Merge tag 'nfs-for-4.1-1' of git://git.linux-nfs.org/projects/trondmy/linux-nfs

Pull NFS client updates from Trond Myklebust:
 "Another set of mainly bugfixes and a couple of cleanups.  No new
  functionality in this round.

  Highlights include:

  Stable patches:
   - Fix a regression in /proc/self/mountstats
   - Fix the pNFS flexfiles O_DIRECT support
   - Fix high load average due to callback thread sleeping

  Bugfixes:
   - Various patches to fix the pNFS layoutcommit support
   - Do not cache pNFS deviceids unless server notifications are enabled
   - Fix a SUNRPC transport reconnection regression
   - make debugfs file creation failure non-fatal in SUNRPC
   - Another fix for circular directory warnings on NFSv4 "junctioned"
     mountpoints
   - Fix locking around NFSv4.2 fallocate() support
   - Truncating NFSv4 file opens should also sync O_DIRECT writes
   - Prevent infinite loop in rpcrdma_ep_create()

  Features:
   - Various improvements to the RDMA transport code's handling of
     memory registration
   - Various code cleanups"

* tag 'nfs-for-4.1-1' of git://git.linux-nfs.org/projects/trondmy/linux-nfs: (55 commits)
  fs/nfs: fix new compiler warning about boolean in switch
  nfs: Remove unneeded casts in nfs
  NFS: Don't attempt to decode missing directory entries
  Revert "nfs: replace nfs_add_stats with nfs_inc_stats when add one"
  NFS: Rename idmap.c to nfs4idmap.c
  NFS: Move nfs_idmap.h into fs/nfs/
  NFS: Remove CONFIG_NFS_V4 checks from nfs_idmap.h
  NFS: Add a stub for GETDEVICELIST
  nfs: remove WARN_ON_ONCE from nfs_direct_good_bytes
  nfs: fix DIO good bytes calculation
  nfs: Fetch MOUNTED_ON_FILEID when updating an inode
  sunrpc: make debugfs file creation failure non-fatal
  nfs: fix high load average due to callback thread sleeping
  NFS: Reduce time spent holding the i_mutex during fallocate()
  NFS: Don't zap caches on fallocate()
  xprtrdma: Make rpcrdma_{un}map_one() into inline functions
  xprtrdma: Handle non-SEND completions via a callout
  xprtrdma: Add "open" memreg op
  xprtrdma: Add "destroy MRs" memreg op
  xprtrdma: Add "reset MRs" memreg op
  ...

34 files changed, 313 insertions, 163 deletions

diff --git a/fs/nfs/Makefile b/fs/nfs/Makefile
index 1e987ac..8664417 100644
--- a/fs/nfs/Makefile
+++ b/fs/nfs/Makefile
@@ -22,7 +22,7 @@ nfsv3-$(CONFIG_NFS_V3_ACL) += nfs3acl.o
 obj-$(CONFIG_NFS_V4) += nfsv4.o
 CFLAGS_nfs4trace.o += -I$(src)
 nfsv4-y := nfs4proc.o nfs4xdr.o nfs4state.o nfs4renewd.o nfs4super.o nfs4file.o \
-	  delegation.o idmap.o callback.o callback_xdr.o callback_proc.o \
+	  delegation.o nfs4idmap.o callback.o callback_xdr.o callback_proc.o \
 	  nfs4namespace.o nfs4getroot.o nfs4client.o nfs4session.o \
 	  dns_resolve.o nfs4trace.o
 nfsv4-$(CONFIG_NFS_USE_LEGACY_DNS) += cache_lib.o
diff --git a/fs/nfs/blocklayout/blocklayout.c b/fs/nfs/blocklayout/blocklayout.c
index 1cac3c1..d2554fe 100644
--- a/fs/nfs/blocklayout/blocklayout.c
+++ b/fs/nfs/blocklayout/blocklayout.c
@@ -890,6 +890,7 @@ static struct pnfs_layoutdriver_type blocklayout_type = {
 	.free_deviceid_node		= bl_free_deviceid_node,
 	.pg_read_ops			= &bl_pg_read_ops,
 	.pg_write_ops			= &bl_pg_write_ops,
+	.sync				= pnfs_generic_sync,
 };
 
 static int __init nfs4blocklayout_init(void)
diff --git a/fs/nfs/blocklayout/dev.c b/fs/nfs/blocklayout/dev.c
index 5aed4f9..e535599 100644
--- a/fs/nfs/blocklayout/dev.c
+++ b/fs/nfs/blocklayout/dev.c
@@ -33,7 +33,7 @@ bl_free_deviceid_node(struct nfs4_deviceid_node *d)
 		container_of(d, struct pnfs_block_dev, node);
 
 	bl_free_device(dev);
-	kfree(dev);
+	kfree_rcu(dev, node.rcu);
 }
 
 static int
diff --git a/fs/nfs/callback.c b/fs/nfs/callback.c
index 351be920..8d129bb 100644
--- a/fs/nfs/callback.c
+++ b/fs/nfs/callback.c
@@ -128,7 +128,7 @@ nfs41_callback_svc(void *vrqstp)
 		if (try_to_freeze())
 			continue;
 
-		prepare_to_wait(&serv->sv_cb_waitq, &wq, TASK_UNINTERRUPTIBLE);
+		prepare_to_wait(&serv->sv_cb_waitq, &wq, TASK_INTERRUPTIBLE);
 		spin_lock_bh(&serv->sv_cb_lock);
 		if (!list_empty(&serv->sv_cb_list)) {
 			req = list_first_entry(&serv->sv_cb_list,
@@ -142,10 +142,10 @@ nfs41_callback_svc(void *vrqstp)
 				error);
 		} else {
 			spin_unlock_bh(&serv->sv_cb_lock);
-			/* schedule_timeout to game the hung task watchdog */
-			schedule_timeout(60 * HZ);
+			schedule();
 			finish_wait(&serv->sv_cb_waitq, &wq);
 		}
+		flush_signals(current);
 	}
 	return 0;
 }
diff --git a/fs/nfs/client.c b/fs/nfs/client.c
index 1987415..892aeff 100644
--- a/fs/nfs/client.c
+++ b/fs/nfs/client.c
@@ -31,7 +31,6 @@
 #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/in6.h>
diff --git a/fs/nfs/delegation.c b/fs/nfs/delegation.c
index a6ad688..029d688 100644
--- a/fs/nfs/delegation.c
+++ b/fs/nfs/delegation.c
@@ -378,7 +378,7 @@ int nfs_inode_set_delegation(struct inode *inode, struct rpc_cred *cred, struct
 		if (freeme == NULL)
 			goto out;
 	}
-	list_add_rcu(&delegation->super_list, &server->delegations);
+	list_add_tail_rcu(&delegation->super_list, &server->delegations);
 	rcu_assign_pointer(nfsi->delegation, delegation);
 	delegation = NULL;
 
@@ -514,7 +514,7 @@ void nfs_inode_return_delegation_noreclaim(struct inode *inode)
 
 	delegation = nfs_inode_detach_delegation(inode);
 	if (delegation != NULL)
-		nfs_do_return_delegation(inode, delegation, 0);
+		nfs_do_return_delegation(inode, delegation, 1);
 }
 
 /**
diff --git a/fs/nfs/dir.c b/fs/nfs/dir.c
index 1e51ecd..b2c8b31 100644
--- a/fs/nfs/dir.c
+++ b/fs/nfs/dir.c
@@ -543,6 +543,9 @@ int nfs_readdir_page_filler(nfs_readdir_descriptor_t *desc, struct nfs_entry *en
 	if (scratch == NULL)
 		return -ENOMEM;
 
+	if (buflen == 0)
+		goto out_nopages;
+
 	xdr_init_decode_pages(&stream, &buf, xdr_pages, buflen);
 	xdr_set_scratch_buffer(&stream, page_address(scratch), PAGE_SIZE);
 
@@ -564,6 +567,7 @@ int nfs_readdir_page_filler(nfs_readdir_descriptor_t *desc, struct nfs_entry *en
 			break;
 	} while (!entry->eof);
 
+out_nopages:
 	if (count == 0 || (status == -EBADCOOKIE && entry->eof != 0)) {
 		array = nfs_readdir_get_array(page);
 		if (!IS_ERR(array)) {
diff --git a/fs/nfs/direct.c b/fs/nfs/direct.c
index b2cbc3a..38678d9 100644
--- a/fs/nfs/direct.c
+++ b/fs/nfs/direct.c
@@ -129,22 +129,25 @@ nfs_direct_good_bytes(struct nfs_direct_req *dreq, struct nfs_pgio_header *hdr)
 	int i;
 	ssize_t count;
 
