Merge tag 'nfs-for-3.4-1' of git://git.linux-nfs.org/projects/trondmy/linux-nfs

Pull NFS client updates for Linux 3.4 from Trond Myklebust:
 "New features include:
   - Add NFS client support for containers.

     This should enable most of the necessary functionality, including
     lockd support, and support for rpc.statd, NFSv4 idmapper and
     RPCSEC_GSS upcalls into the correct network namespace from which
     the mount system call was issued.

   - NFSv4 idmapper scalability improvements

     Base the idmapper cache on the keyring interface to allow
     concurrent access to idmapper entries.  Start the process of
     migrating users from the single-threaded daemon-based approach to
     the multi-threaded request-key based approach.

   - NFSv4.1 implementation id.

     Allows the NFSv4.1 client and server to mutually identify each
     other for logging and debugging purposes.

   - Support the 'vers=4.1' mount option for mounting NFSv4.1 instead of
     having to use the more counterintuitive 'vers=4,minorversion=1'.

   - SUNRPC tracepoints.

     Start the process of adding tracepoints in order to improve
     debugging of the RPC layer.

   - pNFS object layout support for autologin.

  Important bugfixes include:

   - Fix a bug in rpc_wake_up/rpc_wake_up_status that caused them to
     fail to wake up all tasks when applied to priority waitqueues.

   - Ensure that we handle read delegations correctly, when we try to
     truncate a file.

   - A number of fixes for NFSv4 state manager loops (mostly to do with
     delegation recovery)."

* tag 'nfs-for-3.4-1' of git://git.linux-nfs.org/projects/trondmy/linux-nfs: (224 commits)
  NFS: fix sb->s_id in nfs debug prints
  xprtrdma: Remove assumption that each segment is <= PAGE_SIZE
  xprtrdma: The transport should not bug-check when a dup reply is received
  pnfs-obj: autologin: Add support for protocol autologin
  NFS: Remove nfs4_setup_sequence from generic rename code
  NFS: Remove nfs4_setup_sequence from generic unlink code
  NFS: Remove nfs4_setup_sequence from generic read code
  NFS: Remove nfs4_setup_sequence from generic write code
  NFS: Fix more NFS debug related build warnings
  SUNRPC/LOCKD: Fix build warnings when CONFIG_SUNRPC_DEBUG is undefined
  nfs: non void functions must return a value
  SUNRPC: Kill compiler warning when RPC_DEBUG is unset
  SUNRPC/NFS: Add Kbuild dependencies for NFS_DEBUG/RPC_DEBUG
  NFS: Use cond_resched_lock() to reduce latencies in the commit scans
  NFSv4: It is not safe to dereference lsp->ls_state in release_lockowner
  NFS: ncommit count is being double decremented
  SUNRPC: We must not use list_for_each_entry_safe() in rpc_wake_up()
  Try using machine credentials for RENEW calls
  NFSv4.1: Fix a few issues in filelayout_commit_pagelist
  NFSv4.1: Clean ups and bugfixes for the pNFS read/writeback/commit code
  ...

53 files changed, 2902 insertions, 1992 deletions

diff --git a/fs/nfs/Kconfig b/fs/nfs/Kconfig
index dbcd82126ae..2a0e6c59914 100644
--- a/fs/nfs/Kconfig
+++ b/fs/nfs/Kconfig
@@ -64,6 +64,7 @@ config NFS_V4
         bool "NFS client support for NFS version 4"
         depends on NFS_FS
         select SUNRPC_GSS
+        select KEYS
         help
           This option enables support for version 4 of the NFS protocol
           (RFC 3530) in the kernel's NFS client.
@@ -98,6 +99,18 @@ config PNFS_OBJLAYOUT
         depends on NFS_FS && NFS_V4_1 && SCSI_OSD_ULD
         default m
 
+config NFS_V4_1_IMPLEMENTATION_ID_DOMAIN
+        string "NFSv4.1 Implementation ID Domain"
+        depends on NFS_V4_1
+        default "kernel.org"
+        help
+          This option defines the domain portion of the implementation ID that
+          may be sent in the NFS exchange_id operation.  The value must be in
+          the format of a DNS domain name and should be set to the DNS domain
+          name of the distribution.
+          If the NFS client is unchanged from the upstream kernel, this
+          option should be set to the default "kernel.org".
+
 config ROOT_NFS
         bool "Root file system on NFS"
         depends on NFS_FS=y && IP_PNP
@@ -130,16 +143,10 @@ 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.
+config NFS_DEBUG
+        bool
+        depends on NFS_FS && SUNRPC_DEBUG
+        select CRC32
+        default y
diff --git a/fs/nfs/blocklayout/blocklayout.c b/fs/nfs/blocklayout/blocklayout.c
index 48cfac31f64..9c94297bb70 100644
--- a/fs/nfs/blocklayout/blocklayout.c
+++ b/fs/nfs/blocklayout/blocklayout.c
@@ -46,9 +46,6 @@ MODULE_LICENSE("GPL");
 MODULE_AUTHOR("Andy Adamson <andros@citi.umich.edu>");
 MODULE_DESCRIPTION("The NFSv4.1 pNFS Block layout driver");
 
-struct dentry *bl_device_pipe;
-wait_queue_head_t bl_wq;
-
 static void print_page(struct page *page)
 {
         dprintk("PRINTPAGE page %p\n", page);
@@ -236,12 +233,11 @@ bl_read_pagelist(struct nfs_read_data *rdata)
         sector_t isect, extent_length = 0;
         struct parallel_io *par;
         loff_t f_offset = rdata->args.offset;
-        size_t count = rdata->args.count;
         struct page **pages = rdata->args.pages;
         int pg_index = rdata->args.pgbase >> PAGE_CACHE_SHIFT;
 
-        dprintk("%s enter nr_pages %u offset %lld count %Zd\n", __func__,
-               rdata->npages, f_offset, count);
+        dprintk("%s enter nr_pages %u offset %lld count %u\n", __func__,
+               rdata->npages, f_offset, (unsigned int)rdata->args.count);
 
         par = alloc_parallel(rdata);
         if (!par)
@@ -1025,10 +1021,128 @@ static const struct rpc_pipe_ops bl_upcall_ops = {
         .destroy_msg    = bl_pipe_destroy_msg,
 };
 
+static struct dentry *nfs4blocklayout_register_sb(struct super_block *sb,
+                                            struct rpc_pipe *pipe)
+{
+        struct dentry *dir, *dentry;
+
+        dir = rpc_d_lookup_sb(sb, NFS_PIPE_DIRNAME);
+        if (dir == NULL)
+                return ERR_PTR(-ENOENT);
+        dentry = rpc_mkpipe_dentry(dir, "blocklayout", NULL, pipe);
+        dput(dir);
+        return dentry;
+}
+
+static void nfs4blocklayout_unregister_sb(struct super_block *sb,
+                                          struct rpc_pipe *pipe)
+{
+        if (pipe->dentry)
+                rpc_unlink(pipe->dentry);
+}
+
+static int rpc_pipefs_event(struct notifier_block *nb, unsigned long event,
+                           void *ptr)
+{
+        struct super_block *sb = ptr;
+        struct net *net = sb->s_fs_info;
+        struct nfs_net *nn = net_generic(net, nfs_net_id);
+        struct dentry *dentry;
+        int ret = 0;
+
+        if (!try_module_get(THIS_MODULE))
+                return 0;
+
+        if (nn->bl_device_pipe == NULL) {
+                module_put(THIS_MODULE);
+                return 0;
+        }
+
+        switch (event) {
+        case RPC_PIPEFS_MOUNT:
+                dentry = nfs4blocklayout_register_sb(sb, nn->bl_device_pipe);
+                if (IS_ERR(dentry)) {
+                        ret = PTR_ERR(dentry);
+                        break;
+                }
+                nn->bl_device_pipe->dentry = dentry;
+                break;
+        case RPC_PIPEFS_UMOUNT:
+                if (nn->bl_device_pipe->dentry)
+                        nfs4blocklayout_unregister_sb(sb, nn->bl_device_pipe);
+                break;
+        default:
+                ret = -ENOTSUPP;
+                break;
+        }
+        module_put(THIS_MODULE);
+        return ret;
+}
+
+static struct notifier_block nfs4blocklayout_block = {
+        .notifier_call = rpc_pipefs_event,
+};
+
+static struct dentry *nfs4blocklayout_register_net(struct net *net,
+                                                   struct rpc_pipe *pipe)
+{
+        struct super_block *pipefs_sb;
+        struct dentry *dentry;
+
+        pipefs_sb = rpc_get_sb_net(net);
+        if (!pipefs_sb)
+                return NULL;
+        dentry = nfs4blocklayout_register_sb(pipefs_sb, pipe);
+        rpc_put_sb_net(net);
+        return dentry;
+}
+
+static void nfs4blocklayout_unregister_net(struct net *net,
+                                           struct rpc_pipe *pipe)
+{
+        struct super_block *pipefs_sb;
+
+        pipefs_sb = rpc_get_sb_net(net);
+        if (pipefs_sb) {
+                nfs4blocklayout_unregister_sb(pipefs_sb, pipe);
+                rpc_put_sb_net(net);
+        }
+}
+
+static int nfs4blocklayout_net_init(struct net *net)
+{
+        struct nfs_net *nn = net_generic(net, nfs_net_id);
+        struct dentry *dentry;
+
+        init_waitqueue_head(&nn->bl_wq);
+        nn->bl_device_pipe = rpc_mkpipe_data(&bl_upcall_ops, 0);
+        if (IS_ERR(nn->bl_device_pipe))
+                return PTR_ERR(nn->bl_device_pipe);
+        dentry = nfs4blocklayout_register_net(net, nn->bl_device_pipe);
+        if (IS_ERR(dentry)) {
+                rpc_destroy_pipe_data(nn->bl_device_pipe);
+                return PTR_ERR(dentry);
+        }
+        nn->bl_device_pipe->dentry = dentry;
+        return 0;
+}
+
+static void nfs4blocklayout_net_exit(struct net *net)
+{
+        struct nfs_net *nn = net_generic(net, nfs_net_id);
+
+        nfs4blocklayout_unregister_net(net, nn->bl_device_pipe);
+        rpc_destroy_pipe_data(nn->bl_device_pipe);
+        nn->bl_device_pipe = NULL;
+}
+
+static struct pernet_operations nfs4blocklayout_net_ops = {
+        .init = nfs4blocklayout_net_init,
+        .exit = nfs4blocklayout_net_exit,
+};
+
 static int __init nfs4blocklayout_init(void)
 {
-        struct vfsmount *mnt;
-        struct path path;
         int ret;
 
         dprintk("%s: NFSv4 Block Layout Driver Registering...\n", __func__);
@@ -1037,32 +1151,17 @@ static int __init nfs4blocklayout_init(void)
         if (ret)
                 goto out;
 
