1 files changed, 282 insertions, 375 deletions

diff --git a/fs/nfsd/vfs.c b/fs/nfsd/vfs.c
index c22ad0532e8e..f650afedd67f 100644
--- a/fs/nfsd/vfs.c
+++ b/fs/nfsd/vfs.c
@@ -199,27 +199,13 @@ nfsd_lookup_dentry(struct svc_rqst *rqstp, struct svc_fh *fhp,
 				goto out_nfserr;
 		}
 	} else {
-		/*
-		 * In the nfsd4_open() case, this may be held across
-		 * subsequent open and delegation acquisition which may
-		 * need to take the child's i_mutex:
-		 */
-		fh_lock_nested(fhp, I_MUTEX_PARENT);
-		dentry = lookup_one_len(name, dparent, len);
+		dentry = lookup_one_len_unlocked(name, dparent, len);
 		host_err = PTR_ERR(dentry);
 		if (IS_ERR(dentry))
 			goto out_nfserr;
 		if (nfsd_mountpoint(dentry, exp)) {
-			/*
-			 * We don't need the i_mutex after all.  It's
-			 * still possible we could open this (regular
-			 * files can be mountpoints too), but the
-			 * i_mutex is just there to prevent renames of
-			 * something that we might be about to delegate,
-			 * and a mountpoint won't be renamed:
-			 */
-			fh_unlock(fhp);
-			if ((host_err = nfsd_cross_mnt(rqstp, &dentry, &exp))) {
+			host_err = nfsd_cross_mnt(rqstp, &dentry, &exp);
+			if (host_err) {
 				dput(dentry);
 				goto out_nfserr;
 			}
@@ -234,7 +220,15 @@ out_nfserr:
 	return nfserrno(host_err);
 }
 
-/*
+/**
+ * nfsd_lookup - look up a single path component for nfsd
+ *
+ * @rqstp:   the request context
+ * @fhp:     the file handle of the directory
+ * @name:    the component name, or %NULL to look up parent
+ * @len:     length of name to examine
+ * @resfh:   pointer to pre-initialised filehandle to hold result.
+ *
  * Look up one component of a pathname.
  * N.B. After this call _both_ fhp and resfh need an fh_put
  *
@@ -244,11 +238,11 @@ out_nfserr:
  * returned. Otherwise the covered directory is returned.
  * NOTE: this mountpoint crossing is not supported properly by all
  *   clients and is explicitly disallowed for NFSv3
- *      NeilBrown <neilb@cse.unsw.edu.au>
+ *
  */
 __be32
 nfsd_lookup(struct svc_rqst *rqstp, struct svc_fh *fhp, const char *name,
-				unsigned int len, struct svc_fh *resfh)
+	    unsigned int len, struct svc_fh *resfh)
 {
 	struct svc_export	*exp;
 	struct dentry		*dentry;
@@ -306,6 +300,10 @@ commit_metadata(struct svc_fh *fhp)
 static void
 nfsd_sanitize_attrs(struct inode *inode, struct iattr *iap)
 {
+	/* Ignore mode updates on symlinks */
+	if (S_ISLNK(inode->i_mode))
+		iap->ia_valid &= ~ATTR_MODE;
+
 	/* sanitize the mode change */
 	if (iap->ia_valid & ATTR_MODE) {
 		iap->ia_mode &= S_IALLUGO;
@@ -345,21 +343,77 @@ nfsd_get_write_access(struct svc_rqst *rqstp, struct svc_fh *fhp,
 	return nfserrno(get_write_access(inode));
 }
 
-/*
- * Set various file attributes.  After this call fhp needs an fh_put.
+static int __nfsd_setattr(struct dentry *dentry, struct iattr *iap)
+{
+	int host_err;
+
+	if (iap->ia_valid & ATTR_SIZE) {
+		/*
+		 * RFC5661, Section 18.30.4:
+		 *   Changing the size of a file with SETATTR indirectly
+		 *   changes the time_modify and change attributes.
+		 *
+		 * (and similar for the older RFCs)
+		 */
+		struct iattr size_attr = {
+			.ia_valid	= ATTR_SIZE | ATTR_CTIME | ATTR_MTIME,
+			.ia_size	= iap->ia_size,
+		};
+
+		if (iap->ia_size < 0)
+			return -EFBIG;
+
+		host_err = notify_change(&init_user_ns, dentry, &size_attr, NULL);
+		if (host_err)
+			return host_err;
+		iap->ia_valid &= ~ATTR_SIZE;
+
+		/*
+		 * Avoid the additional setattr call below if the only other
+		 * attribute that the client sends is the mtime, as we update
+		 * it as part of the size change above.
+		 */
+		if ((iap->ia_valid & ~ATTR_MTIME) == 0)
+			return 0;
+	}
+
+	if (!iap->ia_valid)
+		return 0;
+
+	iap->ia_valid |= ATTR_CTIME;
+	return notify_change(&init_user_ns, dentry, iap, NULL);
+}
+
+/**
+ * nfsd_setattr - Set various file attributes.
+ * @rqstp: controlling RPC transaction
+ * @fhp: filehandle of target
+ * @attr: attributes to set
+ * @check_guard: set to 1 if guardtime is a valid timestamp
+ * @guardtime: do not act if ctime.tv_sec does not match this timestamp
+ *
+ * This call may adjust the contents of @attr (in particular, this
+ * call may change the bits in the na_iattr.ia_valid field).
+ *
+ * Returns nfs_ok on success, otherwise an NFS status code is
+ * returned. Caller must release @fhp by calling fh_put in either
+ * case.
  */
 __be32
-nfsd_setattr(struct svc_rqst *rqstp, struct svc_fh *fhp, struct iattr *iap,
+nfsd_setattr(struct svc_rqst *rqstp, struct svc_fh *fhp,
+	     struct nfsd_attrs *attr,
 	     int check_guard, time64_t guardtime)
 {
 	struct dentry	*dentry;
 	struct inode	*inode;
+	struct iattr	*iap = attr->na_iattr;
 	int		accmode = NFSD_MAY_SATTR;
 	umode_t		ftype = 0;
 	__be32		err;
 	int		host_err;
 	bool		get_write_count;
 	bool		size_change = (iap->ia_valid & ATTR_SIZE);
+	int		retries;
 
