Merge tag 'nfs-for-3.14-1' of git://git.linux-nfs.org/projects/trondmy/linux-nfs

Pull NFS client updates from Trond Myklebust:
 "Highlights include:

   - stable fix for an infinite loop in RPC state machine
   - stable fix for a use after free situation in the NFSv4 trunking discovery
   - stable fix for error handling in the NFSv4 trunking discovery
   - stable fix for the page write update code
   - stable fix for the NFSv4.1 mount time security negotiation
   - stable fix for the NFSv4 open code.
   - O_DIRECT locking fixes
   - fix an Oops in the pnfs file commit code
   - RPC layer needs finer grained handling of connection errors
   - more RPC GSS upcall fixes"

* tag 'nfs-for-3.14-1' of git://git.linux-nfs.org/projects/trondmy/linux-nfs: (30 commits)
  pnfs: Proper delay for NFS4ERR_RECALLCONFLICT in layout_get_done
  pnfs: fix BUG in filelayout_recover_commit_reqs
  nfs4: fix discover_server_trunking use after free
  NFSv4.1: Handle errors correctly in nfs41_walk_client_list
  nfs: always make sure page is up-to-date before extending a write to cover the entire page
  nfs: page cache invalidation for dio
  nfs: take i_mutex during direct I/O reads
  nfs: merge nfs_direct_write into nfs_file_direct_write
  nfs: merge nfs_direct_read into nfs_file_direct_read
  nfs: increment i_dio_count for reads, too
  nfs: defer inode_dio_done call until size update is done
  nfs: fix size updates for aio writes
  nfs4.1: properly handle ENOTSUP in SECINFO_NO_NAME
  NFSv4.1: Fix a race in nfs4_write_inode
  NFSv4.1: Don't trust attributes if a pNFS LAYOUTCOMMIT is outstanding
  point to the right include file in a comment (left over from a9004abc3)
  NFS: dprintk() should not print negative fileids and inode numbers
  nfs: fix dead code of ipv6_addr_scope
  sunrpc: Fix infinite loop in RPC state machine
  SUNRPC: Add tracepoint for socket errors
  ...

15 files changed, 359 insertions, 257 deletions

diff --git a/fs/nfs/dir.c b/fs/nfs/dir.c
index 812154aff98..b266f734bd5 100644
--- a/fs/nfs/dir.c
+++ b/fs/nfs/dir.c
@@ -1404,7 +1404,7 @@ int nfs_atomic_open(struct inode *dir, struct dentry *dentry,
 	/* Expect a negative dentry */
 	BUG_ON(dentry->d_inode);
 
-	dfprintk(VFS, "NFS: atomic_open(%s/%ld), %pd\n",
+	dfprintk(VFS, "NFS: atomic_open(%s/%lu), %pd\n",
 			dir->i_sb->s_id, dir->i_ino, dentry);
 
 	err = nfs_check_flags(open_flags);
@@ -1594,7 +1594,7 @@ int nfs_create(struct inode *dir, struct dentry *dentry,
 	int open_flags = excl ? O_CREAT | O_EXCL : O_CREAT;
 	int error;
 
-	dfprintk(VFS, "NFS: create(%s/%ld), %pd\n",
+	dfprintk(VFS, "NFS: create(%s/%lu), %pd\n",
 			dir->i_sb->s_id, dir->i_ino, dentry);
 
 	attr.ia_mode = mode;
@@ -1621,7 +1621,7 @@ nfs_mknod(struct inode *dir, struct dentry *dentry, umode_t mode, dev_t rdev)
 	struct iattr attr;
 	int status;
 
-	dfprintk(VFS, "NFS: mknod(%s/%ld), %pd\n",
+	dfprintk(VFS, "NFS: mknod(%s/%lu), %pd\n",
 			dir->i_sb->s_id, dir->i_ino, dentry);
 
 	if (!new_valid_dev(rdev))
@@ -1650,7 +1650,7 @@ int nfs_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode)
 	struct iattr attr;
 	int error;
 
-	dfprintk(VFS, "NFS: mkdir(%s/%ld), %pd\n",
+	dfprintk(VFS, "NFS: mkdir(%s/%lu), %pd\n",
 			dir->i_sb->s_id, dir->i_ino, dentry);
 
 	attr.ia_valid = ATTR_MODE;
@@ -1678,7 +1678,7 @@ int nfs_rmdir(struct inode *dir, struct dentry *dentry)
 {
 	int error;
 
-	dfprintk(VFS, "NFS: rmdir(%s/%ld), %pd\n",
+	dfprintk(VFS, "NFS: rmdir(%s/%lu), %pd\n",
 			dir->i_sb->s_id, dir->i_ino, dentry);
 
 	trace_nfs_rmdir_enter(dir, dentry);
@@ -1747,7 +1747,7 @@ int nfs_unlink(struct inode *dir, struct dentry *dentry)
 	int error;
 	int need_rehash = 0;
 
-	dfprintk(VFS, "NFS: unlink(%s/%ld, %pd)\n", dir->i_sb->s_id,
+	dfprintk(VFS, "NFS: unlink(%s/%lu, %pd)\n", dir->i_sb->s_id,
 		dir->i_ino, dentry);
 
 	trace_nfs_unlink_enter(dir, dentry);
@@ -1798,7 +1798,7 @@ int nfs_symlink(struct inode *dir, struct dentry *dentry, const char *symname)
 	unsigned int pathlen = strlen(symname);
 	int error;
 
-	dfprintk(VFS, "NFS: symlink(%s/%ld, %pd, %s)\n", dir->i_sb->s_id,
+	dfprintk(VFS, "NFS: symlink(%s/%lu, %pd, %s)\n", dir->i_sb->s_id,
 		dir->i_ino, dentry, symname);
 
 	if (pathlen > PAGE_SIZE)
@@ -1821,7 +1821,7 @@ int nfs_symlink(struct inode *dir, struct dentry *dentry, const char *symname)
 	error = NFS_PROTO(dir)->symlink(dir, dentry, page, pathlen, &attr);
 	trace_nfs_symlink_exit(dir, dentry, error);
 	if (error != 0) {
-		dfprintk(VFS, "NFS: symlink(%s/%ld, %pd, %s) error %d\n",
+		dfprintk(VFS, "NFS: symlink(%s/%lu, %pd, %s) error %d\n",
 			dir->i_sb->s_id, dir->i_ino,
 			dentry, symname, error);
 		d_drop(dentry);
@@ -2304,7 +2304,7 @@ out:
 	if (!res && (mask & MAY_EXEC) && !execute_ok(inode))
 		res = -EACCES;
 
