Merge branch 'for-2.6.33' of git://linux-nfs.org/~bfields/linux

* 'for-2.6.33' of git://linux-nfs.org/~bfields/linux: (42 commits) nfsd: remove pointless paths in file headers nfsd: move most of nfsfh.h to fs/nfsd nfsd: remove unused field rq_reffh nfsd: enable V4ROOT exports nfsd: make V4ROOT exports read-only nfsd: restrict filehandles accepted in V4ROOT case nfsd: allow exports of symlinks nfsd: filter readdir results in V4ROOT case nfsd: filter lookup results in V4ROOT case nfsd4: don't continue "under" mounts in V4ROOT case nfsd: introduce export flag for v4 pseudoroot nfsd: let "insecure" flag vary by pseudoflavor nfsd: new interface to advertise export features nfsd: Move private headers to source directory vfs: nfsctl.c un-used nfsd #includes lockd: Remove un-used nfsd headers #includes s390: remove un-used nfsd #includes sparc: remove un-used nfsd #includes parsic: remove un-used nfsd #includes compat.c: Remove dependence on nfsd private headers ...
author: Linus Torvalds <torvalds@linux-foundation.org> 2009-12-16 10:43:34 -0800
committer: Linus Torvalds <torvalds@linux-foundation.org> 2009-12-16 10:43:34 -0800
commit: 37c24b37fb2454e95136139d10bb6828967105bf (patch)
tree: d5c3fa61fa689567caeb2a7cb5891473e444ff7d
parent: 5ac4d630eb87656bd4dc313b910776d54d88ea28 (diff)
parent: 7663dacd926584093dfc350892792054692b6cb3 (diff)
63 files changed, 719 insertions, 863 deletions
diff --git a/Documentation/filesystems/00-INDEX b/Documentation/filesystems/00-INDEX
index 7001782ab932..875d49696b6e 100644
--- a/Documentation/filesystems/00-INDEX
+++ b/Documentation/filesystems/00-INDEX
@@ -1,7 +1,5 @@
 00-INDEX
 	- this file (info on some of the filesystems supported by linux).
-Exporting
-	- explanation of how to make filesystems exportable.
 Locking
 	- info on locking rules as they pertain to Linux VFS.
 9p.txt
@@ -68,12 +66,8 @@ mandatory-locking.txt
 	- info on the Linux implementation of Sys V mandatory file locking.
 ncpfs.txt
 	- info on Novell Netware(tm) filesystem using NCP protocol.
-nfs41-server.txt
-	- info on the Linux server implementation of NFSv4 minor version 1.
-nfs-rdma.txt
-	- how to install and setup the Linux NFS/RDMA client and server software.
-nfsroot.txt
-	- short guide on setting up a diskless box with NFS root filesystem.
+nfs/
+	- nfs-related documentation.
 nilfs2.txt
 	- info and mount options for the NILFS2 filesystem.
 ntfs.txt
@@ -92,8 +86,6 @@ relay.txt
 	- info on relay, for efficient streaming from kernel to user space.
 romfs.txt
 	- description of the ROMFS filesystem.
-rpc-cache.txt
-	- introduction to the caching mechanisms in the sunrpc layer.
 seq_file.txt
 	- how to use the seq_file API
 sharedsubtree.txt
diff --git a/Documentation/filesystems/nfs/00-INDEX b/Documentation/filesystems/nfs/00-INDEX
new file mode 100644
index 000000000000..2f68cd688769
--- /dev/null
+++ b/Documentation/filesystems/nfs/00-INDEX
@@ -0,0 +1,16 @@
+00-INDEX
+	- this file (nfs-related documentation).
+Exporting
+	- explanation of how to make filesystems exportable.
+knfsd-stats.txt
+	- statistics which the NFS server makes available to user space.
+nfs.txt
+	- nfs client, and DNS resolution for fs_locations.
+nfs41-server.txt
+	- info on the Linux server implementation of NFSv4 minor version 1.
+nfs-rdma.txt
+	- how to install and setup the Linux NFS/RDMA client and server software
+nfsroot.txt
+	- short guide on setting up a diskless box with NFS root filesystem.
+rpc-cache.txt
+	- introduction to the caching mechanisms in the sunrpc layer.
diff --git a/Documentation/filesystems/Exporting b/Documentation/filesystems/nfs/Exporting
index 87019d2b5981..87019d2b5981 100644
--- a/Documentation/filesystems/Exporting
+++ b/Documentation/filesystems/nfs/Exporting
diff --git a/Documentation/filesystems/knfsd-stats.txt b/Documentation/filesystems/nfs/knfsd-stats.txt
index 64ced5149d37..64ced5149d37 100644
--- a/Documentation/filesystems/knfsd-stats.txt
+++ b/Documentation/filesystems/nfs/knfsd-stats.txt
diff --git a/Documentation/filesystems/nfs-rdma.txt b/Documentation/filesystems/nfs/nfs-rdma.txt
index e386f7e4bcee..e386f7e4bcee 100644
--- a/Documentation/filesystems/nfs-rdma.txt
+++ b/Documentation/filesystems/nfs/nfs-rdma.txt
diff --git a/Documentation/filesystems/nfs.txt b/Documentation/filesystems/nfs/nfs.txt
index f50f26ce6cd0..f50f26ce6cd0 100644
--- a/Documentation/filesystems/nfs.txt
+++ b/Documentation/filesystems/nfs/nfs.txt
diff --git a/Documentation/filesystems/nfs41-server.txt b/Documentation/filesystems/nfs/nfs41-server.txt
index 5920fe26e6ff..1bd0d0c05171 100644
--- a/Documentation/filesystems/nfs41-server.txt
+++ b/Documentation/filesystems/nfs/nfs41-server.txt
@@ -41,7 +41,7 @@ interoperability problems with future clients.  Known issues:
 	  conformant with the spec (for example, we don't use kerberos
 	  on the backchannel correctly).
 	- no trunking support: no clients currently take advantage of
-	  trunking, but this is a mandatory failure, and its use is
+	  trunking, but this is a mandatory feature, and its use is
 	  recommended to clients in a number of places.  (E.g. to ensure
 	  timely renewal in case an existing connection's retry timeouts
 	  have gotten too long; see section 8.3 of the draft.)
@@ -213,3 +213,10 @@ The following cases aren't supported yet:
   DESTROY_CLIENTID, DESTROY_SESSION, EXCHANGE_ID.
 * DESTROY_SESSION MUST be the final operation in the COMPOUND request.
 
+Nonstandard compound limitations:
+* No support for a sessions fore channel RPC compound that requires both a
+  ca_maxrequestsize request and a ca_maxresponsesize reply, so we may
+  fail to live up to the promise we made in CREATE_SESSION fore channel
+  negotiation.
+* No more than one IO operation (read, write, readdir) allowed per
+  compound.
diff --git a/Documentation/filesystems/nfsroot.txt b/Documentation/filesystems/nfs/nfsroot.txt
index 3ba0b945aaf8..3ba0b945aaf8 100644
--- a/Documentation/filesystems/nfsroot.txt
+++ b/Documentation/filesystems/nfs/nfsroot.txt
diff --git a/Documentation/filesystems/rpc-cache.txt b/Documentation/filesystems/nfs/rpc-cache.txt
index 8a382bea6808..8a382bea6808 100644
--- a/Documentation/filesystems/rpc-cache.txt
+++ b/Documentation/filesystems/nfs/rpc-cache.txt
diff --git a/Documentation/filesystems/porting b/Documentation/filesystems/porting
index 92b888d540a6..a7e9746ee7ea 100644
--- a/Documentation/filesystems/porting
+++ b/Documentation/filesystems/porting
@@ -140,7 +140,7 @@ Callers of notify_change() need ->i_mutex now.
 New super_block field "struct export_operations *s_export_op" for
 explicit support for exporting, e.g. via NFS.  The structure is fully
 documented at its declaration in include/linux/fs.h, and in
-Documentation/filesystems/Exporting.
+Documentation/filesystems/nfs/Exporting.
 
 Briefly it allows for the definition of decode_fh and encode_fh operations
 to encode and decode filehandles, and allows the filesystem to use
diff --git a/Documentation/kernel-parameters.txt b/Documentation/kernel-parameters.txt
index c309515ae959..5ba4d9dff113 100644
--- a/Documentation/kernel-parameters.txt
+++ b/Documentation/kernel-parameters.txt
@@ -1032,7 +1032,7 @@ and is between 256 and 4096 characters. It is defined in the file
 			No delay
 
 	ip=		[IP_PNP]
-			See Documentation/filesystems/nfsroot.txt.
+			See Documentation/filesystems/nfs/nfsroot.txt.
 
 	ip2=		[HW] Set IO/IRQ pairs for up to 4 IntelliPort boards
 			See comment before ip2_setup() in
@@ -1553,10 +1553,10 @@ and is between 256 and 4096 characters. It is defined in the file
 			going to be removed in 2.6.29.
 
 	nfsaddrs=	[NFS]
-			See Documentation/filesystems/nfsroot.txt.
+			See Documentation/filesystems/nfs/nfsroot.txt.
 
 	nfsroot=	[NFS] nfs root filesystem for disk-less boxes.
-			See Documentation/filesystems/nfsroot.txt.
+			See Documentation/filesystems/nfs/nfsroot.txt.
 
 	nfs.callback_tcpport=
 			[NFS] set the TCP port on which the NFSv4 callback
diff --git a/arch/parisc/kernel/sys_parisc32.c b/arch/parisc/kernel/sys_parisc32.c
index 76d23ec8dfaa..9779ece2b070 100644
--- a/arch/parisc/kernel/sys_parisc32.c
+++ b/arch/parisc/kernel/sys_parisc32.c
@@ -26,13 +26,7 @@
 #include <linux/shm.h>
 #include <linux/slab.h>
 #include <linux/uio.h>
-#include <linux/nfs_fs.h>
 #include <linux/ncp_fs.h>
-#include <linux/sunrpc/svc.h>
-#include <linux/nfsd/nfsd.h>
-#include <linux/nfsd/cache.h>
-#include <linux/nfsd/xdr.h>
-#include <linux/nfsd/syscall.h>
 #include <linux/poll.h>
 #include <linux/personality.h>
 #include <linux/stat.h>
diff --git a/fs/cifs/export.c b/fs/cifs/export.c
index 75949d6a5f1b..6177f7cca16a 100644
--- a/fs/cifs/export.c
+++ b/fs/cifs/export.c
@@ -24,7 +24,7 @@
  */
 
  /*
-  * See Documentation/filesystems/Exporting
+  * See Documentation/filesystems/nfs/Exporting
   * and examples in fs/exportfs
   *
   * Since cifs is a network file system, an "fsid" must be included for
diff --git a/fs/compat.c b/fs/compat.c
index 6c19040ffeef..00d90c2e66f0 100644
--- a/fs/compat.c
+++ b/fs/compat.c
@@ -38,8 +38,6 @@
 #include <linux/dirent.h>
 #include <linux/fsnotify.h>
 #include <linux/highuid.h>
-#include <linux/sunrpc/svc.h>
-#include <linux/nfsd/nfsd.h>
 #include <linux/nfsd/syscall.h>
 #include <linux/personality.h>
 #include <linux/rwsem.h>
diff --git a/fs/exportfs/expfs.c b/fs/exportfs/expfs.c
index 197c7db583c7..e9e175949a63 100644
--- a/fs/exportfs/expfs.c
+++ b/fs/exportfs/expfs.c
@@ -6,7 +6,7 @@
  * and for mapping back from file handles to dentries.
  *
  * For details on why we do all the strange and hairy things in here
- * take a look at Documentation/filesystems/Exporting.
+ * take a look at Documentation/filesystems/nfs/Exporting.
  */
 #include <linux/exportfs.h>
 #include <linux/fs.h>
diff --git a/fs/isofs/export.c b/fs/isofs/export.c
index e81a30593ba9..ed752cb38474 100644
--- a/fs/isofs/export.c
+++ b/fs/isofs/export.c
@@ -9,7 +9,7 @@
  *
  * The following files are helpful:
  *
- *     Documentation/filesystems/Exporting
+ *     Documentation/filesystems/nfs/Exporting
  *     fs/exportfs/expfs.c.
  */
 
diff --git a/fs/lockd/svc4proc.c b/fs/lockd/svc4proc.c
index bd173a6ca3b1..a7966eed3c17 100644
--- a/fs/lockd/svc4proc.c
+++ b/fs/lockd/svc4proc.c
@@ -11,10 +11,6 @@
 #include <linux/time.h>
 #include <linux/slab.h>
 #include <linux/smp_lock.h>
-#include <linux/in.h>
-#include <linux/sunrpc/svc.h>
-#include <linux/sunrpc/clnt.h>
-#include <linux/nfsd/nfsd.h>
 #include <linux/lockd/lockd.h>
 #include <linux/lockd/share.h>
 
diff --git a/fs/lockd/svcproc.c b/fs/lockd/svcproc.c
index e1d28ddd2169..56c9519d900a 100644
--- a/fs/lockd/svcproc.c
+++ b/fs/lockd/svcproc.c
@@ -11,10 +11,6 @@
 #include <linux/time.h>
 #include <linux/slab.h>
 #include <linux/smp_lock.h>
-#include <linux/in.h>
-#include <linux/sunrpc/svc.h>
-#include <linux/sunrpc/clnt.h>
-#include <linux/nfsd/nfsd.h>
 #include <linux/lockd/lockd.h>
 #include <linux/lockd/share.h>
 
diff --git a/fs/nfs/Kconfig b/fs/nfs/Kconfig
index 2a77bc25d5af..59e5673b4597 100644
--- a/fs/nfs/Kconfig
+++ b/fs/nfs/Kconfig
@@ -90,7 +90,7 @@ config ROOT_NFS
 	  If you want your system to mount its root file system via NFS,
 	  choose Y here.  This is common practice for managing systems
 	  without local permanent storage.  For details, read
-	  <file:Documentation/filesystems/nfsroot.txt>.
+	  <file:Documentation/filesystems/nfs/nfsroot.txt>.
 
