Merge branch 'for-2.6.31' of git://fieldses.org/git/linux-nfsd

* 'for-2.6.31' of git://fieldses.org/git/linux-nfsd: (60 commits)
  SUNRPC: Fix the TCP server's send buffer accounting
  nfsd41: Backchannel: minorversion support for the back channel
  nfsd41: Backchannel: cleanup nfs4.0 callback encode routines
  nfsd41: Remove ip address collision detection case
  nfsd: optimise the starting of zero threads when none are running.
  nfsd: don't take nfsd_mutex twice when setting number of threads.
  nfsd41: sanity check client drc maxreqs
  nfsd41: move channel attributes from nfsd4_session to a nfsd4_channel_attr struct
  NFS: kill off complicated macro 'PROC'
  sunrpc: potential memory leak in function rdma_read_xdr
  nfsd: minor nfsd_vfs_write cleanup
  nfsd: Pull write-gathering code out of nfsd_vfs_write
  nfsd: track last inode only in use_wgather case
  sunrpc: align cache_clean work's timer
  nfsd: Use write gathering only with NFSv2
  NFSv4: kill off complicated macro 'PROC'
  NFSv4: do exact check about attribute specified
  knfsd: remove unreported filehandle stats counters
  knfsd: fix reply cache memory corruption
  knfsd: reply cache cleanups
  ...

29 files changed, 1329 insertions, 700 deletions

diff --git a/Documentation/filesystems/00-INDEX b/Documentation/filesystems/00-INDEX
index 8dd6db76171..f15621ee559 100644
--- a/Documentation/filesystems/00-INDEX
+++ b/Documentation/filesystems/00-INDEX
@@ -66,6 +66,10 @@ 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.
 nilfs2.txt
diff --git a/fs/Kconfig b/fs/Kconfig
index d78e950402c..a97263be6a9 100644
--- a/fs/Kconfig
+++ b/fs/Kconfig
@@ -236,10 +236,12 @@ source "fs/nfsd/Kconfig"
 
 config LOCKD
 	tristate
+	depends on FILE_LOCKING
 
 config LOCKD_V4
 	bool
 	depends on NFSD_V3 || NFS_V3
+	depends on FILE_LOCKING
 	default y
 
 config EXPORTFS
diff --git a/fs/lockd/svclock.c b/fs/lockd/svclock.c
index 83ee34203bd..e577a78d7ba 100644
--- a/fs/lockd/svclock.c
+++ b/fs/lockd/svclock.c
@@ -326,6 +326,8 @@ static void nlmsvc_freegrantargs(struct nlm_rqst *call)
 {
 	if (call->a_args.lock.oh.data != call->a_owner)
 		kfree(call->a_args.lock.oh.data);
+
+	locks_release_private(&call->a_args.lock.fl);
 }
 
 /*
diff --git a/fs/locks.c b/fs/locks.c
index ec3deea29e3..b6440f52178 100644
--- a/fs/locks.c
+++ b/fs/locks.c
@@ -151,7 +151,7 @@ static struct file_lock *locks_alloc_lock(void)
 	return kmem_cache_alloc(filelock_cache, GFP_KERNEL);
 }
 
-static void locks_release_private(struct file_lock *fl)
+void locks_release_private(struct file_lock *fl)
 {
 	if (fl->fl_ops) {
 		if (fl->fl_ops->fl_release_private)
@@ -165,6 +165,7 @@ static void locks_release_private(struct file_lock *fl)
 	}
 
 }
+EXPORT_SYMBOL_GPL(locks_release_private);
 
 /* Free a lock which is not in use. */
 static void locks_free_lock(struct file_lock *fl)
diff --git a/fs/nfs/Kconfig b/fs/nfs/Kconfig
index 5d6d6f41593..2a77bc25d5a 100644
--- a/fs/nfs/Kconfig
+++ b/fs/nfs/Kconfig
@@ -1,6 +1,6 @@
 config NFS_FS
 	tristate "NFS client support"
-	depends on INET
+	depends on INET && FILE_LOCKING
 	select LOCKD
 	select SUNRPC
 	select NFS_ACL_SUPPORT if NFS_V3_ACL
diff --git a/fs/nfsd/export.c b/fs/nfsd/export.c
index 8b1f8efb469..b92a27629fb 100644
--- a/fs/nfsd/export.c
+++ b/fs/nfsd/export.c
@@ -464,16 +464,11 @@ static int secinfo_parse(char **mesg, char *buf, struct svc_export *exp)
 		if (err)
 			return err;
 		/*
-		 * Just a quick sanity check; we could also try to check
-		 * whether this pseudoflavor is supported, but at worst
-		 * an unsupported pseudoflavor on the export would just
-		 * be a pseudoflavor that won't match the flavor of any
-		 * authenticated request.  The administrator will
-		 * probably discover the problem when someone fails to
-		 * authenticate.
+		 * XXX: It would be nice to also check whether this
+		 * pseudoflavor is supported, so we can discover the
+		 * problem at export time instead of when a client fails
+		 * to authenticate.
 		 */
-		if (f->pseudoflavor < 0)
-			return -EINVAL;
 		err = get_int(mesg, &f->flags);
 		if (err)
 			return err;
diff --git a/fs/nfsd/nfs3proc.c b/fs/nfsd/nfs3proc.c
index 7c9fe838f03..a713c418a92 100644
--- a/fs/nfsd/nfs3proc.c
+++ b/fs/nfsd/nfs3proc.c
@@ -652,8 +652,6 @@ nfsd3_proc_commit(struct svc_rqst * rqstp, struct nfsd3_commitargs *argp,
  * NFSv3 Server procedures.
  * Only the results of non-idempotent operations are cached.
  */
-#define nfs3svc_decode_voidargs		NULL
-#define nfs3svc_release_void		NULL
 #define nfs3svc_decode_fhandleargs	nfs3svc_decode_fhandle
 #define nfs3svc_encode_attrstatres	nfs3svc_encode_attrstat
 #define nfs3svc_encode_wccstatres	nfs3svc_encode_wccstat
@@ -686,28 +684,219 @@ struct nfsd3_voidargs { int dummy; };
 #define WC (7+pAT)	/* WCC attributes */
 
