Merge tag 'nfs-for-3.6-1' of git://git.linux-nfs.org/projects/trondmy/linux-nfs

Pull NFS client updates from Trond Myklebust:
 "Features include:
   - More preparatory patches for modularising NFSv2/v3/v4.  Split out
     the various NFSv2/v3/v4-specific code into separate files
   - More preparation for the NFSv4 migration code
   - Ensure that OPEN(O_CREATE) observes the pNFS mds threshold
     parameters
   - pNFS fast failover when the data servers are down
   - Various cleanups and debugging patches"

* tag 'nfs-for-3.6-1' of git://git.linux-nfs.org/projects/trondmy/linux-nfs: (67 commits)
  nfs: fix fl_type tests in NFSv4 code
  NFS: fix pnfs regression with directio writes
  NFS: fix pnfs regression with directio reads
  sunrpc: clnt: Add missing braces
  nfs: fix stub return type warnings
  NFS: exit_nfs_v4() shouldn't be an __exit function
  SUNRPC: Add a missing spin_unlock to gss_mech_list_pseudoflavors
  NFS: Split out NFS v4 client functions
  NFS: Split out the NFS v4 filesystem types
  NFS: Create a single nfs_clone_super() function
  NFS: Split out NFS v4 server creating code
  NFS: Initialize the NFS v4 client from init_nfs_v4()
  NFS: Move the v4 getroot code to nfs4getroot.c
  NFS: Split out NFS v4 file operations
  NFS: Initialize v4 sysctls from nfs_init_v4()
  NFS: Create an init_nfs_v4() function
  NFS: Split out NFS v4 inode operations
  NFS: Split out NFS v3 inode operations
  NFS: Split out NFS v2 inode operations
  NFS: Clean up nfs4_proc_setclientid() and friends
  ...

fs/nfs/Kconfig

@@ -88,9 +88,8 @@ config NFS_V4
 
 config NFS_V4_1
 	bool "NFS client support for NFSv4.1 (EXPERIMENTAL)"
-	depends on NFS_FS && NFS_V4 && EXPERIMENTAL
+	depends on NFS_V4 && EXPERIMENTAL
 	select SUNRPC_BACKCHANNEL
-	select PNFS_FILE_LAYOUT
 	help
 	  This option enables support for minor version 1 of the NFSv4 protocol
 	  (RFC 5661) in the kernel's NFS client.
@@ -99,15 +98,17 @@ config NFS_V4_1
 
 config PNFS_FILE_LAYOUT
 	tristate
+	depends on NFS_V4_1
+	default m
 
 config PNFS_BLOCK
 	tristate
-	depends on NFS_FS && NFS_V4_1 && BLK_DEV_DM
+	depends on NFS_V4_1 && BLK_DEV_DM
 	default m
 
 config PNFS_OBJLAYOUT
 	tristate
-	depends on NFS_FS && NFS_V4_1 && SCSI_OSD_ULD
+	depends on NFS_V4_1 && SCSI_OSD_ULD
 	default m
 
 config NFS_V4_1_IMPLEMENTATION_ID_DOMAIN

fs/nfs/Makefile

@@ -13,11 +13,16 @@ nfs-$(CONFIG_NFS_V2)	+= proc.o nfs2xdr.o
 nfs-$(CONFIG_NFS_V3)	+= nfs3proc.o nfs3xdr.o
 nfs-$(CONFIG_NFS_V3_ACL)	+= nfs3acl.o
 nfs-$(CONFIG_NFS_V4)	+= nfs4proc.o nfs4xdr.o nfs4state.o nfs4renewd.o \
-			   delegation.o idmap.o \
+			   nfs4super.o nfs4file.o delegation.o idmap.o \
 			   callback.o callback_xdr.o callback_proc.o \
-			   nfs4namespace.o
+			   nfs4namespace.o nfs4getroot.o nfs4client.o
 nfs-$(CONFIG_NFS_V4_1)	+= pnfs.o pnfs_dev.o
-nfs-$(CONFIG_SYSCTL) += sysctl.o
+
+ifeq ($(CONFIG_SYSCTL), y)
+nfs-y += sysctl.o
+nfs-$(CONFIG_NFS_V4) += nfs4sysctl.o
+endif
+
 nfs-$(CONFIG_NFS_FSCACHE) += fscache.o fscache-index.o
 
 obj-$(CONFIG_PNFS_FILE_LAYOUT) += nfs_layout_nfsv41_files.o

fs/nfs/client.c

@@ -56,35 +56,6 @@
 #define NFSDBG_FACILITY		NFSDBG_CLIENT
 
 static DECLARE_WAIT_QUEUE_HEAD(nfs_client_active_wq);
-#ifdef CONFIG_NFS_V4
-
-/*
- * Get a unique NFSv4.0 callback identifier which will be used
- * by the V4.0 callback service to lookup the nfs_client struct
- */
-static int nfs_get_cb_ident_idr(struct nfs_client *clp, int minorversion)
-{
-	int ret = 0;
-	struct nfs_net *nn = net_generic(clp->cl_net, nfs_net_id);
-
-	if (clp->rpc_ops->version != 4 || minorversion != 0)
-		return ret;
-retry:
-	if (!idr_pre_get(&nn->cb_ident_idr, GFP_KERNEL))
-		return -ENOMEM;
-	spin_lock(&nn->nfs_client_lock);
-	ret = idr_get_new(&nn->cb_ident_idr, clp, &clp->cl_cb_ident);
-	spin_unlock(&nn->nfs_client_lock);
-	if (ret == -EAGAIN)
-		goto retry;
-	return ret;
-}
-#endif /* CONFIG_NFS_V4 */
-
-/*
- * Turn off NFSv4 uid/gid mapping when using AUTH_SYS
- */
-static bool nfs4_disable_idmapping = true;
 
 /*
  * RPC cruft for NFS
@@ -130,24 +101,13 @@ const struct rpc_program nfsacl_program = {
 };
 #endif  /* CONFIG_NFS_V3_ACL */
 
-struct nfs_client_initdata {
-	unsigned long init_flags;
-	const char *hostname;
-	const struct sockaddr *addr;
-	size_t addrlen;
-	const struct nfs_rpc_ops *rpc_ops;
-	int proto;
-	u32 minorversion;
-	struct net *net;
-};
-
 /*
  * Allocate a shared client record
  *
  * Since these are allocated/deallocated very rarely, we don't
  * bother putting them in a slab cache...
  */
-static struct nfs_client *nfs_alloc_client(const struct nfs_client_initdata *cl_init)
+struct nfs_client *nfs_alloc_client(const struct nfs_client_initdata *cl_init)
 {
 	struct nfs_client *clp;
 	struct rpc_cred *cred;
@@ -177,18 +137,6 @@ static struct nfs_client *nfs_alloc_client(const struct nfs_client_initdata *cl_
 	clp->cl_proto = cl_init->proto;
 	clp->cl_net = get_net(cl_init->net);
 
-#ifdef CONFIG_NFS_V4
-	err = nfs_get_cb_ident_idr(clp, cl_init->minorversion);
-	if (err)
-		goto error_cleanup;
-
-	spin_lock_init(&clp->cl_lock);
-	INIT_DELAYED_WORK(&clp->cl_renewd, nfs4_renew_state);
-	rpc_init_wait_queue(&clp->cl_rpcwaitq, "NFS client");
-	clp->cl_state = 1 << NFS4CLNT_LEASE_EXPIRED;
-	clp->cl_minorversion = cl_init->minorversion;
-	clp->cl_mvops = nfs_v4_minor_ops[cl_init->minorversion];
-#endif
 	cred = rpc_lookup_machine_cred("*");
 	if (!IS_ERR(cred))
 		clp->cl_machine_cred = cred;
@@ -203,45 +151,6 @@ error_0:
 }
 
 #ifdef CONFIG_NFS_V4
-#ifdef CONFIG_NFS_V4_1
-static void nfs4_shutdown_session(struct nfs_client *clp)
-{
-	if (nfs4_has_session(clp)) {
-		nfs4_destroy_session(clp->cl_session);
-		nfs4_destroy_clientid(clp);
-	}
-
-}
-#else /* CONFIG_NFS_V4_1 */
-static void nfs4_shutdown_session(struct nfs_client *clp)
-{
-}
-#endif /* CONFIG_NFS_V4_1 */
-
-/*
- * Destroy the NFS4 callback service
- */
-static void nfs4_destroy_callback(struct nfs_client *clp)
-{
-	if (__test_and_clear_bit(NFS_CS_CALLBACK, &clp->cl_res_state))
-		nfs_callback_down(clp->cl_mvops->minor_version);
-}
-
-static void nfs4_shutdown_client(struct nfs_client *clp)
-{
-	if (__test_and_clear_bit(NFS_CS_RENEWD, &clp->cl_res_state))
-		nfs4_kill_renewd(clp);
-	nfs4_shutdown_session(clp);
-	nfs4_destroy_callback(clp);
-	if (__test_and_clear_bit(NFS_CS_IDMAP, &clp->cl_res_state))
-		nfs_idmap_delete(clp);
-
-	rpc_destroy_wait_queue(&clp->cl_rpcwaitq);
-	kfree(clp->cl_serverowner);
-	kfree(clp->cl_serverscope);
-	kfree(clp->cl_implid);
-}
-
 /* idr_remove_all is not needed as all id's are removed by nfs_put_client */
 void nfs_cleanup_cb_ident_idr(struct net *net)
 {
@@ -264,16 +173,7 @@ static void pnfs_init_server(struct nfs_server *server)
 	rpc_init_wait_queue(&server->roc_rpcwaitq, "pNFS ROC");
 }
 
-static void nfs4_destroy_server(struct nfs_server *server)
-{
-	nfs4_purge_state_owners(server);
-}
-
 #else
-static void nfs4_shutdown_client(struct nfs_client *clp)
-{
-}
-
 void nfs_cleanup_cb_ident_idr(struct net *net)
 {
 }
@@ -291,12 +191,10 @@ static void pnfs_init_server(struct nfs_server *server)
 /*
  * Destroy a shared client record
  */
-static void nfs_free_client(struct nfs_client *clp)
+void nfs_free_client(struct nfs_client *clp)
 {
 	dprintk("--> nfs_free_client(%u)\n", clp->rpc_ops->version);
 
-	nfs4_shutdown_client(clp);
-
 	nfs_fscache_release_client_cookie(clp);
 
 	/* -EIO all pending I/O */
@@ -333,7 +231,7 @@ void nfs_put_client(struct nfs_client *clp)
 
 		BUG_ON(!list_empty(&clp->cl_superblocks));
 
-		nfs_free_client(clp);
+		clp->rpc_ops->free_client(clp);
 	}
 }
 EXPORT_SYMBOL_GPL(nfs_put_client);
@@ -412,8 +310,8 @@ static int nfs_sockaddr_cmp_ip4(const struct sockaddr *sa1,
  * Test if two socket addresses represent the same actual socket,
  * by comparing (only) relevant fields, excluding the port number.
  */
-static int nfs_sockaddr_match_ipaddr(const struct sockaddr *sa1,
-				     const struct sockaddr *sa2)
+int nfs_sockaddr_match_ipaddr(const struct sockaddr *sa1,
+			      const struct sockaddr *sa2)
 {
 	if (sa1->sa_family != sa2->sa_family)
 		return 0;
@@ -447,33 +345,6 @@ static int nfs_sockaddr_cmp(const struct sockaddr *sa1,
 	return 0;
 }
 
-#if defined(CONFIG_NFS_V4_1)
-/* Common match routine for v4.0 and v4.1 callback services */
-static bool nfs4_cb_match_client(const struct sockaddr *addr,
-		struct nfs_client *clp, u32 minorversion)
-{
-	struct sockaddr *clap = (struct sockaddr *)&clp->cl_addr;
-
-	/* Don't match clients that failed to initialise */
-	if (!(clp->cl_cons_state == NFS_CS_READY ||
-	    clp->cl_cons_state == NFS_CS_SESSION_INITING))
-		return false;
-
-	smp_rmb();
-
-	/* Match the version and minorversion */
-	if (clp->rpc_ops->version != 4 ||
-	    clp->cl_minorversion != minorversion)
-		return false;
-
-	/* Match only the IP address, not the port number */
-	if (!nfs_sockaddr_match_ipaddr(addr, clap))
-		return false;
-
-	return true;
-}
-#endif /* CONFIG_NFS_V4_1 */
-
 /*
  * Find an nfs_client on the list that matches the initialisation data
  * that is supplied.
@@ -552,7 +423,7 @@ nfs_found_client(const struct nfs_client_initdata *cl_init,
  * Look up a client by IP address and protocol version
  * - creates a new record if one doesn't yet exist
  */
-static struct nfs_client *
+struct nfs_client *
 nfs_get_client(const struct nfs_client_initdata *cl_init,
 	       const struct rpc_timeout *timeparms,
 	       const char *ip_addr,
@@ -572,7 +443,7 @@ nfs_get_client(const struct nfs_client_initdata *cl_init,
 		if (clp) {
 			spin_unlock(&nn->nfs_client_lock);
 			if (new)
-				nfs_free_client(new);
+				new->rpc_ops->free_client(new);
 			return nfs_found_client(cl_init, clp);
 		}
 		if (new) {
@@ -586,7 +457,7 @@ nfs_get_client(const struct nfs_client_initdata *cl_init,
 
 		spin_unlock(&nn->nfs_client_lock);
 
-		new = nfs_alloc_client(cl_init);
+		new = cl_init->rpc_ops->alloc_client(cl_init);
 	} while (!IS_ERR(new));
 
 	dprintk("<-- nfs_get_client() Failed to find %s (%ld)\n",
@@ -607,7 +478,7 @@ void nfs_mark_client_ready(struct nfs_client *clp, int state)
 /*
  * Initialise the timeout values for a connection
  */
-static void nfs_init_timeout_values(struct rpc_timeout *to, int proto,
+void nfs_init_timeout_values(struct rpc_timeout *to, int proto,
 				    unsigned int timeo, unsigned int retrans)
 {
 	to->to_initval = timeo * HZ / 10;
@@ -648,9 +519,9 @@ static void nfs_init_timeout_values(struct rpc_timeout *to, int proto,
 /*
  * Create an RPC client handle
  */
-static int nfs_create_rpc_client(struct nfs_client *clp,
-				 const struct rpc_timeout *timeparms,
-				 rpc_authflavor_t flavor)
+int nfs_create_rpc_client(struct nfs_client *clp,
+			  const struct rpc_timeout *timeparms,
+			  rpc_authflavor_t flavor)
 {
 	struct rpc_clnt		*clnt = NULL;
 	struct rpc_create_args args = {
@@ -767,7 +638,7 @@ static inline void nfs_init_server_aclclient(struct nfs_server *server)
 /*
  * Create a general RPC client
  */
-static int nfs_init_server_rpcclient(struct nfs_server *server,
+int nfs_init_server_rpcclient(struct nfs_server *server,
 		const struct rpc_timeout *timeo,
 		rpc_authflavor_t pseudoflavour)
 {
@@ -975,7 +846,6 @@ static void nfs_server_set_fsinfo(struct nfs_server *server,
 		server->wsize = NFS_MAX_FILE_IO_SIZE;
 	server->wpages = (server->wsize + PAGE_CACHE_SIZE - 1) >> PAGE_CACHE_SHIFT;
 	server->pnfs_blksize = fsinfo->blksize;
-	set_pnfs_layoutdriver(server, mntfh, fsinfo->layouttype);
 
 	server->wtmult = nfs_block_bits(fsinfo->wtmult, NULL);
 
@@ -1001,7 +871,7 @@ static void nfs_server_set_fsinfo(struct nfs_server *server,
 /*
  * Probe filesystem information, including the FSID on v2/v3
  */
-static int nfs_probe_fsinfo(struct nfs_server *server, struct nfs_fh *mntfh, struct nfs_fattr *fattr)
+int nfs_probe_fsinfo(struct nfs_server *server, struct nfs_fh *mntfh, struct nfs_fattr *fattr)
 {
 	struct nfs_fsinfo fsinfo;
 	struct nfs_client *clp = server->nfs_client;
@@ -1045,7 +915,7 @@ out_error:
 /*
  * Copy useful information when duplicating a server record
  */
-static void nfs_server_copy_userdata(struct nfs_server *target, struct nfs_server *source)
+void nfs_server_copy_userdata(struct nfs_server *target, struct nfs_server *source)
 {
 	target->flags = source->flags;
 	target->rsize = source->rsize;
@@ -1058,7 +928,7 @@ static void nfs_server_copy_userdata(struct nfs_server *target, struct nfs_serve
 	target->options = source->options;
 }
 
-static void nfs_server_insert_lists(struct nfs_server *server)
+void nfs_server_insert_lists(struct nfs_server *server)
 {
 	struct nfs_client *clp = server->nfs_client;
 	struct nfs_net *nn = net_generic(clp->cl_net, nfs_net_id);
@@ -1092,7 +962,7 @@ static void nfs_server_remove_lists(struct nfs_server *server)
 /*
  * Allocate and initialise a server record
  */
-static struct nfs_server *nfs_alloc_server(void)
+struct nfs_server *nfs_alloc_server(void)
 {
 	struct nfs_server *server;
 
@@ -1138,7 +1008,6 @@ void nfs_free_server(struct nfs_server *server)
 	dprintk("--> nfs_free_server()\n");
 
 	nfs_server_remove_lists(server);
-	unset_pnfs_layoutdriver(server);
 
 	if (server->destroy != NULL)
 		server->destroy(server);
@@ -1226,522 +1095,6 @@ error:
 	return ERR_PTR(error);
 }
 
-#ifdef CONFIG_NFS_V4
-/*
- * NFSv4.0 callback thread helper
- *
- * Find a client by callback identifier
- */
-struct nfs_client *
-nfs4_find_client_ident(struct net *net, int cb_ident)
-{
-	struct nfs_client *clp;
-	struct nfs_net *nn = net_generic(net, nfs_net_id);
-
-	spin_lock(&nn->nfs_client_lock);
-	clp = idr_find(&nn->cb_ident_idr, cb_ident);
-	if (clp)
-		atomic_inc(&clp->cl_count);
-	spin_unlock(&nn->nfs_client_lock);
-	return clp;
-}
-
-#if defined(CONFIG_NFS_V4_1)
-/*
- * NFSv4.1 callback thread helper
- * For CB_COMPOUND calls, find a client by IP address, protocol version,
- * minorversion, and sessionID
- *
- * Returns NULL if no such client
- */
-struct nfs_client *
-nfs4_find_client_sessionid(struct net *net, const struct sockaddr *addr,
-			   struct nfs4_sessionid *sid)
-{
-	struct nfs_client *clp;
-	struct nfs_net *nn = net_generic(net, nfs_net_id);
-
-	spin_lock(&nn->nfs_client_lock);
-	list_for_each_entry(clp, &nn->nfs_client_list, cl_share_link) {
-		if (nfs4_cb_match_client(addr, clp, 1) == false)
-			continue;
-
-		if (!nfs4_has_session(clp))
-			continue;
-
-		/* Match sessionid*/
-		if (memcmp(clp->cl_session->sess_id.data,
-		    sid->data, NFS4_MAX_SESSIONID_LEN) != 0)
-			continue;
-
-		atomic_inc(&clp->cl_count);
-		spin_unlock(&nn->nfs_client_lock);
-		return clp;
-	}
-	spin_unlock(&nn->nfs_client_lock);
-	return NULL;
-}
-
-#else /* CONFIG_NFS_V4_1 */
-
-struct nfs_client *
-nfs4_find_client_sessionid(struct net *net, const struct sockaddr *addr,
-			   struct nfs4_sessionid *sid)
-{
-	return NULL;
-}
-#endif /* CONFIG_NFS_V4_1 */
-
-/*
- * Initialize the NFS4 callback service
- */
-static int nfs4_init_callback(struct nfs_client *clp)
-{
-	int error;
-
-	if (clp->rpc_ops->version == 4) {
-		struct rpc_xprt *xprt;
-
-		xprt = rcu_dereference_raw(clp->cl_rpcclient->cl_xprt);
-
-		if (nfs4_has_session(clp)) {
-			error = xprt_setup_backchannel(xprt,
-						NFS41_BC_MIN_CALLBACKS);
-			if (error < 0)
-				return error;
-		}
-
-		error = nfs_callback_up(clp->cl_mvops->minor_version, xprt);
-		if (error < 0) {
-			dprintk("%s: failed to start callback. Error = %d\n",
-				__func__, error);
-			return error;
-		}
-		__set_bit(NFS_CS_CALLBACK, &clp->cl_res_state);
-	}
-	return 0;
-}
-
-/*
- * Initialize the minor version specific parts of an NFS4 client record
- */
-static int nfs4_init_client_minor_version(struct nfs_client *clp)
-{
-#if defined(CONFIG_NFS_V4_1)
-	if (clp->cl_mvops->minor_version) {
-		struct nfs4_session *session = NULL;
-		/*
-		 * Create the session and mark it expired.
-		 * When a SEQUENCE operation encounters the expired session
-		 * it will do session recovery to initialize it.
-		 */
-		session = nfs4_alloc_session(clp);
-		if (!session)
-			return -ENOMEM;
-
-		clp->cl_session = session;
-		/*
-		 * The create session reply races with the server back
-		 * channel probe. Mark the client NFS_CS_SESSION_INITING
-		 * so that the client back channel can find the
-		 * nfs_client struct
-		 */
-		nfs_mark_client_ready(clp, NFS_CS_SESSION_INITING);
-	}
-#endif /* CONFIG_NFS_V4_1 */
-
-	return nfs4_init_callback(clp);
-}
-
-/**
- * nfs4_init_client - Initialise an NFS4 client record
- *
- * @clp: nfs_client to initialise
- * @timeparms: timeout parameters for underlying RPC transport
- * @ip_addr: callback IP address in presentation format
- * @authflavor: authentication flavor for underlying RPC transport
- *
- * Returns pointer to an NFS client, or an ERR_PTR value.
- */
-struct nfs_client *nfs4_init_client(struct nfs_client *clp,
-				    const struct rpc_timeout *timeparms,
-				    const char *ip_addr,
-				    rpc_authflavor_t authflavour)
-{
-	char buf[INET6_ADDRSTRLEN + 1];
-	int error;
-
-	if (clp->cl_cons_state == NFS_CS_READY) {
-		/* the client is initialised already */
-		dprintk("<-- nfs4_init_client() = 0 [already %p]\n", clp);
-		return clp;
-	}
-
-	/* Check NFS protocol revision and initialize RPC op vector */
-	clp->rpc_ops = &nfs_v4_clientops;
-
-	__set_bit(NFS_CS_DISCRTRY, &clp->cl_flags);
-	error = nfs_create_rpc_client(clp, timeparms, authflavour);
-	if (error < 0)
-		goto error;
-
-	/* If no clientaddr= option was specified, find a usable cb address */
-	if (ip_addr == NULL) {
-		struct sockaddr_storage cb_addr;
-		struct sockaddr *sap = (struct sockaddr *)&cb_addr;
-
-		error = rpc_localaddr(clp->cl_rpcclient, sap, sizeof(cb_addr));
-		if (error < 0)
-			goto error;
-		error = rpc_ntop(sap, buf, sizeof(buf));
-		if (error < 0)
-			goto error;
-		ip_addr = (const char *)buf;
-	}
-	strlcpy(clp->cl_ipaddr, ip_addr, sizeof(clp->cl_ipaddr));
-
-	error = nfs_idmap_new(clp);
-	if (error < 0) {
-		dprintk("%s: failed to create idmapper. Error = %d\n",
-			__func__, error);
-		goto error;
-	}
-	__set_bit(NFS_CS_IDMAP, &clp->cl_res_state);
-
-	error = nfs4_init_client_minor_version(clp);
-	if (error < 0)
-		goto error;
-
-	if (!nfs4_has_session(clp))
-		nfs_mark_client_ready(clp, NFS_CS_READY);
-	return clp;
-
-error:
-	nfs_mark_client_ready(clp, error);
-	nfs_put_client(clp);
-	dprintk("<-- nfs4_init_client() = xerror %d\n", error);
-	return ERR_PTR(error);
-}
-
-/*
- * Set up an NFS4 client
- */
-static int nfs4_set_client(struct nfs_server *server,
-		const char *hostname,
-		const struct sockaddr *addr,
-		const size_t addrlen,
-		const char *ip_addr,
-		rpc_authflavor_t authflavour,
-		int proto, const struct rpc_timeout *timeparms,
-		u32 minorversion, struct net *net)
-{
-	struct nfs_client_initdata cl_init = {
-		.hostname = hostname,
-		.addr = addr,
-		.addrlen = addrlen,
-		.rpc_ops = &nfs_v4_clientops,
-		.proto = proto,
-		.minorversion = minorversion,
-		.net = net,
-	};
-	struct nfs_client *clp;
-	int error;
-
-	dprintk("--> nfs4_set_client()\n");
-
-	if (server->flags & NFS_MOUNT_NORESVPORT)
-		set_bit(NFS_CS_NORESVPORT, &cl_init.init_flags);
-
-	/* Allocate or find a client reference we can use */
-	clp = nfs_get_client(&cl_init, timeparms, ip_addr, authflavour);
-	if (IS_ERR(clp)) {
-		error = PTR_ERR(clp);
-		goto error;
-	}
-
-	/*
-	 * Query for the lease time on clientid setup or renewal
-	 *
-	 * Note that this will be set on nfs_clients that were created
-	 * only for the DS role and did not set this bit, but now will
-	 * serve a dual role.
-	 */
-	set_bit(NFS_CS_CHECK_LEASE_TIME, &clp->cl_res_state);
-
-	server->nfs_client = clp;
-	dprintk("<-- nfs4_set_client() = 0 [new %p]\n", clp);
-	return 0;
-error:
-	dprintk("<-- nfs4_set_client() = xerror %d\n", error);
-	return error;
-}
-
-/*
- * Set up a pNFS Data Server client.
- *
- * Return any existing nfs_client that matches server address,port,version
- * and minorversion.
- *
- * For a new nfs_client, use a soft mount (default), a low retrans and a
- * low timeout interval so that if a connection is lost, we retry through
- * the MDS.
- */
-struct nfs_client *nfs4_set_ds_client(struct nfs_client* mds_clp,
-		const struct sockaddr *ds_addr, int ds_addrlen,
-		int ds_proto, unsigned int ds_timeo, unsigned int ds_retrans)
-{
-	struct nfs_client_initdata cl_init = {
-		.addr = ds_addr,
-		.addrlen = ds_addrlen,
-		.rpc_ops = &nfs_v4_clientops,
-		.proto = ds_proto,
-		.minorversion = mds_clp->cl_minorversion,
-		.net = mds_clp->cl_net,
-	};
-	struct rpc_timeout ds_timeout;
-	struct nfs_client *clp;
-
-	/*
-	 * Set an authflavor equual to the MDS value. Use the MDS nfs_client
-	 * cl_ipaddr so as to use the same EXCHANGE_ID co_ownerid as the MDS
-	 * (section 13.1 RFC 5661).
-	 */
-	nfs_init_timeout_values(&ds_timeout, ds_proto, ds_timeo, ds_retrans);
-	clp = nfs_get_client(&cl_init, &ds_timeout, mds_clp->cl_ipaddr,
-			     mds_clp->cl_rpcclient->cl_auth->au_flavor);
-
-	dprintk("<-- %s %p\n", __func__, clp);
-	return clp;
-}
-EXPORT_SYMBOL_GPL(nfs4_set_ds_client);
-
-/*
- * Session has been established, and the client marked ready.
- * Set the mount rsize and wsize with negotiated fore channel
- * attributes which will be bound checked in nfs_server_set_fsinfo.
- */
-static void nfs4_session_set_rwsize(struct nfs_server *server)
-{
-#ifdef CONFIG_NFS_V4_1
-	struct nfs4_session *sess;
-	u32 server_resp_sz;
-	u32 server_rqst_sz;
-
-	if (!nfs4_has_session(server->nfs_client))
-		return;
-	sess = server->nfs_client->cl_session;
-	server_resp_sz = sess->fc_attrs.max_resp_sz - nfs41_maxread_overhead;
-	server_rqst_sz = sess->fc_attrs.max_rqst_sz - nfs41_maxwrite_overhead;
-
-	if (server->rsize > server_resp_sz)
-		server->rsize = server_resp_sz;
-	if (server->wsize > server_rqst_sz)
-		server->wsize = server_rqst_sz;
-#endif /* CONFIG_NFS_V4_1 */
-}
-
-static int nfs4_server_common_setup(struct nfs_server *server,
-		struct nfs_fh *mntfh)
-{
-	struct nfs_fattr *fattr;
-	int error;
-
-	BUG_ON(!server->nfs_client);
-	BUG_ON(!server->nfs_client->rpc_ops);
-	BUG_ON(!server->nfs_client->rpc_ops->file_inode_ops);
-
-	/* data servers support only a subset of NFSv4.1 */
-	if (is_ds_only_client(server->nfs_client))
-		return -EPROTONOSUPPORT;
-
-	fattr = nfs_alloc_fattr();
-	if (fattr == NULL)
-		return -ENOMEM;
-
-	/* We must ensure the session is initialised first */
-	error = nfs4_init_session(server);
-	if (error < 0)
-		goto out;
-
-	/* Probe the root fh to retrieve its FSID and filehandle */
-	error = nfs4_get_rootfh(server, mntfh);
-	if (error < 0)
-		goto out;
-
-	dprintk("Server FSID: %llx:%llx\n",
-			(unsigned long long) server->fsid.major,
-			(unsigned long long) server->fsid.minor);
-	dprintk("Mount FH: %d\n", mntfh->size);
-
-	nfs4_session_set_rwsize(server);
-
-	error = nfs_probe_fsinfo(server, mntfh, fattr);
-	if (error < 0)
-		goto out;
-
-	if (server->namelen == 0 || server->namelen > NFS4_MAXNAMLEN)
-		server->namelen = NFS4_MAXNAMLEN;
-
-	nfs_server_insert_lists(server);
-	server->mount_time = jiffies;
-	server->destroy = nfs4_destroy_server;
-out:
-	nfs_free_fattr(fattr);
-	return error;
-}
-
-/*
- * Create a version 4 volume record
- */
-static int nfs4_init_server(struct nfs_server *server,
-		const struct nfs_parsed_mount_data *data)
-{
-	struct rpc_timeout timeparms;
-	int error;
-
-	dprintk("--> nfs4_init_server()\n");
-
-	nfs_init_timeout_values(&timeparms, data->nfs_server.protocol,
-			data->timeo, data->retrans);
-
-	/* Initialise the client representation from the mount data */
-	server->flags = data->flags;
-	server->caps |= NFS_CAP_ATOMIC_OPEN|NFS_CAP_CHANGE_ATTR|NFS_CAP_POSIX_LOCK;
-	if (!(data->flags & NFS_MOUNT_NORDIRPLUS))
-			server->caps |= NFS_CAP_READDIRPLUS;
-	server->options = data->options;
-
-	/* Get a client record */
-	error = nfs4_set_client(server,
-			data->nfs_server.hostname,
-			(const struct sockaddr *)&data->nfs_server.address,
-			data->nfs_server.addrlen,
-			data->client_address,
-			data->auth_flavors[0],
-			data->nfs_server.protocol,
-			&timeparms,
-			data->minorversion,
-			data->net);
-	if (error < 0)
-		goto error;
-
-	/*
-	 * Don't use NFS uid/gid mapping if we're using AUTH_SYS or lower
-	 * authentication.
-	 */
-	if (nfs4_disable_idmapping && data->auth_flavors[0] == RPC_AUTH_UNIX)
-		server->caps |= NFS_CAP_UIDGID_NOMAP;
-
-	if (data->rsize)
-		server->rsize = nfs_block_size(data->rsize, NULL);
-	if (data->wsize)
-		server->wsize = nfs_block_size(data->wsize, NULL);
-
-	server->acregmin = data->acregmin * HZ;
-	server->acregmax = data->acregmax * HZ;
-	server->acdirmin = data->acdirmin * HZ;
-	server->acdirmax = data->acdirmax * HZ;
-
-	server->port = data->nfs_server.port;
-
-	error = nfs_init_server_rpcclient(server, &timeparms, data->auth_flavors[0]);
-
-error:
-	/* Done */
-	dprintk("<-- nfs4_init_server() = %d\n", error);
-	return error;
-}
-
-/*
- * Create a version 4 volume record
- * - keyed on server and FSID
- */
-struct nfs_server *nfs4_create_server(const struct nfs_parsed_mount_data *data,
-				      struct nfs_fh *mntfh)
-{
-	struct nfs_server *server;
-	int error;
-
-	dprintk("--> nfs4_create_server()\n");
-
-	server = nfs_alloc_server();
-	if (!server)
-		return ERR_PTR(-ENOMEM);
-
-	/* set up the general RPC client */
-	error = nfs4_init_server(server, data);
-	if (error < 0)
-		goto error;
-
-	error = nfs4_server_common_setup(server, mntfh);
-	if (error < 0)
-		goto error;
-
-	dprintk("<-- nfs4_create_server() = %p\n", server);
-	return server;
-
-error:
-	nfs_free_server(server);
-	dprintk("<-- nfs4_create_server() = error %d\n", error);
-	return ERR_PTR(error);
-}
-
-/*
- * Create an NFS4 referral server record
- */
-struct nfs_server *nfs4_create_referral_server(struct nfs_clone_mount *data,
-					       struct nfs_fh *mntfh)
-{
-	struct nfs_client *parent_client;
-	struct nfs_server *server, *parent_server;
-	int error;
-
-	dprintk("--> nfs4_create_referral_server()\n");
-
-	server = nfs_alloc_server();
-	if (!server)
-		return ERR_PTR(-ENOMEM);
-
-	parent_server = NFS_SB(data->sb);
-	parent_client = parent_server->nfs_client;
-
-	/* Initialise the client representation from the parent server */
-	nfs_server_copy_userdata(server, parent_server);
-	server->caps |= NFS_CAP_ATOMIC_OPEN|NFS_CAP_CHANGE_ATTR;
-
-	/* Get a client representation.
-	 * Note: NFSv4 always uses TCP, */
-	error = nfs4_set_client(server, data->hostname,
-				data->addr,
-				data->addrlen,
-				parent_client->cl_ipaddr,
-				data->authflavor,
-				rpc_protocol(parent_server->client),
-				parent_server->client->cl_timeout,
-				parent_client->cl_mvops->minor_version,
-				parent_client->cl_net);
-	if (error < 0)
-		goto error;
-
-	error = nfs_init_server_rpcclient(server, parent_server->client->cl_timeout, data->authflavor);
-	if (error < 0)
-		goto error;
-
-	error = nfs4_server_common_setup(server, mntfh);
-	if (error < 0)
-		goto error;
-
-	dprintk("<-- nfs_create_referral_server() = %p\n", server);
-	return server;
-
-error:
-	nfs_free_server(server);
-	dprintk("<-- nfs4_create_referral_server() = error %d\n", error);
-	return ERR_PTR(error);
-}
-
-#endif /* CONFIG_NFS_V4 */
-
 /*
  * Clone an NFS2, NFS3 or NFS4 server record
  */
@@ -2091,7 +1444,3 @@ void nfs_fs_proc_exit(void)
 }
 
