Merge branch 'nfsd-next' of git://git.linux-nfs.org/~bfields/linux.git

18 files changed, 269 insertions, 284 deletions

diff --git a/Documentation/filesystems/nfs/index.rst b/Documentation/filesystems/nfs/index.rst
index 65805624e39bf5..288d8ddb2bc6c3 100644
--- a/Documentation/filesystems/nfs/index.rst
+++ b/Documentation/filesystems/nfs/index.rst
@@ -11,3 +11,4 @@ NFS
    rpc-server-gss
    nfs41-server
    knfsd-stats
+   reexport
diff --git a/Documentation/filesystems/nfs/reexport.rst b/Documentation/filesystems/nfs/reexport.rst
new file mode 100644
index 00000000000000..ff9ae4a46530af
--- /dev/null
+++ b/Documentation/filesystems/nfs/reexport.rst
@@ -0,0 +1,113 @@
+Reexporting NFS filesystems
+===========================
+
+Overview
+--------
+
+It is possible to reexport an NFS filesystem over NFS.  However, this
+feature comes with a number of limitations.  Before trying it, we
+recommend some careful research to determine whether it will work for
+your purposes.
+
+A discussion of current known limitations follows.
+
+"fsid=" required, crossmnt broken
+---------------------------------
+
+We require the "fsid=" export option on any reexport of an NFS
+filesystem.  You can use "uuidgen -r" to generate a unique argument.
+
+The "crossmnt" export does not propagate "fsid=", so it will not allow
+traversing into further nfs filesystems; if you wish to export nfs
+filesystems mounted under the exported filesystem, you'll need to export
+them explicitly, assigning each its own unique "fsid= option.
+
+Reboot recovery
+---------------
+
+The NFS protocol's normal reboot recovery mechanisms don't work for the
+case when the reexport server reboots.  Clients will lose any locks
+they held before the reboot, and further IO will result in errors.
+Closing and reopening files should clear the errors.
+
+Filehandle limits
+-----------------
+
+If the original server uses an X byte filehandle for a given object, the
+reexport server's filehandle for the reexported object will be X+22
+bytes, rounded up to the nearest multiple of four bytes.
+
+The result must fit into the RFC-mandated filehandle size limits:
+
++-------+-----------+
+| NFSv2 |  32 bytes |
++-------+-----------+
+| NFSv3 |  64 bytes |
++-------+-----------+
+| NFSv4 | 128 bytes |
++-------+-----------+
+
+So, for example, you will only be able to reexport a filesystem over
+NFSv2 if the original server gives you filehandles that fit in 10
+bytes--which is unlikely.
+
+In general there's no way to know the maximum filehandle size given out
+by an NFS server without asking the server vendor.
+
+But the following table gives a few examples.  The first column is the
+typical length of the filehandle from a Linux server exporting the given
+filesystem, the second is the length after that nfs export is reexported
+by another Linux host:
+
++--------+-------------------+----------------+
+|        | filehandle length | after reexport |
++========+===================+================+
+| ext4:  | 28 bytes          | 52 bytes       |
++--------+-------------------+----------------+
+| xfs:   | 32 bytes          | 56 bytes       |
++--------+-------------------+----------------+
+| btrfs: | 40 bytes          | 64 bytes       |
++--------+-------------------+----------------+
+
+All will therefore fit in an NFSv3 or NFSv4 filehandle after reexport,
+but none are reexportable over NFSv2.
+
+Linux server filehandles are a bit more complicated than this, though;
+for example:
+
+        - The (non-default) "subtreecheck" export option generally
+          requires another 4 to 8 bytes in the filehandle.
+        - If you export a subdirectory of a filesystem (instead of
+          exporting the filesystem root), that also usually adds 4 to 8
+          bytes.
+        - If you export over NFSv2, knfsd usually uses a shorter
+          filesystem identifier that saves 8 bytes.
+        - The root directory of an export uses a filehandle that is
+          shorter.
+
+As you can see, the 128-byte NFSv4 filehandle is large enough that
+you're unlikely to have trouble using NFSv4 to reexport any filesystem
+exported from a Linux server.  In general, if the original server is
+something that also supports NFSv3, you're *probably* OK.  Re-exporting
+over NFSv3 may be dicier, and reexporting over NFSv2 will probably
+never work.
+
+For more details of Linux filehandle structure, the best reference is
+the source code and comments; see in particular:
+
+        - include/linux/exportfs.h:enum fid_type
+        - include/uapi/linux/nfsd/nfsfh.h:struct nfs_fhbase_new
+        - fs/nfsd/nfsfh.c:set_version_and_fsid_type
+        - fs/nfs/export.c:nfs_encode_fh
+
+Open DENY bits ignored
+----------------------
+
+NFS since NFSv4 supports ALLOW and DENY bits taken from Windows, which
+allow you, for example, to open a file in a mode which forbids other
+read opens or write opens. The Linux client doesn't use them, and the
+server's support has always been incomplete: they are enforced only
+against other NFS users, not against processes accessing the exported
+filesystem locally. A reexport server will also not pass them along to
+the original server, so they will not be enforced between clients of
+different reexport servers.
diff --git a/fs/nfsd/flexfilelayout.c b/fs/nfsd/flexfilelayout.c
index db7ef07ae50c9b..2e2f1d5e9f623c 100644
--- a/fs/nfsd/flexfilelayout.c
+++ b/fs/nfsd/flexfilelayout.c
@@ -61,7 +61,7 @@ nfsd4_ff_proc_layoutget(struct inode *inode, const struct svc_fh *fhp,
 		goto out_error;
 
 	fl->fh.size = fhp->fh_handle.fh_size;
-	memcpy(fl->fh.data, &fhp->fh_handle.fh_base, fl->fh.size);
+	memcpy(fl->fh.data, &fhp->fh_handle.fh_raw, fl->fh.size);
 
