Merge branch 'for-2.6.31' of git://git.linux-nfs.org/projects/trondmy/nfs-2.6

* 'for-2.6.31' of git://git.linux-nfs.org/projects/trondmy/nfs-2.6: (128 commits)
  nfs41: sunrpc: xprt_alloc_bc_request() should not use spin_lock_bh()
  nfs41: Move initialization of nfs4_opendata seq_res to nfs4_init_opendata_res
  nfs: remove unnecessary NFS_INO_INVALID_ACL checks
  NFS: More "sloppy" parsing problems
  NFS: Invalid mount option values should always fail, even with "sloppy"
  NFS: Remove unused XDR decoder functions
  NFS: Update MNT and MNT3 reply decoding functions
  NFS: add XDR decoder for mountd version 3 auth-flavor lists
  NFS: add new file handle decoders to in-kernel mountd client
  NFS: Add separate mountd status code decoders for each mountd version
  NFS: remove unused function in fs/nfs/mount_clnt.c
  NFS: Use xdr_stream-based XDR encoder for MNT's dirpath argument
  NFS: Clean up MNT program definitions
  lockd: Don't bother with RPC ping for NSM upcalls
  lockd: Update NSM state from SM_MON replies
  NFS: Fix false error return from nfs_callback_up() if ipv6.ko is not available
  NFS: Return error code from nfs_callback_up() to user space
  NFS: Do not display the setting of the "intr" mount option
  NFS: add support for splice writes
  nfs41: Backchannel: CB_SEQUENCE validation
  ...

fs/lockd/clntproc.c

@@ -126,7 +126,6 @@ static void nlmclnt_setlockargs(struct nlm_rqst *req, struct file_lock *fl)
 	struct nlm_lock	*lock = &argp->lock;
 
 	nlmclnt_next_cookie(&argp->cookie);
-	argp->state   = nsm_local_state;
 	memcpy(&lock->fh, NFS_FH(fl->fl_file->f_path.dentry->d_inode), sizeof(struct nfs_fh));
 	lock->caller  = utsname()->nodename;
 	lock->oh.data = req->a_owner;
@@ -165,6 +164,7 @@ int nlmclnt_proc(struct nlm_host *host, int cmd, struct file_lock *fl)
 	/* Set up the argument struct */
 	nlmclnt_setlockargs(call, fl);
 
+	lock_kernel();
 	if (IS_SETLK(cmd) || IS_SETLKW(cmd)) {
 		if (fl->fl_type != F_UNLCK) {
 			call->a_args.block = IS_SETLKW(cmd) ? 1 : 0;
@@ -178,6 +178,7 @@ int nlmclnt_proc(struct nlm_host *host, int cmd, struct file_lock *fl)
 
 	fl->fl_ops->fl_release_private(fl);
 	fl->fl_ops = NULL;
+	unlock_kernel();
 
 	dprintk("lockd: clnt proc returns %d\n", status);
 	return status;
@@ -519,6 +520,7 @@ nlmclnt_lock(struct nlm_rqst *req, struct file_lock *fl)
 
 	if (nsm_monitor(host) < 0)
 		goto out;
+	req->a_args.state = nsm_local_state;
 
 	fl->fl_flags |= FL_ACCESS;
 	status = do_vfs_lock(fl);

fs/lockd/mon.c

@@ -53,7 +53,7 @@ static				DEFINE_SPINLOCK(nsm_lock);
 /*
  * Local NSM state
  */
-int	__read_mostly		nsm_local_state;
+u32	__read_mostly		nsm_local_state;
 int	__read_mostly		nsm_use_hostnames;
 
 static inline struct sockaddr *nsm_addr(const struct nsm_handle *nsm)
@@ -112,6 +112,7 @@ static struct rpc_clnt *nsm_create(void)
 		.program		= &nsm_program,
 		.version		= NSM_VERSION,
 		.authflavor		= RPC_AUTH_NULL,
+		.flags			= RPC_CLNT_CREATE_NOPING,
 	};
 
 	return rpc_create(&args);
@@ -184,13 +185,19 @@ int nsm_monitor(const struct nlm_host *host)
 	nsm->sm_mon_name = nsm_use_hostnames ? nsm->sm_name : nsm->sm_addrbuf;
 
 	status = nsm_mon_unmon(nsm, NSMPROC_MON, &res);
-	if (res.status != 0)
+	if (unlikely(res.status != 0))
 		status = -EIO;
-	if (status < 0)
+	if (unlikely(status < 0)) {
 		printk(KERN_NOTICE "lockd: cannot monitor %s\n", nsm->sm_name);
-	else
-		nsm->sm_monitored = 1;
-	return status;
+		return status;
+	}
+
+	nsm->sm_monitored = 1;
+	if (unlikely(nsm_local_state != res.state)) {
+		nsm_local_state = res.state;
+		dprintk("lockd: NSM state changed to %d\n", nsm_local_state);
+	}
+	return 0;
 }
 
 /**

fs/nfs/Kconfig

@@ -74,6 +74,15 @@ config NFS_V4
 
 	  If unsure, say N.
 
+config NFS_V4_1
+	bool "NFS client support for NFSv4.1 (DEVELOPER ONLY)"
+	depends on NFS_V4 && EXPERIMENTAL
+	help
+	  This option enables support for minor version 1 of the NFSv4 protocol
+	  (draft-ietf-nfsv4-minorversion1) in the kernel's NFS client.
+
+	  Unless you're an NFS developer, say N.
+
 config ROOT_NFS
 	bool "Root file system on NFS"
 	depends on NFS_FS=y && IP_PNP

fs/nfs/callback.c

@@ -17,6 +17,9 @@
 #include <linux/freezer.h>
 #include <linux/kthread.h>
 #include <linux/sunrpc/svcauth_gss.h>
+#if defined(CONFIG_NFS_V4_1)
+#include <linux/sunrpc/bc_xprt.h>
+#endif
 
 #include <net/inet_sock.h>
 
@@ -28,11 +31,12 @@
 
 struct nfs_callback_data {
 	unsigned int users;
+	struct svc_serv *serv;
 	struct svc_rqst *rqst;
 	struct task_struct *task;
 };
 
-static struct nfs_callback_data nfs_callback_info;
+static struct nfs_callback_data nfs_callback_info[NFS4_MAX_MINOR_VERSION + 1];
 static DEFINE_MUTEX(nfs_callback_mutex);
 static struct svc_program nfs4_callback_program;
 
@@ -56,10 +60,10 @@ module_param_call(callback_tcpport, param_set_port, param_get_int,
 		 &nfs_callback_set_tcpport, 0644);
 
 /*
- * This is the callback kernel thread.
+ * This is the NFSv4 callback kernel thread.
  */
 static int
-nfs_callback_svc(void *vrqstp)
+nfs4_callback_svc(void *vrqstp)
 {
 	int err, preverr = 0;
 	struct svc_rqst *rqstp = vrqstp;
@@ -97,20 +101,12 @@ nfs_callback_svc(void *vrqstp)
 }
 
 /*
- * Bring up the callback thread if it is not already up.
+ * Prepare to bring up the NFSv4 callback service
  */
-int nfs_callback_up(void)
+struct svc_rqst *
+nfs4_callback_up(struct svc_serv *serv)
 {
-	struct svc_serv *serv = NULL;
-	int ret = 0;
-
-	mutex_lock(&nfs_callback_mutex);
-	if (nfs_callback_info.users++ || nfs_callback_info.task != NULL)
-		goto out;
-	serv = svc_create(&nfs4_callback_program, NFS4_CALLBACK_BUFSIZE, NULL);
-	ret = -ENOMEM;
-	if (!serv)
-		goto out_err;
+	int ret;
 
 	ret = svc_create_xprt(serv, "tcp", PF_INET,
 				nfs_callback_set_tcpport, SVC_SOCK_ANONYMOUS);
@@ -127,27 +123,174 @@ int nfs_callback_up(void)
 		nfs_callback_tcpport6 = ret;
 		dprintk("NFS: Callback listener port = %u (af %u)\n",
 				nfs_callback_tcpport6, PF_INET6);
-	} else if (ret != -EAFNOSUPPORT)
+	} else if (ret == -EAFNOSUPPORT)
+		ret = 0;
+	else
 		goto out_err;
 #endif	/* defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE) */
 
-	nfs_callback_info.rqst = svc_prepare_thread(serv, &serv->sv_pools[0]);
-	if (IS_ERR(nfs_callback_info.rqst)) {
-		ret = PTR_ERR(nfs_callback_info.rqst);
-		nfs_callback_info.rqst = NULL;
+	return svc_prepare_thread(serv, &serv->sv_pools[0]);
+
+out_err:
+	if (ret == 0)
+		ret = -ENOMEM;
+	return ERR_PTR(ret);
+}
+
+#if defined(CONFIG_NFS_V4_1)
+/*
+ * The callback service for NFSv4.1 callbacks
+ */
+static int
+nfs41_callback_svc(void *vrqstp)
+{
+	struct svc_rqst *rqstp = vrqstp;
+	struct svc_serv *serv = rqstp->rq_server;
+	struct rpc_rqst *req;
+	int error;
+	DEFINE_WAIT(wq);
+
+	set_freezable();
+
+	/*
+	 * FIXME: do we really need to run this under the BKL? If so, please
+	 * add a comment about what it's intended to protect.
+	 */
+	lock_kernel();
+	while (!kthread_should_stop()) {
+		prepare_to_wait(&serv->sv_cb_waitq, &wq, TASK_INTERRUPTIBLE);
+		spin_lock_bh(&serv->sv_cb_lock);
+		if (!list_empty(&serv->sv_cb_list)) {
+			req = list_first_entry(&serv->sv_cb_list,
+					struct rpc_rqst, rq_bc_list);
+			list_del(&req->rq_bc_list);
+			spin_unlock_bh(&serv->sv_cb_lock);
+			dprintk("Invoking bc_svc_process()\n");
+			error = bc_svc_process(serv, req, rqstp);
+			dprintk("bc_svc_process() returned w/ error code= %d\n",
+				error);
+		} else {
+			spin_unlock_bh(&serv->sv_cb_lock);
+			schedule();
+		}
+		finish_wait(&serv->sv_cb_waitq, &wq);
+	}
+	unlock_kernel();
+	return 0;
+}
+
+/*
+ * Bring up the NFSv4.1 callback service
+ */
+struct svc_rqst *
+nfs41_callback_up(struct svc_serv *serv, struct rpc_xprt *xprt)
+{
+	struct svc_xprt *bc_xprt;
+	struct svc_rqst *rqstp = ERR_PTR(-ENOMEM);
+
+	dprintk("--> %s\n", __func__);
+	/* Create a svc_sock for the service */
+	bc_xprt = svc_sock_create(serv, xprt->prot);
+	if (!bc_xprt)
+		goto out;
+
+	/*
+	 * Save the svc_serv in the transport so that it can
+	 * be referenced when the session backchannel is initialized
+	 */
+	serv->bc_xprt = bc_xprt;
+	xprt->bc_serv = serv;
+
+	INIT_LIST_HEAD(&serv->sv_cb_list);
+	spin_lock_init(&serv->sv_cb_lock);
+	init_waitqueue_head(&serv->sv_cb_waitq);
+	rqstp = svc_prepare_thread(serv, &serv->sv_pools[0]);
+	if (IS_ERR(rqstp))
+		svc_sock_destroy(bc_xprt);
+out:
+	dprintk("--> %s return %p\n", __func__, rqstp);
+	return rqstp;
+}
+
+static inline int nfs_minorversion_callback_svc_setup(u32 minorversion,
+		struct svc_serv *serv, struct rpc_xprt *xprt,
+		struct svc_rqst **rqstpp, int (**callback_svc)(void *vrqstp))
+{
+	if (minorversion) {
+		*rqstpp = nfs41_callback_up(serv, xprt);
+		*callback_svc = nfs41_callback_svc;
+	}
+	return minorversion;
+}
+
+static inline void nfs_callback_bc_serv(u32 minorversion, struct rpc_xprt *xprt,
+		struct nfs_callback_data *cb_info)
+{
+	if (minorversion)
+		xprt->bc_serv = cb_info->serv;
+}
+#else
+static inline int nfs_minorversion_callback_svc_setup(u32 minorversion,
+		struct svc_serv *serv, struct rpc_xprt *xprt,
+		struct svc_rqst **rqstpp, int (**callback_svc)(void *vrqstp))
+{
+	return 0;
+}
+
+static inline void nfs_callback_bc_serv(u32 minorversion, struct rpc_xprt *xprt,
+		struct nfs_callback_data *cb_info)
+{
+}
+#endif /* CONFIG_NFS_V4_1 */
+
+/*
+ * Bring up the callback thread if it is not already up.
+ */
+int nfs_callback_up(u32 minorversion, struct rpc_xprt *xprt)
+{
+	struct svc_serv *serv = NULL;
+	struct svc_rqst *rqstp;
+	int (*callback_svc)(void *vrqstp);
+	struct nfs_callback_data *cb_info = &nfs_callback_info[minorversion];
+	char svc_name[12];
+	int ret = 0;
+	int minorversion_setup;
+
+	mutex_lock(&nfs_callback_mutex);
+	if (cb_info->users++ || cb_info->task != NULL) {
+		nfs_callback_bc_serv(minorversion, xprt, cb_info);
+		goto out;
+	}
+	serv = svc_create(&nfs4_callback_program, NFS4_CALLBACK_BUFSIZE, NULL);
+	if (!serv) {
+		ret = -ENOMEM;
+		goto out_err;
+	}
+
+	minorversion_setup =  nfs_minorversion_callback_svc_setup(minorversion,
+					serv, xprt, &rqstp, &callback_svc);
+	if (!minorversion_setup) {
+		/* v4.0 callback setup */
+		rqstp = nfs4_callback_up(serv);
+		callback_svc = nfs4_callback_svc;
+	}
+
+	if (IS_ERR(rqstp)) {
+		ret = PTR_ERR(rqstp);
 		goto out_err;
 	}
 
 	svc_sock_update_bufs(serv);
 
-	nfs_callback_info.task = kthread_run(nfs_callback_svc,
-					     nfs_callback_info.rqst,
-					     "nfsv4-svc");
-	if (IS_ERR(nfs_callback_info.task)) {
-		ret = PTR_ERR(nfs_callback_info.task);
-		svc_exit_thread(nfs_callback_info.rqst);
-		nfs_callback_info.rqst = NULL;
-		nfs_callback_info.task = NULL;
+	sprintf(svc_name, "nfsv4.%u-svc", minorversion);
+	cb_info->serv = serv;
+	cb_info->rqst = rqstp;
+	cb_info->task = kthread_run(callback_svc, cb_info->rqst, svc_name);
+	if (IS_ERR(cb_info->task)) {
+		ret = PTR_ERR(cb_info->task);
+		svc_exit_thread(cb_info->rqst);
+		cb_info->rqst = NULL;
+		cb_info->task = NULL;
 		goto out_err;
 	}
 out:
@@ -164,22 +307,25 @@ out:
 out_err:
 	dprintk("NFS: Couldn't create callback socket or server thread; "
 		"err = %d\n", ret);
-	nfs_callback_info.users--;
+	cb_info->users--;
 	goto out;
 }
 
 /*
  * Kill the callback thread if it's no longer being used.
  */
-void nfs_callback_down(void)
+void nfs_callback_down(int minorversion)
 {
+	struct nfs_callback_data *cb_info = &nfs_callback_info[minorversion];
+
 	mutex_lock(&nfs_callback_mutex);
-	nfs_callback_info.users--;
-	if (nfs_callback_info.users == 0 && nfs_callback_info.task != NULL) {
-		kthread_stop(nfs_callback_info.task);
-		svc_exit_thread(nfs_callback_info.rqst);
-		nfs_callback_info.rqst = NULL;
-		nfs_callback_info.task = NULL;
+	cb_info->users--;
+	if (cb_info->users == 0 && cb_info->task != NULL) {
+		kthread_stop(cb_info->task);
+		svc_exit_thread(cb_info->rqst);
+		cb_info->serv = NULL;
+		cb_info->rqst = NULL;
+		cb_info->task = NULL;
 	}
 	mutex_unlock(&nfs_callback_mutex);
 }

fs/nfs/callback.h

@@ -20,13 +20,24 @@ enum nfs4_callback_procnum {
 enum nfs4_callback_opnum {
 	OP_CB_GETATTR = 3,
 	OP_CB_RECALL  = 4,
+/* Callback operations new to NFSv4.1 */
+	OP_CB_LAYOUTRECALL  = 5,
+	OP_CB_NOTIFY        = 6,
+	OP_CB_PUSH_DELEG    = 7,
+	OP_CB_RECALL_ANY    = 8,
+	OP_CB_RECALLABLE_OBJ_AVAIL = 9,
+	OP_CB_RECALL_SLOT   = 10,
+	OP_CB_SEQUENCE      = 11,
+	OP_CB_WANTS_CANCELLED = 12,
+	OP_CB_NOTIFY_LOCK   = 13,
+	OP_CB_NOTIFY_DEVICEID = 14,
 	OP_CB_ILLEGAL = 10044,
 };
 
 struct cb_compound_hdr_arg {
 	unsigned int taglen;
 	const char *tag;
-	unsigned int callback_ident;
+	unsigned int minorversion;
 	unsigned nops;
 };
 
@@ -59,16 +70,59 @@ struct cb_recallargs {
 	uint32_t truncate;
 };
 
+#if defined(CONFIG_NFS_V4_1)
+
+struct referring_call {
+	uint32_t			rc_sequenceid;
+	uint32_t			rc_slotid;
+};
+
+struct referring_call_list {
+	struct nfs4_sessionid		rcl_sessionid;
+	uint32_t			rcl_nrefcalls;
+	struct referring_call 		*rcl_refcalls;
+};
+
+struct cb_sequenceargs {
+	struct sockaddr			*csa_addr;
+	struct nfs4_sessionid		csa_sessionid;
+	uint32_t			csa_sequenceid;
+	uint32_t			csa_slotid;
+	uint32_t			csa_highestslotid;
+	uint32_t			csa_cachethis;
+	uint32_t			csa_nrclists;
+	struct referring_call_list	*csa_rclists;
+};
+
+struct cb_sequenceres {
+	__be32				csr_status;
+	struct nfs4_sessionid		csr_sessionid;
+	uint32_t			csr_sequenceid;
+	uint32_t			csr_slotid;
+	uint32_t			csr_highestslotid;
+	uint32_t			csr_target_highestslotid;
+};
+
+extern unsigned nfs4_callback_sequence(struct cb_sequenceargs *args,
+				       struct cb_sequenceres *res);
+
+#endif /* CONFIG_NFS_V4_1 */
+
 extern __be32 nfs4_callback_getattr(struct cb_getattrargs *args, struct cb_getattrres *res);
 extern __be32 nfs4_callback_recall(struct cb_recallargs *args, void *dummy);
 
 #ifdef CONFIG_NFS_V4
-extern int nfs_callback_up(void);
-extern void nfs_callback_down(void);
-#else
-#define nfs_callback_up()	(0)
-#define nfs_callback_down()	do {} while(0)
-#endif
+extern int nfs_callback_up(u32 minorversion, struct rpc_xprt *xprt);
+extern void nfs_callback_down(int minorversion);
+#endif /* CONFIG_NFS_V4 */
+
+/*
+ * nfs41: Callbacks are expected to not cause substantial latency,
+ * so we limit their concurrency to 1 by setting up the maximum number
+ * of slots for the backchannel.
+ */
+#define NFS41_BC_MIN_CALLBACKS 1
+#define NFS41_BC_MAX_CALLBACKS 1
 
 extern unsigned int nfs_callback_set_tcpport;
 extern unsigned short nfs_callback_tcpport;

fs/nfs/callback_proc.c

@@ -101,3 +101,130 @@ out:
 	dprintk("%s: exit with status = %d\n", __func__, ntohl(res));
 	return res;
 }
+
+#if defined(CONFIG_NFS_V4_1)
+
+/*
+ * Validate the sequenceID sent by the server.
+ * Return success if the sequenceID is one more than what we last saw on
+ * this slot, accounting for wraparound.  Increments the slot's sequence.
+ *
+ * We don't yet implement a duplicate request cache, so at this time
+ * we will log replays, and process them as if we had not seen them before,
+ * but we don't bump the sequence in the slot.  Not too worried about it,
+ * since we only currently implement idempotent callbacks anyway.
+ *
+ * We have a single slot backchannel at this time, so we don't bother
+ * checking the used_slots bit array on the table.  The lower layer guarantees
+ * a single outstanding callback request at a time.
+ */
+static int
+validate_seqid(struct nfs4_slot_table *tbl, u32 slotid, u32 seqid)
+{
+	struct nfs4_slot *slot;
+
+	dprintk("%s enter. slotid %d seqid %d\n",
+		__func__, slotid, seqid);
+
+	if (slotid > NFS41_BC_MAX_CALLBACKS)
+		return htonl(NFS4ERR_BADSLOT);
+
+	slot = tbl->slots + slotid;
+	dprintk("%s slot table seqid: %d\n", __func__, slot->seq_nr);
+
+	/* Normal */
+	if (likely(seqid == slot->seq_nr + 1)) {
+		slot->seq_nr++;
+		return htonl(NFS4_OK);
+	}
+
+	/* Replay */
+	if (seqid == slot->seq_nr) {
+		dprintk("%s seqid %d is a replay - no DRC available\n",
+			__func__, seqid);
+		return htonl(NFS4_OK);
+	}
+
+	/* Wraparound */
+	if (seqid == 1 && (slot->seq_nr + 1) == 0) {
+		slot->seq_nr = 1;
+		return htonl(NFS4_OK);
+	}
+
+	/* Misordered request */
+	return htonl(NFS4ERR_SEQ_MISORDERED);
+}
+
+/*
+ * Returns a pointer to a held 'struct nfs_client' that matches the server's
+ * address, major version number, and session ID.  It is the caller's
+ * responsibility to release the returned reference.
+ *
+ * Returns NULL if there are no connections with sessions, or if no session
+ * matches the one of interest.
+ */
+ static struct nfs_client *find_client_with_session(
+	const struct sockaddr *addr, u32 nfsversion,
+	struct nfs4_sessionid *sessionid)
+{
+	struct nfs_client *clp;
+
+	clp = nfs_find_client(addr, 4);
+	if (clp == NULL)
+		return NULL;
+
+	do {
+		struct nfs_client *prev = clp;
+
+		if (clp->cl_session != NULL) {
+			if (memcmp(clp->cl_session->sess_id.data,
+					sessionid->data,
+					NFS4_MAX_SESSIONID_LEN) == 0) {
+				/* Returns a held reference to clp */
+				return clp;
+			}
+		}
+		clp = nfs_find_client_next(prev);
+		nfs_put_client(prev);
+	} while (clp != NULL);
+
+	return NULL;
+}
+
+/* FIXME: referring calls should be processed */
+unsigned nfs4_callback_sequence(struct cb_sequenceargs *args,
+				struct cb_sequenceres *res)
+{
+	struct nfs_client *clp;
+	int i, status;
+
+	for (i = 0; i < args->csa_nrclists; i++)
+		kfree(args->csa_rclists[i].rcl_refcalls);
+	kfree(args->csa_rclists);
+
+	status = htonl(NFS4ERR_BADSESSION);
+	clp = find_client_with_session(args->csa_addr, 4, &args->csa_sessionid);
+	if (clp == NULL)
+		goto out;
+
+	status = validate_seqid(&clp->cl_session->bc_slot_table,
+				args->csa_slotid, args->csa_sequenceid);
+	if (status)
+		goto out_putclient;
+
+	memcpy(&res->csr_sessionid, &args->csa_sessionid,
+	       sizeof(res->csr_sessionid));
+	res->csr_sequenceid = args->csa_sequenceid;
+	res->csr_slotid = args->csa_slotid;
+	res->csr_highestslotid = NFS41_BC_MAX_CALLBACKS - 1;
+	res->csr_target_highestslotid = NFS41_BC_MAX_CALLBACKS - 1;
+
+out_putclient:
+	nfs_put_client(clp);
+out:
+	dprintk("%s: exit with status = %d\n", __func__, ntohl(status));
+	res->csr_status = status;
+	return res->csr_status;
+}
+
+#endif /* CONFIG_NFS_V4_1 */

fs/nfs/callback_xdr.c

@@ -20,6 +20,11 @@
 				2 + 2 + 3 + 3)
 #define CB_OP_RECALL_RES_MAXSZ	(CB_OP_HDR_RES_MAXSZ)
 
+#if defined(CONFIG_NFS_V4_1)
+#define CB_OP_SEQUENCE_RES_MAXSZ	(CB_OP_HDR_RES_MAXSZ + \
+					4 + 1 + 3)
+#endif /* CONFIG_NFS_V4_1 */
+
 #define NFSDBG_FACILITY NFSDBG_CALLBACK
 
 typedef __be32 (*callback_process_op_t)(void *, void *);
@@ -132,7 +137,6 @@ static __be32 decode_stateid(struct xdr_stream *xdr, nfs4_stateid *stateid)
 static __be32 decode_compound_hdr_arg(struct xdr_stream *xdr, struct cb_compound_hdr_arg *hdr)
 {
 	__be32 *p;
-	unsigned int minor_version;
 	__be32 status;
 
 	status = decode_string(xdr, &hdr->taglen, &hdr->tag);
@@ -147,15 +151,19 @@ static __be32 decode_compound_hdr_arg(struct xdr_stream *xdr, struct cb_compound
 	p = read_buf(xdr, 12);
 	if (unlikely(p == NULL))
 		return htonl(NFS4ERR_RESOURCE);
-	minor_version = ntohl(*p++);
-	/* Check minor version is zero. */
-	if (minor_version != 0) {
-		printk(KERN_WARNING "%s: NFSv4 server callback with illegal minor version %u!\n",
-				__func__, minor_version);
+	hdr->minorversion = ntohl(*p++);
+	/* Check minor version is zero or one. */
+	if (hdr->minorversion <= 1) {
+		p++;	/* skip callback_ident */
+	} else {
+		printk(KERN_WARNING "%s: NFSv4 server callback with "
+			"illegal minor version %u!\n",
+			__func__, hdr->minorversion);
 		return htonl(NFS4ERR_MINOR_VERS_MISMATCH);
 	}
-	hdr->callback_ident = ntohl(*p++);
 	hdr->nops = ntohl(*p);
+	dprintk("%s: minorversion %d nops %d\n", __func__,
+		hdr->minorversion, hdr->nops);
 	return 0;
 }
 
@@ -204,6 +212,122 @@ out:
 	return status;
 }
 
+#if defined(CONFIG_NFS_V4_1)
+
+static unsigned decode_sessionid(struct xdr_stream *xdr,
+				 struct nfs4_sessionid *sid)
+{
+	uint32_t *p;
+	int len = NFS4_MAX_SESSIONID_LEN;
+
+	p = read_buf(xdr, len);
+	if (unlikely(p == NULL))
+		return htonl(NFS4ERR_RESOURCE);;
+
+	memcpy(sid->data, p, len);
+	return 0;
+}
+
+static unsigned decode_rc_list(struct xdr_stream *xdr,
+			       struct referring_call_list *rc_list)
+{
+	uint32_t *p;
+	int i;
+	unsigned status;
+
+	status = decode_sessionid(xdr, &rc_list->rcl_sessionid);
+	if (status)
+		goto out;
+
+	status = htonl(NFS4ERR_RESOURCE);
+	p = read_buf(xdr, sizeof(uint32_t));
+	if (unlikely(p == NULL))
+		goto out;
+
+	rc_list->rcl_nrefcalls = ntohl(*p++);
+	if (rc_list->rcl_nrefcalls) {
+		p = read_buf(xdr,
+			     rc_list->rcl_nrefcalls * 2 * sizeof(uint32_t));
+		if (unlikely(p == NULL))
+			goto out;
+		rc_list->rcl_refcalls = kmalloc(rc_list->rcl_nrefcalls *
+						sizeof(*rc_list->rcl_refcalls),
+						GFP_KERNEL);
+		if (unlikely(rc_list->rcl_refcalls == NULL))
+			goto out;
+		for (i = 0; i < rc_list->rcl_nrefcalls; i++) {
+			rc_list->rcl_refcalls[i].rc_sequenceid = ntohl(*p++);
+			rc_list->rcl_refcalls[i].rc_slotid = ntohl(*p++);
+		}
+	}
+	status = 0;
+
+out:
+	return status;
+}
+
+static unsigned decode_cb_sequence_args(struct svc_rqst *rqstp,
+					struct xdr_stream *xdr,
+					struct cb_sequenceargs *args)
+{
+	uint32_t *p;
+	int i;
+	unsigned status;
+
+	status = decode_sessionid(xdr, &args->csa_sessionid);
+	if (status)
+		goto out;
+
+	status = htonl(NFS4ERR_RESOURCE);
+	p = read_buf(xdr, 5 * sizeof(uint32_t));
+	if (unlikely(p == NULL))
+		goto out;
+
+	args->csa_addr = svc_addr(rqstp);
+	args->csa_sequenceid = ntohl(*p++);
+	args->csa_slotid = ntohl(*p++);
+	args->csa_highestslotid = ntohl(*p++);
+	args->csa_cachethis = ntohl(*p++);
+	args->csa_nrclists = ntohl(*p++);
+	args->csa_rclists = NULL;
+	if (args->csa_nrclists) {
+		args->csa_rclists = kmalloc(args->csa_nrclists *
+					    sizeof(*args->csa_rclists),
+					    GFP_KERNEL);
+		if (unlikely(args->csa_rclists == NULL))
+			goto out;
+
+		for (i = 0; i < args->csa_nrclists; i++) {
+			status = decode_rc_list(xdr, &args->csa_rclists[i]);
+			if (status)
+				goto out_free;
+		}
+	}
+	status = 0;
+
+	dprintk("%s: sessionid %x:%x:%x:%x sequenceid %u slotid %u "
+		"highestslotid %u cachethis %d nrclists %u\n",
+		__func__,
+		((u32 *)&args->csa_sessionid)[0],
+		((u32 *)&args->csa_sessionid)[1],
+		((u32 *)&args->csa_sessionid)[2],
+		((u32 *)&args->csa_sessionid)[3],
+		args->csa_sequenceid, args->csa_slotid,
+		args->csa_highestslotid, args->csa_cachethis,
+		args->csa_nrclists);
+out:
+	dprintk("%s: exit with status = %d\n", __func__, ntohl(status));
+	return status;
+
+out_free:
+	for (i = 0; i < args->csa_nrclists; i++)
+		kfree(args->csa_rclists[i].rcl_refcalls);
+	kfree(args->csa_rclists);
+	goto out;
+}
+
+#endif /* CONFIG_NFS_V4_1 */
+
 static __be32 encode_string(struct xdr_stream *xdr, unsigned int len, const char *str)
 {
 	__be32 *p;
@@ -353,31 +477,134 @@ out:
 	return status;
 }
 
-static __be32 process_op(struct svc_rqst *rqstp,
+#if defined(CONFIG_NFS_V4_1)
+
+static unsigned encode_sessionid(struct xdr_stream *xdr,
+				 const struct nfs4_sessionid *sid)
+{
+	uint32_t *p;
+	int len = NFS4_MAX_SESSIONID_LEN;
+
+	p = xdr_reserve_space(xdr, len);
+	if (unlikely(p == NULL))
+		return htonl(NFS4ERR_RESOURCE);
+
+	memcpy(p, sid, len);
+	return 0;
+}
+
+static unsigned encode_cb_sequence_res(struct svc_rqst *rqstp,
+				       struct xdr_stream *xdr,
+				       const struct cb_sequenceres *res)
+{
+	uint32_t *p;
+	unsigned status = res->csr_status;
+
+	if (unlikely(status != 0))
+		goto out;
+
+	encode_sessionid(xdr, &res->csr_sessionid);
+
+	p = xdr_reserve_space(xdr, 4 * sizeof(uint32_t));
+	if (unlikely(p == NULL))
+		return htonl(NFS4ERR_RESOURCE);
+
+	*p++ = htonl(res->csr_sequenceid);
+	*p++ = htonl(res->csr_slotid);
+	*p++ = htonl(res->csr_highestslotid);
+	*p++ = htonl(res->csr_target_highestslotid);
+out:
+	dprintk("%s: exit with status = %d\n", __func__, ntohl(status));
+	return status;
+}
+
+static __be32
+preprocess_nfs41_op(int nop, unsigned int op_nr, struct callback_op **op)
+{
+	if (op_nr == OP_CB_SEQUENCE) {
+		if (nop != 0)
+			return htonl(NFS4ERR_SEQUENCE_POS);
+	} else {
+		if (nop == 0)
+			return htonl(NFS4ERR_OP_NOT_IN_SESSION);
+	}
+
+	switch (op_nr) {
+	case OP_CB_GETATTR:
+	case OP_CB_RECALL:
+	case OP_CB_SEQUENCE:
+		*op = &callback_ops[op_nr];
+		break;
+
+	case OP_CB_LAYOUTRECALL:
+	case OP_CB_NOTIFY_DEVICEID:
+	case OP_CB_NOTIFY:
+	case OP_CB_PUSH_DELEG:
+	case OP_CB_RECALL_ANY:
+	case OP_CB_RECALLABLE_OBJ_AVAIL:
+	case OP_CB_RECALL_SLOT:
+	case OP_CB_WANTS_CANCELLED:
+	case OP_CB_NOTIFY_LOCK:
+		return htonl(NFS4ERR_NOTSUPP);
+
+	default:
+		return htonl(NFS4ERR_OP_ILLEGAL);
+	}
+
+	return htonl(NFS_OK);
+}
+
+#else /* CONFIG_NFS_V4_1 */
+
+static __be32
+preprocess_nfs41_op(int nop, unsigned int op_nr, struct callback_op **op)
+{
+	return htonl(NFS4ERR_MINOR_VERS_MISMATCH);
+}
+
+#endif /* CONFIG_NFS_V4_1 */
+
+static __be32
+preprocess_nfs4_op(unsigned int op_nr, struct callback_op **op)
+{
+	switch (op_nr) {
+	case OP_CB_GETATTR:
+	case OP_CB_RECALL:
+		*op = &callback_ops[op_nr];
+		break;
+	default:
+		return htonl(NFS4ERR_OP_ILLEGAL);
+	}
+
+	return htonl(NFS_OK);
+}
+
+static __be32 process_op(uint32_t minorversion, int nop,
+		struct svc_rqst *rqstp,
 		struct xdr_stream *xdr_in, void *argp,
 		struct xdr_stream *xdr_out, void *resp)
 {
 	struct callback_op *op = &callback_ops[0];
 	unsigned int op_nr = OP_CB_ILLEGAL;
-	__be32 status = 0;
+	__be32 status;
 	long maxlen;
 	__be32 res;
 
 	dprintk("%s: start\n", __func__);
 	status = decode_op_hdr(xdr_in, &op_nr);
-	if (likely(status == 0)) {
-		switch (op_nr) {
-			case OP_CB_GETATTR:
-			case OP_CB_RECALL:
-				op = &callback_ops[op_nr];
-				break;
-			default:
-				op_nr = OP_CB_ILLEGAL;
-				op = &callback_ops[0];
-				status = htonl(NFS4ERR_OP_ILLEGAL);
-		}
+	if (unlikely(status)) {
+		status = htonl(NFS4ERR_OP_ILLEGAL);
+		goto out;
 	}
 
+	dprintk("%s: minorversion=%d nop=%d op_nr=%u\n",
+		__func__, minorversion, nop, op_nr);
+
+	status = minorversion ? preprocess_nfs41_op(nop, op_nr, &op) :
+				preprocess_nfs4_op(op_nr, &op);
+	if (status == htonl(NFS4ERR_OP_ILLEGAL))
+		op_nr = OP_CB_ILLEGAL;
+out:
 	maxlen = xdr_out->end - xdr_out->p;
 	if (maxlen > 0 && maxlen < PAGE_SIZE) {
 		if (likely(status == 0 && op->decode_args != NULL))
@@ -425,7 +652,8 @@ static __be32 nfs4_callback_compound(struct svc_rqst *rqstp, void *argp, void *r
 		return rpc_system_err;
 
 	while (status == 0 && nops != hdr_arg.nops) {
-		status = process_op(rqstp, &xdr_in, argp, &xdr_out, resp);
+		status = process_op(hdr_arg.minorversion, nops,
+				    rqstp, &xdr_in, argp, &xdr_out, resp);
 		nops++;
 	}
 
@@ -452,7 +680,15 @@ static struct callback_op callback_ops[] = {
 		.process_op = (callback_process_op_t)nfs4_callback_recall,
 		.decode_args = (callback_decode_arg_t)decode_recall_args,
 		.res_maxsize = CB_OP_RECALL_RES_MAXSZ,
-	}
+	},
+#if defined(CONFIG_NFS_V4_1)
+	[OP_CB_SEQUENCE] = {
+		.process_op = (callback_process_op_t)nfs4_callback_sequence,
+		.decode_args = (callback_decode_arg_t)decode_cb_sequence_args,
+		.encode_res = (callback_encode_res_t)encode_cb_sequence_res,
+		.res_maxsize = CB_OP_SEQUENCE_RES_MAXSZ,
+	},
+#endif /* CONFIG_NFS_V4_1 */
 };
 
 /*

fs/nfs/client.c

@@ -37,6 +37,7 @@
 #include <linux/in6.h>
 #include <net/ipv6.h>
 #include <linux/nfs_xdr.h>
+#include <linux/sunrpc/bc_xprt.h>
 
 #include <asm/system.h>
 
@@ -102,6 +103,7 @@ struct nfs_client_initdata {
 	size_t addrlen;
 	const struct nfs_rpc_ops *rpc_ops;
 	int proto;
+	u32 minorversion;
 };
 
 /*
@@ -114,18 +116,13 @@ static struct nfs_client *nfs_alloc_client(const struct nfs_client_initdata *cl_
 {
 	struct nfs_client *clp;
 	struct rpc_cred *cred;
+	int err = -ENOMEM;
 
 	if ((clp = kzalloc(sizeof(*clp), GFP_KERNEL)) == NULL)
 		goto error_0;
 
 	clp->rpc_ops = cl_init->rpc_ops;
 
-	if (cl_init->rpc_ops->version == 4) {
-		if (nfs_callback_up() < 0)
-			goto error_2;
-		__set_bit(NFS_CS_CALLBACK, &clp->cl_res_state);
-	}
-
 	atomic_set(&clp->cl_count, 1);
 	clp->cl_cons_state = NFS_CS_INITING;
 
@@ -133,9 +130,10 @@ static struct nfs_client *nfs_alloc_client(const struct nfs_client_initdata *cl_
 	clp->cl_addrlen = cl_init->addrlen;
 
 	if (cl_init->hostname) {
+		err = -ENOMEM;
 		clp->cl_hostname = kstrdup(cl_init->hostname, GFP_KERNEL);
 		if (!clp->cl_hostname)
-			goto error_3;
+			goto error_cleanup;
 	}
 
 	INIT_LIST_HEAD(&clp->cl_superblocks);
@@ -150,6 +148,7 @@ static struct nfs_client *nfs_alloc_client(const struct nfs_client_initdata *cl_
 	rpc_init_wait_queue(&clp->cl_rpcwaitq, "NFS client");
 	clp->cl_boot_time = CURRENT_TIME;
 	clp->cl_state = 1 << NFS4CLNT_LEASE_EXPIRED;
+	clp->cl_minorversion = cl_init->minorversion;
 #endif
 	cred = rpc_lookup_machine_cred();
 	if (!IS_ERR(cred))
@@ -159,13 +158,10 @@ static struct nfs_client *nfs_alloc_client(const struct nfs_client_initdata *cl_
 
 	return clp;
 
-error_3:
-	if (__test_and_clear_bit(NFS_CS_CALLBACK, &clp->cl_res_state))
-		nfs_callback_down();
-error_2:
+error_cleanup:
 	kfree(clp);
 error_0:
-	return NULL;
+	return ERR_PTR(err);
 }
 
 static void nfs4_shutdown_client(struct nfs_client *clp)
@@ -181,6 +177,35 @@ static void nfs4_shutdown_client(struct nfs_client *clp)
 #endif
 }
 
+/*
+ * Destroy the NFS4 callback service
+ */
+static void nfs4_destroy_callback(struct nfs_client *clp)
+{
+#ifdef CONFIG_NFS_V4
+	if (__test_and_clear_bit(NFS_CS_CALLBACK, &clp->cl_res_state))
+		nfs_callback_down(clp->cl_minorversion);
+#endif /* CONFIG_NFS_V4 */
+}
+
+/*
+ * Clears/puts all minor version specific parts from an nfs_client struct
+ * reverting it to minorversion 0.
+ */
+static void nfs4_clear_client_minor_version(struct nfs_client *clp)
+{
+#ifdef CONFIG_NFS_V4_1
+	if (nfs4_has_session(clp)) {
+		nfs4_destroy_session(clp->cl_session);
+		clp->cl_session = NULL;
+	}
+
+	clp->cl_call_sync = _nfs4_call_sync;
+#endif /* CONFIG_NFS_V4_1 */
+
+	nfs4_destroy_callback(clp);
+}
+
 /*
  * Destroy a shared client record
  */
@@ -188,6 +213,7 @@ static void nfs_free_client(struct nfs_client *clp)
 {
 	dprintk("--> nfs_free_client(%u)\n", clp->rpc_ops->version);
 
+	nfs4_clear_client_minor_version(clp);
 	nfs4_shutdown_client(clp);
 
 	nfs_fscache_release_client_cookie(clp);
@@ -196,9 +222,6 @@ static void nfs_free_client(struct nfs_client *clp)
 	if (!IS_ERR(clp->cl_rpcclient))
 		rpc_shutdown_client(clp->cl_rpcclient);
 
-	if (__test_and_clear_bit(NFS_CS_CALLBACK, &clp->cl_res_state))
-		nfs_callback_down();
-
 	if (clp->cl_machine_cred != NULL)
 		put_rpccred(clp->cl_machine_cred);
 
@@ -347,7 +370,8 @@ struct nfs_client *nfs_find_client(const struct sockaddr *addr, u32 nfsversion)
 		struct sockaddr *clap = (struct sockaddr *)&clp->cl_addr;
 
 		/* Don't match clients that failed to initialise properly */
-		if (clp->cl_cons_state != NFS_CS_READY)
+		if (!(clp->cl_cons_state == NFS_CS_READY ||
+		      clp->cl_cons_state == NFS_CS_SESSION_INITING))
 			continue;
 
 		/* Different NFS versions cannot share the same nfs_client */
@@ -420,7 +444,9 @@ static struct nfs_client *nfs_match_client(const struct nfs_client_initdata *dat
 
 		if (clp->cl_proto != data->proto)
 			continue;
-
+		/* Match nfsv4 minorversion */
+		if (clp->cl_minorversion != data->minorversion)
+			continue;
 		/* Match the full socket address */
 		if (!nfs_sockaddr_cmp(sap, clap))
 			continue;
@@ -456,9 +482,10 @@ static struct nfs_client *nfs_get_client(const struct nfs_client_initdata *cl_in
 		spin_unlock(&nfs_client_lock);
 
 		new = nfs_alloc_client(cl_init);
-	} while (new);
+	} while (!IS_ERR(new));
 
-	return ERR_PTR(-ENOMEM);
+	dprintk("--> nfs_get_client() = %ld [failed]\n", PTR_ERR(new));
+	return new;
 
 	/* install a new client and return with it unready */
 install_client:
@@ -478,7 +505,7 @@ found_client:
 		nfs_free_client(new);
 
 	error = wait_event_killable(nfs_client_active_wq,
-				clp->cl_cons_state != NFS_CS_INITING);
+				clp->cl_cons_state < NFS_CS_INITING);
 	if (error < 0) {
 		nfs_put_client(clp);
 		return ERR_PTR(-ERESTARTSYS);
@@ -499,12 +526,28 @@ found_client:
 /*
  * Mark a server as ready or failed
  */
-static void nfs_mark_client_ready(struct nfs_client *clp, int state)
+void nfs_mark_client_ready(struct nfs_client *clp, int state)
 {
 	clp->cl_cons_state = state;
 	wake_up_all(&nfs_client_active_wq);
 }
 
+/*
+ * With sessions, the client is not marked ready until after a
+ * successful EXCHANGE_ID and CREATE_SESSION.
+ *
+ * Map errors cl_cons_state errors to EPROTONOSUPPORT to indicate
+ * other versions of NFS can be tried.
+ */
+int nfs4_check_client_ready(struct nfs_client *clp)
+{
+	if (!nfs4_has_session(clp))
+		return 0;
+	if (clp->cl_cons_state < NFS_CS_READY)
+		return -EPROTONOSUPPORT;
+	return 0;
+}
+
 /*
  * Initialise the timeout values for a connection
  */
@@ -1049,6 +1092,61 @@ error:
 }
 
 #ifdef CONFIG_NFS_V4
+/*
+ * Initialize the NFS4 callback service
+ */
+static int nfs4_init_callback(struct nfs_client *clp)
+{
+	int error;
+
+	if (clp->rpc_ops->version == 4) {
+		if (nfs4_has_session(clp)) {
+			error = xprt_setup_backchannel(
+						clp->cl_rpcclient->cl_xprt,
+						NFS41_BC_MIN_CALLBACKS);
+			if (error < 0)
+				return error;
+		}
+
+		error = nfs_callback_up(clp->cl_minorversion,
+					clp->cl_rpcclient->cl_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)
+{
+	clp->cl_call_sync = _nfs4_call_sync;
+
+#if defined(CONFIG_NFS_V4_1)
+	if (clp->cl_minorversion) {
+		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;
+		clp->cl_call_sync = _nfs4_call_sync_session;
+	}
+#endif /* CONFIG_NFS_V4_1 */
+
+	return nfs4_init_callback(clp);
+}
+
 /*
  * Initialise an NFS4 client record
  */
@@ -1083,7 +1181,12 @@ static int nfs4_init_client(struct nfs_client *clp,
 	}
 	__set_bit(NFS_CS_IDMAP, &clp->cl_res_state);
 
-	nfs_mark_client_ready(clp, NFS_CS_READY);
+	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 0;
 
 error:
@@ -1101,7 +1204,8 @@ static int nfs4_set_client(struct nfs_server *server,
 		const size_t addrlen,
 		const char *ip_addr,
 		rpc_authflavor_t authflavour,
-		int proto, const struct rpc_timeout *timeparms)
+		int proto, const struct rpc_timeout *timeparms,
+		u32 minorversion)
 {
 	struct nfs_client_initdata cl_init = {
 		.hostname = hostname,
@@ -1109,6 +1213,7 @@ static int nfs4_set_client(struct nfs_server *server,
 		.addrlen = addrlen,
 		.rpc_ops = &nfs_v4_clientops,
 		.proto = proto,
+		.minorversion = minorversion,
 	};
 	struct nfs_client *clp;
 	int error;
@@ -1137,6 +1242,36 @@ error:
 	return error;
 }
 
+/*
+ * Initialize a session.
+ * Note: save the mount rsize and wsize for create_server negotiation.
+ */
+static void nfs4_init_session(struct nfs_client *clp,
+			      unsigned int wsize, unsigned int rsize)
+{
+#if defined(CONFIG_NFS_V4_1)
+	if (nfs4_has_session(clp)) {
+		clp->cl_session->fc_attrs.max_rqst_sz = wsize;
+		clp->cl_session->fc_attrs.max_resp_sz = rsize;
+	}
+#endif /* CONFIG_NFS_V4_1 */
+}
+
+/*
+ * 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
+	if (!nfs4_has_session(server->nfs_client))
+		return;
+	server->rsize = server->nfs_client->cl_session->fc_attrs.max_resp_sz;
+	server->wsize = server->nfs_client->cl_session->fc_attrs.max_rqst_sz;
+#endif /* CONFIG_NFS_V4_1 */
+}
+
 /*
  * Create a version 4 volume record
  */
@@ -1164,7 +1299,8 @@ static int nfs4_init_server(struct nfs_server *server,
 			data->client_address,
 			data->auth_flavors[0],
 			data->nfs_server.protocol,
-			&timeparms);
+			&timeparms,
+			data->minorversion);
 	if (error < 0)
 		goto error;
 
@@ -1214,6 +1350,8 @@ struct nfs_server *nfs4_create_server(const struct nfs_parsed_mount_data *data,
 	BUG_ON(!server->nfs_client->rpc_ops);
 	BUG_ON(!server->nfs_client->rpc_ops->file_inode_ops);
 