-	dfprintk(VFS, "NFS: permission(%s/%ld), mask=0x%x, res=%d\n",
+	dfprintk(VFS, "NFS: permission(%s/%lu), mask=0x%x, res=%d\n",
 		inode->i_sb->s_id, inode->i_ino, mask, res);
 	return res;
 out_notsup:
diff --git a/fs/nfs/direct.c b/fs/nfs/direct.c
index d71d66c9e0a..b8797ae6831 100644
--- a/fs/nfs/direct.c
+++ b/fs/nfs/direct.c
@@ -222,14 +222,31 @@ out:
  * Synchronous I/O uses a stack-allocated iocb.  Thus we can't trust
  * the iocb is still valid here if this is a synchronous request.
  */
-static void nfs_direct_complete(struct nfs_direct_req *dreq)
+static void nfs_direct_complete(struct nfs_direct_req *dreq, bool write)
 {
+	struct inode *inode = dreq->inode;
+
+	if (dreq->iocb && write) {
+		loff_t pos = dreq->iocb->ki_pos + dreq->count;
+
+		spin_lock(&inode->i_lock);
+		if (i_size_read(inode) < pos)
+			i_size_write(inode, pos);
+		spin_unlock(&inode->i_lock);
+	}
+
+	if (write)
+		nfs_zap_mapping(inode, inode->i_mapping);
+
+	inode_dio_done(inode);
+
 	if (dreq->iocb) {
 		long res = (long) dreq->error;
 		if (!res)
 			res = (long) dreq->count;
 		aio_complete(dreq->iocb, res, 0);
 	}
+
 	complete_all(&dreq->completion);
 
 	nfs_direct_req_release(dreq);
@@ -237,9 +254,9 @@ static void nfs_direct_complete(struct nfs_direct_req *dreq)
 
 static void nfs_direct_readpage_release(struct nfs_page *req)
 {
-	dprintk("NFS: direct read done (%s/%lld %d@%lld)\n",
+	dprintk("NFS: direct read done (%s/%llu %d@%lld)\n",
 		req->wb_context->dentry->d_inode->i_sb->s_id,
-		(long long)NFS_FILEID(req->wb_context->dentry->d_inode),
+		(unsigned long long)NFS_FILEID(req->wb_context->dentry->d_inode),
 		req->wb_bytes,
 		(long long)req_offset(req));
 	nfs_release_request(req);
@@ -272,7 +289,7 @@ static void nfs_direct_read_completion(struct nfs_pgio_header *hdr)
 	}
 out_put:
 	if (put_dreq(dreq))
-		nfs_direct_complete(dreq);
+		nfs_direct_complete(dreq, false);
 	hdr->release(hdr);
 }
 
@@ -402,6 +419,7 @@ static ssize_t nfs_direct_read_schedule_iovec(struct nfs_direct_req *dreq,
 					      loff_t pos, bool uio)
 {
 	struct nfs_pageio_descriptor desc;
+	struct inode *inode = dreq->inode;
 	ssize_t result = -EINVAL;
 	size_t requested_bytes = 0;
 	unsigned long seg;
@@ -410,6 +428,7 @@ static ssize_t nfs_direct_read_schedule_iovec(struct nfs_direct_req *dreq,
 			     &nfs_direct_read_completion_ops);
 	get_dreq(dreq);
 	desc.pg_dreq = dreq;
+	atomic_inc(&inode->i_dio_count);
 
 	for (seg = 0; seg < nr_segs; seg++) {
 		const struct iovec *vec = &iov[seg];
@@ -429,26 +448,69 @@ static ssize_t nfs_direct_read_schedule_iovec(struct nfs_direct_req *dreq,
 	 * generic layer handle the completion.
 	 */
 	if (requested_bytes == 0) {
+		inode_dio_done(inode);
 		nfs_direct_req_release(dreq);
 		return result < 0 ? result : -EIO;
 	}
 
 	if (put_dreq(dreq))
-		nfs_direct_complete(dreq);
+		nfs_direct_complete(dreq, false);
 	return 0;
 }
 
-static ssize_t nfs_direct_read(struct kiocb *iocb, const struct iovec *iov,
-			       unsigned long nr_segs, loff_t pos, bool uio)
+/**
+ * nfs_file_direct_read - file direct read operation for NFS files
+ * @iocb: target I/O control block
+ * @iov: vector of user buffers into which to read data
+ * @nr_segs: size of iov vector
+ * @pos: byte offset in file where reading starts
+ *
+ * We use this function for direct reads instead of calling
+ * generic_file_aio_read() in order to avoid gfar's check to see if
+ * the request starts before the end of the file.  For that check
+ * to work, we must generate a GETATTR before each direct read, and
+ * even then there is a window between the GETATTR and the subsequent
+ * READ where the file size could change.  Our preference is simply
+ * to do all reads the application wants, and the server will take
+ * care of managing the end of file boundary.
+ *
+ * This function also eliminates unnecessarily updating the file's
+ * atime locally, as the NFS server sets the file's atime, and this
+ * client must read the updated atime from the server back into its
+ * cache.
+ */
+ssize_t nfs_file_direct_read(struct kiocb *iocb, const struct iovec *iov,
+				unsigned long nr_segs, loff_t pos, bool uio)
 {
-	ssize_t result = -ENOMEM;
-	struct inode *inode = iocb->ki_filp->f_mapping->host;
+	struct file *file = iocb->ki_filp;
+	struct address_space *mapping = file->f_mapping;
+	struct inode *inode = mapping->host;
 	struct nfs_direct_req *dreq;
 	struct nfs_lock_context *l_ctx;
+	ssize_t result = -EINVAL;
+	size_t count;
 
+	count = iov_length(iov, nr_segs);
+	nfs_add_stats(mapping->host, NFSIOS_DIRECTREADBYTES, count);
+
+	dfprintk(FILE, "NFS: direct read(%pD2, %zd@%Ld)\n",
+		file, count, (long long) pos);
+
+	result = 0;
+	if (!count)
+		goto out;
+
+	mutex_lock(&inode->i_mutex);
+	result = nfs_sync_mapping(mapping);
+	if (result)
+		goto out_unlock;
+
+	task_io_account_read(count);
+
+	result = -ENOMEM;
 	dreq = nfs_direct_req_alloc();
 	if (dreq == NULL)
-		goto out;
+		goto out_unlock;
 
 	dreq->inode = inode;
 	dreq->bytes_left = iov_length(iov, nr_segs);
@@ -464,20 +526,26 @@ static ssize_t nfs_direct_read(struct kiocb *iocb, const struct iovec *iov,
 
 	NFS_I(inode)->read_io += iov_length(iov, nr_segs);
 	result = nfs_direct_read_schedule_iovec(dreq, iov, nr_segs, pos, uio);
-	if (!result)
+
+	mutex_unlock(&inode->i_mutex);
+
+	if (!result) {
 		result = nfs_direct_wait(dreq);
+		if (result > 0)
+			iocb->ki_pos = pos + result;
+	}
+
+	nfs_direct_req_release(dreq);
+	return result;
+
 out_release:
 	nfs_direct_req_release(dreq);
+out_unlock:
+	mutex_unlock(&inode->i_mutex);
 out:
 	return result;
 }
 