 static struct svc_procedure		nfsd_procedures3[22] = {
-  PROC(null,	 void,		void,		void,	  RC_NOCACHE, ST),
-  PROC(getattr,	 fhandle,	attrstat,	fhandle,  RC_NOCACHE, ST+AT),
-  PROC(setattr,  sattr,		wccstat,	fhandle,  RC_REPLBUFF, ST+WC),
-  PROC(lookup,	 dirop,		dirop,		fhandle2, RC_NOCACHE, ST+FH+pAT+pAT),
-  PROC(access,	 access,	access,		fhandle,  RC_NOCACHE, ST+pAT+1),
-  PROC(readlink, readlink,	readlink,	fhandle,  RC_NOCACHE, ST+pAT+1+NFS3_MAXPATHLEN/4),
-  PROC(read,	 read,		read,		fhandle,  RC_NOCACHE, ST+pAT+4+NFSSVC_MAXBLKSIZE/4),
-  PROC(write,	 write,		write,		fhandle,  RC_REPLBUFF, ST+WC+4),
-  PROC(create,	 create,	create,		fhandle2, RC_REPLBUFF, ST+(1+FH+pAT)+WC),
-  PROC(mkdir,	 mkdir,		create,		fhandle2, RC_REPLBUFF, ST+(1+FH+pAT)+WC),
-  PROC(symlink,	 symlink,	create,		fhandle2, RC_REPLBUFF, ST+(1+FH+pAT)+WC),
-  PROC(mknod,	 mknod,		create,		fhandle2, RC_REPLBUFF, ST+(1+FH+pAT)+WC),
-  PROC(remove,	 dirop,		wccstat,	fhandle,  RC_REPLBUFF, ST+WC),
-  PROC(rmdir,	 dirop,		wccstat,	fhandle,  RC_REPLBUFF, ST+WC),
-  PROC(rename,	 rename,	rename,		fhandle2, RC_REPLBUFF, ST+WC+WC),
-  PROC(link,	 link,		link,		fhandle2, RC_REPLBUFF, ST+pAT+WC),
-  PROC(readdir,	 readdir,	readdir,	fhandle,  RC_NOCACHE, 0),
-  PROC(readdirplus,readdirplus,	readdir,	fhandle,  RC_NOCACHE, 0),
-  PROC(fsstat,	 fhandle,	fsstat,		void,     RC_NOCACHE, ST+pAT+2*6+1),
-  PROC(fsinfo,   fhandle,	fsinfo,		void,     RC_NOCACHE, ST+pAT+12),
-  PROC(pathconf, fhandle,	pathconf,	void,     RC_NOCACHE, ST+pAT+6),
-  PROC(commit,	 commit,	commit,		fhandle,  RC_NOCACHE, ST+WC+2),
+	[NFS3PROC_NULL] = {
+		.pc_func = (svc_procfunc) nfsd3_proc_null,
+		.pc_encode = (kxdrproc_t) nfs3svc_encode_voidres,
+		.pc_argsize = sizeof(struct nfsd3_voidargs),
+		.pc_ressize = sizeof(struct nfsd3_voidres),
+		.pc_cachetype = RC_NOCACHE,
+		.pc_xdrressize = ST,
+	},
+	[NFS3PROC_GETATTR] = {
+		.pc_func = (svc_procfunc) nfsd3_proc_getattr,
+		.pc_decode = (kxdrproc_t) nfs3svc_decode_fhandleargs,
+		.pc_encode = (kxdrproc_t) nfs3svc_encode_attrstatres,
+		.pc_release = (kxdrproc_t) nfs3svc_release_fhandle,
+		.pc_argsize = sizeof(struct nfsd3_fhandleargs),
+		.pc_ressize = sizeof(struct nfsd3_attrstatres),
+		.pc_cachetype = RC_NOCACHE,
+		.pc_xdrressize = ST+AT,
+	},
+	[NFS3PROC_SETATTR] = {
+		.pc_func = (svc_procfunc) nfsd3_proc_setattr,
+		.pc_decode = (kxdrproc_t) nfs3svc_decode_sattrargs,
+		.pc_encode = (kxdrproc_t) nfs3svc_encode_wccstatres,
+		.pc_release = (kxdrproc_t) nfs3svc_release_fhandle,
+		.pc_argsize = sizeof(struct nfsd3_sattrargs),
+		.pc_ressize = sizeof(struct nfsd3_wccstatres),
+		.pc_cachetype = RC_REPLBUFF,
+		.pc_xdrressize = ST+WC,
+	},
+	[NFS3PROC_LOOKUP] = {
+		.pc_func = (svc_procfunc) nfsd3_proc_lookup,
+		.pc_decode = (kxdrproc_t) nfs3svc_decode_diropargs,
+		.pc_encode = (kxdrproc_t) nfs3svc_encode_diropres,
+		.pc_release = (kxdrproc_t) nfs3svc_release_fhandle2,
+		.pc_argsize = sizeof(struct nfsd3_diropargs),
+		.pc_ressize = sizeof(struct nfsd3_diropres),
+		.pc_cachetype = RC_NOCACHE,
+		.pc_xdrressize = ST+FH+pAT+pAT,
+	},
+	[NFS3PROC_ACCESS] = {
+		.pc_func = (svc_procfunc) nfsd3_proc_access,
+		.pc_decode = (kxdrproc_t) nfs3svc_decode_accessargs,
+		.pc_encode = (kxdrproc_t) nfs3svc_encode_accessres,
+		.pc_release = (kxdrproc_t) nfs3svc_release_fhandle,
+		.pc_argsize = sizeof(struct nfsd3_accessargs),
+		.pc_ressize = sizeof(struct nfsd3_accessres),