 #endif /* CONFIG_PROC_FS */
-
-module_param(nfs4_disable_idmapping, bool, 0644);
-MODULE_PARM_DESC(nfs4_disable_idmapping,
-		"Turn off NFSv4 idmapping when using 'sec=sys'");

fs/nfs/delegation.c

@@ -47,7 +47,7 @@ void nfs_mark_delegation_referenced(struct nfs_delegation *delegation)
  *
  * Returns one if inode has the indicated delegation, otherwise zero.
  */
-int nfs_have_delegation(struct inode *inode, fmode_t flags)
+int nfs4_have_delegation(struct inode *inode, fmode_t flags)
 {
 	struct nfs_delegation *delegation;
 	int ret = 0;
@@ -388,7 +388,7 @@ void nfs_inode_return_delegation_noreclaim(struct inode *inode)
  *
  * Returns zero on success, or a negative errno value.
  */
-int nfs_inode_return_delegation(struct inode *inode)
+int nfs4_inode_return_delegation(struct inode *inode)
 {
 	struct nfs_server *server = NFS_SERVER(inode);
 	struct nfs_inode *nfsi = NFS_I(inode);
@@ -417,9 +417,8 @@ static void nfs_mark_return_delegation(struct nfs_server *server,
  * @sb: sb to process
  *
  */
-void nfs_super_return_all_delegations(struct super_block *sb)
+void nfs_server_return_all_delegations(struct nfs_server *server)
 {
-	struct nfs_server *server = NFS_SB(sb);
 	struct nfs_client *clp = server->nfs_client;
 	struct nfs_delegation *delegation;
 

fs/nfs/delegation.h

@@ -33,12 +33,12 @@ enum {
 
 int nfs_inode_set_delegation(struct inode *inode, struct rpc_cred *cred, struct nfs_openres *res);
 void nfs_inode_reclaim_delegation(struct inode *inode, struct rpc_cred *cred, struct nfs_openres *res);
-int nfs_inode_return_delegation(struct inode *inode);
+int nfs4_inode_return_delegation(struct inode *inode);
 int nfs_async_inode_return_delegation(struct inode *inode, const nfs4_stateid *stateid);
 void nfs_inode_return_delegation_noreclaim(struct inode *inode);
 
 struct inode *nfs_delegation_find_inode(struct nfs_client *clp, const struct nfs_fh *fhandle);
-void nfs_super_return_all_delegations(struct super_block *sb);
+void nfs_server_return_all_delegations(struct nfs_server *);
 void nfs_expire_all_delegations(struct nfs_client *clp);
 void nfs_expire_all_delegation_types(struct nfs_client *clp, fmode_t flags);
 void nfs_expire_unreferenced_delegations(struct nfs_client *clp);
@@ -56,24 +56,13 @@ int nfs4_lock_delegation_recall(struct nfs4_state *state, struct file_lock *fl);
 bool nfs4_copy_delegation_stateid(nfs4_stateid *dst, struct inode *inode, fmode_t flags);
 
 void nfs_mark_delegation_referenced(struct nfs_delegation *delegation);
-int nfs_have_delegation(struct inode *inode, fmode_t flags);
+int nfs4_have_delegation(struct inode *inode, fmode_t flags);
 
-#else
-static inline int nfs_have_delegation(struct inode *inode, fmode_t flags)
-{
-	return 0;
-}
-
-static inline int nfs_inode_return_delegation(struct inode *inode)
-{
-	nfs_wb_all(inode);
-	return 0;
-}
 #endif
 
 static inline int nfs_have_delegated_attributes(struct inode *inode)
 {
-	return nfs_have_delegation(inode, FMODE_READ) &&
+	return NFS_PROTO(inode)->have_delegation(inode, FMODE_READ) &&
 		!(NFS_I(inode)->cache_validity & NFS_INO_REVAL_FORCED);
 }
 

fs/nfs/dir.c

@@ -46,16 +46,6 @@
 static int nfs_opendir(struct inode *, struct file *);
 static int nfs_closedir(struct inode *, struct file *);
 static int nfs_readdir(struct file *, void *, filldir_t);
-static struct dentry *nfs_lookup(struct inode *, struct dentry *, unsigned int);
-static int nfs_create(struct inode *, struct dentry *, umode_t, bool);
-static int nfs_mkdir(struct inode *, struct dentry *, umode_t);
-static int nfs_rmdir(struct inode *, struct dentry *);
-static int nfs_unlink(struct inode *, struct dentry *);
-static int nfs_symlink(struct inode *, struct dentry *, const char *);
-static int nfs_link(struct dentry *, struct inode *, struct dentry *);
-static int nfs_mknod(struct inode *, struct dentry *, umode_t, dev_t);
-static int nfs_rename(struct inode *, struct dentry *,
-		      struct inode *, struct dentry *);
 static int nfs_fsync_dir(struct file *, loff_t, loff_t, int);
 static loff_t nfs_llseek_dir(struct file *, loff_t, int);
 static void nfs_readdir_clear_array(struct page*);
@@ -69,73 +59,10 @@ const struct file_operations nfs_dir_operations = {
 	.fsync		= nfs_fsync_dir,
 };
 
-const struct inode_operations nfs_dir_inode_operations = {
-	.create		= nfs_create,
-	.lookup		= nfs_lookup,
-	.link		= nfs_link,
-	.unlink		= nfs_unlink,
-	.symlink	= nfs_symlink,
-	.mkdir		= nfs_mkdir,
-	.rmdir		= nfs_rmdir,
-	.mknod		= nfs_mknod,
-	.rename		= nfs_rename,
-	.permission	= nfs_permission,
-	.getattr	= nfs_getattr,
-	.setattr	= nfs_setattr,
-};
-
 const struct address_space_operations nfs_dir_aops = {
 	.freepage = nfs_readdir_clear_array,
 };
 
-#ifdef CONFIG_NFS_V3
-const struct inode_operations nfs3_dir_inode_operations = {
-	.create		= nfs_create,
-	.lookup		= nfs_lookup,
-	.link		= nfs_link,
-	.unlink		= nfs_unlink,
-	.symlink	= nfs_symlink,
-	.mkdir		= nfs_mkdir,
-	.rmdir		= nfs_rmdir,
-	.mknod		= nfs_mknod,
-	.rename		= nfs_rename,
-	.permission	= nfs_permission,
-	.getattr	= nfs_getattr,
-	.setattr	= nfs_setattr,
-	.listxattr	= nfs3_listxattr,
-	.getxattr	= nfs3_getxattr,
-	.setxattr	= nfs3_setxattr,
-	.removexattr	= nfs3_removexattr,
-};
-#endif  /* CONFIG_NFS_V3 */
-
-#ifdef CONFIG_NFS_V4
-
-static int nfs_atomic_open(struct inode *, struct dentry *,
-			   struct file *, unsigned, umode_t,
-			   int *);
-const struct inode_operations nfs4_dir_inode_operations = {
-	.create		= nfs_create,
-	.lookup		= nfs_lookup,
-	.atomic_open	= nfs_atomic_open,
-	.link		= nfs_link,
-	.unlink		= nfs_unlink,
-	.symlink	= nfs_symlink,
-	.mkdir		= nfs_mkdir,
-	.rmdir		= nfs_rmdir,
-	.mknod		= nfs_mknod,
-	.rename		= nfs_rename,
-	.permission	= nfs_permission,
-	.getattr	= nfs_getattr,
-	.setattr	= nfs_setattr,
-	.getxattr	= generic_getxattr,
-	.setxattr	= generic_setxattr,
-	.listxattr	= generic_listxattr,
-	.removexattr	= generic_removexattr,
-};
-
-#endif /* CONFIG_NFS_V4 */
-
 static struct nfs_open_dir_context *alloc_nfs_open_dir_context(struct inode *dir, struct rpc_cred *cred)
 {
 	struct nfs_open_dir_context *ctx;
@@ -1128,7 +1055,7 @@ static int nfs_lookup_revalidate(struct dentry *dentry, unsigned int flags)
 		goto out_bad;
 	}
 
-	if (nfs_have_delegation(inode, FMODE_READ))
+	if (NFS_PROTO(dir)->have_delegation(inode, FMODE_READ))
 		goto out_set_verifier;
 
 	/* Force a full look up iff the parent directory has changed */
@@ -1270,7 +1197,7 @@ const struct dentry_operations nfs_dentry_operations = {
 	.d_release	= nfs_d_release,
 };
 
-static struct dentry *nfs_lookup(struct inode *dir, struct dentry * dentry, unsigned int flags)
+struct dentry *nfs_lookup(struct inode *dir, struct dentry * dentry, unsigned int flags)
 {
 	struct dentry *res;
 	struct dentry *parent;
@@ -1398,9 +1325,9 @@ out:
 	return err;
 }
 
-static int nfs_atomic_open(struct inode *dir, struct dentry *dentry,
-			    struct file *file, unsigned open_flags,
-			    umode_t mode, int *opened)
+int nfs_atomic_open(struct inode *dir, struct dentry *dentry,
+		    struct file *file, unsigned open_flags,
+		    umode_t mode, int *opened)
 {
 	struct nfs_open_context *ctx;
 	struct dentry *res;
@@ -1588,7 +1515,7 @@ out_error:
  * that the operation succeeded on the server, but an error in the
  * reply path made it appear to have failed.
  */
-static int nfs_create(struct inode *dir, struct dentry *dentry,
+int nfs_create(struct inode *dir, struct dentry *dentry,
 		umode_t mode, bool excl)
 {
 	struct iattr attr;
@@ -1613,7 +1540,7 @@ out_err:
 /*
  * See comments for nfs_proc_create regarding failed operations.
  */
-static int
+int
 nfs_mknod(struct inode *dir, struct dentry *dentry, umode_t mode, dev_t rdev)
 {
 	struct iattr attr;
@@ -1640,7 +1567,7 @@ out_err:
 /*
  * See comments for nfs_proc_create regarding failed operations.
  */
-static int nfs_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode)
+int nfs_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode)
 {
 	struct iattr attr;
 	int error;
@@ -1666,7 +1593,7 @@ static void nfs_dentry_handle_enoent(struct dentry *dentry)
 		d_delete(dentry);
 }
 
-static int nfs_rmdir(struct inode *dir, struct dentry *dentry)
+int nfs_rmdir(struct inode *dir, struct dentry *dentry)
 {
 	int error;
 
@@ -1706,7 +1633,7 @@ static int nfs_safe_remove(struct dentry *dentry)
 	}
 
 	if (inode != NULL) {
-		nfs_inode_return_delegation(inode);
+		NFS_PROTO(inode)->return_delegation(inode);
 		error = NFS_PROTO(dir)->remove(dir, &dentry->d_name);
 		/* The VFS may want to delete this inode */
 		if (error == 0)
@@ -1725,7 +1652,7 @@ out:
  *
  *  If sillyrename() returns 0, we do nothing, otherwise we unlink.
  */
-static int nfs_unlink(struct inode *dir, struct dentry *dentry)
+int nfs_unlink(struct inode *dir, struct dentry *dentry)
 {
 	int error;
 	int need_rehash = 0;
@@ -1769,7 +1696,7 @@ static int nfs_unlink(struct inode *dir, struct dentry *dentry)
  * now have a new file handle and can instantiate an in-core NFS inode
  * and move the raw page into its mapping.
  */
-static int nfs_symlink(struct inode *dir, struct dentry *dentry, const char *symname)
+int nfs_symlink(struct inode *dir, struct dentry *dentry, const char *symname)
 {
 	struct pagevec lru_pvec;
 	struct page *page;
@@ -1824,7 +1751,7 @@ static int nfs_symlink(struct inode *dir, struct dentry *dentry, const char *sym
 	return 0;
 }
 
-static int 
+int
 nfs_link(struct dentry *old_dentry, struct inode *dir, struct dentry *dentry)
 {
 	struct inode *inode = old_dentry->d_inode;
@@ -1834,7 +1761,7 @@ nfs_link(struct dentry *old_dentry, struct inode *dir, struct dentry *dentry)
 		old_dentry->d_parent->d_name.name, old_dentry->d_name.name,
 		dentry->d_parent->d_name.name, dentry->d_name.name);
 
-	nfs_inode_return_delegation(inode);
+	NFS_PROTO(inode)->return_delegation(inode);
 
 	d_drop(dentry);
 	error = NFS_PROTO(dir)->link(inode, dir, &dentry->d_name);
@@ -1869,7 +1796,7 @@ nfs_link(struct dentry *old_dentry, struct inode *dir, struct dentry *dentry)
  * If these conditions are met, we can drop the dentries before doing
  * the rename.
  */
-static int nfs_rename(struct inode *old_dir, struct dentry *old_dentry,
+int nfs_rename(struct inode *old_dir, struct dentry *old_dentry,
 		      struct inode *new_dir, struct dentry *new_dentry)
 {
 	struct inode *old_inode = old_dentry->d_inode;
@@ -1918,9 +1845,9 @@ static int nfs_rename(struct inode *old_dir, struct dentry *old_dentry,
 		}
 	}
 
-	nfs_inode_return_delegation(old_inode);
+	NFS_PROTO(old_inode)->return_delegation(old_inode);
 	if (new_inode != NULL)
-		nfs_inode_return_delegation(new_inode);
+		NFS_PROTO(new_inode)->return_delegation(new_inode);
 
 	error = NFS_PROTO(old_dir)->rename(old_dir, &old_dentry->d_name,
 					   new_dir, &new_dentry->d_name);

fs/nfs/direct.c

@@ -393,7 +393,7 @@ static ssize_t nfs_direct_read_schedule_iovec(struct nfs_direct_req *dreq,
 	size_t requested_bytes = 0;
 	unsigned long seg;
 
-	nfs_pageio_init_read(&desc, dreq->inode,
+	NFS_PROTO(dreq->inode)->read_pageio_init(&desc, dreq->inode,
 			     &nfs_direct_read_completion_ops);
 	get_dreq(dreq);
 	desc.pg_dreq = dreq;
@@ -478,7 +478,7 @@ static void nfs_direct_write_reschedule(struct nfs_direct_req *dreq)
 	dreq->count = 0;
 	get_dreq(dreq);
 
-	nfs_pageio_init_write(&desc, dreq->inode, FLUSH_STABLE,
+	NFS_PROTO(dreq->inode)->write_pageio_init(&desc, dreq->inode, FLUSH_STABLE,
 			      &nfs_direct_write_completion_ops);
 	desc.pg_dreq = dreq;
 
@@ -782,7 +782,7 @@ static ssize_t nfs_direct_write_schedule_iovec(struct nfs_direct_req *dreq,
 	size_t requested_bytes = 0;
 	unsigned long seg;
 
-	nfs_pageio_init_write(&desc, inode, FLUSH_COND_STABLE,
+	NFS_PROTO(inode)->write_pageio_init(&desc, inode, FLUSH_COND_STABLE,
 			      &nfs_direct_write_completion_ops);
 	desc.pg_dreq = dreq;
 	get_dreq(dreq);

fs/nfs/file.c

@@ -35,36 +35,17 @@
 #include "internal.h"
 #include "iostat.h"
 #include "fscache.h"
-#include "pnfs.h"
 
 #define NFSDBG_FACILITY		NFSDBG_FILE
 
 static const struct vm_operations_struct nfs_file_vm_ops;
 
-const struct inode_operations nfs_file_inode_operations = {
-	.permission	= nfs_permission,
-	.getattr	= nfs_getattr,
-	.setattr	= nfs_setattr,
-};
-
-#ifdef CONFIG_NFS_V3
-const struct inode_operations nfs3_file_inode_operations = {
-	.permission	= nfs_permission,
-	.getattr	= nfs_getattr,
-	.setattr	= nfs_setattr,
-	.listxattr	= nfs3_listxattr,
-	.getxattr	= nfs3_getxattr,
-	.setxattr	= nfs3_setxattr,
-	.removexattr	= nfs3_removexattr,
-};
-#endif  /* CONFIG_NFS_v3 */
-
 /* Hack for future NFS swap support */
 #ifndef IS_SWAPFILE
 # define IS_SWAPFILE(inode)	(0)
 #endif
 
-static int nfs_check_flags(int flags)
+int nfs_check_flags(int flags)
 {
 	if ((flags & (O_APPEND | O_DIRECT)) == (O_APPEND | O_DIRECT))
 		return -EINVAL;
@@ -93,7 +74,7 @@ nfs_file_open(struct inode *inode, struct file *filp)
 	return res;
 }
 
-static int
+int
 nfs_file_release(struct inode *inode, struct file *filp)
 {
 	dprintk("NFS: release(%s/%s)\n",
@@ -135,7 +116,7 @@ force_reval:
 	return __nfs_revalidate_inode(server, inode);
 }
 
-static loff_t nfs_file_llseek(struct file *filp, loff_t offset, int origin)
+loff_t nfs_file_llseek(struct file *filp, loff_t offset, int origin)
 {
 	dprintk("NFS: llseek file(%s/%s, %lld, %d)\n",
 			filp->f_path.dentry->d_parent->d_name.name,
@@ -160,7 +141,7 @@ static loff_t nfs_file_llseek(struct file *filp, loff_t offset, int origin)
 /*
  * Flush all dirty pages, and check for write errors.
  */
-static int
+int
 nfs_file_flush(struct file *file, fl_owner_t id)
 {
 	struct dentry	*dentry = file->f_path.dentry;
@@ -178,14 +159,14 @@ nfs_file_flush(struct file *file, fl_owner_t id)
 	 * If we're holding a write delegation, then just start the i/o
 	 * but don't wait for completion (or send a commit).
 	 */
-	if (nfs_have_delegation(inode, FMODE_WRITE))
+	if (NFS_PROTO(inode)->have_delegation(inode, FMODE_WRITE))
 		return filemap_fdatawrite(file->f_mapping);
 
 	/* Flush writes to the server and return any errors */
 	return vfs_fsync(file, 0);
 }
 
-static ssize_t
+ssize_t
 nfs_file_read(struct kiocb *iocb, const struct iovec *iov,
 		unsigned long nr_segs, loff_t pos)
 {
@@ -209,7 +190,7 @@ nfs_file_read(struct kiocb *iocb, const struct iovec *iov,
 	return result;
 }
 
-static ssize_t
+ssize_t
 nfs_file_splice_read(struct file *filp, loff_t *ppos,
 		     struct pipe_inode_info *pipe, size_t count,
 		     unsigned int flags)
@@ -231,7 +212,7 @@ nfs_file_splice_read(struct file *filp, loff_t *ppos,
 	return res;
 }
 
-static int
+int
 nfs_file_mmap(struct file * file, struct vm_area_struct * vma)
 {
 	struct dentry *dentry = file->f_path.dentry;
@@ -264,8 +245,8 @@ nfs_file_mmap(struct file * file, struct vm_area_struct * vma)
  * nfs_file_write() that a write error occurred, and hence cause it to
  * fall back to doing a synchronous write.
  */
-static int
-nfs_file_fsync(struct file *file, loff_t start, loff_t end, int datasync)
+int
+nfs_file_fsync_commit(struct file *file, loff_t start, loff_t end, int datasync)
 {
 	struct dentry *dentry = file->f_path.dentry;
 	struct nfs_open_context *ctx = nfs_file_open_context(file);
@@ -277,9 +258,6 @@ nfs_file_fsync(struct file *file, loff_t start, loff_t end, int datasync)
 			dentry->d_parent->d_name.name, dentry->d_name.name,
 			datasync);
 
-	ret = filemap_write_and_wait_range(inode->i_mapping, start, end);
-	mutex_lock(&inode->i_mutex);
-
 	nfs_inc_stats(inode, NFSIOS_VFSFSYNC);
 	have_error = test_and_clear_bit(NFS_CONTEXT_ERROR_WRITE, &ctx->flags);
 	status = nfs_commit_inode(inode, FLUSH_SYNC);
@@ -290,10 +268,20 @@ nfs_file_fsync(struct file *file, loff_t start, loff_t end, int datasync)
 		ret = xchg(&ctx->error, 0);
 	if (!ret && status < 0)
 		ret = status;
-	if (!ret && !datasync)
-		/* application has asked for meta-data sync */
-		ret = pnfs_layoutcommit_inode(inode, true);
+	return ret;
+}
+
+static int
+nfs_file_fsync(struct file *file, loff_t start, loff_t end, int datasync)
+{
+	int ret;
+	struct inode *inode = file->f_path.dentry->d_inode;
+
+	ret = filemap_write_and_wait_range(inode->i_mapping, start, end);
+	mutex_lock(&inode->i_mutex);
+	ret = nfs_file_fsync_commit(file, start, end, datasync);
 	mutex_unlock(&inode->i_mutex);
+
 	return ret;
 }
 
@@ -572,8 +560,8 @@ static int nfs_need_sync_write(struct file *filp, struct inode *inode)
 	return 0;
 }
 
-static ssize_t nfs_file_write(struct kiocb *iocb, const struct iovec *iov,
-				unsigned long nr_segs, loff_t pos)
+ssize_t nfs_file_write(struct kiocb *iocb, const struct iovec *iov,
+		       unsigned long nr_segs, loff_t pos)
 {
 	struct dentry * dentry = iocb->ki_filp->f_path.dentry;
 	struct inode * inode = dentry->d_inode;
@@ -624,9 +612,9 @@ out_swapfile:
 	goto out;
 }
 
-static ssize_t nfs_file_splice_write(struct pipe_inode_info *pipe,
-				     struct file *filp, loff_t *ppos,
-				     size_t count, unsigned int flags)
+ssize_t nfs_file_splice_write(struct pipe_inode_info *pipe,
+			      struct file *filp, loff_t *ppos,
+			      size_t count, unsigned int flags)
 {
 	struct dentry *dentry = filp->f_path.dentry;
 	struct inode *inode = dentry->d_inode;
@@ -670,7 +658,7 @@ do_getlk(struct file *filp, int cmd, struct file_lock *fl, int is_local)
 	}
 	fl->fl_type = saved_type;
 
-	if (nfs_have_delegation(inode, FMODE_READ))
+	if (NFS_PROTO(inode)->have_delegation(inode, FMODE_READ))
 		goto out_noconflict;
 
 	if (is_local)
@@ -765,7 +753,7 @@ do_setlk(struct file *filp, int cmd, struct file_lock *fl, int is_local)
 	 * This makes locking act as a cache coherency point.
 	 */
 	nfs_sync_mapping(filp->f_mapping);
-	if (!nfs_have_delegation(inode, FMODE_READ)) {
+	if (!NFS_PROTO(inode)->have_delegation(inode, FMODE_READ)) {
 		if (is_time_granular(&NFS_SERVER(inode)->time_delta))
 			__nfs_revalidate_inode(NFS_SERVER(inode), inode);
 		else
@@ -778,7 +766,7 @@ out:
 /*
  * Lock a (portion of) a file
  */
-static int nfs_lock(struct file *filp, int cmd, struct file_lock *fl)
+int nfs_lock(struct file *filp, int cmd, struct file_lock *fl)
 {
 	struct inode *inode = filp->f_mapping->host;
 	int ret = -ENOLCK;
@@ -818,7 +806,7 @@ out_err:
 /*
  * Lock a (portion of) a file
  */
-static int nfs_flock(struct file *filp, int cmd, struct file_lock *fl)
+int nfs_flock(struct file *filp, int cmd, struct file_lock *fl)
 {
 	struct inode *inode = filp->f_mapping->host;
 	int is_local = 0;
@@ -848,7 +836,7 @@ static int nfs_flock(struct file *filp, int cmd, struct file_lock *fl)
  * There is no protocol support for leases, so we have no way to implement
  * them correctly in the face of opens by other clients.
  */
-static int nfs_setlease(struct file *file, long arg, struct file_lock **fl)
+int nfs_setlease(struct file *file, long arg, struct file_lock **fl)
 {
 	dprintk("NFS: setlease(%s/%s, arg=%ld)\n",
 			file->f_path.dentry->d_parent->d_name.name,
@@ -874,104 +862,3 @@ const struct file_operations nfs_file_operations = {
 	.check_flags	= nfs_check_flags,
 	.setlease	= nfs_setlease,
 };
-
-#ifdef CONFIG_NFS_V4
-static int
-nfs4_file_open(struct inode *inode, struct file *filp)
-{
-	struct nfs_open_context *ctx;
-	struct dentry *dentry = filp->f_path.dentry;
-	struct dentry *parent = NULL;
-	struct inode *dir;
-	unsigned openflags = filp->f_flags;
-	struct iattr attr;
-	int err;
-
-	BUG_ON(inode != dentry->d_inode);
-	/*
-	 * If no cached dentry exists or if it's negative, NFSv4 handled the
-	 * opens in ->lookup() or ->create().
-	 *
-	 * We only get this far for a cached positive dentry.  We skipped
-	 * revalidation, so handle it here by dropping the dentry and returning
-	 * -EOPENSTALE.  The VFS will retry the lookup/create/open.
-	 */
-
-	dprintk("NFS: open file(%s/%s)\n",
-		dentry->d_parent->d_name.name,
-		dentry->d_name.name);
-
-	if ((openflags & O_ACCMODE) == 3)
-		openflags--;
-
-	/* We can't create new files here */
-	openflags &= ~(O_CREAT|O_EXCL);
-
-	parent = dget_parent(dentry);
-	dir = parent->d_inode;
-
-	ctx = alloc_nfs_open_context(filp->f_path.dentry, filp->f_mode);
-	err = PTR_ERR(ctx);
-	if (IS_ERR(ctx))
-		goto out;
-
-	attr.ia_valid = ATTR_OPEN;
-	if (openflags & O_TRUNC) {
-		attr.ia_valid |= ATTR_SIZE;
-		attr.ia_size = 0;
-		nfs_wb_all(inode);
-	}
-
-	inode = NFS_PROTO(dir)->open_context(dir, ctx, openflags, &attr);
-	if (IS_ERR(inode)) {
-		err = PTR_ERR(inode);
-		switch (err) {
-		case -EPERM:
-		case -EACCES:
-		case -EDQUOT:
-		case -ENOSPC:
-		case -EROFS:
-			goto out_put_ctx;
-		default:
-			goto out_drop;
-		}
-	}
-	iput(inode);
-	if (inode != dentry->d_inode)
-		goto out_drop;
-
-	nfs_set_verifier(dentry, nfs_save_change_attribute(dir));
-	nfs_file_set_open_context(filp, ctx);
-	err = 0;
-
-out_put_ctx:
-	put_nfs_open_context(ctx);
-out:
-	dput(parent);
-	return err;
-
-out_drop:
-	d_drop(dentry);
-	err = -EOPENSTALE;
-	goto out_put_ctx;
-}
-
-const struct file_operations nfs4_file_operations = {
-	.llseek		= nfs_file_llseek,
-	.read		= do_sync_read,
-	.write		= do_sync_write,
-	.aio_read	= nfs_file_read,
-	.aio_write	= nfs_file_write,
-	.mmap		= nfs_file_mmap,
-	.open		= nfs4_file_open,
-	.flush		= nfs_file_flush,
-	.release	= nfs_file_release,
-	.fsync		= nfs_file_fsync,
-	.lock		= nfs_lock,
-	.flock		= nfs_flock,
-	.splice_read	= nfs_file_splice_read,
-	.splice_write	= nfs_file_splice_write,
-	.check_flags	= nfs_check_flags,
-	.setlease	= nfs_setlease,
-};
-#endif /* CONFIG_NFS_V4 */

fs/nfs/getroot.c

@@ -23,21 +23,15 @@
 #include <linux/sunrpc/stats.h>
 #include <linux/nfs_fs.h>
 #include <linux/nfs_mount.h>
-#include <linux/nfs4_mount.h>
 #include <linux/lockd/bind.h>
 #include <linux/seq_file.h>
 #include <linux/mount.h>
-#include <linux/nfs_idmap.h>
 #include <linux/vfs.h>
 #include <linux/namei.h>
 #include <linux/security.h>
 
 #include <asm/uaccess.h>
 
-#include "nfs4_fs.h"
-#include "delegation.h"
-#include "internal.h"
-
 #define NFSDBG_FACILITY		NFSDBG_CLIENT
 
