Merge tag 'v3.8' of /home/kaber/src/repos/linux

Linux 3.8

Signed-off-by: Patrick McHardy <kaber@trash.net>

Conflicts:
	include/linux/Kbuild
	include/linux/netlink.h

63 files changed, 6176 insertions, 3980 deletions

diff --git a/fs/nfs/Kconfig b/fs/nfs/Kconfig
index f90f4f5cd42..13ca196385f 100644
--- a/fs/nfs/Kconfig
+++ b/fs/nfs/Kconfig
@@ -30,7 +30,7 @@ config NFS_FS
 	  If unsure, say N.
 
 config NFS_V2
-	bool "NFS client support for NFS version 2"
+	tristate "NFS client support for NFS version 2"
 	depends on NFS_FS
 	default y
 	help
@@ -40,7 +40,7 @@ config NFS_V2
 	  If unsure, say Y.
 
 config NFS_V3
-	bool "NFS client support for NFS version 3"
+	tristate "NFS client support for NFS version 3"
 	depends on NFS_FS
 	default y
 	help
@@ -72,7 +72,7 @@ config NFS_V3_ACL
 	  If unsure, say N.
 
 config NFS_V4
-	bool "NFS client support for NFS version 4"
+	tristate "NFS client support for NFS version 4"
 	depends on NFS_FS
 	select SUNRPC_GSS
 	select KEYS
@@ -86,11 +86,18 @@ config NFS_V4
 
 	  If unsure, say Y.
 
+config NFS_SWAP
+	bool "Provide swap over NFS support"
+	default n
+	depends on NFS_FS
+	select SUNRPC_SWAP
+	help
+	  This option enables swapon to work on files located on NFS mounts.
+
 config NFS_V4_1
-	bool "NFS client support for NFSv4.1 (EXPERIMENTAL)"
-	depends on NFS_FS && NFS_V4 && EXPERIMENTAL
+	bool "NFS client support for NFSv4.1"
+	depends on NFS_V4
 	select SUNRPC_BACKCHANNEL
-	select PNFS_FILE_LAYOUT
 	help
 	  This option enables support for minor version 1 of the NFSv4 protocol
 	  (RFC 5661) in the kernel's NFS client.
@@ -99,15 +106,17 @@ config NFS_V4_1
 
 config PNFS_FILE_LAYOUT
 	tristate
+	depends on NFS_V4_1
+	default m
 
 config PNFS_BLOCK
 	tristate
-	depends on NFS_FS && NFS_V4_1 && BLK_DEV_DM
+	depends on NFS_V4_1 && BLK_DEV_DM
 	default m
 
 config PNFS_OBJLAYOUT
 	tristate
-	depends on NFS_FS && NFS_V4_1 && SCSI_OSD_ULD
+	depends on NFS_V4_1 && SCSI_OSD_ULD
 	default m
 
 config NFS_V4_1_IMPLEMENTATION_ID_DOMAIN
diff --git a/fs/nfs/Makefile b/fs/nfs/Makefile
index 7ddd45d9f17..cce2c057bd2 100644
--- a/fs/nfs/Makefile
+++ b/fs/nfs/Makefile
@@ -9,17 +9,23 @@ nfs-y 			:= client.o dir.o file.o getroot.o inode.o super.o \
 			   write.o namespace.o mount_clnt.o \
 			   dns_resolve.o cache_lib.o
 nfs-$(CONFIG_ROOT_NFS)	+= nfsroot.o
-nfs-$(CONFIG_NFS_V2)	+= proc.o nfs2xdr.o
-nfs-$(CONFIG_NFS_V3)	+= nfs3proc.o nfs3xdr.o
-nfs-$(CONFIG_NFS_V3_ACL)	+= nfs3acl.o
-nfs-$(CONFIG_NFS_V4)	+= nfs4proc.o nfs4xdr.o nfs4state.o nfs4renewd.o \
-			   delegation.o idmap.o \
-			   callback.o callback_xdr.o callback_proc.o \
-			   nfs4namespace.o
-nfs-$(CONFIG_NFS_V4_1)	+= pnfs.o pnfs_dev.o
-nfs-$(CONFIG_SYSCTL) += sysctl.o
+nfs-$(CONFIG_SYSCTL)	+= sysctl.o
 nfs-$(CONFIG_NFS_FSCACHE) += fscache.o fscache-index.o
 
+obj-$(CONFIG_NFS_V2) += nfsv2.o
+nfsv2-y := nfs2super.o proc.o nfs2xdr.o
+
+obj-$(CONFIG_NFS_V3) += nfsv3.o
+nfsv3-y := nfs3super.o nfs3client.o nfs3proc.o nfs3xdr.o
+nfsv3-$(CONFIG_NFS_V3_ACL) += nfs3acl.o
+
+obj-$(CONFIG_NFS_V4) += nfsv4.o
+nfsv4-y := nfs4proc.o nfs4xdr.o nfs4state.o nfs4renewd.o nfs4super.o nfs4file.o \
+	  delegation.o idmap.o callback.o callback_xdr.o callback_proc.o \
+	  nfs4namespace.o nfs4getroot.o nfs4client.o
+nfsv4-$(CONFIG_SYSCTL)	+= nfs4sysctl.o
+nfsv4-$(CONFIG_NFS_V4_1)	+= nfs4session.o pnfs.o pnfs_dev.o
+
 obj-$(CONFIG_PNFS_FILE_LAYOUT) += nfs_layout_nfsv41_files.o
 nfs_layout_nfsv41_files-y := nfs4filelayout.o nfs4filelayoutdev.o
 
diff --git a/fs/nfs/blocklayout/blocklayout.c b/fs/nfs/blocklayout/blocklayout.c
index 7ae8a608956..4fa788c93f4 100644
--- a/fs/nfs/blocklayout/blocklayout.c
+++ b/fs/nfs/blocklayout/blocklayout.c
@@ -37,8 +37,10 @@
 #include <linux/bio.h>		/* struct bio */
 #include <linux/buffer_head.h>	/* various write calls */
 #include <linux/prefetch.h>
+#include <linux/pagevec.h>
 
 #include "../pnfs.h"
+#include "../nfs4session.h"
 #include "../internal.h"
 #include "blocklayout.h"
 
@@ -162,25 +164,39 @@ static struct bio *bl_alloc_init_bio(int npg, sector_t isect,
 	return bio;
 }
 
-static struct bio *bl_add_page_to_bio(struct bio *bio, int npg, int rw,
+static struct bio *do_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)
+				      struct parallel_io *par,
+				      unsigned int offset, int len)
 {
+	isect = isect + (offset >> SECTOR_SHIFT);
+	dprintk("%s: npg %d rw %d isect %llu offset %u len %d\n", __func__,
+		npg, rw, (unsigned long long)isect, offset, len);
 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) {
+	if (bio_add_page(bio, page, len, offset) < len) {
 		bio = bl_submit_bio(rw, bio);
 		goto retry;
 	}
 	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)
+{
+	return do_add_page_to_bio(bio, npg, rw, isect, page, be,
+				  end_io, par, 0, PAGE_CACHE_SIZE);
+}
+
 /* This is basically copied from mpage_end_io_read */
 static void bl_end_io_read(struct bio *bio, int err)
 {
@@ -238,8 +254,11 @@ bl_read_pagelist(struct nfs_read_data *rdata)
 	sector_t isect, extent_length = 0;
 	struct parallel_io *par;
 	loff_t f_offset = rdata->args.offset;
+	size_t bytes_left = rdata->args.count;
+	unsigned int pg_offset, pg_len;
 	struct page **pages = rdata->args.pages;
 	int pg_index = rdata->args.pgbase >> PAGE_CACHE_SHIFT;
+	const bool is_dio = (header->dreq != NULL);
 
 	dprintk("%s enter nr_pages %u offset %lld count %u\n", __func__,
 	       rdata->pages.npages, f_offset, (unsigned int)rdata->args.count);
@@ -273,36 +292,53 @@ bl_read_pagelist(struct nfs_read_data *rdata)
 				extent_length = min(extent_length, cow_length);
 			}
 		}
+
+		if (is_dio) {
+			pg_offset = f_offset & ~PAGE_CACHE_MASK;
+			if (pg_offset + bytes_left > PAGE_CACHE_SIZE)
+				pg_len = PAGE_CACHE_SIZE - pg_offset;
+			else
+				pg_len = bytes_left;
+
+			f_offset += pg_len;
+			bytes_left -= pg_len;
+			isect += (pg_offset >> SECTOR_SHIFT);
+		} else {
+			pg_offset = 0;
+			pg_len = PAGE_CACHE_SIZE;
+		}
+
 		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);
+			zero_user_segment(pages[i], pg_offset, pg_len);
 			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->pages.npages - i,
+			bio = do_add_page_to_bio(bio, rdata->pages.npages - i,
 						 READ,
 						 isect, pages[i], be_read,
-						 bl_end_io_read, par);
+						 bl_end_io_read, par,
+						 pg_offset, pg_len);
 			if (IS_ERR(bio)) {
 				header->pnfs_error = PTR_ERR(bio);
 				bio = NULL;
 				goto out;
 			}
 		}
-		isect += PAGE_CACHE_SECTORS;
+		isect += (pg_len >> SECTOR_SHIFT);
 		extent_length -= PAGE_CACHE_SECTORS;
 	}
 	if ((isect << SECTOR_SHIFT) >= header->inode->i_size) {
 		rdata->res.eof = 1;
-		rdata->res.count = header->inode->i_size - f_offset;
+		rdata->res.count = header->inode->i_size - rdata->args.offset;
 	} else {
-		rdata->res.count = (isect << SECTOR_SHIFT) - f_offset;
+		rdata->res.count = (isect << SECTOR_SHIFT) - rdata->args.offset;
 	}
 out:
 	bl_put_extent(be);
@@ -450,6 +486,106 @@ map_block(struct buffer_head *bh, sector_t isect, struct pnfs_block_extent *be)
 	return;
 }
 
+static void
+bl_read_single_end_io(struct bio *bio, int error)
+{
+	struct bio_vec *bvec = bio->bi_io_vec + bio->bi_vcnt - 1;
+	struct page *page = bvec->bv_page;
+
+	/* Only one page in bvec */
+	unlock_page(page);
+}
+
+static int
+bl_do_readpage_sync(struct page *page, struct pnfs_block_extent *be,
+		    unsigned int offset, unsigned int len)
+{
+	struct bio *bio;
+	struct page *shadow_page;
+	sector_t isect;
+	char *kaddr, *kshadow_addr;
+	int ret = 0;
+
+	dprintk("%s: offset %u len %u\n", __func__, offset, len);
+
+	shadow_page = alloc_page(GFP_NOFS | __GFP_HIGHMEM);
+	if (shadow_page == NULL)
+		return -ENOMEM;
+
+	bio = bio_alloc(GFP_NOIO, 1);
+	if (bio == NULL)
+		return -ENOMEM;
+
+	isect = (page->index << PAGE_CACHE_SECTOR_SHIFT) +
+		(offset / SECTOR_SIZE);
+
+	bio->bi_sector = isect - be->be_f_offset + be->be_v_offset;
+	bio->bi_bdev = be->be_mdev;
+	bio->bi_end_io = bl_read_single_end_io;
+
+	lock_page(shadow_page);
+	if (bio_add_page(bio, shadow_page,
+			 SECTOR_SIZE, round_down(offset, SECTOR_SIZE)) == 0) {
+		unlock_page(shadow_page);
+		bio_put(bio);
+		return -EIO;
+	}
+
+	submit_bio(READ, bio);
+	wait_on_page_locked(shadow_page);
+	if (unlikely(!test_bit(BIO_UPTODATE, &bio->bi_flags))) {
+		ret = -EIO;
+	} else {
+		kaddr = kmap_atomic(page);
+		kshadow_addr = kmap_atomic(shadow_page);
+		memcpy(kaddr + offset, kshadow_addr + offset, len);
+		kunmap_atomic(kshadow_addr);
+		kunmap_atomic(kaddr);
+	}
+	__free_page(shadow_page);
+	bio_put(bio);
+
+	return ret;
+}
+
+static int
+bl_read_partial_page_sync(struct page *page, struct pnfs_block_extent *be,
+			  unsigned int dirty_offset, unsigned int dirty_len,
+			  bool full_page)
+{
+	int ret = 0;
+	unsigned int start, end;
+
+	if (full_page) {
+		start = 0;
+		end = PAGE_CACHE_SIZE;
+	} else {
+		start = round_down(dirty_offset, SECTOR_SIZE);
+		end = round_up(dirty_offset + dirty_len, SECTOR_SIZE);
+	}
+
+	dprintk("%s: offset %u len %d\n", __func__, dirty_offset, dirty_len);
+	if (!be) {
+		zero_user_segments(page, start, dirty_offset,
+				   dirty_offset + dirty_len, end);
+		if (start == 0 && end == PAGE_CACHE_SIZE &&
+		    trylock_page(page)) {
+			SetPageUptodate(page);
+			unlock_page(page);
+		}
+		return ret;
+	}
+
+	if (start != dirty_offset)
+		ret = bl_do_readpage_sync(page, be, start, dirty_offset - start);
+
+	if (!ret && (dirty_offset + dirty_len < end))
+		ret = bl_do_readpage_sync(page, be, dirty_offset + dirty_len,
+					  end - dirty_offset - dirty_len);
+
+	return ret;
+}
+
 /* Given an unmapped page, zero it or read in page for COW, page is locked
  * by caller.
  */
@@ -483,7 +619,6 @@ init_page_for_write(struct page *page, struct pnfs_block_extent *cow_read)
 	SetPageUptodate(page);
 
 cleanup:
-	bl_put_extent(cow_read);
 	if (bh)
 		free_buffer_head(bh);
 	if (ret) {
@@ -552,9 +687,10 @@ bl_write_pagelist(struct nfs_write_data *wdata, int sync)
 	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;
+	struct parallel_io *par = NULL;
 	loff_t offset = wdata->args.offset;
 	size_t count = wdata->args.count;
+	unsigned int pg_offset, pg_len, saved_len;
 	struct page **pages = wdata->args.pages;
 	struct page *page;
 	pgoff_t index;
@@ -563,6 +699,13 @@ bl_write_pagelist(struct nfs_write_data *wdata, int sync)
 	    NFS_SERVER(header->inode)->pnfs_blksize >> PAGE_CACHE_SHIFT;
 
 	dprintk("%s enter, %Zu@%lld\n", __func__, count, offset);
+
+	if (header->dreq != NULL &&
+	    (!IS_ALIGNED(offset, NFS_SERVER(header->inode)->pnfs_blksize) ||
+	     !IS_ALIGNED(count, NFS_SERVER(header->inode)->pnfs_blksize))) {
+		dprintk("pnfsblock nonblock aligned DIO writes. Resend MDS\n");
+		goto out_mds;
+	}
 	/* 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.
@@ -659,10 +802,11 @@ next_page:
 		if (!extent_length) {
 			/* We've used up the previous extent */
 			bl_put_extent(be);
+			bl_put_extent(cow_read);
 			bio = bl_submit_bio(WRITE, bio);
 			/* Get the next one */
 			be = bl_find_get_extent(BLK_LSEG2EXT(header->lseg),
-					     isect, NULL);
+					     isect, &cow_read);
 			if (!be || !is_writable(be, isect)) {
 				header->pnfs_error = -EINVAL;
 				goto out;
@@ -679,7 +823,26 @@ next_page:
 			extent_length = be->be_length -
 			    (isect - be->be_f_offset);
 		}
-		if (be->be_state == PNFS_BLOCK_INVALID_DATA) {
+
+		dprintk("%s offset %lld count %Zu\n", __func__, offset, count);
+		pg_offset = offset & ~PAGE_CACHE_MASK;
+		if (pg_offset + count > PAGE_CACHE_SIZE)
+			pg_len = PAGE_CACHE_SIZE - pg_offset;
+		else
+			pg_len = count;
+
+		saved_len = pg_len;
+		if (be->be_state == PNFS_BLOCK_INVALID_DATA &&
+		    !bl_is_sector_init(be->be_inval, isect)) {
+			ret = bl_read_partial_page_sync(pages[i], cow_read,
+							pg_offset, pg_len, true);
+			if (ret) {
+				dprintk("%s bl_read_partial_page_sync fail %d\n",
+					__func__, ret);
+				header->pnfs_error = ret;
+				goto out;
+			}
+
 			ret = bl_mark_sectors_init(be->be_inval, isect,
 						       PAGE_CACHE_SECTORS);
 			if (unlikely(ret)) {
@@ -688,15 +851,35 @@ next_page:
 				header->pnfs_error = ret;
 				goto out;
 			}
+
+			/* Expand to full page write */
+			pg_offset = 0;
+			pg_len = PAGE_CACHE_SIZE;
+		} else if  ((pg_offset & (SECTOR_SIZE - 1)) ||
+			    (pg_len & (SECTOR_SIZE - 1))){
+			/* ahh, nasty case. We have to do sync full sector
+			 * read-modify-write cycles.
+			 */
+			unsigned int saved_offset = pg_offset;
+			ret = bl_read_partial_page_sync(pages[i], be, pg_offset,
+							pg_len, false);
+			pg_offset = round_down(pg_offset, SECTOR_SIZE);
+			pg_len = round_up(saved_offset + pg_len, SECTOR_SIZE)
+				 - pg_offset;
 		}
-		bio = bl_add_page_to_bio(bio, wdata->pages.npages - i, WRITE,
+
+
+		bio = do_add_page_to_bio(bio, wdata->pages.npages - i, WRITE,
 					 isect, pages[i], be,
-					 bl_end_io_write, par);
+					 bl_end_io_write, par,
+					 pg_offset, pg_len);
 		if (IS_ERR(bio)) {
 			header->pnfs_error = PTR_ERR(bio);
 			bio = NULL;
 			goto out;
 		}
+		offset += saved_len;
+		count -= saved_len;
 		isect += PAGE_CACHE_SECTORS;
 		last_isect = isect;
 		extent_length -= PAGE_CACHE_SECTORS;
@@ -714,17 +897,16 @@ next_page:
 	}
 
 write_done:
-	wdata->res.count = (last_isect << SECTOR_SHIFT) - (offset);
-	if (count < wdata->res.count) {
-		wdata->res.count = count;
-	}
+	wdata->res.count = wdata->args.count;
 out:
 	bl_put_extent(be);
+	bl_put_extent(cow_read);
 	bl_submit_bio(WRITE, bio);
 	put_parallel(par);
 	return PNFS_ATTEMPTED;
 out_mds:
 	bl_put_extent(be);
+	bl_put_extent(cow_read);
 	kfree(par);
 	return PNFS_NOT_ATTEMPTED;
 }
@@ -859,7 +1041,7 @@ static void free_blk_mountid(struct block_mount_id *mid)
 	}
 }
 
-/* This is mostly copied from the filelayout's get_device_info function.
+/* This is mostly copied from the filelayout_get_device_info function.
  * It seems much of this should be at the generic pnfs level.
  */
 static struct pnfs_block_dev *
@@ -996,15 +1178,95 @@ bl_clear_layoutdriver(struct nfs_server *server)
 	return 0;
 }
 
+static bool
+is_aligned_req(struct nfs_page *req, unsigned int alignment)
+{
+	return IS_ALIGNED(req->wb_offset, alignment) &&
+	       IS_ALIGNED(req->wb_bytes, alignment);
+}
+
+static void
+bl_pg_init_read(struct nfs_pageio_descriptor *pgio, struct nfs_page *req)
+{
+	if (pgio->pg_dreq != NULL &&
+	    !is_aligned_req(req, SECTOR_SIZE))
+		nfs_pageio_reset_read_mds(pgio);
+	else
+		pnfs_generic_pg_init_read(pgio, req);
+}
+
+static bool
+bl_pg_test_read(struct nfs_pageio_descriptor *pgio, struct nfs_page *prev,
+		struct nfs_page *req)
+{
+	if (pgio->pg_dreq != NULL &&
+	    !is_aligned_req(req, SECTOR_SIZE))
+		return false;
+
+	return pnfs_generic_pg_test(pgio, prev, req);
+}
+
+/*
+ * Return the number of contiguous bytes for a given inode
+ * starting at page frame idx.
+ */
+static u64 pnfs_num_cont_bytes(struct inode *inode, pgoff_t idx)
+{
+	struct address_space *mapping = inode->i_mapping;
+	pgoff_t end;
+
+	/* Optimize common case that writes from 0 to end of file */
+	end = DIV_ROUND_UP(i_size_read(inode), PAGE_CACHE_SIZE);
+	if (end != NFS_I(inode)->npages) {
+		rcu_read_lock();
+		end = radix_tree_next_hole(&mapping->page_tree, idx + 1, ULONG_MAX);
+		rcu_read_unlock();
+	}
+
+	if (!end)
+		return i_size_read(inode) - (idx << PAGE_CACHE_SHIFT);
+	else
+		return (end - idx) << PAGE_CACHE_SHIFT;
+}
+
+static void
+bl_pg_init_write(struct nfs_pageio_descriptor *pgio, struct nfs_page *req)
+{
+	if (pgio->pg_dreq != NULL &&
+	    !is_aligned_req(req, PAGE_CACHE_SIZE)) {
+		nfs_pageio_reset_write_mds(pgio);
+	} else {
+		u64 wb_size;
+		if (pgio->pg_dreq == NULL)
+			wb_size = pnfs_num_cont_bytes(pgio->pg_inode,
+						      req->wb_index);
+		else
+			wb_size = nfs_dreq_bytes_left(pgio->pg_dreq);
+
+		pnfs_generic_pg_init_write(pgio, req, wb_size);
+	}
+}
+
+static bool
+bl_pg_test_write(struct nfs_pageio_descriptor *pgio, struct nfs_page *prev,
+		 struct nfs_page *req)
+{
+	if (pgio->pg_dreq != NULL &&
+	    !is_aligned_req(req, PAGE_CACHE_SIZE))
+		return false;
+
+	return pnfs_generic_pg_test(pgio, prev, req);
+}
+
 static const struct nfs_pageio_ops bl_pg_read_ops = {
-	.pg_init = pnfs_generic_pg_init_read,
-	.pg_test = pnfs_generic_pg_test,
+	.pg_init = bl_pg_init_read,
+	.pg_test = bl_pg_test_read,
 	.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_init = bl_pg_init_write,
+	.pg_test = bl_pg_test_write,
 	.pg_doio = pnfs_generic_pg_writepages,
 };
 
diff --git a/fs/nfs/blocklayout/blocklayout.h b/fs/nfs/blocklayout/blocklayout.h
index 03350690118..f4891bde885 100644
--- a/fs/nfs/blocklayout/blocklayout.h
+++ b/fs/nfs/blocklayout/blocklayout.h
@@ -41,6 +41,7 @@
 
 #define PAGE_CACHE_SECTORS (PAGE_CACHE_SIZE >> SECTOR_SHIFT)
 #define PAGE_CACHE_SECTOR_SHIFT (PAGE_CACHE_SHIFT - SECTOR_SHIFT)
+#define SECTOR_SIZE (1 << SECTOR_SHIFT)
 
 struct block_mount_id {
 	spinlock_t			bm_lock;    /* protects list */
@@ -172,7 +173,6 @@ struct bl_msg_hdr {
 /* blocklayoutdev.c */
 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);
diff --git a/fs/nfs/blocklayout/blocklayoutdev.c b/fs/nfs/blocklayout/blocklayoutdev.c
index c96554245cc..a86c5bdad9e 100644
--- a/fs/nfs/blocklayout/blocklayoutdev.c
+++ b/fs/nfs/blocklayout/blocklayoutdev.c
@@ -53,22 +53,6 @@ static int decode_sector_number(__be32 **rp, sector_t *sp)
 	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
  */
@@ -172,11 +156,12 @@ nfs4_blk_decode_device(struct nfs_server *server,
 		goto out;
 	}
 
-	bd = nfs4_blkdev_get(MKDEV(reply->major, reply->minor));
+	bd = blkdev_get_by_dev(MKDEV(reply->major, reply->minor),
+			       FMODE_READ, NULL);
 	if (IS_ERR(bd)) {
-		rc = PTR_ERR(bd);
-		dprintk("%s failed to open device : %d\n", __func__, rc);
-		rv = ERR_PTR(rc);
+		dprintk("%s failed to open device : %ld\n", __func__,
+			PTR_ERR(bd));
+		rv = ERR_CAST(bd);
 		goto out;
 	}
 
diff --git a/fs/nfs/blocklayout/extents.c b/fs/nfs/blocklayout/extents.c
index 1f9a6032796..9c3e117c3ed 100644
--- a/fs/nfs/blocklayout/extents.c
+++ b/fs/nfs/blocklayout/extents.c
@@ -683,8 +683,7 @@ encode_pnfs_block_layoutupdate(struct pnfs_block_layout *bl,
 		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);
+		list_move_tail(&lce->bse_node, &bl->bl_committing);
 		bl->bl_count--;
 		count++;
 	}
diff --git a/fs/nfs/cache_lib.c b/fs/nfs/cache_lib.c
index dded2636811..862a2f16db6 100644
--- a/fs/nfs/cache_lib.c
+++ b/fs/nfs/cache_lib.c
@@ -118,7 +118,6 @@ int nfs_cache_register_sb(struct super_block *sb, struct cache_detail *cd)
 	struct dentry *dir;
 
 	dir = rpc_d_lookup_sb(sb, "cache");
-	BUG_ON(dir == NULL);
 	ret = sunrpc_cache_register_pipefs(dir, cd->name, 0600, cd);
 	dput(dir);
 	return ret;
diff --git a/fs/nfs/callback.c b/fs/nfs/callback.c
index 23ff18fe080..5088b57b078 100644
--- a/fs/nfs/callback.c
+++ b/fs/nfs/callback.c
@@ -12,6 +12,7 @@
 #include <linux/sunrpc/svc.h>
 #include <linux/sunrpc/svcsock.h>
 #include <linux/nfs_fs.h>
+#include <linux/errno.h>
 #include <linux/mutex.h>
 #include <linux/freezer.h>
 #include <linux/kthread.h>
@@ -23,6 +24,7 @@
 #include "nfs4_fs.h"
 #include "callback.h"
 #include "internal.h"
+#include "netns.h"
 
 #define NFSDBG_FACILITY NFSDBG_CALLBACK
 
@@ -37,31 +39,32 @@ static struct nfs_callback_data nfs_callback_info[NFS4_MAX_MINOR_VERSION + 1];
 static DEFINE_MUTEX(nfs_callback_mutex);
 static struct svc_program nfs4_callback_program;
 
-unsigned int nfs_callback_set_tcpport;
-unsigned short nfs_callback_tcpport;
-unsigned short nfs_callback_tcpport6;
-#define NFS_CALLBACK_MAXPORTNR (65535U)
-
-static int param_set_portnr(const char *val, const struct kernel_param *kp)
+static int nfs4_callback_up_net(struct svc_serv *serv, struct net *net)
 {
-	unsigned long num;
 	int ret;
+	struct nfs_net *nn = net_generic(net, nfs_net_id);
+
+	ret = svc_create_xprt(serv, "tcp", net, PF_INET,
+				nfs_callback_set_tcpport, SVC_SOCK_ANONYMOUS);
+	if (ret <= 0)
+		goto out_err;
+	nn->nfs_callback_tcpport = ret;
+	dprintk("NFS: Callback listener port = %u (af %u, net %p)\n",
+			nn->nfs_callback_tcpport, PF_INET, net);
 
-	if (!val)
-		return -EINVAL;
-	ret = strict_strtoul(val, 0, &num);
-	if (ret == -EINVAL || num > NFS_CALLBACK_MAXPORTNR)
-		return -EINVAL;
-	*((unsigned int *)kp->arg) = num;
+	ret = svc_create_xprt(serv, "tcp", net, PF_INET6,
+				nfs_callback_set_tcpport, SVC_SOCK_ANONYMOUS);
+	if (ret > 0) {
+		nn->nfs_callback_tcpport6 = ret;
+		dprintk("NFS: Callback listener port = %u (af %u, net %p)\n",
+				nn->nfs_callback_tcpport6, PF_INET6, net);
+	} else if (ret != -EAFNOSUPPORT)
+		goto out_err;
 	return 0;
-}
-static struct kernel_param_ops param_ops_portnr = {
-	.set = param_set_portnr,
-	.get = param_get_uint,
-};
-#define param_check_portnr(name, p) __param_check(name, p, unsigned int);
 
-module_param_named(callback_tcpport, nfs_callback_set_tcpport, portnr, 0644);
+out_err:
+	return (ret) ? ret : -ENOMEM;
+}
 
 /*
  * This is the NFSv4 callback kernel thread.
@@ -69,7 +72,7 @@ module_param_named(callback_tcpport, nfs_callback_set_tcpport, portnr, 0644);
 static int
 nfs4_callback_svc(void *vrqstp)
 {
-	int err, preverr = 0;
+	int err;
 	struct svc_rqst *rqstp = vrqstp;
 
 	set_freezable();
@@ -79,20 +82,8 @@ nfs4_callback_svc(void *vrqstp)
 		 * Listen for a request on the socket
 		 */
 		err = svc_recv(rqstp, MAX_SCHEDULE_TIMEOUT);
-		if (err == -EAGAIN || err == -EINTR) {
-			preverr = err;
-			continue;
-		}
-		if (err < 0) {
-			if (err != preverr) {
-				printk(KERN_WARNING "NFS: %s: unexpected error "
-					"from svc_recv (%d)\n", __func__, err);
-				preverr = err;
-			}
-			schedule_timeout_uninterruptible(HZ);
+		if (err == -EAGAIN || err == -EINTR)
 			continue;
-		}
-		preverr = err;
 		svc_process(rqstp);
 	}
 	return 0;
@@ -102,38 +93,23 @@ nfs4_callback_svc(void *vrqstp)
  * Prepare to bring up the NFSv4 callback service
  */
 static struct svc_rqst *
-nfs4_callback_up(struct svc_serv *serv, struct rpc_xprt *xprt)
+nfs4_callback_up(struct svc_serv *serv)
 {
-	int ret;
-
-	ret = svc_create_xprt(serv, "tcp", &init_net, PF_INET,
-				nfs_callback_set_tcpport, SVC_SOCK_ANONYMOUS);
-	if (ret <= 0)
-		goto out_err;
-	nfs_callback_tcpport = ret;
-	dprintk("NFS: Callback listener port = %u (af %u)\n",
-			nfs_callback_tcpport, PF_INET);
-
-	ret = svc_create_xprt(serv, "tcp", &init_net, PF_INET6,
-				nfs_callback_set_tcpport, SVC_SOCK_ANONYMOUS);
-	if (ret > 0) {
-		nfs_callback_tcpport6 = ret;
-		dprintk("NFS: Callback listener port = %u (af %u)\n",
-				nfs_callback_tcpport6, PF_INET6);
-	} else if (ret == -EAFNOSUPPORT)
-		ret = 0;
-	else
-		goto out_err;
-
 	return svc_prepare_thread(serv, &serv->sv_pools[0], NUMA_NO_NODE);
-
-out_err:
-	if (ret == 0)
-		ret = -ENOMEM;
-	return ERR_PTR(ret);
 }
 
 #if defined(CONFIG_NFS_V4_1)
+static int nfs41_callback_up_net(struct svc_serv *serv, struct net *net)
+{
+	/*
+	 * Create an svc_sock for the back channel service that shares the
+	 * fore channel connection.
+	 * Returns the input port (0) and sets the svc_serv bc_xprt on success
+	 */
+	return svc_create_xprt(serv, "tcp-bc", net, PF_INET, 0,
+			      SVC_SOCK_ANONYMOUS);
+}
+
 /*
  * The callback service for NFSv4.1 callbacks
  */
@@ -173,28 +149,9 @@ nfs41_callback_svc(void *vrqstp)
  * Bring up the NFSv4.1 callback service
  */
 static struct svc_rqst *
-nfs41_callback_up(struct svc_serv *serv, struct rpc_xprt *xprt)
+nfs41_callback_up(struct svc_serv *serv)
 {
 	struct svc_rqst *rqstp;
-	int ret;
-
-	/*
-	 * Create an svc_sock for the back channel service that shares the
-	 * fore channel connection.
-	 * Returns the input port (0) and sets the svc_serv bc_xprt on success
-	 */
-	ret = svc_create_xprt(serv, "tcp-bc", &init_net, PF_INET, 0,
-			      SVC_SOCK_ANONYMOUS);
-	if (ret < 0) {
-		rqstp = ERR_PTR(ret);
-		goto out;
-	}
-
-	/*
-	 * Save the svc_serv in the transport so that it can
-	 * be referenced when the session backchannel is initialized
-	 */
-	xprt->bc_serv = serv;
 
 	INIT_LIST_HEAD(&serv->sv_cb_list);
 	spin_lock_init(&serv->sv_cb_lock);
@@ -204,86 +161,74 @@ nfs41_callback_up(struct svc_serv *serv, struct rpc_xprt *xprt)
 		svc_xprt_put(serv->sv_bc_xprt);
 		serv->sv_bc_xprt = NULL;
 	}
-out:
 	dprintk("--> %s return %ld\n", __func__,
 		IS_ERR(rqstp) ? PTR_ERR(rqstp) : 0);
 	return rqstp;
 }
 
-static inline int nfs_minorversion_callback_svc_setup(u32 minorversion,
-		struct svc_serv *serv, struct rpc_xprt *xprt,
+static void nfs_minorversion_callback_svc_setup(struct svc_serv *serv,
 		struct svc_rqst **rqstpp, int (**callback_svc)(void *vrqstp))
 {
-	if (minorversion) {
-		*rqstpp = nfs41_callback_up(serv, xprt);
-		*callback_svc = nfs41_callback_svc;
-	}
-	return minorversion;
+	*rqstpp = nfs41_callback_up(serv);
+	*callback_svc = nfs41_callback_svc;
 }
 
 static inline void nfs_callback_bc_serv(u32 minorversion, struct rpc_xprt *xprt,
-		struct nfs_callback_data *cb_info)
+		struct svc_serv *serv)
 {
 	if (minorversion)
-		xprt->bc_serv = cb_info->serv;
+		/*
+		 * Save the svc_serv in the transport so that it can
+		 * be referenced when the session backchannel is initialized
+		 */
+		xprt->bc_serv = serv;
 }
 #else
-static inline int nfs_minorversion_callback_svc_setup(u32 minorversion,
-		struct svc_serv *serv, struct rpc_xprt *xprt,
-		struct svc_rqst **rqstpp, int (**callback_svc)(void *vrqstp))
+static int nfs41_callback_up_net(struct svc_serv *serv, struct net *net)
 {
 	return 0;
 }
 
+static void nfs_minorversion_callback_svc_setup(struct svc_serv *serv,
+		struct svc_rqst **rqstpp, int (**callback_svc)(void *vrqstp))
+{
+	*rqstpp = ERR_PTR(-ENOTSUPP);
+	*callback_svc = ERR_PTR(-ENOTSUPP);
+}
+
 static inline void nfs_callback_bc_serv(u32 minorversion, struct rpc_xprt *xprt,
-		struct nfs_callback_data *cb_info)
+		struct svc_serv *serv)
 {
 }
 #endif /* CONFIG_NFS_V4_1 */
 
-/*
- * Bring up the callback thread if it is not already up.
- */
-int nfs_callback_up(u32 minorversion, struct rpc_xprt *xprt)
+static int nfs_callback_start_svc(int minorversion, struct rpc_xprt *xprt,
+				  struct svc_serv *serv)
 {
-	struct svc_serv *serv = NULL;
 	struct svc_rqst *rqstp;
 	int (*callback_svc)(void *vrqstp);
 	struct nfs_callback_data *cb_info = &nfs_callback_info[minorversion];
 	char svc_name[12];
-	int ret = 0;
-	int minorversion_setup;
-	struct net *net = &init_net;
+	int ret;
 
-	mutex_lock(&nfs_callback_mutex);
-	if (cb_info->users++ || cb_info->task != NULL) {
-		nfs_callback_bc_serv(minorversion, xprt, cb_info);
-		goto out;
-	}
-	serv = svc_create(&nfs4_callback_program, NFS4_CALLBACK_BUFSIZE, NULL);
-	if (!serv) {
-		ret = -ENOMEM;
-		goto out_err;
-	}
+	nfs_callback_bc_serv(minorversion, xprt, serv);
 
-	ret = svc_bind(serv, net);
-	if (ret < 0) {
-		printk(KERN_WARNING "NFS: bind callback service failed\n");
-		goto out_err;
-	}
+	if (cb_info->task)
+		return 0;
 
-	minorversion_setup =  nfs_minorversion_callback_svc_setup(minorversion,
-					serv, xprt, &rqstp, &callback_svc);
-	if (!minorversion_setup) {
+	switch (minorversion) {
+	case 0:
 		/* v4.0 callback setup */
-		rqstp = nfs4_callback_up(serv, xprt);
+		rqstp = nfs4_callback_up(serv);
 		callback_svc = nfs4_callback_svc;
+		break;
+	default:
+		nfs_minorversion_callback_svc_setup(serv,
+				&rqstp, &callback_svc);
 	}
 
-	if (IS_ERR(rqstp)) {
-		ret = PTR_ERR(rqstp);
-		goto out_err;
-	}
+	if (IS_ERR(rqstp))
+		return PTR_ERR(rqstp);
 
 	svc_sock_update_bufs(serv);
 
@@ -296,41 +241,165 @@ int nfs_callback_up(u32 minorversion, struct rpc_xprt *xprt)
 		svc_exit_thread(cb_info->rqst);
 		cb_info->rqst = NULL;
 		cb_info->task = NULL;
-		goto out_err;
+		return ret;
+	}
+	dprintk("nfs_callback_up: service started\n");
+	return 0;
+}
+
+static void nfs_callback_down_net(u32 minorversion, struct svc_serv *serv, struct net *net)
+{
+	struct nfs_net *nn = net_generic(net, nfs_net_id);
+
+	if (--nn->cb_users[minorversion])
+		return;
+
+	dprintk("NFS: destroy per-net callback data; net=%p\n", net);
+	svc_shutdown_net(serv, net);
+}
+
+static int nfs_callback_up_net(int minorversion, struct svc_serv *serv, struct net *net)
+{
+	struct nfs_net *nn = net_generic(net, nfs_net_id);
+	int ret;
+
+	if (nn->cb_users[minorversion]++)
+		return 0;
+
+	dprintk("NFS: create per-net callback data; net=%p\n", net);
+
+	ret = svc_bind(serv, net);
+	if (ret < 0) {
+		printk(KERN_WARNING "NFS: bind callback service failed\n");
+		goto err_bind;
+	}
+
+	switch (minorversion) {
+		case 0:
+			ret = nfs4_callback_up_net(serv, net);
+			break;
+		case 1:
+			ret = nfs41_callback_up_net(serv, net);
+			break;
+		default:
+			printk(KERN_ERR "NFS: unknown callback version: %d\n",
+					minorversion);
+			ret = -EINVAL;
+			break;
+	}
+
+	if (ret < 0) {
+		printk(KERN_ERR "NFS: callback service start failed\n");
+		goto err_socks;
+	}
+	return 0;
+
+err_socks:
+	svc_rpcb_cleanup(serv, net);
+err_bind:
+	dprintk("NFS: Couldn't create callback socket: err = %d; "
+			"net = %p\n", ret, net);
+	return ret;
+}
+
+static struct svc_serv *nfs_callback_create_svc(int minorversion)
+{
+	struct nfs_callback_data *cb_info = &nfs_callback_info[minorversion];
+	struct svc_serv *serv;
+
+	/*
+	 * Check whether we're already up and running.
+	 */
+	if (cb_info->task) {
+		/*
+		 * Note: increase service usage, because later in case of error
+		 * svc_destroy() will be called.
+		 */
+		svc_get(cb_info->serv);
+		return cb_info->serv;
+	}
+
+	/*
+	 * Sanity check: if there's no task,
+	 * we should be the first user ...
+	 */
+	if (cb_info->users)
+		printk(KERN_WARNING "nfs_callback_create_svc: no kthread, %d users??\n",
+			cb_info->users);
+
+	serv = svc_create(&nfs4_callback_program, NFS4_CALLBACK_BUFSIZE, NULL);
+	if (!serv) {
+		printk(KERN_ERR "nfs_callback_create_svc: create service failed\n");
+		return ERR_PTR(-ENOMEM);
+	}
+	/* As there is only one thread we need to over-ride the
+	 * default maximum of 80 connections
+	 */
+	serv->sv_maxconn = 1024;
+	dprintk("nfs_callback_create_svc: service created\n");
+	return serv;
+}
+
+/*
+ * Bring up the callback thread if it is not already up.
+ */
+int nfs_callback_up(u32 minorversion, struct rpc_xprt *xprt)
+{
+	struct svc_serv *serv;
+	struct nfs_callback_data *cb_info = &nfs_callback_info[minorversion];
+	int ret;
+	struct net *net = xprt->xprt_net;
+
+	mutex_lock(&nfs_callback_mutex);
+
+	serv = nfs_callback_create_svc(minorversion);
+	if (IS_ERR(serv)) {
+		ret = PTR_ERR(serv);
+		goto err_create;
 	}
-out:
+
+	ret = nfs_callback_up_net(minorversion, serv, net);
+	if (ret < 0)
+		goto err_net;
+
+	ret = nfs_callback_start_svc(minorversion, xprt, serv);
+	if (ret < 0)
+		goto err_start;
+
+	cb_info->users++;
 	/*
 	 * svc_create creates the svc_serv with sv_nrthreads == 1, and then
 	 * svc_prepare_thread increments that. So we need to call svc_destroy
 	 * on both success and failure so that the refcount is 1 when the
 	 * thread exits.
 	 */
-	if (serv)
-		svc_destroy(serv);
+err_net:
+	svc_destroy(serv);
+err_create:
 	mutex_unlock(&nfs_callback_mutex);
 	return ret;
-out_err:
-	dprintk("NFS: Couldn't create callback socket or server thread; "
-		"err = %d\n", ret);
-	cb_info->users--;
-	if (serv)
-		svc_shutdown_net(serv, net);
-	goto out;
+
+err_start:
+	nfs_callback_down_net(minorversion, serv, net);
+	dprintk("NFS: Couldn't create server thread; err = %d\n", ret);
+	goto err_net;
 }
 
 /*
  * Kill the callback thread if it's no longer being used.
  */
-void nfs_callback_down(int minorversion)
+void nfs_callback_down(int minorversion, struct net *net)
 {
 	struct nfs_callback_data *cb_info = &nfs_callback_info[minorversion];
 
 	mutex_lock(&nfs_callback_mutex);
+	nfs_callback_down_net(minorversion, cb_info->serv, net);
 	cb_info->users--;
 	if (cb_info->users == 0 && cb_info->task != NULL) {
 		kthread_stop(cb_info->task);
-		svc_shutdown_net(cb_info->serv, &init_net);
+		dprintk("nfs_callback_down: service stopped\n");
 		svc_exit_thread(cb_info->rqst);
+		dprintk("nfs_callback_down: service destroyed\n");
 		cb_info->serv = NULL;
 		cb_info->rqst = NULL;
 		cb_info->task = NULL;
diff --git a/fs/nfs/callback.h b/fs/nfs/callback.h
index a5527c90a5a..efd54f0a4c4 100644
--- a/fs/nfs/callback.h
+++ b/fs/nfs/callback.h
@@ -142,7 +142,7 @@ extern __be32 nfs4_callback_recallany(struct cb_recallanyargs *args,
 
 struct cb_recallslotargs {
 	struct sockaddr	*crsa_addr;
-	uint32_t	crsa_target_max_slots;
+	uint32_t	crsa_target_highest_slotid;
 };
 extern __be32 nfs4_callback_recallslot(struct cb_recallslotargs *args,
 					 void *dummy,
@@ -167,8 +167,6 @@ extern __be32 nfs4_callback_layoutrecall(
 	struct cb_layoutrecallargs *args,
 	void *dummy, struct cb_process_state *cps);
 
-extern void nfs4_check_drain_bc_complete(struct nfs4_session *ses);
-
 struct cb_devicenotifyitem {
 	uint32_t		cbd_notify_type;
 	uint32_t		cbd_layout_type;
@@ -192,9 +190,9 @@ extern __be32 nfs4_callback_getattr(struct cb_getattrargs *args,
 				    struct cb_process_state *cps);
 extern __be32 nfs4_callback_recall(struct cb_recallargs *args, void *dummy,
 				   struct cb_process_state *cps);
-#ifdef CONFIG_NFS_V4
+#if IS_ENABLED(CONFIG_NFS_V4)
 extern int nfs_callback_up(u32 minorversion, struct rpc_xprt *xprt);
-extern void nfs_callback_down(int minorversion);
+extern void nfs_callback_down(int minorversion, struct net *net);
 extern int nfs4_validate_delegation_stateid(struct nfs_delegation *delegation,
 					    const nfs4_stateid *stateid);
 extern int nfs4_set_callback_sessionid(struct nfs_client *clp);
@@ -209,6 +207,5 @@ extern int nfs4_set_callback_sessionid(struct nfs_client *clp);
 
 extern unsigned int nfs_callback_set_tcpport;
 extern unsigned short nfs_callback_tcpport;
-extern unsigned short nfs_callback_tcpport6;
 
 #endif /* __LINUX_FS_NFS_CALLBACK_H */
diff --git a/fs/nfs/callback_proc.c b/fs/nfs/callback_proc.c
index 1b5d809a105..264d1aa935f 100644
--- a/fs/nfs/callback_proc.c
+++ b/fs/nfs/callback_proc.c
@@ -14,6 +14,7 @@
 #include "delegation.h"
 #include "internal.h"
 #include "pnfs.h"
+#include "nfs4session.h"
 
 #ifdef NFS_DEBUG
 #define NFSDBG_FACILITY NFSDBG_CALLBACK
@@ -122,7 +123,15 @@ static struct pnfs_layout_hdr * get_layout_by_fh_locked(struct nfs_client *clp,
 			ino = igrab(lo->plh_inode);
 			if (!ino)
 				continue;
-			get_layout_hdr(lo);
+			spin_lock(&ino->i_lock);
+			/* Is this layout in the process of being freed? */
+			if (NFS_I(ino)->layout != lo) {
+				spin_unlock(&ino->i_lock);
+				iput(ino);
+				continue;
+			}
+			pnfs_get_layout_hdr(lo);
+			spin_unlock(&ino->i_lock);
 			return lo;
 		}
 	}
@@ -158,7 +167,7 @@ static u32 initiate_file_draining(struct nfs_client *clp,
 	ino = lo->plh_inode;
 	spin_lock(&ino->i_lock);
 	if (test_bit(NFS_LAYOUT_BULK_RECALL, &lo->plh_flags) ||
-	    mark_matching_lsegs_invalid(lo, &free_me_list,
+	    pnfs_mark_matching_lsegs_invalid(lo, &free_me_list,
 					&args->cbl_range))
 		rv = NFS4ERR_DELAY;
 	else
@@ -166,7 +175,7 @@ static u32 initiate_file_draining(struct nfs_client *clp,
 	pnfs_set_layout_stateid(lo, &args->cbl_stateid, true);
 	spin_unlock(&ino->i_lock);
 	pnfs_free_lseg_list(&free_me_list);
-	put_layout_hdr(lo);
+	pnfs_put_layout_hdr(lo);
 	iput(ino);
 	return rv;
 }
@@ -196,10 +205,18 @@ static u32 initiate_bulk_draining(struct nfs_client *clp,
 			continue;
 
 		list_for_each_entry(lo, &server->layouts, plh_layouts) {
-			if (!igrab(lo->plh_inode))
+			ino = igrab(lo->plh_inode);
+			if (!ino)
+				continue;
+			spin_lock(&ino->i_lock);
+			/* Is this layout in the process of being freed? */
+			if (NFS_I(ino)->layout != lo) {
+				spin_unlock(&ino->i_lock);
+				iput(ino);
 				continue;
-			get_layout_hdr(lo);
-			BUG_ON(!list_empty(&lo->plh_bulk_recall));
+			}
+			pnfs_get_layout_hdr(lo);
+			spin_unlock(&ino->i_lock);
 			list_add(&lo->plh_bulk_recall, &recall_list);
 		}
 	}
@@ -211,12 +228,12 @@ static u32 initiate_bulk_draining(struct nfs_client *clp,
 		ino = lo->plh_inode;
 		spin_lock(&ino->i_lock);
 		set_bit(NFS_LAYOUT_BULK_RECALL, &lo->plh_flags);
-		if (mark_matching_lsegs_invalid(lo, &free_me_list, &range))
+		if (pnfs_mark_matching_lsegs_invalid(lo, &free_me_list, &range))
 			rv = NFS4ERR_DELAY;
 		list_del_init(&lo->plh_bulk_recall);
 		spin_unlock(&ino->i_lock);
 		pnfs_free_lseg_list(&free_me_list);
-		put_layout_hdr(lo);
+		pnfs_put_layout_hdr(lo);
 		iput(ino);
 	}
 	return rv;
@@ -545,23 +562,16 @@ __be32 nfs4_callback_recallslot(struct cb_recallslotargs *args, void *dummy,
 	if (!cps->clp) /* set in cb_sequence */
 		goto out;
 
-	dprintk_rcu("NFS: CB_RECALL_SLOT request from %s target max slots %d\n",
+	dprintk_rcu("NFS: CB_RECALL_SLOT request from %s target highest slotid %d\n",
 		rpc_peeraddr2str(cps->clp->cl_rpcclient, RPC_DISPLAY_ADDR),
-		args->crsa_target_max_slots);
+		args->crsa_target_highest_slotid);
 
 	fc_tbl = &cps->clp->cl_session->fc_slot_table;
 
-	status = htonl(NFS4ERR_BAD_HIGH_SLOT);
-	if (args->crsa_target_max_slots > fc_tbl->max_slots ||
-	    args->crsa_target_max_slots < 1)
-		goto out;
-
 	status = htonl(NFS4_OK);
-	if (args->crsa_target_max_slots == fc_tbl->max_slots)
-		goto out;
 
-	fc_tbl->target_max_slots = args->crsa_target_max_slots;
-	nfs41_handle_recall_slot(cps->clp);
+	nfs41_set_target_slotid(fc_tbl, args->crsa_target_highest_slotid);
+	nfs41_server_notify_target_slotid_update(cps->clp);
 out:
 	dprintk("%s: exit with status = %d\n", __func__, ntohl(status));
 	return status;
diff --git a/fs/nfs/callback_xdr.c b/fs/nfs/callback_xdr.c
index e64b01d2a33..59461c957d9 100644
--- a/fs/nfs/callback_xdr.c
+++ b/fs/nfs/callback_xdr.c
@@ -16,6 +16,7 @@
 #include "nfs4_fs.h"
 #include "callback.h"
 #include "internal.h"
+#include "nfs4session.h"
 
 #define CB_OP_TAGLEN_MAXSZ	(512)
 #define CB_OP_HDR_RES_MAXSZ	(2 + CB_OP_TAGLEN_MAXSZ)
@@ -520,7 +521,7 @@ static __be32 decode_recallslot_args(struct svc_rqst *rqstp,
 	p = read_buf(xdr, 4);
 	if (unlikely(p == NULL))
 		return htonl(NFS4ERR_BADXDR);
-	args->crsa_target_max_slots = ntohl(*p++);
+	args->crsa_target_highest_slotid = ntohl(*p++);
 	return 0;
 }
 
@@ -762,7 +763,7 @@ static void nfs4_callback_free_slot(struct nfs4_session *session)
 	 * A single slot, so highest used slotid is either 0 or -1
 	 */
 	tbl->highest_used_slotid = NFS4_NO_SLOT;
-	nfs4_check_drain_bc_complete(session);
+	nfs4_session_drain_complete(session, tbl);
 	spin_unlock(&tbl->slot_tbl_lock);
 }
 
@@ -863,7 +864,7 @@ static __be32 nfs4_callback_compound(struct svc_rqst *rqstp, void *argp, void *r
 		.drc_status = 0,
 		.clp = NULL,
 		.slotid = NFS4_NO_SLOT,
-		.net = rqstp->rq_xprt->xpt_net,
+		.net = SVC_NET(rqstp),
 	};
 	unsigned int nops = 0;
 
@@ -879,7 +880,7 @@ static __be32 nfs4_callback_compound(struct svc_rqst *rqstp, void *argp, void *r
 		return rpc_garbage_args;
 
 	if (hdr_arg.minorversion == 0) {
-		cps.clp = nfs4_find_client_ident(rqstp->rq_xprt->xpt_net, hdr_arg.cb_ident);
+		cps.clp = nfs4_find_client_ident(SVC_NET(rqstp), hdr_arg.cb_ident);
 		if (!cps.clp || !check_gss_callback_principal(cps.clp, rqstp))
 			return rpc_drop_reply;
 	}
diff --git a/fs/nfs/client.c b/fs/nfs/client.c
index f005b5bebdc..9f3c66438d0 100644
--- a/fs/nfs/client.c
+++ b/fs/nfs/client.c
@@ -51,54 +51,23 @@
 #include "internal.h"
 #include "fscache.h"
 #include "pnfs.h"
+#include "nfs.h"
 #include "netns.h"
 
 #define NFSDBG_FACILITY		NFSDBG_CLIENT
 
 static DECLARE_WAIT_QUEUE_HEAD(nfs_client_active_wq);
-#ifdef CONFIG_NFS_V4
-
-/*
- * Get a unique NFSv4.0 callback identifier which will be used
- * by the V4.0 callback service to lookup the nfs_client struct
- */
-static int nfs_get_cb_ident_idr(struct nfs_client *clp, int minorversion)
-{
-	int ret = 0;
-	struct nfs_net *nn = net_generic(clp->cl_net, nfs_net_id);
-
-	if (clp->rpc_ops->version != 4 || minorversion != 0)
-		return ret;
-retry:
-	if (!idr_pre_get(&nn->cb_ident_idr, GFP_KERNEL))
-		return -ENOMEM;
-	spin_lock(&nn->nfs_client_lock);
-	ret = idr_get_new(&nn->cb_ident_idr, clp, &clp->cl_cb_ident);
-	spin_unlock(&nn->nfs_client_lock);
-	if (ret == -EAGAIN)
-		goto retry;
-	return ret;
-}
-#endif /* CONFIG_NFS_V4 */
-
-/*
- * Turn off NFSv4 uid/gid mapping when using AUTH_SYS
- */
-static bool nfs4_disable_idmapping = true;
+static DEFINE_SPINLOCK(nfs_version_lock);
+static DEFINE_MUTEX(nfs_version_mutex);
+static LIST_HEAD(nfs_versions);
 
 /*
  * RPC cruft for NFS
  */
 static const struct rpc_version *nfs_version[5] = {
-#ifdef CONFIG_NFS_V2
-	[2]			= &nfs_version2,
-#endif
-#ifdef CONFIG_NFS_V3
-	[3]			= &nfs_version3,
-#endif
-#ifdef CONFIG_NFS_V4
-	[4]			= &nfs_version4,
-#endif
+	[2] = NULL,
+	[3] = NULL,
+	[4] = NULL,
 };
 
 const struct rpc_program nfs_program = {
@@ -114,32 +83,64 @@ struct rpc_stat nfs_rpcstat = {
 	.program		= &nfs_program
 };
 
+static struct nfs_subversion *find_nfs_version(unsigned int version)
+{
+	struct nfs_subversion *nfs;
+	spin_lock(&nfs_version_lock);
 
-#ifdef CONFIG_NFS_V3_ACL
-static struct rpc_stat		nfsacl_rpcstat = { &nfsacl_program };
-static const struct rpc_version *nfsacl_version[] = {
-	[3]			= &nfsacl_version3,
-};
+	list_for_each_entry(nfs, &nfs_versions, list) {
+		if (nfs->rpc_ops->version == version) {
+			spin_unlock(&nfs_version_lock);
+			return nfs;
+		}
+	}
 
-const struct rpc_program nfsacl_program = {
-	.name			= "nfsacl",
-	.number			= NFS_ACL_PROGRAM,
-	.nrvers			= ARRAY_SIZE(nfsacl_version),
-	.version		= nfsacl_version,
-	.stats			= &nfsacl_rpcstat,
-};
-#endif  /* CONFIG_NFS_V3_ACL */
-
-struct nfs_client_initdata {
-	unsigned long init_flags;
-	const char *hostname;
-	const struct sockaddr *addr;
-	size_t addrlen;
-	const struct nfs_rpc_ops *rpc_ops;
-	int proto;
-	u32 minorversion;
-	struct net *net;
-};
+	spin_unlock(&nfs_version_lock);
+	return ERR_PTR(-EPROTONOSUPPORT);
+}
+
+struct nfs_subversion *get_nfs_version(unsigned int version)
+{
+	struct nfs_subversion *nfs = find_nfs_version(version);
+
+	if (IS_ERR(nfs)) {
+		mutex_lock(&nfs_version_mutex);
+		request_module("nfsv%d", version);
+		nfs = find_nfs_version(version);
+		mutex_unlock(&nfs_version_mutex);
+	}
+
+	if (!IS_ERR(nfs))
+		try_module_get(nfs->owner);
+	return nfs;
+}
+
+void put_nfs_version(struct nfs_subversion *nfs)
+{
+	module_put(nfs->owner);
+}
+
+void register_nfs_version(struct nfs_subversion *nfs)
+{
+	spin_lock(&nfs_version_lock);
+
+	list_add(&nfs->list, &nfs_versions);
+	nfs_version[nfs->rpc_ops->version] = nfs->rpc_vers;
+
+	spin_unlock(&nfs_version_lock);
+}
+EXPORT_SYMBOL_GPL(register_nfs_version);
+
+void unregister_nfs_version(struct nfs_subversion *nfs)
+{
+	spin_lock(&nfs_version_lock);
+
+	nfs_version[nfs->rpc_ops->version] = NULL;
+	list_del(&nfs->list);
+
+	spin_unlock(&nfs_version_lock);
+}
+EXPORT_SYMBOL_GPL(unregister_nfs_version);
 
 /*
  * Allocate a shared client record
@@ -147,7 +148,7 @@ struct nfs_client_initdata {
  * Since these are allocated/deallocated very rarely, we don't
  * bother putting them in a slab cache...
  */
-static struct nfs_client *nfs_alloc_client(const struct nfs_client_initdata *cl_init)
+struct nfs_client *nfs_alloc_client(const struct nfs_client_initdata *cl_init)
 {
 	struct nfs_client *clp;
 	struct rpc_cred *cred;
@@ -156,7 +157,10 @@ static struct nfs_client *nfs_alloc_client(const struct nfs_client_initdata *cl_
 	if ((clp = kzalloc(sizeof(*clp), GFP_KERNEL)) == NULL)
 		goto error_0;
 
-	clp->rpc_ops = cl_init->rpc_ops;
+	clp->cl_nfs_mod = cl_init->nfs_mod;
+	try_module_get(clp->cl_nfs_mod->owner);
+
+	clp->rpc_ops = clp->cl_nfs_mod->rpc_ops;
 
 	atomic_set(&clp->cl_count, 1);
 	clp->cl_cons_state = NFS_CS_INITING;
@@ -177,18 +181,6 @@ static struct nfs_client *nfs_alloc_client(const struct nfs_client_initdata *cl_
 	clp->cl_proto = cl_init->proto;
 	clp->cl_net = get_net(cl_init->net);
 
-#ifdef CONFIG_NFS_V4
-	err = nfs_get_cb_ident_idr(clp, cl_init->minorversion);
-	if (err)
-		goto error_cleanup;
-
-	spin_lock_init(&clp->cl_lock);
-	INIT_DELAYED_WORK(&clp->cl_renewd, nfs4_renew_state);
-	rpc_init_wait_queue(&clp->cl_rpcwaitq, "NFS client");
-	clp->cl_state = 1 << NFS4CLNT_LEASE_EXPIRED;
-	clp->cl_minorversion = cl_init->minorversion;
-	clp->cl_mvops = nfs_v4_minor_ops[cl_init->minorversion];
-#endif
 	cred = rpc_lookup_machine_cred("*");
 	if (!IS_ERR(cred))
 		clp->cl_machine_cred = cred;
@@ -197,51 +189,14 @@ static struct nfs_client *nfs_alloc_client(const struct nfs_client_initdata *cl_
 	return clp;
 
 error_cleanup:
+	put_nfs_version(clp->cl_nfs_mod);
 	kfree(clp);
 error_0:
 	return ERR_PTR(err);
 }
+EXPORT_SYMBOL_GPL(nfs_alloc_client);
 
-#ifdef CONFIG_NFS_V4
-#ifdef CONFIG_NFS_V4_1
-static void nfs4_shutdown_session(struct nfs_client *clp)
-{
-	if (nfs4_has_session(clp)) {
-		nfs4_destroy_session(clp->cl_session);
-		nfs4_destroy_clientid(clp);
-	}
-
-}
-#else /* CONFIG_NFS_V4_1 */
-static void nfs4_shutdown_session(struct nfs_client *clp)
-{
-}
-#endif /* CONFIG_NFS_V4_1 */
-
-/*
- * Destroy the NFS4 callback service
- */
-static void nfs4_destroy_callback(struct nfs_client *clp)
-{
-	if (__test_and_clear_bit(NFS_CS_CALLBACK, &clp->cl_res_state))
-		nfs_callback_down(clp->cl_mvops->minor_version);
-}
-
-static void nfs4_shutdown_client(struct nfs_client *clp)
-{
-	if (__test_and_clear_bit(NFS_CS_RENEWD, &clp->cl_res_state))
-		nfs4_kill_renewd(clp);
-	nfs4_shutdown_session(clp);
-	nfs4_destroy_callback(clp);
-	if (__test_and_clear_bit(NFS_CS_IDMAP, &clp->cl_res_state))
-		nfs_idmap_delete(clp);
-
-	rpc_destroy_wait_queue(&clp->cl_rpcwaitq);
-	kfree(clp->cl_serverowner);
-	kfree(clp->cl_serverscope);
-	kfree(clp->cl_implid);
-}
-
+#if IS_ENABLED(CONFIG_NFS_V4)
 /* idr_remove_all is not needed as all id's are removed by nfs_put_client */
 void nfs_cleanup_cb_ident_idr(struct net *net)
 {
@@ -264,16 +219,7 @@ static void pnfs_init_server(struct nfs_server *server)
 	rpc_init_wait_queue(&server->roc_rpcwaitq, "pNFS ROC");
 }
 
-static void nfs4_destroy_server(struct nfs_server *server)
-{
-	nfs4_purge_state_owners(server);
-}
-
 #else
-static void nfs4_shutdown_client(struct nfs_client *clp)
-{
-}
-
 void nfs_cleanup_cb_ident_idr(struct net *net)
 {
 }
@@ -291,12 +237,10 @@ static void pnfs_init_server(struct nfs_server *server)
 /*
  * Destroy a shared client record
  */
-static void nfs_free_client(struct nfs_client *clp)
+void nfs_free_client(struct nfs_client *clp)
 {
 	dprintk("--> nfs_free_client(%u)\n", clp->rpc_ops->version);
 
-	nfs4_shutdown_client(clp);
-
 	nfs_fscache_release_client_cookie(clp);
 
 	/* -EIO all pending I/O */
@@ -307,11 +251,13 @@ static void nfs_free_client(struct nfs_client *clp)
 		put_rpccred(clp->cl_machine_cred);
 
 	put_net(clp->cl_net);
+	put_nfs_version(clp->cl_nfs_mod);
 	kfree(clp->cl_hostname);
 	kfree(clp);
 
 	dprintk("<-- nfs_free_client()\n");
 }
+EXPORT_SYMBOL_GPL(nfs_free_client);
 
 /*
  * Release a reference to a shared client record
@@ -331,9 +277,9 @@ void nfs_put_client(struct nfs_client *clp)
 		nfs_cb_idr_remove_locked(clp);
 		spin_unlock(&nn->nfs_client_lock);
 
-		BUG_ON(!list_empty(&clp->cl_superblocks));
+		WARN_ON_ONCE(!list_empty(&clp->cl_superblocks));
 
-		nfs_free_client(clp);
+		clp->rpc_ops->free_client(clp);
 	}
 }
 EXPORT_SYMBOL_GPL(nfs_put_client);
@@ -412,8 +358,8 @@ static int nfs_sockaddr_cmp_ip4(const struct sockaddr *sa1,
  * Test if two socket addresses represent the same actual socket,
  * by comparing (only) relevant fields, excluding the port number.
  */
-static int nfs_sockaddr_match_ipaddr(const struct sockaddr *sa1,
-				     const struct sockaddr *sa2)
+int nfs_sockaddr_match_ipaddr(const struct sockaddr *sa1,
+			      const struct sockaddr *sa2)
 {
 	if (sa1->sa_family != sa2->sa_family)
 		return 0;
@@ -426,6 +372,7 @@ static int nfs_sockaddr_match_ipaddr(const struct sockaddr *sa1,
 	}
 	return 0;
 }
+EXPORT_SYMBOL_GPL(nfs_sockaddr_match_ipaddr);
 #endif /* CONFIG_NFS_V4_1 */
 
 /*
@@ -447,33 +394,6 @@ static int nfs_sockaddr_cmp(const struct sockaddr *sa1,
 	return 0;
 }
 
-#if defined(CONFIG_NFS_V4_1)
-/* Common match routine for v4.0 and v4.1 callback services */
-static bool nfs4_cb_match_client(const struct sockaddr *addr,
-		struct nfs_client *clp, u32 minorversion)
-{
-	struct sockaddr *clap = (struct sockaddr *)&clp->cl_addr;
-
-	/* Don't match clients that failed to initialise */
-	if (!(clp->cl_cons_state == NFS_CS_READY ||
-	    clp->cl_cons_state == NFS_CS_SESSION_INITING))
-		return false;
-
-	smp_rmb();
-
-	/* Match the version and minorversion */
-	if (clp->rpc_ops->version != 4 ||
-	    clp->cl_minorversion != minorversion)
-		return false;
-
-	/* Match only the IP address, not the port number */
-	if (!nfs_sockaddr_match_ipaddr(addr, clap))
-		return false;
-
-	return true;
-}
-#endif /* CONFIG_NFS_V4_1 */
-
 /*
  * Find an nfs_client on the list that matches the initialisation data
  * that is supplied.
@@ -491,7 +411,7 @@ static struct nfs_client *nfs_match_client(const struct nfs_client_initdata *dat
 			continue;
 
 		/* Different NFS versions cannot share the same nfs_client */
-		if (clp->rpc_ops != data->rpc_ops)
+		if (clp->rpc_ops != data->nfs_mod->rpc_ops)
 			continue;
 
 		if (clp->cl_proto != data->proto)
@@ -519,6 +439,7 @@ int nfs_wait_client_init_complete(const struct nfs_client *clp)
 	return wait_event_killable(nfs_client_active_wq,
 			nfs_client_init_is_complete(clp));
 }
+EXPORT_SYMBOL_GPL(nfs_wait_client_init_complete);
 
 /*
  * Found an existing client.  Make sure it's ready before returning.
@@ -552,7 +473,7 @@ nfs_found_client(const struct nfs_client_initdata *cl_init,
  * Look up a client by IP address and protocol version
  * - creates a new record if one doesn't yet exist
  */
-static struct nfs_client *
+struct nfs_client *
 nfs_get_client(const struct nfs_client_initdata *cl_init,
 	       const struct rpc_timeout *timeparms,
 	       const char *ip_addr,
@@ -560,9 +481,10 @@ nfs_get_client(const struct nfs_client_initdata *cl_init,
 {
 	struct nfs_client *clp, *new = NULL;
 	struct nfs_net *nn = net_generic(cl_init->net, nfs_net_id);
+	const struct nfs_rpc_ops *rpc_ops = cl_init->nfs_mod->rpc_ops;
 
 	dprintk("--> nfs_get_client(%s,v%u)\n",
-		cl_init->hostname ?: "", cl_init->rpc_ops->version);
+		cl_init->hostname ?: "", rpc_ops->version);
 
 	/* see if the client already exists */
 	do {
@@ -572,27 +494,28 @@ nfs_get_client(const struct nfs_client_initdata *cl_init,
 		if (clp) {
 			spin_unlock(&nn->nfs_client_lock);
 			if (new)
-				nfs_free_client(new);
+				new->rpc_ops->free_client(new);
 			return nfs_found_client(cl_init, clp);
 		}
 		if (new) {
-			list_add(&new->cl_share_link, &nn->nfs_client_list);
+			list_add_tail(&new->cl_share_link,
+					&nn->nfs_client_list);
 			spin_unlock(&nn->nfs_client_lock);
 			new->cl_flags = cl_init->init_flags;
-			return cl_init->rpc_ops->init_client(new,
-						timeparms, ip_addr,
-						authflavour);
+			return rpc_ops->init_client(new, timeparms, ip_addr,
+						    authflavour);
 		}
 
 		spin_unlock(&nn->nfs_client_lock);
 
-		new = nfs_alloc_client(cl_init);
+		new = rpc_ops->alloc_client(cl_init);
 	} while (!IS_ERR(new));
 
 	dprintk("<-- nfs_get_client() Failed to find %s (%ld)\n",
 		cl_init->hostname ?: "", PTR_ERR(new));
 	return new;
 }
+EXPORT_SYMBOL_GPL(nfs_get_client);
 
 /*
  * Mark a server as ready or failed
@@ -603,11 +526,12 @@ void nfs_mark_client_ready(struct nfs_client *clp, int state)
 	clp->cl_cons_state = state;
 	wake_up_all(&nfs_client_active_wq);
 }
+EXPORT_SYMBOL_GPL(nfs_mark_client_ready);
 
 /*
  * Initialise the timeout values for a connection
  */
-static void nfs_init_timeout_values(struct rpc_timeout *to, int proto,
+void nfs_init_timeout_values(struct rpc_timeout *to, int proto,
 				    unsigned int timeo, unsigned int retrans)
 {
 	to->to_initval = timeo * HZ / 10;
@@ -644,13 +568,14 @@ static void nfs_init_timeout_values(struct rpc_timeout *to, int proto,
 		BUG();
 	}
 }
+EXPORT_SYMBOL_GPL(nfs_init_timeout_values);
 
 /*
  * Create an RPC client handle
  */
-static int nfs_create_rpc_client(struct nfs_client *clp,
-				 const struct rpc_timeout *timeparms,
-				 rpc_authflavor_t flavor)
+int nfs_create_rpc_client(struct nfs_client *clp,
+			  const struct rpc_timeout *timeparms,
+			  rpc_authflavor_t flavor)
 {
 	struct rpc_clnt		*clnt = NULL;
 	struct rpc_create_args args = {
@@ -683,14 +608,14 @@ static int nfs_create_rpc_client(struct nfs_client *clp,
 	clp->cl_rpcclient = clnt;
 	return 0;
 }
+EXPORT_SYMBOL_GPL(nfs_create_rpc_client);
 
 /*
  * Version 2 or 3 client destruction
  */
 static void nfs_destroy_server(struct nfs_server *server)
 {
-	if (!(server->flags & NFS_MOUNT_LOCAL_FLOCK) ||
-			!(server->flags & NFS_MOUNT_LOCAL_FCNTL))
+	if (server->nlm_host)
 		nlmclnt_done(server->nlm_host);
 }
 
@@ -735,45 +660,16 @@ static int nfs_start_lockd(struct nfs_server *server)
 }
 
 /*
- * Initialise an NFSv3 ACL client connection
- */
-#ifdef CONFIG_NFS_V3_ACL
-static void nfs_init_server_aclclient(struct nfs_server *server)
-{
-	if (server->nfs_client->rpc_ops->version != 3)
-		goto out_noacl;
-	if (server->flags & NFS_MOUNT_NOACL)
-		goto out_noacl;
-
-	server->client_acl = rpc_bind_new_program(server->client, &nfsacl_program, 3);
-	if (IS_ERR(server->client_acl))
-		goto out_noacl;
-
-	/* No errors! Assume that Sun nfsacls are supported */
-	server->caps |= NFS_CAP_ACLS;
-	return;
-
-out_noacl:
-	server->caps &= ~NFS_CAP_ACLS;
-}
-#else
-static inline void nfs_init_server_aclclient(struct nfs_server *server)
-{
-	server->flags &= ~NFS_MOUNT_NOACL;
-	server->caps &= ~NFS_CAP_ACLS;
-}
-#endif
-
-/*
  * Create a general RPC client
  */
-static int nfs_init_server_rpcclient(struct nfs_server *server,
+int nfs_init_server_rpcclient(struct nfs_server *server,
 		const struct rpc_timeout *timeo,
 		rpc_authflavor_t pseudoflavour)
 {
 	struct nfs_client *clp = server->nfs_client;
 
-	server->client = rpc_clone_client(clp->cl_rpcclient);
+	server->client = rpc_clone_client_set_auth(clp->cl_rpcclient,
+							pseudoflavour);
 	if (IS_ERR(server->client)) {
 		dprintk("%s: couldn't create rpc_client!\n", __func__);
 		return PTR_ERR(server->client);
@@ -783,22 +679,13 @@ static int nfs_init_server_rpcclient(struct nfs_server *server,
 			timeo,
 			sizeof(server->client->cl_timeout_default));
 	server->client->cl_timeout = &server->client->cl_timeout_default;
-
-	if (pseudoflavour != clp->cl_rpcclient->cl_auth->au_flavor) {
-		struct rpc_auth *auth;
-
-		auth = rpcauth_create(pseudoflavour, server->client);
-		if (IS_ERR(auth)) {
-			dprintk("%s: couldn't create credcache!\n", __func__);
-			return PTR_ERR(auth);
-		}
-	}
 	server->client->cl_softrtry = 0;
 	if (server->flags & NFS_MOUNT_SOFT)
 		server->client->cl_softrtry = 1;
 
 	return 0;
 }
+EXPORT_SYMBOL_GPL(nfs_init_server_rpcclient);
 
 /**
  * nfs_init_client - Initialise an NFS2 or NFS3 client
@@ -838,18 +725,20 @@ error:
 	dprintk("<-- nfs_init_client() = xerror %d\n", error);
 	return ERR_PTR(error);
 }
+EXPORT_SYMBOL_GPL(nfs_init_client);
 
 /*
  * Create a version 2 or 3 client
  */
 static int nfs_init_server(struct nfs_server *server,
-			   const struct nfs_parsed_mount_data *data)
+			   const struct nfs_parsed_mount_data *data,
+			   struct nfs_subversion *nfs_mod)
 {
 	struct nfs_client_initdata cl_init = {
 		.hostname = data->nfs_server.hostname,
 		.addr = (const struct sockaddr *)&data->nfs_server.address,
 		.addrlen = data->nfs_server.addrlen,
-		.rpc_ops = NULL,
+		.nfs_mod = nfs_mod,
 		.proto = data->nfs_server.protocol,
 		.net = data->net,
 	};
@@ -859,25 +748,12 @@ static int nfs_init_server(struct nfs_server *server,
 
 	dprintk("--> nfs_init_server()\n");
 
-	switch (data->version) {
-#ifdef CONFIG_NFS_V2
-	case 2:
-		cl_init.rpc_ops = &nfs_v2_clientops;
-		break;
-#endif
-#ifdef CONFIG_NFS_V3
-	case 3:
-		cl_init.rpc_ops = &nfs_v3_clientops;
-		break;
-#endif
-	default:
-		return -EPROTONOSUPPORT;
-	}
-
 	nfs_init_timeout_values(&timeparms, data->nfs_server.protocol,
 			data->timeo, data->retrans);
 	if (data->flags & NFS_MOUNT_NORESVPORT)
 		set_bit(NFS_CS_NORESVPORT, &cl_init.init_flags);
+	if (server->options & NFS_OPTION_MIGRATION)
+		set_bit(NFS_CS_MIGRATION, &cl_init.init_flags);
 
 	/* Allocate or find a client reference we can use */
 	clp = nfs_get_client(&cl_init, &timeparms, NULL, RPC_AUTH_UNIX);
@@ -927,8 +803,6 @@ static int nfs_init_server(struct nfs_server *server,
 	server->mountd_protocol = data->mount_server.protocol;
 
 	server->namelen  = data->namlen;
-	/* Create a client RPC handle for the NFSv3 ACL management interface */
-	nfs_init_server_aclclient(server);
 	dprintk("<-- nfs_init_server() = 0 [new %p]\n", clp);
 	return 0;
 
@@ -974,8 +848,6 @@ static void nfs_server_set_fsinfo(struct nfs_server *server,
 	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;
-	server->pnfs_blksize = fsinfo->blksize;
-	set_pnfs_layoutdriver(server, mntfh, fsinfo->layouttype);
 
 	server->wtmult = nfs_block_bits(fsinfo->wtmult, NULL);
 
@@ -1001,7 +873,7 @@ static void nfs_server_set_fsinfo(struct nfs_server *server,
 /*
  * Probe filesystem information, including the FSID on v2/v3
  */
-static int nfs_probe_fsinfo(struct nfs_server *server, struct nfs_fh *mntfh, struct nfs_fattr *fattr)
+int nfs_probe_fsinfo(struct nfs_server *server, struct nfs_fh *mntfh, struct nfs_fattr *fattr)
 {
 	struct nfs_fsinfo fsinfo;
 	struct nfs_client *clp = server->nfs_client;
@@ -1041,11 +913,12 @@ out_error:
 	dprintk("nfs_probe_fsinfo: error = %d\n", -error);
 	return error;
 }
+EXPORT_SYMBOL_GPL(nfs_probe_fsinfo);
 
 /*
  * Copy useful information when duplicating a server record
  */
-static void nfs_server_copy_userdata(struct nfs_server *target, struct nfs_server *source)
+void nfs_server_copy_userdata(struct nfs_server *target, struct nfs_server *source)
 {
 	target->flags = source->flags;
 	target->rsize = source->rsize;
@@ -1057,8 +930,9 @@ static void nfs_server_copy_userdata(struct nfs_server *target, struct nfs_serve
 	target->caps = source->caps;
 	target->options = source->options;
 }
+EXPORT_SYMBOL_GPL(nfs_server_copy_userdata);
 
-static void nfs_server_insert_lists(struct nfs_server *server)
+void nfs_server_insert_lists(struct nfs_server *server)
 {
 	struct nfs_client *clp = server->nfs_client;
 	struct nfs_net *nn = net_generic(clp->cl_net, nfs_net_id);
@@ -1070,6 +944,7 @@ static void nfs_server_insert_lists(struct nfs_server *server)
 	spin_unlock(&nn->nfs_client_lock);
 
 }
+EXPORT_SYMBOL_GPL(nfs_server_insert_lists);
 
 static void nfs_server_remove_lists(struct nfs_server *server)
 {
@@ -1092,7 +967,7 @@ static void nfs_server_remove_lists(struct nfs_server *server)
 /*
  * Allocate and initialise a server record
  */
-static struct nfs_server *nfs_alloc_server(void)
+struct nfs_server *nfs_alloc_server(void)
 {
 	struct nfs_server *server;
 
@@ -1129,6 +1004,7 @@ static struct nfs_server *nfs_alloc_server(void)
 
 	return server;
 }
+EXPORT_SYMBOL_GPL(nfs_alloc_server);
 
 /*
  * Free up a server record
@@ -1138,7 +1014,6 @@ void nfs_free_server(struct nfs_server *server)
 	dprintk("--> nfs_free_server()\n");
 
 	nfs_server_remove_lists(server);
-	unset_pnfs_layoutdriver(server);
 
 	if (server->destroy != NULL)
 		server->destroy(server);
@@ -1158,13 +1033,14 @@ void nfs_free_server(struct nfs_server *server)
 	nfs_release_automount_timer();
 	dprintk("<-- nfs_free_server()\n");
 }
+EXPORT_SYMBOL_GPL(nfs_free_server);
 
 /*
  * Create a version 2 or 3 volume record
  * - keyed on server and FSID
  */
-struct nfs_server *nfs_create_server(const struct nfs_parsed_mount_data *data,
-				     struct nfs_fh *mntfh)
+struct nfs_server *nfs_create_server(struct nfs_mount_info *mount_info,
+				     struct nfs_subversion *nfs_mod)
 {
 	struct nfs_server *server;
 	struct nfs_fattr *fattr;
@@ -1180,22 +1056,18 @@ struct nfs_server *nfs_create_server(const struct nfs_parsed_mount_data *data,
 		goto error;
 
 	/* Get a client representation */
-	error = nfs_init_server(server, data);
+	error = nfs_init_server(server, mount_info->parsed, nfs_mod);
 	if (error < 0)
 		goto error;
 