-static void nfs_inode_dio_write_done(struct inode *inode)
-{
-	nfs_zap_mapping(inode, inode->i_mapping);
-	inode_dio_done(inode);
-}
-
 #if IS_ENABLED(CONFIG_NFS_V3) || IS_ENABLED(CONFIG_NFS_V4)
 static void nfs_direct_write_reschedule(struct nfs_direct_req *dreq)
 {
@@ -593,8 +661,7 @@ static void nfs_direct_write_schedule_work(struct work_struct *work)
 			nfs_direct_write_reschedule(dreq);
 			break;
 		default:
-			nfs_inode_dio_write_done(dreq->inode);
-			nfs_direct_complete(dreq);
+			nfs_direct_complete(dreq, true);
 	}
 }
 
@@ -610,8 +677,7 @@ static void nfs_direct_write_schedule_work(struct work_struct *work)
 
 static void nfs_direct_write_complete(struct nfs_direct_req *dreq, struct inode *inode)
 {
-	nfs_inode_dio_write_done(inode);
-	nfs_direct_complete(dreq);
+	nfs_direct_complete(dreq, true);
 }
 #endif
 
@@ -842,93 +908,6 @@ static ssize_t nfs_direct_write_schedule_iovec(struct nfs_direct_req *dreq,
 	return 0;
 }
 
-static ssize_t nfs_direct_write(struct kiocb *iocb, const struct iovec *iov,
-				unsigned long nr_segs, loff_t pos,
-				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));
-	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, uio);
-	if (!result)
-		result = nfs_direct_wait(dreq);
-out_release:
-	nfs_direct_req_release(dreq);
-out:
-	return result;
-}
-
-/**
- * nfs_file_direct_read - file direct read operation for NFS files
- * @iocb: target I/O control block
- * @iov: vector of user buffers into which to read data
- * @nr_segs: size of iov vector
- * @pos: byte offset in file where reading starts
- *
- * We use this function for direct reads instead of calling
- * generic_file_aio_read() in order to avoid gfar's check to see if
- * the request starts before the end of the file.  For that check
- * to work, we must generate a GETATTR before each direct read, and
- * even then there is a window between the GETATTR and the subsequent
- * READ where the file size could change.  Our preference is simply
- * to do all reads the application wants, and the server will take
- * care of managing the end of file boundary.
- *
- * This function also eliminates unnecessarily updating the file's
- * atime locally, as the NFS server sets the file's atime, and this
- * client must read the updated atime from the server back into its
- * cache.
- */
-ssize_t nfs_file_direct_read(struct kiocb *iocb, const struct iovec *iov,
-				unsigned long nr_segs, loff_t pos, bool uio)
-{
-	ssize_t retval = -EINVAL;
-	struct file *file = iocb->ki_filp;
-	struct address_space *mapping = file->f_mapping;
-	size_t count;
-
-	count = iov_length(iov, nr_segs);
-	nfs_add_stats(mapping->host, NFSIOS_DIRECTREADBYTES, count);
-
-	dfprintk(FILE, "NFS: direct read(%pD2, %zd@%Ld)\n",
-		file, count, (long long) pos);
-
-	retval = 0;
-	if (!count)
-		goto out;
-
-	retval = nfs_sync_mapping(mapping);
-	if (retval)
-		goto out;
-
-	task_io_account_read(count);
-
-	retval = nfs_direct_read(iocb, iov, nr_segs, pos, uio);
-	if (retval > 0)
-		iocb->ki_pos = pos + retval;
-
-out:
-	return retval;
-}
-
 /**
  * nfs_file_direct_write - file direct write operation for NFS files
  * @iocb: target I/O control block
@@ -954,46 +933,96 @@ out:
 ssize_t nfs_file_direct_write(struct kiocb *iocb, const struct iovec *iov,
 				unsigned long nr_segs, loff_t pos, bool uio)
 {
-	ssize_t retval = -EINVAL;
+	ssize_t result = -EINVAL;
 	struct file *file = iocb->ki_filp;
 	struct address_space *mapping = file->f_mapping;
+	struct inode *inode = mapping->host;
+	struct nfs_direct_req *dreq;
+	struct nfs_lock_context *l_ctx;
+	loff_t end;
 	size_t count;
 
 	count = iov_length(iov, nr_segs);
+	end = (pos + count - 1) >> PAGE_CACHE_SHIFT;
+
 	nfs_add_stats(mapping->host, NFSIOS_DIRECTWRITTENBYTES, count);
 
 	dfprintk(FILE, "NFS: direct write(%pD2, %zd@%Ld)\n",
 		file, count, (long long) pos);
 
-	retval = generic_write_checks(file, &pos, &count, 0);
-	if (retval)
+	result = generic_write_checks(file, &pos, &count, 0);
+	if (result)
 		goto out;
 
-	retval = -EINVAL;
+	result = -EINVAL;
 	if ((ssize_t) count < 0)
 		goto out;
-	retval = 0;
+	result = 0;
 	if (!count)
 		goto out;
 
-	retval = nfs_sync_mapping(mapping);
-	if (retval)
-		goto out;
+	mutex_lock(&inode->i_mutex);
+
+	result = nfs_sync_mapping(mapping);
+	if (result)
+		goto out_unlock;
+
+	if (mapping->nrpages) {
+		result = invalidate_inode_pages2_range(mapping,
+					pos >> PAGE_CACHE_SHIFT, end);
+		if (result)
+			goto out_unlock;
+	}
 
 	task_io_account_write(count);
 
-	retval = nfs_direct_write(iocb, iov, nr_segs, pos, count, uio);
-	if (retval > 0) {
-		struct inode *inode = mapping->host;
+	result = -ENOMEM;
+	dreq = nfs_direct_req_alloc();
+	if (!dreq)
+		goto out_unlock;
 
-		iocb->ki_pos = pos + retval;
-		spin_lock(&inode->i_lock);
-		if (i_size_read(inode) < iocb->ki_pos)
-			i_size_write(inode, iocb->ki_pos);
-		spin_unlock(&inode->i_lock);
+	dreq->inode = inode;
+	dreq->bytes_left = count;
+	dreq->ctx = get_nfs_open_context(nfs_file_open_context(iocb->ki_filp));
+	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, uio);
+
+	if (mapping->nrpages) {
+		invalidate_inode_pages2_range(mapping,
+					      pos >> PAGE_CACHE_SHIFT, end);
 	}
+
+	mutex_unlock(&inode->i_mutex);
+
+	if (!result) {
+		result = nfs_direct_wait(dreq);
+		if (result > 0) {
+			struct inode *inode = mapping->host;
+
+			iocb->ki_pos = pos + result;
+			spin_lock(&inode->i_lock);
+			if (i_size_read(inode) < iocb->ki_pos)
+				i_size_write(inode, iocb->ki_pos);
+			spin_unlock(&inode->i_lock);
+		}
+	}
+	nfs_direct_req_release(dreq);
+	return result;
+
+out_release:
+	nfs_direct_req_release(dreq);
+out_unlock:
+	mutex_unlock(&inode->i_mutex);
 out:
-	return retval;
+	return result;
 }
 
