_map);
 	layout->olo_comps_index = be32_to_cpup(p++);
 	layout->olo_num_comps = be32_to_cpup(p++);
+	dprintk("%s: olo_comps_index=%d olo_num_comps=%d\n", __func__,
+		layout->olo_comps_index, layout->olo_num_comps);
+
 	iter->total_comps = layout->olo_num_comps;
 	return 0;
 }
diff --git a/fs/nfs/pagelist.c b/fs/nfs/pagelist.c
index 18449f43c568..b60970cc7f1f 100644
--- a/fs/nfs/pagelist.c
+++ b/fs/nfs/pagelist.c
@@ -230,7 +230,7 @@ EXPORT_SYMBOL_GPL(nfs_generic_pg_test);
  */
 void nfs_pageio_init(struct nfs_pageio_descriptor *desc,
 		     struct inode *inode,
-		     int (*doio)(struct nfs_pageio_descriptor *),
+		     const struct nfs_pageio_ops *pg_ops,
 		     size_t bsize,
 		     int io_flags)
 {
@@ -240,13 +240,12 @@ void nfs_pageio_init(struct nfs_pageio_descriptor *desc,
 	desc->pg_bsize = bsize;
 	desc->pg_base = 0;
 	desc->pg_moreio = 0;
+	desc->pg_recoalesce = 0;
 	desc->pg_inode = inode;
-	desc->pg_doio = doio;
+	desc->pg_ops = pg_ops;
 	desc->pg_ioflags = io_flags;
 	desc->pg_error = 0;
 	desc->pg_lseg = NULL;
-	desc->pg_test = nfs_generic_pg_test;
-	pnfs_pageio_init(desc, inode);
 }
 
 /**
@@ -276,7 +275,7 @@ static bool nfs_can_coalesce_requests(struct nfs_page *prev,
 		return false;
 	if (prev->wb_pgbase + prev->wb_bytes != PAGE_CACHE_SIZE)
 		return false;
-	return pgio->pg_test(pgio, prev, req);
+	return pgio->pg_ops->pg_test(pgio, prev, req);
 }
 
 /**
@@ -297,6 +296,8 @@ static int nfs_pageio_do_add_request(struct nfs_pageio_descriptor *desc,
 		if (!nfs_can_coalesce_requests(prev, req, desc))
 			return 0;
 	} else {
+		if (desc->pg_ops->pg_init)
+			desc->pg_ops->pg_init(desc, req);
 		desc->pg_base = req->wb_pgbase;
 	}
 	nfs_list_remove_request(req);
@@ -311,7 +312,7 @@ static int nfs_pageio_do_add_request(struct nfs_pageio_descriptor *desc,
 static void nfs_pageio_doio(struct nfs_pageio_descriptor *desc)
 {
 	if (!list_empty(&desc->pg_list)) {
-		int error = desc->pg_doio(desc);
+		int error = desc->pg_ops->pg_doio(desc);
 		if (error < 0)
 			desc->pg_error = error;
 		else
@@ -331,7 +332,7 @@ static void nfs_pageio_doio(struct nfs_pageio_descriptor *desc)
  * Returns true if the request 'req' was successfully coalesced into the
  * existing list of pages 'desc'.
  */
-int nfs_pageio_add_request(struct nfs_pageio_descriptor *desc,
+static int __nfs_pageio_add_request(struct nfs_pageio_descriptor *desc,
 			   struct nfs_page *req)
 {
 	while (!nfs_pageio_do_add_request(desc, req)) {
@@ -340,17 +341,67 @@ int nfs_pageio_add_request(struct nfs_pageio_descriptor *desc,
 		if (desc->pg_error < 0)
 			return 0;
 		desc->pg_moreio = 0;
+		if (desc->pg_recoalesce)
+			return 0;
 	}
 	return 1;
 }
 
+static int nfs_do_recoalesce(struct nfs_pageio_descriptor *desc)
+{
+	LIST_HEAD(head);
+
+	do {
+		list_splice_init(&desc->pg_list, &head);
+		desc->pg_bytes_written -= desc->pg_count;
+		desc->pg_count = 0;
+		desc->pg_base = 0;
+		desc->pg_recoalesce = 0;
+
+		while (!list_empty(&head)) {
+			struct nfs_page *req;
+
+			req = list_first_entry(&head, struct nfs_page, wb_list);
+			nfs_list_remove_request(req);
+			if (__nfs_pageio_add_request(desc, req))
+				continue;
+			if (desc->pg_error < 0)
+				return 0;
+			break;
+		}
+	} while (desc->pg_recoalesce);
+	return 1;
+}
+
+int nfs_pageio_add_request(struct nfs_pageio_descriptor *desc,
+		struct nfs_page *req)
+{
+	int ret;
+
+	do {
+		ret = __nfs_pageio_add_request(desc, req);
+		if (ret)
+			break;
+		if (desc->pg_error < 0)
+			break;
+		ret = nfs_do_recoalesce(desc);
+	} while (ret);
+	return ret;
+}
+
 /**
  * nfs_pageio_complete - Complete I/O on an nfs_pageio_descriptor
  * @desc: pointer to io descriptor
  */
 void nfs_pageio_complete(struct nfs_pageio_descriptor *desc)
 {
-	nfs_pageio_doio(desc);
+	for (;;) {
+		nfs_pageio_doio(desc);
+		if (!desc->pg_recoalesce)
+			break;
+		if (!nfs_do_recoalesce(desc))
+			break;
+	}
 }
 
 /**
@@ -369,7 +420,7 @@ void nfs_pageio_cond_complete(struct nfs_pageio_descriptor *desc, pgoff_t index)
 	if (!list_empty(&desc->pg_list)) {
 		struct nfs_page *prev = nfs_list_entry(desc->pg_list.prev);
 		if (index != prev->wb_index + 1)
-			nfs_pageio_doio(desc);
+			nfs_pageio_complete(desc);
 	}
 }
 
diff --git a/fs/nfs/pnfs.c b/fs/nfs/pnfs.c
index 29c0ca7fc347..e550e8836c37 100644
--- a/fs/nfs/pnfs.c
+++ b/fs/nfs/pnfs.c
@@ -28,6 +28,7 @@
  */
 
 #include <linux/nfs_fs.h>
+#include <linux/nfs_page.h>
 #include "internal.h"
 #include "pnfs.h"
 #include "iostat.h"
@@ -75,8 +76,11 @@ find_pnfs_driver(u32 id)
 void
 unset_pnfs_layoutdriver(struct nfs_server *nfss)
 {
-	if (nfss->pnfs_curr_ld)
+	if (nfss->pnfs_curr_ld) {
+		if (nfss->pnfs_curr_ld->clear_layoutdriver)
+			nfss->pnfs_curr_ld->clear_layoutdriver(nfss);
 		module_put(nfss->pnfs_curr_ld->owner);
+	}
 	nfss->pnfs_curr_ld = NULL;
 }
 
@@ -87,7 +91,8 @@ unset_pnfs_layoutdriver(struct nfs_server *nfss)
  * @id layout type. Zero (illegal layout type) indicates pNFS not in use.
  */
 void
-set_pnfs_layoutdriver(struct nfs_server *server, u32 id)
+set_pnfs_layoutdriver(struct nfs_server *server, const struct nfs_fh *mntfh,
+		      u32 id)
 {
 	struct pnfs_layoutdriver_type *ld_type = NULL;
 
@@ -114,6 +119,13 @@ set_pnfs_layoutdriver(struct nfs_server *server, u32 id)
 		goto out_no_driver;
 	}
 	server->pnfs_curr_ld = ld_type;
+	if (ld_type->set_layoutdriver
+	    && ld_type->set_layoutdriver(server, mntfh)) {
+		printk(KERN_ERR "%s: Error initializing pNFS layout driver %u.\n",
+				__func__, id);
+		module_put(ld_type->owner);
+		goto out_no_driver;
+	}
 
 	dprintk("%s: pNFS module for %u set\n", __func__, id);
 	return;
@@ -189,6 +201,7 @@ static void
 pnfs_free_layout_hdr(struct pnfs_layout_hdr *lo)
 {
 	struct pnfs_layoutdriver_type *ld = NFS_SERVER(lo->plh_inode)->pnfs_curr_ld;
+	put_rpccred(lo->plh_lc_cred);
 	return ld->alloc_layout_hdr ? ld->free_layout_hdr(lo) : kfree(lo);
 }
 
@@ -223,6 +236,7 @@ static void
 init_lseg(struct pnfs_layout_hdr *lo, struct pnfs_layout_segment *lseg)
 {
 	INIT_LIST_HEAD(&lseg->pls_list);
+	INIT_LIST_HEAD(&lseg->pls_lc_list);
 	atomic_set(&lseg->pls_refcount, 1);
 	smp_mb();
 	set_bit(NFS_LSEG_VALID, &lseg->pls_flags);
@@ -448,11 +462,20 @@ pnfs_destroy_layout(struct nfs_inode *nfsi)
 void
 pnfs_destroy_all_layouts(struct nfs_client *clp)
 {
+	struct nfs_server *server;
 	struct pnfs_layout_hdr *lo;
 	LIST_HEAD(tmp_list);
 