-	BUG_ON(!server->nfs_client);
-	BUG_ON(!server->nfs_client->rpc_ops);
-	BUG_ON(!server->nfs_client->rpc_ops->file_inode_ops);
-
 	/* Probe the root fh to retrieve its FSID */
-	error = nfs_probe_fsinfo(server, mntfh, fattr);
+	error = nfs_probe_fsinfo(server, mount_info->mntfh, fattr);
 	if (error < 0)
 		goto error;
 	if (server->nfs_client->rpc_ops->version == 3) {
 		if (server->namelen == 0 || server->namelen > NFS3_MAXNAMLEN)
 			server->namelen = NFS3_MAXNAMLEN;
-		if (!(data->flags & NFS_MOUNT_NORDIRPLUS))
+		if (!(mount_info->parsed->flags & NFS_MOUNT_NORDIRPLUS))
 			server->caps |= NFS_CAP_READDIRPLUS;
 	} else {
 		if (server->namelen == 0 || server->namelen > NFS2_MAXNAMLEN)
@@ -1203,7 +1075,7 @@ struct nfs_server *nfs_create_server(const struct nfs_parsed_mount_data *data,
 	}
 
 	if (!(fattr->valid & NFS_ATTR_FATTR)) {
-		error = server->nfs_client->rpc_ops->getattr(server, mntfh, fattr);
+		error = nfs_mod->rpc_ops->getattr(server, mount_info->mntfh, fattr);
 		if (error < 0) {
 			dprintk("nfs_create_server: getattr error = %d\n", -error);
 			goto error;
@@ -1225,522 +1097,7 @@ error:
 	nfs_free_server(server);
 	return ERR_PTR(error);
 }
-
-#ifdef CONFIG_NFS_V4
-/*
- * NFSv4.0 callback thread helper
- *
- * Find a client by callback identifier
- */
-struct nfs_client *
-nfs4_find_client_ident(struct net *net, int cb_ident)
-{
-	struct nfs_client *clp;
-	struct nfs_net *nn = net_generic(net, nfs_net_id);
-
-	spin_lock(&nn->nfs_client_lock);
-	clp = idr_find(&nn->cb_ident_idr, cb_ident);
-	if (clp)
-		atomic_inc(&clp->cl_count);
-	spin_unlock(&nn->nfs_client_lock);
-	return clp;
-}
-
-#if defined(CONFIG_NFS_V4_1)
-/*
- * NFSv4.1 callback thread helper
- * For CB_COMPOUND calls, find a client by IP address, protocol version,
- * minorversion, and sessionID
- *
- * Returns NULL if no such client
- */
-struct nfs_client *
-nfs4_find_client_sessionid(struct net *net, const struct sockaddr *addr,
-			   struct nfs4_sessionid *sid)
-{
-	struct nfs_client *clp;
-	struct nfs_net *nn = net_generic(net, nfs_net_id);
-
-	spin_lock(&nn->nfs_client_lock);
-	list_for_each_entry(clp, &nn->nfs_client_list, cl_share_link) {
-		if (nfs4_cb_match_client(addr, clp, 1) == false)
-			continue;
-
-		if (!nfs4_has_session(clp))
-			continue;
-
-		/* Match sessionid*/
-		if (memcmp(clp->cl_session->sess_id.data,
-		    sid->data, NFS4_MAX_SESSIONID_LEN) != 0)
-			continue;
-
-		atomic_inc(&clp->cl_count);
-		spin_unlock(&nn->nfs_client_lock);
-		return clp;
-	}
-	spin_unlock(&nn->nfs_client_lock);
-	return NULL;
-}
-
-#else /* CONFIG_NFS_V4_1 */
-
-struct nfs_client *
-nfs4_find_client_sessionid(struct net *net, const struct sockaddr *addr,
-			   struct nfs4_sessionid *sid)
-{
-	return NULL;
-}
-#endif /* CONFIG_NFS_V4_1 */
-
-/*
- * Initialize the NFS4 callback service
- */
-static int nfs4_init_callback(struct nfs_client *clp)
-{
-	int error;
-
-	if (clp->rpc_ops->version == 4) {
-		struct rpc_xprt *xprt;
-
-		xprt = rcu_dereference_raw(clp->cl_rpcclient->cl_xprt);
-
-		if (nfs4_has_session(clp)) {
-			error = xprt_setup_backchannel(xprt,
-						NFS41_BC_MIN_CALLBACKS);
-			if (error < 0)
-				return error;
-		}
-
-		error = nfs_callback_up(clp->cl_mvops->minor_version, xprt);
-		if (error < 0) {
-			dprintk("%s: failed to start callback. Error = %d\n",
-				__func__, error);
-			return error;
-		}
-		__set_bit(NFS_CS_CALLBACK, &clp->cl_res_state);
-	}
-	return 0;
-}
-
-/*
- * Initialize the minor version specific parts of an NFS4 client record
- */
-static int nfs4_init_client_minor_version(struct nfs_client *clp)
-{
-#if defined(CONFIG_NFS_V4_1)
-	if (clp->cl_mvops->minor_version) {
-		struct nfs4_session *session = NULL;
-		/*
-		 * Create the session and mark it expired.
-		 * When a SEQUENCE operation encounters the expired session
-		 * it will do session recovery to initialize it.
-		 */
-		session = nfs4_alloc_session(clp);
-		if (!session)
-			return -ENOMEM;
-
-		clp->cl_session = session;
-		/*
-		 * The create session reply races with the server back
-		 * channel probe. Mark the client NFS_CS_SESSION_INITING
-		 * so that the client back channel can find the
-		 * nfs_client struct
-		 */
-		nfs_mark_client_ready(clp, NFS_CS_SESSION_INITING);
-	}
-#endif /* CONFIG_NFS_V4_1 */
-
-	return nfs4_init_callback(clp);
-}
-
-/**
- * nfs4_init_client - Initialise an NFS4 client record
- *
- * @clp: nfs_client to initialise
- * @timeparms: timeout parameters for underlying RPC transport
- * @ip_addr: callback IP address in presentation format
- * @authflavor: authentication flavor for underlying RPC transport
- *
- * Returns pointer to an NFS client, or an ERR_PTR value.
- */
-struct nfs_client *nfs4_init_client(struct nfs_client *clp,
-				    const struct rpc_timeout *timeparms,
-				    const char *ip_addr,
-				    rpc_authflavor_t authflavour)
-{
-	char buf[INET6_ADDRSTRLEN + 1];
-	int error;
-
-	if (clp->cl_cons_state == NFS_CS_READY) {
-		/* the client is initialised already */
-		dprintk("<-- nfs4_init_client() = 0 [already %p]\n", clp);
-		return clp;
-	}
-
-	/* Check NFS protocol revision and initialize RPC op vector */
-	clp->rpc_ops = &nfs_v4_clientops;
-
-	__set_bit(NFS_CS_DISCRTRY, &clp->cl_flags);
-	error = nfs_create_rpc_client(clp, timeparms, authflavour);
-	if (error < 0)
-		goto error;
-
-	/* If no clientaddr= option was specified, find a usable cb address */
-	if (ip_addr == NULL) {
-		struct sockaddr_storage cb_addr;
-		struct sockaddr *sap = (struct sockaddr *)&cb_addr;
-
-		error = rpc_localaddr(clp->cl_rpcclient, sap, sizeof(cb_addr));
-		if (error < 0)
-			goto error;
-		error = rpc_ntop(sap, buf, sizeof(buf));
-		if (error < 0)
-			goto error;
-		ip_addr = (const char *)buf;
-	}
-	strlcpy(clp->cl_ipaddr, ip_addr, sizeof(clp->cl_ipaddr));
-
-	error = nfs_idmap_new(clp);
-	if (error < 0) {
-		dprintk("%s: failed to create idmapper. Error = %d\n",
-			__func__, error);
-		goto error;
-	}
-	__set_bit(NFS_CS_IDMAP, &clp->cl_res_state);
-
-	error = nfs4_init_client_minor_version(clp);
-	if (error < 0)
-		goto error;
-
-	if (!nfs4_has_session(clp))
-		nfs_mark_client_ready(clp, NFS_CS_READY);
-	return clp;
-
-error:
-	nfs_mark_client_ready(clp, error);
-	nfs_put_client(clp);
-	dprintk("<-- nfs4_init_client() = xerror %d\n", error);
-	return ERR_PTR(error);
-}
-
-/*
- * Set up an NFS4 client
- */
-static int nfs4_set_client(struct nfs_server *server,
-		const char *hostname,
-		const struct sockaddr *addr,
-		const size_t addrlen,
-		const char *ip_addr,
-		rpc_authflavor_t authflavour,
-		int proto, const struct rpc_timeout *timeparms,
-		u32 minorversion, struct net *net)
-{
-	struct nfs_client_initdata cl_init = {
-		.hostname = hostname,
-		.addr = addr,
-		.addrlen = addrlen,
-		.rpc_ops = &nfs_v4_clientops,
-		.proto = proto,
-		.minorversion = minorversion,
-		.net = net,
-	};
-	struct nfs_client *clp;
-	int error;
-
-	dprintk("--> nfs4_set_client()\n");
-
-	if (server->flags & NFS_MOUNT_NORESVPORT)
-		set_bit(NFS_CS_NORESVPORT, &cl_init.init_flags);
-
-	/* Allocate or find a client reference we can use */
-	clp = nfs_get_client(&cl_init, timeparms, ip_addr, authflavour);
-	if (IS_ERR(clp)) {
-		error = PTR_ERR(clp);
-		goto error;
-	}
-
-	/*
-	 * Query for the lease time on clientid setup or renewal
-	 *
-	 * Note that this will be set on nfs_clients that were created
-	 * only for the DS role and did not set this bit, but now will
-	 * serve a dual role.
-	 */
-	set_bit(NFS_CS_CHECK_LEASE_TIME, &clp->cl_res_state);
-
-	server->nfs_client = clp;
-	dprintk("<-- nfs4_set_client() = 0 [new %p]\n", clp);
-	return 0;
-error:
-	dprintk("<-- nfs4_set_client() = xerror %d\n", error);
-	return error;
-}
-
-/*
- * Set up a pNFS Data Server client.
- *
- * Return any existing nfs_client that matches server address,port,version
- * and minorversion.
- *
- * For a new nfs_client, use a soft mount (default), a low retrans and a
- * low timeout interval so that if a connection is lost, we retry through
- * the MDS.
- */
-struct nfs_client *nfs4_set_ds_client(struct nfs_client* mds_clp,
-		const struct sockaddr *ds_addr, int ds_addrlen,
-		int ds_proto, unsigned int ds_timeo, unsigned int ds_retrans)
-{
-	struct nfs_client_initdata cl_init = {
-		.addr = ds_addr,
-		.addrlen = ds_addrlen,
-		.rpc_ops = &nfs_v4_clientops,
-		.proto = ds_proto,
-		.minorversion = mds_clp->cl_minorversion,
-		.net = mds_clp->cl_net,
-	};
-	struct rpc_timeout ds_timeout;
-	struct nfs_client *clp;
-
-	/*
-	 * Set an authflavor equual to the MDS value. Use the MDS nfs_client
-	 * cl_ipaddr so as to use the same EXCHANGE_ID co_ownerid as the MDS
-	 * (section 13.1 RFC 5661).
-	 */
-	nfs_init_timeout_values(&ds_timeout, ds_proto, ds_timeo, ds_retrans);
-	clp = nfs_get_client(&cl_init, &ds_timeout, mds_clp->cl_ipaddr,
-			     mds_clp->cl_rpcclient->cl_auth->au_flavor);
-
-	dprintk("<-- %s %p\n", __func__, clp);
-	return clp;
-}
-EXPORT_SYMBOL_GPL(nfs4_set_ds_client);
-
-/*
- * Session has been established, and the client marked ready.
- * Set the mount rsize and wsize with negotiated fore channel
- * attributes which will be bound checked in nfs_server_set_fsinfo.
- */
-static void nfs4_session_set_rwsize(struct nfs_server *server)
-{
-#ifdef CONFIG_NFS_V4_1
-	struct nfs4_session *sess;
-	u32 server_resp_sz;
-	u32 server_rqst_sz;
-
-	if (!nfs4_has_session(server->nfs_client))
-		return;
-	sess = server->nfs_client->cl_session;
-	server_resp_sz = sess->fc_attrs.max_resp_sz - nfs41_maxread_overhead;
-	server_rqst_sz = sess->fc_attrs.max_rqst_sz - nfs41_maxwrite_overhead;
-
-	if (server->rsize > server_resp_sz)
-		server->rsize = server_resp_sz;
-	if (server->wsize > server_rqst_sz)
-		server->wsize = server_rqst_sz;
-#endif /* CONFIG_NFS_V4_1 */
-}
-
-static int nfs4_server_common_setup(struct nfs_server *server,
-		struct nfs_fh *mntfh)
-{
-	struct nfs_fattr *fattr;
-	int error;
-
-	BUG_ON(!server->nfs_client);
-	BUG_ON(!server->nfs_client->rpc_ops);
-	BUG_ON(!server->nfs_client->rpc_ops->file_inode_ops);
-
-	/* data servers support only a subset of NFSv4.1 */
-	if (is_ds_only_client(server->nfs_client))
-		return -EPROTONOSUPPORT;
-
-	fattr = nfs_alloc_fattr();
-	if (fattr == NULL)
-		return -ENOMEM;
-
-	/* We must ensure the session is initialised first */
-	error = nfs4_init_session(server);
-	if (error < 0)
-		goto out;
-
-	/* Probe the root fh to retrieve its FSID and filehandle */
-	error = nfs4_get_rootfh(server, mntfh);
-	if (error < 0)
-		goto out;
-
-	dprintk("Server FSID: %llx:%llx\n",
-			(unsigned long long) server->fsid.major,
-			(unsigned long long) server->fsid.minor);
-	dprintk("Mount FH: %d\n", mntfh->size);
-
-	nfs4_session_set_rwsize(server);
-
-	error = nfs_probe_fsinfo(server, mntfh, fattr);
-	if (error < 0)
-		goto out;
-
-	if (server->namelen == 0 || server->namelen > NFS4_MAXNAMLEN)
-		server->namelen = NFS4_MAXNAMLEN;
-
-	nfs_server_insert_lists(server);
-	server->mount_time = jiffies;
-	server->destroy = nfs4_destroy_server;
-out:
-	nfs_free_fattr(fattr);
-	return error;
-}
-
-/*
- * Create a version 4 volume record
- */
-static int nfs4_init_server(struct nfs_server *server,
-		const struct nfs_parsed_mount_data *data)
-{
-	struct rpc_timeout timeparms;
-	int error;
-
-	dprintk("--> nfs4_init_server()\n");
-
-	nfs_init_timeout_values(&timeparms, data->nfs_server.protocol,
-			data->timeo, data->retrans);
-
-	/* Initialise the client representation from the mount data */
-	server->flags = data->flags;
-	server->caps |= NFS_CAP_ATOMIC_OPEN|NFS_CAP_CHANGE_ATTR|NFS_CAP_POSIX_LOCK;
-	if (!(data->flags & NFS_MOUNT_NORDIRPLUS))
-			server->caps |= NFS_CAP_READDIRPLUS;
-	server->options = data->options;
-
-	/* Get a client record */
-	error = nfs4_set_client(server,
-			data->nfs_server.hostname,
-			(const struct sockaddr *)&data->nfs_server.address,
-			data->nfs_server.addrlen,
-			data->client_address,
-			data->auth_flavors[0],
-			data->nfs_server.protocol,
-			&timeparms,
-			data->minorversion,
-			data->net);
-	if (error < 0)
-		goto error;
-
-	/*
-	 * Don't use NFS uid/gid mapping if we're using AUTH_SYS or lower
-	 * authentication.
-	 */
-	if (nfs4_disable_idmapping && data->auth_flavors[0] == RPC_AUTH_UNIX)
-		server->caps |= NFS_CAP_UIDGID_NOMAP;
-
-	if (data->rsize)
-		server->rsize = nfs_block_size(data->rsize, NULL);
-	if (data->wsize)
-		server->wsize = nfs_block_size(data->wsize, NULL);
-
-	server->acregmin = data->acregmin * HZ;
-	server->acregmax = data->acregmax * HZ;
-	server->acdirmin = data->acdirmin * HZ;
-	server->acdirmax = data->acdirmax * HZ;
-
-	server->port = data->nfs_server.port;
-
-	error = nfs_init_server_rpcclient(server, &timeparms, data->auth_flavors[0]);
-
-error:
-	/* Done */
-	dprintk("<-- nfs4_init_server() = %d\n", error);
-	return error;
-}
-
-/*
- * Create a version 4 volume record
- * - keyed on server and FSID
- */
-struct nfs_server *nfs4_create_server(const struct nfs_parsed_mount_data *data,
-				      struct nfs_fh *mntfh)
-{
-	struct nfs_server *server;
-	int error;
-
-	dprintk("--> nfs4_create_server()\n");
-
-	server = nfs_alloc_server();
-	if (!server)
-		return ERR_PTR(-ENOMEM);
-
-	/* set up the general RPC client */
-	error = nfs4_init_server(server, data);
-	if (error < 0)
-		goto error;
-
-	error = nfs4_server_common_setup(server, mntfh);
-	if (error < 0)
-		goto error;
-
-	dprintk("<-- nfs4_create_server() = %p\n", server);
-	return server;
-
-error:
-	nfs_free_server(server);
-	dprintk("<-- nfs4_create_server() = error %d\n", error);
-	return ERR_PTR(error);
-}
-
-/*
- * Create an NFS4 referral server record
- */
-struct nfs_server *nfs4_create_referral_server(struct nfs_clone_mount *data,
-					       struct nfs_fh *mntfh)
-{
-	struct nfs_client *parent_client;
-	struct nfs_server *server, *parent_server;
-	int error;
-
-	dprintk("--> nfs4_create_referral_server()\n");
-
-	server = nfs_alloc_server();
-	if (!server)
-		return ERR_PTR(-ENOMEM);
-
-	parent_server = NFS_SB(data->sb);
-	parent_client = parent_server->nfs_client;
-
-	/* Initialise the client representation from the parent server */
-	nfs_server_copy_userdata(server, parent_server);
-	server->caps |= NFS_CAP_ATOMIC_OPEN|NFS_CAP_CHANGE_ATTR;
-
-	/* Get a client representation.
-	 * Note: NFSv4 always uses TCP, */
-	error = nfs4_set_client(server, data->hostname,
-				data->addr,
-				data->addrlen,
-				parent_client->cl_ipaddr,
-				data->authflavor,
-				rpc_protocol(parent_server->client),
-				parent_server->client->cl_timeout,
-				parent_client->cl_mvops->minor_version,
-				parent_client->cl_net);
-	if (error < 0)
-		goto error;
-
-	error = nfs_init_server_rpcclient(server, parent_server->client->cl_timeout, data->authflavor);
-	if (error < 0)
-		goto error;
-
-	error = nfs4_server_common_setup(server, mntfh);
-	if (error < 0)
-		goto error;
-
-	dprintk("<-- nfs_create_referral_server() = %p\n", server);
-	return server;
-
-error:
-	nfs_free_server(server);
-	dprintk("<-- nfs4_create_referral_server() = error %d\n", error);
-	return ERR_PTR(error);
-}
-
-#endif /* CONFIG_NFS_V4 */
+EXPORT_SYMBOL_GPL(nfs_create_server);
 
 /*
  * Clone an NFS2, NFS3 or NFS4 server record
@@ -1780,8 +1137,6 @@ struct nfs_server *nfs_clone_server(struct nfs_server *source,
 			flavor);
 	if (error < 0)
 		goto out_free_server;
-	if (!IS_ERR(source->client_acl))
-		nfs_init_server_aclclient(server);
 
 	/* probe the filesystem info for this server filesystem */
 	error = nfs_probe_fsinfo(server, fh, fattr_fsinfo);
@@ -1812,6 +1167,7 @@ out_free_server:
 	dprintk("<-- nfs_clone_server() = error %d\n", error);
 	return ERR_PTR(error);
 }
+EXPORT_SYMBOL_GPL(nfs_clone_server);
 
 void nfs_clients_init(struct net *net)
 {
@@ -1819,7 +1175,7 @@ void nfs_clients_init(struct net *net)
 
 	INIT_LIST_HEAD(&nn->nfs_client_list);
 	INIT_LIST_HEAD(&nn->nfs_volume_list);
-#ifdef CONFIG_NFS_V4
+#if IS_ENABLED(CONFIG_NFS_V4)
 	idr_init(&nn->cb_ident_idr);
 #endif
 	spin_lock_init(&nn->nfs_client_lock);
@@ -2091,7 +1447,3 @@ void nfs_fs_proc_exit(void)
 }
 
 #endif /* CONFIG_PROC_FS */
-
-module_param(nfs4_disable_idmapping, bool, 0644);
-MODULE_PARM_DESC(nfs4_disable_idmapping,
-		"Turn off NFSv4 idmapping when using 'sec=sys'");
diff --git a/fs/nfs/delegation.c b/fs/nfs/delegation.c
index bd3a9601d32..81c5eec3cf3 100644
--- a/fs/nfs/delegation.c
+++ b/fs/nfs/delegation.c
@@ -47,7 +47,7 @@ void nfs_mark_delegation_referenced(struct nfs_delegation *delegation)
  *
  * Returns one if inode has the indicated delegation, otherwise zero.
  */
-int nfs_have_delegation(struct inode *inode, fmode_t flags)
+int nfs4_have_delegation(struct inode *inode, fmode_t flags)
 {
 	struct nfs_delegation *delegation;
 	int ret = 0;
@@ -388,7 +388,7 @@ void nfs_inode_return_delegation_noreclaim(struct inode *inode)
  *
  * Returns zero on success, or a negative errno value.
  */
-int nfs_inode_return_delegation(struct inode *inode)
+int nfs4_inode_return_delegation(struct inode *inode)
 {
 	struct nfs_server *server = NFS_SERVER(inode);
 	struct nfs_inode *nfsi = NFS_I(inode);
@@ -417,9 +417,8 @@ static void nfs_mark_return_delegation(struct nfs_server *server,
  * @sb: sb to process
  *
  */
-void nfs_super_return_all_delegations(struct super_block *sb)
+void nfs_server_return_all_delegations(struct nfs_server *server)
 {
-	struct nfs_server *server = NFS_SB(sb);
 	struct nfs_client *clp = server->nfs_client;
 	struct nfs_delegation *delegation;
 
diff --git a/fs/nfs/delegation.h b/fs/nfs/delegation.h
index 72709c4193f..bbc6a4dba0d 100644
--- a/fs/nfs/delegation.h
+++ b/fs/nfs/delegation.h
@@ -8,7 +8,7 @@
 #ifndef FS_NFS_DELEGATION_H
 #define FS_NFS_DELEGATION_H
 
-#if defined(CONFIG_NFS_V4)
+#if IS_ENABLED(CONFIG_NFS_V4)
 /*
  * NFSv4 delegation
  */
@@ -33,12 +33,12 @@ enum {
 
 int nfs_inode_set_delegation(struct inode *inode, struct rpc_cred *cred, struct nfs_openres *res);
 void nfs_inode_reclaim_delegation(struct inode *inode, struct rpc_cred *cred, struct nfs_openres *res);
-int nfs_inode_return_delegation(struct inode *inode);
+int nfs4_inode_return_delegation(struct inode *inode);
 int nfs_async_inode_return_delegation(struct inode *inode, const nfs4_stateid *stateid);
 void nfs_inode_return_delegation_noreclaim(struct inode *inode);
 
 struct inode *nfs_delegation_find_inode(struct nfs_client *clp, const struct nfs_fh *fhandle);
-void nfs_super_return_all_delegations(struct super_block *sb);
+void nfs_server_return_all_delegations(struct nfs_server *);
 void nfs_expire_all_delegations(struct nfs_client *clp);
 void nfs_expire_all_delegation_types(struct nfs_client *clp, fmode_t flags);
 void nfs_expire_unreferenced_delegations(struct nfs_client *clp);
@@ -56,24 +56,13 @@ int nfs4_lock_delegation_recall(struct nfs4_state *state, struct file_lock *fl);
 bool nfs4_copy_delegation_stateid(nfs4_stateid *dst, struct inode *inode, fmode_t flags);
 
 void nfs_mark_delegation_referenced(struct nfs_delegation *delegation);
-int nfs_have_delegation(struct inode *inode, fmode_t flags);
+int nfs4_have_delegation(struct inode *inode, fmode_t flags);
 
-#else
-static inline int nfs_have_delegation(struct inode *inode, fmode_t flags)
-{
-	return 0;
-}
-
-static inline int nfs_inode_return_delegation(struct inode *inode)
-{
-	nfs_wb_all(inode);
-	return 0;
-}
 #endif
 
 static inline int nfs_have_delegated_attributes(struct inode *inode)
 {
-	return nfs_have_delegation(inode, FMODE_READ) &&
+	return NFS_PROTO(inode)->have_delegation(inode, FMODE_READ) &&
 		!(NFS_I(inode)->cache_validity & NFS_INO_REVAL_FORCED);
 }
 
diff --git a/fs/nfs/dir.c b/fs/nfs/dir.c
index f430057ff3b..1b2d7eb9379 100644
--- a/fs/nfs/dir.c
+++ b/fs/nfs/dir.c
@@ -17,6 +17,7 @@
  *  6 Jun 1999	Cache readdir lookups in the page cache. -DaveM
  */
 
+#include <linux/module.h>
 #include <linux/time.h>
 #include <linux/errno.h>
 #include <linux/stat.h>
@@ -46,16 +47,6 @@
 static int nfs_opendir(struct inode *, struct file *);
 static int nfs_closedir(struct inode *, struct file *);
 static int nfs_readdir(struct file *, void *, filldir_t);
-static struct dentry *nfs_lookup(struct inode *, struct dentry *, struct nameidata *);
-static int nfs_create(struct inode *, struct dentry *, umode_t, struct nameidata *);
-static int nfs_mkdir(struct inode *, struct dentry *, umode_t);
-static int nfs_rmdir(struct inode *, struct dentry *);
-static int nfs_unlink(struct inode *, struct dentry *);
-static int nfs_symlink(struct inode *, struct dentry *, const char *);
-static int nfs_link(struct dentry *, struct inode *, struct dentry *);
-static int nfs_mknod(struct inode *, struct dentry *, umode_t, dev_t);
-static int nfs_rename(struct inode *, struct dentry *,
-		      struct inode *, struct dentry *);
 static int nfs_fsync_dir(struct file *, loff_t, loff_t, int);
 static loff_t nfs_llseek_dir(struct file *, loff_t, int);
 static void nfs_readdir_clear_array(struct page*);
@@ -69,71 +60,10 @@ const struct file_operations nfs_dir_operations = {
 	.fsync		= nfs_fsync_dir,
 };
 
-const struct inode_operations nfs_dir_inode_operations = {
-	.create		= nfs_create,
-	.lookup		= nfs_lookup,
-	.link		= nfs_link,
-	.unlink		= nfs_unlink,
-	.symlink	= nfs_symlink,
-	.mkdir		= nfs_mkdir,
-	.rmdir		= nfs_rmdir,
-	.mknod		= nfs_mknod,
-	.rename		= nfs_rename,
-	.permission	= nfs_permission,
-	.getattr	= nfs_getattr,
-	.setattr	= nfs_setattr,
-};
-
 const struct address_space_operations nfs_dir_aops = {
 	.freepage = nfs_readdir_clear_array,
 };
 
-#ifdef CONFIG_NFS_V3
-const struct inode_operations nfs3_dir_inode_operations = {
-	.create		= nfs_create,
-	.lookup		= nfs_lookup,
-	.link		= nfs_link,
-	.unlink		= nfs_unlink,
-	.symlink	= nfs_symlink,
-	.mkdir		= nfs_mkdir,
-	.rmdir		= nfs_rmdir,
-	.mknod		= nfs_mknod,
-	.rename		= nfs_rename,
-	.permission	= nfs_permission,
-	.getattr	= nfs_getattr,
-	.setattr	= nfs_setattr,
-	.listxattr	= nfs3_listxattr,
-	.getxattr	= nfs3_getxattr,
-	.setxattr	= nfs3_setxattr,
-	.removexattr	= nfs3_removexattr,
-};
-#endif  /* CONFIG_NFS_V3 */
-
-#ifdef CONFIG_NFS_V4
-
-static struct dentry *nfs_atomic_lookup(struct inode *, struct dentry *, struct nameidata *);
-static int nfs_open_create(struct inode *dir, struct dentry *dentry, umode_t mode, struct nameidata *nd);
-const struct inode_operations nfs4_dir_inode_operations = {
-	.create		= nfs_open_create,
-	.lookup		= nfs_atomic_lookup,
-	.link		= nfs_link,
-	.unlink		= nfs_unlink,
-	.symlink	= nfs_symlink,
-	.mkdir		= nfs_mkdir,
-	.rmdir		= nfs_rmdir,
-	.mknod		= nfs_mknod,
-	.rename		= nfs_rename,
-	.permission	= nfs_permission,
-	.getattr	= nfs_getattr,
-	.setattr	= nfs_setattr,
-	.getxattr	= generic_getxattr,
-	.setxattr	= generic_setxattr,
-	.listxattr	= generic_listxattr,
-	.removexattr	= generic_removexattr,
-};
-
-#endif /* CONFIG_NFS_V4 */
-
 static struct nfs_open_dir_context *alloc_nfs_open_dir_context(struct inode *dir, struct rpc_cred *cred)
 {
 	struct nfs_open_dir_context *ctx;
@@ -520,7 +450,8 @@ void nfs_prime_dcache(struct dentry *parent, struct nfs_entry *entry)
 			nfs_refresh_inode(dentry->d_inode, entry->fattr);
 			goto out;
 		} else {
-			d_drop(dentry);
+			if (d_invalidate(dentry) != 0)
+				goto out;
 			dput(dentry);
 		}
 	}
@@ -940,7 +871,7 @@ out:
 	return res;
 }
 
-static loff_t nfs_llseek_dir(struct file *filp, loff_t offset, int origin)
+static loff_t nfs_llseek_dir(struct file *filp, loff_t offset, int whence)
 {
 	struct dentry *dentry = filp->f_path.dentry;
 	struct inode *inode = dentry->d_inode;
@@ -949,10 +880,10 @@ static loff_t nfs_llseek_dir(struct file *filp, loff_t offset, int origin)
 	dfprintk(FILE, "NFS: llseek dir(%s/%s, %lld, %d)\n",
 			dentry->d_parent->d_name.name,
 			dentry->d_name.name,
-			offset, origin);
+			offset, whence);
 
 	mutex_lock(&inode->i_mutex);
-	switch (origin) {
+	switch (whence) {
 		case 1:
 			offset += filp->f_pos;
 		case 0:
@@ -1006,6 +937,7 @@ void nfs_force_lookup_revalidate(struct inode *dir)
 {
 	NFS_I(dir)->cache_change_attribute++;
 }
+EXPORT_SYMBOL_GPL(nfs_force_lookup_revalidate);
 
 /*
  * A check for whether or not the parent directory has changed.
@@ -1029,27 +961,14 @@ static int nfs_check_verifier(struct inode *dir, struct dentry *dentry)
 }
 
 /*
- * Return the intent data that applies to this particular path component
- *
- * Note that the current set of intents only apply to the very last
- * component of the path and none of them is set before that last
- * component.
- */
-static inline unsigned int nfs_lookup_check_intent(struct nameidata *nd,
-						unsigned int mask)
-{
-	return nd->flags & mask;
-}
-
-/*
  * Use intent information to check whether or not we're going to do
  * an O_EXCL create using this path component.
  */
-static int nfs_is_exclusive_create(struct inode *dir, struct nameidata *nd)
+static int nfs_is_exclusive_create(struct inode *dir, unsigned int flags)
 {
 	if (NFS_PROTO(dir)->version == 2)
 		return 0;
-	return nd && nfs_lookup_check_intent(nd, LOOKUP_EXCL);
+	return flags & LOOKUP_EXCL;
 }
 
 /*
@@ -1060,28 +979,28 @@ static int nfs_is_exclusive_create(struct inode *dir, struct nameidata *nd)
  * particular file and the "nocto" mount flag is not set.
  *
  */
-static inline
-int nfs_lookup_verify_inode(struct inode *inode, struct nameidata *nd)
+static
+int nfs_lookup_verify_inode(struct inode *inode, unsigned int flags)
 {
 	struct nfs_server *server = NFS_SERVER(inode);
+	int ret;
 
 	if (IS_AUTOMOUNT(inode))
 		return 0;
-	if (nd != NULL) {
-		/* VFS wants an on-the-wire revalidation */
-		if (nd->flags & LOOKUP_REVAL)
-			goto out_force;
-		/* This is an open(2) */
-		if (nfs_lookup_check_intent(nd, LOOKUP_OPEN) != 0 &&
-				!(server->flags & NFS_MOUNT_NOCTO) &&
-				(S_ISREG(inode->i_mode) ||
-				 S_ISDIR(inode->i_mode)))
-			goto out_force;
-		return 0;
-	}
-	return nfs_revalidate_inode(server, inode);
+	/* VFS wants an on-the-wire revalidation */
+	if (flags & LOOKUP_REVAL)
+		goto out_force;
+	/* This is an open(2) */
+	if ((flags & LOOKUP_OPEN) && !(server->flags & NFS_MOUNT_NOCTO) &&
+	    (S_ISREG(inode->i_mode) || S_ISDIR(inode->i_mode)))
+		goto out_force;
+out:
+	return (inode->i_nlink == 0) ? -ENOENT : 0;
 out_force:
-	return __nfs_revalidate_inode(server, inode);
+	ret = __nfs_revalidate_inode(server, inode);
+	if (ret != 0)
+		return ret;
+	goto out;
 }
 
 /*
@@ -1093,10 +1012,10 @@ out_force:
  */
 static inline
 int nfs_neg_need_reval(struct inode *dir, struct dentry *dentry,
-		       struct nameidata *nd)
+		       unsigned int flags)
 {
 	/* Don't revalidate a negative dentry if we're creating a new file */
-	if (nd != NULL && nfs_lookup_check_intent(nd, LOOKUP_CREATE) != 0)
+	if (flags & LOOKUP_CREATE)
 		return 0;
 	if (NFS_SERVER(dir)->flags & NFS_MOUNT_LOOKUP_CACHE_NONEG)
 		return 1;
@@ -1114,7 +1033,7 @@ int nfs_neg_need_reval(struct inode *dir, struct dentry *dentry,
  * If the parent directory is seen to have changed, we throw out the
  * cached dentry and do a new lookup.
  */
-static int nfs_lookup_revalidate(struct dentry *dentry, struct nameidata *nd)
+static int nfs_lookup_revalidate(struct dentry *dentry, unsigned int flags)
 {
 	struct inode *dir;
 	struct inode *inode;
@@ -1123,7 +1042,7 @@ static int nfs_lookup_revalidate(struct dentry *dentry, struct nameidata *nd)
 	struct nfs_fattr *fattr = NULL;
 	int error;
 
-	if (nd->flags & LOOKUP_RCU)
+	if (flags & LOOKUP_RCU)
 		return -ECHILD;
 
 	parent = dget_parent(dentry);
@@ -1132,7 +1051,7 @@ static int nfs_lookup_revalidate(struct dentry *dentry, struct nameidata *nd)
 	inode = dentry->d_inode;
 
 	if (!inode) {
-		if (nfs_neg_need_reval(dir, dentry, nd))
+		if (nfs_neg_need_reval(dir, dentry, flags))
 			goto out_bad;
 		goto out_valid_noent;
 	}
@@ -1144,12 +1063,12 @@ static int nfs_lookup_revalidate(struct dentry *dentry, struct nameidata *nd)
 		goto out_bad;
 	}
 
-	if (nfs_have_delegation(inode, FMODE_READ))
+	if (NFS_PROTO(dir)->have_delegation(inode, FMODE_READ))
 		goto out_set_verifier;
 
 	/* Force a full look up iff the parent directory has changed */
-	if (!nfs_is_exclusive_create(dir, nd) && nfs_check_verifier(dir, dentry)) {
-		if (nfs_lookup_verify_inode(inode, nd))
+	if (!nfs_is_exclusive_create(dir, flags) && nfs_check_verifier(dir, dentry)) {
+		if (nfs_lookup_verify_inode(inode, flags))
 			goto out_zap_parent;
 		goto out_valid;
 	}
@@ -1187,6 +1106,8 @@ out_set_verifier:
 out_zap_parent:
 	nfs_zap_caches(dir);
  out_bad:
+	nfs_free_fattr(fattr);
+	nfs_free_fhandle(fhandle);
 	nfs_mark_for_revalidate(dir);
 	if (inode && S_ISDIR(inode->i_mode)) {
 		/* Purge readdir caches. */
@@ -1199,8 +1120,6 @@ out_zap_parent:
 		shrink_dcache_parent(dentry);
 	}
 	d_drop(dentry);
-	nfs_free_fattr(fattr);
-	nfs_free_fhandle(fhandle);
 	dput(parent);
 	dfprintk(LOOKUPCACHE, "NFS: %s(%s/%s) is invalid\n",
 			__func__, dentry->d_parent->d_name.name,
@@ -1242,11 +1161,14 @@ static int nfs_dentry_delete(const struct dentry *dentry)
 
 }
 
+/* Ensure that we revalidate inode->i_nlink */
 static void nfs_drop_nlink(struct inode *inode)
 {
 	spin_lock(&inode->i_lock);
-	if (inode->i_nlink > 0)
-		drop_nlink(inode);
+	/* drop the inode if we're reasonably sure this is the last link */
+	if (inode->i_nlink == 1)
+		clear_nlink(inode);
+	NFS_I(inode)->cache_validity |= NFS_INO_INVALID_ATTR;
 	spin_unlock(&inode->i_lock);
 }
 
@@ -1261,8 +1183,8 @@ static void nfs_dentry_iput(struct dentry *dentry, struct inode *inode)
 		NFS_I(inode)->cache_validity |= NFS_INO_INVALID_DATA;
 
 	if (dentry->d_flags & DCACHE_NFSFS_RENAMED) {
-		drop_nlink(inode);
 		nfs_complete_unlink(dentry, inode);
+		nfs_drop_nlink(inode);
 	}
 	iput(inode);
 }
@@ -1285,8 +1207,9 @@ const struct dentry_operations nfs_dentry_operations = {
 	.d_automount	= nfs_d_automount,
 	.d_release	= nfs_d_release,
 };
+EXPORT_SYMBOL_GPL(nfs_dentry_operations);
 
-static struct dentry *nfs_lookup(struct inode *dir, struct dentry * dentry, struct nameidata *nd)
+struct dentry *nfs_lookup(struct inode *dir, struct dentry * dentry, unsigned int flags)
 {
 	struct dentry *res;
 	struct dentry *parent;
@@ -1307,7 +1230,7 @@ static struct dentry *nfs_lookup(struct inode *dir, struct dentry * dentry, stru
 	 * If we're doing an exclusive create, optimize away the lookup
 	 * but don't hash the dentry.
 	 */
-	if (nfs_is_exclusive_create(dir, nd)) {
+	if (nfs_is_exclusive_create(dir, flags)) {
 		d_instantiate(dentry, NULL);
 		res = NULL;
 		goto out;
@@ -1352,9 +1275,10 @@ out:
 	nfs_free_fhandle(fhandle);
 	return res;
 }
+EXPORT_SYMBOL_GPL(nfs_lookup);
 
-#ifdef CONFIG_NFS_V4
-static int nfs4_lookup_revalidate(struct dentry *, struct nameidata *);
+#if IS_ENABLED(CONFIG_NFS_V4)
+static int nfs4_lookup_revalidate(struct dentry *, unsigned int);
 
 const struct dentry_operations nfs4_dentry_operations = {
 	.d_revalidate	= nfs4_lookup_revalidate,
@@ -1363,24 +1287,7 @@ const struct dentry_operations nfs4_dentry_operations = {
 	.d_automount	= nfs_d_automount,
 	.d_release	= nfs_d_release,
 };
-
-/*
- * Use intent information to determine whether we need to substitute
- * the NFSv4-style stateful OPEN for the LOOKUP call
- */
-static int is_atomic_open(struct nameidata *nd)
-{
-	if (nd == NULL || nfs_lookup_check_intent(nd, LOOKUP_OPEN) == 0)
-		return 0;
-	/* NFS does not (yet) have a stateful open for directories */
-	if (nd->flags & LOOKUP_DIRECTORY)
-		return 0;
-	/* Are we trying to write to a read only partition? */
-	if (__mnt_is_readonly(nd->path.mnt) &&
-	    (nd->intent.open.flags & (O_CREAT|O_TRUNC|O_ACCMODE)))
-		return 0;
-	return 1;
-}
+EXPORT_SYMBOL_GPL(nfs4_dentry_operations);
 
 static fmode_t flags_to_mode(int flags)
 {
@@ -1403,136 +1310,144 @@ static int do_open(struct inode *inode, struct file *filp)
 	return 0;
 }
 
-static int nfs_intent_set_file(struct nameidata *nd, struct nfs_open_context *ctx)
+static int nfs_finish_open(struct nfs_open_context *ctx,
+			   struct dentry *dentry,
+			   struct file *file, unsigned open_flags,
+			   int *opened)
 {
-	struct file *filp;
-	int ret = 0;
+	int err;
+
+	if (ctx->dentry != dentry) {
+		dput(ctx->dentry);
+		ctx->dentry = dget(dentry);
+	}
 
 	/* If the open_intent is for execute, we have an extra check to make */
 	if (ctx->mode & FMODE_EXEC) {
-		ret = nfs_may_open(ctx->dentry->d_inode,
-				ctx->cred,
-				nd->intent.open.flags);
-		if (ret < 0)
+		err = nfs_may_open(dentry->d_inode, ctx->cred, open_flags);
+		if (err < 0)
 			goto out;
 	}
-	filp = lookup_instantiate_filp(nd, ctx->dentry, do_open);
-	if (IS_ERR(filp))
-		ret = PTR_ERR(filp);
-	else
-		nfs_file_set_open_context(filp, ctx);
+
+	err = finish_open(file, dentry, do_open, opened);
+	if (err)
+		goto out;
+	nfs_file_set_open_context(file, ctx);
+
 out:
 	put_nfs_open_context(ctx);
-	return ret;
+	return err;
 }
 
-static struct dentry *nfs_atomic_lookup(struct inode *dir, struct dentry *dentry, struct nameidata *nd)
+int nfs_atomic_open(struct inode *dir, struct dentry *dentry,
+		    struct file *file, unsigned open_flags,
+		    umode_t mode, int *opened)
 {
 	struct nfs_open_context *ctx;
-	struct iattr attr;
-	struct dentry *res = NULL;
+	struct dentry *res;
+	struct iattr attr = { .ia_valid = ATTR_OPEN };
 	struct inode *inode;
-	int open_flags;
 	int err;
 
-	dfprintk(VFS, "NFS: atomic_lookup(%s/%ld), %s\n",
+	/* Expect a negative dentry */
+	BUG_ON(dentry->d_inode);
+
+	dfprintk(VFS, "NFS: atomic_open(%s/%ld), %s\n",
 			dir->i_sb->s_id, dir->i_ino, dentry->d_name.name);
 
-	/* Check that we are indeed trying to open this file */
-	if (!is_atomic_open(nd))
+	/* NFS only supports OPEN on regular files */
+	if ((open_flags & O_DIRECTORY)) {
+		if (!d_unhashed(dentry)) {
+			/*
+			 * Hashed negative dentry with O_DIRECTORY: dentry was
+			 * revalidated and is fine, no need to perform lookup
+			 * again
+			 */
+			return -ENOENT;
+		}
 		goto no_open;
-
-	if (dentry->d_name.len > NFS_SERVER(dir)->namelen) {
-		res = ERR_PTR(-ENAMETOOLONG);
-		goto out;
-	}
-
-	/* Let vfs_create() deal with O_EXCL. Instantiate, but don't hash
-	 * the dentry. */
-	if (nd->flags & LOOKUP_EXCL) {
-		d_instantiate(dentry, NULL);
-		goto out;
 	}
 
-	open_flags = nd->intent.open.flags;
-	attr.ia_valid = ATTR_OPEN;
-
-	ctx = create_nfs_open_context(dentry, open_flags);
-	res = ERR_CAST(ctx);
-	if (IS_ERR(ctx))
-		goto out;
+	if (dentry->d_name.len > NFS_SERVER(dir)->namelen)
+		return -ENAMETOOLONG;
 
-	if (nd->flags & LOOKUP_CREATE) {
-		attr.ia_mode = nd->intent.open.create_mode;
+	if (open_flags & O_CREAT) {
 		attr.ia_valid |= ATTR_MODE;
-		attr.ia_mode &= ~current_umask();
-	} else
-		open_flags &= ~(O_EXCL | O_CREAT);
-
+		attr.ia_mode = mode & ~current_umask();
+	}
 	if (open_flags & O_TRUNC) {
 		attr.ia_valid |= ATTR_SIZE;
 		attr.ia_size = 0;
 	}
 
-	/* Open the file on the server */
+	ctx = create_nfs_open_context(dentry, open_flags);
+	err = PTR_ERR(ctx);
+	if (IS_ERR(ctx))
+		goto out;
+
 	nfs_block_sillyrename(dentry->d_parent);
 	inode = NFS_PROTO(dir)->open_context(dir, ctx, open_flags, &attr);
+	d_drop(dentry);
 	if (IS_ERR(inode)) {
 		nfs_unblock_sillyrename(dentry->d_parent);
 		put_nfs_open_context(ctx);
-		switch (PTR_ERR(inode)) {
-			/* Make a negative dentry */
-			case -ENOENT:
-				d_add(dentry, NULL);
-				res = NULL;
-				goto out;
-			/* This turned out not to be a regular file */
-			case -EISDIR:
-			case -ENOTDIR:
+		err = PTR_ERR(inode);
+		switch (err) {
+		case -ENOENT:
+			d_add(dentry, NULL);
+			break;
+		case -EISDIR:
+		case -ENOTDIR:
+			goto no_open;
+		case -ELOOP:
+			if (!(open_flags & O_NOFOLLOW))
 				goto no_open;
-			case -ELOOP:
-				if (!(nd->intent.open.flags & O_NOFOLLOW))
-					goto no_open;
+			break;
 			/* case -EINVAL: */
-			default:
-				res = ERR_CAST(inode);
-				goto out;
+		default:
+			break;
 		}
+		goto out;
 	}
 	res = d_add_unique(dentry, inode);
-	nfs_unblock_sillyrename(dentry->d_parent);
-	if (res != NULL) {
-		dput(ctx->dentry);
-		ctx->dentry = dget(res);
+	if (res != NULL)
 		dentry = res;
-	}
-	err = nfs_intent_set_file(nd, ctx);
-	if (err < 0) {
-		if (res != NULL)
-			dput(res);
-		return ERR_PTR(err);
-	}
-out:
+
+	nfs_unblock_sillyrename(dentry->d_parent);
 	nfs_set_verifier(dentry, nfs_save_change_attribute(dir));
-	return res;
+
+	err = nfs_finish_open(ctx, dentry, file, open_flags, opened);
+
+	dput(res);
+out:
+	return err;
+
 no_open:
-	return nfs_lookup(dir, dentry, nd);
+	res = nfs_lookup(dir, dentry, 0);
+	err = PTR_ERR(res);
+	if (IS_ERR(res))
+		goto out;
+
+	return finish_no_open(file, res);
 }
+EXPORT_SYMBOL_GPL(nfs_atomic_open);
 
-static int nfs4_lookup_revalidate(struct dentry *dentry, struct nameidata *nd)
+static int nfs4_lookup_revalidate(struct dentry *dentry, unsigned int flags)
 {
 	struct dentry *parent = NULL;
 	struct inode *inode;
 	struct inode *dir;
-	int openflags, ret = 0;
+	int ret = 0;
 
-	if (nd->flags & LOOKUP_RCU)
+	if (flags & LOOKUP_RCU)
 		return -ECHILD;
 
-	inode = dentry->d_inode;
-	if (!is_atomic_open(nd) || d_mountpoint(dentry))
+	if (!(flags & LOOKUP_OPEN) || (flags & LOOKUP_DIRECTORY))
+		goto no_open;
+	if (d_mountpoint(dentry))
 		goto no_open;
 
+	inode = dentry->d_inode;
 	parent = dget_parent(dentry);
 	dir = parent->d_inode;
 
@@ -1540,7 +1455,7 @@ static int nfs4_lookup_revalidate(struct dentry *dentry, struct nameidata *nd)
 	 * optimize away revalidation of negative dentries.
 	 */
 	if (inode == NULL) {
-		if (!nfs_neg_need_reval(dir, dentry, nd))
+		if (!nfs_neg_need_reval(dir, dentry, flags))
 			ret = 1;
 		goto out;
 	}
@@ -1548,9 +1463,8 @@ static int nfs4_lookup_revalidate(struct dentry *dentry, struct nameidata *nd)
 	/* NFS only supports OPEN on regular files */
 	if (!S_ISREG(inode->i_mode))
 		goto no_open_dput;
-	openflags = nd->intent.open.flags;
 	/* We cannot do exclusive creation on a positive dentry */
-	if ((openflags & (O_CREAT|O_EXCL)) == (O_CREAT|O_EXCL))
+	if (flags & LOOKUP_EXCL)
 		goto no_open_dput;
 
 	/* Let f_op->open() actually open (and revalidate) the file */
@@ -1563,48 +1477,7 @@ out:
 no_open_dput:
 	dput(parent);
 no_open:
-	return nfs_lookup_revalidate(dentry, nd);
-}
-
-static int nfs_open_create(struct inode *dir, struct dentry *dentry,
-		umode_t mode, struct nameidata *nd)
-{
-	struct nfs_open_context *ctx = NULL;
-	struct iattr attr;
-	int error;
-	int open_flags = O_CREAT|O_EXCL;
-
-	dfprintk(VFS, "NFS: create(%s/%ld), %s\n",
-			dir->i_sb->s_id, dir->i_ino, dentry->d_name.name);
-
-	attr.ia_mode = mode;
-	attr.ia_valid = ATTR_MODE;
-
-	if (nd)
-		open_flags = nd->intent.open.flags;
-
-	ctx = create_nfs_open_context(dentry, open_flags);
-	error = PTR_ERR(ctx);
-	if (IS_ERR(ctx))
-		goto out_err_drop;
-
-	error = NFS_PROTO(dir)->create(dir, dentry, &attr, open_flags, ctx);
-	if (error != 0)
-		goto out_put_ctx;
-	if (nd) {
-		error = nfs_intent_set_file(nd, ctx);
-		if (error < 0)
-			goto out_err;
-	} else {
-		put_nfs_open_context(ctx);
-	}
-	return 0;
-out_put_ctx:
-	put_nfs_open_context(ctx);
-out_err_drop:
-	d_drop(dentry);
-out_err:
-	return error;
+	return nfs_lookup_revalidate(dentry, flags);
 }
 
 #endif /* CONFIG_NFSV4 */
@@ -1650,6 +1523,7 @@ out_error:
 	dput(parent);
 	return error;
 }
+EXPORT_SYMBOL_GPL(nfs_instantiate);
 
 /*
  * Following a failed create operation, we drop the dentry rather
@@ -1657,12 +1531,12 @@ out_error:
  * that the operation succeeded on the server, but an error in the
  * reply path made it appear to have failed.
  */
-static int nfs_create(struct inode *dir, struct dentry *dentry,
-		umode_t mode, struct nameidata *nd)
+int nfs_create(struct inode *dir, struct dentry *dentry,
+		umode_t mode, bool excl)
 {
 	struct iattr attr;
+	int open_flags = excl ? O_CREAT | O_EXCL : O_CREAT;
 	int error;
-	int open_flags = O_CREAT|O_EXCL;
 
 	dfprintk(VFS, "NFS: create(%s/%ld), %s\n",
 			dir->i_sb->s_id, dir->i_ino, dentry->d_name.name);
@@ -1670,10 +1544,7 @@ static int nfs_create(struct inode *dir, struct dentry *dentry,
 	attr.ia_mode = mode;
 	attr.ia_valid = ATTR_MODE;
 
-	if (nd)
-		open_flags = nd->intent.open.flags;
-
-	error = NFS_PROTO(dir)->create(dir, dentry, &attr, open_flags, NULL);
+	error = NFS_PROTO(dir)->create(dir, dentry, &attr, open_flags);
 	if (error != 0)
 		goto out_err;
 	return 0;
@@ -1681,11 +1552,12 @@ out_err:
 	d_drop(dentry);
 	return error;
 }
+EXPORT_SYMBOL_GPL(nfs_create);
 
 /*
  * See comments for nfs_proc_create regarding failed operations.
  */
-static int
+int
 nfs_mknod(struct inode *dir, struct dentry *dentry, umode_t mode, dev_t rdev)
 {
 	struct iattr attr;
@@ -1708,11 +1580,12 @@ out_err:
 	d_drop(dentry);
 	return status;
 }
+EXPORT_SYMBOL_GPL(nfs_mknod);
 
 /*
  * See comments for nfs_proc_create regarding failed operations.
  */
-static int nfs_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode)
+int nfs_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode)
 {
 	struct iattr attr;
 	int error;
@@ -1731,6 +1604,7 @@ out_err:
 	d_drop(dentry);
 	return error;
 }
+EXPORT_SYMBOL_GPL(nfs_mkdir);
 
 static void nfs_dentry_handle_enoent(struct dentry *dentry)
 {
@@ -1738,7 +1612,7 @@ static void nfs_dentry_handle_enoent(struct dentry *dentry)
 		d_delete(dentry);
 }
 
-static int nfs_rmdir(struct inode *dir, struct dentry *dentry)
+int nfs_rmdir(struct inode *dir, struct dentry *dentry)
 {
 	int error;
 
@@ -1754,6 +1628,7 @@ static int nfs_rmdir(struct inode *dir, struct dentry *dentry)
 
 	return error;
 }
+EXPORT_SYMBOL_GPL(nfs_rmdir);
 
 /*
  * Remove a file after making sure there are no pending writes,
@@ -1778,12 +1653,10 @@ static int nfs_safe_remove(struct dentry *dentry)
 	}
 
 	if (inode != NULL) {
-		nfs_inode_return_delegation(inode);
+		NFS_PROTO(inode)->return_delegation(inode);
 		error = NFS_PROTO(dir)->remove(dir, &dentry->d_name);
-		/* The VFS may want to delete this inode */
 		if (error == 0)
 			nfs_drop_nlink(inode);
-		nfs_mark_for_revalidate(inode);
 	} else
 		error = NFS_PROTO(dir)->remove(dir, &dentry->d_name);
 	if (error == -ENOENT)
@@ -1797,7 +1670,7 @@ out:
  *
  *  If sillyrename() returns 0, we do nothing, otherwise we unlink.
  */
-static int nfs_unlink(struct inode *dir, struct dentry *dentry)
+int nfs_unlink(struct inode *dir, struct dentry *dentry)
 {
 	int error;
 	int need_rehash = 0;
@@ -1825,6 +1698,7 @@ static int nfs_unlink(struct inode *dir, struct dentry *dentry)
 		d_rehash(dentry);
 	return error;
 }
+EXPORT_SYMBOL_GPL(nfs_unlink);
 
 /*
  * To create a symbolic link, most file systems instantiate a new inode,
@@ -1841,7 +1715,7 @@ static int nfs_unlink(struct inode *dir, struct dentry *dentry)
  * now have a new file handle and can instantiate an in-core NFS inode
  * and move the raw page into its mapping.
  */
-static int nfs_symlink(struct inode *dir, struct dentry *dentry, const char *symname)
+int nfs_symlink(struct inode *dir, struct dentry *dentry, const char *symname)
 {
 	struct pagevec lru_pvec;
 	struct page *page;
@@ -1895,8 +1769,9 @@ static int nfs_symlink(struct inode *dir, struct dentry *dentry, const char *sym
 
 	return 0;
 }
+EXPORT_SYMBOL_GPL(nfs_symlink);
 
-static int 
+int
 nfs_link(struct dentry *old_dentry, struct inode *dir, struct dentry *dentry)
 {
 	struct inode *inode = old_dentry->d_inode;
@@ -1906,7 +1781,7 @@ nfs_link(struct dentry *old_dentry, struct inode *dir, struct dentry *dentry)
 		old_dentry->d_parent->d_name.name, old_dentry->d_name.name,
 		dentry->d_parent->d_name.name, dentry->d_name.name);
 
-	nfs_inode_return_delegation(inode);
+	NFS_PROTO(inode)->return_delegation(inode);
 
 	d_drop(dentry);
 	error = NFS_PROTO(dir)->link(inode, dir, &dentry->d_name);
@@ -1916,6 +1791,7 @@ nfs_link(struct dentry *old_dentry, struct inode *dir, struct dentry *dentry)
 	}
 	return error;
 }
+EXPORT_SYMBOL_GPL(nfs_link);
 
 /*
  * RENAME
@@ -1941,7 +1817,7 @@ nfs_link(struct dentry *old_dentry, struct inode *dir, struct dentry *dentry)
  * If these conditions are met, we can drop the dentries before doing
  * the rename.
  */
-static int nfs_rename(struct inode *old_dir, struct dentry *old_dentry,
+int nfs_rename(struct inode *old_dir, struct dentry *old_dentry,
 		      struct inode *new_dir, struct dentry *new_dentry)
 {
 	struct inode *old_inode = old_dentry->d_inode;
@@ -1990,9 +1866,9 @@ static int nfs_rename(struct inode *old_dir, struct dentry *old_dentry,
 		}
 	}
 
-	nfs_inode_return_delegation(old_inode);
+	NFS_PROTO(old_inode)->return_delegation(old_inode);
 	if (new_inode != NULL)
-		nfs_inode_return_delegation(new_inode);
+		NFS_PROTO(new_inode)->return_delegation(new_inode);
 
 	error = NFS_PROTO(old_dir)->rename(old_dir, &old_dentry->d_name,
 					   new_dir, &new_dentry->d_name);
@@ -2014,6 +1890,7 @@ out:
 		dput(dentry);
 	return error;
 }
+EXPORT_SYMBOL_GPL(nfs_rename);
 
 static DEFINE_SPINLOCK(nfs_access_lru_lock);
 static LIST_HEAD(nfs_access_lru_list);
@@ -2114,6 +1991,7 @@ void nfs_access_zap_cache(struct inode *inode)
 	spin_unlock(&nfs_access_lru_lock);
 	nfs_access_free_list(&head);
 }
+EXPORT_SYMBOL_GPL(nfs_access_zap_cache);
 
 static struct nfs_access_entry *nfs_access_search_rbtree(struct inode *inode, struct rpc_cred *cred)
 {
@@ -2201,7 +2079,7 @@ found:
 	nfs_access_free_entry(entry);
 }
 
-static void nfs_access_add_cache(struct inode *inode, struct nfs_access_entry *set)
+void nfs_access_add_cache(struct inode *inode, struct nfs_access_entry *set)
 {
 	struct nfs_access_entry *cache = kmalloc(sizeof(*cache), GFP_KERNEL);
 	if (cache == NULL)
@@ -2227,6 +2105,20 @@ static void nfs_access_add_cache(struct inode *inode, struct nfs_access_entry *s
 		spin_unlock(&nfs_access_lru_lock);
 	}
 }
+EXPORT_SYMBOL_GPL(nfs_access_add_cache);
+
+void nfs_access_set_mask(struct nfs_access_entry *entry, u32 access_result)
+{
+	entry->mask = 0;
+	if (access_result & NFS4_ACCESS_READ)
+		entry->mask |= MAY_READ;
+	if (access_result &
+	    (NFS4_ACCESS_MODIFY | NFS4_ACCESS_EXTEND | NFS4_ACCESS_DELETE))
+		entry->mask |= MAY_WRITE;
+	if (access_result & (NFS4_ACCESS_LOOKUP|NFS4_ACCESS_EXECUTE))
+		entry->mask |= MAY_EXEC;
+}
+EXPORT_SYMBOL_GPL(nfs_access_set_mask);
 
 static int nfs_do_access(struct inode *inode, struct rpc_cred *cred, int mask)
 {
@@ -2261,12 +2153,16 @@ static int nfs_open_permission_mask(int openflags)
 {
 	int mask = 0;
 
-	if ((openflags & O_ACCMODE) != O_WRONLY)
-		mask |= MAY_READ;
-	if ((openflags & O_ACCMODE) != O_RDONLY)
-		mask |= MAY_WRITE;
-	if (openflags & __FMODE_EXEC)
-		mask |= MAY_EXEC;
+	if (openflags & __FMODE_EXEC) {
+		/* ONLY check exec rights */
+		mask = MAY_EXEC;
+	} else {
+		if ((openflags & O_ACCMODE) != O_WRONLY)
+			mask |= MAY_READ;
+		if ((openflags & O_ACCMODE) != O_RDONLY)
+			mask |= MAY_WRITE;
+	}
+
 	return mask;
 }
 
@@ -2274,6 +2170,7 @@ int nfs_may_open(struct inode *inode, struct rpc_cred *cred, int openflags)
 {
 	return nfs_do_access(inode, cred, nfs_open_permission_mask(openflags));
 }
+EXPORT_SYMBOL_GPL(nfs_may_open);
 
 int nfs_permission(struct inode *inode, int mask)
 {
@@ -2333,6 +2230,7 @@ out_notsup:
 		res = generic_permission(inode, mask);
 	goto out;
 }
+EXPORT_SYMBOL_GPL(nfs_permission);
 
 /*
  * Local variables:
diff --git a/fs/nfs/direct.c b/fs/nfs/direct.c
index 48253372ab1..0bd7a55a5f0 100644
--- a/fs/nfs/direct.c
+++ b/fs/nfs/direct.c
@@ -46,6 +46,7 @@
 #include <linux/kref.h>
 #include <linux/slab.h>
 #include <linux/task_io_accounting_ops.h>
+#include <linux/module.h>
 
 #include <linux/nfs_fs.h>
 #include <linux/nfs_page.h>
@@ -78,6 +79,7 @@ struct nfs_direct_req {
 	atomic_t		io_count;	/* i/os we're waiting for */
 	spinlock_t		lock;		/* protect completion state */
 	ssize_t			count,		/* bytes actually processed */
+				bytes_left,	/* bytes left to be sent */
 				error;		/* any reported error */
 	struct completion	completion;	/* wait for i/o completion */
 
@@ -115,17 +117,28 @@ static inline int put_dreq(struct nfs_direct_req *dreq)
  * @nr_segs: size of iovec array
  *
  * The presence of this routine in the address space ops vector means
- * the NFS client supports direct I/O.  However, we shunt off direct
- * read and write requests before the VFS gets them, so this method
- * should never be called.
+ * the NFS client supports direct I/O. However, for most direct IO, we
+ * shunt off direct read and write requests before the VFS gets them,
+ * so this method is only ever called for swap.
  */
 ssize_t nfs_direct_IO(int rw, struct kiocb *iocb, const struct iovec *iov, loff_t pos, unsigned long nr_segs)
 {
+#ifndef CONFIG_NFS_SWAP
 	dprintk("NFS: nfs_direct_IO (%s) off/no(%Ld/%lu) EINVAL\n",
 			iocb->ki_filp->f_path.dentry->d_name.name,
 			(long long) pos, nr_segs);
 
 	return -EINVAL;
+#else
+	VM_BUG_ON(iocb->ki_left != PAGE_SIZE);
+	VM_BUG_ON(iocb->ki_nbytes != PAGE_SIZE);
+
+	if (rw == READ || rw == KERNEL_READ)
+		return nfs_file_direct_read(iocb, iov, nr_segs, pos,
+				rw == READ ? true : false);
+	return nfs_file_direct_write(iocb, iov, nr_segs, pos,
+				rw == WRITE ? true : false);
+#endif /* CONFIG_NFS_SWAP */
 }
 
 static void nfs_direct_release_pages(struct page **pages, unsigned int npages)
@@ -179,6 +192,12 @@ static void nfs_direct_req_release(struct nfs_direct_req *dreq)
 	kref_put(&dreq->kref, nfs_direct_req_free);
 }
 
+ssize_t nfs_dreq_bytes_left(struct nfs_direct_req *dreq)
+{
+	return dreq->bytes_left;
+}
+EXPORT_SYMBOL_GPL(nfs_dreq_bytes_left);
+
 /*
  * Collects and returns the final error value/byte-count.
  */
@@ -247,21 +266,8 @@ static void nfs_direct_read_completion(struct nfs_pgio_header *hdr)
 		struct nfs_page *req = nfs_list_entry(hdr->pages.next);
 		struct page *page = req->wb_page;
 
-		if (test_bit(NFS_IOHDR_EOF, &hdr->flags)) {
-			if (bytes > hdr->good_bytes)
-				zero_user(page, 0, PAGE_SIZE);
-			else if (hdr->good_bytes - bytes < PAGE_SIZE)
-				zero_user_segment(page,
-					hdr->good_bytes & ~PAGE_MASK,
-					PAGE_SIZE);
-		}
-		if (!PageCompound(page)) {
-			if (test_bit(NFS_IOHDR_ERROR, &hdr->flags)) {
-				if (bytes < hdr->good_bytes)
-					set_page_dirty(page);
-			} else
-				set_page_dirty(page);
-		}
+		if (!PageCompound(page) && bytes < hdr->good_bytes)
+			set_page_dirty(page);
 		bytes += req->wb_bytes;
 		nfs_list_remove_request(req);
 		nfs_direct_readpage_release(req);
@@ -303,7 +309,7 @@ static const struct nfs_pgio_completion_ops nfs_direct_read_completion_ops = {
  */
 static ssize_t nfs_direct_read_schedule_segment(struct nfs_pageio_descriptor *desc,
 						const struct iovec *iov,
-						loff_t pos)
+						loff_t pos, bool uio)
 {
 	struct nfs_direct_req *dreq = desc->pg_dreq;
 	struct nfs_open_context *ctx = dreq->ctx;
@@ -331,12 +337,20 @@ static ssize_t nfs_direct_read_schedule_segment(struct nfs_pageio_descriptor *de
 					  GFP_KERNEL);
 		if (!pagevec)
 			break;
-		down_read(&current->mm->mmap_sem);
-		result = get_user_pages(current, current->mm, user_addr,
+		if (uio) {
+			down_read(&current->mm->mmap_sem);
+			result = get_user_pages(current, current->mm, user_addr,
 					npages, 1, 0, pagevec, NULL);
-		up_read(&current->mm->mmap_sem);
-		if (result < 0)
-			break;
+			up_read(&current->mm->mmap_sem);
+			if (result < 0)
+				break;
+		} else {
+			WARN_ON(npages != 1);
+			result = get_kernel_page(user_addr, 1, pagevec);
+			if (WARN_ON(result != 1))
+				break;
+		}
+
 		if ((unsigned)result < npages) {
 			bytes = result * PAGE_SIZE;
 			if (bytes <= pgbase) {
@@ -371,6 +385,7 @@ static ssize_t nfs_direct_read_schedule_segment(struct nfs_pageio_descriptor *de
 			user_addr += req_len;
 			pos += req_len;
 			count -= req_len;
+			dreq->bytes_left -= req_len;
 		}
 		/* The nfs_page now hold references to these pages */
 		nfs_direct_release_pages(pagevec, npages);
@@ -386,21 +401,21 @@ static ssize_t nfs_direct_read_schedule_segment(struct nfs_pageio_descriptor *de
 static ssize_t nfs_direct_read_schedule_iovec(struct nfs_direct_req *dreq,
 					      const struct iovec *iov,
 					      unsigned long nr_segs,
-					      loff_t pos)
+					      loff_t pos, bool uio)
 {
 	struct nfs_pageio_descriptor desc;
 	ssize_t result = -EINVAL;
 	size_t requested_bytes = 0;
 	unsigned long seg;
 
-	nfs_pageio_init_read(&desc, dreq->inode,
+	NFS_PROTO(dreq->inode)->read_pageio_init(&desc, dreq->inode,
 			     &nfs_direct_read_completion_ops);
 	get_dreq(dreq);
 	desc.pg_dreq = dreq;
 
 	for (seg = 0; seg < nr_segs; seg++) {
 		const struct iovec *vec = &iov[seg];
-		result = nfs_direct_read_schedule_segment(&desc, vec, pos);
+		result = nfs_direct_read_schedule_segment(&desc, vec, pos, uio);
 		if (result < 0)
 			break;
 		requested_bytes += result;
@@ -426,28 +441,33 @@ static ssize_t nfs_direct_read_schedule_iovec(struct nfs_direct_req *dreq,
 }
 
 static ssize_t nfs_direct_read(struct kiocb *iocb, const struct iovec *iov,
-			       unsigned long nr_segs, loff_t pos)
+			       unsigned long nr_segs, loff_t pos, bool uio)
 {
 	ssize_t result = -ENOMEM;
 	struct inode *inode = iocb->ki_filp->f_mapping->host;
 	struct nfs_direct_req *dreq;
+	struct nfs_lock_context *l_ctx;
 
 	dreq = nfs_direct_req_alloc();
 	if (dreq == NULL)
 		goto out;
 
 	dreq->inode = inode;
+	dreq->bytes_left = iov_length(iov, nr_segs);
 	dreq->ctx = get_nfs_open_context(nfs_file_open_context(iocb->ki_filp));
-	dreq->l_ctx = nfs_get_lock_context(dreq->ctx);
-	if (dreq->l_ctx == NULL)
+	l_ctx = nfs_get_lock_context(dreq->ctx);
+	if (IS_ERR(l_ctx)) {
+		result = PTR_ERR(l_ctx);
 		goto out_release;
+	}
+	dreq->l_ctx = l_ctx;
 	if (!is_sync_kiocb(iocb))
 		dreq->iocb = iocb;
 
-	result = nfs_direct_read_schedule_iovec(dreq, iov, nr_segs, pos);
+	NFS_I(inode)->read_io += iov_length(iov, nr_segs);
+	result = nfs_direct_read_schedule_iovec(dreq, iov, nr_segs, pos, uio);
 	if (!result)
 		result = nfs_direct_wait(dreq);
-	NFS_I(inode)->read_io += result;
 out_release:
 	nfs_direct_req_release(dreq);
 out:
@@ -460,7 +480,7 @@ static void nfs_inode_dio_write_done(struct inode *inode)
 	inode_dio_done(inode);
 }
 
-#if defined(CONFIG_NFS_V3) || defined(CONFIG_NFS_V4)
+#if IS_ENABLED(CONFIG_NFS_V3) || IS_ENABLED(CONFIG_NFS_V4)
 static void nfs_direct_write_reschedule(struct nfs_direct_req *dreq)
 {
 	struct nfs_pageio_descriptor desc;
@@ -478,7 +498,7 @@ static void nfs_direct_write_reschedule(struct nfs_direct_req *dreq)
 	dreq->count = 0;
 	get_dreq(dreq);
 
-	nfs_pageio_init_write(&desc, dreq->inode, FLUSH_STABLE,
+	NFS_PROTO(dreq->inode)->write_pageio_init(&desc, dreq->inode, FLUSH_STABLE,
 			      &nfs_direct_write_completion_ops);
 	desc.pg_dreq = dreq;
 
@@ -610,7 +630,7 @@ static void nfs_direct_write_complete(struct nfs_direct_req *dreq, struct inode
  */
 static ssize_t nfs_direct_write_schedule_segment(struct nfs_pageio_descriptor *desc,
 						 const struct iovec *iov,
-						 loff_t pos)
+						 loff_t pos, bool uio)
 {
 	struct nfs_direct_req *dreq = desc->pg_dreq;
 	struct nfs_open_context *ctx = dreq->ctx;
@@ -638,12 +658,19 @@ static ssize_t nfs_direct_write_schedule_segment(struct nfs_pageio_descriptor *d
 		if (!pagevec)
 			break;
 
-		down_read(&current->mm->mmap_sem);
-		result = get_user_pages(current, current->mm, user_addr,
-					npages, 0, 0, pagevec, NULL);
-		up_read(&current->mm->mmap_sem);
-		if (result < 0)
-			break;
+		if (uio) {
+			down_read(&current->mm->mmap_sem);
+			result = get_user_pages(current, current->mm, user_addr,
+						npages, 0, 0, pagevec, NULL);
+			up_read(&current->mm->mmap_sem);
+			if (result < 0)
+				break;
+		} else {
+			WARN_ON(npages != 1);
+			result = get_kernel_page(user_addr, 0, pagevec);
+			if (WARN_ON(result != 1))
+				break;
+		}
 
 		if ((unsigned)result < npages) {
 			bytes = result * PAGE_SIZE;
@@ -680,6 +707,7 @@ static ssize_t nfs_direct_write_schedule_segment(struct nfs_pageio_descriptor *d
 			user_addr += req_len;
 			pos += req_len;
 			count -= req_len;
+			dreq->bytes_left -= req_len;
 		}
 		/* The nfs_page now hold references to these pages */
 		nfs_direct_release_pages(pagevec, npages);
@@ -774,7 +802,7 @@ static const struct nfs_pgio_completion_ops nfs_direct_write_completion_ops = {
 static ssize_t nfs_direct_write_schedule_iovec(struct nfs_direct_req *dreq,
 					       const struct iovec *iov,
 					       unsigned long nr_segs,
-					       loff_t pos)
+					       loff_t pos, bool uio)
 {
 	struct nfs_pageio_descriptor desc;
 	struct inode *inode = dreq->inode;
@@ -782,15 +810,16 @@ static ssize_t nfs_direct_write_schedule_iovec(struct nfs_direct_req *dreq,
 	size_t requested_bytes = 0;
 	unsigned long seg;
 
-	nfs_pageio_init_write(&desc, inode, FLUSH_COND_STABLE,
+	NFS_PROTO(inode)->write_pageio_init(&desc, inode, FLUSH_COND_STABLE,
 			      &nfs_direct_write_completion_ops);
 	desc.pg_dreq = dreq;
 	get_dreq(dreq);
 	atomic_inc(&inode->i_dio_count);
 
+	NFS_I(dreq->inode)->write_io += iov_length(iov, nr_segs);
 	for (seg = 0; seg < nr_segs; seg++) {
 		const struct iovec *vec = &iov[seg];
-		result = nfs_direct_write_schedule_segment(&desc, vec, pos);
+		result = nfs_direct_write_schedule_segment(&desc, vec, pos, uio);
 		if (result < 0)
 			break;
 		requested_bytes += result;
@@ -799,7 +828,6 @@ static ssize_t nfs_direct_write_schedule_iovec(struct nfs_direct_req *dreq,
 		pos += vec->iov_len;
 	}
 	nfs_pageio_complete(&desc);
-	NFS_I(dreq->inode)->write_io += desc.pg_bytes_written;
 
 	/*
 	 * If no bytes were started, return the error, and let the
@@ -818,25 +846,30 @@ static ssize_t nfs_direct_write_schedule_iovec(struct nfs_direct_req *dreq,
 
 static ssize_t nfs_direct_write(struct kiocb *iocb, const struct iovec *iov,
 				unsigned long nr_segs, loff_t pos,
-				size_t count)
+				size_t count, bool uio)
 {
 	ssize_t result = -ENOMEM;
 	struct inode *inode = iocb->ki_filp->f_mapping->host;
 	struct nfs_direct_req *dreq;
+	struct nfs_lock_context *l_ctx;
 
 	dreq = nfs_direct_req_alloc();
 	if (!dreq)
 		goto out;
 
 	dreq->inode = inode;
+	dreq->bytes_left = count;
 	dreq->ctx = get_nfs_open_context(nfs_file_open_context(iocb->ki_filp));
-	dreq->l_ctx = nfs_get_lock_context(dreq->ctx);
-	if (dreq->l_ctx == NULL)
+	l_ctx = nfs_get_lock_context(dreq->ctx);
+	if (IS_ERR(l_ctx)) {
+		result = PTR_ERR(l_ctx);
 		goto out_release;
+	}
+	dreq->l_ctx = l_ctx;
 	if (!is_sync_kiocb(iocb))
 		dreq->iocb = iocb;
 
-	result = nfs_direct_write_schedule_iovec(dreq, iov, nr_segs, pos);
+	result = nfs_direct_write_schedule_iovec(dreq, iov, nr_segs, pos, uio);
 	if (!result)
 		result = nfs_direct_wait(dreq);
 out_release:
@@ -867,7 +900,7 @@ out:
  * cache.
  */
 ssize_t nfs_file_direct_read(struct kiocb *iocb, const struct iovec *iov,
-				unsigned long nr_segs, loff_t pos)
+				unsigned long nr_segs, loff_t pos, bool uio)
 {
 	ssize_t retval = -EINVAL;
 	struct file *file = iocb->ki_filp;
@@ -892,7 +925,7 @@ ssize_t nfs_file_direct_read(struct kiocb *iocb, const struct iovec *iov,
 
 	task_io_account_read(count);
 
-	retval = nfs_direct_read(iocb, iov, nr_segs, pos);
+	retval = nfs_direct_read(iocb, iov, nr_segs, pos, uio);
 	if (retval > 0)
 		iocb->ki_pos = pos + retval;
 
@@ -923,7 +956,7 @@ out:
  * is no atomic O_APPEND write facility in the NFS protocol.
  */
 ssize_t nfs_file_direct_write(struct kiocb *iocb, const struct iovec *iov,
-				unsigned long nr_segs, loff_t pos)
+				unsigned long nr_segs, loff_t pos, bool uio)
 {
 	ssize_t retval = -EINVAL;
 	struct file *file = iocb->ki_filp;
@@ -955,7 +988,7 @@ ssize_t nfs_file_direct_write(struct kiocb *iocb, const struct iovec *iov,
 
 	task_io_account_write(count);
 
-	retval = nfs_direct_write(iocb, iov, nr_segs, pos, count);
+	retval = nfs_direct_write(iocb, iov, nr_segs, pos, count, uio);
 	if (retval > 0) {
 		struct inode *inode = mapping->host;
 
diff --git a/fs/nfs/dns_resolve.c b/fs/nfs/dns_resolve.c
index b3924b8a600..ca4b11ec87a 100644
--- a/fs/nfs/dns_resolve.c
+++ b/fs/nfs/dns_resolve.c
@@ -8,6 +8,7 @@
 
 #ifdef CONFIG_NFS_USE_KERNEL_DNS
 
+#include <linux/module.h>
 #include <linux/sunrpc/clnt.h>
 #include <linux/dns_resolver.h>
 #include "dns_resolve.h"
@@ -27,9 +28,11 @@ ssize_t nfs_dns_resolve_name(struct net *net, char *name, size_t namelen,
 	kfree(ip_addr);
 	return ret;
 }
+EXPORT_SYMBOL_GPL(nfs_dns_resolve_name);
 
 #else
 
+#include <linux/module.h>
 #include <linux/hash.h>
 #include <linux/string.h>
 #include <linux/kmod.h>
@@ -214,7 +217,7 @@ static int nfs_dns_parse(struct cache_detail *cd, char *buf, int buflen)
 {
 	char buf1[NFS_DNS_HOSTNAME_MAXLEN+1];
 	struct nfs_dns_ent key, *item;
-	unsigned long ttl;
+	unsigned int ttl;
 	ssize_t len;
 	int ret = -EINVAL;
 
@@ -237,7 +240,8 @@ static int nfs_dns_parse(struct cache_detail *cd, char *buf, int buflen)
 	key.namelen = len;
 	memset(&key.h, 0, sizeof(key.h));
 
-	ttl = get_expiry(&buf);
+	if (get_uint(&buf, &ttl) < 0)
+		goto out;
 	if (ttl == 0)
 		goto out;
 	key.h.expiry_time = ttl + seconds_since_boot();
@@ -345,6 +349,7 @@ ssize_t nfs_dns_resolve_name(struct net *net, char *name,
 		ret = -ESRCH;
 	return ret;
 }
+EXPORT_SYMBOL_GPL(nfs_dns_resolve_name);
 
 int nfs_dns_resolver_cache_init(struct net *net)
 {
diff --git a/fs/nfs/file.c b/fs/nfs/file.c
index a6708e6b438..3c2b893665b 100644
--- a/fs/nfs/file.c
+++ b/fs/nfs/file.c
@@ -16,6 +16,7 @@
  *  nfs regular file handling functions
  */
 
+#include <linux/module.h>
 #include <linux/time.h>
 #include <linux/kernel.h>
 #include <linux/errno.h>
@@ -35,42 +36,24 @@
 #include "internal.h"
 #include "iostat.h"
 #include "fscache.h"
-#include "pnfs.h"
 
 #define NFSDBG_FACILITY		NFSDBG_FILE
 
 static const struct vm_operations_struct nfs_file_vm_ops;
 
-const struct inode_operations nfs_file_inode_operations = {
-	.permission	= nfs_permission,
-	.getattr	= nfs_getattr,
-	.setattr	= nfs_setattr,
-};
-
-#ifdef CONFIG_NFS_V3
-const struct inode_operations nfs3_file_inode_operations = {
-	.permission	= nfs_permission,
-	.getattr	= nfs_getattr,
-	.setattr	= nfs_setattr,
-	.listxattr	= nfs3_listxattr,
-	.getxattr	= nfs3_getxattr,
-	.setxattr	= nfs3_setxattr,
-	.removexattr	= nfs3_removexattr,
-};
-#endif  /* CONFIG_NFS_v3 */
-
 /* Hack for future NFS swap support */
 #ifndef IS_SWAPFILE
 # define IS_SWAPFILE(inode)	(0)
 #endif
 
-static int nfs_check_flags(int flags)
+int nfs_check_flags(int flags)
 {
 	if ((flags & (O_APPEND | O_DIRECT)) == (O_APPEND | O_DIRECT))
 		return -EINVAL;
 
 	return 0;
 }
+EXPORT_SYMBOL_GPL(nfs_check_flags);
 
 /*
  * Open file
@@ -93,7 +76,7 @@ nfs_file_open(struct inode *inode, struct file *filp)
 	return res;
 }
 
-static int
+int
 nfs_file_release(struct inode *inode, struct file *filp)
 {
 	dprintk("NFS: release(%s/%s)\n",
@@ -103,6 +86,7 @@ nfs_file_release(struct inode *inode, struct file *filp)
 	nfs_inc_stats(inode, NFSIOS_VFSRELEASE);
 	return nfs_release(inode, filp);
 }
+EXPORT_SYMBOL_GPL(nfs_file_release);
 
 /**
  * nfs_revalidate_size - Revalidate the file size
@@ -135,18 +119,18 @@ force_reval:
 	return __nfs_revalidate_inode(server, inode);
 }
 
-static loff_t nfs_file_llseek(struct file *filp, loff_t offset, int origin)
+loff_t nfs_file_llseek(struct file *filp, loff_t offset, int whence)
 {
 	dprintk("NFS: llseek file(%s/%s, %lld, %d)\n",
 			filp->f_path.dentry->d_parent->d_name.name,
 			filp->f_path.dentry->d_name.name,
-			offset, origin);
+			offset, whence);
 
 	/*
-	 * origin == SEEK_END || SEEK_DATA || SEEK_HOLE => we must revalidate
+	 * whence == SEEK_END || SEEK_DATA || SEEK_HOLE => we must revalidate
 	 * the cached file length
 	 */
-	if (origin != SEEK_SET && origin != SEEK_CUR) {
+	if (whence != SEEK_SET && whence != SEEK_CUR) {
 		struct inode *inode = filp->f_mapping->host;
 
 		int retval = nfs_revalidate_file_size(inode, filp);
@@ -154,13 +138,14 @@ static loff_t nfs_file_llseek(struct file *filp, loff_t offset, int origin)
 			return (loff_t)retval;
 	}
 
-	return generic_file_llseek(filp, offset, origin);
+	return generic_file_llseek(filp, offset, whence);
 }
+EXPORT_SYMBOL_GPL(nfs_file_llseek);
 
 /*
  * Flush all dirty pages, and check for write errors.
  */
-static int
+int
 nfs_file_flush(struct file *file, fl_owner_t id)
 {
 	struct dentry	*dentry = file->f_path.dentry;
@@ -178,14 +163,15 @@ nfs_file_flush(struct file *file, fl_owner_t id)
 	 * If we're holding a write delegation, then just start the i/o
 	 * but don't wait for completion (or send a commit).
 	 */
-	if (nfs_have_delegation(inode, FMODE_WRITE))
+	if (NFS_PROTO(inode)->have_delegation(inode, FMODE_WRITE))
 		return filemap_fdatawrite(file->f_mapping);
 
 	/* Flush writes to the server and return any errors */
 	return vfs_fsync(file, 0);
 }
+EXPORT_SYMBOL_GPL(nfs_file_flush);
 
-static ssize_t
+ssize_t
 nfs_file_read(struct kiocb *iocb, const struct iovec *iov,
 		unsigned long nr_segs, loff_t pos)
 {
@@ -194,7 +180,7 @@ nfs_file_read(struct kiocb *iocb, const struct iovec *iov,
 	ssize_t result;
 
 	if (iocb->ki_filp->f_flags & O_DIRECT)
-		return nfs_file_direct_read(iocb, iov, nr_segs, pos);
+		return nfs_file_direct_read(iocb, iov, nr_segs, pos, true);
 
 	dprintk("NFS: read(%s/%s, %lu@%lu)\n",
 		dentry->d_parent->d_name.name, dentry->d_name.name,
@@ -208,8 +194,9 @@ nfs_file_read(struct kiocb *iocb, const struct iovec *iov,
 	}
 	return result;
 }
+EXPORT_SYMBOL_GPL(nfs_file_read);
 
-static ssize_t
+ssize_t
 nfs_file_splice_read(struct file *filp, loff_t *ppos,
 		     struct pipe_inode_info *pipe, size_t count,
 		     unsigned int flags)
@@ -230,8 +217,9 @@ nfs_file_splice_read(struct file *filp, loff_t *ppos,
 	}
 	return res;
 }
+EXPORT_SYMBOL_GPL(nfs_file_splice_read);
 
-static int
+int
 nfs_file_mmap(struct file * file, struct vm_area_struct * vma)
 {
 	struct dentry *dentry = file->f_path.dentry;
@@ -251,6 +239,7 @@ nfs_file_mmap(struct file * file, struct vm_area_struct * vma)
 	}
 	return status;
 }
+EXPORT_SYMBOL_GPL(nfs_file_mmap);
 
 /*
  * Flush any dirty pages for this process, and check for write errors.
@@ -264,36 +253,63 @@ nfs_file_mmap(struct file * file, struct vm_area_struct * vma)
  * nfs_file_write() that a write error occurred, and hence cause it to
  * fall back to doing a synchronous write.
  */
-static int
-nfs_file_fsync(struct file *file, loff_t start, loff_t end, int datasync)
+int
+nfs_file_fsync_commit(struct file *file, loff_t start, loff_t end, int datasync)
 {
 	struct dentry *dentry = file->f_path.dentry;
 	struct nfs_open_context *ctx = nfs_file_open_context(file);
 	struct inode *inode = dentry->d_inode;
-	int have_error, status;
+	int have_error, do_resend, status;
 	int ret = 0;
 
 	dprintk("NFS: fsync file(%s/%s) datasync %d\n",
 			dentry->d_parent->d_name.name, dentry->d_name.name,
 			datasync);
 
-	ret = filemap_write_and_wait_range(inode->i_mapping, start, end);
-	mutex_lock(&inode->i_mutex);
-
 	nfs_inc_stats(inode, NFSIOS_VFSFSYNC);
+	do_resend = test_and_clear_bit(NFS_CONTEXT_RESEND_WRITES, &ctx->flags);
 	have_error = test_and_clear_bit(NFS_CONTEXT_ERROR_WRITE, &ctx->flags);
 	status = nfs_commit_inode(inode, FLUSH_SYNC);
-	if (status >= 0 && ret < 0)
-		status = ret;
 	have_error |= test_bit(NFS_CONTEXT_ERROR_WRITE, &ctx->flags);
-	if (have_error)
+	if (have_error) {
 		ret = xchg(&ctx->error, 0);
-	if (!ret && status < 0)
+		if (ret)
+			goto out;
+	}
+	if (status < 0) {
 		ret = status;
-	if (!ret && !datasync)
-		/* application has asked for meta-data sync */
-		ret = pnfs_layoutcommit_inode(inode, true);
-	mutex_unlock(&inode->i_mutex);
+		goto out;
+	}
+	do_resend |= test_bit(NFS_CONTEXT_RESEND_WRITES, &ctx->flags);
+	if (do_resend)
+		ret = -EAGAIN;
+out:
+	return ret;
+}
+EXPORT_SYMBOL_GPL(nfs_file_fsync_commit);
+
+static int
+nfs_file_fsync(struct file *file, loff_t start, loff_t end, int datasync)
+{
+	int ret;
+	struct inode *inode = file->f_path.dentry->d_inode;
+
+	do {
+		ret = filemap_write_and_wait_range(inode->i_mapping, start, end);
+		if (ret != 0)
+			break;
+		mutex_lock(&inode->i_mutex);
+		ret = nfs_file_fsync_commit(file, start, end, datasync);
+		mutex_unlock(&inode->i_mutex);
+		/*
+		 * If nfs_file_fsync_commit detected a server reboot, then
+		 * resend all dirty pages that might have been covered by
+		 * the NFS_CONTEXT_RESEND_WRITES flag
+		 */
+		start = 0;
+		end = LLONG_MAX;
+	} while (ret == -EAGAIN);
+
 	return ret;
 }
 
@@ -442,7 +458,7 @@ static void nfs_invalidate_page(struct page *page, unsigned long offset)
 	if (offset != 0)
 		return;
 	/* Cancel any unstarted writes on this page */
-	nfs_wb_page_cancel(page->mapping->host, page);
+	nfs_wb_page_cancel(page_file_mapping(page)->host, page);
 
 	nfs_fscache_invalidate_page(page, page->mapping->host);
 }
@@ -459,8 +475,11 @@ static int nfs_release_page(struct page *page, gfp_t gfp)
 
 	dfprintk(PAGECACHE, "NFS: release_page(%p)\n", page);
 
-	/* Only do I/O if gfp is a superset of GFP_KERNEL */
-	if (mapping && (gfp & GFP_KERNEL) == GFP_KERNEL) {
+	/* Only do I/O if gfp is a superset of GFP_KERNEL, and we're not
+	 * doing this memory reclaim for a fs-related allocation.
+	 */
+	if (mapping && (gfp & GFP_KERNEL) == GFP_KERNEL &&
+	    !(current->flags & PF_FSTRANS)) {
 		int how = FLUSH_SYNC;
 
 		/* Don't let kswapd deadlock waiting for OOM RPC calls */
@@ -484,7 +503,7 @@ static int nfs_release_page(struct page *page, gfp_t gfp)
  */
 static int nfs_launder_page(struct page *page)
 {
-	struct inode *inode = page->mapping->host;
+	struct inode *inode = page_file_mapping(page)->host;
 	struct nfs_inode *nfsi = NFS_I(inode);
 
 	dfprintk(PAGECACHE, "NFS: launder_page(%ld, %llu)\n",
@@ -494,6 +513,20 @@ static int nfs_launder_page(struct page *page)
 	return nfs_wb_page(inode, page);
 }
 
+#ifdef CONFIG_NFS_SWAP
+static int nfs_swap_activate(struct swap_info_struct *sis, struct file *file,
+						sector_t *span)
+{
+	*span = sis->pages;
+	return xs_swapper(NFS_CLIENT(file->f_mapping->host)->cl_xprt, 1);
+}
+
+static void nfs_swap_deactivate(struct file *file)
+{
+	xs_swapper(NFS_CLIENT(file->f_mapping->host)->cl_xprt, 0);
+}
+#endif
+
 const struct address_space_operations nfs_file_aops = {
 	.readpage = nfs_readpage,
 	.readpages = nfs_readpages,
@@ -508,6 +541,10 @@ const struct address_space_operations nfs_file_aops = {
 	.migratepage = nfs_migrate_page,
 	.launder_page = nfs_launder_page,
 	.error_remove_page = generic_error_remove_page,
+#ifdef CONFIG_NFS_SWAP
+	.swap_activate = nfs_swap_activate,
+	.swap_deactivate = nfs_swap_deactivate,
+#endif
 };
 
 /*
@@ -533,7 +570,7 @@ static int nfs_vm_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf)
 	nfs_fscache_wait_on_page_write(NFS_I(dentry->d_inode), page);
 
 	lock_page(page);
-	mapping = page->mapping;
+	mapping = page_file_mapping(page);
 	if (mapping != dentry->d_inode->i_mapping)
 		goto out_unlock;
 
@@ -558,6 +595,7 @@ out:
 static const struct vm_operations_struct nfs_file_vm_ops = {
 	.fault = filemap_fault,
 	.page_mkwrite = nfs_vm_page_mkwrite,
+	.remap_pages = generic_file_remap_pages,
 };
 
 static int nfs_need_sync_write(struct file *filp, struct inode *inode)
@@ -572,8 +610,8 @@ static int nfs_need_sync_write(struct file *filp, struct inode *inode)
 	return 0;
 }
 
-static ssize_t nfs_file_write(struct kiocb *iocb, const struct iovec *iov,
-				unsigned long nr_segs, loff_t pos)
+ssize_t nfs_file_write(struct kiocb *iocb, const struct iovec *iov,
+		       unsigned long nr_segs, loff_t pos)
 {
 	struct dentry * dentry = iocb->ki_filp->f_path.dentry;
 	struct inode * inode = dentry->d_inode;
@@ -582,7 +620,7 @@ static ssize_t nfs_file_write(struct kiocb *iocb, const struct iovec *iov,
 	size_t count = iov_length(iov, nr_segs);
 
 	if (iocb->ki_filp->f_flags & O_DIRECT)
-		return nfs_file_direct_write(iocb, iov, nr_segs, pos);
+		return nfs_file_direct_write(iocb, iov, nr_segs, pos, true);
 
 	dprintk("NFS: write(%s/%s, %lu@%Ld)\n",
 		dentry->d_parent->d_name.name, dentry->d_name.name,
@@ -623,10 +661,11 @@ out_swapfile:
 	printk(KERN_INFO "NFS: attempt to write to active swap file!\n");
 	goto out;
 }
+EXPORT_SYMBOL_GPL(nfs_file_write);
 
-static ssize_t nfs_file_splice_write(struct pipe_inode_info *pipe,
-				     struct file *filp, loff_t *ppos,
-				     size_t count, unsigned int flags)
+ssize_t nfs_file_splice_write(struct pipe_inode_info *pipe,
+			      struct file *filp, loff_t *ppos,
+			      size_t count, unsigned int flags)
 {
 	struct dentry *dentry = filp->f_path.dentry;
 	struct inode *inode = dentry->d_inode;
@@ -654,6 +693,7 @@ static ssize_t nfs_file_splice_write(struct pipe_inode_info *pipe,
 		nfs_add_stats(inode, NFSIOS_NORMALWRITTENBYTES, written);
 	return ret;
 }
+EXPORT_SYMBOL_GPL(nfs_file_splice_write);
 
 static int
 do_getlk(struct file *filp, int cmd, struct file_lock *fl, int is_local)
@@ -670,7 +710,7 @@ do_getlk(struct file *filp, int cmd, struct file_lock *fl, int is_local)
 	}
 	fl->fl_type = saved_type;
 
-	if (nfs_have_delegation(inode, FMODE_READ))
+	if (NFS_PROTO(inode)->have_delegation(inode, FMODE_READ))
 		goto out_noconflict;
 
 	if (is_local)
@@ -765,7 +805,7 @@ do_setlk(struct file *filp, int cmd, struct file_lock *fl, int is_local)
 	 * This makes locking act as a cache coherency point.
 	 */
 	nfs_sync_mapping(filp->f_mapping);
-	if (!nfs_have_delegation(inode, FMODE_READ)) {
+	if (!NFS_PROTO(inode)->have_delegation(inode, FMODE_READ)) {
 		if (is_time_granular(&NFS_SERVER(inode)->time_delta))
 			__nfs_revalidate_inode(NFS_SERVER(inode), inode);
 		else
@@ -778,7 +818,7 @@ out:
 /*
  * Lock a (portion of) a file
  */
-static int nfs_lock(struct file *filp, int cmd, struct file_lock *fl)
+int nfs_lock(struct file *filp, int cmd, struct file_lock *fl)
 {
 	struct inode *inode = filp->f_mapping->host;
 	int ret = -ENOLCK;
@@ -814,11 +854,12 @@ static int nfs_lock(struct file *filp, int cmd, struct file_lock *fl)
 out_err:
 	return ret;
 }
+EXPORT_SYMBOL_GPL(nfs_lock);
 
 /*
  * Lock a (portion of) a file
  */
-static int nfs_flock(struct file *filp, int cmd, struct file_lock *fl)
+int nfs_flock(struct file *filp, int cmd, struct file_lock *fl)
 {
 	struct inode *inode = filp->f_mapping->host;
 	int is_local = 0;
@@ -831,6 +872,15 @@ static int nfs_flock(struct file *filp, int cmd, struct file_lock *fl)
 	if (!(fl->fl_flags & FL_FLOCK))
 		return -ENOLCK;
 
+	/*
+	 * The NFSv4 protocol doesn't support LOCK_MAND, which is not part of
+	 * any standard. In principle we might be able to support LOCK_MAND
+	 * on NFSv2/3 since NLMv3/4 support DOS share modes, but for now the
+	 * NFS code is not set up for it.
+	 */
+	if (fl->fl_type & LOCK_MAND)
+		return -EINVAL;
+
 	if (NFS_SERVER(inode)->flags & NFS_MOUNT_LOCAL_FLOCK)
 		is_local = 1;
 
@@ -843,18 +893,20 @@ static int nfs_flock(struct file *filp, int cmd, struct file_lock *fl)
 		return do_unlk(filp, cmd, fl, is_local);
 	return do_setlk(filp, cmd, fl, is_local);
 }
+EXPORT_SYMBOL_GPL(nfs_flock);
 