 /*
@@ -135,47 +129,3 @@ out:
 	nfs_free_fattr(fsinfo.fattr);
 	return ret;
 }
-
-#ifdef CONFIG_NFS_V4
-
-int nfs4_get_rootfh(struct nfs_server *server, struct nfs_fh *mntfh)
-{
-	struct nfs_fsinfo fsinfo;
-	int ret = -ENOMEM;
-
-	dprintk("--> nfs4_get_rootfh()\n");
-
-	fsinfo.fattr = nfs_alloc_fattr();
-	if (fsinfo.fattr == NULL)
-		goto out;
-
-	/* Start by getting the root filehandle from the server */
-	ret = nfs4_proc_get_rootfh(server, mntfh, &fsinfo);
-	if (ret < 0) {
-		dprintk("nfs4_get_rootfh: getroot error = %d\n", -ret);
-		goto out;
-	}
-
-	if (!(fsinfo.fattr->valid & NFS_ATTR_FATTR_TYPE)
-			|| !S_ISDIR(fsinfo.fattr->mode)) {
-		printk(KERN_ERR "nfs4_get_rootfh:"
-		       " getroot encountered non-directory\n");
-		ret = -ENOTDIR;
-		goto out;
-	}
-
-	if (fsinfo.fattr->valid & NFS_ATTR_FATTR_V4_REFERRAL) {
-		printk(KERN_ERR "nfs4_get_rootfh:"
-		       " getroot obtained referral\n");
-		ret = -EREMOTE;
-		goto out;
-	}
-
-	memcpy(&server->fsid, &fsinfo.fattr->fsid, sizeof(server->fsid));
-out:
-	nfs_free_fattr(fsinfo.fattr);
-	dprintk("<-- nfs4_get_rootfh() = %d\n", ret);
-	return ret;
-}
-
-#endif /* CONFIG_NFS_V4 */

fs/nfs/inode.c

@@ -32,7 +32,6 @@
 #include <linux/lockd/bind.h>
 #include <linux/seq_file.h>
 #include <linux/mount.h>
-#include <linux/nfs_idmap.h>
 #include <linux/vfs.h>
 #include <linux/inet.h>
 #include <linux/nfs_xdr.h>
@@ -430,7 +429,7 @@ nfs_setattr(struct dentry *dentry, struct iattr *attr)
 	 * Return any delegations if we're going to change ACLs
 	 */
 	if ((attr->ia_valid & (ATTR_MODE|ATTR_UID|ATTR_GID)) != 0)
-		nfs_inode_return_delegation(inode);
+		NFS_PROTO(inode)->return_delegation(inode);
 	error = NFS_PROTO(inode)->setattr(dentry, fattr, attr);
 	if (error == 0)
 		nfs_refresh_inode(inode, fattr);
@@ -1457,7 +1456,7 @@ static int nfs_update_inode(struct inode *inode, struct nfs_fattr *fattr)
 	if (!(S_ISREG(inode->i_mode) || S_ISDIR(inode->i_mode)
 				|| S_ISLNK(inode->i_mode)))
 		invalid &= ~NFS_INO_INVALID_DATA;
-	if (!nfs_have_delegation(inode, FMODE_READ) ||
+	if (!NFS_PROTO(inode)->have_delegation(inode, FMODE_READ) ||
 			(save_cache_validity & NFS_INO_REVAL_FORCED))
 		nfsi->cache_validity |= invalid;
 
@@ -1628,87 +1627,96 @@ static int __init init_nfs_fs(void)
 {
 	int err;
 
-	err = nfs_idmap_init();
-	if (err < 0)
-		goto out10;
-
 	err = nfs_dns_resolver_init();
 	if (err < 0)
-		goto out9;
+		goto out11;
 
 	err = register_pernet_subsys(&nfs_net_ops);
 	if (err < 0)
-		goto out8;
+		goto out10;
 
 	err = nfs_fscache_register();
 	if (err < 0)
-		goto out7;
+		goto out9;
 
 	err = nfsiod_start();
 	if (err)
-		goto out6;
+		goto out8;
 
 	err = nfs_fs_proc_init();
 	if (err)
-		goto out5;
+		goto out7;
 
 	err = nfs_init_nfspagecache();
 	if (err)
-		goto out4;
+		goto out6;
 
 	err = nfs_init_inodecache();
 	if (err)
-		goto out3;
+		goto out5;
 
 	err = nfs_init_readpagecache();
 	if (err)
-		goto out2;
+		goto out4;
 
 	err = nfs_init_writepagecache();
 	if (err)
-		goto out1;
+		goto out3;
 
 	err = nfs_init_directcache();
 	if (err)
-		goto out0;
+		goto out2;
 
 #ifdef CONFIG_PROC_FS
 	rpc_proc_register(&init_net, &nfs_rpcstat);
 #endif
+
+#ifdef CONFIG_NFS_V4
+	err = init_nfs_v4();
+	if (err)
+		goto out1;
+#endif
+
 	if ((err = register_nfs_fs()) != 0)
-		goto out;
+		goto out0;
+
 	return 0;
-out:
+out0:
+#ifdef CONFIG_NFS_V4
+	exit_nfs_v4();
+out1:
+#endif
 #ifdef CONFIG_PROC_FS
 	rpc_proc_unregister(&init_net, "nfs");
 #endif
 	nfs_destroy_directcache();
-out0:
-	nfs_destroy_writepagecache();
-out1:
-	nfs_destroy_readpagecache();
 out2:
-	nfs_destroy_inodecache();
+	nfs_destroy_writepagecache();
 out3:
-	nfs_destroy_nfspagecache();
+	nfs_destroy_readpagecache();
 out4:
-	nfs_fs_proc_exit();
+	nfs_destroy_inodecache();
 out5:
-	nfsiod_stop();
+	nfs_destroy_nfspagecache();
 out6:
-	nfs_fscache_unregister();
+	nfs_fs_proc_exit();
 out7:
-	unregister_pernet_subsys(&nfs_net_ops);
+	nfsiod_stop();
 out8:
-	nfs_dns_resolver_destroy();
+	nfs_fscache_unregister();
 out9:
-	nfs_idmap_quit();
+	unregister_pernet_subsys(&nfs_net_ops);
 out10:
+	nfs_dns_resolver_destroy();
+out11:
 	return err;
 }
 
 static void __exit exit_nfs_fs(void)
 {
+#ifdef CONFIG_NFS_V4
+	exit_nfs_v4();
+#endif
 	nfs_destroy_directcache();
 	nfs_destroy_writepagecache();
 	nfs_destroy_readpagecache();
@@ -1717,7 +1725,6 @@ static void __exit exit_nfs_fs(void)
 	nfs_fscache_unregister();
 	unregister_pernet_subsys(&nfs_net_ops);
 	nfs_dns_resolver_destroy();
-	nfs_idmap_quit();
 #ifdef CONFIG_PROC_FS
 	rpc_proc_unregister(&init_net, "nfs");
 #endif

fs/nfs/internal.h

@@ -85,6 +85,17 @@ struct nfs_clone_mount {
  */
 #define NFS_MAX_READDIR_PAGES 8
 
+struct nfs_client_initdata {
+	unsigned long init_flags;
+	const char *hostname;
+	const struct sockaddr *addr;
+	size_t addrlen;
+	const struct nfs_rpc_ops *rpc_ops;
+	int proto;
+	u32 minorversion;
+	struct net *net;
+};
+
 /*
  * In-kernel mount arguments
  */
@@ -142,15 +153,36 @@ struct nfs_mount_request {
 	struct net		*net;
 };
 
+struct nfs_mount_info {
+	void (*fill_super)(struct super_block *, struct nfs_mount_info *);
+	int (*set_security)(struct super_block *, struct dentry *, struct nfs_mount_info *);
+	struct nfs_parsed_mount_data *parsed;
+	struct nfs_clone_mount *cloned;
+	struct nfs_fh *mntfh;
+};
+
 extern int nfs_mount(struct nfs_mount_request *info);
 extern void nfs_umount(const struct nfs_mount_request *info);
 
 /* client.c */
 extern const struct rpc_program nfs_program;
 extern void nfs_clients_init(struct net *net);
+extern struct nfs_client *nfs_alloc_client(const struct nfs_client_initdata *);
+int nfs_create_rpc_client(struct nfs_client *, const struct rpc_timeout *, rpc_authflavor_t);
+struct nfs_client *nfs_get_client(const struct nfs_client_initdata *,
+				  const struct rpc_timeout *, const char *,
+				  rpc_authflavor_t);
+int nfs_probe_fsinfo(struct nfs_server *server, struct nfs_fh *, struct nfs_fattr *);
+void nfs_server_insert_lists(struct nfs_server *);
+void nfs_init_timeout_values(struct rpc_timeout *, int, unsigned int, unsigned int);
+int nfs_init_server_rpcclient(struct nfs_server *, const struct rpc_timeout *t,
+		rpc_authflavor_t);
+struct nfs_server *nfs_alloc_server(void);
+void nfs_server_copy_userdata(struct nfs_server *, struct nfs_server *);
 
 extern void nfs_cleanup_cb_ident_idr(struct net *);
 extern void nfs_put_client(struct nfs_client *);
+extern void nfs_free_client(struct nfs_client *);
 extern struct nfs_client *nfs4_find_client_ident(struct net *, int);
 extern struct nfs_client *
 nfs4_find_client_sessionid(struct net *, const struct sockaddr *,
@@ -188,6 +220,10 @@ static inline void nfs_fs_proc_exit(void)
 }
 #endif
 
+#ifdef CONFIG_NFS_V4_1
+int nfs_sockaddr_match_ipaddr(const struct sockaddr *, const struct sockaddr *);
+#endif
+
 /* callback_xdr.c */
 extern struct svc_version nfs4_callback_version1;
 extern struct svc_version nfs4_callback_version4;
@@ -245,6 +281,32 @@ extern struct nfs_client *nfs_init_client(struct nfs_client *clp,
 /* dir.c */
 extern int nfs_access_cache_shrinker(struct shrinker *shrink,
 					struct shrink_control *sc);
+struct dentry *nfs_lookup(struct inode *, struct dentry *, unsigned int);
+int nfs_create(struct inode *, struct dentry *, umode_t, bool);
+int nfs_mkdir(struct inode *, struct dentry *, umode_t);
+int nfs_rmdir(struct inode *, struct dentry *);
+int nfs_unlink(struct inode *, struct dentry *);
+int nfs_symlink(struct inode *, struct dentry *, const char *);
+int nfs_link(struct dentry *, struct inode *, struct dentry *);
+int nfs_mknod(struct inode *, struct dentry *, umode_t, dev_t);
+int nfs_rename(struct inode *, struct dentry *, struct inode *, struct dentry *);
+
+/* file.c */
+int nfs_file_fsync_commit(struct file *, loff_t, loff_t, int);
+loff_t nfs_file_llseek(struct file *, loff_t, int);
+int nfs_file_flush(struct file *, fl_owner_t);
+ssize_t nfs_file_read(struct kiocb *, const struct iovec *, unsigned long, loff_t);
+ssize_t nfs_file_splice_read(struct file *, loff_t *, struct pipe_inode_info *,
+			     size_t, unsigned int);
+int nfs_file_mmap(struct file *, struct vm_area_struct *);
+ssize_t nfs_file_write(struct kiocb *, const struct iovec *, unsigned long, loff_t);
+int nfs_file_release(struct inode *, struct file *);
+int nfs_lock(struct file *, int, struct file_lock *);
+int nfs_flock(struct file *, int, struct file_lock *);
+ssize_t nfs_file_splice_write(struct pipe_inode_info *, struct file *, loff_t *,
+			      size_t, unsigned int);
+int nfs_check_flags(int);
+int nfs_setlease(struct file *, long, struct file_lock **);
 
 /* inode.c */
 extern struct workqueue_struct *nfsiod_workqueue;
@@ -264,6 +326,16 @@ extern struct file_system_type nfs_xdev_fs_type;
 extern struct file_system_type nfs4_xdev_fs_type;
 extern struct file_system_type nfs4_referral_fs_type;
 #endif
+void nfs_initialise_sb(struct super_block *);
+int nfs_set_sb_security(struct super_block *, struct dentry *, struct nfs_mount_info *);
+int nfs_clone_sb_security(struct super_block *, struct dentry *, struct nfs_mount_info *);
+struct dentry *nfs_fs_mount_common(struct file_system_type *, struct nfs_server *,
+				   int, const char *, struct nfs_mount_info *);
+struct dentry *nfs_fs_mount(struct file_system_type *, int, const char *, void *);
+struct dentry * nfs_xdev_mount_common(struct file_system_type *, int,
+		const char *, struct nfs_mount_info *);
+void nfs_kill_super(struct super_block *);
+void nfs_fill_super(struct super_block *, struct nfs_mount_info *);
 
 extern struct rpc_stat nfs_rpcstat;
 
@@ -304,12 +376,23 @@ extern int nfs_initiate_read(struct rpc_clnt *clnt,
 extern void nfs_read_prepare(struct rpc_task *task, void *calldata);
 extern int nfs_generic_pagein(struct nfs_pageio_descriptor *desc,
 			      struct nfs_pgio_header *hdr);
-extern void nfs_pageio_init_read_mds(struct nfs_pageio_descriptor *pgio,
+extern void nfs_pageio_init_read(struct nfs_pageio_descriptor *pgio,
 			struct inode *inode,
 			const struct nfs_pgio_completion_ops *compl_ops);
 extern void nfs_pageio_reset_read_mds(struct nfs_pageio_descriptor *pgio);
 extern void nfs_readdata_release(struct nfs_read_data *rdata);
 
+/* super.c */
+void nfs_clone_super(struct super_block *, struct nfs_mount_info *);
+void nfs_umount_begin(struct super_block *);
+int  nfs_statfs(struct dentry *, struct kstatfs *);
+int  nfs_show_options(struct seq_file *, struct dentry *);
+int  nfs_show_devname(struct seq_file *, struct dentry *);
+int  nfs_show_path(struct seq_file *, struct dentry *);
+int  nfs_show_stats(struct seq_file *, struct dentry *);
+void nfs_put_super(struct super_block *);
+int nfs_remount(struct super_block *sb, int *flags, char *raw_data);
+
 /* write.c */
 extern void nfs_pageio_init_write(struct nfs_pageio_descriptor *pgio,
 			struct inode *inode, int ioflags,
@@ -318,7 +401,7 @@ extern struct nfs_write_header *nfs_writehdr_alloc(void);
 extern void nfs_writehdr_free(struct nfs_pgio_header *hdr);
 extern int nfs_generic_flush(struct nfs_pageio_descriptor *desc,
 			     struct nfs_pgio_header *hdr);
-extern void nfs_pageio_init_write_mds(struct nfs_pageio_descriptor *pgio,
+extern void nfs_pageio_init_write(struct nfs_pageio_descriptor *pgio,
 			struct inode *inode, int ioflags,
 			const struct nfs_pgio_completion_ops *compl_ops);
 extern void nfs_pageio_reset_write_mds(struct nfs_pageio_descriptor *pgio);

fs/nfs/nfs2xdr.c

@@ -106,19 +106,16 @@ static void print_overflow_msg(const char *func, const struct xdr_stream *xdr)
 static int decode_nfsdata(struct xdr_stream *xdr, struct nfs_readres *result)
 {
 	u32 recvd, count;
-	size_t hdrlen;
 	__be32 *p;
 
 	p = xdr_inline_decode(xdr, 4);
 	if (unlikely(p == NULL))
 		goto out_overflow;
 	count = be32_to_cpup(p);
-	hdrlen = (u8 *)xdr->p - (u8 *)xdr->iov->iov_base;
-	recvd = xdr->buf->len - hdrlen;
+	recvd = xdr_read_pages(xdr, count);
 	if (unlikely(count > recvd))
 		goto out_cheating;
 out:
-	xdr_read_pages(xdr, count);
 	result->eof = 0;	/* NFSv2 does not pass EOF flag on the wire. */
 	result->count = count;
 	return count;
@@ -440,7 +437,6 @@ static void encode_path(struct xdr_stream *xdr, struct page **pages, u32 length)
 static int decode_path(struct xdr_stream *xdr)
 {
 	u32 length, recvd;
-	size_t hdrlen;
 	__be32 *p;
 
 	p = xdr_inline_decode(xdr, 4);
@@ -449,12 +445,9 @@ static int decode_path(struct xdr_stream *xdr)
 	length = be32_to_cpup(p);
 	if (unlikely(length >= xdr->buf->page_len || length > NFS_MAXPATHLEN))
 		goto out_size;
-	hdrlen = (u8 *)xdr->p - (u8 *)xdr->iov->iov_base;
-	recvd = xdr->buf->len - hdrlen;
+	recvd = xdr_read_pages(xdr, length);
 	if (unlikely(length > recvd))
 		goto out_cheating;
-
-	xdr_read_pages(xdr, length);
 	xdr_terminate_string(xdr->buf, length);
 	return 0;
 out_size:
@@ -972,22 +965,7 @@ out_overflow:
  */
 static int decode_readdirok(struct xdr_stream *xdr)
 {
-	u32 recvd, pglen;
-	size_t hdrlen;
-
-	pglen = xdr->buf->page_len;
-	hdrlen = (u8 *)xdr->p - (u8 *)xdr->iov->iov_base;
-	recvd = xdr->buf->len - hdrlen;
-	if (unlikely(pglen > recvd))
-		goto out_cheating;
-out:
-	xdr_read_pages(xdr, pglen);
-	return pglen;
-out_cheating:
-	dprintk("NFS: server cheating in readdir result: "
-		"pglen %u > recvd %u\n", pglen, recvd);
-	pglen = recvd;
-	goto out;
+	return xdr_read_pages(xdr, xdr->buf->page_len);
 }
 
 static int nfs2_xdr_dec_readdirres(struct rpc_rqst *req,

fs/nfs/nfs3proc.c

@@ -877,6 +877,46 @@ nfs3_proc_lock(struct file *filp, int cmd, struct file_lock *fl)
 	return nlmclnt_proc(NFS_SERVER(inode)->nlm_host, cmd, fl);
 }
 
+static int nfs3_have_delegation(struct inode *inode, fmode_t flags)
+{
+	return 0;
+}
+
+static int nfs3_return_delegation(struct inode *inode)
+{
+	nfs_wb_all(inode);
+	return 0;
+}
+
+static const struct inode_operations nfs3_dir_inode_operations = {
+	.create		= nfs_create,
+	.lookup		= nfs_lookup,
+	.link		= nfs_link,
+	.unlink		= nfs_unlink,
+	.symlink	= nfs_symlink,
+	.mkdir		= nfs_mkdir,
+	.rmdir		= nfs_rmdir,
+	.mknod		= nfs_mknod,
+	.rename		= nfs_rename,
+	.permission	= nfs_permission,
+	.getattr	= nfs_getattr,
+	.setattr	= nfs_setattr,
+	.listxattr	= nfs3_listxattr,
+	.getxattr	= nfs3_getxattr,
+	.setxattr	= nfs3_setxattr,
+	.removexattr	= nfs3_removexattr,
+};
+
+static const struct inode_operations nfs3_file_inode_operations = {
+	.permission	= nfs_permission,
+	.getattr	= nfs_getattr,
+	.setattr	= nfs_setattr,
+	.listxattr	= nfs3_listxattr,
+	.getxattr	= nfs3_getxattr,
+	.setxattr	= nfs3_setxattr,
+	.removexattr	= nfs3_removexattr,
+};
+
 const struct nfs_rpc_ops nfs_v3_clientops = {
 	.version	= 3,			/* protocol version */
 	.dentry_ops	= &nfs_dentry_operations,
@@ -910,9 +950,11 @@ const struct nfs_rpc_ops nfs_v3_clientops = {
 	.pathconf	= nfs3_proc_pathconf,
 	.decode_dirent	= nfs3_decode_dirent,
 	.read_setup	= nfs3_proc_read_setup,
+	.read_pageio_init = nfs_pageio_init_read,
 	.read_rpc_prepare = nfs3_proc_read_rpc_prepare,
 	.read_done	= nfs3_read_done,
 	.write_setup	= nfs3_proc_write_setup,
+	.write_pageio_init = nfs_pageio_init_write,
 	.write_rpc_prepare = nfs3_proc_write_rpc_prepare,
 	.write_done	= nfs3_write_done,
 	.commit_setup	= nfs3_proc_commit_setup,
@@ -921,5 +963,9 @@ const struct nfs_rpc_ops nfs_v3_clientops = {
 	.lock		= nfs3_proc_lock,
 	.clear_acl_cache = nfs3_forget_cached_acls,
 	.close_context	= nfs_close_context,
+	.have_delegation = nfs3_have_delegation,
+	.return_delegation = nfs3_return_delegation,
+	.alloc_client	= nfs_alloc_client,
 	.init_client	= nfs_init_client,
+	.free_client	= nfs_free_client,
 };

fs/nfs/nfs3xdr.c

@@ -246,7 +246,6 @@ static void encode_nfspath3(struct xdr_stream *xdr, struct page **pages,
 static int decode_nfspath3(struct xdr_stream *xdr)
 {
 	u32 recvd, count;
-	size_t hdrlen;
 	__be32 *p;
 
 	p = xdr_inline_decode(xdr, 4);
@@ -255,12 +254,9 @@ static int decode_nfspath3(struct xdr_stream *xdr)
 	count = be32_to_cpup(p);
 	if (unlikely(count >= xdr->buf->page_len || count > NFS3_MAXPATHLEN))
 		goto out_nametoolong;
-	hdrlen = (u8 *)xdr->p - (u8 *)xdr->iov->iov_base;
-	recvd = xdr->buf->len - hdrlen;
+	recvd = xdr_read_pages(xdr, count);
 	if (unlikely(count > recvd))
 		goto out_cheating;
-
-	xdr_read_pages(xdr, count);
 	xdr_terminate_string(xdr->buf, count);
 	return 0;
 
@@ -329,14 +325,14 @@ static void encode_createverf3(struct xdr_stream *xdr, const __be32 *verifier)
 	memcpy(p, verifier, NFS3_CREATEVERFSIZE);
 }
 
-static int decode_writeverf3(struct xdr_stream *xdr, __be32 *verifier)
+static int decode_writeverf3(struct xdr_stream *xdr, struct nfs_write_verifier *verifier)
 {
 	__be32 *p;
 
 	p = xdr_inline_decode(xdr, NFS3_WRITEVERFSIZE);
 	if (unlikely(p == NULL))
 		goto out_overflow;
-	memcpy(verifier, p, NFS3_WRITEVERFSIZE);
+	memcpy(verifier->data, p, NFS3_WRITEVERFSIZE);
 	return 0;
 out_overflow:
 	print_overflow_msg(__func__, xdr);
@@ -1587,7 +1583,6 @@ static int decode_read3resok(struct xdr_stream *xdr,
 			     struct nfs_readres *result)
 {
 	u32 eof, count, ocount, recvd;
-	size_t hdrlen;
 	__be32 *p;
 
 	p = xdr_inline_decode(xdr, 4 + 4 + 4);
@@ -1598,13 +1593,10 @@ static int decode_read3resok(struct xdr_stream *xdr,
 	ocount = be32_to_cpup(p++);
 	if (unlikely(ocount != count))
 		goto out_mismatch;
-	hdrlen = (u8 *)xdr->p - (u8 *)xdr->iov->iov_base;
-	recvd = xdr->buf->len - hdrlen;
+	recvd = xdr_read_pages(xdr, count);
 	if (unlikely(count > recvd))
 		goto out_cheating;
-
 out:
-	xdr_read_pages(xdr, count);
 	result->eof = eof;
 	result->count = count;
 	return count;
@@ -1676,20 +1668,22 @@ static int decode_write3resok(struct xdr_stream *xdr,
 {
 	__be32 *p;
 
-	p = xdr_inline_decode(xdr, 4 + 4 + NFS3_WRITEVERFSIZE);
+	p = xdr_inline_decode(xdr, 4 + 4);
 	if (unlikely(p == NULL))
 		goto out_overflow;
 	result->count = be32_to_cpup(p++);
 	result->verf->committed = be32_to_cpup(p++);
 	if (unlikely(result->verf->committed > NFS_FILE_SYNC))
 		goto out_badvalue;
-	memcpy(result->verf->verifier, p, NFS3_WRITEVERFSIZE);
+	if (decode_writeverf3(xdr, &result->verf->verifier))
+		goto out_eio;
 	return result->count;
 out_badvalue:
 	dprintk("NFS: bad stable_how value: %u\n", result->verf->committed);
 	return -EIO;
 out_overflow:
 	print_overflow_msg(__func__, xdr);
+out_eio:
 	return -EIO;
 }
 
@@ -2039,22 +2033,7 @@ out_truncated:
  */
 static int decode_dirlist3(struct xdr_stream *xdr)
 {
-	u32 recvd, pglen;
-	size_t hdrlen;
-
-	pglen = xdr->buf->page_len;
-	hdrlen = (u8 *)xdr->p - (u8 *)xdr->iov->iov_base;
-	recvd = xdr->buf->len - hdrlen;
-	if (unlikely(pglen > recvd))
-		goto out_cheating;
-out:
-	xdr_read_pages(xdr, pglen);
-	return pglen;
-out_cheating:
-	dprintk("NFS: server cheating in readdir result: "
-		"pglen %u > recvd %u\n", pglen, recvd);
-	pglen = recvd;
-	goto out;
+	return xdr_read_pages(xdr, xdr->buf->page_len);
 }
 
 static int decode_readdir3resok(struct xdr_stream *xdr,
@@ -2337,7 +2316,7 @@ static int nfs3_xdr_dec_commit3res(struct rpc_rqst *req,
 		goto out;
 	if (status != NFS3_OK)
 		goto out_status;
-	error = decode_writeverf3(xdr, result->verf->verifier);
+	error = decode_writeverf3(xdr, &result->verf->verifier);
 out:
 	return error;
 out_status:
@@ -2364,7 +2343,7 @@ static inline int decode_getacl3resok(struct xdr_stream *xdr,
 	if (result->mask & ~(NFS_ACL|NFS_ACLCNT|NFS_DFACL|NFS_DFACLCNT))
 		goto out;
 
-	hdrlen = (u8 *)xdr->p - (u8 *)xdr->iov->iov_base;
+	hdrlen = xdr_stream_pos(xdr);
 
 	acl = NULL;
 	if (result->mask & NFS_ACL)

fs/nfs/nfs4_fs.h

@@ -200,7 +200,13 @@ struct nfs4_state_maintenance_ops {
 };
 
 extern const struct dentry_operations nfs4_dentry_operations;
-extern const struct inode_operations nfs4_dir_inode_operations;
+
+/* dir.c */
+int nfs_atomic_open(struct inode *, struct dentry *, struct file *,
+		    unsigned, umode_t, int *);
+
+/* write.c */
+int nfs4_write_inode(struct inode *, struct writeback_control *);
 
 /* nfs4namespace.c */
 rpc_authflavor_t nfs_find_best_sec(struct nfs4_secinfo_flavors *);
@@ -301,6 +307,10 @@ extern const u32 nfs4_pathconf_bitmap[2];
 extern const u32 nfs4_fsinfo_bitmap[3];
 extern const u32 nfs4_fs_locations_bitmap[2];
 
+void nfs4_free_client(struct nfs_client *);
+
+struct nfs_client *nfs4_alloc_client(const struct nfs_client_initdata *);
+
 /* nfs4renewd.c */
 extern void nfs4_schedule_state_renewal(struct nfs_client *);
 extern void nfs4_renewd_prepare_shutdown(struct nfs_server *);
@@ -354,6 +364,27 @@ extern void nfs4_free_lock_state(struct nfs_server *server, struct nfs4_lock_sta
 
 extern const nfs4_stateid zero_stateid;
 
