Merge branch 'master' of master.kernel.org:/pub/scm/linux/kernel/git/torvalds/linux-2.6 into common/serial-rework

Conflicts:
	arch/sh/kernel/cpu/sh2/setup-sh7619.c
	arch/sh/kernel/cpu/sh2a/setup-mxg.c
	arch/sh/kernel/cpu/sh2a/setup-sh7201.c
	arch/sh/kernel/cpu/sh2a/setup-sh7203.c
	arch/sh/kernel/cpu/sh2a/setup-sh7206.c
	arch/sh/kernel/cpu/sh3/setup-sh7705.c
	arch/sh/kernel/cpu/sh3/setup-sh770x.c
	arch/sh/kernel/cpu/sh3/setup-sh7710.c
	arch/sh/kernel/cpu/sh3/setup-sh7720.c
	arch/sh/kernel/cpu/sh4/setup-sh4-202.c
	arch/sh/kernel/cpu/sh4/setup-sh7750.c
	arch/sh/kernel/cpu/sh4/setup-sh7760.c
	arch/sh/kernel/cpu/sh4a/setup-sh7343.c
	arch/sh/kernel/cpu/sh4a/setup-sh7366.c
	arch/sh/kernel/cpu/sh4a/setup-sh7722.c
	arch/sh/kernel/cpu/sh4a/setup-sh7723.c
	arch/sh/kernel/cpu/sh4a/setup-sh7724.c
	arch/sh/kernel/cpu/sh4a/setup-sh7763.c
	arch/sh/kernel/cpu/sh4a/setup-sh7770.c
	arch/sh/kernel/cpu/sh4a/setup-sh7780.c
	arch/sh/kernel/cpu/sh4a/setup-sh7785.c
	arch/sh/kernel/cpu/sh4a/setup-sh7786.c
	arch/sh/kernel/cpu/sh4a/setup-shx3.c
	arch/sh/kernel/cpu/sh5/setup-sh5.c
	drivers/serial/sh-sci.c
	drivers/serial/sh-sci.h
	include/linux/serial_sci.h

49 files changed, 14782 insertions, 6516 deletions

diff --git a/fs/nfs/Kconfig b/fs/nfs/Kconfig
index 2a77bc25d5af..ba306658a6db 100644
--- a/fs/nfs/Kconfig
+++ b/fs/nfs/Kconfig
@@ -61,9 +61,9 @@ config NFS_V3_ACL
           If unsure, say N.
 
 config NFS_V4
-        bool "NFS client support for NFS version 4 (EXPERIMENTAL)"
-        depends on NFS_FS && EXPERIMENTAL
-        select RPCSEC_GSS_KRB5
+        bool "NFS client support for NFS version 4"
+        depends on NFS_FS
+        select SUNRPC_GSS
         help
           This option enables support for version 4 of the NFS protocol
           (RFC 3530) in the kernel's NFS client.
@@ -72,16 +72,20 @@ config NFS_V4
           space programs which can be found in the Linux nfs-utils package,
           available from http://linux-nfs.org/.
 
-          If unsure, say N.
+          If unsure, say Y.
 
 config NFS_V4_1
-        bool "NFS client support for NFSv4.1 (DEVELOPER ONLY)"
-        depends on NFS_V4 && EXPERIMENTAL
+        bool "NFS client support for NFSv4.1 (EXPERIMENTAL)"
+        depends on NFS_FS && NFS_V4 && EXPERIMENTAL
+        select PNFS_FILE_LAYOUT
         help
           This option enables support for minor version 1 of the NFSv4 protocol
-          (draft-ietf-nfsv4-minorversion1) in the kernel's NFS client.
+          (RFC 5661) in the kernel's NFS client.
+
+          If unsure, say N.
 
-          Unless you're an NFS developer, say N.
+config PNFS_FILE_LAYOUT
+        tristate
 
 config ROOT_NFS
         bool "Root file system on NFS"
@@ -90,14 +94,41 @@ config ROOT_NFS
           If you want your system to mount its root file system via NFS,
           choose Y here.  This is common practice for managing systems
           without local permanent storage.  For details, read
-          <file:Documentation/filesystems/nfsroot.txt>.
+          <file:Documentation/filesystems/nfs/nfsroot.txt>.
 
           Most people say N here.
 
 config NFS_FSCACHE
-        bool "Provide NFS client caching support (EXPERIMENTAL)"
-        depends on EXPERIMENTAL
+        bool "Provide NFS client caching support"
         depends on NFS_FS=m && FSCACHE || NFS_FS=y && FSCACHE=y
         help
           Say Y here if you want NFS data to be cached locally on disc through
           the general filesystem cache manager
+
+config NFS_USE_LEGACY_DNS
+        bool "Use the legacy NFS DNS resolver"
+        depends on NFS_V4
+        help
+          The kernel now provides a method for translating a host name into an
+          IP address.  Select Y here if you would rather use your own DNS
+          resolver script.
+
+          If unsure, say N
+
+config NFS_USE_KERNEL_DNS
+        bool
+        depends on NFS_V4 && !NFS_USE_LEGACY_DNS
+        select DNS_RESOLVER
+        select KEYS
+        default y
+
+config NFS_USE_NEW_IDMAPPER
+        bool "Use the new idmapper upcall routine"
+        depends on NFS_V4 && KEYS
+        help
+          Say Y here if you want NFS to use the new idmapper upcall functions.
+          You will need /sbin/request-key (usually provided by the keyutils
+          package).  For details, read
+          <file:Documentation/filesystems/nfs/idmapper.txt>.
+
+          If you are unsure, say N.
diff --git a/fs/nfs/Makefile b/fs/nfs/Makefile
index 845159814de2..4776ff9e3814 100644
--- a/fs/nfs/Makefile
+++ b/fs/nfs/Makefile
@@ -6,7 +6,8 @@ obj-$(CONFIG_NFS_FS) += nfs.o
 
 nfs-y                   := client.o dir.o file.o getroot.o inode.o super.o nfs2xdr.o \
                            direct.o pagelist.o proc.o read.o symlink.o unlink.o \
-                           write.o namespace.o mount_clnt.o
+                           write.o namespace.o mount_clnt.o \
+                           dns_resolve.o cache_lib.o
 nfs-$(CONFIG_ROOT_NFS)  += nfsroot.o
 nfs-$(CONFIG_NFS_V3)    += nfs3proc.o nfs3xdr.o
 nfs-$(CONFIG_NFS_V3_ACL)        += nfs3acl.o
@@ -14,5 +15,9 @@ nfs-$(CONFIG_NFS_V4)	+= nfs4proc.o nfs4xdr.o nfs4state.o nfs4renewd.o \
                            delegation.o idmap.o \
                            callback.o callback_xdr.o callback_proc.o \
                            nfs4namespace.o
+nfs-$(CONFIG_NFS_V4_1)  += pnfs.o
 nfs-$(CONFIG_SYSCTL) += sysctl.o
 nfs-$(CONFIG_NFS_FSCACHE) += fscache.o fscache-index.o
+
+obj-$(CONFIG_PNFS_FILE_LAYOUT) += nfs_layout_nfsv41_files.o
+nfs_layout_nfsv41_files-y := nfs4filelayout.o nfs4filelayoutdev.o
diff --git a/fs/nfs/cache_lib.c b/fs/nfs/cache_lib.c
new file mode 100644
index 000000000000..84690319e625
--- /dev/null
+++ b/fs/nfs/cache_lib.c
@@ -0,0 +1,141 @@
+/*
+ * linux/fs/nfs/cache_lib.c
+ *
+ * Helper routines for the NFS client caches
+ *
+ * Copyright (c) 2009 Trond Myklebust <Trond.Myklebust@netapp.com>
+ */
+#include <linux/kmod.h>
+#include <linux/module.h>
+#include <linux/moduleparam.h>
+#include <linux/mount.h>
+#include <linux/namei.h>
+#include <linux/slab.h>
+#include <linux/sunrpc/cache.h>
+#include <linux/sunrpc/rpc_pipe_fs.h>
+
+#include "cache_lib.h"
+
+#define NFS_CACHE_UPCALL_PATHLEN 256
+#define NFS_CACHE_UPCALL_TIMEOUT 15
+
+static char nfs_cache_getent_prog[NFS_CACHE_UPCALL_PATHLEN] =
+                                "/sbin/nfs_cache_getent";
+static unsigned long nfs_cache_getent_timeout = NFS_CACHE_UPCALL_TIMEOUT;
+
+module_param_string(cache_getent, nfs_cache_getent_prog,
+                sizeof(nfs_cache_getent_prog), 0600);
+MODULE_PARM_DESC(cache_getent, "Path to the client cache upcall program");
+module_param_named(cache_getent_timeout, nfs_cache_getent_timeout, ulong, 0600);
+MODULE_PARM_DESC(cache_getent_timeout, "Timeout (in seconds) after which "
+                "the cache upcall is assumed to have failed");
+
+int nfs_cache_upcall(struct cache_detail *cd, char *entry_name)
+{
+        static char *envp[] = { "HOME=/",
+                "TERM=linux",
+                "PATH=/sbin:/usr/sbin:/bin:/usr/bin",
+                NULL
+        };
+        char *argv[] = {
+                nfs_cache_getent_prog,
+                cd->name,
+                entry_name,
+                NULL
+        };
+        int ret = -EACCES;
+
+        if (nfs_cache_getent_prog[0] == '\0')
+                goto out;
+        ret = call_usermodehelper(argv[0], argv, envp, UMH_WAIT_EXEC);
+        /*
+         * Disable the upcall mechanism if we're getting an ENOENT or
+         * EACCES error. The admin can re-enable it on the fly by using
+         * sysfs to set the 'cache_getent' parameter once the problem
+         * has been fixed.
+         */
+        if (ret == -ENOENT || ret == -EACCES)
+                nfs_cache_getent_prog[0] = '\0';
+out:
+        return ret > 0 ? 0 : ret;
+}
+
+/*
+ * Deferred request handling
+ */
+void nfs_cache_defer_req_put(struct nfs_cache_defer_req *dreq)
+{
+        if (atomic_dec_and_test(&dreq->count))
+                kfree(dreq);
+}
+
+static void nfs_dns_cache_revisit(struct cache_deferred_req *d, int toomany)
+{
+        struct nfs_cache_defer_req *dreq;
+
+        dreq = container_of(d, struct nfs_cache_defer_req, deferred_req);
+
+        complete_all(&dreq->completion);
+        nfs_cache_defer_req_put(dreq);
+}
+
+static struct cache_deferred_req *nfs_dns_cache_defer(struct cache_req *req)
+{
+        struct nfs_cache_defer_req *dreq;
+
+        dreq = container_of(req, struct nfs_cache_defer_req, req);
+        dreq->deferred_req.revisit = nfs_dns_cache_revisit;
+        atomic_inc(&dreq->count);
+
+        return &dreq->deferred_req;
+}
+
+struct nfs_cache_defer_req *nfs_cache_defer_req_alloc(void)
+{
+        struct nfs_cache_defer_req *dreq;
+
+        dreq = kzalloc(sizeof(*dreq), GFP_KERNEL);
+        if (dreq) {
+                init_completion(&dreq->completion);
+                atomic_set(&dreq->count, 1);
+                dreq->req.defer = nfs_dns_cache_defer;
+        }
+        return dreq;
+}
+
+int nfs_cache_wait_for_upcall(struct nfs_cache_defer_req *dreq)
+{
+        if (wait_for_completion_timeout(&dreq->completion,
+                        nfs_cache_getent_timeout * HZ) == 0)
+                return -ETIMEDOUT;
+        return 0;
+}
+
+int nfs_cache_register(struct cache_detail *cd)
+{
+        struct nameidata nd;
+        struct vfsmount *mnt;
+        int ret;
+
+        mnt = rpc_get_mount();
+        if (IS_ERR(mnt))
+                return PTR_ERR(mnt);
+        ret = vfs_path_lookup(mnt->mnt_root, mnt, "/cache", 0, &nd);
+        if (ret)
+                goto err;
+        ret = sunrpc_cache_register_pipefs(nd.path.dentry,
+                        cd->name, 0600, cd);
+        path_put(&nd.path);
+        if (!ret)
+                return ret;
+err:
+        rpc_put_mount();
+        return ret;
+}
+
+void nfs_cache_unregister(struct cache_detail *cd)
+{
+        sunrpc_cache_unregister_pipefs(cd);
+        rpc_put_mount();
+}
+
diff --git a/fs/nfs/cache_lib.h b/fs/nfs/cache_lib.h
new file mode 100644
index 000000000000..76f856e284e4
--- /dev/null
+++ b/fs/nfs/cache_lib.h
@@ -0,0 +1,27 @@
+/*
+ * Helper routines for the NFS client caches
+ *
+ * Copyright (c) 2009 Trond Myklebust <Trond.Myklebust@netapp.com>
+ */
+
+#include <linux/completion.h>
+#include <linux/sunrpc/cache.h>
+#include <asm/atomic.h>
+
+/*
+ * Deferred request handling
+ */
+struct nfs_cache_defer_req {
+        struct cache_req req;
+        struct cache_deferred_req deferred_req;
+        struct completion completion;
+        atomic_t count;
+};
+
+extern int nfs_cache_upcall(struct cache_detail *cd, char *entry_name);
+extern struct nfs_cache_defer_req *nfs_cache_defer_req_alloc(void);
+extern void nfs_cache_defer_req_put(struct nfs_cache_defer_req *dreq);
+extern int nfs_cache_wait_for_upcall(struct nfs_cache_defer_req *dreq);
+
+extern int nfs_cache_register(struct cache_detail *cd);
+extern void nfs_cache_unregister(struct cache_detail *cd);
diff --git a/fs/nfs/callback.c b/fs/nfs/callback.c
index 7f604c7941fb..199016528fcb 100644
--- a/fs/nfs/callback.c
+++ b/fs/nfs/callback.c
@@ -9,7 +9,6 @@
 #include <linux/completion.h>
 #include <linux/ip.h>
 #include <linux/module.h>
-#include <linux/smp_lock.h>
 #include <linux/sunrpc/svc.h>
 #include <linux/sunrpc/svcsock.h>
 #include <linux/nfs_fs.h>
@@ -17,9 +16,7 @@
 #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>
 
@@ -43,21 +40,28 @@ static struct svc_program nfs4_callback_program;
 unsigned int nfs_callback_set_tcpport;
 unsigned short nfs_callback_tcpport;
 unsigned short nfs_callback_tcpport6;
-static const int nfs_set_port_min = 0;
-static const int nfs_set_port_max = 65535;
+#define NFS_CALLBACK_MAXPORTNR (65535U)
 
-static int param_set_port(const char *val, struct kernel_param *kp)
+static int param_set_portnr(const char *val, const struct kernel_param *kp)
 {
-        char *endp;
-        int num = simple_strtol(val, &endp, 0);
-        if (endp == val || *endp || num < nfs_set_port_min || num > nfs_set_port_max)
+        unsigned long num;
+        int ret;
+
+        if (!val)
+                return -EINVAL;
+        ret = strict_strtoul(val, 0, &num);
+        if (ret == -EINVAL || num > NFS_CALLBACK_MAXPORTNR)
                 return -EINVAL;
-        *((int *)kp->arg) = num;
+        *((unsigned int *)kp->arg) = num;
         return 0;
 }
+static struct kernel_param_ops param_ops_portnr = {
+        .set = param_set_portnr,
+        .get = param_get_uint,
+};
+#define param_check_portnr(name, p) __param_check(name, p, unsigned int);
 
-module_param_call(callback_tcpport, param_set_port, param_get_int,
-                 &nfs_callback_set_tcpport, 0644);
+module_param_named(callback_tcpport, nfs_callback_set_tcpport, portnr, 0644);
 
 /*
  * This is the NFSv4 callback kernel thread.
@@ -70,11 +74,6 @@ nfs4_callback_svc(void *vrqstp)
 
         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()) {
                 /*
                  * Listen for a request on the socket
@@ -96,7 +95,6 @@ nfs4_callback_svc(void *vrqstp)
                 preverr = err;
                 svc_process(rqstp);
         }
-        unlock_kernel();
         return 0;
 }
 
@@ -108,7 +106,7 @@ nfs4_callback_up(struct svc_serv *serv)
 {
         int ret;
 
-        ret = svc_create_xprt(serv, "tcp", PF_INET,
+        ret = svc_create_xprt(serv, "tcp", &init_net, PF_INET,
                                 nfs_callback_set_tcpport, SVC_SOCK_ANONYMOUS);
         if (ret <= 0)
                 goto out_err;
@@ -116,8 +114,7 @@ nfs4_callback_up(struct svc_serv *serv)
         dprintk("NFS: Callback listener port = %u (af %u)\n",
                         nfs_callback_tcpport, PF_INET);
 
-#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
-        ret = svc_create_xprt(serv, "tcp", PF_INET6,
+        ret = svc_create_xprt(serv, "tcp", &init_net, PF_INET6,
                                 nfs_callback_set_tcpport, SVC_SOCK_ANONYMOUS);
         if (ret > 0) {
                 nfs_callback_tcpport6 = ret;
@@ -127,7 +124,6 @@ nfs4_callback_up(struct svc_serv *serv)
                 ret = 0;
         else
                 goto out_err;
-#endif  /* defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE) */
 
         return svc_prepare_thread(serv, &serv->sv_pools[0]);
 
@@ -139,6 +135,33 @@ out_err:
 
 #if defined(CONFIG_NFS_V4_1)
 /*
+ *  * CB_SEQUENCE operations will fail until the callback sessionid is set.
+ *   */
+int nfs4_set_callback_sessionid(struct nfs_client *clp)
+{
+        struct svc_serv *serv = clp->cl_rpcclient->cl_xprt->bc_serv;
+        struct nfs4_sessionid *bc_sid;
+
+        if (!serv->sv_bc_xprt)
+                return -EINVAL;
+
+        /* on success freed in xprt_free */
+        bc_sid = kmalloc(sizeof(struct nfs4_sessionid), GFP_KERNEL);
+        if (!bc_sid)
+                return -ENOMEM;
+        memcpy(bc_sid->data, &clp->cl_session->sess_id.data,
+                NFS4_MAX_SESSIONID_LEN);
+        spin_lock_bh(&serv->sv_cb_lock);
+        serv->sv_bc_xprt->xpt_bc_sid = bc_sid;
+        spin_unlock_bh(&serv->sv_cb_lock);
+        dprintk("%s set xpt_bc_sid=%u:%u:%u:%u for sv_bc_xprt %p\n", __func__,
+                ((u32 *)bc_sid->data)[0], ((u32 *)bc_sid->data)[1],
+                ((u32 *)bc_sid->data)[2], ((u32 *)bc_sid->data)[3],
+                serv->sv_bc_xprt);
+        return 0;
+}
+
+/*
  * The callback service for NFSv4.1 callbacks
  */
 static int
@@ -152,11 +175,6 @@ nfs41_callback_svc(void *vrqstp)
 
         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);
@@ -175,7 +193,6 @@ nfs41_callback_svc(void *vrqstp)
                 }
                 finish_wait(&serv->sv_cb_waitq, &wq);
         }
-        unlock_kernel();
         return 0;
 }
 
@@ -185,30 +202,38 @@ nfs41_callback_svc(void *vrqstp)
 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);
+        struct svc_rqst *rqstp;
+        int ret;
 
-        dprintk("--> %s\n", __func__);
-        /* Create a svc_sock for the service */
-        bc_xprt = svc_sock_create(serv, xprt->prot);
-        if (!bc_xprt)
+        /*
+         * Create an svc_sock for the back channel service that shares the
+         * fore channel connection.
+         * Returns the input port (0) and sets the svc_serv bc_xprt on success
+         */
+        ret = svc_create_xprt(serv, "tcp-bc", &init_net, PF_INET, 0,
+                              SVC_SOCK_ANONYMOUS);
+        if (ret < 0) {
+                rqstp = ERR_PTR(ret);
                 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);
+        if (IS_ERR(rqstp)) {
+                svc_xprt_put(serv->sv_bc_xprt);
+                serv->sv_bc_xprt = NULL;
+        }
 out:
-        dprintk("--> %s return %p\n", __func__, rqstp);
+        dprintk("--> %s return %ld\n", __func__,
+                IS_ERR(rqstp) ? PTR_ERR(rqstp) : 0);
         return rqstp;
 }
 
@@ -241,6 +266,10 @@ static inline void nfs_callback_bc_serv(u32 minorversion, struct rpc_xprt *xprt,
                 struct nfs_callback_data *cb_info)
 {
 }
+int nfs4_set_callback_sessionid(struct nfs_client *clp)
+{
+        return 0;
+}
 #endif /* CONFIG_NFS_V4_1 */
 
 /*
@@ -336,6 +365,9 @@ static int check_gss_callback_principal(struct nfs_client *clp,
         struct rpc_clnt *r = clp->cl_rpcclient;
         char *p = svc_gss_principal(rqstp);
 
+        /* No RPC_AUTH_GSS on NFSv4.1 back channel yet */
+        if (clp->cl_minorversion != 0)
+                return SVC_DROP;
         /*
          * It might just be a normal user principal, in which case
          * userspace won't bother to tell us the name at all.
@@ -353,6 +385,23 @@ static int check_gss_callback_principal(struct nfs_client *clp,
         return SVC_OK;
 }
 
+/* pg_authenticate method helper */
+static struct nfs_client *nfs_cb_find_client(struct svc_rqst *rqstp)
+{
+        struct nfs4_sessionid *sessionid = bc_xprt_sid(rqstp);
+        int is_cb_compound = rqstp->rq_proc == CB_COMPOUND ? 1 : 0;
+
+        dprintk("--> %s rq_proc %d\n", __func__, rqstp->rq_proc);
+        if (svc_is_backchannel(rqstp))
+                /* Sessionid (usually) set after CB_NULL ping */
+                return nfs4_find_client_sessionid(svc_addr(rqstp), sessionid,
+                                                  is_cb_compound);
+        else
+                /* No callback identifier in pg_authenticate */
+                return nfs4_find_client_no_ident(svc_addr(rqstp));
+}
+
+/* pg_authenticate method for nfsv4 callback threads. */
 static int nfs_callback_authenticate(struct svc_rqst *rqstp)
 {
         struct nfs_client *clp;
@@ -360,7 +409,7 @@ static int nfs_callback_authenticate(struct svc_rqst *rqstp)
         int ret = SVC_OK;
 
         /* Don't talk to strangers */
-        clp = nfs_find_client(svc_addr(rqstp), 4);
+        clp = nfs_cb_find_client(rqstp);
         if (clp == NULL)
                 return SVC_DROP;
 
@@ -389,6 +438,7 @@ static int nfs_callback_authenticate(struct svc_rqst *rqstp)
  */
 static struct svc_version *nfs4_callback_version[] = {
         [1] = &nfs4_callback_version1,
+        [4] = &nfs4_callback_version4,
 };
 
 static struct svc_stat nfs4_callback_stats;
diff --git a/fs/nfs/callback.h b/fs/nfs/callback.h
index 07baa8254ca1..d3b44f9bd747 100644
--- a/fs/nfs/callback.h
+++ b/fs/nfs/callback.h
@@ -34,10 +34,17 @@ enum nfs4_callback_opnum {
         OP_CB_ILLEGAL = 10044,
 };
 
+struct cb_process_state {
+        __be32                  drc_status;
+        struct nfs_client       *clp;
+        struct nfs4_sessionid   *svc_sid; /* v4.1 callback service sessionid */
+};
+
 struct cb_compound_hdr_arg {
         unsigned int taglen;
         const char *tag;
         unsigned int minorversion;
+        unsigned int cb_ident; /* v4.0 callback identifier */
         unsigned nops;
 };
 
@@ -103,19 +110,77 @@ struct cb_sequenceres {
         uint32_t                        csr_target_highestslotid;
 };
 
-extern unsigned nfs4_callback_sequence(struct cb_sequenceargs *args,
-                                       struct cb_sequenceres *res);
+extern __be32 nfs4_callback_sequence(struct cb_sequenceargs *args,
+                                       struct cb_sequenceres *res,
+                                       struct cb_process_state *cps);
+
+extern int nfs41_validate_delegation_stateid(struct nfs_delegation *delegation,
+                                             const nfs4_stateid *stateid);
+
+#define RCA4_TYPE_MASK_RDATA_DLG        0
+#define RCA4_TYPE_MASK_WDATA_DLG        1
+#define RCA4_TYPE_MASK_DIR_DLG         2
+#define RCA4_TYPE_MASK_FILE_LAYOUT     3
+#define RCA4_TYPE_MASK_BLK_LAYOUT      4
+#define RCA4_TYPE_MASK_OBJ_LAYOUT_MIN  8
+#define RCA4_TYPE_MASK_OBJ_LAYOUT_MAX  9
+#define RCA4_TYPE_MASK_OTHER_LAYOUT_MIN 12
+#define RCA4_TYPE_MASK_OTHER_LAYOUT_MAX 15
+#define RCA4_TYPE_MASK_ALL 0xf31f
+
+struct cb_recallanyargs {
+        struct sockaddr *craa_addr;
+        uint32_t        craa_objs_to_keep;
+        uint32_t        craa_type_mask;
+};
 
-#endif /* CONFIG_NFS_V4_1 */
+extern __be32 nfs4_callback_recallany(struct cb_recallanyargs *args,
+                                        void *dummy,
+                                        struct cb_process_state *cps);
+
+struct cb_recallslotargs {
+        struct sockaddr *crsa_addr;
+        uint32_t        crsa_target_max_slots;
+};
+extern __be32 nfs4_callback_recallslot(struct cb_recallslotargs *args,
+                                         void *dummy,
+                                         struct cb_process_state *cps);
+
+struct cb_layoutrecallargs {
+        struct sockaddr         *cbl_addr;
+        uint32_t                cbl_recall_type;
+        uint32_t                cbl_layout_type;
+        uint32_t                cbl_layoutchanged;
+        union {
+                struct {
+                        struct nfs_fh           cbl_fh;
+                        struct pnfs_layout_range cbl_range;
+                        nfs4_stateid            cbl_stateid;
+                };
+                struct nfs_fsid         cbl_fsid;
+        };
+};
 
-extern __be32 nfs4_callback_getattr(struct cb_getattrargs *args, struct cb_getattrres *res);
-extern __be32 nfs4_callback_recall(struct cb_recallargs *args, void *dummy);
+extern unsigned nfs4_callback_layoutrecall(
+        struct cb_layoutrecallargs *args,
+        void *dummy, struct cb_process_state *cps);
 
+extern void nfs4_check_drain_bc_complete(struct nfs4_session *ses);
+extern void nfs4_cb_take_slot(struct nfs_client *clp);
+#endif /* CONFIG_NFS_V4_1 */
+
+extern __be32 nfs4_callback_getattr(struct cb_getattrargs *args,
+                                    struct cb_getattrres *res,
+                                    struct cb_process_state *cps);
+extern __be32 nfs4_callback_recall(struct cb_recallargs *args, void *dummy,
+                                   struct cb_process_state *cps);
 #ifdef CONFIG_NFS_V4
 extern int nfs_callback_up(u32 minorversion, struct rpc_xprt *xprt);
 extern void nfs_callback_down(int minorversion);
+extern int nfs4_validate_delegation_stateid(struct nfs_delegation *delegation,
+                                            const nfs4_stateid *stateid);
+extern int nfs4_set_callback_sessionid(struct nfs_client *clp);
 #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
diff --git a/fs/nfs/callback_proc.c b/fs/nfs/callback_proc.c
index b7da1f54da68..4bb91cb2620d 100644
--- a/fs/nfs/callback_proc.c
+++ b/fs/nfs/callback_proc.c
@@ -7,37 +7,41 @@
  */
 #include <linux/nfs4.h>
 #include <linux/nfs_fs.h>
+#include <linux/slab.h>
 #include "nfs4_fs.h"
 #include "callback.h"
 #include "delegation.h"
 #include "internal.h"
+#include "pnfs.h"
 
 #ifdef NFS_DEBUG
 #define NFSDBG_FACILITY NFSDBG_CALLBACK
 #endif
- 
-__be32 nfs4_callback_getattr(struct cb_getattrargs *args, struct cb_getattrres *res)
+
+__be32 nfs4_callback_getattr(struct cb_getattrargs *args,
+                             struct cb_getattrres *res,
+                             struct cb_process_state *cps)
 {
-        struct nfs_client *clp;
         struct nfs_delegation *delegation;
         struct nfs_inode *nfsi;
         struct inode *inode;
 
+        res->status = htonl(NFS4ERR_OP_NOT_IN_SESSION);
+        if (!cps->clp) /* Always set for v4.0. Set in cb_sequence for v4.1 */
+                goto out;
+
         res->bitmap[0] = res->bitmap[1] = 0;
         res->status = htonl(NFS4ERR_BADHANDLE);
-        clp = nfs_find_client(args->addr, 4);
-        if (clp == NULL)
-                goto out;
 
         dprintk("NFS: GETATTR callback request from %s\n",
-                rpc_peeraddr2str(clp->cl_rpcclient, RPC_DISPLAY_ADDR));
+                rpc_peeraddr2str(cps->clp->cl_rpcclient, RPC_DISPLAY_ADDR));
 
-        inode = nfs_delegation_find_inode(clp, &args->fh);
+        inode = nfs_delegation_find_inode(cps->clp, &args->fh);
         if (inode == NULL)
-                goto out_putclient;
+                goto out;
         nfsi = NFS_I(inode);
-        down_read(&nfsi->rwsem);
-        delegation = nfsi->delegation;
+        rcu_read_lock();
+        delegation = rcu_dereference(nfsi->delegation);
         if (delegation == NULL || (delegation->type & FMODE_WRITE) == 0)
                 goto out_iput;
         res->size = i_size_read(inode);
@@ -52,101 +56,254 @@ __be32 nfs4_callback_getattr(struct cb_getattrargs *args, struct cb_getattrres *
                 args->bitmap[1];
         res->status = 0;
 out_iput:
-        up_read(&nfsi->rwsem);
+        rcu_read_unlock();
         iput(inode);
-out_putclient:
-        nfs_put_client(clp);
 out:
         dprintk("%s: exit with status = %d\n", __func__, ntohl(res->status));
         return res->status;
 }
 
-__be32 nfs4_callback_recall(struct cb_recallargs *args, void *dummy)
+__be32 nfs4_callback_recall(struct cb_recallargs *args, void *dummy,
+                            struct cb_process_state *cps)
 {
-        struct nfs_client *clp;
         struct inode *inode;
         __be32 res;
         
-        res = htonl(NFS4ERR_BADHANDLE);
-        clp = nfs_find_client(args->addr, 4);
-        if (clp == NULL)
+        res = htonl(NFS4ERR_OP_NOT_IN_SESSION);
+        if (!cps->clp) /* Always set for v4.0. Set in cb_sequence for v4.1 */
                 goto out;
 
         dprintk("NFS: RECALL callback request from %s\n",
-                rpc_peeraddr2str(clp->cl_rpcclient, RPC_DISPLAY_ADDR));
-
-        do {
-                struct nfs_client *prev = clp;
-
-                inode = nfs_delegation_find_inode(clp, &args->fh);
-                if (inode != NULL) {
-                        /* Set up a helper thread to actually return the delegation */
-                        switch(nfs_async_inode_return_delegation(inode, &args->stateid)) {
-                                case 0:
-                                        res = 0;
-                                        break;
-                                case -ENOENT:
-                                        if (res != 0)
-                                                res = htonl(NFS4ERR_BAD_STATEID);
-                                        break;
-                                default:
-                                        res = htonl(NFS4ERR_RESOURCE);
-                        }
-                        iput(inode);
-                }
-                clp = nfs_find_client_next(prev);
-                nfs_put_client(prev);
-        } while (clp != NULL);
+                rpc_peeraddr2str(cps->clp->cl_rpcclient, RPC_DISPLAY_ADDR));
+
+        res = htonl(NFS4ERR_BADHANDLE);
+        inode = nfs_delegation_find_inode(cps->clp, &args->fh);
+        if (inode == NULL)
+                goto out;
+        /* Set up a helper thread to actually return the delegation */
+        switch (nfs_async_inode_return_delegation(inode, &args->stateid)) {
+        case 0:
+                res = 0;
+                break;
+        case -ENOENT:
+                if (res != 0)
+                        res = htonl(NFS4ERR_BAD_STATEID);
+                break;
+        default:
+                res = htonl(NFS4ERR_RESOURCE);
+        }
+        iput(inode);
 out:
         dprintk("%s: exit with status = %d\n", __func__, ntohl(res));
         return res;
 }
 
+int nfs4_validate_delegation_stateid(struct nfs_delegation *delegation, const nfs4_stateid *stateid)
+{
+        if (delegation == NULL || memcmp(delegation->stateid.data, stateid->data,
+                                         sizeof(delegation->stateid.data)) != 0)
+                return 0;
+        return 1;
+}
+
 #if defined(CONFIG_NFS_V4_1)
 
+static u32 initiate_file_draining(struct nfs_client *clp,
+                                  struct cb_layoutrecallargs *args)
+{
+        struct pnfs_layout_hdr *lo;
+        struct inode *ino;
+        bool found = false;
+        u32 rv = NFS4ERR_NOMATCHING_LAYOUT;
+        LIST_HEAD(free_me_list);
+
+        spin_lock(&clp->cl_lock);
+        list_for_each_entry(lo, &clp->cl_layouts, plh_layouts) {
+                if (nfs_compare_fh(&args->cbl_fh,
+                                   &NFS_I(lo->plh_inode)->fh))
+                        continue;
+                ino = igrab(lo->plh_inode);
+                if (!ino)
+                        continue;
+                found = true;
+                /* Without this, layout can be freed as soon
+                 * as we release cl_lock.
+                 */
+                get_layout_hdr(lo);
+                break;
+        }
+        spin_unlock(&clp->cl_lock);
+        if (!found)
+                return NFS4ERR_NOMATCHING_LAYOUT;
+
+        spin_lock(&ino->i_lock);
+        if (test_bit(NFS_LAYOUT_BULK_RECALL, &lo->plh_flags) ||
+            mark_matching_lsegs_invalid(lo, &free_me_list,
+                                        args->cbl_range.iomode))
+                rv = NFS4ERR_DELAY;
+        else
+                rv = NFS4ERR_NOMATCHING_LAYOUT;
+        pnfs_set_layout_stateid(lo, &args->cbl_stateid, true);
+        spin_unlock(&ino->i_lock);
+        pnfs_free_lseg_list(&free_me_list);
+        put_layout_hdr(lo);
+        iput(ino);
+        return rv;
+}
+
+static u32 initiate_bulk_draining(struct nfs_client *clp,
+                                  struct cb_layoutrecallargs *args)
+{
+        struct pnfs_layout_hdr *lo;
+        struct inode *ino;
+        u32 rv = NFS4ERR_NOMATCHING_LAYOUT;
+        struct pnfs_layout_hdr *tmp;
+        LIST_HEAD(recall_list);
+        LIST_HEAD(free_me_list);
+        struct pnfs_layout_range range = {
+                .iomode = IOMODE_ANY,
+                .offset = 0,
+                .length = NFS4_MAX_UINT64,
+        };
+
+        spin_lock(&clp->cl_lock);
+        list_for_each_entry(lo, &clp->cl_layouts, plh_layouts) {
+                if ((args->cbl_recall_type == RETURN_FSID) &&
+                    memcmp(&NFS_SERVER(lo->plh_inode)->fsid,
+                           &args->cbl_fsid, sizeof(struct nfs_fsid)))
+                        continue;
+                if (!igrab(lo->plh_inode))
+                        continue;
+                get_layout_hdr(lo);
+                BUG_ON(!list_empty(&lo->plh_bulk_recall));
+                list_add(&lo->plh_bulk_recall, &recall_list);
+        }
+        spin_unlock(&clp->cl_lock);
+        list_for_each_entry_safe(lo, tmp,
+                                 &recall_list, plh_bulk_recall) {
+                ino = lo->plh_inode;
+                spin_lock(&ino->i_lock);
+                set_bit(NFS_LAYOUT_BULK_RECALL, &lo->plh_flags);
+                if (mark_matching_lsegs_invalid(lo, &free_me_list, range.iomode))
+                        rv = NFS4ERR_DELAY;
+                list_del_init(&lo->plh_bulk_recall);
+                spin_unlock(&ino->i_lock);
+                put_layout_hdr(lo);
+                iput(ino);
+        }
+        pnfs_free_lseg_list(&free_me_list);
+        return rv;
+}
+
+static u32 do_callback_layoutrecall(struct nfs_client *clp,
+                                    struct cb_layoutrecallargs *args)
+{
+        u32 res = NFS4ERR_DELAY;
+
+        dprintk("%s enter, type=%i\n", __func__, args->cbl_recall_type);
+        if (test_and_set_bit(NFS4CLNT_LAYOUTRECALL, &clp->cl_state))
+                goto out;
+        if (args->cbl_recall_type == RETURN_FILE)
+                res = initiate_file_draining(clp, args);
+        else
+                res = initiate_bulk_draining(clp, args);
+        clear_bit(NFS4CLNT_LAYOUTRECALL, &clp->cl_state);
+out:
+        dprintk("%s returning %i\n", __func__, res);
+        return res;
+
+}
+
+__be32 nfs4_callback_layoutrecall(struct cb_layoutrecallargs *args,
+                                  void *dummy, struct cb_process_state *cps)
+{
+        u32 res;
+
+        dprintk("%s: -->\n", __func__);
+
+        if (cps->clp)
+                res = do_callback_layoutrecall(cps->clp, args);
+        else
+                res = NFS4ERR_OP_NOT_IN_SESSION;
+
+        dprintk("%s: exit with status = %d\n", __func__, res);
+        return cpu_to_be32(res);
+}
+
+static void pnfs_recall_all_layouts(struct nfs_client *clp)
+{
+        struct cb_layoutrecallargs args;
+
+        /* Pretend we got a CB_LAYOUTRECALL(ALL) */
+        memset(&args, 0, sizeof(args));
+        args.cbl_recall_type = RETURN_ALL;
+        /* FIXME we ignore errors, what should we do? */
+        do_callback_layoutrecall(clp, &args);
+}
+
+int nfs41_validate_delegation_stateid(struct nfs_delegation *delegation, const nfs4_stateid *stateid)
+{
+        if (delegation == NULL)
+                return 0;
+
+        if (stateid->stateid.seqid != 0)
+                return 0;
+        if (memcmp(&delegation->stateid.stateid.other,
+                   &stateid->stateid.other,
+                   NFS4_STATEID_OTHER_SIZE))
+                return 0;
+
+        return 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,
+ * We don't yet implement a duplicate request cache, instead we set the
+ * back channel ca_maxresponsesize_cached to zero. This is OK for now
  * 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)
+static __be32
+validate_seqid(struct nfs4_slot_table *tbl, struct cb_sequenceargs * args)
 {
         struct nfs4_slot *slot;
 
         dprintk("%s enter. slotid %d seqid %d\n",
-                __func__, slotid, seqid);
+                __func__, args->csa_slotid, args->csa_sequenceid);
 
-        if (slotid > NFS41_BC_MAX_CALLBACKS)
+        if (args->csa_slotid > NFS41_BC_MAX_CALLBACKS)
                 return htonl(NFS4ERR_BADSLOT);
 
-        slot = tbl->slots + slotid;
+        slot = tbl->slots + args->csa_slotid;
         dprintk("%s slot table seqid: %d\n", __func__, slot->seq_nr);
 
         /* Normal */
-        if (likely(seqid == slot->seq_nr + 1)) {
+        if (likely(args->csa_sequenceid == 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);
+        if (args->csa_sequenceid == slot->seq_nr) {
+                dprintk("%s seqid %d is a replay\n",
+                        __func__, args->csa_sequenceid);
+                /* Signal process_op to set this error on next op */
+                if (args->csa_cachethis == 0)
+                        return htonl(NFS4ERR_RETRY_UNCACHED_REP);
+
+                /* The ca_maxresponsesize_cached is 0 with no DRC */
+                else if (args->csa_cachethis == 1)
+                        return htonl(NFS4ERR_REP_TOO_BIG_TO_CACHE);
         }
 
         /* Wraparound */
-        if (seqid == 1 && (slot->seq_nr + 1) == 0) {
+        if (args->csa_sequenceid == 1 && (slot->seq_nr + 1) == 0) {
                 slot->seq_nr = 1;
                 return htonl(NFS4_OK);
         }
@@ -156,61 +313,99 @@ validate_seqid(struct nfs4_slot_table *tbl, u32 slotid, u32 seqid)
 }
 
 /*
- * 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.
+ * For each referring call triple, check the session's slot table for
+ * a match.  If the slot is in use and the sequence numbers match, the
+ * client is still waiting for a response to the original request.
  */
- static struct nfs_client *find_client_with_session(
-        const struct sockaddr *addr, u32 nfsversion,
-        struct nfs4_sessionid *sessionid)
+static bool referring_call_exists(struct nfs_client *clp,
+                                  uint32_t nrclists,
+                                  struct referring_call_list *rclists)
 {
-        struct nfs_client *clp;
+        bool status = 0;
+        int i, j;
+        struct nfs4_session *session;
+        struct nfs4_slot_table *tbl;
+        struct referring_call_list *rclist;
+        struct referring_call *ref;
 
-        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;
-                        }
+        /*
+         * XXX When client trunking is implemented, this becomes
+         * a session lookup from within the loop
+         */
+        session = clp->cl_session;
+        tbl = &session->fc_slot_table;
+
+        for (i = 0; i < nrclists; i++) {
+                rclist = &rclists[i];
+                if (memcmp(session->sess_id.data,
+                           rclist->rcl_sessionid.data,
+                           NFS4_MAX_SESSIONID_LEN) != 0)
+                        continue;
+
+                for (j = 0; j < rclist->rcl_nrefcalls; j++) {
+                        ref = &rclist->rcl_refcalls[j];
+
+                        dprintk("%s: sessionid %x:%x:%x:%x sequenceid %u "
+                                "slotid %u\n", __func__,
+                                ((u32 *)&rclist->rcl_sessionid.data)[0],
+                                ((u32 *)&rclist->rcl_sessionid.data)[1],
+                                ((u32 *)&rclist->rcl_sessionid.data)[2],
+                                ((u32 *)&rclist->rcl_sessionid.data)[3],
+                                ref->rc_sequenceid, ref->rc_slotid);
+
+                        spin_lock(&tbl->slot_tbl_lock);
+                        status = (test_bit(ref->rc_slotid, tbl->used_slots) &&
+                                  tbl->slots[ref->rc_slotid].seq_nr ==
+                                        ref->rc_sequenceid);
+                        spin_unlock(&tbl->slot_tbl_lock);
+                        if (status)
+                                goto out;
                 }
-                clp = nfs_find_client_next(prev);
-                nfs_put_client(prev);
-        } while (clp != NULL);
+        }
 
-        return NULL;
+out:
+        return status;
 }
 
-/* FIXME: referring calls should be processed */
-unsigned nfs4_callback_sequence(struct cb_sequenceargs *args,
-                                struct cb_sequenceres *res)
+__be32 nfs4_callback_sequence(struct cb_sequenceargs *args,
+                              struct cb_sequenceres *res,
+                              struct cb_process_state *cps)
 {
         struct nfs_client *clp;
-        int i, status;
+        int i;
+        __be32 status;
 
-        for (i = 0; i < args->csa_nrclists; i++)
-                kfree(args->csa_rclists[i].rcl_refcalls);
-        kfree(args->csa_rclists);
+        cps->clp = NULL;
 
         status = htonl(NFS4ERR_BADSESSION);
-        clp = find_client_with_session(args->csa_addr, 4, &args->csa_sessionid);
+        /* Incoming session must match the callback session */
+        if (memcmp(&args->csa_sessionid, cps->svc_sid, NFS4_MAX_SESSIONID_LEN))
+                goto out;
+
+        clp = nfs4_find_client_sessionid(args->csa_addr,
+                                         &args->csa_sessionid, 1);
         if (clp == NULL)
                 goto out;
 
-        status = validate_seqid(&clp->cl_session->bc_slot_table,
-                                args->csa_slotid, args->csa_sequenceid);
+        /* state manager is resetting the session */
+        if (test_bit(NFS4_SESSION_DRAINING, &clp->cl_session->session_state)) {
+                status = NFS4ERR_DELAY;
+                goto out;
+        }
+
+        status = validate_seqid(&clp->cl_session->bc_slot_table, args);
         if (status)
-                goto out_putclient;
+                goto out;
+
+        /*
+         * Check for pending referring calls.  If a match is found, a
+         * related callback was received before the response to the original
+         * call.
+         */
+        if (referring_call_exists(clp, args->csa_nrclists, args->csa_rclists)) {
+                status = htonl(NFS4ERR_DELAY);
+                goto out;
+        }
 
         memcpy(&res->csr_sessionid, &args->csa_sessionid,
                sizeof(res->csr_sessionid));
@@ -218,13 +413,95 @@ unsigned nfs4_callback_sequence(struct cb_sequenceargs *args,
         res->csr_slotid = args->csa_slotid;
         res->csr_highestslotid = NFS41_BC_MAX_CALLBACKS - 1;
         res->csr_target_highestslotid = NFS41_BC_MAX_CALLBACKS - 1;
+        nfs4_cb_take_slot(clp);
+        cps->clp = clp; /* put in nfs4_callback_compound */
+
+out:
+        for (i = 0; i < args->csa_nrclists; i++)
+                kfree(args->csa_rclists[i].rcl_refcalls);
+        kfree(args->csa_rclists);
+
+        if (status == htonl(NFS4ERR_RETRY_UNCACHED_REP)) {
+                cps->drc_status = status;
+                status = 0;
+        } else
+                res->csr_status = status;
+
+        dprintk("%s: exit with status = %d res->csr_status %d\n", __func__,
+                ntohl(status), ntohl(res->csr_status));
+        return status;
+}
+
+static bool
+validate_bitmap_values(unsigned long mask)
+{
+        return (mask & ~RCA4_TYPE_MASK_ALL) == 0;
+}
+
+__be32 nfs4_callback_recallany(struct cb_recallanyargs *args, void *dummy,
+                               struct cb_process_state *cps)
+{
+        __be32 status;
+        fmode_t flags = 0;
+
+        status = cpu_to_be32(NFS4ERR_OP_NOT_IN_SESSION);
+        if (!cps->clp) /* set in cb_sequence */
+                goto out;
+
+        dprintk("NFS: RECALL_ANY callback request from %s\n",
+                rpc_peeraddr2str(cps->clp->cl_rpcclient, RPC_DISPLAY_ADDR));
+
+        status = cpu_to_be32(NFS4ERR_INVAL);
+        if (!validate_bitmap_values(args->craa_type_mask))
+                goto out;
 
-out_putclient:
-        nfs_put_client(clp);
+        status = cpu_to_be32(NFS4_OK);
+        if (test_bit(RCA4_TYPE_MASK_RDATA_DLG, (const unsigned long *)
+                     &args->craa_type_mask))
+                flags = FMODE_READ;
+        if (test_bit(RCA4_TYPE_MASK_WDATA_DLG, (const unsigned long *)
+                     &args->craa_type_mask))
+                flags |= FMODE_WRITE;
+        if (test_bit(RCA4_TYPE_MASK_FILE_LAYOUT, (const unsigned long *)
+                     &args->craa_type_mask))
+                pnfs_recall_all_layouts(cps->clp);
+        if (flags)
+                nfs_expire_all_delegation_types(cps->clp, flags);
 out:
         dprintk("%s: exit with status = %d\n", __func__, ntohl(status));
-        res->csr_status = status;
-        return res->csr_status;
+        return status;
 }
 
+/* Reduce the fore channel's max_slots to the target value */
+__be32 nfs4_callback_recallslot(struct cb_recallslotargs *args, void *dummy,
+                                struct cb_process_state *cps)
+{
+        struct nfs4_slot_table *fc_tbl;
+        __be32 status;
+
+        status = htonl(NFS4ERR_OP_NOT_IN_SESSION);
+        if (!cps->clp) /* set in cb_sequence */
+                goto out;
+
+        dprintk("NFS: CB_RECALL_SLOT request from %s target max slots %d\n",
+                rpc_peeraddr2str(cps->clp->cl_rpcclient, RPC_DISPLAY_ADDR),
+                args->crsa_target_max_slots);
+
+        fc_tbl = &cps->clp->cl_session->fc_slot_table;
+
+        status = htonl(NFS4ERR_BAD_HIGH_SLOT);
+        if (args->crsa_target_max_slots > fc_tbl->max_slots ||
+            args->crsa_target_max_slots < 1)
+                goto out;
+
+        status = htonl(NFS4_OK);
+        if (args->crsa_target_max_slots == fc_tbl->max_slots)
+                goto out;
+
+        fc_tbl->target_max_slots = args->crsa_target_max_slots;
+        nfs41_handle_recall_slot(cps->clp);
+out:
+        dprintk("%s: exit with status = %d\n", __func__, ntohl(status));
+        return status;
+}
 #endif /* CONFIG_NFS_V4_1 */
diff --git a/fs/nfs/callback_xdr.c b/fs/nfs/callback_xdr.c
index e5a2dac5f715..23112c263f81 100644
--- a/fs/nfs/callback_xdr.c
+++ b/fs/nfs/callback_xdr.c
@@ -9,8 +9,11 @@
 #include <linux/sunrpc/svc.h>
 #include <linux/nfs4.h>
 #include <linux/nfs_fs.h>
+#include <linux/slab.h>
+#include <linux/sunrpc/bc_xprt.h>
 #include "nfs4_fs.h"
 #include "callback.h"
+#include "internal.h"
 
 #define CB_OP_TAGLEN_MAXSZ      (512)
 #define CB_OP_HDR_RES_MAXSZ     (2 + CB_OP_TAGLEN_MAXSZ)
@@ -21,13 +24,20 @@
 #define CB_OP_RECALL_RES_MAXSZ  (CB_OP_HDR_RES_MAXSZ)
 
 #if defined(CONFIG_NFS_V4_1)
+#define CB_OP_LAYOUTRECALL_RES_MAXSZ    (CB_OP_HDR_RES_MAXSZ)
 #define CB_OP_SEQUENCE_RES_MAXSZ        (CB_OP_HDR_RES_MAXSZ + \
                                         4 + 1 + 3)
+#define CB_OP_RECALLANY_RES_MAXSZ       (CB_OP_HDR_RES_MAXSZ)
+#define CB_OP_RECALLSLOT_RES_MAXSZ      (CB_OP_HDR_RES_MAXSZ)
 #endif /* CONFIG_NFS_V4_1 */
 
 #define NFSDBG_FACILITY NFSDBG_CALLBACK
 
-typedef __be32 (*callback_process_op_t)(void *, void *);
+/* Internal error code */
+#define NFS4ERR_RESOURCE_HDR    11050
+
+typedef __be32 (*callback_process_op_t)(void *, void *,
+                                        struct cb_process_state *);
 typedef __be32 (*callback_decode_arg_t)(struct svc_rqst *, struct xdr_stream *, void *);
 typedef __be32 (*callback_encode_res_t)(struct svc_rqst *, struct xdr_stream *, void *);
 
@@ -154,7 +164,7 @@ static __be32 decode_compound_hdr_arg(struct xdr_stream *xdr, struct cb_compound
         hdr->minorversion = ntohl(*p++);
         /* Check minor version is zero or one. */
         if (hdr->minorversion <= 1) {
-                p++;    /* skip callback_ident */
+                hdr->cb_ident = ntohl(*p++); /* ignored by v4.1 */
         } else {
                 printk(KERN_WARNING "%s: NFSv4 server callback with "
                         "illegal minor version %u!\n",
@@ -172,7 +182,7 @@ static __be32 decode_op_hdr(struct xdr_stream *xdr, unsigned int *op)
         __be32 *p;
         p = read_buf(xdr, 4);
         if (unlikely(p == NULL))
-                return htonl(NFS4ERR_RESOURCE);
+                return htonl(NFS4ERR_RESOURCE_HDR);
         *op = ntohl(*p);
         return 0;
 }
@@ -214,26 +224,86 @@ out:
 
 #if defined(CONFIG_NFS_V4_1)
 
-static unsigned decode_sessionid(struct xdr_stream *xdr,
+static __be32 decode_layoutrecall_args(struct svc_rqst *rqstp,
+                                       struct xdr_stream *xdr,
+                                       struct cb_layoutrecallargs *args)
+{
+        __be32 *p;
+        __be32 status = 0;
+        uint32_t iomode;
+
+        args->cbl_addr = svc_addr(rqstp);
+        p = read_buf(xdr, 4 * sizeof(uint32_t));
+        if (unlikely(p == NULL)) {
+                status = htonl(NFS4ERR_BADXDR);
+                goto out;
+        }
+
+        args->cbl_layout_type = ntohl(*p++);
+        /* Depite the spec's xdr, iomode really belongs in the FILE switch,
+         * as it is unuseable and ignored with the other types.
+         */
+        iomode = ntohl(*p++);
+        args->cbl_layoutchanged = ntohl(*p++);
+        args->cbl_recall_type = ntohl(*p++);
+
+        if (args->cbl_recall_type == RETURN_FILE) {
+                args->cbl_range.iomode = iomode;
+                status = decode_fh(xdr, &args->cbl_fh);
+                if (unlikely(status != 0))
+                        goto out;
+
+                p = read_buf(xdr, 2 * sizeof(uint64_t));
+                if (unlikely(p == NULL)) {
+                        status = htonl(NFS4ERR_BADXDR);
+                        goto out;
+                }
+                p = xdr_decode_hyper(p, &args->cbl_range.offset);
+                p = xdr_decode_hyper(p, &args->cbl_range.length);
+                status = decode_stateid(xdr, &args->cbl_stateid);
+                if (unlikely(status != 0))
+                        goto out;
+        } else if (args->cbl_recall_type == RETURN_FSID) {
+                p = read_buf(xdr, 2 * sizeof(uint64_t));
+                if (unlikely(p == NULL)) {
+                        status = htonl(NFS4ERR_BADXDR);
+                        goto out;
+                }
+                p = xdr_decode_hyper(p, &args->cbl_fsid.major);
+                p = xdr_decode_hyper(p, &args->cbl_fsid.minor);
+        } else if (args->cbl_recall_type != RETURN_ALL) {
+                status = htonl(NFS4ERR_BADXDR);
+                goto out;
+        }
+        dprintk("%s: ltype 0x%x iomode %d changed %d recall_type %d\n",
+                __func__,
+                args->cbl_layout_type, iomode,
+                args->cbl_layoutchanged, args->cbl_recall_type);
+out:
+        dprintk("%s: exit with status = %d\n", __func__, ntohl(status));
+        return status;
+}
+
+static __be32 decode_sessionid(struct xdr_stream *xdr,
                                  struct nfs4_sessionid *sid)
 {
-        uint32_t *p;
+        __be32 *p;
         int len = NFS4_MAX_SESSIONID_LEN;
 
         p = read_buf(xdr, len);
         if (unlikely(p == NULL))
-                return htonl(NFS4ERR_RESOURCE);;
+                return htonl(NFS4ERR_RESOURCE);
 
         memcpy(sid->data, p, len);
         return 0;
 }
 
-static unsigned decode_rc_list(struct xdr_stream *xdr,
+static __be32 decode_rc_list(struct xdr_stream *xdr,
                                struct referring_call_list *rc_list)
 {
-        uint32_t *p;
+        __be32 *p;
         int i;
-        unsigned status;
+        __be32 status;
 
         status = decode_sessionid(xdr, &rc_list->rcl_sessionid);
         if (status)
@@ -266,13 +336,13 @@ out:
         return status;
 }
 
-static unsigned decode_cb_sequence_args(struct svc_rqst *rqstp,
+static __be32 decode_cb_sequence_args(struct svc_rqst *rqstp,
                                         struct xdr_stream *xdr,
                                         struct cb_sequenceargs *args)
 {
-        uint32_t *p;
+        __be32 *p;
         int i;
-        unsigned status;
+        __be32 status;
 
         status = decode_sessionid(xdr, &args->csa_sessionid);
         if (status)
@@ -326,6 +396,39 @@ out_free:
         goto out;
 }
 
+static __be32 decode_recallany_args(struct svc_rqst *rqstp,
+                                      struct xdr_stream *xdr,
+                                      struct cb_recallanyargs *args)
+{
+        __be32 *p;
+
+        args->craa_addr = svc_addr(rqstp);
+        p = read_buf(xdr, 4);
+        if (unlikely(p == NULL))
+                return htonl(NFS4ERR_BADXDR);
+        args->craa_objs_to_keep = ntohl(*p++);
+        p = read_buf(xdr, 4);
+        if (unlikely(p == NULL))
+                return htonl(NFS4ERR_BADXDR);
+        args->craa_type_mask = ntohl(*p);
+
+        return 0;
+}
+
+static __be32 decode_recallslot_args(struct svc_rqst *rqstp,
+                                        struct xdr_stream *xdr,
+                                        struct cb_recallslotargs *args)
+{
+        __be32 *p;
+
+        args->crsa_addr = svc_addr(rqstp);
+        p = read_buf(xdr, 4);
+        if (unlikely(p == NULL))
+                return htonl(NFS4ERR_BADXDR);
+        args->crsa_target_max_slots = ntohl(*p++);
+        return 0;
+}
+
 #endif /* CONFIG_NFS_V4_1 */
 
 static __be32 encode_string(struct xdr_stream *xdr, unsigned int len, const char *str)
@@ -445,7 +548,7 @@ static __be32 encode_op_hdr(struct xdr_stream *xdr, uint32_t op, __be32 res)
         
         p = xdr_reserve_space(xdr, 8);
         if (unlikely(p == NULL))
-                return htonl(NFS4ERR_RESOURCE);
+                return htonl(NFS4ERR_RESOURCE_HDR);
         *p++ = htonl(op);
         *p = res;
         return 0;
@@ -479,10 +582,10 @@ out:
 
 #if defined(CONFIG_NFS_V4_1)
 
-static unsigned encode_sessionid(struct xdr_stream *xdr,
+static __be32 encode_sessionid(struct xdr_stream *xdr,
                                  const struct nfs4_sessionid *sid)
 {
-        uint32_t *p;
+        __be32 *p;
         int len = NFS4_MAX_SESSIONID_LEN;
 
         p = xdr_reserve_space(xdr, len);
@@ -493,11 +596,11 @@ static unsigned encode_sessionid(struct xdr_stream *xdr,
         return 0;
 }
 
-static unsigned encode_cb_sequence_res(struct svc_rqst *rqstp,
+static __be32 encode_cb_sequence_res(struct svc_rqst *rqstp,
                                        struct xdr_stream *xdr,
                                        const struct cb_sequenceres *res)
 {
-        uint32_t *p;
+        __be32 *p;
         unsigned status = res->csr_status;
 
         if (unlikely(status != 0))
@@ -533,16 +636,16 @@ preprocess_nfs41_op(int nop, unsigned int op_nr, struct callback_op **op)
         case OP_CB_GETATTR:
         case OP_CB_RECALL:
         case OP_CB_SEQUENCE:
+        case OP_CB_RECALL_ANY:
+        case OP_CB_RECALL_SLOT:
+        case OP_CB_LAYOUTRECALL:
                 *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);
@@ -554,6 +657,37 @@ preprocess_nfs41_op(int nop, unsigned int op_nr, struct callback_op **op)
         return htonl(NFS_OK);
 }
 
+static void nfs4_callback_free_slot(struct nfs4_session *session)
+{
+        struct nfs4_slot_table *tbl = &session->bc_slot_table;
+
+        spin_lock(&tbl->slot_tbl_lock);
+        /*
+         * Let the state manager know callback processing done.
+         * A single slot, so highest used slotid is either 0 or -1
+         */
+        tbl->highest_used_slotid--;
+        nfs4_check_drain_bc_complete(session);
+        spin_unlock(&tbl->slot_tbl_lock);
+}
+
+static void nfs4_cb_free_slot(struct nfs_client *clp)
+{
+        if (clp && clp->cl_session)
+                nfs4_callback_free_slot(clp->cl_session);
+}
+
+/* A single slot, so highest used slotid is either 0 or -1 */
+void nfs4_cb_take_slot(struct nfs_client *clp)
+{
+        struct nfs4_slot_table *tbl = &clp->cl_session->bc_slot_table;
+
+        spin_lock(&tbl->slot_tbl_lock);
+        tbl->highest_used_slotid++;
+        BUG_ON(tbl->highest_used_slotid != 0);
+        spin_unlock(&tbl->slot_tbl_lock);
+}
+
 #else /* CONFIG_NFS_V4_1 */
 
 static __be32
@@ -562,6 +696,9 @@ preprocess_nfs41_op(int nop, unsigned int op_nr, struct callback_op **op)
         return htonl(NFS4ERR_MINOR_VERS_MISMATCH);
 }
 
+static void nfs4_cb_free_slot(struct nfs_client *clp)
+{
+}
 #endif /* CONFIG_NFS_V4_1 */
 
 static __be32
@@ -582,20 +719,19 @@ preprocess_nfs4_op(unsigned int op_nr, struct callback_op **op)
 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 xdr_stream *xdr_out, void *resp,
+                struct cb_process_state *cps)
 {
         struct callback_op *op = &callback_ops[0];
-        unsigned int op_nr = OP_CB_ILLEGAL;
+        unsigned int op_nr;
         __be32 status;
         long maxlen;
         __be32 res;
 
         dprintk("%s: start\n", __func__);
         status = decode_op_hdr(xdr_in, &op_nr);
-        if (unlikely(status)) {
-                status = htonl(NFS4ERR_OP_ILLEGAL);
-                goto out;
-        }
+        if (unlikely(status))
+                return status;
 
         dprintk("%s: minorversion=%d nop=%d op_nr=%u\n",
                 __func__, minorversion, nop, op_nr);
@@ -604,19 +740,26 @@ static __be32 process_op(uint32_t minorversion, int nop,
                                 preprocess_nfs4_op(op_nr, &op);
         if (status == htonl(NFS4ERR_OP_ILLEGAL))
                 op_nr = OP_CB_ILLEGAL;
-out:
+        if (status)
+                goto encode_hdr;
+
+        if (cps->drc_status) {
+                status = cps->drc_status;
+                goto encode_hdr;
+        }
+
         maxlen = xdr_out->end - xdr_out->p;
         if (maxlen > 0 && maxlen < PAGE_SIZE) {
-                if (likely(status == 0 && op->decode_args != NULL))
-                        status = op->decode_args(rqstp, xdr_in, argp);
-                if (likely(status == 0 && op->process_op != NULL))
-                        status = op->process_op(argp, resp);
+                status = op->decode_args(rqstp, xdr_in, argp);
+                if (likely(status == 0))
+                        status = op->process_op(argp, resp, cps);
         } else
                 status = htonl(NFS4ERR_RESOURCE);
 
+encode_hdr:
         res = encode_op_hdr(xdr_out, op_nr, status);
-        if (status == 0)
-                status = res;
+        if (unlikely(res))
+                return res;
         if (op->encode_res != NULL && status == 0)
                 status = op->encode_res(rqstp, xdr_out, resp);
         dprintk("%s: done, status = %d\n", __func__, ntohl(status));
@@ -631,8 +774,11 @@ static __be32 nfs4_callback_compound(struct svc_rqst *rqstp, void *argp, void *r
         struct cb_compound_hdr_arg hdr_arg = { 0 };
         struct cb_compound_hdr_res hdr_res = { NULL };
         struct xdr_stream xdr_in, xdr_out;
-        __be32 *p;
-        __be32 status;
+        __be32 *p, status;
+        struct cb_process_state cps = {
+                .drc_status = 0,
+                .clp = NULL,
+        };
         unsigned int nops = 0;
 
         dprintk("%s: start\n", __func__);
@@ -646,19 +792,35 @@ static __be32 nfs4_callback_compound(struct svc_rqst *rqstp, void *argp, void *r
         if (status == __constant_htonl(NFS4ERR_RESOURCE))
                 return rpc_garbage_args;
 
+        if (hdr_arg.minorversion == 0) {
+                cps.clp = nfs4_find_client_ident(hdr_arg.cb_ident);
+                if (!cps.clp)
+                        return rpc_drop_reply;
+        } else
+                cps.svc_sid = bc_xprt_sid(rqstp);
+
         hdr_res.taglen = hdr_arg.taglen;
         hdr_res.tag = hdr_arg.tag;
         if (encode_compound_hdr_res(&xdr_out, &hdr_res) != 0)
                 return rpc_system_err;
 
         while (status == 0 && nops != hdr_arg.nops) {
-                status = process_op(hdr_arg.minorversion, nops,
-                                    rqstp, &xdr_in, argp, &xdr_out, resp);
+                status = process_op(hdr_arg.minorversion, nops, rqstp,
+                                    &xdr_in, argp, &xdr_out, resp, &cps);
                 nops++;
         }
 
+        /* Buffer overflow in decode_ops_hdr or encode_ops_hdr. Return
+        * resource error in cb_compound status without returning op */
+        if (unlikely(status == htonl(NFS4ERR_RESOURCE_HDR))) {
+                status = htonl(NFS4ERR_RESOURCE);
+                nops--;
+        }
+
         *hdr_res.status = status;
         *hdr_res.nops = htonl(nops);
+        nfs4_cb_free_slot(cps.clp);
+        nfs_put_client(cps.clp);
         dprintk("%s: done, status = %u\n", __func__, ntohl(status));
         return rpc_success;
 }
@@ -682,12 +844,28 @@ static struct callback_op callback_ops[] = {
                 .res_maxsize = CB_OP_RECALL_RES_MAXSZ,
         },
 #if defined(CONFIG_NFS_V4_1)
+        [OP_CB_LAYOUTRECALL] = {
+                .process_op = (callback_process_op_t)nfs4_callback_layoutrecall,
+                .decode_args =
+                        (callback_decode_arg_t)decode_layoutrecall_args,
+                .res_maxsize = CB_OP_LAYOUTRECALL_RES_MAXSZ,
+        },
         [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,
         },
+        [OP_CB_RECALL_ANY] = {
+                .process_op = (callback_process_op_t)nfs4_callback_recallany,
+                .decode_args = (callback_decode_arg_t)decode_recallany_args,
+                .res_maxsize = CB_OP_RECALLANY_RES_MAXSZ,
+        },
+        [OP_CB_RECALL_SLOT] = {
+                .process_op = (callback_process_op_t)nfs4_callback_recallslot,
+                .decode_args = (callback_decode_arg_t)decode_recallslot_args,
+                .res_maxsize = CB_OP_RECALLSLOT_RES_MAXSZ,
+        },
 #endif /* CONFIG_NFS_V4_1 */
 };
 
@@ -716,5 +894,13 @@ struct svc_version nfs4_callback_version1 = {
         .vs_proc = nfs4_callback_procedures1,
         .vs_xdrsize = NFS4_CALLBACK_XDRSIZE,
         .vs_dispatch = NULL,
+        .vs_hidden = 1,
 };
 
+struct svc_version nfs4_callback_version4 = {
+        .vs_vers = 4,
+        .vs_nproc = ARRAY_SIZE(nfs4_callback_procedures1),
+        .vs_proc = nfs4_callback_procedures1,
+        .vs_xdrsize = NFS4_CALLBACK_XDRSIZE,
+        .vs_dispatch = NULL,
+};
diff --git a/fs/nfs/client.c b/fs/nfs/client.c
index c2d061675d80..192f2f860265 100644
--- a/fs/nfs/client.c
+++ b/fs/nfs/client.c
@@ -35,6 +35,7 @@
 #include <linux/vfs.h>
 #include <linux/inet.h>
 #include <linux/in6.h>
+#include <linux/slab.h>
 #include <net/ipv6.h>
 #include <linux/nfs_xdr.h>
 #include <linux/sunrpc/bc_xprt.h>
@@ -47,6 +48,7 @@
 #include "iostat.h"
 #include "internal.h"
 #include "fscache.h"
+#include "pnfs.h"
 
 #define NFSDBG_FACILITY         NFSDBG_CLIENT
 
@@ -54,6 +56,30 @@ static DEFINE_SPINLOCK(nfs_client_lock);
 static LIST_HEAD(nfs_client_list);
 static LIST_HEAD(nfs_volume_list);
 static DECLARE_WAIT_QUEUE_HEAD(nfs_client_active_wq);
+#ifdef CONFIG_NFS_V4
+static DEFINE_IDR(cb_ident_idr); /* Protected by nfs_client_lock */
+
+/*
+ * Get a unique NFSv4.0 callback identifier which will be used
+ * by the V4.0 callback service to lookup the nfs_client struct
+ */
+static int nfs_get_cb_ident_idr(struct nfs_client *clp, int minorversion)
+{
+        int ret = 0;
+
+        if (clp->rpc_ops->version != 4 || minorversion != 0)
+                return ret;
+retry:
+        if (!idr_pre_get(&cb_ident_idr, GFP_KERNEL))
+                return -ENOMEM;
+        spin_lock(&nfs_client_lock);
+        ret = idr_get_new(&cb_ident_idr, clp, &clp->cl_cb_ident);
+        spin_unlock(&nfs_client_lock);
+        if (ret == -EAGAIN)
+                goto retry;
+        return ret;
+}
+#endif /* CONFIG_NFS_V4 */
 
 /*
  * RPC cruft for NFS
@@ -142,18 +168,24 @@ static struct nfs_client *nfs_alloc_client(const struct nfs_client_initdata *cl_
         clp->cl_proto = cl_init->proto;
 
 #ifdef CONFIG_NFS_V4
-        INIT_LIST_HEAD(&clp->cl_delegations);
+        err = nfs_get_cb_ident_idr(clp, cl_init->minorversion);
+        if (err)
+                goto error_cleanup;
+
         spin_lock_init(&clp->cl_lock);
         INIT_DELAYED_WORK(&clp->cl_renewd, nfs4_renew_state);
         rpc_init_wait_queue(&clp->cl_rpcwaitq, "NFS client");
         clp->cl_boot_time = CURRENT_TIME;
         clp->cl_state = 1 << NFS4CLNT_LEASE_EXPIRED;
         clp->cl_minorversion = cl_init->minorversion;
+        clp->cl_mvops = nfs_v4_minor_ops[cl_init->minorversion];
 #endif
         cred = rpc_lookup_machine_cred();
         if (!IS_ERR(cred))
                 clp->cl_machine_cred = cred;
-
+#if defined(CONFIG_NFS_V4_1)
+        INIT_LIST_HEAD(&clp->cl_layouts);
+#endif
         nfs_fscache_get_client_cookie(clp);
 
         return clp;
@@ -164,48 +196,77 @@ error_0:
         return ERR_PTR(err);
 }
 
+#ifdef CONFIG_NFS_V4
+#ifdef CONFIG_NFS_V4_1
+static void nfs4_shutdown_session(struct nfs_client *clp)
+{
+        if (nfs4_has_session(clp))
+                nfs4_destroy_session(clp->cl_session);
+}
+#else /* CONFIG_NFS_V4_1 */
+static void nfs4_shutdown_session(struct nfs_client *clp)
+{
+}
+#endif /* CONFIG_NFS_V4_1 */
+
+/*
+ * Destroy the NFS4 callback service
+ */
+static void nfs4_destroy_callback(struct nfs_client *clp)
+{
+        if (__test_and_clear_bit(NFS_CS_CALLBACK, &clp->cl_res_state))
+                nfs_callback_down(clp->cl_mvops->minor_version);
+}
+
 static void nfs4_shutdown_client(struct nfs_client *clp)
 {
-#ifdef CONFIG_NFS_V4
         if (__test_and_clear_bit(NFS_CS_RENEWD, &clp->cl_res_state))
                 nfs4_kill_renewd(clp);
-        BUG_ON(!RB_EMPTY_ROOT(&clp->cl_state_owners));
+        nfs4_shutdown_session(clp);
+        nfs4_destroy_callback(clp);
         if (__test_and_clear_bit(NFS_CS_IDMAP, &clp->cl_res_state))
                 nfs_idmap_delete(clp);
 
         rpc_destroy_wait_queue(&clp->cl_rpcwaitq);
-#endif
 }
 
-/*
- * Destroy the NFS4 callback service
- */
-static void nfs4_destroy_callback(struct nfs_client *clp)
+/* idr_remove_all is not needed as all id's are removed by nfs_put_client */
+void nfs_cleanup_cb_ident_idr(void)
 {
-#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 */
+        idr_destroy(&cb_ident_idr);
 }
 
-/*
- * 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)
+/* nfs_client_lock held */
+static void nfs_cb_idr_remove_locked(struct nfs_client *clp)
 {
-#ifdef CONFIG_NFS_V4_1
-        if (nfs4_has_session(clp)) {
-                nfs4_destroy_session(clp->cl_session);
-                clp->cl_session = NULL;
-        }
+        if (clp->cl_cb_ident)
+                idr_remove(&cb_ident_idr, clp->cl_cb_ident);
+}
 
-        clp->cl_call_sync = _nfs4_call_sync;
-#endif /* CONFIG_NFS_V4_1 */
+static void pnfs_init_server(struct nfs_server *server)
+{
+        rpc_init_wait_queue(&server->roc_rpcwaitq, "pNFS ROC");
+}
 
-        nfs4_destroy_callback(clp);
+#else
+static void nfs4_shutdown_client(struct nfs_client *clp)
+{
 }
 
+void nfs_cleanup_cb_ident_idr(void)
+{
+}
+
+static void nfs_cb_idr_remove_locked(struct nfs_client *clp)
+{
+}
+
+static void pnfs_init_server(struct nfs_server *server)
+{
+}
+
+#endif /* CONFIG_NFS_V4 */
+
 /*
  * Destroy a shared client record
  */
@@ -213,7 +274,6 @@ 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);
@@ -243,6 +303,7 @@ void nfs_put_client(struct nfs_client *clp)
 
         if (atomic_dec_and_lock(&clp->cl_count, &nfs_client_lock)) {
                 list_del(&clp->cl_share_link);
+                nfs_cb_idr_remove_locked(clp);
                 spin_unlock(&nfs_client_lock);
 
                 BUG_ON(!list_empty(&clp->cl_superblocks));
@@ -250,6 +311,7 @@ void nfs_put_client(struct nfs_client *clp)
                 nfs_free_client(clp);
         }
 }
+EXPORT_SYMBOL_GPL(nfs_put_client);
 
 #if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
 /*
@@ -273,7 +335,7 @@ static int nfs_sockaddr_match_ipaddr6(const struct sockaddr *sa1,
             sin1->sin6_scope_id != sin2->sin6_scope_id)
                 return 0;
 
-        return ipv6_addr_equal(&sin1->sin6_addr, &sin1->sin6_addr);
+        return ipv6_addr_equal(&sin1->sin6_addr, &sin2->sin6_addr);
 }
 #else   /* !defined(CONFIG_IPV6) && !defined(CONFIG_IPV6_MODULE) */
 static int nfs_sockaddr_match_ipaddr6(const struct sockaddr *sa1,
@@ -357,70 +419,28 @@ static int nfs_sockaddr_cmp(const struct sockaddr *sa1,
         return 0;
 }
 
-/*
- * Find a client by IP address and protocol version
- * - returns NULL if no such client
- */
-struct nfs_client *nfs_find_client(const struct sockaddr *addr, u32 nfsversion)
-{
-        struct nfs_client *clp;
-
-        spin_lock(&nfs_client_lock);
-        list_for_each_entry(clp, &nfs_client_list, cl_share_link) {
-                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 ||
-                      clp->cl_cons_state == NFS_CS_SESSION_INITING))
-                        continue;
-
-                /* Different NFS versions cannot share the same nfs_client */
-                if (clp->rpc_ops->version != nfsversion)
-                        continue;
-
-                /* Match only the IP address, not the port number */
-                if (!nfs_sockaddr_match_ipaddr(addr, clap))
-                        continue;
-
-                atomic_inc(&clp->cl_count);
-                spin_unlock(&nfs_client_lock);
-                return clp;
-        }
-        spin_unlock(&nfs_client_lock);
-        return NULL;
-}
-
-/*
- * Find a client by IP address and protocol version
- * - returns NULL if no such client
- */
-struct nfs_client *nfs_find_client_next(struct nfs_client *clp)
+/* Common match routine for v4.0 and v4.1 callback services */
+bool
+nfs4_cb_match_client(const struct sockaddr *addr, struct nfs_client *clp,
+                     u32 minorversion)
 {
-        struct sockaddr *sap = (struct sockaddr *)&clp->cl_addr;
-        u32 nfsvers = clp->rpc_ops->version;
-
-        spin_lock(&nfs_client_lock);
-        list_for_each_entry_continue(clp, &nfs_client_list, cl_share_link) {
-                struct sockaddr *clap = (struct sockaddr *)&clp->cl_addr;
+        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)
-                        continue;
+        /* Don't match clients that failed to initialise */
+        if (!(clp->cl_cons_state == NFS_CS_READY ||
+            clp->cl_cons_state == NFS_CS_SESSION_INITING))
+                return false;
 
-                /* Different NFS versions cannot share the same nfs_client */
-                if (clp->rpc_ops->version != nfsvers)
-                        continue;
+        /* Match the version and minorversion */
+        if (clp->rpc_ops->version != 4 ||
+            clp->cl_minorversion != minorversion)
+                return false;
 
-                /* Match only the IP address, not the port number */
-                if (!nfs_sockaddr_match_ipaddr(sap, clap))
-                        continue;
+        /* Match only the IP address, not the port number */
+        if (!nfs_sockaddr_match_ipaddr(addr, clap))
+                return false;
 
-                atomic_inc(&clp->cl_count);
-                spin_unlock(&nfs_client_lock);
-                return clp;
-        }
-        spin_unlock(&nfs_client_lock);
-        return NULL;
+        return true;
 }
 
 /*
@@ -599,6 +619,7 @@ static int nfs_create_rpc_client(struct nfs_client *clp,
 {
         struct rpc_clnt         *clnt = NULL;
         struct rpc_create_args args = {
+                .net            = &init_net,
                 .protocol       = clp->cl_proto,
                 .address        = (struct sockaddr *)&clp->cl_addr,
                 .addrsize       = clp->cl_addrlen,
@@ -633,7 +654,8 @@ static int nfs_create_rpc_client(struct nfs_client *clp,
  */
 static void nfs_destroy_server(struct nfs_server *server)
 {
-        if (!(server->flags & NFS_MOUNT_NONLM))
+        if (!(server->flags & NFS_MOUNT_LOCAL_FLOCK) ||
+                        !(server->flags & NFS_MOUNT_LOCAL_FCNTL))
                 nlmclnt_done(server->nlm_host);
 }
 
@@ -648,8 +670,6 @@ static int nfs_start_lockd(struct nfs_server *server)
                 .hostname       = clp->cl_hostname,
                 .address        = (struct sockaddr *)&clp->cl_addr,
                 .addrlen        = clp->cl_addrlen,
-                .protocol       = server->flags & NFS_MOUNT_TCP ?
-                                                IPPROTO_TCP : IPPROTO_UDP,
                 .nfs_version    = clp->rpc_ops->version,
                 .noresvport     = server->flags & NFS_MOUNT_NORESVPORT ?
                                         1 : 0,
@@ -657,9 +677,18 @@ static int nfs_start_lockd(struct nfs_server *server)
 
         if (nlm_init.nfs_version > 3)
                 return 0;
-        if (server->flags & NFS_MOUNT_NONLM)
+        if ((server->flags & NFS_MOUNT_LOCAL_FLOCK) &&
+                        (server->flags & NFS_MOUNT_LOCAL_FCNTL))
                 return 0;
 
+        switch (clp->cl_proto) {
+                default:
+                        nlm_init.protocol = IPPROTO_TCP;
+                        break;
+                case XPRT_TRANSPORT_UDP:
+                        nlm_init.protocol = IPPROTO_UDP;
+        }
+
         host = nlmclnt_init(&nlm_init);
         if (IS_ERR(host))
                 return PTR_ERR(host);
@@ -787,7 +816,7 @@ static int nfs_init_server(struct nfs_server *server,
         dprintk("--> nfs_init_server()\n");
 
 #ifdef CONFIG_NFS_V3
-        if (data->flags & NFS_MOUNT_VER3)
+        if (data->version == 3)
                 cl_init.rpc_ops = &nfs_v3_clientops;
 #endif
 
@@ -809,6 +838,9 @@ static int nfs_init_server(struct nfs_server *server,
         /* Initialise the client representation from the mount data */
         server->flags = data->flags;
         server->options = data->options;
+        server->caps |= NFS_CAP_HARDLINKS|NFS_CAP_SYMLINKS|NFS_CAP_FILEID|
+                NFS_CAP_MODE|NFS_CAP_NLINK|NFS_CAP_OWNER|NFS_CAP_OWNER_GROUP|
+                NFS_CAP_ATIME|NFS_CAP_CTIME|NFS_CAP_MTIME;
 
         if (data->rsize)
                 server->rsize = nfs_block_size(data->rsize, NULL);
@@ -879,6 +911,7 @@ static void nfs_server_set_fsinfo(struct nfs_server *server, struct nfs_fsinfo *
                 server->rsize = NFS_MAX_FILE_IO_SIZE;
         server->rpages = (server->rsize + PAGE_CACHE_SIZE - 1) >> PAGE_CACHE_SHIFT;
 
+        server->backing_dev_info.name = "nfs";
         server->backing_dev_info.ra_pages = server->rpages * NFS_MAX_READAHEAD;
 
         if (server->wsize > max_rpc_payload)
@@ -886,11 +919,13 @@ static void nfs_server_set_fsinfo(struct nfs_server *server, struct nfs_fsinfo *
         if (server->wsize > NFS_MAX_FILE_IO_SIZE)
                 server->wsize = NFS_MAX_FILE_IO_SIZE;
         server->wpages = (server->wsize + PAGE_CACHE_SIZE - 1) >> PAGE_CACHE_SHIFT;
+        set_pnfs_layoutdriver(server, fsinfo->layouttype);
+
         server->wtmult = nfs_block_bits(fsinfo->wtmult, NULL);
 
         server->dtsize = nfs_block_size(fsinfo->dtpref, NULL);
-        if (server->dtsize > PAGE_CACHE_SIZE)
-                server->dtsize = PAGE_CACHE_SIZE;
+        if (server->dtsize > PAGE_CACHE_SIZE * NFS_MAX_READDIR_PAGES)
+                server->dtsize = PAGE_CACHE_SIZE * NFS_MAX_READDIR_PAGES;
         if (server->dtsize > server->rsize)
                 server->dtsize = server->rsize;
 
@@ -901,6 +936,8 @@ static void nfs_server_set_fsinfo(struct nfs_server *server, struct nfs_fsinfo *
 
         server->maxfilesize = fsinfo->maxfilesize;
 
+        server->time_delta = fsinfo->time_delta;
+
         /* We're airborne Set socket buffersize */
         rpc_setbufsize(server->client, server->wsize + 100, server->rsize + 100);
 }
@@ -923,16 +960,12 @@ static int nfs_probe_fsinfo(struct nfs_server *server, struct nfs_fh *mntfh, str
         }
 
         fsinfo.fattr = fattr;
-        nfs_fattr_init(fattr);
+        fsinfo.layouttype = 0;
         error = clp->rpc_ops->fsinfo(server, mntfh, &fsinfo);
         if (error < 0)
                 goto out_error;
 
         nfs_server_set_fsinfo(server, &fsinfo);
-        error = bdi_init(&server->backing_dev_info);
-        if (error)
-                goto out_error;
-
 
         /* Get some general file system info */
         if (server->namelen == 0) {
@@ -959,11 +992,35 @@ out_error:
 static void nfs_server_copy_userdata(struct nfs_server *target, struct nfs_server *source)
 {
         target->flags = source->flags;
+        target->rsize = source->rsize;
+        target->wsize = source->wsize;
         target->acregmin = source->acregmin;
         target->acregmax = source->acregmax;
         target->acdirmin = source->acdirmin;
         target->acdirmax = source->acdirmax;
         target->caps = source->caps;
+        target->options = source->options;
+}
+
+static void nfs_server_insert_lists(struct nfs_server *server)
+{
+        struct nfs_client *clp = server->nfs_client;
+
+        spin_lock(&nfs_client_lock);
+        list_add_tail_rcu(&server->client_link, &clp->cl_superblocks);
+        list_add_tail(&server->master_link, &nfs_volume_list);
+        spin_unlock(&nfs_client_lock);
+
+}
+
+static void nfs_server_remove_lists(struct nfs_server *server)
+{
+        spin_lock(&nfs_client_lock);
+        list_del_rcu(&server->client_link);
+        list_del(&server->master_link);
+        spin_unlock(&nfs_client_lock);
+
+        synchronize_rcu();
 }
 
 /*
@@ -982,6 +1039,7 @@ static struct nfs_server *nfs_alloc_server(void)
         /* Zero out the NFS state stuff */
         INIT_LIST_HEAD(&server->client_link);
         INIT_LIST_HEAD(&server->master_link);
+        INIT_LIST_HEAD(&server->delegations);
 
         atomic_set(&server->active, 0);
 
@@ -991,6 +1049,14 @@ static struct nfs_server *nfs_alloc_server(void)
                 return NULL;
         }
 
+        if (bdi_init(&server->backing_dev_info)) {
+                nfs_free_iostats(server->io_stats);
+                kfree(server);
+                return NULL;
+        }
+
+        pnfs_init_server(server);
+
         return server;
 }
 
@@ -1001,10 +1067,8 @@ void nfs_free_server(struct nfs_server *server)
 {
         dprintk("--> nfs_free_server()\n");
 
-        spin_lock(&nfs_client_lock);
-        list_del(&server->client_link);
-        list_del(&server->master_link);
-        spin_unlock(&nfs_client_lock);
+        nfs_server_remove_lists(server);
+        unset_pnfs_layoutdriver(server);
 
         if (server->destroy != NULL)
                 server->destroy(server);
@@ -1031,13 +1095,18 @@ struct nfs_server *nfs_create_server(const struct nfs_parsed_mount_data *data,
                                      struct nfs_fh *mntfh)
 {
         struct nfs_server *server;
-        struct nfs_fattr fattr;
+        struct nfs_fattr *fattr;
         int error;
 
         server = nfs_alloc_server();
         if (!server)
                 return ERR_PTR(-ENOMEM);
 
+        error = -ENOMEM;
+        fattr = nfs_alloc_fattr();
+        if (fattr == NULL)
+                goto error;
+
         /* Get a client representation */
         error = nfs_init_server(server, data);
         if (error < 0)
@@ -1048,7 +1117,7 @@ struct nfs_server *nfs_create_server(const struct nfs_parsed_mount_data *data,
         BUG_ON(!server->nfs_client->rpc_ops->file_inode_ops);
 
         /* Probe the root fh to retrieve its FSID */
-        error = nfs_probe_fsinfo(server, mntfh, &fattr);
+        error = nfs_probe_fsinfo(server, mntfh, fattr);
         if (error < 0)
                 goto error;
         if (server->nfs_client->rpc_ops->version == 3) {
@@ -1061,38 +1130,127 @@ struct nfs_server *nfs_create_server(const struct nfs_parsed_mount_data *data,
                         server->namelen = NFS2_MAXNAMLEN;
         }
 
-        if (!(fattr.valid & NFS_ATTR_FATTR)) {
-                error = server->nfs_client->rpc_ops->getattr(server, mntfh, &fattr);
+        if (!(fattr->valid & NFS_ATTR_FATTR)) {
+                error = server->nfs_client->rpc_ops->getattr(server, mntfh, fattr);
                 if (error < 0) {
                         dprintk("nfs_create_server: getattr error = %d\n", -error);
                         goto error;
                 }
         }
-        memcpy(&server->fsid, &fattr.fsid, sizeof(server->fsid));
+        memcpy(&server->fsid, &fattr->fsid, sizeof(server->fsid));
 
         dprintk("Server FSID: %llx:%llx\n",
                 (unsigned long long) server->fsid.major,
                 (unsigned long long) server->fsid.minor);
 
-        BUG_ON(!server->nfs_client);
-        BUG_ON(!server->nfs_client->rpc_ops);
-        BUG_ON(!server->nfs_client->rpc_ops->file_inode_ops);
-
-        spin_lock(&nfs_client_lock);
-        list_add_tail(&server->client_link, &server->nfs_client->cl_superblocks);
-        list_add_tail(&server->master_link, &nfs_volume_list);
-        spin_unlock(&nfs_client_lock);
-
+        nfs_server_insert_lists(server);
         server->mount_time = jiffies;
+        nfs_free_fattr(fattr);
         return server;
 
 error:
+        nfs_free_fattr(fattr);
         nfs_free_server(server);
         return ERR_PTR(error);
 }
 
 #ifdef CONFIG_NFS_V4
 /*
+ * NFSv4.0 callback thread helper
+ *
+ * Find a client by IP address, protocol version, and minorversion
+ *
+ * Called from the pg_authenticate method. The callback identifier
+ * is not used as it has not been decoded.
+ *
+ * Returns NULL if no such client
+ */
+struct nfs_client *
+nfs4_find_client_no_ident(const struct sockaddr *addr)
+{
+        struct nfs_client *clp;
+
+        spin_lock(&nfs_client_lock);
+        list_for_each_entry(clp, &nfs_client_list, cl_share_link) {
+                if (nfs4_cb_match_client(addr, clp, 0) == false)
+                        continue;
+                atomic_inc(&clp->cl_count);
+                spin_unlock(&nfs_client_lock);
+                return clp;
+        }
+        spin_unlock(&nfs_client_lock);
+        return NULL;
+}
+
+/*
+ * NFSv4.0 callback thread helper
+ *
+ * Find a client by callback identifier
+ */
+struct nfs_client *
+nfs4_find_client_ident(int cb_ident)
+{
+        struct nfs_client *clp;
+
+        spin_lock(&nfs_client_lock);
+        clp = idr_find(&cb_ident_idr, cb_ident);
+        if (clp)
+                atomic_inc(&clp->cl_count);
+        spin_unlock(&nfs_client_lock);
+        return clp;
+}
+
+#if defined(CONFIG_NFS_V4_1)
+/*
+ * NFSv4.1 callback thread helper
+ * For CB_COMPOUND calls, find a client by IP address, protocol version,
+ * minorversion, and sessionID
+ *
+ * CREATE_SESSION triggers a CB_NULL ping from servers. The callback service
+ * sessionid can only be set after the CREATE_SESSION return, so a CB_NULL
+ * can arrive before the callback sessionid is set. For CB_NULL calls,
+ * find a client by IP address protocol version, and minorversion.
+ *
+ * Returns NULL if no such client
+ */
+struct nfs_client *
+nfs4_find_client_sessionid(const struct sockaddr *addr,
+                           struct nfs4_sessionid *sid, int is_cb_compound)
+{
+        struct nfs_client *clp;
+
+        spin_lock(&nfs_client_lock);
+        list_for_each_entry(clp, &nfs_client_list, cl_share_link) {
+                if (nfs4_cb_match_client(addr, clp, 1) == false)
+                        continue;
+
+                if (!nfs4_has_session(clp))
+                        continue;
+
+                /* Match sessionid unless cb_null call*/
+                if (is_cb_compound && (memcmp(clp->cl_session->sess_id.data,
+                    sid->data, NFS4_MAX_SESSIONID_LEN) != 0))
+                        continue;
+
+                atomic_inc(&clp->cl_count);
+                spin_unlock(&nfs_client_lock);
+                return clp;
+        }
+        spin_unlock(&nfs_client_lock);
+        return NULL;
+}
+
+#else /* CONFIG_NFS_V4_1 */
+
+struct nfs_client *
+nfs4_find_client_sessionid(const struct sockaddr *addr,
+                           struct nfs4_sessionid *sid, int is_cb_compound)
+{
+        return NULL;
+}
+#endif /* CONFIG_NFS_V4_1 */
+
+/*
  * Initialize the NFS4 callback service
  */
 static int nfs4_init_callback(struct nfs_client *clp)
@@ -1108,7 +1266,7 @@ static int nfs4_init_callback(struct nfs_client *clp)
                                 return error;
                 }
 
-                error = nfs_callback_up(clp->cl_minorversion,
+                error = nfs_callback_up(clp->cl_mvops->minor_version,
                                         clp->cl_rpcclient->cl_xprt);
                 if (error < 0) {
                         dprintk("%s: failed to start callback. Error = %d\n",
@@ -1125,10 +1283,8 @@ static int nfs4_init_callback(struct nfs_client *clp)
  */
 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) {
+        if (clp->cl_mvops->minor_version) {
                 struct nfs4_session *session = NULL;
                 /*
                  * Create the session and mark it expired.
@@ -1140,7 +1296,13 @@ static int nfs4_init_client_minor_version(struct nfs_client *clp)
                         return -ENOMEM;
 
                 clp->cl_session = session;
-                clp->cl_call_sync = _nfs4_call_sync_session;
+                /*
+                 * The create session reply races with the server back
+                 * channel probe. Mark the client NFS_CS_SESSION_INITING
+                 * so that the client back channel can find the
+                 * nfs_client struct
+                 */
+                clp->cl_cons_state = NFS_CS_SESSION_INITING;
         }
 #endif /* CONFIG_NFS_V4_1 */
 
@@ -1171,7 +1333,7 @@ static int nfs4_init_client(struct nfs_client *clp,
                                       1, flags & NFS_MOUNT_NORESVPORT);
         if (error < 0)
                 goto error;
-        memcpy(clp->cl_ipaddr, ip_addr, sizeof(clp->cl_ipaddr));
+        strlcpy(clp->cl_ipaddr, ip_addr, sizeof(clp->cl_ipaddr));
 
         error = nfs_idmap_new(clp);
         if (error < 0) {
@@ -1242,20 +1404,6 @@ 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.
@@ -1265,13 +1413,68 @@ static void nfs4_init_session(struct nfs_client *clp,
 static void nfs4_session_set_rwsize(struct nfs_server *server)
 {
 #ifdef CONFIG_NFS_V4_1
+        struct nfs4_session *sess;
+        u32 server_resp_sz;
+        u32 server_rqst_sz;
+
         if (!nfs4_has_session(server->nfs_client))
                 return;
-        server->rsize = server->nfs_client->cl_session->fc_attrs.max_resp_sz;
-        server->wsize = server->nfs_client->cl_session->fc_attrs.max_rqst_sz;
+        sess = server->nfs_client->cl_session;
+        server_resp_sz = sess->fc_attrs.max_resp_sz - nfs41_maxread_overhead;
+        server_rqst_sz = sess->fc_attrs.max_rqst_sz - nfs41_maxwrite_overhead;
+
+        if (server->rsize > server_resp_sz)
+                server->rsize = server_resp_sz;
+        if (server->wsize > server_rqst_sz)
+                server->wsize = server_rqst_sz;
 #endif /* CONFIG_NFS_V4_1 */
 }
 
+static int nfs4_server_common_setup(struct nfs_server *server,
+                struct nfs_fh *mntfh)
+{
+        struct nfs_fattr *fattr;
+        int error;
+
+        BUG_ON(!server->nfs_client);
+        BUG_ON(!server->nfs_client->rpc_ops);
+        BUG_ON(!server->nfs_client->rpc_ops->file_inode_ops);
+
+        fattr = nfs_alloc_fattr();
+        if (fattr == NULL)
+                return -ENOMEM;
+
+        /* We must ensure the session is initialised first */
+        error = nfs4_init_session(server);
+        if (error < 0)
+                goto out;
+
+        /* Probe the root fh to retrieve its FSID and filehandle */
+        error = nfs4_get_rootfh(server, mntfh);
+        if (error < 0)
+                goto out;
+
+        dprintk("Server FSID: %llx:%llx\n",
+                        (unsigned long long) server->fsid.major,
+                        (unsigned long long) server->fsid.minor);
+        dprintk("Mount FH: %d\n", mntfh->size);
+
+        nfs4_session_set_rwsize(server);
+
+        error = nfs_probe_fsinfo(server, mntfh, fattr);
+        if (error < 0)
+                goto out;
+
+        if (server->namelen == 0 || server->namelen > NFS4_MAXNAMLEN)
+                server->namelen = NFS4_MAXNAMLEN;
+
+        nfs_server_insert_lists(server);
+        server->mount_time = jiffies;
+out:
+        nfs_free_fattr(fattr);
+        return error;
+}
+
 /*
  * Create a version 4 volume record
  */
@@ -1288,7 +1491,9 @@ static int nfs4_init_server(struct nfs_server *server,
 
         /* Initialise the client representation from the mount data */
         server->flags = data->flags;
-        server->caps |= NFS_CAP_ATOMIC_OPEN;
+        server->caps |= NFS_CAP_ATOMIC_OPEN|NFS_CAP_CHANGE_ATTR|NFS_CAP_POSIX_LOCK;
+        if (!(data->flags & NFS_MOUNT_NORDIRPLUS))
+                        server->caps |= NFS_CAP_READDIRPLUS;
         server->options = data->options;
 
         /* Get a client record */
@@ -1331,7 +1536,6 @@ error:
 struct nfs_server *nfs4_create_server(const struct nfs_parsed_mount_data *data,
                                       struct nfs_fh *mntfh)
 {
-        struct nfs_fattr fattr;
         struct nfs_server *server;
         int error;
 
@@ -1346,41 +1550,10 @@ struct nfs_server *nfs4_create_server(const struct nfs_parsed_mount_data *data,
         if (error < 0)
                 goto error;
 
-        BUG_ON(!server->nfs_client);
-        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);
+        error = nfs4_server_common_setup(server, mntfh);
         if (error < 0)
                 goto error;
 
-        dprintk("Server FSID: %llx:%llx\n",
-                (unsigned long long) server->fsid.major,
-                (unsigned long long) server->fsid.minor);
-        dprintk("Mount FH: %d\n", mntfh->size);
-
-        nfs4_session_set_rwsize(server);
-
-        error = nfs_probe_fsinfo(server, mntfh, &fattr);
-        if (error < 0)
-                goto error;
-
-        if (server->namelen == 0 || server->namelen > NFS4_MAXNAMLEN)
-                server->namelen = NFS4_MAXNAMLEN;
-
-        BUG_ON(!server->nfs_client);
-        BUG_ON(!server->nfs_client->rpc_ops);
-        BUG_ON(!server->nfs_client->rpc_ops->file_inode_ops);
-
-        spin_lock(&nfs_client_lock);
-        list_add_tail(&server->client_link, &server->nfs_client->cl_superblocks);
-        list_add_tail(&server->master_link, &nfs_volume_list);
-        spin_unlock(&nfs_client_lock);
-
-        server->mount_time = jiffies;
         dprintk("<-- nfs4_create_server() = %p\n", server);
         return server;
 
@@ -1398,7 +1571,6 @@ struct nfs_server *nfs4_create_referral_server(struct nfs_clone_mount *data,
 {
         struct nfs_client *parent_client;
         struct nfs_server *server, *parent_server;
-        struct nfs_fattr fattr;
         int error;
 
         dprintk("--> nfs4_create_referral_server()\n");
@@ -1412,7 +1584,7 @@ struct nfs_server *nfs4_create_referral_server(struct nfs_clone_mount *data,
 
         /* Initialise the client representation from the parent server */
         nfs_server_copy_userdata(server, parent_server);
-        server->caps |= NFS_CAP_ATOMIC_OPEN;
+        server->caps |= NFS_CAP_ATOMIC_OPEN|NFS_CAP_CHANGE_ATTR;
 
         /* Get a client representation.
          * Note: NFSv4 always uses TCP, */
@@ -1423,7 +1595,7 @@ struct nfs_server *nfs4_create_referral_server(struct nfs_clone_mount *data,
                                 data->authflavor,
                                 parent_server->client->cl_xprt->prot,
                                 parent_server->client->cl_timeout,
-                                parent_client->cl_minorversion);
+                                parent_client->cl_mvops->minor_version);
         if (error < 0)
                 goto error;
 
@@ -1431,34 +1603,10 @@ struct nfs_server *nfs4_create_referral_server(struct nfs_clone_mount *data,
         if (error < 0)
                 goto error;
 
-        BUG_ON(!server->nfs_client);
-        BUG_ON(!server->nfs_client->rpc_ops);
-        BUG_ON(!server->nfs_client->rpc_ops->file_inode_ops);
-
-        /* Probe the root fh to retrieve its FSID and filehandle */
-        error = nfs4_path_walk(server, mntfh, data->mnt_path);
-        if (error < 0)
-                goto error;
-
-        /* probe the filesystem info for this server filesystem */
-        error = nfs_probe_fsinfo(server, mntfh, &fattr);
+        error = nfs4_server_common_setup(server, mntfh);
         if (error < 0)
                 goto error;
 
-        if (server->namelen == 0 || server->namelen > NFS4_MAXNAMLEN)
-                server->namelen = NFS4_MAXNAMLEN;
-
-        dprintk("Referral FSID: %llx:%llx\n",
-                (unsigned long long) server->fsid.major,
-                (unsigned long long) server->fsid.minor);
-
-        spin_lock(&nfs_client_lock);
-        list_add_tail(&server->client_link, &server->nfs_client->cl_superblocks);
-        list_add_tail(&server->master_link, &nfs_volume_list);
-        spin_unlock(&nfs_client_lock);
-
-        server->mount_time = jiffies;
-
         dprintk("<-- nfs_create_referral_server() = %p\n", server);
         return server;
 
@@ -1478,7 +1626,7 @@ struct nfs_server *nfs_clone_server(struct nfs_server *source,
                                     struct nfs_fattr *fattr)
 {
         struct nfs_server *server;
-        struct nfs_fattr fattr_fsinfo;
+        struct nfs_fattr *fattr_fsinfo;
         int error;
 
         dprintk("--> nfs_clone_server(,%llx:%llx,)\n",
@@ -1489,6 +1637,11 @@ struct nfs_server *nfs_clone_server(struct nfs_server *source,
         if (!server)
                 return ERR_PTR(-ENOMEM);
 
+        error = -ENOMEM;
+        fattr_fsinfo = nfs_alloc_fattr();
+        if (fattr_fsinfo == NULL)
+                goto out_free_server;
+
         /* Copy data from the source */
         server->nfs_client = source->nfs_client;
         atomic_inc(&server->nfs_client->cl_count);
@@ -1505,7 +1658,7 @@ struct nfs_server *nfs_clone_server(struct nfs_server *source,
                 nfs_init_server_aclclient(server);
 
         /* probe the filesystem info for this server filesystem */
-        error = nfs_probe_fsinfo(server, fh, &fattr_fsinfo);
+        error = nfs_probe_fsinfo(server, fh, fattr_fsinfo);
         if (error < 0)
                 goto out_free_server;
 
@@ -1520,17 +1673,15 @@ struct nfs_server *nfs_clone_server(struct nfs_server *source,
         if (error < 0)
                 goto out_free_server;
 
-        spin_lock(&nfs_client_lock);
-        list_add_tail(&server->client_link, &server->nfs_client->cl_superblocks);
-        list_add_tail(&server->master_link, &nfs_volume_list);
-        spin_unlock(&nfs_client_lock);
-
+        nfs_server_insert_lists(server);
         server->mount_time = jiffies;
 
+        nfs_free_fattr(fattr_fsinfo);
         dprintk("<-- nfs_clone_server() = %p\n", server);
         return server;
 
 out_free_server:
+        nfs_free_fattr(fattr_fsinfo);
         nfs_free_server(server);
         dprintk("<-- nfs_clone_server() = error %d\n", error);
         return ERR_PTR(error);
@@ -1545,7 +1696,7 @@ static void *nfs_server_list_next(struct seq_file *p, void *v, loff_t *pos);
 static void nfs_server_list_stop(struct seq_file *p, void *v);
 static int nfs_server_list_show(struct seq_file *m, void *v);
 
-static struct seq_operations nfs_server_list_ops = {
+static const struct seq_operations nfs_server_list_ops = {
         .start  = nfs_server_list_start,
         .next   = nfs_server_list_next,
         .stop   = nfs_server_list_stop,
@@ -1566,7 +1717,7 @@ static void *nfs_volume_list_next(struct seq_file *p, void *v, loff_t *pos);
 static void nfs_volume_list_stop(struct seq_file *p, void *v);
 static int nfs_volume_list_show(struct seq_file *m, void *v);
 
-static struct seq_operations nfs_volume_list_ops = {
+static const struct seq_operations nfs_volume_list_ops = {
         .start  = nfs_volume_list_start,
         .next   = nfs_volume_list_next,
         .stop   = nfs_volume_list_stop,
diff --git a/fs/nfs/delegation.c b/fs/nfs/delegation.c
index af05b918cb5b..364e4328f392 100644
--- a/fs/nfs/delegation.c
+++ b/fs/nfs/delegation.c
@@ -10,6 +10,7 @@
 #include <linux/kthread.h>
 #include <linux/module.h>
 #include <linux/sched.h>
+#include <linux/slab.h>
 #include <linux/spinlock.h>
 
 #include <linux/nfs4.h>
@@ -22,6 +23,8 @@
 
 static void nfs_do_free_delegation(struct nfs_delegation *delegation)
 {
+        if (delegation->cred)
+                put_rpccred(delegation->cred);
         kfree(delegation);
 }
 
@@ -34,20 +37,26 @@ static void nfs_free_delegation_callback(struct rcu_head *head)
 
 static void nfs_free_delegation(struct nfs_delegation *delegation)
 {
-        struct rpc_cred *cred;
-
-        cred = rcu_dereference(delegation->cred);
-        rcu_assign_pointer(delegation->cred, NULL);
         call_rcu(&delegation->rcu, nfs_free_delegation_callback);
-        if (cred)
-                put_rpccred(cred);
 }
 
+/**
+ * nfs_mark_delegation_referenced - set delegation's REFERENCED flag
+ * @delegation: delegation to process
+ *
+ */
 void nfs_mark_delegation_referenced(struct nfs_delegation *delegation)
 {
         set_bit(NFS_DELEGATION_REFERENCED, &delegation->flags);
 }
 
+/**
+ * nfs_have_delegation - check if inode has a delegation
+ * @inode: inode to check
+ * @flags: delegation types to check for
+ *
+ * Returns one if inode has the indicated delegation, otherwise zero.
+ */
 int nfs_have_delegation(struct inode *inode, fmode_t flags)
 {
         struct nfs_delegation *delegation;
@@ -73,25 +82,25 @@ static int nfs_delegation_claim_locks(struct nfs_open_context *ctx, struct nfs4_
         if (inode->i_flock == NULL)
                 goto out;
 
-        /* Protect inode->i_flock using the BKL */
-        lock_kernel();
+        /* Protect inode->i_flock using the file locks lock */
+        lock_flocks();
         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();
+                unlock_flocks();
                 status = nfs4_lock_delegation_recall(state, fl);
                 if (status < 0)
                         goto out;
-                lock_kernel();
+                lock_flocks();
         }
-        unlock_kernel();
+        unlock_flocks();
 out:
         return status;
 }
 
-static void nfs_delegation_claim_opens(struct inode *inode, const nfs4_stateid *stateid)
+static int nfs_delegation_claim_opens(struct inode *inode, const nfs4_stateid *stateid)
 {
         struct nfs_inode *nfsi = NFS_I(inode);
         struct nfs_open_context *ctx;
@@ -115,32 +124,52 @@ again:
                         err = nfs_delegation_claim_locks(ctx, state);
                 put_nfs_open_context(ctx);
                 if (err != 0)
-                        return;
+                        return err;
                 goto again;
         }
         spin_unlock(&inode->i_lock);
+        return 0;
 }
 
-/*
- * Set up a delegation on an inode
+/**
+ * nfs_inode_reclaim_delegation - process a delegation reclaim request
+ * @inode: inode to process
+ * @cred: credential to use for request
+ * @res: new delegation state from server
+ *
  */
-void nfs_inode_reclaim_delegation(struct inode *inode, struct rpc_cred *cred, struct nfs_openres *res)
+void nfs_inode_reclaim_delegation(struct inode *inode, struct rpc_cred *cred,
+                                  struct nfs_openres *res)
 {
-        struct nfs_delegation *delegation = NFS_I(inode)->delegation;
-        struct rpc_cred *oldcred;
+        struct nfs_delegation *delegation;
+        struct rpc_cred *oldcred = NULL;
 
-        if (delegation == NULL)
-                return;
-        memcpy(delegation->stateid.data, res->delegation.data,
-                        sizeof(delegation->stateid.data));
-        delegation->type = res->delegation_type;
-        delegation->maxsize = res->maxsize;
-        oldcred = delegation->cred;
-        delegation->cred = get_rpccred(cred);
-        clear_bit(NFS_DELEGATION_NEED_RECLAIM, &delegation->flags);
-        NFS_I(inode)->delegation_state = delegation->type;
-        smp_wmb();
-        put_rpccred(oldcred);
+        rcu_read_lock();
+        delegation = rcu_dereference(NFS_I(inode)->delegation);
+        if (delegation != NULL) {
+                spin_lock(&delegation->lock);
+                if (delegation->inode != NULL) {
+                        memcpy(delegation->stateid.data, res->delegation.data,
+                               sizeof(delegation->stateid.data));
+                        delegation->type = res->delegation_type;
+                        delegation->maxsize = res->maxsize;
+                        oldcred = delegation->cred;
+                        delegation->cred = get_rpccred(cred);
+                        clear_bit(NFS_DELEGATION_NEED_RECLAIM,
+                                  &delegation->flags);
+                        NFS_I(inode)->delegation_state = delegation->type;
+                        spin_unlock(&delegation->lock);
+                        put_rpccred(oldcred);
+                        rcu_read_unlock();
+                } else {
+                        /* We appear to have raced with a delegation return. */
+                        spin_unlock(&delegation->lock);
+                        rcu_read_unlock();
+                        nfs_inode_set_delegation(inode, cred, res);
+                }
+        } else {
+                rcu_read_unlock();
+        }
 }
 
 static int nfs_do_return_delegation(struct inode *inode, struct nfs_delegation *delegation, int issync)
@@ -163,40 +192,58 @@ static struct inode *nfs_delegation_grab_inode(struct nfs_delegation *delegation
         return inode;
 }
 
-static struct nfs_delegation *nfs_detach_delegation_locked(struct nfs_inode *nfsi, const nfs4_stateid *stateid)
+static struct nfs_delegation *
+nfs_detach_delegation_locked(struct nfs_inode *nfsi,
+                             struct nfs_server *server)
 {
-        struct nfs_delegation *delegation = rcu_dereference(nfsi->delegation);
+        struct nfs_delegation *delegation =
+                rcu_dereference_protected(nfsi->delegation,
+                                lockdep_is_held(&server->nfs_client->cl_lock));
 
         if (delegation == NULL)
                 goto nomatch;
+
         spin_lock(&delegation->lock);
-        if (stateid != NULL && memcmp(delegation->stateid.data, stateid->data,
-                                sizeof(delegation->stateid.data)) != 0)
-                goto nomatch_unlock;
         list_del_rcu(&delegation->super_list);
         delegation->inode = NULL;
         nfsi->delegation_state = 0;
         rcu_assign_pointer(nfsi->delegation, NULL);
         spin_unlock(&delegation->lock);
         return delegation;
-nomatch_unlock:
-        spin_unlock(&delegation->lock);
 nomatch:
         return NULL;
 }
 
-/*
- * Set up a delegation on an inode
+static struct nfs_delegation *nfs_detach_delegation(struct nfs_inode *nfsi,
+                                                    struct nfs_server *server)
+{
+        struct nfs_client *clp = server->nfs_client;
+        struct nfs_delegation *delegation;
+
+        spin_lock(&clp->cl_lock);
+        delegation = nfs_detach_delegation_locked(nfsi, server);
+        spin_unlock(&clp->cl_lock);
+        return delegation;
+}
+
+/**
+ * nfs_inode_set_delegation - set up a delegation on an inode
+ * @inode: inode to which delegation applies
+ * @cred: cred to use for subsequent delegation processing
+ * @res: new delegation state from server
+ *
+ * Returns zero on success, or a negative errno value.
  */
 int nfs_inode_set_delegation(struct inode *inode, struct rpc_cred *cred, struct nfs_openres *res)
 {
-        struct nfs_client *clp = NFS_SERVER(inode)->nfs_client;
+        struct nfs_server *server = NFS_SERVER(inode);
+        struct nfs_client *clp = server->nfs_client;
         struct nfs_inode *nfsi = NFS_I(inode);
-        struct nfs_delegation *delegation;
+        struct nfs_delegation *delegation, *old_delegation;
         struct nfs_delegation *freeme = NULL;
         int status = 0;
 
-        delegation = kmalloc(sizeof(*delegation), GFP_KERNEL);
+        delegation = kmalloc(sizeof(*delegation), GFP_NOFS);
         if (delegation == NULL)
                 return -ENOMEM;
         memcpy(delegation->stateid.data, res->delegation.data,
@@ -210,10 +257,12 @@ int nfs_inode_set_delegation(struct inode *inode, struct rpc_cred *cred, struct
         spin_lock_init(&delegation->lock);
 
         spin_lock(&clp->cl_lock);
-        if (rcu_dereference(nfsi->delegation) != NULL) {
-                if (memcmp(&delegation->stateid, &nfsi->delegation->stateid,
-                                        sizeof(delegation->stateid)) == 0 &&
-                                delegation->type == nfsi->delegation->type) {
+        old_delegation = rcu_dereference_protected(nfsi->delegation,
+                                        lockdep_is_held(&clp->cl_lock));
+        if (old_delegation != NULL) {
+                if (memcmp(&delegation->stateid, &old_delegation->stateid,
+                                        sizeof(old_delegation->stateid)) == 0 &&
+                                delegation->type == old_delegation->type) {
                         goto out;
                 }
                 /*
@@ -223,14 +272,14 @@ int nfs_inode_set_delegation(struct inode *inode, struct rpc_cred *cred, struct
                 dfprintk(FILE, "%s: server %s handed out "
                                 "a duplicate delegation!\n",
                                 __func__, clp->cl_hostname);
-                if (delegation->type <= nfsi->delegation->type) {
+                if (delegation->type <= old_delegation->type) {
                         freeme = delegation;
                         delegation = NULL;
                         goto out;
                 }
-                freeme = nfs_detach_delegation_locked(nfsi, NULL);
+                freeme = nfs_detach_delegation_locked(nfsi, server);
         }
-        list_add_rcu(&delegation->super_list, &clp->cl_delegations);
+        list_add_rcu(&delegation->super_list, &server->delegations);
         nfsi->delegation_state = delegation->type;
         rcu_assign_pointer(nfsi->delegation, delegation);
         delegation = NULL;
@@ -249,153 +298,211 @@ out:
         return status;
 }
 
-/* Sync all data to disk upon delegation return */
-static void nfs_msync_inode(struct inode *inode)
-{
-        filemap_fdatawrite(inode->i_mapping);
-        nfs_wb_all(inode);
-        filemap_fdatawait(inode->i_mapping);
-}
-
 /*
  * Basic procedure for returning a delegation to the server
  */
-static int __nfs_inode_return_delegation(struct inode *inode, struct nfs_delegation *delegation)
+static int __nfs_inode_return_delegation(struct inode *inode, struct nfs_delegation *delegation, int issync)
 {
         struct nfs_inode *nfsi = NFS_I(inode);
+        int err;
 
-        nfs_msync_inode(inode);
         /*
          * Guard against new delegated open/lock/unlock calls and against
          * state recovery
          */
         down_write(&nfsi->rwsem);
-        nfs_delegation_claim_opens(inode, &delegation->stateid);
+        err = nfs_delegation_claim_opens(inode, &delegation->stateid);
         up_write(&nfsi->rwsem);
-        nfs_msync_inode(inode);
+        if (err)
+                goto out;
 
-        return nfs_do_return_delegation(inode, delegation, 1);
+        err = nfs_do_return_delegation(inode, delegation, issync);
+out:
+        return err;
 }
 
-/*
- * Return all delegations that have been marked for return
+/**
+ * nfs_client_return_marked_delegations - return previously marked delegations
+ * @clp: nfs_client to process
+ *
+ * Returns zero on success, or a negative errno value.
  */
-void nfs_client_return_marked_delegations(struct nfs_client *clp)
+int nfs_client_return_marked_delegations(struct nfs_client *clp)
 {
         struct nfs_delegation *delegation;
+        struct nfs_server *server;
         struct inode *inode;
+        int err = 0;
 
 restart:
         rcu_read_lock();
-        list_for_each_entry_rcu(delegation, &clp->cl_delegations, super_list) {
-                if (!test_and_clear_bit(NFS_DELEGATION_RETURN, &delegation->flags))
-                        continue;
-                inode = nfs_delegation_grab_inode(delegation);
-                if (inode == NULL)
-                        continue;
-                spin_lock(&clp->cl_lock);
-                delegation = nfs_detach_delegation_locked(NFS_I(inode), NULL);
-                spin_unlock(&clp->cl_lock);
-                rcu_read_unlock();
-                if (delegation != NULL)
-                        __nfs_inode_return_delegation(inode, delegation);
-                iput(inode);
-                goto restart;
+        list_for_each_entry_rcu(server, &clp->cl_superblocks, client_link) {
+                list_for_each_entry_rcu(delegation, &server->delegations,
+                                                                super_list) {
+                        if (!test_and_clear_bit(NFS_DELEGATION_RETURN,
+                                                        &delegation->flags))
+                                continue;
+                        inode = nfs_delegation_grab_inode(delegation);
+                        if (inode == NULL)
+                                continue;
+                        delegation = nfs_detach_delegation(NFS_I(inode),
+                                                                server);
+                        rcu_read_unlock();
+
+                        if (delegation != NULL) {
+                                filemap_flush(inode->i_mapping);
+                                err = __nfs_inode_return_delegation(inode,
+                                                                delegation, 0);
+                        }
+                        iput(inode);
+                        if (!err)
+                                goto restart;
+                        set_bit(NFS4CLNT_DELEGRETURN, &clp->cl_state);
+                        return err;
+                }
         }
         rcu_read_unlock();
+        return 0;
 }
 
-/*
- * This function returns the delegation without reclaiming opens
- * or protecting against delegation reclaims.
- * It is therefore really only safe to be called from
- * nfs4_clear_inode()
+/**
+ * nfs_inode_return_delegation_noreclaim - return delegation, don't reclaim opens
+ * @inode: inode to process
+ *
+ * Does not protect against delegation reclaims, therefore really only safe
+ * to be called from nfs4_clear_inode().
  */
 void nfs_inode_return_delegation_noreclaim(struct inode *inode)
 {
-        struct nfs_client *clp = NFS_SERVER(inode)->nfs_client;
+        struct nfs_server *server = NFS_SERVER(inode);
         struct nfs_inode *nfsi = NFS_I(inode);
         struct nfs_delegation *delegation;
 
-        if (rcu_dereference(nfsi->delegation) != NULL) {
-                spin_lock(&clp->cl_lock);
-                delegation = nfs_detach_delegation_locked(nfsi, NULL);
-                spin_unlock(&clp->cl_lock);
+        if (rcu_access_pointer(nfsi->delegation) != NULL) {
+                delegation = nfs_detach_delegation(nfsi, server);
                 if (delegation != NULL)
                         nfs_do_return_delegation(inode, delegation, 0);
         }
 }
 
+/**
+ * nfs_inode_return_delegation - synchronously return a delegation
+ * @inode: inode to process
+ *
+ * Returns zero on success, or a negative errno value.
+ */
 int nfs_inode_return_delegation(struct inode *inode)
 {
-        struct nfs_client *clp = NFS_SERVER(inode)->nfs_client;
+        struct nfs_server *server = NFS_SERVER(inode);
         struct nfs_inode *nfsi = NFS_I(inode);
         struct nfs_delegation *delegation;
         int err = 0;
 
-        if (rcu_dereference(nfsi->delegation) != NULL) {
-                spin_lock(&clp->cl_lock);
-                delegation = nfs_detach_delegation_locked(nfsi, NULL);
-                spin_unlock(&clp->cl_lock);
-                if (delegation != NULL)
-                        err = __nfs_inode_return_delegation(inode, delegation);
+        if (rcu_access_pointer(nfsi->delegation) != NULL) {
+                delegation = nfs_detach_delegation(nfsi, server);
+                if (delegation != NULL) {
+                        nfs_wb_all(inode);
+                        err = __nfs_inode_return_delegation(inode, delegation, 1);
+                }
         }
         return err;
 }
 
-static void nfs_mark_return_delegation(struct nfs_client *clp, struct nfs_delegation *delegation)
+static void nfs_mark_return_delegation(struct nfs_delegation *delegation)
 {
+        struct nfs_client *clp = NFS_SERVER(delegation->inode)->nfs_client;
+
         set_bit(NFS_DELEGATION_RETURN, &delegation->flags);
         set_bit(NFS4CLNT_DELEGRETURN, &clp->cl_state);
 }
 
-/*
- * Return all delegations associated to a super block
+/**
+ * nfs_super_return_all_delegations - return delegations for one superblock
+ * @sb: sb to process
+ *
  */
 void nfs_super_return_all_delegations(struct super_block *sb)
 {
-        struct nfs_client *clp = NFS_SB(sb)->nfs_client;
+        struct nfs_server *server = NFS_SB(sb);
+        struct nfs_client *clp = server->nfs_client;
         struct nfs_delegation *delegation;
 
         if (clp == NULL)
                 return;
+
         rcu_read_lock();
-        list_for_each_entry_rcu(delegation, &clp->cl_delegations, super_list) {
+        list_for_each_entry_rcu(delegation, &server->delegations, super_list) {
                 spin_lock(&delegation->lock);
-                if (delegation->inode != NULL && delegation->inode->i_sb == sb)
-                        set_bit(NFS_DELEGATION_RETURN, &delegation->flags);
+                set_bit(NFS_DELEGATION_RETURN, &delegation->flags);
                 spin_unlock(&delegation->lock);
         }
         rcu_read_unlock();
-        nfs_client_return_marked_delegations(clp);
+
+        if (nfs_client_return_marked_delegations(clp) != 0)
+                nfs4_schedule_state_manager(clp);
 }
 
-static void nfs_client_mark_return_all_delegations(struct nfs_client *clp)
+static void nfs_mark_return_all_delegation_types(struct nfs_server *server,
+                                                 fmode_t flags)
 {
         struct nfs_delegation *delegation;
 
-        rcu_read_lock();
-        list_for_each_entry_rcu(delegation, &clp->cl_delegations, super_list) {
-                set_bit(NFS_DELEGATION_RETURN, &delegation->flags);
-                set_bit(NFS4CLNT_DELEGRETURN, &clp->cl_state);
+        list_for_each_entry_rcu(delegation, &server->delegations, super_list) {
+                if ((delegation->type == (FMODE_READ|FMODE_WRITE)) && !(flags & FMODE_WRITE))
+                        continue;
+                if (delegation->type & flags)
+                        nfs_mark_return_delegation(delegation);
         }
+}
+
+static void nfs_client_mark_return_all_delegation_types(struct nfs_client *clp,
+                                                        fmode_t flags)
+{
+        struct nfs_server *server;
+
+        rcu_read_lock();
+        list_for_each_entry_rcu(server, &clp->cl_superblocks, client_link)
+                nfs_mark_return_all_delegation_types(server, flags);
         rcu_read_unlock();
 }
 
+static void nfs_client_mark_return_all_delegations(struct nfs_client *clp)
+{
+        nfs_client_mark_return_all_delegation_types(clp, FMODE_READ|FMODE_WRITE);
+}
+
 static void nfs_delegation_run_state_manager(struct nfs_client *clp)
 {
         if (test_bit(NFS4CLNT_DELEGRETURN, &clp->cl_state))
                 nfs4_schedule_state_manager(clp);
 }
 
-void nfs_expire_all_delegations(struct nfs_client *clp)
+/**
+ * nfs_expire_all_delegation_types
+ * @clp: client to process
+ * @flags: delegation types to expire
+ *
+ */
+void nfs_expire_all_delegation_types(struct nfs_client *clp, fmode_t flags)
 {
-        nfs_client_mark_return_all_delegations(clp);
+        nfs_client_mark_return_all_delegation_types(clp, flags);
         nfs_delegation_run_state_manager(clp);
 }
 
-/*
- * Return all delegations following an NFS4ERR_CB_PATH_DOWN error.
+/**
+ * nfs_expire_all_delegations
+ * @clp: client to process
+ *
+ */
+void nfs_expire_all_delegations(struct nfs_client *clp)
+{
+        nfs_expire_all_delegation_types(clp, FMODE_READ|FMODE_WRITE);
+}
+
+/**
+ * nfs_handle_cb_pathdown - return all delegations after NFS4ERR_CB_PATH_DOWN
+ * @clp: client to process
+ *
  */
 void nfs_handle_cb_pathdown(struct nfs_client *clp)
 {
@@ -404,56 +511,69 @@ void nfs_handle_cb_pathdown(struct nfs_client *clp)
         nfs_client_mark_return_all_delegations(clp);
 }
 
-static void nfs_client_mark_return_unreferenced_delegations(struct nfs_client *clp)
+static void nfs_mark_return_unreferenced_delegations(struct nfs_server *server)
 {
         struct nfs_delegation *delegation;
 
-        rcu_read_lock();
-        list_for_each_entry_rcu(delegation, &clp->cl_delegations, super_list) {
+        list_for_each_entry_rcu(delegation, &server->delegations, super_list) {
                 if (test_and_clear_bit(NFS_DELEGATION_REFERENCED, &delegation->flags))
                         continue;
-                set_bit(NFS_DELEGATION_RETURN, &delegation->flags);
-                set_bit(NFS4CLNT_DELEGRETURN, &clp->cl_state);
+                nfs_mark_return_delegation(delegation);
         }
-        rcu_read_unlock();
 }
 
+/**
+ * nfs_expire_unreferenced_delegations - Eliminate unused delegations
+ * @clp: nfs_client to process
+ *
+ */
 void nfs_expire_unreferenced_delegations(struct nfs_client *clp)
 {
-        nfs_client_mark_return_unreferenced_delegations(clp);
+        struct nfs_server *server;
+
+        rcu_read_lock();
+        list_for_each_entry_rcu(server, &clp->cl_superblocks, client_link)
+                nfs_mark_return_unreferenced_delegations(server);
+        rcu_read_unlock();
+
         nfs_delegation_run_state_manager(clp);
 }
 
-/*
- * Asynchronous delegation recall!
+/**
+ * nfs_async_inode_return_delegation - asynchronously return a delegation
+ * @inode: inode to process
+ * @stateid: state ID information from CB_RECALL arguments
+ *
+ * Returns zero on success, or a negative errno value.
  */
-int nfs_async_inode_return_delegation(struct inode *inode, const nfs4_stateid *stateid)
+int nfs_async_inode_return_delegation(struct inode *inode,
+                                      const nfs4_stateid *stateid)
 {
         struct nfs_client *clp = NFS_SERVER(inode)->nfs_client;
         struct nfs_delegation *delegation;
 
         rcu_read_lock();
         delegation = rcu_dereference(NFS_I(inode)->delegation);
-        if (delegation == NULL || memcmp(delegation->stateid.data, stateid->data,
-                                sizeof(delegation->stateid.data)) != 0) {
+
+        if (!clp->cl_mvops->validate_stateid(delegation, stateid)) {
                 rcu_read_unlock();
                 return -ENOENT;
         }
-        nfs_mark_return_delegation(clp, delegation);
+        nfs_mark_return_delegation(delegation);
         rcu_read_unlock();
+
         nfs_delegation_run_state_manager(clp);
         return 0;
 }
 
-/*
- * Retrieve the inode associated with a delegation
- */
-struct inode *nfs_delegation_find_inode(struct nfs_client *clp, const struct nfs_fh *fhandle)
+static struct inode *
+nfs_delegation_find_inode_server(struct nfs_server *server,
+                                 const struct nfs_fh *fhandle)
 {
         struct nfs_delegation *delegation;
         struct inode *res = NULL;
-        rcu_read_lock();
-        list_for_each_entry_rcu(delegation, &clp->cl_delegations, super_list) {
+
+        list_for_each_entry_rcu(delegation, &server->delegations, super_list) {
                 spin_lock(&delegation->lock);
                 if (delegation->inode != NULL &&
                     nfs_compare_fh(fhandle, &NFS_I(delegation->inode)->fh) == 0) {
@@ -463,49 +583,121 @@ struct inode *nfs_delegation_find_inode(struct nfs_client *clp, const struct nfs
                 if (res != NULL)
                         break;
         }
+        return res;
+}
+
+/**
+ * nfs_delegation_find_inode - retrieve the inode associated with a delegation
+ * @clp: client state handle
+ * @fhandle: filehandle from a delegation recall
+ *
+ * Returns pointer to inode matching "fhandle," or NULL if a matching inode
+ * cannot be found.
+ */
+struct inode *nfs_delegation_find_inode(struct nfs_client *clp,
+                                        const struct nfs_fh *fhandle)
+{
+        struct nfs_server *server;
+        struct inode *res = NULL;
+
+        rcu_read_lock();
+        list_for_each_entry_rcu(server, &clp->cl_superblocks, client_link) {
+                res = nfs_delegation_find_inode_server(server, fhandle);
+                if (res != NULL)
+                        break;
+        }
         rcu_read_unlock();
         return res;
 }
 
-/*
- * Mark all delegations as needing to be reclaimed
+static void nfs_delegation_mark_reclaim_server(struct nfs_server *server)
+{
+        struct nfs_delegation *delegation;
+
+        list_for_each_entry_rcu(delegation, &server->delegations, super_list)
+                set_bit(NFS_DELEGATION_NEED_RECLAIM, &delegation->flags);
+}
+
+/**
+ * nfs_delegation_mark_reclaim - mark all delegations as needing to be reclaimed
+ * @clp: nfs_client to process
+ *
  */
 void nfs_delegation_mark_reclaim(struct nfs_client *clp)
 {
-        struct nfs_delegation *delegation;
+        struct nfs_server *server;
+
         rcu_read_lock();
-        list_for_each_entry_rcu(delegation, &clp->cl_delegations, super_list)
-                set_bit(NFS_DELEGATION_NEED_RECLAIM, &delegation->flags);
+        list_for_each_entry_rcu(server, &clp->cl_superblocks, client_link)
+                nfs_delegation_mark_reclaim_server(server);
         rcu_read_unlock();
 }
 
-/*
- * Reap all unclaimed delegations after reboot recovery is done
+/**
+ * nfs_delegation_reap_unclaimed - reap unclaimed delegations after reboot recovery is done
+ * @clp: nfs_client to process
+ *
  */
 void nfs_delegation_reap_unclaimed(struct nfs_client *clp)
 {
         struct nfs_delegation *delegation;
+        struct nfs_server *server;
         struct inode *inode;
+
 restart:
         rcu_read_lock();
-        list_for_each_entry_rcu(delegation, &clp->cl_delegations, super_list) {
-                if (test_bit(NFS_DELEGATION_NEED_RECLAIM, &delegation->flags) == 0)
-                        continue;
-                inode = nfs_delegation_grab_inode(delegation);
-                if (inode == NULL)
-                        continue;
-                spin_lock(&clp->cl_lock);
-                delegation = nfs_detach_delegation_locked(NFS_I(inode), NULL);
-                spin_unlock(&clp->cl_lock);
-                rcu_read_unlock();
-                if (delegation != NULL)
-                        nfs_free_delegation(delegation);
-                iput(inode);
-                goto restart;
+        list_for_each_entry_rcu(server, &clp->cl_superblocks, client_link) {
+                list_for_each_entry_rcu(delegation, &server->delegations,
+                                                                super_list) {
+                        if (test_bit(NFS_DELEGATION_NEED_RECLAIM,
+                                                &delegation->flags) == 0)
+                                continue;
+                        inode = nfs_delegation_grab_inode(delegation);
+                        if (inode == NULL)
+                                continue;
+                        delegation = nfs_detach_delegation(NFS_I(inode),
+                                                                server);
+                        rcu_read_unlock();
+
+                        if (delegation != NULL)
+                                nfs_free_delegation(delegation);
+                        iput(inode);
+                        goto restart;
+                }
         }
         rcu_read_unlock();
 }
 
+/**
+ * nfs_delegations_present - check for existence of delegations
+ * @clp: client state handle
+ *
+ * Returns one if there are any nfs_delegation structures attached
+ * to this nfs_client.
+ */
+int nfs_delegations_present(struct nfs_client *clp)
+{
+        struct nfs_server *server;
+        int ret = 0;
+
+        rcu_read_lock();
+        list_for_each_entry_rcu(server, &clp->cl_superblocks, client_link)
+                if (!list_empty(&server->delegations)) {
+                        ret = 1;
+                        break;
+                }
+        rcu_read_unlock();
+        return ret;
+}
+
+/**
+ * nfs4_copy_delegation_stateid - Copy inode's state ID information
+ * @dst: stateid data structure to fill in
+ * @inode: inode to check
+ *
+ * Returns one and fills in "dst->data" * if inode had a delegation,
+ * otherwise zero is returned.
+ */
 int nfs4_copy_delegation_stateid(nfs4_stateid *dst, struct inode *inode)
 {
         struct nfs_inode *nfsi = NFS_I(inode);
diff --git a/fs/nfs/delegation.h b/fs/nfs/delegation.h
index 09f383795174..d9322e490c56 100644
--- a/fs/nfs/delegation.h
+++ b/fs/nfs/delegation.h
@@ -40,9 +40,11 @@ void nfs_inode_return_delegation_noreclaim(struct inode *inode);
 struct inode *nfs_delegation_find_inode(struct nfs_client *clp, const struct nfs_fh *fhandle);
 void nfs_super_return_all_delegations(struct super_block *sb);
 void nfs_expire_all_delegations(struct nfs_client *clp);
+void nfs_expire_all_delegation_types(struct nfs_client *clp, fmode_t flags);
 void nfs_expire_unreferenced_delegations(struct nfs_client *clp);
 void nfs_handle_cb_pathdown(struct nfs_client *clp);
-void nfs_client_return_marked_delegations(struct nfs_client *clp);
+int nfs_client_return_marked_delegations(struct nfs_client *clp);
+int nfs_delegations_present(struct nfs_client *clp);
 
 void nfs_delegation_mark_reclaim(struct nfs_client *clp);
 void nfs_delegation_reap_unclaimed(struct nfs_client *clp);
@@ -68,4 +70,10 @@ static inline int nfs_inode_return_delegation(struct inode *inode)
 }
 #endif
 
+static inline int nfs_have_delegated_attributes(struct inode *inode)
+{
+        return nfs_have_delegation(inode, FMODE_READ) &&
+                !(NFS_I(inode)->cache_validity & NFS_INO_REVAL_FORCED);
+}
+
 #endif
diff --git a/fs/nfs/dir.c b/fs/nfs/dir.c
index 89f98e9a024b..abe4f0c8dc5f 100644
--- a/fs/nfs/dir.c
+++ b/fs/nfs/dir.c
@@ -29,16 +29,17 @@
 #include <linux/nfs_fs.h>
 #include <linux/nfs_mount.h>
 #include <linux/pagemap.h>
-#include <linux/smp_lock.h>
 #include <linux/pagevec.h>
 #include <linux/namei.h>
 #include <linux/mount.h>
 #include <linux/sched.h>
+#include <linux/kmemleak.h>
+#include <linux/xattr.h>
 
-#include "nfs4_fs.h"
 #include "delegation.h"
 #include "iostat.h"
 #include "internal.h"
+#include "fscache.h"
 
 /* #define NFS_DEBUG_VERBOSE 1 */
 
@@ -54,8 +55,9 @@ static int nfs_link(struct dentry *, struct inode *, struct dentry *);
 static int nfs_mknod(struct inode *, struct dentry *, int, dev_t);
 static int nfs_rename(struct inode *, struct dentry *,
                       struct inode *, struct dentry *);
-static int nfs_fsync_dir(struct file *, struct dentry *, int);
+static int nfs_fsync_dir(struct file *, int);
 static loff_t nfs_llseek_dir(struct file *, loff_t, int);
+static void nfs_readdir_clear_array(struct page*);
 
 const struct file_operations nfs_dir_operations = {
         .llseek         = nfs_llseek_dir,
@@ -81,6 +83,10 @@ const struct inode_operations nfs_dir_inode_operations = {
         .setattr        = nfs_setattr,
 };
 
+const struct address_space_operations nfs_dir_aops = {
+        .freepage = nfs_readdir_clear_array,
+};
+
 #ifdef CONFIG_NFS_V3
 const struct inode_operations nfs3_dir_inode_operations = {
         .create         = nfs_create,
@@ -105,8 +111,9 @@ const struct inode_operations nfs3_dir_inode_operations = {
 #ifdef CONFIG_NFS_V4
 
 static struct dentry *nfs_atomic_lookup(struct inode *, struct dentry *, struct nameidata *);
+static int nfs_open_create(struct inode *dir, struct dentry *dentry, int mode, struct nameidata *nd);
 const struct inode_operations nfs4_dir_inode_operations = {
-        .create         = nfs_create,
+        .create         = nfs_open_create,
         .lookup         = nfs_atomic_lookup,
         .link           = nfs_link,
         .unlink         = nfs_unlink,
@@ -118,9 +125,10 @@ const struct inode_operations nfs4_dir_inode_operations = {
         .permission     = nfs_permission,
         .getattr        = nfs_getattr,
         .setattr        = nfs_setattr,
-        .getxattr       = nfs4_getxattr,
-        .setxattr       = nfs4_setxattr,
-        .listxattr      = nfs4_listxattr,
+        .getxattr       = generic_getxattr,
+        .setxattr       = generic_setxattr,
+        .listxattr      = generic_listxattr,
+        .removexattr    = generic_removexattr,
 };
 
 #endif /* CONFIG_NFS_V4 */
@@ -141,54 +149,219 @@ nfs_opendir(struct inode *inode, struct file *filp)
 
         /* Call generic open code in order to cache credentials */
         res = nfs_open(inode, filp);
+        if (filp->f_path.dentry == filp->f_path.mnt->mnt_root) {
+                /* This is a mountpoint, so d_revalidate will never
+                 * have been called, so we need to refresh the
+                 * inode (for close-open consistency) ourselves.
+                 */
+                __nfs_revalidate_inode(NFS_SERVER(inode), inode);
+        }
         return res;
 }
 
-typedef __be32 * (*decode_dirent_t)(__be32 *, struct nfs_entry *, int);
+struct nfs_cache_array_entry {
+        u64 cookie;
+        u64 ino;
+        struct qstr string;
+        unsigned char d_type;
+};
+
+struct nfs_cache_array {
+        unsigned int size;
+        int eof_index;
+        u64 last_cookie;
+        struct nfs_cache_array_entry array[0];
+};
+
+typedef int (*decode_dirent_t)(struct xdr_stream *, struct nfs_entry *, int);
 typedef struct {
         struct file     *file;
         struct page     *page;
         unsigned long   page_index;
-        __be32          *ptr;
         u64             *dir_cookie;
+        u64             last_cookie;
         loff_t          current_index;
-        struct nfs_entry *entry;
         decode_dirent_t decode;
-        int             plus;
+
         unsigned long   timestamp;
         unsigned long   gencount;
-        int             timestamp_valid;
+        unsigned int    cache_entry_index;
+        unsigned int    plus:1;
+        unsigned int    eof:1;
 } nfs_readdir_descriptor_t;
 
-/* Now we cache directories properly, by stuffing the dirent
- * data directly in the page cache.
- *
- * Inode invalidation due to refresh etc. takes care of
- * _everything_, no sloppy entry flushing logic, no extraneous
- * copying, network direct to page cache, the way it was meant
- * to be.
- *
- * NOTE: Dirent information verification is done always by the
- *       page-in of the RPC reply, nowhere else, this simplies
- *       things substantially.
+/*
+ * The caller is responsible for calling nfs_readdir_release_array(page)
  */
 static
-int nfs_readdir_filler(nfs_readdir_descriptor_t *desc, struct page *page)
+struct nfs_cache_array *nfs_readdir_get_array(struct page *page)
+{
+        void *ptr;
+        if (page == NULL)
+                return ERR_PTR(-EIO);
+        ptr = kmap(page);
+        if (ptr == NULL)
+                return ERR_PTR(-ENOMEM);
+        return ptr;
+}
+
+static
+void nfs_readdir_release_array(struct page *page)
+{
+        kunmap(page);
+}
+
+/*
+ * we are freeing strings created by nfs_add_to_readdir_array()
+ */
+static
+void nfs_readdir_clear_array(struct page *page)
+{
+        struct nfs_cache_array *array;
+        int i;
+
+        array = kmap_atomic(page, KM_USER0);
+        for (i = 0; i < array->size; i++)
+                kfree(array->array[i].string.name);
+        kunmap_atomic(array, KM_USER0);
+}
+
+/*
+ * the caller is responsible for freeing qstr.name
+ * when called by nfs_readdir_add_to_array, the strings will be freed in
+ * nfs_clear_readdir_array()
+ */
+static
+int nfs_readdir_make_qstr(struct qstr *string, const char *name, unsigned int len)
+{
+        string->len = len;
+        string->name = kmemdup(name, len, GFP_KERNEL);
+        if (string->name == NULL)
+                return -ENOMEM;
+        /*
+         * Avoid a kmemleak false positive. The pointer to the name is stored
+         * in a page cache page which kmemleak does not scan.
+         */
+        kmemleak_not_leak(string->name);
+        string->hash = full_name_hash(name, len);
+        return 0;
+}
+
+static
+int nfs_readdir_add_to_array(struct nfs_entry *entry, struct page *page)
+{
+        struct nfs_cache_array *array = nfs_readdir_get_array(page);
+        struct nfs_cache_array_entry *cache_entry;
+        int ret;
+
+        if (IS_ERR(array))
+                return PTR_ERR(array);
+
+        cache_entry = &array->array[array->size];
+
+        /* Check that this entry lies within the page bounds */
+        ret = -ENOSPC;
+        if ((char *)&cache_entry[1] - (char *)page_address(page) > PAGE_SIZE)
+                goto out;
+
+        cache_entry->cookie = entry->prev_cookie;
+        cache_entry->ino = entry->ino;
+        cache_entry->d_type = entry->d_type;
+        ret = nfs_readdir_make_qstr(&cache_entry->string, entry->name, entry->len);
+        if (ret)
+                goto out;
+        array->last_cookie = entry->cookie;
+        array->size++;
+        if (entry->eof != 0)
+                array->eof_index = array->size;
+out:
+        nfs_readdir_release_array(page);
+        return ret;
+}
+
+static
+int nfs_readdir_search_for_pos(struct nfs_cache_array *array, nfs_readdir_descriptor_t *desc)
+{
+        loff_t diff = desc->file->f_pos - desc->current_index;
+        unsigned int index;
+
+        if (diff < 0)
+                goto out_eof;
+        if (diff >= array->size) {
+                if (array->eof_index >= 0)
+                        goto out_eof;
+                desc->current_index += array->size;
+                return -EAGAIN;
+        }
+
+        index = (unsigned int)diff;
+        *desc->dir_cookie = array->array[index].cookie;
+        desc->cache_entry_index = index;
+        return 0;
+out_eof:
+        desc->eof = 1;
+        return -EBADCOOKIE;
+}
+
+static
+int nfs_readdir_search_for_cookie(struct nfs_cache_array *array, nfs_readdir_descriptor_t *desc)
+{
+        int i;
+        int status = -EAGAIN;
+
+        for (i = 0; i < array->size; i++) {
+                if (array->array[i].cookie == *desc->dir_cookie) {
+                        desc->cache_entry_index = i;
+                        return 0;
+                }
+        }
+        if (array->eof_index >= 0) {
+                status = -EBADCOOKIE;
+                if (*desc->dir_cookie == array->last_cookie)
+                        desc->eof = 1;
+        }
+        return status;
+}
+
+static
+int nfs_readdir_search_array(nfs_readdir_descriptor_t *desc)
+{
+        struct nfs_cache_array *array;
+        int status;
+
+        array = nfs_readdir_get_array(desc->page);
+        if (IS_ERR(array)) {
+                status = PTR_ERR(array);
+                goto out;
+        }
+
+        if (*desc->dir_cookie == 0)
+                status = nfs_readdir_search_for_pos(array, desc);
+        else
+                status = nfs_readdir_search_for_cookie(array, desc);
+
+        if (status == -EAGAIN) {
+                desc->last_cookie = array->last_cookie;
+                desc->page_index++;
+        }
+        nfs_readdir_release_array(desc->page);
+out:
+        return status;
+}
+
+/* Fill a page with xdr information before transferring to the cache page */
+static
+int nfs_readdir_xdr_filler(struct page **pages, nfs_readdir_descriptor_t *desc,
+                        struct nfs_entry *entry, struct file *file, struct inode *inode)
 {
-        struct file     *file = desc->file;
-        struct inode    *inode = file->f_path.dentry->d_inode;
         struct rpc_cred *cred = nfs_file_cred(file);
         unsigned long   timestamp, gencount;
         int             error;
 
-        dfprintk(DIRCACHE, "NFS: %s: reading cookie %Lu into page %lu\n",
-                        __func__, (long long)desc->entry->cookie,
-                        page->index);
-
  again:
         timestamp = jiffies;
         gencount = nfs_inc_attr_generation_counter();
-        error = NFS_PROTO(inode)->readdir(file->f_path.dentry, cred, desc->entry->cookie, page,
+        error = NFS_PROTO(inode)->readdir(file->f_path.dentry, cred, entry->cookie, pages,
                                           NFS_SERVER(inode)->dtsize, desc->plus);
         if (error < 0) {
                 /* We requested READDIRPLUS, but the server doesn't grok it */
@@ -202,199 +375,313 @@ int nfs_readdir_filler(nfs_readdir_descriptor_t *desc, struct page *page)
         }
         desc->timestamp = timestamp;
         desc->gencount = gencount;
-        desc->timestamp_valid = 1;
-        SetPageUptodate(page);
-        /* Ensure consistent page alignment of the data.
-         * Note: assumes we have exclusive access to this mapping either
-         *       through inode->i_mutex or some other mechanism.
-         */
-        if (invalidate_inode_pages2_range(inode->i_mapping, page->index + 1, -1) < 0) {
-                /* Should never happen */
-                nfs_zap_mapping(inode, inode->i_mapping);
-        }
-        unlock_page(page);
-        return 0;
- error:
-        unlock_page(page);
-        return -EIO;
+error:
+        return error;
 }
 
-static inline
-int dir_decode(nfs_readdir_descriptor_t *desc)
-{
-        __be32  *p = desc->ptr;
-        p = desc->decode(p, desc->entry, desc->plus);
-        if (IS_ERR(p))
-                return PTR_ERR(p);
-        desc->ptr = p;
-        if (desc->timestamp_valid) {
-                desc->entry->fattr->time_start = desc->timestamp;
-                desc->entry->fattr->gencount = desc->gencount;
-        } else
-                desc->entry->fattr->valid &= ~NFS_ATTR_FATTR;
+static int xdr_decode(nfs_readdir_descriptor_t *desc,
+                      struct nfs_entry *entry, struct xdr_stream *xdr)
+{
+        int error;
+
+        error = desc->decode(xdr, entry, desc->plus);
+        if (error)
+                return error;
+        entry->fattr->time_start = desc->timestamp;
+        entry->fattr->gencount = desc->gencount;
         return 0;
 }
 
-static inline
-void dir_page_release(nfs_readdir_descriptor_t *desc)
+static
+int nfs_same_file(struct dentry *dentry, struct nfs_entry *entry)
 {
-        kunmap(desc->page);
-        page_cache_release(desc->page);
-        desc->page = NULL;
-        desc->ptr = NULL;
+        if (dentry->d_inode == NULL)
+                goto different;
+        if (nfs_compare_fh(entry->fh, NFS_FH(dentry->d_inode)) != 0)
+                goto different;
+        return 1;
+different:
+        return 0;
 }
 
-/*
- * Given a pointer to a buffer that has already been filled by a call
- * to readdir, find the next entry with cookie '*desc->dir_cookie'.
- *
- * If the end of the buffer has been reached, return -EAGAIN, if not,
- * return the offset within the buffer of the next entry to be
- * read.
- */
-static inline
-int find_dirent(nfs_readdir_descriptor_t *desc)
+static
+void nfs_prime_dcache(struct dentry *parent, struct nfs_entry *entry)
 {
-        struct nfs_entry *entry = desc->entry;
-        int             loop_count = 0,
-                        status;
+        struct qstr filename = {
+                .len = entry->len,
+                .name = entry->name,
+        };
+        struct dentry *dentry;
+        struct dentry *alias;
+        struct inode *dir = parent->d_inode;
+        struct inode *inode;
 
-        while((status = dir_decode(desc)) == 0) {
-                dfprintk(DIRCACHE, "NFS: %s: examining cookie %Lu\n",
-                                __func__, (unsigned long long)entry->cookie);
-                if (entry->prev_cookie == *desc->dir_cookie)
-                        break;
-                if (loop_count++ > 200) {
-                        loop_count = 0;
-                        schedule();
+        if (filename.name[0] == '.') {
+                if (filename.len == 1)
+                        return;
+                if (filename.len == 2 && filename.name[1] == '.')
+                        return;
+        }
+        filename.hash = full_name_hash(filename.name, filename.len);
+
+        dentry = d_lookup(parent, &filename);
+        if (dentry != NULL) {
+                if (nfs_same_file(dentry, entry)) {
+                        nfs_refresh_inode(dentry->d_inode, entry->fattr);
+                        goto out;
+                } else {
+                        d_drop(dentry);
+                        dput(dentry);
                 }
         }
-        return status;
+
+        dentry = d_alloc(parent, &filename);
+        if (dentry == NULL)
+                return;
+
+        d_set_d_op(dentry, NFS_PROTO(dir)->dentry_ops);
+        inode = nfs_fhget(dentry->d_sb, entry->fh, entry->fattr);
+        if (IS_ERR(inode))
+                goto out;
+
+        alias = d_materialise_unique(dentry, inode);
+        if (IS_ERR(alias))
+                goto out;
+        else if (alias) {
+                nfs_set_verifier(alias, nfs_save_change_attribute(dir));
+                dput(alias);
+        } else
+                nfs_set_verifier(dentry, nfs_save_change_attribute(dir));
+
+out:
+        dput(dentry);
 }
 
-/*
- * Given a pointer to a buffer that has already been filled by a call
- * to readdir, find the entry at offset 'desc->file->f_pos'.
- *
- * If the end of the buffer has been reached, return -EAGAIN, if not,
- * return the offset within the buffer of the next entry to be
- * read.
- */
-static inline
-int find_dirent_index(nfs_readdir_descriptor_t *desc)
+/* Perform conversion from xdr to cache array */
+static
+int nfs_readdir_page_filler(nfs_readdir_descriptor_t *desc, struct nfs_entry *entry,
+                                struct page **xdr_pages, struct page *page, unsigned int buflen)
 {
-        struct nfs_entry *entry = desc->entry;
-        int             loop_count = 0,
-                        status;
+        struct xdr_stream stream;
+        struct xdr_buf buf = {
+                .pages = xdr_pages,
+                .page_len = buflen,
+                .buflen = buflen,
+                .len = buflen,
+        };
+        struct page *scratch;
+        struct nfs_cache_array *array;
+        unsigned int count = 0;
+        int status;
 
-        for(;;) {
-                status = dir_decode(desc);
-                if (status)
-                        break;
+        scratch = alloc_page(GFP_KERNEL);
+        if (scratch == NULL)
+                return -ENOMEM;
 
-                dfprintk(DIRCACHE, "NFS: found cookie %Lu at index %Ld\n",
-                                (unsigned long long)entry->cookie, desc->current_index);
+        xdr_init_decode(&stream, &buf, NULL);
+        xdr_set_scratch_buffer(&stream, page_address(scratch), PAGE_SIZE);
 