 /*
  * There is no protocol support for leases, so we have no way to implement
  * them correctly in the face of opens by other clients.
  */
-static int nfs_setlease(struct file *file, long arg, struct file_lock **fl)
+int nfs_setlease(struct file *file, long arg, struct file_lock **fl)
 {
 	dprintk("NFS: setlease(%s/%s, arg=%ld)\n",
 			file->f_path.dentry->d_parent->d_name.name,
 			file->f_path.dentry->d_name.name, arg);
 	return -EINVAL;
 }
+EXPORT_SYMBOL_GPL(nfs_setlease);
 
 const struct file_operations nfs_file_operations = {
 	.llseek		= nfs_file_llseek,
@@ -874,104 +926,4 @@ const struct file_operations nfs_file_operations = {
 	.check_flags	= nfs_check_flags,
 	.setlease	= nfs_setlease,
 };
-
-#ifdef CONFIG_NFS_V4
-static int
-nfs4_file_open(struct inode *inode, struct file *filp)
-{
-	struct nfs_open_context *ctx;
-	struct dentry *dentry = filp->f_path.dentry;
-	struct dentry *parent = NULL;
-	struct inode *dir;
-	unsigned openflags = filp->f_flags;
-	struct iattr attr;
-	int err;
-
-	BUG_ON(inode != dentry->d_inode);
-	/*
-	 * If no cached dentry exists or if it's negative, NFSv4 handled the
-	 * opens in ->lookup() or ->create().
-	 *
-	 * We only get this far for a cached positive dentry.  We skipped
-	 * revalidation, so handle it here by dropping the dentry and returning
-	 * -EOPENSTALE.  The VFS will retry the lookup/create/open.
-	 */
-
-	dprintk("NFS: open file(%s/%s)\n",
-		dentry->d_parent->d_name.name,
-		dentry->d_name.name);
-
-	if ((openflags & O_ACCMODE) == 3)
-		openflags--;
-
-	/* We can't create new files here */
-	openflags &= ~(O_CREAT|O_EXCL);
-
-	parent = dget_parent(dentry);
-	dir = parent->d_inode;
-
-	ctx = alloc_nfs_open_context(filp->f_path.dentry, filp->f_mode);
-	err = PTR_ERR(ctx);
-	if (IS_ERR(ctx))
-		goto out;
-
-	attr.ia_valid = ATTR_OPEN;
-	if (openflags & O_TRUNC) {
-		attr.ia_valid |= ATTR_SIZE;
-		attr.ia_size = 0;
-		nfs_wb_all(inode);
-	}
-
-	inode = NFS_PROTO(dir)->open_context(dir, ctx, openflags, &attr);
-	if (IS_ERR(inode)) {
-		err = PTR_ERR(inode);
-		switch (err) {
-		case -EPERM:
-		case -EACCES:
-		case -EDQUOT:
-		case -ENOSPC:
-		case -EROFS:
-			goto out_put_ctx;
-		default:
-			goto out_drop;
-		}
-	}
-	iput(inode);
-	if (inode != dentry->d_inode)
-		goto out_drop;
-
-	nfs_set_verifier(dentry, nfs_save_change_attribute(dir));
-	nfs_file_set_open_context(filp, ctx);
-	err = 0;
-
-out_put_ctx:
-	put_nfs_open_context(ctx);
-out:
-	dput(parent);
-	return err;
-
-out_drop:
-	d_drop(dentry);
-	err = -EOPENSTALE;
-	goto out_put_ctx;
-}
-
-const struct file_operations nfs4_file_operations = {
-	.llseek		= nfs_file_llseek,
-	.read		= do_sync_read,
-	.write		= do_sync_write,
-	.aio_read	= nfs_file_read,
-	.aio_write	= nfs_file_write,
-	.mmap		= nfs_file_mmap,
-	.open		= nfs4_file_open,
-	.flush		= nfs_file_flush,
-	.release	= nfs_file_release,
-	.fsync		= nfs_file_fsync,
-	.lock		= nfs_lock,
-	.flock		= nfs_flock,
-	.splice_read	= nfs_file_splice_read,
-	.splice_write	= nfs_file_splice_write,
-	.check_flags	= nfs_check_flags,
-	.setlease	= nfs_setlease,
-};
-#endif /* CONFIG_NFS_V4 */
+EXPORT_SYMBOL_GPL(nfs_file_operations);
diff --git a/fs/nfs/fscache.c b/fs/nfs/fscache.c
index c817787fbdb..24d1d1c5fca 100644
--- a/fs/nfs/fscache.c
+++ b/fs/nfs/fscache.c
@@ -307,6 +307,7 @@ void nfs_fscache_set_inode_cookie(struct inode *inode, struct file *filp)
 		nfs_fscache_inode_unlock(inode);
 	}
 }
+EXPORT_SYMBOL_GPL(nfs_fscache_set_inode_cookie);
 
 /*
  * Replace a per-inode cookie due to revalidation detecting a file having
diff --git a/fs/nfs/fscache.h b/fs/nfs/fscache.h
index c5b11b53ff3..4ecb76652eb 100644
--- a/fs/nfs/fscache.h
+++ b/fs/nfs/fscache.h
@@ -153,6 +153,22 @@ static inline void nfs_readpage_to_fscache(struct inode *inode,
 }
 
 /*
+ * Invalidate the contents of fscache for this inode.  This will not sleep.
+ */
+static inline void nfs_fscache_invalidate(struct inode *inode)
+{
+	fscache_invalidate(NFS_I(inode)->fscache);
+}
+
+/*
+ * Wait for an object to finish being invalidated.
+ */
+static inline void nfs_fscache_wait_on_invalidate(struct inode *inode)
+{
+	fscache_wait_on_invalidate(NFS_I(inode)->fscache);
+}
+
+/*
  * indicate the client caching state as readable text
  */
 static inline const char *nfs_server_fscache_state(struct nfs_server *server)
@@ -162,7 +178,6 @@ static inline const char *nfs_server_fscache_state(struct nfs_server *server)
 	return "no ";
 }
 
-
 #else /* CONFIG_NFS_FSCACHE */
 static inline int nfs_fscache_register(void) { return 0; }
 static inline void nfs_fscache_unregister(void) {}
@@ -205,6 +220,10 @@ static inline int nfs_readpages_from_fscache(struct nfs_open_context *ctx,
 static inline void nfs_readpage_to_fscache(struct inode *inode,
 					   struct page *page, int sync) {}
 
+
+static inline void nfs_fscache_invalidate(struct inode *inode) {}
+static inline void nfs_fscache_wait_on_invalidate(struct inode *inode) {}
+
 static inline const char *nfs_server_fscache_state(struct nfs_server *server)
 {
 	return "no ";
diff --git a/fs/nfs/getroot.c b/fs/nfs/getroot.c
index 8abfb19bd3a..033803c3664 100644
--- a/fs/nfs/getroot.c
+++ b/fs/nfs/getroot.c
@@ -23,19 +23,15 @@
 #include <linux/sunrpc/stats.h>
 #include <linux/nfs_fs.h>
 #include <linux/nfs_mount.h>
-#include <linux/nfs4_mount.h>
 #include <linux/lockd/bind.h>
 #include <linux/seq_file.h>
 #include <linux/mount.h>
-#include <linux/nfs_idmap.h>
 #include <linux/vfs.h>
 #include <linux/namei.h>
 #include <linux/security.h>
 
 #include <asm/uaccess.h>
 
-#include "nfs4_fs.h"
-#include "delegation.h"
 #include "internal.h"
 
 #define NFSDBG_FACILITY		NFSDBG_CLIENT
@@ -62,7 +58,7 @@ static int nfs_superblock_set_dummy_root(struct super_block *sb, struct inode *i
 		 */
 		spin_lock(&sb->s_root->d_inode->i_lock);
 		spin_lock(&sb->s_root->d_lock);
-		list_del_init(&sb->s_root->d_alias);
+		hlist_del_init(&sb->s_root->d_alias);
 		spin_unlock(&sb->s_root->d_lock);
 		spin_unlock(&sb->s_root->d_inode->i_lock);
 	}
@@ -135,47 +131,3 @@ out:
 	nfs_free_fattr(fsinfo.fattr);
 	return ret;
 }
-
-#ifdef CONFIG_NFS_V4
-
-int nfs4_get_rootfh(struct nfs_server *server, struct nfs_fh *mntfh)
-{
-	struct nfs_fsinfo fsinfo;
-	int ret = -ENOMEM;
-
-	dprintk("--> nfs4_get_rootfh()\n");
-
-	fsinfo.fattr = nfs_alloc_fattr();
-	if (fsinfo.fattr == NULL)
-		goto out;
-
-	/* Start by getting the root filehandle from the server */
-	ret = nfs4_proc_get_rootfh(server, mntfh, &fsinfo);
-	if (ret < 0) {
-		dprintk("nfs4_get_rootfh: getroot error = %d\n", -ret);
-		goto out;
-	}
-
-	if (!(fsinfo.fattr->valid & NFS_ATTR_FATTR_TYPE)
-			|| !S_ISDIR(fsinfo.fattr->mode)) {
-		printk(KERN_ERR "nfs4_get_rootfh:"
-		       " getroot encountered non-directory\n");
-		ret = -ENOTDIR;
-		goto out;
-	}
-
-	if (fsinfo.fattr->valid & NFS_ATTR_FATTR_V4_REFERRAL) {
-		printk(KERN_ERR "nfs4_get_rootfh:"
-		       " getroot obtained referral\n");
-		ret = -EREMOTE;
-		goto out;
-	}
-
-	memcpy(&server->fsid, &fsinfo.fattr->fsid, sizeof(server->fsid));
-out:
-	nfs_free_fattr(fsinfo.fattr);
-	dprintk("<-- nfs4_get_rootfh() = %d\n", ret);
-	return ret;
-}
-
-#endif /* CONFIG_NFS_V4 */
diff --git a/fs/nfs/idmap.c b/fs/nfs/idmap.c
index 864c51e4b40..bc3968fa81e 100644
--- a/fs/nfs/idmap.c
+++ b/fs/nfs/idmap.c
@@ -52,14 +52,19 @@
 
 #define NFS_UINT_MAXLEN 11
 
-/* Default cache timeout is 10 minutes */
-unsigned int nfs_idmap_cache_timeout = 600;
 static const struct cred *id_resolver_cache;
 static struct key_type key_type_id_resolver_legacy;
 
+struct idmap_legacy_upcalldata {
+	struct rpc_pipe_msg pipe_msg;
+	struct idmap_msg idmap_msg;
+	struct key_construction	*key_cons;
+	struct idmap *idmap;
+};
+
 struct idmap {
 	struct rpc_pipe		*idmap_pipe;
-	struct key_construction	*idmap_key_cons;
+	struct idmap_legacy_upcalldata *idmap_upcall_data;
 	struct mutex		idmap_mutex;
 };
 
@@ -154,7 +159,7 @@ static int nfs_map_string_to_numeric(const char *name, size_t namelen, __u32 *re
 		return 0;
 	memcpy(buf, name, namelen);
 	buf[namelen] = '\0';
-	if (strict_strtoul(buf, 0, &val) != 0)
+	if (kstrtoul(buf, 0, &val) != 0)
 		return 0;
 	*res = val;
 	return 1;
@@ -188,22 +193,22 @@ static int nfs_idmap_init_keyring(void)
 	if (!cred)
 		return -ENOMEM;
 
-	keyring = key_alloc(&key_type_keyring, ".id_resolver", 0, 0, cred,
-			     (KEY_POS_ALL & ~KEY_POS_SETATTR) |
-			     KEY_USR_VIEW | KEY_USR_READ,
-			     KEY_ALLOC_NOT_IN_QUOTA);
+	keyring = keyring_alloc(".id_resolver", 0, 0, cred,
+				(KEY_POS_ALL & ~KEY_POS_SETATTR) |
+				KEY_USR_VIEW | KEY_USR_READ,
+				KEY_ALLOC_NOT_IN_QUOTA, NULL);
 	if (IS_ERR(keyring)) {
 		ret = PTR_ERR(keyring);
 		goto failed_put_cred;
 	}
 
-	ret = key_instantiate_and_link(keyring, NULL, 0, NULL, NULL);
+	ret = register_key_type(&key_type_id_resolver);
 	if (ret < 0)
 		goto failed_put_key;
 
-	ret = register_key_type(&key_type_id_resolver);
+	ret = register_key_type(&key_type_id_resolver_legacy);
 	if (ret < 0)
-		goto failed_put_key;
+		goto failed_reg_legacy;
 
 	set_bit(KEY_FLAG_ROOT_CAN_CLEAR, &keyring->flags);
 	cred->thread_keyring = keyring;
@@ -211,6 +216,8 @@ static int nfs_idmap_init_keyring(void)
 	id_resolver_cache = cred;
 	return 0;
 
+failed_reg_legacy:
+	unregister_key_type(&key_type_id_resolver);
 failed_put_key:
 	key_put(keyring);
 failed_put_cred:
@@ -222,6 +229,7 @@ static void nfs_idmap_quit_keyring(void)
 {
 	key_revoke(id_resolver_cache->thread_keyring);
 	unregister_key_type(&key_type_id_resolver);
+	unregister_key_type(&key_type_id_resolver_legacy);
 	put_cred(id_resolver_cache);
 }
 
@@ -352,14 +360,13 @@ static int nfs_idmap_lookup_id(const char *name, size_t namelen, const char *typ
 	if (data_size <= 0) {
 		ret = -EINVAL;
 	} else {
-		ret = strict_strtol(id_str, 10, &id_long);
+		ret = kstrtol(id_str, 10, &id_long);
 		*id = (__u32)id_long;
 	}
 	return ret;
 }
 
 /* idmap classic begins here */
-module_param(nfs_idmap_cache_timeout, int, 0644);
 
 enum {
 	Opt_find_uid, Opt_find_gid, Opt_find_user, Opt_find_group, Opt_find_err
@@ -376,16 +383,18 @@ static const match_table_t nfs_idmap_tokens = {
 static int nfs_idmap_legacy_upcall(struct key_construction *, const char *, void *);
 static ssize_t idmap_pipe_downcall(struct file *, const char __user *,
 				   size_t);
+static void idmap_release_pipe(struct inode *);
 static void idmap_pipe_destroy_msg(struct rpc_pipe_msg *);
 
 static const struct rpc_pipe_ops idmap_upcall_ops = {
 	.upcall		= rpc_pipe_generic_upcall,
 	.downcall	= idmap_pipe_downcall,
+	.release_pipe	= idmap_release_pipe,
 	.destroy_msg	= idmap_pipe_destroy_msg,
 };
 
 static struct key_type key_type_id_resolver_legacy = {
-	.name		= "id_resolver",
+	.name		= "id_legacy",
 	.instantiate	= user_instantiate,
 	.match		= user_match,
 	.revoke		= user_revoke,
@@ -452,8 +461,6 @@ nfs_idmap_new(struct nfs_client *clp)
 	struct rpc_pipe *pipe;
 	int error;
 
-	BUG_ON(clp->cl_idmap != NULL);
-
 	idmap = kzalloc(sizeof(*idmap), GFP_KERNEL);
 	if (idmap == NULL)
 		return -ENOMEM;
@@ -497,7 +504,6 @@ static int __rpc_pipefs_event(struct nfs_client *clp, unsigned long event,
 
 	switch (event) {
 	case RPC_PIPEFS_MOUNT:
-		BUG_ON(clp->cl_rpcclient->cl_dentry == NULL);
 		err = __nfs_idmap_register(clp->cl_rpcclient->cl_dentry,
 						clp->cl_idmap,
 						clp->cl_idmap->idmap_pipe);
@@ -612,15 +618,13 @@ void nfs_idmap_quit(void)
 	nfs_idmap_quit_keyring();
 }
 
-static int nfs_idmap_prepare_message(char *desc, struct idmap_msg *im,
+static int nfs_idmap_prepare_message(char *desc, struct idmap *idmap,
+				     struct idmap_msg *im,
 				     struct rpc_pipe_msg *msg)
 {
 	substring_t substr;
 	int token, ret;
 
-	memset(im,  0, sizeof(*im));
-	memset(msg, 0, sizeof(*msg));
-
 	im->im_type = IDMAP_TYPE_GROUP;
 	token = match_token(desc, nfs_idmap_tokens, &substr);
 
@@ -651,10 +655,40 @@ out:
 	return ret;
 }
 
+static bool
+nfs_idmap_prepare_pipe_upcall(struct idmap *idmap,
+		struct idmap_legacy_upcalldata *data)
+{
+	if (idmap->idmap_upcall_data != NULL) {
+		WARN_ON_ONCE(1);
+		return false;
+	}
+	idmap->idmap_upcall_data = data;
+	return true;
+}
+
+static void
+nfs_idmap_complete_pipe_upcall_locked(struct idmap *idmap, int ret)
+{
+	struct key_construction *cons = idmap->idmap_upcall_data->key_cons;
+
+	kfree(idmap->idmap_upcall_data);
+	idmap->idmap_upcall_data = NULL;
+	complete_request_key(cons, ret);
+}
+
+static void
+nfs_idmap_abort_pipe_upcall(struct idmap *idmap, int ret)
+{
+	if (idmap->idmap_upcall_data != NULL)
+		nfs_idmap_complete_pipe_upcall_locked(idmap, ret);
+}
+
 static int nfs_idmap_legacy_upcall(struct key_construction *cons,
 				   const char *op,
 				   void *aux)
 {
+	struct idmap_legacy_upcalldata *data;
 	struct rpc_pipe_msg *msg;
 	struct idmap_msg *im;
 	struct idmap *idmap = (struct idmap *)aux;
@@ -662,33 +696,32 @@ static int nfs_idmap_legacy_upcall(struct key_construction *cons,
 	int ret = -ENOMEM;
 
 	/* msg and im are freed in idmap_pipe_destroy_msg */
-	msg = kmalloc(sizeof(*msg), GFP_KERNEL);
-	if (!msg)
-		goto out0;
-
-	im = kmalloc(sizeof(*im), GFP_KERNEL);
-	if (!im)
+	data = kzalloc(sizeof(*data), GFP_KERNEL);
+	if (!data)
 		goto out1;
 
-	ret = nfs_idmap_prepare_message(key->description, im, msg);
+	msg = &data->pipe_msg;
+	im = &data->idmap_msg;
+	data->idmap = idmap;
+	data->key_cons = cons;
+
+	ret = nfs_idmap_prepare_message(key->description, idmap, im, msg);
 	if (ret < 0)
 		goto out2;
 
-	idmap->idmap_key_cons = cons;
+	ret = -EAGAIN;
+	if (!nfs_idmap_prepare_pipe_upcall(idmap, data))
+		goto out2;
 
 	ret = rpc_queue_upcall(idmap->idmap_pipe, msg);
 	if (ret < 0)
-		goto out2;
+		nfs_idmap_abort_pipe_upcall(idmap, ret);
 
 	return ret;
-
 out2:
-	kfree(im);
+	kfree(data);
 out1:
-	kfree(msg);
-out0:
-	key_revoke(cons->key);
-	key_revoke(cons->authkey);
+	complete_request_key(cons, ret);
 	return ret;
 }
 
@@ -699,21 +732,32 @@ static int nfs_idmap_instantiate(struct key *key, struct key *authkey, char *dat
 					authkey);
 }
 
-static int nfs_idmap_read_message(struct idmap_msg *im, struct key *key, struct key *authkey)
+static int nfs_idmap_read_and_verify_message(struct idmap_msg *im,
+		struct idmap_msg *upcall,
+		struct key *key, struct key *authkey)
 {
 	char id_str[NFS_UINT_MAXLEN];
-	int ret = -EINVAL;
+	int ret = -ENOKEY;
 
+	/* ret = -ENOKEY */
+	if (upcall->im_type != im->im_type || upcall->im_conv != im->im_conv)
+		goto out;
 	switch (im->im_conv) {
 	case IDMAP_CONV_NAMETOID:
+		if (strcmp(upcall->im_name, im->im_name) != 0)
+			break;
 		sprintf(id_str, "%d", im->im_id);
 		ret = nfs_idmap_instantiate(key, authkey, id_str);
 		break;
 	case IDMAP_CONV_IDTONAME:
+		if (upcall->im_id != im->im_id)
+			break;
 		ret = nfs_idmap_instantiate(key, authkey, im->im_name);
 		break;
+	default:
+		ret = -EINVAL;
 	}
-
+out:
 	return ret;
 }
 
@@ -722,10 +766,19 @@ idmap_pipe_downcall(struct file *filp, const char __user *src, size_t mlen)
 {
 	struct rpc_inode *rpci = RPC_I(filp->f_path.dentry->d_inode);
 	struct idmap *idmap = (struct idmap *)rpci->private;
-	struct key_construction *cons = idmap->idmap_key_cons;
+	struct key_construction *cons;
 	struct idmap_msg im;
 	size_t namelen_in;
-	int ret;
+	int ret = -ENOKEY;
+
+	/* If instantiation is successful, anyone waiting for key construction
+	 * will have been woken up and someone else may now have used
+	 * idmap_key_cons - so after this point we may no longer touch it.
+	 */
+	if (idmap->idmap_upcall_data == NULL)
+		goto out_noupcall;
+
+	cons = idmap->idmap_upcall_data->key_cons;
 
 	if (mlen != sizeof(im)) {
 		ret = -ENOSPC;
@@ -738,35 +791,49 @@ idmap_pipe_downcall(struct file *filp, const char __user *src, size_t mlen)
 	}
 
 	if (!(im.im_status & IDMAP_STATUS_SUCCESS)) {
-		ret = mlen;
-		complete_request_key(idmap->idmap_key_cons, -ENOKEY);
-		goto out_incomplete;
+		ret = -ENOKEY;
+		goto out;
 	}
 
 	namelen_in = strnlen(im.im_name, IDMAP_NAMESZ);
 	if (namelen_in == 0 || namelen_in == IDMAP_NAMESZ) {
 		ret = -EINVAL;
 		goto out;
-	}
+}
 
-	ret = nfs_idmap_read_message(&im, cons->key, cons->authkey);
+	ret = nfs_idmap_read_and_verify_message(&im,
+			&idmap->idmap_upcall_data->idmap_msg,
+			cons->key, cons->authkey);
 	if (ret >= 0) {
 		key_set_timeout(cons->key, nfs_idmap_cache_timeout);
 		ret = mlen;
 	}
 
 out:
-	complete_request_key(idmap->idmap_key_cons, ret);
-out_incomplete:
+	nfs_idmap_complete_pipe_upcall_locked(idmap, ret);
+out_noupcall:
 	return ret;
 }
 
 static void
 idmap_pipe_destroy_msg(struct rpc_pipe_msg *msg)
 {
-	/* Free memory allocated in nfs_idmap_legacy_upcall() */
-	kfree(msg->data);
-	kfree(msg);
+	struct idmap_legacy_upcalldata *data = container_of(msg,
+			struct idmap_legacy_upcalldata,
+			pipe_msg);
+	struct idmap *idmap = data->idmap;
+
+	if (msg->errno)
+		nfs_idmap_abort_pipe_upcall(idmap, msg->errno);
+}
+
+static void
+idmap_release_pipe(struct inode *inode)
+{
+	struct rpc_inode *rpci = RPC_I(inode);
+	struct idmap *idmap = (struct idmap *)rpci->private;
+
+	nfs_idmap_abort_pipe_upcall(idmap, -EPIPE);
 }
 
 int nfs_map_name_to_uid(const struct nfs_server *server, const char *name, size_t namelen, __u32 *uid)
diff --git a/fs/nfs/inode.c b/fs/nfs/inode.c
index f7296983eba..ebeb94ce1b0 100644
--- a/fs/nfs/inode.c
+++ b/fs/nfs/inode.c
@@ -32,7 +32,6 @@
 #include <linux/lockd/bind.h>
 #include <linux/seq_file.h>
 #include <linux/mount.h>
-#include <linux/nfs_idmap.h>
 #include <linux/vfs.h>
 #include <linux/inet.h>
 #include <linux/nfs_xdr.h>
@@ -51,6 +50,7 @@
 #include "fscache.h"
 #include "dns_resolve.h"
 #include "pnfs.h"
+#include "nfs.h"
 #include "netns.h"
 
 #define NFSDBG_FACILITY		NFSDBG_VFS
@@ -82,6 +82,7 @@ int nfs_wait_bit_killable(void *word)
 	freezable_schedule();
 	return 0;
 }
+EXPORT_SYMBOL_GPL(nfs_wait_bit_killable);
 
 /**
  * nfs_compat_user_ino64 - returns the user-visible inode number
@@ -106,17 +107,24 @@ u64 nfs_compat_user_ino64(u64 fileid)
 	return ino;
 }
 
-static void nfs_clear_inode(struct inode *inode)
+int nfs_drop_inode(struct inode *inode)
+{
+	return NFS_STALE(inode) || generic_drop_inode(inode);
+}
+EXPORT_SYMBOL_GPL(nfs_drop_inode);
+
+void nfs_clear_inode(struct inode *inode)
 {
 	/*
 	 * The following should never happen...
 	 */
-	BUG_ON(nfs_have_writebacks(inode));
-	BUG_ON(!list_empty(&NFS_I(inode)->open_files));
+	WARN_ON_ONCE(nfs_have_writebacks(inode));
+	WARN_ON_ONCE(!list_empty(&NFS_I(inode)->open_files));
 	nfs_zap_acl_cache(inode);
 	nfs_access_zap_cache(inode);
 	nfs_fscache_release_inode_cookie(inode);
 }
+EXPORT_SYMBOL_GPL(nfs_clear_inode);
 
 void nfs_evict_inode(struct inode *inode)
 {
@@ -152,11 +160,13 @@ static void nfs_zap_caches_locked(struct inode *inode)
 	nfsi->attrtimeo = NFS_MINATTRTIMEO(inode);
 	nfsi->attrtimeo_timestamp = jiffies;
 
-	memset(NFS_COOKIEVERF(inode), 0, sizeof(NFS_COOKIEVERF(inode)));
-	if (S_ISREG(mode) || S_ISDIR(mode) || S_ISLNK(mode))
+	memset(NFS_I(inode)->cookieverf, 0, sizeof(NFS_I(inode)->cookieverf));
+	if (S_ISREG(mode) || S_ISDIR(mode) || S_ISLNK(mode)) {
 		nfsi->cache_validity |= NFS_INO_INVALID_ATTR|NFS_INO_INVALID_DATA|NFS_INO_INVALID_ACCESS|NFS_INO_INVALID_ACL|NFS_INO_REVAL_PAGECACHE;
-	else
+		nfs_fscache_invalidate(inode);
+	} else {
 		nfsi->cache_validity |= NFS_INO_INVALID_ATTR|NFS_INO_INVALID_ACCESS|NFS_INO_INVALID_ACL|NFS_INO_REVAL_PAGECACHE;
+	}
 }
 
 void nfs_zap_caches(struct inode *inode)
@@ -171,6 +181,7 @@ void nfs_zap_mapping(struct inode *inode, struct address_space *mapping)
 	if (mapping->nrpages != 0) {
 		spin_lock(&inode->i_lock);
 		NFS_I(inode)->cache_validity |= NFS_INO_INVALID_DATA;
+		nfs_fscache_invalidate(inode);
 		spin_unlock(&inode->i_lock);
 	}
 }
@@ -186,6 +197,7 @@ void nfs_zap_acl_cache(struct inode *inode)
 	NFS_I(inode)->cache_validity &= ~NFS_INO_INVALID_ACL;
 	spin_unlock(&inode->i_lock);
 }
+EXPORT_SYMBOL_GPL(nfs_zap_acl_cache);
 
 void nfs_invalidate_atime(struct inode *inode)
 {
@@ -193,6 +205,7 @@ void nfs_invalidate_atime(struct inode *inode)
 	NFS_I(inode)->cache_validity |= NFS_INO_INVALID_ATIME;
 	spin_unlock(&inode->i_lock);
 }
+EXPORT_SYMBOL_GPL(nfs_invalidate_atime);
 
 /*
  * Invalidate, but do not unhash, the inode.
@@ -391,6 +404,7 @@ out_no_inode:
 	dprintk("nfs_fhget: iget failed with error %ld\n", PTR_ERR(inode));
 	goto out;
 }
+EXPORT_SYMBOL_GPL(nfs_fhget);
 
 #define NFS_VALID_ATTRS (ATTR_MODE|ATTR_UID|ATTR_GID|ATTR_SIZE|ATTR_ATIME|ATTR_ATIME_SET|ATTR_MTIME|ATTR_MTIME_SET|ATTR_FILE|ATTR_OPEN)
 
@@ -430,7 +444,7 @@ nfs_setattr(struct dentry *dentry, struct iattr *attr)
 	 * Return any delegations if we're going to change ACLs
 	 */
 	if ((attr->ia_valid & (ATTR_MODE|ATTR_UID|ATTR_GID)) != 0)
-		nfs_inode_return_delegation(inode);
+		NFS_PROTO(inode)->return_delegation(inode);
 	error = NFS_PROTO(inode)->setattr(dentry, fattr, attr);
 	if (error == 0)
 		nfs_refresh_inode(inode, fattr);
@@ -438,6 +452,7 @@ nfs_setattr(struct dentry *dentry, struct iattr *attr)
 out:
 	return error;
 }
+EXPORT_SYMBOL_GPL(nfs_setattr);
 
 /**
  * nfs_vmtruncate - unmap mappings "freed" by truncate() syscall
@@ -496,6 +511,7 @@ void nfs_setattr_update_inode(struct inode *inode, struct iattr *attr)
 		nfs_vmtruncate(inode, attr->ia_size);
 	}
 }
+EXPORT_SYMBOL_GPL(nfs_setattr_update_inode);
 
 int nfs_getattr(struct vfsmount *mnt, struct dentry *dentry, struct kstat *stat)
 {
@@ -535,12 +551,13 @@ int nfs_getattr(struct vfsmount *mnt, struct dentry *dentry, struct kstat *stat)
 out:
 	return err;
 }
+EXPORT_SYMBOL_GPL(nfs_getattr);
 
 static void nfs_init_lock_context(struct nfs_lock_context *l_ctx)
 {
 	atomic_set(&l_ctx->count, 1);
-	l_ctx->lockowner = current->files;
-	l_ctx->pid = current->tgid;
+	l_ctx->lockowner.l_owner = current->files;
+	l_ctx->lockowner.l_pid = current->tgid;
 	INIT_LIST_HEAD(&l_ctx->list);
 }
 
@@ -549,9 +566,9 @@ static struct nfs_lock_context *__nfs_find_lock_context(struct nfs_open_context
 	struct nfs_lock_context *pos;
 
 	list_for_each_entry(pos, &ctx->lock_context.list, list) {
-		if (pos->lockowner != current->files)
+		if (pos->lockowner.l_owner != current->files)
 			continue;
-		if (pos->pid != current->tgid)
+		if (pos->lockowner.l_pid != current->tgid)
 			continue;
 		atomic_inc(&pos->count);
 		return pos;
@@ -570,7 +587,7 @@ struct nfs_lock_context *nfs_get_lock_context(struct nfs_open_context *ctx)
 		spin_unlock(&inode->i_lock);
 		new = kmalloc(sizeof(*new), GFP_KERNEL);
 		if (new == NULL)
-			return NULL;
+			return ERR_PTR(-ENOMEM);
 		nfs_init_lock_context(new);
 		spin_lock(&inode->i_lock);
 		res = __nfs_find_lock_context(ctx);
@@ -623,6 +640,7 @@ void nfs_close_context(struct nfs_open_context *ctx, int is_sync)
 		return;
 	nfs_revalidate_inode(server, inode);
 }
+EXPORT_SYMBOL_GPL(nfs_close_context);
 
 struct nfs_open_context *alloc_nfs_open_context(struct dentry *dentry, fmode_t f_mode)
 {
@@ -649,6 +667,7 @@ struct nfs_open_context *alloc_nfs_open_context(struct dentry *dentry, fmode_t f
 	ctx->mdsthreshold = NULL;
 	return ctx;
 }
+EXPORT_SYMBOL_GPL(alloc_nfs_open_context);
 
 struct nfs_open_context *get_nfs_open_context(struct nfs_open_context *ctx)
 {
@@ -656,6 +675,7 @@ struct nfs_open_context *get_nfs_open_context(struct nfs_open_context *ctx)
 		atomic_inc(&ctx->lock_context.count);
 	return ctx;
 }
+EXPORT_SYMBOL_GPL(get_nfs_open_context);
 
 static void __put_nfs_open_context(struct nfs_open_context *ctx, int is_sync)
 {
@@ -674,7 +694,10 @@ static void __put_nfs_open_context(struct nfs_open_context *ctx, int is_sync)
 	if (ctx->cred != NULL)
 		put_rpccred(ctx->cred);
 	dput(ctx->dentry);
-	nfs_sb_deactive(sb);
+	if (is_sync)
+		nfs_sb_deactive(sb);
+	else
+		nfs_sb_deactive_async(sb);
 	kfree(ctx->mdsthreshold);
 	kfree(ctx);
 }
@@ -683,6 +706,7 @@ void put_nfs_open_context(struct nfs_open_context *ctx)
 {
 	__put_nfs_open_context(ctx, 0);
 }
+EXPORT_SYMBOL_GPL(put_nfs_open_context);
 
 /*
  * Ensure that mmap has a recent RPC credential for use when writing out
@@ -698,6 +722,7 @@ void nfs_file_set_open_context(struct file *filp, struct nfs_open_context *ctx)
 	list_add(&ctx->list, &nfsi->open_files);
 	spin_unlock(&inode->i_lock);
 }
+EXPORT_SYMBOL_GPL(nfs_file_set_open_context);
 
 /*
  * Given an inode, search for an open context with the desired characteristics
@@ -842,6 +867,7 @@ int nfs_revalidate_inode(struct nfs_server *server, struct inode *inode)
 		return NFS_STALE(inode) ? -ESTALE : 0;
 	return __nfs_revalidate_inode(server, inode);
 }
+EXPORT_SYMBOL_GPL(nfs_revalidate_inode);
 
 static int nfs_invalidate_mapping(struct inode *inode, struct address_space *mapping)
 {
@@ -858,7 +884,7 @@ static int nfs_invalidate_mapping(struct inode *inode, struct address_space *map
 		memset(nfsi->cookieverf, 0, sizeof(nfsi->cookieverf));
 	spin_unlock(&inode->i_lock);
 	nfs_inc_stats(inode, NFSIOS_DATAINVALIDATE);
-	nfs_fscache_reset_inode_cookie(inode);
+	nfs_fscache_wait_on_invalidate(inode);
 	dfprintk(PAGECACHE, "NFS: (%s/%Ld) data cache invalidated\n",
 			inode->i_sb->s_id, (long long)NFS_FILEID(inode));
 	return 0;
@@ -883,6 +909,10 @@ int nfs_revalidate_mapping(struct inode *inode, struct address_space *mapping)
 	struct nfs_inode *nfsi = NFS_I(inode);
 	int ret = 0;
 
+	/* swapfiles are not supposed to be shared. */
+	if (IS_SWAPFILE(inode))
+		goto out;
+
 	if (nfs_mapping_need_revalidate_inode(inode)) {
 		ret = __nfs_revalidate_inode(NFS_SERVER(inode), inode);
 		if (ret < 0)
@@ -930,6 +960,10 @@ static unsigned long nfs_wcc_update_inode(struct inode *inode, struct nfs_fattr
 		i_size_write(inode, nfs_size_to_loff_t(fattr->size));
 		ret |= NFS_INO_INVALID_ATTR;
 	}
+
+	if (nfsi->cache_validity & NFS_INO_INVALID_DATA)
+		nfs_fscache_invalidate(inode);
+
 	return ret;
 }
 
@@ -1028,6 +1062,7 @@ void nfs_fattr_init(struct nfs_fattr *fattr)
 	fattr->owner_name = NULL;
 	fattr->group_name = NULL;
 }
+EXPORT_SYMBOL_GPL(nfs_fattr_init);
 
 struct nfs_fattr *nfs_alloc_fattr(void)
 {
@@ -1038,6 +1073,7 @@ struct nfs_fattr *nfs_alloc_fattr(void)
 		nfs_fattr_init(fattr);
 	return fattr;
 }
+EXPORT_SYMBOL_GPL(nfs_alloc_fattr);
 
 struct nfs_fh *nfs_alloc_fhandle(void)
 {
@@ -1048,6 +1084,7 @@ struct nfs_fh *nfs_alloc_fhandle(void)
 		fh->size = 0;
 	return fh;
 }
+EXPORT_SYMBOL_GPL(nfs_alloc_fhandle);
 
 #ifdef NFS_DEBUG
 /*
@@ -1168,14 +1205,17 @@ int nfs_refresh_inode(struct inode *inode, struct nfs_fattr *fattr)
 
 	return status;
 }
+EXPORT_SYMBOL_GPL(nfs_refresh_inode);
 
 static int nfs_post_op_update_inode_locked(struct inode *inode, struct nfs_fattr *fattr)
 {
 	struct nfs_inode *nfsi = NFS_I(inode);
 
 	nfsi->cache_validity |= NFS_INO_INVALID_ATTR|NFS_INO_REVAL_PAGECACHE;
-	if (S_ISDIR(inode->i_mode))
+	if (S_ISDIR(inode->i_mode)) {
 		nfsi->cache_validity |= NFS_INO_INVALID_DATA;
+		nfs_fscache_invalidate(inode);
+	}
 	if ((fattr->valid & NFS_ATTR_FATTR) == 0)
 		return 0;
 	return nfs_refresh_inode_locked(inode, fattr);
@@ -1204,6 +1244,7 @@ int nfs_post_op_update_inode(struct inode *inode, struct nfs_fattr *fattr)
 	spin_unlock(&inode->i_lock);
 	return status;
 }
+EXPORT_SYMBOL_GPL(nfs_post_op_update_inode);
 
 /**
  * nfs_post_op_update_inode_force_wcc - try to update the inode attribute cache
@@ -1255,6 +1296,7 @@ out_noforce:
 	spin_unlock(&inode->i_lock);
 	return status;
 }
+EXPORT_SYMBOL_GPL(nfs_post_op_update_inode_force_wcc);
 
 /*
  * Many nfs protocol calls return the new file attributes after
@@ -1457,10 +1499,13 @@ static int nfs_update_inode(struct inode *inode, struct nfs_fattr *fattr)
 	if (!(S_ISREG(inode->i_mode) || S_ISDIR(inode->i_mode)
 				|| S_ISLNK(inode->i_mode)))
 		invalid &= ~NFS_INO_INVALID_DATA;
-	if (!nfs_have_delegation(inode, FMODE_READ) ||
+	if (!NFS_PROTO(inode)->have_delegation(inode, FMODE_READ) ||
 			(save_cache_validity & NFS_INO_REVAL_FORCED))
 		nfsi->cache_validity |= invalid;
 
+	if (invalid & NFS_INO_INVALID_DATA)
+		nfs_fscache_invalidate(inode);
+
 	return 0;
  out_err:
 	/*
@@ -1472,27 +1517,6 @@ static int nfs_update_inode(struct inode *inode, struct nfs_fattr *fattr)
 	return -ESTALE;
 }
 
-
-#ifdef CONFIG_NFS_V4
-
-/*
- * Clean out any remaining NFSv4 state that might be left over due
- * to open() calls that passed nfs_atomic_lookup, but failed to call
- * nfs_open().
- */
-void nfs4_evict_inode(struct inode *inode)
-{
-	truncate_inode_pages(&inode->i_data, 0);
-	clear_inode(inode);
-	pnfs_return_layout(inode);
-	pnfs_destroy_layout(NFS_I(inode));
-	/* If we are holding a delegation, return it! */
-	nfs_inode_return_delegation_noreclaim(inode);
-	/* First call standard NFS clear_inode() code */
-	nfs_clear_inode(inode);
-}
-#endif
-
 struct inode *nfs_alloc_inode(struct super_block *sb)
 {
 	struct nfs_inode *nfsi;
@@ -1505,11 +1529,12 @@ struct inode *nfs_alloc_inode(struct super_block *sb)
 	nfsi->acl_access = ERR_PTR(-EAGAIN);
 	nfsi->acl_default = ERR_PTR(-EAGAIN);
 #endif
-#ifdef CONFIG_NFS_V4
+#if IS_ENABLED(CONFIG_NFS_V4)
 	nfsi->nfs4_acl = NULL;
 #endif /* CONFIG_NFS_V4 */
 	return &nfsi->vfs_inode;
 }
+EXPORT_SYMBOL_GPL(nfs_alloc_inode);
 
 static void nfs_i_callback(struct rcu_head *head)
 {
@@ -1521,10 +1546,11 @@ void nfs_destroy_inode(struct inode *inode)
 {
 	call_rcu(&inode->i_rcu, nfs_i_callback);
 }
+EXPORT_SYMBOL_GPL(nfs_destroy_inode);
 
 static inline void nfs4_init_once(struct nfs_inode *nfsi)
 {
-#ifdef CONFIG_NFS_V4
+#if IS_ENABLED(CONFIG_NFS_V4)
 	INIT_LIST_HEAD(&nfsi->open_states);
 	nfsi->delegation = NULL;
 	nfsi->delegation_state = 0;
@@ -1566,10 +1592,16 @@ static int __init nfs_init_inodecache(void)
 
 static void nfs_destroy_inodecache(void)
 {
+	/*
+	 * Make sure all delayed rcu free inodes are flushed before we
+	 * destroy cache.
+	 */
+	rcu_barrier();
 	kmem_cache_destroy(nfs_inode_cachep);
 }
 
 struct workqueue_struct *nfsiod_workqueue;
+EXPORT_SYMBOL_GPL(nfsiod_workqueue);
 
 /*
  * start up the nfsiod workqueue
@@ -1628,81 +1660,76 @@ static int __init init_nfs_fs(void)
 {
 	int err;
 
-	err = nfs_idmap_init();
-	if (err < 0)
-		goto out10;
-
 	err = nfs_dns_resolver_init();
 	if (err < 0)
-		goto out9;
+		goto out10;;
 
 	err = register_pernet_subsys(&nfs_net_ops);
 	if (err < 0)
-		goto out8;
+		goto out9;
 
 	err = nfs_fscache_register();
 	if (err < 0)
-		goto out7;
+		goto out8;
 
 	err = nfsiod_start();
 	if (err)
-		goto out6;
+		goto out7;
 
 	err = nfs_fs_proc_init();
 	if (err)
-		goto out5;
+		goto out6;
 
 	err = nfs_init_nfspagecache();
 	if (err)
-		goto out4;
+		goto out5;
 
 	err = nfs_init_inodecache();
 	if (err)
-		goto out3;
+		goto out4;
 
 	err = nfs_init_readpagecache();
 	if (err)
-		goto out2;
+		goto out3;
 
 	err = nfs_init_writepagecache();
 	if (err)
-		goto out1;
+		goto out2;
 
 	err = nfs_init_directcache();
 	if (err)
-		goto out0;
+		goto out1;
 
 #ifdef CONFIG_PROC_FS
 	rpc_proc_register(&init_net, &nfs_rpcstat);
 #endif
 	if ((err = register_nfs_fs()) != 0)
-		goto out;
+		goto out0;
+
 	return 0;
-out:
+out0:
 #ifdef CONFIG_PROC_FS
 	rpc_proc_unregister(&init_net, "nfs");
 #endif
 	nfs_destroy_directcache();
-out0:
-	nfs_destroy_writepagecache();
 out1:
-	nfs_destroy_readpagecache();
+	nfs_destroy_writepagecache();
 out2:
-	nfs_destroy_inodecache();
+	nfs_destroy_readpagecache();
 out3:
-	nfs_destroy_nfspagecache();
+	nfs_destroy_inodecache();
 out4:
-	nfs_fs_proc_exit();
+	nfs_destroy_nfspagecache();
 out5:
-	nfsiod_stop();
+	nfs_fs_proc_exit();
 out6:
-	nfs_fscache_unregister();
+	nfsiod_stop();
 out7:
-	unregister_pernet_subsys(&nfs_net_ops);
+	nfs_fscache_unregister();
 out8:
-	nfs_dns_resolver_destroy();
+	unregister_pernet_subsys(&nfs_net_ops);
 out9:
-	nfs_idmap_quit();
+	nfs_dns_resolver_destroy();
 out10:
 	return err;
 }
@@ -1717,7 +1744,6 @@ static void __exit exit_nfs_fs(void)
 	nfs_fscache_unregister();
 	unregister_pernet_subsys(&nfs_net_ops);
 	nfs_dns_resolver_destroy();
-	nfs_idmap_quit();
 #ifdef CONFIG_PROC_FS
 	rpc_proc_unregister(&init_net, "nfs");
 #endif
diff --git a/fs/nfs/internal.h b/fs/nfs/internal.h
index 18f99ef7134..f0e6c7df1a0 100644
--- a/fs/nfs/internal.h
+++ b/fs/nfs/internal.h
@@ -18,27 +18,6 @@ struct nfs_string;
  */
 #define NFS_MAX_READAHEAD	(RPC_DEF_SLOT_TABLE - 1)
 
-/*
- * Determine if sessions are in use.
- */
-static inline int nfs4_has_session(const struct nfs_client *clp)
-{
-#ifdef CONFIG_NFS_V4_1
-	if (clp->cl_session)
-		return 1;
-#endif /* CONFIG_NFS_V4_1 */
-	return 0;
-}
-
-static inline int nfs4_has_persistent_session(const struct nfs_client *clp)
-{
-#ifdef CONFIG_NFS_V4_1
-	if (nfs4_has_session(clp))
-		return (clp->cl_session->flags & SESSION4_PERSIST);
-#endif /* CONFIG_NFS_V4_1 */
-	return 0;
-}
-
 static inline void nfs_attr_check_mountpoint(struct super_block *parent, struct nfs_fattr *fattr)
 {
 	if (!nfs_fsid_equal(&NFS_SB(parent)->fsid, &fattr->fsid))
@@ -85,16 +64,27 @@ struct nfs_clone_mount {
  */
 #define NFS_MAX_READDIR_PAGES 8
 
+struct nfs_client_initdata {
+	unsigned long init_flags;
+	const char *hostname;
+	const struct sockaddr *addr;
+	size_t addrlen;
+	struct nfs_subversion *nfs_mod;
+	int proto;
+	u32 minorversion;
+	struct net *net;
+};
+
 /*
  * In-kernel mount arguments
  */
 struct nfs_parsed_mount_data {
 	int			flags;
-	int			rsize, wsize;
-	int			timeo, retrans;
-	int			acregmin, acregmax,
+	unsigned int		rsize, wsize;
+	unsigned int		timeo, retrans;
+	unsigned int		acregmin, acregmax,
 				acdirmin, acdirmax;
-	int			namlen;
+	unsigned int		namlen;
 	unsigned int		options;
 	unsigned int		bsize;
 	unsigned int		auth_flavor_len;
@@ -142,25 +132,45 @@ struct nfs_mount_request {
 	struct net		*net;
 };
 
+struct nfs_mount_info {
+	void (*fill_super)(struct super_block *, struct nfs_mount_info *);
+	int (*set_security)(struct super_block *, struct dentry *, struct nfs_mount_info *);
+	struct nfs_parsed_mount_data *parsed;
+	struct nfs_clone_mount *cloned;
+	struct nfs_fh *mntfh;
+};
+
 extern int nfs_mount(struct nfs_mount_request *info);
 extern void nfs_umount(const struct nfs_mount_request *info);
 
 /* client.c */
 extern const struct rpc_program nfs_program;
 extern void nfs_clients_init(struct net *net);
+extern struct nfs_client *nfs_alloc_client(const struct nfs_client_initdata *);
+int nfs_create_rpc_client(struct nfs_client *, const struct rpc_timeout *, rpc_authflavor_t);
+struct nfs_client *nfs_get_client(const struct nfs_client_initdata *,
+				  const struct rpc_timeout *, const char *,
+				  rpc_authflavor_t);
+int nfs_probe_fsinfo(struct nfs_server *server, struct nfs_fh *, struct nfs_fattr *);
+void nfs_server_insert_lists(struct nfs_server *);
+void nfs_init_timeout_values(struct rpc_timeout *, int, unsigned int, unsigned int);
+int nfs_init_server_rpcclient(struct nfs_server *, const struct rpc_timeout *t,
+		rpc_authflavor_t);
+struct nfs_server *nfs_alloc_server(void);
+void nfs_server_copy_userdata(struct nfs_server *, struct nfs_server *);
 
 extern void nfs_cleanup_cb_ident_idr(struct net *);
 extern void nfs_put_client(struct nfs_client *);
+extern void nfs_free_client(struct nfs_client *);
 extern struct nfs_client *nfs4_find_client_ident(struct net *, int);
 extern struct nfs_client *
 nfs4_find_client_sessionid(struct net *, const struct sockaddr *,
 				struct nfs4_sessionid *);
-extern struct nfs_server *nfs_create_server(
-					const struct nfs_parsed_mount_data *,
-					struct nfs_fh *);
+extern struct nfs_server *nfs_create_server(struct nfs_mount_info *,
+					struct nfs_subversion *);
 extern struct nfs_server *nfs4_create_server(
-					const struct nfs_parsed_mount_data *,
-					struct nfs_fh *);
+					struct nfs_mount_info *,
+					struct nfs_subversion *);
 extern struct nfs_server *nfs4_create_referral_server(struct nfs_clone_mount *,
 						      struct nfs_fh *);
 extern void nfs_free_server(struct nfs_server *server);
@@ -188,6 +198,17 @@ static inline void nfs_fs_proc_exit(void)
 }
 #endif
 
+#ifdef CONFIG_NFS_V4_1
+int nfs_sockaddr_match_ipaddr(const struct sockaddr *, const struct sockaddr *);
+#endif
+
+/* nfs3client.c */
+#if IS_ENABLED(CONFIG_NFS_V3)
+struct nfs_server *nfs3_create_server(struct nfs_mount_info *, struct nfs_subversion *);
+struct nfs_server *nfs3_clone_server(struct nfs_server *, struct nfs_fh *,
+				     struct nfs_fattr *, rpc_authflavor_t);
+#endif
+
 /* callback_xdr.c */
 extern struct svc_version nfs4_callback_version1;
 extern struct svc_version nfs4_callback_version4;
@@ -220,7 +241,7 @@ extern int nfs3_decode_dirent(struct xdr_stream *,
 				struct nfs_entry *, int);
 
 /* nfs4xdr.c */
-#ifdef CONFIG_NFS_V4
+#if IS_ENABLED(CONFIG_NFS_V4)
 extern int nfs4_decode_dirent(struct xdr_stream *,
 				struct nfs_entry *, int);
 #endif
@@ -230,12 +251,10 @@ extern const u32 nfs41_maxwrite_overhead;
 #endif
 
 /* nfs4proc.c */
-#ifdef CONFIG_NFS_V4
+#if IS_ENABLED(CONFIG_NFS_V4)
 extern struct rpc_procinfo nfs4_procedures[];
 #endif
 
-extern int nfs4_init_ds_session(struct nfs_client *, unsigned long);
-
 /* proc.c */
 void nfs_close_context(struct nfs_open_context *ctx, int is_sync);
 extern struct nfs_client *nfs_init_client(struct nfs_client *clp,
@@ -245,25 +264,64 @@ extern struct nfs_client *nfs_init_client(struct nfs_client *clp,
 /* dir.c */
 extern int nfs_access_cache_shrinker(struct shrinker *shrink,
 					struct shrink_control *sc);
+struct dentry *nfs_lookup(struct inode *, struct dentry *, unsigned int);
+int nfs_create(struct inode *, struct dentry *, umode_t, bool);
+int nfs_mkdir(struct inode *, struct dentry *, umode_t);
+int nfs_rmdir(struct inode *, struct dentry *);
+int nfs_unlink(struct inode *, struct dentry *);
+int nfs_symlink(struct inode *, struct dentry *, const char *);
+int nfs_link(struct dentry *, struct inode *, struct dentry *);
+int nfs_mknod(struct inode *, struct dentry *, umode_t, dev_t);
+int nfs_rename(struct inode *, struct dentry *, struct inode *, struct dentry *);
+
+/* file.c */
+int nfs_file_fsync_commit(struct file *, loff_t, loff_t, int);
+loff_t nfs_file_llseek(struct file *, loff_t, int);
+int nfs_file_flush(struct file *, fl_owner_t);
+ssize_t nfs_file_read(struct kiocb *, const struct iovec *, unsigned long, loff_t);
+ssize_t nfs_file_splice_read(struct file *, loff_t *, struct pipe_inode_info *,
+			     size_t, unsigned int);
+int nfs_file_mmap(struct file *, struct vm_area_struct *);
+ssize_t nfs_file_write(struct kiocb *, const struct iovec *, unsigned long, loff_t);
+int nfs_file_release(struct inode *, struct file *);
+int nfs_lock(struct file *, int, struct file_lock *);
+int nfs_flock(struct file *, int, struct file_lock *);
+ssize_t nfs_file_splice_write(struct pipe_inode_info *, struct file *, loff_t *,
+			      size_t, unsigned int);
+int nfs_check_flags(int);
+int nfs_setlease(struct file *, long, struct file_lock **);
 
 /* inode.c */
 extern struct workqueue_struct *nfsiod_workqueue;
 extern struct inode *nfs_alloc_inode(struct super_block *sb);
 extern void nfs_destroy_inode(struct inode *);
 extern int nfs_write_inode(struct inode *, struct writeback_control *);
+extern int nfs_drop_inode(struct inode *);
+extern void nfs_clear_inode(struct inode *);
 extern void nfs_evict_inode(struct inode *);
-#ifdef CONFIG_NFS_V4
-extern void nfs4_evict_inode(struct inode *);
-#endif
 void nfs_zap_acl_cache(struct inode *inode);
 extern int nfs_wait_bit_killable(void *word);
 
 /* super.c */
+extern const struct super_operations nfs_sops;
+extern struct file_system_type nfs_fs_type;
 extern struct file_system_type nfs_xdev_fs_type;
-#ifdef CONFIG_NFS_V4
+#if IS_ENABLED(CONFIG_NFS_V4)
 extern struct file_system_type nfs4_xdev_fs_type;
 extern struct file_system_type nfs4_referral_fs_type;
 #endif
+struct dentry *nfs_try_mount(int, const char *, struct nfs_mount_info *,
+			struct nfs_subversion *);
+void nfs_initialise_sb(struct super_block *);
+int nfs_set_sb_security(struct super_block *, struct dentry *, struct nfs_mount_info *);
+int nfs_clone_sb_security(struct super_block *, struct dentry *, struct nfs_mount_info *);
+struct dentry *nfs_fs_mount_common(struct nfs_server *, int, const char *,
+				   struct nfs_mount_info *, struct nfs_subversion *);
+struct dentry *nfs_fs_mount(struct file_system_type *, int, const char *, void *);
+struct dentry * nfs_xdev_mount_common(struct file_system_type *, int,
+		const char *, struct nfs_mount_info *);
+void nfs_kill_super(struct super_block *);
+void nfs_fill_super(struct super_block *, struct nfs_mount_info *);
 
 extern struct rpc_stat nfs_rpcstat;
 
@@ -271,10 +329,12 @@ extern int __init register_nfs_fs(void);
 extern void __exit unregister_nfs_fs(void);
 extern void nfs_sb_active(struct super_block *sb);
 extern void nfs_sb_deactive(struct super_block *sb);
+extern void nfs_sb_deactive_async(struct super_block *sb);
 
 /* namespace.c */
+#define NFS_PATH_CANONICAL 1
 extern char *nfs_path(char **p, struct dentry *dentry,
-		      char *buffer, ssize_t buflen);
+		      char *buffer, ssize_t buflen, unsigned flags);
 extern struct vfsmount *nfs_d_automount(struct path *path);
 struct vfsmount *nfs_submount(struct nfs_server *, struct dentry *,
 			      struct nfs_fh *, struct nfs_fattr *);
@@ -284,7 +344,7 @@ struct vfsmount *nfs_do_submount(struct dentry *, struct nfs_fh *,
 /* getroot.c */
 extern struct dentry *nfs_get_root(struct super_block *, struct nfs_fh *,
 				   const char *);
-#ifdef CONFIG_NFS_V4
+#if IS_ENABLED(CONFIG_NFS_V4)
 extern struct dentry *nfs4_get_root(struct super_block *, struct nfs_fh *,
 				    const char *);
 
@@ -304,12 +364,20 @@ extern int nfs_initiate_read(struct rpc_clnt *clnt,
 extern void nfs_read_prepare(struct rpc_task *task, void *calldata);
 extern int nfs_generic_pagein(struct nfs_pageio_descriptor *desc,
 			      struct nfs_pgio_header *hdr);
-extern void nfs_pageio_init_read_mds(struct nfs_pageio_descriptor *pgio,
-			struct inode *inode,
-			const struct nfs_pgio_completion_ops *compl_ops);
 extern void nfs_pageio_reset_read_mds(struct nfs_pageio_descriptor *pgio);
 extern void nfs_readdata_release(struct nfs_read_data *rdata);
 
+/* super.c */
+void nfs_clone_super(struct super_block *, struct nfs_mount_info *);
+void nfs_umount_begin(struct super_block *);
+int  nfs_statfs(struct dentry *, struct kstatfs *);
+int  nfs_show_options(struct seq_file *, struct dentry *);
+int  nfs_show_devname(struct seq_file *, struct dentry *);
+int  nfs_show_path(struct seq_file *, struct dentry *);
+int  nfs_show_stats(struct seq_file *, struct dentry *);
+void nfs_put_super(struct super_block *);
+int nfs_remount(struct super_block *sb, int *flags, char *raw_data);
+
 /* write.c */
 extern void nfs_pageio_init_write(struct nfs_pageio_descriptor *pgio,
 			struct inode *inode, int ioflags,
@@ -318,9 +386,6 @@ extern struct nfs_write_header *nfs_writehdr_alloc(void);
 extern void nfs_writehdr_free(struct nfs_pgio_header *hdr);
 extern int nfs_generic_flush(struct nfs_pageio_descriptor *desc,
 			     struct nfs_pgio_header *hdr);
-extern void nfs_pageio_init_write_mds(struct nfs_pageio_descriptor *pgio,
-			struct inode *inode, int ioflags,
-			const struct nfs_pgio_completion_ops *compl_ops);
 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_commit_data *p);
@@ -373,6 +438,7 @@ static inline void nfs_inode_dio_wait(struct inode *inode)
 {
 	inode_dio_wait(inode);
 }
+extern ssize_t nfs_dreq_bytes_left(struct nfs_direct_req *dreq);
 
 /* nfs4proc.c */
 extern void __nfs4_read_done_cb(struct nfs_read_data *);
@@ -380,18 +446,12 @@ extern struct nfs_client *nfs4_init_client(struct nfs_client *clp,
 			    const struct rpc_timeout *timeparms,
 			    const char *ip_addr,
 			    rpc_authflavor_t authflavour);
-extern int _nfs4_call_sync(struct rpc_clnt *clnt,
-			   struct nfs_server *server,
-			   struct rpc_message *msg,
-			   struct nfs4_sequence_args *args,
-			   struct nfs4_sequence_res *res,
-			   int cache_reply);
-extern int _nfs4_call_sync_session(struct rpc_clnt *clnt,
-				   struct nfs_server *server,
-				   struct rpc_message *msg,
-				   struct nfs4_sequence_args *args,
-				   struct nfs4_sequence_res *res,
-				   int cache_reply);
+extern int nfs40_walk_client_list(struct nfs_client *clp,
+				struct nfs_client **result,
+				struct rpc_cred *cred);
+extern int nfs41_walk_client_list(struct nfs_client *clp,
+				struct nfs_client **result,
+				struct rpc_cred *cred);
 
 /*
  * Determine the device name as a string
@@ -400,7 +460,7 @@ static inline char *nfs_devname(struct dentry *dentry,
 				char *buffer, ssize_t buflen)
 {
 	char *dummy;
-	return nfs_path(&dummy, dentry, buffer, buflen);
+	return nfs_path(&dummy, dentry, buffer, buflen, NFS_PATH_CANONICAL);
 }
 
 /*
@@ -463,13 +523,14 @@ void nfs_super_set_maxbytes(struct super_block *sb, __u64 maxfilesize)
 static inline
 unsigned int nfs_page_length(struct page *page)
 {
-	loff_t i_size = i_size_read(page->mapping->host);
+	loff_t i_size = i_size_read(page_file_mapping(page)->host);
 
 	if (i_size > 0) {
+		pgoff_t page_index = page_file_index(page);
 		pgoff_t end_index = (i_size - 1) >> PAGE_CACHE_SHIFT;
-		if (page->index < end_index)
+		if (page_index < end_index)
 			return PAGE_CACHE_SIZE;
-		if (page->index == end_index)
+		if (page_index == end_index)
 			return ((i_size - 1) & ~PAGE_CACHE_MASK) + 1;
 	}
 	return 0;
diff --git a/fs/nfs/mount_clnt.c b/fs/nfs/mount_clnt.c
index 8e65c7f1f87..91a6faf811a 100644
--- a/fs/nfs/mount_clnt.c
+++ b/fs/nfs/mount_clnt.c
@@ -169,6 +169,9 @@ int nfs_mount(struct nfs_mount_request *info)
 		(info->hostname ? info->hostname : "server"),
 			info->dirpath);
 
+	if (strlen(info->dirpath) > MNTPATHLEN)
+		return -ENAMETOOLONG;
+
 	if (info->noresvport)
 		args.flags |= RPC_CLNT_CREATE_NONPRIVPORT;
 
@@ -181,7 +184,7 @@ int nfs_mount(struct nfs_mount_request *info)
 	else
 		msg.rpc_proc = &mnt_clnt->cl_procinfo[MOUNTPROC_MNT];
 
-	status = rpc_call_sync(mnt_clnt, &msg, 0);
+	status = rpc_call_sync(mnt_clnt, &msg, RPC_TASK_SOFT|RPC_TASK_TIMEOUT);
 	rpc_shutdown_client(mnt_clnt);
 
 	if (status < 0)
@@ -242,6 +245,9 @@ void nfs_umount(const struct nfs_mount_request *info)
 	struct rpc_clnt *clnt;
 	int status;
 
+	if (strlen(info->dirpath) > MNTPATHLEN)
+		return;
+
 	if (info->noresvport)
 		args.flags |= RPC_CLNT_CREATE_NONPRIVPORT;
 
@@ -283,7 +289,6 @@ static void encode_mntdirpath(struct xdr_stream *xdr, const char *pathname)
 	const u32 pathname_len = strlen(pathname);
 	__be32 *p;
 
-	BUG_ON(pathname_len > MNTPATHLEN);
 	p = xdr_reserve_space(xdr, 4 + pathname_len);
 	xdr_encode_opaque(p, pathname, pathname_len);
 }
diff --git a/fs/nfs/namespace.c b/fs/nfs/namespace.c
index 08b9c93675d..fc8dc20fdeb 100644
--- a/fs/nfs/namespace.c
+++ b/fs/nfs/namespace.c
@@ -7,6 +7,7 @@
  * NFS namespace
  */
 
+#include <linux/module.h>
 #include <linux/dcache.h>
 #include <linux/gfp.h>
 #include <linux/mount.h>
@@ -32,6 +33,7 @@ int nfs_mountpoint_expiry_timeout = 500 * HZ;
  * @dentry - pointer to dentry
  * @buffer - result buffer
  * @buflen - length of buffer
+ * @flags - options (see below)
  *
  * Helper function for constructing the server pathname
  * by arbitrary hashed dentry.
@@ -39,8 +41,14 @@ int nfs_mountpoint_expiry_timeout = 500 * HZ;
  * This is mainly for use in figuring out the path on the
  * server side when automounting on top of an existing partition
  * and in generating /proc/mounts and friends.
+ *
+ * Supported flags:
+ * NFS_PATH_CANONICAL: ensure there is exactly one slash after
+ *		       the original device (export) name
+ *		       (if unset, the original name is returned verbatim)
  */
-char *nfs_path(char **p, struct dentry *dentry, char *buffer, ssize_t buflen)
+char *nfs_path(char **p, struct dentry *dentry, char *buffer, ssize_t buflen,
+	       unsigned flags)
 {
 	char *end;
 	int namelen;
@@ -73,7 +81,7 @@ rename_retry:
 		rcu_read_unlock();
 		goto rename_retry;
 	}
-	if (*end != '/') {
+	if ((flags & NFS_PATH_CANONICAL) && *end != '/') {
 		if (--buflen < 0) {
 			spin_unlock(&dentry->d_lock);
 			rcu_read_unlock();
@@ -90,9 +98,11 @@ rename_retry:
 		return end;
 	}
 	namelen = strlen(base);
-	/* Strip off excess slashes in base string */
-	while (namelen > 0 && base[namelen - 1] == '/')
-		namelen--;
+	if (flags & NFS_PATH_CANONICAL) {
+		/* Strip off excess slashes in base string */
+		while (namelen > 0 && base[namelen - 1] == '/')
+			namelen--;
+	}
 	buflen -= namelen;
 	if (buflen < 0) {
 		spin_unlock(&dentry->d_lock);
@@ -112,6 +122,7 @@ Elong_unlock:
 Elong:
 	return ERR_PTR(-ENAMETOOLONG);
 }
+EXPORT_SYMBOL_GPL(nfs_path);
 
 /*
  * nfs_d_automount - Handle crossing a mountpoint on the server
@@ -166,11 +177,31 @@ out_nofree:
 	return mnt;
 }
 
+static int
+nfs_namespace_getattr(struct vfsmount *mnt, struct dentry *dentry, struct kstat *stat)
+{
+	if (NFS_FH(dentry->d_inode)->size != 0)
+		return nfs_getattr(mnt, dentry, stat);
+	generic_fillattr(dentry->d_inode, stat);
+	return 0;
+}
+
+static int
+nfs_namespace_setattr(struct dentry *dentry, struct iattr *attr)
+{
+	if (NFS_FH(dentry->d_inode)->size != 0)
+		return nfs_setattr(dentry, attr);
+	return -EACCES;
+}
+
 const struct inode_operations nfs_mountpoint_inode_operations = {
 	.getattr	= nfs_getattr,
+	.setattr	= nfs_setattr,
 };
 
 const struct inode_operations nfs_referral_inode_operations = {
+	.getattr	= nfs_namespace_getattr,
+	.setattr	= nfs_namespace_setattr,
 };
 
 static void nfs_expire_automounts(struct work_struct *work)
@@ -195,20 +226,7 @@ static struct vfsmount *nfs_do_clone_mount(struct nfs_server *server,
 					   const char *devname,
 					   struct nfs_clone_mount *mountdata)
 {
-#ifdef CONFIG_NFS_V4
-	struct vfsmount *mnt = ERR_PTR(-EINVAL);
-	switch (server->nfs_client->rpc_ops->version) {
-		case 2:
-		case 3:
-			mnt = vfs_kern_mount(&nfs_xdev_fs_type, 0, devname, mountdata);
-			break;
-		case 4:
-			mnt = vfs_kern_mount(&nfs4_xdev_fs_type, 0, devname, mountdata);
-	}
-	return mnt;
-#else
 	return vfs_kern_mount(&nfs_xdev_fs_type, 0, devname, mountdata);
-#endif
 }
 
 /**
@@ -253,6 +271,7 @@ out:
 	dprintk("<-- nfs_do_submount() = %p\n", mnt);
 	return mnt;
 }
+EXPORT_SYMBOL_GPL(nfs_do_submount);
 
 struct vfsmount *nfs_submount(struct nfs_server *server, struct dentry *dentry,
 			      struct nfs_fh *fh, struct nfs_fattr *fattr)
@@ -268,3 +287,4 @@ struct vfsmount *nfs_submount(struct nfs_server *server, struct dentry *dentry,
 
 	return nfs_do_submount(dentry, fh, fattr, server->client->cl_auth->au_flavor);
 }
+EXPORT_SYMBOL_GPL(nfs_submount);
diff --git a/fs/nfs/netns.h b/fs/nfs/netns.h
index 8a6394edb8b..8ee1fab8326 100644
--- a/fs/nfs/netns.h
+++ b/fs/nfs/netns.h
@@ -5,6 +5,7 @@
 #ifndef __NFS_NETNS_H__
 #define __NFS_NETNS_H__
 
+#include <linux/nfs4.h>
 #include <net/net_namespace.h>
 #include <net/netns/generic.h>
 
@@ -20,8 +21,11 @@ struct nfs_net {
 	wait_queue_head_t bl_wq;
 	struct list_head nfs_client_list;
 	struct list_head nfs_volume_list;
-#ifdef CONFIG_NFS_V4
+#if IS_ENABLED(CONFIG_NFS_V4)
 	struct idr cb_ident_idr; /* Protected by nfs_client_lock */
+	unsigned short nfs_callback_tcpport;
+	unsigned short nfs_callback_tcpport6;
+	int cb_users[NFS4_MAX_MINOR_VERSION + 1];
 #endif
 	spinlock_t nfs_client_lock;
 	struct timespec boot_time;
diff --git a/fs/nfs/nfs.h b/fs/nfs/nfs.h
new file mode 100644
index 00000000000..43679df56cd
--- /dev/null
+++ b/fs/nfs/nfs.h
@@ -0,0 +1,29 @@
+/*
+ * Copyright (c) 2012 Netapp, Inc. All rights reserved.
+ *
+ * Function and structures exported by the NFS module
+ * for use by NFS version-specific modules.
+ */
+#ifndef __LINUX_INTERNAL_NFS_H
+#define __LINUX_INTERNAL_NFS_H
+
+#include <linux/fs.h>
+#include <linux/sunrpc/sched.h>
+#include <linux/nfs_xdr.h>
+
+struct nfs_subversion {
+	struct module *owner;	/* THIS_MODULE pointer */
+	struct file_system_type *nfs_fs;	/* NFS filesystem type */
+	const struct rpc_version *rpc_vers;	/* NFS version information */
+	const struct nfs_rpc_ops *rpc_ops;	/* NFS operations */
+	const struct super_operations *sops;	/* NFS Super operations */
+	const struct xattr_handler **xattr;	/* NFS xattr handlers */
+	struct list_head list;		/* List of NFS versions */
+};
+
+struct nfs_subversion *get_nfs_version(unsigned int);
+void put_nfs_version(struct nfs_subversion *);
+void register_nfs_version(struct nfs_subversion *);
+void unregister_nfs_version(struct nfs_subversion *);
+
+#endif /* __LINUX_INTERNAL_NFS_H */
diff --git a/fs/nfs/nfs2super.c b/fs/nfs/nfs2super.c
new file mode 100644
index 00000000000..0a9782c9171
--- /dev/null
+++ b/fs/nfs/nfs2super.c
@@ -0,0 +1,31 @@
+/*
+ * Copyright (c) 2012 Netapp, Inc. All rights reserved.
+ */
+#include <linux/module.h>
+#include <linux/nfs_fs.h>
+#include "internal.h"
+#include "nfs.h"
+
+static struct nfs_subversion nfs_v2 = {
+	.owner = THIS_MODULE,
+	.nfs_fs   = &nfs_fs_type,
+	.rpc_vers = &nfs_version2,
+	.rpc_ops  = &nfs_v2_clientops,
+	.sops     = &nfs_sops,
+};
+
+static int __init init_nfs_v2(void)
+{
+	register_nfs_version(&nfs_v2);
+	return 0;
+}
+
+static void __exit exit_nfs_v2(void)
+{
+	unregister_nfs_version(&nfs_v2);
+}
+
+MODULE_LICENSE("GPL");
+
+module_init(init_nfs_v2);
+module_exit(exit_nfs_v2);
diff --git a/fs/nfs/nfs2xdr.c b/fs/nfs/nfs2xdr.c
index baf759bccd0..06b9df49f7f 100644
--- a/fs/nfs/nfs2xdr.c
+++ b/fs/nfs/nfs2xdr.c
@@ -106,19 +106,16 @@ static void print_overflow_msg(const char *func, const struct xdr_stream *xdr)
 static int decode_nfsdata(struct xdr_stream *xdr, struct nfs_readres *result)
 {
 	u32 recvd, count;
-	size_t hdrlen;
 	__be32 *p;
 
 	p = xdr_inline_decode(xdr, 4);
 	if (unlikely(p == NULL))
 		goto out_overflow;
 	count = be32_to_cpup(p);
-	hdrlen = (u8 *)xdr->p - (u8 *)xdr->iov->iov_base;
-	recvd = xdr->buf->len - hdrlen;
+	recvd = xdr_read_pages(xdr, count);
 	if (unlikely(count > recvd))
 		goto out_cheating;
 out:
-	xdr_read_pages(xdr, count);
 	result->eof = 0;	/* NFSv2 does not pass EOF flag on the wire. */
 	result->count = count;
 	return count;
@@ -198,7 +195,6 @@ static void encode_fhandle(struct xdr_stream *xdr, const struct nfs_fh *fh)
 {
 	__be32 *p;
 
-	BUG_ON(fh->size != NFS2_FHSIZE);
 	p = xdr_reserve_space(xdr, NFS2_FHSIZE);
 	memcpy(p, fh->data, NFS2_FHSIZE);
 }
@@ -391,7 +387,7 @@ static void encode_filename(struct xdr_stream *xdr,
 {
 	__be32 *p;
 
-	BUG_ON(length > NFS2_MAXNAMLEN);
+	WARN_ON_ONCE(length > NFS2_MAXNAMLEN);
 	p = xdr_reserve_space(xdr, 4 + length);
 	xdr_encode_opaque(p, name, length);
 }
@@ -431,7 +427,6 @@ static void encode_path(struct xdr_stream *xdr, struct page **pages, u32 length)
 {
 	__be32 *p;
 
-	BUG_ON(length > NFS2_MAXPATHLEN);
 	p = xdr_reserve_space(xdr, 4);
 	*p = cpu_to_be32(length);
 	xdr_write_pages(xdr, pages, 0, length);
@@ -440,7 +435,6 @@ static void encode_path(struct xdr_stream *xdr, struct page **pages, u32 length)
 static int decode_path(struct xdr_stream *xdr)
 {
 	u32 length, recvd;
-	size_t hdrlen;
 	__be32 *p;
 
 	p = xdr_inline_decode(xdr, 4);
@@ -449,12 +443,9 @@ static int decode_path(struct xdr_stream *xdr)
 	length = be32_to_cpup(p);
 	if (unlikely(length >= xdr->buf->page_len || length > NFS_MAXPATHLEN))
 		goto out_size;
-	hdrlen = (u8 *)xdr->p - (u8 *)xdr->iov->iov_base;
-	recvd = xdr->buf->len - hdrlen;
+	recvd = xdr_read_pages(xdr, length);
 	if (unlikely(length > recvd))
 		goto out_cheating;
-
-	xdr_read_pages(xdr, length);
 	xdr_terminate_string(xdr->buf, length);
 	return 0;
 out_size:
@@ -972,22 +963,7 @@ out_overflow:
  */
 static int decode_readdirok(struct xdr_stream *xdr)
 {
-	u32 recvd, pglen;
-	size_t hdrlen;
-
-	pglen = xdr->buf->page_len;
-	hdrlen = (u8 *)xdr->p - (u8 *)xdr->iov->iov_base;
-	recvd = xdr->buf->len - hdrlen;
-	if (unlikely(pglen > recvd))
-		goto out_cheating;
-out:
-	xdr_read_pages(xdr, pglen);
-	return pglen;
-out_cheating:
-	dprintk("NFS: server cheating in readdir result: "
-		"pglen %u > recvd %u\n", pglen, recvd);
-	pglen = recvd;
-	goto out;
+	return xdr_read_pages(xdr, xdr->buf->page_len);
 }
 
 static int nfs2_xdr_dec_readdirres(struct rpc_rqst *req,
diff --git a/fs/nfs/nfs3acl.c b/fs/nfs/nfs3acl.c
index e4498dc351a..4a1aafba6a2 100644
--- a/fs/nfs/nfs3acl.c
+++ b/fs/nfs/nfs3acl.c
@@ -70,7 +70,7 @@ ssize_t nfs3_getxattr(struct dentry *dentry, const char *name,
 		if (type == ACL_TYPE_ACCESS && acl->a_count == 0)
 			error = -ENODATA;
 		else
-			error = posix_acl_to_xattr(acl, buffer, size);
+			error = posix_acl_to_xattr(&init_user_ns, acl, buffer, size);
 		posix_acl_release(acl);
 	} else
 		error = -ENODATA;
@@ -92,7 +92,7 @@ int nfs3_setxattr(struct dentry *dentry, const char *name,
 	else
 		return -EOPNOTSUPP;
 
-	acl = posix_acl_from_xattr(value, size);
+	acl = posix_acl_from_xattr(&init_user_ns, value, size);
 	if (IS_ERR(acl))
 		return PTR_ERR(acl);
 	error = nfs3_proc_setacl(inode, type, acl);
diff --git a/fs/nfs/nfs3client.c b/fs/nfs/nfs3client.c
new file mode 100644
index 00000000000..b3fc65ef39c
--- /dev/null
+++ b/fs/nfs/nfs3client.c
@@ -0,0 +1,65 @@
+#include <linux/nfs_fs.h>
+#include <linux/nfs_mount.h>
+#include "internal.h"
+
+#ifdef CONFIG_NFS_V3_ACL
+static struct rpc_stat		nfsacl_rpcstat = { &nfsacl_program };
+static const struct rpc_version *nfsacl_version[] = {
+	[3]			= &nfsacl_version3,
+};
+
+const struct rpc_program nfsacl_program = {
+	.name			= "nfsacl",
+	.number			= NFS_ACL_PROGRAM,
+	.nrvers			= ARRAY_SIZE(nfsacl_version),
+	.version		= nfsacl_version,
+	.stats			= &nfsacl_rpcstat,
+};
+
+/*
+ * Initialise an NFSv3 ACL client connection
+ */
+static void nfs_init_server_aclclient(struct nfs_server *server)
+{
+	if (server->flags & NFS_MOUNT_NOACL)
+		goto out_noacl;
+
+	server->client_acl = rpc_bind_new_program(server->client, &nfsacl_program, 3);
+	if (IS_ERR(server->client_acl))
+		goto out_noacl;
+
+	/* No errors! Assume that Sun nfsacls are supported */
+	server->caps |= NFS_CAP_ACLS;
+	return;
+
+out_noacl:
+	server->caps &= ~NFS_CAP_ACLS;
+}
+#else
+static inline void nfs_init_server_aclclient(struct nfs_server *server)
+{
+	server->flags &= ~NFS_MOUNT_NOACL;
+	server->caps &= ~NFS_CAP_ACLS;
+}
+#endif
+
+struct nfs_server *nfs3_create_server(struct nfs_mount_info *mount_info,
+				      struct nfs_subversion *nfs_mod)
+{
+	struct nfs_server *server = nfs_create_server(mount_info, nfs_mod);
+	/* Create a client RPC handle for the NFS v3 ACL management interface */
+	if (!IS_ERR(server))
+		nfs_init_server_aclclient(server);
+	return server;
+}
+
+struct nfs_server *nfs3_clone_server(struct nfs_server *source,
+				     struct nfs_fh *fh,
+				     struct nfs_fattr *fattr,
+				     rpc_authflavor_t flavor)
+{
+	struct nfs_server *server = nfs_clone_server(source, fh, fattr, flavor);
+	if (!IS_ERR(server) && !IS_ERR(source->client_acl))
+		nfs_init_server_aclclient(server);
+	return server;
+}
diff --git a/fs/nfs/nfs3proc.c b/fs/nfs/nfs3proc.c
index 2292a0fd2bf..70efb63b1e4 100644
--- a/fs/nfs/nfs3proc.c
+++ b/fs/nfs/nfs3proc.c
@@ -24,14 +24,14 @@
 
 #define NFSDBG_FACILITY		NFSDBG_PROC
 
-/* A wrapper to handle the EJUKEBOX and EKEYEXPIRED error messages */
+/* A wrapper to handle the EJUKEBOX error messages */
 static int
 nfs3_rpc_wrapper(struct rpc_clnt *clnt, struct rpc_message *msg, int flags)
 {
 	int res;
 	do {
 		res = rpc_call_sync(clnt, msg, flags);
-		if (res != -EJUKEBOX && res != -EKEYEXPIRED)
+		if (res != -EJUKEBOX)
 			break;
 		freezable_schedule_timeout_killable(NFS_JUKEBOX_RETRY_TIME);
 		res = -ERESTARTSYS;
@@ -44,7 +44,7 @@ nfs3_rpc_wrapper(struct rpc_clnt *clnt, struct rpc_message *msg, int flags)
 static int
 nfs3_async_handle_jukebox(struct rpc_task *task, struct inode *inode)
 {
-	if (task->tk_status != -EJUKEBOX && task->tk_status != -EKEYEXPIRED)
+	if (task->tk_status != -EJUKEBOX)
 		return 0;
 	if (task->tk_status == -EJUKEBOX)
 		nfs_inc_stats(inode, NFSIOS_DELAY);
@@ -69,7 +69,7 @@ do_proc_get_root(struct rpc_clnt *client, struct nfs_fh *fhandle,
 	nfs_fattr_init(info->fattr);
 	status = rpc_call_sync(client, &msg, 0);
 	dprintk("%s: reply fsinfo: %d\n", __func__, status);
-	if (!(info->fattr->valid & NFS_ATTR_FATTR)) {
+	if (status == 0 && !(info->fattr->valid & NFS_ATTR_FATTR)) {
 		msg.rpc_proc = &nfs3_procedures[NFS3PROC_GETATTR];
 		msg.rpc_resp = info->fattr;
 		status = rpc_call_sync(client, &msg, 0);
@@ -314,7 +314,7 @@ static void nfs3_free_createdata(struct nfs3_createdata *data)
  */
 static int
 nfs3_proc_create(struct inode *dir, struct dentry *dentry, struct iattr *sattr,
-		 int flags, struct nfs_open_context *ctx)
+		 int flags)
 {
 	struct nfs3_createdata *data;
 	umode_t mode = sattr->ia_mode;
@@ -643,7 +643,7 @@ nfs3_proc_readdir(struct dentry *dentry, struct rpc_cred *cred,
 		  u64 cookie, struct page **pages, unsigned int count, int plus)
 {
 	struct inode		*dir = dentry->d_inode;
-	__be32			*verf = NFS_COOKIEVERF(dir);
+	__be32			*verf = NFS_I(dir)->cookieverf;
 	struct nfs3_readdirargs	arg = {
 		.fh		= NFS_FH(dir),
 		.cookie		= cookie,
@@ -877,6 +877,46 @@ nfs3_proc_lock(struct file *filp, int cmd, struct file_lock *fl)
 	return nlmclnt_proc(NFS_SERVER(inode)->nlm_host, cmd, fl);
 }
 
+static int nfs3_have_delegation(struct inode *inode, fmode_t flags)
+{
+	return 0;
+}
+
+static int nfs3_return_delegation(struct inode *inode)
+{
+	nfs_wb_all(inode);
+	return 0;
+}
+
+static const struct inode_operations nfs3_dir_inode_operations = {
+	.create		= nfs_create,
+	.lookup		= nfs_lookup,
+	.link		= nfs_link,
+	.unlink		= nfs_unlink,
+	.symlink	= nfs_symlink,
+	.mkdir		= nfs_mkdir,
+	.rmdir		= nfs_rmdir,
+	.mknod		= nfs_mknod,
+	.rename		= nfs_rename,
+	.permission	= nfs_permission,
+	.getattr	= nfs_getattr,
+	.setattr	= nfs_setattr,
+	.listxattr	= nfs3_listxattr,
+	.getxattr	= nfs3_getxattr,
+	.setxattr	= nfs3_setxattr,
+	.removexattr	= nfs3_removexattr,
+};
+
+static const struct inode_operations nfs3_file_inode_operations = {
+	.permission	= nfs_permission,
+	.getattr	= nfs_getattr,
+	.setattr	= nfs_setattr,
+	.listxattr	= nfs3_listxattr,
+	.getxattr	= nfs3_getxattr,
+	.setxattr	= nfs3_setxattr,
+	.removexattr	= nfs3_removexattr,
+};
+
 const struct nfs_rpc_ops nfs_v3_clientops = {
 	.version	= 3,			/* protocol version */
 	.dentry_ops	= &nfs_dentry_operations,
@@ -885,6 +925,7 @@ const struct nfs_rpc_ops nfs_v3_clientops = {
 	.file_ops	= &nfs_file_operations,
 	.getroot	= nfs3_proc_get_root,
 	.submount	= nfs_submount,
+	.try_mount	= nfs_try_mount,
 	.getattr	= nfs3_proc_getattr,
 	.setattr	= nfs3_proc_setattr,
 	.lookup		= nfs3_proc_lookup,
@@ -910,9 +951,11 @@ const struct nfs_rpc_ops nfs_v3_clientops = {
 	.pathconf	= nfs3_proc_pathconf,
 	.decode_dirent	= nfs3_decode_dirent,
 	.read_setup	= nfs3_proc_read_setup,
+	.read_pageio_init = nfs_pageio_init_read,
 	.read_rpc_prepare = nfs3_proc_read_rpc_prepare,
 	.read_done	= nfs3_read_done,
 	.write_setup	= nfs3_proc_write_setup,
+	.write_pageio_init = nfs_pageio_init_write,
 	.write_rpc_prepare = nfs3_proc_write_rpc_prepare,
 	.write_done	= nfs3_write_done,
 	.commit_setup	= nfs3_proc_commit_setup,
@@ -921,5 +964,11 @@ const struct nfs_rpc_ops nfs_v3_clientops = {
 	.lock		= nfs3_proc_lock,
 	.clear_acl_cache = nfs3_forget_cached_acls,
 	.close_context	= nfs_close_context,
+	.have_delegation = nfs3_have_delegation,
+	.return_delegation = nfs3_return_delegation,
+	.alloc_client	= nfs_alloc_client,
 	.init_client	= nfs_init_client,
+	.free_client	= nfs_free_client,
+	.create_server	= nfs3_create_server,
+	.clone_server	= nfs3_clone_server,
 };
diff --git a/fs/nfs/nfs3super.c b/fs/nfs/nfs3super.c
new file mode 100644
index 00000000000..cc471c72523
--- /dev/null
+++ b/fs/nfs/nfs3super.c
@@ -0,0 +1,31 @@
+/*
+ * Copyright (c) 2012 Netapp, Inc. All rights reserved.
+ */
+#include <linux/module.h>
+#include <linux/nfs_fs.h>
+#include "internal.h"
+#include "nfs.h"
+
+static struct nfs_subversion nfs_v3 = {
+	.owner = THIS_MODULE,
+	.nfs_fs   = &nfs_fs_type,
+	.rpc_vers = &nfs_version3,
+	.rpc_ops  = &nfs_v3_clientops,
+	.sops     = &nfs_sops,
+};
+
+static int __init init_nfs_v3(void)
+{
+	register_nfs_version(&nfs_v3);
+	return 0;
+}
+
+static void __exit exit_nfs_v3(void)
+{
+	unregister_nfs_version(&nfs_v3);
+}
+
+MODULE_LICENSE("GPL");
+
+module_init(init_nfs_v3);
+module_exit(exit_nfs_v3);
diff --git a/fs/nfs/nfs3xdr.c b/fs/nfs/nfs3xdr.c
index 902de489ec9..bffc32406fb 100644
--- a/fs/nfs/nfs3xdr.c
+++ b/fs/nfs/nfs3xdr.c
@@ -198,7 +198,7 @@ static void encode_filename3(struct xdr_stream *xdr,
 {
 	__be32 *p;
 
-	BUG_ON(length > NFS3_MAXNAMLEN);
+	WARN_ON_ONCE(length > NFS3_MAXNAMLEN);
 	p = xdr_reserve_space(xdr, 4 + length);
 	xdr_encode_opaque(p, name, length);
 }
@@ -238,7 +238,6 @@ out_overflow:
 static void encode_nfspath3(struct xdr_stream *xdr, struct page **pages,
 			    const u32 length)
 {
-	BUG_ON(length > NFS3_MAXPATHLEN);
 	encode_uint32(xdr, length);
 	xdr_write_pages(xdr, pages, 0, length);
 }
@@ -246,7 +245,6 @@ static void encode_nfspath3(struct xdr_stream *xdr, struct page **pages,
 static int decode_nfspath3(struct xdr_stream *xdr)
 {
 	u32 recvd, count;
-	size_t hdrlen;
 	__be32 *p;
 
 	p = xdr_inline_decode(xdr, 4);
@@ -255,12 +253,9 @@ static int decode_nfspath3(struct xdr_stream *xdr)
 	count = be32_to_cpup(p);
 	if (unlikely(count >= xdr->buf->page_len || count > NFS3_MAXPATHLEN))
 		goto out_nametoolong;
-	hdrlen = (u8 *)xdr->p - (u8 *)xdr->iov->iov_base;
-	recvd = xdr->buf->len - hdrlen;
+	recvd = xdr_read_pages(xdr, count);
 	if (unlikely(count > recvd))
 		goto out_cheating;
-
-	xdr_read_pages(xdr, count);
 	xdr_terminate_string(xdr->buf, count);
 	return 0;
 
@@ -329,14 +324,14 @@ static void encode_createverf3(struct xdr_stream *xdr, const __be32 *verifier)
 	memcpy(p, verifier, NFS3_CREATEVERFSIZE);
 }
 
-static int decode_writeverf3(struct xdr_stream *xdr, __be32 *verifier)
+static int decode_writeverf3(struct xdr_stream *xdr, struct nfs_write_verifier *verifier)
 {
 	__be32 *p;
 
 	p = xdr_inline_decode(xdr, NFS3_WRITEVERFSIZE);
 	if (unlikely(p == NULL))
 		goto out_overflow;
-	memcpy(verifier, p, NFS3_WRITEVERFSIZE);
+	memcpy(verifier->data, p, NFS3_WRITEVERFSIZE);
 	return 0;
 out_overflow:
 	print_overflow_msg(__func__, xdr);
@@ -392,7 +387,6 @@ out_overflow:
  */
 static void encode_ftype3(struct xdr_stream *xdr, const u32 type)
 {
-	BUG_ON(type > NF3FIFO);
 	encode_uint32(xdr, type);
 }
 
@@ -447,7 +441,7 @@ static void encode_nfs_fh3(struct xdr_stream *xdr, const struct nfs_fh *fh)
 {
 	__be32 *p;
 