 	/* Give whole file layout segments */
 	seg->offset = 0;
diff --git a/fs/nfsd/lockd.c b/fs/nfsd/lockd.c
index 606fa155c28adf..46a7f9b813e527 100644
--- a/fs/nfsd/lockd.c
+++ b/fs/nfsd/lockd.c
@@ -35,7 +35,7 @@ nlm_fopen(struct svc_rqst *rqstp, struct nfs_fh *f, struct file **filp,
 	/* must initialize before using! but maxsize doesn't matter */
 	fh_init(&fh,0);
 	fh.fh_handle.fh_size = f->size;
-	memcpy((char*)&fh.fh_handle.fh_base, f->data, f->size);
+	memcpy(&fh.fh_handle.fh_raw, f->data, f->size);
 	fh.fh_export = NULL;
 
 	access = (mode == O_WRONLY) ? NFSD_MAY_WRITE : NFSD_MAY_READ;
diff --git a/fs/nfsd/nfs3xdr.c b/fs/nfsd/nfs3xdr.c
index 0a5ebc52e6a9cc..3d37923afb06cb 100644
--- a/fs/nfsd/nfs3xdr.c
+++ b/fs/nfsd/nfs3xdr.c
@@ -92,7 +92,7 @@ svcxdr_decode_nfs_fh3(struct xdr_stream *xdr, struct svc_fh *fhp)
 		return false;
 	fh_init(fhp, NFS3_FHSIZE);
 	fhp->fh_handle.fh_size = size;
-	memcpy(&fhp->fh_handle.fh_base, p, size);
+	memcpy(&fhp->fh_handle.fh_raw, p, size);
 
 	return true;
 }
@@ -131,7 +131,7 @@ svcxdr_encode_nfs_fh3(struct xdr_stream *xdr, const struct svc_fh *fhp)
 	*p++ = cpu_to_be32(size);
 	if (size)
 		p[XDR_QUADLEN(size) - 1] = 0;
-	memcpy(p, &fhp->fh_handle.fh_base, size);
+	memcpy(p, &fhp->fh_handle.fh_raw, size);
 
 	return true;
 }
diff --git a/fs/nfsd/nfs4callback.c b/fs/nfsd/nfs4callback.c
index 0f8b10f363e7f3..11f8715d92d63a 100644
--- a/fs/nfsd/nfs4callback.c
+++ b/fs/nfsd/nfs4callback.c
@@ -121,7 +121,7 @@ static void encode_nfs_fh4(struct xdr_stream *xdr, const struct knfsd_fh *fh)
 
 	BUG_ON(length > NFS4_FHSIZE);
 	p = xdr_reserve_space(xdr, 4 + length);
-	xdr_encode_opaque(p, &fh->fh_base, length);
+	xdr_encode_opaque(p, &fh->fh_raw, length);
 }
 
 /*
diff --git a/fs/nfsd/nfs4proc.c b/fs/nfsd/nfs4proc.c
index 486c5dba4b6502..3dc40c1d32bc6b 100644
--- a/fs/nfsd/nfs4proc.c
+++ b/fs/nfsd/nfs4proc.c
@@ -519,7 +519,7 @@ nfsd4_putfh(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
 
 	fh_put(&cstate->current_fh);
 	cstate->current_fh.fh_handle.fh_size = putfh->pf_fhlen;
-	memcpy(&cstate->current_fh.fh_handle.fh_base, putfh->pf_fhval,
+	memcpy(&cstate->current_fh.fh_handle.fh_raw, putfh->pf_fhval,
 	       putfh->pf_fhlen);
 	ret = fh_verify(rqstp, &cstate->current_fh, 0, NFSD_MAY_BYPASS_GSS);
 #ifdef CONFIG_NFSD_V4_2_INTER_SSC
@@ -1178,7 +1178,7 @@ extern void nfs_sb_deactive(struct super_block *sb);
 static __be32 nfsd4_ssc_setup_dul(struct nfsd_net *nn, char *ipaddr,
 		struct nfsd4_ssc_umount_item **retwork, struct vfsmount **ss_mnt)
 {
-	struct nfsd4_ssc_umount_item *ni = 0;
+	struct nfsd4_ssc_umount_item *ni = NULL;
 	struct nfsd4_ssc_umount_item *work = NULL;
 	struct nfsd4_ssc_umount_item *tmp;
 	DEFINE_WAIT(wait);
@@ -1383,7 +1383,7 @@ nfsd4_setup_inter_ssc(struct svc_rqst *rqstp,
 	s_fh = &cstate->save_fh;
 