-	WARN_ON_ONCE(hdr->pgio_mirror_idx >= dreq->mirror_count);
-
-	count = dreq->mirrors[hdr->pgio_mirror_idx].count;
-	if (count + dreq->io_start < hdr->io_start + hdr->good_bytes) {
-		count = hdr->io_start + hdr->good_bytes - dreq->io_start;
-		dreq->mirrors[hdr->pgio_mirror_idx].count = count;
-	}
-
-	/* update the dreq->count by finding the minimum agreed count from all
-	 * mirrors */
-	count = dreq->mirrors[0].count;
+	if (dreq->mirror_count == 1) {
+		dreq->mirrors[hdr->pgio_mirror_idx].count += hdr->good_bytes;
+		dreq->count += hdr->good_bytes;
+	} else {
+		/* mirrored writes */
+		count = dreq->mirrors[hdr->pgio_mirror_idx].count;
+		if (count + dreq->io_start < hdr->io_start + hdr->good_bytes) {
+			count = hdr->io_start + hdr->good_bytes - dreq->io_start;
+			dreq->mirrors[hdr->pgio_mirror_idx].count = count;
+		}
+		/* update the dreq->count by finding the minimum agreed count from all
+		 * mirrors */
+		count = dreq->mirrors[0].count;
 
-	for (i = 1; i < dreq->mirror_count; i++)
-		count = min(count, dreq->mirrors[i].count);
+		for (i = 1; i < dreq->mirror_count; i++)
+			count = min(count, dreq->mirrors[i].count);
 
-	dreq->count = count;
+		dreq->count = count;
+	}
 }
 
 /*
@@ -258,18 +261,11 @@ ssize_t nfs_direct_IO(struct kiocb *iocb, struct iov_iter *iter, loff_t pos)
 	if (!IS_SWAPFILE(inode))
 		return 0;
 
-#ifndef CONFIG_NFS_SWAP
-	dprintk("NFS: nfs_direct_IO (%pD) off/no(%Ld/%lu) EINVAL\n",
-			iocb->ki_filp, (long long) pos, iter->nr_segs);
-
-	return -EINVAL;
-#else
 	VM_BUG_ON(iov_iter_count(iter) != PAGE_SIZE);
 
 	if (iov_iter_rw(iter) == READ)
 		return nfs_file_direct_read(iocb, iter, pos);
 	return nfs_file_direct_write(iocb, iter);
-#endif /* CONFIG_NFS_SWAP */
 }
 
 static void nfs_direct_release_pages(struct page **pages, unsigned int npages)
@@ -1030,6 +1026,7 @@ ssize_t nfs_file_direct_write(struct kiocb *iocb, struct iov_iter *iter)
 			if (i_size_read(inode) < iocb->ki_pos)
 				i_size_write(inode, iocb->ki_pos);
 			spin_unlock(&inode->i_lock);
+			generic_write_sync(file, pos, result);
 		}
 	}
 	nfs_direct_req_release(dreq);
diff --git a/fs/nfs/file.c b/fs/nfs/file.c
index c40e436..8b8d83a 100644
--- a/fs/nfs/file.c
+++ b/fs/nfs/file.c
@@ -280,6 +280,7 @@ nfs_file_fsync(struct file *file, loff_t start, loff_t end, int datasync)
 
 	trace_nfs_fsync_enter(inode);
 
+	nfs_inode_dio_wait(inode);
 	do {
 		ret = filemap_write_and_wait_range(inode->i_mapping, start, end);
 		if (ret != 0)
@@ -782,7 +783,7 @@ do_unlk(struct file *filp, int cmd, struct file_lock *fl, int is_local)
 	 * Flush all pending writes before doing anything
 	 * with locks..
 	 */
-	nfs_sync_mapping(filp->f_mapping);
+	vfs_fsync(filp, 0);
 
 	l_ctx = nfs_get_lock_context(nfs_file_open_context(filp));
 	if (!IS_ERR(l_ctx)) {
diff --git a/fs/nfs/filelayout/filelayout.c b/fs/nfs/filelayout/filelayout.c
index 91e88a7..a46bf6d 100644
--- a/fs/nfs/filelayout/filelayout.c
+++ b/fs/nfs/filelayout/filelayout.c
@@ -258,7 +258,8 @@ filelayout_set_layoutcommit(struct nfs_pgio_header *hdr)
 	    hdr->res.verf->committed != NFS_DATA_SYNC)
 		return;
 
-	pnfs_set_layoutcommit(hdr);
+	pnfs_set_layoutcommit(hdr->inode, hdr->lseg,
+			hdr->mds_offset + hdr->res.count);
 	dprintk("%s inode %lu pls_end_pos %lu\n", __func__, hdr->inode->i_ino,
 		(unsigned long) NFS_I(hdr->inode)->layout->plh_lwb);
 }
@@ -373,7 +374,7 @@ static int filelayout_commit_done_cb(struct rpc_task *task,
 	}
 
 	if (data->verf.committed == NFS_UNSTABLE)
-		pnfs_commit_set_layoutcommit(data);
+		pnfs_set_layoutcommit(data->inode, data->lseg, data->lwb);
 
 	return 0;
 }
@@ -1086,7 +1087,7 @@ filelayout_alloc_deviceid_node(struct nfs_server *server,
 }
 
 static void
-filelayout_free_deveiceid_node(struct nfs4_deviceid_node *d)
+filelayout_free_deviceid_node(struct nfs4_deviceid_node *d)
 {
 	nfs4_fl_free_deviceid(container_of(d, struct nfs4_file_layout_dsaddr, id_node));
 }
@@ -1137,7 +1138,8 @@ static struct pnfs_layoutdriver_type filelayout_type = {
 	.read_pagelist		= filelayout_read_pagelist,
 	.write_pagelist		= filelayout_write_pagelist,
 	.alloc_deviceid_node	= filelayout_alloc_deviceid_node,
-	.free_deviceid_node	= filelayout_free_deveiceid_node,
+	.free_deviceid_node	= filelayout_free_deviceid_node,
+	.sync			= pnfs_nfs_generic_sync,
 };
 
 static int __init nfs4filelayout_init(void)
diff --git a/fs/nfs/filelayout/filelayoutdev.c b/fs/nfs/filelayout/filelayoutdev.c
index 4f372e2..4946ef4 100644
--- a/fs/nfs/filelayout/filelayoutdev.c
+++ b/fs/nfs/filelayout/filelayoutdev.c
@@ -55,7 +55,7 @@ nfs4_fl_free_deviceid(struct nfs4_file_layout_dsaddr *dsaddr)
 			nfs4_pnfs_ds_put(ds);
 	}
 	kfree(dsaddr->stripe_indices);
-	kfree(dsaddr);
+	kfree_rcu(dsaddr, id_node.rcu);
 }
 
 /* Decode opaque device data and return the result */
diff --git a/fs/nfs/flexfilelayout/flexfilelayout.c b/fs/nfs/flexfilelayout/flexfilelayout.c
index 315cc68..7d05089 100644
--- a/fs/nfs/flexfilelayout/flexfilelayout.c
+++ b/fs/nfs/flexfilelayout/flexfilelayout.c
@@ -11,10 +11,10 @@
 #include <linux/module.h>
 