 	if (iap->ia_valid & ATTR_SIZE) {
 		accmode |= NFSD_MAY_WRITE|NFSD_MAY_OWNER_OVERRIDE;
@@ -395,13 +449,6 @@ nfsd_setattr(struct svc_rqst *rqstp, struct svc_fh *fhp, struct iattr *iap,
 	dentry = fhp->fh_dentry;
 	inode = d_inode(dentry);
 
-	/* Ignore any mode updates on symlinks */
-	if (S_ISLNK(inode->i_mode))
-		iap->ia_valid &= ~ATTR_MODE;
-
-	if (!iap->ia_valid)
-		return 0;
-
 	nfsd_sanitize_attrs(inode, iap);
 
 	if (check_guard && guardtime != inode->i_ctime.tv_sec)
@@ -420,43 +467,27 @@ nfsd_setattr(struct svc_rqst *rqstp, struct svc_fh *fhp, struct iattr *iap,
 			return err;
 	}
 
-	fh_lock(fhp);
-	if (size_change) {
-		/*
-		 * RFC5661, Section 18.30.4:
-		 *   Changing the size of a file with SETATTR indirectly
-		 *   changes the time_modify and change attributes.
-		 *
-		 * (and similar for the older RFCs)
-		 */
-		struct iattr size_attr = {
-			.ia_valid	= ATTR_SIZE | ATTR_CTIME | ATTR_MTIME,
-			.ia_size	= iap->ia_size,
-		};
-
-		host_err = -EFBIG;
-		if (iap->ia_size < 0)
-			goto out_unlock;
-
-		host_err = notify_change(&init_user_ns, dentry, &size_attr, NULL);
-		if (host_err)
-			goto out_unlock;
-		iap->ia_valid &= ~ATTR_SIZE;
-
-		/*
-		 * Avoid the additional setattr call below if the only other
-		 * attribute that the client sends is the mtime, as we update
-		 * it as part of the size change above.
-		 */
-		if ((iap->ia_valid & ~ATTR_MTIME) == 0)
-			goto out_unlock;
+	inode_lock(inode);
+	for (retries = 1;;) {
+		host_err = __nfsd_setattr(dentry, iap);
+		if (host_err != -EAGAIN || !retries--)
+			break;
+		if (!nfsd_wait_for_delegreturn(rqstp, inode))
+			break;
 	}
-
-	iap->ia_valid |= ATTR_CTIME;
-	host_err = notify_change(&init_user_ns, dentry, iap, NULL);
-
-out_unlock:
-	fh_unlock(fhp);
+	if (attr->na_seclabel && attr->na_seclabel->len)
+		attr->na_labelerr = security_inode_setsecctx(dentry,
+			attr->na_seclabel->data, attr->na_seclabel->len);
+	if (IS_ENABLED(CONFIG_FS_POSIX_ACL) && attr->na_pacl)
+		attr->na_aclerr = set_posix_acl(&init_user_ns,
+						inode, ACL_TYPE_ACCESS,
+						attr->na_pacl);
+	if (IS_ENABLED(CONFIG_FS_POSIX_ACL) &&
+	    !attr->na_aclerr && attr->na_dpacl && S_ISDIR(inode->i_mode))
+		attr->na_aclerr = set_posix_acl(&init_user_ns,
+						inode, ACL_TYPE_DEFAULT,
+						attr->na_dpacl);
+	inode_unlock(inode);
 	if (size_change)
 		put_write_access(inode);
 out:
@@ -494,32 +525,6 @@ int nfsd4_is_junction(struct dentry *dentry)
 		return 0;
 	return 1;
 }
-#ifdef CONFIG_NFSD_V4_SECURITY_LABEL
-__be32 nfsd4_set_nfs4_label(struct svc_rqst *rqstp, struct svc_fh *fhp,
-		struct xdr_netobj *label)
-{
-	__be32 error;
-	int host_error;
-	struct dentry *dentry;
-
-	error = fh_verify(rqstp, fhp, 0 /* S_IFREG */, NFSD_MAY_SATTR);
-	if (error)
-		return error;
-
-	dentry = fhp->fh_dentry;
-
-	inode_lock(d_inode(dentry));
-	host_error = security_inode_setsecctx(dentry, label->data, label->len);
-	inode_unlock(d_inode(dentry));
-	return nfserrno(host_error);
-}
-#else
-__be32 nfsd4_set_nfs4_label(struct svc_rqst *rqstp, struct svc_fh *fhp,
-		struct xdr_netobj *label)
-{
-	return nfserr_notsupp;
-}
-#endif
 