 /**
diff --git a/fs/nfs/file.c b/fs/nfs/file.c
index e2fcacf07de..5bb790a69c7 100644
--- a/fs/nfs/file.c
+++ b/fs/nfs/file.c
@@ -354,7 +354,7 @@ static int nfs_write_begin(struct file *file, struct address_space *mapping,
 	struct page *page;
 	int once_thru = 0;
 
-	dfprintk(PAGECACHE, "NFS: write_begin(%pD2(%ld), %u@%lld)\n",
+	dfprintk(PAGECACHE, "NFS: write_begin(%pD2(%lu), %u@%lld)\n",
 		file, mapping->host->i_ino, len, (long long) pos);
 
 start:
@@ -395,7 +395,7 @@ static int nfs_write_end(struct file *file, struct address_space *mapping,
 	struct nfs_open_context *ctx = nfs_file_open_context(file);
 	int status;
 
-	dfprintk(PAGECACHE, "NFS: write_end(%pD2(%ld), %u@%lld)\n",
+	dfprintk(PAGECACHE, "NFS: write_end(%pD2(%lu), %u@%lld)\n",
 		file, mapping->host->i_ino, len, (long long) pos);
 
 	/*
@@ -585,7 +585,7 @@ static int nfs_vm_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf)
 	int ret = VM_FAULT_NOPAGE;
 	struct address_space *mapping;
 
-	dfprintk(PAGECACHE, "NFS: vm_page_mkwrite(%pD2(%ld), offset %lld)\n",
+	dfprintk(PAGECACHE, "NFS: vm_page_mkwrite(%pD2(%lu), offset %lld)\n",
 		filp, filp->f_mapping->host->i_ino,
 		(long long)page_offset(page));
 
diff --git a/fs/nfs/inode.c b/fs/nfs/inode.c
index ecd11ba7f96..ea00b34ff07 100644
--- a/fs/nfs/inode.c
+++ b/fs/nfs/inode.c
@@ -458,9 +458,9 @@ nfs_fhget(struct super_block *sb, struct nfs_fh *fh, struct nfs_fattr *fattr, st
 		unlock_new_inode(inode);
 	} else
 		nfs_refresh_inode(inode, fattr);
-	dprintk("NFS: nfs_fhget(%s/%Ld fh_crc=0x%08x ct=%d)\n",
+	dprintk("NFS: nfs_fhget(%s/%Lu fh_crc=0x%08x ct=%d)\n",
 		inode->i_sb->s_id,
-		(long long)NFS_FILEID(inode),
+		(unsigned long long)NFS_FILEID(inode),
 		nfs_display_fhandle_hash(fh),
 		atomic_read(&inode->i_count));
 
@@ -870,8 +870,8 @@ __nfs_revalidate_inode(struct nfs_server *server, struct inode *inode)
 	struct nfs_fattr *fattr = NULL;
 	struct nfs_inode *nfsi = NFS_I(inode);
 
-	dfprintk(PAGECACHE, "NFS: revalidating (%s/%Ld)\n",
-		inode->i_sb->s_id, (long long)NFS_FILEID(inode));
+	dfprintk(PAGECACHE, "NFS: revalidating (%s/%Lu)\n",
+		inode->i_sb->s_id, (unsigned long long)NFS_FILEID(inode));
 
 	trace_nfs_revalidate_inode_enter(inode);
 
@@ -895,9 +895,9 @@ __nfs_revalidate_inode(struct nfs_server *server, struct inode *inode)
 
 	status = NFS_PROTO(inode)->getattr(server, NFS_FH(inode), fattr, label);
 	if (status != 0) {
-		dfprintk(PAGECACHE, "nfs_revalidate_inode: (%s/%Ld) getattr failed, error=%d\n",
+		dfprintk(PAGECACHE, "nfs_revalidate_inode: (%s/%Lu) getattr failed, error=%d\n",
 			 inode->i_sb->s_id,
-			 (long long)NFS_FILEID(inode), status);
+			 (unsigned long long)NFS_FILEID(inode), status);
 		if (status == -ESTALE) {
 			nfs_zap_caches(inode);
 			if (!S_ISDIR(inode->i_mode))
@@ -908,9 +908,9 @@ __nfs_revalidate_inode(struct nfs_server *server, struct inode *inode)
 
 	status = nfs_refresh_inode(inode, fattr);
 	if (status) {
-		dfprintk(PAGECACHE, "nfs_revalidate_inode: (%s/%Ld) refresh failed, error=%d\n",
+		dfprintk(PAGECACHE, "nfs_revalidate_inode: (%s/%Lu) refresh failed, error=%d\n",
 			 inode->i_sb->s_id,
-			 (long long)NFS_FILEID(inode), status);
+			 (unsigned long long)NFS_FILEID(inode), status);
 		goto err_out;
 	}
 
@@ -919,9 +919,9 @@ __nfs_revalidate_inode(struct nfs_server *server, struct inode *inode)
 
 	nfs_setsecurity(inode, fattr, label);
 
-	dfprintk(PAGECACHE, "NFS: (%s/%Ld) revalidation complete\n",
+	dfprintk(PAGECACHE, "NFS: (%s/%Lu) revalidation complete\n",
 		inode->i_sb->s_id,
-		(long long)NFS_FILEID(inode));
+		(unsigned long long)NFS_FILEID(inode));
 
 err_out:
 	nfs4_label_free(label);
@@ -985,8 +985,9 @@ static int nfs_invalidate_mapping(struct inode *inode, struct address_space *map
 	nfs_inc_stats(inode, NFSIOS_DATAINVALIDATE);
 	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));
+	dfprintk(PAGECACHE, "NFS: (%s/%Lu) data cache invalidated\n",
+			inode->i_sb->s_id,
+			(unsigned long long)NFS_FILEID(inode));
 	return 0;
 }
 
@@ -1282,12 +1283,28 @@ static int nfs_inode_attrs_need_update(const struct inode *inode, const struct n
 		((long)nfsi->attr_gencount - (long)nfs_read_attr_generation_counter() > 0);
 }
 
+/*
+ * Don't trust the change_attribute, mtime, ctime or size if
+ * a pnfs LAYOUTCOMMIT is outstanding
+ */
+static void nfs_inode_attrs_handle_layoutcommit(struct inode *inode,
+		struct nfs_fattr *fattr)
+{
+	if (pnfs_layoutcommit_outstanding(inode))
+		fattr->valid &= ~(NFS_ATTR_FATTR_CHANGE |
+				NFS_ATTR_FATTR_MTIME |
+				NFS_ATTR_FATTR_CTIME |
+				NFS_ATTR_FATTR_SIZE);
+}
+
 static int nfs_refresh_inode_locked(struct inode *inode, struct nfs_fattr *fattr)
 {
 	int ret;
 
 	trace_nfs_refresh_inode_enter(inode);
 
+	nfs_inode_attrs_handle_layoutcommit(inode, fattr);
+
 	if (nfs_inode_attrs_need_update(inode, fattr))
 		ret = nfs_update_inode(inode, fattr);
 	else
@@ -1434,7 +1451,7 @@ static int nfs_update_inode(struct inode *inode, struct nfs_fattr *fattr)
 	unsigned long now = jiffies;
 	unsigned long save_cache_validity;
 