+/* nfs4super.c */
+struct nfs_mount_info;
+struct dentry *nfs4_try_mount(int, const char *, struct nfs_mount_info *);
+int init_nfs_v4(void);
+void exit_nfs_v4(void);
+
+/* nfs4sysctl.c */
+#ifdef CONFIG_SYSCTL
+int nfs4_register_sysctl(void);
+void nfs4_unregister_sysctl(void);
+#else
+static inline int nfs4_register_sysctl(void)
+{
+	return 0;
+}
+
+static inline void nfs4_unregister_sysctl(void)
+{
+}
+#endif
+
 /* nfs4xdr.c */
 extern struct rpc_procinfo nfs4_procedures[];
 

fs/nfs/nfs4client.c

@@ -0,0 +1,663 @@
+/*
+ * Copyright (C) 2006 Red Hat, Inc. All Rights Reserved.
+ * Written by David Howells (dhowells@redhat.com)
+ */
+#include <linux/module.h>
+#include <linux/nfs_fs.h>
+#include <linux/nfs_idmap.h>
+#include <linux/nfs_mount.h>
+#include <linux/sunrpc/auth.h>
+#include <linux/sunrpc/xprt.h>
+#include <linux/sunrpc/bc_xprt.h>
+#include "internal.h"
+#include "callback.h"
+#include "delegation.h"
+#include "pnfs.h"
+#include "netns.h"
+
+#define NFSDBG_FACILITY		NFSDBG_CLIENT
+
+/*
+ * Turn off NFSv4 uid/gid mapping when using AUTH_SYS
+ */
+static bool nfs4_disable_idmapping = true;
+
+/*
+ * Get a unique NFSv4.0 callback identifier which will be used
+ * by the V4.0 callback service to lookup the nfs_client struct
+ */
+static int nfs_get_cb_ident_idr(struct nfs_client *clp, int minorversion)
+{
+	int ret = 0;
+	struct nfs_net *nn = net_generic(clp->cl_net, nfs_net_id);
+
+	if (clp->rpc_ops->version != 4 || minorversion != 0)
+		return ret;
+retry:
+	if (!idr_pre_get(&nn->cb_ident_idr, GFP_KERNEL))
+		return -ENOMEM;
+	spin_lock(&nn->nfs_client_lock);
+	ret = idr_get_new(&nn->cb_ident_idr, clp, &clp->cl_cb_ident);
+	spin_unlock(&nn->nfs_client_lock);
+	if (ret == -EAGAIN)
+		goto retry;
+	return ret;
+}
+
+#ifdef CONFIG_NFS_V4_1
+static void nfs4_shutdown_session(struct nfs_client *clp)
+{
+	if (nfs4_has_session(clp)) {
+		nfs4_destroy_session(clp->cl_session);
+		nfs4_destroy_clientid(clp);
+	}
+
+}
+#else /* CONFIG_NFS_V4_1 */
+static void nfs4_shutdown_session(struct nfs_client *clp)
+{
+}
+#endif /* CONFIG_NFS_V4_1 */
+
+struct nfs_client *nfs4_alloc_client(const struct nfs_client_initdata *cl_init)
+{
+	int err;
+	struct nfs_client *clp = nfs_alloc_client(cl_init);
+	if (IS_ERR(clp))
+		return clp;
+
+	err = nfs_get_cb_ident_idr(clp, cl_init->minorversion);
+	if (err)
+		goto error;
+
+	spin_lock_init(&clp->cl_lock);
+	INIT_DELAYED_WORK(&clp->cl_renewd, nfs4_renew_state);
+	rpc_init_wait_queue(&clp->cl_rpcwaitq, "NFS client");
+	clp->cl_state = 1 << NFS4CLNT_LEASE_EXPIRED;
+	clp->cl_minorversion = cl_init->minorversion;
+	clp->cl_mvops = nfs_v4_minor_ops[cl_init->minorversion];
+	return clp;
+
+error:
+	kfree(clp);
+	return ERR_PTR(err);
+}
+
+/*
+ * Destroy the NFS4 callback service
+ */
+static void nfs4_destroy_callback(struct nfs_client *clp)
+{
+	if (__test_and_clear_bit(NFS_CS_CALLBACK, &clp->cl_res_state))
+		nfs_callback_down(clp->cl_mvops->minor_version);
+}
+
+static void nfs4_shutdown_client(struct nfs_client *clp)
+{
+	if (__test_and_clear_bit(NFS_CS_RENEWD, &clp->cl_res_state))
+		nfs4_kill_renewd(clp);
+	nfs4_shutdown_session(clp);
+	nfs4_destroy_callback(clp);
+	if (__test_and_clear_bit(NFS_CS_IDMAP, &clp->cl_res_state))
+		nfs_idmap_delete(clp);
+
+	rpc_destroy_wait_queue(&clp->cl_rpcwaitq);
+	kfree(clp->cl_serverowner);
+	kfree(clp->cl_serverscope);
+	kfree(clp->cl_implid);
+}
+
+void nfs4_free_client(struct nfs_client *clp)
+{
+	nfs4_shutdown_client(clp);
+	nfs_free_client(clp);
+}
+
+/*
+ * Initialize the NFS4 callback service
+ */
+static int nfs4_init_callback(struct nfs_client *clp)
+{
+	int error;
+
+	if (clp->rpc_ops->version == 4) {
+		struct rpc_xprt *xprt;
+
+		xprt = rcu_dereference_raw(clp->cl_rpcclient->cl_xprt);
+
+		if (nfs4_has_session(clp)) {
+			error = xprt_setup_backchannel(xprt,
+						NFS41_BC_MIN_CALLBACKS);
+			if (error < 0)
+				return error;
+		}
+
+		error = nfs_callback_up(clp->cl_mvops->minor_version, xprt);
+		if (error < 0) {
+			dprintk("%s: failed to start callback. Error = %d\n",
+				__func__, error);
+			return error;
+		}
+		__set_bit(NFS_CS_CALLBACK, &clp->cl_res_state);
+	}
+	return 0;
+}
+
+/*
+ * Initialize the minor version specific parts of an NFS4 client record
+ */
+static int nfs4_init_client_minor_version(struct nfs_client *clp)
+{
+#if defined(CONFIG_NFS_V4_1)
+	if (clp->cl_mvops->minor_version) {
+		struct nfs4_session *session = NULL;
+		/*
+		 * Create the session and mark it expired.
+		 * When a SEQUENCE operation encounters the expired session
+		 * it will do session recovery to initialize it.
+		 */
+		session = nfs4_alloc_session(clp);
+		if (!session)
+			return -ENOMEM;
+
+		clp->cl_session = session;
+		/*
+		 * The create session reply races with the server back
+		 * channel probe. Mark the client NFS_CS_SESSION_INITING
+		 * so that the client back channel can find the
+		 * nfs_client struct
+		 */
+		nfs_mark_client_ready(clp, NFS_CS_SESSION_INITING);
+	}
+#endif /* CONFIG_NFS_V4_1 */
+
+	return nfs4_init_callback(clp);
+}
+
+/**
+ * nfs4_init_client - Initialise an NFS4 client record
+ *
+ * @clp: nfs_client to initialise
+ * @timeparms: timeout parameters for underlying RPC transport
+ * @ip_addr: callback IP address in presentation format
+ * @authflavor: authentication flavor for underlying RPC transport
+ *
+ * Returns pointer to an NFS client, or an ERR_PTR value.
+ */
+struct nfs_client *nfs4_init_client(struct nfs_client *clp,
+				    const struct rpc_timeout *timeparms,
+				    const char *ip_addr,
+				    rpc_authflavor_t authflavour)
+{
+	char buf[INET6_ADDRSTRLEN + 1];
+	int error;
+
+	if (clp->cl_cons_state == NFS_CS_READY) {
+		/* the client is initialised already */
+		dprintk("<-- nfs4_init_client() = 0 [already %p]\n", clp);
+		return clp;
+	}
+
+	/* Check NFS protocol revision and initialize RPC op vector */
+	clp->rpc_ops = &nfs_v4_clientops;
+
+	__set_bit(NFS_CS_DISCRTRY, &clp->cl_flags);
+	error = nfs_create_rpc_client(clp, timeparms, authflavour);
+	if (error < 0)
+		goto error;
+
+	/* If no clientaddr= option was specified, find a usable cb address */
+	if (ip_addr == NULL) {
+		struct sockaddr_storage cb_addr;
+		struct sockaddr *sap = (struct sockaddr *)&cb_addr;
+
+		error = rpc_localaddr(clp->cl_rpcclient, sap, sizeof(cb_addr));
+		if (error < 0)
+			goto error;
+		error = rpc_ntop(sap, buf, sizeof(buf));
+		if (error < 0)
+			goto error;
+		ip_addr = (const char *)buf;
+	}
+	strlcpy(clp->cl_ipaddr, ip_addr, sizeof(clp->cl_ipaddr));
+
+	error = nfs_idmap_new(clp);
+	if (error < 0) {
+		dprintk("%s: failed to create idmapper. Error = %d\n",
+			__func__, error);
+		goto error;
+	}
+	__set_bit(NFS_CS_IDMAP, &clp->cl_res_state);
+
+	error = nfs4_init_client_minor_version(clp);
+	if (error < 0)
+		goto error;
+
+	if (!nfs4_has_session(clp))
+		nfs_mark_client_ready(clp, NFS_CS_READY);
+	return clp;
+
+error:
+	nfs_mark_client_ready(clp, error);
+	nfs_put_client(clp);
+	dprintk("<-- nfs4_init_client() = xerror %d\n", error);
+	return ERR_PTR(error);
+}
+
+static void nfs4_destroy_server(struct nfs_server *server)
+{
+	nfs_server_return_all_delegations(server);
+	unset_pnfs_layoutdriver(server);
+	nfs4_purge_state_owners(server);
+}
+
+/*
+ * NFSv4.0 callback thread helper
+ *
+ * Find a client by callback identifier
+ */
+struct nfs_client *
+nfs4_find_client_ident(struct net *net, int cb_ident)
+{
+	struct nfs_client *clp;
+	struct nfs_net *nn = net_generic(net, nfs_net_id);
+
+	spin_lock(&nn->nfs_client_lock);
+	clp = idr_find(&nn->cb_ident_idr, cb_ident);
+	if (clp)
+		atomic_inc(&clp->cl_count);
+	spin_unlock(&nn->nfs_client_lock);
+	return clp;
+}
+
+#if defined(CONFIG_NFS_V4_1)
+/* Common match routine for v4.0 and v4.1 callback services */
+static bool nfs4_cb_match_client(const struct sockaddr *addr,
+		struct nfs_client *clp, u32 minorversion)
+{
+	struct sockaddr *clap = (struct sockaddr *)&clp->cl_addr;
+
+	/* Don't match clients that failed to initialise */
+	if (!(clp->cl_cons_state == NFS_CS_READY ||
+	    clp->cl_cons_state == NFS_CS_SESSION_INITING))
+		return false;
+
+	smp_rmb();
+
+	/* Match the version and minorversion */
+	if (clp->rpc_ops->version != 4 ||
+	    clp->cl_minorversion != minorversion)
+		return false;
+
+	/* Match only the IP address, not the port number */
+	if (!nfs_sockaddr_match_ipaddr(addr, clap))
+		return false;
+
+	return true;
+}
+
+/*
+ * NFSv4.1 callback thread helper
+ * For CB_COMPOUND calls, find a client by IP address, protocol version,
+ * minorversion, and sessionID
+ *
+ * Returns NULL if no such client
+ */
+struct nfs_client *
+nfs4_find_client_sessionid(struct net *net, const struct sockaddr *addr,
+			   struct nfs4_sessionid *sid)
+{
+	struct nfs_client *clp;
+	struct nfs_net *nn = net_generic(net, nfs_net_id);
+
+	spin_lock(&nn->nfs_client_lock);
+	list_for_each_entry(clp, &nn->nfs_client_list, cl_share_link) {
+		if (nfs4_cb_match_client(addr, clp, 1) == false)
+			continue;
+
+		if (!nfs4_has_session(clp))
+			continue;
+
+		/* Match sessionid*/
+		if (memcmp(clp->cl_session->sess_id.data,
+		    sid->data, NFS4_MAX_SESSIONID_LEN) != 0)
+			continue;
+
+		atomic_inc(&clp->cl_count);
+		spin_unlock(&nn->nfs_client_lock);
+		return clp;
+	}
+	spin_unlock(&nn->nfs_client_lock);
+	return NULL;
+}
+
+#else /* CONFIG_NFS_V4_1 */
+
+struct nfs_client *
+nfs4_find_client_sessionid(struct net *net, const struct sockaddr *addr,
+			   struct nfs4_sessionid *sid)
+{
+	return NULL;
+}
+#endif /* CONFIG_NFS_V4_1 */
+
+/*
+ * Set up an NFS4 client
+ */
+static int nfs4_set_client(struct nfs_server *server,
+		const char *hostname,
+		const struct sockaddr *addr,
+		const size_t addrlen,
+		const char *ip_addr,
+		rpc_authflavor_t authflavour,
+		int proto, const struct rpc_timeout *timeparms,
+		u32 minorversion, struct net *net)
+{
+	struct nfs_client_initdata cl_init = {
+		.hostname = hostname,
+		.addr = addr,
+		.addrlen = addrlen,
+		.rpc_ops = &nfs_v4_clientops,
+		.proto = proto,
+		.minorversion = minorversion,
+		.net = net,
+	};
+	struct nfs_client *clp;
+	int error;
+
+	dprintk("--> nfs4_set_client()\n");
+
+	if (server->flags & NFS_MOUNT_NORESVPORT)
+		set_bit(NFS_CS_NORESVPORT, &cl_init.init_flags);
+
+	/* Allocate or find a client reference we can use */
+	clp = nfs_get_client(&cl_init, timeparms, ip_addr, authflavour);
+	if (IS_ERR(clp)) {
+		error = PTR_ERR(clp);
+		goto error;
+	}
+
+	/*
+	 * Query for the lease time on clientid setup or renewal
+	 *
+	 * Note that this will be set on nfs_clients that were created
+	 * only for the DS role and did not set this bit, but now will
+	 * serve a dual role.
+	 */
+	set_bit(NFS_CS_CHECK_LEASE_TIME, &clp->cl_res_state);
+
+	server->nfs_client = clp;
+	dprintk("<-- nfs4_set_client() = 0 [new %p]\n", clp);
+	return 0;
+error:
+	dprintk("<-- nfs4_set_client() = xerror %d\n", error);
+	return error;
+}
+
+/*
+ * Set up a pNFS Data Server client.
+ *
+ * Return any existing nfs_client that matches server address,port,version
+ * and minorversion.
+ *
+ * For a new nfs_client, use a soft mount (default), a low retrans and a
+ * low timeout interval so that if a connection is lost, we retry through
+ * the MDS.
+ */
+struct nfs_client *nfs4_set_ds_client(struct nfs_client* mds_clp,
+		const struct sockaddr *ds_addr, int ds_addrlen,
+		int ds_proto, unsigned int ds_timeo, unsigned int ds_retrans)
+{
+	struct nfs_client_initdata cl_init = {
+		.addr = ds_addr,
+		.addrlen = ds_addrlen,
+		.rpc_ops = &nfs_v4_clientops,
+		.proto = ds_proto,
+		.minorversion = mds_clp->cl_minorversion,
+		.net = mds_clp->cl_net,
+	};
+	struct rpc_timeout ds_timeout;
+	struct nfs_client *clp;
+
+	/*
+	 * Set an authflavor equual to the MDS value. Use the MDS nfs_client
+	 * cl_ipaddr so as to use the same EXCHANGE_ID co_ownerid as the MDS
+	 * (section 13.1 RFC 5661).
+	 */
+	nfs_init_timeout_values(&ds_timeout, ds_proto, ds_timeo, ds_retrans);
+	clp = nfs_get_client(&cl_init, &ds_timeout, mds_clp->cl_ipaddr,
+			     mds_clp->cl_rpcclient->cl_auth->au_flavor);
+
+	dprintk("<-- %s %p\n", __func__, clp);
+	return clp;
+}
+EXPORT_SYMBOL_GPL(nfs4_set_ds_client);
+
+/*
+ * Session has been established, and the client marked ready.
+ * Set the mount rsize and wsize with negotiated fore channel
+ * attributes which will be bound checked in nfs_server_set_fsinfo.
+ */
+static void nfs4_session_set_rwsize(struct nfs_server *server)
+{
+#ifdef CONFIG_NFS_V4_1
+	struct nfs4_session *sess;
+	u32 server_resp_sz;
+	u32 server_rqst_sz;
+
+	if (!nfs4_has_session(server->nfs_client))
+		return;
+	sess = server->nfs_client->cl_session;
+	server_resp_sz = sess->fc_attrs.max_resp_sz - nfs41_maxread_overhead;
+	server_rqst_sz = sess->fc_attrs.max_rqst_sz - nfs41_maxwrite_overhead;
+
+	if (server->rsize > server_resp_sz)
+		server->rsize = server_resp_sz;
+	if (server->wsize > server_rqst_sz)
+		server->wsize = server_rqst_sz;
+#endif /* CONFIG_NFS_V4_1 */
+}
+
+static int nfs4_server_common_setup(struct nfs_server *server,
+		struct nfs_fh *mntfh)
+{
+	struct nfs_fattr *fattr;
+	int error;
+
+	BUG_ON(!server->nfs_client);
+	BUG_ON(!server->nfs_client->rpc_ops);
+	BUG_ON(!server->nfs_client->rpc_ops->file_inode_ops);
+
+	/* data servers support only a subset of NFSv4.1 */
+	if (is_ds_only_client(server->nfs_client))
+		return -EPROTONOSUPPORT;
+
+	fattr = nfs_alloc_fattr();
+	if (fattr == NULL)
+		return -ENOMEM;
+
+	/* We must ensure the session is initialised first */
+	error = nfs4_init_session(server);
+	if (error < 0)
+		goto out;
+
+	/* Probe the root fh to retrieve its FSID and filehandle */
+	error = nfs4_get_rootfh(server, mntfh);
+	if (error < 0)
+		goto out;
+
+	dprintk("Server FSID: %llx:%llx\n",
+			(unsigned long long) server->fsid.major,
+			(unsigned long long) server->fsid.minor);
+	dprintk("Mount FH: %d\n", mntfh->size);
+
+	nfs4_session_set_rwsize(server);
+
+	error = nfs_probe_fsinfo(server, mntfh, fattr);
+	if (error < 0)
+		goto out;
+
+	if (server->namelen == 0 || server->namelen > NFS4_MAXNAMLEN)
+		server->namelen = NFS4_MAXNAMLEN;
+
+	nfs_server_insert_lists(server);
+	server->mount_time = jiffies;
+	server->destroy = nfs4_destroy_server;
+out:
+	nfs_free_fattr(fattr);
+	return error;
+}
+
+/*
+ * Create a version 4 volume record
+ */
+static int nfs4_init_server(struct nfs_server *server,
+		const struct nfs_parsed_mount_data *data)
+{
+	struct rpc_timeout timeparms;
+	int error;
+
+	dprintk("--> nfs4_init_server()\n");
+
+	nfs_init_timeout_values(&timeparms, data->nfs_server.protocol,
+			data->timeo, data->retrans);
+
+	/* Initialise the client representation from the mount data */
+	server->flags = data->flags;
+	server->caps |= NFS_CAP_ATOMIC_OPEN|NFS_CAP_CHANGE_ATTR|NFS_CAP_POSIX_LOCK;
+	if (!(data->flags & NFS_MOUNT_NORDIRPLUS))
+			server->caps |= NFS_CAP_READDIRPLUS;
+	server->options = data->options;
+
+	/* Get a client record */
+	error = nfs4_set_client(server,
+			data->nfs_server.hostname,
+			(const struct sockaddr *)&data->nfs_server.address,
+			data->nfs_server.addrlen,
+			data->client_address,
+			data->auth_flavors[0],
+			data->nfs_server.protocol,
+			&timeparms,
+			data->minorversion,
+			data->net);
+	if (error < 0)
+		goto error;
+
+	/*
+	 * Don't use NFS uid/gid mapping if we're using AUTH_SYS or lower
+	 * authentication.
+	 */
+	if (nfs4_disable_idmapping && data->auth_flavors[0] == RPC_AUTH_UNIX)
+		server->caps |= NFS_CAP_UIDGID_NOMAP;
+
+	if (data->rsize)
+		server->rsize = nfs_block_size(data->rsize, NULL);
+	if (data->wsize)
+		server->wsize = nfs_block_size(data->wsize, NULL);
+
+	server->acregmin = data->acregmin * HZ;
+	server->acregmax = data->acregmax * HZ;
+	server->acdirmin = data->acdirmin * HZ;
+	server->acdirmax = data->acdirmax * HZ;
+
+	server->port = data->nfs_server.port;
+
+	error = nfs_init_server_rpcclient(server, &timeparms, data->auth_flavors[0]);
+
+error:
+	/* Done */
+	dprintk("<-- nfs4_init_server() = %d\n", error);
+	return error;
+}
+
+/*
+ * Create a version 4 volume record
+ * - keyed on server and FSID
+ */
+struct nfs_server *nfs4_create_server(const struct nfs_parsed_mount_data *data,
+				      struct nfs_fh *mntfh)
+{
+	struct nfs_server *server;
+	int error;
+
+	dprintk("--> nfs4_create_server()\n");
+
+	server = nfs_alloc_server();
+	if (!server)
+		return ERR_PTR(-ENOMEM);
+
+	/* set up the general RPC client */
+	error = nfs4_init_server(server, data);
+	if (error < 0)
+		goto error;
+
+	error = nfs4_server_common_setup(server, mntfh);
+	if (error < 0)
+		goto error;
+
+	dprintk("<-- nfs4_create_server() = %p\n", server);
+	return server;
+
+error:
+	nfs_free_server(server);
+	dprintk("<-- nfs4_create_server() = error %d\n", error);
+	return ERR_PTR(error);
+}
+
+/*
+ * Create an NFS4 referral server record
+ */
+struct nfs_server *nfs4_create_referral_server(struct nfs_clone_mount *data,
+					       struct nfs_fh *mntfh)
+{
+	struct nfs_client *parent_client;
+	struct nfs_server *server, *parent_server;
+	int error;
+
+	dprintk("--> nfs4_create_referral_server()\n");
+
+	server = nfs_alloc_server();
+	if (!server)
+		return ERR_PTR(-ENOMEM);
+
+	parent_server = NFS_SB(data->sb);
+	parent_client = parent_server->nfs_client;
+
+	/* Initialise the client representation from the parent server */
+	nfs_server_copy_userdata(server, parent_server);
+	server->caps |= NFS_CAP_ATOMIC_OPEN|NFS_CAP_CHANGE_ATTR;
+
+	/* Get a client representation.
+	 * Note: NFSv4 always uses TCP, */
+	error = nfs4_set_client(server, data->hostname,
+				data->addr,
+				data->addrlen,
+				parent_client->cl_ipaddr,
+				data->authflavor,
+				rpc_protocol(parent_server->client),
+				parent_server->client->cl_timeout,
+				parent_client->cl_mvops->minor_version,
+				parent_client->cl_net);
+	if (error < 0)
+		goto error;
+
+	error = nfs_init_server_rpcclient(server, parent_server->client->cl_timeout, data->authflavor);
+	if (error < 0)
+		goto error;
+
+	error = nfs4_server_common_setup(server, mntfh);
+	if (error < 0)
+		goto error;
+
+	dprintk("<-- nfs_create_referral_server() = %p\n", server);
+	return server;
+
+error:
+	nfs_free_server(server);
+	dprintk("<-- nfs4_create_referral_server() = error %d\n", error);
+	return ERR_PTR(error);
+}
+
+module_param(nfs4_disable_idmapping, bool, 0644);
+MODULE_PARM_DESC(nfs4_disable_idmapping,
+		"Turn off NFSv4 idmapping when using 'sec=sys'");

fs/nfs/nfs4file.c

@@ -0,0 +1,126 @@
+/*
+ *  linux/fs/nfs/file.c
+ *
+ *  Copyright (C) 1992  Rick Sladkey
+ */
+#include <linux/nfs_fs.h>
+#include "internal.h"
+#include "pnfs.h"
+
+#define NFSDBG_FACILITY		NFSDBG_FILE
+
+static int
+nfs4_file_open(struct inode *inode, struct file *filp)
+{
+	struct nfs_open_context *ctx;
+	struct dentry *dentry = filp->f_path.dentry;
+	struct dentry *parent = NULL;
+	struct inode *dir;
+	unsigned openflags = filp->f_flags;
+	struct iattr attr;
+	int err;
+
+	BUG_ON(inode != dentry->d_inode);
+	/*
+	 * If no cached dentry exists or if it's negative, NFSv4 handled the
+	 * opens in ->lookup() or ->create().
+	 *
+	 * We only get this far for a cached positive dentry.  We skipped
+	 * revalidation, so handle it here by dropping the dentry and returning
+	 * -EOPENSTALE.  The VFS will retry the lookup/create/open.
+	 */
+
+	dprintk("NFS: open file(%s/%s)\n",
+		dentry->d_parent->d_name.name,
+		dentry->d_name.name);
+
+	if ((openflags & O_ACCMODE) == 3)
+		openflags--;
+
+	/* We can't create new files here */
+	openflags &= ~(O_CREAT|O_EXCL);
+
+	parent = dget_parent(dentry);
+	dir = parent->d_inode;
+
+	ctx = alloc_nfs_open_context(filp->f_path.dentry, filp->f_mode);
+	err = PTR_ERR(ctx);
+	if (IS_ERR(ctx))
+		goto out;
+
+	attr.ia_valid = ATTR_OPEN;
+	if (openflags & O_TRUNC) {
+		attr.ia_valid |= ATTR_SIZE;
+		attr.ia_size = 0;
+		nfs_wb_all(inode);
+	}
+
+	inode = NFS_PROTO(dir)->open_context(dir, ctx, openflags, &attr);
+	if (IS_ERR(inode)) {
+		err = PTR_ERR(inode);
+		switch (err) {
+		case -EPERM:
+		case -EACCES:
+		case -EDQUOT:
+		case -ENOSPC:
+		case -EROFS:
+			goto out_put_ctx;
+		default:
+			goto out_drop;
+		}
+	}
+	iput(inode);
+	if (inode != dentry->d_inode)
+		goto out_drop;
+
+	nfs_set_verifier(dentry, nfs_save_change_attribute(dir));
+	nfs_file_set_open_context(filp, ctx);
+	err = 0;
+
+out_put_ctx:
+	put_nfs_open_context(ctx);
+out:
+	dput(parent);
+	return err;
+
+out_drop:
+	d_drop(dentry);
+	err = -EOPENSTALE;
+	goto out_put_ctx;
+}
+
+static int
+nfs4_file_fsync(struct file *file, loff_t start, loff_t end, int datasync)
+{
+	int ret;
+	struct inode *inode = file->f_path.dentry->d_inode;
+
+	ret = filemap_write_and_wait_range(inode->i_mapping, start, end);
+	mutex_lock(&inode->i_mutex);
+	ret = nfs_file_fsync_commit(file, start, end, datasync);
+	if (!ret && !datasync)
+		/* application has asked for meta-data sync */
+		ret = pnfs_layoutcommit_inode(inode, true);
+	mutex_unlock(&inode->i_mutex);
+
+	return ret;
+}
+
+const struct file_operations nfs4_file_operations = {
+	.llseek		= nfs_file_llseek,
+	.read		= do_sync_read,
+	.write		= do_sync_write,
+	.aio_read	= nfs_file_read,
+	.aio_write	= nfs_file_write,
+	.mmap		= nfs_file_mmap,
+	.open		= nfs4_file_open,
+	.flush		= nfs_file_flush,
+	.release	= nfs_file_release,
+	.fsync		= nfs4_file_fsync,
+	.lock		= nfs_lock,
+	.flock		= nfs_flock,
+	.splice_read	= nfs_file_splice_read,
+	.splice_write	= nfs_file_splice_write,
+	.check_flags	= nfs_check_flags,
+	.setlease	= nfs_setlease,
+};

fs/nfs/nfs4filelayout.c

@@ -205,9 +205,9 @@ static int filelayout_async_handle_error(struct rpc_task *task,
 	case -EPIPE:
 		dprintk("%s DS connection error %d\n", __func__,
 			task->tk_status);
-		if (!filelayout_test_devid_invalid(devid))
-			_pnfs_return_layout(inode);
 		filelayout_mark_devid_invalid(devid);
+		clear_bit(NFS_INO_LAYOUTCOMMIT, &NFS_I(inode)->flags);
+		_pnfs_return_layout(inode);
 		rpc_wake_up(&tbl->slot_tbl_waitq);
 		nfs4_ds_disconnect(clp);
 		/* fall through */
@@ -351,9 +351,9 @@ static void prepare_to_resend_writes(struct nfs_commit_data *data)
 	struct nfs_page *first = nfs_list_entry(data->pages.next);
 
 	data->task.tk_status = 0;
-	memcpy(data->verf.verifier, first->wb_verf.verifier,
-	       sizeof(first->wb_verf.verifier));
-	data->verf.verifier[0]++; /* ensure verifier mismatch */
+	memcpy(&data->verf.verifier, &first->wb_verf,
+	       sizeof(data->verf.verifier));
+	data->verf.verifier.data[0]++; /* ensure verifier mismatch */
 }
 
 static int filelayout_commit_done_cb(struct rpc_task *task,

fs/nfs/nfs4filelayoutdev.c

@@ -728,7 +728,7 @@ get_device_info(struct inode *inode, struct nfs4_deviceid *dev_id, gfp_t gfp_fla
 	pdev->layout_type = LAYOUT_NFSV4_1_FILES;
 	pdev->pages = pages;
 	pdev->pgbase = 0;
-	pdev->pglen = PAGE_SIZE * max_pages;
+	pdev->pglen = max_resp_sz;
 	pdev->mincount = 0;
 
 	rc = nfs4_proc_getdeviceinfo(server, pdev);

fs/nfs/nfs4getroot.c

@@ -0,0 +1,49 @@
+/*
+* Copyright (C) 2006 Red Hat, Inc. All Rights Reserved.
+* Written by David Howells (dhowells@redhat.com)
+*/
+
+#include <linux/nfs_fs.h>
+#include "nfs4_fs.h"
+
+#define NFSDBG_FACILITY		NFSDBG_CLIENT
+
+int nfs4_get_rootfh(struct nfs_server *server, struct nfs_fh *mntfh)
+{
+	struct nfs_fsinfo fsinfo;
+	int ret = -ENOMEM;
+
+	dprintk("--> nfs4_get_rootfh()\n");
+
+	fsinfo.fattr = nfs_alloc_fattr();
+	if (fsinfo.fattr == NULL)
+		goto out;
+
+	/* Start by getting the root filehandle from the server */
+	ret = nfs4_proc_get_rootfh(server, mntfh, &fsinfo);
+	if (ret < 0) {
+		dprintk("nfs4_get_rootfh: getroot error = %d\n", -ret);
+		goto out;
+	}
+
+	if (!(fsinfo.fattr->valid & NFS_ATTR_FATTR_TYPE)
+			|| !S_ISDIR(fsinfo.fattr->mode)) {
+		printk(KERN_ERR "nfs4_get_rootfh:"
+		       " getroot encountered non-directory\n");
+		ret = -ENOTDIR;
+		goto out;
+	}
+
+	if (fsinfo.fattr->valid & NFS_ATTR_FATTR_V4_REFERRAL) {
+		printk(KERN_ERR "nfs4_get_rootfh:"
+		       " getroot obtained referral\n");
+		ret = -EREMOTE;
+		goto out;
+	}
+
+	memcpy(&server->fsid, &fsinfo.fattr->fsid, sizeof(server->fsid));
+out:
+	nfs_free_fattr(fsinfo.fattr);
+	dprintk("<-- nfs4_get_rootfh() = %d\n", ret);
+	return ret;
+}

fs/nfs/nfs4proc.c

@@ -43,7 +43,6 @@
 #include <linux/printk.h>
 #include <linux/slab.h>
 #include <linux/sunrpc/clnt.h>
-#include <linux/sunrpc/gss_api.h>
 #include <linux/nfs.h>
 #include <linux/nfs4.h>
 #include <linux/nfs_fs.h>
@@ -259,7 +258,12 @@ static int nfs4_wait_clnt_recover(struct nfs_client *clp)
 
 	res = wait_on_bit(&clp->cl_state, NFS4CLNT_MANAGER_RUNNING,
 			nfs_wait_bit_killable, TASK_KILLABLE);
-	return res;
+	if (res)
+		return res;
+
+	if (clp->cl_cons_state < 0)
+		return clp->cl_cons_state;
+	return 0;
 }
 
 static int nfs4_delay(struct rpc_clnt *clnt, long *timeout)
@@ -294,8 +298,8 @@ static int nfs4_handle_exception(struct nfs_server *server, int errorcode, struc
 		case 0:
 			return 0;
 		case -NFS4ERR_OPENMODE:
-			if (inode && nfs_have_delegation(inode, FMODE_READ)) {
-				nfs_inode_return_delegation(inode);
+			if (inode && nfs4_have_delegation(inode, FMODE_READ)) {
+				nfs4_inode_return_delegation(inode);
 				exception->retry = 1;
 				return 0;
 			}
@@ -1065,7 +1069,7 @@ static void nfs4_return_incompatible_delegation(struct inode *inode, fmode_t fmo
 		return;
 	}
 	rcu_read_unlock();
-	nfs_inode_return_delegation(inode);
+	nfs4_inode_return_delegation(inode);
 }
 
 static struct nfs4_state *nfs4_try_open_cached(struct nfs4_opendata *opendata)
@@ -1756,33 +1760,70 @@ static int nfs4_open_expired(struct nfs4_state_owner *sp, struct nfs4_state *sta
 }
 
 #if defined(CONFIG_NFS_V4_1)
-static int nfs41_check_expired_stateid(struct nfs4_state *state, nfs4_stateid *stateid, unsigned int flags)
+static void nfs41_clear_delegation_stateid(struct nfs4_state *state)
 {
-	int status = NFS_OK;
 	struct nfs_server *server = NFS_SERVER(state->inode);
+	nfs4_stateid *stateid = &state->stateid;
+	int status;
+
+	/* If a state reset has been done, test_stateid is unneeded */
+	if (test_bit(NFS_DELEGATED_STATE, &state->flags) == 0)
+		return;
 
-	if (state->flags & flags) {
-		status = nfs41_test_stateid(server, stateid);
-		if (status != NFS_OK) {
+	status = nfs41_test_stateid(server, stateid);
+	if (status != NFS_OK) {
+		/* Free the stateid unless the server explicitly
+		 * informs us the stateid is unrecognized. */
+		if (status != -NFS4ERR_BAD_STATEID)
 			nfs41_free_stateid(server, stateid);
-			state->flags &= ~flags;
-		}
+
+		clear_bit(NFS_DELEGATED_STATE, &state->flags);
+	}
+}
+
+/**
+ * nfs41_check_open_stateid - possibly free an open stateid
+ *
+ * @state: NFSv4 state for an inode
+ *
+ * Returns NFS_OK if recovery for this stateid is now finished.
+ * Otherwise a negative NFS4ERR value is returned.
+ */
+static int nfs41_check_open_stateid(struct nfs4_state *state)
+{
+	struct nfs_server *server = NFS_SERVER(state->inode);
+	nfs4_stateid *stateid = &state->stateid;
+	int status;
+
+	/* If a state reset has been done, test_stateid is unneeded */
+	if ((test_bit(NFS_O_RDONLY_STATE, &state->flags) == 0) &&
+	    (test_bit(NFS_O_WRONLY_STATE, &state->flags) == 0) &&
+	    (test_bit(NFS_O_RDWR_STATE, &state->flags) == 0))
+		return -NFS4ERR_BAD_STATEID;
+
+	status = nfs41_test_stateid(server, stateid);
+	if (status != NFS_OK) {
+		/* Free the stateid unless the server explicitly
+		 * informs us the stateid is unrecognized. */
+		if (status != -NFS4ERR_BAD_STATEID)
+			nfs41_free_stateid(server, stateid);
+
+		clear_bit(NFS_O_RDONLY_STATE, &state->flags);
+		clear_bit(NFS_O_WRONLY_STATE, &state->flags);
+		clear_bit(NFS_O_RDWR_STATE, &state->flags);
 	}
 	return status;
 }
 
 static int nfs41_open_expired(struct nfs4_state_owner *sp, struct nfs4_state *state)
 {
-	int deleg_status, open_status;
-	int deleg_flags = 1 << NFS_DELEGATED_STATE;
-	int open_flags = (1 << NFS_O_RDONLY_STATE) | (1 << NFS_O_WRONLY_STATE) | (1 << NFS_O_RDWR_STATE);
-
-	deleg_status = nfs41_check_expired_stateid(state, &state->stateid, deleg_flags);
-	open_status = nfs41_check_expired_stateid(state,  &state->open_stateid, open_flags);
+	int status;
 