-        init_waitqueue_head(&bl_wq);
-
-        mnt = rpc_get_mount();
-        if (IS_ERR(mnt)) {
-                ret = PTR_ERR(mnt);
+        ret = rpc_pipefs_notifier_register(&nfs4blocklayout_block);
+        if (ret)
                 goto out_remove;
-        }
-
-        ret = vfs_path_lookup(mnt->mnt_root,
-                              mnt,
-                              NFS_PIPE_DIRNAME, 0, &path);
+        ret = register_pernet_subsys(&nfs4blocklayout_net_ops);
         if (ret)
-                goto out_putrpc;
-
-        bl_device_pipe = rpc_mkpipe(path.dentry, "blocklayout", NULL,
-                                    &bl_upcall_ops, 0);
-        path_put(&path);
-        if (IS_ERR(bl_device_pipe)) {
-                ret = PTR_ERR(bl_device_pipe);
-                goto out_putrpc;
-        }
+                goto out_notifier;
 out:
         return ret;
 
-out_putrpc:
-        rpc_put_mount();
+out_notifier:
+        rpc_pipefs_notifier_unregister(&nfs4blocklayout_block);
 out_remove:
         pnfs_unregister_layoutdriver(&blocklayout_type);
         return ret;
@@ -1073,9 +1172,9 @@ static void __exit nfs4blocklayout_exit(void)
         dprintk("%s: NFSv4 Block Layout Driver Unregistering...\n",
                __func__);
 
+        rpc_pipefs_notifier_unregister(&nfs4blocklayout_block);
+        unregister_pernet_subsys(&nfs4blocklayout_net_ops);
         pnfs_unregister_layoutdriver(&blocklayout_type);
-        rpc_unlink(bl_device_pipe);
-        rpc_put_mount();
 }
 
 MODULE_ALIAS("nfs-layouttype4-3");
diff --git a/fs/nfs/blocklayout/blocklayout.h b/fs/nfs/blocklayout/blocklayout.h
index e31a2df28e7..03350690118 100644
--- a/fs/nfs/blocklayout/blocklayout.h
+++ b/fs/nfs/blocklayout/blocklayout.h
@@ -37,6 +37,7 @@
 #include <linux/sunrpc/rpc_pipe_fs.h>
 
 #include "../pnfs.h"
+#include "../netns.h"
 
 #define PAGE_CACHE_SECTORS (PAGE_CACHE_SIZE >> SECTOR_SHIFT)
 #define PAGE_CACHE_SECTOR_SHIFT (PAGE_CACHE_SHIFT - SECTOR_SHIFT)
@@ -50,6 +51,7 @@ struct pnfs_block_dev {
         struct list_head                bm_node;
         struct nfs4_deviceid            bm_mdevid;    /* associated devid */
         struct block_device             *bm_mdev;     /* meta device itself */
+        struct net                      *net;
 };
 
 enum exstate4 {
@@ -151,9 +153,9 @@ BLK_LSEG2EXT(struct pnfs_layout_segment *lseg)
         return BLK_LO2EXT(lseg->pls_layout);
 }
 
-struct bl_dev_msg {
-        int32_t status;
-        uint32_t major, minor;
+struct bl_pipe_msg {
+        struct rpc_pipe_msg msg;
+        wait_queue_head_t *bl_wq;
 };
 
 struct bl_msg_hdr {
@@ -161,9 +163,6 @@ struct bl_msg_hdr {
         u16 totallen; /* length of entire message, including hdr itself */
 };
 
-extern struct dentry *bl_device_pipe;
-extern wait_queue_head_t bl_wq;
-
 #define BL_DEVICE_UMOUNT               0x0 /* Umount--delete devices */
 #define BL_DEVICE_MOUNT                0x1 /* Mount--create devices*/
 #define BL_DEVICE_REQUEST_INIT         0x0 /* Start request */
diff --git a/fs/nfs/blocklayout/blocklayoutdev.c b/fs/nfs/blocklayout/blocklayoutdev.c
index d08ba9107fd..a5c88a554d9 100644
--- a/fs/nfs/blocklayout/blocklayoutdev.c
+++ b/fs/nfs/blocklayout/blocklayoutdev.c
@@ -46,7 +46,7 @@ static int decode_sector_number(__be32 **rp, sector_t *sp)
 
         *rp = xdr_decode_hyper(*rp, &s);
         if (s & 0x1ff) {
-                printk(KERN_WARNING "%s: sector not aligned\n", __func__);
+                printk(KERN_WARNING "NFS: %s: sector not aligned\n", __func__);
                 return -1;
         }
         *sp = s >> SECTOR_SHIFT;
@@ -79,27 +79,30 @@ int nfs4_blkdev_put(struct block_device *bdev)
         return blkdev_put(bdev, FMODE_READ);
 }
 
-static struct bl_dev_msg bl_mount_reply;
-
 ssize_t bl_pipe_downcall(struct file *filp, const char __user *src,
                          size_t mlen)
 {
+        struct nfs_net *nn = net_generic(filp->f_dentry->d_sb->s_fs_info,
+                                         nfs_net_id);
+
         if (mlen != sizeof (struct bl_dev_msg))
                 return -EINVAL;
 
-        if (copy_from_user(&bl_mount_reply, src, mlen) != 0)
+        if (copy_from_user(&nn->bl_mount_reply, src, mlen) != 0)
                 return -EFAULT;
 
-        wake_up(&bl_wq);
+        wake_up(&nn->bl_wq);
 
         return mlen;
 }
 
 void bl_pipe_destroy_msg(struct rpc_pipe_msg *msg)
 {
+        struct bl_pipe_msg *bl_pipe_msg = container_of(msg, struct bl_pipe_msg, msg);
+
         if (msg->errno >= 0)
                 return;
-        wake_up(&bl_wq);
+        wake_up(bl_pipe_msg->bl_wq);
 }
 
 /*
@@ -111,29 +114,33 @@ nfs4_blk_decode_device(struct nfs_server *server,
 {
         struct pnfs_block_dev *rv;
         struct block_device *bd = NULL;
-        struct rpc_pipe_msg msg;
+        struct bl_pipe_msg bl_pipe_msg;
+        struct rpc_pipe_msg *msg = &bl_pipe_msg.msg;
         struct bl_msg_hdr bl_msg = {
                 .type = BL_DEVICE_MOUNT,
                 .totallen = dev->mincount,
         };
         uint8_t *dataptr;
         DECLARE_WAITQUEUE(wq, current);
-        struct bl_dev_msg *reply = &bl_mount_reply;
         int offset, len, i, rc;
+        struct net *net = server->nfs_client->net;
+        struct nfs_net *nn = net_generic(net, nfs_net_id);
+        struct bl_dev_msg *reply = &nn->bl_mount_reply;
 
         dprintk("%s CREATING PIPEFS MESSAGE\n", __func__);
         dprintk("%s: deviceid: %s, mincount: %d\n", __func__, dev->dev_id.data,
                 dev->mincount);
 
-        memset(&msg, 0, sizeof(msg));
-        msg.data = kzalloc(sizeof(bl_msg) + dev->mincount, GFP_NOFS);
-        if (!msg.data) {
+        bl_pipe_msg.bl_wq = &nn->bl_wq;
+        memset(msg, 0, sizeof(*msg));
+        msg->data = kzalloc(sizeof(bl_msg) + dev->mincount, GFP_NOFS);
+        if (!msg->data) {
                 rv = ERR_PTR(-ENOMEM);
                 goto out;
         }
 
-        memcpy(msg.data, &bl_msg, sizeof(bl_msg));
-        dataptr = (uint8_t *) msg.data;
+        memcpy(msg->data, &bl_msg, sizeof(bl_msg));
+        dataptr = (uint8_t *) msg->data;
         len = dev->mincount;
         offset = sizeof(bl_msg);
         for (i = 0; len > 0; i++) {
@@ -142,13 +149,13 @@ nfs4_blk_decode_device(struct nfs_server *server,
                 len -= PAGE_CACHE_SIZE;
                 offset += PAGE_CACHE_SIZE;
         }
-        msg.len = sizeof(bl_msg) + dev->mincount;
+        msg->len = sizeof(bl_msg) + dev->mincount;
 
         dprintk("%s CALLING USERSPACE DAEMON\n", __func__);
-        add_wait_queue(&bl_wq, &wq);
-        rc = rpc_queue_upcall(bl_device_pipe->d_inode, &msg);
+        add_wait_queue(&nn->bl_wq, &wq);
+        rc = rpc_queue_upcall(nn->bl_device_pipe, msg);
         if (rc < 0) {
-                remove_wait_queue(&bl_wq, &wq);
+                remove_wait_queue(&nn->bl_wq, &wq);
                 rv = ERR_PTR(rc);
                 goto out;
         }
@@ -156,7 +163,7 @@ nfs4_blk_decode_device(struct nfs_server *server,
         set_current_state(TASK_UNINTERRUPTIBLE);
         schedule();
         __set_current_state(TASK_RUNNING);
-        remove_wait_queue(&bl_wq, &wq);
+        remove_wait_queue(&nn->bl_wq, &wq);
 
         if (reply->status != BL_DEVICE_REQUEST_PROC) {
                 dprintk("%s failed to open device: %d\n",
@@ -181,13 +188,14 @@ nfs4_blk_decode_device(struct nfs_server *server,
 
         rv->bm_mdev = bd;
         memcpy(&rv->bm_mdevid, &dev->dev_id, sizeof(struct nfs4_deviceid));
+        rv->net = net;
         dprintk("%s Created device %s with bd_block_size %u\n",
                 __func__,
                 bd->bd_disk->disk_name,
                 bd->bd_block_size);
 
 out:
-        kfree(msg.data);
+        kfree(msg->data);
         return rv;
 }
 
diff --git a/fs/nfs/blocklayout/blocklayoutdm.c b/fs/nfs/blocklayout/blocklayoutdm.c
index d055c755807..737d839bc17 100644
--- a/fs/nfs/blocklayout/blocklayoutdm.c
+++ b/fs/nfs/blocklayout/blocklayoutdm.c
@@ -38,9 +38,10 @@
 