+		.pc_cachetype = RC_NOCACHE,
+		.pc_xdrressize = ST+pAT+1,
+	},
+	[NFS3PROC_READLINK] = {
+		.pc_func = (svc_procfunc) nfsd3_proc_readlink,
+		.pc_decode = (kxdrproc_t) nfs3svc_decode_readlinkargs,
+		.pc_encode = (kxdrproc_t) nfs3svc_encode_readlinkres,
+		.pc_release = (kxdrproc_t) nfs3svc_release_fhandle,
+		.pc_argsize = sizeof(struct nfsd3_readlinkargs),
+		.pc_ressize = sizeof(struct nfsd3_readlinkres),
+		.pc_cachetype = RC_NOCACHE,
+		.pc_xdrressize = ST+pAT+1+NFS3_MAXPATHLEN/4,
+	},
+	[NFS3PROC_READ] = {
+		.pc_func = (svc_procfunc) nfsd3_proc_read,
+		.pc_decode = (kxdrproc_t) nfs3svc_decode_readargs,
+		.pc_encode = (kxdrproc_t) nfs3svc_encode_readres,
+		.pc_release = (kxdrproc_t) nfs3svc_release_fhandle,
+		.pc_argsize = sizeof(struct nfsd3_readargs),
+		.pc_ressize = sizeof(struct nfsd3_readres),
+		.pc_cachetype = RC_NOCACHE,
+		.pc_xdrressize = ST+pAT+4+NFSSVC_MAXBLKSIZE/4,
+	},
+	[NFS3PROC_WRITE] = {
+		.pc_func = (svc_procfunc) nfsd3_proc_write,
+		.pc_decode = (kxdrproc_t) nfs3svc_decode_writeargs,
+		.pc_encode = (kxdrproc_t) nfs3svc_encode_writeres,
+		.pc_release = (kxdrproc_t) nfs3svc_release_fhandle,
+		.pc_argsize = sizeof(struct nfsd3_writeargs),
+		.pc_ressize = sizeof(struct nfsd3_writeres),
+		.pc_cachetype = RC_REPLBUFF,
+		.pc_xdrressize = ST+WC+4,
+	},
+	[NFS3PROC_CREATE] = {
+		.pc_func = (svc_procfunc) nfsd3_proc_create,
+		.pc_decode = (kxdrproc_t) nfs3svc_decode_createargs,
+		.pc_encode = (kxdrproc_t) nfs3svc_encode_createres,
+		.pc_release = (kxdrproc_t) nfs3svc_release_fhandle2,
+		.pc_argsize = sizeof(struct nfsd3_createargs),
+		.pc_ressize = sizeof(struct nfsd3_createres),
+		.pc_cachetype = RC_REPLBUFF,
+		.pc_xdrressize = ST+(1+FH+pAT)+WC,
+	},
+	[NFS3PROC_MKDIR] = {
+		.pc_func = (svc_procfunc) nfsd3_proc_mkdir,
+		.pc_decode = (kxdrproc_t) nfs3svc_decode_mkdirargs,
+		.pc_encode = (kxdrproc_t) nfs3svc_encode_createres,
+		.pc_release = (kxdrproc_t) nfs3svc_release_fhandle2,
+		.pc_argsize = sizeof(struct nfsd3_mkdirargs),
+		.pc_ressize = sizeof(struct nfsd3_createres),
+		.pc_cachetype = RC_REPLBUFF,
+		.pc_xdrressize = ST+(1+FH+pAT)+WC,
+	},
+	[NFS3PROC_SYMLINK] = {
+		.pc_func = (svc_procfunc) nfsd3_proc_symlink,
+		.pc_decode = (kxdrproc_t) nfs3svc_decode_symlinkargs,
+		.pc_encode = (kxdrproc_t) nfs3svc_encode_createres,
+		.pc_release = (kxdrproc_t) nfs3svc_release_fhandle2,
+		.pc_argsize = sizeof(struct nfsd3_symlinkargs),
+		.pc_ressize = sizeof(struct nfsd3_createres),
+		.pc_cachetype = RC_REPLBUFF,
+		.pc_xdrressize = ST+(1+FH+pAT)+WC,
+	},
+	[NFS3PROC_MKNOD] = {
+		.pc_func = (svc_procfunc) nfsd3_proc_mknod,
+		.pc_decode = (kxdrproc_t) nfs3svc_decode_mknodargs,
+		.pc_encode = (kxdrproc_t) nfs3svc_encode_createres,
+		.pc_release = (kxdrproc_t) nfs3svc_release_fhandle2,
+		.pc_argsize = sizeof(struct nfsd3_mknodargs),
+		.pc_ressize = sizeof(struct nfsd3_createres),
+		.pc_cachetype = RC_REPLBUFF,
+		.pc_xdrressize = ST+(1+FH+pAT)+WC,
+	},
+	[NFS3PROC_REMOVE] = {
+		.pc_func = (svc_procfunc) nfsd3_proc_remove,
+		.pc_decode = (kxdrproc_t) nfs3svc_decode_diropargs,
+		.pc_encode = (kxdrproc_t) nfs3svc_encode_wccstatres,
+		.pc_release = (kxdrproc_t) nfs3svc_release_fhandle,
+		.pc_argsize = sizeof(struct nfsd3_diropargs),
+		.pc_ressize = sizeof(struct nfsd3_wccstatres),
+		.pc_cachetype = RC_REPLBUFF,
+		.pc_xdrressize = ST+WC,
+	},
+	[NFS3PROC_RMDIR] = {