-	if ((deleg_status == NFS_OK) && (open_status == NFS_OK))
-		return NFS_OK;
-	return nfs4_open_expired(sp, state);
+	nfs41_clear_delegation_stateid(state);
+	status = nfs41_check_open_stateid(state);
+	if (status != NFS_OK)
+		status = nfs4_open_expired(sp, state);
+	return status;
 }
 #endif
 
@@ -2375,11 +2416,15 @@ static int nfs4_find_root_sec(struct nfs_server *server, struct nfs_fh *fhandle,
 	int i, len, status = 0;
 	rpc_authflavor_t flav_array[NFS_MAX_SECFLAVORS];
 
-	len = gss_mech_list_pseudoflavors(&flav_array[0]);
-	flav_array[len] = RPC_AUTH_NULL;
-	len += 1;
+	len = rpcauth_list_flavors(flav_array, ARRAY_SIZE(flav_array));
+	BUG_ON(len < 0);
 
 	for (i = 0; i < len; i++) {
+		/* AUTH_UNIX is the default flavor if none was specified,
+		 * thus has already been tried. */
+		if (flav_array[i] == RPC_AUTH_UNIX)
+			continue;
+
 		status = nfs4_lookup_root_sec(server, fhandle, info, flav_array[i]);
 		if (status == -NFS4ERR_WRONGSEC || status == -EACCES)
 			continue;
@@ -2766,9 +2811,7 @@ static int nfs4_proc_access(struct inode *inode, struct nfs_access_entry *entry)
  *
  * In the case of WRITE, we also want to put the GETATTR after
  * the operation -- in this case because we want to make sure
- * we get the post-operation mtime and size.  This means that
- * we can't use xdr_encode_pages() as written: we need a variant
- * of it which would leave room in the 'tail' iovec.
+ * we get the post-operation mtime and size.
  *
  * Both of these changes to the XDR layer would in fact be quite
  * minor, but I decided to leave them for a subsequent patch.
@@ -2821,7 +2864,9 @@ nfs4_proc_create(struct inode *dir, struct dentry *dentry, struct iattr *sattr,
 		return PTR_ERR(ctx);
 
 	sattr->ia_mode &= ~current_umask();
-	state = nfs4_do_open(dir, dentry, ctx->mode, flags, sattr, ctx->cred, NULL);
+	state = nfs4_do_open(dir, dentry, ctx->mode,
+			flags, sattr, ctx->cred,
+			&ctx->mdsthreshold);
 	d_drop(dentry);
 	if (IS_ERR(state)) {
 		status = PTR_ERR(state);
@@ -3315,8 +3360,14 @@ static int nfs4_do_fsinfo(struct nfs_server *server, struct nfs_fh *fhandle, str
 
 static int nfs4_proc_fsinfo(struct nfs_server *server, struct nfs_fh *fhandle, struct nfs_fsinfo *fsinfo)
 {
+	int error;
+
 	nfs_fattr_init(fsinfo->fattr);
-	return nfs4_do_fsinfo(server, fhandle, fsinfo);
+	error = nfs4_do_fsinfo(server, fhandle, fsinfo);
+	if (error == 0)
+		set_pnfs_layoutdriver(server, fhandle, fsinfo->layouttype);
+
+	return error;
 }
 
 static int _nfs4_proc_pathconf(struct nfs_server *server, struct nfs_fh *fhandle,
@@ -3443,7 +3494,7 @@ bool nfs4_write_need_cache_consistency_data(const struct nfs_write_data *data)
 	/* Otherwise, request attributes if and only if we don't hold
 	 * a delegation
 	 */
-	return nfs_have_delegation(hdr->inode, FMODE_READ) == 0;
+	return nfs4_have_delegation(hdr->inode, FMODE_READ) == 0;
 }
 
 static void nfs4_proc_write_setup(struct nfs_write_data *data, struct rpc_message *msg)
@@ -3732,7 +3783,8 @@ static ssize_t __nfs4_get_acl_uncached(struct inode *inode, void *buf, size_t bu
 		.rpc_argp = &args,
 		.rpc_resp = &res,
 	};
-	int ret = -ENOMEM, npages, i, acl_len = 0;
+	int ret = -ENOMEM, npages, i;
+	size_t acl_len = 0;
 
 	npages = (buflen + PAGE_SIZE - 1) >> PAGE_SHIFT;
 	/* As long as we're doing a round trip to the server anyway,
@@ -3847,7 +3899,7 @@ static int __nfs4_proc_set_acl(struct inode *inode, const void *buf, size_t bufl
 	i = buf_to_pages_noslab(buf, buflen, arg.acl_pages, &arg.acl_pgbase);
 	if (i < 0)
 		return i;
-	nfs_inode_return_delegation(inode);
+	nfs4_inode_return_delegation(inode);
 	ret = nfs4_call_sync(server->client, server, &msg, &arg.seq_args, &res.seq_res, 1);
 
 	/*
@@ -3961,6 +4013,16 @@ static void nfs4_init_boot_verifier(const struct nfs_client *clp,
 	memcpy(bootverf->data, verf, sizeof(bootverf->data));
 }
 
+/**
+ * nfs4_proc_setclientid - Negotiate client ID
+ * @clp: state data structure
+ * @program: RPC program for NFSv4 callback service
+ * @port: IP port number for NFS4 callback service
+ * @cred: RPC credential to use for this call
+ * @res: where to place the result
+ *
+ * Returns zero, a negative errno, or a negative NFS4ERR status code.
+ */
 int nfs4_proc_setclientid(struct nfs_client *clp, u32 program,
 		unsigned short port, struct rpc_cred *cred,
 		struct nfs4_setclientid_res *res)
@@ -3977,44 +4039,44 @@ int nfs4_proc_setclientid(struct nfs_client *clp, u32 program,
 		.rpc_resp = res,
 		.rpc_cred = cred,
 	};
-	int loop = 0;
 	int status;
 
+	/* nfs_client_id4 */
 	nfs4_init_boot_verifier(clp, &sc_verifier);
-
-	for(;;) {
-		rcu_read_lock();
-		setclientid.sc_name_len = scnprintf(setclientid.sc_name,
-				sizeof(setclientid.sc_name), "%s/%s %s %s %u",
-				clp->cl_ipaddr,
-				rpc_peeraddr2str(clp->cl_rpcclient,
-							RPC_DISPLAY_ADDR),
-				rpc_peeraddr2str(clp->cl_rpcclient,
-							RPC_DISPLAY_PROTO),
-				clp->cl_rpcclient->cl_auth->au_ops->au_name,
-				clp->cl_id_uniquifier);
-		setclientid.sc_netid_len = scnprintf(setclientid.sc_netid,
+	rcu_read_lock();
+	setclientid.sc_name_len = scnprintf(setclientid.sc_name,
+			sizeof(setclientid.sc_name), "%s/%s %s",
+			clp->cl_ipaddr,
+			rpc_peeraddr2str(clp->cl_rpcclient,
+						RPC_DISPLAY_ADDR),
+			rpc_peeraddr2str(clp->cl_rpcclient,
+						RPC_DISPLAY_PROTO));
+	/* cb_client4 */
+	setclientid.sc_netid_len = scnprintf(setclientid.sc_netid,
 				sizeof(setclientid.sc_netid),
 				rpc_peeraddr2str(clp->cl_rpcclient,
 							RPC_DISPLAY_NETID));
-		setclientid.sc_uaddr_len = scnprintf(setclientid.sc_uaddr,
+	rcu_read_unlock();
+	setclientid.sc_uaddr_len = scnprintf(setclientid.sc_uaddr,
 				sizeof(setclientid.sc_uaddr), "%s.%u.%u",
 				clp->cl_ipaddr, port >> 8, port & 255);
-		rcu_read_unlock();
 
-		status = rpc_call_sync(clp->cl_rpcclient, &msg, RPC_TASK_TIMEOUT);
-		if (status != -NFS4ERR_CLID_INUSE)
-			break;
-		if (loop != 0) {
-			++clp->cl_id_uniquifier;
-			break;
-		}
-		++loop;
-		ssleep(clp->cl_lease_time / HZ + 1);
-	}
+	dprintk("NFS call  setclientid auth=%s, '%.*s'\n",
+		clp->cl_rpcclient->cl_auth->au_ops->au_name,
+		setclientid.sc_name_len, setclientid.sc_name);
+	status = rpc_call_sync(clp->cl_rpcclient, &msg, RPC_TASK_TIMEOUT);
+	dprintk("NFS reply setclientid: %d\n", status);
 	return status;
 }
 
+/**
+ * nfs4_proc_setclientid_confirm - Confirm client ID
+ * @clp: state data structure
+ * @res: result of a previous SETCLIENTID
+ * @cred: RPC credential to use for this call
+ *
+ * Returns zero, a negative errno, or a negative NFS4ERR status code.
+ */
 int nfs4_proc_setclientid_confirm(struct nfs_client *clp,
 		struct nfs4_setclientid_res *arg,
 		struct rpc_cred *cred)
@@ -4029,6 +4091,9 @@ int nfs4_proc_setclientid_confirm(struct nfs_client *clp,
 	unsigned long now;
 	int status;
 
+	dprintk("NFS call  setclientid_confirm auth=%s, (client ID %llx)\n",
+		clp->cl_rpcclient->cl_auth->au_ops->au_name,
+		clp->cl_clientid);
 	now = jiffies;
 	status = rpc_call_sync(clp->cl_rpcclient, &msg, RPC_TASK_TIMEOUT);
 	if (status == 0) {
@@ -4037,6 +4102,7 @@ int nfs4_proc_setclientid_confirm(struct nfs_client *clp,
 		clp->cl_last_renewal = now;
 		spin_unlock(&clp->cl_lock);
 	}
+	dprintk("NFS reply setclientid_confirm: %d\n", status);
 	return status;
 }
 
@@ -4681,9 +4747,17 @@ out:
 }
 
 #if defined(CONFIG_NFS_V4_1)
+/**
+ * nfs41_check_expired_locks - possibly free a lock stateid
+ *
+ * @state: NFSv4 state for an inode
+ *
+ * Returns NFS_OK if recovery for this stateid is now finished.
+ * Otherwise a negative NFS4ERR value is returned.
+ */
 static int nfs41_check_expired_locks(struct nfs4_state *state)
 {
-	int status, ret = NFS_OK;
+	int status, ret = -NFS4ERR_BAD_STATEID;
 	struct nfs4_lock_state *lsp;
 	struct nfs_server *server = NFS_SERVER(state->inode);
 
@@ -4691,7 +4765,11 @@ static int nfs41_check_expired_locks(struct nfs4_state *state)
 		if (lsp->ls_flags & NFS_LOCK_INITIALIZED) {
 			status = nfs41_test_stateid(server, &lsp->ls_stateid);
 			if (status != NFS_OK) {
-				nfs41_free_stateid(server, &lsp->ls_stateid);
+				/* Free the stateid unless the server
+				 * informs us the stateid is unrecognized. */
+				if (status != -NFS4ERR_BAD_STATEID)
+					nfs41_free_stateid(server,
+							&lsp->ls_stateid);
 				lsp->ls_flags &= ~NFS_LOCK_INITIALIZED;
 				ret = status;
 			}
@@ -4707,9 +4785,9 @@ static int nfs41_lock_expired(struct nfs4_state *state, struct file_lock *reques
 
 	if (test_bit(LK_STATE_IN_USE, &state->flags))
 		status = nfs41_check_expired_locks(state);
-	if (status == NFS_OK)
-		return status;
-	return nfs4_lock_expired(state, request);
+	if (status != NFS_OK)
+		status = nfs4_lock_expired(state, request);
+	return status;
 }
 #endif
 
@@ -4807,7 +4885,7 @@ nfs4_proc_lock(struct file *filp, int cmd, struct file_lock *request)
 	 * Don't rely on the VFS having checked the file open mode,
 	 * since it won't do this for flock() locks.
 	 */
-	switch (request->fl_type & (F_RDLCK|F_WRLCK|F_UNLCK)) {
+	switch (request->fl_type) {
 	case F_RDLCK:
 		if (!(filp->f_mode & FMODE_READ))
 			return -EBADF;
@@ -5168,6 +5246,8 @@ out:
 /*
  * nfs4_proc_exchange_id()
  *
+ * Returns zero, a negative errno, or a negative NFS4ERR status code.
+ *
  * Since the clientid has expired, all compounds using sessions
  * associated with the stale clientid will be returning
  * NFS4ERR_BADSESSION in the sequence operation, and will therefore
@@ -5192,16 +5272,14 @@ int nfs4_proc_exchange_id(struct nfs_client *clp, struct rpc_cred *cred)
 		.rpc_cred = cred,
 	};
 
-	dprintk("--> %s\n", __func__);
-	BUG_ON(clp == NULL);
-
 	nfs4_init_boot_verifier(clp, &verifier);
-
 	args.id_len = scnprintf(args.id, sizeof(args.id),
-				"%s/%s/%u",
+				"%s/%s",
 				clp->cl_ipaddr,
-				clp->cl_rpcclient->cl_nodename,
-				clp->cl_rpcclient->cl_auth->au_flavor);
+				clp->cl_rpcclient->cl_nodename);
+	dprintk("NFS call  exchange_id auth=%s, '%.*s'\n",
+		clp->cl_rpcclient->cl_auth->au_ops->au_name,
+		args.id_len, args.id);
 
 	res.server_owner = kzalloc(sizeof(struct nfs41_server_owner),
 					GFP_NOFS);
@@ -5264,12 +5342,12 @@ out_server_scope:
 	kfree(res.server_scope);
 out:
 	if (clp->cl_implid != NULL)
-		dprintk("%s: Server Implementation ID: "
+		dprintk("NFS reply exchange_id: Server Implementation ID: "
 			"domain: %s, name: %s, date: %llu,%u\n",
-			__func__, clp->cl_implid->domain, clp->cl_implid->name,
+			clp->cl_implid->domain, clp->cl_implid->name,
 			clp->cl_implid->date.seconds,
 			clp->cl_implid->date.nseconds);
-	dprintk("<-- %s status= %d\n", __func__, status);
+	dprintk("NFS reply exchange_id: %d\n", status);
 	return status;
 }
 
@@ -6570,22 +6648,36 @@ static int _nfs41_test_stateid(struct nfs_server *server, nfs4_stateid *stateid)
 		.rpc_resp = &res,
 	};
 
+	dprintk("NFS call  test_stateid %p\n", stateid);
 	nfs41_init_sequence(&args.seq_args, &res.seq_res, 0);
 	status = nfs4_call_sync_sequence(server->client, server, &msg, &args.seq_args, &res.seq_res, 1);
-
-	if (status == NFS_OK)
-		return res.status;
-	return status;
+	if (status != NFS_OK) {
+		dprintk("NFS reply test_stateid: failed, %d\n", status);
+		return status;
+	}
+	dprintk("NFS reply test_stateid: succeeded, %d\n", -res.status);
+	return -res.status;
 }
 
+/**
+ * nfs41_test_stateid - perform a TEST_STATEID operation
+ *
+ * @server: server / transport on which to perform the operation
+ * @stateid: state ID to test
+ *
+ * Returns NFS_OK if the server recognizes that "stateid" is valid.
+ * Otherwise a negative NFS4ERR value is returned if the operation
+ * failed or the state ID is not currently valid.
+ */
 static int nfs41_test_stateid(struct nfs_server *server, nfs4_stateid *stateid)
 {
 	struct nfs4_exception exception = { };
 	int err;
 	do {
-		err = nfs4_handle_exception(server,
-				_nfs41_test_stateid(server, stateid),
-				&exception);
+		err = _nfs41_test_stateid(server, stateid);
+		if (err != -NFS4ERR_DELAY)
+			break;
+		nfs4_handle_exception(server, err, &exception);
 	} while (exception.retry);
 	return err;
 }
@@ -6601,19 +6693,34 @@ static int _nfs4_free_stateid(struct nfs_server *server, nfs4_stateid *stateid)
 		.rpc_argp = &args,
 		.rpc_resp = &res,
 	};
+	int status;
 
+	dprintk("NFS call  free_stateid %p\n", stateid);
 	nfs41_init_sequence(&args.seq_args, &res.seq_res, 0);
-	return nfs4_call_sync_sequence(server->client, server, &msg, &args.seq_args, &res.seq_res, 1);
+	status = nfs4_call_sync_sequence(server->client, server, &msg,
+					 &args.seq_args, &res.seq_res, 1);
+	dprintk("NFS reply free_stateid: %d\n", status);
+	return status;
 }
 
+/**
+ * nfs41_free_stateid - perform a FREE_STATEID operation
+ *
+ * @server: server / transport on which to perform the operation
+ * @stateid: state ID to release
+ *
+ * Returns NFS_OK if the server freed "stateid".  Otherwise a
+ * negative NFS4ERR value is returned.
+ */
 static int nfs41_free_stateid(struct nfs_server *server, nfs4_stateid *stateid)
 {
 	struct nfs4_exception exception = { };
 	int err;
 	do {
-		err = nfs4_handle_exception(server,
-				_nfs4_free_stateid(server, stateid),
-				&exception);
+		err = _nfs4_free_stateid(server, stateid);
+		if (err != -NFS4ERR_DELAY)
+			break;
+		nfs4_handle_exception(server, err, &exception);
 	} while (exception.retry);
 	return err;
 }
@@ -6725,6 +6832,26 @@ const struct nfs4_minor_version_ops *nfs_v4_minor_ops[] = {
 #endif
 };
 
+const struct inode_operations nfs4_dir_inode_operations = {
+	.create		= nfs_create,
+	.lookup		= nfs_lookup,
+	.atomic_open	= nfs_atomic_open,
+	.link		= nfs_link,
+	.unlink		= nfs_unlink,
+	.symlink	= nfs_symlink,
+	.mkdir		= nfs_mkdir,
+	.rmdir		= nfs_rmdir,
+	.mknod		= nfs_mknod,
+	.rename		= nfs_rename,
+	.permission	= nfs_permission,
+	.getattr	= nfs_getattr,
+	.setattr	= nfs_setattr,
+	.getxattr	= generic_getxattr,
+	.setxattr	= generic_setxattr,
+	.listxattr	= generic_listxattr,
+	.removexattr	= generic_removexattr,
+};
+
 static const struct inode_operations nfs4_file_inode_operations = {
 	.permission	= nfs_permission,
 	.getattr	= nfs_getattr,
@@ -6769,9 +6896,11 @@ const struct nfs_rpc_ops nfs_v4_clientops = {
 	.set_capabilities = nfs4_server_capabilities,
 	.decode_dirent	= nfs4_decode_dirent,
 	.read_setup	= nfs4_proc_read_setup,
+	.read_pageio_init = pnfs_pageio_init_read,
 	.read_rpc_prepare = nfs4_proc_read_rpc_prepare,
 	.read_done	= nfs4_read_done,
 	.write_setup	= nfs4_proc_write_setup,
+	.write_pageio_init = pnfs_pageio_init_write,
 	.write_rpc_prepare = nfs4_proc_write_rpc_prepare,
 	.write_done	= nfs4_write_done,
 	.commit_setup	= nfs4_proc_commit_setup,
@@ -6781,7 +6910,11 @@ const struct nfs_rpc_ops nfs_v4_clientops = {
 	.clear_acl_cache = nfs4_zap_acl_attr,
 	.close_context  = nfs4_close_context,
 	.open_context	= nfs4_atomic_open,
+	.have_delegation = nfs4_have_delegation,
+	.return_delegation = nfs4_inode_return_delegation,
+	.alloc_client	= nfs4_alloc_client,
 	.init_client	= nfs4_init_client,
+	.free_client	= nfs4_free_client,
 };
 
 static const struct xattr_handler nfs4_xattr_nfs4_acl_handler = {

fs/nfs/nfs4state.c

@@ -1606,10 +1606,15 @@ static int nfs4_handle_reclaim_lease_error(struct nfs_client *clp, int status)
 			return -ESERVERFAULT;
 		/* Lease confirmation error: retry after purging the lease */
 		ssleep(1);
-	case -NFS4ERR_CLID_INUSE:
 	case -NFS4ERR_STALE_CLIENTID:
 		clear_bit(NFS4CLNT_LEASE_CONFIRM, &clp->cl_state);
 		break;
+	case -NFS4ERR_CLID_INUSE:
+		pr_err("NFS: Server %s reports our clientid is in use\n",
+			clp->cl_hostname);
+		nfs_mark_client_ready(clp, -EPERM);
+		clear_bit(NFS4CLNT_LEASE_CONFIRM, &clp->cl_state);
+		return -EPERM;
 	case -EACCES:
 		if (clp->cl_machine_cred == NULL)
 			return -EACCES;
@@ -1642,7 +1647,7 @@ static int nfs4_handle_reclaim_lease_error(struct nfs_client *clp, int status)
 	return 0;
 }
 
-static int nfs4_reclaim_lease(struct nfs_client *clp)
+static int nfs4_establish_lease(struct nfs_client *clp)
 {
 	struct rpc_cred *cred;
 	const struct nfs4_state_recovery_ops *ops =
@@ -1655,7 +1660,41 @@ static int nfs4_reclaim_lease(struct nfs_client *clp)
 	status = ops->establish_clid(clp, cred);
 	put_rpccred(cred);
 	if (status != 0)
+		return status;
+	pnfs_destroy_all_layouts(clp);
+	return 0;
+}
+
+/*
+ * Returns zero or a negative errno.  NFS4ERR values are converted
+ * to local errno values.
+ */
+static int nfs4_reclaim_lease(struct nfs_client *clp)
+{
+	int status;
+
+	status = nfs4_establish_lease(clp);
+	if (status < 0)
+		return nfs4_handle_reclaim_lease_error(clp, status);
+	if (test_and_clear_bit(NFS4CLNT_SERVER_SCOPE_MISMATCH, &clp->cl_state))
+		nfs4_state_start_reclaim_nograce(clp);
+	if (!test_bit(NFS4CLNT_RECLAIM_NOGRACE, &clp->cl_state))
+		set_bit(NFS4CLNT_RECLAIM_REBOOT, &clp->cl_state);
+	clear_bit(NFS4CLNT_CHECK_LEASE, &clp->cl_state);
+	clear_bit(NFS4CLNT_LEASE_EXPIRED, &clp->cl_state);
+	return 0;
+}
+
+static int nfs4_purge_lease(struct nfs_client *clp)
+{
+	int status;
+
+	status = nfs4_establish_lease(clp);
+	if (status < 0)
 		return nfs4_handle_reclaim_lease_error(clp, status);
+	clear_bit(NFS4CLNT_PURGE_STATE, &clp->cl_state);
+	set_bit(NFS4CLNT_LEASE_EXPIRED, &clp->cl_state);
+	nfs4_state_start_reclaim_nograce(clp);
 	return 0;
 }
 
@@ -1764,6 +1803,8 @@ static int nfs4_reset_session(struct nfs_client *clp)
 	struct rpc_cred *cred;
 	int status;
 
+	if (!nfs4_has_session(clp))
+		return 0;
 	nfs4_begin_drain_session(clp);
 	cred = nfs4_get_exchange_id_cred(clp);
 	status = nfs4_proc_destroy_session(clp->cl_session, cred);
@@ -1792,12 +1833,14 @@ out:
 
 static int nfs4_recall_slot(struct nfs_client *clp)
 {
-	struct nfs4_slot_table *fc_tbl = &clp->cl_session->fc_slot_table;
-	struct nfs4_channel_attrs *fc_attrs = &clp->cl_session->fc_attrs;
+	struct nfs4_slot_table *fc_tbl;
 	struct nfs4_slot *new, *old;
 	int i;
 
+	if (!nfs4_has_session(clp))
+		return 0;
 	nfs4_begin_drain_session(clp);
+	fc_tbl = &clp->cl_session->fc_slot_table;
 	new = kmalloc(fc_tbl->target_max_slots * sizeof(struct nfs4_slot),
 		      GFP_NOFS);
         if (!new)
@@ -1810,11 +1853,10 @@ static int nfs4_recall_slot(struct nfs_client *clp)
 	fc_tbl->slots = new;
 	fc_tbl->max_slots = fc_tbl->target_max_slots;
 	fc_tbl->target_max_slots = 0;
-	fc_attrs->max_reqs = fc_tbl->max_slots;
+	clp->cl_session->fc_attrs.max_reqs = fc_tbl->max_slots;
 	spin_unlock(&fc_tbl->slot_tbl_lock);
 
 	kfree(old);
-	nfs4_end_drain_session(clp);
 	return 0;
 }
 
@@ -1823,6 +1865,8 @@ static int nfs4_bind_conn_to_session(struct nfs_client *clp)
 	struct rpc_cred *cred;
 	int ret;
 
+	if (!nfs4_has_session(clp))
+		return 0;
 	nfs4_begin_drain_session(clp);
 	cred = nfs4_get_exchange_id_cred(clp);
 	ret = nfs4_proc_bind_conn_to_session(clp, cred);
@@ -1857,37 +1901,29 @@ static int nfs4_bind_conn_to_session(struct nfs_client *clp)
 static void nfs4_state_manager(struct nfs_client *clp)
 {
 	int status = 0;
+	const char *section = "", *section_sep = "";
 
 	/* Ensure exclusive access to NFSv4 state */
 	do {
 		if (test_bit(NFS4CLNT_PURGE_STATE, &clp->cl_state)) {
-			status = nfs4_reclaim_lease(clp);
+			section = "purge state";
+			status = nfs4_purge_lease(clp);
 			if (status < 0)
 				goto out_error;
-			clear_bit(NFS4CLNT_PURGE_STATE, &clp->cl_state);
-			set_bit(NFS4CLNT_LEASE_EXPIRED, &clp->cl_state);
+			continue;
 		}
 
-		if (test_and_clear_bit(NFS4CLNT_LEASE_EXPIRED, &clp->cl_state)) {
+		if (test_bit(NFS4CLNT_LEASE_EXPIRED, &clp->cl_state)) {
+			section = "lease expired";
 			/* We're going to have to re-establish a clientid */
 			status = nfs4_reclaim_lease(clp);
 			if (status < 0)
 				goto out_error;
-			if (test_bit(NFS4CLNT_LEASE_EXPIRED, &clp->cl_state))
-				continue;
-			clear_bit(NFS4CLNT_CHECK_LEASE, &clp->cl_state);
-
-			if (test_and_clear_bit(NFS4CLNT_SERVER_SCOPE_MISMATCH,
-					       &clp->cl_state))
-				nfs4_state_start_reclaim_nograce(clp);
-			else
-				set_bit(NFS4CLNT_RECLAIM_REBOOT,
-					&clp->cl_state);
-
-			pnfs_destroy_all_layouts(clp);
+			continue;
 		}
 
 		if (test_and_clear_bit(NFS4CLNT_CHECK_LEASE, &clp->cl_state)) {
+			section = "check lease";
 			status = nfs4_check_lease(clp);
 			if (status < 0)
 				goto out_error;
@@ -1896,8 +1932,8 @@ static void nfs4_state_manager(struct nfs_client *clp)
 		}
 
 		/* Initialize or reset the session */
-		if (test_and_clear_bit(NFS4CLNT_SESSION_RESET, &clp->cl_state)
-		   && nfs4_has_session(clp)) {
+		if (test_and_clear_bit(NFS4CLNT_SESSION_RESET, &clp->cl_state)) {
+			section = "reset session";
 			status = nfs4_reset_session(clp);
 			if (test_bit(NFS4CLNT_LEASE_EXPIRED, &clp->cl_state))
 				continue;
@@ -1907,15 +1943,26 @@ static void nfs4_state_manager(struct nfs_client *clp)
 
 		/* Send BIND_CONN_TO_SESSION */
 		if (test_and_clear_bit(NFS4CLNT_BIND_CONN_TO_SESSION,
-				&clp->cl_state) && nfs4_has_session(clp)) {
+				&clp->cl_state)) {
+			section = "bind conn to session";
 			status = nfs4_bind_conn_to_session(clp);
 			if (status < 0)
 				goto out_error;
 			continue;
 		}
 
+		/* Recall session slots */
+		if (test_and_clear_bit(NFS4CLNT_RECALL_SLOT, &clp->cl_state)) {
+			section = "recall slot";
+			status = nfs4_recall_slot(clp);
+			if (status < 0)
+				goto out_error;
+			continue;
+		}
+
 		/* First recover reboot state... */
 		if (test_bit(NFS4CLNT_RECLAIM_REBOOT, &clp->cl_state)) {
+			section = "reclaim reboot";
 			status = nfs4_do_reclaim(clp,
 				clp->cl_mvops->reboot_recovery_ops);
 			if (test_bit(NFS4CLNT_LEASE_EXPIRED, &clp->cl_state) ||
@@ -1930,6 +1977,7 @@ static void nfs4_state_manager(struct nfs_client *clp)
 