 #include <linux/sunrpc/metrics.h>
-#include <linux/nfs_idmap.h>
 
 #include "flexfilelayout.h"
 #include "../nfs4session.h"
+#include "../nfs4idmap.h"
 #include "../internal.h"
 #include "../delegation.h"
 #include "../nfs4trace.h"
@@ -891,7 +891,8 @@ static int ff_layout_read_done_cb(struct rpc_task *task,
 static void
 ff_layout_set_layoutcommit(struct nfs_pgio_header *hdr)
 {
-	pnfs_set_layoutcommit(hdr);
+	pnfs_set_layoutcommit(hdr->inode, hdr->lseg,
+			hdr->mds_offset + hdr->res.count);
 	dprintk("%s inode %lu pls_end_pos %lu\n", __func__, hdr->inode->i_ino,
 		(unsigned long) NFS_I(hdr->inode)->layout->plh_lwb);
 }
@@ -1074,7 +1075,7 @@ static int ff_layout_commit_done_cb(struct rpc_task *task,
 	}
 
 	if (data->verf.committed == NFS_UNSTABLE)
-		pnfs_commit_set_layoutcommit(data);
+		pnfs_set_layoutcommit(data->inode, data->lseg, data->lwb);
 
 	return 0;
 }
@@ -1414,7 +1415,7 @@ ff_layout_get_ds_info(struct inode *inode)
 }
 
 static void
-ff_layout_free_deveiceid_node(struct nfs4_deviceid_node *d)
+ff_layout_free_deviceid_node(struct nfs4_deviceid_node *d)
 {
 	nfs4_ff_layout_free_deviceid(container_of(d, struct nfs4_ff_layout_ds,
 						  id_node));
@@ -1498,7 +1499,7 @@ static struct pnfs_layoutdriver_type flexfilelayout_type = {
 	.pg_read_ops		= &ff_layout_pg_read_ops,
 	.pg_write_ops		= &ff_layout_pg_write_ops,
 	.get_ds_info		= ff_layout_get_ds_info,
-	.free_deviceid_node	= ff_layout_free_deveiceid_node,
+	.free_deviceid_node	= ff_layout_free_deviceid_node,
 	.mark_request_commit	= pnfs_layout_mark_request_commit,
 	.clear_request_commit	= pnfs_generic_clear_request_commit,
 	.scan_commit_lists	= pnfs_generic_scan_commit_lists,
@@ -1508,6 +1509,7 @@ static struct pnfs_layoutdriver_type flexfilelayout_type = {
 	.write_pagelist		= ff_layout_write_pagelist,
 	.alloc_deviceid_node    = ff_layout_alloc_deviceid_node,
 	.encode_layoutreturn    = ff_layout_encode_layoutreturn,
+	.sync			= pnfs_nfs_generic_sync,
 };
 
 static int __init nfs4flexfilelayout_init(void)
diff --git a/fs/nfs/flexfilelayout/flexfilelayoutdev.c b/fs/nfs/flexfilelayout/flexfilelayoutdev.c
index e2c01f2..77a2d02 100644
--- a/fs/nfs/flexfilelayout/flexfilelayoutdev.c
+++ b/fs/nfs/flexfilelayout/flexfilelayoutdev.c
@@ -30,7 +30,7 @@ void nfs4_ff_layout_free_deviceid(struct nfs4_ff_layout_ds *mirror_ds)
 {
 	nfs4_print_deviceid(&mirror_ds->id_node.deviceid);
 	nfs4_pnfs_ds_put(mirror_ds->ds);
-	kfree(mirror_ds);
+	kfree_rcu(mirror_ds, id_node.rcu);
 }
 
 /* Decode opaque device data and construct new_ds using it */
diff --git a/fs/nfs/inode.c b/fs/nfs/inode.c
index 3689e95..f734562 100644
--- a/fs/nfs/inode.c
+++ b/fs/nfs/inode.c
@@ -133,6 +133,13 @@ void nfs_evict_inode(struct inode *inode)
 	nfs_clear_inode(inode);
 }
 
+int nfs_sync_inode(struct inode *inode)
+{
+	nfs_inode_dio_wait(inode);
+	return nfs_wb_all(inode);
+}
+EXPORT_SYMBOL_GPL(nfs_sync_inode);
+
 /**
  * nfs_sync_mapping - helper to flush all mmapped dirty data to disk
  */
@@ -192,7 +199,6 @@ void nfs_zap_caches(struct inode *inode)
 	nfs_zap_caches_locked(inode);
 	spin_unlock(&inode->i_lock);
 }
-EXPORT_SYMBOL_GPL(nfs_zap_caches);
 
 void nfs_zap_mapping(struct inode *inode, struct address_space *mapping)
 {
@@ -525,10 +531,8 @@ nfs_setattr(struct dentry *dentry, struct iattr *attr)
 	trace_nfs_setattr_enter(inode);
 
 	/* Write all dirty data */
-	if (S_ISREG(inode->i_mode)) {
-		nfs_inode_dio_wait(inode);
-		nfs_wb_all(inode);
-	}
+	if (S_ISREG(inode->i_mode))
+		nfs_sync_inode(inode);
 
 	fattr = nfs_alloc_fattr();
 	if (fattr == NULL)
@@ -644,8 +648,9 @@ int nfs_getattr(struct vfsmount *mnt, struct dentry *dentry, struct kstat *stat)
 	trace_nfs_getattr_enter(inode);
 	/* Flush out writes to the server in order to update c/mtime.  */
 	if (S_ISREG(inode->i_mode)) {
-		nfs_inode_dio_wait(inode);
-		err = filemap_write_and_wait(inode->i_mapping);
+		mutex_lock(&inode->i_mutex);
+		err = nfs_sync_inode(inode);
+		mutex_unlock(&inode->i_mutex);
 		if (err)
 			goto out;
 	}
@@ -1588,6 +1593,19 @@ int nfs_post_op_update_inode_force_wcc(struct inode *inode, struct nfs_fattr *fa
 }
 EXPORT_SYMBOL_GPL(nfs_post_op_update_inode_force_wcc);
 
+
+static inline bool nfs_fileid_valid(struct nfs_inode *nfsi,
+				    struct nfs_fattr *fattr)
+{
+	bool ret1 = true, ret2 = true;
+
+	if (fattr->valid & NFS_ATTR_FATTR_FILEID)
+		ret1 = (nfsi->fileid == fattr->fileid);
+	if (fattr->valid & NFS_ATTR_FATTR_MOUNTED_ON_FILEID)
+		ret2 = (nfsi->fileid == fattr->mounted_on_fileid);
+	return ret1 || ret2;
+}
+
 /*
  * Many nfs protocol calls return the new file attributes after
  * an operation.  Here we update the inode to reflect the state
@@ -1614,7 +1632,7 @@ static int nfs_update_inode(struct inode *inode, struct nfs_fattr *fattr)
 			nfs_display_fhandle_hash(NFS_FH(inode)),
 			atomic_read(&inode->i_count), fattr->valid);
 
-	if ((fattr->valid & NFS_ATTR_FATTR_FILEID) && nfsi->fileid != fattr->fileid) {
+	if (!nfs_fileid_valid(nfsi, fattr)) {
 		printk(KERN_ERR "NFS: server %s error: fileid changed\n"
 			"fsid %s: expected fileid 0x%Lx, got 0x%Lx\n",
 			NFS_SERVER(inode)->nfs_client->cl_hostname,
@@ -1819,7 +1837,7 @@ static int nfs_update_inode(struct inode *inode, struct nfs_fattr *fattr)
 struct inode *nfs_alloc_inode(struct super_block *sb)
 {
 	struct nfs_inode *nfsi;
-	nfsi = (struct nfs_inode *)kmem_cache_alloc(nfs_inode_cachep, GFP_KERNEL);
+	nfsi = kmem_cache_alloc(nfs_inode_cachep, GFP_KERNEL);
 	if (!nfsi)
 		return NULL;
 	nfsi->flags = 0UL;
diff --git a/fs/nfs/nfs42proc.c b/fs/nfs/nfs42proc.c
index cb17072..3a9e752 100644
--- a/fs/nfs/nfs42proc.c
+++ b/fs/nfs/nfs42proc.c
@@ -36,13 +36,16 @@ static int _nfs42_proc_fallocate(struct rpc_message *msg, struct file *filep,
 				 loff_t offset, loff_t len)
 {
 	struct inode *inode = file_inode(filep);
+	struct nfs_server *server = NFS_SERVER(inode);
 	struct nfs42_falloc_args args = {
 		.falloc_fh	= NFS_FH(inode),
 		.falloc_offset	= offset,
 		.falloc_length	= len,
+		.falloc_bitmask	= server->cache_consistency_bitmask,
+	};
+	struct nfs42_falloc_res res = {
+		.falloc_server	= server,
 	};
-	struct nfs42_falloc_res res;
-	struct nfs_server *server = NFS_SERVER(inode);
 	int status;
 
 	msg->rpc_argp = &args;
@@ -52,8 +55,17 @@ static int _nfs42_proc_fallocate(struct rpc_message *msg, struct file *filep,
 	if (status)
 		return status;
 
-	return nfs4_call_sync(server->client, server, msg,
-			      &args.seq_args, &res.seq_res, 0);
+	res.falloc_fattr = nfs_alloc_fattr();
+	if (!res.falloc_fattr)
+		return -ENOMEM;
+
+	status = nfs4_call_sync(server->client, server, msg,
+				&args.seq_args, &res.seq_res, 0);
+	if (status == 0)
+		status = nfs_post_op_update_inode(inode, res.falloc_fattr);
+
+	kfree(res.falloc_fattr);
+	return status;
 }
 
 static int nfs42_proc_fallocate(struct rpc_message *msg, struct file *filep,
@@ -84,9 +96,13 @@ int nfs42_proc_allocate(struct file *filep, loff_t offset, loff_t len)
 	if (!nfs_server_capable(inode, NFS_CAP_ALLOCATE))
 		return -EOPNOTSUPP;
 