 #define NFSDBG_FACILITY         NFSDBG_PNFS_LD
 
-static void dev_remove(dev_t dev)
+static void dev_remove(struct net *net, dev_t dev)
 {
-        struct rpc_pipe_msg msg;
+        struct bl_pipe_msg bl_pipe_msg;
+        struct rpc_pipe_msg *msg = &bl_pipe_msg.msg;
         struct bl_dev_msg bl_umount_request;
         struct bl_msg_hdr bl_msg = {
                 .type = BL_DEVICE_UMOUNT,
@@ -48,36 +49,38 @@ static void dev_remove(dev_t dev)
         };
         uint8_t *dataptr;
         DECLARE_WAITQUEUE(wq, current);
+        struct nfs_net *nn = net_generic(net, nfs_net_id);
 
         dprintk("Entering %s\n", __func__);
 
-        memset(&msg, 0, sizeof(msg));
-        msg.data = kzalloc(1 + sizeof(bl_umount_request), GFP_NOFS);
-        if (!msg.data)
+        bl_pipe_msg.bl_wq = &nn->bl_wq;
+        memset(msg, 0, sizeof(*msg));
+        msg->data = kzalloc(1 + sizeof(bl_umount_request), GFP_NOFS);
+        if (!msg->data)
                 goto out;
 
         memset(&bl_umount_request, 0, sizeof(bl_umount_request));
         bl_umount_request.major = MAJOR(dev);
         bl_umount_request.minor = MINOR(dev);
 
-        memcpy(msg.data, &bl_msg, sizeof(bl_msg));
-        dataptr = (uint8_t *) msg.data;
+        memcpy(msg->data, &bl_msg, sizeof(bl_msg));
+        dataptr = (uint8_t *) msg->data;
         memcpy(&dataptr[sizeof(bl_msg)], &bl_umount_request, sizeof(bl_umount_request));
-        msg.len = sizeof(bl_msg) + bl_msg.totallen;
+        msg->len = sizeof(bl_msg) + bl_msg.totallen;
 
-        add_wait_queue(&bl_wq, &wq);
-        if (rpc_queue_upcall(bl_device_pipe->d_inode, &msg) < 0) {
-                remove_wait_queue(&bl_wq, &wq);
+        add_wait_queue(&nn->bl_wq, &wq);
+        if (rpc_queue_upcall(nn->bl_device_pipe, msg) < 0) {
+                remove_wait_queue(&nn->bl_wq, &wq);
                 goto out;
         }
 
         set_current_state(TASK_UNINTERRUPTIBLE);
         schedule();
         __set_current_state(TASK_RUNNING);
-        remove_wait_queue(&bl_wq, &wq);
+        remove_wait_queue(&nn->bl_wq, &wq);
 
 out:
-        kfree(msg.data);
+        kfree(msg->data);
 }
 
 /*
@@ -90,10 +93,10 @@ static void nfs4_blk_metadev_release(struct pnfs_block_dev *bdev)
         dprintk("%s Releasing\n", __func__);
         rv = nfs4_blkdev_put(bdev->bm_mdev);
         if (rv)
-                printk(KERN_ERR "%s nfs4_blkdev_put returns %d\n",
+                printk(KERN_ERR "NFS: %s nfs4_blkdev_put returns %d\n",
                                 __func__, rv);
 
-        dev_remove(bdev->bm_mdev->bd_dev);
+        dev_remove(bdev->net, bdev->bm_mdev->bd_dev);
 }
 
 void bl_free_block_dev(struct pnfs_block_dev *bdev)
diff --git a/fs/nfs/blocklayout/extents.c b/fs/nfs/blocklayout/extents.c
index 1abac09f7cd..1f9a6032796 100644
--- a/fs/nfs/blocklayout/extents.c
+++ b/fs/nfs/blocklayout/extents.c
@@ -147,7 +147,7 @@ static int _preload_range(struct pnfs_inval_markings *marks,
         count = (int)(end - start) / (int)tree->mtt_step_size;
 
         /* Pre-malloc what memory we might need */
-        storage = kmalloc(sizeof(*storage) * count, GFP_NOFS);
+        storage = kcalloc(count, sizeof(*storage), GFP_NOFS);
         if (!storage)
                 return -ENOMEM;
         for (i = 0; i < count; i++) {
diff --git a/fs/nfs/cache_lib.c b/fs/nfs/cache_lib.c
index c98b439332f..dded2636811 100644
--- a/fs/nfs/cache_lib.c
+++ b/fs/nfs/cache_lib.c
@@ -13,6 +13,7 @@
 #include <linux/slab.h>
 #include <linux/sunrpc/cache.h>
 #include <linux/sunrpc/rpc_pipe_fs.h>
+#include <net/net_namespace.h>
 
 #include "cache_lib.h"
 
@@ -111,30 +112,54 @@ int nfs_cache_wait_for_upcall(struct nfs_cache_defer_req *dreq)
         return 0;
 }
 
-int nfs_cache_register(struct cache_detail *cd)
+int nfs_cache_register_sb(struct super_block *sb, struct cache_detail *cd)
 {
-        struct vfsmount *mnt;
-        struct path path;
         int ret;
+        struct dentry *dir;
 
-        mnt = rpc_get_mount();
-        if (IS_ERR(mnt))
-                return PTR_ERR(mnt);
-        ret = vfs_path_lookup(mnt->mnt_root, mnt, "/cache", 0, &path);
-        if (ret)
-                goto err;
-        ret = sunrpc_cache_register_pipefs(path.dentry, cd->name, 0600, cd);
-        path_put(&path);
-        if (!ret)
-                return ret;
-err:
-        rpc_put_mount();
+        dir = rpc_d_lookup_sb(sb, "cache");
+        BUG_ON(dir == NULL);
+        ret = sunrpc_cache_register_pipefs(dir, cd->name, 0600, cd);
+        dput(dir);
         return ret;
 }
 
-void nfs_cache_unregister(struct cache_detail *cd)
+int nfs_cache_register_net(struct net *net, struct cache_detail *cd)
 {
-        sunrpc_cache_unregister_pipefs(cd);
-        rpc_put_mount();
+        struct super_block *pipefs_sb;
+        int ret = 0;
+
+        pipefs_sb = rpc_get_sb_net(net);
+        if (pipefs_sb) {
+                ret = nfs_cache_register_sb(pipefs_sb, cd);
+                rpc_put_sb_net(net);
+        }
+        return ret;
+}
+
+void nfs_cache_unregister_sb(struct super_block *sb, struct cache_detail *cd)
+{
+        if (cd->u.pipefs.dir)
+                sunrpc_cache_unregister_pipefs(cd);
+}
+
+void nfs_cache_unregister_net(struct net *net, struct cache_detail *cd)
+{
+        struct super_block *pipefs_sb;
+
+        pipefs_sb = rpc_get_sb_net(net);
+        if (pipefs_sb) {
+                nfs_cache_unregister_sb(pipefs_sb, cd);
+                rpc_put_sb_net(net);
+        }
+}
+
+void nfs_cache_init(struct cache_detail *cd)
+{
+        sunrpc_init_cache_detail(cd);
 }
 
+void nfs_cache_destroy(struct cache_detail *cd)
+{
+        sunrpc_destroy_cache_detail(cd);
+}
diff --git a/fs/nfs/cache_lib.h b/fs/nfs/cache_lib.h
index 7cf6cafcc00..317db95e37f 100644
--- a/fs/nfs/cache_lib.h
+++ b/fs/nfs/cache_lib.h
@@ -23,5 +23,11 @@ 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);
+extern void nfs_cache_init(struct cache_detail *cd);
+extern void nfs_cache_destroy(struct cache_detail *cd);
+extern int nfs_cache_register_net(struct net *net, struct cache_detail *cd);
+extern void nfs_cache_unregister_net(struct net *net, struct cache_detail *cd);
+extern int nfs_cache_register_sb(struct super_block *sb,
+                                 struct cache_detail *cd);
+extern void nfs_cache_unregister_sb(struct super_block *sb,
+                                    struct cache_detail *cd);
diff --git a/fs/nfs/callback.c b/fs/nfs/callback.c
index 516f3375e06..eb95f5091c1 100644
--- a/fs/nfs/callback.c
+++ b/fs/nfs/callback.c
@@ -85,7 +85,7 @@ nfs4_callback_svc(void *vrqstp)
                 }
                 if (err < 0) {
                         if (err != preverr) {
-                                printk(KERN_WARNING "%s: unexpected error "
+                                printk(KERN_WARNING "NFS: %s: unexpected error "
                                         "from svc_recv (%d)\n", __func__, err);
                                 preverr = err;
                         }
@@ -101,12 +101,12 @@ nfs4_callback_svc(void *vrqstp)
 /*
  * Prepare to bring up the NFSv4 callback service
  */
-struct svc_rqst *
-nfs4_callback_up(struct svc_serv *serv)
+static struct svc_rqst *
+nfs4_callback_up(struct svc_serv *serv, struct rpc_xprt *xprt)
 {
         int ret;
 
-        ret = svc_create_xprt(serv, "tcp", &init_net, PF_INET,
+        ret = svc_create_xprt(serv, "tcp", xprt->xprt_net, PF_INET,
                                 nfs_callback_set_tcpport, SVC_SOCK_ANONYMOUS);
         if (ret <= 0)
                 goto out_err;
@@ -114,7 +114,7 @@ nfs4_callback_up(struct svc_serv *serv)
         dprintk("NFS: Callback listener port = %u (af %u)\n",
                         nfs_callback_tcpport, PF_INET);
 
-        ret = svc_create_xprt(serv, "tcp", &init_net, PF_INET6,
+        ret = svc_create_xprt(serv, "tcp", xprt->xprt_net, PF_INET6,
                                 nfs_callback_set_tcpport, SVC_SOCK_ANONYMOUS);
         if (ret > 0) {
                 nfs_callback_tcpport6 = ret;
@@ -172,7 +172,7 @@ nfs41_callback_svc(void *vrqstp)
 /*
  * Bring up the NFSv4.1 callback service
  */
-struct svc_rqst *
+static struct svc_rqst *
 nfs41_callback_up(struct svc_serv *serv, struct rpc_xprt *xprt)
 {
         struct svc_rqst *rqstp;
@@ -183,7 +183,7 @@ nfs41_callback_up(struct svc_serv *serv, struct rpc_xprt *xprt)
          * 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,
+        ret = svc_create_xprt(serv, "tcp-bc", xprt->xprt_net, PF_INET, 0,
                               SVC_SOCK_ANONYMOUS);
         if (ret < 0) {
                 rqstp = ERR_PTR(ret);
@@ -269,7 +269,7 @@ int nfs_callback_up(u32 minorversion, struct rpc_xprt *xprt)
                                         serv, xprt, &rqstp, &callback_svc);
         if (!minorversion_setup) {
                 /* v4.0 callback setup */
-                rqstp = nfs4_callback_up(serv);
+                rqstp = nfs4_callback_up(serv, xprt);
                 callback_svc = nfs4_callback_svc;
         }
 