 		/* Now recover expired state... */
 		if (test_and_clear_bit(NFS4CLNT_RECLAIM_NOGRACE, &clp->cl_state)) {
+			section = "reclaim nograce";
 			status = nfs4_do_reclaim(clp,
 				clp->cl_mvops->nograce_recovery_ops);
 			if (test_bit(NFS4CLNT_LEASE_EXPIRED, &clp->cl_state) ||
@@ -1945,15 +1993,6 @@ static void nfs4_state_manager(struct nfs_client *clp)
 			nfs_client_return_marked_delegations(clp);
 			continue;
 		}
-		/* Recall session slots */
-		if (test_and_clear_bit(NFS4CLNT_RECALL_SLOT, &clp->cl_state)
-		   && nfs4_has_session(clp)) {
-			status = nfs4_recall_slot(clp);
-			if (status < 0)
-				goto out_error;
-			continue;
-		}
-
 
 		nfs4_clear_state_manager_bit(clp);
 		/* Did we race with an attempt to give us more work? */
@@ -1964,8 +2003,11 @@ static void nfs4_state_manager(struct nfs_client *clp)
 	} while (atomic_read(&clp->cl_count) > 1);
 	return;
 out_error:
-	pr_warn_ratelimited("NFS: state manager failed on NFSv4 server %s"
-			" with error %d\n", clp->cl_hostname, -status);
+	if (strlen(section))
+		section_sep = ": ";
+	pr_warn_ratelimited("NFS: state manager%s%s failed on NFSv4 server %s"
+			" with error %d\n", section_sep, section,
+			clp->cl_hostname, -status);
 	nfs4_end_drain_session(clp);
 	nfs4_clear_state_manager_bit(clp);
 }

fs/nfs/nfs4super.c

@@ -0,0 +1,360 @@
+/*
+ * Copyright (c) 2012 Bryan Schumaker <bjschuma@netapp.com>
+ */
+#include <linux/init.h>
+#include <linux/module.h>
+#include <linux/nfs_idmap.h>
+#include <linux/nfs4_mount.h>
+#include <linux/nfs_fs.h>
+#include "internal.h"
+#include "nfs4_fs.h"
+
+#define NFSDBG_FACILITY		NFSDBG_VFS
+
+static struct dentry *nfs4_remote_mount(struct file_system_type *fs_type,
+	int flags, const char *dev_name, void *raw_data);
+static struct dentry *nfs4_xdev_mount(struct file_system_type *fs_type,
+	int flags, const char *dev_name, void *raw_data);
+static struct dentry *nfs4_referral_mount(struct file_system_type *fs_type,
+	int flags, const char *dev_name, void *raw_data);
+static struct dentry *nfs4_remote_referral_mount(struct file_system_type *fs_type,
+	int flags, const char *dev_name, void *raw_data);
+
+static struct file_system_type nfs4_fs_type = {
+	.owner		= THIS_MODULE,
+	.name		= "nfs4",
+	.mount		= nfs_fs_mount,
+	.kill_sb	= nfs_kill_super,
+	.fs_flags	= FS_RENAME_DOES_D_MOVE|FS_REVAL_DOT|FS_BINARY_MOUNTDATA,
+};
+
+static struct file_system_type nfs4_remote_fs_type = {
+	.owner		= THIS_MODULE,
+	.name		= "nfs4",
+	.mount		= nfs4_remote_mount,
+	.kill_sb	= nfs_kill_super,
+	.fs_flags	= FS_RENAME_DOES_D_MOVE|FS_REVAL_DOT|FS_BINARY_MOUNTDATA,
+};
+
+struct file_system_type nfs4_xdev_fs_type = {
+	.owner		= THIS_MODULE,
+	.name		= "nfs4",
+	.mount		= nfs4_xdev_mount,
+	.kill_sb	= nfs_kill_super,
+	.fs_flags	= FS_RENAME_DOES_D_MOVE|FS_REVAL_DOT|FS_BINARY_MOUNTDATA,
+};
+
+static struct file_system_type nfs4_remote_referral_fs_type = {
+	.owner		= THIS_MODULE,
+	.name		= "nfs4",
+	.mount		= nfs4_remote_referral_mount,
+	.kill_sb	= nfs_kill_super,
+	.fs_flags	= FS_RENAME_DOES_D_MOVE|FS_REVAL_DOT|FS_BINARY_MOUNTDATA,
+};
+
+struct file_system_type nfs4_referral_fs_type = {
+	.owner		= THIS_MODULE,
+	.name		= "nfs4",
+	.mount		= nfs4_referral_mount,
+	.kill_sb	= nfs_kill_super,
+	.fs_flags	= FS_RENAME_DOES_D_MOVE|FS_REVAL_DOT|FS_BINARY_MOUNTDATA,
+};
+
+static const struct super_operations nfs4_sops = {
+	.alloc_inode	= nfs_alloc_inode,
+	.destroy_inode	= nfs_destroy_inode,
+	.write_inode	= nfs4_write_inode,
+	.put_super	= nfs_put_super,
+	.statfs		= nfs_statfs,
+	.evict_inode	= nfs4_evict_inode,
+	.umount_begin	= nfs_umount_begin,
+	.show_options	= nfs_show_options,
+	.show_devname	= nfs_show_devname,
+	.show_path	= nfs_show_path,
+	.show_stats	= nfs_show_stats,
+	.remount_fs	= nfs_remount,
+};
+
+/*
+ * Set up an NFS4 superblock
+ */
+static void nfs4_fill_super(struct super_block *sb,
+			    struct nfs_mount_info *mount_info)
+{
+	sb->s_time_gran = 1;
+	sb->s_op = &nfs4_sops;
+	/*
+	 * The VFS shouldn't apply the umask to mode bits. We will do
+	 * so ourselves when necessary.
+	 */
+	sb->s_flags  |= MS_POSIXACL;
+	sb->s_xattr = nfs4_xattr_handlers;
+	nfs_initialise_sb(sb);
+}
+
+/*
+ * Get the superblock for the NFS4 root partition
+ */
+static struct dentry *
+nfs4_remote_mount(struct file_system_type *fs_type, int flags,
+		  const char *dev_name, void *info)
+{
+	struct nfs_mount_info *mount_info = info;
+	struct nfs_server *server;
+	struct dentry *mntroot = ERR_PTR(-ENOMEM);
+
+	mount_info->fill_super = nfs4_fill_super;
+	mount_info->set_security = nfs_set_sb_security;
+
+	/* Get a volume representation */
+	server = nfs4_create_server(mount_info->parsed, mount_info->mntfh);
+	if (IS_ERR(server)) {
+		mntroot = ERR_CAST(server);
+		goto out;
+	}
+
+	mntroot = nfs_fs_mount_common(fs_type, server, flags, dev_name, mount_info);
+
+out:
+	return mntroot;
+}
+
+static struct vfsmount *nfs_do_root_mount(struct file_system_type *fs_type,
+		int flags, void *data, const char *hostname)
+{
+	struct vfsmount *root_mnt;
+	char *root_devname;
+	size_t len;
+
+	len = strlen(hostname) + 5;
+	root_devname = kmalloc(len, GFP_KERNEL);
+	if (root_devname == NULL)
+		return ERR_PTR(-ENOMEM);
+	/* Does hostname needs to be enclosed in brackets? */
+	if (strchr(hostname, ':'))
+		snprintf(root_devname, len, "[%s]:/", hostname);
+	else
+		snprintf(root_devname, len, "%s:/", hostname);
+	root_mnt = vfs_kern_mount(fs_type, flags, root_devname, data);
+	kfree(root_devname);
+	return root_mnt;
+}
+
+struct nfs_referral_count {
+	struct list_head list;
+	const struct task_struct *task;
+	unsigned int referral_count;
+};
+
+static LIST_HEAD(nfs_referral_count_list);
+static DEFINE_SPINLOCK(nfs_referral_count_list_lock);
+
+static struct nfs_referral_count *nfs_find_referral_count(void)
+{
+	struct nfs_referral_count *p;
+
+	list_for_each_entry(p, &nfs_referral_count_list, list) {
+		if (p->task == current)
+			return p;
+	}
+	return NULL;
+}
+
+#define NFS_MAX_NESTED_REFERRALS 2
+
+static int nfs_referral_loop_protect(void)
+{
+	struct nfs_referral_count *p, *new;
+	int ret = -ENOMEM;
+
+	new = kmalloc(sizeof(*new), GFP_KERNEL);
+	if (!new)
+		goto out;
+	new->task = current;
+	new->referral_count = 1;
+
+	ret = 0;
+	spin_lock(&nfs_referral_count_list_lock);
+	p = nfs_find_referral_count();
+	if (p != NULL) {
+		if (p->referral_count >= NFS_MAX_NESTED_REFERRALS)
+			ret = -ELOOP;
+		else
+			p->referral_count++;
+	} else {
+		list_add(&new->list, &nfs_referral_count_list);
+		new = NULL;
+	}
+	spin_unlock(&nfs_referral_count_list_lock);
+	kfree(new);
+out:
+	return ret;
+}
+
+static void nfs_referral_loop_unprotect(void)
+{
+	struct nfs_referral_count *p;
+
+	spin_lock(&nfs_referral_count_list_lock);
+	p = nfs_find_referral_count();
+	p->referral_count--;
+	if (p->referral_count == 0)
+		list_del(&p->list);
+	else
+		p = NULL;
+	spin_unlock(&nfs_referral_count_list_lock);
+	kfree(p);
+}
+
+static struct dentry *nfs_follow_remote_path(struct vfsmount *root_mnt,
+		const char *export_path)
+{
+	struct dentry *dentry;
+	int err;
+
+	if (IS_ERR(root_mnt))
+		return ERR_CAST(root_mnt);
+
+	err = nfs_referral_loop_protect();
+	if (err) {
+		mntput(root_mnt);
+		return ERR_PTR(err);
+	}
+
+	dentry = mount_subtree(root_mnt, export_path);
+	nfs_referral_loop_unprotect();
+
+	return dentry;
+}
+
+struct dentry *nfs4_try_mount(int flags, const char *dev_name,
+			 struct nfs_mount_info *mount_info)
+{
+	char *export_path;
+	struct vfsmount *root_mnt;
+	struct dentry *res;
+	struct nfs_parsed_mount_data *data = mount_info->parsed;
+
+	dfprintk(MOUNT, "--> nfs4_try_mount()\n");
+
+	mount_info->fill_super = nfs4_fill_super;
+
+	export_path = data->nfs_server.export_path;
+	data->nfs_server.export_path = "/";
+	root_mnt = nfs_do_root_mount(&nfs4_remote_fs_type, flags, mount_info,
+			data->nfs_server.hostname);
+	data->nfs_server.export_path = export_path;
+
+	res = nfs_follow_remote_path(root_mnt, export_path);
+
+	dfprintk(MOUNT, "<-- nfs4_try_mount() = %ld%s\n",
+			IS_ERR(res) ? PTR_ERR(res) : 0,
+			IS_ERR(res) ? " [error]" : "");
+	return res;
+}
+
+/*
+ * Clone an NFS4 server record on xdev traversal (FSID-change)
+ */
+static struct dentry *
+nfs4_xdev_mount(struct file_system_type *fs_type, int flags,
+		 const char *dev_name, void *raw_data)
+{
+	struct nfs_mount_info mount_info = {
+		.fill_super = nfs_clone_super,
+		.set_security = nfs_clone_sb_security,
+		.cloned = raw_data,
+	};
+	return nfs_xdev_mount_common(&nfs4_fs_type, flags, dev_name, &mount_info);
+}
+
+static struct dentry *
+nfs4_remote_referral_mount(struct file_system_type *fs_type, int flags,
+			   const char *dev_name, void *raw_data)
+{
+	struct nfs_mount_info mount_info = {
+		.fill_super = nfs4_fill_super,
+		.set_security = nfs_clone_sb_security,
+		.cloned = raw_data,
+	};
+	struct nfs_server *server;
+	struct dentry *mntroot = ERR_PTR(-ENOMEM);
+
+	dprintk("--> nfs4_referral_get_sb()\n");
+
+	mount_info.mntfh = nfs_alloc_fhandle();
+	if (mount_info.cloned == NULL || mount_info.mntfh == NULL)
+		goto out;
+
+	/* create a new volume representation */
+	server = nfs4_create_referral_server(mount_info.cloned, mount_info.mntfh);
+	if (IS_ERR(server)) {
+		mntroot = ERR_CAST(server);
+		goto out;
+	}
+
+	mntroot = nfs_fs_mount_common(&nfs4_fs_type, server, flags, dev_name, &mount_info);
+out:
+	nfs_free_fhandle(mount_info.mntfh);
+	return mntroot;
+}
+
+/*
+ * Create an NFS4 server record on referral traversal
+ */
+static struct dentry *nfs4_referral_mount(struct file_system_type *fs_type,
+		int flags, const char *dev_name, void *raw_data)
+{
+	struct nfs_clone_mount *data = raw_data;
+	char *export_path;
+	struct vfsmount *root_mnt;
+	struct dentry *res;
+
+	dprintk("--> nfs4_referral_mount()\n");
+
+	export_path = data->mnt_path;
+	data->mnt_path = "/";
+
+	root_mnt = nfs_do_root_mount(&nfs4_remote_referral_fs_type,
+			flags, data, data->hostname);
+	data->mnt_path = export_path;
+
+	res = nfs_follow_remote_path(root_mnt, export_path);
+	dprintk("<-- nfs4_referral_mount() = %ld%s\n",
+			IS_ERR(res) ? PTR_ERR(res) : 0,
+			IS_ERR(res) ? " [error]" : "");
+	return res;
+}
+
+
+int __init init_nfs_v4(void)
+{
+	int err;
+
+	err = nfs_idmap_init();
+	if (err)
+		goto out;
+
+	err = nfs4_register_sysctl();
+	if (err)
+		goto out1;
+
+	err = register_filesystem(&nfs4_fs_type);
+	if (err < 0)
+		goto out2;
+
+	return 0;
+out2:
+	nfs4_unregister_sysctl();
+out1:
+	nfs_idmap_quit();
+out:
+	return err;
+}
+
+void exit_nfs_v4(void)
+{
+	unregister_filesystem(&nfs4_fs_type);
+	nfs4_unregister_sysctl();
+	nfs_idmap_quit();
+}

fs/nfs/nfs4sysctl.c

@@ -0,0 +1,68 @@
+/*
+ * linux/fs/nfs/nfs4sysctl.c
+ *
+ * Sysctl interface to NFS v4 parameters
+ *
+ * Copyright (c) 2006 Trond Myklebust <Trond.Myklebust@netapp.com>
+ */
+#include <linux/sysctl.h>
+#include <linux/nfs_idmap.h>
+#include <linux/nfs_fs.h>
+
+#include "callback.h"
+
+static const int nfs_set_port_min = 0;
+static const int nfs_set_port_max = 65535;
+static struct ctl_table_header *nfs4_callback_sysctl_table;
+
+static ctl_table nfs4_cb_sysctls[] = {
+	{
+		.procname = "nfs_callback_tcpport",
+		.data = &nfs_callback_set_tcpport,
+		.maxlen = sizeof(int),
+		.mode = 0644,
+		.proc_handler = proc_dointvec_minmax,
+		.extra1 = (int *)&nfs_set_port_min,
+		.extra2 = (int *)&nfs_set_port_max,
+	},
+	{
+		.procname = "idmap_cache_timeout",
+		.data = &nfs_idmap_cache_timeout,
+		.maxlen = sizeof(int),
+		.mode = 0644,
+		.proc_handler = proc_dointvec_jiffies,
+	},
+	{ }
+};
+
+static ctl_table nfs4_cb_sysctl_dir[] = {
+	{
+		.procname = "nfs",
+		.mode = 0555,
+		.child = nfs4_cb_sysctls,
+	},
+	{ }
+};
+
+static ctl_table nfs4_cb_sysctl_root[] = {
+	{
+		.procname = "fs",
+		.mode = 0555,
+		.child = nfs4_cb_sysctl_dir,
+	},
+	{ }
+};
+
+int nfs4_register_sysctl(void)
+{
+	nfs4_callback_sysctl_table = register_sysctl_table(nfs4_cb_sysctl_root);
+	if (nfs4_callback_sysctl_table == NULL)
+		return -ENOMEM;
+	return 0;
+}
+
+void nfs4_unregister_sysctl(void)
+{
+	unregister_sysctl_table(nfs4_callback_sysctl_table);
+	nfs4_callback_sysctl_table = NULL;
+}

fs/nfs/nfs4xdr.c

@@ -1236,7 +1236,7 @@ static void encode_link(struct xdr_stream *xdr, const struct qstr *name, struct
 
 static inline int nfs4_lock_type(struct file_lock *fl, int block)
 {
-	if ((fl->fl_type & (F_RDLCK|F_WRLCK|F_UNLCK)) == F_RDLCK)
+	if (fl->fl_type == F_RDLCK)
 		return block ? NFS4_READW_LT : NFS4_READ_LT;
 	return block ? NFS4_WRITEW_LT : NFS4_WRITE_LT;
 }
@@ -3078,7 +3078,7 @@ out_overflow:
 	return -EIO;
 }
 
-static inline int decode_attr_length(struct xdr_stream *xdr, uint32_t *attrlen, __be32 **savep)
+static int decode_attr_length(struct xdr_stream *xdr, uint32_t *attrlen, unsigned int *savep)
 {
 	__be32 *p;
 
@@ -3086,7 +3086,7 @@ static inline int decode_attr_length(struct xdr_stream *xdr, uint32_t *attrlen,
 	if (unlikely(!p))
 		goto out_overflow;
 	*attrlen = be32_to_cpup(p);
-	*savep = xdr->p;
+	*savep = xdr_stream_pos(xdr);
 	return 0;
 out_overflow:
 	print_overflow_msg(__func__, xdr);
@@ -4068,10 +4068,10 @@ static int decode_attr_time_modify(struct xdr_stream *xdr, uint32_t *bitmap, str
 	return status;
 }
 
-static int verify_attr_len(struct xdr_stream *xdr, __be32 *savep, uint32_t attrlen)
+static int verify_attr_len(struct xdr_stream *xdr, unsigned int savep, uint32_t attrlen)
 {
 	unsigned int attrwords = XDR_QUADLEN(attrlen);
-	unsigned int nwords = xdr->p - savep;
+	unsigned int nwords = (xdr_stream_pos(xdr) - savep) >> 2;
 
 	if (unlikely(attrwords != nwords)) {
 		dprintk("%s: server returned incorrect attribute length: "
@@ -4158,13 +4158,18 @@ static int decode_verifier(struct xdr_stream *xdr, void *verifier)
 	return decode_opaque_fixed(xdr, verifier, NFS4_VERIFIER_SIZE);
 }
 
+static int decode_write_verifier(struct xdr_stream *xdr, struct nfs_write_verifier *verifier)
+{
+	return decode_opaque_fixed(xdr, verifier->data, NFS4_VERIFIER_SIZE);
+}
+
 static int decode_commit(struct xdr_stream *xdr, struct nfs_commitres *res)
 {
 	int status;
 
 	status = decode_op_hdr(xdr, OP_COMMIT);
 	if (!status)
-		status = decode_verifier(xdr, res->verf->verifier);
+		status = decode_write_verifier(xdr, &res->verf->verifier);
 	return status;
 }
 
@@ -4193,7 +4198,7 @@ out_overflow:
 
 static int decode_server_caps(struct xdr_stream *xdr, struct nfs4_server_caps_res *res)
 {
-	__be32 *savep;
+	unsigned int savep;
 	uint32_t attrlen, bitmap[3] = {0};
 	int status;
 
@@ -4222,7 +4227,7 @@ xdr_error:
 
 static int decode_statfs(struct xdr_stream *xdr, struct nfs_fsstat *fsstat)
 {
-	__be32 *savep;
+	unsigned int savep;
 	uint32_t attrlen, bitmap[3] = {0};
 	int status;
 
@@ -4254,7 +4259,7 @@ xdr_error:
 
 static int decode_pathconf(struct xdr_stream *xdr, struct nfs_pathconf *pathconf)
 {
-	__be32 *savep;
+	unsigned int savep;
 	uint32_t attrlen, bitmap[3] = {0};
 	int status;
 
@@ -4299,7 +4304,8 @@ out_overflow:
 static int decode_first_threshold_item4(struct xdr_stream *xdr,
 					struct nfs4_threshold *res)
 {
-	__be32 *p, *savep;
+	__be32 *p;
+	unsigned int savep;
 	uint32_t bitmap[3] = {0,}, attrlen;
 	int status;
 
@@ -4503,7 +4509,7 @@ static int decode_getfattr_generic(struct xdr_stream *xdr, struct nfs_fattr *fat
 		struct nfs_fh *fh, struct nfs4_fs_locations *fs_loc,
 		const struct nfs_server *server)
 {
-	__be32 *savep;
+	unsigned int savep;
 	uint32_t attrlen,
 		 bitmap[3] = {0};
 	int status;
@@ -4615,7 +4621,7 @@ static int decode_attr_layout_blksize(struct xdr_stream *xdr, uint32_t *bitmap,
 
 static int decode_fsinfo(struct xdr_stream *xdr, struct nfs_fsinfo *fsinfo)
 {
-	__be32 *savep;
+	unsigned int savep;
 	uint32_t attrlen, bitmap[3];
 	int status;
 
@@ -4920,9 +4926,8 @@ static int decode_putrootfh(struct xdr_stream *xdr)
 
 static int decode_read(struct xdr_stream *xdr, struct rpc_rqst *req, struct nfs_readres *res)
 {
-	struct kvec *iov = req->rq_rcv_buf.head;
 	__be32 *p;
-	uint32_t count, eof, recvd, hdrlen;
+	uint32_t count, eof, recvd;
 	int status;
 
 	status = decode_op_hdr(xdr, OP_READ);
@@ -4933,15 +4938,13 @@ static int decode_read(struct xdr_stream *xdr, struct rpc_rqst *req, struct nfs_
 		goto out_overflow;
 	eof = be32_to_cpup(p++);
 	count = be32_to_cpup(p);
-	hdrlen = (u8 *) xdr->p - (u8 *) iov->iov_base;
-	recvd = req->rq_rcv_buf.len - hdrlen;
+	recvd = xdr_read_pages(xdr, count);
 	if (count > recvd) {
 		dprintk("NFS: server cheating in read reply: "
 				"count %u > recvd %u\n", count, recvd);
 		count = recvd;
 		eof = 0;
 	}
-	xdr_read_pages(xdr, count);
 	res->eof = eof;
 	res->count = count;
 	return 0;
@@ -4952,10 +4955,6 @@ out_overflow:
 
 static int decode_readdir(struct xdr_stream *xdr, struct rpc_rqst *req, struct nfs4_readdir_res *readdir)
 {
-	struct xdr_buf	*rcvbuf = &req->rq_rcv_buf;
-	struct kvec	*iov = rcvbuf->head;
-	size_t		hdrlen;
-	u32		recvd, pglen = rcvbuf->page_len;
 	int		status;
 	__be32		verf[2];
 
@@ -4967,22 +4966,12 @@ static int decode_readdir(struct xdr_stream *xdr, struct rpc_rqst *req, struct n
 	memcpy(verf, readdir->verifier.data, sizeof(verf));
 	dprintk("%s: verifier = %08x:%08x\n",
 			__func__, verf[0], verf[1]);
-
-	hdrlen = (char *) xdr->p - (char *) iov->iov_base;
-	recvd = rcvbuf->len - hdrlen;
-	if (pglen > recvd)
-		pglen = recvd;
-	xdr_read_pages(xdr, pglen);
-
-
-	return pglen;
+	return xdr_read_pages(xdr, xdr->buf->page_len);
 }
 
 static int decode_readlink(struct xdr_stream *xdr, struct rpc_rqst *req)
 {
 	struct xdr_buf *rcvbuf = &req->rq_rcv_buf;
-	struct kvec *iov = rcvbuf->head;
-	size_t hdrlen;
 	u32 len, recvd;
 	__be32 *p;
 	int status;
@@ -5000,14 +4989,12 @@ static int decode_readlink(struct xdr_stream *xdr, struct rpc_rqst *req)
 		dprintk("nfs: server returned giant symlink!\n");
 		return -ENAMETOOLONG;
 	}
-	hdrlen = (char *) xdr->p - (char *) iov->iov_base;
-	recvd = req->rq_rcv_buf.len - hdrlen;
+	recvd = xdr_read_pages(xdr, len);
 	if (recvd < len) {
 		dprintk("NFS: server cheating in readlink reply: "
 				"count %u > recvd %u\n", len, recvd);
 		return -EIO;
 	}
-	xdr_read_pages(xdr, len);
 	/*
 	 * The XDR encode routine has set things up so that
 	 * the link text will be copied directly into the
@@ -5063,10 +5050,10 @@ decode_restorefh(struct xdr_stream *xdr)
 static int decode_getacl(struct xdr_stream *xdr, struct rpc_rqst *req,
 			 struct nfs_getaclres *res)
 {
-	__be32 *savep, *bm_p;
+	unsigned int savep;
+	__be32 *bm_p;
 	uint32_t attrlen,
 		 bitmap[3] = {0};
-	struct kvec *iov = req->rq_rcv_buf.head;
 	int status;
 	size_t page_len = xdr->buf->page_len;
 
@@ -5089,7 +5076,6 @@ static int decode_getacl(struct xdr_stream *xdr, struct rpc_rqst *req,
 	if (unlikely(bitmap[0] & (FATTR4_WORD0_ACL - 1U)))
 		return -EIO;
 	if (likely(bitmap[0] & FATTR4_WORD0_ACL)) {
-		size_t hdrlen;
 
 		/* The bitmap (xdr len + bitmaps) and the attr xdr len words
 		 * are stored with the acl data to handle the problem of
@@ -5098,7 +5084,6 @@ static int decode_getacl(struct xdr_stream *xdr, struct rpc_rqst *req,
 
 		/* We ignore &savep and don't do consistency checks on
 		 * the attr length.  Let userspace figure it out.... */
-		hdrlen = (u8 *)xdr->p - (u8 *)iov->iov_base;
 		attrlen += res->acl_data_offset;
 		if (attrlen > page_len) {
 			if (res->acl_flags & NFS4_ACL_LEN_REQUEST) {
@@ -5212,13 +5197,12 @@ static int decode_write(struct xdr_stream *xdr, struct nfs_writeres *res)
 	if (status)
 		return status;
 
-	p = xdr_inline_decode(xdr, 16);
+	p = xdr_inline_decode(xdr, 8);
 	if (unlikely(!p))
 		goto out_overflow;
 	res->count = be32_to_cpup(p++);
 	res->verf->committed = be32_to_cpup(p++);
-	memcpy(res->verf->verifier, p, NFS4_VERIFIER_SIZE);
-	return 0;
+	return decode_write_verifier(xdr, &res->verf->verifier);
 out_overflow:
 	print_overflow_msg(__func__, xdr);
 	return -EIO;
@@ -5599,7 +5583,7 @@ static int decode_getdevicelist(struct xdr_stream *xdr,
 {
 	__be32 *p;
 	int status, i;
-	struct nfs_writeverf verftemp;
+	nfs4_verifier verftemp;
 
 	status = decode_op_hdr(xdr, OP_GETDEVICELIST);
 	if (status)
@@ -5613,7 +5597,7 @@ static int decode_getdevicelist(struct xdr_stream *xdr,
 	p += 2;
 
 	/* Read verifier */
-	p = xdr_decode_opaque_fixed(p, verftemp.verifier, NFS4_VERIFIER_SIZE);
+	p = xdr_decode_opaque_fixed(p, verftemp.data, NFS4_VERIFIER_SIZE);
 
 	res->num_devs = be32_to_cpup(p);
 
@@ -5707,9 +5691,7 @@ static int decode_layoutget(struct xdr_stream *xdr, struct rpc_rqst *req,
 	__be32 *p;
 	int status;
 	u32 layout_count;
-	struct xdr_buf *rcvbuf = &req->rq_rcv_buf;
-	struct kvec *iov = rcvbuf->head;
-	u32 hdrlen, recvd;
+	u32 recvd;
 
 	status = decode_op_hdr(xdr, OP_LAYOUTGET);
 	if (status)
@@ -5746,8 +5728,7 @@ static int decode_layoutget(struct xdr_stream *xdr, struct rpc_rqst *req,
 		res->type,
 		res->layoutp->len);
 
-	hdrlen = (u8 *) xdr->p - (u8 *) iov->iov_base;
-	recvd = req->rq_rcv_buf.len - hdrlen;
+	recvd = xdr_read_pages(xdr, res->layoutp->len);
 	if (res->layoutp->len > recvd) {
 		dprintk("NFS: server cheating in layoutget reply: "
 				"layout len %u > recvd %u\n",
@@ -5755,8 +5736,6 @@ static int decode_layoutget(struct xdr_stream *xdr, struct rpc_rqst *req,
 		return -EINVAL;
 	}
 
-	xdr_read_pages(xdr, res->layoutp->len);
-
 	if (layout_count > 1) {
 		/* We only handle a length one array at the moment.  Any
 		 * further entries are just ignored.  Note that this means
@@ -7103,6 +7082,7 @@ out:
 int nfs4_decode_dirent(struct xdr_stream *xdr, struct nfs_entry *entry,
 		       int plus)
 {
+	unsigned int savep;
 	uint32_t bitmap[3] = {0};
 	uint32_t len;
 	__be32 *p = xdr_inline_decode(xdr, 4);
@@ -7141,7 +7121,7 @@ int nfs4_decode_dirent(struct xdr_stream *xdr, struct nfs_entry *entry,
 	if (decode_attr_bitmap(xdr, bitmap) < 0)
 		goto out_overflow;
 
-	if (decode_attr_length(xdr, &len, &p) < 0)
+	if (decode_attr_length(xdr, &len, &savep) < 0)
 		goto out_overflow;
 
 	if (decode_getfattr_attrs(xdr, bitmap, entry->fattr, entry->fh,

fs/nfs/pnfs.c

@@ -651,7 +651,14 @@ out_err_free:
 	return NULL;
 }
 
-/* Initiates a LAYOUTRETURN(FILE) */
+/*
+ * Initiates a LAYOUTRETURN(FILE), and removes the pnfs_layout_hdr
+ * when the layout segment list is empty.
+ *
+ * Note that a pnfs_layout_hdr can exist with an empty layout segment
+ * list when LAYOUTGET has failed, or when LAYOUTGET succeeded, but the
+ * deviceid is marked invalid.
+ */
 int
 _pnfs_return_layout(struct inode *ino)
 {
@@ -660,22 +667,31 @@ _pnfs_return_layout(struct inode *ino)
 	LIST_HEAD(tmp_list);
 	struct nfs4_layoutreturn *lrp;
 	nfs4_stateid stateid;
-	int status = 0;
+	int status = 0, empty;
 
-	dprintk("--> %s\n", __func__);
+	dprintk("NFS: %s for inode %lu\n", __func__, ino->i_ino);
 
 	spin_lock(&ino->i_lock);
 	lo = nfsi->layout;
-	if (!lo) {
+	if (!lo || pnfs_test_layout_returned(lo)) {
 		spin_unlock(&ino->i_lock);
-		dprintk("%s: no layout to return\n", __func__);
-		return status;
+		dprintk("NFS: %s no layout to return\n", __func__);
+		goto out;
 	}
 	stateid = nfsi->layout->plh_stateid;
 	/* Reference matched in nfs4_layoutreturn_release */
 	get_layout_hdr(lo);
+	empty = list_empty(&lo->plh_segs);
 	mark_matching_lsegs_invalid(lo, &tmp_list, NULL);
+	/* Don't send a LAYOUTRETURN if list was initially empty */
+	if (empty) {
+		spin_unlock(&ino->i_lock);
+		put_layout_hdr(lo);
+		dprintk("NFS: %s no layout segments to return\n", __func__);
+		goto out;
+	}
 	lo->plh_block_lgets++;
+	pnfs_mark_layout_returned(lo);
 	spin_unlock(&ino->i_lock);
 	pnfs_free_lseg_list(&tmp_list);
 
@@ -686,6 +702,7 @@ _pnfs_return_layout(struct inode *ino)
 		status = -ENOMEM;
 		set_bit(NFS_LAYOUT_RW_FAILED, &lo->plh_flags);
 		set_bit(NFS_LAYOUT_RO_FAILED, &lo->plh_flags);
+		pnfs_clear_layout_returned(lo);
 		put_layout_hdr(lo);
 		goto out;
 	}
@@ -1075,6 +1092,10 @@ pnfs_update_layout(struct inode *ino,
 	get_layout_hdr(lo);
 	if (list_empty(&lo->plh_segs))
 		first = true;
+
+	/* Enable LAYOUTRETURNs */
+	pnfs_clear_layout_returned(lo);
+
 	spin_unlock(&ino->i_lock);
 	if (first) {
 		/* The lo must be on the clp list if there is any
@@ -1209,7 +1230,7 @@ pnfs_generic_pg_init_write(struct nfs_pageio_descriptor *pgio, struct nfs_page *
 }
 EXPORT_SYMBOL_GPL(pnfs_generic_pg_init_write);
 
-bool
+void
 pnfs_pageio_init_read(struct nfs_pageio_descriptor *pgio, struct inode *inode,
 		      const struct nfs_pgio_completion_ops *compl_ops)
 {
@@ -1217,13 +1238,12 @@ pnfs_pageio_init_read(struct nfs_pageio_descriptor *pgio, struct inode *inode,
 	struct pnfs_layoutdriver_type *ld = server->pnfs_curr_ld;
 
 	if (ld == NULL)
-		return false;
-	nfs_pageio_init(pgio, inode, ld->pg_read_ops, compl_ops,
-			server->rsize, 0);
-	return true;
+		nfs_pageio_init_read(pgio, inode, compl_ops);
+	else
+		nfs_pageio_init(pgio, inode, ld->pg_read_ops, compl_ops, server->rsize, 0);
 }
 