+	mutex_lock(&inode->i_mutex);
+
 	err = nfs42_proc_fallocate(&msg, filep, offset, len);
 	if (err == -EOPNOTSUPP)
 		NFS_SERVER(inode)->caps &= ~NFS_CAP_ALLOCATE;
+
+	mutex_unlock(&inode->i_mutex);
 	return err;
 }
 
@@ -101,9 +117,16 @@ int nfs42_proc_deallocate(struct file *filep, loff_t offset, loff_t len)
 	if (!nfs_server_capable(inode, NFS_CAP_DEALLOCATE))
 		return -EOPNOTSUPP;
 
+	nfs_wb_all(inode);
+	mutex_lock(&inode->i_mutex);
+
 	err = nfs42_proc_fallocate(&msg, filep, offset, len);
+	if (err == 0)
+		truncate_pagecache_range(inode, offset, (offset + len) -1);
 	if (err == -EOPNOTSUPP)
 		NFS_SERVER(inode)->caps &= ~NFS_CAP_DEALLOCATE;
+
+	mutex_unlock(&inode->i_mutex);
 	return err;
 }
 
diff --git a/fs/nfs/nfs42xdr.c b/fs/nfs/nfs42xdr.c
index 038a7e15..1a25b27 100644
--- a/fs/nfs/nfs42xdr.c
+++ b/fs/nfs/nfs42xdr.c
@@ -25,16 +25,20 @@
 
 #define NFS4_enc_allocate_sz		(compound_encode_hdr_maxsz + \
 					 encode_putfh_maxsz + \
-					 encode_allocate_maxsz)
+					 encode_allocate_maxsz + \
+					 encode_getattr_maxsz)
 #define NFS4_dec_allocate_sz		(compound_decode_hdr_maxsz + \
 					 decode_putfh_maxsz + \
-					 decode_allocate_maxsz)
+					 decode_allocate_maxsz + \
+					 decode_getattr_maxsz)
 #define NFS4_enc_deallocate_sz		(compound_encode_hdr_maxsz + \
 					 encode_putfh_maxsz + \
-					 encode_deallocate_maxsz)
+					 encode_deallocate_maxsz + \
+					 encode_getattr_maxsz)
 #define NFS4_dec_deallocate_sz		(compound_decode_hdr_maxsz + \
 					 decode_putfh_maxsz + \
-					 decode_deallocate_maxsz)
+					 decode_deallocate_maxsz + \
+					 decode_getattr_maxsz)
 #define NFS4_enc_seek_sz		(compound_encode_hdr_maxsz + \
 					 encode_putfh_maxsz + \
 					 encode_seek_maxsz)
@@ -92,6 +96,7 @@ static void nfs4_xdr_enc_allocate(struct rpc_rqst *req,
 	encode_sequence(xdr, &args->seq_args, &hdr);
 	encode_putfh(xdr, args->falloc_fh, &hdr);
 	encode_allocate(xdr, args, &hdr);
+	encode_getfattr(xdr, args->falloc_bitmask, &hdr);
 	encode_nops(&hdr);
 }
 
@@ -110,6 +115,7 @@ static void nfs4_xdr_enc_deallocate(struct rpc_rqst *req,
 	encode_sequence(xdr, &args->seq_args, &hdr);
 	encode_putfh(xdr, args->falloc_fh, &hdr);
 	encode_deallocate(xdr, args, &hdr);
+	encode_getfattr(xdr, args->falloc_bitmask, &hdr);
 	encode_nops(&hdr);
 }
 
@@ -183,6 +189,9 @@ static int nfs4_xdr_dec_allocate(struct rpc_rqst *rqstp,
 	if (status)
 		goto out;
 	status = decode_allocate(xdr, res);
+	if (status)
+		goto out;
+	decode_getfattr(xdr, res->falloc_fattr, res->falloc_server);
 out:
 	return status;
 }
@@ -207,6 +216,9 @@ static int nfs4_xdr_dec_deallocate(struct rpc_rqst *rqstp,
 	if (status)
 		goto out;
 	status = decode_deallocate(xdr, res);
+	if (status)
+		goto out;
+	decode_getfattr(xdr, res->falloc_fattr, res->falloc_server);
 out:
 	return status;
 }
diff --git a/fs/nfs/nfs4client.c b/fs/nfs/nfs4client.c
index 51c2dbd..e42be52 100644
--- a/fs/nfs/nfs4client.c
+++ b/fs/nfs/nfs4client.c
@@ -4,7 +4,6 @@
  */
 #include <linux/module.h>
 #include <linux/nfs_fs.h>
-#include <linux/nfs_idmap.h>
 #include <linux/nfs_mount.h>
 #include <linux/sunrpc/addr.h>
 #include <linux/sunrpc/auth.h>
@@ -15,6 +14,7 @@
 #include "callback.h"
 #include "delegation.h"
 #include "nfs4session.h"
+#include "nfs4idmap.h"
 #include "pnfs.h"
 #include "netns.h"
 
diff --git a/fs/nfs/nfs4file.c b/fs/nfs/nfs4file.c
index 619eca3..f58c17b 100644
--- a/fs/nfs/nfs4file.c
+++ b/fs/nfs/nfs4file.c
@@ -10,6 +10,8 @@
 #include "fscache.h"
 #include "pnfs.h"
 
+#include "nfstrace.h"
+
 #ifdef CONFIG_NFS_V4_2
 #include "nfs42.h"
 #endif
@@ -57,7 +59,7 @@ nfs4_file_open(struct inode *inode, struct file *filp)
 	if (openflags & O_TRUNC) {
 		attr.ia_valid |= ATTR_SIZE;
 		attr.ia_size = 0;
-		nfs_wb_all(inode);
+		nfs_sync_inode(inode);
 	}
 
 	inode = NFS_PROTO(dir)->open_context(dir, ctx, openflags, &attr, &opened);
@@ -100,6 +102,9 @@ nfs4_file_fsync(struct file *file, loff_t start, loff_t end, int datasync)
 	int ret;
 	struct inode *inode = file_inode(file);
 
+	trace_nfs_fsync_enter(inode);
+
+	nfs_inode_dio_wait(inode);
 	do {
 		ret = filemap_write_and_wait_range(inode->i_mapping, start, end);
 		if (ret != 0)
@@ -107,7 +112,7 @@ nfs4_file_fsync(struct file *file, loff_t start, loff_t end, int datasync)
 		mutex_lock(&inode->i_mutex);
 		ret = nfs_file_fsync_commit(file, start, end, datasync);
 		if (!ret)
-			ret = pnfs_layoutcommit_inode(inode, true);
+			ret = pnfs_sync_inode(inode, !!datasync);
 		mutex_unlock(&inode->i_mutex);
 		/*
 		 * If nfs_file_fsync_commit detected a server reboot, then
@@ -118,6 +123,7 @@ nfs4_file_fsync(struct file *file, loff_t start, loff_t end, int datasync)
 		end = LLONG_MAX;
 	} while (ret == -EAGAIN);
 
+	trace_nfs_fsync_exit(inode, ret);
 	return ret;
 }
 
@@ -152,15 +158,9 @@ static long nfs42_fallocate(struct file *filep, int mode, loff_t offset, loff_t
 	if (ret < 0)
 		return ret;
 
-	mutex_lock(&inode->i_mutex);
 	if (mode & FALLOC_FL_PUNCH_HOLE)
-		ret = nfs42_proc_deallocate(filep, offset, len);
-	else
-		ret = nfs42_proc_allocate(filep, offset, len);
-	mutex_unlock(&inode->i_mutex);
-
-	nfs_zap_caches(inode);
-	return ret;
+		return nfs42_proc_deallocate(filep, offset, len);
+	return nfs42_proc_allocate(filep, offset, len);
 }
 #endif /* CONFIG_NFS_V4_2 */
 
diff --git a/fs/nfs/idmap.c b/fs/nfs/nfs4idmap.c
index 857e2a9..2e1737c 100644
--- a/fs/nfs/idmap.c
+++ b/fs/nfs/nfs4idmap.c
@@ -36,7 +36,6 @@
 #include <linux/types.h>
 #include <linux/parser.h>
 #include <linux/fs.h>
-#include <linux/nfs_idmap.h>
 #include <net/net_namespace.h>
 #include <linux/sunrpc/rpc_pipe_fs.h>
 #include <linux/nfs_fs.h>
@@ -49,6 +48,7 @@
 