-	BUG_ON(fh->size > NFS3_FHSIZE);
+	WARN_ON_ONCE(fh->size > NFS3_FHSIZE);
 	p = xdr_reserve_space(xdr, 4 + fh->size);
 	xdr_encode_opaque(p, fh->data, fh->size);
 }
@@ -1343,6 +1337,7 @@ static void nfs3_xdr_enc_setacl3args(struct rpc_rqst *req,
 	error = nfsacl_encode(xdr->buf, base, args->inode,
 			    (args->mask & NFS_ACL) ?
 			    args->acl_access : NULL, 1, 0);
+	/* FIXME: this is just broken */
 	BUG_ON(error < 0);
 	error = nfsacl_encode(xdr->buf, base + error, args->inode,
 			    (args->mask & NFS_DFACL) ?
@@ -1587,7 +1582,6 @@ static int decode_read3resok(struct xdr_stream *xdr,
 			     struct nfs_readres *result)
 {
 	u32 eof, count, ocount, recvd;
-	size_t hdrlen;
 	__be32 *p;
 
 	p = xdr_inline_decode(xdr, 4 + 4 + 4);
@@ -1598,13 +1592,10 @@ static int decode_read3resok(struct xdr_stream *xdr,
 	ocount = be32_to_cpup(p++);
 	if (unlikely(ocount != count))
 		goto out_mismatch;
-	hdrlen = (u8 *)xdr->p - (u8 *)xdr->iov->iov_base;
-	recvd = xdr->buf->len - hdrlen;
+	recvd = xdr_read_pages(xdr, count);
 	if (unlikely(count > recvd))
 		goto out_cheating;
-
 out:
-	xdr_read_pages(xdr, count);
 	result->eof = eof;
 	result->count = count;
 	return count;
@@ -1676,20 +1667,22 @@ static int decode_write3resok(struct xdr_stream *xdr,
 {
 	__be32 *p;
 
-	p = xdr_inline_decode(xdr, 4 + 4 + NFS3_WRITEVERFSIZE);
+	p = xdr_inline_decode(xdr, 4 + 4);
 	if (unlikely(p == NULL))
 		goto out_overflow;
 	result->count = be32_to_cpup(p++);
 	result->verf->committed = be32_to_cpup(p++);
 	if (unlikely(result->verf->committed > NFS_FILE_SYNC))
 		goto out_badvalue;
-	memcpy(result->verf->verifier, p, NFS3_WRITEVERFSIZE);
+	if (decode_writeverf3(xdr, &result->verf->verifier))
+		goto out_eio;
 	return result->count;
 out_badvalue:
 	dprintk("NFS: bad stable_how value: %u\n", result->verf->committed);
 	return -EIO;
 out_overflow:
 	print_overflow_msg(__func__, xdr);
+out_eio:
 	return -EIO;
 }
 
@@ -2039,22 +2032,7 @@ out_truncated:
  */
 static int decode_dirlist3(struct xdr_stream *xdr)
 {
-	u32 recvd, pglen;
-	size_t hdrlen;
-
-	pglen = xdr->buf->page_len;
-	hdrlen = (u8 *)xdr->p - (u8 *)xdr->iov->iov_base;
-	recvd = xdr->buf->len - hdrlen;
-	if (unlikely(pglen > recvd))
-		goto out_cheating;
-out:
-	xdr_read_pages(xdr, pglen);
-	return pglen;
-out_cheating:
-	dprintk("NFS: server cheating in readdir result: "
-		"pglen %u > recvd %u\n", pglen, recvd);
-	pglen = recvd;
-	goto out;
+	return xdr_read_pages(xdr, xdr->buf->page_len);
 }
 
 static int decode_readdir3resok(struct xdr_stream *xdr,
@@ -2337,7 +2315,7 @@ static int nfs3_xdr_dec_commit3res(struct rpc_rqst *req,
 		goto out;
 	if (status != NFS3_OK)
 		goto out_status;
-	error = decode_writeverf3(xdr, result->verf->verifier);
+	error = decode_writeverf3(xdr, &result->verf->verifier);
 out:
 	return error;
 out_status:
@@ -2364,7 +2342,7 @@ static inline int decode_getacl3resok(struct xdr_stream *xdr,
 	if (result->mask & ~(NFS_ACL|NFS_ACLCNT|NFS_DFACL|NFS_DFACLCNT))
 		goto out;
 
-	hdrlen = (u8 *)xdr->p - (u8 *)xdr->iov->iov_base;
+	hdrlen = xdr_stream_pos(xdr);
 
 	acl = NULL;
 	if (result->mask & NFS_ACL)
diff --git a/fs/nfs/nfs4_fs.h b/fs/nfs/nfs4_fs.h
index cc5900ac61b..a3f488b074a 100644
--- a/fs/nfs/nfs4_fs.h
+++ b/fs/nfs/nfs4_fs.h
@@ -9,7 +9,9 @@
 #ifndef __LINUX_FS_NFS_NFS4_FS_H
 #define __LINUX_FS_NFS_NFS4_FS_H
 
-#ifdef CONFIG_NFS_V4
+#if IS_ENABLED(CONFIG_NFS_V4)
+
+#define NFS4_MAX_LOOP_ON_RECOVER (10)
 
 struct idmap;
 
@@ -21,18 +23,12 @@ enum nfs4_client_state {
 	NFS4CLNT_RECLAIM_NOGRACE,
 	NFS4CLNT_DELEGRETURN,
 	NFS4CLNT_SESSION_RESET,
-	NFS4CLNT_RECALL_SLOT,
 	NFS4CLNT_LEASE_CONFIRM,
 	NFS4CLNT_SERVER_SCOPE_MISMATCH,
 	NFS4CLNT_PURGE_STATE,
 	NFS4CLNT_BIND_CONN_TO_SESSION,
 };
 
-enum nfs4_session_state {
-	NFS4_SESSION_INITING,
-	NFS4_SESSION_DRAINING,
-};
-
 #define NFS4_RENEW_TIMEOUT		0x01
 #define NFS4_RENEW_DELEGATION_CB	0x02
 
@@ -43,8 +39,7 @@ struct nfs4_minor_version_ops {
 			struct nfs_server *server,
 			struct rpc_message *msg,
 			struct nfs4_sequence_args *args,
-			struct nfs4_sequence_res *res,
-			int cache_reply);
+			struct nfs4_sequence_res *res);
 	bool	(*match_stateid)(const nfs4_stateid *,
 			const nfs4_stateid *);
 	int	(*find_root_sec)(struct nfs_server *, struct nfs_fh *,
@@ -132,8 +127,8 @@ struct nfs4_lock_owner {
 struct nfs4_lock_state {
 	struct list_head	ls_locks;	/* Other lock stateids */
 	struct nfs4_state *	ls_state;	/* Pointer to open state */
-#define NFS_LOCK_INITIALIZED 1
-	int			ls_flags;
+#define NFS_LOCK_INITIALIZED 0
+	unsigned long		ls_flags;
 	struct nfs_seqid_counter	ls_seqid;
 	nfs4_stateid		ls_stateid;
 	atomic_t		ls_count;
@@ -191,6 +186,8 @@ struct nfs4_state_recovery_ops {
 	int (*establish_clid)(struct nfs_client *, struct rpc_cred *);
 	struct rpc_cred * (*get_clid_cred)(struct nfs_client *);
 	int (*reclaim_complete)(struct nfs_client *);
+	int (*detect_trunking)(struct nfs_client *, struct nfs_client **,
+		struct rpc_cred *);
 };
 
 struct nfs4_state_maintenance_ops {
@@ -200,7 +197,13 @@ struct nfs4_state_maintenance_ops {
 };
 
 extern const struct dentry_operations nfs4_dentry_operations;
-extern const struct inode_operations nfs4_dir_inode_operations;
+
+/* dir.c */
+int nfs_atomic_open(struct inode *, struct dentry *, struct file *,
+		    unsigned, umode_t, int *);
+
+/* super.c */
+extern struct file_system_type nfs4_fs_type;
 
 /* nfs4namespace.c */
 rpc_authflavor_t nfs_find_best_sec(struct nfs4_secinfo_flavors *);
@@ -217,7 +220,7 @@ extern int nfs4_proc_exchange_id(struct nfs_client *clp, struct rpc_cred *cred);
 extern int nfs4_destroy_clientid(struct nfs_client *clp);
 extern int nfs4_init_clientid(struct nfs_client *, struct rpc_cred *);
 extern int nfs41_init_clientid(struct nfs_client *, struct rpc_cred *);
-extern int nfs4_do_close(struct nfs4_state *state, gfp_t gfp_mask, int wait, bool roc);
+extern int nfs4_do_close(struct nfs4_state *state, gfp_t gfp_mask, int wait);
 extern int nfs4_server_capabilities(struct nfs_server *server, struct nfs_fh *fhandle);
 extern int nfs4_proc_fs_locations(struct rpc_clnt *, struct inode *, const struct qstr *,
 				  struct nfs4_fs_locations *, struct page *);
@@ -233,18 +236,14 @@ static inline struct nfs4_session *nfs4_get_session(const struct nfs_server *ser
 	return server->nfs_client->cl_session;
 }
 
-extern bool nfs4_set_task_privileged(struct rpc_task *task, void *dummy);
 extern int nfs4_setup_sequence(const struct nfs_server *server,
 		struct nfs4_sequence_args *args, struct nfs4_sequence_res *res,
 		struct rpc_task *task);
 extern int nfs41_setup_sequence(struct nfs4_session *session,
 		struct nfs4_sequence_args *args, struct nfs4_sequence_res *res,
 		struct rpc_task *task);
-extern void nfs4_destroy_session(struct nfs4_session *session);
-extern struct nfs4_session *nfs4_alloc_session(struct nfs_client *clp);
 extern int nfs4_proc_create_session(struct nfs_client *, struct rpc_cred *);
 extern int nfs4_proc_destroy_session(struct nfs4_session *, struct rpc_cred *);
-extern int nfs4_init_session(struct nfs_server *server);
 extern int nfs4_proc_get_lease_time(struct nfs_client *clp,
 		struct nfs_fsinfo *fsinfo);
 extern int nfs4_proc_layoutcommit(struct nfs4_layoutcommit_data *data,
@@ -272,11 +271,7 @@ static inline int nfs4_setup_sequence(const struct nfs_server *server,
 		struct nfs4_sequence_args *args, struct nfs4_sequence_res *res,
 		struct rpc_task *task)
 {
-	return 0;
-}
-
-static inline int nfs4_init_session(struct nfs_server *server)
-{
+	rpc_call_start(task);
 	return 0;
 }
 
@@ -301,6 +296,10 @@ extern const u32 nfs4_pathconf_bitmap[2];
 extern const u32 nfs4_fsinfo_bitmap[3];
 extern const u32 nfs4_fs_locations_bitmap[2];
 
+void nfs4_free_client(struct nfs_client *);
+
+struct nfs_client *nfs4_alloc_client(const struct nfs_client_initdata *);
+
 /* nfs4renewd.c */
 extern void nfs4_schedule_state_renewal(struct nfs_client *);
 extern void nfs4_renewd_prepare_shutdown(struct nfs_server *);
@@ -309,11 +308,20 @@ extern void nfs4_renew_state(struct work_struct *);
 
 /* nfs4state.c */
 struct rpc_cred *nfs4_get_setclientid_cred(struct nfs_client *clp);
+struct rpc_cred *nfs4_get_machine_cred_locked(struct nfs_client *clp);
 struct rpc_cred *nfs4_get_renew_cred_locked(struct nfs_client *clp);
+int nfs4_discover_server_trunking(struct nfs_client *clp,
+			struct nfs_client **);
+int nfs40_discover_server_trunking(struct nfs_client *clp,
+			struct nfs_client **, struct rpc_cred *);
 #if defined(CONFIG_NFS_V4_1)
-struct rpc_cred *nfs4_get_machine_cred_locked(struct nfs_client *clp);
 struct rpc_cred *nfs4_get_exchange_id_cred(struct nfs_client *clp);
+int nfs41_discover_server_trunking(struct nfs_client *clp,
+			struct nfs_client **, struct rpc_cred *);
 extern void nfs4_schedule_session_recovery(struct nfs4_session *, int);
+extern void nfs41_server_notify_target_slotid_update(struct nfs_client *clp);
+extern void nfs41_server_notify_highest_slotid_update(struct nfs_client *clp);
+
 #else
 static inline void nfs4_schedule_session_recovery(struct nfs4_session *session, int err)
 {
@@ -331,17 +339,18 @@ extern void nfs4_state_set_mode_locked(struct nfs4_state *, fmode_t);
 extern void nfs_inode_find_state_and_recover(struct inode *inode,
 		const nfs4_stateid *stateid);
 extern void nfs4_schedule_lease_recovery(struct nfs_client *);
+extern int nfs4_wait_clnt_recover(struct nfs_client *clp);
+extern int nfs4_client_recover_expired_lease(struct nfs_client *clp);
 extern void nfs4_schedule_state_manager(struct nfs_client *);
 extern void nfs4_schedule_path_down_recovery(struct nfs_client *clp);
 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 nfs41_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_select_rw_stateid(nfs4_stateid *, struct nfs4_state *,
-		fmode_t, fl_owner_t, pid_t);
+		fmode_t, const struct nfs_lockowner *);
 
 extern struct nfs_seqid *nfs_alloc_seqid(struct nfs_seqid_counter *counter, gfp_t gfp_mask);
 extern int nfs_wait_on_sequence(struct nfs_seqid *seqid, struct rpc_task *task);
@@ -354,6 +363,32 @@ extern void nfs4_free_lock_state(struct nfs_server *server, struct nfs4_lock_sta
 
 extern const nfs4_stateid zero_stateid;
 
+/* nfs4super.c */
+struct nfs_mount_info;
+extern struct nfs_subversion nfs_v4;
+struct dentry *nfs4_try_mount(int, const char *, struct nfs_mount_info *, struct nfs_subversion *);
+extern bool nfs4_disable_idmapping;
+extern unsigned short max_session_slots;
+extern unsigned short send_implementation_id;
+
+#define NFS4_CLIENT_ID_UNIQ_LEN		(64)
+extern char nfs4_client_id_uniquifier[NFS4_CLIENT_ID_UNIQ_LEN];
+
+/* nfs4sysctl.c */
+#ifdef CONFIG_SYSCTL
+int nfs4_register_sysctl(void);
+void nfs4_unregister_sysctl(void);
+#else
+static inline int nfs4_register_sysctl(void)
+{
+	return 0;
+}
+
+static inline void nfs4_unregister_sysctl(void)
+{
+}
+#endif
+
 /* nfs4xdr.c */
 extern struct rpc_procinfo nfs4_procedures[];
 
diff --git a/fs/nfs/nfs4client.c b/fs/nfs/nfs4client.c
new file mode 100644
index 00000000000..2e9779b58b7
--- /dev/null
+++ b/fs/nfs/nfs4client.c
@@ -0,0 +1,897 @@
+/*
+ * Copyright (C) 2006 Red Hat, Inc. All Rights Reserved.
+ * Written by David Howells (dhowells@redhat.com)
+ */
+#include <linux/module.h>
+#include <linux/nfs_fs.h>
+#include <linux/nfs_idmap.h>
+#include <linux/nfs_mount.h>
+#include <linux/sunrpc/auth.h>
+#include <linux/sunrpc/xprt.h>
+#include <linux/sunrpc/bc_xprt.h>
+#include "internal.h"
+#include "callback.h"
+#include "delegation.h"
+#include "nfs4session.h"
+#include "pnfs.h"
+#include "netns.h"
+
+#define NFSDBG_FACILITY		NFSDBG_CLIENT
+
+/*
+ * Get a unique NFSv4.0 callback identifier which will be used
+ * by the V4.0 callback service to lookup the nfs_client struct
+ */
+static int nfs_get_cb_ident_idr(struct nfs_client *clp, int minorversion)
+{
+	int ret = 0;
+	struct nfs_net *nn = net_generic(clp->cl_net, nfs_net_id);
+
+	if (clp->rpc_ops->version != 4 || minorversion != 0)
+		return ret;
+retry:
+	if (!idr_pre_get(&nn->cb_ident_idr, GFP_KERNEL))
+		return -ENOMEM;
+	spin_lock(&nn->nfs_client_lock);
+	ret = idr_get_new(&nn->cb_ident_idr, clp, &clp->cl_cb_ident);
+	spin_unlock(&nn->nfs_client_lock);
+	if (ret == -EAGAIN)
+		goto retry;
+	return ret;
+}
+
+#ifdef CONFIG_NFS_V4_1
+static void nfs4_shutdown_session(struct nfs_client *clp)
+{
+	if (nfs4_has_session(clp)) {
+		nfs4_destroy_session(clp->cl_session);
+		nfs4_destroy_clientid(clp);
+	}
+
+}
+#else /* CONFIG_NFS_V4_1 */
+static void nfs4_shutdown_session(struct nfs_client *clp)
+{
+}
+#endif /* CONFIG_NFS_V4_1 */
+
+struct nfs_client *nfs4_alloc_client(const struct nfs_client_initdata *cl_init)
+{
+	int err;
+	struct nfs_client *clp = nfs_alloc_client(cl_init);
+	if (IS_ERR(clp))
+		return clp;
+
+	err = nfs_get_cb_ident_idr(clp, cl_init->minorversion);
+	if (err)
+		goto error;
+
+	spin_lock_init(&clp->cl_lock);
+	INIT_DELAYED_WORK(&clp->cl_renewd, nfs4_renew_state);
+	rpc_init_wait_queue(&clp->cl_rpcwaitq, "NFS client");
+	clp->cl_state = 1 << NFS4CLNT_LEASE_EXPIRED;
+	clp->cl_minorversion = cl_init->minorversion;
+	clp->cl_mvops = nfs_v4_minor_ops[cl_init->minorversion];
+	return clp;
+
+error:
+	nfs_free_client(clp);
+	return ERR_PTR(err);
+}
+
+/*
+ * Destroy the NFS4 callback service
+ */
+static void nfs4_destroy_callback(struct nfs_client *clp)
+{
+	if (__test_and_clear_bit(NFS_CS_CALLBACK, &clp->cl_res_state))
+		nfs_callback_down(clp->cl_mvops->minor_version, clp->cl_net);
+}
+
+static void nfs4_shutdown_client(struct nfs_client *clp)
+{
+	if (__test_and_clear_bit(NFS_CS_RENEWD, &clp->cl_res_state))
+		nfs4_kill_renewd(clp);
+	nfs4_shutdown_session(clp);
+	nfs4_destroy_callback(clp);
+	if (__test_and_clear_bit(NFS_CS_IDMAP, &clp->cl_res_state))
+		nfs_idmap_delete(clp);
+
+	rpc_destroy_wait_queue(&clp->cl_rpcwaitq);
+	kfree(clp->cl_serverowner);
+	kfree(clp->cl_serverscope);
+	kfree(clp->cl_implid);
+}
+
+void nfs4_free_client(struct nfs_client *clp)
+{
+	nfs4_shutdown_client(clp);
+	nfs_free_client(clp);
+}
+
+/*
+ * Initialize the NFS4 callback service
+ */
+static int nfs4_init_callback(struct nfs_client *clp)
+{
+	int error;
+
+	if (clp->rpc_ops->version == 4) {
+		struct rpc_xprt *xprt;
+
+		xprt = rcu_dereference_raw(clp->cl_rpcclient->cl_xprt);
+
+		if (nfs4_has_session(clp)) {
+			error = xprt_setup_backchannel(xprt,
+						NFS41_BC_MIN_CALLBACKS);
+			if (error < 0)
+				return error;
+		}
+
+		error = nfs_callback_up(clp->cl_mvops->minor_version, xprt);
+		if (error < 0) {
+			dprintk("%s: failed to start callback. Error = %d\n",
+				__func__, error);
+			return error;
+		}
+		__set_bit(NFS_CS_CALLBACK, &clp->cl_res_state);
+	}
+	return 0;
+}
+
+/*
+ * Initialize the minor version specific parts of an NFS4 client record
+ */
+static int nfs4_init_client_minor_version(struct nfs_client *clp)
+{
+#if defined(CONFIG_NFS_V4_1)
+	if (clp->cl_mvops->minor_version) {
+		struct nfs4_session *session = NULL;
+		/*
+		 * Create the session and mark it expired.
+		 * When a SEQUENCE operation encounters the expired session
+		 * it will do session recovery to initialize it.
+		 */
+		session = nfs4_alloc_session(clp);
+		if (!session)
+			return -ENOMEM;
+
+		clp->cl_session = session;
+		/*
+		 * The create session reply races with the server back
+		 * channel probe. Mark the client NFS_CS_SESSION_INITING
+		 * so that the client back channel can find the
+		 * nfs_client struct
+		 */
+		nfs_mark_client_ready(clp, NFS_CS_SESSION_INITING);
+	}
+#endif /* CONFIG_NFS_V4_1 */
+
+	return nfs4_init_callback(clp);
+}
+
+/**
+ * nfs4_init_client - Initialise an NFS4 client record
+ *
+ * @clp: nfs_client to initialise
+ * @timeparms: timeout parameters for underlying RPC transport
+ * @ip_addr: callback IP address in presentation format
+ * @authflavor: authentication flavor for underlying RPC transport
+ *
+ * Returns pointer to an NFS client, or an ERR_PTR value.
+ */
+struct nfs_client *nfs4_init_client(struct nfs_client *clp,
+				    const struct rpc_timeout *timeparms,
+				    const char *ip_addr,
+				    rpc_authflavor_t authflavour)
+{
+	char buf[INET6_ADDRSTRLEN + 1];
+	struct nfs_client *old;
+	int error;
+
+	if (clp->cl_cons_state == NFS_CS_READY) {
+		/* the client is initialised already */
+		dprintk("<-- nfs4_init_client() = 0 [already %p]\n", clp);
+		return clp;
+	}
+
+	/* Check NFS protocol revision and initialize RPC op vector */
+	clp->rpc_ops = &nfs_v4_clientops;
+
+	__set_bit(NFS_CS_DISCRTRY, &clp->cl_flags);
+	error = nfs_create_rpc_client(clp, timeparms, authflavour);
+	if (error < 0)
+		goto error;
+
+	/* If no clientaddr= option was specified, find a usable cb address */
+	if (ip_addr == NULL) {
+		struct sockaddr_storage cb_addr;
+		struct sockaddr *sap = (struct sockaddr *)&cb_addr;
+
+		error = rpc_localaddr(clp->cl_rpcclient, sap, sizeof(cb_addr));
+		if (error < 0)
+			goto error;
+		error = rpc_ntop(sap, buf, sizeof(buf));
+		if (error < 0)
+			goto error;
+		ip_addr = (const char *)buf;
+	}
+	strlcpy(clp->cl_ipaddr, ip_addr, sizeof(clp->cl_ipaddr));
+
+	error = nfs_idmap_new(clp);
+	if (error < 0) {
+		dprintk("%s: failed to create idmapper. Error = %d\n",
+			__func__, error);
+		goto error;
+	}
+	__set_bit(NFS_CS_IDMAP, &clp->cl_res_state);
+
+	error = nfs4_init_client_minor_version(clp);
+	if (error < 0)
+		goto error;
+
+	if (!nfs4_has_session(clp))
+		nfs_mark_client_ready(clp, NFS_CS_READY);
+
+	error = nfs4_discover_server_trunking(clp, &old);
+	if (error < 0)
+		goto error;
+	nfs_put_client(clp);
+	if (clp != old) {
+		clp->cl_preserve_clid = true;
+		clp = old;
+	}
+
+	return clp;
+
+error:
+	nfs_mark_client_ready(clp, error);
+	nfs_put_client(clp);
+	dprintk("<-- nfs4_init_client() = xerror %d\n", error);
+	return ERR_PTR(error);
+}
+
+/*
+ * SETCLIENTID just did a callback update with the callback ident in
+ * "drop," but server trunking discovery claims "drop" and "keep" are
+ * actually the same server.  Swap the callback IDs so that "keep"
+ * will continue to use the callback ident the server now knows about,
+ * and so that "keep"'s original callback ident is destroyed when
+ * "drop" is freed.
+ */
+static void nfs4_swap_callback_idents(struct nfs_client *keep,
+				      struct nfs_client *drop)
+{
+	struct nfs_net *nn = net_generic(keep->cl_net, nfs_net_id);
+	unsigned int save = keep->cl_cb_ident;
+
+	if (keep->cl_cb_ident == drop->cl_cb_ident)
+		return;
+
+	dprintk("%s: keeping callback ident %u and dropping ident %u\n",
+		__func__, keep->cl_cb_ident, drop->cl_cb_ident);
+
+	spin_lock(&nn->nfs_client_lock);
+
+	idr_replace(&nn->cb_ident_idr, keep, drop->cl_cb_ident);
+	keep->cl_cb_ident = drop->cl_cb_ident;
+
+	idr_replace(&nn->cb_ident_idr, drop, save);
+	drop->cl_cb_ident = save;
+
+	spin_unlock(&nn->nfs_client_lock);
+}
+
+/**
+ * nfs40_walk_client_list - Find server that recognizes a client ID
+ *
+ * @new: nfs_client with client ID to test
+ * @result: OUT: found nfs_client, or new
+ * @cred: credential to use for trunking test
+ *
+ * Returns zero, a negative errno, or a negative NFS4ERR status.
+ * If zero is returned, an nfs_client pointer is planted in "result."
+ *
+ * NB: nfs40_walk_client_list() relies on the new nfs_client being
+ *     the last nfs_client on the list.
+ */
+int nfs40_walk_client_list(struct nfs_client *new,
+			   struct nfs_client **result,
+			   struct rpc_cred *cred)
+{
+	struct nfs_net *nn = net_generic(new->cl_net, nfs_net_id);
+	struct nfs_client *pos, *n, *prev = NULL;
+	struct nfs4_setclientid_res clid = {
+		.clientid	= new->cl_clientid,
+		.confirm	= new->cl_confirm,
+	};
+	int status = -NFS4ERR_STALE_CLIENTID;
+
+	spin_lock(&nn->nfs_client_lock);
+	list_for_each_entry_safe(pos, n, &nn->nfs_client_list, cl_share_link) {
+		/* If "pos" isn't marked ready, we can't trust the
+		 * remaining fields in "pos" */
+		if (pos->cl_cons_state < NFS_CS_READY)
+			continue;
+
+		if (pos->rpc_ops != new->rpc_ops)
+			continue;
+
+		if (pos->cl_proto != new->cl_proto)
+			continue;
+
+		if (pos->cl_minorversion != new->cl_minorversion)
+			continue;
+
+		if (pos->cl_clientid != new->cl_clientid)
+			continue;
+
+		atomic_inc(&pos->cl_count);
+		spin_unlock(&nn->nfs_client_lock);
+
+		if (prev)
+			nfs_put_client(prev);
+		prev = pos;
+
+		status = nfs4_proc_setclientid_confirm(pos, &clid, cred);
+		switch (status) {
+		case -NFS4ERR_STALE_CLIENTID:
+			break;
+		case 0:
+			nfs4_swap_callback_idents(pos, new);
+
+			prev = NULL;
+			*result = pos;
+			dprintk("NFS: <-- %s using nfs_client = %p ({%d})\n",
+				__func__, pos, atomic_read(&pos->cl_count));
+		default:
+			goto out;
+		}
+
+		spin_lock(&nn->nfs_client_lock);
+	}
+	spin_unlock(&nn->nfs_client_lock);
+
+	/* No match found. The server lost our clientid */
+out:
+	if (prev)
+		nfs_put_client(prev);
+	dprintk("NFS: <-- %s status = %d\n", __func__, status);
+	return status;
+}
+
+#ifdef CONFIG_NFS_V4_1
+/*
+ * Returns true if the client IDs match
+ */
+static bool nfs4_match_clientids(struct nfs_client *a, struct nfs_client *b)
+{
+	if (a->cl_clientid != b->cl_clientid) {
+		dprintk("NFS: --> %s client ID %llx does not match %llx\n",
+			__func__, a->cl_clientid, b->cl_clientid);
+		return false;
+	}
+	dprintk("NFS: --> %s client ID %llx matches %llx\n",
+		__func__, a->cl_clientid, b->cl_clientid);
+	return true;
+}
+
+/*
+ * Returns true if the server owners match
+ */
+static bool
+nfs4_match_serverowners(struct nfs_client *a, struct nfs_client *b)
+{
+	struct nfs41_server_owner *o1 = a->cl_serverowner;
+	struct nfs41_server_owner *o2 = b->cl_serverowner;
+
+	if (o1->minor_id != o2->minor_id) {
+		dprintk("NFS: --> %s server owner minor IDs do not match\n",
+			__func__);
+		return false;
+	}
+
+	if (o1->major_id_sz != o2->major_id_sz)
+		goto out_major_mismatch;
+	if (memcmp(o1->major_id, o2->major_id, o1->major_id_sz) != 0)
+		goto out_major_mismatch;
+
+	dprintk("NFS: --> %s server owners match\n", __func__);
+	return true;
+
+out_major_mismatch:
+	dprintk("NFS: --> %s server owner major IDs do not match\n",
+		__func__);
+	return false;
+}
+
+/**
+ * nfs41_walk_client_list - Find nfs_client that matches a client/server owner
+ *
+ * @new: nfs_client with client ID to test
+ * @result: OUT: found nfs_client, or new
+ * @cred: credential to use for trunking test
+ *
+ * Returns zero, a negative errno, or a negative NFS4ERR status.
+ * If zero is returned, an nfs_client pointer is planted in "result."
+ *
+ * NB: nfs41_walk_client_list() relies on the new nfs_client being
+ *     the last nfs_client on the list.
+ */
+int nfs41_walk_client_list(struct nfs_client *new,
+			   struct nfs_client **result,
+			   struct rpc_cred *cred)
+{
+	struct nfs_net *nn = net_generic(new->cl_net, nfs_net_id);
+	struct nfs_client *pos, *n, *prev = NULL;
+	int status = -NFS4ERR_STALE_CLIENTID;
+
+	spin_lock(&nn->nfs_client_lock);
+	list_for_each_entry_safe(pos, n, &nn->nfs_client_list, cl_share_link) {
+		/* If "pos" isn't marked ready, we can't trust the
+		 * remaining fields in "pos", especially the client
+		 * ID and serverowner fields.  Wait for CREATE_SESSION
+		 * to finish. */
+		if (pos->cl_cons_state < NFS_CS_READY) {
+			atomic_inc(&pos->cl_count);
+			spin_unlock(&nn->nfs_client_lock);
+
+			if (prev)
+				nfs_put_client(prev);
+			prev = pos;
+
+			nfs4_schedule_lease_recovery(pos);
+			status = nfs_wait_client_init_complete(pos);
+			if (status < 0) {
+				nfs_put_client(pos);
+				spin_lock(&nn->nfs_client_lock);
+				continue;
+			}
+			status = pos->cl_cons_state;
+			spin_lock(&nn->nfs_client_lock);
+			if (status < 0)
+				continue;
+		}
+
+		if (pos->rpc_ops != new->rpc_ops)
+			continue;
+
+		if (pos->cl_proto != new->cl_proto)
+			continue;
+
+		if (pos->cl_minorversion != new->cl_minorversion)
+			continue;
+
+		if (!nfs4_match_clientids(pos, new))
+			continue;
+
+		if (!nfs4_match_serverowners(pos, new))
+			continue;
+
+		atomic_inc(&pos->cl_count);
+		spin_unlock(&nn->nfs_client_lock);
+		dprintk("NFS: <-- %s using nfs_client = %p ({%d})\n",
+			__func__, pos, atomic_read(&pos->cl_count));
+
+		*result = pos;
+		return 0;
+	}
+
+	/* No matching nfs_client found. */
+	spin_unlock(&nn->nfs_client_lock);
+	dprintk("NFS: <-- %s status = %d\n", __func__, status);
+	return status;
+}
+#endif	/* CONFIG_NFS_V4_1 */
+
+static void nfs4_destroy_server(struct nfs_server *server)
+{
+	nfs_server_return_all_delegations(server);
+	unset_pnfs_layoutdriver(server);
+	nfs4_purge_state_owners(server);
+}
+
+/*
+ * NFSv4.0 callback thread helper
+ *
+ * Find a client by callback identifier
+ */
+struct nfs_client *
+nfs4_find_client_ident(struct net *net, int cb_ident)
+{
+	struct nfs_client *clp;
+	struct nfs_net *nn = net_generic(net, nfs_net_id);
+
+	spin_lock(&nn->nfs_client_lock);
+	clp = idr_find(&nn->cb_ident_idr, cb_ident);
+	if (clp)
+		atomic_inc(&clp->cl_count);
+	spin_unlock(&nn->nfs_client_lock);
+	return clp;
+}
+
+#if defined(CONFIG_NFS_V4_1)
+/* Common match routine for v4.0 and v4.1 callback services */
+static bool nfs4_cb_match_client(const struct sockaddr *addr,
+		struct nfs_client *clp, u32 minorversion)
+{
+	struct sockaddr *clap = (struct sockaddr *)&clp->cl_addr;
+
+	/* Don't match clients that failed to initialise */
+	if (!(clp->cl_cons_state == NFS_CS_READY ||
+	    clp->cl_cons_state == NFS_CS_SESSION_INITING))
+		return false;
+
+	smp_rmb();
+
+	/* Match the version and minorversion */
+	if (clp->rpc_ops->version != 4 ||
+	    clp->cl_minorversion != minorversion)
+		return false;
+
+	/* Match only the IP address, not the port number */
+	if (!nfs_sockaddr_match_ipaddr(addr, clap))
+		return false;
+
+	return true;
+}
+
+/*
+ * NFSv4.1 callback thread helper
+ * For CB_COMPOUND calls, find a client by IP address, protocol version,
+ * minorversion, and sessionID
+ *
+ * Returns NULL if no such client
+ */
+struct nfs_client *
+nfs4_find_client_sessionid(struct net *net, const struct sockaddr *addr,
+			   struct nfs4_sessionid *sid)
+{
+	struct nfs_client *clp;
+	struct nfs_net *nn = net_generic(net, nfs_net_id);
+
+	spin_lock(&nn->nfs_client_lock);
+	list_for_each_entry(clp, &nn->nfs_client_list, cl_share_link) {
+		if (nfs4_cb_match_client(addr, clp, 1) == false)
+			continue;
+
+		if (!nfs4_has_session(clp))
+			continue;
+
+		/* Match sessionid*/
+		if (memcmp(clp->cl_session->sess_id.data,
+		    sid->data, NFS4_MAX_SESSIONID_LEN) != 0)
+			continue;
+
+		atomic_inc(&clp->cl_count);
+		spin_unlock(&nn->nfs_client_lock);
+		return clp;
+	}
+	spin_unlock(&nn->nfs_client_lock);
+	return NULL;
+}
+
+#else /* CONFIG_NFS_V4_1 */
+
+struct nfs_client *
+nfs4_find_client_sessionid(struct net *net, const struct sockaddr *addr,
+			   struct nfs4_sessionid *sid)
+{
+	return NULL;
+}
+#endif /* CONFIG_NFS_V4_1 */
+
+/*
+ * Set up an NFS4 client
+ */
+static int nfs4_set_client(struct nfs_server *server,
+		const char *hostname,
+		const struct sockaddr *addr,
+		const size_t addrlen,
+		const char *ip_addr,
+		rpc_authflavor_t authflavour,
+		int proto, const struct rpc_timeout *timeparms,
+		u32 minorversion, struct net *net)
+{
+	struct nfs_client_initdata cl_init = {
+		.hostname = hostname,
+		.addr = addr,
+		.addrlen = addrlen,
+		.nfs_mod = &nfs_v4,
+		.proto = proto,
+		.minorversion = minorversion,
+		.net = net,
+	};
+	struct nfs_client *clp;
+	int error;
+
+	dprintk("--> nfs4_set_client()\n");
+
+	if (server->flags & NFS_MOUNT_NORESVPORT)
+		set_bit(NFS_CS_NORESVPORT, &cl_init.init_flags);
+
+	/* Allocate or find a client reference we can use */
+	clp = nfs_get_client(&cl_init, timeparms, ip_addr, authflavour);
+	if (IS_ERR(clp)) {
+		error = PTR_ERR(clp);
+		goto error;
+	}
+
+	/*
+	 * Query for the lease time on clientid setup or renewal
+	 *
+	 * Note that this will be set on nfs_clients that were created
+	 * only for the DS role and did not set this bit, but now will
+	 * serve a dual role.
+	 */
+	set_bit(NFS_CS_CHECK_LEASE_TIME, &clp->cl_res_state);
+
+	server->nfs_client = clp;
+	dprintk("<-- nfs4_set_client() = 0 [new %p]\n", clp);
+	return 0;
+error:
+	dprintk("<-- nfs4_set_client() = xerror %d\n", error);
+	return error;
+}
+
+/*
+ * Set up a pNFS Data Server client.
+ *
+ * Return any existing nfs_client that matches server address,port,version
+ * and minorversion.
+ *
+ * For a new nfs_client, use a soft mount (default), a low retrans and a
+ * low timeout interval so that if a connection is lost, we retry through
+ * the MDS.
+ */
+struct nfs_client *nfs4_set_ds_client(struct nfs_client* mds_clp,
+		const struct sockaddr *ds_addr, int ds_addrlen,
+		int ds_proto, unsigned int ds_timeo, unsigned int ds_retrans)
+{
+	struct nfs_client_initdata cl_init = {
+		.addr = ds_addr,
+		.addrlen = ds_addrlen,
+		.nfs_mod = &nfs_v4,
+		.proto = ds_proto,
+		.minorversion = mds_clp->cl_minorversion,
+		.net = mds_clp->cl_net,
+	};
+	struct rpc_timeout ds_timeout;
+	struct nfs_client *clp;
+
+	/*
+	 * Set an authflavor equual to the MDS value. Use the MDS nfs_client
+	 * cl_ipaddr so as to use the same EXCHANGE_ID co_ownerid as the MDS
+	 * (section 13.1 RFC 5661).
+	 */
+	nfs_init_timeout_values(&ds_timeout, ds_proto, ds_timeo, ds_retrans);
+	clp = nfs_get_client(&cl_init, &ds_timeout, mds_clp->cl_ipaddr,
+			     mds_clp->cl_rpcclient->cl_auth->au_flavor);
+
+	dprintk("<-- %s %p\n", __func__, clp);
+	return clp;
+}
+EXPORT_SYMBOL_GPL(nfs4_set_ds_client);
+
+/*
+ * Session has been established, and the client marked ready.
+ * Set the mount rsize and wsize with negotiated fore channel
+ * attributes which will be bound checked in nfs_server_set_fsinfo.
+ */
+static void nfs4_session_set_rwsize(struct nfs_server *server)
+{
+#ifdef CONFIG_NFS_V4_1
+	struct nfs4_session *sess;
+	u32 server_resp_sz;
+	u32 server_rqst_sz;
+
+	if (!nfs4_has_session(server->nfs_client))
+		return;
+	sess = server->nfs_client->cl_session;
+	server_resp_sz = sess->fc_attrs.max_resp_sz - nfs41_maxread_overhead;
+	server_rqst_sz = sess->fc_attrs.max_rqst_sz - nfs41_maxwrite_overhead;
+
+	if (server->rsize > server_resp_sz)
+		server->rsize = server_resp_sz;
+	if (server->wsize > server_rqst_sz)
+		server->wsize = server_rqst_sz;
+#endif /* CONFIG_NFS_V4_1 */
+}
+
+static int nfs4_server_common_setup(struct nfs_server *server,
+		struct nfs_fh *mntfh)
+{
+	struct nfs_fattr *fattr;
+	int error;
+
+	/* data servers support only a subset of NFSv4.1 */
+	if (is_ds_only_client(server->nfs_client))
+		return -EPROTONOSUPPORT;
+
+	fattr = nfs_alloc_fattr();
+	if (fattr == NULL)
+		return -ENOMEM;
+
+	/* We must ensure the session is initialised first */
+	error = nfs4_init_session(server);
+	if (error < 0)
+		goto out;
+
+	/* Probe the root fh to retrieve its FSID and filehandle */
+	error = nfs4_get_rootfh(server, mntfh);
+	if (error < 0)
+		goto out;
+
+	dprintk("Server FSID: %llx:%llx\n",
+			(unsigned long long) server->fsid.major,
+			(unsigned long long) server->fsid.minor);
+	dprintk("Mount FH: %d\n", mntfh->size);
+
+	nfs4_session_set_rwsize(server);
+
+	error = nfs_probe_fsinfo(server, mntfh, fattr);
+	if (error < 0)
+		goto out;
+
+	if (server->namelen == 0 || server->namelen > NFS4_MAXNAMLEN)
+		server->namelen = NFS4_MAXNAMLEN;
+
+	nfs_server_insert_lists(server);
+	server->mount_time = jiffies;
+	server->destroy = nfs4_destroy_server;
+out:
+	nfs_free_fattr(fattr);
+	return error;
+}
+
+/*
+ * Create a version 4 volume record
+ */
+static int nfs4_init_server(struct nfs_server *server,
+		const struct nfs_parsed_mount_data *data)
+{
+	struct rpc_timeout timeparms;
+	int error;
+
+	dprintk("--> nfs4_init_server()\n");
+
+	nfs_init_timeout_values(&timeparms, data->nfs_server.protocol,
+			data->timeo, data->retrans);
+
+	/* Initialise the client representation from the mount data */
+	server->flags = data->flags;
+	server->caps |= NFS_CAP_ATOMIC_OPEN|NFS_CAP_CHANGE_ATTR|NFS_CAP_POSIX_LOCK;
+	if (!(data->flags & NFS_MOUNT_NORDIRPLUS))
+			server->caps |= NFS_CAP_READDIRPLUS;
+	server->options = data->options;
+
+	/* Get a client record */
+	error = nfs4_set_client(server,
+			data->nfs_server.hostname,
+			(const struct sockaddr *)&data->nfs_server.address,
+			data->nfs_server.addrlen,
+			data->client_address,
+			data->auth_flavors[0],
+			data->nfs_server.protocol,
+			&timeparms,
+			data->minorversion,
+			data->net);
+	if (error < 0)
+		goto error;
+
+	/*
+	 * Don't use NFS uid/gid mapping if we're using AUTH_SYS or lower
+	 * authentication.
+	 */
+	if (nfs4_disable_idmapping && data->auth_flavors[0] == RPC_AUTH_UNIX)
+		server->caps |= NFS_CAP_UIDGID_NOMAP;
+
+	if (data->rsize)
+		server->rsize = nfs_block_size(data->rsize, NULL);
+	if (data->wsize)
+		server->wsize = nfs_block_size(data->wsize, NULL);
+
+	server->acregmin = data->acregmin * HZ;
+	server->acregmax = data->acregmax * HZ;
+	server->acdirmin = data->acdirmin * HZ;
+	server->acdirmax = data->acdirmax * HZ;
+
+	server->port = data->nfs_server.port;
+
+	error = nfs_init_server_rpcclient(server, &timeparms, data->auth_flavors[0]);
+
+error:
+	/* Done */
+	dprintk("<-- nfs4_init_server() = %d\n", error);
+	return error;
+}
+
+/*
+ * Create a version 4 volume record
+ * - keyed on server and FSID
+ */
+/*struct nfs_server *nfs4_create_server(const struct nfs_parsed_mount_data *data,
+				      struct nfs_fh *mntfh)*/
+struct nfs_server *nfs4_create_server(struct nfs_mount_info *mount_info,
+				      struct nfs_subversion *nfs_mod)
+{
+	struct nfs_server *server;
+	int error;
+
+	dprintk("--> nfs4_create_server()\n");
+
+	server = nfs_alloc_server();
+	if (!server)
+		return ERR_PTR(-ENOMEM);
+
+	/* set up the general RPC client */
+	error = nfs4_init_server(server, mount_info->parsed);
+	if (error < 0)
+		goto error;
+
+	error = nfs4_server_common_setup(server, mount_info->mntfh);
+	if (error < 0)
+		goto error;
+
+	dprintk("<-- nfs4_create_server() = %p\n", server);
+	return server;
+
+error:
+	nfs_free_server(server);
+	dprintk("<-- nfs4_create_server() = error %d\n", error);
+	return ERR_PTR(error);
+}
+
+/*
+ * Create an NFS4 referral server record
+ */
+struct nfs_server *nfs4_create_referral_server(struct nfs_clone_mount *data,
+					       struct nfs_fh *mntfh)
+{
+	struct nfs_client *parent_client;
+	struct nfs_server *server, *parent_server;
+	int error;
+
+	dprintk("--> nfs4_create_referral_server()\n");
+
+	server = nfs_alloc_server();
+	if (!server)
+		return ERR_PTR(-ENOMEM);
+
+	parent_server = NFS_SB(data->sb);
+	parent_client = parent_server->nfs_client;
+
+	/* Initialise the client representation from the parent server */
+	nfs_server_copy_userdata(server, parent_server);
+	server->caps |= NFS_CAP_ATOMIC_OPEN|NFS_CAP_CHANGE_ATTR;
+
+	/* Get a client representation.
+	 * Note: NFSv4 always uses TCP, */
+	error = nfs4_set_client(server, data->hostname,
+				data->addr,
+				data->addrlen,
+				parent_client->cl_ipaddr,
+				data->authflavor,
+				rpc_protocol(parent_server->client),
+				parent_server->client->cl_timeout,
+				parent_client->cl_mvops->minor_version,
+				parent_client->cl_net);
+	if (error < 0)
+		goto error;
+
+	error = nfs_init_server_rpcclient(server, parent_server->client->cl_timeout, data->authflavor);
+	if (error < 0)
+		goto error;
+
+	error = nfs4_server_common_setup(server, mntfh);
+	if (error < 0)
+		goto error;
+
+	dprintk("<-- nfs_create_referral_server() = %p\n", server);
+	return server;
+
+error:
+	nfs_free_server(server);
+	dprintk("<-- nfs4_create_referral_server() = error %d\n", error);
+	return ERR_PTR(error);
+}
diff --git a/fs/nfs/nfs4file.c b/fs/nfs/nfs4file.c
new file mode 100644
index 00000000000..08ddcccb888
--- /dev/null
+++ b/fs/nfs/nfs4file.c
@@ -0,0 +1,138 @@
+/*
+ *  linux/fs/nfs/file.c
+ *
+ *  Copyright (C) 1992  Rick Sladkey
+ */
+#include <linux/nfs_fs.h>
+#include "internal.h"
+#include "fscache.h"
+#include "pnfs.h"
+
+#define NFSDBG_FACILITY		NFSDBG_FILE
+
+static int
+nfs4_file_open(struct inode *inode, struct file *filp)
+{
+	struct nfs_open_context *ctx;
+	struct dentry *dentry = filp->f_path.dentry;
+	struct dentry *parent = NULL;
+	struct inode *dir;
+	unsigned openflags = filp->f_flags;
+	struct iattr attr;
+	int err;
+
+	/*
+	 * If no cached dentry exists or if it's negative, NFSv4 handled the
+	 * opens in ->lookup() or ->create().
+	 *
+	 * We only get this far for a cached positive dentry.  We skipped
+	 * revalidation, so handle it here by dropping the dentry and returning
+	 * -EOPENSTALE.  The VFS will retry the lookup/create/open.
+	 */
+
+	dprintk("NFS: open file(%s/%s)\n",
+		dentry->d_parent->d_name.name,
+		dentry->d_name.name);
+
+	if ((openflags & O_ACCMODE) == 3)
+		openflags--;
+
+	/* We can't create new files here */
+	openflags &= ~(O_CREAT|O_EXCL);
+
+	parent = dget_parent(dentry);
+	dir = parent->d_inode;
+
+	ctx = alloc_nfs_open_context(filp->f_path.dentry, filp->f_mode);
+	err = PTR_ERR(ctx);
+	if (IS_ERR(ctx))
+		goto out;
+
+	attr.ia_valid = ATTR_OPEN;
+	if (openflags & O_TRUNC) {
+		attr.ia_valid |= ATTR_SIZE;
+		attr.ia_size = 0;
+		nfs_wb_all(inode);
+	}
+
+	inode = NFS_PROTO(dir)->open_context(dir, ctx, openflags, &attr);
+	if (IS_ERR(inode)) {
+		err = PTR_ERR(inode);
+		switch (err) {
+		case -EPERM:
+		case -EACCES:
+		case -EDQUOT:
+		case -ENOSPC:
+		case -EROFS:
+			goto out_put_ctx;
+		default:
+			goto out_drop;
+		}
+	}
+	iput(inode);
+	if (inode != dentry->d_inode)
+		goto out_drop;
+
+	nfs_set_verifier(dentry, nfs_save_change_attribute(dir));
+	nfs_file_set_open_context(filp, ctx);
+	nfs_fscache_set_inode_cookie(inode, filp);
+	err = 0;
+
+out_put_ctx:
+	put_nfs_open_context(ctx);
+out:
+	dput(parent);
+	return err;
+
+out_drop:
+	d_drop(dentry);
+	err = -EOPENSTALE;
+	goto out_put_ctx;
+}
+
+static int
+nfs4_file_fsync(struct file *file, loff_t start, loff_t end, int datasync)
+{
+	int ret;
+	struct inode *inode = file->f_path.dentry->d_inode;
+
+	do {
+		ret = filemap_write_and_wait_range(inode->i_mapping, start, end);
+		if (ret != 0)
+			break;
+		mutex_lock(&inode->i_mutex);
+		ret = nfs_file_fsync_commit(file, start, end, datasync);
+		if (!ret && !datasync)
+			/* application has asked for meta-data sync */
+			ret = pnfs_layoutcommit_inode(inode, true);
+		mutex_unlock(&inode->i_mutex);
+		/*
+		 * If nfs_file_fsync_commit detected a server reboot, then
+		 * resend all dirty pages that might have been covered by
+		 * the NFS_CONTEXT_RESEND_WRITES flag
+		 */
+		start = 0;
+		end = LLONG_MAX;
+	} while (ret == -EAGAIN);
+
+	return ret;
+}
+
+const struct file_operations nfs4_file_operations = {
+	.llseek		= nfs_file_llseek,
+	.read		= do_sync_read,
+	.write		= do_sync_write,
+	.aio_read	= nfs_file_read,
+	.aio_write	= nfs_file_write,
+	.mmap		= nfs_file_mmap,
+	.open		= nfs4_file_open,
+	.flush		= nfs_file_flush,
+	.release	= nfs_file_release,
+	.fsync		= nfs4_file_fsync,
+	.lock		= nfs_lock,
+	.flock		= nfs_flock,
+	.splice_read	= nfs_file_splice_read,
+	.splice_write	= nfs_file_splice_write,
+	.check_flags	= nfs_check_flags,
+	.setlease	= nfs_setlease,
+};
diff --git a/fs/nfs/nfs4filelayout.c b/fs/nfs/nfs4filelayout.c
index e1340293872..194c4841033 100644
--- a/fs/nfs/nfs4filelayout.c
+++ b/fs/nfs/nfs4filelayout.c
@@ -35,6 +35,7 @@
 
 #include <linux/sunrpc/metrics.h>
 
+#include "nfs4session.h"
 #include "internal.h"
 #include "delegation.h"
 #include "nfs4filelayout.h"
@@ -122,12 +123,21 @@ static void filelayout_reset_read(struct nfs_read_data *data)
 	}
 }
 
+static void filelayout_fenceme(struct inode *inode, struct pnfs_layout_hdr *lo)
+{
+	if (!test_and_clear_bit(NFS_LAYOUT_RETURN, &lo->plh_flags))
+		return;
+	clear_bit(NFS_INO_LAYOUTCOMMIT, &NFS_I(inode)->flags);
+	pnfs_return_layout(inode);
+}
+
 static int filelayout_async_handle_error(struct rpc_task *task,
 					 struct nfs4_state *state,
 					 struct nfs_client *clp,
 					 struct pnfs_layout_segment *lseg)
 {
-	struct inode *inode = lseg->pls_layout->plh_inode;
+	struct pnfs_layout_hdr *lo = lseg->pls_layout;
+	struct inode *inode = lo->plh_inode;
 	struct nfs_server *mds_server = NFS_SERVER(inode);
 	struct nfs4_deviceid_node *devid = FILELAYOUT_DEVID_NODE(lseg);
 	struct nfs_client *mds_client = mds_server->nfs_client;
@@ -169,7 +179,6 @@ static int filelayout_async_handle_error(struct rpc_task *task,
 		break;
 	case -NFS4ERR_DELAY:
 	case -NFS4ERR_GRACE:
-	case -EKEYEXPIRED:
 		rpc_delay(task, FILELAYOUT_POLL_RETRY_MAX);
 		break;
 	case -NFS4ERR_RETRY_UNCACHED_REP:
@@ -190,8 +199,6 @@ static int filelayout_async_handle_error(struct rpc_task *task,
 		 * i/o and all i/o waiting on the slot table to the MDS until
 		 * layout is destroyed and a new valid layout is obtained.
 		 */
-		set_bit(NFS_LAYOUT_INVALID,
-				&NFS_I(inode)->layout->plh_flags);
 		pnfs_destroy_layout(NFS_I(inode));
 		rpc_wake_up(&tbl->slot_tbl_waitq);
 		goto reset;
@@ -205,11 +212,9 @@ static int filelayout_async_handle_error(struct rpc_task *task,
 	case -EPIPE:
 		dprintk("%s DS connection error %d\n", __func__,
 			task->tk_status);
-		if (!filelayout_test_devid_invalid(devid))
-			_pnfs_return_layout(inode);
-		filelayout_mark_devid_invalid(devid);
+		nfs4_mark_deviceid_unavailable(devid);
+		set_bit(NFS_LAYOUT_RETURN, &lo->plh_flags);
 		rpc_wake_up(&tbl->slot_tbl_waitq);
-		nfs4_ds_disconnect(clp);
 		/* fall through */
 	default:
 reset:
@@ -269,6 +274,21 @@ filelayout_set_layoutcommit(struct nfs_write_data *wdata)
 		(unsigned long) NFS_I(hdr->inode)->layout->plh_lwb);
 }
 
+bool
+filelayout_test_devid_unavailable(struct nfs4_deviceid_node *node)
+{
+	return filelayout_test_devid_invalid(node) ||
+		nfs4_test_deviceid_unavailable(node);
+}
+
+static bool
+filelayout_reset_to_mds(struct pnfs_layout_segment *lseg)
+{
+	struct nfs4_deviceid_node *node = FILELAYOUT_DEVID_NODE(lseg);
+
+	return filelayout_test_devid_unavailable(node);
+}
+
 /*
  * Call ops for the async read/write cases
  * In the case of dense layouts, the offset needs to be reset to its
@@ -286,12 +306,10 @@ static void filelayout_read_prepare(struct rpc_task *task, void *data)
 	}
 	rdata->read_done_cb = filelayout_read_done_cb;
 
-	if (nfs41_setup_sequence(rdata->ds_clp->cl_session,
-				&rdata->args.seq_args, &rdata->res.seq_res,
-				task))
-		return;
-
-	rpc_call_start(task);
+	nfs41_setup_sequence(rdata->ds_clp->cl_session,
+			&rdata->args.seq_args,
+			&rdata->res.seq_res,
+			task);
 }
 
 static void filelayout_read_call_done(struct rpc_task *task, void *data)
@@ -318,7 +336,9 @@ static void filelayout_read_count_stats(struct rpc_task *task, void *data)
 static void filelayout_read_release(void *data)
 {
 	struct nfs_read_data *rdata = data;
+	struct pnfs_layout_hdr *lo = rdata->header->lseg->pls_layout;
 
+	filelayout_fenceme(lo->plh_inode, lo);
 	nfs_put_client(rdata->ds_clp);
 	rdata->header->mds_ops->rpc_release(data);
 }
@@ -351,9 +371,9 @@ static void prepare_to_resend_writes(struct nfs_commit_data *data)
 	struct nfs_page *first = nfs_list_entry(data->pages.next);
 
 	data->task.tk_status = 0;
-	memcpy(data->verf.verifier, first->wb_verf.verifier,
-	       sizeof(first->wb_verf.verifier));
-	data->verf.verifier[0]++; /* ensure verifier mismatch */
+	memcpy(&data->verf.verifier, &first->wb_verf,
+	       sizeof(data->verf.verifier));
+	data->verf.verifier.data[0]++; /* ensure verifier mismatch */
 }
 
 static int filelayout_commit_done_cb(struct rpc_task *task,
@@ -386,12 +406,10 @@ static void filelayout_write_prepare(struct rpc_task *task, void *data)
 		rpc_exit(task, 0);
 		return;
 	}
-	if (nfs41_setup_sequence(wdata->ds_clp->cl_session,
-				&wdata->args.seq_args, &wdata->res.seq_res,
-				task))
-		return;
-
-	rpc_call_start(task);
+	nfs41_setup_sequence(wdata->ds_clp->cl_session,
+			&wdata->args.seq_args,
+			&wdata->res.seq_res,
+			task);
 }
 
 static void filelayout_write_call_done(struct rpc_task *task, void *data)
@@ -416,7 +434,9 @@ static void filelayout_write_count_stats(struct rpc_task *task, void *data)
 static void filelayout_write_release(void *data)
 {
 	struct nfs_write_data *wdata = data;
+	struct pnfs_layout_hdr *lo = wdata->header->lseg->pls_layout;
 
+	filelayout_fenceme(lo->plh_inode, lo);
 	nfs_put_client(wdata->ds_clp);
 	wdata->header->mds_ops->rpc_release(data);
 }
@@ -425,12 +445,10 @@ static void filelayout_commit_prepare(struct rpc_task *task, void *data)
 {
 	struct nfs_commit_data *wdata = data;
 
-	if (nfs41_setup_sequence(wdata->ds_clp->cl_session,
-				&wdata->args.seq_args, &wdata->res.seq_res,
-				task))
-		return;
-
-	rpc_call_start(task);
+	nfs41_setup_sequence(wdata->ds_clp->cl_session,
+			&wdata->args.seq_args,
+			&wdata->res.seq_res,
+			task);
 }
 
 static void filelayout_write_commit_done(struct rpc_task *task, void *data)
@@ -453,7 +471,7 @@ static void filelayout_commit_release(void *calldata)
 	struct nfs_commit_data *data = calldata;
 
 	data->completion_ops->completion(data);
-	put_lseg(data->lseg);
+	pnfs_put_lseg(data->lseg);
 	nfs_put_client(data->ds_clp);
 	nfs_commitdata_release(data);
 }
@@ -488,7 +506,6 @@ filelayout_read_pagelist(struct nfs_read_data *data)
 	loff_t offset = data->args.offset;
 	u32 j, idx;
 	struct nfs_fh *fh;
-	int status;
 
 	dprintk("--> %s ino %lu pgbase %u req %Zu@%llu\n",
 		__func__, hdr->inode->i_ino,
@@ -514,9 +531,8 @@ filelayout_read_pagelist(struct nfs_read_data *data)
 	data->mds_offset = offset;
 
 	/* Perform an asynchronous read to ds */
-	status = nfs_initiate_read(ds->ds_clp->cl_rpcclient, data,
+	nfs_initiate_read(ds->ds_clp->cl_rpcclient, data,
 				  &filelayout_read_call_ops, RPC_TASK_SOFTCONN);
-	BUG_ON(status != 0);
 	return PNFS_ATTEMPTED;
 }
 
@@ -530,7 +546,6 @@ filelayout_write_pagelist(struct nfs_write_data *data, int sync)
 	loff_t offset = data->args.offset;
 	u32 j, idx;
 	struct nfs_fh *fh;
-	int status;
 
 	/* Retrieve the correct rpc_client for the byte range */
 	j = nfs4_fl_calc_j_index(lseg, offset);
@@ -555,10 +570,9 @@ filelayout_write_pagelist(struct nfs_write_data *data, int sync)
 	data->args.offset = filelayout_get_dserver_offset(lseg, offset);
 
 	/* Perform an asynchronous write */
-	status = nfs_initiate_write(ds->ds_clp->cl_rpcclient, data,
+	nfs_initiate_write(ds->ds_clp->cl_rpcclient, data,
 				    &filelayout_write_call_ops, sync,
 				    RPC_TASK_SOFTCONN);
-	BUG_ON(status != 0);
 	return PNFS_ATTEMPTED;
 }
 
@@ -608,13 +622,13 @@ filelayout_check_layout(struct pnfs_layout_hdr *lo,
 	d = nfs4_find_get_deviceid(NFS_SERVER(lo->plh_inode)->pnfs_curr_ld,
 				   NFS_SERVER(lo->plh_inode)->nfs_client, id);
 	if (d == NULL) {
-		dsaddr = get_device_info(lo->plh_inode, id, gfp_flags);
+		dsaddr = filelayout_get_device_info(lo->plh_inode, id, gfp_flags);
 		if (dsaddr == NULL)
 			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))
+	/* Found deviceid is unavailable */
+	if (filelayout_test_devid_unavailable(&dsaddr->id_node))
 			goto out_put;
 
 	fl->dsaddr = dsaddr;
@@ -726,7 +740,7 @@ filelayout_decode_layout(struct pnfs_layout_hdr *flo,
 		goto out_err;
 
 	if (fl->num_fh > 0) {
-		fl->fh_array = kzalloc(fl->num_fh * sizeof(struct nfs_fh *),
+		fl->fh_array = kcalloc(fl->num_fh, sizeof(fl->fh_array[0]),
 				       gfp_flags);
 		if (!fl->fh_array)
 			goto out_err;
@@ -885,7 +899,7 @@ static void
 filelayout_pg_init_read(struct nfs_pageio_descriptor *pgio,
 			struct nfs_page *req)
 {
-	BUG_ON(pgio->pg_lseg != NULL);
+	WARN_ON_ONCE(pgio->pg_lseg != NULL);
 
 	if (req->wb_offset != req->wb_pgbase) {
 		/*
@@ -915,7 +929,7 @@ filelayout_pg_init_write(struct nfs_pageio_descriptor *pgio,
 	struct nfs_commit_info cinfo;
 	int status;
 
-	BUG_ON(pgio->pg_lseg != NULL);
+	WARN_ON_ONCE(pgio->pg_lseg != NULL);
 
 	if (req->wb_offset != req->wb_pgbase)
 		goto out_mds;
@@ -931,7 +945,7 @@ filelayout_pg_init_write(struct nfs_pageio_descriptor *pgio,
 	nfs_init_cinfo(&cinfo, pgio->pg_inode, pgio->pg_dreq);
 	status = filelayout_alloc_commit_info(pgio->pg_lseg, &cinfo, GFP_NOFS);
 	if (status < 0) {
-		put_lseg(pgio->pg_lseg);
+		pnfs_put_lseg(pgio->pg_lseg);
 		pgio->pg_lseg = NULL;
 		goto out_mds;
 	}
@@ -985,7 +999,7 @@ filelayout_clear_request_commit(struct nfs_page *req,
 out:
 	nfs_request_remove_commit_list(req, cinfo);
 	spin_unlock(cinfo->lock);
-	put_lseg(freeme);
+	pnfs_put_lseg(freeme);
 }
 
 static struct list_head *
@@ -1018,7 +1032,7 @@ filelayout_choose_commit_list(struct nfs_page *req,
 		 * off due to a rewrite, in which case it will be done in
 		 * filelayout_clear_request_commit
 		 */
-		buckets[i].wlseg = get_lseg(lseg);
+		buckets[i].wlseg = pnfs_get_lseg(lseg);
 	}
 	set_bit(PG_COMMIT_TO_DS, &req->wb_flags);
 	cinfo->ds->nwritten++;
@@ -1128,7 +1142,7 @@ filelayout_scan_ds_commit_list(struct pnfs_commit_bucket *bucket,
 		if (list_empty(src))
 			bucket->wlseg = NULL;
 		else
-			get_lseg(bucket->clseg);
+			pnfs_get_lseg(bucket->clseg);
 	}
 	return ret;
 }
@@ -1159,12 +1173,11 @@ static void filelayout_recover_commit_reqs(struct list_head *dst,
 
 	/* NOTE cinfo->lock is NOT held, relying on fact that this is
 	 * only called on single thread per dreq.
-	 * Can't take the lock because need to do put_lseg
+	 * Can't take the lock because need to do pnfs_put_lseg
 	 */
 	for (i = 0, b = cinfo->ds->buckets; i < cinfo->ds->nbuckets; i++, b++) {
 		if (transfer_commit_list(&b->written, dst, cinfo, 0)) {
-			BUG_ON(!list_empty(&b->written));
-			put_lseg(b->wlseg);
+			pnfs_put_lseg(b->wlseg);
 			b->wlseg = NULL;
 		}
 	}
@@ -1200,7 +1213,7 @@ alloc_ds_commits(struct nfs_commit_info *cinfo, struct list_head *list)
 		if (list_empty(&bucket->committing))
 			continue;
 		nfs_retry_commit(&bucket->committing, bucket->clseg, cinfo);
-		put_lseg(bucket->clseg);
+		pnfs_put_lseg(bucket->clseg);
 		bucket->clseg = NULL;
 	}
 	/* Caller will clean up entries put on list */
diff --git a/fs/nfs/nfs4filelayout.h b/fs/nfs/nfs4filelayout.h
index 43fe802dd67..8c07241fe52 100644
--- a/fs/nfs/nfs4filelayout.h
+++ b/fs/nfs/nfs4filelayout.h
@@ -129,23 +129,13 @@ filelayout_mark_devid_invalid(struct nfs4_deviceid_node *node)
 }
 
 static inline bool
-filelayout_test_layout_invalid(struct pnfs_layout_hdr *lo)
-{
-	return test_bit(NFS_LAYOUT_INVALID, &lo->plh_flags);
-}
-
-static inline bool
 filelayout_test_devid_invalid(struct nfs4_deviceid_node *node)
 {
 	return test_bit(NFS_DEVICEID_INVALID, &node->flags);
 }
 
-static inline bool
-filelayout_reset_to_mds(struct pnfs_layout_segment *lseg)
-{
-	return filelayout_test_devid_invalid(FILELAYOUT_DEVID_NODE(lseg)) ||
-		filelayout_test_layout_invalid(lseg->pls_layout);
-}
+extern bool
+filelayout_test_devid_unavailable(struct nfs4_deviceid_node *node);
 
 extern struct nfs_fh *
 nfs4_fl_select_ds_fh(struct pnfs_layout_segment *lseg, u32 j);
@@ -158,7 +148,6 @@ struct nfs4_pnfs_ds *nfs4_fl_prepare_ds(struct pnfs_layout_segment *lseg,
 extern void nfs4_fl_put_deviceid(struct nfs4_file_layout_dsaddr *dsaddr);
 extern void nfs4_fl_free_deviceid(struct nfs4_file_layout_dsaddr *dsaddr);
 struct nfs4_file_layout_dsaddr *
-get_device_info(struct inode *inode, struct nfs4_deviceid *dev_id, gfp_t gfp_flags);
-void nfs4_ds_disconnect(struct nfs_client *clp);
+filelayout_get_device_info(struct inode *inode, struct nfs4_deviceid *dev_id, gfp_t gfp_flags);
 
 #endif /* FS_NFS_NFS4FILELAYOUT_H */
diff --git a/fs/nfs/nfs4filelayoutdev.c b/fs/nfs/nfs4filelayoutdev.c
index a1fab8da7f0..b720064bcd7 100644
--- a/fs/nfs/nfs4filelayoutdev.c
+++ b/fs/nfs/nfs4filelayoutdev.c
@@ -33,6 +33,7 @@
 #include <linux/module.h>
 
 #include "internal.h"
+#include "nfs4session.h"
 #include "nfs4filelayout.h"
 
 #define NFSDBG_FACILITY		NFSDBG_PNFS_LD
@@ -149,28 +150,6 @@ _data_server_lookup_locked(const struct list_head *dsaddrs)
 }
 
 /*
- * Lookup DS by nfs_client pointer. Zero data server client pointer
- */
-void nfs4_ds_disconnect(struct nfs_client *clp)
-{
-	struct nfs4_pnfs_ds *ds;
-	struct nfs_client *found = NULL;
-
-	dprintk("%s clp %p\n", __func__, clp);
-	spin_lock(&nfs4_ds_cache_lock);
-	list_for_each_entry(ds, &nfs4_data_server_cache, ds_node)
-		if (ds->ds_clp && ds->ds_clp == clp) {
-			found = ds->ds_clp;
-			ds->ds_clp = NULL;
-		}
-	spin_unlock(&nfs4_ds_cache_lock);
-	if (found) {
-		set_bit(NFS_CS_STOP_RENEW, &clp->cl_res_state);
-		nfs_put_client(clp);
-	}
-}
-
-/*
  * Create an rpc connection to the nfs4_pnfs_ds data server
  * Currently only supports IPv4 and IPv6 addresses
  */
@@ -184,8 +163,6 @@ nfs4_ds_connect(struct nfs_server *mds_srv, struct nfs4_pnfs_ds *ds)
 	dprintk("--> %s DS %s au_flavor %d\n", __func__, ds->ds_remotestr,
 		mds_srv->nfs_client->cl_rpcclient->cl_auth->au_flavor);
 
-	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);
@@ -690,7 +667,7 @@ decode_and_add_device(struct inode *inode, struct pnfs_device *dev, gfp_t gfp_fl
  * of available devices, and return it.
  */
 struct nfs4_file_layout_dsaddr *
-get_device_info(struct inode *inode, struct nfs4_deviceid *dev_id, gfp_t gfp_flags)
+filelayout_get_device_info(struct inode *inode, struct nfs4_deviceid *dev_id, gfp_t gfp_flags)
 {
 	struct pnfs_device *pdev = NULL;
 	u32 max_resp_sz;
@@ -728,7 +705,7 @@ get_device_info(struct inode *inode, struct nfs4_deviceid *dev_id, gfp_t gfp_fla
 	pdev->layout_type = LAYOUT_NFSV4_1_FILES;
 	pdev->pages = pages;
 	pdev->pgbase = 0;
-	pdev->pglen = PAGE_SIZE * max_pages;
+	pdev->pglen = max_resp_sz;
 	pdev->mincount = 0;
 
 	rc = nfs4_proc_getdeviceinfo(server, pdev);
@@ -804,13 +781,14 @@ nfs4_fl_prepare_ds(struct pnfs_layout_segment *lseg, u32 ds_idx)
 	struct nfs4_pnfs_ds *ds = dsaddr->ds_list[ds_idx];
 	struct nfs4_deviceid_node *devid = FILELAYOUT_DEVID_NODE(lseg);
 
-	if (filelayout_test_devid_invalid(devid))
+	if (filelayout_test_devid_unavailable(devid))
 		return NULL;
 
 	if (ds == NULL) {
 		printk(KERN_ERR "NFS: %s: No data server for offset index %d\n",
 			__func__, ds_idx);
-		goto mark_dev_invalid;
+		filelayout_mark_devid_invalid(devid);
+		return NULL;
 	}
 
 	if (!ds->ds_clp) {
@@ -818,14 +796,12 @@ nfs4_fl_prepare_ds(struct pnfs_layout_segment *lseg, u32 ds_idx)
 		int err;
 
 		err = nfs4_ds_connect(s, ds);
-		if (err)
-			goto mark_dev_invalid;
+		if (err) {
+			nfs4_mark_deviceid_unavailable(devid);
+			return NULL;
+		}
 	}
 	return ds;
-
-mark_dev_invalid:
-	filelayout_mark_devid_invalid(devid);
-	return NULL;
 }
 
 module_param(dataserver_retrans, uint, 0644);
diff --git a/fs/nfs/nfs4getroot.c b/fs/nfs/nfs4getroot.c
new file mode 100644
index 00000000000..549462e5b9b
--- /dev/null
+++ b/fs/nfs/nfs4getroot.c
@@ -0,0 +1,50 @@
+/*
+* Copyright (C) 2006 Red Hat, Inc. All Rights Reserved.
+* Written by David Howells (dhowells@redhat.com)
+*/
+
+#include <linux/nfs_fs.h>
+#include "nfs4_fs.h"
+#include "internal.h"
+
+#define NFSDBG_FACILITY		NFSDBG_CLIENT
+
+int nfs4_get_rootfh(struct nfs_server *server, struct nfs_fh *mntfh)
+{
+	struct nfs_fsinfo fsinfo;
+	int ret = -ENOMEM;
+
+	dprintk("--> nfs4_get_rootfh()\n");
+
+	fsinfo.fattr = nfs_alloc_fattr();
+	if (fsinfo.fattr == NULL)
+		goto out;
+
+	/* Start by getting the root filehandle from the server */
+	ret = nfs4_proc_get_rootfh(server, mntfh, &fsinfo);
+	if (ret < 0) {
+		dprintk("nfs4_get_rootfh: getroot error = %d\n", -ret);
+		goto out;
+	}
+
+	if (!(fsinfo.fattr->valid & NFS_ATTR_FATTR_TYPE)
+			|| !S_ISDIR(fsinfo.fattr->mode)) {
+		printk(KERN_ERR "nfs4_get_rootfh:"
+		       " getroot encountered non-directory\n");
+		ret = -ENOTDIR;
+		goto out;
+	}
+
+	if (fsinfo.fattr->valid & NFS_ATTR_FATTR_V4_REFERRAL) {
+		printk(KERN_ERR "nfs4_get_rootfh:"
+		       " getroot obtained referral\n");
+		ret = -EREMOTE;
+		goto out;
+	}
+
+	memcpy(&server->fsid, &fsinfo.fattr->fsid, sizeof(server->fsid));
+out:
+	nfs_free_fattr(fsinfo.fattr);
+	dprintk("<-- nfs4_get_rootfh() = %d\n", ret);
+	return ret;
+}
diff --git a/fs/nfs/nfs4namespace.c b/fs/nfs/nfs4namespace.c
index 017b4b01a69..1e09eb78543 100644
--- a/fs/nfs/nfs4namespace.c
+++ b/fs/nfs/nfs4namespace.c
@@ -81,7 +81,8 @@ static char *nfs_path_component(const char *nfspath, const char *end)
 static char *nfs4_path(struct dentry *dentry, char *buffer, ssize_t buflen)
 {
 	char *limit;
-	char *path = nfs_path(&limit, dentry, buffer, buflen);
+	char *path = nfs_path(&limit, dentry, buffer, buflen,
+			      NFS_PATH_CANONICAL);
 	if (!IS_ERR(path)) {
 		char *path_component = nfs_path_component(path, limit);
 		if (path_component)
@@ -192,25 +193,13 @@ out:
 struct rpc_clnt *nfs4_create_sec_client(struct rpc_clnt *clnt, struct inode *inode,
 					struct qstr *name)
 {
-	struct rpc_clnt *clone;
-	struct rpc_auth *auth;
 	rpc_authflavor_t flavor;
 
 	flavor = nfs4_negotiate_security(inode, name);
 	if ((int)flavor < 0)
-		return ERR_PTR(flavor);
+		return ERR_PTR((int)flavor);
 
-	clone = rpc_clone_client(clnt);
-	if (IS_ERR(clone))
-		return clone;
-
-	auth = rpcauth_create(flavor, clone);
-	if (!auth) {
-		rpc_shutdown_client(clone);
-		clone = ERR_PTR(-EIO);
-	}
-
-	return clone;
+	return rpc_clone_client_set_auth(clnt, flavor);
 }
 
 static struct vfsmount *try_location(struct nfs_clone_mount *mountdata,
diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c
index 15fc7e4664e..cf747ef8665 100644
--- a/fs/nfs/nfs4proc.c
+++ b/fs/nfs/nfs4proc.c
@@ -43,7 +43,6 @@
 #include <linux/printk.h>
 #include <linux/slab.h>
 #include <linux/sunrpc/clnt.h>
-#include <linux/sunrpc/gss_api.h>
 #include <linux/nfs.h>
 #include <linux/nfs4.h>
 #include <linux/nfs_fs.h>
@@ -53,7 +52,6 @@
 #include <linux/mount.h>
 #include <linux/module.h>
 #include <linux/nfs_idmap.h>
-#include <linux/sunrpc/bc_xprt.h>
 #include <linux/xattr.h>
 #include <linux/utsname.h>
 #include <linux/freezer.h>
@@ -65,16 +63,14 @@
 #include "callback.h"
 #include "pnfs.h"
 #include "netns.h"
+#include "nfs4session.h"
+#include "fscache.h"
 
 #define NFSDBG_FACILITY		NFSDBG_PROC
 
 #define NFS4_POLL_RETRY_MIN	(HZ/10)
 #define NFS4_POLL_RETRY_MAX	(15*HZ)
 
-#define NFS4_MAX_LOOP_ON_RECOVER (10)
-
-static unsigned short max_session_slots = NFS4_DEF_SLOT_TABLE_SIZE;
-
 struct nfs4_opendata;
 static int _nfs4_proc_open(struct nfs4_opendata *data);
 static int _nfs4_recover_proc_open(struct nfs4_opendata *data);
@@ -107,6 +103,8 @@ static int nfs4_map_errors(int err)
 		return -EACCES;
 	case -NFS4ERR_MINOR_VERS_MISMATCH:
 		return -EPROTONOSUPPORT;
+	case -NFS4ERR_ACCESS:
+		return -EACCES;
 	default:
 		dprintk("%s could not handle NFSv4 error %d\n",
 				__func__, -err);
@@ -153,6 +151,12 @@ static const u32 nfs4_pnfs_open_bitmap[3] = {
 	FATTR4_WORD2_MDSTHRESHOLD
 };
 
+static const u32 nfs4_open_noattr_bitmap[3] = {
+	FATTR4_WORD0_TYPE
+	| FATTR4_WORD0_CHANGE
+	| FATTR4_WORD0_FILEID,
+};
+
 const u32 nfs4_statfs_bitmap[2] = {
 	FATTR4_WORD0_FILES_AVAIL
 	| FATTR4_WORD0_FILES_FREE
@@ -201,7 +205,6 @@ static void nfs4_setup_readdir(u64 cookie, __be32 *verifier, struct dentry *dent
 {
 	__be32 *start, *p;
 
-	BUG_ON(readdir->count < 80);
 	if (cookie > 2) {
 		readdir->cookie = cookie;
 		memcpy(&readdir->verifier, verifier, sizeof(readdir->verifier));
@@ -251,17 +254,6 @@ static void nfs4_setup_readdir(u64 cookie, __be32 *verifier, struct dentry *dent
 	kunmap_atomic(start);
 }
 
-static int nfs4_wait_clnt_recover(struct nfs_client *clp)
-{
-	int res;
-
-	might_sleep();
-
-	res = wait_on_bit(&clp->cl_state, NFS4CLNT_MANAGER_RUNNING,
-			nfs_wait_bit_killable, TASK_KILLABLE);
-	return res;
-}
-
 static int nfs4_delay(struct rpc_clnt *clnt, long *timeout)
 {
 	int res = 0;
@@ -294,8 +286,8 @@ static int nfs4_handle_exception(struct nfs_server *server, int errorcode, struc
 		case 0:
 			return 0;
 		case -NFS4ERR_OPENMODE:
-			if (inode && nfs_have_delegation(inode, FMODE_READ)) {
-				nfs_inode_return_delegation(inode);
+			if (inode && nfs4_have_delegation(inode, FMODE_READ)) {
+				nfs4_inode_return_delegation(inode);
 				exception->retry = 1;
 				return 0;
 			}
@@ -329,8 +321,7 @@ static int nfs4_handle_exception(struct nfs_server *server, int errorcode, struc
 			dprintk("%s ERROR: %d Reset session\n", __func__,
 				errorcode);
 			nfs4_schedule_session_recovery(clp->cl_session, errorcode);
-			exception->retry = 1;
-			break;
+			goto wait_on_recovery;
 #endif /* defined(CONFIG_NFS_V4_1) */
 		case -NFS4ERR_FILE_OPEN:
 			if (exception->timeout > HZ) {
@@ -342,7 +333,6 @@ static int nfs4_handle_exception(struct nfs_server *server, int errorcode, struc
 			}
 		case -NFS4ERR_GRACE:
 		case -NFS4ERR_DELAY:
-		case -EKEYEXPIRED:
 			ret = nfs4_delay(server->client, &exception->timeout);
 			if (ret != 0)
 				break;
@@ -388,144 +378,136 @@ static void renew_lease(const struct nfs_server *server, unsigned long timestamp
 
 #if defined(CONFIG_NFS_V4_1)
 
-/*
- * nfs4_free_slot - free a slot and efficiently update slot table.
- *
- * freeing a slot is trivially done by clearing its respective bit
- * in the bitmap.
- * If the freed slotid equals highest_used_slotid we want to update it
- * so that the server would be able to size down the slot table if needed,
- * otherwise we know that the highest_used_slotid is still in use.
- * When updating highest_used_slotid there may be "holes" in the bitmap
- * so we need to scan down from highest_used_slotid to 0 looking for the now
- * highest slotid in use.
- * If none found, highest_used_slotid is set to NFS4_NO_SLOT.
- *
- * Must be called while holding tbl->slot_tbl_lock
- */
-static void
-nfs4_free_slot(struct nfs4_slot_table *tbl, u32 slotid)
-{
-	BUG_ON(slotid >= NFS4_MAX_SLOT_TABLE);
-	/* clear used bit in bitmap */
-	__clear_bit(slotid, tbl->used_slots);
-
-	/* update highest_used_slotid when it is freed */
-	if (slotid == tbl->highest_used_slotid) {
-		slotid = find_last_bit(tbl->used_slots, tbl->max_slots);
-		if (slotid < tbl->max_slots)
-			tbl->highest_used_slotid = slotid;
-		else
-			tbl->highest_used_slotid = NFS4_NO_SLOT;
-	}
-	dprintk("%s: slotid %u highest_used_slotid %d\n", __func__,
-		slotid, tbl->highest_used_slotid);
-}
-
-bool nfs4_set_task_privileged(struct rpc_task *task, void *dummy)
-{
-	rpc_task_set_priority(task, RPC_PRIORITY_PRIVILEGED);
-	return true;
-}
-
-/*
- * Signal state manager thread if session fore channel is drained
- */
-static void nfs4_check_drain_fc_complete(struct nfs4_session *ses)
-{
-	if (!test_bit(NFS4_SESSION_DRAINING, &ses->session_state)) {
-		rpc_wake_up_first(&ses->fc_slot_table.slot_tbl_waitq,
-				nfs4_set_task_privileged, NULL);
-		return;
-	}
-
-	if (ses->fc_slot_table.highest_used_slotid != NFS4_NO_SLOT)
-		return;
-
-	dprintk("%s COMPLETE: Session Fore Channel Drained\n", __func__);
-	complete(&ses->fc_slot_table.complete);
-}
-
-/*
- * Signal state manager thread if session back channel is drained
- */
-void nfs4_check_drain_bc_complete(struct nfs4_session *ses)
-{
-	if (!test_bit(NFS4_SESSION_DRAINING, &ses->session_state) ||
-	    ses->bc_slot_table.highest_used_slotid != NFS4_NO_SLOT)
-		return;
-	dprintk("%s COMPLETE: Session Back Channel Drained\n", __func__);
-	complete(&ses->bc_slot_table.complete);
-}
-
 static void nfs41_sequence_free_slot(struct nfs4_sequence_res *res)
 {
+	struct nfs4_session *session;
 	struct nfs4_slot_table *tbl;
+	bool send_new_highest_used_slotid = false;
 
-	tbl = &res->sr_session->fc_slot_table;
 	if (!res->sr_slot) {
 		/* just wake up the next guy waiting since
 		 * we may have not consumed a slot after all */
 		dprintk("%s: No slot\n", __func__);
 		return;
 	}
+	tbl = res->sr_slot->table;
+	session = tbl->session;
 
 	spin_lock(&tbl->slot_tbl_lock);
-	nfs4_free_slot(tbl, res->sr_slot - tbl->slots);
-	nfs4_check_drain_fc_complete(res->sr_session);
+	/* Be nice to the server: try to ensure that the last transmitted
+	 * value for highest_user_slotid <= target_highest_slotid
+	 */
+	if (tbl->highest_used_slotid > tbl->target_highest_slotid)
+		send_new_highest_used_slotid = true;
+
+	if (nfs41_wake_and_assign_slot(tbl, res->sr_slot)) {
+		send_new_highest_used_slotid = false;
+		goto out_unlock;
+	}
+	nfs4_free_slot(tbl, res->sr_slot);
+
+	if (tbl->highest_used_slotid != NFS4_NO_SLOT)
+		send_new_highest_used_slotid = false;
+out_unlock:
 	spin_unlock(&tbl->slot_tbl_lock);
 	res->sr_slot = NULL;
+	if (send_new_highest_used_slotid)
+		nfs41_server_notify_highest_slotid_update(session->clp);
 }
 
 static int nfs41_sequence_done(struct rpc_task *task, struct nfs4_sequence_res *res)
 {
-	unsigned long timestamp;
+	struct nfs4_session *session;
+	struct nfs4_slot *slot;
 	struct nfs_client *clp;
-
-	/*
-	 * sr_status remains 1 if an RPC level error occurred. The server
-	 * may or may not have processed the sequence operation..
-	 * Proceed as if the server received and processed the sequence
-	 * operation.
-	 */
-	if (res->sr_status == 1)
-		res->sr_status = NFS_OK;
+	bool interrupted = false;
+	int ret = 1;
 
 	/* don't increment the sequence number if the task wasn't sent */
 	if (!RPC_WAS_SENT(task))
 		goto out;
 
+	slot = res->sr_slot;
+	session = slot->table->session;
+
+	if (slot->interrupted) {
+		slot->interrupted = 0;
+		interrupted = true;
+	}
+
 	/* Check the SEQUENCE operation status */
 	switch (res->sr_status) {
 	case 0:
 		/* Update the slot's sequence and clientid lease timer */
-		++res->sr_slot->seq_nr;
-		timestamp = res->sr_renewal_time;
-		clp = res->sr_session->clp;
-		do_renew_lease(clp, timestamp);
+		++slot->seq_nr;
+		clp = session->clp;
+		do_renew_lease(clp, res->sr_timestamp);
 		/* Check sequence flags */
 		if (res->sr_status_flags != 0)
 			nfs4_schedule_lease_recovery(clp);
+		nfs41_update_target_slotid(slot->table, slot, res);
 		break;
+	case 1:
+		/*
+		 * sr_status remains 1 if an RPC level error occurred.
+		 * The server may or may not have processed the sequence
+		 * operation..
+		 * Mark the slot as having hosted an interrupted RPC call.
+		 */
+		slot->interrupted = 1;
+		goto out;
 	case -NFS4ERR_DELAY:
 		/* The server detected a resend of the RPC call and
 		 * returned NFS4ERR_DELAY as per Section 2.10.6.2
 		 * of RFC5661.
 		 */
-		dprintk("%s: slot=%td seq=%d: Operation in progress\n",
+		dprintk("%s: slot=%u seq=%u: Operation in progress\n",
 			__func__,
-			res->sr_slot - res->sr_session->fc_slot_table.slots,
-			res->sr_slot->seq_nr);
+			slot->slot_nr,
+			slot->seq_nr);
 		goto out_retry;
+	case -NFS4ERR_BADSLOT:
+		/*
+		 * The slot id we used was probably retired. Try again
+		 * using a different slot id.
+		 */
+		goto retry_nowait;
+	case -NFS4ERR_SEQ_MISORDERED:
+		/*
+		 * Was the last operation on this sequence interrupted?
+		 * If so, retry after bumping the sequence number.
+		 */
+		if (interrupted) {
+			++slot->seq_nr;
+			goto retry_nowait;
+		}
+		/*
+		 * Could this slot have been previously retired?
+		 * If so, then the server may be expecting seq_nr = 1!
+		 */
+		if (slot->seq_nr != 1) {
+			slot->seq_nr = 1;
+			goto retry_nowait;
+		}
+		break;
+	case -NFS4ERR_SEQ_FALSE_RETRY:
+		++slot->seq_nr;
+		goto retry_nowait;
 	default:
 		/* Just update the slot sequence no. */
-		++res->sr_slot->seq_nr;
+		++slot->seq_nr;
 	}
 out:
 	/* The session may be reset by one of the error handlers. */
 	dprintk("%s: Error %d free the slot \n", __func__, res->sr_status);
 	nfs41_sequence_free_slot(res);
-	return 1;
+	return ret;
+retry_nowait:
+	if (rpc_restart_call_prepare(task)) {
+		task->tk_status = 0;
+		ret = 0;
+	}
+	goto out;
 out_retry:
 	if (!rpc_restart_call(task))
 		goto out;
@@ -536,55 +518,27 @@ out_retry:
 static int nfs4_sequence_done(struct rpc_task *task,
 			       struct nfs4_sequence_res *res)
 {
-	if (res->sr_session == NULL)
+	if (res->sr_slot == NULL)
 		return 1;
 	return nfs41_sequence_done(task, res);
 }
 
-/*
- * nfs4_find_slot - efficiently look for a free slot
- *
- * nfs4_find_slot looks for an unset bit in the used_slots bitmap.
- * If found, we mark the slot as used, update the highest_used_slotid,
- * and respectively set up the sequence operation args.
- * The slot number is returned if found, or NFS4_NO_SLOT otherwise.
- *
- * Note: must be called with under the slot_tbl_lock.
- */
-static u32
-nfs4_find_slot(struct nfs4_slot_table *tbl)
-{
-	u32 slotid;
-	u32 ret_id = NFS4_NO_SLOT;
-
-	dprintk("--> %s used_slots=%04lx highest_used=%u max_slots=%u\n",
-		__func__, tbl->used_slots[0], tbl->highest_used_slotid,
-		tbl->max_slots);
-	slotid = find_first_zero_bit(tbl->used_slots, tbl->max_slots);
-	if (slotid >= tbl->max_slots)
-		goto out;
-	__set_bit(slotid, tbl->used_slots);
-	if (slotid > tbl->highest_used_slotid ||
-			tbl->highest_used_slotid == NFS4_NO_SLOT)
-		tbl->highest_used_slotid = slotid;
-	ret_id = slotid;
-out:
-	dprintk("<-- %s used_slots=%04lx highest_used=%d slotid=%d \n",
-		__func__, tbl->used_slots[0], tbl->highest_used_slotid, ret_id);
-	return ret_id;
-}
-
 static void nfs41_init_sequence(struct nfs4_sequence_args *args,
 		struct nfs4_sequence_res *res, int cache_reply)
 {
-	args->sa_session = NULL;
+	args->sa_slot = NULL;
 	args->sa_cache_this = 0;
+	args->sa_privileged = 0;
 	if (cache_reply)
 		args->sa_cache_this = 1;
-	res->sr_session = NULL;
 	res->sr_slot = NULL;
 }
 