 	copy->c_fh.size = s_fh->fh_handle.fh_size;
-	memcpy(copy->c_fh.data, &s_fh->fh_handle.fh_base, copy->c_fh.size);
+	memcpy(copy->c_fh.data, &s_fh->fh_handle.fh_raw, copy->c_fh.size);
 	copy->stateid.seqid = cpu_to_be32(s_stid->si_generation);
 	memcpy(copy->stateid.other, (void *)&s_stid->si_opaque,
 	       sizeof(stateid_opaque_t));
diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c
index 3f4027a5de8834..bfad94c70b84bc 100644
--- a/fs/nfsd/nfs4state.c
+++ b/fs/nfsd/nfs4state.c
@@ -1010,7 +1010,7 @@ static int delegation_blocked(struct knfsd_fh *fh)
 		}
 		spin_unlock(&blocked_delegations_lock);
 	}
-	hash = jhash(&fh->fh_base, fh->fh_size, 0);
+	hash = jhash(&fh->fh_raw, fh->fh_size, 0);
 	if (test_bit(hash&255, bd->set[0]) &&
 	    test_bit((hash>>8)&255, bd->set[0]) &&
 	    test_bit((hash>>16)&255, bd->set[0]))
@@ -1029,7 +1029,7 @@ static void block_delegations(struct knfsd_fh *fh)
 	u32 hash;
 	struct bloom_pair *bd = &blocked_delegations;
 
-	hash = jhash(&fh->fh_base, fh->fh_size, 0);
+	hash = jhash(&fh->fh_raw, fh->fh_size, 0);
 
 	spin_lock(&blocked_delegations_lock);
 	__set_bit(hash&255, bd->set[bd->new]);
@@ -5541,7 +5541,7 @@ static void nfsd4_ssc_shutdown_umount(struct nfsd_net *nn)
 static void nfsd4_ssc_expire_umount(struct nfsd_net *nn)
 {
 	bool do_wakeup = false;
-	struct nfsd4_ssc_umount_item *ni = 0;
+	struct nfsd4_ssc_umount_item *ni = NULL;
 	struct nfsd4_ssc_umount_item *tmp;
 
 	spin_lock(&nn->nfsd_ssc_lock);
diff --git a/fs/nfsd/nfs4xdr.c b/fs/nfsd/nfs4xdr.c
index 7abeccb975b227..a54b2845473b39 100644
--- a/fs/nfsd/nfs4xdr.c
+++ b/fs/nfsd/nfs4xdr.c
@@ -3110,7 +3110,7 @@ out_acl:
 		p = xdr_reserve_space(xdr, fhp->fh_handle.fh_size + 4);
 		if (!p)
 			goto out_resource;
-		p = xdr_encode_opaque(p, &fhp->fh_handle.fh_base,
+		p = xdr_encode_opaque(p, &fhp->fh_handle.fh_raw,
 					fhp->fh_handle.fh_size);
 	}
 	if (bmval0 & FATTR4_WORD0_FILEID) {
@@ -3667,7 +3667,7 @@ nfsd4_encode_getfh(struct nfsd4_compoundres *resp, __be32 nfserr, struct svc_fh
 	p = xdr_reserve_space(xdr, len + 4);
 	if (!p)
 		return nfserr_resource;
-	p = xdr_encode_opaque(p, &fhp->fh_handle.fh_base, len);
+	p = xdr_encode_opaque(p, &fhp->fh_handle.fh_raw, len);
 	return 0;
 }
 
diff --git a/fs/nfsd/nfscache.c b/fs/nfsd/nfscache.c
index 96cdf77925f33b..6e0b6f3148dca4 100644
--- a/fs/nfsd/nfscache.c
+++ b/fs/nfsd/nfscache.c
@@ -241,8 +241,8 @@ lru_put_end(struct nfsd_drc_bucket *b, struct svc_cacherep *rp)
 	list_move_tail(&rp->c_lru, &b->lru_head);
 }
 
-static long
-prune_bucket(struct nfsd_drc_bucket *b, struct nfsd_net *nn)
+static long prune_bucket(struct nfsd_drc_bucket *b, struct nfsd_net *nn,
+			 unsigned int max)
 {
 	struct svc_cacherep *rp, *tmp;
 	long freed = 0;
@@ -258,11 +258,17 @@ prune_bucket(struct nfsd_drc_bucket *b, struct nfsd_net *nn)
 		    time_before(jiffies, rp->c_timestamp + RC_EXPIRE))
 			break;
 		nfsd_reply_cache_free_locked(b, rp, nn);
-		freed++;
+		if (max && freed++ > max)
+			break;
 	}
 	return freed;
 }
 
+static long nfsd_prune_bucket(struct nfsd_drc_bucket *b, struct nfsd_net *nn)
+{
+	return prune_bucket(b, nn, 3);
+}
+
 /*
  * Walk the LRU list and prune off entries that are older than RC_EXPIRE.
  * Also prune the oldest ones when the total exceeds the max number of entries.
@@ -279,7 +285,7 @@ prune_cache_entries(struct nfsd_net *nn)
 		if (list_empty(&b->lru_head))
 			continue;
 		spin_lock(&b->cache_lock);
-		freed += prune_bucket(b, nn);
+		freed += prune_bucket(b, nn, 0);
 		spin_unlock(&b->cache_lock);
 	}
 	return freed;
@@ -453,8 +459,7 @@ int nfsd_cache_lookup(struct svc_rqst *rqstp)
 	atomic_inc(&nn->num_drc_entries);
 	nfsd_stats_drc_mem_usage_add(nn, sizeof(*rp));
 