 static struct nfsd4_compound_state *nfsd4_get_cstate(struct svc_rqst *rqstp)
 {
@@ -577,6 +582,7 @@ out_err:
 ssize_t nfsd_copy_file_range(struct file *src, u64 src_pos, struct file *dst,
 			     u64 dst_pos, u64 count)
 {
+	ssize_t ret;
 
 	/*
 	 * Limit copy to 4MB to prevent indefinitely blocking an nfsd
@@ -587,7 +593,12 @@ ssize_t nfsd_copy_file_range(struct file *src, u64 src_pos, struct file *dst,
 	 * limit like this and pipeline multiple COPY requests.
 	 */
 	count = min_t(u64, count, 1 << 22);
-	return vfs_copy_file_range(src, src_pos, dst, dst_pos, count, 0);
+	ret = vfs_copy_file_range(src, src_pos, dst, dst_pos, count, 0);
+
+	if (ret == -EOPNOTSUPP || ret == -EXDEV)
+		ret = generic_copy_file_range(src, src_pos, dst, dst_pos,
+					      count, 0);
+	return ret;
 }
 
 __be32 nfsd4_vfs_fallocate(struct svc_rqst *rqstp, struct svc_fh *fhp,
@@ -827,14 +838,23 @@ retry:
 	return err;
 }
 
+/**
+ * nfsd_open_verified - Open a regular file for the filecache
+ * @rqstp: RPC request
+ * @fhp: NFS filehandle of the file to open
+ * @may_flags: internal permission flags
+ * @filp: OUT: open "struct file *"
+ *
+ * Returns an nfsstat value in network byte order.
+ */
 __be32
-nfsd_open_verified(struct svc_rqst *rqstp, struct svc_fh *fhp, umode_t type,
-		int may_flags, struct file **filp)
+nfsd_open_verified(struct svc_rqst *rqstp, struct svc_fh *fhp, int may_flags,
+		   struct file **filp)
 {
 	__be32 err;
 
 	validate_process_creds();
-	err = __nfsd_open(rqstp, fhp, type, may_flags, filp);
+	err = __nfsd_open(rqstp, fhp, S_IFREG, may_flags, filp);
 	validate_process_creds();
 	return err;
 }
@@ -849,17 +869,15 @@ nfsd_splice_actor(struct pipe_inode_info *pipe, struct pipe_buffer *buf,
 		  struct splice_desc *sd)
 {
 	struct svc_rqst *rqstp = sd->u.data;
-	struct page **pp = rqstp->rq_next_page;
-	struct page *page = buf->page;
-
-	if (rqstp->rq_res.page_len == 0) {
-		svc_rqst_replace_page(rqstp, page);
-		rqstp->rq_res.page_base = buf->offset;
-	} else if (page != pp[-1]) {
-		svc_rqst_replace_page(rqstp, page);
-	}
+	struct page *page = buf->page;	// may be a compound one
+	unsigned offset = buf->offset;
+
+	page += offset / PAGE_SIZE;
+	for (int i = sd->len; i > 0; i -= PAGE_SIZE)
+		svc_rqst_replace_page(rqstp, page++);
+	if (rqstp->rq_res.page_len == 0)	// first call
+		rqstp->rq_res.page_base = offset % PAGE_SIZE;
 	rqstp->rq_res.page_len += sd->len;
-
 	return sd->len;
 }
 
@@ -1170,6 +1188,7 @@ nfsd_commit(struct svc_rqst *rqstp, struct svc_fh *fhp, u64 offset,
 			nfsd_copy_write_verifier(verf, nn);
 			err2 = filemap_check_wb_err(nf->nf_file->f_mapping,
 						    since);
+			err = nfserrno(err2);
 			break;
 		case -EINVAL:
 			err = nfserr_notsupp;
@@ -1177,8 +1196,8 @@ nfsd_commit(struct svc_rqst *rqstp, struct svc_fh *fhp, u64 offset,
 		default:
 			nfsd_reset_write_verifier(nn);
 			trace_nfsd_writeverf_reset(nn, rqstp, err2);
+			err = nfserrno(err2);
 		}
-		err = nfserrno(err2);
 	} else
 		nfsd_copy_write_verifier(verf, nn);
 