+	nfs4_init_session(server->nfs_client, server->wsize, server->rsize);
+
 	/* Probe the root fh to retrieve its FSID */
 	error = nfs4_path_walk(server, mntfh, data->nfs_server.export_path);
 	if (error < 0)
@@ -1224,6 +1362,8 @@ struct nfs_server *nfs4_create_server(const struct nfs_parsed_mount_data *data,
 		(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 error;
@@ -1282,7 +1422,8 @@ struct nfs_server *nfs4_create_referral_server(struct nfs_clone_mount *data,
 				parent_client->cl_ipaddr,
 				data->authflavor,
 				parent_server->client->cl_xprt->prot,
-				parent_server->client->cl_timeout);
+				parent_server->client->cl_timeout,
+				parent_client->cl_minorversion);
 	if (error < 0)
 		goto error;
 

fs/nfs/delegation.c

@@ -68,29 +68,26 @@ static int nfs_delegation_claim_locks(struct nfs_open_context *ctx, struct nfs4_
 {
 	struct inode *inode = state->inode;
 	struct file_lock *fl;
-	int status;
+	int status = 0;
+
+	if (inode->i_flock == NULL)
+		goto out;
 
+	/* Protect inode->i_flock using the BKL */
+	lock_kernel();
 	for (fl = inode->i_flock; fl != NULL; fl = fl->fl_next) {
 		if (!(fl->fl_flags & (FL_POSIX|FL_FLOCK)))
 			continue;
 		if (nfs_file_open_context(fl->fl_file) != ctx)
 			continue;
+		unlock_kernel();
 		status = nfs4_lock_delegation_recall(state, fl);
-		if (status >= 0)
-			continue;
-		switch (status) {
-			default:
-				printk(KERN_ERR "%s: unhandled error %d.\n",
-						__func__, status);
-			case -NFS4ERR_EXPIRED:
-				/* kill_proc(fl->fl_pid, SIGLOST, 1); */
-			case -NFS4ERR_STALE_CLIENTID:
-				nfs4_schedule_state_recovery(NFS_SERVER(inode)->nfs_client);
-				goto out_err;
-		}
+		if (status < 0)
+			goto out;
+		lock_kernel();
 	}
-	return 0;
-out_err:
+	unlock_kernel();
+out:
 	return status;
 }
 
@@ -268,7 +265,10 @@ static int __nfs_inode_return_delegation(struct inode *inode, struct nfs_delegat
 	struct nfs_inode *nfsi = NFS_I(inode);
 
 	nfs_msync_inode(inode);
-	/* Guard against new delegated open calls */
+	/*
+	 * Guard against new delegated open/lock/unlock calls and against
+	 * state recovery
+	 */
 	down_write(&nfsi->rwsem);
 	nfs_delegation_claim_opens(inode, &delegation->stateid);
 	up_write(&nfsi->rwsem);

fs/nfs/direct.c

@@ -259,6 +259,9 @@ static void nfs_direct_read_release(void *calldata)
 }
 
 static const struct rpc_call_ops nfs_read_direct_ops = {
+#if defined(CONFIG_NFS_V4_1)
+	.rpc_call_prepare = nfs_read_prepare,
+#endif /* CONFIG_NFS_V4_1 */
 	.rpc_call_done = nfs_direct_read_result,
 	.rpc_release = nfs_direct_read_release,
 };
@@ -535,6 +538,9 @@ static void nfs_direct_commit_release(void *calldata)
 }
 
 static const struct rpc_call_ops nfs_commit_direct_ops = {
+#if defined(CONFIG_NFS_V4_1)
+	.rpc_call_prepare = nfs_write_prepare,
+#endif /* CONFIG_NFS_V4_1 */
 	.rpc_call_done = nfs_direct_commit_result,
 	.rpc_release = nfs_direct_commit_release,
 };
@@ -673,6 +679,9 @@ out_unlock:
 }
 
 static const struct rpc_call_ops nfs_write_direct_ops = {
+#if defined(CONFIG_NFS_V4_1)
+	.rpc_call_prepare = nfs_write_prepare,
+#endif /* CONFIG_NFS_V4_1 */
 	.rpc_call_done = nfs_direct_write_result,
 	.rpc_release = nfs_direct_write_release,
 };

fs/nfs/file.c

@@ -48,6 +48,9 @@ static ssize_t nfs_file_splice_read(struct file *filp, loff_t *ppos,
 					size_t count, unsigned int flags);
 static ssize_t nfs_file_read(struct kiocb *, const struct iovec *iov,
 				unsigned long nr_segs, loff_t pos);
+static ssize_t nfs_file_splice_write(struct pipe_inode_info *pipe,
+					struct file *filp, loff_t *ppos,
+					size_t count, unsigned int flags);
 static ssize_t nfs_file_write(struct kiocb *, const struct iovec *iov,
 				unsigned long nr_segs, loff_t pos);
 static int  nfs_file_flush(struct file *, fl_owner_t id);
@@ -73,6 +76,7 @@ const struct file_operations nfs_file_operations = {
 	.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,
 };
@@ -587,12 +591,38 @@ 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)
+{
+	struct dentry *dentry = filp->f_path.dentry;
+	struct inode *inode = dentry->d_inode;
+	ssize_t ret;
+
+	dprintk("NFS splice_write(%s/%s, %lu@%llu)\n",
+		dentry->d_parent->d_name.name, dentry->d_name.name,
+		(unsigned long) count, (unsigned long long) *ppos);
+
+	/*
+	 * The combination of splice and an O_APPEND destination is disallowed.
+	 */
+
+	nfs_add_stats(inode, NFSIOS_NORMALWRITTENBYTES, count);
+
+	ret = generic_file_splice_write(pipe, filp, ppos, count, flags);
+	if (ret >= 0 && nfs_need_sync_write(filp, inode)) {
+		int err = nfs_do_fsync(nfs_file_open_context(filp), inode);
+		if (err < 0)
+			ret = err;
+	}
+	return ret;
+}
+
 static int do_getlk(struct file *filp, int cmd, struct file_lock *fl)
 {
 	struct inode *inode = filp->f_mapping->host;
 	int status = 0;
 
-	lock_kernel();
 	/* Try local locking first */
 	posix_test_lock(filp, fl);
 	if (fl->fl_type != F_UNLCK) {
@@ -608,7 +638,6 @@ static int do_getlk(struct file *filp, int cmd, struct file_lock *fl)
 
 	status = NFS_PROTO(inode)->lock(filp, cmd, fl);
 out:
-	unlock_kernel();
 	return status;
 out_noconflict:
 	fl->fl_type = F_UNLCK;
@@ -650,13 +679,11 @@ static int do_unlk(struct file *filp, int cmd, struct file_lock *fl)
 	 * 	If we're signalled while cleaning up locks on process exit, we
 	 * 	still need to complete the unlock.
 	 */
-	lock_kernel();
 	/* Use local locking if mounted with "-onolock" */
 	if (!(NFS_SERVER(inode)->flags & NFS_MOUNT_NONLM))
 		status = NFS_PROTO(inode)->lock(filp, cmd, fl);
 	else
 		status = do_vfs_lock(filp, fl);
-	unlock_kernel();
 	return status;
 }
 
@@ -673,13 +700,11 @@ static int do_setlk(struct file *filp, int cmd, struct file_lock *fl)
 	if (status != 0)
 		goto out;
 
-	lock_kernel();
 	/* Use local locking if mounted with "-onolock" */
 	if (!(NFS_SERVER(inode)->flags & NFS_MOUNT_NONLM))
 		status = NFS_PROTO(inode)->lock(filp, cmd, fl);
 	else
 		status = do_vfs_lock(filp, fl);
-	unlock_kernel();
 	if (status < 0)
 		goto out;
 	/*

fs/nfs/internal.h

@@ -2,6 +2,7 @@
  * NFS internal definitions
  */
 
+#include "nfs4_fs.h"
 #include <linux/mount.h>
 #include <linux/security.h>
 
@@ -17,6 +18,18 @@ struct nfs_string;
  */
 #define NFS_MAX_READAHEAD	(RPC_DEF_SLOT_TABLE - 1)
 
+/*
+ * Determine if sessions are in use.
+ */
+static inline int nfs4_has_session(const struct nfs_client *clp)
+{
+#ifdef CONFIG_NFS_V4_1
+	if (clp->cl_session)
+		return 1;
+#endif /* CONFIG_NFS_V4_1 */
+	return 0;
+}
+
 struct nfs_clone_mount {
 	const struct super_block *sb;
 	const struct dentry *dentry;
@@ -29,6 +42,12 @@ struct nfs_clone_mount {
 	rpc_authflavor_t authflavor;
 };
 
+/*
+ * Note: RFC 1813 doesn't limit the number of auth flavors that
+ * a server can return, so make something up.
+ */
+#define NFS_MAX_SECFLAVORS	(12)
+
 /*
  * In-kernel mount arguments
  */
@@ -44,6 +63,7 @@ struct nfs_parsed_mount_data {
 	unsigned int		auth_flavor_len;
 	rpc_authflavor_t	auth_flavors[1];
 	char			*client_address;
+	unsigned int		minorversion;
 	char			*fscache_uniq;
 
 	struct {
@@ -77,6 +97,8 @@ struct nfs_mount_request {
 	unsigned short		protocol;
 	struct nfs_fh		*fh;
 	int			noresvport;
+	unsigned int		*auth_flav_len;
+	rpc_authflavor_t	*auth_flavs;
 };
 
 extern int nfs_mount(struct nfs_mount_request *info);
@@ -99,6 +121,8 @@ extern void nfs_free_server(struct nfs_server *server);
 extern struct nfs_server *nfs_clone_server(struct nfs_server *,
 					   struct nfs_fh *,
 					   struct nfs_fattr *);
+extern void nfs_mark_client_ready(struct nfs_client *clp, int state);
+extern int nfs4_check_client_ready(struct nfs_client *clp);
 #ifdef CONFIG_PROC_FS
 extern int __init nfs_fs_proc_init(void);
 extern void nfs_fs_proc_exit(void);
@@ -146,6 +170,20 @@ extern __be32 * nfs_decode_dirent(__be32 *, struct nfs_entry *, int);
 extern struct rpc_procinfo nfs3_procedures[];
 extern __be32 *nfs3_decode_dirent(__be32 *, struct nfs_entry *, int);
 
+/* nfs4proc.c */
+static inline void nfs4_restart_rpc(struct rpc_task *task,
+				    const struct nfs_client *clp)
+{
+#ifdef CONFIG_NFS_V4_1
+	if (nfs4_has_session(clp) &&
+	    test_bit(NFS4CLNT_SESSION_SETUP, &clp->cl_state)) {
+		rpc_restart_call_prepare(task);
+		return;
+	}
+#endif /* CONFIG_NFS_V4_1 */
+	rpc_restart_call(task);
+}
+
 /* nfs4xdr.c */
 #ifdef CONFIG_NFS_V4
 extern __be32 *nfs4_decode_dirent(__be32 *p, struct nfs_entry *entry, int plus);
@@ -205,6 +243,38 @@ extern int nfs4_path_walk(struct nfs_server *server,
 			  const char *path);
 #endif
 
+/* read.c */
+extern void nfs_read_prepare(struct rpc_task *task, void *calldata);
+
+/* write.c */
+extern void nfs_write_prepare(struct rpc_task *task, void *calldata);
+
+/* nfs4proc.c */
+extern int _nfs4_call_sync(struct nfs_server *server,
+			   struct rpc_message *msg,
+			   struct nfs4_sequence_args *args,
+			   struct nfs4_sequence_res *res,
+			   int cache_reply);
+extern int _nfs4_call_sync_session(struct nfs_server *server,
+				   struct rpc_message *msg,
+				   struct nfs4_sequence_args *args,
+				   struct nfs4_sequence_res *res,
+				   int cache_reply);
+
+#ifdef CONFIG_NFS_V4_1
+extern void nfs41_sequence_free_slot(const struct nfs_client *,
+				     struct nfs4_sequence_res *res);
+#endif /* CONFIG_NFS_V4_1 */
+
+static inline void nfs4_sequence_free_slot(const struct nfs_client *clp,
+					   struct nfs4_sequence_res *res)
+{
+#ifdef CONFIG_NFS_V4_1
+	if (nfs4_has_session(clp))
+		nfs41_sequence_free_slot(clp, res);
+#endif /* CONFIG_NFS_V4_1 */
+}
+
 /*
  * Determine the device name as a string
  */

fs/nfs/mount_clnt.c

@@ -20,8 +20,116 @@
 # define NFSDBG_FACILITY	NFSDBG_MOUNT
 #endif
 
+/*
+ * Defined by RFC 1094, section A.3; and RFC 1813, section 5.1.4
+ */
+#define MNTPATHLEN		(1024)
+
+/*
+ * XDR data type sizes
+ */
+#define encode_dirpath_sz	(1 + XDR_QUADLEN(MNTPATHLEN))
+#define MNT_status_sz		(1)
+#define MNT_fhs_status_sz	(1)
+#define MNT_fhandle_sz		XDR_QUADLEN(NFS2_FHSIZE)
+#define MNT_fhandle3_sz		(1 + XDR_QUADLEN(NFS3_FHSIZE))
+#define MNT_authflav3_sz	(1 + NFS_MAX_SECFLAVORS)
+
+/*
+ * XDR argument and result sizes
+ */
+#define MNT_enc_dirpath_sz	encode_dirpath_sz
+#define MNT_dec_mountres_sz	(MNT_status_sz + MNT_fhandle_sz)
+#define MNT_dec_mountres3_sz	(MNT_status_sz + MNT_fhandle_sz + \
+				 MNT_authflav3_sz)
+
+/*
+ * Defined by RFC 1094, section A.5
+ */
+enum {
+	MOUNTPROC_NULL		= 0,
+	MOUNTPROC_MNT		= 1,
+	MOUNTPROC_DUMP		= 2,
+	MOUNTPROC_UMNT		= 3,
+	MOUNTPROC_UMNTALL	= 4,
+	MOUNTPROC_EXPORT	= 5,
+};
+
+/*
+ * Defined by RFC 1813, section 5.2
+ */
+enum {
+	MOUNTPROC3_NULL		= 0,
+	MOUNTPROC3_MNT		= 1,
+	MOUNTPROC3_DUMP		= 2,
+	MOUNTPROC3_UMNT		= 3,
+	MOUNTPROC3_UMNTALL	= 4,
+	MOUNTPROC3_EXPORT	= 5,
+};
+
 static struct rpc_program	mnt_program;
 
+/*
+ * Defined by OpenGroup XNFS Version 3W, chapter 8
+ */
+enum mountstat {
+	MNT_OK			= 0,
+	MNT_EPERM		= 1,
+	MNT_ENOENT		= 2,
+	MNT_EACCES		= 13,
+	MNT_EINVAL		= 22,
+};
+
+static struct {
+	u32 status;
+	int errno;
+} mnt_errtbl[] = {
+	{ .status = MNT_OK,			.errno = 0,		},
+	{ .status = MNT_EPERM,			.errno = -EPERM,	},
+	{ .status = MNT_ENOENT,			.errno = -ENOENT,	},
+	{ .status = MNT_EACCES,			.errno = -EACCES,	},
+	{ .status = MNT_EINVAL,			.errno = -EINVAL,	},
+};
+
+/*
+ * Defined by RFC 1813, section 5.1.5
+ */
+enum mountstat3 {
+	MNT3_OK			= 0,		/* no error */
+	MNT3ERR_PERM		= 1,		/* Not owner */
+	MNT3ERR_NOENT		= 2,		/* No such file or directory */
+	MNT3ERR_IO		= 5,		/* I/O error */
+	MNT3ERR_ACCES		= 13,		/* Permission denied */
+	MNT3ERR_NOTDIR		= 20,		/* Not a directory */
+	MNT3ERR_INVAL		= 22,		/* Invalid argument */
+	MNT3ERR_NAMETOOLONG	= 63,		/* Filename too long */
+	MNT3ERR_NOTSUPP		= 10004,	/* Operation not supported */
+	MNT3ERR_SERVERFAULT	= 10006,	/* A failure on the server */
+};
+
+static struct {
+	u32 status;
+	int errno;
+} mnt3_errtbl[] = {
+	{ .status = MNT3_OK,			.errno = 0,		},
+	{ .status = MNT3ERR_PERM,		.errno = -EPERM,	},
+	{ .status = MNT3ERR_NOENT,		.errno = -ENOENT,	},
+	{ .status = MNT3ERR_IO,			.errno = -EIO,		},
+	{ .status = MNT3ERR_ACCES,		.errno = -EACCES,	},
+	{ .status = MNT3ERR_NOTDIR,		.errno = -ENOTDIR,	},
+	{ .status = MNT3ERR_INVAL,		.errno = -EINVAL,	},
+	{ .status = MNT3ERR_NAMETOOLONG,	.errno = -ENAMETOOLONG,	},
+	{ .status = MNT3ERR_NOTSUPP,		.errno = -ENOTSUPP,	},
+	{ .status = MNT3ERR_SERVERFAULT,	.errno = -ESERVERFAULT,	},
+};
+
+struct mountres {
+	int errno;
+	struct nfs_fh *fh;
+	unsigned int *auth_count;
+	rpc_authflavor_t *auth_flavors;
+};
+
 struct mnt_fhstatus {
 	u32 status;
 	struct nfs_fh *fh;
@@ -35,8 +143,10 @@ struct mnt_fhstatus {
  */
 int nfs_mount(struct nfs_mount_request *info)
 {
-	struct mnt_fhstatus	result = {
-		.fh		= info->fh
+	struct mountres	result = {
+		.fh		= info->fh,
+		.auth_count	= info->auth_flav_len,
+		.auth_flavors	= info->auth_flavs,
 	};
 	struct rpc_message msg	= {
 		.rpc_argp	= info->dirpath,
@@ -68,14 +178,14 @@ int nfs_mount(struct nfs_mount_request *info)
 	if (info->version == NFS_MNT3_VERSION)
 		msg.rpc_proc = &mnt_clnt->cl_procinfo[MOUNTPROC3_MNT];
 	else
-		msg.rpc_proc = &mnt_clnt->cl_procinfo[MNTPROC_MNT];
+		msg.rpc_proc = &mnt_clnt->cl_procinfo[MOUNTPROC_MNT];
 
 	status = rpc_call_sync(mnt_clnt, &msg, 0);
 	rpc_shutdown_client(mnt_clnt);
 
 	if (status < 0)
 		goto out_call_err;
-	if (result.status != 0)
+	if (result.errno != 0)
 		goto out_mnt_err;
 
 	dprintk("NFS: MNT request succeeded\n");
@@ -86,72 +196,215 @@ out:
 
 out_clnt_err:
 	status = PTR_ERR(mnt_clnt);
-	dprintk("NFS: failed to create RPC client, status=%d\n", status);
+	dprintk("NFS: failed to create MNT RPC client, status=%d\n", status);
 	goto out;
 
 out_call_err:
-	dprintk("NFS: failed to start MNT request, status=%d\n", status);
+	dprintk("NFS: MNT request failed, status=%d\n", status);
 	goto out;
 
 out_mnt_err:
-	dprintk("NFS: MNT server returned result %d\n", result.status);
-	status = nfs_stat_to_errno(result.status);
+	dprintk("NFS: MNT server returned result %d\n", result.errno);
+	status = result.errno;
 	goto out;
 }
 
 /*
  * XDR encode/decode functions for MOUNT
  */
-static int xdr_encode_dirpath(struct rpc_rqst *req, __be32 *p,
-			      const char *path)
+
+static int encode_mntdirpath(struct xdr_stream *xdr, const char *pathname)
+{
+	const u32 pathname_len = strlen(pathname);
+	__be32 *p;
+
+	if (unlikely(pathname_len > MNTPATHLEN))
+		return -EIO;
+
+	p = xdr_reserve_space(xdr, sizeof(u32) + pathname_len);
+	if (unlikely(p == NULL))
+		return -EIO;
+	xdr_encode_opaque(p, pathname, pathname_len);
+
+	return 0;
+}
+
+static int mnt_enc_dirpath(struct rpc_rqst *req, __be32 *p,
+			   const char *dirpath)
+{
+	struct xdr_stream xdr;
+
+	xdr_init_encode(&xdr, &req->rq_snd_buf, p);
+	return encode_mntdirpath(&xdr, dirpath);
+}
+
+/*
+ * RFC 1094: "A non-zero status indicates some sort of error.  In this
+ * case, the status is a UNIX error number."  This can be problematic
+ * if the server and client use different errno values for the same
+ * error.
+ *
+ * However, the OpenGroup XNFS spec provides a simple mapping that is
+ * independent of local errno values on the server and the client.
+ */
+static int decode_status(struct xdr_stream *xdr, struct mountres *res)
 {
-	p = xdr_encode_string(p, path);
+	unsigned int i;
+	u32 status;
+	__be32 *p;
+
+	p = xdr_inline_decode(xdr, sizeof(status));
+	if (unlikely(p == NULL))
+		return -EIO;
+	status = ntohl(*p);
 
-	req->rq_slen = xdr_adjust_iovec(req->rq_svec, p);
+	for (i = 0; i <= ARRAY_SIZE(mnt_errtbl); i++) {
+		if (mnt_errtbl[i].status == status) {
+			res->errno = mnt_errtbl[i].errno;
+			return 0;
+		}
+	}
+
+	dprintk("NFS: unrecognized MNT status code: %u\n", status);
+	res->errno = -EACCES;
 	return 0;
 }
 
-static int xdr_decode_fhstatus(struct rpc_rqst *req, __be32 *p,
-			       struct mnt_fhstatus *res)
+static int decode_fhandle(struct xdr_stream *xdr, struct mountres *res)
 {
 	struct nfs_fh *fh = res->fh;
+	__be32 *p;
+
+	p = xdr_inline_decode(xdr, NFS2_FHSIZE);
+	if (unlikely(p == NULL))
+		return -EIO;
+
+	fh->size = NFS2_FHSIZE;
+	memcpy(fh->data, p, NFS2_FHSIZE);
+	return 0;
+}
+
+static int mnt_dec_mountres(struct rpc_rqst *req, __be32 *p,
+			    struct mountres *res)
+{
+	struct xdr_stream xdr;
+	int status;
+
+	xdr_init_decode(&xdr, &req->rq_rcv_buf, p);
+
+	status = decode_status(&xdr, res);
+	if (unlikely(status != 0 || res->errno != 0))
+		return status;
+	return decode_fhandle(&xdr, res);
+}
+
+static int decode_fhs_status(struct xdr_stream *xdr, struct mountres *res)
+{
+	unsigned int i;
+	u32 status;
+	__be32 *p;
 
-	if ((res->status = ntohl(*p++)) == 0) {
-		fh->size = NFS2_FHSIZE;
-		memcpy(fh->data, p, NFS2_FHSIZE);
+	p = xdr_inline_decode(xdr, sizeof(status));
+	if (unlikely(p == NULL))
+		return -EIO;
+	status = ntohl(*p);
+
+	for (i = 0; i <= ARRAY_SIZE(mnt3_errtbl); i++) {
+		if (mnt3_errtbl[i].status == status) {
+			res->errno = mnt3_errtbl[i].errno;
+			return 0;
+		}
 	}
+
+	dprintk("NFS: unrecognized MNT3 status code: %u\n", status);
+	res->errno = -EACCES;
 	return 0;
 }
 
-static int xdr_decode_fhstatus3(struct rpc_rqst *req, __be32 *p,
-				struct mnt_fhstatus *res)
+static int decode_fhandle3(struct xdr_stream *xdr, struct mountres *res)
 {
 	struct nfs_fh *fh = res->fh;
-	unsigned size;
-
-	if ((res->status = ntohl(*p++)) == 0) {
-		size = ntohl(*p++);
-		if (size <= NFS3_FHSIZE && size != 0) {
-			fh->size = size;
-			memcpy(fh->data, p, size);
-		} else
-			res->status = -EBADHANDLE;
+	u32 size;
+	__be32 *p;
+
+	p = xdr_inline_decode(xdr, sizeof(size));
+	if (unlikely(p == NULL))
+		return -EIO;
+
+	size = ntohl(*p++);
+	if (size > NFS3_FHSIZE || size == 0)
+		return -EIO;
+
+	p = xdr_inline_decode(xdr, size);
+	if (unlikely(p == NULL))
+		return -EIO;
+
+	fh->size = size;
+	memcpy(fh->data, p, size);
+	return 0;
+}
+
+static int decode_auth_flavors(struct xdr_stream *xdr, struct mountres *res)
+{
+	rpc_authflavor_t *flavors = res->auth_flavors;
+	unsigned int *count = res->auth_count;
+	u32 entries, i;
+	__be32 *p;
+
+	if (*count == 0)
+		return 0;
+
+	p = xdr_inline_decode(xdr, sizeof(entries));
+	if (unlikely(p == NULL))
+		return -EIO;
+	entries = ntohl(*p);
+	dprintk("NFS: received %u auth flavors\n", entries);
+	if (entries > NFS_MAX_SECFLAVORS)
+		entries = NFS_MAX_SECFLAVORS;
+
+	p = xdr_inline_decode(xdr, sizeof(u32) * entries);
+	if (unlikely(p == NULL))
+		return -EIO;
+
+	if (entries > *count)
+		entries = *count;
+
+	for (i = 0; i < entries; i++) {
+		flavors[i] = ntohl(*p++);
+		dprintk("NFS:\tflavor %u: %d\n", i, flavors[i]);
 	}
+	*count = i;
+
 	return 0;
 }
 
-#define MNT_dirpath_sz		(1 + 256)
-#define MNT_fhstatus_sz		(1 + 8)
-#define MNT_fhstatus3_sz	(1 + 16)
+static int mnt_dec_mountres3(struct rpc_rqst *req, __be32 *p,
+			     struct mountres *res)
+{
+	struct xdr_stream xdr;
+	int status;
+
+	xdr_init_decode(&xdr, &req->rq_rcv_buf, p);
+
+	status = decode_fhs_status(&xdr, res);
+	if (unlikely(status != 0 || res->errno != 0))
+		return status;
+	status = decode_fhandle3(&xdr, res);
+	if (unlikely(status != 0)) {
+		res->errno = -EBADHANDLE;
+		return 0;
+	}
+	return decode_auth_flavors(&xdr, res);
+}
 
 static struct rpc_procinfo mnt_procedures[] = {
-	[MNTPROC_MNT] = {
-		.p_proc		= MNTPROC_MNT,
-		.p_encode	= (kxdrproc_t) xdr_encode_dirpath,
-		.p_decode	= (kxdrproc_t) xdr_decode_fhstatus,
-		.p_arglen	= MNT_dirpath_sz,
-		.p_replen	= MNT_fhstatus_sz,
-		.p_statidx	= MNTPROC_MNT,
+	[MOUNTPROC_MNT] = {
+		.p_proc		= MOUNTPROC_MNT,
+		.p_encode	= (kxdrproc_t)mnt_enc_dirpath,
+		.p_decode	= (kxdrproc_t)mnt_dec_mountres,
+		.p_arglen	= MNT_enc_dirpath_sz,
+		.p_replen	= MNT_dec_mountres_sz,
+		.p_statidx	= MOUNTPROC_MNT,
 		.p_name		= "MOUNT",
 	},
 };
@@ -159,10 +412,10 @@ static struct rpc_procinfo mnt_procedures[] = {
 static struct rpc_procinfo mnt3_procedures[] = {
 	[MOUNTPROC3_MNT] = {
 		.p_proc		= MOUNTPROC3_MNT,
-		.p_encode	= (kxdrproc_t) xdr_encode_dirpath,
-		.p_decode	= (kxdrproc_t) xdr_decode_fhstatus3,
-		.p_arglen	= MNT_dirpath_sz,
-		.p_replen	= MNT_fhstatus3_sz,
+		.p_encode	= (kxdrproc_t)mnt_enc_dirpath,
+		.p_decode	= (kxdrproc_t)mnt_dec_mountres3,
+		.p_arglen	= MNT_enc_dirpath_sz,
+		.p_replen	= MNT_dec_mountres3_sz,
 		.p_statidx	= MOUNTPROC3_MNT,
 		.p_name		= "MOUNT",
 	},

fs/nfs/nfs3acl.c

@@ -207,8 +207,6 @@ struct posix_acl *nfs3_proc_getacl(struct inode *inode, int type)
 	status = nfs_revalidate_inode(server, inode);
 	if (status < 0)
 		return ERR_PTR(status);
-	if (NFS_I(inode)->cache_validity & NFS_INO_INVALID_ACL)
-		nfs_zap_acl_cache(inode);
 	acl = nfs3_get_cached_acl(inode, type);
 	if (acl != ERR_PTR(-EAGAIN))
 		return acl;

fs/nfs/nfs4_fs.h

@@ -44,6 +44,7 @@ enum nfs4_client_state {
 	NFS4CLNT_RECLAIM_REBOOT,
 	NFS4CLNT_RECLAIM_NOGRACE,
 	NFS4CLNT_DELEGRETURN,
+	NFS4CLNT_SESSION_SETUP,
 };
 
 /*
@@ -177,6 +178,14 @@ struct nfs4_state_recovery_ops {
 	int state_flag_bit;
 	int (*recover_open)(struct nfs4_state_owner *, struct nfs4_state *);
 	int (*recover_lock)(struct nfs4_state *, struct file_lock *);
+	int (*establish_clid)(struct nfs_client *, struct rpc_cred *);
+	struct rpc_cred * (*get_clid_cred)(struct nfs_client *);
+};
+
+struct nfs4_state_maintenance_ops {
+	int (*sched_state_renewal)(struct nfs_client *, struct rpc_cred *);
+	struct rpc_cred * (*get_state_renewal_cred_locked)(struct nfs_client *);
+	int (*renew_lease)(struct nfs_client *, struct rpc_cred *);
 };
 
 extern const struct dentry_operations nfs4_dentry_operations;
@@ -193,6 +202,7 @@ extern int nfs4_proc_setclientid(struct nfs_client *, u32, unsigned short, struc
 extern int nfs4_proc_setclientid_confirm(struct nfs_client *, struct rpc_cred *);
 extern int nfs4_proc_async_renew(struct nfs_client *, struct rpc_cred *);
 extern int nfs4_proc_renew(struct nfs_client *, struct rpc_cred *);
+extern int nfs4_init_clientid(struct nfs_client *, struct rpc_cred *);
 extern int nfs4_do_close(struct path *path, struct nfs4_state *state, int wait);
 extern struct dentry *nfs4_atomic_open(struct inode *, struct dentry *, struct nameidata *);
 extern int nfs4_open_revalidate(struct inode *, struct dentry *, int, struct nameidata *);
@@ -200,8 +210,26 @@ extern int nfs4_server_capabilities(struct nfs_server *server, struct nfs_fh *fh
 extern int nfs4_proc_fs_locations(struct inode *dir, const struct qstr *name,
 		struct nfs4_fs_locations *fs_locations, struct page *page);
 
-extern struct nfs4_state_recovery_ops nfs4_reboot_recovery_ops;
-extern struct nfs4_state_recovery_ops nfs4_nograce_recovery_ops;
+extern struct nfs4_state_recovery_ops *nfs4_reboot_recovery_ops[];
+extern struct nfs4_state_recovery_ops *nfs4_nograce_recovery_ops[];
+#if defined(CONFIG_NFS_V4_1)
+extern int nfs4_setup_sequence(struct nfs_client *clp,
+		struct nfs4_sequence_args *args, struct nfs4_sequence_res *res,
+		int cache_reply, struct rpc_task *task);
+extern void nfs4_destroy_session(struct nfs4_session *session);
+extern struct nfs4_session *nfs4_alloc_session(struct nfs_client *clp);
+extern int nfs4_proc_create_session(struct nfs_client *, int reset);
+extern int nfs4_proc_destroy_session(struct nfs4_session *);
+#else /* CONFIG_NFS_v4_1 */
+static inline int nfs4_setup_sequence(struct nfs_client *clp,
+		struct nfs4_sequence_args *args, struct nfs4_sequence_res *res,
+		int cache_reply, struct rpc_task *task)
+{
+	return 0;
+}
+#endif /* CONFIG_NFS_V4_1 */
+
+extern struct nfs4_state_maintenance_ops *nfs4_state_renewal_ops[];
 
 extern const u32 nfs4_fattr_bitmap[2];
 extern const u32 nfs4_statfs_bitmap[2];
@@ -216,7 +244,12 @@ extern void nfs4_kill_renewd(struct nfs_client *);
 extern void nfs4_renew_state(struct work_struct *);
 
 /* nfs4state.c */
+struct rpc_cred *nfs4_get_setclientid_cred(struct nfs_client *clp);
 struct rpc_cred *nfs4_get_renew_cred_locked(struct nfs_client *clp);
+#if defined(CONFIG_NFS_V4_1)
+struct rpc_cred *nfs4_get_machine_cred_locked(struct nfs_client *clp);
+struct rpc_cred *nfs4_get_exchange_id_cred(struct nfs_client *clp);
+#endif /* CONFIG_NFS_V4_1 */
 
 extern struct nfs4_state_owner * nfs4_get_state_owner(struct nfs_server *, struct rpc_cred *);
 extern void nfs4_put_state_owner(struct nfs4_state_owner *);

fs/nfs/nfs4proc.c

@@ -48,11 +48,14 @@
 #include <linux/smp_lock.h>
 #include <linux/namei.h>
 #include <linux/mount.h>
+#include <linux/module.h>
+#include <linux/sunrpc/bc_xprt.h>
 
 #include "nfs4_fs.h"
 #include "delegation.h"
 #include "internal.h"
 #include "iostat.h"
+#include "callback.h"
 
 #define NFSDBG_FACILITY		NFSDBG_PROC
 
@@ -247,7 +250,25 @@ static int nfs4_handle_exception(const struct nfs_server *server, int errorcode,
 			ret = nfs4_wait_clnt_recover(clp);
 			if (ret == 0)
 				exception->retry = 1;
+#if !defined(CONFIG_NFS_V4_1)
 			break;
+#else /* !defined(CONFIG_NFS_V4_1) */
+			if (!nfs4_has_session(server->nfs_client))
+				break;
+			/* FALLTHROUGH */
+		case -NFS4ERR_BADSESSION:
+		case -NFS4ERR_BADSLOT:
+		case -NFS4ERR_BAD_HIGH_SLOT:
+		case -NFS4ERR_CONN_NOT_BOUND_TO_SESSION:
+		case -NFS4ERR_DEADSESSION:
+		case -NFS4ERR_SEQ_FALSE_RETRY:
+		case -NFS4ERR_SEQ_MISORDERED:
+			dprintk("%s ERROR: %d Reset session\n", __func__,
+				errorcode);
+			set_bit(NFS4CLNT_SESSION_SETUP, &clp->cl_state);
+			exception->retry = 1;
+			/* FALLTHROUGH */
+#endif /* !defined(CONFIG_NFS_V4_1) */
 		case -NFS4ERR_FILE_OPEN:
 		case -NFS4ERR_GRACE:
 		case -NFS4ERR_DELAY:
@@ -271,6 +292,353 @@ static void renew_lease(const struct nfs_server *server, unsigned long timestamp
 	spin_unlock(&clp->cl_lock);
 }
 
+#if defined(CONFIG_NFS_V4_1)
+
+/*
+ * nfs4_free_slot - free a slot and efficiently update slot table.
+ *
+ * freeing a slot is trivially done by clearing its respective bit
+ * in the bitmap.
+ * If the freed slotid equals highest_used_slotid we want to update it
+ * so that the server would be able to size down the slot table if needed,
+ * otherwise we know that the highest_used_slotid is still in use.
+ * When updating highest_used_slotid there may be "holes" in the bitmap
+ * so we need to scan down from highest_used_slotid to 0 looking for the now
+ * highest slotid in use.
+ * If none found, highest_used_slotid is set to -1.
+ */
+static void
+nfs4_free_slot(struct nfs4_slot_table *tbl, u8 free_slotid)
+{
+	int slotid = free_slotid;
+
+	spin_lock(&tbl->slot_tbl_lock);
+	/* clear used bit in bitmap */
+	__clear_bit(slotid, tbl->used_slots);
+
+	/* update highest_used_slotid when it is freed */
+	if (slotid == tbl->highest_used_slotid) {
+		slotid = find_last_bit(tbl->used_slots, tbl->max_slots);
+		if (slotid >= 0 && slotid < tbl->max_slots)
+			tbl->highest_used_slotid = slotid;
+		else
+			tbl->highest_used_slotid = -1;
+	}
+	rpc_wake_up_next(&tbl->slot_tbl_waitq);
+	spin_unlock(&tbl->slot_tbl_lock);
+	dprintk("%s: free_slotid %u highest_used_slotid %d\n", __func__,
+		free_slotid, tbl->highest_used_slotid);
+}
+
+void nfs41_sequence_free_slot(const struct nfs_client *clp,
+			      struct nfs4_sequence_res *res)
+{
+	struct nfs4_slot_table *tbl;
+
+	if (!nfs4_has_session(clp)) {
+		dprintk("%s: No session\n", __func__);
+		return;
+	}
+	tbl = &clp->cl_session->fc_slot_table;
+	if (res->sr_slotid == NFS4_MAX_SLOT_TABLE) {
+		dprintk("%s: No slot\n", __func__);
+		/* just wake up the next guy waiting since
+		 * we may have not consumed a slot after all */
+		rpc_wake_up_next(&tbl->slot_tbl_waitq);
+		return;
+	}
+	nfs4_free_slot(tbl, res->sr_slotid);
+	res->sr_slotid = NFS4_MAX_SLOT_TABLE;
+}
+
+static void nfs41_sequence_done(struct nfs_client *clp,
+				struct nfs4_sequence_res *res,
+				int rpc_status)
+{
+	unsigned long timestamp;
+	struct nfs4_slot_table *tbl;
+	struct nfs4_slot *slot;
+
+	/*
+	 * sr_status remains 1 if an RPC level error occurred. The server
+	 * may or may not have processed the sequence operation..
+	 * Proceed as if the server received and processed the sequence
+	 * operation.
+	 */
+	if (res->sr_status == 1)
+		res->sr_status = NFS_OK;
+
+	/* -ERESTARTSYS can result in skipping nfs41_sequence_setup */
+	if (res->sr_slotid == NFS4_MAX_SLOT_TABLE)
+		goto out;
+
+	tbl = &clp->cl_session->fc_slot_table;
+	slot = tbl->slots + res->sr_slotid;
+
+	if (res->sr_status == 0) {
+		/* Update the slot's sequence and clientid lease timer */
+		++slot->seq_nr;
+		timestamp = res->sr_renewal_time;
+		spin_lock(&clp->cl_lock);
+		if (time_before(clp->cl_last_renewal, timestamp))
+			clp->cl_last_renewal = timestamp;
+		spin_unlock(&clp->cl_lock);
+		return;
+	}
+out:
+	/* The session may be reset by one of the error handlers. */
+	dprintk("%s: Error %d free the slot \n", __func__, res->sr_status);
+	nfs41_sequence_free_slot(clp, res);
+}
+
+/*
+ * nfs4_find_slot - efficiently look for a free slot
+ *
+ * nfs4_find_slot looks for an unset bit in the used_slots bitmap.
+ * If found, we mark the slot as used, update the highest_used_slotid,
+ * and respectively set up the sequence operation args.
+ * The slot number is returned if found, or NFS4_MAX_SLOT_TABLE otherwise.
+ *
+ * Note: must be called with under the slot_tbl_lock.
+ */
+static u8
+nfs4_find_slot(struct nfs4_slot_table *tbl, struct rpc_task *task)
+{
+	int slotid;
+	u8 ret_id = NFS4_MAX_SLOT_TABLE;
+	BUILD_BUG_ON((u8)NFS4_MAX_SLOT_TABLE != (int)NFS4_MAX_SLOT_TABLE);
+
+	dprintk("--> %s used_slots=%04lx highest_used=%d max_slots=%d\n",
+		__func__, tbl->used_slots[0], tbl->highest_used_slotid,
+		tbl->max_slots);
+	slotid = find_first_zero_bit(tbl->used_slots, tbl->max_slots);
+	if (slotid >= tbl->max_slots)
+		goto out;
+	__set_bit(slotid, tbl->used_slots);
+	if (slotid > tbl->highest_used_slotid)
+		tbl->highest_used_slotid = slotid;
+	ret_id = slotid;
+out:
+	dprintk("<-- %s used_slots=%04lx highest_used=%d slotid=%d \n",
+		__func__, tbl->used_slots[0], tbl->highest_used_slotid, ret_id);
+	return ret_id;
+}
+
+static int nfs4_recover_session(struct nfs4_session *session)
+{
+	struct nfs_client *clp = session->clp;
+	int ret;
+
+	for (;;) {
+		ret = nfs4_wait_clnt_recover(clp);
+		if (ret != 0)
+				return ret;
+		if (!test_bit(NFS4CLNT_SESSION_SETUP, &clp->cl_state))
+			break;
+		nfs4_schedule_state_manager(clp);
+	}
+	return 0;
+}
+
+static int nfs41_setup_sequence(struct nfs4_session *session,
+				struct nfs4_sequence_args *args,
+				struct nfs4_sequence_res *res,
+				int cache_reply,
+				struct rpc_task *task)
+{
+	struct nfs4_slot *slot;
+	struct nfs4_slot_table *tbl;
+	int status = 0;
+	u8 slotid;
+
+	dprintk("--> %s\n", __func__);
+	/* slot already allocated? */
+	if (res->sr_slotid != NFS4_MAX_SLOT_TABLE)
+		return 0;
+
+	memset(res, 0, sizeof(*res));
+	res->sr_slotid = NFS4_MAX_SLOT_TABLE;
+	tbl = &session->fc_slot_table;
+
+	spin_lock(&tbl->slot_tbl_lock);
+	if (test_bit(NFS4CLNT_SESSION_SETUP, &session->clp->cl_state)) {
+		if (tbl->highest_used_slotid != -1) {
+			rpc_sleep_on(&tbl->slot_tbl_waitq, task, NULL);
+			spin_unlock(&tbl->slot_tbl_lock);
+			dprintk("<-- %s: Session reset: draining\n", __func__);
+			return -EAGAIN;
+		}
+
+		/* The slot table is empty; start the reset thread */
+		dprintk("%s Session Reset\n", __func__);
+		spin_unlock(&tbl->slot_tbl_lock);
+		status = nfs4_recover_session(session);
+		if (status)
+			return status;
+		spin_lock(&tbl->slot_tbl_lock);
+	}
+
+	slotid = nfs4_find_slot(tbl, task);
+	if (slotid == NFS4_MAX_SLOT_TABLE) {
+		rpc_sleep_on(&tbl->slot_tbl_waitq, task, NULL);
+		spin_unlock(&tbl->slot_tbl_lock);
+		dprintk("<-- %s: no free slots\n", __func__);
+		return -EAGAIN;
+	}
+	spin_unlock(&tbl->slot_tbl_lock);
+
+	slot = tbl->slots + slotid;
+	args->sa_session = session;
+	args->sa_slotid = slotid;
+	args->sa_cache_this = cache_reply;
+
+	dprintk("<-- %s slotid=%d seqid=%d\n", __func__, slotid, slot->seq_nr);
+
+	res->sr_session = session;
+	res->sr_slotid = slotid;
+	res->sr_renewal_time = jiffies;
+	/*
+	 * sr_status is only set in decode_sequence, and so will remain
+	 * set to 1 if an rpc level failure occurs.
+	 */
+	res->sr_status = 1;
+	return 0;
+}
+
+int nfs4_setup_sequence(struct nfs_client *clp,
+			struct nfs4_sequence_args *args,
+			struct nfs4_sequence_res *res,
+			int cache_reply,
+			struct rpc_task *task)
+{
+	int ret = 0;
+
+	dprintk("--> %s clp %p session %p sr_slotid %d\n",
+		__func__, clp, clp->cl_session, res->sr_slotid);
+
+	if (!nfs4_has_session(clp))
+		goto out;
+	ret = nfs41_setup_sequence(clp->cl_session, args, res, cache_reply,
+				   task);
+	if (ret != -EAGAIN) {
+		/* terminate rpc task */
+		task->tk_status = ret;
+		task->tk_action = NULL;
+	}
+out:
+	dprintk("<-- %s status=%d\n", __func__, ret);
+	return ret;
+}
+
+struct nfs41_call_sync_data {
+	struct nfs_client *clp;
+	struct nfs4_sequence_args *seq_args;
+	struct nfs4_sequence_res *seq_res;
+	int cache_reply;
+};
+
+static void nfs41_call_sync_prepare(struct rpc_task *task, void *calldata)
+{
+	struct nfs41_call_sync_data *data = calldata;
+
+	dprintk("--> %s data->clp->cl_session %p\n", __func__,
+		data->clp->cl_session);
+	if (nfs4_setup_sequence(data->clp, data->seq_args,
+				data->seq_res, data->cache_reply, task))
+		return;
+	rpc_call_start(task);
+}
+
+static void nfs41_call_sync_done(struct rpc_task *task, void *calldata)
+{
+	struct nfs41_call_sync_data *data = calldata;
+
+	nfs41_sequence_done(data->clp, data->seq_res, task->tk_status);
+	nfs41_sequence_free_slot(data->clp, data->seq_res);
+}
+
+struct rpc_call_ops nfs41_call_sync_ops = {
+	.rpc_call_prepare = nfs41_call_sync_prepare,
+	.rpc_call_done = nfs41_call_sync_done,
+};
+
+static int nfs4_call_sync_sequence(struct nfs_client *clp,
+				   struct rpc_clnt *clnt,
+				   struct rpc_message *msg,
+				   struct nfs4_sequence_args *args,
+				   struct nfs4_sequence_res *res,
+				   int cache_reply)
+{
+	int ret;
+	struct rpc_task *task;
+	struct nfs41_call_sync_data data = {
+		.clp = clp,
+		.seq_args = args,
+		.seq_res = res,
+		.cache_reply = cache_reply,
+	};
+	struct rpc_task_setup task_setup = {
+		.rpc_client = clnt,
+		.rpc_message = msg,
+		.callback_ops = &nfs41_call_sync_ops,
+		.callback_data = &data
+	};
+
+	res->sr_slotid = NFS4_MAX_SLOT_TABLE;
+	task = rpc_run_task(&task_setup);
+	if (IS_ERR(task))
+		ret = PTR_ERR(task);
+	else {
+		ret = task->tk_status;
+		rpc_put_task(task);
+	}
+	return ret;
+}
+
+int _nfs4_call_sync_session(struct nfs_server *server,
+			    struct rpc_message *msg,
+			    struct nfs4_sequence_args *args,
+			    struct nfs4_sequence_res *res,
+			    int cache_reply)
+{
+	return nfs4_call_sync_sequence(server->nfs_client, server->client,
+				       msg, args, res, cache_reply);
+}
+
+#endif /* CONFIG_NFS_V4_1 */
+
+int _nfs4_call_sync(struct nfs_server *server,
+		    struct rpc_message *msg,
+		    struct nfs4_sequence_args *args,
+		    struct nfs4_sequence_res *res,
+		    int cache_reply)
+{
+	args->sa_session = res->sr_session = NULL;
+	return rpc_call_sync(server->client, msg, 0);
+}
+
+#define nfs4_call_sync(server, msg, args, res, cache_reply) \
+	(server)->nfs_client->cl_call_sync((server), (msg), &(args)->seq_args, \
+			&(res)->seq_res, (cache_reply))
+
+static void nfs4_sequence_done(const struct nfs_server *server,
+			       struct nfs4_sequence_res *res, int rpc_status)
+{
+#ifdef CONFIG_NFS_V4_1
+	if (nfs4_has_session(server->nfs_client))
+		nfs41_sequence_done(server->nfs_client, res, rpc_status);
+#endif /* CONFIG_NFS_V4_1 */
+}
+
+/* no restart, therefore free slot here */
+static void nfs4_sequence_done_free_slot(const struct nfs_server *server,
+					 struct nfs4_sequence_res *res,
+					 int rpc_status)
+{
+	nfs4_sequence_done(server, res, rpc_status);
+	nfs4_sequence_free_slot(server->nfs_client, res);
+}
+
 static void update_changeattr(struct inode *dir, struct nfs4_change_info *cinfo)
 {
 	struct nfs_inode *nfsi = NFS_I(dir);
@@ -312,6 +680,7 @@ static void nfs4_init_opendata_res(struct nfs4_opendata *p)
 	p->o_res.server = p->o_arg.server;
 	nfs_fattr_init(&p->f_attr);
 	nfs_fattr_init(&p->dir_attr);
+	p->o_res.seq_res.sr_slotid = NFS4_MAX_SLOT_TABLE;
 }
 
 static struct nfs4_opendata *nfs4_opendata_alloc(struct path *path,
@@ -804,16 +1173,30 @@ int nfs4_open_delegation_recall(struct nfs_open_context *ctx, struct nfs4_state
 		err = _nfs4_open_delegation_recall(ctx, state, stateid);
 		switch (err) {
 			case 0:
-				return err;
+			case -ENOENT:
+			case -ESTALE:
+				goto out;
 			case -NFS4ERR_STALE_CLIENTID:
 			case -NFS4ERR_STALE_STATEID:
 			case -NFS4ERR_EXPIRED:
 				/* Don't recall a delegation if it was lost */
 				nfs4_schedule_state_recovery(server->nfs_client);
-				return err;
+				goto out;
+			case -ERESTARTSYS:
+				/*
+				 * The show must go on: exit, but mark the
+				 * stateid as needing recovery.
+				 */
+			case -NFS4ERR_ADMIN_REVOKED:
+			case -NFS4ERR_BAD_STATEID:
+				nfs4_state_mark_reclaim_nograce(server->nfs_client, state);
+			case -ENOMEM:
+				err = 0;
+				goto out;
 		}
 		err = nfs4_handle_exception(server, err, &exception);
 	} while (exception.retry);
+out:
 	return err;
 }
 