 	  Most people say N here.
 
diff --git a/fs/nfsctl.c b/fs/nfsctl.c
index 8f9a20556f79..d3854d94b7cf 100644
--- a/fs/nfsctl.c
+++ b/fs/nfsctl.c
@@ -7,8 +7,6 @@
 #include <linux/types.h>
 #include <linux/file.h>
 #include <linux/fs.h>
-#include <linux/sunrpc/svc.h>
-#include <linux/nfsd/nfsd.h>
 #include <linux/nfsd/syscall.h>
 #include <linux/cred.h>
 #include <linux/sched.h>
diff --git a/fs/nfsd/auth.c b/fs/nfsd/auth.c
index 36fcabbf5186..79717a40daba 100644
--- a/fs/nfsd/auth.c
+++ b/fs/nfsd/auth.c
@@ -1,15 +1,7 @@
-/*
- * linux/fs/nfsd/auth.c
- *
- * Copyright (C) 1995, 1996 Olaf Kirch <okir@monad.swb.de>
- */
+/* Copyright (C) 1995, 1996 Olaf Kirch <okir@monad.swb.de> */
 
-#include <linux/types.h>
 #include <linux/sched.h>
-#include <linux/sunrpc/svc.h>
-#include <linux/sunrpc/svcauth.h>
-#include <linux/nfsd/nfsd.h>
-#include <linux/nfsd/export.h>
+#include "nfsd.h"
 #include "auth.h"
 
 int nfsexp_flags(struct svc_rqst *rqstp, struct svc_export *exp)
diff --git a/include/linux/nfsd/cache.h b/fs/nfsd/cache.h
index 3a3f58934f5e..d892be61016c 100644
--- a/include/linux/nfsd/cache.h
+++ b/fs/nfsd/cache.h
@@ -1,6 +1,4 @@
 /*
- * include/linux/nfsd/cache.h
- *
  * Request reply cache. This was heavily inspired by the
  * implementation in 4.3BSD/4.4BSD.
  *
@@ -10,8 +8,7 @@
 #ifndef NFSCACHE_H
 #define NFSCACHE_H
 
-#include <linux/in.h>
-#include <linux/uio.h>
+#include <linux/sunrpc/svc.h>
 
 /*
  * Representation of a reply cache entry.
diff --git a/fs/nfsd/export.c b/fs/nfsd/export.c
index c1c9e035d4a4..c487810a2366 100644
--- a/fs/nfsd/export.c
+++ b/fs/nfsd/export.c
@@ -1,7 +1,5 @@
 #define MSNFS	/* HACK HACK */
 /*
- * linux/fs/nfsd/export.c
- *
  * NFS exporting and validation.
  *
  * We maintain a list of clients, each of which has a list of
@@ -14,29 +12,16 @@
  * Copyright (C) 1995, 1996 Olaf Kirch, <okir@monad.swb.de>
  */
 
-#include <linux/unistd.h>
-#include <linux/slab.h>
-#include <linux/stat.h>
-#include <linux/in.h>
-#include <linux/seq_file.h>
-#include <linux/syscalls.h>
-#include <linux/rwsem.h>
-#include <linux/dcache.h>
 #include <linux/namei.h>
-#include <linux/mount.h>
-#include <linux/hash.h>
 #include <linux/module.h>
 #include <linux/exportfs.h>
 
-#include <linux/sunrpc/svc.h>
-#include <linux/nfsd/nfsd.h>
-#include <linux/nfsd/nfsfh.h>
 #include <linux/nfsd/syscall.h>
-#include <linux/lockd/bind.h>
-#include <linux/sunrpc/msg_prot.h>
-#include <linux/sunrpc/gss_api.h>
 #include <net/ipv6.h>
 
+#include "nfsd.h"
+#include "nfsfh.h"
+
 #define NFSDDBG_FACILITY	NFSDDBG_EXPORT
 
 typedef struct auth_domain	svc_client;
@@ -369,16 +354,25 @@ static struct svc_export *svc_export_update(struct svc_export *new,
 					    struct svc_export *old);
 static struct svc_export *svc_export_lookup(struct svc_export *);
 
-static int check_export(struct inode *inode, int flags, unsigned char *uuid)
+static int check_export(struct inode *inode, int *flags, unsigned char *uuid)
 {
 
-	/* We currently export only dirs and regular files.
-	 * This is what umountd does.
+	/*
+	 * We currently export only dirs, regular files, and (for v4
+	 * pseudoroot) symlinks.
 	 */
 	if (!S_ISDIR(inode->i_mode) &&
+	    !S_ISLNK(inode->i_mode) &&
 	    !S_ISREG(inode->i_mode))
 		return -ENOTDIR;
 
+	/*
+	 * Mountd should never pass down a writeable V4ROOT export, but,
+	 * just to make sure:
+	 */
+	if (*flags & NFSEXP_V4ROOT)
+		*flags |= NFSEXP_READONLY;
+
 	/* There are two requirements on a filesystem to be exportable.
 	 * 1:  We must be able to identify the filesystem from a number.
 	 *       either a device number (so FS_REQUIRES_DEV needed)
@@ -387,7 +381,7 @@ static int check_export(struct inode *inode, int flags, unsigned char *uuid)
 	 *       This means that s_export_op must be set.
 	 */
 	if (!(inode->i_sb->s_type->fs_flags & FS_REQUIRES_DEV) &&
-	    !(flags & NFSEXP_FSID) &&
+	    !(*flags & NFSEXP_FSID) &&
 	    uuid == NULL) {
 		dprintk("exp_export: export of non-dev fs without fsid\n");
 		return -EINVAL;
@@ -602,7 +596,7 @@ static int svc_export_parse(struct cache_detail *cd, char *mesg, int mlen)
 				goto out4;
 		}
 
-		err = check_export(exp.ex_path.dentry->d_inode, exp.ex_flags,
+		err = check_export(exp.ex_path.dentry->d_inode, &exp.ex_flags,
 				   exp.ex_uuid);
 		if (err)
 			goto out4;
@@ -1041,7 +1035,7 @@ exp_export(struct nfsctl_export *nxp)
 		goto finish;
 	}
 
-	err = check_export(path.dentry->d_inode, nxp->ex_flags, NULL);
+	err = check_export(path.dentry->d_inode, &nxp->ex_flags, NULL);
 	if (err) goto finish;
 
 	err = -ENOMEM;
@@ -1320,6 +1314,23 @@ rqst_exp_parent(struct svc_rqst *rqstp, struct path *path)
 	return exp;
 }
 
+static struct svc_export *find_fsidzero_export(struct svc_rqst *rqstp)
+{
+	struct svc_export *exp;
+	u32 fsidv[2];
+
+	mk_fsid(FSID_NUM, fsidv, 0, 0, 0, NULL);
+
+	exp = rqst_exp_find(rqstp, FSID_NUM, fsidv);
+	/*
+	 * We shouldn't have accepting an nfsv4 request at all if we
+	 * don't have a pseudoexport!:
+	 */
+	if (IS_ERR(exp) && PTR_ERR(exp) == -ENOENT)
+		exp = ERR_PTR(-ESERVERFAULT);
+	return exp;
+}
+
 /*
  * Called when we need the filehandle for the root of the pseudofs,
  * for a given NFSv4 client.   The root is defined to be the
@@ -1330,11 +1341,8 @@ exp_pseudoroot(struct svc_rqst *rqstp, struct svc_fh *fhp)
 {
 	struct svc_export *exp;
 	__be32 rv;
-	u32 fsidv[2];
 
-	mk_fsid(FSID_NUM, fsidv, 0, 0, 0, NULL);
-
-	exp = rqst_exp_find(rqstp, FSID_NUM, fsidv);
+	exp = find_fsidzero_export(rqstp);
 	if (IS_ERR(exp))
 		return nfserrno(PTR_ERR(exp));
 	rv = fh_compose(fhp, exp, exp->ex_path.dentry, NULL);
@@ -1425,6 +1433,7 @@ static struct flags {
 	{ NFSEXP_CROSSMOUNT, {"crossmnt", ""}},
 	{ NFSEXP_NOSUBTREECHECK, {"no_subtree_check", ""}},
 	{ NFSEXP_NOAUTHNLM, {"insecure_locks", ""}},
+	{ NFSEXP_V4ROOT, {"v4root", ""}},
 #ifdef MSNFS
 	{ NFSEXP_MSNFS, {"msnfs", ""}},
 #endif
diff --git a/fs/nfsd/lockd.c b/fs/nfsd/lockd.c
index b2786a5f9afe..0c6d81670137 100644
--- a/fs/nfsd/lockd.c
+++ b/fs/nfsd/lockd.c
@@ -1,6 +1,4 @@
 /*
- * linux/fs/nfsd/lockd.c
- *
  * This file contains all the stubs needed when communicating with lockd.
  * This level of indirection is necessary so we can run nfsd+lockd without
  * requiring the nfs client to be compiled in/loaded, and vice versa.
@@ -8,14 +6,10 @@
  * Copyright (C) 1996, Olaf Kirch <okir@monad.swb.de>
  */
 
-#include <linux/types.h>
-#include <linux/fs.h>
 #include <linux/file.h>
-#include <linux/mount.h>
-#include <linux/sunrpc/clnt.h>
-#include <linux/sunrpc/svc.h>
-#include <linux/nfsd/nfsd.h>
 #include <linux/lockd/bind.h>
+#include "nfsd.h"
+#include "vfs.h"
 
 #define NFSDDBG_FACILITY		NFSDDBG_LOCKD
 
diff --git a/fs/nfsd/nfs2acl.c b/fs/nfsd/nfs2acl.c
index 4e3219e84116..f20589d2ae27 100644
--- a/fs/nfsd/nfs2acl.c
+++ b/fs/nfsd/nfs2acl.c
@@ -1,19 +1,15 @@
 /*
- * linux/fs/nfsd/nfs2acl.c
- *
  * Process version 2 NFSACL requests.
  *
  * Copyright (C) 2002-2003 Andreas Gruenbacher <agruen@suse.de>
  */
 
-#include <linux/sunrpc/svc.h>
-#include <linux/nfs.h>
-#include <linux/nfsd/nfsd.h>
-#include <linux/nfsd/cache.h>
-#include <linux/nfsd/xdr.h>
-#include <linux/nfsd/xdr3.h>
-#include <linux/posix_acl.h>
+#include "nfsd.h"
+/* FIXME: nfsacl.h is a broken header */
 #include <linux/nfsacl.h>
+#include "cache.h"
+#include "xdr3.h"
+#include "vfs.h"
 
 #define NFSDDBG_FACILITY		NFSDDBG_PROC
 #define RETURN_STATUS(st)	{ resp->status = (st); return (st); }
@@ -217,6 +213,16 @@ static int nfsaclsvc_decode_accessargs(struct svc_rqst *rqstp, __be32 *p,
  * XDR encode functions
  */
 
+/*
+ * There must be an encoding function for void results so svc_process
+ * will work properly.
+ */
+int
+nfsaclsvc_encode_voidres(struct svc_rqst *rqstp, __be32 *p, void *dummy)
+{
+	return xdr_ressize_check(rqstp, p);
+}
+
 /* GETACL */
 static int nfsaclsvc_encode_getaclres(struct svc_rqst *rqstp, __be32 *p,
 		struct nfsd3_getaclres *resp)
@@ -308,7 +314,6 @@ static int nfsaclsvc_release_access(struct svc_rqst *rqstp, __be32 *p,
 }
 
 #define nfsaclsvc_decode_voidargs	NULL
-#define nfsaclsvc_encode_voidres	NULL
 #define nfsaclsvc_release_void		NULL
 #define nfsd3_fhandleargs	nfsd_fhandle
 #define nfsd3_attrstatres	nfsd_attrstat
@@ -346,5 +351,5 @@ struct svc_version	nfsd_acl_version2 = {
 		.vs_proc	= nfsd_acl_procedures2,
 		.vs_dispatch	= nfsd_dispatch,
 		.vs_xdrsize	= NFS3_SVC_XDRSIZE,
-		.vs_hidden	= 1,
+		.vs_hidden	= 0,
 };
diff --git a/fs/nfsd/nfs3acl.c b/fs/nfsd/nfs3acl.c
index 9981dbb377a3..e0c4846bad92 100644
--- a/fs/nfsd/nfs3acl.c
+++ b/fs/nfsd/nfs3acl.c
@@ -1,18 +1,15 @@
 /*
- * linux/fs/nfsd/nfs3acl.c
- *
  * Process version 3 NFSACL requests.
  *
  * Copyright (C) 2002-2003 Andreas Gruenbacher <agruen@suse.de>
  */
 
-#include <linux/sunrpc/svc.h>
-#include <linux/nfs3.h>
-#include <linux/nfsd/nfsd.h>
-#include <linux/nfsd/cache.h>
-#include <linux/nfsd/xdr3.h>
-#include <linux/posix_acl.h>
+#include "nfsd.h"
+/* FIXME: nfsacl.h is a broken header */
 #include <linux/nfsacl.h>
+#include "cache.h"
+#include "xdr3.h"
+#include "vfs.h"
 
 #define RETURN_STATUS(st)	{ resp->status = (st); return (st); }
 
@@ -264,6 +261,6 @@ struct svc_version	nfsd_acl_version3 = {
 		.vs_proc	= nfsd_acl_procedures3,
 		.vs_dispatch	= nfsd_dispatch,
 		.vs_xdrsize	= NFS3_SVC_XDRSIZE,
-		.vs_hidden	= 1,
+		.vs_hidden	= 0,
 };
 
diff --git a/fs/nfsd/nfs3proc.c b/fs/nfsd/nfs3proc.c
index a713c418a922..3d68f45a37b9 100644
--- a/fs/nfsd/nfs3proc.c
+++ b/fs/nfsd/nfs3proc.c
@@ -1,30 +1,16 @@
 /*
- * linux/fs/nfsd/nfs3proc.c
- *
  * Process version 3 NFS requests.
  *
  * Copyright (C) 1996, 1997, 1998 Olaf Kirch <okir@monad.swb.de>
  */
 
-#include <linux/linkage.h>
-#include <linux/time.h>
-#include <linux/errno.h>
 #include <linux/fs.h>
 #include <linux/ext2_fs.h>
-#include <linux/stat.h>
-#include <linux/fcntl.h>
-#include <linux/net.h>
-#include <linux/in.h>
-#include <linux/unistd.h>
-#include <linux/slab.h>
-#include <linux/major.h>
 #include <linux/magic.h>
 
-#include <linux/sunrpc/svc.h>
-#include <linux/nfsd/nfsd.h>
-#include <linux/nfsd/cache.h>
-#include <linux/nfsd/xdr3.h>
-#include <linux/nfs3.h>
+#include "cache.h"
+#include "xdr3.h"
+#include "vfs.h"
 
 #define NFSDDBG_FACILITY		NFSDDBG_PROC
 
diff --git a/fs/nfsd/nfs3xdr.c b/fs/nfsd/nfs3xdr.c
index d0a2ce1b4324..2a533a0af2a9 100644
--- a/fs/nfsd/nfs3xdr.c
+++ b/fs/nfsd/nfs3xdr.c
@@ -1,6 +1,4 @@
 /*
- * linux/fs/nfsd/nfs3xdr.c
- *
  * XDR support for nfsd/protocol version 3.
  *
  * Copyright (C) 1995, 1996, 1997 Olaf Kirch <okir@monad.swb.de>
@@ -8,19 +6,8 @@
  * 2003-08-09 Jamie Lokier: Use htonl() for nanoseconds, not htons()!
  */
 
-#include <linux/types.h>
-#include <linux/time.h>
-#include <linux/nfs3.h>
-#include <linux/list.h>
-#include <linux/spinlock.h>
-#include <linux/dcache.h>
 #include <linux/namei.h>
-#include <linux/mm.h>
-#include <linux/vfs.h>
-#include <linux/sunrpc/xdr.h>
-#include <linux/sunrpc/svc.h>
-#include <linux/nfsd/nfsd.h>
-#include <linux/nfsd/xdr3.h>
+#include "xdr3.h"
 #include "auth.h"
 
 #define NFSDDBG_FACILITY		NFSDDBG_XDR
diff --git a/fs/nfsd/nfs4acl.c b/fs/nfsd/nfs4acl.c
index 725d02f210e2..88150685df34 100644
--- a/fs/nfsd/nfs4acl.c
+++ b/fs/nfsd/nfs4acl.c
@@ -1,6 +1,4 @@
 /*
- *  fs/nfs4acl/acl.c
- *
  *  Common NFSv4 ACL handling code.
  *
  *  Copyright (c) 2002, 2003 The Regents of the University of Michigan.
@@ -36,15 +34,7 @@
  *  SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
  */
 