+	nfs4_deviceid_mark_client_invalid(clp);
+	nfs4_deviceid_purge_client(clp);
+
 	spin_lock(&clp->cl_lock);
-	list_splice_init(&clp->cl_layouts, &tmp_list);
+	rcu_read_lock();
+	list_for_each_entry_rcu(server, &clp->cl_superblocks, client_link) {
+		if (!list_empty(&server->layouts))
+			list_splice_init(&server->layouts, &tmp_list);
+	}
+	rcu_read_unlock();
 	spin_unlock(&clp->cl_lock);
 
 	while (!list_empty(&tmp_list)) {
@@ -661,6 +684,7 @@ _pnfs_return_layout(struct inode *ino)
 	lrp->args.stateid = stateid;
 	lrp->args.layout_type = NFS_SERVER(ino)->pnfs_curr_ld->id;
 	lrp->args.inode = ino;
+	lrp->args.layout = lo;
 	lrp->clp = NFS_SERVER(ino)->nfs_client;
 
 	status = nfs4_proc_layoutreturn(lrp);
@@ -805,7 +829,9 @@ out:
 }
 
 static struct pnfs_layout_hdr *
-alloc_init_layout_hdr(struct inode *ino, gfp_t gfp_flags)
+alloc_init_layout_hdr(struct inode *ino,
+		      struct nfs_open_context *ctx,
+		      gfp_t gfp_flags)
 {
 	struct pnfs_layout_hdr *lo;
 
@@ -817,11 +843,14 @@ alloc_init_layout_hdr(struct inode *ino, gfp_t gfp_flags)
 	INIT_LIST_HEAD(&lo->plh_segs);
 	INIT_LIST_HEAD(&lo->plh_bulk_recall);
 	lo->plh_inode = ino;
+	lo->plh_lc_cred = get_rpccred(ctx->state->owner->so_cred);
 	return lo;
 }
 
 static struct pnfs_layout_hdr *
-pnfs_find_alloc_layout(struct inode *ino, gfp_t gfp_flags)
+pnfs_find_alloc_layout(struct inode *ino,
+		       struct nfs_open_context *ctx,
+		       gfp_t gfp_flags)
 {
 	struct nfs_inode *nfsi = NFS_I(ino);
 	struct pnfs_layout_hdr *new = NULL;
@@ -836,7 +865,7 @@ pnfs_find_alloc_layout(struct inode *ino, gfp_t gfp_flags)
 			return nfsi->layout;
 	}
 	spin_unlock(&ino->i_lock);
-	new = alloc_init_layout_hdr(ino, gfp_flags);
+	new = alloc_init_layout_hdr(ino, ctx, gfp_flags);
 	spin_lock(&ino->i_lock);
 
 	if (likely(nfsi->layout == NULL))	/* Won the race? */
@@ -920,7 +949,8 @@ pnfs_update_layout(struct inode *ino,
 	};
 	unsigned pg_offset;
 	struct nfs_inode *nfsi = NFS_I(ino);
-	struct nfs_client *clp = NFS_SERVER(ino)->nfs_client;
+	struct nfs_server *server = NFS_SERVER(ino);
+	struct nfs_client *clp = server->nfs_client;
 	struct pnfs_layout_hdr *lo;
 	struct pnfs_layout_segment *lseg = NULL;
 	bool first = false;
@@ -928,7 +958,7 @@ pnfs_update_layout(struct inode *ino,
 	if (!pnfs_enabled_sb(NFS_SERVER(ino)))
 		return NULL;
 	spin_lock(&ino->i_lock);
-	lo = pnfs_find_alloc_layout(ino, gfp_flags);
+	lo = pnfs_find_alloc_layout(ino, ctx, gfp_flags);
 	if (lo == NULL) {
 		dprintk("%s ERROR: can't get pnfs_layout_hdr\n", __func__);
 		goto out_unlock;
@@ -964,7 +994,7 @@ pnfs_update_layout(struct inode *ino,
 		 */
 		spin_lock(&clp->cl_lock);
 		BUG_ON(!list_empty(&lo->plh_layouts));
-		list_add_tail(&lo->plh_layouts, &clp->cl_layouts);
+		list_add_tail(&lo->plh_layouts, &server->layouts);
 		spin_unlock(&clp->cl_lock);
 	}
 
@@ -973,7 +1003,8 @@ pnfs_update_layout(struct inode *ino,
 		arg.offset -= pg_offset;
 		arg.length += pg_offset;
 	}
-	arg.length = PAGE_CACHE_ALIGN(arg.length);
+	if (arg.length != NFS4_MAX_UINT64)
+		arg.length = PAGE_CACHE_ALIGN(arg.length);
 
 	lseg = send_layoutget(lo, ctx, &arg, gfp_flags);
 	if (!lseg && first) {
@@ -991,6 +1022,7 @@ out_unlock:
 	spin_unlock(&ino->i_lock);
 	goto out;
 }
+EXPORT_SYMBOL_GPL(pnfs_update_layout);
 
 int
 pnfs_layout_process(struct nfs4_layoutget *lgp)
@@ -1048,35 +1080,71 @@ out_forget_reply:
 	goto out;
 }
 
+void
+pnfs_generic_pg_init_read(struct nfs_pageio_descriptor *pgio, struct nfs_page *req)
+{
+	BUG_ON(pgio->pg_lseg != NULL);
+
+	pgio->pg_lseg = pnfs_update_layout(pgio->pg_inode,
+					   req->wb_context,
+					   req_offset(req),
+					   req->wb_bytes,
+					   IOMODE_READ,
+					   GFP_KERNEL);
+	/* If no lseg, fall back to read through mds */
+	if (pgio->pg_lseg == NULL)
+		nfs_pageio_reset_read_mds(pgio);
+
+}
+EXPORT_SYMBOL_GPL(pnfs_generic_pg_init_read);
+
+void
+pnfs_generic_pg_init_write(struct nfs_pageio_descriptor *pgio, struct nfs_page *req)
+{
+	BUG_ON(pgio->pg_lseg != NULL);
+
+	pgio->pg_lseg = pnfs_update_layout(pgio->pg_inode,
+					   req->wb_context,
+					   req_offset(req),
+					   req->wb_bytes,
+					   IOMODE_RW,
+					   GFP_NOFS);
+	/* If no lseg, fall back to write through mds */
+	if (pgio->pg_lseg == NULL)
+		nfs_pageio_reset_write_mds(pgio);
+}
+EXPORT_SYMBOL_GPL(pnfs_generic_pg_init_write);
+
 bool
-pnfs_generic_pg_test(struct nfs_pageio_descriptor *pgio, struct nfs_page *prev,
-		     struct nfs_page *req)
+pnfs_pageio_init_read(struct nfs_pageio_descriptor *pgio, struct inode *inode)
 {
-	enum pnfs_iomode access_type;
-	gfp_t gfp_flags;
+	struct nfs_server *server = NFS_SERVER(inode);
+	struct pnfs_layoutdriver_type *ld = server->pnfs_curr_ld;
 
-	/* We assume that pg_ioflags == 0 iff we're reading a page */
-	if (pgio->pg_ioflags == 0) {
-		access_type = IOMODE_READ;
-		gfp_flags = GFP_KERNEL;
-	} else {
-		access_type = IOMODE_RW;
-		gfp_flags = GFP_NOFS;
-	}
+	if (ld == NULL)
+		return false;
+	nfs_pageio_init(pgio, inode, ld->pg_read_ops, server->rsize, 0);
+	return true;
+}
 
-	if (pgio->pg_lseg == NULL) {
-		if (pgio->pg_count != prev->wb_bytes)
-			return true;
-		/* This is first coelesce call for a series of nfs_pages */
-		pgio->pg_lseg = pnfs_update_layout(pgio->pg_inode,
-						   prev->wb_context,
-						   req_offset(prev),
-						   pgio->pg_count,
-						   access_type,
-						   gfp_flags);
-		if (pgio->pg_lseg == NULL)
-			return true;
-	}
+bool
+pnfs_pageio_init_write(struct nfs_pageio_descriptor *pgio, struct inode *inode, int ioflags)
+{
+	struct nfs_server *server = NFS_SERVER(inode);
+	struct pnfs_layoutdriver_type *ld = server->pnfs_curr_ld;
+
+	if (ld == NULL)
+		return false;
+	nfs_pageio_init(pgio, inode, ld->pg_write_ops, server->wsize, ioflags);
+	return true;
+}
+
+bool
+pnfs_generic_pg_test(struct nfs_pageio_descriptor *pgio, struct nfs_page *prev,
+		     struct nfs_page *req)
+{
+	if (pgio->pg_lseg == NULL)
+		return nfs_generic_pg_test(pgio, prev, req);
 
 	/*
 	 * Test if a nfs_page is fully contained in the pnfs_layout_range.
@@ -1120,15 +1188,30 @@ pnfs_ld_write_done(struct nfs_write_data *data)
 }
 EXPORT_SYMBOL_GPL(pnfs_ld_write_done);
 