@@ -929,6 +1312,10 @@ static void nfs4_open_prepare(struct rpc_task *task, void *calldata)
 		nfs_copy_fh(&data->o_res.fh, data->o_arg.fh);
 	}
 	data->timestamp = jiffies;
+	if (nfs4_setup_sequence(data->o_arg.server->nfs_client,
+				&data->o_arg.seq_args,
+				&data->o_res.seq_res, 1, task))
+		return;
 	rpc_call_start(task);
 	return;
 out_no_action:
@@ -941,6 +1328,10 @@ static void nfs4_open_done(struct rpc_task *task, void *calldata)
 	struct nfs4_opendata *data = calldata;
 
 	data->rpc_status = task->tk_status;
+
+	nfs4_sequence_done_free_slot(data->o_arg.server, &data->o_res.seq_res,
+				     task->tk_status);
+
 	if (RPC_ASSASSINATED(task))
 		return;
 	if (task->tk_status == 0) {
@@ -1269,7 +1660,7 @@ static int _nfs4_do_setattr(struct inode *inode, struct rpc_cred *cred,
 	} else
 		memcpy(&arg.stateid, &zero_stateid, sizeof(arg.stateid));
 
-	status = rpc_call_sync(server->client, &msg, 0);
+	status = nfs4_call_sync(server, &msg, &arg, &res, 1);
 	if (status == 0 && state != NULL)
 		renew_lease(server, timestamp);
 	return status;
@@ -1318,6 +1709,7 @@ static void nfs4_close_done(struct rpc_task *task, void *data)
 	struct nfs4_state *state = calldata->state;
 	struct nfs_server *server = NFS_SERVER(calldata->inode);
 
+	nfs4_sequence_done(server, &calldata->res.seq_res, task->tk_status);
 	if (RPC_ASSASSINATED(task))
 		return;
         /* hmm. we are done with the inode, and in the process of freeing
@@ -1336,10 +1728,11 @@ static void nfs4_close_done(struct rpc_task *task, void *data)
 				break;
 		default:
 			if (nfs4_async_handle_error(task, server, state) == -EAGAIN) {
-				rpc_restart_call(task);
+				nfs4_restart_rpc(task, server->nfs_client);
 				return;
 			}
 	}
+	nfs4_sequence_free_slot(server->nfs_client, &calldata->res.seq_res);
 	nfs_refresh_inode(calldata->inode, calldata->res.fattr);
 }
 
@@ -1380,6 +1773,10 @@ static void nfs4_close_prepare(struct rpc_task *task, void *data)
 		calldata->arg.fmode = FMODE_WRITE;
 	}
 	calldata->timestamp = jiffies;
+	if (nfs4_setup_sequence((NFS_SERVER(calldata->inode))->nfs_client,
+				&calldata->arg.seq_args, &calldata->res.seq_res,
+				1, task))
+		return;
 	rpc_call_start(task);
 }
 
@@ -1419,13 +1816,15 @@ int nfs4_do_close(struct path *path, struct nfs4_state *state, int wait)
 	};
 	int status = -ENOMEM;
 
-	calldata = kmalloc(sizeof(*calldata), GFP_KERNEL);
+	calldata = kzalloc(sizeof(*calldata), GFP_KERNEL);
 	if (calldata == NULL)
 		goto out;
 	calldata->inode = state->inode;
 	calldata->state = state;
 	calldata->arg.fh = NFS_FH(state->inode);
 	calldata->arg.stateid = &state->open_stateid;
+	if (nfs4_has_session(server->nfs_client))
+		memset(calldata->arg.stateid->data, 0, 4);    /* clear seqid */
 	/* Serialization for the sequence id */
 	calldata->arg.seqid = nfs_alloc_seqid(&state->owner->so_seqid);
 	if (calldata->arg.seqid == NULL)
@@ -1435,6 +1834,7 @@ int nfs4_do_close(struct path *path, struct nfs4_state *state, int wait)
 	calldata->res.fattr = &calldata->fattr;
 	calldata->res.seqid = calldata->arg.seqid;
 	calldata->res.server = server;
+	calldata->res.seq_res.sr_slotid = NFS4_MAX_SLOT_TABLE;
 	calldata->path.mnt = mntget(path->mnt);
 	calldata->path.dentry = dget(path->dentry);
 
@@ -1584,15 +1984,18 @@ void nfs4_close_context(struct nfs_open_context *ctx, int is_sync)
 
 static int _nfs4_server_capabilities(struct nfs_server *server, struct nfs_fh *fhandle)
 {
+	struct nfs4_server_caps_arg args = {
+		.fhandle = fhandle,
+	};
 	struct nfs4_server_caps_res res = {};
 	struct rpc_message msg = {
 		.rpc_proc = &nfs4_procedures[NFSPROC4_CLNT_SERVER_CAPS],
-		.rpc_argp = fhandle,
+		.rpc_argp = &args,
 		.rpc_resp = &res,
 	};
 	int status;
 
-	status = rpc_call_sync(server->client, &msg, 0);
+	status = nfs4_call_sync(server, &msg, &args, &res, 0);
 	if (status == 0) {
 		memcpy(server->attr_bitmask, res.attr_bitmask, sizeof(server->attr_bitmask));
 		if (res.attr_bitmask[0] & FATTR4_WORD0_ACL)
@@ -1606,6 +2009,7 @@ static int _nfs4_server_capabilities(struct nfs_server *server, struct nfs_fh *f
 		server->cache_consistency_bitmask[1] &= FATTR4_WORD1_TIME_METADATA|FATTR4_WORD1_TIME_MODIFY;
 		server->acl_bitmask = res.acl_bitmask;
 	}
+
 	return status;
 }
 
@@ -1637,8 +2041,15 @@ static int _nfs4_lookup_root(struct nfs_server *server, struct nfs_fh *fhandle,
 		.rpc_argp = &args,
 		.rpc_resp = &res,
 	};
+	int status;
+
 	nfs_fattr_init(info->fattr);
-	return rpc_call_sync(server->client, &msg, 0);
+	status = nfs4_recover_expired_lease(server);
+	if (!status)
+		status = nfs4_check_client_ready(server->nfs_client);
+	if (!status)
+		status = nfs4_call_sync(server, &msg, &args, &res, 0);
+	return status;
 }
 
 static int nfs4_lookup_root(struct nfs_server *server, struct nfs_fh *fhandle,
@@ -1728,7 +2139,7 @@ static int _nfs4_proc_getattr(struct nfs_server *server, struct nfs_fh *fhandle,
 	};
 	
 	nfs_fattr_init(fattr);
-	return rpc_call_sync(server->client, &msg, 0);
+	return nfs4_call_sync(server, &msg, &args, &res, 0);
 }
 
 static int nfs4_proc_getattr(struct nfs_server *server, struct nfs_fh *fhandle, struct nfs_fattr *fattr)
@@ -1812,7 +2223,7 @@ static int _nfs4_proc_lookupfh(struct nfs_server *server, const struct nfs_fh *d
 	nfs_fattr_init(fattr);
 
 	dprintk("NFS call  lookupfh %s\n", name->name);
-	status = rpc_call_sync(server->client, &msg, 0);
+	status = nfs4_call_sync(server, &msg, &args, &res, 0);
 	dprintk("NFS reply lookupfh: %d\n", status);
 	return status;
 }
@@ -1898,7 +2309,7 @@ static int _nfs4_proc_access(struct inode *inode, struct nfs_access_entry *entry
 			args.access |= NFS4_ACCESS_EXECUTE;
 	}
 	nfs_fattr_init(&fattr);
-	status = rpc_call_sync(NFS_CLIENT(inode), &msg, 0);
+	status = nfs4_call_sync(server, &msg, &args, &res, 0);
 	if (!status) {
 		entry->mask = 0;
 		if (res.access & NFS4_ACCESS_READ)
@@ -1957,13 +2368,14 @@ static int _nfs4_proc_readlink(struct inode *inode, struct page *page,
 		.pglen    = pglen,
 		.pages    = &page,
 	};
+	struct nfs4_readlink_res res;
 	struct rpc_message msg = {
 		.rpc_proc = &nfs4_procedures[NFSPROC4_CLNT_READLINK],
 		.rpc_argp = &args,
-		.rpc_resp = NULL,
+		.rpc_resp = &res,
 	};
 
-	return rpc_call_sync(NFS_CLIENT(inode), &msg, 0);
+	return nfs4_call_sync(NFS_SERVER(inode), &msg, &args, &res, 0);
 }
 
 static int nfs4_proc_readlink(struct inode *inode, struct page *page,
@@ -2057,7 +2469,7 @@ static int _nfs4_proc_remove(struct inode *dir, struct qstr *name)
 	int			status;
 
 	nfs_fattr_init(&res.dir_attr);
-	status = rpc_call_sync(server->client, &msg, 0);
+	status = nfs4_call_sync(server, &msg, &args, &res, 1);
 	if (status == 0) {
 		update_changeattr(dir, &res.cinfo);
 		nfs_post_op_update_inode(dir, &res.dir_attr);
@@ -2092,8 +2504,10 @@ static int nfs4_proc_unlink_done(struct rpc_task *task, struct inode *dir)
 {
 	struct nfs_removeres *res = task->tk_msg.rpc_resp;
 
+	nfs4_sequence_done(res->server, &res->seq_res, task->tk_status);
 	if (nfs4_async_handle_error(task, res->server, NULL) == -EAGAIN)
 		return 0;
+	nfs4_sequence_free_slot(res->server->nfs_client, &res->seq_res);
 	update_changeattr(dir, &res->cinfo);
 	nfs_post_op_update_inode(dir, &res->dir_attr);
 	return 1;
@@ -2125,7 +2539,7 @@ static int _nfs4_proc_rename(struct inode *old_dir, struct qstr *old_name,
 	
 	nfs_fattr_init(res.old_fattr);
 	nfs_fattr_init(res.new_fattr);
-	status = rpc_call_sync(server->client, &msg, 0);
+	status = nfs4_call_sync(server, &msg, &arg, &res, 1);
 
 	if (!status) {
 		update_changeattr(old_dir, &res.old_cinfo);
@@ -2174,7 +2588,7 @@ static int _nfs4_proc_link(struct inode *inode, struct inode *dir, struct qstr *
 
 	nfs_fattr_init(res.fattr);
 	nfs_fattr_init(res.dir_attr);
-	status = rpc_call_sync(server->client, &msg, 0);
+	status = nfs4_call_sync(server, &msg, &arg, &res, 1);
 	if (!status) {
 		update_changeattr(dir, &res.cinfo);
 		nfs_post_op_update_inode(dir, res.dir_attr);
@@ -2235,7 +2649,8 @@ static struct nfs4_createdata *nfs4_alloc_createdata(struct inode *dir,
 
 static int nfs4_do_create(struct inode *dir, struct dentry *dentry, struct nfs4_createdata *data)
 {
-	int status = rpc_call_sync(NFS_CLIENT(dir), &data->msg, 0);
+	int status = nfs4_call_sync(NFS_SERVER(dir), &data->msg,
+				    &data->arg, &data->res, 1);
 	if (status == 0) {
 		update_changeattr(dir, &data->res.dir_cinfo);
 		nfs_post_op_update_inode(dir, data->res.dir_fattr);
@@ -2344,7 +2759,7 @@ static int _nfs4_proc_readdir(struct dentry *dentry, struct rpc_cred *cred,
 			(unsigned long long)cookie);
 	nfs4_setup_readdir(cookie, NFS_COOKIEVERF(dir), dentry, &args);
 	res.pgbase = args.pgbase;
-	status = rpc_call_sync(NFS_CLIENT(dir), &msg, 0);
+	status = nfs4_call_sync(NFS_SERVER(dir), &msg, &args, &res, 0);
 	if (status == 0)
 		memcpy(NFS_COOKIEVERF(dir), res.verifier.data, NFS4_VERIFIER_SIZE);
 
@@ -2422,14 +2837,17 @@ static int _nfs4_proc_statfs(struct nfs_server *server, struct nfs_fh *fhandle,
 		.fh = fhandle,
 		.bitmask = server->attr_bitmask,
 	};
+	struct nfs4_statfs_res res = {
+		.fsstat = fsstat,
+	};
 	struct rpc_message msg = {
 		.rpc_proc = &nfs4_procedures[NFSPROC4_CLNT_STATFS],
 		.rpc_argp = &args,
-		.rpc_resp = fsstat,
+		.rpc_resp = &res,
 	};
 
 	nfs_fattr_init(fsstat->fattr);
-	return rpc_call_sync(server->client, &msg, 0);
+	return  nfs4_call_sync(server, &msg, &args, &res, 0);
 }
 
 static int nfs4_proc_statfs(struct nfs_server *server, struct nfs_fh *fhandle, struct nfs_fsstat *fsstat)
@@ -2451,13 +2869,16 @@ static int _nfs4_do_fsinfo(struct nfs_server *server, struct nfs_fh *fhandle,
 		.fh = fhandle,
 		.bitmask = server->attr_bitmask,
 	};
+	struct nfs4_fsinfo_res res = {
+		.fsinfo = fsinfo,
+	};
 	struct rpc_message msg = {
 		.rpc_proc = &nfs4_procedures[NFSPROC4_CLNT_FSINFO],
 		.rpc_argp = &args,
-		.rpc_resp = fsinfo,
+		.rpc_resp = &res,
 	};
 
-	return rpc_call_sync(server->client, &msg, 0);
+	return nfs4_call_sync(server, &msg, &args, &res, 0);
 }
 
 static int nfs4_do_fsinfo(struct nfs_server *server, struct nfs_fh *fhandle, struct nfs_fsinfo *fsinfo)
@@ -2486,10 +2907,13 @@ static int _nfs4_proc_pathconf(struct nfs_server *server, struct nfs_fh *fhandle
 		.fh = fhandle,
 		.bitmask = server->attr_bitmask,
 	};
+	struct nfs4_pathconf_res res = {
+		.pathconf = pathconf,
+	};
 	struct rpc_message msg = {
 		.rpc_proc = &nfs4_procedures[NFSPROC4_CLNT_PATHCONF],
 		.rpc_argp = &args,
-		.rpc_resp = pathconf,
+		.rpc_resp = &res,
 	};
 
 	/* None of the pathconf attributes are mandatory to implement */
@@ -2499,7 +2923,7 @@ static int _nfs4_proc_pathconf(struct nfs_server *server, struct nfs_fh *fhandle
 	}
 
 	nfs_fattr_init(pathconf->fattr);
-	return rpc_call_sync(server->client, &msg, 0);
+	return nfs4_call_sync(server, &msg, &args, &res, 0);
 }
 
 static int nfs4_proc_pathconf(struct nfs_server *server, struct nfs_fh *fhandle,
@@ -2520,8 +2944,13 @@ static int nfs4_read_done(struct rpc_task *task, struct nfs_read_data *data)
 {
 	struct nfs_server *server = NFS_SERVER(data->inode);
 
+	dprintk("--> %s\n", __func__);
+
+	/* nfs4_sequence_free_slot called in the read rpc_call_done */
+	nfs4_sequence_done(server, &data->res.seq_res, task->tk_status);
+
 	if (nfs4_async_handle_error(task, server, data->args.context->state) == -EAGAIN) {
-		rpc_restart_call(task);
+		nfs4_restart_rpc(task, server->nfs_client);
 		return -EAGAIN;
 	}
 
@@ -2541,8 +2970,12 @@ static int nfs4_write_done(struct rpc_task *task, struct nfs_write_data *data)
 {
 	struct inode *inode = data->inode;
 	
+	/* slot is freed in nfs_writeback_done */
+	nfs4_sequence_done(NFS_SERVER(inode), &data->res.seq_res,
+			   task->tk_status);
+
 	if (nfs4_async_handle_error(task, NFS_SERVER(inode), data->args.context->state) == -EAGAIN) {
-		rpc_restart_call(task);
+		nfs4_restart_rpc(task, NFS_SERVER(inode)->nfs_client);
 		return -EAGAIN;
 	}
 	if (task->tk_status >= 0) {
@@ -2567,10 +3000,14 @@ static int nfs4_commit_done(struct rpc_task *task, struct nfs_write_data *data)
 {
 	struct inode *inode = data->inode;
 	
+	nfs4_sequence_done(NFS_SERVER(inode), &data->res.seq_res,
+			   task->tk_status);
 	if (nfs4_async_handle_error(task, NFS_SERVER(inode), NULL) == -EAGAIN) {
-		rpc_restart_call(task);
+		nfs4_restart_rpc(task, NFS_SERVER(inode)->nfs_client);
 		return -EAGAIN;
 	}
+	nfs4_sequence_free_slot(NFS_SERVER(inode)->nfs_client,
+				&data->res.seq_res);
 	nfs_refresh_inode(inode, data->res.fattr);
 	return 0;
 }
@@ -2603,6 +3040,9 @@ static void nfs4_renew_done(struct rpc_task *task, void *data)
 	if (time_before(clp->cl_last_renewal,timestamp))
 		clp->cl_last_renewal = timestamp;
 	spin_unlock(&clp->cl_lock);
+	dprintk("%s calling put_rpccred on rpc_cred %p\n", __func__,
+				task->tk_msg.rpc_cred);
+	put_rpccred(task->tk_msg.rpc_cred);
 }
 
 static const struct rpc_call_ops nfs4_renew_ops = {
@@ -2742,12 +3182,14 @@ static ssize_t __nfs4_get_acl_uncached(struct inode *inode, void *buf, size_t bu
 		.acl_pages = pages,
 		.acl_len = buflen,
 	};
-	size_t resp_len = buflen;
+	struct nfs_getaclres res = {
+		.acl_len = buflen,
+	};
 	void *resp_buf;
 	struct rpc_message msg = {
 		.rpc_proc = &nfs4_procedures[NFSPROC4_CLNT_GETACL],
 		.rpc_argp = &args,
-		.rpc_resp = &resp_len,
+		.rpc_resp = &res,
 	};
 	struct page *localpage = NULL;
 	int ret;
@@ -2761,26 +3203,26 @@ static ssize_t __nfs4_get_acl_uncached(struct inode *inode, void *buf, size_t bu
 			return -ENOMEM;
 		args.acl_pages[0] = localpage;
 		args.acl_pgbase = 0;
-		resp_len = args.acl_len = PAGE_SIZE;
+		args.acl_len = PAGE_SIZE;
 	} else {
 		resp_buf = buf;
 		buf_to_pages(buf, buflen, args.acl_pages, &args.acl_pgbase);
 	}
-	ret = rpc_call_sync(NFS_CLIENT(inode), &msg, 0);
+	ret = nfs4_call_sync(NFS_SERVER(inode), &msg, &args, &res, 0);
 	if (ret)
 		goto out_free;
-	if (resp_len > args.acl_len)
-		nfs4_write_cached_acl(inode, NULL, resp_len);
+	if (res.acl_len > args.acl_len)
+		nfs4_write_cached_acl(inode, NULL, res.acl_len);
 	else
-		nfs4_write_cached_acl(inode, resp_buf, resp_len);
+		nfs4_write_cached_acl(inode, resp_buf, res.acl_len);
 	if (buf) {
 		ret = -ERANGE;
-		if (resp_len > buflen)
+		if (res.acl_len > buflen)
 			goto out_free;
 		if (localpage)
-			memcpy(buf, resp_buf, resp_len);
+			memcpy(buf, resp_buf, res.acl_len);
 	}
-	ret = resp_len;
+	ret = res.acl_len;
 out_free:
 	if (localpage)
 		__free_page(localpage);
@@ -2810,8 +3252,6 @@ static ssize_t nfs4_proc_get_acl(struct inode *inode, void *buf, size_t buflen)
 	ret = nfs_revalidate_inode(server, inode);
 	if (ret < 0)
 		return ret;
-	if (NFS_I(inode)->cache_validity & NFS_INO_INVALID_ACL)
-		nfs_zap_acl_cache(inode);
 	ret = nfs4_read_cached_acl(inode, buf, buflen);
 	if (ret != -ENOENT)
 		return ret;
@@ -2827,10 +3267,11 @@ static int __nfs4_proc_set_acl(struct inode *inode, const void *buf, size_t bufl
 		.acl_pages	= pages,
 		.acl_len	= buflen,
 	};
+	struct nfs_setaclres res;
 	struct rpc_message msg = {
 		.rpc_proc	= &nfs4_procedures[NFSPROC4_CLNT_SETACL],
 		.rpc_argp	= &arg,
-		.rpc_resp	= NULL,
+		.rpc_resp	= &res,
 	};
 	int ret;
 
@@ -2838,7 +3279,7 @@ static int __nfs4_proc_set_acl(struct inode *inode, const void *buf, size_t bufl
 		return -EOPNOTSUPP;
 	nfs_inode_return_delegation(inode);
 	buf_to_pages(buf, buflen, arg.acl_pages, &arg.acl_pgbase);
-	ret = rpc_call_sync(NFS_CLIENT(inode), &msg, 0);
+	ret = nfs4_call_sync(server, &msg, &arg, &res, 1);
 	nfs_access_zap_cache(inode);
 	nfs_zap_acl_cache(inode);
 	return ret;
@@ -2857,10 +3298,8 @@ static int nfs4_proc_set_acl(struct inode *inode, const void *buf, size_t buflen
 }
 
 static int
-nfs4_async_handle_error(struct rpc_task *task, const struct nfs_server *server, struct nfs4_state *state)
+_nfs4_async_handle_error(struct rpc_task *task, const struct nfs_server *server, struct nfs_client *clp, struct nfs4_state *state)
 {
-	struct nfs_client *clp = server->nfs_client;
-
 	if (!clp || task->tk_status >= 0)
 		return 0;
 	switch(task->tk_status) {
@@ -2879,8 +3318,23 @@ nfs4_async_handle_error(struct rpc_task *task, const struct nfs_server *server,
 				rpc_wake_up_queued_task(&clp->cl_rpcwaitq, task);
 			task->tk_status = 0;
 			return -EAGAIN;
+#if defined(CONFIG_NFS_V4_1)
+		case -NFS4ERR_BADSESSION:
+		case -NFS4ERR_BADSLOT:
+		case -NFS4ERR_BAD_HIGH_SLOT:
+		case -NFS4ERR_DEADSESSION:
+		case -NFS4ERR_CONN_NOT_BOUND_TO_SESSION:
+		case -NFS4ERR_SEQ_FALSE_RETRY:
+		case -NFS4ERR_SEQ_MISORDERED:
+			dprintk("%s ERROR %d, Reset session\n", __func__,
+				task->tk_status);
+			set_bit(NFS4CLNT_SESSION_SETUP, &clp->cl_state);
+			task->tk_status = 0;
+			return -EAGAIN;
+#endif /* CONFIG_NFS_V4_1 */
 		case -NFS4ERR_DELAY:
-			nfs_inc_server_stats(server, NFSIOS_DELAY);
+			if (server)
+				nfs_inc_server_stats(server, NFSIOS_DELAY);
 		case -NFS4ERR_GRACE:
 			rpc_delay(task, NFS4_POLL_RETRY_MAX);
 			task->tk_status = 0;
@@ -2893,6 +3347,12 @@ nfs4_async_handle_error(struct rpc_task *task, const struct nfs_server *server,
 	return 0;
 }
 
+static int
+nfs4_async_handle_error(struct rpc_task *task, const struct nfs_server *server, struct nfs4_state *state)
+{
+	return _nfs4_async_handle_error(task, server, server->nfs_client, state);
+}
+
 int nfs4_proc_setclientid(struct nfs_client *clp, u32 program, unsigned short port, struct rpc_cred *cred)
 {
 	nfs4_verifier sc_verifier;
@@ -3000,6 +3460,10 @@ struct nfs4_delegreturndata {
 static void nfs4_delegreturn_done(struct rpc_task *task, void *calldata)
 {
 	struct nfs4_delegreturndata *data = calldata;
+
+	nfs4_sequence_done_free_slot(data->res.server, &data->res.seq_res,
+				     task->tk_status);
+
 	data->rpc_status = task->tk_status;
 	if (data->rpc_status == 0)
 		renew_lease(data->res.server, data->timestamp);
@@ -3010,7 +3474,25 @@ static void nfs4_delegreturn_release(void *calldata)
 	kfree(calldata);
 }
 
+#if defined(CONFIG_NFS_V4_1)
+static void nfs4_delegreturn_prepare(struct rpc_task *task, void *data)
+{
+	struct nfs4_delegreturndata *d_data;
+
+	d_data = (struct nfs4_delegreturndata *)data;
+
+	if (nfs4_setup_sequence(d_data->res.server->nfs_client,
+				&d_data->args.seq_args,
+				&d_data->res.seq_res, 1, task))
+		return;
+	rpc_call_start(task);
+}
+#endif /* CONFIG_NFS_V4_1 */
+
 static const struct rpc_call_ops nfs4_delegreturn_ops = {
+#if defined(CONFIG_NFS_V4_1)
+	.rpc_call_prepare = nfs4_delegreturn_prepare,
+#endif /* CONFIG_NFS_V4_1 */
 	.rpc_call_done = nfs4_delegreturn_done,
 	.rpc_release = nfs4_delegreturn_release,
 };
@@ -3032,7 +3514,7 @@ static int _nfs4_proc_delegreturn(struct inode *inode, struct rpc_cred *cred, co
 	};
 	int status = 0;
 
-	data = kmalloc(sizeof(*data), GFP_KERNEL);
+	data = kzalloc(sizeof(*data), GFP_KERNEL);
 	if (data == NULL)
 		return -ENOMEM;
 	data->args.fhandle = &data->fh;
@@ -3042,6 +3524,7 @@ static int _nfs4_proc_delegreturn(struct inode *inode, struct rpc_cred *cred, co
 	memcpy(&data->stateid, stateid, sizeof(data->stateid));
 	data->res.fattr = &data->fattr;
 	data->res.server = server;
+	data->res.seq_res.sr_slotid = NFS4_MAX_SLOT_TABLE;
 	nfs_fattr_init(data->res.fattr);
 	data->timestamp = jiffies;
 	data->rpc_status = 0;
@@ -3127,7 +3610,7 @@ static int _nfs4_proc_getlk(struct nfs4_state *state, int cmd, struct file_lock
 		goto out;
 	lsp = request->fl_u.nfs4_fl.owner;
 	arg.lock_owner.id = lsp->ls_id.id;
-	status = rpc_call_sync(server->client, &msg, 0);
+	status = nfs4_call_sync(server, &msg, &arg, &res, 1);
 	switch (status) {
 		case 0:
 			request->fl_type = F_UNLCK;
@@ -3187,13 +3670,14 @@ static struct nfs4_unlockdata *nfs4_alloc_unlockdata(struct file_lock *fl,
 	struct nfs4_unlockdata *p;
 	struct inode *inode = lsp->ls_state->inode;
 
-	p = kmalloc(sizeof(*p), GFP_KERNEL);
+	p = kzalloc(sizeof(*p), GFP_KERNEL);
 	if (p == NULL)
 		return NULL;
 	p->arg.fh = NFS_FH(inode);
 	p->arg.fl = &p->fl;
 	p->arg.seqid = seqid;
 	p->res.seqid = seqid;
+	p->res.seq_res.sr_slotid = NFS4_MAX_SLOT_TABLE;
 	p->arg.stateid = &lsp->ls_stateid;
 	p->lsp = lsp;
 	atomic_inc(&lsp->ls_count);
@@ -3217,6 +3701,8 @@ static void nfs4_locku_done(struct rpc_task *task, void *data)
 {
 	struct nfs4_unlockdata *calldata = data;
 
+	nfs4_sequence_done(calldata->server, &calldata->res.seq_res,
+			   task->tk_status);
 	if (RPC_ASSASSINATED(task))
 		return;
 	switch (task->tk_status) {
@@ -3233,8 +3719,11 @@ static void nfs4_locku_done(struct rpc_task *task, void *data)
 			break;
 		default:
 			if (nfs4_async_handle_error(task, calldata->server, NULL) == -EAGAIN)
-				rpc_restart_call(task);
+				nfs4_restart_rpc(task,
+						calldata->server->nfs_client);
 	}
+	nfs4_sequence_free_slot(calldata->server->nfs_client,
+				&calldata->res.seq_res);
 }
 
 static void nfs4_locku_prepare(struct rpc_task *task, void *data)
@@ -3249,6 +3738,10 @@ static void nfs4_locku_prepare(struct rpc_task *task, void *data)
 		return;
 	}
 	calldata->timestamp = jiffies;
+	if (nfs4_setup_sequence(calldata->server->nfs_client,
+				&calldata->arg.seq_args,
+				&calldata->res.seq_res, 1, task))
+		return;
 	rpc_call_start(task);
 }
 
@@ -3341,6 +3834,7 @@ struct nfs4_lockdata {
 	unsigned long timestamp;
 	int rpc_status;
 	int cancelled;
+	struct nfs_server *server;
 };
 
 static struct nfs4_lockdata *nfs4_alloc_lockdata(struct file_lock *fl,
@@ -3366,7 +3860,9 @@ static struct nfs4_lockdata *nfs4_alloc_lockdata(struct file_lock *fl,
 	p->arg.lock_owner.clientid = server->nfs_client->cl_clientid;
 	p->arg.lock_owner.id = lsp->ls_id.id;
 	p->res.lock_seqid = p->arg.lock_seqid;
+	p->res.seq_res.sr_slotid = NFS4_MAX_SLOT_TABLE;
 	p->lsp = lsp;
+	p->server = server;
 	atomic_inc(&lsp->ls_count);
 	p->ctx = get_nfs_open_context(ctx);
 	memcpy(&p->fl, fl, sizeof(p->fl));
@@ -3396,6 +3892,9 @@ static void nfs4_lock_prepare(struct rpc_task *task, void *calldata)
 	} else
 		data->arg.new_lock_owner = 0;
 	data->timestamp = jiffies;
+	if (nfs4_setup_sequence(data->server->nfs_client, &data->arg.seq_args,
+				&data->res.seq_res, 1, task))
+		return;
 	rpc_call_start(task);
 	dprintk("%s: done!, ret = %d\n", __func__, data->rpc_status);
 }
@@ -3406,6 +3905,9 @@ static void nfs4_lock_done(struct rpc_task *task, void *calldata)
 
 	dprintk("%s: begin!\n", __func__);
 
+	nfs4_sequence_done_free_slot(data->server, &data->res.seq_res,
+				     task->tk_status);
+
 	data->rpc_status = task->tk_status;
 	if (RPC_ASSASSINATED(task))
 		goto out;
@@ -3487,8 +3989,6 @@ static int _nfs4_do_setlk(struct nfs4_state *state, int cmd, struct file_lock *f
 	ret = nfs4_wait_for_completion_rpc_task(task);
 	if (ret == 0) {
 		ret = data->rpc_status;
-		if (ret == -NFS4ERR_DENIED)
-			ret = -EAGAIN;
 	} else
 		data->cancelled = 1;
 	rpc_put_task(task);
@@ -3576,9 +4076,11 @@ static int nfs4_proc_setlk(struct nfs4_state *state, int cmd, struct file_lock *
 	int err;
 
 	do {
+		err = _nfs4_proc_setlk(state, cmd, request);
+		if (err == -NFS4ERR_DENIED)
+			err = -EAGAIN;
 		err = nfs4_handle_exception(NFS_SERVER(state->inode),
-				_nfs4_proc_setlk(state, cmd, request),
-				&exception);
+				err, &exception);
 	} while (exception.retry);
 	return err;
 }
@@ -3630,8 +4132,37 @@ int nfs4_lock_delegation_recall(struct nfs4_state *state, struct file_lock *fl)
 		goto out;
 	do {
 		err = _nfs4_do_setlk(state, F_SETLK, fl, 0);
-		if (err != -NFS4ERR_DELAY)
-			break;
+		switch (err) {
+			default:
+				printk(KERN_ERR "%s: unhandled error %d.\n",
+						__func__, err);
+			case 0:
+			case -ESTALE:
+				goto out;
+			case -NFS4ERR_EXPIRED:
+			case -NFS4ERR_STALE_CLIENTID:
+			case -NFS4ERR_STALE_STATEID:
+				nfs4_schedule_state_recovery(server->nfs_client);
+				goto out;
+			case -ERESTARTSYS:
+				/*
+				 * The show must go on: exit, but mark the
+				 * stateid as needing recovery.
+				 */
+			case -NFS4ERR_ADMIN_REVOKED:
+			case -NFS4ERR_BAD_STATEID:
+			case -NFS4ERR_OPENMODE:
+				nfs4_state_mark_reclaim_nograce(server->nfs_client, state);
+				err = 0;
+				goto out;
+			case -ENOMEM:
+			case -NFS4ERR_DENIED:
+				/* kill_proc(fl->fl_pid, SIGLOST, 1); */
+				err = 0;
+				goto out;
+			case -NFS4ERR_DELAY:
+				break;
+		}
 		err = nfs4_handle_exception(server, err, &exception);
 	} while (exception.retry);
 out:
@@ -3706,10 +4237,13 @@ int nfs4_proc_fs_locations(struct inode *dir, const struct qstr *name,
 		.page = page,
 		.bitmask = bitmask,
 	};
+	struct nfs4_fs_locations_res res = {
+		.fs_locations = fs_locations,
+	};
 	struct rpc_message msg = {
 		.rpc_proc = &nfs4_procedures[NFSPROC4_CLNT_FS_LOCATIONS],
 		.rpc_argp = &args,
-		.rpc_resp = fs_locations,
+		.rpc_resp = &res,
 	};
 	int status;
 
@@ -3717,24 +4251,720 @@ int nfs4_proc_fs_locations(struct inode *dir, const struct qstr *name,
 	nfs_fattr_init(&fs_locations->fattr);
 	fs_locations->server = server;
 	fs_locations->nlocations = 0;
-	status = rpc_call_sync(server->client, &msg, 0);
+	status = nfs4_call_sync(server, &msg, &args, &res, 0);
 	nfs_fixup_referral_attributes(&fs_locations->fattr);
 	dprintk("%s: returned status = %d\n", __func__, status);
 	return status;
 }
 
-struct nfs4_state_recovery_ops nfs4_reboot_recovery_ops = {
+#ifdef CONFIG_NFS_V4_1
+/*
+ * nfs4_proc_exchange_id()
+ *
+ * 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
+ * be in some phase of session reset.
+ */
+static int nfs4_proc_exchange_id(struct nfs_client *clp, struct rpc_cred *cred)
+{
+	nfs4_verifier verifier;
+	struct nfs41_exchange_id_args args = {
+		.client = clp,
+		.flags = clp->cl_exchange_flags,
+	};
+	struct nfs41_exchange_id_res res = {
+		.client = clp,
+	};
+	int status;
+	struct rpc_message msg = {
+		.rpc_proc = &nfs4_procedures[NFSPROC4_CLNT_EXCHANGE_ID],
+		.rpc_argp = &args,
+		.rpc_resp = &res,
+		.rpc_cred = cred,
+	};
+	__be32 *p;
+
+	dprintk("--> %s\n", __func__);
+	BUG_ON(clp == NULL);
+
+	p = (u32 *)verifier.data;
+	*p++ = htonl((u32)clp->cl_boot_time.tv_sec);
+	*p = htonl((u32)clp->cl_boot_time.tv_nsec);
+	args.verifier = &verifier;
+
+	while (1) {
+		args.id_len = scnprintf(args.id, sizeof(args.id),
+					"%s/%s %u",
+					clp->cl_ipaddr,
+					rpc_peeraddr2str(clp->cl_rpcclient,
+							 RPC_DISPLAY_ADDR),
+					clp->cl_id_uniquifier);
+
+		status = rpc_call_sync(clp->cl_rpcclient, &msg, 0);
+
+		if (status != NFS4ERR_CLID_INUSE)
+			break;
+
+		if (signalled())
+			break;
+
+		if (++clp->cl_id_uniquifier == 0)
+			break;
+	}
+
+	dprintk("<-- %s status= %d\n", __func__, status);
+	return status;
+}
+
+struct nfs4_get_lease_time_data {
+	struct nfs4_get_lease_time_args *args;
+	struct nfs4_get_lease_time_res *res;
+	struct nfs_client *clp;
+};
+
+static void nfs4_get_lease_time_prepare(struct rpc_task *task,
+					void *calldata)
+{
+	int ret;
+	struct nfs4_get_lease_time_data *data =
+			(struct nfs4_get_lease_time_data *)calldata;
+
+	dprintk("--> %s\n", __func__);
+	/* just setup sequence, do not trigger session recovery
+	   since we're invoked within one */
+	ret = nfs41_setup_sequence(data->clp->cl_session,
+					&data->args->la_seq_args,
+					&data->res->lr_seq_res, 0, task);
+
+	BUG_ON(ret == -EAGAIN);
+	rpc_call_start(task);
+	dprintk("<-- %s\n", __func__);
+}
+
+/*
+ * Called from nfs4_state_manager thread for session setup, so don't recover
+ * from sequence operation or clientid errors.
+ */
+static void nfs4_get_lease_time_done(struct rpc_task *task, void *calldata)
+{
+	struct nfs4_get_lease_time_data *data =
+			(struct nfs4_get_lease_time_data *)calldata;
+
+	dprintk("--> %s\n", __func__);
+	nfs41_sequence_done(data->clp, &data->res->lr_seq_res, task->tk_status);
+	switch (task->tk_status) {
+	case -NFS4ERR_DELAY:
+	case -NFS4ERR_GRACE:
+		dprintk("%s Retry: tk_status %d\n", __func__, task->tk_status);
+		rpc_delay(task, NFS4_POLL_RETRY_MIN);
+		task->tk_status = 0;
+		nfs4_restart_rpc(task, data->clp);
+		return;
+	}
+	nfs41_sequence_free_slot(data->clp, &data->res->lr_seq_res);
+	dprintk("<-- %s\n", __func__);
+}
+
+struct rpc_call_ops nfs4_get_lease_time_ops = {
+	.rpc_call_prepare = nfs4_get_lease_time_prepare,
+	.rpc_call_done = nfs4_get_lease_time_done,
+};
+
+int nfs4_proc_get_lease_time(struct nfs_client *clp, struct nfs_fsinfo *fsinfo)
+{
+	struct rpc_task *task;
+	struct nfs4_get_lease_time_args args;
+	struct nfs4_get_lease_time_res res = {
+		.lr_fsinfo = fsinfo,
+	};
+	struct nfs4_get_lease_time_data data = {
+		.args = &args,
+		.res = &res,
+		.clp = clp,
+	};
+	struct rpc_message msg = {
+		.rpc_proc = &nfs4_procedures[NFSPROC4_CLNT_GET_LEASE_TIME],
+		.rpc_argp = &args,
+		.rpc_resp = &res,
+	};
+	struct rpc_task_setup task_setup = {
+		.rpc_client = clp->cl_rpcclient,
+		.rpc_message = &msg,
+		.callback_ops = &nfs4_get_lease_time_ops,
+		.callback_data = &data
+	};
+	int status;
+
+	res.lr_seq_res.sr_slotid = NFS4_MAX_SLOT_TABLE;
+	dprintk("--> %s\n", __func__);
+	task = rpc_run_task(&task_setup);
+
+	if (IS_ERR(task))
+		status = PTR_ERR(task);
+	else {
+		status = task->tk_status;
+		rpc_put_task(task);
+	}
+	dprintk("<-- %s return %d\n", __func__, status);
+
+	return status;
+}
+
+/*
+ * Reset a slot table
+ */
+static int nfs4_reset_slot_table(struct nfs4_slot_table *tbl, int max_slots,
+		int old_max_slots, int ivalue)
+{
+	int i;
+	int ret = 0;
+
+	dprintk("--> %s: max_reqs=%u, tbl %p\n", __func__, max_slots, tbl);
+
+	/*
+	 * Until we have dynamic slot table adjustment, insist
+	 * upon the same slot table size
+	 */
+	if (max_slots != old_max_slots) {
+		dprintk("%s reset slot table does't match old\n",
+			__func__);
+		ret = -EINVAL; /*XXX NFS4ERR_REQ_TOO_BIG ? */
+		goto out;
+	}
+	spin_lock(&tbl->slot_tbl_lock);
+	for (i = 0; i < max_slots; ++i)
+		tbl->slots[i].seq_nr = ivalue;
+	tbl->highest_used_slotid = -1;
+	spin_unlock(&tbl->slot_tbl_lock);
+	dprintk("%s: tbl=%p slots=%p max_slots=%d\n", __func__,
+		tbl, tbl->slots, tbl->max_slots);
+out:
+	dprintk("<-- %s: return %d\n", __func__, ret);
+	return ret;
+}
+
+/*
+ * Reset the forechannel and backchannel slot tables
+ */
+static int nfs4_reset_slot_tables(struct nfs4_session *session)
+{
+	int status;
+
+	status = nfs4_reset_slot_table(&session->fc_slot_table,
+			session->fc_attrs.max_reqs,
+			session->fc_slot_table.max_slots,
+			1);
+	if (status)
+		return status;
+
+	status = nfs4_reset_slot_table(&session->bc_slot_table,
+			session->bc_attrs.max_reqs,
+			session->bc_slot_table.max_slots,
+			0);
+	return status;
+}
+
+/* Destroy the slot table */
+static void nfs4_destroy_slot_tables(struct nfs4_session *session)
+{
+	if (session->fc_slot_table.slots != NULL) {
+		kfree(session->fc_slot_table.slots);
+		session->fc_slot_table.slots = NULL;
+	}
+	if (session->bc_slot_table.slots != NULL) {
+		kfree(session->bc_slot_table.slots);
+		session->bc_slot_table.slots = NULL;
+	}
+	return;
+}
+
+/*
+ * Initialize slot table
+ */
+static int nfs4_init_slot_table(struct nfs4_slot_table *tbl,
+		int max_slots, int ivalue)
+{
+	int i;
+	struct nfs4_slot *slot;
+	int ret = -ENOMEM;
+
+	BUG_ON(max_slots > NFS4_MAX_SLOT_TABLE);
+
+	dprintk("--> %s: max_reqs=%u\n", __func__, max_slots);
+
+	slot = kcalloc(max_slots, sizeof(struct nfs4_slot), GFP_KERNEL);
+	if (!slot)
+		goto out;
+	for (i = 0; i < max_slots; ++i)
+		slot[i].seq_nr = ivalue;
+	ret = 0;
+
+	spin_lock(&tbl->slot_tbl_lock);
+	if (tbl->slots != NULL) {
+		spin_unlock(&tbl->slot_tbl_lock);
+		dprintk("%s: slot table already initialized. tbl=%p slots=%p\n",
+			__func__, tbl, tbl->slots);
+		WARN_ON(1);
+		goto out_free;
+	}
+	tbl->max_slots = max_slots;
+	tbl->slots = slot;
+	tbl->highest_used_slotid = -1;  /* no slot is currently used */
+	spin_unlock(&tbl->slot_tbl_lock);
+	dprintk("%s: tbl=%p slots=%p max_slots=%d\n", __func__,
+		tbl, tbl->slots, tbl->max_slots);
+out:
+	dprintk("<-- %s: return %d\n", __func__, ret);
+	return ret;
+
+out_free:
+	kfree(slot);
+	goto out;
+}
+
+/*
+ * Initialize the forechannel and backchannel tables
+ */
+static int nfs4_init_slot_tables(struct nfs4_session *session)
+{
+	int status;
+
+	status = nfs4_init_slot_table(&session->fc_slot_table,
+			session->fc_attrs.max_reqs, 1);
+	if (status)
+		return status;
+
+	status = nfs4_init_slot_table(&session->bc_slot_table,
+			session->bc_attrs.max_reqs, 0);
+	if (status)
+		nfs4_destroy_slot_tables(session);
+
+	return status;
+}
+
+struct nfs4_session *nfs4_alloc_session(struct nfs_client *clp)
+{
+	struct nfs4_session *session;
+	struct nfs4_slot_table *tbl;
+
+	session = kzalloc(sizeof(struct nfs4_session), GFP_KERNEL);
+	if (!session)
+		return NULL;
+
+	set_bit(NFS4CLNT_SESSION_SETUP, &clp->cl_state);
+	/*
+	 * 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
+	 */
+	clp->cl_cons_state = NFS_CS_SESSION_INITING;
+
+	tbl = &session->fc_slot_table;
+	spin_lock_init(&tbl->slot_tbl_lock);
+	rpc_init_wait_queue(&tbl->slot_tbl_waitq, "ForeChannel Slot table");
+
+	tbl = &session->bc_slot_table;
+	spin_lock_init(&tbl->slot_tbl_lock);
+	rpc_init_wait_queue(&tbl->slot_tbl_waitq, "BackChannel Slot table");
+
+	session->clp = clp;
+	return session;
+}
+
+void nfs4_destroy_session(struct nfs4_session *session)
+{
+	nfs4_proc_destroy_session(session);
+	dprintk("%s Destroy backchannel for xprt %p\n",
+		__func__, session->clp->cl_rpcclient->cl_xprt);
+	xprt_destroy_backchannel(session->clp->cl_rpcclient->cl_xprt,
+				NFS41_BC_MIN_CALLBACKS);
+	nfs4_destroy_slot_tables(session);
+	kfree(session);
+}
+
+/*
+ * Initialize the values to be used by the client in CREATE_SESSION
+ * If nfs4_init_session set the fore channel request and response sizes,
+ * use them.
+ *
+ * Set the back channel max_resp_sz_cached to zero to force the client to
+ * always set csa_cachethis to FALSE because the current implementation
+ * of the back channel DRC only supports caching the CB_SEQUENCE operation.
+ */
+static void nfs4_init_channel_attrs(struct nfs41_create_session_args *args)
+{
+	struct nfs4_session *session = args->client->cl_session;
+	unsigned int mxrqst_sz = session->fc_attrs.max_rqst_sz,
+		     mxresp_sz = session->fc_attrs.max_resp_sz;
+
+	if (mxrqst_sz == 0)
+		mxrqst_sz = NFS_MAX_FILE_IO_SIZE;
+	if (mxresp_sz == 0)
+		mxresp_sz = NFS_MAX_FILE_IO_SIZE;
+	/* Fore channel attributes */
+	args->fc_attrs.headerpadsz = 0;
+	args->fc_attrs.max_rqst_sz = mxrqst_sz;
+	args->fc_attrs.max_resp_sz = mxresp_sz;
+	args->fc_attrs.max_resp_sz_cached = mxresp_sz;
+	args->fc_attrs.max_ops = NFS4_MAX_OPS;
+	args->fc_attrs.max_reqs = session->clp->cl_rpcclient->cl_xprt->max_reqs;
+
+	dprintk("%s: Fore Channel : max_rqst_sz=%u max_resp_sz=%u "
+		"max_resp_sz_cached=%u max_ops=%u max_reqs=%u\n",
+		__func__,
+		args->fc_attrs.max_rqst_sz, args->fc_attrs.max_resp_sz,
+		args->fc_attrs.max_resp_sz_cached, args->fc_attrs.max_ops,
+		args->fc_attrs.max_reqs);
+
+	/* Back channel attributes */
+	args->bc_attrs.headerpadsz = 0;
+	args->bc_attrs.max_rqst_sz = PAGE_SIZE;
+	args->bc_attrs.max_resp_sz = PAGE_SIZE;
+	args->bc_attrs.max_resp_sz_cached = 0;
+	args->bc_attrs.max_ops = NFS4_MAX_BACK_CHANNEL_OPS;
+	args->bc_attrs.max_reqs = 1;
+
+	dprintk("%s: Back Channel : max_rqst_sz=%u max_resp_sz=%u "
+		"max_resp_sz_cached=%u max_ops=%u max_reqs=%u\n",
+		__func__,
+		args->bc_attrs.max_rqst_sz, args->bc_attrs.max_resp_sz,
+		args->bc_attrs.max_resp_sz_cached, args->bc_attrs.max_ops,
+		args->bc_attrs.max_reqs);
+}
+
+static int _verify_channel_attr(char *chan, char *attr_name, u32 sent, u32 rcvd)
+{
+	if (rcvd <= sent)
+		return 0;
+	printk(KERN_WARNING "%s: Session INVALID: %s channel %s increased. "
+		"sent=%u rcvd=%u\n", __func__, chan, attr_name, sent, rcvd);
+	return -EINVAL;
+}
+
+#define _verify_fore_channel_attr(_name_) \
+	_verify_channel_attr("fore", #_name_, \
+			     args->fc_attrs._name_, \
+			     session->fc_attrs._name_)
+
+#define _verify_back_channel_attr(_name_) \
+	_verify_channel_attr("back", #_name_, \
+			     args->bc_attrs._name_, \
+			     session->bc_attrs._name_)
+
+/*
+ * The server is not allowed to increase the fore channel header pad size,
+ * maximum response size, or maximum number of operations.
+ *
+ * The back channel attributes are only negotiatied down: We send what the
+ * (back channel) server insists upon.
+ */
+static int nfs4_verify_channel_attrs(struct nfs41_create_session_args *args,
+				     struct nfs4_session *session)
+{
+	int ret = 0;
+
+	ret |= _verify_fore_channel_attr(headerpadsz);
+	ret |= _verify_fore_channel_attr(max_resp_sz);
+	ret |= _verify_fore_channel_attr(max_ops);
+
+	ret |= _verify_back_channel_attr(headerpadsz);
+	ret |= _verify_back_channel_attr(max_rqst_sz);
+	ret |= _verify_back_channel_attr(max_resp_sz);
+	ret |= _verify_back_channel_attr(max_resp_sz_cached);
+	ret |= _verify_back_channel_attr(max_ops);
+	ret |= _verify_back_channel_attr(max_reqs);
+
+	return ret;
+}
+
+static int _nfs4_proc_create_session(struct nfs_client *clp)
+{
+	struct nfs4_session *session = clp->cl_session;
+	struct nfs41_create_session_args args = {
+		.client = clp,
+		.cb_program = NFS4_CALLBACK,
+	};
+	struct nfs41_create_session_res res = {
+		.client = clp,
+	};
+	struct rpc_message msg = {
+		.rpc_proc = &nfs4_procedures[NFSPROC4_CLNT_CREATE_SESSION],
+		.rpc_argp = &args,
+		.rpc_resp = &res,
+	};
+	int status;
+
+	nfs4_init_channel_attrs(&args);
+	args.flags = (SESSION4_PERSIST | SESSION4_BACK_CHAN);
+
+	status = rpc_call_sync(session->clp->cl_rpcclient, &msg, 0);
+
+	if (!status)
+		/* Verify the session's negotiated channel_attrs values */
+		status = nfs4_verify_channel_attrs(&args, session);
+	if (!status) {
+		/* Increment the clientid slot sequence id */
+		clp->cl_seqid++;
+	}
+
+	return status;
+}
+
+/*
+ * Issues a CREATE_SESSION operation to the server.
+ * It is the responsibility of the caller to verify the session is
+ * expired before calling this routine.
+ */
+int nfs4_proc_create_session(struct nfs_client *clp, int reset)
+{
+	int status;
+	unsigned *ptr;
+	struct nfs_fsinfo fsinfo;
+	struct nfs4_session *session = clp->cl_session;
+
+	dprintk("--> %s clp=%p session=%p\n", __func__, clp, session);
+
+	status = _nfs4_proc_create_session(clp);
+	if (status)
+		goto out;
+
+	/* Init or reset the fore channel */
+	if (reset)
+		status = nfs4_reset_slot_tables(session);
+	else
+		status = nfs4_init_slot_tables(session);
+	dprintk("fore channel slot table initialization returned %d\n", status);
+	if (status)
+		goto out;
+
+	ptr = (unsigned *)&session->sess_id.data[0];
+	dprintk("%s client>seqid %d sessionid %u:%u:%u:%u\n", __func__,
+		clp->cl_seqid, ptr[0], ptr[1], ptr[2], ptr[3]);
+
+	if (reset)
+		/* Lease time is aleady set */
+		goto out;
+
+	/* Get the lease time */
+	status = nfs4_proc_get_lease_time(clp, &fsinfo);
+	if (status == 0) {
+		/* Update lease time and schedule renewal */
+		spin_lock(&clp->cl_lock);
+		clp->cl_lease_time = fsinfo.lease_time * HZ;
+		clp->cl_last_renewal = jiffies;
+		clear_bit(NFS4CLNT_LEASE_EXPIRED, &clp->cl_state);
+		spin_unlock(&clp->cl_lock);
+
+		nfs4_schedule_state_renewal(clp);
+	}
+out:
+	dprintk("<-- %s\n", __func__);
+	return status;
+}
+
+/*
+ * Issue the over-the-wire RPC DESTROY_SESSION.
+ * The caller must serialize access to this routine.
+ */
+int nfs4_proc_destroy_session(struct nfs4_session *session)
+{
+	int status = 0;
+	struct rpc_message msg;
+
+	dprintk("--> nfs4_proc_destroy_session\n");
+
+	/* session is still being setup */
+	if (session->clp->cl_cons_state != NFS_CS_READY)
+		return status;
+
+	msg.rpc_proc = &nfs4_procedures[NFSPROC4_CLNT_DESTROY_SESSION];
+	msg.rpc_argp = session;
+	msg.rpc_resp = NULL;
+	msg.rpc_cred = NULL;
+	status = rpc_call_sync(session->clp->cl_rpcclient, &msg, 0);
+
+	if (status)
+		printk(KERN_WARNING
+			"Got error %d from the server on DESTROY_SESSION. "
+			"Session has been destroyed regardless...\n", status);
+
+	dprintk("<-- nfs4_proc_destroy_session\n");
+	return status;
+}
+
+/*
+ * Renew the cl_session lease.
+ */
+static int nfs4_proc_sequence(struct nfs_client *clp, struct rpc_cred *cred)
+{
+	struct nfs4_sequence_args args;
+	struct nfs4_sequence_res res;
+
+	struct rpc_message msg = {
+		.rpc_proc = &nfs4_procedures[NFSPROC4_CLNT_SEQUENCE],
+		.rpc_argp = &args,
+		.rpc_resp = &res,
+		.rpc_cred = cred,
+	};
+
+	args.sa_cache_this = 0;
+
+	return nfs4_call_sync_sequence(clp, clp->cl_rpcclient, &msg, &args,
+				       &res, 0);
+}
+
+void nfs41_sequence_call_done(struct rpc_task *task, void *data)
+{
+	struct nfs_client *clp = (struct nfs_client *)data;
+
+	nfs41_sequence_done(clp, task->tk_msg.rpc_resp, task->tk_status);
+
+	if (task->tk_status < 0) {
+		dprintk("%s ERROR %d\n", __func__, task->tk_status);
+
+		if (_nfs4_async_handle_error(task, NULL, clp, NULL)
+								== -EAGAIN) {
+			nfs4_restart_rpc(task, clp);
+			return;
+		}
+	}
+	nfs41_sequence_free_slot(clp, task->tk_msg.rpc_resp);
+	dprintk("%s rpc_cred %p\n", __func__, task->tk_msg.rpc_cred);
+
+	put_rpccred(task->tk_msg.rpc_cred);
+	kfree(task->tk_msg.rpc_argp);
+	kfree(task->tk_msg.rpc_resp);
+
+	dprintk("<-- %s\n", __func__);
+}
+
+static void nfs41_sequence_prepare(struct rpc_task *task, void *data)
+{
+	struct nfs_client *clp;
+	struct nfs4_sequence_args *args;
+	struct nfs4_sequence_res *res;
+
+	clp = (struct nfs_client *)data;
+	args = task->tk_msg.rpc_argp;
+	res = task->tk_msg.rpc_resp;
+
+	if (nfs4_setup_sequence(clp, args, res, 0, task))
+		return;
+	rpc_call_start(task);
+}
+
+static const struct rpc_call_ops nfs41_sequence_ops = {
+	.rpc_call_done = nfs41_sequence_call_done,
+	.rpc_call_prepare = nfs41_sequence_prepare,
+};
+
+static int nfs41_proc_async_sequence(struct nfs_client *clp,
+				     struct rpc_cred *cred)
+{
+	struct nfs4_sequence_args *args;
+	struct nfs4_sequence_res *res;
+	struct rpc_message msg = {
+		.rpc_proc = &nfs4_procedures[NFSPROC4_CLNT_SEQUENCE],
+		.rpc_cred = cred,
+	};
+
+	args = kzalloc(sizeof(*args), GFP_KERNEL);
+	if (!args)
+		return -ENOMEM;
+	res = kzalloc(sizeof(*res), GFP_KERNEL);
+	if (!res) {
+		kfree(args);
+		return -ENOMEM;
+	}
+	res->sr_slotid = NFS4_MAX_SLOT_TABLE;
+	msg.rpc_argp = args;
+	msg.rpc_resp = res;
+
+	return rpc_call_async(clp->cl_rpcclient, &msg, RPC_TASK_SOFT,
+			      &nfs41_sequence_ops, (void *)clp);
+}
+
+#endif /* CONFIG_NFS_V4_1 */
+
+struct nfs4_state_recovery_ops nfs40_reboot_recovery_ops = {
 	.owner_flag_bit = NFS_OWNER_RECLAIM_REBOOT,
 	.state_flag_bit	= NFS_STATE_RECLAIM_REBOOT,
 	.recover_open	= nfs4_open_reclaim,
 	.recover_lock	= nfs4_lock_reclaim,
+	.establish_clid = nfs4_init_clientid,
+	.get_clid_cred	= nfs4_get_setclientid_cred,
+};
+
+#if defined(CONFIG_NFS_V4_1)
+struct nfs4_state_recovery_ops nfs41_reboot_recovery_ops = {
+	.owner_flag_bit = NFS_OWNER_RECLAIM_REBOOT,
+	.state_flag_bit	= NFS_STATE_RECLAIM_REBOOT,
+	.recover_open	= nfs4_open_reclaim,
+	.recover_lock	= nfs4_lock_reclaim,
+	.establish_clid = nfs4_proc_exchange_id,
+	.get_clid_cred	= nfs4_get_exchange_id_cred,
+};
+#endif /* CONFIG_NFS_V4_1 */
+
+struct nfs4_state_recovery_ops nfs40_nograce_recovery_ops = {
+	.owner_flag_bit = NFS_OWNER_RECLAIM_NOGRACE,
+	.state_flag_bit	= NFS_STATE_RECLAIM_NOGRACE,
+	.recover_open	= nfs4_open_expired,
+	.recover_lock	= nfs4_lock_expired,
+	.establish_clid = nfs4_init_clientid,
+	.get_clid_cred	= nfs4_get_setclientid_cred,
 };
 