@@ -1187,14 +1206,27 @@ out:
 	return err;
 }
 
-static __be32
-nfsd_create_setattr(struct svc_rqst *rqstp, struct svc_fh *resfhp,
-			struct iattr *iap)
+/**
+ * nfsd_create_setattr - Set a created file's attributes
+ * @rqstp: RPC transaction being executed
+ * @fhp: NFS filehandle of parent directory
+ * @resfhp: NFS filehandle of new object
+ * @attrs: requested attributes of new object
+ *
+ * Returns nfs_ok on success, or an nfsstat in network byte order.
+ */
+__be32
+nfsd_create_setattr(struct svc_rqst *rqstp, struct svc_fh *fhp,
+		    struct svc_fh *resfhp, struct nfsd_attrs *attrs)
 {
+	struct iattr *iap = attrs->na_iattr;
+	__be32 status;
+
 	/*
-	 * Mode has already been set earlier in create:
+	 * Mode has already been set by file creation.
 	 */
 	iap->ia_valid &= ~ATTR_MODE;
+
 	/*
 	 * Setting uid/gid works only for root.  Irix appears to
 	 * send along the gid on create when it tries to implement
@@ -1202,10 +1234,31 @@ nfsd_create_setattr(struct svc_rqst *rqstp, struct svc_fh *resfhp,
 	 */
 	if (!uid_eq(current_fsuid(), GLOBAL_ROOT_UID))
 		iap->ia_valid &= ~(ATTR_UID|ATTR_GID);
+
+	/*
+	 * Callers expect new file metadata to be committed even
+	 * if the attributes have not changed.
+	 */
 	if (iap->ia_valid)
-		return nfsd_setattr(rqstp, resfhp, iap, 0, (time64_t)0);
-	/* Callers expect file metadata to be committed here */
-	return nfserrno(commit_metadata(resfhp));
+		status = nfsd_setattr(rqstp, resfhp, attrs, 0, (time64_t)0);
+	else
+		status = nfserrno(commit_metadata(resfhp));
+
+	/*
+	 * Transactional filesystems had a chance to commit changes
+	 * for both parent and child simultaneously making the
+	 * following commit_metadata a noop in many cases.
+	 */
+	if (!status)
+		status = nfserrno(commit_metadata(fhp));
+
+	/*
+	 * Update the new filehandle to pick up the new attributes.
+	 */
+	if (!status)
+		status = fh_update(resfhp);
+
+	return status;
 }
 
 /* HPUX client sometimes creates a file in mode 000, and sets size to 0.
@@ -1226,26 +1279,19 @@ nfsd_check_ignore_resizing(struct iattr *iap)
 /* The parent directory should already be locked: */
 __be32
 nfsd_create_locked(struct svc_rqst *rqstp, struct svc_fh *fhp,
-		char *fname, int flen, struct iattr *iap,
-		int type, dev_t rdev, struct svc_fh *resfhp)
+		   struct nfsd_attrs *attrs,
+		   int type, dev_t rdev, struct svc_fh *resfhp)
 {
 	struct dentry	*dentry, *dchild;
 	struct inode	*dirp;
+	struct iattr	*iap = attrs->na_iattr;
 	__be32		err;
-	__be32		err2;
 	int		host_err;
 
 	dentry = fhp->fh_dentry;
 	dirp = d_inode(dentry);
 
 	dchild = dget(resfhp->fh_dentry);
-	if (!fhp->fh_locked) {
-		WARN_ONCE(1, "nfsd_create: parent %pd2 not locked!\n",
-				dentry);
-		err = nfserr_io;
-		goto out;
-	}
-
 	err = nfsd_permission(rqstp, fhp->fh_export, dentry, NFSD_MAY_CREATE);
 	if (err)
 		goto out;
@@ -1305,22 +1351,8 @@ nfsd_create_locked(struct svc_rqst *rqstp, struct svc_fh *fhp,
 	if (host_err < 0)
 		goto out_nfserr;
 
-	err = nfsd_create_setattr(rqstp, resfhp, iap);
+	err = nfsd_create_setattr(rqstp, fhp, resfhp, attrs);
 
-	/*
-	 * nfsd_create_setattr already committed the child.  Transactional
-	 * filesystems had a chance to commit changes for both parent and
-	 * child simultaneously making the following commit_metadata a
-	 * noop.
-	 */
-	err2 = nfserrno(commit_metadata(fhp));
-	if (err2)
-		err = err2;
-	/*
-	 * Update the file handle to get the new inode info.
-	 */
-	if (!err)
-		err = fh_update(resfhp);
 out:
 	dput(dchild);
 	return err;
@@ -1338,8 +1370,8 @@ out_nfserr:
  */
 __be32
 nfsd_create(struct svc_rqst *rqstp, struct svc_fh *fhp,
-		char *fname, int flen, struct iattr *iap,
-		int type, dev_t rdev, struct svc_fh *resfhp)
+	    char *fname, int flen, struct nfsd_attrs *attrs,
+	    int type, dev_t rdev, struct svc_fh *resfhp)
 {
 	struct dentry	*dentry, *dchild = NULL;
 	__be32		err;
@@ -1358,11 +1390,13 @@ nfsd_create(struct svc_rqst *rqstp, struct svc_fh *fhp,
 	if (host_err)
 		return nfserrno(host_err);
 