@@ -332,7 +332,6 @@ void nfs_callback_down(int minorversion)
 int
 check_gss_callback_principal(struct nfs_client *clp, struct svc_rqst *rqstp)
 {
-        struct rpc_clnt *r = clp->cl_rpcclient;
         char *p = svc_gss_principal(rqstp);
 
         if (rqstp->rq_authop->flavour != RPC_AUTH_GSS)
@@ -353,7 +352,7 @@ check_gss_callback_principal(struct nfs_client *clp, struct svc_rqst *rqstp)
         if (memcmp(p, "nfs@", 4) != 0)
                 return 0;
         p += 4;
-        if (strcmp(p, r->cl_server) != 0)
+        if (strcmp(p, clp->cl_hostname) != 0)
                 return 0;
         return 1;
 }
diff --git a/fs/nfs/callback.h b/fs/nfs/callback.h
index c89d3b9e483..a5527c90a5a 100644
--- a/fs/nfs/callback.h
+++ b/fs/nfs/callback.h
@@ -38,7 +38,8 @@ enum nfs4_callback_opnum {
 struct cb_process_state {
         __be32                  drc_status;
         struct nfs_client       *clp;
-        int                     slotid;
+        u32                     slotid;
+        struct net              *net;
 };
 
 struct cb_compound_hdr_arg {
diff --git a/fs/nfs/callback_proc.c b/fs/nfs/callback_proc.c
index 54cea8ad5a7..1b5d809a105 100644
--- a/fs/nfs/callback_proc.c
+++ b/fs/nfs/callback_proc.c
@@ -8,6 +8,7 @@
 #include <linux/nfs4.h>
 #include <linux/nfs_fs.h>
 #include <linux/slab.h>
+#include <linux/rcupdate.h>
 #include "nfs4_fs.h"
 #include "callback.h"
 #include "delegation.h"
@@ -33,7 +34,7 @@ __be32 nfs4_callback_getattr(struct cb_getattrargs *args,
         res->bitmap[0] = res->bitmap[1] = 0;
         res->status = htonl(NFS4ERR_BADHANDLE);
 
-        dprintk("NFS: GETATTR callback request from %s\n",
+        dprintk_rcu("NFS: GETATTR callback request from %s\n",
                 rpc_peeraddr2str(cps->clp->cl_rpcclient, RPC_DISPLAY_ADDR));
 
         inode = nfs_delegation_find_inode(cps->clp, &args->fh);
@@ -73,7 +74,7 @@ __be32 nfs4_callback_recall(struct cb_recallargs *args, void *dummy,
         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",
+        dprintk_rcu("NFS: RECALL callback request from %s\n",
                 rpc_peeraddr2str(cps->clp->cl_rpcclient, RPC_DISPLAY_ADDR));
 
         res = htonl(NFS4ERR_BADHANDLE);
@@ -86,8 +87,7 @@ __be32 nfs4_callback_recall(struct cb_recallargs *args, void *dummy,
                 res = 0;
                 break;
         case -ENOENT:
-                if (res != 0)
-                        res = htonl(NFS4ERR_BAD_STATEID);
+                res = htonl(NFS4ERR_BAD_STATEID);
                 break;
         default:
                 res = htonl(NFS4ERR_RESOURCE);
@@ -98,52 +98,64 @@ out:
         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)
+/*
+ * Lookup a layout by filehandle.
+ *
+ * Note: gets a refcount on the layout hdr and on its respective inode.
+ * Caller must put the layout hdr and the inode.
+ *
+ * TODO: keep track of all layouts (and delegations) in a hash table
+ * hashed by filehandle.
+ */
+static struct pnfs_layout_hdr * get_layout_by_fh_locked(struct nfs_client *clp, struct nfs_fh *fh)
 {
         struct nfs_server *server;
-        struct pnfs_layout_hdr *lo;
         struct inode *ino;
-        bool found = false;
-        u32 rv = NFS4ERR_NOMATCHING_LAYOUT;
-        LIST_HEAD(free_me_list);
+        struct pnfs_layout_hdr *lo;
 
-        spin_lock(&clp->cl_lock);
-        rcu_read_lock();
         list_for_each_entry_rcu(server, &clp->cl_superblocks, client_link) {
                 list_for_each_entry(lo, &server->layouts, plh_layouts) {
-                        if (nfs_compare_fh(&args->cbl_fh,
-                                           &NFS_I(lo->plh_inode)->fh))
+                        if (nfs_compare_fh(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;
+                        return lo;
                 }
-                if (found)
-                        break;
         }
+
+        return NULL;
+}
+
+static struct pnfs_layout_hdr * get_layout_by_fh(struct nfs_client *clp, struct nfs_fh *fh)
+{
+        struct pnfs_layout_hdr *lo;
+
+        spin_lock(&clp->cl_lock);
+        rcu_read_lock();
+        lo = get_layout_by_fh_locked(clp, fh);
         rcu_read_unlock();
         spin_unlock(&clp->cl_lock);
 
-        if (!found)
+        return lo;
+}
+
+static u32 initiate_file_draining(struct nfs_client *clp,
+                                  struct cb_layoutrecallargs *args)
+{
+        struct inode *ino;
+        struct pnfs_layout_hdr *lo;
+        u32 rv = NFS4ERR_NOMATCHING_LAYOUT;
+        LIST_HEAD(free_me_list);
+
+        lo = get_layout_by_fh(clp, &args->cbl_fh);
+        if (!lo)
                 return NFS4ERR_NOMATCHING_LAYOUT;
 
+        ino = lo->plh_inode;
         spin_lock(&ino->i_lock);
         if (test_bit(NFS_LAYOUT_BULK_RECALL, &lo->plh_flags) ||
             mark_matching_lsegs_invalid(lo, &free_me_list,
@@ -213,17 +225,13 @@ static u32 initiate_bulk_draining(struct nfs_client *clp,
 static u32 do_callback_layoutrecall(struct nfs_client *clp,
                                     struct cb_layoutrecallargs *args)
 {
-        u32 res = NFS4ERR_DELAY;
+        u32 res;
 
         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;
 
@@ -303,21 +311,6 @@ out:
         return res;
 }
 
-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
@@ -441,7 +434,7 @@ __be32 nfs4_callback_sequence(struct cb_sequenceargs *args,
         int i;
         __be32 status = htonl(NFS4ERR_BADSESSION);
 
-        clp = nfs4_find_client_sessionid(args->csa_addr, &args->csa_sessionid);
+        clp = nfs4_find_client_sessionid(cps->net, args->csa_addr, &args->csa_sessionid);
         if (clp == NULL)
                 goto out;
 
@@ -517,7 +510,7 @@ __be32 nfs4_callback_recallany(struct cb_recallanyargs *args, void *dummy,
         if (!cps->clp) /* set in cb_sequence */
                 goto out;
 
-        dprintk("NFS: RECALL_ANY callback request from %s\n",
+        dprintk_rcu("NFS: RECALL_ANY callback request from %s\n",
                 rpc_peeraddr2str(cps->clp->cl_rpcclient, RPC_DISPLAY_ADDR));
 
         status = cpu_to_be32(NFS4ERR_INVAL);
@@ -552,7 +545,7 @@ __be32 nfs4_callback_recallslot(struct cb_recallslotargs *args, void *dummy,
         if (!cps->clp) /* set in cb_sequence */
                 goto out;
 
-        dprintk("NFS: CB_RECALL_SLOT request from %s target max slots %d\n",
+        dprintk_rcu("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);
 
diff --git a/fs/nfs/callback_xdr.c b/fs/nfs/callback_xdr.c
index d50b2742f23..95bfc243992 100644
--- a/fs/nfs/callback_xdr.c
+++ b/fs/nfs/callback_xdr.c
@@ -9,6 +9,8 @@
 #include <linux/sunrpc/svc.h>
 #include <linux/nfs4.h>
 #include <linux/nfs_fs.h>
+#include <linux/ratelimit.h>
+#include <linux/printk.h>
 #include <linux/slab.h>
 #include <linux/sunrpc/bc_xprt.h>
 #include "nfs4_fs.h"
@@ -73,7 +75,7 @@ static __be32 *read_buf(struct xdr_stream *xdr, int nbytes)
 
         p = xdr_inline_decode(xdr, nbytes);
         if (unlikely(p == NULL))
-                printk(KERN_WARNING "NFSv4 callback reply buffer overflowed!\n");
+                printk(KERN_WARNING "NFS: NFSv4 callback reply buffer overflowed!\n");
         return p;
 }
 
@@ -138,10 +140,10 @@ static __be32 decode_stateid(struct xdr_stream *xdr, nfs4_stateid *stateid)
 {
         __be32 *p;
 
-        p = read_buf(xdr, 16);
+        p = read_buf(xdr, NFS4_STATEID_SIZE);
         if (unlikely(p == NULL))
                 return htonl(NFS4ERR_RESOURCE);
-        memcpy(stateid->data, p, 16);
+        memcpy(stateid, p, NFS4_STATEID_SIZE);
         return 0;
 }
 