-	dfprintk(VFS, "NFS: %s(%s/%ld fh_crc=0x%08x ct=%d info=0x%x)\n",
+	dfprintk(VFS, "NFS: %s(%s/%lu fh_crc=0x%08x ct=%d info=0x%x)\n",
 			__func__, inode->i_sb->s_id, inode->i_ino,
 			nfs_display_fhandle_hash(NFS_FH(inode)),
 			atomic_read(&inode->i_count), fattr->valid);
@@ -1455,7 +1472,7 @@ static int nfs_update_inode(struct inode *inode, struct nfs_fattr *fattr)
 		/*
 		* Big trouble! The inode has become a different object.
 		*/
-		printk(KERN_DEBUG "NFS: %s: inode %ld mode changed, %07o to %07o\n",
+		printk(KERN_DEBUG "NFS: %s: inode %lu mode changed, %07o to %07o\n",
 				__func__, inode->i_ino, inode->i_mode, fattr->mode);
 		goto out_err;
 	}
@@ -1517,8 +1534,7 @@ static int nfs_update_inode(struct inode *inode, struct nfs_fattr *fattr)
 		if (new_isize != cur_isize) {
 			/* Do we perhaps have any outstanding writes, or has
 			 * the file grown beyond our last write? */
-			if ((nfsi->npages == 0 && !test_bit(NFS_INO_LAYOUTCOMMIT, &nfsi->flags)) ||
-			     new_isize > cur_isize) {
+			if ((nfsi->npages == 0) || new_isize > cur_isize) {
 				i_size_write(inode, new_isize);
 				invalid |= NFS_INO_INVALID_ATTR|NFS_INO_INVALID_DATA;
 			}
diff --git a/fs/nfs/nfs4client.c b/fs/nfs/nfs4client.c
index b4a160a405c..73d4ecda1e3 100644
--- a/fs/nfs/nfs4client.c
+++ b/fs/nfs/nfs4client.c
@@ -10,6 +10,7 @@
 #include <linux/sunrpc/auth.h>
 #include <linux/sunrpc/xprt.h>
 #include <linux/sunrpc/bc_xprt.h>
+#include <linux/sunrpc/rpc_pipe_fs.h>
 #include "internal.h"
 #include "callback.h"
 #include "delegation.h"
@@ -370,7 +371,11 @@ struct nfs_client *nfs4_init_client(struct nfs_client *clp,
 		__set_bit(NFS_CS_INFINITE_SLOTS, &clp->cl_flags);
 	__set_bit(NFS_CS_DISCRTRY, &clp->cl_flags);
 	__set_bit(NFS_CS_NO_RETRANS_TIMEOUT, &clp->cl_flags);
-	error = nfs_create_rpc_client(clp, timeparms, RPC_AUTH_GSS_KRB5I);
+
+	error = -EINVAL;
+	if (gssd_running(clp->cl_net))
+		error = nfs_create_rpc_client(clp, timeparms,
+					      RPC_AUTH_GSS_KRB5I);
 	if (error == -EINVAL)
 		error = nfs_create_rpc_client(clp, timeparms, RPC_AUTH_UNIX);
 	if (error < 0)
@@ -409,13 +414,11 @@ struct nfs_client *nfs4_init_client(struct nfs_client *clp,
 	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;
+	if (clp != old)
+		clp->cl_preserve_clid = true;
+	nfs_put_client(clp);
+	return old;
 
 error:
 	nfs_mark_client_ready(clp, error);
@@ -493,9 +496,10 @@ int nfs40_walk_client_list(struct nfs_client *new,
 			prev = pos;
 
 			status = nfs_wait_client_init_complete(pos);
-			spin_lock(&nn->nfs_client_lock);
 			if (status < 0)
-				continue;
+				goto out;
+			status = -NFS4ERR_STALE_CLIENTID;
+			spin_lock(&nn->nfs_client_lock);
 		}
 		if (pos->cl_cons_state != NFS_CS_READY)
 			continue;
@@ -633,7 +637,8 @@ int nfs41_walk_client_list(struct nfs_client *new,
 			}
 			spin_lock(&nn->nfs_client_lock);
 			if (status < 0)
-				continue;
+				break;
+			status = -NFS4ERR_STALE_CLIENTID;
 		}
 		if (pos->cl_cons_state != NFS_CS_READY)
 			continue;
diff --git a/fs/nfs/nfs4filelayout.c b/fs/nfs/nfs4filelayout.c
index b86464ba25e..03fd8be8c0c 100644
--- a/fs/nfs/nfs4filelayout.c
+++ b/fs/nfs/nfs4filelayout.c
@@ -91,10 +91,10 @@ static void filelayout_reset_write(struct nfs_write_data *data)
 
 	if (!test_and_set_bit(NFS_IOHDR_REDO, &hdr->flags)) {
 		dprintk("%s Reset task %5u for i/o through MDS "
-			"(req %s/%lld, %u bytes @ offset %llu)\n", __func__,
+			"(req %s/%llu, %u bytes @ offset %llu)\n", __func__,
 			data->task.tk_pid,
 			hdr->inode->i_sb->s_id,
-			(long long)NFS_FILEID(hdr->inode),
+			(unsigned long long)NFS_FILEID(hdr->inode),
 			data->args.count,
 			(unsigned long long)data->args.offset);
 
@@ -112,10 +112,10 @@ static void filelayout_reset_read(struct nfs_read_data *data)
 
 	if (!test_and_set_bit(NFS_IOHDR_REDO, &hdr->flags)) {
 		dprintk("%s Reset task %5u for i/o through MDS "
-			"(req %s/%lld, %u bytes @ offset %llu)\n", __func__,
+			"(req %s/%llu, %u bytes @ offset %llu)\n", __func__,
 			data->task.tk_pid,
 			hdr->inode->i_sb->s_id,
-			(long long)NFS_FILEID(hdr->inode),
+			(unsigned long long)NFS_FILEID(hdr->inode),
 			data->args.count,
 			(unsigned long long)data->args.offset);
 
@@ -1216,17 +1216,17 @@ static void filelayout_recover_commit_reqs(struct list_head *dst,
 	struct pnfs_commit_bucket *b;
 	int i;
 
-	/* 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 pnfs_put_lseg
-	 */
+	spin_lock(cinfo->lock);
 	for (i = 0, b = cinfo->ds->buckets; i < cinfo->ds->nbuckets; i++, b++) {
 		if (transfer_commit_list(&b->written, dst, cinfo, 0)) {
+			spin_unlock(cinfo->lock);
 			pnfs_put_lseg(b->wlseg);
 			b->wlseg = NULL;
+			spin_lock(cinfo->lock);
 		}
 	}
 	cinfo->ds->nwritten = 0;
+	spin_unlock(cinfo->lock);
 }
 
 static unsigned int
diff --git a/fs/nfs/nfs4filelayoutdev.c b/fs/nfs/nfs4filelayoutdev.c
index c7c295e556e..efac602edb3 100644
--- a/fs/nfs/nfs4filelayoutdev.c
+++ b/fs/nfs/nfs4filelayoutdev.c
@@ -95,7 +95,7 @@ same_sockaddr(struct sockaddr *addr1, struct sockaddr *addr2)
 		b6 = (struct sockaddr_in6 *)addr2;
 