-	fh_lock_nested(fhp, I_MUTEX_PARENT);
+	inode_lock_nested(dentry->d_inode, I_MUTEX_PARENT);
 	dchild = lookup_one_len(fname, dentry, flen);
 	host_err = PTR_ERR(dchild);
-	if (IS_ERR(dchild))
-		return nfserrno(host_err);
+	if (IS_ERR(dchild)) {
+		err = nfserrno(host_err);
+		goto out_unlock;
+	}
 	err = fh_compose(resfhp, fhp->fh_export, dchild, fhp);
 	/*
 	 * We unconditionally drop our ref to dchild as fh_compose will have
@@ -1370,175 +1404,13 @@ nfsd_create(struct svc_rqst *rqstp, struct svc_fh *fhp,
 	 */
 	dput(dchild);
 	if (err)
-		return err;
-	return nfsd_create_locked(rqstp, fhp, fname, flen, iap, type,
-					rdev, resfhp);
-}
-
-/*
- * NFSv3 and NFSv4 version of nfsd_create
- */
-__be32
-do_nfsd_create(struct svc_rqst *rqstp, struct svc_fh *fhp,
-		char *fname, int flen, struct iattr *iap,
-		struct svc_fh *resfhp, int createmode, u32 *verifier,
-	        bool *truncp, bool *created)
-{
-	struct dentry	*dentry, *dchild = NULL;
-	struct inode	*dirp;
-	__be32		err;
-	int		host_err;
-	__u32		v_mtime=0, v_atime=0;
-
-	err = nfserr_perm;
-	if (!flen)
-		goto out;
-	err = nfserr_exist;
-	if (isdotent(fname, flen))
-		goto out;
-	if (!(iap->ia_valid & ATTR_MODE))
-		iap->ia_mode = 0;
-	err = fh_verify(rqstp, fhp, S_IFDIR, NFSD_MAY_EXEC);
-	if (err)
-		goto out;
-
-	dentry = fhp->fh_dentry;
-	dirp = d_inode(dentry);
-
-	host_err = fh_want_write(fhp);
-	if (host_err)
-		goto out_nfserr;
-
-	fh_lock_nested(fhp, I_MUTEX_PARENT);
-
-	/*
-	 * Compose the response file handle.
-	 */
-	dchild = lookup_one_len(fname, dentry, flen);
-	host_err = PTR_ERR(dchild);
-	if (IS_ERR(dchild))
-		goto out_nfserr;
-
-	/* If file doesn't exist, check for permissions to create one */
-	if (d_really_is_negative(dchild)) {
-		err = fh_verify(rqstp, fhp, S_IFDIR, NFSD_MAY_CREATE);
-		if (err)
-			goto out;
-	}
-
-	err = fh_compose(resfhp, fhp->fh_export, dchild, fhp);
-	if (err)
-		goto out;
-
-	if (nfsd_create_is_exclusive(createmode)) {
-		/* solaris7 gets confused (bugid 4218508) if these have
-		 * the high bit set, as do xfs filesystems without the
-		 * "bigtime" feature.  So just clear the high bits. If this is
-		 * ever changed to use different attrs for storing the
-		 * verifier, then do_open_lookup() will also need to be fixed
-		 * accordingly.
-		 */
-		v_mtime = verifier[0]&0x7fffffff;
-		v_atime = verifier[1]&0x7fffffff;
-	}
-	
-	if (d_really_is_positive(dchild)) {
-		err = 0;
-
-		switch (createmode) {
-		case NFS3_CREATE_UNCHECKED:
-			if (! d_is_reg(dchild))
-				goto out;
-			else if (truncp) {
-				/* in nfsv4, we need to treat this case a little
-				 * differently.  we don't want to truncate the
-				 * file now; this would be wrong if the OPEN
-				 * fails for some other reason.  furthermore,
-				 * if the size is nonzero, we should ignore it
-				 * according to spec!
-				 */
-				*truncp = (iap->ia_valid & ATTR_SIZE) && !iap->ia_size;
-			}
-			else {
-				iap->ia_valid &= ATTR_SIZE;
-				goto set_attr;
-			}
-			break;
-		case NFS3_CREATE_EXCLUSIVE:
-			if (   d_inode(dchild)->i_mtime.tv_sec == v_mtime
-			    && d_inode(dchild)->i_atime.tv_sec == v_atime
-			    && d_inode(dchild)->i_size  == 0 ) {
-				if (created)
-					*created = true;
-				break;
-			}
-			fallthrough;
-		case NFS4_CREATE_EXCLUSIVE4_1:
-			if (   d_inode(dchild)->i_mtime.tv_sec == v_mtime
-			    && d_inode(dchild)->i_atime.tv_sec == v_atime
-			    && d_inode(dchild)->i_size  == 0 ) {
-				if (created)
-					*created = true;
-				goto set_attr;
-			}
-			fallthrough;
-		case NFS3_CREATE_GUARDED:
-			err = nfserr_exist;
-		}
-		fh_drop_write(fhp);
-		goto out;
-	}
-
-	if (!IS_POSIXACL(dirp))
-		iap->ia_mode &= ~current_umask();
-
-	host_err = vfs_create(&init_user_ns, dirp, dchild, iap->ia_mode, true);
-	if (host_err < 0) {
-		fh_drop_write(fhp);
-		goto out_nfserr;
-	}
-	if (created)
-		*created = true;
-
-	nfsd_check_ignore_resizing(iap);
-
-	if (nfsd_create_is_exclusive(createmode)) {
-		/* Cram the verifier into atime/mtime */
-		iap->ia_valid = ATTR_MTIME|ATTR_ATIME
-			| ATTR_MTIME_SET|ATTR_ATIME_SET;
-		/* XXX someone who knows this better please fix it for nsec */ 
-		iap->ia_mtime.tv_sec = v_mtime;
-		iap->ia_atime.tv_sec = v_atime;
-		iap->ia_mtime.tv_nsec = 0;
-		iap->ia_atime.tv_nsec = 0;
-	}
-
- set_attr:
-	err = nfsd_create_setattr(rqstp, resfhp, iap);
-
-	/*
-	 * nfsd_create_setattr already committed the child
-	 * (and possibly also the parent).
-	 */
-	if (!err)
-		err = nfserrno(commit_metadata(fhp));
-
-	/*
-	 * Update the filehandle to get the new inode info.
-	 */
-	if (!err)
-		err = fh_update(resfhp);
-
- out:
-	fh_unlock(fhp);
-	if (dchild && !IS_ERR(dchild))
-		dput(dchild);
-	fh_drop_write(fhp);
- 	return err;
- 
- out_nfserr:
-	err = nfserrno(host_err);
-	goto out;
+		goto out_unlock;
+	fh_fill_pre_attrs(fhp);
+	err = nfsd_create_locked(rqstp, fhp, attrs, type, rdev, resfhp);
+	fh_fill_post_attrs(fhp);
+out_unlock:
+	inode_unlock(dentry->d_inode);
+	return err;
 }
 