-struct nfs4_state_recovery_ops nfs4_nograce_recovery_ops = {
+#if defined(CONFIG_NFS_V4_1)
+struct nfs4_state_recovery_ops nfs41_nograce_recovery_ops = {
 	.owner_flag_bit = NFS_OWNER_RECLAIM_NOGRACE,
 	.state_flag_bit	= NFS_STATE_RECLAIM_NOGRACE,
 	.recover_open	= nfs4_open_expired,
 	.recover_lock	= nfs4_lock_expired,
+	.establish_clid = nfs4_proc_exchange_id,
+	.get_clid_cred	= nfs4_get_exchange_id_cred,
+};
+#endif /* CONFIG_NFS_V4_1 */
+
+struct nfs4_state_maintenance_ops nfs40_state_renewal_ops = {
+	.sched_state_renewal = nfs4_proc_async_renew,
+	.get_state_renewal_cred_locked = nfs4_get_renew_cred_locked,
+	.renew_lease = nfs4_proc_renew,
+};
+
+#if defined(CONFIG_NFS_V4_1)
+struct nfs4_state_maintenance_ops nfs41_state_renewal_ops = {
+	.sched_state_renewal = nfs41_proc_async_sequence,
+	.get_state_renewal_cred_locked = nfs4_get_machine_cred_locked,
+	.renew_lease = nfs4_proc_sequence,
+};
+#endif
+
+/*
+ * Per minor version reboot and network partition recovery ops
+ */
+
+struct nfs4_state_recovery_ops *nfs4_reboot_recovery_ops[] = {
+	&nfs40_reboot_recovery_ops,
+#if defined(CONFIG_NFS_V4_1)
+	&nfs41_reboot_recovery_ops,
+#endif
+};
+
+struct nfs4_state_recovery_ops *nfs4_nograce_recovery_ops[] = {
+	&nfs40_nograce_recovery_ops,
+#if defined(CONFIG_NFS_V4_1)
+	&nfs41_nograce_recovery_ops,
+#endif
+};
+
+struct nfs4_state_maintenance_ops *nfs4_state_renewal_ops[] = {
+	&nfs40_state_renewal_ops,
+#if defined(CONFIG_NFS_V4_1)
+	&nfs41_state_renewal_ops,
+#endif
 };
 
 static const struct inode_operations nfs4_file_inode_operations = {

fs/nfs/nfs4renewd.c

@@ -59,12 +59,14 @@
 void
 nfs4_renew_state(struct work_struct *work)
 {
+	struct nfs4_state_maintenance_ops *ops;
 	struct nfs_client *clp =
 		container_of(work, struct nfs_client, cl_renewd.work);
 	struct rpc_cred *cred;
 	long lease, timeout;
 	unsigned long last, now;
 
+	ops = nfs4_state_renewal_ops[clp->cl_minorversion];
 	dprintk("%s: start\n", __func__);
 	/* Are there any active superblocks? */
 	if (list_empty(&clp->cl_superblocks))
@@ -76,7 +78,7 @@ nfs4_renew_state(struct work_struct *work)
 	timeout = (2 * lease) / 3 + (long)last - (long)now;
 	/* Are we close to a lease timeout? */
 	if (time_after(now, last + lease/3)) {
-		cred = nfs4_get_renew_cred_locked(clp);
+		cred = ops->get_state_renewal_cred_locked(clp);
 		spin_unlock(&clp->cl_lock);
 		if (cred == NULL) {
 			if (list_empty(&clp->cl_delegations)) {
@@ -86,7 +88,7 @@ nfs4_renew_state(struct work_struct *work)
 			nfs_expire_all_delegations(clp);
 		} else {
 			/* Queue an asynchronous RENEW. */
-			nfs4_proc_async_renew(clp, cred);
+			ops->sched_state_renewal(clp, cred);
 			put_rpccred(cred);
 		}
 		timeout = (2 * lease) / 3;

fs/nfs/nfs4state.c

@@ -60,7 +60,7 @@ const nfs4_stateid zero_stateid;
 
 static LIST_HEAD(nfs4_clientid_list);
 
-static int nfs4_init_client(struct nfs_client *clp, struct rpc_cred *cred)
+int nfs4_init_clientid(struct nfs_client *clp, struct rpc_cred *cred)
 {
 	unsigned short port;
 	int status;
@@ -77,7 +77,7 @@ static int nfs4_init_client(struct nfs_client *clp, struct rpc_cred *cred)
 	return status;
 }
 
-static struct rpc_cred *nfs4_get_machine_cred_locked(struct nfs_client *clp)
+struct rpc_cred *nfs4_get_machine_cred_locked(struct nfs_client *clp)
 {
 	struct rpc_cred *cred = NULL;
 
@@ -114,17 +114,21 @@ struct rpc_cred *nfs4_get_renew_cred_locked(struct nfs_client *clp)
 	return cred;
 }
 
-static struct rpc_cred *nfs4_get_renew_cred(struct nfs_client *clp)
+#if defined(CONFIG_NFS_V4_1)
+
+struct rpc_cred *nfs4_get_exchange_id_cred(struct nfs_client *clp)
 {
 	struct rpc_cred *cred;
 
 	spin_lock(&clp->cl_lock);
-	cred = nfs4_get_renew_cred_locked(clp);
+	cred = nfs4_get_machine_cred_locked(clp);
 	spin_unlock(&clp->cl_lock);
 	return cred;
 }
 
-static struct rpc_cred *nfs4_get_setclientid_cred(struct nfs_client *clp)
+#endif /* CONFIG_NFS_V4_1 */
+
+struct rpc_cred *nfs4_get_setclientid_cred(struct nfs_client *clp)
 {
 	struct nfs4_state_owner *sp;
 	struct rb_node *pos;
@@ -738,12 +742,14 @@ static void nfs_increment_seqid(int status, struct nfs_seqid *seqid)
 
 void nfs_increment_open_seqid(int status, struct nfs_seqid *seqid)
 {
-	if (status == -NFS4ERR_BAD_SEQID) {
-		struct nfs4_state_owner *sp = container_of(seqid->sequence,
-				struct nfs4_state_owner, so_seqid);
+	struct nfs4_state_owner *sp = container_of(seqid->sequence,
+					struct nfs4_state_owner, so_seqid);
+	struct nfs_server *server = sp->so_server;
+
+	if (status == -NFS4ERR_BAD_SEQID)
 		nfs4_drop_state_owner(sp);
-	}
-	nfs_increment_seqid(status, seqid);
+	if (!nfs4_has_session(server->nfs_client))
+		nfs_increment_seqid(status, seqid);
 }
 
 /*
@@ -847,32 +853,45 @@ static int nfs4_reclaim_locks(struct nfs4_state *state, const struct nfs4_state_
 	struct file_lock *fl;
 	int status = 0;
 
+	if (inode->i_flock == NULL)
+		return 0;
+
+	/* Guard against delegation returns and new lock/unlock calls */
 	down_write(&nfsi->rwsem);
+	/* Protect inode->i_flock using the BKL */
+	lock_kernel();
 	for (fl = inode->i_flock; fl != NULL; fl = fl->fl_next) {
 		if (!(fl->fl_flags & (FL_POSIX|FL_FLOCK)))
 			continue;
 		if (nfs_file_open_context(fl->fl_file)->state != state)
 			continue;
+		unlock_kernel();
 		status = ops->recover_lock(state, fl);
-		if (status >= 0)
-			continue;
 		switch (status) {
+			case 0:
+				break;
+			case -ESTALE:
+			case -NFS4ERR_ADMIN_REVOKED:
+			case -NFS4ERR_STALE_STATEID:
+			case -NFS4ERR_BAD_STATEID:
+			case -NFS4ERR_EXPIRED:
+			case -NFS4ERR_NO_GRACE:
+			case -NFS4ERR_STALE_CLIENTID:
+				goto out;
 			default:
 				printk(KERN_ERR "%s: unhandled error %d. Zeroing state\n",
 						__func__, status);
-			case -NFS4ERR_EXPIRED:
-			case -NFS4ERR_NO_GRACE:
+			case -ENOMEM:
+			case -NFS4ERR_DENIED:
 			case -NFS4ERR_RECLAIM_BAD:
 			case -NFS4ERR_RECLAIM_CONFLICT:
 				/* kill_proc(fl->fl_pid, SIGLOST, 1); */
-				break;
-			case -NFS4ERR_STALE_CLIENTID:
-				goto out_err;
+				status = 0;
 		}
+		lock_kernel();
 	}
-	up_write(&nfsi->rwsem);
-	return 0;
-out_err:
+	unlock_kernel();
+out:
 	up_write(&nfsi->rwsem);
 	return status;
 }
@@ -918,6 +937,7 @@ restart:
 				printk(KERN_ERR "%s: unhandled error %d. Zeroing state\n",
 						__func__, status);
 			case -ENOENT:
+			case -ENOMEM:
 			case -ESTALE:
 				/*
 				 * Open state on this file cannot be recovered
@@ -928,6 +948,9 @@ restart:
 				/* Mark the file as being 'closed' */
 				state->state = 0;
 				break;
+			case -NFS4ERR_ADMIN_REVOKED:
+			case -NFS4ERR_STALE_STATEID:
+			case -NFS4ERR_BAD_STATEID:
 			case -NFS4ERR_RECLAIM_BAD:
 			case -NFS4ERR_RECLAIM_CONFLICT:
 				nfs4_state_mark_reclaim_nograce(sp->so_client, state);
@@ -1042,6 +1065,14 @@ static void nfs4_recovery_handle_error(struct nfs_client *clp, int error)
 		case -NFS4ERR_EXPIRED:
 			set_bit(NFS4CLNT_LEASE_EXPIRED, &clp->cl_state);
 			nfs4_state_start_reclaim_nograce(clp);
+		case -NFS4ERR_BADSESSION:
+		case -NFS4ERR_BADSLOT:
+		case -NFS4ERR_BAD_HIGH_SLOT:
+		case -NFS4ERR_DEADSESSION:
+		case -NFS4ERR_CONN_NOT_BOUND_TO_SESSION:
+		case -NFS4ERR_SEQ_FALSE_RETRY:
+		case -NFS4ERR_SEQ_MISORDERED:
+			set_bit(NFS4CLNT_SESSION_SETUP, &clp->cl_state);
 	}
 }
 
@@ -1075,18 +1106,22 @@ restart:
 static int nfs4_check_lease(struct nfs_client *clp)
 {
 	struct rpc_cred *cred;
+	struct nfs4_state_maintenance_ops *ops =
+		nfs4_state_renewal_ops[clp->cl_minorversion];
 	int status = -NFS4ERR_EXPIRED;
 
 	/* Is the client already known to have an expired lease? */
 	if (test_bit(NFS4CLNT_LEASE_EXPIRED, &clp->cl_state))
 		return 0;
-	cred = nfs4_get_renew_cred(clp);
+	spin_lock(&clp->cl_lock);
+	cred = ops->get_state_renewal_cred_locked(clp);
+	spin_unlock(&clp->cl_lock);
 	if (cred == NULL) {
 		cred = nfs4_get_setclientid_cred(clp);
 		if (cred == NULL)
 			goto out;
 	}
-	status = nfs4_proc_renew(clp, cred);
+	status = ops->renew_lease(clp, cred);
 	put_rpccred(cred);
 out:
 	nfs4_recovery_handle_error(clp, status);
@@ -1096,21 +1131,98 @@ out:
 static int nfs4_reclaim_lease(struct nfs_client *clp)
 {
 	struct rpc_cred *cred;
+	struct nfs4_state_recovery_ops *ops =
+		nfs4_reboot_recovery_ops[clp->cl_minorversion];
 	int status = -ENOENT;
 
-	cred = nfs4_get_setclientid_cred(clp);
+	cred = ops->get_clid_cred(clp);
 	if (cred != NULL) {
-		status = nfs4_init_client(clp, cred);
+		status = ops->establish_clid(clp, cred);
 		put_rpccred(cred);
 		/* Handle case where the user hasn't set up machine creds */
 		if (status == -EACCES && cred == clp->cl_machine_cred) {
 			nfs4_clear_machine_cred(clp);
 			status = -EAGAIN;
 		}
+		if (status == -NFS4ERR_MINOR_VERS_MISMATCH)
+			status = -EPROTONOSUPPORT;
+	}
+	return status;
+}
+
+#ifdef CONFIG_NFS_V4_1
+static void nfs4_session_recovery_handle_error(struct nfs_client *clp, int err)
+{
+	switch (err) {
+	case -NFS4ERR_STALE_CLIENTID:
+		set_bit(NFS4CLNT_LEASE_EXPIRED, &clp->cl_state);
+		set_bit(NFS4CLNT_SESSION_SETUP, &clp->cl_state);
+	}
+}
+
+static int nfs4_reset_session(struct nfs_client *clp)
+{
+	int status;
+
+	status = nfs4_proc_destroy_session(clp->cl_session);
+	if (status && status != -NFS4ERR_BADSESSION &&
+	    status != -NFS4ERR_DEADSESSION) {
+		nfs4_session_recovery_handle_error(clp, status);
+		goto out;
 	}
+
+	memset(clp->cl_session->sess_id.data, 0, NFS4_MAX_SESSIONID_LEN);
+	status = nfs4_proc_create_session(clp, 1);
+	if (status)
+		nfs4_session_recovery_handle_error(clp, status);
+		/* fall through*/
+out:
+	/* Wake up the next rpc task even on error */
+	rpc_wake_up_next(&clp->cl_session->fc_slot_table.slot_tbl_waitq);
 	return status;
 }
 
+static int nfs4_initialize_session(struct nfs_client *clp)
+{
+	int status;
+
+	status = nfs4_proc_create_session(clp, 0);
+	if (!status) {
+		nfs_mark_client_ready(clp, NFS_CS_READY);
+	} else if (status == -NFS4ERR_STALE_CLIENTID) {
+		set_bit(NFS4CLNT_LEASE_EXPIRED, &clp->cl_state);
+		set_bit(NFS4CLNT_SESSION_SETUP, &clp->cl_state);
+	} else {
+		nfs_mark_client_ready(clp, status);
+	}
+	return status;
+}
+#else /* CONFIG_NFS_V4_1 */
+static int nfs4_reset_session(struct nfs_client *clp) { return 0; }
+static int nfs4_initialize_session(struct nfs_client *clp) { return 0; }
+#endif /* CONFIG_NFS_V4_1 */
+
+/* Set NFS4CLNT_LEASE_EXPIRED for all v4.0 errors and for recoverable errors
+ * on EXCHANGE_ID for v4.1
+ */
+static void nfs4_set_lease_expired(struct nfs_client *clp, int status)
+{
+	if (nfs4_has_session(clp)) {
+		switch (status) {
+		case -NFS4ERR_DELAY:
+		case -NFS4ERR_CLID_INUSE:
+		case -EAGAIN:
+			break;
+
+		case -NFS4ERR_NOT_SAME: /* FixMe: implement recovery
+					 * in nfs4_exchange_id */
+		default:
+			return;
+		}
+	}
+	set_bit(NFS4CLNT_LEASE_EXPIRED, &clp->cl_state);
+}
+
 static void nfs4_state_manager(struct nfs_client *clp)
 {
 	int status = 0;
@@ -1121,9 +1233,12 @@ static void nfs4_state_manager(struct nfs_client *clp)
 			/* We're going to have to re-establish a clientid */
 			status = nfs4_reclaim_lease(clp);
 			if (status) {
-				set_bit(NFS4CLNT_LEASE_EXPIRED, &clp->cl_state);
+				nfs4_set_lease_expired(clp, status);
 				if (status == -EAGAIN)
 					continue;
+				if (clp->cl_cons_state ==
+							NFS_CS_SESSION_INITING)
+					nfs_mark_client_ready(clp, status);
 				goto out_error;
 			}
 			clear_bit(NFS4CLNT_CHECK_LEASE, &clp->cl_state);
@@ -1134,25 +1249,44 @@ static void nfs4_state_manager(struct nfs_client *clp)
 			if (status != 0)
 				continue;
 		}
-
+		/* Initialize or reset the session */
+		if (nfs4_has_session(clp) &&
+		   test_and_clear_bit(NFS4CLNT_SESSION_SETUP, &clp->cl_state)) {
+			if (clp->cl_cons_state == NFS_CS_SESSION_INITING)
+				status = nfs4_initialize_session(clp);
+			else
+				status = nfs4_reset_session(clp);
+			if (status) {
+				if (status == -NFS4ERR_STALE_CLIENTID)
+					continue;
+				goto out_error;
+			}
+		}
 		/* First recover reboot state... */
 		if (test_and_clear_bit(NFS4CLNT_RECLAIM_REBOOT, &clp->cl_state)) {
-			status = nfs4_do_reclaim(clp, &nfs4_reboot_recovery_ops);
+			status = nfs4_do_reclaim(clp,
+				nfs4_reboot_recovery_ops[clp->cl_minorversion]);
 			if (status == -NFS4ERR_STALE_CLIENTID)
 				continue;
+			if (test_bit(NFS4CLNT_SESSION_SETUP, &clp->cl_state))
+				continue;
 			nfs4_state_end_reclaim_reboot(clp);
 			continue;
 		}
 
 		/* Now recover expired state... */
 		if (test_and_clear_bit(NFS4CLNT_RECLAIM_NOGRACE, &clp->cl_state)) {
-			status = nfs4_do_reclaim(clp, &nfs4_nograce_recovery_ops);
+			status = nfs4_do_reclaim(clp,
+				nfs4_nograce_recovery_ops[clp->cl_minorversion]);
 			if (status < 0) {
 				set_bit(NFS4CLNT_RECLAIM_NOGRACE, &clp->cl_state);
 				if (status == -NFS4ERR_STALE_CLIENTID)
 					continue;
 				if (status == -NFS4ERR_EXPIRED)
 					continue;
+				if (test_bit(NFS4CLNT_SESSION_SETUP,
+								&clp->cl_state))
+					continue;
 				goto out_error;
 			} else
 				nfs4_state_end_reclaim_nograce(clp);

fs/nfs/nfs4xdr.c

@@ -192,12 +192,16 @@ static int nfs4_stat_to_errno(int);
 				 decode_verifier_maxsz)
 #define encode_remove_maxsz	(op_encode_hdr_maxsz + \
 				nfs4_name_maxsz)
+#define decode_remove_maxsz	(op_decode_hdr_maxsz + \
+				 decode_change_info_maxsz)
 #define encode_rename_maxsz	(op_encode_hdr_maxsz + \
 				2 * nfs4_name_maxsz)
-#define decode_rename_maxsz	(op_decode_hdr_maxsz + 5 + 5)
+#define decode_rename_maxsz	(op_decode_hdr_maxsz + \
+				 decode_change_info_maxsz + \
+				 decode_change_info_maxsz)
 #define encode_link_maxsz	(op_encode_hdr_maxsz + \
 				nfs4_name_maxsz)
-#define decode_link_maxsz	(op_decode_hdr_maxsz + 5)
+#define decode_link_maxsz	(op_decode_hdr_maxsz + decode_change_info_maxsz)
 #define encode_lock_maxsz	(op_encode_hdr_maxsz + \
 				 7 + \
 				 1 + encode_stateid_maxsz + 8)
@@ -240,43 +244,115 @@ static int nfs4_stat_to_errno(int);
 				(encode_getattr_maxsz)
 #define decode_fs_locations_maxsz \
 				(0)
+
+#if defined(CONFIG_NFS_V4_1)
+#define NFS4_MAX_MACHINE_NAME_LEN (64)
+
+#define encode_exchange_id_maxsz (op_encode_hdr_maxsz + \
+				encode_verifier_maxsz + \
+				1 /* co_ownerid.len */ + \
+				XDR_QUADLEN(NFS4_EXCHANGE_ID_LEN) + \
+				1 /* flags */ + \
+				1 /* spa_how */ + \
+				0 /* SP4_NONE (for now) */ + \
+				1 /* zero implemetation id array */)
+#define decode_exchange_id_maxsz (op_decode_hdr_maxsz + \
+				2 /* eir_clientid */ + \
+				1 /* eir_sequenceid */ + \
+				1 /* eir_flags */ + \
+				1 /* spr_how */ + \
+				0 /* SP4_NONE (for now) */ + \
+				2 /* eir_server_owner.so_minor_id */ + \
+				/* eir_server_owner.so_major_id<> */ \
+				XDR_QUADLEN(NFS4_OPAQUE_LIMIT) + 1 + \
+				/* eir_server_scope<> */ \
+				XDR_QUADLEN(NFS4_OPAQUE_LIMIT) + 1 + \
+				1 /* eir_server_impl_id array length */ + \
+				0 /* ignored eir_server_impl_id contents */)
+#define encode_channel_attrs_maxsz  (6 + 1 /* ca_rdma_ird.len (0) */)
+#define decode_channel_attrs_maxsz  (6 + \
+				     1 /* ca_rdma_ird.len */ + \
+				     1 /* ca_rdma_ird */)
+#define encode_create_session_maxsz  (op_encode_hdr_maxsz + \
+				     2 /* csa_clientid */ + \
+				     1 /* csa_sequence */ + \
+				     1 /* csa_flags */ + \
+				     encode_channel_attrs_maxsz + \
+				     encode_channel_attrs_maxsz + \
+				     1 /* csa_cb_program */ + \
+				     1 /* csa_sec_parms.len (1) */ + \
+				     1 /* cb_secflavor (AUTH_SYS) */ + \
+				     1 /* stamp */ + \
+				     1 /* machinename.len */ + \
+				     XDR_QUADLEN(NFS4_MAX_MACHINE_NAME_LEN) + \
+				     1 /* uid */ + \
+				     1 /* gid */ + \
+				     1 /* gids.len (0) */)
+#define decode_create_session_maxsz  (op_decode_hdr_maxsz +	\
+				     XDR_QUADLEN(NFS4_MAX_SESSIONID_LEN) + \
+				     1 /* csr_sequence */ + \
+				     1 /* csr_flags */ + \
+				     decode_channel_attrs_maxsz + \
+				     decode_channel_attrs_maxsz)
+#define encode_destroy_session_maxsz    (op_encode_hdr_maxsz + 4)
+#define decode_destroy_session_maxsz    (op_decode_hdr_maxsz)
+#define encode_sequence_maxsz	(op_encode_hdr_maxsz + \
+				XDR_QUADLEN(NFS4_MAX_SESSIONID_LEN) + 4)
+#define decode_sequence_maxsz	(op_decode_hdr_maxsz + \
+				XDR_QUADLEN(NFS4_MAX_SESSIONID_LEN) + 5)
+#else /* CONFIG_NFS_V4_1 */
+#define encode_sequence_maxsz	0
+#define decode_sequence_maxsz	0
+#endif /* CONFIG_NFS_V4_1 */
+
 #define NFS4_enc_compound_sz	(1024)  /* XXX: large enough? */
 #define NFS4_dec_compound_sz	(1024)  /* XXX: large enough? */
 #define NFS4_enc_read_sz	(compound_encode_hdr_maxsz + \
+				encode_sequence_maxsz + \
 				encode_putfh_maxsz + \
 				encode_read_maxsz)
 #define NFS4_dec_read_sz	(compound_decode_hdr_maxsz + \
+				decode_sequence_maxsz + \
 				decode_putfh_maxsz + \
 				decode_read_maxsz)
 #define NFS4_enc_readlink_sz	(compound_encode_hdr_maxsz + \
+				encode_sequence_maxsz + \
 				encode_putfh_maxsz + \
 				encode_readlink_maxsz)
 #define NFS4_dec_readlink_sz	(compound_decode_hdr_maxsz + \
+				decode_sequence_maxsz + \
 				decode_putfh_maxsz + \
 				decode_readlink_maxsz)
 #define NFS4_enc_readdir_sz	(compound_encode_hdr_maxsz + \
+				encode_sequence_maxsz + \
 				encode_putfh_maxsz + \
 				encode_readdir_maxsz)
 #define NFS4_dec_readdir_sz	(compound_decode_hdr_maxsz + \
+				decode_sequence_maxsz + \
 				decode_putfh_maxsz + \
 				decode_readdir_maxsz)
 #define NFS4_enc_write_sz	(compound_encode_hdr_maxsz + \
+				encode_sequence_maxsz + \
 				encode_putfh_maxsz + \
 				encode_write_maxsz + \
 				encode_getattr_maxsz)
 #define NFS4_dec_write_sz	(compound_decode_hdr_maxsz + \
+				decode_sequence_maxsz + \
 				decode_putfh_maxsz + \
 				decode_write_maxsz + \
 				decode_getattr_maxsz)
 #define NFS4_enc_commit_sz	(compound_encode_hdr_maxsz + \
+				encode_sequence_maxsz + \
 				encode_putfh_maxsz + \
 				encode_commit_maxsz + \
 				encode_getattr_maxsz)
 #define NFS4_dec_commit_sz	(compound_decode_hdr_maxsz + \
+				decode_sequence_maxsz + \
 				decode_putfh_maxsz + \
 				decode_commit_maxsz + \
 				decode_getattr_maxsz)
 #define NFS4_enc_open_sz        (compound_encode_hdr_maxsz + \
+				encode_sequence_maxsz + \
 				encode_putfh_maxsz + \
 				encode_savefh_maxsz + \
 				encode_open_maxsz + \
@@ -285,6 +361,7 @@ static int nfs4_stat_to_errno(int);
 				encode_restorefh_maxsz + \
 				encode_getattr_maxsz)
 #define NFS4_dec_open_sz        (compound_decode_hdr_maxsz + \
+				decode_sequence_maxsz + \
 				decode_putfh_maxsz + \
 				decode_savefh_maxsz + \
 				decode_open_maxsz + \
@@ -301,43 +378,53 @@ static int nfs4_stat_to_errno(int);
 				 decode_putfh_maxsz + \
 				 decode_open_confirm_maxsz)
 #define NFS4_enc_open_noattr_sz	(compound_encode_hdr_maxsz + \
+					encode_sequence_maxsz + \
 					encode_putfh_maxsz + \
 					encode_open_maxsz + \
 					encode_getattr_maxsz)
 #define NFS4_dec_open_noattr_sz	(compound_decode_hdr_maxsz + \
+					decode_sequence_maxsz + \
 					decode_putfh_maxsz + \
 					decode_open_maxsz + \
 					decode_getattr_maxsz)
 #define NFS4_enc_open_downgrade_sz \
 				(compound_encode_hdr_maxsz + \
+				 encode_sequence_maxsz + \
 				 encode_putfh_maxsz + \
 				 encode_open_downgrade_maxsz + \
 				 encode_getattr_maxsz)
 #define NFS4_dec_open_downgrade_sz \
 				(compound_decode_hdr_maxsz + \
+				 decode_sequence_maxsz + \
 				 decode_putfh_maxsz + \
 				 decode_open_downgrade_maxsz + \
 				 decode_getattr_maxsz)
 #define NFS4_enc_close_sz	(compound_encode_hdr_maxsz + \
+				 encode_sequence_maxsz + \
 				 encode_putfh_maxsz + \
 				 encode_close_maxsz + \
 				 encode_getattr_maxsz)
 #define NFS4_dec_close_sz	(compound_decode_hdr_maxsz + \
+				 decode_sequence_maxsz + \
 				 decode_putfh_maxsz + \
 				 decode_close_maxsz + \
 				 decode_getattr_maxsz)
 #define NFS4_enc_setattr_sz	(compound_encode_hdr_maxsz + \
+				 encode_sequence_maxsz + \
 				 encode_putfh_maxsz + \
 				 encode_setattr_maxsz + \
 				 encode_getattr_maxsz)
 #define NFS4_dec_setattr_sz	(compound_decode_hdr_maxsz + \
+				 decode_sequence_maxsz + \
 				 decode_putfh_maxsz + \
 				 decode_setattr_maxsz + \
 				 decode_getattr_maxsz)
 #define NFS4_enc_fsinfo_sz	(compound_encode_hdr_maxsz + \
+				encode_sequence_maxsz + \
 				encode_putfh_maxsz + \
 				encode_fsinfo_maxsz)
 #define NFS4_dec_fsinfo_sz	(compound_decode_hdr_maxsz + \
+				decode_sequence_maxsz + \
 				decode_putfh_maxsz + \
 				decode_fsinfo_maxsz)
 #define NFS4_enc_renew_sz	(compound_encode_hdr_maxsz + \
@@ -359,64 +446,81 @@ static int nfs4_stat_to_errno(int);
 				decode_putrootfh_maxsz + \
 				decode_fsinfo_maxsz)
 #define NFS4_enc_lock_sz        (compound_encode_hdr_maxsz + \
+				encode_sequence_maxsz + \
 				encode_putfh_maxsz + \
 				encode_lock_maxsz)
 #define NFS4_dec_lock_sz        (compound_decode_hdr_maxsz + \
+				decode_sequence_maxsz + \
 				decode_putfh_maxsz + \
 				decode_lock_maxsz)
 #define NFS4_enc_lockt_sz       (compound_encode_hdr_maxsz + \
+				encode_sequence_maxsz + \
 				encode_putfh_maxsz + \
 				encode_lockt_maxsz)
 #define NFS4_dec_lockt_sz       (compound_decode_hdr_maxsz + \
+				 decode_sequence_maxsz + \
 				 decode_putfh_maxsz + \
 				 decode_lockt_maxsz)
 #define NFS4_enc_locku_sz       (compound_encode_hdr_maxsz + \
+				encode_sequence_maxsz + \
 				encode_putfh_maxsz + \
 				encode_locku_maxsz)
 #define NFS4_dec_locku_sz       (compound_decode_hdr_maxsz + \
+				decode_sequence_maxsz + \
 				decode_putfh_maxsz + \
 				decode_locku_maxsz)
 #define NFS4_enc_access_sz	(compound_encode_hdr_maxsz + \
+				encode_sequence_maxsz + \
 				encode_putfh_maxsz + \
 				encode_access_maxsz + \
 				encode_getattr_maxsz)
 #define NFS4_dec_access_sz	(compound_decode_hdr_maxsz + \
+				decode_sequence_maxsz + \
 				decode_putfh_maxsz + \
 				decode_access_maxsz + \
 				decode_getattr_maxsz)
 #define NFS4_enc_getattr_sz	(compound_encode_hdr_maxsz + \
+				encode_sequence_maxsz + \
 				encode_putfh_maxsz + \
 				encode_getattr_maxsz)
 #define NFS4_dec_getattr_sz	(compound_decode_hdr_maxsz + \
+				decode_sequence_maxsz + \
 				decode_putfh_maxsz + \
 				decode_getattr_maxsz)
 #define NFS4_enc_lookup_sz	(compound_encode_hdr_maxsz + \
+				encode_sequence_maxsz + \
 				encode_putfh_maxsz + \
 				encode_lookup_maxsz + \
 				encode_getattr_maxsz + \
 				encode_getfh_maxsz)
 #define NFS4_dec_lookup_sz	(compound_decode_hdr_maxsz + \
+				decode_sequence_maxsz + \
 				decode_putfh_maxsz + \
 				decode_lookup_maxsz + \
 				decode_getattr_maxsz + \
 				decode_getfh_maxsz)
 #define NFS4_enc_lookup_root_sz (compound_encode_hdr_maxsz + \
+				encode_sequence_maxsz + \
 				encode_putrootfh_maxsz + \
 				encode_getattr_maxsz + \
 				encode_getfh_maxsz)
 #define NFS4_dec_lookup_root_sz (compound_decode_hdr_maxsz + \
+				decode_sequence_maxsz + \
 				decode_putrootfh_maxsz + \
 				decode_getattr_maxsz + \
 				decode_getfh_maxsz)
 #define NFS4_enc_remove_sz	(compound_encode_hdr_maxsz + \
+				encode_sequence_maxsz + \
 				encode_putfh_maxsz + \
 				encode_remove_maxsz + \
 				encode_getattr_maxsz)
 #define NFS4_dec_remove_sz	(compound_decode_hdr_maxsz + \
+				decode_sequence_maxsz + \
 				decode_putfh_maxsz + \
-				op_decode_hdr_maxsz + 5 + \
+				decode_remove_maxsz + \
 				decode_getattr_maxsz)
 #define NFS4_enc_rename_sz	(compound_encode_hdr_maxsz + \
+				encode_sequence_maxsz + \
 				encode_putfh_maxsz + \
 				encode_savefh_maxsz + \
 				encode_putfh_maxsz + \
@@ -425,6 +529,7 @@ static int nfs4_stat_to_errno(int);
 				encode_restorefh_maxsz + \
 				encode_getattr_maxsz)
 #define NFS4_dec_rename_sz	(compound_decode_hdr_maxsz + \
+				decode_sequence_maxsz + \
 				decode_putfh_maxsz + \
 				decode_savefh_maxsz + \
 				decode_putfh_maxsz + \
@@ -433,6 +538,7 @@ static int nfs4_stat_to_errno(int);
 				decode_restorefh_maxsz + \
 				decode_getattr_maxsz)
 #define NFS4_enc_link_sz	(compound_encode_hdr_maxsz + \
+				encode_sequence_maxsz + \
 				encode_putfh_maxsz + \
 				encode_savefh_maxsz + \
 				encode_putfh_maxsz + \
@@ -441,6 +547,7 @@ static int nfs4_stat_to_errno(int);
 				encode_restorefh_maxsz + \
 				decode_getattr_maxsz)
 #define NFS4_dec_link_sz	(compound_decode_hdr_maxsz + \
+				decode_sequence_maxsz + \
 				decode_putfh_maxsz + \
 				decode_savefh_maxsz + \
 				decode_putfh_maxsz + \
@@ -449,16 +556,19 @@ static int nfs4_stat_to_errno(int);
 				decode_restorefh_maxsz + \
 				decode_getattr_maxsz)
 #define NFS4_enc_symlink_sz	(compound_encode_hdr_maxsz + \
+				encode_sequence_maxsz + \
 				encode_putfh_maxsz + \
 				encode_symlink_maxsz + \
 				encode_getattr_maxsz + \
 				encode_getfh_maxsz)
 #define NFS4_dec_symlink_sz	(compound_decode_hdr_maxsz + \
+				decode_sequence_maxsz + \
 				decode_putfh_maxsz + \
 				decode_symlink_maxsz + \
 				decode_getattr_maxsz + \
 				decode_getfh_maxsz)
 #define NFS4_enc_create_sz	(compound_encode_hdr_maxsz + \
+				encode_sequence_maxsz + \
 				encode_putfh_maxsz + \
 				encode_savefh_maxsz + \
 				encode_create_maxsz + \
@@ -467,6 +577,7 @@ static int nfs4_stat_to_errno(int);
 				encode_restorefh_maxsz + \
 				encode_getattr_maxsz)
 #define NFS4_dec_create_sz	(compound_decode_hdr_maxsz + \
+				decode_sequence_maxsz + \
 				decode_putfh_maxsz + \
 				decode_savefh_maxsz + \
 				decode_create_maxsz + \
@@ -475,52 +586,98 @@ static int nfs4_stat_to_errno(int);
 				decode_restorefh_maxsz + \
 				decode_getattr_maxsz)
 #define NFS4_enc_pathconf_sz	(compound_encode_hdr_maxsz + \
+				encode_sequence_maxsz + \
 				encode_putfh_maxsz + \
 				encode_getattr_maxsz)
 #define NFS4_dec_pathconf_sz	(compound_decode_hdr_maxsz + \
+				decode_sequence_maxsz + \
 				decode_putfh_maxsz + \
 				decode_getattr_maxsz)
 #define NFS4_enc_statfs_sz	(compound_encode_hdr_maxsz + \
+				encode_sequence_maxsz + \
 				encode_putfh_maxsz + \
 				encode_statfs_maxsz)
 #define NFS4_dec_statfs_sz	(compound_decode_hdr_maxsz + \
+				decode_sequence_maxsz + \
 				decode_putfh_maxsz + \
 				decode_statfs_maxsz)
 #define NFS4_enc_server_caps_sz (compound_encode_hdr_maxsz + \
+				encode_sequence_maxsz + \
 				encode_putfh_maxsz + \
 				encode_getattr_maxsz)
 #define NFS4_dec_server_caps_sz (compound_decode_hdr_maxsz + \
+				decode_sequence_maxsz + \
 				decode_putfh_maxsz + \
 				decode_getattr_maxsz)
 #define NFS4_enc_delegreturn_sz	(compound_encode_hdr_maxsz + \
+				encode_sequence_maxsz + \
 				encode_putfh_maxsz + \
 				encode_delegreturn_maxsz + \
 				encode_getattr_maxsz)
 #define NFS4_dec_delegreturn_sz (compound_decode_hdr_maxsz + \
+				decode_sequence_maxsz + \
 				decode_delegreturn_maxsz + \
 				decode_getattr_maxsz)
 #define NFS4_enc_getacl_sz	(compound_encode_hdr_maxsz + \
+				encode_sequence_maxsz + \
 				encode_putfh_maxsz + \
 				encode_getacl_maxsz)
 #define NFS4_dec_getacl_sz	(compound_decode_hdr_maxsz + \
+				decode_sequence_maxsz + \
 				decode_putfh_maxsz + \
 				decode_getacl_maxsz)
 #define NFS4_enc_setacl_sz	(compound_encode_hdr_maxsz + \
+				encode_sequence_maxsz + \
 				encode_putfh_maxsz + \
 				encode_setacl_maxsz)
 #define NFS4_dec_setacl_sz	(compound_decode_hdr_maxsz + \
+				decode_sequence_maxsz + \
 				decode_putfh_maxsz + \
 				decode_setacl_maxsz)
 #define NFS4_enc_fs_locations_sz \
 				(compound_encode_hdr_maxsz + \
+				 encode_sequence_maxsz + \
 				 encode_putfh_maxsz + \
 				 encode_lookup_maxsz + \
 				 encode_fs_locations_maxsz)
 #define NFS4_dec_fs_locations_sz \
 				(compound_decode_hdr_maxsz + \
+				 decode_sequence_maxsz + \
 				 decode_putfh_maxsz + \
 				 decode_lookup_maxsz + \
 				 decode_fs_locations_maxsz)
+#if defined(CONFIG_NFS_V4_1)
+#define NFS4_enc_exchange_id_sz \
+				(compound_encode_hdr_maxsz + \
+				 encode_exchange_id_maxsz)
+#define NFS4_dec_exchange_id_sz \
+				(compound_decode_hdr_maxsz + \
+				 decode_exchange_id_maxsz)
+#define NFS4_enc_create_session_sz \
+				(compound_encode_hdr_maxsz + \
+				 encode_create_session_maxsz)
+#define NFS4_dec_create_session_sz \
+				(compound_decode_hdr_maxsz + \
+				 decode_create_session_maxsz)
+#define NFS4_enc_destroy_session_sz	(compound_encode_hdr_maxsz + \
+					 encode_destroy_session_maxsz)
+#define NFS4_dec_destroy_session_sz	(compound_decode_hdr_maxsz + \
+					 decode_destroy_session_maxsz)
+#define NFS4_enc_sequence_sz \
+				(compound_decode_hdr_maxsz + \
+				 encode_sequence_maxsz)
+#define NFS4_dec_sequence_sz \
+				(compound_decode_hdr_maxsz + \
+				 decode_sequence_maxsz)
+#define NFS4_enc_get_lease_time_sz	(compound_encode_hdr_maxsz + \
+					 encode_sequence_maxsz + \
+					 encode_putrootfh_maxsz + \
+					 encode_fsinfo_maxsz)
+#define NFS4_dec_get_lease_time_sz	(compound_decode_hdr_maxsz + \
+					 decode_sequence_maxsz + \
+					 decode_putrootfh_maxsz + \
+					 decode_fsinfo_maxsz)
+#endif /* CONFIG_NFS_V4_1 */
 
 static const umode_t nfs_type2fmt[] = {
 	[NF4BAD] = 0,
@@ -541,6 +698,8 @@ struct compound_hdr {
 	__be32 *	nops_p;
 	uint32_t	taglen;
 	char *		tag;
+	uint32_t	replen;		/* expected reply words */
+	u32		minorversion;
 };
 