 		/* LINKLOCAL addresses must have matching scope_id */
-		if (ipv6_addr_scope(&a6->sin6_addr) ==
+		if (ipv6_addr_src_scope(&a6->sin6_addr) ==
 		    IPV6_ADDR_SCOPE_LINKLOCAL &&
 		    a6->sin6_scope_id != b6->sin6_scope_id)
 			return false;
diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c
index 15052b81df4..a1965329a12 100644
--- a/fs/nfs/nfs4proc.c
+++ b/fs/nfs/nfs4proc.c
@@ -7409,9 +7409,9 @@ static void nfs4_layoutget_done(struct rpc_task *task, void *calldata)
 	struct nfs_server *server = NFS_SERVER(inode);
 	struct pnfs_layout_hdr *lo;
 	struct nfs4_state *state = NULL;
-	unsigned long timeo, giveup;
+	unsigned long timeo, now, giveup;
 
-	dprintk("--> %s\n", __func__);
+	dprintk("--> %s tk_status => %d\n", __func__, -task->tk_status);
 
 	if (!nfs41_sequence_done(task, &lgp->res.seq_res))
 		goto out;
@@ -7419,12 +7419,38 @@ static void nfs4_layoutget_done(struct rpc_task *task, void *calldata)
 	switch (task->tk_status) {
 	case 0:
 		goto out;
+	/*
+	 * NFS4ERR_LAYOUTTRYLATER is a conflict with another client
+	 * (or clients) writing to the same RAID stripe
+	 */
 	case -NFS4ERR_LAYOUTTRYLATER:
+	/*
+	 * NFS4ERR_RECALLCONFLICT is when conflict with self (must recall
+	 * existing layout before getting a new one).
+	 */
 	case -NFS4ERR_RECALLCONFLICT:
 		timeo = rpc_get_timeout(task->tk_client);
 		giveup = lgp->args.timestamp + timeo;
-		if (time_after(giveup, jiffies))
-			task->tk_status = -NFS4ERR_DELAY;
+		now = jiffies;
+		if (time_after(giveup, now)) {
+			unsigned long delay;
+
+			/* Delay for:
+			 * - Not less then NFS4_POLL_RETRY_MIN.
+			 * - One last time a jiffie before we give up
+			 * - exponential backoff (time_now minus start_attempt)
+			 */
+			delay = max_t(unsigned long, NFS4_POLL_RETRY_MIN,
+				    min((giveup - now - 1),
+					now - lgp->args.timestamp));
+
+			dprintk("%s: NFS4ERR_RECALLCONFLICT waiting %lu\n",
+				__func__, delay);
+			rpc_delay(task, delay);
+			task->tk_status = 0;
+			rpc_restart_call_prepare(task);
+			goto out; /* Do not call nfs4_async_handle_error() */
+		}
 		break;
 	case -NFS4ERR_EXPIRED:
 	case -NFS4ERR_BAD_STATEID:
@@ -7780,10 +7806,7 @@ nfs4_layoutcommit_done(struct rpc_task *task, void *calldata)
 	case -NFS4ERR_BADLAYOUT:     /* no layout */
 	case -NFS4ERR_GRACE:	    /* loca_recalim always false */
 		task->tk_status = 0;
-		break;
 	case 0:
-		nfs_post_op_update_inode_force_wcc(data->args.inode,
-						   data->res.fattr);
 		break;
 	default:
 		if (nfs4_async_handle_error(task, server, NULL) == -EAGAIN) {
@@ -7798,6 +7821,8 @@ static void nfs4_layoutcommit_release(void *calldata)
 	struct nfs4_layoutcommit_data *data = calldata;
 
 	pnfs_cleanup_layoutcommit(data);
+	nfs_post_op_update_inode_force_wcc(data->args.inode,
+					   data->res.fattr);
 	put_rpccred(data->cred);
 	kfree(data);
 }
@@ -7920,7 +7945,7 @@ nfs41_proc_secinfo_no_name(struct nfs_server *server, struct nfs_fh *fhandle,
 		switch (err) {
 		case 0:
 		case -NFS4ERR_WRONGSEC:
-		case -NFS4ERR_NOTSUPP:
+		case -ENOTSUPP:
 			goto out;
 		default:
 			err = nfs4_handle_exception(server, err, &exception);
@@ -7954,7 +7979,7 @@ nfs41_find_root_sec(struct nfs_server *server, struct nfs_fh *fhandle,
 	 * Fall back on "guess and check" method if
 	 * the server doesn't support SECINFO_NO_NAME
 	 */
-	if (err == -NFS4ERR_WRONGSEC || err == -NFS4ERR_NOTSUPP) {
+	if (err == -NFS4ERR_WRONGSEC || err == -ENOTSUPP) {
 		err = nfs4_find_root_sec(server, fhandle, info);
 		goto out_freepage;
 	}
diff --git a/fs/nfs/nfs4state.c b/fs/nfs/nfs4state.c
index 059c01b67a7..e5be72518bd 100644
--- a/fs/nfs/nfs4state.c
+++ b/fs/nfs/nfs4state.c
@@ -1071,7 +1071,7 @@ void nfs_free_seqid(struct nfs_seqid *seqid)
 /*
  * Increment the seqid if the OPEN/OPEN_DOWNGRADE/CLOSE succeeded, or
  * failed with a seqid incrementing error -
- * see comments nfs_fs.h:seqid_mutating_error()
+ * see comments nfs4.h:seqid_mutating_error()
  */
 static void nfs_increment_seqid(int status, struct nfs_seqid *seqid)
 {
@@ -1116,7 +1116,7 @@ void nfs_increment_open_seqid(int status, struct nfs_seqid *seqid)
 /*
  * Increment the seqid if the LOCK/LOCKU succeeded, or
  * failed with a seqid incrementing error -
- * see comments nfs_fs.h:seqid_mutating_error()
+ * see comments nfs4.h:seqid_mutating_error()
  */
 void nfs_increment_lock_seqid(int status, struct nfs_seqid *seqid)
 {
diff --git a/fs/nfs/nfs4super.c b/fs/nfs/nfs4super.c
index 65ab0a0ca1c..808f2957441 100644
--- a/fs/nfs/nfs4super.c
+++ b/fs/nfs/nfs4super.c
@@ -77,17 +77,9 @@ 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;
-	}
+	if (ret == 0)
+		ret = pnfs_layoutcommit_inode(inode,
+				wbc->sync_mode == WB_SYNC_ALL);
 	return ret;
 }
 
diff --git a/fs/nfs/nfs4xdr.c b/fs/nfs/nfs4xdr.c
index 5be2868c02f..8c21d69a9dc 100644
--- a/fs/nfs/nfs4xdr.c
+++ b/fs/nfs/nfs4xdr.c
@@ -3097,7 +3097,8 @@ out_overflow:
 	return -EIO;
 }
 