 #include "internal.h"
 #include "netns.h"
+#include "nfs4idmap.h"
 #include "nfs4trace.h"
 
 #define NFS_UINT_MAXLEN 11
diff --git a/fs/nfs/nfs4idmap.h b/fs/nfs/nfs4idmap.h
new file mode 100644
index 0000000..de44d73
--- /dev/null
+++ b/fs/nfs/nfs4idmap.h
@@ -0,0 +1,68 @@
+/*
+ * fs/nfs/nfs4idmap.h
+ *
+ *  UID and GID to name mapping for clients.
+ *
+ *  Copyright (c) 2002 The Regents of the University of Michigan.
+ *  All rights reserved.
+ *
+ *  Marius Aamodt Eriksen <marius@umich.edu>
+ *
+ *  Redistribution and use in source and binary forms, with or without
+ *  modification, are permitted provided that the following conditions
+ *  are met:
+ *
+ *  1. Redistributions of source code must retain the above copyright
+ *     notice, this list of conditions and the following disclaimer.
+ *  2. Redistributions in binary form must reproduce the above copyright
+ *     notice, this list of conditions and the following disclaimer in the
+ *     documentation and/or other materials provided with the distribution.
+ *  3. Neither the name of the University nor the names of its
+ *     contributors may be used to endorse or promote products derived
+ *     from this software without specific prior written permission.
+ *
+ *  THIS SOFTWARE IS PROVIDED ``AS IS'' AND ANY EXPRESS OR IMPLIED
+ *  WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES OF
+ *  MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
+ *  DISCLAIMED. IN NO EVENT SHALL THE REGENTS OR CONTRIBUTORS BE LIABLE
+ *  FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
+ *  CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
+ *  SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR
+ *  BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF
+ *  LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING
+ *  NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS
+ *  SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+ */
+#ifndef NFS_IDMAP_H
+#define NFS_IDMAP_H
+
+#include <linux/uidgid.h>
+#include <uapi/linux/nfs_idmap.h>
+
+
+/* Forward declaration to make this header independent of others */
+struct nfs_client;
+struct nfs_server;
+struct nfs_fattr;
+struct nfs4_string;
+
+int nfs_idmap_init(void);
+void nfs_idmap_quit(void);
+int nfs_idmap_new(struct nfs_client *);
+void nfs_idmap_delete(struct nfs_client *);
+
+void nfs_fattr_init_names(struct nfs_fattr *fattr,
+		struct nfs4_string *owner_name,
+		struct nfs4_string *group_name);
+void nfs_fattr_free_names(struct nfs_fattr *);
+void nfs_fattr_map_and_free_names(struct nfs_server *, struct nfs_fattr *);
+
+int nfs_map_name_to_uid(const struct nfs_server *, const char *, size_t, kuid_t *);
+int nfs_map_group_to_gid(const struct nfs_server *, const char *, size_t, kgid_t *);
+int nfs_map_uid_to_name(const struct nfs_server *, kuid_t, char *, size_t);
+int nfs_map_gid_to_group(const struct nfs_server *, kgid_t, char *, size_t);
+
+int nfs_map_string_to_numeric(const char *name, size_t namelen, __u32 *res);
+
+extern unsigned int nfs_idmap_cache_timeout;
+#endif /* NFS_IDMAP_H */
diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c
index 98e533f..45b35b9 100644
--- a/fs/nfs/nfs4proc.c
+++ b/fs/nfs/nfs4proc.c
@@ -51,7 +51,6 @@
 #include <linux/namei.h>
 #include <linux/mount.h>
 #include <linux/module.h>
-#include <linux/nfs_idmap.h>
 #include <linux/xattr.h>
 #include <linux/utsname.h>
 #include <linux/freezer.h>
@@ -63,6 +62,7 @@
 #include "callback.h"
 #include "pnfs.h"
 #include "netns.h"
+#include "nfs4idmap.h"
 #include "nfs4session.h"
 #include "fscache.h"
 
@@ -185,7 +185,8 @@ const u32 nfs4_fattr_bitmap[3] = {
 	| FATTR4_WORD1_SPACE_USED
 	| FATTR4_WORD1_TIME_ACCESS
 	| FATTR4_WORD1_TIME_METADATA
-	| FATTR4_WORD1_TIME_MODIFY,
+	| FATTR4_WORD1_TIME_MODIFY
+	| FATTR4_WORD1_MOUNTED_ON_FILEID,
 #ifdef CONFIG_NFS_V4_SECURITY_LABEL
 	FATTR4_WORD2_SECURITY_LABEL
 #endif
@@ -3095,16 +3096,13 @@ int nfs4_proc_get_rootfh(struct nfs_server *server, struct nfs_fh *fhandle,
 			 struct nfs_fsinfo *info,
 			 bool auth_probe)
 {
-	int status;
+	int status = 0;
 
-	switch (auth_probe) {
-	case false:
+	if (!auth_probe)
 		status = nfs4_lookup_root(server, fhandle, info);
-		if (status != -NFS4ERR_WRONGSEC)
-			break;
-	default:
+
+	if (auth_probe || status == NFS4ERR_WRONGSEC)
 		status = nfs4_do_find_root_sec(server, fhandle, info);
-	}
 
 	if (status == 0)
 		status = nfs4_server_capabilities(server, fhandle);
@@ -7944,6 +7942,8 @@ _nfs4_proc_getdeviceinfo(struct nfs_server *server,
 {
 	struct nfs4_getdeviceinfo_args args = {
 		.pdev = pdev,
+		.notify_types = NOTIFY_DEVICEID4_CHANGE |
+			NOTIFY_DEVICEID4_DELETE,
 	};
 	struct nfs4_getdeviceinfo_res res = {
 		.pdev = pdev,
@@ -7958,6 +7958,11 @@ _nfs4_proc_getdeviceinfo(struct nfs_server *server,
 
 	dprintk("--> %s\n", __func__);
 	status = nfs4_call_sync(server->client, server, &msg, &args.seq_args, &res.seq_res, 0);
+	if (res.notification & ~args.notify_types)
+		dprintk("%s: unsupported notification\n", __func__);
+	if (res.notification != args.notify_types)
+		pdev->nocache = 1;
+
 	dprintk("<-- %s status=%d\n", __func__, status);
 
 	return status;
diff --git a/fs/nfs/nfs4state.c b/fs/nfs/nfs4state.c
index 3b2b205..2782cfc 100644
--- a/fs/nfs/nfs4state.c
+++ b/fs/nfs/nfs4state.c
@@ -42,7 +42,6 @@
 #include <linux/slab.h>
 #include <linux/fs.h>
 #include <linux/nfs_fs.h>
-#include <linux/nfs_idmap.h>
 #include <linux/kthread.h>
 #include <linux/module.h>
 #include <linux/random.h>
@@ -57,6 +56,7 @@
 #include "callback.h"
 #include "delegation.h"
 #include "internal.h"
+#include "nfs4idmap.h"
 #include "nfs4session.h"
 #include "pnfs.h"
 #include "netns.h"
diff --git a/fs/nfs/nfs4super.c b/fs/nfs/nfs4super.c
index 75090fe..6fb7cb6 100644
--- a/fs/nfs/nfs4super.c
+++ b/fs/nfs/nfs4super.c
@@ -3,12 +3,12 @@
  */
 #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 "nfs4idmap.h"
 #include "dns_resolve.h"
 #include "pnfs.h"
 #include "nfs.h"
@@ -91,10 +91,11 @@ static void nfs4_evict_inode(struct inode *inode)
 {
 	truncate_inode_pages_final(&inode->i_data);
 	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);
+	/* Note that above delegreturn would trigger pnfs return-on-close */
+	pnfs_return_layout(inode);
+	pnfs_destroy_layout(NFS_I(inode));
 	/* First call standard NFS clear_inode() code */
 	nfs_clear_inode(inode);
 }
diff --git a/fs/nfs/nfs4sysctl.c b/fs/nfs/nfs4sysctl.c
index b6ebe7e..0fbd3ab 100644
--- a/fs/nfs/nfs4sysctl.c
+++ b/fs/nfs/nfs4sysctl.c
@@ -6,10 +6,10 @@
  * 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 "nfs4idmap.h"
 #include "callback.h"
 
 static const int nfs_set_port_min = 0;
diff --git a/fs/nfs/nfs4xdr.c b/fs/nfs/nfs4xdr.c
index 5c399ec..0aea978 100644
--- a/fs/nfs/nfs4xdr.c
+++ b/fs/nfs/nfs4xdr.c
@@ -52,10 +52,10 @@
 #include <linux/nfs.h>
 #include <linux/nfs4.h>
 #include <linux/nfs_fs.h>
-#include <linux/nfs_idmap.h>
 