-enum pnfs_try_status
+static void
+pnfs_write_through_mds(struct nfs_pageio_descriptor *desc,
+		struct nfs_write_data *data)
+{
+	list_splice_tail_init(&data->pages, &desc->pg_list);
+	if (data->req && list_empty(&data->req->wb_list))
+		nfs_list_add_request(data->req, &desc->pg_list);
+	nfs_pageio_reset_write_mds(desc);
+	desc->pg_recoalesce = 1;
+	nfs_writedata_release(data);
+}
+
+static enum pnfs_try_status
 pnfs_try_to_write_data(struct nfs_write_data *wdata,
-			const struct rpc_call_ops *call_ops, int how)
+			const struct rpc_call_ops *call_ops,
+			struct pnfs_layout_segment *lseg,
+			int how)
 {
 	struct inode *inode = wdata->inode;
 	enum pnfs_try_status trypnfs;
 	struct nfs_server *nfss = NFS_SERVER(inode);
 
 	wdata->mds_ops = call_ops;
+	wdata->lseg = get_lseg(lseg);
 
 	dprintk("%s: Writing ino:%lu %u@%llu (how %d)\n", __func__,
 		inode->i_ino, wdata->args.count, wdata->args.offset, how);
@@ -1144,6 +1227,44 @@ pnfs_try_to_write_data(struct nfs_write_data *wdata,
 	return trypnfs;
 }
 
+static void
+pnfs_do_multiple_writes(struct nfs_pageio_descriptor *desc, struct list_head *head, int how)
+{
+	struct nfs_write_data *data;
+	const struct rpc_call_ops *call_ops = desc->pg_rpc_callops;
+	struct pnfs_layout_segment *lseg = desc->pg_lseg;
+
+	desc->pg_lseg = NULL;
+	while (!list_empty(head)) {
+		enum pnfs_try_status trypnfs;
+
+		data = list_entry(head->next, struct nfs_write_data, list);
+		list_del_init(&data->list);
+
+		trypnfs = pnfs_try_to_write_data(data, call_ops, lseg, how);
+		if (trypnfs == PNFS_NOT_ATTEMPTED)
+			pnfs_write_through_mds(desc, data);
+	}
+	put_lseg(lseg);
+}
+
+int
+pnfs_generic_pg_writepages(struct nfs_pageio_descriptor *desc)
+{
+	LIST_HEAD(head);
+	int ret;
+
+	ret = nfs_generic_flush(desc, &head);
+	if (ret != 0) {
+		put_lseg(desc->pg_lseg);
+		desc->pg_lseg = NULL;
+		return ret;
+	}
+	pnfs_do_multiple_writes(desc, &head, desc->pg_ioflags);
+	return 0;
+}
+EXPORT_SYMBOL_GPL(pnfs_generic_pg_writepages);
+
 /*
  * Called by non rpc-based layout drivers
  */
@@ -1167,18 +1288,32 @@ pnfs_ld_read_done(struct nfs_read_data *data)
 }
 EXPORT_SYMBOL_GPL(pnfs_ld_read_done);
 
+static void
+pnfs_read_through_mds(struct nfs_pageio_descriptor *desc,
+		struct nfs_read_data *data)
+{
+	list_splice_tail_init(&data->pages, &desc->pg_list);
+	if (data->req && list_empty(&data->req->wb_list))
+		nfs_list_add_request(data->req, &desc->pg_list);
+	nfs_pageio_reset_read_mds(desc);
+	desc->pg_recoalesce = 1;
+	nfs_readdata_release(data);
+}
+
 /*
  * Call the appropriate parallel I/O subsystem read function.
  */
-enum pnfs_try_status
+static enum pnfs_try_status
 pnfs_try_to_read_data(struct nfs_read_data *rdata,
-		       const struct rpc_call_ops *call_ops)
+		       const struct rpc_call_ops *call_ops,
+		       struct pnfs_layout_segment *lseg)
 {
 	struct inode *inode = rdata->inode;
 	struct nfs_server *nfss = NFS_SERVER(inode);
 	enum pnfs_try_status trypnfs;
 
 	rdata->mds_ops = call_ops;
+	rdata->lseg = get_lseg(lseg);
 
 	dprintk("%s: Reading ino:%lu %u@%llu\n",
 		__func__, inode->i_ino, rdata->args.count, rdata->args.offset);
@@ -1194,17 +1329,56 @@ pnfs_try_to_read_data(struct nfs_read_data *rdata,
 	return trypnfs;
 }
 
+static void
+pnfs_do_multiple_reads(struct nfs_pageio_descriptor *desc, struct list_head *head)
+{
+	struct nfs_read_data *data;
+	const struct rpc_call_ops *call_ops = desc->pg_rpc_callops;
+	struct pnfs_layout_segment *lseg = desc->pg_lseg;
+
+	desc->pg_lseg = NULL;
+	while (!list_empty(head)) {
+		enum pnfs_try_status trypnfs;
+
+		data = list_entry(head->next, struct nfs_read_data, list);
+		list_del_init(&data->list);
+
+		trypnfs = pnfs_try_to_read_data(data, call_ops, lseg);
+		if (trypnfs == PNFS_NOT_ATTEMPTED)
+			pnfs_read_through_mds(desc, data);
+	}
+	put_lseg(lseg);
+}
+
+int
+pnfs_generic_pg_readpages(struct nfs_pageio_descriptor *desc)
+{
+	LIST_HEAD(head);
+	int ret;
+
+	ret = nfs_generic_pagein(desc, &head);
+	if (ret != 0) {
+		put_lseg(desc->pg_lseg);
+		desc->pg_lseg = NULL;
+		return ret;
+	}
+	pnfs_do_multiple_reads(desc, &head);
+	return 0;
+}
+EXPORT_SYMBOL_GPL(pnfs_generic_pg_readpages);
+
 /*
- * Currently there is only one (whole file) write lseg.
+ * There can be multiple RW segments.
  */
-static struct pnfs_layout_segment *pnfs_list_write_lseg(struct inode *inode)
+static void pnfs_list_write_lseg(struct inode *inode, struct list_head *listp)
 {
-	struct pnfs_layout_segment *lseg, *rv = NULL;
+	struct pnfs_layout_segment *lseg;
 
-	list_for_each_entry(lseg, &NFS_I(inode)->layout->plh_segs, pls_list)
-		if (lseg->pls_range.iomode == IOMODE_RW)
-			rv = lseg;
-	return rv;
+	list_for_each_entry(lseg, &NFS_I(inode)->layout->plh_segs, pls_list) {
+		if (lseg->pls_range.iomode == IOMODE_RW &&
+		    test_bit(NFS_LSEG_LAYOUTCOMMIT, &lseg->pls_flags))
+			list_add(&lseg->pls_lc_list, listp);
+	}
 }
 
 void
@@ -1216,17 +1390,19 @@ pnfs_set_layoutcommit(struct nfs_write_data *wdata)
 
 	spin_lock(&nfsi->vfs_inode.i_lock);
 	if (!test_and_set_bit(NFS_INO_LAYOUTCOMMIT, &nfsi->flags)) {
-		/* references matched in nfs4_layoutcommit_release */
-		get_lseg(wdata->lseg);
-		wdata->lseg->pls_lc_cred =
-			get_rpccred(wdata->args.context->state->owner->so_cred);
 		mark_as_dirty = true;
 		dprintk("%s: Set layoutcommit for inode %lu ",
 			__func__, wdata->inode->i_ino);
 	}
-	if (end_pos > wdata->lseg->pls_end_pos)
-		wdata->lseg->pls_end_pos = end_pos;
+	if (!test_and_set_bit(NFS_LSEG_LAYOUTCOMMIT, &wdata->lseg->pls_flags)) {
+		/* references matched in nfs4_layoutcommit_release */
+		get_lseg(wdata->lseg);
+	}
+	if (end_pos > nfsi->layout->plh_lwb)
+		nfsi->layout->plh_lwb = end_pos;
 	spin_unlock(&nfsi->vfs_inode.i_lock);
+	dprintk("%s: lseg %p end_pos %llu\n",
+		__func__, wdata->lseg, nfsi->layout->plh_lwb);
 
 	/* if pnfs_layoutcommit_inode() runs between inode locks, the next one
 	 * will be a noop because NFS_INO_LAYOUTCOMMIT will not be set */
@@ -1235,6 +1411,14 @@ pnfs_set_layoutcommit(struct nfs_write_data *wdata)
 }
 EXPORT_SYMBOL_GPL(pnfs_set_layoutcommit);
 
+void pnfs_cleanup_layoutcommit(struct nfs4_layoutcommit_data *data)
+{
+	struct nfs_server *nfss = NFS_SERVER(data->args.inode);
+
+	if (nfss->pnfs_curr_ld->cleanup_layoutcommit)
+		nfss->pnfs_curr_ld->cleanup_layoutcommit(data);
+}
+
 /*
  * For the LAYOUT4_NFSV4_1_FILES layout type, NFS_DATA_SYNC WRITEs and
  * NFS_UNSTABLE WRITEs with a COMMIT to data servers must store enough
@@ -1248,8 +1432,6 @@ pnfs_layoutcommit_inode(struct inode *inode, bool sync)
 {
 	struct nfs4_layoutcommit_data *data;
 	struct nfs_inode *nfsi = NFS_I(inode);
-	struct pnfs_layout_segment *lseg;
-	struct rpc_cred *cred;
 	loff_t end_pos;
 	int status = 0;
 