+		.pc_func = (svc_procfunc) nfsd3_proc_rmdir,
+		.pc_decode = (kxdrproc_t) nfs3svc_decode_diropargs,
+		.pc_encode = (kxdrproc_t) nfs3svc_encode_wccstatres,
+		.pc_release = (kxdrproc_t) nfs3svc_release_fhandle,
+		.pc_argsize = sizeof(struct nfsd3_diropargs),
+		.pc_ressize = sizeof(struct nfsd3_wccstatres),
+		.pc_cachetype = RC_REPLBUFF,
+		.pc_xdrressize = ST+WC,
+	},
+	[NFS3PROC_RENAME] = {
+		.pc_func = (svc_procfunc) nfsd3_proc_rename,
+		.pc_decode = (kxdrproc_t) nfs3svc_decode_renameargs,
+		.pc_encode = (kxdrproc_t) nfs3svc_encode_renameres,
+		.pc_release = (kxdrproc_t) nfs3svc_release_fhandle2,
+		.pc_argsize = sizeof(struct nfsd3_renameargs),
+		.pc_ressize = sizeof(struct nfsd3_renameres),
+		.pc_cachetype = RC_REPLBUFF,
+		.pc_xdrressize = ST+WC+WC,
+	},
+	[NFS3PROC_LINK] = {
+		.pc_func = (svc_procfunc) nfsd3_proc_link,
+		.pc_decode = (kxdrproc_t) nfs3svc_decode_linkargs,
+		.pc_encode = (kxdrproc_t) nfs3svc_encode_linkres,
+		.pc_release = (kxdrproc_t) nfs3svc_release_fhandle2,
+		.pc_argsize = sizeof(struct nfsd3_linkargs),
+		.pc_ressize = sizeof(struct nfsd3_linkres),
+		.pc_cachetype = RC_REPLBUFF,
+		.pc_xdrressize = ST+pAT+WC,
+	},
+	[NFS3PROC_READDIR] = {
+		.pc_func = (svc_procfunc) nfsd3_proc_readdir,
+		.pc_decode = (kxdrproc_t) nfs3svc_decode_readdirargs,
+		.pc_encode = (kxdrproc_t) nfs3svc_encode_readdirres,
+		.pc_release = (kxdrproc_t) nfs3svc_release_fhandle,
+		.pc_argsize = sizeof(struct nfsd3_readdirargs),
+		.pc_ressize = sizeof(struct nfsd3_readdirres),
+		.pc_cachetype = RC_NOCACHE,
+	},
+	[NFS3PROC_READDIRPLUS] = {
+		.pc_func = (svc_procfunc) nfsd3_proc_readdirplus,
+		.pc_decode = (kxdrproc_t) nfs3svc_decode_readdirplusargs,
+		.pc_encode = (kxdrproc_t) nfs3svc_encode_readdirres,
+		.pc_release = (kxdrproc_t) nfs3svc_release_fhandle,
+		.pc_argsize = sizeof(struct nfsd3_readdirplusargs),
+		.pc_ressize = sizeof(struct nfsd3_readdirres),
+		.pc_cachetype = RC_NOCACHE,
+	},
+	[NFS3PROC_FSSTAT] = {
+		.pc_func = (svc_procfunc) nfsd3_proc_fsstat,
+		.pc_decode = (kxdrproc_t) nfs3svc_decode_fhandleargs,
+		.pc_encode = (kxdrproc_t) nfs3svc_encode_fsstatres,
+		.pc_argsize = sizeof(struct nfsd3_fhandleargs),
+		.pc_ressize = sizeof(struct nfsd3_fsstatres),
+		.pc_cachetype = RC_NOCACHE,
+		.pc_xdrressize = ST+pAT+2*6+1,
+	},
+	[NFS3PROC_FSINFO] = {
+		.pc_func = (svc_procfunc) nfsd3_proc_fsinfo,
+		.pc_decode = (kxdrproc_t) nfs3svc_decode_fhandleargs,
+		.pc_encode = (kxdrproc_t) nfs3svc_encode_fsinfores,
+		.pc_argsize = sizeof(struct nfsd3_fhandleargs),
+		.pc_ressize = sizeof(struct nfsd3_fsinfores),
+		.pc_cachetype = RC_NOCACHE,
+		.pc_xdrressize = ST+pAT+12,
+	},
+	[NFS3PROC_PATHCONF] = {
+		.pc_func = (svc_procfunc) nfsd3_proc_pathconf,
+		.pc_decode = (kxdrproc_t) nfs3svc_decode_fhandleargs,
+		.pc_encode = (kxdrproc_t) nfs3svc_encode_pathconfres,
+		.pc_argsize = sizeof(struct nfsd3_fhandleargs),
+		.pc_ressize = sizeof(struct nfsd3_pathconfres),
+		.pc_cachetype = RC_NOCACHE,
+		.pc_xdrressize = ST+pAT+6,
+	},
+	[NFS3PROC_COMMIT] = {
+		.pc_func = (svc_procfunc) nfsd3_proc_commit,
+		.pc_decode = (kxdrproc_t) nfs3svc_decode_commitargs,
+		.pc_encode = (kxdrproc_t) nfs3svc_encode_commitres,
+		.pc_release = (kxdrproc_t) nfs3svc_release_fhandle,
+		.pc_argsize = sizeof(struct nfsd3_commitargs),
+		.pc_ressize = sizeof(struct nfsd3_commitres),
+		.pc_cachetype = RC_NOCACHE,
+		.pc_xdrressize = ST+WC+2,
+	},
 };
 