-                if (desc->file->f_pos == desc->current_index) {
-                        *desc->dir_cookie = entry->cookie;
+        do {
+                status = xdr_decode(desc, entry, &stream);
+                if (status != 0) {
+                        if (status == -EAGAIN)
+                                status = 0;
                         break;
                 }
-                desc->current_index++;
-                if (loop_count++ > 200) {
-                        loop_count = 0;
-                        schedule();
-                }
+
+                count++;
+
+                if (desc->plus != 0)
+                        nfs_prime_dcache(desc->file->f_path.dentry, entry);
+
+                status = nfs_readdir_add_to_array(entry, page);
+                if (status != 0)
+                        break;
+        } while (!entry->eof);
+
+        if (count == 0 || (status == -EBADCOOKIE && entry->eof != 0)) {
+                array = nfs_readdir_get_array(page);
+                if (!IS_ERR(array)) {
+                        array->eof_index = array->size;
+                        status = 0;
+                        nfs_readdir_release_array(page);
+                } else
+                        status = PTR_ERR(array);
         }
+
+        put_page(scratch);
         return status;
 }
 
+static
+void nfs_readdir_free_pagearray(struct page **pages, unsigned int npages)
+{
+        unsigned int i;
+        for (i = 0; i < npages; i++)
+                put_page(pages[i]);
+}
+
+static
+void nfs_readdir_free_large_page(void *ptr, struct page **pages,
+                unsigned int npages)
+{
+        nfs_readdir_free_pagearray(pages, npages);
+}
+
 /*
- * Find the given page, and call find_dirent() or find_dirent_index in
- * order to try to return the next entry.
+ * nfs_readdir_large_page will allocate pages that must be freed with a call
+ * to nfs_readdir_free_large_page
  */
-static inline
-int find_dirent_page(nfs_readdir_descriptor_t *desc)
+static
+int nfs_readdir_large_page(struct page **pages, unsigned int npages)
 {
-        struct inode    *inode = desc->file->f_path.dentry->d_inode;
-        struct page     *page;
-        int             status;
+        unsigned int i;
+
+        for (i = 0; i < npages; i++) {
+                struct page *page = alloc_page(GFP_KERNEL);
+                if (page == NULL)
+                        goto out_freepages;
+                pages[i] = page;
+        }
+        return 0;
 
-        dfprintk(DIRCACHE, "NFS: %s: searching page %ld for target %Lu\n",
-                        __func__, desc->page_index,
-                        (long long) *desc->dir_cookie);
+out_freepages:
+        nfs_readdir_free_pagearray(pages, i);
+        return -ENOMEM;
+}
 
-        /* If we find the page in the page_cache, we cannot be sure
-         * how fresh the data is, so we will ignore readdir_plus attributes.
-         */
-        desc->timestamp_valid = 0;
-        page = read_cache_page(inode->i_mapping, desc->page_index,
-                               (filler_t *)nfs_readdir_filler, desc);
-        if (IS_ERR(page)) {
-                status = PTR_ERR(page);
+static
+int nfs_readdir_xdr_to_array(nfs_readdir_descriptor_t *desc, struct page *page, struct inode *inode)
+{
+        struct page *pages[NFS_MAX_READDIR_PAGES];
+        void *pages_ptr = NULL;
+        struct nfs_entry entry;
+        struct file     *file = desc->file;
+        struct nfs_cache_array *array;
+        int status = -ENOMEM;
+        unsigned int array_size = ARRAY_SIZE(pages);
+
+        entry.prev_cookie = 0;
+        entry.cookie = desc->last_cookie;
+        entry.eof = 0;
+        entry.fh = nfs_alloc_fhandle();
+        entry.fattr = nfs_alloc_fattr();
+        entry.server = NFS_SERVER(inode);
+        if (entry.fh == NULL || entry.fattr == NULL)
+                goto out;
+
+        array = nfs_readdir_get_array(page);
+        if (IS_ERR(array)) {
+                status = PTR_ERR(array);
                 goto out;
         }
+        memset(array, 0, sizeof(struct nfs_cache_array));
+        array->eof_index = -1;
 
-        /* NOTE: Someone else may have changed the READDIRPLUS flag */
-        desc->page = page;
-        desc->ptr = kmap(page);         /* matching kunmap in nfs_do_filldir */
-        if (*desc->dir_cookie != 0)
-                status = find_dirent(desc);
-        else
-                status = find_dirent_index(desc);
+        status = nfs_readdir_large_page(pages, array_size);
         if (status < 0)
-                dir_page_release(desc);
- out:
-        dfprintk(DIRCACHE, "NFS: %s: returns %d\n", __func__, status);
+                goto out_release_array;
+        do {
+                unsigned int pglen;
+                status = nfs_readdir_xdr_filler(pages, desc, &entry, file, inode);
+
+                if (status < 0)
+                        break;
+                pglen = status;
+                status = nfs_readdir_page_filler(desc, &entry, pages, page, pglen);
+                if (status < 0) {
+                        if (status == -ENOSPC)
+                                status = 0;
+                        break;
+                }
+        } while (array->eof_index < 0);
+
+        nfs_readdir_free_large_page(pages_ptr, pages, array_size);
+out_release_array:
+        nfs_readdir_release_array(page);
+out:
+        nfs_free_fattr(entry.fattr);
+        nfs_free_fhandle(entry.fh);
         return status;
 }
 
 /*
- * Recurse through the page cache pages, and return a
- * filled nfs_entry structure of the next directory entry if possible.
- *
- * The target for the search is '*desc->dir_cookie' if non-0,
- * 'desc->file->f_pos' otherwise
+ * Now we cache directories properly, by converting xdr information
+ * to an array that can be used for lookups later.  This results in
+ * fewer cache pages, since we can store more information on each page.
+ * We only need to convert from xdr once so future lookups are much simpler
  */
-static inline
-int readdir_search_pagecache(nfs_readdir_descriptor_t *desc)
+static
+int nfs_readdir_filler(nfs_readdir_descriptor_t *desc, struct page* page)
 {
-        int             loop_count = 0;
-        int             res;
+        struct inode    *inode = desc->file->f_path.dentry->d_inode;
+        int ret;
 
-        /* Always search-by-index from the beginning of the cache */
-        if (*desc->dir_cookie == 0) {
-                dfprintk(DIRCACHE, "NFS: readdir_search_pagecache() searching for offset %Ld\n",
-                                (long long)desc->file->f_pos);
-                desc->page_index = 0;
-                desc->entry->cookie = desc->entry->prev_cookie = 0;
-                desc->entry->eof = 0;
-                desc->current_index = 0;
-        } else
-                dfprintk(DIRCACHE, "NFS: readdir_search_pagecache() searching for cookie %Lu\n",
-                                (unsigned long long)*desc->dir_cookie);
+        ret = nfs_readdir_xdr_to_array(desc, page, inode);
+        if (ret < 0)
+                goto error;
+        SetPageUptodate(page);
 
-        for (;;) {
-                res = find_dirent_page(desc);
-                if (res != -EAGAIN)
-                        break;
-                /* Align to beginning of next page */
-                desc->page_index ++;
-                if (loop_count++ > 200) {
-                        loop_count = 0;
-                        schedule();
-                }
+        if (invalidate_inode_pages2_range(inode->i_mapping, page->index + 1, -1) < 0) {
+                /* Should never happen */
+                nfs_zap_mapping(inode, inode->i_mapping);
         }
+        unlock_page(page);
+        return 0;
+ error:
+        unlock_page(page);
+        return ret;
+}
 
-        dfprintk(DIRCACHE, "NFS: %s: returns %d\n", __func__, res);
-        return res;
+static
+void cache_page_release(nfs_readdir_descriptor_t *desc)
+{
+        if (!desc->page->mapping)
+                nfs_readdir_clear_array(desc->page);
+        page_cache_release(desc->page);
+        desc->page = NULL;
 }
 
-static inline unsigned int dt_type(struct inode *inode)
+static
+struct page *get_cache_page(nfs_readdir_descriptor_t *desc)
+{
+        return read_cache_page(desc->file->f_path.dentry->d_inode->i_mapping,
+                        desc->page_index, (filler_t *)nfs_readdir_filler, desc);
+}
+
+/*
+ * Returns 0 if desc->dir_cookie was found on page desc->page_index
+ */
+static
+int find_cache_page(nfs_readdir_descriptor_t *desc)
 {
-        return (inode->i_mode >> 12) & 15;
+        int res;
+
+        desc->page = get_cache_page(desc);
+        if (IS_ERR(desc->page))
+                return PTR_ERR(desc->page);
+
+        res = nfs_readdir_search_array(desc);
+        if (res != 0)
+                cache_page_release(desc);
+        return res;
 }
 
-static struct dentry *nfs_readdir_lookup(nfs_readdir_descriptor_t *desc);
+/* Search for desc->dir_cookie from the beginning of the page cache */
+static inline
+int readdir_search_pagecache(nfs_readdir_descriptor_t *desc)
+{
+        int res;
+
+        if (desc->page_index == 0) {
+                desc->current_index = 0;
+                desc->last_cookie = 0;
+        }
+        do {
+                res = find_cache_page(desc);
+        } while (res == -EAGAIN);
+        return res;
+}
 
 /*
  * Once we've found the start of the dirent within a page: fill 'er up...
@@ -404,51 +691,38 @@ int nfs_do_filldir(nfs_readdir_descriptor_t *desc, void *dirent,
                    filldir_t filldir)
 {
         struct file     *file = desc->file;
-        struct nfs_entry *entry = desc->entry;
-        struct dentry   *dentry = NULL;
-        u64             fileid;
-        int             loop_count = 0,
-                        res;
-
-        dfprintk(DIRCACHE, "NFS: nfs_do_filldir() filling starting @ cookie %Lu\n",
-                        (unsigned long long)entry->cookie);
-
-        for(;;) {
-                unsigned d_type = DT_UNKNOWN;
-                /* Note: entry->prev_cookie contains the cookie for
-                 *       retrieving the current dirent on the server */
-                fileid = entry->ino;
-
-                /* Get a dentry if we have one */
-                if (dentry != NULL)
-                        dput(dentry);
-                dentry = nfs_readdir_lookup(desc);
+        int i = 0;
+        int res = 0;
+        struct nfs_cache_array *array = NULL;
 
-                /* Use readdirplus info */
-                if (dentry != NULL && dentry->d_inode != NULL) {
-                        d_type = dt_type(dentry->d_inode);
-                        fileid = NFS_FILEID(dentry->d_inode);
-                }
+        array = nfs_readdir_get_array(desc->page);
+        if (IS_ERR(array)) {
+                res = PTR_ERR(array);
+                goto out;
+        }
 
-                res = filldir(dirent, entry->name, entry->len, 
-                              file->f_pos, nfs_compat_user_ino64(fileid),
-                              d_type);
-                if (res < 0)
-                        break;
-                file->f_pos++;
-                *desc->dir_cookie = entry->cookie;
-                if (dir_decode(desc) != 0) {
-                        desc->page_index ++;
+        for (i = desc->cache_entry_index; i < array->size; i++) {
+                struct nfs_cache_array_entry *ent;
+
+                ent = &array->array[i];
+                if (filldir(dirent, ent->string.name, ent->string.len,
+                    file->f_pos, nfs_compat_user_ino64(ent->ino),
+                    ent->d_type) < 0) {
+                        desc->eof = 1;
                         break;
                 }
-                if (loop_count++ > 200) {
-                        loop_count = 0;
-                        schedule();
-                }
+                file->f_pos++;
+                if (i < (array->size-1))
+                        *desc->dir_cookie = array->array[i+1].cookie;
+                else
+                        *desc->dir_cookie = array->last_cookie;
         }
-        dir_page_release(desc);
-        if (dentry != NULL)
-                dput(dentry);
+        if (array->eof_index >= 0)
+                desc->eof = 1;
+
+        nfs_readdir_release_array(desc->page);
+out:
+        cache_page_release(desc);
         dfprintk(DIRCACHE, "NFS: nfs_do_filldir() filling ended @ cookie %Lu; returning = %d\n",
                         (unsigned long long)*desc->dir_cookie, res);
         return res;
@@ -470,12 +744,9 @@ static inline
 int uncached_readdir(nfs_readdir_descriptor_t *desc, void *dirent,
                      filldir_t filldir)
 {
-        struct file     *file = desc->file;
-        struct inode    *inode = file->f_path.dentry->d_inode;
-        struct rpc_cred *cred = nfs_file_cred(file);
         struct page     *page = NULL;
         int             status;
-        unsigned long   timestamp, gencount;
+        struct inode *inode = desc->file->f_path.dentry->d_inode;
 
         dfprintk(DIRCACHE, "NFS: uncached_readdir() searching for cookie %Lu\n",
                         (unsigned long long)*desc->dir_cookie);
@@ -485,38 +756,23 @@ int uncached_readdir(nfs_readdir_descriptor_t *desc, void *dirent,
                 status = -ENOMEM;
                 goto out;
         }
-        timestamp = jiffies;
-        gencount = nfs_inc_attr_generation_counter();
-        status = NFS_PROTO(inode)->readdir(file->f_path.dentry, cred,
-                                                *desc->dir_cookie, page,
-                                                NFS_SERVER(inode)->dtsize,
-                                                desc->plus);
+
+        desc->page_index = 0;
+        desc->last_cookie = *desc->dir_cookie;
         desc->page = page;
-        desc->ptr = kmap(page);         /* matching kunmap in nfs_do_filldir */
-        if (status >= 0) {
-                desc->timestamp = timestamp;
-                desc->gencount = gencount;
-                desc->timestamp_valid = 1;
-                if ((status = dir_decode(desc)) == 0)
-                        desc->entry->prev_cookie = *desc->dir_cookie;
-        } else
-                status = -EIO;
+
+        status = nfs_readdir_xdr_to_array(desc, page, inode);
         if (status < 0)
                 goto out_release;
 
         status = nfs_do_filldir(desc, dirent, filldir);
 
-        /* Reset read descriptor so it searches the page cache from
-         * the start upon the next call to readdir_search_pagecache() */
-        desc->page_index = 0;
-        desc->entry->cookie = desc->entry->prev_cookie = 0;
-        desc->entry->eof = 0;
  out:
         dfprintk(DIRCACHE, "NFS: %s: returns %d\n",
                         __func__, status);
         return status;
  out_release:
-        dir_page_release(desc);
+        cache_page_release(desc);
         goto out;
 }
 
@@ -530,10 +786,7 @@ static int nfs_readdir(struct file *filp, void *dirent, filldir_t filldir)
         struct inode    *inode = dentry->d_inode;
         nfs_readdir_descriptor_t my_desc,
                         *desc = &my_desc;
-        struct nfs_entry my_entry;
-        struct nfs_fh    fh;
-        struct nfs_fattr fattr;
-        long            res;
+        int res;
 
         dfprintk(FILE, "NFS: readdir(%s/%s) starting at cookie %llu\n",
                         dentry->d_parent->d_name.name, dentry->d_name.name,
@@ -553,53 +806,45 @@ static int nfs_readdir(struct file *filp, void *dirent, filldir_t filldir)
         desc->decode = NFS_PROTO(inode)->decode_dirent;
         desc->plus = NFS_USE_READDIRPLUS(inode);
 
-        my_entry.cookie = my_entry.prev_cookie = 0;
-        my_entry.eof = 0;
-        my_entry.fh = &fh;
-        my_entry.fattr = &fattr;
-        nfs_fattr_init(&fattr);
-        desc->entry = &my_entry;
-
         nfs_block_sillyrename(dentry);
-        res = nfs_revalidate_mapping_nolock(inode, filp->f_mapping);
+        res = nfs_revalidate_mapping(inode, filp->f_mapping);
         if (res < 0)
                 goto out;
 
-        while(!desc->entry->eof) {
+        do {
                 res = readdir_search_pagecache(desc);
 
                 if (res == -EBADCOOKIE) {
+                        res = 0;
                         /* This means either end of directory */
-                        if (*desc->dir_cookie && desc->entry->cookie != *desc->dir_cookie) {
+                        if (*desc->dir_cookie && desc->eof == 0) {
                                 /* Or that the server has 'lost' a cookie */
                                 res = uncached_readdir(desc, dirent, filldir);
-                                if (res >= 0)
+                                if (res == 0)
                                         continue;
                         }
-                        res = 0;
                         break;
                 }
                 if (res == -ETOOSMALL && desc->plus) {
                         clear_bit(NFS_INO_ADVISE_RDPLUS, &NFS_I(inode)->flags);
                         nfs_zap_caches(inode);
+                        desc->page_index = 0;
                         desc->plus = 0;
-                        desc->entry->eof = 0;
+                        desc->eof = 0;
                         continue;
                 }
                 if (res < 0)
                         break;
 
                 res = nfs_do_filldir(desc, dirent, filldir);
-                if (res < 0) {
-                        res = 0;
+                if (res < 0)
                         break;
-                }
-        }
+        } while (!desc->eof);
 out:
         nfs_unblock_sillyrename(dentry);
         if (res > 0)
                 res = 0;
-        dfprintk(FILE, "NFS: readdir(%s/%s) returns %ld\n",
+        dfprintk(FILE, "NFS: readdir(%s/%s) returns %d\n",
                         dentry->d_parent->d_name.name, dentry->d_name.name,
                         res);
         return res;
@@ -639,8 +884,10 @@ out:
  * All directory operations under NFS are synchronous, so fsync()
  * is a dummy operation.
  */
-static int nfs_fsync_dir(struct file *filp, struct dentry *dentry, int datasync)
+static int nfs_fsync_dir(struct file *filp, int datasync)
 {
+        struct dentry *dentry = filp->f_path.dentry;
+
         dfprintk(FILE, "NFS: fsync dir(%s/%s) datasync %d\n",
                         dentry->d_parent->d_name.name, dentry->d_name.name,
                         datasync);
@@ -692,7 +939,8 @@ static int nfs_check_verifier(struct inode *dir, struct dentry *dentry)
  * component of the path.
  * We check for this using LOOKUP_CONTINUE and LOOKUP_PARENT.
  */
-static inline unsigned int nfs_lookup_check_intent(struct nameidata *nd, unsigned int mask)
+static inline unsigned int nfs_lookup_check_intent(struct nameidata *nd,
+                                                unsigned int mask)
 {
         if (nd->flags & (LOOKUP_CONTINUE|LOOKUP_PARENT))
                 return 0;
@@ -772,14 +1020,17 @@ int nfs_neg_need_reval(struct inode *dir, struct dentry *dentry,
  * If the parent directory is seen to have changed, we throw out the
  * cached dentry and do a new lookup.
  */
-static int nfs_lookup_revalidate(struct dentry * dentry, struct nameidata *nd)
+static int nfs_lookup_revalidate(struct dentry *dentry, struct nameidata *nd)
 {
         struct inode *dir;
         struct inode *inode;
         struct dentry *parent;
+        struct nfs_fh *fhandle = NULL;
+        struct nfs_fattr *fattr = NULL;
         int error;
-        struct nfs_fh fhandle;
-        struct nfs_fattr fattr;
+
+        if (nd->flags & LOOKUP_RCU)
+                return -ECHILD;
 
         parent = dget_parent(dentry);
         dir = parent->d_inode;
@@ -812,14 +1063,22 @@ static int nfs_lookup_revalidate(struct dentry * dentry, struct nameidata *nd)
         if (NFS_STALE(inode))
                 goto out_bad;
 
-        error = NFS_PROTO(dir)->lookup(dir, &dentry->d_name, &fhandle, &fattr);
+        error = -ENOMEM;
+        fhandle = nfs_alloc_fhandle();
+        fattr = nfs_alloc_fattr();
+        if (fhandle == NULL || fattr == NULL)
+                goto out_error;
+
+        error = NFS_PROTO(dir)->lookup(dir, &dentry->d_name, fhandle, fattr);
         if (error)
                 goto out_bad;
-        if (nfs_compare_fh(NFS_FH(inode), &fhandle))
+        if (nfs_compare_fh(NFS_FH(inode), fhandle))
                 goto out_bad;
-        if ((error = nfs_refresh_inode(inode, &fattr)) != 0)
+        if ((error = nfs_refresh_inode(inode, fattr)) != 0)
                 goto out_bad;
 
+        nfs_free_fattr(fattr);
+        nfs_free_fhandle(fhandle);
 out_set_verifier:
         nfs_set_verifier(dentry, nfs_save_change_attribute(dir));
  out_valid:
@@ -838,20 +1097,32 @@ out_zap_parent:
                 /* If we have submounts, don't unhash ! */
                 if (have_submounts(dentry))
                         goto out_valid;
+                if (dentry->d_flags & DCACHE_DISCONNECTED)
+                        goto out_valid;
                 shrink_dcache_parent(dentry);
         }
         d_drop(dentry);
+        nfs_free_fattr(fattr);
+        nfs_free_fhandle(fhandle);
         dput(parent);
         dfprintk(LOOKUPCACHE, "NFS: %s(%s/%s) is invalid\n",
                         __func__, dentry->d_parent->d_name.name,
                         dentry->d_name.name);
         return 0;
+out_error:
+        nfs_free_fattr(fattr);
+        nfs_free_fhandle(fhandle);
+        dput(parent);
+        dfprintk(LOOKUPCACHE, "NFS: %s(%s/%s) lookup returned error %d\n",
+                        __func__, dentry->d_parent->d_name.name,
+                        dentry->d_name.name, error);
+        return error;
 }
 
 /*
  * This is called from dput() when d_count is going to 0.
  */
-static int nfs_dentry_delete(struct dentry *dentry)
+static int nfs_dentry_delete(const struct dentry *dentry)
 {
         dfprintk(VFS, "NFS: dentry_delete(%s/%s, %x)\n",
                 dentry->d_parent->d_name.name, dentry->d_name.name,
@@ -910,9 +1181,9 @@ static struct dentry *nfs_lookup(struct inode *dir, struct dentry * dentry, stru
         struct dentry *res;
         struct dentry *parent;
         struct inode *inode = NULL;
+        struct nfs_fh *fhandle = NULL;
+        struct nfs_fattr *fattr = NULL;
         int error;
-        struct nfs_fh fhandle;
-        struct nfs_fattr fattr;
 
         dfprintk(VFS, "NFS: lookup(%s/%s)\n",
                 dentry->d_parent->d_name.name, dentry->d_name.name);
@@ -922,8 +1193,7 @@ static struct dentry *nfs_lookup(struct inode *dir, struct dentry * dentry, stru
         if (dentry->d_name.len > NFS_SERVER(dir)->namelen)
                 goto out;
 
-        res = ERR_PTR(-ENOMEM);
-        dentry->d_op = NFS_PROTO(dir)->dentry_ops;
+        d_set_d_op(dentry, NFS_PROTO(dir)->dentry_ops);
 
         /*
          * If we're doing an exclusive create, optimize away the lookup
@@ -935,18 +1205,24 @@ static struct dentry *nfs_lookup(struct inode *dir, struct dentry * dentry, stru
                 goto out;
         }
 
+        res = ERR_PTR(-ENOMEM);
+        fhandle = nfs_alloc_fhandle();
+        fattr = nfs_alloc_fattr();
+        if (fhandle == NULL || fattr == NULL)
+                goto out;
+
         parent = dentry->d_parent;
         /* Protect against concurrent sillydeletes */
         nfs_block_sillyrename(parent);
-        error = NFS_PROTO(dir)->lookup(dir, &dentry->d_name, &fhandle, &fattr);
+        error = NFS_PROTO(dir)->lookup(dir, &dentry->d_name, fhandle, fattr);
         if (error == -ENOENT)
                 goto no_entry;
         if (error < 0) {
                 res = ERR_PTR(error);
                 goto out_unblock_sillyrename;
         }
-        inode = nfs_fhget(dentry->d_sb, &fhandle, &fattr);
-        res = (struct dentry *)inode;
+        inode = nfs_fhget(dentry->d_sb, fhandle, fattr);
+        res = ERR_CAST(inode);
         if (IS_ERR(res))
                 goto out_unblock_sillyrename;
 
@@ -961,6 +1237,8 @@ no_entry:
 out_unblock_sillyrename:
         nfs_unblock_sillyrename(parent);
 out:
+        nfs_free_fattr(fattr);
+        nfs_free_fhandle(fhandle);
         return res;
 }
 
@@ -991,10 +1269,63 @@ static int is_atomic_open(struct nameidata *nd)
         return 1;
 }
 
+static struct nfs_open_context *nameidata_to_nfs_open_context(struct dentry *dentry, struct nameidata *nd)
+{
+        struct path path = {
+                .mnt = nd->path.mnt,
+                .dentry = dentry,
+        };
+        struct nfs_open_context *ctx;
+        struct rpc_cred *cred;
+        fmode_t fmode = nd->intent.open.flags & (FMODE_READ | FMODE_WRITE | FMODE_EXEC);
+
+        cred = rpc_lookup_cred();
+        if (IS_ERR(cred))
+                return ERR_CAST(cred);
+        ctx = alloc_nfs_open_context(&path, cred, fmode);
+        put_rpccred(cred);
+        if (ctx == NULL)
+                return ERR_PTR(-ENOMEM);
+        return ctx;
+}
+
+static int do_open(struct inode *inode, struct file *filp)
+{
+        nfs_fscache_set_inode_cookie(inode, filp);
+        return 0;
+}
+
+static int nfs_intent_set_file(struct nameidata *nd, struct nfs_open_context *ctx)
+{
+        struct file *filp;
+        int ret = 0;
+
+        /* If the open_intent is for execute, we have an extra check to make */
+        if (ctx->mode & FMODE_EXEC) {
+                ret = nfs_may_open(ctx->path.dentry->d_inode,
+                                ctx->cred,
+                                nd->intent.open.flags);
+                if (ret < 0)
+                        goto out;
+        }
+        filp = lookup_instantiate_filp(nd, ctx->path.dentry, do_open);
+        if (IS_ERR(filp))
+                ret = PTR_ERR(filp);
+        else
+                nfs_file_set_open_context(filp, ctx);
+out:
+        put_nfs_open_context(ctx);
+        return ret;
+}
+
 static struct dentry *nfs_atomic_lookup(struct inode *dir, struct dentry *dentry, struct nameidata *nd)
 {
+        struct nfs_open_context *ctx;
+        struct iattr attr;
         struct dentry *res = NULL;
-        int error;
+        struct inode *inode;
+        int open_flags;
+        int err;
 
         dfprintk(VFS, "NFS: atomic_lookup(%s/%ld), %s\n",
                         dir->i_sb->s_id, dir->i_ino, dentry->d_name.name);
@@ -1007,7 +1338,7 @@ static struct dentry *nfs_atomic_lookup(struct inode *dir, struct dentry *dentry
                 res = ERR_PTR(-ENAMETOOLONG);
                 goto out;
         }
-        dentry->d_op = NFS_PROTO(dir)->dentry_ops;
+        d_set_d_op(dentry, NFS_PROTO(dir)->dentry_ops);
 
         /* Let vfs_create() deal with O_EXCL. Instantiate, but don't hash
          * the dentry. */
@@ -1016,29 +1347,61 @@ static struct dentry *nfs_atomic_lookup(struct inode *dir, struct dentry *dentry
                 goto out;
         }
 
+        ctx = nameidata_to_nfs_open_context(dentry, nd);
+        res = ERR_CAST(ctx);
+        if (IS_ERR(ctx))
+                goto out;
+
+        open_flags = nd->intent.open.flags;
+        if (nd->flags & LOOKUP_CREATE) {
+                attr.ia_mode = nd->intent.open.create_mode;
+                attr.ia_valid = ATTR_MODE;
+                attr.ia_mode &= ~current_umask();
+        } else {
+                open_flags &= ~(O_EXCL | O_CREAT);
+                attr.ia_valid = 0;
+        }
+
         /* Open the file on the server */
-        res = nfs4_atomic_open(dir, dentry, nd);
-        if (IS_ERR(res)) {
-                error = PTR_ERR(res);
-                switch (error) {
+        nfs_block_sillyrename(dentry->d_parent);
+        inode = NFS_PROTO(dir)->open_context(dir, ctx, open_flags, &attr);
+        if (IS_ERR(inode)) {
+                nfs_unblock_sillyrename(dentry->d_parent);
+                put_nfs_open_context(ctx);
+                switch (PTR_ERR(inode)) {
                         /* Make a negative dentry */
                         case -ENOENT:
+                                d_add(dentry, NULL);
                                 res = NULL;
                                 goto out;
                         /* This turned out not to be a regular file */
-                        case -EISDIR:
                         case -ENOTDIR:
                                 goto no_open;
                         case -ELOOP:
                                 if (!(nd->intent.open.flags & O_NOFOLLOW))
                                         goto no_open;
+                        /* case -EISDIR: */
                         /* case -EINVAL: */
                         default:
+                                res = ERR_CAST(inode);
                                 goto out;
                 }
-        } else if (res != NULL)
+        }
+        res = d_add_unique(dentry, inode);
+        nfs_unblock_sillyrename(dentry->d_parent);
+        if (res != NULL) {
+                dput(ctx->path.dentry);
+                ctx->path.dentry = dget(res);
                 dentry = res;
+        }
+        err = nfs_intent_set_file(nd, ctx);
+        if (err < 0) {
+                if (res != NULL)
+                        dput(res);
+                return ERR_PTR(err);
+        }
 out:
+        nfs_set_verifier(dentry, nfs_save_change_attribute(dir));
         return res;
 no_open:
         return nfs_lookup(dir, dentry, nd);
@@ -1049,12 +1412,15 @@ static int nfs_open_revalidate(struct dentry *dentry, struct nameidata *nd)
         struct dentry *parent = NULL;
         struct inode *inode = dentry->d_inode;
         struct inode *dir;
+        struct nfs_open_context *ctx;
         int openflags, ret = 0;
 
-        if (!is_atomic_open(nd))
+        if (!is_atomic_open(nd) || d_mountpoint(dentry))
                 goto no_open;
+
         parent = dget_parent(dentry);
         dir = parent->d_inode;
+
         /* We can't create new files in nfs_open_revalidate(), so we
          * optimize away revalidation of negative dentries.
          */
@@ -1072,101 +1438,98 @@ static int nfs_open_revalidate(struct dentry *dentry, struct nameidata *nd)
         if ((openflags & (O_CREAT|O_EXCL)) == (O_CREAT|O_EXCL))
                 goto no_open_dput;
         /* We can't create new files, or truncate existing ones here */
-        openflags &= ~(O_CREAT|O_TRUNC);
+        openflags &= ~(O_CREAT|O_EXCL|O_TRUNC);
 
+        ctx = nameidata_to_nfs_open_context(dentry, nd);
+        ret = PTR_ERR(ctx);
+        if (IS_ERR(ctx))
+                goto out;
         /*
          * Note: we're not holding inode->i_mutex and so may be racing with
          * operations that change the directory. We therefore save the
          * change attribute *before* we do the RPC call.
          */
-        ret = nfs4_open_revalidate(dir, dentry, openflags, nd);
+        inode = NFS_PROTO(dir)->open_context(dir, ctx, openflags, NULL);
+        if (IS_ERR(inode)) {
+                ret = PTR_ERR(inode);
+                switch (ret) {
+                case -EPERM:
+                case -EACCES:
+                case -EDQUOT:
+                case -ENOSPC:
+                case -EROFS:
+                        goto out_put_ctx;
+                default:
+                        goto out_drop;
+                }
+        }
+        iput(inode);
+        if (inode != dentry->d_inode)
+                goto out_drop;
+
+        nfs_set_verifier(dentry, nfs_save_change_attribute(dir));
+        ret = nfs_intent_set_file(nd, ctx);
+        if (ret >= 0)
+                ret = 1;
 out:
         dput(parent);
-        if (!ret)
-                d_drop(dentry);
         return ret;
+out_drop:
+        d_drop(dentry);
+        ret = 0;
+out_put_ctx:
+        put_nfs_open_context(ctx);
+        goto out;
+
 no_open_dput:
         dput(parent);
 no_open:
         return nfs_lookup_revalidate(dentry, nd);
 }
-#endif /* CONFIG_NFSV4 */
 
-static struct dentry *nfs_readdir_lookup(nfs_readdir_descriptor_t *desc)
+static int nfs_open_create(struct inode *dir, struct dentry *dentry, int mode,
+                struct nameidata *nd)
 {
-        struct dentry *parent = desc->file->f_path.dentry;
-        struct inode *dir = parent->d_inode;
-        struct nfs_entry *entry = desc->entry;
-        struct dentry *dentry, *alias;
-        struct qstr name = {
-                .name = entry->name,
-                .len = entry->len,
-        };
-        struct inode *inode;
-        unsigned long verf = nfs_save_change_attribute(dir);
+        struct nfs_open_context *ctx = NULL;
+        struct iattr attr;
+        int error;
+        int open_flags = 0;
 
-        switch (name.len) {
-                case 2:
-                        if (name.name[0] == '.' && name.name[1] == '.')
-                                return dget_parent(parent);
-                        break;
-                case 1:
-                        if (name.name[0] == '.')
-                                return dget(parent);
-        }
+        dfprintk(VFS, "NFS: create(%s/%ld), %s\n",
+                        dir->i_sb->s_id, dir->i_ino, dentry->d_name.name);
 
-        spin_lock(&dir->i_lock);
-        if (NFS_I(dir)->cache_validity & NFS_INO_INVALID_DATA) {
-                spin_unlock(&dir->i_lock);
-                return NULL;
-        }
-        spin_unlock(&dir->i_lock);
+        attr.ia_mode = mode;
+        attr.ia_valid = ATTR_MODE;
 
-        name.hash = full_name_hash(name.name, name.len);
-        dentry = d_lookup(parent, &name);
-        if (dentry != NULL) {
-                /* Is this a positive dentry that matches the readdir info? */
-                if (dentry->d_inode != NULL &&
-                                (NFS_FILEID(dentry->d_inode) == entry->ino ||
-                                d_mountpoint(dentry))) {
-                        if (!desc->plus || entry->fh->size == 0)
-                                return dentry;
-                        if (nfs_compare_fh(NFS_FH(dentry->d_inode),
-                                                entry->fh) == 0)
-                                goto out_renew;
-                }
-                /* No, so d_drop to allow one to be created */
-                d_drop(dentry);
-                dput(dentry);
-        }
-        if (!desc->plus || !(entry->fattr->valid & NFS_ATTR_FATTR))
-                return NULL;
-        if (name.len > NFS_SERVER(dir)->namelen)
-                return NULL;
-        /* Note: caller is already holding the dir->i_mutex! */
-        dentry = d_alloc(parent, &name);
-        if (dentry == NULL)
-                return NULL;
-        dentry->d_op = NFS_PROTO(dir)->dentry_ops;
-        inode = nfs_fhget(dentry->d_sb, entry->fh, entry->fattr);
-        if (IS_ERR(inode)) {
-                dput(dentry);
-                return NULL;
-        }
+        if ((nd->flags & LOOKUP_CREATE) != 0) {
+                open_flags = nd->intent.open.flags;
 
-        alias = d_materialise_unique(dentry, inode);
-        if (alias != NULL) {
-                dput(dentry);
-                if (IS_ERR(alias))
-                        return NULL;
-                dentry = alias;
+                ctx = nameidata_to_nfs_open_context(dentry, nd);
+                error = PTR_ERR(ctx);
+                if (IS_ERR(ctx))
+                        goto out_err_drop;
         }
 
-out_renew:
-        nfs_set_verifier(dentry, verf);
-        return dentry;
+        error = NFS_PROTO(dir)->create(dir, dentry, &attr, open_flags, ctx);
+        if (error != 0)
+                goto out_put_ctx;
+        if (ctx != NULL) {
+                error = nfs_intent_set_file(nd, ctx);
+                if (error < 0)
+                        goto out_err;
+        }
+        return 0;
+out_put_ctx:
+        if (ctx != NULL)
+                put_nfs_open_context(ctx);
+out_err_drop:
+        d_drop(dentry);
+out_err:
+        return error;
 }
 
+#endif /* CONFIG_NFSV4 */
+
 /*
  * Code common to create, mkdir, and mknod.
  */
@@ -1220,7 +1583,6 @@ static int nfs_create(struct inode *dir, struct dentry *dentry, int mode,
 {
         struct iattr attr;
         int error;
-        int open_flags = 0;
 
         dfprintk(VFS, "NFS: create(%s/%ld), %s\n",
                         dir->i_sb->s_id, dir->i_ino, dentry->d_name.name);
@@ -1228,10 +1590,7 @@ static int nfs_create(struct inode *dir, struct dentry *dentry, int mode,
         attr.ia_mode = mode;
         attr.ia_valid = ATTR_MODE;
 
-        if ((nd->flags & LOOKUP_CREATE) != 0)
-                open_flags = nd->intent.open.flags;
-
-        error = NFS_PROTO(dir)->create(dir, dentry, &attr, open_flags, nd);
+        error = NFS_PROTO(dir)->create(dir, dentry, &attr, 0, NULL);
         if (error != 0)
                 goto out_err;
         return 0;
@@ -1313,76 +1672,6 @@ static int nfs_rmdir(struct inode *dir, struct dentry *dentry)
         return error;
 }
 
-static int nfs_sillyrename(struct inode *dir, struct dentry *dentry)
-{
-        static unsigned int sillycounter;
-        const int      fileidsize  = sizeof(NFS_FILEID(dentry->d_inode))*2;
-        const int      countersize = sizeof(sillycounter)*2;
-        const int      slen        = sizeof(".nfs")+fileidsize+countersize-1;
-        char           silly[slen+1];
-        struct qstr    qsilly;
-        struct dentry *sdentry;
-        int            error = -EIO;
-
-        dfprintk(VFS, "NFS: silly-rename(%s/%s, ct=%d)\n",
-                dentry->d_parent->d_name.name, dentry->d_name.name, 
-                atomic_read(&dentry->d_count));
-        nfs_inc_stats(dir, NFSIOS_SILLYRENAME);
-
-        /*
-         * We don't allow a dentry to be silly-renamed twice.
-         */
-        error = -EBUSY;
-        if (dentry->d_flags & DCACHE_NFSFS_RENAMED)
-                goto out;
-
-        sprintf(silly, ".nfs%*.*Lx",
-                fileidsize, fileidsize,
-                (unsigned long long)NFS_FILEID(dentry->d_inode));
-
-        /* Return delegation in anticipation of the rename */
-        nfs_inode_return_delegation(dentry->d_inode);
-
-        sdentry = NULL;
-        do {
-                char *suffix = silly + slen - countersize;
-
-                dput(sdentry);
-                sillycounter++;
-                sprintf(suffix, "%*.*x", countersize, countersize, sillycounter);
-
-                dfprintk(VFS, "NFS: trying to rename %s to %s\n",
-                                dentry->d_name.name, silly);
-                
-                sdentry = lookup_one_len(silly, dentry->d_parent, slen);
-                /*
-                 * N.B. Better to return EBUSY here ... it could be
-                 * dangerous to delete the file while it's in use.
-                 */
-                if (IS_ERR(sdentry))
-                        goto out;
-        } while(sdentry->d_inode != NULL); /* need negative lookup */
-
-        qsilly.name = silly;
-        qsilly.len  = strlen(silly);
-        if (dentry->d_inode) {
-                error = NFS_PROTO(dir)->rename(dir, &dentry->d_name,
-                                dir, &qsilly);
-                nfs_mark_for_revalidate(dentry->d_inode);
-        } else
-                error = NFS_PROTO(dir)->rename(dir, &dentry->d_name,
-                                dir, &qsilly);
-        if (!error) {
-                nfs_set_verifier(dentry, nfs_save_change_attribute(dir));
-                d_move(dentry, sdentry);
-                error = nfs_async_unlink(dir, dentry);
-                /* If we return 0 we don't unlink */
-        }
-        dput(sdentry);
-out:
-        return error;
-}
-
 /*
  * Remove a file after making sure there are no pending writes,
  * and after checking that the file has only one user. 
@@ -1433,11 +1722,9 @@ static int nfs_unlink(struct inode *dir, struct dentry *dentry)
         dfprintk(VFS, "NFS: unlink(%s/%ld, %s)\n", dir->i_sb->s_id,
                 dir->i_ino, dentry->d_name.name);
 
-        spin_lock(&dcache_lock);
         spin_lock(&dentry->d_lock);
-        if (atomic_read(&dentry->d_count) > 1) {
+        if (dentry->d_count > 1) {
                 spin_unlock(&dentry->d_lock);
-                spin_unlock(&dcache_lock);
                 /* Start asynchronous writeout of the inode */
                 write_inode_now(dentry->d_inode, 0);
                 error = nfs_sillyrename(dir, dentry);
@@ -1448,7 +1735,6 @@ static int nfs_unlink(struct inode *dir, struct dentry *dentry)
                 need_rehash = 1;
         }
         spin_unlock(&dentry->d_lock);
-        spin_unlock(&dcache_lock);
         error = nfs_safe_remove(dentry);
         if (!error || error == -ENOENT) {
                 nfs_set_verifier(dentry, nfs_save_change_attribute(dir));
@@ -1537,10 +1823,12 @@ nfs_link(struct dentry *old_dentry, struct inode *dir, struct dentry *dentry)
                 old_dentry->d_parent->d_name.name, old_dentry->d_name.name,
                 dentry->d_parent->d_name.name, dentry->d_name.name);
 
+        nfs_inode_return_delegation(inode);
+
         d_drop(dentry);
         error = NFS_PROTO(dir)->link(inode, dir, &dentry->d_name);
         if (error == 0) {
-                atomic_inc(&inode->i_count);
+                ihold(inode);
                 d_add(dentry, inode);
         }
         return error;
@@ -1578,65 +1866,48 @@ static int nfs_rename(struct inode *old_dir, struct dentry *old_dentry,
         struct dentry *dentry = NULL, *rehash = NULL;
         int error = -EBUSY;
 
-        /*
-         * To prevent any new references to the target during the rename,
-         * we unhash the dentry and free the inode in advance.
-         */
-        if (!d_unhashed(new_dentry)) {
-                d_drop(new_dentry);
-                rehash = new_dentry;
-        }
-
         dfprintk(VFS, "NFS: rename(%s/%s -> %s/%s, ct=%d)\n",
                  old_dentry->d_parent->d_name.name, old_dentry->d_name.name,
                  new_dentry->d_parent->d_name.name, new_dentry->d_name.name,
-                 atomic_read(&new_dentry->d_count));
+                 new_dentry->d_count);
 
         /*
-         * First check whether the target is busy ... we can't
-         * safely do _any_ rename if the target is in use.
-         *
-         * For files, make a copy of the dentry and then do a 
-         * silly-rename. If the silly-rename succeeds, the
-         * copied dentry is hashed and becomes the new target.
+         * For non-directories, check whether the target is busy and if so,
+         * make a copy of the dentry and then do a silly-rename. If the
+         * silly-rename succeeds, the copied dentry is hashed and becomes
+         * the new target.
          */
-        if (!new_inode)
-                goto go_ahead;
-        if (S_ISDIR(new_inode->i_mode)) {
-                error = -EISDIR;
-                if (!S_ISDIR(old_inode->i_mode))
-                        goto out;
-        } else if (atomic_read(&new_dentry->d_count) > 2) {
-                int err;
-                /* copy the target dentry's name */
-                dentry = d_alloc(new_dentry->d_parent,
-                                 &new_dentry->d_name);
-                if (!dentry)
-                        goto out;
+        if (new_inode && !S_ISDIR(new_inode->i_mode)) {
+                /*
+                 * To prevent any new references to the target during the
+                 * rename, we unhash the dentry in advance.
+                 */
+                if (!d_unhashed(new_dentry)) {
+                        d_drop(new_dentry);
+                        rehash = new_dentry;
+                }
+
+                if (new_dentry->d_count > 2) {
+                        int err;
 
-                /* silly-rename the existing target ... */
-                err = nfs_sillyrename(new_dir, new_dentry);
-                if (!err) {
-                        new_dentry = rehash = dentry;
+                        /* copy the target dentry's name */
+                        dentry = d_alloc(new_dentry->d_parent,
+                                         &new_dentry->d_name);
+                        if (!dentry)
+                                goto out;
+
+                        /* silly-rename the existing target ... */
+                        err = nfs_sillyrename(new_dir, new_dentry);
+                        if (err)
+                                goto out;
+
+                        new_dentry = dentry;
+                        rehash = NULL;
                         new_inode = NULL;
-                        /* instantiate the replacement target */
-                        d_instantiate(new_dentry, NULL);
-                } else if (atomic_read(&new_dentry->d_count) > 1)
-                        /* dentry still busy? */
-                        goto out;
+                }
         }
 
-go_ahead:
-        /*
-         * ... prune child dentries and writebacks if needed.
-         */
-        if (atomic_read(&old_dentry->d_count) > 1) {
-                if (S_ISREG(old_inode->i_mode))
-                        nfs_wb_all(old_inode);
-                shrink_dcache_parent(old_dentry);
-        }
         nfs_inode_return_delegation(old_inode);
-
         if (new_inode != NULL)
                 nfs_inode_return_delegation(new_inode);
 
@@ -1674,28 +1945,33 @@ static void nfs_access_free_entry(struct nfs_access_entry *entry)
         smp_mb__after_atomic_dec();
 }
 
-int nfs_access_cache_shrinker(int nr_to_scan, gfp_t gfp_mask)
+static void nfs_access_free_list(struct list_head *head)
+{
+        struct nfs_access_entry *cache;
+
+        while (!list_empty(head)) {
+                cache = list_entry(head->next, struct nfs_access_entry, lru);
+                list_del(&cache->lru);
+                nfs_access_free_entry(cache);
+        }
+}
+
+int nfs_access_cache_shrinker(struct shrinker *shrink, int nr_to_scan, gfp_t gfp_mask)
 {
         LIST_HEAD(head);
-        struct nfs_inode *nfsi;
+        struct nfs_inode *nfsi, *next;
         struct nfs_access_entry *cache;
 
-restart:
+        if ((gfp_mask & GFP_KERNEL) != GFP_KERNEL)
+                return (nr_to_scan == 0) ? 0 : -1;
+
         spin_lock(&nfs_access_lru_lock);
-        list_for_each_entry(nfsi, &nfs_access_lru_list, access_cache_inode_lru) {
-                struct rw_semaphore *s_umount;
+        list_for_each_entry_safe(nfsi, next, &nfs_access_lru_list, access_cache_inode_lru) {
                 struct inode *inode;
 
                 if (nr_to_scan-- == 0)
                         break;
-                s_umount = &nfsi->vfs_inode.i_sb->s_umount;
-                if (!down_read_trylock(s_umount))
-                        continue;
-                inode = igrab(&nfsi->vfs_inode);
-                if (inode == NULL) {
-                        up_read(s_umount);
-                        continue;
-                }
+                inode = &nfsi->vfs_inode;
                 spin_lock(&inode->i_lock);
                 if (list_empty(&nfsi->access_cache_entry_lru))
                         goto remove_lru_entry;
@@ -1709,61 +1985,48 @@ restart:
                 else {
 remove_lru_entry:
                         list_del_init(&nfsi->access_cache_inode_lru);
+                        smp_mb__before_clear_bit();
                         clear_bit(NFS_INO_ACL_LRU_SET, &nfsi->flags);
+                        smp_mb__after_clear_bit();
                 }
                 spin_unlock(&inode->i_lock);
-                spin_unlock(&nfs_access_lru_lock);
-                iput(inode);
-                up_read(s_umount);
-                goto restart;
         }
         spin_unlock(&nfs_access_lru_lock);
-        while (!list_empty(&head)) {
-                cache = list_entry(head.next, struct nfs_access_entry, lru);
-                list_del(&cache->lru);
-                nfs_access_free_entry(cache);
-        }
+        nfs_access_free_list(&head);
         return (atomic_long_read(&nfs_access_nr_entries) / 100) * sysctl_vfs_cache_pressure;
 }
 
-static void __nfs_access_zap_cache(struct inode *inode)
+static void __nfs_access_zap_cache(struct nfs_inode *nfsi, struct list_head *head)
 {
-        struct nfs_inode *nfsi = NFS_I(inode);
         struct rb_root *root_node = &nfsi->access_cache;
-        struct rb_node *n, *dispose = NULL;
+        struct rb_node *n;
         struct nfs_access_entry *entry;
 
         /* Unhook entries from the cache */
         while ((n = rb_first(root_node)) != NULL) {
                 entry = rb_entry(n, struct nfs_access_entry, rb_node);
                 rb_erase(n, root_node);
-                list_del(&entry->lru);
-                n->rb_left = dispose;
-                dispose = n;
+                list_move(&entry->lru, head);
         }
         nfsi->cache_validity &= ~NFS_INO_INVALID_ACCESS;
-        spin_unlock(&inode->i_lock);
-
-        /* Now kill them all! */
-        while (dispose != NULL) {
-                n = dispose;
-                dispose = n->rb_left;
-                nfs_access_free_entry(rb_entry(n, struct nfs_access_entry, rb_node));
-        }
 }
 
 void nfs_access_zap_cache(struct inode *inode)
 {
+        LIST_HEAD(head);
+
+        if (test_bit(NFS_INO_ACL_LRU_SET, &NFS_I(inode)->flags) == 0)
+                return;
         /* Remove from global LRU init */
-        if (test_and_clear_bit(NFS_INO_ACL_LRU_SET, &NFS_I(inode)->flags)) {
-                spin_lock(&nfs_access_lru_lock);
+        spin_lock(&nfs_access_lru_lock);
+        if (test_and_clear_bit(NFS_INO_ACL_LRU_SET, &NFS_I(inode)->flags))
                 list_del_init(&NFS_I(inode)->access_cache_inode_lru);
-                spin_unlock(&nfs_access_lru_lock);
-        }
 
         spin_lock(&inode->i_lock);
-        /* This will release the spinlock */
-        __nfs_access_zap_cache(inode);
+        __nfs_access_zap_cache(NFS_I(inode), &head);
+        spin_unlock(&inode->i_lock);
+        spin_unlock(&nfs_access_lru_lock);
+        nfs_access_free_list(&head);
 }
 
 static struct nfs_access_entry *nfs_access_search_rbtree(struct inode *inode, struct rpc_cred *cred)
@@ -1796,7 +2059,7 @@ static int nfs_access_get_cached(struct inode *inode, struct rpc_cred *cred, str
         cache = nfs_access_search_rbtree(inode, cred);
         if (cache == NULL)
                 goto out;
-        if (!nfs_have_delegation(inode, FMODE_READ) &&
+        if (!nfs_have_delegated_attributes(inode) &&
             !time_in_range_open(jiffies, cache->jiffies, cache->jiffies + nfsi->attrtimeo))
                 goto out_stale;
         res->jiffies = cache->jiffies;
@@ -1814,8 +2077,8 @@ out_stale:
         nfs_access_free_entry(cache);
         return -ENOENT;
 out_zap:
-        /* This will release the spinlock */
-        __nfs_access_zap_cache(inode);
+        spin_unlock(&inode->i_lock);
+        nfs_access_zap_cache(inode);
         return -ENOENT;
 }
 
@@ -1870,9 +2133,11 @@ static void nfs_access_add_cache(struct inode *inode, struct nfs_access_entry *s
         smp_mb__after_atomic_inc();
 
         /* Add inode to global LRU list */
-        if (!test_and_set_bit(NFS_INO_ACL_LRU_SET, &NFS_I(inode)->flags)) {
+        if (!test_bit(NFS_INO_ACL_LRU_SET, &NFS_I(inode)->flags)) {
                 spin_lock(&nfs_access_lru_lock);
-                list_add_tail(&NFS_I(inode)->access_cache_inode_lru, &nfs_access_lru_list);
+                if (!test_and_set_bit(NFS_INO_ACL_LRU_SET, &NFS_I(inode)->flags))
+                        list_add_tail(&NFS_I(inode)->access_cache_inode_lru,
+                                        &nfs_access_lru_list);
                 spin_unlock(&nfs_access_lru_lock);
         }
 }
@@ -1924,17 +2189,20 @@ int nfs_may_open(struct inode *inode, struct rpc_cred *cred, int openflags)
         return nfs_do_access(inode, cred, nfs_open_permission_mask(openflags));
 }
 
-int nfs_permission(struct inode *inode, int mask)
+int nfs_permission(struct inode *inode, int mask, unsigned int flags)
 {
         struct rpc_cred *cred;
         int res = 0;
 
+        if (flags & IPERM_FLAG_RCU)
+                return -ECHILD;
+
         nfs_inc_stats(inode, NFSIOS_VFSACCESS);
 
         if ((mask & (MAY_READ | MAY_WRITE | MAY_EXEC)) == 0)
                 goto out;
         /* Is this sys_access() ? */
-        if (mask & MAY_ACCESS)
+        if (mask & (MAY_ACCESS | MAY_CHDIR))
                 goto force_lookup;
 
         switch (inode->i_mode & S_IFMT) {
@@ -1976,7 +2244,7 @@ out:
 out_notsup:
         res = nfs_revalidate_inode(NFS_SERVER(inode), inode);
         if (res == 0)
-                res = generic_permission(inode, mask, NULL);
+                res = generic_permission(inode, mask, flags, NULL);
         goto out;
 }
 
diff --git a/fs/nfs/direct.c b/fs/nfs/direct.c
index 489fc01a3204..e6ace0d93c71 100644
--- a/fs/nfs/direct.c
+++ b/fs/nfs/direct.c
@@ -44,6 +44,7 @@
 #include <linux/file.h>
 #include <linux/pagemap.h>
 #include <linux/kref.h>
+#include <linux/slab.h>
 
 #include <linux/nfs_fs.h>
 #include <linux/nfs_page.h>
@@ -68,6 +69,7 @@ struct nfs_direct_req {
 
         /* I/O parameters */
         struct nfs_open_context *ctx;           /* file open context info */
+        struct nfs_lock_context *l_ctx;         /* Lock context info */
         struct kiocb *          iocb;           /* controlling i/o request */
         struct inode *          inode;          /* target file of i/o */
 
@@ -159,6 +161,7 @@ static inline struct nfs_direct_req *nfs_direct_req_alloc(void)
         INIT_LIST_HEAD(&dreq->rewrite_list);
         dreq->iocb = NULL;
         dreq->ctx = NULL;
+        dreq->l_ctx = NULL;
         spin_lock_init(&dreq->lock);
         atomic_set(&dreq->io_count, 0);
         dreq->count = 0;
@@ -172,6 +175,8 @@ static void nfs_direct_req_free(struct kref *kref)
 {
         struct nfs_direct_req *dreq = container_of(kref, struct nfs_direct_req, kref);
 
+        if (dreq->l_ctx != NULL)
+                nfs_put_lock_context(dreq->l_ctx);
         if (dreq->ctx != NULL)
                 put_nfs_open_context(dreq->ctx);
         kmem_cache_free(nfs_direct_cachep, dreq);
@@ -255,7 +260,7 @@ static void nfs_direct_read_release(void *calldata)
 
         if (put_dreq(dreq))
                 nfs_direct_complete(dreq);
-        nfs_readdata_release(calldata);
+        nfs_readdata_free(data);
 }
 
 static const struct rpc_call_ops nfs_read_direct_ops = {
@@ -314,14 +319,14 @@ static ssize_t nfs_direct_read_schedule_segment(struct nfs_direct_req *dreq,
                                         data->npages, 1, 0, data->pagevec, NULL);
                 up_read(&current->mm->mmap_sem);
                 if (result < 0) {
-                        nfs_readdata_release(data);
+                        nfs_readdata_free(data);
                         break;
                 }
                 if ((unsigned)result < data->npages) {
                         bytes = result * PAGE_SIZE;
                         if (bytes <= pgbase) {
                                 nfs_direct_release_pages(data->pagevec, result);
-                                nfs_readdata_release(data);
+                                nfs_readdata_free(data);
                                 break;
                         }
                         bytes -= pgbase;
@@ -334,7 +339,8 @@ static ssize_t nfs_direct_read_schedule_segment(struct nfs_direct_req *dreq,
                 data->inode = inode;
                 data->cred = msg.rpc_cred;
                 data->args.fh = NFS_FH(inode);
-                data->args.context = get_nfs_open_context(ctx);
+                data->args.context = ctx;
+                data->args.lock_context = dreq->l_ctx;
                 data->args.offset = pos;
                 data->args.pgbase = pgbase;
                 data->args.pages = data->pagevec;
@@ -342,6 +348,7 @@ static ssize_t nfs_direct_read_schedule_segment(struct nfs_direct_req *dreq,
                 data->res.fattr = &data->fattr;
                 data->res.eof = 0;
                 data->res.count = bytes;
+                nfs_fattr_init(&data->fattr);
                 msg.rpc_argp = &data->args;
                 msg.rpc_resp = &data->res;
 
@@ -414,24 +421,28 @@ static ssize_t nfs_direct_read_schedule_iovec(struct nfs_direct_req *dreq,
 static ssize_t nfs_direct_read(struct kiocb *iocb, const struct iovec *iov,
                                unsigned long nr_segs, loff_t pos)
 {
-        ssize_t result = 0;
+        ssize_t result = -ENOMEM;
         struct inode *inode = iocb->ki_filp->f_mapping->host;
         struct nfs_direct_req *dreq;
 
         dreq = nfs_direct_req_alloc();
-        if (!dreq)
-                return -ENOMEM;
+        if (dreq == NULL)
+                goto out;
 
         dreq->inode = inode;
         dreq->ctx = get_nfs_open_context(nfs_file_open_context(iocb->ki_filp));
+        dreq->l_ctx = nfs_get_lock_context(dreq->ctx);
+        if (dreq->l_ctx == NULL)
+                goto out_release;
         if (!is_sync_kiocb(iocb))
                 dreq->iocb = iocb;
 
         result = nfs_direct_read_schedule_iovec(dreq, iov, nr_segs, pos);
         if (!result)
                 result = nfs_direct_wait(dreq);
+out_release:
         nfs_direct_req_release(dreq);
-
+out:
         return result;
 }
 
@@ -441,7 +452,7 @@ static void nfs_direct_free_writedata(struct nfs_direct_req *dreq)
                 struct nfs_write_data *data = list_entry(dreq->rewrite_list.next, struct nfs_write_data, pages);
                 list_del(&data->pages);
                 nfs_direct_release_pages(data->pagevec, data->npages);
-                nfs_writedata_release(data);
+                nfs_writedata_free(data);
         }
 }
 
@@ -457,6 +468,7 @@ static void nfs_direct_write_reschedule(struct nfs_direct_req *dreq)
         };
         struct rpc_task_setup task_setup_data = {
                 .rpc_client = NFS_CLIENT(inode),
+                .rpc_message = &msg,
                 .callback_ops = &nfs_write_direct_ops,
                 .workqueue = nfsiod_workqueue,
                 .flags = RPC_TASK_ASYNC,
@@ -534,7 +546,7 @@ static void nfs_direct_commit_release(void *calldata)
 
         dprintk("NFS: %5u commit returned %d\n", data->task.tk_pid, status);
         nfs_direct_write_complete(dreq, data->inode);
-        nfs_commitdata_release(calldata);
+        nfs_commit_free(data);
 }
 
 static const struct rpc_call_ops nfs_commit_direct_ops = {
@@ -570,10 +582,12 @@ static void nfs_direct_commit_schedule(struct nfs_direct_req *dreq)
         data->args.fh = NFS_FH(data->inode);
         data->args.offset = 0;
         data->args.count = 0;
-        data->args.context = get_nfs_open_context(dreq->ctx);
+        data->args.context = dreq->ctx;
+        data->args.lock_context = dreq->l_ctx;
         data->res.count = 0;
         data->res.fattr = &data->fattr;
         data->res.verf = &data->verf;
+        nfs_fattr_init(&data->fattr);
 
         NFS_PROTO(data->inode)->commit_setup(data, &msg);
 
@@ -734,14 +748,14 @@ static ssize_t nfs_direct_write_schedule_segment(struct nfs_direct_req *dreq,
                                         data->npages, 0, 0, data->pagevec, NULL);
                 up_read(&current->mm->mmap_sem);
                 if (result < 0) {
-                        nfs_writedata_release(data);
+                        nfs_writedata_free(data);
                         break;
                 }
                 if ((unsigned)result < data->npages) {
                         bytes = result * PAGE_SIZE;
                         if (bytes <= pgbase) {
                                 nfs_direct_release_pages(data->pagevec, result);
-                                nfs_writedata_release(data);
+                                nfs_writedata_free(data);
                                 break;
                         }
                         bytes -= pgbase;
@@ -756,7 +770,8 @@ static ssize_t nfs_direct_write_schedule_segment(struct nfs_direct_req *dreq,
                 data->inode = inode;
                 data->cred = msg.rpc_cred;
                 data->args.fh = NFS_FH(inode);
-                data->args.context = get_nfs_open_context(ctx);
+                data->args.context = ctx;
+                data->args.lock_context = dreq->l_ctx;
                 data->args.offset = pos;
                 data->args.pgbase = pgbase;
                 data->args.pages = data->pagevec;
@@ -765,6 +780,7 @@ static ssize_t nfs_direct_write_schedule_segment(struct nfs_direct_req *dreq,
                 data->res.fattr = &data->fattr;
                 data->res.count = bytes;
                 data->res.verf = &data->verf;
+                nfs_fattr_init(&data->fattr);
 
                 task_setup_data.task = &data->task;
                 task_setup_data.callback_data = data;
@@ -840,7 +856,7 @@ static ssize_t nfs_direct_write(struct kiocb *iocb, const struct iovec *iov,
                                 unsigned long nr_segs, loff_t pos,
                                 size_t count)
 {
-        ssize_t result = 0;
+        ssize_t result = -ENOMEM;
         struct inode *inode = iocb->ki_filp->f_mapping->host;
         struct nfs_direct_req *dreq;
         size_t wsize = NFS_SERVER(inode)->wsize;
@@ -848,22 +864,26 @@ static ssize_t nfs_direct_write(struct kiocb *iocb, const struct iovec *iov,
 
         dreq = nfs_direct_req_alloc();
         if (!dreq)
-                return -ENOMEM;
+                goto out;
         nfs_alloc_commit_data(dreq);
 
-        if (dreq->commit_data == NULL || count < wsize)
+        if (dreq->commit_data == NULL || count <= wsize)
                 sync = NFS_FILE_SYNC;
 
         dreq->inode = inode;
         dreq->ctx = get_nfs_open_context(nfs_file_open_context(iocb->ki_filp));
+        dreq->l_ctx = nfs_get_lock_context(dreq->ctx);
+        if (dreq->l_ctx == NULL)
+                goto out_release;
         if (!is_sync_kiocb(iocb))
                 dreq->iocb = iocb;
 
         result = nfs_direct_write_schedule_iovec(dreq, iov, nr_segs, pos, sync);
         if (!result)
                 result = nfs_direct_wait(dreq);
+out_release:
         nfs_direct_req_release(dreq);
-
+out:
         return result;
 }
 
@@ -934,9 +954,6 @@ out:
  * back into its cache.  We let the server do generic write
  * parameter checking and report problems.
  *
- * We also avoid an unnecessary invocation of generic_osync_inode(),
- * as it is fairly meaningless to sync the metadata of an NFS file.
- *
  * We eliminate local atime updates, see direct read above.
  *
  * We avoid unnecessary page cache invalidations for normal cached
diff --git a/fs/nfs/dns_resolve.c b/fs/nfs/dns_resolve.c
new file mode 100644
index 000000000000..a6e711ad130f
--- /dev/null
+++ b/fs/nfs/dns_resolve.c
@@ -0,0 +1,372 @@
+/*
+ * linux/fs/nfs/dns_resolve.c
+ *
+ * Copyright (c) 2009 Trond Myklebust <Trond.Myklebust@netapp.com>
+ *
+ * Resolves DNS hostnames into valid ip addresses
+ */
+
+#ifdef CONFIG_NFS_USE_KERNEL_DNS
+
+#include <linux/sunrpc/clnt.h>
+#include <linux/dns_resolver.h>
+
+ssize_t nfs_dns_resolve_name(char *name, size_t namelen,
+                struct sockaddr *sa, size_t salen)
+{
+        ssize_t ret;
+        char *ip_addr = NULL;
+        int ip_len;
+
+        ip_len = dns_query(NULL, name, namelen, NULL, &ip_addr, NULL);
+        if (ip_len > 0)
+                ret = rpc_pton(ip_addr, ip_len, sa, salen);
+        else
+                ret = -ESRCH;
+        kfree(ip_addr);
+        return ret;
+}
+
+#else
+
+#include <linux/hash.h>
+#include <linux/string.h>
+#include <linux/kmod.h>
+#include <linux/slab.h>
+#include <linux/module.h>
+#include <linux/socket.h>
+#include <linux/seq_file.h>
+#include <linux/inet.h>
+#include <linux/sunrpc/clnt.h>
+#include <linux/sunrpc/cache.h>
+#include <linux/sunrpc/svcauth.h>
+
+#include "dns_resolve.h"
+#include "cache_lib.h"
+
+#define NFS_DNS_HASHBITS 4
+#define NFS_DNS_HASHTBL_SIZE (1 << NFS_DNS_HASHBITS)
+
+static struct cache_head *nfs_dns_table[NFS_DNS_HASHTBL_SIZE];
+
+struct nfs_dns_ent {
+        struct cache_head h;
+
+        char *hostname;
+        size_t namelen;
+
+        struct sockaddr_storage addr;
+        size_t addrlen;
+};
+
+
+static void nfs_dns_ent_update(struct cache_head *cnew,
+                struct cache_head *ckey)
+{
+        struct nfs_dns_ent *new;
+        struct nfs_dns_ent *key;
+
+        new = container_of(cnew, struct nfs_dns_ent, h);
+        key = container_of(ckey, struct nfs_dns_ent, h);
+
+        memcpy(&new->addr, &key->addr, key->addrlen);
+        new->addrlen = key->addrlen;
+}
+
+static void nfs_dns_ent_init(struct cache_head *cnew,
+                struct cache_head *ckey)
+{
+        struct nfs_dns_ent *new;
+        struct nfs_dns_ent *key;
+
+        new = container_of(cnew, struct nfs_dns_ent, h);
+        key = container_of(ckey, struct nfs_dns_ent, h);
+
+        kfree(new->hostname);
+        new->hostname = kstrndup(key->hostname, key->namelen, GFP_KERNEL);
+        if (new->hostname) {
+                new->namelen = key->namelen;
+                nfs_dns_ent_update(cnew, ckey);
+        } else {
+                new->namelen = 0;
+                new->addrlen = 0;
+        }
+}
+
+static void nfs_dns_ent_put(struct kref *ref)
+{
+        struct nfs_dns_ent *item;
+
+        item = container_of(ref, struct nfs_dns_ent, h.ref);
+        kfree(item->hostname);
+        kfree(item);
+}
+
+static struct cache_head *nfs_dns_ent_alloc(void)
+{
+        struct nfs_dns_ent *item = kmalloc(sizeof(*item), GFP_KERNEL);
+
+        if (item != NULL) {
+                item->hostname = NULL;
+                item->namelen = 0;
+                item->addrlen = 0;
+                return &item->h;
+        }
+        return NULL;
+};
+
+static unsigned int nfs_dns_hash(const struct nfs_dns_ent *key)
+{
+        return hash_str(key->hostname, NFS_DNS_HASHBITS);
+}
+
+static void nfs_dns_request(struct cache_detail *cd,
+                struct cache_head *ch,
+                char **bpp, int *blen)
+{
+        struct nfs_dns_ent *key = container_of(ch, struct nfs_dns_ent, h);
+
+        qword_add(bpp, blen, key->hostname);
+        (*bpp)[-1] = '\n';
+}
+
+static int nfs_dns_upcall(struct cache_detail *cd,
+                struct cache_head *ch)
+{
+        struct nfs_dns_ent *key = container_of(ch, struct nfs_dns_ent, h);
+        int ret;
+
+        ret = nfs_cache_upcall(cd, key->hostname);
+        if (ret)
+                ret = sunrpc_cache_pipe_upcall(cd, ch, nfs_dns_request);
+        return ret;
+}
+
+static int nfs_dns_match(struct cache_head *ca,
+                struct cache_head *cb)
+{
+        struct nfs_dns_ent *a;
+        struct nfs_dns_ent *b;
+
+        a = container_of(ca, struct nfs_dns_ent, h);
+        b = container_of(cb, struct nfs_dns_ent, h);
+
+        if (a->namelen == 0 || a->namelen != b->namelen)
+                return 0;
+        return memcmp(a->hostname, b->hostname, a->namelen) == 0;
+}
+
+static int nfs_dns_show(struct seq_file *m, struct cache_detail *cd,
+                struct cache_head *h)
+{
+        struct nfs_dns_ent *item;
+        long ttl;
+
+        if (h == NULL) {
+                seq_puts(m, "# ip address      hostname        ttl\n");
+                return 0;
+        }
+        item = container_of(h, struct nfs_dns_ent, h);
+        ttl = item->h.expiry_time - seconds_since_boot();
+        if (ttl < 0)
+                ttl = 0;
+
+        if (!test_bit(CACHE_NEGATIVE, &h->flags)) {
+                char buf[INET6_ADDRSTRLEN+IPV6_SCOPE_ID_LEN+1];
+
+                rpc_ntop((struct sockaddr *)&item->addr, buf, sizeof(buf));
+                seq_printf(m, "%15s ", buf);
+        } else
+                seq_puts(m, "<none>          ");
+        seq_printf(m, "%15s %ld\n", item->hostname, ttl);
+        return 0;
+}
+
+static struct nfs_dns_ent *nfs_dns_lookup(struct cache_detail *cd,
+                struct nfs_dns_ent *key)
+{
+        struct cache_head *ch;
+
+        ch = sunrpc_cache_lookup(cd,
+                        &key->h,
+                        nfs_dns_hash(key));
+        if (!ch)
+                return NULL;
+        return container_of(ch, struct nfs_dns_ent, h);
+}
+
+static struct nfs_dns_ent *nfs_dns_update(struct cache_detail *cd,
+                struct nfs_dns_ent *new,
+                struct nfs_dns_ent *key)
+{
+        struct cache_head *ch;
+
+        ch = sunrpc_cache_update(cd,
+                        &new->h, &key->h,
+                        nfs_dns_hash(key));
+        if (!ch)
+                return NULL;
+        return container_of(ch, struct nfs_dns_ent, h);
+}
+
+static int nfs_dns_parse(struct cache_detail *cd, char *buf, int buflen)
+{
+        char buf1[NFS_DNS_HOSTNAME_MAXLEN+1];
+        struct nfs_dns_ent key, *item;
+        unsigned long ttl;
+        ssize_t len;
+        int ret = -EINVAL;
+
+        if (buf[buflen-1] != '\n')
+                goto out;
+        buf[buflen-1] = '\0';
+
+        len = qword_get(&buf, buf1, sizeof(buf1));
+        if (len <= 0)
+                goto out;
+        key.addrlen = rpc_pton(buf1, len,
+                        (struct sockaddr *)&key.addr,
+                        sizeof(key.addr));
+
+        len = qword_get(&buf, buf1, sizeof(buf1));
+        if (len <= 0)
+                goto out;
+
+        key.hostname = buf1;
+        key.namelen = len;
+        memset(&key.h, 0, sizeof(key.h));
+
+        ttl = get_expiry(&buf);
+        if (ttl == 0)
+                goto out;
+        key.h.expiry_time = ttl + seconds_since_boot();
+
+        ret = -ENOMEM;
+        item = nfs_dns_lookup(cd, &key);
+        if (item == NULL)
+                goto out;
+
+        if (key.addrlen == 0)
+                set_bit(CACHE_NEGATIVE, &key.h.flags);
+
+        item = nfs_dns_update(cd, &key, item);
+        if (item == NULL)
+                goto out;
+
+        ret = 0;
+        cache_put(&item->h, cd);
+out:
+        return ret;
+}
+
+static struct cache_detail nfs_dns_resolve = {
+        .owner = THIS_MODULE,
+        .hash_size = NFS_DNS_HASHTBL_SIZE,
+        .hash_table = nfs_dns_table,
+        .name = "dns_resolve",
+        .cache_put = nfs_dns_ent_put,
+        .cache_upcall = nfs_dns_upcall,
+        .cache_parse = nfs_dns_parse,
+        .cache_show = nfs_dns_show,
+        .match = nfs_dns_match,
+        .init = nfs_dns_ent_init,
+        .update = nfs_dns_ent_update,
+        .alloc = nfs_dns_ent_alloc,
+};
+
+static int do_cache_lookup(struct cache_detail *cd,
+                struct nfs_dns_ent *key,
+                struct nfs_dns_ent **item,
+                struct nfs_cache_defer_req *dreq)
+{
+        int ret = -ENOMEM;
+
+        *item = nfs_dns_lookup(cd, key);
+        if (*item) {
+                ret = cache_check(cd, &(*item)->h, &dreq->req);
+                if (ret)
+                        *item = NULL;
+        }
+        return ret;
+}
+
+static int do_cache_lookup_nowait(struct cache_detail *cd,
+                struct nfs_dns_ent *key,
+                struct nfs_dns_ent **item)
+{
+        int ret = -ENOMEM;
+
+        *item = nfs_dns_lookup(cd, key);
+        if (!*item)
+                goto out_err;
+        ret = -ETIMEDOUT;
+        if (!test_bit(CACHE_VALID, &(*item)->h.flags)
+                        || (*item)->h.expiry_time < seconds_since_boot()
+                        || cd->flush_time > (*item)->h.last_refresh)
+                goto out_put;
+        ret = -ENOENT;
+        if (test_bit(CACHE_NEGATIVE, &(*item)->h.flags))
+                goto out_put;
+        return 0;
+out_put:
+        cache_put(&(*item)->h, cd);
+out_err:
+        *item = NULL;
+        return ret;
+}
+
+static int do_cache_lookup_wait(struct cache_detail *cd,
+                struct nfs_dns_ent *key,
+                struct nfs_dns_ent **item)
+{
+        struct nfs_cache_defer_req *dreq;
+        int ret = -ENOMEM;
+
+        dreq = nfs_cache_defer_req_alloc();
+        if (!dreq)
+                goto out;
+        ret = do_cache_lookup(cd, key, item, dreq);
+        if (ret == -EAGAIN) {
+                ret = nfs_cache_wait_for_upcall(dreq);
+                if (!ret)
+                        ret = do_cache_lookup_nowait(cd, key, item);
+        }
+        nfs_cache_defer_req_put(dreq);
+out:
+        return ret;
+}
+
+ssize_t nfs_dns_resolve_name(char *name, size_t namelen,
+                struct sockaddr *sa, size_t salen)
+{
+        struct nfs_dns_ent key = {
+                .hostname = name,
+                .namelen = namelen,
+        };
+        struct nfs_dns_ent *item = NULL;
+        ssize_t ret;
+
+        ret = do_cache_lookup_wait(&nfs_dns_resolve, &key, &item);
+        if (ret == 0) {
+                if (salen >= item->addrlen) {
+                        memcpy(sa, &item->addr, item->addrlen);
+                        ret = item->addrlen;
+                } else
+                        ret = -EOVERFLOW;
+                cache_put(&item->h, &nfs_dns_resolve);
+        } else if (ret == -ENOENT)
+                ret = -ESRCH;
+        return ret;
+}
+
+int nfs_dns_resolver_init(void)
+{
+        return nfs_cache_register(&nfs_dns_resolve);
+}
+
+void nfs_dns_resolver_destroy(void)
+{
+        nfs_cache_unregister(&nfs_dns_resolve);
+}
+
+#endif
diff --git a/fs/nfs/dns_resolve.h b/fs/nfs/dns_resolve.h
new file mode 100644
index 000000000000..199bb5543a91
--- /dev/null
+++ b/fs/nfs/dns_resolve.h
@@ -0,0 +1,26 @@
+/*
+ * Resolve DNS hostnames into valid ip addresses
+ */
+#ifndef __LINUX_FS_NFS_DNS_RESOLVE_H
+#define __LINUX_FS_NFS_DNS_RESOLVE_H
+
+#define NFS_DNS_HOSTNAME_MAXLEN (128)
+
+
+#ifdef CONFIG_NFS_USE_KERNEL_DNS
+static inline int nfs_dns_resolver_init(void)
+{
+        return 0;
+}
+
+static inline void nfs_dns_resolver_destroy(void)
+{}
+#else
+extern int nfs_dns_resolver_init(void);
+extern void nfs_dns_resolver_destroy(void);
+#endif
+
+extern ssize_t nfs_dns_resolve_name(char *name, size_t namelen,
+                struct sockaddr *sa, size_t salen);
+
+#endif
diff --git a/fs/nfs/file.c b/fs/nfs/file.c
index 0055b813ec2c..7bf029ef4084 100644
--- a/fs/nfs/file.c
+++ b/fs/nfs/file.c
@@ -24,10 +24,10 @@
 #include <linux/nfs_fs.h>
 #include <linux/nfs_mount.h>
 #include <linux/mm.h>
-#include <linux/slab.h>
 #include <linux/pagemap.h>
-#include <linux/smp_lock.h>
 #include <linux/aio.h>
+#include <linux/gfp.h>
+#include <linux/swap.h>
 
 #include <asm/uaccess.h>
 #include <asm/system.h>
@@ -36,6 +36,7 @@
 #include "internal.h"
 #include "iostat.h"
 #include "fscache.h"
+#include "pnfs.h"
 
 #define NFSDBG_FACILITY         NFSDBG_FILE
 
@@ -54,13 +55,13 @@ static ssize_t nfs_file_splice_write(struct pipe_inode_info *pipe,
 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);
-static int  nfs_file_fsync(struct file *, struct dentry *dentry, int datasync);
+static int  nfs_file_fsync(struct file *, int datasync);
 static int nfs_check_flags(int flags);
 static int nfs_lock(struct file *filp, int cmd, struct file_lock *fl);
 static int nfs_flock(struct file *filp, int cmd, struct file_lock *fl);
 static int nfs_setlease(struct file *file, long arg, struct file_lock **fl);
 
-static struct vm_operations_struct nfs_file_vm_ops;
+static const struct vm_operations_struct nfs_file_vm_ops;
 
 const struct file_operations nfs_file_operations = {
         .llseek         = nfs_file_llseek,
@@ -124,11 +125,11 @@ nfs_file_open(struct inode *inode, struct file *filp)
                         filp->f_path.dentry->d_parent->d_name.name,
                         filp->f_path.dentry->d_name.name);
 
+        nfs_inc_stats(inode, NFSIOS_VFSOPEN);
         res = nfs_check_flags(filp->f_flags);
         if (res)
                 return res;
 
-        nfs_inc_stats(inode, NFSIOS_VFSOPEN);
         res = nfs_open(inode, filp);
         return res;
 }
@@ -162,14 +163,17 @@ static int nfs_revalidate_file_size(struct inode *inode, struct file *filp)
         struct nfs_server *server = NFS_SERVER(inode);
         struct nfs_inode *nfsi = NFS_I(inode);
 
-        if (server->flags & NFS_MOUNT_NOAC)
-                goto force_reval;
+        if (nfs_have_delegated_attributes(inode))
+                goto out_noreval;
+
         if (filp->f_flags & O_DIRECT)
                 goto force_reval;
-        if (nfsi->npages != 0)
-                return 0;
-        if (!(nfsi->cache_validity & NFS_INO_REVAL_PAGECACHE) && !nfs_attribute_timeout(inode))
-                return 0;
+        if (nfsi->cache_validity & NFS_INO_REVAL_PAGECACHE)
+                goto force_reval;
+        if (nfs_attribute_timeout(inode))
+                goto force_reval;
+out_noreval:
+        return 0;
 force_reval:
         return __nfs_revalidate_inode(server, inode);
 }
@@ -200,37 +204,11 @@ static loff_t nfs_file_llseek(struct file *filp, loff_t offset, int origin)
 }
 
 /*
- * Helper for nfs_file_flush() and nfs_file_fsync()
- *
- * Notice that it clears the NFS_CONTEXT_ERROR_WRITE before synching to
- * disk, but it retrieves and clears ctx->error after synching, despite
- * the two being set at the same time in nfs_context_set_write_error().
- * This is because the former is used to notify the _next_ call to
- * nfs_file_write() that a write error occured, and hence cause it to
- * fall back to doing a synchronous write.
- */
-static int nfs_do_fsync(struct nfs_open_context *ctx, struct inode *inode)
-{
-        int have_error, status;
-        int ret = 0;
-
-        have_error = test_and_clear_bit(NFS_CONTEXT_ERROR_WRITE, &ctx->flags);
-        status = nfs_wb_all(inode);
-        have_error |= test_bit(NFS_CONTEXT_ERROR_WRITE, &ctx->flags);
-        if (have_error)
-                ret = xchg(&ctx->error, 0);
-        if (!ret)
-                ret = status;
-        return ret;
-}
-
-/*
  * Flush all dirty pages, and check for write errors.
  */
 static int
 nfs_file_flush(struct file *file, fl_owner_t id)
 {
-        struct nfs_open_context *ctx = nfs_file_open_context(file);
         struct dentry   *dentry = file->f_path.dentry;
         struct inode    *inode = dentry->d_inode;
 
@@ -238,12 +216,12 @@ nfs_file_flush(struct file *file, fl_owner_t id)
                         dentry->d_parent->d_name.name,
                         dentry->d_name.name);
 
+        nfs_inc_stats(inode, NFSIOS_VFSFLUSH);
         if ((file->f_mode & FMODE_WRITE) == 0)
                 return 0;
-        nfs_inc_stats(inode, NFSIOS_VFSFLUSH);
 
         /* Flush writes to the server and return any errors */
-        return nfs_do_fsync(ctx, inode);
+        return vfs_fsync(file, 0);
 }
 
 static ssize_t
@@ -263,9 +241,11 @@ nfs_file_read(struct kiocb *iocb, const struct iovec *iov,
                 (unsigned long) count, (unsigned long) pos);
 
         result = nfs_revalidate_mapping(inode, iocb->ki_filp->f_mapping);
-        nfs_add_stats(inode, NFSIOS_NORMALREADBYTES, count);
-        if (!result)
+        if (!result) {
                 result = generic_file_aio_read(iocb, iov, nr_segs, pos);
+                if (result > 0)
+                        nfs_add_stats(inode, NFSIOS_NORMALREADBYTES, result);
+        }
         return result;
 }
 
@@ -283,8 +263,11 @@ nfs_file_splice_read(struct file *filp, loff_t *ppos,
                 (unsigned long) count, (unsigned long long) *ppos);
 
         res = nfs_revalidate_mapping(inode, filp->f_mapping);
-        if (!res)
+        if (!res) {
                 res = generic_file_splice_read(filp, ppos, pipe, count, flags);
+                if (res > 0)
+                        nfs_add_stats(inode, NFSIOS_NORMALREADBYTES, res);
+        }
         return res;
 }
 
@@ -313,19 +296,73 @@ nfs_file_mmap(struct file * file, struct vm_area_struct * vma)
  * Flush any dirty pages for this process, and check for write errors.
  * The return status from this call provides a reliable indication of
  * whether any write errors occurred for this process.
+ *
+ * Notice that it clears the NFS_CONTEXT_ERROR_WRITE before synching to
+ * disk, but it retrieves and clears ctx->error after synching, despite
+ * the two being set at the same time in nfs_context_set_write_error().
+ * This is because the former is used to notify the _next_ call to
+ * nfs_file_write() that a write error occured, and hence cause it to
+ * fall back to doing a synchronous write.
  */
 static int
-nfs_file_fsync(struct file *file, struct dentry *dentry, int datasync)
+nfs_file_fsync(struct file *file, int datasync)
 {
+        struct dentry *dentry = file->f_path.dentry;
         struct nfs_open_context *ctx = nfs_file_open_context(file);
         struct inode *inode = dentry->d_inode;
+        int have_error, status;
+        int ret = 0;
+
 
         dprintk("NFS: fsync file(%s/%s) datasync %d\n",
                         dentry->d_parent->d_name.name, dentry->d_name.name,
                         datasync);
 
         nfs_inc_stats(inode, NFSIOS_VFSFSYNC);
-        return nfs_do_fsync(ctx, inode);
+        have_error = test_and_clear_bit(NFS_CONTEXT_ERROR_WRITE, &ctx->flags);
+        status = nfs_commit_inode(inode, FLUSH_SYNC);
+        have_error |= test_bit(NFS_CONTEXT_ERROR_WRITE, &ctx->flags);
+        if (have_error)
+                ret = xchg(&ctx->error, 0);
+        if (!ret && status < 0)
+                ret = status;
+        return ret;
+}
+
+/*
+ * Decide whether a read/modify/write cycle may be more efficient
+ * then a modify/write/read cycle when writing to a page in the
+ * page cache.
+ *
+ * The modify/write/read cycle may occur if a page is read before
+ * being completely filled by the writer.  In this situation, the
+ * page must be completely written to stable storage on the server
+ * before it can be refilled by reading in the page from the server.
+ * This can lead to expensive, small, FILE_SYNC mode writes being
+ * done.
+ *
+ * It may be more efficient to read the page first if the file is
+ * open for reading in addition to writing, the page is not marked
+ * as Uptodate, it is not dirty or waiting to be committed,
+ * indicating that it was previously allocated and then modified,
+ * that there were valid bytes of data in that range of the file,
+ * and that the new data won't completely replace the old data in
+ * that range of the file.
+ */
+static int nfs_want_read_modify_write(struct file *file, struct page *page,
+                        loff_t pos, unsigned len)
+{
+        unsigned int pglen = nfs_page_length(page);
+        unsigned int offset = pos & (PAGE_CACHE_SIZE - 1);
+        unsigned int end = offset + len;
+
+        if ((file->f_mode & FMODE_READ) &&      /* open for read? */
+            !PageUptodate(page) &&              /* Uptodate? */
+            !PagePrivate(page) &&               /* i/o request already? */
+            pglen &&                            /* valid bytes of file? */
+            (end < pglen || offset))            /* replace all valid bytes? */
+                return 1;
+        return 0;
 }
 
 /*
@@ -341,15 +378,20 @@ static int nfs_write_begin(struct file *file, struct address_space *mapping,
                         struct page **pagep, void **fsdata)
 {
         int ret;
-        pgoff_t index;
+        pgoff_t index = pos >> PAGE_CACHE_SHIFT;
         struct page *page;
-        index = pos >> PAGE_CACHE_SHIFT;
+        int once_thru = 0;
 
         dfprintk(PAGECACHE, "NFS: write_begin(%s/%s(%ld), %u@%lld)\n",
                 file->f_path.dentry->d_parent->d_name.name,
                 file->f_path.dentry->d_name.name,
                 mapping->host->i_ino, len, (long long) pos);
 
+        pnfs_update_layout(mapping->host,
+                           nfs_file_open_context(file),
+                           IOMODE_RW);
+
+start:
         /*
          * Prevent starvation issues if someone is doing a consistency
          * sync-to-disk
@@ -368,6 +410,13 @@ static int nfs_write_begin(struct file *file, struct address_space *mapping,
         if (ret) {
                 unlock_page(page);
                 page_cache_release(page);
+        } else if (!once_thru &&
+                   nfs_want_read_modify_write(file, page, pos, len)) {
+                once_thru = 1;
+                ret = nfs_readpage(file, page);
+                page_cache_release(page);
+                if (!ret)
+                        goto start;
         }
         return ret;
 }
@@ -441,8 +490,19 @@ static void nfs_invalidate_page(struct page *page, unsigned long offset)
  */
 static int nfs_release_page(struct page *page, gfp_t gfp)
 {
+        struct address_space *mapping = page->mapping;
+
         dfprintk(PAGECACHE, "NFS: release_page(%p)\n", page);
 
+        /* Only do I/O if gfp is a superset of GFP_KERNEL */
+        if (mapping && (gfp & GFP_KERNEL) == GFP_KERNEL) {
+                int how = FLUSH_SYNC;
+
+                /* Don't let kswapd deadlock waiting for OOM RPC calls */
+                if (current_is_kswapd())
+                        how = 0;
+                nfs_commit_inode(mapping->host, how);
+        }
         /* If PagePrivate() is set, then the page is not freeable */
         if (PagePrivate(page))
                 return 0;
@@ -480,7 +540,9 @@ const struct address_space_operations nfs_file_aops = {
         .invalidatepage = nfs_invalidate_page,
         .releasepage = nfs_release_page,
         .direct_IO = nfs_direct_IO,
+        .migratepage = nfs_migrate_page,
         .launder_page = nfs_launder_page,
+        .error_remove_page = generic_error_remove_page,
 };
 
 /*
@@ -494,7 +556,7 @@ static int nfs_vm_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf)
         struct file *filp = vma->vm_file;
         struct dentry *dentry = filp->f_path.dentry;
         unsigned pagelen;
-        int ret = -EINVAL;
+        int ret = VM_FAULT_NOPAGE;
         struct address_space *mapping;
 
         dfprintk(PAGECACHE, "NFS: vm_page_mkwrite(%s/%s(%ld), offset %lld)\n",
@@ -510,24 +572,23 @@ static int nfs_vm_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf)
         if (mapping != dentry->d_inode->i_mapping)
                 goto out_unlock;
 
-        ret = 0;
         pagelen = nfs_page_length(page);
         if (pagelen == 0)
                 goto out_unlock;
 
-        ret = nfs_flush_incompatible(filp, page);
-        if (ret != 0)
-                goto out_unlock;
+        ret = VM_FAULT_LOCKED;
+        if (nfs_flush_incompatible(filp, page) == 0 &&
+            nfs_updatepage(filp, page, 0, pagelen) == 0)
+                goto out;
 
-        ret = nfs_updatepage(filp, page, 0, pagelen);
+        ret = VM_FAULT_SIGBUS;
 out_unlock:
-        if (!ret)
-                return VM_FAULT_LOCKED;
         unlock_page(page);
-        return VM_FAULT_SIGBUS;
+out:
+        return ret;
 }
 
-static struct vm_operations_struct nfs_file_vm_ops = {
+static const struct vm_operations_struct nfs_file_vm_ops = {
         .fault = filemap_fault,
         .page_mkwrite = nfs_vm_page_mkwrite,
 };
@@ -536,7 +597,7 @@ static int nfs_need_sync_write(struct file *filp, struct inode *inode)
 {
         struct nfs_open_context *ctx;
 
-        if (IS_SYNC(inode) || (filp->f_flags & O_SYNC))
+        if (IS_SYNC(inode) || (filp->f_flags & O_DSYNC))
                 return 1;
         ctx = nfs_file_open_context(filp);
         if (test_bit(NFS_CONTEXT_ERROR_WRITE, &ctx->flags))
@@ -549,6 +610,7 @@ static ssize_t nfs_file_write(struct kiocb *iocb, const struct iovec *iov,
 {
         struct dentry * dentry = iocb->ki_filp->f_path.dentry;
         struct inode * inode = dentry->d_inode;
+        unsigned long written = 0;
         ssize_t result;
         size_t count = iov_length(iov, nr_segs);
 
@@ -575,14 +637,18 @@ static ssize_t nfs_file_write(struct kiocb *iocb, const struct iovec *iov,
         if (!count)
                 goto out;
 
-        nfs_add_stats(inode, NFSIOS_NORMALWRITTENBYTES, count);
         result = generic_file_aio_write(iocb, iov, nr_segs, pos);
-        /* Return error values for O_SYNC and IS_SYNC() */
+        if (result > 0)
+                written = result;
+
+        /* Return error values for O_DSYNC and IS_SYNC() */
         if (result >= 0 && nfs_need_sync_write(iocb->ki_filp, inode)) {
-                int err = nfs_do_fsync(nfs_file_open_context(iocb->ki_filp), inode);
+                int err = vfs_fsync(iocb->ki_filp, 0);
                 if (err < 0)
                         result = err;
         }
+        if (result > 0)
+                nfs_add_stats(inode, NFSIOS_NORMALWRITTENBYTES, written);
 out:
         return result;
 
@@ -597,6 +663,7 @@ static ssize_t nfs_file_splice_write(struct pipe_inode_info *pipe,
 {
         struct dentry *dentry = filp->f_path.dentry;
         struct inode *inode = dentry->d_inode;
+        unsigned long written = 0;
         ssize_t ret;
 
         dprintk("NFS splice_write(%s/%s, %lu@%llu)\n",
@@ -607,21 +674,26 @@ static ssize_t nfs_file_splice_write(struct pipe_inode_info *pipe,
          * 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)
+                written = ret;
+
         if (ret >= 0 && nfs_need_sync_write(filp, inode)) {
-                int err = nfs_do_fsync(nfs_file_open_context(filp), inode);
+                int err = vfs_fsync(filp, 0);
                 if (err < 0)
                         ret = err;
         }
+        if (ret > 0)
+                nfs_add_stats(inode, NFSIOS_NORMALWRITTENBYTES, written);
         return ret;
 }
 
-static int do_getlk(struct file *filp, int cmd, struct file_lock *fl)
+static int
+do_getlk(struct file *filp, int cmd, struct file_lock *fl, int is_local)
 {
         struct inode *inode = filp->f_mapping->host;
         int status = 0;
+        unsigned int saved_type = fl->fl_type;
 
         /* Try local locking first */
         posix_test_lock(filp, fl);
@@ -629,11 +701,12 @@ static int do_getlk(struct file *filp, int cmd, struct file_lock *fl)
                 /* found a conflict */
                 goto out;
         }
+        fl->fl_type = saved_type;
 
         if (nfs_have_delegation(inode, FMODE_READ))
                 goto out_noconflict;
 
-        if (NFS_SERVER(inode)->flags & NFS_MOUNT_NONLM)
+        if (is_local)
                 goto out_noconflict;
 
         status = NFS_PROTO(inode)->lock(filp, cmd, fl);
@@ -657,14 +730,11 @@ static int do_vfs_lock(struct file *file, struct file_lock *fl)
                 default:
                         BUG();
         }
-        if (res < 0)
-                dprintk(KERN_WARNING "%s: VFS is out of sync with lock manager"
-                        " - error %d!\n",
-                                __func__, res);
         return res;
 }
 
-static int do_unlk(struct file *filp, int cmd, struct file_lock *fl)
+static int
+do_unlk(struct file *filp, int cmd, struct file_lock *fl, int is_local)
 {
         struct inode *inode = filp->f_mapping->host;
         int status;
@@ -679,15 +749,24 @@ 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.
          */
-        /* Use local locking if mounted with "-onolock" */
-        if (!(NFS_SERVER(inode)->flags & NFS_MOUNT_NONLM))
+        /*
+         * Use local locking if mounted with "-onolock" or with appropriate
+         * "-olocal_lock="
+         */
+        if (!is_local)
                 status = NFS_PROTO(inode)->lock(filp, cmd, fl);
         else
                 status = do_vfs_lock(filp, fl);
         return status;
 }
 
-static int do_setlk(struct file *filp, int cmd, struct file_lock *fl)
+static int
+is_time_granular(struct timespec *ts) {
+        return ((ts->tv_sec == 0) && (ts->tv_nsec <= 1000));
+}
+
+static int
+do_setlk(struct file *filp, int cmd, struct file_lock *fl, int is_local)
 {
         struct inode *inode = filp->f_mapping->host;
         int status;
@@ -700,20 +779,31 @@ static int do_setlk(struct file *filp, int cmd, struct file_lock *fl)
         if (status != 0)
                 goto out;
 
-        /* Use local locking if mounted with "-onolock" */
-        if (!(NFS_SERVER(inode)->flags & NFS_MOUNT_NONLM))
+        /*
+         * Use local locking if mounted with "-onolock" or with appropriate
+         * "-olocal_lock="
+         */
+        if (!is_local)
                 status = NFS_PROTO(inode)->lock(filp, cmd, fl);
         else
                 status = do_vfs_lock(filp, fl);
         if (status < 0)
                 goto out;
+
         /*
-         * Make sure we clear the cache whenever we try to get the lock.
+         * Revalidate the cache if the server has time stamps granular
+         * enough to detect subsecond changes.  Otherwise, clear the
+         * cache to prevent missing any changes.
+         *
          * This makes locking act as a cache coherency point.
          */
         nfs_sync_mapping(filp->f_mapping);
-        if (!nfs_have_delegation(inode, FMODE_READ))
-                nfs_zap_caches(inode);
+        if (!nfs_have_delegation(inode, FMODE_READ)) {
+                if (is_time_granular(&NFS_SERVER(inode)->time_delta))
+                        __nfs_revalidate_inode(NFS_SERVER(inode), inode);
+                else
+                        nfs_zap_caches(inode);
+        }
 out:
         return status;
 }
@@ -725,6 +815,7 @@ static int nfs_lock(struct file *filp, int cmd, struct file_lock *fl)
 {
         struct inode *inode = filp->f_mapping->host;
         int ret = -ENOLCK;
+        int is_local = 0;
 
         dprintk("NFS: lock(%s/%s, t=%x, fl=%x, r=%lld:%lld)\n",
                         filp->f_path.dentry->d_parent->d_name.name,
@@ -738,6 +829,9 @@ static int nfs_lock(struct file *filp, int cmd, struct file_lock *fl)
         if (__mandatory_lock(inode) && fl->fl_type != F_UNLCK)
                 goto out_err;
 
+        if (NFS_SERVER(inode)->flags & NFS_MOUNT_LOCAL_FCNTL)
+                is_local = 1;
+
         if (NFS_PROTO(inode)->lock_check_bounds != NULL) {
                 ret = NFS_PROTO(inode)->lock_check_bounds(fl);
                 if (ret < 0)
@@ -745,11 +839,11 @@ static int nfs_lock(struct file *filp, int cmd, struct file_lock *fl)
         }
 
         if (IS_GETLK(cmd))
-                ret = do_getlk(filp, cmd, fl);
+                ret = do_getlk(filp, cmd, fl, is_local);
         else if (fl->fl_type == F_UNLCK)
-                ret = do_unlk(filp, cmd, fl);
+                ret = do_unlk(filp, cmd, fl, is_local);
         else
-                ret = do_setlk(filp, cmd, fl);
+                ret = do_setlk(filp, cmd, fl, is_local);
 out_err:
         return ret;
 }
@@ -759,6 +853,9 @@ out_err:
  */
 static int nfs_flock(struct file *filp, int cmd, struct file_lock *fl)
 {
+        struct inode *inode = filp->f_mapping->host;
+        int is_local = 0;
+
         dprintk("NFS: flock(%s/%s, t=%x, fl=%x)\n",
                         filp->f_path.dentry->d_parent->d_name.name,
                         filp->f_path.dentry->d_name.name,
@@ -767,14 +864,17 @@ static int nfs_flock(struct file *filp, int cmd, struct file_lock *fl)
         if (!(fl->fl_flags & FL_FLOCK))
                 return -ENOLCK;
 
+        if (NFS_SERVER(inode)->flags & NFS_MOUNT_LOCAL_FLOCK)
+                is_local = 1;
+
         /* We're simulating flock() locks using posix locks on the server */
         fl->fl_owner = (fl_owner_t)filp;
         fl->fl_start = 0;
         fl->fl_end = OFFSET_MAX;
 
         if (fl->fl_type == F_UNLCK)
-                return do_unlk(filp, cmd, fl);
-        return do_setlk(filp, cmd, fl);
+                return do_unlk(filp, cmd, fl, is_local);
+        return do_setlk(filp, cmd, fl, is_local);
 }
 
 /*
@@ -786,6 +886,5 @@ static int nfs_setlease(struct file *file, long arg, struct file_lock **fl)
         dprintk("NFS: setlease(%s/%s, arg=%ld)\n",
                         file->f_path.dentry->d_parent->d_name.name,
                         file->f_path.dentry->d_name.name, arg);
-
         return -EINVAL;
 }
diff --git a/fs/nfs/fscache.c b/fs/nfs/fscache.c
index 379be678cb7e..ce153a6b3aec 100644
--- a/fs/nfs/fscache.c
+++ b/fs/nfs/fscache.c
@@ -17,6 +17,7 @@
 #include <linux/nfs_fs_sb.h>
 #include <linux/in6.h>
 #include <linux/seq_file.h>
+#include <linux/slab.h>
 
 #include "internal.h"
 #include "iostat.h"
@@ -58,17 +59,34 @@ void nfs_fscache_release_client_cookie(struct nfs_client *clp)
 /*
  * Get the cache cookie for an NFS superblock.  We have to handle
  * uniquification here because the cache doesn't do it for us.
+ *
+ * The default uniquifier is just an empty string, but it may be overridden
+ * either by the 'fsc=xxx' option to mount, or by inheriting it from the parent
+ * superblock across an automount point of some nature.
  */
-void nfs_fscache_get_super_cookie(struct super_block *sb,
-                                  struct nfs_parsed_mount_data *data)
+void nfs_fscache_get_super_cookie(struct super_block *sb, const char *uniq,
+                                  struct nfs_clone_mount *mntdata)
 {
         struct nfs_fscache_key *key, *xkey;
         struct nfs_server *nfss = NFS_SB(sb);
         struct rb_node **p, *parent;
-        const char *uniq = data->fscache_uniq ?: "";
         int diff, ulen;
 
-        ulen = strlen(uniq);
+        if (uniq) {
+                ulen = strlen(uniq);
+        } else if (mntdata) {
+                struct nfs_server *mnt_s = NFS_SB(mntdata->sb);
+                if (mnt_s->fscache_key) {
+                        uniq = mnt_s->fscache_key->key.uniquifier;
+                        ulen = mnt_s->fscache_key->key.uniq_len;
+                }
+        }
+
+        if (!uniq) {
+                uniq = "";
+                ulen = 1;
+        }
+
         key = kzalloc(sizeof(*key) + ulen, GFP_KERNEL);
         if (!key)
                 return;
@@ -337,22 +355,17 @@ void nfs_fscache_reset_inode_cookie(struct inode *inode)
  */
 int nfs_fscache_release_page(struct page *page, gfp_t gfp)
 {
-        struct nfs_inode *nfsi = NFS_I(page->mapping->host);
-        struct fscache_cookie *cookie = nfsi->fscache;
-
-        BUG_ON(!cookie);
-
-        if (fscache_check_page_write(cookie, page)) {
-                if (!(gfp & __GFP_WAIT))
-                        return 0;
-                fscache_wait_on_page_write(cookie, page);
-        }
-
         if (PageFsCache(page)) {
+                struct nfs_inode *nfsi = NFS_I(page->mapping->host);
+                struct fscache_cookie *cookie = nfsi->fscache;
+
+                BUG_ON(!cookie);
                 dfprintk(FSCACHE, "NFS: fscache releasepage (0x%p/0x%p/0x%p)\n",
                          cookie, page, nfsi);
 
-                fscache_uncache_page(cookie, page);
+                if (!fscache_maybe_release_page(cookie, page, gfp))
+                        return 0;
+
                 nfs_add_fscache_stats(page->mapping->host,
                                       NFSIOS_FSCACHE_PAGES_UNCACHED, 1);
         }
@@ -454,7 +467,8 @@ int __nfs_readpages_from_fscache(struct nfs_open_context *ctx,
                                  struct list_head *pages,
                                  unsigned *nr_pages)
 {
-        int ret, npages = *nr_pages;
+        unsigned npages = *nr_pages;
+        int ret;
 
         dfprintk(FSCACHE, "NFS: nfs_getpages_from_fscache (0x%p/%u/0x%p)\n",
                  NFS_I(inode)->fscache, npages, inode);
diff --git a/fs/nfs/fscache.h b/fs/nfs/fscache.h
index 6e809bb0ff08..b9c572d0679f 100644
--- a/fs/nfs/fscache.h
+++ b/fs/nfs/fscache.h
@@ -74,7 +74,8 @@ extern void nfs_fscache_get_client_cookie(struct nfs_client *);
 extern void nfs_fscache_release_client_cookie(struct nfs_client *);
 
 extern void nfs_fscache_get_super_cookie(struct super_block *,
-                                         struct nfs_parsed_mount_data *);
+                                         const char *,
+                                         struct nfs_clone_mount *);
 extern void nfs_fscache_release_super_cookie(struct super_block *);
 
 extern void nfs_fscache_init_inode_cookie(struct inode *);
@@ -173,7 +174,8 @@ static inline void nfs_fscache_release_client_cookie(struct nfs_client *clp) {}
 
 static inline void nfs_fscache_get_super_cookie(
         struct super_block *sb,
-        struct nfs_parsed_mount_data *data)
+        const char *uniq,
+        struct nfs_clone_mount *mntdata)
 {
 }
 static inline void nfs_fscache_release_super_cookie(struct super_block *sb) {}
diff --git a/fs/nfs/getroot.c b/fs/nfs/getroot.c
index 46177cb87064..5596c6a2881e 100644
--- a/fs/nfs/getroot.c
+++ b/fs/nfs/getroot.c
@@ -30,7 +30,6 @@
 #include <linux/nfs_idmap.h>
 #include <linux/vfs.h>
 #include <linux/namei.h>
-#include <linux/mnt_namespace.h>
 #include <linux/security.h>
 
 #include <asm/system.h>
@@ -55,8 +54,7 @@ static int nfs_superblock_set_dummy_root(struct super_block *sb, struct inode *i
                         iput(inode);
                         return -ENOMEM;
                 }
-                /* Circumvent igrab(): we know the inode is not being freed */
-                atomic_inc(&inode->i_count);
+                ihold(inode);
                 /*
                  * Ensure that this dentry is invisible to d_find_alias().
                  * Otherwise, it may be spliced into the tree by
@@ -65,9 +63,11 @@ static int nfs_superblock_set_dummy_root(struct super_block *sb, struct inode *i
                  * This again causes shrink_dcache_for_umount_subtree() to
                  * Oops, since the test for IS_ROOT() will fail.
                  */
-                spin_lock(&dcache_lock);
+                spin_lock(&sb->s_root->d_inode->i_lock);
+                spin_lock(&sb->s_root->d_lock);
                 list_del_init(&sb->s_root->d_alias);
-                spin_unlock(&dcache_lock);
+                spin_unlock(&sb->s_root->d_lock);
+                spin_unlock(&sb->s_root->d_inode->i_lock);
         }
         return 0;
 }
@@ -79,159 +79,94 @@ struct dentry *nfs_get_root(struct super_block *sb, struct nfs_fh *mntfh)
 {
         struct nfs_server *server = NFS_SB(sb);
         struct nfs_fsinfo fsinfo;
-        struct nfs_fattr fattr;
-        struct dentry *mntroot;
+        struct dentry *ret;
         struct inode *inode;
         int error;
 
         /* get the actual root for this mount */
-        fsinfo.fattr = &fattr;
+        fsinfo.fattr = nfs_alloc_fattr();
+        if (fsinfo.fattr == NULL)
+                return ERR_PTR(-ENOMEM);
 
         error = server->nfs_client->rpc_ops->getroot(server, mntfh, &fsinfo);
         if (error < 0) {
                 dprintk("nfs_get_root: getattr error = %d\n", -error);
-                return ERR_PTR(error);
+                ret = ERR_PTR(error);
+                goto out;
         }
 
         inode = nfs_fhget(sb, mntfh, fsinfo.fattr);
         if (IS_ERR(inode)) {
                 dprintk("nfs_get_root: get root inode failed\n");
-                return ERR_CAST(inode);
+                ret = ERR_CAST(inode);
+                goto out;
         }
 
         error = nfs_superblock_set_dummy_root(sb, inode);
-        if (error != 0)
-                return ERR_PTR(error);
+        if (error != 0) {
+                ret = ERR_PTR(error);
+                goto out;
+        }
 
         /* root dentries normally start off anonymous and get spliced in later
          * if the dentry tree reaches them; however if the dentry already
          * exists, we'll pick it up at this point and use it as the root
          */
-        mntroot = d_obtain_alias(inode);
-        if (IS_ERR(mntroot)) {
+        ret = d_obtain_alias(inode);
+        if (IS_ERR(ret)) {
                 dprintk("nfs_get_root: get root dentry failed\n");
-                return mntroot;
+                goto out;
         }
 
-        security_d_instantiate(mntroot, inode);
-
-        if (!mntroot->d_op)
-                mntroot->d_op = server->nfs_client->rpc_ops->dentry_ops;
+        security_d_instantiate(ret, inode);
 
-        return mntroot;
+        if (ret->d_op == NULL)
+                d_set_d_op(ret, server->nfs_client->rpc_ops->dentry_ops);
+out:
+        nfs_free_fattr(fsinfo.fattr);
+        return ret;
 }
 
 #ifdef CONFIG_NFS_V4
 
-/*
- * Do a simple pathwalk from the root FH of the server to the nominated target
- * of the mountpoint
- * - give error on symlinks
- * - give error on ".." occurring in the path
- * - follow traversals
- */
-int nfs4_path_walk(struct nfs_server *server,
-                   struct nfs_fh *mntfh,
-                   const char *path)
+int nfs4_get_rootfh(struct nfs_server *server, struct nfs_fh *mntfh)
 {
         struct nfs_fsinfo fsinfo;
-        struct nfs_fattr fattr;
-        struct nfs_fh lastfh;
-        struct qstr name;
-        int ret;
+        int ret = -ENOMEM;
 
-        dprintk("--> nfs4_path_walk(,,%s)\n", path);
+        dprintk("--> nfs4_get_rootfh()\n");
 
-        fsinfo.fattr = &fattr;
-        nfs_fattr_init(&fattr);
-
-        /* Eat leading slashes */
-        while (*path == '/')
-                path++;
+        fsinfo.fattr = nfs_alloc_fattr();
+        if (fsinfo.fattr == NULL)
+                goto out;
 
         /* Start by getting the root filehandle from the server */
         ret = server->nfs_client->rpc_ops->getroot(server, mntfh, &fsinfo);
         if (ret < 0) {
-                dprintk("nfs4_get_root: getroot error = %d\n", -ret);
-                return ret;
+                dprintk("nfs4_get_rootfh: getroot error = %d\n", -ret);
+                goto out;
         }
 
-        if (!S_ISDIR(fattr.mode)) {
-                printk(KERN_ERR "nfs4_get_root:"
+        if (!(fsinfo.fattr->valid & NFS_ATTR_FATTR_TYPE)
+                        || !S_ISDIR(fsinfo.fattr->mode)) {
+                printk(KERN_ERR "nfs4_get_rootfh:"
                        " getroot encountered non-directory\n");
-                return -ENOTDIR;
+                ret = -ENOTDIR;
+                goto out;
         }
 
-        /* FIXME: It is quite valid for the server to return a referral here */
-        if (fattr.valid & NFS_ATTR_FATTR_V4_REFERRAL) {
-                printk(KERN_ERR "nfs4_get_root:"
+        if (fsinfo.fattr->valid & NFS_ATTR_FATTR_V4_REFERRAL) {
+                printk(KERN_ERR "nfs4_get_rootfh:"
                        " getroot obtained referral\n");
-                return -EREMOTE;
-        }
-
-next_component:
-        dprintk("Next: %s\n", path);
-
-        /* extract the next bit of the path */
-        if (!*path)
-                goto path_walk_complete;
-
-        name.name = path;
-        while (*path && *path != '/')
-                path++;
-        name.len = path - (const char *) name.name;
-
-        if (name.len > NFS4_MAXNAMLEN)
-                return -ENAMETOOLONG;
-
-eat_dot_dir:
-        while (*path == '/')
-                path++;
-
-        if (path[0] == '.' && (path[1] == '/' || !path[1])) {
-                path += 2;
-                goto eat_dot_dir;
-        }
-
-        /* FIXME: Why shouldn't the user be able to use ".." in the path? */
-        if (path[0] == '.' && path[1] == '.' && (path[2] == '/' || !path[2])
-            ) {
-                printk(KERN_ERR "nfs4_get_root:"
-                       " Mount path contains reference to \"..\"\n");
-                return -EINVAL;
+                ret = -EREMOTE;
+                goto out;
         }
 
-        /* lookup the next FH in the sequence */
-        memcpy(&lastfh, mntfh, sizeof(lastfh));
-
-        dprintk("LookupFH: %*.*s [%s]\n", name.len, name.len, name.name, path);
-
-        ret = server->nfs_client->rpc_ops->lookupfh(server, &lastfh, &name,
-                                                    mntfh, &fattr);
-        if (ret < 0) {
-                dprintk("nfs4_get_root: getroot error = %d\n", -ret);
-                return ret;
-        }
-
-        if (!S_ISDIR(fattr.mode)) {
-                printk(KERN_ERR "nfs4_get_root:"
-                       " lookupfh encountered non-directory\n");
-                return -ENOTDIR;
-        }
-
-        /* FIXME: Referrals are quite valid here too */
-        if (fattr.valid & NFS_ATTR_FATTR_V4_REFERRAL) {
-                printk(KERN_ERR "nfs4_get_root:"
-                       " lookupfh obtained referral\n");
-                return -EREMOTE;
-        }
-
-        goto next_component;
-
-path_walk_complete:
-        memcpy(&server->fsid, &fattr.fsid, sizeof(server->fsid));
-        dprintk("<-- nfs4_path_walk() = 0\n");
-        return 0;
+        memcpy(&server->fsid, &fsinfo.fattr->fsid, sizeof(server->fsid));
+out:
+        nfs_free_fattr(fsinfo.fattr);
+        dprintk("<-- nfs4_get_rootfh() = %d\n", ret);
+        return ret;
 }
 
 /*
@@ -240,8 +175,8 @@ path_walk_complete:
 struct dentry *nfs4_get_root(struct super_block *sb, struct nfs_fh *mntfh)
 {
         struct nfs_server *server = NFS_SB(sb);
-        struct nfs_fattr fattr;
-        struct dentry *mntroot;
+        struct nfs_fattr *fattr = NULL;
+        struct dentry *ret;
         struct inode *inode;
         int error;
 
@@ -255,40 +190,50 @@ struct dentry *nfs4_get_root(struct super_block *sb, struct nfs_fh *mntfh)
                 return ERR_PTR(error);
         }
 
+        fattr = nfs_alloc_fattr();
+        if (fattr == NULL)
+                return ERR_PTR(-ENOMEM);;
+
         /* get the actual root for this mount */
-        error = server->nfs_client->rpc_ops->getattr(server, mntfh, &fattr);
+        error = server->nfs_client->rpc_ops->getattr(server, mntfh, fattr);
         if (error < 0) {
                 dprintk("nfs_get_root: getattr error = %d\n", -error);
-                return ERR_PTR(error);
+                ret = ERR_PTR(error);
+                goto out;
         }
 
-        inode = nfs_fhget(sb, mntfh, &fattr);
+        inode = nfs_fhget(sb, mntfh, fattr);
         if (IS_ERR(inode)) {
                 dprintk("nfs_get_root: get root inode failed\n");
-                return ERR_CAST(inode);
+                ret = ERR_CAST(inode);
+                goto out;
         }
 
         error = nfs_superblock_set_dummy_root(sb, inode);
-        if (error != 0)
-                return ERR_PTR(error);
+        if (error != 0) {
+                ret = ERR_PTR(error);
+                goto out;
+        }
 
         /* root dentries normally start off anonymous and get spliced in later
          * if the dentry tree reaches them; however if the dentry already
          * exists, we'll pick it up at this point and use it as the root
          */
-        mntroot = d_obtain_alias(inode);
-        if (IS_ERR(mntroot)) {
+        ret = d_obtain_alias(inode);
+        if (IS_ERR(ret)) {
                 dprintk("nfs_get_root: get root dentry failed\n");
-                return mntroot;
+                goto out;
         }
 
-        security_d_instantiate(mntroot, inode);
+        security_d_instantiate(ret, inode);
 
-        if (!mntroot->d_op)
-                mntroot->d_op = server->nfs_client->rpc_ops->dentry_ops;
+        if (ret->d_op == NULL)
+                d_set_d_op(ret, server->nfs_client->rpc_ops->dentry_ops);
 
+out:
+        nfs_free_fattr(fattr);
         dprintk("<-- nfs4_get_root()\n");
-        return mntroot;
+        return ret;
 }
 
 #endif /* CONFIG_NFS_V4 */
diff --git a/fs/nfs/idmap.c b/fs/nfs/idmap.c
index 86147b0ab2cf..18696882f1c6 100644
--- a/fs/nfs/idmap.c
+++ b/fs/nfs/idmap.c
@@ -34,6 +34,212 @@
  *  SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
  */
 
+#ifdef CONFIG_NFS_USE_NEW_IDMAPPER
+
+#include <linux/slab.h>
+#include <linux/cred.h>
+#include <linux/nfs_idmap.h>
+#include <linux/keyctl.h>
+#include <linux/key-type.h>
+#include <linux/rcupdate.h>
+#include <linux/kernel.h>
+#include <linux/err.h>
+
+#include <keys/user-type.h>
+
+#define NFS_UINT_MAXLEN 11
+
+const struct cred *id_resolver_cache;
+
+struct key_type key_type_id_resolver = {
+        .name           = "id_resolver",
+        .instantiate    = user_instantiate,
+        .match          = user_match,
+        .revoke         = user_revoke,
+        .destroy        = user_destroy,
+        .describe       = user_describe,
+        .read           = user_read,
+};
+
+int nfs_idmap_init(void)
+{
+        struct cred *cred;
+        struct key *keyring;
+        int ret = 0;
+
+        printk(KERN_NOTICE "Registering the %s key type\n", key_type_id_resolver.name);
+
+        cred = prepare_kernel_cred(NULL);
+        if (!cred)
+                return -ENOMEM;
+
+        keyring = key_alloc(&key_type_keyring, ".id_resolver", 0, 0, cred,
+                             (KEY_POS_ALL & ~KEY_POS_SETATTR) |
+                             KEY_USR_VIEW | KEY_USR_READ,
+                             KEY_ALLOC_NOT_IN_QUOTA);
+        if (IS_ERR(keyring)) {
+                ret = PTR_ERR(keyring);
+                goto failed_put_cred;
+        }
+
+        ret = key_instantiate_and_link(keyring, NULL, 0, NULL, NULL);
+        if (ret < 0)
+                goto failed_put_key;
+
+        ret = register_key_type(&key_type_id_resolver);
+        if (ret < 0)
+                goto failed_put_key;
+
+        cred->thread_keyring = keyring;
+        cred->jit_keyring = KEY_REQKEY_DEFL_THREAD_KEYRING;
+        id_resolver_cache = cred;
+        return 0;
+
+failed_put_key:
+        key_put(keyring);
+failed_put_cred:
+        put_cred(cred);
+        return ret;
+}
+
+void nfs_idmap_quit(void)
+{
+        key_revoke(id_resolver_cache->thread_keyring);
+        unregister_key_type(&key_type_id_resolver);
+        put_cred(id_resolver_cache);
+}
+
+/*
+ * Assemble the description to pass to request_key()
+ * This function will allocate a new string and update dest to point
+ * at it.  The caller is responsible for freeing dest.
+ *
+ * On error 0 is returned.  Otherwise, the length of dest is returned.
+ */
+static ssize_t nfs_idmap_get_desc(const char *name, size_t namelen,
+                                const char *type, size_t typelen, char **desc)
+{
+        char *cp;
+        size_t desclen = typelen + namelen + 2;
+
+        *desc = kmalloc(desclen, GFP_KERNEL);
+        if (!*desc)
+                return -ENOMEM;
+
+        cp = *desc;
+        memcpy(cp, type, typelen);
+        cp += typelen;
+        *cp++ = ':';
+
+        memcpy(cp, name, namelen);
+        cp += namelen;
+        *cp = '\0';
+        return desclen;
+}
+
+static ssize_t nfs_idmap_request_key(const char *name, size_t namelen,
+                const char *type, void *data, size_t data_size)
+{
+        const struct cred *saved_cred;
+        struct key *rkey;
+        char *desc;
+        struct user_key_payload *payload;
+        ssize_t ret;
+
+        ret = nfs_idmap_get_desc(name, namelen, type, strlen(type), &desc);
+        if (ret <= 0)
+                goto out;
+
+        saved_cred = override_creds(id_resolver_cache);
+        rkey = request_key(&key_type_id_resolver, desc, "");
+        revert_creds(saved_cred);
+        kfree(desc);
+        if (IS_ERR(rkey)) {
+                ret = PTR_ERR(rkey);
+                goto out;
+        }
+
+        rcu_read_lock();
+        rkey->perm |= KEY_USR_VIEW;
+
+        ret = key_validate(rkey);
+        if (ret < 0)
+                goto out_up;
+
+        payload = rcu_dereference(rkey->payload.data);
+        if (IS_ERR_OR_NULL(payload)) {
+                ret = PTR_ERR(payload);
+                goto out_up;
+        }
+
+        ret = payload->datalen;
+        if (ret > 0 && ret <= data_size)
+                memcpy(data, payload->data, ret);
+        else
+                ret = -EINVAL;
+
+out_up:
+        rcu_read_unlock();
+        key_put(rkey);
+out:
+        return ret;
+}
+
+
+/* ID -> Name */
+static ssize_t nfs_idmap_lookup_name(__u32 id, const char *type, char *buf, size_t buflen)
+{
+        char id_str[NFS_UINT_MAXLEN];
+        int id_len;
+        ssize_t ret;
+
+        id_len = snprintf(id_str, sizeof(id_str), "%u", id);
+        ret = nfs_idmap_request_key(id_str, id_len, type, buf, buflen);
+        if (ret < 0)
+                return -EINVAL;
+        return ret;
+}
+
+/* Name -> ID */
+static int nfs_idmap_lookup_id(const char *name, size_t namelen,
+                                const char *type, __u32 *id)
+{
+        char id_str[NFS_UINT_MAXLEN];
+        long id_long;
+        ssize_t data_size;
+        int ret = 0;
+
+        data_size = nfs_idmap_request_key(name, namelen, type, id_str, NFS_UINT_MAXLEN);
+        if (data_size <= 0) {
+                ret = -EINVAL;
+        } else {
+                ret = strict_strtol(id_str, 10, &id_long);
+                *id = (__u32)id_long;
+        }
+        return ret;
+}
+
+int nfs_map_name_to_uid(struct nfs_client *clp, const char *name, size_t namelen, __u32 *uid)
+{
+        return nfs_idmap_lookup_id(name, namelen, "uid", uid);
+}
+
+int nfs_map_group_to_gid(struct nfs_client *clp, const char *name, size_t namelen, __u32 *gid)
+{
+        return nfs_idmap_lookup_id(name, namelen, "gid", gid);
+}
+
+int nfs_map_uid_to_name(struct nfs_client *clp, __u32 uid, char *buf, size_t buflen)
+{
+        return nfs_idmap_lookup_name(uid, "user", buf, buflen);
+}
+int nfs_map_gid_to_group(struct nfs_client *clp, __u32 gid, char *buf, size_t buflen)
+{
+        return nfs_idmap_lookup_name(gid, "group", buf, buflen);
+}
+
+#else  /* CONFIG_NFS_USE_NEW_IDMAPPER not defined */
+
 #include <linux/module.h>
 #include <linux/mutex.h>
 #include <linux/init.h>
@@ -101,7 +307,7 @@ static void idmap_pipe_destroy_msg(struct rpc_pipe_msg *);
 
 static unsigned int fnvhash32(const void *, size_t);
 
-static struct rpc_pipe_ops idmap_upcall_ops = {
+static const struct rpc_pipe_ops idmap_upcall_ops = {
         .upcall         = idmap_pipe_upcall,
         .downcall       = idmap_pipe_downcall,
         .destroy_msg    = idmap_pipe_destroy_msg,
@@ -119,8 +325,8 @@ nfs_idmap_new(struct nfs_client *clp)
         if (idmap == NULL)
                 return -ENOMEM;
 
-        idmap->idmap_dentry = rpc_mkpipe(clp->cl_rpcclient->cl_dentry, "idmap",
-                                         idmap, &idmap_upcall_ops, 0);
+        idmap->idmap_dentry = rpc_mkpipe(clp->cl_rpcclient->cl_path.dentry,
+                        "idmap", idmap, &idmap_upcall_ops, 0);
         if (IS_ERR(idmap->idmap_dentry)) {
                 error = PTR_ERR(idmap->idmap_dentry);
                 kfree(idmap);
@@ -503,16 +709,17 @@ int nfs_map_group_to_gid(struct nfs_client *clp, const char *name, size_t namele
         return nfs_idmap_id(idmap, &idmap->idmap_group_hash, name, namelen, uid);
 }
 
-int nfs_map_uid_to_name(struct nfs_client *clp, __u32 uid, char *buf)
+int nfs_map_uid_to_name(struct nfs_client *clp, __u32 uid, char *buf, size_t buflen)
 {
         struct idmap *idmap = clp->cl_idmap;
 
         return nfs_idmap_name(idmap, &idmap->idmap_user_hash, uid, buf);
 }
-int nfs_map_gid_to_group(struct nfs_client *clp, __u32 uid, char *buf)
+int nfs_map_gid_to_group(struct nfs_client *clp, __u32 uid, char *buf, size_t buflen)
 {
         struct idmap *idmap = clp->cl_idmap;
 
         return nfs_idmap_name(idmap, &idmap->idmap_group_hash, uid, buf);
 }
 
+#endif /* CONFIG_NFS_USE_NEW_IDMAPPER */
diff --git a/fs/nfs/inode.c b/fs/nfs/inode.c
index 64f87194d390..ce00b704452c 100644
--- a/fs/nfs/inode.c
+++ b/fs/nfs/inode.c
@@ -30,13 +30,13 @@
 #include <linux/nfs_mount.h>
 #include <linux/nfs4_mount.h>
 #include <linux/lockd/bind.h>
-#include <linux/smp_lock.h>
 #include <linux/seq_file.h>
 #include <linux/mount.h>
 #include <linux/nfs_idmap.h>
 #include <linux/vfs.h>
 #include <linux/inet.h>
 #include <linux/nfs_xdr.h>
+#include <linux/slab.h>
 
 #include <asm/system.h>
 #include <asm/uaccess.h>
@@ -47,6 +47,8 @@
 #include "iostat.h"
 #include "internal.h"
 #include "fscache.h"
+#include "dns_resolve.h"
+#include "pnfs.h"
 
 #define NFSDBG_FACILITY         NFSDBG_VFS
 
@@ -97,23 +99,7 @@ u64 nfs_compat_user_ino64(u64 fileid)
         return ino;
 }
 
-int nfs_write_inode(struct inode *inode, int sync)
-{
-        int ret;
-
-        if (sync) {
-                ret = filemap_fdatawait(inode->i_mapping);
-                if (ret == 0)
-                        ret = nfs_commit_inode(inode, FLUSH_SYNC);
-        } else
-                ret = nfs_commit_inode(inode, 0);
-        if (ret >= 0)
-                return 0;
-        __mark_inode_dirty(inode, I_DIRTY_DATASYNC);
-        return ret;
-}
-
-void nfs_clear_inode(struct inode *inode)
+static void nfs_clear_inode(struct inode *inode)
 {
         /*
          * The following should never happen...
@@ -125,21 +111,24 @@ void nfs_clear_inode(struct inode *inode)
         nfs_fscache_release_inode_cookie(inode);
 }
 
+void nfs_evict_inode(struct inode *inode)
+{
+        truncate_inode_pages(&inode->i_data, 0);
+        end_writeback(inode);
+        nfs_clear_inode(inode);
+}
+
 /**
  * nfs_sync_mapping - helper to flush all mmapped dirty data to disk
  */
 int nfs_sync_mapping(struct address_space *mapping)
 {
-        int ret;
+        int ret = 0;
 
-        if (mapping->nrpages == 0)
-                return 0;
-        unmap_mapping_range(mapping, 0, 0, 0);
-        ret = filemap_write_and_wait(mapping);
-        if (ret != 0)
-                goto out;
-        ret = nfs_wb_all(mapping->host);
-out:
+        if (mapping->nrpages != 0) {
+                unmap_mapping_range(mapping, 0, 0, 0);
+                ret = nfs_wb_all(mapping->host);
+        }
         return ret;
 }
 
@@ -246,9 +235,6 @@ nfs_init_locked(struct inode *inode, void *opaque)
         return 0;
 }
 
-/* Don't use READDIRPLUS on directories that we believe are too large */
-#define NFS_LIMIT_READDIRPLUS (8*PAGE_SIZE)
-
 /*
  * This is our front-end to iget that looks up inodes by file handle
  * instead of inode number.
@@ -287,6 +273,11 @@ nfs_fhget(struct super_block *sb, struct nfs_fh *fh, struct nfs_fattr *fattr)
                 /* We can't support update_atime(), since the server will reset it */
                 inode->i_flags |= S_NOATIME|S_NOCMTIME;
                 inode->i_mode = fattr->mode;
+                if ((fattr->valid & NFS_ATTR_FATTR_MODE) == 0
+                                && nfs_server_capable(inode, NFS_CAP_MODE))
+                        nfsi->cache_validity |= NFS_INO_INVALID_ATTR
+                                | NFS_INO_INVALID_ACCESS
+                                | NFS_INO_INVALID_ACL;
                 /* Why so? Because we want revalidate for devices/FIFOs, and
                  * that's precisely what we have in nfs_file_inode_operations.
                  */
@@ -298,8 +289,8 @@ nfs_fhget(struct super_block *sb, struct nfs_fh *fh, struct nfs_fattr *fattr)
                 } else if (S_ISDIR(inode->i_mode)) {
                         inode->i_op = NFS_SB(sb)->nfs_client->rpc_ops->dir_inode_ops;
                         inode->i_fop = &nfs_dir_operations;
-                        if (nfs_server_capable(inode, NFS_CAP_READDIRPLUS)
-                            && fattr->size <= NFS_LIMIT_READDIRPLUS)
+                        inode->i_data.a_ops = &nfs_dir_aops;
+                        if (nfs_server_capable(inode, NFS_CAP_READDIRPLUS))
                                 set_bit(NFS_INO_ADVISE_RDPLUS, &NFS_I(inode)->flags);
                         /* Deal with crossing mountpoints */
                         if ((fattr->valid & NFS_ATTR_FATTR_FSID)
@@ -331,20 +322,46 @@ nfs_fhget(struct super_block *sb, struct nfs_fh *fh, struct nfs_fattr *fattr)
                 nfsi->attr_gencount = fattr->gencount;
                 if (fattr->valid & NFS_ATTR_FATTR_ATIME)
                         inode->i_atime = fattr->atime;
+                else if (nfs_server_capable(inode, NFS_CAP_ATIME))
+                        nfsi->cache_validity |= NFS_INO_INVALID_ATTR;
                 if (fattr->valid & NFS_ATTR_FATTR_MTIME)
                         inode->i_mtime = fattr->mtime;
+                else if (nfs_server_capable(inode, NFS_CAP_MTIME))
+                        nfsi->cache_validity |= NFS_INO_INVALID_ATTR
+                                | NFS_INO_INVALID_DATA;
                 if (fattr->valid & NFS_ATTR_FATTR_CTIME)
                         inode->i_ctime = fattr->ctime;
+                else if (nfs_server_capable(inode, NFS_CAP_CTIME))
+                        nfsi->cache_validity |= NFS_INO_INVALID_ATTR
+                                | NFS_INO_INVALID_ACCESS
+                                | NFS_INO_INVALID_ACL;
                 if (fattr->valid & NFS_ATTR_FATTR_CHANGE)
                         nfsi->change_attr = fattr->change_attr;
+                else if (nfs_server_capable(inode, NFS_CAP_CHANGE_ATTR))
+                        nfsi->cache_validity |= NFS_INO_INVALID_ATTR
+                                | NFS_INO_INVALID_DATA;
                 if (fattr->valid & NFS_ATTR_FATTR_SIZE)
                         inode->i_size = nfs_size_to_loff_t(fattr->size);
+                else
+                        nfsi->cache_validity |= NFS_INO_INVALID_ATTR
+                                | NFS_INO_INVALID_DATA
+                                | NFS_INO_REVAL_PAGECACHE;
                 if (fattr->valid & NFS_ATTR_FATTR_NLINK)
                         inode->i_nlink = fattr->nlink;
+                else if (nfs_server_capable(inode, NFS_CAP_NLINK))
+                        nfsi->cache_validity |= NFS_INO_INVALID_ATTR;
                 if (fattr->valid & NFS_ATTR_FATTR_OWNER)
                         inode->i_uid = fattr->uid;
+                else if (nfs_server_capable(inode, NFS_CAP_OWNER))
+                        nfsi->cache_validity |= NFS_INO_INVALID_ATTR
+                                | NFS_INO_INVALID_ACCESS
+                                | NFS_INO_INVALID_ACL;
                 if (fattr->valid & NFS_ATTR_FATTR_GROUP)
                         inode->i_gid = fattr->gid;
+                else if (nfs_server_capable(inode, NFS_CAP_OWNER_GROUP))
+                        nfsi->cache_validity |= NFS_INO_INVALID_ATTR
+                                | NFS_INO_INVALID_ACCESS
+                                | NFS_INO_INVALID_ACL;
                 if (fattr->valid & NFS_ATTR_FATTR_BLOCKS_USED)
                         inode->i_blocks = fattr->du.nfs2.blocks;
                 if (fattr->valid & NFS_ATTR_FATTR_SPACE_USED) {
@@ -381,8 +398,8 @@ int
 nfs_setattr(struct dentry *dentry, struct iattr *attr)
 {
         struct inode *inode = dentry->d_inode;
-        struct nfs_fattr fattr;
-        int error;
+        struct nfs_fattr *fattr;
+        int error = -ENOMEM;
 
         nfs_inc_stats(inode, NFSIOS_VFSSETATTR);
 
@@ -401,18 +418,22 @@ nfs_setattr(struct dentry *dentry, struct iattr *attr)
                 return 0;
 
         /* Write all dirty data */
-        if (S_ISREG(inode->i_mode)) {
-                filemap_write_and_wait(inode->i_mapping);
+        if (S_ISREG(inode->i_mode))
                 nfs_wb_all(inode);
-        }
+
+        fattr = nfs_alloc_fattr();
+        if (fattr == NULL)
+                goto out;
         /*
          * Return any delegations if we're going to change ACLs
          */
         if ((attr->ia_valid & (ATTR_MODE|ATTR_UID|ATTR_GID)) != 0)
                 nfs_inode_return_delegation(inode);
-        error = NFS_PROTO(inode)->setattr(dentry, &fattr, attr);
+        error = NFS_PROTO(inode)->setattr(dentry, fattr, attr);
         if (error == 0)
-                nfs_refresh_inode(inode, &fattr);
+                nfs_refresh_inode(inode, fattr);
+        nfs_free_fattr(fattr);
+out:
         return error;
 }
 
@@ -427,49 +448,21 @@ nfs_setattr(struct dentry *dentry, struct iattr *attr)
  */
 static int nfs_vmtruncate(struct inode * inode, loff_t offset)
 {
-        if (i_size_read(inode) < offset) {
-                unsigned long limit;
+        loff_t oldsize;
+        int err;
 
-                limit = current->signal->rlim[RLIMIT_FSIZE].rlim_cur;
-                if (limit != RLIM_INFINITY && offset > limit)
-                        goto out_sig;
-                if (offset > inode->i_sb->s_maxbytes)
-                        goto out_big;
-                spin_lock(&inode->i_lock);
-                i_size_write(inode, offset);
-                spin_unlock(&inode->i_lock);
-        } else {
-                struct address_space *mapping = inode->i_mapping;
+        err = inode_newsize_ok(inode, offset);
+        if (err)
+                goto out;
 
-                /*
-                 * truncation of in-use swapfiles is disallowed - it would
-                 * cause subsequent swapout to scribble on the now-freed
-                 * blocks.
-                 */
-                if (IS_SWAPFILE(inode))
-                        return -ETXTBSY;
-                spin_lock(&inode->i_lock);
-                i_size_write(inode, offset);
-                spin_unlock(&inode->i_lock);
+        spin_lock(&inode->i_lock);
+        oldsize = inode->i_size;
+        i_size_write(inode, offset);
+        spin_unlock(&inode->i_lock);
 
-                /*
-                 * unmap_mapping_range is called twice, first simply for
-                 * efficiency so that truncate_inode_pages does fewer
-                 * single-page unmaps.  However after this first call, and
-                 * before truncate_inode_pages finishes, it is possible for
-                 * private pages to be COWed, which remain after
-                 * truncate_inode_pages finishes, hence the second
-                 * unmap_mapping_range call must be made for correctness.
-                 */
-                unmap_mapping_range(mapping, offset + PAGE_SIZE - 1, 0, 1);
-                truncate_inode_pages(mapping, offset);
-                unmap_mapping_range(mapping, offset + PAGE_SIZE - 1, 0, 1);
-        }
-        return 0;
-out_sig:
-        send_sig(SIGXFSZ, current, 0);
-out_big:
-        return -EFBIG;
+        truncate_pagecache(inode, oldsize, offset);
+out:
+        return err;
 }
 
 /**
@@ -508,17 +501,11 @@ int nfs_getattr(struct vfsmount *mnt, struct dentry *dentry, struct kstat *stat)
         int need_atime = NFS_I(inode)->cache_validity & NFS_INO_INVALID_ATIME;
         int err;
 
-        /*
-         * Flush out writes to the server in order to update c/mtime.
-         *
-         * Hold the i_mutex to suspend application writes temporarily;
-         * this prevents long-running writing applications from blocking
-         * nfs_wb_nocommit.
-         */
+        /* Flush out writes to the server in order to update c/mtime.  */
         if (S_ISREG(inode->i_mode)) {
-                mutex_lock(&inode->i_mutex);
-                nfs_wb_nocommit(inode);
-                mutex_unlock(&inode->i_mutex);
+                err = filemap_write_and_wait(inode->i_mapping);
+                if (err)
+                        goto out;
         }
 
         /*
@@ -542,9 +529,72 @@ int nfs_getattr(struct vfsmount *mnt, struct dentry *dentry, struct kstat *stat)
                 generic_fillattr(inode, stat);
                 stat->ino = nfs_compat_user_ino64(NFS_FILEID(inode));
         }
+out:
         return err;
 }
 
+static void nfs_init_lock_context(struct nfs_lock_context *l_ctx)
+{
+        atomic_set(&l_ctx->count, 1);
+        l_ctx->lockowner = current->files;
+        l_ctx->pid = current->tgid;
+        INIT_LIST_HEAD(&l_ctx->list);
+}
+
+static struct nfs_lock_context *__nfs_find_lock_context(struct nfs_open_context *ctx)
+{
+        struct nfs_lock_context *pos;
+
+        list_for_each_entry(pos, &ctx->lock_context.list, list) {
+                if (pos->lockowner != current->files)
+                        continue;
+                if (pos->pid != current->tgid)
+                        continue;
+                atomic_inc(&pos->count);
+                return pos;
+        }
+        return NULL;
+}
+
+struct nfs_lock_context *nfs_get_lock_context(struct nfs_open_context *ctx)
+{
+        struct nfs_lock_context *res, *new = NULL;
+        struct inode *inode = ctx->path.dentry->d_inode;
+
+        spin_lock(&inode->i_lock);
+        res = __nfs_find_lock_context(ctx);
+        if (res == NULL) {
+                spin_unlock(&inode->i_lock);
+                new = kmalloc(sizeof(*new), GFP_KERNEL);
+                if (new == NULL)
+                        return NULL;
+                nfs_init_lock_context(new);
+                spin_lock(&inode->i_lock);
+                res = __nfs_find_lock_context(ctx);
+                if (res == NULL) {
+                        list_add_tail(&new->list, &ctx->lock_context.list);
+                        new->open_context = ctx;
+                        res = new;
+                        new = NULL;
+                }
+        }
+        spin_unlock(&inode->i_lock);
+        kfree(new);
+        return res;
+}
+
+void nfs_put_lock_context(struct nfs_lock_context *l_ctx)
+{
+        struct nfs_open_context *ctx = l_ctx->open_context;
+        struct inode *inode = ctx->path.dentry->d_inode;
+
+        if (!atomic_dec_and_lock(&l_ctx->count, &inode->i_lock))
+                return;
+        list_del(&l_ctx->list);
+        spin_unlock(&inode->i_lock);
+        kfree(l_ctx);
+}
+
 /**
  * nfs_close_context - Common close_context() routine NFSv2/v3
  * @ctx: pointer to context
@@ -571,21 +621,23 @@ void nfs_close_context(struct nfs_open_context *ctx, int is_sync)
         nfs_revalidate_inode(server, inode);
 }
 
-static struct nfs_open_context *alloc_nfs_open_context(struct vfsmount *mnt, struct dentry *dentry, struct rpc_cred *cred)
+struct nfs_open_context *alloc_nfs_open_context(struct path *path, struct rpc_cred *cred, fmode_t f_mode)
 {
         struct nfs_open_context *ctx;
 
         ctx = kmalloc(sizeof(*ctx), GFP_KERNEL);
         if (ctx != NULL) {
-                ctx->path.dentry = dget(dentry);
-                ctx->path.mnt = mntget(mnt);
+                ctx->path = *path;
+                path_get(&ctx->path);
                 ctx->cred = get_rpccred(cred);
                 ctx->state = NULL;
-                ctx->lockowner = current->files;
+                ctx->mode = f_mode;
                 ctx->flags = 0;
                 ctx->error = 0;
                 ctx->dir_cookie = 0;
-                atomic_set(&ctx->count, 1);
+                nfs_init_lock_context(&ctx->lock_context);
+                ctx->lock_context.open_context = ctx;
+                INIT_LIST_HEAD(&ctx->list);
         }
         return ctx;
 }
@@ -593,7 +645,7 @@ static struct nfs_open_context *alloc_nfs_open_context(struct vfsmount *mnt, str
 struct nfs_open_context *get_nfs_open_context(struct nfs_open_context *ctx)
 {
         if (ctx != NULL)
-                atomic_inc(&ctx->count);
+                atomic_inc(&ctx->lock_context.count);
         return ctx;
 }
 
@@ -601,11 +653,15 @@ static void __put_nfs_open_context(struct nfs_open_context *ctx, int is_sync)
 {
         struct inode *inode = ctx->path.dentry->d_inode;
 
-        if (!atomic_dec_and_lock(&ctx->count, &inode->i_lock))
+        if (!list_empty(&ctx->list)) {
+                if (!atomic_dec_and_lock(&ctx->lock_context.count, &inode->i_lock))
+                        return;
+                list_del(&ctx->list);
+                spin_unlock(&inode->i_lock);
+        } else if (!atomic_dec_and_test(&ctx->lock_context.count))
                 return;
-        list_del(&ctx->list);
-        spin_unlock(&inode->i_lock);
-        NFS_PROTO(inode)->close_context(ctx, is_sync);
+        if (inode != NULL)
+                NFS_PROTO(inode)->close_context(ctx, is_sync);
         if (ctx->cred != NULL)
                 put_rpccred(ctx->cred);
         path_put(&ctx->path);
@@ -617,16 +673,11 @@ void put_nfs_open_context(struct nfs_open_context *ctx)
         __put_nfs_open_context(ctx, 0);
 }
 
-static void put_nfs_open_context_sync(struct nfs_open_context *ctx)
-{
-        __put_nfs_open_context(ctx, 1);
-}
-
 /*
  * Ensure that mmap has a recent RPC credential for use when writing out
  * shared pages
  */
-static void nfs_file_set_open_context(struct file *filp, struct nfs_open_context *ctx)
+void nfs_file_set_open_context(struct file *filp, struct nfs_open_context *ctx)
 {
         struct inode *inode = filp->f_path.dentry->d_inode;
         struct nfs_inode *nfsi = NFS_I(inode);
@@ -649,10 +700,10 @@ struct nfs_open_context *nfs_find_open_context(struct inode *inode, struct rpc_c
         list_for_each_entry(pos, &nfsi->open_files, list) {
                 if (cred != NULL && pos->cred != cred)
                         continue;
-                if ((pos->mode & mode) == mode) {
-                        ctx = get_nfs_open_context(pos);
-                        break;
-                }
+                if ((pos->mode & (FMODE_READ|FMODE_WRITE)) != mode)
+                        continue;
+                ctx = get_nfs_open_context(pos);
+                break;
         }
         spin_unlock(&inode->i_lock);
         return ctx;
@@ -668,7 +719,7 @@ static void nfs_file_clear_open_context(struct file *filp)
                 spin_lock(&inode->i_lock);
                 list_move_tail(&ctx->list, &NFS_I(inode)->open_files);
                 spin_unlock(&inode->i_lock);
-                put_nfs_open_context_sync(ctx);
+                __put_nfs_open_context(ctx, filp->f_flags & O_DIRECT ? 0 : 1);
         }
 }
 
@@ -683,11 +734,10 @@ int nfs_open(struct inode *inode, struct file *filp)
         cred = rpc_lookup_cred();
         if (IS_ERR(cred))
                 return PTR_ERR(cred);
-        ctx = alloc_nfs_open_context(filp->f_path.mnt, filp->f_path.dentry, cred);
+        ctx = alloc_nfs_open_context(&filp->f_path, cred, filp->f_mode);
         put_rpccred(cred);
         if (ctx == NULL)
                 return -ENOMEM;
-        ctx->mode = filp->f_mode;
         nfs_file_set_open_context(filp, ctx);
         put_nfs_open_context(ctx);
         nfs_fscache_set_inode_cookie(inode, filp);
@@ -708,7 +758,7 @@ int
 __nfs_revalidate_inode(struct nfs_server *server, struct inode *inode)
 {
         int              status = -ESTALE;
-        struct nfs_fattr fattr;
+        struct nfs_fattr *fattr = NULL;
         struct nfs_inode *nfsi = NFS_I(inode);
 
         dfprintk(PAGECACHE, "NFS: revalidating (%s/%Ld)\n",
@@ -719,8 +769,13 @@ __nfs_revalidate_inode(struct nfs_server *server, struct inode *inode)
         if (NFS_STALE(inode))
                 goto out;
 
+        status = -ENOMEM;
+        fattr = nfs_alloc_fattr();
+        if (fattr == NULL)
+                goto out;
+
         nfs_inc_stats(inode, NFSIOS_INODEREVALIDATE);
-        status = NFS_PROTO(inode)->getattr(server, NFS_FH(inode), &fattr);
+        status = NFS_PROTO(inode)->getattr(server, NFS_FH(inode), fattr);
         if (status != 0) {
                 dfprintk(PAGECACHE, "nfs_revalidate_inode: (%s/%Ld) getattr failed, error=%d\n",
                          inode->i_sb->s_id,
@@ -733,7 +788,7 @@ __nfs_revalidate_inode(struct nfs_server *server, struct inode *inode)
                 goto out;
         }
 
-        status = nfs_refresh_inode(inode, &fattr);
+        status = nfs_refresh_inode(inode, fattr);
         if (status) {
                 dfprintk(PAGECACHE, "nfs_revalidate_inode: (%s/%Ld) refresh failed, error=%d\n",
                          inode->i_sb->s_id,
@@ -749,6 +804,7 @@ __nfs_revalidate_inode(struct nfs_server *server, struct inode *inode)
                 (long long)NFS_FILEID(inode));
 
  out:
+        nfs_free_fattr(fattr);
         return status;
 }
 
@@ -756,11 +812,16 @@ int nfs_attribute_timeout(struct inode *inode)
 {
         struct nfs_inode *nfsi = NFS_I(inode);
 
-        if (nfs_have_delegation(inode, FMODE_READ))
-                return 0;
         return !time_in_range_open(jiffies, nfsi->read_cache_jiffies, nfsi->read_cache_jiffies + nfsi->attrtimeo);
 }
 
+static int nfs_attribute_cache_expired(struct inode *inode)
+{
+        if (nfs_have_delegated_attributes(inode))
+                return 0;
+        return nfs_attribute_timeout(inode);
+}
+
 /**
  * nfs_revalidate_inode - Revalidate the inode attributes
  * @server - pointer to nfs_server struct
@@ -771,12 +832,12 @@ int nfs_attribute_timeout(struct inode *inode)
 int nfs_revalidate_inode(struct nfs_server *server, struct inode *inode)
 {
         if (!(NFS_I(inode)->cache_validity & NFS_INO_INVALID_ATTR)
-                        && !nfs_attribute_timeout(inode))
+                        && !nfs_attribute_cache_expired(inode))
                 return NFS_STALE(inode) ? -ESTALE : 0;
         return __nfs_revalidate_inode(server, inode);
 }
 
-static int nfs_invalidate_mapping_nolock(struct inode *inode, struct address_space *mapping)
+static int nfs_invalidate_mapping(struct inode *inode, struct address_space *mapping)
 {
         struct nfs_inode *nfsi = NFS_I(inode);
         
@@ -797,49 +858,10 @@ static int nfs_invalidate_mapping_nolock(struct inode *inode, struct address_spa
         return 0;
 }
 
-static int nfs_invalidate_mapping(struct inode *inode, struct address_space *mapping)
-{
-        int ret = 0;
-
-        mutex_lock(&inode->i_mutex);
-        if (NFS_I(inode)->cache_validity & NFS_INO_INVALID_DATA) {
-                ret = nfs_sync_mapping(mapping);
-                if (ret == 0)
-                        ret = nfs_invalidate_mapping_nolock(inode, mapping);
-        }
-        mutex_unlock(&inode->i_mutex);
-        return ret;
-}
-
-/**
- * nfs_revalidate_mapping_nolock - Revalidate the pagecache
- * @inode - pointer to host inode
- * @mapping - pointer to mapping
- */
-int nfs_revalidate_mapping_nolock(struct inode *inode, struct address_space *mapping)
-{
-        struct nfs_inode *nfsi = NFS_I(inode);
-        int ret = 0;
-
-        if ((nfsi->cache_validity & NFS_INO_REVAL_PAGECACHE)
-                        || nfs_attribute_timeout(inode) || NFS_STALE(inode)) {
-                ret = __nfs_revalidate_inode(NFS_SERVER(inode), inode);
-                if (ret < 0)
-                        goto out;
-        }
-        if (nfsi->cache_validity & NFS_INO_INVALID_DATA)
-                ret = nfs_invalidate_mapping_nolock(inode, mapping);
-out:
-        return ret;
-}
-
 /**
  * nfs_revalidate_mapping - Revalidate the pagecache
  * @inode - pointer to host inode
  * @mapping - pointer to mapping
- *
- * This version of the function will take the inode->i_mutex and attempt to
- * flush out all dirty data if it needs to invalidate the page cache.
  */
 int nfs_revalidate_mapping(struct inode *inode, struct address_space *mapping)
 {
@@ -847,7 +869,8 @@ int nfs_revalidate_mapping(struct inode *inode, struct address_space *mapping)
         int ret = 0;
 
         if ((nfsi->cache_validity & NFS_INO_REVAL_PAGECACHE)
-                        || nfs_attribute_timeout(inode) || NFS_STALE(inode)) {
+                        || nfs_attribute_cache_expired(inode)
+                        || NFS_STALE(inode)) {
                 ret = __nfs_revalidate_inode(NFS_SERVER(inode), inode);
                 if (ret < 0)
                         goto out;
@@ -981,6 +1004,26 @@ void nfs_fattr_init(struct nfs_fattr *fattr)
         fattr->gencount = nfs_inc_attr_generation_counter();
 }
 
+struct nfs_fattr *nfs_alloc_fattr(void)
+{
+        struct nfs_fattr *fattr;
+
+        fattr = kmalloc(sizeof(*fattr), GFP_NOFS);
+        if (fattr != NULL)
+                nfs_fattr_init(fattr);
+        return fattr;
+}
+
+struct nfs_fh *nfs_alloc_fhandle(void)
+{
+        struct nfs_fh *fh;
+
+        fh = kmalloc(sizeof(struct nfs_fh), GFP_NOFS);
+        if (fh != NULL)
+                fh->size = 0;
+        return fh;
+}
+
 /**
  * nfs_inode_attrs_need_update - check if the inode attributes need updating
  * @inode - pointer to inode
@@ -1146,6 +1189,7 @@ static int nfs_update_inode(struct inode *inode, struct nfs_fattr *fattr)
         loff_t cur_isize, new_isize;
         unsigned long invalid = 0;
         unsigned long now = jiffies;
+        unsigned long save_cache_validity;
 
         dfprintk(VFS, "NFS: %s(%s/%ld ct=%d info=0x%x)\n",
                         __func__, inode->i_sb->s_id, inode->i_ino,
@@ -1172,10 +1216,11 @@ static int nfs_update_inode(struct inode *inode, struct nfs_fattr *fattr)
          */
         nfsi->read_cache_jiffies = fattr->time_start;
 