-static int decode_op_hdr(struct xdr_stream *xdr, enum nfs_opnum4 expected)
+static bool __decode_op_hdr(struct xdr_stream *xdr, enum nfs_opnum4 expected,
+		int *nfs_retval)
 {
 	__be32 *p;
 	uint32_t opnum;
@@ -3107,19 +3108,32 @@ static int decode_op_hdr(struct xdr_stream *xdr, enum nfs_opnum4 expected)
 	if (unlikely(!p))
 		goto out_overflow;
 	opnum = be32_to_cpup(p++);
-	if (opnum != expected) {
-		dprintk("nfs: Server returned operation"
-			" %d but we issued a request for %d\n",
-				opnum, expected);
-		return -EIO;
-	}
+	if (unlikely(opnum != expected))
+		goto out_bad_operation;
 	nfserr = be32_to_cpup(p);
-	if (nfserr != NFS_OK)
-		return nfs4_stat_to_errno(nfserr);
-	return 0;
+	if (nfserr == NFS_OK)
+		*nfs_retval = 0;
+	else
+		*nfs_retval = nfs4_stat_to_errno(nfserr);
+	return true;
+out_bad_operation:
+	dprintk("nfs: Server returned operation"
+		" %d but we issued a request for %d\n",
+			opnum, expected);
+	*nfs_retval = -EREMOTEIO;
+	return false;
 out_overflow:
 	print_overflow_msg(__func__, xdr);
-	return -EIO;
+	*nfs_retval = -EIO;
+	return false;
+}
+
+static int decode_op_hdr(struct xdr_stream *xdr, enum nfs_opnum4 expected)
+{
+	int retval;
+
+	__decode_op_hdr(xdr, expected, &retval);
+	return retval;
 }
 
 /* Dummy routine */
@@ -5001,11 +5015,12 @@ static int decode_open(struct xdr_stream *xdr, struct nfs_openres *res)
 	uint32_t savewords, bmlen, i;
 	int status;
 
-	status = decode_op_hdr(xdr, OP_OPEN);
-	if (status != -EIO)
-		nfs_increment_open_seqid(status, res->seqid);
-	if (!status)
-		status = decode_stateid(xdr, &res->stateid);
+	if (!__decode_op_hdr(xdr, OP_OPEN, &status))
+		return status;
+	nfs_increment_open_seqid(status, res->seqid);
+	if (status)
+		return status;
+	status = decode_stateid(xdr, &res->stateid);
 	if (unlikely(status))
 		return status;
 
diff --git a/fs/nfs/pnfs.c b/fs/nfs/pnfs.c
index d75d938d36c..4755858e37a 100644
--- a/fs/nfs/pnfs.c
+++ b/fs/nfs/pnfs.c
@@ -1790,6 +1790,15 @@ pnfs_generic_pg_readpages(struct nfs_pageio_descriptor *desc)
 }
 EXPORT_SYMBOL_GPL(pnfs_generic_pg_readpages);
 
+static void pnfs_clear_layoutcommitting(struct inode *inode)
+{
+	unsigned long *bitlock = &NFS_I(inode)->flags;
+
+	clear_bit_unlock(NFS_INO_LAYOUTCOMMITTING, bitlock);
+	smp_mb__after_clear_bit();
+	wake_up_bit(bitlock, NFS_INO_LAYOUTCOMMITTING);
+}
+
 /*
  * There can be multiple RW segments.
  */
@@ -1807,7 +1816,6 @@ static void pnfs_list_write_lseg(struct inode *inode, struct list_head *listp)
 static void pnfs_list_write_lseg_done(struct inode *inode, struct list_head *listp)
 {
 	struct pnfs_layout_segment *lseg, *tmp;
-	unsigned long *bitlock = &NFS_I(inode)->flags;
 
 	/* Matched by references in pnfs_set_layoutcommit */
 	list_for_each_entry_safe(lseg, tmp, listp, pls_lc_list) {
@@ -1815,9 +1823,7 @@ static void pnfs_list_write_lseg_done(struct inode *inode, struct list_head *lis
 		pnfs_put_lseg(lseg);
 	}
 
-	clear_bit_unlock(NFS_INO_LAYOUTCOMMITTING, bitlock);
-	smp_mb__after_clear_bit();
-	wake_up_bit(bitlock, NFS_INO_LAYOUTCOMMITTING);
+	pnfs_clear_layoutcommitting(inode);
 }
 
 void pnfs_set_lo_fail(struct pnfs_layout_segment *lseg)
@@ -1881,43 +1887,37 @@ pnfs_layoutcommit_inode(struct inode *inode, bool sync)
 	struct nfs4_layoutcommit_data *data;
 	struct nfs_inode *nfsi = NFS_I(inode);
 	loff_t end_pos;
-	int status = 0;
+	int status;
 
-	dprintk("--> %s inode %lu\n", __func__, inode->i_ino);
-
-	if (!test_bit(NFS_INO_LAYOUTCOMMIT, &nfsi->flags))
+	if (!pnfs_layoutcommit_outstanding(inode))
 		return 0;
 
-	/* Note kzalloc ensures data->res.seq_res.sr_slot == NULL */
-	data = kzalloc(sizeof(*data), GFP_NOFS);
-	if (!data) {
-		status = -ENOMEM;
-		goto out;
-	}
-
-	if (!test_bit(NFS_INO_LAYOUTCOMMIT, &nfsi->flags))
-		goto out_free;
+	dprintk("--> %s inode %lu\n", __func__, inode->i_ino);
 
+	status = -EAGAIN;
 	if (test_and_set_bit(NFS_INO_LAYOUTCOMMITTING, &nfsi->flags)) {
-		if (!sync) {
-			status = -EAGAIN;
-			goto out_free;
-		}
-		status = wait_on_bit_lock(&nfsi->flags, NFS_INO_LAYOUTCOMMITTING,
-					nfs_wait_bit_killable, TASK_KILLABLE);
+		if (!sync)
+			goto out;
+		status = wait_on_bit_lock(&nfsi->flags,
+				NFS_INO_LAYOUTCOMMITTING,
+				nfs_wait_bit_killable,
+				TASK_KILLABLE);
 		if (status)
-			goto out_free;
+			goto out;
 	}
 
-	INIT_LIST_HEAD(&data->lseg_list);
+	status = -ENOMEM;
+	/* Note kzalloc ensures data->res.seq_res.sr_slot == NULL */
+	data = kzalloc(sizeof(*data), GFP_NOFS);
+	if (!data)
+		goto clear_layoutcommitting;
+
+	status = 0;
 	spin_lock(&inode->i_lock);
-	if (!test_and_clear_bit(NFS_INO_LAYOUTCOMMIT, &nfsi->flags)) {
-		clear_bit(NFS_INO_LAYOUTCOMMITTING, &nfsi->flags);
-		spin_unlock(&inode->i_lock);
-		wake_up_bit(&nfsi->flags, NFS_INO_LAYOUTCOMMITTING);
-		goto out_free;
-	}
+	if (!test_and_clear_bit(NFS_INO_LAYOUTCOMMIT, &nfsi->flags))
+		goto out_unlock;
 