 struct svc_version	nfsd_version3 = {
diff --git a/fs/nfsd/nfs3xdr.c b/fs/nfsd/nfs3xdr.c
index 17d0dd99720..01d4ec1c88e 100644
--- a/fs/nfsd/nfs3xdr.c
+++ b/fs/nfsd/nfs3xdr.c
@@ -272,6 +272,7 @@ void fill_post_wcc(struct svc_fh *fhp)
 
 	err = vfs_getattr(fhp->fh_export->ex_path.mnt, fhp->fh_dentry,
 			&fhp->fh_post_attr);
+	fhp->fh_post_change = fhp->fh_dentry->d_inode->i_version;
 	if (err)
 		fhp->fh_post_saved = 0;
 	else
diff --git a/fs/nfsd/nfs4callback.c b/fs/nfsd/nfs4callback.c
index 290289bd44f..3fd23f7acec 100644
--- a/fs/nfsd/nfs4callback.c
+++ b/fs/nfsd/nfs4callback.c
@@ -140,8 +140,10 @@ struct nfs4_cb_compound_hdr {
 	int		status;
 	u32		ident;
 	u32		nops;
+	__be32		*nops_p;
+	u32		minorversion;
 	u32		taglen;
-	char *		tag;
+	char		*tag;
 };
 