-bool
+void
 pnfs_pageio_init_write(struct nfs_pageio_descriptor *pgio, struct inode *inode,
 		       int ioflags,
 		       const struct nfs_pgio_completion_ops *compl_ops)
@@ -1232,10 +1252,9 @@ pnfs_pageio_init_write(struct nfs_pageio_descriptor *pgio, struct inode *inode,
 	struct pnfs_layoutdriver_type *ld = server->pnfs_curr_ld;
 
 	if (ld == NULL)
-		return false;
-	nfs_pageio_init(pgio, inode, ld->pg_write_ops, compl_ops,
-			server->wsize, ioflags);
-	return true;
+		nfs_pageio_init_write(pgio, inode, ioflags, compl_ops);
+	else
+		nfs_pageio_init(pgio, inode, ld->pg_write_ops, compl_ops, server->wsize, ioflags);
 }
 
 bool
@@ -1272,7 +1291,7 @@ int pnfs_write_done_resend_to_mds(struct inode *inode,
 	LIST_HEAD(failed);
 
 	/* Resend all requests through the MDS */
-	nfs_pageio_init_write_mds(&pgio, inode, FLUSH_STABLE, compl_ops);
+	nfs_pageio_init_write(&pgio, inode, FLUSH_STABLE, compl_ops);
 	while (!list_empty(head)) {
 		struct nfs_page *req = nfs_list_entry(head->next);
 
@@ -1427,7 +1446,7 @@ int pnfs_read_done_resend_to_mds(struct inode *inode,
 	LIST_HEAD(failed);
 
 	/* Resend all requests through the MDS */
-	nfs_pageio_init_read_mds(&pgio, inode, compl_ops);
+	nfs_pageio_init_read(&pgio, inode, compl_ops);
 	while (!list_empty(head)) {
 		struct nfs_page *req = nfs_list_entry(head->next);
 

fs/nfs/pnfs.h

@@ -64,6 +64,7 @@ enum {
 	NFS_LAYOUT_ROC,			/* some lseg had roc bit set */
 	NFS_LAYOUT_DESTROYED,		/* no new use of layout allowed */
 	NFS_LAYOUT_INVALID,		/* layout is being destroyed */
+	NFS_LAYOUT_RETURNED,		/* layout has already been returned */
 };
 
 enum layoutdriver_policy_flags {
@@ -178,9 +179,9 @@ extern int nfs4_proc_layoutreturn(struct nfs4_layoutreturn *lrp);
 void get_layout_hdr(struct pnfs_layout_hdr *lo);
 void put_lseg(struct pnfs_layout_segment *lseg);
 
-bool pnfs_pageio_init_read(struct nfs_pageio_descriptor *, struct inode *,
+void pnfs_pageio_init_read(struct nfs_pageio_descriptor *, struct inode *,
 			   const struct nfs_pgio_completion_ops *);
-bool pnfs_pageio_init_write(struct nfs_pageio_descriptor *, struct inode *,
+void pnfs_pageio_init_write(struct nfs_pageio_descriptor *, struct inode *,
 			    int, const struct nfs_pgio_completion_ops *);
 
 void set_pnfs_layoutdriver(struct nfs_server *, const struct nfs_fh *, u32);
@@ -255,6 +256,24 @@ struct nfs4_deviceid_node *nfs4_insert_deviceid_node(struct nfs4_deviceid_node *
 bool nfs4_put_deviceid_node(struct nfs4_deviceid_node *);
 void nfs4_deviceid_purge_client(const struct nfs_client *);
 
+static inline void
+pnfs_mark_layout_returned(struct pnfs_layout_hdr *lo)
+{
+	set_bit(NFS_LAYOUT_RETURNED, &lo->plh_flags);
+}
+
+static inline void
+pnfs_clear_layout_returned(struct pnfs_layout_hdr *lo)
+{
+	clear_bit(NFS_LAYOUT_RETURNED, &lo->plh_flags);
+}
+
+static inline bool
+pnfs_test_layout_returned(struct pnfs_layout_hdr *lo)
+{
+	return test_bit(NFS_LAYOUT_RETURNED, &lo->plh_flags);
+}
+
 static inline int lo_fail_bit(u32 iomode)
 {
 	return iomode == IOMODE_RW ?
@@ -438,16 +457,16 @@ static inline void unset_pnfs_layoutdriver(struct nfs_server *s)
 {
 }
 
-static inline bool pnfs_pageio_init_read(struct nfs_pageio_descriptor *pgio, struct inode *inode,
+static inline void pnfs_pageio_init_read(struct nfs_pageio_descriptor *pgio, struct inode *inode,
 					 const struct nfs_pgio_completion_ops *compl_ops)
 {
-	return false;
+	nfs_pageio_init_read(pgio, inode, compl_ops);
 }
 
-static inline bool pnfs_pageio_init_write(struct nfs_pageio_descriptor *pgio, struct inode *inode, int ioflags,
+static inline void pnfs_pageio_init_write(struct nfs_pageio_descriptor *pgio, struct inode *inode, int ioflags,
 					  const struct nfs_pgio_completion_ops *compl_ops)
 {
-	return false;
+	nfs_pageio_init_write(pgio, inode, ioflags, compl_ops);
 }
 
 static inline int

fs/nfs/proc.c

@@ -734,6 +734,38 @@ out_einval:
 	return -EINVAL;
 }
 
+static int nfs_have_delegation(struct inode *inode, fmode_t flags)
+{
+	return 0;
+}
+
+static int nfs_return_delegation(struct inode *inode)
+{
+	nfs_wb_all(inode);
+	return 0;
+}
+
+static const struct inode_operations nfs_dir_inode_operations = {
+	.create		= nfs_create,
+	.lookup		= nfs_lookup,
+	.link		= nfs_link,
+	.unlink		= nfs_unlink,
+	.symlink	= nfs_symlink,
+	.mkdir		= nfs_mkdir,
+	.rmdir		= nfs_rmdir,
+	.mknod		= nfs_mknod,
+	.rename		= nfs_rename,
+	.permission	= nfs_permission,
+	.getattr	= nfs_getattr,
+	.setattr	= nfs_setattr,
+};
+
+static const struct inode_operations nfs_file_inode_operations = {
+	.permission	= nfs_permission,
+	.getattr	= nfs_getattr,
+	.setattr	= nfs_setattr,
+};
+
 const struct nfs_rpc_ops nfs_v2_clientops = {
 	.version	= 2,		       /* protocol version */
 	.dentry_ops	= &nfs_dentry_operations,
@@ -767,9 +799,11 @@ const struct nfs_rpc_ops nfs_v2_clientops = {
 	.pathconf	= nfs_proc_pathconf,
 	.decode_dirent	= nfs2_decode_dirent,
 	.read_setup	= nfs_proc_read_setup,
+	.read_pageio_init = nfs_pageio_init_read,
 	.read_rpc_prepare = nfs_proc_read_rpc_prepare,
 	.read_done	= nfs_read_done,
 	.write_setup	= nfs_proc_write_setup,
+	.write_pageio_init = nfs_pageio_init_write,
 	.write_rpc_prepare = nfs_proc_write_rpc_prepare,
 	.write_done	= nfs_write_done,
 	.commit_setup	= nfs_proc_commit_setup,
@@ -777,5 +811,9 @@ const struct nfs_rpc_ops nfs_v2_clientops = {
 	.lock		= nfs_proc_lock,
 	.lock_check_bounds = nfs_lock_check_bounds,
 	.close_context	= nfs_close_context,
+	.have_delegation = nfs_have_delegation,
+	.return_delegation = nfs_return_delegation,
+	.alloc_client	= nfs_alloc_client,
 	.init_client	= nfs_init_client,
+	.free_client	= nfs_free_client,
 };

fs/nfs/read.c

@@ -20,8 +20,6 @@
 #include <linux/nfs_page.h>
 #include <linux/module.h>
 
-#include "pnfs.h"
-
 #include "nfs4_fs.h"
 #include "internal.h"
 #include "iostat.h"
@@ -108,7 +106,7 @@ int nfs_return_empty_page(struct page *page)
 	return 0;
 }
 
-void nfs_pageio_init_read_mds(struct nfs_pageio_descriptor *pgio,
+void nfs_pageio_init_read(struct nfs_pageio_descriptor *pgio,
 			      struct inode *inode,
 			      const struct nfs_pgio_completion_ops *compl_ops)
 {
@@ -123,14 +121,6 @@ void nfs_pageio_reset_read_mds(struct nfs_pageio_descriptor *pgio)
 }
 EXPORT_SYMBOL_GPL(nfs_pageio_reset_read_mds);
 
-void nfs_pageio_init_read(struct nfs_pageio_descriptor *pgio,
-			  struct inode *inode,
-			  const struct nfs_pgio_completion_ops *compl_ops)
-{
-	if (!pnfs_pageio_init_read(pgio, inode, compl_ops))
-		nfs_pageio_init_read_mds(pgio, inode, compl_ops);
-}
-
 int nfs_readpage_async(struct nfs_open_context *ctx, struct inode *inode,
 		       struct page *page)
 {
@@ -149,7 +139,7 @@ int nfs_readpage_async(struct nfs_open_context *ctx, struct inode *inode,
 	if (len < PAGE_CACHE_SIZE)
 		zero_user_segment(page, len, PAGE_CACHE_SIZE);
 
-	nfs_pageio_init_read(&pgio, inode, &nfs_async_read_completion_ops);
+	NFS_PROTO(inode)->read_pageio_init(&pgio, inode, &nfs_async_read_completion_ops);
 	nfs_pageio_add_request(&pgio, new);
 	nfs_pageio_complete(&pgio);
 	NFS_I(inode)->read_io += pgio.pg_bytes_written;
@@ -652,7 +642,7 @@ int nfs_readpages(struct file *filp, struct address_space *mapping,
 	if (ret == 0)
 		goto read_complete; /* all pages were read */
 
-	nfs_pageio_init_read(&pgio, inode, &nfs_async_read_completion_ops);
+	NFS_PROTO(inode)->read_pageio_init(&pgio, inode, &nfs_async_read_completion_ops);
 
 	ret = read_cache_pages(mapping, pages, readpage_async_filler, &desc);
 

fs/nfs/super.c

@@ -278,29 +278,8 @@ static match_table_t nfs_vers_tokens = {
 	{ Opt_vers_err, NULL }
 };
 
-struct nfs_mount_info {
-	void (*fill_super)(struct super_block *, struct nfs_mount_info *);
-	int (*set_security)(struct super_block *, struct dentry *, struct nfs_mount_info *);
-	struct nfs_parsed_mount_data *parsed;
-	struct nfs_clone_mount *cloned;
-	struct nfs_fh *mntfh;
-};
-
-static void nfs_umount_begin(struct super_block *);
-static int  nfs_statfs(struct dentry *, struct kstatfs *);
-static int  nfs_show_options(struct seq_file *, struct dentry *);
-static int  nfs_show_devname(struct seq_file *, struct dentry *);
-static int  nfs_show_path(struct seq_file *, struct dentry *);
-static int  nfs_show_stats(struct seq_file *, struct dentry *);
-static struct dentry *nfs_fs_mount_common(struct file_system_type *,
-		struct nfs_server *, int, const char *, struct nfs_mount_info *);
-static struct dentry *nfs_fs_mount(struct file_system_type *,
-		int, const char *, void *);
 static struct dentry *nfs_xdev_mount(struct file_system_type *fs_type,
 		int flags, const char *dev_name, void *raw_data);
-static void nfs_put_super(struct super_block *);
-static void nfs_kill_super(struct super_block *);
-static int nfs_remount(struct super_block *sb, int *flags, char *raw_data);
 
 static struct file_system_type nfs_fs_type = {
 	.owner		= THIS_MODULE,
@@ -337,72 +316,6 @@ static const struct super_operations nfs_sops = {
 static void nfs4_validate_mount_flags(struct nfs_parsed_mount_data *);
 static int nfs4_validate_mount_data(void *options,
 	struct nfs_parsed_mount_data *args, const char *dev_name);
-static struct dentry *nfs4_try_mount(int flags, const char *dev_name,
-	struct nfs_mount_info *mount_info);
-static struct dentry *nfs4_remote_mount(struct file_system_type *fs_type,
-	int flags, const char *dev_name, void *raw_data);
-static struct dentry *nfs4_xdev_mount(struct file_system_type *fs_type,
-	int flags, const char *dev_name, void *raw_data);
-static struct dentry *nfs4_referral_mount(struct file_system_type *fs_type,
-	int flags, const char *dev_name, void *raw_data);
-static struct dentry *nfs4_remote_referral_mount(struct file_system_type *fs_type,
-	int flags, const char *dev_name, void *raw_data);
-static void nfs4_kill_super(struct super_block *sb);
-
-static struct file_system_type nfs4_fs_type = {
-	.owner		= THIS_MODULE,
-	.name		= "nfs4",
-	.mount		= nfs_fs_mount,
-	.kill_sb	= nfs4_kill_super,
-	.fs_flags	= FS_RENAME_DOES_D_MOVE|FS_REVAL_DOT|FS_BINARY_MOUNTDATA,
-};
-
-static struct file_system_type nfs4_remote_fs_type = {
-	.owner		= THIS_MODULE,
-	.name		= "nfs4",
-	.mount		= nfs4_remote_mount,
-	.kill_sb	= nfs4_kill_super,
-	.fs_flags	= FS_RENAME_DOES_D_MOVE|FS_REVAL_DOT|FS_BINARY_MOUNTDATA,
-};
-
-struct file_system_type nfs4_xdev_fs_type = {
-	.owner		= THIS_MODULE,
-	.name		= "nfs4",
-	.mount		= nfs4_xdev_mount,
-	.kill_sb	= nfs4_kill_super,
-	.fs_flags	= FS_RENAME_DOES_D_MOVE|FS_REVAL_DOT|FS_BINARY_MOUNTDATA,
-};
-
-static struct file_system_type nfs4_remote_referral_fs_type = {
-	.owner		= THIS_MODULE,
-	.name		= "nfs4",
-	.mount		= nfs4_remote_referral_mount,
-	.kill_sb	= nfs4_kill_super,
-	.fs_flags	= FS_RENAME_DOES_D_MOVE|FS_REVAL_DOT|FS_BINARY_MOUNTDATA,
-};
-
-struct file_system_type nfs4_referral_fs_type = {
-	.owner		= THIS_MODULE,
-	.name		= "nfs4",
-	.mount		= nfs4_referral_mount,
-	.kill_sb	= nfs4_kill_super,
-	.fs_flags	= FS_RENAME_DOES_D_MOVE|FS_REVAL_DOT|FS_BINARY_MOUNTDATA,
-};
-
-static const struct super_operations nfs4_sops = {
-	.alloc_inode	= nfs_alloc_inode,
-	.destroy_inode	= nfs_destroy_inode,
-	.write_inode	= nfs_write_inode,
-	.put_super	= nfs_put_super,
-	.statfs		= nfs_statfs,
-	.evict_inode	= nfs4_evict_inode,
-	.umount_begin	= nfs_umount_begin,
-	.show_options	= nfs_show_options,
-	.show_devname	= nfs_show_devname,
-	.show_path	= nfs_show_path,
-	.show_stats	= nfs_show_stats,
-	.remount_fs	= nfs_remount,
-};
 #endif
 
 static struct shrinker acl_shrinker = {
@@ -424,18 +337,9 @@ int __init register_nfs_fs(void)
 	ret = nfs_register_sysctl();
 	if (ret < 0)
 		goto error_1;
-#ifdef CONFIG_NFS_V4
-	ret = register_filesystem(&nfs4_fs_type);
-	if (ret < 0)
-		goto error_2;
-#endif
 	register_shrinker(&acl_shrinker);
 	return 0;
 
-#ifdef CONFIG_NFS_V4
-error_2:
-	nfs_unregister_sysctl();
-#endif
 error_1:
 	unregister_filesystem(&nfs_fs_type);
 error_0:
@@ -448,9 +352,6 @@ error_0:
 void __exit unregister_nfs_fs(void)
 {
 	unregister_shrinker(&acl_shrinker);
-#ifdef CONFIG_NFS_V4
-	unregister_filesystem(&nfs4_fs_type);
-#endif
 	nfs_unregister_sysctl();
 	unregister_filesystem(&nfs_fs_type);
 }
@@ -474,7 +375,7 @@ void nfs_sb_deactive(struct super_block *sb)
 /*
  * Deliver file system statistics to userspace
  */
-static int nfs_statfs(struct dentry *dentry, struct kstatfs *buf)
+int nfs_statfs(struct dentry *dentry, struct kstatfs *buf)
 {
 	struct nfs_server *server = NFS_SB(dentry->d_sb);
 	unsigned char blockbits;
@@ -757,7 +658,7 @@ static void nfs_show_mount_options(struct seq_file *m, struct nfs_server *nfss,
 /*
  * Describe the mount options on this VFS mountpoint
  */
-static int nfs_show_options(struct seq_file *m, struct dentry *root)
+int nfs_show_options(struct seq_file *m, struct dentry *root)
 {
 	struct nfs_server *nfss = NFS_SB(root->d_sb);
 
@@ -815,7 +716,7 @@ static void show_implementation_id(struct seq_file *m, struct nfs_server *nfss)
 }
 #endif
 
-static int nfs_show_devname(struct seq_file *m, struct dentry *root)
+int nfs_show_devname(struct seq_file *m, struct dentry *root)
 {
 	char *page = (char *) __get_free_page(GFP_KERNEL);
 	char *devname, *dummy;
@@ -831,7 +732,7 @@ static int nfs_show_devname(struct seq_file *m, struct dentry *root)
 	return err;
 }
 
-static int nfs_show_path(struct seq_file *m, struct dentry *dentry)
+int nfs_show_path(struct seq_file *m, struct dentry *dentry)
 {
 	seq_puts(m, "/");
 	return 0;
@@ -840,7 +741,7 @@ static int nfs_show_path(struct seq_file *m, struct dentry *dentry)
 /*
  * Present statistical information for this VFS mountpoint
  */
-static int nfs_show_stats(struct seq_file *m, struct dentry *root)
+int nfs_show_stats(struct seq_file *m, struct dentry *root)
 {
 	int i, cpu;
 	struct nfs_server *nfss = NFS_SB(root->d_sb);
@@ -933,7 +834,7 @@ static int nfs_show_stats(struct seq_file *m, struct dentry *root)
  * Begin unmount by attempting to remove all automounted mountpoints we added
  * in response to xdev traversals and referrals
  */
-static void nfs_umount_begin(struct super_block *sb)
+void nfs_umount_begin(struct super_block *sb)
 {
 	struct nfs_server *server;
 	struct rpc_clnt *rpc;
@@ -2108,7 +2009,7 @@ nfs_compare_remount_data(struct nfs_server *nfss,
 	return 0;
 }
 
-static int
+int
 nfs_remount(struct super_block *sb, int *flags, char *raw_data)
 {
 	int error;
@@ -2173,7 +2074,7 @@ out:
 /*
  * Initialise the common bits of the superblock
  */
-static inline void nfs_initialise_sb(struct super_block *sb)
+inline void nfs_initialise_sb(struct super_block *sb)
 {
 	struct nfs_server *server = NFS_SB(sb);
 
@@ -2195,8 +2096,7 @@ static inline void nfs_initialise_sb(struct super_block *sb)
 /*
  * Finish setting up an NFS2/3 superblock
  */
-static void nfs_fill_super(struct super_block *sb,
-			   struct nfs_mount_info *mount_info)
+void nfs_fill_super(struct super_block *sb, struct nfs_mount_info *mount_info)
 {
 	struct nfs_parsed_mount_data *data = mount_info->parsed;
 	struct nfs_server *server = NFS_SB(sb);
@@ -2219,10 +2119,9 @@ static void nfs_fill_super(struct super_block *sb,
 }
 
 /*
- * Finish setting up a cloned NFS2/3 superblock
+ * Finish setting up a cloned NFS2/3/4 superblock
  */
-static void nfs_clone_super(struct super_block *sb,
-			    struct nfs_mount_info *mount_info)
+void nfs_clone_super(struct super_block *sb, struct nfs_mount_info *mount_info)
 {
 	const struct super_block *old_sb = mount_info->cloned->sb;
 	struct nfs_server *server = NFS_SB(sb);
@@ -2230,16 +2129,17 @@ static void nfs_clone_super(struct super_block *sb,
 	sb->s_blocksize_bits = old_sb->s_blocksize_bits;
 	sb->s_blocksize = old_sb->s_blocksize;
 	sb->s_maxbytes = old_sb->s_maxbytes;
+	sb->s_xattr = old_sb->s_xattr;
+	sb->s_op = old_sb->s_op;
+	sb->s_time_gran = 1;
 
-	if (server->nfs_client->rpc_ops->version == 3) {
+	if (server->nfs_client->rpc_ops->version != 2) {
 		/* The VFS shouldn't apply the umask to mode bits. We will do
 		 * so ourselves when necessary.
 		 */
 		sb->s_flags |= MS_POSIXACL;
-		sb->s_time_gran = 1;
 	}
 
-	sb->s_op = old_sb->s_op;
  	nfs_initialise_sb(sb);
 }
 
@@ -2381,14 +2281,14 @@ static int nfs_bdi_register(struct nfs_server *server)
 	return bdi_register_dev(&server->backing_dev_info, server->s_dev);
 }
 
-static int nfs_set_sb_security(struct super_block *s, struct dentry *mntroot,
-			       struct nfs_mount_info *mount_info)
+int nfs_set_sb_security(struct super_block *s, struct dentry *mntroot,
+			struct nfs_mount_info *mount_info)
 {
 	return security_sb_set_mnt_opts(s, &mount_info->parsed->lsm_opts);
 }
 
-static int nfs_clone_sb_security(struct super_block *s, struct dentry *mntroot,
-				 struct nfs_mount_info *mount_info)
+int nfs_clone_sb_security(struct super_block *s, struct dentry *mntroot,
+			  struct nfs_mount_info *mount_info)
 {
 	/* clone any lsm security options from the parent to the new sb */
 	security_sb_clone_mnt_opts(mount_info->cloned->sb, s);
@@ -2397,10 +2297,10 @@ static int nfs_clone_sb_security(struct super_block *s, struct dentry *mntroot,
 	return 0;
 }
 
-static struct dentry *nfs_fs_mount_common(struct file_system_type *fs_type,
-					  struct nfs_server *server,
-					  int flags, const char *dev_name,
-					  struct nfs_mount_info *mount_info)
+struct dentry *nfs_fs_mount_common(struct file_system_type *fs_type,
+				   struct nfs_server *server,
+				   int flags, const char *dev_name,
+				   struct nfs_mount_info *mount_info)
 {
 	struct super_block *s;
 	struct dentry *mntroot = ERR_PTR(-ENOMEM);
@@ -2470,7 +2370,7 @@ error_splat_bdi:
 	goto out;
 }
 
-static struct dentry *nfs_fs_mount(struct file_system_type *fs_type,
+struct dentry *nfs_fs_mount(struct file_system_type *fs_type,
 	int flags, const char *dev_name, void *raw_data)
 {
 	struct nfs_mount_info mount_info = {
@@ -2511,7 +2411,7 @@ out:
  * Ensure that we unregister the bdi before kill_anon_super
  * releases the device name
  */
-static void nfs_put_super(struct super_block *s)
+void nfs_put_super(struct super_block *s)
 {
 	struct nfs_server *server = NFS_SB(s);
 
@@ -2521,7 +2421,7 @@ static void nfs_put_super(struct super_block *s)
 /*
  * Destroy an NFS2/3 superblock
  */
-static void nfs_kill_super(struct super_block *s)
+void nfs_kill_super(struct super_block *s)
 {
 	struct nfs_server *server = NFS_SB(s);
 
@@ -2533,7 +2433,7 @@ static void nfs_kill_super(struct super_block *s)
 /*
  * Clone an NFS2/3/4 server record on xdev traversal (FSID-change)
  */
-static struct dentry *
+struct dentry *
 nfs_xdev_mount_common(struct file_system_type *fs_type, int flags,
 		const char *dev_name, struct nfs_mount_info *mount_info)
 {
@@ -2580,44 +2480,6 @@ nfs_xdev_mount(struct file_system_type *fs_type, int flags,
 
 #ifdef CONFIG_NFS_V4
 
-/*
- * Finish setting up a cloned NFS4 superblock
- */
-static void nfs4_clone_super(struct super_block *sb,
-			     struct nfs_mount_info *mount_info)
-{
-	const struct super_block *old_sb = mount_info->cloned->sb;
-	sb->s_blocksize_bits = old_sb->s_blocksize_bits;
-	sb->s_blocksize = old_sb->s_blocksize;
-	sb->s_maxbytes = old_sb->s_maxbytes;
-	sb->s_time_gran = 1;
-	sb->s_op = old_sb->s_op;
-	/*
-	 * The VFS shouldn't apply the umask to mode bits. We will do
-	 * so ourselves when necessary.
-	 */
-	sb->s_flags  |= MS_POSIXACL;
-	sb->s_xattr  = old_sb->s_xattr;
-	nfs_initialise_sb(sb);
-}
-
-/*
- * Set up an NFS4 superblock
- */
-static void nfs4_fill_super(struct super_block *sb,
-			    struct nfs_mount_info *mount_info)
-{
-	sb->s_time_gran = 1;
-	sb->s_op = &nfs4_sops;
-	/*
-	 * The VFS shouldn't apply the umask to mode bits. We will do
-	 * so ourselves when necessary.
-	 */
-	sb->s_flags  |= MS_POSIXACL;
-	sb->s_xattr = nfs4_xattr_handlers;
-	nfs_initialise_sb(sb);
-}
-
 static void nfs4_validate_mount_flags(struct nfs_parsed_mount_data *args)
 {
 	args->flags &= ~(NFS_MOUNT_NONLM|NFS_MOUNT_NOACL|NFS_MOUNT_VER3|
@@ -2715,250 +2577,4 @@ out_no_address:
 	return -EINVAL;
 }
 
-/*
- * Get the superblock for the NFS4 root partition
- */
-static struct dentry *
-nfs4_remote_mount(struct file_system_type *fs_type, int flags,
-		  const char *dev_name, void *info)
-{
-	struct nfs_mount_info *mount_info = info;
-	struct nfs_server *server;
-	struct dentry *mntroot = ERR_PTR(-ENOMEM);
-
-	mount_info->fill_super = nfs4_fill_super;
-	mount_info->set_security = nfs_set_sb_security;
-
-	/* Get a volume representation */
-	server = nfs4_create_server(mount_info->parsed, mount_info->mntfh);
-	if (IS_ERR(server)) {
-		mntroot = ERR_CAST(server);
-		goto out;
-	}
-
-	mntroot = nfs_fs_mount_common(fs_type, server, flags, dev_name, mount_info);
-
-out:
-	return mntroot;
-}
-
-static struct vfsmount *nfs_do_root_mount(struct file_system_type *fs_type,
-		int flags, void *data, const char *hostname)
-{
-	struct vfsmount *root_mnt;
-	char *root_devname;
-	size_t len;
-
-	len = strlen(hostname) + 5;
-	root_devname = kmalloc(len, GFP_KERNEL);
-	if (root_devname == NULL)
-		return ERR_PTR(-ENOMEM);
-	/* Does hostname needs to be enclosed in brackets? */
-	if (strchr(hostname, ':'))
-		snprintf(root_devname, len, "[%s]:/", hostname);
-	else
-		snprintf(root_devname, len, "%s:/", hostname);
-	root_mnt = vfs_kern_mount(fs_type, flags, root_devname, data);
-	kfree(root_devname);
-	return root_mnt;
-}
-
-struct nfs_referral_count {
-	struct list_head list;
-	const struct task_struct *task;
-	unsigned int referral_count;
-};
-
-static LIST_HEAD(nfs_referral_count_list);
-static DEFINE_SPINLOCK(nfs_referral_count_list_lock);
-
-static struct nfs_referral_count *nfs_find_referral_count(void)
-{
-	struct nfs_referral_count *p;
-
-	list_for_each_entry(p, &nfs_referral_count_list, list) {
-		if (p->task == current)
-			return p;
-	}
-	return NULL;
-}
-
-#define NFS_MAX_NESTED_REFERRALS 2
-
-static int nfs_referral_loop_protect(void)
-{
-	struct nfs_referral_count *p, *new;
-	int ret = -ENOMEM;
-
-	new = kmalloc(sizeof(*new), GFP_KERNEL);
-	if (!new)
-		goto out;
-	new->task = current;
-	new->referral_count = 1;
-
-	ret = 0;
-	spin_lock(&nfs_referral_count_list_lock);
-	p = nfs_find_referral_count();
-	if (p != NULL) {
-		if (p->referral_count >= NFS_MAX_NESTED_REFERRALS)
-			ret = -ELOOP;
-		else
-			p->referral_count++;
-	} else {
-		list_add(&new->list, &nfs_referral_count_list);
-		new = NULL;
-	}
-	spin_unlock(&nfs_referral_count_list_lock);
-	kfree(new);
-out:
-	return ret;
-}
-
-static void nfs_referral_loop_unprotect(void)
-{
-	struct nfs_referral_count *p;
-
-	spin_lock(&nfs_referral_count_list_lock);
-	p = nfs_find_referral_count();
-	p->referral_count--;
-	if (p->referral_count == 0)
-		list_del(&p->list);
-	else
-		p = NULL;
-	spin_unlock(&nfs_referral_count_list_lock);
-	kfree(p);
-}
-
-static struct dentry *nfs_follow_remote_path(struct vfsmount *root_mnt,
-		const char *export_path)
-{
-	struct dentry *dentry;
-	int err;
-
-	if (IS_ERR(root_mnt))
-		return ERR_CAST(root_mnt);
-
-	err = nfs_referral_loop_protect();
-	if (err) {
-		mntput(root_mnt);
-		return ERR_PTR(err);
-	}
-
-	dentry = mount_subtree(root_mnt, export_path);
-	nfs_referral_loop_unprotect();
-
-	return dentry;
-}
-
-static struct dentry *nfs4_try_mount(int flags, const char *dev_name,
-			 struct nfs_mount_info *mount_info)
-{
-	char *export_path;
-	struct vfsmount *root_mnt;
-	struct dentry *res;
-	struct nfs_parsed_mount_data *data = mount_info->parsed;
-
-	dfprintk(MOUNT, "--> nfs4_try_mount()\n");
-
-	mount_info->fill_super = nfs4_fill_super;
-
-	export_path = data->nfs_server.export_path;
-	data->nfs_server.export_path = "/";
-	root_mnt = nfs_do_root_mount(&nfs4_remote_fs_type, flags, mount_info,
-			data->nfs_server.hostname);
-	data->nfs_server.export_path = export_path;
-
-	res = nfs_follow_remote_path(root_mnt, export_path);
-
-	dfprintk(MOUNT, "<-- nfs4_try_mount() = %ld%s\n",
-			IS_ERR(res) ? PTR_ERR(res) : 0,
-			IS_ERR(res) ? " [error]" : "");
-	return res;
-}
-
-static void nfs4_kill_super(struct super_block *sb)
-{
-	struct nfs_server *server = NFS_SB(sb);
-
-	dprintk("--> %s\n", __func__);
-	nfs_super_return_all_delegations(sb);
-	kill_anon_super(sb);
-	nfs_fscache_release_super_cookie(sb);
-	nfs_free_server(server);
-	dprintk("<-- %s\n", __func__);
-}
-
-/*
- * Clone an NFS4 server record on xdev traversal (FSID-change)
- */
-static struct dentry *
-nfs4_xdev_mount(struct file_system_type *fs_type, int flags,
-		 const char *dev_name, void *raw_data)
-{
-	struct nfs_mount_info mount_info = {
-		.fill_super = nfs4_clone_super,
-		.set_security = nfs_clone_sb_security,
-		.cloned = raw_data,
-	};
-	return nfs_xdev_mount_common(&nfs4_fs_type, flags, dev_name, &mount_info);
-}
-
-static struct dentry *
-nfs4_remote_referral_mount(struct file_system_type *fs_type, int flags,
-			   const char *dev_name, void *raw_data)
-{
-	struct nfs_mount_info mount_info = {
-		.fill_super = nfs4_fill_super,
-		.set_security = nfs_clone_sb_security,
-		.cloned = raw_data,
-	};
-	struct nfs_server *server;
-	struct dentry *mntroot = ERR_PTR(-ENOMEM);
-
-	dprintk("--> nfs4_referral_get_sb()\n");
-
-	mount_info.mntfh = nfs_alloc_fhandle();
-	if (mount_info.cloned == NULL || mount_info.mntfh == NULL)
-		goto out;
-
-	/* create a new volume representation */
-	server = nfs4_create_referral_server(mount_info.cloned, mount_info.mntfh);
-	if (IS_ERR(server)) {
-		mntroot = ERR_CAST(server);
-		goto out;
-	}
-
-	mntroot = nfs_fs_mount_common(&nfs4_fs_type, server, flags, dev_name, &mount_info);
-out:
-	nfs_free_fhandle(mount_info.mntfh);
-	return mntroot;
-}
-
-/*
- * Create an NFS4 server record on referral traversal
- */
-static struct dentry *nfs4_referral_mount(struct file_system_type *fs_type,
-		int flags, const char *dev_name, void *raw_data)
-{
-	struct nfs_clone_mount *data = raw_data;
-	char *export_path;
-	struct vfsmount *root_mnt;
-	struct dentry *res;
-
-	dprintk("--> nfs4_referral_mount()\n");
-
-	export_path = data->mnt_path;
-	data->mnt_path = "/";
-
-	root_mnt = nfs_do_root_mount(&nfs4_remote_referral_fs_type,
-			flags, data, data->hostname);
-	data->mnt_path = export_path;
-
-	res = nfs_follow_remote_path(root_mnt, export_path);
-	dprintk("<-- nfs4_referral_mount() = %ld%s\n",
-			IS_ERR(res) ? PTR_ERR(res) : 0,
-			IS_ERR(res) ? " [error]" : "");
-	return res;
-}
-
 #endif /* CONFIG_NFS_V4 */

fs/nfs/sysctl.c

@@ -9,37 +9,11 @@
 #include <linux/fs.h>
 #include <linux/sysctl.h>
 #include <linux/module.h>
-#include <linux/nfs4.h>
-#include <linux/nfs_idmap.h>
 #include <linux/nfs_fs.h>
 