 /*
@@ -576,22 +735,31 @@ static void encode_string(struct xdr_stream *xdr, unsigned int len, const char *
 	xdr_encode_opaque(p, str, len);
 }
 
-static void encode_compound_hdr(struct xdr_stream *xdr, struct compound_hdr *hdr)
+static void encode_compound_hdr(struct xdr_stream *xdr,
+				struct rpc_rqst *req,
+				struct compound_hdr *hdr)
 {
 	__be32 *p;
+	struct rpc_auth *auth = req->rq_task->tk_msg.rpc_cred->cr_auth;
+
+	/* initialize running count of expected bytes in reply.
+	 * NOTE: the replied tag SHOULD be the same is the one sent,
+	 * but this is not required as a MUST for the server to do so. */
+	hdr->replen = RPC_REPHDRSIZE + auth->au_rslack + 3 + hdr->taglen;
 
 	dprintk("encode_compound: tag=%.*s\n", (int)hdr->taglen, hdr->tag);
 	BUG_ON(hdr->taglen > NFS4_MAXTAGLEN);
 	RESERVE_SPACE(12+(XDR_QUADLEN(hdr->taglen)<<2));
 	WRITE32(hdr->taglen);
 	WRITEMEM(hdr->tag, hdr->taglen);
-	WRITE32(NFS4_MINOR_VERSION);
+	WRITE32(hdr->minorversion);
 	hdr->nops_p = p;
 	WRITE32(hdr->nops);
 }
 
 static void encode_nops(struct compound_hdr *hdr)
 {
+	BUG_ON(hdr->nops > NFS4_MAX_OPS);
 	*hdr->nops_p = htonl(hdr->nops);
 }
 
@@ -736,6 +904,7 @@ static void encode_access(struct xdr_stream *xdr, u32 access, struct compound_hd
 	WRITE32(OP_ACCESS);
 	WRITE32(access);
 	hdr->nops++;
+	hdr->replen += decode_access_maxsz;
 }
 
 static void encode_close(struct xdr_stream *xdr, const struct nfs_closeargs *arg, struct compound_hdr *hdr)
@@ -747,6 +916,7 @@ static void encode_close(struct xdr_stream *xdr, const struct nfs_closeargs *arg
 	WRITE32(arg->seqid->sequence->counter);
 	WRITEMEM(arg->stateid->data, NFS4_STATEID_SIZE);
 	hdr->nops++;
+	hdr->replen += decode_close_maxsz;
 }
 
 static void encode_commit(struct xdr_stream *xdr, const struct nfs_writeargs *args, struct compound_hdr *hdr)
@@ -758,6 +928,7 @@ static void encode_commit(struct xdr_stream *xdr, const struct nfs_writeargs *ar
 	WRITE64(args->offset);
 	WRITE32(args->count);
 	hdr->nops++;
+	hdr->replen += decode_commit_maxsz;
 }
 
 static void encode_create(struct xdr_stream *xdr, const struct nfs4_create_arg *create, struct compound_hdr *hdr)
@@ -789,6 +960,7 @@ static void encode_create(struct xdr_stream *xdr, const struct nfs4_create_arg *
 	WRITE32(create->name->len);
 	WRITEMEM(create->name->name, create->name->len);
 	hdr->nops++;
+	hdr->replen += decode_create_maxsz;
 
 	encode_attrs(xdr, create->attrs, create->server);
 }
@@ -802,6 +974,7 @@ static void encode_getattr_one(struct xdr_stream *xdr, uint32_t bitmap, struct c
 	WRITE32(1);
 	WRITE32(bitmap);
 	hdr->nops++;
+	hdr->replen += decode_getattr_maxsz;
 }
 
 static void encode_getattr_two(struct xdr_stream *xdr, uint32_t bm0, uint32_t bm1, struct compound_hdr *hdr)
@@ -814,6 +987,7 @@ static void encode_getattr_two(struct xdr_stream *xdr, uint32_t bm0, uint32_t bm
 	WRITE32(bm0);
 	WRITE32(bm1);
 	hdr->nops++;
+	hdr->replen += decode_getattr_maxsz;
 }
 
 static void encode_getfattr(struct xdr_stream *xdr, const u32* bitmask, struct compound_hdr *hdr)
@@ -841,6 +1015,7 @@ static void encode_getfh(struct xdr_stream *xdr, struct compound_hdr *hdr)
 	RESERVE_SPACE(4);
 	WRITE32(OP_GETFH);
 	hdr->nops++;
+	hdr->replen += decode_getfh_maxsz;
 }
 
 static void encode_link(struct xdr_stream *xdr, const struct qstr *name, struct compound_hdr *hdr)
@@ -852,6 +1027,7 @@ static void encode_link(struct xdr_stream *xdr, const struct qstr *name, struct
 	WRITE32(name->len);
 	WRITEMEM(name->name, name->len);
 	hdr->nops++;
+	hdr->replen += decode_link_maxsz;
 }
 
 static inline int nfs4_lock_type(struct file_lock *fl, int block)
@@ -899,6 +1075,7 @@ static void encode_lock(struct xdr_stream *xdr, const struct nfs_lock_args *args
 		WRITE32(args->lock_seqid->sequence->counter);
 	}
 	hdr->nops++;
+	hdr->replen += decode_lock_maxsz;
 }
 
 static void encode_lockt(struct xdr_stream *xdr, const struct nfs_lockt_args *args, struct compound_hdr *hdr)
@@ -915,6 +1092,7 @@ static void encode_lockt(struct xdr_stream *xdr, const struct nfs_lockt_args *ar
 	WRITEMEM("lock id:", 8);
 	WRITE64(args->lock_owner.id);
 	hdr->nops++;
+	hdr->replen += decode_lockt_maxsz;
 }
 
 static void encode_locku(struct xdr_stream *xdr, const struct nfs_locku_args *args, struct compound_hdr *hdr)
@@ -929,6 +1107,7 @@ static void encode_locku(struct xdr_stream *xdr, const struct nfs_locku_args *ar
 	WRITE64(args->fl->fl_start);
 	WRITE64(nfs4_lock_length(args->fl));
 	hdr->nops++;
+	hdr->replen += decode_locku_maxsz;
 }
 
 static void encode_lookup(struct xdr_stream *xdr, const struct qstr *name, struct compound_hdr *hdr)
@@ -941,6 +1120,7 @@ static void encode_lookup(struct xdr_stream *xdr, const struct qstr *name, struc
 	WRITE32(len);
 	WRITEMEM(name->name, len);
 	hdr->nops++;
+	hdr->replen += decode_lookup_maxsz;
 }
 
 static void encode_share_access(struct xdr_stream *xdr, fmode_t fmode)
@@ -1080,6 +1260,7 @@ static void encode_open(struct xdr_stream *xdr, const struct nfs_openargs *arg,
 		BUG();
 	}
 	hdr->nops++;
+	hdr->replen += decode_open_maxsz;
 }
 
 static void encode_open_confirm(struct xdr_stream *xdr, const struct nfs_open_confirmargs *arg, struct compound_hdr *hdr)
@@ -1091,6 +1272,7 @@ static void encode_open_confirm(struct xdr_stream *xdr, const struct nfs_open_co
 	WRITEMEM(arg->stateid->data, NFS4_STATEID_SIZE);
 	WRITE32(arg->seqid->sequence->counter);
 	hdr->nops++;
+	hdr->replen += decode_open_confirm_maxsz;
 }
 
 static void encode_open_downgrade(struct xdr_stream *xdr, const struct nfs_closeargs *arg, struct compound_hdr *hdr)
@@ -1103,6 +1285,7 @@ static void encode_open_downgrade(struct xdr_stream *xdr, const struct nfs_close
 	WRITE32(arg->seqid->sequence->counter);
 	encode_share_access(xdr, arg->fmode);
 	hdr->nops++;
+	hdr->replen += decode_open_downgrade_maxsz;
 }
 
 static void
@@ -1116,6 +1299,7 @@ encode_putfh(struct xdr_stream *xdr, const struct nfs_fh *fh, struct compound_hd
 	WRITE32(len);
 	WRITEMEM(fh->data, len);
 	hdr->nops++;
+	hdr->replen += decode_putfh_maxsz;
 }
 
 static void encode_putrootfh(struct xdr_stream *xdr, struct compound_hdr *hdr)
@@ -1125,6 +1309,7 @@ static void encode_putrootfh(struct xdr_stream *xdr, struct compound_hdr *hdr)
 	RESERVE_SPACE(4);
 	WRITE32(OP_PUTROOTFH);
 	hdr->nops++;
+	hdr->replen += decode_putrootfh_maxsz;
 }
 
 static void encode_stateid(struct xdr_stream *xdr, const struct nfs_open_context *ctx)
@@ -1153,6 +1338,7 @@ static void encode_read(struct xdr_stream *xdr, const struct nfs_readargs *args,
 	WRITE64(args->offset);
 	WRITE32(args->count);
 	hdr->nops++;
+	hdr->replen += decode_read_maxsz;
 }
 
 static void encode_readdir(struct xdr_stream *xdr, const struct nfs4_readdir_arg *readdir, struct rpc_rqst *req, struct compound_hdr *hdr)
@@ -1178,6 +1364,7 @@ static void encode_readdir(struct xdr_stream *xdr, const struct nfs4_readdir_arg
 	WRITE32(attrs[0] & readdir->bitmask[0]);
 	WRITE32(attrs[1] & readdir->bitmask[1]);
 	hdr->nops++;
+	hdr->replen += decode_readdir_maxsz;
 	dprintk("%s: cookie = %Lu, verifier = %08x:%08x, bitmap = %08x:%08x\n",
 			__func__,
 			(unsigned long long)readdir->cookie,
@@ -1194,6 +1381,7 @@ static void encode_readlink(struct xdr_stream *xdr, const struct nfs4_readlink *
 	RESERVE_SPACE(4);
 	WRITE32(OP_READLINK);
 	hdr->nops++;
+	hdr->replen += decode_readlink_maxsz;
 }
 
 static void encode_remove(struct xdr_stream *xdr, const struct qstr *name, struct compound_hdr *hdr)
@@ -1205,6 +1393,7 @@ static void encode_remove(struct xdr_stream *xdr, const struct qstr *name, struc
 	WRITE32(name->len);
 	WRITEMEM(name->name, name->len);
 	hdr->nops++;
+	hdr->replen += decode_remove_maxsz;
 }
 
 static void encode_rename(struct xdr_stream *xdr, const struct qstr *oldname, const struct qstr *newname, struct compound_hdr *hdr)
@@ -1220,6 +1409,7 @@ static void encode_rename(struct xdr_stream *xdr, const struct qstr *oldname, co
 	WRITE32(newname->len);
 	WRITEMEM(newname->name, newname->len);
 	hdr->nops++;
+	hdr->replen += decode_rename_maxsz;
 }
 
 static void encode_renew(struct xdr_stream *xdr, const struct nfs_client *client_stateid, struct compound_hdr *hdr)
@@ -1230,6 +1420,7 @@ static void encode_renew(struct xdr_stream *xdr, const struct nfs_client *client
 	WRITE32(OP_RENEW);
 	WRITE64(client_stateid->cl_clientid);
 	hdr->nops++;
+	hdr->replen += decode_renew_maxsz;
 }
 
 static void
@@ -1240,6 +1431,7 @@ encode_restorefh(struct xdr_stream *xdr, struct compound_hdr *hdr)
 	RESERVE_SPACE(4);
 	WRITE32(OP_RESTOREFH);
 	hdr->nops++;
+	hdr->replen += decode_restorefh_maxsz;
 }
 
 static int
@@ -1259,6 +1451,7 @@ encode_setacl(struct xdr_stream *xdr, struct nfs_setaclargs *arg, struct compoun
 	WRITE32(arg->acl_len);
 	xdr_write_pages(xdr, arg->acl_pages, arg->acl_pgbase, arg->acl_len);
 	hdr->nops++;
+	hdr->replen += decode_setacl_maxsz;
 	return 0;
 }
 
@@ -1270,6 +1463,7 @@ encode_savefh(struct xdr_stream *xdr, struct compound_hdr *hdr)
 	RESERVE_SPACE(4);
 	WRITE32(OP_SAVEFH);
 	hdr->nops++;
+	hdr->replen += decode_savefh_maxsz;
 }
 
 static void encode_setattr(struct xdr_stream *xdr, const struct nfs_setattrargs *arg, const struct nfs_server *server, struct compound_hdr *hdr)
@@ -1280,6 +1474,7 @@ static void encode_setattr(struct xdr_stream *xdr, const struct nfs_setattrargs
 	WRITE32(OP_SETATTR);
 	WRITEMEM(arg->stateid.data, NFS4_STATEID_SIZE);
 	hdr->nops++;
+	hdr->replen += decode_setattr_maxsz;
 	encode_attrs(xdr, arg->iap, server);
 }
 
@@ -1299,6 +1494,7 @@ static void encode_setclientid(struct xdr_stream *xdr, const struct nfs4_setclie
 	RESERVE_SPACE(4);
 	WRITE32(setclientid->sc_cb_ident);
 	hdr->nops++;
+	hdr->replen += decode_setclientid_maxsz;
 }
 
 static void encode_setclientid_confirm(struct xdr_stream *xdr, const struct nfs_client *client_state, struct compound_hdr *hdr)
@@ -1310,6 +1506,7 @@ static void encode_setclientid_confirm(struct xdr_stream *xdr, const struct nfs_
 	WRITE64(client_state->cl_clientid);
 	WRITEMEM(client_state->cl_confirm.data, NFS4_VERIFIER_SIZE);
 	hdr->nops++;
+	hdr->replen += decode_setclientid_confirm_maxsz;
 }
 
 static void encode_write(struct xdr_stream *xdr, const struct nfs_writeargs *args, struct compound_hdr *hdr)
@@ -1328,6 +1525,7 @@ static void encode_write(struct xdr_stream *xdr, const struct nfs_writeargs *arg
 
 	xdr_write_pages(xdr, args->pages, args->pgbase, args->count);
 	hdr->nops++;
+	hdr->replen += decode_write_maxsz;
 }
 
 static void encode_delegreturn(struct xdr_stream *xdr, const nfs4_stateid *stateid, struct compound_hdr *hdr)
@@ -1339,11 +1537,163 @@ static void encode_delegreturn(struct xdr_stream *xdr, const nfs4_stateid *state
 	WRITE32(OP_DELEGRETURN);
 	WRITEMEM(stateid->data, NFS4_STATEID_SIZE);
 	hdr->nops++;
+	hdr->replen += decode_delegreturn_maxsz;
+}
+
+#if defined(CONFIG_NFS_V4_1)
+/* NFSv4.1 operations */
+static void encode_exchange_id(struct xdr_stream *xdr,
+			       struct nfs41_exchange_id_args *args,
+			       struct compound_hdr *hdr)
+{
+	__be32 *p;
+
+	RESERVE_SPACE(4 + sizeof(args->verifier->data));
+	WRITE32(OP_EXCHANGE_ID);
+	WRITEMEM(args->verifier->data, sizeof(args->verifier->data));
+
+	encode_string(xdr, args->id_len, args->id);
+
+	RESERVE_SPACE(12);
+	WRITE32(args->flags);
+	WRITE32(0);	/* zero length state_protect4_a */
+	WRITE32(0);	/* zero length implementation id array */
+	hdr->nops++;
+	hdr->replen += decode_exchange_id_maxsz;
+}
+
+static void encode_create_session(struct xdr_stream *xdr,
+				  struct nfs41_create_session_args *args,
+				  struct compound_hdr *hdr)
+{
+	__be32 *p;
+	char machine_name[NFS4_MAX_MACHINE_NAME_LEN];
+	uint32_t len;
+	struct nfs_client *clp = args->client;
+
+	RESERVE_SPACE(4);
+	WRITE32(OP_CREATE_SESSION);
+
+	RESERVE_SPACE(8);
+	WRITE64(clp->cl_ex_clid);
+
+	RESERVE_SPACE(8);
+	WRITE32(clp->cl_seqid);			/*Sequence id */
+	WRITE32(args->flags);			/*flags */
+
+	RESERVE_SPACE(2*28);			/* 2 channel_attrs */
+	/* Fore Channel */
+	WRITE32(args->fc_attrs.headerpadsz);	/* header padding size */
+	WRITE32(args->fc_attrs.max_rqst_sz);	/* max req size */
+	WRITE32(args->fc_attrs.max_resp_sz);	/* max resp size */
+	WRITE32(args->fc_attrs.max_resp_sz_cached);	/* Max resp sz cached */
+	WRITE32(args->fc_attrs.max_ops);	/* max operations */
+	WRITE32(args->fc_attrs.max_reqs);	/* max requests */
+	WRITE32(0);				/* rdmachannel_attrs */
+
+	/* Back Channel */
+	WRITE32(args->fc_attrs.headerpadsz);	/* header padding size */
+	WRITE32(args->bc_attrs.max_rqst_sz);	/* max req size */
+	WRITE32(args->bc_attrs.max_resp_sz);	/* max resp size */
+	WRITE32(args->bc_attrs.max_resp_sz_cached);	/* Max resp sz cached */
+	WRITE32(args->bc_attrs.max_ops);	/* max operations */
+	WRITE32(args->bc_attrs.max_reqs);	/* max requests */
+	WRITE32(0);				/* rdmachannel_attrs */
+
+	RESERVE_SPACE(4);
+	WRITE32(args->cb_program);		/* cb_program */
+
+	RESERVE_SPACE(4);			/* # of security flavors */
+	WRITE32(1);
+
+	RESERVE_SPACE(4);
+	WRITE32(RPC_AUTH_UNIX);			/* auth_sys */
+
+	/* authsys_parms rfc1831 */
+	RESERVE_SPACE(4);
+	WRITE32((u32)clp->cl_boot_time.tv_nsec);	/* stamp */
+	len = scnprintf(machine_name, sizeof(machine_name), "%s",
+			clp->cl_ipaddr);
+	RESERVE_SPACE(16 + len);
+	WRITE32(len);
+	WRITEMEM(machine_name, len);
+	WRITE32(0);				/* UID */
+	WRITE32(0);				/* GID */
+	WRITE32(0);				/* No more gids */
+	hdr->nops++;
+	hdr->replen += decode_create_session_maxsz;
+}
+
+static void encode_destroy_session(struct xdr_stream *xdr,
+				   struct nfs4_session *session,
+				   struct compound_hdr *hdr)
+{
+	__be32 *p;
+	RESERVE_SPACE(4 + NFS4_MAX_SESSIONID_LEN);
+	WRITE32(OP_DESTROY_SESSION);
+	WRITEMEM(session->sess_id.data, NFS4_MAX_SESSIONID_LEN);
+	hdr->nops++;
+	hdr->replen += decode_destroy_session_maxsz;
 }
+#endif /* CONFIG_NFS_V4_1 */
+
+static void encode_sequence(struct xdr_stream *xdr,
+			    const struct nfs4_sequence_args *args,
+			    struct compound_hdr *hdr)
+{
+#if defined(CONFIG_NFS_V4_1)
+	struct nfs4_session *session = args->sa_session;
+	struct nfs4_slot_table *tp;
+	struct nfs4_slot *slot;
+	__be32 *p;
+
+	if (!session)
+		return;
+
+	tp = &session->fc_slot_table;
+
+	WARN_ON(args->sa_slotid == NFS4_MAX_SLOT_TABLE);
+	slot = tp->slots + args->sa_slotid;
+
+	RESERVE_SPACE(4);
+	WRITE32(OP_SEQUENCE);
+
+	/*
+	 * Sessionid + seqid + slotid + max slotid + cache_this
+	 */
+	dprintk("%s: sessionid=%u:%u:%u:%u seqid=%d slotid=%d "
+		"max_slotid=%d cache_this=%d\n",
+		__func__,
+		((u32 *)session->sess_id.data)[0],
+		((u32 *)session->sess_id.data)[1],
+		((u32 *)session->sess_id.data)[2],
+		((u32 *)session->sess_id.data)[3],
+		slot->seq_nr, args->sa_slotid,
+		tp->highest_used_slotid, args->sa_cache_this);
+	RESERVE_SPACE(NFS4_MAX_SESSIONID_LEN + 16);
+	WRITEMEM(session->sess_id.data, NFS4_MAX_SESSIONID_LEN);
+	WRITE32(slot->seq_nr);
+	WRITE32(args->sa_slotid);
+	WRITE32(tp->highest_used_slotid);
+	WRITE32(args->sa_cache_this);
+	hdr->nops++;
+	hdr->replen += decode_sequence_maxsz;
+#endif /* CONFIG_NFS_V4_1 */
+}
+
 /*
  * END OF "GENERIC" ENCODE ROUTINES.
  */
 
+static u32 nfs4_xdr_minorversion(const struct nfs4_sequence_args *args)
+{
+#if defined(CONFIG_NFS_V4_1)
+	if (args->sa_session)
+		return args->sa_session->clp->cl_minorversion;
+#endif /* CONFIG_NFS_V4_1 */
+	return 0;
+}
+
 /*
  * Encode an ACCESS request
  */
@@ -1351,11 +1701,12 @@ static int nfs4_xdr_enc_access(struct rpc_rqst *req, __be32 *p, const struct nfs
 {
 	struct xdr_stream xdr;
 	struct compound_hdr hdr = {
-		.nops = 0,
+		.minorversion = nfs4_xdr_minorversion(&args->seq_args),
 	};
 
 	xdr_init_encode(&xdr, &req->rq_snd_buf, p);
-	encode_compound_hdr(&xdr, &hdr);
+	encode_compound_hdr(&xdr, req, &hdr);
+	encode_sequence(&xdr, &args->seq_args, &hdr);
 	encode_putfh(&xdr, args->fh, &hdr);
 	encode_access(&xdr, args->access, &hdr);
 	encode_getfattr(&xdr, args->bitmask, &hdr);
@@ -1370,11 +1721,12 @@ static int nfs4_xdr_enc_lookup(struct rpc_rqst *req, __be32 *p, const struct nfs
 {
 	struct xdr_stream xdr;
 	struct compound_hdr hdr = {
-		.nops = 0,
+		.minorversion = nfs4_xdr_minorversion(&args->seq_args),
 	};
 
 	xdr_init_encode(&xdr, &req->rq_snd_buf, p);
-	encode_compound_hdr(&xdr, &hdr);
+	encode_compound_hdr(&xdr, req, &hdr);
+	encode_sequence(&xdr, &args->seq_args, &hdr);
 	encode_putfh(&xdr, args->dir_fh, &hdr);
 	encode_lookup(&xdr, args->name, &hdr);
 	encode_getfh(&xdr, &hdr);
@@ -1390,11 +1742,12 @@ static int nfs4_xdr_enc_lookup_root(struct rpc_rqst *req, __be32 *p, const struc
 {
 	struct xdr_stream xdr;
 	struct compound_hdr hdr = {
-		.nops = 0,
+		.minorversion = nfs4_xdr_minorversion(&args->seq_args),
 	};
 
 	xdr_init_encode(&xdr, &req->rq_snd_buf, p);
-	encode_compound_hdr(&xdr, &hdr);
+	encode_compound_hdr(&xdr, req, &hdr);
+	encode_sequence(&xdr, &args->seq_args, &hdr);
 	encode_putrootfh(&xdr, &hdr);
 	encode_getfh(&xdr, &hdr);
 	encode_getfattr(&xdr, args->bitmask, &hdr);
@@ -1409,11 +1762,12 @@ static int nfs4_xdr_enc_remove(struct rpc_rqst *req, __be32 *p, const struct nfs
 {
 	struct xdr_stream xdr;
 	struct compound_hdr hdr = {
-		.nops = 0,
+		.minorversion = nfs4_xdr_minorversion(&args->seq_args),
 	};
 
 	xdr_init_encode(&xdr, &req->rq_snd_buf, p);
-	encode_compound_hdr(&xdr, &hdr);
+	encode_compound_hdr(&xdr, req, &hdr);
+	encode_sequence(&xdr, &args->seq_args, &hdr);
 	encode_putfh(&xdr, args->fh, &hdr);
 	encode_remove(&xdr, &args->name, &hdr);
 	encode_getfattr(&xdr, args->bitmask, &hdr);
@@ -1428,11 +1782,12 @@ static int nfs4_xdr_enc_rename(struct rpc_rqst *req, __be32 *p, const struct nfs
 {
 	struct xdr_stream xdr;
 	struct compound_hdr hdr = {
-		.nops = 0,
+		.minorversion = nfs4_xdr_minorversion(&args->seq_args),
 	};
 
 	xdr_init_encode(&xdr, &req->rq_snd_buf, p);
-	encode_compound_hdr(&xdr, &hdr);
+	encode_compound_hdr(&xdr, req, &hdr);
+	encode_sequence(&xdr, &args->seq_args, &hdr);
 	encode_putfh(&xdr, args->old_dir, &hdr);
 	encode_savefh(&xdr, &hdr);
 	encode_putfh(&xdr, args->new_dir, &hdr);
@@ -1451,11 +1806,12 @@ static int nfs4_xdr_enc_link(struct rpc_rqst *req, __be32 *p, const struct nfs4_
 {
 	struct xdr_stream xdr;
 	struct compound_hdr hdr = {
-		.nops = 0,
+		.minorversion = nfs4_xdr_minorversion(&args->seq_args),
 	};
 
 	xdr_init_encode(&xdr, &req->rq_snd_buf, p);
-	encode_compound_hdr(&xdr, &hdr);
+	encode_compound_hdr(&xdr, req, &hdr);
+	encode_sequence(&xdr, &args->seq_args, &hdr);
 	encode_putfh(&xdr, args->fh, &hdr);
 	encode_savefh(&xdr, &hdr);
 	encode_putfh(&xdr, args->dir_fh, &hdr);
@@ -1474,11 +1830,12 @@ static int nfs4_xdr_enc_create(struct rpc_rqst *req, __be32 *p, const struct nfs
 {
 	struct xdr_stream xdr;
 	struct compound_hdr hdr = {
-		.nops = 0,
+		.minorversion = nfs4_xdr_minorversion(&args->seq_args),
 	};
 
 	xdr_init_encode(&xdr, &req->rq_snd_buf, p);
-	encode_compound_hdr(&xdr, &hdr);
+	encode_compound_hdr(&xdr, req, &hdr);
+	encode_sequence(&xdr, &args->seq_args, &hdr);
 	encode_putfh(&xdr, args->dir_fh, &hdr);
 	encode_savefh(&xdr, &hdr);
 	encode_create(&xdr, args, &hdr);
@@ -1505,11 +1862,12 @@ static int nfs4_xdr_enc_getattr(struct rpc_rqst *req, __be32 *p, const struct nf
 {
 	struct xdr_stream xdr;
 	struct compound_hdr hdr = {
-		.nops = 0,
+		.minorversion = nfs4_xdr_minorversion(&args->seq_args),
 	};
 
 	xdr_init_encode(&xdr, &req->rq_snd_buf, p);
-	encode_compound_hdr(&xdr, &hdr);
+	encode_compound_hdr(&xdr, req, &hdr);
+	encode_sequence(&xdr, &args->seq_args, &hdr);
 	encode_putfh(&xdr, args->fh, &hdr);
 	encode_getfattr(&xdr, args->bitmask, &hdr);
 	encode_nops(&hdr);
@@ -1523,11 +1881,12 @@ static int nfs4_xdr_enc_close(struct rpc_rqst *req, __be32 *p, struct nfs_closea
 {
 	struct xdr_stream xdr;
 	struct compound_hdr hdr = {
-		.nops   = 0,
+		.minorversion = nfs4_xdr_minorversion(&args->seq_args),
 	};
 
 	xdr_init_encode(&xdr, &req->rq_snd_buf, p);
-	encode_compound_hdr(&xdr, &hdr);
+	encode_compound_hdr(&xdr, req, &hdr);
+	encode_sequence(&xdr, &args->seq_args, &hdr);
 	encode_putfh(&xdr, args->fh, &hdr);
 	encode_close(&xdr, args, &hdr);
 	encode_getfattr(&xdr, args->bitmask, &hdr);
@@ -1542,11 +1901,12 @@ static int nfs4_xdr_enc_open(struct rpc_rqst *req, __be32 *p, struct nfs_openarg
 {
 	struct xdr_stream xdr;
 	struct compound_hdr hdr = {
-		.nops = 0,
+		.minorversion = nfs4_xdr_minorversion(&args->seq_args),
 	};
 
 	xdr_init_encode(&xdr, &req->rq_snd_buf, p);
-	encode_compound_hdr(&xdr, &hdr);
+	encode_compound_hdr(&xdr, req, &hdr);
+	encode_sequence(&xdr, &args->seq_args, &hdr);
 	encode_putfh(&xdr, args->fh, &hdr);
 	encode_savefh(&xdr, &hdr);
 	encode_open(&xdr, args, &hdr);
@@ -1569,7 +1929,7 @@ static int nfs4_xdr_enc_open_confirm(struct rpc_rqst *req, __be32 *p, struct nfs
 	};
 
 	xdr_init_encode(&xdr, &req->rq_snd_buf, p);
-	encode_compound_hdr(&xdr, &hdr);
+	encode_compound_hdr(&xdr, req, &hdr);
 	encode_putfh(&xdr, args->fh, &hdr);
 	encode_open_confirm(&xdr, args, &hdr);
 	encode_nops(&hdr);
@@ -1583,11 +1943,12 @@ static int nfs4_xdr_enc_open_noattr(struct rpc_rqst *req, __be32 *p, struct nfs_
 {
 	struct xdr_stream xdr;
 	struct compound_hdr hdr = {
-		.nops   = 0,
+		.minorversion = nfs4_xdr_minorversion(&args->seq_args),
 	};
 
 	xdr_init_encode(&xdr, &req->rq_snd_buf, p);
-	encode_compound_hdr(&xdr, &hdr);
+	encode_compound_hdr(&xdr, req, &hdr);
+	encode_sequence(&xdr, &args->seq_args, &hdr);
 	encode_putfh(&xdr, args->fh, &hdr);
 	encode_open(&xdr, args, &hdr);
 	encode_getfattr(&xdr, args->bitmask, &hdr);
@@ -1602,11 +1963,12 @@ static int nfs4_xdr_enc_open_downgrade(struct rpc_rqst *req, __be32 *p, struct n
 {
 	struct xdr_stream xdr;
 	struct compound_hdr hdr = {
-		.nops	= 0,
+		.minorversion = nfs4_xdr_minorversion(&args->seq_args),
 	};
 
 	xdr_init_encode(&xdr, &req->rq_snd_buf, p);
-	encode_compound_hdr(&xdr, &hdr);
+	encode_compound_hdr(&xdr, req, &hdr);
+	encode_sequence(&xdr, &args->seq_args, &hdr);
 	encode_putfh(&xdr, args->fh, &hdr);
 	encode_open_downgrade(&xdr, args, &hdr);
 	encode_getfattr(&xdr, args->bitmask, &hdr);
@@ -1621,11 +1983,12 @@ static int nfs4_xdr_enc_lock(struct rpc_rqst *req, __be32 *p, struct nfs_lock_ar
 {
 	struct xdr_stream xdr;
 	struct compound_hdr hdr = {
-		.nops   = 0,
+		.minorversion = nfs4_xdr_minorversion(&args->seq_args),
 	};
 
 	xdr_init_encode(&xdr, &req->rq_snd_buf, p);
-	encode_compound_hdr(&xdr, &hdr);
+	encode_compound_hdr(&xdr, req, &hdr);
+	encode_sequence(&xdr, &args->seq_args, &hdr);
 	encode_putfh(&xdr, args->fh, &hdr);
 	encode_lock(&xdr, args, &hdr);
 	encode_nops(&hdr);
@@ -1639,11 +2002,12 @@ static int nfs4_xdr_enc_lockt(struct rpc_rqst *req, __be32 *p, struct nfs_lockt_
 {
 	struct xdr_stream xdr;
 	struct compound_hdr hdr = {
-		.nops   = 0,
+		.minorversion = nfs4_xdr_minorversion(&args->seq_args),
 	};
 
 	xdr_init_encode(&xdr, &req->rq_snd_buf, p);
-	encode_compound_hdr(&xdr, &hdr);
+	encode_compound_hdr(&xdr, req, &hdr);
+	encode_sequence(&xdr, &args->seq_args, &hdr);
 	encode_putfh(&xdr, args->fh, &hdr);
 	encode_lockt(&xdr, args, &hdr);
 	encode_nops(&hdr);
@@ -1657,11 +2021,12 @@ static int nfs4_xdr_enc_locku(struct rpc_rqst *req, __be32 *p, struct nfs_locku_
 {
 	struct xdr_stream xdr;
 	struct compound_hdr hdr = {
-		.nops   = 0,
+		.minorversion = nfs4_xdr_minorversion(&args->seq_args),
 	};
 
 	xdr_init_encode(&xdr, &req->rq_snd_buf, p);
-	encode_compound_hdr(&xdr, &hdr);
+	encode_compound_hdr(&xdr, req, &hdr);
+	encode_sequence(&xdr, &args->seq_args, &hdr);
 	encode_putfh(&xdr, args->fh, &hdr);
 	encode_locku(&xdr, args, &hdr);
 	encode_nops(&hdr);
@@ -1675,22 +2040,16 @@ static int nfs4_xdr_enc_readlink(struct rpc_rqst *req, __be32 *p, const struct n
 {
 	struct xdr_stream xdr;
 	struct compound_hdr hdr = {
-		.nops = 0,
+		.minorversion = nfs4_xdr_minorversion(&args->seq_args),
 	};
-	struct rpc_auth *auth = req->rq_task->tk_msg.rpc_cred->cr_auth;
-	unsigned int replen;
 
 	xdr_init_encode(&xdr, &req->rq_snd_buf, p);
-	encode_compound_hdr(&xdr, &hdr);
+	encode_compound_hdr(&xdr, req, &hdr);
+	encode_sequence(&xdr, &args->seq_args, &hdr);
 	encode_putfh(&xdr, args->fh, &hdr);
 	encode_readlink(&xdr, args, req, &hdr);
 
-	/* set up reply kvec
-	 *    toplevel_status + taglen + rescount + OP_PUTFH + status
-	 *      + OP_READLINK + status + string length = 8
-	 */
-	replen = (RPC_REPHDRSIZE + auth->au_rslack + NFS4_dec_readlink_sz) << 2;
-	xdr_inline_pages(&req->rq_rcv_buf, replen, args->pages,
+	xdr_inline_pages(&req->rq_rcv_buf, hdr.replen << 2, args->pages,
 			args->pgbase, args->pglen);
 	encode_nops(&hdr);
 	return 0;
@@ -1703,25 +2062,19 @@ static int nfs4_xdr_enc_readdir(struct rpc_rqst *req, __be32 *p, const struct nf
 {
 	struct xdr_stream xdr;
 	struct compound_hdr hdr = {
-		.nops = 0,
+		.minorversion = nfs4_xdr_minorversion(&args->seq_args),
 	};
-	struct rpc_auth *auth = req->rq_task->tk_msg.rpc_cred->cr_auth;
-	int replen;
 
 	xdr_init_encode(&xdr, &req->rq_snd_buf, p);
-	encode_compound_hdr(&xdr, &hdr);
+	encode_compound_hdr(&xdr, req, &hdr);
+	encode_sequence(&xdr, &args->seq_args, &hdr);
 	encode_putfh(&xdr, args->fh, &hdr);
 	encode_readdir(&xdr, args, req, &hdr);
 
-	/* set up reply kvec
-	 *    toplevel_status + taglen + rescount + OP_PUTFH + status
-	 *      + OP_READDIR + status + verifer(2)  = 9
-	 */
-	replen = (RPC_REPHDRSIZE + auth->au_rslack + NFS4_dec_readdir_sz) << 2;
-	xdr_inline_pages(&req->rq_rcv_buf, replen, args->pages,
+	xdr_inline_pages(&req->rq_rcv_buf, hdr.replen << 2, args->pages,
 			 args->pgbase, args->count);
 	dprintk("%s: inlined page args = (%u, %p, %u, %u)\n",
-			__func__, replen, args->pages,
+			__func__, hdr.replen << 2, args->pages,
 			args->pgbase, args->count);
 	encode_nops(&hdr);
 	return 0;
@@ -1732,24 +2085,18 @@ static int nfs4_xdr_enc_readdir(struct rpc_rqst *req, __be32 *p, const struct nf
  */
 static int nfs4_xdr_enc_read(struct rpc_rqst *req, __be32 *p, struct nfs_readargs *args)
 {
-	struct rpc_auth *auth = req->rq_task->tk_msg.rpc_cred->cr_auth;
 	struct xdr_stream xdr;
 	struct compound_hdr hdr = {
-		.nops = 0,
+		.minorversion = nfs4_xdr_minorversion(&args->seq_args),
 	};
-	int replen;
 
 	xdr_init_encode(&xdr, &req->rq_snd_buf, p);
-	encode_compound_hdr(&xdr, &hdr);
+	encode_compound_hdr(&xdr, req, &hdr);
+	encode_sequence(&xdr, &args->seq_args, &hdr);
 	encode_putfh(&xdr, args->fh, &hdr);
 	encode_read(&xdr, args, &hdr);
 
-	/* set up reply kvec
-	 *    toplevel status + taglen=0 + rescount + OP_PUTFH + status
-	 *       + OP_READ + status + eof + datalen = 9
-	 */
-	replen = (RPC_REPHDRSIZE + auth->au_rslack + NFS4_dec_read_sz) << 2;
-	xdr_inline_pages(&req->rq_rcv_buf, replen,
+	xdr_inline_pages(&req->rq_rcv_buf, hdr.replen << 2,
 			 args->pages, args->pgbase, args->count);
 	req->rq_rcv_buf.flags |= XDRBUF_READ;
 	encode_nops(&hdr);
@@ -1763,11 +2110,12 @@ static int nfs4_xdr_enc_setattr(struct rpc_rqst *req, __be32 *p, struct nfs_seta
 {
 	struct xdr_stream xdr;
 	struct compound_hdr hdr = {
-		.nops   = 0,
+		.minorversion = nfs4_xdr_minorversion(&args->seq_args),
 	};
 
 	xdr_init_encode(&xdr, &req->rq_snd_buf, p);
-	encode_compound_hdr(&xdr, &hdr);
+	encode_compound_hdr(&xdr, req, &hdr);
+	encode_sequence(&xdr, &args->seq_args, &hdr);
 	encode_putfh(&xdr, args->fh, &hdr);
 	encode_setattr(&xdr, args, args->server, &hdr);
 	encode_getfattr(&xdr, args->bitmask, &hdr);
@@ -1783,20 +2131,19 @@ nfs4_xdr_enc_getacl(struct rpc_rqst *req, __be32 *p,
 		struct nfs_getaclargs *args)
 {
 	struct xdr_stream xdr;
-	struct rpc_auth *auth = req->rq_task->tk_msg.rpc_cred->cr_auth;
 	struct compound_hdr hdr = {
-		.nops   = 0,
+		.minorversion = nfs4_xdr_minorversion(&args->seq_args),
 	};
-	int replen;
+	uint32_t replen;
 
 	xdr_init_encode(&xdr, &req->rq_snd_buf, p);
-	encode_compound_hdr(&xdr, &hdr);
+	encode_compound_hdr(&xdr, req, &hdr);
+	encode_sequence(&xdr, &args->seq_args, &hdr);
 	encode_putfh(&xdr, args->fh, &hdr);
+	replen = hdr.replen + nfs4_fattr_bitmap_maxsz + 1;
 	encode_getattr_two(&xdr, FATTR4_WORD0_ACL, 0, &hdr);
 
-	/* set up reply buffer: */
-	replen = (RPC_REPHDRSIZE + auth->au_rslack + NFS4_dec_getacl_sz) << 2;
-	xdr_inline_pages(&req->rq_rcv_buf, replen,
+	xdr_inline_pages(&req->rq_rcv_buf, replen << 2,
 		args->acl_pages, args->acl_pgbase, args->acl_len);
 	encode_nops(&hdr);
 	return 0;
@@ -1809,11 +2156,12 @@ static int nfs4_xdr_enc_write(struct rpc_rqst *req, __be32 *p, struct nfs_writea
 {
 	struct xdr_stream xdr;
 	struct compound_hdr hdr = {
-		.nops = 0,
+		.minorversion = nfs4_xdr_minorversion(&args->seq_args),
 	};
 
 	xdr_init_encode(&xdr, &req->rq_snd_buf, p);
-	encode_compound_hdr(&xdr, &hdr);
+	encode_compound_hdr(&xdr, req, &hdr);
+	encode_sequence(&xdr, &args->seq_args, &hdr);
 	encode_putfh(&xdr, args->fh, &hdr);
 	encode_write(&xdr, args, &hdr);
 	req->rq_snd_buf.flags |= XDRBUF_WRITE;
@@ -1829,11 +2177,12 @@ static int nfs4_xdr_enc_commit(struct rpc_rqst *req, __be32 *p, struct nfs_write
 {
 	struct xdr_stream xdr;
 	struct compound_hdr hdr = {
-		.nops = 0,
+		.minorversion = nfs4_xdr_minorversion(&args->seq_args),
 	};
 
 	xdr_init_encode(&xdr, &req->rq_snd_buf, p);
-	encode_compound_hdr(&xdr, &hdr);
+	encode_compound_hdr(&xdr, req, &hdr);
+	encode_sequence(&xdr, &args->seq_args, &hdr);
 	encode_putfh(&xdr, args->fh, &hdr);
 	encode_commit(&xdr, args, &hdr);
 	encode_getfattr(&xdr, args->bitmask, &hdr);
@@ -1848,11 +2197,12 @@ static int nfs4_xdr_enc_fsinfo(struct rpc_rqst *req, __be32 *p, struct nfs4_fsin
 {
 	struct xdr_stream xdr;
 	struct compound_hdr hdr = {
-		.nops	= 0,
+		.minorversion = nfs4_xdr_minorversion(&args->seq_args),
 	};
 
 	xdr_init_encode(&xdr, &req->rq_snd_buf, p);
-	encode_compound_hdr(&xdr, &hdr);
+	encode_compound_hdr(&xdr, req, &hdr);
+	encode_sequence(&xdr, &args->seq_args, &hdr);
 	encode_putfh(&xdr, args->fh, &hdr);
 	encode_fsinfo(&xdr, args->bitmask, &hdr);
 	encode_nops(&hdr);
@@ -1866,11 +2216,12 @@ static int nfs4_xdr_enc_pathconf(struct rpc_rqst *req, __be32 *p, const struct n
 {
 	struct xdr_stream xdr;
 	struct compound_hdr hdr = {
-		.nops = 0,
+		.minorversion = nfs4_xdr_minorversion(&args->seq_args),
 	};
 
 	xdr_init_encode(&xdr, &req->rq_snd_buf, p);
-	encode_compound_hdr(&xdr, &hdr);
+	encode_compound_hdr(&xdr, req, &hdr);
+	encode_sequence(&xdr, &args->seq_args, &hdr);
 	encode_putfh(&xdr, args->fh, &hdr);
 	encode_getattr_one(&xdr, args->bitmask[0] & nfs4_pathconf_bitmap[0],
 			   &hdr);
@@ -1885,11 +2236,12 @@ static int nfs4_xdr_enc_statfs(struct rpc_rqst *req, __be32 *p, const struct nfs
 {
 	struct xdr_stream xdr;
 	struct compound_hdr hdr = {
-		.nops = 0,
+		.minorversion = nfs4_xdr_minorversion(&args->seq_args),
 	};
 
 	xdr_init_encode(&xdr, &req->rq_snd_buf, p);
-	encode_compound_hdr(&xdr, &hdr);
+	encode_compound_hdr(&xdr, req, &hdr);
+	encode_sequence(&xdr, &args->seq_args, &hdr);
 	encode_putfh(&xdr, args->fh, &hdr);
 	encode_getattr_two(&xdr, args->bitmask[0] & nfs4_statfs_bitmap[0],
 			   args->bitmask[1] & nfs4_statfs_bitmap[1], &hdr);
@@ -1900,16 +2252,18 @@ static int nfs4_xdr_enc_statfs(struct rpc_rqst *req, __be32 *p, const struct nfs
 /*
  * GETATTR_BITMAP request
  */
-static int nfs4_xdr_enc_server_caps(struct rpc_rqst *req, __be32 *p, const struct nfs_fh *fhandle)
+static int nfs4_xdr_enc_server_caps(struct rpc_rqst *req, __be32 *p,
+				    struct nfs4_server_caps_arg *args)
 {
 	struct xdr_stream xdr;
 	struct compound_hdr hdr = {
-		.nops = 0,
+		.minorversion = nfs4_xdr_minorversion(&args->seq_args),
 	};
 
 	xdr_init_encode(&xdr, &req->rq_snd_buf, p);
-	encode_compound_hdr(&xdr, &hdr);
-	encode_putfh(&xdr, fhandle, &hdr);
+	encode_compound_hdr(&xdr, req, &hdr);
+	encode_sequence(&xdr, &args->seq_args, &hdr);
+	encode_putfh(&xdr, args->fhandle, &hdr);
 	encode_getattr_one(&xdr, FATTR4_WORD0_SUPPORTED_ATTRS|
 			   FATTR4_WORD0_LINK_SUPPORT|
 			   FATTR4_WORD0_SYMLINK_SUPPORT|
@@ -1929,7 +2283,7 @@ static int nfs4_xdr_enc_renew(struct rpc_rqst *req, __be32 *p, struct nfs_client
 	};
 
 	xdr_init_encode(&xdr, &req->rq_snd_buf, p);
-	encode_compound_hdr(&xdr, &hdr);
+	encode_compound_hdr(&xdr, req, &hdr);
 	encode_renew(&xdr, clp, &hdr);
 	encode_nops(&hdr);
 	return 0;
@@ -1946,7 +2300,7 @@ static int nfs4_xdr_enc_setclientid(struct rpc_rqst *req, __be32 *p, struct nfs4
 	};
 
 	xdr_init_encode(&xdr, &req->rq_snd_buf, p);
-	encode_compound_hdr(&xdr, &hdr);
+	encode_compound_hdr(&xdr, req, &hdr);
 	encode_setclientid(&xdr, sc, &hdr);
 	encode_nops(&hdr);
 	return 0;
@@ -1964,7 +2318,7 @@ static int nfs4_xdr_enc_setclientid_confirm(struct rpc_rqst *req, __be32 *p, str
 	const u32 lease_bitmap[2] = { FATTR4_WORD0_LEASE_TIME, 0 };
 
 	xdr_init_encode(&xdr, &req->rq_snd_buf, p);
-	encode_compound_hdr(&xdr, &hdr);
+	encode_compound_hdr(&xdr, req, &hdr);
 	encode_setclientid_confirm(&xdr, clp, &hdr);
 	encode_putrootfh(&xdr, &hdr);
 	encode_fsinfo(&xdr, lease_bitmap, &hdr);
@@ -1979,11 +2333,12 @@ static int nfs4_xdr_enc_delegreturn(struct rpc_rqst *req, __be32 *p, const struc
 {
 	struct xdr_stream xdr;
 	struct compound_hdr hdr = {
-		.nops = 0,
+		.minorversion = nfs4_xdr_minorversion(&args->seq_args),
 	};
 
 	xdr_init_encode(&xdr, &req->rq_snd_buf, p);
-	encode_compound_hdr(&xdr, &hdr);
+	encode_compound_hdr(&xdr, req, &hdr);
+	encode_sequence(&xdr, &args->seq_args, &hdr);
 	encode_putfh(&xdr, args->fhandle, &hdr);
 	encode_delegreturn(&xdr, args->stateid, &hdr);
 	encode_getfattr(&xdr, args->bitmask, &hdr);
@@ -1998,28 +2353,119 @@ static int nfs4_xdr_enc_fs_locations(struct rpc_rqst *req, __be32 *p, struct nfs
 {
 	struct xdr_stream xdr;
 	struct compound_hdr hdr = {
-		.nops = 0,
+		.minorversion = nfs4_xdr_minorversion(&args->seq_args),
 	};
-	struct rpc_auth *auth = req->rq_task->tk_msg.rpc_cred->cr_auth;
-	int replen;
+	uint32_t replen;
 
 	xdr_init_encode(&xdr, &req->rq_snd_buf, p);
-	encode_compound_hdr(&xdr, &hdr);
+	encode_compound_hdr(&xdr, req, &hdr);
+	encode_sequence(&xdr, &args->seq_args, &hdr);
 	encode_putfh(&xdr, args->dir_fh, &hdr);
 	encode_lookup(&xdr, args->name, &hdr);
+	replen = hdr.replen;	/* get the attribute into args->page */
 	encode_fs_locations(&xdr, args->bitmask, &hdr);
 