-#include <linux/string.h>
-#include <linux/slab.h>
-#include <linux/list.h>
-#include <linux/types.h>
-#include <linux/fs.h>
-#include <linux/module.h>
 #include <linux/nfs_fs.h>
-#include <linux/posix_acl.h>
-#include <linux/nfs4.h>
 #include <linux/nfs4_acl.h>
 
 
@@ -389,7 +379,7 @@ sort_pacl(struct posix_acl *pacl)
 	sort_pacl_range(pacl, 1, i-1);
 
 	BUG_ON(pacl->a_entries[i].e_tag != ACL_GROUP_OBJ);
-	j = i++;
+	j = ++i;
 	while (pacl->a_entries[j].e_tag == ACL_GROUP)
 		j++;
 	sort_pacl_range(pacl, i, j-1);
diff --git a/fs/nfsd/nfs4callback.c b/fs/nfsd/nfs4callback.c
index 24e8d78f8dde..c6eed2a3b093 100644
--- a/fs/nfsd/nfs4callback.c
+++ b/fs/nfsd/nfs4callback.c
@@ -1,6 +1,4 @@
 /*
- *  linux/fs/nfsd/nfs4callback.c
- *
  *  Copyright (c) 2001 The Regents of the University of Michigan.
  *  All rights reserved.
  *
@@ -33,22 +31,9 @@
  *  SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
  */
 
-#include <linux/module.h>
-#include <linux/list.h>
-#include <linux/inet.h>
-#include <linux/errno.h>
-#include <linux/delay.h>
-#include <linux/sched.h>
-#include <linux/kthread.h>
-#include <linux/sunrpc/xdr.h>
-#include <linux/sunrpc/svc.h>
 #include <linux/sunrpc/clnt.h>
-#include <linux/sunrpc/svcsock.h>
-#include <linux/nfsd/nfsd.h>
-#include <linux/nfsd/state.h>
-#include <linux/sunrpc/sched.h>
-#include <linux/nfs4.h>
-#include <linux/sunrpc/xprtsock.h>
+#include "nfsd.h"
+#include "state.h"
 
 #define NFSDDBG_FACILITY                NFSDDBG_PROC
 
diff --git a/fs/nfsd/nfs4idmap.c b/fs/nfsd/nfs4idmap.c
index ba2c199592fd..6e2983b27f3c 100644
--- a/fs/nfsd/nfs4idmap.c
+++ b/fs/nfsd/nfs4idmap.c
@@ -1,6 +1,4 @@
 /*
- *  fs/nfsd/nfs4idmap.c
- *
  *  Mapping of UID/GIDs to name and vice versa.
  *
  *  Copyright (c) 2002, 2003 The Regents of the University of
@@ -35,22 +33,9 @@
  */
 
 #include <linux/module.h>
-#include <linux/init.h>
-
-#include <linux/mm.h>
-#include <linux/errno.h>
-#include <linux/string.h>
-#include <linux/sunrpc/clnt.h>
-#include <linux/nfs.h>
-#include <linux/nfs4.h>
-#include <linux/nfs_fs.h>
-#include <linux/nfs_page.h>
-#include <linux/sunrpc/cache.h>
 #include <linux/nfsd_idmap.h>
-#include <linux/list.h>
-#include <linux/time.h>
 #include <linux/seq_file.h>
-#include <linux/sunrpc/svcauth.h>
+#include <linux/sched.h>
 
 /*
  * Cache entry
diff --git a/fs/nfsd/nfs4proc.c b/fs/nfsd/nfs4proc.c
index bebc0c2e1b0a..37514c469846 100644
--- a/fs/nfsd/nfs4proc.c
+++ b/fs/nfsd/nfs4proc.c
@@ -1,6 +1,4 @@
 /*
- *  fs/nfsd/nfs4proc.c
- *
  *  Server-side procedures for NFSv4.
  *
  *  Copyright (c) 2002 The Regents of the University of Michigan.
@@ -34,20 +32,11 @@
  *  NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS
  *  SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
  */
-
-#include <linux/param.h>
-#include <linux/major.h>
-#include <linux/slab.h>
 #include <linux/file.h>
 
-#include <linux/sunrpc/svc.h>
-#include <linux/nfsd/nfsd.h>
-#include <linux/nfsd/cache.h>
-#include <linux/nfs4.h>
-#include <linux/nfsd/state.h>
-#include <linux/nfsd/xdr4.h>
-#include <linux/nfs4_acl.h>
-#include <linux/sunrpc/gss_api.h>
+#include "cache.h"
+#include "xdr4.h"
+#include "vfs.h"
 
 #define NFSDDBG_FACILITY		NFSDDBG_PROC
 
@@ -170,7 +159,7 @@ do_open_permission(struct svc_rqst *rqstp, struct svc_fh *current_fh, struct nfs
 		accmode |= NFSD_MAY_READ;
 	if (open->op_share_access & NFS4_SHARE_ACCESS_WRITE)
 		accmode |= (NFSD_MAY_WRITE | NFSD_MAY_TRUNC);
-	if (open->op_share_deny & NFS4_SHARE_DENY_WRITE)
+	if (open->op_share_deny & NFS4_SHARE_DENY_READ)
 		accmode |= NFSD_MAY_WRITE;
 
 	status = fh_verify(rqstp, current_fh, S_IFREG, accmode);
diff --git a/fs/nfsd/nfs4recover.c b/fs/nfsd/nfs4recover.c
index b5348405046b..5a754f7b71ed 100644
--- a/fs/nfsd/nfs4recover.c
+++ b/fs/nfsd/nfs4recover.c
@@ -1,6 +1,4 @@
 /*
-*  linux/fs/nfsd/nfs4recover.c
-*
 *  Copyright (c) 2004 The Regents of the University of Michigan.
 *  All rights reserved.
 *
@@ -33,20 +31,14 @@
 *
 */
 
-#include <linux/err.h>
-#include <linux/sunrpc/svc.h>
-#include <linux/nfsd/nfsd.h>
-#include <linux/nfs4.h>
-#include <linux/nfsd/state.h>
-#include <linux/nfsd/xdr4.h>
-#include <linux/param.h>
 #include <linux/file.h>
 #include <linux/namei.h>
-#include <asm/uaccess.h>
-#include <linux/scatterlist.h>
 #include <linux/crypto.h>
 #include <linux/sched.h>
-#include <linux/mount.h>
+
+#include "nfsd.h"
+#include "state.h"
+#include "vfs.h"
 
 #define NFSDDBG_FACILITY                NFSDDBG_PROC
 
diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c
index 2153f9bdbebd..f19ed866c95f 100644
--- a/fs/nfsd/nfs4state.c
+++ b/fs/nfsd/nfs4state.c
@@ -1,6 +1,4 @@
 /*
-*  linux/fs/nfsd/nfs4state.c
-*
 *  Copyright (c) 2001 The Regents of the University of Michigan.
 *  All rights reserved.
 *
@@ -34,28 +32,14 @@
 *
 */
 
-#include <linux/param.h>
-#include <linux/major.h>
-#include <linux/slab.h>
-
-#include <linux/sunrpc/svc.h>
-#include <linux/nfsd/nfsd.h>
-#include <linux/nfsd/cache.h>
 #include <linux/file.h>
-#include <linux/mount.h>
-#include <linux/workqueue.h>
 #include <linux/smp_lock.h>
-#include <linux/kthread.h>
-#include <linux/nfs4.h>
-#include <linux/nfsd/state.h>
-#include <linux/nfsd/xdr4.h>
 #include <linux/namei.h>
 #include <linux/swap.h>
-#include <linux/mutex.h>
-#include <linux/lockd/bind.h>
-#include <linux/module.h>
 #include <linux/sunrpc/svcauth_gss.h>
 #include <linux/sunrpc/clnt.h>
+#include "xdr4.h"
+#include "vfs.h"
 
 #define NFSDDBG_FACILITY                NFSDDBG_PROC
 
@@ -477,13 +461,14 @@ static int set_forechannel_drc_size(struct nfsd4_channel_attrs *fchan)
 
 /*
  * fchan holds the client values on input, and the server values on output
+ * sv_max_mesg is the maximum payload plus one page for overhead.
  */
 static int init_forechannel_attrs(struct svc_rqst *rqstp,
 				  struct nfsd4_channel_attrs *session_fchan,
 				  struct nfsd4_channel_attrs *fchan)
 {
 	int status = 0;
-	__u32   maxcount = svc_max_payload(rqstp);
+	__u32   maxcount = nfsd_serv->sv_max_mesg;
 
 	/* headerpadsz set to zero in encode routine */
 
@@ -523,6 +508,15 @@ free_session_slots(struct nfsd4_session *ses)
 		kfree(ses->se_slots[i]);
 }
 
+/*
+ * We don't actually need to cache the rpc and session headers, so we
+ * can allocate a little less for each slot:
+ */
+static inline int slot_bytes(struct nfsd4_channel_attrs *ca)
+{
+	return ca->maxresp_cached - NFSD_MIN_HDR_SEQ_SZ;
+}
+
 static int
 alloc_init_session(struct svc_rqst *rqstp, struct nfs4_client *clp,
 		   struct nfsd4_create_session *cses)
@@ -554,7 +548,7 @@ alloc_init_session(struct svc_rqst *rqstp, struct nfs4_client *clp,
 	memcpy(new, &tmp, sizeof(*new));
 
 	/* allocate each struct nfsd4_slot and data cache in one piece */
-	cachesize = new->se_fchannel.maxresp_cached - NFSD_MIN_HDR_SEQ_SZ;
+	cachesize = slot_bytes(&new->se_fchannel);
 	for (i = 0; i < new->se_fchannel.maxreqs; i++) {
 		sp = kzalloc(sizeof(*sp) + cachesize, GFP_KERNEL);
 		if (!sp)
@@ -628,10 +622,12 @@ void
 free_session(struct kref *kref)
 {
 	struct nfsd4_session *ses;
+	int mem;
 
 	ses = container_of(kref, struct nfsd4_session, se_ref);
 	spin_lock(&nfsd_drc_lock);
-	nfsd_drc_mem_used -= ses->se_fchannel.maxreqs * NFSD_SLOT_CACHE_SIZE;
+	mem = ses->se_fchannel.maxreqs * slot_bytes(&ses->se_fchannel);
+	nfsd_drc_mem_used -= mem;
 	spin_unlock(&nfsd_drc_lock);
 	free_session_slots(ses);
 	kfree(ses);
@@ -2404,11 +2400,8 @@ nfs4_open_delegation(struct svc_fh *fh, struct nfsd4_open *open, struct nfs4_sta
 
 	memcpy(&open->op_delegate_stateid, &dp->dl_stateid, sizeof(dp->dl_stateid));
 
-	dprintk("NFSD: delegation stateid=(%08x/%08x/%08x/%08x)\n\n",
-	             dp->dl_stateid.si_boot,
-	             dp->dl_stateid.si_stateownerid,
-	             dp->dl_stateid.si_fileid,
-	             dp->dl_stateid.si_generation);
+	dprintk("NFSD: delegation stateid=" STATEID_FMT "\n",
+		STATEID_VAL(&dp->dl_stateid));
 out:
 	if (open->op_claim_type == NFS4_OPEN_CLAIM_PREVIOUS
 			&& flag == NFS4_OPEN_DELEGATE_NONE
@@ -2498,9 +2491,8 @@ nfsd4_process_open2(struct svc_rqst *rqstp, struct svc_fh *current_fh, struct nf
 
 	status = nfs_ok;
 
-	dprintk("nfs4_process_open2: stateid=(%08x/%08x/%08x/%08x)\n",
-	            stp->st_stateid.si_boot, stp->st_stateid.si_stateownerid,
-	            stp->st_stateid.si_fileid, stp->st_stateid.si_generation);
+	dprintk("%s: stateid=" STATEID_FMT "\n", __func__,
+		STATEID_VAL(&stp->st_stateid));
 out:
 	if (fp)
 		put_nfs4_file(fp);
@@ -2666,9 +2658,8 @@ STALE_STATEID(stateid_t *stateid)
 {
 	if (time_after((unsigned long)boot_time,
 			(unsigned long)stateid->si_boot)) {
-		dprintk("NFSD: stale stateid (%08x/%08x/%08x/%08x)!\n",
-			stateid->si_boot, stateid->si_stateownerid,
-			stateid->si_fileid, stateid->si_generation);
+		dprintk("NFSD: stale stateid " STATEID_FMT "!\n",
+			STATEID_VAL(stateid));
 		return 1;
 	}
 	return 0;
@@ -2680,9 +2671,8 @@ EXPIRED_STATEID(stateid_t *stateid)
 	if (time_before((unsigned long)boot_time,
 			((unsigned long)stateid->si_boot)) &&
 	    time_before((unsigned long)(stateid->si_boot + lease_time), get_seconds())) {
-		dprintk("NFSD: expired stateid (%08x/%08x/%08x/%08x)!\n",
-			stateid->si_boot, stateid->si_stateownerid,
-			stateid->si_fileid, stateid->si_generation);
+		dprintk("NFSD: expired stateid " STATEID_FMT "!\n",
+			STATEID_VAL(stateid));
 		return 1;
 	}
 	return 0;
@@ -2696,9 +2686,8 @@ stateid_error_map(stateid_t *stateid)
 	if (EXPIRED_STATEID(stateid))
 		return nfserr_expired;
 
-	dprintk("NFSD: bad stateid (%08x/%08x/%08x/%08x)!\n",
-		stateid->si_boot, stateid->si_stateownerid,
-		stateid->si_fileid, stateid->si_generation);
+	dprintk("NFSD: bad stateid " STATEID_FMT "!\n",
+		STATEID_VAL(stateid));
 	return nfserr_bad_stateid;
 }
 
@@ -2884,10 +2873,8 @@ nfs4_preprocess_seqid_op(struct nfsd4_compound_state *cstate, u32 seqid,
 	struct svc_fh *current_fh = &cstate->current_fh;
 	__be32 status;
 
-	dprintk("NFSD: preprocess_seqid_op: seqid=%d " 
-			"stateid = (%08x/%08x/%08x/%08x)\n", seqid,
-		stateid->si_boot, stateid->si_stateownerid, stateid->si_fileid,
-		stateid->si_generation);
+	dprintk("NFSD: %s: seqid=%d stateid = " STATEID_FMT "\n", __func__,
+		seqid, STATEID_VAL(stateid));
 
 	*stpp = NULL;
 	*sopp = NULL;
@@ -3019,12 +3006,8 @@ nfsd4_open_confirm(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
 	sop->so_confirmed = 1;
 	update_stateid(&stp->st_stateid);
 	memcpy(&oc->oc_resp_stateid, &stp->st_stateid, sizeof(stateid_t));
-	dprintk("NFSD: nfsd4_open_confirm: success, seqid=%d " 
-		"stateid=(%08x/%08x/%08x/%08x)\n", oc->oc_seqid,
-		         stp->st_stateid.si_boot,
-		         stp->st_stateid.si_stateownerid,
-		         stp->st_stateid.si_fileid,
-		         stp->st_stateid.si_generation);
+	dprintk("NFSD: %s: success, seqid=%d stateid=" STATEID_FMT "\n",
+		__func__, oc->oc_seqid, STATEID_VAL(&stp->st_stateid));
 
 	nfsd4_create_clid_dir(sop->so_client);
 out:
@@ -3283,9 +3266,8 @@ find_delegation_stateid(struct inode *ino, stateid_t *stid)
 	struct nfs4_file *fp;
 	struct nfs4_delegation *dl;
 