-	/* go ahead and prune the cache */
-	prune_bucket(b, nn);
+	nfsd_prune_bucket(b, nn);
 
 out_unlock:
 	spin_unlock(&b->cache_lock);
diff --git a/fs/nfsd/nfsctl.c b/fs/nfsd/nfsctl.c
index c2c3d9077dc581..5e48bc48942e6d 100644
--- a/fs/nfsd/nfsctl.c
+++ b/fs/nfsd/nfsctl.c
@@ -395,12 +395,12 @@ static ssize_t write_filehandle(struct file *file, char *buf, size_t size)
 	auth_domain_put(dom);
 	if (len)
 		return len;
-	
+
 	mesg = buf;
 	len = SIMPLE_TRANSACTION_LIMIT;
-	qword_addhex(&mesg, &len, (char*)&fh.fh_base, fh.fh_size);
+	qword_addhex(&mesg, &len, fh.fh_raw, fh.fh_size);
 	mesg[-1] = '\n';
-	return mesg - buf;	
+	return mesg - buf;
 }
 
 /*
diff --git a/fs/nfsd/nfsfh.c b/fs/nfsd/nfsfh.c
index c475d2271f9c50..f3779fa72c8962 100644
--- a/fs/nfsd/nfsfh.c
+++ b/fs/nfsd/nfsfh.c
@@ -154,11 +154,12 @@ static inline __be32 check_pseudo_root(struct svc_rqst *rqstp,
 static __be32 nfsd_set_fh_dentry(struct svc_rqst *rqstp, struct svc_fh *fhp)
 {
 	struct knfsd_fh	*fh = &fhp->fh_handle;
-	struct fid *fid = NULL, sfid;
+	struct fid *fid = NULL;
 	struct svc_export *exp;
 	struct dentry *dentry;
 	int fileid_type;
 	int data_left = fh->fh_size/4;
+	int len;
 	__be32 error;
 
 	error = nfserr_stale;
@@ -167,48 +168,35 @@ static __be32 nfsd_set_fh_dentry(struct svc_rqst *rqstp, struct svc_fh *fhp)
 	if (rqstp->rq_vers == 4 && fh->fh_size == 0)
 		return nfserr_nofilehandle;
 
-	if (fh->fh_version == 1) {
-		int len;
-
-		if (--data_left < 0)
-			return error;
-		if (fh->fh_auth_type != 0)
-			return error;
-		len = key_len(fh->fh_fsid_type) / 4;
-		if (len == 0)
-			return error;
-		if  (fh->fh_fsid_type == FSID_MAJOR_MINOR) {
-			/* deprecated, convert to type 3 */
-			len = key_len(FSID_ENCODE_DEV)/4;
-			fh->fh_fsid_type = FSID_ENCODE_DEV;
-			/*
-			 * struct knfsd_fh uses host-endian fields, which are
-			 * sometimes used to hold net-endian values. This
-			 * confuses sparse, so we must use __force here to
-			 * keep it from complaining.
-			 */
-			fh->fh_fsid[0] = new_encode_dev(MKDEV(ntohl((__force __be32)fh->fh_fsid[0]),
-							ntohl((__force __be32)fh->fh_fsid[1])));
-			fh->fh_fsid[1] = fh->fh_fsid[2];
-		}
-		data_left -= len;
-		if (data_left < 0)
-			return error;
-		exp = rqst_exp_find(rqstp, fh->fh_fsid_type, fh->fh_fsid);
-		fid = (struct fid *)(fh->fh_fsid + len);
-	} else {
-		__u32 tfh[2];
-		dev_t xdev;
-		ino_t xino;
-
-		if (fh->fh_size != NFS_FHSIZE)
-			return error;
-		/* assume old filehandle format */
-		xdev = old_decode_dev(fh->ofh_xdev);
-		xino = u32_to_ino_t(fh->ofh_xino);
-		mk_fsid(FSID_DEV, tfh, xdev, xino, 0, NULL);
-		exp = rqst_exp_find(rqstp, FSID_DEV, tfh);
+	if (fh->fh_version != 1)
+		return error;
+
+	if (--data_left < 0)
+		return error;
+	if (fh->fh_auth_type != 0)
+		return error;
+	len = key_len(fh->fh_fsid_type) / 4;
+	if (len == 0)
+		return error;
+	if (fh->fh_fsid_type == FSID_MAJOR_MINOR) {
+		/* deprecated, convert to type 3 */
+		len = key_len(FSID_ENCODE_DEV)/4;
+		fh->fh_fsid_type = FSID_ENCODE_DEV;
+		/*
+		 * struct knfsd_fh uses host-endian fields, which are
+		 * sometimes used to hold net-endian values. This
+		 * confuses sparse, so we must use __force here to
+		 * keep it from complaining.
+		 */
+		fh->fh_fsid[0] = new_encode_dev(MKDEV(ntohl((__force __be32)fh->fh_fsid[0]),
+						      ntohl((__force __be32)fh->fh_fsid[1])));
+		fh->fh_fsid[1] = fh->fh_fsid[2];
 	}
+	data_left -= len;
+	if (data_left < 0)
+		return error;
+	exp = rqst_exp_find(rqstp, fh->fh_fsid_type, fh->fh_fsid);
+	fid = (struct fid *)(fh->fh_fsid + len);
 
 	error = nfserr_stale;
 	if (IS_ERR(exp)) {
@@ -253,18 +241,7 @@ static __be32 nfsd_set_fh_dentry(struct svc_rqst *rqstp, struct svc_fh *fhp)
 	if (rqstp->rq_vers > 2)
 		error = nfserr_badhandle;
 