+	INIT_LIST_HEAD(&data->lseg_list);
 	pnfs_list_write_lseg(inode, &data->lseg_list);
 
 	end_pos = nfsi->layout->plh_lwb;
@@ -1940,8 +1940,11 @@ out:
 		mark_inode_dirty_sync(inode);
 	dprintk("<-- %s status %d\n", __func__, status);
 	return status;
-out_free:
+out_unlock:
+	spin_unlock(&inode->i_lock);
 	kfree(data);
+clear_layoutcommitting:
+	pnfs_clear_layoutcommitting(inode);
 	goto out;
 }
 
diff --git a/fs/nfs/pnfs.h b/fs/nfs/pnfs.h
index a4f41810a7f..02379390977 100644
--- a/fs/nfs/pnfs.h
+++ b/fs/nfs/pnfs.h
@@ -359,6 +359,15 @@ pnfs_ld_layoutret_on_setattr(struct inode *inode)
 		PNFS_LAYOUTRET_ON_SETATTR;
 }
 
+static inline bool
+pnfs_layoutcommit_outstanding(struct inode *inode)
+{
+	struct nfs_inode *nfsi = NFS_I(inode);
+
+	return test_bit(NFS_INO_LAYOUTCOMMIT, &nfsi->flags) != 0 ||
+		test_bit(NFS_INO_LAYOUTCOMMITTING, &nfsi->flags) != 0;
+}
+
 static inline int pnfs_return_layout(struct inode *ino)
 {
 	struct nfs_inode *nfsi = NFS_I(ino);
@@ -515,6 +524,13 @@ pnfs_use_threshold(struct nfs4_threshold **dst, struct nfs4_threshold *src,
 	return false;
 }
 
+static inline bool
+pnfs_layoutcommit_outstanding(struct inode *inode)
+{
+	return false;
+}
+
+
 static inline struct nfs4_threshold *pnfs_mdsthreshold_alloc(void)
 {
 	return NULL;
diff --git a/fs/nfs/read.c b/fs/nfs/read.c
index 31db5c366b8..411aedda14b 100644
--- a/fs/nfs/read.c
+++ b/fs/nfs/read.c
@@ -163,9 +163,9 @@ static void nfs_readpage_release(struct nfs_page *req)
 
 	unlock_page(req->wb_page);
 
-	dprintk("NFS: read done (%s/%Ld %d@%Ld)\n",
+	dprintk("NFS: read done (%s/%Lu %d@%Ld)\n",
 			req->wb_context->dentry->d_inode->i_sb->s_id,
-			(long long)NFS_FILEID(req->wb_context->dentry->d_inode),
+			(unsigned long long)NFS_FILEID(req->wb_context->dentry->d_inode),
 			req->wb_bytes,
 			(long long)req_offset(req));
 	nfs_release_request(req);
@@ -228,11 +228,11 @@ int nfs_initiate_read(struct rpc_clnt *clnt,
 	/* Set up the initial task struct. */
 	NFS_PROTO(inode)->read_setup(data, &msg);
 
-	dprintk("NFS: %5u initiated read call (req %s/%lld, %u bytes @ "
+	dprintk("NFS: %5u initiated read call (req %s/%llu, %u bytes @ "
 			"offset %llu)\n",
 			data->task.tk_pid,
 			inode->i_sb->s_id,
-			(long long)NFS_FILEID(inode),
+			(unsigned long long)NFS_FILEID(inode),
 			data->args.count,
 			(unsigned long long)data->args.offset);
 
@@ -630,9 +630,9 @@ int nfs_readpages(struct file *filp, struct address_space *mapping,
 	unsigned long npages;
 	int ret = -ESTALE;
 
-	dprintk("NFS: nfs_readpages (%s/%Ld %d)\n",
+	dprintk("NFS: nfs_readpages (%s/%Lu %d)\n",
 			inode->i_sb->s_id,
-			(long long)NFS_FILEID(inode),
+			(unsigned long long)NFS_FILEID(inode),
 			nr_pages);
 	nfs_inc_stats(inode, NFSIOS_VFSREADPAGES);
 
diff --git a/fs/nfs/write.c b/fs/nfs/write.c
index c1d548211c3..a44a87268a6 100644
--- a/fs/nfs/write.c
+++ b/fs/nfs/write.c
@@ -922,19 +922,20 @@ out:
  * extend the write to cover the entire page in order to avoid fragmentation
  * inefficiencies.
  *
- * If the file is opened for synchronous writes or if we have a write delegation
- * from the server then we can just skip the rest of the checks.
+ * If the file is opened for synchronous writes then we can just skip the rest
+ * of the checks.
  */
 static int nfs_can_extend_write(struct file *file, struct page *page, struct inode *inode)
 {
 	if (file->f_flags & O_DSYNC)
 		return 0;
+	if (!nfs_write_pageuptodate(page, inode))
+		return 0;
 	if (NFS_PROTO(inode)->have_delegation(inode, FMODE_WRITE))
 		return 1;
-	if (nfs_write_pageuptodate(page, inode) && (inode->i_flock == NULL ||
-			(inode->i_flock->fl_start == 0 &&
+	if (inode->i_flock == NULL || (inode->i_flock->fl_start == 0 &&
 			inode->i_flock->fl_end == OFFSET_MAX &&
-			inode->i_flock->fl_type != F_RDLCK)))
+			inode->i_flock->fl_type != F_RDLCK))
 		return 1;
 	return 0;
 }
@@ -1013,10 +1014,10 @@ int nfs_initiate_write(struct rpc_clnt *clnt,
 	NFS_PROTO(inode)->write_setup(data, &msg);
 
 	dprintk("NFS: %5u initiated write call "
-		"(req %s/%lld, %u bytes @ offset %llu)\n",
+		"(req %s/%llu, %u bytes @ offset %llu)\n",
 		data->task.tk_pid,
 		inode->i_sb->s_id,
-		(long long)NFS_FILEID(inode),
+		(unsigned long long)NFS_FILEID(inode),
 		data->args.count,
 		(unsigned long long)data->args.offset);
 
@@ -1606,9 +1607,9 @@ static void nfs_commit_release_pages(struct nfs_commit_data *data)
 		nfs_list_remove_request(req);
 		nfs_clear_page_commit(req->wb_page);
 
-		dprintk("NFS:       commit (%s/%lld %d@%lld)",
+		dprintk("NFS:       commit (%s/%llu %d@%lld)",
 			req->wb_context->dentry->d_sb->s_id,
-			(long long)NFS_FILEID(req->wb_context->dentry->d_inode),
+			(unsigned long long)NFS_FILEID(req->wb_context->dentry->d_inode),
 			req->wb_bytes,
 			(long long)req_offset(req));
 		if (status < 0) {