-	dprintk("NFSD:find_delegation_stateid stateid=(%08x/%08x/%08x/%08x)\n",
-                    stid->si_boot, stid->si_stateownerid,
-                    stid->si_fileid, stid->si_generation);
+	dprintk("NFSD: %s: stateid=" STATEID_FMT "\n", __func__,
+		STATEID_VAL(stid));
 
 	fp = find_file(ino);
 	if (!fp)
diff --git a/fs/nfsd/nfs4xdr.c b/fs/nfsd/nfs4xdr.c
index 0fbd50cee1f6..a8587e90fd5a 100644
--- a/fs/nfsd/nfs4xdr.c
+++ b/fs/nfsd/nfs4xdr.c
@@ -40,24 +40,16 @@
  * at the end of nfs4svc_decode_compoundargs.
  */
 
-#include <linux/param.h>
-#include <linux/smp.h>
-#include <linux/fs.h>
 #include <linux/namei.h>
-#include <linux/vfs.h>
+#include <linux/statfs.h>
 #include <linux/utsname.h>
-#include <linux/sunrpc/xdr.h>
-#include <linux/sunrpc/svc.h>
-#include <linux/sunrpc/clnt.h>
-#include <linux/nfsd/nfsd.h>
-#include <linux/nfsd/state.h>
-#include <linux/nfsd/xdr4.h>
 #include <linux/nfsd_idmap.h>
-#include <linux/nfs4.h>
 #include <linux/nfs4_acl.h>
-#include <linux/sunrpc/gss_api.h>
 #include <linux/sunrpc/svcauth_gss.h>
 
+#include "xdr4.h"
+#include "vfs.h"
+
 #define NFSDDBG_FACILITY		NFSDDBG_XDR
 
 /*
@@ -2204,11 +2196,14 @@ nfsd4_encode_dirent_fattr(struct nfsd4_readdir *cd,
 	 * we will not follow the cross mount and will fill the attribtutes
 	 * directly from the mountpoint dentry.
 	 */
-	if (d_mountpoint(dentry) && !attributes_need_mount(cd->rd_bmval))
-		ignore_crossmnt = 1;
-	else if (d_mountpoint(dentry)) {
+	if (nfsd_mountpoint(dentry, exp)) {
 		int err;
 
+		if (!(exp->ex_flags & NFSEXP_V4ROOT)
+				&& !attributes_need_mount(cd->rd_bmval)) {
+			ignore_crossmnt = 1;
+			goto out_encode;
+		}
 		/*
 		 * Why the heck aren't we just using nfsd_lookup??
 		 * Different "."/".." handling?  Something else?
@@ -2224,6 +2219,7 @@ nfsd4_encode_dirent_fattr(struct nfsd4_readdir *cd,
 			goto out_put;
 
 	}
+out_encode:
 	nfserr = nfsd4_encode_fattr(NULL, exp, dentry, p, buflen, cd->rd_bmval,
 					cd->rd_rqstp, ignore_crossmnt);
 out_put:
diff --git a/fs/nfsd/nfscache.c b/fs/nfsd/nfscache.c
index 4638635c5d87..da08560c4818 100644
--- a/fs/nfsd/nfscache.c
+++ b/fs/nfsd/nfscache.c
@@ -1,6 +1,4 @@
 /*
- * linux/fs/nfsd/nfscache.c
- *
  * Request reply cache. This is currently a global cache, but this may
  * change in the future and be a per-client cache.
  *
@@ -10,16 +8,8 @@
  * Copyright (C) 1995, 1996 Olaf Kirch <okir@monad.swb.de>
  */
 
-#include <linux/kernel.h>
-#include <linux/time.h>
-#include <linux/slab.h>
-#include <linux/string.h>
-#include <linux/spinlock.h>
-#include <linux/list.h>
-
-#include <linux/sunrpc/svc.h>
-#include <linux/nfsd/nfsd.h>
-#include <linux/nfsd/cache.h>
+#include "nfsd.h"
+#include "cache.h"
 
 /* Size of reply cache. Common values are:
  * 4.3BSD:	128
diff --git a/fs/nfsd/nfsctl.c b/fs/nfsd/nfsctl.c
index 5c01fc148ce8..2604c3e70ea5 100644
--- a/fs/nfsd/nfsctl.c
+++ b/fs/nfsd/nfsctl.c
@@ -1,46 +1,20 @@
 /*
- * linux/fs/nfsd/nfsctl.c
- *
  * Syscall interface to knfsd.
  *
  * Copyright (C) 1995, 1996 Olaf Kirch <okir@monad.swb.de>
  */
 
-#include <linux/module.h>
-
-#include <linux/linkage.h>
-#include <linux/time.h>
-#include <linux/errno.h>
-#include <linux/fs.h>
 #include <linux/namei.h>
-#include <linux/fcntl.h>
-#include <linux/net.h>
-#include <linux/in.h>
-#include <linux/syscalls.h>
-#include <linux/unistd.h>
-#include <linux/slab.h>
-#include <linux/proc_fs.h>
-#include <linux/seq_file.h>
-#include <linux/pagemap.h>
-#include <linux/init.h>
-#include <linux/inet.h>
-#include <linux/string.h>
 #include <linux/ctype.h>
 
-#include <linux/nfs.h>
 #include <linux/nfsd_idmap.h>
-#include <linux/lockd/bind.h>
-#include <linux/sunrpc/svc.h>
 #include <linux/sunrpc/svcsock.h>
-#include <linux/nfsd/nfsd.h>
-#include <linux/nfsd/cache.h>
-#include <linux/nfsd/xdr.h>
 #include <linux/nfsd/syscall.h>
 #include <linux/lockd/lockd.h>
 #include <linux/sunrpc/clnt.h>
 
-#include <asm/uaccess.h>
-#include <net/ipv6.h>
+#include "nfsd.h"
+#include "cache.h"
 
 /*
  *	We have a single directory with 9 nodes in it.
@@ -55,6 +29,7 @@ enum {
 	NFSD_Getfd,
 	NFSD_Getfs,
 	NFSD_List,
+	NFSD_Export_features,
 	NFSD_Fh,
 	NFSD_FO_UnlockIP,
 	NFSD_FO_UnlockFS,
@@ -173,6 +148,24 @@ static const struct file_operations exports_operations = {
 	.owner		= THIS_MODULE,
 };
 
+static int export_features_show(struct seq_file *m, void *v)
+{
+	seq_printf(m, "0x%x 0x%x\n", NFSEXP_ALLFLAGS, NFSEXP_SECINFO_FLAGS);
+	return 0;
+}
+
+static int export_features_open(struct inode *inode, struct file *file)
+{
+	return single_open(file, export_features_show, NULL);
+}
+
+static struct file_operations export_features_operations = {
+	.open		= export_features_open,
+	.read		= seq_read,
+	.llseek		= seq_lseek,
+	.release	= single_release,
+};
+
 extern int nfsd_pool_stats_open(struct inode *inode, struct file *file);
 extern int nfsd_pool_stats_release(struct inode *inode, struct file *file);
 
@@ -1330,6 +1323,8 @@ static int nfsd_fill_super(struct super_block * sb, void * data, int silent)
 		[NFSD_Getfd] = {".getfd", &transaction_ops, S_IWUSR|S_IRUSR},
 		[NFSD_Getfs] = {".getfs", &transaction_ops, S_IWUSR|S_IRUSR},
 		[NFSD_List] = {"exports", &exports_operations, S_IRUGO},
+		[NFSD_Export_features] = {"export_features",
+					&export_features_operations, S_IRUGO},
 		[NFSD_FO_UnlockIP] = {"unlock_ip",
 					&transaction_ops, S_IWUSR|S_IRUSR},
 		[NFSD_FO_UnlockFS] = {"unlock_filesystem",
diff --git a/include/linux/nfsd/nfsd.h b/fs/nfsd/nfsd.h
index 510ffdd5020e..e942a1aaac92 100644
--- a/include/linux/nfsd/nfsd.h
+++ b/fs/nfsd/nfsd.h
@@ -1,6 +1,4 @@
 /*
- * linux/include/linux/nfsd/nfsd.h
- *
  * Hodge-podge collection of knfsd-related stuff.
  * I will sort this out later.
  *
@@ -11,13 +9,9 @@
 #define LINUX_NFSD_NFSD_H
 
 #include <linux/types.h>
-#include <linux/unistd.h>
-#include <linux/fs.h>
-#include <linux/posix_acl.h>
 #include <linux/mount.h>
 
 #include <linux/nfsd/debug.h>
-#include <linux/nfsd/nfsfh.h>
 #include <linux/nfsd/export.h>
 #include <linux/nfsd/stats.h>
 /*
@@ -25,30 +19,10 @@
  */
 #define NFSD_SUPPORTED_MINOR_VERSION	1
 
-/*
- * Flags for nfsd_permission
- */
-#define NFSD_MAY_NOP		0
-#define NFSD_MAY_EXEC		1 /* == MAY_EXEC */
-#define NFSD_MAY_WRITE		2 /* == MAY_WRITE */
-#define NFSD_MAY_READ		4 /* == MAY_READ */
-#define NFSD_MAY_SATTR		8
-#define NFSD_MAY_TRUNC		16
-#define NFSD_MAY_LOCK		32
-#define NFSD_MAY_OWNER_OVERRIDE	64
-#define NFSD_MAY_LOCAL_ACCESS	128 /* IRIX doing local access check on device special file*/
-#define NFSD_MAY_BYPASS_GSS_ON_ROOT 256
-
-#define NFSD_MAY_CREATE		(NFSD_MAY_EXEC|NFSD_MAY_WRITE)
-#define NFSD_MAY_REMOVE		(NFSD_MAY_EXEC|NFSD_MAY_WRITE|NFSD_MAY_TRUNC)
-
-/*
- * Callback function for readdir
- */
 struct readdir_cd {
 	__be32			err;	/* 0, nfserr, or nfserr_eof */
 };
-typedef int (*nfsd_dirop_t)(struct inode *, struct dentry *, int, int);
+
 
 extern struct svc_program	nfsd_program;
 extern struct svc_version	nfsd_version2, nfsd_version3,
@@ -73,69 +47,6 @@ int		nfsd_nrpools(void);
 int		nfsd_get_nrthreads(int n, int *);
 int		nfsd_set_nrthreads(int n, int *);
 
-/* nfsd/vfs.c */
-int		fh_lock_parent(struct svc_fh *, struct dentry *);
-int		nfsd_racache_init(int);
-void		nfsd_racache_shutdown(void);
-int		nfsd_cross_mnt(struct svc_rqst *rqstp, struct dentry **dpp,
-		                struct svc_export **expp);
-__be32		nfsd_lookup(struct svc_rqst *, struct svc_fh *,
-				const char *, unsigned int, struct svc_fh *);
-__be32		 nfsd_lookup_dentry(struct svc_rqst *, struct svc_fh *,
-				const char *, unsigned int,
-				struct svc_export **, struct dentry **);
-__be32		nfsd_setattr(struct svc_rqst *, struct svc_fh *,
-				struct iattr *, int, time_t);
-#ifdef CONFIG_NFSD_V4
-__be32          nfsd4_set_nfs4_acl(struct svc_rqst *, struct svc_fh *,
-                    struct nfs4_acl *);
-int             nfsd4_get_nfs4_acl(struct svc_rqst *, struct dentry *, struct nfs4_acl **);
-#endif /* CONFIG_NFSD_V4 */
-__be32		nfsd_create(struct svc_rqst *, struct svc_fh *,
-				char *name, int len, struct iattr *attrs,
-				int type, dev_t rdev, struct svc_fh *res);
-#ifdef CONFIG_NFSD_V3
-__be32		nfsd_access(struct svc_rqst *, struct svc_fh *, u32 *, u32 *);
-__be32		nfsd_create_v3(struct svc_rqst *, struct svc_fh *,
-				char *name, int len, struct iattr *attrs,
-				struct svc_fh *res, int createmode,
-				u32 *verifier, int *truncp, int *created);
-__be32		nfsd_commit(struct svc_rqst *, struct svc_fh *,
-				loff_t, unsigned long);
-#endif /* CONFIG_NFSD_V3 */
-__be32		nfsd_open(struct svc_rqst *, struct svc_fh *, int,
-				int, struct file **);
-void		nfsd_close(struct file *);
-__be32 		nfsd_read(struct svc_rqst *, struct svc_fh *, struct file *,
-				loff_t, struct kvec *, int, unsigned long *);
-__be32 		nfsd_write(struct svc_rqst *, struct svc_fh *,struct file *,
-				loff_t, struct kvec *,int, unsigned long *, int *);
-__be32		nfsd_readlink(struct svc_rqst *, struct svc_fh *,
-				char *, int *);
-__be32		nfsd_symlink(struct svc_rqst *, struct svc_fh *,
-				char *name, int len, char *path, int plen,
-				struct svc_fh *res, struct iattr *);
-__be32		nfsd_link(struct svc_rqst *, struct svc_fh *,
-				char *, int, struct svc_fh *);
-__be32		nfsd_rename(struct svc_rqst *,
-				struct svc_fh *, char *, int,
-				struct svc_fh *, char *, int);
-__be32		nfsd_remove(struct svc_rqst *,
-				struct svc_fh *, char *, int);
-__be32		nfsd_unlink(struct svc_rqst *, struct svc_fh *, int type,
-				char *name, int len);
-int		nfsd_truncate(struct svc_rqst *, struct svc_fh *,
-				unsigned long size);
-__be32		nfsd_readdir(struct svc_rqst *, struct svc_fh *,
-			     loff_t *, struct readdir_cd *, filldir_t);
-__be32		nfsd_statfs(struct svc_rqst *, struct svc_fh *,
-				struct kstatfs *, int access);
-
-int		nfsd_notify_change(struct inode *, struct iattr *);
-__be32		nfsd_permission(struct svc_rqst *, struct svc_export *,
-				struct dentry *, int);
-int		nfsd_sync_dir(struct dentry *dp);
-
 #if defined(CONFIG_NFSD_V2_ACL) || defined(CONFIG_NFSD_V3_ACL)
 #ifdef CONFIG_NFSD_V2_ACL
 extern struct svc_version nfsd_acl_version2;
@@ -147,8 +58,6 @@ extern struct svc_version nfsd_acl_version3;
 #else
 #define nfsd_acl_version3 NULL
 #endif
-struct posix_acl *nfsd_get_posix_acl(struct svc_fh *, int);
-int nfsd_set_posix_acl(struct svc_fh *, int, struct posix_acl *);
 #endif
 
 enum vers_op {NFSD_SET, NFSD_CLEAR, NFSD_TEST, NFSD_AVAIL };
@@ -159,6 +68,11 @@ int nfsd_create_serv(void);
 
 extern int nfsd_max_blksize;
 
+static inline int nfsd_v4client(struct svc_rqst *rq)
+{
+	return rq->rq_prog == NFS_PROGRAM && rq->rq_vers == 4;
+}
+
 /* 
  * NFSv4 State
  */
diff --git a/fs/nfsd/nfsfh.c b/fs/nfsd/nfsfh.c
index 01965b2f3a76..1c12177b908c 100644
--- a/fs/nfsd/nfsfh.c
+++ b/fs/nfsd/nfsfh.c
@@ -1,6 +1,4 @@
 /*
- * linux/fs/nfsd/nfsfh.c
- *
  * NFS server file handle treatment.
  *
  * Copyright (C) 1995, 1996 Olaf Kirch <okir@monad.swb.de>
@@ -9,19 +7,11 @@
  * ... and again Southern-Winter 2001 to support export_operations
  */
 