@@ -155,7 +157,7 @@ static __be32 decode_compound_hdr_arg(struct xdr_stream *xdr, struct cb_compound
                 return status;
         /* We do not like overly long tags! */
         if (hdr->taglen > CB_OP_TAGLEN_MAXSZ - 12) {
-                printk("NFSv4 CALLBACK %s: client sent tag of length %u\n",
+                printk("NFS: NFSv4 CALLBACK %s: client sent tag of length %u\n",
                                 __func__, hdr->taglen);
                 return htonl(NFS4ERR_RESOURCE);
         }
@@ -167,7 +169,7 @@ static __be32 decode_compound_hdr_arg(struct xdr_stream *xdr, struct cb_compound
         if (hdr->minorversion <= 1) {
                 hdr->cb_ident = ntohl(*p++); /* ignored by v4.1 */
         } else {
-                printk(KERN_WARNING "%s: NFSv4 server callback with "
+                pr_warn_ratelimited("NFS: %s: NFSv4 server callback with "
                         "illegal minor version %u!\n",
                         __func__, hdr->minorversion);
                 return htonl(NFS4ERR_MINOR_VERS_MISMATCH);
@@ -759,14 +761,14 @@ static void nfs4_callback_free_slot(struct nfs4_session *session)
          * Let the state manager know callback processing done.
          * A single slot, so highest used slotid is either 0 or -1
          */
-        tbl->highest_used_slotid = -1;
+        tbl->highest_used_slotid = NFS4_NO_SLOT;
         nfs4_check_drain_bc_complete(session);
         spin_unlock(&tbl->slot_tbl_lock);
 }
 
 static void nfs4_cb_free_slot(struct cb_process_state *cps)
 {
-        if (cps->slotid != -1)
+        if (cps->slotid != NFS4_NO_SLOT)
                 nfs4_callback_free_slot(cps->clp->cl_session);
 }
 
@@ -860,7 +862,8 @@ static __be32 nfs4_callback_compound(struct svc_rqst *rqstp, void *argp, void *r
         struct cb_process_state cps = {
                 .drc_status = 0,
                 .clp = NULL,
-                .slotid = -1,
+                .slotid = NFS4_NO_SLOT,
+                .net = rqstp->rq_xprt->xpt_net,
         };
         unsigned int nops = 0;
 
@@ -876,7 +879,7 @@ static __be32 nfs4_callback_compound(struct svc_rqst *rqstp, void *argp, void *r
                 return rpc_garbage_args;
 
         if (hdr_arg.minorversion == 0) {
-                cps.clp = nfs4_find_client_ident(hdr_arg.cb_ident);
+                cps.clp = nfs4_find_client_ident(rqstp->rq_xprt->xpt_net, hdr_arg.cb_ident);
                 if (!cps.clp || !check_gss_callback_principal(cps.clp, rqstp))
                         return rpc_drop_reply;
         }
diff --git a/fs/nfs/client.c b/fs/nfs/client.c
index d4f772ebd1e..4a108a0a2a6 100644
--- a/fs/nfs/client.c
+++ b/fs/nfs/client.c
@@ -40,6 +40,8 @@
 #include <net/ipv6.h>
 #include <linux/nfs_xdr.h>
 #include <linux/sunrpc/bc_xprt.h>
+#include <linux/nsproxy.h>
+#include <linux/pid_namespace.h>
 
 #include <asm/system.h>
 
@@ -50,15 +52,12 @@
 #include "internal.h"
 #include "fscache.h"
 #include "pnfs.h"
+#include "netns.h"
 
 #define NFSDBG_FACILITY         NFSDBG_CLIENT
 
-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
@@ -67,15 +66,16 @@ static DEFINE_IDR(cb_ident_idr); /* Protected by nfs_client_lock */
 static int nfs_get_cb_ident_idr(struct nfs_client *clp, int minorversion)
 {
         int ret = 0;
+        struct nfs_net *nn = net_generic(clp->net, nfs_net_id);
 
         if (clp->rpc_ops->version != 4 || minorversion != 0)
                 return ret;
 retry:
-        if (!idr_pre_get(&cb_ident_idr, GFP_KERNEL))
+        if (!idr_pre_get(&nn->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);
+        spin_lock(&nn->nfs_client_lock);
+        ret = idr_get_new(&nn->cb_ident_idr, clp, &clp->cl_cb_ident);
+        spin_unlock(&nn->nfs_client_lock);
         if (ret == -EAGAIN)
                 goto retry;
         return ret;
@@ -90,7 +90,7 @@ static bool nfs4_disable_idmapping = true;
 /*
  * RPC cruft for NFS
  */
-static struct rpc_version *nfs_version[5] = {
+static const struct rpc_version *nfs_version[5] = {
         [2]                     = &nfs_version2,
 #ifdef CONFIG_NFS_V3
         [3]                     = &nfs_version3,
@@ -100,7 +100,7 @@ static struct rpc_version *nfs_version[5] = {
 #endif
 };
 
-struct rpc_program nfs_program = {
+const struct rpc_program nfs_program = {
         .name                   = "nfs",
         .number                 = NFS_PROGRAM,
         .nrvers                 = ARRAY_SIZE(nfs_version),
@@ -116,11 +116,11 @@ struct rpc_stat nfs_rpcstat = {
 
 #ifdef CONFIG_NFS_V3_ACL
 static struct rpc_stat          nfsacl_rpcstat = { &nfsacl_program };
-static struct rpc_version *     nfsacl_version[] = {
+static const struct rpc_version *nfsacl_version[] = {
         [3]                     = &nfsacl_version3,
 };
 
-struct rpc_program              nfsacl_program = {
+const struct rpc_program nfsacl_program = {
         .name                   = "nfsacl",
         .number                 = NFS_ACL_PROGRAM,
         .nrvers                 = ARRAY_SIZE(nfsacl_version),
@@ -136,6 +136,7 @@ struct nfs_client_initdata {
         const struct nfs_rpc_ops *rpc_ops;
         int proto;
         u32 minorversion;
+        struct net *net;
 };
 
 /*
@@ -172,6 +173,7 @@ static struct nfs_client *nfs_alloc_client(const struct nfs_client_initdata *cl_
         clp->cl_rpcclient = ERR_PTR(-EINVAL);
 
         clp->cl_proto = cl_init->proto;
+        clp->net = get_net(cl_init->net);
 
 #ifdef CONFIG_NFS_V4
         err = nfs_get_cb_ident_idr(clp, cl_init->minorversion);
@@ -203,8 +205,11 @@ error_0:
 #ifdef CONFIG_NFS_V4_1
 static void nfs4_shutdown_session(struct nfs_client *clp)
 {
-        if (nfs4_has_session(clp))
+        if (nfs4_has_session(clp)) {
+                nfs4_deviceid_purge_client(clp);
                 nfs4_destroy_session(clp->cl_session);
+        }
+
 }
 #else /* CONFIG_NFS_V4_1 */
 static void nfs4_shutdown_session(struct nfs_client *clp)
@@ -234,16 +239,20 @@ static void nfs4_shutdown_client(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)
+void nfs_cleanup_cb_ident_idr(struct net *net)
 {
-        idr_destroy(&cb_ident_idr);
+        struct nfs_net *nn = net_generic(net, nfs_net_id);
+
+        idr_destroy(&nn->cb_ident_idr);
 }
 
 /* nfs_client_lock held */
 static void nfs_cb_idr_remove_locked(struct nfs_client *clp)
 {
+        struct nfs_net *nn = net_generic(clp->net, nfs_net_id);
+
         if (clp->cl_cb_ident)
-                idr_remove(&cb_ident_idr, clp->cl_cb_ident);
+                idr_remove(&nn->cb_ident_idr, clp->cl_cb_ident);
 }
 
 static void pnfs_init_server(struct nfs_server *server)
@@ -261,7 +270,7 @@ static void nfs4_shutdown_client(struct nfs_client *clp)
 {
 }
 
-void nfs_cleanup_cb_ident_idr(void)
+void nfs_cleanup_cb_ident_idr(struct net *net)
 {
 }
 
@@ -293,10 +302,10 @@ static void nfs_free_client(struct nfs_client *clp)
         if (clp->cl_machine_cred != NULL)
                 put_rpccred(clp->cl_machine_cred);
 
-        nfs4_deviceid_purge_client(clp);
-
+        put_net(clp->net);
         kfree(clp->cl_hostname);
         kfree(clp->server_scope);
+        kfree(clp->impl_id);
         kfree(clp);
 
         dprintk("<-- nfs_free_client()\n");
@@ -307,15 +316,18 @@ static void nfs_free_client(struct nfs_client *clp)
  */
 void nfs_put_client(struct nfs_client *clp)
 {
+        struct nfs_net *nn;
+
         if (!clp)
                 return;
 
         dprintk("--> nfs_put_client({%d})\n", atomic_read(&clp->cl_count));
+        nn = net_generic(clp->net, nfs_net_id);
 
-        if (atomic_dec_and_lock(&clp->cl_count, &nfs_client_lock)) {
+        if (atomic_dec_and_lock(&clp->cl_count, &nn->nfs_client_lock)) {
                 list_del(&clp->cl_share_link);
                 nfs_cb_idr_remove_locked(clp);
-                spin_unlock(&nfs_client_lock);
+                spin_unlock(&nn->nfs_client_lock);
 
                 BUG_ON(!list_empty(&clp->cl_superblocks));
 
@@ -393,6 +405,7 @@ static int nfs_sockaddr_cmp_ip4(const struct sockaddr *sa1,
                 (sin1->sin_port == sin2->sin_port);
 }
 
+#if defined(CONFIG_NFS_V4_1)
 /*
  * Test if two socket addresses represent the same actual socket,
  * by comparing (only) relevant fields, excluding the port number.
@@ -411,6 +424,7 @@ static int nfs_sockaddr_match_ipaddr(const struct sockaddr *sa1,
         }
         return 0;
 }
+#endif /* CONFIG_NFS_V4_1 */
 
 /*
  * Test if two socket addresses represent the same actual socket,
@@ -431,10 +445,10 @@ static int nfs_sockaddr_cmp(const struct sockaddr *sa1,
         return 0;
 }
 
+#if defined(CONFIG_NFS_V4_1)
 /* Common match routine for v4.0 and v4.1 callback services */
-bool
-nfs4_cb_match_client(const struct sockaddr *addr, struct nfs_client *clp,
-                     u32 minorversion)
+static bool nfs4_cb_match_client(const struct sockaddr *addr,
+                struct nfs_client *clp, u32 minorversion)
 {
         struct sockaddr *clap = (struct sockaddr *)&clp->cl_addr;
 
@@ -454,6 +468,7 @@ nfs4_cb_match_client(const struct sockaddr *addr, struct nfs_client *clp,
 
         return true;
 }
+#endif /* CONFIG_NFS_V4_1 */
 
 /*
  * Find an nfs_client on the list that matches the initialisation data
@@ -463,8 +478,9 @@ static struct nfs_client *nfs_match_client(const struct nfs_client_initdata *dat
 {
         struct nfs_client *clp;
         const struct sockaddr *sap = data->addr;
+        struct nfs_net *nn = net_generic(data->net, nfs_net_id);
 