-	if (fh->fh_version != 1) {
-		sfid.i32.ino = fh->ofh_ino;
-		sfid.i32.gen = fh->ofh_generation;
-		sfid.i32.parent_ino = fh->ofh_dirino;
-		fid = &sfid;
-		data_left = 3;
-		if (fh->ofh_dirino == 0)
-			fileid_type = FILEID_INO32_GEN;
-		else
-			fileid_type = FILEID_INO32_GEN_PARENT;
-	} else
-		fileid_type = fh->fh_fileid_type;
+	fileid_type = fh->fh_fileid_type;
 
 	if (fileid_type == FILEID_ROOT)
 		dentry = dget(exp->ex_path.dentry);
@@ -452,20 +429,6 @@ static void _fh_update(struct svc_fh *fhp, struct svc_export *exp,
 	}
 }
 
-/*
- * for composing old style file handles
- */
-static inline void _fh_update_old(struct dentry *dentry,
-				  struct svc_export *exp,
-				  struct knfsd_fh *fh)
-{
-	fh->ofh_ino = ino_t_to_u32(d_inode(dentry)->i_ino);
-	fh->ofh_generation = d_inode(dentry)->i_generation;
-	if (d_is_dir(dentry) ||
-	    (exp->ex_flags & NFSEXP_NOSUBTREECHECK))
-		fh->ofh_dirino = 0;
-}
-
 static bool is_root_export(struct svc_export *exp)
 {
 	return exp->ex_path.dentry == exp->ex_path.dentry->d_sb->s_root;
@@ -562,9 +525,6 @@ fh_compose(struct svc_fh *fhp, struct svc_export *exp, struct dentry *dentry,
 	/* ref_fh is a reference file handle.
 	 * if it is non-null and for the same filesystem, then we should compose
 	 * a filehandle which is of the same version, where possible.
-	 * Currently, that means that if ref_fh->fh_handle.fh_version == 0xca
-	 * Then create a 32byte filehandle using nfs_fhbase_old
-	 *
 	 */
 
 	struct inode * inode = d_inode(dentry);
@@ -600,35 +560,21 @@ fh_compose(struct svc_fh *fhp, struct svc_export *exp, struct dentry *dentry,
 	fhp->fh_dentry = dget(dentry); /* our internal copy */
 	fhp->fh_export = exp_get(exp);
 
-	if (fhp->fh_handle.fh_version == 0xca) {
-		/* old style filehandle please */
-		memset(&fhp->fh_handle.fh_base, 0, NFS_FHSIZE);
-		fhp->fh_handle.fh_size = NFS_FHSIZE;
-		fhp->fh_handle.ofh_dcookie = 0xfeebbaca;
-		fhp->fh_handle.ofh_dev =  old_encode_dev(ex_dev);
-		fhp->fh_handle.ofh_xdev = fhp->fh_handle.ofh_dev;
-		fhp->fh_handle.ofh_xino =
-			ino_t_to_u32(d_inode(exp->ex_path.dentry)->i_ino);
-		fhp->fh_handle.ofh_dirino = ino_t_to_u32(parent_ino(dentry));
-		if (inode)
-			_fh_update_old(dentry, exp, &fhp->fh_handle);
-	} else {
-		fhp->fh_handle.fh_size =
-			key_len(fhp->fh_handle.fh_fsid_type) + 4;
-		fhp->fh_handle.fh_auth_type = 0;
-
-		mk_fsid(fhp->fh_handle.fh_fsid_type,
-			fhp->fh_handle.fh_fsid,
-			ex_dev,
-			d_inode(exp->ex_path.dentry)->i_ino,
-			exp->ex_fsid, exp->ex_uuid);
-
-		if (inode)
-			_fh_update(fhp, exp, dentry);
-		if (fhp->fh_handle.fh_fileid_type == FILEID_INVALID) {
-			fh_put(fhp);
-			return nfserr_opnotsupp;
-		}
+	fhp->fh_handle.fh_size =
+		key_len(fhp->fh_handle.fh_fsid_type) + 4;
+	fhp->fh_handle.fh_auth_type = 0;
+
+	mk_fsid(fhp->fh_handle.fh_fsid_type,
+		fhp->fh_handle.fh_fsid,
+		ex_dev,
+		d_inode(exp->ex_path.dentry)->i_ino,
+		exp->ex_fsid, exp->ex_uuid);
+
+	if (inode)
+		_fh_update(fhp, exp, dentry);
+	if (fhp->fh_handle.fh_fileid_type == FILEID_INVALID) {
+		fh_put(fhp);
+		return nfserr_opnotsupp;
 	}
 
 	return 0;
@@ -649,16 +595,12 @@ fh_update(struct svc_fh *fhp)
 	dentry = fhp->fh_dentry;
 	if (d_really_is_negative(dentry))
 		goto out_negative;
-	if (fhp->fh_handle.fh_version != 1) {
-		_fh_update_old(dentry, fhp->fh_export, &fhp->fh_handle);
-	} else {
-		if (fhp->fh_handle.fh_fileid_type != FILEID_ROOT)
-			return 0;
+	if (fhp->fh_handle.fh_fileid_type != FILEID_ROOT)
+		return 0;
 