-#include <linux/slab.h>
-#include <linux/fs.h>
-#include <linux/unistd.h>
-#include <linux/string.h>
-#include <linux/stat.h>
-#include <linux/dcache.h>
 #include <linux/exportfs.h>
-#include <linux/mount.h>
 
-#include <linux/sunrpc/clnt.h>
-#include <linux/sunrpc/svc.h>
 #include <linux/sunrpc/svcauth_gss.h>
-#include <linux/nfsd/nfsd.h>
+#include "nfsd.h"
+#include "vfs.h"
 #include "auth.h"
 
 #define NFSDDBG_FACILITY		NFSDDBG_FH
@@ -96,8 +86,10 @@ nfsd_mode_check(struct svc_rqst *rqstp, umode_t mode, int type)
 static __be32 nfsd_setuser_and_check_port(struct svc_rqst *rqstp,
 					  struct svc_export *exp)
 {
+	int flags = nfsexp_flags(rqstp, exp);
+
 	/* Check if the request originated from a secure port. */
-	if (!rqstp->rq_secure && EX_SECURE(exp)) {
+	if (!rqstp->rq_secure && (flags & NFSEXP_INSECURE_PORT)) {
 		RPC_IFDEBUG(char buf[RPC_MAX_ADDRBUFLEN]);
 		dprintk(KERN_WARNING
 		       "nfsd: request from insecure port %s!\n",
@@ -109,6 +101,36 @@ static __be32 nfsd_setuser_and_check_port(struct svc_rqst *rqstp,
 	return nfserrno(nfsd_setuser(rqstp, exp));
 }
 
+static inline __be32 check_pseudo_root(struct svc_rqst *rqstp,
+	struct dentry *dentry, struct svc_export *exp)
+{
+	if (!(exp->ex_flags & NFSEXP_V4ROOT))
+		return nfs_ok;
+	/*
+	 * v2/v3 clients have no need for the V4ROOT export--they use
+	 * the mount protocl instead; also, further V4ROOT checks may be
+	 * in v4-specific code, in which case v2/v3 clients could bypass
+	 * them.
+	 */
+	if (!nfsd_v4client(rqstp))
+		return nfserr_stale;
+	/*
+	 * We're exposing only the directories and symlinks that have to be
+	 * traversed on the way to real exports:
+	 */
+	if (unlikely(!S_ISDIR(dentry->d_inode->i_mode) &&
+		     !S_ISLNK(dentry->d_inode->i_mode)))
+		return nfserr_stale;
+	/*
+	 * A pseudoroot export gives permission to access only one
+	 * single directory; the kernel has to make another upcall
+	 * before granting access to anything else under it:
+	 */
+	if (unlikely(dentry != exp->ex_path.dentry))
+		return nfserr_stale;
+	return nfs_ok;
+}
+
 /*
  * Use the given filehandle to look up the corresponding export and
  * dentry.  On success, the results are used to set fh_export and
@@ -232,14 +254,6 @@ static __be32 nfsd_set_fh_dentry(struct svc_rqst *rqstp, struct svc_fh *fhp)
 		goto out;
 	}
 
-	if (exp->ex_flags & NFSEXP_NOSUBTREECHECK) {
-		error = nfsd_setuser_and_check_port(rqstp, exp);
-		if (error) {
-			dput(dentry);
-			goto out;
-		}
-	}
-
 	if (S_ISDIR(dentry->d_inode->i_mode) &&
 			(dentry->d_flags & DCACHE_DISCONNECTED)) {
 		printk("nfsd: find_fh_dentry returned a DISCONNECTED directory: %s/%s\n",
@@ -294,28 +308,32 @@ fh_verify(struct svc_rqst *rqstp, struct svc_fh *fhp, int type, int access)
 		error = nfsd_set_fh_dentry(rqstp, fhp);
 		if (error)
 			goto out;
-		dentry = fhp->fh_dentry;
-		exp = fhp->fh_export;
-	} else {
-		/*
-		 * just rechecking permissions
-		 * (e.g. nfsproc_create calls fh_verify, then nfsd_create
-		 * does as well)
-		 */
-		dprintk("nfsd: fh_verify - just checking\n");
-		dentry = fhp->fh_dentry;
-		exp = fhp->fh_export;
-		/*
-		 * Set user creds for this exportpoint; necessary even
-		 * in the "just checking" case because this may be a
-		 * filehandle that was created by fh_compose, and that
-		 * is about to be used in another nfsv4 compound
-		 * operation.
-		 */
-		error = nfsd_setuser_and_check_port(rqstp, exp);
-		if (error)
-			goto out;
 	}
+	dentry = fhp->fh_dentry;
+	exp = fhp->fh_export;
+	/*
+	 * We still have to do all these permission checks, even when
+	 * fh_dentry is already set:
+	 * 	- fh_verify may be called multiple times with different
+	 * 	  "access" arguments (e.g. nfsd_proc_create calls
+	 * 	  fh_verify(...,NFSD_MAY_EXEC) first, then later (in
+	 * 	  nfsd_create) calls fh_verify(...,NFSD_MAY_CREATE).
+	 *	- in the NFSv4 case, the filehandle may have been filled
+	 *	  in by fh_compose, and given a dentry, but further
+	 *	  compound operations performed with that filehandle
+	 *	  still need permissions checks.  In the worst case, a
+	 *	  mountpoint crossing may have changed the export
+	 *	  options, and we may now need to use a different uid
+	 *	  (for example, if different id-squashing options are in
+	 *	  effect on the new filesystem).
+	 */
+	error = check_pseudo_root(rqstp, dentry, exp);
+	if (error)
+		goto out;
+
+	error = nfsd_setuser_and_check_port(rqstp, exp);
+	if (error)
+		goto out;
 
 	error = nfsd_mode_check(rqstp, dentry->d_inode->i_mode, type);
 	if (error)
diff --git a/fs/nfsd/nfsfh.h b/fs/nfsd/nfsfh.h
new file mode 100644
index 000000000000..cdfb8c6a4206
--- /dev/null
+++ b/fs/nfsd/nfsfh.h
@@ -0,0 +1,208 @@
+/* Copyright (C) 1995, 1996, 1997 Olaf Kirch <okir@monad.swb.de> */
+
+#ifndef _LINUX_NFSD_FH_INT_H
+#define _LINUX_NFSD_FH_INT_H
+
+#include <linux/nfsd/nfsfh.h>
+
+enum nfsd_fsid {
+	FSID_DEV = 0,
+	FSID_NUM,
+	FSID_MAJOR_MINOR,
+	FSID_ENCODE_DEV,
+	FSID_UUID4_INUM,
+	FSID_UUID8,
+	FSID_UUID16,
+	FSID_UUID16_INUM,
+};
+
+enum fsid_source {
+	FSIDSOURCE_DEV,
+	FSIDSOURCE_FSID,
+	FSIDSOURCE_UUID,
+};
+extern enum fsid_source fsid_source(struct svc_fh *fhp);
+
+
+/* This might look a little large to "inline" but in all calls except
+ * one, 'vers' is constant so moste of the function disappears.
+ */
+static inline void mk_fsid(int vers, u32 *fsidv, dev_t dev, ino_t ino,
+			   u32 fsid, unsigned char *uuid)
+{
+	u32 *up;
+	switch(vers) {
+	case FSID_DEV:
+		fsidv[0] = htonl((MAJOR(dev)<<16) |
+				 MINOR(dev));
+		fsidv[1] = ino_t_to_u32(ino);
+		break;
+	case FSID_NUM:
+		fsidv[0] = fsid;
+		break;
+	case FSID_MAJOR_MINOR:
+		fsidv[0] = htonl(MAJOR(dev));
+		fsidv[1] = htonl(MINOR(dev));
+		fsidv[2] = ino_t_to_u32(ino);
+		break;
+
+	case FSID_ENCODE_DEV:
+		fsidv[0] = new_encode_dev(dev);
+		fsidv[1] = ino_t_to_u32(ino);
+		break;
+
+	case FSID_UUID4_INUM:
+		/* 4 byte fsid and inode number */
+		up = (u32*)uuid;
+		fsidv[0] = ino_t_to_u32(ino);
+		fsidv[1] = up[0] ^ up[1] ^ up[2] ^ up[3];
+		break;
+
+	case FSID_UUID8:
+		/* 8 byte fsid  */
+		up = (u32*)uuid;
+		fsidv[0] = up[0] ^ up[2];
+		fsidv[1] = up[1] ^ up[3];
+		break;
+
+	case FSID_UUID16:
+		/* 16 byte fsid - NFSv3+ only */
+		memcpy(fsidv, uuid, 16);
+		break;
+
+	case FSID_UUID16_INUM:
+		/* 8 byte inode and 16 byte fsid */
+		*(u64*)fsidv = (u64)ino;
+		memcpy(fsidv+2, uuid, 16);
+		break;
+	default: BUG();
+	}
+}
+
+static inline int key_len(int type)
+{
+	switch(type) {
+	case FSID_DEV:		return 8;
+	case FSID_NUM: 		return 4;
+	case FSID_MAJOR_MINOR:	return 12;
+	case FSID_ENCODE_DEV:	return 8;
+	case FSID_UUID4_INUM:	return 8;
+	case FSID_UUID8:	return 8;
+	case FSID_UUID16:	return 16;
+	case FSID_UUID16_INUM:	return 24;
+	default: return 0;
+	}
+}
+
+/*
+ * Shorthand for dprintk()'s
+ */
+extern char * SVCFH_fmt(struct svc_fh *fhp);
+
+/*
+ * Function prototypes
+ */
+__be32	fh_verify(struct svc_rqst *, struct svc_fh *, int, int);
+__be32	fh_compose(struct svc_fh *, struct svc_export *, struct dentry *, struct svc_fh *);
+__be32	fh_update(struct svc_fh *);
+void	fh_put(struct svc_fh *);
+
+static __inline__ struct svc_fh *
+fh_copy(struct svc_fh *dst, struct svc_fh *src)
+{
+	WARN_ON(src->fh_dentry || src->fh_locked);
+			
+	*dst = *src;
+	return dst;
+}
+
+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);
+}
+
+static __inline__ struct svc_fh *
+fh_init(struct svc_fh *fhp, int maxsize)
+{
+	memset(fhp, 0, sizeof(*fhp));
+	fhp->fh_maxsize = maxsize;
+	return fhp;
+}
+
+#ifdef CONFIG_NFSD_V3
+/*
+ * Fill in the pre_op attr for the wcc data
+ */
+static inline void
+fill_pre_wcc(struct svc_fh *fhp)
+{
+	struct inode    *inode;
+
+	inode = fhp->fh_dentry->d_inode;
+	if (!fhp->fh_pre_saved) {
+		fhp->fh_pre_mtime = inode->i_mtime;
+		fhp->fh_pre_ctime = inode->i_ctime;
+		fhp->fh_pre_size  = inode->i_size;
+		fhp->fh_pre_change = inode->i_version;
+		fhp->fh_pre_saved = 1;
+	}
+}
+
+extern void fill_post_wcc(struct svc_fh *);
+#else
+#define	fill_pre_wcc(ignored)
+#define fill_post_wcc(notused)
+#endif /* CONFIG_NFSD_V3 */
+
+
+/*
+ * Lock a file handle/inode
+ * NOTE: both fh_lock and fh_unlock are done "by hand" in
+ * vfs.c:nfsd_rename as it needs to grab 2 i_mutex's at once
+ * so, any changes here should be reflected there.
+ */
+
+static inline void
+fh_lock_nested(struct svc_fh *fhp, unsigned int subclass)
+{
+	struct dentry	*dentry = fhp->fh_dentry;
+	struct inode	*inode;
+
+	BUG_ON(!dentry);
+
+	if (fhp->fh_locked) {
+		printk(KERN_WARNING "fh_lock: %s/%s already locked!\n",
+			dentry->d_parent->d_name.name, dentry->d_name.name);
+		return;
+	}
+
+	inode = dentry->d_inode;
+	mutex_lock_nested(&inode->i_mutex, subclass);
+	fill_pre_wcc(fhp);
+	fhp->fh_locked = 1;
+}
+
+static inline void
+fh_lock(struct svc_fh *fhp)
+{
+	fh_lock_nested(fhp, I_MUTEX_NORMAL);
+}
+
+/*
+ * Unlock a file handle/inode
+ */
+static inline void
+fh_unlock(struct svc_fh *fhp)
+{
+	BUG_ON(!fhp->fh_dentry);
+
+	if (fhp->fh_locked) {
+		fill_post_wcc(fhp);
+		mutex_unlock(&fhp->fh_dentry->d_inode->i_mutex);
+		fhp->fh_locked = 0;
+	}
+}
+
+#endif /* _LINUX_NFSD_FH_INT_H */
diff --git a/fs/nfsd/nfsproc.c b/fs/nfsd/nfsproc.c
index 0eb9c820b7a6..a047ad6111ef 100644
--- a/fs/nfsd/nfsproc.c
+++ b/fs/nfsd/nfsproc.c
@@ -1,29 +1,14 @@
 /*
- * nfsproc2.c	Process version 2 NFS requests.
- * linux/fs/nfsd/nfs2proc.c
- * 
  * Process version 2 NFS requests.
  *
  * Copyright (C) 1995-1997 Olaf Kirch <okir@monad.swb.de>
  */
 
-#include <linux/linkage.h>
-#include <linux/time.h>
-#include <linux/errno.h>
-#include <linux/fs.h>
-#include <linux/stat.h>
-#include <linux/fcntl.h>
-#include <linux/net.h>
-#include <linux/in.h>
 #include <linux/namei.h>
-#include <linux/unistd.h>
-#include <linux/slab.h>
 
-#include <linux/sunrpc/clnt.h>
-#include <linux/sunrpc/svc.h>
-#include <linux/nfsd/nfsd.h>
-#include <linux/nfsd/cache.h>
-#include <linux/nfsd/xdr.h>
+#include "cache.h"
+#include "xdr.h"
+#include "vfs.h"
 
 typedef struct svc_rqst	svc_rqst;
 typedef struct svc_buf	svc_buf;
@@ -758,6 +743,7 @@ nfserrno (int errno)
 		{ nfserr_io, -ETXTBSY },
 		{ nfserr_notsupp, -EOPNOTSUPP },
 		{ nfserr_toosmall, -ETOOSMALL },
+		{ nfserr_serverfault, -ESERVERFAULT },
 	};
 	int	i;
 
diff --git a/fs/nfsd/nfssvc.c b/fs/nfsd/nfssvc.c
index 67ea83eedd43..171699eb07c8 100644
--- a/fs/nfsd/nfssvc.c
+++ b/fs/nfsd/nfssvc.c
@@ -1,6 +1,4 @@
 /*
- * linux/fs/nfsd/nfssvc.c
- *
  * Central processing for nfsd.
  *
  * Authors:	Olaf Kirch (okir@monad.swb.de)
@@ -8,33 +6,19 @@
  * Copyright (C) 1995, 1996, 1997 Olaf Kirch <okir@monad.swb.de>
  */
 