 static struct {
@@ -201,33 +203,39 @@ nfs_cb_stat_to_errno(int stat)
  * XDR encode
  */
 
-static int
+static void
 encode_cb_compound_hdr(struct xdr_stream *xdr, struct nfs4_cb_compound_hdr *hdr)
 {
 	__be32 * p;
 
 	RESERVE_SPACE(16);
 	WRITE32(0);            /* tag length is always 0 */
-	WRITE32(NFS4_MINOR_VERSION);
+	WRITE32(hdr->minorversion);
 	WRITE32(hdr->ident);
+	hdr->nops_p = p;
 	WRITE32(hdr->nops);
-	return 0;
 }
 
-static int
-encode_cb_recall(struct xdr_stream *xdr, struct nfs4_cb_recall *cb_rec)
+static void encode_cb_nops(struct nfs4_cb_compound_hdr *hdr)
+{
+	*hdr->nops_p = htonl(hdr->nops);
+}
+
+static void
+encode_cb_recall(struct xdr_stream *xdr, struct nfs4_delegation *dp,
+		struct nfs4_cb_compound_hdr *hdr)
 {
 	__be32 *p;
-	int len = cb_rec->cbr_fh.fh_size;
+	int len = dp->dl_fh.fh_size;
 
-	RESERVE_SPACE(12+sizeof(cb_rec->cbr_stateid) + len);
+	RESERVE_SPACE(12+sizeof(dp->dl_stateid) + len);
 	WRITE32(OP_CB_RECALL);
-	WRITE32(cb_rec->cbr_stateid.si_generation);
-	WRITEMEM(&cb_rec->cbr_stateid.si_opaque, sizeof(stateid_opaque_t));
-	WRITE32(cb_rec->cbr_trunc);
+	WRITE32(dp->dl_stateid.si_generation);
+	WRITEMEM(&dp->dl_stateid.si_opaque, sizeof(stateid_opaque_t));
+	WRITE32(0); /* truncate optimization not implemented */
 	WRITE32(len);
-	WRITEMEM(&cb_rec->cbr_fh.fh_base, len);
-	return 0;
+	WRITEMEM(&dp->dl_fh.fh_base, len);
+	hdr->nops++;
 }
 
 static int
@@ -241,17 +249,18 @@ nfs4_xdr_enc_cb_null(struct rpc_rqst *req, __be32 *p)
 }
 
 static int
-nfs4_xdr_enc_cb_recall(struct rpc_rqst *req, __be32 *p, struct nfs4_cb_recall *args)
+nfs4_xdr_enc_cb_recall(struct rpc_rqst *req, __be32 *p, struct nfs4_delegation *args)
 {
 	struct xdr_stream xdr;
 	struct nfs4_cb_compound_hdr hdr = {
-		.ident = args->cbr_ident,
-		.nops   = 1,
+		.ident = args->dl_ident,
 	};
 
 	xdr_init_encode(&xdr, &req->rq_snd_buf, p);
 	encode_cb_compound_hdr(&xdr, &hdr);
-	return (encode_cb_recall(&xdr, args));
+	encode_cb_recall(&xdr, args, &hdr);
+	encode_cb_nops(&hdr);
+	return 0;
 }
 
 
@@ -358,18 +367,21 @@ static struct rpc_program cb_program = {
 		.pipe_dir_name  = "/nfsd4_cb",
 };
 
+static int max_cb_time(void)
+{
+	return max(NFSD_LEASE_TIME/10, (time_t)1) * HZ;
+}
+
 /* Reference counting, callback cleanup, etc., all look racy as heck.
  * And why is cb_set an atomic? */
 
-static struct rpc_clnt *setup_callback_client(struct nfs4_client *clp)
+int setup_callback_client(struct nfs4_client *clp)
 {
 	struct sockaddr_in	addr;
-	struct nfs4_callback    *cb = &clp->cl_callback;
+	struct nfs4_cb_conn *cb = &clp->cl_cb_conn;
 	struct rpc_timeout	timeparms = {
-		.to_initval	= (NFSD_LEASE_TIME/4) * HZ,
-		.to_retries	= 5,
-		.to_maxval	= (NFSD_LEASE_TIME/2) * HZ,
-		.to_exponential	= 1,
+		.to_initval	= max_cb_time(),
+		.to_retries	= 0,
 	};
 	struct rpc_create_args args = {
 		.protocol	= IPPROTO_TCP,
@@ -386,7 +398,7 @@ static struct rpc_clnt *setup_callback_client(struct nfs4_client *clp)
 	struct rpc_clnt *client;
 
 	if (!clp->cl_principal && (clp->cl_flavor >= RPC_AUTH_GSS_KRB5))
-		return ERR_PTR(-EINVAL);
+		return -EINVAL;
 
 	/* Initialize address */
 	memset(&addr, 0, sizeof(addr));
@@ -396,48 +408,77 @@ static struct rpc_clnt *setup_callback_client(struct nfs4_client *clp)
 
 	/* Create RPC client */
 	client = rpc_create(&args);
-	if (IS_ERR(client))
+	if (IS_ERR(client)) {
 		dprintk("NFSD: couldn't create callback client: %ld\n",
 			PTR_ERR(client));
-	return client;
+		return PTR_ERR(client);
+	}
+	cb->cb_client = client;
+	return 0;
+
+}
+
+static void warn_no_callback_path(struct nfs4_client *clp, int reason)
+{
+	dprintk("NFSD: warning: no callback path to client %.*s: error %d\n",
+		(int)clp->cl_name.len, clp->cl_name.data, reason);
+}
+
+static void nfsd4_cb_probe_done(struct rpc_task *task, void *calldata)
+{
+	struct nfs4_client *clp = calldata;
+
+	if (task->tk_status)
+		warn_no_callback_path(clp, task->tk_status);
+	else
+		atomic_set(&clp->cl_cb_conn.cb_set, 1);
+	put_nfs4_client(clp);
+}
+
+static const struct rpc_call_ops nfsd4_cb_probe_ops = {
+	.rpc_call_done = nfsd4_cb_probe_done,
+};
 
+static struct rpc_cred *lookup_cb_cred(struct nfs4_cb_conn *cb)
+{
+	struct auth_cred acred = {
+		.machine_cred = 1
+	};
+
+	/*
+	 * Note in the gss case this doesn't actually have to wait for a
+	 * gss upcall (or any calls to the client); this just creates a
+	 * non-uptodate cred which the rpc state machine will fill in with
+	 * a refresh_upcall later.
+	 */
+	return rpcauth_lookup_credcache(cb->cb_client->cl_auth, &acred,
+							RPCAUTH_LOOKUP_NEW);
 }
 