-        if ((fattr->valid & NFS_ATTR_FATTR_CHANGE) || (fattr->valid & (NFS_ATTR_FATTR_MTIME|NFS_ATTR_FATTR_CTIME)))
-            nfsi->cache_validity &= ~(NFS_INO_INVALID_ATTR
-                    | NFS_INO_INVALID_ATIME
-                    | NFS_INO_REVAL_PAGECACHE);
+        save_cache_validity = nfsi->cache_validity;
+        nfsi->cache_validity &= ~(NFS_INO_INVALID_ATTR
+                        | NFS_INO_INVALID_ATIME
+                        | NFS_INO_REVAL_FORCED
+                        | NFS_INO_REVAL_PAGECACHE);
 
         /* Do atomic weak cache consistency updates */
         nfs_wcc_update_inode(inode, fattr);
@@ -1190,7 +1235,8 @@ static int nfs_update_inode(struct inode *inode, struct nfs_fattr *fattr)
                                 nfs_force_lookup_revalidate(inode);
                         nfsi->change_attr = fattr->change_attr;
                 }
-        }
+        } else if (server->caps & NFS_CAP_CHANGE_ATTR)
+                invalid |= save_cache_validity;
 
         if (fattr->valid & NFS_ATTR_FATTR_MTIME) {
                 /* NFSv2/v3: Check if the mtime agrees */
@@ -1202,7 +1248,12 @@ static int nfs_update_inode(struct inode *inode, struct nfs_fattr *fattr)
                                 nfs_force_lookup_revalidate(inode);
                         memcpy(&inode->i_mtime, &fattr->mtime, sizeof(inode->i_mtime));
                 }
-        }
+        } else if (server->caps & NFS_CAP_MTIME)
+                invalid |= save_cache_validity & (NFS_INO_INVALID_ATTR
+                                | NFS_INO_INVALID_DATA
+                                | NFS_INO_REVAL_PAGECACHE
+                                | NFS_INO_REVAL_FORCED);
+
         if (fattr->valid & NFS_ATTR_FATTR_CTIME) {
                 /* If ctime has changed we should definitely clear access+acl caches */
                 if (!timespec_equal(&inode->i_ctime, &fattr->ctime)) {
@@ -1216,7 +1267,11 @@ static int nfs_update_inode(struct inode *inode, struct nfs_fattr *fattr)
                         }
                         memcpy(&inode->i_ctime, &fattr->ctime, sizeof(inode->i_ctime));
                 }
-        }
+        } else if (server->caps & NFS_CAP_CTIME)
+                invalid |= save_cache_validity & (NFS_INO_INVALID_ATTR
+                                | NFS_INO_INVALID_ACCESS
+                                | NFS_INO_INVALID_ACL
+                                | NFS_INO_REVAL_FORCED);
 
         /* Check if our cached file size is stale */
         if (fattr->valid & NFS_ATTR_FATTR_SIZE) {
@@ -1232,30 +1287,52 @@ static int nfs_update_inode(struct inode *inode, struct nfs_fattr *fattr)
                         dprintk("NFS: isize change on server for file %s/%ld\n",
                                         inode->i_sb->s_id, inode->i_ino);
                 }
-        }
+        } else
+                invalid |= save_cache_validity & (NFS_INO_INVALID_ATTR
+                                | NFS_INO_REVAL_PAGECACHE
+                                | NFS_INO_REVAL_FORCED);
 
 
         if (fattr->valid & NFS_ATTR_FATTR_ATIME)
                 memcpy(&inode->i_atime, &fattr->atime, sizeof(inode->i_atime));
+        else if (server->caps & NFS_CAP_ATIME)
+                invalid |= save_cache_validity & (NFS_INO_INVALID_ATIME
+                                | NFS_INO_REVAL_FORCED);
 
         if (fattr->valid & NFS_ATTR_FATTR_MODE) {
                 if ((inode->i_mode & S_IALLUGO) != (fattr->mode & S_IALLUGO)) {
+                        umode_t newmode = inode->i_mode & S_IFMT;
+                        newmode |= fattr->mode & S_IALLUGO;
+                        inode->i_mode = newmode;
                         invalid |= NFS_INO_INVALID_ATTR|NFS_INO_INVALID_ACCESS|NFS_INO_INVALID_ACL;
-                        inode->i_mode = fattr->mode;
                 }
-        }
+        } else if (server->caps & NFS_CAP_MODE)
+                invalid |= save_cache_validity & (NFS_INO_INVALID_ATTR
+                                | NFS_INO_INVALID_ACCESS
+                                | NFS_INO_INVALID_ACL
+                                | NFS_INO_REVAL_FORCED);
+
         if (fattr->valid & NFS_ATTR_FATTR_OWNER) {
                 if (inode->i_uid != fattr->uid) {
                         invalid |= NFS_INO_INVALID_ATTR|NFS_INO_INVALID_ACCESS|NFS_INO_INVALID_ACL;
                         inode->i_uid = fattr->uid;
                 }
-        }
+        } else if (server->caps & NFS_CAP_OWNER)
+                invalid |= save_cache_validity & (NFS_INO_INVALID_ATTR
+                                | NFS_INO_INVALID_ACCESS
+                                | NFS_INO_INVALID_ACL
+                                | NFS_INO_REVAL_FORCED);
+
         if (fattr->valid & NFS_ATTR_FATTR_GROUP) {
                 if (inode->i_gid != fattr->gid) {
                         invalid |= NFS_INO_INVALID_ATTR|NFS_INO_INVALID_ACCESS|NFS_INO_INVALID_ACL;
                         inode->i_gid = fattr->gid;
                 }
-        }
+        } else if (server->caps & NFS_CAP_OWNER_GROUP)
+                invalid |= save_cache_validity & (NFS_INO_INVALID_ATTR
+                                | NFS_INO_INVALID_ACCESS
+                                | NFS_INO_INVALID_ACL
+                                | NFS_INO_REVAL_FORCED);
 
         if (fattr->valid & NFS_ATTR_FATTR_NLINK) {
                 if (inode->i_nlink != fattr->nlink) {
@@ -1264,7 +1341,9 @@ static int nfs_update_inode(struct inode *inode, struct nfs_fattr *fattr)
                                 invalid |= NFS_INO_INVALID_DATA;
                         inode->i_nlink = fattr->nlink;
                 }
-        }
+        } else if (server->caps & NFS_CAP_NLINK)
+                invalid |= save_cache_validity & (NFS_INO_INVALID_ATTR
+                                | NFS_INO_REVAL_FORCED);
 
         if (fattr->valid & NFS_ATTR_FATTR_SPACE_USED) {
                 /*
@@ -1294,9 +1373,8 @@ static int nfs_update_inode(struct inode *inode, struct nfs_fattr *fattr)
                                 || S_ISLNK(inode->i_mode)))
                 invalid &= ~NFS_INO_INVALID_DATA;
         if (!nfs_have_delegation(inode, FMODE_READ) ||
-                        (nfsi->cache_validity & NFS_INO_REVAL_FORCED))
+                        (save_cache_validity & NFS_INO_REVAL_FORCED))
                 nfsi->cache_validity |= invalid;
-        nfsi->cache_validity &= ~NFS_INO_REVAL_FORCED;
 
         return 0;
  out_changed:
@@ -1330,8 +1408,11 @@ static int nfs_update_inode(struct inode *inode, struct nfs_fattr *fattr)
  * to open() calls that passed nfs_atomic_lookup, but failed to call
  * nfs_open().
  */
-void nfs4_clear_inode(struct inode *inode)
+void nfs4_evict_inode(struct inode *inode)
 {
+        pnfs_destroy_layout(NFS_I(inode));
+        truncate_inode_pages(&inode->i_data, 0);
+        end_writeback(inode);
         /* If we are holding a delegation, return it! */
         nfs_inode_return_delegation_noreclaim(inode);
         /* First call standard NFS clear_inode() code */
@@ -1357,11 +1438,18 @@ struct inode *nfs_alloc_inode(struct super_block *sb)
         return &nfsi->vfs_inode;
 }
 
-void nfs_destroy_inode(struct inode *inode)
+static void nfs_i_callback(struct rcu_head *head)
 {
+        struct inode *inode = container_of(head, struct inode, i_rcu);
+        INIT_LIST_HEAD(&inode->i_dentry);
         kmem_cache_free(nfs_inode_cachep, NFS_I(inode));
 }
 
+void nfs_destroy_inode(struct inode *inode)
+{
+        call_rcu(&inode->i_rcu, nfs_i_callback);
+}
+
 static inline void nfs4_init_once(struct nfs_inode *nfsi)
 {
 #ifdef CONFIG_NFS_V4
@@ -1369,6 +1457,7 @@ static inline void nfs4_init_once(struct nfs_inode *nfsi)
         nfsi->delegation = NULL;
         nfsi->delegation_state = 0;
         init_rwsem(&nfsi->rwsem);
+        nfsi->layout = NULL;
 #endif
 }
 
@@ -1382,6 +1471,7 @@ static void init_once(void *foo)
         INIT_LIST_HEAD(&nfsi->access_cache_inode_lru);
         INIT_RADIX_TREE(&nfsi->nfs_page_tree, GFP_ATOMIC);
         nfsi->npages = 0;
+        nfsi->ncommit = 0;
         atomic_set(&nfsi->silly_count, 1);
         INIT_HLIST_HEAD(&nfsi->silly_list);
         init_waitqueue_head(&nfsi->waitqueue);
@@ -1415,7 +1505,7 @@ static int nfsiod_start(void)
 {
         struct workqueue_struct *wq;
         dprintk("RPC:       creating workqueue nfsiod\n");
-        wq = create_singlethread_workqueue("nfsiod");
+        wq = alloc_workqueue("nfsiod", WQ_RESCUER, 0);
         if (wq == NULL)
                 return -ENOMEM;
         nfsiod_workqueue = wq;
@@ -1443,6 +1533,14 @@ static int __init init_nfs_fs(void)
 {
         int err;
 
+        err = nfs_idmap_init();
+        if (err < 0)
+                goto out9;
+
+        err = nfs_dns_resolver_init();
+        if (err < 0)
+                goto out8;
+
         err = nfs_fscache_register();
         if (err < 0)
                 goto out7;
@@ -1501,6 +1599,10 @@ out5:
 out6:
         nfs_fscache_unregister();
 out7:
+        nfs_dns_resolver_destroy();
+out8:
+        nfs_idmap_quit();
+out9:
         return err;
 }
 
@@ -1512,9 +1614,12 @@ static void __exit exit_nfs_fs(void)
         nfs_destroy_inodecache();
         nfs_destroy_nfspagecache();
         nfs_fscache_unregister();
+        nfs_dns_resolver_destroy();
+        nfs_idmap_quit();
 #ifdef CONFIG_PROC_FS
         rpc_proc_unregister("nfs");
 #endif
+        nfs_cleanup_cb_ident_idr();
         unregister_nfs_fs();
         nfs_fs_proc_exit();
         nfsiod_stop();
diff --git a/fs/nfs/internal.h b/fs/nfs/internal.h
index 7dd90a6769d0..bfa3a34af801 100644
--- a/fs/nfs/internal.h
+++ b/fs/nfs/internal.h
@@ -30,6 +30,15 @@ static inline int nfs4_has_session(const struct nfs_client *clp)
         return 0;
 }
 
+static inline int nfs4_has_persistent_session(const struct nfs_client *clp)
+{
+#ifdef CONFIG_NFS_V4_1
+        if (nfs4_has_session(clp))
+                return (clp->cl_session->flags & SESSION4_PERSIST);
+#endif /* CONFIG_NFS_V4_1 */
+        return 0;
+}
+
 struct nfs_clone_mount {
         const struct super_block *sb;
         const struct dentry *dentry;
@@ -49,6 +58,17 @@ struct nfs_clone_mount {
 #define NFS_MAX_SECFLAVORS      (12)
 
 /*
+ * Value used if the user did not specify a port value.
+ */
+#define NFS_UNSPEC_PORT         (-1)
+
+/*
+ * Maximum number of pages that readdir can use for creating
+ * a vmapped array of pages.
+ */
+#define NFS_MAX_READDIR_PAGES 8
+
+/*
  * In-kernel mount arguments
  */
 struct nfs_parsed_mount_data {
@@ -63,6 +83,7 @@ struct nfs_parsed_mount_data {
         unsigned int            auth_flavor_len;
         rpc_authflavor_t        auth_flavors[1];
         char                    *client_address;
+        unsigned int            version;
         unsigned int            minorversion;
         char                    *fscache_uniq;
 
@@ -71,7 +92,7 @@ struct nfs_parsed_mount_data {
                 size_t                  addrlen;
                 char                    *hostname;
                 u32                     version;
-                unsigned short          port;
+                int                     port;
                 unsigned short          protocol;
         } mount_server;
 
@@ -80,7 +101,7 @@ struct nfs_parsed_mount_data {
                 size_t                  addrlen;
                 char                    *hostname;
                 char                    *export_path;
-                unsigned short          port;
+                int                     port;
                 unsigned short          protocol;
         } nfs_server;
 
@@ -102,13 +123,18 @@ struct nfs_mount_request {
 };
 
 extern int nfs_mount(struct nfs_mount_request *info);
+extern void nfs_umount(const struct nfs_mount_request *info);
 
 /* client.c */
 extern struct rpc_program nfs_program;
 
+extern void nfs_cleanup_cb_ident_idr(void);
 extern void nfs_put_client(struct nfs_client *);
-extern struct nfs_client *nfs_find_client(const struct sockaddr *, u32);
-extern struct nfs_client *nfs_find_client_next(struct nfs_client *);
+extern struct nfs_client *nfs4_find_client_no_ident(const struct sockaddr *);
+extern struct nfs_client *nfs4_find_client_ident(int);
+extern struct nfs_client *
+nfs4_find_client_sessionid(const struct sockaddr *, struct nfs4_sessionid *,
+                           int);
 extern struct nfs_server *nfs_create_server(
                                         const struct nfs_parsed_mount_data *,
                                         struct nfs_fh *);
@@ -149,6 +175,7 @@ struct vfsmount *nfs_do_refmount(const struct vfsmount *mnt_parent, struct dentr
 
 /* callback_xdr.c */
 extern struct svc_version nfs4_callback_version1;
+extern struct svc_version nfs4_callback_version4;
 
 /* pagelist.c */
 extern int __init nfs_init_nfspagecache(void);
@@ -162,31 +189,24 @@ extern int __init nfs_init_directcache(void);
 extern void nfs_destroy_directcache(void);
 
 /* nfs2xdr.c */
-extern int nfs_stat_to_errno(int);
+extern int nfs_stat_to_errno(enum nfs_stat);
 extern struct rpc_procinfo nfs_procedures[];
-extern __be32 * nfs_decode_dirent(__be32 *, struct nfs_entry *, int);
+extern int nfs2_decode_dirent(struct xdr_stream *,
+                                struct nfs_entry *, int);
 
 /* nfs3xdr.c */
 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);
-}
+extern int nfs3_decode_dirent(struct xdr_stream *,
+                                struct nfs_entry *, int);
 
 /* nfs4xdr.c */
 #ifdef CONFIG_NFS_V4
-extern __be32 *nfs4_decode_dirent(__be32 *p, struct nfs_entry *entry, int plus);
+extern int nfs4_decode_dirent(struct xdr_stream *,
+                                struct nfs_entry *, int);
+#endif
+#ifdef CONFIG_NFS_V4_1
+extern const u32 nfs41_maxread_overhead;
+extern const u32 nfs41_maxwrite_overhead;
 #endif
 
 /* nfs4proc.c */
@@ -198,22 +218,22 @@ extern struct rpc_procinfo nfs4_procedures[];
 void nfs_close_context(struct nfs_open_context *ctx, int is_sync);
 
 /* dir.c */
-extern int nfs_access_cache_shrinker(int nr_to_scan, gfp_t gfp_mask);
+extern int nfs_access_cache_shrinker(struct shrinker *shrink,
+                                        int nr_to_scan, gfp_t gfp_mask);
 
 /* inode.c */
 extern struct workqueue_struct *nfsiod_workqueue;
 extern struct inode *nfs_alloc_inode(struct super_block *sb);
 extern void nfs_destroy_inode(struct inode *);
-extern int nfs_write_inode(struct inode *,int);
-extern void nfs_clear_inode(struct inode *);
+extern int nfs_write_inode(struct inode *, struct writeback_control *);
+extern void nfs_evict_inode(struct inode *);
 #ifdef CONFIG_NFS_V4
-extern void nfs4_clear_inode(struct inode *);
+extern void nfs4_evict_inode(struct inode *);
 #endif
 void nfs_zap_acl_cache(struct inode *inode);
 extern int nfs_wait_bit_killable(void *word);
 
 /* super.c */
-void nfs_parse_ip_address(char *, size_t, struct sockaddr *, size_t *);
 extern struct file_system_type nfs_xdev_fs_type;
 #ifdef CONFIG_NFS_V4
 extern struct file_system_type nfs4_xdev_fs_type;
@@ -238,9 +258,7 @@ extern struct dentry *nfs_get_root(struct super_block *, struct nfs_fh *);
 #ifdef CONFIG_NFS_V4
 extern struct dentry *nfs4_get_root(struct super_block *, struct nfs_fh *);
 
-extern int nfs4_path_walk(struct nfs_server *server,
-                          struct nfs_fh *mntfh,
-                          const char *path);
+extern int nfs4_get_rootfh(struct nfs_server *server, struct nfs_fh *mntfh);
 #endif
 
 /* read.c */
@@ -248,6 +266,12 @@ extern void nfs_read_prepare(struct rpc_task *task, void *calldata);
 
 /* write.c */
 extern void nfs_write_prepare(struct rpc_task *task, void *calldata);
+#ifdef CONFIG_MIGRATION
+extern int nfs_migrate_page(struct address_space *,
+                struct page *, struct page *);
+#else
+#define nfs_migrate_page NULL
+#endif
 
 /* nfs4proc.c */
 extern int _nfs4_call_sync(struct nfs_server *server,
@@ -261,20 +285,6 @@ extern int _nfs4_call_sync_session(struct nfs_server *server,
                                    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
  */
@@ -359,6 +369,15 @@ unsigned int nfs_page_length(struct page *page)
 }
 
 /*
+ * Convert a umode to a dirent->d_type
+ */
+static inline
+unsigned char nfs_umode_to_dtype(umode_t mode)
+{
+        return (mode >> 12) & 15;
+}
+
+/*
  * Determine the number of pages in an array of length 'len' and
  * with a base offset of 'base'
  */
@@ -369,23 +388,13 @@ unsigned int nfs_page_array_len(unsigned int base, size_t len)
                 PAGE_SIZE - 1) >> PAGE_SHIFT;
 }
 
-#define IPV6_SCOPE_DELIMITER    '%'
-
 /*
- * Set the port number in an address.  Be agnostic about the address
- * family.
+ * Helper for restarting RPC calls in the possible presence of NFSv4.1
+ * sessions.
  */
-static inline void nfs_set_port(struct sockaddr *sap, unsigned short port)
+static inline int nfs_restart_rpc(struct rpc_task *task, const struct nfs_client *clp)
 {
-        struct sockaddr_in *ap = (struct sockaddr_in *)sap;
-        struct sockaddr_in6 *ap6 = (struct sockaddr_in6 *)sap;
-
-        switch (sap->sa_family) {
-        case AF_INET:
-                ap->sin_port = htons(port);
-                break;
-        case AF_INET6:
-                ap6->sin6_port = htons(port);
-                break;
-        }
+        if (nfs4_has_session(clp))
+                return rpc_restart_call_prepare(task);
+        return rpc_restart_call(task);
 }
diff --git a/fs/nfs/iostat.h b/fs/nfs/iostat.h
index ceda50aad73c..c5832487c456 100644
--- a/fs/nfs/iostat.h
+++ b/fs/nfs/iostat.h
@@ -25,13 +25,7 @@ struct nfs_iostats {
 static inline void nfs_inc_server_stats(const struct nfs_server *server,
                                         enum nfs_stat_eventcounters stat)
 {
-        struct nfs_iostats *iostats;
-        int cpu;
-
-        cpu = get_cpu();
-        iostats = per_cpu_ptr(server->io_stats, cpu);
-        iostats->events[stat]++;
-        put_cpu();
+        this_cpu_inc(server->io_stats->events[stat]);
 }
 
 static inline void nfs_inc_stats(const struct inode *inode,
@@ -42,20 +36,14 @@ static inline void nfs_inc_stats(const struct inode *inode,
 
 static inline void nfs_add_server_stats(const struct nfs_server *server,
                                         enum nfs_stat_bytecounters stat,
-                                        unsigned long addend)
+                                        long addend)
 {
-        struct nfs_iostats *iostats;
-        int cpu;
-
-        cpu = get_cpu();
-        iostats = per_cpu_ptr(server->io_stats, cpu);
-        iostats->bytes[stat] += addend;
-        put_cpu();
+        this_cpu_add(server->io_stats->bytes[stat], addend);
 }
 
 static inline void nfs_add_stats(const struct inode *inode,
                                  enum nfs_stat_bytecounters stat,
-                                 unsigned long addend)
+                                 long addend)
 {
         nfs_add_server_stats(NFS_SERVER(inode), stat, addend);
 }
@@ -63,24 +51,18 @@ static inline void nfs_add_stats(const struct inode *inode,
 #ifdef CONFIG_NFS_FSCACHE
 static inline void nfs_add_fscache_stats(struct inode *inode,
                                          enum nfs_stat_fscachecounters stat,
-                                         unsigned long addend)
+                                         long addend)
 {
-        struct nfs_iostats *iostats;
-        int cpu;
-
-        cpu = get_cpu();
-        iostats = per_cpu_ptr(NFS_SERVER(inode)->io_stats, cpu);
-        iostats->fscache[stat] += addend;
-        put_cpu();
+        this_cpu_add(NFS_SERVER(inode)->io_stats->fscache[stat], addend);
 }
 #endif
 
-static inline struct nfs_iostats *nfs_alloc_iostats(void)
+static inline struct nfs_iostats __percpu *nfs_alloc_iostats(void)
 {
         return alloc_percpu(struct nfs_iostats);
 }
 
-static inline void nfs_free_iostats(struct nfs_iostats *stats)
+static inline void nfs_free_iostats(struct nfs_iostats __percpu *stats)
 {
         if (stats != NULL)
                 free_percpu(stats);
diff --git a/fs/nfs/mount_clnt.c b/fs/nfs/mount_clnt.c
index 38ef9eaec407..d4c2d6b7507e 100644
--- a/fs/nfs/mount_clnt.c
+++ b/fs/nfs/mount_clnt.c
@@ -120,7 +120,7 @@ static struct {
         { .status = MNT3ERR_INVAL,              .errno = -EINVAL,       },
         { .status = MNT3ERR_NAMETOOLONG,        .errno = -ENAMETOOLONG, },
         { .status = MNT3ERR_NOTSUPP,            .errno = -ENOTSUPP,     },
-        { .status = MNT3ERR_SERVERFAULT,        .errno = -ESERVERFAULT, },
+        { .status = MNT3ERR_SERVERFAULT,        .errno = -EREMOTEIO,    },
 };
 
 struct mountres {
@@ -153,6 +153,7 @@ int nfs_mount(struct nfs_mount_request *info)
                 .rpc_resp       = &result,
         };
         struct rpc_create_args args = {
+                .net            = &init_net,
                 .protocol       = info->protocol,
                 .address        = info->sap,
                 .addrsize       = info->salen,
@@ -209,33 +210,88 @@ out_mnt_err:
         goto out;
 }
 
+/**
+ * nfs_umount - Notify a server that we have unmounted this export
+ * @info: pointer to umount request arguments
+ *
+ * MOUNTPROC_UMNT is advisory, so we set a short timeout, and always
+ * use UDP.
+ */
+void nfs_umount(const struct nfs_mount_request *info)
+{
+        static const struct rpc_timeout nfs_umnt_timeout = {
+                .to_initval = 1 * HZ,
+                .to_maxval = 3 * HZ,
+                .to_retries = 2,
+        };
+        struct rpc_create_args args = {
+                .net            = &init_net,
+                .protocol       = IPPROTO_UDP,
+                .address        = info->sap,
+                .addrsize       = info->salen,
+                .timeout        = &nfs_umnt_timeout,
+                .servername     = info->hostname,
+                .program        = &mnt_program,
+                .version        = info->version,
+                .authflavor     = RPC_AUTH_UNIX,
+                .flags          = RPC_CLNT_CREATE_NOPING,
+        };
+        struct rpc_message msg  = {
+                .rpc_argp       = info->dirpath,
+        };
+        struct rpc_clnt *clnt;
+        int status;
+
+        if (info->noresvport)
+                args.flags |= RPC_CLNT_CREATE_NONPRIVPORT;
+
+        clnt = rpc_create(&args);
+        if (IS_ERR(clnt))
+                goto out_clnt_err;
+
+        dprintk("NFS: sending UMNT request for %s:%s\n",
+                (info->hostname ? info->hostname : "server"), info->dirpath);
+
+        if (info->version == NFS_MNT3_VERSION)
+                msg.rpc_proc = &clnt->cl_procinfo[MOUNTPROC3_UMNT];
+        else
+                msg.rpc_proc = &clnt->cl_procinfo[MOUNTPROC_UMNT];
+
+        status = rpc_call_sync(clnt, &msg, 0);
+        rpc_shutdown_client(clnt);
+
+        if (unlikely(status < 0))
+                goto out_call_err;
+
+        return;
+
+out_clnt_err:
+        dprintk("NFS: failed to create UMNT RPC client, status=%ld\n",
+                        PTR_ERR(clnt));
+        return;
+
+out_call_err:
+        dprintk("NFS: UMNT request failed, status=%d\n", status);
+}
+
 /*
  * XDR encode/decode functions for MOUNT
  */
 
-static int encode_mntdirpath(struct xdr_stream *xdr, const char *pathname)
+static void 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;
+        BUG_ON(pathname_len > MNTPATHLEN);
+        p = xdr_reserve_space(xdr, 4 + pathname_len);
         xdr_encode_opaque(p, pathname, pathname_len);
-
-        return 0;
 }
 
-static int mnt_enc_dirpath(struct rpc_rqst *req, __be32 *p,
-                           const char *dirpath)
+static void mnt_xdr_enc_dirpath(struct rpc_rqst *req, struct xdr_stream *xdr,
+                                const char *dirpath)
 {
-        struct xdr_stream xdr;
-
-        xdr_init_encode(&xdr, &req->rq_snd_buf, p);
-        return encode_mntdirpath(&xdr, dirpath);
+        encode_mntdirpath(xdr, dirpath);
 }
 
 /*
@@ -253,12 +309,12 @@ static int decode_status(struct xdr_stream *xdr, struct mountres *res)
         u32 status;
         __be32 *p;
 
-        p = xdr_inline_decode(xdr, sizeof(status));
+        p = xdr_inline_decode(xdr, 4);
         if (unlikely(p == NULL))
                 return -EIO;
-        status = ntohl(*p);
+        status = be32_to_cpup(p);
 
-        for (i = 0; i <= ARRAY_SIZE(mnt_errtbl); i++) {
+        for (i = 0; i < ARRAY_SIZE(mnt_errtbl); i++) {
                 if (mnt_errtbl[i].status == status) {
                         res->errno = mnt_errtbl[i].errno;
                         return 0;
@@ -284,18 +340,16 @@ static int decode_fhandle(struct xdr_stream *xdr, struct mountres *res)
         return 0;
 }
 
-static int mnt_dec_mountres(struct rpc_rqst *req, __be32 *p,
-                            struct mountres *res)
+static int mnt_xdr_dec_mountres(struct rpc_rqst *req,
+                                struct xdr_stream *xdr,
+                                struct mountres *res)
 {
-        struct xdr_stream xdr;
         int status;
 
-        xdr_init_decode(&xdr, &req->rq_rcv_buf, p);
-
-        status = decode_status(&xdr, res);
+        status = decode_status(xdr, res);
         if (unlikely(status != 0 || res->errno != 0))
                 return status;
-        return decode_fhandle(&xdr, res);
+        return decode_fhandle(xdr, res);
 }
 
 static int decode_fhs_status(struct xdr_stream *xdr, struct mountres *res)
@@ -304,12 +358,12 @@ static int decode_fhs_status(struct xdr_stream *xdr, struct mountres *res)
         u32 status;
         __be32 *p;
 
-        p = xdr_inline_decode(xdr, sizeof(status));
+        p = xdr_inline_decode(xdr, 4);
         if (unlikely(p == NULL))
                 return -EIO;
-        status = ntohl(*p);
+        status = be32_to_cpup(p);
 
-        for (i = 0; i <= ARRAY_SIZE(mnt3_errtbl); i++) {
+        for (i = 0; i < ARRAY_SIZE(mnt3_errtbl); i++) {
                 if (mnt3_errtbl[i].status == status) {
                         res->errno = mnt3_errtbl[i].errno;
                         return 0;
@@ -327,11 +381,11 @@ static int decode_fhandle3(struct xdr_stream *xdr, struct mountres *res)
         u32 size;
         __be32 *p;
 
-        p = xdr_inline_decode(xdr, sizeof(size));
+        p = xdr_inline_decode(xdr, 4);
         if (unlikely(p == NULL))
                 return -EIO;
 
-        size = ntohl(*p++);
+        size = be32_to_cpup(p);
         if (size > NFS3_FHSIZE || size == 0)
                 return -EIO;
 
@@ -354,15 +408,15 @@ static int decode_auth_flavors(struct xdr_stream *xdr, struct mountres *res)
         if (*count == 0)
                 return 0;
 
-        p = xdr_inline_decode(xdr, sizeof(entries));
+        p = xdr_inline_decode(xdr, 4);
         if (unlikely(p == NULL))
                 return -EIO;
-        entries = ntohl(*p);
+        entries = be32_to_cpup(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);
+        p = xdr_inline_decode(xdr, 4 * entries);
         if (unlikely(p == NULL))
                 return -EIO;
 
@@ -370,67 +424,79 @@ static int decode_auth_flavors(struct xdr_stream *xdr, struct mountres *res)
                 entries = *count;
 
         for (i = 0; i < entries; i++) {
-                flavors[i] = ntohl(*p++);
-                dprintk("NFS:\tflavor %u: %d\n", i, flavors[i]);
+                flavors[i] = be32_to_cpup(p++);
+                dprintk("NFS:   auth flavor[%u]: %d\n", i, flavors[i]);
         }
         *count = i;
 
         return 0;
 }
 
-static int mnt_dec_mountres3(struct rpc_rqst *req, __be32 *p,
-                             struct mountres *res)
+static int mnt_xdr_dec_mountres3(struct rpc_rqst *req,
+                                 struct xdr_stream *xdr,
+                                 struct mountres *res)
 {
-        struct xdr_stream xdr;
         int status;
 
-        xdr_init_decode(&xdr, &req->rq_rcv_buf, p);
-
-        status = decode_fhs_status(&xdr, res);
+        status = decode_fhs_status(xdr, res);
         if (unlikely(status != 0 || res->errno != 0))
                 return status;
-        status = decode_fhandle3(&xdr, res);
+        status = decode_fhandle3(xdr, res);
         if (unlikely(status != 0)) {
                 res->errno = -EBADHANDLE;
                 return 0;
         }
-        return decode_auth_flavors(&xdr, res);
+        return decode_auth_flavors(xdr, res);
 }
 
 static struct rpc_procinfo mnt_procedures[] = {
         [MOUNTPROC_MNT] = {
                 .p_proc         = MOUNTPROC_MNT,
-                .p_encode       = (kxdrproc_t)mnt_enc_dirpath,
-                .p_decode       = (kxdrproc_t)mnt_dec_mountres,
+                .p_encode       = (kxdreproc_t)mnt_xdr_enc_dirpath,
+                .p_decode       = (kxdrdproc_t)mnt_xdr_dec_mountres,
                 .p_arglen       = MNT_enc_dirpath_sz,
                 .p_replen       = MNT_dec_mountres_sz,
                 .p_statidx      = MOUNTPROC_MNT,
                 .p_name         = "MOUNT",
         },
+        [MOUNTPROC_UMNT] = {
+                .p_proc         = MOUNTPROC_UMNT,
+                .p_encode       = (kxdreproc_t)mnt_xdr_enc_dirpath,
+                .p_arglen       = MNT_enc_dirpath_sz,
+                .p_statidx      = MOUNTPROC_UMNT,
+                .p_name         = "UMOUNT",
+        },
 };
 
 static struct rpc_procinfo mnt3_procedures[] = {
         [MOUNTPROC3_MNT] = {
                 .p_proc         = MOUNTPROC3_MNT,
-                .p_encode       = (kxdrproc_t)mnt_enc_dirpath,
-                .p_decode       = (kxdrproc_t)mnt_dec_mountres3,
+                .p_encode       = (kxdreproc_t)mnt_xdr_enc_dirpath,
+                .p_decode       = (kxdrdproc_t)mnt_xdr_dec_mountres3,
                 .p_arglen       = MNT_enc_dirpath_sz,
                 .p_replen       = MNT_dec_mountres3_sz,
                 .p_statidx      = MOUNTPROC3_MNT,
                 .p_name         = "MOUNT",
         },
+        [MOUNTPROC3_UMNT] = {
+                .p_proc         = MOUNTPROC3_UMNT,
+                .p_encode       = (kxdreproc_t)mnt_xdr_enc_dirpath,
+                .p_arglen       = MNT_enc_dirpath_sz,
+                .p_statidx      = MOUNTPROC3_UMNT,
+                .p_name         = "UMOUNT",
+        },
 };
 
 
 static struct rpc_version mnt_version1 = {
         .number         = 1,
-        .nrprocs        = 2,
+        .nrprocs        = ARRAY_SIZE(mnt_procedures),
         .procs          = mnt_procedures,
 };
 
 static struct rpc_version mnt_version3 = {
         .number         = 3,
-        .nrprocs        = 2,
+        .nrprocs        = ARRAY_SIZE(mnt3_procedures),
         .procs          = mnt3_procedures,
 };
 
diff --git a/fs/nfs/namespace.c b/fs/nfs/namespace.c
index 40c766782891..74aaf3963c10 100644
--- a/fs/nfs/namespace.c
+++ b/fs/nfs/namespace.c
@@ -8,6 +8,7 @@
  */
 
 #include <linux/dcache.h>
+#include <linux/gfp.h>
 #include <linux/mount.h>
 #include <linux/namei.h>
 #include <linux/nfs_fs.h>
@@ -48,12 +49,17 @@ char *nfs_path(const char *base,
                const struct dentry *dentry,
                char *buffer, ssize_t buflen)
 {
-        char *end = buffer+buflen;
+        char *end;
         int namelen;
+        unsigned seq;
 
+rename_retry:
+        end = buffer+buflen;
         *--end = '\0';
         buflen--;
-        spin_lock(&dcache_lock);
+
+        seq = read_seqbegin(&rename_lock);
+        rcu_read_lock();
         while (!IS_ROOT(dentry) && dentry != droot) {
                 namelen = dentry->d_name.len;
                 buflen -= namelen + 1;
@@ -64,7 +70,9 @@ char *nfs_path(const char *base,
                 *--end = '/';
                 dentry = dentry->d_parent;
         }
-        spin_unlock(&dcache_lock);
+        rcu_read_unlock();
+        if (read_seqretry(&rename_lock, seq))
+                goto rename_retry;
         if (*end != '/') {
                 if (--buflen < 0)
                         goto Elong;
@@ -81,7 +89,9 @@ char *nfs_path(const char *base,
         memcpy(end, base, namelen);
         return end;
 Elong_unlock:
-        spin_unlock(&dcache_lock);
+        rcu_read_unlock();
+        if (read_seqretry(&rename_lock, seq))
+                goto rename_retry;
 Elong:
         return ERR_PTR(-ENAMETOOLONG);
 }
@@ -104,8 +114,8 @@ static void * nfs_follow_mountpoint(struct dentry *dentry, struct nameidata *nd)
         struct vfsmount *mnt;
         struct nfs_server *server = NFS_SERVER(dentry->d_inode);
         struct dentry *parent;
-        struct nfs_fh fh;
-        struct nfs_fattr fattr;
+        struct nfs_fh *fh = NULL;
+        struct nfs_fattr *fattr = NULL;
         int err;
 
         dprintk("--> nfs_follow_mountpoint()\n");
@@ -114,6 +124,12 @@ static void * nfs_follow_mountpoint(struct dentry *dentry, struct nameidata *nd)
         if (IS_ROOT(dentry))
                 goto out_err;
 
+        err = -ENOMEM;
+        fh = nfs_alloc_fhandle();
+        fattr = nfs_alloc_fattr();
+        if (fh == NULL || fattr == NULL)
+                goto out_err;
+
         dprintk("%s: enter\n", __func__);
         dput(nd->path.dentry);
         nd->path.dentry = dget(dentry);
@@ -122,16 +138,16 @@ static void * nfs_follow_mountpoint(struct dentry *dentry, struct nameidata *nd)
         parent = dget_parent(nd->path.dentry);
         err = server->nfs_client->rpc_ops->lookup(parent->d_inode,
                                                   &nd->path.dentry->d_name,
-                                                  &fh, &fattr);
+                                                  fh, fattr);
         dput(parent);
         if (err != 0)
                 goto out_err;
 
-        if (fattr.valid & NFS_ATTR_FATTR_V4_REFERRAL)
+        if (fattr->valid & NFS_ATTR_FATTR_V4_REFERRAL)
                 mnt = nfs_do_refmount(nd->path.mnt, nd->path.dentry);
         else
-                mnt = nfs_do_submount(nd->path.mnt, nd->path.dentry, &fh,
-                                      &fattr);
+                mnt = nfs_do_submount(nd->path.mnt, nd->path.dentry, fh,
+                                      fattr);
         err = PTR_ERR(mnt);
         if (IS_ERR(mnt))
                 goto out_err;
@@ -150,6 +166,8 @@ static void * nfs_follow_mountpoint(struct dentry *dentry, struct nameidata *nd)
         nd->path.dentry = dget(mnt->mnt_root);
         schedule_delayed_work(&nfs_automount_task, nfs_mountpoint_expiry_timeout);
 out:
+        nfs_free_fattr(fattr);
+        nfs_free_fhandle(fh);
         dprintk("%s: done, returned %d\n", __func__, err);
 
         dprintk("<-- nfs_follow_mountpoint() = %d\n", err);
diff --git a/fs/nfs/nfs2xdr.c b/fs/nfs/nfs2xdr.c
index c862c9340f9a..792cb13a4304 100644
--- a/fs/nfs/nfs2xdr.c
+++ b/fs/nfs/nfs2xdr.c
@@ -12,8 +12,6 @@
 #include <linux/param.h>
 #include <linux/time.h>
 #include <linux/mm.h>
-#include <linux/slab.h>
-#include <linux/utsname.h>
 #include <linux/errno.h>
 #include <linux/string.h>
 #include <linux/in.h>
@@ -63,610 +61,1008 @@
 #define NFS_readdirres_sz       (1)
 #define NFS_statfsres_sz        (1+NFS_info_sz)
 
+
 /*
- * Common NFS XDR functions as inlines
+ * While encoding arguments, set up the reply buffer in advance to
+ * receive reply data directly into the page cache.
  */
-static inline __be32 *
-xdr_encode_fhandle(__be32 *p, const struct nfs_fh *fhandle)
+static void prepare_reply_buffer(struct rpc_rqst *req, struct page **pages,
+                                 unsigned int base, unsigned int len,
+                                 unsigned int bufsize)
 {
-        memcpy(p, fhandle->data, NFS2_FHSIZE);
-        return p + XDR_QUADLEN(NFS2_FHSIZE);
+        struct rpc_auth *auth = req->rq_cred->cr_auth;
+        unsigned int replen;
+
+        replen = RPC_REPHDRSIZE + auth->au_rslack + bufsize;
+        xdr_inline_pages(&req->rq_rcv_buf, replen << 2, pages, base, len);
 }
 
-static inline __be32 *
-xdr_decode_fhandle(__be32 *p, struct nfs_fh *fhandle)
+/*
+ * Handle decode buffer overflows out-of-line.
+ */
+static void print_overflow_msg(const char *func, const struct xdr_stream *xdr)
 {
-        /* NFSv2 handles have a fixed length */
-        fhandle->size = NFS2_FHSIZE;
-        memcpy(fhandle->data, p, NFS2_FHSIZE);
-        return p + XDR_QUADLEN(NFS2_FHSIZE);
+        dprintk("NFS: %s prematurely hit the end of our receive buffer. "
+                "Remaining buffer length is %tu words.\n",
+                func, xdr->end - xdr->p);
 }
 
-static inline __be32*
-xdr_encode_time(__be32 *p, struct timespec *timep)
+
+/*
+ * Encode/decode NFSv2 basic data types
+ *
+ * Basic NFSv2 data types are defined in section 2.3 of RFC 1094:
+ * "NFS: Network File System Protocol Specification".
+ *
+ * Not all basic data types have their own encoding and decoding
+ * functions.  For run-time efficiency, some data types are encoded
+ * or decoded inline.
+ */
+
+/*
+ *      typedef opaque  nfsdata<>;
+ */
+static int decode_nfsdata(struct xdr_stream *xdr, struct nfs_readres *result)
 {
-        *p++ = htonl(timep->tv_sec);
-        /* Convert nanoseconds into microseconds */
-        *p++ = htonl(timep->tv_nsec ? timep->tv_nsec / 1000 : 0);
+        u32 recvd, count;
+        size_t hdrlen;
+        __be32 *p;
+
+        p = xdr_inline_decode(xdr, 4);
+        if (unlikely(p == NULL))
+                goto out_overflow;
+        count = be32_to_cpup(p);
+        hdrlen = (u8 *)xdr->p - (u8 *)xdr->iov->iov_base;
+        recvd = xdr->buf->len - hdrlen;
+        if (unlikely(count > recvd))
+                goto out_cheating;
+out:
+        xdr_read_pages(xdr, count);
+        result->eof = 0;        /* NFSv2 does not pass EOF flag on the wire. */
+        result->count = count;
+        return count;
+out_cheating:
+        dprintk("NFS: server cheating in read result: "
+                "count %u > recvd %u\n", count, recvd);
+        count = recvd;
+        goto out;
+out_overflow:
+        print_overflow_msg(__func__, xdr);
+        return -EIO;
+}
+
+/*
+ *      enum stat {
+ *              NFS_OK = 0,
+ *              NFSERR_PERM = 1,
+ *              NFSERR_NOENT = 2,
+ *              NFSERR_IO = 5,
+ *              NFSERR_NXIO = 6,
+ *              NFSERR_ACCES = 13,
+ *              NFSERR_EXIST = 17,
+ *              NFSERR_NODEV = 19,
+ *              NFSERR_NOTDIR = 20,
+ *              NFSERR_ISDIR = 21,
+ *              NFSERR_FBIG = 27,
+ *              NFSERR_NOSPC = 28,
+ *              NFSERR_ROFS = 30,
+ *              NFSERR_NAMETOOLONG = 63,
+ *              NFSERR_NOTEMPTY = 66,
+ *              NFSERR_DQUOT = 69,
+ *              NFSERR_STALE = 70,
+ *              NFSERR_WFLUSH = 99
+ *      };
+ */
+static int decode_stat(struct xdr_stream *xdr, enum nfs_stat *status)
+{
+        __be32 *p;
+
+        p = xdr_inline_decode(xdr, 4);
+        if (unlikely(p == NULL))
+                goto out_overflow;
+        *status = be32_to_cpup(p);
+        return 0;
+out_overflow:
+        print_overflow_msg(__func__, xdr);
+        return -EIO;
+}
+
+/*
+ * 2.3.2.  ftype
+ *
+ *      enum ftype {
+ *              NFNON = 0,
+ *              NFREG = 1,
+ *              NFDIR = 2,
+ *              NFBLK = 3,
+ *              NFCHR = 4,
+ *              NFLNK = 5
+ *      };
+ *
+ */
+static __be32 *xdr_decode_ftype(__be32 *p, u32 *type)
+{
+        *type = be32_to_cpup(p++);
+        if (unlikely(*type > NF2FIFO))
+                *type = NFBAD;
         return p;
 }
 
-static inline __be32*
-xdr_encode_current_server_time(__be32 *p, struct timespec *timep)
+/*
+ * 2.3.3.  fhandle
+ *
+ *      typedef opaque fhandle[FHSIZE];
+ */
+static void encode_fhandle(struct xdr_stream *xdr, const struct nfs_fh *fh)
 {
-        /*
-         * Passing the invalid value useconds=1000000 is a
-         * Sun convention for "set to current server time".
-         * It's needed to make permissions checks for the
-         * "touch" program across v2 mounts to Solaris and
-         * Irix boxes work correctly. See description of
-         * sattr in section 6.1 of "NFS Illustrated" by
-         * Brent Callaghan, Addison-Wesley, ISBN 0-201-32750-5
-         */
-        *p++ = htonl(timep->tv_sec);
-        *p++ = htonl(1000000);
+        __be32 *p;
+
+        BUG_ON(fh->size != NFS2_FHSIZE);
+        p = xdr_reserve_space(xdr, NFS2_FHSIZE);
+        memcpy(p, fh->data, NFS2_FHSIZE);
+}
+
+static int decode_fhandle(struct xdr_stream *xdr, struct nfs_fh *fh)
+{
+        __be32 *p;
+
+        p = xdr_inline_decode(xdr, NFS2_FHSIZE);
+        if (unlikely(p == NULL))
+                goto out_overflow;
+        fh->size = NFS2_FHSIZE;
+        memcpy(fh->data, p, NFS2_FHSIZE);
+        return 0;
+out_overflow:
+        print_overflow_msg(__func__, xdr);
+        return -EIO;
+}
+
+/*
+ * 2.3.4.  timeval
+ *
+ *      struct timeval {
+ *              unsigned int seconds;
+ *              unsigned int useconds;
+ *      };
+ */
+static __be32 *xdr_encode_time(__be32 *p, const struct timespec *timep)
+{
+        *p++ = cpu_to_be32(timep->tv_sec);
+        if (timep->tv_nsec != 0)
+                *p++ = cpu_to_be32(timep->tv_nsec / NSEC_PER_USEC);
+        else
+                *p++ = cpu_to_be32(0);
+        return p;
+}
+
+/*
+ * Passing the invalid value useconds=1000000 is a Sun convention for
+ * "set to current server time".  It's needed to make permissions checks
+ * for the "touch" program across v2 mounts to Solaris and Irix servers
+ * work correctly.  See description of sattr in section 6.1 of "NFS
+ * Illustrated" by Brent Callaghan, Addison-Wesley, ISBN 0-201-32750-5.
+ */
+static __be32 *xdr_encode_current_server_time(__be32 *p,
+                                              const struct timespec *timep)
+{
+        *p++ = cpu_to_be32(timep->tv_sec);
+        *p++ = cpu_to_be32(1000000);
         return p;
 }
 
-static inline __be32*
-xdr_decode_time(__be32 *p, struct timespec *timep)
+static __be32 *xdr_decode_time(__be32 *p, struct timespec *timep)
 {
-        timep->tv_sec = ntohl(*p++);
-        /* Convert microseconds into nanoseconds */
-        timep->tv_nsec = ntohl(*p++) * 1000;
+        timep->tv_sec = be32_to_cpup(p++);
+        timep->tv_nsec = be32_to_cpup(p++) * NSEC_PER_USEC;
         return p;
 }
 
-static __be32 *
-xdr_decode_fattr(__be32 *p, struct nfs_fattr *fattr)
+/*
+ * 2.3.5.  fattr
+ *
+ *      struct fattr {
+ *              ftype           type;
+ *              unsigned int    mode;
+ *              unsigned int    nlink;
+ *              unsigned int    uid;
+ *              unsigned int    gid;
+ *              unsigned int    size;
+ *              unsigned int    blocksize;
+ *              unsigned int    rdev;
+ *              unsigned int    blocks;
+ *              unsigned int    fsid;
+ *              unsigned int    fileid;
+ *              timeval         atime;
+ *              timeval         mtime;
+ *              timeval         ctime;
+ *      };
+ *
+ */
+static int decode_fattr(struct xdr_stream *xdr, struct nfs_fattr *fattr)
 {
         u32 rdev, type;
-        type = ntohl(*p++);
-        fattr->mode = ntohl(*p++);
-        fattr->nlink = ntohl(*p++);
-        fattr->uid = ntohl(*p++);
-        fattr->gid = ntohl(*p++);
-        fattr->size = ntohl(*p++);
-        fattr->du.nfs2.blocksize = ntohl(*p++);
-        rdev = ntohl(*p++);
-        fattr->du.nfs2.blocks = ntohl(*p++);
-        fattr->fsid.major = ntohl(*p++);
-        fattr->fsid.minor = 0;
-        fattr->fileid = ntohl(*p++);
-        p = xdr_decode_time(p, &fattr->atime);
-        p = xdr_decode_time(p, &fattr->mtime);
-        p = xdr_decode_time(p, &fattr->ctime);
+        __be32 *p;
+
+        p = xdr_inline_decode(xdr, NFS_fattr_sz << 2);
+        if (unlikely(p == NULL))
+                goto out_overflow;
+
         fattr->valid |= NFS_ATTR_FATTR_V2;
+
+        p = xdr_decode_ftype(p, &type);
+
+        fattr->mode = be32_to_cpup(p++);
+        fattr->nlink = be32_to_cpup(p++);
+        fattr->uid = be32_to_cpup(p++);
+        fattr->gid = be32_to_cpup(p++);
+        fattr->size = be32_to_cpup(p++);
+        fattr->du.nfs2.blocksize = be32_to_cpup(p++);
+
+        rdev = be32_to_cpup(p++);
         fattr->rdev = new_decode_dev(rdev);
-        if (type == NFCHR && rdev == NFS2_FIFO_DEV) {
+        if (type == (u32)NFCHR && rdev == (u32)NFS2_FIFO_DEV) {
                 fattr->mode = (fattr->mode & ~S_IFMT) | S_IFIFO;
                 fattr->rdev = 0;
         }
-        return p;
+
+        fattr->du.nfs2.blocks = be32_to_cpup(p++);
+        fattr->fsid.major = be32_to_cpup(p++);
+        fattr->fsid.minor = 0;
+        fattr->fileid = be32_to_cpup(p++);
+
+        p = xdr_decode_time(p, &fattr->atime);
+        p = xdr_decode_time(p, &fattr->mtime);
+        xdr_decode_time(p, &fattr->ctime);
+        return 0;
+out_overflow:
+        print_overflow_msg(__func__, xdr);
+        return -EIO;
 }
 
-static inline __be32 *
-xdr_encode_sattr(__be32 *p, struct iattr *attr)
-{
-        const __be32 not_set = __constant_htonl(0xFFFFFFFF);
+/*
+ * 2.3.6.  sattr
+ *
+ *      struct sattr {
+ *              unsigned int    mode;
+ *              unsigned int    uid;
+ *              unsigned int    gid;
+ *              unsigned int    size;
+ *              timeval         atime;
+ *              timeval         mtime;
+ *      };
+ */
+
+#define NFS2_SATTR_NOT_SET      (0xffffffff)
 
-        *p++ = (attr->ia_valid & ATTR_MODE) ? htonl(attr->ia_mode) : not_set;
-        *p++ = (attr->ia_valid & ATTR_UID) ? htonl(attr->ia_uid) : not_set;
-        *p++ = (attr->ia_valid & ATTR_GID) ? htonl(attr->ia_gid) : not_set;
-        *p++ = (attr->ia_valid & ATTR_SIZE) ? htonl(attr->ia_size) : not_set;
+static __be32 *xdr_time_not_set(__be32 *p)
+{
+        *p++ = cpu_to_be32(NFS2_SATTR_NOT_SET);
+        *p++ = cpu_to_be32(NFS2_SATTR_NOT_SET);
+        return p;
+}
 
-        if (attr->ia_valid & ATTR_ATIME_SET) {
+static void encode_sattr(struct xdr_stream *xdr, const struct iattr *attr)
+{
+        __be32 *p;
+
+        p = xdr_reserve_space(xdr, NFS_sattr_sz << 2);
+
+        if (attr->ia_valid & ATTR_MODE)
+                *p++ = cpu_to_be32(attr->ia_mode);
+        else
+                *p++ = cpu_to_be32(NFS2_SATTR_NOT_SET);
+        if (attr->ia_valid & ATTR_UID)
+                *p++ = cpu_to_be32(attr->ia_uid);
+        else
+                *p++ = cpu_to_be32(NFS2_SATTR_NOT_SET);
+        if (attr->ia_valid & ATTR_GID)
+                *p++ = cpu_to_be32(attr->ia_gid);
+        else
+                *p++ = cpu_to_be32(NFS2_SATTR_NOT_SET);
+        if (attr->ia_valid & ATTR_SIZE)
+                *p++ = cpu_to_be32((u32)attr->ia_size);
+        else
+                *p++ = cpu_to_be32(NFS2_SATTR_NOT_SET);
+
+        if (attr->ia_valid & ATTR_ATIME_SET)
                 p = xdr_encode_time(p, &attr->ia_atime);
-        } else if (attr->ia_valid & ATTR_ATIME) {
+        else if (attr->ia_valid & ATTR_ATIME)
                 p = xdr_encode_current_server_time(p, &attr->ia_atime);
-        } else {
-                *p++ = not_set;
-                *p++ = not_set;
-        }
-
-        if (attr->ia_valid & ATTR_MTIME_SET) {
-                p = xdr_encode_time(p, &attr->ia_mtime);
-        } else if (attr->ia_valid & ATTR_MTIME) {
-                p = xdr_encode_current_server_time(p, &attr->ia_mtime);
-        } else {
-                *p++ = not_set; 
-                *p++ = not_set;
-        }
-        return p;
+        else
+                p = xdr_time_not_set(p);
+        if (attr->ia_valid & ATTR_MTIME_SET)
+                xdr_encode_time(p, &attr->ia_mtime);
+        else if (attr->ia_valid & ATTR_MTIME)
+                xdr_encode_current_server_time(p, &attr->ia_mtime);
+        else
+                xdr_time_not_set(p);
 }
 
 /*
- * NFS encode functions
- */
-/*
- * Encode file handle argument
- * GETATTR, READLINK, STATFS
+ * 2.3.7.  filename
+ *
+ *      typedef string filename<MAXNAMLEN>;
  */
-static int
-nfs_xdr_fhandle(struct rpc_rqst *req, __be32 *p, struct nfs_fh *fh)
+static void encode_filename(struct xdr_stream *xdr,
+                            const char *name, u32 length)
 {
-        p = xdr_encode_fhandle(p, fh);
-        req->rq_slen = xdr_adjust_iovec(req->rq_svec, p);
+        __be32 *p;
+
+        BUG_ON(length > NFS2_MAXNAMLEN);
+        p = xdr_reserve_space(xdr, 4 + length);
+        xdr_encode_opaque(p, name, length);
+}
+
+static int decode_filename_inline(struct xdr_stream *xdr,
+                                  const char **name, u32 *length)
+{
+        __be32 *p;
+        u32 count;
+
+        p = xdr_inline_decode(xdr, 4);
+        if (unlikely(p == NULL))
+                goto out_overflow;
+        count = be32_to_cpup(p);
+        if (count > NFS3_MAXNAMLEN)
+                goto out_nametoolong;
+        p = xdr_inline_decode(xdr, count);
+        if (unlikely(p == NULL))
+                goto out_overflow;
+        *name = (const char *)p;
+        *length = count;
         return 0;
+out_nametoolong:
+        dprintk("NFS: returned filename too long: %u\n", count);
+        return -ENAMETOOLONG;
+out_overflow:
+        print_overflow_msg(__func__, xdr);
+        return -EIO;
 }
 
 /*
- * Encode SETATTR arguments
+ * 2.3.8.  path
+ *
+ *      typedef string path<MAXPATHLEN>;
  */
-static int
-nfs_xdr_sattrargs(struct rpc_rqst *req, __be32 *p, struct nfs_sattrargs *args)
+static void encode_path(struct xdr_stream *xdr, struct page **pages, u32 length)
 {
-        p = xdr_encode_fhandle(p, args->fh);
-        p = xdr_encode_sattr(p, args->sattr);
-        req->rq_slen = xdr_adjust_iovec(req->rq_svec, p);
+        __be32 *p;
+
+        BUG_ON(length > NFS2_MAXPATHLEN);
+        p = xdr_reserve_space(xdr, 4);
+        *p = cpu_to_be32(length);
+        xdr_write_pages(xdr, pages, 0, length);
+}
+
+static int decode_path(struct xdr_stream *xdr)
+{
+        u32 length, recvd;
+        size_t hdrlen;
+        __be32 *p;
+
+        p = xdr_inline_decode(xdr, 4);
+        if (unlikely(p == NULL))
+                goto out_overflow;
+        length = be32_to_cpup(p);
+        if (unlikely(length >= xdr->buf->page_len || length > NFS_MAXPATHLEN))
+                goto out_size;
+        hdrlen = (u8 *)xdr->p - (u8 *)xdr->iov->iov_base;
+        recvd = xdr->buf->len - hdrlen;
+        if (unlikely(length > recvd))
+                goto out_cheating;
+
+        xdr_read_pages(xdr, length);
+        xdr_terminate_string(xdr->buf, length);
         return 0;
+out_size:
+        dprintk("NFS: returned pathname too long: %u\n", length);
+        return -ENAMETOOLONG;
+out_cheating:
+        dprintk("NFS: server cheating in pathname result: "
+                "length %u > received %u\n", length, recvd);
+        return -EIO;
+out_overflow:
+        print_overflow_msg(__func__, xdr);
+        return -EIO;
 }
 
 /*
- * Encode directory ops argument
- * LOOKUP, RMDIR
+ * 2.3.9.  attrstat
+ *
+ *      union attrstat switch (stat status) {
+ *      case NFS_OK:
+ *              fattr attributes;
+ *      default:
+ *              void;
+ *      };
  */
-static int
-nfs_xdr_diropargs(struct rpc_rqst *req, __be32 *p, struct nfs_diropargs *args)
+static int decode_attrstat(struct xdr_stream *xdr, struct nfs_fattr *result)
 {
-        p = xdr_encode_fhandle(p, args->fh);
-        p = xdr_encode_array(p, args->name, args->len);
-        req->rq_slen = xdr_adjust_iovec(req->rq_svec, p);
-        return 0;
+        enum nfs_stat status;
+        int error;
+
+        error = decode_stat(xdr, &status);
+        if (unlikely(error))
+                goto out;
+        if (status != NFS_OK)
+                goto out_default;
+        error = decode_fattr(xdr, result);
+out:
+        return error;
+out_default:
+        return nfs_stat_to_errno(status);
 }
 
 /*
- * Encode REMOVE argument
+ * 2.3.10.  diropargs
+ *
+ *      struct diropargs {
+ *              fhandle  dir;
+ *              filename name;
+ *      };
  */
-static int
-nfs_xdr_removeargs(struct rpc_rqst *req, __be32 *p, const struct nfs_removeargs *args)
+static void encode_diropargs(struct xdr_stream *xdr, const struct nfs_fh *fh,
+                             const char *name, u32 length)
 {
-        p = xdr_encode_fhandle(p, args->fh);
-        p = xdr_encode_array(p, args->name.name, args->name.len);
-        req->rq_slen = xdr_adjust_iovec(req->rq_svec, p);
-        return 0;
+        encode_fhandle(xdr, fh);
+        encode_filename(xdr, name, length);
 }
 
 /*
- * Arguments to a READ call. Since we read data directly into the page
- * cache, we also set up the reply iovec here so that iov[1] points
- * exactly to the page we want to fetch.
+ * 2.3.11.  diropres
+ *
+ *      union diropres switch (stat status) {
+ *      case NFS_OK:
+ *              struct {
+ *                      fhandle file;
+ *                      fattr   attributes;
+ *              } diropok;
+ *      default:
+ *              void;
+ *      };
  */
-static int
-nfs_xdr_readargs(struct rpc_rqst *req, __be32 *p, struct nfs_readargs *args)
+static int decode_diropok(struct xdr_stream *xdr, struct nfs_diropok *result)
 {
-        struct rpc_auth *auth = req->rq_task->tk_msg.rpc_cred->cr_auth;
-        unsigned int replen;
-        u32 offset = (u32)args->offset;
-        u32 count = args->count;
-
-        p = xdr_encode_fhandle(p, args->fh);
-        *p++ = htonl(offset);
-        *p++ = htonl(count);
-        *p++ = htonl(count);
-        req->rq_slen = xdr_adjust_iovec(req->rq_svec, p);
+        int error;
+
+        error = decode_fhandle(xdr, result->fh);
+        if (unlikely(error))
+                goto out;
+        error = decode_fattr(xdr, result->fattr);
+out:
+        return error;
+}
 
-        /* Inline the page array */
-        replen = (RPC_REPHDRSIZE + auth->au_rslack + NFS_readres_sz) << 2;
-        xdr_inline_pages(&req->rq_rcv_buf, replen,
-                         args->pages, args->pgbase, count);
-        req->rq_rcv_buf.flags |= XDRBUF_READ;
-        return 0;
+static int decode_diropres(struct xdr_stream *xdr, struct nfs_diropok *result)
+{
+        enum nfs_stat status;
+        int error;
+
+        error = decode_stat(xdr, &status);
+        if (unlikely(error))
+                goto out;
+        if (status != NFS_OK)
+                goto out_default;
+        error = decode_diropok(xdr, result);
+out:
+        return error;
+out_default:
+        return nfs_stat_to_errno(status);
 }
 
+
 /*
- * Decode READ reply
+ * NFSv2 XDR encode functions
+ *
+ * NFSv2 argument types are defined in section 2.2 of RFC 1094:
+ * "NFS: Network File System Protocol Specification".
  */
-static int
-nfs_xdr_readres(struct rpc_rqst *req, __be32 *p, struct nfs_readres *res)
-{
-        struct kvec *iov = req->rq_rcv_buf.head;
-        size_t hdrlen;
-        u32 count, recvd;
-        int status;
-
-        if ((status = ntohl(*p++)))
-                return nfs_stat_to_errno(status);
-        p = xdr_decode_fattr(p, res->fattr);
-
-        count = ntohl(*p++);
-        res->eof = 0;
-        hdrlen = (u8 *) p - (u8 *) iov->iov_base;
-        if (iov->iov_len < hdrlen) {
-                dprintk("NFS: READ reply header overflowed:"
-                                "length %Zu > %Zu\n", hdrlen, iov->iov_len);
-                return -errno_NFSERR_IO;
-        } else if (iov->iov_len != hdrlen) {
-                dprintk("NFS: READ header is short. iovec will be shifted.\n");
-                xdr_shift_buf(&req->rq_rcv_buf, iov->iov_len - hdrlen);
-        }
 
-        recvd = req->rq_rcv_buf.len - hdrlen;
-        if (count > recvd) {
-                dprintk("NFS: server cheating in read reply: "
-                        "count %u > recvd %u\n", count, recvd);
-                count = recvd;
-        }
+static void nfs2_xdr_enc_fhandle(struct rpc_rqst *req,
+                                 struct xdr_stream *xdr,
+                                 const struct nfs_fh *fh)
+{
+        encode_fhandle(xdr, fh);
+}
 
-        dprintk("RPC:      readres OK count %u\n", count);
-        if (count < res->count)
-                res->count = count;
+/*
+ * 2.2.3.  sattrargs
+ *
+ *      struct sattrargs {
+ *              fhandle file;
+ *              sattr attributes;
+ *      };
+ */
+static void nfs2_xdr_enc_sattrargs(struct rpc_rqst *req,
+                                   struct xdr_stream *xdr,
+                                   const struct nfs_sattrargs *args)
+{
+        encode_fhandle(xdr, args->fh);
+        encode_sattr(xdr, args->sattr);
+}
 
-        return count;
+static void nfs2_xdr_enc_diropargs(struct rpc_rqst *req,
+                                   struct xdr_stream *xdr,
+                                   const struct nfs_diropargs *args)
+{
+        encode_diropargs(xdr, args->fh, args->name, args->len);
 }
 
+static void nfs2_xdr_enc_readlinkargs(struct rpc_rqst *req,
+                                      struct xdr_stream *xdr,
+                                      const struct nfs_readlinkargs *args)
+{
+        encode_fhandle(xdr, args->fh);
+        prepare_reply_buffer(req, args->pages, args->pgbase,
+                                        args->pglen, NFS_readlinkres_sz);
+}
 
 /*
- * Write arguments. Splice the buffer to be written into the iovec.
+ * 2.2.7.  readargs
+ *
+ *      struct readargs {
+ *              fhandle file;
+ *              unsigned offset;
+ *              unsigned count;
+ *              unsigned totalcount;
+ *      };
  */
-static int
-nfs_xdr_writeargs(struct rpc_rqst *req, __be32 *p, struct nfs_writeargs *args)
+static void encode_readargs(struct xdr_stream *xdr,
+                            const struct nfs_readargs *args)
 {
-        struct xdr_buf *sndbuf = &req->rq_snd_buf;
-        u32 offset = (u32)args->offset;
+        u32 offset = args->offset;
         u32 count = args->count;
+        __be32 *p;
 
-        p = xdr_encode_fhandle(p, args->fh);
-        *p++ = htonl(offset);
-        *p++ = htonl(offset);
-        *p++ = htonl(count);
-        *p++ = htonl(count);
-        sndbuf->len = xdr_adjust_iovec(sndbuf->head, p);
+        encode_fhandle(xdr, args->fh);
 
-        /* Copy the page array */
-        xdr_encode_pages(sndbuf, args->pages, args->pgbase, count);
-        sndbuf->flags |= XDRBUF_WRITE;
-        return 0;
+        p = xdr_reserve_space(xdr, 4 + 4 + 4);
+        *p++ = cpu_to_be32(offset);
+        *p++ = cpu_to_be32(count);
+        *p = cpu_to_be32(count);
 }
 
-/*
- * Encode create arguments
- * CREATE, MKDIR
- */
-static int
-nfs_xdr_createargs(struct rpc_rqst *req, __be32 *p, struct nfs_createargs *args)
+static void nfs2_xdr_enc_readargs(struct rpc_rqst *req,
+                                  struct xdr_stream *xdr,
+                                  const struct nfs_readargs *args)
 {
-        p = xdr_encode_fhandle(p, args->fh);
-        p = xdr_encode_array(p, args->name, args->len);
-        p = xdr_encode_sattr(p, args->sattr);
-        req->rq_slen = xdr_adjust_iovec(req->rq_svec, p);
-        return 0;
+        encode_readargs(xdr, args);
+        prepare_reply_buffer(req, args->pages, args->pgbase,
+                                        args->count, NFS_readres_sz);
+        req->rq_rcv_buf.flags |= XDRBUF_READ;
 }
 
 /*
- * Encode RENAME arguments
+ * 2.2.9.  writeargs
+ *
+ *      struct writeargs {
+ *              fhandle file;
+ *              unsigned beginoffset;
+ *              unsigned offset;
+ *              unsigned totalcount;
+ *              nfsdata data;
+ *      };
  */
-static int
-nfs_xdr_renameargs(struct rpc_rqst *req, __be32 *p, struct nfs_renameargs *args)
+static void encode_writeargs(struct xdr_stream *xdr,
+                             const struct nfs_writeargs *args)
 {
-        p = xdr_encode_fhandle(p, args->fromfh);
-        p = xdr_encode_array(p, args->fromname, args->fromlen);
-        p = xdr_encode_fhandle(p, args->tofh);
-        p = xdr_encode_array(p, args->toname, args->tolen);
-        req->rq_slen = xdr_adjust_iovec(req->rq_svec, p);
-        return 0;
+        u32 offset = args->offset;
+        u32 count = args->count;
+        __be32 *p;
+
+        encode_fhandle(xdr, args->fh);
+
+        p = xdr_reserve_space(xdr, 4 + 4 + 4 + 4);
+        *p++ = cpu_to_be32(offset);
+        *p++ = cpu_to_be32(offset);
+        *p++ = cpu_to_be32(count);
+
+        /* nfsdata */
+        *p = cpu_to_be32(count);
+        xdr_write_pages(xdr, args->pages, args->pgbase, count);
 }
 
-/*
- * Encode LINK arguments
- */
-static int
-nfs_xdr_linkargs(struct rpc_rqst *req, __be32 *p, struct nfs_linkargs *args)
+static void nfs2_xdr_enc_writeargs(struct rpc_rqst *req,
+                                   struct xdr_stream *xdr,
+                                   const struct nfs_writeargs *args)
 {
-        p = xdr_encode_fhandle(p, args->fromfh);
-        p = xdr_encode_fhandle(p, args->tofh);
-        p = xdr_encode_array(p, args->toname, args->tolen);
-        req->rq_slen = xdr_adjust_iovec(req->rq_svec, p);
-        return 0;
+        encode_writeargs(xdr, args);
+        xdr->buf->flags |= XDRBUF_WRITE;
 }
 
 /*
- * Encode SYMLINK arguments
+ * 2.2.10.  createargs
+ *
+ *      struct createargs {
+ *              diropargs where;
+ *              sattr attributes;
+ *      };
  */
-static int
-nfs_xdr_symlinkargs(struct rpc_rqst *req, __be32 *p, struct nfs_symlinkargs *args)
+static void nfs2_xdr_enc_createargs(struct rpc_rqst *req,
+                                    struct xdr_stream *xdr,
+                                    const struct nfs_createargs *args)
 {
-        struct xdr_buf *sndbuf = &req->rq_snd_buf;
-        size_t pad;
+        encode_diropargs(xdr, args->fh, args->name, args->len);
+        encode_sattr(xdr, args->sattr);
+}
 
-        p = xdr_encode_fhandle(p, args->fromfh);
-        p = xdr_encode_array(p, args->fromname, args->fromlen);
-        *p++ = htonl(args->pathlen);
-        sndbuf->len = xdr_adjust_iovec(sndbuf->head, p);
+static void nfs2_xdr_enc_removeargs(struct rpc_rqst *req,
+                                    struct xdr_stream *xdr,
+                                    const struct nfs_removeargs *args)
+{
+        encode_diropargs(xdr, args->fh, args->name.name, args->name.len);
+}
 
-        xdr_encode_pages(sndbuf, args->pages, 0, args->pathlen);
+/*
+ * 2.2.12.  renameargs
+ *
+ *      struct renameargs {
+ *              diropargs from;
+ *              diropargs to;
+ *      };
+ */
+static void nfs2_xdr_enc_renameargs(struct rpc_rqst *req,
+                                    struct xdr_stream *xdr,
+                                    const struct nfs_renameargs *args)
+{
+        const struct qstr *old = args->old_name;
+        const struct qstr *new = args->new_name;
 
-        /*
-         * xdr_encode_pages may have added a few bytes to ensure the
-         * pathname ends on a 4-byte boundary.  Start encoding the
-         * attributes after the pad bytes.
-         */
-        pad = sndbuf->tail->iov_len;
-        if (pad > 0)
-                p++;
-        p = xdr_encode_sattr(p, args->sattr);
-        sndbuf->len += xdr_adjust_iovec(sndbuf->tail, p) - pad;
-        return 0;
+        encode_diropargs(xdr, args->old_dir, old->name, old->len);
+        encode_diropargs(xdr, args->new_dir, new->name, new->len);
 }
 
 /*
- * Encode arguments to readdir call
+ * 2.2.13.  linkargs
+ *
+ *      struct linkargs {
+ *              fhandle from;
+ *              diropargs to;
+ *      };
  */
-static int
-nfs_xdr_readdirargs(struct rpc_rqst *req, __be32 *p, struct nfs_readdirargs *args)
+static void nfs2_xdr_enc_linkargs(struct rpc_rqst *req,
+                                  struct xdr_stream *xdr,
+                                  const struct nfs_linkargs *args)
 {
-        struct rpc_task *task = req->rq_task;
-        struct rpc_auth *auth = task->tk_msg.rpc_cred->cr_auth;
-        unsigned int replen;
-        u32 count = args->count;
-
-        p = xdr_encode_fhandle(p, args->fh);
-        *p++ = htonl(args->cookie);
-        *p++ = htonl(count); /* see above */
-        req->rq_slen = xdr_adjust_iovec(req->rq_svec, p);
+        encode_fhandle(xdr, args->fromfh);
+        encode_diropargs(xdr, args->tofh, args->toname, args->tolen);
+}
 
-        /* Inline the page array */
-        replen = (RPC_REPHDRSIZE + auth->au_rslack + NFS_readdirres_sz) << 2;
-        xdr_inline_pages(&req->rq_rcv_buf, replen, args->pages, 0, count);
-        return 0;
+/*
+ * 2.2.14.  symlinkargs
+ *
+ *      struct symlinkargs {
+ *              diropargs from;
+ *              path to;
+ *              sattr attributes;
+ *      };
+ */
+static void nfs2_xdr_enc_symlinkargs(struct rpc_rqst *req,
+                                     struct xdr_stream *xdr,
+                                     const struct nfs_symlinkargs *args)
+{
+        encode_diropargs(xdr, args->fromfh, args->fromname, args->fromlen);
+        encode_path(xdr, args->pages, args->pathlen);
+        encode_sattr(xdr, args->sattr);
 }
 
 /*
- * Decode the result of a readdir call.
- * We're not really decoding anymore, we just leave the buffer untouched
- * and only check that it is syntactically correct.
- * The real decoding happens in nfs_decode_entry below, called directly
- * from nfs_readdir for each entry.
+ * 2.2.17.  readdirargs
+ *
+ *      struct readdirargs {
+ *              fhandle dir;
+ *              nfscookie cookie;
+ *              unsigned count;
+ *      };
  */
-static int
-nfs_xdr_readdirres(struct rpc_rqst *req, __be32 *p, void *dummy)
+static void encode_readdirargs(struct xdr_stream *xdr,
+                               const struct nfs_readdirargs *args)
 {
-        struct xdr_buf *rcvbuf = &req->rq_rcv_buf;
-        struct kvec *iov = rcvbuf->head;
-        struct page **page;
-        size_t hdrlen;
-        unsigned int pglen, recvd;
-        u32 len;
-        int status, nr = 0;
-        __be32 *end, *entry, *kaddr;
-
-        if ((status = ntohl(*p++)))
-                return nfs_stat_to_errno(status);
-
-        hdrlen = (u8 *) p - (u8 *) iov->iov_base;
-        if (iov->iov_len < hdrlen) {
-                dprintk("NFS: READDIR reply header overflowed:"
-                                "length %Zu > %Zu\n", hdrlen, iov->iov_len);
-                return -errno_NFSERR_IO;
-        } else if (iov->iov_len != hdrlen) {
-                dprintk("NFS: READDIR header is short. iovec will be shifted.\n");
-                xdr_shift_buf(rcvbuf, iov->iov_len - hdrlen);
-        }
+        __be32 *p;
 
-        pglen = rcvbuf->page_len;
-        recvd = rcvbuf->len - hdrlen;
-        if (pglen > recvd)
-                pglen = recvd;
-        page = rcvbuf->pages;
-        kaddr = p = kmap_atomic(*page, KM_USER0);
-        end = (__be32 *)((char *)p + pglen);
-        entry = p;
-
-        /* Make sure the packet actually has a value_follows and EOF entry */
-        if ((entry + 1) > end)
-                goto short_pkt;
-
-        for (; *p++; nr++) {
-                if (p + 2 > end)
-                        goto short_pkt;
-                p++; /* fileid */
-                len = ntohl(*p++);
-                p += XDR_QUADLEN(len) + 1;      /* name plus cookie */
-                if (len > NFS2_MAXNAMLEN) {
-                        dprintk("NFS: giant filename in readdir (len 0x%x)!\n",
-                                                len);
-                        goto err_unmap;
-                }
-                if (p + 2 > end)
-                        goto short_pkt;
-                entry = p;
-        }
+        encode_fhandle(xdr, args->fh);
 
-        /*
-         * Apparently some server sends responses that are a valid size, but
-         * contain no entries, and have value_follows==0 and EOF==0. For
-         * those, just set the EOF marker.
-         */
-        if (!nr && entry[1] == 0) {
-                dprintk("NFS: readdir reply truncated!\n");
-                entry[1] = 1;
-        }
- out:
-        kunmap_atomic(kaddr, KM_USER0);
-        return nr;
- short_pkt:
-        /*
-         * When we get a short packet there are 2 possibilities. We can
-         * return an error, or fix up the response to look like a valid
-         * response and return what we have so far. If there are no
-         * entries and the packet was short, then return -EIO. If there
-         * are valid entries in the response, return them and pretend that
-         * the call was successful, but incomplete. The caller can retry the
-         * readdir starting at the last cookie.
-         */
-        entry[0] = entry[1] = 0;
-        if (!nr)
-                nr = -errno_NFSERR_IO;
-        goto out;
-err_unmap:
-        nr = -errno_NFSERR_IO;
-        goto out;
+        p = xdr_reserve_space(xdr, 4 + 4);
+        *p++ = cpu_to_be32(args->cookie);
+        *p = cpu_to_be32(args->count);
 }
 
-__be32 *
-nfs_decode_dirent(__be32 *p, struct nfs_entry *entry, int plus)
+static void nfs2_xdr_enc_readdirargs(struct rpc_rqst *req,
+                                     struct xdr_stream *xdr,
+                                     const struct nfs_readdirargs *args)
 {
-        if (!*p++) {
-                if (!*p)
-                        return ERR_PTR(-EAGAIN);
-                entry->eof = 1;
-                return ERR_PTR(-EBADCOOKIE);
-        }
-
-        entry->ino        = ntohl(*p++);
-        entry->len        = ntohl(*p++);
-        entry->name       = (const char *) p;
-        p                += XDR_QUADLEN(entry->len);
-        entry->prev_cookie        = entry->cookie;
-        entry->cookie     = ntohl(*p++);
-        entry->eof        = !p[0] && p[1];
-
-        return p;
+        encode_readdirargs(xdr, args);
+        prepare_reply_buffer(req, args->pages, 0,
+                                        args->count, NFS_readdirres_sz);
 }
 
 /*
- * NFS XDR decode functions
- */
-/*
- * Decode simple status reply
+ * NFSv2 XDR decode functions
+ *
+ * NFSv2 result types are defined in section 2.2 of RFC 1094:
+ * "NFS: Network File System Protocol Specification".
  */
-static int
-nfs_xdr_stat(struct rpc_rqst *req, __be32 *p, void *dummy)
+
+static int nfs2_xdr_dec_stat(struct rpc_rqst *req, struct xdr_stream *xdr,
+                             void *__unused)
+{
+        enum nfs_stat status;
+        int error;
+
+        error = decode_stat(xdr, &status);
+        if (unlikely(error))
+                goto out;
+        if (status != NFS_OK)
+                goto out_default;
+out:
+        return error;
+out_default:
+        return nfs_stat_to_errno(status);
+}
+
+static int nfs2_xdr_dec_attrstat(struct rpc_rqst *req, struct xdr_stream *xdr,
+                                 struct nfs_fattr *result)
 {
-        int     status;
+        return decode_attrstat(xdr, result);
+}
 
-        if ((status = ntohl(*p++)) != 0)
-                status = nfs_stat_to_errno(status);
-        return status;
+static int nfs2_xdr_dec_diropres(struct rpc_rqst *req, struct xdr_stream *xdr,
+                                 struct nfs_diropok *result)
+{
+        return decode_diropres(xdr, result);
 }
 
 /*
- * Decode attrstat reply
- * GETATTR, SETATTR, WRITE
+ * 2.2.6.  readlinkres
+ *
+ *      union readlinkres switch (stat status) {
+ *      case NFS_OK:
+ *              path data;
+ *      default:
+ *              void;
+ *      };
  */
-static int
-nfs_xdr_attrstat(struct rpc_rqst *req, __be32 *p, struct nfs_fattr *fattr)
+static int nfs2_xdr_dec_readlinkres(struct rpc_rqst *req,
+                                    struct xdr_stream *xdr, void *__unused)
 {
-        int     status;
-
-        if ((status = ntohl(*p++)))
-                return nfs_stat_to_errno(status);
-        xdr_decode_fattr(p, fattr);
-        return 0;
+        enum nfs_stat status;
+        int error;
+
+        error = decode_stat(xdr, &status);
+        if (unlikely(error))
+                goto out;
+        if (status != NFS_OK)
+                goto out_default;
+        error = decode_path(xdr);
+out:
+        return error;
+out_default:
+        return nfs_stat_to_errno(status);
 }
 
 /*
- * Decode diropres reply
- * LOOKUP, CREATE, MKDIR
+ * 2.2.7.  readres
+ *
+ *      union readres switch (stat status) {
+ *      case NFS_OK:
+ *              fattr attributes;
+ *              nfsdata data;
+ *      default:
+ *              void;
+ *      };
  */
-static int
-nfs_xdr_diropres(struct rpc_rqst *req, __be32 *p, struct nfs_diropok *res)
+static int nfs2_xdr_dec_readres(struct rpc_rqst *req, struct xdr_stream *xdr,
+                                struct nfs_readres *result)
 {
-        int     status;
+        enum nfs_stat status;
+        int error;
+
+        error = decode_stat(xdr, &status);
+        if (unlikely(error))
+                goto out;
+        if (status != NFS_OK)
+                goto out_default;
+        error = decode_fattr(xdr, result->fattr);
+        if (unlikely(error))
+                goto out;
+        error = decode_nfsdata(xdr, result);
+out:
+        return error;
+out_default:
+        return nfs_stat_to_errno(status);
+}
 
-        if ((status = ntohl(*p++)))
-                return nfs_stat_to_errno(status);
-        p = xdr_decode_fhandle(p, res->fh);
-        xdr_decode_fattr(p, res->fattr);
-        return 0;
+static int nfs2_xdr_dec_writeres(struct rpc_rqst *req, struct xdr_stream *xdr,
+                                 struct nfs_writeres *result)
+{
+        /* All NFSv2 writes are "file sync" writes */
+        result->verf->committed = NFS_FILE_SYNC;
+        return decode_attrstat(xdr, result->fattr);
 }
 
-/*
- * Encode READLINK args
+/**
+ * nfs2_decode_dirent - Decode a single NFSv2 directory entry stored in
+ *                      the local page cache.
+ * @xdr: XDR stream where entry resides
+ * @entry: buffer to fill in with entry data
+ * @plus: boolean indicating whether this should be a readdirplus entry
+ *
+ * Returns zero if successful, otherwise a negative errno value is
+ * returned.
+ *
+ * This function is not invoked during READDIR reply decoding, but
+ * rather whenever an application invokes the getdents(2) system call
+ * on a directory already in our cache.
+ *
+ * 2.2.17.  entry
+ *
+ *      struct entry {
+ *              unsigned        fileid;
+ *              filename        name;
+ *              nfscookie       cookie;
+ *              entry           *nextentry;
+ *      };
  */
-static int
-nfs_xdr_readlinkargs(struct rpc_rqst *req, __be32 *p, struct nfs_readlinkargs *args)
+int nfs2_decode_dirent(struct xdr_stream *xdr, struct nfs_entry *entry,
+                       int plus)
 {
-        struct rpc_auth *auth = req->rq_task->tk_msg.rpc_cred->cr_auth;
-        unsigned int replen;
+        __be32 *p;
+        int error;
+
+        p = xdr_inline_decode(xdr, 4);
+        if (unlikely(p == NULL))
+                goto out_overflow;
+        if (*p++ == xdr_zero) {
+                p = xdr_inline_decode(xdr, 4);
+                if (unlikely(p == NULL))
+                        goto out_overflow;
+                if (*p++ == xdr_zero)
+                        return -EAGAIN;
+                entry->eof = 1;
+                return -EBADCOOKIE;
+        }
+
+        p = xdr_inline_decode(xdr, 4);
+        if (unlikely(p == NULL))
+                goto out_overflow;
+        entry->ino = be32_to_cpup(p);
+
+        error = decode_filename_inline(xdr, &entry->name, &entry->len);
+        if (unlikely(error))
+                return error;
+
+        /*
+         * The type (size and byte order) of nfscookie isn't defined in
+         * RFC 1094.  This implementation assumes that it's an XDR uint32.
+         */
+        entry->prev_cookie = entry->cookie;
+        p = xdr_inline_decode(xdr, 4);
+        if (unlikely(p == NULL))
+                goto out_overflow;
+        entry->cookie = be32_to_cpup(p);
 
-        p = xdr_encode_fhandle(p, args->fh);
-        req->rq_slen = xdr_adjust_iovec(req->rq_svec, p);
+        entry->d_type = DT_UNKNOWN;
 
-        /* Inline the page array */
-        replen = (RPC_REPHDRSIZE + auth->au_rslack + NFS_readlinkres_sz) << 2;
-        xdr_inline_pages(&req->rq_rcv_buf, replen, args->pages, args->pgbase, args->pglen);
         return 0;
+
+out_overflow:
+        print_overflow_msg(__func__, xdr);
+        return -EAGAIN;
 }
 
 /*
- * Decode READLINK reply
+ * 2.2.17.  readdirres
+ *
+ *      union readdirres switch (stat status) {
+ *      case NFS_OK:
+ *              struct {
+ *                      entry *entries;
+ *                      bool eof;
+ *              } readdirok;
+ *      default:
+ *              void;
+ *      };
+ *
+ * Read the directory contents into the page cache, but don't
+ * touch them.  The actual decoding is done by nfs2_decode_dirent()
+ * during subsequent nfs_readdir() calls.
  */
-static int
-nfs_xdr_readlinkres(struct rpc_rqst *req, __be32 *p, void *dummy)
+static int decode_readdirok(struct xdr_stream *xdr)
 {
-        struct xdr_buf *rcvbuf = &req->rq_rcv_buf;
-        struct kvec *iov = rcvbuf->head;
+        u32 recvd, pglen;
         size_t hdrlen;
-        u32 len, recvd;
-        char    *kaddr;
-        int     status;
-
-        if ((status = ntohl(*p++)))
-                return nfs_stat_to_errno(status);
-        /* Convert length of symlink */
-        len = ntohl(*p++);
-        if (len >= rcvbuf->page_len) {
-                dprintk("nfs: server returned giant symlink!\n");
-                return -ENAMETOOLONG;
-        }
-        hdrlen = (u8 *) p - (u8 *) iov->iov_base;
-        if (iov->iov_len < hdrlen) {
-                dprintk("NFS: READLINK reply header overflowed:"
-                                "length %Zu > %Zu\n", hdrlen, iov->iov_len);
-                return -errno_NFSERR_IO;
-        } else if (iov->iov_len != hdrlen) {
-                dprintk("NFS: READLINK header is short. iovec will be shifted.\n");
-                xdr_shift_buf(rcvbuf, iov->iov_len - hdrlen);
-        }
-        recvd = req->rq_rcv_buf.len - hdrlen;
-        if (recvd < len) {
-                dprintk("NFS: server cheating in readlink reply: "
-                                "count %u > recvd %u\n", len, recvd);
-                return -EIO;
-        }
 
-        /* NULL terminate the string we got */
-        kaddr = (char *)kmap_atomic(rcvbuf->pages[0], KM_USER0);
-        kaddr[len+rcvbuf->page_base] = '\0';
-        kunmap_atomic(kaddr, KM_USER0);
-        return 0;
+        pglen = xdr->buf->page_len;
+        hdrlen = (u8 *)xdr->p - (u8 *)xdr->iov->iov_base;
+        recvd = xdr->buf->len - hdrlen;
+        if (unlikely(pglen > recvd))
+                goto out_cheating;
+out:
+        xdr_read_pages(xdr, pglen);
+        return pglen;
+out_cheating:
+        dprintk("NFS: server cheating in readdir result: "
+                "pglen %u > recvd %u\n", pglen, recvd);
+        pglen = recvd;
+        goto out;
 }
 
-/*
- * Decode WRITE reply
- */
-static int
-nfs_xdr_writeres(struct rpc_rqst *req, __be32 *p, struct nfs_writeres *res)
+static int nfs2_xdr_dec_readdirres(struct rpc_rqst *req,
+                                   struct xdr_stream *xdr, void *__unused)
 {
-        res->verf->committed = NFS_FILE_SYNC;
-        return nfs_xdr_attrstat(req, p, res->fattr);
+        enum nfs_stat status;
+        int error;
+
+        error = decode_stat(xdr, &status);
+        if (unlikely(error))
+                goto out;
+        if (status != NFS_OK)
+                goto out_default;
+        error = decode_readdirok(xdr);
+out:
+        return error;
+out_default:
+        return nfs_stat_to_errno(status);
 }
 
 /*
- * Decode STATFS reply
+ * 2.2.18.  statfsres
+ *
+ *      union statfsres (stat status) {
+ *      case NFS_OK:
+ *              struct {
+ *                      unsigned tsize;
+ *                      unsigned bsize;
+ *                      unsigned blocks;
+ *                      unsigned bfree;
+ *                      unsigned bavail;
+ *              } info;
+ *      default:
+ *              void;
+ *      };
  */
-static int
-nfs_xdr_statfsres(struct rpc_rqst *req, __be32 *p, struct nfs2_fsstat *res)
+static int decode_info(struct xdr_stream *xdr, struct nfs2_fsstat *result)
 {
-        int     status;
-
-        if ((status = ntohl(*p++)))
-                return nfs_stat_to_errno(status);
-
-        res->tsize  = ntohl(*p++);
-        res->bsize  = ntohl(*p++);
-        res->blocks = ntohl(*p++);
-        res->bfree  = ntohl(*p++);
-        res->bavail = ntohl(*p++);
+        __be32 *p;
+
+        p = xdr_inline_decode(xdr, NFS_info_sz << 2);
+        if (unlikely(p == NULL))
+                goto out_overflow;
+        result->tsize  = be32_to_cpup(p++);
+        result->bsize  = be32_to_cpup(p++);
+        result->blocks = be32_to_cpup(p++);
+        result->bfree  = be32_to_cpup(p++);
+        result->bavail = be32_to_cpup(p);
         return 0;
+out_overflow:
+        print_overflow_msg(__func__, xdr);
+        return -EIO;
+}
+
+static int nfs2_xdr_dec_statfsres(struct rpc_rqst *req, struct xdr_stream *xdr,
+                                  struct nfs2_fsstat *result)
+{
+        enum nfs_stat status;
+        int error;
+
+        error = decode_stat(xdr, &status);
+        if (unlikely(error))
+                goto out;
+        if (status != NFS_OK)
+                goto out_default;
+        error = decode_info(xdr, result);
+out:
+        return error;
+out_default:
+        return nfs_stat_to_errno(status);
 }
 
+
 /*
  * We need to translate between nfs status return values and
  * the local errno values which may not be the same.
  */
-static struct {
+static const struct {
         int stat;
         int errno;
 } nfs_errtbl[] = {
@@ -700,34 +1096,36 @@ static struct {
         { NFSERR_BAD_COOKIE,    -EBADCOOKIE     },
         { NFSERR_NOTSUPP,       -ENOTSUPP       },
         { NFSERR_TOOSMALL,      -ETOOSMALL      },
-        { NFSERR_SERVERFAULT,   -ESERVERFAULT   },
+        { NFSERR_SERVERFAULT,   -EREMOTEIO      },
         { NFSERR_BADTYPE,       -EBADTYPE       },
         { NFSERR_JUKEBOX,       -EJUKEBOX       },
         { -1,                   -EIO            }
 };
 
-/*
- * Convert an NFS error code to a local one.
- * This one is used jointly by NFSv2 and NFSv3.
+/**
+ * nfs_stat_to_errno - convert an NFS status code to a local errno
+ * @status: NFS status code to convert
+ *
+ * Returns a local errno value, or -EIO if the NFS status code is
+ * not recognized.  This function is used jointly by NFSv2 and NFSv3.
  */
-int
-nfs_stat_to_errno(int stat)
+int nfs_stat_to_errno(enum nfs_stat status)
 {
         int i;
 
         for (i = 0; nfs_errtbl[i].stat != -1; i++) {
-                if (nfs_errtbl[i].stat == stat)
+                if (nfs_errtbl[i].stat == (int)status)
                         return nfs_errtbl[i].errno;
         }
-        dprintk("nfs_stat_to_errno: bad nfs status return value: %d\n", stat);
+        dprintk("NFS: Unrecognized nfs status value: %u\n", status);
         return nfs_errtbl[i].errno;
 }
 
 #define PROC(proc, argtype, restype, timer)                             \
 [NFSPROC_##proc] = {                                                    \
         .p_proc     =  NFSPROC_##proc,                                  \
-        .p_encode   =  (kxdrproc_t) nfs_xdr_##argtype,                  \
-        .p_decode   =  (kxdrproc_t) nfs_xdr_##restype,                  \
+        .p_encode   =  (kxdreproc_t)nfs2_xdr_enc_##argtype,             \
+        .p_decode   =  (kxdrdproc_t)nfs2_xdr_dec_##restype,             \
         .p_arglen   =  NFS_##argtype##_sz,                              \
         .p_replen   =  NFS_##restype##_sz,                              \
         .p_timer    =  timer,                                           \
@@ -735,21 +1133,21 @@ nfs_stat_to_errno(int stat)
         .p_name     =  #proc,                                           \
         }
 struct rpc_procinfo     nfs_procedures[] = {
-    PROC(GETATTR,       fhandle,        attrstat, 1),
-    PROC(SETATTR,       sattrargs,      attrstat, 0),
-    PROC(LOOKUP,        diropargs,      diropres, 2),
-    PROC(READLINK,      readlinkargs,   readlinkres, 3),
-    PROC(READ,          readargs,       readres, 3),
-    PROC(WRITE,         writeargs,      writeres, 4),
-    PROC(CREATE,        createargs,     diropres, 0),
-    PROC(REMOVE,        removeargs,     stat, 0),
-    PROC(RENAME,        renameargs,     stat, 0),
-    PROC(LINK,          linkargs,       stat, 0),
-    PROC(SYMLINK,       symlinkargs,    stat, 0),
-    PROC(MKDIR,         createargs,     diropres, 0),
-    PROC(RMDIR,         diropargs,      stat, 0),
-    PROC(READDIR,       readdirargs,    readdirres, 3),
-    PROC(STATFS,        fhandle,        statfsres, 0),
+        PROC(GETATTR,   fhandle,        attrstat,       1),
+        PROC(SETATTR,   sattrargs,      attrstat,       0),
+        PROC(LOOKUP,    diropargs,      diropres,       2),
+        PROC(READLINK,  readlinkargs,   readlinkres,    3),
+        PROC(READ,      readargs,       readres,        3),
+        PROC(WRITE,     writeargs,      writeres,       4),
+        PROC(CREATE,    createargs,     diropres,       0),
+        PROC(REMOVE,    removeargs,     stat,           0),
+        PROC(RENAME,    renameargs,     stat,           0),
+        PROC(LINK,      linkargs,       stat,           0),
+        PROC(SYMLINK,   symlinkargs,    stat,           0),
+        PROC(MKDIR,     createargs,     diropres,       0),
+        PROC(RMDIR,     diropargs,      stat,           0),
+        PROC(READDIR,   readdirargs,    readdirres,     3),
+        PROC(STATFS,    fhandle,        statfsres,      0),
 };
 
 struct rpc_version              nfs_version2 = {
diff --git a/fs/nfs/nfs3acl.c b/fs/nfs/nfs3acl.c
index bac60515a4b3..9f88c5f4c7e2 100644
--- a/fs/nfs/nfs3acl.c
+++ b/fs/nfs/nfs3acl.c
@@ -1,4 +1,5 @@
 #include <linux/fs.h>
+#include <linux/gfp.h>
 #include <linux/nfs.h>
 #include <linux/nfs3.h>
 #include <linux/nfs_fs.h>
@@ -184,7 +185,6 @@ static void nfs3_cache_acls(struct inode *inode, struct posix_acl *acl,
 struct posix_acl *nfs3_proc_getacl(struct inode *inode, int type)
 {
         struct nfs_server *server = NFS_SERVER(inode);
-        struct nfs_fattr fattr;
         struct page *pages[NFSACL_MAXPAGES] = { };
         struct nfs3_getaclargs args = {
                 .fh = NFS_FH(inode),
@@ -192,7 +192,7 @@ struct posix_acl *nfs3_proc_getacl(struct inode *inode, int type)
                 .pages = pages,
         };
         struct nfs3_getaclres res = {
-                .fattr =        &fattr,
+                0
         };
         struct rpc_message msg = {
                 .rpc_argp       = &args,
@@ -227,7 +227,10 @@ struct posix_acl *nfs3_proc_getacl(struct inode *inode, int type)
 
         dprintk("NFS call getacl\n");
         msg.rpc_proc = &server->client_acl->cl_procinfo[ACLPROC3_GETACL];
-        nfs_fattr_init(&fattr);
+        res.fattr = nfs_alloc_fattr();
+        if (res.fattr == NULL)
+                return ERR_PTR(-ENOMEM);
+
         status = rpc_call_sync(server->client_acl, &msg, 0);
         dprintk("NFS reply getacl: %d\n", status);
 
@@ -237,7 +240,7 @@ struct posix_acl *nfs3_proc_getacl(struct inode *inode, int type)
 
         switch (status) {
                 case 0:
-                        status = nfs_refresh_inode(inode, &fattr);
+                        status = nfs_refresh_inode(inode, res.fattr);
                         break;
                 case -EPFNOSUPPORT:
                 case -EPROTONOSUPPORT:
@@ -277,6 +280,7 @@ struct posix_acl *nfs3_proc_getacl(struct inode *inode, int type)
 getout:
         posix_acl_release(res.acl_access);
         posix_acl_release(res.acl_default);
+        nfs_free_fattr(res.fattr);
 
         if (status != 0) {
                 posix_acl_release(acl);
@@ -289,7 +293,7 @@ static int nfs3_proc_setacls(struct inode *inode, struct posix_acl *acl,
                   struct posix_acl *dfacl)
 {
         struct nfs_server *server = NFS_SERVER(inode);
-        struct nfs_fattr fattr;
+        struct nfs_fattr *fattr;
         struct page *pages[NFSACL_MAXPAGES];
         struct nfs3_setaclargs args = {
                 .inode = inode,
@@ -334,8 +338,13 @@ static int nfs3_proc_setacls(struct inode *inode, struct posix_acl *acl,
         }
 
         dprintk("NFS call setacl\n");
+        status = -ENOMEM;
+        fattr = nfs_alloc_fattr();
+        if (fattr == NULL)
+                goto out_freepages;
+
         msg.rpc_proc = &server->client_acl->cl_procinfo[ACLPROC3_SETACL];
-        nfs_fattr_init(&fattr);
+        msg.rpc_resp = fattr;
         status = rpc_call_sync(server->client_acl, &msg, 0);
         nfs_access_zap_cache(inode);
         nfs_zap_acl_cache(inode);
@@ -343,7 +352,7 @@ static int nfs3_proc_setacls(struct inode *inode, struct posix_acl *acl,
 
         switch (status) {
                 case 0:
-                        status = nfs_refresh_inode(inode, &fattr);
+                        status = nfs_refresh_inode(inode, fattr);
                         nfs3_cache_acls(inode, acl, dfacl);
                         break;
                 case -EPFNOSUPPORT:
@@ -354,6 +363,7 @@ static int nfs3_proc_setacls(struct inode *inode, struct posix_acl *acl,
                 case -ENOTSUPP:
                         status = -EOPNOTSUPP;
         }
+        nfs_free_fattr(fattr);
 out_freepages:
         while (args.npages != 0) {
                 args.npages--;
diff --git a/fs/nfs/nfs3proc.c b/fs/nfs/nfs3proc.c
index d0cc5ce0edfe..ce939c062a52 100644
--- a/fs/nfs/nfs3proc.c
+++ b/fs/nfs/nfs3proc.c
@@ -7,10 +7,10 @@
  */
 
 #include <linux/mm.h>
-#include <linux/utsname.h>
 #include <linux/errno.h>
 #include <linux/string.h>
 #include <linux/sunrpc/clnt.h>
+#include <linux/slab.h>
 #include <linux/nfs.h>
 #include <linux/nfs3.h>
 #include <linux/nfs_fs.h>
@@ -23,14 +23,14 @@
 
 #define NFSDBG_FACILITY         NFSDBG_PROC
 
-/* A wrapper to handle the EJUKEBOX error message */
+/* A wrapper to handle the EJUKEBOX and EKEYEXPIRED error messages */
 static int
 nfs3_rpc_wrapper(struct rpc_clnt *clnt, struct rpc_message *msg, int flags)
 {
         int res;
         do {
                 res = rpc_call_sync(clnt, msg, flags);
-                if (res != -EJUKEBOX)
+                if (res != -EJUKEBOX && res != -EKEYEXPIRED)
                         break;
                 schedule_timeout_killable(NFS_JUKEBOX_RETRY_TIME);
                 res = -ERESTARTSYS;
@@ -43,9 +43,10 @@ nfs3_rpc_wrapper(struct rpc_clnt *clnt, struct rpc_message *msg, int flags)
 static int
 nfs3_async_handle_jukebox(struct rpc_task *task, struct inode *inode)
 {
-        if (task->tk_status != -EJUKEBOX)
+        if (task->tk_status != -EJUKEBOX && task->tk_status != -EKEYEXPIRED)
                 return 0;
-        nfs_inc_stats(inode, NFSIOS_DELAY);
+        if (task->tk_status == -EJUKEBOX)
+                nfs_inc_stats(inode, NFSIOS_DELAY);
         task->tk_status = 0;
         rpc_restart_call(task);
         rpc_delay(task, NFS_JUKEBOX_RETRY_TIME);
@@ -143,14 +144,12 @@ static int
 nfs3_proc_lookup(struct inode *dir, struct qstr *name,
                  struct nfs_fh *fhandle, struct nfs_fattr *fattr)
 {
-        struct nfs_fattr        dir_attr;
         struct nfs3_diropargs   arg = {
                 .fh             = NFS_FH(dir),
                 .name           = name->name,
                 .len            = name->len
         };
         struct nfs3_diropres    res = {
-                .dir_attr       = &dir_attr,
                 .fh             = fhandle,
                 .fattr          = fattr
         };
@@ -162,29 +161,30 @@ nfs3_proc_lookup(struct inode *dir, struct qstr *name,
         int                     status;
 
         dprintk("NFS call  lookup %s\n", name->name);
-        nfs_fattr_init(&dir_attr);
+        res.dir_attr = nfs_alloc_fattr();
+        if (res.dir_attr == NULL)
+                return -ENOMEM;
+
         nfs_fattr_init(fattr);
         status = rpc_call_sync(NFS_CLIENT(dir), &msg, 0);
-        nfs_refresh_inode(dir, &dir_attr);
+        nfs_refresh_inode(dir, res.dir_attr);
         if (status >= 0 && !(fattr->valid & NFS_ATTR_FATTR)) {
                 msg.rpc_proc = &nfs3_procedures[NFS3PROC_GETATTR];
                 msg.rpc_argp = fhandle;
                 msg.rpc_resp = fattr;
                 status = rpc_call_sync(NFS_CLIENT(dir), &msg, 0);
         }
+        nfs_free_fattr(res.dir_attr);
         dprintk("NFS reply lookup: %d\n", status);
         return status;
 }
 
 static int nfs3_proc_access(struct inode *inode, struct nfs_access_entry *entry)
 {
-        struct nfs_fattr        fattr;
         struct nfs3_accessargs  arg = {
                 .fh             = NFS_FH(inode),
         };
-        struct nfs3_accessres   res = {
-                .fattr          = &fattr,
-        };
+        struct nfs3_accessres   res;
         struct rpc_message msg = {
                 .rpc_proc       = &nfs3_procedures[NFS3PROC_ACCESS],
                 .rpc_argp       = &arg,
@@ -192,7 +192,7 @@ static int nfs3_proc_access(struct inode *inode, struct nfs_access_entry *entry)
                 .rpc_cred       = entry->cred,
         };
         int mode = entry->mask;
-        int status;
+        int status = -ENOMEM;
 
         dprintk("NFS call  access\n");
 
@@ -209,9 +209,13 @@ static int nfs3_proc_access(struct inode *inode, struct nfs_access_entry *entry)
                 if (mode & MAY_EXEC)
                         arg.access |= NFS3_ACCESS_EXECUTE;
         }
-        nfs_fattr_init(&fattr);
+
+        res.fattr = nfs_alloc_fattr();
+        if (res.fattr == NULL)
+                goto out;
+
         status = rpc_call_sync(NFS_CLIENT(inode), &msg, 0);
-        nfs_refresh_inode(inode, &fattr);
+        nfs_refresh_inode(inode, res.fattr);
         if (status == 0) {
                 entry->mask = 0;
                 if (res.access & NFS3_ACCESS_READ)
@@ -221,6 +225,8 @@ static int nfs3_proc_access(struct inode *inode, struct nfs_access_entry *entry)
                 if (res.access & (NFS3_ACCESS_LOOKUP|NFS3_ACCESS_EXECUTE))
                         entry->mask |= MAY_EXEC;
         }
+        nfs_free_fattr(res.fattr);
+out:
         dprintk("NFS reply access: %d\n", status);
         return status;
 }
@@ -228,7 +234,7 @@ static int nfs3_proc_access(struct inode *inode, struct nfs_access_entry *entry)
 static int nfs3_proc_readlink(struct inode *inode, struct page *page,
                 unsigned int pgbase, unsigned int pglen)
 {
-        struct nfs_fattr        fattr;
+        struct nfs_fattr        *fattr;
         struct nfs3_readlinkargs args = {
                 .fh             = NFS_FH(inode),
                 .pgbase         = pgbase,
@@ -238,14 +244,19 @@ static int nfs3_proc_readlink(struct inode *inode, struct page *page,
         struct rpc_message msg = {
                 .rpc_proc       = &nfs3_procedures[NFS3PROC_READLINK],
                 .rpc_argp       = &args,
-                .rpc_resp       = &fattr,
         };
-        int                     status;
+        int status = -ENOMEM;
 
         dprintk("NFS call  readlink\n");
-        nfs_fattr_init(&fattr);
+        fattr = nfs_alloc_fattr();
+        if (fattr == NULL)
+                goto out;
+        msg.rpc_resp = fattr;
+
         status = rpc_call_sync(NFS_CLIENT(inode), &msg, 0);
-        nfs_refresh_inode(inode, &fattr);
+        nfs_refresh_inode(inode, fattr);
+        nfs_free_fattr(fattr);
+out:
         dprintk("NFS reply readlink: %d\n", status);
         return status;
 }
@@ -299,11 +310,10 @@ static void nfs3_free_createdata(struct nfs3_createdata *data)
 
 /*
  * Create a regular file.
- * For now, we don't implement O_EXCL.
  */
 static int
 nfs3_proc_create(struct inode *dir, struct dentry *dentry, struct iattr *sattr,
-                 int flags, struct nameidata *nd)
+                 int flags, struct nfs_open_context *ctx)
 {
         struct nfs3_createdata *data;
         mode_t mode = sattr->ia_mode;
@@ -396,12 +406,17 @@ nfs3_proc_remove(struct inode *dir, struct qstr *name)
                 .rpc_argp = &arg,
                 .rpc_resp = &res,
         };
-        int                     status;
+        int status = -ENOMEM;
 
         dprintk("NFS call  remove %s\n", name->name);
-        nfs_fattr_init(&res.dir_attr);
+        res.dir_attr = nfs_alloc_fattr();
+        if (res.dir_attr == NULL)
+                goto out;
+
         status = rpc_call_sync(NFS_CLIENT(dir), &msg, 0);
-        nfs_post_op_update_inode(dir, &res.dir_attr);
+        nfs_post_op_update_inode(dir, res.dir_attr);
+        nfs_free_fattr(res.dir_attr);
+out:
         dprintk("NFS reply remove: %d\n", status);
         return status;
 }
@@ -419,7 +434,28 @@ nfs3_proc_unlink_done(struct rpc_task *task, struct inode *dir)
         if (nfs3_async_handle_jukebox(task, dir))
                 return 0;
         res = task->tk_msg.rpc_resp;
-        nfs_post_op_update_inode(dir, &res->dir_attr);
+        nfs_post_op_update_inode(dir, res->dir_attr);
+        return 1;
+}
+
+static void
+nfs3_proc_rename_setup(struct rpc_message *msg, struct inode *dir)
+{
+        msg->rpc_proc = &nfs3_procedures[NFS3PROC_RENAME];
+}
+
+static int
+nfs3_proc_rename_done(struct rpc_task *task, struct inode *old_dir,
+                      struct inode *new_dir)
+{
+        struct nfs_renameres *res;
+
+        if (nfs3_async_handle_jukebox(task, old_dir))
+                return 0;
+        res = task->tk_msg.rpc_resp;
+
+        nfs_post_op_update_inode(old_dir, res->old_fattr);
+        nfs_post_op_update_inode(new_dir, res->new_fattr);
         return 1;
 }
 
@@ -427,32 +463,33 @@ static int
 nfs3_proc_rename(struct inode *old_dir, struct qstr *old_name,
                  struct inode *new_dir, struct qstr *new_name)
 {
-        struct nfs_fattr        old_dir_attr, new_dir_attr;
-        struct nfs3_renameargs  arg = {
-                .fromfh         = NFS_FH(old_dir),
-                .fromname       = old_name->name,
-                .fromlen        = old_name->len,
-                .tofh           = NFS_FH(new_dir),
-                .toname         = new_name->name,
-                .tolen          = new_name->len
-        };
-        struct nfs3_renameres   res = {
-                .fromattr       = &old_dir_attr,
-                .toattr         = &new_dir_attr
+        struct nfs_renameargs   arg = {
+                .old_dir        = NFS_FH(old_dir),
+                .old_name       = old_name,
+                .new_dir        = NFS_FH(new_dir),
+                .new_name       = new_name,
         };
+        struct nfs_renameres res;
         struct rpc_message msg = {
                 .rpc_proc       = &nfs3_procedures[NFS3PROC_RENAME],
                 .rpc_argp       = &arg,
                 .rpc_resp       = &res,
         };
-        int                     status;
+        int status = -ENOMEM;
 
         dprintk("NFS call  rename %s -> %s\n", old_name->name, new_name->name);
-        nfs_fattr_init(&old_dir_attr);
-        nfs_fattr_init(&new_dir_attr);
+
+        res.old_fattr = nfs_alloc_fattr();
+        res.new_fattr = nfs_alloc_fattr();
+        if (res.old_fattr == NULL || res.new_fattr == NULL)
+                goto out;
+
         status = rpc_call_sync(NFS_CLIENT(old_dir), &msg, 0);
-        nfs_post_op_update_inode(old_dir, &old_dir_attr);
-        nfs_post_op_update_inode(new_dir, &new_dir_attr);
+        nfs_post_op_update_inode(old_dir, res.old_fattr);
+        nfs_post_op_update_inode(new_dir, res.new_fattr);
+out:
+        nfs_free_fattr(res.old_fattr);
+        nfs_free_fattr(res.new_fattr);
         dprintk("NFS reply rename: %d\n", status);
         return status;
 }
@@ -460,30 +497,32 @@ nfs3_proc_rename(struct inode *old_dir, struct qstr *old_name,
 static int
 nfs3_proc_link(struct inode *inode, struct inode *dir, struct qstr *name)
 {
-        struct nfs_fattr        dir_attr, fattr;
         struct nfs3_linkargs    arg = {
                 .fromfh         = NFS_FH(inode),
                 .tofh           = NFS_FH(dir),
                 .toname         = name->name,
                 .tolen          = name->len
         };
-        struct nfs3_linkres     res = {
-                .dir_attr       = &dir_attr,
-                .fattr          = &fattr
-        };
+        struct nfs3_linkres     res;
         struct rpc_message msg = {
                 .rpc_proc       = &nfs3_procedures[NFS3PROC_LINK],
                 .rpc_argp       = &arg,
                 .rpc_resp       = &res,
         };
-        int                     status;
+        int status = -ENOMEM;
 
         dprintk("NFS call  link %s\n", name->name);
-        nfs_fattr_init(&dir_attr);
-        nfs_fattr_init(&fattr);
+        res.fattr = nfs_alloc_fattr();
+        res.dir_attr = nfs_alloc_fattr();
+        if (res.fattr == NULL || res.dir_attr == NULL)
+                goto out;
+
         status = rpc_call_sync(NFS_CLIENT(inode), &msg, 0);
-        nfs_post_op_update_inode(dir, &dir_attr);
-        nfs_post_op_update_inode(inode, &fattr);
+        nfs_post_op_update_inode(dir, res.dir_attr);
+        nfs_post_op_update_inode(inode, res.fattr);
+out:
+        nfs_free_fattr(res.dir_attr);
+        nfs_free_fattr(res.fattr);
         dprintk("NFS reply link: %d\n", status);
         return status;
 }
@@ -554,7 +593,7 @@ out:
 static int
 nfs3_proc_rmdir(struct inode *dir, struct qstr *name)
 {
-        struct nfs_fattr        dir_attr;
+        struct nfs_fattr        *dir_attr;
         struct nfs3_diropargs   arg = {
                 .fh             = NFS_FH(dir),
                 .name           = name->name,
@@ -563,14 +602,19 @@ nfs3_proc_rmdir(struct inode *dir, struct qstr *name)
         struct rpc_message msg = {
                 .rpc_proc       = &nfs3_procedures[NFS3PROC_RMDIR],
                 .rpc_argp       = &arg,
-                .rpc_resp       = &dir_attr,
         };
-        int                     status;
+        int status = -ENOMEM;
 
         dprintk("NFS call  rmdir %s\n", name->name);
-        nfs_fattr_init(&dir_attr);
+        dir_attr = nfs_alloc_fattr();
+        if (dir_attr == NULL)
+                goto out;
+
+        msg.rpc_resp = dir_attr;
         status = rpc_call_sync(NFS_CLIENT(dir), &msg, 0);
-        nfs_post_op_update_inode(dir, &dir_attr);
+        nfs_post_op_update_inode(dir, dir_attr);
+        nfs_free_fattr(dir_attr);
+out:
         dprintk("NFS reply rmdir: %d\n", status);
         return status;
 }
@@ -586,10 +630,9 @@ nfs3_proc_rmdir(struct inode *dir, struct qstr *name)
  */
 static int
 nfs3_proc_readdir(struct dentry *dentry, struct rpc_cred *cred,
-                  u64 cookie, struct page *page, unsigned int count, int plus)
+                  u64 cookie, struct page **pages, unsigned int count, int plus)
 {
         struct inode            *dir = dentry->d_inode;
-        struct nfs_fattr        dir_attr;
         __be32                  *verf = NFS_COOKIEVERF(dir);
         struct nfs3_readdirargs arg = {
                 .fh             = NFS_FH(dir),
@@ -597,10 +640,9 @@ nfs3_proc_readdir(struct dentry *dentry, struct rpc_cred *cred,
                 .verf           = {verf[0], verf[1]},
                 .plus           = plus,
                 .count          = count,
-                .pages          = &page
+                .pages          = pages
         };
         struct nfs3_readdirres  res = {
-                .dir_attr       = &dir_attr,
                 .verf           = verf,
                 .plus           = plus
         };
@@ -610,7 +652,7 @@ nfs3_proc_readdir(struct dentry *dentry, struct rpc_cred *cred,
                 .rpc_resp       = &res,
                 .rpc_cred       = cred
         };
-        int                     status;
+        int status = -ENOMEM;
 
         if (plus)
                 msg.rpc_proc = &nfs3_procedures[NFS3PROC_READDIRPLUS];
@@ -618,13 +660,19 @@ nfs3_proc_readdir(struct dentry *dentry, struct rpc_cred *cred,
         dprintk("NFS call  readdir%s %d\n",
                         plus? "plus" : "", (unsigned int) cookie);
 
-        nfs_fattr_init(&dir_attr);
+        res.dir_attr = nfs_alloc_fattr();
+        if (res.dir_attr == NULL)
+                goto out;
+
         status = rpc_call_sync(NFS_CLIENT(dir), &msg, 0);
 
         nfs_invalidate_atime(dir);
+        nfs_refresh_inode(dir, res.dir_attr);
 
-        nfs_refresh_inode(dir, &dir_attr);
-        dprintk("NFS reply readdir: %d\n", status);
+        nfs_free_fattr(res.dir_attr);
+out:
+        dprintk("NFS reply readdir%s: %d\n",
+                        plus? "plus" : "", status);
         return status;
 }
 
@@ -694,7 +742,7 @@ nfs3_proc_statfs(struct nfs_server *server, struct nfs_fh *fhandle,
         dprintk("NFS call  fsstat\n");
         nfs_fattr_init(stat->fattr);
         status = rpc_call_sync(server->client, &msg, 0);
-        dprintk("NFS reply statfs: %d\n", status);
+        dprintk("NFS reply fsstat: %d\n", status);
         return status;
 }
 
@@ -816,6 +864,8 @@ const struct nfs_rpc_ops nfs_v3_clientops = {
         .unlink_setup   = nfs3_proc_unlink_setup,
         .unlink_done    = nfs3_proc_unlink_done,
         .rename         = nfs3_proc_rename,
+        .rename_setup   = nfs3_proc_rename_setup,
+        .rename_done    = nfs3_proc_rename_done,
         .link           = nfs3_proc_link,
         .symlink        = nfs3_proc_symlink,
         .mkdir          = nfs3_proc_mkdir,
diff --git a/fs/nfs/nfs3xdr.c b/fs/nfs/nfs3xdr.c
index 35869a4921f1..01c5e8b1941d 100644
--- a/fs/nfs/nfs3xdr.c
+++ b/fs/nfs/nfs3xdr.c
@@ -9,8 +9,6 @@
 #include <linux/param.h>
 #include <linux/time.h>
 #include <linux/mm.h>
-#include <linux/slab.h>
-#include <linux/utsname.h>
 #include <linux/errno.h>
 #include <linux/string.h>
 #include <linux/in.h>
@@ -39,18 +37,16 @@
 #define NFS3_filename_sz        (1+(NFS3_MAXNAMLEN>>2))
 #define NFS3_path_sz            (1+(NFS3_MAXPATHLEN>>2))
 #define NFS3_fattr_sz           (21)
-#define NFS3_wcc_attr_sz                (6)
+#define NFS3_cookieverf_sz      (NFS3_COOKIEVERFSIZE>>2)
+#define NFS3_wcc_attr_sz        (6)
 #define NFS3_pre_op_attr_sz     (1+NFS3_wcc_attr_sz)
 #define NFS3_post_op_attr_sz    (1+NFS3_fattr_sz)
-#define NFS3_wcc_data_sz                (NFS3_pre_op_attr_sz+NFS3_post_op_attr_sz)
-#define NFS3_fsstat_sz          
-#define NFS3_fsinfo_sz          
-#define NFS3_pathconf_sz                
-#define NFS3_entry_sz           (NFS3_filename_sz+3)
-
-#define NFS3_sattrargs_sz       (NFS3_fh_sz+NFS3_sattr_sz+3)
+#define NFS3_wcc_data_sz        (NFS3_pre_op_attr_sz+NFS3_post_op_attr_sz)
 #define NFS3_diropargs_sz       (NFS3_fh_sz+NFS3_filename_sz)
-#define NFS3_removeargs_sz      (NFS3_fh_sz+NFS3_filename_sz)
+
+#define NFS3_getattrargs_sz     (NFS3_fh_sz)
+#define NFS3_setattrargs_sz     (NFS3_fh_sz+NFS3_sattr_sz+3)
+#define NFS3_lookupargs_sz      (NFS3_fh_sz+NFS3_filename_sz)
 #define NFS3_accessargs_sz      (NFS3_fh_sz+1)
 #define NFS3_readlinkargs_sz    (NFS3_fh_sz)
 #define NFS3_readargs_sz        (NFS3_fh_sz+3)
@@ -59,14 +55,16 @@
 #define NFS3_mkdirargs_sz       (NFS3_diropargs_sz+NFS3_sattr_sz)
 #define NFS3_symlinkargs_sz     (NFS3_diropargs_sz+1+NFS3_sattr_sz)
 #define NFS3_mknodargs_sz       (NFS3_diropargs_sz+2+NFS3_sattr_sz)
+#define NFS3_removeargs_sz      (NFS3_fh_sz+NFS3_filename_sz)
 #define NFS3_renameargs_sz      (NFS3_diropargs_sz+NFS3_diropargs_sz)
 #define NFS3_linkargs_sz                (NFS3_fh_sz+NFS3_diropargs_sz)
-#define NFS3_readdirargs_sz     (NFS3_fh_sz+2)
+#define NFS3_readdirargs_sz     (NFS3_fh_sz+NFS3_cookieverf_sz+3)
+#define NFS3_readdirplusargs_sz (NFS3_fh_sz+NFS3_cookieverf_sz+4)
 #define NFS3_commitargs_sz      (NFS3_fh_sz+3)
 
-#define NFS3_attrstat_sz        (1+NFS3_fattr_sz)
-#define NFS3_wccstat_sz         (1+NFS3_wcc_data_sz)
-#define NFS3_removeres_sz       (NFS3_wccstat_sz)
+#define NFS3_getattrres_sz      (1+NFS3_fattr_sz)
+#define NFS3_setattrres_sz      (1+NFS3_wcc_data_sz)
+#define NFS3_removeres_sz       (NFS3_setattrres_sz)
 #define NFS3_lookupres_sz       (1+NFS3_fh_sz+(2 * NFS3_post_op_attr_sz))
 #define NFS3_accessres_sz       (1+NFS3_post_op_attr_sz+1)
 #define NFS3_readlinkres_sz     (1+NFS3_post_op_attr_sz+1)
@@ -103,1074 +101,2361 @@ static const umode_t nfs_type2fmt[] = {
 };
 
 /*
- * Common NFS XDR functions as inlines
+ * While encoding arguments, set up the reply buffer in advance to
+ * receive reply data directly into the page cache.
  */
-static inline __be32 *
-xdr_encode_fhandle(__be32 *p, const struct nfs_fh *fh)
+static void prepare_reply_buffer(struct rpc_rqst *req, struct page **pages,
+                                 unsigned int base, unsigned int len,
+                                 unsigned int bufsize)
 {
-        return xdr_encode_array(p, fh->data, fh->size);
+        struct rpc_auth *auth = req->rq_cred->cr_auth;
+        unsigned int replen;
+
+        replen = RPC_REPHDRSIZE + auth->au_rslack + bufsize;
+        xdr_inline_pages(&req->rq_rcv_buf, replen << 2, pages, base, len);
 }
 
-static inline __be32 *
-xdr_decode_fhandle(__be32 *p, struct nfs_fh *fh)
+/*
+ * Handle decode buffer overflows out-of-line.
+ */
+static void print_overflow_msg(const char *func, const struct xdr_stream *xdr)
 {
-        if ((fh->size = ntohl(*p++)) <= NFS3_FHSIZE) {
-                memcpy(fh->data, p, fh->size);
-                return p + XDR_QUADLEN(fh->size);
-        }
-        return NULL;
+        dprintk("NFS: %s prematurely hit the end of our receive buffer. "
+                "Remaining buffer length is %tu words.\n",
+                func, xdr->end - xdr->p);
 }
 
+
 /*
- * Encode/decode time.
+ * Encode/decode NFSv3 basic data types
+ *
+ * Basic NFSv3 data types are defined in section 2.5 of RFC 1813:
+ * "NFS Version 3 Protocol Specification".
+ *
+ * Not all basic data types have their own encoding and decoding
+ * functions.  For run-time efficiency, some data types are encoded
+ * or decoded inline.
  */
-static inline __be32 *
-xdr_encode_time3(__be32 *p, struct timespec *timep)
+
+static void encode_uint32(struct xdr_stream *xdr, u32 value)
 {
-        *p++ = htonl(timep->tv_sec);
-        *p++ = htonl(timep->tv_nsec);
-        return p;
+        __be32 *p = xdr_reserve_space(xdr, 4);
+        *p = cpu_to_be32(value);
 }
 
-static inline __be32 *
-xdr_decode_time3(__be32 *p, struct timespec *timep)
+static int decode_uint32(struct xdr_stream *xdr, u32 *value)
 {
-        timep->tv_sec = ntohl(*p++);
-        timep->tv_nsec = ntohl(*p++);
-        return p;
+        __be32 *p;
+
+        p = xdr_inline_decode(xdr, 4);
+        if (unlikely(p == NULL))
+                goto out_overflow;
+        *value = be32_to_cpup(p);
+        return 0;
+out_overflow:
+        print_overflow_msg(__func__, xdr);
+        return -EIO;
 }
 
-static __be32 *
-xdr_decode_fattr(__be32 *p, struct nfs_fattr *fattr)
+static int decode_uint64(struct xdr_stream *xdr, u64 *value)
 {
-        unsigned int    type, major, minor;
-        umode_t         fmode;
+        __be32 *p;
 
-        type = ntohl(*p++);
-        if (type > NF3FIFO)
-                type = NF3NON;
-        fmode = nfs_type2fmt[type];
-        fattr->mode = (ntohl(*p++) & ~S_IFMT) | fmode;
-        fattr->nlink = ntohl(*p++);
-        fattr->uid = ntohl(*p++);
-        fattr->gid = ntohl(*p++);
-        p = xdr_decode_hyper(p, &fattr->size);
-        p = xdr_decode_hyper(p, &fattr->du.nfs3.used);
-
-        /* Turn remote device info into Linux-specific dev_t */
-        major = ntohl(*p++);
-        minor = ntohl(*p++);
-        fattr->rdev = MKDEV(major, minor);
-        if (MAJOR(fattr->rdev) != major || MINOR(fattr->rdev) != minor)
-                fattr->rdev = 0;
+        p = xdr_inline_decode(xdr, 8);
+        if (unlikely(p == NULL))
+                goto out_overflow;
+        xdr_decode_hyper(p, value);
+        return 0;
+out_overflow:
+        print_overflow_msg(__func__, xdr);
+        return -EIO;
+}
 
-        p = xdr_decode_hyper(p, &fattr->fsid.major);
-        fattr->fsid.minor = 0;
-        p = xdr_decode_hyper(p, &fattr->fileid);
-        p = xdr_decode_time3(p, &fattr->atime);
-        p = xdr_decode_time3(p, &fattr->mtime);
-        p = xdr_decode_time3(p, &fattr->ctime);
+/*
+ * fileid3
+ *
+ *      typedef uint64 fileid3;
+ */
+static __be32 *xdr_decode_fileid3(__be32 *p, u64 *fileid)
+{
+        return xdr_decode_hyper(p, fileid);
+}
 
-        /* Update the mode bits */
-        fattr->valid |= NFS_ATTR_FATTR_V3;
-        return p;
+static int decode_fileid3(struct xdr_stream *xdr, u64 *fileid)
+{
+        return decode_uint64(xdr, fileid);
 }
 
-static inline __be32 *
-xdr_encode_sattr(__be32 *p, struct iattr *attr)
+/*
+ * filename3
+ *
+ *      typedef string filename3<>;
+ */
+static void encode_filename3(struct xdr_stream *xdr,
+                             const char *name, u32 length)
 {
-        if (attr->ia_valid & ATTR_MODE) {
-                *p++ = xdr_one;
-                *p++ = htonl(attr->ia_mode & S_IALLUGO);
-        } else {
-                *p++ = xdr_zero;
-        }
-        if (attr->ia_valid & ATTR_UID) {
-                *p++ = xdr_one;
-                *p++ = htonl(attr->ia_uid);
-        } else {
-                *p++ = xdr_zero;
-        }
-        if (attr->ia_valid & ATTR_GID) {
-                *p++ = xdr_one;
-                *p++ = htonl(attr->ia_gid);
-        } else {
-                *p++ = xdr_zero;
-        }
-        if (attr->ia_valid & ATTR_SIZE) {
-                *p++ = xdr_one;
-                p = xdr_encode_hyper(p, (__u64) attr->ia_size);
-        } else {
-                *p++ = xdr_zero;
-        }
-        if (attr->ia_valid & ATTR_ATIME_SET) {
-                *p++ = xdr_two;
-                p = xdr_encode_time3(p, &attr->ia_atime);
-        } else if (attr->ia_valid & ATTR_ATIME) {
-                *p++ = xdr_one;
-        } else {
-                *p++ = xdr_zero;
-        }
-        if (attr->ia_valid & ATTR_MTIME_SET) {
-                *p++ = xdr_two;
-                p = xdr_encode_time3(p, &attr->ia_mtime);
-        } else if (attr->ia_valid & ATTR_MTIME) {
-                *p++ = xdr_one;
-        } else {
-                *p++ = xdr_zero;
-        }
-        return p;
+        __be32 *p;
+
+        BUG_ON(length > NFS3_MAXNAMLEN);
+        p = xdr_reserve_space(xdr, 4 + length);
+        xdr_encode_opaque(p, name, length);
 }
 
-static inline __be32 *
-xdr_decode_wcc_attr(__be32 *p, struct nfs_fattr *fattr)
+static int decode_inline_filename3(struct xdr_stream *xdr,
+                                   const char **name, u32 *length)
 {
-        p = xdr_decode_hyper(p, &fattr->pre_size);
-        p = xdr_decode_time3(p, &fattr->pre_mtime);
-        p = xdr_decode_time3(p, &fattr->pre_ctime);
-        fattr->valid |= NFS_ATTR_FATTR_PRESIZE
-                | NFS_ATTR_FATTR_PREMTIME
-                | NFS_ATTR_FATTR_PRECTIME;
-        return p;
+        __be32 *p;
+        u32 count;
+
+        p = xdr_inline_decode(xdr, 4);
+        if (unlikely(p == NULL))
+                goto out_overflow;
+        count = be32_to_cpup(p);
+        if (count > NFS3_MAXNAMLEN)
+                goto out_nametoolong;
+        p = xdr_inline_decode(xdr, count);
+        if (unlikely(p == NULL))
+                goto out_overflow;
+        *name = (const char *)p;
+        *length = count;
+        return 0;
+
+out_nametoolong:
+        dprintk("NFS: returned filename too long: %u\n", count);
+        return -ENAMETOOLONG;
+out_overflow:
+        print_overflow_msg(__func__, xdr);
+        return -EIO;
 }
 
-static inline __be32 *
-xdr_decode_post_op_attr(__be32 *p, struct nfs_fattr *fattr)
+/*
+ * nfspath3
+ *
+ *      typedef string nfspath3<>;
+ */
+static void encode_nfspath3(struct xdr_stream *xdr, struct page **pages,
+                            const u32 length)
 {
-        if (*p++)
-                p = xdr_decode_fattr(p, fattr);
-        return p;
+        BUG_ON(length > NFS3_MAXPATHLEN);
+        encode_uint32(xdr, length);
+        xdr_write_pages(xdr, pages, 0, length);
 }
 
-static inline __be32 *
-xdr_decode_pre_op_attr(__be32 *p, struct nfs_fattr *fattr)
+static int decode_nfspath3(struct xdr_stream *xdr)
 {
-        if (*p++)
-                return xdr_decode_wcc_attr(p, fattr);
-        return p;
+        u32 recvd, count;
+        size_t hdrlen;
+        __be32 *p;
+
+        p = xdr_inline_decode(xdr, 4);
+        if (unlikely(p == NULL))
+                goto out_overflow;
+        count = be32_to_cpup(p);
+        if (unlikely(count >= xdr->buf->page_len || count > NFS3_MAXPATHLEN))
+                goto out_nametoolong;
+        hdrlen = (u8 *)xdr->p - (u8 *)xdr->iov->iov_base;
+        recvd = xdr->buf->len - hdrlen;
+        if (unlikely(count > recvd))
+                goto out_cheating;
+
+        xdr_read_pages(xdr, count);
+        xdr_terminate_string(xdr->buf, count);
+        return 0;
+
+out_nametoolong:
+        dprintk("NFS: returned pathname too long: %u\n", count);
+        return -ENAMETOOLONG;
+out_cheating:
+        dprintk("NFS: server cheating in pathname result: "
+                "count %u > recvd %u\n", count, recvd);
+        return -EIO;
+out_overflow:
+        print_overflow_msg(__func__, xdr);
+        return -EIO;
 }
 
+/*
+ * cookie3
+ *
+ *      typedef uint64 cookie3
+ */
+static __be32 *xdr_encode_cookie3(__be32 *p, u64 cookie)
+{
+        return xdr_encode_hyper(p, cookie);
+}
 
-static inline __be32 *
-xdr_decode_wcc_data(__be32 *p, struct nfs_fattr *fattr)
+static int decode_cookie3(struct xdr_stream *xdr, u64 *cookie)
 {
-        p = xdr_decode_pre_op_attr(p, fattr);
-        return xdr_decode_post_op_attr(p, fattr);
+        return decode_uint64(xdr, cookie);
 }
 
 /*
- * NFS encode functions
+ * cookieverf3
+ *
+ *      typedef opaque cookieverf3[NFS3_COOKIEVERFSIZE];
  */
+static __be32 *xdr_encode_cookieverf3(__be32 *p, const __be32 *verifier)
+{
+        memcpy(p, verifier, NFS3_COOKIEVERFSIZE);
+        return p + XDR_QUADLEN(NFS3_COOKIEVERFSIZE);
+}
+
+static int decode_cookieverf3(struct xdr_stream *xdr, __be32 *verifier)
+{
+        __be32 *p;
+
+        p = xdr_inline_decode(xdr, NFS3_COOKIEVERFSIZE);
+        if (unlikely(p == NULL))
+                goto out_overflow;
+        memcpy(verifier, p, NFS3_COOKIEVERFSIZE);
+        return 0;
+out_overflow:
+        print_overflow_msg(__func__, xdr);
+        return -EIO;
+}
 
 /*
- * Encode file handle argument
+ * createverf3
+ *
+ *      typedef opaque createverf3[NFS3_CREATEVERFSIZE];
  */
-static int
-nfs3_xdr_fhandle(struct rpc_rqst *req, __be32 *p, struct nfs_fh *fh)
+static void encode_createverf3(struct xdr_stream *xdr, const __be32 *verifier)
+{
+        __be32 *p;
+
+        p = xdr_reserve_space(xdr, NFS3_CREATEVERFSIZE);
+        memcpy(p, verifier, NFS3_CREATEVERFSIZE);
+}
+
+static int decode_writeverf3(struct xdr_stream *xdr, __be32 *verifier)
 {
-        p = xdr_encode_fhandle(p, fh);
-        req->rq_slen = xdr_adjust_iovec(req->rq_svec, p);
+        __be32 *p;
+
+        p = xdr_inline_decode(xdr, NFS3_WRITEVERFSIZE);
+        if (unlikely(p == NULL))
+                goto out_overflow;
+        memcpy(verifier, p, NFS3_WRITEVERFSIZE);
         return 0;
+out_overflow:
+        print_overflow_msg(__func__, xdr);
+        return -EIO;
 }
 
 /*
- * Encode SETATTR arguments
+ * size3
+ *
+ *      typedef uint64 size3;
  */
-static int
-nfs3_xdr_sattrargs(struct rpc_rqst *req, __be32 *p, struct nfs3_sattrargs *args)
-{
-        p = xdr_encode_fhandle(p, args->fh);
-        p = xdr_encode_sattr(p, args->sattr);
-        *p++ = htonl(args->guard);
-        if (args->guard)
-                p = xdr_encode_time3(p, &args->guardtime);
-        req->rq_slen = xdr_adjust_iovec(req->rq_svec, p);
-        return 0;
+static __be32 *xdr_decode_size3(__be32 *p, u64 *size)
+{
+        return xdr_decode_hyper(p, size);
 }
 
 /*
- * Encode directory ops argument
+ * nfsstat3
+ *
+ *      enum nfsstat3 {
+ *              NFS3_OK = 0,
+ *              ...
+ *      }
  */
-static int
-nfs3_xdr_diropargs(struct rpc_rqst *req, __be32 *p, struct nfs3_diropargs *args)
+#define NFS3_OK         NFS_OK
+
+static int decode_nfsstat3(struct xdr_stream *xdr, enum nfs_stat *status)
 {
-        p = xdr_encode_fhandle(p, args->fh);
-        p = xdr_encode_array(p, args->name, args->len);
-        req->rq_slen = xdr_adjust_iovec(req->rq_svec, p);
+        __be32 *p;
+
+        p = xdr_inline_decode(xdr, 4);
+        if (unlikely(p == NULL))
+                goto out_overflow;
+        *status = be32_to_cpup(p);
         return 0;
+out_overflow:
+        print_overflow_msg(__func__, xdr);
+        return -EIO;
 }
 
 /*
- * Encode REMOVE argument
+ * ftype3
+ *
+ *      enum ftype3 {
+ *              NF3REG  = 1,
+ *              NF3DIR  = 2,
+ *              NF3BLK  = 3,
+ *              NF3CHR  = 4,
+ *              NF3LNK  = 5,
+ *              NF3SOCK = 6,
+ *              NF3FIFO = 7
+ *      };
  */
-static int
-nfs3_xdr_removeargs(struct rpc_rqst *req, __be32 *p, const struct nfs_removeargs *args)
+static void encode_ftype3(struct xdr_stream *xdr, const u32 type)
 {
-        p = xdr_encode_fhandle(p, args->fh);
-        p = xdr_encode_array(p, args->name.name, args->name.len);
-        req->rq_slen = xdr_adjust_iovec(req->rq_svec, p);
-        return 0;
+        BUG_ON(type > NF3FIFO);
+        encode_uint32(xdr, type);
+}
+
+static __be32 *xdr_decode_ftype3(__be32 *p, umode_t *mode)
+{
+        u32 type;
+
+        type = be32_to_cpup(p++);
+        if (type > NF3FIFO)
+                type = NF3NON;
+        *mode = nfs_type2fmt[type];
+        return p;
 }
 
 /*
- * Encode access() argument
+ * specdata3
+ *
+ *     struct specdata3 {
+ *             uint32  specdata1;
+ *             uint32  specdata2;
+ *     };
  */
-static int
-nfs3_xdr_accessargs(struct rpc_rqst *req, __be32 *p, struct nfs3_accessargs *args)
+static void encode_specdata3(struct xdr_stream *xdr, const dev_t rdev)
 {
-        p = xdr_encode_fhandle(p, args->fh);
-        *p++ = htonl(args->access);
-        req->rq_slen = xdr_adjust_iovec(req->rq_svec, p);
-        return 0;
+        __be32 *p;
+
+        p = xdr_reserve_space(xdr, 8);
+        *p++ = cpu_to_be32(MAJOR(rdev));
+        *p = cpu_to_be32(MINOR(rdev));
+}
+
+static __be32 *xdr_decode_specdata3(__be32 *p, dev_t *rdev)
+{
+        unsigned int major, minor;
+
+        major = be32_to_cpup(p++);
+        minor = be32_to_cpup(p++);
+        *rdev = MKDEV(major, minor);
+        if (MAJOR(*rdev) != major || MINOR(*rdev) != minor)
+                *rdev = 0;
+        return p;
 }
 
 /*
- * Arguments to a READ call. Since we read data directly into the page
- * cache, we also set up the reply iovec here so that iov[1] points
- * exactly to the page we want to fetch.
+ * nfs_fh3
+ *
+ *      struct nfs_fh3 {
+ *              opaque       data<NFS3_FHSIZE>;
+ *      };
  */
-static int
-nfs3_xdr_readargs(struct rpc_rqst *req, __be32 *p, struct nfs_readargs *args)
+static void encode_nfs_fh3(struct xdr_stream *xdr, const struct nfs_fh *fh)
 {
-        struct rpc_auth *auth = req->rq_task->tk_msg.rpc_cred->cr_auth;
-        unsigned int replen;
-        u32 count = args->count;
+        __be32 *p;
 
-        p = xdr_encode_fhandle(p, args->fh);
-        p = xdr_encode_hyper(p, args->offset);
-        *p++ = htonl(count);
-        req->rq_slen = xdr_adjust_iovec(req->rq_svec, p);
+        BUG_ON(fh->size > NFS3_FHSIZE);
+        p = xdr_reserve_space(xdr, 4 + fh->size);
+        xdr_encode_opaque(p, fh->data, fh->size);
+}
 
-        /* Inline the page array */
-        replen = (RPC_REPHDRSIZE + auth->au_rslack + NFS3_readres_sz) << 2;
-        xdr_inline_pages(&req->rq_rcv_buf, replen,
-                         args->pages, args->pgbase, count);
-        req->rq_rcv_buf.flags |= XDRBUF_READ;
+static int decode_nfs_fh3(struct xdr_stream *xdr, struct nfs_fh *fh)
+{
+        u32 length;
+        __be32 *p;
+
+        p = xdr_inline_decode(xdr, 4);
+        if (unlikely(p == NULL))
+                goto out_overflow;
+        length = be32_to_cpup(p++);
+        if (unlikely(length > NFS3_FHSIZE))
+                goto out_toobig;
+        p = xdr_inline_decode(xdr, length);
+        if (unlikely(p == NULL))
+                goto out_overflow;
+        fh->size = length;
+        memcpy(fh->data, p, length);
         return 0;
+out_toobig:
+        dprintk("NFS: file handle size (%u) too big\n", length);
+        return -E2BIG;
+out_overflow:
+        print_overflow_msg(__func__, xdr);
+        return -EIO;
+}
+
+static void zero_nfs_fh3(struct nfs_fh *fh)
+{
+        memset(fh, 0, sizeof(*fh));
 }
 
 /*
- * Write arguments. Splice the buffer to be written into the iovec.
+ * nfstime3
+ *
+ *      struct nfstime3 {
+ *              uint32  seconds;
+ *              uint32  nseconds;
+ *      };
  */
-static int
-nfs3_xdr_writeargs(struct rpc_rqst *req, __be32 *p, struct nfs_writeargs *args)
+static __be32 *xdr_encode_nfstime3(__be32 *p, const struct timespec *timep)
 {
-        struct xdr_buf *sndbuf = &req->rq_snd_buf;
-        u32 count = args->count;
+        *p++ = cpu_to_be32(timep->tv_sec);
+        *p++ = cpu_to_be32(timep->tv_nsec);
+        return p;
+}
 
-        p = xdr_encode_fhandle(p, args->fh);
-        p = xdr_encode_hyper(p, args->offset);
-        *p++ = htonl(count);
-        *p++ = htonl(args->stable);
-        *p++ = htonl(count);
-        sndbuf->len = xdr_adjust_iovec(sndbuf->head, p);
-
-        /* Copy the page array */
-        xdr_encode_pages(sndbuf, args->pages, args->pgbase, count);
-        sndbuf->flags |= XDRBUF_WRITE;
-        return 0;
+static __be32 *xdr_decode_nfstime3(__be32 *p, struct timespec *timep)
+{
+        timep->tv_sec = be32_to_cpup(p++);
+        timep->tv_nsec = be32_to_cpup(p++);
+        return p;
 }
 
 /*
- * Encode CREATE arguments
+ * sattr3
+ *
+ *      enum time_how {
+ *              DONT_CHANGE             = 0,
+ *              SET_TO_SERVER_TIME      = 1,
+ *              SET_TO_CLIENT_TIME      = 2
+ *      };
+ *
+ *      union set_mode3 switch (bool set_it) {
+ *      case TRUE:
+ *              mode3   mode;
+ *      default:
+ *              void;
+ *      };
+ *
+ *      union set_uid3 switch (bool set_it) {
+ *      case TRUE:
+ *              uid3    uid;
+ *      default:
+ *              void;
+ *      };
+ *
+ *      union set_gid3 switch (bool set_it) {
+ *      case TRUE:
+ *              gid3    gid;
+ *      default:
+ *              void;
+ *      };
+ *
+ *      union set_size3 switch (bool set_it) {
+ *      case TRUE:
+ *              size3   size;
+ *      default:
+ *              void;
+ *      };
+ *
+ *      union set_atime switch (time_how set_it) {
+ *      case SET_TO_CLIENT_TIME:
+ *              nfstime3        atime;
+ *      default:
+ *              void;
+ *      };
+ *
+ *      union set_mtime switch (time_how set_it) {
+ *      case SET_TO_CLIENT_TIME:
+ *              nfstime3  mtime;
+ *      default:
+ *              void;
+ *      };
+ *
+ *      struct sattr3 {
+ *              set_mode3       mode;
+ *              set_uid3        uid;
+ *              set_gid3        gid;
+ *              set_size3       size;
+ *              set_atime       atime;
+ *              set_mtime       mtime;
+ *      };
  */
-static int
-nfs3_xdr_createargs(struct rpc_rqst *req, __be32 *p, struct nfs3_createargs *args)
+static void encode_sattr3(struct xdr_stream *xdr, const struct iattr *attr)
 {
-        p = xdr_encode_fhandle(p, args->fh);
-        p = xdr_encode_array(p, args->name, args->len);
+        u32 nbytes;
+        __be32 *p;
+
+        /*
+         * In order to make only a single xdr_reserve_space() call,
+         * pre-compute the total number of bytes to be reserved.
+         * Six boolean values, one for each set_foo field, are always
+         * present in the encoded result, so start there.
+         */
+        nbytes = 6 * 4;
+        if (attr->ia_valid & ATTR_MODE)
+                nbytes += 4;
+        if (attr->ia_valid & ATTR_UID)
+                nbytes += 4;
+        if (attr->ia_valid & ATTR_GID)
+                nbytes += 4;
+        if (attr->ia_valid & ATTR_SIZE)
+                nbytes += 8;
+        if (attr->ia_valid & ATTR_ATIME_SET)
+                nbytes += 8;
+        if (attr->ia_valid & ATTR_MTIME_SET)
+                nbytes += 8;
+        p = xdr_reserve_space(xdr, nbytes);
 
-        *p++ = htonl(args->createmode);
-        if (args->createmode == NFS3_CREATE_EXCLUSIVE) {
-                *p++ = args->verifier[0];
-                *p++ = args->verifier[1];
+        if (attr->ia_valid & ATTR_MODE) {
+                *p++ = xdr_one;
+                *p++ = cpu_to_be32(attr->ia_mode & S_IALLUGO);
         } else
-                p = xdr_encode_sattr(p, args->sattr);
+                *p++ = xdr_zero;
 
-        req->rq_slen = xdr_adjust_iovec(req->rq_svec, p);
-        return 0;
+        if (attr->ia_valid & ATTR_UID) {
+                *p++ = xdr_one;
+                *p++ = cpu_to_be32(attr->ia_uid);
+        } else
+                *p++ = xdr_zero;
+
+        if (attr->ia_valid & ATTR_GID) {
+                *p++ = xdr_one;
+                *p++ = cpu_to_be32(attr->ia_gid);
+        } else
+                *p++ = xdr_zero;
+
+        if (attr->ia_valid & ATTR_SIZE) {
+                *p++ = xdr_one;
+                p = xdr_encode_hyper(p, (u64)attr->ia_size);
+        } else
+                *p++ = xdr_zero;
+
+        if (attr->ia_valid & ATTR_ATIME_SET) {
+                *p++ = xdr_two;
+                p = xdr_encode_nfstime3(p, &attr->ia_atime);
+        } else if (attr->ia_valid & ATTR_ATIME) {
+                *p++ = xdr_one;
+        } else
+                *p++ = xdr_zero;
+
+        if (attr->ia_valid & ATTR_MTIME_SET) {
+                *p++ = xdr_two;
+                xdr_encode_nfstime3(p, &attr->ia_mtime);
+        } else if (attr->ia_valid & ATTR_MTIME) {
+                *p = xdr_one;
+        } else
+                *p = xdr_zero;
 }
 
 /*
- * Encode MKDIR arguments
+ * fattr3
+ *
+ *      struct fattr3 {
+ *              ftype3          type;
+ *              mode3           mode;
+ *              uint32          nlink;
+ *              uid3            uid;
+ *              gid3            gid;
+ *              size3           size;
+ *              size3           used;
+ *              specdata3       rdev;
+ *              uint64          fsid;
+ *              fileid3         fileid;
+ *              nfstime3        atime;
+ *              nfstime3        mtime;
+ *              nfstime3        ctime;
+ *      };
  */
-static int
-nfs3_xdr_mkdirargs(struct rpc_rqst *req, __be32 *p, struct nfs3_mkdirargs *args)
+static int decode_fattr3(struct xdr_stream *xdr, struct nfs_fattr *fattr)
 {
-        p = xdr_encode_fhandle(p, args->fh);
-        p = xdr_encode_array(p, args->name, args->len);
-        p = xdr_encode_sattr(p, args->sattr);
-        req->rq_slen = xdr_adjust_iovec(req->rq_svec, p);
+        umode_t fmode;
+        __be32 *p;
+
+        p = xdr_inline_decode(xdr, NFS3_fattr_sz << 2);
+        if (unlikely(p == NULL))
+                goto out_overflow;
+
+        p = xdr_decode_ftype3(p, &fmode);
+
+        fattr->mode = (be32_to_cpup(p++) & ~S_IFMT) | fmode;
+        fattr->nlink = be32_to_cpup(p++);
+        fattr->uid = be32_to_cpup(p++);
+        fattr->gid = be32_to_cpup(p++);
+
+        p = xdr_decode_size3(p, &fattr->size);
+        p = xdr_decode_size3(p, &fattr->du.nfs3.used);
+        p = xdr_decode_specdata3(p, &fattr->rdev);
+
+        p = xdr_decode_hyper(p, &fattr->fsid.major);
+        fattr->fsid.minor = 0;
+
+        p = xdr_decode_fileid3(p, &fattr->fileid);
+        p = xdr_decode_nfstime3(p, &fattr->atime);
+        p = xdr_decode_nfstime3(p, &fattr->mtime);
+        xdr_decode_nfstime3(p, &fattr->ctime);
+
+        fattr->valid |= NFS_ATTR_FATTR_V3;
         return 0;
+out_overflow:
+        print_overflow_msg(__func__, xdr);
+        return -EIO;
 }
 
 /*
- * Encode SYMLINK arguments
+ * post_op_attr
+ *
+ *      union post_op_attr switch (bool attributes_follow) {
+ *      case TRUE:
+ *              fattr3  attributes;
+ *      case FALSE:
+ *              void;
+ *      };
  */
-static int
-nfs3_xdr_symlinkargs(struct rpc_rqst *req, __be32 *p, struct nfs3_symlinkargs *args)
+static int decode_post_op_attr(struct xdr_stream *xdr, struct nfs_fattr *fattr)
 {
-        p = xdr_encode_fhandle(p, args->fromfh);
-        p = xdr_encode_array(p, args->fromname, args->fromlen);
-        p = xdr_encode_sattr(p, args->sattr);
-        *p++ = htonl(args->pathlen);
-        req->rq_slen = xdr_adjust_iovec(req->rq_svec, p);
+        __be32 *p;
 
-        /* Copy the page */
-        xdr_encode_pages(&req->rq_snd_buf, args->pages, 0, args->pathlen);
+        p = xdr_inline_decode(xdr, 4);
+        if (unlikely(p == NULL))
+                goto out_overflow;
+        if (*p != xdr_zero)
+                return decode_fattr3(xdr, fattr);
         return 0;
+out_overflow:
+        print_overflow_msg(__func__, xdr);
+        return -EIO;
 }
 