+static void nfs4_set_sequence_privileged(struct nfs4_sequence_args *args)
+{
+	args->sa_privileged = 1;
+}
+
 int nfs41_setup_sequence(struct nfs4_session *session,
 				struct nfs4_sequence_args *args,
 				struct nfs4_sequence_res *res,
@@ -592,59 +546,59 @@ int nfs41_setup_sequence(struct nfs4_session *session,
 {
 	struct nfs4_slot *slot;
 	struct nfs4_slot_table *tbl;
-	u32 slotid;
 
 	dprintk("--> %s\n", __func__);
 	/* slot already allocated? */
 	if (res->sr_slot != NULL)
-		return 0;
+		goto out_success;
 
 	tbl = &session->fc_slot_table;
 
+	task->tk_timeout = 0;
+
 	spin_lock(&tbl->slot_tbl_lock);
 	if (test_bit(NFS4_SESSION_DRAINING, &session->session_state) &&
-	    !rpc_task_has_priority(task, RPC_PRIORITY_PRIVILEGED)) {
+	    !args->sa_privileged) {
 		/* The state manager will wait until the slot table is empty */
-		rpc_sleep_on(&tbl->slot_tbl_waitq, task, NULL);
-		spin_unlock(&tbl->slot_tbl_lock);
 		dprintk("%s session is draining\n", __func__);
-		return -EAGAIN;
-	}
-
-	if (!rpc_queue_empty(&tbl->slot_tbl_waitq) &&
-	    !rpc_task_has_priority(task, RPC_PRIORITY_PRIVILEGED)) {
-		rpc_sleep_on(&tbl->slot_tbl_waitq, task, NULL);
-		spin_unlock(&tbl->slot_tbl_lock);
-		dprintk("%s enforce FIFO order\n", __func__);
-		return -EAGAIN;
+		goto out_sleep;
 	}
 
-	slotid = nfs4_find_slot(tbl);
-	if (slotid == NFS4_NO_SLOT) {
-		rpc_sleep_on(&tbl->slot_tbl_waitq, task, NULL);
-		spin_unlock(&tbl->slot_tbl_lock);
+	slot = nfs4_alloc_slot(tbl);
+	if (IS_ERR(slot)) {
+		/* If out of memory, try again in 1/4 second */
+		if (slot == ERR_PTR(-ENOMEM))
+			task->tk_timeout = HZ >> 2;
 		dprintk("<-- %s: no free slots\n", __func__);
-		return -EAGAIN;
+		goto out_sleep;
 	}
 	spin_unlock(&tbl->slot_tbl_lock);
 
-	rpc_task_set_priority(task, RPC_PRIORITY_NORMAL);
-	slot = tbl->slots + slotid;
-	args->sa_session = session;
-	args->sa_slotid = slotid;
+	args->sa_slot = slot;
 
-	dprintk("<-- %s slotid=%d seqid=%d\n", __func__, slotid, slot->seq_nr);
+	dprintk("<-- %s slotid=%d seqid=%d\n", __func__,
+			slot->slot_nr, slot->seq_nr);
 
-	res->sr_session = session;
 	res->sr_slot = slot;
-	res->sr_renewal_time = jiffies;
+	res->sr_timestamp = jiffies;
 	res->sr_status_flags = 0;
 	/*
 	 * sr_status is only set in decode_sequence, and so will remain
 	 * set to 1 if an rpc level failure occurs.
 	 */
 	res->sr_status = 1;
+out_success:
+	rpc_call_start(task);
 	return 0;
+out_sleep:
+	/* Privileged tasks are queued with top priority */
+	if (args->sa_privileged)
+		rpc_sleep_on_priority(&tbl->slot_tbl_waitq, task,
+				NULL, RPC_PRIORITY_PRIVILEGED);
+	else
+		rpc_sleep_on(&tbl->slot_tbl_waitq, task, NULL);
+	spin_unlock(&tbl->slot_tbl_lock);
+	return -EAGAIN;
 }
 EXPORT_SYMBOL_GPL(nfs41_setup_sequence);
 
@@ -656,12 +610,14 @@ int nfs4_setup_sequence(const struct nfs_server *server,
 	struct nfs4_session *session = nfs4_get_session(server);
 	int ret = 0;
 
-	if (session == NULL)
+	if (session == NULL) {
+		rpc_call_start(task);
 		goto out;
+	}
 
-	dprintk("--> %s clp %p session %p sr_slot %td\n",
+	dprintk("--> %s clp %p session %p sr_slot %d\n",
 		__func__, session->clp, session, res->sr_slot ?
-			res->sr_slot - session->fc_slot_table.slots : -1);
+			res->sr_slot->slot_nr : -1);
 
 	ret = nfs41_setup_sequence(session, args, res, task);
 out:
@@ -678,19 +634,11 @@ struct nfs41_call_sync_data {
 static void nfs41_call_sync_prepare(struct rpc_task *task, void *calldata)
 {
 	struct nfs41_call_sync_data *data = calldata;
+	struct nfs4_session *session = nfs4_get_session(data->seq_server);
 
 	dprintk("--> %s data->seq_server %p\n", __func__, data->seq_server);
 
-	if (nfs4_setup_sequence(data->seq_server, data->seq_args,
-				data->seq_res, task))
-		return;
-	rpc_call_start(task);
-}
-
-static void nfs41_call_priv_sync_prepare(struct rpc_task *task, void *calldata)
-{
-	rpc_task_set_priority(task, RPC_PRIORITY_PRIVILEGED);
-	nfs41_call_sync_prepare(task, calldata);
+	nfs41_setup_sequence(session, data->seq_args, data->seq_res, task);
 }
 
 static void nfs41_call_sync_done(struct rpc_task *task, void *calldata)
@@ -705,17 +653,11 @@ static const struct rpc_call_ops nfs41_call_sync_ops = {
 	.rpc_call_done = nfs41_call_sync_done,
 };
 
-static const struct rpc_call_ops nfs41_call_priv_sync_ops = {
-	.rpc_call_prepare = nfs41_call_priv_sync_prepare,
-	.rpc_call_done = nfs41_call_sync_done,
-};
-
 static int nfs4_call_sync_sequence(struct rpc_clnt *clnt,
 				   struct nfs_server *server,
 				   struct rpc_message *msg,
 				   struct nfs4_sequence_args *args,
-				   struct nfs4_sequence_res *res,
-				   int privileged)
+				   struct nfs4_sequence_res *res)
 {
 	int ret;
 	struct rpc_task *task;
@@ -731,8 +673,6 @@ static int nfs4_call_sync_sequence(struct rpc_clnt *clnt,
 		.callback_data = &data
 	};
 
-	if (privileged)
-		task_setup.callback_ops = &nfs41_call_priv_sync_ops;
 	task = rpc_run_task(&task_setup);
 	if (IS_ERR(task))
 		ret = PTR_ERR(task);
@@ -743,24 +683,18 @@ static int nfs4_call_sync_sequence(struct rpc_clnt *clnt,
 	return ret;
 }
 
-int _nfs4_call_sync_session(struct rpc_clnt *clnt,
-			    struct nfs_server *server,
-			    struct rpc_message *msg,
-			    struct nfs4_sequence_args *args,
-			    struct nfs4_sequence_res *res,
-			    int cache_reply)
-{
-	nfs41_init_sequence(args, res, cache_reply);
-	return nfs4_call_sync_sequence(clnt, server, msg, args, res, 0);
-}
-
 #else
-static inline
+static
 void nfs41_init_sequence(struct nfs4_sequence_args *args,
 		struct nfs4_sequence_res *res, int cache_reply)
 {
 }
 
+static void nfs4_set_sequence_privileged(struct nfs4_sequence_args *args)
+{
+}
+
+
 static int nfs4_sequence_done(struct rpc_task *task,
 			       struct nfs4_sequence_res *res)
 {
@@ -768,18 +702,17 @@ static int nfs4_sequence_done(struct rpc_task *task,
 }
 #endif /* CONFIG_NFS_V4_1 */
 
+static
 int _nfs4_call_sync(struct rpc_clnt *clnt,
 		    struct nfs_server *server,
 		    struct rpc_message *msg,
 		    struct nfs4_sequence_args *args,
-		    struct nfs4_sequence_res *res,
-		    int cache_reply)
+		    struct nfs4_sequence_res *res)
 {
-	nfs41_init_sequence(args, res, cache_reply);
 	return rpc_call_sync(clnt, msg, 0);
 }
 
-static inline
+static
 int nfs4_call_sync(struct rpc_clnt *clnt,
 		   struct nfs_server *server,
 		   struct rpc_message *msg,
@@ -787,8 +720,9 @@ int nfs4_call_sync(struct rpc_clnt *clnt,
 		   struct nfs4_sequence_res *res,
 		   int cache_reply)
 {
+	nfs41_init_sequence(args, res, cache_reply);
 	return server->nfs_client->cl_mvops->call_sync(clnt, server, msg,
-						args, res, cache_reply);
+						args, res);
 }
 
 static void update_changeattr(struct inode *dir, struct nfs4_change_info *cinfo)
@@ -800,6 +734,7 @@ static void update_changeattr(struct inode *dir, struct nfs4_change_info *cinfo)
 	if (!cinfo->atomic || cinfo->before != dir->i_version)
 		nfs_force_lookup_revalidate(dir);
 	dir->i_version = cinfo->after;
+	nfs_fscache_invalidate(dir);
 	spin_unlock(&dir->i_lock);
 }
 
@@ -830,6 +765,7 @@ static void nfs4_init_opendata_res(struct nfs4_opendata *p)
 	p->o_res.seqid = p->o_arg.seqid;
 	p->c_res.seqid = p->c_arg.seqid;
 	p->o_res.server = p->o_arg.server;
+	p->o_res.access_request = p->o_arg.access;
 	nfs_fattr_init(&p->f_attr);
 	nfs_fattr_init_names(&p->f_attr, &p->owner_name, &p->group_name);
 }
@@ -858,6 +794,14 @@ static struct nfs4_opendata *nfs4_opendata_alloc(struct dentry *dentry,
 	p->o_arg.fh = NFS_FH(dir);
 	p->o_arg.open_flags = flags;
 	p->o_arg.fmode = fmode & (FMODE_READ|FMODE_WRITE);
+	/* don't put an ACCESS op in OPEN compound if O_EXCL, because ACCESS
+	 * will return permission denied for all bits until close */
+	if (!(flags & O_EXCL)) {
+		/* ask server to check for all possible rights as results
+		 * are cached */
+		p->o_arg.access = NFS4_ACCESS_READ | NFS4_ACCESS_MODIFY |
+				  NFS4_ACCESS_EXTEND | NFS4_ACCESS_EXECUTE;
+	}
 	p->o_arg.clientid = server->nfs_client->cl_clientid;
 	p->o_arg.id.create_time = ktime_to_ns(sp->so_seqid.create_time);
 	p->o_arg.id.uniquifier = sp->so_seqid.owner_id;
@@ -1065,7 +1009,7 @@ static void nfs4_return_incompatible_delegation(struct inode *inode, fmode_t fmo
 		return;
 	}
 	rcu_read_unlock();
-	nfs_inode_return_delegation(inode);
+	nfs4_inode_return_delegation(inode);
 }
 
 static struct nfs4_state *nfs4_try_open_cached(struct nfs4_opendata *opendata)
@@ -1113,11 +1057,80 @@ out_return_state:
 	return state;
 }
 
-static struct nfs4_state *nfs4_opendata_to_nfs4_state(struct nfs4_opendata *data)
+static void
+nfs4_opendata_check_deleg(struct nfs4_opendata *data, struct nfs4_state *state)
+{
+	struct nfs_client *clp = NFS_SERVER(state->inode)->nfs_client;
+	struct nfs_delegation *delegation;
+	int delegation_flags = 0;
+
+	rcu_read_lock();
+	delegation = rcu_dereference(NFS_I(state->inode)->delegation);
+	if (delegation)
+		delegation_flags = delegation->flags;
+	rcu_read_unlock();
+	if (data->o_arg.claim == NFS4_OPEN_CLAIM_DELEGATE_CUR) {
+		pr_err_ratelimited("NFS: Broken NFSv4 server %s is "
+				   "returning a delegation for "
+				   "OPEN(CLAIM_DELEGATE_CUR)\n",
+				   clp->cl_hostname);
+	} else if ((delegation_flags & 1UL<<NFS_DELEGATION_NEED_RECLAIM) == 0)
+		nfs_inode_set_delegation(state->inode,
+					 data->owner->so_cred,
+					 &data->o_res);
+	else
+		nfs_inode_reclaim_delegation(state->inode,
+					     data->owner->so_cred,
+					     &data->o_res);
+}
+
+/*
+ * Check the inode attributes against the CLAIM_PREVIOUS returned attributes
+ * and update the nfs4_state.
+ */
+static struct nfs4_state *
+_nfs4_opendata_reclaim_to_nfs4_state(struct nfs4_opendata *data)
+{
+	struct inode *inode = data->state->inode;
+	struct nfs4_state *state = data->state;
+	int ret;
+
+	if (!data->rpc_done) {
+		ret = data->rpc_status;
+		goto err;
+	}
+
+	ret = -ESTALE;
+	if (!(data->f_attr.valid & NFS_ATTR_FATTR_TYPE) ||
+	    !(data->f_attr.valid & NFS_ATTR_FATTR_FILEID) ||
+	    !(data->f_attr.valid & NFS_ATTR_FATTR_CHANGE))
+		goto err;
+
+	ret = -ENOMEM;
+	state = nfs4_get_open_state(inode, data->owner);
+	if (state == NULL)
+		goto err;
+
+	ret = nfs_refresh_inode(inode, &data->f_attr);
+	if (ret)
+		goto err;
+
+	if (data->o_res.delegation_type != 0)
+		nfs4_opendata_check_deleg(data, state);
+	update_open_stateid(state, &data->o_res.stateid, NULL,
+			    data->o_arg.fmode);
+
+	return state;
+err:
+	return ERR_PTR(ret);
+
+}
+
+static struct nfs4_state *
+_nfs4_opendata_to_nfs4_state(struct nfs4_opendata *data)
 {
 	struct inode *inode;
 	struct nfs4_state *state = NULL;
-	struct nfs_delegation *delegation;
 	int ret;
 
 	if (!data->rpc_done) {
@@ -1136,30 +1149,8 @@ static struct nfs4_state *nfs4_opendata_to_nfs4_state(struct nfs4_opendata *data
 	state = nfs4_get_open_state(inode, data->owner);
 	if (state == NULL)
 		goto err_put_inode;
-	if (data->o_res.delegation_type != 0) {
-		struct nfs_client *clp = NFS_SERVER(inode)->nfs_client;
-		int delegation_flags = 0;
-
-		rcu_read_lock();
-		delegation = rcu_dereference(NFS_I(inode)->delegation);
-		if (delegation)
-			delegation_flags = delegation->flags;
-		rcu_read_unlock();
-		if (data->o_arg.claim == NFS4_OPEN_CLAIM_DELEGATE_CUR) {
-			pr_err_ratelimited("NFS: Broken NFSv4 server %s is "
-					"returning a delegation for "
-					"OPEN(CLAIM_DELEGATE_CUR)\n",
-					clp->cl_hostname);
-		} else if ((delegation_flags & 1UL<<NFS_DELEGATION_NEED_RECLAIM) == 0)
-			nfs_inode_set_delegation(state->inode,
-					data->owner->so_cred,
-					&data->o_res);
-		else
-			nfs_inode_reclaim_delegation(state->inode,
-					data->owner->so_cred,
-					&data->o_res);
-	}
-
+	if (data->o_res.delegation_type != 0)
+		nfs4_opendata_check_deleg(data, state);
 	update_open_stateid(state, &data->o_res.stateid, NULL,
 			data->o_arg.fmode);
 	iput(inode);
@@ -1171,6 +1162,14 @@ err:
 	return ERR_PTR(ret);
 }
 
+static struct nfs4_state *
+nfs4_opendata_to_nfs4_state(struct nfs4_opendata *data)
+{
+	if (data->o_arg.claim == NFS4_OPEN_CLAIM_PREVIOUS)
+		return _nfs4_opendata_reclaim_to_nfs4_state(data);
+	return _nfs4_opendata_to_nfs4_state(data);
+}
+
 static struct nfs_open_context *nfs4_state_find_open_context(struct nfs4_state *state)
 {
 	struct nfs_inode *nfsi = NFS_I(state->inode);
@@ -1372,13 +1371,6 @@ int nfs4_open_delegation_recall(struct nfs_open_context *ctx, struct nfs4_state
 				nfs_inode_find_state_and_recover(state->inode,
 						stateid);
 				nfs4_schedule_stateid_recovery(server, state);
-			case -EKEYEXPIRED:
-				/*
-				 * User RPCSEC_GSS context has expired.
-				 * We cannot recover this stateid now, so
-				 * skip it and allow recovery thread to
-				 * proceed.
-				 */
 			case -ENOMEM:
 				err = 0;
 				goto out;
@@ -1492,26 +1484,21 @@ static void nfs4_open_prepare(struct rpc_task *task, void *calldata)
 	data->o_arg.clientid = sp->so_server->nfs_client->cl_clientid;
 	if (data->o_arg.claim == NFS4_OPEN_CLAIM_PREVIOUS) {
 		task->tk_msg.rpc_proc = &nfs4_procedures[NFSPROC4_CLNT_OPEN_NOATTR];
+		data->o_arg.open_bitmap = &nfs4_open_noattr_bitmap[0];
 		nfs_copy_fh(&data->o_res.fh, data->o_arg.fh);
 	}
 	data->timestamp = jiffies;
 	if (nfs4_setup_sequence(data->o_arg.server,
 				&data->o_arg.seq_args,
-				&data->o_res.seq_res, task))
-		return;
-	rpc_call_start(task);
+				&data->o_res.seq_res,
+				task) != 0)
+		nfs_release_seqid(data->o_arg.seqid);
 	return;
 unlock_no_action:
 	rcu_read_unlock();
 out_no_action:
 	task->tk_action = NULL;
-
-}
-
-static void nfs4_recover_open_prepare(struct rpc_task *task, void *calldata)
-{
-	rpc_task_set_priority(task, RPC_PRIORITY_PRIVILEGED);
-	nfs4_open_prepare(task, calldata);
+	nfs4_sequence_done(task, &data->o_res.seq_res);
 }
 
 static void nfs4_open_done(struct rpc_task *task, void *calldata)
@@ -1524,7 +1511,8 @@ static void nfs4_open_done(struct rpc_task *task, void *calldata)
 		return;
 
 	if (task->tk_status == 0) {
-		switch (data->o_res.f_attr->mode & S_IFMT) {
+		if (data->o_res.f_attr->valid & NFS_ATTR_FATTR_TYPE) {
+			switch (data->o_res.f_attr->mode & S_IFMT) {
 			case S_IFREG:
 				break;
 			case S_IFLNK:
@@ -1535,6 +1523,7 @@ static void nfs4_open_done(struct rpc_task *task, void *calldata)
 				break;
 			default:
 				data->rpc_status = -ENOTDIR;
+			}
 		}
 		renew_lease(data->o_res.server, data->timestamp);
 		if (!(data->o_res.rflags & NFS4_OPEN_RESULT_CONFIRM))
@@ -1570,12 +1559,6 @@ static const struct rpc_call_ops nfs4_open_ops = {
 	.rpc_release = nfs4_open_release,
 };
 
-static const struct rpc_call_ops nfs4_recover_open_ops = {
-	.rpc_call_prepare = nfs4_recover_open_prepare,
-	.rpc_call_done = nfs4_open_done,
-	.rpc_release = nfs4_open_release,
-};
-
 static int nfs4_run_open_task(struct nfs4_opendata *data, int isrecover)
 {
 	struct inode *dir = data->dir->d_inode;
@@ -1605,7 +1588,7 @@ static int nfs4_run_open_task(struct nfs4_opendata *data, int isrecover)
 	data->rpc_status = 0;
 	data->cancelled = 0;
 	if (isrecover)
-		task_setup_data.callback_ops = &nfs4_recover_open_ops;
+		nfs4_set_sequence_privileged(&o_arg->seq_args);
 	task = rpc_run_task(&task_setup_data);
         if (IS_ERR(task))
                 return PTR_ERR(task);
@@ -1641,6 +1624,43 @@ static int _nfs4_recover_proc_open(struct nfs4_opendata *data)
 	return status;
 }
 
+static int nfs4_opendata_access(struct rpc_cred *cred,
+				struct nfs4_opendata *opendata,
+				struct nfs4_state *state, fmode_t fmode,
+				int openflags)
+{
+	struct nfs_access_entry cache;
+	u32 mask;
+
+	/* access call failed or for some reason the server doesn't
+	 * support any access modes -- defer access call until later */
+	if (opendata->o_res.access_supported == 0)
+		return 0;
+
+	mask = 0;
+	/* don't check MAY_WRITE - a newly created file may not have
+	 * write mode bits, but POSIX allows the creating process to write.
+	 * use openflags to check for exec, because fmode won't
+	 * always have FMODE_EXEC set when file open for exec. */
+	if (openflags & __FMODE_EXEC) {
+		/* ONLY check for exec rights */
+		mask = MAY_EXEC;
+	} else if (fmode & FMODE_READ)
+		mask = MAY_READ;
+
+	cache.cred = cred;
+	cache.jiffies = jiffies;
+	nfs_access_set_mask(&cache, opendata->o_res.access_result);
+	nfs_access_add_cache(state->inode, &cache);
+
+	if ((mask & ~cache.mask & (MAY_READ | MAY_EXEC)) == 0)
+		return 0;
+
+	/* even though OPEN succeeded, access is denied. Close the file */
+	nfs4_close_state(state, fmode);
+	return -EACCES;
+}
+
 /*
  * Note: On error, nfs4_proc_open will free the struct nfs4_opendata
  */
@@ -1678,24 +1698,6 @@ static int _nfs4_proc_open(struct nfs4_opendata *data)
 	return 0;
 }
 
-static int nfs4_client_recover_expired_lease(struct nfs_client *clp)
-{
-	unsigned int loop;
-	int ret;
-
-	for (loop = NFS4_MAX_LOOP_ON_RECOVER; loop != 0; loop--) {
-		ret = nfs4_wait_clnt_recover(clp);
-		if (ret != 0)
-			break;
-		if (!test_bit(NFS4CLNT_LEASE_EXPIRED, &clp->cl_state) &&
-		    !test_bit(NFS4CLNT_CHECK_LEASE,&clp->cl_state))
-			break;
-		nfs4_schedule_state_manager(clp);
-		ret = -EIO;
-	}
-	return ret;
-}
-
 static int nfs4_recover_expired_lease(struct nfs_server *server)
 {
 	return nfs4_client_recover_expired_lease(server->nfs_client);
@@ -1756,33 +1758,74 @@ static int nfs4_open_expired(struct nfs4_state_owner *sp, struct nfs4_state *sta
 }
 
 #if defined(CONFIG_NFS_V4_1)
-static int nfs41_check_expired_stateid(struct nfs4_state *state, nfs4_stateid *stateid, unsigned int flags)
+static void nfs41_clear_delegation_stateid(struct nfs4_state *state)
 {
-	int status = NFS_OK;
 	struct nfs_server *server = NFS_SERVER(state->inode);
+	nfs4_stateid *stateid = &state->stateid;
+	int status;
 
-	if (state->flags & flags) {
-		status = nfs41_test_stateid(server, stateid);
-		if (status != NFS_OK) {
+	/* If a state reset has been done, test_stateid is unneeded */
+	if (test_bit(NFS_DELEGATED_STATE, &state->flags) == 0)
+		return;
+
+	status = nfs41_test_stateid(server, stateid);
+	if (status != NFS_OK) {
+		/* Free the stateid unless the server explicitly
+		 * informs us the stateid is unrecognized. */
+		if (status != -NFS4ERR_BAD_STATEID)
 			nfs41_free_stateid(server, stateid);
-			state->flags &= ~flags;
-		}
+		nfs_remove_bad_delegation(state->inode);
+
+		write_seqlock(&state->seqlock);
+		nfs4_stateid_copy(&state->stateid, &state->open_stateid);
+		write_sequnlock(&state->seqlock);
+		clear_bit(NFS_DELEGATED_STATE, &state->flags);
+	}
+}
+
+/**
+ * nfs41_check_open_stateid - possibly free an open stateid
+ *
+ * @state: NFSv4 state for an inode
+ *
+ * Returns NFS_OK if recovery for this stateid is now finished.
+ * Otherwise a negative NFS4ERR value is returned.
+ */
+static int nfs41_check_open_stateid(struct nfs4_state *state)
+{
+	struct nfs_server *server = NFS_SERVER(state->inode);
+	nfs4_stateid *stateid = &state->open_stateid;
+	int status;
+
+	/* If a state reset has been done, test_stateid is unneeded */
+	if ((test_bit(NFS_O_RDONLY_STATE, &state->flags) == 0) &&
+	    (test_bit(NFS_O_WRONLY_STATE, &state->flags) == 0) &&
+	    (test_bit(NFS_O_RDWR_STATE, &state->flags) == 0))
+		return -NFS4ERR_BAD_STATEID;
+
+	status = nfs41_test_stateid(server, stateid);
+	if (status != NFS_OK) {
+		/* Free the stateid unless the server explicitly
+		 * informs us the stateid is unrecognized. */
+		if (status != -NFS4ERR_BAD_STATEID)
+			nfs41_free_stateid(server, stateid);
+
+		clear_bit(NFS_O_RDONLY_STATE, &state->flags);
+		clear_bit(NFS_O_WRONLY_STATE, &state->flags);
+		clear_bit(NFS_O_RDWR_STATE, &state->flags);
 	}
 	return status;
 }
 
 static int nfs41_open_expired(struct nfs4_state_owner *sp, struct nfs4_state *state)
 {
-	int deleg_status, open_status;
-	int deleg_flags = 1 << NFS_DELEGATED_STATE;
-	int open_flags = (1 << NFS_O_RDONLY_STATE) | (1 << NFS_O_WRONLY_STATE) | (1 << NFS_O_RDWR_STATE);
-
-	deleg_status = nfs41_check_expired_stateid(state, &state->stateid, deleg_flags);
-	open_status = nfs41_check_expired_stateid(state,  &state->open_stateid, open_flags);
+	int status;
 
-	if ((deleg_status == NFS_OK) && (open_status == NFS_OK))
-		return NFS_OK;
-	return nfs4_open_expired(sp, state);
+	nfs41_clear_delegation_stateid(state);
+	status = nfs41_check_open_stateid(state);
+	if (status != NFS_OK)
+		status = nfs4_open_expired(sp, state);
+	return status;
 }
 #endif
 
@@ -1857,6 +1900,10 @@ static int _nfs4_do_open(struct inode *dir,
 	if (server->caps & NFS_CAP_POSIX_LOCK)
 		set_bit(NFS_STATE_POSIX_LOCKS, &state->flags);
 
+	status = nfs4_opendata_access(cred, opendata, state, fmode, flags);
+	if (status != 0)
+		goto err_opendata_put;
+
 	if (opendata->o_arg.open_flags & O_EXCL) {
 		nfs4_exclusive_attrset(opendata, sattr);
 
@@ -1902,7 +1949,7 @@ static struct nfs4_state *nfs4_do_open(struct inode *dir,
 	struct nfs4_state *res;
 	int status;
 
-	fmode &= FMODE_READ|FMODE_WRITE;
+	fmode &= FMODE_READ|FMODE_WRITE|FMODE_EXEC;
 	do {
 		status = _nfs4_do_open(dir, dentry, fmode, flags, sattr, cred,
 				       &res, ctx_th);
@@ -1974,8 +2021,12 @@ static int _nfs4_do_setattr(struct inode *inode, struct rpc_cred *cred,
 	nfs_fattr_init(fattr);
 
 	if (state != NULL) {
+		struct nfs_lockowner lockowner = {
+			.l_owner = current->files,
+			.l_pid = current->tgid,
+		};
 		nfs4_select_rw_stateid(&arg.stateid, state, FMODE_WRITE,
-				current->files, current->tgid);
+				&lockowner);
 	} else if (nfs4_copy_delegation_stateid(&arg.stateid, inode,
 				FMODE_WRITE)) {
 		/* Use that stateid */
@@ -2037,7 +2088,7 @@ static void nfs4_free_closedata(void *data)
 	nfs4_put_open_state(calldata->state);
 	nfs_free_seqid(calldata->arg.seqid);
 	nfs4_put_state_owner(sp);
-	nfs_sb_deactive(sb);
+	nfs_sb_deactive_async(sb);
 	kfree(calldata);
 }
 
@@ -2094,6 +2145,7 @@ static void nfs4_close_prepare(struct rpc_task *task, void *data)
 {
 	struct nfs4_closedata *calldata = data;
 	struct nfs4_state *state = calldata->state;
+	struct inode *inode = calldata->inode;
 	int call_close = 0;
 
 	dprintk("%s: begin!\n", __func__);
@@ -2121,27 +2173,24 @@ static void nfs4_close_prepare(struct rpc_task *task, void *data)
 	if (!call_close) {
 		/* Note: exit _without_ calling nfs4_close_done */
 		task->tk_action = NULL;
+		nfs4_sequence_done(task, &calldata->res.seq_res);
 		goto out;
 	}
 
 	if (calldata->arg.fmode == 0) {
 		task->tk_msg.rpc_proc = &nfs4_procedures[NFSPROC4_CLNT_CLOSE];
 		if (calldata->roc &&
-		    pnfs_roc_drain(calldata->inode, &calldata->roc_barrier)) {
-			rpc_sleep_on(&NFS_SERVER(calldata->inode)->roc_rpcwaitq,
-				     task, NULL);
+		    pnfs_roc_drain(inode, &calldata->roc_barrier, task))
 			goto out;
-		}
 	}
 
 	nfs_fattr_init(calldata->res.fattr);
 	calldata->timestamp = jiffies;
-	if (nfs4_setup_sequence(NFS_SERVER(calldata->inode),
+	if (nfs4_setup_sequence(NFS_SERVER(inode),
 				&calldata->arg.seq_args,
 				&calldata->res.seq_res,
-				task))
-		goto out;
-	rpc_call_start(task);
+				task) != 0)
+		nfs_release_seqid(calldata->arg.seqid);
 out:
 	dprintk("%s: done!\n", __func__);
 }
@@ -2163,7 +2212,7 @@ static const struct rpc_call_ops nfs4_close_ops = {
  *
  * NOTE: Caller must be holding the sp->so_owner semaphore!
  */
-int nfs4_do_close(struct nfs4_state *state, gfp_t gfp_mask, int wait, bool roc)
+int nfs4_do_close(struct nfs4_state *state, gfp_t gfp_mask, int wait)
 {
 	struct nfs_server *server = NFS_SERVER(state->inode);
 	struct nfs4_closedata *calldata;
@@ -2199,7 +2248,7 @@ int nfs4_do_close(struct nfs4_state *state, gfp_t gfp_mask, int wait, bool roc)
 	calldata->res.fattr = &calldata->fattr;
 	calldata->res.seqid = calldata->arg.seqid;
 	calldata->res.server = server;
-	calldata->roc = roc;
+	calldata->roc = pnfs_roc(state->inode);
 	nfs_sb_active(calldata->inode->i_sb);
 
 	msg.rpc_argp = &calldata->arg;
@@ -2216,8 +2265,6 @@ int nfs4_do_close(struct nfs4_state *state, gfp_t gfp_mask, int wait, bool roc)
 out_free_calldata:
 	kfree(calldata);
 out:
-	if (roc)
-		pnfs_roc_release(state->inode);
 	nfs4_put_open_state(state);
 	nfs4_put_state_owner(sp);
 	return status;
@@ -2360,7 +2407,7 @@ static int nfs4_lookup_root_sec(struct nfs_server *server, struct nfs_fh *fhandl
 	int ret;
 
 	auth = rpcauth_create(flavor, server->client);
-	if (!auth) {
+	if (IS_ERR(auth)) {
 		ret = -EIO;
 		goto out;
 	}
@@ -2375,11 +2422,16 @@ static int nfs4_find_root_sec(struct nfs_server *server, struct nfs_fh *fhandle,
 	int i, len, status = 0;
 	rpc_authflavor_t flav_array[NFS_MAX_SECFLAVORS];
 
-	len = gss_mech_list_pseudoflavors(&flav_array[0]);
-	flav_array[len] = RPC_AUTH_NULL;
-	len += 1;
+	len = rpcauth_list_flavors(flav_array, ARRAY_SIZE(flav_array));
+	if (len < 0)
+		return len;
 
 	for (i = 0; i < len; i++) {
+		/* AUTH_UNIX is the default flavor if none was specified,
+		 * thus has already been tried. */
+		if (flav_array[i] == RPC_AUTH_UNIX)
+			continue;
+
 		status = nfs4_lookup_root_sec(server, fhandle, info, flav_array[i]);
 		if (status == -NFS4ERR_WRONGSEC || status == -EACCES)
 			continue;
@@ -2724,13 +2776,7 @@ static int _nfs4_proc_access(struct inode *inode, struct nfs_access_entry *entry
 
 	status = nfs4_call_sync(server->client, server, &msg, &args.seq_args, &res.seq_res, 0);
 	if (!status) {
-		entry->mask = 0;
-		if (res.access & NFS4_ACCESS_READ)
-			entry->mask |= MAY_READ;
-		if (res.access & (NFS4_ACCESS_MODIFY | NFS4_ACCESS_EXTEND | NFS4_ACCESS_DELETE))
-			entry->mask |= MAY_WRITE;
-		if (res.access & (NFS4_ACCESS_LOOKUP|NFS4_ACCESS_EXECUTE))
-			entry->mask |= MAY_EXEC;
+		nfs_access_set_mask(entry, res.access);
 		nfs_refresh_inode(inode, res.fattr);
 	}
 	nfs_free_fattr(res.fattr);
@@ -2766,9 +2812,7 @@ static int nfs4_proc_access(struct inode *inode, struct nfs_access_entry *entry)
  *
  * In the case of WRITE, we also want to put the GETATTR after
  * the operation -- in this case because we want to make sure
- * we get the post-operation mtime and size.  This means that
- * we can't use xdr_encode_pages() as written: we need a variant
- * of it which would leave room in the 'tail' iovec.
+ * we get the post-operation mtime and size.
  *
  * Both of these changes to the XDR layer would in fact be quite
  * minor, but I decided to leave them for a subsequent patch.
@@ -2806,37 +2850,24 @@ static int nfs4_proc_readlink(struct inode *inode, struct page *page,
 }
 
 /*
- * Got race?
- * We will need to arrange for the VFS layer to provide an atomic open.
- * Until then, this create/open method is prone to inefficiency and race
- * conditions due to the lookup, create, and open VFS calls from sys_open()
- * placed on the wire.
- *
- * Given the above sorry state of affairs, I'm simply sending an OPEN.
- * The file will be opened again in the subsequent VFS open call
- * (nfs4_proc_file_open).
- *
- * The open for read will just hang around to be used by any process that
- * opens the file O_RDONLY. This will all be resolved with the VFS changes.
+ * This is just for mknod.  open(O_CREAT) will always do ->open_context().
  */
-
 static int
 nfs4_proc_create(struct inode *dir, struct dentry *dentry, struct iattr *sattr,
-                 int flags, struct nfs_open_context *ctx)
+		 int flags)
 {
-	struct dentry *de = dentry;
+	struct nfs_open_context *ctx;
 	struct nfs4_state *state;
-	struct rpc_cred *cred = NULL;
-	fmode_t fmode = 0;
 	int status = 0;
 
-	if (ctx != NULL) {
-		cred = ctx->cred;
-		de = ctx->dentry;
-		fmode = ctx->mode;
-	}
+	ctx = alloc_nfs_open_context(dentry, FMODE_READ);
+	if (IS_ERR(ctx))
+		return PTR_ERR(ctx);
+
 	sattr->ia_mode &= ~current_umask();
-	state = nfs4_do_open(dir, de, fmode, flags, sattr, cred, NULL);
+	state = nfs4_do_open(dir, dentry, ctx->mode,
+			flags, sattr, ctx->cred,
+			&ctx->mdsthreshold);
 	d_drop(dentry);
 	if (IS_ERR(state)) {
 		status = PTR_ERR(state);
@@ -2844,11 +2875,9 @@ nfs4_proc_create(struct inode *dir, struct dentry *dentry, struct iattr *sattr,
 	}
 	d_add(dentry, igrab(state->inode));
 	nfs_set_verifier(dentry, nfs_save_change_attribute(dir));
-	if (ctx != NULL)
-		ctx->state = state;
-	else
-		nfs4_close_sync(state, fmode);
+	ctx->state = state;
 out:
+	put_nfs_open_context(ctx);
 	return status;
 }
 
@@ -2900,12 +2929,10 @@ static void nfs4_proc_unlink_setup(struct rpc_message *msg, struct inode *dir)
 
 static void nfs4_proc_unlink_rpc_prepare(struct rpc_task *task, struct nfs_unlinkdata *data)
 {
-	if (nfs4_setup_sequence(NFS_SERVER(data->dir),
-				&data->args.seq_args,
-				&data->res.seq_res,
-				task))
-		return;
-	rpc_call_start(task);
+	nfs4_setup_sequence(NFS_SERVER(data->dir),
+			&data->args.seq_args,
+			&data->res.seq_res,
+			task);
 }
 
 static int nfs4_proc_unlink_done(struct rpc_task *task, struct inode *dir)
@@ -2933,12 +2960,10 @@ static void nfs4_proc_rename_setup(struct rpc_message *msg, struct inode *dir)
 
 static void nfs4_proc_rename_rpc_prepare(struct rpc_task *task, struct nfs_renamedata *data)
 {
-	if (nfs4_setup_sequence(NFS_SERVER(data->old_dir),
-				&data->args.seq_args,
-				&data->res.seq_res,
-				task))
-		return;
-	rpc_call_start(task);
+	nfs4_setup_sequence(NFS_SERVER(data->old_dir),
+			&data->args.seq_args,
+			&data->res.seq_res,
+			task);
 }
 
 static int nfs4_proc_rename_done(struct rpc_task *task, struct inode *old_dir,
@@ -3189,11 +3214,11 @@ static int _nfs4_proc_readdir(struct dentry *dentry, struct rpc_cred *cred,
 			dentry->d_parent->d_name.name,
 			dentry->d_name.name,
 			(unsigned long long)cookie);
-	nfs4_setup_readdir(cookie, NFS_COOKIEVERF(dir), dentry, &args);
+	nfs4_setup_readdir(cookie, NFS_I(dir)->cookieverf, dentry, &args);
 	res.pgbase = args.pgbase;
 	status = nfs4_call_sync(NFS_SERVER(dir)->client, NFS_SERVER(dir), &msg, &args.seq_args, &res.seq_res, 0);
 	if (status >= 0) {
-		memcpy(NFS_COOKIEVERF(dir), res.verifier.data, NFS4_VERIFIER_SIZE);
+		memcpy(NFS_I(dir)->cookieverf, res.verifier.data, NFS4_VERIFIER_SIZE);
 		status += args.pgbase;
 	}
 
@@ -3224,9 +3249,6 @@ static int _nfs4_proc_mknod(struct inode *dir, struct dentry *dentry,
 	int mode = sattr->ia_mode;
 	int status = -ENOMEM;
 
-	BUG_ON(!(sattr->ia_valid & ATTR_MODE));
-	BUG_ON(!S_ISFIFO(mode) && !S_ISBLK(mode) && !S_ISCHR(mode) && !S_ISSOCK(mode));
-
 	data = nfs4_alloc_createdata(dir, &dentry->d_name, sattr, NF4SOCK);
 	if (data == NULL)
 		goto out;
@@ -3242,10 +3264,13 @@ static int _nfs4_proc_mknod(struct inode *dir, struct dentry *dentry,
 		data->arg.ftype = NF4CHR;
 		data->arg.u.device.specdata1 = MAJOR(rdev);
 		data->arg.u.device.specdata2 = MINOR(rdev);
+	} else if (!S_ISSOCK(mode)) {
+		status = -EINVAL;
+		goto out_free;
 	}
 	
 	status = nfs4_do_create(dir, dentry, data);
-
+out_free:
 	nfs4_free_createdata(data);
 out:
 	return status;
@@ -3332,8 +3357,17 @@ static int nfs4_do_fsinfo(struct nfs_server *server, struct nfs_fh *fhandle, str
 
 static int nfs4_proc_fsinfo(struct nfs_server *server, struct nfs_fh *fhandle, struct nfs_fsinfo *fsinfo)
 {
+	int error;
+
 	nfs_fattr_init(fsinfo->fattr);
-	return nfs4_do_fsinfo(server, fhandle, fsinfo);
+	error = nfs4_do_fsinfo(server, fhandle, fsinfo);
+	if (error == 0) {
+		/* block layout checks this! */
+		server->pnfs_blksize = fsinfo->blksize;
+		set_pnfs_layoutdriver(server, fhandle, fsinfo->layouttype);
+	}
+
+	return error;
 }
 
 static int _nfs4_proc_pathconf(struct nfs_server *server, struct nfs_fh *fhandle,
@@ -3418,12 +3452,10 @@ static void nfs4_proc_read_setup(struct nfs_read_data *data, struct rpc_message
 
 static void nfs4_proc_read_rpc_prepare(struct rpc_task *task, struct nfs_read_data *data)
 {
-	if (nfs4_setup_sequence(NFS_SERVER(data->header->inode),
-				&data->args.seq_args,
-				&data->res.seq_res,
-				task))
-		return;
-	rpc_call_start(task);
+	nfs4_setup_sequence(NFS_SERVER(data->header->inode),
+			&data->args.seq_args,
+			&data->res.seq_res,
+			task);
 }
 
 static int nfs4_write_done_cb(struct rpc_task *task, struct nfs_write_data *data)
@@ -3460,7 +3492,7 @@ bool nfs4_write_need_cache_consistency_data(const struct nfs_write_data *data)
 	/* Otherwise, request attributes if and only if we don't hold
 	 * a delegation
 	 */
-	return nfs_have_delegation(hdr->inode, FMODE_READ) == 0;
+	return nfs4_have_delegation(hdr->inode, FMODE_READ) == 0;
 }
 
 static void nfs4_proc_write_setup(struct nfs_write_data *data, struct rpc_message *msg)
@@ -3484,22 +3516,18 @@ static void nfs4_proc_write_setup(struct nfs_write_data *data, struct rpc_messag
 
 static void nfs4_proc_write_rpc_prepare(struct rpc_task *task, struct nfs_write_data *data)
 {
-	if (nfs4_setup_sequence(NFS_SERVER(data->header->inode),
-				&data->args.seq_args,
-				&data->res.seq_res,
-				task))
-		return;
-	rpc_call_start(task);
+	nfs4_setup_sequence(NFS_SERVER(data->header->inode),
+			&data->args.seq_args,
+			&data->res.seq_res,
+			task);
 }
 
 static void nfs4_proc_commit_rpc_prepare(struct rpc_task *task, struct nfs_commit_data *data)
 {
-	if (nfs4_setup_sequence(NFS_SERVER(data->inode),
-				&data->args.seq_args,
-				&data->res.seq_res,
-				task))
-		return;
-	rpc_call_start(task);
+	nfs4_setup_sequence(NFS_SERVER(data->inode),
+			&data->args.seq_args,
+			&data->res.seq_res,
+			task);
 }
 
 static int nfs4_commit_done_cb(struct rpc_task *task, struct nfs_commit_data *data)
@@ -3621,11 +3649,11 @@ static inline int nfs4_server_supports_acls(struct nfs_server *server)
 		&& (server->acl_bitmask & ACL4_SUPPORT_DENY_ACL);
 }
 
-/* Assuming that XATTR_SIZE_MAX is a multiple of PAGE_CACHE_SIZE, and that
- * it's OK to put sizeof(void) * (XATTR_SIZE_MAX/PAGE_CACHE_SIZE) bytes on
+/* Assuming that XATTR_SIZE_MAX is a multiple of PAGE_SIZE, and that
+ * it's OK to put sizeof(void) * (XATTR_SIZE_MAX/PAGE_SIZE) bytes on
  * the stack.
  */
-#define NFS4ACL_MAXPAGES (XATTR_SIZE_MAX >> PAGE_CACHE_SHIFT)
+#define NFS4ACL_MAXPAGES DIV_ROUND_UP(XATTR_SIZE_MAX, PAGE_SIZE)
 
 static int buf_to_pages_noslab(const void *buf, size_t buflen,
 		struct page **pages, unsigned int *pgbase)
@@ -3636,7 +3664,7 @@ static int buf_to_pages_noslab(const void *buf, size_t buflen,
 	spages = pages;
 
 	do {
-		len = min_t(size_t, PAGE_CACHE_SIZE, buflen);
+		len = min_t(size_t, PAGE_SIZE, buflen);
 		newpage = alloc_page(GFP_KERNEL);
 
 		if (newpage == NULL)
@@ -3705,9 +3733,10 @@ out:
 static void nfs4_write_cached_acl(struct inode *inode, struct page **pages, size_t pgbase, size_t acl_len)
 {
 	struct nfs4_cached_acl *acl;
+	size_t buflen = sizeof(*acl) + acl_len;
 
-	if (pages && acl_len <= PAGE_SIZE) {
-		acl = kmalloc(sizeof(*acl) + acl_len, GFP_KERNEL);
+	if (buflen <= PAGE_SIZE) {
+		acl = kmalloc(buflen, GFP_KERNEL);
 		if (acl == NULL)
 			goto out;
 		acl->cached = 1;
@@ -3749,16 +3778,15 @@ static ssize_t __nfs4_get_acl_uncached(struct inode *inode, void *buf, size_t bu
 		.rpc_argp = &args,
 		.rpc_resp = &res,
 	};
-	int ret = -ENOMEM, npages, i, acl_len = 0;
+	unsigned int npages = DIV_ROUND_UP(buflen, PAGE_SIZE);
+	int ret = -ENOMEM, i;
 
-	npages = (buflen + PAGE_SIZE - 1) >> PAGE_SHIFT;
 	/* As long as we're doing a round trip to the server anyway,
 	 * let's be prepared for a page of acl data. */
 	if (npages == 0)
 		npages = 1;
-
-	/* Add an extra page to handle the bitmap returned */
-	npages++;
+	if (npages > ARRAY_SIZE(pages))
+		return -ERANGE;
 
 	for (i = 0; i < npages; i++) {
 		pages[i] = alloc_page(GFP_KERNEL);
@@ -3774,11 +3802,6 @@ static ssize_t __nfs4_get_acl_uncached(struct inode *inode, void *buf, size_t bu
 	args.acl_len = npages * PAGE_SIZE;
 	args.acl_pgbase = 0;
 
-	/* Let decode_getfacl know not to fail if the ACL data is larger than
-	 * the page we send as a guess */
-	if (buf == NULL)
-		res.acl_flags |= NFS4_ACL_LEN_REQUEST;
-
 	dprintk("%s  buf %p buflen %zu npages %d args.acl_len %zu\n",
 		__func__, buf, buflen, npages, args.acl_len);
 	ret = nfs4_call_sync(NFS_SERVER(inode)->client, NFS_SERVER(inode),
@@ -3786,20 +3809,24 @@ static ssize_t __nfs4_get_acl_uncached(struct inode *inode, void *buf, size_t bu
 	if (ret)
 		goto out_free;
 
-	acl_len = res.acl_len - res.acl_data_offset;
-	if (acl_len > args.acl_len)
-		nfs4_write_cached_acl(inode, NULL, 0, acl_len);
-	else
-		nfs4_write_cached_acl(inode, pages, res.acl_data_offset,
-				      acl_len);
-	if (buf) {
+	/* Handle the case where the passed-in buffer is too short */
+	if (res.acl_flags & NFS4_ACL_TRUNC) {
+		/* Did the user only issue a request for the acl length? */
+		if (buf == NULL)
+			goto out_ok;
 		ret = -ERANGE;
-		if (acl_len > buflen)
+		goto out_free;
+	}
+	nfs4_write_cached_acl(inode, pages, res.acl_data_offset, res.acl_len);
+	if (buf) {
+		if (res.acl_len > buflen) {
+			ret = -ERANGE;
 			goto out_free;
-		_copy_from_pages(buf, pages, res.acl_data_offset,
-				acl_len);
+		}
+		_copy_from_pages(buf, pages, res.acl_data_offset, res.acl_len);
 	}
-	ret = acl_len;
+out_ok:
+	ret = res.acl_len;
 out_free:
 	for (i = 0; i < npages; i++)
 		if (pages[i])
@@ -3857,14 +3884,17 @@ static int __nfs4_proc_set_acl(struct inode *inode, const void *buf, size_t bufl
 		.rpc_argp	= &arg,
 		.rpc_resp	= &res,
 	};
+	unsigned int npages = DIV_ROUND_UP(buflen, PAGE_SIZE);
 	int ret, i;
 
 	if (!nfs4_server_supports_acls(server))
 		return -EOPNOTSUPP;
+	if (npages > ARRAY_SIZE(pages))
+		return -ERANGE;
 	i = buf_to_pages_noslab(buf, buflen, arg.acl_pages, &arg.acl_pgbase);
 	if (i < 0)
 		return i;
-	nfs_inode_return_delegation(inode);
+	nfs4_inode_return_delegation(inode);
 	ret = nfs4_call_sync(server->client, server, &msg, &arg.seq_args, &res.seq_res, 1);
 
 	/*
@@ -3941,7 +3971,6 @@ nfs4_async_handle_error(struct rpc_task *task, const struct nfs_server *server,
 		case -NFS4ERR_DELAY:
 			nfs_inc_server_stats(server, NFSIOS_DELAY);
 		case -NFS4ERR_GRACE:
-		case -EKEYEXPIRED:
 			rpc_delay(task, NFS4_POLL_RETRY_MAX);
 			task->tk_status = 0;
 			return -EAGAIN;
@@ -3978,6 +4007,46 @@ static void nfs4_init_boot_verifier(const struct nfs_client *clp,
 	memcpy(bootverf->data, verf, sizeof(bootverf->data));
 }
 
+static unsigned int
+nfs4_init_nonuniform_client_string(const struct nfs_client *clp,
+				   char *buf, size_t len)
+{
+	unsigned int result;
+
+	rcu_read_lock();
+	result = scnprintf(buf, len, "Linux NFSv4.0 %s/%s %s",
+				clp->cl_ipaddr,
+				rpc_peeraddr2str(clp->cl_rpcclient,
+							RPC_DISPLAY_ADDR),
+				rpc_peeraddr2str(clp->cl_rpcclient,
+							RPC_DISPLAY_PROTO));
+	rcu_read_unlock();
+	return result;
+}
+
+static unsigned int
+nfs4_init_uniform_client_string(const struct nfs_client *clp,
+				char *buf, size_t len)
+{
+	char *nodename = clp->cl_rpcclient->cl_nodename;
+
+	if (nfs4_client_id_uniquifier[0] != '\0')
+		nodename = nfs4_client_id_uniquifier;
+	return scnprintf(buf, len, "Linux NFSv%u.%u %s",
+				clp->rpc_ops->version, clp->cl_minorversion,
+				nodename);
+}
+
+/**
+ * nfs4_proc_setclientid - Negotiate client ID
+ * @clp: state data structure
+ * @program: RPC program for NFSv4 callback service
+ * @port: IP port number for NFS4 callback service
+ * @cred: RPC credential to use for this call
+ * @res: where to place the result
+ *
+ * Returns zero, a negative errno, or a negative NFS4ERR status code.
+ */
 int nfs4_proc_setclientid(struct nfs_client *clp, u32 program,
 		unsigned short port, struct rpc_cred *cred,
 		struct nfs4_setclientid_res *res)
@@ -3994,44 +4063,47 @@ int nfs4_proc_setclientid(struct nfs_client *clp, u32 program,
 		.rpc_resp = res,
 		.rpc_cred = cred,
 	};
-	int loop = 0;
 	int status;
 
+	/* nfs_client_id4 */
 	nfs4_init_boot_verifier(clp, &sc_verifier);
-
-	for(;;) {
-		rcu_read_lock();
-		setclientid.sc_name_len = scnprintf(setclientid.sc_name,
-				sizeof(setclientid.sc_name), "%s/%s %s %s %u",
-				clp->cl_ipaddr,
-				rpc_peeraddr2str(clp->cl_rpcclient,
-							RPC_DISPLAY_ADDR),
-				rpc_peeraddr2str(clp->cl_rpcclient,
-							RPC_DISPLAY_PROTO),
-				clp->cl_rpcclient->cl_auth->au_ops->au_name,
-				clp->cl_id_uniquifier);
-		setclientid.sc_netid_len = scnprintf(setclientid.sc_netid,
+	if (test_bit(NFS_CS_MIGRATION, &clp->cl_flags))
+		setclientid.sc_name_len =
+				nfs4_init_uniform_client_string(clp,
+						setclientid.sc_name,
+						sizeof(setclientid.sc_name));
+	else
+		setclientid.sc_name_len =
+				nfs4_init_nonuniform_client_string(clp,
+						setclientid.sc_name,
+						sizeof(setclientid.sc_name));
+	/* cb_client4 */
+	rcu_read_lock();
+	setclientid.sc_netid_len = scnprintf(setclientid.sc_netid,
 				sizeof(setclientid.sc_netid),
 				rpc_peeraddr2str(clp->cl_rpcclient,
 							RPC_DISPLAY_NETID));
-		setclientid.sc_uaddr_len = scnprintf(setclientid.sc_uaddr,
+	rcu_read_unlock();
+	setclientid.sc_uaddr_len = scnprintf(setclientid.sc_uaddr,
 				sizeof(setclientid.sc_uaddr), "%s.%u.%u",
 				clp->cl_ipaddr, port >> 8, port & 255);
-		rcu_read_unlock();
 
-		status = rpc_call_sync(clp->cl_rpcclient, &msg, RPC_TASK_TIMEOUT);
-		if (status != -NFS4ERR_CLID_INUSE)
-			break;
-		if (loop != 0) {
-			++clp->cl_id_uniquifier;
-			break;
-		}
-		++loop;
-		ssleep(clp->cl_lease_time / HZ + 1);
-	}
+	dprintk("NFS call  setclientid auth=%s, '%.*s'\n",
+		clp->cl_rpcclient->cl_auth->au_ops->au_name,
+		setclientid.sc_name_len, setclientid.sc_name);
+	status = rpc_call_sync(clp->cl_rpcclient, &msg, RPC_TASK_TIMEOUT);
+	dprintk("NFS reply setclientid: %d\n", status);
 	return status;
 }
 
+/**
+ * nfs4_proc_setclientid_confirm - Confirm client ID
+ * @clp: state data structure
+ * @res: result of a previous SETCLIENTID
+ * @cred: RPC credential to use for this call
+ *
+ * Returns zero, a negative errno, or a negative NFS4ERR status code.
+ */
 int nfs4_proc_setclientid_confirm(struct nfs_client *clp,
 		struct nfs4_setclientid_res *arg,
 		struct rpc_cred *cred)
@@ -4046,6 +4118,9 @@ int nfs4_proc_setclientid_confirm(struct nfs_client *clp,
 	unsigned long now;
 	int status;
 
+	dprintk("NFS call  setclientid_confirm auth=%s, (client ID %llx)\n",
+		clp->cl_rpcclient->cl_auth->au_ops->au_name,
+		clp->cl_clientid);
 	now = jiffies;
 	status = rpc_call_sync(clp->cl_rpcclient, &msg, RPC_TASK_TIMEOUT);
 	if (status == 0) {
@@ -4054,6 +4129,7 @@ int nfs4_proc_setclientid_confirm(struct nfs_client *clp,
 		clp->cl_last_renewal = now;
 		spin_unlock(&clp->cl_lock);
 	}
+	dprintk("NFS reply setclientid_confirm: %d\n", status);
 	return status;
 }
 
@@ -4102,11 +4178,10 @@ static void nfs4_delegreturn_prepare(struct rpc_task *task, void *data)
 
 	d_data = (struct nfs4_delegreturndata *)data;
 
-	if (nfs4_setup_sequence(d_data->res.server,
-				&d_data->args.seq_args,
-				&d_data->res.seq_res, task))
-		return;
-	rpc_call_start(task);
+	nfs4_setup_sequence(d_data->res.server,
+			&d_data->args.seq_args,
+			&d_data->res.seq_res,
+			task);
 }
 #endif /* CONFIG_NFS_V4_1 */
 
@@ -4340,6 +4415,7 @@ static void nfs4_locku_done(struct rpc_task *task, void *data)
 			if (nfs4_async_handle_error(task, calldata->server, NULL) == -EAGAIN)
 				rpc_restart_call_prepare(task);
 	}
+	nfs_release_seqid(calldata->arg.seqid);
 }
 
 static void nfs4_locku_prepare(struct rpc_task *task, void *data)
@@ -4348,17 +4424,18 @@ static void nfs4_locku_prepare(struct rpc_task *task, void *data)
 
 	if (nfs_wait_on_sequence(calldata->arg.seqid, task) != 0)
 		return;
-	if ((calldata->lsp->ls_flags & NFS_LOCK_INITIALIZED) == 0) {
+	if (test_bit(NFS_LOCK_INITIALIZED, &calldata->lsp->ls_flags) == 0) {
 		/* Note: exit _without_ running nfs4_locku_done */
 		task->tk_action = NULL;
+		nfs4_sequence_done(task, &calldata->res.seq_res);
 		return;
 	}
 	calldata->timestamp = jiffies;
 	if (nfs4_setup_sequence(calldata->server,
 				&calldata->arg.seq_args,
-				&calldata->res.seq_res, task))
-		return;
-	rpc_call_start(task);
+				&calldata->res.seq_res,
+				task) != 0)
+		nfs_release_seqid(calldata->arg.seqid);
 }
 
 static const struct rpc_call_ops nfs4_locku_ops = {
@@ -4502,8 +4579,9 @@ static void nfs4_lock_prepare(struct rpc_task *task, void *calldata)
 		return;
 	/* Do we need to do an open_to_lock_owner? */
 	if (!(data->arg.lock_seqid->sequence->flags & NFS_SEQID_CONFIRMED)) {
-		if (nfs_wait_on_sequence(data->arg.open_seqid, task) != 0)
-			return;
+		if (nfs_wait_on_sequence(data->arg.open_seqid, task) != 0) {
+			goto out_release_lock_seqid;
+		}
 		data->arg.open_stateid = &state->stateid;
 		data->arg.new_lock_owner = 1;
 		data->res.open_seqid = data->arg.open_seqid;
@@ -4512,18 +4590,15 @@ static void nfs4_lock_prepare(struct rpc_task *task, void *calldata)
 	data->timestamp = jiffies;
 	if (nfs4_setup_sequence(data->server,
 				&data->arg.seq_args,
-				&data->res.seq_res, task))
+				&data->res.seq_res,
+				task) == 0)
 		return;
-	rpc_call_start(task);
+	nfs_release_seqid(data->arg.open_seqid);
+out_release_lock_seqid:
+	nfs_release_seqid(data->arg.lock_seqid);
 	dprintk("%s: done!, ret = %d\n", __func__, data->rpc_status);
 }
 
-static void nfs4_recover_lock_prepare(struct rpc_task *task, void *calldata)
-{
-	rpc_task_set_priority(task, RPC_PRIORITY_PRIVILEGED);
-	nfs4_lock_prepare(task, calldata);
-}
-
 static void nfs4_lock_done(struct rpc_task *task, void *calldata)
 {
 	struct nfs4_lockdata *data = calldata;
@@ -4542,7 +4617,7 @@ static void nfs4_lock_done(struct rpc_task *task, void *calldata)
 	}
 	if (data->rpc_status == 0) {
 		nfs4_stateid_copy(&data->lsp->ls_stateid, &data->res.stateid);
-		data->lsp->ls_flags |= NFS_LOCK_INITIALIZED;
+		set_bit(NFS_LOCK_INITIALIZED, &data->lsp->ls_flags);
 		renew_lease(NFS_SERVER(data->ctx->dentry->d_inode), data->timestamp);
 	}
 out:
@@ -4576,12 +4651,6 @@ static const struct rpc_call_ops nfs4_lock_ops = {
 	.rpc_release = nfs4_lock_release,
 };
 
-static const struct rpc_call_ops nfs4_recover_lock_ops = {
-	.rpc_call_prepare = nfs4_recover_lock_prepare,
-	.rpc_call_done = nfs4_lock_done,
-	.rpc_release = nfs4_lock_release,
-};
-
 static void nfs4_handle_setlk_error(struct nfs_server *server, struct nfs4_lock_state *lsp, int new_lock_owner, int error)
 {
 	switch (error) {
@@ -4589,7 +4658,7 @@ static void nfs4_handle_setlk_error(struct nfs_server *server, struct nfs4_lock_
 	case -NFS4ERR_BAD_STATEID:
 		lsp->ls_seqid.flags &= ~NFS_SEQID_CONFIRMED;
 		if (new_lock_owner != 0 ||
-		   (lsp->ls_flags & NFS_LOCK_INITIALIZED) != 0)
+		   test_bit(NFS_LOCK_INITIALIZED, &lsp->ls_flags) != 0)
 			nfs4_schedule_stateid_recovery(server, lsp->ls_state);
 		break;
 	case -NFS4ERR_STALE_STATEID:
@@ -4624,15 +4693,15 @@ static int _nfs4_do_setlk(struct nfs4_state *state, int cmd, struct file_lock *f
 		return -ENOMEM;
 	if (IS_SETLKW(cmd))
 		data->arg.block = 1;
-	if (recovery_type > NFS_LOCK_NEW) {
-		if (recovery_type == NFS_LOCK_RECLAIM)
-			data->arg.reclaim = NFS_LOCK_RECLAIM;
-		task_setup_data.callback_ops = &nfs4_recover_lock_ops;
-	}
 	nfs41_init_sequence(&data->arg.seq_args, &data->res.seq_res, 1);
 	msg.rpc_argp = &data->arg;
 	msg.rpc_resp = &data->res;
 	task_setup_data.callback_data = data;
+	if (recovery_type > NFS_LOCK_NEW) {
+		if (recovery_type == NFS_LOCK_RECLAIM)
+			data->arg.reclaim = NFS_LOCK_RECLAIM;
+		nfs4_set_sequence_privileged(&data->arg.seq_args);
+	}
 	task = rpc_run_task(&task_setup_data);
 	if (IS_ERR(task))
 		return PTR_ERR(task);
@@ -4698,18 +4767,30 @@ out:
 }
 
 #if defined(CONFIG_NFS_V4_1)
+/**
+ * nfs41_check_expired_locks - possibly free a lock stateid
+ *
+ * @state: NFSv4 state for an inode
+ *
+ * Returns NFS_OK if recovery for this stateid is now finished.
+ * Otherwise a negative NFS4ERR value is returned.
+ */
 static int nfs41_check_expired_locks(struct nfs4_state *state)
 {
-	int status, ret = NFS_OK;
+	int status, ret = -NFS4ERR_BAD_STATEID;
 	struct nfs4_lock_state *lsp;
 	struct nfs_server *server = NFS_SERVER(state->inode);
 
 	list_for_each_entry(lsp, &state->lock_states, ls_locks) {
-		if (lsp->ls_flags & NFS_LOCK_INITIALIZED) {
+		if (test_bit(NFS_LOCK_INITIALIZED, &lsp->ls_flags)) {
 			status = nfs41_test_stateid(server, &lsp->ls_stateid);
 			if (status != NFS_OK) {
-				nfs41_free_stateid(server, &lsp->ls_stateid);
-				lsp->ls_flags &= ~NFS_LOCK_INITIALIZED;
+				/* Free the stateid unless the server
+				 * informs us the stateid is unrecognized. */
+				if (status != -NFS4ERR_BAD_STATEID)
+					nfs41_free_stateid(server,
+							&lsp->ls_stateid);
+				clear_bit(NFS_LOCK_INITIALIZED, &lsp->ls_flags);
 				ret = status;
 			}
 		}
@@ -4724,9 +4805,9 @@ static int nfs41_lock_expired(struct nfs4_state *state, struct file_lock *reques
 
 	if (test_bit(LK_STATE_IN_USE, &state->flags))
 		status = nfs41_check_expired_locks(state);
-	if (status == NFS_OK)
-		return status;
-	return nfs4_lock_expired(state, request);
+	if (status != NFS_OK)
+		status = nfs4_lock_expired(state, request);
+	return status;
 }
 #endif
 
@@ -4824,7 +4905,7 @@ nfs4_proc_lock(struct file *filp, int cmd, struct file_lock *request)
 	 * Don't rely on the VFS having checked the file open mode,
 	 * since it won't do this for flock() locks.
 	 */
-	switch (request->fl_type & (F_RDLCK|F_WRLCK|F_UNLCK)) {
+	switch (request->fl_type) {
 	case F_RDLCK:
 		if (!(filp->f_mode & FMODE_READ))
 			return -EBADF;
@@ -4889,15 +4970,6 @@ int nfs4_lock_delegation_recall(struct nfs4_state *state, struct file_lock *fl)
 				nfs4_schedule_stateid_recovery(server, state);
 				err = 0;
 				goto out;
-			case -EKEYEXPIRED:
-				/*
-				 * User RPCSEC_GSS context has expired.
-				 * We cannot recover this stateid now, so
-				 * skip it and allow recovery thread to
-				 * proceed.
-				 */
-				err = 0;
-				goto out;
 			case -ENOMEM:
 			case -NFS4ERR_DENIED:
 				/* kill_proc(fl->fl_pid, SIGLOST, 1); */
@@ -5146,7 +5218,6 @@ int nfs4_proc_bind_conn_to_session(struct nfs_client *clp, struct rpc_cred *cred
 	};
 
 	dprintk("--> %s\n", __func__);
-	BUG_ON(clp == NULL);
 
 	res.session = kzalloc(sizeof(struct nfs4_session), GFP_NOFS);
 	if (unlikely(res.session == NULL)) {
@@ -5185,6 +5256,8 @@ out:
 /*
  * nfs4_proc_exchange_id()
  *
+ * Returns zero, a negative errno, or a negative NFS4ERR status code.
+ *
  * Since the clientid has expired, all compounds using sessions
  * associated with the stale clientid will be returning
  * NFS4ERR_BADSESSION in the sequence operation, and will therefore
@@ -5209,16 +5282,12 @@ int nfs4_proc_exchange_id(struct nfs_client *clp, struct rpc_cred *cred)
 		.rpc_cred = cred,
 	};
 
-	dprintk("--> %s\n", __func__);
-	BUG_ON(clp == NULL);
-
 	nfs4_init_boot_verifier(clp, &verifier);
-
-	args.id_len = scnprintf(args.id, sizeof(args.id),
-				"%s/%s/%u",
-				clp->cl_ipaddr,
-				clp->cl_rpcclient->cl_nodename,
-				clp->cl_rpcclient->cl_auth->au_flavor);
+	args.id_len = nfs4_init_uniform_client_string(clp, args.id,
+							sizeof(args.id));
+	dprintk("NFS call  exchange_id auth=%s, '%.*s'\n",
+		clp->cl_rpcclient->cl_auth->au_ops->au_name,
+		args.id_len, args.id);
 
 	res.server_owner = kzalloc(sizeof(struct nfs41_server_owner),
 					GFP_NOFS);
@@ -5281,12 +5350,12 @@ out_server_scope:
 	kfree(res.server_scope);
 out:
 	if (clp->cl_implid != NULL)
-		dprintk("%s: Server Implementation ID: "
+		dprintk("NFS reply exchange_id: Server Implementation ID: "
 			"domain: %s, name: %s, date: %llu,%u\n",
-			__func__, clp->cl_implid->domain, clp->cl_implid->name,
+			clp->cl_implid->domain, clp->cl_implid->name,
 			clp->cl_implid->date.seconds,
 			clp->cl_implid->date.nseconds);
-	dprintk("<-- %s status= %d\n", __func__, status);
+	dprintk("NFS reply exchange_id: %d\n", status);
 	return status;
 }
 
@@ -5336,6 +5405,8 @@ int nfs4_destroy_clientid(struct nfs_client *clp)
 		goto out;
 	if (clp->cl_exchange_flags == 0)
 		goto out;
+	if (clp->cl_preserve_clid)
+		goto out;
 	cred = nfs4_get_exchange_id_cred(clp);
 	ret = nfs4_proc_destroy_clientid(clp, cred);
 	if (cred)
@@ -5358,20 +5429,16 @@ struct nfs4_get_lease_time_data {
 static void nfs4_get_lease_time_prepare(struct rpc_task *task,
 					void *calldata)
 {
-	int ret;
 	struct nfs4_get_lease_time_data *data =
 			(struct nfs4_get_lease_time_data *)calldata;
 
 	dprintk("--> %s\n", __func__);
-	rpc_task_set_priority(task, RPC_PRIORITY_PRIVILEGED);
 	/* just setup sequence, do not trigger session recovery
 	   since we're invoked within one */
-	ret = nfs41_setup_sequence(data->clp->cl_session,
-				   &data->args->la_seq_args,
-				   &data->res->lr_seq_res, task);
-
-	BUG_ON(ret == -EAGAIN);
-	rpc_call_start(task);
+	nfs41_setup_sequence(data->clp->cl_session,
+			&data->args->la_seq_args,
+			&data->res->lr_seq_res,
+			task);
 	dprintk("<-- %s\n", __func__);
 }
 
@@ -5433,6 +5500,7 @@ int nfs4_proc_get_lease_time(struct nfs_client *clp, struct nfs_fsinfo *fsinfo)
 	int status;
 
 	nfs41_init_sequence(&args.la_seq_args, &res.lr_seq_res, 0);
+	nfs4_set_sequence_privileged(&args.la_seq_args);
 	dprintk("--> %s\n", __func__);
 	task = rpc_run_task(&task_setup);
 
@@ -5447,145 +5515,6 @@ int nfs4_proc_get_lease_time(struct nfs_client *clp, struct nfs_fsinfo *fsinfo)
 	return status;
 }
 
-static struct nfs4_slot *nfs4_alloc_slots(u32 max_slots, gfp_t gfp_flags)
-{
-	return kcalloc(max_slots, sizeof(struct nfs4_slot), gfp_flags);
-}
-
-static void nfs4_add_and_init_slots(struct nfs4_slot_table *tbl,
-		struct nfs4_slot *new,
-		u32 max_slots,
-		u32 ivalue)
-{
-	struct nfs4_slot *old = NULL;
-	u32 i;
-
-	spin_lock(&tbl->slot_tbl_lock);
-	if (new) {
-		old = tbl->slots;
-		tbl->slots = new;
-		tbl->max_slots = max_slots;
-	}
-	tbl->highest_used_slotid = -1;	/* no slot is currently used */
-	for (i = 0; i < tbl->max_slots; i++)
-		tbl->slots[i].seq_nr = ivalue;
-	spin_unlock(&tbl->slot_tbl_lock);
-	kfree(old);
-}
-
-/*
- * (re)Initialise a slot table
- */
-static int nfs4_realloc_slot_table(struct nfs4_slot_table *tbl, u32 max_reqs,
-				 u32 ivalue)
-{
-	struct nfs4_slot *new = NULL;
-	int ret = -ENOMEM;
-
-	dprintk("--> %s: max_reqs=%u, tbl->max_slots %d\n", __func__,
-		max_reqs, tbl->max_slots);
-
-	/* Does the newly negotiated max_reqs match the existing slot table? */
-	if (max_reqs != tbl->max_slots) {
-		new = nfs4_alloc_slots(max_reqs, GFP_NOFS);
-		if (!new)
-			goto out;
-	}
-	ret = 0;
-
-	nfs4_add_and_init_slots(tbl, new, max_reqs, ivalue);
-	dprintk("%s: tbl=%p slots=%p max_slots=%d\n", __func__,
-		tbl, tbl->slots, tbl->max_slots);
-out:
-	dprintk("<-- %s: return %d\n", __func__, ret);
-	return ret;
-}
-
-/* Destroy the slot table */
-static void nfs4_destroy_slot_tables(struct nfs4_session *session)
-{
-	if (session->fc_slot_table.slots != NULL) {
-		kfree(session->fc_slot_table.slots);
-		session->fc_slot_table.slots = NULL;
-	}
-	if (session->bc_slot_table.slots != NULL) {
-		kfree(session->bc_slot_table.slots);
-		session->bc_slot_table.slots = NULL;
-	}
-	return;
-}
-
-/*
- * Initialize or reset the forechannel and backchannel tables
- */
-static int nfs4_setup_session_slot_tables(struct nfs4_session *ses)
-{
-	struct nfs4_slot_table *tbl;
-	int status;
-
-	dprintk("--> %s\n", __func__);
-	/* Fore channel */
-	tbl = &ses->fc_slot_table;
-	status = nfs4_realloc_slot_table(tbl, ses->fc_attrs.max_reqs, 1);
-	if (status) /* -ENOMEM */
-		return status;
-	/* Back channel */
-	tbl = &ses->bc_slot_table;
-	status = nfs4_realloc_slot_table(tbl, ses->bc_attrs.max_reqs, 0);
-	if (status && tbl->slots == NULL)
-		/* Fore and back channel share a connection so get
-		 * both slot tables or neither */
-		nfs4_destroy_slot_tables(ses);
-	return status;
-}
-
-struct nfs4_session *nfs4_alloc_session(struct nfs_client *clp)
-{
-	struct nfs4_session *session;
-	struct nfs4_slot_table *tbl;
-
-	session = kzalloc(sizeof(struct nfs4_session), GFP_NOFS);
-	if (!session)
-		return NULL;
-
-	tbl = &session->fc_slot_table;
-	tbl->highest_used_slotid = NFS4_NO_SLOT;
-	spin_lock_init(&tbl->slot_tbl_lock);
-	rpc_init_priority_wait_queue(&tbl->slot_tbl_waitq, "ForeChannel Slot table");
-	init_completion(&tbl->complete);
-
-	tbl = &session->bc_slot_table;
-	tbl->highest_used_slotid = NFS4_NO_SLOT;
-	spin_lock_init(&tbl->slot_tbl_lock);
-	rpc_init_wait_queue(&tbl->slot_tbl_waitq, "BackChannel Slot table");
-	init_completion(&tbl->complete);
-
-	session->session_state = 1<<NFS4_SESSION_INITING;
-
-	session->clp = clp;
-	return session;
-}
-
-void nfs4_destroy_session(struct nfs4_session *session)
-{
-	struct rpc_xprt *xprt;
-	struct rpc_cred *cred;
-
-	cred = nfs4_get_exchange_id_cred(session->clp);
-	nfs4_proc_destroy_session(session, cred);
-	if (cred)
-		put_rpccred(cred);
-
-	rcu_read_lock();
-	xprt = rcu_dereference(session->clp->cl_rpcclient->cl_xprt);
-	rcu_read_unlock();
-	dprintk("%s Destroy backchannel for xprt %p\n",
-		__func__, xprt);
-	xprt_destroy_backchannel(xprt, NFS41_BC_MIN_CALLBACKS);
-	nfs4_destroy_slot_tables(session);
-	kfree(session);
-}
-
 /*
  * Initialize the values to be used by the client in CREATE_SESSION
  * If nfs4_init_session set the fore channel request and response sizes,
@@ -5598,8 +5527,8 @@ void nfs4_destroy_session(struct nfs4_session *session)
 static void nfs4_init_channel_attrs(struct nfs41_create_session_args *args)
 {
 	struct nfs4_session *session = args->client->cl_session;
-	unsigned int mxrqst_sz = session->fc_attrs.max_rqst_sz,
-		     mxresp_sz = session->fc_attrs.max_resp_sz;
+	unsigned int mxrqst_sz = session->fc_target_max_rqst_sz,
+		     mxresp_sz = session->fc_target_max_resp_sz;
 
 	if (mxrqst_sz == 0)
 		mxrqst_sz = NFS_MAX_FILE_IO_SIZE;
@@ -5708,10 +5637,9 @@ static int _nfs4_proc_create_session(struct nfs_client *clp,
 
 	status = rpc_call_sync(session->clp->cl_rpcclient, &msg, RPC_TASK_TIMEOUT);
 
-	if (!status)
+	if (!status) {
 		/* Verify the session's negotiated channel_attrs values */
 		status = nfs4_verify_channel_attrs(&args, session);
-	if (!status) {
 		/* Increment the clientid slot sequence id */
 		clp->cl_seqid++;
 	}
@@ -5781,83 +5709,6 @@ int nfs4_proc_destroy_session(struct nfs4_session *session,
 }
 
 /*
- * With sessions, the client is not marked ready until after a
- * successful EXCHANGE_ID and CREATE_SESSION.
- *
- * Map errors cl_cons_state errors to EPROTONOSUPPORT to indicate
- * other versions of NFS can be tried.
- */
-static int nfs41_check_session_ready(struct nfs_client *clp)
-{
-	int ret;
-	
-	if (clp->cl_cons_state == NFS_CS_SESSION_INITING) {
-		ret = nfs4_client_recover_expired_lease(clp);
-		if (ret)
-			return ret;
-	}
-	if (clp->cl_cons_state < NFS_CS_READY)
-		return -EPROTONOSUPPORT;
-	smp_rmb();
-	return 0;
-}
-
-int nfs4_init_session(struct nfs_server *server)
-{
-	struct nfs_client *clp = server->nfs_client;
-	struct nfs4_session *session;
-	unsigned int rsize, wsize;
-
-	if (!nfs4_has_session(clp))
-		return 0;
-
-	session = clp->cl_session;
-	spin_lock(&clp->cl_lock);
-	if (test_and_clear_bit(NFS4_SESSION_INITING, &session->session_state)) {
-
-		rsize = server->rsize;
-		if (rsize == 0)
-			rsize = NFS_MAX_FILE_IO_SIZE;
-		wsize = server->wsize;
-		if (wsize == 0)
-			wsize = NFS_MAX_FILE_IO_SIZE;
-
-		session->fc_attrs.max_rqst_sz = wsize + nfs41_maxwrite_overhead;
-		session->fc_attrs.max_resp_sz = rsize + nfs41_maxread_overhead;
-	}
-	spin_unlock(&clp->cl_lock);
-
-	return nfs41_check_session_ready(clp);
-}
-
-int nfs4_init_ds_session(struct nfs_client *clp, unsigned long lease_time)
-{
-	struct nfs4_session *session = clp->cl_session;
-	int ret;
-
-	spin_lock(&clp->cl_lock);
-	if (test_and_clear_bit(NFS4_SESSION_INITING, &session->session_state)) {
-		/*
-		 * Do not set NFS_CS_CHECK_LEASE_TIME instead set the
-		 * DS lease to be equal to the MDS lease.
-		 */
-		clp->cl_lease_time = lease_time;
-		clp->cl_last_renewal = jiffies;
-	}
-	spin_unlock(&clp->cl_lock);
-
-	ret = nfs41_check_session_ready(clp);
-	if (ret)
-		return ret;
-	/* Test for the DS role */
-	if (!is_ds_client(clp))
-		return -ENODEV;
-	return 0;
-}
-EXPORT_SYMBOL_GPL(nfs4_init_ds_session);
-
-
-/*
  * Renew the cl_session lease.
  */
 struct nfs4_sequence_data {
@@ -5922,9 +5773,7 @@ static void nfs41_sequence_prepare(struct rpc_task *task, void *data)
 	args = task->tk_msg.rpc_argp;
 	res = task->tk_msg.rpc_resp;
 
-	if (nfs41_setup_sequence(clp->cl_session, args, res, task))
-		return;
-	rpc_call_start(task);
+	nfs41_setup_sequence(clp->cl_session, args, res, task);
 }
 
 static const struct rpc_call_ops nfs41_sequence_ops = {
@@ -5933,7 +5782,9 @@ static const struct rpc_call_ops nfs41_sequence_ops = {
 	.rpc_release = nfs41_sequence_release,
 };
 
-static struct rpc_task *_nfs41_proc_sequence(struct nfs_client *clp, struct rpc_cred *cred)
+static struct rpc_task *_nfs41_proc_sequence(struct nfs_client *clp,
+		struct rpc_cred *cred,
+		bool is_privileged)
 {
 	struct nfs4_sequence_data *calldata;
 	struct rpc_message msg = {
@@ -5955,6 +5806,8 @@ static struct rpc_task *_nfs41_proc_sequence(struct nfs_client *clp, struct rpc_
 		return ERR_PTR(-ENOMEM);
 	}
 	nfs41_init_sequence(&calldata->args, &calldata->res, 0);
+	if (is_privileged)
+		nfs4_set_sequence_privileged(&calldata->args);
 	msg.rpc_argp = &calldata->args;
 	msg.rpc_resp = &calldata->res;
 	calldata->clp = clp;
@@ -5970,7 +5823,7 @@ static int nfs41_proc_async_sequence(struct nfs_client *clp, struct rpc_cred *cr
 
 	if ((renew_flags & NFS4_RENEW_TIMEOUT) == 0)
 		return 0;
-	task = _nfs41_proc_sequence(clp, cred);
+	task = _nfs41_proc_sequence(clp, cred, false);
 	if (IS_ERR(task))
 		ret = PTR_ERR(task);
 	else
@@ -5984,7 +5837,7 @@ static int nfs4_proc_sequence(struct nfs_client *clp, struct rpc_cred *cred)
 	struct rpc_task *task;
 	int ret;
 
-	task = _nfs41_proc_sequence(clp, cred);
+	task = _nfs41_proc_sequence(clp, cred, true);
 	if (IS_ERR(task)) {
 		ret = PTR_ERR(task);
 		goto out;
@@ -6013,13 +5866,10 @@ static void nfs4_reclaim_complete_prepare(struct rpc_task *task, void *data)
 {
 	struct nfs4_reclaim_complete_data *calldata = data;
 
-	rpc_task_set_priority(task, RPC_PRIORITY_PRIVILEGED);
-	if (nfs41_setup_sequence(calldata->clp->cl_session,
-				&calldata->arg.seq_args,
-				&calldata->res.seq_res, task))
-		return;
-
-	rpc_call_start(task);
+	nfs41_setup_sequence(calldata->clp->cl_session,
+			&calldata->arg.seq_args,
+			&calldata->res.seq_res,
+			task);
 }
 
 static int nfs41_reclaim_complete_handle_errors(struct rpc_task *task, struct nfs_client *clp)
@@ -6096,6 +5946,7 @@ static int nfs41_proc_reclaim_complete(struct nfs_client *clp)
 	calldata->arg.one_fs = 0;
 
 	nfs41_init_sequence(&calldata->arg.seq_args, &calldata->res.seq_res, 0);
+	nfs4_set_sequence_privileged(&calldata->arg.seq_args);
 	msg.rpc_argp = &calldata->arg;
 	msg.rpc_resp = &calldata->res;
 	task_setup_data.callback_data = calldata;
@@ -6119,6 +5970,7 @@ nfs4_layoutget_prepare(struct rpc_task *task, void *calldata)
 {
 	struct nfs4_layoutget *lgp = calldata;
 	struct nfs_server *server = NFS_SERVER(lgp->args.inode);
+	struct nfs4_session *session = nfs4_get_session(server);
 
 	dprintk("--> %s\n", __func__);
 	/* Note the is a race here, where a CB_LAYOUTRECALL can come in
@@ -6126,49 +5978,112 @@ nfs4_layoutget_prepare(struct rpc_task *task, void *calldata)
 	 * However, that is not so catastrophic, and there seems
 	 * to be no way to prevent it completely.
 	 */
-	if (nfs4_setup_sequence(server, &lgp->args.seq_args,
+	if (nfs41_setup_sequence(session, &lgp->args.seq_args,
 				&lgp->res.seq_res, task))
 		return;
 	if (pnfs_choose_layoutget_stateid(&lgp->args.stateid,
 					  NFS_I(lgp->args.inode)->layout,
 					  lgp->args.ctx->state)) {
 		rpc_exit(task, NFS4_OK);
-		return;
 	}
-	rpc_call_start(task);
 }
 
 static void nfs4_layoutget_done(struct rpc_task *task, void *calldata)
 {
 	struct nfs4_layoutget *lgp = calldata;
-	struct nfs_server *server = NFS_SERVER(lgp->args.inode);
+	struct inode *inode = lgp->args.inode;
+	struct nfs_server *server = NFS_SERVER(inode);
+	struct pnfs_layout_hdr *lo;
+	struct nfs4_state *state = NULL;
 
 	dprintk("--> %s\n", __func__);
 
-	if (!nfs4_sequence_done(task, &lgp->res.seq_res))
-		return;
+	if (!nfs41_sequence_done(task, &lgp->res.seq_res))
+		goto out;
 
 	switch (task->tk_status) {
 	case 0:
-		break;
+		goto out;
 	case -NFS4ERR_LAYOUTTRYLATER:
 	case -NFS4ERR_RECALLCONFLICT:
 		task->tk_status = -NFS4ERR_DELAY;
-		/* Fall through */
-	default:
-		if (nfs4_async_handle_error(task, server, NULL) == -EAGAIN) {
-			rpc_restart_call_prepare(task);
-			return;
+		break;
+	case -NFS4ERR_EXPIRED:
+	case -NFS4ERR_BAD_STATEID:
+		spin_lock(&inode->i_lock);
+		lo = NFS_I(inode)->layout;
+		if (!lo || list_empty(&lo->plh_segs)) {
+			spin_unlock(&inode->i_lock);
+			/* If the open stateid was bad, then recover it. */
+			state = lgp->args.ctx->state;
+		} else {
+			LIST_HEAD(head);
+
+			pnfs_mark_matching_lsegs_invalid(lo, &head, NULL);
+			spin_unlock(&inode->i_lock);
+			/* Mark the bad layout state as invalid, then
+			 * retry using the open stateid. */
+			pnfs_free_lseg_list(&head);
 		}
 	}
+	if (nfs4_async_handle_error(task, server, state) == -EAGAIN)
+		rpc_restart_call_prepare(task);
+out:
 	dprintk("<-- %s\n", __func__);
 }
 
+static size_t max_response_pages(struct nfs_server *server)
+{
+	u32 max_resp_sz = server->nfs_client->cl_session->fc_attrs.max_resp_sz;
+	return nfs_page_array_len(0, max_resp_sz);
+}
+
+static void nfs4_free_pages(struct page **pages, size_t size)
+{
+	int i;
+
+	if (!pages)
+		return;
+
+	for (i = 0; i < size; i++) {
+		if (!pages[i])
+			break;
+		__free_page(pages[i]);
+	}
+	kfree(pages);
+}
+
+static struct page **nfs4_alloc_pages(size_t size, gfp_t gfp_flags)
+{
+	struct page **pages;
+	int i;
+
+	pages = kcalloc(size, sizeof(struct page *), gfp_flags);
+	if (!pages) {
+		dprintk("%s: can't alloc array of %zu pages\n", __func__, size);
+		return NULL;
+	}
+
+	for (i = 0; i < size; i++) {
+		pages[i] = alloc_page(gfp_flags);
+		if (!pages[i]) {
+			dprintk("%s: failed to allocate page\n", __func__);
+			nfs4_free_pages(pages, size);
+			return NULL;
+		}
+	}
+
+	return pages;
+}
+
 static void nfs4_layoutget_release(void *calldata)
 {
 	struct nfs4_layoutget *lgp = calldata;
+	struct nfs_server *server = NFS_SERVER(lgp->args.inode);
+	size_t max_pages = max_response_pages(server);
 
 	dprintk("--> %s\n", __func__);
+	nfs4_free_pages(lgp->args.layout.pages, max_pages);
 	put_nfs_open_context(lgp->args.ctx);
 	kfree(calldata);
 	dprintk("<-- %s\n", __func__);
@@ -6180,9 +6095,11 @@ static const struct rpc_call_ops nfs4_layoutget_call_ops = {
 	.rpc_release = nfs4_layoutget_release,
 };
 
-int nfs4_proc_layoutget(struct nfs4_layoutget *lgp)
+struct pnfs_layout_segment *
+nfs4_proc_layoutget(struct nfs4_layoutget *lgp, gfp_t gfp_flags)
 {
 	struct nfs_server *server = NFS_SERVER(lgp->args.inode);
+	size_t max_pages = max_response_pages(server);
 	struct rpc_task *task;
 	struct rpc_message msg = {
 		.rpc_proc = &nfs4_procedures[NFSPROC4_CLNT_LAYOUTGET],
@@ -6196,24 +6113,34 @@ int nfs4_proc_layoutget(struct nfs4_layoutget *lgp)
 		.callback_data = lgp,
 		.flags = RPC_TASK_ASYNC,
 	};
+	struct pnfs_layout_segment *lseg = NULL;
 	int status = 0;
 
 	dprintk("--> %s\n", __func__);
 
+	lgp->args.layout.pages = nfs4_alloc_pages(max_pages, gfp_flags);
+	if (!lgp->args.layout.pages) {
+		nfs4_layoutget_release(lgp);
+		return ERR_PTR(-ENOMEM);
+	}
+	lgp->args.layout.pglen = max_pages * PAGE_SIZE;
+
 	lgp->res.layoutp = &lgp->args.layout;
 	lgp->res.seq_res.sr_slot = NULL;
 	nfs41_init_sequence(&lgp->args.seq_args, &lgp->res.seq_res, 0);
 	task = rpc_run_task(&task_setup_data);
 	if (IS_ERR(task))
-		return PTR_ERR(task);
+		return ERR_CAST(task);
 	status = nfs4_wait_for_completion_rpc_task(task);
 	if (status == 0)
 		status = task->tk_status;
 	if (status == 0)
-		status = pnfs_layout_process(lgp);
+		lseg = pnfs_layout_process(lgp);
 	rpc_put_task(task);
 	dprintk("<-- %s status=%d\n", __func__, status);
-	return status;
+	if (status)
+		return ERR_PTR(status);
+	return lseg;
 }
 
 static void
@@ -6222,21 +6149,20 @@ nfs4_layoutreturn_prepare(struct rpc_task *task, void *calldata)
 	struct nfs4_layoutreturn *lrp = calldata;
 
 	dprintk("--> %s\n", __func__);
-	if (nfs41_setup_sequence(lrp->clp->cl_session, &lrp->args.seq_args,
-				&lrp->res.seq_res, task))
-		return;
-	rpc_call_start(task);
+	nfs41_setup_sequence(lrp->clp->cl_session,
+			&lrp->args.seq_args,
+			&lrp->res.seq_res,
+			task);
 }
 