-static int do_probe_callback(void *data)
+void do_probe_callback(struct nfs4_client *clp)
 {
-	struct nfs4_client *clp = data;
-	struct nfs4_callback    *cb = &clp->cl_callback;
+	struct nfs4_cb_conn *cb = &clp->cl_cb_conn;
 	struct rpc_message msg = {
 		.rpc_proc       = &nfs4_cb_procedures[NFSPROC4_CLNT_CB_NULL],
 		.rpc_argp       = clp,
 	};
-	struct rpc_clnt *client;
+	struct rpc_cred *cred;
 	int status;
 
-	client = setup_callback_client(clp);
-	if (IS_ERR(client)) {
-		status = PTR_ERR(client);
-		dprintk("NFSD: couldn't create callback client: %d\n",
-								status);
-		goto out_err;
+	cred = lookup_cb_cred(cb);
+	if (IS_ERR(cred)) {
+		status = PTR_ERR(cred);
+		goto out;
+	}
+	cb->cb_cred = cred;
+	msg.rpc_cred = cb->cb_cred;
+	status = rpc_call_async(cb->cb_client, &msg, RPC_TASK_SOFT,
+				&nfsd4_cb_probe_ops, (void *)clp);
+out:
+	if (status) {
+		warn_no_callback_path(clp, status);
+		put_nfs4_client(clp);
 	}
-
-	status = rpc_call_sync(client, &msg, RPC_TASK_SOFT);
-
-	if (status)
-		goto out_release_client;
-
-	cb->cb_client = client;
-	atomic_set(&cb->cb_set, 1);
-	put_nfs4_client(clp);
-	return 0;
-out_release_client:
-	rpc_shutdown_client(client);
-out_err:
-	dprintk("NFSD: warning: no callback path to client %.*s: error %d\n",
-		(int)clp->cl_name.len, clp->cl_name.data, status);
-	put_nfs4_client(clp);
-	return 0;
 }
 
 /*
@@ -446,21 +487,65 @@ out_err:
 void
 nfsd4_probe_callback(struct nfs4_client *clp)
 {
-	struct task_struct *t;
+	int status;
 
-	BUG_ON(atomic_read(&clp->cl_callback.cb_set));
+	BUG_ON(atomic_read(&clp->cl_cb_conn.cb_set));
+
+	status = setup_callback_client(clp);
+	if (status) {
+		warn_no_callback_path(clp, status);
+		return;
+	}
 
 	/* the task holds a reference to the nfs4_client struct */
 	atomic_inc(&clp->cl_count);
 
-	t = kthread_run(do_probe_callback, clp, "nfs4_cb_probe");
+	do_probe_callback(clp);
+}
 
-	if (IS_ERR(t))
-		atomic_dec(&clp->cl_count);
+static void nfsd4_cb_recall_done(struct rpc_task *task, void *calldata)
+{
+	struct nfs4_delegation *dp = calldata;
+	struct nfs4_client *clp = dp->dl_client;
 
-	return;
+	switch (task->tk_status) {
+	case -EIO:
+		/* Network partition? */
+		atomic_set(&clp->cl_cb_conn.cb_set, 0);
+		warn_no_callback_path(clp, task->tk_status);
+	case -EBADHANDLE:
+	case -NFS4ERR_BAD_STATEID:
+		/* Race: client probably got cb_recall
+		 * before open reply granting delegation */
+		break;
+	default:
+		/* success, or error we can't handle */
+		return;
+	}
+	if (dp->dl_retries--) {
+		rpc_delay(task, 2*HZ);
+		task->tk_status = 0;
+		rpc_restart_call(task);
+	} else {
+		atomic_set(&clp->cl_cb_conn.cb_set, 0);
+		warn_no_callback_path(clp, task->tk_status);
+	}
+}
+
+static void nfsd4_cb_recall_release(void *calldata)
+{
+	struct nfs4_delegation *dp = calldata;
+	struct nfs4_client *clp = dp->dl_client;
+
+	nfs4_put_delegation(dp);
+	put_nfs4_client(clp);
 }
 