 /*
- * Encode MKNOD arguments
+ * wcc_attr
+ *      struct wcc_attr {
+ *              size3           size;
+ *              nfstime3        mtime;
+ *              nfstime3        ctime;
+ *      };
  */
-static int
-nfs3_xdr_mknodargs(struct rpc_rqst *req, __be32 *p, struct nfs3_mknodargs *args)
-{
-        p = xdr_encode_fhandle(p, args->fh);
-        p = xdr_encode_array(p, args->name, args->len);
-        *p++ = htonl(args->type);
-        p = xdr_encode_sattr(p, args->sattr);
-        if (args->type == NF3CHR || args->type == NF3BLK) {
-                *p++ = htonl(MAJOR(args->rdev));
-                *p++ = htonl(MINOR(args->rdev));
-        }
+static int decode_wcc_attr(struct xdr_stream *xdr, struct nfs_fattr *fattr)
+{
+        __be32 *p;
+
+        p = xdr_inline_decode(xdr, NFS3_wcc_attr_sz << 2);
+        if (unlikely(p == NULL))
+                goto out_overflow;
+
+        fattr->valid |= NFS_ATTR_FATTR_PRESIZE
+                | NFS_ATTR_FATTR_PREMTIME
+                | NFS_ATTR_FATTR_PRECTIME;
+
+        p = xdr_decode_size3(p, &fattr->pre_size);
+        p = xdr_decode_nfstime3(p, &fattr->pre_mtime);
+        xdr_decode_nfstime3(p, &fattr->pre_ctime);
 
-        req->rq_slen = xdr_adjust_iovec(req->rq_svec, p);
         return 0;
+out_overflow:
+        print_overflow_msg(__func__, xdr);
+        return -EIO;
 }
 
 /*
- * Encode RENAME arguments
+ * pre_op_attr
+ *      union pre_op_attr switch (bool attributes_follow) {
+ *      case TRUE:
+ *              wcc_attr        attributes;
+ *      case FALSE:
+ *              void;
+ *      };
+ *
+ * wcc_data
+ *
+ *      struct wcc_data {
+ *              pre_op_attr     before;
+ *              post_op_attr    after;
+ *      };
  */
-static int
-nfs3_xdr_renameargs(struct rpc_rqst *req, __be32 *p, struct nfs3_renameargs *args)
-{
-        p = xdr_encode_fhandle(p, args->fromfh);
-        p = xdr_encode_array(p, args->fromname, args->fromlen);
-        p = xdr_encode_fhandle(p, args->tofh);
-        p = xdr_encode_array(p, args->toname, args->tolen);
-        req->rq_slen = xdr_adjust_iovec(req->rq_svec, p);
+static int decode_pre_op_attr(struct xdr_stream *xdr, struct nfs_fattr *fattr)
+{
+        __be32 *p;
+
+        p = xdr_inline_decode(xdr, 4);
+        if (unlikely(p == NULL))
+                goto out_overflow;
+        if (*p != xdr_zero)
+                return decode_wcc_attr(xdr, fattr);
         return 0;
+out_overflow:
+        print_overflow_msg(__func__, xdr);
+        return -EIO;
 }
 
-/*
- * Encode LINK arguments
- */
-static int
-nfs3_xdr_linkargs(struct rpc_rqst *req, __be32 *p, struct nfs3_linkargs *args)
+static int decode_wcc_data(struct xdr_stream *xdr, struct nfs_fattr *fattr)
 {
-        p = xdr_encode_fhandle(p, args->fromfh);
-        p = xdr_encode_fhandle(p, args->tofh);
-        p = xdr_encode_array(p, args->toname, args->tolen);
-        req->rq_slen = xdr_adjust_iovec(req->rq_svec, p);
-        return 0;
+        int error;
+
+        error = decode_pre_op_attr(xdr, fattr);
+        if (unlikely(error))
+                goto out;
+        error = decode_post_op_attr(xdr, fattr);
+out:
+        return error;
 }
 
 /*
- * Encode arguments to readdir call
+ * post_op_fh3
+ *
+ *      union post_op_fh3 switch (bool handle_follows) {
+ *      case TRUE:
+ *              nfs_fh3  handle;
+ *      case FALSE:
+ *              void;
+ *      };
  */
-static int
-nfs3_xdr_readdirargs(struct rpc_rqst *req, __be32 *p, struct nfs3_readdirargs *args)
+static int decode_post_op_fh3(struct xdr_stream *xdr, struct nfs_fh *fh)
 {
-        struct rpc_auth *auth = req->rq_task->tk_msg.rpc_cred->cr_auth;
-        unsigned int replen;
-        u32 count = args->count;
-
-        p = xdr_encode_fhandle(p, args->fh);
-        p = xdr_encode_hyper(p, args->cookie);
-        *p++ = args->verf[0];
-        *p++ = args->verf[1];
-        if (args->plus) {
-                /* readdirplus: need dircount + buffer size.
-                 * We just make sure we make dircount big enough */
-                *p++ = htonl(count >> 3);
-        }
-        *p++ = htonl(count);
-        req->rq_slen = xdr_adjust_iovec(req->rq_svec, p);
-
-        /* Inline the page array */
-        replen = (RPC_REPHDRSIZE + auth->au_rslack + NFS3_readdirres_sz) << 2;
-        xdr_inline_pages(&req->rq_rcv_buf, replen, args->pages, 0, count);
+        __be32 *p = xdr_inline_decode(xdr, 4);
+        if (unlikely(p == NULL))
+                goto out_overflow;
+        if (*p != xdr_zero)
+                return decode_nfs_fh3(xdr, fh);
+        zero_nfs_fh3(fh);
         return 0;
+out_overflow:
+        print_overflow_msg(__func__, xdr);
+        return -EIO;
 }
 
 /*
- * Decode the result of a readdir call.
- * We just check for syntactical correctness.
+ * diropargs3
+ *
+ *      struct diropargs3 {
+ *              nfs_fh3         dir;
+ *              filename3       name;
+ *      };
  */
-static int
-nfs3_xdr_readdirres(struct rpc_rqst *req, __be32 *p, struct nfs3_readdirres *res)
+static void encode_diropargs3(struct xdr_stream *xdr, const struct nfs_fh *fh,
+                              const char *name, u32 length)
 {
-        struct xdr_buf *rcvbuf = &req->rq_rcv_buf;
-        struct kvec *iov = rcvbuf->head;
-        struct page **page;
-        size_t hdrlen;
-        u32 len, recvd, pglen;
-        int status, nr = 0;
-        __be32 *entry, *end, *kaddr;
-
-        status = ntohl(*p++);
-        /* Decode post_op_attrs */
-        p = xdr_decode_post_op_attr(p, res->dir_attr);
-        if (status)
-                return nfs_stat_to_errno(status);
-        /* Decode verifier cookie */
-        if (res->verf) {
-                res->verf[0] = *p++;
-                res->verf[1] = *p++;
-        } else {
-                p += 2;
-        }
-
-        hdrlen = (u8 *) p - (u8 *) iov->iov_base;
-        if (iov->iov_len < hdrlen) {
-                dprintk("NFS: READDIR reply header overflowed:"
-                                "length %Zu > %Zu\n", hdrlen, iov->iov_len);
-                return -errno_NFSERR_IO;
-        } else if (iov->iov_len != hdrlen) {
-                dprintk("NFS: READDIR header is short. iovec will be shifted.\n");
-                xdr_shift_buf(rcvbuf, iov->iov_len - hdrlen);
-        }
+        encode_nfs_fh3(xdr, fh);
+        encode_filename3(xdr, name, length);
+}
 
-        pglen = rcvbuf->page_len;
-        recvd = rcvbuf->len - hdrlen;
-        if (pglen > recvd)
-                pglen = recvd;
-        page = rcvbuf->pages;
-        kaddr = p = kmap_atomic(*page, KM_USER0);
-        end = (__be32 *)((char *)p + pglen);
-        entry = p;
-
-        /* Make sure the packet actually has a value_follows and EOF entry */
-        if ((entry + 1) > end)
-                goto short_pkt;
-
-        for (; *p++; nr++) {
-                if (p + 3 > end)
-                        goto short_pkt;
-                p += 2;                         /* inode # */
-                len = ntohl(*p++);              /* string length */
-                p += XDR_QUADLEN(len) + 2;      /* name + cookie */
-                if (len > NFS3_MAXNAMLEN) {
-                        dprintk("NFS: giant filename in readdir (len 0x%x)!\n",
-                                                len);
-                        goto err_unmap;
-                }
-
-                if (res->plus) {
-                        /* post_op_attr */
-                        if (p + 2 > end)
-                                goto short_pkt;
-                        if (*p++) {
-                                p += 21;
-                                if (p + 1 > end)
-                                        goto short_pkt;
-                        }
-                        /* post_op_fh3 */
-                        if (*p++) {
-                                if (p + 1 > end)
-                                        goto short_pkt;
-                                len = ntohl(*p++);
-                                if (len > NFS3_FHSIZE) {
-                                        dprintk("NFS: giant filehandle in "
-                                                "readdir (len 0x%x)!\n", len);
-                                        goto err_unmap;
-                                }
-                                p += XDR_QUADLEN(len);
-                        }
-                }
 
-                if (p + 2 > end)
-                        goto short_pkt;
-                entry = p;
-        }
+/*
+ * NFSv3 XDR encode functions
+ *
+ * NFSv3 argument types are defined in section 3.3 of RFC 1813:
+ * "NFS Version 3 Protocol Specification".
+ */
 
-        /*
-         * Apparently some server sends responses that are a valid size, but
-         * contain no entries, and have value_follows==0 and EOF==0. For
-         * those, just set the EOF marker.
-         */
-        if (!nr && entry[1] == 0) {
-                dprintk("NFS: readdir reply truncated!\n");
-                entry[1] = 1;
-        }
- out:
-        kunmap_atomic(kaddr, KM_USER0);
-        return nr;
- short_pkt:
-        /*
-         * When we get a short packet there are 2 possibilities. We can
-         * return an error, or fix up the response to look like a valid
-         * response and return what we have so far. If there are no
-         * entries and the packet was short, then return -EIO. If there
-         * are valid entries in the response, return them and pretend that
-         * the call was successful, but incomplete. The caller can retry the
-         * readdir starting at the last cookie.
-         */
-        entry[0] = entry[1] = 0;
-        if (!nr)
-                nr = -errno_NFSERR_IO;
-        goto out;
-err_unmap:
-        nr = -errno_NFSERR_IO;
-        goto out;
+/*
+ * 3.3.1  GETATTR3args
+ *
+ *      struct GETATTR3args {
+ *              nfs_fh3  object;
+ *      };
+ */
+static void nfs3_xdr_enc_getattr3args(struct rpc_rqst *req,
+                                      struct xdr_stream *xdr,
+                                      const struct nfs_fh *fh)
+{
+        encode_nfs_fh3(xdr, fh);
 }
 
-__be32 *
-nfs3_decode_dirent(__be32 *p, struct nfs_entry *entry, int plus)
+/*
+ * 3.3.2  SETATTR3args
+ *
+ *      union sattrguard3 switch (bool check) {
+ *      case TRUE:
+ *              nfstime3  obj_ctime;
+ *      case FALSE:
+ *              void;
+ *      };
+ *
+ *      struct SETATTR3args {
+ *              nfs_fh3         object;
+ *              sattr3          new_attributes;
+ *              sattrguard3     guard;
+ *      };
+ */
+static void encode_sattrguard3(struct xdr_stream *xdr,
+                               const struct nfs3_sattrargs *args)
 {
-        struct nfs_entry old = *entry;
-
-        if (!*p++) {
-                if (!*p)
-                        return ERR_PTR(-EAGAIN);
-                entry->eof = 1;
-                return ERR_PTR(-EBADCOOKIE);
-        }
-
-        p = xdr_decode_hyper(p, &entry->ino);
-        entry->len  = ntohl(*p++);
-        entry->name = (const char *) p;
-        p += XDR_QUADLEN(entry->len);
-        entry->prev_cookie = entry->cookie;
-        p = xdr_decode_hyper(p, &entry->cookie);
+        __be32 *p;
 
-        if (plus) {
-                entry->fattr->valid = 0;
-                p = xdr_decode_post_op_attr(p, entry->fattr);
-                /* In fact, a post_op_fh3: */
-                if (*p++) {
-                        p = xdr_decode_fhandle(p, entry->fh);
-                        /* Ugh -- server reply was truncated */
-                        if (p == NULL) {
-                                dprintk("NFS: FH truncated\n");
-                                *entry = old;
-                                return ERR_PTR(-EAGAIN);
-                        }
-                } else
-                        memset((u8*)(entry->fh), 0, sizeof(*entry->fh));
+        if (args->guard) {
+                p = xdr_reserve_space(xdr, 4 + 8);
+                *p++ = xdr_one;
+                xdr_encode_nfstime3(p, &args->guardtime);
+        } else {
+                p = xdr_reserve_space(xdr, 4);
+                *p = xdr_zero;
         }
+}
 
-        entry->eof = !p[0] && p[1];
-        return p;
+static void nfs3_xdr_enc_setattr3args(struct rpc_rqst *req,
+                                      struct xdr_stream *xdr,
+                                      const struct nfs3_sattrargs *args)
+{
+        encode_nfs_fh3(xdr, args->fh);
+        encode_sattr3(xdr, args->sattr);
+        encode_sattrguard3(xdr, args);
 }
 
 /*
- * Encode COMMIT arguments
+ * 3.3.3  LOOKUP3args
+ *
+ *      struct LOOKUP3args {
+ *              diropargs3  what;
+ *      };
  */
-static int
-nfs3_xdr_commitargs(struct rpc_rqst *req, __be32 *p, struct nfs_writeargs *args)
+static void nfs3_xdr_enc_lookup3args(struct rpc_rqst *req,
+                                     struct xdr_stream *xdr,
+                                     const struct nfs3_diropargs *args)
 {
-        p = xdr_encode_fhandle(p, args->fh);
-        p = xdr_encode_hyper(p, args->offset);
-        *p++ = htonl(args->count);
-        req->rq_slen = xdr_adjust_iovec(req->rq_svec, p);
-        return 0;
+        encode_diropargs3(xdr, args->fh, args->name, args->len);
 }
 
-#ifdef CONFIG_NFS_V3_ACL
 /*
- * Encode GETACL arguments
+ * 3.3.4  ACCESS3args
+ *
+ *      struct ACCESS3args {
+ *              nfs_fh3         object;
+ *              uint32          access;
+ *      };
  */
-static int
-nfs3_xdr_getaclargs(struct rpc_rqst *req, __be32 *p,
-                    struct nfs3_getaclargs *args)
+static void encode_access3args(struct xdr_stream *xdr,
+                               const struct nfs3_accessargs *args)
 {
-        struct rpc_auth *auth = req->rq_task->tk_msg.rpc_cred->cr_auth;
-        unsigned int replen;
+        encode_nfs_fh3(xdr, args->fh);
+        encode_uint32(xdr, args->access);
+}
 
-        p = xdr_encode_fhandle(p, args->fh);
-        *p++ = htonl(args->mask);
-        req->rq_slen = xdr_adjust_iovec(req->rq_svec, p);
+static void nfs3_xdr_enc_access3args(struct rpc_rqst *req,
+                                     struct xdr_stream *xdr,
+                                     const struct nfs3_accessargs *args)
+{
+        encode_access3args(xdr, args);
+}
 
-        if (args->mask & (NFS_ACL | NFS_DFACL)) {
-                /* Inline the page array */
-                replen = (RPC_REPHDRSIZE + auth->au_rslack +
-                          ACL3_getaclres_sz) << 2;
-                xdr_inline_pages(&req->rq_rcv_buf, replen, args->pages, 0,
-                                 NFSACL_MAXPAGES << PAGE_SHIFT);
-        }
-        return 0;
+/*
+ * 3.3.5  READLINK3args
+ *
+ *      struct READLINK3args {
+ *              nfs_fh3 symlink;
+ *      };
+ */
+static void nfs3_xdr_enc_readlink3args(struct rpc_rqst *req,
+                                       struct xdr_stream *xdr,
+                                       const struct nfs3_readlinkargs *args)
+{
+        encode_nfs_fh3(xdr, args->fh);
+        prepare_reply_buffer(req, args->pages, args->pgbase,
+                                        args->pglen, NFS3_readlinkres_sz);
 }
 
 /*
- * Encode SETACL arguments
+ * 3.3.6  READ3args
+ *
+ *      struct READ3args {
+ *              nfs_fh3         file;
+ *              offset3         offset;
+ *              count3          count;
+ *      };
  */
-static int
-nfs3_xdr_setaclargs(struct rpc_rqst *req, __be32 *p,
-                   struct nfs3_setaclargs *args)
+static void encode_read3args(struct xdr_stream *xdr,
+                             const struct nfs_readargs *args)
 {
-        struct xdr_buf *buf = &req->rq_snd_buf;
-        unsigned int base;
-        int err;
+        __be32 *p;
 
-        p = xdr_encode_fhandle(p, NFS_FH(args->inode));
-        *p++ = htonl(args->mask);
-        req->rq_slen = xdr_adjust_iovec(req->rq_svec, p);
-        base = req->rq_slen;
+        encode_nfs_fh3(xdr, args->fh);
 
-        if (args->npages != 0)
-                xdr_encode_pages(buf, args->pages, 0, args->len);
-        else
-                req->rq_slen = xdr_adjust_iovec(req->rq_svec,
-                                p + XDR_QUADLEN(args->len));
+        p = xdr_reserve_space(xdr, 8 + 4);
+        p = xdr_encode_hyper(p, args->offset);
+        *p = cpu_to_be32(args->count);
+}
 
-        err = nfsacl_encode(buf, base, args->inode,
-                            (args->mask & NFS_ACL) ?
-                            args->acl_access : NULL, 1, 0);
-        if (err > 0)
-                err = nfsacl_encode(buf, base + err, args->inode,
-                                    (args->mask & NFS_DFACL) ?
-                                    args->acl_default : NULL, 1,
-                                    NFS_ACL_DEFAULT);
-        return (err > 0) ? 0 : err;
+static void nfs3_xdr_enc_read3args(struct rpc_rqst *req,
+                                   struct xdr_stream *xdr,
+                                   const struct nfs_readargs *args)
+{
+        encode_read3args(xdr, args);
+        prepare_reply_buffer(req, args->pages, args->pgbase,
+                                        args->count, NFS3_readres_sz);
+        req->rq_rcv_buf.flags |= XDRBUF_READ;
 }
-#endif  /* CONFIG_NFS_V3_ACL */
 
 /*
- * NFS XDR decode functions
+ * 3.3.7  WRITE3args
+ *
+ *      enum stable_how {
+ *              UNSTABLE  = 0,
+ *              DATA_SYNC = 1,
+ *              FILE_SYNC = 2
+ *      };
+ *
+ *      struct WRITE3args {
+ *              nfs_fh3         file;
+ *              offset3         offset;
+ *              count3          count;
+ *              stable_how      stable;
+ *              opaque          data<>;
+ *      };
  */
+static void encode_write3args(struct xdr_stream *xdr,
+                              const struct nfs_writeargs *args)
+{
+        __be32 *p;
+
+        encode_nfs_fh3(xdr, args->fh);
+
+        p = xdr_reserve_space(xdr, 8 + 4 + 4 + 4);
+        p = xdr_encode_hyper(p, args->offset);
+        *p++ = cpu_to_be32(args->count);
+        *p++ = cpu_to_be32(args->stable);
+        *p = cpu_to_be32(args->count);
+        xdr_write_pages(xdr, args->pages, args->pgbase, args->count);
+}
+
+static void nfs3_xdr_enc_write3args(struct rpc_rqst *req,
+                                    struct xdr_stream *xdr,
+                                    const struct nfs_writeargs *args)
+{
+        encode_write3args(xdr, args);
+        xdr->buf->flags |= XDRBUF_WRITE;
+}
 
 /*
- * Decode attrstat reply.
+ * 3.3.8  CREATE3args
+ *
+ *      enum createmode3 {
+ *              UNCHECKED = 0,
+ *              GUARDED   = 1,
+ *              EXCLUSIVE = 2
+ *      };
+ *
+ *      union createhow3 switch (createmode3 mode) {
+ *      case UNCHECKED:
+ *      case GUARDED:
+ *              sattr3       obj_attributes;
+ *      case EXCLUSIVE:
+ *              createverf3  verf;
+ *      };
+ *
+ *      struct CREATE3args {
+ *              diropargs3      where;
+ *              createhow3      how;
+ *      };
  */
-static int
-nfs3_xdr_attrstat(struct rpc_rqst *req, __be32 *p, struct nfs_fattr *fattr)
+static void encode_createhow3(struct xdr_stream *xdr,
+                              const struct nfs3_createargs *args)
 {
-        int     status;
+        encode_uint32(xdr, args->createmode);
+        switch (args->createmode) {
+        case NFS3_CREATE_UNCHECKED:
+        case NFS3_CREATE_GUARDED:
+                encode_sattr3(xdr, args->sattr);
+                break;
+        case NFS3_CREATE_EXCLUSIVE:
+                encode_createverf3(xdr, args->verifier);
+                break;
+        default:
+                BUG();
+        }
+}
 
-        if ((status = ntohl(*p++)))
-                return nfs_stat_to_errno(status);
-        xdr_decode_fattr(p, fattr);
-        return 0;
+static void nfs3_xdr_enc_create3args(struct rpc_rqst *req,
+                                     struct xdr_stream *xdr,
+                                     const struct nfs3_createargs *args)
+{
+        encode_diropargs3(xdr, args->fh, args->name, args->len);
+        encode_createhow3(xdr, args);
 }
 
 /*
- * Decode status+wcc_data reply
- * SATTR, REMOVE, RMDIR
+ * 3.3.9  MKDIR3args
+ *
+ *      struct MKDIR3args {
+ *              diropargs3      where;
+ *              sattr3          attributes;
+ *      };
  */
-static int
-nfs3_xdr_wccstat(struct rpc_rqst *req, __be32 *p, struct nfs_fattr *fattr)
+static void nfs3_xdr_enc_mkdir3args(struct rpc_rqst *req,
+                                    struct xdr_stream *xdr,
+                                    const struct nfs3_mkdirargs *args)
 {
-        int     status;
+        encode_diropargs3(xdr, args->fh, args->name, args->len);
+        encode_sattr3(xdr, args->sattr);
+}
 
-        if ((status = ntohl(*p++)))
-                status = nfs_stat_to_errno(status);
-        xdr_decode_wcc_data(p, fattr);
-        return status;
+/*
+ * 3.3.10  SYMLINK3args
+ *
+ *      struct symlinkdata3 {
+ *              sattr3          symlink_attributes;
+ *              nfspath3        symlink_data;
+ *      };
+ *
+ *      struct SYMLINK3args {
+ *              diropargs3      where;
+ *              symlinkdata3    symlink;
+ *      };
+ */
+static void encode_symlinkdata3(struct xdr_stream *xdr,
+                                const struct nfs3_symlinkargs *args)
+{
+        encode_sattr3(xdr, args->sattr);
+        encode_nfspath3(xdr, args->pages, args->pathlen);
 }
 
-static int
-nfs3_xdr_removeres(struct rpc_rqst *req, __be32 *p, struct nfs_removeres *res)
+static void nfs3_xdr_enc_symlink3args(struct rpc_rqst *req,
+                                      struct xdr_stream *xdr,
+                                      const struct nfs3_symlinkargs *args)
 {
-        return nfs3_xdr_wccstat(req, p, &res->dir_attr);
+        encode_diropargs3(xdr, args->fromfh, args->fromname, args->fromlen);
+        encode_symlinkdata3(xdr, args);
 }
 
 /*
- * Decode LOOKUP reply
+ * 3.3.11  MKNOD3args
+ *
+ *      struct devicedata3 {
+ *              sattr3          dev_attributes;
+ *              specdata3       spec;
+ *      };
+ *
+ *      union mknoddata3 switch (ftype3 type) {
+ *      case NF3CHR:
+ *      case NF3BLK:
+ *              devicedata3     device;
+ *      case NF3SOCK:
+ *      case NF3FIFO:
+ *              sattr3          pipe_attributes;
+ *      default:
+ *              void;
+ *      };
+ *
+ *      struct MKNOD3args {
+ *              diropargs3      where;
+ *              mknoddata3      what;
+ *      };
  */
-static int
-nfs3_xdr_lookupres(struct rpc_rqst *req, __be32 *p, struct nfs3_diropres *res)
+static void encode_devicedata3(struct xdr_stream *xdr,
+                               const struct nfs3_mknodargs *args)
 {
-        int     status;
+        encode_sattr3(xdr, args->sattr);
+        encode_specdata3(xdr, args->rdev);
+}
 
-        if ((status = ntohl(*p++))) {
-                status = nfs_stat_to_errno(status);
-        } else {
-                if (!(p = xdr_decode_fhandle(p, res->fh)))
-                        return -errno_NFSERR_IO;
-                p = xdr_decode_post_op_attr(p, res->fattr);
+static void encode_mknoddata3(struct xdr_stream *xdr,
+                              const struct nfs3_mknodargs *args)
+{
+        encode_ftype3(xdr, args->type);
+        switch (args->type) {
+        case NF3CHR:
+        case NF3BLK:
+                encode_devicedata3(xdr, args);
+                break;
+        case NF3SOCK:
+        case NF3FIFO:
+                encode_sattr3(xdr, args->sattr);
+                break;
+        case NF3REG:
+        case NF3DIR:
+                break;
+        default:
+                BUG();
         }
-        xdr_decode_post_op_attr(p, res->dir_attr);
-        return status;
+}
+
+static void nfs3_xdr_enc_mknod3args(struct rpc_rqst *req,
+                                    struct xdr_stream *xdr,
+                                    const struct nfs3_mknodargs *args)
+{
+        encode_diropargs3(xdr, args->fh, args->name, args->len);
+        encode_mknoddata3(xdr, args);
 }
 
 /*
- * Decode ACCESS reply
+ * 3.3.12  REMOVE3args
+ *
+ *      struct REMOVE3args {
+ *              diropargs3  object;
+ *      };
  */
-static int
-nfs3_xdr_accessres(struct rpc_rqst *req, __be32 *p, struct nfs3_accessres *res)
+static void nfs3_xdr_enc_remove3args(struct rpc_rqst *req,
+                                     struct xdr_stream *xdr,
+                                     const struct nfs_removeargs *args)
 {
-        int     status = ntohl(*p++);
+        encode_diropargs3(xdr, args->fh, args->name.name, args->name.len);
+}
 
-        p = xdr_decode_post_op_attr(p, res->fattr);
-        if (status)
-                return nfs_stat_to_errno(status);
-        res->access = ntohl(*p++);
-        return 0;
+/*
+ * 3.3.14  RENAME3args
+ *
+ *      struct RENAME3args {
+ *              diropargs3      from;
+ *              diropargs3      to;
+ *      };
+ */
+static void nfs3_xdr_enc_rename3args(struct rpc_rqst *req,
+                                     struct xdr_stream *xdr,
+                                     const struct nfs_renameargs *args)
+{
+        const struct qstr *old = args->old_name;
+        const struct qstr *new = args->new_name;
+
+        encode_diropargs3(xdr, args->old_dir, old->name, old->len);
+        encode_diropargs3(xdr, args->new_dir, new->name, new->len);
 }
 
-static int
-nfs3_xdr_readlinkargs(struct rpc_rqst *req, __be32 *p, struct nfs3_readlinkargs *args)
+/*
+ * 3.3.15  LINK3args
+ *
+ *      struct LINK3args {
+ *              nfs_fh3         file;
+ *              diropargs3      link;
+ *      };
+ */
+static void nfs3_xdr_enc_link3args(struct rpc_rqst *req,
+                                   struct xdr_stream *xdr,
+                                   const struct nfs3_linkargs *args)
 {
-        struct rpc_auth *auth = req->rq_task->tk_msg.rpc_cred->cr_auth;
-        unsigned int replen;
+        encode_nfs_fh3(xdr, args->fromfh);
+        encode_diropargs3(xdr, args->tofh, args->toname, args->tolen);
+}
 
-        p = xdr_encode_fhandle(p, args->fh);
-        req->rq_slen = xdr_adjust_iovec(req->rq_svec, p);
+/*
+ * 3.3.16  READDIR3args
+ *
+ *      struct READDIR3args {
+ *              nfs_fh3         dir;
+ *              cookie3         cookie;
+ *              cookieverf3     cookieverf;
+ *              count3          count;
+ *      };
+ */
+static void encode_readdir3args(struct xdr_stream *xdr,
+                                const struct nfs3_readdirargs *args)
+{
+        __be32 *p;
 
-        /* Inline the page array */
-        replen = (RPC_REPHDRSIZE + auth->au_rslack + NFS3_readlinkres_sz) << 2;
-        xdr_inline_pages(&req->rq_rcv_buf, replen, args->pages, args->pgbase, args->pglen);
-        return 0;
+        encode_nfs_fh3(xdr, args->fh);
+
+        p = xdr_reserve_space(xdr, 8 + NFS3_COOKIEVERFSIZE + 4);
+        p = xdr_encode_cookie3(p, args->cookie);
+        p = xdr_encode_cookieverf3(p, args->verf);
+        *p = cpu_to_be32(args->count);
+}
+
+static void nfs3_xdr_enc_readdir3args(struct rpc_rqst *req,
+                                      struct xdr_stream *xdr,
+                                      const struct nfs3_readdirargs *args)
+{
+        encode_readdir3args(xdr, args);
+        prepare_reply_buffer(req, args->pages, 0,
+                                args->count, NFS3_readdirres_sz);
 }
 
 /*
- * Decode READLINK reply
+ * 3.3.17  READDIRPLUS3args
+ *
+ *      struct READDIRPLUS3args {
+ *              nfs_fh3         dir;
+ *              cookie3         cookie;
+ *              cookieverf3     cookieverf;
+ *              count3          dircount;
+ *              count3          maxcount;
+ *      };
  */
-static int
-nfs3_xdr_readlinkres(struct rpc_rqst *req, __be32 *p, struct nfs_fattr *fattr)
+static void encode_readdirplus3args(struct xdr_stream *xdr,
+                                    const struct nfs3_readdirargs *args)
 {
-        struct xdr_buf *rcvbuf = &req->rq_rcv_buf;
-        struct kvec *iov = rcvbuf->head;
-        size_t hdrlen;
-        u32 len, recvd;
-        char    *kaddr;
-        int     status;
+        __be32 *p;
 
-        status = ntohl(*p++);
-        p = xdr_decode_post_op_attr(p, fattr);
+        encode_nfs_fh3(xdr, args->fh);
 
-        if (status != 0)
-                return nfs_stat_to_errno(status);
+        p = xdr_reserve_space(xdr, 8 + NFS3_COOKIEVERFSIZE + 4 + 4);
+        p = xdr_encode_cookie3(p, args->cookie);
+        p = xdr_encode_cookieverf3(p, args->verf);
 
-        /* Convert length of symlink */
-        len = ntohl(*p++);
-        if (len >= rcvbuf->page_len) {
-                dprintk("nfs: server returned giant symlink!\n");
-                return -ENAMETOOLONG;
-        }
+        /*
+         * readdirplus: need dircount + buffer size.
+         * We just make sure we make dircount big enough
+         */
+        *p++ = cpu_to_be32(args->count >> 3);
 
-        hdrlen = (u8 *) p - (u8 *) iov->iov_base;
-        if (iov->iov_len < hdrlen) {
-                dprintk("NFS: READLINK reply header overflowed:"
-                                "length %Zu > %Zu\n", hdrlen, iov->iov_len);
-                return -errno_NFSERR_IO;
-        } else if (iov->iov_len != hdrlen) {
-                dprintk("NFS: READLINK header is short. "
-                        "iovec will be shifted.\n");
-                xdr_shift_buf(rcvbuf, iov->iov_len - hdrlen);
-        }
-        recvd = req->rq_rcv_buf.len - hdrlen;
-        if (recvd < len) {
-                dprintk("NFS: server cheating in readlink reply: "
-                                "count %u > recvd %u\n", len, recvd);
-                return -EIO;
-        }
+        *p = cpu_to_be32(args->count);
+}
 
-        /* NULL terminate the string we got */
-        kaddr = (char*)kmap_atomic(rcvbuf->pages[0], KM_USER0);
-        kaddr[len+rcvbuf->page_base] = '\0';
-        kunmap_atomic(kaddr, KM_USER0);
-        return 0;
+static void nfs3_xdr_enc_readdirplus3args(struct rpc_rqst *req,
+                                          struct xdr_stream *xdr,
+                                          const struct nfs3_readdirargs *args)
+{
+        encode_readdirplus3args(xdr, args);
+        prepare_reply_buffer(req, args->pages, 0,
+                                args->count, NFS3_readdirres_sz);
 }
 
 /*
- * Decode READ reply
+ * 3.3.21  COMMIT3args
+ *
+ *      struct COMMIT3args {
+ *              nfs_fh3         file;
+ *              offset3         offset;
+ *              count3          count;
+ *      };
  */
-static int
-nfs3_xdr_readres(struct rpc_rqst *req, __be32 *p, struct nfs_readres *res)
+static void encode_commit3args(struct xdr_stream *xdr,
+                               const struct nfs_writeargs *args)
 {
-        struct kvec *iov = req->rq_rcv_buf.head;
-        size_t hdrlen;
-        u32 count, ocount, recvd;
-        int status;
+        __be32 *p;
 
-        status = ntohl(*p++);
-        p = xdr_decode_post_op_attr(p, res->fattr);
+        encode_nfs_fh3(xdr, args->fh);
 
-        if (status != 0)
-                return nfs_stat_to_errno(status);
+        p = xdr_reserve_space(xdr, 8 + 4);
+        p = xdr_encode_hyper(p, args->offset);
+        *p = cpu_to_be32(args->count);
+}
 
-        /* Decode reply count and EOF flag. NFSv3 is somewhat redundant
-         * in that it puts the count both in the res struct and in the
-         * opaque data count. */
-        count    = ntohl(*p++);
-        res->eof = ntohl(*p++);
-        ocount   = ntohl(*p++);
+static void nfs3_xdr_enc_commit3args(struct rpc_rqst *req,
+                                     struct xdr_stream *xdr,
+                                     const struct nfs_writeargs *args)
+{
+        encode_commit3args(xdr, args);
+}
 
-        if (ocount != count) {
-                dprintk("NFS: READ count doesn't match RPC opaque count.\n");
-                return -errno_NFSERR_IO;
-        }
+#ifdef CONFIG_NFS_V3_ACL
 
-        hdrlen = (u8 *) p - (u8 *) iov->iov_base;
-        if (iov->iov_len < hdrlen) {
-                dprintk("NFS: READ reply header overflowed:"
-                                "length %Zu > %Zu\n", hdrlen, iov->iov_len);
-                return -errno_NFSERR_IO;
-        } else if (iov->iov_len != hdrlen) {
-                dprintk("NFS: READ header is short. iovec will be shifted.\n");
-                xdr_shift_buf(&req->rq_rcv_buf, iov->iov_len - hdrlen);
-        }
+static void nfs3_xdr_enc_getacl3args(struct rpc_rqst *req,
+                                     struct xdr_stream *xdr,
+                                     const struct nfs3_getaclargs *args)
+{
+        encode_nfs_fh3(xdr, args->fh);
+        encode_uint32(xdr, args->mask);
+        if (args->mask & (NFS_ACL | NFS_DFACL))
+                prepare_reply_buffer(req, args->pages, 0,
+                                        NFSACL_MAXPAGES << PAGE_SHIFT,
+                                        ACL3_getaclres_sz);
+}
 
-        recvd = req->rq_rcv_buf.len - hdrlen;
-        if (count > recvd) {
-                dprintk("NFS: server cheating in read reply: "
-                        "count %u > recvd %u\n", count, recvd);
-                count = recvd;
-                res->eof = 0;
-        }
+static void nfs3_xdr_enc_setacl3args(struct rpc_rqst *req,
+                                     struct xdr_stream *xdr,
+                                     const struct nfs3_setaclargs *args)
+{
+        unsigned int base;
+        int error;
 
-        if (count < res->count)
-                res->count = count;
+        encode_nfs_fh3(xdr, NFS_FH(args->inode));
+        encode_uint32(xdr, args->mask);
+        if (args->npages != 0)
+                xdr_write_pages(xdr, args->pages, 0, args->len);
 
-        return count;
+        base = req->rq_slen;
+        error = nfsacl_encode(xdr->buf, base, args->inode,
+                            (args->mask & NFS_ACL) ?
+                            args->acl_access : NULL, 1, 0);
+        BUG_ON(error < 0);
+        error = nfsacl_encode(xdr->buf, base + error, args->inode,
+                            (args->mask & NFS_DFACL) ?
+                            args->acl_default : NULL, 1,
+                            NFS_ACL_DEFAULT);
+        BUG_ON(error < 0);
 }
 
+#endif  /* CONFIG_NFS_V3_ACL */
+
 /*
- * Decode WRITE response
+ * NFSv3 XDR decode functions
+ *
+ * NFSv3 result types are defined in section 3.3 of RFC 1813:
+ * "NFS Version 3 Protocol Specification".
  */
-static int
-nfs3_xdr_writeres(struct rpc_rqst *req, __be32 *p, struct nfs_writeres *res)
-{
-        int     status;
 
-        status = ntohl(*p++);
-        p = xdr_decode_wcc_data(p, res->fattr);
+/*
+ * 3.3.1  GETATTR3res
+ *
+ *      struct GETATTR3resok {
+ *              fattr3          obj_attributes;
+ *      };
+ *
+ *      union GETATTR3res switch (nfsstat3 status) {
+ *      case NFS3_OK:
+ *              GETATTR3resok  resok;
+ *      default:
+ *              void;
+ *      };
+ */
+static int nfs3_xdr_dec_getattr3res(struct rpc_rqst *req,
+                                    struct xdr_stream *xdr,
+                                    struct nfs_fattr *result)
+{
+        enum nfs_stat status;
+        int error;
+
+        error = decode_nfsstat3(xdr, &status);
+        if (unlikely(error))
+                goto out;
+        if (status != NFS3_OK)
+                goto out_default;
+        error = decode_fattr3(xdr, result);
+out:
+        return error;
+out_default:
+        return nfs_stat_to_errno(status);
+}
 
-        if (status != 0)
-                return nfs_stat_to_errno(status);
+/*
+ * 3.3.2  SETATTR3res
+ *
+ *      struct SETATTR3resok {
+ *              wcc_data  obj_wcc;
+ *      };
+ *
+ *      struct SETATTR3resfail {
+ *              wcc_data  obj_wcc;
+ *      };
+ *
+ *      union SETATTR3res switch (nfsstat3 status) {
+ *      case NFS3_OK:
+ *              SETATTR3resok   resok;
+ *      default:
+ *              SETATTR3resfail resfail;
+ *      };
+ */
+static int nfs3_xdr_dec_setattr3res(struct rpc_rqst *req,
+                                    struct xdr_stream *xdr,
+                                    struct nfs_fattr *result)
+{
+        enum nfs_stat status;
+        int error;
+
+        error = decode_nfsstat3(xdr, &status);
+        if (unlikely(error))
+                goto out;
+        error = decode_wcc_data(xdr, result);
+        if (unlikely(error))
+                goto out;
+        if (status != NFS3_OK)
+                goto out_status;
+out:
+        return error;
+out_status:
+        return nfs_stat_to_errno(status);
+}
 
-        res->count = ntohl(*p++);
-        res->verf->committed = (enum nfs3_stable_how)ntohl(*p++);
-        res->verf->verifier[0] = *p++;
-        res->verf->verifier[1] = *p++;
+/*
+ * 3.3.3  LOOKUP3res
+ *
+ *      struct LOOKUP3resok {
+ *              nfs_fh3         object;
+ *              post_op_attr    obj_attributes;
+ *              post_op_attr    dir_attributes;
+ *      };
+ *
+ *      struct LOOKUP3resfail {
+ *              post_op_attr    dir_attributes;
+ *      };
+ *
+ *      union LOOKUP3res switch (nfsstat3 status) {
+ *      case NFS3_OK:
+ *              LOOKUP3resok    resok;
+ *      default:
+ *              LOOKUP3resfail  resfail;
+ *      };
+ */
+static int nfs3_xdr_dec_lookup3res(struct rpc_rqst *req,
+                                   struct xdr_stream *xdr,
+                                   struct nfs3_diropres *result)
+{
+        enum nfs_stat status;
+        int error;
+
+        error = decode_nfsstat3(xdr, &status);
+        if (unlikely(error))
+                goto out;
+        if (status != NFS3_OK)
+                goto out_default;
+        error = decode_nfs_fh3(xdr, result->fh);
+        if (unlikely(error))
+                goto out;
+        error = decode_post_op_attr(xdr, result->fattr);
+        if (unlikely(error))
+                goto out;
+        error = decode_post_op_attr(xdr, result->dir_attr);
+out:
+        return error;
+out_default:
+        error = decode_post_op_attr(xdr, result->dir_attr);
+        if (unlikely(error))
+                goto out;
+        return nfs_stat_to_errno(status);
+}
 
-        return res->count;
+/*
+ * 3.3.4  ACCESS3res
+ *
+ *      struct ACCESS3resok {
+ *              post_op_attr    obj_attributes;
+ *              uint32          access;
+ *      };
+ *
+ *      struct ACCESS3resfail {
+ *              post_op_attr    obj_attributes;
+ *      };
+ *
+ *      union ACCESS3res switch (nfsstat3 status) {
+ *      case NFS3_OK:
+ *              ACCESS3resok    resok;
+ *      default:
+ *              ACCESS3resfail  resfail;
+ *      };
+ */
+static int nfs3_xdr_dec_access3res(struct rpc_rqst *req,
+                                   struct xdr_stream *xdr,
+                                   struct nfs3_accessres *result)
+{
+        enum nfs_stat status;
+        int error;
+
+        error = decode_nfsstat3(xdr, &status);
+        if (unlikely(error))
+                goto out;
+        error = decode_post_op_attr(xdr, result->fattr);
+        if (unlikely(error))
+                goto out;
+        if (status != NFS3_OK)
+                goto out_default;
+        error = decode_uint32(xdr, &result->access);
+out:
+        return error;
+out_default:
+        return nfs_stat_to_errno(status);
 }
 
 /*
- * Decode a CREATE response
+ * 3.3.5  READLINK3res
+ *
+ *      struct READLINK3resok {
+ *              post_op_attr    symlink_attributes;
+ *              nfspath3        data;
+ *      };
+ *
+ *      struct READLINK3resfail {
+ *              post_op_attr    symlink_attributes;
+ *      };
+ *
+ *      union READLINK3res switch (nfsstat3 status) {
+ *      case NFS3_OK:
+ *              READLINK3resok  resok;
+ *      default:
+ *              READLINK3resfail resfail;
+ *      };
  */
-static int
-nfs3_xdr_createres(struct rpc_rqst *req, __be32 *p, struct nfs3_diropres *res)
-{
-        int     status;
-
-        status = ntohl(*p++);
-        if (status == 0) {
-                if (*p++) {
-                        if (!(p = xdr_decode_fhandle(p, res->fh)))
-                                return -errno_NFSERR_IO;
-                        p = xdr_decode_post_op_attr(p, res->fattr);
-                } else {
-                        memset(res->fh, 0, sizeof(*res->fh));
-                        /* Do decode post_op_attr but set it to NULL */
-                        p = xdr_decode_post_op_attr(p, res->fattr);
-                        res->fattr->valid = 0;
-                }
-        } else {
-                status = nfs_stat_to_errno(status);
-        }
-        p = xdr_decode_wcc_data(p, res->dir_attr);
-        return status;
+static int nfs3_xdr_dec_readlink3res(struct rpc_rqst *req,
+                                     struct xdr_stream *xdr,
+                                     struct nfs_fattr *result)
+{
+        enum nfs_stat status;
+        int error;
+
+        error = decode_nfsstat3(xdr, &status);
+        if (unlikely(error))
+                goto out;
+        error = decode_post_op_attr(xdr, result);
+        if (unlikely(error))
+                goto out;
+        if (status != NFS3_OK)
+                goto out_default;
+        error = decode_nfspath3(xdr);
+out:
+        return error;
+out_default:
+        return nfs_stat_to_errno(status);
 }
 
 /*
- * Decode RENAME reply
+ * 3.3.6  READ3res
+ *
+ *      struct READ3resok {
+ *              post_op_attr    file_attributes;
+ *              count3          count;
+ *              bool            eof;
+ *              opaque          data<>;
+ *      };
+ *
+ *      struct READ3resfail {
+ *              post_op_attr    file_attributes;
+ *      };
+ *
+ *      union READ3res switch (nfsstat3 status) {
+ *      case NFS3_OK:
+ *              READ3resok      resok;
+ *      default:
+ *              READ3resfail    resfail;
+ *      };
  */
-static int
-nfs3_xdr_renameres(struct rpc_rqst *req, __be32 *p, struct nfs3_renameres *res)
+static int decode_read3resok(struct xdr_stream *xdr,
+                             struct nfs_readres *result)
 {
-        int     status;
+        u32 eof, count, ocount, recvd;
+        size_t hdrlen;
+        __be32 *p;
+
+        p = xdr_inline_decode(xdr, 4 + 4 + 4);
+        if (unlikely(p == NULL))
+                goto out_overflow;
+        count = be32_to_cpup(p++);
+        eof = be32_to_cpup(p++);
+        ocount = be32_to_cpup(p++);
+        if (unlikely(ocount != count))
+                goto out_mismatch;
+        hdrlen = (u8 *)xdr->p - (u8 *)xdr->iov->iov_base;
+        recvd = xdr->buf->len - hdrlen;
+        if (unlikely(count > recvd))
+                goto out_cheating;
+
+out:
+        xdr_read_pages(xdr, count);
+        result->eof = eof;
+        result->count = count;
+        return count;
+out_mismatch:
+        dprintk("NFS: READ count doesn't match length of opaque: "
+                "count %u != ocount %u\n", count, ocount);
+        return -EIO;
+out_cheating:
+        dprintk("NFS: server cheating in read result: "
+                "count %u > recvd %u\n", count, recvd);
+        count = recvd;
+        eof = 0;
+        goto out;
+out_overflow:
+        print_overflow_msg(__func__, xdr);
+        return -EIO;
+}
 
-        if ((status = ntohl(*p++)) != 0)
-                status = nfs_stat_to_errno(status);
-        p = xdr_decode_wcc_data(p, res->fromattr);
-        p = xdr_decode_wcc_data(p, res->toattr);
-        return status;
+static int nfs3_xdr_dec_read3res(struct rpc_rqst *req, struct xdr_stream *xdr,
+                                 struct nfs_readres *result)
+{
+        enum nfs_stat status;
+        int error;
+
+        error = decode_nfsstat3(xdr, &status);
+        if (unlikely(error))
+                goto out;
+        error = decode_post_op_attr(xdr, result->fattr);
+        if (unlikely(error))
+                goto out;
+        if (status != NFS3_OK)
+                goto out_status;
+        error = decode_read3resok(xdr, result);
+out:
+        return error;
+out_status:
+        return nfs_stat_to_errno(status);
 }
 
 /*
- * Decode LINK reply
+ * 3.3.7  WRITE3res
+ *
+ *      enum stable_how {
+ *              UNSTABLE  = 0,
+ *              DATA_SYNC = 1,
+ *              FILE_SYNC = 2
+ *      };
+ *
+ *      struct WRITE3resok {
+ *              wcc_data        file_wcc;
+ *              count3          count;
+ *              stable_how      committed;
+ *              writeverf3      verf;
+ *      };
+ *
+ *      struct WRITE3resfail {
+ *              wcc_data        file_wcc;
+ *      };
+ *
+ *      union WRITE3res switch (nfsstat3 status) {
+ *      case NFS3_OK:
+ *              WRITE3resok     resok;
+ *      default:
+ *              WRITE3resfail   resfail;
+ *      };
  */
-static int
-nfs3_xdr_linkres(struct rpc_rqst *req, __be32 *p, struct nfs3_linkres *res)
+static int decode_write3resok(struct xdr_stream *xdr,
+                              struct nfs_writeres *result)
 {
-        int     status;
+        __be32 *p;
+
+        p = xdr_inline_decode(xdr, 4 + 4 + NFS3_WRITEVERFSIZE);
+        if (unlikely(p == NULL))
+                goto out_overflow;
+        result->count = be32_to_cpup(p++);
+        result->verf->committed = be32_to_cpup(p++);
+        if (unlikely(result->verf->committed > NFS_FILE_SYNC))
+                goto out_badvalue;
+        memcpy(result->verf->verifier, p, NFS3_WRITEVERFSIZE);
+        return result->count;
+out_badvalue:
+        dprintk("NFS: bad stable_how value: %u\n", result->verf->committed);
+        return -EIO;
+out_overflow:
+        print_overflow_msg(__func__, xdr);
+        return -EIO;
+}
 
-        if ((status = ntohl(*p++)) != 0)
-                status = nfs_stat_to_errno(status);
-        p = xdr_decode_post_op_attr(p, res->fattr);
-        p = xdr_decode_wcc_data(p, res->dir_attr);
-        return status;
+static int nfs3_xdr_dec_write3res(struct rpc_rqst *req, struct xdr_stream *xdr,
+                                  struct nfs_writeres *result)
+{
+        enum nfs_stat status;
+        int error;
+
+        error = decode_nfsstat3(xdr, &status);
+        if (unlikely(error))
+                goto out;
+        error = decode_wcc_data(xdr, result->fattr);
+        if (unlikely(error))
+                goto out;
+        if (status != NFS3_OK)
+                goto out_status;
+        error = decode_write3resok(xdr, result);
+out:
+        return error;
+out_status:
+        return nfs_stat_to_errno(status);
 }
 
 /*
- * Decode FSSTAT reply
+ * 3.3.8  CREATE3res
+ *
+ *      struct CREATE3resok {
+ *              post_op_fh3     obj;
+ *              post_op_attr    obj_attributes;
+ *              wcc_data        dir_wcc;
+ *      };
+ *
+ *      struct CREATE3resfail {
+ *              wcc_data        dir_wcc;
+ *      };
+ *
+ *      union CREATE3res switch (nfsstat3 status) {
+ *      case NFS3_OK:
+ *              CREATE3resok    resok;
+ *      default:
+ *              CREATE3resfail  resfail;
+ *      };
  */
-static int
-nfs3_xdr_fsstatres(struct rpc_rqst *req, __be32 *p, struct nfs_fsstat *res)
+static int decode_create3resok(struct xdr_stream *xdr,
+                               struct nfs3_diropres *result)
 {
-        int             status;
-
-        status = ntohl(*p++);
+        int error;
+
+        error = decode_post_op_fh3(xdr, result->fh);
+        if (unlikely(error))
+                goto out;
+        error = decode_post_op_attr(xdr, result->fattr);
+        if (unlikely(error))
+                goto out;
+        /* The server isn't required to return a file handle.
+         * If it didn't, force the client to perform a LOOKUP
+         * to determine the correct file handle and attribute
+         * values for the new object. */
+        if (result->fh->size == 0)
+                result->fattr->valid = 0;
+        error = decode_wcc_data(xdr, result->dir_attr);
+out:
+        return error;
+}
 
-        p = xdr_decode_post_op_attr(p, res->fattr);
-        if (status != 0)
-                return nfs_stat_to_errno(status);
+static int nfs3_xdr_dec_create3res(struct rpc_rqst *req,
+                                   struct xdr_stream *xdr,
+                                   struct nfs3_diropres *result)
+{
+        enum nfs_stat status;
+        int error;
+
+        error = decode_nfsstat3(xdr, &status);
+        if (unlikely(error))
+                goto out;
+        if (status != NFS3_OK)
+                goto out_default;
+        error = decode_create3resok(xdr, result);
+out:
+        return error;
+out_default:
+        error = decode_wcc_data(xdr, result->dir_attr);
+        if (unlikely(error))
+                goto out;
+        return nfs_stat_to_errno(status);
+}
 
-        p = xdr_decode_hyper(p, &res->tbytes);
-        p = xdr_decode_hyper(p, &res->fbytes);
-        p = xdr_decode_hyper(p, &res->abytes);
-        p = xdr_decode_hyper(p, &res->tfiles);
-        p = xdr_decode_hyper(p, &res->ffiles);
-        p = xdr_decode_hyper(p, &res->afiles);
+/*
+ * 3.3.12  REMOVE3res
+ *
+ *      struct REMOVE3resok {
+ *              wcc_data    dir_wcc;
+ *      };
+ *
+ *      struct REMOVE3resfail {
+ *              wcc_data    dir_wcc;
+ *      };
+ *
+ *      union REMOVE3res switch (nfsstat3 status) {
+ *      case NFS3_OK:
+ *              REMOVE3resok   resok;
+ *      default:
+ *              REMOVE3resfail resfail;
+ *      };
+ */
+static int nfs3_xdr_dec_remove3res(struct rpc_rqst *req,
+                                   struct xdr_stream *xdr,
+                                   struct nfs_removeres *result)
+{
+        enum nfs_stat status;
+        int error;
+
+        error = decode_nfsstat3(xdr, &status);
+        if (unlikely(error))
+                goto out;
+        error = decode_wcc_data(xdr, result->dir_attr);
+        if (unlikely(error))
+                goto out;
+        if (status != NFS3_OK)
+                goto out_status;
+out:
+        return error;
+out_status:
+        return nfs_stat_to_errno(status);
+}
 
-        /* ignore invarsec */
-        return 0;
+/*
+ * 3.3.14  RENAME3res
+ *
+ *      struct RENAME3resok {
+ *              wcc_data        fromdir_wcc;
+ *              wcc_data        todir_wcc;
+ *      };
+ *
+ *      struct RENAME3resfail {
+ *              wcc_data        fromdir_wcc;
+ *              wcc_data        todir_wcc;
+ *      };
+ *
+ *      union RENAME3res switch (nfsstat3 status) {
+ *      case NFS3_OK:
+ *              RENAME3resok   resok;
+ *      default:
+ *              RENAME3resfail resfail;
+ *      };
+ */
+static int nfs3_xdr_dec_rename3res(struct rpc_rqst *req,
+                                   struct xdr_stream *xdr,
+                                   struct nfs_renameres *result)
+{
+        enum nfs_stat status;
+        int error;
+
+        error = decode_nfsstat3(xdr, &status);
+        if (unlikely(error))
+                goto out;
+        error = decode_wcc_data(xdr, result->old_fattr);
+        if (unlikely(error))
+                goto out;
+        error = decode_wcc_data(xdr, result->new_fattr);
+        if (unlikely(error))
+                goto out;
+        if (status != NFS3_OK)
+                goto out_status;
+out:
+        return error;
+out_status:
+        return nfs_stat_to_errno(status);
 }
 
 /*
- * Decode FSINFO reply
+ * 3.3.15  LINK3res
+ *
+ *      struct LINK3resok {
+ *              post_op_attr    file_attributes;
+ *              wcc_data        linkdir_wcc;
+ *      };
+ *
+ *      struct LINK3resfail {
+ *              post_op_attr    file_attributes;
+ *              wcc_data        linkdir_wcc;
+ *      };
+ *
+ *      union LINK3res switch (nfsstat3 status) {
+ *      case NFS3_OK:
+ *              LINK3resok      resok;
+ *      default:
+ *              LINK3resfail    resfail;
+ *      };
  */
-static int
-nfs3_xdr_fsinfores(struct rpc_rqst *req, __be32 *p, struct nfs_fsinfo *res)
+static int nfs3_xdr_dec_link3res(struct rpc_rqst *req, struct xdr_stream *xdr,
+                                 struct nfs3_linkres *result)
 {
-        int             status;
+        enum nfs_stat status;
+        int error;
+
+        error = decode_nfsstat3(xdr, &status);
+        if (unlikely(error))
+                goto out;
+        error = decode_post_op_attr(xdr, result->fattr);
+        if (unlikely(error))
+                goto out;
+        error = decode_wcc_data(xdr, result->dir_attr);
+        if (unlikely(error))
+                goto out;
+        if (status != NFS3_OK)
+                goto out_status;
+out:
+        return error;
+out_status:
+        return nfs_stat_to_errno(status);
+}
 
-        status = ntohl(*p++);
+/**
+ * nfs3_decode_dirent - Decode a single NFSv3 directory entry stored in
+ *                      the local page cache
+ * @xdr: XDR stream where entry resides
+ * @entry: buffer to fill in with entry data
+ * @plus: boolean indicating whether this should be a readdirplus entry
+ *
+ * Returns zero if successful, otherwise a negative errno value is
+ * returned.
+ *
+ * This function is not invoked during READDIR reply decoding, but
+ * rather whenever an application invokes the getdents(2) system call
+ * on a directory already in our cache.
+ *
+ * 3.3.16  entry3
+ *
+ *      struct entry3 {
+ *              fileid3         fileid;
+ *              filename3       name;
+ *              cookie3         cookie;
+ *              fhandle3        filehandle;
+ *              post_op_attr3   attributes;
+ *              entry3          *nextentry;
+ *      };
+ *
+ * 3.3.17  entryplus3
+ *      struct entryplus3 {
+ *              fileid3         fileid;
+ *              filename3       name;
+ *              cookie3         cookie;
+ *              post_op_attr    name_attributes;
+ *              post_op_fh3     name_handle;
+ *              entryplus3      *nextentry;
+ *      };
+ */
+int nfs3_decode_dirent(struct xdr_stream *xdr, struct nfs_entry *entry,
+                       int plus)
+{
+        struct nfs_entry old = *entry;
+        __be32 *p;
+        int error;
+
+        p = xdr_inline_decode(xdr, 4);
+        if (unlikely(p == NULL))
+                goto out_overflow;
+        if (*p == xdr_zero) {
+                p = xdr_inline_decode(xdr, 4);
+                if (unlikely(p == NULL))
+                        goto out_overflow;
+                if (*p == xdr_zero)
+                        return -EAGAIN;
+                entry->eof = 1;
+                return -EBADCOOKIE;
+        }
+
+        error = decode_fileid3(xdr, &entry->ino);
+        if (unlikely(error))
+                return error;
+
+        error = decode_inline_filename3(xdr, &entry->name, &entry->len);
+        if (unlikely(error))
+                return error;
 
-        p = xdr_decode_post_op_attr(p, res->fattr);
-        if (status != 0)
-                return nfs_stat_to_errno(status);
+        entry->prev_cookie = entry->cookie;
+        error = decode_cookie3(xdr, &entry->cookie);
+        if (unlikely(error))
+                return error;
+
+        entry->d_type = DT_UNKNOWN;
 
-        res->rtmax  = ntohl(*p++);
-        res->rtpref = ntohl(*p++);
-        res->rtmult = ntohl(*p++);
-        res->wtmax  = ntohl(*p++);
-        res->wtpref = ntohl(*p++);
-        res->wtmult = ntohl(*p++);
-        res->dtpref = ntohl(*p++);
-        p = xdr_decode_hyper(p, &res->maxfilesize);
+        if (plus) {
+                entry->fattr->valid = 0;
+                error = decode_post_op_attr(xdr, entry->fattr);
+                if (unlikely(error))
+                        return error;
+                if (entry->fattr->valid & NFS_ATTR_FATTR_V3)
+                        entry->d_type = nfs_umode_to_dtype(entry->fattr->mode);
+
+                /* In fact, a post_op_fh3: */
+                p = xdr_inline_decode(xdr, 4);
+                if (unlikely(p == NULL))
+                        goto out_overflow;
+                if (*p != xdr_zero) {
+                        error = decode_nfs_fh3(xdr, entry->fh);
+                        if (unlikely(error)) {
+                                if (error == -E2BIG)
+                                        goto out_truncated;
+                                return error;
+                        }
+                } else
+                        zero_nfs_fh3(entry->fh);
+        }
 
-        /* ignore time_delta and properties */
-        res->lease_time = 0;
         return 0;
+
+out_overflow:
+        print_overflow_msg(__func__, xdr);
+        return -EAGAIN;
+out_truncated:
+        dprintk("NFS: directory entry contains invalid file handle\n");
+        *entry = old;
+        return -EAGAIN;
 }
 
 /*
- * Decode PATHCONF reply
+ * 3.3.16  READDIR3res
+ *
+ *      struct dirlist3 {
+ *              entry3          *entries;
+ *              bool            eof;
+ *      };
+ *
+ *      struct READDIR3resok {
+ *              post_op_attr    dir_attributes;
+ *              cookieverf3     cookieverf;
+ *              dirlist3        reply;
+ *      };
+ *
+ *      struct READDIR3resfail {
+ *              post_op_attr    dir_attributes;
+ *      };
+ *
+ *      union READDIR3res switch (nfsstat3 status) {
+ *      case NFS3_OK:
+ *              READDIR3resok   resok;
+ *      default:
+ *              READDIR3resfail resfail;
+ *      };
+ *
+ * Read the directory contents into the page cache, but otherwise
+ * don't touch them.  The actual decoding is done by nfs3_decode_entry()
+ * during subsequent nfs_readdir() calls.
  */
-static int
-nfs3_xdr_pathconfres(struct rpc_rqst *req, __be32 *p, struct nfs_pathconf *res)
+static int decode_dirlist3(struct xdr_stream *xdr)
 {
-        int             status;
+        u32 recvd, pglen;
+        size_t hdrlen;
 
-        status = ntohl(*p++);
+        pglen = xdr->buf->page_len;
+        hdrlen = (u8 *)xdr->p - (u8 *)xdr->iov->iov_base;
+        recvd = xdr->buf->len - hdrlen;
+        if (unlikely(pglen > recvd))
+                goto out_cheating;
+out:
+        xdr_read_pages(xdr, pglen);
+        return pglen;
+out_cheating:
+        dprintk("NFS: server cheating in readdir result: "
+                "pglen %u > recvd %u\n", pglen, recvd);
+        pglen = recvd;
+        goto out;
+}
 
-        p = xdr_decode_post_op_attr(p, res->fattr);
-        if (status != 0)
-                return nfs_stat_to_errno(status);
-        res->max_link = ntohl(*p++);
-        res->max_namelen = ntohl(*p++);
+static int decode_readdir3resok(struct xdr_stream *xdr,
+                                struct nfs3_readdirres *result)
+{
+        int error;
+
+        error = decode_post_op_attr(xdr, result->dir_attr);
+        if (unlikely(error))
+                goto out;
+        /* XXX: do we need to check if result->verf != NULL ? */
+        error = decode_cookieverf3(xdr, result->verf);
+        if (unlikely(error))
+                goto out;
+        error = decode_dirlist3(xdr);
+out:
+        return error;
+}
 
-        /* ignore remaining fields */
-        return 0;
+static int nfs3_xdr_dec_readdir3res(struct rpc_rqst *req,
+                                    struct xdr_stream *xdr,
+                                    struct nfs3_readdirres *result)
+{
+        enum nfs_stat status;
+        int error;
+
+        error = decode_nfsstat3(xdr, &status);
+        if (unlikely(error))
+                goto out;
+        if (status != NFS3_OK)
+                goto out_default;
+        error = decode_readdir3resok(xdr, result);
+out:
+        return error;
+out_default:
+        error = decode_post_op_attr(xdr, result->dir_attr);
+        if (unlikely(error))
+                goto out;
+        return nfs_stat_to_errno(status);
 }
 
 /*
- * Decode COMMIT reply
+ * 3.3.18  FSSTAT3res
+ *
+ *      struct FSSTAT3resok {
+ *              post_op_attr    obj_attributes;
+ *              size3           tbytes;
+ *              size3           fbytes;
+ *              size3           abytes;
+ *              size3           tfiles;
+ *              size3           ffiles;
+ *              size3           afiles;
+ *              uint32          invarsec;
+ *      };
+ *
+ *      struct FSSTAT3resfail {
+ *              post_op_attr    obj_attributes;
+ *      };
+ *
+ *      union FSSTAT3res switch (nfsstat3 status) {
+ *      case NFS3_OK:
+ *              FSSTAT3resok    resok;
+ *      default:
+ *              FSSTAT3resfail  resfail;
+ *      };
  */
-static int
-nfs3_xdr_commitres(struct rpc_rqst *req, __be32 *p, struct nfs_writeres *res)
+static int decode_fsstat3resok(struct xdr_stream *xdr,
+                               struct nfs_fsstat *result)
 {
-        int             status;
+        __be32 *p;
+
+        p = xdr_inline_decode(xdr, 8 * 6 + 4);
+        if (unlikely(p == NULL))
+                goto out_overflow;
+        p = xdr_decode_size3(p, &result->tbytes);
+        p = xdr_decode_size3(p, &result->fbytes);
+        p = xdr_decode_size3(p, &result->abytes);
+        p = xdr_decode_size3(p, &result->tfiles);
+        p = xdr_decode_size3(p, &result->ffiles);
+        xdr_decode_size3(p, &result->afiles);
+        /* ignore invarsec */
+        return 0;
+out_overflow:
+        print_overflow_msg(__func__, xdr);
+        return -EIO;
+}
 
-        status = ntohl(*p++);
-        p = xdr_decode_wcc_data(p, res->fattr);
-        if (status != 0)
-                return nfs_stat_to_errno(status);
+static int nfs3_xdr_dec_fsstat3res(struct rpc_rqst *req,
+                                   struct xdr_stream *xdr,
+                                   struct nfs_fsstat *result)
+{
+        enum nfs_stat status;
+        int error;
+
+        error = decode_nfsstat3(xdr, &status);
+        if (unlikely(error))
+                goto out;
+        error = decode_post_op_attr(xdr, result->fattr);
+        if (unlikely(error))
+                goto out;
+        if (status != NFS3_OK)
+                goto out_status;
+        error = decode_fsstat3resok(xdr, result);
+out:
+        return error;
+out_status:
+        return nfs_stat_to_errno(status);
+}
 
-        res->verf->verifier[0] = *p++;
-        res->verf->verifier[1] = *p++;
+/*
+ * 3.3.19  FSINFO3res
+ *
+ *      struct FSINFO3resok {
+ *              post_op_attr    obj_attributes;
+ *              uint32          rtmax;
+ *              uint32          rtpref;
+ *              uint32          rtmult;
+ *              uint32          wtmax;
+ *              uint32          wtpref;
+ *              uint32          wtmult;
+ *              uint32          dtpref;
+ *              size3           maxfilesize;
+ *              nfstime3        time_delta;
+ *              uint32          properties;
+ *      };
+ *
+ *      struct FSINFO3resfail {
+ *              post_op_attr    obj_attributes;
+ *      };
+ *
+ *      union FSINFO3res switch (nfsstat3 status) {
+ *      case NFS3_OK:
+ *              FSINFO3resok    resok;
+ *      default:
+ *              FSINFO3resfail  resfail;
+ *      };
+ */
+static int decode_fsinfo3resok(struct xdr_stream *xdr,
+                               struct nfs_fsinfo *result)
+{
+        __be32 *p;
+
+        p = xdr_inline_decode(xdr, 4 * 7 + 8 + 8 + 4);
+        if (unlikely(p == NULL))
+                goto out_overflow;
+        result->rtmax  = be32_to_cpup(p++);
+        result->rtpref = be32_to_cpup(p++);
+        result->rtmult = be32_to_cpup(p++);
+        result->wtmax  = be32_to_cpup(p++);
+        result->wtpref = be32_to_cpup(p++);
+        result->wtmult = be32_to_cpup(p++);
+        result->dtpref = be32_to_cpup(p++);
+        p = xdr_decode_size3(p, &result->maxfilesize);
+        xdr_decode_nfstime3(p, &result->time_delta);
+
+        /* ignore properties */
+        result->lease_time = 0;
         return 0;
+out_overflow:
+        print_overflow_msg(__func__, xdr);
+        return -EIO;
+}
+
+static int nfs3_xdr_dec_fsinfo3res(struct rpc_rqst *req,
+                                   struct xdr_stream *xdr,
+                                   struct nfs_fsinfo *result)
+{
+        enum nfs_stat status;
+        int error;
+
+        error = decode_nfsstat3(xdr, &status);
+        if (unlikely(error))
+                goto out;
+        error = decode_post_op_attr(xdr, result->fattr);
+        if (unlikely(error))
+                goto out;
+        if (status != NFS3_OK)
+                goto out_status;
+        error = decode_fsinfo3resok(xdr, result);
+out:
+        return error;
+out_status:
+        return nfs_stat_to_errno(status);
 }
 
-#ifdef CONFIG_NFS_V3_ACL
 /*
- * Decode GETACL reply
+ * 3.3.20  PATHCONF3res
+ *
+ *      struct PATHCONF3resok {
+ *              post_op_attr    obj_attributes;
+ *              uint32          linkmax;
+ *              uint32          name_max;
+ *              bool            no_trunc;
+ *              bool            chown_restricted;
+ *              bool            case_insensitive;
+ *              bool            case_preserving;
+ *      };
+ *
+ *      struct PATHCONF3resfail {
+ *              post_op_attr    obj_attributes;
+ *      };
+ *
+ *      union PATHCONF3res switch (nfsstat3 status) {
+ *      case NFS3_OK:
+ *              PATHCONF3resok  resok;
+ *      default:
+ *              PATHCONF3resfail resfail;
+ *      };
  */
-static int
-nfs3_xdr_getaclres(struct rpc_rqst *req, __be32 *p,
-                   struct nfs3_getaclres *res)
+static int decode_pathconf3resok(struct xdr_stream *xdr,
+                                 struct nfs_pathconf *result)
 {
-        struct xdr_buf *buf = &req->rq_rcv_buf;
-        int status = ntohl(*p++);
-        struct posix_acl **acl;
-        unsigned int *aclcnt;
-        int err, base;
-
-        if (status != 0)
-                return nfs_stat_to_errno(status);
-        p = xdr_decode_post_op_attr(p, res->fattr);
-        res->mask = ntohl(*p++);
-        if (res->mask & ~(NFS_ACL|NFS_ACLCNT|NFS_DFACL|NFS_DFACLCNT))
-                return -EINVAL;
-        base = (char *)p - (char *)req->rq_rcv_buf.head->iov_base;
+        __be32 *p;
 
-        acl = (res->mask & NFS_ACL) ? &res->acl_access : NULL;
-        aclcnt = (res->mask & NFS_ACLCNT) ? &res->acl_access_count : NULL;
-        err = nfsacl_decode(buf, base, aclcnt, acl);
+        p = xdr_inline_decode(xdr, 4 * 6);
+        if (unlikely(p == NULL))
+                goto out_overflow;
+        result->max_link = be32_to_cpup(p++);
+        result->max_namelen = be32_to_cpup(p);
+        /* ignore remaining fields */
+        return 0;
+out_overflow:
+        print_overflow_msg(__func__, xdr);
+        return -EIO;
+}
 
-        acl = (res->mask & NFS_DFACL) ? &res->acl_default : NULL;
-        aclcnt = (res->mask & NFS_DFACLCNT) ? &res->acl_default_count : NULL;
-        if (err > 0)
-                err = nfsacl_decode(buf, base + err, aclcnt, acl);
-        return (err > 0) ? 0 : err;
+static int nfs3_xdr_dec_pathconf3res(struct rpc_rqst *req,
+                                     struct xdr_stream *xdr,
+                                     struct nfs_pathconf *result)
+{
+        enum nfs_stat status;
+        int error;
+
+        error = decode_nfsstat3(xdr, &status);
+        if (unlikely(error))
+                goto out;
+        error = decode_post_op_attr(xdr, result->fattr);
+        if (unlikely(error))
+                goto out;
+        if (status != NFS3_OK)
+                goto out_status;
+        error = decode_pathconf3resok(xdr, result);
+out:
+        return error;
+out_status:
+        return nfs_stat_to_errno(status);
 }
 
 /*
- * Decode setacl reply.
+ * 3.3.21  COMMIT3res
+ *
+ *      struct COMMIT3resok {
+ *              wcc_data        file_wcc;
+ *              writeverf3      verf;
+ *      };
+ *
+ *      struct COMMIT3resfail {
+ *              wcc_data        file_wcc;
+ *      };
+ *
+ *      union COMMIT3res switch (nfsstat3 status) {
+ *      case NFS3_OK:
+ *              COMMIT3resok    resok;
+ *      default:
+ *              COMMIT3resfail  resfail;
+ *      };
  */
-static int
-nfs3_xdr_setaclres(struct rpc_rqst *req, __be32 *p, struct nfs_fattr *fattr)
+static int nfs3_xdr_dec_commit3res(struct rpc_rqst *req,
+                                   struct xdr_stream *xdr,
+                                   struct nfs_writeres *result)
 {
-        int status = ntohl(*p++);
+        enum nfs_stat status;
+        int error;
+
+        error = decode_nfsstat3(xdr, &status);
+        if (unlikely(error))
+                goto out;
+        error = decode_wcc_data(xdr, result->fattr);
+        if (unlikely(error))
+                goto out;
+        if (status != NFS3_OK)
+                goto out_status;
+        error = decode_writeverf3(xdr, result->verf->verifier);
+out:
+        return error;
+out_status:
+        return nfs_stat_to_errno(status);
+}
 
-        if (status)
-                return nfs_stat_to_errno(status);
-        xdr_decode_post_op_attr(p, fattr);
-        return 0;
+#ifdef CONFIG_NFS_V3_ACL
+
+static inline int decode_getacl3resok(struct xdr_stream *xdr,
+                                      struct nfs3_getaclres *result)
+{
+        struct posix_acl **acl;
+        unsigned int *aclcnt;
+        size_t hdrlen;
+        int error;
+
+        error = decode_post_op_attr(xdr, result->fattr);
+        if (unlikely(error))
+                goto out;
+        error = decode_uint32(xdr, &result->mask);
+        if (unlikely(error))
+                goto out;
+        error = -EINVAL;
+        if (result->mask & ~(NFS_ACL|NFS_ACLCNT|NFS_DFACL|NFS_DFACLCNT))
+                goto out;
+
+        hdrlen = (u8 *)xdr->p - (u8 *)xdr->iov->iov_base;
+
+        acl = NULL;
+        if (result->mask & NFS_ACL)
+                acl = &result->acl_access;
+        aclcnt = NULL;
+        if (result->mask & NFS_ACLCNT)
+                aclcnt = &result->acl_access_count;
+        error = nfsacl_decode(xdr->buf, hdrlen, aclcnt, acl);
+        if (unlikely(error <= 0))
+                goto out;
+
+        acl = NULL;
+        if (result->mask & NFS_DFACL)
+                acl = &result->acl_default;
+        aclcnt = NULL;
+        if (result->mask & NFS_DFACLCNT)
+                aclcnt = &result->acl_default_count;
+        error = nfsacl_decode(xdr->buf, hdrlen + error, aclcnt, acl);
+        if (unlikely(error <= 0))
+                return error;
+        error = 0;
+out:
+        return error;
+}
+
+static int nfs3_xdr_dec_getacl3res(struct rpc_rqst *req,
+                                   struct xdr_stream *xdr,
+                                   struct nfs3_getaclres *result)
+{
+        enum nfs_stat status;
+        int error;
+
+        error = decode_nfsstat3(xdr, &status);
+        if (unlikely(error))
+                goto out;
+        if (status != NFS3_OK)
+                goto out_default;
+        error = decode_getacl3resok(xdr, result);
+out:
+        return error;
+out_default:
+        return nfs_stat_to_errno(status);
 }
+
+static int nfs3_xdr_dec_setacl3res(struct rpc_rqst *req,
+                                   struct xdr_stream *xdr,
+                                   struct nfs_fattr *result)
+{
+        enum nfs_stat status;
+        int error;
+
+        error = decode_nfsstat3(xdr, &status);
+        if (unlikely(error))
+                goto out;
+        if (status != NFS3_OK)
+                goto out_default;
+        error = decode_post_op_attr(xdr, result);
+out:
+        return error;
+out_default:
+        return nfs_stat_to_errno(status);
+}
+
 #endif  /* CONFIG_NFS_V3_ACL */
 
 #define PROC(proc, argtype, restype, timer)                             \
 [NFS3PROC_##proc] = {                                                   \
         .p_proc      = NFS3PROC_##proc,                                 \
-        .p_encode    = (kxdrproc_t) nfs3_xdr_##argtype,                 \
-        .p_decode    = (kxdrproc_t) nfs3_xdr_##restype,                 \
-        .p_arglen    = NFS3_##argtype##_sz,                             \
-        .p_replen    = NFS3_##restype##_sz,                             \
+        .p_encode    = (kxdreproc_t)nfs3_xdr_enc_##argtype##3args,      \
+        .p_decode    = (kxdrdproc_t)nfs3_xdr_dec_##restype##3res,       \
+        .p_arglen    = NFS3_##argtype##args_sz,                         \
+        .p_replen    = NFS3_##restype##res_sz,                          \
         .p_timer     = timer,                                           \
         .p_statidx   = NFS3PROC_##proc,                                 \
         .p_name      = #proc,                                           \
         }
 
 struct rpc_procinfo     nfs3_procedures[] = {
-  PROC(GETATTR,         fhandle,        attrstat, 1),
-  PROC(SETATTR,         sattrargs,      wccstat, 0),
-  PROC(LOOKUP,          diropargs,      lookupres, 2),
-  PROC(ACCESS,          accessargs,     accessres, 1),
-  PROC(READLINK,        readlinkargs,   readlinkres, 3),
-  PROC(READ,            readargs,       readres, 3),
-  PROC(WRITE,           writeargs,      writeres, 4),
-  PROC(CREATE,          createargs,     createres, 0),
-  PROC(MKDIR,           mkdirargs,      createres, 0),
-  PROC(SYMLINK,         symlinkargs,    createres, 0),
-  PROC(MKNOD,           mknodargs,      createres, 0),
-  PROC(REMOVE,          removeargs,     removeres, 0),
-  PROC(RMDIR,           diropargs,      wccstat, 0),
-  PROC(RENAME,          renameargs,     renameres, 0),
-  PROC(LINK,            linkargs,       linkres, 0),
-  PROC(READDIR,         readdirargs,    readdirres, 3),
-  PROC(READDIRPLUS,     readdirargs,    readdirres, 3),
-  PROC(FSSTAT,          fhandle,        fsstatres, 0),
-  PROC(FSINFO,          fhandle,        fsinfores, 0),
-  PROC(PATHCONF,        fhandle,        pathconfres, 0),
-  PROC(COMMIT,          commitargs,     commitres, 5),
+        PROC(GETATTR,           getattr,        getattr,        1),
+        PROC(SETATTR,           setattr,        setattr,        0),
+        PROC(LOOKUP,            lookup,         lookup,         2),
+        PROC(ACCESS,            access,         access,         1),
+        PROC(READLINK,          readlink,       readlink,       3),
+        PROC(READ,              read,           read,           3),
+        PROC(WRITE,             write,          write,          4),
+        PROC(CREATE,            create,         create,         0),
+        PROC(MKDIR,             mkdir,          create,         0),
+        PROC(SYMLINK,           symlink,        create,         0),
+        PROC(MKNOD,             mknod,          create,         0),
+        PROC(REMOVE,            remove,         remove,         0),
+        PROC(RMDIR,             lookup,         setattr,        0),
+        PROC(RENAME,            rename,         rename,         0),
+        PROC(LINK,              link,           link,           0),
+        PROC(READDIR,           readdir,        readdir,        3),
+        PROC(READDIRPLUS,       readdirplus,    readdir,        3),
+        PROC(FSSTAT,            getattr,        fsstat,         0),
+        PROC(FSINFO,            getattr,        fsinfo,         0),
+        PROC(PATHCONF,          getattr,        pathconf,       0),
+        PROC(COMMIT,            commit,         commit,         5),
 };
 
 struct rpc_version              nfs_version3 = {
@@ -1183,8 +2468,8 @@ struct rpc_version		nfs_version3 = {
 static struct rpc_procinfo      nfs3_acl_procedures[] = {
         [ACLPROC3_GETACL] = {
                 .p_proc = ACLPROC3_GETACL,
-                .p_encode = (kxdrproc_t) nfs3_xdr_getaclargs,
-                .p_decode = (kxdrproc_t) nfs3_xdr_getaclres,
+                .p_encode = (kxdreproc_t)nfs3_xdr_enc_getacl3args,
+                .p_decode = (kxdrdproc_t)nfs3_xdr_dec_getacl3res,
                 .p_arglen = ACL3_getaclargs_sz,
                 .p_replen = ACL3_getaclres_sz,
                 .p_timer = 1,
@@ -1192,8 +2477,8 @@ static struct rpc_procinfo	nfs3_acl_procedures[] = {
         },
         [ACLPROC3_SETACL] = {
                 .p_proc = ACLPROC3_SETACL,
-                .p_encode = (kxdrproc_t) nfs3_xdr_setaclargs,
-                .p_decode = (kxdrproc_t) nfs3_xdr_setaclres,
+                .p_encode = (kxdreproc_t)nfs3_xdr_enc_setacl3args,
+                .p_decode = (kxdrdproc_t)nfs3_xdr_dec_setacl3res,
                 .p_arglen = ACL3_setaclargs_sz,
                 .p_replen = ACL3_setaclres_sz,
                 .p_timer = 0,
diff --git a/fs/nfs/nfs4_fs.h b/fs/nfs/nfs4_fs.h
index 61bc3a32e1e2..7a7474073148 100644
--- a/fs/nfs/nfs4_fs.h
+++ b/fs/nfs/nfs4_fs.h
@@ -44,7 +44,29 @@ enum nfs4_client_state {
         NFS4CLNT_RECLAIM_REBOOT,
         NFS4CLNT_RECLAIM_NOGRACE,
         NFS4CLNT_DELEGRETURN,
-        NFS4CLNT_SESSION_SETUP,
+        NFS4CLNT_LAYOUTRECALL,
+        NFS4CLNT_SESSION_RESET,
+        NFS4CLNT_RECALL_SLOT,
+};
+
+enum nfs4_session_state {
+        NFS4_SESSION_INITING,
+        NFS4_SESSION_DRAINING,
+};
+
+struct nfs4_minor_version_ops {
+        u32     minor_version;
+
+        int     (*call_sync)(struct nfs_server *server,
+                        struct rpc_message *msg,
+                        struct nfs4_sequence_args *args,
+                        struct nfs4_sequence_res *res,
+                        int cache_reply);
+        int     (*validate_stateid)(struct nfs_delegation *,
+                        const nfs4_stateid *);
+        const struct nfs4_state_recovery_ops *reboot_recovery_ops;
+        const struct nfs4_state_recovery_ops *nograce_recovery_ops;
+        const struct nfs4_state_maintenance_ops *state_renewal_ops;
 };
 
 /*
@@ -87,9 +109,8 @@ struct nfs_unique_id {
  */
 struct nfs4_state_owner {
         struct nfs_unique_id so_owner_id;
-        struct nfs_client    *so_client;
         struct nfs_server    *so_server;
-        struct rb_node       so_client_node;
+        struct rb_node       so_server_node;
 
         struct rpc_cred      *so_cred;   /* Associated cred */
 
@@ -97,7 +118,6 @@ struct nfs4_state_owner {
         atomic_t             so_count;
         unsigned long        so_flags;
         struct list_head     so_states;
-        struct list_head     so_delegations;
         struct nfs_seqid_counter so_seqid;
         struct rpc_sequence  so_sequence;
 };
@@ -107,6 +127,10 @@ enum {
         NFS_OWNER_RECLAIM_NOGRACE
 };
 
+#define NFS_LOCK_NEW            0
+#define NFS_LOCK_RECLAIM        1
+#define NFS_LOCK_EXPIRED        2
+
 /*
  * struct nfs4_state maintains the client-side state for a given
  * (state_owner,inode) tuple (OPEN) or state_owner (LOCK).
@@ -119,10 +143,20 @@ enum {
  * LOCK: one nfs4_state (LOCK) to hold the lock stateid nfs4_state(OPEN)
  */
 
+struct nfs4_lock_owner {
+        unsigned int lo_type;
+#define NFS4_ANY_LOCK_TYPE      (0U)
+#define NFS4_FLOCK_LOCK_TYPE    (1U << 0)
+#define NFS4_POSIX_LOCK_TYPE    (1U << 1)
+        union {
+                fl_owner_t posix_owner;
+                pid_t flock_owner;
+        } lo_u;
+};
+
 struct nfs4_lock_state {
         struct list_head        ls_locks;       /* Other lock stateids */
         struct nfs4_state *     ls_state;       /* Pointer to open state */
-        fl_owner_t              ls_owner;       /* POSIX lock owner */
 #define NFS_LOCK_INITIALIZED 1
         int                     ls_flags;
         struct nfs_seqid_counter        ls_seqid;
@@ -130,6 +164,7 @@ struct nfs4_lock_state {
         struct nfs_unique_id    ls_id;
         nfs4_stateid            ls_stateid;
         atomic_t                ls_count;
+        struct nfs4_lock_owner  ls_owner;
 };
 
 /* bits for nfs4_state->flags */
@@ -141,6 +176,7 @@ enum {
         NFS_O_RDWR_STATE,               /* OPEN stateid has read/write state */
         NFS_STATE_RECLAIM_REBOOT,       /* OPEN stateid server rebooted */
         NFS_STATE_RECLAIM_NOGRACE,      /* OPEN stateid needs to recover state */
+        NFS_STATE_POSIX_LOCKS,          /* Posix locks are supported */
 };
 
 struct nfs4_state {
@@ -180,6 +216,7 @@ struct nfs4_state_recovery_ops {
         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 *);
+        int (*reclaim_complete)(struct nfs_client *);
 };
 
 struct nfs4_state_maintenance_ops {
@@ -191,45 +228,57 @@ struct nfs4_state_maintenance_ops {
 extern const struct dentry_operations nfs4_dentry_operations;
 extern const struct inode_operations nfs4_dir_inode_operations;
 
-/* inode.c */
-extern ssize_t nfs4_getxattr(struct dentry *, const char *, void *, size_t);
-extern int nfs4_setxattr(struct dentry *, const char *, const void *, size_t, int);
-extern ssize_t nfs4_listxattr(struct dentry *, char *, size_t);
-
-
 /* nfs4proc.c */
-extern int nfs4_proc_setclientid(struct nfs_client *, u32, unsigned short, struct rpc_cred *);
-extern int nfs4_proc_setclientid_confirm(struct nfs_client *, struct rpc_cred *);
+extern int nfs4_proc_setclientid(struct nfs_client *, u32, unsigned short, struct rpc_cred *, struct nfs4_setclientid_res *);
+extern int nfs4_proc_setclientid_confirm(struct nfs_client *, struct nfs4_setclientid_res *arg, struct rpc_cred *);
+extern int nfs4_proc_exchange_id(struct nfs_client *clp, struct rpc_cred *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 *);
+extern int nfs41_init_clientid(struct nfs_client *, struct rpc_cred *);
+extern int nfs4_do_close(struct path *path, struct nfs4_state *state, gfp_t gfp_mask, int wait, bool roc);
 extern int nfs4_server_capabilities(struct nfs_server *server, struct nfs_fh *fhandle);
 extern int nfs4_proc_fs_locations(struct inode *dir, const struct qstr *name,
                 struct nfs4_fs_locations *fs_locations, struct page *page);
+extern void nfs4_release_lockowner(const struct nfs4_lock_state *);
+extern const struct xattr_handler *nfs4_xattr_handlers[];
 
-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,
+static inline struct nfs4_session *nfs4_get_session(const struct nfs_server *server)
+{
+        return server->nfs_client->cl_session;
+}
+
+extern int nfs4_setup_sequence(const struct nfs_server *server,
                 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_create_session(struct nfs_client *);
 extern int nfs4_proc_destroy_session(struct nfs4_session *);
+extern int nfs4_init_session(struct nfs_server *server);
+extern int nfs4_proc_get_lease_time(struct nfs_client *clp,
+                struct nfs_fsinfo *fsinfo);
 #else /* CONFIG_NFS_v4_1 */
-static inline int nfs4_setup_sequence(struct nfs_client *clp,
+static inline struct nfs4_session *nfs4_get_session(const struct nfs_server *server)
+{
+        return NULL;
+}
+
+static inline int nfs4_setup_sequence(const struct nfs_server *server,
                 struct nfs4_sequence_args *args, struct nfs4_sequence_res *res,
                 int cache_reply, struct rpc_task *task)
 {
         return 0;
 }
+
+static inline int nfs4_init_session(struct nfs_server *server)
+{
+        return 0;
+}
 #endif /* CONFIG_NFS_V4_1 */
 
-extern struct nfs4_state_maintenance_ops *nfs4_state_renewal_ops[];
+extern const struct nfs4_minor_version_ops *nfs_v4_minor_ops[];
 
 extern const u32 nfs4_fattr_bitmap[2];
 extern const u32 nfs4_statfs_bitmap[2];
@@ -261,26 +310,30 @@ extern void nfs4_state_set_mode_locked(struct nfs4_state *, fmode_t);
 extern void nfs4_schedule_state_recovery(struct nfs_client *);
 extern void nfs4_schedule_state_manager(struct nfs_client *);
 extern int nfs4_state_mark_reclaim_nograce(struct nfs_client *clp, struct nfs4_state *state);
+extern int nfs4_state_mark_reclaim_reboot(struct nfs_client *clp, struct nfs4_state *state);
+extern void nfs41_handle_sequence_flag_errors(struct nfs_client *clp, u32 flags);
+extern void nfs41_handle_recall_slot(struct nfs_client *clp);
 extern void nfs4_put_lock_state(struct nfs4_lock_state *lsp);
 extern int nfs4_set_lock_state(struct nfs4_state *state, struct file_lock *fl);
-extern void nfs4_copy_stateid(nfs4_stateid *, struct nfs4_state *, fl_owner_t);
+extern void nfs4_copy_stateid(nfs4_stateid *, struct nfs4_state *, fl_owner_t, pid_t);
 
-extern struct nfs_seqid *nfs_alloc_seqid(struct nfs_seqid_counter *counter);
+extern struct nfs_seqid *nfs_alloc_seqid(struct nfs_seqid_counter *counter, gfp_t gfp_mask);
 extern int nfs_wait_on_sequence(struct nfs_seqid *seqid, struct rpc_task *task);
 extern void nfs_increment_open_seqid(int status, struct nfs_seqid *seqid);
 extern void nfs_increment_lock_seqid(int status, struct nfs_seqid *seqid);
+extern void nfs_release_seqid(struct nfs_seqid *seqid);
 extern void nfs_free_seqid(struct nfs_seqid *seqid);
 
 extern const nfs4_stateid zero_stateid;
 
 /* nfs4xdr.c */
-extern __be32 *nfs4_decode_dirent(__be32 *p, struct nfs_entry *entry, int plus);
 extern struct rpc_procinfo nfs4_procedures[];
 
 struct nfs4_mount_data;
 
 /* callback_xdr.c */
 extern struct svc_version nfs4_callback_version1;
+extern struct svc_version nfs4_callback_version4;
 
 #else
 
diff --git a/fs/nfs/nfs4filelayout.c b/fs/nfs/nfs4filelayout.c
new file mode 100644
index 000000000000..23f930caf1e2
--- /dev/null
+++ b/fs/nfs/nfs4filelayout.c
@@ -0,0 +1,280 @@
+/*
+ *  Module for the pnfs nfs4 file layout driver.
+ *  Defines all I/O and Policy interface operations, plus code
+ *  to register itself with the pNFS client.
+ *
+ *  Copyright (c) 2002
+ *  The Regents of the University of Michigan
+ *  All Rights Reserved
+ *
+ *  Dean Hildebrand <dhildebz@umich.edu>
+ *
+ *  Permission is granted to use, copy, create derivative works, and
+ *  redistribute this software and such derivative works for any purpose,
+ *  so long as the name of the University of Michigan is not used in
+ *  any advertising or publicity pertaining to the use or distribution
+ *  of this software without specific, written prior authorization. If
+ *  the above copyright notice or any other identification of the
+ *  University of Michigan is included in any copy of any portion of
+ *  this software, then the disclaimer below must also be included.
+ *
+ *  This software is provided as is, without representation or warranty
+ *  of any kind either express or implied, including without limitation
+ *  the implied warranties of merchantability, fitness for a particular
+ *  purpose, or noninfringement.  The Regents of the University of
+ *  Michigan shall not be liable for any damages, including special,
+ *  indirect, incidental, or consequential damages, with respect to any
+ *  claim arising out of or in connection with the use of the software,
+ *  even if it has been or is hereafter advised of the possibility of
+ *  such damages.
+ */
+
+#include <linux/nfs_fs.h>
+
+#include "internal.h"
+#include "nfs4filelayout.h"
+
+#define NFSDBG_FACILITY         NFSDBG_PNFS_LD
+
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Dean Hildebrand <dhildebz@umich.edu>");
+MODULE_DESCRIPTION("The NFSv4 file layout driver");
+
+static int
+filelayout_set_layoutdriver(struct nfs_server *nfss)
+{
+        int status = pnfs_alloc_init_deviceid_cache(nfss->nfs_client,
+                                                nfs4_fl_free_deviceid_callback);
+        if (status) {
+                printk(KERN_WARNING "%s: deviceid cache could not be "
+                        "initialized\n", __func__);
+                return status;
+        }
+        dprintk("%s: deviceid cache has been initialized successfully\n",
+                __func__);
+        return 0;
+}
+
+/* Clear out the layout by destroying its device list */
+static int
+filelayout_clear_layoutdriver(struct nfs_server *nfss)
+{
+        dprintk("--> %s\n", __func__);
+
+        if (nfss->nfs_client->cl_devid_cache)
+                pnfs_put_deviceid_cache(nfss->nfs_client);
+        return 0;
+}
+
+/*
+ * filelayout_check_layout()
+ *
+ * Make sure layout segment parameters are sane WRT the device.
+ * At this point no generic layer initialization of the lseg has occurred,
+ * and nothing has been added to the layout_hdr cache.
+ *
+ */
+static int
+filelayout_check_layout(struct pnfs_layout_hdr *lo,
+                        struct nfs4_filelayout_segment *fl,
+                        struct nfs4_layoutget_res *lgr,
+                        struct nfs4_deviceid *id)
+{
+        struct nfs4_file_layout_dsaddr *dsaddr;
+        int status = -EINVAL;
+        struct nfs_server *nfss = NFS_SERVER(lo->plh_inode);
+
+        dprintk("--> %s\n", __func__);
+
+        if (fl->pattern_offset > lgr->range.offset) {
+                dprintk("%s pattern_offset %lld to large\n",
+                                __func__, fl->pattern_offset);
+                goto out;
+        }
+
+        if (fl->stripe_unit % PAGE_SIZE) {
+                dprintk("%s Stripe unit (%u) not page aligned\n",
+                        __func__, fl->stripe_unit);
+                goto out;
+        }
+
+        /* find and reference the deviceid */
+        dsaddr = nfs4_fl_find_get_deviceid(nfss->nfs_client, id);
+        if (dsaddr == NULL) {
+                dsaddr = get_device_info(lo->plh_inode, id);
+                if (dsaddr == NULL)
+                        goto out;
+        }
+        fl->dsaddr = dsaddr;
+
+        if (fl->first_stripe_index < 0 ||
+            fl->first_stripe_index >= dsaddr->stripe_count) {
+                dprintk("%s Bad first_stripe_index %d\n",
+                                __func__, fl->first_stripe_index);
+                goto out_put;
+        }
+
+        if ((fl->stripe_type == STRIPE_SPARSE &&
+            fl->num_fh > 1 && fl->num_fh != dsaddr->ds_num) ||
+            (fl->stripe_type == STRIPE_DENSE &&
+            fl->num_fh != dsaddr->stripe_count)) {
+                dprintk("%s num_fh %u not valid for given packing\n",
+                        __func__, fl->num_fh);
+                goto out_put;
+        }
+
+        if (fl->stripe_unit % nfss->rsize || fl->stripe_unit % nfss->wsize) {
+                dprintk("%s Stripe unit (%u) not aligned with rsize %u "
+                        "wsize %u\n", __func__, fl->stripe_unit, nfss->rsize,
+                        nfss->wsize);
+        }
+
+        status = 0;
+out:
+        dprintk("--> %s returns %d\n", __func__, status);
+        return status;
+out_put:
+        pnfs_put_deviceid(nfss->nfs_client->cl_devid_cache, &dsaddr->deviceid);
+        goto out;
+}
+
+static void filelayout_free_fh_array(struct nfs4_filelayout_segment *fl)
+{
+        int i;
+
+        for (i = 0; i < fl->num_fh; i++) {
+                if (!fl->fh_array[i])
+                        break;
+                kfree(fl->fh_array[i]);
+        }
+        kfree(fl->fh_array);
+        fl->fh_array = NULL;
+}
+
+static void
+_filelayout_free_lseg(struct nfs4_filelayout_segment *fl)
+{
+        filelayout_free_fh_array(fl);
+        kfree(fl);
+}
+
+static int
+filelayout_decode_layout(struct pnfs_layout_hdr *flo,
+                         struct nfs4_filelayout_segment *fl,
+                         struct nfs4_layoutget_res *lgr,
+                         struct nfs4_deviceid *id)
+{
+        uint32_t *p = (uint32_t *)lgr->layout.buf;
+        uint32_t nfl_util;
+        int i;
+
+        dprintk("%s: set_layout_map Begin\n", __func__);
+
+        memcpy(id, p, sizeof(*id));
+        p += XDR_QUADLEN(NFS4_DEVICEID4_SIZE);
+        print_deviceid(id);
+
+        nfl_util = be32_to_cpup(p++);
+        if (nfl_util & NFL4_UFLG_COMMIT_THRU_MDS)
+                fl->commit_through_mds = 1;
+        if (nfl_util & NFL4_UFLG_DENSE)
+                fl->stripe_type = STRIPE_DENSE;
+        else
+                fl->stripe_type = STRIPE_SPARSE;
+        fl->stripe_unit = nfl_util & ~NFL4_UFLG_MASK;
+
+        fl->first_stripe_index = be32_to_cpup(p++);
+        p = xdr_decode_hyper(p, &fl->pattern_offset);
+        fl->num_fh = be32_to_cpup(p++);
+
+        dprintk("%s: nfl_util 0x%X num_fh %u fsi %u po %llu\n",
+                __func__, nfl_util, fl->num_fh, fl->first_stripe_index,
+                fl->pattern_offset);
+
+        fl->fh_array = kzalloc(fl->num_fh * sizeof(struct nfs_fh *),
+                               GFP_KERNEL);
+        if (!fl->fh_array)
+                return -ENOMEM;
+
+        for (i = 0; i < fl->num_fh; i++) {
+                /* Do we want to use a mempool here? */
+                fl->fh_array[i] = kmalloc(sizeof(struct nfs_fh), GFP_KERNEL);
+                if (!fl->fh_array[i]) {
+                        filelayout_free_fh_array(fl);
+                        return -ENOMEM;
+                }
+                fl->fh_array[i]->size = be32_to_cpup(p++);
+                if (sizeof(struct nfs_fh) < fl->fh_array[i]->size) {
+                        printk(KERN_ERR "Too big fh %d received %d\n",
+                               i, fl->fh_array[i]->size);
+                        filelayout_free_fh_array(fl);
+                        return -EIO;
+                }
+                memcpy(fl->fh_array[i]->data, p, fl->fh_array[i]->size);
+                p += XDR_QUADLEN(fl->fh_array[i]->size);
+                dprintk("DEBUG: %s: fh len %d\n", __func__,
+                        fl->fh_array[i]->size);
+        }
+
+        return 0;
+}
+
+static struct pnfs_layout_segment *
+filelayout_alloc_lseg(struct pnfs_layout_hdr *layoutid,
+                      struct nfs4_layoutget_res *lgr)
+{
+        struct nfs4_filelayout_segment *fl;
+        int rc;
+        struct nfs4_deviceid id;
+
+        dprintk("--> %s\n", __func__);
+        fl = kzalloc(sizeof(*fl), GFP_KERNEL);
+        if (!fl)
+                return NULL;
+
+        rc = filelayout_decode_layout(layoutid, fl, lgr, &id);
+        if (rc != 0 || filelayout_check_layout(layoutid, fl, lgr, &id)) {
+                _filelayout_free_lseg(fl);
+                return NULL;
+        }
+        return &fl->generic_hdr;
+}
+
+static void
+filelayout_free_lseg(struct pnfs_layout_segment *lseg)
+{
+        struct nfs_server *nfss = NFS_SERVER(lseg->pls_layout->plh_inode);
+        struct nfs4_filelayout_segment *fl = FILELAYOUT_LSEG(lseg);
+
+        dprintk("--> %s\n", __func__);
+        pnfs_put_deviceid(nfss->nfs_client->cl_devid_cache,
+                          &fl->dsaddr->deviceid);
+        _filelayout_free_lseg(fl);
+}
+
+static struct pnfs_layoutdriver_type filelayout_type = {
+        .id = LAYOUT_NFSV4_1_FILES,
+        .name = "LAYOUT_NFSV4_1_FILES",
+        .owner = THIS_MODULE,
+        .set_layoutdriver = filelayout_set_layoutdriver,
+        .clear_layoutdriver = filelayout_clear_layoutdriver,
+        .alloc_lseg              = filelayout_alloc_lseg,
+        .free_lseg               = filelayout_free_lseg,
+};
+
+static int __init nfs4filelayout_init(void)
+{
+        printk(KERN_INFO "%s: NFSv4 File Layout Driver Registering...\n",
+               __func__);
+        return pnfs_register_layoutdriver(&filelayout_type);
+}
+
+static void __exit nfs4filelayout_exit(void)
+{
+        printk(KERN_INFO "%s: NFSv4 File Layout Driver Unregistering...\n",
+               __func__);
+        pnfs_unregister_layoutdriver(&filelayout_type);
+}
+
+module_init(nfs4filelayout_init);
+module_exit(nfs4filelayout_exit);
diff --git a/fs/nfs/nfs4filelayout.h b/fs/nfs/nfs4filelayout.h
new file mode 100644
index 000000000000..bbf60dd2ab9d
--- /dev/null
+++ b/fs/nfs/nfs4filelayout.h
@@ -0,0 +1,94 @@
+/*
+ *  NFSv4 file layout driver data structures.
+ *
+ *  Copyright (c) 2002
+ *  The Regents of the University of Michigan
+ *  All Rights Reserved
+ *
+ *  Dean Hildebrand <dhildebz@umich.edu>
+ *
+ *  Permission is granted to use, copy, create derivative works, and
+ *  redistribute this software and such derivative works for any purpose,
+ *  so long as the name of the University of Michigan is not used in
+ *  any advertising or publicity pertaining to the use or distribution
+ *  of this software without specific, written prior authorization. If
+ *  the above copyright notice or any other identification of the
+ *  University of Michigan is included in any copy of any portion of
+ *  this software, then the disclaimer below must also be included.
+ *
+ *  This software is provided as is, without representation or warranty
+ *  of any kind either express or implied, including without limitation
+ *  the implied warranties of merchantability, fitness for a particular
+ *  purpose, or noninfringement.  The Regents of the University of
+ *  Michigan shall not be liable for any damages, including special,
+ *  indirect, incidental, or consequential damages, with respect to any
+ *  claim arising out of or in connection with the use of the software,
+ *  even if it has been or is hereafter advised of the possibility of
+ *  such damages.
+ */
+
+#ifndef FS_NFS_NFS4FILELAYOUT_H
+#define FS_NFS_NFS4FILELAYOUT_H
+
+#include "pnfs.h"
+
+/*
+ * Field testing shows we need to support upto 4096 stripe indices.
+ * We store each index as a u8 (u32 on the wire) to keep the memory footprint
+ * reasonable. This in turn means we support a maximum of 256
+ * RFC 5661 multipath_list4 structures.
+ */
+#define NFS4_PNFS_MAX_STRIPE_CNT 4096
+#define NFS4_PNFS_MAX_MULTI_CNT  256 /* 256 fit into a u8 stripe_index */
+
+enum stripetype4 {
+        STRIPE_SPARSE = 1,
+        STRIPE_DENSE = 2
+};
+
+/* Individual ip address */
+struct nfs4_pnfs_ds {
+        struct list_head        ds_node;  /* nfs4_pnfs_dev_hlist dev_dslist */
+        u32                     ds_ip_addr;
+        u32                     ds_port;
+        struct nfs_client       *ds_clp;
+        atomic_t                ds_count;
+};
+
+struct nfs4_file_layout_dsaddr {
+        struct pnfs_deviceid_node       deviceid;
+        u32                             stripe_count;
+        u8                              *stripe_indices;
+        u32                             ds_num;
+        struct nfs4_pnfs_ds             *ds_list[1];
+};
+
+struct nfs4_filelayout_segment {
+        struct pnfs_layout_segment generic_hdr;
+        u32 stripe_type;
+        u32 commit_through_mds;
+        u32 stripe_unit;
+        u32 first_stripe_index;
+        u64 pattern_offset;
+        struct nfs4_file_layout_dsaddr *dsaddr; /* Point to GETDEVINFO data */
+        unsigned int num_fh;
+        struct nfs_fh **fh_array;
+};
+
+static inline struct nfs4_filelayout_segment *
+FILELAYOUT_LSEG(struct pnfs_layout_segment *lseg)
+{
+        return container_of(lseg,
+                            struct nfs4_filelayout_segment,
+                            generic_hdr);
+}
+
+extern void nfs4_fl_free_deviceid_callback(struct pnfs_deviceid_node *);
+extern void print_ds(struct nfs4_pnfs_ds *ds);
+extern void print_deviceid(struct nfs4_deviceid *dev_id);
+extern struct nfs4_file_layout_dsaddr *
+nfs4_fl_find_get_deviceid(struct nfs_client *, struct nfs4_deviceid *dev_id);
+struct nfs4_file_layout_dsaddr *
+get_device_info(struct inode *inode, struct nfs4_deviceid *dev_id);
+
+#endif /* FS_NFS_NFS4FILELAYOUT_H */
diff --git a/fs/nfs/nfs4filelayoutdev.c b/fs/nfs/nfs4filelayoutdev.c
new file mode 100644
index 000000000000..51fe64ace55a
--- /dev/null
+++ b/fs/nfs/nfs4filelayoutdev.c
@@ -0,0 +1,448 @@
+/*
+ *  Device operations for the pnfs nfs4 file layout driver.
+ *
+ *  Copyright (c) 2002
+ *  The Regents of the University of Michigan
+ *  All Rights Reserved
+ *
+ *  Dean Hildebrand <dhildebz@umich.edu>
+ *  Garth Goodson   <Garth.Goodson@netapp.com>
+ *
+ *  Permission is granted to use, copy, create derivative works, and
+ *  redistribute this software and such derivative works for any purpose,
+ *  so long as the name of the University of Michigan is not used in
+ *  any advertising or publicity pertaining to the use or distribution
+ *  of this software without specific, written prior authorization. If
+ *  the above copyright notice or any other identification of the
+ *  University of Michigan is included in any copy of any portion of
+ *  this software, then the disclaimer below must also be included.
+ *
+ *  This software is provided as is, without representation or warranty
+ *  of any kind either express or implied, including without limitation
+ *  the implied warranties of merchantability, fitness for a particular
+ *  purpose, or noninfringement.  The Regents of the University of
+ *  Michigan shall not be liable for any damages, including special,
+ *  indirect, incidental, or consequential damages, with respect to any
+ *  claim arising out of or in connection with the use of the software,
+ *  even if it has been or is hereafter advised of the possibility of
+ *  such damages.
+ */
+
+#include <linux/nfs_fs.h>
+#include <linux/vmalloc.h>
+
+#include "internal.h"
+#include "nfs4filelayout.h"
+
+#define NFSDBG_FACILITY         NFSDBG_PNFS_LD
+
+/*
+ * Data server cache
+ *
+ * Data servers can be mapped to different device ids.
+ * nfs4_pnfs_ds reference counting
+ *   - set to 1 on allocation
+ *   - incremented when a device id maps a data server already in the cache.
+ *   - decremented when deviceid is removed from the cache.
+ */
+DEFINE_SPINLOCK(nfs4_ds_cache_lock);
+static LIST_HEAD(nfs4_data_server_cache);
+
+/* Debug routines */
+void
+print_ds(struct nfs4_pnfs_ds *ds)
+{
+        if (ds == NULL) {
+                printk("%s NULL device\n", __func__);
+                return;
+        }
+        printk("        ip_addr %x port %hu\n"
+                "        ref count %d\n"
+                "        client %p\n"
+                "        cl_exchange_flags %x\n",
+                ntohl(ds->ds_ip_addr), ntohs(ds->ds_port),
+                atomic_read(&ds->ds_count), ds->ds_clp,
+                ds->ds_clp ? ds->ds_clp->cl_exchange_flags : 0);
+}
+
+void
+print_ds_list(struct nfs4_file_layout_dsaddr *dsaddr)
+{
+        int i;
+
+        ifdebug(FACILITY) {
+                printk("%s dsaddr->ds_num %d\n", __func__,
+                       dsaddr->ds_num);
+                for (i = 0; i < dsaddr->ds_num; i++)
+                        print_ds(dsaddr->ds_list[i]);
+        }
+}
+
+void print_deviceid(struct nfs4_deviceid *id)
+{
+        u32 *p = (u32 *)id;
+
+        dprintk("%s: device id= [%x%x%x%x]\n", __func__,
+                p[0], p[1], p[2], p[3]);
+}
+
+/* nfs4_ds_cache_lock is held */
+static struct nfs4_pnfs_ds *
+_data_server_lookup_locked(u32 ip_addr, u32 port)
+{
+        struct nfs4_pnfs_ds *ds;
+
+        dprintk("_data_server_lookup: ip_addr=%x port=%hu\n",
+                        ntohl(ip_addr), ntohs(port));
+
+        list_for_each_entry(ds, &nfs4_data_server_cache, ds_node) {
+                if (ds->ds_ip_addr == ip_addr &&
+                    ds->ds_port == port) {
+                        return ds;
+                }
+        }
+        return NULL;
+}
+
+static void
+destroy_ds(struct nfs4_pnfs_ds *ds)
+{
+        dprintk("--> %s\n", __func__);
+        ifdebug(FACILITY)
+                print_ds(ds);
+
+        if (ds->ds_clp)
+                nfs_put_client(ds->ds_clp);
+        kfree(ds);
+}
+
+static void
+nfs4_fl_free_deviceid(struct nfs4_file_layout_dsaddr *dsaddr)
+{
+        struct nfs4_pnfs_ds *ds;
+        int i;
+
+        print_deviceid(&dsaddr->deviceid.de_id);
+
+        for (i = 0; i < dsaddr->ds_num; i++) {
+                ds = dsaddr->ds_list[i];
+                if (ds != NULL) {
+                        if (atomic_dec_and_lock(&ds->ds_count,
+                                                &nfs4_ds_cache_lock)) {
+                                list_del_init(&ds->ds_node);
+                                spin_unlock(&nfs4_ds_cache_lock);
+                                destroy_ds(ds);
+                        }
+                }
+        }
+        kfree(dsaddr->stripe_indices);
+        kfree(dsaddr);
+}
+
+void
+nfs4_fl_free_deviceid_callback(struct pnfs_deviceid_node *device)
+{
+        struct nfs4_file_layout_dsaddr *dsaddr =
+                container_of(device, struct nfs4_file_layout_dsaddr, deviceid);
+
+        nfs4_fl_free_deviceid(dsaddr);
+}
+
+static struct nfs4_pnfs_ds *
+nfs4_pnfs_ds_add(struct inode *inode, u32 ip_addr, u32 port)
+{
+        struct nfs4_pnfs_ds *tmp_ds, *ds;
+
+        ds = kzalloc(sizeof(*tmp_ds), GFP_KERNEL);
+        if (!ds)
+                goto out;
+
+        spin_lock(&nfs4_ds_cache_lock);
+        tmp_ds = _data_server_lookup_locked(ip_addr, port);
+        if (tmp_ds == NULL) {
+                ds->ds_ip_addr = ip_addr;
+                ds->ds_port = port;
+                atomic_set(&ds->ds_count, 1);
+                INIT_LIST_HEAD(&ds->ds_node);
+                ds->ds_clp = NULL;
+                list_add(&ds->ds_node, &nfs4_data_server_cache);
+                dprintk("%s add new data server ip 0x%x\n", __func__,
+                        ds->ds_ip_addr);
+        } else {
+                kfree(ds);
+                atomic_inc(&tmp_ds->ds_count);
+                dprintk("%s data server found ip 0x%x, inc'ed ds_count to %d\n",
+                        __func__, tmp_ds->ds_ip_addr,
+                        atomic_read(&tmp_ds->ds_count));
+                ds = tmp_ds;
+        }
+        spin_unlock(&nfs4_ds_cache_lock);
+out:
+        return ds;
+}
+
+/*
+ * Currently only support ipv4, and one multi-path address.
+ */
+static struct nfs4_pnfs_ds *
+decode_and_add_ds(__be32 **pp, struct inode *inode)
+{
+        struct nfs4_pnfs_ds *ds = NULL;
+        char *buf;
+        const char *ipend, *pstr;
+        u32 ip_addr, port;
+        int nlen, rlen, i;
+        int tmp[2];
+        __be32 *r_netid, *r_addr, *p = *pp;
+
+        /* r_netid */
+        nlen = be32_to_cpup(p++);
+        r_netid = p;
+        p += XDR_QUADLEN(nlen);
+
+        /* r_addr */
+        rlen = be32_to_cpup(p++);
+        r_addr = p;
+        p += XDR_QUADLEN(rlen);
+        *pp = p;
+
+        /* Check that netid is "tcp" */
+        if (nlen != 3 ||  memcmp((char *)r_netid, "tcp", 3)) {
+                dprintk("%s: ERROR: non ipv4 TCP r_netid\n", __func__);
+                goto out_err;
+        }
+
+        /* ipv6 length plus port is legal */
+        if (rlen > INET6_ADDRSTRLEN + 8) {
+                dprintk("%s Invalid address, length %d\n", __func__,
+                        rlen);
+                goto out_err;
+        }
+        buf = kmalloc(rlen + 1, GFP_KERNEL);
+        buf[rlen] = '\0';
+        memcpy(buf, r_addr, rlen);
+
+        /* replace the port dots with dashes for the in4_pton() delimiter*/
+        for (i = 0; i < 2; i++) {
+                char *res = strrchr(buf, '.');
+                *res = '-';
+        }
+
+        /* Currently only support ipv4 address */
+        if (in4_pton(buf, rlen, (u8 *)&ip_addr, '-', &ipend) == 0) {
+                dprintk("%s: Only ipv4 addresses supported\n", __func__);
+                goto out_free;
+        }
+
+        /* port */
+        pstr = ipend;
+        sscanf(pstr, "-%d-%d", &tmp[0], &tmp[1]);
+        port = htons((tmp[0] << 8) | (tmp[1]));
+
+        ds = nfs4_pnfs_ds_add(inode, ip_addr, port);
+        dprintk("%s Decoded address and port %s\n", __func__, buf);
+out_free:
+        kfree(buf);
+out_err:
+        return ds;
+}
+
+/* Decode opaque device data and return the result */
+static struct nfs4_file_layout_dsaddr*
+decode_device(struct inode *ino, struct pnfs_device *pdev)
+{
+        int i, dummy;
+        u32 cnt, num;
+        u8 *indexp;
+        __be32 *p = (__be32 *)pdev->area, *indicesp;
+        struct nfs4_file_layout_dsaddr *dsaddr;
+
+        /* Get the stripe count (number of stripe index) */
+        cnt = be32_to_cpup(p++);
+        dprintk("%s stripe count  %d\n", __func__, cnt);
+        if (cnt > NFS4_PNFS_MAX_STRIPE_CNT) {
+                printk(KERN_WARNING "%s: stripe count %d greater than "
+                       "supported maximum %d\n", __func__,
+                        cnt, NFS4_PNFS_MAX_STRIPE_CNT);
+                goto out_err;
+        }
+
+        /* Check the multipath list count */
+        indicesp = p;
+        p += XDR_QUADLEN(cnt << 2);
+        num = be32_to_cpup(p++);
+        dprintk("%s ds_num %u\n", __func__, num);
+        if (num > NFS4_PNFS_MAX_MULTI_CNT) {
+                printk(KERN_WARNING "%s: multipath count %d greater than "
+                        "supported maximum %d\n", __func__,
+                        num, NFS4_PNFS_MAX_MULTI_CNT);
+                goto out_err;
+        }
+        dsaddr = kzalloc(sizeof(*dsaddr) +
+                        (sizeof(struct nfs4_pnfs_ds *) * (num - 1)),
+                        GFP_KERNEL);
+        if (!dsaddr)
+                goto out_err;
+
+        dsaddr->stripe_indices = kzalloc(sizeof(u8) * cnt, GFP_KERNEL);
+        if (!dsaddr->stripe_indices)
+                goto out_err_free;
+
+        dsaddr->stripe_count = cnt;
+        dsaddr->ds_num = num;
+
+        memcpy(&dsaddr->deviceid.de_id, &pdev->dev_id, sizeof(pdev->dev_id));
+
+        /* Go back an read stripe indices */
+        p = indicesp;
+        indexp = &dsaddr->stripe_indices[0];
+        for (i = 0; i < dsaddr->stripe_count; i++) {
+                *indexp = be32_to_cpup(p++);
+                if (*indexp >= num)
+                        goto out_err_free;
+                indexp++;
+        }
+        /* Skip already read multipath list count */
+        p++;
+
+        for (i = 0; i < dsaddr->ds_num; i++) {
+                int j;
+
+                dummy = be32_to_cpup(p++); /* multipath count */
+                if (dummy > 1) {
+                        printk(KERN_WARNING
+                               "%s: Multipath count %d not supported, "
+                               "skipping all greater than 1\n", __func__,
+                                dummy);
+                }
+                for (j = 0; j < dummy; j++) {
+                        if (j == 0) {
+                                dsaddr->ds_list[i] = decode_and_add_ds(&p, ino);
+                                if (dsaddr->ds_list[i] == NULL)
+                                        goto out_err_free;
+                        } else {
+                                u32 len;
+                                /* skip extra multipath */
+                                len = be32_to_cpup(p++);
+                                p += XDR_QUADLEN(len);
+                                len = be32_to_cpup(p++);
+                                p += XDR_QUADLEN(len);
+                                continue;
+                        }
+                }
+        }
+        return dsaddr;
+
+out_err_free:
+        nfs4_fl_free_deviceid(dsaddr);
+out_err:
+        dprintk("%s ERROR: returning NULL\n", __func__);
+        return NULL;
+}
+
+/*
+ * Decode the opaque device specified in 'dev'
+ * and add it to the list of available devices.
+ * If the deviceid is already cached, nfs4_add_deviceid will return
+ * a pointer to the cached struct and throw away the new.
+ */
+static struct nfs4_file_layout_dsaddr*
+decode_and_add_device(struct inode *inode, struct pnfs_device *dev)
+{
+        struct nfs4_file_layout_dsaddr *dsaddr;
+        struct pnfs_deviceid_node *d;
+
+        dsaddr = decode_device(inode, dev);
+        if (!dsaddr) {
+                printk(KERN_WARNING "%s: Could not decode or add device\n",
+                        __func__);
+                return NULL;
+        }
+
+        d = pnfs_add_deviceid(NFS_SERVER(inode)->nfs_client->cl_devid_cache,
+                              &dsaddr->deviceid);
+
+        return container_of(d, struct nfs4_file_layout_dsaddr, deviceid);
+}
+
+/*
+ * Retrieve the information for dev_id, add it to the list
+ * of available devices, and return it.
+ */
+struct nfs4_file_layout_dsaddr *
+get_device_info(struct inode *inode, struct nfs4_deviceid *dev_id)
+{
+        struct pnfs_device *pdev = NULL;
+        u32 max_resp_sz;
+        int max_pages;
+        struct page **pages = NULL;
+        struct nfs4_file_layout_dsaddr *dsaddr = NULL;
+        int rc, i;
+        struct nfs_server *server = NFS_SERVER(inode);
+
+        /*
+         * Use the session max response size as the basis for setting
+         * GETDEVICEINFO's maxcount
+         */
+        max_resp_sz = server->nfs_client->cl_session->fc_attrs.max_resp_sz;
+        max_pages = max_resp_sz >> PAGE_SHIFT;
+        dprintk("%s inode %p max_resp_sz %u max_pages %d\n",
+                __func__, inode, max_resp_sz, max_pages);
+
+        pdev = kzalloc(sizeof(struct pnfs_device), GFP_KERNEL);
+        if (pdev == NULL)
+                return NULL;
+
+        pages = kzalloc(max_pages * sizeof(struct page *), GFP_KERNEL);
+        if (pages == NULL) {
+                kfree(pdev);
+                return NULL;
+        }
+        for (i = 0; i < max_pages; i++) {
+                pages[i] = alloc_page(GFP_KERNEL);
+                if (!pages[i])
+                        goto out_free;
+        }
+
+        /* set pdev->area */
+        pdev->area = vmap(pages, max_pages, VM_MAP, PAGE_KERNEL);
+        if (!pdev->area)
+                goto out_free;
+
+        memcpy(&pdev->dev_id, dev_id, sizeof(*dev_id));
+        pdev->layout_type = LAYOUT_NFSV4_1_FILES;
+        pdev->pages = pages;
+        pdev->pgbase = 0;
+        pdev->pglen = PAGE_SIZE * max_pages;
+        pdev->mincount = 0;
+
+        rc = nfs4_proc_getdeviceinfo(server, pdev);
+        dprintk("%s getdevice info returns %d\n", __func__, rc);
+        if (rc)
+                goto out_free;
+
+        /*
+         * Found new device, need to decode it and then add it to the
+         * list of known devices for this mountpoint.
+         */
+        dsaddr = decode_and_add_device(inode, pdev);
+out_free:
+        if (pdev->area != NULL)
+                vunmap(pdev->area);
+        for (i = 0; i < max_pages; i++)
+                __free_page(pages[i]);
+        kfree(pages);
+        kfree(pdev);
+        dprintk("<-- %s dsaddr %p\n", __func__, dsaddr);
+        return dsaddr;
+}
+
+struct nfs4_file_layout_dsaddr *
+nfs4_fl_find_get_deviceid(struct nfs_client *clp, struct nfs4_deviceid *id)
+{
+        struct pnfs_deviceid_node *d;
+
+        d = pnfs_find_get_deviceid(clp->cl_devid_cache, id);
+        return (d == NULL) ? NULL :
+                container_of(d, struct nfs4_file_layout_dsaddr, deviceid);
+}
diff --git a/fs/nfs/nfs4namespace.c b/fs/nfs/nfs4namespace.c
index 2a2a0a7143ad..3c2a1724fbd2 100644
--- a/fs/nfs/nfs4namespace.c
+++ b/fs/nfs/nfs4namespace.c
@@ -11,12 +11,14 @@
 #include <linux/mount.h>
 #include <linux/namei.h>
 #include <linux/nfs_fs.h>
+#include <linux/slab.h>
 #include <linux/string.h>
 #include <linux/sunrpc/clnt.h>
 #include <linux/vfs.h>
 #include <linux/inet.h>
 #include "internal.h"
 #include "nfs4_fs.h"
+#include "dns_resolve.h"
 
 #define NFSDBG_FACILITY         NFSDBG_VFS
 
@@ -95,10 +97,25 @@ static int nfs4_validate_fspath(const struct vfsmount *mnt_parent,
         return 0;
 }
 
+static size_t nfs_parse_server_name(char *string, size_t len,
+                struct sockaddr *sa, size_t salen)
+{
+        ssize_t ret;
+
+        ret = rpc_pton(string, len, sa, salen);
+        if (ret == 0) {
+                ret = nfs_dns_resolve_name(string, len, sa, salen);
+                if (ret < 0)
+                        ret = 0;
+        }
+        return ret;
+}
+
 static struct vfsmount *try_location(struct nfs_clone_mount *mountdata,
                                      char *page, char *page2,
                                      const struct nfs4_fs_location *location)
 {
+        const size_t addr_bufsize = sizeof(struct sockaddr_storage);
         struct vfsmount *mnt = ERR_PTR(-ENOENT);
         char *mnt_path;
         unsigned int maxbuflen;
@@ -106,26 +123,29 @@ static struct vfsmount *try_location(struct nfs_clone_mount *mountdata,
 
         mnt_path = nfs4_pathname_string(&location->rootpath, page2, PAGE_SIZE);
         if (IS_ERR(mnt_path))
-                return mnt;
+                return ERR_CAST(mnt_path);
         mountdata->mnt_path = mnt_path;
         maxbuflen = mnt_path - 1 - page2;
 
+        mountdata->addr = kmalloc(addr_bufsize, GFP_KERNEL);
+        if (mountdata->addr == NULL)
+                return ERR_PTR(-ENOMEM);
+
         for (s = 0; s < location->nservers; s++) {
                 const struct nfs4_string *buf = &location->servers[s];
-                struct sockaddr_storage addr;
 
                 if (buf->len <= 0 || buf->len >= maxbuflen)
                         continue;
 
-                mountdata->addr = (struct sockaddr *)&addr;
-
                 if (memchr(buf->data, IPV6_SCOPE_DELIMITER, buf->len))
                         continue;
-                nfs_parse_ip_address(buf->data, buf->len,
-                                mountdata->addr, &mountdata->addrlen);
-                if (mountdata->addr->sa_family == AF_UNSPEC)
+
+                mountdata->addrlen = nfs_parse_server_name(buf->data, buf->len,
+                                mountdata->addr, addr_bufsize);
+                if (mountdata->addrlen == 0)
                         continue;
-                nfs_set_port(mountdata->addr, NFS_PORT);
+
+                rpc_set_port(mountdata->addr, NFS_PORT);
 
                 memcpy(page2, buf->data, buf->len);
                 page2[buf->len] = '\0';
@@ -139,6 +159,7 @@ static struct vfsmount *try_location(struct nfs_clone_mount *mountdata,
                 if (!IS_ERR(mnt))
                         break;
         }
+        kfree(mountdata->addr);
         return mnt;
 }
 
@@ -204,8 +225,8 @@ out:
 
 /*
  * nfs_do_refmount - handle crossing a referral on server
+ * @mnt_parent - mountpoint of referral
  * @dentry - dentry of referral
- * @nd - nameidata info
  *
  */
 struct vfsmount *nfs_do_refmount(const struct vfsmount *mnt_parent, struct dentry *dentry)
diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c
index 92ce43517814..9d992b0346e3 100644
--- a/fs/nfs/nfs4proc.c
+++ b/fs/nfs/nfs4proc.c
@@ -36,48 +36,60 @@
  */
 
 #include <linux/mm.h>
-#include <linux/utsname.h>
 #include <linux/delay.h>
 #include <linux/errno.h>
 #include <linux/string.h>
+#include <linux/slab.h>
 #include <linux/sunrpc/clnt.h>
 #include <linux/nfs.h>
 #include <linux/nfs4.h>
 #include <linux/nfs_fs.h>
 #include <linux/nfs_page.h>
-#include <linux/smp_lock.h>
 #include <linux/namei.h>
 #include <linux/mount.h>
 #include <linux/module.h>
 #include <linux/sunrpc/bc_xprt.h>
+#include <linux/xattr.h>
 
 #include "nfs4_fs.h"
 #include "delegation.h"
 #include "internal.h"
 #include "iostat.h"
 #include "callback.h"
+#include "pnfs.h"
 
 #define NFSDBG_FACILITY         NFSDBG_PROC
 
 #define NFS4_POLL_RETRY_MIN     (HZ/10)
 #define NFS4_POLL_RETRY_MAX     (15*HZ)
 
+#define NFS4_MAX_LOOP_ON_RECOVER (10)
+
 struct nfs4_opendata;
 static int _nfs4_proc_open(struct nfs4_opendata *data);
+static int _nfs4_recover_proc_open(struct nfs4_opendata *data);
 static int nfs4_do_fsinfo(struct nfs_server *, struct nfs_fh *, struct nfs_fsinfo *);
 static int nfs4_async_handle_error(struct rpc_task *, const struct nfs_server *, struct nfs4_state *);
 static int _nfs4_proc_lookup(struct inode *dir, const struct qstr *name, struct nfs_fh *fhandle, struct nfs_fattr *fattr);
 static int _nfs4_proc_getattr(struct nfs_server *server, struct nfs_fh *fhandle, struct nfs_fattr *fattr);
+static int nfs4_do_setattr(struct inode *inode, struct rpc_cred *cred,
+                            struct nfs_fattr *fattr, struct iattr *sattr,
+                            struct nfs4_state *state);
 
 /* Prevent leaks of NFSv4 errors into userland */
 static int nfs4_map_errors(int err)
 {
-        if (err < -1000) {
+        if (err >= -1000)
+                return err;
+        switch (err) {
+        case -NFS4ERR_RESOURCE:
+                return -EREMOTEIO;
+        default:
                 dprintk("%s could not handle NFSv4 error %d\n",
                                 __func__, -err);
-                return -EIO;
+                break;
         }
-        return err;
+        return -EIO;
 }
 
 /*
@@ -119,7 +131,8 @@ const u32 nfs4_fsinfo_bitmap[2] = { FATTR4_WORD0_MAXFILESIZE
                         | FATTR4_WORD0_MAXREAD
                         | FATTR4_WORD0_MAXWRITE
                         | FATTR4_WORD0_LEASE_TIME,
-                        0
+                        FATTR4_WORD1_TIME_DELTA
+                        | FATTR4_WORD1_FS_LAYOUT_TYPES
 };
 
 const u32 nfs4_fs_locations_bitmap[2] = {
@@ -243,19 +256,12 @@ static int nfs4_handle_exception(const struct nfs_server *server, int errorcode,
                         if (state == NULL)
                                 break;
                         nfs4_state_mark_reclaim_nograce(clp, state);
-                case -NFS4ERR_STALE_CLIENTID:
+                        goto do_state_recovery;
                 case -NFS4ERR_STALE_STATEID:
+                case -NFS4ERR_STALE_CLIENTID:
                 case -NFS4ERR_EXPIRED:
-                        nfs4_schedule_state_recovery(clp);
-                        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 */
+                        goto do_state_recovery;
+#if defined(CONFIG_NFS_V4_1)
                 case -NFS4ERR_BADSESSION:
                 case -NFS4ERR_BADSLOT:
                 case -NFS4ERR_BAD_HIGH_SLOT:
@@ -265,13 +271,21 @@ static int nfs4_handle_exception(const struct nfs_server *server, int errorcode,
                 case -NFS4ERR_SEQ_MISORDERED:
                         dprintk("%s ERROR: %d Reset session\n", __func__,
                                 errorcode);
-                        set_bit(NFS4CLNT_SESSION_SETUP, &clp->cl_state);
+                        nfs4_schedule_state_recovery(clp);
                         exception->retry = 1;
-                        /* FALLTHROUGH */
-#endif /* !defined(CONFIG_NFS_V4_1) */
+                        break;
+#endif /* defined(CONFIG_NFS_V4_1) */
                 case -NFS4ERR_FILE_OPEN:
+                        if (exception->timeout > HZ) {
+                                /* We have retried a decent amount, time to
+                                 * fail
+                                 */
+                                ret = -EBUSY;
+                                break;
+                        }
                 case -NFS4ERR_GRACE:
                 case -NFS4ERR_DELAY:
+                case -EKEYEXPIRED:
                         ret = nfs4_delay(server->client, &exception->timeout);
                         if (ret != 0)
                                 break;
@@ -280,18 +294,28 @@ static int nfs4_handle_exception(const struct nfs_server *server, int errorcode,
         }
         /* We failed to handle the error */
         return nfs4_map_errors(ret);
+do_state_recovery:
+        nfs4_schedule_state_recovery(clp);
+        ret = nfs4_wait_clnt_recover(clp);
+        if (ret == 0)
+                exception->retry = 1;
+        return ret;
 }
 
 
-static void renew_lease(const struct nfs_server *server, unsigned long timestamp)
+static void do_renew_lease(struct nfs_client *clp, unsigned long timestamp)
 {
-        struct nfs_client *clp = server->nfs_client;
         spin_lock(&clp->cl_lock);
         if (time_before(clp->cl_last_renewal,timestamp))
                 clp->cl_last_renewal = timestamp;
         spin_unlock(&clp->cl_lock);
 }
 
+static void renew_lease(const struct nfs_server *server, unsigned long timestamp)
+{
+        do_renew_lease(server->nfs_client, timestamp);
+}
+
 #if defined(CONFIG_NFS_V4_1)
 
 /*
@@ -306,58 +330,87 @@ static void renew_lease(const struct nfs_server *server, unsigned long timestamp
  * 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.
+ *
+ * Must be called while holding tbl->slot_tbl_lock
  */
 static void
-nfs4_free_slot(struct nfs4_slot_table *tbl, u8 free_slotid)
+nfs4_free_slot(struct nfs4_slot_table *tbl, struct nfs4_slot *free_slot)
 {
+        int free_slotid = free_slot - tbl->slots;
         int slotid = free_slotid;
 
-        spin_lock(&tbl->slot_tbl_lock);
+        BUG_ON(slotid < 0 || slotid >= NFS4_MAX_SLOT_TABLE);
         /* 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)
+                if (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)
+/*
+ * Signal state manager thread if session fore channel is drained
+ */
+static void nfs4_check_drain_fc_complete(struct nfs4_session *ses)
 {
-        struct nfs4_slot_table *tbl;
+        struct rpc_task *task;
 
-        if (!nfs4_has_session(clp)) {
-                dprintk("%s: No session\n", __func__);
+        if (!test_bit(NFS4_SESSION_DRAINING, &ses->session_state)) {
+                task = rpc_wake_up_next(&ses->fc_slot_table.slot_tbl_waitq);
+                if (task)
+                        rpc_task_set_priority(task, RPC_PRIORITY_PRIVILEGED);
                 return;
         }
-        tbl = &clp->cl_session->fc_slot_table;
-        if (res->sr_slotid == NFS4_MAX_SLOT_TABLE) {
-                dprintk("%s: No slot\n", __func__);
+
+        if (ses->fc_slot_table.highest_used_slotid != -1)
+                return;
+
+        dprintk("%s COMPLETE: Session Fore Channel Drained\n", __func__);
+        complete(&ses->fc_slot_table.complete);
+}
+
+/*
+ * Signal state manager thread if session back channel is drained
+ */
+void nfs4_check_drain_bc_complete(struct nfs4_session *ses)
+{
+        if (!test_bit(NFS4_SESSION_DRAINING, &ses->session_state) ||
+            ses->bc_slot_table.highest_used_slotid != -1)
+                return;
+        dprintk("%s COMPLETE: Session Back Channel Drained\n", __func__);
+        complete(&ses->bc_slot_table.complete);
+}
+
+static void nfs41_sequence_free_slot(struct nfs4_sequence_res *res)
+{
+        struct nfs4_slot_table *tbl;
+
+        tbl = &res->sr_session->fc_slot_table;
+        if (!res->sr_slot) {
                 /* 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);
+                dprintk("%s: No slot\n", __func__);
                 return;
         }
-        nfs4_free_slot(tbl, res->sr_slotid);
-        res->sr_slotid = NFS4_MAX_SLOT_TABLE;
+
+        spin_lock(&tbl->slot_tbl_lock);
+        nfs4_free_slot(tbl, res->sr_slot);
+        nfs4_check_drain_fc_complete(res->sr_session);
+        spin_unlock(&tbl->slot_tbl_lock);
+        res->sr_slot = NULL;
 }
 
-static void nfs41_sequence_done(struct nfs_client *clp,
-                                struct nfs4_sequence_res *res,
-                                int rpc_status)
+static int nfs41_sequence_done(struct rpc_task *task, struct nfs4_sequence_res *res)
 {
         unsigned long timestamp;
-        struct nfs4_slot_table *tbl;
-        struct nfs4_slot *slot;
+        struct nfs_client *clp;
 
         /*
          * sr_status remains 1 if an RPC level error occurred. The server
@@ -369,26 +422,53 @@ static void nfs41_sequence_done(struct nfs_client *clp,
                 res->sr_status = NFS_OK;
 
         /* -ERESTARTSYS can result in skipping nfs41_sequence_setup */
-        if (res->sr_slotid == NFS4_MAX_SLOT_TABLE)
+        if (!res->sr_slot)
                 goto out;
 
-        tbl = &clp->cl_session->fc_slot_table;
-        slot = tbl->slots + res->sr_slotid;
-
-        if (res->sr_status == 0) {
+        /* Check the SEQUENCE operation status */
+        switch (res->sr_status) {
+        case 0:
                 /* Update the slot's sequence and clientid lease timer */
-                ++slot->seq_nr;
+                ++res->sr_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;
+                clp = res->sr_session->clp;
+                do_renew_lease(clp, timestamp);
+                /* Check sequence flags */
+                if (atomic_read(&clp->cl_count) > 1)
+                        nfs41_handle_sequence_flag_errors(clp, res->sr_status_flags);
+                break;
+        case -NFS4ERR_DELAY:
+                /* The server detected a resend of the RPC call and
+                 * returned NFS4ERR_DELAY as per Section 2.10.6.2
+                 * of RFC5661.
+                 */
+                dprintk("%s: slot=%td seq=%d: Operation in progress\n",
+                        __func__,
+                        res->sr_slot - res->sr_session->fc_slot_table.slots,
+                        res->sr_slot->seq_nr);
+                goto out_retry;
+        default:
+                /* Just update the slot sequence no. */
+                ++res->sr_slot->seq_nr;
         }
 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);
+        nfs41_sequence_free_slot(res);
+        return 1;
+out_retry:
+        if (!rpc_restart_call(task))
+                goto out;
+        rpc_delay(task, NFS4_POLL_RETRY_MAX);
+        return 0;
+}
+
+static int nfs4_sequence_done(struct rpc_task *task,
+                               struct nfs4_sequence_res *res)
+{
+        if (res->sr_session == NULL)
+                return 1;
+        return nfs41_sequence_done(task, res);
 }
 
 /*
@@ -402,7 +482,7 @@ out:
  * Note: must be called with under the slot_tbl_lock.
  */
 static u8
-nfs4_find_slot(struct nfs4_slot_table *tbl, struct rpc_task *task)
+nfs4_find_slot(struct nfs4_slot_table *tbl)
 {
         int slotid;
         u8 ret_id = NFS4_MAX_SLOT_TABLE;
@@ -424,22 +504,6 @@ out:
         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,
@@ -448,37 +512,37 @@ static int nfs41_setup_sequence(struct nfs4_session *session,
 {
         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)
+        if (res->sr_slot != NULL)
                 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;
-                }
+        if (test_bit(NFS4_SESSION_DRAINING, &session->session_state) &&
+            !rpc_task_has_priority(task, RPC_PRIORITY_PRIVILEGED)) {
+                /*
+                 * The state manager will wait until the slot table is empty.
+                 * Schedule the reset thread
+                 */
+                rpc_sleep_on(&tbl->slot_tbl_waitq, task, NULL);
+                spin_unlock(&tbl->slot_tbl_lock);
+                dprintk("%s Schedule Session Reset\n", __func__);
+                return -EAGAIN;
+        }
 
-                /* The slot table is empty; start the reset thread */
-                dprintk("%s Session Reset\n", __func__);
+        if (!rpc_queue_empty(&tbl->slot_tbl_waitq) &&
+            !rpc_task_has_priority(task, RPC_PRIORITY_PRIVILEGED)) {
+                rpc_sleep_on(&tbl->slot_tbl_waitq, task, NULL);
                 spin_unlock(&tbl->slot_tbl_lock);
-                status = nfs4_recover_session(session);
-                if (status)
-                        return status;
-                spin_lock(&tbl->slot_tbl_lock);
+                dprintk("%s enforce FIFO order\n", __func__);
+                return -EAGAIN;
         }
 
-        slotid = nfs4_find_slot(tbl, task);
+        slotid = nfs4_find_slot(tbl);
         if (slotid == NFS4_MAX_SLOT_TABLE) {
                 rpc_sleep_on(&tbl->slot_tbl_waitq, task, NULL);
                 spin_unlock(&tbl->slot_tbl_lock);
@@ -487,6 +551,7 @@ static int nfs41_setup_sequence(struct nfs4_session *session,
         }
         spin_unlock(&tbl->slot_tbl_lock);
 
+        rpc_task_set_priority(task, RPC_PRIORITY_NORMAL);
         slot = tbl->slots + slotid;
         args->sa_session = session;
         args->sa_slotid = slotid;
@@ -495,8 +560,9 @@ static int nfs41_setup_sequence(struct nfs4_session *session,
         dprintk("<-- %s slotid=%d seqid=%d\n", __func__, slotid, slot->seq_nr);
 
         res->sr_session = session;
-        res->sr_slotid = slotid;
+        res->sr_slot = slot;
         res->sr_renewal_time = jiffies;
+        res->sr_status_flags = 0;
         /*
          * sr_status is only set in decode_sequence, and so will remain
          * set to 1 if an rpc level failure occurs.
@@ -505,33 +571,34 @@ static int nfs41_setup_sequence(struct nfs4_session *session,
         return 0;
 }
 
-int nfs4_setup_sequence(struct nfs_client *clp,
+int nfs4_setup_sequence(const struct nfs_server *server,
                         struct nfs4_sequence_args *args,
                         struct nfs4_sequence_res *res,
                         int cache_reply,
                         struct rpc_task *task)
 {
+        struct nfs4_session *session = nfs4_get_session(server);
         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))
+        if (session == NULL) {
+                args->sa_session = NULL;
+                res->sr_session = NULL;
                 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;
         }
+
+        dprintk("--> %s clp %p session %p sr_slot %td\n",
+                __func__, session->clp, session, res->sr_slot ?
+                        res->sr_slot - session->fc_slot_table.slots : -1);
+
+        ret = nfs41_setup_sequence(session, args, res, cache_reply,
+                                   task);
 out:
         dprintk("<-- %s status=%d\n", __func__, ret);
         return ret;
 }
 
 struct nfs41_call_sync_data {
-        struct nfs_client *clp;
+        const struct nfs_server *seq_server;
         struct nfs4_sequence_args *seq_args;
         struct nfs4_sequence_res *seq_res;
         int cache_reply;
@@ -541,20 +608,25 @@ 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,
+        dprintk("--> %s data->seq_server %p\n", __func__, data->seq_server);
+
+        if (nfs4_setup_sequence(data->seq_server, data->seq_args,
                                 data->seq_res, data->cache_reply, task))
                 return;
         rpc_call_start(task);
 }
 
+static void nfs41_call_priv_sync_prepare(struct rpc_task *task, void *calldata)
+{
+        rpc_task_set_priority(task, RPC_PRIORITY_PRIVILEGED);
+        nfs41_call_sync_prepare(task, calldata);
+}
+
 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);
+        nfs41_sequence_done(task, data->seq_res);
 }
 
 struct rpc_call_ops nfs41_call_sync_ops = {
@@ -562,29 +634,36 @@ struct rpc_call_ops nfs41_call_sync_ops = {
         .rpc_call_done = nfs41_call_sync_done,
 };
 
-static int nfs4_call_sync_sequence(struct nfs_client *clp,
-                                   struct rpc_clnt *clnt,
+struct rpc_call_ops nfs41_call_priv_sync_ops = {
+        .rpc_call_prepare = nfs41_call_priv_sync_prepare,
+        .rpc_call_done = nfs41_call_sync_done,
+};
+
+static int nfs4_call_sync_sequence(struct nfs_server *server,
                                    struct rpc_message *msg,
                                    struct nfs4_sequence_args *args,
                                    struct nfs4_sequence_res *res,
-                                   int cache_reply)
+                                   int cache_reply,
+                                   int privileged)
 {
         int ret;
         struct rpc_task *task;
         struct nfs41_call_sync_data data = {
-                .clp = clp,
+                .seq_server = server,
                 .seq_args = args,
                 .seq_res = res,
                 .cache_reply = cache_reply,
         };
         struct rpc_task_setup task_setup = {
-                .rpc_client = clnt,
+                .rpc_client = server->client,
                 .rpc_message = msg,
                 .callback_ops = &nfs41_call_sync_ops,
                 .callback_data = &data
         };
 
-        res->sr_slotid = NFS4_MAX_SLOT_TABLE;
+        res->sr_slot = NULL;
+        if (privileged)
+                task_setup.callback_ops = &nfs41_call_priv_sync_ops;
         task = rpc_run_task(&task_setup);
         if (IS_ERR(task))
                 ret = PTR_ERR(task);
@@ -601,10 +680,15 @@ int _nfs4_call_sync_session(struct nfs_server *server,
                             struct nfs4_sequence_res *res,
                             int cache_reply)
 {
-        return nfs4_call_sync_sequence(server->nfs_client, server->client,
-                                       msg, args, res, cache_reply);
+        return nfs4_call_sync_sequence(server, msg, args, res, cache_reply, 0);
 }
 
+#else
+static int nfs4_sequence_done(struct rpc_task *task,
+                               struct nfs4_sequence_res *res)
+{
+        return 1;
+}
 #endif /* CONFIG_NFS_V4_1 */
 
 int _nfs4_call_sync(struct nfs_server *server,
@@ -618,27 +702,9 @@ int _nfs4_call_sync(struct nfs_server *server,
 }
 
 #define nfs4_call_sync(server, msg, args, res, cache_reply) \
-        (server)->nfs_client->cl_call_sync((server), (msg), &(args)->seq_args, \
+        (server)->nfs_client->cl_mvops->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);
@@ -680,26 +746,26 @@ 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,
                 struct nfs4_state_owner *sp, fmode_t fmode, int flags,
-                const struct iattr *attrs)
+                const struct iattr *attrs,
+                gfp_t gfp_mask)
 {
         struct dentry *parent = dget_parent(path->dentry);
         struct inode *dir = parent->d_inode;
         struct nfs_server *server = NFS_SERVER(dir);
         struct nfs4_opendata *p;
 
-        p = kzalloc(sizeof(*p), GFP_KERNEL);
+        p = kzalloc(sizeof(*p), gfp_mask);
         if (p == NULL)
                 goto err;
-        p->o_arg.seqid = nfs_alloc_seqid(&sp->so_seqid);
+        p->o_arg.seqid = nfs_alloc_seqid(&sp->so_seqid, gfp_mask);
         if (p->o_arg.seqid == NULL)
                 goto err_free;
-        p->path.mnt = mntget(path->mnt);
-        p->path.dentry = dget(path->dentry);
+        path_get(path);
+        p->path = *path;
         p->dir = parent;
         p->owner = sp;
         atomic_inc(&sp->so_count);
@@ -712,13 +778,14 @@ static struct nfs4_opendata *nfs4_opendata_alloc(struct path *path,
         p->o_arg.server = server;
         p->o_arg.bitmask = server->attr_bitmask;
         p->o_arg.claim = NFS4_OPEN_CLAIM_NULL;
-        if (flags & O_EXCL) {
-                u32 *s = (u32 *) p->o_arg.u.verifier.data;
-                s[0] = jiffies;
-                s[1] = current->pid;
-        } else if (flags & O_CREAT) {
+        if (flags & O_CREAT) {
+                u32 *s;
+
                 p->o_arg.u.attrs = &p->attrs;
                 memcpy(&p->attrs, attrs, sizeof(p->attrs));
+                s = (u32 *) p->o_arg.u.verifier.data;
+                s[0] = jiffies;
+                s[1] = current->pid;
         }
         p->c_arg.fh = &p->o_res.fh;
         p->c_arg.stateid = &p->o_res.stateid;
@@ -769,13 +836,16 @@ static int can_open_cached(struct nfs4_state *state, fmode_t mode, int open_mode
                 goto out;
         switch (mode & (FMODE_READ|FMODE_WRITE)) {
                 case FMODE_READ:
-                        ret |= test_bit(NFS_O_RDONLY_STATE, &state->flags) != 0;
+                        ret |= test_bit(NFS_O_RDONLY_STATE, &state->flags) != 0
+                                && state->n_rdonly != 0;
                         break;
                 case FMODE_WRITE:
-                        ret |= test_bit(NFS_O_WRONLY_STATE, &state->flags) != 0;
+                        ret |= test_bit(NFS_O_WRONLY_STATE, &state->flags) != 0
+                                && state->n_wronly != 0;
                         break;
                 case FMODE_READ|FMODE_WRITE:
-                        ret |= test_bit(NFS_O_RDWR_STATE, &state->flags) != 0;
+                        ret |= test_bit(NFS_O_RDWR_STATE, &state->flags) != 0
+                                && state->n_rdwr != 0;
         }
 out:
         return ret;
@@ -1022,7 +1092,7 @@ static struct nfs4_opendata *nfs4_open_recoverdata_alloc(struct nfs_open_context
 {
         struct nfs4_opendata *opendata;
 
-        opendata = nfs4_opendata_alloc(&ctx->path, state->owner, 0, 0, NULL);
+        opendata = nfs4_opendata_alloc(&ctx->path, state->owner, 0, 0, NULL, GFP_NOFS);
         if (opendata == NULL)
                 return ERR_PTR(-ENOMEM);
         opendata->state = state;
@@ -1040,7 +1110,7 @@ static int nfs4_open_recover_helper(struct nfs4_opendata *opendata, fmode_t fmod
         memset(&opendata->o_res, 0, sizeof(opendata->o_res));
         memset(&opendata->c_res, 0, sizeof(opendata->c_res));
         nfs4_init_opendata_res(opendata);
-        ret = _nfs4_proc_open(opendata);
+        ret = _nfs4_recover_proc_open(opendata);
         if (ret != 0)
                 return ret; 
         newstate = nfs4_opendata_to_nfs4_state(opendata);
@@ -1060,6 +1130,7 @@ static int nfs4_open_recover(struct nfs4_opendata *opendata, struct nfs4_state *
         clear_bit(NFS_DELEGATED_STATE, &state->flags);
         smp_rmb();
         if (state->n_rdwr != 0) {
+                clear_bit(NFS_O_RDWR_STATE, &state->flags);
                 ret = nfs4_open_recover_helper(opendata, FMODE_READ|FMODE_WRITE, &newstate);
                 if (ret != 0)
                         return ret;
@@ -1067,6 +1138,7 @@ static int nfs4_open_recover(struct nfs4_opendata *opendata, struct nfs4_state *
                         return -ESTALE;
         }
         if (state->n_wronly != 0) {
+                clear_bit(NFS_O_WRONLY_STATE, &state->flags);
                 ret = nfs4_open_recover_helper(opendata, FMODE_WRITE, &newstate);
                 if (ret != 0)
                         return ret;
@@ -1074,6 +1146,7 @@ static int nfs4_open_recover(struct nfs4_opendata *opendata, struct nfs4_state *
                         return -ESTALE;
         }
         if (state->n_rdonly != 0) {
+                clear_bit(NFS_O_RDONLY_STATE, &state->flags);
                 ret = nfs4_open_recover_helper(opendata, FMODE_READ, &newstate);
                 if (ret != 0)
                         return ret;
@@ -1176,6 +1249,14 @@ int nfs4_open_delegation_recall(struct nfs_open_context *ctx, struct nfs4_state
                         case -ENOENT:
                         case -ESTALE:
                                 goto out;
+                        case -NFS4ERR_BADSESSION:
+                        case -NFS4ERR_BADSLOT:
+                        case -NFS4ERR_BAD_HIGH_SLOT:
+                        case -NFS4ERR_CONN_NOT_BOUND_TO_SESSION:
+                        case -NFS4ERR_DEADSESSION:
+                                nfs4_schedule_state_recovery(
+                                        server->nfs_client);
+                                goto out;
                         case -NFS4ERR_STALE_CLIENTID:
                         case -NFS4ERR_STALE_STATEID:
                         case -NFS4ERR_EXPIRED:
@@ -1190,6 +1271,13 @@ int nfs4_open_delegation_recall(struct nfs_open_context *ctx, struct nfs4_state
                         case -NFS4ERR_ADMIN_REVOKED:
                         case -NFS4ERR_BAD_STATEID:
                                 nfs4_state_mark_reclaim_nograce(server->nfs_client, state);
+                        case -EKEYEXPIRED:
+                                /*
+                                 * User RPCSEC_GSS context has expired.
+                                 * We cannot recover this stateid now, so
+                                 * skip it and allow recovery thread to
+                                 * proceed.
+                                 */
                         case -ENOMEM:
                                 err = 0;
                                 goto out;
@@ -1205,8 +1293,6 @@ static void nfs4_open_confirm_done(struct rpc_task *task, void *calldata)
         struct nfs4_opendata *data = calldata;
 
         data->rpc_status = task->tk_status;
-        if (RPC_ASSASSINATED(task))
-                return;
         if (data->rpc_status == 0) {
                 memcpy(data->o_res.stateid.data, data->c_res.stateid.data,
                                 sizeof(data->o_res.stateid.data));
@@ -1306,13 +1392,13 @@ static void nfs4_open_prepare(struct rpc_task *task, void *calldata)
         }
         /* Update sequence id. */
         data->o_arg.id = sp->so_owner_id.id;
-        data->o_arg.clientid = sp->so_client->cl_clientid;
+        data->o_arg.clientid = sp->so_server->nfs_client->cl_clientid;
         if (data->o_arg.claim == NFS4_OPEN_CLAIM_PREVIOUS) {
                 task->tk_msg.rpc_proc = &nfs4_procedures[NFSPROC4_CLNT_OPEN_NOATTR];
                 nfs_copy_fh(&data->o_res.fh, data->o_arg.fh);
         }
         data->timestamp = jiffies;
-        if (nfs4_setup_sequence(data->o_arg.server->nfs_client,
+        if (nfs4_setup_sequence(data->o_arg.server,
                                 &data->o_arg.seq_args,
                                 &data->o_res.seq_res, 1, task))
                 return;
@@ -1323,17 +1409,21 @@ out_no_action:
 