@@ -1266,30 +1448,25 @@ pnfs_layoutcommit_inode(struct inode *inode, bool sync)
 		goto out;
 	}
 
+	INIT_LIST_HEAD(&data->lseg_list);
 	spin_lock(&inode->i_lock);
 	if (!test_and_clear_bit(NFS_INO_LAYOUTCOMMIT, &nfsi->flags)) {
 		spin_unlock(&inode->i_lock);
 		kfree(data);
 		goto out;
 	}
-	/*
-	 * Currently only one (whole file) write lseg which is referenced
-	 * in pnfs_set_layoutcommit and will be found.
-	 */
-	lseg = pnfs_list_write_lseg(inode);
 
-	end_pos = lseg->pls_end_pos;
-	cred = lseg->pls_lc_cred;
-	lseg->pls_end_pos = 0;
-	lseg->pls_lc_cred = NULL;
+	pnfs_list_write_lseg(inode, &data->lseg_list);
+
+	end_pos = nfsi->layout->plh_lwb;
+	nfsi->layout->plh_lwb = 0;
 
 	memcpy(&data->args.stateid.data, nfsi->layout->plh_stateid.data,
 		sizeof(nfsi->layout->plh_stateid.data));
 	spin_unlock(&inode->i_lock);
 
 	data->args.inode = inode;
-	data->lseg = lseg;
-	data->cred = cred;
+	data->cred = get_rpccred(nfsi->layout->plh_lc_cred);
 	nfs_fattr_init(&data->fattr);
 	data->args.bitmask = NFS_SERVER(inode)->cache_consistency_bitmask;
 	data->res.fattr = &data->fattr;
diff --git a/fs/nfs/pnfs.h b/fs/nfs/pnfs.h
index 96bf4e6f45be..01cbfd54f3cb 100644
--- a/fs/nfs/pnfs.h
+++ b/fs/nfs/pnfs.h
@@ -36,16 +36,16 @@
 enum {
 	NFS_LSEG_VALID = 0,	/* cleared when lseg is recalled/returned */
 	NFS_LSEG_ROC,		/* roc bit received from server */
+	NFS_LSEG_LAYOUTCOMMIT,	/* layoutcommit bit set for layoutcommit */
 };
 
 struct pnfs_layout_segment {
 	struct list_head pls_list;
+	struct list_head pls_lc_list;
 	struct pnfs_layout_range pls_range;
 	atomic_t pls_refcount;
 	unsigned long pls_flags;
 	struct pnfs_layout_hdr *pls_layout;
-	struct rpc_cred	*pls_lc_cred; /* LAYOUTCOMMIT credential */
-	loff_t pls_end_pos; /* LAYOUTCOMMIT write end */
 };
 
 enum pnfs_try_status {
@@ -80,6 +80,9 @@ struct pnfs_layoutdriver_type {
 	struct module *owner;
 	unsigned flags;
 
+	int (*set_layoutdriver) (struct nfs_server *, const struct nfs_fh *);
+	int (*clear_layoutdriver) (struct nfs_server *);
+
 	struct pnfs_layout_hdr * (*alloc_layout_hdr) (struct inode *inode, gfp_t gfp_flags);
 	void (*free_layout_hdr) (struct pnfs_layout_hdr *);
 
@@ -87,7 +90,8 @@ struct pnfs_layoutdriver_type {
 	void (*free_lseg) (struct pnfs_layout_segment *lseg);
 
 	/* test for nfs page cache coalescing */
-	bool (*pg_test)(struct nfs_pageio_descriptor *, struct nfs_page *, struct nfs_page *);
+	const struct nfs_pageio_ops *pg_read_ops;
+	const struct nfs_pageio_ops *pg_write_ops;
 
 	/* Returns true if layoutdriver wants to divert this request to
 	 * driver's commit routine.
@@ -109,6 +113,8 @@ struct pnfs_layoutdriver_type {
 				     struct xdr_stream *xdr,
 				     const struct nfs4_layoutreturn_args *args);
 
+	void (*cleanup_layoutcommit) (struct nfs4_layoutcommit_data *data);
+
 	void (*encode_layoutcommit) (struct pnfs_layout_hdr *layoutid,
 				     struct xdr_stream *xdr,
 				     const struct nfs4_layoutcommit_args *args);
@@ -124,6 +130,8 @@ struct pnfs_layout_hdr {
 	unsigned long		plh_block_lgets; /* block LAYOUTGET if >0 */
 	u32			plh_barrier; /* ignore lower seqids */
 	unsigned long		plh_flags;
+	loff_t			plh_lwb; /* last write byte for layoutcommit */
+	struct rpc_cred		*plh_lc_cred; /* layoutcommit cred */
 	struct inode		*plh_inode;
 };
 
@@ -136,10 +144,21 @@ struct pnfs_device {
 	unsigned int  pglen;
 };
 
+#define NFS4_PNFS_GETDEVLIST_MAXNUM 16
+
+struct pnfs_devicelist {
+	unsigned int		eof;
+	unsigned int		num_devs;
+	struct nfs4_deviceid	dev_id[NFS4_PNFS_GETDEVLIST_MAXNUM];
+};
+
 extern int pnfs_register_layoutdriver(struct pnfs_layoutdriver_type *);
 extern void pnfs_unregister_layoutdriver(struct pnfs_layoutdriver_type *);
 
 /* nfs4proc.c */
+extern int nfs4_proc_getdevicelist(struct nfs_server *server,
+				   const struct nfs_fh *fh,
+				   struct pnfs_devicelist *devlist);
 extern int nfs4_proc_getdeviceinfo(struct nfs_server *server,
 				   struct pnfs_device *dev);
 extern int nfs4_proc_layoutget(struct nfs4_layoutget *lgp);
@@ -148,16 +167,16 @@ extern int nfs4_proc_layoutreturn(struct nfs4_layoutreturn *lrp);
 /* pnfs.c */
 void get_layout_hdr(struct pnfs_layout_hdr *lo);
 void put_lseg(struct pnfs_layout_segment *lseg);
-struct pnfs_layout_segment *
-pnfs_update_layout(struct inode *ino, struct nfs_open_context *ctx,
-		   loff_t pos, u64 count, enum pnfs_iomode access_type,
-		   gfp_t gfp_flags);
-void set_pnfs_layoutdriver(struct nfs_server *, u32 id);
+
+bool pnfs_pageio_init_read(struct nfs_pageio_descriptor *, struct inode *);
+bool pnfs_pageio_init_write(struct nfs_pageio_descriptor *, struct inode *, int);
+
+void set_pnfs_layoutdriver(struct nfs_server *, const struct nfs_fh *, u32);
 void unset_pnfs_layoutdriver(struct nfs_server *);
-enum pnfs_try_status pnfs_try_to_write_data(struct nfs_write_data *,
-					     const struct rpc_call_ops *, int);
-enum pnfs_try_status pnfs_try_to_read_data(struct nfs_read_data *,
-					    const struct rpc_call_ops *);
+void pnfs_generic_pg_init_read(struct nfs_pageio_descriptor *, struct nfs_page *);
+int pnfs_generic_pg_readpages(struct nfs_pageio_descriptor *desc);
+void pnfs_generic_pg_init_write(struct nfs_pageio_descriptor *, struct nfs_page *);
+int pnfs_generic_pg_writepages(struct nfs_pageio_descriptor *desc);
 bool pnfs_generic_pg_test(struct nfs_pageio_descriptor *pgio, struct nfs_page *prev, struct nfs_page *req);
 int pnfs_layout_process(struct nfs4_layoutget *lgp);
 void pnfs_free_lseg_list(struct list_head *tmp_list);
@@ -178,10 +197,24 @@ void pnfs_roc_release(struct inode *ino);
 void pnfs_roc_set_barrier(struct inode *ino, u32 barrier);
 bool pnfs_roc_drain(struct inode *ino, u32 *barrier);
 void pnfs_set_layoutcommit(struct nfs_write_data *wdata);
+void pnfs_cleanup_layoutcommit(struct nfs4_layoutcommit_data *data);
 int pnfs_layoutcommit_inode(struct inode *inode, bool sync);
 int _pnfs_return_layout(struct inode *);
 int pnfs_ld_write_done(struct nfs_write_data *);
 int pnfs_ld_read_done(struct nfs_read_data *);
+struct pnfs_layout_segment *pnfs_update_layout(struct inode *ino,
+					       struct nfs_open_context *ctx,
+					       loff_t pos,
+					       u64 count,
+					       enum pnfs_iomode iomode,
+					       gfp_t gfp_flags);
+
+void nfs4_deviceid_mark_client_invalid(struct nfs_client *clp);
+
+/* nfs4_deviceid_flags */
+enum {
+	NFS_DEVICEID_INVALID = 0,       /* set when MDS clientid recalled */
+};
 