-#include <linux/module.h>
 #include <linux/sched.h>
-#include <linux/time.h>
-#include <linux/errno.h>
-#include <linux/nfs.h>
-#include <linux/in.h>
-#include <linux/uio.h>
-#include <linux/unistd.h>
-#include <linux/slab.h>
-#include <linux/smp.h>
 #include <linux/freezer.h>
 #include <linux/fs_struct.h>
-#include <linux/kthread.h>
 #include <linux/swap.h>
 
-#include <linux/sunrpc/types.h>
 #include <linux/sunrpc/stats.h>
-#include <linux/sunrpc/svc.h>
 #include <linux/sunrpc/svcsock.h>
-#include <linux/sunrpc/cache.h>
-#include <linux/nfsd/nfsd.h>
-#include <linux/nfsd/stats.h>
-#include <linux/nfsd/cache.h>
-#include <linux/nfsd/syscall.h>
 #include <linux/lockd/bind.h>
 #include <linux/nfsacl.h>
 #include <linux/seq_file.h>
+#include "nfsd.h"
+#include "cache.h"
+#include "vfs.h"
 
 #define NFSDDBG_FACILITY	NFSDDBG_SVC
 
diff --git a/fs/nfsd/nfsxdr.c b/fs/nfsd/nfsxdr.c
index afd08e2c90a5..4ce005dbf3e6 100644
--- a/fs/nfsd/nfsxdr.c
+++ b/fs/nfsd/nfsxdr.c
@@ -1,20 +1,10 @@
 /*
- * linux/fs/nfsd/nfsxdr.c
- *
  * XDR support for nfsd
  *
  * Copyright (C) 1995, 1996 Olaf Kirch <okir@monad.swb.de>
  */
 
-#include <linux/types.h>
-#include <linux/time.h>
-#include <linux/nfs.h>
-#include <linux/vfs.h>
-#include <linux/sunrpc/xdr.h>
-#include <linux/sunrpc/svc.h>
-#include <linux/nfsd/nfsd.h>
-#include <linux/nfsd/xdr.h>
-#include <linux/mm.h>
+#include "xdr.h"
 #include "auth.h"
 
 #define NFSDDBG_FACILITY		NFSDDBG_XDR
diff --git a/include/linux/nfsd/state.h b/fs/nfsd/state.h
index b38d11324189..fefeae27f25e 100644
--- a/include/linux/nfsd/state.h
+++ b/fs/nfsd/state.h
@@ -1,6 +1,4 @@
 /*
- *  linux/include/nfsd/state.h
- *
  *  Copyright (c) 2001 The Regents of the University of Michigan.
  *  All rights reserved.
  *
@@ -37,9 +35,8 @@
 #ifndef _NFSD4_STATE_H
 #define _NFSD4_STATE_H
 
-#include <linux/list.h>
-#include <linux/kref.h>
-#include <linux/sunrpc/clnt.h>
+#include <linux/nfsd/nfsfh.h>
+#include "nfsfh.h"
 
 typedef struct {
 	u32             cl_boot;
@@ -60,6 +57,13 @@ typedef struct {
 #define si_stateownerid   si_opaque.so_stateownerid
 #define si_fileid         si_opaque.so_fileid
 
+#define STATEID_FMT	"(%08x/%08x/%08x/%08x)"
+#define STATEID_VAL(s) \
+	(s)->si_boot, \
+	(s)->si_stateownerid, \
+	(s)->si_fileid, \
+	(s)->si_generation
+
 struct nfsd4_cb_sequence {
 	/* args/res */
 	u32			cbs_minorversion;
diff --git a/fs/nfsd/stats.c b/fs/nfsd/stats.c
index 71944cddf680..5232d3e8fb2f 100644
--- a/fs/nfsd/stats.c
+++ b/fs/nfsd/stats.c
@@ -1,6 +1,4 @@
 /*
- * linux/fs/nfsd/stats.c
- *
  * procfs-based user access to knfsd statistics
  *
  * /proc/net/rpc/nfsd
@@ -23,18 +21,13 @@
  * Copyright (C) 1995, 1996, 1997 Olaf Kirch <okir@monad.swb.de>
  */
 
-#include <linux/kernel.h>
-#include <linux/time.h>
-#include <linux/proc_fs.h>
 #include <linux/seq_file.h>
-#include <linux/stat.h>
 #include <linux/module.h>
-
-#include <linux/sunrpc/svc.h>
 #include <linux/sunrpc/stats.h>
-#include <linux/nfsd/nfsd.h>
 #include <linux/nfsd/stats.h>
 
+#include "nfsd.h"
+
 struct nfsd_stats	nfsdstats;
 struct svc_stat		nfsd_svcstats = {
 	.program	= &nfsd_program,
diff --git a/fs/nfsd/vfs.c b/fs/nfsd/vfs.c
index a293f0273263..e3ef3ec0efd0 100644
--- a/fs/nfsd/vfs.c
+++ b/fs/nfsd/vfs.c
@@ -1,7 +1,5 @@
 #define MSNFS	/* HACK HACK */
 /*
- * linux/fs/nfsd/vfs.c
- *
  * File operations used by nfsd. Some of these have been ripped from
  * other parts of the kernel because they weren't exported, others
  * are partial duplicates with added or changed functionality.
@@ -16,48 +14,31 @@
  * Zerocpy NFS support (C) 2002 Hirokazu Takahashi <taka@valinux.co.jp>
  */
 
-#include <linux/string.h>
-#include <linux/time.h>
-#include <linux/errno.h>
 #include <linux/fs.h>
 #include <linux/file.h>
-#include <linux/mount.h>
-#include <linux/major.h>
 #include <linux/splice.h>
-#include <linux/proc_fs.h>
-#include <linux/stat.h>
 #include <linux/fcntl.h>
-#include <linux/net.h>
-#include <linux/unistd.h>
-#include <linux/slab.h>
-#include <linux/pagemap.h>
-#include <linux/in.h>
-#include <linux/module.h>
 #include <linux/namei.h>
-#include <linux/vfs.h>
 #include <linux/delay.h>
-#include <linux/sunrpc/svc.h>
-#include <linux/nfsd/nfsd.h>
-#ifdef CONFIG_NFSD_V3
-#include <linux/nfs3.h>
-#include <linux/nfsd/xdr3.h>
-#endif /* CONFIG_NFSD_V3 */
-#include <linux/nfsd/nfsfh.h>
 #include <linux/quotaops.h>
 #include <linux/fsnotify.h>
-#include <linux/posix_acl.h>
 #include <linux/posix_acl_xattr.h>
 #include <linux/xattr.h>
+#include <linux/jhash.h>
+#include <linux/ima.h>
+#include <asm/uaccess.h>
+
+#ifdef CONFIG_NFSD_V3
+#include "xdr3.h"
+#endif /* CONFIG_NFSD_V3 */
+
 #ifdef CONFIG_NFSD_V4
-#include <linux/nfs4.h>
 #include <linux/nfs4_acl.h>
 #include <linux/nfsd_idmap.h>
-#include <linux/security.h>
 #endif /* CONFIG_NFSD_V4 */
-#include <linux/jhash.h>
-#include <linux/ima.h>
 
-#include <asm/uaccess.h>
+#include "nfsd.h"
+#include "vfs.h"
 
 #define NFSDDBG_FACILITY		NFSDDBG_FILEOP
 
@@ -89,12 +70,6 @@ struct raparm_hbucket {
 #define RAPARM_HASH_MASK	(RAPARM_HASH_SIZE-1)
 static struct raparm_hbucket	raparm_hash[RAPARM_HASH_SIZE];
 
-static inline int
-nfsd_v4client(struct svc_rqst *rq)
-{
-    return rq->rq_prog == NFS_PROGRAM && rq->rq_vers == 4;
-}
-
 /* 
  * Called from nfsd_lookup and encode_dirent. Check if we have crossed 
  * a mount point.
@@ -116,8 +91,16 @@ nfsd_cross_mnt(struct svc_rqst *rqstp, struct dentry **dpp,
 
 	exp2 = rqst_exp_get_by_name(rqstp, &path);
 	if (IS_ERR(exp2)) {
-		if (PTR_ERR(exp2) != -ENOENT)
-			err = PTR_ERR(exp2);
+		err = PTR_ERR(exp2);
+		/*
+		 * We normally allow NFS clients to continue
+		 * "underneath" a mountpoint that is not exported.
+		 * The exception is V4ROOT, where no traversal is ever
+		 * allowed without an explicit export of the new
+		 * directory.
+		 */
+		if (err == -ENOENT && !(exp->ex_flags & NFSEXP_V4ROOT))
+			err = 0;
 		path_put(&path);
 		goto out;
 	}
@@ -141,6 +124,53 @@ out:
 	return err;
 }
 
+static void follow_to_parent(struct path *path)
+{
+	struct dentry *dp;
+
+	while (path->dentry == path->mnt->mnt_root && follow_up(path))
+		;
+	dp = dget_parent(path->dentry);
+	dput(path->dentry);
+	path->dentry = dp;
+}
+
+static int nfsd_lookup_parent(struct svc_rqst *rqstp, struct dentry *dparent, struct svc_export **exp, struct dentry **dentryp)
+{
+	struct svc_export *exp2;
+	struct path path = {.mnt = mntget((*exp)->ex_path.mnt),
+			    .dentry = dget(dparent)};
+
+	follow_to_parent(&path);
+
+	exp2 = rqst_exp_parent(rqstp, &path);
+	if (PTR_ERR(exp2) == -ENOENT) {
+		*dentryp = dget(dparent);
+	} else if (IS_ERR(exp2)) {
+		path_put(&path);
+		return PTR_ERR(exp2);
+	} else {
+		*dentryp = dget(path.dentry);
+		exp_put(*exp);
+		*exp = exp2;
+	}
+	path_put(&path);
+	return 0;
+}
+
+/*
+ * For nfsd purposes, we treat V4ROOT exports as though there was an
+ * export at *every* directory.
+ */
+int nfsd_mountpoint(struct dentry *dentry, struct svc_export *exp)
+{
+	if (d_mountpoint(dentry))
+		return 1;
+	if (!(exp->ex_flags & NFSEXP_V4ROOT))
+		return 0;
+	return dentry->d_inode != NULL;
+}
+
 __be32
 nfsd_lookup_dentry(struct svc_rqst *rqstp, struct svc_fh *fhp,
 		   const char *name, unsigned int len,
@@ -169,35 +199,13 @@ nfsd_lookup_dentry(struct svc_rqst *rqstp, struct svc_fh *fhp,
 			dentry = dget(dparent);
 		else if (dparent != exp->ex_path.dentry)
 			dentry = dget_parent(dparent);
-		else if (!EX_NOHIDE(exp))
+		else if (!EX_NOHIDE(exp) && !nfsd_v4client(rqstp))
 			dentry = dget(dparent); /* .. == . just like at / */
 		else {
 			/* checking mountpoint crossing is very different when stepping up */
-			struct svc_export *exp2 = NULL;
-			struct dentry *dp;
-			struct path path = {.mnt = mntget(exp->ex_path.mnt),
-					    .dentry = dget(dparent)};
-
-			while (path.dentry == path.mnt->mnt_root &&
-			       follow_up(&path))
-				;
-			dp = dget_parent(path.dentry);
-			dput(path.dentry);
-			path.dentry = dp;
-
-			exp2 = rqst_exp_parent(rqstp, &path);
-			if (PTR_ERR(exp2) == -ENOENT) {
-				dentry = dget(dparent);
-			} else if (IS_ERR(exp2)) {
-				host_err = PTR_ERR(exp2);
-				path_put(&path);
+			host_err = nfsd_lookup_parent(rqstp, dparent, &exp, &dentry);
+			if (host_err)
 				goto out_nfserr;
-			} else {
-				dentry = dget(path.dentry);
-				exp_put(exp);
-				exp = exp2;
-			}
-			path_put(&path);
 		}
 	} else {
 		fh_lock(fhp);
@@ -208,7 +216,7 @@ nfsd_lookup_dentry(struct svc_rqst *rqstp, struct svc_fh *fhp,
 		/*
 		 * check if we have crossed a mount point ...
 		 */
-		if (d_mountpoint(dentry)) {
+		if (nfsd_mountpoint(dentry, exp)) {
 			if ((host_err = nfsd_cross_mnt(rqstp, &dentry, &exp))) {
 				dput(dentry);
 				goto out_nfserr;
diff --git a/fs/nfsd/vfs.h b/fs/nfsd/vfs.h
new file mode 100644
index 000000000000..4b1de0a9ea75
--- /dev/null
+++ b/fs/nfsd/vfs.h
@@ -0,0 +1,101 @@
+/*
+ * Copyright (C) 1995-1997 Olaf Kirch <okir@monad.swb.de>
+ */
+
+#ifndef LINUX_NFSD_VFS_H
+#define LINUX_NFSD_VFS_H
+
+#include "nfsfh.h"
+
+/*
+ * Flags for nfsd_permission
+ */
+#define NFSD_MAY_NOP		0
+#define NFSD_MAY_EXEC		1 /* == MAY_EXEC */
+#define NFSD_MAY_WRITE		2 /* == MAY_WRITE */
+#define NFSD_MAY_READ		4 /* == MAY_READ */
+#define NFSD_MAY_SATTR		8
+#define NFSD_MAY_TRUNC		16
+#define NFSD_MAY_LOCK		32
+#define NFSD_MAY_OWNER_OVERRIDE	64
+#define NFSD_MAY_LOCAL_ACCESS	128 /* IRIX doing local access check on device special file*/
+#define NFSD_MAY_BYPASS_GSS_ON_ROOT 256
+
+#define NFSD_MAY_CREATE		(NFSD_MAY_EXEC|NFSD_MAY_WRITE)
+#define NFSD_MAY_REMOVE		(NFSD_MAY_EXEC|NFSD_MAY_WRITE|NFSD_MAY_TRUNC)
+
+/*
+ * Callback function for readdir
+ */
+typedef int (*nfsd_dirop_t)(struct inode *, struct dentry *, int, int);
+
+/* nfsd/vfs.c */
+int		fh_lock_parent(struct svc_fh *, struct dentry *);
+int		nfsd_racache_init(int);
+void		nfsd_racache_shutdown(void);
+int		nfsd_cross_mnt(struct svc_rqst *rqstp, struct dentry **dpp,
+		                struct svc_export **expp);
+__be32		nfsd_lookup(struct svc_rqst *, struct svc_fh *,
+				const char *, unsigned int, struct svc_fh *);
+__be32		 nfsd_lookup_dentry(struct svc_rqst *, struct svc_fh *,
+				const char *, unsigned int,
+				struct svc_export **, struct dentry **);
+__be32		nfsd_setattr(struct svc_rqst *, struct svc_fh *,
+				struct iattr *, int, time_t);
+int nfsd_mountpoint(struct dentry *, struct svc_export *);
+#ifdef CONFIG_NFSD_V4
+__be32          nfsd4_set_nfs4_acl(struct svc_rqst *, struct svc_fh *,
+                    struct nfs4_acl *);
+int             nfsd4_get_nfs4_acl(struct svc_rqst *, struct dentry *, struct nfs4_acl **);
+#endif /* CONFIG_NFSD_V4 */
+__be32		nfsd_create(struct svc_rqst *, struct svc_fh *,
+				char *name, int len, struct iattr *attrs,
+				int type, dev_t rdev, struct svc_fh *res);
+#ifdef CONFIG_NFSD_V3
+__be32		nfsd_access(struct svc_rqst *, struct svc_fh *, u32 *, u32 *);
+__be32		nfsd_create_v3(struct svc_rqst *, struct svc_fh *,
+				char *name, int len, struct iattr *attrs,
+				struct svc_fh *res, int createmode,
+				u32 *verifier, int *truncp, int *created);
+__be32		nfsd_commit(struct svc_rqst *, struct svc_fh *,
+				loff_t, unsigned long);
+#endif /* CONFIG_NFSD_V3 */
+__be32		nfsd_open(struct svc_rqst *, struct svc_fh *, int,
+				int, struct file **);
+void		nfsd_close(struct file *);
+__be32 		nfsd_read(struct svc_rqst *, struct svc_fh *, struct file *,
+				loff_t, struct kvec *, int, unsigned long *);
+__be32 		nfsd_write(struct svc_rqst *, struct svc_fh *,struct file *,
+				loff_t, struct kvec *,int, unsigned long *, int *);
+__be32		nfsd_readlink(struct svc_rqst *, struct svc_fh *,
+				char *, int *);
+__be32		nfsd_symlink(struct svc_rqst *, struct svc_fh *,
+				char *name, int len, char *path, int plen,
+				struct svc_fh *res, struct iattr *);
+__be32		nfsd_link(struct svc_rqst *, struct svc_fh *,
+				char *, int, struct svc_fh *);
+__be32		nfsd_rename(struct svc_rqst *,
+				struct svc_fh *, char *, int,
+				struct svc_fh *, char *, int);
+__be32		nfsd_remove(struct svc_rqst *,
+				struct svc_fh *, char *, int);
+__be32		nfsd_unlink(struct svc_rqst *, struct svc_fh *, int type,
+				char *name, int len);
+int		nfsd_truncate(struct svc_rqst *, struct svc_fh *,
+				unsigned long size);
+__be32		nfsd_readdir(struct svc_rqst *, struct svc_fh *,
+			     loff_t *, struct readdir_cd *, filldir_t);
+__be32		nfsd_statfs(struct svc_rqst *, struct svc_fh *,
+				struct kstatfs *, int access);
+
+int		nfsd_notify_change(struct inode *, struct iattr *);
+__be32		nfsd_permission(struct svc_rqst *, struct svc_export *,
+				struct dentry *, int);
+int		nfsd_sync_dir(struct dentry *dp);
+
+#if defined(CONFIG_NFSD_V2_ACL) || defined(CONFIG_NFSD_V3_ACL)
+struct posix_acl *nfsd_get_posix_acl(struct svc_fh *, int);
+int nfsd_set_posix_acl(struct svc_fh *, int, struct posix_acl *);
+#endif
+
+#endif /* LINUX_NFSD_VFS_H */
diff --git a/include/linux/nfsd/xdr.h b/fs/nfsd/xdr.h
index a0132ef58f21..53b1863dd8f6 100644
--- a/include/linux/nfsd/xdr.h
+++ b/fs/nfsd/xdr.h
@@ -1,15 +1,11 @@
-/*
- * linux/include/linux/nfsd/xdr.h
- *
- * XDR types for nfsd. This is mainly a typing exercise.
- */
+/* XDR types for nfsd. This is mainly a typing exercise. */
 