 /*
@@ -1579,15 +1451,25 @@ nfsd_readlink(struct svc_rqst *rqstp, struct svc_fh *fhp, char *buf, int *lenp)
 	return 0;
 }
 
-/*
- * Create a symlink and look up its inode
+/**
+ * nfsd_symlink - Create a symlink and look up its inode
+ * @rqstp: RPC transaction being executed
+ * @fhp: NFS filehandle of parent directory
+ * @fname: filename of the new symlink
+ * @flen: length of @fname
+ * @path: content of the new symlink (NUL-terminated)
+ * @attrs: requested attributes of new object
+ * @resfhp: NFS filehandle of new object
+ *
  * N.B. After this call _both_ fhp and resfhp need an fh_put
+ *
+ * Returns nfs_ok on success, or an nfsstat in network byte order.
  */
 __be32
 nfsd_symlink(struct svc_rqst *rqstp, struct svc_fh *fhp,
-				char *fname, int flen,
-				char *path,
-				struct svc_fh *resfhp)
+	     char *fname, int flen,
+	     char *path, struct nfsd_attrs *attrs,
+	     struct svc_fh *resfhp)
 {
 	struct dentry	*dentry, *dnew;
 	__be32		err, cerr;
@@ -1605,33 +1487,35 @@ nfsd_symlink(struct svc_rqst *rqstp, struct svc_fh *fhp,
 		goto out;
 
 	host_err = fh_want_write(fhp);
-	if (host_err)
-		goto out_nfserr;
+	if (host_err) {
+		err = nfserrno(host_err);
+		goto out;
+	}
 
-	fh_lock(fhp);
 	dentry = fhp->fh_dentry;
+	inode_lock_nested(dentry->d_inode, I_MUTEX_PARENT);
 	dnew = lookup_one_len(fname, dentry, flen);
-	host_err = PTR_ERR(dnew);
-	if (IS_ERR(dnew))
-		goto out_nfserr;
-
+	if (IS_ERR(dnew)) {
+		err = nfserrno(PTR_ERR(dnew));
+		inode_unlock(dentry->d_inode);
+		goto out_drop_write;
+	}
+	fh_fill_pre_attrs(fhp);
 	host_err = vfs_symlink(&init_user_ns, d_inode(dentry), dnew, path);
 	err = nfserrno(host_err);
-	fh_unlock(fhp);
+	cerr = fh_compose(resfhp, fhp->fh_export, dnew, fhp);
+	if (!err)
+		nfsd_create_setattr(rqstp, fhp, resfhp, attrs);
+	fh_fill_post_attrs(fhp);
+	inode_unlock(dentry->d_inode);
 	if (!err)
 		err = nfserrno(commit_metadata(fhp));
-
-	fh_drop_write(fhp);
-
-	cerr = fh_compose(resfhp, fhp->fh_export, dnew, fhp);
 	dput(dnew);
 	if (err==0) err = cerr;
+out_drop_write:
+	fh_drop_write(fhp);
 out:
 	return err;
-
-out_nfserr:
-	err = nfserrno(host_err);
-	goto out;
 }
 