 /* pnfs_dev.c */
 struct nfs4_deviceid_node {
@@ -189,13 +222,13 @@ struct nfs4_deviceid_node {
 	struct hlist_node		tmpnode;
 	const struct pnfs_layoutdriver_type *ld;
 	const struct nfs_client		*nfs_client;
+	unsigned long 			flags;
 	struct nfs4_deviceid		deviceid;
 	atomic_t			ref;
 };
 
 void nfs4_print_deviceid(const struct nfs4_deviceid *dev_id);
 struct nfs4_deviceid_node *nfs4_find_get_deviceid(const struct pnfs_layoutdriver_type *, const struct nfs_client *, const struct nfs4_deviceid *);
-struct nfs4_deviceid_node *nfs4_unhash_put_deviceid(const struct pnfs_layoutdriver_type *, const struct nfs_client *, const struct nfs4_deviceid *);
 void nfs4_delete_deviceid(const struct pnfs_layoutdriver_type *, const struct nfs_client *, const struct nfs4_deviceid *);
 void nfs4_init_deviceid_node(struct nfs4_deviceid_node *,
 			     const struct pnfs_layoutdriver_type *,
@@ -293,15 +326,6 @@ static inline int pnfs_return_layout(struct inode *ino)
 	return 0;
 }
 
-static inline void pnfs_pageio_init(struct nfs_pageio_descriptor *pgio,
-				    struct inode *inode)
-{
-	struct pnfs_layoutdriver_type *ld = NFS_SERVER(inode)->pnfs_curr_ld;
-
-	if (ld)
-		pgio->pg_test = ld->pg_test;
-}
-
 #else  /* CONFIG_NFS_V4_1 */
 
 static inline void pnfs_destroy_all_layouts(struct nfs_client *clp)
@@ -322,28 +346,6 @@ static inline void put_lseg(struct pnfs_layout_segment *lseg)
 {
 }
 
-static inline struct pnfs_layout_segment *
-pnfs_update_layout(struct inode *ino, struct nfs_open_context *ctx,
-		   loff_t pos, u64 count, enum pnfs_iomode access_type,
-		   gfp_t gfp_flags)
-{
-	return NULL;
-}
-
-static inline enum pnfs_try_status
-pnfs_try_to_read_data(struct nfs_read_data *data,
-		      const struct rpc_call_ops *call_ops)
-{
-	return PNFS_NOT_ATTEMPTED;
-}
-
-static inline enum pnfs_try_status
-pnfs_try_to_write_data(struct nfs_write_data *data,
-		       const struct rpc_call_ops *call_ops, int how)
-{
-	return PNFS_NOT_ATTEMPTED;
-}
-
 static inline int pnfs_return_layout(struct inode *ino)
 {
 	return 0;
@@ -377,7 +379,8 @@ pnfs_roc_drain(struct inode *ino, u32 *barrier)
 	return false;
 }
 
-static inline void set_pnfs_layoutdriver(struct nfs_server *s, u32 id)
+static inline void set_pnfs_layoutdriver(struct nfs_server *s,
+					 const struct nfs_fh *mntfh, u32 id)
 {
 }
 
@@ -385,9 +388,14 @@ static inline void unset_pnfs_layoutdriver(struct nfs_server *s)
 {
 }
 
-static inline void pnfs_pageio_init(struct nfs_pageio_descriptor *pgio,
-				    struct inode *inode)
+static inline bool pnfs_pageio_init_read(struct nfs_pageio_descriptor *pgio, struct inode *inode)
+{
+	return false;
+}
+
+static inline bool pnfs_pageio_init_write(struct nfs_pageio_descriptor *pgio, struct inode *inode, int ioflags)
 {
+	return false;
 }
 
 static inline void
diff --git a/fs/nfs/pnfs_dev.c b/fs/nfs/pnfs_dev.c
index f0f8e1e22f6c..6fda5228ef56 100644
--- a/fs/nfs/pnfs_dev.c
+++ b/fs/nfs/pnfs_dev.c
@@ -100,8 +100,8 @@ _find_get_deviceid(const struct pnfs_layoutdriver_type *ld,
 
 	rcu_read_lock();
 	d = _lookup_deviceid(ld, clp, id, hash);
-	if (d && !atomic_inc_not_zero(&d->ref))
-		d = NULL;
+	if (d != NULL)
+		atomic_inc(&d->ref);
 	rcu_read_unlock();
 	return d;
 }
@@ -115,15 +115,15 @@ nfs4_find_get_deviceid(const struct pnfs_layoutdriver_type *ld,
 EXPORT_SYMBOL_GPL(nfs4_find_get_deviceid);
 
 /*
- * Unhash and put deviceid
+ * Remove a deviceid from cache
  *
  * @clp nfs_client associated with deviceid
  * @id the deviceid to unhash
  *
  * @ret the unhashed node, if found and dereferenced to zero, NULL otherwise.
  */
-struct nfs4_deviceid_node *
-nfs4_unhash_put_deviceid(const struct pnfs_layoutdriver_type *ld,
+void
+nfs4_delete_deviceid(const struct pnfs_layoutdriver_type *ld,
 			 const struct nfs_client *clp, const struct nfs4_deviceid *id)
 {
 	struct nfs4_deviceid_node *d;
@@ -134,7 +134,7 @@ nfs4_unhash_put_deviceid(const struct pnfs_layoutdriver_type *ld,
 	rcu_read_unlock();
 	if (!d) {
 		spin_unlock(&nfs4_deviceid_lock);
-		return NULL;
+		return;
 	}
 	hlist_del_init_rcu(&d->node);
 	spin_unlock(&nfs4_deviceid_lock);
@@ -142,28 +142,7 @@ nfs4_unhash_put_deviceid(const struct pnfs_layoutdriver_type *ld,
 
 	/* balance the initial ref set in pnfs_insert_deviceid */
 	if (atomic_dec_and_test(&d->ref))
-		return d;
-
-	return NULL;
-}
-EXPORT_SYMBOL_GPL(nfs4_unhash_put_deviceid);
-
-/*
- * Delete a deviceid from cache
- *
- * @clp struct nfs_client qualifying the deviceid
- * @id deviceid to delete
- */
-void
-nfs4_delete_deviceid(const struct pnfs_layoutdriver_type *ld,
-		     const struct nfs_client *clp, const struct nfs4_deviceid *id)
-{
-	struct nfs4_deviceid_node *d;
-
-	d = nfs4_unhash_put_deviceid(ld, clp, id);
-	if (!d)
-		return;
-	d->ld->free_deviceid_node(d);
+		d->ld->free_deviceid_node(d);
 }
 EXPORT_SYMBOL_GPL(nfs4_delete_deviceid);
 
@@ -177,6 +156,7 @@ nfs4_init_deviceid_node(struct nfs4_deviceid_node *d,
 	INIT_HLIST_NODE(&d->tmpnode);
 	d->ld = ld;
 	d->nfs_client = nfs_client;
+	d->flags = 0;
 	d->deviceid = *id;
 	atomic_set(&d->ref, 1);
 }
@@ -221,16 +201,15 @@ EXPORT_SYMBOL_GPL(nfs4_insert_deviceid_node);
  *
  * @d deviceid node to put
  *
- * @ret true iff the node was deleted
+ * return true iff the node was deleted
+ * Note that since the test for d->ref == 0 is sufficient to establish
+ * that the node is no longer hashed in the global device id cache.
  */
 bool
 nfs4_put_deviceid_node(struct nfs4_deviceid_node *d)
 {
-	if (!atomic_dec_and_lock(&d->ref, &nfs4_deviceid_lock))
+	if (!atomic_dec_and_test(&d->ref))
 		return false;
-	hlist_del_init_rcu(&d->node);
-	spin_unlock(&nfs4_deviceid_lock);
-	synchronize_rcu();
 	d->ld->free_deviceid_node(d);
 	return true;
 }
@@ -275,3 +254,22 @@ nfs4_deviceid_purge_client(const struct nfs_client *clp)
 	for (h = 0; h < NFS4_DEVICE_ID_HASH_SIZE; h++)
 		_deviceid_purge_client(clp, h);
 }
+
+/*
+ * Stop use of all deviceids associated with an nfs_client
+ */
+void
+nfs4_deviceid_mark_client_invalid(struct nfs_client *clp)
+{
+	struct nfs4_deviceid_node *d;
+	struct hlist_node *n;
+	int i;
+
+	rcu_read_lock();
+	for (i = 0; i < NFS4_DEVICE_ID_HASH_SIZE; i ++){
+		hlist_for_each_entry_rcu(d, n, &nfs4_deviceid_cache[i], node)
+			if (d->nfs_client == clp)
+				set_bit(NFS_DEVICEID_INVALID, &d->flags);
+	}
+	rcu_read_unlock();
+}
diff --git a/fs/nfs/read.c b/fs/nfs/read.c
index a68679f538fc..2171c043ab08 100644
--- a/fs/nfs/read.c
+++ b/fs/nfs/read.c
@@ -30,8 +30,7 @@
 
 #define NFSDBG_FACILITY		NFSDBG_PAGECACHE
 
-static int nfs_pagein_multi(struct nfs_pageio_descriptor *desc);
-static int nfs_pagein_one(struct nfs_pageio_descriptor *desc);
+static const struct nfs_pageio_ops nfs_pageio_read_ops;
 static const struct rpc_call_ops nfs_read_partial_ops;
 static const struct rpc_call_ops nfs_read_full_ops;
 