 }
 
+static void nfs4_recover_open_prepare(struct rpc_task *task, void *calldata)
+{
+        rpc_task_set_priority(task, RPC_PRIORITY_PRIVILEGED);
+        nfs4_open_prepare(task, calldata);
+}
+
 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))
+        if (!nfs4_sequence_done(task, &data->o_res.seq_res))
                 return;
+
         if (task->tk_status == 0) {
                 switch (data->o_res.f_attr->mode & S_IFMT) {
                         case S_IFREG:
@@ -1381,10 +1471,13 @@ static const struct rpc_call_ops nfs4_open_ops = {
         .rpc_release = nfs4_open_release,
 };
 
-/*
- * Note: On error, nfs4_proc_open will free the struct nfs4_opendata
- */
-static int _nfs4_proc_open(struct nfs4_opendata *data)
+static const struct rpc_call_ops nfs4_recover_open_ops = {
+        .rpc_call_prepare = nfs4_recover_open_prepare,
+        .rpc_call_done = nfs4_open_done,
+        .rpc_release = nfs4_open_release,
+};
+
+static int nfs4_run_open_task(struct nfs4_opendata *data, int isrecover)
 {
         struct inode *dir = data->dir->d_inode;
         struct nfs_server *server = NFS_SERVER(dir);
@@ -1411,27 +1504,65 @@ static int _nfs4_proc_open(struct nfs4_opendata *data)
         data->rpc_done = 0;
         data->rpc_status = 0;
         data->cancelled = 0;
+        if (isrecover)
+                task_setup_data.callback_ops = &nfs4_recover_open_ops;
         task = rpc_run_task(&task_setup_data);
-        if (IS_ERR(task))
-                return PTR_ERR(task);
-        status = nfs4_wait_for_completion_rpc_task(task);
-        if (status != 0) {
-                data->cancelled = 1;
-                smp_wmb();
-        } else
-                status = data->rpc_status;
-        rpc_put_task(task);
+        if (IS_ERR(task))
+                return PTR_ERR(task);
+        status = nfs4_wait_for_completion_rpc_task(task);
+        if (status != 0) {
+                data->cancelled = 1;
+                smp_wmb();
+        } else
+                status = data->rpc_status;
+        rpc_put_task(task);
+
+        return status;
+}
+
+static int _nfs4_recover_proc_open(struct nfs4_opendata *data)
+{
+        struct inode *dir = data->dir->d_inode;
+        struct nfs_openres *o_res = &data->o_res;
+        int status;
+
+        status = nfs4_run_open_task(data, 1);
         if (status != 0 || !data->rpc_done)
                 return status;
 
-        if (o_res->fh.size == 0)
-                _nfs4_proc_lookup(dir, o_arg->name, &o_res->fh, o_res->f_attr);
+        nfs_refresh_inode(dir, o_res->dir_attr);
+
+        if (o_res->rflags & NFS4_OPEN_RESULT_CONFIRM) {
+                status = _nfs4_proc_open_confirm(data);
+                if (status != 0)
+                        return status;
+        }
+
+        return status;
+}
+
+/*
+ * Note: On error, nfs4_proc_open will free the struct nfs4_opendata
+ */
+static int _nfs4_proc_open(struct nfs4_opendata *data)
+{
+        struct inode *dir = data->dir->d_inode;
+        struct nfs_server *server = NFS_SERVER(dir);
+        struct nfs_openargs *o_arg = &data->o_arg;
+        struct nfs_openres *o_res = &data->o_res;
+        int status;
+
+        status = nfs4_run_open_task(data, 0);
+        if (status != 0 || !data->rpc_done)
+                return status;
 
         if (o_arg->open_flags & O_CREAT) {
                 update_changeattr(dir, &o_res->cinfo);
                 nfs_post_op_update_inode(dir, o_res->dir_attr);
         } else
                 nfs_refresh_inode(dir, o_res->dir_attr);
+        if ((o_res->rflags & NFS4_OPEN_RESULT_LOCKTYPE_POSIX) == 0)
+                server->caps &= ~NFS_CAP_POSIX_LOCK;
         if(o_res->rflags & NFS4_OPEN_RESULT_CONFIRM) {
                 status = _nfs4_proc_open_confirm(data);
                 if (status != 0)
@@ -1445,18 +1576,20 @@ static int _nfs4_proc_open(struct nfs4_opendata *data)
 static int nfs4_recover_expired_lease(struct nfs_server *server)
 {
         struct nfs_client *clp = server->nfs_client;
+        unsigned int loop;
         int ret;
 
-        for (;;) {
+        for (loop = NFS4_MAX_LOOP_ON_RECOVER; loop != 0; loop--) {
                 ret = nfs4_wait_clnt_recover(clp);
                 if (ret != 0)
-                        return ret;
+                        break;
                 if (!test_bit(NFS4CLNT_LEASE_EXPIRED, &clp->cl_state) &&
                     !test_bit(NFS4CLNT_CHECK_LEASE,&clp->cl_state))
                         break;
                 nfs4_schedule_state_recovery(clp);
+                ret = -EIO;
         }
-        return 0;
+        return ret;
 }
 
 /*
@@ -1479,7 +1612,7 @@ static int _nfs4_open_expired(struct nfs_open_context *ctx, struct nfs4_state *s
         return ret;
 }
 
-static inline int nfs4_do_open_expired(struct nfs_open_context *ctx, struct nfs4_state *state)
+static int nfs4_do_open_expired(struct nfs_open_context *ctx, struct nfs4_state *state)
 {
         struct nfs_server *server = NFS_SERVER(state->inode);
         struct nfs4_exception exception = { };
@@ -1487,10 +1620,16 @@ static inline int nfs4_do_open_expired(struct nfs_open_context *ctx, struct nfs4
 
         do {
                 err = _nfs4_open_expired(ctx, state);
-                if (err != -NFS4ERR_DELAY)
-                        break;
-                nfs4_handle_exception(server, err, &exception);
+                switch (err) {
+                default:
+                        goto out;
+                case -NFS4ERR_GRACE:
+                case -NFS4ERR_DELAY:
+                        nfs4_handle_exception(server, err, &exception);
+                        err = 0;
+                }
         } while (exception.retry);
+out:
         return err;
 }
 
@@ -1546,7 +1685,7 @@ static int _nfs4_do_open(struct inode *dir, struct path *path, fmode_t fmode, in
         if (path->dentry->d_inode != NULL)
                 nfs4_return_incompatible_delegation(path->dentry->d_inode, fmode);
         status = -ENOMEM;
-        opendata = nfs4_opendata_alloc(path, sp, fmode, flags, sattr);
+        opendata = nfs4_opendata_alloc(path, sp, fmode, flags, sattr, GFP_KERNEL);
         if (opendata == NULL)
                 goto err_put_state_owner;
 
@@ -1557,13 +1696,24 @@ static int _nfs4_do_open(struct inode *dir, struct path *path, fmode_t fmode, in
         if (status != 0)
                 goto err_opendata_put;
 
-        if (opendata->o_arg.open_flags & O_EXCL)
-                nfs4_exclusive_attrset(opendata, sattr);
-
         state = nfs4_opendata_to_nfs4_state(opendata);
         status = PTR_ERR(state);
         if (IS_ERR(state))
                 goto err_opendata_put;
+        if (server->caps & NFS_CAP_POSIX_LOCK)
+                set_bit(NFS_STATE_POSIX_LOCKS, &state->flags);
+
+        if (opendata->o_arg.open_flags & O_EXCL) {
+                nfs4_exclusive_attrset(opendata, sattr);
+
+                nfs_fattr_init(opendata->o_res.f_attr);
+                status = nfs4_do_setattr(state->inode, cred,
+                                opendata->o_res.f_attr, sattr,
+                                state);
+                if (status == 0)
+                        nfs_setattr_update_inode(state->inode, sattr);
+                nfs_post_op_update_inode(state->inode, opendata->o_res.f_attr);
+        }
         nfs4_opendata_put(opendata);
         nfs4_put_state_owner(sp);
         *res = state;
@@ -1656,7 +1806,7 @@ static int _nfs4_do_setattr(struct inode *inode, struct rpc_cred *cred,
         if (nfs4_copy_delegation_stateid(&arg.stateid, inode)) {
                 /* Use that stateid */
         } else if (state != NULL) {
-                nfs4_copy_stateid(&arg.stateid, state, current->files);
+                nfs4_copy_stateid(&arg.stateid, state, current->files, current->tgid);
         } else
                 memcpy(&arg.stateid, &zero_stateid, sizeof(arg.stateid));
 
@@ -1689,6 +1839,8 @@ struct nfs4_closedata {
         struct nfs_closeres res;
         struct nfs_fattr fattr;
         unsigned long timestamp;
+        bool roc;
+        u32 roc_barrier;
 };
 
 static void nfs4_free_closedata(void *data)
@@ -1696,6 +1848,8 @@ static void nfs4_free_closedata(void *data)
         struct nfs4_closedata *calldata = data;
         struct nfs4_state_owner *sp = calldata->state->owner;
 
+        if (calldata->roc)
+                pnfs_roc_release(calldata->state->inode);
         nfs4_put_open_state(calldata->state);
         nfs_free_seqid(calldata->arg.seqid);
         nfs4_put_state_owner(sp);
@@ -1703,22 +1857,38 @@ static void nfs4_free_closedata(void *data)
         kfree(calldata);
 }
 
+static void nfs4_close_clear_stateid_flags(struct nfs4_state *state,
+                fmode_t fmode)
+{
+        spin_lock(&state->owner->so_lock);
+        if (!(fmode & FMODE_READ))
+                clear_bit(NFS_O_RDONLY_STATE, &state->flags);
+        if (!(fmode & FMODE_WRITE))
+                clear_bit(NFS_O_WRONLY_STATE, &state->flags);
+        clear_bit(NFS_O_RDWR_STATE, &state->flags);
+        spin_unlock(&state->owner->so_lock);
+}
+
 static void nfs4_close_done(struct rpc_task *task, void *data)
 {
         struct nfs4_closedata *calldata = 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))
+        if (!nfs4_sequence_done(task, &calldata->res.seq_res))
                 return;
         /* hmm. we are done with the inode, and in the process of freeing
          * the state_owner. we keep this around to process errors
          */
         switch (task->tk_status) {
                 case 0:
+                        if (calldata->roc)
+                                pnfs_roc_set_barrier(state->inode,
+                                                     calldata->roc_barrier);
                         nfs_set_open_stateid(state, &calldata->res.stateid, 0);
                         renew_lease(server, calldata->timestamp);
+                        nfs4_close_clear_stateid_flags(state,
+                                        calldata->arg.fmode);
                         break;
                 case -NFS4ERR_STALE_STATEID:
                 case -NFS4ERR_OLD_STATEID:
@@ -1727,12 +1897,10 @@ static void nfs4_close_done(struct rpc_task *task, void *data)
                         if (calldata->arg.fmode == 0)
                                 break;
                 default:
-                        if (nfs4_async_handle_error(task, server, state) == -EAGAIN) {
-                                nfs4_restart_rpc(task, server->nfs_client);
-                                return;
-                        }
+                        if (nfs4_async_handle_error(task, server, state) == -EAGAIN)
+                                rpc_restart_call_prepare(task);
         }
-        nfs4_sequence_free_slot(server->nfs_client, &calldata->res.seq_res);
+        nfs_release_seqid(calldata->arg.seqid);
         nfs_refresh_inode(calldata->inode, calldata->res.fattr);
 }
 
@@ -1740,40 +1908,48 @@ static void nfs4_close_prepare(struct rpc_task *task, void *data)
 {
         struct nfs4_closedata *calldata = data;
         struct nfs4_state *state = calldata->state;
-        int clear_rd, clear_wr, clear_rdwr;
+        int call_close = 0;
 
         if (nfs_wait_on_sequence(calldata->arg.seqid, task) != 0)
                 return;
 
-        clear_rd = clear_wr = clear_rdwr = 0;
+        task->tk_msg.rpc_proc = &nfs4_procedures[NFSPROC4_CLNT_OPEN_DOWNGRADE];
+        calldata->arg.fmode = FMODE_READ|FMODE_WRITE;
         spin_lock(&state->owner->so_lock);
         /* Calculate the change in open mode */
         if (state->n_rdwr == 0) {
                 if (state->n_rdonly == 0) {
-                        clear_rd |= test_and_clear_bit(NFS_O_RDONLY_STATE, &state->flags);
-                        clear_rdwr |= test_and_clear_bit(NFS_O_RDWR_STATE, &state->flags);
+                        call_close |= test_bit(NFS_O_RDONLY_STATE, &state->flags);
+                        call_close |= test_bit(NFS_O_RDWR_STATE, &state->flags);
+                        calldata->arg.fmode &= ~FMODE_READ;
                 }
                 if (state->n_wronly == 0) {
-                        clear_wr |= test_and_clear_bit(NFS_O_WRONLY_STATE, &state->flags);
-                        clear_rdwr |= test_and_clear_bit(NFS_O_RDWR_STATE, &state->flags);
+                        call_close |= test_bit(NFS_O_WRONLY_STATE, &state->flags);
+                        call_close |= test_bit(NFS_O_RDWR_STATE, &state->flags);
+                        calldata->arg.fmode &= ~FMODE_WRITE;
                 }
         }
         spin_unlock(&state->owner->so_lock);
-        if (!clear_rd && !clear_wr && !clear_rdwr) {
+
+        if (!call_close) {
                 /* Note: exit _without_ calling nfs4_close_done */
                 task->tk_action = NULL;
                 return;
         }
-        nfs_fattr_init(calldata->res.fattr);
-        if (test_bit(NFS_O_RDONLY_STATE, &state->flags) != 0) {
-                task->tk_msg.rpc_proc = &nfs4_procedures[NFSPROC4_CLNT_OPEN_DOWNGRADE];
-                calldata->arg.fmode = FMODE_READ;
-        } else if (test_bit(NFS_O_WRONLY_STATE, &state->flags) != 0) {
-                task->tk_msg.rpc_proc = &nfs4_procedures[NFSPROC4_CLNT_OPEN_DOWNGRADE];
-                calldata->arg.fmode = FMODE_WRITE;
+
+        if (calldata->arg.fmode == 0) {
+                task->tk_msg.rpc_proc = &nfs4_procedures[NFSPROC4_CLNT_CLOSE];
+                if (calldata->roc &&
+                    pnfs_roc_drain(calldata->inode, &calldata->roc_barrier)) {
+                        rpc_sleep_on(&NFS_SERVER(calldata->inode)->roc_rpcwaitq,
+                                     task, NULL);
+                        return;
+                }
         }
+
+        nfs_fattr_init(calldata->res.fattr);
         calldata->timestamp = jiffies;
-        if (nfs4_setup_sequence((NFS_SERVER(calldata->inode))->nfs_client,
+        if (nfs4_setup_sequence(NFS_SERVER(calldata->inode),
                                 &calldata->arg.seq_args, &calldata->res.seq_res,
                                 1, task))
                 return;
@@ -1797,7 +1973,7 @@ static const struct rpc_call_ops nfs4_close_ops = {
  *
  * NOTE: Caller must be holding the sp->so_owner semaphore!
  */
-int nfs4_do_close(struct path *path, struct nfs4_state *state, int wait)
+int nfs4_do_close(struct path *path, struct nfs4_state *state, gfp_t gfp_mask, int wait, bool roc)
 {
         struct nfs_server *server = NFS_SERVER(state->inode);
         struct nfs4_closedata *calldata;
@@ -1816,17 +1992,15 @@ int nfs4_do_close(struct path *path, struct nfs4_state *state, int wait)
         };
         int status = -ENOMEM;
 
-        calldata = kzalloc(sizeof(*calldata), GFP_KERNEL);
+        calldata = kzalloc(sizeof(*calldata), gfp_mask);
         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);
+        calldata->arg.seqid = nfs_alloc_seqid(&state->owner->so_seqid, gfp_mask);
         if (calldata->arg.seqid == NULL)
                 goto out_free_calldata;
         calldata->arg.fmode = 0;
@@ -1834,12 +2008,12 @@ 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);
+        calldata->roc = roc;
+        path_get(path);
+        calldata->path = *path;
 
-        msg.rpc_argp = &calldata->arg,
-        msg.rpc_resp = &calldata->res,
+        msg.rpc_argp = &calldata->arg;
+        msg.rpc_resp = &calldata->res;
         task_setup_data.callback_data = calldata;
         task = rpc_run_task(&task_setup_data);
         if (IS_ERR(task))
@@ -1852,127 +2026,27 @@ int nfs4_do_close(struct path *path, struct nfs4_state *state, int wait)
 out_free_calldata:
         kfree(calldata);
 out:
+        if (roc)
+                pnfs_roc_release(state->inode);
         nfs4_put_open_state(state);
         nfs4_put_state_owner(sp);
         return status;
 }
 
-static int nfs4_intent_set_file(struct nameidata *nd, struct path *path, struct nfs4_state *state, fmode_t fmode)
+static struct inode *
+nfs4_atomic_open(struct inode *dir, struct nfs_open_context *ctx, int open_flags, struct iattr *attr)
 {
-        struct file *filp;
-        int ret;
-
-        /* If the open_intent is for execute, we have an extra check to make */
-        if (fmode & FMODE_EXEC) {
-                ret = nfs_may_open(state->inode,
-                                state->owner->so_cred,
-                                nd->intent.open.flags);
-                if (ret < 0)
-                        goto out_close;
-        }
-        filp = lookup_instantiate_filp(nd, path->dentry, NULL);
-        if (!IS_ERR(filp)) {
-                struct nfs_open_context *ctx;
-                ctx = nfs_file_open_context(filp);
-                ctx->state = state;
-                return 0;
-        }
-        ret = PTR_ERR(filp);
-out_close:
-        nfs4_close_sync(path, state, fmode & (FMODE_READ|FMODE_WRITE));
-        return ret;
-}
-
-struct dentry *
-nfs4_atomic_open(struct inode *dir, struct dentry *dentry, struct nameidata *nd)
-{
-        struct path path = {
-                .mnt = nd->path.mnt,
-                .dentry = dentry,
-        };
-        struct dentry *parent;
-        struct iattr attr;
-        struct rpc_cred *cred;
         struct nfs4_state *state;
-        struct dentry *res;
-        fmode_t fmode = nd->intent.open.flags & (FMODE_READ | FMODE_WRITE | FMODE_EXEC);
-
-        if (nd->flags & LOOKUP_CREATE) {
-                attr.ia_mode = nd->intent.open.create_mode;
-                attr.ia_valid = ATTR_MODE;
-                if (!IS_POSIXACL(dir))
-                        attr.ia_mode &= ~current_umask();
-        } else {
-                attr.ia_valid = 0;
-                BUG_ON(nd->intent.open.flags & O_CREAT);
-        }
 
-        cred = rpc_lookup_cred();
-        if (IS_ERR(cred))
-                return (struct dentry *)cred;
-        parent = dentry->d_parent;
         /* Protect against concurrent sillydeletes */
-        nfs_block_sillyrename(parent);
-        state = nfs4_do_open(dir, &path, fmode, nd->intent.open.flags, &attr, cred);
-        put_rpccred(cred);
-        if (IS_ERR(state)) {
-                if (PTR_ERR(state) == -ENOENT) {
-                        d_add(dentry, NULL);
-                        nfs_set_verifier(dentry, nfs_save_change_attribute(dir));
-                }
-                nfs_unblock_sillyrename(parent);
-                return (struct dentry *)state;
-        }
-        res = d_add_unique(dentry, igrab(state->inode));
-        if (res != NULL)
-                path.dentry = res;
-        nfs_set_verifier(path.dentry, nfs_save_change_attribute(dir));
-        nfs_unblock_sillyrename(parent);
-        nfs4_intent_set_file(nd, &path, state, fmode);
-        return res;
-}
-
-int
-nfs4_open_revalidate(struct inode *dir, struct dentry *dentry, int openflags, struct nameidata *nd)
-{
-        struct path path = {
-                .mnt = nd->path.mnt,
-                .dentry = dentry,
-        };
-        struct rpc_cred *cred;
-        struct nfs4_state *state;
-        fmode_t fmode = openflags & (FMODE_READ | FMODE_WRITE);
-
-        cred = rpc_lookup_cred();
-        if (IS_ERR(cred))
-                return PTR_ERR(cred);
-        state = nfs4_do_open(dir, &path, fmode, openflags, NULL, cred);
-        put_rpccred(cred);
-        if (IS_ERR(state)) {
-                switch (PTR_ERR(state)) {
-                        case -EPERM:
-                        case -EACCES:
-                        case -EDQUOT:
-                        case -ENOSPC:
-                        case -EROFS:
-                                lookup_instantiate_filp(nd, (struct dentry *)state, NULL);
-                                return 1;
-                        default:
-                                goto out_drop;
-                }
-        }
-        if (state->inode == dentry->d_inode) {
-                nfs_set_verifier(dentry, nfs_save_change_attribute(dir));
-                nfs4_intent_set_file(nd, &path, state, fmode);
-                return 1;
-        }
-        nfs4_close_sync(&path, state, fmode);
-out_drop:
-        d_drop(dentry);
-        return 0;
+        state = nfs4_do_open(dir, &ctx->path, ctx->mode, open_flags, attr, ctx->cred);
+        if (IS_ERR(state))
+                return ERR_CAST(state);
+        ctx->state = state;
+        return igrab(state->inode);
 }
 
-void nfs4_close_context(struct nfs_open_context *ctx, int is_sync)
+static void nfs4_close_context(struct nfs_open_context *ctx, int is_sync)
 {
         if (ctx->state == NULL)
                 return;
@@ -1998,12 +2072,34 @@ static int _nfs4_server_capabilities(struct nfs_server *server, struct nfs_fh *f
         status = nfs4_call_sync(server, &msg, &args, &res, 0);
         if (status == 0) {
                 memcpy(server->attr_bitmask, res.attr_bitmask, sizeof(server->attr_bitmask));
+                server->caps &= ~(NFS_CAP_ACLS|NFS_CAP_HARDLINKS|
+                                NFS_CAP_SYMLINKS|NFS_CAP_FILEID|
+                                NFS_CAP_MODE|NFS_CAP_NLINK|NFS_CAP_OWNER|
+                                NFS_CAP_OWNER_GROUP|NFS_CAP_ATIME|
+                                NFS_CAP_CTIME|NFS_CAP_MTIME);
                 if (res.attr_bitmask[0] & FATTR4_WORD0_ACL)
                         server->caps |= NFS_CAP_ACLS;
                 if (res.has_links != 0)
                         server->caps |= NFS_CAP_HARDLINKS;
                 if (res.has_symlinks != 0)
                         server->caps |= NFS_CAP_SYMLINKS;
+                if (res.attr_bitmask[0] & FATTR4_WORD0_FILEID)
+                        server->caps |= NFS_CAP_FILEID;
+                if (res.attr_bitmask[1] & FATTR4_WORD1_MODE)
+                        server->caps |= NFS_CAP_MODE;
+                if (res.attr_bitmask[1] & FATTR4_WORD1_NUMLINKS)
+                        server->caps |= NFS_CAP_NLINK;
+                if (res.attr_bitmask[1] & FATTR4_WORD1_OWNER)
+                        server->caps |= NFS_CAP_OWNER;
+                if (res.attr_bitmask[1] & FATTR4_WORD1_OWNER_GROUP)
+                        server->caps |= NFS_CAP_OWNER_GROUP;
+                if (res.attr_bitmask[1] & FATTR4_WORD1_TIME_ACCESS)
+                        server->caps |= NFS_CAP_ATIME;
+                if (res.attr_bitmask[1] & FATTR4_WORD1_TIME_METADATA)
+                        server->caps |= NFS_CAP_CTIME;
+                if (res.attr_bitmask[1] & FATTR4_WORD1_TIME_MODIFY)
+                        server->caps |= NFS_CAP_MTIME;
+
                 memcpy(server->cache_consistency_bitmask, res.attr_bitmask, sizeof(server->cache_consistency_bitmask));
                 server->cache_consistency_bitmask[0] &= FATTR4_WORD0_CHANGE|FATTR4_WORD0_SIZE;
                 server->cache_consistency_bitmask[1] &= FATTR4_WORD1_TIME_METADATA|FATTR4_WORD1_TIME_MODIFY;
@@ -2041,15 +2137,9 @@ 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);
-        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;
+        return nfs4_call_sync(server, &msg, &args, &res, 0);
 }
 
 static int nfs4_lookup_root(struct nfs_server *server, struct nfs_fh *fhandle,
@@ -2117,8 +2207,7 @@ static int nfs4_get_referral(struct inode *dir, const struct qstr *name, struct
 out:
         if (page)
                 __free_page(page);
-        if (locations)
-                kfree(locations);
+        kfree(locations);
         return status;
 }
 
@@ -2274,14 +2363,12 @@ static int nfs4_proc_lookup(struct inode *dir, struct qstr *name, struct nfs_fh
 static int _nfs4_proc_access(struct inode *inode, struct nfs_access_entry *entry)
 {
         struct nfs_server *server = NFS_SERVER(inode);
-        struct nfs_fattr fattr;
         struct nfs4_accessargs args = {
                 .fh = NFS_FH(inode),
                 .bitmask = server->attr_bitmask,
         };
         struct nfs4_accessres res = {
                 .server = server,
-                .fattr = &fattr,
         };
         struct rpc_message msg = {
                 .rpc_proc = &nfs4_procedures[NFSPROC4_CLNT_ACCESS],
@@ -2308,7 +2395,11 @@ static int _nfs4_proc_access(struct inode *inode, struct nfs_access_entry *entry
                 if (mode & MAY_EXEC)
                         args.access |= NFS4_ACCESS_EXECUTE;
         }
-        nfs_fattr_init(&fattr);
+
+        res.fattr = nfs_alloc_fattr();
+        if (res.fattr == NULL)
+                return -ENOMEM;
+
         status = nfs4_call_sync(server, &msg, &args, &res, 0);
         if (!status) {
                 entry->mask = 0;
@@ -2318,8 +2409,9 @@ static int _nfs4_proc_access(struct inode *inode, struct nfs_access_entry *entry
                         entry->mask |= MAY_WRITE;
                 if (res.access & (NFS4_ACCESS_LOOKUP|NFS4_ACCESS_EXECUTE))
                         entry->mask |= MAY_EXEC;
-                nfs_refresh_inode(inode, &fattr);
+                nfs_refresh_inode(inode, res.fattr);
         }
+        nfs_free_fattr(res.fattr);
         return status;
 }
 
@@ -2408,43 +2500,35 @@ static int nfs4_proc_readlink(struct inode *inode, struct page *page,
 
 static int
 nfs4_proc_create(struct inode *dir, struct dentry *dentry, struct iattr *sattr,
-                 int flags, struct nameidata *nd)
+                 int flags, struct nfs_open_context *ctx)
 {
-        struct path path = {
-                .mnt = nd->path.mnt,
+        struct path my_path = {
                 .dentry = dentry,
         };
+        struct path *path = &my_path;
         struct nfs4_state *state;
-        struct rpc_cred *cred;
-        fmode_t fmode = flags & (FMODE_READ | FMODE_WRITE);
+        struct rpc_cred *cred = NULL;
+        fmode_t fmode = 0;
         int status = 0;
 
-        cred = rpc_lookup_cred();
-        if (IS_ERR(cred)) {
-                status = PTR_ERR(cred);
-                goto out;
+        if (ctx != NULL) {
+                cred = ctx->cred;
+                path = &ctx->path;
+                fmode = ctx->mode;
         }
-        state = nfs4_do_open(dir, &path, fmode, flags, sattr, cred);
+        sattr->ia_mode &= ~current_umask();
+        state = nfs4_do_open(dir, path, fmode, flags, sattr, cred);
         d_drop(dentry);
         if (IS_ERR(state)) {
                 status = PTR_ERR(state);
-                goto out_putcred;
+                goto out;
         }
         d_add(dentry, igrab(state->inode));
         nfs_set_verifier(dentry, nfs_save_change_attribute(dir));
-        if (flags & O_EXCL) {
-                struct nfs_fattr fattr;
-                status = nfs4_do_setattr(state->inode, cred, &fattr, sattr, state);
-                if (status == 0)
-                        nfs_setattr_update_inode(state->inode, sattr);
-                nfs_post_op_update_inode(state->inode, &fattr);
-        }
-        if (status == 0 && (nd->flags & LOOKUP_OPEN) != 0)
-                status = nfs4_intent_set_file(nd, &path, state, fmode);
+        if (ctx != NULL)
+                ctx->state = state;
         else
-                nfs4_close_sync(&path, state, fmode);
-out_putcred:
-        put_rpccred(cred);
+                nfs4_close_sync(path, state, fmode);
 out:
         return status;
 }
@@ -2466,14 +2550,19 @@ static int _nfs4_proc_remove(struct inode *dir, struct qstr *name)
                 .rpc_argp = &args,
                 .rpc_resp = &res,
         };
-        int                     status;
+        int status = -ENOMEM;
+
+        res.dir_attr = nfs_alloc_fattr();
+        if (res.dir_attr == NULL)
+                goto out;
 
-        nfs_fattr_init(&res.dir_attr);
         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);
+                nfs_post_op_update_inode(dir, res.dir_attr);
         }
+        nfs_free_fattr(res.dir_attr);
+out:
         return status;
 }
 
@@ -2497,6 +2586,7 @@ static void nfs4_proc_unlink_setup(struct rpc_message *msg, struct inode *dir)
 
         args->bitmask = server->cache_consistency_bitmask;
         res->server = server;
+        res->seq_res.sr_slot = NULL;
         msg->rpc_proc = &nfs4_procedures[NFSPROC4_CLNT_REMOVE];
 }
 
@@ -2504,12 +2594,40 @@ 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_sequence_done(task, &res->seq_res))
+                return 0;
         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);
+        nfs_post_op_update_inode(dir, res->dir_attr);
+        return 1;
+}
+
+static void nfs4_proc_rename_setup(struct rpc_message *msg, struct inode *dir)
+{
+        struct nfs_server *server = NFS_SERVER(dir);
+        struct nfs_renameargs *arg = msg->rpc_argp;
+        struct nfs_renameres *res = msg->rpc_resp;
+
+        msg->rpc_proc = &nfs4_procedures[NFSPROC4_CLNT_RENAME];
+        arg->bitmask = server->attr_bitmask;
+        res->server = server;
+}
+
+static int nfs4_proc_rename_done(struct rpc_task *task, struct inode *old_dir,
+                                 struct inode *new_dir)
+{
+        struct nfs_renameres *res = task->tk_msg.rpc_resp;
+
+        if (!nfs4_sequence_done(task, &res->seq_res))
+                return 0;
+        if (nfs4_async_handle_error(task, res->server, NULL) == -EAGAIN)
+                return 0;
+
+        update_changeattr(old_dir, &res->old_cinfo);
+        nfs_post_op_update_inode(old_dir, res->old_fattr);
+        update_changeattr(new_dir, &res->new_cinfo);
+        nfs_post_op_update_inode(new_dir, res->new_fattr);
         return 1;
 }
 
@@ -2517,36 +2635,38 @@ static int _nfs4_proc_rename(struct inode *old_dir, struct qstr *old_name,
                 struct inode *new_dir, struct qstr *new_name)
 {
         struct nfs_server *server = NFS_SERVER(old_dir);
-        struct nfs4_rename_arg arg = {
+        struct nfs_renameargs arg = {
                 .old_dir = NFS_FH(old_dir),
                 .new_dir = NFS_FH(new_dir),
                 .old_name = old_name,
                 .new_name = new_name,
                 .bitmask = server->attr_bitmask,
         };
-        struct nfs_fattr old_fattr, new_fattr;
-        struct nfs4_rename_res res = {
+        struct nfs_renameres res = {
                 .server = server,
-                .old_fattr = &old_fattr,
-                .new_fattr = &new_fattr,
         };
         struct rpc_message msg = {
                 .rpc_proc = &nfs4_procedures[NFSPROC4_CLNT_RENAME],
                 .rpc_argp = &arg,
                 .rpc_resp = &res,
         };
-        int                     status;
+        int status = -ENOMEM;
         
-        nfs_fattr_init(res.old_fattr);
-        nfs_fattr_init(res.new_fattr);
-        status = nfs4_call_sync(server, &msg, &arg, &res, 1);
+        res.old_fattr = nfs_alloc_fattr();
+        res.new_fattr = nfs_alloc_fattr();
+        if (res.old_fattr == NULL || res.new_fattr == NULL)
+                goto out;
 
+        status = nfs4_call_sync(server, &msg, &arg, &res, 1);
         if (!status) {
                 update_changeattr(old_dir, &res.old_cinfo);
                 nfs_post_op_update_inode(old_dir, res.old_fattr);
                 update_changeattr(new_dir, &res.new_cinfo);
                 nfs_post_op_update_inode(new_dir, res.new_fattr);
         }
+out:
+        nfs_free_fattr(res.new_fattr);
+        nfs_free_fattr(res.old_fattr);
         return status;
 }
 
@@ -2573,28 +2693,30 @@ static int _nfs4_proc_link(struct inode *inode, struct inode *dir, struct qstr *
                 .name   = name,
                 .bitmask = server->attr_bitmask,
         };
-        struct nfs_fattr fattr, dir_attr;
         struct nfs4_link_res res = {
                 .server = server,
-                .fattr = &fattr,
-                .dir_attr = &dir_attr,
         };
         struct rpc_message msg = {
                 .rpc_proc = &nfs4_procedures[NFSPROC4_CLNT_LINK],
                 .rpc_argp = &arg,
                 .rpc_resp = &res,
         };
-        int                     status;
+        int status = -ENOMEM;
+
+        res.fattr = nfs_alloc_fattr();
+        res.dir_attr = nfs_alloc_fattr();
+        if (res.fattr == NULL || res.dir_attr == NULL)
+                goto out;
 
-        nfs_fattr_init(res.fattr);
-        nfs_fattr_init(res.dir_attr);
         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);
                 nfs_post_op_update_inode(inode, res.fattr);
         }
-
+out:
+        nfs_free_fattr(res.dir_attr);
+        nfs_free_fattr(res.fattr);
         return status;
 }
 
@@ -2725,6 +2847,8 @@ static int nfs4_proc_mkdir(struct inode *dir, struct dentry *dentry,
 {
         struct nfs4_exception exception = { };
         int err;
+
+        sattr->ia_mode &= ~current_umask();
         do {
                 err = nfs4_handle_exception(NFS_SERVER(dir),
                                 _nfs4_proc_mkdir(dir, dentry, sattr),
@@ -2734,15 +2858,16 @@ static int nfs4_proc_mkdir(struct inode *dir, struct dentry *dentry,
 }
 
 static int _nfs4_proc_readdir(struct dentry *dentry, struct rpc_cred *cred,
-                  u64 cookie, struct page *page, unsigned int count, int plus)
+                u64 cookie, struct page **pages, unsigned int count, int plus)
 {
         struct inode            *dir = dentry->d_inode;
         struct nfs4_readdir_arg args = {
                 .fh = NFS_FH(dir),
-                .pages = &page,
+                .pages = pages,
                 .pgbase = 0,
                 .count = count,
-                .bitmask = NFS_SERVER(dentry->d_inode)->cache_consistency_bitmask,
+                .bitmask = NFS_SERVER(dentry->d_inode)->attr_bitmask,
+                .plus = plus,
         };
         struct nfs4_readdir_res res;
         struct rpc_message msg = {
@@ -2760,8 +2885,10 @@ static int _nfs4_proc_readdir(struct dentry *dentry, struct rpc_cred *cred,
         nfs4_setup_readdir(cookie, NFS_COOKIEVERF(dir), dentry, &args);
         res.pgbase = args.pgbase;
         status = nfs4_call_sync(NFS_SERVER(dir), &msg, &args, &res, 0);
-        if (status == 0)
+        if (status >= 0) {
                 memcpy(NFS_COOKIEVERF(dir), res.verifier.data, NFS4_VERIFIER_SIZE);
+                status += args.pgbase;
+        }
 
         nfs_invalidate_atime(dir);
 
@@ -2770,14 +2897,14 @@ static int _nfs4_proc_readdir(struct dentry *dentry, struct rpc_cred *cred,
 }
 
 static int nfs4_proc_readdir(struct dentry *dentry, struct rpc_cred *cred,
-                  u64 cookie, struct page *page, unsigned int count, int plus)
+                u64 cookie, struct page **pages, unsigned int count, int plus)
 {
         struct nfs4_exception exception = { };
         int err;
         do {
                 err = nfs4_handle_exception(NFS_SERVER(dentry->d_inode),
                                 _nfs4_proc_readdir(dentry, cred, cookie,
-                                        page, count, plus),
+                                        pages, count, plus),
                                 &exception);
         } while (exception.retry);
         return err;
@@ -2822,6 +2949,8 @@ static int nfs4_proc_mknod(struct inode *dir, struct dentry *dentry,
 {
         struct nfs4_exception exception = { };
         int err;
+
+        sattr->ia_mode &= ~current_umask();
         do {
                 err = nfs4_handle_exception(NFS_SERVER(dir),
                                 _nfs4_proc_mknod(dir, dentry, sattr, rdev),
@@ -2946,11 +3075,11 @@ static int nfs4_read_done(struct rpc_task *task, struct nfs_read_data *data)
 
         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_sequence_done(task, &data->res.seq_res))
+                return -EAGAIN;
 
         if (nfs4_async_handle_error(task, server, data->args.context->state) == -EAGAIN) {
-                nfs4_restart_rpc(task, server->nfs_client);
+                nfs_restart_rpc(task, server->nfs_client);
                 return -EAGAIN;
         }
 
@@ -2970,12 +3099,11 @@ 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_sequence_done(task, &data->res.seq_res))
+                return -EAGAIN;
 
         if (nfs4_async_handle_error(task, NFS_SERVER(inode), data->args.context->state) == -EAGAIN) {
-                nfs4_restart_rpc(task, NFS_SERVER(inode)->nfs_client);
+                nfs_restart_rpc(task, NFS_SERVER(inode)->nfs_client);
                 return -EAGAIN;
         }
         if (task->tk_status >= 0) {
@@ -3000,14 +3128,13 @@ 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_sequence_done(task, &data->res.seq_res))
+                return -EAGAIN;
+
         if (nfs4_async_handle_error(task, NFS_SERVER(inode), NULL) == -EAGAIN) {
-                nfs4_restart_rpc(task, NFS_SERVER(inode)->nfs_client);
+                nfs_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;
 }
@@ -3021,14 +3148,31 @@ static void nfs4_proc_commit_setup(struct nfs_write_data *data, struct rpc_messa
         msg->rpc_proc = &nfs4_procedures[NFSPROC4_CLNT_COMMIT];
 }
 
+struct nfs4_renewdata {
+        struct nfs_client       *client;
+        unsigned long           timestamp;
+};
+
 /*
  * nfs4_proc_async_renew(): This is not one of the nfs_rpc_ops; it is a special
  * standalone procedure for queueing an asynchronous RENEW.
  */
-static void nfs4_renew_done(struct rpc_task *task, void *data)
+static void nfs4_renew_release(void *calldata)
 {
-        struct nfs_client *clp = (struct nfs_client *)task->tk_msg.rpc_argp;
-        unsigned long timestamp = (unsigned long)data;
+        struct nfs4_renewdata *data = calldata;
+        struct nfs_client *clp = data->client;
+
+        if (atomic_read(&clp->cl_count) > 1)
+                nfs4_schedule_state_renewal(clp);
+        nfs_put_client(clp);
+        kfree(data);
+}
+
+static void nfs4_renew_done(struct rpc_task *task, void *calldata)
+{
+        struct nfs4_renewdata *data = calldata;
+        struct nfs_client *clp = data->client;
+        unsigned long timestamp = data->timestamp;
 
         if (task->tk_status < 0) {
                 /* Unless we're shutting down, schedule state recovery! */
@@ -3036,17 +3180,12 @@ static void nfs4_renew_done(struct rpc_task *task, void *data)
                         nfs4_schedule_state_recovery(clp);
                 return;
         }
-        spin_lock(&clp->cl_lock);
-        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);
+        do_renew_lease(clp, timestamp);
 }
 
 static const struct rpc_call_ops nfs4_renew_ops = {
         .rpc_call_done = nfs4_renew_done,
+        .rpc_release = nfs4_renew_release,
 };
 
 int nfs4_proc_async_renew(struct nfs_client *clp, struct rpc_cred *cred)
@@ -3056,9 +3195,17 @@ int nfs4_proc_async_renew(struct nfs_client *clp, struct rpc_cred *cred)
                 .rpc_argp       = clp,
                 .rpc_cred       = cred,
         };
+        struct nfs4_renewdata *data;
 
+        if (!atomic_inc_not_zero(&clp->cl_count))
+                return -EIO;
+        data = kmalloc(sizeof(*data), GFP_KERNEL);
+        if (data == NULL)
+                return -ENOMEM;
+        data->client = clp;
+        data->timestamp = jiffies;
         return rpc_call_async(clp->cl_rpcclient, &msg, RPC_TASK_SOFT,
-                        &nfs4_renew_ops, (void *)jiffies);
+                        &nfs4_renew_ops, data);
 }
 
 int nfs4_proc_renew(struct nfs_client *clp, struct rpc_cred *cred)
@@ -3074,10 +3221,7 @@ int nfs4_proc_renew(struct nfs_client *clp, struct rpc_cred *cred)
         status = rpc_call_sync(clp->cl_rpcclient, &msg, 0);
         if (status < 0)
                 return status;
-        spin_lock(&clp->cl_lock);
-        if (time_before(clp->cl_last_renewal,now))
-                clp->cl_last_renewal = now;
-        spin_unlock(&clp->cl_lock);
+        do_renew_lease(clp, now);
         return 0;
 }
 
@@ -3252,6 +3396,8 @@ 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;
@@ -3280,6 +3426,13 @@ static int __nfs4_proc_set_acl(struct inode *inode, const void *buf, size_t bufl
         nfs_inode_return_delegation(inode);
         buf_to_pages(buf, buflen, arg.acl_pages, &arg.acl_pgbase);
         ret = nfs4_call_sync(server, &msg, &arg, &res, 1);
+        /*
+         * Acl update can result in inode attribute update.
+         * so mark the attribute cache invalid.
+         */
+        spin_lock(&inode->i_lock);
+        NFS_I(inode)->cache_validity |= NFS_INO_INVALID_ATTR;
+        spin_unlock(&inode->i_lock);
         nfs_access_zap_cache(inode);
         nfs_zap_acl_cache(inode);
         return ret;
@@ -3298,9 +3451,11 @@ 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 nfs_client *clp, struct nfs4_state *state)
+nfs4_async_handle_error(struct rpc_task *task, const struct nfs_server *server, struct nfs4_state *state)
 {
-        if (!clp || task->tk_status >= 0)
+        struct nfs_client *clp = server->nfs_client;
+
+        if (task->tk_status >= 0)
                 return 0;
         switch(task->tk_status) {
                 case -NFS4ERR_ADMIN_REVOKED:
@@ -3309,15 +3464,11 @@ _nfs4_async_handle_error(struct rpc_task *task, const struct nfs_server *server,
                         if (state == NULL)
                                 break;
                         nfs4_state_mark_reclaim_nograce(clp, state);
-                case -NFS4ERR_STALE_CLIENTID:
+                        goto do_state_recovery;
                 case -NFS4ERR_STALE_STATEID:
+                case -NFS4ERR_STALE_CLIENTID:
                 case -NFS4ERR_EXPIRED:
-                        rpc_sleep_on(&clp->cl_rpcwaitq, task, NULL);
-                        nfs4_schedule_state_recovery(clp);
-                        if (test_bit(NFS4CLNT_MANAGER_RUNNING, &clp->cl_state) == 0)
-                                rpc_wake_up_queued_task(&clp->cl_rpcwaitq, task);
-                        task->tk_status = 0;
-                        return -EAGAIN;
+                        goto do_state_recovery;
 #if defined(CONFIG_NFS_V4_1)
                 case -NFS4ERR_BADSESSION:
                 case -NFS4ERR_BADSLOT:
@@ -3328,14 +3479,14 @@ _nfs4_async_handle_error(struct rpc_task *task, const struct nfs_server *server,
                 case -NFS4ERR_SEQ_MISORDERED:
                         dprintk("%s ERROR %d, Reset session\n", __func__,
                                 task->tk_status);
-                        set_bit(NFS4CLNT_SESSION_SETUP, &clp->cl_state);
+                        nfs4_schedule_state_recovery(clp);
                         task->tk_status = 0;
                         return -EAGAIN;
 #endif /* CONFIG_NFS_V4_1 */
                 case -NFS4ERR_DELAY:
-                        if (server)
-                                nfs_inc_server_stats(server, NFSIOS_DELAY);
+                        nfs_inc_server_stats(server, NFSIOS_DELAY);
                 case -NFS4ERR_GRACE:
+                case -EKEYEXPIRED:
                         rpc_delay(task, NFS4_POLL_RETRY_MAX);
                         task->tk_status = 0;
                         return -EAGAIN;
@@ -3345,25 +3496,29 @@ _nfs4_async_handle_error(struct rpc_task *task, const struct nfs_server *server,
         }
         task->tk_status = nfs4_map_errors(task->tk_status);
         return 0;
+do_state_recovery:
+        rpc_sleep_on(&clp->cl_rpcwaitq, task, NULL);
+        nfs4_schedule_state_recovery(clp);
+        if (test_bit(NFS4CLNT_MANAGER_RUNNING, &clp->cl_state) == 0)
+                rpc_wake_up_queued_task(&clp->cl_rpcwaitq, task);
+        task->tk_status = 0;
+        return -EAGAIN;
 }
 
-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)
+int nfs4_proc_setclientid(struct nfs_client *clp, u32 program,
+                unsigned short port, struct rpc_cred *cred,
+                struct nfs4_setclientid_res *res)
 {
         nfs4_verifier sc_verifier;
         struct nfs4_setclientid setclientid = {
                 .sc_verifier = &sc_verifier,
                 .sc_prog = program,
+                .sc_cb_ident = clp->cl_cb_ident,
         };
         struct rpc_message msg = {
                 .rpc_proc = &nfs4_procedures[NFSPROC4_CLNT_SETCLIENTID],
                 .rpc_argp = &setclientid,
-                .rpc_resp = clp,
+                .rpc_resp = res,
                 .rpc_cred = cred,
         };
         __be32 *p;
@@ -3398,7 +3553,7 @@ int nfs4_proc_setclientid(struct nfs_client *clp, u32 program, unsigned short po
                 if (signalled())
                         break;
                 if (loop++ & 1)
-                        ssleep(clp->cl_lease_time + 1);
+                        ssleep(clp->cl_lease_time / HZ + 1);
                 else
                         if (++clp->cl_id_uniquifier == 0)
                                 break;
@@ -3406,12 +3561,14 @@ int nfs4_proc_setclientid(struct nfs_client *clp, u32 program, unsigned short po
         return status;
 }
 
-static int _nfs4_proc_setclientid_confirm(struct nfs_client *clp, struct rpc_cred *cred)
+static int _nfs4_proc_setclientid_confirm(struct nfs_client *clp,
+                struct nfs4_setclientid_res *arg,
+                struct rpc_cred *cred)
 {
         struct nfs_fsinfo fsinfo;
         struct rpc_message msg = {
                 .rpc_proc = &nfs4_procedures[NFSPROC4_CLNT_SETCLIENTID_CONFIRM],
-                .rpc_argp = clp,
+                .rpc_argp = arg,
                 .rpc_resp = &fsinfo,
                 .rpc_cred = cred,
         };
@@ -3429,12 +3586,14 @@ static int _nfs4_proc_setclientid_confirm(struct nfs_client *clp, struct rpc_cre
         return status;
 }
 
-int nfs4_proc_setclientid_confirm(struct nfs_client *clp, struct rpc_cred *cred)
+int nfs4_proc_setclientid_confirm(struct nfs_client *clp,
+                struct nfs4_setclientid_res *arg,
+                struct rpc_cred *cred)
 {
         long timeout = 0;
         int err;
         do {
-                err = _nfs4_proc_setclientid_confirm(clp, cred);
+                err = _nfs4_proc_setclientid_confirm(clp, arg, cred);
                 switch (err) {
                         case 0:
                                 return err;
@@ -3461,12 +3620,23 @@ 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);
+        if (!nfs4_sequence_done(task, &data->res.seq_res))
+                return;
 
-        data->rpc_status = task->tk_status;
-        if (data->rpc_status == 0)
+        switch (task->tk_status) {
+        case -NFS4ERR_STALE_STATEID:
+        case -NFS4ERR_EXPIRED:
+        case 0:
                 renew_lease(data->res.server, data->timestamp);
+                break;
+        default:
+                if (nfs4_async_handle_error(task, data->res.server, NULL) ==
+                                -EAGAIN) {
+                        nfs_restart_rpc(task, data->res.server->nfs_client);
+                        return;
+                }
+        }
+        data->rpc_status = task->tk_status;
 }
 
 static void nfs4_delegreturn_release(void *calldata)
@@ -3481,7 +3651,7 @@ static void nfs4_delegreturn_prepare(struct rpc_task *task, void *data)
 
         d_data = (struct nfs4_delegreturndata *)data;
 
-        if (nfs4_setup_sequence(d_data->res.server->nfs_client,
+        if (nfs4_setup_sequence(d_data->res.server,
                                 &d_data->args.seq_args,
                                 &d_data->res.seq_res, 1, task))
                 return;
@@ -3514,7 +3684,7 @@ static int _nfs4_proc_delegreturn(struct inode *inode, struct rpc_cred *cred, co
         };
         int status = 0;
 
-        data = kzalloc(sizeof(*data), GFP_KERNEL);
+        data = kzalloc(sizeof(*data), GFP_NOFS);
         if (data == NULL)
                 return -ENOMEM;
         data->args.fhandle = &data->fh;
@@ -3524,14 +3694,13 @@ 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;
 
         task_setup_data.callback_data = data;
-        msg.rpc_argp = &data->args,
-        msg.rpc_resp = &data->res,
+        msg.rpc_argp = &data->args;
+        msg.rpc_resp = &data->res;
         task = rpc_run_task(&task_setup_data);
         if (IS_ERR(task))
                 return PTR_ERR(task);
@@ -3610,6 +3779,7 @@ 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;
+        arg.lock_owner.s_dev = server->s_dev;
         status = nfs4_call_sync(server, &msg, &arg, &res, 1);
         switch (status) {
                 case 0:
@@ -3670,14 +3840,13 @@ static struct nfs4_unlockdata *nfs4_alloc_unlockdata(struct file_lock *fl,
         struct nfs4_unlockdata *p;
         struct inode *inode = lsp->ls_state->inode;
 
-        p = kzalloc(sizeof(*p), GFP_KERNEL);
+        p = kzalloc(sizeof(*p), GFP_NOFS);
         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);
@@ -3701,9 +3870,7 @@ 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))
+        if (!nfs4_sequence_done(task, &calldata->res.seq_res))
                 return;
         switch (task->tk_status) {
                 case 0:
@@ -3719,11 +3886,9 @@ static void nfs4_locku_done(struct rpc_task *task, void *data)
                         break;
                 default:
                         if (nfs4_async_handle_error(task, calldata->server, NULL) == -EAGAIN)
-                                nfs4_restart_rpc(task,
-                                                calldata->server->nfs_client);
+                                nfs_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)
@@ -3738,7 +3903,7 @@ static void nfs4_locku_prepare(struct rpc_task *task, void *data)
                 return;
         }
         calldata->timestamp = jiffies;
-        if (nfs4_setup_sequence(calldata->server->nfs_client,
+        if (nfs4_setup_sequence(calldata->server,
                                 &calldata->arg.seq_args,
                                 &calldata->res.seq_res, 1, task))
                 return;
@@ -3780,8 +3945,8 @@ static struct rpc_task *nfs4_do_unlck(struct file_lock *fl,
                 return ERR_PTR(-ENOMEM);
         }
 
-        msg.rpc_argp = &data->arg,
-        msg.rpc_resp = &data->res,
+        msg.rpc_argp = &data->arg;
+        msg.rpc_resp = &data->res;
         task_setup_data.callback_data = data;
         return rpc_run_task(&task_setup_data);
 }
@@ -3810,7 +3975,7 @@ static int nfs4_proc_unlck(struct nfs4_state *state, int cmd, struct file_lock *
         if (test_bit(NFS_DELEGATED_STATE, &state->flags))
                 goto out;
         lsp = request->fl_u.nfs4_fl.owner;
-        seqid = nfs_alloc_seqid(&lsp->ls_seqid);
+        seqid = nfs_alloc_seqid(&lsp->ls_seqid, GFP_KERNEL);
         status = -ENOMEM;
         if (seqid == NULL)
                 goto out;
@@ -3838,29 +4003,30 @@ struct nfs4_lockdata {
 };
 
 static struct nfs4_lockdata *nfs4_alloc_lockdata(struct file_lock *fl,
-                struct nfs_open_context *ctx, struct nfs4_lock_state *lsp)
+                struct nfs_open_context *ctx, struct nfs4_lock_state *lsp,
+                gfp_t gfp_mask)
 {
         struct nfs4_lockdata *p;
         struct inode *inode = lsp->ls_state->inode;
         struct nfs_server *server = NFS_SERVER(inode);
 
-        p = kzalloc(sizeof(*p), GFP_KERNEL);
+        p = kzalloc(sizeof(*p), gfp_mask);
         if (p == NULL)
                 return NULL;
 
         p->arg.fh = NFS_FH(inode);
         p->arg.fl = &p->fl;
-        p->arg.open_seqid = nfs_alloc_seqid(&lsp->ls_state->owner->so_seqid);
+        p->arg.open_seqid = nfs_alloc_seqid(&lsp->ls_state->owner->so_seqid, gfp_mask);
         if (p->arg.open_seqid == NULL)
                 goto out_free;
-        p->arg.lock_seqid = nfs_alloc_seqid(&lsp->ls_seqid);
+        p->arg.lock_seqid = nfs_alloc_seqid(&lsp->ls_seqid, gfp_mask);
         if (p->arg.lock_seqid == NULL)
                 goto out_free_seqid;
         p->arg.lock_stateid = &lsp->ls_stateid;
         p->arg.lock_owner.clientid = server->nfs_client->cl_clientid;
         p->arg.lock_owner.id = lsp->ls_id.id;
+        p->arg.lock_owner.s_dev = server->s_dev;
         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);
@@ -3892,25 +4058,30 @@ 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,
+        if (nfs4_setup_sequence(data->server,
+                                &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);
 }
 
+static void nfs4_recover_lock_prepare(struct rpc_task *task, void *calldata)
+{
+        rpc_task_set_priority(task, RPC_PRIORITY_PRIVILEGED);
+        nfs4_lock_prepare(task, calldata);
+}
+
 static void nfs4_lock_done(struct rpc_task *task, void *calldata)
 {
         struct nfs4_lockdata *data = calldata;
 
         dprintk("%s: begin!\n", __func__);
 
-        nfs4_sequence_done_free_slot(data->server, &data->res.seq_res,
-                                     task->tk_status);
+        if (!nfs4_sequence_done(task, &data->res.seq_res))
+                return;
 
         data->rpc_status = task->tk_status;
-        if (RPC_ASSASSINATED(task))
-                goto out;
         if (data->arg.new_lock_owner != 0) {
                 if (data->rpc_status == 0)
                         nfs_confirm_seqid(&data->lsp->ls_seqid, 0);
@@ -3954,7 +4125,35 @@ static const struct rpc_call_ops nfs4_lock_ops = {
         .rpc_release = nfs4_lock_release,
 };
 
-static int _nfs4_do_setlk(struct nfs4_state *state, int cmd, struct file_lock *fl, int reclaim)
+static const struct rpc_call_ops nfs4_recover_lock_ops = {
+        .rpc_call_prepare = nfs4_recover_lock_prepare,
+        .rpc_call_done = nfs4_lock_done,
+        .rpc_release = nfs4_lock_release,
+};
+
+static void nfs4_handle_setlk_error(struct nfs_server *server, struct nfs4_lock_state *lsp, int new_lock_owner, int error)
+{
+        struct nfs_client *clp = server->nfs_client;
+        struct nfs4_state *state = lsp->ls_state;
+
+        switch (error) {
+        case -NFS4ERR_ADMIN_REVOKED:
+        case -NFS4ERR_BAD_STATEID:
+        case -NFS4ERR_EXPIRED:
+                if (new_lock_owner != 0 ||
+                   (lsp->ls_flags & NFS_LOCK_INITIALIZED) != 0)
+                        nfs4_state_mark_reclaim_nograce(clp, state);
+                lsp->ls_seqid.flags &= ~NFS_SEQID_CONFIRMED;
+                break;
+        case -NFS4ERR_STALE_STATEID:
+                if (new_lock_owner != 0 ||
+                    (lsp->ls_flags & NFS_LOCK_INITIALIZED) != 0)
+                        nfs4_state_mark_reclaim_reboot(clp, state);
+                lsp->ls_seqid.flags &= ~NFS_SEQID_CONFIRMED;
+        };
+}
+
+static int _nfs4_do_setlk(struct nfs4_state *state, int cmd, struct file_lock *fl, int recovery_type)
 {
         struct nfs4_lockdata *data;
         struct rpc_task *task;
@@ -3973,15 +4172,19 @@ static int _nfs4_do_setlk(struct nfs4_state *state, int cmd, struct file_lock *f
 
         dprintk("%s: begin!\n", __func__);
         data = nfs4_alloc_lockdata(fl, nfs_file_open_context(fl->fl_file),
-                        fl->fl_u.nfs4_fl.owner);
+                        fl->fl_u.nfs4_fl.owner,
+                        recovery_type == NFS_LOCK_NEW ? GFP_KERNEL : GFP_NOFS);
         if (data == NULL)
                 return -ENOMEM;
         if (IS_SETLKW(cmd))
                 data->arg.block = 1;
-        if (reclaim != 0)
-                data->arg.reclaim = 1;
-        msg.rpc_argp = &data->arg,
-        msg.rpc_resp = &data->res,
+        if (recovery_type > NFS_LOCK_NEW) {
+                if (recovery_type == NFS_LOCK_RECLAIM)
+                        data->arg.reclaim = NFS_LOCK_RECLAIM;
+                task_setup_data.callback_ops = &nfs4_recover_lock_ops;
+        }
+        msg.rpc_argp = &data->arg;
+        msg.rpc_resp = &data->res;
         task_setup_data.callback_data = data;
         task = rpc_run_task(&task_setup_data);
         if (IS_ERR(task))
@@ -3989,6 +4192,9 @@ 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)
+                        nfs4_handle_setlk_error(data->server, data->lsp,
+                                        data->arg.new_lock_owner, ret);
         } else
                 data->cancelled = 1;
         rpc_put_task(task);
@@ -4006,7 +4212,7 @@ static int nfs4_lock_reclaim(struct nfs4_state *state, struct file_lock *request
                 /* Cache the lock if possible... */
                 if (test_bit(NFS_DELEGATED_STATE, &state->flags) != 0)
                         return 0;
-                err = _nfs4_do_setlk(state, F_SETLK, request, 1);
+                err = _nfs4_do_setlk(state, F_SETLK, request, NFS_LOCK_RECLAIM);
                 if (err != -NFS4ERR_DELAY)
                         break;
                 nfs4_handle_exception(server, err, &exception);
@@ -4026,11 +4232,17 @@ static int nfs4_lock_expired(struct nfs4_state *state, struct file_lock *request
         do {
                 if (test_bit(NFS_DELEGATED_STATE, &state->flags) != 0)
                         return 0;
-                err = _nfs4_do_setlk(state, F_SETLK, request, 0);
-                if (err != -NFS4ERR_DELAY)
-                        break;
-                nfs4_handle_exception(server, err, &exception);
+                err = _nfs4_do_setlk(state, F_SETLK, request, NFS_LOCK_EXPIRED);
+                switch (err) {
+                default:
+                        goto out;
+                case -NFS4ERR_GRACE:
+                case -NFS4ERR_DELAY:
+                        nfs4_handle_exception(server, err, &exception);
+                        err = 0;
+                }
         } while (exception.retry);
+out:
         return err;
 }
 
@@ -4038,8 +4250,11 @@ static int _nfs4_proc_setlk(struct nfs4_state *state, int cmd, struct file_lock
 {
         struct nfs_inode *nfsi = NFS_I(state->inode);
         unsigned char fl_flags = request->fl_flags;
-        int status;
+        int status = -ENOLCK;
 
+        if ((fl_flags & FL_POSIX) &&
+                        !test_bit(NFS_STATE_POSIX_LOCKS, &state->flags))
+                goto out;
         /* Is this a delegated open? */
         status = nfs4_set_lock_state(state, request);
         if (status != 0)
@@ -4056,7 +4271,7 @@ static int _nfs4_proc_setlk(struct nfs4_state *state, int cmd, struct file_lock
                 status = do_vfs_lock(request->fl_file, request);
                 goto out_unlock;
         }
-        status = _nfs4_do_setlk(state, cmd, request, 0);
+        status = _nfs4_do_setlk(state, cmd, request, NFS_LOCK_NEW);
         if (status != 0)
                 goto out_unlock;
         /* Note: we always want to sleep here! */
@@ -4100,15 +4315,23 @@ nfs4_proc_lock(struct file *filp, int cmd, struct file_lock *request)
         if (request->fl_start < 0 || request->fl_end < 0)
                 return -EINVAL;
 
-        if (IS_GETLK(cmd))
-                return nfs4_proc_getlk(state, F_GETLK, request);
+        if (IS_GETLK(cmd)) {
+                if (state != NULL)
+                        return nfs4_proc_getlk(state, F_GETLK, request);
+                return 0;
+        }
 
         if (!(IS_SETLK(cmd) || IS_SETLKW(cmd)))
                 return -EINVAL;
 
-        if (request->fl_type == F_UNLCK)
-                return nfs4_proc_unlck(state, cmd, request);
+        if (request->fl_type == F_UNLCK) {
+                if (state != NULL)
+                        return nfs4_proc_unlck(state, cmd, request);
+                return 0;
+        }
 
+        if (state == NULL)
+                return -ENOLCK;
         do {
                 status = nfs4_proc_setlk(state, cmd, request);
                 if ((status != -EAGAIN) || IS_SETLK(cmd))
@@ -4131,7 +4354,7 @@ int nfs4_lock_delegation_recall(struct nfs4_state *state, struct file_lock *fl)
         if (err != 0)
                 goto out;
         do {
-                err = _nfs4_do_setlk(state, F_SETLK, fl, 0);
+                err = _nfs4_do_setlk(state, F_SETLK, fl, NFS_LOCK_NEW);
                 switch (err) {
                         default:
                                 printk(KERN_ERR "%s: unhandled error %d.\n",
@@ -4142,6 +4365,11 @@ int nfs4_lock_delegation_recall(struct nfs4_state *state, struct file_lock *fl)
                         case -NFS4ERR_EXPIRED:
                         case -NFS4ERR_STALE_CLIENTID:
                         case -NFS4ERR_STALE_STATEID:
+                        case -NFS4ERR_BADSESSION:
+                        case -NFS4ERR_BADSLOT:
+                        case -NFS4ERR_BAD_HIGH_SLOT:
+                        case -NFS4ERR_CONN_NOT_BOUND_TO_SESSION:
+                        case -NFS4ERR_DEADSESSION:
                                 nfs4_schedule_state_recovery(server->nfs_client);
                                 goto out;
                         case -ERESTARTSYS:
@@ -4155,6 +4383,15 @@ int nfs4_lock_delegation_recall(struct nfs4_state *state, struct file_lock *fl)
                                 nfs4_state_mark_reclaim_nograce(server->nfs_client, state);
                                 err = 0;
                                 goto out;
+                        case -EKEYEXPIRED:
+                                /*
+                                 * User RPCSEC_GSS context has expired.
+                                 * We cannot recover this stateid now, so
+                                 * skip it and allow recovery thread to
+                                 * proceed.
+                                 */
+                                err = 0;
+                                goto out;
                         case -ENOMEM:
                         case -NFS4ERR_DENIED:
                                 /* kill_proc(fl->fl_pid, SIGLOST, 1); */
@@ -4169,44 +4406,67 @@ out:
         return err;
 }
 
-#define XATTR_NAME_NFSV4_ACL "system.nfs4_acl"
-
-int nfs4_setxattr(struct dentry *dentry, const char *key, const void *buf,
-                size_t buflen, int flags)
+static void nfs4_release_lockowner_release(void *calldata)
 {
-        struct inode *inode = dentry->d_inode;
+        kfree(calldata);
+}
 
-        if (strcmp(key, XATTR_NAME_NFSV4_ACL) != 0)
-                return -EOPNOTSUPP;
+const struct rpc_call_ops nfs4_release_lockowner_ops = {
+        .rpc_release = nfs4_release_lockowner_release,
+};
+
+void nfs4_release_lockowner(const struct nfs4_lock_state *lsp)
+{
+        struct nfs_server *server = lsp->ls_state->owner->so_server;
+        struct nfs_release_lockowner_args *args;
+        struct rpc_message msg = {
+                .rpc_proc = &nfs4_procedures[NFSPROC4_CLNT_RELEASE_LOCKOWNER],
+        };
 
-        return nfs4_proc_set_acl(inode, buf, buflen);
+        if (server->nfs_client->cl_mvops->minor_version != 0)
+                return;
+        args = kmalloc(sizeof(*args), GFP_NOFS);
+        if (!args)
+                return;
+        args->lock_owner.clientid = server->nfs_client->cl_clientid;
+        args->lock_owner.id = lsp->ls_id.id;
+        args->lock_owner.s_dev = server->s_dev;
+        msg.rpc_argp = args;
+        rpc_call_async(server->client, &msg, 0, &nfs4_release_lockowner_ops, args);
 }
 
-/* The getxattr man page suggests returning -ENODATA for unknown attributes,
- * and that's what we'll do for e.g. user attributes that haven't been set.
- * But we'll follow ext2/ext3's lead by returning -EOPNOTSUPP for unsupported
- * attributes in kernel-managed attribute namespaces. */
-ssize_t nfs4_getxattr(struct dentry *dentry, const char *key, void *buf,
-                size_t buflen)
+#define XATTR_NAME_NFSV4_ACL "system.nfs4_acl"
+
+static int nfs4_xattr_set_nfs4_acl(struct dentry *dentry, const char *key,
+                                   const void *buf, size_t buflen,
+                                   int flags, int type)
 {
-        struct inode *inode = dentry->d_inode;
+        if (strcmp(key, "") != 0)
+                return -EINVAL;
 
-        if (strcmp(key, XATTR_NAME_NFSV4_ACL) != 0)
-                return -EOPNOTSUPP;
+        return nfs4_proc_set_acl(dentry->d_inode, buf, buflen);
+}
 
-        return nfs4_proc_get_acl(inode, buf, buflen);
+static int nfs4_xattr_get_nfs4_acl(struct dentry *dentry, const char *key,
+                                   void *buf, size_t buflen, int type)
+{
+        if (strcmp(key, "") != 0)
+                return -EINVAL;
+
+        return nfs4_proc_get_acl(dentry->d_inode, buf, buflen);
 }
 
-ssize_t nfs4_listxattr(struct dentry *dentry, char *buf, size_t buflen)
+static size_t nfs4_xattr_list_nfs4_acl(struct dentry *dentry, char *list,
+                                       size_t list_len, const char *name,
+                                       size_t name_len, int type)
 {
-        size_t len = strlen(XATTR_NAME_NFSV4_ACL) + 1;
+        size_t len = sizeof(XATTR_NAME_NFSV4_ACL);
 
         if (!nfs4_server_supports_acls(NFS_SERVER(dentry->d_inode)))
                 return 0;
-        if (buf && buflen < len)
-                return -ERANGE;
-        if (buf)
-                memcpy(buf, XATTR_NAME_NFSV4_ACL, len);
+
+        if (list && len <= list_len)
+                memcpy(list, XATTR_NAME_NFSV4_ACL, len);
         return len;
 }
 
@@ -4259,6 +4519,25 @@ int nfs4_proc_fs_locations(struct inode *dir, const struct qstr *name,
 
 #ifdef CONFIG_NFS_V4_1
 /*
+ * Check the exchange flags returned by the server for invalid flags, having
+ * both PNFS and NON_PNFS flags set, and not having one of NON_PNFS, PNFS, or
+ * DS flags set.
+ */
+static int nfs4_check_cl_exchange_flags(u32 flags)
+{
+        if (flags & ~EXCHGID4_FLAG_MASK_R)
+                goto out_inval;
+        if ((flags & EXCHGID4_FLAG_USE_PNFS_MDS) &&
+            (flags & EXCHGID4_FLAG_USE_NON_PNFS))
+                goto out_inval;
+        if (!(flags & (EXCHGID4_FLAG_MASK_PNFS)))
+                goto out_inval;
+        return NFS_OK;
+out_inval:
+        return -NFS4ERR_INVAL;
+}
+
+/*
  * nfs4_proc_exchange_id()
  *
  * Since the clientid has expired, all compounds using sessions
@@ -4266,12 +4545,12 @@ int nfs4_proc_fs_locations(struct inode *dir, const struct qstr *name,
  * 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)
+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,
+                .flags = EXCHGID4_FLAG_SUPP_MOVED_REFER,
         };
         struct nfs41_exchange_id_res res = {
                 .client = clp,
@@ -4303,7 +4582,7 @@ static int nfs4_proc_exchange_id(struct nfs_client *clp, struct rpc_cred *cred)
 
                 status = rpc_call_sync(clp->cl_rpcclient, &msg, 0);
 
-                if (status != NFS4ERR_CLID_INUSE)
+                if (status != -NFS4ERR_CLID_INUSE)
                         break;
 
                 if (signalled())
@@ -4313,6 +4592,7 @@ static int nfs4_proc_exchange_id(struct nfs_client *clp, struct rpc_cred *cred)
                         break;
         }
 
+        status = nfs4_check_cl_exchange_flags(clp->cl_exchange_flags);
         dprintk("<-- %s status= %d\n", __func__, status);
         return status;
 }
@@ -4331,11 +4611,12 @@ static void nfs4_get_lease_time_prepare(struct rpc_task *task,
                         (struct nfs4_get_lease_time_data *)calldata;
 
         dprintk("--> %s\n", __func__);
+        rpc_task_set_priority(task, RPC_PRIORITY_PRIVILEGED);
         /* 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);
+                                   &data->args->la_seq_args,
+                                   &data->res->lr_seq_res, 0, task);
 
         BUG_ON(ret == -EAGAIN);
         rpc_call_start(task);
@@ -4352,17 +4633,17 @@ static void nfs4_get_lease_time_done(struct rpc_task *task, void *calldata)
                         (struct nfs4_get_lease_time_data *)calldata;
 
         dprintk("--> %s\n", __func__);
-        nfs41_sequence_done(data->clp, &data->res->lr_seq_res, task->tk_status);
+        if (!nfs41_sequence_done(task, &data->res->lr_seq_res))
+                return;
         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);
+                nfs_restart_rpc(task, data->clp);
                 return;
         }
-        nfs41_sequence_free_slot(data->clp, &data->res->lr_seq_res);
         dprintk("<-- %s\n", __func__);
 }
 
@@ -4396,7 +4677,6 @@ int nfs4_proc_get_lease_time(struct nfs_client *clp, struct nfs_fsinfo *fsinfo)
         };
         int status;
 
-        res.lr_seq_res.sr_slotid = NFS4_MAX_SLOT_TABLE;
         dprintk("--> %s\n", __func__);
         task = rpc_run_task(&task_setup);
 
@@ -4414,28 +4694,33 @@ int nfs4_proc_get_lease_time(struct nfs_client *clp, struct nfs_fsinfo *fsinfo)
 /*
  * Reset a slot table
  */
-static int nfs4_reset_slot_table(struct nfs4_slot_table *tbl, int max_slots,
-                int old_max_slots, int ivalue)
+static int nfs4_reset_slot_table(struct nfs4_slot_table *tbl, u32 max_reqs,
+                                 int ivalue)
 {
+        struct nfs4_slot *new = NULL;
         int i;
         int ret = 0;
 
-        dprintk("--> %s: max_reqs=%u, tbl %p\n", __func__, max_slots, tbl);
+        dprintk("--> %s: max_reqs=%u, tbl->max_slots %d\n", __func__,
+                max_reqs, tbl->max_slots);
 
-        /*
-         * 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;
+        /* Does the newly negotiated max_reqs match the existing slot table? */
+        if (max_reqs != tbl->max_slots) {
+                ret = -ENOMEM;
+                new = kmalloc(max_reqs * sizeof(struct nfs4_slot),
+                              GFP_NOFS);
+                if (!new)
+                        goto out;
+                ret = 0;
+                kfree(tbl->slots);
         }
         spin_lock(&tbl->slot_tbl_lock);
-        for (i = 0; i < max_slots; ++i)
+        if (new) {
+                tbl->slots = new;
+                tbl->max_slots = max_reqs;
+        }
+        for (i = 0; i < tbl->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);
@@ -4452,16 +4737,12 @@ 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);
+                        session->fc_attrs.max_reqs, 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);
+                        session->bc_attrs.max_reqs, 0);
         return status;
 }
 
@@ -4485,7 +4766,6 @@ static void nfs4_destroy_slot_tables(struct nfs4_session *session)
 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;
 
@@ -4493,21 +4773,12 @@ static int nfs4_init_slot_table(struct nfs4_slot_table *tbl,
 
         dprintk("--> %s: max_reqs=%u\n", __func__, max_slots);
 
-        slot = kcalloc(max_slots, sizeof(struct nfs4_slot), GFP_KERNEL);
+        slot = kcalloc(max_slots, sizeof(struct nfs4_slot), GFP_NOFS);
         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 */
@@ -4517,10 +4788,6 @@ static int nfs4_init_slot_table(struct nfs4_slot_table *tbl,
 out:
         dprintk("<-- %s: return %d\n", __func__, ret);
         return ret;
-
-out_free:
-        kfree(slot);
-        goto out;
 }
 
 /*
@@ -4528,17 +4795,24 @@ out_free:
  */
 static int nfs4_init_slot_tables(struct nfs4_session *session)
 {
-        int status;
+        struct nfs4_slot_table *tbl;
+        int status = 0;
 
-        status = nfs4_init_slot_table(&session->fc_slot_table,
-                        session->fc_attrs.max_reqs, 1);
-        if (status)
-                return status;
+        tbl = &session->fc_slot_table;
+        if (tbl->slots == NULL) {
+                status = nfs4_init_slot_table(tbl,
+                                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);
+        tbl = &session->bc_slot_table;
+        if (tbl->slots == NULL) {
+                status = nfs4_init_slot_table(tbl,
+                                session->bc_attrs.max_reqs, 0);
+                if (status)
+                        nfs4_destroy_slot_tables(session);
+        }
 
         return status;
 }
@@ -4548,26 +4822,23 @@ 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);
+        session = kzalloc(sizeof(struct nfs4_session), GFP_NOFS);
         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;
+        tbl->highest_used_slotid = -1;
         spin_lock_init(&tbl->slot_tbl_lock);
-        rpc_init_wait_queue(&tbl->slot_tbl_waitq, "ForeChannel Slot table");
+        rpc_init_priority_wait_queue(&tbl->slot_tbl_waitq, "ForeChannel Slot table");
+        init_completion(&tbl->complete);
 
         tbl = &session->bc_slot_table;
+        tbl->highest_used_slotid = -1;
         spin_lock_init(&tbl->slot_tbl_lock);
         rpc_init_wait_queue(&tbl->slot_tbl_waitq, "BackChannel Slot table");
+        init_completion(&tbl->complete);
+
+        session->session_state = 1<<NFS4_SESSION_INITING;
 
         session->clp = clp;
         return session;
@@ -4607,16 +4878,14 @@ static void nfs4_init_channel_attrs(struct nfs41_create_session_args *args)
         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",
+                "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);
+                args->fc_attrs.max_ops, args->fc_attrs.max_reqs);
 
         /* Back channel attributes */
         args->bc_attrs.headerpadsz = 0;
@@ -4634,49 +4903,56 @@ static void nfs4_init_channel_attrs(struct nfs41_create_session_args *args)
                 args->bc_attrs.max_reqs);
 }
 
-static int _verify_channel_attr(char *chan, char *attr_name, u32 sent, u32 rcvd)
+static int nfs4_verify_fore_channel_attrs(struct nfs41_create_session_args *args, struct nfs4_session *session)
 {
-        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;
+        struct nfs4_channel_attrs *sent = &args->fc_attrs;
+        struct nfs4_channel_attrs *rcvd = &session->fc_attrs;
+
+        if (rcvd->headerpadsz > sent->headerpadsz)
+                return -EINVAL;
+        if (rcvd->max_resp_sz > sent->max_resp_sz)
+                return -EINVAL;
+        /*
+         * Our requested max_ops is the minimum we need; we're not
+         * prepared to break up compounds into smaller pieces than that.
+         * So, no point even trying to continue if the server won't
+         * cooperate:
+         */
+        if (rcvd->max_ops < sent->max_ops)
+                return -EINVAL;
+        if (rcvd->max_reqs == 0)
+                return -EINVAL;
+        return 0;
 }
 
-#define _verify_fore_channel_attr(_name_) \
-        _verify_channel_attr("fore", #_name_, \
-                             args->fc_attrs._name_, \
-                             session->fc_attrs._name_)
+static int nfs4_verify_back_channel_attrs(struct nfs41_create_session_args *args, struct nfs4_session *session)
+{
+        struct nfs4_channel_attrs *sent = &args->bc_attrs;
+        struct nfs4_channel_attrs *rcvd = &session->bc_attrs;
 
-#define _verify_back_channel_attr(_name_) \
-        _verify_channel_attr("back", #_name_, \
-                             args->bc_attrs._name_, \
-                             session->bc_attrs._name_)
+        if (rcvd->max_rqst_sz > sent->max_rqst_sz)
+                return -EINVAL;
+        if (rcvd->max_resp_sz < sent->max_resp_sz)
+                return -EINVAL;
+        if (rcvd->max_resp_sz_cached > sent->max_resp_sz_cached)
+                return -EINVAL;
+        /* These would render the backchannel useless: */
+        if (rcvd->max_ops  == 0)
+                return -EINVAL;
+        if (rcvd->max_reqs == 0)
+                return -EINVAL;
+        return 0;
+}
 
-/*
- * 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);
+        int ret;
 
-        return ret;
+        ret = nfs4_verify_fore_channel_attrs(args, session);
+        if (ret)
+                return ret;
+        return nfs4_verify_back_channel_attrs(args, session);
 }
 
 static int _nfs4_proc_create_session(struct nfs_client *clp)
@@ -4717,11 +4993,10 @@ static int _nfs4_proc_create_session(struct nfs_client *clp)
  * 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 nfs4_proc_create_session(struct nfs_client *clp)
 {
         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);
@@ -4730,35 +5005,19 @@ int nfs4_proc_create_session(struct nfs_client *clp, int reset)
         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);
+        /* Init and reset the fore channel */
+        status = nfs4_init_slot_tables(session);
+        dprintk("slot table initialization returned %d\n", status);
+        if (status)
+                goto out;
+        status = nfs4_reset_slot_tables(session);
+        dprintk("slot table reset 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;
@@ -4794,63 +5053,102 @@ int nfs4_proc_destroy_session(struct nfs4_session *session)
         return status;
 }
 
+int nfs4_init_session(struct nfs_server *server)
+{
+        struct nfs_client *clp = server->nfs_client;
+        struct nfs4_session *session;
+        unsigned int rsize, wsize;
+        int ret;
+
+        if (!nfs4_has_session(clp))
+                return 0;
+
+        session = clp->cl_session;
+        if (!test_and_clear_bit(NFS4_SESSION_INITING, &session->session_state))
+                return 0;
+
+        rsize = server->rsize;
+        if (rsize == 0)
+                rsize = NFS_MAX_FILE_IO_SIZE;
+        wsize = server->wsize;
+        if (wsize == 0)
+                wsize = NFS_MAX_FILE_IO_SIZE;
+
+        session->fc_attrs.max_rqst_sz = wsize + nfs41_maxwrite_overhead;
+        session->fc_attrs.max_resp_sz = rsize + nfs41_maxread_overhead;
+
+        ret = nfs4_recover_expired_lease(server);
+        if (!ret)
+                ret = nfs4_check_client_ready(clp);
+        return ret;
+}
+
 /*
  * Renew the cl_session lease.
  */
-static int nfs4_proc_sequence(struct nfs_client *clp, struct rpc_cred *cred)
-{
+struct nfs4_sequence_data {
+        struct nfs_client *clp;
         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,
-        };
+static void nfs41_sequence_release(void *data)
+{
+        struct nfs4_sequence_data *calldata = data;
+        struct nfs_client *clp = calldata->clp;
 
-        args.sa_cache_this = 0;
+        if (atomic_read(&clp->cl_count) > 1)
+                nfs4_schedule_state_renewal(clp);
+        nfs_put_client(clp);
+        kfree(calldata);
+}
 
-        return nfs4_call_sync_sequence(clp, clp->cl_rpcclient, &msg, &args,
-                                       &res, 0);
+static int nfs41_sequence_handle_errors(struct rpc_task *task, struct nfs_client *clp)
+{
+        switch(task->tk_status) {
+        case -NFS4ERR_DELAY:
+                rpc_delay(task, NFS4_POLL_RETRY_MAX);
+                return -EAGAIN;
+        default:
+                nfs4_schedule_state_recovery(clp);
+        }
+        return 0;
 }
 
-void nfs41_sequence_call_done(struct rpc_task *task, void *data)
+static void nfs41_sequence_call_done(struct rpc_task *task, void *data)
 {
-        struct nfs_client *clp = (struct nfs_client *)data;
+        struct nfs4_sequence_data *calldata = data;
+        struct nfs_client *clp = calldata->clp;
 
-        nfs41_sequence_done(clp, task->tk_msg.rpc_resp, task->tk_status);
+        if (!nfs41_sequence_done(task, task->tk_msg.rpc_resp))
+                return;
 
         if (task->tk_status < 0) {
                 dprintk("%s ERROR %d\n", __func__, task->tk_status);
+                if (atomic_read(&clp->cl_count) == 1)
+                        goto out;
 
-                if (_nfs4_async_handle_error(task, NULL, clp, NULL)
-                                                                == -EAGAIN) {
-                        nfs4_restart_rpc(task, clp);
+                if (nfs41_sequence_handle_errors(task, clp) == -EAGAIN) {
+                        rpc_restart_call_prepare(task);
                         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);
-
+out:
         dprintk("<-- %s\n", __func__);
 }
 
 static void nfs41_sequence_prepare(struct rpc_task *task, void *data)
 {
-        struct nfs_client *clp;
+        struct nfs4_sequence_data *calldata = data;
+        struct nfs_client *clp = calldata->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))
+        if (nfs41_setup_sequence(clp->cl_session, args, res, 0, task))
                 return;
         rpc_call_start(task);
 }
@@ -4858,33 +5156,320 @@ static void nfs41_sequence_prepare(struct rpc_task *task, void *data)
 static const struct rpc_call_ops nfs41_sequence_ops = {
         .rpc_call_done = nfs41_sequence_call_done,
         .rpc_call_prepare = nfs41_sequence_prepare,
+        .rpc_release = nfs41_sequence_release,
 };
 
-static int nfs41_proc_async_sequence(struct nfs_client *clp,
-                                     struct rpc_cred *cred)
+static struct rpc_task *_nfs41_proc_sequence(struct nfs_client *clp, struct rpc_cred *cred)
 {
-        struct nfs4_sequence_args *args;
-        struct nfs4_sequence_res *res;
+        struct nfs4_sequence_data *calldata;
         struct rpc_message msg = {
                 .rpc_proc = &nfs4_procedures[NFSPROC4_CLNT_SEQUENCE],
                 .rpc_cred = cred,
         };
+        struct rpc_task_setup task_setup_data = {
+                .rpc_client = clp->cl_rpcclient,
+                .rpc_message = &msg,
+                .callback_ops = &nfs41_sequence_ops,
+                .flags = RPC_TASK_ASYNC | RPC_TASK_SOFT,
+        };
 
-        args = kzalloc(sizeof(*args), GFP_KERNEL);
-        if (!args)
-                return -ENOMEM;
-        res = kzalloc(sizeof(*res), GFP_KERNEL);
-        if (!res) {
-                kfree(args);
+        if (!atomic_inc_not_zero(&clp->cl_count))
+                return ERR_PTR(-EIO);
+        calldata = kzalloc(sizeof(*calldata), GFP_NOFS);
+        if (calldata == NULL) {
+                nfs_put_client(clp);
+                return ERR_PTR(-ENOMEM);
+        }
+        msg.rpc_argp = &calldata->args;
+        msg.rpc_resp = &calldata->res;
+        calldata->clp = clp;
+        task_setup_data.callback_data = calldata;
+
+        return rpc_run_task(&task_setup_data);
+}
+
+static int nfs41_proc_async_sequence(struct nfs_client *clp, struct rpc_cred *cred)
+{
+        struct rpc_task *task;
+        int ret = 0;
+
+        task = _nfs41_proc_sequence(clp, cred);
+        if (IS_ERR(task))
+                ret = PTR_ERR(task);
+        else
+                rpc_put_task(task);
+        dprintk("<-- %s status=%d\n", __func__, ret);
+        return ret;
+}
+
+static int nfs4_proc_sequence(struct nfs_client *clp, struct rpc_cred *cred)
+{
+        struct rpc_task *task;
+        int ret;
+
+        task = _nfs41_proc_sequence(clp, cred);
+        if (IS_ERR(task)) {
+                ret = PTR_ERR(task);
+                goto out;
+        }
+        ret = rpc_wait_for_completion_task(task);
+        if (!ret)
+                ret = task->tk_status;
+        rpc_put_task(task);
+out:
+        dprintk("<-- %s status=%d\n", __func__, ret);
+        return ret;
+}
+
+struct nfs4_reclaim_complete_data {
+        struct nfs_client *clp;
+        struct nfs41_reclaim_complete_args arg;
+        struct nfs41_reclaim_complete_res res;
+};
+
+static void nfs4_reclaim_complete_prepare(struct rpc_task *task, void *data)
+{
+        struct nfs4_reclaim_complete_data *calldata = data;
+
+        rpc_task_set_priority(task, RPC_PRIORITY_PRIVILEGED);
+        if (nfs41_setup_sequence(calldata->clp->cl_session,
+                                &calldata->arg.seq_args,
+                                &calldata->res.seq_res, 0, task))
+                return;
+
+        rpc_call_start(task);
+}
+
+static int nfs41_reclaim_complete_handle_errors(struct rpc_task *task, struct nfs_client *clp)
+{
+        switch(task->tk_status) {
+        case 0:
+        case -NFS4ERR_COMPLETE_ALREADY:
+        case -NFS4ERR_WRONG_CRED: /* What to do here? */
+                break;
+        case -NFS4ERR_DELAY:
+                rpc_delay(task, NFS4_POLL_RETRY_MAX);
+                return -EAGAIN;
+        default:
+                nfs4_schedule_state_recovery(clp);
+        }
+        return 0;
+}
+
+static void nfs4_reclaim_complete_done(struct rpc_task *task, void *data)
+{
+        struct nfs4_reclaim_complete_data *calldata = data;
+        struct nfs_client *clp = calldata->clp;
+        struct nfs4_sequence_res *res = &calldata->res.seq_res;
+
+        dprintk("--> %s\n", __func__);
+        if (!nfs41_sequence_done(task, res))
+                return;
+
+        if (nfs41_reclaim_complete_handle_errors(task, clp) == -EAGAIN) {
+                rpc_restart_call_prepare(task);
+                return;
+        }
+        dprintk("<-- %s\n", __func__);
+}
+
+static void nfs4_free_reclaim_complete_data(void *data)
+{
+        struct nfs4_reclaim_complete_data *calldata = data;
+
+        kfree(calldata);
+}
+
+static const struct rpc_call_ops nfs4_reclaim_complete_call_ops = {
+        .rpc_call_prepare = nfs4_reclaim_complete_prepare,
+        .rpc_call_done = nfs4_reclaim_complete_done,
+        .rpc_release = nfs4_free_reclaim_complete_data,
+};
+
+/*
+ * Issue a global reclaim complete.
+ */
+static int nfs41_proc_reclaim_complete(struct nfs_client *clp)
+{
+        struct nfs4_reclaim_complete_data *calldata;
+        struct rpc_task *task;
+        struct rpc_message msg = {
+                .rpc_proc = &nfs4_procedures[NFSPROC4_CLNT_RECLAIM_COMPLETE],
+        };
+        struct rpc_task_setup task_setup_data = {
+                .rpc_client = clp->cl_rpcclient,
+                .rpc_message = &msg,
+                .callback_ops = &nfs4_reclaim_complete_call_ops,
+                .flags = RPC_TASK_ASYNC,
+        };
+        int status = -ENOMEM;
+
+        dprintk("--> %s\n", __func__);
+        calldata = kzalloc(sizeof(*calldata), GFP_NOFS);
+        if (calldata == NULL)
+                goto out;
+        calldata->clp = clp;
+        calldata->arg.one_fs = 0;
+
+        msg.rpc_argp = &calldata->arg;
+        msg.rpc_resp = &calldata->res;
+        task_setup_data.callback_data = calldata;
+        task = rpc_run_task(&task_setup_data);
+        if (IS_ERR(task)) {
+                status = PTR_ERR(task);
+                goto out;
+        }
+        rpc_put_task(task);
+        return 0;
+out:
+        dprintk("<-- %s status=%d\n", __func__, status);
+        return status;
+}
+
+static void
+nfs4_layoutget_prepare(struct rpc_task *task, void *calldata)
+{
+        struct nfs4_layoutget *lgp = calldata;
+        struct nfs_server *server = NFS_SERVER(lgp->args.inode);
+
+        dprintk("--> %s\n", __func__);
+        /* Note the is a race here, where a CB_LAYOUTRECALL can come in
+         * right now covering the LAYOUTGET we are about to send.
+         * However, that is not so catastrophic, and there seems
+         * to be no way to prevent it completely.
+         */
+        if (nfs4_setup_sequence(server, &lgp->args.seq_args,
+                                &lgp->res.seq_res, 0, task))
+                return;
+        if (pnfs_choose_layoutget_stateid(&lgp->args.stateid,
+                                          NFS_I(lgp->args.inode)->layout,
+                                          lgp->args.ctx->state)) {
+                rpc_exit(task, NFS4_OK);
+                return;
+        }
+        rpc_call_start(task);
+}
+
+static void nfs4_layoutget_done(struct rpc_task *task, void *calldata)
+{
+        struct nfs4_layoutget *lgp = calldata;
+        struct nfs_server *server = NFS_SERVER(lgp->args.inode);
+
+        dprintk("--> %s\n", __func__);
+
+        if (!nfs4_sequence_done(task, &lgp->res.seq_res))
+                return;
+
+        switch (task->tk_status) {
+        case 0:
+                break;
+        case -NFS4ERR_LAYOUTTRYLATER:
+        case -NFS4ERR_RECALLCONFLICT:
+                task->tk_status = -NFS4ERR_DELAY;
+                /* Fall through */
+        default:
+                if (nfs4_async_handle_error(task, server, NULL) == -EAGAIN) {
+                        rpc_restart_call_prepare(task);
+                        return;
+                }
+        }
+        dprintk("<-- %s\n", __func__);
+}
+
+static void nfs4_layoutget_release(void *calldata)
+{
+        struct nfs4_layoutget *lgp = calldata;
+
+        dprintk("--> %s\n", __func__);
+        if (lgp->res.layout.buf != NULL)
+                free_page((unsigned long) lgp->res.layout.buf);
+        put_nfs_open_context(lgp->args.ctx);
+        kfree(calldata);
+        dprintk("<-- %s\n", __func__);
+}
+
+static const struct rpc_call_ops nfs4_layoutget_call_ops = {
+        .rpc_call_prepare = nfs4_layoutget_prepare,
+        .rpc_call_done = nfs4_layoutget_done,
+        .rpc_release = nfs4_layoutget_release,
+};
+
+int nfs4_proc_layoutget(struct nfs4_layoutget *lgp)
+{
+        struct nfs_server *server = NFS_SERVER(lgp->args.inode);
+        struct rpc_task *task;
+        struct rpc_message msg = {
+                .rpc_proc = &nfs4_procedures[NFSPROC4_CLNT_LAYOUTGET],
+                .rpc_argp = &lgp->args,
+                .rpc_resp = &lgp->res,
+        };
+        struct rpc_task_setup task_setup_data = {
+                .rpc_client = server->client,
+                .rpc_message = &msg,
+                .callback_ops = &nfs4_layoutget_call_ops,
+                .callback_data = lgp,
+                .flags = RPC_TASK_ASYNC,
+        };
+        int status = 0;
+
+        dprintk("--> %s\n", __func__);
+
+        lgp->res.layout.buf = (void *)__get_free_page(GFP_NOFS);
+        if (lgp->res.layout.buf == NULL) {
+                nfs4_layoutget_release(lgp);
                 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);
+        lgp->res.seq_res.sr_slot = NULL;
+        task = rpc_run_task(&task_setup_data);
+        if (IS_ERR(task))
+                return PTR_ERR(task);
+        status = nfs4_wait_for_completion_rpc_task(task);
+        if (status == 0)
+                status = task->tk_status;
+        if (status == 0)
+                status = pnfs_layout_process(lgp);
+        rpc_put_task(task);
+        dprintk("<-- %s status=%d\n", __func__, status);
+        return status;
+}
+
+static int
+_nfs4_proc_getdeviceinfo(struct nfs_server *server, struct pnfs_device *pdev)
+{
+        struct nfs4_getdeviceinfo_args args = {
+                .pdev = pdev,
+        };
+        struct nfs4_getdeviceinfo_res res = {
+                .pdev = pdev,
+        };
+        struct rpc_message msg = {
+                .rpc_proc = &nfs4_procedures[NFSPROC4_CLNT_GETDEVICEINFO],
+                .rpc_argp = &args,
+                .rpc_resp = &res,
+        };
+        int status;
+
+        dprintk("--> %s\n", __func__);
+        status = nfs4_call_sync(server, &msg, &args, &res, 0);
+        dprintk("<-- %s status=%d\n", __func__, status);
+
+        return status;
+}
+
+int nfs4_proc_getdeviceinfo(struct nfs_server *server, struct pnfs_device *pdev)
+{
+        struct nfs4_exception exception = { };
+        int err;
+
+        do {
+                err = nfs4_handle_exception(server,
+                                        _nfs4_proc_getdeviceinfo(server, pdev),
+                                        &exception);
+        } while (exception.retry);
+        return err;
 }
+EXPORT_SYMBOL_GPL(nfs4_proc_getdeviceinfo);
 
 #endif /* CONFIG_NFS_V4_1 */
 
@@ -4903,8 +5488,9 @@ struct nfs4_state_recovery_ops nfs41_reboot_recovery_ops = {
         .state_flag_bit = NFS_STATE_RECLAIM_REBOOT,
         .recover_open   = nfs4_open_reclaim,
         .recover_lock   = nfs4_lock_reclaim,
-        .establish_clid = nfs4_proc_exchange_id,
+        .establish_clid = nfs41_init_clientid,
         .get_clid_cred  = nfs4_get_exchange_id_cred,
+        .reclaim_complete = nfs41_proc_reclaim_complete,
 };
 #endif /* CONFIG_NFS_V4_1 */
 
@@ -4923,7 +5509,7 @@ struct nfs4_state_recovery_ops nfs41_nograce_recovery_ops = {
         .state_flag_bit = NFS_STATE_RECLAIM_NOGRACE,
         .recover_open   = nfs4_open_expired,
         .recover_lock   = nfs4_lock_expired,
-        .establish_clid = nfs4_proc_exchange_id,
+        .establish_clid = nfs41_init_clientid,
         .get_clid_cred  = nfs4_get_exchange_id_cred,
 };
 #endif /* CONFIG_NFS_V4_1 */
@@ -4942,28 +5528,30 @@ struct nfs4_state_maintenance_ops nfs41_state_renewal_ops = {
 };
 #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
+static const struct nfs4_minor_version_ops nfs_v4_0_minor_ops = {
+        .minor_version = 0,
+        .call_sync = _nfs4_call_sync,
+        .validate_stateid = nfs4_validate_delegation_stateid,
+        .reboot_recovery_ops = &nfs40_reboot_recovery_ops,
+        .nograce_recovery_ops = &nfs40_nograce_recovery_ops,
+        .state_renewal_ops = &nfs40_state_renewal_ops,
 };
 
-struct nfs4_state_recovery_ops *nfs4_nograce_recovery_ops[] = {
-        &nfs40_nograce_recovery_ops,
 #if defined(CONFIG_NFS_V4_1)
-        &nfs41_nograce_recovery_ops,
-#endif
+static const struct nfs4_minor_version_ops nfs_v4_1_minor_ops = {
+        .minor_version = 1,
+        .call_sync = _nfs4_call_sync_session,
+        .validate_stateid = nfs41_validate_delegation_stateid,
+        .reboot_recovery_ops = &nfs41_reboot_recovery_ops,
+        .nograce_recovery_ops = &nfs41_nograce_recovery_ops,
+        .state_renewal_ops = &nfs41_state_renewal_ops,
 };
+#endif
 
-struct nfs4_state_maintenance_ops *nfs4_state_renewal_ops[] = {
-        &nfs40_state_renewal_ops,
+const struct nfs4_minor_version_ops *nfs_v4_minor_ops[] = {
+        [0] = &nfs_v4_0_minor_ops,
 #if defined(CONFIG_NFS_V4_1)
-        &nfs41_state_renewal_ops,
+        [1] = &nfs_v4_1_minor_ops,
 #endif
 };
 
@@ -4971,9 +5559,10 @@ static const struct inode_operations nfs4_file_inode_operations = {
         .permission     = nfs_permission,
         .getattr        = nfs_getattr,
         .setattr        = nfs_setattr,
-        .getxattr       = nfs4_getxattr,
-        .setxattr       = nfs4_setxattr,
-        .listxattr      = nfs4_listxattr,
+        .getxattr       = generic_getxattr,
+        .setxattr       = generic_setxattr,
+        .listxattr      = generic_listxattr,
+        .removexattr    = generic_removexattr,
 };
 
 const struct nfs_rpc_ops nfs_v4_clientops = {
@@ -4993,6 +5582,8 @@ const struct nfs_rpc_ops nfs_v4_clientops = {
         .unlink_setup   = nfs4_proc_unlink_setup,
         .unlink_done    = nfs4_proc_unlink_done,
         .rename         = nfs4_proc_rename,
+        .rename_setup   = nfs4_proc_rename_setup,
+        .rename_done    = nfs4_proc_rename_done,
         .link           = nfs4_proc_link,
         .symlink        = nfs4_proc_symlink,
         .mkdir          = nfs4_proc_mkdir,
@@ -5013,6 +5604,19 @@ const struct nfs_rpc_ops nfs_v4_clientops = {
         .lock           = nfs4_proc_lock,
         .clear_acl_cache = nfs4_zap_acl_attr,
         .close_context  = nfs4_close_context,
+        .open_context   = nfs4_atomic_open,
+};
+
+static const struct xattr_handler nfs4_xattr_nfs4_acl_handler = {
+        .prefix = XATTR_NAME_NFSV4_ACL,
+        .list   = nfs4_xattr_list_nfs4_acl,
+        .get    = nfs4_xattr_get_nfs4_acl,
+        .set    = nfs4_xattr_set_nfs4_acl,
+};
+
+const struct xattr_handler *nfs4_xattr_handlers[] = {
+        &nfs4_xattr_nfs4_acl_handler,
+        NULL
 };
 
 /*
diff --git a/fs/nfs/nfs4renewd.c b/fs/nfs/nfs4renewd.c
index e27c6cef18f2..402143d75fc5 100644
--- a/fs/nfs/nfs4renewd.c
+++ b/fs/nfs/nfs4renewd.c
@@ -36,11 +36,6 @@
  * as an rpc_task, not a real kernel thread, so it always runs in rpciod's
  * context.  There is one renewd per nfs_server.
  *
- * TODO: If the send queue gets backlogged (e.g., if the server goes down),
- * we will keep filling the queue with periodic RENEW requests.  We need a
- * mechanism for ensuring that if renewd successfully sends off a request,
- * then it only wakes up when the request is finished.  Maybe use the
- * child task framework of the RPC layer?
  */
 
 #include <linux/mm.h>
@@ -59,29 +54,33 @@
 void
 nfs4_renew_state(struct work_struct *work)
 {
-        struct nfs4_state_maintenance_ops *ops;
+        const 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;
+        long lease;
         unsigned long last, now;
 
-        ops = nfs4_state_renewal_ops[clp->cl_minorversion];
+        ops = clp->cl_mvops->state_renewal_ops;
         dprintk("%s: start\n", __func__);
-        /* Are there any active superblocks? */
-        if (list_empty(&clp->cl_superblocks))
+
+        rcu_read_lock();
+        if (list_empty(&clp->cl_superblocks)) {
+                rcu_read_unlock();
                 goto out;
+        }
+        rcu_read_unlock();
+
         spin_lock(&clp->cl_lock);
         lease = clp->cl_lease_time;
         last = clp->cl_last_renewal;
         now = jiffies;
-        timeout = (2 * lease) / 3 + (long)last - (long)now;
         /* Are we close to a lease timeout? */
         if (time_after(now, last + lease/3)) {
                 cred = ops->get_state_renewal_cred_locked(clp);
                 spin_unlock(&clp->cl_lock);
                 if (cred == NULL) {
-                        if (list_empty(&clp->cl_delegations)) {
+                        if (!nfs_delegations_present(clp)) {
                                 set_bit(NFS4CLNT_LEASE_EXPIRED, &clp->cl_state);
                                 goto out;
                         }
@@ -90,19 +89,15 @@ nfs4_renew_state(struct work_struct *work)
                         /* Queue an asynchronous RENEW. */
                         ops->sched_state_renewal(clp, cred);
                         put_rpccred(cred);
+                        goto out_exp;
                 }
-                timeout = (2 * lease) / 3;
-                spin_lock(&clp->cl_lock);
-        } else
+        } else {
                 dprintk("%s: failed to call renewd. Reason: lease not expired \n",
                                 __func__);
-        if (timeout < 5 * HZ)    /* safeguard */
-                timeout = 5 * HZ;
-        dprintk("%s: requeueing work. Lease period = %ld\n",
-                        __func__, (timeout + HZ - 1) / HZ);
-        cancel_delayed_work(&clp->cl_renewd);
-        schedule_delayed_work(&clp->cl_renewd, timeout);
-        spin_unlock(&clp->cl_lock);
+                spin_unlock(&clp->cl_lock);
+        }
+        nfs4_schedule_state_renewal(clp);
+out_exp:
         nfs_expire_unreferenced_delegations(clp);
 out:
         dprintk("%s: done\n", __func__);
@@ -127,12 +122,6 @@ nfs4_schedule_state_renewal(struct nfs_client *clp)
 }
 
 void
-nfs4_renewd_prepare_shutdown(struct nfs_server *server)
-{
-        cancel_delayed_work(&server->nfs_client->cl_renewd);
-}
-
-void
 nfs4_kill_renewd(struct nfs_client *clp)
 {
         cancel_delayed_work_sync(&clp->cl_renewd);
diff --git a/fs/nfs/nfs4state.c b/fs/nfs/nfs4state.c
index b73c5a728655..2336d532cf66 100644
--- a/fs/nfs/nfs4state.c
+++ b/fs/nfs/nfs4state.c
@@ -40,12 +40,13 @@
 
 #include <linux/kernel.h>
 #include <linux/slab.h>
-#include <linux/smp_lock.h>
+#include <linux/fs.h>
 #include <linux/nfs_fs.h>
 #include <linux/nfs_idmap.h>
 #include <linux/kthread.h>
 #include <linux/module.h>
 #include <linux/random.h>
+#include <linux/ratelimit.h>
 #include <linux/workqueue.h>
 #include <linux/bitops.h>
 
@@ -53,6 +54,7 @@
 #include "callback.h"
 #include "delegation.h"
 #include "internal.h"
+#include "pnfs.h"
 
 #define OPENOWNER_POOL_SIZE     8
 
@@ -62,6 +64,7 @@ static LIST_HEAD(nfs4_clientid_list);
 
 int nfs4_init_clientid(struct nfs_client *clp, struct rpc_cred *cred)
 {
+        struct nfs4_setclientid_res clid;
         unsigned short port;
         int status;
 
@@ -69,11 +72,15 @@ int nfs4_init_clientid(struct nfs_client *clp, struct rpc_cred *cred)
         if (clp->cl_addr.ss_family == AF_INET6)
                 port = nfs_callback_tcpport6;
 
-        status = nfs4_proc_setclientid(clp, NFS4_CALLBACK, port, cred);
-        if (status == 0)
-                status = nfs4_proc_setclientid_confirm(clp, cred);
-        if (status == 0)
-                nfs4_schedule_state_renewal(clp);
+        status = nfs4_proc_setclientid(clp, NFS4_CALLBACK, port, cred, &clid);
+        if (status != 0)
+                goto out;
+        status = nfs4_proc_setclientid_confirm(clp, &clid, cred);
+        if (status != 0)
+                goto out;
+        clp->cl_clientid = clid.clientid;
+        nfs4_schedule_state_renewal(clp);
+out:
         return status;
 }
 
@@ -98,14 +105,17 @@ static void nfs4_clear_machine_cred(struct nfs_client *clp)
                 put_rpccred(cred);
 }
 
-struct rpc_cred *nfs4_get_renew_cred_locked(struct nfs_client *clp)
+static struct rpc_cred *
+nfs4_get_renew_cred_server_locked(struct nfs_server *server)
 {
+        struct rpc_cred *cred = NULL;
         struct nfs4_state_owner *sp;
         struct rb_node *pos;
-        struct rpc_cred *cred = NULL;
 
-        for (pos = rb_first(&clp->cl_state_owners); pos != NULL; pos = rb_next(pos)) {
-                sp = rb_entry(pos, struct nfs4_state_owner, so_client_node);
+        for (pos = rb_first(&server->state_owners);
+             pos != NULL;
+             pos = rb_next(pos)) {
+                sp = rb_entry(pos, struct nfs4_state_owner, so_server_node);
                 if (list_empty(&sp->so_states))
                         continue;
                 cred = get_rpccred(sp->so_cred);
@@ -114,8 +124,126 @@ struct rpc_cred *nfs4_get_renew_cred_locked(struct nfs_client *clp)
         return cred;
 }
 
+/**
+ * nfs4_get_renew_cred_locked - Acquire credential for a renew operation
+ * @clp: client state handle
+ *
+ * Returns an rpc_cred with reference count bumped, or NULL.
+ * Caller must hold clp->cl_lock.
+ */
+struct rpc_cred *nfs4_get_renew_cred_locked(struct nfs_client *clp)
+{
+        struct rpc_cred *cred = NULL;
+        struct nfs_server *server;
+
+        rcu_read_lock();
+        list_for_each_entry_rcu(server, &clp->cl_superblocks, client_link) {
+                cred = nfs4_get_renew_cred_server_locked(server);
+                if (cred != NULL)
+                        break;
+        }
+        rcu_read_unlock();
+        return cred;
+}
+
 #if defined(CONFIG_NFS_V4_1)
 
+static int nfs41_setup_state_renewal(struct nfs_client *clp)
+{
+        int status;
+        struct nfs_fsinfo fsinfo;
+
+        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;
+                spin_unlock(&clp->cl_lock);
+
+                nfs4_schedule_state_renewal(clp);
+        }
+
+        return status;
+}
+
+/*
+ * Back channel returns NFS4ERR_DELAY for new requests when
+ * NFS4_SESSION_DRAINING is set so there is no work to be done when draining
+ * is ended.
+ */
+static void nfs4_end_drain_session(struct nfs_client *clp)
+{
+        struct nfs4_session *ses = clp->cl_session;
+        int max_slots;
+
+        if (ses == NULL)
+                return;
+        if (test_and_clear_bit(NFS4_SESSION_DRAINING, &ses->session_state)) {
+                spin_lock(&ses->fc_slot_table.slot_tbl_lock);
+                max_slots = ses->fc_slot_table.max_slots;
+                while (max_slots--) {
+                        struct rpc_task *task;
+
+                        task = rpc_wake_up_next(&ses->fc_slot_table.
+                                                slot_tbl_waitq);
+                        if (!task)
+                                break;
+                        rpc_task_set_priority(task, RPC_PRIORITY_PRIVILEGED);
+                }
+                spin_unlock(&ses->fc_slot_table.slot_tbl_lock);
+        }
+}
+
+static int nfs4_wait_on_slot_tbl(struct nfs4_slot_table *tbl)
+{
+        spin_lock(&tbl->slot_tbl_lock);
+        if (tbl->highest_used_slotid != -1) {
+                INIT_COMPLETION(tbl->complete);
+                spin_unlock(&tbl->slot_tbl_lock);
+                return wait_for_completion_interruptible(&tbl->complete);
+        }
+        spin_unlock(&tbl->slot_tbl_lock);
+        return 0;
+}
+
+static int nfs4_begin_drain_session(struct nfs_client *clp)
+{
+        struct nfs4_session *ses = clp->cl_session;
+        int ret = 0;
+
+        set_bit(NFS4_SESSION_DRAINING, &ses->session_state);
+        /* back channel */
+        ret = nfs4_wait_on_slot_tbl(&ses->bc_slot_table);
+        if (ret)
+                return ret;
+        /* fore channel */
+        return nfs4_wait_on_slot_tbl(&ses->fc_slot_table);
+}
+
+int nfs41_init_clientid(struct nfs_client *clp, struct rpc_cred *cred)
+{
+        int status;
+
+        nfs4_begin_drain_session(clp);
+        status = nfs4_proc_exchange_id(clp, cred);
+        if (status != 0)
+                goto out;
+        status = nfs4_proc_create_session(clp);
+        if (status != 0)
+                goto out;
+        status = nfs4_set_callback_sessionid(clp);
+        if (status != 0) {
+                printk(KERN_WARNING "Sessionid not set. No callback service\n");
+                nfs_callback_down(1);
+                status = 0;
+        }
+        nfs41_setup_state_renewal(clp);
+        nfs_mark_client_ready(clp, NFS_CS_READY);
+out:
+        return status;
+}
+
 struct rpc_cred *nfs4_get_exchange_id_cred(struct nfs_client *clp)
 {
         struct rpc_cred *cred;
@@ -128,28 +256,56 @@ struct rpc_cred *nfs4_get_exchange_id_cred(struct nfs_client *clp)
 
 #endif /* CONFIG_NFS_V4_1 */
 
-struct rpc_cred *nfs4_get_setclientid_cred(struct nfs_client *clp)
+static struct rpc_cred *
+nfs4_get_setclientid_cred_server(struct nfs_server *server)
 {
+        struct nfs_client *clp = server->nfs_client;
+        struct rpc_cred *cred = NULL;
         struct nfs4_state_owner *sp;
         struct rb_node *pos;
+
+        spin_lock(&clp->cl_lock);
+        pos = rb_first(&server->state_owners);
+        if (pos != NULL) {
+                sp = rb_entry(pos, struct nfs4_state_owner, so_server_node);
+                cred = get_rpccred(sp->so_cred);
+        }
+        spin_unlock(&clp->cl_lock);
+        return cred;
+}
+
+/**
+ * nfs4_get_setclientid_cred - Acquire credential for a setclientid operation
+ * @clp: client state handle
+ *
+ * Returns an rpc_cred with reference count bumped, or NULL.
+ */
+struct rpc_cred *nfs4_get_setclientid_cred(struct nfs_client *clp)
+{
+        struct nfs_server *server;
         struct rpc_cred *cred;
 
         spin_lock(&clp->cl_lock);
         cred = nfs4_get_machine_cred_locked(clp);
+        spin_unlock(&clp->cl_lock);
         if (cred != NULL)
                 goto out;
-        pos = rb_first(&clp->cl_state_owners);
-        if (pos != NULL) {
-                sp = rb_entry(pos, struct nfs4_state_owner, so_client_node);
-                cred = get_rpccred(sp->so_cred);
+
+        rcu_read_lock();
+        list_for_each_entry_rcu(server, &clp->cl_superblocks, client_link) {
+                cred = nfs4_get_setclientid_cred_server(server);
+                if (cred != NULL)
+                        break;
         }
+        rcu_read_unlock();
+
 out:
-        spin_unlock(&clp->cl_lock);
         return cred;
 }
 
-static void nfs_alloc_unique_id(struct rb_root *root, struct nfs_unique_id *new,
-                __u64 minval, int maxbits)
+static void nfs_alloc_unique_id_locked(struct rb_root *root,
+                                       struct nfs_unique_id *new,
+                                       __u64 minval, int maxbits)
 {
         struct rb_node **p, *parent;
         struct nfs_unique_id *pos;
@@ -204,16 +360,15 @@ static void nfs_free_unique_id(struct rb_root *root, struct nfs_unique_id *id)
 }
 
 static struct nfs4_state_owner *
-nfs4_find_state_owner(struct nfs_server *server, struct rpc_cred *cred)
+nfs4_find_state_owner_locked(struct nfs_server *server, struct rpc_cred *cred)
 {
-        struct nfs_client *clp = server->nfs_client;
-        struct rb_node **p = &clp->cl_state_owners.rb_node,
+        struct rb_node **p = &server->state_owners.rb_node,
                        *parent = NULL;
         struct nfs4_state_owner *sp, *res = NULL;
 
         while (*p != NULL) {
                 parent = *p;
-                sp = rb_entry(parent, struct nfs4_state_owner, so_client_node);
+                sp = rb_entry(parent, struct nfs4_state_owner, so_server_node);
 
                 if (server < sp->so_server) {
                         p = &parent->rb_left;
@@ -237,24 +392,17 @@ nfs4_find_state_owner(struct nfs_server *server, struct rpc_cred *cred)
 }
 
 static struct nfs4_state_owner *
-nfs4_insert_state_owner(struct nfs_client *clp, struct nfs4_state_owner *new)
+nfs4_insert_state_owner_locked(struct nfs4_state_owner *new)
 {
-        struct rb_node **p = &clp->cl_state_owners.rb_node,
+        struct nfs_server *server = new->so_server;
+        struct rb_node **p = &server->state_owners.rb_node,
                        *parent = NULL;
         struct nfs4_state_owner *sp;
 
         while (*p != NULL) {
                 parent = *p;
-                sp = rb_entry(parent, struct nfs4_state_owner, so_client_node);
+                sp = rb_entry(parent, struct nfs4_state_owner, so_server_node);
 
-                if (new->so_server < sp->so_server) {
-                        p = &parent->rb_left;
-                        continue;
-                }
-                if (new->so_server > sp->so_server) {
-                        p = &parent->rb_right;
-                        continue;
-                }
                 if (new->so_cred < sp->so_cred)
                         p = &parent->rb_left;
                 else if (new->so_cred > sp->so_cred)
@@ -264,18 +412,21 @@ nfs4_insert_state_owner(struct nfs_client *clp, struct nfs4_state_owner *new)
                         return sp;
                 }
         }
-        nfs_alloc_unique_id(&clp->cl_openowner_id, &new->so_owner_id, 1, 64);
-        rb_link_node(&new->so_client_node, parent, p);
-        rb_insert_color(&new->so_client_node, &clp->cl_state_owners);
+        nfs_alloc_unique_id_locked(&server->openowner_id,
+                                        &new->so_owner_id, 1, 64);
+        rb_link_node(&new->so_server_node, parent, p);
+        rb_insert_color(&new->so_server_node, &server->state_owners);
         return new;
 }
 
 static void
-nfs4_remove_state_owner(struct nfs_client *clp, struct nfs4_state_owner *sp)
+nfs4_remove_state_owner_locked(struct nfs4_state_owner *sp)
 {
-        if (!RB_EMPTY_NODE(&sp->so_client_node))
-                rb_erase(&sp->so_client_node, &clp->cl_state_owners);
-        nfs_free_unique_id(&clp->cl_openowner_id, &sp->so_owner_id);
+        struct nfs_server *server = sp->so_server;
+
+        if (!RB_EMPTY_NODE(&sp->so_server_node))
+                rb_erase(&sp->so_server_node, &server->state_owners);
+        nfs_free_unique_id(&server->openowner_id, &sp->so_owner_id);
 }
 
 /*
@@ -288,12 +439,11 @@ nfs4_alloc_state_owner(void)
 {
         struct nfs4_state_owner *sp;
 
-        sp = kzalloc(sizeof(*sp),GFP_KERNEL);
+        sp = kzalloc(sizeof(*sp),GFP_NOFS);
         if (!sp)
                 return NULL;
         spin_lock_init(&sp->so_lock);
         INIT_LIST_HEAD(&sp->so_states);
-        INIT_LIST_HEAD(&sp->so_delegations);
         rpc_init_wait_queue(&sp->so_sequence.wait, "Seqid_waitqueue");
         sp->so_seqid.sequence = &sp->so_sequence;
         spin_lock_init(&sp->so_sequence.lock);
@@ -305,34 +455,42 @@ nfs4_alloc_state_owner(void)
 static void
 nfs4_drop_state_owner(struct nfs4_state_owner *sp)
 {
-        if (!RB_EMPTY_NODE(&sp->so_client_node)) {
-                struct nfs_client *clp = sp->so_client;
+        if (!RB_EMPTY_NODE(&sp->so_server_node)) {
+                struct nfs_server *server = sp->so_server;
+                struct nfs_client *clp = server->nfs_client;
 
                 spin_lock(&clp->cl_lock);
-                rb_erase(&sp->so_client_node, &clp->cl_state_owners);
-                RB_CLEAR_NODE(&sp->so_client_node);
+                rb_erase(&sp->so_server_node, &server->state_owners);
+                RB_CLEAR_NODE(&sp->so_server_node);
                 spin_unlock(&clp->cl_lock);
         }
 }
 
-struct nfs4_state_owner *nfs4_get_state_owner(struct nfs_server *server, struct rpc_cred *cred)
+/**
+ * nfs4_get_state_owner - Look up a state owner given a credential
+ * @server: nfs_server to search
+ * @cred: RPC credential to match
+ *
+ * Returns a pointer to an instantiated nfs4_state_owner struct, or NULL.
+ */
+struct nfs4_state_owner *nfs4_get_state_owner(struct nfs_server *server,
+                                              struct rpc_cred *cred)
 {
         struct nfs_client *clp = server->nfs_client;
         struct nfs4_state_owner *sp, *new;
 
         spin_lock(&clp->cl_lock);
-        sp = nfs4_find_state_owner(server, cred);
+        sp = nfs4_find_state_owner_locked(server, cred);
         spin_unlock(&clp->cl_lock);
         if (sp != NULL)
                 return sp;
         new = nfs4_alloc_state_owner();
         if (new == NULL)
                 return NULL;
-        new->so_client = clp;
         new->so_server = server;
         new->so_cred = cred;
         spin_lock(&clp->cl_lock);
-        sp = nfs4_insert_state_owner(clp, new);
+        sp = nfs4_insert_state_owner_locked(new);
         spin_unlock(&clp->cl_lock);
         if (sp == new)
                 get_rpccred(cred);
@@ -343,14 +501,19 @@ struct nfs4_state_owner *nfs4_get_state_owner(struct nfs_server *server, struct
         return sp;
 }
 
+/**
+ * nfs4_put_state_owner - Release a nfs4_state_owner
+ * @sp: state owner data to release
+ *
+ */
 void nfs4_put_state_owner(struct nfs4_state_owner *sp)
 {
-        struct nfs_client *clp = sp->so_client;
+        struct nfs_client *clp = sp->so_server->nfs_client;
         struct rpc_cred *cred = sp->so_cred;
 
         if (!atomic_dec_and_lock(&sp->so_count, &clp->cl_lock))
                 return;
-        nfs4_remove_state_owner(clp, sp);
+        nfs4_remove_state_owner_locked(sp);
         spin_unlock(&clp->cl_lock);
         rpc_destroy_wait_queue(&sp->so_sequence.wait);
         put_rpccred(cred);
@@ -362,7 +525,7 @@ nfs4_alloc_open_state(void)
 {
         struct nfs4_state *state;
 
-        state = kzalloc(sizeof(*state), GFP_KERNEL);
+        state = kzalloc(sizeof(*state), GFP_NOFS);
         if (!state)
                 return NULL;
         atomic_set(&state->count, 1);
@@ -464,7 +627,8 @@ void nfs4_put_open_state(struct nfs4_state *state)
 /*
  * Close the current file.
  */
-static void __nfs4_close(struct path *path, struct nfs4_state *state, fmode_t fmode, int wait)
+static void __nfs4_close(struct path *path, struct nfs4_state *state,
+                fmode_t fmode, gfp_t gfp_mask, int wait)
 {
         struct nfs4_state_owner *owner = state->owner;
         int call_close = 0;
@@ -504,18 +668,21 @@ static void __nfs4_close(struct path *path, struct nfs4_state *state, fmode_t fm
         if (!call_close) {
                 nfs4_put_open_state(state);
                 nfs4_put_state_owner(owner);
-        } else
-                nfs4_do_close(path, state, wait);
+        } else {
+                bool roc = pnfs_roc(state->inode);
+
+                nfs4_do_close(path, state, gfp_mask, wait, roc);
+        }
 }
 
 void nfs4_close_state(struct path *path, struct nfs4_state *state, fmode_t fmode)
 {
-        __nfs4_close(path, state, fmode, 0);
+        __nfs4_close(path, state, fmode, GFP_NOFS, 0);
 }
 
 void nfs4_close_sync(struct path *path, struct nfs4_state *state, fmode_t fmode)
 {
-        __nfs4_close(path, state, fmode, 1);
+        __nfs4_close(path, state, fmode, GFP_KERNEL, 1);
 }
 
 /*
@@ -523,12 +690,21 @@ void nfs4_close_sync(struct path *path, struct nfs4_state *state, fmode_t fmode)
  * that is compatible with current->files
  */
 static struct nfs4_lock_state *
-__nfs4_find_lock_state(struct nfs4_state *state, fl_owner_t fl_owner)
+__nfs4_find_lock_state(struct nfs4_state *state, fl_owner_t fl_owner, pid_t fl_pid, unsigned int type)
 {
         struct nfs4_lock_state *pos;
         list_for_each_entry(pos, &state->lock_states, ls_locks) {
-                if (pos->ls_owner != fl_owner)
+                if (type != NFS4_ANY_LOCK_TYPE && pos->ls_owner.lo_type != type)
                         continue;
+                switch (pos->ls_owner.lo_type) {
+                case NFS4_POSIX_LOCK_TYPE:
+                        if (pos->ls_owner.lo_u.posix_owner != fl_owner)
+                                continue;
+                        break;
+                case NFS4_FLOCK_LOCK_TYPE:
+                        if (pos->ls_owner.lo_u.flock_owner != fl_pid)
+                                continue;
+                }
                 atomic_inc(&pos->ls_count);
                 return pos;
         }
@@ -540,12 +716,13 @@ __nfs4_find_lock_state(struct nfs4_state *state, fl_owner_t fl_owner)
  * exists, return an uninitialized one.
  *
  */
-static struct nfs4_lock_state *nfs4_alloc_lock_state(struct nfs4_state *state, fl_owner_t fl_owner)
+static struct nfs4_lock_state *nfs4_alloc_lock_state(struct nfs4_state *state, fl_owner_t fl_owner, pid_t fl_pid, unsigned int type)
 {
         struct nfs4_lock_state *lsp;
-        struct nfs_client *clp = state->owner->so_client;
+        struct nfs_server *server = state->owner->so_server;
+        struct nfs_client *clp = server->nfs_client;
 
-        lsp = kzalloc(sizeof(*lsp), GFP_KERNEL);
+        lsp = kzalloc(sizeof(*lsp), GFP_NOFS);
         if (lsp == NULL)
                 return NULL;
         rpc_init_wait_queue(&lsp->ls_sequence.wait, "lock_seqid_waitqueue");
@@ -553,9 +730,21 @@ static struct nfs4_lock_state *nfs4_alloc_lock_state(struct nfs4_state *state, f
         INIT_LIST_HEAD(&lsp->ls_sequence.list);
         lsp->ls_seqid.sequence = &lsp->ls_sequence;
         atomic_set(&lsp->ls_count, 1);
-        lsp->ls_owner = fl_owner;
+        lsp->ls_state = state;
+        lsp->ls_owner.lo_type = type;
+        switch (lsp->ls_owner.lo_type) {
+        case NFS4_FLOCK_LOCK_TYPE:
+                lsp->ls_owner.lo_u.flock_owner = fl_pid;
+                break;
+        case NFS4_POSIX_LOCK_TYPE:
+                lsp->ls_owner.lo_u.posix_owner = fl_owner;
+                break;
+        default:
+                kfree(lsp);
+                return NULL;
+        }
         spin_lock(&clp->cl_lock);
-        nfs_alloc_unique_id(&clp->cl_lockowner_id, &lsp->ls_id, 1, 64);
+        nfs_alloc_unique_id_locked(&server->lockowner_id, &lsp->ls_id, 1, 64);
         spin_unlock(&clp->cl_lock);
         INIT_LIST_HEAD(&lsp->ls_locks);
         return lsp;
@@ -563,10 +752,11 @@ static struct nfs4_lock_state *nfs4_alloc_lock_state(struct nfs4_state *state, f
 
 static void nfs4_free_lock_state(struct nfs4_lock_state *lsp)
 {
-        struct nfs_client *clp = lsp->ls_state->owner->so_client;
+        struct nfs_server *server = lsp->ls_state->owner->so_server;
+        struct nfs_client *clp = server->nfs_client;
 
         spin_lock(&clp->cl_lock);
-        nfs_free_unique_id(&clp->cl_lockowner_id, &lsp->ls_id);
+        nfs_free_unique_id(&server->lockowner_id, &lsp->ls_id);
         spin_unlock(&clp->cl_lock);
         rpc_destroy_wait_queue(&lsp->ls_sequence.wait);
         kfree(lsp);
@@ -577,17 +767,16 @@ static void nfs4_free_lock_state(struct nfs4_lock_state *lsp)
  * exists, return an uninitialized one.
  *
  */
-static struct nfs4_lock_state *nfs4_get_lock_state(struct nfs4_state *state, fl_owner_t owner)
+static struct nfs4_lock_state *nfs4_get_lock_state(struct nfs4_state *state, fl_owner_t owner, pid_t pid, unsigned int type)
 {
         struct nfs4_lock_state *lsp, *new = NULL;
         
         for(;;) {
                 spin_lock(&state->state_lock);
-                lsp = __nfs4_find_lock_state(state, owner);
+                lsp = __nfs4_find_lock_state(state, owner, pid, type);
                 if (lsp != NULL)
                         break;
                 if (new != NULL) {
-                        new->ls_state = state;
                         list_add(&new->ls_locks, &state->lock_states);
                         set_bit(LK_STATE_IN_USE, &state->flags);
                         lsp = new;
@@ -595,7 +784,7 @@ static struct nfs4_lock_state *nfs4_get_lock_state(struct nfs4_state *state, fl_
                         break;
                 }
                 spin_unlock(&state->state_lock);
-                new = nfs4_alloc_lock_state(state, owner);
+                new = nfs4_alloc_lock_state(state, owner, pid, type);
                 if (new == NULL)
                         return NULL;
         }
@@ -622,6 +811,8 @@ void nfs4_put_lock_state(struct nfs4_lock_state *lsp)
         if (list_empty(&state->lock_states))
                 clear_bit(LK_STATE_IN_USE, &state->flags);
         spin_unlock(&state->state_lock);
+        if (lsp->ls_flags & NFS_LOCK_INITIALIZED)
+                nfs4_release_lockowner(lsp);
         nfs4_free_lock_state(lsp);
 }
 
@@ -638,7 +829,7 @@ static void nfs4_fl_release_lock(struct file_lock *fl)
         nfs4_put_lock_state(fl->fl_u.nfs4_fl.owner);
 }
 
-static struct file_lock_operations nfs4_fl_lock_ops = {
+static const struct file_lock_operations nfs4_fl_lock_ops = {
         .fl_copy_lock = nfs4_fl_copy_lock,
         .fl_release_private = nfs4_fl_release_lock,
 };
@@ -649,7 +840,12 @@ int nfs4_set_lock_state(struct nfs4_state *state, struct file_lock *fl)
 
         if (fl->fl_ops != NULL)
                 return 0;
-        lsp = nfs4_get_lock_state(state, fl->fl_owner);
+        if (fl->fl_flags & FL_POSIX)
+                lsp = nfs4_get_lock_state(state, fl->fl_owner, 0, NFS4_POSIX_LOCK_TYPE);
+        else if (fl->fl_flags & FL_FLOCK)
+                lsp = nfs4_get_lock_state(state, 0, fl->fl_pid, NFS4_FLOCK_LOCK_TYPE);
+        else
+                return -EINVAL;
         if (lsp == NULL)
                 return -ENOMEM;
         fl->fl_u.nfs4_fl.owner = lsp;
@@ -661,7 +857,7 @@ int nfs4_set_lock_state(struct nfs4_state *state, struct file_lock *fl)
  * Byte-range lock aware utility to initialize the stateid of read/write
  * requests.
  */
-void nfs4_copy_stateid(nfs4_stateid *dst, struct nfs4_state *state, fl_owner_t fl_owner)
+void nfs4_copy_stateid(nfs4_stateid *dst, struct nfs4_state *state, fl_owner_t fl_owner, pid_t fl_pid)
 {
         struct nfs4_lock_state *lsp;
         int seq;
@@ -674,18 +870,18 @@ void nfs4_copy_stateid(nfs4_stateid *dst, struct nfs4_state *state, fl_owner_t f
                 return;
 
         spin_lock(&state->state_lock);
-        lsp = __nfs4_find_lock_state(state, fl_owner);
+        lsp = __nfs4_find_lock_state(state, fl_owner, fl_pid, NFS4_ANY_LOCK_TYPE);
         if (lsp != NULL && (lsp->ls_flags & NFS_LOCK_INITIALIZED) != 0)
                 memcpy(dst, &lsp->ls_stateid, sizeof(*dst));
         spin_unlock(&state->state_lock);
         nfs4_put_lock_state(lsp);
 }
 
-struct nfs_seqid *nfs_alloc_seqid(struct nfs_seqid_counter *counter)
+struct nfs_seqid *nfs_alloc_seqid(struct nfs_seqid_counter *counter, gfp_t gfp_mask)
 {
         struct nfs_seqid *new;
 
-        new = kmalloc(sizeof(*new), GFP_KERNEL);
+        new = kmalloc(sizeof(*new), gfp_mask);
         if (new != NULL) {
                 new->sequence = counter;
                 INIT_LIST_HEAD(&new->list);
@@ -693,16 +889,21 @@ struct nfs_seqid *nfs_alloc_seqid(struct nfs_seqid_counter *counter)
         return new;
 }
 
-void nfs_free_seqid(struct nfs_seqid *seqid)
+void nfs_release_seqid(struct nfs_seqid *seqid)
 {
         if (!list_empty(&seqid->list)) {
                 struct rpc_sequence *sequence = seqid->sequence->sequence;
 
                 spin_lock(&sequence->lock);
-                list_del(&seqid->list);
+                list_del_init(&seqid->list);
                 spin_unlock(&sequence->lock);
                 rpc_wake_up(&sequence->wait);
         }
+}
+
+void nfs_free_seqid(struct nfs_seqid *seqid)
+{
+        nfs_release_seqid(seqid);
         kfree(seqid);
 }
 
@@ -823,7 +1024,7 @@ void nfs4_schedule_state_recovery(struct nfs_client *clp)
         nfs4_schedule_state_manager(clp);
 }
 
-static int nfs4_state_mark_reclaim_reboot(struct nfs_client *clp, struct nfs4_state *state)
+int nfs4_state_mark_reclaim_reboot(struct nfs_client *clp, struct nfs4_state *state)
 {
 
         set_bit(NFS_STATE_RECLAIM_REBOOT, &state->flags);
@@ -859,13 +1060,13 @@ static int nfs4_reclaim_locks(struct nfs4_state *state, const struct nfs4_state_
         /* Guard against delegation returns and new lock/unlock calls */
         down_write(&nfsi->rwsem);
         /* Protect inode->i_flock using the BKL */
-        lock_kernel();
+        lock_flocks();
         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();
+                unlock_flocks();
                 status = ops->recover_lock(state, fl);
                 switch (status) {
                         case 0:
@@ -877,6 +1078,10 @@ static int nfs4_reclaim_locks(struct nfs4_state *state, const struct nfs4_state_
                         case -NFS4ERR_EXPIRED:
                         case -NFS4ERR_NO_GRACE:
                         case -NFS4ERR_STALE_CLIENTID:
+                        case -NFS4ERR_BADSESSION:
+                        case -NFS4ERR_BADSLOT:
+                        case -NFS4ERR_BAD_HIGH_SLOT:
+                        case -NFS4ERR_CONN_NOT_BOUND_TO_SESSION:
                                 goto out;
                         default:
                                 printk(KERN_ERR "%s: unhandled error %d. Zeroing state\n",
@@ -888,9 +1093,9 @@ static int nfs4_reclaim_locks(struct nfs4_state *state, const struct nfs4_state_
                                 /* kill_proc(fl->fl_pid, SIGLOST, 1); */
                                 status = 0;
                 }
-                lock_kernel();
+                lock_flocks();
         }
-        unlock_kernel();
+        unlock_flocks();
 out:
         up_write(&nfsi->rwsem);
         return status;
@@ -948,17 +1153,29 @@ restart:
                                 /* Mark the file as being 'closed' */
                                 state->state = 0;
                                 break;
+                        case -EKEYEXPIRED:
+                                /*
+                                 * User RPCSEC_GSS context has expired.
+                                 * We cannot recover this stateid now, so
+                                 * skip it and allow recovery thread to
+                                 * proceed.
+                                 */
+                                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);
+                                nfs4_state_mark_reclaim_nograce(sp->so_server->nfs_client, state);
                                 break;
                         case -NFS4ERR_EXPIRED:
                         case -NFS4ERR_NO_GRACE:
-                                nfs4_state_mark_reclaim_nograce(sp->so_client, state);
+                                nfs4_state_mark_reclaim_nograce(sp->so_server->nfs_client, state);
                         case -NFS4ERR_STALE_CLIENTID:
+                        case -NFS4ERR_BADSESSION:
+                        case -NFS4ERR_BADSLOT:
+                        case -NFS4ERR_BAD_HIGH_SLOT:
+                        case -NFS4ERR_CONN_NOT_BOUND_TO_SESSION:
                                 goto out_err;
                 }
                 nfs4_put_open_state(state);
@@ -985,15 +1202,19 @@ static void nfs4_clear_open_state(struct nfs4_state *state)
         }
 }
 
-static void nfs4_state_mark_reclaim_helper(struct nfs_client *clp, int (*mark_reclaim)(struct nfs_client *clp, struct nfs4_state *state))
+static void nfs4_reset_seqids(struct nfs_server *server,
+        int (*mark_reclaim)(struct nfs_client *clp, struct nfs4_state *state))
 {
+        struct nfs_client *clp = server->nfs_client;
         struct nfs4_state_owner *sp;
         struct rb_node *pos;
         struct nfs4_state *state;
 
-        /* Reset all sequence ids to zero */
-        for (pos = rb_first(&clp->cl_state_owners); pos != NULL; pos = rb_next(pos)) {
-                sp = rb_entry(pos, struct nfs4_state_owner, so_client_node);
+        spin_lock(&clp->cl_lock);
+        for (pos = rb_first(&server->state_owners);
+             pos != NULL;
+             pos = rb_next(pos)) {
+                sp = rb_entry(pos, struct nfs4_state_owner, so_server_node);
                 sp->so_seqid.flags = 0;
                 spin_lock(&sp->so_lock);
                 list_for_each_entry(state, &sp->so_states, open_states) {
@@ -1002,6 +1223,18 @@ static void nfs4_state_mark_reclaim_helper(struct nfs_client *clp, int (*mark_re
                 }
                 spin_unlock(&sp->so_lock);
         }
+        spin_unlock(&clp->cl_lock);
+}
+
+static void nfs4_state_mark_reclaim_helper(struct nfs_client *clp,
+        int (*mark_reclaim)(struct nfs_client *clp, struct nfs4_state *state))
+{
+        struct nfs_server *server;
+
+        rcu_read_lock();
+        list_for_each_entry_rcu(server, &clp->cl_superblocks, client_link)
+                nfs4_reset_seqids(server, mark_reclaim);
+        rcu_read_unlock();
 }
 
 static void nfs4_state_start_reclaim_reboot(struct nfs_client *clp)
@@ -1011,27 +1244,59 @@ static void nfs4_state_start_reclaim_reboot(struct nfs_client *clp)
         nfs4_state_mark_reclaim_helper(clp, nfs4_state_mark_reclaim_reboot);
 }
 
-static void nfs4_state_end_reclaim_reboot(struct nfs_client *clp)
+static void nfs4_reclaim_complete(struct nfs_client *clp,
+                                 const struct nfs4_state_recovery_ops *ops)
+{
+        /* Notify the server we're done reclaiming our state */
+        if (ops->reclaim_complete)
+                (void)ops->reclaim_complete(clp);
+}
+
+static void nfs4_clear_reclaim_server(struct nfs_server *server)
 {
+        struct nfs_client *clp = server->nfs_client;
         struct nfs4_state_owner *sp;
         struct rb_node *pos;
         struct nfs4_state *state;
 
-        if (!test_and_clear_bit(NFS4CLNT_RECLAIM_REBOOT, &clp->cl_state))
-                return;
-
-        for (pos = rb_first(&clp->cl_state_owners); pos != NULL; pos = rb_next(pos)) {
-                sp = rb_entry(pos, struct nfs4_state_owner, so_client_node);
+        spin_lock(&clp->cl_lock);
+        for (pos = rb_first(&server->state_owners);
+             pos != NULL;
+             pos = rb_next(pos)) {
+                sp = rb_entry(pos, struct nfs4_state_owner, so_server_node);
                 spin_lock(&sp->so_lock);
                 list_for_each_entry(state, &sp->so_states, open_states) {
-                        if (!test_and_clear_bit(NFS_STATE_RECLAIM_REBOOT, &state->flags))
+                        if (!test_and_clear_bit(NFS_STATE_RECLAIM_REBOOT,
+                                                &state->flags))
                                 continue;
                         nfs4_state_mark_reclaim_nograce(clp, state);
                 }
                 spin_unlock(&sp->so_lock);
         }
+        spin_unlock(&clp->cl_lock);
+}
+
+static int nfs4_state_clear_reclaim_reboot(struct nfs_client *clp)
+{
+        struct nfs_server *server;
+
+        if (!test_and_clear_bit(NFS4CLNT_RECLAIM_REBOOT, &clp->cl_state))
+                return 0;
+
+        rcu_read_lock();
+        list_for_each_entry_rcu(server, &clp->cl_superblocks, client_link)
+                nfs4_clear_reclaim_server(server);
+        rcu_read_unlock();
 
         nfs_delegation_reap_unclaimed(clp);
+        return 1;
+}
+
+static void nfs4_state_end_reclaim_reboot(struct nfs_client *clp)
+{
+        if (!nfs4_state_clear_reclaim_reboot(clp))
+                return;
+        nfs4_reclaim_complete(clp, clp->cl_mvops->reboot_recovery_ops);
 }
 
 static void nfs_delegation_clear_all(struct nfs_client *clp)
@@ -1046,25 +1311,33 @@ static void nfs4_state_start_reclaim_nograce(struct nfs_client *clp)
         nfs4_state_mark_reclaim_helper(clp, nfs4_state_mark_reclaim_nograce);
 }
 
-static void nfs4_state_end_reclaim_nograce(struct nfs_client *clp)
+static void nfs4_warn_keyexpired(const char *s)
 {
-        clear_bit(NFS4CLNT_RECLAIM_NOGRACE, &clp->cl_state);
+        printk_ratelimited(KERN_WARNING "Error: state manager"
+                        " encountered RPCSEC_GSS session"
+                        " expired against NFSv4 server %s.\n",
+                        s);
 }
 
-static void nfs4_recovery_handle_error(struct nfs_client *clp, int error)
+static int nfs4_recovery_handle_error(struct nfs_client *clp, int error)
 {
         switch (error) {
                 case -NFS4ERR_CB_PATH_DOWN:
                         nfs_handle_cb_pathdown(clp);
-                        break;
+                        return 0;
+                case -NFS4ERR_NO_GRACE:
+                        nfs4_state_end_reclaim_reboot(clp);
+                        return 0;
                 case -NFS4ERR_STALE_CLIENTID:
                 case -NFS4ERR_LEASE_MOVED:
                         set_bit(NFS4CLNT_LEASE_EXPIRED, &clp->cl_state);
+                        nfs4_state_clear_reclaim_reboot(clp);
                         nfs4_state_start_reclaim_reboot(clp);
                         break;
                 case -NFS4ERR_EXPIRED:
                         set_bit(NFS4CLNT_LEASE_EXPIRED, &clp->cl_state);
                         nfs4_state_start_reclaim_nograce(clp);
+                        break;
                 case -NFS4ERR_BADSESSION:
                 case -NFS4ERR_BADSLOT:
                 case -NFS4ERR_BAD_HIGH_SLOT:
@@ -1072,42 +1345,61 @@ static void nfs4_recovery_handle_error(struct nfs_client *clp, int error)
                 case -NFS4ERR_CONN_NOT_BOUND_TO_SESSION:
                 case -NFS4ERR_SEQ_FALSE_RETRY:
                 case -NFS4ERR_SEQ_MISORDERED:
-                        set_bit(NFS4CLNT_SESSION_SETUP, &clp->cl_state);
+                        set_bit(NFS4CLNT_SESSION_RESET, &clp->cl_state);
+                        /* Zero session reset errors */
+                        return 0;
+                case -EKEYEXPIRED:
+                        /* Nothing we can do */
+                        nfs4_warn_keyexpired(clp->cl_hostname);
+                        return 0;
         }
+        return error;
 }
 
 static int nfs4_do_reclaim(struct nfs_client *clp, const struct nfs4_state_recovery_ops *ops)
 {
+        struct nfs4_state_owner *sp;
+        struct nfs_server *server;
         struct rb_node *pos;
         int status = 0;
 
 restart:
-        spin_lock(&clp->cl_lock);
-        for (pos = rb_first(&clp->cl_state_owners); pos != NULL; pos = rb_next(pos)) {
-                struct nfs4_state_owner *sp = rb_entry(pos, struct nfs4_state_owner, so_client_node);
-                if (!test_and_clear_bit(ops->owner_flag_bit, &sp->so_flags))
-                        continue;
-                atomic_inc(&sp->so_count);
-                spin_unlock(&clp->cl_lock);
-                status = nfs4_reclaim_open_state(sp, ops);
-                if (status < 0) {
-                        set_bit(ops->owner_flag_bit, &sp->so_flags);
+        rcu_read_lock();
+        list_for_each_entry_rcu(server, &clp->cl_superblocks, client_link) {
+                spin_lock(&clp->cl_lock);
+                for (pos = rb_first(&server->state_owners);
+                     pos != NULL;
+                     pos = rb_next(pos)) {
+                        sp = rb_entry(pos,
+                                struct nfs4_state_owner, so_server_node);
+                        if (!test_and_clear_bit(ops->owner_flag_bit,
+                                                        &sp->so_flags))
+                                continue;
+                        atomic_inc(&sp->so_count);
+                        spin_unlock(&clp->cl_lock);
+                        rcu_read_unlock();
+
+                        status = nfs4_reclaim_open_state(sp, ops);
+                        if (status < 0) {
+                                set_bit(ops->owner_flag_bit, &sp->so_flags);
+                                nfs4_put_state_owner(sp);
+                                return nfs4_recovery_handle_error(clp, status);
+                        }
+
                         nfs4_put_state_owner(sp);
-                        nfs4_recovery_handle_error(clp, status);
-                        return status;
+                        goto restart;
                 }
-                nfs4_put_state_owner(sp);
-                goto restart;
+                spin_unlock(&clp->cl_lock);
         }
-        spin_unlock(&clp->cl_lock);
+        rcu_read_unlock();
         return status;
 }
 
 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];
+        const struct nfs4_state_maintenance_ops *ops =
+                clp->cl_mvops->state_renewal_ops;
         int status = -NFS4ERR_EXPIRED;
 
         /* Is the client already known to have an expired lease? */
@@ -1124,15 +1416,14 @@ static int nfs4_check_lease(struct nfs_client *clp)
         status = ops->renew_lease(clp, cred);
         put_rpccred(cred);
 out:
-        nfs4_recovery_handle_error(clp, status);
-        return status;
+        return nfs4_recovery_handle_error(clp, status);
 }
 
 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];
+        const struct nfs4_state_recovery_ops *ops =
+                clp->cl_mvops->reboot_recovery_ops;
         int status = -ENOENT;
 
         cred = ops->get_clid_cred(clp);
@@ -1151,55 +1442,127 @@ static int nfs4_reclaim_lease(struct nfs_client *clp)
 }
 
 #ifdef CONFIG_NFS_V4_1
-static void nfs4_session_recovery_handle_error(struct nfs_client *clp, int err)
+void nfs41_handle_recall_slot(struct nfs_client *clp)
+{
+        set_bit(NFS4CLNT_RECALL_SLOT, &clp->cl_state);
+        nfs4_schedule_state_recovery(clp);
+}
+
+static void nfs4_reset_all_state(struct nfs_client *clp)
+{
+        if (test_and_set_bit(NFS4CLNT_LEASE_EXPIRED, &clp->cl_state) == 0) {
+                clp->cl_boot_time = CURRENT_TIME;
+                nfs4_state_start_reclaim_nograce(clp);
+                nfs4_schedule_state_recovery(clp);
+        }
+}
+
+static void nfs41_handle_server_reboot(struct nfs_client *clp)
 {
-        switch (err) {
-        case -NFS4ERR_STALE_CLIENTID:
-                set_bit(NFS4CLNT_LEASE_EXPIRED, &clp->cl_state);
-                set_bit(NFS4CLNT_SESSION_SETUP, &clp->cl_state);
+        if (test_and_set_bit(NFS4CLNT_LEASE_EXPIRED, &clp->cl_state) == 0) {
+                nfs4_state_start_reclaim_reboot(clp);
+                nfs4_schedule_state_recovery(clp);
         }
 }
 
+static void nfs41_handle_state_revoked(struct nfs_client *clp)
+{
+        /* Temporary */
+        nfs4_reset_all_state(clp);
+}
+
+static void nfs41_handle_recallable_state_revoked(struct nfs_client *clp)
+{
+        /* This will need to handle layouts too */
+        nfs_expire_all_delegations(clp);
+}
+
+static void nfs41_handle_cb_path_down(struct nfs_client *clp)
+{
+        nfs_expire_all_delegations(clp);
+        if (test_and_set_bit(NFS4CLNT_SESSION_RESET, &clp->cl_state) == 0)
+                nfs4_schedule_state_recovery(clp);
+}
+
+void nfs41_handle_sequence_flag_errors(struct nfs_client *clp, u32 flags)
+{
+        if (!flags)
+                return;
+        else if (flags & SEQ4_STATUS_RESTART_RECLAIM_NEEDED)
+                nfs41_handle_server_reboot(clp);
+        else if (flags & (SEQ4_STATUS_EXPIRED_ALL_STATE_REVOKED |
+                            SEQ4_STATUS_EXPIRED_SOME_STATE_REVOKED |
+                            SEQ4_STATUS_ADMIN_STATE_REVOKED |
+                            SEQ4_STATUS_LEASE_MOVED))
+                nfs41_handle_state_revoked(clp);
+        else if (flags & SEQ4_STATUS_RECALLABLE_STATE_REVOKED)
+                nfs41_handle_recallable_state_revoked(clp);
+        else if (flags & (SEQ4_STATUS_CB_PATH_DOWN |
+                            SEQ4_STATUS_BACKCHANNEL_FAULT |
+                            SEQ4_STATUS_CB_PATH_DOWN_SESSION))
+                nfs41_handle_cb_path_down(clp);
+}
+
 static int nfs4_reset_session(struct nfs_client *clp)
 {
         int status;
 
+        nfs4_begin_drain_session(clp);
         status = nfs4_proc_destroy_session(clp->cl_session);
         if (status && status != -NFS4ERR_BADSESSION &&
             status != -NFS4ERR_DEADSESSION) {
-                nfs4_session_recovery_handle_error(clp, status);
+                status = nfs4_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*/
+        status = nfs4_proc_create_session(clp);
+        if (status) {
+                status = nfs4_recovery_handle_error(clp, status);
+                goto out;
+        }
+        /* create_session negotiated new slot table */
+        clear_bit(NFS4CLNT_RECALL_SLOT, &clp->cl_state);
+
+         /* Let the state manager reestablish state */
+        if (!test_bit(NFS4CLNT_LEASE_EXPIRED, &clp->cl_state))
+                nfs41_setup_state_renewal(clp);
 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)
+static int nfs4_recall_slot(struct nfs_client *clp)
 {
-        int status;
+        struct nfs4_slot_table *fc_tbl = &clp->cl_session->fc_slot_table;
+        struct nfs4_channel_attrs *fc_attrs = &clp->cl_session->fc_attrs;
+        struct nfs4_slot *new, *old;
+        int i;
+
+        nfs4_begin_drain_session(clp);
+        new = kmalloc(fc_tbl->target_max_slots * sizeof(struct nfs4_slot),
+                      GFP_NOFS);
+        if (!new)
+                return -ENOMEM;
 