 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 = lrp->args.layout;
 
 	dprintk("--> %s\n", __func__);
 
-	if (!nfs4_sequence_done(task, &lrp->res.seq_res))
+	if (!nfs41_sequence_done(task, &lrp->res.seq_res))
 		return;
 
 	server = NFS_SERVER(lrp->args.inode);
@@ -6244,24 +6170,21 @@ static void nfs4_layoutreturn_done(struct rpc_task *task, void *calldata)
 		rpc_restart_call_prepare(task);
 		return;
 	}
-	spin_lock(&lo->plh_inode->i_lock);
-	if (task->tk_status == 0) {
-		if (lrp->res.lrs_present) {
-			pnfs_set_layout_stateid(lo, &lrp->res.stateid, true);
-		} else
-			BUG_ON(!list_empty(&lo->plh_segs));
-	}
-	lo->plh_block_lgets--;
-	spin_unlock(&lo->plh_inode->i_lock);
 	dprintk("<-- %s\n", __func__);
 }
 
 static void nfs4_layoutreturn_release(void *calldata)
 {
 	struct nfs4_layoutreturn *lrp = calldata;
+	struct pnfs_layout_hdr *lo = lrp->args.layout;
 
 	dprintk("--> %s\n", __func__);
-	put_layout_hdr(lrp->args.layout);
+	spin_lock(&lo->plh_inode->i_lock);
+	if (lrp->res.lrs_present)
+		pnfs_set_layout_stateid(lo, &lrp->res.stateid, true);
+	lo->plh_block_lgets--;
+	spin_unlock(&lo->plh_inode->i_lock);
+	pnfs_put_layout_hdr(lrp->args.layout);
 	kfree(calldata);
 	dprintk("<-- %s\n", __func__);
 }
@@ -6388,11 +6311,12 @@ static void nfs4_layoutcommit_prepare(struct rpc_task *task, void *calldata)
 {
 	struct nfs4_layoutcommit_data *data = calldata;
 	struct nfs_server *server = NFS_SERVER(data->args.inode);
+	struct nfs4_session *session = nfs4_get_session(server);
 
-	if (nfs4_setup_sequence(server, &data->args.seq_args,
-				&data->res.seq_res, task))
-		return;
-	rpc_call_start(task);
+	nfs41_setup_sequence(session,
+			&data->args.seq_args,
+			&data->res.seq_res,
+			task);
 }
 
 static void
@@ -6401,7 +6325,7 @@ nfs4_layoutcommit_done(struct rpc_task *task, void *calldata)
 	struct nfs4_layoutcommit_data *data = calldata;
 	struct nfs_server *server = NFS_SERVER(data->args.inode);
 
-	if (!nfs4_sequence_done(task, &data->res.seq_res))
+	if (!nfs41_sequence_done(task, &data->res.seq_res))
 		return;
 
 	switch (task->tk_status) { /* Just ignore these failures */
@@ -6435,7 +6359,7 @@ static void nfs4_layoutcommit_release(void *calldata)
 		list_del_init(&lseg->pls_lc_list);
 		if (test_and_clear_bit(NFS_LSEG_LAYOUTCOMMIT,
 				       &lseg->pls_flags))
-			put_lseg(lseg);
+			pnfs_put_lseg(lseg);
 	}
 
 	clear_bit_unlock(NFS_INO_LAYOUTCOMMITTING, bitlock);
@@ -6587,22 +6511,38 @@ static int _nfs41_test_stateid(struct nfs_server *server, nfs4_stateid *stateid)
 		.rpc_resp = &res,
 	};
 
+	dprintk("NFS call  test_stateid %p\n", stateid);
 	nfs41_init_sequence(&args.seq_args, &res.seq_res, 0);
-	status = nfs4_call_sync_sequence(server->client, server, &msg, &args.seq_args, &res.seq_res, 1);
-
-	if (status == NFS_OK)
-		return res.status;
-	return status;
+	nfs4_set_sequence_privileged(&args.seq_args);
+	status = nfs4_call_sync_sequence(server->client, server, &msg,
+			&args.seq_args, &res.seq_res);
+	if (status != NFS_OK) {
+		dprintk("NFS reply test_stateid: failed, %d\n", status);
+		return status;
+	}
+	dprintk("NFS reply test_stateid: succeeded, %d\n", -res.status);
+	return -res.status;
 }
 
+/**
+ * nfs41_test_stateid - perform a TEST_STATEID operation
+ *
+ * @server: server / transport on which to perform the operation
+ * @stateid: state ID to test
+ *
+ * Returns NFS_OK if the server recognizes that "stateid" is valid.
+ * Otherwise a negative NFS4ERR value is returned if the operation
+ * failed or the state ID is not currently valid.
+ */
 static int nfs41_test_stateid(struct nfs_server *server, nfs4_stateid *stateid)
 {
 	struct nfs4_exception exception = { };
 	int err;
 	do {
-		err = nfs4_handle_exception(server,
-				_nfs41_test_stateid(server, stateid),
-				&exception);
+		err = _nfs41_test_stateid(server, stateid);
+		if (err != -NFS4ERR_DELAY)
+			break;
+		nfs4_handle_exception(server, err, &exception);
 	} while (exception.retry);
 	return err;
 }
@@ -6618,19 +6558,35 @@ static int _nfs4_free_stateid(struct nfs_server *server, nfs4_stateid *stateid)
 		.rpc_argp = &args,
 		.rpc_resp = &res,
 	};
+	int status;
 
+	dprintk("NFS call  free_stateid %p\n", stateid);
 	nfs41_init_sequence(&args.seq_args, &res.seq_res, 0);
-	return nfs4_call_sync_sequence(server->client, server, &msg, &args.seq_args, &res.seq_res, 1);
+	nfs4_set_sequence_privileged(&args.seq_args);
+	status = nfs4_call_sync_sequence(server->client, server, &msg,
+			&args.seq_args, &res.seq_res);
+	dprintk("NFS reply free_stateid: %d\n", status);
+	return status;
 }
 
+/**
+ * nfs41_free_stateid - perform a FREE_STATEID operation
+ *
+ * @server: server / transport on which to perform the operation
+ * @stateid: state ID to release
+ *
+ * Returns NFS_OK if the server freed "stateid".  Otherwise a
+ * negative NFS4ERR value is returned.
+ */
 static int nfs41_free_stateid(struct nfs_server *server, nfs4_stateid *stateid)
 {
 	struct nfs4_exception exception = { };
 	int err;
 	do {
-		err = nfs4_handle_exception(server,
-				_nfs4_free_stateid(server, stateid),
-				&exception);
+		err = _nfs4_free_stateid(server, stateid);
+		if (err != -NFS4ERR_DELAY)
+			break;
+		nfs4_handle_exception(server, err, &exception);
 	} while (exception.retry);
 	return err;
 }
@@ -6665,6 +6621,7 @@ static const struct nfs4_state_recovery_ops nfs40_reboot_recovery_ops = {
 	.recover_lock	= nfs4_lock_reclaim,
 	.establish_clid = nfs4_init_clientid,
 	.get_clid_cred	= nfs4_get_setclientid_cred,
+	.detect_trunking = nfs40_discover_server_trunking,
 };
 
 #if defined(CONFIG_NFS_V4_1)
@@ -6676,6 +6633,7 @@ static const struct nfs4_state_recovery_ops nfs41_reboot_recovery_ops = {
 	.establish_clid = nfs41_init_clientid,
 	.get_clid_cred	= nfs4_get_exchange_id_cred,
 	.reclaim_complete = nfs41_proc_reclaim_complete,
+	.detect_trunking = nfs41_discover_server_trunking,
 };
 #endif /* CONFIG_NFS_V4_1 */
 
@@ -6726,7 +6684,7 @@ static const struct nfs4_minor_version_ops nfs_v4_0_minor_ops = {
 #if defined(CONFIG_NFS_V4_1)
 static const struct nfs4_minor_version_ops nfs_v4_1_minor_ops = {
 	.minor_version = 1,
-	.call_sync = _nfs4_call_sync_session,
+	.call_sync = nfs4_call_sync_sequence,
 	.match_stateid = nfs41_match_stateid,
 	.find_root_sec = nfs41_find_root_sec,
 	.reboot_recovery_ops = &nfs41_reboot_recovery_ops,
@@ -6742,6 +6700,26 @@ const struct nfs4_minor_version_ops *nfs_v4_minor_ops[] = {
 #endif
 };
 
+const struct inode_operations nfs4_dir_inode_operations = {
+	.create		= nfs_create,
+	.lookup		= nfs_lookup,
+	.atomic_open	= nfs_atomic_open,
+	.link		= nfs_link,
+	.unlink		= nfs_unlink,
+	.symlink	= nfs_symlink,
+	.mkdir		= nfs_mkdir,
+	.rmdir		= nfs_rmdir,
+	.mknod		= nfs_mknod,
+	.rename		= nfs_rename,
+	.permission	= nfs_permission,
+	.getattr	= nfs_getattr,
+	.setattr	= nfs_setattr,
+	.getxattr	= generic_getxattr,
+	.setxattr	= generic_setxattr,
+	.listxattr	= generic_listxattr,
+	.removexattr	= generic_removexattr,
+};
+
 static const struct inode_operations nfs4_file_inode_operations = {
 	.permission	= nfs_permission,
 	.getattr	= nfs_getattr,
@@ -6760,6 +6738,7 @@ const struct nfs_rpc_ops nfs_v4_clientops = {
 	.file_ops	= &nfs4_file_operations,
 	.getroot	= nfs4_proc_get_root,
 	.submount	= nfs4_submount,
+	.try_mount	= nfs4_try_mount,
 	.getattr	= nfs4_proc_getattr,
 	.setattr	= nfs4_proc_setattr,
 	.lookup		= nfs4_proc_lookup,
@@ -6786,9 +6765,11 @@ const struct nfs_rpc_ops nfs_v4_clientops = {
 	.set_capabilities = nfs4_server_capabilities,
 	.decode_dirent	= nfs4_decode_dirent,
 	.read_setup	= nfs4_proc_read_setup,
+	.read_pageio_init = pnfs_pageio_init_read,
 	.read_rpc_prepare = nfs4_proc_read_rpc_prepare,
 	.read_done	= nfs4_read_done,
 	.write_setup	= nfs4_proc_write_setup,
+	.write_pageio_init = pnfs_pageio_init_write,
 	.write_rpc_prepare = nfs4_proc_write_rpc_prepare,
 	.write_done	= nfs4_write_done,
 	.commit_setup	= nfs4_proc_commit_setup,
@@ -6798,7 +6779,13 @@ const struct nfs_rpc_ops nfs_v4_clientops = {
 	.clear_acl_cache = nfs4_zap_acl_attr,
 	.close_context  = nfs4_close_context,
 	.open_context	= nfs4_atomic_open,
+	.have_delegation = nfs4_have_delegation,
+	.return_delegation = nfs4_inode_return_delegation,
+	.alloc_client	= nfs4_alloc_client,
 	.init_client	= nfs4_init_client,
+	.free_client	= nfs4_free_client,
+	.create_server	= nfs4_create_server,
+	.clone_server	= nfs_clone_server,
 };
 
 static const struct xattr_handler nfs4_xattr_nfs4_acl_handler = {
@@ -6813,10 +6800,6 @@ const struct xattr_handler *nfs4_xattr_handlers[] = {
 	NULL
 };
 
-module_param(max_session_slots, ushort, 0644);
-MODULE_PARM_DESC(max_session_slots, "Maximum number of outstanding NFSv4.1 "
-		"requests the client will negotiate");
-
 /*
  * Local variables:
  *  c-basic-offset: 8
diff --git a/fs/nfs/nfs4renewd.c b/fs/nfs/nfs4renewd.c
index 6930bec91bc..1720d32ffa5 100644
--- a/fs/nfs/nfs4renewd.c
+++ b/fs/nfs/nfs4renewd.c
@@ -117,8 +117,7 @@ nfs4_schedule_state_renewal(struct nfs_client *clp)
 		timeout = 5 * HZ;
 	dprintk("%s: requeueing work. Lease period = %ld\n",
 			__func__, (timeout + HZ - 1) / HZ);
-	cancel_delayed_work(&clp->cl_renewd);
-	schedule_delayed_work(&clp->cl_renewd, timeout);
+	mod_delayed_work(system_wq, &clp->cl_renewd, timeout);
 	set_bit(NFS_CS_RENEWD, &clp->cl_res_state);
 	spin_unlock(&clp->cl_lock);
 }
diff --git a/fs/nfs/nfs4session.c b/fs/nfs/nfs4session.c
new file mode 100644
index 00000000000..ebda5f4a031
--- /dev/null
+++ b/fs/nfs/nfs4session.c
@@ -0,0 +1,552 @@
+/*
+ * fs/nfs/nfs4session.c
+ *
+ * Copyright (c) 2012 Trond Myklebust <Trond.Myklebust@netapp.com>
+ *
+ */
+#include <linux/kernel.h>
+#include <linux/errno.h>
+#include <linux/string.h>
+#include <linux/printk.h>
+#include <linux/slab.h>
+#include <linux/sunrpc/sched.h>
+#include <linux/sunrpc/bc_xprt.h>
+#include <linux/nfs.h>
+#include <linux/nfs4.h>
+#include <linux/nfs_fs.h>
+#include <linux/module.h>
+
+#include "nfs4_fs.h"
+#include "internal.h"
+#include "nfs4session.h"
+#include "callback.h"
+
+#define NFSDBG_FACILITY		NFSDBG_STATE
+
+/*
+ * nfs4_shrink_slot_table - free retired slots from the slot table
+ */
+static void nfs4_shrink_slot_table(struct nfs4_slot_table  *tbl, u32 newsize)
+{
+	struct nfs4_slot **p;
+	if (newsize >= tbl->max_slots)
+		return;
+
+	p = &tbl->slots;
+	while (newsize--)
+		p = &(*p)->next;
+	while (*p) {
+		struct nfs4_slot *slot = *p;
+
+		*p = slot->next;
+		kfree(slot);
+		tbl->max_slots--;
+	}
+}
+
+/*
+ * nfs4_free_slot - free a slot and efficiently update slot table.
+ *
+ * freeing a slot is trivially done by clearing its respective bit
+ * in the bitmap.
+ * If the freed slotid equals highest_used_slotid we want to update it
+ * so that the server would be able to size down the slot table if needed,
+ * otherwise we know that the highest_used_slotid is still in use.
+ * When updating highest_used_slotid there may be "holes" in the bitmap
+ * so we need to scan down from highest_used_slotid to 0 looking for the now
+ * highest slotid in use.
+ * If none found, highest_used_slotid is set to NFS4_NO_SLOT.
+ *
+ * Must be called while holding tbl->slot_tbl_lock
+ */
+void nfs4_free_slot(struct nfs4_slot_table *tbl, struct nfs4_slot *slot)
+{
+	u32 slotid = slot->slot_nr;
+
+	/* clear used bit in bitmap */
+	__clear_bit(slotid, tbl->used_slots);
+
+	/* update highest_used_slotid when it is freed */
+	if (slotid == tbl->highest_used_slotid) {
+		u32 new_max = find_last_bit(tbl->used_slots, slotid);
+		if (new_max < slotid)
+			tbl->highest_used_slotid = new_max;
+		else {
+			tbl->highest_used_slotid = NFS4_NO_SLOT;
+			nfs4_session_drain_complete(tbl->session, tbl);
+		}
+	}
+	dprintk("%s: slotid %u highest_used_slotid %d\n", __func__,
+		slotid, tbl->highest_used_slotid);
+}
+
+static struct nfs4_slot *nfs4_new_slot(struct nfs4_slot_table  *tbl,
+		u32 slotid, u32 seq_init, gfp_t gfp_mask)
+{
+	struct nfs4_slot *slot;
+
+	slot = kzalloc(sizeof(*slot), gfp_mask);
+	if (slot) {
+		slot->table = tbl;
+		slot->slot_nr = slotid;
+		slot->seq_nr = seq_init;
+	}
+	return slot;
+}
+
+static struct nfs4_slot *nfs4_find_or_create_slot(struct nfs4_slot_table  *tbl,
+		u32 slotid, u32 seq_init, gfp_t gfp_mask)
+{
+	struct nfs4_slot **p, *slot;
+
+	p = &tbl->slots;
+	for (;;) {
+		if (*p == NULL) {
+			*p = nfs4_new_slot(tbl, tbl->max_slots,
+					seq_init, gfp_mask);
+			if (*p == NULL)
+				break;
+			tbl->max_slots++;
+		}
+		slot = *p;
+		if (slot->slot_nr == slotid)
+			return slot;
+		p = &slot->next;
+	}
+	return ERR_PTR(-ENOMEM);
+}
+
+/*
+ * nfs4_alloc_slot - efficiently look for a free slot
+ *
+ * nfs4_alloc_slot looks for an unset bit in the used_slots bitmap.
+ * If found, we mark the slot as used, update the highest_used_slotid,
+ * and respectively set up the sequence operation args.
+ *
+ * Note: must be called with under the slot_tbl_lock.
+ */
+struct nfs4_slot *nfs4_alloc_slot(struct nfs4_slot_table *tbl)
+{
+	struct nfs4_slot *ret = ERR_PTR(-EBUSY);
+	u32 slotid;
+
+	dprintk("--> %s used_slots=%04lx highest_used=%u max_slots=%u\n",
+		__func__, tbl->used_slots[0], tbl->highest_used_slotid,
+		tbl->max_slotid + 1);
+	slotid = find_first_zero_bit(tbl->used_slots, tbl->max_slotid + 1);
+	if (slotid > tbl->max_slotid)
+		goto out;
+	ret = nfs4_find_or_create_slot(tbl, slotid, 1, GFP_NOWAIT);
+	if (IS_ERR(ret))
+		goto out;
+	__set_bit(slotid, tbl->used_slots);
+	if (slotid > tbl->highest_used_slotid ||
+			tbl->highest_used_slotid == NFS4_NO_SLOT)
+		tbl->highest_used_slotid = slotid;
+	ret->generation = tbl->generation;
+
+out:
+	dprintk("<-- %s used_slots=%04lx highest_used=%d slotid=%d \n",
+		__func__, tbl->used_slots[0], tbl->highest_used_slotid,
+		!IS_ERR(ret) ? ret->slot_nr : -1);
+	return ret;
+}
+
+static int nfs4_grow_slot_table(struct nfs4_slot_table *tbl,
+		 u32 max_reqs, u32 ivalue)
+{
+	if (max_reqs <= tbl->max_slots)
+		return 0;
+	if (!IS_ERR(nfs4_find_or_create_slot(tbl, max_reqs - 1, ivalue, GFP_NOFS)))
+		return 0;
+	return -ENOMEM;
+}
+
+static void nfs4_reset_slot_table(struct nfs4_slot_table *tbl,
+		u32 server_highest_slotid,
+		u32 ivalue)
+{
+	struct nfs4_slot **p;
+
+	nfs4_shrink_slot_table(tbl, server_highest_slotid + 1);
+	p = &tbl->slots;
+	while (*p) {
+		(*p)->seq_nr = ivalue;
+		(*p)->interrupted = 0;
+		p = &(*p)->next;
+	}
+	tbl->highest_used_slotid = NFS4_NO_SLOT;
+	tbl->target_highest_slotid = server_highest_slotid;
+	tbl->server_highest_slotid = server_highest_slotid;
+	tbl->d_target_highest_slotid = 0;
+	tbl->d2_target_highest_slotid = 0;
+	tbl->max_slotid = server_highest_slotid;
+}
+
+/*
+ * (re)Initialise a slot table
+ */
+static int nfs4_realloc_slot_table(struct nfs4_slot_table *tbl,
+		u32 max_reqs, u32 ivalue)
+{
+	int ret;
+
+	dprintk("--> %s: max_reqs=%u, tbl->max_slots %d\n", __func__,
+		max_reqs, tbl->max_slots);
+
+	if (max_reqs > NFS4_MAX_SLOT_TABLE)
+		max_reqs = NFS4_MAX_SLOT_TABLE;
+
+	ret = nfs4_grow_slot_table(tbl, max_reqs, ivalue);
+	if (ret)
+		goto out;
+
+	spin_lock(&tbl->slot_tbl_lock);
+	nfs4_reset_slot_table(tbl, max_reqs - 1, ivalue);
+	spin_unlock(&tbl->slot_tbl_lock);
+
+	dprintk("%s: tbl=%p slots=%p max_slots=%d\n", __func__,
+		tbl, tbl->slots, tbl->max_slots);
+out:
+	dprintk("<-- %s: return %d\n", __func__, ret);
+	return ret;
+}
+
+/* Destroy the slot table */
+static void nfs4_destroy_slot_tables(struct nfs4_session *session)
+{
+	nfs4_shrink_slot_table(&session->fc_slot_table, 0);
+	nfs4_shrink_slot_table(&session->bc_slot_table, 0);
+}
+
+static bool nfs41_assign_slot(struct rpc_task *task, void *pslot)
+{
+	struct nfs4_sequence_args *args = task->tk_msg.rpc_argp;
+	struct nfs4_sequence_res *res = task->tk_msg.rpc_resp;
+	struct nfs4_slot *slot = pslot;
+	struct nfs4_slot_table *tbl = slot->table;
+
+	if (nfs4_session_draining(tbl->session) && !args->sa_privileged)
+		return false;
+	slot->generation = tbl->generation;
+	args->sa_slot = slot;
+	res->sr_timestamp = jiffies;
+	res->sr_slot = slot;
+	res->sr_status_flags = 0;
+	res->sr_status = 1;
+	return true;
+}
+
+static bool __nfs41_wake_and_assign_slot(struct nfs4_slot_table *tbl,
+		struct nfs4_slot *slot)
+{
+	if (rpc_wake_up_first(&tbl->slot_tbl_waitq, nfs41_assign_slot, slot))
+		return true;
+	return false;
+}
+
+bool nfs41_wake_and_assign_slot(struct nfs4_slot_table *tbl,
+		struct nfs4_slot *slot)
+{
+	if (slot->slot_nr > tbl->max_slotid)
+		return false;
+	return __nfs41_wake_and_assign_slot(tbl, slot);
+}
+
+static bool nfs41_try_wake_next_slot_table_entry(struct nfs4_slot_table *tbl)
+{
+	struct nfs4_slot *slot = nfs4_alloc_slot(tbl);
+	if (!IS_ERR(slot)) {
+		bool ret = __nfs41_wake_and_assign_slot(tbl, slot);
+		if (ret)
+			return ret;
+		nfs4_free_slot(tbl, slot);
+	}
+	return false;
+}
+
+void nfs41_wake_slot_table(struct nfs4_slot_table *tbl)
+{
+	for (;;) {
+		if (!nfs41_try_wake_next_slot_table_entry(tbl))
+			break;
+	}
+}
+
+static void nfs41_set_max_slotid_locked(struct nfs4_slot_table *tbl,
+		u32 target_highest_slotid)
+{
+	u32 max_slotid;
+
+	max_slotid = min(NFS4_MAX_SLOT_TABLE - 1, target_highest_slotid);
+	if (max_slotid > tbl->server_highest_slotid)
+		max_slotid = tbl->server_highest_slotid;
+	if (max_slotid > tbl->target_highest_slotid)
+		max_slotid = tbl->target_highest_slotid;
+	tbl->max_slotid = max_slotid;
+	nfs41_wake_slot_table(tbl);
+}
+
+/* Update the client's idea of target_highest_slotid */
+static void nfs41_set_target_slotid_locked(struct nfs4_slot_table *tbl,
+		u32 target_highest_slotid)
+{
+	if (tbl->target_highest_slotid == target_highest_slotid)
+		return;
+	tbl->target_highest_slotid = target_highest_slotid;
+	tbl->generation++;
+}
+
+void nfs41_set_target_slotid(struct nfs4_slot_table *tbl,
+		u32 target_highest_slotid)
+{
+	spin_lock(&tbl->slot_tbl_lock);
+	nfs41_set_target_slotid_locked(tbl, target_highest_slotid);
+	tbl->d_target_highest_slotid = 0;
+	tbl->d2_target_highest_slotid = 0;
+	nfs41_set_max_slotid_locked(tbl, target_highest_slotid);
+	spin_unlock(&tbl->slot_tbl_lock);
+}
+
+static void nfs41_set_server_slotid_locked(struct nfs4_slot_table *tbl,
+		u32 highest_slotid)
+{
+	if (tbl->server_highest_slotid == highest_slotid)
+		return;
+	if (tbl->highest_used_slotid > highest_slotid)
+		return;
+	/* Deallocate slots */
+	nfs4_shrink_slot_table(tbl, highest_slotid + 1);
+	tbl->server_highest_slotid = highest_slotid;
+}
+
+static s32 nfs41_derivative_target_slotid(s32 s1, s32 s2)
+{
+	s1 -= s2;
+	if (s1 == 0)
+		return 0;
+	if (s1 < 0)
+		return (s1 - 1) >> 1;
+	return (s1 + 1) >> 1;
+}
+
+static int nfs41_sign_s32(s32 s1)
+{
+	if (s1 > 0)
+		return 1;
+	if (s1 < 0)
+		return -1;
+	return 0;
+}
+
+static bool nfs41_same_sign_or_zero_s32(s32 s1, s32 s2)
+{
+	if (!s1 || !s2)
+		return true;
+	return nfs41_sign_s32(s1) == nfs41_sign_s32(s2);
+}
+
+/* Try to eliminate outliers by checking for sharp changes in the
+ * derivatives and second derivatives
+ */
+static bool nfs41_is_outlier_target_slotid(struct nfs4_slot_table *tbl,
+		u32 new_target)
+{
+	s32 d_target, d2_target;
+	bool ret = true;
+
+	d_target = nfs41_derivative_target_slotid(new_target,
+			tbl->target_highest_slotid);
+	d2_target = nfs41_derivative_target_slotid(d_target,
+			tbl->d_target_highest_slotid);
+	/* Is first derivative same sign? */
+	if (nfs41_same_sign_or_zero_s32(d_target, tbl->d_target_highest_slotid))
+		ret = false;
+	/* Is second derivative same sign? */
+	if (nfs41_same_sign_or_zero_s32(d2_target, tbl->d2_target_highest_slotid))
+		ret = false;
+	tbl->d_target_highest_slotid = d_target;
+	tbl->d2_target_highest_slotid = d2_target;
+	return ret;
+}
+
+void nfs41_update_target_slotid(struct nfs4_slot_table *tbl,
+		struct nfs4_slot *slot,
+		struct nfs4_sequence_res *res)
+{
+	spin_lock(&tbl->slot_tbl_lock);
+	if (!nfs41_is_outlier_target_slotid(tbl, res->sr_target_highest_slotid))
+		nfs41_set_target_slotid_locked(tbl, res->sr_target_highest_slotid);
+	if (tbl->generation == slot->generation)
+		nfs41_set_server_slotid_locked(tbl, res->sr_highest_slotid);
+	nfs41_set_max_slotid_locked(tbl, res->sr_target_highest_slotid);
+	spin_unlock(&tbl->slot_tbl_lock);
+}
+
+/*
+ * Initialize or reset the forechannel and backchannel tables
+ */
+int nfs4_setup_session_slot_tables(struct nfs4_session *ses)
+{
+	struct nfs4_slot_table *tbl;
+	int status;
+
+	dprintk("--> %s\n", __func__);
+	/* Fore channel */
+	tbl = &ses->fc_slot_table;
+	tbl->session = ses;
+	status = nfs4_realloc_slot_table(tbl, ses->fc_attrs.max_reqs, 1);
+	if (status) /* -ENOMEM */
+		return status;
+	/* Back channel */
+	tbl = &ses->bc_slot_table;
+	tbl->session = ses;
+	status = nfs4_realloc_slot_table(tbl, ses->bc_attrs.max_reqs, 0);
+	if (status && tbl->slots == NULL)
+		/* Fore and back channel share a connection so get
+		 * both slot tables or neither */
+		nfs4_destroy_slot_tables(ses);
+	return status;
+}
+
+struct nfs4_session *nfs4_alloc_session(struct nfs_client *clp)
+{
+	struct nfs4_session *session;
+	struct nfs4_slot_table *tbl;
+
+	session = kzalloc(sizeof(struct nfs4_session), GFP_NOFS);
+	if (!session)
+		return NULL;
+
+	tbl = &session->fc_slot_table;
+	tbl->highest_used_slotid = NFS4_NO_SLOT;
+	spin_lock_init(&tbl->slot_tbl_lock);
+	rpc_init_priority_wait_queue(&tbl->slot_tbl_waitq, "ForeChannel Slot table");
+	init_completion(&tbl->complete);
+
+	tbl = &session->bc_slot_table;
+	tbl->highest_used_slotid = NFS4_NO_SLOT;
+	spin_lock_init(&tbl->slot_tbl_lock);
+	rpc_init_wait_queue(&tbl->slot_tbl_waitq, "BackChannel Slot table");
+	init_completion(&tbl->complete);
+
+	session->session_state = 1<<NFS4_SESSION_INITING;
+
+	session->clp = clp;
+	return session;
+}
+
+void nfs4_destroy_session(struct nfs4_session *session)
+{
+	struct rpc_xprt *xprt;
+	struct rpc_cred *cred;
+
+	cred = nfs4_get_exchange_id_cred(session->clp);
+	nfs4_proc_destroy_session(session, cred);
+	if (cred)
+		put_rpccred(cred);
+
+	rcu_read_lock();
+	xprt = rcu_dereference(session->clp->cl_rpcclient->cl_xprt);
+	rcu_read_unlock();
+	dprintk("%s Destroy backchannel for xprt %p\n",
+		__func__, xprt);
+	xprt_destroy_backchannel(xprt, NFS41_BC_MIN_CALLBACKS);
+	nfs4_destroy_slot_tables(session);
+	kfree(session);
+}
+
+/*
+ * With sessions, the client is not marked ready until after a
+ * successful EXCHANGE_ID and CREATE_SESSION.
+ *
+ * Map errors cl_cons_state errors to EPROTONOSUPPORT to indicate
+ * other versions of NFS can be tried.
+ */
+static int nfs41_check_session_ready(struct nfs_client *clp)
+{
+	int ret;
+	
+	if (clp->cl_cons_state == NFS_CS_SESSION_INITING) {
+		ret = nfs4_client_recover_expired_lease(clp);
+		if (ret)
+			return ret;
+	}
+	if (clp->cl_cons_state < NFS_CS_READY)
+		return -EPROTONOSUPPORT;
+	smp_rmb();
+	return 0;
+}
+
+int nfs4_init_session(struct nfs_server *server)
+{
+	struct nfs_client *clp = server->nfs_client;
+	struct nfs4_session *session;
+	unsigned int target_max_rqst_sz = NFS_MAX_FILE_IO_SIZE;
+	unsigned int target_max_resp_sz = NFS_MAX_FILE_IO_SIZE;
+
+	if (!nfs4_has_session(clp))
+		return 0;
+
+	if (server->rsize != 0)
+		target_max_resp_sz = server->rsize;
+	target_max_resp_sz += nfs41_maxread_overhead;
+
+	if (server->wsize != 0)
+		target_max_rqst_sz = server->wsize;
+	target_max_rqst_sz += nfs41_maxwrite_overhead;
+
+	session = clp->cl_session;
+	spin_lock(&clp->cl_lock);
+	if (test_and_clear_bit(NFS4_SESSION_INITING, &session->session_state)) {
+		/* Initialise targets and channel attributes */
+		session->fc_target_max_rqst_sz = target_max_rqst_sz;
+		session->fc_attrs.max_rqst_sz = target_max_rqst_sz;
+		session->fc_target_max_resp_sz = target_max_resp_sz;
+		session->fc_attrs.max_resp_sz = target_max_resp_sz;
+	} else {
+		/* Just adjust the targets */
+		if (target_max_rqst_sz > session->fc_target_max_rqst_sz) {
+			session->fc_target_max_rqst_sz = target_max_rqst_sz;
+			set_bit(NFS4CLNT_SESSION_RESET, &clp->cl_state);
+		}
+		if (target_max_resp_sz > session->fc_target_max_resp_sz) {
+			session->fc_target_max_resp_sz = target_max_resp_sz;
+			set_bit(NFS4CLNT_SESSION_RESET, &clp->cl_state);
+		}
+	}
+	spin_unlock(&clp->cl_lock);
+
+	if (test_bit(NFS4CLNT_SESSION_RESET, &clp->cl_state))
+		nfs4_schedule_lease_recovery(clp);
+
+	return nfs41_check_session_ready(clp);
+}
+
+int nfs4_init_ds_session(struct nfs_client *clp, unsigned long lease_time)
+{
+	struct nfs4_session *session = clp->cl_session;
+	int ret;
+
+	spin_lock(&clp->cl_lock);
+	if (test_and_clear_bit(NFS4_SESSION_INITING, &session->session_state)) {
+		/*
+		 * Do not set NFS_CS_CHECK_LEASE_TIME instead set the
+		 * DS lease to be equal to the MDS lease.
+		 */
+		clp->cl_lease_time = lease_time;
+		clp->cl_last_renewal = jiffies;
+	}
+	spin_unlock(&clp->cl_lock);
+
+	ret = nfs41_check_session_ready(clp);
+	if (ret)
+		return ret;
+	/* Test for the DS role */
+	if (!is_ds_client(clp))
+		return -ENODEV;
+	return 0;
+}
+EXPORT_SYMBOL_GPL(nfs4_init_ds_session);
+
+
diff --git a/fs/nfs/nfs4session.h b/fs/nfs/nfs4session.h
new file mode 100644
index 00000000000..6f3cb39386d
--- /dev/null
+++ b/fs/nfs/nfs4session.h
@@ -0,0 +1,142 @@
+/*
+ * fs/nfs/nfs4session.h
+ *
+ * Copyright (c) 2012 Trond Myklebust <Trond.Myklebust@netapp.com>
+ *
+ */
+#ifndef __LINUX_FS_NFS_NFS4SESSION_H
+#define __LINUX_FS_NFS_NFS4SESSION_H
+
+/* maximum number of slots to use */
+#define NFS4_DEF_SLOT_TABLE_SIZE (16U)
+#define NFS4_MAX_SLOT_TABLE (1024U)
+#define NFS4_NO_SLOT ((u32)-1)
+
+#if IS_ENABLED(CONFIG_NFS_V4)
+
+/* Sessions slot seqid */
+struct nfs4_slot {
+	struct nfs4_slot_table	*table;
+	struct nfs4_slot	*next;
+	unsigned long		generation;
+	u32			slot_nr;
+	u32		 	seq_nr;
+	unsigned int		interrupted : 1;
+};
+
+/* Sessions */
+#define SLOT_TABLE_SZ DIV_ROUND_UP(NFS4_MAX_SLOT_TABLE, 8*sizeof(long))
+struct nfs4_slot_table {
+	struct nfs4_session *session;		/* Parent session */
+	struct nfs4_slot *slots;		/* seqid per slot */
+	unsigned long   used_slots[SLOT_TABLE_SZ]; /* used/unused bitmap */
+	spinlock_t	slot_tbl_lock;
+	struct rpc_wait_queue	slot_tbl_waitq;	/* allocators may wait here */
+	u32		max_slots;		/* # slots in table */
+	u32		max_slotid;		/* Max allowed slotid value */
+	u32		highest_used_slotid;	/* sent to server on each SEQ.
+						 * op for dynamic resizing */
+	u32		target_highest_slotid;	/* Server max_slot target */
+	u32		server_highest_slotid;	/* Server highest slotid */
+	s32		d_target_highest_slotid; /* Derivative */
+	s32		d2_target_highest_slotid; /* 2nd derivative */
+	unsigned long	generation;		/* Generation counter for
+						   target_highest_slotid */
+	struct completion complete;
+};
+
+/*
+ * Session related parameters
+ */
+struct nfs4_session {
+	struct nfs4_sessionid		sess_id;
+	u32				flags;
+	unsigned long			session_state;
+	u32				hash_alg;
+	u32				ssv_len;
+
+	/* The fore and back channel */
+	struct nfs4_channel_attrs	fc_attrs;
+	struct nfs4_slot_table		fc_slot_table;
+	struct nfs4_channel_attrs	bc_attrs;
+	struct nfs4_slot_table		bc_slot_table;
+	struct nfs_client		*clp;
+	/* Create session arguments */
+	unsigned int			fc_target_max_rqst_sz;
+	unsigned int			fc_target_max_resp_sz;
+};
+
+enum nfs4_session_state {
+	NFS4_SESSION_INITING,
+	NFS4_SESSION_DRAINING,
+};
+
+#if defined(CONFIG_NFS_V4_1)
+extern struct nfs4_slot *nfs4_alloc_slot(struct nfs4_slot_table *tbl);
+extern void nfs4_free_slot(struct nfs4_slot_table *tbl, struct nfs4_slot *slot);
+
+extern void nfs41_set_target_slotid(struct nfs4_slot_table *tbl,
+		u32 target_highest_slotid);
+extern void nfs41_update_target_slotid(struct nfs4_slot_table *tbl,
+		struct nfs4_slot *slot,
+		struct nfs4_sequence_res *res);
+
+extern int nfs4_setup_session_slot_tables(struct nfs4_session *ses);
+
+extern struct nfs4_session *nfs4_alloc_session(struct nfs_client *clp);
+extern void nfs4_destroy_session(struct nfs4_session *session);
+extern int nfs4_init_session(struct nfs_server *server);
+extern int nfs4_init_ds_session(struct nfs_client *, unsigned long);
+
+extern void nfs4_session_drain_complete(struct nfs4_session *session,
+		struct nfs4_slot_table *tbl);
+
+static inline bool nfs4_session_draining(struct nfs4_session *session)
+{
+	return !!test_bit(NFS4_SESSION_DRAINING, &session->session_state);
+}
+
+bool nfs41_wake_and_assign_slot(struct nfs4_slot_table *tbl,
+		struct nfs4_slot *slot);
+void nfs41_wake_slot_table(struct nfs4_slot_table *tbl);
+
+/*
+ * Determine if sessions are in use.
+ */
+static inline int nfs4_has_session(const struct nfs_client *clp)
+{
+	if (clp->cl_session)
+		return 1;
+	return 0;
+}
+
+static inline int nfs4_has_persistent_session(const struct nfs_client *clp)
+{
+	if (nfs4_has_session(clp))
+		return (clp->cl_session->flags & SESSION4_PERSIST);
+	return 0;
+}
+
+#else /* defined(CONFIG_NFS_V4_1) */
+
+static inline int nfs4_init_session(struct nfs_server *server)
+{
+	return 0;
+}
+
+/*
+ * Determine if sessions are in use.
+ */
+static inline int nfs4_has_session(const struct nfs_client *clp)
+{
+	return 0;
+}
+
+static inline int nfs4_has_persistent_session(const struct nfs_client *clp)
+{
+	return 0;
+}
+
+#endif /* defined(CONFIG_NFS_V4_1) */
+#endif /* IS_ENABLED(CONFIG_NFS_V4) */
+#endif /* __LINUX_FS_NFS_NFS4SESSION_H */
diff --git a/fs/nfs/nfs4state.c b/fs/nfs/nfs4state.c
index f38300e9f17..e61f68d5ef2 100644
--- a/fs/nfs/nfs4state.c
+++ b/fs/nfs/nfs4state.c
@@ -51,19 +51,22 @@
 #include <linux/bitops.h>
 #include <linux/jiffies.h>
 
+#include <linux/sunrpc/clnt.h>
+
 #include "nfs4_fs.h"
 #include "callback.h"
 #include "delegation.h"
 #include "internal.h"
+#include "nfs4session.h"
 #include "pnfs.h"
+#include "netns.h"
 
 #define NFSDBG_FACILITY		NFSDBG_STATE
 
 #define OPENOWNER_POOL_SIZE	8
 
 const nfs4_stateid zero_stateid;
-
-static LIST_HEAD(nfs4_clientid_list);
+static DEFINE_MUTEX(nfs_clid_init_mutex);
 
 int nfs4_init_clientid(struct nfs_client *clp, struct rpc_cred *cred)
 {
@@ -73,12 +76,13 @@ int nfs4_init_clientid(struct nfs_client *clp, struct rpc_cred *cred)
 	};
 	unsigned short port;
 	int status;
+	struct nfs_net *nn = net_generic(clp->cl_net, nfs_net_id);
 
 	if (test_bit(NFS4CLNT_LEASE_CONFIRM, &clp->cl_state))
 		goto do_confirm;
-	port = nfs_callback_tcpport;
+	port = nn->nfs_callback_tcpport;
 	if (clp->cl_addr.ss_family == AF_INET6)
-		port = nfs_callback_tcpport6;
+		port = nn->nfs_callback_tcpport6;
 
 	status = nfs4_proc_setclientid(clp, NFS4_CALLBACK, port, cred, &clid);
 	if (status != 0)
@@ -96,6 +100,51 @@ out:
 	return status;
 }
 
+/**
+ * nfs40_discover_server_trunking - Detect server IP address trunking (mv0)
+ *
+ * @clp: nfs_client under test
+ * @result: OUT: found nfs_client, or clp
+ * @cred: credential to use for trunking test
+ *
+ * Returns zero, a negative errno, or a negative NFS4ERR status.
+ * If zero is returned, an nfs_client pointer is planted in
+ * "result".
+ *
+ * Note: The returned client may not yet be marked ready.
+ */
+int nfs40_discover_server_trunking(struct nfs_client *clp,
+				   struct nfs_client **result,
+				   struct rpc_cred *cred)
+{
+	struct nfs4_setclientid_res clid = {
+		.clientid = clp->cl_clientid,
+		.confirm = clp->cl_confirm,
+	};
+	struct nfs_net *nn = net_generic(clp->cl_net, nfs_net_id);
+	unsigned short port;
+	int status;
+
+	port = nn->nfs_callback_tcpport;
+	if (clp->cl_addr.ss_family == AF_INET6)
+		port = nn->nfs_callback_tcpport6;
+
+	status = nfs4_proc_setclientid(clp, NFS4_CALLBACK, port, cred, &clid);
+	if (status != 0)
+		goto out;
+	clp->cl_clientid = clid.clientid;
+	clp->cl_confirm = clid.confirm;
+
+	status = nfs40_walk_client_list(clp, result, cred);
+	if (status == 0) {
+		/* Sustain the lease, even if it's empty.  If the clientid4
+		 * goes stale it's of no use for trunking discovery. */
+		nfs4_schedule_state_renewal(*result);
+	}
+out:
+	return status;
+}
+
 struct rpc_cred *nfs4_get_machine_cred_locked(struct nfs_client *clp)
 {
 	struct rpc_cred *cred = NULL;
@@ -200,24 +249,27 @@ static void nfs4_end_drain_session(struct nfs_client *clp)
 {
 	struct nfs4_session *ses = clp->cl_session;
 	struct nfs4_slot_table *tbl;
-	int max_slots;
 
 	if (ses == NULL)
 		return;
 	tbl = &ses->fc_slot_table;
 	if (test_and_clear_bit(NFS4_SESSION_DRAINING, &ses->session_state)) {
 		spin_lock(&tbl->slot_tbl_lock);
-		max_slots = tbl->max_slots;
-		while (max_slots--) {
-			if (rpc_wake_up_first(&tbl->slot_tbl_waitq,
-						nfs4_set_task_privileged,
-						NULL) == NULL)
-				break;
-		}
+		nfs41_wake_slot_table(tbl);
 		spin_unlock(&tbl->slot_tbl_lock);
 	}
 }
 
+/*
+ * Signal state manager thread if session fore channel is drained
+ */
+void nfs4_session_drain_complete(struct nfs4_session *session,
+		struct nfs4_slot_table *tbl)
+{
+	if (nfs4_session_draining(session))
+		complete(&tbl->complete);
+}
+
 static int nfs4_wait_on_slot_tbl(struct nfs4_slot_table *tbl)
 {
 	spin_lock(&tbl->slot_tbl_lock);
@@ -249,7 +301,6 @@ static void nfs41_finish_session_reset(struct nfs_client *clp)
 	clear_bit(NFS4CLNT_LEASE_CONFIRM, &clp->cl_state);
 	clear_bit(NFS4CLNT_SESSION_RESET, &clp->cl_state);
 	/* create_session negotiated new slot table */
-	clear_bit(NFS4CLNT_RECALL_SLOT, &clp->cl_state);
 	clear_bit(NFS4CLNT_BIND_CONN_TO_SESSION, &clp->cl_state);
 	nfs41_setup_state_renewal(clp);
 }
@@ -275,6 +326,33 @@ out:
 	return status;
 }
 
+/**
+ * nfs41_discover_server_trunking - Detect server IP address trunking (mv1)
+ *
+ * @clp: nfs_client under test
+ * @result: OUT: found nfs_client, or clp
+ * @cred: credential to use for trunking test
+ *
+ * Returns NFS4_OK, a negative errno, or a negative NFS4ERR status.
+ * If NFS4_OK is returned, an nfs_client pointer is planted in
+ * "result".
+ *
+ * Note: The returned client may not yet be marked ready.
+ */
+int nfs41_discover_server_trunking(struct nfs_client *clp,
+				   struct nfs_client **result,
+				   struct rpc_cred *cred)
+{
+	int status;
+
+	status = nfs4_proc_exchange_id(clp, cred);
+	if (status != NFS4_OK)
+		return status;
+	set_bit(NFS4CLNT_LEASE_CONFIRM, &clp->cl_state);
+
+	return nfs41_walk_client_list(clp, result, cred);
+}
+
 struct rpc_cred *nfs4_get_exchange_id_cred(struct nfs_client *clp)
 {
 	struct rpc_cred *cred;
@@ -729,11 +807,8 @@ static void __nfs4_close(struct nfs4_state *state,
 	if (!call_close) {
 		nfs4_put_open_state(state);
 		nfs4_put_state_owner(owner);
-	} else {
-		bool roc = pnfs_roc(state->inode);
-
-		nfs4_do_close(state, gfp_mask, wait, roc);
-	}
+	} else
+		nfs4_do_close(state, gfp_mask, wait);
 }
 
 void nfs4_close_state(struct nfs4_state *state, fmode_t fmode)
@@ -865,7 +940,7 @@ void nfs4_put_lock_state(struct nfs4_lock_state *lsp)
 	if (list_empty(&state->lock_states))
 		clear_bit(LK_STATE_IN_USE, &state->flags);
 	spin_unlock(&state->state_lock);
-	if (lsp->ls_flags & NFS_LOCK_INITIALIZED) {
+	if (test_bit(NFS_LOCK_INITIALIZED, &lsp->ls_flags)) {
 		if (nfs4_release_lockowner(lsp) == 0)
 			return;
 	}
@@ -911,17 +986,25 @@ int nfs4_set_lock_state(struct nfs4_state *state, struct file_lock *fl)
 }
 
 static bool nfs4_copy_lock_stateid(nfs4_stateid *dst, struct nfs4_state *state,
-		fl_owner_t fl_owner, pid_t fl_pid)
+		const struct nfs_lockowner *lockowner)
 {
 	struct nfs4_lock_state *lsp;
+	fl_owner_t fl_owner;
+	pid_t fl_pid;
 	bool ret = false;
 
+
+	if (lockowner == NULL)
+		goto out;
+
 	if (test_bit(LK_STATE_IN_USE, &state->flags) == 0)
 		goto out;
 
+	fl_owner = lockowner->l_owner;
+	fl_pid = lockowner->l_pid;
 	spin_lock(&state->state_lock);
 	lsp = __nfs4_find_lock_state(state, fl_owner, fl_pid, NFS4_ANY_LOCK_TYPE);
-	if (lsp != NULL && (lsp->ls_flags & NFS_LOCK_INITIALIZED) != 0) {
+	if (lsp != NULL && test_bit(NFS_LOCK_INITIALIZED, &lsp->ls_flags) != 0) {
 		nfs4_stateid_copy(dst, &lsp->ls_stateid);
 		ret = true;
 	}
@@ -946,11 +1029,11 @@ static void nfs4_copy_open_stateid(nfs4_stateid *dst, struct nfs4_state *state)
  * requests.
  */
 void nfs4_select_rw_stateid(nfs4_stateid *dst, struct nfs4_state *state,
-		fmode_t fmode, fl_owner_t fl_owner, pid_t fl_pid)
+		fmode_t fmode, const struct nfs_lockowner *lockowner)
 {
 	if (nfs4_copy_delegation_stateid(dst, state->inode, fmode))
 		return;
-	if (nfs4_copy_lock_stateid(dst, state, fl_owner, fl_pid))
+	if (nfs4_copy_lock_stateid(dst, state, lockowner))
 		return;
 	nfs4_copy_open_stateid(dst, state);
 }
@@ -1000,7 +1083,6 @@ void nfs_free_seqid(struct nfs_seqid *seqid)
  */
 static void nfs_increment_seqid(int status, struct nfs_seqid *seqid)
 {
-	BUG_ON(list_first_entry(&seqid->sequence->list, struct nfs_seqid, list) != seqid);
 	switch (status) {
 		case 0:
 			break;
@@ -1123,6 +1205,40 @@ void nfs4_schedule_lease_recovery(struct nfs_client *clp)
 }
 EXPORT_SYMBOL_GPL(nfs4_schedule_lease_recovery);
 
+int nfs4_wait_clnt_recover(struct nfs_client *clp)
+{
+	int res;
+
+	might_sleep();
+
+	res = wait_on_bit(&clp->cl_state, NFS4CLNT_MANAGER_RUNNING,
+			nfs_wait_bit_killable, TASK_KILLABLE);
+	if (res)
+		return res;
+
+	if (clp->cl_cons_state < 0)
+		return clp->cl_cons_state;
+	return 0;
+}
+
+int nfs4_client_recover_expired_lease(struct nfs_client *clp)
+{
+	unsigned int loop;
+	int ret;
+
+	for (loop = NFS4_MAX_LOOP_ON_RECOVER; loop != 0; loop--) {
+		ret = nfs4_wait_clnt_recover(clp);
+		if (ret != 0)
+			break;
+		if (!test_bit(NFS4CLNT_LEASE_EXPIRED, &clp->cl_state) &&
+		    !test_bit(NFS4CLNT_CHECK_LEASE,&clp->cl_state))
+			break;
+		nfs4_schedule_state_manager(clp);
+		ret = -EIO;
+	}
+	return ret;
+}
+
 /*
  * nfs40_handle_cb_pathdown - return all delegations after NFS4ERR_CB_PATH_DOWN
  * @clp: client to process
@@ -1289,7 +1405,7 @@ restart:
 			if (status >= 0) {
 				spin_lock(&state->state_lock);
 				list_for_each_entry(lock, &state->lock_states, ls_locks) {
-					if (!(lock->ls_flags & NFS_LOCK_INITIALIZED))
+					if (!test_bit(NFS_LOCK_INITIALIZED, &lock->ls_flags))
 						pr_warn_ratelimited("NFS: "
 							"%s: Lock reclaim "
 							"failed!\n", __func__);
@@ -1315,14 +1431,6 @@ restart:
 				/* Mark the file as being 'closed' */
 				state->state = 0;
 				break;
-			case -EKEYEXPIRED:
-				/*
-				 * User RPCSEC_GSS context has expired.
-				 * We cannot recover this stateid now, so
-				 * skip it and allow recovery thread to
-				 * proceed.
-				 */
-				break;
 			case -NFS4ERR_ADMIN_REVOKED:
 			case -NFS4ERR_STALE_STATEID:
 			case -NFS4ERR_BAD_STATEID:
@@ -1361,7 +1469,7 @@ static void nfs4_clear_open_state(struct nfs4_state *state)
 	spin_lock(&state->state_lock);
 	list_for_each_entry(lock, &state->lock_states, ls_locks) {
 		lock->ls_seqid.flags = 0;
-		lock->ls_flags &= ~NFS_LOCK_INITIALIZED;
+		clear_bit(NFS_LOCK_INITIALIZED, &lock->ls_flags);
 	}
 	spin_unlock(&state->state_lock);
 }
@@ -1475,14 +1583,6 @@ static void nfs4_state_start_reclaim_nograce(struct nfs_client *clp)
 	nfs4_state_mark_reclaim_helper(clp, nfs4_state_mark_reclaim_nograce);
 }
 
-static void nfs4_warn_keyexpired(const char *s)
-{
-	printk_ratelimited(KERN_WARNING "Error: state manager"
-			" encountered RPCSEC_GSS session"
-			" expired against NFSv4 server %s.\n",
-			s);
-}
-
 static int nfs4_recovery_handle_error(struct nfs_client *clp, int error)
 {
 	switch (error) {
@@ -1516,10 +1616,6 @@ static int nfs4_recovery_handle_error(struct nfs_client *clp, int error)
 		case -NFS4ERR_CONN_NOT_BOUND_TO_SESSION:
 			set_bit(NFS4CLNT_BIND_CONN_TO_SESSION, &clp->cl_state);
 			break;
-		case -EKEYEXPIRED:
-			/* Nothing we can do */
-			nfs4_warn_keyexpired(clp->cl_hostname);
-			break;
 		default:
 			dprintk("%s: failed to handle error %d for server %s\n",
 					__func__, error, clp->cl_hostname);
@@ -1595,8 +1691,8 @@ out:
 	return nfs4_recovery_handle_error(clp, status);
 }
 
-/* Set NFS4CLNT_LEASE_EXPIRED for all v4.0 errors and for recoverable errors
- * on EXCHANGE_ID for v4.1
+/* Set NFS4CLNT_LEASE_EXPIRED and reclaim reboot state for all v4.0 errors
+ * and for recoverable errors on EXCHANGE_ID for v4.1
  */
 static int nfs4_handle_reclaim_lease_error(struct nfs_client *clp, int status)
 {
@@ -1606,10 +1702,19 @@ static int nfs4_handle_reclaim_lease_error(struct nfs_client *clp, int status)
 			return -ESERVERFAULT;
 		/* Lease confirmation error: retry after purging the lease */
 		ssleep(1);
-	case -NFS4ERR_CLID_INUSE:
+		clear_bit(NFS4CLNT_LEASE_CONFIRM, &clp->cl_state);
+		break;
 	case -NFS4ERR_STALE_CLIENTID:
 		clear_bit(NFS4CLNT_LEASE_CONFIRM, &clp->cl_state);
+		nfs4_state_clear_reclaim_reboot(clp);
+		nfs4_state_start_reclaim_reboot(clp);
 		break;
+	case -NFS4ERR_CLID_INUSE:
+		pr_err("NFS: Server %s reports our clientid is in use\n",
+			clp->cl_hostname);
+		nfs_mark_client_ready(clp, -EPERM);
+		clear_bit(NFS4CLNT_LEASE_CONFIRM, &clp->cl_state);
+		return -EPERM;
 	case -EACCES:
 		if (clp->cl_machine_cred == NULL)
 			return -EACCES;
@@ -1627,8 +1732,6 @@ static int nfs4_handle_reclaim_lease_error(struct nfs_client *clp, int status)
 		dprintk("%s: exit with error %d for server %s\n",
 				__func__, -EPROTONOSUPPORT, clp->cl_hostname);
 		return -EPROTONOSUPPORT;
-	case -EKEYEXPIRED:
-		nfs4_warn_keyexpired(clp->cl_hostname);
 	case -NFS4ERR_NOT_SAME: /* FixMe: implement recovery
 				 * in nfs4_exchange_id */
 	default:
@@ -1642,7 +1745,7 @@ static int nfs4_handle_reclaim_lease_error(struct nfs_client *clp, int status)
 	return 0;
 }
 
-static int nfs4_reclaim_lease(struct nfs_client *clp)
+static int nfs4_establish_lease(struct nfs_client *clp)
 {
 	struct rpc_cred *cred;
 	const struct nfs4_state_recovery_ops *ops =
@@ -1655,10 +1758,147 @@ static int nfs4_reclaim_lease(struct nfs_client *clp)
 	status = ops->establish_clid(clp, cred);
 	put_rpccred(cred);
 	if (status != 0)
+		return status;
+	pnfs_destroy_all_layouts(clp);
+	return 0;
+}
+
+/*
+ * Returns zero or a negative errno.  NFS4ERR values are converted
+ * to local errno values.
+ */
+static int nfs4_reclaim_lease(struct nfs_client *clp)
+{
+	int status;
+
+	status = nfs4_establish_lease(clp);
+	if (status < 0)
 		return nfs4_handle_reclaim_lease_error(clp, status);
+	if (test_and_clear_bit(NFS4CLNT_SERVER_SCOPE_MISMATCH, &clp->cl_state))
+		nfs4_state_start_reclaim_nograce(clp);
+	if (!test_bit(NFS4CLNT_RECLAIM_NOGRACE, &clp->cl_state))
+		set_bit(NFS4CLNT_RECLAIM_REBOOT, &clp->cl_state);
+	clear_bit(NFS4CLNT_CHECK_LEASE, &clp->cl_state);
+	clear_bit(NFS4CLNT_LEASE_EXPIRED, &clp->cl_state);
+	return 0;
+}
+
+static int nfs4_purge_lease(struct nfs_client *clp)
+{
+	int status;
+
+	status = nfs4_establish_lease(clp);
+	if (status < 0)
+		return nfs4_handle_reclaim_lease_error(clp, status);
+	clear_bit(NFS4CLNT_PURGE_STATE, &clp->cl_state);
+	set_bit(NFS4CLNT_LEASE_EXPIRED, &clp->cl_state);
+	nfs4_state_start_reclaim_nograce(clp);
 	return 0;
 }
 
+/**
+ * nfs4_discover_server_trunking - Detect server IP address trunking
+ *
+ * @clp: nfs_client under test
+ * @result: OUT: found nfs_client, or clp
+ *
+ * Returns zero or a negative errno.  If zero is returned,
+ * an nfs_client pointer is planted in "result".
+ *
+ * Note: since we are invoked in process context, and
+ * not from inside the state manager, we cannot use
+ * nfs4_handle_reclaim_lease_error().
+ */
+int nfs4_discover_server_trunking(struct nfs_client *clp,
+				  struct nfs_client **result)
+{
+	const struct nfs4_state_recovery_ops *ops =
+				clp->cl_mvops->reboot_recovery_ops;
+	rpc_authflavor_t *flavors, flav, save;
+	struct rpc_clnt *clnt;
+	struct rpc_cred *cred;
+	int i, len, status;
+
+	dprintk("NFS: %s: testing '%s'\n", __func__, clp->cl_hostname);
+
+	len = NFS_MAX_SECFLAVORS;
+	flavors = kcalloc(len, sizeof(*flavors), GFP_KERNEL);
+	if (flavors == NULL) {
+		status = -ENOMEM;
+		goto out;
+	}
+	len = rpcauth_list_flavors(flavors, len);
+	if (len < 0) {
+		status = len;
+		goto out_free;
+	}
+	clnt = clp->cl_rpcclient;
+	save = clnt->cl_auth->au_flavor;
+	i = 0;
+
+	mutex_lock(&nfs_clid_init_mutex);
+	status  = -ENOENT;
+again:
+	cred = ops->get_clid_cred(clp);
+	if (cred == NULL)
+		goto out_unlock;
+
+	status = ops->detect_trunking(clp, result, cred);
+	put_rpccred(cred);
+	switch (status) {
+	case 0:
+		break;
+
+	case -EACCES:
+		if (clp->cl_machine_cred == NULL)
+			break;
+		/* Handle case where the user hasn't set up machine creds */
+		nfs4_clear_machine_cred(clp);
+	case -NFS4ERR_DELAY:
+	case -ETIMEDOUT:
+	case -EAGAIN:
+		ssleep(1);
+	case -NFS4ERR_STALE_CLIENTID:
+		dprintk("NFS: %s after status %d, retrying\n",
+			__func__, status);
+		goto again;
+
+	case -NFS4ERR_CLID_INUSE:
+	case -NFS4ERR_WRONGSEC:
+		status = -EPERM;
+		if (i >= len)
+			break;
+
+		flav = flavors[i++];
+		if (flav == save)
+			flav = flavors[i++];
+		clnt = rpc_clone_client_set_auth(clnt, flav);
+		if (IS_ERR(clnt)) {
+			status = PTR_ERR(clnt);
+			break;
+		}
+		clp->cl_rpcclient = clnt;
+		goto again;
+
+	case -NFS4ERR_MINOR_VERS_MISMATCH:
+		status = -EPROTONOSUPPORT;
+		break;
+
+	case -EKEYEXPIRED:
+	case -NFS4ERR_NOT_SAME: /* FixMe: implement recovery
+				 * in nfs4_exchange_id */
+		status = -EKEYEXPIRED;
+	}
+
+out_unlock:
+	mutex_unlock(&nfs_clid_init_mutex);
+out_free:
+	kfree(flavors);
+out:
+	dprintk("NFS: %s: status = %d\n", __func__, status);
+	return status;
+}
+
 #ifdef CONFIG_NFS_V4_1
 void nfs4_schedule_session_recovery(struct nfs4_session *session, int err)
 {
@@ -1675,14 +1915,23 @@ void nfs4_schedule_session_recovery(struct nfs4_session *session, int err)
 }
 EXPORT_SYMBOL_GPL(nfs4_schedule_session_recovery);
 
-void nfs41_handle_recall_slot(struct nfs_client *clp)
+static void nfs41_ping_server(struct nfs_client *clp)
 {
-	set_bit(NFS4CLNT_RECALL_SLOT, &clp->cl_state);
-	dprintk("%s: scheduling slot recall for server %s\n", __func__,
-			clp->cl_hostname);
+	/* Use CHECK_LEASE to ping the server with a SEQUENCE */
+	set_bit(NFS4CLNT_CHECK_LEASE, &clp->cl_state);
 	nfs4_schedule_state_manager(clp);
 }
 
+void nfs41_server_notify_target_slotid_update(struct nfs_client *clp)
+{
+	nfs41_ping_server(clp);
+}
+
+void nfs41_server_notify_highest_slotid_update(struct nfs_client *clp)
+{
+	nfs41_ping_server(clp);
+}
+
 static void nfs4_reset_all_state(struct nfs_client *clp)
 {
 	if (test_and_set_bit(NFS4CLNT_LEASE_EXPIRED, &clp->cl_state) == 0) {
@@ -1764,11 +2013,23 @@ static int nfs4_reset_session(struct nfs_client *clp)
 	struct rpc_cred *cred;
 	int status;
 
+	if (!nfs4_has_session(clp))
+		return 0;
 	nfs4_begin_drain_session(clp);
 	cred = nfs4_get_exchange_id_cred(clp);
 	status = nfs4_proc_destroy_session(clp->cl_session, cred);
-	if (status && status != -NFS4ERR_BADSESSION &&
-	    status != -NFS4ERR_DEADSESSION) {
+	switch (status) {
+	case 0:
+	case -NFS4ERR_BADSESSION:
+	case -NFS4ERR_DEADSESSION:
+		break;
+	case -NFS4ERR_BACK_CHAN_BUSY:
+	case -NFS4ERR_DELAY:
+		set_bit(NFS4CLNT_SESSION_RESET, &clp->cl_state);
+		status = 0;
+		ssleep(1);
+		goto out;
+	default:
 		status = nfs4_recovery_handle_error(clp, status);
 		goto out;
 	}
@@ -1790,39 +2051,13 @@ out:
 	return status;
 }
 
-static int nfs4_recall_slot(struct nfs_client *clp)
-{
-	struct nfs4_slot_table *fc_tbl = &clp->cl_session->fc_slot_table;
-	struct nfs4_channel_attrs *fc_attrs = &clp->cl_session->fc_attrs;
-	struct nfs4_slot *new, *old;
-	int i;
-
-	nfs4_begin_drain_session(clp);
-	new = kmalloc(fc_tbl->target_max_slots * sizeof(struct nfs4_slot),
-		      GFP_NOFS);
-        if (!new)
-		return -ENOMEM;
-
-	spin_lock(&fc_tbl->slot_tbl_lock);
-	for (i = 0; i < fc_tbl->target_max_slots; i++)
-		new[i].seq_nr = fc_tbl->slots[i].seq_nr;
-	old = fc_tbl->slots;
-	fc_tbl->slots = new;
-	fc_tbl->max_slots = fc_tbl->target_max_slots;
-	fc_tbl->target_max_slots = 0;
-	fc_attrs->max_reqs = fc_tbl->max_slots;
-	spin_unlock(&fc_tbl->slot_tbl_lock);
-
-	kfree(old);
-	nfs4_end_drain_session(clp);
-	return 0;
-}
-
 static int nfs4_bind_conn_to_session(struct nfs_client *clp)
 {
 	struct rpc_cred *cred;
 	int ret;
 
+	if (!nfs4_has_session(clp))
+		return 0;
 	nfs4_begin_drain_session(clp);
 	cred = nfs4_get_exchange_id_cred(clp);
 	ret = nfs4_proc_bind_conn_to_session(clp, cred);
@@ -1846,7 +2081,6 @@ static int nfs4_bind_conn_to_session(struct nfs_client *clp)
 #else /* CONFIG_NFS_V4_1 */
 static int nfs4_reset_session(struct nfs_client *clp) { return 0; }
 static int nfs4_end_drain_session(struct nfs_client *clp) { return 0; }
-static int nfs4_recall_slot(struct nfs_client *clp) { return 0; }
 
 static int nfs4_bind_conn_to_session(struct nfs_client *clp)
 {
@@ -1857,47 +2091,30 @@ static int nfs4_bind_conn_to_session(struct nfs_client *clp)
 static void nfs4_state_manager(struct nfs_client *clp)
 {
 	int status = 0;
+	const char *section = "", *section_sep = "";
 
 	/* Ensure exclusive access to NFSv4 state */
 	do {
 		if (test_bit(NFS4CLNT_PURGE_STATE, &clp->cl_state)) {
-			status = nfs4_reclaim_lease(clp);
+			section = "purge state";
+			status = nfs4_purge_lease(clp);
 			if (status < 0)
 				goto out_error;
-			clear_bit(NFS4CLNT_PURGE_STATE, &clp->cl_state);
-			set_bit(NFS4CLNT_LEASE_EXPIRED, &clp->cl_state);
+			continue;
 		}
 
-		if (test_and_clear_bit(NFS4CLNT_LEASE_EXPIRED, &clp->cl_state)) {
+		if (test_bit(NFS4CLNT_LEASE_EXPIRED, &clp->cl_state)) {
+			section = "lease expired";
 			/* We're going to have to re-establish a clientid */
 			status = nfs4_reclaim_lease(clp);
 			if (status < 0)
 				goto out_error;
-			if (test_bit(NFS4CLNT_LEASE_EXPIRED, &clp->cl_state))
-				continue;
-			clear_bit(NFS4CLNT_CHECK_LEASE, &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);
-		}
-
-		if (test_and_clear_bit(NFS4CLNT_CHECK_LEASE, &clp->cl_state)) {
-			status = nfs4_check_lease(clp);
-			if (status < 0)
-				goto out_error;
-			if (test_bit(NFS4CLNT_LEASE_EXPIRED, &clp->cl_state))
-				continue;
+			continue;
 		}
 
 		/* Initialize or reset the session */
-		if (test_and_clear_bit(NFS4CLNT_SESSION_RESET, &clp->cl_state)
-		   && nfs4_has_session(clp)) {
+		if (test_and_clear_bit(NFS4CLNT_SESSION_RESET, &clp->cl_state)) {
+			section = "reset session";
 			status = nfs4_reset_session(clp);
 			if (test_bit(NFS4CLNT_LEASE_EXPIRED, &clp->cl_state))
 				continue;
@@ -1907,15 +2124,25 @@ static void nfs4_state_manager(struct nfs_client *clp)
 
 		/* Send BIND_CONN_TO_SESSION */
 		if (test_and_clear_bit(NFS4CLNT_BIND_CONN_TO_SESSION,
-				&clp->cl_state) && nfs4_has_session(clp)) {
+				&clp->cl_state)) {
+			section = "bind conn to session";
 			status = nfs4_bind_conn_to_session(clp);
 			if (status < 0)
 				goto out_error;
 			continue;
 		}
 
+		if (test_and_clear_bit(NFS4CLNT_CHECK_LEASE, &clp->cl_state)) {
+			section = "check lease";
+			status = nfs4_check_lease(clp);
+			if (status < 0)
+				goto out_error;
+			continue;
+		}
+
 		/* First recover reboot state... */
 		if (test_bit(NFS4CLNT_RECLAIM_REBOOT, &clp->cl_state)) {
+			section = "reclaim reboot";
 			status = nfs4_do_reclaim(clp,
 				clp->cl_mvops->reboot_recovery_ops);
 			if (test_bit(NFS4CLNT_LEASE_EXPIRED, &clp->cl_state) ||
@@ -1930,6 +2157,7 @@ static void nfs4_state_manager(struct nfs_client *clp)
 
 		/* Now recover expired state... */
 		if (test_and_clear_bit(NFS4CLNT_RECLAIM_NOGRACE, &clp->cl_state)) {
+			section = "reclaim nograce";
 			status = nfs4_do_reclaim(clp,
 				clp->cl_mvops->nograce_recovery_ops);
 			if (test_bit(NFS4CLNT_LEASE_EXPIRED, &clp->cl_state) ||
@@ -1945,15 +2173,6 @@ static void nfs4_state_manager(struct nfs_client *clp)
 			nfs_client_return_marked_delegations(clp);
 			continue;
 		}
-		/* Recall session slots */
-		if (test_and_clear_bit(NFS4CLNT_RECALL_SLOT, &clp->cl_state)
-		   && nfs4_has_session(clp)) {
-			status = nfs4_recall_slot(clp);
-			if (status < 0)
-				goto out_error;
-			continue;
-		}
-
 
 		nfs4_clear_state_manager_bit(clp);
 		/* Did we race with an attempt to give us more work? */
@@ -1964,8 +2183,12 @@ static void nfs4_state_manager(struct nfs_client *clp)
 	} while (atomic_read(&clp->cl_count) > 1);
 	return;
 out_error:
-	pr_warn_ratelimited("NFS: state manager failed on NFSv4 server %s"
-			" with error %d\n", clp->cl_hostname, -status);
+	if (strlen(section))
+		section_sep = ": ";
+	pr_warn_ratelimited("NFS: state manager%s%s failed on NFSv4 server %s"
+			" with error %d\n", section_sep, section,
+			clp->cl_hostname, -status);
+	ssleep(1);
 	nfs4_end_drain_session(clp);
 	nfs4_clear_state_manager_bit(clp);
 }
diff --git a/fs/nfs/nfs4super.c b/fs/nfs/nfs4super.c
new file mode 100644
index 00000000000..84d2e9e2f31
--- /dev/null
+++ b/fs/nfs/nfs4super.c
@@ -0,0 +1,358 @@
+/*
+ * Copyright (c) 2012 Bryan Schumaker <bjschuma@netapp.com>
+ */
+#include <linux/init.h>
+#include <linux/module.h>
+#include <linux/nfs_idmap.h>
+#include <linux/nfs4_mount.h>
+#include <linux/nfs_fs.h>
+#include "delegation.h"
+#include "internal.h"
+#include "nfs4_fs.h"
+#include "pnfs.h"
+#include "nfs.h"
+
+#define NFSDBG_FACILITY		NFSDBG_VFS
+
+static int nfs4_write_inode(struct inode *inode, struct writeback_control *wbc);
+static void nfs4_evict_inode(struct inode *inode);
+static struct dentry *nfs4_remote_mount(struct file_system_type *fs_type,
+	int flags, const char *dev_name, void *raw_data);
+static struct dentry *nfs4_referral_mount(struct file_system_type *fs_type,
+	int flags, const char *dev_name, void *raw_data);
+static struct dentry *nfs4_remote_referral_mount(struct file_system_type *fs_type,
+	int flags, const char *dev_name, void *raw_data);
+
+static struct file_system_type nfs4_remote_fs_type = {
+	.owner		= THIS_MODULE,
+	.name		= "nfs4",
+	.mount		= nfs4_remote_mount,
+	.kill_sb	= nfs_kill_super,
+	.fs_flags	= FS_RENAME_DOES_D_MOVE|FS_REVAL_DOT|FS_BINARY_MOUNTDATA,
+};
+
+static struct file_system_type nfs4_remote_referral_fs_type = {
+	.owner		= THIS_MODULE,
+	.name		= "nfs4",
+	.mount		= nfs4_remote_referral_mount,
+	.kill_sb	= nfs_kill_super,
+	.fs_flags	= FS_RENAME_DOES_D_MOVE|FS_REVAL_DOT|FS_BINARY_MOUNTDATA,
+};
+
+struct file_system_type nfs4_referral_fs_type = {
+	.owner		= THIS_MODULE,
+	.name		= "nfs4",
+	.mount		= nfs4_referral_mount,
+	.kill_sb	= nfs_kill_super,
+	.fs_flags	= FS_RENAME_DOES_D_MOVE|FS_REVAL_DOT|FS_BINARY_MOUNTDATA,
+};
+
+static const struct super_operations nfs4_sops = {
+	.alloc_inode	= nfs_alloc_inode,
+	.destroy_inode	= nfs_destroy_inode,
+	.write_inode	= nfs4_write_inode,
+	.drop_inode	= nfs_drop_inode,
+	.put_super	= nfs_put_super,
+	.statfs		= nfs_statfs,
+	.evict_inode	= nfs4_evict_inode,
+	.umount_begin	= nfs_umount_begin,
+	.show_options	= nfs_show_options,
+	.show_devname	= nfs_show_devname,
+	.show_path	= nfs_show_path,
+	.show_stats	= nfs_show_stats,
+	.remount_fs	= nfs_remount,
+};
+
+struct nfs_subversion nfs_v4 = {
+	.owner = THIS_MODULE,
+	.nfs_fs   = &nfs4_fs_type,
+	.rpc_vers = &nfs_version4,
+	.rpc_ops  = &nfs_v4_clientops,
+	.sops     = &nfs4_sops,
+	.xattr    = nfs4_xattr_handlers,
+};
+
+static int nfs4_write_inode(struct inode *inode, struct writeback_control *wbc)
+{
+	int ret = nfs_write_inode(inode, wbc);
+
+	if (ret >= 0 && test_bit(NFS_INO_LAYOUTCOMMIT, &NFS_I(inode)->flags)) {
+		int status;
+		bool sync = true;
+
+		if (wbc->sync_mode == WB_SYNC_NONE)
+			sync = false;
+
+		status = pnfs_layoutcommit_inode(inode, sync);
+		if (status < 0)
+			return status;
+	}
+	return ret;
+}
+
+/*
+ * Clean out any remaining NFSv4 state that might be left over due
+ * to open() calls that passed nfs_atomic_lookup, but failed to call
+ * nfs_open().
+ */
+static void nfs4_evict_inode(struct inode *inode)
+{
+	truncate_inode_pages(&inode->i_data, 0);
+	clear_inode(inode);
+	pnfs_return_layout(inode);
+	pnfs_destroy_layout(NFS_I(inode));
+	/* If we are holding a delegation, return it! */
+	nfs_inode_return_delegation_noreclaim(inode);
+	/* First call standard NFS clear_inode() code */
+	nfs_clear_inode(inode);
+}
+
+/*
+ * Get the superblock for the NFS4 root partition
+ */
+static struct dentry *
+nfs4_remote_mount(struct file_system_type *fs_type, int flags,
+		  const char *dev_name, void *info)
+{
+	struct nfs_mount_info *mount_info = info;
+	struct nfs_server *server;
+	struct dentry *mntroot = ERR_PTR(-ENOMEM);
+
+	mount_info->set_security = nfs_set_sb_security;
+
+	/* Get a volume representation */
+	server = nfs4_create_server(mount_info, &nfs_v4);
+	if (IS_ERR(server)) {
+		mntroot = ERR_CAST(server);
+		goto out;
+	}
+
+	mntroot = nfs_fs_mount_common(server, flags, dev_name, mount_info, &nfs_v4);
+
+out:
+	return mntroot;
+}
+
+static struct vfsmount *nfs_do_root_mount(struct file_system_type *fs_type,
+		int flags, void *data, const char *hostname)
+{
+	struct vfsmount *root_mnt;
+	char *root_devname;
+	size_t len;
+
+	len = strlen(hostname) + 5;
+	root_devname = kmalloc(len, GFP_KERNEL);
+	if (root_devname == NULL)
+		return ERR_PTR(-ENOMEM);
+	/* Does hostname needs to be enclosed in brackets? */
+	if (strchr(hostname, ':'))
+		snprintf(root_devname, len, "[%s]:/", hostname);
+	else
+		snprintf(root_devname, len, "%s:/", hostname);
+	root_mnt = vfs_kern_mount(fs_type, flags, root_devname, data);
+	kfree(root_devname);
+	return root_mnt;
+}
+
+struct nfs_referral_count {
+	struct list_head list;
+	const struct task_struct *task;
+	unsigned int referral_count;
+};
+
+static LIST_HEAD(nfs_referral_count_list);
+static DEFINE_SPINLOCK(nfs_referral_count_list_lock);
+
+static struct nfs_referral_count *nfs_find_referral_count(void)
+{
+	struct nfs_referral_count *p;
+
+	list_for_each_entry(p, &nfs_referral_count_list, list) {
+		if (p->task == current)
+			return p;
+	}
+	return NULL;
+}
+
+#define NFS_MAX_NESTED_REFERRALS 2
+
+static int nfs_referral_loop_protect(void)
+{
+	struct nfs_referral_count *p, *new;
+	int ret = -ENOMEM;
+
+	new = kmalloc(sizeof(*new), GFP_KERNEL);
+	if (!new)
+		goto out;
+	new->task = current;
+	new->referral_count = 1;
+
+	ret = 0;
+	spin_lock(&nfs_referral_count_list_lock);
+	p = nfs_find_referral_count();
+	if (p != NULL) {
+		if (p->referral_count >= NFS_MAX_NESTED_REFERRALS)
+			ret = -ELOOP;
+		else
+			p->referral_count++;
+	} else {
+		list_add(&new->list, &nfs_referral_count_list);
+		new = NULL;
+	}
+	spin_unlock(&nfs_referral_count_list_lock);
+	kfree(new);
+out:
+	return ret;
+}
+
+static void nfs_referral_loop_unprotect(void)
+{
+	struct nfs_referral_count *p;
+
+	spin_lock(&nfs_referral_count_list_lock);
+	p = nfs_find_referral_count();
+	p->referral_count--;
+	if (p->referral_count == 0)
+		list_del(&p->list);
+	else
+		p = NULL;
+	spin_unlock(&nfs_referral_count_list_lock);
+	kfree(p);
+}
+
+static struct dentry *nfs_follow_remote_path(struct vfsmount *root_mnt,
+		const char *export_path)
+{
+	struct dentry *dentry;
+	int err;
+
+	if (IS_ERR(root_mnt))
+		return ERR_CAST(root_mnt);
+
+	err = nfs_referral_loop_protect();
+	if (err) {
+		mntput(root_mnt);
+		return ERR_PTR(err);
+	}
+
+	dentry = mount_subtree(root_mnt, export_path);
+	nfs_referral_loop_unprotect();
+
+	return dentry;
+}
+
+struct dentry *nfs4_try_mount(int flags, const char *dev_name,
+			      struct nfs_mount_info *mount_info,
+			      struct nfs_subversion *nfs_mod)
+{
+	char *export_path;
+	struct vfsmount *root_mnt;
+	struct dentry *res;
+	struct nfs_parsed_mount_data *data = mount_info->parsed;
+
+	dfprintk(MOUNT, "--> nfs4_try_mount()\n");
+
+	export_path = data->nfs_server.export_path;
+	data->nfs_server.export_path = "/";
+	root_mnt = nfs_do_root_mount(&nfs4_remote_fs_type, flags, mount_info,
+			data->nfs_server.hostname);
+	data->nfs_server.export_path = export_path;
+
+	res = nfs_follow_remote_path(root_mnt, export_path);
+
+	dfprintk(MOUNT, "<-- nfs4_try_mount() = %ld%s\n",
+			IS_ERR(res) ? PTR_ERR(res) : 0,
+			IS_ERR(res) ? " [error]" : "");
+	return res;
+}
+
+static struct dentry *
+nfs4_remote_referral_mount(struct file_system_type *fs_type, int flags,
+			   const char *dev_name, void *raw_data)
+{
+	struct nfs_mount_info mount_info = {
+		.fill_super = nfs_fill_super,
+		.set_security = nfs_clone_sb_security,
+		.cloned = raw_data,
+	};
+	struct nfs_server *server;
+	struct dentry *mntroot = ERR_PTR(-ENOMEM);
+
+	dprintk("--> nfs4_referral_get_sb()\n");
+
+	mount_info.mntfh = nfs_alloc_fhandle();
+	if (mount_info.cloned == NULL || mount_info.mntfh == NULL)
+		goto out;
+
+	/* create a new volume representation */
+	server = nfs4_create_referral_server(mount_info.cloned, mount_info.mntfh);
+	if (IS_ERR(server)) {
+		mntroot = ERR_CAST(server);
+		goto out;
+	}
+
+	mntroot = nfs_fs_mount_common(server, flags, dev_name, &mount_info, &nfs_v4);
+out:
+	nfs_free_fhandle(mount_info.mntfh);
+	return mntroot;
+}
+
+/*
+ * Create an NFS4 server record on referral traversal
+ */
+static struct dentry *nfs4_referral_mount(struct file_system_type *fs_type,
+		int flags, const char *dev_name, void *raw_data)
+{
+	struct nfs_clone_mount *data = raw_data;
+	char *export_path;
+	struct vfsmount *root_mnt;
+	struct dentry *res;
+
+	dprintk("--> nfs4_referral_mount()\n");
+
+	export_path = data->mnt_path;
+	data->mnt_path = "/";
+
+	root_mnt = nfs_do_root_mount(&nfs4_remote_referral_fs_type,
+			flags, data, data->hostname);
+	data->mnt_path = export_path;
+
+	res = nfs_follow_remote_path(root_mnt, export_path);
+	dprintk("<-- nfs4_referral_mount() = %ld%s\n",
+			IS_ERR(res) ? PTR_ERR(res) : 0,
+			IS_ERR(res) ? " [error]" : "");
+	return res;
+}
+
+
+static int __init init_nfs_v4(void)
+{
+	int err;
+
+	err = nfs_idmap_init();
+	if (err)
+		goto out;
+
+	err = nfs4_register_sysctl();
+	if (err)
+		goto out1;
+
+	register_nfs_version(&nfs_v4);
+	return 0;
+out1:
+	nfs_idmap_quit();
+out:
+	return err;
+}
+
+static void __exit exit_nfs_v4(void)
+{
+	unregister_nfs_version(&nfs_v4);
+	nfs4_unregister_sysctl();
+	nfs_idmap_quit();
+}
+
+MODULE_LICENSE("GPL");
+
+module_init(init_nfs_v4);
+module_exit(exit_nfs_v4);
diff --git a/fs/nfs/nfs4sysctl.c b/fs/nfs/nfs4sysctl.c
new file mode 100644
index 00000000000..2628d921b7e
--- /dev/null
+++ b/fs/nfs/nfs4sysctl.c
@@ -0,0 +1,69 @@
+/*
+ * linux/fs/nfs/nfs4sysctl.c
+ *
+ * Sysctl interface to NFS v4 parameters
+ *
+ * Copyright (c) 2006 Trond Myklebust <Trond.Myklebust@netapp.com>
+ */
+#include <linux/sysctl.h>
+#include <linux/nfs_idmap.h>
+#include <linux/nfs_fs.h>
+
+#include "nfs4_fs.h"
+#include "callback.h"
+
+static const int nfs_set_port_min = 0;
+static const int nfs_set_port_max = 65535;
+static struct ctl_table_header *nfs4_callback_sysctl_table;
+
+static ctl_table nfs4_cb_sysctls[] = {
+	{
+		.procname = "nfs_callback_tcpport",
+		.data = &nfs_callback_set_tcpport,
+		.maxlen = sizeof(int),
+		.mode = 0644,
+		.proc_handler = proc_dointvec_minmax,
+		.extra1 = (int *)&nfs_set_port_min,
+		.extra2 = (int *)&nfs_set_port_max,
+	},
+	{
+		.procname = "idmap_cache_timeout",
+		.data = &nfs_idmap_cache_timeout,
+		.maxlen = sizeof(int),
+		.mode = 0644,
+		.proc_handler = proc_dointvec_jiffies,
+	},
+	{ }
+};
+
+static ctl_table nfs4_cb_sysctl_dir[] = {
+	{
+		.procname = "nfs",
+		.mode = 0555,
+		.child = nfs4_cb_sysctls,
+	},
+	{ }
+};
+
+static ctl_table nfs4_cb_sysctl_root[] = {
+	{
+		.procname = "fs",
+		.mode = 0555,
+		.child = nfs4_cb_sysctl_dir,
+	},
+	{ }
+};
+
+int nfs4_register_sysctl(void)
+{
+	nfs4_callback_sysctl_table = register_sysctl_table(nfs4_cb_sysctl_root);
+	if (nfs4_callback_sysctl_table == NULL)
+		return -ENOMEM;
+	return 0;
+}
+
+void nfs4_unregister_sysctl(void)
+{
+	unregister_sysctl_table(nfs4_callback_sysctl_table);
+	nfs4_callback_sysctl_table = NULL;
+}
diff --git a/fs/nfs/nfs4xdr.c b/fs/nfs/nfs4xdr.c
index 18fae29b030..26b14392043 100644
--- a/fs/nfs/nfs4xdr.c
+++ b/fs/nfs/nfs4xdr.c
@@ -56,6 +56,7 @@
 
 #include "nfs4_fs.h"
 #include "internal.h"
+#include "nfs4session.h"
 #include "pnfs.h"
 #include "netns.h"
 
@@ -270,6 +271,8 @@ static int nfs4_stat_to_errno(int);
 
 #if defined(CONFIG_NFS_V4_1)
 #define NFS4_MAX_MACHINE_NAME_LEN (64)
+#define IMPL_NAME_LIMIT (sizeof(utsname()->sysname) + sizeof(utsname()->release) + \
+			 sizeof(utsname()->version) + sizeof(utsname()->machine) + 8)
 
 #define encode_exchange_id_maxsz (op_encode_hdr_maxsz + \
 				encode_verifier_maxsz + \
@@ -282,7 +285,7 @@ static int nfs4_stat_to_errno(int);
 				1 /* nii_domain */ + \
 				XDR_QUADLEN(NFS4_OPAQUE_LIMIT) + \
 				1 /* nii_name */ + \
-				XDR_QUADLEN(NFS4_OPAQUE_LIMIT) + \
+				XDR_QUADLEN(IMPL_NAME_LIMIT) + \
 				3 /* nii_date */)
 #define decode_exchange_id_maxsz (op_decode_hdr_maxsz + \
 				2 /* eir_clientid */ + \
@@ -447,12 +450,14 @@ static int nfs4_stat_to_errno(int);
 				encode_sequence_maxsz + \
 				encode_putfh_maxsz + \
 				encode_open_maxsz + \
+				encode_access_maxsz + \
 				encode_getfh_maxsz + \
 				encode_getattr_maxsz)
 #define NFS4_dec_open_sz        (compound_decode_hdr_maxsz + \
 				decode_sequence_maxsz + \
 				decode_putfh_maxsz + \
 				decode_open_maxsz + \
+				decode_access_maxsz + \
 				decode_getfh_maxsz + \
 				decode_getattr_maxsz)
 #define NFS4_enc_open_confirm_sz \
@@ -467,11 +472,13 @@ static int nfs4_stat_to_errno(int);
 					encode_sequence_maxsz + \
 					encode_putfh_maxsz + \
 					encode_open_maxsz + \
+					encode_access_maxsz + \
 					encode_getattr_maxsz)
 #define NFS4_dec_open_noattr_sz	(compound_decode_hdr_maxsz + \
 					decode_sequence_maxsz + \
 					decode_putfh_maxsz + \
 					decode_open_maxsz + \
+					decode_access_maxsz + \
 					decode_getattr_maxsz)
 #define NFS4_enc_open_downgrade_sz \
 				(compound_encode_hdr_maxsz + \
@@ -852,12 +859,6 @@ const u32 nfs41_maxread_overhead = ((RPC_MAX_HEADER_WITH_AUTH +
 				    XDR_UNIT);
 #endif /* CONFIG_NFS_V4_1 */
 
-static unsigned short send_implementation_id = 1;
-
-module_param(send_implementation_id, ushort, 0644);
-MODULE_PARM_DESC(send_implementation_id,
-		"Send implementation ID with NFSv4.1 exchange_id");
-
 static const umode_t nfs_type2fmt[] = {
 	[NF4BAD] = 0,
 	[NF4REG] = S_IFREG,
@@ -938,7 +939,7 @@ static void encode_compound_hdr(struct xdr_stream *xdr,
 	 * but this is not required as a MUST for the server to do so. */
 	hdr->replen = RPC_REPHDRSIZE + auth->au_rslack + 3 + hdr->taglen;
 
-	BUG_ON(hdr->taglen > NFS4_MAXTAGLEN);
+	WARN_ON_ONCE(hdr->taglen > NFS4_MAXTAGLEN);
 	encode_string(xdr, hdr->taglen, hdr->tag);
 	p = reserve_space(xdr, 8);
 	*p++ = cpu_to_be32(hdr->minorversion);
@@ -957,7 +958,7 @@ static void encode_op_hdr(struct xdr_stream *xdr, enum nfs_opnum4 op,
 
 static void encode_nops(struct compound_hdr *hdr)
 {
-	BUG_ON(hdr->nops > NFS4_MAX_OPS);
+	WARN_ON_ONCE(hdr->nops > NFS4_MAX_OPS);
 	*hdr->nops_p = htonl(hdr->nops);
 }
 