@@ -68,7 +67,7 @@ void nfs_readdata_free(struct nfs_read_data *p)
 	mempool_free(p, nfs_rdata_mempool);
 }
 
-static void nfs_readdata_release(struct nfs_read_data *rdata)
+void nfs_readdata_release(struct nfs_read_data *rdata)
 {
 	put_lseg(rdata->lseg);
 	put_nfs_open_context(rdata->args.context);
@@ -113,6 +112,27 @@ static void nfs_readpage_truncate_uninitialised_page(struct nfs_read_data *data)
 	}
 }
 
+static void nfs_pageio_init_read_mds(struct nfs_pageio_descriptor *pgio,
+		struct inode *inode)
+{
+	nfs_pageio_init(pgio, inode, &nfs_pageio_read_ops,
+			NFS_SERVER(inode)->rsize, 0);
+}
+
+void nfs_pageio_reset_read_mds(struct nfs_pageio_descriptor *pgio)
+{
+	pgio->pg_ops = &nfs_pageio_read_ops;
+	pgio->pg_bsize = NFS_SERVER(pgio->pg_inode)->rsize;
+}
+EXPORT_SYMBOL_GPL(nfs_pageio_reset_read_mds);
+
+static void nfs_pageio_init_read(struct nfs_pageio_descriptor *pgio,
+		struct inode *inode)
+{
+	if (!pnfs_pageio_init_read(pgio, inode))
+		nfs_pageio_init_read_mds(pgio, inode);
+}
+
 int nfs_readpage_async(struct nfs_open_context *ctx, struct inode *inode,
 		       struct page *page)
 {
@@ -131,14 +151,9 @@ int nfs_readpage_async(struct nfs_open_context *ctx, struct inode *inode,
 	if (len < PAGE_CACHE_SIZE)
 		zero_user_segment(page, len, PAGE_CACHE_SIZE);
 
-	nfs_pageio_init(&pgio, inode, NULL, 0, 0);
-	nfs_list_add_request(new, &pgio.pg_list);
-	pgio.pg_count = len;
-
-	if (NFS_SERVER(inode)->rsize < PAGE_CACHE_SIZE)
-		nfs_pagein_multi(&pgio);
-	else
-		nfs_pagein_one(&pgio);
+	nfs_pageio_init_read(&pgio, inode);
+	nfs_pageio_add_request(&pgio, new);
+	nfs_pageio_complete(&pgio);
 	return 0;
 }
 
@@ -202,17 +217,14 @@ EXPORT_SYMBOL_GPL(nfs_initiate_read);
 /*
  * Set up the NFS read request struct
  */
-static int nfs_read_rpcsetup(struct nfs_page *req, struct nfs_read_data *data,
-		const struct rpc_call_ops *call_ops,
-		unsigned int count, unsigned int offset,
-		struct pnfs_layout_segment *lseg)
+static void nfs_read_rpcsetup(struct nfs_page *req, struct nfs_read_data *data,
+		unsigned int count, unsigned int offset)
 {
 	struct inode *inode = req->wb_context->dentry->d_inode;
 
 	data->req	  = req;
 	data->inode	  = inode;
 	data->cred	  = req->wb_context->cred;
-	data->lseg	  = get_lseg(lseg);
 
 	data->args.fh     = NFS_FH(inode);
 	data->args.offset = req_offset(req) + offset;
@@ -226,14 +238,36 @@ static int nfs_read_rpcsetup(struct nfs_page *req, struct nfs_read_data *data,
 	data->res.count   = count;
 	data->res.eof     = 0;
 	nfs_fattr_init(&data->fattr);
+}
 
-	if (data->lseg &&
-	    (pnfs_try_to_read_data(data, call_ops) == PNFS_ATTEMPTED))
-		return 0;
+static int nfs_do_read(struct nfs_read_data *data,
+		const struct rpc_call_ops *call_ops)
+{
+	struct inode *inode = data->args.context->dentry->d_inode;
 
 	return nfs_initiate_read(data, NFS_CLIENT(inode), call_ops);
 }
 
+static int
+nfs_do_multiple_reads(struct list_head *head,
+		const struct rpc_call_ops *call_ops)
+{
+	struct nfs_read_data *data;
+	int ret = 0;
+
+	while (!list_empty(head)) {
+		int ret2;
+
+		data = list_entry(head->next, struct nfs_read_data, list);
+		list_del_init(&data->list);
+
+		ret2 = nfs_do_read(data, call_ops);
+		if (ret == 0)
+			ret = ret2;
+	}
+	return ret;
+}
+
 static void
 nfs_async_read_error(struct list_head *head)
 {
@@ -260,20 +294,19 @@ nfs_async_read_error(struct list_head *head)
  * won't see the new data until our attribute cache is updated.  This is more
  * or less conventional NFS client behavior.
  */
-static int nfs_pagein_multi(struct nfs_pageio_descriptor *desc)
+static int nfs_pagein_multi(struct nfs_pageio_descriptor *desc, struct list_head *res)
 {
 	struct nfs_page *req = nfs_list_entry(desc->pg_list.next);
 	struct page *page = req->wb_page;
 	struct nfs_read_data *data;
-	size_t rsize = NFS_SERVER(desc->pg_inode)->rsize, nbytes;
+	size_t rsize = desc->pg_bsize, nbytes;
 	unsigned int offset;
 	int requests = 0;
 	int ret = 0;
-	struct pnfs_layout_segment *lseg;
-	LIST_HEAD(list);
 
 	nfs_list_remove_request(req);
 
+	offset = 0;
 	nbytes = desc->pg_count;
 	do {
 		size_t len = min(nbytes,rsize);
@@ -281,45 +314,21 @@ static int nfs_pagein_multi(struct nfs_pageio_descriptor *desc)
 		data = nfs_readdata_alloc(1);
 		if (!data)
 			goto out_bad;
-		list_add(&data->pages, &list);
+		data->pagevec[0] = page;
+		nfs_read_rpcsetup(req, data, len, offset);
+		list_add(&data->list, res);
 		requests++;
 		nbytes -= len;
+		offset += len;
 	} while(nbytes != 0);
 	atomic_set(&req->wb_complete, requests);
-
-	BUG_ON(desc->pg_lseg != NULL);
-	lseg = pnfs_update_layout(desc->pg_inode, req->wb_context,
-				  req_offset(req), desc->pg_count,
-				  IOMODE_READ, GFP_KERNEL);
 	ClearPageError(page);
-	offset = 0;
-	nbytes = desc->pg_count;
-	do {
-		int ret2;
-
-		data = list_entry(list.next, struct nfs_read_data, pages);
-		list_del_init(&data->pages);
-
-		data->pagevec[0] = page;
-
-		if (nbytes < rsize)
-			rsize = nbytes;
-		ret2 = nfs_read_rpcsetup(req, data, &nfs_read_partial_ops,
-					 rsize, offset, lseg);
-		if (ret == 0)
-			ret = ret2;
-		offset += rsize;
-		nbytes -= rsize;
-	} while (nbytes != 0);
-	put_lseg(lseg);
-	desc->pg_lseg = NULL;
-
+	desc->pg_rpc_callops = &nfs_read_partial_ops;
 	return ret;
-
 out_bad:
-	while (!list_empty(&list)) {
-		data = list_entry(list.next, struct nfs_read_data, pages);
-		list_del(&data->pages);
+	while (!list_empty(res)) {
+		data = list_entry(res->next, struct nfs_read_data, list);
+		list_del(&data->list);
 		nfs_readdata_free(data);
 	}
 	SetPageError(page);
@@ -327,19 +336,19 @@ out_bad:
 	return -ENOMEM;
 }
 
-static int nfs_pagein_one(struct nfs_pageio_descriptor *desc)
+static int nfs_pagein_one(struct nfs_pageio_descriptor *desc, struct list_head *res)
 {
 	struct nfs_page		*req;
 	struct page		**pages;
 	struct nfs_read_data	*data;
 	struct list_head *head = &desc->pg_list;
-	struct pnfs_layout_segment *lseg = desc->pg_lseg;
-	int ret = -ENOMEM;
+	int ret = 0;
 
 	data = nfs_readdata_alloc(nfs_page_array_len(desc->pg_base,
 						     desc->pg_count));
 	if (!data) {
 		nfs_async_read_error(head);
+		ret = -ENOMEM;
 		goto out;
 	}
 
@@ -352,19 +361,37 @@ static int nfs_pagein_one(struct nfs_pageio_descriptor *desc)
 		*pages++ = req->wb_page;
 	}
 	req = nfs_list_entry(data->pages.next);
-	if ((!lseg) && list_is_singular(&data->pages))
-		lseg = pnfs_update_layout(desc->pg_inode, req->wb_context,
-					  req_offset(req), desc->pg_count,
-					  IOMODE_READ, GFP_KERNEL);
 
-	ret = nfs_read_rpcsetup(req, data, &nfs_read_full_ops, desc->pg_count,
-				0, lseg);
+	nfs_read_rpcsetup(req, data, desc->pg_count, 0);
+	list_add(&data->list, res);
+	desc->pg_rpc_callops = &nfs_read_full_ops;
 out:
-	put_lseg(lseg);
-	desc->pg_lseg = NULL;
 	return ret;
 }
 