-        list_for_each_entry(clp, &nfs_client_list, cl_share_link) {
+        list_for_each_entry(clp, &nn->nfs_client_list, cl_share_link) {
                 const struct sockaddr *clap = (struct sockaddr *)&clp->cl_addr;
                 /* Don't match clients that failed to initialise properly */
                 if (clp->cl_cons_state < 0)
@@ -502,13 +518,14 @@ nfs_get_client(const struct nfs_client_initdata *cl_init,
 {
         struct nfs_client *clp, *new = NULL;
         int error;
+        struct nfs_net *nn = net_generic(cl_init->net, nfs_net_id);
 
         dprintk("--> nfs_get_client(%s,v%u)\n",
                 cl_init->hostname ?: "", cl_init->rpc_ops->version);
 
         /* see if the client already exists */
         do {
-                spin_lock(&nfs_client_lock);
+                spin_lock(&nn->nfs_client_lock);
 
                 clp = nfs_match_client(cl_init);
                 if (clp)
@@ -516,7 +533,7 @@ nfs_get_client(const struct nfs_client_initdata *cl_init,
                 if (new)
                         goto install_client;
 
-                spin_unlock(&nfs_client_lock);
+                spin_unlock(&nn->nfs_client_lock);
 
                 new = nfs_alloc_client(cl_init);
         } while (!IS_ERR(new));
@@ -527,8 +544,8 @@ nfs_get_client(const struct nfs_client_initdata *cl_init,
         /* install a new client and return with it unready */
 install_client:
         clp = new;
-        list_add(&clp->cl_share_link, &nfs_client_list);
-        spin_unlock(&nfs_client_lock);
+        list_add(&clp->cl_share_link, &nn->nfs_client_list);
+        spin_unlock(&nn->nfs_client_lock);
 
         error = cl_init->rpc_ops->init_client(clp, timeparms, ip_addr,
                                               authflavour, noresvport);
@@ -543,7 +560,7 @@ install_client:
          * - make sure it's ready before returning
          */
 found_client:
-        spin_unlock(&nfs_client_lock);
+        spin_unlock(&nn->nfs_client_lock);
 
         if (new)
                 nfs_free_client(new);
@@ -643,7 +660,7 @@ static int nfs_create_rpc_client(struct nfs_client *clp,
 {
         struct rpc_clnt         *clnt = NULL;
         struct rpc_create_args args = {
-                .net            = &init_net,
+                .net            = clp->net,
                 .protocol       = clp->cl_proto,
                 .address        = (struct sockaddr *)&clp->cl_addr,
                 .addrsize       = clp->cl_addrlen,
@@ -697,6 +714,7 @@ static int nfs_start_lockd(struct nfs_server *server)
                 .nfs_version    = clp->rpc_ops->version,
                 .noresvport     = server->flags & NFS_MOUNT_NORESVPORT ?
                                         1 : 0,
+                .net            = clp->net,
         };
 
         if (nlm_init.nfs_version > 3)
@@ -832,6 +850,7 @@ static int nfs_init_server(struct nfs_server *server,
                 .addrlen = data->nfs_server.addrlen,
                 .rpc_ops = &nfs_v2_clientops,
                 .proto = data->nfs_server.protocol,
+                .net = data->net,
         };
         struct rpc_timeout timeparms;
         struct nfs_client *clp;
@@ -1030,25 +1049,30 @@ static void nfs_server_copy_userdata(struct nfs_server *target, struct nfs_serve
 static void nfs_server_insert_lists(struct nfs_server *server)
 {
         struct nfs_client *clp = server->nfs_client;
+        struct nfs_net *nn = net_generic(clp->net, nfs_net_id);
 
-        spin_lock(&nfs_client_lock);
+        spin_lock(&nn->nfs_client_lock);
         list_add_tail_rcu(&server->client_link, &clp->cl_superblocks);
-        list_add_tail(&server->master_link, &nfs_volume_list);
+        list_add_tail(&server->master_link, &nn->nfs_volume_list);
         clear_bit(NFS_CS_STOP_RENEW, &clp->cl_res_state);
-        spin_unlock(&nfs_client_lock);
+        spin_unlock(&nn->nfs_client_lock);
 
 }
 
 static void nfs_server_remove_lists(struct nfs_server *server)
 {
         struct nfs_client *clp = server->nfs_client;
+        struct nfs_net *nn;
 
-        spin_lock(&nfs_client_lock);
+        if (clp == NULL)
+                return;
+        nn = net_generic(clp->net, nfs_net_id);
+        spin_lock(&nn->nfs_client_lock);
         list_del_rcu(&server->client_link);
-        if (clp && list_empty(&clp->cl_superblocks))
+        if (list_empty(&clp->cl_superblocks))
                 set_bit(NFS_CS_STOP_RENEW, &clp->cl_res_state);
         list_del(&server->master_link);
-        spin_unlock(&nfs_client_lock);
+        spin_unlock(&nn->nfs_client_lock);
 
         synchronize_rcu();
 }
@@ -1087,6 +1111,8 @@ static struct nfs_server *nfs_alloc_server(void)
                 return NULL;
         }
 
+        ida_init(&server->openowner_id);
+        ida_init(&server->lockowner_id);
         pnfs_init_server(server);
 
         return server;
@@ -1112,6 +1138,8 @@ void nfs_free_server(struct nfs_server *server)
 
         nfs_put_client(server->nfs_client);
 
+        ida_destroy(&server->lockowner_id);
+        ida_destroy(&server->openowner_id);
         nfs_free_iostats(server->io_stats);
         bdi_destroy(&server->backing_dev_info);
         kfree(server);
@@ -1190,45 +1218,19 @@ error:
 /*
  * 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)
+nfs4_find_client_ident(struct net *net, int cb_ident)
 {
         struct nfs_client *clp;
+        struct nfs_net *nn = net_generic(net, nfs_net_id);
 
-        spin_lock(&nfs_client_lock);
-        clp = idr_find(&cb_ident_idr, cb_ident);
+        spin_lock(&nn->nfs_client_lock);
+        clp = idr_find(&nn->cb_ident_idr, cb_ident);
         if (clp)
                 atomic_inc(&clp->cl_count);
-        spin_unlock(&nfs_client_lock);
+        spin_unlock(&nn->nfs_client_lock);
         return clp;
 }
 
@@ -1241,13 +1243,14 @@ nfs4_find_client_ident(int cb_ident)
  * Returns NULL if no such client
  */
 struct nfs_client *
-nfs4_find_client_sessionid(const struct sockaddr *addr,
+nfs4_find_client_sessionid(struct net *net, const struct sockaddr *addr,
                            struct nfs4_sessionid *sid)
 {
         struct nfs_client *clp;
+        struct nfs_net *nn = net_generic(net, nfs_net_id);
 
-        spin_lock(&nfs_client_lock);
-        list_for_each_entry(clp, &nfs_client_list, cl_share_link) {
+        spin_lock(&nn->nfs_client_lock);
+        list_for_each_entry(clp, &nn->nfs_client_list, cl_share_link) {
                 if (nfs4_cb_match_client(addr, clp, 1) == false)
                         continue;
 
@@ -1260,17 +1263,17 @@ nfs4_find_client_sessionid(const struct sockaddr *addr,
                         continue;
 
                 atomic_inc(&clp->cl_count);
-                spin_unlock(&nfs_client_lock);
+                spin_unlock(&nn->nfs_client_lock);
                 return clp;
         }
-        spin_unlock(&nfs_client_lock);
+        spin_unlock(&nn->nfs_client_lock);
         return NULL;
 }
 
 #else /* CONFIG_NFS_V4_1 */
 
 struct nfs_client *
-nfs4_find_client_sessionid(const struct sockaddr *addr,
+nfs4_find_client_sessionid(struct net *net, const struct sockaddr *addr,
                            struct nfs4_sessionid *sid)
 {
         return NULL;
@@ -1285,16 +1288,18 @@ static int nfs4_init_callback(struct nfs_client *clp)
         int error;
 
         if (clp->rpc_ops->version == 4) {
+                struct rpc_xprt *xprt;
+
+                xprt = rcu_dereference_raw(clp->cl_rpcclient->cl_xprt);
+
                 if (nfs4_has_session(clp)) {
-                        error = xprt_setup_backchannel(
-                                                clp->cl_rpcclient->cl_xprt,
+                        error = xprt_setup_backchannel(xprt,
                                                 NFS41_BC_MIN_CALLBACKS);
                         if (error < 0)
                                 return error;
                 }
 
-                error = nfs_callback_up(clp->cl_mvops->minor_version,
-                                        clp->cl_rpcclient->cl_xprt);
+                error = nfs_callback_up(clp->cl_mvops->minor_version, xprt);
                 if (error < 0) {
                         dprintk("%s: failed to start callback. Error = %d\n",
                                 __func__, error);
@@ -1345,6 +1350,7 @@ int nfs4_init_client(struct nfs_client *clp,
                      rpc_authflavor_t authflavour,
                      int noresvport)
 {
+        char buf[INET6_ADDRSTRLEN + 1];
         int error;
 
         if (clp->cl_cons_state == NFS_CS_READY) {
@@ -1360,6 +1366,20 @@ int nfs4_init_client(struct nfs_client *clp,
                                       1, noresvport);
         if (error < 0)
                 goto error;
+
+        /* If no clientaddr= option was specified, find a usable cb address */
+        if (ip_addr == NULL) {
+                struct sockaddr_storage cb_addr;
+                struct sockaddr *sap = (struct sockaddr *)&cb_addr;
+
+                error = rpc_localaddr(clp->cl_rpcclient, sap, sizeof(cb_addr));
+                if (error < 0)
+                        goto error;
+                error = rpc_ntop(sap, buf, sizeof(buf));
+                if (error < 0)
+                        goto error;
+                ip_addr = (const char *)buf;
+        }
         strlcpy(clp->cl_ipaddr, ip_addr, sizeof(clp->cl_ipaddr));
 
         error = nfs_idmap_new(clp);
@@ -1394,7 +1414,7 @@ static int nfs4_set_client(struct nfs_server *server,
                 const char *ip_addr,
                 rpc_authflavor_t authflavour,
                 int proto, const struct rpc_timeout *timeparms,
-                u32 minorversion)
+                u32 minorversion, struct net *net)
 {
         struct nfs_client_initdata cl_init = {
                 .hostname = hostname,
@@ -1403,6 +1423,7 @@ static int nfs4_set_client(struct nfs_server *server,
                 .rpc_ops = &nfs_v4_clientops,
                 .proto = proto,
                 .minorversion = minorversion,
+                .net = net,
         };
         struct nfs_client *clp;
         int error;
@@ -1454,6 +1475,7 @@ struct nfs_client *nfs4_set_ds_client(struct nfs_client* mds_clp,
                 .rpc_ops = &nfs_v4_clientops,
                 .proto = ds_proto,
                 .minorversion = mds_clp->cl_minorversion,
+                .net = mds_clp->net,
         };
         struct rpc_timeout ds_timeout = {
                 .to_initval = 15 * HZ,
@@ -1581,7 +1603,8 @@ static int nfs4_init_server(struct nfs_server *server,
                         data->auth_flavors[0],
                         data->nfs_server.protocol,
                         &timeparms,
-                        data->minorversion);
+                        data->minorversion,
+                        data->net);
         if (error < 0)
                 goto error;
 