@@ -1236,7 +1237,7 @@ static void encode_link(struct xdr_stream *xdr, const struct qstr *name, struct
 
 static inline int nfs4_lock_type(struct file_lock *fl, int block)
 {
-	if ((fl->fl_type & (F_RDLCK|F_WRLCK|F_UNLCK)) == F_RDLCK)
+	if (fl->fl_type == F_RDLCK)
 		return block ? NFS4_READW_LT : NFS4_READ_LT;
 	return block ? NFS4_WRITEW_LT : NFS4_WRITE_LT;
 }
@@ -1405,7 +1406,6 @@ static void encode_opentype(struct xdr_stream *xdr, const struct nfs_openargs *a
 		*p = cpu_to_be32(NFS4_OPEN_NOCREATE);
 		break;
 	default:
-		BUG_ON(arg->claim != NFS4_OPEN_CLAIM_NULL);
 		*p = cpu_to_be32(NFS4_OPEN_CREATE);
 		encode_createmode(xdr, arg);
 	}
@@ -1515,8 +1515,12 @@ static void encode_open_stateid(struct xdr_stream *xdr,
 	nfs4_stateid stateid;
 
 	if (ctx->state != NULL) {
+		const struct nfs_lockowner *lockowner = NULL;
+
+		if (l_ctx != NULL)
+			lockowner = &l_ctx->lockowner;
 		nfs4_select_rw_stateid(&stateid, ctx->state,
-				fmode, l_ctx->lockowner, l_ctx->pid);
+				fmode, lockowner);
 		if (zero_seqid)
 			stateid.seqid = 0;
 		encode_nfs4_stateid(xdr, &stateid);
@@ -1619,7 +1623,6 @@ encode_setacl(struct xdr_stream *xdr, struct nfs_setaclargs *arg, struct compoun
 	p = reserve_space(xdr, 2*4);
 	*p++ = cpu_to_be32(1);
 	*p = cpu_to_be32(FATTR4_WORD0_ACL);
-	BUG_ON(arg->acl_len % 4);
 	p = reserve_space(xdr, 4);
 	*p = cpu_to_be32(arg->acl_len);
 	xdr_write_pages(xdr, arg->acl_pages, arg->acl_pgbase, arg->acl_len);
@@ -1711,7 +1714,7 @@ static void encode_exchange_id(struct xdr_stream *xdr,
 			       struct compound_hdr *hdr)
 {
 	__be32 *p;
-	char impl_name[NFS4_OPAQUE_LIMIT];
+	char impl_name[IMPL_NAME_LIMIT];
 	int len = 0;
 
 	encode_op_hdr(xdr, OP_EXCHANGE_ID, decode_exchange_id_maxsz, hdr);
@@ -1726,7 +1729,7 @@ static void encode_exchange_id(struct xdr_stream *xdr,
 	if (send_implementation_id &&
 	    sizeof(CONFIG_NFS_V4_1_IMPLEMENTATION_ID_DOMAIN) > 1 &&
 	    sizeof(CONFIG_NFS_V4_1_IMPLEMENTATION_ID_DOMAIN)
-		<= NFS4_OPAQUE_LIMIT + 1)
+		<= sizeof(impl_name) + 1)
 		len = snprintf(impl_name, sizeof(impl_name), "%s %s %s %s",
 			       utsname()->sysname, utsname()->release,
 			       utsname()->version, utsname()->machine);
@@ -1833,18 +1836,16 @@ static void encode_sequence(struct xdr_stream *xdr,
 			    struct compound_hdr *hdr)
 {
 #if defined(CONFIG_NFS_V4_1)
-	struct nfs4_session *session = args->sa_session;
+	struct nfs4_session *session;
 	struct nfs4_slot_table *tp;
-	struct nfs4_slot *slot;
+	struct nfs4_slot *slot = args->sa_slot;
 	__be32 *p;
 
-	if (!session)
+	if (slot == NULL)
 		return;
 
-	tp = &session->fc_slot_table;
-
-	WARN_ON(args->sa_slotid == NFS4_MAX_SLOT_TABLE);
-	slot = tp->slots + args->sa_slotid;
+	tp = slot->table;
+	session = tp->session;
 
 	encode_op_hdr(xdr, OP_SEQUENCE, decode_sequence_maxsz, hdr);
 
@@ -1858,12 +1859,12 @@ static void encode_sequence(struct xdr_stream *xdr,
 		((u32 *)session->sess_id.data)[1],
 		((u32 *)session->sess_id.data)[2],
 		((u32 *)session->sess_id.data)[3],
-		slot->seq_nr, args->sa_slotid,
+		slot->seq_nr, slot->slot_nr,
 		tp->highest_used_slotid, args->sa_cache_this);
 	p = reserve_space(xdr, NFS4_MAX_SESSIONID_LEN + 16);
 	p = xdr_encode_opaque_fixed(p, session->sess_id.data, NFS4_MAX_SESSIONID_LEN);
 	*p++ = cpu_to_be32(slot->seq_nr);
-	*p++ = cpu_to_be32(args->sa_slotid);
+	*p++ = cpu_to_be32(slot->slot_nr);
 	*p++ = cpu_to_be32(tp->highest_used_slotid);
 	*p = cpu_to_be32(args->sa_cache_this);
 #endif /* CONFIG_NFS_V4_1 */
@@ -2025,8 +2026,9 @@ static void encode_free_stateid(struct xdr_stream *xdr,
 static u32 nfs4_xdr_minorversion(const struct nfs4_sequence_args *args)
 {
 #if defined(CONFIG_NFS_V4_1)
-	if (args->sa_session)
-		return args->sa_session->clp->cl_mvops->minor_version;
+
+	if (args->sa_slot)
+		return args->sa_slot->table->session->clp->cl_mvops->minor_version;
 #endif /* CONFIG_NFS_V4_1 */
 	return 0;
 }
@@ -2222,6 +2224,8 @@ static void nfs4_xdr_enc_open(struct rpc_rqst *req, struct xdr_stream *xdr,
 	encode_putfh(xdr, args->fh, &hdr);
 	encode_open(xdr, args, &hdr);
 	encode_getfh(xdr, &hdr);
+	if (args->access)
+		encode_access(xdr, args->access, &hdr);
 	encode_getfattr_open(xdr, args->bitmask, args->open_bitmap, &hdr);
 	encode_nops(&hdr);
 }
@@ -2258,7 +2262,9 @@ static void nfs4_xdr_enc_open_noattr(struct rpc_rqst *req,
 	encode_sequence(xdr, &args->seq_args, &hdr);
 	encode_putfh(xdr, args->fh, &hdr);
 	encode_open(xdr, args, &hdr);
-	encode_getfattr(xdr, args->bitmask, &hdr);
+	if (args->access)
+		encode_access(xdr, args->access, &hdr);
+	encode_getfattr_open(xdr, args->bitmask, args->open_bitmap, &hdr);
 	encode_nops(&hdr);
 }
 
@@ -3078,7 +3084,7 @@ out_overflow:
 	return -EIO;
 }
 
-static inline int decode_attr_length(struct xdr_stream *xdr, uint32_t *attrlen, __be32 **savep)
+static int decode_attr_length(struct xdr_stream *xdr, uint32_t *attrlen, unsigned int *savep)
 {
 	__be32 *p;
 
@@ -3086,7 +3092,7 @@ static inline int decode_attr_length(struct xdr_stream *xdr, uint32_t *attrlen,
 	if (unlikely(!p))
 		goto out_overflow;
 	*attrlen = be32_to_cpup(p);
-	*savep = xdr->p;
+	*savep = xdr_stream_pos(xdr);
 	return 0;
 out_overflow:
 	print_overflow_msg(__func__, xdr);
@@ -4068,10 +4074,10 @@ static int decode_attr_time_modify(struct xdr_stream *xdr, uint32_t *bitmap, str
 	return status;
 }
 
-static int verify_attr_len(struct xdr_stream *xdr, __be32 *savep, uint32_t attrlen)
+static int verify_attr_len(struct xdr_stream *xdr, unsigned int savep, uint32_t attrlen)
 {
 	unsigned int attrwords = XDR_QUADLEN(attrlen);
-	unsigned int nwords = xdr->p - savep;
+	unsigned int nwords = (xdr_stream_pos(xdr) - savep) >> 2;
 
 	if (unlikely(attrwords != nwords)) {
 		dprintk("%s: server returned incorrect attribute length: "
@@ -4101,7 +4107,7 @@ out_overflow:
 	return -EIO;
 }
 
-static int decode_access(struct xdr_stream *xdr, struct nfs4_accessres *access)
+static int decode_access(struct xdr_stream *xdr, u32 *supported, u32 *access)
 {
 	__be32 *p;
 	uint32_t supp, acc;
@@ -4115,8 +4121,8 @@ static int decode_access(struct xdr_stream *xdr, struct nfs4_accessres *access)
 		goto out_overflow;
 	supp = be32_to_cpup(p++);
 	acc = be32_to_cpup(p);
-	access->supported = supp;
-	access->access = acc;
+	*supported = supp;
+	*access = acc;
 	return 0;
 out_overflow:
 	print_overflow_msg(__func__, xdr);
@@ -4158,13 +4164,18 @@ static int decode_verifier(struct xdr_stream *xdr, void *verifier)
 	return decode_opaque_fixed(xdr, verifier, NFS4_VERIFIER_SIZE);
 }
 
+static int decode_write_verifier(struct xdr_stream *xdr, struct nfs_write_verifier *verifier)
+{
+	return decode_opaque_fixed(xdr, verifier->data, NFS4_VERIFIER_SIZE);
+}
+
 static int decode_commit(struct xdr_stream *xdr, struct nfs_commitres *res)
 {
 	int status;
 
 	status = decode_op_hdr(xdr, OP_COMMIT);
 	if (!status)
-		status = decode_verifier(xdr, res->verf->verifier);
+		status = decode_write_verifier(xdr, &res->verf->verifier);
 	return status;
 }
 
@@ -4193,7 +4204,7 @@ out_overflow:
 
 static int decode_server_caps(struct xdr_stream *xdr, struct nfs4_server_caps_res *res)
 {
-	__be32 *savep;
+	unsigned int savep;
 	uint32_t attrlen, bitmap[3] = {0};
 	int status;
 
@@ -4222,7 +4233,7 @@ xdr_error:
 
 static int decode_statfs(struct xdr_stream *xdr, struct nfs_fsstat *fsstat)
 {
-	__be32 *savep;
+	unsigned int savep;
 	uint32_t attrlen, bitmap[3] = {0};
 	int status;
 
@@ -4254,7 +4265,7 @@ xdr_error:
 
 static int decode_pathconf(struct xdr_stream *xdr, struct nfs_pathconf *pathconf)
 {
-	__be32 *savep;
+	unsigned int savep;
 	uint32_t attrlen, bitmap[3] = {0};
 	int status;
 
@@ -4299,7 +4310,8 @@ out_overflow:
 static int decode_first_threshold_item4(struct xdr_stream *xdr,
 					struct nfs4_threshold *res)
 {
-	__be32 *p, *savep;
+	__be32 *p;
+	unsigned int savep;
 	uint32_t bitmap[3] = {0,}, attrlen;
 	int status;
 
@@ -4503,7 +4515,7 @@ static int decode_getfattr_generic(struct xdr_stream *xdr, struct nfs_fattr *fat
 		struct nfs_fh *fh, struct nfs4_fs_locations *fs_loc,
 		const struct nfs_server *server)
 {
-	__be32 *savep;
+	unsigned int savep;
 	uint32_t attrlen,
 		 bitmap[3] = {0};
 	int status;
@@ -4615,7 +4627,7 @@ static int decode_attr_layout_blksize(struct xdr_stream *xdr, uint32_t *bitmap,
 
 static int decode_fsinfo(struct xdr_stream *xdr, struct nfs_fsinfo *fsinfo)
 {
-	__be32 *savep;
+	unsigned int savep;
 	uint32_t attrlen, bitmap[3];
 	int status;
 
@@ -4920,9 +4932,8 @@ static int decode_putrootfh(struct xdr_stream *xdr)
 
 static int decode_read(struct xdr_stream *xdr, struct rpc_rqst *req, struct nfs_readres *res)
 {
-	struct kvec *iov = req->rq_rcv_buf.head;
 	__be32 *p;
-	uint32_t count, eof, recvd, hdrlen;
+	uint32_t count, eof, recvd;
 	int status;
 
 	status = decode_op_hdr(xdr, OP_READ);
@@ -4933,15 +4944,13 @@ static int decode_read(struct xdr_stream *xdr, struct rpc_rqst *req, struct nfs_
 		goto out_overflow;
 	eof = be32_to_cpup(p++);
 	count = be32_to_cpup(p);
-	hdrlen = (u8 *) xdr->p - (u8 *) iov->iov_base;
-	recvd = req->rq_rcv_buf.len - hdrlen;
+	recvd = xdr_read_pages(xdr, count);
 	if (count > recvd) {
 		dprintk("NFS: server cheating in read reply: "
 				"count %u > recvd %u\n", count, recvd);
 		count = recvd;
 		eof = 0;
 	}
-	xdr_read_pages(xdr, count);
 	res->eof = eof;
 	res->count = count;
 	return 0;
@@ -4952,10 +4961,6 @@ out_overflow:
 
 static int decode_readdir(struct xdr_stream *xdr, struct rpc_rqst *req, struct nfs4_readdir_res *readdir)
 {
-	struct xdr_buf	*rcvbuf = &req->rq_rcv_buf;
-	struct kvec	*iov = rcvbuf->head;
-	size_t		hdrlen;
-	u32		recvd, pglen = rcvbuf->page_len;
 	int		status;
 	__be32		verf[2];
 
@@ -4967,22 +4972,12 @@ static int decode_readdir(struct xdr_stream *xdr, struct rpc_rqst *req, struct n
 	memcpy(verf, readdir->verifier.data, sizeof(verf));
 	dprintk("%s: verifier = %08x:%08x\n",
 			__func__, verf[0], verf[1]);
-
-	hdrlen = (char *) xdr->p - (char *) iov->iov_base;
-	recvd = rcvbuf->len - hdrlen;
-	if (pglen > recvd)
-		pglen = recvd;
-	xdr_read_pages(xdr, pglen);
-
-
-	return pglen;
+	return xdr_read_pages(xdr, xdr->buf->page_len);
 }
 
 static int decode_readlink(struct xdr_stream *xdr, struct rpc_rqst *req)
 {
 	struct xdr_buf *rcvbuf = &req->rq_rcv_buf;
-	struct kvec *iov = rcvbuf->head;
-	size_t hdrlen;
 	u32 len, recvd;
 	__be32 *p;
 	int status;
@@ -5000,14 +4995,12 @@ static int decode_readlink(struct xdr_stream *xdr, struct rpc_rqst *req)
 		dprintk("nfs: server returned giant symlink!\n");
 		return -ENAMETOOLONG;
 	}
-	hdrlen = (char *) xdr->p - (char *) iov->iov_base;
-	recvd = req->rq_rcv_buf.len - hdrlen;
+	recvd = xdr_read_pages(xdr, len);
 	if (recvd < len) {
 		dprintk("NFS: server cheating in readlink reply: "
 				"count %u > recvd %u\n", len, recvd);
 		return -EIO;
 	}
-	xdr_read_pages(xdr, len);
 	/*
 	 * The XDR encode routine has set things up so that
 	 * the link text will be copied directly into the
@@ -5063,23 +5056,20 @@ decode_restorefh(struct xdr_stream *xdr)
 static int decode_getacl(struct xdr_stream *xdr, struct rpc_rqst *req,
 			 struct nfs_getaclres *res)
 {
-	__be32 *savep, *bm_p;
+	unsigned int savep;
 	uint32_t attrlen,
 		 bitmap[3] = {0};
-	struct kvec *iov = req->rq_rcv_buf.head;
 	int status;
-	size_t page_len = xdr->buf->page_len;
+	unsigned int pg_offset;
 
 	res->acl_len = 0;
 	if ((status = decode_op_hdr(xdr, OP_GETATTR)) != 0)
 		goto out;
 
-	bm_p = xdr->p;
-	res->acl_data_offset = be32_to_cpup(bm_p) + 2;
-	res->acl_data_offset <<= 2;
-	/* Check if the acl data starts beyond the allocated buffer */
-	if (res->acl_data_offset > page_len)
-		return -ERANGE;
+	xdr_enter_page(xdr, xdr->buf->page_len);
+
+	/* Calculate the offset of the page data */
+	pg_offset = xdr->buf->head[0].iov_len;
 
 	if ((status = decode_attr_bitmap(xdr, bitmap)) != 0)
 		goto out;
@@ -5089,29 +5079,20 @@ static int decode_getacl(struct xdr_stream *xdr, struct rpc_rqst *req,
 	if (unlikely(bitmap[0] & (FATTR4_WORD0_ACL - 1U)))
 		return -EIO;
 	if (likely(bitmap[0] & FATTR4_WORD0_ACL)) {
-		size_t hdrlen;
 
 		/* The bitmap (xdr len + bitmaps) and the attr xdr len words
 		 * are stored with the acl data to handle the problem of
 		 * variable length bitmaps.*/
-		xdr->p = bm_p;
-
-		/* We ignore &savep and don't do consistency checks on
-		 * the attr length.  Let userspace figure it out.... */
-		hdrlen = (u8 *)xdr->p - (u8 *)iov->iov_base;
-		attrlen += res->acl_data_offset;
-		if (attrlen > page_len) {
-			if (res->acl_flags & NFS4_ACL_LEN_REQUEST) {
-				/* getxattr interface called with a NULL buf */
-				res->acl_len = attrlen;
-				goto out;
-			}
-			dprintk("NFS: acl reply: attrlen %u > page_len %zu\n",
-					attrlen, page_len);
-			return -EINVAL;
-		}
-		xdr_read_pages(xdr, attrlen);
+		res->acl_data_offset = xdr_stream_pos(xdr) - pg_offset;
 		res->acl_len = attrlen;
+
+		/* Check for receive buffer overflow */
+		if (res->acl_len > (xdr->nwords << 2) ||
+		    res->acl_len + res->acl_data_offset > xdr->buf->page_len) {
+			res->acl_flags |= NFS4_ACL_TRUNC;
+			dprintk("NFS: acl reply: attrlen %u > page_len %u\n",
+					attrlen, xdr->nwords << 2);
+		}
 	} else
 		status = -EOPNOTSUPP;
 
@@ -5212,13 +5193,12 @@ static int decode_write(struct xdr_stream *xdr, struct nfs_writeres *res)
 	if (status)
 		return status;
 
-	p = xdr_inline_decode(xdr, 16);
+	p = xdr_inline_decode(xdr, 8);
 	if (unlikely(!p))
 		goto out_overflow;
 	res->count = be32_to_cpup(p++);
 	res->verf->committed = be32_to_cpup(p++);
-	memcpy(res->verf->verifier, p, NFS4_VERIFIER_SIZE);
-	return 0;
+	return decode_write_verifier(xdr, &res->verf->verifier);
 out_overflow:
 	print_overflow_msg(__func__, xdr);
 	return -EIO;
@@ -5529,12 +5509,13 @@ static int decode_sequence(struct xdr_stream *xdr,
 			   struct rpc_rqst *rqstp)
 {
 #if defined(CONFIG_NFS_V4_1)
+	struct nfs4_session *session;
 	struct nfs4_sessionid id;
 	u32 dummy;
 	int status;
 	__be32 *p;
 
-	if (!res->sr_session)
+	if (res->sr_slot == NULL)
 		return 0;
 
 	status = decode_op_hdr(xdr, OP_SEQUENCE);
@@ -5548,8 +5529,9 @@ static int decode_sequence(struct xdr_stream *xdr,
 	 * sequence number, the server is looney tunes.
 	 */
 	status = -EREMOTEIO;
+	session = res->sr_slot->table->session;
 
-	if (memcmp(id.data, res->sr_session->sess_id.data,
+	if (memcmp(id.data, session->sess_id.data,
 		   NFS4_MAX_SESSIONID_LEN)) {
 		dprintk("%s Invalid session id\n", __func__);
 		goto out_err;
@@ -5567,14 +5549,14 @@ static int decode_sequence(struct xdr_stream *xdr,
 	}
 	/* slot id */
 	dummy = be32_to_cpup(p++);
-	if (dummy != res->sr_slot - res->sr_session->fc_slot_table.slots) {
+	if (dummy != res->sr_slot->slot_nr) {
 		dprintk("%s Invalid slot id\n", __func__);
 		goto out_err;
 	}
-	/* highest slot id - currently not processed */
-	dummy = be32_to_cpup(p++);
-	/* target highest slot id - currently not processed */
-	dummy = be32_to_cpup(p++);
+	/* highest slot id */
+	res->sr_highest_slotid = be32_to_cpup(p++);
+	/* target highest slot id */
+	res->sr_target_highest_slotid = be32_to_cpup(p++);
 	/* result flags */
 	res->sr_status_flags = be32_to_cpup(p);
 	status = 0;
@@ -5599,7 +5581,7 @@ static int decode_getdevicelist(struct xdr_stream *xdr,
 {
 	__be32 *p;
 	int status, i;
-	struct nfs_writeverf verftemp;
+	nfs4_verifier verftemp;
 
 	status = decode_op_hdr(xdr, OP_GETDEVICELIST);
 	if (status)
@@ -5613,7 +5595,7 @@ static int decode_getdevicelist(struct xdr_stream *xdr,
 	p += 2;
 
 	/* Read verifier */
-	p = xdr_decode_opaque_fixed(p, verftemp.verifier, NFS4_VERIFIER_SIZE);
+	p = xdr_decode_opaque_fixed(p, verftemp.data, NFS4_VERIFIER_SIZE);
 
 	res->num_devs = be32_to_cpup(p);
 
@@ -5674,7 +5656,8 @@ static int decode_getdeviceinfo(struct xdr_stream *xdr,
 	 * and places the remaining xdr data in xdr_buf->tail
 	 */
 	pdev->mincount = be32_to_cpup(p);
-	xdr_read_pages(xdr, pdev->mincount); /* include space for the length */
+	if (xdr_read_pages(xdr, pdev->mincount) != pdev->mincount)
+		goto out_overflow;
 
 	/* Parse notification bitmap, verifying that it is zero. */
 	p = xdr_inline_decode(xdr, 4);
@@ -5707,9 +5690,7 @@ static int decode_layoutget(struct xdr_stream *xdr, struct rpc_rqst *req,
 	__be32 *p;
 	int status;
 	u32 layout_count;
-	struct xdr_buf *rcvbuf = &req->rq_rcv_buf;
-	struct kvec *iov = rcvbuf->head;
-	u32 hdrlen, recvd;
+	u32 recvd;
 
 	status = decode_op_hdr(xdr, OP_LAYOUTGET);
 	if (status)
@@ -5746,8 +5727,7 @@ static int decode_layoutget(struct xdr_stream *xdr, struct rpc_rqst *req,
 		res->type,
 		res->layoutp->len);
 
-	hdrlen = (u8 *) xdr->p - (u8 *) iov->iov_base;
-	recvd = req->rq_rcv_buf.len - hdrlen;
+	recvd = xdr_read_pages(xdr, res->layoutp->len);
 	if (res->layoutp->len > recvd) {
 		dprintk("NFS: server cheating in layoutget reply: "
 				"layout len %u > recvd %u\n",
@@ -5755,8 +5735,6 @@ static int decode_layoutget(struct xdr_stream *xdr, struct rpc_rqst *req,
 		return -EINVAL;
 	}
 
-	xdr_read_pages(xdr, res->layoutp->len);
-
 	if (layout_count > 1) {
 		/* We only handle a length one array at the moment.  Any
 		 * further entries are just ignored.  Note that this means
@@ -5924,7 +5902,7 @@ static int nfs4_xdr_dec_access(struct rpc_rqst *rqstp, struct xdr_stream *xdr,
 	status = decode_putfh(xdr);
 	if (status != 0)
 		goto out;
-	status = decode_access(xdr, res);
+	status = decode_access(xdr, &res->supported, &res->access);
 	if (status != 0)
 		goto out;
 	decode_getfattr(xdr, res->fattr, res->server);
@@ -6262,8 +6240,11 @@ static int nfs4_xdr_dec_open(struct rpc_rqst *rqstp, struct xdr_stream *xdr,
 	status = decode_open(xdr, res);
 	if (status)
 		goto out;
-	if (decode_getfh(xdr, &res->fh) != 0)
+	status = decode_getfh(xdr, &res->fh);
+	if (status)
 		goto out;
+	if (res->access_request)
+		decode_access(xdr, &res->access_supported, &res->access_result);
 	decode_getfattr(xdr, res->f_attr, res->server);
 out:
 	return status;
@@ -6312,6 +6293,8 @@ static int nfs4_xdr_dec_open_noattr(struct rpc_rqst *rqstp,
 	status = decode_open(xdr, res);
 	if (status)
 		goto out;
+	if (res->access_request)
+		decode_access(xdr, &res->access_supported, &res->access_result);
 	decode_getfattr(xdr, res->f_attr, res->server);
 out:
 	return status;
@@ -7103,6 +7086,7 @@ out:
 int nfs4_decode_dirent(struct xdr_stream *xdr, struct nfs_entry *entry,
 		       int plus)
 {
+	unsigned int savep;
 	uint32_t bitmap[3] = {0};
 	uint32_t len;
 	__be32 *p = xdr_inline_decode(xdr, 4);
@@ -7141,7 +7125,7 @@ int nfs4_decode_dirent(struct xdr_stream *xdr, struct nfs_entry *entry,
 	if (decode_attr_bitmap(xdr, bitmap) < 0)
 		goto out_overflow;
 
-	if (decode_attr_length(xdr, &len, &p) < 0)
+	if (decode_attr_length(xdr, &len, &savep) < 0)
 		goto out_overflow;
 
 	if (decode_getfattr_attrs(xdr, bitmap, entry->fattr, entry->fh,
diff --git a/fs/nfs/objlayout/objio_osd.c b/fs/nfs/objlayout/objio_osd.c
index f50d3e8d6f2..c6f990656f8 100644
--- a/fs/nfs/objlayout/objio_osd.c
+++ b/fs/nfs/objlayout/objio_osd.c
@@ -41,6 +41,7 @@
 #include <scsi/osd_ore.h>
 
 #include "objlayout.h"
+#include "../internal.h"
 
 #define NFSDBG_FACILITY         NFSDBG_PNFS_LD
 
@@ -368,7 +369,7 @@ void objio_free_result(struct objlayout_io_res *oir)
 	kfree(objios);
 }
 
-enum pnfs_osd_errno osd_pri_2_pnfs_err(enum osd_err_priority oep)
+static enum pnfs_osd_errno osd_pri_2_pnfs_err(enum osd_err_priority oep)
 {
 	switch (oep) {
 	case OSD_ERR_PRI_NO_ERROR:
@@ -570,17 +571,72 @@ static bool objio_pg_test(struct nfs_pageio_descriptor *pgio,
 		return false;
 
 	return pgio->pg_count + req->wb_bytes <=
-			OBJIO_LSEG(pgio->pg_lseg)->layout.max_io_length;
+			(unsigned long)pgio->pg_layout_private;
+}
+
+static void objio_init_read(struct nfs_pageio_descriptor *pgio, struct nfs_page *req)
+{
+	pnfs_generic_pg_init_read(pgio, req);
+	if (unlikely(pgio->pg_lseg == NULL))
+		return; /* Not pNFS */
+
+	pgio->pg_layout_private = (void *)
+				OBJIO_LSEG(pgio->pg_lseg)->layout.max_io_length;
+}
+
+static bool aligned_on_raid_stripe(u64 offset, struct ore_layout *layout,
+				   unsigned long *stripe_end)
+{
+	u32 stripe_off;
+	unsigned stripe_size;
+
+	if (layout->raid_algorithm == PNFS_OSD_RAID_0)
+		return true;
+
+	stripe_size = layout->stripe_unit *
+				(layout->group_width - layout->parity);
+
+	div_u64_rem(offset, stripe_size, &stripe_off);
+	if (!stripe_off)
+		return true;
+
+	*stripe_end = stripe_size - stripe_off;
+	return false;
+}
+
+static void objio_init_write(struct nfs_pageio_descriptor *pgio, struct nfs_page *req)
+{
+	unsigned long stripe_end = 0;
+	u64 wb_size;
+
+	if (pgio->pg_dreq == NULL)
+		wb_size = i_size_read(pgio->pg_inode) - req_offset(req);
+	else
+		wb_size = nfs_dreq_bytes_left(pgio->pg_dreq);
+
+	pnfs_generic_pg_init_write(pgio, req, wb_size);
+	if (unlikely(pgio->pg_lseg == NULL))
+		return; /* Not pNFS */
+
+	if (req->wb_offset ||
+	    !aligned_on_raid_stripe(req->wb_index * PAGE_SIZE,
+			       &OBJIO_LSEG(pgio->pg_lseg)->layout,
+			       &stripe_end)) {
+		pgio->pg_layout_private = (void *)stripe_end;
+	} else {
+		pgio->pg_layout_private = (void *)
+				OBJIO_LSEG(pgio->pg_lseg)->layout.max_io_length;
+	}
 }
 
 static const struct nfs_pageio_ops objio_pg_read_ops = {
-	.pg_init = pnfs_generic_pg_init_read,
+	.pg_init = objio_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_init = objio_init_write,
 	.pg_test = objio_pg_test,
 	.pg_doio = pnfs_generic_pg_writepages,
 };
diff --git a/fs/nfs/objlayout/objlayout.c b/fs/nfs/objlayout/objlayout.c
index 87461354530..a9ebd817278 100644
--- a/fs/nfs/objlayout/objlayout.c
+++ b/fs/nfs/objlayout/objlayout.c
@@ -148,17 +148,6 @@ end_offset(u64 start, u64 len)
 	return end >= start ? end : NFS4_MAX_UINT64;
 }
 
-/* last octet in a range */
-static inline u64
-last_byte_offset(u64 start, u64 len)
-{
-	u64 end;
-
-	BUG_ON(!len);
-	end = start + len;
-	return end > start ? end - 1 : NFS4_MAX_UINT64;
-}
-
 static void _fix_verify_io_params(struct pnfs_layout_segment *lseg,
 			   struct page ***p_pages, unsigned *p_pgbase,
 			   u64 offset, unsigned long count)
diff --git a/fs/nfs/pagelist.c b/fs/nfs/pagelist.c
index aed913c833f..e56e846e9d2 100644
--- a/fs/nfs/pagelist.c
+++ b/fs/nfs/pagelist.c
@@ -49,11 +49,13 @@ void nfs_pgheader_init(struct nfs_pageio_descriptor *desc,
 	hdr->io_start = req_offset(hdr->req);
 	hdr->good_bytes = desc->pg_count;
 	hdr->dreq = desc->pg_dreq;
+	hdr->layout_private = desc->pg_layout_private;
 	hdr->release = release;
 	hdr->completion_ops = desc->pg_completion_ops;
 	if (hdr->completion_ops->init_hdr)
 		hdr->completion_ops->init_hdr(hdr);
 }
+EXPORT_SYMBOL_GPL(nfs_pgheader_init);
 
 void nfs_set_pgio_error(struct nfs_pgio_header *hdr, int error, loff_t pos)
 {
@@ -70,7 +72,7 @@ void nfs_set_pgio_error(struct nfs_pgio_header *hdr, int error, loff_t pos)
 static inline struct nfs_page *
 nfs_page_alloc(void)
 {
-	struct nfs_page	*p = kmem_cache_zalloc(nfs_page_cachep, GFP_KERNEL);
+	struct nfs_page	*p = kmem_cache_zalloc(nfs_page_cachep, GFP_NOIO);
 	if (p)
 		INIT_LIST_HEAD(&p->wb_list);
 	return p;
@@ -100,6 +102,7 @@ nfs_create_request(struct nfs_open_context *ctx, struct inode *inode,
 		   unsigned int offset, unsigned int count)
 {
 	struct nfs_page		*req;
+	struct nfs_lock_context *l_ctx;
 
 	/* try to allocate the request struct */
 	req = nfs_page_alloc();
@@ -107,17 +110,18 @@ nfs_create_request(struct nfs_open_context *ctx, struct inode *inode,
 		return ERR_PTR(-ENOMEM);
 
 	/* get lock context early so we can deal with alloc failures */
-	req->wb_lock_context = nfs_get_lock_context(ctx);
-	if (req->wb_lock_context == NULL) {
+	l_ctx = nfs_get_lock_context(ctx);
+	if (IS_ERR(l_ctx)) {
 		nfs_page_free(req);
-		return ERR_PTR(-ENOMEM);
+		return ERR_CAST(l_ctx);
 	}
+	req->wb_lock_context = l_ctx;
 
 	/* Initialize the request struct. Initially, we assume a
 	 * long write-back delay. This will be adjusted in
 	 * update_nfs_request below if the region is not locked. */
 	req->wb_page    = page;
-	req->wb_index	= page->index;
+	req->wb_index	= page_file_index(page);
 	page_cache_get(page);
 	req->wb_offset  = offset;
 	req->wb_pgbase	= offset;
@@ -267,7 +271,9 @@ void nfs_pageio_init(struct nfs_pageio_descriptor *desc,
 	desc->pg_error = 0;
 	desc->pg_lseg = NULL;
 	desc->pg_dreq = NULL;
+	desc->pg_layout_private = NULL;
 }
+EXPORT_SYMBOL_GPL(nfs_pageio_init);
 
 /**
  * nfs_can_coalesce_requests - test two requests for compatibility
@@ -286,7 +292,9 @@ static bool nfs_can_coalesce_requests(struct nfs_page *prev,
 {
 	if (req->wb_context->cred != prev->wb_context->cred)
 		return false;
-	if (req->wb_lock_context->lockowner != prev->wb_lock_context->lockowner)
+	if (req->wb_lock_context->lockowner.l_owner != prev->wb_lock_context->lockowner.l_owner)
+		return false;
+	if (req->wb_lock_context->lockowner.l_pid != prev->wb_lock_context->lockowner.l_pid)
 		return false;
 	if (req->wb_context->state != prev->wb_context->state)
 		return false;
@@ -409,6 +417,7 @@ int nfs_pageio_add_request(struct nfs_pageio_descriptor *desc,
 	} while (ret);
 	return ret;
 }
+EXPORT_SYMBOL_GPL(nfs_pageio_add_request);
 
 /**
  * nfs_pageio_complete - Complete I/O on an nfs_pageio_descriptor
@@ -424,6 +433,7 @@ void nfs_pageio_complete(struct nfs_pageio_descriptor *desc)
 			break;
 	}
 }
+EXPORT_SYMBOL_GPL(nfs_pageio_complete);
 
 /**
  * nfs_pageio_cond_complete - Conditional I/O completion
diff --git a/fs/nfs/pnfs.c b/fs/nfs/pnfs.c
index bbc49caa7a8..d00260b0810 100644
--- a/fs/nfs/pnfs.c
+++ b/fs/nfs/pnfs.c
@@ -35,6 +35,7 @@
 #include "iostat.h"
 
 #define NFSDBG_FACILITY		NFSDBG_PNFS
+#define PNFS_LAYOUTGET_RETRY_TIMEOUT (120*HZ)
 
 /* Locking:
  *
@@ -190,7 +191,7 @@ EXPORT_SYMBOL_GPL(pnfs_unregister_layoutdriver);
 
 /* Need to hold i_lock if caller does not already hold reference */
 void
-get_layout_hdr(struct pnfs_layout_hdr *lo)
+pnfs_get_layout_hdr(struct pnfs_layout_hdr *lo)
 {
 	atomic_inc(&lo->plh_refcount);
 }
@@ -199,43 +200,107 @@ static struct pnfs_layout_hdr *
 pnfs_alloc_layout_hdr(struct inode *ino, gfp_t gfp_flags)
 {
 	struct pnfs_layoutdriver_type *ld = NFS_SERVER(ino)->pnfs_curr_ld;
-	return ld->alloc_layout_hdr ? ld->alloc_layout_hdr(ino, gfp_flags) :
-		kzalloc(sizeof(struct pnfs_layout_hdr), gfp_flags);
+	return ld->alloc_layout_hdr(ino, gfp_flags);
 }
 
 static void
 pnfs_free_layout_hdr(struct pnfs_layout_hdr *lo)
 {
-	struct pnfs_layoutdriver_type *ld = NFS_SERVER(lo->plh_inode)->pnfs_curr_ld;
+	struct nfs_server *server = NFS_SERVER(lo->plh_inode);
+	struct pnfs_layoutdriver_type *ld = server->pnfs_curr_ld;
+
+	if (!list_empty(&lo->plh_layouts)) {
+		struct nfs_client *clp = server->nfs_client;
+
+		spin_lock(&clp->cl_lock);
+		list_del_init(&lo->plh_layouts);
+		spin_unlock(&clp->cl_lock);
+	}
 	put_rpccred(lo->plh_lc_cred);
-	return ld->alloc_layout_hdr ? ld->free_layout_hdr(lo) : kfree(lo);
+	return ld->free_layout_hdr(lo);
 }
 
 static void
-destroy_layout_hdr(struct pnfs_layout_hdr *lo)
+pnfs_detach_layout_hdr(struct pnfs_layout_hdr *lo)
 {
+	struct nfs_inode *nfsi = NFS_I(lo->plh_inode);
 	dprintk("%s: freeing layout cache %p\n", __func__, lo);
-	BUG_ON(!list_empty(&lo->plh_layouts));
-	NFS_I(lo->plh_inode)->layout = NULL;
-	pnfs_free_layout_hdr(lo);
+	nfsi->layout = NULL;
+	/* Reset MDS Threshold I/O counters */
+	nfsi->write_io = 0;
+	nfsi->read_io = 0;
+}
+
+void
+pnfs_put_layout_hdr(struct pnfs_layout_hdr *lo)
+{
+	struct inode *inode = lo->plh_inode;
+
+	if (atomic_dec_and_lock(&lo->plh_refcount, &inode->i_lock)) {
+		pnfs_detach_layout_hdr(lo);
+		spin_unlock(&inode->i_lock);
+		pnfs_free_layout_hdr(lo);
+	}
+}
+
+static int
+pnfs_iomode_to_fail_bit(u32 iomode)
+{
+	return iomode == IOMODE_RW ?
+		NFS_LAYOUT_RW_FAILED : NFS_LAYOUT_RO_FAILED;
 }
 
 static void
-put_layout_hdr_locked(struct pnfs_layout_hdr *lo)
+pnfs_layout_set_fail_bit(struct pnfs_layout_hdr *lo, int fail_bit)
 {
-	if (atomic_dec_and_test(&lo->plh_refcount))
-		destroy_layout_hdr(lo);
+	lo->plh_retry_timestamp = jiffies;
+	if (!test_and_set_bit(fail_bit, &lo->plh_flags))
+		atomic_inc(&lo->plh_refcount);
 }
 
-void
-put_layout_hdr(struct pnfs_layout_hdr *lo)
+static void
+pnfs_layout_clear_fail_bit(struct pnfs_layout_hdr *lo, int fail_bit)
+{
+	if (test_and_clear_bit(fail_bit, &lo->plh_flags))
+		atomic_dec(&lo->plh_refcount);
+}
+
+static void
+pnfs_layout_io_set_failed(struct pnfs_layout_hdr *lo, u32 iomode)
 {
 	struct inode *inode = lo->plh_inode;
+	struct pnfs_layout_range range = {
+		.iomode = iomode,
+		.offset = 0,
+		.length = NFS4_MAX_UINT64,
+	};
+	LIST_HEAD(head);
 
-	if (atomic_dec_and_lock(&lo->plh_refcount, &inode->i_lock)) {
-		destroy_layout_hdr(lo);
-		spin_unlock(&inode->i_lock);
+	spin_lock(&inode->i_lock);
+	pnfs_layout_set_fail_bit(lo, pnfs_iomode_to_fail_bit(iomode));
+	pnfs_mark_matching_lsegs_invalid(lo, &head, &range);
+	spin_unlock(&inode->i_lock);
+	pnfs_free_lseg_list(&head);
+	dprintk("%s Setting layout IOMODE_%s fail bit\n", __func__,
+			iomode == IOMODE_RW ?  "RW" : "READ");
+}
+
+static bool
+pnfs_layout_io_test_failed(struct pnfs_layout_hdr *lo, u32 iomode)
+{
+	unsigned long start, end;
+	int fail_bit = pnfs_iomode_to_fail_bit(iomode);
+
+	if (test_bit(fail_bit, &lo->plh_flags) == 0)
+		return false;
+	end = jiffies;
+	start = end - PNFS_LAYOUTGET_RETRY_TIMEOUT;
+	if (!time_in_range(lo->plh_retry_timestamp, start, end)) {
+		/* It is time to retry the failed layoutgets */
+		pnfs_layout_clear_fail_bit(lo, fail_bit);
+		return false;
 	}
+	return true;
 }
 
 static void
@@ -249,33 +314,32 @@ init_lseg(struct pnfs_layout_hdr *lo, struct pnfs_layout_segment *lseg)
 	lseg->pls_layout = lo;
 }
 
-static void free_lseg(struct pnfs_layout_segment *lseg)
+static void pnfs_free_lseg(struct pnfs_layout_segment *lseg)
 {
 	struct inode *ino = lseg->pls_layout->plh_inode;
 
 	NFS_SERVER(ino)->pnfs_curr_ld->free_lseg(lseg);
-	/* Matched by get_layout_hdr in pnfs_insert_layout */
-	put_layout_hdr(NFS_I(ino)->layout);
 }
 
 static void
-put_lseg_common(struct pnfs_layout_segment *lseg)
+pnfs_layout_remove_lseg(struct pnfs_layout_hdr *lo,
+		struct pnfs_layout_segment *lseg)
 {
-	struct inode *inode = lseg->pls_layout->plh_inode;
+	struct inode *inode = lo->plh_inode;
 
 	WARN_ON(test_bit(NFS_LSEG_VALID, &lseg->pls_flags));
 	list_del_init(&lseg->pls_list);
-	if (list_empty(&lseg->pls_layout->plh_segs)) {
-		set_bit(NFS_LAYOUT_DESTROYED, &lseg->pls_layout->plh_flags);
-		/* Matched by initial refcount set in alloc_init_layout_hdr */
-		put_layout_hdr_locked(lseg->pls_layout);
-	}
+	/* Matched by pnfs_get_layout_hdr in pnfs_layout_insert_lseg */
+	atomic_dec(&lo->plh_refcount);
+	if (list_empty(&lo->plh_segs))
+		clear_bit(NFS_LAYOUT_BULK_RECALL, &lo->plh_flags);
 	rpc_wake_up(&NFS_SERVER(inode)->roc_rpcwaitq);
 }
 
 void
-put_lseg(struct pnfs_layout_segment *lseg)
+pnfs_put_lseg(struct pnfs_layout_segment *lseg)
 {
+	struct pnfs_layout_hdr *lo;
 	struct inode *inode;
 
 	if (!lseg)
@@ -284,17 +348,17 @@ put_lseg(struct pnfs_layout_segment *lseg)
 	dprintk("%s: lseg %p ref %d valid %d\n", __func__, lseg,
 		atomic_read(&lseg->pls_refcount),
 		test_bit(NFS_LSEG_VALID, &lseg->pls_flags));
-	inode = lseg->pls_layout->plh_inode;
+	lo = lseg->pls_layout;
+	inode = lo->plh_inode;
 	if (atomic_dec_and_lock(&lseg->pls_refcount, &inode->i_lock)) {
-		LIST_HEAD(free_me);
-
-		put_lseg_common(lseg);
-		list_add(&lseg->pls_list, &free_me);
+		pnfs_get_layout_hdr(lo);
+		pnfs_layout_remove_lseg(lo, lseg);
 		spin_unlock(&inode->i_lock);
-		pnfs_free_lseg_list(&free_me);
+		pnfs_free_lseg(lseg);
+		pnfs_put_layout_hdr(lo);
 	}
 }
-EXPORT_SYMBOL_GPL(put_lseg);
+EXPORT_SYMBOL_GPL(pnfs_put_lseg);
 
 static inline u64
 end_offset(u64 start, u64 len)
@@ -305,17 +369,6 @@ end_offset(u64 start, u64 len)
 	return end >= start ? end : NFS4_MAX_UINT64;
 }
 
-/* last octet in a range */
-static inline u64
-last_byte_offset(u64 start, u64 len)
-{
-	u64 end;
-
-	BUG_ON(!len);
-	end = start + len;
-	return end > start ? end - 1 : NFS4_MAX_UINT64;
-}
-
 /*
  * is l2 fully contained in l1?
  *   start1                             end1
@@ -378,7 +431,7 @@ static int mark_lseg_invalid(struct pnfs_layout_segment *lseg,
 		dprintk("%s: lseg %p ref %d\n", __func__, lseg,
 			atomic_read(&lseg->pls_refcount));
 		if (atomic_dec_and_test(&lseg->pls_refcount)) {
-			put_lseg_common(lseg);
+			pnfs_layout_remove_lseg(lseg->pls_layout, lseg);
 			list_add(&lseg->pls_list, tmp_list);
 			rv = 1;
 		}
@@ -390,7 +443,7 @@ static int mark_lseg_invalid(struct pnfs_layout_segment *lseg,
  * after call.
  */
 int
-mark_matching_lsegs_invalid(struct pnfs_layout_hdr *lo,
+pnfs_mark_matching_lsegs_invalid(struct pnfs_layout_hdr *lo,
 			    struct list_head *tmp_list,
 			    struct pnfs_layout_range *recall_range)
 {
@@ -399,14 +452,8 @@ mark_matching_lsegs_invalid(struct pnfs_layout_hdr *lo,
 
 	dprintk("%s:Begin lo %p\n", __func__, lo);
 
-	if (list_empty(&lo->plh_segs)) {
-		/* Reset MDS Threshold I/O counters */
-		NFS_I(lo->plh_inode)->write_io = 0;
-		NFS_I(lo->plh_inode)->read_io = 0;
-		if (!test_and_set_bit(NFS_LAYOUT_DESTROYED, &lo->plh_flags))
-			put_layout_hdr_locked(lo);
+	if (list_empty(&lo->plh_segs))
 		return 0;
-	}
 	list_for_each_entry_safe(lseg, next, &lo->plh_segs, pls_list)
 		if (!recall_range ||
 		    should_free_lseg(&lseg->pls_range, recall_range)) {
@@ -426,25 +473,13 @@ void
 pnfs_free_lseg_list(struct list_head *free_me)
 {
 	struct pnfs_layout_segment *lseg, *tmp;
-	struct pnfs_layout_hdr *lo;
 
 	if (list_empty(free_me))
 		return;
 
-	lo = list_first_entry(free_me, struct pnfs_layout_segment,
-			      pls_list)->pls_layout;
-
-	if (test_bit(NFS_LAYOUT_DESTROYED, &lo->plh_flags)) {
-		struct nfs_client *clp;
-
-		clp = NFS_SERVER(lo->plh_inode)->nfs_client;
-		spin_lock(&clp->cl_lock);
-		list_del_init(&lo->plh_layouts);
-		spin_unlock(&clp->cl_lock);
-	}
 	list_for_each_entry_safe(lseg, tmp, free_me, pls_list) {
 		list_del(&lseg->pls_list);
-		free_lseg(lseg);
+		pnfs_free_lseg(lseg);
 	}
 }
 
@@ -458,10 +493,15 @@ pnfs_destroy_layout(struct nfs_inode *nfsi)
 	lo = nfsi->layout;
 	if (lo) {
 		lo->plh_block_lgets++; /* permanently block new LAYOUTGETs */
-		mark_matching_lsegs_invalid(lo, &tmp_list, NULL);
-	}
-	spin_unlock(&nfsi->vfs_inode.i_lock);
-	pnfs_free_lseg_list(&tmp_list);
+		pnfs_mark_matching_lsegs_invalid(lo, &tmp_list, NULL);
+		pnfs_get_layout_hdr(lo);
+		pnfs_layout_clear_fail_bit(lo, NFS_LAYOUT_RO_FAILED);
+		pnfs_layout_clear_fail_bit(lo, NFS_LAYOUT_RW_FAILED);
+		spin_unlock(&nfsi->vfs_inode.i_lock);
+		pnfs_free_lseg_list(&tmp_list);
+		pnfs_put_layout_hdr(lo);
+	} else
+		spin_unlock(&nfsi->vfs_inode.i_lock);
 }
 EXPORT_SYMBOL_GPL(pnfs_destroy_layout);
 
@@ -498,46 +538,54 @@ pnfs_destroy_all_layouts(struct nfs_client *clp)
 	}
 }
 
+/*
+ * Compare 2 layout stateid sequence ids, to see which is newer,
+ * taking into account wraparound issues.
+ */
+static bool pnfs_seqid_is_newer(u32 s1, u32 s2)
+{
+	return (s32)s1 - (s32)s2 > 0;
+}
+
 /* update lo->plh_stateid with new if is more recent */
 void
 pnfs_set_layout_stateid(struct pnfs_layout_hdr *lo, const nfs4_stateid *new,
 			bool update_barrier)
 {
-	u32 oldseq, newseq;
+	u32 oldseq, newseq, new_barrier;
+	int empty = list_empty(&lo->plh_segs);
 
 	oldseq = be32_to_cpu(lo->plh_stateid.seqid);
 	newseq = be32_to_cpu(new->seqid);
-	if ((int)(newseq - oldseq) > 0) {
+	if (empty || pnfs_seqid_is_newer(newseq, oldseq)) {
 		nfs4_stateid_copy(&lo->plh_stateid, new);
 		if (update_barrier) {
-			u32 new_barrier = be32_to_cpu(new->seqid);
-
-			if ((int)(new_barrier - lo->plh_barrier))
-				lo->plh_barrier = new_barrier;
+			new_barrier = be32_to_cpu(new->seqid);
 		} else {
 			/* Because of wraparound, we want to keep the barrier
-			 * "close" to the current seqids.  It needs to be
-			 * within 2**31 to count as "behind", so if it
-			 * gets too near that limit, give us a litle leeway
-			 * and bring it to within 2**30.
-			 * NOTE - and yes, this is all unsigned arithmetic.
+			 * "close" to the current seqids.
 			 */
-			if (unlikely((newseq - lo->plh_barrier) > (3 << 29)))
-				lo->plh_barrier = newseq - (1 << 30);
+			new_barrier = newseq - atomic_read(&lo->plh_outstanding);
 		}
+		if (empty || pnfs_seqid_is_newer(new_barrier, lo->plh_barrier))
+			lo->plh_barrier = new_barrier;
 	}
 }
 
+static bool
+pnfs_layout_stateid_blocked(const struct pnfs_layout_hdr *lo,
+		const nfs4_stateid *stateid)
+{
+	u32 seqid = be32_to_cpu(stateid->seqid);
+
+	return !pnfs_seqid_is_newer(seqid, lo->plh_barrier);
+}
+
 /* lget is set to 1 if called from inside send_layoutget call chain */
 static bool
-pnfs_layoutgets_blocked(struct pnfs_layout_hdr *lo, nfs4_stateid *stateid,
-			int lget)
+pnfs_layoutgets_blocked(const struct pnfs_layout_hdr *lo, int lget)
 {
-	if ((stateid) &&
-	    (int)(lo->plh_barrier - be32_to_cpu(stateid->seqid)) >= 0)
-		return true;
 	return lo->plh_block_lgets ||
-		test_bit(NFS_LAYOUT_DESTROYED, &lo->plh_flags) ||
 		test_bit(NFS_LAYOUT_BULK_RECALL, &lo->plh_flags) ||
 		(list_empty(&lo->plh_segs) &&
 		 (atomic_read(&lo->plh_outstanding) > lget));
@@ -551,7 +599,7 @@ pnfs_choose_layoutget_stateid(nfs4_stateid *dst, struct pnfs_layout_hdr *lo,
 
 	dprintk("--> %s\n", __func__);
 	spin_lock(&lo->plh_inode->i_lock);
-	if (pnfs_layoutgets_blocked(lo, NULL, 1)) {
+	if (pnfs_layoutgets_blocked(lo, 1)) {
 		status = -EAGAIN;
 	} else if (list_empty(&lo->plh_segs)) {
 		int seq;
@@ -582,32 +630,14 @@ send_layoutget(struct pnfs_layout_hdr *lo,
 	struct inode *ino = lo->plh_inode;
 	struct nfs_server *server = NFS_SERVER(ino);
 	struct nfs4_layoutget *lgp;
-	struct pnfs_layout_segment *lseg = NULL;
-	struct page **pages = NULL;
-	int i;
-	u32 max_resp_sz, max_pages;
+	struct pnfs_layout_segment *lseg;
 
 	dprintk("--> %s\n", __func__);
 
-	BUG_ON(ctx == NULL);
 	lgp = kzalloc(sizeof(*lgp), gfp_flags);
 	if (lgp == NULL)
 		return NULL;
 
-	/* allocate pages for xdr post processing */
-	max_resp_sz = server->nfs_client->cl_session->fc_attrs.max_resp_sz;
-	max_pages = nfs_page_array_len(0, max_resp_sz);
-
-	pages = kcalloc(max_pages, sizeof(struct page *), gfp_flags);
-	if (!pages)
-		goto out_err_free;
-
-	for (i = 0; i < max_pages; i++) {
-		pages[i] = alloc_page(gfp_flags);
-		if (!pages[i])
-			goto out_err_free;
-	}
-
 	lgp->args.minlength = PAGE_CACHE_SIZE;
 	if (lgp->args.minlength > range->length)
 		lgp->args.minlength = range->length;
@@ -616,42 +646,35 @@ send_layoutget(struct pnfs_layout_hdr *lo,
 	lgp->args.type = server->pnfs_curr_ld->id;
 	lgp->args.inode = ino;
 	lgp->args.ctx = get_nfs_open_context(ctx);
-	lgp->args.layout.pages = pages;
-	lgp->args.layout.pglen = max_pages * PAGE_SIZE;
-	lgp->lsegpp = &lseg;
 	lgp->gfp_flags = gfp_flags;
 
 	/* Synchronously retrieve layout information from server and
 	 * store in lseg.
 	 */
-	nfs4_proc_layoutget(lgp);
-	if (!lseg) {
-		/* remember that LAYOUTGET failed and suspend trying */
-		set_bit(lo_fail_bit(range->iomode), &lo->plh_flags);
+	lseg = nfs4_proc_layoutget(lgp, gfp_flags);
+	if (IS_ERR(lseg)) {
+		switch (PTR_ERR(lseg)) {
+		case -ENOMEM:
+		case -ERESTARTSYS:
+			break;
+		default:
+			/* remember that LAYOUTGET failed and suspend trying */
+			pnfs_layout_io_set_failed(lo, range->iomode);
+		}
+		return NULL;
 	}
 
-	/* free xdr pages */
-	for (i = 0; i < max_pages; i++)
-		__free_page(pages[i]);
-	kfree(pages);
-
 	return lseg;
-
-out_err_free:
-	/* free any allocated xdr pages, lgp as it's not used */
-	if (pages) {
-		for (i = 0; i < max_pages; i++) {
-			if (!pages[i])
-				break;
-			__free_page(pages[i]);
-		}
-		kfree(pages);
-	}
-	kfree(lgp);
-	return NULL;
 }
 
-/* Initiates a LAYOUTRETURN(FILE) */
+/*
+ * Initiates a LAYOUTRETURN(FILE), and removes the pnfs_layout_hdr
+ * when the layout segment list is empty.
+ *
+ * Note that a pnfs_layout_hdr can exist with an empty layout segment
+ * list when LAYOUTGET has failed, or when LAYOUTGET succeeded, but the
+ * deviceid is marked invalid.
+ */
 int
 _pnfs_return_layout(struct inode *ino)
 {
@@ -660,21 +683,29 @@ _pnfs_return_layout(struct inode *ino)
 	LIST_HEAD(tmp_list);
 	struct nfs4_layoutreturn *lrp;
 	nfs4_stateid stateid;
-	int status = 0;
+	int status = 0, empty;
 
-	dprintk("--> %s\n", __func__);
+	dprintk("NFS: %s for inode %lu\n", __func__, ino->i_ino);
 
 	spin_lock(&ino->i_lock);
 	lo = nfsi->layout;
 	if (!lo) {
 		spin_unlock(&ino->i_lock);
-		dprintk("%s: no layout to return\n", __func__);
-		return status;
+		dprintk("NFS: %s no layout to return\n", __func__);
+		goto out;
 	}
 	stateid = nfsi->layout->plh_stateid;
 	/* Reference matched in nfs4_layoutreturn_release */
-	get_layout_hdr(lo);
-	mark_matching_lsegs_invalid(lo, &tmp_list, NULL);
+	pnfs_get_layout_hdr(lo);
+	empty = list_empty(&lo->plh_segs);
+	pnfs_mark_matching_lsegs_invalid(lo, &tmp_list, NULL);
+	/* Don't send a LAYOUTRETURN if list was initially empty */
+	if (empty) {
+		spin_unlock(&ino->i_lock);
+		pnfs_put_layout_hdr(lo);
+		dprintk("NFS: %s no layout segments to return\n", __func__);
+		goto out;
+	}
 	lo->plh_block_lgets++;
 	spin_unlock(&ino->i_lock);
 	pnfs_free_lseg_list(&tmp_list);
@@ -684,9 +715,10 @@ _pnfs_return_layout(struct inode *ino)
 	lrp = kzalloc(sizeof(*lrp), GFP_KERNEL);
 	if (unlikely(lrp == NULL)) {
 		status = -ENOMEM;
-		set_bit(NFS_LAYOUT_RW_FAILED, &lo->plh_flags);
-		set_bit(NFS_LAYOUT_RO_FAILED, &lo->plh_flags);
-		put_layout_hdr(lo);
+		spin_lock(&ino->i_lock);
+		lo->plh_block_lgets--;
+		spin_unlock(&ino->i_lock);
+		pnfs_put_layout_hdr(lo);
 		goto out;
 	}
 
@@ -723,7 +755,7 @@ bool pnfs_roc(struct inode *ino)
 	if (!found)
 		goto out_nolayout;
 	lo->plh_block_lgets++;
-	get_layout_hdr(lo); /* matched in pnfs_roc_release */
+	pnfs_get_layout_hdr(lo); /* matched in pnfs_roc_release */
 	spin_unlock(&ino->i_lock);
 	pnfs_free_lseg_list(&tmp_list);
 	return true;
@@ -740,8 +772,12 @@ void pnfs_roc_release(struct inode *ino)
 	spin_lock(&ino->i_lock);
 	lo = NFS_I(ino)->layout;
 	lo->plh_block_lgets--;
-	put_layout_hdr_locked(lo);
-	spin_unlock(&ino->i_lock);
+	if (atomic_dec_and_test(&lo->plh_refcount)) {
+		pnfs_detach_layout_hdr(lo);
+		spin_unlock(&ino->i_lock);
+		pnfs_free_layout_hdr(lo);
+	} else
+		spin_unlock(&ino->i_lock);
 }
 
 void pnfs_roc_set_barrier(struct inode *ino, u32 barrier)
@@ -750,32 +786,34 @@ void pnfs_roc_set_barrier(struct inode *ino, u32 barrier)
 
 	spin_lock(&ino->i_lock);
 	lo = NFS_I(ino)->layout;
-	if ((int)(barrier - lo->plh_barrier) > 0)
+	if (pnfs_seqid_is_newer(barrier, lo->plh_barrier))
 		lo->plh_barrier = barrier;
 	spin_unlock(&ino->i_lock);
 }
 
-bool pnfs_roc_drain(struct inode *ino, u32 *barrier)
+bool pnfs_roc_drain(struct inode *ino, u32 *barrier, struct rpc_task *task)
 {
 	struct nfs_inode *nfsi = NFS_I(ino);
+	struct pnfs_layout_hdr *lo;
 	struct pnfs_layout_segment *lseg;
+	u32 current_seqid;
 	bool found = false;
 
 	spin_lock(&ino->i_lock);
 	list_for_each_entry(lseg, &nfsi->layout->plh_segs, pls_list)
 		if (test_bit(NFS_LSEG_ROC, &lseg->pls_flags)) {
+			rpc_sleep_on(&NFS_SERVER(ino)->roc_rpcwaitq, task, NULL);
 			found = true;
-			break;
+			goto out;
 		}
-	if (!found) {
-		struct pnfs_layout_hdr *lo = nfsi->layout;
-		u32 current_seqid = be32_to_cpu(lo->plh_stateid.seqid);
+	lo = nfsi->layout;
+	current_seqid = be32_to_cpu(lo->plh_stateid.seqid);
 
-		/* Since close does not return a layout stateid for use as
-		 * a barrier, we choose the worst-case barrier.
-		 */
-		*barrier = current_seqid + atomic_read(&lo->plh_outstanding);
-	}
+	/* Since close does not return a layout stateid for use as
+	 * a barrier, we choose the worst-case barrier.
+	 */
+	*barrier = current_seqid + atomic_read(&lo->plh_outstanding);
+out:
 	spin_unlock(&ino->i_lock);
 	return found;
 }
@@ -806,14 +844,13 @@ cmp_layout(struct pnfs_layout_range *l1,
 }
 
 static void
-pnfs_insert_layout(struct pnfs_layout_hdr *lo,
+pnfs_layout_insert_lseg(struct pnfs_layout_hdr *lo,
 		   struct pnfs_layout_segment *lseg)
 {
 	struct pnfs_layout_segment *lp;
 
 	dprintk("%s:Begin\n", __func__);
 
-	assert_spin_locked(&lo->plh_inode->i_lock);
 	list_for_each_entry(lp, &lo->plh_segs, pls_list) {
 		if (cmp_layout(&lseg->pls_range, &lp->pls_range) > 0)
 			continue;
@@ -833,7 +870,7 @@ pnfs_insert_layout(struct pnfs_layout_hdr *lo,
 		__func__, lseg, lseg->pls_range.iomode,
 		lseg->pls_range.offset, lseg->pls_range.length);
 out:
-	get_layout_hdr(lo);
+	pnfs_get_layout_hdr(lo);
 
 	dprintk("%s:Return\n", __func__);
 }
@@ -867,21 +904,19 @@ pnfs_find_alloc_layout(struct inode *ino,
 
 	dprintk("%s Begin ino=%p layout=%p\n", __func__, ino, nfsi->layout);
 
-	assert_spin_locked(&ino->i_lock);
-	if (nfsi->layout) {
-		if (test_bit(NFS_LAYOUT_DESTROYED, &nfsi->layout->plh_flags))
-			return NULL;
-		else
-			return nfsi->layout;
-	}
+	if (nfsi->layout != NULL)
+		goto out_existing;
 	spin_unlock(&ino->i_lock);
 	new = alloc_init_layout_hdr(ino, ctx, gfp_flags);
 	spin_lock(&ino->i_lock);
 
-	if (likely(nfsi->layout == NULL))	/* Won the race? */
+	if (likely(nfsi->layout == NULL)) {	/* Won the race? */
 		nfsi->layout = new;
-	else
+		return new;
+	} else if (new != NULL)
 		pnfs_free_layout_hdr(new);
+out_existing:
+	pnfs_get_layout_hdr(nfsi->layout);
 	return nfsi->layout;
 }
 
@@ -924,11 +959,10 @@ pnfs_find_lseg(struct pnfs_layout_hdr *lo,
 
 	dprintk("%s:Begin\n", __func__);
 
-	assert_spin_locked(&lo->plh_inode->i_lock);
 	list_for_each_entry(lseg, &lo->plh_segs, pls_list) {
 		if (test_bit(NFS_LSEG_VALID, &lseg->pls_flags) &&
 		    is_matching_lseg(&lseg->pls_range, range)) {
-			ret = get_lseg(lseg);
+			ret = pnfs_get_lseg(lseg);
 			break;
 		}
 		if (lseg->pls_range.offset > range->offset)
@@ -1033,7 +1067,6 @@ pnfs_update_layout(struct inode *ino,
 		.length = count,
 	};
 	unsigned pg_offset;
-	struct nfs_inode *nfsi = NFS_I(ino);
 	struct nfs_server *server = NFS_SERVER(ino);
 	struct nfs_client *clp = server->nfs_client;
 	struct pnfs_layout_hdr *lo;
@@ -1041,16 +1074,16 @@ pnfs_update_layout(struct inode *ino,
 	bool first = false;
 
 	if (!pnfs_enabled_sb(NFS_SERVER(ino)))
-		return NULL;
+		goto out;
 
 	if (pnfs_within_mdsthreshold(ctx, ino, iomode))
-		return NULL;
+		goto out;
 
 	spin_lock(&ino->i_lock);
 	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;
+		spin_unlock(&ino->i_lock);
+		goto out;
 	}
 
 	/* Do we even need to bother with this? */
@@ -1060,7 +1093,7 @@ pnfs_update_layout(struct inode *ino,
 	}
 
 	/* if LAYOUTGET already failed once we don't try again */
-	if (test_bit(lo_fail_bit(iomode), &nfsi->layout->plh_flags))
+	if (pnfs_layout_io_test_failed(lo, iomode))
 		goto out_unlock;
 
 	/* Check to see if the layout for the given range already exists */
@@ -1068,20 +1101,19 @@ pnfs_update_layout(struct inode *ino,
 	if (lseg)
 		goto out_unlock;
 
-	if (pnfs_layoutgets_blocked(lo, NULL, 0))
+	if (pnfs_layoutgets_blocked(lo, 0))
 		goto out_unlock;
 	atomic_inc(&lo->plh_outstanding);
 
-	get_layout_hdr(lo);
 	if (list_empty(&lo->plh_segs))
 		first = true;
+
 	spin_unlock(&ino->i_lock);
 	if (first) {
 		/* The lo must be on the clp list if there is any
 		 * chance of a CB_LAYOUTRECALL(FILE) coming in.
 		 */
 		spin_lock(&clp->cl_lock);
-		BUG_ON(!list_empty(&lo->plh_layouts));
 		list_add_tail(&lo->plh_layouts, &server->layouts);
 		spin_unlock(&clp->cl_lock);
 	}
@@ -1095,24 +1127,26 @@ pnfs_update_layout(struct inode *ino,
 		arg.length = PAGE_CACHE_ALIGN(arg.length);
 
 	lseg = send_layoutget(lo, ctx, &arg, gfp_flags);
-	if (!lseg && first) {
-		spin_lock(&clp->cl_lock);
-		list_del_init(&lo->plh_layouts);
-		spin_unlock(&clp->cl_lock);
-	}
 	atomic_dec(&lo->plh_outstanding);
-	put_layout_hdr(lo);
+out_put_layout_hdr:
+	pnfs_put_layout_hdr(lo);
 out:
-	dprintk("%s end, state 0x%lx lseg %p\n", __func__,
-		nfsi->layout ? nfsi->layout->plh_flags : -1, lseg);
+	dprintk("%s: inode %s/%llu pNFS layout segment %s for "
+			"(%s, offset: %llu, length: %llu)\n",
+			__func__, ino->i_sb->s_id,
+			(unsigned long long)NFS_FILEID(ino),
+			lseg == NULL ? "not found" : "found",
+			iomode==IOMODE_RW ?  "read/write" : "read-only",
+			(unsigned long long)pos,
+			(unsigned long long)count);
 	return lseg;
 out_unlock:
 	spin_unlock(&ino->i_lock);
-	goto out;
+	goto out_put_layout_hdr;
 }
 EXPORT_SYMBOL_GPL(pnfs_update_layout);
 
-int
+struct pnfs_layout_segment *
 pnfs_layout_process(struct nfs4_layoutget *lgp)
 {
 	struct pnfs_layout_hdr *lo = NFS_I(lgp->args.inode)->layout;
@@ -1139,25 +1173,29 @@ pnfs_layout_process(struct nfs4_layoutget *lgp)
 		goto out_forget_reply;
 	}
 
-	if (pnfs_layoutgets_blocked(lo, &res->stateid, 1)) {
+	if (pnfs_layoutgets_blocked(lo, 1) ||
+	    pnfs_layout_stateid_blocked(lo, &res->stateid)) {
 		dprintk("%s forget reply due to state\n", __func__);
 		goto out_forget_reply;
 	}
+
+	/* Done processing layoutget. Set the layout stateid */
+	pnfs_set_layout_stateid(lo, &res->stateid, false);
+
 	init_lseg(lo, lseg);
 	lseg->pls_range = res->range;
-	*lgp->lsegpp = get_lseg(lseg);
-	pnfs_insert_layout(lo, lseg);
+	pnfs_get_lseg(lseg);
+	pnfs_layout_insert_lseg(lo, lseg);
 
 	if (res->return_on_close) {
 		set_bit(NFS_LSEG_ROC, &lseg->pls_flags);
 		set_bit(NFS_LAYOUT_ROC, &lo->plh_flags);
 	}
 
-	/* Done processing layoutget. Set the layout stateid */
-	pnfs_set_layout_stateid(lo, &res->stateid, false);
 	spin_unlock(&ino->i_lock);
+	return lseg;
 out:
-	return status;
+	return ERR_PTR(status);
 
 out_forget_reply:
 	spin_unlock(&ino->i_lock);
@@ -1169,16 +1207,24 @@ out_forget_reply:
 void
 pnfs_generic_pg_init_read(struct nfs_pageio_descriptor *pgio, struct nfs_page *req)
 {
-	BUG_ON(pgio->pg_lseg != NULL);
+	u64 rd_size = req->wb_bytes;
+
+	WARN_ON_ONCE(pgio->pg_lseg != NULL);
 
 	if (req->wb_offset != req->wb_pgbase) {
 		nfs_pageio_reset_read_mds(pgio);
 		return;
 	}
+
+	if (pgio->pg_dreq == NULL)
+		rd_size = i_size_read(pgio->pg_inode) - req_offset(req);
+	else
+		rd_size = nfs_dreq_bytes_left(pgio->pg_dreq);
+
 	pgio->pg_lseg = pnfs_update_layout(pgio->pg_inode,
 					   req->wb_context,
 					   req_offset(req),
-					   req->wb_bytes,
+					   rd_size,
 					   IOMODE_READ,
 					   GFP_KERNEL);
 	/* If no lseg, fall back to read through mds */
@@ -1189,18 +1235,20 @@ pnfs_generic_pg_init_read(struct nfs_pageio_descriptor *pgio, struct nfs_page *r
 EXPORT_SYMBOL_GPL(pnfs_generic_pg_init_read);
 
 void
-pnfs_generic_pg_init_write(struct nfs_pageio_descriptor *pgio, struct nfs_page *req)
+pnfs_generic_pg_init_write(struct nfs_pageio_descriptor *pgio,
+			   struct nfs_page *req, u64 wb_size)
 {
-	BUG_ON(pgio->pg_lseg != NULL);
+	WARN_ON_ONCE(pgio->pg_lseg != NULL);
 
 	if (req->wb_offset != req->wb_pgbase) {
 		nfs_pageio_reset_write_mds(pgio);
 		return;
 	}
+
 	pgio->pg_lseg = pnfs_update_layout(pgio->pg_inode,
 					   req->wb_context,
 					   req_offset(req),
-					   req->wb_bytes,
+					   wb_size,
 					   IOMODE_RW,
 					   GFP_NOFS);
 	/* If no lseg, fall back to write through mds */
@@ -1209,7 +1257,7 @@ pnfs_generic_pg_init_write(struct nfs_pageio_descriptor *pgio, struct nfs_page *
 }
 EXPORT_SYMBOL_GPL(pnfs_generic_pg_init_write);
 
-bool
+void
 pnfs_pageio_init_read(struct nfs_pageio_descriptor *pgio, struct inode *inode,
 		      const struct nfs_pgio_completion_ops *compl_ops)
 {
@@ -1217,13 +1265,12 @@ pnfs_pageio_init_read(struct nfs_pageio_descriptor *pgio, struct inode *inode,
 	struct pnfs_layoutdriver_type *ld = server->pnfs_curr_ld;
 
 	if (ld == NULL)
-		return false;
-	nfs_pageio_init(pgio, inode, ld->pg_read_ops, compl_ops,
-			server->rsize, 0);
-	return true;
+		nfs_pageio_init_read(pgio, inode, compl_ops);
+	else
+		nfs_pageio_init(pgio, inode, ld->pg_read_ops, compl_ops, server->rsize, 0);
 }
 
-bool
+void
 pnfs_pageio_init_write(struct nfs_pageio_descriptor *pgio, struct inode *inode,
 		       int ioflags,
 		       const struct nfs_pgio_completion_ops *compl_ops)
@@ -1232,10 +1279,9 @@ pnfs_pageio_init_write(struct nfs_pageio_descriptor *pgio, struct inode *inode,
 	struct pnfs_layoutdriver_type *ld = server->pnfs_curr_ld;
 
 	if (ld == NULL)
-		return false;
-	nfs_pageio_init(pgio, inode, ld->pg_write_ops, compl_ops,
-			server->wsize, ioflags);
-	return true;
+		nfs_pageio_init_write(pgio, inode, ioflags, compl_ops);
+	else
+		nfs_pageio_init(pgio, inode, ld->pg_write_ops, compl_ops, server->wsize, ioflags);
 }
 
 bool
@@ -1272,7 +1318,7 @@ int pnfs_write_done_resend_to_mds(struct inode *inode,
 	LIST_HEAD(failed);
 
 	/* Resend all requests through the MDS */
-	nfs_pageio_init_write_mds(&pgio, inode, FLUSH_STABLE, compl_ops);
+	nfs_pageio_init_write(&pgio, inode, FLUSH_STABLE, compl_ops);
 	while (!list_empty(head)) {
 		struct nfs_page *req = nfs_list_entry(head->next);
 
@@ -1380,14 +1426,15 @@ pnfs_do_multiple_writes(struct nfs_pageio_descriptor *desc, struct list_head *he
 		if (trypnfs == PNFS_NOT_ATTEMPTED)
 			pnfs_write_through_mds(desc, data);
 	}
-	put_lseg(lseg);
+	pnfs_put_lseg(lseg);
 }
 
 static void pnfs_writehdr_free(struct nfs_pgio_header *hdr)
 {
-	put_lseg(hdr->lseg);
+	pnfs_put_lseg(hdr->lseg);
 	nfs_writehdr_free(hdr);
 }
+EXPORT_SYMBOL_GPL(pnfs_writehdr_free);
 
 int
 pnfs_generic_pg_writepages(struct nfs_pageio_descriptor *desc)
@@ -1399,17 +1446,17 @@ pnfs_generic_pg_writepages(struct nfs_pageio_descriptor *desc)
 	whdr = nfs_writehdr_alloc();
 	if (!whdr) {
 		desc->pg_completion_ops->error_cleanup(&desc->pg_list);
-		put_lseg(desc->pg_lseg);
+		pnfs_put_lseg(desc->pg_lseg);
 		desc->pg_lseg = NULL;
 		return -ENOMEM;
 	}
 	hdr = &whdr->header;
 	nfs_pgheader_init(desc, hdr, pnfs_writehdr_free);
-	hdr->lseg = get_lseg(desc->pg_lseg);
+	hdr->lseg = pnfs_get_lseg(desc->pg_lseg);
 	atomic_inc(&hdr->refcnt);
 	ret = nfs_generic_flush(desc, hdr);
 	if (ret != 0) {
-		put_lseg(desc->pg_lseg);
+		pnfs_put_lseg(desc->pg_lseg);
 		desc->pg_lseg = NULL;
 	} else
 		pnfs_do_multiple_writes(desc, &hdr->rpc_list, desc->pg_ioflags);
@@ -1427,7 +1474,7 @@ int pnfs_read_done_resend_to_mds(struct inode *inode,
 	LIST_HEAD(failed);
 
 	/* Resend all requests through the MDS */
-	nfs_pageio_init_read_mds(&pgio, inode, compl_ops);
+	nfs_pageio_init_read(&pgio, inode, compl_ops);
 	while (!list_empty(head)) {
 		struct nfs_page *req = nfs_list_entry(head->next);
 
@@ -1534,14 +1581,15 @@ pnfs_do_multiple_reads(struct nfs_pageio_descriptor *desc, struct list_head *hea
 		if (trypnfs == PNFS_NOT_ATTEMPTED)
 			pnfs_read_through_mds(desc, data);
 	}
-	put_lseg(lseg);
+	pnfs_put_lseg(lseg);
 }
 
 static void pnfs_readhdr_free(struct nfs_pgio_header *hdr)
 {
-	put_lseg(hdr->lseg);
+	pnfs_put_lseg(hdr->lseg);
 	nfs_readhdr_free(hdr);
 }
+EXPORT_SYMBOL_GPL(pnfs_readhdr_free);
 
 int
 pnfs_generic_pg_readpages(struct nfs_pageio_descriptor *desc)
@@ -1554,17 +1602,17 @@ pnfs_generic_pg_readpages(struct nfs_pageio_descriptor *desc)
 	if (!rhdr) {
 		desc->pg_completion_ops->error_cleanup(&desc->pg_list);
 		ret = -ENOMEM;
-		put_lseg(desc->pg_lseg);
+		pnfs_put_lseg(desc->pg_lseg);
 		desc->pg_lseg = NULL;
 		return ret;
 	}
 	hdr = &rhdr->header;
 	nfs_pgheader_init(desc, hdr, pnfs_readhdr_free);
-	hdr->lseg = get_lseg(desc->pg_lseg);
+	hdr->lseg = pnfs_get_lseg(desc->pg_lseg);
 	atomic_inc(&hdr->refcnt);
 	ret = nfs_generic_pagein(desc, hdr);
 	if (ret != 0) {
-		put_lseg(desc->pg_lseg);
+		pnfs_put_lseg(desc->pg_lseg);
 		desc->pg_lseg = NULL;
 	} else
 		pnfs_do_multiple_reads(desc, &hdr->rpc_list);
@@ -1590,13 +1638,7 @@ static void pnfs_list_write_lseg(struct inode *inode, struct list_head *listp)
 
 void pnfs_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);
-	}
+	pnfs_layout_io_set_failed(lseg->pls_layout, lseg->pls_range.iomode);
 }
 EXPORT_SYMBOL_GPL(pnfs_set_lo_fail);
 
@@ -1617,7 +1659,7 @@ pnfs_set_layoutcommit(struct nfs_write_data *wdata)
 	}
 	if (!test_and_set_bit(NFS_LSEG_LAYOUTCOMMIT, &hdr->lseg->pls_flags)) {
 		/* references matched in nfs4_layoutcommit_release */
-		get_lseg(hdr->lseg);
+		pnfs_get_lseg(hdr->lseg);
 	}
 	if (end_pos > nfsi->layout->plh_lwb)
 		nfsi->layout->plh_lwb = end_pos;
diff --git a/fs/nfs/pnfs.h b/fs/nfs/pnfs.h
index 64f90d845f6..dbf7bba52da 100644
--- a/fs/nfs/pnfs.h
+++ b/fs/nfs/pnfs.h
@@ -62,8 +62,7 @@ enum {
 	NFS_LAYOUT_RW_FAILED,		/* get rw layout failed stop trying */
 	NFS_LAYOUT_BULK_RECALL,		/* bulk recall affecting layout */
 	NFS_LAYOUT_ROC,			/* some lseg had roc bit set */
-	NFS_LAYOUT_DESTROYED,		/* no new use of layout allowed */
-	NFS_LAYOUT_INVALID,		/* layout is being destroyed */
+	NFS_LAYOUT_RETURN,		/* Return this layout ASAP */
 };
 
 enum layoutdriver_policy_flags {
@@ -139,6 +138,7 @@ struct pnfs_layout_hdr {
 	atomic_t		plh_outstanding; /* number of RPCs out */
 	unsigned long		plh_block_lgets; /* block LAYOUTGET if >0 */
 	u32			plh_barrier; /* ignore lower seqids */
+	unsigned long		plh_retry_timestamp;
 	unsigned long		plh_flags;
 	loff_t			plh_lwb; /* last write byte for layoutcommit */
 	struct rpc_cred		*plh_lc_cred; /* layoutcommit cred */
@@ -171,44 +171,45 @@ extern int nfs4_proc_getdevicelist(struct nfs_server *server,
 				   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);
+extern struct pnfs_layout_segment* nfs4_proc_layoutget(struct nfs4_layoutget *lgp, gfp_t gfp_flags);
 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);
+void pnfs_get_layout_hdr(struct pnfs_layout_hdr *lo);
+void pnfs_put_lseg(struct pnfs_layout_segment *lseg);
 
-bool pnfs_pageio_init_read(struct nfs_pageio_descriptor *, struct inode *,
+void pnfs_pageio_init_read(struct nfs_pageio_descriptor *, struct inode *,
 			   const struct nfs_pgio_completion_ops *);
-bool pnfs_pageio_init_write(struct nfs_pageio_descriptor *, struct inode *,
+void pnfs_pageio_init_write(struct nfs_pageio_descriptor *, struct inode *,
 			    int, const struct nfs_pgio_completion_ops *);
 
 void set_pnfs_layoutdriver(struct nfs_server *, const struct nfs_fh *, u32);
 void unset_pnfs_layoutdriver(struct nfs_server *);
 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 *);
+void pnfs_generic_pg_init_write(struct nfs_pageio_descriptor *pgio,
+			        struct nfs_page *req, u64 wb_size);
 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);
 void pnfs_set_lo_fail(struct pnfs_layout_segment *lseg);
-int pnfs_layout_process(struct nfs4_layoutget *lgp);
+struct pnfs_layout_segment *pnfs_layout_process(struct nfs4_layoutget *lgp);
 void pnfs_free_lseg_list(struct list_head *tmp_list);
 void pnfs_destroy_layout(struct nfs_inode *);
 void pnfs_destroy_all_layouts(struct nfs_client *);
-void put_layout_hdr(struct pnfs_layout_hdr *lo);
+void pnfs_put_layout_hdr(struct pnfs_layout_hdr *lo);
 void pnfs_set_layout_stateid(struct pnfs_layout_hdr *lo,
 			     const nfs4_stateid *new,
 			     bool update_barrier);
 int pnfs_choose_layoutget_stateid(nfs4_stateid *dst,
 				  struct pnfs_layout_hdr *lo,
 				  struct nfs4_state *open_state);
-int mark_matching_lsegs_invalid(struct pnfs_layout_hdr *lo,
+int pnfs_mark_matching_lsegs_invalid(struct pnfs_layout_hdr *lo,
 				struct list_head *tmp_list,
 				struct pnfs_layout_range *recall_range);
 bool pnfs_roc(struct inode *ino);
 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);
+bool pnfs_roc_drain(struct inode *ino, u32 *barrier, struct rpc_task *task);
 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);
@@ -232,6 +233,7 @@ struct nfs4_threshold *pnfs_mdsthreshold_alloc(void);
 /* nfs4_deviceid_flags */
 enum {
 	NFS_DEVICEID_INVALID = 0,       /* set when MDS clientid recalled */
+	NFS_DEVICEID_UNAVAILABLE,	/* device temporarily unavailable */
 };
 
 /* pnfs_dev.c */
@@ -241,6 +243,7 @@ struct nfs4_deviceid_node {
 	const struct pnfs_layoutdriver_type *ld;
 	const struct nfs_client		*nfs_client;
 	unsigned long 			flags;
+	unsigned long			timestamp_unavailable;
 	struct nfs4_deviceid		deviceid;
 	atomic_t			ref;
 };
@@ -253,16 +256,12 @@ void nfs4_init_deviceid_node(struct nfs4_deviceid_node *,
 			     const struct nfs4_deviceid *);
 struct nfs4_deviceid_node *nfs4_insert_deviceid_node(struct nfs4_deviceid_node *);
 bool nfs4_put_deviceid_node(struct nfs4_deviceid_node *);
+void nfs4_mark_deviceid_unavailable(struct nfs4_deviceid_node *node);
+bool nfs4_test_deviceid_unavailable(struct nfs4_deviceid_node *node);
 void nfs4_deviceid_purge_client(const struct nfs_client *);
 
-static inline int lo_fail_bit(u32 iomode)
-{
-	return iomode == IOMODE_RW ?
-			 NFS_LAYOUT_RW_FAILED : NFS_LAYOUT_RO_FAILED;
-}
-
 static inline struct pnfs_layout_segment *
-get_lseg(struct pnfs_layout_segment *lseg)
+pnfs_get_lseg(struct pnfs_layout_segment *lseg)
 {
 	if (lseg) {
 		atomic_inc(&lseg->pls_refcount);
@@ -387,12 +386,12 @@ static inline void pnfs_destroy_layout(struct nfs_inode *nfsi)
 }
 
 static inline struct pnfs_layout_segment *
-get_lseg(struct pnfs_layout_segment *lseg)
+pnfs_get_lseg(struct pnfs_layout_segment *lseg)
 {
 	return NULL;
 }
 
-static inline void put_lseg(struct pnfs_layout_segment *lseg)
+static inline void pnfs_put_lseg(struct pnfs_layout_segment *lseg)
 {
 }
 
@@ -424,7 +423,7 @@ pnfs_roc_set_barrier(struct inode *ino, u32 barrier)
 }
 
 static inline bool
-pnfs_roc_drain(struct inode *ino, u32 *barrier)
+pnfs_roc_drain(struct inode *ino, u32 *barrier, struct rpc_task *task)
 {
 	return false;
 }
@@ -438,16 +437,16 @@ static inline void unset_pnfs_layoutdriver(struct nfs_server *s)
 {
 }
 
-static inline bool pnfs_pageio_init_read(struct nfs_pageio_descriptor *pgio, struct inode *inode,
+static inline void pnfs_pageio_init_read(struct nfs_pageio_descriptor *pgio, struct inode *inode,
 					 const struct nfs_pgio_completion_ops *compl_ops)
 {
-	return false;
+	nfs_pageio_init_read(pgio, inode, compl_ops);
 }
 
-static inline bool pnfs_pageio_init_write(struct nfs_pageio_descriptor *pgio, struct inode *inode, int ioflags,
+static inline void pnfs_pageio_init_write(struct nfs_pageio_descriptor *pgio, struct inode *inode, int ioflags,
 					  const struct nfs_pgio_completion_ops *compl_ops)
 {
-	return false;
+	nfs_pageio_init_write(pgio, inode, ioflags, compl_ops);
 }
 
 static inline int
diff --git a/fs/nfs/pnfs_dev.c b/fs/nfs/pnfs_dev.c
index 73f701f1f4d..d35b62e83ea 100644
--- a/fs/nfs/pnfs_dev.c
+++ b/fs/nfs/pnfs_dev.c
@@ -40,6 +40,8 @@
 #define NFS4_DEVICE_ID_HASH_SIZE	(1 << NFS4_DEVICE_ID_HASH_BITS)
 #define NFS4_DEVICE_ID_HASH_MASK	(NFS4_DEVICE_ID_HASH_SIZE - 1)
 
+#define PNFS_DEVICE_RETRY_TIMEOUT (120*HZ)
+
 static struct hlist_head nfs4_deviceid_cache[NFS4_DEVICE_ID_HASH_SIZE];
 static DEFINE_SPINLOCK(nfs4_deviceid_lock);
 
@@ -218,6 +220,30 @@ nfs4_put_deviceid_node(struct nfs4_deviceid_node *d)
 }
 EXPORT_SYMBOL_GPL(nfs4_put_deviceid_node);
 
+void
+nfs4_mark_deviceid_unavailable(struct nfs4_deviceid_node *node)
+{
+	node->timestamp_unavailable = jiffies;
+	set_bit(NFS_DEVICEID_UNAVAILABLE, &node->flags);
+}
+EXPORT_SYMBOL_GPL(nfs4_mark_deviceid_unavailable);
+
+bool
+nfs4_test_deviceid_unavailable(struct nfs4_deviceid_node *node)
+{
+	if (test_bit(NFS_DEVICEID_UNAVAILABLE, &node->flags)) {
+		unsigned long start, end;
+
+		end = jiffies;
+		start = end - PNFS_DEVICE_RETRY_TIMEOUT;
+		if (time_in_range(node->timestamp_unavailable, start, end))
+			return true;
+		clear_bit(NFS_DEVICEID_UNAVAILABLE, &node->flags);
+	}
+	return false;
+}
+EXPORT_SYMBOL_GPL(nfs4_test_deviceid_unavailable);
+
 static void
 _deviceid_purge_client(const struct nfs_client *clp, long hash)
 {
@@ -276,3 +302,4 @@ nfs4_deviceid_mark_client_invalid(struct nfs_client *clp)
 	}
 	rcu_read_unlock();
 }
+
diff --git a/fs/nfs/proc.c b/fs/nfs/proc.c
index 617c7419a08..f084dac948e 100644
--- a/fs/nfs/proc.c
+++ b/fs/nfs/proc.c
@@ -47,39 +47,6 @@
 #define NFSDBG_FACILITY		NFSDBG_PROC
 