 /*
@@ -1669,22 +1553,25 @@ nfsd_link(struct svc_rqst *rqstp, struct svc_fh *ffhp,
 		goto out;
 	}
 
-	fh_lock_nested(ffhp, I_MUTEX_PARENT);
 	ddir = ffhp->fh_dentry;
 	dirp = d_inode(ddir);
+	inode_lock_nested(dirp, I_MUTEX_PARENT);
 
 	dnew = lookup_one_len(name, ddir, len);
-	host_err = PTR_ERR(dnew);
-	if (IS_ERR(dnew))
-		goto out_nfserr;
+	if (IS_ERR(dnew)) {
+		err = nfserrno(PTR_ERR(dnew));
+		goto out_unlock;
+	}
 
 	dold = tfhp->fh_dentry;
 
 	err = nfserr_noent;
 	if (d_really_is_negative(dold))
 		goto out_dput;
+	fh_fill_pre_attrs(ffhp);
 	host_err = vfs_link(dold, &init_user_ns, dirp, dnew, NULL);
-	fh_unlock(ffhp);
+	fh_fill_post_attrs(ffhp);
+	inode_unlock(dirp);
 	if (!host_err) {
 		err = nfserrno(commit_metadata(ffhp));
 		if (!err)
@@ -1695,17 +1582,17 @@ nfsd_link(struct svc_rqst *rqstp, struct svc_fh *ffhp,
 		else
 			err = nfserrno(host_err);
 	}
-out_dput:
 	dput(dnew);
-out_unlock:
-	fh_unlock(ffhp);
+out_drop_write:
 	fh_drop_write(tfhp);
 out:
 	return err;
 
-out_nfserr:
-	err = nfserrno(host_err);
-	goto out_unlock;
+out_dput:
+	dput(dnew);
+out_unlock:
+	inode_unlock(dirp);
+	goto out_drop_write;
 }
 
 static void
@@ -1766,10 +1653,7 @@ retry:
 		goto out;
 	}
 
-	/* cannot use fh_lock as we need deadlock protective ordering
-	 * so do it by hand */
 	trap = lock_rename(tdentry, fdentry);
-	ffhp->fh_locked = tfhp->fh_locked = true;
 	fh_fill_pre_attrs(ffhp);
 	fh_fill_pre_attrs(tfhp);
 
@@ -1812,7 +1696,15 @@ retry:
 			.new_dir	= tdir,
 			.new_dentry	= ndentry,
 		};
-		host_err = vfs_rename(&rd);
+		int retries;
+
+		for (retries = 1;;) {
+			host_err = vfs_rename(&rd);
+			if (host_err != -EAGAIN || !retries--)
+				break;
+			if (!nfsd_wait_for_delegreturn(rqstp, d_inode(odentry)))
+				break;
+		}
 		if (!host_err) {
 			host_err = commit_metadata(tfhp);
 			if (!host_err)
@@ -1825,17 +1717,12 @@ retry:
 	dput(odentry);
  out_nfserr:
 	err = nfserrno(host_err);
-	/*
-	 * We cannot rely on fh_unlock on the two filehandles,
-	 * as that would do the wrong thing if the two directories
-	 * were the same, so again we do it by hand.
-	 */
+
 	if (!close_cached) {
 		fh_fill_post_attrs(ffhp);
 		fh_fill_post_attrs(tfhp);
 	}
 	unlock_rename(tdentry, fdentry);
-	ffhp->fh_locked = tfhp->fh_locked = false;
 	fh_drop_write(ffhp);
 
 	/*
@@ -1879,19 +1766,19 @@ nfsd_unlink(struct svc_rqst *rqstp, struct svc_fh *fhp, int type,
 	if (host_err)
 		goto out_nfserr;
 
-	fh_lock_nested(fhp, I_MUTEX_PARENT);
 	dentry = fhp->fh_dentry;
 	dirp = d_inode(dentry);
+	inode_lock_nested(dirp, I_MUTEX_PARENT);
 
 	rdentry = lookup_one_len(fname, dentry, flen);
 	host_err = PTR_ERR(rdentry);
 	if (IS_ERR(rdentry))
-		goto out_drop_write;
+		goto out_unlock;
 
 	if (d_really_is_negative(rdentry)) {
 		dput(rdentry);
 		host_err = -ENOENT;
-		goto out_drop_write;
+		goto out_unlock;
 	}
 	rinode = d_inode(rdentry);
 	ihold(rinode);
@@ -1899,15 +1786,26 @@ nfsd_unlink(struct svc_rqst *rqstp, struct svc_fh *fhp, int type,
 	if (!type)
 		type = d_inode(rdentry)->i_mode & S_IFMT;
 