-		_fh_update(fhp, fhp->fh_export, dentry);
-		if (fhp->fh_handle.fh_fileid_type == FILEID_INVALID)
-			return nfserr_opnotsupp;
-	}
+	_fh_update(fhp, fhp->fh_export, dentry);
+	if (fhp->fh_handle.fh_fileid_type == FILEID_INVALID)
+		return nfserr_opnotsupp;
 	return 0;
 out_bad:
 	printk(KERN_ERR "fh_update: fh not verified!\n");
@@ -698,16 +640,11 @@ fh_put(struct svc_fh *fhp)
 char * SVCFH_fmt(struct svc_fh *fhp)
 {
 	struct knfsd_fh *fh = &fhp->fh_handle;
+	static char buf[2+1+1+64*3+1];
 
-	static char buf[80];
-	sprintf(buf, "%d: %08x %08x %08x %08x %08x %08x",
-		fh->fh_size,
-		fh->fh_base.fh_pad[0],
-		fh->fh_base.fh_pad[1],
-		fh->fh_base.fh_pad[2],
-		fh->fh_base.fh_pad[3],
-		fh->fh_base.fh_pad[4],
-		fh->fh_base.fh_pad[5]);
+	if (fh->fh_size < 0 || fh->fh_size> 64)
+		return "bad-fh";
+	sprintf(buf, "%d: %*ph", fh->fh_size, fh->fh_size, fh->fh_raw);
 	return buf;
 }
 
diff --git a/fs/nfsd/nfsfh.h b/fs/nfsd/nfsfh.h
index 6106697adc04ba..d11e4b6870d681 100644
--- a/fs/nfsd/nfsfh.h
+++ b/fs/nfsd/nfsfh.h
@@ -10,9 +10,56 @@
 
 #include <linux/crc32.h>
 #include <linux/sunrpc/svc.h>
-#include <uapi/linux/nfsd/nfsfh.h>
 #include <linux/iversion.h>
 #include <linux/exportfs.h>
+#include <linux/nfs4.h>
+
+/*
+ * The file handle starts with a sequence of four-byte words.
+ * The first word contains a version number (1) and three descriptor bytes
+ * that tell how the remaining 3 variable length fields should be handled.
+ * These three bytes are auth_type, fsid_type and fileid_type.
+ *
+ * All four-byte values are in host-byte-order.
+ *
+ * The auth_type field is deprecated and must be set to 0.
+ *
+ * The fsid_type identifies how the filesystem (or export point) is
+ *    encoded.
+ *  Current values:
+ *     0  - 4 byte device id (ms-2-bytes major, ls-2-bytes minor), 4byte inode number
+ *        NOTE: we cannot use the kdev_t device id value, because kdev_t.h
+ *              says we mustn't.  We must break it up and reassemble.
+ *     1  - 4 byte user specified identifier
+ *     2  - 4 byte major, 4 byte minor, 4 byte inode number - DEPRECATED
+ *     3  - 4 byte device id, encoded for user-space, 4 byte inode number
+ *     4  - 4 byte inode number and 4 byte uuid
+ *     5  - 8 byte uuid
+ *     6  - 16 byte uuid
+ *     7  - 8 byte inode number and 16 byte uuid
+ *
+ * The fileid_type identifies how the file within the filesystem is encoded.
+ *   The values for this field are filesystem specific, exccept that
+ *   filesystems must not use the values '0' or '0xff'. 'See enum fid_type'
+ *   in include/linux/exportfs.h for currently registered values.
+ */
+
+struct knfsd_fh {
+	unsigned int	fh_size;	/*
+					 * Points to the current size while
+					 * building a new file handle.
+					 */
+	union {
+		char			fh_raw[NFS4_FHSIZE];
+		struct {
+			u8		fh_version;	/* == 1 */
+			u8		fh_auth_type;	/* deprecated */
+			u8		fh_fsid_type;
+			u8		fh_fileid_type;
+			u32		fh_fsid[]; /* flexible-array member */
+		};
+	};
+};
 
 static inline __u32 ino_t_to_u32(ino_t ino)
 {
@@ -188,7 +235,7 @@ static inline void
 fh_copy_shallow(struct knfsd_fh *dst, struct knfsd_fh *src)
 {
 	dst->fh_size = src->fh_size;
-	memcpy(&dst->fh_base, &src->fh_base, src->fh_size);
+	memcpy(&dst->fh_raw, &src->fh_raw, src->fh_size);
 }
 