 /*
- * wrapper to handle the -EKEYEXPIRED error message. This should generally
- * only happen if using krb5 auth and a user's TGT expires. NFSv2 doesn't
- * support the NFSERR_JUKEBOX error code, but we handle this situation in the
- * same way that we handle that error with NFSv3.
- */
-static int
-nfs_rpc_wrapper(struct rpc_clnt *clnt, struct rpc_message *msg, int flags)
-{
-	int res;
-	do {
-		res = rpc_call_sync(clnt, msg, flags);
-		if (res != -EKEYEXPIRED)
-			break;
-		freezable_schedule_timeout_killable(NFS_JUKEBOX_RETRY_TIME);
-		res = -ERESTARTSYS;
-	} while (!fatal_signal_pending(current));
-	return res;
-}
-
-#define rpc_call_sync(clnt, msg, flags)	nfs_rpc_wrapper(clnt, msg, flags)
-
-static int
-nfs_async_handle_expired_key(struct rpc_task *task)
-{
-	if (task->tk_status != -EKEYEXPIRED)
-		return 0;
-	task->tk_status = 0;
-	rpc_restart_call(task);
-	rpc_delay(task, NFS_JUKEBOX_RETRY_TIME);
-	return 1;
-}
-
-/*
  * Bare-bones access to getattr: this is for nfs_read_super.
  */
 static int
@@ -259,7 +226,7 @@ static void nfs_free_createdata(const struct nfs_createdata *data)
 
 static int
 nfs_proc_create(struct inode *dir, struct dentry *dentry, struct iattr *sattr,
-		int flags, struct nfs_open_context *ctx)
+		int flags)
 {
 	struct nfs_createdata *data;
 	struct rpc_message msg = {
@@ -364,8 +331,6 @@ static void nfs_proc_unlink_rpc_prepare(struct rpc_task *task, struct nfs_unlink
 
 static int nfs_proc_unlink_done(struct rpc_task *task, struct inode *dir)
 {
-	if (nfs_async_handle_expired_key(task))
-		return 0;
 	nfs_mark_for_revalidate(dir);
 	return 1;
 }
@@ -385,8 +350,6 @@ static int
 nfs_proc_rename_done(struct rpc_task *task, struct inode *old_dir,
 		     struct inode *new_dir)
 {
-	if (nfs_async_handle_expired_key(task))
-		return 0;
 	nfs_mark_for_revalidate(old_dir);
 	nfs_mark_for_revalidate(new_dir);
 	return 1;
@@ -642,9 +605,6 @@ static int nfs_read_done(struct rpc_task *task, struct nfs_read_data *data)
 {
 	struct inode *inode = data->header->inode;
 
-	if (nfs_async_handle_expired_key(task))
-		return -EAGAIN;
-
 	nfs_invalidate_atime(inode);
 	if (task->tk_status >= 0) {
 		nfs_refresh_inode(inode, data->res.fattr);
@@ -671,9 +631,6 @@ static int nfs_write_done(struct rpc_task *task, struct nfs_write_data *data)
 {
 	struct inode *inode = data->header->inode;
 
-	if (nfs_async_handle_expired_key(task))
-		return -EAGAIN;
-
 	if (task->tk_status >= 0)
 		nfs_post_op_update_inode_force_wcc(inode, data->res.fattr);
 	return 0;
@@ -734,6 +691,38 @@ out_einval:
 	return -EINVAL;
 }
 
+static int nfs_have_delegation(struct inode *inode, fmode_t flags)
+{
+	return 0;
+}
+
+static int nfs_return_delegation(struct inode *inode)
+{
+	nfs_wb_all(inode);
+	return 0;
+}
+
+static const struct inode_operations nfs_dir_inode_operations = {
+	.create		= nfs_create,
+	.lookup		= nfs_lookup,
+	.link		= nfs_link,
+	.unlink		= nfs_unlink,
+	.symlink	= nfs_symlink,
+	.mkdir		= nfs_mkdir,
+	.rmdir		= nfs_rmdir,
+	.mknod		= nfs_mknod,
+	.rename		= nfs_rename,
+	.permission	= nfs_permission,
+	.getattr	= nfs_getattr,
+	.setattr	= nfs_setattr,
+};
+
+static const struct inode_operations nfs_file_inode_operations = {
+	.permission	= nfs_permission,
+	.getattr	= nfs_getattr,
+	.setattr	= nfs_setattr,
+};
+
 const struct nfs_rpc_ops nfs_v2_clientops = {
 	.version	= 2,		       /* protocol version */
 	.dentry_ops	= &nfs_dentry_operations,
@@ -742,6 +731,7 @@ const struct nfs_rpc_ops nfs_v2_clientops = {
 	.file_ops	= &nfs_file_operations,
 	.getroot	= nfs_proc_get_root,
 	.submount	= nfs_submount,
+	.try_mount	= nfs_try_mount,
 	.getattr	= nfs_proc_getattr,
 	.setattr	= nfs_proc_setattr,
 	.lookup		= nfs_proc_lookup,
@@ -767,9 +757,11 @@ const struct nfs_rpc_ops nfs_v2_clientops = {
 	.pathconf	= nfs_proc_pathconf,
 	.decode_dirent	= nfs2_decode_dirent,
 	.read_setup	= nfs_proc_read_setup,
+	.read_pageio_init = nfs_pageio_init_read,
 	.read_rpc_prepare = nfs_proc_read_rpc_prepare,
 	.read_done	= nfs_read_done,
 	.write_setup	= nfs_proc_write_setup,
+	.write_pageio_init = nfs_pageio_init_write,
 	.write_rpc_prepare = nfs_proc_write_rpc_prepare,
 	.write_done	= nfs_write_done,
 	.commit_setup	= nfs_proc_commit_setup,
@@ -777,5 +769,11 @@ const struct nfs_rpc_ops nfs_v2_clientops = {
 	.lock		= nfs_proc_lock,
 	.lock_check_bounds = nfs_lock_check_bounds,
 	.close_context	= nfs_close_context,
+	.have_delegation = nfs_have_delegation,
+	.return_delegation = nfs_return_delegation,
+	.alloc_client	= nfs_alloc_client,
 	.init_client	= nfs_init_client,
+	.free_client	= nfs_free_client,
+	.create_server	= nfs_create_server,
+	.clone_server	= nfs_clone_server,
 };
diff --git a/fs/nfs/read.c b/fs/nfs/read.c
index 86ced783621..a5e5d9899d5 100644
--- a/fs/nfs/read.c
+++ b/fs/nfs/read.c
@@ -20,8 +20,6 @@
 #include <linux/nfs_page.h>
 #include <linux/module.h>
 
-#include "pnfs.h"
-
 #include "nfs4_fs.h"
 #include "internal.h"
 #include "iostat.h"
@@ -50,6 +48,7 @@ struct nfs_read_header *nfs_readhdr_alloc(void)
 	}
 	return rhdr;
 }
+EXPORT_SYMBOL_GPL(nfs_readhdr_alloc);
 
 static struct nfs_read_data *nfs_readdata_alloc(struct nfs_pgio_header *hdr,
 						unsigned int pagecount)
@@ -82,6 +81,7 @@ void nfs_readhdr_free(struct nfs_pgio_header *hdr)
 
 	kmem_cache_free(nfs_rdata_cachep, rhdr);
 }
+EXPORT_SYMBOL_GPL(nfs_readhdr_free);
 
 void nfs_readdata_release(struct nfs_read_data *rdata)
 {
@@ -91,13 +91,18 @@ void nfs_readdata_release(struct nfs_read_data *rdata)
 	put_nfs_open_context(rdata->args.context);
 	if (rdata->pages.pagevec != rdata->pages.page_array)
 		kfree(rdata->pages.pagevec);
-	if (rdata != &read_header->rpc_data)
-		kfree(rdata);
-	else
+	if (rdata == &read_header->rpc_data) {
 		rdata->header = NULL;
+		rdata = NULL;
+	}
 	if (atomic_dec_and_test(&hdr->refcnt))
 		hdr->completion_ops->completion(hdr);
+	/* Note: we only free the rpc_task after callbacks are done.
+	 * See the comment in rpc_free_task() for why
+	 */
+	kfree(rdata);
 }
+EXPORT_SYMBOL_GPL(nfs_readdata_release);
 
 static
 int nfs_return_empty_page(struct page *page)
@@ -108,13 +113,14 @@ int nfs_return_empty_page(struct page *page)
 	return 0;
 }
 
-void nfs_pageio_init_read_mds(struct nfs_pageio_descriptor *pgio,
+void nfs_pageio_init_read(struct nfs_pageio_descriptor *pgio,
 			      struct inode *inode,
 			      const struct nfs_pgio_completion_ops *compl_ops)
 {
 	nfs_pageio_init(pgio, inode, &nfs_pageio_read_ops, compl_ops,
 			NFS_SERVER(inode)->rsize, 0);
 }
+EXPORT_SYMBOL_GPL(nfs_pageio_init_read);
 
 void nfs_pageio_reset_read_mds(struct nfs_pageio_descriptor *pgio)
 {
@@ -123,14 +129,6 @@ void nfs_pageio_reset_read_mds(struct nfs_pageio_descriptor *pgio)
 }
 EXPORT_SYMBOL_GPL(nfs_pageio_reset_read_mds);
 
-void nfs_pageio_init_read(struct nfs_pageio_descriptor *pgio,
-			  struct inode *inode,
-			  const struct nfs_pgio_completion_ops *compl_ops)
-{
-	if (!pnfs_pageio_init_read(pgio, inode, compl_ops))
-		nfs_pageio_init_read_mds(pgio, inode, compl_ops);
-}
-
 int nfs_readpage_async(struct nfs_open_context *ctx, struct inode *inode,
 		       struct page *page)
 {
@@ -149,7 +147,7 @@ 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_read(&pgio, inode, &nfs_async_read_completion_ops);
+	NFS_PROTO(inode)->read_pageio_init(&pgio, inode, &nfs_async_read_completion_ops);
 	nfs_pageio_add_request(&pgio, new);
 	nfs_pageio_complete(&pgio);
 	NFS_I(inode)->read_io += pgio.pg_bytes_written;
@@ -407,6 +405,7 @@ int nfs_generic_pagein(struct nfs_pageio_descriptor *desc,
 		return nfs_pagein_multi(desc, hdr);
 	return nfs_pagein_one(desc, hdr);
 }
+EXPORT_SYMBOL_GPL(nfs_generic_pagein);
 
 static int nfs_generic_pg_readpages(struct nfs_pageio_descriptor *desc)
 {
@@ -532,11 +531,11 @@ static const struct rpc_call_ops nfs_read_common_ops = {
 int nfs_readpage(struct file *file, struct page *page)
 {
 	struct nfs_open_context *ctx;
-	struct inode *inode = page->mapping->host;
+	struct inode *inode = page_file_mapping(page)->host;
 	int		error;
 
 	dprintk("NFS: nfs_readpage (%p %ld@%lu)\n",
-		page, PAGE_CACHE_SIZE, page->index);
+		page, PAGE_CACHE_SIZE, page_file_index(page));
 	nfs_inc_stats(inode, NFSIOS_VFSREADPAGE);
 	nfs_add_stats(inode, NFSIOS_READPAGES, 1);
 
@@ -590,7 +589,7 @@ static int
 readpage_async_filler(void *data, struct page *page)
 {
 	struct nfs_readdesc *desc = (struct nfs_readdesc *)data;
-	struct inode *inode = page->mapping->host;
+	struct inode *inode = page_file_mapping(page)->host;
 	struct nfs_page *new;
 	unsigned int len;
 	int error;
@@ -652,7 +651,7 @@ int nfs_readpages(struct file *filp, struct address_space *mapping,
 	if (ret == 0)
 		goto read_complete; /* all pages were read */
 
-	nfs_pageio_init_read(&pgio, inode, &nfs_async_read_completion_ops);
+	NFS_PROTO(inode)->read_pageio_init(&pgio, inode, &nfs_async_read_completion_ops);
 
 	ret = read_cache_pages(mapping, pages, readpage_async_filler, &desc);
 
diff --git a/fs/nfs/super.c b/fs/nfs/super.c
index 06228192f64..b056b162872 100644
--- a/fs/nfs/super.c
+++ b/fs/nfs/super.c
@@ -54,6 +54,7 @@
 #include <linux/parser.h>
 #include <linux/nsproxy.h>
 #include <linux/rcupdate.h>
+#include <linux/kthread.h>
 
 #include <asm/uaccess.h>
 
@@ -63,12 +64,14 @@
 #include "iostat.h"
 #include "internal.h"
 #include "fscache.h"
+#include "nfs4session.h"
 #include "pnfs.h"
+#include "nfs.h"
 
 #define NFSDBG_FACILITY		NFSDBG_VFS
 #define NFS_TEXT_DATA		1
 
-#ifdef CONFIG_NFS_V3
+#if IS_ENABLED(CONFIG_NFS_V3)
 #define NFS_DEFAULT_VERSION 3
 #else
 #define NFS_DEFAULT_VERSION 2
@@ -87,6 +90,7 @@ enum {
 	Opt_sharecache, Opt_nosharecache,
 	Opt_resvport, Opt_noresvport,
 	Opt_fscache, Opt_nofscache,
+	Opt_migration, Opt_nomigration,
 
 	/* Mount options that take integer arguments */
 	Opt_port,
@@ -146,6 +150,8 @@ static const match_table_t nfs_mount_option_tokens = {
 	{ Opt_noresvport, "noresvport" },
 	{ Opt_fscache, "fsc" },
 	{ Opt_nofscache, "nofsc" },
+	{ Opt_migration, "migration" },
+	{ Opt_nomigration, "nomigration" },
 
 	{ Opt_port, "port=%s" },
 	{ Opt_rsize, "rsize=%s" },
@@ -278,37 +284,17 @@ static match_table_t nfs_vers_tokens = {
 	{ Opt_vers_err, NULL }
 };
 
-struct nfs_mount_info {
-	void (*fill_super)(struct super_block *, struct nfs_mount_info *);
-	int (*set_security)(struct super_block *, struct dentry *, struct nfs_mount_info *);
-	struct nfs_parsed_mount_data *parsed;
-	struct nfs_clone_mount *cloned;
-	struct nfs_fh *mntfh;
-};
-
-static void nfs_umount_begin(struct super_block *);
-static int  nfs_statfs(struct dentry *, struct kstatfs *);
-static int  nfs_show_options(struct seq_file *, struct dentry *);
-static int  nfs_show_devname(struct seq_file *, struct dentry *);
-static int  nfs_show_path(struct seq_file *, struct dentry *);
-static int  nfs_show_stats(struct seq_file *, struct dentry *);
-static struct dentry *nfs_fs_mount_common(struct file_system_type *,
-		struct nfs_server *, int, const char *, struct nfs_mount_info *);
-static struct dentry *nfs_fs_mount(struct file_system_type *,
-		int, const char *, void *);
 static struct dentry *nfs_xdev_mount(struct file_system_type *fs_type,
 		int flags, const char *dev_name, void *raw_data);
-static void nfs_put_super(struct super_block *);
-static void nfs_kill_super(struct super_block *);
-static int nfs_remount(struct super_block *sb, int *flags, char *raw_data);
 
-static struct file_system_type nfs_fs_type = {
+struct file_system_type nfs_fs_type = {
 	.owner		= THIS_MODULE,
 	.name		= "nfs",
 	.mount		= nfs_fs_mount,
 	.kill_sb	= nfs_kill_super,
 	.fs_flags	= FS_RENAME_DOES_D_MOVE|FS_REVAL_DOT|FS_BINARY_MOUNTDATA,
 };
+EXPORT_SYMBOL_GPL(nfs_fs_type);
 
 struct file_system_type nfs_xdev_fs_type = {
 	.owner		= THIS_MODULE,
@@ -318,10 +304,11 @@ struct file_system_type nfs_xdev_fs_type = {
 	.fs_flags	= FS_RENAME_DOES_D_MOVE|FS_REVAL_DOT|FS_BINARY_MOUNTDATA,
 };
 
-static const struct super_operations nfs_sops = {
+const struct super_operations nfs_sops = {
 	.alloc_inode	= nfs_alloc_inode,
 	.destroy_inode	= nfs_destroy_inode,
 	.write_inode	= nfs_write_inode,
+	.drop_inode	= nfs_drop_inode,
 	.put_super	= nfs_put_super,
 	.statfs		= nfs_statfs,
 	.evict_inode	= nfs_evict_inode,
@@ -332,77 +319,40 @@ static const struct super_operations nfs_sops = {
 	.show_stats	= nfs_show_stats,
 	.remount_fs	= nfs_remount,
 };
+EXPORT_SYMBOL_GPL(nfs_sops);
 
-#ifdef CONFIG_NFS_V4
+#if IS_ENABLED(CONFIG_NFS_V4)
 static void nfs4_validate_mount_flags(struct nfs_parsed_mount_data *);
 static int nfs4_validate_mount_data(void *options,
 	struct nfs_parsed_mount_data *args, const char *dev_name);
-static struct dentry *nfs4_try_mount(int flags, const char *dev_name,
-	struct nfs_mount_info *mount_info);
-static struct dentry *nfs4_remote_mount(struct file_system_type *fs_type,
-	int flags, const char *dev_name, void *raw_data);
-static struct dentry *nfs4_xdev_mount(struct file_system_type *fs_type,
-	int flags, const char *dev_name, void *raw_data);
-static struct dentry *nfs4_referral_mount(struct file_system_type *fs_type,
-	int flags, const char *dev_name, void *raw_data);
-static struct dentry *nfs4_remote_referral_mount(struct file_system_type *fs_type,
-	int flags, const char *dev_name, void *raw_data);
-static void nfs4_kill_super(struct super_block *sb);
-
-static struct file_system_type nfs4_fs_type = {
-	.owner		= THIS_MODULE,
-	.name		= "nfs4",
-	.mount		= nfs_fs_mount,
-	.kill_sb	= nfs4_kill_super,
-	.fs_flags	= FS_RENAME_DOES_D_MOVE|FS_REVAL_DOT|FS_BINARY_MOUNTDATA,
-};
-
-static struct file_system_type nfs4_remote_fs_type = {
-	.owner		= THIS_MODULE,
-	.name		= "nfs4",
-	.mount		= nfs4_remote_mount,
-	.kill_sb	= nfs4_kill_super,
-	.fs_flags	= FS_RENAME_DOES_D_MOVE|FS_REVAL_DOT|FS_BINARY_MOUNTDATA,
-};
 
-struct file_system_type nfs4_xdev_fs_type = {
+struct file_system_type nfs4_fs_type = {
 	.owner		= THIS_MODULE,
 	.name		= "nfs4",
-	.mount		= nfs4_xdev_mount,
-	.kill_sb	= nfs4_kill_super,
+	.mount		= nfs_fs_mount,
+	.kill_sb	= nfs_kill_super,
 	.fs_flags	= FS_RENAME_DOES_D_MOVE|FS_REVAL_DOT|FS_BINARY_MOUNTDATA,
 };
+EXPORT_SYMBOL_GPL(nfs4_fs_type);
 
-static struct file_system_type nfs4_remote_referral_fs_type = {
-	.owner		= THIS_MODULE,
-	.name		= "nfs4",
-	.mount		= nfs4_remote_referral_mount,
-	.kill_sb	= nfs4_kill_super,
-	.fs_flags	= FS_RENAME_DOES_D_MOVE|FS_REVAL_DOT|FS_BINARY_MOUNTDATA,
-};
+static int __init register_nfs4_fs(void)
+{
+	return register_filesystem(&nfs4_fs_type);
+}
 
-struct file_system_type nfs4_referral_fs_type = {
-	.owner		= THIS_MODULE,
-	.name		= "nfs4",
-	.mount		= nfs4_referral_mount,
-	.kill_sb	= nfs4_kill_super,
-	.fs_flags	= FS_RENAME_DOES_D_MOVE|FS_REVAL_DOT|FS_BINARY_MOUNTDATA,
-};
+static void unregister_nfs4_fs(void)
+{
+	unregister_filesystem(&nfs4_fs_type);
+}
+#else
+static int __init register_nfs4_fs(void)
+{
+	return 0;
+}
 
-static const struct super_operations nfs4_sops = {
-	.alloc_inode	= nfs_alloc_inode,
-	.destroy_inode	= nfs_destroy_inode,
-	.write_inode	= nfs_write_inode,
-	.put_super	= nfs_put_super,
-	.statfs		= nfs_statfs,
-	.evict_inode	= nfs4_evict_inode,
-	.umount_begin	= nfs_umount_begin,
-	.show_options	= nfs_show_options,
-	.show_devname	= nfs_show_devname,
-	.show_path	= nfs_show_path,
-	.show_stats	= nfs_show_stats,
-	.remount_fs	= nfs_remount,
-};
+static void unregister_nfs4_fs(void)
+{
+}
 #endif
 
 static struct shrinker acl_shrinker = {
@@ -421,21 +371,18 @@ int __init register_nfs_fs(void)
 	if (ret < 0)
 		goto error_0;
 
-	ret = nfs_register_sysctl();
+	ret = register_nfs4_fs();
 	if (ret < 0)
 		goto error_1;
-#ifdef CONFIG_NFS_V4
-	ret = register_filesystem(&nfs4_fs_type);
+
+	ret = nfs_register_sysctl();
 	if (ret < 0)
 		goto error_2;
-#endif
 	register_shrinker(&acl_shrinker);
 	return 0;
 
-#ifdef CONFIG_NFS_V4
 error_2:
-	nfs_unregister_sysctl();
-#endif
+	unregister_nfs4_fs();
 error_1:
 	unregister_filesystem(&nfs_fs_type);
 error_0:
@@ -448,10 +395,8 @@ error_0:
 void __exit unregister_nfs_fs(void)
 {
 	unregister_shrinker(&acl_shrinker);
-#ifdef CONFIG_NFS_V4
-	unregister_filesystem(&nfs4_fs_type);
-#endif
 	nfs_unregister_sysctl();
+	unregister_nfs4_fs();
 	unregister_filesystem(&nfs_fs_type);
 }
 
@@ -462,6 +407,7 @@ void nfs_sb_active(struct super_block *sb)
 	if (atomic_inc_return(&server->active) == 1)
 		atomic_inc(&sb->s_active);
 }
+EXPORT_SYMBOL_GPL(nfs_sb_active);
 
 void nfs_sb_deactive(struct super_block *sb)
 {
@@ -470,11 +416,60 @@ void nfs_sb_deactive(struct super_block *sb)
 	if (atomic_dec_and_test(&server->active))
 		deactivate_super(sb);
 }
+EXPORT_SYMBOL_GPL(nfs_sb_deactive);
+
+static int nfs_deactivate_super_async_work(void *ptr)
+{
+	struct super_block *sb = ptr;
+
+	deactivate_super(sb);
+	module_put_and_exit(0);
+	return 0;
+}
+
+/*
+ * same effect as deactivate_super, but will do final unmount in kthread
+ * context
+ */
+static void nfs_deactivate_super_async(struct super_block *sb)
+{
+	struct task_struct *task;
+	char buf[INET6_ADDRSTRLEN + 1];
+	struct nfs_server *server = NFS_SB(sb);
+	struct nfs_client *clp = server->nfs_client;
+
+	if (!atomic_add_unless(&sb->s_active, -1, 1)) {
+		rcu_read_lock();
+		snprintf(buf, sizeof(buf),
+			rpc_peeraddr2str(clp->cl_rpcclient, RPC_DISPLAY_ADDR));
+		rcu_read_unlock();
+
+		__module_get(THIS_MODULE);
+		task = kthread_run(nfs_deactivate_super_async_work, sb,
+				"%s-deactivate-super", buf);
+		if (IS_ERR(task)) {
+			pr_err("%s: kthread_run: %ld\n",
+				__func__, PTR_ERR(task));
+			/* make synchronous call and hope for the best */
+			deactivate_super(sb);
+			module_put(THIS_MODULE);
+		}
+	}
+}
+
+void nfs_sb_deactive_async(struct super_block *sb)
+{
+	struct nfs_server *server = NFS_SB(sb);
+
+	if (atomic_dec_and_test(&server->active))
+		nfs_deactivate_super_async(sb);
+}
+EXPORT_SYMBOL_GPL(nfs_sb_deactive_async);
 
 /*
  * Deliver file system statistics to userspace
  */
-static int nfs_statfs(struct dentry *dentry, struct kstatfs *buf)
+int nfs_statfs(struct dentry *dentry, struct kstatfs *buf)
 {
 	struct nfs_server *server = NFS_SB(dentry->d_sb);
 	unsigned char blockbits;
@@ -535,6 +530,7 @@ static int nfs_statfs(struct dentry *dentry, struct kstatfs *buf)
 	dprintk("%s: statfs error = %d\n", __func__, -error);
 	return error;
 }
+EXPORT_SYMBOL_GPL(nfs_statfs);
 
 /*
  * Map the security flavour number to a name
@@ -640,7 +636,7 @@ static void nfs_show_mountd_options(struct seq_file *m, struct nfs_server *nfss,
 	nfs_show_mountd_netid(m, nfss, showdefaults);
 }
 
-#ifdef CONFIG_NFS_V4
+#if IS_ENABLED(CONFIG_NFS_V4)
 static void nfs_show_nfsv4_options(struct seq_file *m, struct nfs_server *nfss,
 				    int showdefaults)
 {
@@ -734,6 +730,9 @@ static void nfs_show_mount_options(struct seq_file *m, struct nfs_server *nfss,
 	if (nfss->options & NFS_OPTION_FSCACHE)
 		seq_printf(m, ",fsc");
 
+	if (nfss->options & NFS_OPTION_MIGRATION)
+		seq_printf(m, ",migration");
+
 	if (nfss->flags & NFS_MOUNT_LOOKUP_CACHE_NONEG) {
 		if (nfss->flags & NFS_MOUNT_LOOKUP_CACHE_NONE)
 			seq_printf(m, ",lookupcache=none");
@@ -757,7 +756,7 @@ static void nfs_show_mount_options(struct seq_file *m, struct nfs_server *nfss,
 /*
  * Describe the mount options on this VFS mountpoint
  */
-static int nfs_show_options(struct seq_file *m, struct dentry *root)
+int nfs_show_options(struct seq_file *m, struct dentry *root)
 {
 	struct nfs_server *nfss = NFS_SB(root->d_sb);
 
@@ -771,8 +770,9 @@ static int nfs_show_options(struct seq_file *m, struct dentry *root)
 
 	return 0;
 }
+EXPORT_SYMBOL_GPL(nfs_show_options);
 
-#ifdef CONFIG_NFS_V4
+#if IS_ENABLED(CONFIG_NFS_V4)
 #ifdef CONFIG_NFS_V4_1
 static void show_sessions(struct seq_file *m, struct nfs_server *server)
 {
@@ -805,7 +805,7 @@ static void show_implementation_id(struct seq_file *m, struct nfs_server *nfss)
 	}
 }
 #else
-#ifdef CONFIG_NFS_V4
+#if IS_ENABLED(CONFIG_NFS_V4)
 static void show_pnfs(struct seq_file *m, struct nfs_server *server)
 {
 }
@@ -815,14 +815,14 @@ static void show_implementation_id(struct seq_file *m, struct nfs_server *nfss)
 }
 #endif
 
-static int nfs_show_devname(struct seq_file *m, struct dentry *root)
+int nfs_show_devname(struct seq_file *m, struct dentry *root)
 {
 	char *page = (char *) __get_free_page(GFP_KERNEL);
 	char *devname, *dummy;
 	int err = 0;
 	if (!page)
 		return -ENOMEM;
-	devname = nfs_path(&dummy, root, page, PAGE_SIZE);
+	devname = nfs_path(&dummy, root, page, PAGE_SIZE, 0);
 	if (IS_ERR(devname))
 		err = PTR_ERR(devname);
 	else
@@ -830,17 +830,19 @@ static int nfs_show_devname(struct seq_file *m, struct dentry *root)
 	free_page((unsigned long)page);
 	return err;
 }
+EXPORT_SYMBOL_GPL(nfs_show_devname);
 
-static int nfs_show_path(struct seq_file *m, struct dentry *dentry)
+int nfs_show_path(struct seq_file *m, struct dentry *dentry)
 {
 	seq_puts(m, "/");
 	return 0;
 }
+EXPORT_SYMBOL_GPL(nfs_show_path);
 
 /*
  * Present statistical information for this VFS mountpoint
  */
-static int nfs_show_stats(struct seq_file *m, struct dentry *root)
+int nfs_show_stats(struct seq_file *m, struct dentry *root)
 {
 	int i, cpu;
 	struct nfs_server *nfss = NFS_SB(root->d_sb);
@@ -870,7 +872,7 @@ static int nfs_show_stats(struct seq_file *m, struct dentry *root)
 	seq_printf(m, ",bsize=%u", nfss->bsize);
 	seq_printf(m, ",namlen=%u", nfss->namelen);
 
-#ifdef CONFIG_NFS_V4
+#if IS_ENABLED(CONFIG_NFS_V4)
 	if (nfss->nfs_client->rpc_ops->version == 4) {
 		seq_printf(m, "\n\tnfsv4:\t");
 		seq_printf(m, "bm0=0x%x", nfss->attr_bitmask[0]);
@@ -928,12 +930,13 @@ static int nfs_show_stats(struct seq_file *m, struct dentry *root)
 
 	return 0;
 }
+EXPORT_SYMBOL_GPL(nfs_show_stats);
 
 /*
  * Begin unmount by attempting to remove all automounted mountpoints we added
  * in response to xdev traversals and referrals
  */
-static void nfs_umount_begin(struct super_block *sb)
+void nfs_umount_begin(struct super_block *sb)
 {
 	struct nfs_server *server;
 	struct rpc_clnt *rpc;
@@ -947,6 +950,7 @@ static void nfs_umount_begin(struct super_block *sb)
 	if (!IS_ERR(rpc))
 		rpc_killall_tasks(rpc);
 }
+EXPORT_SYMBOL_GPL(nfs_umount_begin);
 
 static struct nfs_parsed_mount_data *nfs_alloc_parsed_mount_data(void)
 {
@@ -1148,7 +1152,7 @@ static int nfs_get_option_str(substring_t args[], char **option)
 {
 	kfree(*option);
 	*option = match_strdup(args);
-	return !option;
+	return !*option;
 }
 
 static int nfs_get_option_ul(substring_t args[], unsigned long *option)
@@ -1159,7 +1163,7 @@ static int nfs_get_option_ul(substring_t args[], unsigned long *option)
 	string = match_strdup(args);
 	if (string == NULL)
 		return -ENOMEM;
-	rc = strict_strtoul(string, 10, option);
+	rc = kstrtoul(string, 10, option);
 	kfree(string);
 
 	return rc;
@@ -1296,6 +1300,12 @@ static int nfs_parse_mount_options(char *raw,
 			kfree(mnt->fscache_uniq);
 			mnt->fscache_uniq = NULL;
 			break;
+		case Opt_migration:
+			mnt->options |= NFS_OPTION_MIGRATION;
+			break;
+		case Opt_nomigration:
+			mnt->options &= NFS_OPTION_MIGRATION;
+			break;
 
 		/*
 		 * options that take numeric values
@@ -1588,9 +1598,13 @@ static int nfs_parse_mount_options(char *raw,
 	if (mnt->minorversion && mnt->version != 4)
 		goto out_minorversion_mismatch;
 
+	if (mnt->options & NFS_OPTION_MIGRATION &&
+	    mnt->version != 4 && mnt->minorversion != 0)
+		goto out_migration_misuse;
+
 	/*
 	 * verify that any proto=/mountproto= options match the address
-	 * familiies in the addr=/mountaddr= options.
+	 * families in the addr=/mountaddr= options.
 	 */
 	if (protofamily != AF_UNSPEC &&
 	    protofamily != mnt->nfs_server.address.ss_family)
@@ -1625,6 +1639,10 @@ out_minorversion_mismatch:
 	printk(KERN_INFO "NFS: mount option vers=%u does not support "
 			 "minorversion=%u\n", mnt->version, mnt->minorversion);
 	return 0;
+out_migration_misuse:
+	printk(KERN_INFO
+		"NFS: 'migration' not supported for this NFS version\n");
+	return 0;
 out_nomem:
 	printk(KERN_INFO "NFS: not enough memory to parse option\n");
 	return 0;
@@ -1748,8 +1766,9 @@ static int nfs_request_mount(struct nfs_parsed_mount_data *args,
 	return nfs_walk_authlist(args, &request);
 }
 
-static struct dentry *nfs_try_mount(int flags, const char *dev_name,
-				    struct nfs_mount_info *mount_info)
+struct dentry *nfs_try_mount(int flags, const char *dev_name,
+			     struct nfs_mount_info *mount_info,
+			     struct nfs_subversion *nfs_mod)
 {
 	int status;
 	struct nfs_server *server;
@@ -1761,12 +1780,13 @@ static struct dentry *nfs_try_mount(int flags, const char *dev_name,
 	}
 
 	/* Get a volume representation */
-	server = nfs_create_server(mount_info->parsed, mount_info->mntfh);
+	server = nfs_mod->rpc_ops->create_server(mount_info, nfs_mod);
 	if (IS_ERR(server))
 		return ERR_CAST(server);
 
-	return nfs_fs_mount_common(&nfs_fs_type, server, flags, dev_name, mount_info);
+	return nfs_fs_mount_common(server, flags, dev_name, mount_info, nfs_mod);
 }
+EXPORT_SYMBOL_GPL(nfs_try_mount);
 
 /*
  * Split "dev_name" into "hostname:export_path".
@@ -1918,6 +1938,7 @@ static int nfs23_validate_mount_data(void *options,
 
 		memcpy(sap, &data->addr, sizeof(data->addr));
 		args->nfs_server.addrlen = sizeof(data->addr);
+		args->nfs_server.port = ntohs(data->addr.sin_port);
 		if (!nfs_verify_server_address(sap))
 			goto out_no_address;
 
@@ -1970,7 +1991,7 @@ static int nfs23_validate_mount_data(void *options,
 		return NFS_TEXT_DATA;
 	}
 
-#ifndef CONFIG_NFS_V3
+#if !IS_ENABLED(CONFIG_NFS_V3)
 	if (args->version == 3)
 		goto out_v3_not_compiled;
 #endif /* !CONFIG_NFS_V3 */
@@ -1990,7 +2011,7 @@ out_no_sec:
 	dfprintk(MOUNT, "NFS: nfs_mount_data version supports only AUTH_SYS\n");
 	return -EINVAL;
 
-#ifndef CONFIG_NFS_V3
+#if !IS_ENABLED(CONFIG_NFS_V3)
 out_v3_not_compiled:
 	dfprintk(MOUNT, "NFS: NFSv3 is not compiled into kernel\n");
 	return -EPROTONOSUPPORT;
@@ -2009,7 +2030,7 @@ out_invalid_fh:
 	return -EINVAL;
 }
 
-#ifdef CONFIG_NFS_V4
+#if IS_ENABLED(CONFIG_NFS_V4)
 static int nfs_validate_mount_data(struct file_system_type *fs_type,
 				   void *options,
 				   struct nfs_parsed_mount_data *args,
@@ -2047,7 +2068,7 @@ static int nfs_validate_text_mount_data(void *options,
 		goto out_no_address;
 
 	if (args->version == 4) {
-#ifdef CONFIG_NFS_V4
+#if IS_ENABLED(CONFIG_NFS_V4)
 		port = NFS_PORT;
 		max_namelen = NFS4_MAXNAMLEN;
 		max_pathlen = NFS4_MAXPATHLEN;
@@ -2070,7 +2091,7 @@ static int nfs_validate_text_mount_data(void *options,
 				   &args->nfs_server.export_path,
 				   max_pathlen);
 
-#ifndef CONFIG_NFS_V4
+#if !IS_ENABLED(CONFIG_NFS_V4)
 out_v4_not_compiled:
 	dfprintk(MOUNT, "NFS: NFSv4 is not compiled into kernel\n");
 	return -EPROTONOSUPPORT;
@@ -2108,7 +2129,7 @@ nfs_compare_remount_data(struct nfs_server *nfss,
 	return 0;
 }
 
-static int
+int
 nfs_remount(struct super_block *sb, int *flags, char *raw_data)
 {
 	int error;
@@ -2169,11 +2190,12 @@ out:
 	kfree(data);
 	return error;
 }
+EXPORT_SYMBOL_GPL(nfs_remount);
 
 /*
  * Initialise the common bits of the superblock
  */
-static inline void nfs_initialise_sb(struct super_block *sb)
+inline void nfs_initialise_sb(struct super_block *sb)
 {
 	struct nfs_server *server = NFS_SB(sb);
 
@@ -2195,18 +2217,19 @@ static inline void nfs_initialise_sb(struct super_block *sb)
 /*
  * Finish setting up an NFS2/3 superblock
  */
-static void nfs_fill_super(struct super_block *sb,
-			   struct nfs_mount_info *mount_info)
+void nfs_fill_super(struct super_block *sb, struct nfs_mount_info *mount_info)
 {
 	struct nfs_parsed_mount_data *data = mount_info->parsed;
 	struct nfs_server *server = NFS_SB(sb);
 
 	sb->s_blocksize_bits = 0;
 	sb->s_blocksize = 0;
-	if (data->bsize)
+	sb->s_xattr = server->nfs_client->cl_nfs_mod->xattr;
+	sb->s_op = server->nfs_client->cl_nfs_mod->sops;
+	if (data && data->bsize)
 		sb->s_blocksize = nfs_block_size(data->bsize, &sb->s_blocksize_bits);
 
-	if (server->nfs_client->rpc_ops->version == 3) {
+	if (server->nfs_client->rpc_ops->version != 2) {
 		/* The VFS shouldn't apply the umask to mode bits. We will do
 		 * so ourselves when necessary.
 		 */
@@ -2214,15 +2237,14 @@ static void nfs_fill_super(struct super_block *sb,
 		sb->s_time_gran = 1;
 	}
 
-	sb->s_op = &nfs_sops;
  	nfs_initialise_sb(sb);
 }
+EXPORT_SYMBOL_GPL(nfs_fill_super);
 
 /*
- * Finish setting up a cloned NFS2/3 superblock
+ * Finish setting up a cloned NFS2/3/4 superblock
  */
-static void nfs_clone_super(struct super_block *sb,
-			    struct nfs_mount_info *mount_info)
+void nfs_clone_super(struct super_block *sb, struct nfs_mount_info *mount_info)
 {
 	const struct super_block *old_sb = mount_info->cloned->sb;
 	struct nfs_server *server = NFS_SB(sb);
@@ -2230,16 +2252,17 @@ static void nfs_clone_super(struct super_block *sb,
 	sb->s_blocksize_bits = old_sb->s_blocksize_bits;
 	sb->s_blocksize = old_sb->s_blocksize;
 	sb->s_maxbytes = old_sb->s_maxbytes;
+	sb->s_xattr = old_sb->s_xattr;
+	sb->s_op = old_sb->s_op;
+	sb->s_time_gran = 1;
 
-	if (server->nfs_client->rpc_ops->version == 3) {
+	if (server->nfs_client->rpc_ops->version != 2) {
 		/* The VFS shouldn't apply the umask to mode bits. We will do
 		 * so ourselves when necessary.
 		 */
 		sb->s_flags |= MS_POSIXACL;
-		sb->s_time_gran = 1;
 	}
 
-	sb->s_op = old_sb->s_op;
  	nfs_initialise_sb(sb);
 }
 
@@ -2352,19 +2375,30 @@ static void nfs_get_cache_cookie(struct super_block *sb,
 				 struct nfs_parsed_mount_data *parsed,
 				 struct nfs_clone_mount *cloned)
 {
+	struct nfs_server *nfss = NFS_SB(sb);
 	char *uniq = NULL;
 	int ulen = 0;
 
-	if (parsed && parsed->fscache_uniq) {
-		uniq = parsed->fscache_uniq;
-		ulen = strlen(parsed->fscache_uniq);
+	nfss->fscache_key = NULL;
+	nfss->fscache = NULL;
+
+	if (parsed) {
+		if (!(parsed->options & NFS_OPTION_FSCACHE))
+			return;
+		if (parsed->fscache_uniq) {
+			uniq = parsed->fscache_uniq;
+			ulen = strlen(parsed->fscache_uniq);
+		}
 	} else if (cloned) {
 		struct nfs_server *mnt_s = NFS_SB(cloned->sb);
+		if (!(mnt_s->options & NFS_OPTION_FSCACHE))
+			return;
 		if (mnt_s->fscache_key) {
 			uniq = mnt_s->fscache_key->key.uniquifier;
 			ulen = mnt_s->fscache_key->key.uniq_len;
 		};
-	}
+	} else
+		return;
 
 	nfs_fscache_get_super_cookie(sb, uniq, ulen);
 }
@@ -2381,14 +2415,15 @@ static int nfs_bdi_register(struct nfs_server *server)
 	return bdi_register_dev(&server->backing_dev_info, server->s_dev);
 }
 
-static int nfs_set_sb_security(struct super_block *s, struct dentry *mntroot,
-			       struct nfs_mount_info *mount_info)
+int nfs_set_sb_security(struct super_block *s, struct dentry *mntroot,
+			struct nfs_mount_info *mount_info)
 {
 	return security_sb_set_mnt_opts(s, &mount_info->parsed->lsm_opts);
 }
+EXPORT_SYMBOL_GPL(nfs_set_sb_security);
 
-static int nfs_clone_sb_security(struct super_block *s, struct dentry *mntroot,
-				 struct nfs_mount_info *mount_info)
+int nfs_clone_sb_security(struct super_block *s, struct dentry *mntroot,
+			  struct nfs_mount_info *mount_info)
 {
 	/* clone any lsm security options from the parent to the new sb */
 	security_sb_clone_mnt_opts(mount_info->cloned->sb, s);
@@ -2396,11 +2431,12 @@ static int nfs_clone_sb_security(struct super_block *s, struct dentry *mntroot,
 		return -ESTALE;
 	return 0;
 }
+EXPORT_SYMBOL_GPL(nfs_clone_sb_security);
 
-static struct dentry *nfs_fs_mount_common(struct file_system_type *fs_type,
-					  struct nfs_server *server,
-					  int flags, const char *dev_name,
-					  struct nfs_mount_info *mount_info)
+struct dentry *nfs_fs_mount_common(struct nfs_server *server,
+				   int flags, const char *dev_name,
+				   struct nfs_mount_info *mount_info,
+				   struct nfs_subversion *nfs_mod)
 {
 	struct super_block *s;
 	struct dentry *mntroot = ERR_PTR(-ENOMEM);
@@ -2419,7 +2455,7 @@ static struct dentry *nfs_fs_mount_common(struct file_system_type *fs_type,
 		sb_mntdata.mntflags |= MS_SYNCHRONOUS;
 
 	/* Get a superblock - note that we may end up sharing one that already exists */
-	s = sget(fs_type, compare_super, nfs_set_super, &sb_mntdata);
+	s = sget(nfs_mod->nfs_fs, compare_super, nfs_set_super, flags, &sb_mntdata);
 	if (IS_ERR(s)) {
 		mntroot = ERR_CAST(s);
 		goto out_err_nosb;
@@ -2469,8 +2505,9 @@ error_splat_bdi:
 	deactivate_locked_super(s);
 	goto out;
 }
+EXPORT_SYMBOL_GPL(nfs_fs_mount_common);
 
-static struct dentry *nfs_fs_mount(struct file_system_type *fs_type,
+struct dentry *nfs_fs_mount(struct file_system_type *fs_type,
 	int flags, const char *dev_name, void *raw_data)
 {
 	struct nfs_mount_info mount_info = {
@@ -2478,6 +2515,7 @@ static struct dentry *nfs_fs_mount(struct file_system_type *fs_type,
 		.set_security = nfs_set_sb_security,
 	};
 	struct dentry *mntroot = ERR_PTR(-ENOMEM);
+	struct nfs_subversion *nfs_mod;
 	int error;
 
 	mount_info.parsed = nfs_alloc_parsed_mount_data();
@@ -2494,34 +2532,38 @@ static struct dentry *nfs_fs_mount(struct file_system_type *fs_type,
 		goto out;
 	}
 
-#ifdef CONFIG_NFS_V4
-	if (mount_info.parsed->version == 4)
-		mntroot = nfs4_try_mount(flags, dev_name, &mount_info);
-	else
-#endif	/* CONFIG_NFS_V4 */
-		mntroot = nfs_try_mount(flags, dev_name, &mount_info);
+	nfs_mod = get_nfs_version(mount_info.parsed->version);
+	if (IS_ERR(nfs_mod)) {
+		mntroot = ERR_CAST(nfs_mod);
+		goto out;
+	}
 
+	mntroot = nfs_mod->rpc_ops->try_mount(flags, dev_name, &mount_info, nfs_mod);
+
+	put_nfs_version(nfs_mod);
 out:
 	nfs_free_parsed_mount_data(mount_info.parsed);
 	nfs_free_fhandle(mount_info.mntfh);
 	return mntroot;
 }
+EXPORT_SYMBOL_GPL(nfs_fs_mount);
 
 /*
  * Ensure that we unregister the bdi before kill_anon_super
  * releases the device name
  */
-static void nfs_put_super(struct super_block *s)
+void nfs_put_super(struct super_block *s)
 {
 	struct nfs_server *server = NFS_SB(s);
 
 	bdi_unregister(&server->backing_dev_info);
 }
+EXPORT_SYMBOL_GPL(nfs_put_super);
 
 /*
  * Destroy an NFS2/3 superblock
  */
-static void nfs_kill_super(struct super_block *s)
+void nfs_kill_super(struct super_block *s)
 {
 	struct nfs_server *server = NFS_SB(s);
 
@@ -2529,95 +2571,45 @@ static void nfs_kill_super(struct super_block *s)
 	nfs_fscache_release_super_cookie(s);
 	nfs_free_server(server);
 }
+EXPORT_SYMBOL_GPL(nfs_kill_super);
 
 /*
  * Clone an NFS2/3/4 server record on xdev traversal (FSID-change)
  */
 static struct dentry *
-nfs_xdev_mount_common(struct file_system_type *fs_type, int flags,
-		const char *dev_name, struct nfs_mount_info *mount_info)
-{
-	struct nfs_clone_mount *data = mount_info->cloned;
-	struct nfs_server *server;
-	struct dentry *mntroot = ERR_PTR(-ENOMEM);
-	int error;
-
-	dprintk("--> nfs_xdev_mount_common()\n");
-
-	mount_info->mntfh = data->fh;
-
-	/* create a new volume representation */
-	server = nfs_clone_server(NFS_SB(data->sb), data->fh, data->fattr, data->authflavor);
-	if (IS_ERR(server)) {
-		error = PTR_ERR(server);
-		goto out_err;
-	}
-
-	mntroot = nfs_fs_mount_common(fs_type, server, flags, dev_name, mount_info);
-	dprintk("<-- nfs_xdev_mount_common() = 0\n");
-out:
-	return mntroot;
-
-out_err:
-	dprintk("<-- nfs_xdev_mount_common() = %d [error]\n", error);
-	goto out;
-}
-
-/*
- * Clone an NFS2/3 server record on xdev traversal (FSID-change)
- */
-static struct dentry *
 nfs_xdev_mount(struct file_system_type *fs_type, int flags,
 		const char *dev_name, void *raw_data)
 {
+	struct nfs_clone_mount *data = raw_data;
 	struct nfs_mount_info mount_info = {
 		.fill_super = nfs_clone_super,
 		.set_security = nfs_clone_sb_security,
-		.cloned   = raw_data,
+		.cloned = data,
 	};
-	return nfs_xdev_mount_common(&nfs_fs_type, flags, dev_name, &mount_info);
-}
+	struct nfs_server *server;
+	struct dentry *mntroot = ERR_PTR(-ENOMEM);
+	struct nfs_subversion *nfs_mod = NFS_SB(data->sb)->nfs_client->cl_nfs_mod;
 
-#ifdef CONFIG_NFS_V4
+	dprintk("--> nfs_xdev_mount()\n");
 
-/*
- * Finish setting up a cloned NFS4 superblock
- */
-static void nfs4_clone_super(struct super_block *sb,
-			     struct nfs_mount_info *mount_info)
-{
-	const struct super_block *old_sb = mount_info->cloned->sb;
-	sb->s_blocksize_bits = old_sb->s_blocksize_bits;
-	sb->s_blocksize = old_sb->s_blocksize;
-	sb->s_maxbytes = old_sb->s_maxbytes;
-	sb->s_time_gran = 1;
-	sb->s_op = old_sb->s_op;
-	/*
-	 * The VFS shouldn't apply the umask to mode bits. We will do
-	 * so ourselves when necessary.
-	 */
-	sb->s_flags  |= MS_POSIXACL;
-	sb->s_xattr  = old_sb->s_xattr;
-	nfs_initialise_sb(sb);
-}
+	mount_info.mntfh = mount_info.cloned->fh;
 
-/*
- * Set up an NFS4 superblock
- */
-static void nfs4_fill_super(struct super_block *sb,
-			    struct nfs_mount_info *mount_info)
-{
-	sb->s_time_gran = 1;
-	sb->s_op = &nfs4_sops;
-	/*
-	 * The VFS shouldn't apply the umask to mode bits. We will do
-	 * so ourselves when necessary.
-	 */
-	sb->s_flags  |= MS_POSIXACL;
-	sb->s_xattr = nfs4_xattr_handlers;
-	nfs_initialise_sb(sb);
+	/* create a new volume representation */
+	server = nfs_mod->rpc_ops->clone_server(NFS_SB(data->sb), data->fh, data->fattr, data->authflavor);
+
+	if (IS_ERR(server))
+		mntroot = ERR_CAST(server);
+	else
+		mntroot = nfs_fs_mount_common(server, flags,
+				dev_name, &mount_info, nfs_mod);
+
+	dprintk("<-- nfs_xdev_mount() = %ld\n",
+			IS_ERR(mntroot) ? PTR_ERR(mntroot) : 0L);
+	return mntroot;
 }
 
+#if IS_ENABLED(CONFIG_NFS_V4)
+
 static void nfs4_validate_mount_flags(struct nfs_parsed_mount_data *args)
 {
 	args->flags &= ~(NFS_MOUNT_NONLM|NFS_MOUNT_NOACL|NFS_MOUNT_VER3|
@@ -2651,6 +2643,7 @@ static int nfs4_validate_mount_data(void *options,
 			return -EFAULT;
 		if (!nfs_verify_server_address(sap))
 			goto out_no_address;
+		args->nfs_server.port = ntohs(((struct sockaddr_in *)sap)->sin_port);
 
 		if (data->auth_flavourlen) {
 			if (data->auth_flavourlen > 1)
@@ -2716,249 +2709,62 @@ out_no_address:
 }
 
 /*
- * Get the superblock for the NFS4 root partition
+ * NFS v4 module parameters need to stay in the
+ * NFS client for backwards compatibility
  */
-static struct dentry *
-nfs4_remote_mount(struct file_system_type *fs_type, int flags,
-		  const char *dev_name, void *info)
-{
-	struct nfs_mount_info *mount_info = info;
-	struct nfs_server *server;
-	struct dentry *mntroot = ERR_PTR(-ENOMEM);
-
-	mount_info->fill_super = nfs4_fill_super;
-	mount_info->set_security = nfs_set_sb_security;
-
-	/* Get a volume representation */
-	server = nfs4_create_server(mount_info->parsed, mount_info->mntfh);
-	if (IS_ERR(server)) {
-		mntroot = ERR_CAST(server);
-		goto out;
-	}
-
-	mntroot = nfs_fs_mount_common(fs_type, server, flags, dev_name, mount_info);
-
-out:
-	return mntroot;
-}
-
-static struct vfsmount *nfs_do_root_mount(struct file_system_type *fs_type,
-		int flags, void *data, const char *hostname)
-{
-	struct vfsmount *root_mnt;
-	char *root_devname;
-	size_t len;
+unsigned int nfs_callback_set_tcpport;
+unsigned short nfs_callback_tcpport;
+/* Default cache timeout is 10 minutes */
+unsigned int nfs_idmap_cache_timeout = 600;
+/* Turn off NFSv4 uid/gid mapping when using AUTH_SYS */
+bool nfs4_disable_idmapping = true;
+unsigned short max_session_slots = NFS4_DEF_SLOT_TABLE_SIZE;
+unsigned short send_implementation_id = 1;
+char nfs4_client_id_uniquifier[NFS4_CLIENT_ID_UNIQ_LEN] = "";
+
+EXPORT_SYMBOL_GPL(nfs_callback_set_tcpport);
+EXPORT_SYMBOL_GPL(nfs_callback_tcpport);
+EXPORT_SYMBOL_GPL(nfs_idmap_cache_timeout);
+EXPORT_SYMBOL_GPL(nfs4_disable_idmapping);
+EXPORT_SYMBOL_GPL(max_session_slots);
+EXPORT_SYMBOL_GPL(send_implementation_id);
+EXPORT_SYMBOL_GPL(nfs4_client_id_uniquifier);
+
+#define NFS_CALLBACK_MAXPORTNR (65535U)
+
+static int param_set_portnr(const char *val, const struct kernel_param *kp)
+{
+	unsigned long num;
+	int ret;
 
-	len = strlen(hostname) + 5;
-	root_devname = kmalloc(len, GFP_KERNEL);
-	if (root_devname == NULL)
-		return ERR_PTR(-ENOMEM);
-	/* Does hostname needs to be enclosed in brackets? */
-	if (strchr(hostname, ':'))
-		snprintf(root_devname, len, "[%s]:/", hostname);
-	else
-		snprintf(root_devname, len, "%s:/", hostname);
-	root_mnt = vfs_kern_mount(fs_type, flags, root_devname, data);
-	kfree(root_devname);
-	return root_mnt;
+	if (!val)
+		return -EINVAL;
+	ret = kstrtoul(val, 0, &num);
+	if (ret == -EINVAL || num > NFS_CALLBACK_MAXPORTNR)
+		return -EINVAL;
+	*((unsigned int *)kp->arg) = num;
+	return 0;
 }
-
-struct nfs_referral_count {
-	struct list_head list;
-	const struct task_struct *task;
-	unsigned int referral_count;
+static struct kernel_param_ops param_ops_portnr = {
+	.set = param_set_portnr,
+	.get = param_get_uint,
 };
-
-static LIST_HEAD(nfs_referral_count_list);
-static DEFINE_SPINLOCK(nfs_referral_count_list_lock);
-
-static struct nfs_referral_count *nfs_find_referral_count(void)
-{
-	struct nfs_referral_count *p;
-
-	list_for_each_entry(p, &nfs_referral_count_list, list) {
-		if (p->task == current)
-			return p;
-	}
-	return NULL;
-}
-
-#define NFS_MAX_NESTED_REFERRALS 2
-
-static int nfs_referral_loop_protect(void)
-{
-	struct nfs_referral_count *p, *new;
-	int ret = -ENOMEM;
-
-	new = kmalloc(sizeof(*new), GFP_KERNEL);
-	if (!new)
-		goto out;
-	new->task = current;
-	new->referral_count = 1;
-
-	ret = 0;
-	spin_lock(&nfs_referral_count_list_lock);
-	p = nfs_find_referral_count();
-	if (p != NULL) {
-		if (p->referral_count >= NFS_MAX_NESTED_REFERRALS)
-			ret = -ELOOP;
-		else
-			p->referral_count++;
-	} else {
-		list_add(&new->list, &nfs_referral_count_list);
-		new = NULL;
-	}
-	spin_unlock(&nfs_referral_count_list_lock);
-	kfree(new);
-out:
-	return ret;
-}
-
-static void nfs_referral_loop_unprotect(void)
-{
-	struct nfs_referral_count *p;
-
-	spin_lock(&nfs_referral_count_list_lock);
-	p = nfs_find_referral_count();
-	p->referral_count--;
-	if (p->referral_count == 0)
-		list_del(&p->list);
-	else
-		p = NULL;
-	spin_unlock(&nfs_referral_count_list_lock);
-	kfree(p);
-}
-
-static struct dentry *nfs_follow_remote_path(struct vfsmount *root_mnt,
-		const char *export_path)
-{
-	struct dentry *dentry;
-	int err;
-
-	if (IS_ERR(root_mnt))
-		return ERR_CAST(root_mnt);
-
-	err = nfs_referral_loop_protect();
-	if (err) {
-		mntput(root_mnt);
-		return ERR_PTR(err);
-	}
-
-	dentry = mount_subtree(root_mnt, export_path);
-	nfs_referral_loop_unprotect();
-
-	return dentry;
-}
-
-static struct dentry *nfs4_try_mount(int flags, const char *dev_name,
-			 struct nfs_mount_info *mount_info)
-{
-	char *export_path;
-	struct vfsmount *root_mnt;
-	struct dentry *res;
-	struct nfs_parsed_mount_data *data = mount_info->parsed;
-
-	dfprintk(MOUNT, "--> nfs4_try_mount()\n");
-
-	mount_info->fill_super = nfs4_fill_super;
-
-	export_path = data->nfs_server.export_path;
-	data->nfs_server.export_path = "/";
-	root_mnt = nfs_do_root_mount(&nfs4_remote_fs_type, flags, mount_info,
-			data->nfs_server.hostname);
-	data->nfs_server.export_path = export_path;
-
-	res = nfs_follow_remote_path(root_mnt, export_path);
-
-	dfprintk(MOUNT, "<-- nfs4_try_mount() = %ld%s\n",
-			IS_ERR(res) ? PTR_ERR(res) : 0,
-			IS_ERR(res) ? " [error]" : "");
-	return res;
-}
-
-static void nfs4_kill_super(struct super_block *sb)
-{
-	struct nfs_server *server = NFS_SB(sb);
-
-	dprintk("--> %s\n", __func__);
-	nfs_super_return_all_delegations(sb);
-	kill_anon_super(sb);
-	nfs_fscache_release_super_cookie(sb);
-	nfs_free_server(server);
-	dprintk("<-- %s\n", __func__);
-}
-
-/*
- * Clone an NFS4 server record on xdev traversal (FSID-change)
- */
-static struct dentry *
-nfs4_xdev_mount(struct file_system_type *fs_type, int flags,
-		 const char *dev_name, void *raw_data)
-{
-	struct nfs_mount_info mount_info = {
-		.fill_super = nfs4_clone_super,
-		.set_security = nfs_clone_sb_security,
-		.cloned = raw_data,
-	};
-	return nfs_xdev_mount_common(&nfs4_fs_type, flags, dev_name, &mount_info);
-}
-
-static struct dentry *
-nfs4_remote_referral_mount(struct file_system_type *fs_type, int flags,
-			   const char *dev_name, void *raw_data)
-{
-	struct nfs_mount_info mount_info = {
-		.fill_super = nfs4_fill_super,
-		.set_security = nfs_clone_sb_security,
-		.cloned = raw_data,
-	};
-	struct nfs_server *server;
-	struct dentry *mntroot = ERR_PTR(-ENOMEM);
-
-	dprintk("--> nfs4_referral_get_sb()\n");
-
-	mount_info.mntfh = nfs_alloc_fhandle();
-	if (mount_info.cloned == NULL || mount_info.mntfh == NULL)
-		goto out;
-
-	/* create a new volume representation */
-	server = nfs4_create_referral_server(mount_info.cloned, mount_info.mntfh);
-	if (IS_ERR(server)) {
-		mntroot = ERR_CAST(server);
-		goto out;
-	}
-
-	mntroot = nfs_fs_mount_common(&nfs4_fs_type, server, flags, dev_name, &mount_info);
-out:
-	nfs_free_fhandle(mount_info.mntfh);
-	return mntroot;
-}
-
-/*
- * Create an NFS4 server record on referral traversal
- */
-static struct dentry *nfs4_referral_mount(struct file_system_type *fs_type,
-		int flags, const char *dev_name, void *raw_data)
-{
-	struct nfs_clone_mount *data = raw_data;
-	char *export_path;
-	struct vfsmount *root_mnt;
-	struct dentry *res;
-
-	dprintk("--> nfs4_referral_mount()\n");
-
-	export_path = data->mnt_path;
-	data->mnt_path = "/";
-
-	root_mnt = nfs_do_root_mount(&nfs4_remote_referral_fs_type,
-			flags, data, data->hostname);
-	data->mnt_path = export_path;
-
-	res = nfs_follow_remote_path(root_mnt, export_path);
-	dprintk("<-- nfs4_referral_mount() = %ld%s\n",
-			IS_ERR(res) ? PTR_ERR(res) : 0,
-			IS_ERR(res) ? " [error]" : "");
-	return res;
-}
+#define param_check_portnr(name, p) __param_check(name, p, unsigned int);
+
+module_param_named(callback_tcpport, nfs_callback_set_tcpport, portnr, 0644);
+module_param(nfs_idmap_cache_timeout, int, 0644);
+module_param(nfs4_disable_idmapping, bool, 0644);
+module_param_string(nfs4_unique_id, nfs4_client_id_uniquifier,
+			NFS4_CLIENT_ID_UNIQ_LEN, 0600);
+MODULE_PARM_DESC(nfs4_disable_idmapping,
+		"Turn off NFSv4 idmapping when using 'sec=sys'");
+module_param(max_session_slots, ushort, 0644);
+MODULE_PARM_DESC(max_session_slots, "Maximum number of outstanding NFSv4.1 "
+		"requests the client will negotiate");
+module_param(send_implementation_id, ushort, 0644);
+MODULE_PARM_DESC(send_implementation_id,
+		"Send implementation ID with NFSv4.1 exchange_id");
+MODULE_PARM_DESC(nfs4_unique_id, "nfs_client_id4 uniquifier string");
+MODULE_ALIAS("nfs4");
 
 #endif /* CONFIG_NFS_V4 */
diff --git a/fs/nfs/sysctl.c b/fs/nfs/sysctl.c
index ad4d2e787b2..6b3f2535a3e 100644
--- a/fs/nfs/sysctl.c
+++ b/fs/nfs/sysctl.c
@@ -9,37 +9,11 @@
 #include <linux/fs.h>
 #include <linux/sysctl.h>
 #include <linux/module.h>
-#include <linux/nfs4.h>
-#include <linux/nfs_idmap.h>
 #include <linux/nfs_fs.h>
 
-#include "callback.h"
-
-#ifdef CONFIG_NFS_V4
-static const int nfs_set_port_min = 0;
-static const int nfs_set_port_max = 65535;
-#endif
 static struct ctl_table_header *nfs_callback_sysctl_table;
 
 static ctl_table nfs_cb_sysctls[] = {
-#ifdef CONFIG_NFS_V4
-	{
-		.procname = "nfs_callback_tcpport",
-		.data = &nfs_callback_set_tcpport,
-		.maxlen = sizeof(int),
-		.mode = 0644,
-		.proc_handler = proc_dointvec_minmax,
-		.extra1 = (int *)&nfs_set_port_min,
-		.extra2 = (int *)&nfs_set_port_max,
-	},
-	{
-		.procname = "idmap_cache_timeout",
-		.data = &nfs_idmap_cache_timeout,
-		.maxlen = sizeof(int),
-		.mode = 0644,
-		.proc_handler = proc_dointvec_jiffies,
-	},
-#endif
 	{
 		.procname	= "nfs_mountpoint_timeout",
 		.data		= &nfs_mountpoint_expiry_timeout,
diff --git a/fs/nfs/unlink.c b/fs/nfs/unlink.c
index 3210a03342f..3f79c77153b 100644
--- a/fs/nfs/unlink.c
+++ b/fs/nfs/unlink.c
@@ -95,7 +95,7 @@ static void nfs_async_unlink_release(void *calldata)
 
 	nfs_dec_sillycount(data->dir);
 	nfs_free_unlinkdata(data);
-	nfs_sb_deactive(sb);
+	nfs_sb_deactive_async(sb);
 }
 
 static void nfs_unlink_prepare(struct rpc_task *task, void *calldata)
@@ -501,7 +501,7 @@ nfs_sillyrename(struct inode *dir, struct dentry *dentry)
 		(unsigned long long)NFS_FILEID(dentry->d_inode));
 
 	/* Return delegation in anticipation of the rename */
-	nfs_inode_return_delegation(dentry->d_inode);
+	NFS_PROTO(dentry->d_inode)->return_delegation(dentry->d_inode);
 
 	sdentry = NULL;
 	do {
diff --git a/fs/nfs/write.c b/fs/nfs/write.c
index 4d6861c0dc1..c483cc50b82 100644
--- a/fs/nfs/write.c
+++ b/fs/nfs/write.c
@@ -52,7 +52,7 @@ static mempool_t *nfs_commit_mempool;
 
 struct nfs_commit_data *nfs_commitdata_alloc(void)
 {
-	struct nfs_commit_data *p = mempool_alloc(nfs_commit_mempool, GFP_NOFS);
+	struct nfs_commit_data *p = mempool_alloc(nfs_commit_mempool, GFP_NOIO);
 
 	if (p) {
 		memset(p, 0, sizeof(*p));
@@ -70,7 +70,7 @@ EXPORT_SYMBOL_GPL(nfs_commit_free);
 
 struct nfs_write_header *nfs_writehdr_alloc(void)
 {
-	struct nfs_write_header *p = mempool_alloc(nfs_wdata_mempool, GFP_NOFS);
+	struct nfs_write_header *p = mempool_alloc(nfs_wdata_mempool, GFP_NOIO);
 
 	if (p) {
 		struct nfs_pgio_header *hdr = &p->header;
@@ -84,6 +84,7 @@ struct nfs_write_header *nfs_writehdr_alloc(void)
 	}
 	return p;
 }
+EXPORT_SYMBOL_GPL(nfs_writehdr_alloc);
 
 static struct nfs_write_data *nfs_writedata_alloc(struct nfs_pgio_header *hdr,
 						  unsigned int pagecount)
@@ -115,6 +116,7 @@ void nfs_writehdr_free(struct nfs_pgio_header *hdr)
 	struct nfs_write_header *whdr = container_of(hdr, struct nfs_write_header, header);
 	mempool_free(whdr, nfs_wdata_mempool);
 }
+EXPORT_SYMBOL_GPL(nfs_writehdr_free);
 
 void nfs_writedata_release(struct nfs_write_data *wdata)
 {
@@ -124,13 +126,18 @@ void nfs_writedata_release(struct nfs_write_data *wdata)
 	put_nfs_open_context(wdata->args.context);
 	if (wdata->pages.pagevec != wdata->pages.page_array)
 		kfree(wdata->pages.pagevec);
-	if (wdata != &write_header->rpc_data)
-		kfree(wdata);
-	else
+	if (wdata == &write_header->rpc_data) {
 		wdata->header = NULL;
+		wdata = NULL;
+	}
 	if (atomic_dec_and_test(&hdr->refcnt))
 		hdr->completion_ops->completion(hdr);
+	/* Note: we only free the rpc_task after callbacks are done.
+	 * See the comment in rpc_free_task() for why
+	 */
+	kfree(wdata);
 }
+EXPORT_SYMBOL_GPL(nfs_writedata_release);
 
 static void nfs_context_set_write_error(struct nfs_open_context *ctx, int error)
 {
@@ -139,25 +146,38 @@ static void nfs_context_set_write_error(struct nfs_open_context *ctx, int error)
 	set_bit(NFS_CONTEXT_ERROR_WRITE, &ctx->flags);
 }
 
-static struct nfs_page *nfs_page_find_request_locked(struct page *page)
+static struct nfs_page *
+nfs_page_find_request_locked(struct nfs_inode *nfsi, struct page *page)
 {
 	struct nfs_page *req = NULL;
 
-	if (PagePrivate(page)) {
+	if (PagePrivate(page))
 		req = (struct nfs_page *)page_private(page);
-		if (req != NULL)
-			kref_get(&req->wb_kref);
+	else if (unlikely(PageSwapCache(page))) {
+		struct nfs_page *freq, *t;
+
+		/* Linearly search the commit list for the correct req */
+		list_for_each_entry_safe(freq, t, &nfsi->commit_info.list, wb_list) {
+			if (freq->wb_page == page) {
+				req = freq;
+				break;
+			}
+		}
 	}
+
+	if (req)
+		kref_get(&req->wb_kref);
+
 	return req;
 }
 
 static struct nfs_page *nfs_page_find_request(struct page *page)
 {
-	struct inode *inode = page->mapping->host;
+	struct inode *inode = page_file_mapping(page)->host;
 	struct nfs_page *req = NULL;
 
 	spin_lock(&inode->i_lock);
-	req = nfs_page_find_request_locked(page);
+	req = nfs_page_find_request_locked(NFS_I(inode), page);
 	spin_unlock(&inode->i_lock);
 	return req;
 }
@@ -165,16 +185,16 @@ static struct nfs_page *nfs_page_find_request(struct page *page)
 /* Adjust the file length if we're writing beyond the end */
 static void nfs_grow_file(struct page *page, unsigned int offset, unsigned int count)
 {
-	struct inode *inode = page->mapping->host;
+	struct inode *inode = page_file_mapping(page)->host;
 	loff_t end, i_size;
 	pgoff_t end_index;
 
 	spin_lock(&inode->i_lock);
 	i_size = i_size_read(inode);
 	end_index = (i_size - 1) >> PAGE_CACHE_SHIFT;
-	if (i_size > 0 && page->index < end_index)
+	if (i_size > 0 && page_file_index(page) < end_index)
 		goto out;
-	end = ((loff_t)page->index << PAGE_CACHE_SHIFT) + ((loff_t)offset+count);
+	end = page_file_offset(page) + ((loff_t)offset+count);
 	if (i_size >= end)
 		goto out;
 	i_size_write(inode, end);
@@ -186,8 +206,7 @@ out:
 /* A writeback failed: mark the page as bad, and invalidate the page cache */
 static void nfs_set_pageerror(struct page *page)
 {
-	SetPageError(page);
-	nfs_zap_mapping(page->mapping->host, page->mapping);
+	nfs_zap_mapping(page_file_mapping(page)->host, page_file_mapping(page));
 }
 
 /* We can set the PG_uptodate flag if we see that a write request
@@ -223,26 +242,23 @@ int nfs_congestion_kb;
 #define NFS_CONGESTION_OFF_THRESH	\
 	(NFS_CONGESTION_ON_THRESH - (NFS_CONGESTION_ON_THRESH >> 2))
 
-static int nfs_set_page_writeback(struct page *page)
+static void nfs_set_page_writeback(struct page *page)
 {
+	struct nfs_server *nfss = NFS_SERVER(page_file_mapping(page)->host);
 	int ret = test_set_page_writeback(page);
 
-	if (!ret) {
-		struct inode *inode = page->mapping->host;
-		struct nfs_server *nfss = NFS_SERVER(inode);
+	WARN_ON_ONCE(ret != 0);
 
-		if (atomic_long_inc_return(&nfss->writeback) >
-				NFS_CONGESTION_ON_THRESH) {
-			set_bdi_congested(&nfss->backing_dev_info,
-						BLK_RW_ASYNC);
-		}
+	if (atomic_long_inc_return(&nfss->writeback) >
+			NFS_CONGESTION_ON_THRESH) {
+		set_bdi_congested(&nfss->backing_dev_info,
+					BLK_RW_ASYNC);
 	}
-	return ret;
 }
 
 static void nfs_end_page_writeback(struct page *page)
 {
-	struct inode *inode = page->mapping->host;
+	struct inode *inode = page_file_mapping(page)->host;
 	struct nfs_server *nfss = NFS_SERVER(inode);
 
 	end_page_writeback(page);
@@ -252,13 +268,13 @@ static void nfs_end_page_writeback(struct page *page)
 
 static struct nfs_page *nfs_find_and_lock_request(struct page *page, bool nonblock)
 {
-	struct inode *inode = page->mapping->host;
+	struct inode *inode = page_file_mapping(page)->host;
 	struct nfs_page *req;
 	int ret;
 
 	spin_lock(&inode->i_lock);
 	for (;;) {
-		req = nfs_page_find_request_locked(page);
+		req = nfs_page_find_request_locked(NFS_I(inode), page);
 		if (req == NULL)
 			break;
 		if (nfs_lock_request(req))
@@ -299,10 +315,10 @@ static int nfs_page_async_flush(struct nfs_pageio_descriptor *pgio,
 	if (IS_ERR(req))
 		goto out;
 
-	ret = nfs_set_page_writeback(page);
-	BUG_ON(ret != 0);
-	BUG_ON(test_bit(PG_CLEAN, &req->wb_flags));
+	nfs_set_page_writeback(page);
+	WARN_ON_ONCE(test_bit(PG_CLEAN, &req->wb_flags));
 
+	ret = 0;
 	if (!nfs_pageio_add_request(pgio, req)) {
 		nfs_redirty_request(req);
 		ret = pgio->pg_error;
@@ -313,13 +329,13 @@ out:
 
 static int nfs_do_writepage(struct page *page, struct writeback_control *wbc, struct nfs_pageio_descriptor *pgio)
 {
-	struct inode *inode = page->mapping->host;
+	struct inode *inode = page_file_mapping(page)->host;
 	int ret;
 
 	nfs_inc_stats(inode, NFSIOS_VFSWRITEPAGE);
 	nfs_add_stats(inode, NFSIOS_WRITEPAGES, 1);
 
-	nfs_pageio_cond_complete(pgio, page->index);
+	nfs_pageio_cond_complete(pgio, page_file_index(page));
 	ret = nfs_page_async_flush(pgio, page, wbc->sync_mode == WB_SYNC_NONE);
 	if (ret == -EAGAIN) {
 		redirty_page_for_writepage(wbc, page);
@@ -336,8 +352,10 @@ static int nfs_writepage_locked(struct page *page, struct writeback_control *wbc
 	struct nfs_pageio_descriptor pgio;
 	int err;
 
-	nfs_pageio_init_write(&pgio, page->mapping->host, wb_priority(wbc),
-			      &nfs_async_write_completion_ops);
+	NFS_PROTO(page_file_mapping(page)->host)->write_pageio_init(&pgio,
+							  page->mapping->host,
+							  wb_priority(wbc),
+							  &nfs_async_write_completion_ops);
 	err = nfs_do_writepage(page, wbc, &pgio);
 	nfs_pageio_complete(&pgio);
 	if (err < 0)
@@ -380,8 +398,7 @@ int nfs_writepages(struct address_space *mapping, struct writeback_control *wbc)
 
 	nfs_inc_stats(inode, NFSIOS_VFSWRITEPAGES);
 
-	nfs_pageio_init_write(&pgio, inode, wb_priority(wbc),
-			      &nfs_async_write_completion_ops);
+	NFS_PROTO(inode)->write_pageio_init(&pgio, inode, wb_priority(wbc), &nfs_async_write_completion_ops);
 	err = write_cache_pages(mapping, wbc, nfs_writepages_callback, &pgio);
 	nfs_pageio_complete(&pgio);
 
@@ -410,11 +427,17 @@ static void nfs_inode_add_request(struct inode *inode, struct nfs_page *req)
 	nfs_lock_request(req);
 
 	spin_lock(&inode->i_lock);
-	if (!nfsi->npages && nfs_have_delegation(inode, FMODE_WRITE))
+	if (!nfsi->npages && NFS_PROTO(inode)->have_delegation(inode, FMODE_WRITE))
 		inode->i_version++;
-	set_bit(PG_MAPPED, &req->wb_flags);
-	SetPagePrivate(req->wb_page);
-	set_page_private(req->wb_page, (unsigned long)req);
+	/*
+	 * Swap-space should not get truncated. Hence no need to plug the race
+	 * with invalidate/truncate.
+	 */
+	if (likely(!PageSwapCache(req->wb_page))) {
+		set_bit(PG_MAPPED, &req->wb_flags);
+		SetPagePrivate(req->wb_page);
+		set_page_private(req->wb_page, (unsigned long)req);
+	}
 	nfsi->npages++;
 	kref_get(&req->wb_kref);
 	spin_unlock(&inode->i_lock);
@@ -428,12 +451,12 @@ static void nfs_inode_remove_request(struct nfs_page *req)
 	struct inode *inode = req->wb_context->dentry->d_inode;
 	struct nfs_inode *nfsi = NFS_I(inode);
 
-	BUG_ON (!NFS_WBACK_BUSY(req));
-
 	spin_lock(&inode->i_lock);
-	set_page_private(req->wb_page, 0);
-	ClearPagePrivate(req->wb_page);
-	clear_bit(PG_MAPPED, &req->wb_flags);
+	if (likely(!PageSwapCache(req->wb_page))) {
+		set_page_private(req->wb_page, 0);
+		ClearPagePrivate(req->wb_page);
+		clear_bit(PG_MAPPED, &req->wb_flags);
+	}
 	nfsi->npages--;
 	spin_unlock(&inode->i_lock);
 	nfs_release_request(req);
@@ -445,7 +468,7 @@ nfs_mark_request_dirty(struct nfs_page *req)
 	__set_page_dirty_nobuffers(req->wb_page);
 }
 
-#if defined(CONFIG_NFS_V3) || defined(CONFIG_NFS_V4)
+#if IS_ENABLED(CONFIG_NFS_V3) || IS_ENABLED(CONFIG_NFS_V4)
 /**
  * nfs_request_add_commit_list - add request to a commit list
  * @req: pointer to a struct nfs_page
@@ -470,7 +493,7 @@ nfs_request_add_commit_list(struct nfs_page *req, struct list_head *dst,
 	spin_unlock(cinfo->lock);
 	if (!cinfo->dreq) {
 		inc_zone_page_state(req->wb_page, NR_UNSTABLE_NFS);
-		inc_bdi_stat(req->wb_page->mapping->backing_dev_info,
+		inc_bdi_stat(page_file_mapping(req->wb_page)->backing_dev_info,
 			     BDI_RECLAIMABLE);
 		__mark_inode_dirty(req->wb_context->dentry->d_inode,
 				   I_DIRTY_DATASYNC);
@@ -537,7 +560,7 @@ static void
 nfs_clear_page_commit(struct page *page)
 {
 	dec_zone_page_state(page, NR_UNSTABLE_NFS);
-	dec_bdi_stat(page->mapping->backing_dev_info, BDI_RECLAIMABLE);
+	dec_bdi_stat(page_file_mapping(page)->backing_dev_info, BDI_RECLAIMABLE);
 }
 
 static void
@@ -620,7 +643,7 @@ static void nfs_write_completion(struct nfs_pgio_header *hdr)
 			goto next;
 		}
 		if (test_bit(NFS_IOHDR_NEED_COMMIT, &hdr->flags)) {
-			memcpy(&req->wb_verf, hdr->verf, sizeof(req->wb_verf));
+			memcpy(&req->wb_verf, &hdr->verf->verifier, sizeof(req->wb_verf));
 			nfs_mark_request_commit(req, hdr->lseg, &cinfo);
 			goto next;
 		}
@@ -635,7 +658,7 @@ out:
 	hdr->release(hdr);
 }
 
-#if defined(CONFIG_NFS_V3) || defined(CONFIG_NFS_V4)
+#if  IS_ENABLED(CONFIG_NFS_V3) || IS_ENABLED(CONFIG_NFS_V4)
 static unsigned long
 nfs_reqs_to_commit(struct nfs_commit_info *cinfo)
 {
@@ -729,7 +752,7 @@ static struct nfs_page *nfs_try_to_update_request(struct inode *inode,
 	spin_lock(&inode->i_lock);
 
 	for (;;) {
-		req = nfs_page_find_request_locked(page);
+		req = nfs_page_find_request_locked(NFS_I(inode), page);
 		if (req == NULL)
 			goto out_unlock;
 
@@ -788,7 +811,7 @@ out_err:
 static struct nfs_page * nfs_setup_write_request(struct nfs_open_context* ctx,
 		struct page *page, unsigned int offset, unsigned int bytes)
 {
-	struct inode *inode = page->mapping->host;
+	struct inode *inode = page_file_mapping(page)->host;
 	struct nfs_page	*req;
 
 	req = nfs_try_to_update_request(inode, page, offset, bytes);
@@ -821,6 +844,7 @@ static int nfs_writepage_setup(struct nfs_open_context *ctx, struct page *page,
 int nfs_flush_incompatible(struct file *file, struct page *page)
 {
 	struct nfs_open_context *ctx = nfs_file_open_context(file);
+	struct nfs_lock_context *l_ctx;
 	struct nfs_page	*req;
 	int do_flush, status;
 	/*
@@ -835,13 +859,16 @@ int nfs_flush_incompatible(struct file *file, struct page *page)
 		req = nfs_page_find_request(page);
 		if (req == NULL)
 			return 0;
-		do_flush = req->wb_page != page || req->wb_context != ctx ||
-			req->wb_lock_context->lockowner != current->files ||
-			req->wb_lock_context->pid != current->tgid;
+		l_ctx = req->wb_lock_context;
+		do_flush = req->wb_page != page || req->wb_context != ctx;
+		if (l_ctx) {
+			do_flush |= l_ctx->lockowner.l_owner != current->files
+				|| l_ctx->lockowner.l_pid != current->tgid;
+		}
 		nfs_release_request(req);
 		if (!do_flush)
 			return 0;
-		status = nfs_wb_page(page->mapping->host, page);
+		status = nfs_wb_page(page_file_mapping(page)->host, page);
 	} while (status == 0);
 	return status;
 }
@@ -855,7 +882,7 @@ static bool nfs_write_pageuptodate(struct page *page, struct inode *inode)
 {
 	if (nfs_have_delegated_attributes(inode))
 		goto out;
-	if (NFS_I(inode)->cache_validity & NFS_INO_REVAL_PAGECACHE)
+	if (NFS_I(inode)->cache_validity & (NFS_INO_INVALID_DATA|NFS_INO_REVAL_PAGECACHE))
 		return false;
 out:
 	return PageUptodate(page) != 0;
@@ -871,7 +898,7 @@ int nfs_updatepage(struct file *file, struct page *page,
 		unsigned int offset, unsigned int count)
 {
 	struct nfs_open_context *ctx = nfs_file_open_context(file);
-	struct inode	*inode = page->mapping->host;
+	struct inode	*inode = page_file_mapping(page)->host;
 	int		status = 0;
 
 	nfs_inc_stats(inode, NFSIOS_VFSUPDATEPAGE);
@@ -879,7 +906,7 @@ int nfs_updatepage(struct file *file, struct page *page,
 	dprintk("NFS:       nfs_updatepage(%s/%s %d@%lld)\n",
 		file->f_path.dentry->d_parent->d_name.name,
 		file->f_path.dentry->d_name.name, count,
-		(long long)(page_offset(page) + offset));
+		(long long)(page_file_offset(page) + offset));
 
 	/* If we're not using byte range locks, and we know the page
 	 * is up to date, it may be more efficient to extend the write
@@ -1172,6 +1199,7 @@ int nfs_generic_flush(struct nfs_pageio_descriptor *desc,
 		return nfs_flush_multi(desc, hdr);
 	return nfs_flush_one(desc, hdr);
 }
+EXPORT_SYMBOL_GPL(nfs_generic_flush);
 
 static int nfs_generic_pg_writepages(struct nfs_pageio_descriptor *desc)
 {
@@ -1202,13 +1230,14 @@ static const struct nfs_pageio_ops nfs_pageio_write_ops = {
 	.pg_doio = nfs_generic_pg_writepages,
 };
 
-void nfs_pageio_init_write_mds(struct nfs_pageio_descriptor *pgio,
+void nfs_pageio_init_write(struct nfs_pageio_descriptor *pgio,
 			       struct inode *inode, int ioflags,
 			       const struct nfs_pgio_completion_ops *compl_ops)
 {
 	nfs_pageio_init(pgio, inode, &nfs_pageio_write_ops, compl_ops,
 				NFS_SERVER(inode)->wsize, ioflags);
 }
+EXPORT_SYMBOL_GPL(nfs_pageio_init_write);
 
 void nfs_pageio_reset_write_mds(struct nfs_pageio_descriptor *pgio)
 {
@@ -1217,13 +1246,6 @@ void nfs_pageio_reset_write_mds(struct nfs_pageio_descriptor *pgio)
 }
 EXPORT_SYMBOL_GPL(nfs_pageio_reset_write_mds);
 
-void nfs_pageio_init_write(struct nfs_pageio_descriptor *pgio,
-			   struct inode *inode, int ioflags,
-			   const struct nfs_pgio_completion_ops *compl_ops)
-{
-	if (!pnfs_pageio_init_write(pgio, inode, ioflags, compl_ops))
-		nfs_pageio_init_write_mds(pgio, inode, ioflags, compl_ops);
-}
 
 void nfs_write_prepare(struct rpc_task *task, void *calldata)
 {
@@ -1303,7 +1325,7 @@ void nfs_writeback_done(struct rpc_task *task, struct nfs_write_data *data)
 		return;
 	nfs_add_stats(inode, NFSIOS_SERVERWRITTENBYTES, resp->count);
 
-#if defined(CONFIG_NFS_V3) || defined(CONFIG_NFS_V4)
+#if IS_ENABLED(CONFIG_NFS_V3) || IS_ENABLED(CONFIG_NFS_V4)
 	if (resp->verf->committed < argp->stable && task->tk_status >= 0) {
 		/* We tried a write call, but the server did not
 		 * commit data to stable storage even though we
@@ -1363,7 +1385,7 @@ void nfs_writeback_done(struct rpc_task *task, struct nfs_write_data *data)
 }
 
 
-#if defined(CONFIG_NFS_V3) || defined(CONFIG_NFS_V4)
+#if IS_ENABLED(CONFIG_NFS_V3) || IS_ENABLED(CONFIG_NFS_V4)
 static int nfs_commit_set_lock(struct nfs_inode *nfsi, int may_wait)
 {
 	int ret;
@@ -1475,7 +1497,7 @@ void nfs_retry_commit(struct list_head *page_list,
 		nfs_mark_request_commit(req, lseg, cinfo);
 		if (!cinfo->dreq) {
 			dec_zone_page_state(req->wb_page, NR_UNSTABLE_NFS);
-			dec_bdi_stat(req->wb_page->mapping->backing_dev_info,
+			dec_bdi_stat(page_file_mapping(req->wb_page)->backing_dev_info,
 				     BDI_RECLAIMABLE);
 		}
 		nfs_unlock_and_release_request(req);
@@ -1547,7 +1569,7 @@ static void nfs_commit_release_pages(struct nfs_commit_data *data)
 
 		/* Okay, COMMIT succeeded, apparently. Check the verifier
 		 * returned by the server against all stored verfs. */
-		if (!memcmp(req->wb_verf.verifier, data->verf.verifier, sizeof(data->verf.verifier))) {
+		if (!memcmp(&req->wb_verf, &data->verf.verifier, sizeof(req->wb_verf))) {
 			/* We have a match */
 			nfs_inode_remove_request(req);
 			dprintk(" OK\n");
@@ -1556,6 +1578,7 @@ static void nfs_commit_release_pages(struct nfs_commit_data *data)
 		/* We have a mismatch. Write the page again */
 		dprintk(" mismatch\n");
 		nfs_mark_request_dirty(req);
+		set_bit(NFS_CONTEXT_RESEND_WRITES, &req->wb_context->flags);
 	next:
 		nfs_unlock_and_release_request(req);
 	}
@@ -1677,22 +1700,9 @@ static int nfs_commit_unstable_pages(struct inode *inode, struct writeback_contr
 
 int nfs_write_inode(struct inode *inode, struct writeback_control *wbc)
 {
-	int ret;
-
-	ret = nfs_commit_unstable_pages(inode, wbc);
-	if (ret >= 0 && test_bit(NFS_INO_LAYOUTCOMMIT, &NFS_I(inode)->flags)) {
-		int status;
-		bool sync = true;
-
-		if (wbc->sync_mode == WB_SYNC_NONE)
-			sync = false;
-
-		status = pnfs_layoutcommit_inode(inode, sync);
-		if (status < 0)
-			return status;
-	}
-	return ret;
+	return nfs_commit_unstable_pages(inode, wbc);
 }
+EXPORT_SYMBOL_GPL(nfs_write_inode);
 
 /*
  * flush the inode to disk.
@@ -1708,13 +1718,13 @@ int nfs_wb_all(struct inode *inode)
 
 	return sync_inode(inode, &wbc);
 }
+EXPORT_SYMBOL_GPL(nfs_wb_all);
 
 int nfs_wb_page_cancel(struct inode *inode, struct page *page)
 {
 	struct nfs_page *req;
 	int ret = 0;
 
-	BUG_ON(!PageLocked(page));
 	for (;;) {
 		wait_on_page_writeback(page);
 		req = nfs_page_find_request(page);
@@ -1744,7 +1754,7 @@ int nfs_wb_page_cancel(struct inode *inode, struct page *page)
  */
 int nfs_wb_page(struct inode *inode, struct page *page)
 {
-	loff_t range_start = page_offset(page);
+	loff_t range_start = page_file_offset(page);
 	loff_t range_end = range_start + (loff_t)(PAGE_CACHE_SIZE - 1);
 	struct writeback_control wbc = {
 		.sync_mode = WB_SYNC_ALL,
@@ -1788,7 +1798,8 @@ int nfs_migrate_page(struct address_space *mapping, struct page *newpage,
 	if (PagePrivate(page))
 		return -EBUSY;
 
-	nfs_fscache_release_page(page, GFP_KERNEL);
+	if (!nfs_fscache_release_page(page, GFP_KERNEL))
+		return -EBUSY;
 
 	return migrate_page(mapping, newpage, page, mode);
 }
@@ -1806,19 +1817,19 @@ int __init nfs_init_writepagecache(void)
 	nfs_wdata_mempool = mempool_create_slab_pool(MIN_POOL_WRITE,
 						     nfs_wdata_cachep);
 	if (nfs_wdata_mempool == NULL)
-		return -ENOMEM;
+		goto out_destroy_write_cache;
 
 	nfs_cdata_cachep = kmem_cache_create("nfs_commit_data",
 					     sizeof(struct nfs_commit_data),
 					     0, SLAB_HWCACHE_ALIGN,
 					     NULL);
 	if (nfs_cdata_cachep == NULL)
-		return -ENOMEM;
+		goto out_destroy_write_mempool;
 
 	nfs_commit_mempool = mempool_create_slab_pool(MIN_POOL_COMMIT,
-						      nfs_wdata_cachep);
+						      nfs_cdata_cachep);
 	if (nfs_commit_mempool == NULL)
-		return -ENOMEM;
+		goto out_destroy_commit_cache;
 
 	/*
 	 * NFS congestion size, scale with available memory.
@@ -1841,11 +1852,20 @@ int __init nfs_init_writepagecache(void)
 		nfs_congestion_kb = 256*1024;
 
 	return 0;
+
+out_destroy_commit_cache:
+	kmem_cache_destroy(nfs_cdata_cachep);
+out_destroy_write_mempool:
+	mempool_destroy(nfs_wdata_mempool);
+out_destroy_write_cache:
+	kmem_cache_destroy(nfs_wdata_cachep);
+	return -ENOMEM;
 }
 
 void nfs_destroy_writepagecache(void)
 {
 	mempool_destroy(nfs_commit_mempool);
+	kmem_cache_destroy(nfs_cdata_cachep);
 	mempool_destroy(nfs_wdata_mempool);
 	kmem_cache_destroy(nfs_wdata_cachep);
 }