+	fh_fill_pre_attrs(fhp);
 	if (type != S_IFDIR) {
+		int retries;
+
 		if (rdentry->d_sb->s_export_op->flags & EXPORT_OP_CLOSE_BEFORE_UNLINK)
 			nfsd_close_cached_files(rdentry);
-		host_err = vfs_unlink(&init_user_ns, dirp, rdentry, NULL);
+
+		for (retries = 1;;) {
+			host_err = vfs_unlink(&init_user_ns, dirp, rdentry, NULL);
+			if (host_err != -EAGAIN || !retries--)
+				break;
+			if (!nfsd_wait_for_delegreturn(rqstp, rinode))
+				break;
+		}
 	} else {
 		host_err = vfs_rmdir(&init_user_ns, dirp, rdentry);
 	}
+	fh_fill_post_attrs(fhp);
 
-	fh_unlock(fhp);
+	inode_unlock(dirp);
 	if (!host_err)
 		host_err = commit_metadata(fhp);
 	dput(rdentry);
@@ -1929,6 +1827,9 @@ out_nfserr:
 	}
 out:
 	return err;
+out_unlock:
+	inode_unlock(dirp);
+	goto out_drop_write;
 }
 
 /*
@@ -1953,7 +1854,7 @@ struct readdir_data {
 	int		full;
 };
 
-static int nfsd_buffered_filldir(struct dir_context *ctx, const char *name,
+static bool nfsd_buffered_filldir(struct dir_context *ctx, const char *name,
 				 int namlen, loff_t offset, u64 ino,
 				 unsigned int d_type)
 {
@@ -1965,7 +1866,7 @@ static int nfsd_buffered_filldir(struct dir_context *ctx, const char *name,
 	reclen = ALIGN(sizeof(struct buffered_dirent) + namlen, sizeof(u64));
 	if (buf->used + reclen > PAGE_SIZE) {
 		buf->full = 1;
-		return -EINVAL;
+		return false;
 	}
 
 	de->namlen = namlen;
@@ -1975,7 +1876,7 @@ static int nfsd_buffered_filldir(struct dir_context *ctx, const char *name,
 	memcpy(de->name, name, namlen);
 	buf->used += reclen;
 
-	return 0;
+	return true;
 }
 
 static __be32 nfsd_buffered_readdir(struct file *file, struct svc_fh *fhp,
@@ -2282,13 +2183,16 @@ out:
 	return err;
 }
 
-/*
- * Removexattr and setxattr need to call fh_lock to both lock the inode
- * and set the change attribute. Since the top-level vfs_removexattr
- * and vfs_setxattr calls already do their own inode_lock calls, call
- * the _locked variant. Pass in a NULL pointer for delegated_inode,
- * and let the client deal with NFS4ERR_DELAY (same as with e.g.
- * setattr and remove).
+/**
+ * nfsd_removexattr - Remove an extended attribute
+ * @rqstp: RPC transaction being executed
+ * @fhp: NFS filehandle of object with xattr to remove
+ * @name: name of xattr to remove (NUL-terminate)
+ *
+ * Pass in a NULL pointer for delegated_inode, and let the client deal
+ * with NFS4ERR_DELAY (same as with e.g. setattr and remove).
+ *
+ * Returns nfs_ok on success, or an nfsstat in network byte order.
  */
 __be32
 nfsd_removexattr(struct svc_rqst *rqstp, struct svc_fh *fhp, char *name)
@@ -2304,12 +2208,14 @@ nfsd_removexattr(struct svc_rqst *rqstp, struct svc_fh *fhp, char *name)
 	if (ret)
 		return nfserrno(ret);
 
-	fh_lock(fhp);
+	inode_lock(fhp->fh_dentry->d_inode);
+	fh_fill_pre_attrs(fhp);
 
 	ret = __vfs_removexattr_locked(&init_user_ns, fhp->fh_dentry,
 				       name, NULL);
 
-	fh_unlock(fhp);
+	fh_fill_post_attrs(fhp);
+	inode_unlock(fhp->fh_dentry->d_inode);
 	fh_drop_write(fhp);
 
 	return nfsd_xattr_errno(ret);
@@ -2329,12 +2235,13 @@ nfsd_setxattr(struct svc_rqst *rqstp, struct svc_fh *fhp, char *name,
 	ret = fh_want_write(fhp);
 	if (ret)
 		return nfserrno(ret);
-	fh_lock(fhp);
+	inode_lock(fhp->fh_dentry->d_inode);
+	fh_fill_pre_attrs(fhp);
 
 	ret = __vfs_setxattr_locked(&init_user_ns, fhp->fh_dentry, name, buf,
 				    len, flags, NULL);
-
-	fh_unlock(fhp);
+	fh_fill_post_attrs(fhp);
+	inode_unlock(fhp->fh_dentry->d_inode);
 	fh_drop_write(fhp);
 
 	return nfsd_xattr_errno(ret);