-        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;
+        spin_lock(&fc_tbl->slot_tbl_lock);
+        for (i = 0; i < fc_tbl->target_max_slots; i++)
+                new[i].seq_nr = fc_tbl->slots[i].seq_nr;
+        old = fc_tbl->slots;
+        fc_tbl->slots = new;
+        fc_tbl->max_slots = fc_tbl->target_max_slots;
+        fc_tbl->target_max_slots = 0;
+        fc_attrs->max_reqs = fc_tbl->max_slots;
+        spin_unlock(&fc_tbl->slot_tbl_lock);
+
+        kfree(old);
+        nfs4_end_drain_session(clp);
+        return 0;
 }
+
 #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; }
+static int nfs4_end_drain_session(struct nfs_client *clp) { return 0; }
+static int nfs4_recall_slot(struct nfs_client *clp) { return 0; }
 #endif /* CONFIG_NFS_V4_1 */
 
 /* Set NFS4CLNT_LEASE_EXPIRED for all v4.0 errors and for recoverable errors
@@ -1214,6 +1577,8 @@ static void nfs4_set_lease_expired(struct nfs_client *clp, int status)
                 case -EAGAIN:
                         break;
 
+                case -EKEYEXPIRED:
+                        nfs4_warn_keyexpired(clp->cl_hostname);
                 case -NFS4ERR_NOT_SAME: /* FixMe: implement recovery
                                          * in nfs4_exchange_id */
                 default:
@@ -1234,7 +1599,8 @@ static void nfs4_state_manager(struct nfs_client *clp)
                         status = nfs4_reclaim_lease(clp);
                         if (status) {
                                 nfs4_set_lease_expired(clp, status);
-                                if (status == -EAGAIN)
+                                if (test_bit(NFS4CLNT_LEASE_EXPIRED,
+                                                        &clp->cl_state))
                                         continue;
                                 if (clp->cl_cons_state ==
                                                         NFS_CS_SESSION_INITING)
@@ -1242,61 +1608,68 @@ static void nfs4_state_manager(struct nfs_client *clp)
                                 goto out_error;
                         }
                         clear_bit(NFS4CLNT_CHECK_LEASE, &clp->cl_state);
+                        set_bit(NFS4CLNT_RECLAIM_REBOOT, &clp->cl_state);
+                        pnfs_destroy_all_layouts(clp);
                 }
 
                 if (test_and_clear_bit(NFS4CLNT_CHECK_LEASE, &clp->cl_state)) {
                         status = nfs4_check_lease(clp);
-                        if (status != 0)
+                        if (test_bit(NFS4CLNT_LEASE_EXPIRED, &clp->cl_state))
                                 continue;
+                        if (status < 0 && status != -NFS4ERR_CB_PATH_DOWN)
+                                goto out_error;
                 }
+
                 /* 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;
+                if (test_and_clear_bit(NFS4CLNT_SESSION_RESET, &clp->cl_state)
+                   && nfs4_has_session(clp)) {
+                        status = nfs4_reset_session(clp);
+                        if (test_bit(NFS4CLNT_LEASE_EXPIRED, &clp->cl_state))
+                                continue;
+                        if (status < 0)
                                 goto out_error;
-                        }
                 }
+
                 /* First recover reboot state... */
-                if (test_and_clear_bit(NFS4CLNT_RECLAIM_REBOOT, &clp->cl_state)) {
+                if (test_bit(NFS4CLNT_RECLAIM_REBOOT, &clp->cl_state)) {
                         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))
+                                clp->cl_mvops->reboot_recovery_ops);
+                        if (test_bit(NFS4CLNT_LEASE_EXPIRED, &clp->cl_state) ||
+                            test_bit(NFS4CLNT_SESSION_RESET, &clp->cl_state))
                                 continue;
                         nfs4_state_end_reclaim_reboot(clp);
-                        continue;
+                        if (test_bit(NFS4CLNT_RECLAIM_NOGRACE, &clp->cl_state))
+                                continue;
+                        if (status < 0)
+                                goto out_error;
                 }
 
                 /* Now recover expired state... */
                 if (test_and_clear_bit(NFS4CLNT_RECLAIM_NOGRACE, &clp->cl_state)) {
                         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;
+                                clp->cl_mvops->nograce_recovery_ops);
+                        if (test_bit(NFS4CLNT_LEASE_EXPIRED, &clp->cl_state) ||
+                            test_bit(NFS4CLNT_SESSION_RESET, &clp->cl_state) ||
+                            test_bit(NFS4CLNT_RECLAIM_REBOOT, &clp->cl_state))
+                                continue;
+                        if (status < 0)
                                 goto out_error;
-                        } else
-                                nfs4_state_end_reclaim_nograce(clp);
-                        continue;
                 }
 
+                nfs4_end_drain_session(clp);
                 if (test_and_clear_bit(NFS4CLNT_DELEGRETURN, &clp->cl_state)) {
                         nfs_client_return_marked_delegations(clp);
                         continue;
                 }
+                /* Recall session slots */
+                if (test_and_clear_bit(NFS4CLNT_RECALL_SLOT, &clp->cl_state)
+                   && nfs4_has_session(clp)) {
+                        status = nfs4_recall_slot(clp);
+                        if (status < 0)
+                                goto out_error;
+                        continue;
+                }
+
 
                 nfs4_clear_state_manager_bit(clp);
                 /* Did we race with an attempt to give us more work? */
@@ -1309,8 +1682,7 @@ static void nfs4_state_manager(struct nfs_client *clp)
 out_error:
         printk(KERN_WARNING "Error: state manager failed on NFSv4 server %s"
                         " with error %d\n", clp->cl_hostname, -status);
-        if (test_bit(NFS4CLNT_RECLAIM_REBOOT, &clp->cl_state))
-                nfs4_state_end_reclaim_reboot(clp);
+        nfs4_end_drain_session(clp);
         nfs4_clear_state_manager_bit(clp);
 }
 
diff --git a/fs/nfs/nfs4xdr.c b/fs/nfs/nfs4xdr.c
index 617273e7d47f..2ab8e5cb8f59 100644
--- a/fs/nfs/nfs4xdr.c
+++ b/fs/nfs/nfs4xdr.c
@@ -38,8 +38,6 @@
 #include <linux/param.h>
 #include <linux/time.h>
 #include <linux/mm.h>
-#include <linux/slab.h>
-#include <linux/utsname.h>
 #include <linux/errno.h>
 #include <linux/string.h>
 #include <linux/in.h>
@@ -47,11 +45,14 @@
 #include <linux/proc_fs.h>
 #include <linux/kdev_t.h>
 #include <linux/sunrpc/clnt.h>
+#include <linux/sunrpc/msg_prot.h>
 #include <linux/nfs.h>
 #include <linux/nfs4.h>
 #include <linux/nfs_fs.h>
 #include <linux/nfs_idmap.h>
 #include "nfs4_fs.h"
+#include "internal.h"
+#include "pnfs.h"
 
 #define NFSDBG_FACILITY         NFSDBG_XDR
 
@@ -70,8 +71,8 @@ static int nfs4_stat_to_errno(int);
 /* lock,open owner id:
  * we currently use size 2 (u64) out of (NFS4_OPAQUE_LIMIT  >> 2)
  */
-#define open_owner_id_maxsz     (1 + 4)
-#define lock_owner_id_maxsz     (1 + 4)
+#define open_owner_id_maxsz     (1 + 1 + 4)
+#define lock_owner_id_maxsz     (1 + 1 + 4)
 #define decode_lockowner_maxsz  (1 + XDR_QUADLEN(IDMAP_NAMESZ))
 #define compound_encode_hdr_maxsz       (3 + (NFS4_MAXTAGLEN >> 2))
 #define compound_decode_hdr_maxsz       (3 + (NFS4_MAXTAGLEN >> 2))
@@ -135,7 +136,7 @@ static int nfs4_stat_to_errno(int);
 #define decode_lookup_maxsz     (op_decode_hdr_maxsz)
 #define encode_share_access_maxsz \
                                 (2)
-#define encode_createmode_maxsz (1 + encode_attrs_maxsz)
+#define encode_createmode_maxsz (1 + encode_attrs_maxsz + encode_verifier_maxsz)
 #define encode_opentype_maxsz   (1 + encode_createmode_maxsz)
 #define encode_claim_null_maxsz (1 + nfs4_name_maxsz)
 #define encode_open_maxsz       (op_encode_hdr_maxsz + \
@@ -202,14 +203,17 @@ static int nfs4_stat_to_errno(int);
 #define encode_link_maxsz       (op_encode_hdr_maxsz + \
                                 nfs4_name_maxsz)
 #define decode_link_maxsz       (op_decode_hdr_maxsz + decode_change_info_maxsz)
+#define encode_lockowner_maxsz  (7)
 #define encode_lock_maxsz       (op_encode_hdr_maxsz + \
                                  7 + \
-                                 1 + encode_stateid_maxsz + 8)
+                                 1 + encode_stateid_maxsz + 1 + \
+                                 encode_lockowner_maxsz)
 #define decode_lock_denied_maxsz \
                                 (8 + decode_lockowner_maxsz)
 #define decode_lock_maxsz       (op_decode_hdr_maxsz + \
                                  decode_lock_denied_maxsz)
-#define encode_lockt_maxsz      (op_encode_hdr_maxsz + 12)
+#define encode_lockt_maxsz      (op_encode_hdr_maxsz + 5 + \
+                                encode_lockowner_maxsz)
 #define decode_lockt_maxsz      (op_decode_hdr_maxsz + \
                                  decode_lock_denied_maxsz)
 #define encode_locku_maxsz      (op_encode_hdr_maxsz + 3 + \
@@ -217,6 +221,11 @@ static int nfs4_stat_to_errno(int);
                                  4)
 #define decode_locku_maxsz      (op_decode_hdr_maxsz + \
                                  decode_stateid_maxsz)
+#define encode_release_lockowner_maxsz \
+                                (op_encode_hdr_maxsz + \
+                                 encode_lockowner_maxsz)
+#define decode_release_lockowner_maxsz \
+                                (op_decode_hdr_maxsz)
 #define encode_access_maxsz     (op_encode_hdr_maxsz + 1)
 #define decode_access_maxsz     (op_decode_hdr_maxsz + 2)
 #define encode_symlink_maxsz    (op_encode_hdr_maxsz + \
@@ -300,6 +309,21 @@ static int nfs4_stat_to_errno(int);
                                 XDR_QUADLEN(NFS4_MAX_SESSIONID_LEN) + 4)
 #define decode_sequence_maxsz   (op_decode_hdr_maxsz + \
                                 XDR_QUADLEN(NFS4_MAX_SESSIONID_LEN) + 5)
+#define encode_reclaim_complete_maxsz   (op_encode_hdr_maxsz + 4)
+#define decode_reclaim_complete_maxsz   (op_decode_hdr_maxsz + 4)
+#define encode_getdeviceinfo_maxsz (op_encode_hdr_maxsz + 4 + \
+                                XDR_QUADLEN(NFS4_DEVICEID4_SIZE))
+#define decode_getdeviceinfo_maxsz (op_decode_hdr_maxsz + \
+                                1 /* layout type */ + \
+                                1 /* opaque devaddr4 length */ + \
+                                  /* devaddr4 payload is read into page */ \
+                                1 /* notification bitmap length */ + \
+                                1 /* notification bitmap */)
+#define encode_layoutget_maxsz  (op_encode_hdr_maxsz + 10 + \
+                                encode_stateid_maxsz)
+#define decode_layoutget_maxsz  (op_decode_hdr_maxsz + 8 + \
+                                decode_stateid_maxsz + \
+                                XDR_QUADLEN(PNFS_LAYOUT_MAXSIZE))
 #else /* CONFIG_NFS_V4_1 */
 #define encode_sequence_maxsz   0
 #define decode_sequence_maxsz   0
@@ -469,6 +493,12 @@ static int nfs4_stat_to_errno(int);
                                 decode_sequence_maxsz + \
                                 decode_putfh_maxsz + \
                                 decode_locku_maxsz)
+#define NFS4_enc_release_lockowner_sz \
+                                (compound_encode_hdr_maxsz + \
+                                 encode_lockowner_maxsz)
+#define NFS4_dec_release_lockowner_sz \
+                                (compound_decode_hdr_maxsz + \
+                                 decode_lockowner_maxsz)
 #define NFS4_enc_access_sz      (compound_encode_hdr_maxsz + \
                                 encode_sequence_maxsz + \
                                 encode_putfh_maxsz + \
@@ -677,6 +707,39 @@ static int nfs4_stat_to_errno(int);
                                          decode_sequence_maxsz + \
                                          decode_putrootfh_maxsz + \
                                          decode_fsinfo_maxsz)
+#define NFS4_enc_reclaim_complete_sz    (compound_encode_hdr_maxsz + \
+                                         encode_sequence_maxsz + \
+                                         encode_reclaim_complete_maxsz)
+#define NFS4_dec_reclaim_complete_sz    (compound_decode_hdr_maxsz + \
+                                         decode_sequence_maxsz + \
+                                         decode_reclaim_complete_maxsz)
+#define NFS4_enc_getdeviceinfo_sz (compound_encode_hdr_maxsz +    \
+                                encode_sequence_maxsz +\
+                                encode_getdeviceinfo_maxsz)
+#define NFS4_dec_getdeviceinfo_sz (compound_decode_hdr_maxsz +    \
+                                decode_sequence_maxsz + \
+                                decode_getdeviceinfo_maxsz)
+#define NFS4_enc_layoutget_sz   (compound_encode_hdr_maxsz + \
+                                encode_sequence_maxsz + \
+                                encode_putfh_maxsz +        \
+                                encode_layoutget_maxsz)
+#define NFS4_dec_layoutget_sz   (compound_decode_hdr_maxsz + \
+                                decode_sequence_maxsz + \
+                                decode_putfh_maxsz +        \
+                                decode_layoutget_maxsz)
+
+const u32 nfs41_maxwrite_overhead = ((RPC_MAX_HEADER_WITH_AUTH +
+                                      compound_encode_hdr_maxsz +
+                                      encode_sequence_maxsz +
+                                      encode_putfh_maxsz +
+                                      encode_getattr_maxsz) *
+                                     XDR_UNIT);
+
+const u32 nfs41_maxread_overhead = ((RPC_MAX_HEADER_WITH_AUTH +
+                                     compound_decode_hdr_maxsz +
+                                     decode_sequence_maxsz +
+                                     decode_putfh_maxsz) *
+                                    XDR_UNIT);
 #endif /* CONFIG_NFS_V4_1 */
 
 static const umode_t nfs_type2fmt[] = {
@@ -702,29 +765,12 @@ struct compound_hdr {
         u32             minorversion;
 };
 
-/*
- * START OF "GENERIC" ENCODE ROUTINES.
- *   These may look a little ugly since they are imported from a "generic"
- * set of XDR encode/decode routines which are intended to be shared by
- * all of our NFSv4 implementations (OpenBSD, MacOS X...).
- *
- * If the pain of reading these is too great, it should be a straightforward
- * task to translate them into Linux-specific versions which are more
- * consistent with the style used in NFSv2/v3...
- */
-#define WRITE32(n)               *p++ = htonl(n)
-#define WRITE64(n)               do {                           \
-        *p++ = htonl((uint32_t)((n) >> 32));                            \
-        *p++ = htonl((uint32_t)(n));                                    \
-} while (0)
-#define WRITEMEM(ptr,nbytes)     do {                           \
-        p = xdr_encode_opaque_fixed(p, ptr, nbytes);            \
-} while (0)
-
-#define RESERVE_SPACE(nbytes)   do {                            \
-        p = xdr_reserve_space(xdr, nbytes);                     \
-        BUG_ON(!p);                                             \
-} while (0)
+static __be32 *reserve_space(struct xdr_stream *xdr, size_t nbytes)
+{
+        __be32 *p = xdr_reserve_space(xdr, nbytes);
+        BUG_ON(!p);
+        return p;
+}
 
 static void encode_string(struct xdr_stream *xdr, unsigned int len, const char *str)
 {
@@ -740,7 +786,7 @@ static void encode_compound_hdr(struct xdr_stream *xdr,
                                 struct compound_hdr *hdr)
 {
         __be32 *p;
-        struct rpc_auth *auth = req->rq_task->tk_msg.rpc_cred->cr_auth;
+        struct rpc_auth *auth = req->rq_cred->cr_auth;
 
         /* initialize running count of expected bytes in reply.
          * NOTE: the replied tag SHOULD be the same is the one sent,
@@ -749,12 +795,11 @@ static void encode_compound_hdr(struct xdr_stream *xdr,
 
         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(hdr->minorversion);
+        p = reserve_space(xdr, 4 + hdr->taglen + 8);
+        p = xdr_encode_opaque(p, hdr->tag, hdr->taglen);
+        *p++ = cpu_to_be32(hdr->minorversion);
         hdr->nops_p = p;
-        WRITE32(hdr->nops);
+        *p = cpu_to_be32(hdr->nops);
 }
 
 static void encode_nops(struct compound_hdr *hdr)
@@ -799,7 +844,7 @@ static void encode_attrs(struct xdr_stream *xdr, const struct iattr *iap, const
         if (iap->ia_valid & ATTR_MODE)
                 len += 4;
         if (iap->ia_valid & ATTR_UID) {
-                owner_namelen = nfs_map_uid_to_name(server->nfs_client, iap->ia_uid, owner_name);
+                owner_namelen = nfs_map_uid_to_name(server->nfs_client, iap->ia_uid, owner_name, IDMAP_NAMESZ);
                 if (owner_namelen < 0) {
                         dprintk("nfs: couldn't resolve uid %d to string\n",
                                         iap->ia_uid);
@@ -811,7 +856,7 @@ static void encode_attrs(struct xdr_stream *xdr, const struct iattr *iap, const
                 len += 4 + (XDR_QUADLEN(owner_namelen) << 2);
         }
         if (iap->ia_valid & ATTR_GID) {
-                owner_grouplen = nfs_map_gid_to_group(server->nfs_client, iap->ia_gid, owner_group);
+                owner_grouplen = nfs_map_gid_to_group(server->nfs_client, iap->ia_gid, owner_group, IDMAP_NAMESZ);
                 if (owner_grouplen < 0) {
                         dprintk("nfs: couldn't resolve gid %d to string\n",
                                         iap->ia_gid);
@@ -829,55 +874,53 @@ static void encode_attrs(struct xdr_stream *xdr, const struct iattr *iap, const
                 len += 16;
         else if (iap->ia_valid & ATTR_MTIME)
                 len += 4;
-        RESERVE_SPACE(len);
+        p = reserve_space(xdr, len);
 
         /*
          * We write the bitmap length now, but leave the bitmap and the attribute
          * buffer length to be backfilled at the end of this routine.
          */
-        WRITE32(2);
+        *p++ = cpu_to_be32(2);
         q = p;
         p += 3;
 
         if (iap->ia_valid & ATTR_SIZE) {
                 bmval0 |= FATTR4_WORD0_SIZE;
-                WRITE64(iap->ia_size);
+                p = xdr_encode_hyper(p, iap->ia_size);
         }
         if (iap->ia_valid & ATTR_MODE) {
                 bmval1 |= FATTR4_WORD1_MODE;
-                WRITE32(iap->ia_mode & S_IALLUGO);
+                *p++ = cpu_to_be32(iap->ia_mode & S_IALLUGO);
         }
         if (iap->ia_valid & ATTR_UID) {
                 bmval1 |= FATTR4_WORD1_OWNER;
-                WRITE32(owner_namelen);
-                WRITEMEM(owner_name, owner_namelen);
+                p = xdr_encode_opaque(p, owner_name, owner_namelen);
         }
         if (iap->ia_valid & ATTR_GID) {
                 bmval1 |= FATTR4_WORD1_OWNER_GROUP;
-                WRITE32(owner_grouplen);
-                WRITEMEM(owner_group, owner_grouplen);
+                p = xdr_encode_opaque(p, owner_group, owner_grouplen);
         }
         if (iap->ia_valid & ATTR_ATIME_SET) {
                 bmval1 |= FATTR4_WORD1_TIME_ACCESS_SET;
-                WRITE32(NFS4_SET_TO_CLIENT_TIME);
-                WRITE32(0);
-                WRITE32(iap->ia_mtime.tv_sec);
-                WRITE32(iap->ia_mtime.tv_nsec);
+                *p++ = cpu_to_be32(NFS4_SET_TO_CLIENT_TIME);
+                *p++ = cpu_to_be32(0);
+                *p++ = cpu_to_be32(iap->ia_atime.tv_sec);
+                *p++ = cpu_to_be32(iap->ia_atime.tv_nsec);
         }
         else if (iap->ia_valid & ATTR_ATIME) {
                 bmval1 |= FATTR4_WORD1_TIME_ACCESS_SET;
-                WRITE32(NFS4_SET_TO_SERVER_TIME);
+                *p++ = cpu_to_be32(NFS4_SET_TO_SERVER_TIME);
         }
         if (iap->ia_valid & ATTR_MTIME_SET) {
                 bmval1 |= FATTR4_WORD1_TIME_MODIFY_SET;
-                WRITE32(NFS4_SET_TO_CLIENT_TIME);
-                WRITE32(0);
-                WRITE32(iap->ia_mtime.tv_sec);
-                WRITE32(iap->ia_mtime.tv_nsec);
+                *p++ = cpu_to_be32(NFS4_SET_TO_CLIENT_TIME);
+                *p++ = cpu_to_be32(0);
+                *p++ = cpu_to_be32(iap->ia_mtime.tv_sec);
+                *p++ = cpu_to_be32(iap->ia_mtime.tv_nsec);
         }
         else if (iap->ia_valid & ATTR_MTIME) {
                 bmval1 |= FATTR4_WORD1_TIME_MODIFY_SET;
-                WRITE32(NFS4_SET_TO_SERVER_TIME);
+                *p++ = cpu_to_be32(NFS4_SET_TO_SERVER_TIME);
         }
 
         /*
@@ -891,7 +934,7 @@ static void encode_attrs(struct xdr_stream *xdr, const struct iattr *iap, const
         len = (char *)p - (char *)q - 12;
         *q++ = htonl(bmval0);
         *q++ = htonl(bmval1);
-        *q++ = htonl(len);
+        *q = htonl(len);
 
 /* out: */
 }
@@ -900,9 +943,9 @@ static void encode_access(struct xdr_stream *xdr, u32 access, struct compound_hd
 {
         __be32 *p;
 
-        RESERVE_SPACE(8);
-        WRITE32(OP_ACCESS);
-        WRITE32(access);
+        p = reserve_space(xdr, 8);
+        *p++ = cpu_to_be32(OP_ACCESS);
+        *p = cpu_to_be32(access);
         hdr->nops++;
         hdr->replen += decode_access_maxsz;
 }
@@ -911,10 +954,10 @@ static void encode_close(struct xdr_stream *xdr, const struct nfs_closeargs *arg
 {
         __be32 *p;
 
-        RESERVE_SPACE(8+NFS4_STATEID_SIZE);
-        WRITE32(OP_CLOSE);
-        WRITE32(arg->seqid->sequence->counter);
-        WRITEMEM(arg->stateid->data, NFS4_STATEID_SIZE);
+        p = reserve_space(xdr, 8+NFS4_STATEID_SIZE);
+        *p++ = cpu_to_be32(OP_CLOSE);
+        *p++ = cpu_to_be32(arg->seqid->sequence->counter);
+        xdr_encode_opaque_fixed(p, arg->stateid->data, NFS4_STATEID_SIZE);
         hdr->nops++;
         hdr->replen += decode_close_maxsz;
 }
@@ -923,10 +966,10 @@ static void encode_commit(struct xdr_stream *xdr, const struct nfs_writeargs *ar
 {
         __be32 *p;
 
-        RESERVE_SPACE(16);
-        WRITE32(OP_COMMIT);
-        WRITE64(args->offset);
-        WRITE32(args->count);
+        p = reserve_space(xdr, 16);
+        *p++ = cpu_to_be32(OP_COMMIT);
+        p = xdr_encode_hyper(p, args->offset);
+        *p = cpu_to_be32(args->count);
         hdr->nops++;
         hdr->replen += decode_commit_maxsz;
 }
@@ -935,30 +978,28 @@ static void encode_create(struct xdr_stream *xdr, const struct nfs4_create_arg *
 {
         __be32 *p;
 
-        RESERVE_SPACE(8);
-        WRITE32(OP_CREATE);
-        WRITE32(create->ftype);
+        p = reserve_space(xdr, 8);
+        *p++ = cpu_to_be32(OP_CREATE);
+        *p = cpu_to_be32(create->ftype);
 
         switch (create->ftype) {
         case NF4LNK:
-                RESERVE_SPACE(4);
-                WRITE32(create->u.symlink.len);
+                p = reserve_space(xdr, 4);
+                *p = cpu_to_be32(create->u.symlink.len);
                 xdr_write_pages(xdr, create->u.symlink.pages, 0, create->u.symlink.len);
                 break;
 
         case NF4BLK: case NF4CHR:
-                RESERVE_SPACE(8);
-                WRITE32(create->u.device.specdata1);
-                WRITE32(create->u.device.specdata2);
+                p = reserve_space(xdr, 8);
+                *p++ = cpu_to_be32(create->u.device.specdata1);
+                *p = cpu_to_be32(create->u.device.specdata2);
                 break;
 
         default:
                 break;
         }
 
-        RESERVE_SPACE(4 + create->name->len);
-        WRITE32(create->name->len);
-        WRITEMEM(create->name->name, create->name->len);
+        encode_string(xdr, create->name->len, create->name->name);
         hdr->nops++;
         hdr->replen += decode_create_maxsz;
 
@@ -969,10 +1010,10 @@ static void encode_getattr_one(struct xdr_stream *xdr, uint32_t bitmap, struct c
 {
         __be32 *p;
 
-        RESERVE_SPACE(12);
-        WRITE32(OP_GETATTR);
-        WRITE32(1);
-        WRITE32(bitmap);
+        p = reserve_space(xdr, 12);
+        *p++ = cpu_to_be32(OP_GETATTR);
+        *p++ = cpu_to_be32(1);
+        *p = cpu_to_be32(bitmap);
         hdr->nops++;
         hdr->replen += decode_getattr_maxsz;
 }
@@ -981,11 +1022,11 @@ static void encode_getattr_two(struct xdr_stream *xdr, uint32_t bm0, uint32_t bm
 {
         __be32 *p;
 
-        RESERVE_SPACE(16);
-        WRITE32(OP_GETATTR);
-        WRITE32(2);
-        WRITE32(bm0);
-        WRITE32(bm1);
+        p = reserve_space(xdr, 16);
+        *p++ = cpu_to_be32(OP_GETATTR);
+        *p++ = cpu_to_be32(2);
+        *p++ = cpu_to_be32(bm0);
+        *p = cpu_to_be32(bm1);
         hdr->nops++;
         hdr->replen += decode_getattr_maxsz;
 }
@@ -1012,8 +1053,8 @@ static void encode_getfh(struct xdr_stream *xdr, struct compound_hdr *hdr)
 {
         __be32 *p;
 
-        RESERVE_SPACE(4);
-        WRITE32(OP_GETFH);
+        p = reserve_space(xdr, 4);
+        *p = cpu_to_be32(OP_GETFH);
         hdr->nops++;
         hdr->replen += decode_getfh_maxsz;
 }
@@ -1022,10 +1063,9 @@ static void encode_link(struct xdr_stream *xdr, const struct qstr *name, struct
 {
         __be32 *p;
 
-        RESERVE_SPACE(8 + name->len);
-        WRITE32(OP_LINK);
-        WRITE32(name->len);
-        WRITEMEM(name->name, name->len);
+        p = reserve_space(xdr, 8 + name->len);
+        *p++ = cpu_to_be32(OP_LINK);
+        xdr_encode_opaque(p, name->name, name->len);
         hdr->nops++;
         hdr->replen += decode_link_maxsz;
 }
@@ -1044,6 +1084,18 @@ static inline uint64_t nfs4_lock_length(struct file_lock *fl)
         return fl->fl_end - fl->fl_start + 1;
 }
 
+static void encode_lockowner(struct xdr_stream *xdr, const struct nfs_lowner *lowner)
+{
+        __be32 *p;
+
+        p = reserve_space(xdr, 32);
+        p = xdr_encode_hyper(p, lowner->clientid);
+        *p++ = cpu_to_be32(20);
+        p = xdr_encode_opaque_fixed(p, "lock id:", 8);
+        *p++ = cpu_to_be32(lowner->s_dev);
+        xdr_encode_hyper(p, lowner->id);
+}
+
 /*
  * opcode,type,reclaim,offset,length,new_lock_owner = 32
  * open_seqid,open_stateid,lock_seqid,lock_owner.clientid, lock_owner.id = 40
@@ -1052,27 +1104,24 @@ static void encode_lock(struct xdr_stream *xdr, const struct nfs_lock_args *args
 {
         __be32 *p;
 
-        RESERVE_SPACE(32);
-        WRITE32(OP_LOCK);
-        WRITE32(nfs4_lock_type(args->fl, args->block));
-        WRITE32(args->reclaim);
-        WRITE64(args->fl->fl_start);
-        WRITE64(nfs4_lock_length(args->fl));
-        WRITE32(args->new_lock_owner);
+        p = reserve_space(xdr, 32);
+        *p++ = cpu_to_be32(OP_LOCK);
+        *p++ = cpu_to_be32(nfs4_lock_type(args->fl, args->block));
+        *p++ = cpu_to_be32(args->reclaim);
+        p = xdr_encode_hyper(p, args->fl->fl_start);
+        p = xdr_encode_hyper(p, nfs4_lock_length(args->fl));
+        *p = cpu_to_be32(args->new_lock_owner);
         if (args->new_lock_owner){
-                RESERVE_SPACE(4+NFS4_STATEID_SIZE+32);
-                WRITE32(args->open_seqid->sequence->counter);
-                WRITEMEM(args->open_stateid->data, NFS4_STATEID_SIZE);
-                WRITE32(args->lock_seqid->sequence->counter);
-                WRITE64(args->lock_owner.clientid);
-                WRITE32(16);
-                WRITEMEM("lock id:", 8);
-                WRITE64(args->lock_owner.id);
+                p = reserve_space(xdr, 4+NFS4_STATEID_SIZE+4);
+                *p++ = cpu_to_be32(args->open_seqid->sequence->counter);
+                p = xdr_encode_opaque_fixed(p, args->open_stateid->data, NFS4_STATEID_SIZE);
+                *p++ = cpu_to_be32(args->lock_seqid->sequence->counter);
+                encode_lockowner(xdr, &args->lock_owner);
         }
         else {
-                RESERVE_SPACE(NFS4_STATEID_SIZE+4);
-                WRITEMEM(args->lock_stateid->data, NFS4_STATEID_SIZE);
-                WRITE32(args->lock_seqid->sequence->counter);
+                p = reserve_space(xdr, NFS4_STATEID_SIZE+4);
+                p = xdr_encode_opaque_fixed(p, args->lock_stateid->data, NFS4_STATEID_SIZE);
+                *p = cpu_to_be32(args->lock_seqid->sequence->counter);
         }
         hdr->nops++;
         hdr->replen += decode_lock_maxsz;
@@ -1082,15 +1131,12 @@ static void encode_lockt(struct xdr_stream *xdr, const struct nfs_lockt_args *ar
 {
         __be32 *p;
 
-        RESERVE_SPACE(52);
-        WRITE32(OP_LOCKT);
-        WRITE32(nfs4_lock_type(args->fl, 0));
-        WRITE64(args->fl->fl_start);
-        WRITE64(nfs4_lock_length(args->fl));
-        WRITE64(args->lock_owner.clientid);
-        WRITE32(16);
-        WRITEMEM("lock id:", 8);
-        WRITE64(args->lock_owner.id);
+        p = reserve_space(xdr, 24);
+        *p++ = cpu_to_be32(OP_LOCKT);
+        *p++ = cpu_to_be32(nfs4_lock_type(args->fl, 0));
+        p = xdr_encode_hyper(p, args->fl->fl_start);
+        p = xdr_encode_hyper(p, nfs4_lock_length(args->fl));
+        encode_lockowner(xdr, &args->lock_owner);
         hdr->nops++;
         hdr->replen += decode_lockt_maxsz;
 }
@@ -1099,26 +1145,36 @@ static void encode_locku(struct xdr_stream *xdr, const struct nfs_locku_args *ar
 {
         __be32 *p;
 
-        RESERVE_SPACE(12+NFS4_STATEID_SIZE+16);
-        WRITE32(OP_LOCKU);
-        WRITE32(nfs4_lock_type(args->fl, 0));
-        WRITE32(args->seqid->sequence->counter);
-        WRITEMEM(args->stateid->data, NFS4_STATEID_SIZE);
-        WRITE64(args->fl->fl_start);
-        WRITE64(nfs4_lock_length(args->fl));
+        p = reserve_space(xdr, 12+NFS4_STATEID_SIZE+16);
+        *p++ = cpu_to_be32(OP_LOCKU);
+        *p++ = cpu_to_be32(nfs4_lock_type(args->fl, 0));
+        *p++ = cpu_to_be32(args->seqid->sequence->counter);
+        p = xdr_encode_opaque_fixed(p, args->stateid->data, NFS4_STATEID_SIZE);
+        p = xdr_encode_hyper(p, args->fl->fl_start);
+        xdr_encode_hyper(p, nfs4_lock_length(args->fl));
         hdr->nops++;
         hdr->replen += decode_locku_maxsz;
 }
 
+static void encode_release_lockowner(struct xdr_stream *xdr, const struct nfs_lowner *lowner, struct compound_hdr *hdr)
+{
+        __be32 *p;
+
+        p = reserve_space(xdr, 4);
+        *p = cpu_to_be32(OP_RELEASE_LOCKOWNER);
+        encode_lockowner(xdr, lowner);
+        hdr->nops++;
+        hdr->replen += decode_release_lockowner_maxsz;
+}
+
 static void encode_lookup(struct xdr_stream *xdr, const struct qstr *name, struct compound_hdr *hdr)
 {
         int len = name->len;
         __be32 *p;
 
-        RESERVE_SPACE(8 + len);
-        WRITE32(OP_LOOKUP);
-        WRITE32(len);
-        WRITEMEM(name->name, len);
+        p = reserve_space(xdr, 8 + len);
+        *p++ = cpu_to_be32(OP_LOOKUP);
+        xdr_encode_opaque(p, name->name, len);
         hdr->nops++;
         hdr->replen += decode_lookup_maxsz;
 }
@@ -1127,21 +1183,21 @@ static void encode_share_access(struct xdr_stream *xdr, fmode_t fmode)
 {
         __be32 *p;
 
-        RESERVE_SPACE(8);
+        p = reserve_space(xdr, 8);
         switch (fmode & (FMODE_READ|FMODE_WRITE)) {
         case FMODE_READ:
-                WRITE32(NFS4_SHARE_ACCESS_READ);
+                *p++ = cpu_to_be32(NFS4_SHARE_ACCESS_READ);
                 break;
         case FMODE_WRITE:
-                WRITE32(NFS4_SHARE_ACCESS_WRITE);
+                *p++ = cpu_to_be32(NFS4_SHARE_ACCESS_WRITE);
                 break;
         case FMODE_READ|FMODE_WRITE:
-                WRITE32(NFS4_SHARE_ACCESS_BOTH);
+                *p++ = cpu_to_be32(NFS4_SHARE_ACCESS_BOTH);
                 break;
         default:
-                WRITE32(0);
+                *p++ = cpu_to_be32(0);
         }
-        WRITE32(0);             /* for linux, share_deny = 0 always */
+        *p = cpu_to_be32(0);            /* for linux, share_deny = 0 always */
 }
 
 static inline void encode_openhdr(struct xdr_stream *xdr, const struct nfs_openargs *arg)
@@ -1151,30 +1207,47 @@ static inline void encode_openhdr(struct xdr_stream *xdr, const struct nfs_opena
  * opcode 4, seqid 4, share_access 4, share_deny 4, clientid 8, ownerlen 4,
  * owner 4 = 32
  */
-        RESERVE_SPACE(8);
-        WRITE32(OP_OPEN);
-        WRITE32(arg->seqid->sequence->counter);
+        p = reserve_space(xdr, 8);
+        *p++ = cpu_to_be32(OP_OPEN);
+        *p = cpu_to_be32(arg->seqid->sequence->counter);
         encode_share_access(xdr, arg->fmode);
-        RESERVE_SPACE(28);
-        WRITE64(arg->clientid);
-        WRITE32(16);
-        WRITEMEM("open id:", 8);
-        WRITE64(arg->id);
+        p = reserve_space(xdr, 32);
+        p = xdr_encode_hyper(p, arg->clientid);
+        *p++ = cpu_to_be32(20);
+        p = xdr_encode_opaque_fixed(p, "open id:", 8);
+        *p++ = cpu_to_be32(arg->server->s_dev);
+        xdr_encode_hyper(p, arg->id);
 }
 
 static inline void encode_createmode(struct xdr_stream *xdr, const struct nfs_openargs *arg)
 {
         __be32 *p;
+        struct nfs_client *clp;
 
-        RESERVE_SPACE(4);
+        p = reserve_space(xdr, 4);
         switch(arg->open_flags & O_EXCL) {
         case 0:
-                WRITE32(NFS4_CREATE_UNCHECKED);
+                *p = cpu_to_be32(NFS4_CREATE_UNCHECKED);
                 encode_attrs(xdr, arg->u.attrs, arg->server);
                 break;
         default:
-                WRITE32(NFS4_CREATE_EXCLUSIVE);
-                encode_nfs4_verifier(xdr, &arg->u.verifier);
+                clp = arg->server->nfs_client;
+                if (clp->cl_mvops->minor_version > 0) {
+                        if (nfs4_has_persistent_session(clp)) {
+                                *p = cpu_to_be32(NFS4_CREATE_GUARDED);
+                                encode_attrs(xdr, arg->u.attrs, arg->server);
+                        } else {
+                                struct iattr dummy;
+
+                                *p = cpu_to_be32(NFS4_CREATE_EXCLUSIVE4_1);
+                                encode_nfs4_verifier(xdr, &arg->u.verifier);
+                                dummy.ia_valid = 0;
+                                encode_attrs(xdr, &dummy, arg->server);
+                        }
+                } else {
+                        *p = cpu_to_be32(NFS4_CREATE_EXCLUSIVE);
+                        encode_nfs4_verifier(xdr, &arg->u.verifier);
+                }
         }
 }
 
@@ -1182,14 +1255,14 @@ static void encode_opentype(struct xdr_stream *xdr, const struct nfs_openargs *a
 {
         __be32 *p;
 
-        RESERVE_SPACE(4);
+        p = reserve_space(xdr, 4);
         switch (arg->open_flags & O_CREAT) {
         case 0:
-                WRITE32(NFS4_OPEN_NOCREATE);
+                *p = cpu_to_be32(NFS4_OPEN_NOCREATE);
                 break;
         default:
                 BUG_ON(arg->claim != NFS4_OPEN_CLAIM_NULL);
-                WRITE32(NFS4_OPEN_CREATE);
+                *p = cpu_to_be32(NFS4_OPEN_CREATE);
                 encode_createmode(xdr, arg);
         }
 }
@@ -1198,16 +1271,16 @@ static inline void encode_delegation_type(struct xdr_stream *xdr, fmode_t delega
 {
         __be32 *p;
 
-        RESERVE_SPACE(4);
+        p = reserve_space(xdr, 4);
         switch (delegation_type) {
         case 0:
-                WRITE32(NFS4_OPEN_DELEGATE_NONE);
+                *p = cpu_to_be32(NFS4_OPEN_DELEGATE_NONE);
                 break;
         case FMODE_READ:
-                WRITE32(NFS4_OPEN_DELEGATE_READ);
+                *p = cpu_to_be32(NFS4_OPEN_DELEGATE_READ);
                 break;
         case FMODE_WRITE|FMODE_READ:
-                WRITE32(NFS4_OPEN_DELEGATE_WRITE);
+                *p = cpu_to_be32(NFS4_OPEN_DELEGATE_WRITE);
                 break;
         default:
                 BUG();
@@ -1218,8 +1291,8 @@ static inline void encode_claim_null(struct xdr_stream *xdr, const struct qstr *
 {
         __be32 *p;
 
-        RESERVE_SPACE(4);
-        WRITE32(NFS4_OPEN_CLAIM_NULL);
+        p = reserve_space(xdr, 4);
+        *p = cpu_to_be32(NFS4_OPEN_CLAIM_NULL);
         encode_string(xdr, name->len, name->name);
 }
 
@@ -1227,8 +1300,8 @@ static inline void encode_claim_previous(struct xdr_stream *xdr, fmode_t type)
 {
         __be32 *p;
 
-        RESERVE_SPACE(4);
-        WRITE32(NFS4_OPEN_CLAIM_PREVIOUS);
+        p = reserve_space(xdr, 4);
+        *p = cpu_to_be32(NFS4_OPEN_CLAIM_PREVIOUS);
         encode_delegation_type(xdr, type);
 }
 
@@ -1236,9 +1309,9 @@ static inline void encode_claim_delegate_cur(struct xdr_stream *xdr, const struc
 {
         __be32 *p;
 
-        RESERVE_SPACE(4+NFS4_STATEID_SIZE);
-        WRITE32(NFS4_OPEN_CLAIM_DELEGATE_CUR);
-        WRITEMEM(stateid->data, NFS4_STATEID_SIZE);
+        p = reserve_space(xdr, 4+NFS4_STATEID_SIZE);
+        *p++ = cpu_to_be32(NFS4_OPEN_CLAIM_DELEGATE_CUR);
+        xdr_encode_opaque_fixed(p, stateid->data, NFS4_STATEID_SIZE);
         encode_string(xdr, name->len, name->name);
 }
 
@@ -1267,10 +1340,10 @@ static void encode_open_confirm(struct xdr_stream *xdr, const struct nfs_open_co
 {
         __be32 *p;
 
-        RESERVE_SPACE(4+NFS4_STATEID_SIZE+4);
-        WRITE32(OP_OPEN_CONFIRM);
-        WRITEMEM(arg->stateid->data, NFS4_STATEID_SIZE);
-        WRITE32(arg->seqid->sequence->counter);
+        p = reserve_space(xdr, 4+NFS4_STATEID_SIZE+4);
+        *p++ = cpu_to_be32(OP_OPEN_CONFIRM);
+        p = xdr_encode_opaque_fixed(p, arg->stateid->data, NFS4_STATEID_SIZE);
+        *p = cpu_to_be32(arg->seqid->sequence->counter);
         hdr->nops++;
         hdr->replen += decode_open_confirm_maxsz;
 }
@@ -1279,10 +1352,10 @@ static void encode_open_downgrade(struct xdr_stream *xdr, const struct nfs_close
 {
         __be32 *p;
 
-        RESERVE_SPACE(4+NFS4_STATEID_SIZE+4);
-        WRITE32(OP_OPEN_DOWNGRADE);
-        WRITEMEM(arg->stateid->data, NFS4_STATEID_SIZE);
-        WRITE32(arg->seqid->sequence->counter);
+        p = reserve_space(xdr, 4+NFS4_STATEID_SIZE+4);
+        *p++ = cpu_to_be32(OP_OPEN_DOWNGRADE);
+        p = xdr_encode_opaque_fixed(p, arg->stateid->data, NFS4_STATEID_SIZE);
+        *p = cpu_to_be32(arg->seqid->sequence->counter);
         encode_share_access(xdr, arg->fmode);
         hdr->nops++;
         hdr->replen += decode_open_downgrade_maxsz;
@@ -1294,10 +1367,9 @@ encode_putfh(struct xdr_stream *xdr, const struct nfs_fh *fh, struct compound_hd
         int len = fh->size;
         __be32 *p;
 
-        RESERVE_SPACE(8 + len);
-        WRITE32(OP_PUTFH);
-        WRITE32(len);
-        WRITEMEM(fh->data, len);
+        p = reserve_space(xdr, 8 + len);
+        *p++ = cpu_to_be32(OP_PUTFH);
+        xdr_encode_opaque(p, fh->data, len);
         hdr->nops++;
         hdr->replen += decode_putfh_maxsz;
 }
@@ -1306,63 +1378,74 @@ static void encode_putrootfh(struct xdr_stream *xdr, struct compound_hdr *hdr)
 {
         __be32 *p;
 
-        RESERVE_SPACE(4);
-        WRITE32(OP_PUTROOTFH);
+        p = reserve_space(xdr, 4);
+        *p = cpu_to_be32(OP_PUTROOTFH);
         hdr->nops++;
         hdr->replen += decode_putrootfh_maxsz;
 }
 
-static void encode_stateid(struct xdr_stream *xdr, const struct nfs_open_context *ctx)
+static void encode_stateid(struct xdr_stream *xdr, const struct nfs_open_context *ctx, const struct nfs_lock_context *l_ctx)
 {
         nfs4_stateid stateid;
         __be32 *p;
 
-        RESERVE_SPACE(NFS4_STATEID_SIZE);
+        p = reserve_space(xdr, NFS4_STATEID_SIZE);
         if (ctx->state != NULL) {
-                nfs4_copy_stateid(&stateid, ctx->state, ctx->lockowner);
-                WRITEMEM(stateid.data, NFS4_STATEID_SIZE);
+                nfs4_copy_stateid(&stateid, ctx->state, l_ctx->lockowner, l_ctx->pid);
+                xdr_encode_opaque_fixed(p, stateid.data, NFS4_STATEID_SIZE);
         } else
-                WRITEMEM(zero_stateid.data, NFS4_STATEID_SIZE);
+                xdr_encode_opaque_fixed(p, zero_stateid.data, NFS4_STATEID_SIZE);
 }
 
 static void encode_read(struct xdr_stream *xdr, const struct nfs_readargs *args, struct compound_hdr *hdr)
 {
         __be32 *p;
 
-        RESERVE_SPACE(4);
-        WRITE32(OP_READ);
+        p = reserve_space(xdr, 4);
+        *p = cpu_to_be32(OP_READ);
 
-        encode_stateid(xdr, args->context);
+        encode_stateid(xdr, args->context, args->lock_context);
 
-        RESERVE_SPACE(12);
-        WRITE64(args->offset);
-        WRITE32(args->count);
+        p = reserve_space(xdr, 12);
+        p = xdr_encode_hyper(p, args->offset);
+        *p = cpu_to_be32(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)
 {
-        uint32_t attrs[2] = {
-                FATTR4_WORD0_RDATTR_ERROR|FATTR4_WORD0_FILEID,
-                FATTR4_WORD1_MOUNTED_ON_FILEID,
-        };
+        uint32_t attrs[2] = {0, 0};
+        uint32_t dircount = readdir->count >> 1;
         __be32 *p;
 
-        RESERVE_SPACE(12+NFS4_VERIFIER_SIZE+20);
-        WRITE32(OP_READDIR);
-        WRITE64(readdir->cookie);
-        WRITEMEM(readdir->verifier.data, NFS4_VERIFIER_SIZE);
-        WRITE32(readdir->count >> 1);  /* We're not doing readdirplus */
-        WRITE32(readdir->count);
-        WRITE32(2);
+        if (readdir->plus) {
+                attrs[0] |= FATTR4_WORD0_TYPE|FATTR4_WORD0_CHANGE|FATTR4_WORD0_SIZE|
+                        FATTR4_WORD0_FSID|FATTR4_WORD0_FILEHANDLE;
+                attrs[1] |= FATTR4_WORD1_MODE|FATTR4_WORD1_NUMLINKS|FATTR4_WORD1_OWNER|
+                        FATTR4_WORD1_OWNER_GROUP|FATTR4_WORD1_RAWDEV|
+                        FATTR4_WORD1_SPACE_USED|FATTR4_WORD1_TIME_ACCESS|
+                        FATTR4_WORD1_TIME_METADATA|FATTR4_WORD1_TIME_MODIFY;
+                dircount >>= 1;
+        }
+        attrs[0] |= FATTR4_WORD0_RDATTR_ERROR|FATTR4_WORD0_FILEID;
+        attrs[1] |= FATTR4_WORD1_MOUNTED_ON_FILEID;
         /* Switch to mounted_on_fileid if the server supports it */
         if (readdir->bitmask[1] & FATTR4_WORD1_MOUNTED_ON_FILEID)
                 attrs[0] &= ~FATTR4_WORD0_FILEID;
         else
                 attrs[1] &= ~FATTR4_WORD1_MOUNTED_ON_FILEID;
-        WRITE32(attrs[0] & readdir->bitmask[0]);
-        WRITE32(attrs[1] & readdir->bitmask[1]);
+
+        p = reserve_space(xdr, 12+NFS4_VERIFIER_SIZE+20);
+        *p++ = cpu_to_be32(OP_READDIR);
+        p = xdr_encode_hyper(p, readdir->cookie);
+        p = xdr_encode_opaque_fixed(p, readdir->verifier.data, NFS4_VERIFIER_SIZE);
+        *p++ = cpu_to_be32(dircount);
+        *p++ = cpu_to_be32(readdir->count);
+        *p++ = cpu_to_be32(2);
+
+        *p++ = cpu_to_be32(attrs[0] & readdir->bitmask[0]);
+        *p = cpu_to_be32(attrs[1] & readdir->bitmask[1]);
         hdr->nops++;
         hdr->replen += decode_readdir_maxsz;
         dprintk("%s: cookie = %Lu, verifier = %08x:%08x, bitmap = %08x:%08x\n",
@@ -1378,8 +1461,8 @@ static void encode_readlink(struct xdr_stream *xdr, const struct nfs4_readlink *
 {
         __be32 *p;
 
-        RESERVE_SPACE(4);
-        WRITE32(OP_READLINK);
+        p = reserve_space(xdr, 4);
+        *p = cpu_to_be32(OP_READLINK);
         hdr->nops++;
         hdr->replen += decode_readlink_maxsz;
 }
@@ -1388,10 +1471,9 @@ static void encode_remove(struct xdr_stream *xdr, const struct qstr *name, struc
 {
         __be32 *p;
 
-        RESERVE_SPACE(8 + name->len);
-        WRITE32(OP_REMOVE);
-        WRITE32(name->len);
-        WRITEMEM(name->name, name->len);
+        p = reserve_space(xdr, 8 + name->len);
+        *p++ = cpu_to_be32(OP_REMOVE);
+        xdr_encode_opaque(p, name->name, name->len);
         hdr->nops++;
         hdr->replen += decode_remove_maxsz;
 }
@@ -1400,14 +1482,10 @@ static void encode_rename(struct xdr_stream *xdr, const struct qstr *oldname, co
 {
         __be32 *p;
 
-        RESERVE_SPACE(8 + oldname->len);
-        WRITE32(OP_RENAME);
-        WRITE32(oldname->len);
-        WRITEMEM(oldname->name, oldname->len);
-
-        RESERVE_SPACE(4 + newname->len);
-        WRITE32(newname->len);
-        WRITEMEM(newname->name, newname->len);
+        p = reserve_space(xdr, 4);
+        *p = cpu_to_be32(OP_RENAME);
+        encode_string(xdr, oldname->len, oldname->name);
+        encode_string(xdr, newname->len, newname->name);
         hdr->nops++;
         hdr->replen += decode_rename_maxsz;
 }
@@ -1416,9 +1494,9 @@ static void encode_renew(struct xdr_stream *xdr, const struct nfs_client *client
 {
         __be32 *p;
 
-        RESERVE_SPACE(12);
-        WRITE32(OP_RENEW);
-        WRITE64(client_stateid->cl_clientid);
+        p = reserve_space(xdr, 12);
+        *p++ = cpu_to_be32(OP_RENEW);
+        xdr_encode_hyper(p, client_stateid->cl_clientid);
         hdr->nops++;
         hdr->replen += decode_renew_maxsz;
 }
@@ -1428,31 +1506,29 @@ encode_restorefh(struct xdr_stream *xdr, struct compound_hdr *hdr)
 {
         __be32 *p;
 
-        RESERVE_SPACE(4);
-        WRITE32(OP_RESTOREFH);
+        p = reserve_space(xdr, 4);
+        *p = cpu_to_be32(OP_RESTOREFH);
         hdr->nops++;
         hdr->replen += decode_restorefh_maxsz;
 }
 
-static int
+static void
 encode_setacl(struct xdr_stream *xdr, struct nfs_setaclargs *arg, struct compound_hdr *hdr)
 {
         __be32 *p;
 
-        RESERVE_SPACE(4+NFS4_STATEID_SIZE);
-        WRITE32(OP_SETATTR);
-        WRITEMEM(zero_stateid.data, NFS4_STATEID_SIZE);
-        RESERVE_SPACE(2*4);
-        WRITE32(1);
-        WRITE32(FATTR4_WORD0_ACL);
-        if (arg->acl_len % 4)
-                return -EINVAL;
-        RESERVE_SPACE(4);
-        WRITE32(arg->acl_len);
+        p = reserve_space(xdr, 4+NFS4_STATEID_SIZE);
+        *p++ = cpu_to_be32(OP_SETATTR);
+        xdr_encode_opaque_fixed(p, zero_stateid.data, NFS4_STATEID_SIZE);
+        p = reserve_space(xdr, 2*4);
+        *p++ = cpu_to_be32(1);
+        *p = cpu_to_be32(FATTR4_WORD0_ACL);
+        BUG_ON(arg->acl_len % 4);
+        p = reserve_space(xdr, 4);
+        *p = cpu_to_be32(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;
 }
 
 static void
@@ -1460,8 +1536,8 @@ encode_savefh(struct xdr_stream *xdr, struct compound_hdr *hdr)
 {
         __be32 *p;
 
-        RESERVE_SPACE(4);
-        WRITE32(OP_SAVEFH);
+        p = reserve_space(xdr, 4);
+        *p = cpu_to_be32(OP_SAVEFH);
         hdr->nops++;
         hdr->replen += decode_savefh_maxsz;
 }
@@ -1470,9 +1546,9 @@ static void encode_setattr(struct xdr_stream *xdr, const struct nfs_setattrargs
 {
         __be32 *p;
 
-        RESERVE_SPACE(4+NFS4_STATEID_SIZE);
-        WRITE32(OP_SETATTR);
-        WRITEMEM(arg->stateid.data, NFS4_STATEID_SIZE);
+        p = reserve_space(xdr, 4+NFS4_STATEID_SIZE);
+        *p++ = cpu_to_be32(OP_SETATTR);
+        xdr_encode_opaque_fixed(p, arg->stateid.data, NFS4_STATEID_SIZE);
         hdr->nops++;
         hdr->replen += decode_setattr_maxsz;
         encode_attrs(xdr, arg->iap, server);
@@ -1482,29 +1558,29 @@ static void encode_setclientid(struct xdr_stream *xdr, const struct nfs4_setclie
 {
         __be32 *p;
 
-        RESERVE_SPACE(4 + NFS4_VERIFIER_SIZE);
-        WRITE32(OP_SETCLIENTID);
-        WRITEMEM(setclientid->sc_verifier->data, NFS4_VERIFIER_SIZE);
+        p = reserve_space(xdr, 4 + NFS4_VERIFIER_SIZE);
+        *p++ = cpu_to_be32(OP_SETCLIENTID);
+        xdr_encode_opaque_fixed(p, setclientid->sc_verifier->data, NFS4_VERIFIER_SIZE);
 
         encode_string(xdr, setclientid->sc_name_len, setclientid->sc_name);
-        RESERVE_SPACE(4);
-        WRITE32(setclientid->sc_prog);
+        p = reserve_space(xdr, 4);
+        *p = cpu_to_be32(setclientid->sc_prog);
         encode_string(xdr, setclientid->sc_netid_len, setclientid->sc_netid);
         encode_string(xdr, setclientid->sc_uaddr_len, setclientid->sc_uaddr);
-        RESERVE_SPACE(4);
-        WRITE32(setclientid->sc_cb_ident);
+        p = reserve_space(xdr, 4);
+        *p = cpu_to_be32(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)
+static void encode_setclientid_confirm(struct xdr_stream *xdr, const struct nfs4_setclientid_res *arg, struct compound_hdr *hdr)
 {
         __be32 *p;
 
-        RESERVE_SPACE(12 + NFS4_VERIFIER_SIZE);
-        WRITE32(OP_SETCLIENTID_CONFIRM);
-        WRITE64(client_state->cl_clientid);
-        WRITEMEM(client_state->cl_confirm.data, NFS4_VERIFIER_SIZE);
+        p = reserve_space(xdr, 12 + NFS4_VERIFIER_SIZE);
+        *p++ = cpu_to_be32(OP_SETCLIENTID_CONFIRM);
+        p = xdr_encode_hyper(p, arg->clientid);
+        xdr_encode_opaque_fixed(p, arg->confirm.data, NFS4_VERIFIER_SIZE);
         hdr->nops++;
         hdr->replen += decode_setclientid_confirm_maxsz;
 }
@@ -1513,15 +1589,15 @@ static void encode_write(struct xdr_stream *xdr, const struct nfs_writeargs *arg
 {
         __be32 *p;
 
-        RESERVE_SPACE(4);
-        WRITE32(OP_WRITE);
+        p = reserve_space(xdr, 4);
+        *p = cpu_to_be32(OP_WRITE);
 
-        encode_stateid(xdr, args->context);
+        encode_stateid(xdr, args->context, args->lock_context);
 
-        RESERVE_SPACE(16);
-        WRITE64(args->offset);
-        WRITE32(args->stable);
-        WRITE32(args->count);
+        p = reserve_space(xdr, 16);
+        p = xdr_encode_hyper(p, args->offset);
+        *p++ = cpu_to_be32(args->stable);
+        *p = cpu_to_be32(args->count);
 
         xdr_write_pages(xdr, args->pages, args->pgbase, args->count);
         hdr->nops++;
@@ -1532,10 +1608,10 @@ static void encode_delegreturn(struct xdr_stream *xdr, const nfs4_stateid *state
 {
         __be32 *p;
 
-        RESERVE_SPACE(4+NFS4_STATEID_SIZE);
+        p = reserve_space(xdr, 4+NFS4_STATEID_SIZE);
 
-        WRITE32(OP_DELEGRETURN);
-        WRITEMEM(stateid->data, NFS4_STATEID_SIZE);
+        *p++ = cpu_to_be32(OP_DELEGRETURN);
+        xdr_encode_opaque_fixed(p, stateid->data, NFS4_STATEID_SIZE);
         hdr->nops++;
         hdr->replen += decode_delegreturn_maxsz;
 }
@@ -1548,16 +1624,16 @@ static void encode_exchange_id(struct xdr_stream *xdr,
 {
         __be32 *p;
 
-        RESERVE_SPACE(4 + sizeof(args->verifier->data));
-        WRITE32(OP_EXCHANGE_ID);
-        WRITEMEM(args->verifier->data, sizeof(args->verifier->data));
+        p = reserve_space(xdr, 4 + sizeof(args->verifier->data));
+        *p++ = cpu_to_be32(OP_EXCHANGE_ID);
+        xdr_encode_opaque_fixed(p, 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 */
+        p = reserve_space(xdr, 12);
+        *p++ = cpu_to_be32(args->flags);
+        *p++ = cpu_to_be32(0);  /* zero length state_protect4_a */
+        *p = cpu_to_be32(0);    /* zero length implementation id array */
         hdr->nops++;
         hdr->replen += decode_exchange_id_maxsz;
 }
@@ -1570,56 +1646,52 @@ static void encode_create_session(struct xdr_stream *xdr,
         char machine_name[NFS4_MAX_MACHINE_NAME_LEN];
         uint32_t len;
         struct nfs_client *clp = args->client;
+        u32 max_resp_sz_cached;
 
-        RESERVE_SPACE(4);
-        WRITE32(OP_CREATE_SESSION);
+        /*
+         * Assumes OPEN is the biggest non-idempotent compound.
+         * 2 is the verifier.
+         */
+        max_resp_sz_cached = (NFS4_dec_open_sz + RPC_REPHDRSIZE +
+                              RPC_MAX_AUTH_SIZE + 2) * XDR_UNIT;
 
-        RESERVE_SPACE(8);
-        WRITE64(clp->cl_ex_clid);
+        len = scnprintf(machine_name, sizeof(machine_name), "%s",
+                        clp->cl_ipaddr);
 
-        RESERVE_SPACE(8);
-        WRITE32(clp->cl_seqid);                 /*Sequence id */
-        WRITE32(args->flags);                   /*flags */
+        p = reserve_space(xdr, 20 + 2*28 + 20 + len + 12);
+        *p++ = cpu_to_be32(OP_CREATE_SESSION);
+        p = xdr_encode_hyper(p, clp->cl_ex_clid);
+        *p++ = cpu_to_be32(clp->cl_seqid);                      /*Sequence id */
+        *p++ = cpu_to_be32(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 */
+        *p++ = cpu_to_be32(args->fc_attrs.headerpadsz); /* header padding size */
+        *p++ = cpu_to_be32(args->fc_attrs.max_rqst_sz); /* max req size */
+        *p++ = cpu_to_be32(args->fc_attrs.max_resp_sz); /* max resp size */
+        *p++ = cpu_to_be32(max_resp_sz_cached);         /* Max resp sz cached */
+        *p++ = cpu_to_be32(args->fc_attrs.max_ops);     /* max operations */
+        *p++ = cpu_to_be32(args->fc_attrs.max_reqs);    /* max requests */
+        *p++ = cpu_to_be32(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 */
+        *p++ = cpu_to_be32(args->fc_attrs.headerpadsz); /* header padding size */
+        *p++ = cpu_to_be32(args->bc_attrs.max_rqst_sz); /* max req size */
+        *p++ = cpu_to_be32(args->bc_attrs.max_resp_sz); /* max resp size */
+        *p++ = cpu_to_be32(args->bc_attrs.max_resp_sz_cached);  /* Max resp sz cached */
+        *p++ = cpu_to_be32(args->bc_attrs.max_ops);     /* max operations */
+        *p++ = cpu_to_be32(args->bc_attrs.max_reqs);    /* max requests */
+        *p++ = cpu_to_be32(0);                          /* rdmachannel_attrs */
+
+        *p++ = cpu_to_be32(args->cb_program);           /* cb_program */
+        *p++ = cpu_to_be32(1);
+        *p++ = cpu_to_be32(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 */
+        *p++ = cpu_to_be32((u32)clp->cl_boot_time.tv_nsec);     /* stamp */
+        p = xdr_encode_opaque(p, machine_name, len);
+        *p++ = cpu_to_be32(0);                          /* UID */
+        *p++ = cpu_to_be32(0);                          /* GID */
+        *p = cpu_to_be32(0);                            /* No more gids */
         hdr->nops++;
         hdr->replen += decode_create_session_maxsz;
 }
@@ -1629,12 +1701,25 @@ static void encode_destroy_session(struct xdr_stream *xdr,
                                    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);
+        p = reserve_space(xdr, 4 + NFS4_MAX_SESSIONID_LEN);
+        *p++ = cpu_to_be32(OP_DESTROY_SESSION);
+        xdr_encode_opaque_fixed(p, session->sess_id.data, NFS4_MAX_SESSIONID_LEN);
         hdr->nops++;
         hdr->replen += decode_destroy_session_maxsz;
 }
+
+static void encode_reclaim_complete(struct xdr_stream *xdr,
+                                    struct nfs41_reclaim_complete_args *args,
+                                    struct compound_hdr *hdr)
+{
+        __be32 *p;
+
+        p = reserve_space(xdr, 8);
+        *p++ = cpu_to_be32(OP_RECLAIM_COMPLETE);
+        *p++ = cpu_to_be32(args->one_fs);
+        hdr->nops++;
+        hdr->replen += decode_reclaim_complete_maxsz;
+}
 #endif /* CONFIG_NFS_V4_1 */
 
 static void encode_sequence(struct xdr_stream *xdr,
@@ -1655,8 +1740,8 @@ static void encode_sequence(struct xdr_stream *xdr,
         WARN_ON(args->sa_slotid == NFS4_MAX_SLOT_TABLE);
         slot = tp->slots + args->sa_slotid;
 
-        RESERVE_SPACE(4);
-        WRITE32(OP_SEQUENCE);
+        p = reserve_space(xdr, 4 + NFS4_MAX_SESSIONID_LEN + 16);
+        *p++ = cpu_to_be32(OP_SEQUENCE);
 
         /*
          * Sessionid + seqid + slotid + max slotid + cache_this
@@ -1670,17 +1755,65 @@ static void encode_sequence(struct xdr_stream *xdr,
                 ((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);
+        p = xdr_encode_opaque_fixed(p, session->sess_id.data, NFS4_MAX_SESSIONID_LEN);
+        *p++ = cpu_to_be32(slot->seq_nr);
+        *p++ = cpu_to_be32(args->sa_slotid);
+        *p++ = cpu_to_be32(tp->highest_used_slotid);
+        *p = cpu_to_be32(args->sa_cache_this);
         hdr->nops++;
         hdr->replen += decode_sequence_maxsz;
 #endif /* CONFIG_NFS_V4_1 */
 }
 
+#ifdef CONFIG_NFS_V4_1
+static void
+encode_getdeviceinfo(struct xdr_stream *xdr,
+                     const struct nfs4_getdeviceinfo_args *args,
+                     struct compound_hdr *hdr)
+{
+        __be32 *p;
+
+        p = reserve_space(xdr, 16 + NFS4_DEVICEID4_SIZE);
+        *p++ = cpu_to_be32(OP_GETDEVICEINFO);
+        p = xdr_encode_opaque_fixed(p, args->pdev->dev_id.data,
+                                    NFS4_DEVICEID4_SIZE);
+        *p++ = cpu_to_be32(args->pdev->layout_type);
+        *p++ = cpu_to_be32(args->pdev->pglen);          /* gdia_maxcount */
+        *p++ = cpu_to_be32(0);                          /* bitmap length 0 */
+        hdr->nops++;
+        hdr->replen += decode_getdeviceinfo_maxsz;
+}
+
+static void
+encode_layoutget(struct xdr_stream *xdr,
+                      const struct nfs4_layoutget_args *args,
+                      struct compound_hdr *hdr)
+{
+        __be32 *p;
+
+        p = reserve_space(xdr, 44 + NFS4_STATEID_SIZE);
+        *p++ = cpu_to_be32(OP_LAYOUTGET);
+        *p++ = cpu_to_be32(0);     /* Signal layout available */
+        *p++ = cpu_to_be32(args->type);
+        *p++ = cpu_to_be32(args->range.iomode);
+        p = xdr_encode_hyper(p, args->range.offset);
+        p = xdr_encode_hyper(p, args->range.length);
+        p = xdr_encode_hyper(p, args->minlength);
+        p = xdr_encode_opaque_fixed(p, &args->stateid.data, NFS4_STATEID_SIZE);
+        *p = cpu_to_be32(args->maxcount);
+
+        dprintk("%s: 1st type:0x%x iomode:%d off:%lu len:%lu mc:%d\n",
+                __func__,
+                args->type,
+                args->range.iomode,
+                (unsigned long)args->range.offset,
+                (unsigned long)args->range.length,
+                args->maxcount);
+        hdr->nops++;
+        hdr->replen += decode_layoutget_maxsz;
+}
+#endif /* CONFIG_NFS_V4_1 */
+
 /*
  * END OF "GENERIC" ENCODE ROUTINES.
  */
@@ -1689,7 +1822,7 @@ 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;
+                return args->sa_session->clp->cl_mvops->minor_version;
 #endif /* CONFIG_NFS_V4_1 */
         return 0;
 }
@@ -1697,379 +1830,362 @@ static u32 nfs4_xdr_minorversion(const struct nfs4_sequence_args *args)
 /*
  * Encode an ACCESS request
  */
-static int nfs4_xdr_enc_access(struct rpc_rqst *req, __be32 *p, const struct nfs4_accessargs *args)
+static void nfs4_xdr_enc_access(struct rpc_rqst *req, struct xdr_stream *xdr,
+                                const struct nfs4_accessargs *args)
 {
-        struct xdr_stream xdr;
         struct compound_hdr hdr = {
                 .minorversion = nfs4_xdr_minorversion(&args->seq_args),
         };
 
-        xdr_init_encode(&xdr, &req->rq_snd_buf, p);
-        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);
+        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);
         encode_nops(&hdr);
-        return 0;
 }
 
 /*
  * Encode LOOKUP request
  */
-static int nfs4_xdr_enc_lookup(struct rpc_rqst *req, __be32 *p, const struct nfs4_lookup_arg *args)
+static void nfs4_xdr_enc_lookup(struct rpc_rqst *req, struct xdr_stream *xdr,
+                                const struct nfs4_lookup_arg *args)
 {
-        struct xdr_stream xdr;
         struct compound_hdr hdr = {
                 .minorversion = nfs4_xdr_minorversion(&args->seq_args),
         };
 
-        xdr_init_encode(&xdr, &req->rq_snd_buf, p);
-        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);
-        encode_getfattr(&xdr, args->bitmask, &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);
+        encode_getfattr(xdr, args->bitmask, &hdr);
         encode_nops(&hdr);
-        return 0;
 }
 
 /*
  * Encode LOOKUP_ROOT request
  */
-static int nfs4_xdr_enc_lookup_root(struct rpc_rqst *req, __be32 *p, const struct nfs4_lookup_root_arg *args)
+static void nfs4_xdr_enc_lookup_root(struct rpc_rqst *req,
+                                     struct xdr_stream *xdr,
+                                     const struct nfs4_lookup_root_arg *args)
 {
-        struct xdr_stream xdr;
         struct compound_hdr hdr = {
                 .minorversion = nfs4_xdr_minorversion(&args->seq_args),
         };
 
-        xdr_init_encode(&xdr, &req->rq_snd_buf, p);
-        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);
+        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);
         encode_nops(&hdr);
-        return 0;
 }
 
 /*
  * Encode REMOVE request
  */
-static int nfs4_xdr_enc_remove(struct rpc_rqst *req, __be32 *p, const struct nfs_removeargs *args)
+static void nfs4_xdr_enc_remove(struct rpc_rqst *req, struct xdr_stream *xdr,
+                                const struct nfs_removeargs *args)
 {
-        struct xdr_stream xdr;
         struct compound_hdr hdr = {
                 .minorversion = nfs4_xdr_minorversion(&args->seq_args),
         };
 
-        xdr_init_encode(&xdr, &req->rq_snd_buf, p);
-        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);
+        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);
         encode_nops(&hdr);
-        return 0;
 }
 
 /*
  * Encode RENAME request
  */
-static int nfs4_xdr_enc_rename(struct rpc_rqst *req, __be32 *p, const struct nfs4_rename_arg *args)
+static void nfs4_xdr_enc_rename(struct rpc_rqst *req, struct xdr_stream *xdr,
+                                const struct nfs_renameargs *args)
 {
-        struct xdr_stream xdr;
         struct compound_hdr hdr = {
                 .minorversion = nfs4_xdr_minorversion(&args->seq_args),
         };
 
-        xdr_init_encode(&xdr, &req->rq_snd_buf, p);
-        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);
-        encode_rename(&xdr, args->old_name, args->new_name, &hdr);
-        encode_getfattr(&xdr, args->bitmask, &hdr);
-        encode_restorefh(&xdr, &hdr);
-        encode_getfattr(&xdr, args->bitmask, &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);
+        encode_rename(xdr, args->old_name, args->new_name, &hdr);
+        encode_getfattr(xdr, args->bitmask, &hdr);
+        encode_restorefh(xdr, &hdr);
+        encode_getfattr(xdr, args->bitmask, &hdr);
         encode_nops(&hdr);
-        return 0;
 }
 
 /*
  * Encode LINK request
  */
-static int nfs4_xdr_enc_link(struct rpc_rqst *req, __be32 *p, const struct nfs4_link_arg *args)
+static void nfs4_xdr_enc_link(struct rpc_rqst *req, struct xdr_stream *xdr,
+                             const struct nfs4_link_arg *args)
 {
-        struct xdr_stream xdr;
         struct compound_hdr hdr = {
                 .minorversion = nfs4_xdr_minorversion(&args->seq_args),
         };
 
-        xdr_init_encode(&xdr, &req->rq_snd_buf, p);
-        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);
-        encode_link(&xdr, args->name, &hdr);
-        encode_getfattr(&xdr, args->bitmask, &hdr);
-        encode_restorefh(&xdr, &hdr);
-        encode_getfattr(&xdr, args->bitmask, &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);
+        encode_link(xdr, args->name, &hdr);
+        encode_getfattr(xdr, args->bitmask, &hdr);
+        encode_restorefh(xdr, &hdr);
+        encode_getfattr(xdr, args->bitmask, &hdr);
         encode_nops(&hdr);
-        return 0;
 }
 
 /*
  * Encode CREATE request
  */
-static int nfs4_xdr_enc_create(struct rpc_rqst *req, __be32 *p, const struct nfs4_create_arg *args)
+static void nfs4_xdr_enc_create(struct rpc_rqst *req, struct xdr_stream *xdr,
+                                const struct nfs4_create_arg *args)
 {
-        struct xdr_stream xdr;
         struct compound_hdr hdr = {
                 .minorversion = nfs4_xdr_minorversion(&args->seq_args),
         };
 
-        xdr_init_encode(&xdr, &req->rq_snd_buf, p);
-        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);
-        encode_getfh(&xdr, &hdr);
-        encode_getfattr(&xdr, args->bitmask, &hdr);
-        encode_restorefh(&xdr, &hdr);
-        encode_getfattr(&xdr, args->bitmask, &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);
+        encode_getfh(xdr, &hdr);
+        encode_getfattr(xdr, args->bitmask, &hdr);
+        encode_restorefh(xdr, &hdr);
+        encode_getfattr(xdr, args->bitmask, &hdr);
         encode_nops(&hdr);
-        return 0;
 }
 
 /*
  * Encode SYMLINK request
  */
-static int nfs4_xdr_enc_symlink(struct rpc_rqst *req, __be32 *p, const struct nfs4_create_arg *args)
+static void nfs4_xdr_enc_symlink(struct rpc_rqst *req, struct xdr_stream *xdr,
+                                 const struct nfs4_create_arg *args)
 {
-        return nfs4_xdr_enc_create(req, p, args);
+        nfs4_xdr_enc_create(req, xdr, args);
 }
 
 /*
  * Encode GETATTR request
  */
-static int nfs4_xdr_enc_getattr(struct rpc_rqst *req, __be32 *p, const struct nfs4_getattr_arg *args)
+static void nfs4_xdr_enc_getattr(struct rpc_rqst *req, struct xdr_stream *xdr,
+                                 const struct nfs4_getattr_arg *args)
 {
-        struct xdr_stream xdr;
         struct compound_hdr hdr = {
                 .minorversion = nfs4_xdr_minorversion(&args->seq_args),
         };
 
-        xdr_init_encode(&xdr, &req->rq_snd_buf, p);
-        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_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);
-        return 0;
 }
 
 /*
  * Encode a CLOSE request
  */
-static int nfs4_xdr_enc_close(struct rpc_rqst *req, __be32 *p, struct nfs_closeargs *args)
+static void nfs4_xdr_enc_close(struct rpc_rqst *req, struct xdr_stream *xdr,
+                               struct nfs_closeargs *args)
 {
-        struct xdr_stream xdr;
         struct compound_hdr hdr = {
                 .minorversion = nfs4_xdr_minorversion(&args->seq_args),
         };
 
-        xdr_init_encode(&xdr, &req->rq_snd_buf, p);
-        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);
+        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);
         encode_nops(&hdr);
-        return 0;
 }
 
 /*
  * Encode an OPEN request
  */
-static int nfs4_xdr_enc_open(struct rpc_rqst *req, __be32 *p, struct nfs_openargs *args)
+static void nfs4_xdr_enc_open(struct rpc_rqst *req, struct xdr_stream *xdr,
+                              struct nfs_openargs *args)
 {
-        struct xdr_stream xdr;
         struct compound_hdr hdr = {
                 .minorversion = nfs4_xdr_minorversion(&args->seq_args),
         };
 
-        xdr_init_encode(&xdr, &req->rq_snd_buf, p);
-        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);
-        encode_getfh(&xdr, &hdr);
-        encode_getfattr(&xdr, args->bitmask, &hdr);
-        encode_restorefh(&xdr, &hdr);
-        encode_getfattr(&xdr, args->bitmask, &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);
+        encode_getfh(xdr, &hdr);
+        encode_getfattr(xdr, args->bitmask, &hdr);
+        encode_restorefh(xdr, &hdr);
+        encode_getfattr(xdr, args->bitmask, &hdr);
         encode_nops(&hdr);
-        return 0;
 }
 
 /*
  * Encode an OPEN_CONFIRM request
  */
-static int nfs4_xdr_enc_open_confirm(struct rpc_rqst *req, __be32 *p, struct nfs_open_confirmargs *args)
+static void nfs4_xdr_enc_open_confirm(struct rpc_rqst *req,
+                                      struct xdr_stream *xdr,
+                                      struct nfs_open_confirmargs *args)
 {
-        struct xdr_stream xdr;
         struct compound_hdr hdr = {
                 .nops   = 0,
         };
 
-        xdr_init_encode(&xdr, &req->rq_snd_buf, p);
-        encode_compound_hdr(&xdr, req, &hdr);
-        encode_putfh(&xdr, args->fh, &hdr);
-        encode_open_confirm(&xdr, args, &hdr);
+        encode_compound_hdr(xdr, req, &hdr);
+        encode_putfh(xdr, args->fh, &hdr);
+        encode_open_confirm(xdr, args, &hdr);
         encode_nops(&hdr);
-        return 0;
 }
 
 /*
  * Encode an OPEN request with no attributes.
  */
-static int nfs4_xdr_enc_open_noattr(struct rpc_rqst *req, __be32 *p, struct nfs_openargs *args)
+static void nfs4_xdr_enc_open_noattr(struct rpc_rqst *req,
+                                     struct xdr_stream *xdr,
+                                     struct nfs_openargs *args)
 {
-        struct xdr_stream xdr;
         struct compound_hdr hdr = {
                 .minorversion = nfs4_xdr_minorversion(&args->seq_args),
         };
 
-        xdr_init_encode(&xdr, &req->rq_snd_buf, p);
-        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);
+        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);
         encode_nops(&hdr);
-        return 0;
 }
 
 /*
  * Encode an OPEN_DOWNGRADE request
  */
-static int nfs4_xdr_enc_open_downgrade(struct rpc_rqst *req, __be32 *p, struct nfs_closeargs *args)
+static void nfs4_xdr_enc_open_downgrade(struct rpc_rqst *req,
+                                        struct xdr_stream *xdr,
+                                        struct nfs_closeargs *args)
 {
-        struct xdr_stream xdr;
         struct compound_hdr hdr = {
                 .minorversion = nfs4_xdr_minorversion(&args->seq_args),
         };
 
-        xdr_init_encode(&xdr, &req->rq_snd_buf, p);
-        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);
+        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);
         encode_nops(&hdr);
-        return 0;
 }
 
 /*
  * Encode a LOCK request
  */
-static int nfs4_xdr_enc_lock(struct rpc_rqst *req, __be32 *p, struct nfs_lock_args *args)
+static void nfs4_xdr_enc_lock(struct rpc_rqst *req, struct xdr_stream *xdr,
+                              struct nfs_lock_args *args)
 {
-        struct xdr_stream xdr;
         struct compound_hdr hdr = {
                 .minorversion = nfs4_xdr_minorversion(&args->seq_args),
         };
 
-        xdr_init_encode(&xdr, &req->rq_snd_buf, p);
-        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_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);
-        return 0;
 }
 
 /*
  * Encode a LOCKT request
  */
-static int nfs4_xdr_enc_lockt(struct rpc_rqst *req, __be32 *p, struct nfs_lockt_args *args)
+static void nfs4_xdr_enc_lockt(struct rpc_rqst *req, struct xdr_stream *xdr,
+                               struct nfs_lockt_args *args)
 {
-        struct xdr_stream xdr;
         struct compound_hdr hdr = {
                 .minorversion = nfs4_xdr_minorversion(&args->seq_args),
         };
 
-        xdr_init_encode(&xdr, &req->rq_snd_buf, p);
-        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_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);
-        return 0;
 }
 
 /*
  * Encode a LOCKU request
  */
-static int nfs4_xdr_enc_locku(struct rpc_rqst *req, __be32 *p, struct nfs_locku_args *args)
+static void nfs4_xdr_enc_locku(struct rpc_rqst *req, struct xdr_stream *xdr,
+                               struct nfs_locku_args *args)
 {
-        struct xdr_stream xdr;
         struct compound_hdr hdr = {
                 .minorversion = nfs4_xdr_minorversion(&args->seq_args),
         };
 
-        xdr_init_encode(&xdr, &req->rq_snd_buf, p);
-        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_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);
+}
+
+static void nfs4_xdr_enc_release_lockowner(struct rpc_rqst *req,
+                                           struct xdr_stream *xdr,
+                                        struct nfs_release_lockowner_args *args)
+{
+        struct compound_hdr hdr = {
+                .minorversion = 0,
+        };
+
+        encode_compound_hdr(xdr, req, &hdr);
+        encode_release_lockowner(xdr, &args->lock_owner, &hdr);
         encode_nops(&hdr);
-        return 0;
 }
 
 /*
  * Encode a READLINK request
  */
-static int nfs4_xdr_enc_readlink(struct rpc_rqst *req, __be32 *p, const struct nfs4_readlink *args)
+static void nfs4_xdr_enc_readlink(struct rpc_rqst *req, struct xdr_stream *xdr,
+                                  const struct nfs4_readlink *args)
 {
-        struct xdr_stream xdr;
         struct compound_hdr hdr = {
                 .minorversion = nfs4_xdr_minorversion(&args->seq_args),
         };
 
-        xdr_init_encode(&xdr, &req->rq_snd_buf, p);
-        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);
+        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);
 
         xdr_inline_pages(&req->rq_rcv_buf, hdr.replen << 2, args->pages,
                         args->pgbase, args->pglen);
         encode_nops(&hdr);
-        return 0;
 }
 
 /*
  * Encode a READDIR request
  */
-static int nfs4_xdr_enc_readdir(struct rpc_rqst *req, __be32 *p, const struct nfs4_readdir_arg *args)
+static void nfs4_xdr_enc_readdir(struct rpc_rqst *req, struct xdr_stream *xdr,
+                                 const struct nfs4_readdir_arg *args)
 {
-        struct xdr_stream xdr;
         struct compound_hdr hdr = {
                 .minorversion = nfs4_xdr_minorversion(&args->seq_args),
         };
 
-        xdr_init_encode(&xdr, &req->rq_snd_buf, p);
-        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);
+        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);
 
         xdr_inline_pages(&req->rq_rcv_buf, hdr.replen << 2, args->pages,
                          args->pgbase, args->count);
@@ -2077,457 +2193,463 @@ static int nfs4_xdr_enc_readdir(struct rpc_rqst *req, __be32 *p, const struct nf
                         __func__, hdr.replen << 2, args->pages,
                         args->pgbase, args->count);
         encode_nops(&hdr);
-        return 0;
 }
 
 /*
  * Encode a READ request
  */
-static int nfs4_xdr_enc_read(struct rpc_rqst *req, __be32 *p, struct nfs_readargs *args)
+static void nfs4_xdr_enc_read(struct rpc_rqst *req, struct xdr_stream *xdr,
+                              struct nfs_readargs *args)
 {
-        struct xdr_stream xdr;
         struct compound_hdr hdr = {
                 .minorversion = nfs4_xdr_minorversion(&args->seq_args),
         };
 
-        xdr_init_encode(&xdr, &req->rq_snd_buf, p);
-        encode_compound_hdr(&xdr, req, &hdr);
-        encode_sequence(&xdr, &args->seq_args, &hdr);
-        encode_putfh(&xdr, args->fh, &hdr);
-        encode_read(&xdr, args, &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);
 
         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);
-        return 0;
 }
 
 /*
  * Encode an SETATTR request
  */
-static int nfs4_xdr_enc_setattr(struct rpc_rqst *req, __be32 *p, struct nfs_setattrargs *args)
+static void nfs4_xdr_enc_setattr(struct rpc_rqst *req, struct xdr_stream *xdr,
+                                 struct nfs_setattrargs *args)
 {
-        struct xdr_stream xdr;
         struct compound_hdr hdr = {
                 .minorversion = nfs4_xdr_minorversion(&args->seq_args),
         };
 
-        xdr_init_encode(&xdr, &req->rq_snd_buf, p);
-        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);
+        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);
         encode_nops(&hdr);
-        return 0;
 }
 
 /*
  * Encode a GETACL request
  */
-static int
-nfs4_xdr_enc_getacl(struct rpc_rqst *req, __be32 *p,
-                struct nfs_getaclargs *args)
+static void nfs4_xdr_enc_getacl(struct rpc_rqst *req, struct xdr_stream *xdr,
+                                struct nfs_getaclargs *args)
 {
-        struct xdr_stream xdr;
         struct compound_hdr hdr = {
                 .minorversion = nfs4_xdr_minorversion(&args->seq_args),
         };
         uint32_t replen;
 
-        xdr_init_encode(&xdr, &req->rq_snd_buf, p);
-        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);
+        encode_compound_hdr(xdr, req, &hdr);
+        encode_sequence(xdr, &args->seq_args, &hdr);
+        encode_putfh(xdr, args->fh, &hdr);
+        replen = hdr.replen + op_decode_hdr_maxsz + nfs4_fattr_bitmap_maxsz + 1;
+        encode_getattr_two(xdr, FATTR4_WORD0_ACL, 0, &hdr);
 
         xdr_inline_pages(&req->rq_rcv_buf, replen << 2,
                 args->acl_pages, args->acl_pgbase, args->acl_len);
         encode_nops(&hdr);
-        return 0;
 }
 
 /*
  * Encode a WRITE request
  */
-static int nfs4_xdr_enc_write(struct rpc_rqst *req, __be32 *p, struct nfs_writeargs *args)
+static void nfs4_xdr_enc_write(struct rpc_rqst *req, struct xdr_stream *xdr,
+                               struct nfs_writeargs *args)
 {
-        struct xdr_stream xdr;
         struct compound_hdr hdr = {
                 .minorversion = nfs4_xdr_minorversion(&args->seq_args),
         };
 
-        xdr_init_encode(&xdr, &req->rq_snd_buf, p);
-        encode_compound_hdr(&xdr, req, &hdr);
-        encode_sequence(&xdr, &args->seq_args, &hdr);
-        encode_putfh(&xdr, args->fh, &hdr);
-        encode_write(&xdr, args, &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;
-        encode_getfattr(&xdr, args->bitmask, &hdr);
+        encode_getfattr(xdr, args->bitmask, &hdr);
         encode_nops(&hdr);
-        return 0;
 }
 
 /*
  *  a COMMIT request
  */
-static int nfs4_xdr_enc_commit(struct rpc_rqst *req, __be32 *p, struct nfs_writeargs *args)
+static void nfs4_xdr_enc_commit(struct rpc_rqst *req, struct xdr_stream *xdr,
+                                struct nfs_writeargs *args)
 {
-        struct xdr_stream xdr;
         struct compound_hdr hdr = {
                 .minorversion = nfs4_xdr_minorversion(&args->seq_args),
         };
 
-        xdr_init_encode(&xdr, &req->rq_snd_buf, p);
-        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);
+        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);
         encode_nops(&hdr);
-        return 0;
 }
 
 /*
  * FSINFO request
  */
-static int nfs4_xdr_enc_fsinfo(struct rpc_rqst *req, __be32 *p, struct nfs4_fsinfo_arg *args)
+static void nfs4_xdr_enc_fsinfo(struct rpc_rqst *req, struct xdr_stream *xdr,
+                                struct nfs4_fsinfo_arg *args)
 {
-        struct xdr_stream xdr;
         struct compound_hdr hdr = {
                 .minorversion = nfs4_xdr_minorversion(&args->seq_args),
         };
 
-        xdr_init_encode(&xdr, &req->rq_snd_buf, p);
-        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_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);
-        return 0;
 }
 
 /*
  * a PATHCONF request
  */
-static int nfs4_xdr_enc_pathconf(struct rpc_rqst *req, __be32 *p, const struct nfs4_pathconf_arg *args)
+static void nfs4_xdr_enc_pathconf(struct rpc_rqst *req, struct xdr_stream *xdr,
+                                  const struct nfs4_pathconf_arg *args)
 {
-        struct xdr_stream xdr;
         struct compound_hdr hdr = {
                 .minorversion = nfs4_xdr_minorversion(&args->seq_args),
         };
 
-        xdr_init_encode(&xdr, &req->rq_snd_buf, p);
-        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],
+        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);
         encode_nops(&hdr);
-        return 0;
 }
 
 /*
  * a STATFS request
  */
-static int nfs4_xdr_enc_statfs(struct rpc_rqst *req, __be32 *p, const struct nfs4_statfs_arg *args)
+static void nfs4_xdr_enc_statfs(struct rpc_rqst *req, struct xdr_stream *xdr,
+                                const struct nfs4_statfs_arg *args)
 {
-        struct xdr_stream xdr;
         struct compound_hdr hdr = {
                 .minorversion = nfs4_xdr_minorversion(&args->seq_args),
         };
 
-        xdr_init_encode(&xdr, &req->rq_snd_buf, p);
-        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],
+        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);
         encode_nops(&hdr);
-        return 0;
 }
 
 /*
  * GETATTR_BITMAP request
  */
-static int nfs4_xdr_enc_server_caps(struct rpc_rqst *req, __be32 *p,
-                                    struct nfs4_server_caps_arg *args)
+static void nfs4_xdr_enc_server_caps(struct rpc_rqst *req,
+                                     struct xdr_stream *xdr,
+                                     struct nfs4_server_caps_arg *args)
 {
-        struct xdr_stream xdr;
         struct compound_hdr hdr = {
                 .minorversion = nfs4_xdr_minorversion(&args->seq_args),
         };
 
-        xdr_init_encode(&xdr, &req->rq_snd_buf, p);
-        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|
+        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|
                            FATTR4_WORD0_ACLSUPPORT, &hdr);
         encode_nops(&hdr);
-        return 0;
 }
 
 /*
  * a RENEW request
  */
-static int nfs4_xdr_enc_renew(struct rpc_rqst *req, __be32 *p, struct nfs_client *clp)
+static void nfs4_xdr_enc_renew(struct rpc_rqst *req, struct xdr_stream *xdr,
+                               struct nfs_client *clp)
 {
-        struct xdr_stream xdr;
         struct compound_hdr hdr = {
                 .nops   = 0,
         };
 
-        xdr_init_encode(&xdr, &req->rq_snd_buf, p);
-        encode_compound_hdr(&xdr, req, &hdr);
-        encode_renew(&xdr, clp, &hdr);
+        encode_compound_hdr(xdr, req, &hdr);
+        encode_renew(xdr, clp, &hdr);
         encode_nops(&hdr);
-        return 0;
 }
 
 /*
  * a SETCLIENTID request
  */
-static int nfs4_xdr_enc_setclientid(struct rpc_rqst *req, __be32 *p, struct nfs4_setclientid *sc)
+static void nfs4_xdr_enc_setclientid(struct rpc_rqst *req,
+                                     struct xdr_stream *xdr,
+                                     struct nfs4_setclientid *sc)
 {
-        struct xdr_stream xdr;
         struct compound_hdr hdr = {
                 .nops   = 0,
         };
 
-        xdr_init_encode(&xdr, &req->rq_snd_buf, p);
-        encode_compound_hdr(&xdr, req, &hdr);
-        encode_setclientid(&xdr, sc, &hdr);
+        encode_compound_hdr(xdr, req, &hdr);
+        encode_setclientid(xdr, sc, &hdr);
         encode_nops(&hdr);
-        return 0;
 }
 
 /*
  * a SETCLIENTID_CONFIRM request
  */
-static int nfs4_xdr_enc_setclientid_confirm(struct rpc_rqst *req, __be32 *p, struct nfs_client *clp)
+static void nfs4_xdr_enc_setclientid_confirm(struct rpc_rqst *req,
+                                             struct xdr_stream *xdr,
+                                             struct nfs4_setclientid_res *arg)
 {
-        struct xdr_stream xdr;
         struct compound_hdr hdr = {
                 .nops   = 0,
         };
         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_setclientid_confirm(&xdr, clp, &hdr);
-        encode_putrootfh(&xdr, &hdr);
-        encode_fsinfo(&xdr, lease_bitmap, &hdr);
+        encode_compound_hdr(xdr, req, &hdr);
+        encode_setclientid_confirm(xdr, arg, &hdr);
+        encode_putrootfh(xdr, &hdr);
+        encode_fsinfo(xdr, lease_bitmap, &hdr);
         encode_nops(&hdr);
-        return 0;
 }
 
 /*
  * DELEGRETURN request
  */
-static int nfs4_xdr_enc_delegreturn(struct rpc_rqst *req, __be32 *p, const struct nfs4_delegreturnargs *args)
+static void nfs4_xdr_enc_delegreturn(struct rpc_rqst *req,
+                                     struct xdr_stream *xdr,
+                                     const struct nfs4_delegreturnargs *args)
 {
-        struct xdr_stream xdr;
         struct compound_hdr hdr = {
                 .minorversion = nfs4_xdr_minorversion(&args->seq_args),
         };
 
-        xdr_init_encode(&xdr, &req->rq_snd_buf, p);
-        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);
+        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);
         encode_nops(&hdr);
-        return 0;
 }
 
 /*
  * Encode FS_LOCATIONS request
  */
-static int nfs4_xdr_enc_fs_locations(struct rpc_rqst *req, __be32 *p, struct nfs4_fs_locations_arg *args)
+static void nfs4_xdr_enc_fs_locations(struct rpc_rqst *req,
+                                      struct xdr_stream *xdr,
+                                      struct nfs4_fs_locations_arg *args)
 {
-        struct xdr_stream xdr;
         struct compound_hdr hdr = {
                 .minorversion = nfs4_xdr_minorversion(&args->seq_args),
         };
         uint32_t replen;
 
-        xdr_init_encode(&xdr, &req->rq_snd_buf, p);
-        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_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);
+        encode_fs_locations(xdr, args->bitmask, &hdr);
 
         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)
+static void nfs4_xdr_enc_exchange_id(struct rpc_rqst *req,
+                                     struct xdr_stream *xdr,
+                                     struct nfs41_exchange_id_args *args)
 {
-        struct xdr_stream xdr;
         struct compound_hdr hdr = {
-                .minorversion = args->client->cl_minorversion,
+                .minorversion = args->client->cl_mvops->minor_version,
         };
 
-        xdr_init_encode(&xdr, &req->rq_snd_buf, p);
-        encode_compound_hdr(&xdr, req, &hdr);
-        encode_exchange_id(&xdr, args, &hdr);
+        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)
+static void nfs4_xdr_enc_create_session(struct rpc_rqst *req,
+                                        struct xdr_stream *xdr,
+                                        struct nfs41_create_session_args *args)
 {
-        struct xdr_stream xdr;
         struct compound_hdr hdr = {
-                .minorversion = args->client->cl_minorversion,
+                .minorversion = args->client->cl_mvops->minor_version,
         };
 
-        xdr_init_encode(&xdr, &req->rq_snd_buf, p);
-        encode_compound_hdr(&xdr, req, &hdr);
-        encode_create_session(&xdr, args, &hdr);
+        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)
+static void nfs4_xdr_enc_destroy_session(struct rpc_rqst *req,
+                                         struct xdr_stream *xdr,
+                                         struct nfs4_session *session)
 {
-        struct xdr_stream xdr;
         struct compound_hdr hdr = {
-                .minorversion = session->clp->cl_minorversion,
+                .minorversion = session->clp->cl_mvops->minor_version,
         };
 
-        xdr_init_encode(&xdr, &req->rq_snd_buf, p);
-        encode_compound_hdr(&xdr, req, &hdr);
-        encode_destroy_session(&xdr, session, &hdr);
+        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)
+static void nfs4_xdr_enc_sequence(struct rpc_rqst *req, struct xdr_stream *xdr,
+                                  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_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)
+static void nfs4_xdr_enc_get_lease_time(struct rpc_rqst *req,
+                                        struct xdr_stream *xdr,
+                                        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_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"
- * set of XDR encode/decode routines which are intended to be shared by
- * all of our NFSv4 implementations (OpenBSD, MacOS X...).
- *
- * If the pain of reading these is too great, it should be a straightforward
- * task to translate them into Linux-specific versions which are more
- * consistent with the style used in NFSv2/v3...
+ * a RECLAIM_COMPLETE request
+ */
+static void nfs4_xdr_enc_reclaim_complete(struct rpc_rqst *req,
+                                          struct xdr_stream *xdr,
+                                struct nfs41_reclaim_complete_args *args)
+{
+        struct compound_hdr hdr = {
+                .minorversion = nfs4_xdr_minorversion(&args->seq_args)
+        };
+
+        encode_compound_hdr(xdr, req, &hdr);
+        encode_sequence(xdr, &args->seq_args, &hdr);
+        encode_reclaim_complete(xdr, args, &hdr);
+        encode_nops(&hdr);
+}
+
+/*
+ * Encode GETDEVICEINFO request
+ */
+static void nfs4_xdr_enc_getdeviceinfo(struct rpc_rqst *req,
+                                       struct xdr_stream *xdr,
+                                       struct nfs4_getdeviceinfo_args *args)
+{
+        struct compound_hdr hdr = {
+                .minorversion = nfs4_xdr_minorversion(&args->seq_args),
+        };
+
+        encode_compound_hdr(xdr, req, &hdr);
+        encode_sequence(xdr, &args->seq_args, &hdr);
+        encode_getdeviceinfo(xdr, args, &hdr);
+
+        /* set up reply kvec. Subtract notification bitmap max size (2)
+         * so that notification bitmap is put in xdr_buf tail */
+        xdr_inline_pages(&req->rq_rcv_buf, (hdr.replen - 2) << 2,
+                         args->pdev->pages, args->pdev->pgbase,
+                         args->pdev->pglen);
+
+        encode_nops(&hdr);
+}
+
+/*
+ *  Encode LAYOUTGET request
  */
-#define READ32(x)         (x) = ntohl(*p++)
-#define READ64(x)         do {                  \
-        (x) = (u64)ntohl(*p++) << 32;           \
-        (x) |= ntohl(*p++);                     \
-} while (0)
-#define READTIME(x)       do {                  \
-        p++;                                    \
-        (x.tv_sec) = ntohl(*p++);               \
-        (x.tv_nsec) = ntohl(*p++);              \
-} while (0)
-#define COPYMEM(x,nbytes) do {                  \
-        memcpy((x), p, nbytes);                 \
-        p += XDR_QUADLEN(nbytes);               \
-} while (0)
-
-#define READ_BUF(nbytes)  do { \
-        p = xdr_inline_decode(xdr, nbytes); \
-        if (unlikely(!p)) { \
-                dprintk("nfs: %s: prematurely hit end of receive" \
-                                " buffer\n", __func__); \
-                dprintk("nfs: %s: xdr->p=%p, bytes=%u, xdr->end=%p\n", \
-                                __func__, xdr->p, nbytes, xdr->end); \
-                return -EIO; \
-        } \
-} while (0)
+static void nfs4_xdr_enc_layoutget(struct rpc_rqst *req,
+                                   struct xdr_stream *xdr,
+                                   struct nfs4_layoutget_args *args)
+{
+        struct compound_hdr hdr = {
+                .minorversion = nfs4_xdr_minorversion(&args->seq_args),
+        };
+
+        encode_compound_hdr(xdr, req, &hdr);
+        encode_sequence(xdr, &args->seq_args, &hdr);
+        encode_putfh(xdr, NFS_FH(args->inode), &hdr);
+        encode_layoutget(xdr, args, &hdr);
+        encode_nops(&hdr);
+}
+#endif /* CONFIG_NFS_V4_1 */
+
+static void print_overflow_msg(const char *func, const struct xdr_stream *xdr)
+{
+        dprintk("nfs: %s: prematurely hit end of receive buffer. "
+                "Remaining buffer length is %tu words.\n",
+                func, xdr->end - xdr->p);
+}
 
 static int decode_opaque_inline(struct xdr_stream *xdr, unsigned int *len, char **string)
 {
         __be32 *p;
 
-        READ_BUF(4);
-        READ32(*len);
-        READ_BUF(*len);
+        p = xdr_inline_decode(xdr, 4);
+        if (unlikely(!p))
+                goto out_overflow;
+        *len = be32_to_cpup(p);
+        p = xdr_inline_decode(xdr, *len);
+        if (unlikely(!p))
+                goto out_overflow;
         *string = (char *)p;
         return 0;
+out_overflow:
+        print_overflow_msg(__func__, xdr);
+        return -EIO;
 }
 
 static int decode_compound_hdr(struct xdr_stream *xdr, struct compound_hdr *hdr)
 {
         __be32 *p;
 
-        READ_BUF(8);
-        READ32(hdr->status);
-        READ32(hdr->taglen);
+        p = xdr_inline_decode(xdr, 8);
+        if (unlikely(!p))
+                goto out_overflow;
+        hdr->status = be32_to_cpup(p++);
+        hdr->taglen = be32_to_cpup(p);
 
-        READ_BUF(hdr->taglen + 4);
+        p = xdr_inline_decode(xdr, hdr->taglen + 4);
+        if (unlikely(!p))
+                goto out_overflow;
         hdr->tag = (char *)p;
         p += XDR_QUADLEN(hdr->taglen);
-        READ32(hdr->nops);
+        hdr->nops = be32_to_cpup(p);
         if (unlikely(hdr->nops < 1))
                 return nfs4_stat_to_errno(hdr->status);
         return 0;
+out_overflow:
+        print_overflow_msg(__func__, xdr);
+        return -EIO;
 }
 
 static int decode_op_hdr(struct xdr_stream *xdr, enum nfs_opnum4 expected)
@@ -2536,18 +2658,23 @@ static int decode_op_hdr(struct xdr_stream *xdr, enum nfs_opnum4 expected)
         uint32_t opnum;
         int32_t nfserr;
 
-        READ_BUF(8);
-        READ32(opnum);
+        p = xdr_inline_decode(xdr, 8);
+        if (unlikely(!p))
+                goto out_overflow;
+        opnum = be32_to_cpup(p++);
         if (opnum != expected) {
                 dprintk("nfs: Server returned operation"
                         " %d but we issued a request for %d\n",
                                 opnum, expected);
                 return -EIO;
         }
-        READ32(nfserr);
+        nfserr = be32_to_cpup(p);
         if (nfserr != NFS_OK)
                 return nfs4_stat_to_errno(nfserr);
         return 0;
+out_overflow:
+        print_overflow_msg(__func__, xdr);
+        return -EIO;
 }
 
 /* Dummy routine */
@@ -2557,8 +2684,11 @@ static int decode_ace(struct xdr_stream *xdr, void *ace, struct nfs_client *clp)
         unsigned int strlen;
         char *str;
 
-        READ_BUF(12);
-        return decode_opaque_inline(xdr, &strlen, &str);
+        p = xdr_inline_decode(xdr, 12);
+        if (likely(p))
+                return decode_opaque_inline(xdr, &strlen, &str);
+        print_overflow_msg(__func__, xdr);
+        return -EIO;
 }
 
 static int decode_attr_bitmap(struct xdr_stream *xdr, uint32_t *bitmap)
@@ -2566,33 +2696,48 @@ static int decode_attr_bitmap(struct xdr_stream *xdr, uint32_t *bitmap)
         uint32_t bmlen;
         __be32 *p;
 
-        READ_BUF(4);
-        READ32(bmlen);
+        p = xdr_inline_decode(xdr, 4);
+        if (unlikely(!p))
+                goto out_overflow;
+        bmlen = be32_to_cpup(p);
 
         bitmap[0] = bitmap[1] = 0;
-        READ_BUF((bmlen << 2));
+        p = xdr_inline_decode(xdr, (bmlen << 2));
+        if (unlikely(!p))
+                goto out_overflow;
         if (bmlen > 0) {
-                READ32(bitmap[0]);
+                bitmap[0] = be32_to_cpup(p++);
                 if (bmlen > 1)
-                        READ32(bitmap[1]);
+                        bitmap[1] = be32_to_cpup(p);
         }
         return 0;
+out_overflow:
+        print_overflow_msg(__func__, xdr);
+        return -EIO;
 }
 
 static inline int decode_attr_length(struct xdr_stream *xdr, uint32_t *attrlen, __be32 **savep)
 {
         __be32 *p;
 
-        READ_BUF(4);
-        READ32(*attrlen);
+        p = xdr_inline_decode(xdr, 4);
+        if (unlikely(!p))
+                goto out_overflow;
+        *attrlen = be32_to_cpup(p);
         *savep = xdr->p;
         return 0;
+out_overflow:
+        print_overflow_msg(__func__, xdr);
+        return -EIO;
 }
 
 static int decode_attr_supported(struct xdr_stream *xdr, uint32_t *bitmap, uint32_t *bitmask)
 {
         if (likely(bitmap[0] & FATTR4_WORD0_SUPPORTED_ATTRS)) {
-                decode_attr_bitmap(xdr, bitmask);
+                int ret;
+                ret = decode_attr_bitmap(xdr, bitmask);
+                if (unlikely(ret < 0))
+                        return ret;
                 bitmap[0] &= ~FATTR4_WORD0_SUPPORTED_ATTRS;
         } else
                 bitmask[0] = bitmask[1] = 0;
@@ -2609,8 +2754,10 @@ static int decode_attr_type(struct xdr_stream *xdr, uint32_t *bitmap, uint32_t *
         if (unlikely(bitmap[0] & (FATTR4_WORD0_TYPE - 1U)))
                 return -EIO;
         if (likely(bitmap[0] & FATTR4_WORD0_TYPE)) {
-                READ_BUF(4);
-                READ32(*type);
+                p = xdr_inline_decode(xdr, 4);
+                if (unlikely(!p))
+                        goto out_overflow;
+                *type = be32_to_cpup(p);
                 if (*type < NF4REG || *type > NF4NAMEDATTR) {
                         dprintk("%s: bad type %d\n", __func__, *type);
                         return -EIO;
@@ -2620,6 +2767,9 @@ static int decode_attr_type(struct xdr_stream *xdr, uint32_t *bitmap, uint32_t *
         }
         dprintk("%s: type=0%o\n", __func__, nfs_type2fmt[*type]);
         return ret;
+out_overflow:
+        print_overflow_msg(__func__, xdr);
+        return -EIO;
 }
 
 static int decode_attr_change(struct xdr_stream *xdr, uint32_t *bitmap, uint64_t *change)
@@ -2631,14 +2781,19 @@ static int decode_attr_change(struct xdr_stream *xdr, uint32_t *bitmap, uint64_t
         if (unlikely(bitmap[0] & (FATTR4_WORD0_CHANGE - 1U)))
                 return -EIO;
         if (likely(bitmap[0] & FATTR4_WORD0_CHANGE)) {
-                READ_BUF(8);
-                READ64(*change);
+                p = xdr_inline_decode(xdr, 8);
+                if (unlikely(!p))
+                        goto out_overflow;
+                xdr_decode_hyper(p, change);
                 bitmap[0] &= ~FATTR4_WORD0_CHANGE;
                 ret = NFS_ATTR_FATTR_CHANGE;
         }
         dprintk("%s: change attribute=%Lu\n", __func__,
                         (unsigned long long)*change);
         return ret;
+out_overflow:
+        print_overflow_msg(__func__, xdr);
+        return -EIO;
 }
 
 static int decode_attr_size(struct xdr_stream *xdr, uint32_t *bitmap, uint64_t *size)
@@ -2650,13 +2805,18 @@ static int decode_attr_size(struct xdr_stream *xdr, uint32_t *bitmap, uint64_t *
         if (unlikely(bitmap[0] & (FATTR4_WORD0_SIZE - 1U)))
                 return -EIO;
         if (likely(bitmap[0] & FATTR4_WORD0_SIZE)) {
-                READ_BUF(8);
-                READ64(*size);
+                p = xdr_inline_decode(xdr, 8);
+                if (unlikely(!p))
+                        goto out_overflow;
+                xdr_decode_hyper(p, size);
                 bitmap[0] &= ~FATTR4_WORD0_SIZE;
                 ret = NFS_ATTR_FATTR_SIZE;
         }
         dprintk("%s: file size=%Lu\n", __func__, (unsigned long long)*size);
         return ret;
+out_overflow:
+        print_overflow_msg(__func__, xdr);
+        return -EIO;
 }
 
 static int decode_attr_link_support(struct xdr_stream *xdr, uint32_t *bitmap, uint32_t *res)
@@ -2667,12 +2827,17 @@ static int decode_attr_link_support(struct xdr_stream *xdr, uint32_t *bitmap, ui
         if (unlikely(bitmap[0] & (FATTR4_WORD0_LINK_SUPPORT - 1U)))
                 return -EIO;
         if (likely(bitmap[0] & FATTR4_WORD0_LINK_SUPPORT)) {
-                READ_BUF(4);
-                READ32(*res);
+                p = xdr_inline_decode(xdr, 4);
+                if (unlikely(!p))
+                        goto out_overflow;
+                *res = be32_to_cpup(p);
                 bitmap[0] &= ~FATTR4_WORD0_LINK_SUPPORT;
         }
         dprintk("%s: link support=%s\n", __func__, *res == 0 ? "false" : "true");
         return 0;
+out_overflow:
+        print_overflow_msg(__func__, xdr);
+        return -EIO;
 }
 
 static int decode_attr_symlink_support(struct xdr_stream *xdr, uint32_t *bitmap, uint32_t *res)
@@ -2683,12 +2848,17 @@ static int decode_attr_symlink_support(struct xdr_stream *xdr, uint32_t *bitmap,
         if (unlikely(bitmap[0] & (FATTR4_WORD0_SYMLINK_SUPPORT - 1U)))
                 return -EIO;
         if (likely(bitmap[0] & FATTR4_WORD0_SYMLINK_SUPPORT)) {
-                READ_BUF(4);
-                READ32(*res);
+                p = xdr_inline_decode(xdr, 4);
+                if (unlikely(!p))
+                        goto out_overflow;
+                *res = be32_to_cpup(p);
                 bitmap[0] &= ~FATTR4_WORD0_SYMLINK_SUPPORT;
         }
         dprintk("%s: symlink support=%s\n", __func__, *res == 0 ? "false" : "true");
         return 0;
+out_overflow:
+        print_overflow_msg(__func__, xdr);
+        return -EIO;
 }
 
 static int decode_attr_fsid(struct xdr_stream *xdr, uint32_t *bitmap, struct nfs_fsid *fsid)
@@ -2701,9 +2871,11 @@ static int decode_attr_fsid(struct xdr_stream *xdr, uint32_t *bitmap, struct nfs
         if (unlikely(bitmap[0] & (FATTR4_WORD0_FSID - 1U)))
                 return -EIO;
         if (likely(bitmap[0] & FATTR4_WORD0_FSID)) {
-                READ_BUF(16);
-                READ64(fsid->major);
-                READ64(fsid->minor);
+                p = xdr_inline_decode(xdr, 16);
+                if (unlikely(!p))
+                        goto out_overflow;
+                p = xdr_decode_hyper(p, &fsid->major);
+                xdr_decode_hyper(p, &fsid->minor);
                 bitmap[0] &= ~FATTR4_WORD0_FSID;
                 ret = NFS_ATTR_FATTR_FSID;
         }
@@ -2711,6 +2883,9 @@ static int decode_attr_fsid(struct xdr_stream *xdr, uint32_t *bitmap, struct nfs
                         (unsigned long long)fsid->major,
                         (unsigned long long)fsid->minor);
         return ret;
+out_overflow:
+        print_overflow_msg(__func__, xdr);
+        return -EIO;
 }
 
 static int decode_attr_lease_time(struct xdr_stream *xdr, uint32_t *bitmap, uint32_t *res)
@@ -2721,12 +2896,67 @@ static int decode_attr_lease_time(struct xdr_stream *xdr, uint32_t *bitmap, uint
         if (unlikely(bitmap[0] & (FATTR4_WORD0_LEASE_TIME - 1U)))
                 return -EIO;
         if (likely(bitmap[0] & FATTR4_WORD0_LEASE_TIME)) {
-                READ_BUF(4);
-                READ32(*res);
+                p = xdr_inline_decode(xdr, 4);
+                if (unlikely(!p))
+                        goto out_overflow;
+                *res = be32_to_cpup(p);
                 bitmap[0] &= ~FATTR4_WORD0_LEASE_TIME;
         }
         dprintk("%s: file size=%u\n", __func__, (unsigned int)*res);
         return 0;
+out_overflow:
+        print_overflow_msg(__func__, xdr);
+        return -EIO;
+}
+
+static int decode_attr_error(struct xdr_stream *xdr, uint32_t *bitmap)
+{
+        __be32 *p;
+
+        if (unlikely(bitmap[0] & (FATTR4_WORD0_RDATTR_ERROR - 1U)))
+                return -EIO;
+        if (likely(bitmap[0] & FATTR4_WORD0_RDATTR_ERROR)) {
+                p = xdr_inline_decode(xdr, 4);
+                if (unlikely(!p))
+                        goto out_overflow;
+                bitmap[0] &= ~FATTR4_WORD0_RDATTR_ERROR;
+        }
+        return 0;
+out_overflow:
+        print_overflow_msg(__func__, xdr);
+        return -EIO;
+}
+
+static int decode_attr_filehandle(struct xdr_stream *xdr, uint32_t *bitmap, struct nfs_fh *fh)
+{
+        __be32 *p;
+        int len;
+
+        if (fh != NULL)
+                memset(fh, 0, sizeof(*fh));
+
+        if (unlikely(bitmap[0] & (FATTR4_WORD0_FILEHANDLE - 1U)))
+                return -EIO;
+        if (likely(bitmap[0] & FATTR4_WORD0_FILEHANDLE)) {
+                p = xdr_inline_decode(xdr, 4);
+                if (unlikely(!p))
+                        goto out_overflow;
+                len = be32_to_cpup(p);
+                if (len > NFS4_FHSIZE)
+                        return -EIO;
+                p = xdr_inline_decode(xdr, len);
+                if (unlikely(!p))
+                        goto out_overflow;
+                if (fh != NULL) {
+                        memcpy(fh->data, p, len);
+                        fh->size = len;
+                }
+                bitmap[0] &= ~FATTR4_WORD0_FILEHANDLE;
+        }
+        return 0;
+out_overflow:
+        print_overflow_msg(__func__, xdr);
+        return -EIO;
 }
 
 static int decode_attr_aclsupport(struct xdr_stream *xdr, uint32_t *bitmap, uint32_t *res)
@@ -2737,12 +2967,17 @@ static int decode_attr_aclsupport(struct xdr_stream *xdr, uint32_t *bitmap, uint
         if (unlikely(bitmap[0] & (FATTR4_WORD0_ACLSUPPORT - 1U)))
                 return -EIO;
         if (likely(bitmap[0] & FATTR4_WORD0_ACLSUPPORT)) {
-                READ_BUF(4);
-                READ32(*res);
+                p = xdr_inline_decode(xdr, 4);
+                if (unlikely(!p))
+                        goto out_overflow;
+                *res = be32_to_cpup(p);
                 bitmap[0] &= ~FATTR4_WORD0_ACLSUPPORT;
         }
         dprintk("%s: ACLs supported=%u\n", __func__, (unsigned int)*res);
         return 0;
+out_overflow:
+        print_overflow_msg(__func__, xdr);
+        return -EIO;
 }
 
 static int decode_attr_fileid(struct xdr_stream *xdr, uint32_t *bitmap, uint64_t *fileid)
@@ -2754,13 +2989,18 @@ static int decode_attr_fileid(struct xdr_stream *xdr, uint32_t *bitmap, uint64_t
         if (unlikely(bitmap[0] & (FATTR4_WORD0_FILEID - 1U)))
                 return -EIO;
         if (likely(bitmap[0] & FATTR4_WORD0_FILEID)) {
-                READ_BUF(8);
-                READ64(*fileid);
+                p = xdr_inline_decode(xdr, 8);
+                if (unlikely(!p))
+                        goto out_overflow;
+                xdr_decode_hyper(p, fileid);
                 bitmap[0] &= ~FATTR4_WORD0_FILEID;
                 ret = NFS_ATTR_FATTR_FILEID;
         }
         dprintk("%s: fileid=%Lu\n", __func__, (unsigned long long)*fileid);
         return ret;
+out_overflow:
+        print_overflow_msg(__func__, xdr);
+        return -EIO;
 }
 
 static int decode_attr_mounted_on_fileid(struct xdr_stream *xdr, uint32_t *bitmap, uint64_t *fileid)
@@ -2772,13 +3012,18 @@ static int decode_attr_mounted_on_fileid(struct xdr_stream *xdr, uint32_t *bitma
         if (unlikely(bitmap[1] & (FATTR4_WORD1_MOUNTED_ON_FILEID - 1U)))
                 return -EIO;
         if (likely(bitmap[1] & FATTR4_WORD1_MOUNTED_ON_FILEID)) {
-                READ_BUF(8);
-                READ64(*fileid);
+                p = xdr_inline_decode(xdr, 8);
+                if (unlikely(!p))
+                        goto out_overflow;
+                xdr_decode_hyper(p, fileid);
                 bitmap[1] &= ~FATTR4_WORD1_MOUNTED_ON_FILEID;
                 ret = NFS_ATTR_FATTR_FILEID;
         }
         dprintk("%s: fileid=%Lu\n", __func__, (unsigned long long)*fileid);
         return ret;
+out_overflow:
+        print_overflow_msg(__func__, xdr);
+        return -EIO;
 }
 
 static int decode_attr_files_avail(struct xdr_stream *xdr, uint32_t *bitmap, uint64_t *res)
@@ -2790,12 +3035,17 @@ static int decode_attr_files_avail(struct xdr_stream *xdr, uint32_t *bitmap, uin
         if (unlikely(bitmap[0] & (FATTR4_WORD0_FILES_AVAIL - 1U)))
                 return -EIO;
         if (likely(bitmap[0] & FATTR4_WORD0_FILES_AVAIL)) {
-                READ_BUF(8);
-                READ64(*res);
+                p = xdr_inline_decode(xdr, 8);
+                if (unlikely(!p))
+                        goto out_overflow;
+                xdr_decode_hyper(p, res);
                 bitmap[0] &= ~FATTR4_WORD0_FILES_AVAIL;
         }
         dprintk("%s: files avail=%Lu\n", __func__, (unsigned long long)*res);
         return status;
+out_overflow:
+        print_overflow_msg(__func__, xdr);
+        return -EIO;
 }
 
 static int decode_attr_files_free(struct xdr_stream *xdr, uint32_t *bitmap, uint64_t *res)
@@ -2807,12 +3057,17 @@ static int decode_attr_files_free(struct xdr_stream *xdr, uint32_t *bitmap, uint
         if (unlikely(bitmap[0] & (FATTR4_WORD0_FILES_FREE - 1U)))
                 return -EIO;
         if (likely(bitmap[0] & FATTR4_WORD0_FILES_FREE)) {
-                READ_BUF(8);
-                READ64(*res);
+                p = xdr_inline_decode(xdr, 8);
+                if (unlikely(!p))
+                        goto out_overflow;
+                xdr_decode_hyper(p, res);
                 bitmap[0] &= ~FATTR4_WORD0_FILES_FREE;
         }
         dprintk("%s: files free=%Lu\n", __func__, (unsigned long long)*res);
         return status;
+out_overflow:
+        print_overflow_msg(__func__, xdr);
+        return -EIO;
 }
 
 static int decode_attr_files_total(struct xdr_stream *xdr, uint32_t *bitmap, uint64_t *res)
@@ -2824,12 +3079,17 @@ static int decode_attr_files_total(struct xdr_stream *xdr, uint32_t *bitmap, uin
         if (unlikely(bitmap[0] & (FATTR4_WORD0_FILES_TOTAL - 1U)))
                 return -EIO;
         if (likely(bitmap[0] & FATTR4_WORD0_FILES_TOTAL)) {
-                READ_BUF(8);
-                READ64(*res);
+                p = xdr_inline_decode(xdr, 8);
+                if (unlikely(!p))
+                        goto out_overflow;
+                xdr_decode_hyper(p, res);
                 bitmap[0] &= ~FATTR4_WORD0_FILES_TOTAL;
         }
         dprintk("%s: files total=%Lu\n", __func__, (unsigned long long)*res);
         return status;
+out_overflow:
+        print_overflow_msg(__func__, xdr);
+        return -EIO;
 }
 
 static int decode_pathname(struct xdr_stream *xdr, struct nfs4_pathname *path)
@@ -2838,8 +3098,10 @@ static int decode_pathname(struct xdr_stream *xdr, struct nfs4_pathname *path)
         __be32 *p;
         int status = 0;
 
-        READ_BUF(4);
-        READ32(n);
+        p = xdr_inline_decode(xdr, 4);
+        if (unlikely(!p))
+                goto out_overflow;
+        n = be32_to_cpup(p);
         if (n == 0)
                 goto root_path;
         dprintk("path ");
@@ -2873,6 +3135,9 @@ out_eio:
         dprintk(" status %d", status);
         status = -EIO;
         goto out;
+out_overflow:
+        print_overflow_msg(__func__, xdr);
+        return -EIO;
 }
 
 static int decode_attr_fs_locations(struct xdr_stream *xdr, uint32_t *bitmap, struct nfs4_fs_locations *res)
@@ -2890,8 +3155,10 @@ static int decode_attr_fs_locations(struct xdr_stream *xdr, uint32_t *bitmap, st
         status = decode_pathname(xdr, &res->fs_path);
         if (unlikely(status != 0))
                 goto out;
-        READ_BUF(4);
-        READ32(n);
+        p = xdr_inline_decode(xdr, 4);
+        if (unlikely(!p))
+                goto out_overflow;
+        n = be32_to_cpup(p);
         if (n <= 0)
                 goto out_eio;
         res->nlocations = 0;
@@ -2899,8 +3166,10 @@ static int decode_attr_fs_locations(struct xdr_stream *xdr, uint32_t *bitmap, st
                 u32 m;
                 struct nfs4_fs_location *loc = &res->locations[res->nlocations];
 
-                READ_BUF(4);
-                READ32(m);
+                p = xdr_inline_decode(xdr, 4);
+                if (unlikely(!p))
+                        goto out_overflow;
+                m = be32_to_cpup(p);
 
                 loc->nservers = 0;
                 dprintk("%s: servers ", __func__);
@@ -2939,6 +3208,8 @@ static int decode_attr_fs_locations(struct xdr_stream *xdr, uint32_t *bitmap, st
 out:
         dprintk("%s: fs_locations done, error = %d\n", __func__, status);
         return status;
+out_overflow:
+        print_overflow_msg(__func__, xdr);
 out_eio:
         status = -EIO;
         goto out;
@@ -2953,12 +3224,17 @@ static int decode_attr_maxfilesize(struct xdr_stream *xdr, uint32_t *bitmap, uin
         if (unlikely(bitmap[0] & (FATTR4_WORD0_MAXFILESIZE - 1U)))
                 return -EIO;
         if (likely(bitmap[0] & FATTR4_WORD0_MAXFILESIZE)) {
-                READ_BUF(8);
-                READ64(*res);
+                p = xdr_inline_decode(xdr, 8);
+                if (unlikely(!p))
+                        goto out_overflow;
+                xdr_decode_hyper(p, res);
                 bitmap[0] &= ~FATTR4_WORD0_MAXFILESIZE;
         }
         dprintk("%s: maxfilesize=%Lu\n", __func__, (unsigned long long)*res);
         return status;
+out_overflow:
+        print_overflow_msg(__func__, xdr);
+        return -EIO;
 }
 
 static int decode_attr_maxlink(struct xdr_stream *xdr, uint32_t *bitmap, uint32_t *maxlink)
@@ -2970,12 +3246,17 @@ static int decode_attr_maxlink(struct xdr_stream *xdr, uint32_t *bitmap, uint32_
         if (unlikely(bitmap[0] & (FATTR4_WORD0_MAXLINK - 1U)))
                 return -EIO;
         if (likely(bitmap[0] & FATTR4_WORD0_MAXLINK)) {
-                READ_BUF(4);
-                READ32(*maxlink);
+                p = xdr_inline_decode(xdr, 4);
+                if (unlikely(!p))
+                        goto out_overflow;
+                *maxlink = be32_to_cpup(p);
                 bitmap[0] &= ~FATTR4_WORD0_MAXLINK;
         }
         dprintk("%s: maxlink=%u\n", __func__, *maxlink);
         return status;
+out_overflow:
+        print_overflow_msg(__func__, xdr);
+        return -EIO;
 }
 
 static int decode_attr_maxname(struct xdr_stream *xdr, uint32_t *bitmap, uint32_t *maxname)
@@ -2987,12 +3268,17 @@ static int decode_attr_maxname(struct xdr_stream *xdr, uint32_t *bitmap, uint32_
         if (unlikely(bitmap[0] & (FATTR4_WORD0_MAXNAME - 1U)))
                 return -EIO;
         if (likely(bitmap[0] & FATTR4_WORD0_MAXNAME)) {
-                READ_BUF(4);
-                READ32(*maxname);
+                p = xdr_inline_decode(xdr, 4);
+                if (unlikely(!p))
+                        goto out_overflow;
+                *maxname = be32_to_cpup(p);
                 bitmap[0] &= ~FATTR4_WORD0_MAXNAME;
         }
         dprintk("%s: maxname=%u\n", __func__, *maxname);
         return status;
+out_overflow:
+        print_overflow_msg(__func__, xdr);
+        return -EIO;
 }
 
 static int decode_attr_maxread(struct xdr_stream *xdr, uint32_t *bitmap, uint32_t *res)
@@ -3005,8 +3291,10 @@ static int decode_attr_maxread(struct xdr_stream *xdr, uint32_t *bitmap, uint32_
                 return -EIO;
         if (likely(bitmap[0] & FATTR4_WORD0_MAXREAD)) {
                 uint64_t maxread;
-                READ_BUF(8);
-                READ64(maxread);
+                p = xdr_inline_decode(xdr, 8);
+                if (unlikely(!p))
+                        goto out_overflow;
+                xdr_decode_hyper(p, &maxread);
                 if (maxread > 0x7FFFFFFF)
                         maxread = 0x7FFFFFFF;
                 *res = (uint32_t)maxread;
@@ -3014,6 +3302,9 @@ static int decode_attr_maxread(struct xdr_stream *xdr, uint32_t *bitmap, uint32_
         }
         dprintk("%s: maxread=%lu\n", __func__, (unsigned long)*res);
         return status;
+out_overflow:
+        print_overflow_msg(__func__, xdr);
+        return -EIO;
 }
 
 static int decode_attr_maxwrite(struct xdr_stream *xdr, uint32_t *bitmap, uint32_t *res)
@@ -3026,8 +3317,10 @@ static int decode_attr_maxwrite(struct xdr_stream *xdr, uint32_t *bitmap, uint32
                 return -EIO;
         if (likely(bitmap[0] & FATTR4_WORD0_MAXWRITE)) {
                 uint64_t maxwrite;
-                READ_BUF(8);
-                READ64(maxwrite);
+                p = xdr_inline_decode(xdr, 8);
+                if (unlikely(!p))
+                        goto out_overflow;
+                xdr_decode_hyper(p, &maxwrite);
                 if (maxwrite > 0x7FFFFFFF)
                         maxwrite = 0x7FFFFFFF;
                 *res = (uint32_t)maxwrite;
@@ -3035,6 +3328,9 @@ static int decode_attr_maxwrite(struct xdr_stream *xdr, uint32_t *bitmap, uint32
         }
         dprintk("%s: maxwrite=%lu\n", __func__, (unsigned long)*res);
         return status;
+out_overflow:
+        print_overflow_msg(__func__, xdr);
+        return -EIO;
 }
 
 static int decode_attr_mode(struct xdr_stream *xdr, uint32_t *bitmap, umode_t *mode)
@@ -3047,14 +3343,19 @@ static int decode_attr_mode(struct xdr_stream *xdr, uint32_t *bitmap, umode_t *m
         if (unlikely(bitmap[1] & (FATTR4_WORD1_MODE - 1U)))
                 return -EIO;
         if (likely(bitmap[1] & FATTR4_WORD1_MODE)) {
-                READ_BUF(4);
-                READ32(tmp);
+                p = xdr_inline_decode(xdr, 4);
+                if (unlikely(!p))
+                        goto out_overflow;
+                tmp = be32_to_cpup(p);
                 *mode = tmp & ~S_IFMT;
                 bitmap[1] &= ~FATTR4_WORD1_MODE;
                 ret = NFS_ATTR_FATTR_MODE;
         }
         dprintk("%s: file mode=0%o\n", __func__, (unsigned int)*mode);
         return ret;
+out_overflow:
+        print_overflow_msg(__func__, xdr);
+        return -EIO;
 }
 
 static int decode_attr_nlink(struct xdr_stream *xdr, uint32_t *bitmap, uint32_t *nlink)
@@ -3066,16 +3367,22 @@ static int decode_attr_nlink(struct xdr_stream *xdr, uint32_t *bitmap, uint32_t
         if (unlikely(bitmap[1] & (FATTR4_WORD1_NUMLINKS - 1U)))
                 return -EIO;
         if (likely(bitmap[1] & FATTR4_WORD1_NUMLINKS)) {
-                READ_BUF(4);
-                READ32(*nlink);
+                p = xdr_inline_decode(xdr, 4);
+                if (unlikely(!p))
+                        goto out_overflow;
+                *nlink = be32_to_cpup(p);
                 bitmap[1] &= ~FATTR4_WORD1_NUMLINKS;
                 ret = NFS_ATTR_FATTR_NLINK;
         }
         dprintk("%s: nlink=%u\n", __func__, (unsigned int)*nlink);
         return ret;
+out_overflow:
+        print_overflow_msg(__func__, xdr);
+        return -EIO;
 }
 
-static int decode_attr_owner(struct xdr_stream *xdr, uint32_t *bitmap, struct nfs_client *clp, uint32_t *uid)
+static int decode_attr_owner(struct xdr_stream *xdr, uint32_t *bitmap,
+                struct nfs_client *clp, uint32_t *uid, int may_sleep)
 {
         uint32_t len;
         __be32 *p;
@@ -3085,10 +3392,16 @@ static int decode_attr_owner(struct xdr_stream *xdr, uint32_t *bitmap, struct nf
         if (unlikely(bitmap[1] & (FATTR4_WORD1_OWNER - 1U)))
                 return -EIO;
         if (likely(bitmap[1] & FATTR4_WORD1_OWNER)) {
-                READ_BUF(4);
-                READ32(len);
-                READ_BUF(len);
-                if (len < XDR_MAX_NETOBJ) {
+                p = xdr_inline_decode(xdr, 4);
+                if (unlikely(!p))
+                        goto out_overflow;
+                len = be32_to_cpup(p);
+                p = xdr_inline_decode(xdr, len);
+                if (unlikely(!p))
+                        goto out_overflow;
+                if (!may_sleep) {
+                        /* do nothing */
+                } else if (len < XDR_MAX_NETOBJ) {
                         if (nfs_map_name_to_uid(clp, (char *)p, len, uid) == 0)
                                 ret = NFS_ATTR_FATTR_OWNER;
                         else
@@ -3101,9 +3414,13 @@ static int decode_attr_owner(struct xdr_stream *xdr, uint32_t *bitmap, struct nf
         }
         dprintk("%s: uid=%d\n", __func__, (int)*uid);
         return ret;
+out_overflow:
+        print_overflow_msg(__func__, xdr);
+        return -EIO;
 }
 
-static int decode_attr_group(struct xdr_stream *xdr, uint32_t *bitmap, struct nfs_client *clp, uint32_t *gid)
+static int decode_attr_group(struct xdr_stream *xdr, uint32_t *bitmap,
+                struct nfs_client *clp, uint32_t *gid, int may_sleep)
 {
         uint32_t len;
         __be32 *p;
@@ -3113,10 +3430,16 @@ static int decode_attr_group(struct xdr_stream *xdr, uint32_t *bitmap, struct nf
         if (unlikely(bitmap[1] & (FATTR4_WORD1_OWNER_GROUP - 1U)))
                 return -EIO;
         if (likely(bitmap[1] & FATTR4_WORD1_OWNER_GROUP)) {
-                READ_BUF(4);
-                READ32(len);
-                READ_BUF(len);
-                if (len < XDR_MAX_NETOBJ) {
+                p = xdr_inline_decode(xdr, 4);
+                if (unlikely(!p))
+                        goto out_overflow;
+                len = be32_to_cpup(p);
+                p = xdr_inline_decode(xdr, len);
+                if (unlikely(!p))
+                        goto out_overflow;
+                if (!may_sleep) {
+                        /* do nothing */
+                } else if (len < XDR_MAX_NETOBJ) {
                         if (nfs_map_group_to_gid(clp, (char *)p, len, gid) == 0)
                                 ret = NFS_ATTR_FATTR_GROUP;
                         else
@@ -3129,6 +3452,9 @@ static int decode_attr_group(struct xdr_stream *xdr, uint32_t *bitmap, struct nf
         }
         dprintk("%s: gid=%d\n", __func__, (int)*gid);
         return ret;
+out_overflow:
+        print_overflow_msg(__func__, xdr);
+        return -EIO;
 }
 
 static int decode_attr_rdev(struct xdr_stream *xdr, uint32_t *bitmap, dev_t *rdev)
@@ -3143,9 +3469,11 @@ static int decode_attr_rdev(struct xdr_stream *xdr, uint32_t *bitmap, dev_t *rde
         if (likely(bitmap[1] & FATTR4_WORD1_RAWDEV)) {
                 dev_t tmp;
 
-                READ_BUF(8);
-                READ32(major);
-                READ32(minor);
+                p = xdr_inline_decode(xdr, 8);
+                if (unlikely(!p))
+                        goto out_overflow;
+                major = be32_to_cpup(p++);
+                minor = be32_to_cpup(p);
                 tmp = MKDEV(major, minor);
                 if (MAJOR(tmp) == major && MINOR(tmp) == minor)
                         *rdev = tmp;
@@ -3154,6 +3482,9 @@ static int decode_attr_rdev(struct xdr_stream *xdr, uint32_t *bitmap, dev_t *rde
         }
         dprintk("%s: rdev=(0x%x:0x%x)\n", __func__, major, minor);
         return ret;
+out_overflow:
+        print_overflow_msg(__func__, xdr);
+        return -EIO;
 }
 
 static int decode_attr_space_avail(struct xdr_stream *xdr, uint32_t *bitmap, uint64_t *res)
@@ -3165,12 +3496,17 @@ static int decode_attr_space_avail(struct xdr_stream *xdr, uint32_t *bitmap, uin
         if (unlikely(bitmap[1] & (FATTR4_WORD1_SPACE_AVAIL - 1U)))
                 return -EIO;
         if (likely(bitmap[1] & FATTR4_WORD1_SPACE_AVAIL)) {
-                READ_BUF(8);
-                READ64(*res);
+                p = xdr_inline_decode(xdr, 8);
+                if (unlikely(!p))
+                        goto out_overflow;
+                xdr_decode_hyper(p, res);
                 bitmap[1] &= ~FATTR4_WORD1_SPACE_AVAIL;
         }
         dprintk("%s: space avail=%Lu\n", __func__, (unsigned long long)*res);
         return status;
+out_overflow:
+        print_overflow_msg(__func__, xdr);
+        return -EIO;
 }
 
 static int decode_attr_space_free(struct xdr_stream *xdr, uint32_t *bitmap, uint64_t *res)
@@ -3182,12 +3518,17 @@ static int decode_attr_space_free(struct xdr_stream *xdr, uint32_t *bitmap, uint
         if (unlikely(bitmap[1] & (FATTR4_WORD1_SPACE_FREE - 1U)))
                 return -EIO;
         if (likely(bitmap[1] & FATTR4_WORD1_SPACE_FREE)) {
-                READ_BUF(8);
-                READ64(*res);
+                p = xdr_inline_decode(xdr, 8);
+                if (unlikely(!p))
+                        goto out_overflow;
+                xdr_decode_hyper(p, res);
                 bitmap[1] &= ~FATTR4_WORD1_SPACE_FREE;
         }
         dprintk("%s: space free=%Lu\n", __func__, (unsigned long long)*res);
         return status;
+out_overflow:
+        print_overflow_msg(__func__, xdr);
+        return -EIO;
 }
 
 static int decode_attr_space_total(struct xdr_stream *xdr, uint32_t *bitmap, uint64_t *res)
@@ -3199,12 +3540,17 @@ static int decode_attr_space_total(struct xdr_stream *xdr, uint32_t *bitmap, uin
         if (unlikely(bitmap[1] & (FATTR4_WORD1_SPACE_TOTAL - 1U)))
                 return -EIO;
         if (likely(bitmap[1] & FATTR4_WORD1_SPACE_TOTAL)) {
-                READ_BUF(8);
-                READ64(*res);
+                p = xdr_inline_decode(xdr, 8);
+                if (unlikely(!p))
+                        goto out_overflow;
+                xdr_decode_hyper(p, res);
                 bitmap[1] &= ~FATTR4_WORD1_SPACE_TOTAL;
         }
         dprintk("%s: space total=%Lu\n", __func__, (unsigned long long)*res);
         return status;
+out_overflow:
+        print_overflow_msg(__func__, xdr);
+        return -EIO;
 }
 
 static int decode_attr_space_used(struct xdr_stream *xdr, uint32_t *bitmap, uint64_t *used)
@@ -3216,14 +3562,19 @@ static int decode_attr_space_used(struct xdr_stream *xdr, uint32_t *bitmap, uint
         if (unlikely(bitmap[1] & (FATTR4_WORD1_SPACE_USED - 1U)))
                 return -EIO;
         if (likely(bitmap[1] & FATTR4_WORD1_SPACE_USED)) {
-                READ_BUF(8);
-                READ64(*used);
+                p = xdr_inline_decode(xdr, 8);
+                if (unlikely(!p))
+                        goto out_overflow;
+                xdr_decode_hyper(p, used);
                 bitmap[1] &= ~FATTR4_WORD1_SPACE_USED;
                 ret = NFS_ATTR_FATTR_SPACE_USED;
         }
         dprintk("%s: space used=%Lu\n", __func__,
                         (unsigned long long)*used);
         return ret;
+out_overflow:
+        print_overflow_msg(__func__, xdr);
+        return -EIO;
 }
 
 static int decode_attr_time(struct xdr_stream *xdr, struct timespec *time)
@@ -3232,12 +3583,17 @@ static int decode_attr_time(struct xdr_stream *xdr, struct timespec *time)
         uint64_t sec;
         uint32_t nsec;
 
-        READ_BUF(12);
-        READ64(sec);
-        READ32(nsec);
+        p = xdr_inline_decode(xdr, 12);
+        if (unlikely(!p))
+                goto out_overflow;
+        p = xdr_decode_hyper(p, &sec);
+        nsec = be32_to_cpup(p);
         time->tv_sec = (time_t)sec;
         time->tv_nsec = (long)nsec;
         return 0;
+out_overflow:
+        print_overflow_msg(__func__, xdr);
+        return -EIO;
 }
 
 static int decode_attr_time_access(struct xdr_stream *xdr, uint32_t *bitmap, struct timespec *time)
@@ -3276,6 +3632,24 @@ static int decode_attr_time_metadata(struct xdr_stream *xdr, uint32_t *bitmap, s
         return status;
 }
 
+static int decode_attr_time_delta(struct xdr_stream *xdr, uint32_t *bitmap,
+                                  struct timespec *time)
+{
+        int status = 0;
+
+        time->tv_sec = 0;
+        time->tv_nsec = 0;
+        if (unlikely(bitmap[1] & (FATTR4_WORD1_TIME_DELTA - 1U)))
+                return -EIO;
+        if (likely(bitmap[1] & FATTR4_WORD1_TIME_DELTA)) {
+                status = decode_attr_time(xdr, time);
+                bitmap[1] &= ~FATTR4_WORD1_TIME_DELTA;
+        }
+        dprintk("%s: time_delta=%ld %ld\n", __func__, (long)time->tv_sec,
+                (long)time->tv_nsec);
+        return status;
+}
+
 static int decode_attr_time_modify(struct xdr_stream *xdr, uint32_t *bitmap, struct timespec *time)
 {
         int status = 0;
@@ -3315,11 +3689,16 @@ static int decode_change_info(struct xdr_stream *xdr, struct nfs4_change_info *c
 {
         __be32 *p;
 
-        READ_BUF(20);
-        READ32(cinfo->atomic);
-        READ64(cinfo->before);
-        READ64(cinfo->after);
+        p = xdr_inline_decode(xdr, 20);
+        if (unlikely(!p))
+                goto out_overflow;
+        cinfo->atomic = be32_to_cpup(p++);
+        p = xdr_decode_hyper(p, &cinfo->before);
+        xdr_decode_hyper(p, &cinfo->after);
         return 0;
+out_overflow:
+        print_overflow_msg(__func__, xdr);
+        return -EIO;
 }
 
 static int decode_access(struct xdr_stream *xdr, struct nfs4_accessres *access)
@@ -3331,40 +3710,62 @@ static int decode_access(struct xdr_stream *xdr, struct nfs4_accessres *access)
         status = decode_op_hdr(xdr, OP_ACCESS);
         if (status)
                 return status;
-        READ_BUF(8);
-        READ32(supp);
-        READ32(acc);
+        p = xdr_inline_decode(xdr, 8);
+        if (unlikely(!p))
+                goto out_overflow;
+        supp = be32_to_cpup(p++);
+        acc = be32_to_cpup(p);
         access->supported = supp;
         access->access = acc;
         return 0;
+out_overflow:
+        print_overflow_msg(__func__, xdr);
+        return -EIO;
 }
 
-static int decode_close(struct xdr_stream *xdr, struct nfs_closeres *res)
+static int decode_opaque_fixed(struct xdr_stream *xdr, void *buf, size_t len)
 {
         __be32 *p;
+
+        p = xdr_inline_decode(xdr, len);
+        if (likely(p)) {
+                memcpy(buf, p, len);
+                return 0;
+        }
+        print_overflow_msg(__func__, xdr);
+        return -EIO;
+}
+
+static int decode_stateid(struct xdr_stream *xdr, nfs4_stateid *stateid)
+{
+        return decode_opaque_fixed(xdr, stateid->data, NFS4_STATEID_SIZE);
+}
+
+static int decode_close(struct xdr_stream *xdr, struct nfs_closeres *res)
+{
         int status;
 
         status = decode_op_hdr(xdr, OP_CLOSE);
         if (status != -EIO)
                 nfs_increment_open_seqid(status, res->seqid);
-        if (status)
-                return status;
-        READ_BUF(NFS4_STATEID_SIZE);
-        COPYMEM(res->stateid.data, NFS4_STATEID_SIZE);
-        return 0;
+        if (!status)
+                status = decode_stateid(xdr, &res->stateid);
+        return status;
+}
+
+static int decode_verifier(struct xdr_stream *xdr, void *verifier)
+{
+        return decode_opaque_fixed(xdr, verifier, 8);
 }
 
 static int decode_commit(struct xdr_stream *xdr, struct nfs_writeres *res)
 {
-        __be32 *p;
         int status;
 
         status = decode_op_hdr(xdr, OP_COMMIT);
-        if (status)
-                return status;
-        READ_BUF(8);
-        COPYMEM(res->verf->verifier, 8);
-        return 0;
+        if (!status)
+                status = decode_verifier(xdr, res->verf->verifier);
+        return status;
 }
 
 static int decode_create(struct xdr_stream *xdr, struct nfs4_change_info *cinfo)
@@ -3378,10 +3779,16 @@ static int decode_create(struct xdr_stream *xdr, struct nfs4_change_info *cinfo)
                 return status;
         if ((status = decode_change_info(xdr, cinfo)))
                 return status;
-        READ_BUF(4);
-        READ32(bmlen);
-        READ_BUF(bmlen << 2);
-        return 0;
+        p = xdr_inline_decode(xdr, 4);
+        if (unlikely(!p))
+                goto out_overflow;
+        bmlen = be32_to_cpup(p);
+        p = xdr_inline_decode(xdr, bmlen << 2);
+        if (likely(p))
+                return 0;
+out_overflow:
+        print_overflow_msg(__func__, xdr);
+        return -EIO;
 }
 
 static int decode_server_caps(struct xdr_stream *xdr, struct nfs4_server_caps_res *res)
@@ -3466,28 +3873,14 @@ xdr_error:
         return status;
 }
 
-static int decode_getfattr(struct xdr_stream *xdr, struct nfs_fattr *fattr, const struct nfs_server *server)
+static int decode_getfattr_attrs(struct xdr_stream *xdr, uint32_t *bitmap,
+                struct nfs_fattr *fattr, struct nfs_fh *fh,
+                const struct nfs_server *server, int may_sleep)
 {
-        __be32 *savep;
-        uint32_t attrlen,
-                 bitmap[2] = {0},
-                 type;
         int status;
         umode_t fmode = 0;
         uint64_t fileid;
-
-        status = decode_op_hdr(xdr, OP_GETATTR);
-        if (status < 0)
-                goto xdr_error;
-
-        status = decode_attr_bitmap(xdr, bitmap);
-        if (status < 0)
-                goto xdr_error;
-
-        status = decode_attr_length(xdr, &attrlen, &savep);
-        if (status < 0)
-                goto xdr_error;
-
+        uint32_t type;
 
         status = decode_attr_type(xdr, bitmap, &type);
         if (status < 0)
@@ -3513,6 +3906,14 @@ static int decode_getfattr(struct xdr_stream *xdr, struct nfs_fattr *fattr, cons
                 goto xdr_error;
         fattr->valid |= status;
 
+        status = decode_attr_error(xdr, bitmap);
+        if (status < 0)
+                goto xdr_error;
+
+        status = decode_attr_filehandle(xdr, bitmap, fh);
+        if (status < 0)
+                goto xdr_error;
+
         status = decode_attr_fileid(xdr, bitmap, &fattr->fileid);
         if (status < 0)
                 goto xdr_error;
@@ -3538,12 +3939,14 @@ static int decode_getfattr(struct xdr_stream *xdr, struct nfs_fattr *fattr, cons
                 goto xdr_error;
         fattr->valid |= status;
 
-        status = decode_attr_owner(xdr, bitmap, server->nfs_client, &fattr->uid);
+        status = decode_attr_owner(xdr, bitmap, server->nfs_client,
+                        &fattr->uid, may_sleep);
         if (status < 0)
                 goto xdr_error;
         fattr->valid |= status;
 
-        status = decode_attr_group(xdr, bitmap, server->nfs_client, &fattr->gid);
+        status = decode_attr_group(xdr, bitmap, server->nfs_client,
+                        &fattr->gid, may_sleep);
         if (status < 0)
                 goto xdr_error;
         fattr->valid |= status;
@@ -3581,12 +3984,101 @@ static int decode_getfattr(struct xdr_stream *xdr, struct nfs_fattr *fattr, cons
                 fattr->valid |= status;
         }
 
+xdr_error:
+        dprintk("%s: xdr returned %d\n", __func__, -status);
+        return status;
+}
+
+static int decode_getfattr_generic(struct xdr_stream *xdr, struct nfs_fattr *fattr,
+                struct nfs_fh *fh, const struct nfs_server *server, int may_sleep)
+{
+        __be32 *savep;
+        uint32_t attrlen,
+                 bitmap[2] = {0};
+        int status;
+
+        status = decode_op_hdr(xdr, OP_GETATTR);
+        if (status < 0)
+                goto xdr_error;
+
+        status = decode_attr_bitmap(xdr, bitmap);
+        if (status < 0)
+                goto xdr_error;
+
+        status = decode_attr_length(xdr, &attrlen, &savep);
+        if (status < 0)
+                goto xdr_error;
+
+        status = decode_getfattr_attrs(xdr, bitmap, fattr, fh, server, may_sleep);
+        if (status < 0)
+                goto xdr_error;
+
         status = verify_attr_len(xdr, savep, attrlen);
 xdr_error:
         dprintk("%s: xdr returned %d\n", __func__, -status);
         return status;
 }
 
+static int decode_getfattr(struct xdr_stream *xdr, struct nfs_fattr *fattr,
+                const struct nfs_server *server, int may_sleep)
+{
+        return decode_getfattr_generic(xdr, fattr, NULL, server, may_sleep);
+}
+
+/*
+ * Decode potentially multiple layout types. Currently we only support
+ * one layout driver per file system.
+ */
+static int decode_first_pnfs_layout_type(struct xdr_stream *xdr,
+                                         uint32_t *layouttype)
+{
+        uint32_t *p;
+        int num;
+
+        p = xdr_inline_decode(xdr, 4);
+        if (unlikely(!p))
+                goto out_overflow;
+        num = be32_to_cpup(p);
+
+        /* pNFS is not supported by the underlying file system */
+        if (num == 0) {
+                *layouttype = 0;
+                return 0;
+        }
+        if (num > 1)
+                printk(KERN_INFO "%s: Warning: Multiple pNFS layout drivers "
+                        "per filesystem not supported\n", __func__);
+
+        /* Decode and set first layout type, move xdr->p past unused types */
+        p = xdr_inline_decode(xdr, num * 4);
+        if (unlikely(!p))
+                goto out_overflow;
+        *layouttype = be32_to_cpup(p);
+        return 0;
+out_overflow:
+        print_overflow_msg(__func__, xdr);
+        return -EIO;
+}
+
+/*
+ * The type of file system exported.
+ * Note we must ensure that layouttype is set in any non-error case.
+ */
+static int decode_attr_pnfstype(struct xdr_stream *xdr, uint32_t *bitmap,
+                                uint32_t *layouttype)
+{
+        int status = 0;
+
+        dprintk("%s: bitmap is %x\n", __func__, bitmap[1]);
+        if (unlikely(bitmap[1] & (FATTR4_WORD1_FS_LAYOUT_TYPES - 1U)))
+                return -EIO;
+        if (bitmap[1] & FATTR4_WORD1_FS_LAYOUT_TYPES) {
+                status = decode_first_pnfs_layout_type(xdr, layouttype);
+                bitmap[1] &= ~FATTR4_WORD1_FS_LAYOUT_TYPES;
+        } else
+                *layouttype = 0;
+        return status;
+}
 
 static int decode_fsinfo(struct xdr_stream *xdr, struct nfs_fsinfo *fsinfo)
 {
@@ -3613,6 +4105,12 @@ static int decode_fsinfo(struct xdr_stream *xdr, struct nfs_fsinfo *fsinfo)
         if ((status = decode_attr_maxwrite(xdr, bitmap, &fsinfo->wtmax)) != 0)
                 goto xdr_error;
         fsinfo->wtpref = fsinfo->wtmax;
+        status = decode_attr_time_delta(xdr, bitmap, &fsinfo->time_delta);
+        if (status != 0)
+                goto xdr_error;
+        status = decode_attr_pnfstype(xdr, bitmap, &fsinfo->layouttype);
+        if (status != 0)
+                goto xdr_error;
 
         status = verify_attr_len(xdr, savep, attrlen);
 xdr_error:
@@ -3633,14 +4131,21 @@ static int decode_getfh(struct xdr_stream *xdr, struct nfs_fh *fh)
         if (status)
                 return status;
 
-        READ_BUF(4);
-        READ32(len);
+        p = xdr_inline_decode(xdr, 4);
+        if (unlikely(!p))
+                goto out_overflow;
+        len = be32_to_cpup(p);
         if (len > NFS4_FHSIZE)
                 return -EIO;
         fh->size = len;
-        READ_BUF(len);
-        COPYMEM(fh->data, len);
+        p = xdr_inline_decode(xdr, len);
+        if (unlikely(!p))
+                goto out_overflow;
+        memcpy(fh->data, p, len);
         return 0;
+out_overflow:
+        print_overflow_msg(__func__, xdr);
+        return -EIO;
 }
 
 static int decode_link(struct xdr_stream *xdr, struct nfs4_change_info *cinfo)
@@ -3662,11 +4167,13 @@ static int decode_lock_denied (struct xdr_stream *xdr, struct file_lock *fl)
         __be32 *p;
         uint32_t namelen, type;
 