+int nfs_generic_pagein(struct nfs_pageio_descriptor *desc, struct list_head *head)
+{
+	if (desc->pg_bsize < PAGE_CACHE_SIZE)
+		return nfs_pagein_multi(desc, head);
+	return nfs_pagein_one(desc, head);
+}
+
+static int nfs_generic_pg_readpages(struct nfs_pageio_descriptor *desc)
+{
+	LIST_HEAD(head);
+	int ret;
+
+	ret = nfs_generic_pagein(desc, &head);
+	if (ret == 0)
+		ret = nfs_do_multiple_reads(&head, desc->pg_rpc_callops);
+	return ret;
+}
+
+static const struct nfs_pageio_ops nfs_pageio_read_ops = {
+	.pg_test = nfs_generic_pg_test,
+	.pg_doio = nfs_generic_pg_readpages,
+};
+
 /*
  * This is the callback from RPC telling us whether a reply was
  * received or some error occurred (timeout or socket shutdown).
@@ -635,8 +662,6 @@ int nfs_readpages(struct file *filp, struct address_space *mapping,
 		.pgio = &pgio,
 	};
 	struct inode *inode = mapping->host;
-	struct nfs_server *server = NFS_SERVER(inode);
-	size_t rsize = server->rsize;
 	unsigned long npages;
 	int ret = -ESTALE;
 
@@ -664,10 +689,7 @@ int nfs_readpages(struct file *filp, struct address_space *mapping,
 	if (ret == 0)
 		goto read_complete; /* all pages were read */
 
-	if (rsize < PAGE_CACHE_SIZE)
-		nfs_pageio_init(&pgio, inode, nfs_pagein_multi, rsize, 0);
-	else
-		nfs_pageio_init(&pgio, inode, nfs_pagein_one, rsize, 0);
+	nfs_pageio_init_read(&pgio, inode);
 
 	ret = read_cache_pages(mapping, pages, readpage_async_filler, &desc);
 
diff --git a/fs/nfs/unlink.c b/fs/nfs/unlink.c
index 8d6864c2a5fa..b2fbbde58e44 100644
--- a/fs/nfs/unlink.c
+++ b/fs/nfs/unlink.c
@@ -147,7 +147,7 @@ static int nfs_do_call_unlink(struct dentry *parent, struct inode *dir, struct n
 
 	alias = d_lookup(parent, &data->args.name);
 	if (alias != NULL) {
-		int ret = 0;
+		int ret;
 		void *devname_garbage = NULL;
 
 		/*
@@ -155,14 +155,16 @@ static int nfs_do_call_unlink(struct dentry *parent, struct inode *dir, struct n
 		 * the sillyrename information to the aliased dentry.
 		 */
 		nfs_free_dname(data);
+		ret = nfs_copy_dname(alias, data);
 		spin_lock(&alias->d_lock);
-		if (alias->d_inode != NULL &&
+		if (ret == 0 && alias->d_inode != NULL &&
 		    !(alias->d_flags & DCACHE_NFSFS_RENAMED)) {
 			devname_garbage = alias->d_fsdata;
 			alias->d_fsdata = data;
 			alias->d_flags |= DCACHE_NFSFS_RENAMED;
 			ret = 1;
-		}
+		} else
+			ret = 0;
 		spin_unlock(&alias->d_lock);
 		nfs_dec_sillycount(dir);
 		dput(alias);
@@ -171,8 +173,7 @@ static int nfs_do_call_unlink(struct dentry *parent, struct inode *dir, struct n
 		 * point dentry is definitely not a root, so we won't need
 		 * that anymore.
 		 */
-		if (devname_garbage)
-			kfree(devname_garbage);
+		kfree(devname_garbage);
 		return ret;
 	}
 	data->dir = igrab(dir);
@@ -204,8 +205,6 @@ static int nfs_call_unlink(struct dentry *dentry, struct nfs_unlinkdata *data)
 	if (parent == NULL)
 		goto out_free;
 	dir = parent->d_inode;
-	if (nfs_copy_dname(dentry, data) != 0)
-		goto out_dput;
 	/* Non-exclusive lock protects against concurrent lookup() calls */
 	spin_lock(&dir->i_lock);
 	if (atomic_inc_not_zero(&NFS_I(dir)->silly_count) == 0) {
@@ -366,6 +365,8 @@ static void nfs_async_rename_done(struct rpc_task *task, void *calldata)
 	struct nfs_renamedata *data = calldata;
 	struct inode *old_dir = data->old_dir;
 	struct inode *new_dir = data->new_dir;
+	struct dentry *old_dentry = data->old_dentry;
+	struct dentry *new_dentry = data->new_dentry;
 
 	if (!NFS_PROTO(old_dir)->rename_done(task, old_dir, new_dir)) {
 		nfs_restart_rpc(task, NFS_SERVER(old_dir)->nfs_client);
@@ -373,12 +374,12 @@ static void nfs_async_rename_done(struct rpc_task *task, void *calldata)
 	}
 
 	if (task->tk_status != 0) {
-		nfs_cancel_async_unlink(data->old_dentry);
+		nfs_cancel_async_unlink(old_dentry);
 		return;
 	}
 
-	nfs_set_verifier(data->old_dentry, nfs_save_change_attribute(old_dir));
-	d_move(data->old_dentry, data->new_dentry);
+	d_drop(old_dentry);
+	d_drop(new_dentry);
 }
 
 /**
@@ -501,6 +502,14 @@ nfs_async_rename(struct inode *old_dir, struct inode *new_dir,
  * and only performs the unlink once the last reference to it is put.
  *
  * The final cleanup is done during dentry_iput.
+ *
+ * (Note: NFSv4 is stateful, and has opens, so in theory an NFSv4 server
+ * could take responsibility for keeping open files referenced.  The server
+ * would also need to ensure that opened-but-deleted files were kept over
+ * reboots.  However, we may not assume a server does so.  (RFC 5661
+ * does provide an OPEN4_RESULT_PRESERVE_UNLINKED flag that a server can
+ * use to advertise that it does this; some day we may take advantage of
+ * it.))
  */
 int
 nfs_sillyrename(struct inode *dir, struct dentry *dentry)
@@ -560,6 +569,14 @@ nfs_sillyrename(struct inode *dir, struct dentry *dentry)
 	if (error)
 		goto out_dput;
 
+	/* populate unlinkdata with the right dname */
+	error = nfs_copy_dname(sdentry,
+				(struct nfs_unlinkdata *)dentry->d_fsdata);
+	if (error) {
+		nfs_cancel_async_unlink(dentry);
+		goto out_dput;
+	}
+
 	/* run the rename task, undo unlink if it fails */
 	task = nfs_async_rename(dir, dir, dentry, sdentry);
 	if (IS_ERR(task)) {
diff --git a/fs/nfs/write.c b/fs/nfs/write.c
index 08579312c57b..b39b37f80913 100644
--- a/fs/nfs/write.c
+++ b/fs/nfs/write.c
@@ -97,7 +97,7 @@ void nfs_writedata_free(struct nfs_write_data *p)
 	mempool_free(p, nfs_wdata_mempool);
 }
 
-static void nfs_writedata_release(struct nfs_write_data *wdata)
+void nfs_writedata_release(struct nfs_write_data *wdata)
 {
 	put_lseg(wdata->lseg);
 	put_nfs_open_context(wdata->args.context);
@@ -845,11 +845,9 @@ EXPORT_SYMBOL_GPL(nfs_initiate_write);
 /*
  * Set up the argument/result storage required for the RPC call.
  */
-static int nfs_write_rpcsetup(struct nfs_page *req,
+static void nfs_write_rpcsetup(struct nfs_page *req,
 		struct nfs_write_data *data,
-		const struct rpc_call_ops *call_ops,
 		unsigned int count, unsigned int offset,
-		struct pnfs_layout_segment *lseg,
 		int how)
 {
 	struct inode *inode = req->wb_context->dentry->d_inode;
@@ -860,7 +858,6 @@ static int nfs_write_rpcsetup(struct nfs_page *req,
 	data->req = req;
 	data->inode = inode = req->wb_context->dentry->d_inode;
 	data->cred = req->wb_context->cred;
-	data->lseg = get_lseg(lseg);
 
 	data->args.fh     = NFS_FH(inode);
 	data->args.offset = req_offset(req) + offset;
@@ -872,24 +869,51 @@ static int nfs_write_rpcsetup(struct nfs_page *req,
 	data->args.context = get_nfs_open_context(req->wb_context);
 	data->args.lock_context = req->wb_lock_context;
 	data->args.stable  = NFS_UNSTABLE;
-	if (how & (FLUSH_STABLE | FLUSH_COND_STABLE)) {
-		data->args.stable = NFS_DATA_SYNC;
-		if (!nfs_need_commit(NFS_I(inode)))
-			data->args.stable = NFS_FILE_SYNC;
+	switch (how & (FLUSH_STABLE | FLUSH_COND_STABLE)) {
+	case 0:
+		break;
+	case FLUSH_COND_STABLE:
+		if (nfs_need_commit(NFS_I(inode)))
+			break;
+	default:
+		data->args.stable = NFS_FILE_SYNC;
 	}
 
 	data->res.fattr   = &data->fattr;
 	data->res.count   = count;
 	data->res.verf    = &data->verf;
 	nfs_fattr_init(&data->fattr);
+}
 