-	/* set up reply
-	 *   toplevel_status + OP_PUTFH + status
-	 *   + OP_LOOKUP + status + OP_GETATTR + status = 7
-	 */
-	replen = (RPC_REPHDRSIZE + auth->au_rslack + 7) << 2;
-	xdr_inline_pages(&req->rq_rcv_buf, replen, &args->page,
+	xdr_inline_pages(&req->rq_rcv_buf, replen << 2, &args->page,
 			0, PAGE_SIZE);
 	encode_nops(&hdr);
 	return 0;
 }
 
+#if defined(CONFIG_NFS_V4_1)
+/*
+ * EXCHANGE_ID request
+ */
+static int nfs4_xdr_enc_exchange_id(struct rpc_rqst *req, uint32_t *p,
+				    struct nfs41_exchange_id_args *args)
+{
+	struct xdr_stream xdr;
+	struct compound_hdr hdr = {
+		.minorversion = args->client->cl_minorversion,
+	};
+
+	xdr_init_encode(&xdr, &req->rq_snd_buf, p);
+	encode_compound_hdr(&xdr, req, &hdr);
+	encode_exchange_id(&xdr, args, &hdr);
+	encode_nops(&hdr);
+	return 0;
+}
+
+/*
+ * a CREATE_SESSION request
+ */
+static int nfs4_xdr_enc_create_session(struct rpc_rqst *req, uint32_t *p,
+				       struct nfs41_create_session_args *args)
+{
+	struct xdr_stream xdr;
+	struct compound_hdr hdr = {
+		.minorversion = args->client->cl_minorversion,
+	};
+
+	xdr_init_encode(&xdr, &req->rq_snd_buf, p);
+	encode_compound_hdr(&xdr, req, &hdr);
+	encode_create_session(&xdr, args, &hdr);
+	encode_nops(&hdr);
+	return 0;
+}
+
+/*
+ * a DESTROY_SESSION request
+ */
+static int nfs4_xdr_enc_destroy_session(struct rpc_rqst *req, uint32_t *p,
+					struct nfs4_session *session)
+{
+	struct xdr_stream xdr;
+	struct compound_hdr hdr = {
+		.minorversion = session->clp->cl_minorversion,
+	};
+
+	xdr_init_encode(&xdr, &req->rq_snd_buf, p);
+	encode_compound_hdr(&xdr, req, &hdr);
+	encode_destroy_session(&xdr, session, &hdr);
+	encode_nops(&hdr);
+	return 0;
+}
+
+/*
+ * a SEQUENCE request
+ */
+static int nfs4_xdr_enc_sequence(struct rpc_rqst *req, uint32_t *p,
+				 struct nfs4_sequence_args *args)
+{
+	struct xdr_stream xdr;
+	struct compound_hdr hdr = {
+		.minorversion = nfs4_xdr_minorversion(args),
+	};
+
+	xdr_init_encode(&xdr, &req->rq_snd_buf, p);
+	encode_compound_hdr(&xdr, req, &hdr);
+	encode_sequence(&xdr, args, &hdr);
+	encode_nops(&hdr);
+	return 0;
+}
+
+/*
+ * a GET_LEASE_TIME request
+ */
+static int nfs4_xdr_enc_get_lease_time(struct rpc_rqst *req, uint32_t *p,
+				       struct nfs4_get_lease_time_args *args)
+{
+	struct xdr_stream xdr;
+	struct compound_hdr hdr = {
+		.minorversion = nfs4_xdr_minorversion(&args->la_seq_args),
+	};
+	const u32 lease_bitmap[2] = { FATTR4_WORD0_LEASE_TIME, 0 };
+
+	xdr_init_encode(&xdr, &req->rq_snd_buf, p);
+	encode_compound_hdr(&xdr, req, &hdr);
+	encode_sequence(&xdr, &args->la_seq_args, &hdr);
+	encode_putrootfh(&xdr, &hdr);
+	encode_fsinfo(&xdr, lease_bitmap, &hdr);
+	encode_nops(&hdr);
+	return 0;
+}
+#endif /* CONFIG_NFS_V4_1 */
+
 /*
  * START OF "GENERIC" DECODE ROUTINES.
  *   These may look a little ugly since they are imported from a "generic"
@@ -3657,7 +4103,7 @@ decode_savefh(struct xdr_stream *xdr)
 	return decode_op_hdr(xdr, OP_SAVEFH);
 }
 
-static int decode_setattr(struct xdr_stream *xdr, struct nfs_setattrres *res)
+static int decode_setattr(struct xdr_stream *xdr)
 {
 	__be32 *p;
 	uint32_t bmlen;
@@ -3735,6 +4181,169 @@ static int decode_delegreturn(struct xdr_stream *xdr)
 	return decode_op_hdr(xdr, OP_DELEGRETURN);
 }
 
+#if defined(CONFIG_NFS_V4_1)
+static int decode_exchange_id(struct xdr_stream *xdr,
+			      struct nfs41_exchange_id_res *res)
+{
+	__be32 *p;
+	uint32_t dummy;
+	int status;
+	struct nfs_client *clp = res->client;
+
+	status = decode_op_hdr(xdr, OP_EXCHANGE_ID);
+	if (status)
+		return status;
+
+	READ_BUF(8);
+	READ64(clp->cl_ex_clid);
+	READ_BUF(12);
+	READ32(clp->cl_seqid);
+	READ32(clp->cl_exchange_flags);
+
+	/* We ask for SP4_NONE */
+	READ32(dummy);
+	if (dummy != SP4_NONE)
+		return -EIO;
+
+	/* Throw away minor_id */
+	READ_BUF(8);
+
+	/* Throw away Major id */
+	READ_BUF(4);
+	READ32(dummy);
+	READ_BUF(dummy);
+
+	/* Throw away server_scope */
+	READ_BUF(4);
+	READ32(dummy);
+	READ_BUF(dummy);
+
+	/* Throw away Implementation id array */
+	READ_BUF(4);
+	READ32(dummy);
+	READ_BUF(dummy);
+
+	return 0;
+}
+
+static int decode_chan_attrs(struct xdr_stream *xdr,
+			     struct nfs4_channel_attrs *attrs)
+{
+	__be32 *p;
+	u32 nr_attrs;
+
+	READ_BUF(28);
+	READ32(attrs->headerpadsz);
+	READ32(attrs->max_rqst_sz);
+	READ32(attrs->max_resp_sz);
+	READ32(attrs->max_resp_sz_cached);
+	READ32(attrs->max_ops);
+	READ32(attrs->max_reqs);
+	READ32(nr_attrs);
+	if (unlikely(nr_attrs > 1)) {
+		printk(KERN_WARNING "%s: Invalid rdma channel attrs count %u\n",
+			__func__, nr_attrs);
+		return -EINVAL;
+	}
+	if (nr_attrs == 1)
+		READ_BUF(4); /* skip rdma_attrs */
+	return 0;
+}
+
+static int decode_create_session(struct xdr_stream *xdr,
+				 struct nfs41_create_session_res *res)
+{
+	__be32 *p;
+	int status;
+	struct nfs_client *clp = res->client;
+	struct nfs4_session *session = clp->cl_session;
+
+	status = decode_op_hdr(xdr, OP_CREATE_SESSION);
+
+	if (status)
+		return status;
+
+	/* sessionid */
+	READ_BUF(NFS4_MAX_SESSIONID_LEN);
+	COPYMEM(&session->sess_id, NFS4_MAX_SESSIONID_LEN);
+
+	/* seqid, flags */
+	READ_BUF(8);
+	READ32(clp->cl_seqid);
+	READ32(session->flags);
+
+	/* Channel attributes */
+	status = decode_chan_attrs(xdr, &session->fc_attrs);
+	if (!status)
+		status = decode_chan_attrs(xdr, &session->bc_attrs);
+	return status;
+}
+
+static int decode_destroy_session(struct xdr_stream *xdr, void *dummy)
+{
+	return decode_op_hdr(xdr, OP_DESTROY_SESSION);
+}
+#endif /* CONFIG_NFS_V4_1 */
+
+static int decode_sequence(struct xdr_stream *xdr,
+			   struct nfs4_sequence_res *res,
+			   struct rpc_rqst *rqstp)
+{
+#if defined(CONFIG_NFS_V4_1)
+	struct nfs4_slot *slot;
+	struct nfs4_sessionid id;
+	u32 dummy;
+	int status;
+	__be32 *p;
+
+	if (!res->sr_session)
+		return 0;
+
+	status = decode_op_hdr(xdr, OP_SEQUENCE);
+	if (status)
+		goto out_err;
+
+	/*
+	 * If the server returns different values for sessionID, slotID or
+	 * sequence number, the server is looney tunes.
+	 */
+	status = -ESERVERFAULT;
+
+	slot = &res->sr_session->fc_slot_table.slots[res->sr_slotid];
+	READ_BUF(NFS4_MAX_SESSIONID_LEN + 20);
+	COPYMEM(id.data, NFS4_MAX_SESSIONID_LEN);
+	if (memcmp(id.data, res->sr_session->sess_id.data,
+		   NFS4_MAX_SESSIONID_LEN)) {
+		dprintk("%s Invalid session id\n", __func__);
+		goto out_err;
+	}
+	/* seqid */
+	READ32(dummy);
+	if (dummy != slot->seq_nr) {
+		dprintk("%s Invalid sequence number\n", __func__);
+		goto out_err;
+	}
+	/* slot id */
+	READ32(dummy);
+	if (dummy != res->sr_slotid) {
+		dprintk("%s Invalid slot id\n", __func__);
+		goto out_err;
+	}
+	/* highest slot id - currently not processed */
+	READ32(dummy);
+	/* target highest slot id - currently not processed */
+	READ32(dummy);
+	/* result flags - currently not processed */
+	READ32(dummy);
+	status = 0;
+out_err:
+	res->sr_status = status;
+	return status;
+#else  /* CONFIG_NFS_V4_1 */
+	return 0;
+#endif /* CONFIG_NFS_V4_1 */
+}
+
 /*
  * END OF "GENERIC" DECODE ROUTINES.
  */
@@ -3750,6 +4359,9 @@ static int nfs4_xdr_dec_open_downgrade(struct rpc_rqst *rqstp, __be32 *p, struct
 
 	xdr_init_decode(&xdr, &rqstp->rq_rcv_buf, p);
 	status = decode_compound_hdr(&xdr, &hdr);
+	if (status)
+		goto out;
+	status = decode_sequence(&xdr, &res->seq_res, rqstp);
 	if (status)
 		goto out;
 	status = decode_putfh(&xdr);
@@ -3773,7 +4385,11 @@ static int nfs4_xdr_dec_access(struct rpc_rqst *rqstp, __be32 *p, struct nfs4_ac
 	int status;
 
 	xdr_init_decode(&xdr, &rqstp->rq_rcv_buf, p);
-	if ((status = decode_compound_hdr(&xdr, &hdr)) != 0)
+	status = decode_compound_hdr(&xdr, &hdr);
+	if (status)
+		goto out;
+	status = decode_sequence(&xdr, &res->seq_res, rqstp);
+	if (status)
 		goto out;
 	status = decode_putfh(&xdr);
 	if (status != 0)
@@ -3796,7 +4412,11 @@ static int nfs4_xdr_dec_lookup(struct rpc_rqst *rqstp, __be32 *p, struct nfs4_lo
 	int status;
 
 	xdr_init_decode(&xdr, &rqstp->rq_rcv_buf, p);
-	if ((status = decode_compound_hdr(&xdr, &hdr)) != 0)
+	status = decode_compound_hdr(&xdr, &hdr);
+	if (status)
+		goto out;
+	status = decode_sequence(&xdr, &res->seq_res, rqstp);
+	if (status)
 		goto out;
 	if ((status = decode_putfh(&xdr)) != 0)
 		goto out;
@@ -3819,7 +4439,11 @@ static int nfs4_xdr_dec_lookup_root(struct rpc_rqst *rqstp, __be32 *p, struct nf
 	int status;
 
 	xdr_init_decode(&xdr, &rqstp->rq_rcv_buf, p);
-	if ((status = decode_compound_hdr(&xdr, &hdr)) != 0)
+	status = decode_compound_hdr(&xdr, &hdr);
+	if (status)
+		goto out;
+	status = decode_sequence(&xdr, &res->seq_res, rqstp);
+	if (status)
 		goto out;
 	if ((status = decode_putrootfh(&xdr)) != 0)
 		goto out;
@@ -3839,7 +4463,11 @@ static int nfs4_xdr_dec_remove(struct rpc_rqst *rqstp, __be32 *p, struct nfs_rem
 	int status;
 
 	xdr_init_decode(&xdr, &rqstp->rq_rcv_buf, p);
-	if ((status = decode_compound_hdr(&xdr, &hdr)) != 0)
+	status = decode_compound_hdr(&xdr, &hdr);
+	if (status)
+		goto out;
+	status = decode_sequence(&xdr, &res->seq_res, rqstp);
+	if (status)
 		goto out;
 	if ((status = decode_putfh(&xdr)) != 0)
 		goto out;
@@ -3860,7 +4488,11 @@ static int nfs4_xdr_dec_rename(struct rpc_rqst *rqstp, __be32 *p, struct nfs4_re
 	int status;
 
 	xdr_init_decode(&xdr, &rqstp->rq_rcv_buf, p);
-	if ((status = decode_compound_hdr(&xdr, &hdr)) != 0)
+	status = decode_compound_hdr(&xdr, &hdr);
+	if (status)
+		goto out;
+	status = decode_sequence(&xdr, &res->seq_res, rqstp);
+	if (status)
 		goto out;
 	if ((status = decode_putfh(&xdr)) != 0)
 		goto out;
@@ -3890,7 +4522,11 @@ static int nfs4_xdr_dec_link(struct rpc_rqst *rqstp, __be32 *p, struct nfs4_link
 	int status;
 
 	xdr_init_decode(&xdr, &rqstp->rq_rcv_buf, p);
-	if ((status = decode_compound_hdr(&xdr, &hdr)) != 0)
+	status = decode_compound_hdr(&xdr, &hdr);
+	if (status)
+		goto out;
+	status = decode_sequence(&xdr, &res->seq_res, rqstp);
+	if (status)
 		goto out;
 	if ((status = decode_putfh(&xdr)) != 0)
 		goto out;
@@ -3923,7 +4559,11 @@ static int nfs4_xdr_dec_create(struct rpc_rqst *rqstp, __be32 *p, struct nfs4_cr
 	int status;
 
 	xdr_init_decode(&xdr, &rqstp->rq_rcv_buf, p);
-	if ((status = decode_compound_hdr(&xdr, &hdr)) != 0)
+	status = decode_compound_hdr(&xdr, &hdr);
+	if (status)
+		goto out;
+	status = decode_sequence(&xdr, &res->seq_res, rqstp);
+	if (status)
 		goto out;
 	if ((status = decode_putfh(&xdr)) != 0)
 		goto out;
@@ -3961,6 +4601,9 @@ static int nfs4_xdr_dec_getattr(struct rpc_rqst *rqstp, __be32 *p, struct nfs4_g
 
 	xdr_init_decode(&xdr, &rqstp->rq_rcv_buf, p);
 	status = decode_compound_hdr(&xdr, &hdr);
+	if (status)
+		goto out;
+	status = decode_sequence(&xdr, &res->seq_res, rqstp);
 	if (status)
 		goto out;
 	status = decode_putfh(&xdr);
@@ -3979,12 +4622,13 @@ nfs4_xdr_enc_setacl(struct rpc_rqst *req, __be32 *p, struct nfs_setaclargs *args
 {
 	struct xdr_stream xdr;
 	struct compound_hdr hdr = {
-		.nops   = 0,
+		.minorversion = nfs4_xdr_minorversion(&args->seq_args),
 	};
 	int status;
 
 	xdr_init_encode(&xdr, &req->rq_snd_buf, p);
-	encode_compound_hdr(&xdr, &hdr);
+	encode_compound_hdr(&xdr, req, &hdr);
+	encode_sequence(&xdr, &args->seq_args, &hdr);
 	encode_putfh(&xdr, args->fh, &hdr);
 	status = encode_setacl(&xdr, args, &hdr);
 	encode_nops(&hdr);
@@ -3995,7 +4639,8 @@ nfs4_xdr_enc_setacl(struct rpc_rqst *req, __be32 *p, struct nfs_setaclargs *args
  * Decode SETACL response
  */
 static int
-nfs4_xdr_dec_setacl(struct rpc_rqst *rqstp, __be32 *p, void *res)
+nfs4_xdr_dec_setacl(struct rpc_rqst *rqstp, __be32 *p,
+		    struct nfs_setaclres *res)
 {
 	struct xdr_stream xdr;
 	struct compound_hdr hdr;
@@ -4003,12 +4648,15 @@ nfs4_xdr_dec_setacl(struct rpc_rqst *rqstp, __be32 *p, void *res)
 
 	xdr_init_decode(&xdr, &rqstp->rq_rcv_buf, p);
 	status = decode_compound_hdr(&xdr, &hdr);
+	if (status)
+		goto out;
+	status = decode_sequence(&xdr, &res->seq_res, rqstp);
 	if (status)
 		goto out;
 	status = decode_putfh(&xdr);
 	if (status)
 		goto out;
-	status = decode_setattr(&xdr, res);
+	status = decode_setattr(&xdr);
 out:
 	return status;
 }
@@ -4017,7 +4665,8 @@ out:
  * Decode GETACL response
  */
 static int
-nfs4_xdr_dec_getacl(struct rpc_rqst *rqstp, __be32 *p, size_t *acl_len)
+nfs4_xdr_dec_getacl(struct rpc_rqst *rqstp, __be32 *p,
+		    struct nfs_getaclres *res)
 {
 	struct xdr_stream xdr;
 	struct compound_hdr hdr;
@@ -4025,12 +4674,15 @@ nfs4_xdr_dec_getacl(struct rpc_rqst *rqstp, __be32 *p, size_t *acl_len)
 
 	xdr_init_decode(&xdr, &rqstp->rq_rcv_buf, p);
 	status = decode_compound_hdr(&xdr, &hdr);
+	if (status)
+		goto out;
+	status = decode_sequence(&xdr, &res->seq_res, rqstp);
 	if (status)
 		goto out;
 	status = decode_putfh(&xdr);
 	if (status)
 		goto out;
-	status = decode_getacl(&xdr, rqstp, acl_len);
+	status = decode_getacl(&xdr, rqstp, &res->acl_len);
 
 out:
 	return status;
@@ -4047,6 +4699,9 @@ static int nfs4_xdr_dec_close(struct rpc_rqst *rqstp, __be32 *p, struct nfs_clos
 
 	xdr_init_decode(&xdr, &rqstp->rq_rcv_buf, p);
 	status = decode_compound_hdr(&xdr, &hdr);
+	if (status)
+		goto out;
+	status = decode_sequence(&xdr, &res->seq_res, rqstp);
 	if (status)
 		goto out;
 	status = decode_putfh(&xdr);
@@ -4077,6 +4732,9 @@ static int nfs4_xdr_dec_open(struct rpc_rqst *rqstp, __be32 *p, struct nfs_openr
 
 	xdr_init_decode(&xdr, &rqstp->rq_rcv_buf, p);
 	status = decode_compound_hdr(&xdr, &hdr);
+	if (status)
+		goto out;
+	status = decode_sequence(&xdr, &res->seq_res, rqstp);
 	if (status)
 		goto out;
 	status = decode_putfh(&xdr);
@@ -4131,6 +4789,9 @@ static int nfs4_xdr_dec_open_noattr(struct rpc_rqst *rqstp, __be32 *p, struct nf
 
 	xdr_init_decode(&xdr, &rqstp->rq_rcv_buf, p);
 	status = decode_compound_hdr(&xdr, &hdr);
+	if (status)
+		goto out;
+	status = decode_sequence(&xdr, &res->seq_res, rqstp);
 	if (status)
 		goto out;
 	status = decode_putfh(&xdr);
@@ -4155,12 +4816,15 @@ static int nfs4_xdr_dec_setattr(struct rpc_rqst *rqstp, __be32 *p, struct nfs_se
 
 	xdr_init_decode(&xdr, &rqstp->rq_rcv_buf, p);
 	status = decode_compound_hdr(&xdr, &hdr);
+	if (status)
+		goto out;
+	status = decode_sequence(&xdr, &res->seq_res, rqstp);
 	if (status)
 		goto out;
 	status = decode_putfh(&xdr);
 	if (status)
 		goto out;
-	status = decode_setattr(&xdr, res);
+	status = decode_setattr(&xdr);
 	if (status)
 		goto out;
 	decode_getfattr(&xdr, res->fattr, res->server);
@@ -4179,6 +4843,9 @@ static int nfs4_xdr_dec_lock(struct rpc_rqst *rqstp, __be32 *p, struct nfs_lock_
 
 	xdr_init_decode(&xdr, &rqstp->rq_rcv_buf, p);
 	status = decode_compound_hdr(&xdr, &hdr);
+	if (status)
+		goto out;
+	status = decode_sequence(&xdr, &res->seq_res, rqstp);
 	if (status)
 		goto out;
 	status = decode_putfh(&xdr);
@@ -4200,6 +4867,9 @@ static int nfs4_xdr_dec_lockt(struct rpc_rqst *rqstp, __be32 *p, struct nfs_lock
 
 	xdr_init_decode(&xdr, &rqstp->rq_rcv_buf, p);
 	status = decode_compound_hdr(&xdr, &hdr);
+	if (status)
+		goto out;
+	status = decode_sequence(&xdr, &res->seq_res, rqstp);
 	if (status)
 		goto out;
 	status = decode_putfh(&xdr);
@@ -4221,6 +4891,9 @@ static int nfs4_xdr_dec_locku(struct rpc_rqst *rqstp, __be32 *p, struct nfs_lock
 
 	xdr_init_decode(&xdr, &rqstp->rq_rcv_buf, p);
 	status = decode_compound_hdr(&xdr, &hdr);
+	if (status)
+		goto out;
+	status = decode_sequence(&xdr, &res->seq_res, rqstp);
 	if (status)
 		goto out;
 	status = decode_putfh(&xdr);
@@ -4234,7 +4907,8 @@ out:
 /*
  * Decode READLINK response
  */
-static int nfs4_xdr_dec_readlink(struct rpc_rqst *rqstp, __be32 *p, void *res)
+static int nfs4_xdr_dec_readlink(struct rpc_rqst *rqstp, __be32 *p,
+				 struct nfs4_readlink_res *res)
 {
 	struct xdr_stream xdr;
 	struct compound_hdr hdr;
@@ -4242,6 +4916,9 @@ static int nfs4_xdr_dec_readlink(struct rpc_rqst *rqstp, __be32 *p, void *res)
 
 	xdr_init_decode(&xdr, &rqstp->rq_rcv_buf, p);
 	status = decode_compound_hdr(&xdr, &hdr);
+	if (status)
+		goto out;
+	status = decode_sequence(&xdr, &res->seq_res, rqstp);
 	if (status)
 		goto out;
 	status = decode_putfh(&xdr);
@@ -4263,6 +4940,9 @@ static int nfs4_xdr_dec_readdir(struct rpc_rqst *rqstp, __be32 *p, struct nfs4_r
 
 	xdr_init_decode(&xdr, &rqstp->rq_rcv_buf, p);
 	status = decode_compound_hdr(&xdr, &hdr);
+	if (status)
+		goto out;
+	status = decode_sequence(&xdr, &res->seq_res, rqstp);
 	if (status)
 		goto out;
 	status = decode_putfh(&xdr);
@@ -4284,6 +4964,9 @@ static int nfs4_xdr_dec_read(struct rpc_rqst *rqstp, __be32 *p, struct nfs_readr
 
 	xdr_init_decode(&xdr, &rqstp->rq_rcv_buf, p);
 	status = decode_compound_hdr(&xdr, &hdr);
+	if (status)
+		goto out;
+	status = decode_sequence(&xdr, &res->seq_res, rqstp);
 	if (status)
 		goto out;
 	status = decode_putfh(&xdr);
@@ -4307,6 +4990,9 @@ static int nfs4_xdr_dec_write(struct rpc_rqst *rqstp, __be32 *p, struct nfs_writ
 
 	xdr_init_decode(&xdr, &rqstp->rq_rcv_buf, p);
 	status = decode_compound_hdr(&xdr, &hdr);
+	if (status)
+		goto out;
+	status = decode_sequence(&xdr, &res->seq_res, rqstp);
 	if (status)
 		goto out;
 	status = decode_putfh(&xdr);
@@ -4333,6 +5019,9 @@ static int nfs4_xdr_dec_commit(struct rpc_rqst *rqstp, __be32 *p, struct nfs_wri
 
 	xdr_init_decode(&xdr, &rqstp->rq_rcv_buf, p);
 	status = decode_compound_hdr(&xdr, &hdr);
+	if (status)
+		goto out;
+	status = decode_sequence(&xdr, &res->seq_res, rqstp);
 	if (status)
 		goto out;
 	status = decode_putfh(&xdr);
@@ -4349,7 +5038,8 @@ out:
 /*
  * FSINFO request
  */
-static int nfs4_xdr_dec_fsinfo(struct rpc_rqst *req, __be32 *p, struct nfs_fsinfo *fsinfo)
+static int nfs4_xdr_dec_fsinfo(struct rpc_rqst *req, __be32 *p,
+			       struct nfs4_fsinfo_res *res)
 {
 	struct xdr_stream xdr;
 	struct compound_hdr hdr;
@@ -4357,17 +5047,20 @@ static int nfs4_xdr_dec_fsinfo(struct rpc_rqst *req, __be32 *p, struct nfs_fsinf
 
 	xdr_init_decode(&xdr, &req->rq_rcv_buf, p);
 	status = decode_compound_hdr(&xdr, &hdr);
+	if (!status)
+		status = decode_sequence(&xdr, &res->seq_res, req);
 	if (!status)
 		status = decode_putfh(&xdr);
 	if (!status)
-		status = decode_fsinfo(&xdr, fsinfo);
+		status = decode_fsinfo(&xdr, res->fsinfo);
 	return status;
 }
 
 /*
  * PATHCONF request
  */
-static int nfs4_xdr_dec_pathconf(struct rpc_rqst *req, __be32 *p, struct nfs_pathconf *pathconf)
+static int nfs4_xdr_dec_pathconf(struct rpc_rqst *req, __be32 *p,
+				 struct nfs4_pathconf_res *res)
 {
 	struct xdr_stream xdr;
 	struct compound_hdr hdr;
@@ -4375,17 +5068,20 @@ static int nfs4_xdr_dec_pathconf(struct rpc_rqst *req, __be32 *p, struct nfs_pat
 
 	xdr_init_decode(&xdr, &req->rq_rcv_buf, p);
 	status = decode_compound_hdr(&xdr, &hdr);
+	if (!status)
+		status = decode_sequence(&xdr, &res->seq_res, req);
 	if (!status)
 		status = decode_putfh(&xdr);
 	if (!status)
-		status = decode_pathconf(&xdr, pathconf);
+		status = decode_pathconf(&xdr, res->pathconf);
 	return status;
 }
 
 /*
  * STATFS request
  */
-static int nfs4_xdr_dec_statfs(struct rpc_rqst *req, __be32 *p, struct nfs_fsstat *fsstat)
+static int nfs4_xdr_dec_statfs(struct rpc_rqst *req, __be32 *p,
+			       struct nfs4_statfs_res *res)
 {
 	struct xdr_stream xdr;
 	struct compound_hdr hdr;
@@ -4393,10 +5089,12 @@ static int nfs4_xdr_dec_statfs(struct rpc_rqst *req, __be32 *p, struct nfs_fssta
 
 	xdr_init_decode(&xdr, &req->rq_rcv_buf, p);
 	status = decode_compound_hdr(&xdr, &hdr);
+	if (!status)
+		status = decode_sequence(&xdr, &res->seq_res, req);
 	if (!status)
 		status = decode_putfh(&xdr);
 	if (!status)
-		status = decode_statfs(&xdr, fsstat);
+		status = decode_statfs(&xdr, res->fsstat);
 	return status;
 }
 
@@ -4410,7 +5108,11 @@ static int nfs4_xdr_dec_server_caps(struct rpc_rqst *req, __be32 *p, struct nfs4
 	int status;
 
 	xdr_init_decode(&xdr, &req->rq_rcv_buf, p);
-	if ((status = decode_compound_hdr(&xdr, &hdr)) != 0)
+	status = decode_compound_hdr(&xdr, &hdr);
+	if (status)
+		goto out;
+	status = decode_sequence(&xdr, &res->seq_res, req);
+	if (status)
 		goto out;
 	if ((status = decode_putfh(&xdr)) != 0)
 		goto out;
@@ -4483,7 +5185,10 @@ static int nfs4_xdr_dec_delegreturn(struct rpc_rqst *rqstp, __be32 *p, struct nf
 
 	xdr_init_decode(&xdr, &rqstp->rq_rcv_buf, p);
 	status = decode_compound_hdr(&xdr, &hdr);
-	if (status != 0)
+	if (status)
+		goto out;
+	status = decode_sequence(&xdr, &res->seq_res, rqstp);
+	if (status)
 		goto out;
 	status = decode_putfh(&xdr);
 	if (status != 0)
@@ -4497,7 +5202,8 @@ out:
 /*
  * FS_LOCATIONS request
  */
-static int nfs4_xdr_dec_fs_locations(struct rpc_rqst *req, __be32 *p, struct nfs4_fs_locations *res)
+static int nfs4_xdr_dec_fs_locations(struct rpc_rqst *req, __be32 *p,
+				     struct nfs4_fs_locations_res *res)
 {
 	struct xdr_stream xdr;
 	struct compound_hdr hdr;
@@ -4505,18 +5211,113 @@ static int nfs4_xdr_dec_fs_locations(struct rpc_rqst *req, __be32 *p, struct nfs
 
 	xdr_init_decode(&xdr, &req->rq_rcv_buf, p);
 	status = decode_compound_hdr(&xdr, &hdr);
-	if (status != 0)
+	if (status)
+		goto out;
+	status = decode_sequence(&xdr, &res->seq_res, req);
+	if (status)
 		goto out;
 	if ((status = decode_putfh(&xdr)) != 0)
 		goto out;
 	if ((status = decode_lookup(&xdr)) != 0)
 		goto out;
 	xdr_enter_page(&xdr, PAGE_SIZE);
-	status = decode_getfattr(&xdr, &res->fattr, res->server);
+	status = decode_getfattr(&xdr, &res->fs_locations->fattr,
+				 res->fs_locations->server);
 out:
 	return status;
 }
 
+#if defined(CONFIG_NFS_V4_1)
+/*
+ * EXCHANGE_ID request
+ */
+static int nfs4_xdr_dec_exchange_id(struct rpc_rqst *rqstp, uint32_t *p,
+				    void *res)
+{
+	struct xdr_stream xdr;
+	struct compound_hdr hdr;
+	int status;
+
+	xdr_init_decode(&xdr, &rqstp->rq_rcv_buf, p);
+	status = decode_compound_hdr(&xdr, &hdr);
+	if (!status)
+		status = decode_exchange_id(&xdr, res);
+	return status;
+}
+
+/*
+ * a CREATE_SESSION request
+ */
+static int nfs4_xdr_dec_create_session(struct rpc_rqst *rqstp, uint32_t *p,
+				       struct nfs41_create_session_res *res)
+{
+	struct xdr_stream xdr;
+	struct compound_hdr hdr;
+	int status;
+
+	xdr_init_decode(&xdr, &rqstp->rq_rcv_buf, p);
+	status = decode_compound_hdr(&xdr, &hdr);
+	if (!status)
+		status = decode_create_session(&xdr, res);
+	return status;
+}
+
+/*
+ * a DESTROY_SESSION request
+ */
+static int nfs4_xdr_dec_destroy_session(struct rpc_rqst *rqstp, uint32_t *p,
+					void *dummy)
+{
+	struct xdr_stream xdr;
+	struct compound_hdr hdr;
+	int status;
+
+	xdr_init_decode(&xdr, &rqstp->rq_rcv_buf, p);
+	status = decode_compound_hdr(&xdr, &hdr);
+	if (!status)
+		status = decode_destroy_session(&xdr, dummy);
+	return status;
+}
+
+/*
+ * a SEQUENCE request
+ */
+static int nfs4_xdr_dec_sequence(struct rpc_rqst *rqstp, uint32_t *p,
+				 struct nfs4_sequence_res *res)
+{
+	struct xdr_stream xdr;
+	struct compound_hdr hdr;
+	int status;
+
+	xdr_init_decode(&xdr, &rqstp->rq_rcv_buf, p);
+	status = decode_compound_hdr(&xdr, &hdr);
+	if (!status)
+		status = decode_sequence(&xdr, res, rqstp);
+	return status;
+}
+
+/*
+ * a GET_LEASE_TIME request
+ */
+static int nfs4_xdr_dec_get_lease_time(struct rpc_rqst *rqstp, uint32_t *p,
+				       struct nfs4_get_lease_time_res *res)
+{
+	struct xdr_stream xdr;
+	struct compound_hdr hdr;
+	int status;
+
+	xdr_init_decode(&xdr, &rqstp->rq_rcv_buf, p);
+	status = decode_compound_hdr(&xdr, &hdr);
+	if (!status)
+		status = decode_sequence(&xdr, &res->lr_seq_res, rqstp);
+	if (!status)
+		status = decode_putrootfh(&xdr);
+	if (!status)
+		status = decode_fsinfo(&xdr, res->lr_fsinfo);
+	return status;
+}
+#endif /* CONFIG_NFS_V4_1 */
+
 __be32 *nfs4_decode_dirent(__be32 *p, struct nfs_entry *entry, int plus)
 {
 	uint32_t bitmap[2] = {0};
@@ -4686,6 +5487,13 @@ struct rpc_procinfo	nfs4_procedures[] = {
   PROC(GETACL,		enc_getacl,	dec_getacl),
   PROC(SETACL,		enc_setacl,	dec_setacl),
   PROC(FS_LOCATIONS,	enc_fs_locations, dec_fs_locations),
+#if defined(CONFIG_NFS_V4_1)
+  PROC(EXCHANGE_ID,	enc_exchange_id,	dec_exchange_id),
+  PROC(CREATE_SESSION,	enc_create_session,	dec_create_session),
+  PROC(DESTROY_SESSION,	enc_destroy_session,	dec_destroy_session),
+  PROC(SEQUENCE,	enc_sequence,	dec_sequence),
+  PROC(GET_LEASE_TIME,	enc_get_lease_time,	dec_get_lease_time),
+#endif /* CONFIG_NFS_V4_1 */
 };
 
 struct rpc_version		nfs_version4 = {

fs/nfs/nfsroot.c

@@ -92,6 +92,9 @@
 #undef NFSROOT_DEBUG
 #define NFSDBG_FACILITY NFSDBG_ROOT
 
+/* Default port to use if server is not running a portmapper */
+#define NFS_MNT_PORT	627
+
 /* Default path we try to mount. "%s" gets replaced by our IP address */
 #define NFS_ROOT		"/tftpboot/%s"
 
@@ -487,6 +490,7 @@ static int __init root_nfs_get_handle(void)
 {
 	struct nfs_fh fh;
 	struct sockaddr_in sin;
+	unsigned int auth_flav_len = 0;
 	struct nfs_mount_request request = {
 		.sap		= (struct sockaddr *)&sin,
 		.salen		= sizeof(sin),
@@ -496,6 +500,7 @@ static int __init root_nfs_get_handle(void)
 		.protocol	= (nfs_data.flags & NFS_MOUNT_TCP) ?
 					XPRT_TRANSPORT_TCP : XPRT_TRANSPORT_UDP,
 		.fh		= &fh,
+		.auth_flav_len	= &auth_flav_len,
 	};
 	int status;
 

fs/nfs/read.c

@@ -22,6 +22,7 @@
 
 #include <asm/system.h>
 
+#include "nfs4_fs.h"
 #include "internal.h"
 #include "iostat.h"
 #include "fscache.h"
@@ -46,6 +47,7 @@ struct nfs_read_data *nfs_readdata_alloc(unsigned int pagecount)
 		memset(p, 0, sizeof(*p));
 		INIT_LIST_HEAD(&p->pages);
 		p->npages = pagecount;
+		p->res.seq_res.sr_slotid = NFS4_MAX_SLOT_TABLE;
 		if (pagecount <= ARRAY_SIZE(p->page_array))
 			p->pagevec = p->page_array;
 		else {
@@ -357,19 +359,25 @@ static void nfs_readpage_retry(struct rpc_task *task, struct nfs_read_data *data
 	struct nfs_readres *resp = &data->res;
 
 	if (resp->eof || resp->count == argp->count)
-		return;
+		goto out;
 
 	/* This is a short read! */
 	nfs_inc_stats(data->inode, NFSIOS_SHORTREAD);
 	/* Has the server at least made some progress? */
 	if (resp->count == 0)
-		return;
+		goto out;
 
 	/* Yes, so retry the read at the end of the data */
 	argp->offset += resp->count;
 	argp->pgbase += resp->count;
 	argp->count -= resp->count;
-	rpc_restart_call(task);
+	nfs4_restart_rpc(task, NFS_SERVER(data->inode)->nfs_client);
+	return;
+out:
+	nfs4_sequence_free_slot(NFS_SERVER(data->inode)->nfs_client,
+				&data->res.seq_res);
+	return;
+
 }
 
 /*
@@ -406,7 +414,23 @@ static void nfs_readpage_release_partial(void *calldata)
 	nfs_readdata_release(calldata);
 }
 
+#if defined(CONFIG_NFS_V4_1)
+void nfs_read_prepare(struct rpc_task *task, void *calldata)
+{
+	struct nfs_read_data *data = calldata;
+
+	if (nfs4_setup_sequence(NFS_SERVER(data->inode)->nfs_client,
+				&data->args.seq_args, &data->res.seq_res,
+				0, task))
+		return;
+	rpc_call_start(task);
+}
+#endif /* CONFIG_NFS_V4_1 */
+
 static const struct rpc_call_ops nfs_read_partial_ops = {
+#if defined(CONFIG_NFS_V4_1)
+	.rpc_call_prepare = nfs_read_prepare,
+#endif /* CONFIG_NFS_V4_1 */
 	.rpc_call_done = nfs_readpage_result_partial,
 	.rpc_release = nfs_readpage_release_partial,
 };
@@ -470,6 +494,9 @@ static void nfs_readpage_release_full(void *calldata)
 }
 
 static const struct rpc_call_ops nfs_read_full_ops = {
+#if defined(CONFIG_NFS_V4_1)
+	.rpc_call_prepare = nfs_read_prepare,
+#endif /* CONFIG_NFS_V4_1 */
 	.rpc_call_done = nfs_readpage_result_full,
 	.rpc_release = nfs_readpage_release_full,
 };

fs/nfs/super.c

@@ -90,6 +90,7 @@ enum {
 	Opt_mountport,
 	Opt_mountvers,
 	Opt_nfsvers,
+	Opt_minorversion,
 
 	/* Mount options that take string arguments */
 	Opt_sec, Opt_proto, Opt_mountproto, Opt_mounthost,
@@ -139,22 +140,23 @@ static const match_table_t nfs_mount_option_tokens = {
 	{ Opt_fscache_uniq, "fsc=%s" },
 	{ Opt_nofscache, "nofsc" },
 
-	{ Opt_port, "port=%u" },
-	{ Opt_rsize, "rsize=%u" },
-	{ Opt_wsize, "wsize=%u" },
-	{ Opt_bsize, "bsize=%u" },
-	{ Opt_timeo, "timeo=%u" },
-	{ Opt_retrans, "retrans=%u" },
-	{ Opt_acregmin, "acregmin=%u" },
-	{ Opt_acregmax, "acregmax=%u" },
-	{ Opt_acdirmin, "acdirmin=%u" },
-	{ Opt_acdirmax, "acdirmax=%u" },
-	{ Opt_actimeo, "actimeo=%u" },
-	{ Opt_namelen, "namlen=%u" },
-	{ Opt_mountport, "mountport=%u" },
-	{ Opt_mountvers, "mountvers=%u" },
-	{ Opt_nfsvers, "nfsvers=%u" },
-	{ Opt_nfsvers, "vers=%u" },
+	{ Opt_port, "port=%s" },
+	{ Opt_rsize, "rsize=%s" },
+	{ Opt_wsize, "wsize=%s" },
+	{ Opt_bsize, "bsize=%s" },
+	{ Opt_timeo, "timeo=%s" },
+	{ Opt_retrans, "retrans=%s" },
+	{ Opt_acregmin, "acregmin=%s" },
+	{ Opt_acregmax, "acregmax=%s" },
+	{ Opt_acdirmin, "acdirmin=%s" },
+	{ Opt_acdirmax, "acdirmax=%s" },
+	{ Opt_actimeo, "actimeo=%s" },
+	{ Opt_namelen, "namlen=%s" },
+	{ Opt_mountport, "mountport=%s" },
+	{ Opt_mountvers, "mountvers=%s" },
+	{ Opt_nfsvers, "nfsvers=%s" },
+	{ Opt_nfsvers, "vers=%s" },
+	{ Opt_minorversion, "minorversion=%u" },
 
 	{ Opt_sec, "sec=%s" },
 	{ Opt_proto, "proto=%s" },
@@ -514,7 +516,6 @@ static void nfs_show_mount_options(struct seq_file *m, struct nfs_server *nfss,
 		const char *nostr;
 	} nfs_info[] = {
 		{ NFS_MOUNT_SOFT, ",soft", ",hard" },
-		{ NFS_MOUNT_INTR, ",intr", ",nointr" },
 		{ NFS_MOUNT_POSIX, ",posix", "" },
 		{ NFS_MOUNT_NOCTO, ",nocto", "" },
 		{ NFS_MOUNT_NOAC, ",noac", "" },
@@ -943,11 +944,6 @@ static int nfs_parse_security_flavors(char *value,
 	return 1;
 }
 
-static void nfs_parse_invalid_value(const char *option)
-{
-	dfprintk(MOUNT, "NFS:   bad value specified for %s option\n", option);
-}
-
 /*
  * Error-check and convert a string of mount options from user space into
  * a data structure.  The whole mount string is processed; bad options are
@@ -958,7 +954,7 @@ static int nfs_parse_mount_options(char *raw,
 				   struct nfs_parsed_mount_data *mnt)
 {
 	char *p, *string, *secdata;
-	int rc, sloppy = 0, errors = 0;
+	int rc, sloppy = 0, invalid_option = 0;
 
 	if (!raw) {
 		dfprintk(MOUNT, "NFS: mount options string was NULL.\n");
@@ -982,7 +978,9 @@ static int nfs_parse_mount_options(char *raw,
 
 	while ((p = strsep(&raw, ",")) != NULL) {
 		substring_t args[MAX_OPT_ARGS];
-		int option, token;
+		unsigned long option;
+		int int_option;
+		int token;
 
 		if (!*p)
 			continue;
@@ -1091,114 +1089,156 @@ static int nfs_parse_mount_options(char *raw,
 		 * options that take numeric values
 		 */
 		case Opt_port:
-			if (match_int(args, &option) ||
-			    option < 0 || option > USHORT_MAX) {
-				errors++;
-				nfs_parse_invalid_value("port");
-			} else
-				mnt->nfs_server.port = option;
+			string = match_strdup(args);
+			if (string == NULL)
+				goto out_nomem;
+			rc = strict_strtoul(string, 10, &option);
+			kfree(string);
+			if (rc != 0 || option > USHORT_MAX)
+				goto out_invalid_value;
+			mnt->nfs_server.port = option;
 			break;
 		case Opt_rsize:
-			if (match_int(args, &option) || option < 0) {
-				errors++;
-				nfs_parse_invalid_value("rsize");
-			} else
-				mnt->rsize = option;
+			string = match_strdup(args);
+			if (string == NULL)
+				goto out_nomem;
+			rc = strict_strtoul(string, 10, &option);
+			kfree(string);
+			if (rc != 0)
+				goto out_invalid_value;
+			mnt->rsize = option;
 			break;
 		case Opt_wsize:
-			if (match_int(args, &option) || option < 0) {
-				errors++;
-				nfs_parse_invalid_value("wsize");
-			} else
-				mnt->wsize = option;
+			string = match_strdup(args);
+			if (string == NULL)
+				goto out_nomem;
+			rc = strict_strtoul(string, 10, &option);
+			kfree(string);
+			if (rc != 0)
+				goto out_invalid_value;
+			mnt->wsize = option;
 			break;
 		case Opt_bsize:
-			if (match_int(args, &option) || option < 0) {
-				errors++;
-				nfs_parse_invalid_value("bsize");
-			} else
-				mnt->bsize = option;
+			string = match_strdup(args);
+			if (string == NULL)
+				goto out_nomem;
+			rc = strict_strtoul(string, 10, &option);
+			kfree(string);
+			if (rc != 0)
+				goto out_invalid_value;
+			mnt->bsize = option;
 			break;
 		case Opt_timeo:
-			if (match_int(args, &option) || option <= 0) {
-				errors++;
-				nfs_parse_invalid_value("timeo");
-			} else
-				mnt->timeo = option;
+			string = match_strdup(args);
+			if (string == NULL)
+				goto out_nomem;
+			rc = strict_strtoul(string, 10, &option);
+			kfree(string);
+			if (rc != 0 || option == 0)
+				goto out_invalid_value;
+			mnt->timeo = option;
 			break;
 		case Opt_retrans:
-			if (match_int(args, &option) || option <= 0) {
-				errors++;
-				nfs_parse_invalid_value("retrans");
-			} else
-				mnt->retrans = option;
+			string = match_strdup(args);
+			if (string == NULL)
+				goto out_nomem;
+			rc = strict_strtoul(string, 10, &option);
+			kfree(string);
+			if (rc != 0 || option == 0)
+				goto out_invalid_value;
+			mnt->retrans = option;
 			break;
 		case Opt_acregmin:
-			if (match_int(args, &option) || option < 0) {
-				errors++;
-				nfs_parse_invalid_value("acregmin");
-			} else
-				mnt->acregmin = option;
+			string = match_strdup(args);
+			if (string == NULL)
+				goto out_nomem;
+			rc = strict_strtoul(string, 10, &option);
+			kfree(string);
+			if (rc != 0)
+				goto out_invalid_value;
+			mnt->acregmin = option;
 			break;
 		case Opt_acregmax:
-			if (match_int(args, &option) || option < 0) {
-				errors++;
-				nfs_parse_invalid_value("acregmax");
-			} else
-				mnt->acregmax = option;
+			string = match_strdup(args);
+			if (string == NULL)
+				goto out_nomem;
+			rc = strict_strtoul(string, 10, &option);
+			kfree(string);
+			if (rc != 0)
+				goto out_invalid_value;
+			mnt->acregmax = option;
 			break;
 		case Opt_acdirmin:
-			if (match_int(args, &option) || option < 0) {
-				errors++;
-				nfs_parse_invalid_value("acdirmin");
-			} else
-				mnt->acdirmin = option;
+			string = match_strdup(args);
+			if (string == NULL)
+				goto out_nomem;
+			rc = strict_strtoul(string, 10, &option);
+			kfree(string);
+			if (rc != 0)
+				goto out_invalid_value;
+			mnt->acdirmin = option;
 			break;
 		case Opt_acdirmax:
-			if (match_int(args, &option) || option < 0) {
-				errors++;
-				nfs_parse_invalid_value("acdirmax");
-			} else
-				mnt->acdirmax = option;
+			string = match_strdup(args);
+			if (string == NULL)
+				goto out_nomem;
+			rc = strict_strtoul(string, 10, &option);
+			kfree(string);
+			if (rc != 0)
+				goto out_invalid_value;
+			mnt->acdirmax = option;
 			break;
 		case Opt_actimeo:
-			if (match_int(args, &option) || option < 0) {
-				errors++;
-				nfs_parse_invalid_value("actimeo");
-			} else
-				mnt->acregmin = mnt->acregmax =
-				mnt->acdirmin = mnt->acdirmax = option;
+			string = match_strdup(args);
+			if (string == NULL)
+				goto out_nomem;
+			rc = strict_strtoul(string, 10, &option);
+			kfree(string);
+			if (rc != 0)
+				goto out_invalid_value;
+			mnt->acregmin = mnt->acregmax =
+			mnt->acdirmin = mnt->acdirmax = option;
 			break;
 		case Opt_namelen:
-			if (match_int(args, &option) || option < 0) {
-				errors++;
-				nfs_parse_invalid_value("namlen");
-			} else
-				mnt->namlen = option;
+			string = match_strdup(args);
+			if (string == NULL)
+				goto out_nomem;
+			rc = strict_strtoul(string, 10, &option);
+			kfree(string);
+			if (rc != 0)
+				goto out_invalid_value;
+			mnt->namlen = option;
 			break;
 		case Opt_mountport:
-			if (match_int(args, &option) ||
-			    option < 0 || option > USHORT_MAX) {
-				errors++;
-				nfs_parse_invalid_value("mountport");
-			} else
-				mnt->mount_server.port = option;
+			string = match_strdup(args);
+			if (string == NULL)
+				goto out_nomem;
+			rc = strict_strtoul(string, 10, &option);
+			kfree(string);
+			if (rc != 0 || option > USHORT_MAX)
+				goto out_invalid_value;
+			mnt->mount_server.port = option;
 			break;
 		case Opt_mountvers:
-			if (match_int(args, &option) ||
+			string = match_strdup(args);
+			if (string == NULL)
+				goto out_nomem;
+			rc = strict_strtoul(string, 10, &option);
+			kfree(string);
+			if (rc != 0 ||
 			    option < NFS_MNT_VERSION ||
-			    option > NFS_MNT3_VERSION) {
-				errors++;
-				nfs_parse_invalid_value("mountvers");
-			} else
-				mnt->mount_server.version = option;
+			    option > NFS_MNT3_VERSION)
+				goto out_invalid_value;
+			mnt->mount_server.version = option;
 			break;
 		case Opt_nfsvers:
-			if (match_int(args, &option)) {
-				errors++;
-				nfs_parse_invalid_value("nfsvers");
-				break;
-			}
+			string = match_strdup(args);
+			if (string == NULL)
+				goto out_nomem;
+			rc = strict_strtoul(string, 10, &option);
+			kfree(string);
+			if (rc != 0)
+				goto out_invalid_value;
 			switch (option) {
 			case NFS2_VERSION:
 				mnt->flags &= ~NFS_MOUNT_VER3;
@@ -1207,10 +1247,16 @@ static int nfs_parse_mount_options(char *raw,
 				mnt->flags |= NFS_MOUNT_VER3;
 				break;
 			default:
-				errors++;
-				nfs_parse_invalid_value("nfsvers");
+				goto out_invalid_value;
 			}
 			break;
+		case Opt_minorversion:
+			if (match_int(args, &int_option))
+				return 0;
+			if (int_option < 0 || int_option > NFS4_MAX_MINOR_VERSION)
+				return 0;
+			mnt->minorversion = int_option;
+			break;
 