-        READ_BUF(32);
-        READ64(offset);
-        READ64(length);
-        READ32(type);
-        if (fl != NULL) {
+        p = xdr_inline_decode(xdr, 32); /* read 32 bytes */
+        if (unlikely(!p))
+                goto out_overflow;
+        p = xdr_decode_hyper(p, &offset); /* read 2 8-byte long words */
+        p = xdr_decode_hyper(p, &length);
+        type = be32_to_cpup(p++); /* 4 byte read */
+        if (fl != NULL) { /* manipulate file lock */
                 fl->fl_start = (loff_t)offset;
                 fl->fl_end = fl->fl_start + (loff_t)length - 1;
                 if (length == ~(uint64_t)0)
@@ -3676,23 +4183,27 @@ static int decode_lock_denied (struct xdr_stream *xdr, struct file_lock *fl)
                         fl->fl_type = F_RDLCK;
                 fl->fl_pid = 0;
         }
-        READ64(clientid);
-        READ32(namelen);
-        READ_BUF(namelen);
-        return -NFS4ERR_DENIED;
+        p = xdr_decode_hyper(p, &clientid); /* read 8 bytes */
+        namelen = be32_to_cpup(p); /* read 4 bytes */  /* have read all 32 bytes now */
+        p = xdr_inline_decode(xdr, namelen); /* variable size field */
+        if (likely(p))
+                return -NFS4ERR_DENIED;
+out_overflow:
+        print_overflow_msg(__func__, xdr);
+        return -EIO;
 }
 
 static int decode_lock(struct xdr_stream *xdr, struct nfs_lock_res *res)
 {
-        __be32 *p;
         int status;
 
         status = decode_op_hdr(xdr, OP_LOCK);
         if (status == -EIO)
                 goto out;
         if (status == 0) {
-                READ_BUF(NFS4_STATEID_SIZE);
-                COPYMEM(res->stateid.data, NFS4_STATEID_SIZE);
+                status = decode_stateid(xdr, &res->stateid);
+                if (unlikely(status))
+                        goto out;
         } else if (status == -NFS4ERR_DENIED)
                 status = decode_lock_denied(xdr, NULL);
         if (res->open_seqid != NULL)
@@ -3713,19 +4224,21 @@ static int decode_lockt(struct xdr_stream *xdr, struct nfs_lockt_res *res)
 
 static int decode_locku(struct xdr_stream *xdr, struct nfs_locku_res *res)
 {
-        __be32 *p;
         int status;
 
         status = decode_op_hdr(xdr, OP_LOCKU);
         if (status != -EIO)
                 nfs_increment_lock_seqid(status, res->seqid);
-        if (status == 0) {
-                READ_BUF(NFS4_STATEID_SIZE);
-                COPYMEM(res->stateid.data, NFS4_STATEID_SIZE);
-        }
+        if (status == 0)
+                status = decode_stateid(xdr, &res->stateid);
         return status;
 }
 
+static int decode_release_lockowner(struct xdr_stream *xdr)
+{
+        return decode_op_hdr(xdr, OP_RELEASE_LOCKOWNER);
+}
+
 static int decode_lookup(struct xdr_stream *xdr)
 {
         return decode_op_hdr(xdr, OP_LOOKUP);
@@ -3737,34 +4250,46 @@ static int decode_space_limit(struct xdr_stream *xdr, u64 *maxsize)
         __be32 *p;
         uint32_t limit_type, nblocks, blocksize;
 
-        READ_BUF(12);
-        READ32(limit_type);
+        p = xdr_inline_decode(xdr, 12);
+        if (unlikely(!p))
+                goto out_overflow;
+        limit_type = be32_to_cpup(p++);
         switch (limit_type) {
         case 1:
-                READ64(*maxsize);
+                xdr_decode_hyper(p, maxsize);
                 break;
         case 2:
-                READ32(nblocks);
-                READ32(blocksize);
+                nblocks = be32_to_cpup(p++);
+                blocksize = be32_to_cpup(p);
                 *maxsize = (uint64_t)nblocks * (uint64_t)blocksize;
         }
         return 0;
+out_overflow:
+        print_overflow_msg(__func__, xdr);
+        return -EIO;
 }
 
 static int decode_delegation(struct xdr_stream *xdr, struct nfs_openres *res)
 {
         __be32 *p;
         uint32_t delegation_type;
+        int status;
 
-        READ_BUF(4);
-        READ32(delegation_type);
+        p = xdr_inline_decode(xdr, 4);
+        if (unlikely(!p))
+                goto out_overflow;
+        delegation_type = be32_to_cpup(p);
         if (delegation_type == NFS4_OPEN_DELEGATE_NONE) {
                 res->delegation_type = 0;
                 return 0;
         }
-        READ_BUF(NFS4_STATEID_SIZE+4);
-        COPYMEM(res->delegation.data, NFS4_STATEID_SIZE);
-        READ32(res->do_recall);
+        status = decode_stateid(xdr, &res->delegation);
+        if (unlikely(status))
+                return status;
+        p = xdr_inline_decode(xdr, 4);
+        if (unlikely(!p))
+                goto out_overflow;
+        res->do_recall = be32_to_cpup(p);
 
         switch (delegation_type) {
         case NFS4_OPEN_DELEGATE_READ:
@@ -3776,6 +4301,9 @@ static int decode_delegation(struct xdr_stream *xdr, struct nfs_openres *res)
                                 return -EIO;
         }
         return decode_ace(xdr, NULL, res->server->nfs_client);
+out_overflow:
+        print_overflow_msg(__func__, xdr);
+        return -EIO;
 }
 
 static int decode_open(struct xdr_stream *xdr, struct nfs_openres *res)
@@ -3787,23 +4315,27 @@ static int decode_open(struct xdr_stream *xdr, struct nfs_openres *res)
         status = decode_op_hdr(xdr, OP_OPEN);
         if (status != -EIO)
                 nfs_increment_open_seqid(status, res->seqid);
-        if (status)
+        if (!status)
+                status = decode_stateid(xdr, &res->stateid);
+        if (unlikely(status))
                 return status;
-        READ_BUF(NFS4_STATEID_SIZE);
-        COPYMEM(res->stateid.data, NFS4_STATEID_SIZE);
 
         decode_change_info(xdr, &res->cinfo);
 
-        READ_BUF(8);
-        READ32(res->rflags);
-        READ32(bmlen);
+        p = xdr_inline_decode(xdr, 8);
+        if (unlikely(!p))
+                goto out_overflow;
+        res->rflags = be32_to_cpup(p++);
+        bmlen = be32_to_cpup(p);
         if (bmlen > 10)
                 goto xdr_error;
 
-        READ_BUF(bmlen << 2);
+        p = xdr_inline_decode(xdr, bmlen << 2);
+        if (unlikely(!p))
+                goto out_overflow;
         savewords = min_t(uint32_t, bmlen, NFS4_BITMAP_SIZE);
         for (i = 0; i < savewords; ++i)
-                READ32(res->attrset[i]);
+                res->attrset[i] = be32_to_cpup(p++);
         for (; i < NFS4_BITMAP_SIZE; i++)
                 res->attrset[i] = 0;
 
@@ -3811,36 +4343,33 @@ static int decode_open(struct xdr_stream *xdr, struct nfs_openres *res)
 xdr_error:
         dprintk("%s: Bitmap too large! Length = %u\n", __func__, bmlen);
         return -EIO;
+out_overflow:
+        print_overflow_msg(__func__, xdr);
+        return -EIO;
 }
 
 static int decode_open_confirm(struct xdr_stream *xdr, struct nfs_open_confirmres *res)
 {
-        __be32 *p;
         int status;
 
         status = decode_op_hdr(xdr, OP_OPEN_CONFIRM);
         if (status != -EIO)
                 nfs_increment_open_seqid(status, res->seqid);
-        if (status)
-                return status;
-        READ_BUF(NFS4_STATEID_SIZE);
-        COPYMEM(res->stateid.data, NFS4_STATEID_SIZE);
-        return 0;
+        if (!status)
+                status = decode_stateid(xdr, &res->stateid);
+        return status;
 }
 
 static int decode_open_downgrade(struct xdr_stream *xdr, struct nfs_closeres *res)
 {
-        __be32 *p;
         int status;
 
         status = decode_op_hdr(xdr, OP_OPEN_DOWNGRADE);
         if (status != -EIO)
                 nfs_increment_open_seqid(status, res->seqid);
-        if (status)
-                return status;
-        READ_BUF(NFS4_STATEID_SIZE);
-        COPYMEM(res->stateid.data, NFS4_STATEID_SIZE);
-        return 0;
+        if (!status)
+                status = decode_stateid(xdr, &res->stateid);
+        return status;
 }
 
 static int decode_putfh(struct xdr_stream *xdr)
@@ -3863,10 +4392,12 @@ static int decode_read(struct xdr_stream *xdr, struct rpc_rqst *req, struct nfs_
         status = decode_op_hdr(xdr, OP_READ);
         if (status)
                 return status;
-        READ_BUF(8);
-        READ32(eof);
-        READ32(count);
-        hdrlen = (u8 *) p - (u8 *) iov->iov_base;
+        p = xdr_inline_decode(xdr, 8);
+        if (unlikely(!p))
+                goto out_overflow;
+        eof = be32_to_cpup(p++);
+        count = be32_to_cpup(p);
+        hdrlen = (u8 *) xdr->p - (u8 *) iov->iov_base;
         recvd = req->rq_rcv_buf.len - hdrlen;
         if (count > recvd) {
                 dprintk("NFS: server cheating in read reply: "
@@ -3878,101 +4409,38 @@ static int decode_read(struct xdr_stream *xdr, struct rpc_rqst *req, struct nfs_
         res->eof = eof;
         res->count = count;
         return 0;
+out_overflow:
+        print_overflow_msg(__func__, xdr);
+        return -EIO;
 }
 
 static int decode_readdir(struct xdr_stream *xdr, struct rpc_rqst *req, struct nfs4_readdir_res *readdir)
 {
         struct xdr_buf  *rcvbuf = &req->rq_rcv_buf;
-        struct page     *page = *rcvbuf->pages;
         struct kvec     *iov = rcvbuf->head;
         size_t          hdrlen;
         u32             recvd, pglen = rcvbuf->page_len;
-        __be32          *end, *entry, *p, *kaddr;
-        unsigned int    nr = 0;
         int             status;
 
         status = decode_op_hdr(xdr, OP_READDIR);
-        if (status)
+        if (!status)
+                status = decode_verifier(xdr, readdir->verifier.data);
+        if (unlikely(status))
                 return status;
-        READ_BUF(8);
-        COPYMEM(readdir->verifier.data, 8);
         dprintk("%s: verifier = %08x:%08x\n",
                         __func__,
                         ((u32 *)readdir->verifier.data)[0],
                         ((u32 *)readdir->verifier.data)[1]);
 
 
-        hdrlen = (char *) p - (char *) iov->iov_base;
+        hdrlen = (char *) xdr->p - (char *) iov->iov_base;
         recvd = rcvbuf->len - hdrlen;
         if (pglen > recvd)
                 pglen = recvd;
         xdr_read_pages(xdr, pglen);
 
-        BUG_ON(pglen + readdir->pgbase > PAGE_CACHE_SIZE);
-        kaddr = p = kmap_atomic(page, KM_USER0);
-        end = p + ((pglen + readdir->pgbase) >> 2);
-        entry = p;
-
-        /* Make sure the packet actually has a value_follows and EOF entry */
-        if ((entry + 1) > end)
-                goto short_pkt;
-
-        for (; *p++; nr++) {
-                u32 len, attrlen, xlen;
-                if (end - p < 3)
-                        goto short_pkt;
-                dprintk("cookie = %Lu, ", *((unsigned long long *)p));
-                p += 2;                 /* cookie */
-                len = ntohl(*p++);      /* filename length */
-                if (len > NFS4_MAXNAMLEN) {
-                        dprintk("NFS: giant filename in readdir (len 0x%x)\n",
-                                        len);
-                        goto err_unmap;
-                }
-                xlen = XDR_QUADLEN(len);
-                if (end - p < xlen + 1)
-                        goto short_pkt;
-                dprintk("filename = %*s\n", len, (char *)p);
-                p += xlen;
-                len = ntohl(*p++);      /* bitmap length */
-                if (end - p < len + 1)
-                        goto short_pkt;
-                p += len;
-                attrlen = XDR_QUADLEN(ntohl(*p++));
-                if (end - p < attrlen + 2)
-                        goto short_pkt;
-                p += attrlen;           /* attributes */
-                entry = p;
-        }
-        /*
-         * Apparently some server sends responses that are a valid size, but
-         * contain no entries, and have value_follows==0 and EOF==0. For
-         * those, just set the EOF marker.
-         */
-        if (!nr && entry[1] == 0) {
-                dprintk("NFS: readdir reply truncated!\n");
-                entry[1] = 1;
-        }
-out:
-        kunmap_atomic(kaddr, KM_USER0);
-        return 0;
-short_pkt:
-        /*
-         * When we get a short packet there are 2 possibilities. We can
-         * return an error, or fix up the response to look like a valid
-         * response and return what we have so far. If there are no
-         * entries and the packet was short, then return -EIO. If there
-         * are valid entries in the response, return them and pretend that
-         * the call was successful, but incomplete. The caller can retry the
-         * readdir starting at the last cookie.
-         */
-        dprintk("%s: short packet at entry %d\n", __func__, nr);
-        entry[0] = entry[1] = 0;
-        if (nr)
-                goto out;
-err_unmap:
-        kunmap_atomic(kaddr, KM_USER0);
-        return -errno_NFSERR_IO;
+
+        return pglen;
 }
 
 static int decode_readlink(struct xdr_stream *xdr, struct rpc_rqst *req)
@@ -3982,7 +4450,6 @@ static int decode_readlink(struct xdr_stream *xdr, struct rpc_rqst *req)
         size_t hdrlen;
         u32 len, recvd;
         __be32 *p;
-        char *kaddr;
         int status;
 
         status = decode_op_hdr(xdr, OP_READLINK);
@@ -3990,8 +4457,10 @@ static int decode_readlink(struct xdr_stream *xdr, struct rpc_rqst *req)
                 return status;
 
         /* Convert length of symlink */
-        READ_BUF(4);
-        READ32(len);
+        p = xdr_inline_decode(xdr, 4);
+        if (unlikely(!p))
+                goto out_overflow;
+        len = be32_to_cpup(p);
         if (len >= rcvbuf->page_len || len <= 0) {
                 dprintk("nfs: server returned giant symlink!\n");
                 return -ENAMETOOLONG;
@@ -4011,10 +4480,11 @@ static int decode_readlink(struct xdr_stream *xdr, struct rpc_rqst *req)
          * and and null-terminate the text (the VFS expects
          * null-termination).
          */
-        kaddr = (char *)kmap_atomic(rcvbuf->pages[0], KM_USER0);
-        kaddr[len+rcvbuf->page_base] = '\0';
-        kunmap_atomic(kaddr, KM_USER0);
+        xdr_terminate_string(rcvbuf, len);
         return 0;
+out_overflow:
+        print_overflow_msg(__func__, xdr);
+        return -EIO;
 }
 
 static int decode_remove(struct xdr_stream *xdr, struct nfs4_change_info *cinfo)
@@ -4112,47 +4582,68 @@ static int decode_setattr(struct xdr_stream *xdr)
         status = decode_op_hdr(xdr, OP_SETATTR);
         if (status)
                 return status;
-        READ_BUF(4);
-        READ32(bmlen);
-        READ_BUF(bmlen << 2);
-        return 0;
+        p = xdr_inline_decode(xdr, 4);
+        if (unlikely(!p))
+                goto out_overflow;
+        bmlen = be32_to_cpup(p);
+        p = xdr_inline_decode(xdr, bmlen << 2);
+        if (likely(p))
+                return 0;
+out_overflow:
+        print_overflow_msg(__func__, xdr);
+        return -EIO;
 }
 
-static int decode_setclientid(struct xdr_stream *xdr, struct nfs_client *clp)
+static int decode_setclientid(struct xdr_stream *xdr, struct nfs4_setclientid_res *res)
 {
         __be32 *p;
         uint32_t opnum;
         int32_t nfserr;
 
-        READ_BUF(8);
-        READ32(opnum);
+        p = xdr_inline_decode(xdr, 8);
+        if (unlikely(!p))
+                goto out_overflow;
+        opnum = be32_to_cpup(p++);
         if (opnum != OP_SETCLIENTID) {
                 dprintk("nfs: decode_setclientid: Server returned operation"
                         " %d\n", opnum);
                 return -EIO;
         }
-        READ32(nfserr);
+        nfserr = be32_to_cpup(p);
         if (nfserr == NFS_OK) {
-                READ_BUF(8 + NFS4_VERIFIER_SIZE);
-                READ64(clp->cl_clientid);
-                COPYMEM(clp->cl_confirm.data, NFS4_VERIFIER_SIZE);
+                p = xdr_inline_decode(xdr, 8 + NFS4_VERIFIER_SIZE);
+                if (unlikely(!p))
+                        goto out_overflow;
+                p = xdr_decode_hyper(p, &res->clientid);
+                memcpy(res->confirm.data, p, NFS4_VERIFIER_SIZE);
         } else if (nfserr == NFSERR_CLID_INUSE) {
                 uint32_t len;
 
                 /* skip netid string */
-                READ_BUF(4);
-                READ32(len);
-                READ_BUF(len);
+                p = xdr_inline_decode(xdr, 4);
+                if (unlikely(!p))
+                        goto out_overflow;
+                len = be32_to_cpup(p);
+                p = xdr_inline_decode(xdr, len);
+                if (unlikely(!p))
+                        goto out_overflow;
 
                 /* skip uaddr string */
-                READ_BUF(4);
-                READ32(len);
-                READ_BUF(len);
+                p = xdr_inline_decode(xdr, 4);
+                if (unlikely(!p))
+                        goto out_overflow;
+                len = be32_to_cpup(p);
+                p = xdr_inline_decode(xdr, len);
+                if (unlikely(!p))
+                        goto out_overflow;
                 return -NFSERR_CLID_INUSE;
         } else
                 return nfs4_stat_to_errno(nfserr);
 
         return 0;
+out_overflow:
+        print_overflow_msg(__func__, xdr);
+        return -EIO;
 }
 
 static int decode_setclientid_confirm(struct xdr_stream *xdr)
@@ -4169,11 +4660,16 @@ static int decode_write(struct xdr_stream *xdr, struct nfs_writeres *res)
         if (status)
                 return status;
 
-        READ_BUF(16);
-        READ32(res->count);
-        READ32(res->verf->committed);
-        COPYMEM(res->verf->verifier, 8);
+        p = xdr_inline_decode(xdr, 16);
+        if (unlikely(!p))
+                goto out_overflow;
+        res->count = be32_to_cpup(p++);
+        res->verf->committed = be32_to_cpup(p++);
+        memcpy(res->verf->verifier, p, 8);
         return 0;
+out_overflow:
+        print_overflow_msg(__func__, xdr);
+        return -EIO;
 }
 
 static int decode_delegreturn(struct xdr_stream *xdr)
@@ -4187,6 +4683,7 @@ static int decode_exchange_id(struct xdr_stream *xdr,
 {
         __be32 *p;
         uint32_t dummy;
+        char *dummy_str;
         int status;
         struct nfs_client *clp = res->client;
 
@@ -4194,36 +4691,45 @@ static int decode_exchange_id(struct xdr_stream *xdr,
         if (status)
                 return status;
 
-        READ_BUF(8);
-        READ64(clp->cl_ex_clid);
-        READ_BUF(12);
-        READ32(clp->cl_seqid);
-        READ32(clp->cl_exchange_flags);
+        p = xdr_inline_decode(xdr, 8);
+        if (unlikely(!p))
+                goto out_overflow;
+        xdr_decode_hyper(p, &clp->cl_ex_clid);
+        p = xdr_inline_decode(xdr, 12);
+        if (unlikely(!p))
+                goto out_overflow;
+        clp->cl_seqid = be32_to_cpup(p++);
+        clp->cl_exchange_flags = be32_to_cpup(p++);
 
         /* We ask for SP4_NONE */
-        READ32(dummy);
+        dummy = be32_to_cpup(p);
         if (dummy != SP4_NONE)
                 return -EIO;
 
         /* Throw away minor_id */
-        READ_BUF(8);
+        p = xdr_inline_decode(xdr, 8);
+        if (unlikely(!p))
+                goto out_overflow;
 
         /* Throw away Major id */
-        READ_BUF(4);
-        READ32(dummy);
-        READ_BUF(dummy);
+        status = decode_opaque_inline(xdr, &dummy, &dummy_str);
+        if (unlikely(status))
+                return status;
 
         /* Throw away server_scope */
-        READ_BUF(4);
-        READ32(dummy);
-        READ_BUF(dummy);
+        status = decode_opaque_inline(xdr, &dummy, &dummy_str);
+        if (unlikely(status))
+                return status;
 
         /* Throw away Implementation id array */
-        READ_BUF(4);
-        READ32(dummy);
-        READ_BUF(dummy);
+        status = decode_opaque_inline(xdr, &dummy, &dummy_str);
+        if (unlikely(status))
+                return status;
 
         return 0;
+out_overflow:
+        print_overflow_msg(__func__, xdr);
+        return -EIO;
 }
 
 static int decode_chan_attrs(struct xdr_stream *xdr,
@@ -4232,22 +4738,35 @@ static int decode_chan_attrs(struct xdr_stream *xdr,
         __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);
+        p = xdr_inline_decode(xdr, 28);
+        if (unlikely(!p))
+                goto out_overflow;
+        attrs->headerpadsz = be32_to_cpup(p++);
+        attrs->max_rqst_sz = be32_to_cpup(p++);
+        attrs->max_resp_sz = be32_to_cpup(p++);
+        attrs->max_resp_sz_cached = be32_to_cpup(p++);
+        attrs->max_ops = be32_to_cpup(p++);
+        attrs->max_reqs = be32_to_cpup(p++);
+        nr_attrs = be32_to_cpup(p);
         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 */
+        if (nr_attrs == 1) {
+                p = xdr_inline_decode(xdr, 4); /* skip rdma_attrs */
+                if (unlikely(!p))
+                        goto out_overflow;
+        }
         return 0;
+out_overflow:
+        print_overflow_msg(__func__, xdr);
+        return -EIO;
+}
+
+static int decode_sessionid(struct xdr_stream *xdr, struct nfs4_sessionid *sid)
+{
+        return decode_opaque_fixed(xdr, sid->data, NFS4_MAX_SESSIONID_LEN);
 }
 
 static int decode_create_session(struct xdr_stream *xdr,
@@ -4259,30 +4778,37 @@ static int decode_create_session(struct xdr_stream *xdr,
         struct nfs4_session *session = clp->cl_session;
 
         status = decode_op_hdr(xdr, OP_CREATE_SESSION);
-
-        if (status)
+        if (!status)
+                status = decode_sessionid(xdr, &session->sess_id);
+        if (unlikely(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);
+        p = xdr_inline_decode(xdr, 8);
+        if (unlikely(!p))
+                goto out_overflow;
+        clp->cl_seqid = be32_to_cpup(p++);
+        session->flags = be32_to_cpup(p);
 
         /* Channel attributes */
         status = decode_chan_attrs(xdr, &session->fc_attrs);
         if (!status)
                 status = decode_chan_attrs(xdr, &session->bc_attrs);
         return status;
+out_overflow:
+        print_overflow_msg(__func__, xdr);
+        return -EIO;
 }
 
 static int decode_destroy_session(struct xdr_stream *xdr, void *dummy)
 {
         return decode_op_hdr(xdr, OP_DESTROY_SESSION);
 }
+
+static int decode_reclaim_complete(struct xdr_stream *xdr, void *dummy)
+{
+        return decode_op_hdr(xdr, OP_RECLAIM_COMPLETE);
+}
 #endif /* CONFIG_NFS_V4_1 */
 
 static int decode_sequence(struct xdr_stream *xdr,
@@ -4290,7 +4816,6 @@ static int decode_sequence(struct xdr_stream *xdr,
                            struct rpc_rqst *rqstp)
 {
 #if defined(CONFIG_NFS_V4_1)
-        struct nfs4_slot *slot;
         struct nfs4_sessionid id;
         u32 dummy;
         int status;
@@ -4300,50 +4825,186 @@ static int decode_sequence(struct xdr_stream *xdr,
                 return 0;
 
         status = decode_op_hdr(xdr, OP_SEQUENCE);
-        if (status)
+        if (!status)
+                status = decode_sessionid(xdr, &id);
+        if (unlikely(status))
                 goto out_err;
 
         /*
          * If the server returns different values for sessionID, slotID or
          * sequence number, the server is looney tunes.
          */
-        status = -ESERVERFAULT;
+        status = -EREMOTEIO;
 
-        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;
         }
+
+        p = xdr_inline_decode(xdr, 20);
+        if (unlikely(!p))
+                goto out_overflow;
+
         /* seqid */
-        READ32(dummy);
-        if (dummy != slot->seq_nr) {
+        dummy = be32_to_cpup(p++);
+        if (dummy != res->sr_slot->seq_nr) {
                 dprintk("%s Invalid sequence number\n", __func__);
                 goto out_err;
         }
         /* slot id */
-        READ32(dummy);
-        if (dummy != res->sr_slotid) {
+        dummy = be32_to_cpup(p++);
+        if (dummy != res->sr_slot - res->sr_session->fc_slot_table.slots) {
                 dprintk("%s Invalid slot id\n", __func__);
                 goto out_err;
         }
         /* highest slot id - currently not processed */
-        READ32(dummy);
+        dummy = be32_to_cpup(p++);
         /* target highest slot id - currently not processed */
-        READ32(dummy);
-        /* result flags - currently not processed */
-        READ32(dummy);
+        dummy = be32_to_cpup(p++);
+        /* result flags */
+        res->sr_status_flags = be32_to_cpup(p);
         status = 0;
 out_err:
         res->sr_status = status;
         return status;
+out_overflow:
+        print_overflow_msg(__func__, xdr);
+        status = -EIO;
+        goto out_err;
 #else  /* CONFIG_NFS_V4_1 */
         return 0;
 #endif /* CONFIG_NFS_V4_1 */
 }
 
+#if defined(CONFIG_NFS_V4_1)
+
+static int decode_getdeviceinfo(struct xdr_stream *xdr,
+                                struct pnfs_device *pdev)
+{
+        __be32 *p;
+        uint32_t len, type;
+        int status;
+
+        status = decode_op_hdr(xdr, OP_GETDEVICEINFO);
+        if (status) {
+                if (status == -ETOOSMALL) {
+                        p = xdr_inline_decode(xdr, 4);
+                        if (unlikely(!p))
+                                goto out_overflow;
+                        pdev->mincount = be32_to_cpup(p);
+                        dprintk("%s: Min count too small. mincnt = %u\n",
+                                __func__, pdev->mincount);
+                }
+                return status;
+        }
+
+        p = xdr_inline_decode(xdr, 8);
+        if (unlikely(!p))
+                goto out_overflow;
+        type = be32_to_cpup(p++);
+        if (type != pdev->layout_type) {
+                dprintk("%s: layout mismatch req: %u pdev: %u\n",
+                        __func__, pdev->layout_type, type);
+                return -EINVAL;
+        }
+        /*
+         * Get the length of the opaque device_addr4. xdr_read_pages places
+         * the opaque device_addr4 in the xdr_buf->pages (pnfs_device->pages)
+         * and places the remaining xdr data in xdr_buf->tail
+         */
+        pdev->mincount = be32_to_cpup(p);
+        xdr_read_pages(xdr, pdev->mincount); /* include space for the length */
+
+        /* Parse notification bitmap, verifying that it is zero. */
+        p = xdr_inline_decode(xdr, 4);
+        if (unlikely(!p))
+                goto out_overflow;
+        len = be32_to_cpup(p);
+        if (len) {
+                uint32_t i;
+
+                p = xdr_inline_decode(xdr, 4 * len);
+                if (unlikely(!p))
+                        goto out_overflow;
+                for (i = 0; i < len; i++, p++) {
+                        if (be32_to_cpup(p)) {
+                                dprintk("%s: notifications not supported\n",
+                                        __func__);
+                                return -EIO;
+                        }
+                }
+        }
+        return 0;
+out_overflow:
+        print_overflow_msg(__func__, xdr);
+        return -EIO;
+}
+
+static int decode_layoutget(struct xdr_stream *xdr, struct rpc_rqst *req,
+                            struct nfs4_layoutget_res *res)
+{
+        __be32 *p;
+        int status;
+        u32 layout_count;
+
+        status = decode_op_hdr(xdr, OP_LAYOUTGET);
+        if (status)
+                return status;
+        p = xdr_inline_decode(xdr, 8 + NFS4_STATEID_SIZE);
+        if (unlikely(!p))
+                goto out_overflow;
+        res->return_on_close = be32_to_cpup(p++);
+        p = xdr_decode_opaque_fixed(p, res->stateid.data, NFS4_STATEID_SIZE);
+        layout_count = be32_to_cpup(p);
+        if (!layout_count) {
+                dprintk("%s: server responded with empty layout array\n",
+                        __func__);
+                return -EINVAL;
+        }
+
+        p = xdr_inline_decode(xdr, 24);
+        if (unlikely(!p))
+                goto out_overflow;
+        p = xdr_decode_hyper(p, &res->range.offset);
+        p = xdr_decode_hyper(p, &res->range.length);
+        res->range.iomode = be32_to_cpup(p++);
+        res->type = be32_to_cpup(p++);
+
+        status = decode_opaque_inline(xdr, &res->layout.len, (char **)&p);
+        if (unlikely(status))
+                return status;
+
+        dprintk("%s roff:%lu rlen:%lu riomode:%d, lo_type:0x%x, lo.len:%d\n",
+                __func__,
+                (unsigned long)res->range.offset,
+                (unsigned long)res->range.length,
+                res->range.iomode,
+                res->type,
+                res->layout.len);
+
+        /* nfs4_proc_layoutget allocated a single page */
+        if (res->layout.len > PAGE_SIZE)
+                return -ENOMEM;
+        memcpy(res->layout.buf, p, res->layout.len);
+
+        if (layout_count > 1) {
+                /* We only handle a length one array at the moment.  Any
+                 * further entries are just ignored.  Note that this means
+                 * the client may see a response that is less than the
+                 * minimum it requested.
+                 */
+                dprintk("%s: server responded with %d layouts, dropping tail\n",
+                        __func__, layout_count);
+        }
+
+        return 0;
+out_overflow:
+        print_overflow_msg(__func__, xdr);
+        return -EIO;
+}
+#endif /* CONFIG_NFS_V4_1 */
+
 /*
  * END OF "GENERIC" DECODE ROUTINES.
  */
@@ -4351,26 +5012,27 @@ out_err:
 /*
  * Decode OPEN_DOWNGRADE response
  */
-static int nfs4_xdr_dec_open_downgrade(struct rpc_rqst *rqstp, __be32 *p, struct nfs_closeres *res)
+static int nfs4_xdr_dec_open_downgrade(struct rpc_rqst *rqstp,
+                                       struct xdr_stream *xdr,
+                                       struct nfs_closeres *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);
+        status = decode_compound_hdr(xdr, &hdr);
         if (status)
                 goto out;
-        status = decode_sequence(&xdr, &res->seq_res, rqstp);
+        status = decode_sequence(xdr, &res->seq_res, rqstp);
         if (status)
                 goto out;
-        status = decode_putfh(&xdr);
+        status = decode_putfh(xdr);
         if (status)
                 goto out;
-        status = decode_open_downgrade(&xdr, res);
+        status = decode_open_downgrade(xdr, res);
         if (status != 0)
                 goto out;
-        decode_getfattr(&xdr, res->fattr, res->server);
+        decode_getfattr(xdr, res->fattr, res->server,
+                        !RPC_IS_ASYNC(rqstp->rq_task));
 out:
         return status;
 }
@@ -4378,26 +5040,26 @@ out:
 /*
  * Decode ACCESS response
  */
-static int nfs4_xdr_dec_access(struct rpc_rqst *rqstp, __be32 *p, struct nfs4_accessres *res)
+static int nfs4_xdr_dec_access(struct rpc_rqst *rqstp, struct xdr_stream *xdr,
+                               struct nfs4_accessres *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);
+        status = decode_compound_hdr(xdr, &hdr);
         if (status)
                 goto out;
-        status = decode_sequence(&xdr, &res->seq_res, rqstp);
+        status = decode_sequence(xdr, &res->seq_res, rqstp);
         if (status)
                 goto out;
-        status = decode_putfh(&xdr);
+        status = decode_putfh(xdr);
         if (status != 0)
                 goto out;
-        status = decode_access(&xdr, res);
+        status = decode_access(xdr, res);
         if (status != 0)
                 goto out;
-        decode_getfattr(&xdr, res->fattr, res->server);
+        decode_getfattr(xdr, res->fattr, res->server,
+                        !RPC_IS_ASYNC(rqstp->rq_task));
 out:
         return status;
 }
@@ -4405,26 +5067,29 @@ out:
 /*
  * Decode LOOKUP response
  */
-static int nfs4_xdr_dec_lookup(struct rpc_rqst *rqstp, __be32 *p, struct nfs4_lookup_res *res)
+static int nfs4_xdr_dec_lookup(struct rpc_rqst *rqstp, struct xdr_stream *xdr,
+                               struct nfs4_lookup_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);
+        status = decode_compound_hdr(xdr, &hdr);
         if (status)
                 goto out;
-        status = decode_sequence(&xdr, &res->seq_res, rqstp);
+        status = decode_sequence(xdr, &res->seq_res, rqstp);
         if (status)
                 goto out;
-        if ((status = decode_putfh(&xdr)) != 0)
+        status = decode_putfh(xdr);
+        if (status)
                 goto out;
-        if ((status = decode_lookup(&xdr)) != 0)
+        status = decode_lookup(xdr);
+        if (status)
                 goto out;
-        if ((status = decode_getfh(&xdr, res->fh)) != 0)
+        status = decode_getfh(xdr, res->fh);
+        if (status)
                 goto out;
-        status = decode_getfattr(&xdr, res->fattr, res->server);
+        status = decode_getfattr(xdr, res->fattr, res->server
+                        ,!RPC_IS_ASYNC(rqstp->rq_task));
 out:
         return status;
 }
@@ -4432,23 +5097,26 @@ out:
 /*
  * Decode LOOKUP_ROOT response
  */
-static int nfs4_xdr_dec_lookup_root(struct rpc_rqst *rqstp, __be32 *p, struct nfs4_lookup_res *res)
+static int nfs4_xdr_dec_lookup_root(struct rpc_rqst *rqstp,
+                                    struct xdr_stream *xdr,
+                                    struct nfs4_lookup_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);
+        status = decode_compound_hdr(xdr, &hdr);
         if (status)
                 goto out;
-        status = decode_sequence(&xdr, &res->seq_res, rqstp);
+        status = decode_sequence(xdr, &res->seq_res, rqstp);
         if (status)
                 goto out;
-        if ((status = decode_putrootfh(&xdr)) != 0)
+        status = decode_putrootfh(xdr);
+        if (status)
                 goto out;
-        if ((status = decode_getfh(&xdr, res->fh)) == 0)
-                status = decode_getfattr(&xdr, res->fattr, res->server);
+        status = decode_getfh(xdr, res->fh);
+        if (status == 0)
+                status = decode_getfattr(xdr, res->fattr, res->server,
+                                !RPC_IS_ASYNC(rqstp->rq_task));
 out:
         return status;
 }
@@ -4456,24 +5124,26 @@ out:
 /*
  * Decode REMOVE response
  */
-static int nfs4_xdr_dec_remove(struct rpc_rqst *rqstp, __be32 *p, struct nfs_removeres *res)
+static int nfs4_xdr_dec_remove(struct rpc_rqst *rqstp, struct xdr_stream *xdr,
+                               struct nfs_removeres *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);
+        status = decode_compound_hdr(xdr, &hdr);
         if (status)
                 goto out;
-        status = decode_sequence(&xdr, &res->seq_res, rqstp);
+        status = decode_sequence(xdr, &res->seq_res, rqstp);
         if (status)
                 goto out;
-        if ((status = decode_putfh(&xdr)) != 0)
+        status = decode_putfh(xdr);
+        if (status)
                 goto out;
-        if ((status = decode_remove(&xdr, &res->cinfo)) != 0)
+        status = decode_remove(xdr, &res->cinfo);
+        if (status)
                 goto out;
-        decode_getfattr(&xdr, &res->dir_attr, res->server);
+        decode_getfattr(xdr, res->dir_attr, res->server,
+                        !RPC_IS_ASYNC(rqstp->rq_task));
 out:
         return status;
 }
@@ -4481,33 +5151,39 @@ out:
 /*
  * Decode RENAME response
  */
-static int nfs4_xdr_dec_rename(struct rpc_rqst *rqstp, __be32 *p, struct nfs4_rename_res *res)
+static int nfs4_xdr_dec_rename(struct rpc_rqst *rqstp, struct xdr_stream *xdr,
+                               struct nfs_renameres *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);
+        status = decode_compound_hdr(xdr, &hdr);
         if (status)
                 goto out;
-        status = decode_sequence(&xdr, &res->seq_res, rqstp);
+        status = decode_sequence(xdr, &res->seq_res, rqstp);
         if (status)
                 goto out;
-        if ((status = decode_putfh(&xdr)) != 0)
+        status = decode_putfh(xdr);
+        if (status)
                 goto out;
-        if ((status = decode_savefh(&xdr)) != 0)
+        status = decode_savefh(xdr);
+        if (status)
                 goto out;
-        if ((status = decode_putfh(&xdr)) != 0)
+        status = decode_putfh(xdr);
+        if (status)
                 goto out;
-        if ((status = decode_rename(&xdr, &res->old_cinfo, &res->new_cinfo)) != 0)
+        status = decode_rename(xdr, &res->old_cinfo, &res->new_cinfo);
+        if (status)
                 goto out;
         /* Current FH is target directory */
-        if (decode_getfattr(&xdr, res->new_fattr, res->server) != 0)
+        if (decode_getfattr(xdr, res->new_fattr, res->server,
+                                !RPC_IS_ASYNC(rqstp->rq_task)) != 0)
                 goto out;
-        if ((status = decode_restorefh(&xdr)) != 0)
+        status = decode_restorefh(xdr);
+        if (status)
                 goto out;
-        decode_getfattr(&xdr, res->old_fattr, res->server);
+        decode_getfattr(xdr, res->old_fattr, res->server,
+                        !RPC_IS_ASYNC(rqstp->rq_task));
 out:
         return status;
 }
@@ -4515,36 +5191,42 @@ out:
 /*
  * Decode LINK response
  */
-static int nfs4_xdr_dec_link(struct rpc_rqst *rqstp, __be32 *p, struct nfs4_link_res *res)
+static int nfs4_xdr_dec_link(struct rpc_rqst *rqstp, struct xdr_stream *xdr,
+                             struct nfs4_link_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);
+        status = decode_compound_hdr(xdr, &hdr);
         if (status)
                 goto out;
-        status = decode_sequence(&xdr, &res->seq_res, rqstp);
+        status = decode_sequence(xdr, &res->seq_res, rqstp);
         if (status)
                 goto out;
-        if ((status = decode_putfh(&xdr)) != 0)
+        status = decode_putfh(xdr);
+        if (status)
                 goto out;
-        if ((status = decode_savefh(&xdr)) != 0)
+        status = decode_savefh(xdr);
+        if (status)
                 goto out;
-        if ((status = decode_putfh(&xdr)) != 0)
+        status = decode_putfh(xdr);
+        if (status)
                 goto out;
-        if ((status = decode_link(&xdr, &res->cinfo)) != 0)
+        status = decode_link(xdr, &res->cinfo);
+        if (status)
                 goto out;
         /*
          * Note order: OP_LINK leaves the directory as the current
          *             filehandle.
          */
-        if (decode_getfattr(&xdr, res->dir_attr, res->server) != 0)
+        if (decode_getfattr(xdr, res->dir_attr, res->server,
+                                !RPC_IS_ASYNC(rqstp->rq_task)) != 0)
                 goto out;
-        if ((status = decode_restorefh(&xdr)) != 0)
+        status = decode_restorefh(xdr);
+        if (status)
                 goto out;
-        decode_getfattr(&xdr, res->fattr, res->server);
+        decode_getfattr(xdr, res->fattr, res->server,
+                        !RPC_IS_ASYNC(rqstp->rq_task));
 out:
         return status;
 }
@@ -4552,32 +5234,38 @@ out:
 /*
  * Decode CREATE response
  */
-static int nfs4_xdr_dec_create(struct rpc_rqst *rqstp, __be32 *p, struct nfs4_create_res *res)
+static int nfs4_xdr_dec_create(struct rpc_rqst *rqstp, struct xdr_stream *xdr,
+                               struct nfs4_create_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);
+        status = decode_compound_hdr(xdr, &hdr);
         if (status)
                 goto out;
-        status = decode_sequence(&xdr, &res->seq_res, rqstp);
+        status = decode_sequence(xdr, &res->seq_res, rqstp);
         if (status)
                 goto out;
-        if ((status = decode_putfh(&xdr)) != 0)
+        status = decode_putfh(xdr);
+        if (status)
                 goto out;
-        if ((status = decode_savefh(&xdr)) != 0)
+        status = decode_savefh(xdr);
+        if (status)
                 goto out;
-        if ((status = decode_create(&xdr,&res->dir_cinfo)) != 0)
+        status = decode_create(xdr, &res->dir_cinfo);
+        if (status)
                 goto out;
-        if ((status = decode_getfh(&xdr, res->fh)) != 0)
+        status = decode_getfh(xdr, res->fh);
+        if (status)
                 goto out;
-        if (decode_getfattr(&xdr, res->fattr, res->server) != 0)
+        if (decode_getfattr(xdr, res->fattr, res->server,
+                                !RPC_IS_ASYNC(rqstp->rq_task)) != 0)
                 goto out;
-        if ((status = decode_restorefh(&xdr)) != 0)
+        status = decode_restorefh(xdr);
+        if (status)
                 goto out;
-        decode_getfattr(&xdr, res->dir_fattr, res->server);
+        decode_getfattr(xdr, res->dir_fattr, res->server,
+                        !RPC_IS_ASYNC(rqstp->rq_task));
 out:
         return status;
 }
@@ -4585,31 +5273,32 @@ out:
 /*
  * Decode SYMLINK response
  */
-static int nfs4_xdr_dec_symlink(struct rpc_rqst *rqstp, __be32 *p, struct nfs4_create_res *res)
+static int nfs4_xdr_dec_symlink(struct rpc_rqst *rqstp, struct xdr_stream *xdr,
+                                struct nfs4_create_res *res)
 {
-        return nfs4_xdr_dec_create(rqstp, p, res);
+        return nfs4_xdr_dec_create(rqstp, xdr, res);
 }
 
 /*
  * Decode GETATTR response
  */
-static int nfs4_xdr_dec_getattr(struct rpc_rqst *rqstp, __be32 *p, struct nfs4_getattr_res *res)
+static int nfs4_xdr_dec_getattr(struct rpc_rqst *rqstp, struct xdr_stream *xdr,
+                                struct nfs4_getattr_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);
+        status = decode_compound_hdr(xdr, &hdr);
         if (status)
                 goto out;
-        status = decode_sequence(&xdr, &res->seq_res, rqstp);
+        status = decode_sequence(xdr, &res->seq_res, rqstp);
         if (status)
                 goto out;
-        status = decode_putfh(&xdr);
+        status = decode_putfh(xdr);
         if (status)
                 goto out;
-        status = decode_getfattr(&xdr, res->fattr, res->server);
+        status = decode_getfattr(xdr, res->fattr, res->server,
+                        !RPC_IS_ASYNC(rqstp->rq_task));
 out:
         return status;
 }
@@ -4617,46 +5306,40 @@ out:
 /*
  * Encode an SETACL request
  */
-static int
-nfs4_xdr_enc_setacl(struct rpc_rqst *req, __be32 *p, struct nfs_setaclargs *args)
+static void nfs4_xdr_enc_setacl(struct rpc_rqst *req, struct xdr_stream *xdr,
+                                struct nfs_setaclargs *args)
 {
-        struct xdr_stream xdr;
         struct compound_hdr hdr = {
                 .minorversion = nfs4_xdr_minorversion(&args->seq_args),
         };
-        int status;
 
-        xdr_init_encode(&xdr, &req->rq_snd_buf, p);
-        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_compound_hdr(xdr, req, &hdr);
+        encode_sequence(xdr, &args->seq_args, &hdr);
+        encode_putfh(xdr, args->fh, &hdr);
+        encode_setacl(xdr, args, &hdr);
         encode_nops(&hdr);
-        return status;
 }
 
 /*
  * Decode SETACL response
  */
 static int
-nfs4_xdr_dec_setacl(struct rpc_rqst *rqstp, __be32 *p,
+nfs4_xdr_dec_setacl(struct rpc_rqst *rqstp, struct xdr_stream *xdr,
                     struct nfs_setaclres *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);
+        status = decode_compound_hdr(xdr, &hdr);
         if (status)
                 goto out;
-        status = decode_sequence(&xdr, &res->seq_res, rqstp);
+        status = decode_sequence(xdr, &res->seq_res, rqstp);
         if (status)
                 goto out;
-        status = decode_putfh(&xdr);
+        status = decode_putfh(xdr);
         if (status)
                 goto out;
-        status = decode_setattr(&xdr);
+        status = decode_setattr(xdr);
 out:
         return status;
 }
@@ -4665,24 +5348,22 @@ out:
  * Decode GETACL response
  */
 static int
-nfs4_xdr_dec_getacl(struct rpc_rqst *rqstp, __be32 *p,
+nfs4_xdr_dec_getacl(struct rpc_rqst *rqstp, struct xdr_stream *xdr,
                     struct nfs_getaclres *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);
+        status = decode_compound_hdr(xdr, &hdr);
         if (status)
                 goto out;
-        status = decode_sequence(&xdr, &res->seq_res, rqstp);
+        status = decode_sequence(xdr, &res->seq_res, rqstp);
         if (status)
                 goto out;
-        status = decode_putfh(&xdr);
+        status = decode_putfh(xdr);
         if (status)
                 goto out;
-        status = decode_getacl(&xdr, rqstp, &res->acl_len);
+        status = decode_getacl(xdr, rqstp, &res->acl_len);
 
 out:
         return status;
@@ -4691,23 +5372,22 @@ out:
 /*
  * Decode CLOSE response
  */
-static int nfs4_xdr_dec_close(struct rpc_rqst *rqstp, __be32 *p, struct nfs_closeres *res)
+static int nfs4_xdr_dec_close(struct rpc_rqst *rqstp, struct xdr_stream *xdr,
+                              struct nfs_closeres *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);
+        status = decode_compound_hdr(xdr, &hdr);
         if (status)
                 goto out;
-        status = decode_sequence(&xdr, &res->seq_res, rqstp);
+        status = decode_sequence(xdr, &res->seq_res, rqstp);
         if (status)
                 goto out;
-        status = decode_putfh(&xdr);
+        status = decode_putfh(xdr);
         if (status)
                 goto out;
-        status = decode_close(&xdr, res);
+        status = decode_close(xdr, res);
         if (status != 0)
                 goto out;
         /*
@@ -4716,7 +5396,8 @@ static int nfs4_xdr_dec_close(struct rpc_rqst *rqstp, __be32 *p, struct nfs_clos
          *      an ESTALE error. Shouldn't be a problem,
          *      though, since fattr->valid will remain unset.
          */
-        decode_getfattr(&xdr, res->fattr, res->server);
+        decode_getfattr(xdr, res->fattr, res->server,
+                        !RPC_IS_ASYNC(rqstp->rq_task));
 out:
         return status;
 }
@@ -4724,35 +5405,36 @@ out:
 /*
  * Decode OPEN response
  */
-static int nfs4_xdr_dec_open(struct rpc_rqst *rqstp, __be32 *p, struct nfs_openres *res)
+static int nfs4_xdr_dec_open(struct rpc_rqst *rqstp, struct xdr_stream *xdr,
+                             struct nfs_openres *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);
+        status = decode_compound_hdr(xdr, &hdr);
         if (status)
                 goto out;
-        status = decode_sequence(&xdr, &res->seq_res, rqstp);
+        status = decode_sequence(xdr, &res->seq_res, rqstp);
         if (status)
                 goto out;
-        status = decode_putfh(&xdr);
+        status = decode_putfh(xdr);
         if (status)
                 goto out;
-        status = decode_savefh(&xdr);
+        status = decode_savefh(xdr);
         if (status)
                 goto out;
-        status = decode_open(&xdr, res);
+        status = decode_open(xdr, res);
         if (status)
                 goto out;
-        if (decode_getfh(&xdr, &res->fh) != 0)
+        if (decode_getfh(xdr, &res->fh) != 0)
                 goto out;
-        if (decode_getfattr(&xdr, res->f_attr, res->server) != 0)
+        if (decode_getfattr(xdr, res->f_attr, res->server,
+                                !RPC_IS_ASYNC(rqstp->rq_task)) != 0)
                 goto out;
-        if (decode_restorefh(&xdr) != 0)
+        if (decode_restorefh(xdr) != 0)
                 goto out;
-        decode_getfattr(&xdr, res->dir_attr, res->server);
+        decode_getfattr(xdr, res->dir_attr, res->server,
+                        !RPC_IS_ASYNC(rqstp->rq_task));
 out:
         return status;
 }
@@ -4760,20 +5442,20 @@ out:
 /*
  * Decode OPEN_CONFIRM response
  */
-static int nfs4_xdr_dec_open_confirm(struct rpc_rqst *rqstp, __be32 *p, struct nfs_open_confirmres *res)
+static int nfs4_xdr_dec_open_confirm(struct rpc_rqst *rqstp,
+                                     struct xdr_stream *xdr,
+                                     struct nfs_open_confirmres *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);
+        status = decode_compound_hdr(xdr, &hdr);
         if (status)
                 goto out;
-        status = decode_putfh(&xdr);
+        status = decode_putfh(xdr);
         if (status)
                 goto out;
-        status = decode_open_confirm(&xdr, res);
+        status = decode_open_confirm(xdr, res);
 out:
         return status;
 }
@@ -4781,26 +5463,27 @@ out:
 /*
  * Decode OPEN response
  */
-static int nfs4_xdr_dec_open_noattr(struct rpc_rqst *rqstp, __be32 *p, struct nfs_openres *res)
+static int nfs4_xdr_dec_open_noattr(struct rpc_rqst *rqstp,
+                                    struct xdr_stream *xdr,
+                                    struct nfs_openres *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);
+        status = decode_compound_hdr(xdr, &hdr);
         if (status)
                 goto out;
-        status = decode_sequence(&xdr, &res->seq_res, rqstp);
+        status = decode_sequence(xdr, &res->seq_res, rqstp);
         if (status)
                 goto out;
-        status = decode_putfh(&xdr);
+        status = decode_putfh(xdr);
         if (status)
                 goto out;
-        status = decode_open(&xdr, res);
+        status = decode_open(xdr, res);
         if (status)
                 goto out;
-        decode_getfattr(&xdr, res->f_attr, res->server);
+        decode_getfattr(xdr, res->f_attr, res->server,
+                        !RPC_IS_ASYNC(rqstp->rq_task));
 out:
         return status;
 }
@@ -4808,26 +5491,27 @@ out:
 /*
  * Decode SETATTR response
  */
-static int nfs4_xdr_dec_setattr(struct rpc_rqst *rqstp, __be32 *p, struct nfs_setattrres *res)
+static int nfs4_xdr_dec_setattr(struct rpc_rqst *rqstp,
+                                struct xdr_stream *xdr,
+                                struct nfs_setattrres *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);
+        status = decode_compound_hdr(xdr, &hdr);
         if (status)
                 goto out;
-        status = decode_sequence(&xdr, &res->seq_res, rqstp);
+        status = decode_sequence(xdr, &res->seq_res, rqstp);
         if (status)
                 goto out;
-        status = decode_putfh(&xdr);
+        status = decode_putfh(xdr);
         if (status)
                 goto out;
-        status = decode_setattr(&xdr);
+        status = decode_setattr(xdr);
         if (status)
                 goto out;
-        decode_getfattr(&xdr, res->fattr, res->server);
+        decode_getfattr(xdr, res->fattr, res->server,
+                        !RPC_IS_ASYNC(rqstp->rq_task));
 out:
         return status;
 }
@@ -4835,23 +5519,22 @@ out:
 /*
  * Decode LOCK response
  */
-static int nfs4_xdr_dec_lock(struct rpc_rqst *rqstp, __be32 *p, struct nfs_lock_res *res)
+static int nfs4_xdr_dec_lock(struct rpc_rqst *rqstp, struct xdr_stream *xdr,
+                             struct nfs_lock_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);
+        status = decode_compound_hdr(xdr, &hdr);
         if (status)
                 goto out;
-        status = decode_sequence(&xdr, &res->seq_res, rqstp);
+        status = decode_sequence(xdr, &res->seq_res, rqstp);
         if (status)
                 goto out;
-        status = decode_putfh(&xdr);
+        status = decode_putfh(xdr);
         if (status)
                 goto out;
-        status = decode_lock(&xdr, res);
+        status = decode_lock(xdr, res);
 out:
         return status;
 }
@@ -4859,23 +5542,22 @@ out:
 /*
  * Decode LOCKT response
  */
-static int nfs4_xdr_dec_lockt(struct rpc_rqst *rqstp, __be32 *p, struct nfs_lockt_res *res)
+static int nfs4_xdr_dec_lockt(struct rpc_rqst *rqstp, struct xdr_stream *xdr,
+                              struct nfs_lockt_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);
+        status = decode_compound_hdr(xdr, &hdr);
         if (status)
                 goto out;
-        status = decode_sequence(&xdr, &res->seq_res, rqstp);
+        status = decode_sequence(xdr, &res->seq_res, rqstp);
         if (status)
                 goto out;
-        status = decode_putfh(&xdr);
+        status = decode_putfh(xdr);
         if (status)
                 goto out;
-        status = decode_lockt(&xdr, res);
+        status = decode_lockt(xdr, res);
 out:
         return status;
 }
@@ -4883,48 +5565,58 @@ out:
 /*
  * Decode LOCKU response
  */
-static int nfs4_xdr_dec_locku(struct rpc_rqst *rqstp, __be32 *p, struct nfs_locku_res *res)
+static int nfs4_xdr_dec_locku(struct rpc_rqst *rqstp, struct xdr_stream *xdr,
+                              struct nfs_locku_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);
+        status = decode_compound_hdr(xdr, &hdr);
         if (status)
                 goto out;
-        status = decode_sequence(&xdr, &res->seq_res, rqstp);
+        status = decode_sequence(xdr, &res->seq_res, rqstp);
         if (status)
                 goto out;
-        status = decode_putfh(&xdr);
+        status = decode_putfh(xdr);
         if (status)
                 goto out;
-        status = decode_locku(&xdr, res);
+        status = decode_locku(xdr, res);
 out:
         return status;
 }
 
+static int nfs4_xdr_dec_release_lockowner(struct rpc_rqst *rqstp,
+                                          struct xdr_stream *xdr, void *dummy)
+{
+        struct compound_hdr hdr;
+        int status;
+
+        status = decode_compound_hdr(xdr, &hdr);
+        if (!status)
+                status = decode_release_lockowner(xdr);
+        return status;
+}
+
 /*
  * Decode READLINK response
  */
-static int nfs4_xdr_dec_readlink(struct rpc_rqst *rqstp, __be32 *p,
+static int nfs4_xdr_dec_readlink(struct rpc_rqst *rqstp,
+                                 struct xdr_stream *xdr,
                                  struct nfs4_readlink_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);
+        status = decode_compound_hdr(xdr, &hdr);
         if (status)
                 goto out;
-        status = decode_sequence(&xdr, &res->seq_res, rqstp);
+        status = decode_sequence(xdr, &res->seq_res, rqstp);
         if (status)
                 goto out;
-        status = decode_putfh(&xdr);
+        status = decode_putfh(xdr);
         if (status)
                 goto out;
-        status = decode_readlink(&xdr, rqstp);
+        status = decode_readlink(xdr, rqstp);
 out:
         return status;
 }
@@ -4932,23 +5624,22 @@ out:
 /*
  * Decode READDIR response
  */
-static int nfs4_xdr_dec_readdir(struct rpc_rqst *rqstp, __be32 *p, struct nfs4_readdir_res *res)
+static int nfs4_xdr_dec_readdir(struct rpc_rqst *rqstp, struct xdr_stream *xdr,
+                                struct nfs4_readdir_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);
+        status = decode_compound_hdr(xdr, &hdr);
         if (status)
                 goto out;
-        status = decode_sequence(&xdr, &res->seq_res, rqstp);
+        status = decode_sequence(xdr, &res->seq_res, rqstp);
         if (status)
                 goto out;
-        status = decode_putfh(&xdr);
+        status = decode_putfh(xdr);
         if (status)
                 goto out;
-        status = decode_readdir(&xdr, rqstp, res);
+        status = decode_readdir(xdr, rqstp, res);
 out:
         return status;
 }
@@ -4956,23 +5647,22 @@ out:
 /*
  * Decode Read response
  */
-static int nfs4_xdr_dec_read(struct rpc_rqst *rqstp, __be32 *p, struct nfs_readres *res)
+static int nfs4_xdr_dec_read(struct rpc_rqst *rqstp, struct xdr_stream *xdr,
+                             struct nfs_readres *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);
+        status = decode_compound_hdr(xdr, &hdr);
         if (status)
                 goto out;
-        status = decode_sequence(&xdr, &res->seq_res, rqstp);
+        status = decode_sequence(xdr, &res->seq_res, rqstp);
         if (status)
                 goto out;
-        status = decode_putfh(&xdr);
+        status = decode_putfh(xdr);
         if (status)
                 goto out;
-        status = decode_read(&xdr, rqstp, res);
+        status = decode_read(xdr, rqstp, res);
         if (!status)
                 status = res->count;
 out:
@@ -4982,26 +5672,26 @@ out:
 /*
  * Decode WRITE response
  */
-static int nfs4_xdr_dec_write(struct rpc_rqst *rqstp, __be32 *p, struct nfs_writeres *res)
+static int nfs4_xdr_dec_write(struct rpc_rqst *rqstp, struct xdr_stream *xdr,
+                              struct nfs_writeres *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);
+        status = decode_compound_hdr(xdr, &hdr);
         if (status)
                 goto out;
-        status = decode_sequence(&xdr, &res->seq_res, rqstp);
+        status = decode_sequence(xdr, &res->seq_res, rqstp);
         if (status)
                 goto out;
-        status = decode_putfh(&xdr);
+        status = decode_putfh(xdr);
         if (status)
                 goto out;
-        status = decode_write(&xdr, res);
+        status = decode_write(xdr, res);
         if (status)
                 goto out;
-        decode_getfattr(&xdr, res->fattr, res->server);
+        decode_getfattr(xdr, res->fattr, res->server,
+                        !RPC_IS_ASYNC(rqstp->rq_task));
         if (!status)
                 status = res->count;
 out:
@@ -5011,112 +5701,107 @@ out:
 /*
  * Decode COMMIT response
  */
-static int nfs4_xdr_dec_commit(struct rpc_rqst *rqstp, __be32 *p, struct nfs_writeres *res)
+static int nfs4_xdr_dec_commit(struct rpc_rqst *rqstp, struct xdr_stream *xdr,
+                               struct nfs_writeres *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);
+        status = decode_compound_hdr(xdr, &hdr);
         if (status)
                 goto out;
-        status = decode_sequence(&xdr, &res->seq_res, rqstp);
+        status = decode_sequence(xdr, &res->seq_res, rqstp);
         if (status)
                 goto out;
-        status = decode_putfh(&xdr);
+        status = decode_putfh(xdr);
         if (status)
                 goto out;
-        status = decode_commit(&xdr, res);
+        status = decode_commit(xdr, res);
         if (status)
                 goto out;
-        decode_getfattr(&xdr, res->fattr, res->server);
+        decode_getfattr(xdr, res->fattr, res->server,
+                        !RPC_IS_ASYNC(rqstp->rq_task));
 out:
         return status;
 }
 
 /*
- * FSINFO request
+ * Decode FSINFO response
  */
-static int nfs4_xdr_dec_fsinfo(struct rpc_rqst *req, __be32 *p,
+static int nfs4_xdr_dec_fsinfo(struct rpc_rqst *req, struct xdr_stream *xdr,
                                struct nfs4_fsinfo_res *res)
 {
-        struct xdr_stream xdr;
         struct compound_hdr hdr;
         int status;
 
-        xdr_init_decode(&xdr, &req->rq_rcv_buf, p);
-        status = decode_compound_hdr(&xdr, &hdr);
+        status = decode_compound_hdr(xdr, &hdr);
         if (!status)
-                status = decode_sequence(&xdr, &res->seq_res, req);
+                status = decode_sequence(xdr, &res->seq_res, req);
         if (!status)
-                status = decode_putfh(&xdr);
+                status = decode_putfh(xdr);
         if (!status)
-                status = decode_fsinfo(&xdr, res->fsinfo);
+                status = decode_fsinfo(xdr, res->fsinfo);
         return status;
 }
 
 /*
- * PATHCONF request
+ * Decode PATHCONF response
  */
-static int nfs4_xdr_dec_pathconf(struct rpc_rqst *req, __be32 *p,
+static int nfs4_xdr_dec_pathconf(struct rpc_rqst *req, struct xdr_stream *xdr,
                                  struct nfs4_pathconf_res *res)
 {
-        struct xdr_stream xdr;
         struct compound_hdr hdr;
         int status;
 
-        xdr_init_decode(&xdr, &req->rq_rcv_buf, p);
-        status = decode_compound_hdr(&xdr, &hdr);
+        status = decode_compound_hdr(xdr, &hdr);
         if (!status)
-                status = decode_sequence(&xdr, &res->seq_res, req);
+                status = decode_sequence(xdr, &res->seq_res, req);
         if (!status)
-                status = decode_putfh(&xdr);
+                status = decode_putfh(xdr);
         if (!status)
-                status = decode_pathconf(&xdr, res->pathconf);
+                status = decode_pathconf(xdr, res->pathconf);
         return status;
 }
 
 /*
- * STATFS request
+ * Decode STATFS response
  */
-static int nfs4_xdr_dec_statfs(struct rpc_rqst *req, __be32 *p,
+static int nfs4_xdr_dec_statfs(struct rpc_rqst *req, struct xdr_stream *xdr,
                                struct nfs4_statfs_res *res)
 {
-        struct xdr_stream xdr;
         struct compound_hdr hdr;
         int status;
 
-        xdr_init_decode(&xdr, &req->rq_rcv_buf, p);
-        status = decode_compound_hdr(&xdr, &hdr);
+        status = decode_compound_hdr(xdr, &hdr);
         if (!status)
-                status = decode_sequence(&xdr, &res->seq_res, req);
+                status = decode_sequence(xdr, &res->seq_res, req);
         if (!status)
-                status = decode_putfh(&xdr);
+                status = decode_putfh(xdr);
         if (!status)
-                status = decode_statfs(&xdr, res->fsstat);
+                status = decode_statfs(xdr, res->fsstat);
         return status;
 }
 
 /*
- * GETATTR_BITMAP request
+ * Decode GETATTR_BITMAP response
  */
-static int nfs4_xdr_dec_server_caps(struct rpc_rqst *req, __be32 *p, struct nfs4_server_caps_res *res)
+static int nfs4_xdr_dec_server_caps(struct rpc_rqst *req,
+                                    struct xdr_stream *xdr,
+                                    struct nfs4_server_caps_res *res)
 {
-        struct xdr_stream xdr;
         struct compound_hdr hdr;
         int status;
 
-        xdr_init_decode(&xdr, &req->rq_rcv_buf, p);
-        status = decode_compound_hdr(&xdr, &hdr);
+        status = decode_compound_hdr(xdr, &hdr);
         if (status)
                 goto out;
-        status = decode_sequence(&xdr, &res->seq_res, req);
+        status = decode_sequence(xdr, &res->seq_res, req);
         if (status)
                 goto out;
-        if ((status = decode_putfh(&xdr)) != 0)
+        status = decode_putfh(xdr);
+        if (status)
                 goto out;
-        status = decode_server_caps(&xdr, res);
+        status = decode_server_caps(xdr, res);
 out:
         return status;
 }
@@ -5124,217 +5809,304 @@ out:
 /*
  * Decode RENEW response
  */
-static int nfs4_xdr_dec_renew(struct rpc_rqst *rqstp, __be32 *p, void *dummy)
+static int nfs4_xdr_dec_renew(struct rpc_rqst *rqstp, struct xdr_stream *xdr,
+                              void *__unused)
 {
-        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);
+        status = decode_compound_hdr(xdr, &hdr);
         if (!status)
-                status = decode_renew(&xdr);
+                status = decode_renew(xdr);
         return status;
 }
 
 /*
- * a SETCLIENTID request
+ * Decode SETCLIENTID response
  */
-static int nfs4_xdr_dec_setclientid(struct rpc_rqst *req, __be32 *p,
-                struct nfs_client *clp)
+static int nfs4_xdr_dec_setclientid(struct rpc_rqst *req,
+                                    struct xdr_stream *xdr,
+                                    struct nfs4_setclientid_res *res)
 {
-        struct xdr_stream xdr;
         struct compound_hdr hdr;
         int status;
 
-        xdr_init_decode(&xdr, &req->rq_rcv_buf, p);
-        status = decode_compound_hdr(&xdr, &hdr);
+        status = decode_compound_hdr(xdr, &hdr);
         if (!status)
-                status = decode_setclientid(&xdr, clp);
+                status = decode_setclientid(xdr, res);
         return status;
 }
 
 /*
- * a SETCLIENTID_CONFIRM request
+ * Decode SETCLIENTID_CONFIRM response
  */
-static int nfs4_xdr_dec_setclientid_confirm(struct rpc_rqst *req, __be32 *p, struct nfs_fsinfo *fsinfo)
+static int nfs4_xdr_dec_setclientid_confirm(struct rpc_rqst *req,
+                                            struct xdr_stream *xdr,
+                                            struct nfs_fsinfo *fsinfo)
 {
-        struct xdr_stream xdr;
         struct compound_hdr hdr;
         int status;
 
-        xdr_init_decode(&xdr, &req->rq_rcv_buf, p);
-        status = decode_compound_hdr(&xdr, &hdr);
+        status = decode_compound_hdr(xdr, &hdr);
         if (!status)
-                status = decode_setclientid_confirm(&xdr);
+                status = decode_setclientid_confirm(xdr);
         if (!status)
-                status = decode_putrootfh(&xdr);
+                status = decode_putrootfh(xdr);
         if (!status)
-                status = decode_fsinfo(&xdr, fsinfo);
+                status = decode_fsinfo(xdr, fsinfo);
         return status;
 }
 
 /*
- * DELEGRETURN request
+ * Decode DELEGRETURN response
  */
-static int nfs4_xdr_dec_delegreturn(struct rpc_rqst *rqstp, __be32 *p, struct nfs4_delegreturnres *res)
+static int nfs4_xdr_dec_delegreturn(struct rpc_rqst *rqstp,
+                                    struct xdr_stream *xdr,
+                                    struct nfs4_delegreturnres *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);
+        status = decode_compound_hdr(xdr, &hdr);
         if (status)
                 goto out;
-        status = decode_sequence(&xdr, &res->seq_res, rqstp);
+        status = decode_sequence(xdr, &res->seq_res, rqstp);
         if (status)
                 goto out;
-        status = decode_putfh(&xdr);
+        status = decode_putfh(xdr);
+        if (status != 0)
+                goto out;
+        status = decode_delegreturn(xdr);
         if (status != 0)
                 goto out;
-        status = decode_delegreturn(&xdr);
-        decode_getfattr(&xdr, res->fattr, res->server);
+        decode_getfattr(xdr, res->fattr, res->server,
+                        !RPC_IS_ASYNC(rqstp->rq_task));
 out:
         return status;
 }
 
 /*
- * FS_LOCATIONS request
+ * Decode FS_LOCATIONS response
  */
-static int nfs4_xdr_dec_fs_locations(struct rpc_rqst *req, __be32 *p,
+static int nfs4_xdr_dec_fs_locations(struct rpc_rqst *req,
+                                     struct xdr_stream *xdr,
                                      struct nfs4_fs_locations_res *res)
 {
-        struct xdr_stream xdr;
         struct compound_hdr hdr;
         int status;
 
-        xdr_init_decode(&xdr, &req->rq_rcv_buf, p);
-        status = decode_compound_hdr(&xdr, &hdr);
+        status = decode_compound_hdr(xdr, &hdr);
         if (status)
                 goto out;
-        status = decode_sequence(&xdr, &res->seq_res, req);
+        status = decode_sequence(xdr, &res->seq_res, req);
         if (status)
                 goto out;
-        if ((status = decode_putfh(&xdr)) != 0)
+        status = decode_putfh(xdr);
+        if (status)
                 goto out;
-        if ((status = decode_lookup(&xdr)) != 0)
+        status = decode_lookup(xdr);
+        if (status)
                 goto out;
-        xdr_enter_page(&xdr, PAGE_SIZE);
-        status = decode_getfattr(&xdr, &res->fs_locations->fattr,
-                                 res->fs_locations->server);
+        xdr_enter_page(xdr, PAGE_SIZE);
+        status = decode_getfattr(xdr, &res->fs_locations->fattr,
+                                 res->fs_locations->server,
+                                 !RPC_IS_ASYNC(req->rq_task));
 out:
         return status;
 }
 
 #if defined(CONFIG_NFS_V4_1)
 /*
- * EXCHANGE_ID request
+ * Decode EXCHANGE_ID response
  */
-static int nfs4_xdr_dec_exchange_id(struct rpc_rqst *rqstp, uint32_t *p,
+static int nfs4_xdr_dec_exchange_id(struct rpc_rqst *rqstp,
+                                    struct xdr_stream *xdr,
                                     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);
+        status = decode_compound_hdr(xdr, &hdr);
         if (!status)
-                status = decode_exchange_id(&xdr, res);
+                status = decode_exchange_id(xdr, res);
         return status;
 }
 
 /*
- * a CREATE_SESSION request
+ * Decode CREATE_SESSION response
  */
-static int nfs4_xdr_dec_create_session(struct rpc_rqst *rqstp, uint32_t *p,
+static int nfs4_xdr_dec_create_session(struct rpc_rqst *rqstp,
+                                       struct xdr_stream *xdr,
                                        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);
+        status = decode_compound_hdr(xdr, &hdr);
         if (!status)
-                status = decode_create_session(&xdr, res);
+                status = decode_create_session(xdr, res);
         return status;
 }
 
 /*
- * a DESTROY_SESSION request
+ * Decode DESTROY_SESSION response
  */
-static int nfs4_xdr_dec_destroy_session(struct rpc_rqst *rqstp, uint32_t *p,
-                                        void *dummy)
+static int nfs4_xdr_dec_destroy_session(struct rpc_rqst *rqstp,
+                                        struct xdr_stream *xdr,
+                                        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);
+        status = decode_compound_hdr(xdr, &hdr);
         if (!status)
-                status = decode_destroy_session(&xdr, dummy);
+                status = decode_destroy_session(xdr, res);
         return status;
 }
 
 /*
- * a SEQUENCE request
+ * Decode SEQUENCE response
  */
-static int nfs4_xdr_dec_sequence(struct rpc_rqst *rqstp, uint32_t *p,
+static int nfs4_xdr_dec_sequence(struct rpc_rqst *rqstp,
+                                 struct xdr_stream *xdr,
                                  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);
+        status = decode_compound_hdr(xdr, &hdr);
         if (!status)
-                status = decode_sequence(&xdr, res, rqstp);
+                status = decode_sequence(xdr, res, rqstp);
         return status;
 }
 
 /*
- * a GET_LEASE_TIME request
+ * Decode GET_LEASE_TIME response
  */
-static int nfs4_xdr_dec_get_lease_time(struct rpc_rqst *rqstp, uint32_t *p,
+static int nfs4_xdr_dec_get_lease_time(struct rpc_rqst *rqstp,
+                                       struct xdr_stream *xdr,
                                        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);
+        status = decode_compound_hdr(xdr, &hdr);
+        if (!status)
+                status = decode_sequence(xdr, &res->lr_seq_res, rqstp);
         if (!status)
-                status = decode_sequence(&xdr, &res->lr_seq_res, rqstp);
+                status = decode_putrootfh(xdr);
+        if (!status)
+                status = decode_fsinfo(xdr, res->lr_fsinfo);
+        return status;
+}
+
+/*
+ * Decode RECLAIM_COMPLETE response
+ */
+static int nfs4_xdr_dec_reclaim_complete(struct rpc_rqst *rqstp,
+                                         struct xdr_stream *xdr,
+                                         struct nfs41_reclaim_complete_res *res)
+{
+        struct compound_hdr hdr;
+        int status;
+
+        status = decode_compound_hdr(xdr, &hdr);
         if (!status)
-                status = decode_putrootfh(&xdr);
+                status = decode_sequence(xdr, &res->seq_res, rqstp);
         if (!status)
-                status = decode_fsinfo(&xdr, res->lr_fsinfo);
+                status = decode_reclaim_complete(xdr, (void *)NULL);
+        return status;
+}
+
+/*
+ * Decode GETDEVINFO response
+ */
+static int nfs4_xdr_dec_getdeviceinfo(struct rpc_rqst *rqstp,
+                                      struct xdr_stream *xdr,
+                                      struct nfs4_getdeviceinfo_res *res)
+{
+        struct compound_hdr hdr;
+        int status;
+
+        status = decode_compound_hdr(xdr, &hdr);
+        if (status != 0)
+                goto out;
+        status = decode_sequence(xdr, &res->seq_res, rqstp);
+        if (status != 0)
+                goto out;
+        status = decode_getdeviceinfo(xdr, res->pdev);
+out:
+        return status;
+}
+
+/*
+ * Decode LAYOUTGET response
+ */
+static int nfs4_xdr_dec_layoutget(struct rpc_rqst *rqstp,
+                                  struct xdr_stream *xdr,
+                                  struct nfs4_layoutget_res *res)
+{
+        struct compound_hdr hdr;
+        int status;
+
+        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_layoutget(xdr, rqstp, res);
+out:
         return status;
 }
 #endif /* CONFIG_NFS_V4_1 */
 
-__be32 *nfs4_decode_dirent(__be32 *p, struct nfs_entry *entry, int plus)
+/**
+ * nfs4_decode_dirent - Decode a single NFSv4 directory entry stored in
+ *                      the local page cache.
+ * @xdr: XDR stream where entry resides
+ * @entry: buffer to fill in with entry data
+ * @plus: boolean indicating whether this should be a readdirplus entry
+ *
+ * Returns zero if successful, otherwise a negative errno value is
+ * returned.
+ *
+ * This function is not invoked during READDIR reply decoding, but
+ * rather whenever an application invokes the getdents(2) system call
+ * on a directory already in our cache.
+ */
+int nfs4_decode_dirent(struct xdr_stream *xdr, struct nfs_entry *entry,
+                       int plus)
 {
         uint32_t bitmap[2] = {0};
         uint32_t len;
-
-        if (!*p++) {
-                if (!*p)
-                        return ERR_PTR(-EAGAIN);
+        __be32 *p = xdr_inline_decode(xdr, 4);
+        if (unlikely(!p))
+                goto out_overflow;
+        if (!ntohl(*p++)) {
+                p = xdr_inline_decode(xdr, 4);
+                if (unlikely(!p))
+                        goto out_overflow;
+                if (!ntohl(*p++))
+                        return -EAGAIN;
                 entry->eof = 1;
-                return ERR_PTR(-EBADCOOKIE);
+                return -EBADCOOKIE;
         }
 
+        p = xdr_inline_decode(xdr, 12);
+        if (unlikely(!p))
+                goto out_overflow;
         entry->prev_cookie = entry->cookie;
         p = xdr_decode_hyper(p, &entry->cookie);
         entry->len = ntohl(*p++);
+
+        p = xdr_inline_decode(xdr, entry->len);
+        if (unlikely(!p))
+                goto out_overflow;
         entry->name = (const char *) p;
-        p += XDR_QUADLEN(entry->len);
 
         /*
          * In case the server doesn't return an inode number,
@@ -5342,32 +6114,32 @@ __be32 *nfs4_decode_dirent(__be32 *p, struct nfs_entry *entry, int plus)
          * since glibc seems to choke on it...)
          */
         entry->ino = 1;
+        entry->fattr->valid = 0;
 
-        len = ntohl(*p++);              /* bitmap length */
-        if (len-- > 0) {
-                bitmap[0] = ntohl(*p++);
-                if (len-- > 0) {
-                        bitmap[1] = ntohl(*p++);
-                        p += len;
-                }
-        }
-        len = XDR_QUADLEN(ntohl(*p++)); /* attribute buffer length */
-        if (len > 0) {
-                if (bitmap[0] & FATTR4_WORD0_RDATTR_ERROR) {
-                        bitmap[0] &= ~FATTR4_WORD0_RDATTR_ERROR;
-                        /* Ignore the return value of rdattr_error for now */
-                        p++;
-                        len--;
-                }
-                if (bitmap[0] == 0 && bitmap[1] == FATTR4_WORD1_MOUNTED_ON_FILEID)
-                        xdr_decode_hyper(p, &entry->ino);
-                else if (bitmap[0] == FATTR4_WORD0_FILEID)
-                        xdr_decode_hyper(p, &entry->ino);
-                p += len;
-        }
+        if (decode_attr_bitmap(xdr, bitmap) < 0)
+                goto out_overflow;
 
-        entry->eof = !p[0] && p[1];
-        return p;
+        if (decode_attr_length(xdr, &len, &p) < 0)
+                goto out_overflow;
+
+        if (decode_getfattr_attrs(xdr, bitmap, entry->fattr, entry->fh,
+                                        entry->server, 1) < 0)
+                goto out_overflow;
+        if (entry->fattr->valid & NFS_ATTR_FATTR_FILEID)
+                entry->ino = entry->fattr->fileid;
+
+        entry->d_type = DT_UNKNOWN;
+        if (entry->fattr->valid & NFS_ATTR_FATTR_TYPE)
+                entry->d_type = nfs_umode_to_dtype(entry->fattr->mode);
+
+        if (verify_attr_len(xdr, p, len) < 0)
+                goto out_overflow;
+
+        return 0;
+
+out_overflow:
+        print_overflow_msg(__func__, xdr);
+        return -EAGAIN;
 }
 
 /*
@@ -5403,10 +6175,9 @@ static struct {
         { NFS4ERR_BAD_COOKIE,   -EBADCOOKIE     },
         { NFS4ERR_NOTSUPP,      -ENOTSUPP       },
         { NFS4ERR_TOOSMALL,     -ETOOSMALL      },
-        { NFS4ERR_SERVERFAULT,  -ESERVERFAULT   },
+        { NFS4ERR_SERVERFAULT,  -EREMOTEIO      },
         { NFS4ERR_BADTYPE,      -EBADTYPE       },
         { NFS4ERR_LOCKED,       -EAGAIN         },
-        { NFS4ERR_RESOURCE,     -EREMOTEIO      },
         { NFS4ERR_SYMLINK,      -ELOOP          },
         { NFS4ERR_OP_ILLEGAL,   -EOPNOTSUPP     },
         { NFS4ERR_DEADLOCK,     -EDEADLK        },
@@ -5431,7 +6202,7 @@ nfs4_stat_to_errno(int stat)
         }
         if (stat <= 10000 || stat > 10100) {
                 /* The server is looney tunes. */
-                return -ESERVERFAULT;
+                return -EREMOTEIO;
         }
         /* If we cannot translate the error, the recovery routines should
          * handle it.
@@ -5444,8 +6215,8 @@ nfs4_stat_to_errno(int stat)
 #define PROC(proc, argtype, restype)                            \
 [NFSPROC4_CLNT_##proc] = {                                      \
         .p_proc   = NFSPROC4_COMPOUND,                          \
-        .p_encode = (kxdrproc_t) nfs4_xdr_##argtype,            \
-        .p_decode = (kxdrproc_t) nfs4_xdr_##restype,            \
+        .p_encode = (kxdreproc_t)nfs4_xdr_##argtype,            \
+        .p_decode = (kxdrdproc_t)nfs4_xdr_##restype,            \
         .p_arglen = NFS4_##argtype##_sz,                        \
         .p_replen = NFS4_##restype##_sz,                        \
         .p_statidx = NFSPROC4_CLNT_##proc,                      \
@@ -5453,46 +6224,50 @@ nfs4_stat_to_errno(int stat)
 }
 
 struct rpc_procinfo     nfs4_procedures[] = {
-  PROC(READ,            enc_read,       dec_read),
-  PROC(WRITE,           enc_write,      dec_write),
-  PROC(COMMIT,          enc_commit,     dec_commit),
-  PROC(OPEN,            enc_open,       dec_open),
-  PROC(OPEN_CONFIRM,    enc_open_confirm,       dec_open_confirm),
-  PROC(OPEN_NOATTR,     enc_open_noattr,        dec_open_noattr),
-  PROC(OPEN_DOWNGRADE,  enc_open_downgrade,     dec_open_downgrade),
-  PROC(CLOSE,           enc_close,      dec_close),
-  PROC(SETATTR,         enc_setattr,    dec_setattr),
-  PROC(FSINFO,          enc_fsinfo,     dec_fsinfo),
-  PROC(RENEW,           enc_renew,      dec_renew),
-  PROC(SETCLIENTID,     enc_setclientid,        dec_setclientid),
-  PROC(SETCLIENTID_CONFIRM,     enc_setclientid_confirm,        dec_setclientid_confirm),
-  PROC(LOCK,            enc_lock,       dec_lock),
-  PROC(LOCKT,           enc_lockt,      dec_lockt),
-  PROC(LOCKU,           enc_locku,      dec_locku),
-  PROC(ACCESS,          enc_access,     dec_access),
-  PROC(GETATTR,         enc_getattr,    dec_getattr),
-  PROC(LOOKUP,          enc_lookup,     dec_lookup),
-  PROC(LOOKUP_ROOT,     enc_lookup_root,        dec_lookup_root),
-  PROC(REMOVE,          enc_remove,     dec_remove),
-  PROC(RENAME,          enc_rename,     dec_rename),
-  PROC(LINK,            enc_link,       dec_link),
-  PROC(SYMLINK,         enc_symlink,    dec_symlink),
-  PROC(CREATE,          enc_create,     dec_create),
-  PROC(PATHCONF,        enc_pathconf,   dec_pathconf),
-  PROC(STATFS,          enc_statfs,     dec_statfs),
-  PROC(READLINK,        enc_readlink,   dec_readlink),
-  PROC(READDIR,         enc_readdir,    dec_readdir),
-  PROC(SERVER_CAPS,     enc_server_caps, dec_server_caps),
-  PROC(DELEGRETURN,     enc_delegreturn, dec_delegreturn),
-  PROC(GETACL,          enc_getacl,     dec_getacl),
-  PROC(SETACL,          enc_setacl,     dec_setacl),
-  PROC(FS_LOCATIONS,    enc_fs_locations, dec_fs_locations),
+        PROC(READ,              enc_read,               dec_read),
+        PROC(WRITE,             enc_write,              dec_write),
+        PROC(COMMIT,            enc_commit,             dec_commit),
+        PROC(OPEN,              enc_open,               dec_open),
+        PROC(OPEN_CONFIRM,      enc_open_confirm,       dec_open_confirm),
+        PROC(OPEN_NOATTR,       enc_open_noattr,        dec_open_noattr),
+        PROC(OPEN_DOWNGRADE,    enc_open_downgrade,     dec_open_downgrade),
+        PROC(CLOSE,             enc_close,              dec_close),
+        PROC(SETATTR,           enc_setattr,            dec_setattr),
+        PROC(FSINFO,            enc_fsinfo,             dec_fsinfo),
+        PROC(RENEW,             enc_renew,              dec_renew),
+        PROC(SETCLIENTID,       enc_setclientid,        dec_setclientid),
+        PROC(SETCLIENTID_CONFIRM, enc_setclientid_confirm, dec_setclientid_confirm),
+        PROC(LOCK,              enc_lock,               dec_lock),
+        PROC(LOCKT,             enc_lockt,              dec_lockt),
+        PROC(LOCKU,             enc_locku,              dec_locku),
+        PROC(ACCESS,            enc_access,             dec_access),
+        PROC(GETATTR,           enc_getattr,            dec_getattr),
+        PROC(LOOKUP,            enc_lookup,             dec_lookup),
+        PROC(LOOKUP_ROOT,       enc_lookup_root,        dec_lookup_root),
+        PROC(REMOVE,            enc_remove,             dec_remove),
+        PROC(RENAME,            enc_rename,             dec_rename),
+        PROC(LINK,              enc_link,               dec_link),
+        PROC(SYMLINK,           enc_symlink,            dec_symlink),
+        PROC(CREATE,            enc_create,             dec_create),
+        PROC(PATHCONF,          enc_pathconf,           dec_pathconf),
+        PROC(STATFS,            enc_statfs,             dec_statfs),
+        PROC(READLINK,          enc_readlink,           dec_readlink),
+        PROC(READDIR,           enc_readdir,            dec_readdir),
+        PROC(SERVER_CAPS,       enc_server_caps,        dec_server_caps),
+        PROC(DELEGRETURN,       enc_delegreturn,        dec_delegreturn),
+        PROC(GETACL,            enc_getacl,             dec_getacl),
+        PROC(SETACL,            enc_setacl,             dec_setacl),
+        PROC(FS_LOCATIONS,      enc_fs_locations,       dec_fs_locations),
+        PROC(RELEASE_LOCKOWNER, enc_release_lockowner,  dec_release_lockowner),
 #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),
+        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),
+        PROC(RECLAIM_COMPLETE,  enc_reclaim_complete,   dec_reclaim_complete),
+        PROC(GETDEVICEINFO,     enc_getdeviceinfo,      dec_getdeviceinfo),
+        PROC(LAYOUTGET,         enc_layoutget,          dec_layoutget),
 #endif /* CONFIG_NFS_V4_1 */
 };
 
diff --git a/fs/nfs/nfsroot.c b/fs/nfs/nfsroot.c
index 8c55b27c0de4..903908a20023 100644
--- a/fs/nfs/nfsroot.c
+++ b/fs/nfs/nfsroot.c
@@ -3,9 +3,10 @@
  *
  *  Allow an NFS filesystem to be mounted as root. The way this works is:
  *     (1) Use the IP autoconfig mechanism to set local IP addresses and routes.
- *     (2) Handle RPC negotiation with the system which replied to RARP or
- *         was reported as a boot server by BOOTP or manually.
- *     (3) The actual mounting is done later, when init() is running.
+ *     (2) Construct the device string and the options string using DHCP
+ *         option 17 and/or kernel command line options.
+ *     (3) When mount_root() sets up the root file system, pass these strings
+ *         to the NFS client's regular mount interface via sys_mount().
  *
  *
  *      Changes:
@@ -65,468 +66,245 @@
  *      Hua Qin         :       Support for mounting root file system via
  *                              NFS over TCP.
  *      Fabian Frederick:       Option parser rebuilt (using parser lib)
-*/
+ *      Chuck Lever     :       Use super.c's text-based mount option parsing
+ *      Chuck Lever     :       Add "nfsrootdebug".
+ */
 
 #include <linux/types.h>
 #include <linux/string.h>
-#include <linux/kernel.h>
-#include <linux/time.h>
-#include <linux/fs.h>
 #include <linux/init.h>
-#include <linux/sunrpc/clnt.h>
-#include <linux/sunrpc/xprtsock.h>
 #include <linux/nfs.h>
 #include <linux/nfs_fs.h>
-#include <linux/nfs_mount.h>
-#include <linux/in.h>
-#include <linux/major.h>
 #include <linux/utsname.h>
-#include <linux/inet.h>
 #include <linux/root_dev.h>
 #include <net/ipconfig.h>
-#include <linux/parser.h>
 
 #include "internal.h"
 
-/* Define this to allow debugging output */
-#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"
 
 /* Parameters passed from the kernel command line */
-static char nfs_root_name[256] __initdata = "";
+static char nfs_root_parms[256] __initdata = "";
+
+/* Text-based mount options passed to super.c */
+static char nfs_root_options[256] __initdata = "";
 
 /* Address of NFS server */
-static __be32 servaddr __initdata = 0;
+static __be32 servaddr __initdata = htonl(INADDR_NONE);
 
 /* Name of directory to mount */
-static char nfs_export_path[NFS_MAXPATHLEN] __initdata = { 0, };
-
-/* NFS-related data */
-static struct nfs_mount_data nfs_data __initdata = { 0, };/* NFS mount info */
-static int nfs_port __initdata = 0;             /* Port to connect to for NFS */
-static int mount_port __initdata = 0;           /* Mount daemon port number */
-
-
-/***************************************************************************
-
-                             Parsing of options
-
- ***************************************************************************/
-
-enum {
-        /* Options that take integer arguments */
-        Opt_port, Opt_rsize, Opt_wsize, Opt_timeo, Opt_retrans, Opt_acregmin,
-        Opt_acregmax, Opt_acdirmin, Opt_acdirmax,
-        /* Options that take no arguments */
-        Opt_soft, Opt_hard, Opt_intr,
-        Opt_nointr, Opt_posix, Opt_noposix, Opt_cto, Opt_nocto, Opt_ac, 
-        Opt_noac, Opt_lock, Opt_nolock, Opt_v2, Opt_v3, Opt_udp, Opt_tcp,
-        Opt_acl, Opt_noacl,
-        /* Error token */
-        Opt_err
-};
-
-static const match_table_t tokens __initconst = {
-        {Opt_port, "port=%u"},
-        {Opt_rsize, "rsize=%u"},
-        {Opt_wsize, "wsize=%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_soft, "soft"},
-        {Opt_hard, "hard"},
-        {Opt_intr, "intr"},
-        {Opt_nointr, "nointr"},
-        {Opt_posix, "posix"},
-        {Opt_noposix, "noposix"},
-        {Opt_cto, "cto"},
-        {Opt_nocto, "nocto"},
-        {Opt_ac, "ac"},
-        {Opt_noac, "noac"},
-        {Opt_lock, "lock"},
-        {Opt_nolock, "nolock"},
-        {Opt_v2, "nfsvers=2"},
-        {Opt_v2, "v2"},
-        {Opt_v3, "nfsvers=3"},
-        {Opt_v3, "v3"},
-        {Opt_udp, "proto=udp"},
-        {Opt_udp, "udp"},
-        {Opt_tcp, "proto=tcp"},
-        {Opt_tcp, "tcp"},
-        {Opt_acl, "acl"},
-        {Opt_noacl, "noacl"},
-        {Opt_err, NULL}
-        
-};
-
-/*
- *  Parse option string.
- */
+static char nfs_export_path[NFS_MAXPATHLEN + 1] __initdata = "";
 
-static int __init root_nfs_parse(char *name, char *buf)
-{
-
-        char *p;
-        substring_t args[MAX_OPT_ARGS];
-        int option;
-
-        if (!name)
-                return 1;
-
-        /* Set the NFS remote path */
-        p = strsep(&name, ",");
-        if (p[0] != '\0' && strcmp(p, "default") != 0)
-                strlcpy(buf, p, NFS_MAXPATHLEN);
-
-        while ((p = strsep (&name, ",")) != NULL) {
-                int token; 
-                if (!*p)
-                        continue;
-                token = match_token(p, tokens, args);
-
-                /* %u tokens only. Beware if you add new tokens! */
-                if (token < Opt_soft && match_int(&args[0], &option))
-                        return 0;
-                switch (token) {
-                        case Opt_port:
-                                nfs_port = option;
-                                break;
-                        case Opt_rsize:
-                                nfs_data.rsize = option;
-                                break;
-                        case Opt_wsize:
-                                nfs_data.wsize = option;
-                                break;
-                        case Opt_timeo:
-                                nfs_data.timeo = option;
-                                break;
-                        case Opt_retrans:
-                                nfs_data.retrans = option;
-                                break;
-                        case Opt_acregmin:
-                                nfs_data.acregmin = option;
-                                break;
-                        case Opt_acregmax:
-                                nfs_data.acregmax = option;
-                                break;
-                        case Opt_acdirmin:
-                                nfs_data.acdirmin = option;
-                                break;
-                        case Opt_acdirmax:
-                                nfs_data.acdirmax = option;
-                                break;
-                        case Opt_soft:
-                                nfs_data.flags |= NFS_MOUNT_SOFT;
-                                break;
-                        case Opt_hard:
-                                nfs_data.flags &= ~NFS_MOUNT_SOFT;
-                                break;
-                        case Opt_intr:
-                        case Opt_nointr:
-                                break;
-                        case Opt_posix:
-                                nfs_data.flags |= NFS_MOUNT_POSIX;
-                                break;
-                        case Opt_noposix:
-                                nfs_data.flags &= ~NFS_MOUNT_POSIX;
-                                break;
-                        case Opt_cto:
-                                nfs_data.flags &= ~NFS_MOUNT_NOCTO;
-                                break;
-                        case Opt_nocto:
-                                nfs_data.flags |= NFS_MOUNT_NOCTO;
-                                break;
-                        case Opt_ac:
-                                nfs_data.flags &= ~NFS_MOUNT_NOAC;
-                                break;
-                        case Opt_noac:
-                                nfs_data.flags |= NFS_MOUNT_NOAC;
-                                break;
-                        case Opt_lock:
-                                nfs_data.flags &= ~NFS_MOUNT_NONLM;
-                                break;
-                        case Opt_nolock:
-                                nfs_data.flags |= NFS_MOUNT_NONLM;
-                                break;
-                        case Opt_v2:
-                                nfs_data.flags &= ~NFS_MOUNT_VER3;
-                                break;
-                        case Opt_v3:
-                                nfs_data.flags |= NFS_MOUNT_VER3;
-                                break;
-                        case Opt_udp:
-                                nfs_data.flags &= ~NFS_MOUNT_TCP;
-                                break;
-                        case Opt_tcp:
-                                nfs_data.flags |= NFS_MOUNT_TCP;
-                                break;
-                        case Opt_acl:
-                                nfs_data.flags &= ~NFS_MOUNT_NOACL;
-                                break;
-                        case Opt_noacl:
-                                nfs_data.flags |= NFS_MOUNT_NOACL;
-                                break;
-                        default:
-                                printk(KERN_WARNING "Root-NFS: unknown "
-                                        "option: %s\n", p);
-                                return 0;
-                }
-        }
-
-        return 1;
-}
+/* server:export path string passed to super.c */
+static char nfs_root_device[NFS_MAXPATHLEN + 1] __initdata = "";
 
+#ifdef RPC_DEBUG
 /*
- *  Prepare the NFS data structure and parse all options.
+ * When the "nfsrootdebug" kernel command line option is specified,
+ * enable debugging messages for NFSROOT.
  */
-static int __init root_nfs_name(char *name)
+static int __init nfs_root_debug(char *__unused)
 {
-        static char buf[NFS_MAXPATHLEN] __initdata;
-        char *cp;
-
-        /* Set some default values */
-        memset(&nfs_data, 0, sizeof(nfs_data));
-        nfs_port          = -1;
-        nfs_data.version  = NFS_MOUNT_VERSION;
-        nfs_data.flags    = NFS_MOUNT_NONLM;    /* No lockd in nfs root yet */
-        nfs_data.rsize    = NFS_DEF_FILE_IO_SIZE;
-        nfs_data.wsize    = NFS_DEF_FILE_IO_SIZE;
-        nfs_data.acregmin = NFS_DEF_ACREGMIN;
-        nfs_data.acregmax = NFS_DEF_ACREGMAX;
-        nfs_data.acdirmin = NFS_DEF_ACDIRMIN;
-        nfs_data.acdirmax = NFS_DEF_ACDIRMAX;
-        strcpy(buf, NFS_ROOT);
-
-        /* Process options received from the remote server */
-        root_nfs_parse(root_server_path, buf);
-
-        /* Override them by options set on kernel command-line */
-        root_nfs_parse(name, buf);
-
-        cp = utsname()->nodename;
-        if (strlen(buf) + strlen(cp) > NFS_MAXPATHLEN) {
-                printk(KERN_ERR "Root-NFS: Pathname for remote directory too long.\n");
-                return -1;
-        }
-        sprintf(nfs_export_path, buf, cp);
-
+        nfs_debug |= NFSDBG_ROOT | NFSDBG_MOUNT;
         return 1;
 }
 
-
-/*
- *  Get NFS server address.
- */
-static int __init root_nfs_addr(void)
-{
-        if ((servaddr = root_server_addr) == htonl(INADDR_NONE)) {
-                printk(KERN_ERR "Root-NFS: No NFS server available, giving up.\n");
-                return -1;
-        }
-
-        snprintf(nfs_data.hostname, sizeof(nfs_data.hostname),
-                 "%pI4", &servaddr);
-        return 0;
-}
-
-/*
- *  Tell the user what's going on.
- */
-#ifdef NFSROOT_DEBUG
-static void __init root_nfs_print(void)
-{
-        printk(KERN_NOTICE "Root-NFS: Mounting %s on server %s as root\n",
-                nfs_export_path, nfs_data.hostname);
-        printk(KERN_NOTICE "Root-NFS:     rsize = %d, wsize = %d, timeo = %d, retrans = %d\n",
-                nfs_data.rsize, nfs_data.wsize, nfs_data.timeo, nfs_data.retrans);
-        printk(KERN_NOTICE "Root-NFS:     acreg (min,max) = (%d,%d), acdir (min,max) = (%d,%d)\n",
-                nfs_data.acregmin, nfs_data.acregmax,
-                nfs_data.acdirmin, nfs_data.acdirmax);
-        printk(KERN_NOTICE "Root-NFS:     nfsd port = %d, mountd port = %d, flags = %08x\n",
-                nfs_port, mount_port, nfs_data.flags);
-}
-#endif
-
-
-static int __init root_nfs_init(void)
-{
-#ifdef NFSROOT_DEBUG
-        nfs_debug |= NFSDBG_ROOT;
+__setup("nfsrootdebug", nfs_root_debug);
 #endif
 
-        /*
-         * Decode the root directory path name and NFS options from
-         * the kernel command line. This has to go here in order to
-         * be able to use the client IP address for the remote root
-         * directory (necessary for pure RARP booting).
-         */
-        if (root_nfs_name(nfs_root_name) < 0 ||
-            root_nfs_addr() < 0)
-                return -1;
-
-#ifdef NFSROOT_DEBUG
-        root_nfs_print();
-#endif
-
-        return 0;
-}
-
-
 /*
  *  Parse NFS server and directory information passed on the kernel
  *  command line.
+ *
+ *  nfsroot=[<server-ip>:]<root-dir>[,<nfs-options>]
+ *
+ *  If there is a "%s" token in the <root-dir> string, it is replaced
+ *  by the ASCII-representation of the client's IP address.
  */
 static int __init nfs_root_setup(char *line)
 {
         ROOT_DEV = Root_NFS;
+
         if (line[0] == '/' || line[0] == ',' || (line[0] >= '0' && line[0] <= '9')) {
-                strlcpy(nfs_root_name, line, sizeof(nfs_root_name));
+                strlcpy(nfs_root_parms, line, sizeof(nfs_root_parms));
         } else {
-                int n = strlen(line) + sizeof(NFS_ROOT) - 1;
-                if (n >= sizeof(nfs_root_name))
-                        line[sizeof(nfs_root_name) - sizeof(NFS_ROOT) - 2] = '\0';
-                sprintf(nfs_root_name, NFS_ROOT, line);
+                size_t n = strlen(line) + sizeof(NFS_ROOT) - 1;
+                if (n >= sizeof(nfs_root_parms))
+                        line[sizeof(nfs_root_parms) - sizeof(NFS_ROOT) - 2] = '\0';
+                sprintf(nfs_root_parms, NFS_ROOT, line);
         }
-        root_server_addr = root_nfs_parse_addr(nfs_root_name);
+
+        /*
+         * Extract the IP address of the NFS server containing our
+         * root file system, if one was specified.
+         *
+         * Note: root_nfs_parse_addr() removes the server-ip from
+         *       nfs_root_parms, if it exists.
+         */
+        root_server_addr = root_nfs_parse_addr(nfs_root_parms);
+
         return 1;
 }
 
 __setup("nfsroot=", nfs_root_setup);
 
-/***************************************************************************
-
-               Routines to actually mount the root directory
-
- ***************************************************************************/
+static int __init root_nfs_copy(char *dest, const char *src,
+                                     const size_t destlen)
+{
+        if (strlcpy(dest, src, destlen) > destlen)
+                return -1;
+        return 0;
+}
 
-/*
- *  Construct sockaddr_in from address and port number.
- */
-static inline void
-set_sockaddr(struct sockaddr_in *sin, __be32 addr, __be16 port)
+static int __init root_nfs_cat(char *dest, const char *src,
+                                  const size_t destlen)
 {
-        sin->sin_family = AF_INET;
-        sin->sin_addr.s_addr = addr;
-        sin->sin_port = port;
+        if (strlcat(dest, src, destlen) > destlen)
+                return -1;
+        return 0;
 }
 
 /*
- *  Query server portmapper for the port of a daemon program.
+ * Parse out root export path and mount options from
+ * passed-in string @incoming.
+ *
+ * Copy the export path into @exppath.
  */
-static int __init root_nfs_getport(int program, int version, int proto)
+static int __init root_nfs_parse_options(char *incoming, char *exppath,
+                                         const size_t exppathlen)
 {
-        struct sockaddr_in sin;
+        char *p;
 
-        printk(KERN_NOTICE "Looking up port of RPC %d/%d on %pI4\n",
-                program, version, &servaddr);
-        set_sockaddr(&sin, servaddr, 0);
-        return rpcb_getport_sync(&sin, program, version, proto);
-}
+        /*
+         * Set the NFS remote path
+         */
+        p = strsep(&incoming, ",");
+        if (*p != '\0' && strcmp(p, "default") != 0)
+                if (root_nfs_copy(exppath, p, exppathlen))
+                        return -1;
+
+        /*
+         * @incoming now points to the rest of the string; if it
+         * contains something, append it to our root options buffer
+         */
+        if (incoming != NULL && *incoming != '\0')
+                if (root_nfs_cat(nfs_root_options, incoming,
+                                                sizeof(nfs_root_options)))
+                        return -1;
 
+        /*
+         * Possibly prepare for more options to be appended
+         */
+        if (nfs_root_options[0] != '\0' &&
+            nfs_root_options[strlen(nfs_root_options)] != ',')
+                if (root_nfs_cat(nfs_root_options, ",",
+                                                sizeof(nfs_root_options)))
+                        return -1;
+
+        return 0;
+}
 
 /*
- *  Use portmapper to find mountd and nfsd port numbers if not overriden
- *  by the user. Use defaults if portmapper is not available.
- *  XXX: Is there any nfs server with no portmapper?
+ *  Decode the export directory path name and NFS options from
+ *  the kernel command line.  This has to be done late in order to
+ *  use a dynamically acquired client IP address for the remote
+ *  root directory path.
+ *
+ *  Returns zero if successful; otherwise -1 is returned.
  */
-static int __init root_nfs_ports(void)
+static int __init root_nfs_data(char *cmdline)
 {
-        int port;
-        int nfsd_ver, mountd_ver;
-        int nfsd_port, mountd_port;
-        int proto;
-
-        if (nfs_data.flags & NFS_MOUNT_VER3) {
-                nfsd_ver = NFS3_VERSION;
-                mountd_ver = NFS_MNT3_VERSION;
-                nfsd_port = NFS_PORT;
-                mountd_port = NFS_MNT_PORT;
-        } else {
-                nfsd_ver = NFS2_VERSION;
-                mountd_ver = NFS_MNT_VERSION;
-                nfsd_port = NFS_PORT;
-                mountd_port = NFS_MNT_PORT;
+        char addr_option[sizeof("nolock,addr=") + INET_ADDRSTRLEN + 1];
+        int len, retval = -1;
+        char *tmp = NULL;
+        const size_t tmplen = sizeof(nfs_export_path);
+
+        tmp = kzalloc(tmplen, GFP_KERNEL);
+        if (tmp == NULL)
+                goto out_nomem;
+        strcpy(tmp, NFS_ROOT);
+
+        if (root_server_path[0] != '\0') {
+                dprintk("Root-NFS: DHCPv4 option 17: %s\n",
+                        root_server_path);
+                if (root_nfs_parse_options(root_server_path, tmp, tmplen))
+                        goto out_optionstoolong;
         }
 
-        proto = (nfs_data.flags & NFS_MOUNT_TCP) ? IPPROTO_TCP : IPPROTO_UDP;
-
-        if (nfs_port < 0) {
-                if ((port = root_nfs_getport(NFS_PROGRAM, nfsd_ver, proto)) < 0) {
-                        printk(KERN_ERR "Root-NFS: Unable to get nfsd port "
-                                        "number from server, using default\n");
-                        port = nfsd_port;
-                }
-                nfs_port = port;
-                dprintk("Root-NFS: Portmapper on server returned %d "
-                        "as nfsd port\n", port);
+        if (cmdline[0] != '\0') {
+                dprintk("Root-NFS: nfsroot=%s\n", cmdline);
+                if (root_nfs_parse_options(cmdline, tmp, tmplen))
+                        goto out_optionstoolong;
         }
 
-        if ((port = root_nfs_getport(NFS_MNT_PROGRAM, mountd_ver, proto)) < 0) {
-                printk(KERN_ERR "Root-NFS: Unable to get mountd port "
-                                "number from server, using default\n");
-                port = mountd_port;
-        }
-        mount_port = port;
-        dprintk("Root-NFS: mountd port is %d\n", port);
+        /*
+         * Append mandatory options for nfsroot so they override
+         * what has come before
+         */
+        snprintf(addr_option, sizeof(addr_option), "nolock,addr=%pI4",
+                        &servaddr);
+        if (root_nfs_cat(nfs_root_options, addr_option,
+                                                sizeof(nfs_root_options)))
+                goto out_optionstoolong;
 
-        return 0;
+        /*
+         * Set up nfs_root_device.  For NFS mounts, this looks like
+         *
+         *      server:/path
+         *
+         * At this point, utsname()->nodename contains our local
+         * IP address or hostname, set by ipconfig.  If "%s" exists
+         * in tmp, substitute the nodename, then shovel the whole
+         * mess into nfs_root_device.
+         */
+        len = snprintf(nfs_export_path, sizeof(nfs_export_path),
+                                tmp, utsname()->nodename);
+        if (len > (int)sizeof(nfs_export_path))
+                goto out_devnametoolong;
+        len = snprintf(nfs_root_device, sizeof(nfs_root_device),
+                                "%pI4:%s", &servaddr, nfs_export_path);
+        if (len > (int)sizeof(nfs_root_device))
+                goto out_devnametoolong;
+
+        retval = 0;
+
+out:
+        kfree(tmp);
+        return retval;
+out_nomem:
+        printk(KERN_ERR "Root-NFS: could not allocate memory\n");
+        goto out;
+out_optionstoolong:
+        printk(KERN_ERR "Root-NFS: mount options string too long\n");
+        goto out;
+out_devnametoolong:
+        printk(KERN_ERR "Root-NFS: root device name too long.\n");
+        goto out;
 }
 
-
-/*
- *  Get a file handle from the server for the directory which is to be
- *  mounted.
+/**
+ * nfs_root_data - Return prepared 'data' for NFSROOT mount
+ * @root_device: OUT: address of string containing NFSROOT device
+ * @root_data: OUT: address of string containing NFSROOT mount options
+ *
+ * Returns zero and sets @root_device and @root_data if successful,
+ * otherwise -1 is returned.
  */
-static int __init root_nfs_get_handle(void)
+int __init nfs_root_data(char **root_device, char **root_data)
 {
-        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),
-                .dirpath        = nfs_export_path,
-                .version        = (nfs_data.flags & NFS_MOUNT_VER3) ?
-                                        NFS_MNT3_VERSION : NFS_MNT_VERSION,
-                .protocol       = (nfs_data.flags & NFS_MOUNT_TCP) ?
-                                        XPRT_TRANSPORT_TCP : XPRT_TRANSPORT_UDP,
-                .fh             = &fh,
-                .auth_flav_len  = &auth_flav_len,
-        };
-        int status;
-
-        set_sockaddr(&sin, servaddr, htons(mount_port));
-        status = nfs_mount(&request);
-        if (status < 0)
-                printk(KERN_ERR "Root-NFS: Server returned error %d "
-                                "while mounting %s\n", status, nfs_export_path);
-        else {
-                nfs_data.root.size = fh.size;
-                memcpy(nfs_data.root.data, fh.data, fh.size);
+        servaddr = root_server_addr;
+        if (servaddr == htonl(INADDR_NONE)) {
+                printk(KERN_ERR "Root-NFS: no NFS server address\n");
+                return -1;
         }
 
-        return status;
-}
+        if (root_nfs_data(nfs_root_parms) < 0)
+                return -1;
 
-/*
- *  Get the NFS port numbers and file handle, and return the prepared 'data'
- *  argument for mount() if everything went OK. Return NULL otherwise.
- */
-void * __init nfs_root_data(void)
-{
-        if (root_nfs_init() < 0
-         || root_nfs_ports() < 0
-         || root_nfs_get_handle() < 0)
-                return NULL;
-        set_sockaddr((struct sockaddr_in *) &nfs_data.addr, servaddr, htons(nfs_port));
-        return (void*)&nfs_data;
+        *root_device = nfs_root_device;
+        *root_data = nfs_root_options;
+        return 0;
 }
diff --git a/fs/nfs/pagelist.c b/fs/nfs/pagelist.c
index e2975939126a..e1164e3f9e69 100644
--- a/fs/nfs/pagelist.c
+++ b/fs/nfs/pagelist.c
@@ -26,12 +26,9 @@ static struct kmem_cache *nfs_page_cachep;
 static inline struct nfs_page *
 nfs_page_alloc(void)
 {
-        struct nfs_page *p;
-        p = kmem_cache_alloc(nfs_page_cachep, GFP_KERNEL);
-        if (p) {
-                memset(p, 0, sizeof(*p));
+        struct nfs_page *p = kmem_cache_zalloc(nfs_page_cachep, GFP_KERNEL);
+        if (p)
                 INIT_LIST_HEAD(&p->wb_list);
-        }
         return p;
 }
 
@@ -60,15 +57,16 @@ nfs_create_request(struct nfs_open_context *ctx, struct inode *inode,
 {
         struct nfs_page         *req;
 
-        for (;;) {
-                /* try to allocate the request struct */
-                req = nfs_page_alloc();
-                if (req != NULL)
-                        break;
+        /* try to allocate the request struct */
+        req = nfs_page_alloc();
+        if (req == NULL)
+                return ERR_PTR(-ENOMEM);
 
-                if (fatal_signal_pending(current))
-                        return ERR_PTR(-ERESTARTSYS);
-                yield();
+        /* get lock context early so we can deal with alloc failures */
+        req->wb_lock_context = nfs_get_lock_context(ctx);
+        if (req->wb_lock_context == NULL) {
+                nfs_page_free(req);
+                return ERR_PTR(-ENOMEM);
         }
 
         /* Initialize the request struct. Initially, we assume a
@@ -112,12 +110,10 @@ void nfs_unlock_request(struct nfs_page *req)
  */
 int nfs_set_page_tag_locked(struct nfs_page *req)
 {
-        struct nfs_inode *nfsi = NFS_I(req->wb_context->path.dentry->d_inode);
-
         if (!nfs_lock_request_dontget(req))
                 return 0;
-        if (req->wb_page != NULL)
-                radix_tree_tag_set(&nfsi->nfs_page_tree, req->wb_index, NFS_PAGE_TAG_LOCKED);
+        if (test_bit(PG_MAPPED, &req->wb_flags))
+                radix_tree_tag_set(&NFS_I(req->wb_context->path.dentry->d_inode)->nfs_page_tree, req->wb_index, NFS_PAGE_TAG_LOCKED);
         return 1;
 }
 
@@ -126,10 +122,10 @@ int nfs_set_page_tag_locked(struct nfs_page *req)
  */
 void nfs_clear_page_tag_locked(struct nfs_page *req)
 {
-        struct inode *inode = req->wb_context->path.dentry->d_inode;
-        struct nfs_inode *nfsi = NFS_I(inode);
+        if (test_bit(PG_MAPPED, &req->wb_flags)) {
+                struct inode *inode = req->wb_context->path.dentry->d_inode;
+                struct nfs_inode *nfsi = NFS_I(inode);
 
-        if (req->wb_page != NULL) {
                 spin_lock(&inode->i_lock);
                 radix_tree_tag_clear(&nfsi->nfs_page_tree, req->wb_index, NFS_PAGE_TAG_LOCKED);
                 nfs_unlock_request(req);
@@ -142,16 +138,27 @@ void nfs_clear_page_tag_locked(struct nfs_page *req)
  * nfs_clear_request - Free up all resources allocated to the request
  * @req:
  *
- * Release page resources associated with a write request after it
- * has completed.
+ * Release page and open context resources associated with a read/write
+ * request after it has completed.
  */
 void nfs_clear_request(struct nfs_page *req)
 {
         struct page *page = req->wb_page;
+        struct nfs_open_context *ctx = req->wb_context;
+        struct nfs_lock_context *l_ctx = req->wb_lock_context;
+
         if (page != NULL) {
                 page_cache_release(page);
                 req->wb_page = NULL;
         }
+        if (l_ctx != NULL) {
+                nfs_put_lock_context(l_ctx);
+                req->wb_lock_context = NULL;
+        }
+        if (ctx != NULL) {
+                put_nfs_open_context(ctx);
+                req->wb_context = NULL;
+        }
 }
 
 
@@ -165,9 +172,8 @@ static void nfs_free_request(struct kref *kref)
 {
         struct nfs_page *req = container_of(kref, struct nfs_page, wb_kref);
 
-        /* Release struct file or cached credential */
+        /* Release struct file and open context */
         nfs_clear_request(req);
-        put_nfs_open_context(req->wb_context);
         nfs_page_free(req);
 }
 
@@ -176,6 +182,12 @@ void nfs_release_request(struct nfs_page *req)
         kref_put(&req->wb_kref, nfs_free_request);
 }
 
+static int nfs_wait_bit_uninterruptible(void *word)
+{
+        io_schedule();
+        return 0;
+}
+
 /**
  * nfs_wait_on_request - Wait for a request to complete.
  * @req: request to wait upon.
@@ -186,14 +198,9 @@ void nfs_release_request(struct nfs_page *req)
 int
 nfs_wait_on_request(struct nfs_page *req)
 {
-        int ret = 0;
-
-        if (!test_bit(PG_BUSY, &req->wb_flags))
-                goto out;
-        ret = out_of_line_wait_on_bit(&req->wb_flags, PG_BUSY,
-                        nfs_wait_bit_killable, TASK_KILLABLE);
-out:
-        return ret;
+        return wait_on_bit(&req->wb_flags, PG_BUSY,
+                        nfs_wait_bit_uninterruptible,
+                        TASK_UNINTERRUPTIBLE);
 }
 
 /**
@@ -237,7 +244,7 @@ static int nfs_can_coalesce_requests(struct nfs_page *prev,
 {
         if (req->wb_context->cred != prev->wb_context->cred)
                 return 0;
-        if (req->wb_context->lockowner != prev->wb_context->lockowner)
+        if (req->wb_lock_context->lockowner != prev->wb_lock_context->lockowner)
                 return 0;
         if (req->wb_context->state != prev->wb_context->state)
                 return 0;
diff --git a/fs/nfs/pnfs.c b/fs/nfs/pnfs.c
new file mode 100644
index 000000000000..bc4089769735
--- /dev/null
+++ b/fs/nfs/pnfs.c
@@ -0,0 +1,965 @@
+/*
+ *  pNFS functions to call and manage layout drivers.
+ *
+ *  Copyright (c) 2002 [year of first publication]
+ *  The Regents of the University of Michigan
+ *  All Rights Reserved
+ *
+ *  Dean Hildebrand <dhildebz@umich.edu>
+ *
+ *  Permission is granted to use, copy, create derivative works, and
+ *  redistribute this software and such derivative works for any purpose,
+ *  so long as the name of the University of Michigan is not used in
+ *  any advertising or publicity pertaining to the use or distribution
+ *  of this software without specific, written prior authorization. If
+ *  the above copyright notice or any other identification of the
+ *  University of Michigan is included in any copy of any portion of
+ *  this software, then the disclaimer below must also be included.
+ *
+ *  This software is provided as is, without representation or warranty
+ *  of any kind either express or implied, including without limitation
+ *  the implied warranties of merchantability, fitness for a particular
+ *  purpose, or noninfringement.  The Regents of the University of
+ *  Michigan shall not be liable for any damages, including special,
+ *  indirect, incidental, or consequential damages, with respect to any
+ *  claim arising out of or in connection with the use of the software,
+ *  even if it has been or is hereafter advised of the possibility of
+ *  such damages.
+ */
+
+#include <linux/nfs_fs.h>
+#include "internal.h"
+#include "pnfs.h"
+
+#define NFSDBG_FACILITY         NFSDBG_PNFS
+
+/* Locking:
+ *
+ * pnfs_spinlock:
+ *      protects pnfs_modules_tbl.
+ */
+static DEFINE_SPINLOCK(pnfs_spinlock);
+
+/*
+ * pnfs_modules_tbl holds all pnfs modules
+ */
+static LIST_HEAD(pnfs_modules_tbl);
+
+/* Return the registered pnfs layout driver module matching given id */
+static struct pnfs_layoutdriver_type *
+find_pnfs_driver_locked(u32 id)
+{
+        struct pnfs_layoutdriver_type *local;
+
+        list_for_each_entry(local, &pnfs_modules_tbl, pnfs_tblid)
+                if (local->id == id)
+                        goto out;
+        local = NULL;
+out:
+        dprintk("%s: Searching for id %u, found %p\n", __func__, id, local);
+        return local;
+}
+
+static struct pnfs_layoutdriver_type *
+find_pnfs_driver(u32 id)
+{
+        struct pnfs_layoutdriver_type *local;
+
+        spin_lock(&pnfs_spinlock);
+        local = find_pnfs_driver_locked(id);
+        spin_unlock(&pnfs_spinlock);
+        return local;
+}
+
+void
+unset_pnfs_layoutdriver(struct nfs_server *nfss)
+{
+        if (nfss->pnfs_curr_ld) {
+                nfss->pnfs_curr_ld->clear_layoutdriver(nfss);
+                module_put(nfss->pnfs_curr_ld->owner);
+        }
+        nfss->pnfs_curr_ld = NULL;
+}
+
+/*
+ * Try to set the server's pnfs module to the pnfs layout type specified by id.
+ * Currently only one pNFS layout driver per filesystem is supported.
+ *
+ * @id layout type. Zero (illegal layout type) indicates pNFS not in use.
+ */
+void
+set_pnfs_layoutdriver(struct nfs_server *server, u32 id)
+{
+        struct pnfs_layoutdriver_type *ld_type = NULL;
+
+        if (id == 0)
+                goto out_no_driver;
+        if (!(server->nfs_client->cl_exchange_flags &
+                 (EXCHGID4_FLAG_USE_NON_PNFS | EXCHGID4_FLAG_USE_PNFS_MDS))) {
+                printk(KERN_ERR "%s: id %u cl_exchange_flags 0x%x\n", __func__,
+                       id, server->nfs_client->cl_exchange_flags);
+                goto out_no_driver;
+        }
+        ld_type = find_pnfs_driver(id);
+        if (!ld_type) {
+                request_module("%s-%u", LAYOUT_NFSV4_1_MODULE_PREFIX, id);
+                ld_type = find_pnfs_driver(id);
+                if (!ld_type) {
+                        dprintk("%s: No pNFS module found for %u.\n",
+                                __func__, id);
+                        goto out_no_driver;
+                }
+        }
+        if (!try_module_get(ld_type->owner)) {
+                dprintk("%s: Could not grab reference on module\n", __func__);
+                goto out_no_driver;
+        }
+        server->pnfs_curr_ld = ld_type;
+        if (ld_type->set_layoutdriver(server)) {
+                printk(KERN_ERR
+                       "%s: Error initializing mount point for layout driver %u.\n",
+                       __func__, id);
+                module_put(ld_type->owner);
+                goto out_no_driver;
+        }
+        dprintk("%s: pNFS module for %u set\n", __func__, id);
+        return;
+
+out_no_driver:
+        dprintk("%s: Using NFSv4 I/O\n", __func__);
+        server->pnfs_curr_ld = NULL;
+}
+
+int
+pnfs_register_layoutdriver(struct pnfs_layoutdriver_type *ld_type)
+{
+        int status = -EINVAL;
+        struct pnfs_layoutdriver_type *tmp;
+
+        if (ld_type->id == 0) {
+                printk(KERN_ERR "%s id 0 is reserved\n", __func__);
+                return status;
+        }
+        if (!ld_type->alloc_lseg || !ld_type->free_lseg) {
+                printk(KERN_ERR "%s Layout driver must provide "
+                       "alloc_lseg and free_lseg.\n", __func__);
+                return status;
+        }
+
+        spin_lock(&pnfs_spinlock);
+        tmp = find_pnfs_driver_locked(ld_type->id);
+        if (!tmp) {
+                list_add(&ld_type->pnfs_tblid, &pnfs_modules_tbl);
+                status = 0;
+                dprintk("%s Registering id:%u name:%s\n", __func__, ld_type->id,
+                        ld_type->name);
+        } else {
+                printk(KERN_ERR "%s Module with id %d already loaded!\n",
+                        __func__, ld_type->id);
+        }
+        spin_unlock(&pnfs_spinlock);
+
+        return status;
+}
+EXPORT_SYMBOL_GPL(pnfs_register_layoutdriver);
+
+void
+pnfs_unregister_layoutdriver(struct pnfs_layoutdriver_type *ld_type)
+{
+        dprintk("%s Deregistering id:%u\n", __func__, ld_type->id);
+        spin_lock(&pnfs_spinlock);
+        list_del(&ld_type->pnfs_tblid);
+        spin_unlock(&pnfs_spinlock);
+}
+EXPORT_SYMBOL_GPL(pnfs_unregister_layoutdriver);
+
+/*
+ * pNFS client layout cache
+ */
+
+/* Need to hold i_lock if caller does not already hold reference */
+void
+get_layout_hdr(struct pnfs_layout_hdr *lo)
+{
+        atomic_inc(&lo->plh_refcount);
+}
+
+static void
+destroy_layout_hdr(struct pnfs_layout_hdr *lo)
+{
+        dprintk("%s: freeing layout cache %p\n", __func__, lo);
+        BUG_ON(!list_empty(&lo->plh_layouts));
+        NFS_I(lo->plh_inode)->layout = NULL;
+        kfree(lo);
+}
+
+static void
+put_layout_hdr_locked(struct pnfs_layout_hdr *lo)
+{
+        if (atomic_dec_and_test(&lo->plh_refcount))
+                destroy_layout_hdr(lo);
+}
+
+void
+put_layout_hdr(struct pnfs_layout_hdr *lo)
+{
+        struct inode *inode = lo->plh_inode;
+
+        if (atomic_dec_and_lock(&lo->plh_refcount, &inode->i_lock)) {
+                destroy_layout_hdr(lo);
+                spin_unlock(&inode->i_lock);
+        }
+}
+
+static void
+init_lseg(struct pnfs_layout_hdr *lo, struct pnfs_layout_segment *lseg)
+{
+        INIT_LIST_HEAD(&lseg->pls_list);
+        atomic_set(&lseg->pls_refcount, 1);
+        smp_mb();
+        set_bit(NFS_LSEG_VALID, &lseg->pls_flags);
+        lseg->pls_layout = lo;
+}
+
+static void free_lseg(struct pnfs_layout_segment *lseg)
+{
+        struct inode *ino = lseg->pls_layout->plh_inode;
+
+        NFS_SERVER(ino)->pnfs_curr_ld->free_lseg(lseg);
+        /* Matched by get_layout_hdr in pnfs_insert_layout */
+        put_layout_hdr(NFS_I(ino)->layout);
+}
+
+/* The use of tmp_list is necessary because pnfs_curr_ld->free_lseg
+ * could sleep, so must be called outside of the lock.
+ * Returns 1 if object was removed, otherwise return 0.
+ */
+static int
+put_lseg_locked(struct pnfs_layout_segment *lseg,
+                struct list_head *tmp_list)
+{
+        dprintk("%s: lseg %p ref %d valid %d\n", __func__, lseg,
+                atomic_read(&lseg->pls_refcount),
+                test_bit(NFS_LSEG_VALID, &lseg->pls_flags));
+        if (atomic_dec_and_test(&lseg->pls_refcount)) {
+                struct inode *ino = lseg->pls_layout->plh_inode;
+
+                BUG_ON(test_bit(NFS_LSEG_VALID, &lseg->pls_flags));
+                list_del(&lseg->pls_list);
+                if (list_empty(&lseg->pls_layout->plh_segs)) {
+                        struct nfs_client *clp;
+
+                        clp = NFS_SERVER(ino)->nfs_client;
+                        spin_lock(&clp->cl_lock);
+                        /* List does not take a reference, so no need for put here */
+                        list_del_init(&lseg->pls_layout->plh_layouts);
+                        spin_unlock(&clp->cl_lock);
+                        clear_bit(NFS_LAYOUT_BULK_RECALL, &lseg->pls_layout->plh_flags);
+                }
+                rpc_wake_up(&NFS_SERVER(ino)->roc_rpcwaitq);
+                list_add(&lseg->pls_list, tmp_list);
+                return 1;
+        }
+        return 0;
+}
+
+static bool
+should_free_lseg(u32 lseg_iomode, u32 recall_iomode)
+{
+        return (recall_iomode == IOMODE_ANY ||
+                lseg_iomode == recall_iomode);
+}
+
+/* Returns 1 if lseg is removed from list, 0 otherwise */
+static int mark_lseg_invalid(struct pnfs_layout_segment *lseg,
+                             struct list_head *tmp_list)
+{
+        int rv = 0;
+
+        if (test_and_clear_bit(NFS_LSEG_VALID, &lseg->pls_flags)) {
+                /* Remove the reference keeping the lseg in the
+                 * list.  It will now be removed when all
+                 * outstanding io is finished.
+                 */
+                rv = put_lseg_locked(lseg, tmp_list);
+        }
+        return rv;
+}
+
+/* Returns count of number of matching invalid lsegs remaining in list
+ * after call.
+ */
+int
+mark_matching_lsegs_invalid(struct pnfs_layout_hdr *lo,
+                            struct list_head *tmp_list,
+                            u32 iomode)
+{
+        struct pnfs_layout_segment *lseg, *next;
+        int invalid = 0, removed = 0;
+
+        dprintk("%s:Begin lo %p\n", __func__, lo);
+
+        list_for_each_entry_safe(lseg, next, &lo->plh_segs, pls_list)
+                if (should_free_lseg(lseg->pls_range.iomode, iomode)) {
+                        dprintk("%s: freeing lseg %p iomode %d "
+                                "offset %llu length %llu\n", __func__,
+                                lseg, lseg->pls_range.iomode, lseg->pls_range.offset,
+                                lseg->pls_range.length);
+                        invalid++;
+                        removed += mark_lseg_invalid(lseg, tmp_list);
+                }
+        dprintk("%s:Return %i\n", __func__, invalid - removed);
+        return invalid - removed;
+}
+
+void
+pnfs_free_lseg_list(struct list_head *free_me)
+{
+        struct pnfs_layout_segment *lseg, *tmp;
+
+        list_for_each_entry_safe(lseg, tmp, free_me, pls_list) {
+                list_del(&lseg->pls_list);
+                free_lseg(lseg);
+        }
+}
+
+void
+pnfs_destroy_layout(struct nfs_inode *nfsi)
+{
+        struct pnfs_layout_hdr *lo;
+        LIST_HEAD(tmp_list);
+
+        spin_lock(&nfsi->vfs_inode.i_lock);
+        lo = nfsi->layout;
+        if (lo) {
+                set_bit(NFS_LAYOUT_DESTROYED, &nfsi->layout->plh_flags);
+                mark_matching_lsegs_invalid(lo, &tmp_list, IOMODE_ANY);
+                /* Matched by refcount set to 1 in alloc_init_layout_hdr */
+                put_layout_hdr_locked(lo);
+        }
+        spin_unlock(&nfsi->vfs_inode.i_lock);
+        pnfs_free_lseg_list(&tmp_list);
+}
+
+/*
+ * Called by the state manger to remove all layouts established under an
+ * expired lease.
+ */
+void
+pnfs_destroy_all_layouts(struct nfs_client *clp)
+{
+        struct pnfs_layout_hdr *lo;
+        LIST_HEAD(tmp_list);
+
+        spin_lock(&clp->cl_lock);
+        list_splice_init(&clp->cl_layouts, &tmp_list);
+        spin_unlock(&clp->cl_lock);
+
+        while (!list_empty(&tmp_list)) {
+                lo = list_entry(tmp_list.next, struct pnfs_layout_hdr,
+                                plh_layouts);
+                dprintk("%s freeing layout for inode %lu\n", __func__,
+                        lo->plh_inode->i_ino);
+                pnfs_destroy_layout(NFS_I(lo->plh_inode));
+        }
+}
+
+/* update lo->plh_stateid with new if is more recent */
+void
+pnfs_set_layout_stateid(struct pnfs_layout_hdr *lo, const nfs4_stateid *new,
+                        bool update_barrier)
+{
+        u32 oldseq, newseq;
+
+        oldseq = be32_to_cpu(lo->plh_stateid.stateid.seqid);
+        newseq = be32_to_cpu(new->stateid.seqid);
+        if ((int)(newseq - oldseq) > 0) {
+                memcpy(&lo->plh_stateid, &new->stateid, sizeof(new->stateid));
+                if (update_barrier) {
+                        u32 new_barrier = be32_to_cpu(new->stateid.seqid);
+
+                        if ((int)(new_barrier - lo->plh_barrier))
+                                lo->plh_barrier = new_barrier;
+                } else {
+                        /* Because of wraparound, we want to keep the barrier
+                         * "close" to the current seqids.  It needs to be
+                         * within 2**31 to count as "behind", so if it
+                         * gets too near that limit, give us a litle leeway
+                         * and bring it to within 2**30.
+                         * NOTE - and yes, this is all unsigned arithmetic.
+                         */
+                        if (unlikely((newseq - lo->plh_barrier) > (3 << 29)))
+                                lo->plh_barrier = newseq - (1 << 30);
+                }
+        }
+}
+
+/* lget is set to 1 if called from inside send_layoutget call chain */
+static bool
+pnfs_layoutgets_blocked(struct pnfs_layout_hdr *lo, nfs4_stateid *stateid,
+                        int lget)
+{
+        if ((stateid) &&
+            (int)(lo->plh_barrier - be32_to_cpu(stateid->stateid.seqid)) >= 0)
+                return true;
+        return lo->plh_block_lgets ||
+                test_bit(NFS_LAYOUT_BULK_RECALL, &lo->plh_flags) ||
+                (list_empty(&lo->plh_segs) &&
+                 (atomic_read(&lo->plh_outstanding) > lget));
+}
+
+int
+pnfs_choose_layoutget_stateid(nfs4_stateid *dst, struct pnfs_layout_hdr *lo,
+                              struct nfs4_state *open_state)
+{
+        int status = 0;
+
+        dprintk("--> %s\n", __func__);
+        spin_lock(&lo->plh_inode->i_lock);
+        if (pnfs_layoutgets_blocked(lo, NULL, 1)) {
+                status = -EAGAIN;
+        } else if (list_empty(&lo->plh_segs)) {
+                int seq;
+
+                do {
+                        seq = read_seqbegin(&open_state->seqlock);
+                        memcpy(dst->data, open_state->stateid.data,
+                               sizeof(open_state->stateid.data));
+                } while (read_seqretry(&open_state->seqlock, seq));
+        } else
+                memcpy(dst->data, lo->plh_stateid.data, sizeof(lo->plh_stateid.data));
+        spin_unlock(&lo->plh_inode->i_lock);
+        dprintk("<-- %s\n", __func__);
+        return status;
+}
+
+/*
+* Get layout from server.
+*    for now, assume that whole file layouts are requested.
+*    arg->offset: 0
+*    arg->length: all ones
+*/
+static struct pnfs_layout_segment *
+send_layoutget(struct pnfs_layout_hdr *lo,
+           struct nfs_open_context *ctx,
+           u32 iomode)
+{
+        struct inode *ino = lo->plh_inode;
+        struct nfs_server *server = NFS_SERVER(ino);
+        struct nfs4_layoutget *lgp;
+        struct pnfs_layout_segment *lseg = NULL;
+
+        dprintk("--> %s\n", __func__);
+
+        BUG_ON(ctx == NULL);
+        lgp = kzalloc(sizeof(*lgp), GFP_KERNEL);
+        if (lgp == NULL)
+                return NULL;
+        lgp->args.minlength = NFS4_MAX_UINT64;
+        lgp->args.maxcount = PNFS_LAYOUT_MAXSIZE;
+        lgp->args.range.iomode = iomode;
+        lgp->args.range.offset = 0;
+        lgp->args.range.length = NFS4_MAX_UINT64;
+        lgp->args.type = server->pnfs_curr_ld->id;
+        lgp->args.inode = ino;
+        lgp->args.ctx = get_nfs_open_context(ctx);
+        lgp->lsegpp = &lseg;
+
+        /* Synchronously retrieve layout information from server and
+         * store in lseg.
+         */
+        nfs4_proc_layoutget(lgp);
+        if (!lseg) {
+                /* remember that LAYOUTGET failed and suspend trying */
+                set_bit(lo_fail_bit(iomode), &lo->plh_flags);
+        }
+        return lseg;
+}
+
+bool pnfs_roc(struct inode *ino)
+{
+        struct pnfs_layout_hdr *lo;
+        struct pnfs_layout_segment *lseg, *tmp;
+        LIST_HEAD(tmp_list);
+        bool found = false;
+
+        spin_lock(&ino->i_lock);
+        lo = NFS_I(ino)->layout;
+        if (!lo || !test_and_clear_bit(NFS_LAYOUT_ROC, &lo->plh_flags) ||
+            test_bit(NFS_LAYOUT_BULK_RECALL, &lo->plh_flags))
+                goto out_nolayout;
+        list_for_each_entry_safe(lseg, tmp, &lo->plh_segs, pls_list)
+                if (test_bit(NFS_LSEG_ROC, &lseg->pls_flags)) {
+                        mark_lseg_invalid(lseg, &tmp_list);
+                        found = true;
+                }
+        if (!found)
+                goto out_nolayout;
+        lo->plh_block_lgets++;
+        get_layout_hdr(lo); /* matched in pnfs_roc_release */
+        spin_unlock(&ino->i_lock);
+        pnfs_free_lseg_list(&tmp_list);
+        return true;
+
+out_nolayout:
+        spin_unlock(&ino->i_lock);
+        return false;
+}
+
+void pnfs_roc_release(struct inode *ino)
+{
+        struct pnfs_layout_hdr *lo;
+
+        spin_lock(&ino->i_lock);
+        lo = NFS_I(ino)->layout;
+        lo->plh_block_lgets--;
+        put_layout_hdr_locked(lo);
+        spin_unlock(&ino->i_lock);
+}
+
+void pnfs_roc_set_barrier(struct inode *ino, u32 barrier)
+{
+        struct pnfs_layout_hdr *lo;
+
+        spin_lock(&ino->i_lock);
+        lo = NFS_I(ino)->layout;
+        if ((int)(barrier - lo->plh_barrier) > 0)
+                lo->plh_barrier = barrier;
+        spin_unlock(&ino->i_lock);
+}
+
+bool pnfs_roc_drain(struct inode *ino, u32 *barrier)
+{
+        struct nfs_inode *nfsi = NFS_I(ino);
+        struct pnfs_layout_segment *lseg;
+        bool found = false;
+
+        spin_lock(&ino->i_lock);
+        list_for_each_entry(lseg, &nfsi->layout->plh_segs, pls_list)
+                if (test_bit(NFS_LSEG_ROC, &lseg->pls_flags)) {
+                        found = true;
+                        break;
+                }
+        if (!found) {
+                struct pnfs_layout_hdr *lo = nfsi->layout;
+                u32 current_seqid = be32_to_cpu(lo->plh_stateid.stateid.seqid);
+
+                /* Since close does not return a layout stateid for use as
+                 * a barrier, we choose the worst-case barrier.
+                 */
+                *barrier = current_seqid + atomic_read(&lo->plh_outstanding);
+        }
+        spin_unlock(&ino->i_lock);
+        return found;
+}
+
+/*
+ * Compare two layout segments for sorting into layout cache.
+ * We want to preferentially return RW over RO layouts, so ensure those
+ * are seen first.
+ */
+static s64
+cmp_layout(u32 iomode1, u32 iomode2)
+{
+        /* read > read/write */
+        return (int)(iomode2 == IOMODE_READ) - (int)(iomode1 == IOMODE_READ);
+}
+
+static void
+pnfs_insert_layout(struct pnfs_layout_hdr *lo,
+                   struct pnfs_layout_segment *lseg)
+{
+        struct pnfs_layout_segment *lp;
+        int found = 0;
+
+        dprintk("%s:Begin\n", __func__);
+
+        assert_spin_locked(&lo->plh_inode->i_lock);
+        list_for_each_entry(lp, &lo->plh_segs, pls_list) {
+                if (cmp_layout(lp->pls_range.iomode, lseg->pls_range.iomode) > 0)
+                        continue;
+                list_add_tail(&lseg->pls_list, &lp->pls_list);
+                dprintk("%s: inserted lseg %p "
+                        "iomode %d offset %llu length %llu before "
+                        "lp %p iomode %d offset %llu length %llu\n",
+                        __func__, lseg, lseg->pls_range.iomode,
+                        lseg->pls_range.offset, lseg->pls_range.length,
+                        lp, lp->pls_range.iomode, lp->pls_range.offset,
+                        lp->pls_range.length);
+                found = 1;
+                break;
+        }
+        if (!found) {
+                list_add_tail(&lseg->pls_list, &lo->plh_segs);
+                dprintk("%s: inserted lseg %p "
+                        "iomode %d offset %llu length %llu at tail\n",
+                        __func__, lseg, lseg->pls_range.iomode,
+                        lseg->pls_range.offset, lseg->pls_range.length);
+        }
+        get_layout_hdr(lo);
+
+        dprintk("%s:Return\n", __func__);
+}
+
+static struct pnfs_layout_hdr *
+alloc_init_layout_hdr(struct inode *ino)
+{
+        struct pnfs_layout_hdr *lo;
+
+        lo = kzalloc(sizeof(struct pnfs_layout_hdr), GFP_KERNEL);
+        if (!lo)
+                return NULL;
+        atomic_set(&lo->plh_refcount, 1);
+        INIT_LIST_HEAD(&lo->plh_layouts);
+        INIT_LIST_HEAD(&lo->plh_segs);
+        INIT_LIST_HEAD(&lo->plh_bulk_recall);
+        lo->plh_inode = ino;
+        return lo;
+}
+
+static struct pnfs_layout_hdr *
+pnfs_find_alloc_layout(struct inode *ino)
+{
+        struct nfs_inode *nfsi = NFS_I(ino);
+        struct pnfs_layout_hdr *new = NULL;
+
+        dprintk("%s Begin ino=%p layout=%p\n", __func__, ino, nfsi->layout);
+
+        assert_spin_locked(&ino->i_lock);
+        if (nfsi->layout) {
+                if (test_bit(NFS_LAYOUT_DESTROYED, &nfsi->layout->plh_flags))
+                        return NULL;
+                else
+                        return nfsi->layout;
+        }
+        spin_unlock(&ino->i_lock);
+        new = alloc_init_layout_hdr(ino);
+        spin_lock(&ino->i_lock);
+
+        if (likely(nfsi->layout == NULL))       /* Won the race? */
+                nfsi->layout = new;
+        else
+                kfree(new);
+        return nfsi->layout;
+}
+
+/*
+ * iomode matching rules:
+ * iomode       lseg    match
+ * -----        -----   -----
+ * ANY          READ    true
+ * ANY          RW      true
+ * RW           READ    false
+ * RW           RW      true
+ * READ         READ    true
+ * READ         RW      true
+ */
+static int
+is_matching_lseg(struct pnfs_layout_segment *lseg, u32 iomode)
+{
+        return (iomode != IOMODE_RW || lseg->pls_range.iomode == IOMODE_RW);
+}
+
+/*
+ * lookup range in layout
+ */
+static struct pnfs_layout_segment *
+pnfs_find_lseg(struct pnfs_layout_hdr *lo, u32 iomode)
+{
+        struct pnfs_layout_segment *lseg, *ret = NULL;
+
+        dprintk("%s:Begin\n", __func__);
+
+        assert_spin_locked(&lo->plh_inode->i_lock);
+        list_for_each_entry(lseg, &lo->plh_segs, pls_list) {
+                if (test_bit(NFS_LSEG_VALID, &lseg->pls_flags) &&
+                    is_matching_lseg(lseg, iomode)) {
+                        ret = lseg;
+                        break;
+                }
+                if (cmp_layout(iomode, lseg->pls_range.iomode) > 0)
+                        break;
+        }
+
+        dprintk("%s:Return lseg %p ref %d\n",
+                __func__, ret, ret ? atomic_read(&ret->pls_refcount) : 0);
+        return ret;
+}
+
+/*
+ * Layout segment is retreived from the server if not cached.
+ * The appropriate layout segment is referenced and returned to the caller.
+ */
+struct pnfs_layout_segment *
+pnfs_update_layout(struct inode *ino,
+                   struct nfs_open_context *ctx,
+                   enum pnfs_iomode iomode)
+{
+        struct nfs_inode *nfsi = NFS_I(ino);
+        struct nfs_client *clp = NFS_SERVER(ino)->nfs_client;
+        struct pnfs_layout_hdr *lo;
+        struct pnfs_layout_segment *lseg = NULL;
+
+        if (!pnfs_enabled_sb(NFS_SERVER(ino)))
+                return NULL;
+        spin_lock(&ino->i_lock);
+        lo = pnfs_find_alloc_layout(ino);
+        if (lo == NULL) {
+                dprintk("%s ERROR: can't get pnfs_layout_hdr\n", __func__);
+                goto out_unlock;
+        }
+
+        /* Do we even need to bother with this? */
+        if (test_bit(NFS4CLNT_LAYOUTRECALL, &clp->cl_state) ||
+            test_bit(NFS_LAYOUT_BULK_RECALL, &lo->plh_flags)) {
+                dprintk("%s matches recall, use MDS\n", __func__);
+                goto out_unlock;
+        }
+        /* Check to see if the layout for the given range already exists */
+        lseg = pnfs_find_lseg(lo, iomode);
+        if (lseg)
+                goto out_unlock;
+
+        /* if LAYOUTGET already failed once we don't try again */
+        if (test_bit(lo_fail_bit(iomode), &nfsi->layout->plh_flags))
+                goto out_unlock;
+
+        if (pnfs_layoutgets_blocked(lo, NULL, 0))
+                goto out_unlock;
+        atomic_inc(&lo->plh_outstanding);
+
+        get_layout_hdr(lo);
+        if (list_empty(&lo->plh_segs)) {
+                /* The lo must be on the clp list if there is any
+                 * chance of a CB_LAYOUTRECALL(FILE) coming in.
+                 */
+                spin_lock(&clp->cl_lock);
+                BUG_ON(!list_empty(&lo->plh_layouts));
+                list_add_tail(&lo->plh_layouts, &clp->cl_layouts);
+                spin_unlock(&clp->cl_lock);
+        }
+        spin_unlock(&ino->i_lock);
+
+        lseg = send_layoutget(lo, ctx, iomode);
+        if (!lseg) {
+                spin_lock(&ino->i_lock);
+                if (list_empty(&lo->plh_segs)) {
+                        spin_lock(&clp->cl_lock);
+                        list_del_init(&lo->plh_layouts);
+                        spin_unlock(&clp->cl_lock);
+                        clear_bit(NFS_LAYOUT_BULK_RECALL, &lo->plh_flags);
+                }
+                spin_unlock(&ino->i_lock);
+        }
+        atomic_dec(&lo->plh_outstanding);
+        put_layout_hdr(lo);
+out:
+        dprintk("%s end, state 0x%lx lseg %p\n", __func__,
+                nfsi->layout->plh_flags, lseg);
+        return lseg;
+out_unlock:
+        spin_unlock(&ino->i_lock);
+        goto out;
+}
+
+int
+pnfs_layout_process(struct nfs4_layoutget *lgp)
+{
+        struct pnfs_layout_hdr *lo = NFS_I(lgp->args.inode)->layout;
+        struct nfs4_layoutget_res *res = &lgp->res;
+        struct pnfs_layout_segment *lseg;
+        struct inode *ino = lo->plh_inode;
+        struct nfs_client *clp = NFS_SERVER(ino)->nfs_client;
+        int status = 0;
+
+        /* Verify we got what we asked for.
+         * Note that because the xdr parsing only accepts a single
+         * element array, this can fail even if the server is behaving
+         * correctly.
+         */
+        if (lgp->args.range.iomode > res->range.iomode ||
+            res->range.offset != 0 ||
+            res->range.length != NFS4_MAX_UINT64) {
+                status = -EINVAL;
+                goto out;
+        }
+        /* Inject layout blob into I/O device driver */
+        lseg = NFS_SERVER(ino)->pnfs_curr_ld->alloc_lseg(lo, res);
+        if (!lseg || IS_ERR(lseg)) {
+                if (!lseg)
+                        status = -ENOMEM;
+                else
+                        status = PTR_ERR(lseg);
+                dprintk("%s: Could not allocate layout: error %d\n",
+                       __func__, status);
+                goto out;
+        }
+
+        spin_lock(&ino->i_lock);
+        if (test_bit(NFS4CLNT_LAYOUTRECALL, &clp->cl_state) ||
+            test_bit(NFS_LAYOUT_BULK_RECALL, &lo->plh_flags)) {
+                dprintk("%s forget reply due to recall\n", __func__);
+                goto out_forget_reply;
+        }
+
+        if (pnfs_layoutgets_blocked(lo, &res->stateid, 1)) {
+                dprintk("%s forget reply due to state\n", __func__);
+                goto out_forget_reply;
+        }
+        init_lseg(lo, lseg);
+        lseg->pls_range = res->range;
+        *lgp->lsegpp = lseg;
+        pnfs_insert_layout(lo, lseg);
+
+        if (res->return_on_close) {
+                set_bit(NFS_LSEG_ROC, &lseg->pls_flags);
+                set_bit(NFS_LAYOUT_ROC, &lo->plh_flags);
+        }
+
+        /* Done processing layoutget. Set the layout stateid */
+        pnfs_set_layout_stateid(lo, &res->stateid, false);
+        spin_unlock(&ino->i_lock);
+out:
+        return status;
+
+out_forget_reply:
+        spin_unlock(&ino->i_lock);
+        lseg->pls_layout = lo;
+        NFS_SERVER(ino)->pnfs_curr_ld->free_lseg(lseg);
+        goto out;
+}
+
+/*
+ * Device ID cache. Currently supports one layout type per struct nfs_client.
+ * Add layout type to the lookup key to expand to support multiple types.
+ */
+int
+pnfs_alloc_init_deviceid_cache(struct nfs_client *clp,
+                         void (*free_callback)(struct pnfs_deviceid_node *))
+{
+        struct pnfs_deviceid_cache *c;
+
+        c = kzalloc(sizeof(struct pnfs_deviceid_cache), GFP_KERNEL);
+        if (!c)
+                return -ENOMEM;
+        spin_lock(&clp->cl_lock);
+        if (clp->cl_devid_cache != NULL) {
+                atomic_inc(&clp->cl_devid_cache->dc_ref);
+                dprintk("%s [kref [%d]]\n", __func__,
+                        atomic_read(&clp->cl_devid_cache->dc_ref));
+                kfree(c);
+        } else {
+                /* kzalloc initializes hlists */
+                spin_lock_init(&c->dc_lock);
+                atomic_set(&c->dc_ref, 1);
+                c->dc_free_callback = free_callback;
+                clp->cl_devid_cache = c;
+                dprintk("%s [new]\n", __func__);
+        }
+        spin_unlock(&clp->cl_lock);
+        return 0;
+}
+EXPORT_SYMBOL_GPL(pnfs_alloc_init_deviceid_cache);
+
+/*
+ * Called from pnfs_layoutdriver_type->free_lseg
+ * last layout segment reference frees deviceid
+ */
+void
+pnfs_put_deviceid(struct pnfs_deviceid_cache *c,
+                  struct pnfs_deviceid_node *devid)
+{
+        struct nfs4_deviceid *id = &devid->de_id;
+        struct pnfs_deviceid_node *d;
+        struct hlist_node *n;
+        long h = nfs4_deviceid_hash(id);
+
+        dprintk("%s [%d]\n", __func__, atomic_read(&devid->de_ref));
+        if (!atomic_dec_and_lock(&devid->de_ref, &c->dc_lock))
+                return;
+
+        hlist_for_each_entry_rcu(d, n, &c->dc_deviceids[h], de_node)
+                if (!memcmp(&d->de_id, id, sizeof(*id))) {
+                        hlist_del_rcu(&d->de_node);
+                        spin_unlock(&c->dc_lock);
+                        synchronize_rcu();
+                        c->dc_free_callback(devid);
+                        return;
+                }
+        spin_unlock(&c->dc_lock);
+        /* Why wasn't it found in  the list? */
+        BUG();
+}
+EXPORT_SYMBOL_GPL(pnfs_put_deviceid);
+
+/* Find and reference a deviceid */
+struct pnfs_deviceid_node *
+pnfs_find_get_deviceid(struct pnfs_deviceid_cache *c, struct nfs4_deviceid *id)
+{
+        struct pnfs_deviceid_node *d;
+        struct hlist_node *n;
+        long hash = nfs4_deviceid_hash(id);
+
+        dprintk("--> %s hash %ld\n", __func__, hash);
+        rcu_read_lock();
+        hlist_for_each_entry_rcu(d, n, &c->dc_deviceids[hash], de_node) {
+                if (!memcmp(&d->de_id, id, sizeof(*id))) {
+                        if (!atomic_inc_not_zero(&d->de_ref)) {
+                                goto fail;
+                        } else {
+                                rcu_read_unlock();
+                                return d;
+                        }
+                }
+        }
+fail:
+        rcu_read_unlock();
+        return NULL;
+}
+EXPORT_SYMBOL_GPL(pnfs_find_get_deviceid);
+
+/*
+ * Add a deviceid to the cache.
+ * GETDEVICEINFOs for same deviceid can race. If deviceid is found, discard new
+ */
+struct pnfs_deviceid_node *
+pnfs_add_deviceid(struct pnfs_deviceid_cache *c, struct pnfs_deviceid_node *new)
+{
+        struct pnfs_deviceid_node *d;
+        long hash = nfs4_deviceid_hash(&new->de_id);
+
+        dprintk("--> %s hash %ld\n", __func__, hash);
+        spin_lock(&c->dc_lock);
+        d = pnfs_find_get_deviceid(c, &new->de_id);
+        if (d) {
+                spin_unlock(&c->dc_lock);
+                dprintk("%s [discard]\n", __func__);
+                c->dc_free_callback(new);
+                return d;
+        }
+        INIT_HLIST_NODE(&new->de_node);
+        atomic_set(&new->de_ref, 1);
+        hlist_add_head_rcu(&new->de_node, &c->dc_deviceids[hash]);
+        spin_unlock(&c->dc_lock);
+        dprintk("%s [new]\n", __func__);
+        return new;
+}
+EXPORT_SYMBOL_GPL(pnfs_add_deviceid);
+
+void
+pnfs_put_deviceid_cache(struct nfs_client *clp)
+{
+        struct pnfs_deviceid_cache *local = clp->cl_devid_cache;
+
+        dprintk("--> %s cl_devid_cache %p\n", __func__, clp->cl_devid_cache);
+        if (atomic_dec_and_lock(&local->dc_ref, &clp->cl_lock)) {
+                int i;
+                /* Verify cache is empty */
+                for (i = 0; i < NFS4_DEVICE_ID_HASH_SIZE; i++)
+                        BUG_ON(!hlist_empty(&local->dc_deviceids[i]));
+                clp->cl_devid_cache = NULL;
+                spin_unlock(&clp->cl_lock);
+                kfree(local);
+        }
+}
+EXPORT_SYMBOL_GPL(pnfs_put_deviceid_cache);
diff --git a/fs/nfs/pnfs.h b/fs/nfs/pnfs.h
new file mode 100644
index 000000000000..e2612ea0cbed
--- /dev/null
+++ b/fs/nfs/pnfs.h
@@ -0,0 +1,235 @@
+/*
+ *  pNFS client data structures.
+ *
+ *  Copyright (c) 2002
+ *  The Regents of the University of Michigan
+ *  All Rights Reserved
+ *
+ *  Dean Hildebrand <dhildebz@umich.edu>
+ *
+ *  Permission is granted to use, copy, create derivative works, and
+ *  redistribute this software and such derivative works for any purpose,
+ *  so long as the name of the University of Michigan is not used in
+ *  any advertising or publicity pertaining to the use or distribution
+ *  of this software without specific, written prior authorization. If
+ *  the above copyright notice or any other identification of the
+ *  University of Michigan is included in any copy of any portion of
+ *  this software, then the disclaimer below must also be included.
+ *
+ *  This software is provided as is, without representation or warranty
+ *  of any kind either express or implied, including without limitation
+ *  the implied warranties of merchantability, fitness for a particular
+ *  purpose, or noninfringement.  The Regents of the University of
+ *  Michigan shall not be liable for any damages, including special,
+ *  indirect, incidental, or consequential damages, with respect to any
+ *  claim arising out of or in connection with the use of the software,
+ *  even if it has been or is hereafter advised of the possibility of
+ *  such damages.
+ */
+
+#ifndef FS_NFS_PNFS_H
+#define FS_NFS_PNFS_H
+
+enum {
+        NFS_LSEG_VALID = 0,     /* cleared when lseg is recalled/returned */
+        NFS_LSEG_ROC,           /* roc bit received from server */
+};
+
+struct pnfs_layout_segment {
+        struct list_head pls_list;
+        struct pnfs_layout_range pls_range;
+        atomic_t pls_refcount;
+        unsigned long pls_flags;
+        struct pnfs_layout_hdr *pls_layout;
+};
+
+#ifdef CONFIG_NFS_V4_1
+
+#define LAYOUT_NFSV4_1_MODULE_PREFIX "nfs-layouttype4"
+
+enum {
+        NFS_LAYOUT_RO_FAILED = 0,       /* get ro layout failed stop trying */
+        NFS_LAYOUT_RW_FAILED,           /* get rw layout failed stop trying */
+        NFS_LAYOUT_BULK_RECALL,         /* bulk recall affecting layout */
+        NFS_LAYOUT_ROC,                 /* some lseg had roc bit set */
+        NFS_LAYOUT_DESTROYED,           /* no new use of layout allowed */
+};
+
+/* Per-layout driver specific registration structure */
+struct pnfs_layoutdriver_type {
+        struct list_head pnfs_tblid;
+        const u32 id;
+        const char *name;
+        struct module *owner;
+        int (*set_layoutdriver) (struct nfs_server *);
+        int (*clear_layoutdriver) (struct nfs_server *);
+        struct pnfs_layout_segment * (*alloc_lseg) (struct pnfs_layout_hdr *layoutid, struct nfs4_layoutget_res *lgr);
+        void (*free_lseg) (struct pnfs_layout_segment *lseg);
+};
+
+struct pnfs_layout_hdr {
+        atomic_t                plh_refcount;
+        struct list_head        plh_layouts;   /* other client layouts */
+        struct list_head        plh_bulk_recall; /* clnt list of bulk recalls */
+        struct list_head        plh_segs;      /* layout segments list */
+        nfs4_stateid            plh_stateid;
+        atomic_t                plh_outstanding; /* number of RPCs out */
+        unsigned long           plh_block_lgets; /* block LAYOUTGET if >0 */
+        u32                     plh_barrier; /* ignore lower seqids */
+        unsigned long           plh_flags;
+        struct inode            *plh_inode;
+};
+
+struct pnfs_device {
+        struct nfs4_deviceid dev_id;
+        unsigned int  layout_type;
+        unsigned int  mincount;
+        struct page **pages;
+        void          *area;
+        unsigned int  pgbase;
+        unsigned int  pglen;
+};
+
+/*
+ * Device ID RCU cache. A device ID is unique per client ID and layout type.
+ */
+#define NFS4_DEVICE_ID_HASH_BITS        5
+#define NFS4_DEVICE_ID_HASH_SIZE        (1 << NFS4_DEVICE_ID_HASH_BITS)
+#define NFS4_DEVICE_ID_HASH_MASK        (NFS4_DEVICE_ID_HASH_SIZE - 1)
+
+static inline u32
+nfs4_deviceid_hash(struct nfs4_deviceid *id)
+{
+        unsigned char *cptr = (unsigned char *)id->data;
+        unsigned int nbytes = NFS4_DEVICEID4_SIZE;
+        u32 x = 0;
+
+        while (nbytes--) {
+                x *= 37;
+                x += *cptr++;
+        }
+        return x & NFS4_DEVICE_ID_HASH_MASK;
+}
+
+struct pnfs_deviceid_node {
+        struct hlist_node       de_node;
+        struct nfs4_deviceid    de_id;
+        atomic_t                de_ref;
+};
+
+struct pnfs_deviceid_cache {
+        spinlock_t              dc_lock;
+        atomic_t                dc_ref;
+        void                    (*dc_free_callback)(struct pnfs_deviceid_node *);
+        struct hlist_head       dc_deviceids[NFS4_DEVICE_ID_HASH_SIZE];
+};
+
+extern int pnfs_alloc_init_deviceid_cache(struct nfs_client *,
+                        void (*free_callback)(struct pnfs_deviceid_node *));
+extern void pnfs_put_deviceid_cache(struct nfs_client *);
+extern struct pnfs_deviceid_node *pnfs_find_get_deviceid(
+                                struct pnfs_deviceid_cache *,
+                                struct nfs4_deviceid *);
+extern struct pnfs_deviceid_node *pnfs_add_deviceid(
+                                struct pnfs_deviceid_cache *,
+                                struct pnfs_deviceid_node *);
+extern void pnfs_put_deviceid(struct pnfs_deviceid_cache *c,
+                              struct pnfs_deviceid_node *devid);
+
+extern int pnfs_register_layoutdriver(struct pnfs_layoutdriver_type *);
+extern void pnfs_unregister_layoutdriver(struct pnfs_layoutdriver_type *);
+
+/* nfs4proc.c */
+extern int nfs4_proc_getdeviceinfo(struct nfs_server *server,
+                                   struct pnfs_device *dev);
+extern int nfs4_proc_layoutget(struct nfs4_layoutget *lgp);
+
+/* pnfs.c */
+void get_layout_hdr(struct pnfs_layout_hdr *lo);
+struct pnfs_layout_segment *
+pnfs_update_layout(struct inode *ino, struct nfs_open_context *ctx,
+                   enum pnfs_iomode access_type);
+void set_pnfs_layoutdriver(struct nfs_server *, u32 id);
+void unset_pnfs_layoutdriver(struct nfs_server *);
+int pnfs_layout_process(struct nfs4_layoutget *lgp);
+void pnfs_free_lseg_list(struct list_head *tmp_list);
+void pnfs_destroy_layout(struct nfs_inode *);
+void pnfs_destroy_all_layouts(struct nfs_client *);
+void put_layout_hdr(struct pnfs_layout_hdr *lo);
+void pnfs_set_layout_stateid(struct pnfs_layout_hdr *lo,
+                             const nfs4_stateid *new,
+                             bool update_barrier);
+int pnfs_choose_layoutget_stateid(nfs4_stateid *dst,
+                                  struct pnfs_layout_hdr *lo,
+                                  struct nfs4_state *open_state);
+int mark_matching_lsegs_invalid(struct pnfs_layout_hdr *lo,
+                                struct list_head *tmp_list,
+                                u32 iomode);
+bool pnfs_roc(struct inode *ino);
+void pnfs_roc_release(struct inode *ino);
+void pnfs_roc_set_barrier(struct inode *ino, u32 barrier);
+bool pnfs_roc_drain(struct inode *ino, u32 *barrier);
+
+
+static inline int lo_fail_bit(u32 iomode)
+{
+        return iomode == IOMODE_RW ?
+                         NFS_LAYOUT_RW_FAILED : NFS_LAYOUT_RO_FAILED;
+}
+
+/* Return true if a layout driver is being used for this mountpoint */
+static inline int pnfs_enabled_sb(struct nfs_server *nfss)
+{
+        return nfss->pnfs_curr_ld != NULL;
+}
+
+#else  /* CONFIG_NFS_V4_1 */
+
+static inline void pnfs_destroy_all_layouts(struct nfs_client *clp)
+{
+}
+
+static inline void pnfs_destroy_layout(struct nfs_inode *nfsi)
+{
+}
+
+static inline struct pnfs_layout_segment *
+pnfs_update_layout(struct inode *ino, struct nfs_open_context *ctx,
+                   enum pnfs_iomode access_type)
+{
+        return NULL;
+}
+
+static inline bool
+pnfs_roc(struct inode *ino)
+{
+        return false;
+}
+
+static inline void
+pnfs_roc_release(struct inode *ino)
+{
+}
+
+static inline void
+pnfs_roc_set_barrier(struct inode *ino, u32 barrier)
+{
+}
+
+static inline bool
+pnfs_roc_drain(struct inode *ino, u32 *barrier)
+{
+        return false;
+}
+
+static inline void set_pnfs_layoutdriver(struct nfs_server *s, u32 id)
+{
+}
+
+static inline void unset_pnfs_layoutdriver(struct nfs_server *s)
+{
+}
+
+#endif /* CONFIG_NFS_V4_1 */
+
+#endif /* FS_NFS_PNFS_H */
diff --git a/fs/nfs/proc.c b/fs/nfs/proc.c
index 7be72d90d49d..77d5e21c4ad6 100644
--- a/fs/nfs/proc.c
+++ b/fs/nfs/proc.c
@@ -29,10 +29,8 @@
 