 #ifndef LINUX_NFSD_H
 #define LINUX_NFSD_H
 
-#include <linux/fs.h>
 #include <linux/vfs.h>
-#include <linux/nfs.h>
+#include "nfsd.h"
+#include "nfsfh.h"
 
 struct nfsd_fhandle {
 	struct svc_fh		fh;
diff --git a/include/linux/nfsd/xdr3.h b/fs/nfsd/xdr3.h
index 421eddd65a25..7df980eb0562 100644
--- a/include/linux/nfsd/xdr3.h
+++ b/fs/nfsd/xdr3.h
@@ -1,6 +1,4 @@
 /*
- * linux/include/linux/nfsd/xdr3.h
- *
  * XDR types for NFSv3 in nfsd.
  *
  * Copyright (C) 1996-1998, Olaf Kirch <okir@monad.swb.de>
@@ -9,7 +7,7 @@
 #ifndef _LINUX_NFSD_XDR3_H
 #define _LINUX_NFSD_XDR3_H
 
-#include <linux/nfsd/xdr.h>
+#include "xdr.h"
 
 struct nfsd3_sattrargs {
 	struct svc_fh		fh;
diff --git a/include/linux/nfsd/xdr4.h b/fs/nfsd/xdr4.h
index 73164c2b3d29..efa337739534 100644
--- a/include/linux/nfsd/xdr4.h
+++ b/fs/nfsd/xdr4.h
@@ -1,6 +1,4 @@
 /*
- *  include/linux/nfsd/xdr4.h
- *
  *  Server-side types for NFSv4.
  *
  *  Copyright (c) 2002 The Regents of the University of Michigan.
@@ -39,7 +37,8 @@
 #ifndef _LINUX_NFSD_XDR4_H
 #define _LINUX_NFSD_XDR4_H
 
-#include <linux/nfs4.h>
+#include "state.h"
+#include "nfsd.h"
 
 #define NFSD4_MAX_TAGLEN	128
 #define XDR_LEN(n)                     (((n) + 3) & ~3)
diff --git a/include/linux/exportfs.h b/include/linux/exportfs.h
index 27e772cefb6a..dc12f416a49f 100644
--- a/include/linux/exportfs.h
+++ b/include/linux/exportfs.h
@@ -97,7 +97,7 @@ struct fid {
  * @get_name:       find the name for a given inode in a given directory
  * @get_parent:     find the parent of a given directory
  *
- * See Documentation/filesystems/Exporting for details on how to use
+ * See Documentation/filesystems/nfs/Exporting for details on how to use
  * this interface correctly.
  *
  * encode_fh:
diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h
index 51071b335751..89b28812ec24 100644
--- a/include/linux/nfs_xdr.h
+++ b/include/linux/nfs_xdr.h
@@ -2,6 +2,7 @@
 #define _LINUX_NFS_XDR_H
 
 #include <linux/nfsacl.h>
+#include <linux/nfs3.h>
 
 /*
  * To change the maximum rsize and wsize supported by the NFS client, adjust
diff --git a/include/linux/nfsacl.h b/include/linux/nfsacl.h
index 43011b69297c..f321b578edeb 100644
--- a/include/linux/nfsacl.h
+++ b/include/linux/nfsacl.h
@@ -29,6 +29,7 @@
 #ifdef __KERNEL__
 
 #include <linux/posix_acl.h>
+#include <linux/sunrpc/xdr.h>
 
 /* Maximum number of ACL entries over NFS */
 #define NFS_ACL_MAX_ENTRIES	1024
diff --git a/include/linux/nfsd/export.h b/include/linux/nfsd/export.h
index a6d9ef2bb34a..8ae78a61eea4 100644
--- a/include/linux/nfsd/export.h
+++ b/include/linux/nfsd/export.h
@@ -12,7 +12,7 @@
 
 # include <linux/types.h>
 #ifdef __KERNEL__
-# include <linux/in.h>
+# include <linux/nfsd/nfsfh.h>
 #endif
 
 /*
@@ -39,11 +39,23 @@
 #define NFSEXP_FSID		0x2000
 #define	NFSEXP_CROSSMOUNT	0x4000
 #define	NFSEXP_NOACL		0x8000	/* reserved for possible ACL related use */
-#define NFSEXP_ALLFLAGS		0xFE3F
+/*
+ * The NFSEXP_V4ROOT flag causes the kernel to give access only to NFSv4
+ * clients, and only to the single directory that is the root of the
+ * export; further lookup and readdir operations are treated as if every
+ * subdirectory was a mountpoint, and ignored if they are not themselves
+ * exported.  This is used by nfsd and mountd to construct the NFSv4
+ * pseudofilesystem, which provides access only to paths leading to each
+ * exported filesystem.
+ */
+#define	NFSEXP_V4ROOT		0x10000
+/* All flags that we claim to support.  (Note we don't support NOACL.) */
+#define NFSEXP_ALLFLAGS		0x17E3F
 
 /* The flags that may vary depending on security flavor: */
 #define NFSEXP_SECINFO_FLAGS	(NFSEXP_READONLY | NFSEXP_ROOTSQUASH \
-					| NFSEXP_ALLSQUASH)
+					| NFSEXP_ALLSQUASH \
+					| NFSEXP_INSECURE_PORT)
 
 #ifdef __KERNEL__
 
@@ -108,7 +120,6 @@ struct svc_expkey {
 	struct path		ek_path;
 };
 
-#define EX_SECURE(exp)		(!((exp)->ex_flags & NFSEXP_INSECURE_PORT))
 #define EX_ISSYNC(exp)		(!((exp)->ex_flags & NFSEXP_ASYNC))
 #define EX_NOHIDE(exp)		((exp)->ex_flags & NFSEXP_NOHIDE)
 #define EX_WGATHER(exp)		((exp)->ex_flags & NFSEXP_GATHERED_WRITES)
diff --git a/include/linux/nfsd/nfsfh.h b/include/linux/nfsd/nfsfh.h
index 8f641c908450..65e333afaee4 100644
--- a/include/linux/nfsd/nfsfh.h
+++ b/include/linux/nfsd/nfsfh.h
@@ -16,11 +16,9 @@
 
 # include <linux/types.h>
 #ifdef __KERNEL__
-# include <linux/string.h>
-# include <linux/fs.h>
+# include <linux/sunrpc/svc.h>
 #endif
 #include <linux/nfsd/const.h>
-#include <linux/nfsd/debug.h>
 
 /*
  * This is the old "dentry style" Linux NFSv2 file handle.
@@ -164,208 +162,6 @@ typedef struct svc_fh {
 
 } svc_fh;
 
-enum nfsd_fsid {
-	FSID_DEV = 0,
-	FSID_NUM,
-	FSID_MAJOR_MINOR,
-	FSID_ENCODE_DEV,
-	FSID_UUID4_INUM,
-	FSID_UUID8,
-	FSID_UUID16,
-	FSID_UUID16_INUM,
-};
-
-enum fsid_source {
-	FSIDSOURCE_DEV,
-	FSIDSOURCE_FSID,
-	FSIDSOURCE_UUID,
-};
-extern enum fsid_source fsid_source(struct svc_fh *fhp);
-
-
-/* This might look a little large to "inline" but in all calls except
- * one, 'vers' is constant so moste of the function disappears.
- */
-static inline void mk_fsid(int vers, u32 *fsidv, dev_t dev, ino_t ino,
-			   u32 fsid, unsigned char *uuid)
-{
-	u32 *up;
-	switch(vers) {
-	case FSID_DEV:
-		fsidv[0] = htonl((MAJOR(dev)<<16) |
-				 MINOR(dev));
-		fsidv[1] = ino_t_to_u32(ino);
-		break;
-	case FSID_NUM:
-		fsidv[0] = fsid;
-		break;
-	case FSID_MAJOR_MINOR:
-		fsidv[0] = htonl(MAJOR(dev));
-		fsidv[1] = htonl(MINOR(dev));
-		fsidv[2] = ino_t_to_u32(ino);
-		break;
-
-	case FSID_ENCODE_DEV:
-		fsidv[0] = new_encode_dev(dev);
-		fsidv[1] = ino_t_to_u32(ino);
-		break;
-
-	case FSID_UUID4_INUM:
-		/* 4 byte fsid and inode number */
-		up = (u32*)uuid;
-		fsidv[0] = ino_t_to_u32(ino);
-		fsidv[1] = up[0] ^ up[1] ^ up[2] ^ up[3];
-		break;
-
-	case FSID_UUID8:
-		/* 8 byte fsid  */
-		up = (u32*)uuid;
-		fsidv[0] = up[0] ^ up[2];
-		fsidv[1] = up[1] ^ up[3];
-		break;
-
-	case FSID_UUID16:
-		/* 16 byte fsid - NFSv3+ only */
-		memcpy(fsidv, uuid, 16);
-		break;
-
-	case FSID_UUID16_INUM:
-		/* 8 byte inode and 16 byte fsid */
-		*(u64*)fsidv = (u64)ino;
-		memcpy(fsidv+2, uuid, 16);
-		break;
-	default: BUG();
-	}
-}
-
-static inline int key_len(int type)
-{
-	switch(type) {
-	case FSID_DEV:		return 8;
-	case FSID_NUM: 		return 4;
-	case FSID_MAJOR_MINOR:	return 12;
-	case FSID_ENCODE_DEV:	return 8;
-	case FSID_UUID4_INUM:	return 8;
-	case FSID_UUID8:	return 8;
-	case FSID_UUID16:	return 16;
-	case FSID_UUID16_INUM:	return 24;
-	default: return 0;
-	}
-}
-
-/*
- * Shorthand for dprintk()'s
- */
-extern char * SVCFH_fmt(struct svc_fh *fhp);
-
-/*
- * Function prototypes
- */
-__be32	fh_verify(struct svc_rqst *, struct svc_fh *, int, int);
-__be32	fh_compose(struct svc_fh *, struct svc_export *, struct dentry *, struct svc_fh *);
-__be32	fh_update(struct svc_fh *);
-void	fh_put(struct svc_fh *);
-
-static __inline__ struct svc_fh *
-fh_copy(struct svc_fh *dst, struct svc_fh *src)
-{
-	WARN_ON(src->fh_dentry || src->fh_locked);
-			
-	*dst = *src;
-	return dst;
-}
-
-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);
-}
-
-static __inline__ struct svc_fh *
-fh_init(struct svc_fh *fhp, int maxsize)
-{
-	memset(fhp, 0, sizeof(*fhp));
-	fhp->fh_maxsize = maxsize;
-	return fhp;
-}
-
-#ifdef CONFIG_NFSD_V3
-/*
- * Fill in the pre_op attr for the wcc data
- */
-static inline void
-fill_pre_wcc(struct svc_fh *fhp)
-{
-	struct inode    *inode;
-
-	inode = fhp->fh_dentry->d_inode;
-	if (!fhp->fh_pre_saved) {
-		fhp->fh_pre_mtime = inode->i_mtime;
-		fhp->fh_pre_ctime = inode->i_ctime;
-		fhp->fh_pre_size  = inode->i_size;
-		fhp->fh_pre_change = inode->i_version;
-		fhp->fh_pre_saved = 1;
-	}
-}
-
-extern void fill_post_wcc(struct svc_fh *);
-#else
-#define	fill_pre_wcc(ignored)
-#define fill_post_wcc(notused)
-#endif /* CONFIG_NFSD_V3 */
-
-
-/*
- * Lock a file handle/inode
- * NOTE: both fh_lock and fh_unlock are done "by hand" in
- * vfs.c:nfsd_rename as it needs to grab 2 i_mutex's at once
- * so, any changes here should be reflected there.
- */
-
-static inline void
-fh_lock_nested(struct svc_fh *fhp, unsigned int subclass)
-{
-	struct dentry	*dentry = fhp->fh_dentry;
-	struct inode	*inode;
-
-	dfprintk(FILEOP, "nfsd: fh_lock(%s) locked = %d\n",
-			SVCFH_fmt(fhp), fhp->fh_locked);
-
-	BUG_ON(!dentry);
-
-	if (fhp->fh_locked) {
-		printk(KERN_WARNING "fh_lock: %s/%s already locked!\n",
-			dentry->d_parent->d_name.name, dentry->d_name.name);
-		return;
-	}
-
-	inode = dentry->d_inode;
-	mutex_lock_nested(&inode->i_mutex, subclass);
-	fill_pre_wcc(fhp);
-	fhp->fh_locked = 1;
-}
-
-static inline void
-fh_lock(struct svc_fh *fhp)
-{
-	fh_lock_nested(fhp, I_MUTEX_NORMAL);
-}
-
-/*
- * Unlock a file handle/inode
- */
-static inline void
-fh_unlock(struct svc_fh *fhp)
-{
-	BUG_ON(!fhp->fh_dentry);
-
-	if (fhp->fh_locked) {
-		fill_post_wcc(fhp);
-		mutex_unlock(&fhp->fh_dentry->d_inode->i_mutex);
-		fhp->fh_locked = 0;
-	}
-}
 #endif /* __KERNEL__ */
 
 
diff --git a/include/linux/nfsd/syscall.h b/include/linux/nfsd/syscall.h
index 7a3b565b898f..812bc1e160dc 100644
--- a/include/linux/nfsd/syscall.h
+++ b/include/linux/nfsd/syscall.h
@@ -9,14 +9,8 @@
 #ifndef NFSD_SYSCALL_H
 #define NFSD_SYSCALL_H
 