 		/*
 		 * options that take text values
@@ -1222,9 +1268,9 @@ static int nfs_parse_mount_options(char *raw,
 			rc = nfs_parse_security_flavors(string, mnt);
 			kfree(string);
 			if (!rc) {
-				errors++;
 				dfprintk(MOUNT, "NFS:   unrecognized "
 						"security flavor\n");
+				return 0;
 			}
 			break;
 		case Opt_proto:
@@ -1238,23 +1284,25 @@ static int nfs_parse_mount_options(char *raw,
 			case Opt_xprt_udp:
 				mnt->flags &= ~NFS_MOUNT_TCP;
 				mnt->nfs_server.protocol = XPRT_TRANSPORT_UDP;
+				kfree(string);
 				break;
 			case Opt_xprt_tcp:
 				mnt->flags |= NFS_MOUNT_TCP;
 				mnt->nfs_server.protocol = XPRT_TRANSPORT_TCP;
+				kfree(string);
 				break;
 			case Opt_xprt_rdma:
 				/* vector side protocols to TCP */
 				mnt->flags |= NFS_MOUNT_TCP;
 				mnt->nfs_server.protocol = XPRT_TRANSPORT_RDMA;
 				xprt_load_transport(string);
+				kfree(string);
 				break;
 			default:
-				errors++;
 				dfprintk(MOUNT, "NFS:   unrecognized "
 						"transport protocol\n");
+				return 0;
 			}
-			kfree(string);
 			break;
 		case Opt_mountproto:
 			string = match_strdup(args);
@@ -1273,9 +1321,9 @@ static int nfs_parse_mount_options(char *raw,
 				break;
 			case Opt_xprt_rdma: /* not used for side protocols */
 			default:
-				errors++;
 				dfprintk(MOUNT, "NFS:   unrecognized "
 						"transport protocol\n");
+				return 0;
 			}
 			break;
 		case Opt_addr:
@@ -1331,9 +1379,9 @@ static int nfs_parse_mount_options(char *raw,
 					mnt->flags |= NFS_MOUNT_LOOKUP_CACHE_NONEG|NFS_MOUNT_LOOKUP_CACHE_NONE;
 					break;
 				default:
-					errors++;
 					dfprintk(MOUNT, "NFS:   invalid "
 							"lookupcache argument\n");
+					return 0;
 			};
 			break;
 
@@ -1351,20 +1399,20 @@ static int nfs_parse_mount_options(char *raw,
 			break;
 
 		default:
-			errors++;
+			invalid_option = 1;
 			dfprintk(MOUNT, "NFS:   unrecognized mount option "
 					"'%s'\n", p);
 		}
 	}
 
-	if (errors > 0) {
-		dfprintk(MOUNT, "NFS: parsing encountered %d error%s\n",
-				errors, (errors == 1 ? "" : "s"));
-		if (!sloppy)
-			return 0;
-	}
+	if (!sloppy && invalid_option)
+		return 0;
+
 	return 1;
 
+out_invalid_value:
+	printk(KERN_INFO "NFS: bad mount option value specified: %s \n", p);
+	return 0;
 out_nomem:
 	printk(KERN_INFO "NFS: not enough memory to parse option\n");
 	return 0;
@@ -1381,6 +1429,7 @@ out_security_failure:
 static int nfs_try_mount(struct nfs_parsed_mount_data *args,
 			 struct nfs_fh *root_fh)
 {
+	unsigned int auth_flavor_len = 0;
 	struct nfs_mount_request request = {
 		.sap		= (struct sockaddr *)
 						&args->mount_server.address,
@@ -1388,6 +1437,7 @@ static int nfs_try_mount(struct nfs_parsed_mount_data *args,
 		.protocol	= args->mount_server.protocol,
 		.fh		= root_fh,
 		.noresvport	= args->flags & NFS_MOUNT_NORESVPORT,
+		.auth_flav_len	= &auth_flavor_len,
 	};
 	int status;
 
@@ -2240,6 +2290,11 @@ static void nfs4_fill_super(struct super_block *sb)
 	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);
+}
+
 /*
  * Validate NFSv4 mount options
  */
@@ -2263,6 +2318,7 @@ static int nfs4_validate_mount_data(void *options,
 	args->nfs_server.port	= NFS_PORT; /* 2049 unless user set port= */
 	args->auth_flavors[0]	= RPC_AUTH_UNIX;
 	args->auth_flavor_len	= 0;
+	args->minorversion	= 0;
 
 	switch (data->version) {
 	case 1:
@@ -2336,6 +2392,8 @@ static int nfs4_validate_mount_data(void *options,
 
 		nfs_validate_transport_protocol(args);
 
+		nfs4_validate_mount_flags(args);
+
 		if (args->auth_flavor_len > 1)
 			goto out_inval_auth;
 
@@ -2477,12 +2535,13 @@ 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);
-
 	nfs4_renewd_prepare_shutdown(server);
 	nfs_fscache_release_super_cookie(sb);
 	nfs_free_server(server);
+	dprintk("<-- %s\n", __func__);
 }
 
 /*

fs/nfs/unlink.c

@@ -15,6 +15,7 @@
 #include <linux/wait.h>
 
 #include "internal.h"
+#include "nfs4_fs.h"
 
 struct nfs_unlinkdata {
 	struct hlist_node list;
@@ -82,7 +83,7 @@ static void nfs_async_unlink_done(struct rpc_task *task, void *calldata)
 	struct inode *dir = data->dir;
 
 	if (!NFS_PROTO(dir)->unlink_done(task, dir))
-		rpc_restart_call(task);
+		nfs4_restart_rpc(task, NFS_SERVER(dir)->nfs_client);
 }
 
 /**
@@ -102,9 +103,25 @@ static void nfs_async_unlink_release(void *calldata)
 	nfs_sb_deactive(sb);
 }
 
+#if defined(CONFIG_NFS_V4_1)
+void nfs_unlink_prepare(struct rpc_task *task, void *calldata)
+{
+	struct nfs_unlinkdata *data = calldata;
+	struct nfs_server *server = NFS_SERVER(data->dir);
+
+	if (nfs4_setup_sequence(server->nfs_client, &data->args.seq_args,
+				&data->res.seq_res, 1, task))
+		return;
+	rpc_call_start(task);
+}
+#endif /* CONFIG_NFS_V4_1 */
+
 static const struct rpc_call_ops nfs_unlink_ops = {
 	.rpc_call_done = nfs_async_unlink_done,
 	.rpc_release = nfs_async_unlink_release,
+#if defined(CONFIG_NFS_V4_1)
+	.rpc_call_prepare = nfs_unlink_prepare,
+#endif /* CONFIG_NFS_V4_1 */
 };
 
 static int nfs_do_call_unlink(struct dentry *parent, struct inode *dir, struct nfs_unlinkdata *data)
@@ -241,6 +258,7 @@ nfs_async_unlink(struct inode *dir, struct dentry *dentry)
 		status = PTR_ERR(data->cred);
 		goto out_free;
 	}
+	data->res.seq_res.sr_slotid = NFS4_MAX_SLOT_TABLE;
 
 	status = -EBUSY;
 	spin_lock(&dentry->d_lock);

fs/nfs/write.c

@@ -25,6 +25,7 @@
 #include "delegation.h"
 #include "internal.h"
 #include "iostat.h"
+#include "nfs4_fs.h"
 
 #define NFSDBG_FACILITY		NFSDBG_PAGECACHE
 
@@ -52,6 +53,7 @@ struct nfs_write_data *nfs_commitdata_alloc(void)
 	if (p) {
 		memset(p, 0, sizeof(*p));
 		INIT_LIST_HEAD(&p->pages);
+		p->res.seq_res.sr_slotid = NFS4_MAX_SLOT_TABLE;
 	}
 	return p;
 }
@@ -71,6 +73,7 @@ struct nfs_write_data *nfs_writedata_alloc(unsigned int pagecount)
 		memset(p, 0, sizeof(*p));
 		INIT_LIST_HEAD(&p->pages);
 		p->npages = pagecount;
+		p->res.seq_res.sr_slotid = NFS4_MAX_SLOT_TABLE;
 		if (pagecount <= ARRAY_SIZE(p->page_array))
 			p->pagevec = p->page_array;
 		else {
@@ -1048,7 +1051,23 @@ out:
 	nfs_writedata_release(calldata);
 }
 
+#if defined(CONFIG_NFS_V4_1)
+void nfs_write_prepare(struct rpc_task *task, void *calldata)
+{
+	struct nfs_write_data *data = calldata;
+	struct nfs_client *clp = (NFS_SERVER(data->inode))->nfs_client;
+
+	if (nfs4_setup_sequence(clp, &data->args.seq_args,
+				&data->res.seq_res, 1, task))
+		return;
+	rpc_call_start(task);
+}
+#endif /* CONFIG_NFS_V4_1 */
+
 static const struct rpc_call_ops nfs_write_partial_ops = {
+#if defined(CONFIG_NFS_V4_1)
+	.rpc_call_prepare = nfs_write_prepare,
+#endif /* CONFIG_NFS_V4_1 */
 	.rpc_call_done = nfs_writeback_done_partial,
 	.rpc_release = nfs_writeback_release_partial,
 };
@@ -1111,6 +1130,9 @@ remove_request:
 }
 
 static const struct rpc_call_ops nfs_write_full_ops = {
+#if defined(CONFIG_NFS_V4_1)
+	.rpc_call_prepare = nfs_write_prepare,
+#endif /* CONFIG_NFS_V4_1 */
 	.rpc_call_done = nfs_writeback_done_full,
 	.rpc_release = nfs_writeback_release_full,
 };
@@ -1123,6 +1145,7 @@ int nfs_writeback_done(struct rpc_task *task, struct nfs_write_data *data)
 {
 	struct nfs_writeargs	*argp = &data->args;
 	struct nfs_writeres	*resp = &data->res;
+	struct nfs_server	*server = NFS_SERVER(data->inode);
 	int status;
 
 	dprintk("NFS: %5u nfs_writeback_done (status %d)\n",
@@ -1155,7 +1178,7 @@ int nfs_writeback_done(struct rpc_task *task, struct nfs_write_data *data)
 		if (time_before(complain, jiffies)) {
 			dprintk("NFS:       faulty NFS server %s:"
 				" (committed = %d) != (stable = %d)\n",
-				NFS_SERVER(data->inode)->nfs_client->cl_hostname,
+				server->nfs_client->cl_hostname,
 				resp->verf->committed, argp->stable);
 			complain = jiffies + 300 * HZ;
 		}
@@ -1181,7 +1204,7 @@ int nfs_writeback_done(struct rpc_task *task, struct nfs_write_data *data)
 				 */
 				argp->stable = NFS_FILE_SYNC;
 			}
-			rpc_restart_call(task);
+			nfs4_restart_rpc(task, server->nfs_client);
 			return -EAGAIN;
 		}
 		if (time_before(complain, jiffies)) {
@@ -1193,6 +1216,7 @@ int nfs_writeback_done(struct rpc_task *task, struct nfs_write_data *data)
 		/* Can't do anything about it except throw an error. */
 		task->tk_status = -EIO;
 	}
+	nfs4_sequence_free_slot(server->nfs_client, &data->res.seq_res);
 	return 0;
 }
 
@@ -1349,6 +1373,9 @@ static void nfs_commit_release(void *calldata)
 }
 
 static const struct rpc_call_ops nfs_commit_ops = {
+#if defined(CONFIG_NFS_V4_1)
+	.rpc_call_prepare = nfs_write_prepare,
+#endif /* CONFIG_NFS_V4_1 */
 	.rpc_call_done = nfs_commit_done,
 	.rpc_release = nfs_commit_release,
 };

include/linux/lockd/lockd.h

@@ -195,7 +195,7 @@ extern struct svc_procedure	nlmsvc_procedures4[];
 extern int			nlmsvc_grace_period;
 extern unsigned long		nlmsvc_timeout;
 extern int			nsm_use_hostnames;
-extern int			nsm_local_state;
+extern u32			nsm_local_state;
 
 /*
  * Lockd client functions

include/linux/nfs.h

@@ -25,8 +25,9 @@
 #define NFSMODE_SOCK	0140000
 #define NFSMODE_FIFO	0010000
 
-#define NFS_MNT_PROGRAM	100005
-#define NFS_MNT_PORT	627
+#define NFS_MNT_PROGRAM		100005
+#define NFS_MNT_VERSION		1
+#define NFS_MNT3_VERSION	3
 
 /*
  * NFS stats. The good thing with these values is that NFSv3 errors are

include/linux/nfs2.h

@@ -64,11 +64,4 @@ struct nfs2_fh {
 #define NFSPROC_READDIR		16
 #define NFSPROC_STATFS		17
 
-#define NFS_MNT_PROGRAM		100005
-#define NFS_MNT_VERSION		1
-#define MNTPROC_NULL		0
-#define MNTPROC_MNT		1
-#define MNTPROC_UMNT		3
-#define MNTPROC_UMNTALL		4
-
 #endif /* _LINUX_NFS2_H */

include/linux/nfs3.h

@@ -88,12 +88,7 @@ struct nfs3_fh {
 #define NFS3PROC_PATHCONF	20
 #define NFS3PROC_COMMIT		21
 
-#define NFS_MNT3_PROGRAM	100005
 #define NFS_MNT3_VERSION	3
-#define MOUNTPROC3_NULL		0
-#define MOUNTPROC3_MNT		1
-#define MOUNTPROC3_UMNT		3
-#define MOUNTPROC3_UMNTALL	4
  
 
 #if defined(__KERNEL__)

include/linux/nfs4.h

@@ -21,6 +21,7 @@
 #define NFS4_FHSIZE		128
 #define NFS4_MAXPATHLEN		PATH_MAX
 #define NFS4_MAXNAMLEN		NAME_MAX
+#define NFS4_OPAQUE_LIMIT	1024
 #define NFS4_MAX_SESSIONID_LEN	16
 
 #define NFS4_ACCESS_READ        0x0001
@@ -130,6 +131,16 @@
 
 #define NFS4_MAX_UINT64	(~(u64)0)
 
+/* An NFS4 sessions server must support at least NFS4_MAX_OPS operations.
+ * If a compound requires more operations, adjust NFS4_MAX_OPS accordingly.
+ */
+#define NFS4_MAX_OPS   8
+
+/* Our NFS4 client back channel server only wants the cb_sequene and the
+ * actual operation per compound
+ */
+#define NFS4_MAX_BACK_CHANNEL_OPS 2
+
 enum nfs4_acl_whotype {
 	NFS4_ACL_WHO_NAMED = 0,
 	NFS4_ACL_WHO_OWNER,
@@ -462,6 +473,13 @@ enum lock_type4 {
 #define NFSPROC4_NULL 0
 #define NFSPROC4_COMPOUND 1
 #define NFS4_MINOR_VERSION 0
+
+#if defined(CONFIG_NFS_V4_1)
+#define NFS4_MAX_MINOR_VERSION 1
+#else
+#define NFS4_MAX_MINOR_VERSION 0
+#endif /* CONFIG_NFS_V4_1 */
+
 #define NFS4_DEBUG 1
 
 /* Index of predefined Linux client operations */

include/linux/nfs_fs_sb.h

@@ -4,11 +4,17 @@
 #include <linux/list.h>
 #include <linux/backing-dev.h>
 #include <linux/wait.h>
+#include <linux/nfs_xdr.h>
+#include <linux/sunrpc/xprt.h>
 
 #include <asm/atomic.h>
 
+struct nfs4_session;
 struct nfs_iostats;
 struct nlm_host;
+struct nfs4_sequence_args;
+struct nfs4_sequence_res;
+struct nfs_server;
 
 /*
  * The nfs_client identifies our client state to the server.
@@ -18,6 +24,7 @@ struct nfs_client {
 	int			cl_cons_state;	/* current construction state (-ve: init error) */
 #define NFS_CS_READY		0		/* ready to be used */
 #define NFS_CS_INITING		1		/* busy initialising */
+#define NFS_CS_SESSION_INITING	2		/* busy initialising  session */
 	unsigned long		cl_res_state;	/* NFS resources state */
 #define NFS_CS_CALLBACK		1		/* - callback started */
 #define NFS_CS_IDMAP		2		/* - idmap started */
@@ -32,6 +39,7 @@ struct nfs_client {
 	const struct nfs_rpc_ops *rpc_ops;	/* NFS protocol vector */
 	int			cl_proto;	/* Network transport protocol */
 
+	u32			cl_minorversion;/* NFSv4 minorversion */
 	struct rpc_cred		*cl_machine_cred;
 
 #ifdef CONFIG_NFS_V4
@@ -63,7 +71,22 @@ struct nfs_client {
 	 */
 	char			cl_ipaddr[48];
 	unsigned char		cl_id_uniquifier;
-#endif
+	int		     (* cl_call_sync)(struct nfs_server *server,
+					      struct rpc_message *msg,
+					      struct nfs4_sequence_args *args,
+					      struct nfs4_sequence_res *res,
+					      int cache_reply);
+#endif /* CONFIG_NFS_V4 */
+
+#ifdef CONFIG_NFS_V4_1
+	/* clientid returned from EXCHANGE_ID, used by session operations */
+	u64			cl_ex_clid;
+	/* The sequence id to use for the next CREATE_SESSION */
+	u32			cl_seqid;
+	/* The flags used for obtaining the clientid during EXCHANGE_ID */
+	u32			cl_exchange_flags;
+	struct nfs4_session	*cl_session; 	/* sharred session */
+#endif /* CONFIG_NFS_V4_1 */
 
 #ifdef CONFIG_NFS_FSCACHE
 	struct fscache_cookie	*fscache;	/* client index cache cookie */
@@ -145,4 +168,46 @@ struct nfs_server {
 #define NFS_CAP_ACLS		(1U << 3)
 #define NFS_CAP_ATOMIC_OPEN	(1U << 4)
 
+
+/* maximum number of slots to use */
+#define NFS4_MAX_SLOT_TABLE RPC_MAX_SLOT_TABLE
+
+#if defined(CONFIG_NFS_V4_1)
+
+/* Sessions */
+#define SLOT_TABLE_SZ (NFS4_MAX_SLOT_TABLE/(8*sizeof(long)))
+struct nfs4_slot_table {
+	struct nfs4_slot *slots;		/* seqid per slot */
+	unsigned long   used_slots[SLOT_TABLE_SZ]; /* used/unused bitmap */
+	spinlock_t	slot_tbl_lock;
+	struct rpc_wait_queue	slot_tbl_waitq;	/* allocators may wait here */
+	int		max_slots;		/* # slots in table */
+	int		highest_used_slotid;	/* sent to server on each SEQ.
+						 * op for dynamic resizing */
+};
+
+static inline int slot_idx(struct nfs4_slot_table *tbl, struct nfs4_slot *sp)
+{
+	return sp - tbl->slots;
+}
+
+/*
+ * Session related parameters
+ */
+struct nfs4_session {
+	struct nfs4_sessionid		sess_id;
+	u32				flags;
+	unsigned long			session_state;
+	u32				hash_alg;
+	u32				ssv_len;
+
+	/* The fore and back channel */
+	struct nfs4_channel_attrs	fc_attrs;
+	struct nfs4_slot_table		fc_slot_table;
+	struct nfs4_channel_attrs	bc_attrs;
+	struct nfs4_slot_table		bc_slot_table;
+	struct nfs_client		*clp;
+};
+
+#endif /* CONFIG_NFS_V4_1 */
 #endif

include/linux/nfs_xdr.h

@@ -145,6 +145,44 @@ struct nfs4_change_info {
 };
 
 struct nfs_seqid;
+
+/* nfs41 sessions channel attributes */
+struct nfs4_channel_attrs {
+	u32			headerpadsz;
+	u32			max_rqst_sz;
+	u32			max_resp_sz;
+	u32			max_resp_sz_cached;
+	u32			max_ops;
+	u32			max_reqs;
+};
+
+/* nfs41 sessions slot seqid */
+struct nfs4_slot {
+	u32		 	seq_nr;
+};
+
+struct nfs4_sequence_args {
+	struct nfs4_session	*sa_session;
+	u8			sa_slotid;
+	u8			sa_cache_this;
+};
+
+struct nfs4_sequence_res {
+	struct nfs4_session	*sr_session;
+	u8			sr_slotid;	/* slot used to send request */
+	unsigned long		sr_renewal_time;
+	int			sr_status;	/* sequence operation status */
+};
+
+struct nfs4_get_lease_time_args {
+	struct nfs4_sequence_args	la_seq_args;
+};
+
+struct nfs4_get_lease_time_res {
+	struct nfs_fsinfo	       *lr_fsinfo;
+	struct nfs4_sequence_res	lr_seq_res;
+};
+
 /*
  * Arguments to the open call.
  */
@@ -165,6 +203,7 @@ struct nfs_openargs {
 	const struct nfs_server *server;	 /* Needed for ID mapping */
 	const u32 *		bitmask;
 	__u32			claim;
+	struct nfs4_sequence_args	seq_args;
 };
 
 struct nfs_openres {
@@ -181,6 +220,7 @@ struct nfs_openres {
 	__u32			do_recall;
 	__u64			maxsize;
 	__u32			attrset[NFS4_BITMAP_SIZE];
+	struct nfs4_sequence_res	seq_res;
 };
 
 /*
@@ -206,6 +246,7 @@ struct nfs_closeargs {
 	struct nfs_seqid *	seqid;
 	fmode_t			fmode;
 	const u32 *		bitmask;
+	struct nfs4_sequence_args	seq_args;
 };
 
 struct nfs_closeres {
@@ -213,6 +254,7 @@ struct nfs_closeres {
 	struct nfs_fattr *	fattr;
 	struct nfs_seqid *	seqid;
 	const struct nfs_server *server;
+	struct nfs4_sequence_res	seq_res;
 };
 /*
  *  * Arguments to the lock,lockt, and locku call.
@@ -233,12 +275,14 @@ struct nfs_lock_args {
 	unsigned char		block : 1;
 	unsigned char		reclaim : 1;
 	unsigned char		new_lock_owner : 1;
+	struct nfs4_sequence_args	seq_args;
 };
 
 struct nfs_lock_res {
 	nfs4_stateid		stateid;
 	struct nfs_seqid *	lock_seqid;
 	struct nfs_seqid *	open_seqid;
+	struct nfs4_sequence_res	seq_res;
 };
 
 struct nfs_locku_args {
@@ -246,32 +290,38 @@ struct nfs_locku_args {
 	struct file_lock *	fl;
 	struct nfs_seqid *	seqid;
 	nfs4_stateid *		stateid;
+	struct nfs4_sequence_args	seq_args;
 };
 
 struct nfs_locku_res {
 	nfs4_stateid		stateid;
 	struct nfs_seqid *	seqid;
+	struct nfs4_sequence_res	seq_res;
 };
 
 struct nfs_lockt_args {
 	struct nfs_fh *		fh;
 	struct file_lock *	fl;
 	struct nfs_lowner	lock_owner;
+	struct nfs4_sequence_args	seq_args;
 };
 
 struct nfs_lockt_res {
 	struct file_lock *	denied; /* LOCK, LOCKT failed */
+	struct nfs4_sequence_res	seq_res;
 };
 
 struct nfs4_delegreturnargs {
 	const struct nfs_fh *fhandle;
 	const nfs4_stateid *stateid;
 	const u32 * bitmask;
+	struct nfs4_sequence_args	seq_args;
 };
 
 struct nfs4_delegreturnres {
 	struct nfs_fattr * fattr;
 	const struct nfs_server *server;
+	struct nfs4_sequence_res	seq_res;
 };
 
 /*
@@ -284,12 +334,14 @@ struct nfs_readargs {
 	__u32			count;
 	unsigned int		pgbase;
 	struct page **		pages;
+	struct nfs4_sequence_args	seq_args;
 };
 
 struct nfs_readres {
 	struct nfs_fattr *	fattr;
 	__u32			count;
 	int                     eof;
+	struct nfs4_sequence_res	seq_res;
 };
 
 /*
@@ -304,6 +356,7 @@ struct nfs_writeargs {
 	unsigned int		pgbase;
 	struct page **		pages;
 	const u32 *		bitmask;
+	struct nfs4_sequence_args	seq_args;
 };
 
 struct nfs_writeverf {
@@ -316,6 +369,7 @@ struct nfs_writeres {
 	struct nfs_writeverf *	verf;
 	__u32			count;
 	const struct nfs_server *server;
+	struct nfs4_sequence_res	seq_res;
 };
 
 /*
@@ -325,12 +379,14 @@ struct nfs_removeargs {
 	const struct nfs_fh	*fh;
 	struct qstr		name;
 	const u32 *		bitmask;
+	struct nfs4_sequence_args	seq_args;
 };
 
 struct nfs_removeres {
 	const struct nfs_server *server;
 	struct nfs4_change_info	cinfo;
 	struct nfs_fattr	dir_attr;
+	struct nfs4_sequence_res 	seq_res;
 };
 
 /*
@@ -383,6 +439,7 @@ struct nfs_setattrargs {
 	struct iattr *                  iap;
 	const struct nfs_server *	server; /* Needed for name mapping */
 	const u32 *			bitmask;
+	struct nfs4_sequence_args 	seq_args;
 };
 
 struct nfs_setaclargs {
@@ -390,6 +447,11 @@ struct nfs_setaclargs {
 	size_t				acl_len;
 	unsigned int			acl_pgbase;
 	struct page **			acl_pages;
+	struct nfs4_sequence_args	seq_args;
+};
+
+struct nfs_setaclres {
+	struct nfs4_sequence_res	seq_res;
 };
 
 struct nfs_getaclargs {
@@ -397,11 +459,18 @@ struct nfs_getaclargs {
 	size_t				acl_len;
 	unsigned int			acl_pgbase;
 	struct page **			acl_pages;
+	struct nfs4_sequence_args 	seq_args;
+};
+
+struct nfs_getaclres {
+	size_t				acl_len;
+	struct nfs4_sequence_res	seq_res;
 };
 
 struct nfs_setattrres {
 	struct nfs_fattr *              fattr;
 	const struct nfs_server *	server;
+	struct nfs4_sequence_res	seq_res;
 };
 
 struct nfs_linkargs {
@@ -583,6 +652,7 @@ struct nfs4_accessargs {
 	const struct nfs_fh *		fh;
 	const u32 *			bitmask;
 	u32				access;
+	struct nfs4_sequence_args	seq_args;
 };
 
 struct nfs4_accessres {
@@ -590,6 +660,7 @@ struct nfs4_accessres {
 	struct nfs_fattr *		fattr;
 	u32				supported;
 	u32				access;
+	struct nfs4_sequence_res	seq_res;
 };
 
 struct nfs4_create_arg {
@@ -609,6 +680,7 @@ struct nfs4_create_arg {
 	const struct iattr *		attrs;
 	const struct nfs_fh *		dir_fh;
 	const u32 *			bitmask;
+	struct nfs4_sequence_args 	seq_args;
 };
 
 struct nfs4_create_res {
@@ -617,21 +689,30 @@ struct nfs4_create_res {
 	struct nfs_fattr *		fattr;
 	struct nfs4_change_info		dir_cinfo;
 	struct nfs_fattr *		dir_fattr;
+	struct nfs4_sequence_res	seq_res;
 };
 
 struct nfs4_fsinfo_arg {
 	const struct nfs_fh *		fh;
 	const u32 *			bitmask;
+	struct nfs4_sequence_args	seq_args;
+};
+
+struct nfs4_fsinfo_res {
+	struct nfs_fsinfo	       *fsinfo;
+	struct nfs4_sequence_res	seq_res;
 };
 
 struct nfs4_getattr_arg {
 	const struct nfs_fh *		fh;
 	const u32 *			bitmask;
+	struct nfs4_sequence_args	seq_args;
 };
 
 struct nfs4_getattr_res {
 	const struct nfs_server *	server;
 	struct nfs_fattr *		fattr;
+	struct nfs4_sequence_res	seq_res;
 };
 
 struct nfs4_link_arg {
@@ -639,6 +720,7 @@ struct nfs4_link_arg {
 	const struct nfs_fh *		dir_fh;
 	const struct qstr *		name;
 	const u32 *			bitmask;
+	struct nfs4_sequence_args 	seq_args;
 };
 
 struct nfs4_link_res {
@@ -646,6 +728,7 @@ struct nfs4_link_res {
 	struct nfs_fattr *		fattr;
 	struct nfs4_change_info		cinfo;
 	struct nfs_fattr *		dir_attr;
+	struct nfs4_sequence_res	seq_res;
 };
 
 
@@ -653,21 +736,30 @@ struct nfs4_lookup_arg {
 	const struct nfs_fh *		dir_fh;
 	const struct qstr *		name;
 	const u32 *			bitmask;
+	struct nfs4_sequence_args	seq_args;
 };
 
 struct nfs4_lookup_res {
 	const struct nfs_server *	server;
 	struct nfs_fattr *		fattr;
 	struct nfs_fh *			fh;
+	struct nfs4_sequence_res	seq_res;
 };
 
 struct nfs4_lookup_root_arg {
 	const u32 *			bitmask;
+	struct nfs4_sequence_args	seq_args;
 };
 
 struct nfs4_pathconf_arg {
 	const struct nfs_fh *		fh;
 	const u32 *			bitmask;
+	struct nfs4_sequence_args	seq_args;
+};
+
+struct nfs4_pathconf_res {
+	struct nfs_pathconf	       *pathconf;
+	struct nfs4_sequence_res	seq_res;
 };
 
 struct nfs4_readdir_arg {
@@ -678,11 +770,13 @@ struct nfs4_readdir_arg {
 	struct page **			pages;	/* zero-copy data */
 	unsigned int			pgbase;	/* zero-copy data */
 	const u32 *			bitmask;
+	struct nfs4_sequence_args	seq_args;
 };
 
 struct nfs4_readdir_res {
 	nfs4_verifier			verifier;
 	unsigned int			pgbase;
+	struct nfs4_sequence_res	seq_res;
 };
 
 struct nfs4_readlink {
@@ -690,6 +784,11 @@ struct nfs4_readlink {
 	unsigned int			pgbase;
 	unsigned int			pglen;   /* zero-copy data */
 	struct page **			pages;   /* zero-copy data */
+	struct nfs4_sequence_args	seq_args;
+};
+
+struct nfs4_readlink_res {
+	struct nfs4_sequence_res	seq_res;
 };
 
 struct nfs4_rename_arg {
@@ -698,6 +797,7 @@ struct nfs4_rename_arg {
 	const struct qstr *		old_name;
 	const struct qstr *		new_name;
 	const u32 *			bitmask;
+	struct nfs4_sequence_args	seq_args;
 };
 
 struct nfs4_rename_res {
@@ -706,6 +806,7 @@ struct nfs4_rename_res {
 	struct nfs_fattr *		old_fattr;
 	struct nfs4_change_info		new_cinfo;
 	struct nfs_fattr *		new_fattr;
+	struct nfs4_sequence_res	seq_res;
 };
 
 #define NFS4_SETCLIENTID_NAMELEN	(127)
@@ -724,6 +825,17 @@ struct nfs4_setclientid {
 struct nfs4_statfs_arg {
 	const struct nfs_fh *		fh;
 	const u32 *			bitmask;
+	struct nfs4_sequence_args	seq_args;
+};
+
+struct nfs4_statfs_res {
+	struct nfs_fsstat	       *fsstat;
+	struct nfs4_sequence_res	seq_res;
+};
+
+struct nfs4_server_caps_arg {
+	struct nfs_fh		       *fhandle;
+	struct nfs4_sequence_args	seq_args;
 };
 
 struct nfs4_server_caps_res {
@@ -731,6 +843,7 @@ struct nfs4_server_caps_res {
 	u32				acl_bitmask;
 	u32				has_links;
 	u32				has_symlinks;
+	struct nfs4_sequence_res	seq_res;
 };
 
 struct nfs4_string {
@@ -765,10 +878,68 @@ struct nfs4_fs_locations_arg {
 	const struct qstr *name;
 	struct page *page;
 	const u32 *bitmask;
+	struct nfs4_sequence_args	seq_args;
+};
+
+struct nfs4_fs_locations_res {
+	struct nfs4_fs_locations       *fs_locations;
+	struct nfs4_sequence_res	seq_res;
 };
 
 #endif /* CONFIG_NFS_V4 */
 
+struct nfstime4 {
+	u64	seconds;
+	u32	nseconds;
+};
+
+#ifdef CONFIG_NFS_V4_1
+struct nfs_impl_id4 {
+	u32		domain_len;
+	char		*domain;
+	u32		name_len;
+	char		*name;
+	struct nfstime4	date;
+};
+
+#define NFS4_EXCHANGE_ID_LEN	(48)
+struct nfs41_exchange_id_args {
+	struct nfs_client		*client;
+	nfs4_verifier			*verifier;
+	unsigned int 			id_len;
+	char 				id[NFS4_EXCHANGE_ID_LEN];
+	u32				flags;
+};
+
+struct server_owner {
+	uint64_t			minor_id;
+	uint32_t			major_id_sz;
+	char				major_id[NFS4_OPAQUE_LIMIT];
+};
+
+struct server_scope {
+	uint32_t			server_scope_sz;
+	char 				server_scope[NFS4_OPAQUE_LIMIT];
+};
+
+struct nfs41_exchange_id_res {
+	struct nfs_client		*client;
+	u32				flags;
+};
+
+struct nfs41_create_session_args {
+	struct nfs_client	       *client;
+	uint32_t			flags;
+	uint32_t			cb_program;
+	struct nfs4_channel_attrs	fc_attrs;	/* Fore Channel */
+	struct nfs4_channel_attrs	bc_attrs;	/* Back Channel */
+};
+
+struct nfs41_create_session_res {
+	struct nfs_client	       *client;
+};
+#endif /* CONFIG_NFS_V4_1 */
+
 struct nfs_page;
 
 #define NFS_PAGEVEC_SIZE	(8U)

include/linux/nfsd/state.h

@@ -41,7 +41,6 @@
 #include <linux/kref.h>
 #include <linux/sunrpc/clnt.h>
 
-#define NFS4_OPAQUE_LIMIT 1024
 typedef struct {
 	u32             cl_boot;
 	u32             cl_id;

include/linux/sunrpc/bc_xprt.h

@@ -0,0 +1,49 @@
+/******************************************************************************
+
+(c) 2008 NetApp.  All Rights Reserved.
+
+NetApp provides this source code under the GPL v2 License.
+The GPL v2 license is available at
+http://opensource.org/licenses/gpl-license.php.
+
+THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
+"AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
+LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
+A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR
+CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL,
+EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO,
+PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR
+PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF
+LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING
+NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS
+SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+
+******************************************************************************/
+
+/*
+ * Functions to create and manage the backchannel
+ */
+
+#ifndef _LINUX_SUNRPC_BC_XPRT_H
+#define _LINUX_SUNRPC_BC_XPRT_H
+
+#include <linux/sunrpc/svcsock.h>
+#include <linux/sunrpc/xprt.h>
+#include <linux/sunrpc/sched.h>
+
+#ifdef CONFIG_NFS_V4_1
+struct rpc_rqst *xprt_alloc_bc_request(struct rpc_xprt *xprt);
+void xprt_free_bc_request(struct rpc_rqst *req);
+int xprt_setup_backchannel(struct rpc_xprt *, unsigned int min_reqs);
+void xprt_destroy_backchannel(struct rpc_xprt *, int max_reqs);
+void bc_release_request(struct rpc_task *);
+int bc_send(struct rpc_rqst *req);
+#else /* CONFIG_NFS_V4_1 */
+static inline int xprt_setup_backchannel(struct rpc_xprt *xprt,
+					 unsigned int min_reqs)
+{
+	return 0;
+}
+#endif /* CONFIG_NFS_V4_1 */
+#endif /* _LINUX_SUNRPC_BC_XPRT_H */
+

include/linux/sunrpc/clnt.h

@@ -143,6 +143,7 @@ int		rpc_call_sync(struct rpc_clnt *clnt,
 			      const struct rpc_message *msg, int flags);
 struct rpc_task *rpc_call_null(struct rpc_clnt *clnt, struct rpc_cred *cred,
 			       int flags);
+void		rpc_restart_call_prepare(struct rpc_task *);
 void		rpc_restart_call(struct rpc_task *);
 void		rpc_setbufsize(struct rpc_clnt *, unsigned int, unsigned int);
 size_t		rpc_max_payload(struct rpc_clnt *);

include/linux/sunrpc/sched.h

@@ -210,6 +210,8 @@ struct rpc_wait_queue {
  */
 struct rpc_task *rpc_new_task(const struct rpc_task_setup *);
 struct rpc_task *rpc_run_task(const struct rpc_task_setup *);
+struct rpc_task *rpc_run_bc_task(struct rpc_rqst *req,
+				const struct rpc_call_ops *ops);
 void		rpc_put_task(struct rpc_task *);
 void		rpc_exit_task(struct rpc_task *);
 void		rpc_release_calldata(const struct rpc_call_ops *, void *);
@@ -237,6 +239,7 @@ void		rpc_show_tasks(void);
 int		rpc_init_mempool(void);
 void		rpc_destroy_mempool(void);
 extern struct workqueue_struct *rpciod_workqueue;
+void		rpc_prepare_task(struct rpc_task *task);
 
 static inline void rpc_exit(struct rpc_task *task, int status)
 {

include/linux/sunrpc/svc.h

@@ -96,6 +96,15 @@ struct svc_serv {
 	svc_thread_fn		sv_function;	/* main function for threads */
 	unsigned int		sv_drc_max_pages; /* Total pages for DRC */
 	unsigned int		sv_drc_pages_used;/* DRC pages used */
+#if defined(CONFIG_NFS_V4_1)
+	struct list_head	sv_cb_list;	/* queue for callback requests
+						 * that arrive over the same
+						 * connection */
+	spinlock_t		sv_cb_lock;	/* protects the svc_cb_list */
+	wait_queue_head_t	sv_cb_waitq;	/* sleep here if there are no
+						 * entries in the svc_cb_list */
+	struct svc_xprt		*bc_xprt;
+#endif /* CONFIG_NFS_V4_1 */
 };
 
 /*
@@ -411,6 +420,8 @@ int		   svc_set_num_threads(struct svc_serv *, struct svc_pool *, int);
 int		   svc_pool_stats_open(struct svc_serv *serv, struct file *file);
 void		   svc_destroy(struct svc_serv *);
 int		   svc_process(struct svc_rqst *);
+int		   bc_svc_process(struct svc_serv *, struct rpc_rqst *,
+			struct svc_rqst *);
 int		   svc_register(const struct svc_serv *, const int,
 				const unsigned short, const unsigned short);
 

include/linux/sunrpc/svcsock.h

@@ -42,6 +42,8 @@ int		svc_sock_names(char *buf, struct svc_serv *serv, char *toclose);
 int		svc_addsock(struct svc_serv *serv, int fd, char *name_return);
 void		svc_init_xprt_sock(void);
 void		svc_cleanup_xprt_sock(void);
+struct svc_xprt *svc_sock_create(struct svc_serv *serv, int prot);
+void		svc_sock_destroy(struct svc_xprt *);
 
 /*
  * svc_makesock socket characteristics

include/linux/sunrpc/xprt.h

@@ -67,7 +67,8 @@ struct rpc_rqst {
 	struct rpc_task *	rq_task;	/* RPC task data */
 	__be32			rq_xid;		/* request XID */
 	int			rq_cong;	/* has incremented xprt->cong */
-	int			rq_received;	/* receive completed */
+	int			rq_reply_bytes_recvd;	/* number of reply */
+							/* bytes received */
 	u32			rq_seqno;	/* gss seq no. used on req. */
 	int			rq_enc_pages_num;
 	struct page		**rq_enc_pages;	/* scratch pages for use by
@@ -97,6 +98,12 @@ struct rpc_rqst {
 
 	unsigned long		rq_xtime;	/* when transmitted */
 	int			rq_ntrans;
+
+#if defined(CONFIG_NFS_V4_1)
+	struct list_head	rq_bc_list;	/* Callback service list */
+	unsigned long		rq_bc_pa_state;	/* Backchannel prealloc state */
+	struct list_head	rq_bc_pa_list;	/* Backchannel prealloc list */
+#endif /* CONFIG_NFS_V4_1 */
 };
 #define rq_svec			rq_snd_buf.head
 #define rq_slen			rq_snd_buf.len
@@ -174,6 +181,15 @@ struct rpc_xprt {
 	spinlock_t		reserve_lock;	/* lock slot table */
 	u32			xid;		/* Next XID value to use */
 	struct rpc_task *	snd_task;	/* Task blocked in send */
+#if defined(CONFIG_NFS_V4_1)
+	struct svc_serv		*bc_serv;       /* The RPC service which will */
+						/* process the callback */
+	unsigned int		bc_alloc_count;	/* Total number of preallocs */
+	spinlock_t		bc_pa_lock;	/* Protects the preallocated
+						 * items */
+	struct list_head	bc_pa_list;	/* List of preallocated
+						 * backchannel rpc_rqst's */
+#endif /* CONFIG_NFS_V4_1 */
 	struct list_head	recv;
 
 	struct {
@@ -192,6 +208,26 @@ struct rpc_xprt {
 	const char		*address_strings[RPC_DISPLAY_MAX];
 };
 