 #include <linux/types.h>
 #include <linux/param.h>
-#include <linux/slab.h>
 #include <linux/time.h>
 #include <linux/mm.h>
-#include <linux/utsname.h>
 #include <linux/errno.h>
 #include <linux/string.h>
 #include <linux/in.h>
@@ -48,6 +46,39 @@
 #define NFSDBG_FACILITY         NFSDBG_PROC
 
 /*
+ * wrapper to handle the -EKEYEXPIRED error message. This should generally
+ * only happen if using krb5 auth and a user's TGT expires. NFSv2 doesn't
+ * support the NFSERR_JUKEBOX error code, but we handle this situation in the
+ * same way that we handle that error with NFSv3.
+ */
+static int
+nfs_rpc_wrapper(struct rpc_clnt *clnt, struct rpc_message *msg, int flags)
+{
+        int res;
+        do {
+                res = rpc_call_sync(clnt, msg, flags);
+                if (res != -EKEYEXPIRED)
+                        break;
+                schedule_timeout_killable(NFS_JUKEBOX_RETRY_TIME);
+                res = -ERESTARTSYS;
+        } while (!fatal_signal_pending(current));
+        return res;
+}
+
+#define rpc_call_sync(clnt, msg, flags) nfs_rpc_wrapper(clnt, msg, flags)
+
+static int
+nfs_async_handle_expired_key(struct rpc_task *task)
+{
+        if (task->tk_status != -EKEYEXPIRED)
+                return 0;
+        task->tk_status = 0;
+        rpc_restart_call(task);
+        rpc_delay(task, NFS_JUKEBOX_RETRY_TIME);
+        return 1;
+}
+
+/*
  * Bare-bones access to getattr: this is for nfs_read_super.
  */
 static int
@@ -193,35 +224,60 @@ static int nfs_proc_readlink(struct inode *inode, struct page *page,
         return status;
 }
 
+struct nfs_createdata {
+        struct nfs_createargs arg;
+        struct nfs_diropok res;
+        struct nfs_fh fhandle;
+        struct nfs_fattr fattr;
+};
+
+static struct nfs_createdata *nfs_alloc_createdata(struct inode *dir,
+                struct dentry *dentry, struct iattr *sattr)
+{
+        struct nfs_createdata *data;
+
+        data = kmalloc(sizeof(*data), GFP_KERNEL);
+
+        if (data != NULL) {
+                data->arg.fh = NFS_FH(dir);
+                data->arg.name = dentry->d_name.name;
+                data->arg.len = dentry->d_name.len;
+                data->arg.sattr = sattr;
+                nfs_fattr_init(&data->fattr);
+                data->fhandle.size = 0;
+                data->res.fh = &data->fhandle;
+                data->res.fattr = &data->fattr;
+        }
+        return data;
+};
+
+static void nfs_free_createdata(const struct nfs_createdata *data)
+{
+        kfree(data);
+}
+
 static int
 nfs_proc_create(struct inode *dir, struct dentry *dentry, struct iattr *sattr,
-                int flags, struct nameidata *nd)
+                int flags, struct nfs_open_context *ctx)
 {
-        struct nfs_fh           fhandle;
-        struct nfs_fattr        fattr;
-        struct nfs_createargs   arg = {
-                .fh             = NFS_FH(dir),
-                .name           = dentry->d_name.name,
-                .len            = dentry->d_name.len,
-                .sattr          = sattr
-        };
-        struct nfs_diropok      res = {
-                .fh             = &fhandle,
-                .fattr          = &fattr
-        };
+        struct nfs_createdata *data;
         struct rpc_message msg = {
                 .rpc_proc       = &nfs_procedures[NFSPROC_CREATE],
-                .rpc_argp       = &arg,
-                .rpc_resp       = &res,
         };
-        int                     status;
+        int status = -ENOMEM;
 
-        nfs_fattr_init(&fattr);
         dprintk("NFS call  create %s\n", dentry->d_name.name);
+        data = nfs_alloc_createdata(dir, dentry, sattr);
+        if (data == NULL)
+                goto out;
+        msg.rpc_argp = &data->arg;
+        msg.rpc_resp = &data->res;
         status = rpc_call_sync(NFS_CLIENT(dir), &msg, 0);
         nfs_mark_for_revalidate(dir);
         if (status == 0)
-                status = nfs_instantiate(dentry, &fhandle, &fattr);
+                status = nfs_instantiate(dentry, data->res.fh, data->res.fattr);
+        nfs_free_createdata(data);
+out:
         dprintk("NFS reply create: %d\n", status);
         return status;
 }
@@ -233,24 +289,12 @@ static int
 nfs_proc_mknod(struct inode *dir, struct dentry *dentry, struct iattr *sattr,
                dev_t rdev)
 {
-        struct nfs_fh fhandle;
-        struct nfs_fattr fattr;
-        struct nfs_createargs   arg = {
-                .fh             = NFS_FH(dir),
-                .name           = dentry->d_name.name,
-                .len            = dentry->d_name.len,
-                .sattr          = sattr
-        };
-        struct nfs_diropok      res = {
-                .fh             = &fhandle,
-                .fattr          = &fattr
-        };
+        struct nfs_createdata *data;
         struct rpc_message msg = {
                 .rpc_proc       = &nfs_procedures[NFSPROC_CREATE],
-                .rpc_argp       = &arg,
-                .rpc_resp       = &res,
         };
-        int status, mode;
+        umode_t mode;
+        int status = -ENOMEM;
 
         dprintk("NFS call  mknod %s\n", dentry->d_name.name);
 
@@ -263,17 +307,24 @@ nfs_proc_mknod(struct inode *dir, struct dentry *dentry, struct iattr *sattr,
                 sattr->ia_size = new_encode_dev(rdev);/* get out your barf bag */
         }
 
-        nfs_fattr_init(&fattr);
+        data = nfs_alloc_createdata(dir, dentry, sattr);
+        if (data == NULL)
+                goto out;
+        msg.rpc_argp = &data->arg;
+        msg.rpc_resp = &data->res;
+
         status = rpc_call_sync(NFS_CLIENT(dir), &msg, 0);
         nfs_mark_for_revalidate(dir);
 
         if (status == -EINVAL && S_ISFIFO(mode)) {
                 sattr->ia_mode = mode;
-                nfs_fattr_init(&fattr);
+                nfs_fattr_init(data->res.fattr);
                 status = rpc_call_sync(NFS_CLIENT(dir), &msg, 0);
         }
         if (status == 0)
-                status = nfs_instantiate(dentry, &fhandle, &fattr);
+                status = nfs_instantiate(dentry, data->res.fh, data->res.fattr);
+        nfs_free_createdata(data);
+out:
         dprintk("NFS reply mknod: %d\n", status);
         return status;
 }
@@ -308,21 +359,38 @@ nfs_proc_unlink_setup(struct rpc_message *msg, struct inode *dir)
 
 static int nfs_proc_unlink_done(struct rpc_task *task, struct inode *dir)
 {
+        if (nfs_async_handle_expired_key(task))
+                return 0;
         nfs_mark_for_revalidate(dir);
         return 1;
 }
 
+static void
+nfs_proc_rename_setup(struct rpc_message *msg, struct inode *dir)
+{
+        msg->rpc_proc = &nfs_procedures[NFSPROC_RENAME];
+}
+
+static int
+nfs_proc_rename_done(struct rpc_task *task, struct inode *old_dir,
+                     struct inode *new_dir)
+{
+        if (nfs_async_handle_expired_key(task))
+                return 0;
+        nfs_mark_for_revalidate(old_dir);
+        nfs_mark_for_revalidate(new_dir);
+        return 1;
+}
+
 static int
 nfs_proc_rename(struct inode *old_dir, struct qstr *old_name,
                 struct inode *new_dir, struct qstr *new_name)
 {
         struct nfs_renameargs   arg = {
-                .fromfh         = NFS_FH(old_dir),
-                .fromname       = old_name->name,
-                .fromlen        = old_name->len,
-                .tofh           = NFS_FH(new_dir),
-                .toname         = new_name->name,
-                .tolen          = new_name->len
+                .old_dir        = NFS_FH(old_dir),
+                .old_name       = old_name,
+                .new_dir        = NFS_FH(new_dir),
+                .new_name       = new_name,
         };
         struct rpc_message msg = {
                 .rpc_proc       = &nfs_procedures[NFSPROC_RENAME],
@@ -365,8 +433,8 @@ static int
 nfs_proc_symlink(struct inode *dir, struct dentry *dentry, struct page *page,
                  unsigned int len, struct iattr *sattr)
 {
-        struct nfs_fh fhandle;
-        struct nfs_fattr fattr;
+        struct nfs_fh *fh;
+        struct nfs_fattr *fattr;
         struct nfs_symlinkargs  arg = {
                 .fromfh         = NFS_FH(dir),
                 .fromname       = dentry->d_name.name,
@@ -379,12 +447,18 @@ nfs_proc_symlink(struct inode *dir, struct dentry *dentry, struct page *page,
                 .rpc_proc       = &nfs_procedures[NFSPROC_SYMLINK],
                 .rpc_argp       = &arg,
         };
-        int                     status;
+        int status = -ENAMETOOLONG;
+
+        dprintk("NFS call  symlink %s\n", dentry->d_name.name);
 
         if (len > NFS2_MAXPATHLEN)
-                return -ENAMETOOLONG;
+                goto out;
 
-        dprintk("NFS call  symlink %s\n", dentry->d_name.name);
+        fh = nfs_alloc_fhandle();
+        fattr = nfs_alloc_fattr();
+        status = -ENOMEM;
+        if (fh == NULL || fattr == NULL)
+                goto out_free;
 
         status = rpc_call_sync(NFS_CLIENT(dir), &msg, 0);
         nfs_mark_for_revalidate(dir);
@@ -394,12 +468,13 @@ nfs_proc_symlink(struct inode *dir, struct dentry *dentry, struct page *page,
          * filehandle size to zero indicates to nfs_instantiate that it
          * should fill in the data with a LOOKUP call on the wire.
          */
-        if (status == 0) {
-                nfs_fattr_init(&fattr);
-                fhandle.size = 0;
-                status = nfs_instantiate(dentry, &fhandle, &fattr);
-        }
+        if (status == 0)
+                status = nfs_instantiate(dentry, fh, fattr);
 
+out_free:
+        nfs_free_fattr(fattr);
+        nfs_free_fhandle(fh);
+out:
         dprintk("NFS reply symlink: %d\n", status);
         return status;
 }
@@ -407,31 +482,25 @@ nfs_proc_symlink(struct inode *dir, struct dentry *dentry, struct page *page,
 static int
 nfs_proc_mkdir(struct inode *dir, struct dentry *dentry, struct iattr *sattr)
 {
-        struct nfs_fh fhandle;
-        struct nfs_fattr fattr;
-        struct nfs_createargs   arg = {
-                .fh             = NFS_FH(dir),
-                .name           = dentry->d_name.name,
-                .len            = dentry->d_name.len,
-                .sattr          = sattr
-        };
-        struct nfs_diropok      res = {
-                .fh             = &fhandle,
-                .fattr          = &fattr
-        };
+        struct nfs_createdata *data;
         struct rpc_message msg = {
                 .rpc_proc       = &nfs_procedures[NFSPROC_MKDIR],
-                .rpc_argp       = &arg,
-                .rpc_resp       = &res,
         };
-        int                     status;
+        int status = -ENOMEM;
 
         dprintk("NFS call  mkdir %s\n", dentry->d_name.name);
-        nfs_fattr_init(&fattr);
+        data = nfs_alloc_createdata(dir, dentry, sattr);
+        if (data == NULL)
+                goto out;
+        msg.rpc_argp = &data->arg;
+        msg.rpc_resp = &data->res;
+
         status = rpc_call_sync(NFS_CLIENT(dir), &msg, 0);
         nfs_mark_for_revalidate(dir);
         if (status == 0)
-                status = nfs_instantiate(dentry, &fhandle, &fattr);
+                status = nfs_instantiate(dentry, data->res.fh, data->res.fattr);
+        nfs_free_createdata(data);
+out:
         dprintk("NFS reply mkdir: %d\n", status);
         return status;
 }
@@ -466,14 +535,14 @@ nfs_proc_rmdir(struct inode *dir, struct qstr *name)
  */
 static int
 nfs_proc_readdir(struct dentry *dentry, struct rpc_cred *cred,
-                 u64 cookie, struct page *page, unsigned int count, int plus)
+                 u64 cookie, struct page **pages, unsigned int count, int plus)
 {
         struct inode            *dir = dentry->d_inode;
         struct nfs_readdirargs  arg = {
                 .fh             = NFS_FH(dir),
                 .cookie         = cookie,
                 .count          = count,
-                .pages          = &page,
+                .pages          = pages,
         };
         struct rpc_message      msg = {
                 .rpc_proc       = &nfs_procedures[NFSPROC_READDIR],
@@ -561,6 +630,9 @@ nfs_proc_pathconf(struct nfs_server *server, struct nfs_fh *fhandle,
 
 static int nfs_read_done(struct rpc_task *task, struct nfs_read_data *data)
 {
+        if (nfs_async_handle_expired_key(task))
+                return -EAGAIN;
+
         nfs_invalidate_atime(data->inode);
         if (task->tk_status >= 0) {
                 nfs_refresh_inode(data->inode, data->res.fattr);
@@ -580,6 +652,9 @@ static void nfs_proc_read_setup(struct nfs_read_data *data, struct rpc_message *
 
 static int nfs_write_done(struct rpc_task *task, struct nfs_write_data *data)
 {
+        if (nfs_async_handle_expired_key(task))
+                return -EAGAIN;
+
         if (task->tk_status >= 0)
                 nfs_post_op_update_inode_force_wcc(data->inode, data->res.fattr);
         return 0;
@@ -646,6 +721,8 @@ const struct nfs_rpc_ops nfs_v2_clientops = {
         .unlink_setup   = nfs_proc_unlink_setup,
         .unlink_done    = nfs_proc_unlink_done,
         .rename         = nfs_proc_rename,
+        .rename_setup   = nfs_proc_rename_setup,
+        .rename_done    = nfs_proc_rename_done,
         .link           = nfs_proc_link,
         .symlink        = nfs_proc_symlink,
         .mkdir          = nfs_proc_mkdir,
@@ -655,7 +732,7 @@ const struct nfs_rpc_ops nfs_v2_clientops = {
         .statfs         = nfs_proc_statfs,
         .fsinfo         = nfs_proc_fsinfo,
         .pathconf       = nfs_proc_pathconf,
-        .decode_dirent  = nfs_decode_dirent,
+        .decode_dirent  = nfs2_decode_dirent,
         .read_setup     = nfs_proc_read_setup,
         .read_done      = nfs_read_done,
         .write_setup    = nfs_proc_write_setup,
diff --git a/fs/nfs/read.c b/fs/nfs/read.c
index 96c4ebfa46f4..aedcaa7f291f 100644
--- a/fs/nfs/read.c
+++ b/fs/nfs/read.c
@@ -18,7 +18,6 @@
 #include <linux/sunrpc/clnt.h>
 #include <linux/nfs_fs.h>
 #include <linux/nfs_page.h>
-#include <linux/smp_lock.h>
 
 #include <asm/system.h>
 
@@ -26,6 +25,7 @@
 #include "internal.h"
 #include "iostat.h"
 #include "fscache.h"
+#include "pnfs.h"
 
 #define NFSDBG_FACILITY         NFSDBG_PAGECACHE
 
@@ -41,17 +41,16 @@ static mempool_t *nfs_rdata_mempool;
 
 struct nfs_read_data *nfs_readdata_alloc(unsigned int pagecount)
 {
-        struct nfs_read_data *p = mempool_alloc(nfs_rdata_mempool, GFP_NOFS);
+        struct nfs_read_data *p = mempool_alloc(nfs_rdata_mempool, GFP_KERNEL);
 
         if (p) {
                 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 {
-                        p->pagevec = kcalloc(pagecount, sizeof(struct page *), GFP_NOFS);
+                        p->pagevec = kcalloc(pagecount, sizeof(struct page *), GFP_KERNEL);
                         if (!p->pagevec) {
                                 mempool_free(p, nfs_rdata_mempool);
                                 p = NULL;
@@ -61,17 +60,15 @@ struct nfs_read_data *nfs_readdata_alloc(unsigned int pagecount)
         return p;
 }
 
-static void nfs_readdata_free(struct nfs_read_data *p)
+void nfs_readdata_free(struct nfs_read_data *p)
 {
         if (p && (p->pagevec != &p->page_array[0]))
                 kfree(p->pagevec);
         mempool_free(p, nfs_rdata_mempool);
 }
 
-void nfs_readdata_release(void *data)
+static void nfs_readdata_release(struct nfs_read_data *rdata)
 {
-        struct nfs_read_data *rdata = data;
-
         put_nfs_open_context(rdata->args.context);
         nfs_readdata_free(rdata);
 }
@@ -124,6 +121,7 @@ int nfs_readpage_async(struct nfs_open_context *ctx, struct inode *inode,
         len = nfs_page_length(page);
         if (len == 0)
                 return nfs_return_empty_page(page);
+        pnfs_update_layout(inode, ctx, IOMODE_READ);
         new = nfs_create_request(ctx, inode, page, 0, len);
         if (IS_ERR(new)) {
                 unlock_page(page);
@@ -154,7 +152,6 @@ static void nfs_readpage_release(struct nfs_page *req)
                         (long long)NFS_FILEID(req->wb_context->path.dentry->d_inode),
                         req->wb_bytes,
                         (long long)req_offset(req));
-        nfs_clear_request(req);
         nfs_release_request(req);
 }
 
@@ -193,6 +190,7 @@ static int nfs_read_rpcsetup(struct nfs_page *req, struct nfs_read_data *data,
         data->args.pages  = data->pagevec;
         data->args.count  = count;
         data->args.context = get_nfs_open_context(req->wb_context);
+        data->args.lock_context = req->wb_lock_context;
 
         data->res.fattr   = &data->fattr;
         data->res.count   = count;
@@ -359,25 +357,19 @@ 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)
-                goto out;
+                return;
 
         /* This is a short read! */
         nfs_inc_stats(data->inode, NFSIOS_SHORTREAD);
         /* Has the server at least made some progress? */
         if (resp->count == 0)
-                goto out;
+                return;
 
         /* Yes, so retry the read at the end of the data */
         argp->offset += resp->count;
         argp->pgbase += resp->count;
         argp->count -= resp->count;
-        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;
-
+        nfs_restart_rpc(task, NFS_SERVER(data->inode)->nfs_client);
 }
 
 /*
@@ -419,7 +411,7 @@ 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,
+        if (nfs4_setup_sequence(NFS_SERVER(data->inode),
                                 &data->args.seq_args, &data->res.seq_res,
                                 0, task))
                 return;
@@ -633,6 +625,7 @@ int nfs_readpages(struct file *filp, struct address_space *mapping,
         if (ret == 0)
                 goto read_complete; /* all pages were read */
 
+        pnfs_update_layout(inode, desc.ctx, IOMODE_READ);
         if (rsize < PAGE_CACHE_SIZE)
                 nfs_pageio_init(&pgio, inode, nfs_pagein_multi, rsize, 0);
         else
diff --git a/fs/nfs/super.c b/fs/nfs/super.c
index 0b4cbdc60abd..0f9ea73e7789 100644
--- a/fs/nfs/super.c
+++ b/fs/nfs/super.c
@@ -39,7 +39,6 @@
 #include <linux/nfs_mount.h>
 #include <linux/nfs4_mount.h>
 #include <linux/lockd/bind.h>
-#include <linux/smp_lock.h>
 #include <linux/seq_file.h>
 #include <linux/mount.h>
 #include <linux/mnt_namespace.h>
@@ -48,6 +47,7 @@
 #include <linux/vfs.h>
 #include <linux/inet.h>
 #include <linux/in6.h>
+#include <linux/slab.h>
 #include <net/ipv6.h>
 #include <linux/netdevice.h>
 #include <linux/nfs_xdr.h>
@@ -66,6 +66,12 @@
 
 #define NFSDBG_FACILITY         NFSDBG_VFS
 
+#ifdef CONFIG_NFS_V3
+#define NFS_DEFAULT_VERSION 3
+#else
+#define NFS_DEFAULT_VERSION 2
+#endif
+
 enum {
         /* Mount options that take no arguments */
         Opt_soft, Opt_hard,
@@ -73,7 +79,7 @@ enum {
         Opt_cto, Opt_nocto,
         Opt_ac, Opt_noac,
         Opt_lock, Opt_nolock,
-        Opt_v2, Opt_v3,
+        Opt_v2, Opt_v3, Opt_v4,
         Opt_udp, Opt_tcp, Opt_rdma,
         Opt_acl, Opt_noacl,
         Opt_rdirplus, Opt_nordirplus,
@@ -99,6 +105,7 @@ enum {
         Opt_addr, Opt_mountaddr, Opt_clientaddr,
         Opt_lookupcache,
         Opt_fscache_uniq,
+        Opt_local_lock,
 
         /* Special mount options */
         Opt_userspace, Opt_deprecated, Opt_sloppy,
@@ -127,6 +134,7 @@ static const match_table_t nfs_mount_option_tokens = {
         { Opt_nolock, "nolock" },
         { Opt_v2, "v2" },
         { Opt_v3, "v3" },
+        { Opt_v4, "v4" },
         { Opt_udp, "udp" },
         { Opt_tcp, "tcp" },
         { Opt_rdma, "rdma" },
@@ -139,7 +147,6 @@ static const match_table_t nfs_mount_option_tokens = {
         { Opt_resvport, "resvport" },
         { Opt_noresvport, "noresvport" },
         { Opt_fscache, "fsc" },
-        { Opt_fscache_uniq, "fsc=%s" },
         { Opt_nofscache, "nofsc" },
 
         { Opt_port, "port=%s" },
@@ -158,7 +165,7 @@ static const match_table_t nfs_mount_option_tokens = {
         { Opt_mountvers, "mountvers=%s" },
         { Opt_nfsvers, "nfsvers=%s" },
         { Opt_nfsvers, "vers=%s" },
-        { Opt_minorversion, "minorversion=%u" },
+        { Opt_minorversion, "minorversion=%s" },
 
         { Opt_sec, "sec=%s" },
         { Opt_proto, "proto=%s" },
@@ -169,19 +176,23 @@ static const match_table_t nfs_mount_option_tokens = {
         { Opt_mountaddr, "mountaddr=%s" },
 
         { Opt_lookupcache, "lookupcache=%s" },
+        { Opt_fscache_uniq, "fsc=%s" },
+        { Opt_local_lock, "local_lock=%s" },
 
         { Opt_err, NULL }
 };
 
 enum {
-        Opt_xprt_udp, Opt_xprt_tcp, Opt_xprt_rdma,
+        Opt_xprt_udp, Opt_xprt_udp6, Opt_xprt_tcp, Opt_xprt_tcp6, Opt_xprt_rdma,
 
         Opt_xprt_err
 };
 
 static const match_table_t nfs_xprt_protocol_tokens = {
         { Opt_xprt_udp, "udp" },
+        { Opt_xprt_udp6, "udp6" },
         { Opt_xprt_tcp, "tcp" },
+        { Opt_xprt_tcp6, "tcp6" },
         { Opt_xprt_rdma, "rdma" },
 
         { Opt_xprt_err, NULL }
@@ -232,14 +243,31 @@ static match_table_t nfs_lookupcache_tokens = {
         { Opt_lookupcache_err, NULL }
 };
 
+enum {
+        Opt_local_lock_all, Opt_local_lock_flock, Opt_local_lock_posix,
+        Opt_local_lock_none,
+
+        Opt_local_lock_err
+};
+
+static match_table_t nfs_local_lock_tokens = {
+        { Opt_local_lock_all, "all" },
+        { Opt_local_lock_flock, "flock" },
+        { Opt_local_lock_posix, "posix" },
+        { Opt_local_lock_none, "none" },
+
+        { Opt_local_lock_err, NULL }
+};
+
 
 static void nfs_umount_begin(struct super_block *);
 static int  nfs_statfs(struct dentry *, struct kstatfs *);
 static int  nfs_show_options(struct seq_file *, struct vfsmount *);
 static int  nfs_show_stats(struct seq_file *, struct vfsmount *);
 static int nfs_get_sb(struct file_system_type *, int, const char *, void *, struct vfsmount *);
-static int nfs_xdev_get_sb(struct file_system_type *fs_type,
-                int flags, const char *dev_name, void *raw_data, struct vfsmount *mnt);
+static struct dentry *nfs_xdev_mount(struct file_system_type *fs_type,
+                int flags, const char *dev_name, void *raw_data);
+static void nfs_put_super(struct super_block *);
 static void nfs_kill_super(struct super_block *);
 static int nfs_remount(struct super_block *sb, int *flags, char *raw_data);
 
@@ -254,7 +282,7 @@ static struct file_system_type nfs_fs_type = {
 struct file_system_type nfs_xdev_fs_type = {
         .owner          = THIS_MODULE,
         .name           = "nfs",
-        .get_sb         = nfs_xdev_get_sb,
+        .mount          = nfs_xdev_mount,
         .kill_sb        = nfs_kill_super,
         .fs_flags       = FS_RENAME_DOES_D_MOVE|FS_REVAL_DOT|FS_BINARY_MOUNTDATA,
 };
@@ -263,8 +291,9 @@ static const struct super_operations nfs_sops = {
         .alloc_inode    = nfs_alloc_inode,
         .destroy_inode  = nfs_destroy_inode,
         .write_inode    = nfs_write_inode,
+        .put_super      = nfs_put_super,
         .statfs         = nfs_statfs,
-        .clear_inode    = nfs_clear_inode,
+        .evict_inode    = nfs_evict_inode,
         .umount_begin   = nfs_umount_begin,
         .show_options   = nfs_show_options,
         .show_stats     = nfs_show_stats,
@@ -272,16 +301,20 @@ static const struct super_operations nfs_sops = {
 };
 
 #ifdef CONFIG_NFS_V4
+static int nfs4_validate_text_mount_data(void *options,
+        struct nfs_parsed_mount_data *args, const char *dev_name);
+static int nfs4_try_mount(int flags, const char *dev_name,
+        struct nfs_parsed_mount_data *data, struct vfsmount *mnt);
 static int nfs4_get_sb(struct file_system_type *fs_type,
         int flags, const char *dev_name, void *raw_data, struct vfsmount *mnt);
-static int nfs4_remote_get_sb(struct file_system_type *fs_type,
-        int flags, const char *dev_name, void *raw_data, struct vfsmount *mnt);
-static int nfs4_xdev_get_sb(struct file_system_type *fs_type,
-        int flags, const char *dev_name, void *raw_data, struct vfsmount *mnt);
+static struct dentry *nfs4_remote_mount(struct file_system_type *fs_type,
+        int flags, const char *dev_name, void *raw_data);
+static struct dentry *nfs4_xdev_mount(struct file_system_type *fs_type,
+        int flags, const char *dev_name, void *raw_data);
 static int nfs4_referral_get_sb(struct file_system_type *fs_type,
         int flags, const char *dev_name, void *raw_data, struct vfsmount *mnt);
-static int nfs4_remote_referral_get_sb(struct file_system_type *fs_type,
-        int flags, const char *dev_name, void *raw_data, struct vfsmount *mnt);
+static struct dentry *nfs4_remote_referral_mount(struct file_system_type *fs_type,
+        int flags, const char *dev_name, void *raw_data);
 static void nfs4_kill_super(struct super_block *sb);
 
 static struct file_system_type nfs4_fs_type = {
@@ -295,7 +328,7 @@ static struct file_system_type nfs4_fs_type = {
 static struct file_system_type nfs4_remote_fs_type = {
         .owner          = THIS_MODULE,
         .name           = "nfs4",
-        .get_sb         = nfs4_remote_get_sb,
+        .mount          = nfs4_remote_mount,
         .kill_sb        = nfs4_kill_super,
         .fs_flags       = FS_RENAME_DOES_D_MOVE|FS_REVAL_DOT|FS_BINARY_MOUNTDATA,
 };
@@ -303,7 +336,7 @@ static struct file_system_type nfs4_remote_fs_type = {
 struct file_system_type nfs4_xdev_fs_type = {
         .owner          = THIS_MODULE,
         .name           = "nfs4",
-        .get_sb         = nfs4_xdev_get_sb,
+        .mount          = nfs4_xdev_mount,
         .kill_sb        = nfs4_kill_super,
         .fs_flags       = FS_RENAME_DOES_D_MOVE|FS_REVAL_DOT|FS_BINARY_MOUNTDATA,
 };
@@ -311,7 +344,7 @@ struct file_system_type nfs4_xdev_fs_type = {
 static struct file_system_type nfs4_remote_referral_fs_type = {
         .owner          = THIS_MODULE,
         .name           = "nfs4",
-        .get_sb         = nfs4_remote_referral_get_sb,
+        .mount          = nfs4_remote_referral_mount,
         .kill_sb        = nfs4_kill_super,
         .fs_flags       = FS_RENAME_DOES_D_MOVE|FS_REVAL_DOT|FS_BINARY_MOUNTDATA,
 };
@@ -328,8 +361,9 @@ static const struct super_operations nfs4_sops = {
         .alloc_inode    = nfs_alloc_inode,
         .destroy_inode  = nfs_destroy_inode,
         .write_inode    = nfs_write_inode,
+        .put_super      = nfs_put_super,
         .statfs         = nfs_statfs,
-        .clear_inode    = nfs4_clear_inode,
+        .evict_inode    = nfs4_evict_inode,
         .umount_begin   = nfs_umount_begin,
         .show_options   = nfs_show_options,
         .show_stats     = nfs_show_stats,
@@ -412,15 +446,27 @@ static int nfs_statfs(struct dentry *dentry, struct kstatfs *buf)
         unsigned char blockbits;
         unsigned long blockres;
         struct nfs_fh *fh = NFS_FH(dentry->d_inode);
-        struct nfs_fattr fattr;
-        struct nfs_fsstat res = {
-                        .fattr = &fattr,
-        };
-        int error;
+        struct nfs_fsstat res;
+        int error = -ENOMEM;
+
+        res.fattr = nfs_alloc_fattr();
+        if (res.fattr == NULL)
+                goto out_err;
 
         error = server->nfs_client->rpc_ops->statfs(server, fh, &res);
+        if (unlikely(error == -ESTALE)) {
+                struct dentry *pd_dentry;
+
+                pd_dentry = dget_parent(dentry);
+                if (pd_dentry != NULL) {
+                        nfs_zap_caches(pd_dentry->d_inode);
+                        dput(pd_dentry);
+                }
+        }
+        nfs_free_fattr(res.fattr);
         if (error < 0)
                 goto out_err;
+
         buf->f_type = NFS_SUPER_MAGIC;
 
         /*
@@ -487,11 +533,53 @@ static const char *nfs_pseudoflavour_to_name(rpc_authflavor_t flavour)
         return sec_flavours[i].str;
 }
 
+static void nfs_show_mountd_netid(struct seq_file *m, struct nfs_server *nfss,
+                                  int showdefaults)
+{
+        struct sockaddr *sap = (struct sockaddr *) &nfss->mountd_address;
+
+        seq_printf(m, ",mountproto=");
+        switch (sap->sa_family) {
+        case AF_INET:
+                switch (nfss->mountd_protocol) {
+                case IPPROTO_UDP:
+                        seq_printf(m, RPCBIND_NETID_UDP);
+                        break;
+                case IPPROTO_TCP:
+                        seq_printf(m, RPCBIND_NETID_TCP);
+                        break;
+                default:
+                        if (showdefaults)
+                                seq_printf(m, "auto");
+                }
+                break;
+        case AF_INET6:
+                switch (nfss->mountd_protocol) {
+                case IPPROTO_UDP:
+                        seq_printf(m, RPCBIND_NETID_UDP6);
+                        break;
+                case IPPROTO_TCP:
+                        seq_printf(m, RPCBIND_NETID_TCP6);
+                        break;
+                default:
+                        if (showdefaults)
+                                seq_printf(m, "auto");
+                }
+                break;
+        default:
+                if (showdefaults)
+                        seq_printf(m, "auto");
+        }
+}
+
 static void nfs_show_mountd_options(struct seq_file *m, struct nfs_server *nfss,
                                     int showdefaults)
 {
         struct sockaddr *sap = (struct sockaddr *)&nfss->mountd_address;
 
+        if (nfss->flags & NFS_MOUNT_LEGACY_INTERFACE)
+                return;
+
         switch (sap->sa_family) {
         case AF_INET: {
                 struct sockaddr_in *sin = (struct sockaddr_in *)sap;
@@ -500,7 +588,7 @@ static void nfs_show_mountd_options(struct seq_file *m, struct nfs_server *nfss,
         }
         case AF_INET6: {
                 struct sockaddr_in6 *sin6 = (struct sockaddr_in6 *)sap;
-                seq_printf(m, ",mountaddr=%pI6", &sin6->sin6_addr);
+                seq_printf(m, ",mountaddr=%pI6c", &sin6->sin6_addr);
                 break;
         }
         default:
@@ -510,22 +598,30 @@ static void nfs_show_mountd_options(struct seq_file *m, struct nfs_server *nfss,
 
         if (nfss->mountd_version || showdefaults)
                 seq_printf(m, ",mountvers=%u", nfss->mountd_version);
-        if (nfss->mountd_port || showdefaults)
+        if ((nfss->mountd_port &&
+                nfss->mountd_port != (unsigned short)NFS_UNSPEC_PORT) ||
+                showdefaults)
                 seq_printf(m, ",mountport=%u", nfss->mountd_port);
 
-        switch (nfss->mountd_protocol) {
-        case IPPROTO_UDP:
-                seq_printf(m, ",mountproto=udp");
-                break;
-        case IPPROTO_TCP:
-                seq_printf(m, ",mountproto=tcp");
-                break;
-        default:
-                if (showdefaults)
-                        seq_printf(m, ",mountproto=auto");
-        }
+        nfs_show_mountd_netid(m, nfss, showdefaults);
 }
 
+#ifdef CONFIG_NFS_V4
+static void nfs_show_nfsv4_options(struct seq_file *m, struct nfs_server *nfss,
+                                    int showdefaults)
+{
+        struct nfs_client *clp = nfss->nfs_client;
+
+        seq_printf(m, ",clientaddr=%s", clp->cl_ipaddr);
+        seq_printf(m, ",minorversion=%u", clp->cl_minorversion);
+}
+#else
+static void nfs_show_nfsv4_options(struct seq_file *m, struct nfs_server *nfss,
+                                    int showdefaults)
+{
+}
+#endif
+
 /*
  * Describe the mount options in force on this server representation
  */
@@ -551,6 +647,7 @@ static void nfs_show_mount_options(struct seq_file *m, struct nfs_server *nfss,
         const struct proc_nfs_info *nfs_infop;
         struct nfs_client *clp = nfss->nfs_client;
         u32 version = clp->rpc_ops->version;
+        int local_flock, local_fcntl;
 
         seq_printf(m, ",vers=%u", version);
         seq_printf(m, ",rsize=%u", nfss->rsize);
@@ -573,7 +670,7 @@ static void nfs_show_mount_options(struct seq_file *m, struct nfs_server *nfss,
                         seq_puts(m, nfs_infop->nostr);
         }
         seq_printf(m, ",proto=%s",
-                   rpc_peeraddr2str(nfss->client, RPC_DISPLAY_PROTO));
+                   rpc_peeraddr2str(nfss->client, RPC_DISPLAY_NETID));
         if (version == 4) {
                 if (nfss->port != NFS_PORT)
                         seq_printf(m, ",port=%u", nfss->port);
@@ -587,13 +684,30 @@ static void nfs_show_mount_options(struct seq_file *m, struct nfs_server *nfss,
 
         if (version != 4)
                 nfs_show_mountd_options(m, nfss, showdefaults);
+        else
+                nfs_show_nfsv4_options(m, nfss, showdefaults);
 
-#ifdef CONFIG_NFS_V4
-        if (clp->rpc_ops->version == 4)
-                seq_printf(m, ",clientaddr=%s", clp->cl_ipaddr);
-#endif
         if (nfss->options & NFS_OPTION_FSCACHE)
                 seq_printf(m, ",fsc");
+
+        if (nfss->flags & NFS_MOUNT_LOOKUP_CACHE_NONEG) {
+                if (nfss->flags & NFS_MOUNT_LOOKUP_CACHE_NONE)
+                        seq_printf(m, ",lookupcache=none");
+                else
+                        seq_printf(m, ",lookupcache=pos");
+        }
+
+        local_flock = nfss->flags & NFS_MOUNT_LOCAL_FLOCK;
+        local_fcntl = nfss->flags & NFS_MOUNT_LOCAL_FCNTL;
+
+        if (!local_flock && !local_fcntl)
+                seq_printf(m, ",local_lock=none");
+        else if (local_flock && local_fcntl)
+                seq_printf(m, ",local_lock=all");
+        else if (local_flock)
+                seq_printf(m, ",local_lock=flock");
+        else
+                seq_printf(m, ",local_lock=posix");
 }
 
 /*
@@ -709,8 +823,6 @@ static void nfs_umount_begin(struct super_block *sb)
         struct nfs_server *server;
         struct rpc_clnt *rpc;
 
-        lock_kernel();
-
         server = NFS_SB(sb);
         /* -EIO all pending I/O */
         rpc = server->client_acl;
@@ -719,8 +831,27 @@ static void nfs_umount_begin(struct super_block *sb)
         rpc = server->client;
         if (!IS_ERR(rpc))
                 rpc_killall_tasks(rpc);
+}
+
+static struct nfs_parsed_mount_data *nfs_alloc_parsed_mount_data(unsigned int version)
+{
+        struct nfs_parsed_mount_data *data;
 
-        unlock_kernel();
+        data = kzalloc(sizeof(*data), GFP_KERNEL);
+        if (data) {
+                data->acregmin          = NFS_DEF_ACREGMIN;
+                data->acregmax          = NFS_DEF_ACREGMAX;
+                data->acdirmin          = NFS_DEF_ACDIRMIN;
+                data->acdirmax          = NFS_DEF_ACDIRMAX;
+                data->mount_server.port = NFS_UNSPEC_PORT;
+                data->nfs_server.port   = NFS_UNSPEC_PORT;
+                data->nfs_server.protocol = XPRT_TRANSPORT_TCP;
+                data->auth_flavors[0]   = RPC_AUTH_UNIX;
+                data->auth_flavor_len   = 1;
+                data->version           = version;
+                data->minorversion      = 0;
+        }
+        return data;
 }
 
 /*
@@ -742,127 +873,21 @@ static int nfs_verify_server_address(struct sockaddr *addr)
         }
         }
 
+        dfprintk(MOUNT, "NFS: Invalid IP address specified\n");
         return 0;
 }
 
-static void nfs_parse_ipv4_address(char *string, size_t str_len,
-                                   struct sockaddr *sap, size_t *addr_len)
-{
-        struct sockaddr_in *sin = (struct sockaddr_in *)sap;
-        u8 *addr = (u8 *)&sin->sin_addr.s_addr;
-
-        if (str_len <= INET_ADDRSTRLEN) {
-                dfprintk(MOUNT, "NFS: parsing IPv4 address %*s\n",
-                                (int)str_len, string);
-
-                sin->sin_family = AF_INET;
-                *addr_len = sizeof(*sin);
-                if (in4_pton(string, str_len, addr, '\0', NULL))
-                        return;
-        }
-
-        sap->sa_family = AF_UNSPEC;
-        *addr_len = 0;
-}
-
-#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
-static int nfs_parse_ipv6_scope_id(const char *string, const size_t str_len,
-                                   const char *delim,
-                                   struct sockaddr_in6 *sin6)
-{
-        char *p;
-        size_t len;
-
-        if ((string + str_len) == delim)
-                return 1;
-
-        if (*delim != IPV6_SCOPE_DELIMITER)
-                return 0;
-
-        if (!(ipv6_addr_type(&sin6->sin6_addr) & IPV6_ADDR_LINKLOCAL))
-                return 0;
-
-        len = (string + str_len) - delim - 1;
-        p = kstrndup(delim + 1, len, GFP_KERNEL);
-        if (p) {
-                unsigned long scope_id = 0;
-                struct net_device *dev;
-
-                dev = dev_get_by_name(&init_net, p);
-                if (dev != NULL) {
-                        scope_id = dev->ifindex;
-                        dev_put(dev);
-                } else {
-                        if (strict_strtoul(p, 10, &scope_id) == 0) {
-                                kfree(p);
-                                return 0;
-                        }
-                }
-
-                kfree(p);
-
-                sin6->sin6_scope_id = scope_id;
-                dfprintk(MOUNT, "NFS: IPv6 scope ID = %lu\n", scope_id);
-                return 1;
-        }
-
-        return 0;
-}
-
-static void nfs_parse_ipv6_address(char *string, size_t str_len,
-                                   struct sockaddr *sap, size_t *addr_len)
-{
-        struct sockaddr_in6 *sin6 = (struct sockaddr_in6 *)sap;
-        u8 *addr = (u8 *)&sin6->sin6_addr.in6_u;
-        const char *delim;
-
-        if (str_len <= INET6_ADDRSTRLEN) {
-                dfprintk(MOUNT, "NFS: parsing IPv6 address %*s\n",
-                                (int)str_len, string);
-
-                sin6->sin6_family = AF_INET6;
-                *addr_len = sizeof(*sin6);
-                if (in6_pton(string, str_len, addr,
-                                        IPV6_SCOPE_DELIMITER, &delim) != 0) {
-                        if (nfs_parse_ipv6_scope_id(string, str_len,
-                                                        delim, sin6) != 0)
-                                return;
-                }
-        }
-
-        sap->sa_family = AF_UNSPEC;
-        *addr_len = 0;
-}
-#else
-static void nfs_parse_ipv6_address(char *string, size_t str_len,
-                                   struct sockaddr *sap, size_t *addr_len)
-{
-        sap->sa_family = AF_UNSPEC;
-        *addr_len = 0;
-}
-#endif
-
 /*
- * Construct a sockaddr based on the contents of a string that contains
- * an IP address in presentation format.
- *
- * If there is a problem constructing the new sockaddr, set the address
- * family to AF_UNSPEC.
+ * Select between a default port value and a user-specified port value.
+ * If a zero value is set, then autobind will be used.
  */
-void nfs_parse_ip_address(char *string, size_t str_len,
-                                 struct sockaddr *sap, size_t *addr_len)
+static void nfs_set_port(struct sockaddr *sap, int *port,
+                                 const unsigned short default_port)
 {
-        unsigned int i, colons;
-
-        colons = 0;
-        for (i = 0; i < str_len; i++)
-                if (string[i] == ':')
-                        colons++;
+        if (*port == NFS_UNSPEC_PORT)
+                *port = default_port;
 
-        if (colons >= 2)
-                nfs_parse_ipv6_address(string, str_len, sap, addr_len);
-        else
-                nfs_parse_ipv4_address(string, str_len, sap, addr_len);
+        rpc_set_port(sap, *port);
 }
 
 /*
@@ -904,8 +929,6 @@ static void nfs_set_mount_transport_protocol(struct nfs_parsed_mount_data *mnt)
 
 /*
  * Parse the value of the 'sec=' option.
- *
- * The flavor_len setting is for v4 mounts.
  */
 static int nfs_parse_security_flavors(char *value,
                                       struct nfs_parsed_mount_data *mnt)
@@ -916,53 +939,43 @@ static int nfs_parse_security_flavors(char *value,
 
         switch (match_token(value, nfs_secflavor_tokens, args)) {
         case Opt_sec_none:
-                mnt->auth_flavor_len = 0;
                 mnt->auth_flavors[0] = RPC_AUTH_NULL;
                 break;
         case Opt_sec_sys:
-                mnt->auth_flavor_len = 0;
                 mnt->auth_flavors[0] = RPC_AUTH_UNIX;
                 break;
         case Opt_sec_krb5:
-                mnt->auth_flavor_len = 1;
                 mnt->auth_flavors[0] = RPC_AUTH_GSS_KRB5;
                 break;
         case Opt_sec_krb5i:
-                mnt->auth_flavor_len = 1;
                 mnt->auth_flavors[0] = RPC_AUTH_GSS_KRB5I;
                 break;
         case Opt_sec_krb5p:
-                mnt->auth_flavor_len = 1;
                 mnt->auth_flavors[0] = RPC_AUTH_GSS_KRB5P;
                 break;
         case Opt_sec_lkey:
-                mnt->auth_flavor_len = 1;
                 mnt->auth_flavors[0] = RPC_AUTH_GSS_LKEY;
                 break;
         case Opt_sec_lkeyi:
-                mnt->auth_flavor_len = 1;
                 mnt->auth_flavors[0] = RPC_AUTH_GSS_LKEYI;
                 break;
         case Opt_sec_lkeyp:
-                mnt->auth_flavor_len = 1;
                 mnt->auth_flavors[0] = RPC_AUTH_GSS_LKEYP;
                 break;
         case Opt_sec_spkm:
-                mnt->auth_flavor_len = 1;
                 mnt->auth_flavors[0] = RPC_AUTH_GSS_SPKM;
                 break;
         case Opt_sec_spkmi:
-                mnt->auth_flavor_len = 1;
                 mnt->auth_flavors[0] = RPC_AUTH_GSS_SPKMI;
                 break;
         case Opt_sec_spkmp:
-                mnt->auth_flavor_len = 1;
                 mnt->auth_flavors[0] = RPC_AUTH_GSS_SPKMP;
                 break;
         default:
                 return 0;
         }
 
+        mnt->auth_flavor_len = 1;
         return 1;
 }
 
@@ -977,6 +990,8 @@ static int nfs_parse_mount_options(char *raw,
 {
         char *p, *string, *secdata;
         int rc, sloppy = 0, invalid_option = 0;
+        unsigned short protofamily = AF_UNSPEC;
+        unsigned short mountfamily = AF_UNSPEC;
 
         if (!raw) {
                 dfprintk(MOUNT, "NFS: mount options string was NULL.\n");
@@ -1001,7 +1016,6 @@ static int nfs_parse_mount_options(char *raw,
         while ((p = strsep(&raw, ",")) != NULL) {
                 substring_t args[MAX_OPT_ARGS];
                 unsigned long option;
-                int int_option;
                 int token;
 
                 if (!*p)
@@ -1041,15 +1055,25 @@ static int nfs_parse_mount_options(char *raw,
                         break;
                 case Opt_lock:
                         mnt->flags &= ~NFS_MOUNT_NONLM;
+                        mnt->flags &= ~(NFS_MOUNT_LOCAL_FLOCK |
+                                        NFS_MOUNT_LOCAL_FCNTL);
                         break;
                 case Opt_nolock:
                         mnt->flags |= NFS_MOUNT_NONLM;
+                        mnt->flags |= (NFS_MOUNT_LOCAL_FLOCK |
+                                       NFS_MOUNT_LOCAL_FCNTL);
                         break;
                 case Opt_v2:
                         mnt->flags &= ~NFS_MOUNT_VER3;
+                        mnt->version = 2;
                         break;
                 case Opt_v3:
                         mnt->flags |= NFS_MOUNT_VER3;
+                        mnt->version = 3;
+                        break;
+                case Opt_v4:
+                        mnt->flags &= ~NFS_MOUNT_VER3;
+                        mnt->version = 4;
                         break;
                 case Opt_udp:
                         mnt->flags &= ~NFS_MOUNT_TCP;
@@ -1098,14 +1122,6 @@ static int nfs_parse_mount_options(char *raw,
                         kfree(mnt->fscache_uniq);
                         mnt->fscache_uniq = NULL;
                         break;
-                case Opt_fscache_uniq:
-                        string = match_strdup(args);
-                        if (!string)
-                                goto out_nomem;
-                        kfree(mnt->fscache_uniq);
-                        mnt->fscache_uniq = string;
-                        mnt->options |= NFS_OPTION_FSCACHE;
-                        break;
 
                 /*
                  * options that take numeric values
@@ -1116,7 +1132,7 @@ static int nfs_parse_mount_options(char *raw,
                                 goto out_nomem;
                         rc = strict_strtoul(string, 10, &option);
                         kfree(string);
-                        if (rc != 0 || option > USHORT_MAX)
+                        if (rc != 0 || option > USHRT_MAX)
                                 goto out_invalid_value;
                         mnt->nfs_server.port = option;
                         break;
@@ -1237,7 +1253,7 @@ static int nfs_parse_mount_options(char *raw,
                                 goto out_nomem;
                         rc = strict_strtoul(string, 10, &option);
                         kfree(string);
-                        if (rc != 0 || option > USHORT_MAX)
+                        if (rc != 0 || option > USHRT_MAX)
                                 goto out_invalid_value;
                         mnt->mount_server.port = option;
                         break;
@@ -1264,20 +1280,31 @@ static int nfs_parse_mount_options(char *raw,
                         switch (option) {
                         case NFS2_VERSION:
                                 mnt->flags &= ~NFS_MOUNT_VER3;
+                                mnt->version = 2;
                                 break;
                         case NFS3_VERSION:
                                 mnt->flags |= NFS_MOUNT_VER3;
+                                mnt->version = 3;
+                                break;
+                        case NFS4_VERSION:
+                                mnt->flags &= ~NFS_MOUNT_VER3;
+                                mnt->version = 4;
                                 break;
                         default:
                                 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;
+                        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;
+                        if (option > NFS4_MAX_MINOR_VERSION)
+                                goto out_invalid_value;
+                        mnt->minorversion = option;
                         break;
 
                 /*
@@ -1302,12 +1329,17 @@ static int nfs_parse_mount_options(char *raw,
                         token = match_token(string,
                                             nfs_xprt_protocol_tokens, args);
 
+                        protofamily = AF_INET;
                         switch (token) {
+                        case Opt_xprt_udp6:
+                                protofamily = AF_INET6;
                         case Opt_xprt_udp:
                                 mnt->flags &= ~NFS_MOUNT_TCP;
                                 mnt->nfs_server.protocol = XPRT_TRANSPORT_UDP;
                                 kfree(string);
                                 break;
+                        case Opt_xprt_tcp6:
+                                protofamily = AF_INET6;
                         case Opt_xprt_tcp:
                                 mnt->flags |= NFS_MOUNT_TCP;
                                 mnt->nfs_server.protocol = XPRT_TRANSPORT_TCP;
@@ -1323,6 +1355,7 @@ static int nfs_parse_mount_options(char *raw,
                         default:
                                 dfprintk(MOUNT, "NFS:   unrecognized "
                                                 "transport protocol\n");
+                                kfree(string);
                                 return 0;
                         }
                         break;
@@ -1334,10 +1367,15 @@ static int nfs_parse_mount_options(char *raw,
                                             nfs_xprt_protocol_tokens, args);
                         kfree(string);
 
+                        mountfamily = AF_INET;
                         switch (token) {
+                        case Opt_xprt_udp6:
+                                mountfamily = AF_INET6;
                         case Opt_xprt_udp:
                                 mnt->mount_server.protocol = XPRT_TRANSPORT_UDP;
                                 break;
+                        case Opt_xprt_tcp6:
+                                mountfamily = AF_INET6;
                         case Opt_xprt_tcp:
                                 mnt->mount_server.protocol = XPRT_TRANSPORT_TCP;
                                 break;
@@ -1352,11 +1390,14 @@ static int nfs_parse_mount_options(char *raw,
                         string = match_strdup(args);
                         if (string == NULL)
                                 goto out_nomem;
-                        nfs_parse_ip_address(string, strlen(string),
-                                             (struct sockaddr *)
-                                                &mnt->nfs_server.address,
-                                             &mnt->nfs_server.addrlen);
+                        mnt->nfs_server.addrlen =
+                                rpc_pton(string, strlen(string),
+                                        (struct sockaddr *)
+                                        &mnt->nfs_server.address,
+                                        sizeof(mnt->nfs_server.address));
                         kfree(string);
+                        if (mnt->nfs_server.addrlen == 0)
+                                goto out_invalid_address;
                         break;
                 case Opt_clientaddr:
                         string = match_strdup(args);
@@ -1376,11 +1417,14 @@ static int nfs_parse_mount_options(char *raw,
                         string = match_strdup(args);
                         if (string == NULL)
                                 goto out_nomem;
-                        nfs_parse_ip_address(string, strlen(string),
-                                             (struct sockaddr *)
-                                                &mnt->mount_server.address,
-                                             &mnt->mount_server.addrlen);
+                        mnt->mount_server.addrlen =
+                                rpc_pton(string, strlen(string),
+                                        (struct sockaddr *)
+                                        &mnt->mount_server.address,
+                                        sizeof(mnt->mount_server.address));
                         kfree(string);
+                        if (mnt->mount_server.addrlen == 0)
+                                goto out_invalid_address;
                         break;
                 case Opt_lookupcache:
                         string = match_strdup(args);
@@ -1406,6 +1450,42 @@ static int nfs_parse_mount_options(char *raw,
                                         return 0;
                         };
                         break;
+                case Opt_fscache_uniq:
+                        string = match_strdup(args);
+                        if (string == NULL)
+                                goto out_nomem;
+                        kfree(mnt->fscache_uniq);
+                        mnt->fscache_uniq = string;
+                        mnt->options |= NFS_OPTION_FSCACHE;
+                        break;
+                case Opt_local_lock:
+                        string = match_strdup(args);
+                        if (string == NULL)
+                                goto out_nomem;
+                        token = match_token(string, nfs_local_lock_tokens,
+                                        args);
+                        kfree(string);
+                        switch (token) {
+                        case Opt_local_lock_all:
+                                mnt->flags |= (NFS_MOUNT_LOCAL_FLOCK |
+                                               NFS_MOUNT_LOCAL_FCNTL);
+                                break;
+                        case Opt_local_lock_flock:
+                                mnt->flags |= NFS_MOUNT_LOCAL_FLOCK;
+                                break;
+                        case Opt_local_lock_posix:
+                                mnt->flags |= NFS_MOUNT_LOCAL_FCNTL;
+                                break;
+                        case Opt_local_lock_none:
+                                mnt->flags &= ~(NFS_MOUNT_LOCAL_FLOCK |
+                                                NFS_MOUNT_LOCAL_FCNTL);
+                                break;
+                        default:
+                                dfprintk(MOUNT, "NFS:   invalid "
+                                                "local_lock argument\n");
+                                return 0;
+                        };
+                        break;
 
                 /*
                  * Special options
@@ -1430,10 +1510,38 @@ static int nfs_parse_mount_options(char *raw,
         if (!sloppy && invalid_option)
                 return 0;
 
+        /*
+         * verify that any proto=/mountproto= options match the address
+         * familiies in the addr=/mountaddr= options.
+         */
+        if (protofamily != AF_UNSPEC &&
+            protofamily != mnt->nfs_server.address.ss_family)
+                goto out_proto_mismatch;
+
+        if (mountfamily != AF_UNSPEC) {
+                if (mnt->mount_server.addrlen) {
+                        if (mountfamily != mnt->mount_server.address.ss_family)
+                                goto out_mountproto_mismatch;
+                } else {
+                        if (mountfamily != mnt->nfs_server.address.ss_family)
+                                goto out_mountproto_mismatch;
+                }
+        }
+
         return 1;
 
+out_mountproto_mismatch:
+        printk(KERN_INFO "NFS: mount server address does not match mountproto= "
+                         "option\n");
+        return 0;
+out_proto_mismatch:
+        printk(KERN_INFO "NFS: server address does not match proto= option\n");
+        return 0;
+out_invalid_address:
+        printk(KERN_INFO "NFS: bad IP address specified: %s\n", p);
+        return 0;
 out_invalid_value:
-        printk(KERN_INFO "NFS: bad mount option value specified: %s \n", p);
+        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");
@@ -1445,13 +1553,60 @@ out_security_failure:
 }
 
 /*
+ * Match the requested auth flavors with the list returned by
+ * the server.  Returns zero and sets the mount's authentication
+ * flavor on success; returns -EACCES if server does not support
+ * the requested flavor.
+ */
+static int nfs_walk_authlist(struct nfs_parsed_mount_data *args,
+                             struct nfs_mount_request *request)
+{
+        unsigned int i, j, server_authlist_len = *(request->auth_flav_len);
+
+        /*
+         * Certain releases of Linux's mountd return an empty
+         * flavor list.  To prevent behavioral regression with
+         * these servers (ie. rejecting mounts that used to
+         * succeed), revert to pre-2.6.32 behavior (no checking)
+         * if the returned flavor list is empty.
+         */
+        if (server_authlist_len == 0)
+                return 0;
+
+        /*
+         * We avoid sophisticated negotiating here, as there are
+         * plenty of cases where we can get it wrong, providing
+         * either too little or too much security.
+         *
+         * RFC 2623, section 2.7 suggests we SHOULD prefer the
+         * flavor listed first.  However, some servers list
+         * AUTH_NULL first.  Our caller plants AUTH_SYS, the
+         * preferred default, in args->auth_flavors[0] if user
+         * didn't specify sec= mount option.
+         */
+        for (i = 0; i < args->auth_flavor_len; i++)
+                for (j = 0; j < server_authlist_len; j++)
+                        if (args->auth_flavors[i] == request->auth_flavs[j]) {
+                                dfprintk(MOUNT, "NFS: using auth flavor %d\n",
+                                        request->auth_flavs[j]);
+                                args->auth_flavors[0] = request->auth_flavs[j];
+                                return 0;
+                        }
+
+        dfprintk(MOUNT, "NFS: server does not support requested auth flavor\n");
+        nfs_umount(request);
+        return -EACCES;
+}
+
+/*
  * Use the remote server's MOUNT service to request the NFS file handle
  * corresponding to the provided path.
  */
 static int nfs_try_mount(struct nfs_parsed_mount_data *args,
                          struct nfs_fh *root_fh)
 {
-        unsigned int auth_flavor_len = 0;
+        rpc_authflavor_t server_authlist[NFS_MAX_SECFLAVORS];
+        unsigned int server_authlist_len = ARRAY_SIZE(server_authlist);
         struct nfs_mount_request request = {
                 .sap            = (struct sockaddr *)
                                                 &args->mount_server.address,
@@ -1459,15 +1614,19 @@ 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,
+                .auth_flav_len  = &server_authlist_len,
+                .auth_flavs     = server_authlist,
         };
         int status;
 
         if (args->mount_server.version == 0) {
-                if (args->flags & NFS_MOUNT_VER3)
-                        args->mount_server.version = NFS_MNT3_VERSION;
-                else
-                        args->mount_server.version = NFS_MNT_VERSION;
+                switch (args->version) {
+                        default:
+                                args->mount_server.version = NFS_MNT3_VERSION;
+                                break;
+                        case 2:
+                                args->mount_server.version = NFS_MNT_VERSION;
+                }
         }
         request.version = args->mount_server.version;
 
@@ -1485,23 +1644,25 @@ static int nfs_try_mount(struct nfs_parsed_mount_data *args,
                 args->mount_server.addrlen = args->nfs_server.addrlen;
         }
         request.salen = args->mount_server.addrlen;
-
-        /*
-         * autobind will be used if mount_server.port == 0
-         */
-        nfs_set_port(request.sap, args->mount_server.port);
+        nfs_set_port(request.sap, &args->mount_server.port, 0);
 
         /*
          * Now ask the mount server to map our export path
          * to a file handle.
          */
         status = nfs_mount(&request);
-        if (status == 0)
-                return 0;
+        if (status != 0) {
+                dfprintk(MOUNT, "NFS: unable to mount server %s, error %d\n",
+                                request.hostname, status);
+                return status;
+        }
 
-        dfprintk(MOUNT, "NFS: unable to mount server %s, error %d\n",
-                        request.hostname, status);
-        return status;
+        /*
+         * MNTv1 (NFSv2) does not support auth flavor negotiation.
+         */
+        if (args->mount_server.version != NFS_MNT3_VERSION)
+                return 0;
+        return nfs_walk_authlist(args, &request);
 }
 
 static int nfs_parse_simple_hostname(const char *dev_name,
@@ -1661,22 +1822,11 @@ static int nfs_validate_mount_data(void *options,
                                    const char *dev_name)
 {
         struct nfs_mount_data *data = (struct nfs_mount_data *)options;
+        struct sockaddr *sap = (struct sockaddr *)&args->nfs_server.address;
 
         if (data == NULL)
                 goto out_no_data;
 
-        args->flags             = (NFS_MOUNT_VER3 | NFS_MOUNT_TCP);
-        args->rsize             = NFS_MAX_FILE_IO_SIZE;
-        args->wsize             = NFS_MAX_FILE_IO_SIZE;
-        args->acregmin          = NFS_DEF_ACREGMIN;
-        args->acregmax          = NFS_DEF_ACREGMAX;
-        args->acdirmin          = NFS_DEF_ACDIRMIN;
-        args->acdirmax          = NFS_DEF_ACDIRMAX;
-        args->mount_server.port = 0;    /* autobind unless user sets port */
-        args->nfs_server.port   = 0;    /* autobind unless user sets port */
-        args->nfs_server.protocol = XPRT_TRANSPORT_TCP;
-        args->auth_flavors[0]   = RPC_AUTH_UNIX;
-
         switch (data->version) {
         case 1:
                 data->namlen = 0;
@@ -1697,8 +1847,11 @@ static int nfs_validate_mount_data(void *options,
                         if (data->root.size > NFS3_FHSIZE || data->root.size == 0)
                                 goto out_invalid_fh;
                         mntfh->size = data->root.size;
-                } else
+                        args->version = 3;
+                } else {
                         mntfh->size = NFS2_FHSIZE;
+                        args->version = 2;
+                }
 
 
                 memcpy(mntfh->data, data->root.data, mntfh->size);
@@ -1711,6 +1864,7 @@ static int nfs_validate_mount_data(void *options,
                  * can deal with.
                  */
                 args->flags             = data->flags & NFS_MOUNT_FLAGMASK;
+                args->flags             |= NFS_MOUNT_LEGACY_INTERFACE;
                 args->rsize             = data->rsize;
                 args->wsize             = data->wsize;
                 args->timeo             = data->timeo;
@@ -1720,11 +1874,9 @@ static int nfs_validate_mount_data(void *options,
                 args->acdirmin          = data->acdirmin;
                 args->acdirmax          = data->acdirmax;
 
-                memcpy(&args->nfs_server.address, &data->addr,
-                       sizeof(data->addr));
+                memcpy(sap, &data->addr, sizeof(data->addr));
                 args->nfs_server.addrlen = sizeof(data->addr);
-                if (!nfs_verify_server_address((struct sockaddr *)
-                                                &args->nfs_server.address))
+                if (!nfs_verify_server_address(sap))
                         goto out_no_address;
 
                 if (!(data->flags & NFS_MOUNT_TCP))
@@ -1739,6 +1891,12 @@ static int nfs_validate_mount_data(void *options,
                 if (!args->nfs_server.hostname)
                         goto out_nomem;
 
+                if (!(data->flags & NFS_MOUNT_NONLM))
+                        args->flags &= ~(NFS_MOUNT_LOCAL_FLOCK|
+                                         NFS_MOUNT_LOCAL_FCNTL);
+                else
+                        args->flags |= (NFS_MOUNT_LOCAL_FLOCK|
+                                        NFS_MOUNT_LOCAL_FCNTL);
                 /*
                  * The legacy version 6 binary mount data from userspace has a
                  * field used only to transport selinux information into the
@@ -1772,12 +1930,18 @@ static int nfs_validate_mount_data(void *options,
                 if (nfs_parse_mount_options((char *)options, args) == 0)
                         return -EINVAL;
 
-                if (!nfs_verify_server_address((struct sockaddr *)
-                                                &args->nfs_server.address))
+                if (!nfs_verify_server_address(sap))
                         goto out_no_address;
 
-                nfs_set_port((struct sockaddr *)&args->nfs_server.address,
-                                args->nfs_server.port);
+                if (args->version == 4)
+#ifdef CONFIG_NFS_V4
+                        return nfs4_validate_text_mount_data(options,
+                                                             args, dev_name);
+#else
+                        goto out_v4_not_compiled;
+#endif
+
+                nfs_set_port(sap, &args->nfs_server.port, 0);
 
                 nfs_set_mount_transport_protocol(args);
 
@@ -1800,7 +1964,7 @@ static int nfs_validate_mount_data(void *options,
         }
 
 #ifndef CONFIG_NFS_V3
-        if (args->flags & NFS_MOUNT_VER3)
+        if (args->version == 3)
                 goto out_v3_not_compiled;
 #endif /* !CONFIG_NFS_V3 */
 
@@ -1825,6 +1989,12 @@ out_v3_not_compiled:
         return -EPROTONOSUPPORT;
 #endif /* !CONFIG_NFS_V3 */
 
+#ifndef CONFIG_NFS_V4
+out_v4_not_compiled:
+        dfprintk(MOUNT, "NFS: NFSv4 is not compiled into kernel\n");
+        return -EPROTONOSUPPORT;
+#endif /* !CONFIG_NFS_V4 */
+
 out_nomem:
         dfprintk(MOUNT, "NFS: not enough memory to handle mount options\n");
         return -ENOMEM;
@@ -1852,9 +2022,10 @@ nfs_compare_remount_data(struct nfs_server *nfss,
             data->acdirmin != nfss->acdirmin / HZ ||
             data->acdirmax != nfss->acdirmax / HZ ||
             data->timeo != (10U * nfss->client->cl_timeout->to_initval / HZ) ||
+            data->nfs_server.port != nfss->port ||
             data->nfs_server.addrlen != nfss->nfs_client->cl_addrlen ||
-            memcmp(&data->nfs_server.address, &nfss->nfs_client->cl_addr,
-                   data->nfs_server.addrlen) != 0)
+            !rpc_cmp_addr((struct sockaddr *)&data->nfs_server.address,
+                          (struct sockaddr *)&nfss->nfs_client->cl_addr))
                 return -EINVAL;
 
         return 0;
@@ -1885,7 +2056,6 @@ nfs_remount(struct super_block *sb, int *flags, char *raw_data)
         if (data == NULL)
                 return -ENOMEM;
 
-        lock_kernel();
         /* fill out struct with values from existing mount */
         data->flags = nfss->flags;
         data->rsize = nfss->rsize;
@@ -1897,6 +2067,7 @@ nfs_remount(struct super_block *sb, int *flags, char *raw_data)
         data->acdirmin = nfss->acdirmin / HZ;
         data->acdirmax = nfss->acdirmax / HZ;
         data->timeo = 10U * nfss->client->cl_timeout->to_initval / HZ;
+        data->nfs_server.port = nfss->port;
         data->nfs_server.addrlen = nfss->nfs_client->cl_addrlen;
         memcpy(&data->nfs_server.address, &nfss->nfs_client->cl_addr,
                 data->nfs_server.addrlen);
@@ -1910,7 +2081,6 @@ nfs_remount(struct super_block *sb, int *flags, char *raw_data)
         error = nfs_compare_remount_data(nfss, data);
 out:
         kfree(data);
-        unlock_kernel();
         return error;
 }
 
@@ -1934,6 +2104,8 @@ static inline void nfs_initialise_sb(struct super_block *sb)
         if (server->flags & NFS_MOUNT_NOAC)
                 sb->s_flags |= MS_SYNCHRONOUS;
 
+        sb->s_bdi = &server->backing_dev_info;
+
         nfs_super_set_maxbytes(sb, server->maxfilesize);
 }
 
@@ -1950,7 +2122,7 @@ static void nfs_fill_super(struct super_block *sb,
         if (data->bsize)
                 sb->s_blocksize = nfs_block_size(data->bsize, &sb->s_blocksize_bits);
 
-        if (server->flags & NFS_MOUNT_VER3) {
+        if (server->nfs_client->rpc_ops->version == 3) {
                 /* The VFS shouldn't apply the umask to mode bits. We will do
                  * so ourselves when necessary.
                  */
@@ -1974,7 +2146,7 @@ static void nfs_clone_super(struct super_block *sb,
         sb->s_blocksize = old_sb->s_blocksize;
         sb->s_maxbytes = old_sb->s_maxbytes;
 
-        if (server->flags & NFS_MOUNT_VER3) {
+        if (server->nfs_client->rpc_ops->version == 3) {
                 /* The VFS shouldn't apply the umask to mode bits. We will do
                  * so ourselves when necessary.
                  */
@@ -2108,8 +2280,8 @@ static int nfs_get_sb(struct file_system_type *fs_type,
         };
         int error = -ENOMEM;
 
-        data = kzalloc(sizeof(*data), GFP_KERNEL);
-        mntfh = kzalloc(sizeof(*mntfh), GFP_KERNEL);
+        data = nfs_alloc_parsed_mount_data(NFS_DEFAULT_VERSION);
+        mntfh = nfs_alloc_fhandle();
         if (data == NULL || mntfh == NULL)
                 goto out_free_fh;
 
@@ -2120,6 +2292,15 @@ static int nfs_get_sb(struct file_system_type *fs_type,
         if (error < 0)
                 goto out;
 
+#ifdef CONFIG_NFS_V4
+        if (data->version == 4) {
+                error = nfs4_try_mount(flags, dev_name, data, mnt);
+                kfree(data->client_address);
+                kfree(data->nfs_server.export_path);
+                goto out;
+        }
+#endif  /* CONFIG_NFS_V4 */
+
         /* Get a volume representation */
         server = nfs_create_server(data, mntfh);
         if (IS_ERR(server)) {
@@ -2144,13 +2325,14 @@ static int nfs_get_sb(struct file_system_type *fs_type,
         } else {
                 error = nfs_bdi_register(server);
                 if (error)
-                        goto error_splat_super;
+                        goto error_splat_bdi;
         }
 
         if (!s->s_root) {
                 /* initial superblock/root creation */
                 nfs_fill_super(s, data);
-                nfs_fscache_get_super_cookie(s, data);
+                nfs_fscache_get_super_cookie(
+                        s, data ? data->fscache_uniq : NULL, NULL);
         }
 
         mntroot = nfs_get_root(s, mntfh);
@@ -2174,7 +2356,7 @@ out:
         kfree(data->fscache_uniq);
         security_free_mnt_opts(&data->lsm_opts);
 out_free_fh:
-        kfree(mntfh);
+        nfs_free_fhandle(mntfh);
         kfree(data);
         return error;
 
@@ -2185,18 +2367,31 @@ out_err_nosb:
 error_splat_root:
         dput(mntroot);
 error_splat_super:
+        if (server && !s->s_root)
+                bdi_unregister(&server->backing_dev_info);
+error_splat_bdi:
         deactivate_locked_super(s);
         goto out;
 }
 
 /*
+ * Ensure that we unregister the bdi before kill_anon_super
+ * releases the device name
+ */
+static void nfs_put_super(struct super_block *s)
+{
+        struct nfs_server *server = NFS_SB(s);
+
+        bdi_unregister(&server->backing_dev_info);
+}
+
+/*
  * Destroy an NFS2/3 superblock
  */
 static void nfs_kill_super(struct super_block *s)
 {
         struct nfs_server *server = NFS_SB(s);
 
-        bdi_unregister(&server->backing_dev_info);
         kill_anon_super(s);
         nfs_fscache_release_super_cookie(s);
         nfs_free_server(server);
@@ -2205,9 +2400,9 @@ static void nfs_kill_super(struct super_block *s)
 /*
  * Clone an NFS2/3 server record on xdev traversal (FSID-change)
  */
-static int nfs_xdev_get_sb(struct file_system_type *fs_type, int flags,
-                           const char *dev_name, void *raw_data,
-                           struct vfsmount *mnt)
+static struct dentry *
+nfs_xdev_mount(struct file_system_type *fs_type, int flags,
+                const char *dev_name, void *raw_data)
 {
         struct nfs_clone_mount *data = raw_data;
         struct super_block *s;
@@ -2219,7 +2414,7 @@ static int nfs_xdev_get_sb(struct file_system_type *fs_type, int flags,
         };
         int error;
 
-        dprintk("--> nfs_xdev_get_sb()\n");
+        dprintk("--> nfs_xdev_mount()\n");
 
         /* create a new volume representation */
         server = nfs_clone_server(NFS_SB(data->sb), data->fh, data->fattr);
@@ -2245,12 +2440,13 @@ static int nfs_xdev_get_sb(struct file_system_type *fs_type, int flags,
         } else {
                 error = nfs_bdi_register(server);
                 if (error)
-                        goto error_splat_super;
+                        goto error_splat_bdi;
         }
 
         if (!s->s_root) {
                 /* initial superblock/root creation */
                 nfs_clone_super(s, data->sb);
+                nfs_fscache_get_super_cookie(s, NULL, data);
         }
 
         mntroot = nfs_get_root(s, data->fh);
@@ -2265,25 +2461,26 @@ static int nfs_xdev_get_sb(struct file_system_type *fs_type, int flags,
         }
 
         s->s_flags |= MS_ACTIVE;
-        mnt->mnt_sb = s;
-        mnt->mnt_root = mntroot;
 
         /* clone any lsm security options from the parent to the new sb */
         security_sb_clone_mnt_opts(data->sb, s);
 
-        dprintk("<-- nfs_xdev_get_sb() = 0\n");
-        return 0;
+        dprintk("<-- nfs_xdev_mount() = 0\n");
+        return mntroot;
 
 out_err_nosb:
         nfs_free_server(server);
 out_err_noserver:
-        dprintk("<-- nfs_xdev_get_sb() = %d [error]\n", error);
-        return error;
+        dprintk("<-- nfs_xdev_mount() = %d [error]\n", error);
+        return ERR_PTR(error);
 
 error_splat_super:
+        if (server && !s->s_root)
+                bdi_unregister(&server->backing_dev_info);
+error_splat_bdi:
         deactivate_locked_super(s);
-        dprintk("<-- nfs_xdev_get_sb() = %d [splat]\n", error);
-        return error;
+        dprintk("<-- nfs_xdev_mount() = %d [splat]\n", error);
+        return ERR_PTR(error);
 }
 
 #ifdef CONFIG_NFS_V4
@@ -2299,7 +2496,13 @@ static void nfs4_clone_super(struct super_block *sb,
         sb->s_maxbytes = old_sb->s_maxbytes;
         sb->s_time_gran = 1;
         sb->s_op = old_sb->s_op;
-        nfs_initialise_sb(sb);
+        /*
+         * The VFS shouldn't apply the umask to mode bits. We will do
+         * so ourselves when necessary.
+         */
+        sb->s_flags  |= MS_POSIXACL;
+        sb->s_xattr  = old_sb->s_xattr;
+        nfs_initialise_sb(sb);
 }
 
 /*
@@ -2309,12 +2512,56 @@ static void nfs4_fill_super(struct super_block *sb)
 {
         sb->s_time_gran = 1;
         sb->s_op = &nfs4_sops;
+        /*
+         * The VFS shouldn't apply the umask to mode bits. We will do
+         * so ourselves when necessary.
+         */
+        sb->s_flags  |= MS_POSIXACL;
+        sb->s_xattr = nfs4_xattr_handlers;
         nfs_initialise_sb(sb);
 }
 
 static void nfs4_validate_mount_flags(struct nfs_parsed_mount_data *args)
 {
-        args->flags &= ~(NFS_MOUNT_NONLM|NFS_MOUNT_NOACL|NFS_MOUNT_VER3);
+        args->flags &= ~(NFS_MOUNT_NONLM|NFS_MOUNT_NOACL|NFS_MOUNT_VER3|
+                         NFS_MOUNT_LOCAL_FLOCK|NFS_MOUNT_LOCAL_FCNTL);
+}
+
+static int nfs4_validate_text_mount_data(void *options,
+                                         struct nfs_parsed_mount_data *args,
+                                         const char *dev_name)
+{
+        struct sockaddr *sap = (struct sockaddr *)&args->nfs_server.address;
+
+        nfs_set_port(sap, &args->nfs_server.port, NFS_PORT);
+
+        nfs_validate_transport_protocol(args);
+
+        nfs4_validate_mount_flags(args);
+
+        if (args->version != 4) {
+                dfprintk(MOUNT,
+                         "NFS4: Illegal mount version\n");
+                return -EINVAL;
+        }
+
+        if (args->auth_flavor_len > 1) {
+                dfprintk(MOUNT,
+                         "NFS4: Too many RPC auth flavours specified\n");
+                return -EINVAL;
+        }
+
+        if (args->client_address == NULL) {
+                dfprintk(MOUNT,
+                         "NFS4: mount program didn't pass callback address\n");
+                return -EINVAL;
+        }
+
+        return nfs_parse_devname(dev_name,
+                                   &args->nfs_server.hostname,
+                                   NFS4_MAXNAMLEN,
+                                   &args->nfs_server.export_path,
+                                   NFS4_MAXPATHLEN);
 }
 
 /*
@@ -2324,36 +2571,23 @@ static int nfs4_validate_mount_data(void *options,
                                     struct nfs_parsed_mount_data *args,
                                     const char *dev_name)
 {
-        struct sockaddr_in *ap;
+        struct sockaddr *sap = (struct sockaddr *)&args->nfs_server.address;
         struct nfs4_mount_data *data = (struct nfs4_mount_data *)options;
         char *c;
 
         if (data == NULL)
                 goto out_no_data;
 
-        args->rsize             = NFS_MAX_FILE_IO_SIZE;
-        args->wsize             = NFS_MAX_FILE_IO_SIZE;
-        args->acregmin          = NFS_DEF_ACREGMIN;
-        args->acregmax          = NFS_DEF_ACREGMAX;
-        args->acdirmin          = NFS_DEF_ACDIRMIN;
-        args->acdirmax          = NFS_DEF_ACDIRMAX;
-        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:
-                ap = (struct sockaddr_in *)&args->nfs_server.address;
                 if (data->host_addrlen > sizeof(args->nfs_server.address))
                         goto out_no_address;
                 if (data->host_addrlen == 0)
                         goto out_no_address;
                 args->nfs_server.addrlen = data->host_addrlen;
-                if (copy_from_user(ap, data->host_addr, data->host_addrlen))
+                if (copy_from_user(sap, data->host_addr, data->host_addrlen))
                         return -EFAULT;
-                if (!nfs_verify_server_address((struct sockaddr *)
-                                                &args->nfs_server.address))
+                if (!nfs_verify_server_address(sap))
                         goto out_no_address;
 
                 if (data->auth_flavourlen) {
@@ -2399,39 +2633,14 @@ static int nfs4_validate_mount_data(void *options,
                 nfs_validate_transport_protocol(args);
 
                 break;
-        default: {
-                int status;
-
+        default:
                 if (nfs_parse_mount_options((char *)options, args) == 0)
                         return -EINVAL;
 
-                if (!nfs_verify_server_address((struct sockaddr *)
-                                                &args->nfs_server.address))
+                if (!nfs_verify_server_address(sap))
                         return -EINVAL;
 
-                nfs_set_port((struct sockaddr *)&args->nfs_server.address,
-                                args->nfs_server.port);
-
-                nfs_validate_transport_protocol(args);
-
-                nfs4_validate_mount_flags(args);
-
-                if (args->auth_flavor_len > 1)
-                        goto out_inval_auth;
-
-                if (args->client_address == NULL)
-                        goto out_no_client_address;
-
-                status = nfs_parse_devname(dev_name,
-                                           &args->nfs_server.hostname,
-                                           NFS4_MAXNAMLEN,
-                                           &args->nfs_server.export_path,
-                                           NFS4_MAXPATHLEN);
-                if (status < 0)
-                        return status;
-
-                break;
-                }
+                return nfs4_validate_text_mount_data(options, args, dev_name);
         }
 
         return 0;
@@ -2448,17 +2657,14 @@ out_inval_auth:
 out_no_address:
         dfprintk(MOUNT, "NFS4: mount program didn't pass remote address\n");
         return -EINVAL;
-
-out_no_client_address:
-        dfprintk(MOUNT, "NFS4: mount program didn't pass callback address\n");
-        return -EINVAL;
 }
 
 /*
  * Get the superblock for the NFS4 root partition
  */
-static int nfs4_remote_get_sb(struct file_system_type *fs_type,
-        int flags, const char *dev_name, void *raw_data, struct vfsmount *mnt)
+static struct dentry *
+nfs4_remote_mount(struct file_system_type *fs_type, int flags,
+                  const char *dev_name, void *raw_data)
 {
         struct nfs_parsed_mount_data *data = raw_data;
         struct super_block *s;
@@ -2471,7 +2677,7 @@ static int nfs4_remote_get_sb(struct file_system_type *fs_type,
         };
         int error = -ENOMEM;
 
-        mntfh = kzalloc(sizeof(*mntfh), GFP_KERNEL);
+        mntfh = nfs_alloc_fhandle();
         if (data == NULL || mntfh == NULL)
                 goto out_free_fh;
 
@@ -2501,13 +2707,14 @@ static int nfs4_remote_get_sb(struct file_system_type *fs_type,
         } else {
                 error = nfs_bdi_register(server);
                 if (error)
-                        goto error_splat_super;
+                        goto error_splat_bdi;
         }
 
         if (!s->s_root) {
                 /* initial superblock/root creation */
                 nfs4_fill_super(s);
-                nfs_fscache_get_super_cookie(s, data);
+                nfs_fscache_get_super_cookie(
+                        s, data ? data->fscache_uniq : NULL, NULL);
         }
 
         mntroot = nfs4_get_root(s, mntfh);
@@ -2521,15 +2728,16 @@ static int nfs4_remote_get_sb(struct file_system_type *fs_type,
                 goto error_splat_root;
 
         s->s_flags |= MS_ACTIVE;
-        mnt->mnt_sb = s;
-        mnt->mnt_root = mntroot;
-        error = 0;
+
+        security_free_mnt_opts(&data->lsm_opts);
+        nfs_free_fhandle(mntfh);
+        return mntroot;
 
 out:
         security_free_mnt_opts(&data->lsm_opts);
 out_free_fh:
-        kfree(mntfh);
-        return error;
+        nfs_free_fhandle(mntfh);
+        return ERR_PTR(error);
 
 out_free:
         nfs_free_server(server);
@@ -2538,6 +2746,9 @@ out_free:
 error_splat_root:
         dput(mntroot);
 error_splat_super:
+        if (server && !s->s_root)
+                bdi_unregister(&server->backing_dev_info);
+error_splat_bdi:
         deactivate_locked_super(s);
         goto out;
 }
@@ -2569,7 +2780,7 @@ static void nfs_fix_devname(const struct path *path, struct vfsmount *mnt)
         devname = nfs_path(path->mnt->mnt_devname,
                         path->mnt->mnt_root, path->dentry,
                         page, PAGE_SIZE);
-        if (devname == NULL)
+        if (IS_ERR(devname))
                 goto out_freepage;
         tmp = kstrdup(devname, GFP_KERNEL);
         if (tmp == NULL)
@@ -2580,44 +2791,151 @@ out_freepage:
         free_page((unsigned long)page);
 }
 
+struct nfs_referral_count {
+        struct list_head list;
+        const struct task_struct *task;
+        unsigned int referral_count;
+};
+
+static LIST_HEAD(nfs_referral_count_list);
+static DEFINE_SPINLOCK(nfs_referral_count_list_lock);
+
+static struct nfs_referral_count *nfs_find_referral_count(void)
+{
+        struct nfs_referral_count *p;
+
+        list_for_each_entry(p, &nfs_referral_count_list, list) {
+                if (p->task == current)
+                        return p;
+        }
+        return NULL;
+}
+
+#define NFS_MAX_NESTED_REFERRALS 2
+
+static int nfs_referral_loop_protect(void)
+{
+        struct nfs_referral_count *p, *new;
+        int ret = -ENOMEM;
+
+        new = kmalloc(sizeof(*new), GFP_KERNEL);
+        if (!new)
+                goto out;
+        new->task = current;
+        new->referral_count = 1;
+
+        ret = 0;
+        spin_lock(&nfs_referral_count_list_lock);
+        p = nfs_find_referral_count();
+        if (p != NULL) {
+                if (p->referral_count >= NFS_MAX_NESTED_REFERRALS)
+                        ret = -ELOOP;
+                else
+                        p->referral_count++;
+        } else {
+                list_add(&new->list, &nfs_referral_count_list);
+                new = NULL;
+        }
+        spin_unlock(&nfs_referral_count_list_lock);
+        kfree(new);
+out:
+        return ret;
+}
+
+static void nfs_referral_loop_unprotect(void)
+{
+        struct nfs_referral_count *p;
+
+        spin_lock(&nfs_referral_count_list_lock);
+        p = nfs_find_referral_count();
+        p->referral_count--;
+        if (p->referral_count == 0)
+                list_del(&p->list);
+        else
+                p = NULL;
+        spin_unlock(&nfs_referral_count_list_lock);
+        kfree(p);
+}
+
 static int nfs_follow_remote_path(struct vfsmount *root_mnt,
                 const char *export_path, struct vfsmount *mnt_target)
 {
+        struct nameidata *nd = NULL;
         struct mnt_namespace *ns_private;
-        struct nameidata nd;
         struct super_block *s;
         int ret;
 
+        nd = kmalloc(sizeof(*nd), GFP_KERNEL);
+        if (nd == NULL)
+                return -ENOMEM;
+
         ns_private = create_mnt_ns(root_mnt);
         ret = PTR_ERR(ns_private);
         if (IS_ERR(ns_private))
                 goto out_mntput;
 
+        ret = nfs_referral_loop_protect();
+        if (ret != 0)
+                goto out_put_mnt_ns;
+
         ret = vfs_path_lookup(root_mnt->mnt_root, root_mnt,
-                        export_path, LOOKUP_FOLLOW, &nd);
+                        export_path, LOOKUP_FOLLOW, nd);
 
+        nfs_referral_loop_unprotect();
         put_mnt_ns(ns_private);
 
         if (ret != 0)
                 goto out_err;
 
-        s = nd.path.mnt->mnt_sb;
+        s = nd->path.mnt->mnt_sb;
         atomic_inc(&s->s_active);
         mnt_target->mnt_sb = s;
-        mnt_target->mnt_root = dget(nd.path.dentry);
+        mnt_target->mnt_root = dget(nd->path.dentry);
 
         /* Correct the device pathname */
-        nfs_fix_devname(&nd.path, mnt_target);
+        nfs_fix_devname(&nd->path, mnt_target);
 
-        path_put(&nd.path);
+        path_put(&nd->path);
+        kfree(nd);
         down_write(&s->s_umount);
         return 0;
+out_put_mnt_ns:
+        put_mnt_ns(ns_private);
 out_mntput:
         mntput(root_mnt);
 out_err:
+        kfree(nd);
         return ret;
 }
 
+static int nfs4_try_mount(int flags, const char *dev_name,
+                         struct nfs_parsed_mount_data *data,
+                         struct vfsmount *mnt)
+{
+        char *export_path;
+        struct vfsmount *root_mnt;
+        int error;
+
+        dfprintk(MOUNT, "--> nfs4_try_mount()\n");
+
+        export_path = data->nfs_server.export_path;
+        data->nfs_server.export_path = "/";
+        root_mnt = nfs_do_root_mount(&nfs4_remote_fs_type, flags, data,
+                        data->nfs_server.hostname);
+        data->nfs_server.export_path = export_path;
+
+        error = PTR_ERR(root_mnt);
+        if (IS_ERR(root_mnt))
+                goto out;
+
+        error = nfs_follow_remote_path(root_mnt, export_path, mnt);
+
+out:
+        dfprintk(MOUNT, "<-- nfs4_try_mount() = %d%s\n", error,
+                        error != 0 ? " [error]" : "");
+        return error;
+}
+
 /*
  * Get the superblock for an NFS4 mountpoint
  */
@@ -2625,11 +2943,9 @@ static int nfs4_get_sb(struct file_system_type *fs_type,
         int flags, const char *dev_name, void *raw_data, struct vfsmount *mnt)
 {
         struct nfs_parsed_mount_data *data;
-        char *export_path;
-        struct vfsmount *root_mnt;
         int error = -ENOMEM;
 
-        data = kzalloc(sizeof(*data), GFP_KERNEL);
+        data = nfs_alloc_parsed_mount_data(4);
         if (data == NULL)
                 goto out_free_data;
 
@@ -2638,17 +2954,7 @@ static int nfs4_get_sb(struct file_system_type *fs_type,
         if (error < 0)
                 goto out;
 
-        export_path = data->nfs_server.export_path;
-        data->nfs_server.export_path = "/";
-        root_mnt = nfs_do_root_mount(&nfs4_remote_fs_type, flags, data,
-                        data->nfs_server.hostname);
-        data->nfs_server.export_path = export_path;
-
-        error = PTR_ERR(root_mnt);
-        if (IS_ERR(root_mnt))
-                goto out;
-
-        error = nfs_follow_remote_path(root_mnt, export_path, mnt);
+        error = nfs4_try_mount(flags, dev_name, data, mnt);
 
 out:
         kfree(data->client_address);
@@ -2669,7 +2975,6 @@ static void nfs4_kill_super(struct super_block *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__);
@@ -2678,9 +2983,9 @@ static void nfs4_kill_super(struct super_block *sb)
 /*
  * Clone an NFS4 server record on xdev traversal (FSID-change)
  */
-static int nfs4_xdev_get_sb(struct file_system_type *fs_type, int flags,
-                            const char *dev_name, void *raw_data,
-                            struct vfsmount *mnt)
+static struct dentry *
+nfs4_xdev_mount(struct file_system_type *fs_type, int flags,
+                 const char *dev_name, void *raw_data)
 {
         struct nfs_clone_mount *data = raw_data;
         struct super_block *s;
@@ -2692,7 +2997,7 @@ static int nfs4_xdev_get_sb(struct file_system_type *fs_type, int flags,
         };
         int error;
 
-        dprintk("--> nfs4_xdev_get_sb()\n");
+        dprintk("--> nfs4_xdev_mount()\n");
 
         /* create a new volume representation */
         server = nfs_clone_server(NFS_SB(data->sb), data->fh, data->fattr);
@@ -2718,12 +3023,13 @@ static int nfs4_xdev_get_sb(struct file_system_type *fs_type, int flags,
         } else {
                 error = nfs_bdi_register(server);
                 if (error)
-                        goto error_splat_super;
+                        goto error_splat_bdi;
         }
 
         if (!s->s_root) {
                 /* initial superblock/root creation */
                 nfs4_clone_super(s, data->sb);
+                nfs_fscache_get_super_cookie(s, NULL, data);
         }
 
         mntroot = nfs4_get_root(s, data->fh);
@@ -2738,45 +3044,50 @@ static int nfs4_xdev_get_sb(struct file_system_type *fs_type, int flags,
         }
 
         s->s_flags |= MS_ACTIVE;
-        mnt->mnt_sb = s;
-        mnt->mnt_root = mntroot;
 
         security_sb_clone_mnt_opts(data->sb, s);
 
-        dprintk("<-- nfs4_xdev_get_sb() = 0\n");
-        return 0;
+        dprintk("<-- nfs4_xdev_mount() = 0\n");
+        return mntroot;
 
 out_err_nosb:
         nfs_free_server(server);
 out_err_noserver:
-        dprintk("<-- nfs4_xdev_get_sb() = %d [error]\n", error);
-        return error;
+        dprintk("<-- nfs4_xdev_mount() = %d [error]\n", error);
+        return ERR_PTR(error);
 
 error_splat_super:
+        if (server && !s->s_root)
+                bdi_unregister(&server->backing_dev_info);
+error_splat_bdi:
         deactivate_locked_super(s);
-        dprintk("<-- nfs4_xdev_get_sb() = %d [splat]\n", error);
-        return error;
+        dprintk("<-- nfs4_xdev_mount() = %d [splat]\n", error);
+        return ERR_PTR(error);
 }
 
-static int nfs4_remote_referral_get_sb(struct file_system_type *fs_type,
-                int flags, const char *dev_name, void *raw_data,
-                struct vfsmount *mnt)
+static struct dentry *
+nfs4_remote_referral_mount(struct file_system_type *fs_type, int flags,
+                           const char *dev_name, void *raw_data)
 {
         struct nfs_clone_mount *data = raw_data;
         struct super_block *s;
         struct nfs_server *server;
         struct dentry *mntroot;
-        struct nfs_fh mntfh;
+        struct nfs_fh *mntfh;
         int (*compare_super)(struct super_block *, void *) = nfs_compare_super;
         struct nfs_sb_mountdata sb_mntdata = {
                 .mntflags = flags,
         };
-        int error;
+        int error = -ENOMEM;
 
         dprintk("--> nfs4_referral_get_sb()\n");
 
+        mntfh = nfs_alloc_fhandle();
+        if (mntfh == NULL)
+                goto out_err_nofh;
+
         /* create a new volume representation */
-        server = nfs4_create_referral_server(data, &mntfh);
+        server = nfs4_create_referral_server(data, mntfh);
         if (IS_ERR(server)) {
                 error = PTR_ERR(server);
                 goto out_err_noserver;
@@ -2799,15 +3110,16 @@ static int nfs4_remote_referral_get_sb(struct file_system_type *fs_type,
         } else {
                 error = nfs_bdi_register(server);
                 if (error)
-                        goto error_splat_super;
+                        goto error_splat_bdi;
         }
 
         if (!s->s_root) {
                 /* initial superblock/root creation */
                 nfs4_fill_super(s);
+                nfs_fscache_get_super_cookie(s, NULL, data);
         }
 
-        mntroot = nfs4_get_root(s, &mntfh);
+        mntroot = nfs4_get_root(s, mntfh);
         if (IS_ERR(mntroot)) {
                 error = PTR_ERR(mntroot);
                 goto error_splat_super;
@@ -2819,24 +3131,29 @@ static int nfs4_remote_referral_get_sb(struct file_system_type *fs_type,
         }
 
         s->s_flags |= MS_ACTIVE;
-        mnt->mnt_sb = s;
-        mnt->mnt_root = mntroot;
 
         security_sb_clone_mnt_opts(data->sb, s);
 
+        nfs_free_fhandle(mntfh);
         dprintk("<-- nfs4_referral_get_sb() = 0\n");
-        return 0;
+        return mntroot;
 
 out_err_nosb:
         nfs_free_server(server);
 out_err_noserver:
+        nfs_free_fhandle(mntfh);
+out_err_nofh:
         dprintk("<-- nfs4_referral_get_sb() = %d [error]\n", error);
-        return error;
+        return ERR_PTR(error);
 
 error_splat_super:
+        if (server && !s->s_root)
+                bdi_unregister(&server->backing_dev_info);
+error_splat_bdi:
         deactivate_locked_super(s);
+        nfs_free_fhandle(mntfh);
         dprintk("<-- nfs4_referral_get_sb() = %d [splat]\n", error);
-        return error;
+        return ERR_PTR(error);
 }
 
 /*
diff --git a/fs/nfs/symlink.c b/fs/nfs/symlink.c
index 412738dbfbc7..05c9e02f4153 100644
--- a/fs/nfs/symlink.c
+++ b/fs/nfs/symlink.c
@@ -19,7 +19,6 @@
 #include <linux/pagemap.h>
 #include <linux/stat.h>
 #include <linux/mm.h>
-#include <linux/slab.h>
 #include <linux/string.h>
 #include <linux/namei.h>
 
@@ -50,7 +49,7 @@ static void *nfs_follow_link(struct dentry *dentry, struct nameidata *nd)
         struct page *page;
         void *err;
 
-        err = ERR_PTR(nfs_revalidate_mapping_nolock(inode, inode->i_mapping));
+        err = ERR_PTR(nfs_revalidate_mapping(inode, inode->i_mapping));
         if (err)
                 goto read_failed;
         page = read_cache_page(&inode->i_data, 0,
diff --git a/fs/nfs/sysctl.c b/fs/nfs/sysctl.c
index b62481dabae9..978aaeb8a093 100644
--- a/fs/nfs/sysctl.c
+++ b/fs/nfs/sysctl.c
@@ -15,70 +15,66 @@
 
 #include "callback.h"
 
+#ifdef CONFIG_NFS_V4
 static const int nfs_set_port_min = 0;
 static const int nfs_set_port_max = 65535;
+#endif
 static struct ctl_table_header *nfs_callback_sysctl_table;
 
 static ctl_table nfs_cb_sysctls[] = {
 #ifdef CONFIG_NFS_V4
         {
-                .ctl_name = CTL_UNNUMBERED,
                 .procname = "nfs_callback_tcpport",
                 .data = &nfs_callback_set_tcpport,
                 .maxlen = sizeof(int),
                 .mode = 0644,
-                .proc_handler = &proc_dointvec_minmax,
+                .proc_handler = proc_dointvec_minmax,
                 .extra1 = (int *)&nfs_set_port_min,
                 .extra2 = (int *)&nfs_set_port_max,
         },
+#ifndef CONFIG_NFS_USE_NEW_IDMAPPER
         {
-                .ctl_name = CTL_UNNUMBERED,
                 .procname = "idmap_cache_timeout",
                 .data = &nfs_idmap_cache_timeout,
                 .maxlen = sizeof(int),
                 .mode = 0644,
-                .proc_handler = &proc_dointvec_jiffies,
-                .strategy = &sysctl_jiffies,
+                .proc_handler = proc_dointvec_jiffies,
         },
+#endif /* CONFIG_NFS_USE_NEW_IDMAPPER */
 #endif
         {
-                .ctl_name       = CTL_UNNUMBERED,
                 .procname       = "nfs_mountpoint_timeout",
                 .data           = &nfs_mountpoint_expiry_timeout,
                 .maxlen         = sizeof(nfs_mountpoint_expiry_timeout),
                 .mode           = 0644,
-                .proc_handler   = &proc_dointvec_jiffies,
-                .strategy       = &sysctl_jiffies,
+                .proc_handler   = proc_dointvec_jiffies,
         },
         {
-                .ctl_name       = CTL_UNNUMBERED,
                 .procname       = "nfs_congestion_kb",
                 .data           = &nfs_congestion_kb,
                 .maxlen         = sizeof(nfs_congestion_kb),
                 .mode           = 0644,
-                .proc_handler   = &proc_dointvec,
+                .proc_handler   = proc_dointvec,
         },
-        { .ctl_name = 0 }
+        { }
 };
 
 static ctl_table nfs_cb_sysctl_dir[] = {
         {
-                .ctl_name = CTL_UNNUMBERED,
                 .procname = "nfs",
                 .mode = 0555,
                 .child = nfs_cb_sysctls,
         },
-        { .ctl_name = 0 }
+        { }
 };
 
 static ctl_table nfs_cb_sysctl_root[] = {
         {
-                .ctl_name = CTL_FS,
                 .procname = "fs",
                 .mode = 0555,
                 .child = nfs_cb_sysctl_dir,
         },
-        { .ctl_name = 0 }
+        { }
 };
 
 int nfs_register_sysctl(void)
diff --git a/fs/nfs/unlink.c b/fs/nfs/unlink.c
index 1064c91ae810..e313a51acdd1 100644
--- a/fs/nfs/unlink.c
+++ b/fs/nfs/unlink.c
@@ -13,9 +13,12 @@
 #include <linux/nfs_fs.h>
 #include <linux/sched.h>
 #include <linux/wait.h>
+#include <linux/namei.h>
 
 #include "internal.h"
 #include "nfs4_fs.h"
+#include "iostat.h"
+#include "delegation.h"
 
 struct nfs_unlinkdata {
         struct hlist_node list;
@@ -23,6 +26,7 @@ struct nfs_unlinkdata {
         struct nfs_removeres res;
         struct inode *dir;
         struct rpc_cred *cred;
+        struct nfs_fattr dir_attr;
 };
 
 /**
@@ -83,7 +87,7 @@ 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))
-                nfs4_restart_rpc(task, NFS_SERVER(dir)->nfs_client);
+                nfs_restart_rpc(task, NFS_SERVER(dir)->nfs_client);
 }
 
 /**
@@ -109,7 +113,7 @@ 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,
+        if (nfs4_setup_sequence(server, &data->args.seq_args,
                                 &data->res.seq_res, 1, task))
                 return;
         rpc_call_start(task);
@@ -169,7 +173,7 @@ static int nfs_do_call_unlink(struct dentry *parent, struct inode *dir, struct n
         }
         nfs_sb_active(dir->i_sb);
         data->args.fh = NFS_FH(dir);
-        nfs_fattr_init(&data->res.dir_attr);
+        nfs_fattr_init(data->res.dir_attr);
 
         NFS_PROTO(dir)->unlink_setup(&msg, dir);
 
@@ -243,7 +247,7 @@ void nfs_unblock_sillyrename(struct dentry *dentry)
  * @dir: parent directory of dentry
  * @dentry: dentry to unlink
  */
-int
+static int
 nfs_async_unlink(struct inode *dir, struct dentry *dentry)
 {
         struct nfs_unlinkdata *data;
@@ -258,7 +262,7 @@ 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;
+        data->res.dir_attr = &data->dir_attr;
 
         status = -EBUSY;
         spin_lock(&dentry->d_lock);
@@ -301,3 +305,256 @@ nfs_complete_unlink(struct dentry *dentry, struct inode *inode)
         if (data != NULL && (NFS_STALE(inode) || !nfs_call_unlink(dentry, data)))
                 nfs_free_unlinkdata(data);
 }
+
+/* Cancel a queued async unlink. Called when a sillyrename run fails. */
+static void
+nfs_cancel_async_unlink(struct dentry *dentry)
+{
+        spin_lock(&dentry->d_lock);
+        if (dentry->d_flags & DCACHE_NFSFS_RENAMED) {
+                struct nfs_unlinkdata *data = dentry->d_fsdata;
+
+                dentry->d_flags &= ~DCACHE_NFSFS_RENAMED;
+                spin_unlock(&dentry->d_lock);
+                nfs_free_unlinkdata(data);
+                return;
+        }
+        spin_unlock(&dentry->d_lock);
+}
+
+struct nfs_renamedata {
+        struct nfs_renameargs   args;
+        struct nfs_renameres    res;
+        struct rpc_cred         *cred;
+        struct inode            *old_dir;
+        struct dentry           *old_dentry;
+        struct nfs_fattr        old_fattr;
+        struct inode            *new_dir;
+        struct dentry           *new_dentry;
+        struct nfs_fattr        new_fattr;
+};
+
+/**
+ * nfs_async_rename_done - Sillyrename post-processing
+ * @task: rpc_task of the sillyrename
+ * @calldata: nfs_renamedata for the sillyrename
+ *
+ * Do the directory attribute updates and the d_move
+ */
+static void nfs_async_rename_done(struct rpc_task *task, void *calldata)
+{
+        struct nfs_renamedata *data = calldata;
+        struct inode *old_dir = data->old_dir;
+        struct inode *new_dir = data->new_dir;
+
+        if (!NFS_PROTO(old_dir)->rename_done(task, old_dir, new_dir)) {
+                nfs_restart_rpc(task, NFS_SERVER(old_dir)->nfs_client);
+                return;
+        }
+
+        if (task->tk_status != 0) {
+                nfs_cancel_async_unlink(data->old_dentry);
+                return;
+        }
+
+        nfs_set_verifier(data->old_dentry, nfs_save_change_attribute(old_dir));
+        d_move(data->old_dentry, data->new_dentry);
+}
+
+/**
+ * nfs_async_rename_release - Release the sillyrename data.
+ * @calldata: the struct nfs_renamedata to be released
+ */
+static void nfs_async_rename_release(void *calldata)
+{
+        struct nfs_renamedata   *data = calldata;
+        struct super_block *sb = data->old_dir->i_sb;
+
+        if (data->old_dentry->d_inode)
+                nfs_mark_for_revalidate(data->old_dentry->d_inode);
+
+        dput(data->old_dentry);
+        dput(data->new_dentry);
+        iput(data->old_dir);
+        iput(data->new_dir);
+        nfs_sb_deactive(sb);
+        put_rpccred(data->cred);
+        kfree(data);
+}
+
+#if defined(CONFIG_NFS_V4_1)
+static void nfs_rename_prepare(struct rpc_task *task, void *calldata)
+{
+        struct nfs_renamedata *data = calldata;
+        struct nfs_server *server = NFS_SERVER(data->old_dir);
+
+        if (nfs4_setup_sequence(server, &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_rename_ops = {
+        .rpc_call_done = nfs_async_rename_done,
+        .rpc_release = nfs_async_rename_release,
+#if defined(CONFIG_NFS_V4_1)
+        .rpc_call_prepare = nfs_rename_prepare,
+#endif /* CONFIG_NFS_V4_1 */
+};
+
+/**
+ * nfs_async_rename - perform an asynchronous rename operation
+ * @old_dir: directory that currently holds the dentry to be renamed
+ * @new_dir: target directory for the rename
+ * @old_dentry: original dentry to be renamed
+ * @new_dentry: dentry to which the old_dentry should be renamed
+ *
+ * It's expected that valid references to the dentries and inodes are held
+ */
+static struct rpc_task *
+nfs_async_rename(struct inode *old_dir, struct inode *new_dir,
+                 struct dentry *old_dentry, struct dentry *new_dentry)
+{
+        struct nfs_renamedata *data;
+        struct rpc_message msg = { };
+        struct rpc_task_setup task_setup_data = {
+                .rpc_message = &msg,
+                .callback_ops = &nfs_rename_ops,
+                .workqueue = nfsiod_workqueue,
+                .rpc_client = NFS_CLIENT(old_dir),
+                .flags = RPC_TASK_ASYNC,
+        };
+
+        data = kzalloc(sizeof(*data), GFP_KERNEL);
+        if (data == NULL)
+                return ERR_PTR(-ENOMEM);
+        task_setup_data.callback_data = data;
+
+        data->cred = rpc_lookup_cred();
+        if (IS_ERR(data->cred)) {
+                struct rpc_task *task = ERR_CAST(data->cred);
+                kfree(data);
+                return task;
+        }
+
+        msg.rpc_argp = &data->args;
+        msg.rpc_resp = &data->res;
+        msg.rpc_cred = data->cred;
+
+        /* set up nfs_renamedata */
+        data->old_dir = old_dir;
+        ihold(old_dir);
+        data->new_dir = new_dir;
+        ihold(new_dir);
+        data->old_dentry = dget(old_dentry);
+        data->new_dentry = dget(new_dentry);
+        nfs_fattr_init(&data->old_fattr);
+        nfs_fattr_init(&data->new_fattr);
+
+        /* set up nfs_renameargs */
+        data->args.old_dir = NFS_FH(old_dir);
+        data->args.old_name = &old_dentry->d_name;
+        data->args.new_dir = NFS_FH(new_dir);
+        data->args.new_name = &new_dentry->d_name;
+
+        /* set up nfs_renameres */
+        data->res.old_fattr = &data->old_fattr;
+        data->res.new_fattr = &data->new_fattr;
+
+        nfs_sb_active(old_dir->i_sb);
+
+        NFS_PROTO(data->old_dir)->rename_setup(&msg, old_dir);
+
+        return rpc_run_task(&task_setup_data);
+}
+
+/**
+ * nfs_sillyrename - Perform a silly-rename of a dentry
+ * @dir: inode of directory that contains dentry
+ * @dentry: dentry to be sillyrenamed
+ *
+ * NFSv2/3 is stateless and the server doesn't know when the client is
+ * holding a file open. To prevent application problems when a file is
+ * unlinked while it's still open, the client performs a "silly-rename".
+ * That is, it renames the file to a hidden file in the same directory,
+ * and only performs the unlink once the last reference to it is put.
+ *
+ * The final cleanup is done during dentry_iput.
+ */
+int
+nfs_sillyrename(struct inode *dir, struct dentry *dentry)
+{
+        static unsigned int sillycounter;
+        const int      fileidsize  = sizeof(NFS_FILEID(dentry->d_inode))*2;
+        const int      countersize = sizeof(sillycounter)*2;
+        const int      slen        = sizeof(".nfs")+fileidsize+countersize-1;
+        char           silly[slen+1];
+        struct dentry *sdentry;
+        struct rpc_task *task;
+        int            error = -EIO;
+
+        dfprintk(VFS, "NFS: silly-rename(%s/%s, ct=%d)\n",
+                dentry->d_parent->d_name.name, dentry->d_name.name,
+                dentry->d_count);
+        nfs_inc_stats(dir, NFSIOS_SILLYRENAME);
+
+        /*
+         * We don't allow a dentry to be silly-renamed twice.
+         */
+        error = -EBUSY;
+        if (dentry->d_flags & DCACHE_NFSFS_RENAMED)
+                goto out;
+
+        sprintf(silly, ".nfs%*.*Lx",
+                fileidsize, fileidsize,
+                (unsigned long long)NFS_FILEID(dentry->d_inode));
+
+        /* Return delegation in anticipation of the rename */
+        nfs_inode_return_delegation(dentry->d_inode);
+
+        sdentry = NULL;
+        do {
+                char *suffix = silly + slen - countersize;
+
+                dput(sdentry);
+                sillycounter++;
+                sprintf(suffix, "%*.*x", countersize, countersize, sillycounter);
+
+                dfprintk(VFS, "NFS: trying to rename %s to %s\n",
+                                dentry->d_name.name, silly);
+
+                sdentry = lookup_one_len(silly, dentry->d_parent, slen);
+                /*
+                 * N.B. Better to return EBUSY here ... it could be
+                 * dangerous to delete the file while it's in use.
+                 */
+                if (IS_ERR(sdentry))
+                        goto out;
+        } while (sdentry->d_inode != NULL); /* need negative lookup */
+
+        /* queue unlink first. Can't do this from rpc_release as it
+         * has to allocate memory
+         */
+        error = nfs_async_unlink(dir, dentry);
+        if (error)
+                goto out_dput;
+
+        /* run the rename task, undo unlink if it fails */
+        task = nfs_async_rename(dir, dir, dentry, sdentry);
+        if (IS_ERR(task)) {
+                error = -EBUSY;
+                nfs_cancel_async_unlink(dentry);
+                goto out_dput;
+        }
+
+        /* wait for the RPC task to complete, unless a SIGKILL intervenes */
+        error = rpc_wait_for_completion_task(task);
+        if (error == 0)
+                error = task->tk_status;
+        rpc_put_task(task);
+out_dput:
+        dput(sdentry);
+out:
+        return error;
+}
diff --git a/fs/nfs/write.c b/fs/nfs/write.c
index ce728829f79a..10d648ea128b 100644
--- a/fs/nfs/write.c
+++ b/fs/nfs/write.c
@@ -13,6 +13,7 @@
 #include <linux/file.h>
 #include <linux/writeback.h>
 #include <linux/swap.h>
+#include <linux/migrate.h>
 
 #include <linux/sunrpc/clnt.h>
 #include <linux/nfs_fs.h>
@@ -26,6 +27,7 @@
 #include "internal.h"
 #include "iostat.h"
 #include "nfs4_fs.h"
+#include "fscache.h"
 
 #define NFSDBG_FACILITY         NFSDBG_PAGECACHE
 
@@ -53,7 +55,6 @@ 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;
 }
@@ -73,7 +74,6 @@ 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 {
@@ -87,17 +87,15 @@ struct nfs_write_data *nfs_writedata_alloc(unsigned int pagecount)
         return p;
 }
 
-static void nfs_writedata_free(struct nfs_write_data *p)
+void nfs_writedata_free(struct nfs_write_data *p)
 {
         if (p && (p->pagevec != &p->page_array[0]))
                 kfree(p->pagevec);
         mempool_free(p, nfs_wdata_mempool);
 }
 
-void nfs_writedata_release(void *data)
+static void nfs_writedata_release(struct nfs_write_data *wdata)
 {
-        struct nfs_write_data *wdata = data;
-
         put_nfs_open_context(wdata->args.context);
         nfs_writedata_free(wdata);
 }
@@ -178,7 +176,7 @@ static int wb_priority(struct writeback_control *wbc)
 {
         if (wbc->for_reclaim)
                 return FLUSH_HIGHPRI | FLUSH_STABLE;
-        if (wbc->for_kupdate)
+        if (wbc->for_kupdate || wbc->for_background)
                 return FLUSH_LOWPRI;
         return 0;
 }
@@ -201,9 +199,12 @@ static int nfs_set_page_writeback(struct page *page)
                 struct inode *inode = page->mapping->host;
                 struct nfs_server *nfss = NFS_SERVER(inode);
 
+                page_cache_get(page);
                 if (atomic_long_inc_return(&nfss->writeback) >
-                                NFS_CONGESTION_ON_THRESH)
-                        set_bdi_congested(&nfss->backing_dev_info, WRITE);
+                                NFS_CONGESTION_ON_THRESH) {
+                        set_bdi_congested(&nfss->backing_dev_info,
+                                                BLK_RW_ASYNC);
+                }
         }
         return ret;
 }
@@ -214,28 +215,22 @@ static void nfs_end_page_writeback(struct page *page)
         struct nfs_server *nfss = NFS_SERVER(inode);
 
         end_page_writeback(page);
+        page_cache_release(page);
         if (atomic_long_dec_return(&nfss->writeback) < NFS_CONGESTION_OFF_THRESH)
-                clear_bdi_congested(&nfss->backing_dev_info, WRITE);
+                clear_bdi_congested(&nfss->backing_dev_info, BLK_RW_ASYNC);
 }
 
-/*
- * Find an associated nfs write request, and prepare to flush it out
- * May return an error if the user signalled nfs_wait_on_request().
- */
-static int nfs_page_async_flush(struct nfs_pageio_descriptor *pgio,
-                                struct page *page)
+static struct nfs_page *nfs_find_and_lock_request(struct page *page, bool nonblock)
 {
         struct inode *inode = page->mapping->host;
         struct nfs_page *req;
         int ret;
 
         spin_lock(&inode->i_lock);
-        for(;;) {
+        for (;;) {
                 req = nfs_page_find_request_locked(page);
-                if (req == NULL) {
-                        spin_unlock(&inode->i_lock);
-                        return 0;
-                }
+                if (req == NULL)
+                        break;
                 if (nfs_set_page_tag_locked(req))
                         break;
                 /* Note: If we hold the page lock, as is the case in nfs_writepage,
@@ -244,37 +239,63 @@ static int nfs_page_async_flush(struct nfs_pageio_descriptor *pgio,
                  *       request as dirty (in which case we don't care).
                  */
                 spin_unlock(&inode->i_lock);
-                ret = nfs_wait_on_request(req);
+                if (!nonblock)
+                        ret = nfs_wait_on_request(req);
+                else
+                        ret = -EAGAIN;
                 nfs_release_request(req);
                 if (ret != 0)
-                        return ret;
+                        return ERR_PTR(ret);
                 spin_lock(&inode->i_lock);
         }
-        if (test_bit(PG_CLEAN, &req->wb_flags)) {
-                spin_unlock(&inode->i_lock);
-                BUG();
-        }
-        if (nfs_set_page_writeback(page) != 0) {
-                spin_unlock(&inode->i_lock);
-                BUG();
-        }
         spin_unlock(&inode->i_lock);
+        return req;
+}
+
+/*
+ * Find an associated nfs write request, and prepare to flush it out
+ * May return an error if the user signalled nfs_wait_on_request().
+ */
+static int nfs_page_async_flush(struct nfs_pageio_descriptor *pgio,
+                                struct page *page, bool nonblock)
+{
+        struct nfs_page *req;
+        int ret = 0;
+
+        req = nfs_find_and_lock_request(page, nonblock);
+        if (!req)
+                goto out;
+        ret = PTR_ERR(req);
+        if (IS_ERR(req))
+                goto out;
+
+        ret = nfs_set_page_writeback(page);
+        BUG_ON(ret != 0);
+        BUG_ON(test_bit(PG_CLEAN, &req->wb_flags));
+
         if (!nfs_pageio_add_request(pgio, req)) {
                 nfs_redirty_request(req);
-                return pgio->pg_error;
+                ret = pgio->pg_error;
         }
-        return 0;
+out:
+        return ret;
 }
 
 static int nfs_do_writepage(struct page *page, struct writeback_control *wbc, struct nfs_pageio_descriptor *pgio)
 {
         struct inode *inode = page->mapping->host;
+        int ret;
 
         nfs_inc_stats(inode, NFSIOS_VFSWRITEPAGE);
         nfs_add_stats(inode, NFSIOS_WRITEPAGES, 1);
 
         nfs_pageio_cond_complete(pgio, page->index);
-        return nfs_page_async_flush(pgio, page);
+        ret = nfs_page_async_flush(pgio, page, wbc->sync_mode == WB_SYNC_NONE);
+        if (ret == -EAGAIN) {
+                redirty_page_for_writepage(wbc, page);
+                ret = 0;
+        }
+        return ret;
 }
 
 /*
@@ -369,6 +390,7 @@ static int nfs_inode_add_request(struct inode *inode, struct nfs_page *req)
                 if (nfs_have_delegation(inode, FMODE_WRITE))
                         nfsi->change_attr++;
         }
+        set_bit(PG_MAPPED, &req->wb_flags);
         SetPagePrivate(req->wb_page);
         set_page_private(req->wb_page, (unsigned long)req);
         nfsi->npages++;
@@ -394,6 +416,7 @@ static void nfs_inode_remove_request(struct nfs_page *req)
         spin_lock(&inode->i_lock);
         set_page_private(req->wb_page, 0);
         ClearPagePrivate(req->wb_page);
+        clear_bit(PG_MAPPED, &req->wb_flags);
         radix_tree_delete(&nfsi->nfs_page_tree, req->wb_index);
         nfsi->npages--;
         if (!nfsi->npages) {
@@ -401,7 +424,6 @@ static void nfs_inode_remove_request(struct nfs_page *req)
                 iput(inode);
         } else
                 spin_unlock(&inode->i_lock);
-        nfs_clear_request(req);
         nfs_release_request(req);
 }
 
@@ -409,6 +431,7 @@ static void
 nfs_mark_request_dirty(struct nfs_page *req)
 {
         __set_page_dirty_nobuffers(req->wb_page);
+        __mark_inode_dirty(req->wb_page->mapping->host, I_DIRTY_DATASYNC);
 }
 
 #if defined(CONFIG_NFS_V3) || defined(CONFIG_NFS_V4)
@@ -426,6 +449,7 @@ nfs_mark_request_commit(struct nfs_page *req)
         radix_tree_tag_set(&nfsi->nfs_page_tree,
                         req->wb_index,
                         NFS_PAGE_TAG_COMMIT);
+        nfsi->ncommit++;
         spin_unlock(&inode->i_lock);
         inc_zone_page_state(req->wb_page, NR_UNSTABLE_NFS);
         inc_bdi_stat(req->wb_page->mapping->backing_dev_info, BDI_RECLAIMABLE);
@@ -489,57 +513,6 @@ int nfs_reschedule_unstable_write(struct nfs_page *req)
 }
 #endif
 
-/*
- * Wait for a request to complete.
- *
- * Interruptible by fatal signals only.
- */
-static int nfs_wait_on_requests_locked(struct inode *inode, pgoff_t idx_start, unsigned int npages)
-{
-        struct nfs_inode *nfsi = NFS_I(inode);
-        struct nfs_page *req;
-        pgoff_t idx_end, next;
-        unsigned int            res = 0;
-        int                     error;
-
-        if (npages == 0)
-                idx_end = ~0;
-        else
-                idx_end = idx_start + npages - 1;
-
-        next = idx_start;
-        while (radix_tree_gang_lookup_tag(&nfsi->nfs_page_tree, (void **)&req, next, 1, NFS_PAGE_TAG_LOCKED)) {
-                if (req->wb_index > idx_end)
-                        break;
-
-                next = req->wb_index + 1;
-                BUG_ON(!NFS_WBACK_BUSY(req));
-
-                kref_get(&req->wb_kref);
-                spin_unlock(&inode->i_lock);
-                error = nfs_wait_on_request(req);
-                nfs_release_request(req);
-                spin_lock(&inode->i_lock);
-                if (error < 0)
-                        return error;
-                res++;
-        }
-        return res;
-}
-
-static void nfs_cancel_commit_list(struct list_head *head)
-{
-        struct nfs_page *req;
-
-        while(!list_empty(head)) {
-                req = nfs_list_entry(head->next);
-                nfs_list_remove_request(req);
-                nfs_clear_request_commit(req);
-                nfs_inode_remove_request(req);
-                nfs_unlock_request(req);
-        }
-}
-
 #if defined(CONFIG_NFS_V3) || defined(CONFIG_NFS_V4)
 static int
 nfs_need_commit(struct nfs_inode *nfsi)
@@ -561,11 +534,17 @@ static int
 nfs_scan_commit(struct inode *inode, struct list_head *dst, pgoff_t idx_start, unsigned int npages)
 {
         struct nfs_inode *nfsi = NFS_I(inode);
+        int ret;
 
         if (!nfs_need_commit(nfsi))
                 return 0;
 
-        return nfs_scan_list(nfsi, dst, idx_start, npages, NFS_PAGE_TAG_COMMIT);
+        ret = nfs_scan_list(nfsi, dst, idx_start, npages, NFS_PAGE_TAG_COMMIT);
+        if (ret > 0)
+                nfsi->ncommit -= ret;
+        if (nfs_need_commit(NFS_I(inode)))
+                __mark_inode_dirty(inode, I_DIRTY_DATASYNC);
+        return ret;
 }
 #else
 static inline int nfs_need_commit(struct nfs_inode *nfsi)
@@ -630,9 +609,10 @@ static struct nfs_page *nfs_try_to_update_request(struct inode *inode,
                 spin_lock(&inode->i_lock);
         }
 
-        if (nfs_clear_request_commit(req))
-                radix_tree_tag_clear(&NFS_I(inode)->nfs_page_tree,
-                                req->wb_index, NFS_PAGE_TAG_COMMIT);
+        if (nfs_clear_request_commit(req) &&
+                        radix_tree_tag_clear(&NFS_I(inode)->nfs_page_tree,
+                                req->wb_index, NFS_PAGE_TAG_COMMIT) != NULL)
+                NFS_I(inode)->ncommit--;
 
         /* Okay, the request matches. Update the region */
         if (offset < req->wb_offset) {
@@ -691,9 +671,11 @@ static int nfs_writepage_setup(struct nfs_open_context *ctx, struct page *page,
         req = nfs_setup_write_request(ctx, page, offset, count);
         if (IS_ERR(req))
                 return PTR_ERR(req);
+        nfs_mark_request_dirty(req);
         /* Update file length */
         nfs_grow_file(page, offset, count);
         nfs_mark_uptodate(page, req->wb_pgbase, req->wb_bytes);
+        nfs_mark_request_dirty(req);
         nfs_clear_page_tag_locked(req);
         return 0;
 }
@@ -715,7 +697,9 @@ int nfs_flush_incompatible(struct file *file, struct page *page)
                 req = nfs_page_find_request(page);
                 if (req == NULL)
                         return 0;
-                do_flush = req->wb_page != page || req->wb_context != ctx;
+                do_flush = req->wb_page != page || req->wb_context != ctx ||
+                        req->wb_lock_context->lockowner != current->files ||
+                        req->wb_lock_context->pid != current->tgid;
                 nfs_release_request(req);
                 if (!do_flush)
                         return 0;
@@ -762,7 +746,7 @@ int nfs_updatepage(struct file *file, struct page *page,
          */
         if (nfs_write_pageuptodate(page, inode) &&
                         inode->i_flock == NULL &&
-                        !(file->f_flags & O_SYNC)) {
+                        !(file->f_flags & O_DSYNC)) {
                 count = max(count + offset, nfs_page_length(page));
                 offset = 0;
         }
@@ -770,8 +754,6 @@ int nfs_updatepage(struct file *file, struct page *page,
         status = nfs_writepage_setup(ctx, page, offset, count);
         if (status < 0)
                 nfs_set_pageerror(page);
-        else
-                __set_page_dirty_nobuffers(page);
 
         dprintk("NFS:       nfs_updatepage returns %d (isize %lld)\n",
                         status, (long long)i_size_read(inode));
@@ -780,13 +762,12 @@ int nfs_updatepage(struct file *file, struct page *page,
 
 static void nfs_writepage_release(struct nfs_page *req)
 {
+        struct page *page = req->wb_page;
 
-        if (PageError(req->wb_page) || !nfs_reschedule_unstable_write(req)) {
-                nfs_end_page_writeback(req->wb_page);
+        if (PageError(req->wb_page) || !nfs_reschedule_unstable_write(req))
                 nfs_inode_remove_request(req);
-        } else
-                nfs_end_page_writeback(req->wb_page);
         nfs_clear_page_tag_locked(req);
+        nfs_end_page_writeback(page);
 }
 
 static int flush_task_priority(int how)
@@ -810,7 +791,6 @@ static int nfs_write_rpcsetup(struct nfs_page *req,
                 int how)
 {
         struct inode *inode = req->wb_context->path.dentry->d_inode;
-        int flags = (how & FLUSH_SYNC) ? 0 : RPC_TASK_ASYNC;
         int priority = flush_task_priority(how);
         struct rpc_task *task;
         struct rpc_message msg = {
@@ -825,9 +805,10 @@ static int nfs_write_rpcsetup(struct nfs_page *req,
                 .callback_ops = call_ops,
                 .callback_data = data,
                 .workqueue = nfsiod_workqueue,
-                .flags = flags,
+                .flags = RPC_TASK_ASYNC,
                 .priority = priority,
         };
+        int ret = 0;
 
         /* Set up the RPC argument and reply structs
          * NB: take care not to mess about with data->commit et al. */
@@ -842,6 +823,7 @@ static int nfs_write_rpcsetup(struct nfs_page *req,
         data->args.pages  = data->pagevec;
         data->args.count  = count;
         data->args.context = get_nfs_open_context(req->wb_context);
+        data->args.lock_context = req->wb_lock_context;
         data->args.stable  = NFS_UNSTABLE;
         if (how & FLUSH_STABLE) {
                 data->args.stable = NFS_DATA_SYNC;
@@ -866,10 +848,18 @@ static int nfs_write_rpcsetup(struct nfs_page *req,
                 (unsigned long long)data->args.offset);
 
         task = rpc_run_task(&task_setup_data);
-        if (IS_ERR(task))
-                return PTR_ERR(task);
+        if (IS_ERR(task)) {
+                ret = PTR_ERR(task);
+                goto out;
+        }
+        if (how & FLUSH_SYNC) {
+                ret = rpc_wait_for_completion_task(task);
+                if (ret == 0)
+                        ret = task->tk_status;
+        }
         rpc_put_task(task);
-        return 0;
+out:
+        return ret;
 }
 
 /* If a nfs_flush_* function fails, it should remove reqs from @head and
@@ -878,9 +868,11 @@ static int nfs_write_rpcsetup(struct nfs_page *req,
  */
 static void nfs_redirty_request(struct nfs_page *req)
 {
+        struct page *page = req->wb_page;
+
         nfs_mark_request_dirty(req);
-        nfs_end_page_writeback(req->wb_page);
         nfs_clear_page_tag_locked(req);
+        nfs_end_page_writeback(page);
 }
 
 /*
@@ -1055,9 +1047,9 @@ out:
 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,
+        if (nfs4_setup_sequence(NFS_SERVER(data->inode),
+                                &data->args.seq_args,
                                 &data->res.seq_res, 1, task))
                 return;
         rpc_call_start(task);
@@ -1115,16 +1107,15 @@ static void nfs_writeback_release_full(void *calldata)
                 if (nfs_write_need_commit(data)) {
                         memcpy(&req->wb_verf, &data->verf, sizeof(req->wb_verf));
                         nfs_mark_request_commit(req);
-                        nfs_end_page_writeback(page);
                         dprintk(" marked for commit\n");
                         goto next;
                 }
                 dprintk(" OK\n");
 remove_request:
-                nfs_end_page_writeback(page);
                 nfs_inode_remove_request(req);
         next:
                 nfs_clear_page_tag_locked(req);
+                nfs_end_page_writeback(page);
         }
         nfs_writedata_release(calldata);
 }
@@ -1204,7 +1195,7 @@ int nfs_writeback_done(struct rpc_task *task, struct nfs_write_data *data)
                                  */
                                 argp->stable = NFS_FILE_SYNC;
                         }
-                        nfs4_restart_rpc(task, server->nfs_client);
+                        nfs_restart_rpc(task, server->nfs_client);
                         return -EAGAIN;
                 }
                 if (time_before(complain, jiffies)) {
@@ -1216,13 +1207,31 @@ 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;
 }
 
 
 #if defined(CONFIG_NFS_V3) || defined(CONFIG_NFS_V4)
-void nfs_commitdata_release(void *data)
+static int nfs_commit_set_lock(struct nfs_inode *nfsi, int may_wait)
+{
+        if (!test_and_set_bit(NFS_INO_COMMIT, &nfsi->flags))
+                return 1;
+        if (may_wait && !out_of_line_wait_on_bit_lock(&nfsi->flags,
+                                NFS_INO_COMMIT, nfs_wait_bit_killable,
+                                TASK_KILLABLE))
+                return 1;
+        return 0;
+}
+
+static void nfs_commit_clear_lock(struct nfs_inode *nfsi)
+{
+        clear_bit(NFS_INO_COMMIT, &nfsi->flags);
+        smp_mb__after_clear_bit();
+        wake_up_bit(&nfsi->flags, NFS_INO_COMMIT);
+}
+
+
+static void nfs_commitdata_release(void *data)
 {
         struct nfs_write_data *wdata = data;
 
@@ -1239,7 +1248,6 @@ static int nfs_commit_rpcsetup(struct list_head *head,
 {
         struct nfs_page *first = nfs_list_entry(head->next);
         struct inode *inode = first->wb_context->path.dentry->d_inode;
-        int flags = (how & FLUSH_SYNC) ? 0 : RPC_TASK_ASYNC;
         int priority = flush_task_priority(how);
         struct rpc_task *task;
         struct rpc_message msg = {
@@ -1254,7 +1262,7 @@ static int nfs_commit_rpcsetup(struct list_head *head,
                 .callback_ops = &nfs_commit_ops,
                 .callback_data = data,
                 .workqueue = nfsiod_workqueue,
-                .flags = flags,
+                .flags = RPC_TASK_ASYNC,
                 .priority = priority,
         };
 
@@ -1314,6 +1322,7 @@ nfs_commit_list(struct inode *inode, struct list_head *head, int how)
                                 BDI_RECLAIMABLE);
                 nfs_clear_page_tag_locked(req);
         }
+        nfs_commit_clear_lock(NFS_I(inode));
         return -ENOMEM;
 }
 
@@ -1369,6 +1378,7 @@ static void nfs_commit_release(void *calldata)
         next:
                 nfs_clear_page_tag_locked(req);
         }
+        nfs_commit_clear_lock(NFS_I(data->inode));
         nfs_commitdata_release(calldata);
 }
 
@@ -1383,8 +1393,11 @@ static const struct rpc_call_ops nfs_commit_ops = {
 int nfs_commit_inode(struct inode *inode, int how)
 {
         LIST_HEAD(head);
-        int res;
+        int may_wait = how & FLUSH_SYNC;
+        int res = 0;
 
+        if (!nfs_commit_set_lock(NFS_I(inode), may_wait))
+                goto out_mark_dirty;
         spin_lock(&inode->i_lock);
         res = nfs_scan_commit(inode, &head, 0, 0);
         spin_unlock(&inode->i_lock);
@@ -1392,96 +1405,66 @@ int nfs_commit_inode(struct inode *inode, int how)
                 int error = nfs_commit_list(inode, &head, how);
                 if (error < 0)
                         return error;
-        }
+                if (may_wait)
+                        wait_on_bit(&NFS_I(inode)->flags, NFS_INO_COMMIT,
+                                        nfs_wait_bit_killable,
+                                        TASK_KILLABLE);
+                else
+                        goto out_mark_dirty;
+        } else
+                nfs_commit_clear_lock(NFS_I(inode));
+        return res;
+        /* Note: If we exit without ensuring that the commit is complete,
+         * we must mark the inode as dirty. Otherwise, future calls to
+         * sync_inode() with the WB_SYNC_ALL flag set will fail to ensure
+         * that the data is on the disk.
+         */
+out_mark_dirty:
+        __mark_inode_dirty(inode, I_DIRTY_DATASYNC);
         return res;
 }
-#else
-static inline int nfs_commit_list(struct inode *inode, struct list_head *head, int how)
-{
-        return 0;
-}
-#endif
 
-long nfs_sync_mapping_wait(struct address_space *mapping, struct writeback_control *wbc, int how)
+static int nfs_commit_unstable_pages(struct inode *inode, struct writeback_control *wbc)
 {
-        struct inode *inode = mapping->host;
-        pgoff_t idx_start, idx_end;
-        unsigned int npages = 0;
-        LIST_HEAD(head);
-        int nocommit = how & FLUSH_NOCOMMIT;
-        long pages, ret;
-
-        /* FIXME */
-        if (wbc->range_cyclic)
-                idx_start = 0;
-        else {
-                idx_start = wbc->range_start >> PAGE_CACHE_SHIFT;
-                idx_end = wbc->range_end >> PAGE_CACHE_SHIFT;
-                if (idx_end > idx_start) {
-                        pgoff_t l_npages = 1 + idx_end - idx_start;
-                        npages = l_npages;
-                        if (sizeof(npages) != sizeof(l_npages) &&
-                                        (pgoff_t)npages != l_npages)
-                                npages = 0;
-                }
+        struct nfs_inode *nfsi = NFS_I(inode);
+        int flags = FLUSH_SYNC;
+        int ret = 0;
+
+        if (wbc->sync_mode == WB_SYNC_NONE) {
+                /* Don't commit yet if this is a non-blocking flush and there
+                 * are a lot of outstanding writes for this mapping.
+                 */
+                if (nfsi->ncommit <= (nfsi->npages >> 1))
+                        goto out_mark_dirty;
+
+                /* don't wait for the COMMIT response */
+                flags = 0;
         }
-        how &= ~FLUSH_NOCOMMIT;
-        spin_lock(&inode->i_lock);
-        do {
-                ret = nfs_wait_on_requests_locked(inode, idx_start, npages);
-                if (ret != 0)
-                        continue;
-                if (nocommit)
-                        break;
-                pages = nfs_scan_commit(inode, &head, idx_start, npages);
-                if (pages == 0)
-                        break;
-                if (how & FLUSH_INVALIDATE) {
-                        spin_unlock(&inode->i_lock);
-                        nfs_cancel_commit_list(&head);
-                        ret = pages;
-                        spin_lock(&inode->i_lock);
-                        continue;
-                }
-                pages += nfs_scan_commit(inode, &head, 0, 0);
-                spin_unlock(&inode->i_lock);
-                ret = nfs_commit_list(inode, &head, how);
-                spin_lock(&inode->i_lock);
 
-        } while (ret >= 0);
-        spin_unlock(&inode->i_lock);
+        ret = nfs_commit_inode(inode, flags);
+        if (ret >= 0) {
+                if (wbc->sync_mode == WB_SYNC_NONE) {
+                        if (ret < wbc->nr_to_write)
+                                wbc->nr_to_write -= ret;
+                        else
+                                wbc->nr_to_write = 0;
+                }
+                return 0;
+        }
+out_mark_dirty:
+        __mark_inode_dirty(inode, I_DIRTY_DATASYNC);
         return ret;
 }
-
-static int __nfs_write_mapping(struct address_space *mapping, struct writeback_control *wbc, int how)
+#else
+static int nfs_commit_unstable_pages(struct inode *inode, struct writeback_control *wbc)
 {
-        int ret;
-
-        ret = nfs_writepages(mapping, wbc);
-        if (ret < 0)
-                goto out;
-        ret = nfs_sync_mapping_wait(mapping, wbc, how);
-        if (ret < 0)
-                goto out;
         return 0;
-out:
-        __mark_inode_dirty(mapping->host, I_DIRTY_PAGES);
-        return ret;
 }
+#endif
 
-/* Two pass sync: first using WB_SYNC_NONE, then WB_SYNC_ALL */
-static int nfs_write_mapping(struct address_space *mapping, int how)
+int nfs_write_inode(struct inode *inode, struct writeback_control *wbc)
 {
-        struct writeback_control wbc = {
-                .bdi = mapping->backing_dev_info,
-                .sync_mode = WB_SYNC_ALL,
-                .nr_to_write = LONG_MAX,
-                .range_start = 0,
-                .range_end = LLONG_MAX,
-                .for_writepages = 1,
-        };
-
-        return __nfs_write_mapping(mapping, &wbc, how);
+        return nfs_commit_unstable_pages(inode, wbc);
 }
 
 /*
@@ -1489,37 +1472,27 @@ static int nfs_write_mapping(struct address_space *mapping, int how)
  */
 int nfs_wb_all(struct inode *inode)
 {
-        return nfs_write_mapping(inode->i_mapping, 0);
-}
+        struct writeback_control wbc = {
+                .sync_mode = WB_SYNC_ALL,
+                .nr_to_write = LONG_MAX,
+                .range_start = 0,
+                .range_end = LLONG_MAX,
+        };
 
-int nfs_wb_nocommit(struct inode *inode)
-{
-        return nfs_write_mapping(inode->i_mapping, FLUSH_NOCOMMIT);
+        return sync_inode(inode, &wbc);
 }
 
 int nfs_wb_page_cancel(struct inode *inode, struct page *page)
 {
         struct nfs_page *req;
-        loff_t range_start = page_offset(page);
-        loff_t range_end = range_start + (loff_t)(PAGE_CACHE_SIZE - 1);
-        struct writeback_control wbc = {
-                .bdi = page->mapping->backing_dev_info,
-                .sync_mode = WB_SYNC_ALL,
-                .nr_to_write = LONG_MAX,
-                .range_start = range_start,
-                .range_end = range_end,
-        };
         int ret = 0;
 
         BUG_ON(!PageLocked(page));
         for (;;) {
+                wait_on_page_writeback(page);
                 req = nfs_page_find_request(page);
                 if (req == NULL)
-                        goto out;
-                if (test_bit(PG_CLEAN, &req->wb_flags)) {
-                        nfs_release_request(req);
                         break;
-                }
                 if (nfs_lock_request_dontget(req)) {
                         nfs_inode_remove_request(req);
                         /*
@@ -1531,54 +1504,81 @@ int nfs_wb_page_cancel(struct inode *inode, struct page *page)
                         break;
                 }
                 ret = nfs_wait_on_request(req);
+                nfs_release_request(req);
                 if (ret < 0)
-                        goto out;
+                        break;
         }
-        if (!PagePrivate(page))
-                return 0;
-        ret = nfs_sync_mapping_wait(page->mapping, &wbc, FLUSH_INVALIDATE);
-out:
         return ret;
 }
 
-static int nfs_wb_page_priority(struct inode *inode, struct page *page,
-                                int how)
+/*
+ * Write back all requests on one page - we do this before reading it.
+ */
+int nfs_wb_page(struct inode *inode, struct page *page)
 {
         loff_t range_start = page_offset(page);
         loff_t range_end = range_start + (loff_t)(PAGE_CACHE_SIZE - 1);
         struct writeback_control wbc = {
-                .bdi = page->mapping->backing_dev_info,
                 .sync_mode = WB_SYNC_ALL,
-                .nr_to_write = LONG_MAX,
+                .nr_to_write = 0,
                 .range_start = range_start,
                 .range_end = range_end,
         };
         int ret;
 
-        do {
+        for (;;) {
+                wait_on_page_writeback(page);
                 if (clear_page_dirty_for_io(page)) {
                         ret = nfs_writepage_locked(page, &wbc);
                         if (ret < 0)
                                 goto out_error;
-                } else if (!PagePrivate(page))
+                        continue;
+                }
+                if (!PagePrivate(page))
                         break;
-                ret = nfs_sync_mapping_wait(page->mapping, &wbc, how);
+                ret = nfs_commit_inode(inode, FLUSH_SYNC);
                 if (ret < 0)
                         goto out_error;
-        } while (PagePrivate(page));
+        }
         return 0;
 out_error:
-        __mark_inode_dirty(inode, I_DIRTY_PAGES);
         return ret;
 }
 
-/*
- * Write back all requests on one page - we do this before reading it.
- */
-int nfs_wb_page(struct inode *inode, struct page* page)
+#ifdef CONFIG_MIGRATION
+int nfs_migrate_page(struct address_space *mapping, struct page *newpage,
+                struct page *page)
 {
-        return nfs_wb_page_priority(inode, page, FLUSH_STABLE);
+        struct nfs_page *req;
+        int ret;
+
+        nfs_fscache_release_page(page, GFP_KERNEL);
+
+        req = nfs_find_and_lock_request(page, false);
+        ret = PTR_ERR(req);
+        if (IS_ERR(req))
+                goto out;
+
+        ret = migrate_page(mapping, newpage, page);
+        if (!req)
+                goto out;
+        if (ret)
+                goto out_unlock;
+        page_cache_get(newpage);
+        spin_lock(&mapping->host->i_lock);
+        req->wb_page = newpage;
+        SetPagePrivate(newpage);
+        set_page_private(newpage, (unsigned long)req);
+        ClearPagePrivate(page);
+        set_page_private(page, 0);
+        spin_unlock(&mapping->host->i_lock);
+        page_cache_release(page);
+out_unlock:
+        nfs_clear_page_tag_locked(req);
+out:
+        return ret;
 }
+#endif
 
 int __init nfs_init_writepagecache(void)
 {