-	if (data->lseg &&
-	    (pnfs_try_to_write_data(data, call_ops, how) == PNFS_ATTEMPTED))
-		return 0;
+static int nfs_do_write(struct nfs_write_data *data,
+		const struct rpc_call_ops *call_ops,
+		int how)
+{
+	struct inode *inode = data->args.context->dentry->d_inode;
 
 	return nfs_initiate_write(data, NFS_CLIENT(inode), call_ops, how);
 }
 
+static int nfs_do_multiple_writes(struct list_head *head,
+		const struct rpc_call_ops *call_ops,
+		int how)
+{
+	struct nfs_write_data *data;
+	int ret = 0;
+
+	while (!list_empty(head)) {
+		int ret2;
+
+		data = list_entry(head->next, struct nfs_write_data, list);
+		list_del_init(&data->list);
+		
+		ret2 = nfs_do_write(data, call_ops, how);
+		 if (ret == 0)
+			 ret = ret2;
+	}
+	return ret;
+}
+
 /* If a nfs_flush_* function fails, it should remove reqs from @head and
  * call this on each, which will prepare them to be retried on next
  * writeback using standard nfs.
@@ -907,17 +931,15 @@ static void nfs_redirty_request(struct nfs_page *req)
  * Generate multiple small requests to write out a single
  * contiguous dirty area on one page.
  */
-static int nfs_flush_multi(struct nfs_pageio_descriptor *desc)
+static int nfs_flush_multi(struct nfs_pageio_descriptor *desc, struct list_head *res)
 {
 	struct nfs_page *req = nfs_list_entry(desc->pg_list.next);
 	struct page *page = req->wb_page;
 	struct nfs_write_data *data;
-	size_t wsize = NFS_SERVER(desc->pg_inode)->wsize, nbytes;
+	size_t wsize = desc->pg_bsize, nbytes;
 	unsigned int offset;
 	int requests = 0;
 	int ret = 0;
-	struct pnfs_layout_segment *lseg;
-	LIST_HEAD(list);
 
 	nfs_list_remove_request(req);
 
@@ -927,6 +949,7 @@ static int nfs_flush_multi(struct nfs_pageio_descriptor *desc)
 		desc->pg_ioflags &= ~FLUSH_COND_STABLE;
 
 
+	offset = 0;
 	nbytes = desc->pg_count;
 	do {
 		size_t len = min(nbytes, wsize);
@@ -934,45 +957,21 @@ static int nfs_flush_multi(struct nfs_pageio_descriptor *desc)
 		data = nfs_writedata_alloc(1);
 		if (!data)
 			goto out_bad;
-		list_add(&data->pages, &list);
+		data->pagevec[0] = page;
+		nfs_write_rpcsetup(req, data, wsize, offset, desc->pg_ioflags);
+		list_add(&data->list, res);
 		requests++;
 		nbytes -= len;
+		offset += len;
 	} while (nbytes != 0);
 	atomic_set(&req->wb_complete, requests);
-
-	BUG_ON(desc->pg_lseg);
-	lseg = pnfs_update_layout(desc->pg_inode, req->wb_context,
-				  req_offset(req), desc->pg_count,
-				  IOMODE_RW, GFP_NOFS);
-	ClearPageError(page);
-	offset = 0;
-	nbytes = desc->pg_count;
-	do {
-		int ret2;
-
-		data = list_entry(list.next, struct nfs_write_data, pages);
-		list_del_init(&data->pages);
-
-		data->pagevec[0] = page;
-
-		if (nbytes < wsize)
-			wsize = nbytes;
-		ret2 = nfs_write_rpcsetup(req, data, &nfs_write_partial_ops,
-					  wsize, offset, lseg, desc->pg_ioflags);
-		if (ret == 0)
-			ret = ret2;
-		offset += wsize;
-		nbytes -= wsize;
-	} while (nbytes != 0);
-
-	put_lseg(lseg);
-	desc->pg_lseg = NULL;
+	desc->pg_rpc_callops = &nfs_write_partial_ops;
 	return ret;
 
 out_bad:
-	while (!list_empty(&list)) {
-		data = list_entry(list.next, struct nfs_write_data, pages);
-		list_del(&data->pages);
+	while (!list_empty(res)) {
+		data = list_entry(res->next, struct nfs_write_data, list);
+		list_del(&data->list);
 		nfs_writedata_free(data);
 	}
 	nfs_redirty_request(req);
@@ -987,14 +986,13 @@ out_bad:
  * This is the case if nfs_updatepage detects a conflicting request
  * that has been written but not committed.
  */
-static int nfs_flush_one(struct nfs_pageio_descriptor *desc)
+static int nfs_flush_one(struct nfs_pageio_descriptor *desc, struct list_head *res)
 {
 	struct nfs_page		*req;
 	struct page		**pages;
 	struct nfs_write_data	*data;
 	struct list_head *head = &desc->pg_list;
-	struct pnfs_layout_segment *lseg = desc->pg_lseg;
-	int ret;
+	int ret = 0;
 
 	data = nfs_writedata_alloc(nfs_page_array_len(desc->pg_base,
 						      desc->pg_count));
@@ -1016,32 +1014,62 @@ static int nfs_flush_one(struct nfs_pageio_descriptor *desc)
 		*pages++ = req->wb_page;
 	}
 	req = nfs_list_entry(data->pages.next);
-	if ((!lseg) && list_is_singular(&data->pages))
-		lseg = pnfs_update_layout(desc->pg_inode, req->wb_context,
-					  req_offset(req), desc->pg_count,
-					  IOMODE_RW, GFP_NOFS);
 
 	if ((desc->pg_ioflags & FLUSH_COND_STABLE) &&
 	    (desc->pg_moreio || NFS_I(desc->pg_inode)->ncommit))
 		desc->pg_ioflags &= ~FLUSH_COND_STABLE;
 
 	/* Set up the argument struct */
-	ret = nfs_write_rpcsetup(req, data, &nfs_write_full_ops, desc->pg_count, 0, lseg, desc->pg_ioflags);
+	nfs_write_rpcsetup(req, data, desc->pg_count, 0, desc->pg_ioflags);
+	list_add(&data->list, res);
+	desc->pg_rpc_callops = &nfs_write_full_ops;
 out:
-	put_lseg(lseg); /* Cleans any gotten in ->pg_test */
-	desc->pg_lseg = NULL;
 	return ret;
 }
 
-static void nfs_pageio_init_write(struct nfs_pageio_descriptor *pgio,
+int nfs_generic_flush(struct nfs_pageio_descriptor *desc, struct list_head *head)
+{
+	if (desc->pg_bsize < PAGE_CACHE_SIZE)
+		return nfs_flush_multi(desc, head);
+	return nfs_flush_one(desc, head);
+}
+
+static int nfs_generic_pg_writepages(struct nfs_pageio_descriptor *desc)
+{
+	LIST_HEAD(head);
+	int ret;
+
+	ret = nfs_generic_flush(desc, &head);
+	if (ret == 0)
+		ret = nfs_do_multiple_writes(&head, desc->pg_rpc_callops,
+				desc->pg_ioflags);
+	return ret;
+}
+
+static const struct nfs_pageio_ops nfs_pageio_write_ops = {
+	.pg_test = nfs_generic_pg_test,
+	.pg_doio = nfs_generic_pg_writepages,
+};
+
+static void nfs_pageio_init_write_mds(struct nfs_pageio_descriptor *pgio,
 				  struct inode *inode, int ioflags)
 {
-	size_t wsize = NFS_SERVER(inode)->wsize;
+	nfs_pageio_init(pgio, inode, &nfs_pageio_write_ops,
+				NFS_SERVER(inode)->wsize, ioflags);
+}
+
+void nfs_pageio_reset_write_mds(struct nfs_pageio_descriptor *pgio)
+{
+	pgio->pg_ops = &nfs_pageio_write_ops;
+	pgio->pg_bsize = NFS_SERVER(pgio->pg_inode)->wsize;
+}
+EXPORT_SYMBOL_GPL(nfs_pageio_reset_write_mds);
 
-	if (wsize < PAGE_CACHE_SIZE)
-		nfs_pageio_init(pgio, inode, nfs_flush_multi, wsize, ioflags);
-	else
-		nfs_pageio_init(pgio, inode, nfs_flush_one, wsize, ioflags);
+static void nfs_pageio_init_write(struct nfs_pageio_descriptor *pgio,
+				  struct inode *inode, int ioflags)
+{
+	if (!pnfs_pageio_init_write(pgio, inode, ioflags))
+		nfs_pageio_init_write_mds(pgio, inode, ioflags);
 }
 
 /*
@@ -1566,8 +1594,7 @@ int nfs_write_inode(struct inode *inode, struct writeback_control *wbc)
 		int status;
 		bool sync = true;
 
-		if (wbc->sync_mode == WB_SYNC_NONE || wbc->nonblocking ||
-		    wbc->for_background)
+		if (wbc->sync_mode == WB_SYNC_NONE)
 			sync = false;
 
 		status = pnfs_layoutcommit_inode(inode, sync);