-# include <linux/types.h>
-#ifdef __KERNEL__
-# include <linux/in.h>
-#endif 
-#include <linux/posix_types.h>
-#include <linux/nfsd/const.h>
+#include <linux/types.h>
 #include <linux/nfsd/export.h>
-#include <linux/nfsd/nfsfh.h>
 
 /*
  * Version of the syscall interface
diff --git a/include/linux/sunrpc/debug.h b/include/linux/sunrpc/debug.h
index 10709cbe96fd..c2786f20016f 100644
--- a/include/linux/sunrpc/debug.h
+++ b/include/linux/sunrpc/debug.h
@@ -28,9 +28,6 @@
 
 #ifdef __KERNEL__
 
-#include <linux/timer.h>
-#include <linux/workqueue.h>
-
 /*
  * Enable RPC debugging/profiling.
  */
diff --git a/include/linux/sunrpc/rpc_rdma.h b/include/linux/sunrpc/rpc_rdma.h
index 87b895d5c786..b78f16b1dea3 100644
--- a/include/linux/sunrpc/rpc_rdma.h
+++ b/include/linux/sunrpc/rpc_rdma.h
@@ -40,6 +40,8 @@
 #ifndef _LINUX_SUNRPC_RPC_RDMA_H
 #define _LINUX_SUNRPC_RPC_RDMA_H
 
+#include <linux/types.h>
+
 struct rpcrdma_segment {
 	__be32 rs_handle;	/* Registered memory handle */
 	__be32 rs_length;	/* Length of the chunk in bytes */
diff --git a/include/linux/sunrpc/svc.h b/include/linux/sunrpc/svc.h
index 52e8cb0a7569..5a3085b9b394 100644
--- a/include/linux/sunrpc/svc.h
+++ b/include/linux/sunrpc/svc.h
@@ -29,7 +29,6 @@ struct svc_pool_stats {
 	unsigned long	packets;
 	unsigned long	sockets_queued;
 	unsigned long	threads_woken;
-	unsigned long	overloads_avoided;
 	unsigned long	threads_timedout;
 };
 
@@ -50,7 +49,6 @@ struct svc_pool {
 	struct list_head	sp_sockets;	/* pending sockets */
 	unsigned int		sp_nrthreads;	/* # of threads in pool */
 	struct list_head	sp_all_threads;	/* all server threads */
-	int			sp_nwaking;	/* number of threads woken but not yet active */
 	struct svc_pool_stats	sp_stats;	/* statistics on pool operation */
 } ____cacheline_aligned_in_smp;
 
@@ -275,16 +273,11 @@ struct svc_rqst {
 	struct auth_domain *	rq_client;	/* RPC peer info */
 	struct auth_domain *	rq_gssclient;	/* "gss/"-style peer info */
 	struct svc_cacherep *	rq_cacherep;	/* cache info */
-	struct knfsd_fh *	rq_reffh;	/* Referrence filehandle, used to
-						 * determine what device number
-						 * to report (real or virtual)
-						 */
 	int			rq_splice_ok;   /* turned off in gss privacy
 						 * to prevent encrypting page
 						 * cache pages */
 	wait_queue_head_t	rq_wait;	/* synchronization */
 	struct task_struct	*rq_task;	/* service thread */
-	int			rq_waking;	/* 1 if thread is being woken */
 };
 
 /*
diff --git a/net/ipv4/Kconfig b/net/ipv4/Kconfig
index 70491d9035eb..0c94a1ac2946 100644
--- a/net/ipv4/Kconfig
+++ b/net/ipv4/Kconfig
@@ -166,7 +166,7 @@ config IP_PNP_DHCP
 
 	  If unsure, say Y. Note that if you want to use DHCP, a DHCP server
 	  must be operating on your network.  Read
-	  <file:Documentation/filesystems/nfsroot.txt> for details.
+	  <file:Documentation/filesystems/nfs/nfsroot.txt> for details.
 
 config IP_PNP_BOOTP
 	bool "IP: BOOTP support"
@@ -181,7 +181,7 @@ config IP_PNP_BOOTP
 	  does BOOTP itself, providing all necessary information on the kernel
 	  command line, you can say N here. If unsure, say Y. Note that if you
 	  want to use BOOTP, a BOOTP server must be operating on your network.
-	  Read <file:Documentation/filesystems/nfsroot.txt> for details.
+	  Read <file:Documentation/filesystems/nfs/nfsroot.txt> for details.
 
 config IP_PNP_RARP
 	bool "IP: RARP support"
@@ -194,7 +194,7 @@ config IP_PNP_RARP
 	  older protocol which is being obsoleted by BOOTP and DHCP), say Y
 	  here. Note that if you want to use RARP, a RARP server must be
 	  operating on your network. Read
-	  <file:Documentation/filesystems/nfsroot.txt> for details.
+	  <file:Documentation/filesystems/nfs/nfsroot.txt> for details.
 
 # not yet ready..
 #   bool '    IP: ARP support' CONFIG_IP_PNP_ARP
diff --git a/net/ipv4/ipconfig.c b/net/ipv4/ipconfig.c
index 4e08b7f2331c..10a6a604bf32 100644
--- a/net/ipv4/ipconfig.c
+++ b/net/ipv4/ipconfig.c
@@ -1446,7 +1446,7 @@ late_initcall(ip_auto_config);
 
 /*
  *  Decode any IP configuration options in the "ip=" or "nfsaddrs=" kernel
- *  command line parameter.  See Documentation/filesystems/nfsroot.txt.
+ *  command line parameter.  See Documentation/filesystems/nfs/nfsroot.txt.
  */
 static int __init ic_proto_name(char *name)
 {
diff --git a/net/sunrpc/svc_xprt.c b/net/sunrpc/svc_xprt.c
index b845e2293dfe..1c924ee0a1ef 100644
--- a/net/sunrpc/svc_xprt.c
+++ b/net/sunrpc/svc_xprt.c
@@ -16,8 +16,6 @@
 
 #define RPCDBG_FACILITY	RPCDBG_SVCXPRT
 
-#define SVC_MAX_WAKING 5
-
 static struct svc_deferred_req *svc_deferred_dequeue(struct svc_xprt *xprt);
 static int svc_deferred_recv(struct svc_rqst *rqstp);
 static struct cache_deferred_req *svc_defer(struct cache_req *req);
@@ -306,7 +304,6 @@ void svc_xprt_enqueue(struct svc_xprt *xprt)
 	struct svc_pool *pool;
 	struct svc_rqst	*rqstp;
 	int cpu;
-	int thread_avail;
 
 	if (!(xprt->xpt_flags &
 	      ((1<<XPT_CONN)|(1<<XPT_DATA)|(1<<XPT_CLOSE)|(1<<XPT_DEFERRED))))
@@ -318,6 +315,12 @@ void svc_xprt_enqueue(struct svc_xprt *xprt)
 
 	spin_lock_bh(&pool->sp_lock);
 
+	if (!list_empty(&pool->sp_threads) &&
+	    !list_empty(&pool->sp_sockets))
+		printk(KERN_ERR
+		       "svc_xprt_enqueue: "
+		       "threads and transports both waiting??\n");
+
 	if (test_bit(XPT_DEAD, &xprt->xpt_flags)) {
 		/* Don't enqueue dead transports */
 		dprintk("svc: transport %p is dead, not enqueued\n", xprt);
@@ -358,15 +361,7 @@ void svc_xprt_enqueue(struct svc_xprt *xprt)
 	}
 
  process:
-	/* Work out whether threads are available */
-	thread_avail = !list_empty(&pool->sp_threads);	/* threads are asleep */
-	if (pool->sp_nwaking >= SVC_MAX_WAKING) {
-		/* too many threads are runnable and trying to wake up */
-		thread_avail = 0;
-		pool->sp_stats.overloads_avoided++;
-	}
-
-	if (thread_avail) {
+	if (!list_empty(&pool->sp_threads)) {
 		rqstp = list_entry(pool->sp_threads.next,
 				   struct svc_rqst,
 				   rq_list);
@@ -381,8 +376,6 @@ void svc_xprt_enqueue(struct svc_xprt *xprt)
 		svc_xprt_get(xprt);
 		rqstp->rq_reserved = serv->sv_max_mesg;
 		atomic_add(rqstp->rq_reserved, &xprt->xpt_reserved);
-		rqstp->rq_waking = 1;
-		pool->sp_nwaking++;
 		pool->sp_stats.threads_woken++;
 		BUG_ON(xprt->xpt_pool != pool);
 		wake_up(&rqstp->rq_wait);
@@ -651,11 +644,6 @@ int svc_recv(struct svc_rqst *rqstp, long timeout)
 		return -EINTR;
 
 	spin_lock_bh(&pool->sp_lock);
-	if (rqstp->rq_waking) {
-		rqstp->rq_waking = 0;
-		pool->sp_nwaking--;
-		BUG_ON(pool->sp_nwaking < 0);
-	}
 	xprt = svc_xprt_dequeue(pool);
 	if (xprt) {
 		rqstp->rq_xprt = xprt;
@@ -1204,16 +1192,15 @@ static int svc_pool_stats_show(struct seq_file *m, void *p)
 	struct svc_pool *pool = p;
 
 	if (p == SEQ_START_TOKEN) {
-		seq_puts(m, "# pool packets-arrived sockets-enqueued threads-woken overloads-avoided threads-timedout\n");
+		seq_puts(m, "# pool packets-arrived sockets-enqueued threads-woken threads-timedout\n");
 		return 0;
 	}
 
-	seq_printf(m, "%u %lu %lu %lu %lu %lu\n",
+	seq_printf(m, "%u %lu %lu %lu %lu\n",
 		pool->sp_id,
 		pool->sp_stats.packets,
 		pool->sp_stats.sockets_queued,
 		pool->sp_stats.threads_woken,
-		pool->sp_stats.overloads_avoided,
 		pool->sp_stats.threads_timedout);
 
 	return 0;
diff --git a/net/sunrpc/svcauth_unix.c b/net/sunrpc/svcauth_unix.c
index 4a8f6558718a..d8c041114497 100644
--- a/net/sunrpc/svcauth_unix.c
+++ b/net/sunrpc/svcauth_unix.c
@@ -655,23 +655,25 @@ static struct unix_gid *unix_gid_lookup(uid_t uid)
 		return NULL;
 }
 
-static int unix_gid_find(uid_t uid, struct group_info **gip,
-			 struct svc_rqst *rqstp)
+static struct group_info *unix_gid_find(uid_t uid, struct svc_rqst *rqstp)
 {
-	struct unix_gid *ug = unix_gid_lookup(uid);
+	struct unix_gid *ug;
+	struct group_info *gi;
+	int ret;
+
+	ug = unix_gid_lookup(uid);
 	if (!ug)
-		return -EAGAIN;
-	switch (cache_check(&unix_gid_cache, &ug->h, &rqstp->rq_chandle)) {
+		return ERR_PTR(-EAGAIN);
+	ret = cache_check(&unix_gid_cache, &ug->h, &rqstp->rq_chandle);
+	switch (ret) {
 	case -ENOENT:
-		*gip = NULL;
-		return 0;
+		return ERR_PTR(-ENOENT);
 	case 0:
-		*gip = ug->gi;
-		get_group_info(*gip);
+		gi = get_group_info(ug->gi);
 		cache_put(&ug->h, &unix_gid_cache);
-		return 0;
+		return gi;
 	default:
-		return -EAGAIN;
+		return ERR_PTR(-EAGAIN);
 	}
 }
 
@@ -681,6 +683,8 @@ svcauth_unix_set_client(struct svc_rqst *rqstp)
 	struct sockaddr_in *sin;
 	struct sockaddr_in6 *sin6, sin6_storage;
 	struct ip_map *ipm;
+	struct group_info *gi;
+	struct svc_cred *cred = &rqstp->rq_cred;
 
 	switch (rqstp->rq_addr.ss_family) {
 	case AF_INET:
@@ -721,6 +725,17 @@ svcauth_unix_set_client(struct svc_rqst *rqstp)
 			ip_map_cached_put(rqstp, ipm);
 			break;
 	}
+
+	gi = unix_gid_find(cred->cr_uid, rqstp);
+	switch (PTR_ERR(gi)) {
+	case -EAGAIN:
+		return SVC_DROP;
+	case -ENOENT:
+		break;
+	default:
+		put_group_info(cred->cr_group_info);
+		cred->cr_group_info = gi;
+	}
 	return SVC_OK;
 }
 
@@ -817,19 +832,11 @@ svcauth_unix_accept(struct svc_rqst *rqstp, __be32 *authp)
 	slen = svc_getnl(argv);			/* gids length */
 	if (slen > 16 || (len -= (slen + 2)*4) < 0)
 		goto badcred;
-	if (unix_gid_find(cred->cr_uid, &cred->cr_group_info, rqstp)
-	    == -EAGAIN)
+	cred->cr_group_info = groups_alloc(slen);
+	if (cred->cr_group_info == NULL)
 		return SVC_DROP;
-	if (cred->cr_group_info == NULL) {
-		cred->cr_group_info = groups_alloc(slen);
-		if (cred->cr_group_info == NULL)
-			return SVC_DROP;
-		for (i = 0; i < slen; i++)
-			GROUP_AT(cred->cr_group_info, i) = svc_getnl(argv);
-	} else {
-		for (i = 0; i < slen ; i++)
-			svc_getnl(argv);
-	}
+	for (i = 0; i < slen; i++)
+		GROUP_AT(cred->cr_group_info, i) = svc_getnl(argv);
 	if (svc_getu32(argv) != htonl(RPC_AUTH_NULL) || svc_getu32(argv) != 0) {
 		*authp = rpc_autherr_badverf;
 		return SVC_DENIED;
author	Linus Torvalds <torvalds@linux-foundation.org>	2009-12-16 10:43:34 -0800
committer	Linus Torvalds <torvalds@linux-foundation.org>	2009-12-16 10:43:34 -0800
commit	37c24b37fb2454e95136139d10bb6828967105bf (patch)
tree	d5c3fa61fa689567caeb2a7cb5891473e444ff7d
parent	5ac4d630eb87656bd4dc313b910776d54d88ea28 (diff)
parent	7663dacd926584093dfc350892792054692b6cb3 (diff)