 #include "nfs4_fs.h"
 #include "internal.h"
+#include "nfs4idmap.h"
 #include "nfs4session.h"
 #include "pnfs.h"
 #include "netns.h"
@@ -1920,7 +1920,7 @@ encode_getdeviceinfo(struct xdr_stream *xdr,
 
 	p = reserve_space(xdr, 4 + 4);
 	*p++ = cpu_to_be32(1);			/* bitmap length */
-	*p++ = cpu_to_be32(NOTIFY_DEVICEID4_CHANGE | NOTIFY_DEVICEID4_DELETE);
+	*p++ = cpu_to_be32(args->notify_types);
 }
 
 static void
@@ -5753,8 +5753,9 @@ out_overflow:
 
 #if defined(CONFIG_NFS_V4_1)
 static int decode_getdeviceinfo(struct xdr_stream *xdr,
-				struct pnfs_device *pdev)
+				struct nfs4_getdeviceinfo_res *res)
 {
+	struct pnfs_device *pdev = res->pdev;
 	__be32 *p;
 	uint32_t len, type;
 	int status;
@@ -5802,12 +5803,7 @@ static int decode_getdeviceinfo(struct xdr_stream *xdr,
 		if (unlikely(!p))
 			goto out_overflow;
 
-		if (be32_to_cpup(p++) &
-		    ~(NOTIFY_DEVICEID4_CHANGE | NOTIFY_DEVICEID4_DELETE)) {
-			dprintk("%s: unsupported notification\n",
-				__func__);
-		}
-
+		res->notification = be32_to_cpup(p++);
 		for (i = 1; i < len; i++) {
 			if (be32_to_cpup(p++)) {
 				dprintk("%s: unsupported notification\n",
@@ -7061,7 +7057,7 @@ static int nfs4_xdr_dec_getdeviceinfo(struct rpc_rqst *rqstp,
 	status = decode_sequence(xdr, &res->seq_res, rqstp);
 	if (status != 0)
 		goto out;
-	status = decode_getdeviceinfo(xdr, res->pdev);
+	status = decode_getdeviceinfo(xdr, res);
 out:
 	return status;
 }
@@ -7365,6 +7361,11 @@ nfs4_stat_to_errno(int stat)
 	.p_name   = #proc,					\
 }
 
+#define STUB(proc)		\
+[NFSPROC4_CLNT_##proc] = {	\
+	.p_name = #proc,	\
+}
+
 struct rpc_procinfo	nfs4_procedures[] = {
 	PROC(READ,		enc_read,		dec_read),
 	PROC(WRITE,		enc_write,		dec_write),
@@ -7417,6 +7418,7 @@ struct rpc_procinfo	nfs4_procedures[] = {
 	PROC(SECINFO_NO_NAME,	enc_secinfo_no_name,	dec_secinfo_no_name),
 	PROC(TEST_STATEID,	enc_test_stateid,	dec_test_stateid),
 	PROC(FREE_STATEID,	enc_free_stateid,	dec_free_stateid),
+	STUB(GETDEVICELIST),
 	PROC(BIND_CONN_TO_SESSION,
 			enc_bind_conn_to_session, dec_bind_conn_to_session),
 	PROC(DESTROY_CLIENTID,	enc_destroy_clientid,	dec_destroy_clientid),
diff --git a/fs/nfs/nfstrace.c b/fs/nfs/nfstrace.c
index 4eb0aea..c74f7af 100644
--- a/fs/nfs/nfstrace.c
+++ b/fs/nfs/nfstrace.c
@@ -7,3 +7,6 @@
 
 #define CREATE_TRACE_POINTS
 #include "nfstrace.h"
+
+EXPORT_TRACEPOINT_SYMBOL_GPL(nfs_fsync_enter);
+EXPORT_TRACEPOINT_SYMBOL_GPL(nfs_fsync_exit);
diff --git a/fs/nfs/objlayout/objio_osd.c b/fs/nfs/objlayout/objio_osd.c
index 24e1d74..5aaed36 100644
--- a/fs/nfs/objlayout/objio_osd.c
+++ b/fs/nfs/objlayout/objio_osd.c
@@ -57,7 +57,7 @@ objio_free_deviceid_node(struct nfs4_deviceid_node *d)
 
 	dprintk("%s: free od=%p\n", __func__, de->od.od);
 	osduld_put_device(de->od.od);
-	kfree(de);
+	kfree_rcu(d, rcu);
 }
 
 struct objio_segment {
@@ -637,6 +637,8 @@ static struct pnfs_layoutdriver_type objlayout_type = {
 	.pg_read_ops             = &objio_pg_read_ops,
 	.pg_write_ops            = &objio_pg_write_ops,
 
+	.sync			 = pnfs_generic_sync,
+
 	.free_deviceid_node	 = objio_free_deviceid_node,
 
 	.encode_layoutcommit	 = objlayout_encode_layoutcommit,
diff --git a/fs/nfs/pnfs.c b/fs/nfs/pnfs.c
index 4f802b0..2306062 100644
--- a/fs/nfs/pnfs.c
+++ b/fs/nfs/pnfs.c
@@ -1090,6 +1090,7 @@ bool pnfs_roc(struct inode *ino)
 	pnfs_get_layout_hdr(lo); /* matched in pnfs_roc_release */
 	spin_unlock(&ino->i_lock);
 	pnfs_free_lseg_list(&tmp_list);
+	pnfs_layoutcommit_inode(ino, true);
 	return true;
 
 out_noroc:
@@ -1104,8 +1105,10 @@ out_noroc:
 		}
 	}
 	spin_unlock(&ino->i_lock);
-	if (layoutreturn)
+	if (layoutreturn) {
+		pnfs_layoutcommit_inode(ino, true);
 		pnfs_send_layoutreturn(lo, stateid, IOMODE_ANY, true);
+	}
 	return false;
 }
 
@@ -1841,7 +1844,8 @@ void pnfs_ld_write_done(struct nfs_pgio_header *hdr)
 {
 	trace_nfs4_pnfs_write(hdr, hdr->pnfs_error);
 	if (!hdr->pnfs_error) {
-		pnfs_set_layoutcommit(hdr);
+		pnfs_set_layoutcommit(hdr->inode, hdr->lseg,
+				hdr->mds_offset + hdr->res.count);
 		hdr->mds_ops->rpc_call_done(&hdr->task, hdr);
 	} else
 		pnfs_ld_handle_write_error(hdr);
@@ -1902,7 +1906,6 @@ static void pnfs_writehdr_free(struct nfs_pgio_header *hdr)
 	pnfs_put_lseg(hdr->lseg);
 	nfs_pgio_header_free(hdr);
 }
-EXPORT_SYMBOL_GPL(pnfs_writehdr_free);
 
 int
 pnfs_generic_pg_writepages(struct nfs_pageio_descriptor *desc)
@@ -2032,7 +2035,6 @@ static void pnfs_readhdr_free(struct nfs_pgio_header *hdr)
 	pnfs_put_lseg(hdr->lseg);
 	nfs_pgio_header_free(hdr);
 }
-EXPORT_SYMBOL_GPL(pnfs_readhdr_free);
 
 int
 pnfs_generic_pg_readpages(struct nfs_pageio_descriptor *desc)
@@ -2099,64 +2101,34 @@ void pnfs_set_lo_fail(struct pnfs_layout_segment *lseg)
 EXPORT_SYMBOL_GPL(pnfs_set_lo_fail);
 
 void
-pnfs_set_layoutcommit(struct nfs_pgio_header *hdr)
+pnfs_set_layoutcommit(struct inode *inode, struct pnfs_layout_segment *lseg,
+		loff_t end_pos)
 {
-	struct inode *inode = hdr->inode;
 	struct nfs_inode *nfsi = NFS_I(inode);
-	loff_t end_pos = hdr->mds_offset + hdr->res.count;
 	bool mark_as_dirty = false;
 