-#include "callback.h"
-
-#ifdef CONFIG_NFS_V4
-static const int nfs_set_port_min = 0;
-static const int nfs_set_port_max = 65535;
-#endif
 static struct ctl_table_header *nfs_callback_sysctl_table;
 
 static ctl_table nfs_cb_sysctls[] = {
-#ifdef CONFIG_NFS_V4
-	{
-		.procname = "nfs_callback_tcpport",
-		.data = &nfs_callback_set_tcpport,
-		.maxlen = sizeof(int),
-		.mode = 0644,
-		.proc_handler = proc_dointvec_minmax,
-		.extra1 = (int *)&nfs_set_port_min,
-		.extra2 = (int *)&nfs_set_port_max,
-	},
-	{
-		.procname = "idmap_cache_timeout",
-		.data = &nfs_idmap_cache_timeout,
-		.maxlen = sizeof(int),
-		.mode = 0644,
-		.proc_handler = proc_dointvec_jiffies,
-	},
-#endif
 	{
 		.procname	= "nfs_mountpoint_timeout",
 		.data		= &nfs_mountpoint_expiry_timeout,

fs/nfs/unlink.c

@@ -501,7 +501,7 @@ nfs_sillyrename(struct inode *dir, struct dentry *dentry)
 		(unsigned long long)NFS_FILEID(dentry->d_inode));
 
 	/* Return delegation in anticipation of the rename */
-	nfs_inode_return_delegation(dentry->d_inode);
+	NFS_PROTO(dentry->d_inode)->return_delegation(dentry->d_inode);
 
 	sdentry = NULL;
 	do {

fs/nfs/write.c

@@ -336,8 +336,10 @@ static int nfs_writepage_locked(struct page *page, struct writeback_control *wbc
 	struct nfs_pageio_descriptor pgio;
 	int err;
 
-	nfs_pageio_init_write(&pgio, page->mapping->host, wb_priority(wbc),
-			      &nfs_async_write_completion_ops);
+	NFS_PROTO(page->mapping->host)->write_pageio_init(&pgio,
+							  page->mapping->host,
+							  wb_priority(wbc),
+							  &nfs_async_write_completion_ops);
 	err = nfs_do_writepage(page, wbc, &pgio);
 	nfs_pageio_complete(&pgio);
 	if (err < 0)
@@ -380,8 +382,7 @@ int nfs_writepages(struct address_space *mapping, struct writeback_control *wbc)
 
 	nfs_inc_stats(inode, NFSIOS_VFSWRITEPAGES);
 
-	nfs_pageio_init_write(&pgio, inode, wb_priority(wbc),
-			      &nfs_async_write_completion_ops);
+	NFS_PROTO(inode)->write_pageio_init(&pgio, inode, wb_priority(wbc), &nfs_async_write_completion_ops);
 	err = write_cache_pages(mapping, wbc, nfs_writepages_callback, &pgio);
 	nfs_pageio_complete(&pgio);
 
@@ -410,7 +411,7 @@ static void nfs_inode_add_request(struct inode *inode, struct nfs_page *req)
 	nfs_lock_request(req);
 
 	spin_lock(&inode->i_lock);
-	if (!nfsi->npages && nfs_have_delegation(inode, FMODE_WRITE))
+	if (!nfsi->npages && NFS_PROTO(inode)->have_delegation(inode, FMODE_WRITE))
 		inode->i_version++;
 	set_bit(PG_MAPPED, &req->wb_flags);
 	SetPagePrivate(req->wb_page);
@@ -620,7 +621,7 @@ static void nfs_write_completion(struct nfs_pgio_header *hdr)
 			goto next;
 		}
 		if (test_bit(NFS_IOHDR_NEED_COMMIT, &hdr->flags)) {
-			memcpy(&req->wb_verf, hdr->verf, sizeof(req->wb_verf));
+			memcpy(&req->wb_verf, &hdr->verf->verifier, sizeof(req->wb_verf));
 			nfs_mark_request_commit(req, hdr->lseg, &cinfo);
 			goto next;
 		}
@@ -1202,7 +1203,7 @@ static const struct nfs_pageio_ops nfs_pageio_write_ops = {
 	.pg_doio = nfs_generic_pg_writepages,
 };
 
-void nfs_pageio_init_write_mds(struct nfs_pageio_descriptor *pgio,
+void nfs_pageio_init_write(struct nfs_pageio_descriptor *pgio,
 			       struct inode *inode, int ioflags,
 			       const struct nfs_pgio_completion_ops *compl_ops)
 {
@@ -1217,13 +1218,6 @@ void nfs_pageio_reset_write_mds(struct nfs_pageio_descriptor *pgio)
 }
 EXPORT_SYMBOL_GPL(nfs_pageio_reset_write_mds);
 
-void nfs_pageio_init_write(struct nfs_pageio_descriptor *pgio,
-			   struct inode *inode, int ioflags,
-			   const struct nfs_pgio_completion_ops *compl_ops)
-{
-	if (!pnfs_pageio_init_write(pgio, inode, ioflags, compl_ops))
-		nfs_pageio_init_write_mds(pgio, inode, ioflags, compl_ops);
-}
 
 void nfs_write_prepare(struct rpc_task *task, void *calldata)
 {
@@ -1547,7 +1541,7 @@ static void nfs_commit_release_pages(struct nfs_commit_data *data)
 
 		/* Okay, COMMIT succeeded, apparently. Check the verifier
 		 * returned by the server against all stored verfs. */
-		if (!memcmp(req->wb_verf.verifier, data->verf.verifier, sizeof(data->verf.verifier))) {
+		if (!memcmp(&req->wb_verf, &data->verf.verifier, sizeof(req->wb_verf))) {
 			/* We have a match */
 			nfs_inode_remove_request(req);
 			dprintk(" OK\n");
@@ -1677,9 +1671,14 @@ static int nfs_commit_unstable_pages(struct inode *inode, struct writeback_contr
 
 int nfs_write_inode(struct inode *inode, struct writeback_control *wbc)
 {
-	int ret;
+	return nfs_commit_unstable_pages(inode, wbc);
+}
+
+#ifdef CONFIG_NFS_V4
+int nfs4_write_inode(struct inode *inode, struct writeback_control *wbc)
+{
+	int ret = nfs_write_inode(inode, wbc);
 
-	ret = nfs_commit_unstable_pages(inode, wbc);
 	if (ret >= 0 && test_bit(NFS_INO_LAYOUTCOMMIT, &NFS_I(inode)->flags)) {
 		int status;
 		bool sync = true;
@@ -1693,6 +1692,7 @@ int nfs_write_inode(struct inode *inode, struct writeback_control *wbc)
 	}
 	return ret;
 }
+#endif
 
 /*
  * flush the inode to disk.

include/linux/nfs_fs.h

@@ -427,10 +427,6 @@ extern __be32 root_nfs_parse_addr(char *name); /*__init*/
 /*
  * linux/fs/nfs/file.c
  */
-extern const struct inode_operations nfs_file_inode_operations;
-#ifdef CONFIG_NFS_V3
-extern const struct inode_operations nfs3_file_inode_operations;
-#endif /* CONFIG_NFS_V3 */
 extern const struct file_operations nfs_file_operations;
 #ifdef CONFIG_NFS_V4
 extern const struct file_operations nfs4_file_operations;
@@ -485,10 +481,6 @@ extern ssize_t nfs_file_direct_write(struct kiocb *iocb,
 /*
  * linux/fs/nfs/dir.c
  */
-extern const struct inode_operations nfs_dir_inode_operations;
-#ifdef CONFIG_NFS_V3
-extern const struct inode_operations nfs3_dir_inode_operations;
-#endif /* CONFIG_NFS_V3 */
 extern const struct file_operations nfs_dir_operations;
 extern const struct dentry_operations nfs_dentry_operations;
 

include/linux/nfs_fs_sb.h

@@ -69,10 +69,9 @@ struct nfs_client {
 	struct idmap *		cl_idmap;
 
 	/* Our own IP address, as a null-terminated string.
-	 * This is used to generate the clientid, and the callback address.
+	 * This is used to generate the mv0 callback address.
 	 */
 	char			cl_ipaddr[48];
-	unsigned char		cl_id_uniquifier;
 	u32			cl_cb_ident;	/* v4.0 callback identifier */
 	const struct nfs4_minor_version_ops *cl_mvops;
 

include/linux/nfs_page.h

@@ -42,7 +42,7 @@ struct nfs_page {
 				wb_bytes;	/* Length of request */
 	struct kref		wb_kref;	/* reference count */
 	unsigned long		wb_flags;
-	struct nfs_writeverf	wb_verf;	/* Commit cookie */
+	struct nfs_write_verifier	wb_verf;	/* Commit cookie */
 };
 
 struct nfs_pageio_descriptor;

include/linux/nfs_xdr.h

@@ -514,9 +514,13 @@ struct nfs_writeargs {
 	struct nfs4_sequence_args	seq_args;
 };
 
+struct nfs_write_verifier {
+	char			data[8];
+};
+
 struct nfs_writeverf {
+	struct nfs_write_verifier verifier;
 	enum nfs3_stable_how	committed;
-	__be32			verifier[2];
 };
 
 struct nfs_writeres {
@@ -1349,6 +1353,8 @@ struct nfs_renamedata {
 struct nfs_access_entry;
 struct nfs_client;
 struct rpc_timeout;
+struct nfs_client_initdata;
+struct nfs_pageio_descriptor;
 
 /*
  * RPC procedure vector for NFSv2/NFSv3 demuxing
@@ -1402,9 +1408,13 @@ struct nfs_rpc_ops {
 	int	(*set_capabilities)(struct nfs_server *, struct nfs_fh *);
 	int	(*decode_dirent)(struct xdr_stream *, struct nfs_entry *, int);
 	void	(*read_setup)   (struct nfs_read_data *, struct rpc_message *);
+	void	(*read_pageio_init)(struct nfs_pageio_descriptor *, struct inode *,
+				    const struct nfs_pgio_completion_ops *);
 	void	(*read_rpc_prepare)(struct rpc_task *, struct nfs_read_data *);
 	int	(*read_done)  (struct rpc_task *, struct nfs_read_data *);
 	void	(*write_setup)  (struct nfs_write_data *, struct rpc_message *);
+	void	(*write_pageio_init)(struct nfs_pageio_descriptor *, struct inode *, int,
+				     const struct nfs_pgio_completion_ops *);
 	void	(*write_rpc_prepare)(struct rpc_task *, struct nfs_write_data *);
 	int	(*write_done)  (struct rpc_task *, struct nfs_write_data *);
 	void	(*commit_setup) (struct nfs_commit_data *, struct rpc_message *);
@@ -1418,9 +1428,13 @@ struct nfs_rpc_ops {
 				struct nfs_open_context *ctx,
 				int open_flags,
 				struct iattr *iattr);
+	int (*have_delegation)(struct inode *, fmode_t);
+	int (*return_delegation)(struct inode *);
+	struct nfs_client *(*alloc_client) (const struct nfs_client_initdata *);
 	struct nfs_client *
 		(*init_client) (struct nfs_client *, const struct rpc_timeout *,
 				const char *, rpc_authflavor_t);
+	void	(*free_client) (struct nfs_client *);
 };
 
 /*

include/linux/sunrpc/auth.h

@@ -101,6 +101,7 @@ struct rpc_authops {
 	struct rpc_cred *	(*crcreate)(struct rpc_auth*, struct auth_cred *, int);
 	int			(*pipes_create)(struct rpc_auth *);
 	void			(*pipes_destroy)(struct rpc_auth *);
+	int			(*list_pseudoflavors)(rpc_authflavor_t *, int);
 };
 
 struct rpc_credops {
@@ -135,6 +136,7 @@ int			rpcauth_register(const struct rpc_authops *);
 int			rpcauth_unregister(const struct rpc_authops *);
 struct rpc_auth *	rpcauth_create(rpc_authflavor_t, struct rpc_clnt *);
 void			rpcauth_release(struct rpc_auth *);
+int			rpcauth_list_flavors(rpc_authflavor_t *, int);
 struct rpc_cred *	rpcauth_lookup_credcache(struct rpc_auth *, struct auth_cred *, int);
 void			rpcauth_init_cred(struct rpc_cred *, const struct auth_cred *, struct rpc_auth *, const struct rpc_credops *);
 struct rpc_cred *	rpcauth_lookupcred(struct rpc_auth *, int);

include/linux/sunrpc/gss_api.h

@@ -14,6 +14,7 @@
 
 #ifdef __KERNEL__
 #include <linux/sunrpc/xdr.h>
+#include <linux/sunrpc/msg_prot.h>
 #include <linux/uio.h>
 
 /* The mechanism-independent gss-api context: */
@@ -127,7 +128,7 @@ struct gss_api_mech *gss_mech_get_by_name(const char *);
 struct gss_api_mech *gss_mech_get_by_pseudoflavor(u32);
 
 /* Fill in an array with a list of supported pseudoflavors */
-int gss_mech_list_pseudoflavors(u32 *);
+int gss_mech_list_pseudoflavors(rpc_authflavor_t *, int);
 
 /* Just increments the mechanism's reference count and returns its input: */
 struct gss_api_mech * gss_mech_get(struct gss_api_mech *);

include/linux/sunrpc/xdr.h

@@ -104,8 +104,6 @@ __be32 *xdr_decode_string_inplace(__be32 *p, char **sp, unsigned int *lenp,
 __be32 *xdr_encode_netobj(__be32 *p, const struct xdr_netobj *);
 __be32 *xdr_decode_netobj(__be32 *p, struct xdr_netobj *);
 
-void	xdr_encode_pages(struct xdr_buf *, struct page **, unsigned int,
-			 unsigned int);
 void	xdr_inline_pages(struct xdr_buf *, unsigned int,
 			 struct page **, unsigned int, unsigned int);
 void	xdr_terminate_string(struct xdr_buf *, const u32);
@@ -205,6 +203,7 @@ struct xdr_stream {
 	struct kvec *iov;	/* pointer to the current kvec */
 	struct kvec scratch;	/* Scratch buffer */
 	struct page **page_ptr;	/* pointer to the current page */
+	unsigned int nwords;	/* Remaining decode buffer length */
 };
 
 /*
@@ -217,12 +216,13 @@ extern void xdr_init_encode(struct xdr_stream *xdr, struct xdr_buf *buf, __be32
 extern __be32 *xdr_reserve_space(struct xdr_stream *xdr, size_t nbytes);
 extern void xdr_write_pages(struct xdr_stream *xdr, struct page **pages,
 		unsigned int base, unsigned int len);
+extern unsigned int xdr_stream_pos(const struct xdr_stream *xdr);
 extern void xdr_init_decode(struct xdr_stream *xdr, struct xdr_buf *buf, __be32 *p);
 extern void xdr_init_decode_pages(struct xdr_stream *xdr, struct xdr_buf *buf,
 		struct page **pages, unsigned int len);
 extern void xdr_set_scratch_buffer(struct xdr_stream *xdr, void *buf, size_t buflen);
 extern __be32 *xdr_inline_decode(struct xdr_stream *xdr, size_t nbytes);
-extern void xdr_read_pages(struct xdr_stream *xdr, unsigned int len);
+extern unsigned int xdr_read_pages(struct xdr_stream *xdr, unsigned int len);
 extern void xdr_enter_page(struct xdr_stream *xdr, unsigned int len);
 extern int xdr_process_buf(struct xdr_buf *buf, unsigned int offset, unsigned int len, int (*actor)(struct scatterlist *, void *), void *data);
 

net/sunrpc/auth.c

@@ -13,6 +13,7 @@
 #include <linux/errno.h>
 #include <linux/hash.h>
 #include <linux/sunrpc/clnt.h>
+#include <linux/sunrpc/gss_api.h>
 #include <linux/spinlock.h>
 
 #ifdef RPC_DEBUG
@@ -122,6 +123,59 @@ rpcauth_unregister(const struct rpc_authops *ops)
 }
 EXPORT_SYMBOL_GPL(rpcauth_unregister);
 
+/**
+ * rpcauth_list_flavors - discover registered flavors and pseudoflavors
+ * @array: array to fill in
+ * @size: size of "array"
+ *
+ * Returns the number of array items filled in, or a negative errno.
+ *
+ * The returned array is not sorted by any policy.  Callers should not
+ * rely on the order of the items in the returned array.
+ */
+int
+rpcauth_list_flavors(rpc_authflavor_t *array, int size)
+{
+	rpc_authflavor_t flavor;
+	int result = 0;
+
+	spin_lock(&rpc_authflavor_lock);
+	for (flavor = 0; flavor < RPC_AUTH_MAXFLAVOR; flavor++) {
+		const struct rpc_authops *ops = auth_flavors[flavor];
+		rpc_authflavor_t pseudos[4];
+		int i, len;
+
+		if (result >= size) {
+			result = -ENOMEM;
+			break;
+		}
+
+		if (ops == NULL)
+			continue;
+		if (ops->list_pseudoflavors == NULL) {
+			array[result++] = ops->au_flavor;
+			continue;
+		}
+		len = ops->list_pseudoflavors(pseudos, ARRAY_SIZE(pseudos));
+		if (len < 0) {
+			result = len;
+			break;
+		}
+		for (i = 0; i < len; i++) {
+			if (result >= size) {
+				result = -ENOMEM;
+				break;
+			}
+			array[result++] = pseudos[i];
+		}
+	}
+	spin_unlock(&rpc_authflavor_lock);
+
+	dprintk("RPC:       %s returns %d\n", __func__, result);
+	return result;
+}
+EXPORT_SYMBOL_GPL(rpcauth_list_flavors);
+
 struct rpc_auth *
 rpcauth_create(rpc_authflavor_t pseudoflavor, struct rpc_clnt *clnt)
 {

net/sunrpc/auth_gss/auth_gss.c

@@ -1619,6 +1619,7 @@ static const struct rpc_authops authgss_ops = {
 	.crcreate	= gss_create_cred,
 	.pipes_create	= gss_pipes_dentries_create,
 	.pipes_destroy	= gss_pipes_dentries_destroy,
+	.list_pseudoflavors = gss_mech_list_pseudoflavors,
 };
 
 static const struct rpc_credops gss_credops = {

net/sunrpc/auth_gss/gss_mech_switch.c

@@ -239,14 +239,28 @@ gss_mech_get_by_pseudoflavor(u32 pseudoflavor)
 
 EXPORT_SYMBOL_GPL(gss_mech_get_by_pseudoflavor);
 
-int gss_mech_list_pseudoflavors(rpc_authflavor_t *array_ptr)
+/**
+ * gss_mech_list_pseudoflavors - Discover registered GSS pseudoflavors
+ * @array: array to fill in
+ * @size: size of "array"
+ *
+ * Returns the number of array items filled in, or a negative errno.
+ *
+ * The returned array is not sorted by any policy.  Callers should not
+ * rely on the order of the items in the returned array.
+ */
+int gss_mech_list_pseudoflavors(rpc_authflavor_t *array_ptr, int size)
 {
 	struct gss_api_mech *pos = NULL;
 	int j, i = 0;
 
 	spin_lock(&registered_mechs_lock);
 	list_for_each_entry(pos, &registered_mechs, gm_list) {
-		for (j=0; j < pos->gm_pf_num; j++) {
+		for (j = 0; j < pos->gm_pf_num; j++) {
+			if (i >= size) {
+				spin_unlock(&registered_mechs_lock);
+				return -ENOMEM;
+			}
 			array_ptr[i++] = pos->gm_pfs[j].pseudoflavor;
 		}
 	}
@@ -254,8 +268,6 @@ int gss_mech_list_pseudoflavors(rpc_authflavor_t *array_ptr)
 	return i;
 }
 
-EXPORT_SYMBOL_GPL(gss_mech_list_pseudoflavors);
-
 u32
 gss_svc_to_pseudoflavor(struct gss_api_mech *gm, u32 service)
 {

net/sunrpc/clnt.c

@@ -1844,12 +1844,13 @@ call_timeout(struct rpc_task *task)
 		return;
 	}
 	if (RPC_IS_SOFT(task)) {
-		if (clnt->cl_chatty)
+		if (clnt->cl_chatty) {
 			rcu_read_lock();
 			printk(KERN_NOTICE "%s: server %s not responding, timed out\n",
 				clnt->cl_protname,
 				rcu_dereference(clnt->cl_xprt)->servername);
 			rcu_read_unlock();
+		}
 		if (task->tk_flags & RPC_TASK_TIMEOUT)
 			rpc_exit(task, -ETIMEDOUT);
 		else

net/sunrpc/xdr.c

@@ -128,34 +128,6 @@ xdr_terminate_string(struct xdr_buf *buf, const u32 len)
 }
 EXPORT_SYMBOL_GPL(xdr_terminate_string);
 
-void
-xdr_encode_pages(struct xdr_buf *xdr, struct page **pages, unsigned int base,
-		 unsigned int len)
-{
-	struct kvec *tail = xdr->tail;
-	u32 *p;
-
-	xdr->pages = pages;
-	xdr->page_base = base;
-	xdr->page_len = len;
-
-	p = (u32 *)xdr->head[0].iov_base + XDR_QUADLEN(xdr->head[0].iov_len);
-	tail->iov_base = p;
-	tail->iov_len = 0;
-
-	if (len & 3) {
-		unsigned int pad = 4 - (len & 3);
-
-		*p = 0;
-		tail->iov_base = (char *)p + (len & 3);
-		tail->iov_len  = pad;
-		len += pad;
-	}
-	xdr->buflen += len;
-	xdr->len += len;
-}
-EXPORT_SYMBOL_GPL(xdr_encode_pages);
-
 void
 xdr_inline_pages(struct xdr_buf *xdr, unsigned int offset,
 		 struct page **pages, unsigned int base, unsigned int len)
@@ -456,6 +428,16 @@ xdr_shift_buf(struct xdr_buf *buf, size_t len)
 }
 EXPORT_SYMBOL_GPL(xdr_shift_buf);
 
+/**
+ * xdr_stream_pos - Return the current offset from the start of the xdr_stream
+ * @xdr: pointer to struct xdr_stream
+ */
+unsigned int xdr_stream_pos(const struct xdr_stream *xdr)
+{
+	return (unsigned int)(XDR_QUADLEN(xdr->buf->len) - xdr->nwords) << 2;
+}
+EXPORT_SYMBOL_GPL(xdr_stream_pos);
+
 /**
  * xdr_init_encode - Initialize a struct xdr_stream for sending data.
  * @xdr: pointer to xdr_stream struct
@@ -556,13 +538,11 @@ void xdr_write_pages(struct xdr_stream *xdr, struct page **pages, unsigned int b
 EXPORT_SYMBOL_GPL(xdr_write_pages);
 
 static void xdr_set_iov(struct xdr_stream *xdr, struct kvec *iov,
-		__be32 *p, unsigned int len)
+		unsigned int len)
 {
 	if (len > iov->iov_len)
 		len = iov->iov_len;
-	if (p == NULL)
-		p = (__be32*)iov->iov_base;
-	xdr->p = p;
+	xdr->p = (__be32*)iov->iov_base;
 	xdr->end = (__be32*)(iov->iov_base + len);
 	xdr->iov = iov;
 	xdr->page_ptr = NULL;
@@ -609,7 +589,7 @@ static void xdr_set_next_page(struct xdr_stream *xdr)
 	newbase -= xdr->buf->page_base;
 
 	if (xdr_set_page_base(xdr, newbase, PAGE_SIZE) < 0)
-		xdr_set_iov(xdr, xdr->buf->tail, NULL, xdr->buf->len);
+		xdr_set_iov(xdr, xdr->buf->tail, xdr->buf->len);
 }
 
 static bool xdr_set_next_buffer(struct xdr_stream *xdr)
@@ -618,7 +598,7 @@ static bool xdr_set_next_buffer(struct xdr_stream *xdr)
 		xdr_set_next_page(xdr);
 	else if (xdr->iov == xdr->buf->head) {
 		if (xdr_set_page_base(xdr, 0, PAGE_SIZE) < 0)
-			xdr_set_iov(xdr, xdr->buf->tail, NULL, xdr->buf->len);
+			xdr_set_iov(xdr, xdr->buf->tail, xdr->buf->len);
 	}
 	return xdr->p != xdr->end;
 }
@@ -634,10 +614,15 @@ void xdr_init_decode(struct xdr_stream *xdr, struct xdr_buf *buf, __be32 *p)
 	xdr->buf = buf;
 	xdr->scratch.iov_base = NULL;
 	xdr->scratch.iov_len = 0;
+	xdr->nwords = XDR_QUADLEN(buf->len);
 	if (buf->head[0].iov_len != 0)
-		xdr_set_iov(xdr, buf->head, p, buf->len);
+		xdr_set_iov(xdr, buf->head, buf->len);
 	else if (buf->page_len != 0)
 		xdr_set_page_base(xdr, 0, buf->len);
+	if (p != NULL && p > xdr->p && xdr->end >= p) {
+		xdr->nwords -= p - xdr->p;
+		xdr->p = p;
+	}
 }
 EXPORT_SYMBOL_GPL(xdr_init_decode);
 
@@ -662,12 +647,14 @@ EXPORT_SYMBOL_GPL(xdr_init_decode_pages);
 
 static __be32 * __xdr_inline_decode(struct xdr_stream *xdr, size_t nbytes)
 {
+	unsigned int nwords = XDR_QUADLEN(nbytes);
 	__be32 *p = xdr->p;
-	__be32 *q = p + XDR_QUADLEN(nbytes);
+	__be32 *q = p + nwords;
 
-	if (unlikely(q > xdr->end || q < p))
+	if (unlikely(nwords > xdr->nwords || q > xdr->end || q < p))
 		return NULL;
 	xdr->p = q;
+	xdr->nwords -= nwords;
 	return p;
 }
 
@@ -734,6 +721,31 @@ __be32 * xdr_inline_decode(struct xdr_stream *xdr, size_t nbytes)
 }
 EXPORT_SYMBOL_GPL(xdr_inline_decode);
 
+static unsigned int xdr_align_pages(struct xdr_stream *xdr, unsigned int len)
+{
+	struct xdr_buf *buf = xdr->buf;
+	struct kvec *iov;
+	unsigned int nwords = XDR_QUADLEN(len);
+	unsigned int cur = xdr_stream_pos(xdr);
+
+	if (xdr->nwords == 0)
+		return 0;
+	if (nwords > xdr->nwords) {
+		nwords = xdr->nwords;
+		len = nwords << 2;
+	}
+	/* Realign pages to current pointer position */
+	iov  = buf->head;
+	if (iov->iov_len > cur)
+		xdr_shrink_bufhead(buf, iov->iov_len - cur);
+
+	/* Truncate page data and move it into the tail */
+	if (buf->page_len > len)
+		xdr_shrink_pagelen(buf, buf->page_len - len);
+	xdr->nwords = XDR_QUADLEN(buf->len - cur);
+	return len;
+}
+
 /**
  * xdr_read_pages - Ensure page-based XDR data to decode is aligned at current pointer position
  * @xdr: pointer to xdr_stream struct
@@ -742,39 +754,37 @@ EXPORT_SYMBOL_GPL(xdr_inline_decode);
  * Moves data beyond the current pointer position from the XDR head[] buffer
  * into the page list. Any data that lies beyond current position + "len"
  * bytes is moved into the XDR tail[].
+ *
+ * Returns the number of XDR encoded bytes now contained in the pages
  */
-void xdr_read_pages(struct xdr_stream *xdr, unsigned int len)
+unsigned int xdr_read_pages(struct xdr_stream *xdr, unsigned int len)
 {
 	struct xdr_buf *buf = xdr->buf;
 	struct kvec *iov;
-	ssize_t shift;
+	unsigned int nwords;
 	unsigned int end;
-	int padding;
+	unsigned int padding;
 
-	/* Realign pages to current pointer position */
-	iov  = buf->head;
-	shift = iov->iov_len + (char *)iov->iov_base - (char *)xdr->p;
-	if (shift > 0)
-		xdr_shrink_bufhead(buf, shift);
-
-	/* Truncate page data and move it into the tail */
-	if (buf->page_len > len)
-		xdr_shrink_pagelen(buf, buf->page_len - len);
-	padding = (XDR_QUADLEN(len) << 2) - len;
+	len = xdr_align_pages(xdr, len);
+	if (len == 0)
+		return 0;
+	nwords = XDR_QUADLEN(len);
+	padding = (nwords << 2) - len;
 	xdr->iov = iov = buf->tail;
 	/* Compute remaining message length.  */
-	end = iov->iov_len;
-	shift = buf->buflen - buf->len;
-	if (shift < end)
-		end -= shift;
-	else if (shift > 0)
-		end = 0;
+	end = ((xdr->nwords - nwords) << 2) + padding;
+	if (end > iov->iov_len)
+		end = iov->iov_len;
+
 	/*
 	 * Position current pointer at beginning of tail, and
 	 * set remaining message length.
 	 */
 	xdr->p = (__be32 *)((char *)iov->iov_base + padding);
 	xdr->end = (__be32 *)((char *)iov->iov_base + end);
+	xdr->page_ptr = NULL;
+	xdr->nwords = XDR_QUADLEN(end - padding);
+	return len;
 }
 EXPORT_SYMBOL_GPL(xdr_read_pages);
 
@@ -790,12 +800,13 @@ EXPORT_SYMBOL_GPL(xdr_read_pages);
  */
 void xdr_enter_page(struct xdr_stream *xdr, unsigned int len)
 {
-	xdr_read_pages(xdr, len);
+	len = xdr_align_pages(xdr, len);
 	/*
 	 * Position current pointer at beginning of tail, and
 	 * set remaining message length.
 	 */
-	xdr_set_page_base(xdr, 0, len);
+	if (len != 0)
+		xdr_set_page_base(xdr, 0, len);
 }
 EXPORT_SYMBOL_GPL(xdr_enter_page);