 static __inline__ struct svc_fh *
@@ -203,7 +250,7 @@ static inline bool fh_match(struct knfsd_fh *fh1, struct knfsd_fh *fh2)
 {
 	if (fh1->fh_size != fh2->fh_size)
 		return false;
-	if (memcmp(fh1->fh_base.fh_pad, fh2->fh_base.fh_pad, fh1->fh_size) != 0)
+	if (memcmp(fh1->fh_raw, fh2->fh_raw, fh1->fh_size) != 0)
 		return false;
 	return true;
 }
@@ -227,7 +274,7 @@ static inline bool fh_fsid_match(struct knfsd_fh *fh1, struct knfsd_fh *fh2)
  */
 static inline u32 knfsd_fh_hash(const struct knfsd_fh *fh)
 {
-	return ~crc32_le(0xFFFFFFFF, (unsigned char *)&fh->fh_base, fh->fh_size);
+	return ~crc32_le(0xFFFFFFFF, fh->fh_raw, fh->fh_size);
 }
 #else
 static inline u32 knfsd_fh_hash(const struct knfsd_fh *fh)
diff --git a/fs/nfsd/nfsxdr.c b/fs/nfsd/nfsxdr.c
index a06c05fe3b4218..082449c7d0dbfa 100644
--- a/fs/nfsd/nfsxdr.c
+++ b/fs/nfsd/nfsxdr.c
@@ -64,7 +64,7 @@ svcxdr_decode_fhandle(struct xdr_stream *xdr, struct svc_fh *fhp)
 	if (!p)
 		return false;
 	fh_init(fhp, NFS_FHSIZE);
-	memcpy(&fhp->fh_handle.fh_base, p, NFS_FHSIZE);
+	memcpy(&fhp->fh_handle.fh_raw, p, NFS_FHSIZE);
 	fhp->fh_handle.fh_size = NFS_FHSIZE;
 
 	return true;
@@ -78,7 +78,7 @@ svcxdr_encode_fhandle(struct xdr_stream *xdr, const struct svc_fh *fhp)
 	p = xdr_reserve_space(xdr, NFS_FHSIZE);
 	if (!p)
 		return false;
-	memcpy(p, &fhp->fh_handle.fh_base, NFS_FHSIZE);
+	memcpy(p, &fhp->fh_handle.fh_raw, NFS_FHSIZE);
 
 	return true;
 }
diff --git a/fs/nfsd/vfs.c b/fs/nfsd/vfs.c
index 738d564ca4ce34..e9c406fd05b667 100644
--- a/fs/nfsd/vfs.c
+++ b/fs/nfsd/vfs.c
@@ -244,6 +244,7 @@ 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,
diff --git a/include/uapi/linux/nfsd/nfsfh.h b/include/uapi/linux/nfsd/nfsfh.h
deleted file mode 100644
index e29e8accc4f4d2..00000000000000
--- a/include/uapi/linux/nfsd/nfsfh.h
+++ /dev/null
@@ -1,115 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
-/*
- * This file describes the layout of the file handles as passed
- * over the wire.
- *
- * Copyright (C) 1995, 1996, 1997 Olaf Kirch <okir@monad.swb.de>
- */
-
-#ifndef _UAPI_LINUX_NFSD_FH_H
-#define _UAPI_LINUX_NFSD_FH_H
-
-#include <linux/types.h>
-#include <linux/nfs.h>
-#include <linux/nfs2.h>
-#include <linux/nfs3.h>
-#include <linux/nfs4.h>
-
-/*
- * This is the old "dentry style" Linux NFSv2 file handle.
- *
- * The xino and xdev fields are currently used to transport the
- * ino/dev of the exported inode.
- */
-struct nfs_fhbase_old {
-	__u32		fb_dcookie;	/* dentry cookie - always 0xfeebbaca */
-	__u32		fb_ino;		/* our inode number */
-	__u32		fb_dirino;	/* dir inode number, 0 for directories */
-	__u32		fb_dev;		/* our device */
-	__u32		fb_xdev;
-	__u32		fb_xino;
-	__u32		fb_generation;
-};
-
-/*
- * This is the new flexible, extensible style NFSv2/v3/v4 file handle.
- *
- * The file handle starts with a sequence of four-byte words.
- * The first word contains a version number (1) and three descriptor bytes
- * that tell how the remaining 3 variable length fields should be handled.
- * These three bytes are auth_type, fsid_type and fileid_type.
- *
- * All four-byte values are in host-byte-order.
- *
- * The auth_type field is deprecated and must be set to 0.
- *
- * The fsid_type identifies how the filesystem (or export point) is
- *    encoded.
- *  Current values:
- *     0  - 4 byte device id (ms-2-bytes major, ls-2-bytes minor), 4byte inode number
- *        NOTE: we cannot use the kdev_t device id value, because kdev_t.h
- *              says we mustn't.  We must break it up and reassemble.
- *     1  - 4 byte user specified identifier
- *     2  - 4 byte major, 4 byte minor, 4 byte inode number - DEPRECATED
- *     3  - 4 byte device id, encoded for user-space, 4 byte inode number
- *     4  - 4 byte inode number and 4 byte uuid
- *     5  - 8 byte uuid
- *     6  - 16 byte uuid
- *     7  - 8 byte inode number and 16 byte uuid
- *
- * The fileid_type identified how the file within the filesystem is encoded.
- *   The values for this field are filesystem specific, exccept that
- *   filesystems must not use the values '0' or '0xff'. 'See enum fid_type'
- *   in include/linux/exportfs.h for currently registered values.
- */
-struct nfs_fhbase_new {
-	union {
-		struct {
-			__u8		fb_version_aux;	/* == 1, even => nfs_fhbase_old */
-			__u8		fb_auth_type_aux;
-			__u8		fb_fsid_type_aux;
-			__u8		fb_fileid_type_aux;
-			__u32		fb_auth[1];
-			/*	__u32		fb_fsid[0]; floating */
-			/*	__u32		fb_fileid[0]; floating */
-		};
-		struct {
-			__u8		fb_version;	/* == 1, even => nfs_fhbase_old */
-			__u8		fb_auth_type;
-			__u8		fb_fsid_type;
-			__u8		fb_fileid_type;
-			__u32		fb_auth_flex[]; /* flexible-array member */
-		};
-	};
-};
-
-struct knfsd_fh {
-	unsigned int	fh_size;	/* significant for NFSv3.
-					 * Points to the current size while building
-					 * a new file handle
-					 */
-	union {
-		struct nfs_fhbase_old	fh_old;
-		__u32			fh_pad[NFS4_FHSIZE/4];
-		struct nfs_fhbase_new	fh_new;
-	} fh_base;
-};
-
-#define ofh_dcookie		fh_base.fh_old.fb_dcookie
-#define ofh_ino			fh_base.fh_old.fb_ino
-#define ofh_dirino		fh_base.fh_old.fb_dirino
-#define ofh_dev			fh_base.fh_old.fb_dev
-#define ofh_xdev		fh_base.fh_old.fb_xdev
-#define ofh_xino		fh_base.fh_old.fb_xino
-#define ofh_generation		fh_base.fh_old.fb_generation
-
-#define	fh_version		fh_base.fh_new.fb_version
-#define	fh_fsid_type		fh_base.fh_new.fb_fsid_type
-#define	fh_auth_type		fh_base.fh_new.fb_auth_type
-#define	fh_fileid_type		fh_base.fh_new.fb_fileid_type
-#define	fh_fsid			fh_base.fh_new.fb_auth_flex
-
-/* Do not use, provided for userspace compatiblity. */
-#define	fh_auth			fh_base.fh_new.fb_auth
-
-#endif /* _UAPI_LINUX_NFSD_FH_H */
diff --git a/net/sunrpc/addr.c b/net/sunrpc/addr.c
index 6e4dbd577a39fa..d435bffc619997 100644
--- a/net/sunrpc/addr.c
+++ b/net/sunrpc/addr.c
@@ -162,8 +162,10 @@ static int rpc_parse_scope_id(struct net *net, const char *buf,
 			      const size_t buflen, const char *delim,
 			      struct sockaddr_in6 *sin6)
 {
-	char *p;
+	char p[IPV6_SCOPE_ID_LEN + 1];
 	size_t len;
+	u32 scope_id = 0;
+	struct net_device *dev;
 