 	spin_lock(&inode->i_lock);
 	if (!test_and_set_bit(NFS_INO_LAYOUTCOMMIT, &nfsi->flags)) {
-		mark_as_dirty = true;
-		dprintk("%s: Set layoutcommit for inode %lu ",
-			__func__, inode->i_ino);
-	}
-	if (!test_and_set_bit(NFS_LSEG_LAYOUTCOMMIT, &hdr->lseg->pls_flags)) {
-		/* references matched in nfs4_layoutcommit_release */
-		pnfs_get_lseg(hdr->lseg);
-	}
-	if (end_pos > nfsi->layout->plh_lwb)
 		nfsi->layout->plh_lwb = end_pos;
-	spin_unlock(&inode->i_lock);
-	dprintk("%s: lseg %p end_pos %llu\n",
-		__func__, hdr->lseg, nfsi->layout->plh_lwb);
-
-	/* if pnfs_layoutcommit_inode() runs between inode locks, the next one
-	 * will be a noop because NFS_INO_LAYOUTCOMMIT will not be set */
-	if (mark_as_dirty)
-		mark_inode_dirty_sync(inode);
-}
-EXPORT_SYMBOL_GPL(pnfs_set_layoutcommit);
-
-void pnfs_commit_set_layoutcommit(struct nfs_commit_data *data)
-{
-	struct inode *inode = data->inode;
-	struct nfs_inode *nfsi = NFS_I(inode);
-	bool mark_as_dirty = false;
-
-	spin_lock(&inode->i_lock);
-	if (!test_and_set_bit(NFS_INO_LAYOUTCOMMIT, &nfsi->flags)) {
 		mark_as_dirty = true;
 		dprintk("%s: Set layoutcommit for inode %lu ",
 			__func__, inode->i_ino);
-	}
-	if (!test_and_set_bit(NFS_LSEG_LAYOUTCOMMIT, &data->lseg->pls_flags)) {
+	} else if (end_pos > nfsi->layout->plh_lwb)
+		nfsi->layout->plh_lwb = end_pos;
+	if (!test_and_set_bit(NFS_LSEG_LAYOUTCOMMIT, &lseg->pls_flags)) {
 		/* references matched in nfs4_layoutcommit_release */
-		pnfs_get_lseg(data->lseg);
+		pnfs_get_lseg(lseg);
 	}
-	if (data->lwb > nfsi->layout->plh_lwb)
-		nfsi->layout->plh_lwb = data->lwb;
 	spin_unlock(&inode->i_lock);
 	dprintk("%s: lseg %p end_pos %llu\n",
-		__func__, data->lseg, nfsi->layout->plh_lwb);
+		__func__, lseg, nfsi->layout->plh_lwb);
 
 	/* if pnfs_layoutcommit_inode() runs between inode locks, the next one
 	 * will be a noop because NFS_INO_LAYOUTCOMMIT will not be set */
 	if (mark_as_dirty)
 		mark_inode_dirty_sync(inode);
 }
-EXPORT_SYMBOL_GPL(pnfs_commit_set_layoutcommit);
+EXPORT_SYMBOL_GPL(pnfs_set_layoutcommit);
 
 void pnfs_cleanup_layoutcommit(struct nfs4_layoutcommit_data *data)
 {
@@ -2216,7 +2188,6 @@ pnfs_layoutcommit_inode(struct inode *inode, bool sync)
 	pnfs_list_write_lseg(inode, &data->lseg_list);
 
 	end_pos = nfsi->layout->plh_lwb;
-	nfsi->layout->plh_lwb = 0;
 
 	nfs4_stateid_copy(&data->args.stateid, &nfsi->layout->plh_stateid);
 	spin_unlock(&inode->i_lock);
@@ -2233,11 +2204,11 @@ pnfs_layoutcommit_inode(struct inode *inode, bool sync)
 		status = ld->prepare_layoutcommit(&data->args);
 		if (status) {
 			spin_lock(&inode->i_lock);
-			if (end_pos < nfsi->layout->plh_lwb)
+			set_bit(NFS_INO_LAYOUTCOMMIT, &nfsi->flags);
+			if (end_pos > nfsi->layout->plh_lwb)
 				nfsi->layout->plh_lwb = end_pos;
 			spin_unlock(&inode->i_lock);
 			put_rpccred(data->cred);
-			set_bit(NFS_INO_LAYOUTCOMMIT, &nfsi->flags);
 			goto clear_layoutcommitting;
 		}
 	}
@@ -2258,6 +2229,13 @@ clear_layoutcommitting:
 }
 EXPORT_SYMBOL_GPL(pnfs_layoutcommit_inode);
 
+int
+pnfs_generic_sync(struct inode *inode, bool datasync)
+{
+	return pnfs_layoutcommit_inode(inode, true);
+}
+EXPORT_SYMBOL_GPL(pnfs_generic_sync);
+
 struct nfs4_threshold *pnfs_mdsthreshold_alloc(void)
 {
 	struct nfs4_threshold *thp;
diff --git a/fs/nfs/pnfs.h b/fs/nfs/pnfs.h
index 084c914..1e6308f 100644
--- a/fs/nfs/pnfs.h
+++ b/fs/nfs/pnfs.h
@@ -155,6 +155,8 @@ struct pnfs_layoutdriver_type {
 			       int how,
 			       struct nfs_commit_info *cinfo);
 
+	int (*sync)(struct inode *inode, bool datasync);
+
 	/*
 	 * Return PNFS_ATTEMPTED to indicate the layout code has attempted
 	 * I/O, else return PNFS_NOT_ATTEMPTED to fall back to normal NFS
@@ -203,6 +205,7 @@ struct pnfs_device {
 	struct page **pages;
 	unsigned int  pgbase;
 	unsigned int  pglen;	/* reply buffer length */
+	unsigned char nocache : 1;/* May not be cached */
 };
 
 #define NFS4_PNFS_GETDEVLIST_MAXNUM 16
@@ -263,10 +266,11 @@ 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, struct rpc_task *task);
-void pnfs_set_layoutcommit(struct nfs_pgio_header *);
-void pnfs_commit_set_layoutcommit(struct nfs_commit_data *data);
+void pnfs_set_layoutcommit(struct inode *, struct pnfs_layout_segment *, loff_t);
 void pnfs_cleanup_layoutcommit(struct nfs4_layoutcommit_data *data);
 int pnfs_layoutcommit_inode(struct inode *inode, bool sync);
+int pnfs_generic_sync(struct inode *inode, bool datasync);
+int pnfs_nfs_generic_sync(struct inode *inode, bool datasync);
 int _pnfs_return_layout(struct inode *);
 int pnfs_commit_and_return_layout(struct inode *);
 void pnfs_ld_write_done(struct nfs_pgio_header *);
@@ -291,6 +295,7 @@ void pnfs_error_mark_layout_for_return(struct inode *inode,
 enum {
 	NFS_DEVICEID_INVALID = 0,       /* set when MDS clientid recalled */
 	NFS_DEVICEID_UNAVAILABLE,	/* device temporarily unavailable */
+	NFS_DEVICEID_NOCACHE,		/* device may not be cached */
 };
 
 /* pnfs_dev.c */
@@ -302,6 +307,7 @@ struct nfs4_deviceid_node {
 	unsigned long 			flags;
 	unsigned long			timestamp_unavailable;
 	struct nfs4_deviceid		deviceid;
+	struct rcu_head			rcu;
 	atomic_t			ref;
 };
 
@@ -486,6 +492,14 @@ pnfs_ld_read_whole_page(struct inode *inode)
 	return NFS_SERVER(inode)->pnfs_curr_ld->flags & PNFS_READ_WHOLE_PAGE;
 }
 
+static inline int
+pnfs_sync_inode(struct inode *inode, bool datasync)
+{
+	if (!pnfs_enabled_sb(NFS_SERVER(inode)))
+		return 0;
+	return NFS_SERVER(inode)->pnfs_curr_ld->sync(inode, datasync);
+}
+
 static inline bool
 pnfs_layoutcommit_outstanding(struct inode *inode)
 {
@@ -568,6 +582,12 @@ pnfs_ld_read_whole_page(struct inode *inode)
 	return false;
 }
 