+#if defined(CONFIG_NFS_V4_1)
+/*
+ * Backchannel flags
+ */
+#define	RPC_BC_PA_IN_USE	0x0001		/* Preallocated backchannel */
+						/* buffer in use */
+#endif /* CONFIG_NFS_V4_1 */
+
+#if defined(CONFIG_NFS_V4_1)
+static inline int bc_prealloc(struct rpc_rqst *req)
+{
+	return test_bit(RPC_BC_PA_IN_USE, &req->rq_bc_pa_state);
+}
+#else
+static inline int bc_prealloc(struct rpc_rqst *req)
+{
+	return 0;
+}
+#endif /* CONFIG_NFS_V4_1 */
+
 struct xprt_create {
 	int			ident;		/* XPRT_TRANSPORT identifier */
 	struct sockaddr *	srcaddr;	/* optional local address */

net/sunrpc/Makefile

@@ -13,5 +13,6 @@ sunrpc-y := clnt.o xprt.o socklib.o xprtsock.o sched.o \
 	    rpcb_clnt.o timer.o xdr.o \
 	    sunrpc_syms.o cache.o rpc_pipe.o \
 	    svc_xprt.o
+sunrpc-$(CONFIG_NFS_V4_1) += backchannel_rqst.o bc_svc.o
 sunrpc-$(CONFIG_PROC_FS) += stats.o
 sunrpc-$(CONFIG_SYSCTL) += sysctl.o

net/sunrpc/backchannel_rqst.c

@@ -0,0 +1,281 @@
+/******************************************************************************
+
+(c) 2007 Network Appliance, Inc.  All Rights Reserved.
+(c) 2009 NetApp.  All Rights Reserved.
+
+NetApp provides this source code under the GPL v2 License.
+The GPL v2 license is available at
+http://opensource.org/licenses/gpl-license.php.
+
+THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
+"AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
+LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
+A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR
+CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL,
+EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO,
+PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR
+PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF
+LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING
+NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS
+SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+
+******************************************************************************/
+
+#include <linux/tcp.h>
+#include <linux/sunrpc/xprt.h>
+
+#ifdef RPC_DEBUG
+#define RPCDBG_FACILITY	RPCDBG_TRANS
+#endif
+
+#if defined(CONFIG_NFS_V4_1)
+
+/*
+ * Helper routines that track the number of preallocation elements
+ * on the transport.
+ */
+static inline int xprt_need_to_requeue(struct rpc_xprt *xprt)
+{
+	return xprt->bc_alloc_count > 0;
+}
+
+static inline void xprt_inc_alloc_count(struct rpc_xprt *xprt, unsigned int n)
+{
+	xprt->bc_alloc_count += n;
+}
+
+static inline int xprt_dec_alloc_count(struct rpc_xprt *xprt, unsigned int n)
+{
+	return xprt->bc_alloc_count -= n;
+}
+
+/*
+ * Free the preallocated rpc_rqst structure and the memory
+ * buffers hanging off of it.
+ */
+static void xprt_free_allocation(struct rpc_rqst *req)
+{
+	struct xdr_buf *xbufp;
+
+	dprintk("RPC:        free allocations for req= %p\n", req);
+	BUG_ON(test_bit(RPC_BC_PA_IN_USE, &req->rq_bc_pa_state));
+	xbufp = &req->rq_private_buf;
+	free_page((unsigned long)xbufp->head[0].iov_base);
+	xbufp = &req->rq_snd_buf;
+	free_page((unsigned long)xbufp->head[0].iov_base);
+	list_del(&req->rq_bc_pa_list);
+	kfree(req);
+}
+
+/*
+ * Preallocate up to min_reqs structures and related buffers for use
+ * by the backchannel.  This function can be called multiple times
+ * when creating new sessions that use the same rpc_xprt.  The
+ * preallocated buffers are added to the pool of resources used by
+ * the rpc_xprt.  Anyone of these resources may be used used by an
+ * incoming callback request.  It's up to the higher levels in the
+ * stack to enforce that the maximum number of session slots is not
+ * being exceeded.
+ *
+ * Some callback arguments can be large.  For example, a pNFS server
+ * using multiple deviceids.  The list can be unbound, but the client
+ * has the ability to tell the server the maximum size of the callback
+ * requests.  Each deviceID is 16 bytes, so allocate one page
+ * for the arguments to have enough room to receive a number of these
+ * deviceIDs.  The NFS client indicates to the pNFS server that its
+ * callback requests can be up to 4096 bytes in size.
+ */
+int xprt_setup_backchannel(struct rpc_xprt *xprt, unsigned int min_reqs)
+{
+	struct page *page_rcv = NULL, *page_snd = NULL;
+	struct xdr_buf *xbufp = NULL;
+	struct rpc_rqst *req, *tmp;
+	struct list_head tmp_list;
+	int i;
+
+	dprintk("RPC:       setup backchannel transport\n");
+
+	/*
+	 * We use a temporary list to keep track of the preallocated
+	 * buffers.  Once we're done building the list we splice it
+	 * into the backchannel preallocation list off of the rpc_xprt
+	 * struct.  This helps minimize the amount of time the list
+	 * lock is held on the rpc_xprt struct.  It also makes cleanup
+	 * easier in case of memory allocation errors.
+	 */
+	INIT_LIST_HEAD(&tmp_list);
+	for (i = 0; i < min_reqs; i++) {
+		/* Pre-allocate one backchannel rpc_rqst */
+		req = kzalloc(sizeof(struct rpc_rqst), GFP_KERNEL);
+		if (req == NULL) {
+			printk(KERN_ERR "Failed to create bc rpc_rqst\n");
+			goto out_free;
+		}
+
+		/* Add the allocated buffer to the tmp list */
+		dprintk("RPC:       adding req= %p\n", req);
+		list_add(&req->rq_bc_pa_list, &tmp_list);
+
+		req->rq_xprt = xprt;
+		INIT_LIST_HEAD(&req->rq_list);
+		INIT_LIST_HEAD(&req->rq_bc_list);
+
+		/* Preallocate one XDR receive buffer */
+		page_rcv = alloc_page(GFP_KERNEL);
+		if (page_rcv == NULL) {
+			printk(KERN_ERR "Failed to create bc receive xbuf\n");
+			goto out_free;
+		}
+		xbufp = &req->rq_rcv_buf;
+		xbufp->head[0].iov_base = page_address(page_rcv);
+		xbufp->head[0].iov_len = PAGE_SIZE;
+		xbufp->tail[0].iov_base = NULL;
+		xbufp->tail[0].iov_len = 0;
+		xbufp->page_len = 0;
+		xbufp->len = PAGE_SIZE;
+		xbufp->buflen = PAGE_SIZE;
+
+		/* Preallocate one XDR send buffer */
+		page_snd = alloc_page(GFP_KERNEL);
+		if (page_snd == NULL) {
+			printk(KERN_ERR "Failed to create bc snd xbuf\n");
+			goto out_free;
+		}
+
+		xbufp = &req->rq_snd_buf;
+		xbufp->head[0].iov_base = page_address(page_snd);
+		xbufp->head[0].iov_len = 0;
+		xbufp->tail[0].iov_base = NULL;
+		xbufp->tail[0].iov_len = 0;
+		xbufp->page_len = 0;
+		xbufp->len = 0;
+		xbufp->buflen = PAGE_SIZE;
+	}
+
+	/*
+	 * Add the temporary list to the backchannel preallocation list
+	 */
+	spin_lock_bh(&xprt->bc_pa_lock);
+	list_splice(&tmp_list, &xprt->bc_pa_list);
+	xprt_inc_alloc_count(xprt, min_reqs);
+	spin_unlock_bh(&xprt->bc_pa_lock);
+
+	dprintk("RPC:       setup backchannel transport done\n");
+	return 0;
+
+out_free:
+	/*
+	 * Memory allocation failed, free the temporary list
+	 */
+	list_for_each_entry_safe(req, tmp, &tmp_list, rq_bc_pa_list)
+		xprt_free_allocation(req);
+
+	dprintk("RPC:       setup backchannel transport failed\n");
+	return -1;
+}
+EXPORT_SYMBOL(xprt_setup_backchannel);
+
+/*
+ * Destroys the backchannel preallocated structures.
+ * Since these structures may have been allocated by multiple calls
+ * to xprt_setup_backchannel, we only destroy up to the maximum number
+ * of reqs specified by the caller.
+ * @xprt:	the transport holding the preallocated strucures
+ * @max_reqs	the maximum number of preallocated structures to destroy
+ */
+void xprt_destroy_backchannel(struct rpc_xprt *xprt, unsigned int max_reqs)
+{
+	struct rpc_rqst *req = NULL, *tmp = NULL;
+
+	dprintk("RPC:        destroy backchannel transport\n");
+
+	BUG_ON(max_reqs == 0);
+	spin_lock_bh(&xprt->bc_pa_lock);
+	xprt_dec_alloc_count(xprt, max_reqs);
+	list_for_each_entry_safe(req, tmp, &xprt->bc_pa_list, rq_bc_pa_list) {
+		dprintk("RPC:        req=%p\n", req);
+		xprt_free_allocation(req);
+		if (--max_reqs == 0)
+			break;
+	}
+	spin_unlock_bh(&xprt->bc_pa_lock);
+
+	dprintk("RPC:        backchannel list empty= %s\n",
+		list_empty(&xprt->bc_pa_list) ? "true" : "false");
+}
+EXPORT_SYMBOL(xprt_destroy_backchannel);
+
+/*
+ * One or more rpc_rqst structure have been preallocated during the
+ * backchannel setup.  Buffer space for the send and private XDR buffers
+ * has been preallocated as well.  Use xprt_alloc_bc_request to allocate
+ * to this request.  Use xprt_free_bc_request to return it.
+ *
+ * We know that we're called in soft interrupt context, grab the spin_lock
+ * since there is no need to grab the bottom half spin_lock.
+ *
+ * Return an available rpc_rqst, otherwise NULL if non are available.
+ */
+struct rpc_rqst *xprt_alloc_bc_request(struct rpc_xprt *xprt)
+{
+	struct rpc_rqst *req;
+
+	dprintk("RPC:       allocate a backchannel request\n");
+	spin_lock(&xprt->bc_pa_lock);
+	if (!list_empty(&xprt->bc_pa_list)) {
+		req = list_first_entry(&xprt->bc_pa_list, struct rpc_rqst,
+				rq_bc_pa_list);
+		list_del(&req->rq_bc_pa_list);
+	} else {
+		req = NULL;
+	}
+	spin_unlock(&xprt->bc_pa_lock);
+
+	if (req != NULL) {
+		set_bit(RPC_BC_PA_IN_USE, &req->rq_bc_pa_state);
+		req->rq_reply_bytes_recvd = 0;
+		req->rq_bytes_sent = 0;
+		memcpy(&req->rq_private_buf, &req->rq_rcv_buf,
+			sizeof(req->rq_private_buf));
+	}
+	dprintk("RPC:       backchannel req=%p\n", req);
+	return req;
+}
+
+/*
+ * Return the preallocated rpc_rqst structure and XDR buffers
+ * associated with this rpc_task.
+ */
+void xprt_free_bc_request(struct rpc_rqst *req)
+{
+	struct rpc_xprt *xprt = req->rq_xprt;
+
+	dprintk("RPC:       free backchannel req=%p\n", req);
+
+	smp_mb__before_clear_bit();
+	BUG_ON(!test_bit(RPC_BC_PA_IN_USE, &req->rq_bc_pa_state));
+	clear_bit(RPC_BC_PA_IN_USE, &req->rq_bc_pa_state);
+	smp_mb__after_clear_bit();
+
+	if (!xprt_need_to_requeue(xprt)) {
+		/*
+		 * The last remaining session was destroyed while this
+		 * entry was in use.  Free the entry and don't attempt
+		 * to add back to the list because there is no need to
+		 * have anymore preallocated entries.
+		 */
+		dprintk("RPC:       Last session removed req=%p\n", req);
+		xprt_free_allocation(req);
+		return;
+	}
+
+	/*
+	 * Return it to the list of preallocations so that it
+	 * may be reused by a new callback request.
+	 */
+	spin_lock_bh(&xprt->bc_pa_lock);
+	list_add(&req->rq_bc_pa_list, &xprt->bc_pa_list);
+	spin_unlock_bh(&xprt->bc_pa_lock);
+}
+
+#endif /* CONFIG_NFS_V4_1 */

net/sunrpc/bc_svc.c

@@ -0,0 +1,81 @@
+/******************************************************************************
+
+(c) 2007 Network Appliance, Inc.  All Rights Reserved.
+(c) 2009 NetApp.  All Rights Reserved.
+
+NetApp provides this source code under the GPL v2 License.
+The GPL v2 license is available at
+http://opensource.org/licenses/gpl-license.php.
+
+THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
+"AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
+LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
+A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR
+CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL,
+EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO,
+PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR
+PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF
+LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING
+NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS
+SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+
+******************************************************************************/
+
+/*
+ * The NFSv4.1 callback service helper routines.
+ * They implement the transport level processing required to send the
+ * reply over an existing open connection previously established by the client.
+ */
+
+#if defined(CONFIG_NFS_V4_1)
+
+#include <linux/module.h>
+
+#include <linux/sunrpc/xprt.h>
+#include <linux/sunrpc/sched.h>
+#include <linux/sunrpc/bc_xprt.h>
+
+#define RPCDBG_FACILITY	RPCDBG_SVCDSP
+
+void bc_release_request(struct rpc_task *task)
+{
+	struct rpc_rqst *req = task->tk_rqstp;
+
+	dprintk("RPC:       bc_release_request: task= %p\n", task);
+
+	/*
+	 * Release this request only if it's a backchannel
+	 * preallocated request
+	 */
+	if (!bc_prealloc(req))
+		return;
+	xprt_free_bc_request(req);
+}
+
+/* Empty callback ops */
+static const struct rpc_call_ops nfs41_callback_ops = {
+};
+
+
+/*
+ * Send the callback reply
+ */
+int bc_send(struct rpc_rqst *req)
+{
+	struct rpc_task *task;
+	int ret;
+
+	dprintk("RPC:       bc_send req= %p\n", req);
+	task = rpc_run_bc_task(req, &nfs41_callback_ops);
+	if (IS_ERR(task))
+		ret = PTR_ERR(task);
+	else {
+		BUG_ON(atomic_read(&task->tk_count) != 1);
+		ret = task->tk_status;
+		rpc_put_task(task);
+	}
+	return ret;
+	dprintk("RPC:       bc_send ret= %d \n", ret);
+}
+
+#endif /* CONFIG_NFS_V4_1 */

net/sunrpc/clnt.c

@@ -36,7 +36,9 @@
 #include <linux/sunrpc/clnt.h>
 #include <linux/sunrpc/rpc_pipe_fs.h>
 #include <linux/sunrpc/metrics.h>
+#include <linux/sunrpc/bc_xprt.h>
 
+#include "sunrpc.h"
 
 #ifdef RPC_DEBUG
 # define RPCDBG_FACILITY	RPCDBG_CALL
@@ -63,6 +65,9 @@ static void	call_decode(struct rpc_task *task);
 static void	call_bind(struct rpc_task *task);
 static void	call_bind_status(struct rpc_task *task);
 static void	call_transmit(struct rpc_task *task);
+#if defined(CONFIG_NFS_V4_1)
+static void	call_bc_transmit(struct rpc_task *task);
+#endif /* CONFIG_NFS_V4_1 */
 static void	call_status(struct rpc_task *task);
 static void	call_transmit_status(struct rpc_task *task);
 static void	call_refresh(struct rpc_task *task);
@@ -613,6 +618,50 @@ rpc_call_async(struct rpc_clnt *clnt, const struct rpc_message *msg, int flags,
 }
 EXPORT_SYMBOL_GPL(rpc_call_async);
 
+#if defined(CONFIG_NFS_V4_1)
+/**
+ * rpc_run_bc_task - Allocate a new RPC task for backchannel use, then run
+ * rpc_execute against it
+ * @ops: RPC call ops
+ */
+struct rpc_task *rpc_run_bc_task(struct rpc_rqst *req,
+					const struct rpc_call_ops *tk_ops)
+{
+	struct rpc_task *task;
+	struct xdr_buf *xbufp = &req->rq_snd_buf;
+	struct rpc_task_setup task_setup_data = {
+		.callback_ops = tk_ops,
+	};
+
+	dprintk("RPC: rpc_run_bc_task req= %p\n", req);
+	/*
+	 * Create an rpc_task to send the data
+	 */
+	task = rpc_new_task(&task_setup_data);
+	if (!task) {
+		xprt_free_bc_request(req);
+		goto out;
+	}
+	task->tk_rqstp = req;
+
+	/*
+	 * Set up the xdr_buf length.
+	 * This also indicates that the buffer is XDR encoded already.
+	 */
+	xbufp->len = xbufp->head[0].iov_len + xbufp->page_len +
+			xbufp->tail[0].iov_len;
+
+	task->tk_action = call_bc_transmit;
+	atomic_inc(&task->tk_count);
+	BUG_ON(atomic_read(&task->tk_count) != 2);
+	rpc_execute(task);
+
+out:
+	dprintk("RPC: rpc_run_bc_task: task= %p\n", task);
+	return task;
+}
+#endif /* CONFIG_NFS_V4_1 */
+
 void
 rpc_call_start(struct rpc_task *task)
 {
@@ -694,6 +743,19 @@ void rpc_force_rebind(struct rpc_clnt *clnt)
 }
 EXPORT_SYMBOL_GPL(rpc_force_rebind);
 
+/*
+ * Restart an (async) RPC call from the call_prepare state.
+ * Usually called from within the exit handler.
+ */
+void
+rpc_restart_call_prepare(struct rpc_task *task)
+{
+	if (RPC_ASSASSINATED(task))
+		return;
+	task->tk_action = rpc_prepare_task;
+}
+EXPORT_SYMBOL_GPL(rpc_restart_call_prepare);
+
 /*
  * Restart an (async) RPC call. Usually called from within the
  * exit handler.
@@ -1085,7 +1147,7 @@ call_transmit(struct rpc_task *task)
 	 * in order to allow access to the socket to other RPC requests.
 	 */
 	call_transmit_status(task);
-	if (task->tk_msg.rpc_proc->p_decode != NULL)
+	if (rpc_reply_expected(task))
 		return;
 	task->tk_action = rpc_exit_task;
 	rpc_wake_up_queued_task(&task->tk_xprt->pending, task);
@@ -1120,6 +1182,72 @@ call_transmit_status(struct rpc_task *task)
 	}
 }
 
+#if defined(CONFIG_NFS_V4_1)
+/*
+ * 5b.	Send the backchannel RPC reply.  On error, drop the reply.  In
+ * addition, disconnect on connectivity errors.
+ */
+static void
+call_bc_transmit(struct rpc_task *task)
+{
+	struct rpc_rqst *req = task->tk_rqstp;
+
+	BUG_ON(task->tk_status != 0);
+	task->tk_status = xprt_prepare_transmit(task);
+	if (task->tk_status == -EAGAIN) {
+		/*
+		 * Could not reserve the transport. Try again after the
+		 * transport is released.
+		 */
+		task->tk_status = 0;
+		task->tk_action = call_bc_transmit;
+		return;
+	}
+
+	task->tk_action = rpc_exit_task;
+	if (task->tk_status < 0) {
+		printk(KERN_NOTICE "RPC: Could not send backchannel reply "
+			"error: %d\n", task->tk_status);
+		return;
+	}
+
+	xprt_transmit(task);
+	xprt_end_transmit(task);
+	dprint_status(task);
+	switch (task->tk_status) {
+	case 0:
+		/* Success */
+		break;
+	case -EHOSTDOWN:
+	case -EHOSTUNREACH:
+	case -ENETUNREACH:
+	case -ETIMEDOUT:
+		/*
+		 * Problem reaching the server.  Disconnect and let the
+		 * forechannel reestablish the connection.  The server will
+		 * have to retransmit the backchannel request and we'll
+		 * reprocess it.  Since these ops are idempotent, there's no
+		 * need to cache our reply at this time.
+		 */
+		printk(KERN_NOTICE "RPC: Could not send backchannel reply "
+			"error: %d\n", task->tk_status);
+		xprt_conditional_disconnect(task->tk_xprt,
+			req->rq_connect_cookie);
+		break;
+	default:
+		/*
+		 * We were unable to reply and will have to drop the
+		 * request.  The server should reconnect and retransmit.
+		 */
+		BUG_ON(task->tk_status == -EAGAIN);
+		printk(KERN_NOTICE "RPC: Could not send backchannel reply "
+			"error: %d\n", task->tk_status);
+		break;
+	}
+	rpc_wake_up_queued_task(&req->rq_xprt->pending, task);
+}
+#endif /* CONFIG_NFS_V4_1 */
+
 /*
  * 6.	Sort out the RPC call status
  */
@@ -1130,8 +1258,8 @@ call_status(struct rpc_task *task)
 	struct rpc_rqst	*req = task->tk_rqstp;
 	int		status;
 
-	if (req->rq_received > 0 && !req->rq_bytes_sent)
-		task->tk_status = req->rq_received;
+	if (req->rq_reply_bytes_recvd > 0 && !req->rq_bytes_sent)
+		task->tk_status = req->rq_reply_bytes_recvd;
 
 	dprint_status(task);
 
@@ -1248,7 +1376,7 @@ call_decode(struct rpc_task *task)
 
 	/*
 	 * Ensure that we see all writes made by xprt_complete_rqst()
-	 * before it changed req->rq_received.
+	 * before it changed req->rq_reply_bytes_recvd.
 	 */
 	smp_rmb();
 	req->rq_rcv_buf.len = req->rq_private_buf.len;
@@ -1289,7 +1417,7 @@ out_retry:
 	task->tk_status = 0;
 	/* Note: rpc_verify_header() may have freed the RPC slot */
 	if (task->tk_rqstp == req) {
-		req->rq_received = req->rq_rcv_buf.len = 0;
+		req->rq_reply_bytes_recvd = req->rq_rcv_buf.len = 0;
 		if (task->tk_client->cl_discrtry)
 			xprt_conditional_disconnect(task->tk_xprt,
 					req->rq_connect_cookie);
@@ -1377,13 +1505,14 @@ rpc_verify_header(struct rpc_task *task)
 	}
 	if ((len -= 3) < 0)
 		goto out_overflow;
-	p += 1;	/* skip XID */
 
+	p += 1; /* skip XID */
 	if ((n = ntohl(*p++)) != RPC_REPLY) {
 		dprintk("RPC: %5u %s: not an RPC reply: %x\n",
-				task->tk_pid, __func__, n);
+			task->tk_pid, __func__, n);
 		goto out_garbage;
 	}
+
 	if ((n = ntohl(*p++)) != RPC_MSG_ACCEPTED) {
 		if (--len < 0)
 			goto out_overflow;

net/sunrpc/sched.c

@@ -569,7 +569,7 @@ EXPORT_SYMBOL_GPL(rpc_delay);
 /*
  * Helper to call task->tk_ops->rpc_call_prepare
  */
-static void rpc_prepare_task(struct rpc_task *task)
+void rpc_prepare_task(struct rpc_task *task)
 {
 	task->tk_ops->rpc_call_prepare(task, task->tk_calldata);
 }

net/sunrpc/stats.c

@@ -141,12 +141,14 @@ EXPORT_SYMBOL_GPL(rpc_free_iostats);
 void rpc_count_iostats(struct rpc_task *task)
 {
 	struct rpc_rqst *req = task->tk_rqstp;
-	struct rpc_iostats *stats = task->tk_client->cl_metrics;
+	struct rpc_iostats *stats;
 	struct rpc_iostats *op_metrics;
 	long rtt, execute, queue;
 
-	if (!stats || !req)
+	if (!task->tk_client || !task->tk_client->cl_metrics || !req)
 		return;
+
+	stats = task->tk_client->cl_metrics;
 	op_metrics = &stats[task->tk_msg.rpc_proc->p_statidx];
 
 	op_metrics->om_ops++;
@@ -154,7 +156,7 @@ void rpc_count_iostats(struct rpc_task *task)
 	op_metrics->om_timeouts += task->tk_timeouts;
 
 	op_metrics->om_bytes_sent += task->tk_bytes_sent;
-	op_metrics->om_bytes_recv += req->rq_received;
+	op_metrics->om_bytes_recv += req->rq_reply_bytes_recvd;
 
 	queue = (long)req->rq_xtime - task->tk_start;
 	if (queue < 0)

net/sunrpc/sunrpc.h

@@ -0,0 +1,37 @@
+/******************************************************************************
+
+(c) 2008 NetApp.  All Rights Reserved.
+
+NetApp provides this source code under the GPL v2 License.
+The GPL v2 license is available at
+http://opensource.org/licenses/gpl-license.php.
+
+THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
+"AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
+LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
+A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR
+CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL,
+EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO,
+PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR
+PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF
+LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING
+NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS
+SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+
+******************************************************************************/
+
+/*
+ * Functions and macros used internally by RPC
+ */
+
+#ifndef _NET_SUNRPC_SUNRPC_H
+#define _NET_SUNRPC_SUNRPC_H
+
+static inline int rpc_reply_expected(struct rpc_task *task)
+{
+	return (task->tk_msg.rpc_proc != NULL) &&
+		(task->tk_msg.rpc_proc->p_decode != NULL);
+}
+
+#endif /* _NET_SUNRPC_SUNRPC_H */
+

net/sunrpc/svc.c

@@ -25,6 +25,7 @@
 #include <linux/sunrpc/stats.h>
 #include <linux/sunrpc/svcsock.h>
 #include <linux/sunrpc/clnt.h>
+#include <linux/sunrpc/bc_xprt.h>
 
 #define RPCDBG_FACILITY	RPCDBG_SVCDSP
 
@@ -486,6 +487,10 @@ svc_destroy(struct svc_serv *serv)
 	if (svc_serv_is_pooled(serv))
 		svc_pool_map_put();
 
+#if defined(CONFIG_NFS_V4_1)
+	svc_sock_destroy(serv->bc_xprt);
+#endif /* CONFIG_NFS_V4_1 */
+
 	svc_unregister(serv);
 	kfree(serv->sv_pools);
 	kfree(serv);
@@ -970,20 +975,18 @@ svc_printk(struct svc_rqst *rqstp, const char *fmt, ...)
 }
 
 /*
- * Process the RPC request.
+ * Common routine for processing the RPC request.
  */
-int
-svc_process(struct svc_rqst *rqstp)
+static int
+svc_process_common(struct svc_rqst *rqstp, struct kvec *argv, struct kvec *resv)
 {
 	struct svc_program	*progp;
 	struct svc_version	*versp = NULL;	/* compiler food */
 	struct svc_procedure	*procp = NULL;
-	struct kvec *		argv = &rqstp->rq_arg.head[0];
-	struct kvec *		resv = &rqstp->rq_res.head[0];
 	struct svc_serv		*serv = rqstp->rq_server;
 	kxdrproc_t		xdr;
 	__be32			*statp;
-	u32			dir, prog, vers, proc;
+	u32			prog, vers, proc;
 	__be32			auth_stat, rpc_stat;
 	int			auth_res;
 	__be32			*reply_statp;
@@ -993,19 +996,6 @@ svc_process(struct svc_rqst *rqstp)
 	if (argv->iov_len < 6*4)
 		goto err_short_len;
 
-	/* setup response xdr_buf.
-	 * Initially it has just one page
-	 */
-	rqstp->rq_resused = 1;
-	resv->iov_base = page_address(rqstp->rq_respages[0]);
-	resv->iov_len = 0;
-	rqstp->rq_res.pages = rqstp->rq_respages + 1;
-	rqstp->rq_res.len = 0;
-	rqstp->rq_res.page_base = 0;
-	rqstp->rq_res.page_len = 0;
-	rqstp->rq_res.buflen = PAGE_SIZE;
-	rqstp->rq_res.tail[0].iov_base = NULL;
-	rqstp->rq_res.tail[0].iov_len = 0;
 	/* Will be turned off only in gss privacy case: */
 	rqstp->rq_splice_ok = 1;
 	/* Will be turned off only when NFSv4 Sessions are used */
@@ -1014,17 +1004,13 @@ svc_process(struct svc_rqst *rqstp)
 	/* Setup reply header */
 	rqstp->rq_xprt->xpt_ops->xpo_prep_reply_hdr(rqstp);
 
-	rqstp->rq_xid = svc_getu32(argv);
 	svc_putu32(resv, rqstp->rq_xid);
 
-	dir  = svc_getnl(argv);
 	vers = svc_getnl(argv);
 
 	/* First words of reply: */
 	svc_putnl(resv, 1);		/* REPLY */
 
-	if (dir != 0)		/* direction != CALL */
-		goto err_bad_dir;
 	if (vers != 2)		/* RPC version number */
 		goto err_bad_rpc;
 
@@ -1147,7 +1133,7 @@ svc_process(struct svc_rqst *rqstp)
  sendit:
 	if (svc_authorise(rqstp))
 		goto dropit;
-	return svc_send(rqstp);
+	return 1;		/* Caller can now send it */
 
  dropit:
 	svc_authorise(rqstp);	/* doesn't hurt to call this twice */
@@ -1161,12 +1147,6 @@ err_short_len:
 
 	goto dropit;			/* drop request */
 
-err_bad_dir:
-	svc_printk(rqstp, "bad direction %d, dropping request\n", dir);
-
-	serv->sv_stats->rpcbadfmt++;
-	goto dropit;			/* drop request */
-
 err_bad_rpc:
 	serv->sv_stats->rpcbadfmt++;
 	svc_putnl(resv, 1);	/* REJECT */
@@ -1219,6 +1199,100 @@ err_bad:
 }
 EXPORT_SYMBOL_GPL(svc_process);
 
+/*
+ * Process the RPC request.
+ */
+int
+svc_process(struct svc_rqst *rqstp)
+{
+	struct kvec		*argv = &rqstp->rq_arg.head[0];
+	struct kvec		*resv = &rqstp->rq_res.head[0];
+	struct svc_serv		*serv = rqstp->rq_server;
+	u32			dir;
+	int			error;
+
+	/*
+	 * Setup response xdr_buf.
+	 * Initially it has just one page
+	 */
+	rqstp->rq_resused = 1;
+	resv->iov_base = page_address(rqstp->rq_respages[0]);
+	resv->iov_len = 0;
+	rqstp->rq_res.pages = rqstp->rq_respages + 1;
+	rqstp->rq_res.len = 0;
+	rqstp->rq_res.page_base = 0;
+	rqstp->rq_res.page_len = 0;
+	rqstp->rq_res.buflen = PAGE_SIZE;
+	rqstp->rq_res.tail[0].iov_base = NULL;
+	rqstp->rq_res.tail[0].iov_len = 0;
+
+	rqstp->rq_xid = svc_getu32(argv);
+
+	dir  = svc_getnl(argv);
+	if (dir != 0) {
+		/* direction != CALL */
+		svc_printk(rqstp, "bad direction %d, dropping request\n", dir);
+		serv->sv_stats->rpcbadfmt++;
+		svc_drop(rqstp);
+		return 0;
+	}
+
+	error = svc_process_common(rqstp, argv, resv);
+	if (error <= 0)
+		return error;
+
+	return svc_send(rqstp);
+}
+
+#if defined(CONFIG_NFS_V4_1)
+/*
+ * Process a backchannel RPC request that arrived over an existing
+ * outbound connection
+ */
+int
+bc_svc_process(struct svc_serv *serv, struct rpc_rqst *req,
+	       struct svc_rqst *rqstp)
+{
+	struct kvec	*argv = &rqstp->rq_arg.head[0];
+	struct kvec	*resv = &rqstp->rq_res.head[0];
+	int 		error;
+
+	/* Build the svc_rqst used by the common processing routine */
+	rqstp->rq_xprt = serv->bc_xprt;
+	rqstp->rq_xid = req->rq_xid;
+	rqstp->rq_prot = req->rq_xprt->prot;
+	rqstp->rq_server = serv;
+
+	rqstp->rq_addrlen = sizeof(req->rq_xprt->addr);
+	memcpy(&rqstp->rq_addr, &req->rq_xprt->addr, rqstp->rq_addrlen);
+	memcpy(&rqstp->rq_arg, &req->rq_rcv_buf, sizeof(rqstp->rq_arg));
+	memcpy(&rqstp->rq_res, &req->rq_snd_buf, sizeof(rqstp->rq_res));
+
+	/* reset result send buffer "put" position */
+	resv->iov_len = 0;
+
+	if (rqstp->rq_prot != IPPROTO_TCP) {
+		printk(KERN_ERR "No support for Non-TCP transports!\n");
+		BUG();
+	}
+
+	/*
+	 * Skip the next two words because they've already been
+	 * processed in the trasport
+	 */
+	svc_getu32(argv);	/* XID */
+	svc_getnl(argv);	/* CALLDIR */
+
+	error = svc_process_common(rqstp, argv, resv);
+	if (error <= 0)
+		return error;
+
+	memcpy(&req->rq_snd_buf, &rqstp->rq_res, sizeof(req->rq_snd_buf));
+	return bc_send(req);
+}
+EXPORT_SYMBOL(bc_svc_process);
+#endif /* CONFIG_NFS_V4_1 */
+
 /*
  * Return (transport-specific) limit on the rpc payload.
  */

net/sunrpc/svcsock.c

@@ -1327,3 +1327,42 @@ static void svc_sock_free(struct svc_xprt *xprt)
 		sock_release(svsk->sk_sock);
 	kfree(svsk);
 }
+
+/*
+ * Create a svc_xprt.
+ *
+ * For internal use only (e.g. nfsv4.1 backchannel).
+ * Callers should typically use the xpo_create() method.
+ */
+struct svc_xprt *svc_sock_create(struct svc_serv *serv, int prot)
+{
+	struct svc_sock *svsk;
+	struct svc_xprt *xprt = NULL;
+
+	dprintk("svc: %s\n", __func__);
+	svsk = kzalloc(sizeof(*svsk), GFP_KERNEL);
+	if (!svsk)
+		goto out;
+
+	xprt = &svsk->sk_xprt;
+	if (prot == IPPROTO_TCP)
+		svc_xprt_init(&svc_tcp_class, xprt, serv);
+	else if (prot == IPPROTO_UDP)
+		svc_xprt_init(&svc_udp_class, xprt, serv);
+	else
+		BUG();
+out:
+	dprintk("svc: %s return %p\n", __func__, xprt);
+	return xprt;
+}
+EXPORT_SYMBOL_GPL(svc_sock_create);
+
+/*
+ * Destroy a svc_sock.
+ */
+void svc_sock_destroy(struct svc_xprt *xprt)
+{
+	if (xprt)
+		kfree(container_of(xprt, struct svc_sock, sk_xprt));
+}
+EXPORT_SYMBOL_GPL(svc_sock_destroy);

net/sunrpc/xprt.c

@@ -12,8 +12,9 @@
  *  -	Next, the caller puts together the RPC message, stuffs it into
  *	the request struct, and calls xprt_transmit().
  *  -	xprt_transmit sends the message and installs the caller on the
- *	transport's wait list. At the same time, it installs a timer that
- *	is run after the packet's timeout has expired.
+ *	transport's wait list. At the same time, if a reply is expected,
+ *	it installs a timer that is run after the packet's timeout has
+ *	expired.
  *  -	When a packet arrives, the data_ready handler walks the list of
  *	pending requests for that transport. If a matching XID is found, the
  *	caller is woken up, and the timer removed.
@@ -46,6 +47,8 @@
 #include <linux/sunrpc/clnt.h>
 #include <linux/sunrpc/metrics.h>
 
+#include "sunrpc.h"
+
 /*
  * Local variables
  */
@@ -192,8 +195,8 @@ EXPORT_SYMBOL_GPL(xprt_load_transport);
  */
 int xprt_reserve_xprt(struct rpc_task *task)
 {
-	struct rpc_xprt	*xprt = task->tk_xprt;
 	struct rpc_rqst *req = task->tk_rqstp;
+	struct rpc_xprt	*xprt = req->rq_xprt;
 
 	if (test_and_set_bit(XPRT_LOCKED, &xprt->state)) {
 		if (task == xprt->snd_task)
@@ -803,9 +806,10 @@ void xprt_complete_rqst(struct rpc_task *task, int copied)
 
 	list_del_init(&req->rq_list);
 	req->rq_private_buf.len = copied;
-	/* Ensure all writes are done before we update req->rq_received */
+	/* Ensure all writes are done before we update */
+	/* req->rq_reply_bytes_recvd */
 	smp_wmb();
-	req->rq_received = copied;
+	req->rq_reply_bytes_recvd = copied;
 	rpc_wake_up_queued_task(&xprt->pending, task);
 }
 EXPORT_SYMBOL_GPL(xprt_complete_rqst);
@@ -820,7 +824,7 @@ static void xprt_timer(struct rpc_task *task)
 	dprintk("RPC: %5u xprt_timer\n", task->tk_pid);
 
 	spin_lock_bh(&xprt->transport_lock);
-	if (!req->rq_received) {
+	if (!req->rq_reply_bytes_recvd) {
 		if (xprt->ops->timer)
 			xprt->ops->timer(task);
 	} else
@@ -842,8 +846,8 @@ int xprt_prepare_transmit(struct rpc_task *task)
 	dprintk("RPC: %5u xprt_prepare_transmit\n", task->tk_pid);
 
 	spin_lock_bh(&xprt->transport_lock);
-	if (req->rq_received && !req->rq_bytes_sent) {
-		err = req->rq_received;
+	if (req->rq_reply_bytes_recvd && !req->rq_bytes_sent) {
+		err = req->rq_reply_bytes_recvd;
 		goto out_unlock;
 	}
 	if (!xprt->ops->reserve_xprt(task))
@@ -855,7 +859,7 @@ out_unlock:
 
 void xprt_end_transmit(struct rpc_task *task)
 {
-	xprt_release_write(task->tk_xprt, task);
+	xprt_release_write(task->tk_rqstp->rq_xprt, task);
 }
 
 /**
@@ -872,8 +876,11 @@ void xprt_transmit(struct rpc_task *task)
 
 	dprintk("RPC: %5u xprt_transmit(%u)\n", task->tk_pid, req->rq_slen);
 
-	if (!req->rq_received) {
-		if (list_empty(&req->rq_list)) {
+	if (!req->rq_reply_bytes_recvd) {
+		if (list_empty(&req->rq_list) && rpc_reply_expected(task)) {
+			/*
+			 * Add to the list only if we're expecting a reply
+			 */
 			spin_lock_bh(&xprt->transport_lock);
 			/* Update the softirq receive buffer */
 			memcpy(&req->rq_private_buf, &req->rq_rcv_buf,
@@ -908,8 +915,13 @@ void xprt_transmit(struct rpc_task *task)
 	/* Don't race with disconnect */
 	if (!xprt_connected(xprt))
 		task->tk_status = -ENOTCONN;
-	else if (!req->rq_received)
+	else if (!req->rq_reply_bytes_recvd && rpc_reply_expected(task)) {
+		/*
+		 * Sleep on the pending queue since
+		 * we're expecting a reply.
+		 */
 		rpc_sleep_on(&xprt->pending, task, xprt_timer);
+	}
 	spin_unlock_bh(&xprt->transport_lock);
 }
 
@@ -982,11 +994,17 @@ static void xprt_request_init(struct rpc_task *task, struct rpc_xprt *xprt)
  */
 void xprt_release(struct rpc_task *task)
 {
-	struct rpc_xprt	*xprt = task->tk_xprt;
+	struct rpc_xprt	*xprt;
 	struct rpc_rqst	*req;
+	int is_bc_request;
 
 	if (!(req = task->tk_rqstp))
 		return;
+
+	/* Preallocated backchannel request? */
+	is_bc_request = bc_prealloc(req);
+
+	xprt = req->rq_xprt;
 	rpc_count_iostats(task);
 	spin_lock_bh(&xprt->transport_lock);
 	xprt->ops->release_xprt(xprt, task);
@@ -999,10 +1017,19 @@ void xprt_release(struct rpc_task *task)
 		mod_timer(&xprt->timer,
 				xprt->last_used + xprt->idle_timeout);
 	spin_unlock_bh(&xprt->transport_lock);
-	xprt->ops->buf_free(req->rq_buffer);
+	if (!bc_prealloc(req))
+		xprt->ops->buf_free(req->rq_buffer);
 	task->tk_rqstp = NULL;
 	if (req->rq_release_snd_buf)
 		req->rq_release_snd_buf(req);
+
+	/*
+	 * Early exit if this is a backchannel preallocated request.
+	 * There is no need to have it added to the RPC slot list.
+	 */
+	if (is_bc_request)
+		return;
+
 	memset(req, 0, sizeof(*req));	/* mark unused */
 
 	dprintk("RPC: %5u release request %p\n", task->tk_pid, req);
@@ -1049,6 +1076,11 @@ found:
 
 	INIT_LIST_HEAD(&xprt->free);
 	INIT_LIST_HEAD(&xprt->recv);
+#if defined(CONFIG_NFS_V4_1)
+	spin_lock_init(&xprt->bc_pa_lock);
+	INIT_LIST_HEAD(&xprt->bc_pa_list);
+#endif /* CONFIG_NFS_V4_1 */
+
 	INIT_WORK(&xprt->task_cleanup, xprt_autoclose);
 	setup_timer(&xprt->timer, xprt_init_autodisconnect,
 			(unsigned long)xprt);

net/sunrpc/xprtsock.c

@@ -34,6 +34,9 @@
 #include <linux/sunrpc/sched.h>
 #include <linux/sunrpc/xprtsock.h>
 #include <linux/file.h>
+#ifdef CONFIG_NFS_V4_1
+#include <linux/sunrpc/bc_xprt.h>
+#endif
 
 #include <net/sock.h>
 #include <net/checksum.h>
@@ -270,6 +273,13 @@ struct sock_xprt {
 #define TCP_RCV_COPY_FRAGHDR	(1UL << 1)
 #define TCP_RCV_COPY_XID	(1UL << 2)
 #define TCP_RCV_COPY_DATA	(1UL << 3)
+#define TCP_RCV_READ_CALLDIR	(1UL << 4)
+#define TCP_RCV_COPY_CALLDIR	(1UL << 5)
+
+/*
+ * TCP RPC flags
+ */
+#define TCP_RPC_REPLY		(1UL << 6)
 
 static inline struct sockaddr *xs_addr(struct rpc_xprt *xprt)
 {
@@ -956,7 +966,7 @@ static inline void xs_tcp_read_fraghdr(struct rpc_xprt *xprt, struct xdr_skb_rea
 	transport->tcp_offset = 0;
 
 	/* Sanity check of the record length */
-	if (unlikely(transport->tcp_reclen < 4)) {
+	if (unlikely(transport->tcp_reclen < 8)) {
 		dprintk("RPC:       invalid TCP record fragment length\n");
 		xprt_force_disconnect(xprt);
 		return;
@@ -991,33 +1001,77 @@ static inline void xs_tcp_read_xid(struct sock_xprt *transport, struct xdr_skb_r
 	if (used != len)
 		return;
 	transport->tcp_flags &= ~TCP_RCV_COPY_XID;
-	transport->tcp_flags |= TCP_RCV_COPY_DATA;
+	transport->tcp_flags |= TCP_RCV_READ_CALLDIR;
 	transport->tcp_copied = 4;
-	dprintk("RPC:       reading reply for XID %08x\n",
+	dprintk("RPC:       reading %s XID %08x\n",
+			(transport->tcp_flags & TCP_RPC_REPLY) ? "reply for"
+							      : "request with",
 			ntohl(transport->tcp_xid));
 	xs_tcp_check_fraghdr(transport);
 }
 
-static inline void xs_tcp_read_request(struct rpc_xprt *xprt, struct xdr_skb_reader *desc)
+static inline void xs_tcp_read_calldir(struct sock_xprt *transport,
+				       struct xdr_skb_reader *desc)
 {
-	struct sock_xprt *transport = container_of(xprt, struct sock_xprt, xprt);
-	struct rpc_rqst *req;
+	size_t len, used;
+	u32 offset;
+	__be32	calldir;
+
+	/*
+	 * We want transport->tcp_offset to be 8 at the end of this routine
+	 * (4 bytes for the xid and 4 bytes for the call/reply flag).
+	 * When this function is called for the first time,
+	 * transport->tcp_offset is 4 (after having already read the xid).
+	 */
+	offset = transport->tcp_offset - sizeof(transport->tcp_xid);
+	len = sizeof(calldir) - offset;
+	dprintk("RPC:       reading CALL/REPLY flag (%Zu bytes)\n", len);
+	used = xdr_skb_read_bits(desc, &calldir, len);
+	transport->tcp_offset += used;
+	if (used != len)
+		return;
+	transport->tcp_flags &= ~TCP_RCV_READ_CALLDIR;
+	transport->tcp_flags |= TCP_RCV_COPY_CALLDIR;
+	transport->tcp_flags |= TCP_RCV_COPY_DATA;
+	/*
+	 * We don't yet have the XDR buffer, so we will write the calldir
+	 * out after we get the buffer from the 'struct rpc_rqst'
+	 */
+	if (ntohl(calldir) == RPC_REPLY)
+		transport->tcp_flags |= TCP_RPC_REPLY;
+	else
+		transport->tcp_flags &= ~TCP_RPC_REPLY;
+	dprintk("RPC:       reading %s CALL/REPLY flag %08x\n",
+			(transport->tcp_flags & TCP_RPC_REPLY) ?
+				"reply for" : "request with", calldir);
+	xs_tcp_check_fraghdr(transport);
+}
+
+static inline void xs_tcp_read_common(struct rpc_xprt *xprt,
+				     struct xdr_skb_reader *desc,
+				     struct rpc_rqst *req)
+{
+	struct sock_xprt *transport =
+				container_of(xprt, struct sock_xprt, xprt);
 	struct xdr_buf *rcvbuf;
 	size_t len;
 	ssize_t r;
 
-	/* Find and lock the request corresponding to this xid */
-	spin_lock(&xprt->transport_lock);
-	req = xprt_lookup_rqst(xprt, transport->tcp_xid);
-	if (!req) {
-		transport->tcp_flags &= ~TCP_RCV_COPY_DATA;
-		dprintk("RPC:       XID %08x request not found!\n",
-				ntohl(transport->tcp_xid));
-		spin_unlock(&xprt->transport_lock);
-		return;
+	rcvbuf = &req->rq_private_buf;
+
+	if (transport->tcp_flags & TCP_RCV_COPY_CALLDIR) {
+		/*
+		 * Save the RPC direction in the XDR buffer
+		 */
+		__be32	calldir = transport->tcp_flags & TCP_RPC_REPLY ?
+					htonl(RPC_REPLY) : 0;
+
+		memcpy(rcvbuf->head[0].iov_base + transport->tcp_copied,
+			&calldir, sizeof(calldir));
+		transport->tcp_copied += sizeof(calldir);
+		transport->tcp_flags &= ~TCP_RCV_COPY_CALLDIR;
 	}
 
-	rcvbuf = &req->rq_private_buf;
 	len = desc->count;
 	if (len > transport->tcp_reclen - transport->tcp_offset) {
 		struct xdr_skb_reader my_desc;
@@ -1054,7 +1108,7 @@ static inline void xs_tcp_read_request(struct rpc_xprt *xprt, struct xdr_skb_rea
 				"tcp_offset = %u, tcp_reclen = %u\n",
 				xprt, transport->tcp_copied,
 				transport->tcp_offset, transport->tcp_reclen);
-		goto out;
+		return;
 	}
 
 	dprintk("RPC:       XID %08x read %Zd bytes\n",
@@ -1070,11 +1124,125 @@ static inline void xs_tcp_read_request(struct rpc_xprt *xprt, struct xdr_skb_rea
 			transport->tcp_flags &= ~TCP_RCV_COPY_DATA;
 	}
 
-out:
+	return;
+}
+
+/*
+ * Finds the request corresponding to the RPC xid and invokes the common
+ * tcp read code to read the data.
+ */
+static inline int xs_tcp_read_reply(struct rpc_xprt *xprt,
+				    struct xdr_skb_reader *desc)
+{
+	struct sock_xprt *transport =
+				container_of(xprt, struct sock_xprt, xprt);
+	struct rpc_rqst *req;
+
+	dprintk("RPC:       read reply XID %08x\n", ntohl(transport->tcp_xid));
+
+	/* Find and lock the request corresponding to this xid */
+	spin_lock(&xprt->transport_lock);
+	req = xprt_lookup_rqst(xprt, transport->tcp_xid);
+	if (!req) {
+		dprintk("RPC:       XID %08x request not found!\n",
+				ntohl(transport->tcp_xid));
+		spin_unlock(&xprt->transport_lock);
+		return -1;
+	}
+
+	xs_tcp_read_common(xprt, desc, req);
+
 	if (!(transport->tcp_flags & TCP_RCV_COPY_DATA))
 		xprt_complete_rqst(req->rq_task, transport->tcp_copied);
+
 	spin_unlock(&xprt->transport_lock);
-	xs_tcp_check_fraghdr(transport);
+	return 0;
+}
+
+#if defined(CONFIG_NFS_V4_1)
+/*
+ * Obtains an rpc_rqst previously allocated and invokes the common
+ * tcp read code to read the data.  The result is placed in the callback
+ * queue.
+ * If we're unable to obtain the rpc_rqst we schedule the closing of the
+ * connection and return -1.
+ */
+static inline int xs_tcp_read_callback(struct rpc_xprt *xprt,
+				       struct xdr_skb_reader *desc)
+{
+	struct sock_xprt *transport =
+				container_of(xprt, struct sock_xprt, xprt);
+	struct rpc_rqst *req;
+
+	req = xprt_alloc_bc_request(xprt);
+	if (req == NULL) {
+		printk(KERN_WARNING "Callback slot table overflowed\n");
+		xprt_force_disconnect(xprt);
+		return -1;
+	}
+
+	req->rq_xid = transport->tcp_xid;
+	dprintk("RPC:       read callback  XID %08x\n", ntohl(req->rq_xid));
+	xs_tcp_read_common(xprt, desc, req);
+
+	if (!(transport->tcp_flags & TCP_RCV_COPY_DATA)) {
+		struct svc_serv *bc_serv = xprt->bc_serv;
+
+		/*
+		 * Add callback request to callback list.  The callback
+		 * service sleeps on the sv_cb_waitq waiting for new
+		 * requests.  Wake it up after adding enqueing the
+		 * request.
+		 */
+		dprintk("RPC:       add callback request to list\n");
+		spin_lock(&bc_serv->sv_cb_lock);
+		list_add(&req->rq_bc_list, &bc_serv->sv_cb_list);
+		spin_unlock(&bc_serv->sv_cb_lock);
+		wake_up(&bc_serv->sv_cb_waitq);
+	}
+
+	req->rq_private_buf.len = transport->tcp_copied;
+
+	return 0;
+}
+
+static inline int _xs_tcp_read_data(struct rpc_xprt *xprt,
+					struct xdr_skb_reader *desc)
+{
+	struct sock_xprt *transport =
+				container_of(xprt, struct sock_xprt, xprt);
+
+	return (transport->tcp_flags & TCP_RPC_REPLY) ?
+		xs_tcp_read_reply(xprt, desc) :
+		xs_tcp_read_callback(xprt, desc);
+}
+#else
+static inline int _xs_tcp_read_data(struct rpc_xprt *xprt,
+					struct xdr_skb_reader *desc)
+{
+	return xs_tcp_read_reply(xprt, desc);
+}
+#endif /* CONFIG_NFS_V4_1 */
+
+/*
+ * Read data off the transport.  This can be either an RPC_CALL or an
+ * RPC_REPLY.  Relay the processing to helper functions.
+ */
+static void xs_tcp_read_data(struct rpc_xprt *xprt,
+				    struct xdr_skb_reader *desc)
+{
+	struct sock_xprt *transport =
+				container_of(xprt, struct sock_xprt, xprt);
+
+	if (_xs_tcp_read_data(xprt, desc) == 0)
+		xs_tcp_check_fraghdr(transport);
+	else {
+		/*
+		 * The transport_lock protects the request handling.
+		 * There's no need to hold it to update the tcp_flags.
+		 */
+		transport->tcp_flags &= ~TCP_RCV_COPY_DATA;
+	}
 }
 
 static inline void xs_tcp_read_discard(struct sock_xprt *transport, struct xdr_skb_reader *desc)
@@ -1114,9 +1282,14 @@ static int xs_tcp_data_recv(read_descriptor_t *rd_desc, struct sk_buff *skb, uns
 			xs_tcp_read_xid(transport, &desc);
 			continue;
 		}
+		/* Read in the call/reply flag */
+		if (transport->tcp_flags & TCP_RCV_READ_CALLDIR) {
+			xs_tcp_read_calldir(transport, &desc);
+			continue;
+		}
 		/* Read in the request data */
 		if (transport->tcp_flags & TCP_RCV_COPY_DATA) {
-			xs_tcp_read_request(xprt, &desc);
+			xs_tcp_read_data(xprt, &desc);
 			continue;
 		}
 		/* Skip over any trailing bytes on short reads */
@@ -1792,6 +1965,7 @@ static void xs_tcp_setup_socket(struct rpc_xprt *xprt,
 		 */
 		set_bit(XPRT_CONNECTION_CLOSE, &xprt->state);
 		xprt_force_disconnect(xprt);
+		break;
 	case -ECONNREFUSED:
 	case -ECONNRESET:
 	case -ENETUNREACH:
@@ -2010,6 +2184,9 @@ static struct rpc_xprt_ops xs_tcp_ops = {
 	.buf_free		= rpc_free,
 	.send_request		= xs_tcp_send_request,
 	.set_retrans_timeout	= xprt_set_retrans_timeout_def,
+#if defined(CONFIG_NFS_V4_1)
+	.release_request	= bc_release_request,
+#endif /* CONFIG_NFS_V4_1 */
 	.close			= xs_tcp_close,
 	.destroy		= xs_destroy,
 	.print_stats		= xs_tcp_print_stats,