+static const struct rpc_call_ops nfsd4_cb_recall_ops = {
+	.rpc_call_done = nfsd4_cb_recall_done,
+	.rpc_release = nfsd4_cb_recall_release,
+};
+
 /*
  * called with dp->dl_count inc'ed.
  */
@@ -468,41 +553,19 @@ void
 nfsd4_cb_recall(struct nfs4_delegation *dp)
 {
 	struct nfs4_client *clp = dp->dl_client;
-	struct rpc_clnt *clnt = clp->cl_callback.cb_client;
-	struct nfs4_cb_recall *cbr = &dp->dl_recall;
+	struct rpc_clnt *clnt = clp->cl_cb_conn.cb_client;
 	struct rpc_message msg = {
 		.rpc_proc = &nfs4_cb_procedures[NFSPROC4_CLNT_CB_RECALL],
-		.rpc_argp = cbr,
+		.rpc_argp = dp,
+		.rpc_cred = clp->cl_cb_conn.cb_cred
 	};
-	int retries = 1;
-	int status = 0;
-
-	cbr->cbr_trunc = 0; /* XXX need to implement truncate optimization */
-	cbr->cbr_dp = dp;
-
-	status = rpc_call_sync(clnt, &msg, RPC_TASK_SOFT);
-	while (retries--) {
-		switch (status) {
-			case -EIO:
-				/* Network partition? */
-				atomic_set(&clp->cl_callback.cb_set, 0);
-			case -EBADHANDLE:
-			case -NFS4ERR_BAD_STATEID:
-				/* Race: client probably got cb_recall
-				 * before open reply granting delegation */
-				break;
-			default:
-				goto out_put_cred;
-		}
-		ssleep(2);
-		status = rpc_call_sync(clnt, &msg, RPC_TASK_SOFT);
+	int status;
+
+	dp->dl_retries = 1;
+	status = rpc_call_async(clnt, &msg, RPC_TASK_SOFT,
+				&nfsd4_cb_recall_ops, dp);
+	if (status) {
+		put_nfs4_client(clp);
+		nfs4_put_delegation(dp);
 	}
-out_put_cred:
-	/*
-	 * Success or failure, now we're either waiting for lease expiration
-	 * or deleg_return.
-	 */
-	put_nfs4_client(clp);
-	nfs4_put_delegation(dp);
-	return;
 }
diff --git a/fs/nfsd/nfs4proc.c b/fs/nfsd/nfs4proc.c
index b2883e9c638..7c8801769a3 100644
--- a/fs/nfsd/nfs4proc.c
+++ b/fs/nfsd/nfs4proc.c
@@ -51,6 +51,78 @@
 
 #define NFSDDBG_FACILITY		NFSDDBG_PROC
 
+static u32 nfsd_attrmask[] = {
+	NFSD_WRITEABLE_ATTRS_WORD0,
+	NFSD_WRITEABLE_ATTRS_WORD1,
+	NFSD_WRITEABLE_ATTRS_WORD2
+};
+
+static u32 nfsd41_ex_attrmask[] = {
+	NFSD_SUPPATTR_EXCLCREAT_WORD0,
+	NFSD_SUPPATTR_EXCLCREAT_WORD1,
+	NFSD_SUPPATTR_EXCLCREAT_WORD2
+};
+
+static __be32
+check_attr_support(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
+		   u32 *bmval, u32 *writable)
+{
+	struct dentry *dentry = cstate->current_fh.fh_dentry;
+	struct svc_export *exp = cstate->current_fh.fh_export;
+
+	/*
+	 * Check about attributes are supported by the NFSv4 server or not.
+	 * According to spec, unsupported attributes return ERR_ATTRNOTSUPP.
+	 */
+	if ((bmval[0] & ~nfsd_suppattrs0(cstate->minorversion)) ||
+	    (bmval[1] & ~nfsd_suppattrs1(cstate->minorversion)) ||
+	    (bmval[2] & ~nfsd_suppattrs2(cstate->minorversion)))
+		return nfserr_attrnotsupp;
+
+	/*
+	 * Check FATTR4_WORD0_ACL & FATTR4_WORD0_FS_LOCATIONS can be supported
+	 * in current environment or not.
+	 */
+	if (bmval[0] & FATTR4_WORD0_ACL) {
+		if (!IS_POSIXACL(dentry->d_inode))
+			return nfserr_attrnotsupp;
+	}
+	if (bmval[0] & FATTR4_WORD0_FS_LOCATIONS) {
+		if (exp->ex_fslocs.locations == NULL)
+			return nfserr_attrnotsupp;
+	}
+
+	/*
+	 * According to spec, read-only attributes return ERR_INVAL.
+	 */
+	if (writable) {
+		if ((bmval[0] & ~writable[0]) || (bmval[1] & ~writable[1]) ||
+		    (bmval[2] & ~writable[2]))
+			return nfserr_inval;
+	}
+
+	return nfs_ok;
+}
+
+static __be32
+nfsd4_check_open_attributes(struct svc_rqst *rqstp,
+	struct nfsd4_compound_state *cstate, struct nfsd4_open *open)
+{
+	__be32 status = nfs_ok;
+
+	if (open->op_create == NFS4_OPEN_CREATE) {
+		if (open->op_createmode == NFS4_CREATE_UNCHECKED
+		    || open->op_createmode == NFS4_CREATE_GUARDED)
+			status = check_attr_support(rqstp, cstate,
+					open->op_bmval, nfsd_attrmask);
+		else if (open->op_createmode == NFS4_CREATE_EXCLUSIVE4_1)
+			status = check_attr_support(rqstp, cstate,
+					open->op_bmval, nfsd41_ex_attrmask);
+	}
+
+	return status;
+}
+
 static inline void
 fh_dup2(struct svc_fh *dst, struct svc_fh *src)
 {
@@ -225,6 +297,10 @@ nfsd4_open(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
 	if (status)
 		goto out;
 
+	status = nfsd4_check_open_attributes(rqstp, cstate, ope