+static inline int
+pnfs_sync_inode(struct inode *inode, bool datasync)
+{
+	return 0;
+}
+
 static inline bool
 pnfs_roc(struct inode *ino)
 {
diff --git a/fs/nfs/pnfs_dev.c b/fs/nfs/pnfs_dev.c
index aa2ec00..2961fcd 100644
--- a/fs/nfs/pnfs_dev.c
+++ b/fs/nfs/pnfs_dev.c
@@ -149,6 +149,8 @@ nfs4_get_device_info(struct nfs_server *server,
 	 */
 	d = server->pnfs_curr_ld->alloc_deviceid_node(server, pdev,
 			gfp_flags);
+	if (d && pdev->nocache)
+		set_bit(NFS_DEVICEID_NOCACHE, &d->flags);
 
 out_free_pages:
 	for (i = 0; i < max_pages; i++)
@@ -175,8 +177,8 @@ __nfs4_find_get_deviceid(struct nfs_server *server,
 	rcu_read_lock();
 	d = _lookup_deviceid(server->pnfs_curr_ld, server->nfs_client, id,
 			hash);
-	if (d != NULL)
-		atomic_inc(&d->ref);
+	if (d != NULL && !atomic_inc_not_zero(&d->ref))
+		d = NULL;
 	rcu_read_unlock();
 	return d;
 }
@@ -235,12 +237,11 @@ nfs4_delete_deviceid(const struct pnfs_layoutdriver_type *ld,
 		return;
 	}
 	hlist_del_init_rcu(&d->node);
+	clear_bit(NFS_DEVICEID_NOCACHE, &d->flags);
 	spin_unlock(&nfs4_deviceid_lock);
-	synchronize_rcu();
 
 	/* balance the initial ref set in pnfs_insert_deviceid */
-	if (atomic_dec_and_test(&d->ref))
-		d->ld->free_deviceid_node(d);
+	nfs4_put_deviceid_node(d);
 }
 EXPORT_SYMBOL_GPL(nfs4_delete_deviceid);
 
@@ -271,6 +272,11 @@ EXPORT_SYMBOL_GPL(nfs4_init_deviceid_node);
 bool
 nfs4_put_deviceid_node(struct nfs4_deviceid_node *d)
 {
+	if (test_bit(NFS_DEVICEID_NOCACHE, &d->flags)) {
+		if (atomic_add_unless(&d->ref, -1, 2))
+			return false;
+		nfs4_delete_deviceid(d->ld, d->nfs_client, &d->deviceid);
+	}
 	if (!atomic_dec_and_test(&d->ref))
 		return false;
 	d->ld->free_deviceid_node(d);
@@ -314,6 +320,7 @@ _deviceid_purge_client(const struct nfs_client *clp, long hash)
 		if (d->nfs_client == clp && atomic_read(&d->ref)) {
 			hlist_del_init_rcu(&d->node);
 			hlist_add_head(&d->tmpnode, &tmp);
+			clear_bit(NFS_DEVICEID_NOCACHE, &d->flags);
 		}
 	rcu_read_unlock();
 	spin_unlock(&nfs4_deviceid_lock);
@@ -321,12 +328,10 @@ _deviceid_purge_client(const struct nfs_client *clp, long hash)
 	if (hlist_empty(&tmp))
 		return;
 
-	synchronize_rcu();
 	while (!hlist_empty(&tmp)) {
 		d = hlist_entry(tmp.first, struct nfs4_deviceid_node, tmpnode);
 		hlist_del(&d->tmpnode);
-		if (atomic_dec_and_test(&d->ref))
-			d->ld->free_deviceid_node(d);
+		nfs4_put_deviceid_node(d);
 	}
 }
 
diff --git a/fs/nfs/pnfs_nfs.c b/fs/nfs/pnfs_nfs.c
index 54e36b3..f37e25b 100644
--- a/fs/nfs/pnfs_nfs.c
+++ b/fs/nfs/pnfs_nfs.c
@@ -561,7 +561,7 @@ static bool load_v3_ds_connect(void)
 	return(get_v3_ds_connect != NULL);
 }
 
-void __exit nfs4_pnfs_v3_ds_connect_unload(void)
+void nfs4_pnfs_v3_ds_connect_unload(void)
 {
 	if (get_v3_ds_connect) {
 		symbol_put(nfs3_set_ds_client);
@@ -868,3 +868,13 @@ pnfs_layout_mark_request_commit(struct nfs_page *req,
 	nfs_request_add_commit_list(req, list, cinfo);
 }
 EXPORT_SYMBOL_GPL(pnfs_layout_mark_request_commit);
+
+int
+pnfs_nfs_generic_sync(struct inode *inode, bool datasync)
+{
+	if (datasync)
+		return 0;
+	return pnfs_layoutcommit_inode(inode, true);
+}
+EXPORT_SYMBOL_GPL(pnfs_nfs_generic_sync);
+
diff --git a/fs/nfs/read.c b/fs/nfs/read.c
index a5b7427..ae0ff7a 100644
--- a/fs/nfs/read.c
+++ b/fs/nfs/read.c
@@ -284,7 +284,7 @@ int nfs_readpage(struct file *file, struct page *page)
 	dprintk("NFS: nfs_readpage (%p %ld@%lu)\n",
 		page, PAGE_CACHE_SIZE, page_file_index(page));
 	nfs_inc_stats(inode, NFSIOS_VFSREADPAGE);
-	nfs_inc_stats(inode, NFSIOS_READPAGES);
+	nfs_add_stats(inode, NFSIOS_READPAGES, 1);
 
 	/*
 	 * Try to flush any pending writes to the file..
diff --git a/fs/nfs/super.c b/fs/nfs/super.c
index 21f8f52..f175b83 100644
--- a/fs/nfs/super.c
+++ b/fs/nfs/super.c
@@ -43,7 +43,6 @@
 #include <linux/seq_file.h>
 #include <linux/mount.h>
 #include <linux/namei.h>
-#include <linux/nfs_idmap.h>
 #include <linux/vfs.h>
 #include <linux/inet.h>
 #include <linux/in6.h>
@@ -2193,7 +2192,7 @@ nfs_compare_remount_data(struct nfs_server *nfss,
 	    data->version != nfss->nfs_client->rpc_ops->version ||
 	    data->minorversion != nfss->nfs_client->cl_minorversion ||
 	    data->retrans != nfss->client->cl_timeout->to_retries ||
-	    data->selected_flavor != nfss->client->cl_auth->au_flavor ||
+	    !nfs_auth_info_match(&data->auth_info, nfss->client->cl_auth->au_flavor) ||
 	    data->acregmin != nfss->acregmin / HZ ||
 	    data->acregmax != nfss->acregmax / HZ ||
 	    data->acdirmin != nfss->acdirmin / HZ ||
@@ -2241,7 +2240,6 @@ nfs_remount(struct super_block *sb, int *flags, char *raw_data)
 	data->wsize = nfss->wsize;
 	data->retrans = nfss->client->cl_timeout->to_retries;
 	data->selected_flavor = nfss->client->cl_auth->au_flavor;
-	data->auth_info = nfss->auth_info;
 	data->acregmin = nfss->acregmin / HZ;
 	data->acregmax = nfss->acregmax / HZ;
 	data->acdirmin = nfss->acdirmin / HZ;
diff --git a/fs/nfs/write.c b/fs/nfs/write.c
index 3612b46..d12a4be 100644
--- a/fs/nfs/write.c
+++ b/fs/nfs/write.c
@@ -580,7 +580,7 @@ static int nfs_do_writepage(struct page *page, struct writeback_control *wbc, st
 	int ret;
 
 	nfs_inc_stats(inode, NFSIOS_VFSWRITEPAGE);
-	nfs_inc_stats(inode, NFSIOS_WRITEPAGES);
+	nfs_add_stats(inode, NFSIOS_WRITEPAGES, 1);
 
 	nfs_pageio_cond_complete(pgio, page_file_index(page));
 	ret = nfs_page_async_flush(pgio, page, wbc->sync_mode == WB_SYNC_NONE);
@@ -1840,17 +1840,16 @@ EXPORT_SYMBOL_GPL(nfs_write_inode);
  */
 int nfs_wb_all(struct inode *inode)
 {
-	struct writeback_control wbc = {
-		.sync_mode = WB_SYNC_ALL,
-		.nr_to_write = LONG_MAX,
-		.range_start = 0,
-		.range_end = LLONG_MAX,
-	};
 	int ret;
 
 	trace_nfs_writeback_inode_enter(inode);
 
-	ret = sync_inode(inode, &wbc);
+	ret = filemap_write_and_wait(inode->i_mapping);
+	if (!ret) {
+		ret = nfs_commit_inode(inode, FLUSH_SYNC);
+		if (!ret)
+			pnfs_sync_inode(inode, true);
+	}
 
 	trace_nfs_writeback_inode_exit(inode, ret);
 	return ret;