 	if ((buf + buflen) == delim)
 		return 1;
@@ -175,29 +177,23 @@ static int rpc_parse_scope_id(struct net *net, const char *buf,
 		return 0;
 
 	len = (buf + buflen) - delim - 1;
-	p = kmemdup_nul(delim + 1, len, GFP_KERNEL);
-	if (p) {
-		u32 scope_id = 0;
-		struct net_device *dev;
-
-		dev = dev_get_by_name(net, p);
-		if (dev != NULL) {
-			scope_id = dev->ifindex;
-			dev_put(dev);
-		} else {
-			if (kstrtou32(p, 10, &scope_id) != 0) {
-				kfree(p);
-				return 0;
-			}
-		}
-
-		kfree(p);
-
-		sin6->sin6_scope_id = scope_id;
-		return 1;
+	if (len > IPV6_SCOPE_ID_LEN)
+		return 0;
+
+	memcpy(p, delim + 1, len);
+	p[len] = 0;
+
+	dev = dev_get_by_name(net, p);
+	if (dev != NULL) {
+		scope_id = dev->ifindex;
+		dev_put(dev);
+	} else {
+		if (kstrtou32(p, 10, &scope_id) != 0)
+			return 0;
 	}
 
-	return 0;
+	sin6->sin6_scope_id = scope_id;
+	return 1;
 }
 
 static size_t rpc_pton6(struct net *net, const char *buf, const size_t buflen,
diff --git a/net/sunrpc/auth_gss/svcauth_gss.c b/net/sunrpc/auth_gss/svcauth_gss.c
index 3e776e3dff913f..7dba6a9c213af3 100644
--- a/net/sunrpc/auth_gss/svcauth_gss.c
+++ b/net/sunrpc/auth_gss/svcauth_gss.c
@@ -781,7 +781,7 @@ gss_write_verf(struct svc_rqst *rqstp, struct gss_ctx *ctx_id, u32 seq)
 	svc_putnl(rqstp->rq_res.head, RPC_AUTH_GSS);
 	xdr_seq = kmalloc(4, GFP_KERNEL);
 	if (!xdr_seq)
-		return -1;
+		return -ENOMEM;
 	*xdr_seq = htonl(seq);
 
 	iov.iov_base = xdr_seq;