@@ -1676,9 +1699,10 @@ struct nfs_server *nfs4_create_referral_server(struct nfs_clone_mount *data,
                                 data->addrlen,
                                 parent_client->cl_ipaddr,
                                 data->authflavor,
-                                parent_server->client->cl_xprt->prot,
+                                rpc_protocol(parent_server->client),
                                 parent_server->client->cl_timeout,
-                                parent_client->cl_mvops->minor_version);
+                                parent_client->cl_mvops->minor_version,
+                                parent_client->net);
         if (error < 0)
                 goto error;
 
@@ -1771,6 +1795,18 @@ out_free_server:
         return ERR_PTR(error);
 }
 
+void nfs_clients_init(struct net *net)
+{
+        struct nfs_net *nn = net_generic(net, nfs_net_id);
+
+        INIT_LIST_HEAD(&nn->nfs_client_list);
+        INIT_LIST_HEAD(&nn->nfs_volume_list);
+#ifdef CONFIG_NFS_V4
+        idr_init(&nn->cb_ident_idr);
+#endif
+        spin_lock_init(&nn->nfs_client_lock);
+}
+
 #ifdef CONFIG_PROC_FS
 static struct proc_dir_entry *proc_fs_nfs;
 
@@ -1824,13 +1860,15 @@ static int nfs_server_list_open(struct inode *inode, struct file *file)
 {
         struct seq_file *m;
         int ret;
+        struct pid_namespace *pid_ns = file->f_dentry->d_sb->s_fs_info;
+        struct net *net = pid_ns->child_reaper->nsproxy->net_ns;
 
         ret = seq_open(file, &nfs_server_list_ops);
         if (ret < 0)
                 return ret;
 
         m = file->private_data;
-        m->private = PDE(inode)->data;
+        m->private = net;
 
         return 0;
 }
@@ -1840,9 +1878,11 @@ static int nfs_server_list_open(struct inode *inode, struct file *file)
  */
 static void *nfs_server_list_start(struct seq_file *m, loff_t *_pos)
 {
+        struct nfs_net *nn = net_generic(m->private, nfs_net_id);
+
         /* lock the list against modification */
-        spin_lock(&nfs_client_lock);
-        return seq_list_start_head(&nfs_client_list, *_pos);
+        spin_lock(&nn->nfs_client_lock);
+        return seq_list_start_head(&nn->nfs_client_list, *_pos);
 }
 
 /*
@@ -1850,7 +1890,9 @@ static void *nfs_server_list_start(struct seq_file *m, loff_t *_pos)
  */
 static void *nfs_server_list_next(struct seq_file *p, void *v, loff_t *pos)
 {
-        return seq_list_next(v, &nfs_client_list, pos);
+        struct nfs_net *nn = net_generic(p->private, nfs_net_id);
+
+        return seq_list_next(v, &nn->nfs_client_list, pos);
 }
 
 /*
@@ -1858,7 +1900,9 @@ 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)
 {
-        spin_unlock(&nfs_client_lock);
+        struct nfs_net *nn = net_generic(p->private, nfs_net_id);
+
+        spin_unlock(&nn->nfs_client_lock);
 }
 
 /*
@@ -1867,9 +1911,10 @@ static void nfs_server_list_stop(struct seq_file *p, void *v)
 static int nfs_server_list_show(struct seq_file *m, void *v)
 {
         struct nfs_client *clp;
+        struct nfs_net *nn = net_generic(m->private, nfs_net_id);
 
         /* display header on line 1 */
-        if (v == &nfs_client_list) {
+        if (v == &nn->nfs_client_list) {
                 seq_puts(m, "NV SERVER   PORT USE HOSTNAME\n");
                 return 0;
         }
@@ -1881,12 +1926,14 @@ static int nfs_server_list_show(struct seq_file *m, void *v)
         if (clp->cl_cons_state != NFS_CS_READY)
                 return 0;
 
+        rcu_read_lock();
         seq_printf(m, "v%u %s %s %3d %s\n",
                    clp->rpc_ops->version,
                    rpc_peeraddr2str(clp->cl_rpcclient, RPC_DISPLAY_HEX_ADDR),
                    rpc_peeraddr2str(clp->cl_rpcclient, RPC_DISPLAY_HEX_PORT),
                    atomic_read(&clp->cl_count),
                    clp->cl_hostname);
+        rcu_read_unlock();
 
         return 0;
 }
@@ -1898,13 +1945,15 @@ static int nfs_volume_list_open(struct inode *inode, struct file *file)
 {
         struct seq_file *m;
         int ret;
+        struct pid_namespace *pid_ns = file->f_dentry->d_sb->s_fs_info;
+        struct net *net = pid_ns->child_reaper->nsproxy->net_ns;
 
         ret = seq_open(file, &nfs_volume_list_ops);
         if (ret < 0)
                 return ret;
 
         m = file->private_data;
-        m->private = PDE(inode)->data;
+        m->private = net;
 
         return 0;
 }
@@ -1914,9 +1963,11 @@ static int nfs_volume_list_open(struct inode *inode, struct file *file)
  */
 static void *nfs_volume_list_start(struct seq_file *m, loff_t *_pos)
 {
+        struct nfs_net *nn = net_generic(m->private, nfs_net_id);
+
         /* lock the list against modification */
-        spin_lock(&nfs_client_lock);
-        return seq_list_start_head(&nfs_volume_list, *_pos);
+        spin_lock(&nn->nfs_client_lock);
+        return seq_list_start_head(&nn->nfs_volume_list, *_pos);
 }
 
 /*
@@ -1924,7 +1975,9 @@ static void *nfs_volume_list_start(struct seq_file *m, loff_t *_pos)
  */
 static void *nfs_volume_list_next(struct seq_file *p, void *v, loff_t *pos)
 {
-        return seq_list_next(v, &nfs_volume_list, pos);
+        struct nfs_net *nn = net_generic(p->private, nfs_net_id);
+
+        return seq_list_next(v, &nn->nfs_volume_list, pos);
 }
 
 /*
@@ -1932,7 +1985,9 @@ 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)
 {
-        spin_unlock(&nfs_client_lock);
+        struct nfs_net *nn = net_generic(p->private, nfs_net_id);
+
+        spin_unlock(&nn->nfs_client_lock);
 }
 
 /*
@@ -1943,9 +1998,10 @@ static int nfs_volume_list_show(struct seq_file *m, void *v)
         struct nfs_server *server;
         struct nfs_client *clp;
         char dev[8], fsid[17];
+        struct nfs_net *nn = net_generic(m->private, nfs_net_id);
 
         /* display header on line 1 */
-        if (v == &nfs_volume_list) {
+        if (v == &nn->nfs_volume_list) {
                 seq_puts(m, "NV SERVER   PORT DEV     FSID              FSC\n");
                 return 0;
         }
@@ -1960,6 +2016,7 @@ static int nfs_volume_list_show(struct seq_file *m, void *v)
                  (unsigned long long) server->fsid.major,
                  (unsigned long long) server->fsid.minor);
 
+        rcu_read_lock();
         seq_printf(m, "v%u %s %s %-7s %-17s %s\n",
                    clp->rpc_ops->version,
                    rpc_peeraddr2str(clp->cl_rpcclient, RPC_DISPLAY_HEX_ADDR),
@@ -1967,6 +2024,7 @@ static int nfs_volume_list_show(struct seq_file *m, void *v)
                    dev,
                    fsid,
                    nfs_server_fscache_state(server));
+        rcu_read_unlock();
 
         return 0;
 }
diff --git a/fs/nfs/delegation.c b/fs/nfs/delegation.c
index 7f265406980..89af1d26927 100644
--- a/fs/nfs/delegation.c
+++ b/fs/nfs/delegation.c
@@ -105,7 +105,7 @@ again:
                         continue;
                 if (!test_bit(NFS_DELEGATED_STATE, &state->flags))
                         continue;
-                if (memcmp(state->stateid.data, stateid->data, sizeof(state->stateid.data)) != 0)
+                if (!nfs4_stateid_match(&state->stateid, stateid))
                         continue;
                 get_nfs_open_context(ctx);
                 spin_unlock(&inode->i_lock);
@@ -139,8 +139,7 @@ void nfs_inode_reclaim_delegation(struct inode *inode, struct rpc_cred *cred,
         if (delegation != NULL) {
                 spin_lock(&delegation->lock);
                 if (delegation->inode != NULL) {
-                        memcpy(delegation->stateid.data, res->delegation.data,
-                               sizeof(delegation->stateid.data));
+                        nfs4_stateid_copy(&delegation->stateid, &res->delegation);
                         delegation->type = res->delegation_type;
                         delegation->maxsize = res->maxsize;
                         oldcred = delegation->cred;
@@ -236,8 +235,7 @@ int nfs_inode_set_delegation(struct inode *inode, struct rpc_cred *cred, struct
         delegation = kmalloc(sizeof(*delegation), GFP_NOFS);
         if (delegation == NULL)
                 return -ENOMEM;
-        memcpy(delegation->stateid.data, res->delegation.data,
-                        sizeof(delegation->stateid.data));
+        nfs4_stateid_copy(&delegation->stateid, &res->delegation);
         delegation->type = res->delegation_type;
         delegation->maxsize = res->maxsize;
         delegation->change_attr = inode->i_version;
@@ -250,19 +248,22 @@ int nfs_inode_set_delegation(struct inode *inode, struct rpc_cred *cred, struct
         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 &&
+                if (nfs4_stateid_match(&delegation->stateid,
+                                        &old_delegation->stateid) &&
                                 delegation->type == old_delegation->type) {
                         goto out;
                 }
                 /*
                  * Deal with broken servers that hand out two
                  * delegations for the same file.
+                 * Allow for upgrades to a WRITE delegation, but
+                 * nothing else.
                  */
                 dfprintk(FILE, "%s: server %s handed out "
                                 "a duplicate delegation!\n",
                                 __func__, clp->cl_hostname);
-                if (delegation->type <= old_delegation->type) {
+                if (delegation->type == old_delegation->type ||
+                    !(delegation->type & FMODE_WRITE)) {
                         freeme = delegation;
                         delegation = NULL;
                         goto out;
@@ -455,17 +456,24 @@ static void nfs_client_mark_return_all_delegation_types(struct nfs_client *clp,
         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_remove_bad_delegation(struct inode *inode)
+{
+        struct nfs_delegation *delegation;
+
+        delegation = nfs_detach_delegation(NFS_I(inode), NFS_SERVER(inode));
+        if (delegation) {
+                nfs_inode_find_state_and_recover(inode, &delegation->stateid);
+                nfs_free_delegation(delegation);
+        }
+}
+EXPORT_SYMBOL_GPL(nfs_remove_bad_delegation);
+
 /**
  * nfs_expire_all_delegation_types
  * @clp: client to process
@@ -488,18 +496,6 @@ 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)
-{
-        if (clp == NULL)
-                return;
-        nfs_client_mark_return_all_delegations(clp);
-}
-
 static void nfs_mark_return_unreferenced_delegations(struct nfs_server *server)
 {
         struct nfs_delegation *delegation;
@@ -531,7 +527,7 @@ void nfs_expire_unreferenced_delegations(struct nfs_client *clp)
 /**
  * nfs_async_inode_return_delegation - asynchronously return a delegation
  * @inode: inode to process
- * @stateid: state ID information from CB_RECALL arguments
+ * @stateid: state ID information
  *
  * Returns zero on success, or a negative errno value.
  */
@@ -545,7 +541,7 @@ int nfs_async_inode_return_delegation(struct inode *inode,
         rcu_read_lock();
         delegation = rcu_dereference(NFS_I(inode)->delegation);
 
-        if (!clp->cl_mvops->validate_stateid(delegation, stateid)) {
+        if (!clp->cl_mvops->match_stateid(&delegation->stateid, stateid)) {
                 rcu_read_unlock();
                 return -ENOENT;
         }
@@ -684,21 +680,25 @@ int nfs_delegations_present(struct nfs_client *clp)
  * nfs4_copy_delegation_stateid - Copy inode's state ID information
  * @dst: stateid data structure to fill in
  * @inode: inode to check
+ * @flags: delegation type requirement
  *
- * Returns one and fills in "dst->data" * if inode had a delegation,
- * otherwise zero is returned.
+ * Returns "true" and fills in "dst->data" * if inode had a delegation,
+ * otherwise "false" is returned.
  */
-int nfs4_copy_delegation_stateid(nfs4_stateid *dst, struct inode *inode)
+bool nfs4_copy_delegation_stateid(nfs4_stateid *dst, struct inode *inode,
+                fmode_t flags)
 {
         struct nfs_inode *nfsi = NFS_I(inode);
         struct nfs_delegation *delegation;
-        int ret = 0;
+        bool ret;
 
+        flags &= FMODE_READ|FMODE_WRITE;
         rcu_read_lock();
         delegation = rcu_dereference(nfsi->delegation);
-        if (delegation != NULL) {
-                memcpy(dst->data, delegation->stateid.data, sizeof(dst->data));
-                ret = 1;
+        ret = (delegation != NULL && (delegation->type & flags) == flags);
+        if (ret) {
+                nfs4_stateid_copy(dst, &delegation->stateid);
+                nfs_mark_delegation_referenced(delegation);
         }
         rcu_read_unlock();
         return ret;
diff --git a/fs/nfs/delegation.h b/fs/nfs/delegation.h
index d9322e490c5..cd6a7a8dada 100644
--- a/fs/nfs/delegation.h
+++ b/fs/nfs/delegation.h
@@ -42,9 +42,9 @@ 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);
 int nfs_client_return_marked_delegations(struct nfs_client *clp);
 int nfs_delegations_present(struct nfs_client *clp);
+void nfs_remove_bad_delegation(struct inode *inode);
 
 void nfs_delegation_mark_reclaim(struct nfs_client *clp);
 void nfs_delegation_reap_unclaimed(struct nfs_client *clp);
@@ -53,7 +53,7 @@ void nfs_delegation_reap_unclaimed(struct nfs_client *clp);
 int nfs4_proc_delegreturn(struct inode *inode, struct rpc_cred *cred, const nfs4_stateid *stateid, int issync);
 int nfs4_open_delegation_recall(struct nfs_open_context *ctx, struct nfs4_state *state, const nfs4_stateid *stateid);
 int nfs4_lock_delegation_recall(struct nfs4_state *state, struct file_lock *fl);
-int nfs4_copy_delegation_stateid(nfs4_stateid *dst, struct inode *inode);
+bool nfs4_copy_delegation_stateid(nfs4_stateid *dst, struct inode *inode, fmode_t flags);
 
 void nfs_mark_delegation_referenced(struct nfs_delegation *delegation);
 int nfs_have_delegation(struct inode *inode, fmode_t flags);
diff --git a/fs/nfs/dir.c b/fs/nfs/dir.c
index 32aa6917265..4aaf0316d76 100644
--- a/fs/nfs/dir.c
+++ b/fs/nfs/dir.c
@@ -207,7 +207,7 @@ struct nfs_cache_array_entry {
 };
 
 struct nfs_cache_array {
-        unsigned int size;
+        int size;
         int eof_index;
         u64 last_cookie;
         struct nfs_cache_array_entry array[0];
@@ -1429,6 +1429,7 @@ static struct dentry *nfs_atomic_lookup(struct inode *dir, struct dentry *dentry
         }
 
         open_flags = nd->intent.open.flags;
+        attr.ia_valid = 0;
 
         ctx = create_nfs_open_context(dentry, open_flags);
         res = ERR_CAST(ctx);
@@ -1437,11 +1438,14 @@ static struct dentry *nfs_atomic_lookup(struct inode *dir, struct dentry *dentry
 
         if (nd->flags & LOOKUP_CREATE) {
                 attr.ia_mode = nd->intent.open.create_mode;
-                attr.ia_valid = ATTR_MODE;
+                attr.ia_valid |= ATTR_MODE;
                 attr.ia_mode &= ~current_umask();
-        } else {
+        } else
                 open_flags &= ~(O_EXCL | O_CREAT);
-                attr.ia_valid = 0;
+
+        if (open_flags & O_TRUNC) {
+                attr.ia_valid |= ATTR_SIZE;
+                attr.ia_size = 0;
         }
 
         /* Open the file on the server */
@@ -1495,6 +1499,7 @@ static int nfs_open_revalidate(struct dentry *dentry, struct nameidata *nd)
         struct inode *inode;
         struct inode *dir;
         struct nfs_open_context *ctx;
+        struct iattr attr;
         int openflags, ret = 0;
 
         if (nd->flags & LOOKUP_RCU)
@@ -1523,19 +1528,27 @@ static int nfs_open_revalidate(struct dentry *dentry, struct nameidata *nd)
         /* We cannot do exclusive creation on a positive dentry */
         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_EXCL|O_TRUNC);
+        /* We can't create new files here */
+        openflags &= ~(O_CREAT|O_EXCL);
 
         ctx = create_nfs_open_context(dentry, openflags);
         ret = PTR_ERR(ctx);
         if (IS_ERR(ctx))
                 goto out;
+
+        attr.ia_valid = 0;
+        if (openflags & O_TRUNC) {
+                attr.ia_valid |= ATTR_SIZE;
+                attr.ia_size = 0;
+                nfs_wb_all(inode);
+        }
+
         /*
          * 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.
          */
-        inode = NFS_PROTO(dir)->open_context(dir, ctx, openflags, NULL);
+        inode = NFS_PROTO(dir)->open_context(dir, ctx, openflags, &attr);
         if (IS_ERR(inode)) {
                 ret = PTR_ERR(inode);
                 switch (ret) {
diff --git a/fs/nfs/direct.c b/fs/nfs/direct.c
index 1940f1a56a5..9c7f66ac6cc 100644
--- a/fs/nfs/direct.c
+++ b/fs/nfs/direct.c
@@ -265,9 +265,7 @@ static void nfs_direct_read_release(void *calldata)
 }
 
 static const struct rpc_call_ops nfs_read_direct_ops = {
-#if defined(CONFIG_NFS_V4_1)
         .rpc_call_prepare = nfs_read_prepare,
-#endif /* CONFIG_NFS_V4_1 */
         .rpc_call_done = nfs_direct_read_result,
         .rpc_release = nfs_direct_read_release,
 };
@@ -554,9 +552,7 @@ static void nfs_direct_commit_release(void *calldata)
 }
 
 static const struct rpc_call_ops nfs_commit_direct_ops = {
-#if defined(CONFIG_NFS_V4_1)
         .rpc_call_prepare = nfs_write_prepare,
-#endif /* CONFIG_NFS_V4_1 */
         .rpc_call_done = nfs_direct_commit_result,
         .rpc_release = nfs_direct_commit_release,
 };
@@ -696,9 +692,7 @@ out_unlock:
 }
 
 static const struct rpc_call_ops nfs_write_direct_ops = {
-#if defined(CONFIG_NFS_V4_1)
         .rpc_call_prepare = nfs_write_prepare,
-#endif /* CONFIG_NFS_V4_1 */
         .rpc_call_done = nfs_direct_write_result,
         .rpc_release = nfs_direct_write_release,
 };
diff --git a/fs/nfs/dns_resolve.c b/fs/nfs/dns_resolve.c
index a6e711ad130..b3924b8a600 100644
--- a/fs/nfs/dns_resolve.c
+++ b/fs/nfs/dns_resolve.c
@@ -10,8 +10,9 @@
 
 #include <linux/sunrpc/clnt.h>
 #include <linux/dns_resolver.h>
+#include "dns_resolve.h"
 
-ssize_t nfs_dns_resolve_name(char *name, size_t namelen,
+ssize_t nfs_dns_resolve_name(struct net *net, char *name, size_t namelen,
                 struct sockaddr *sa, size_t salen)
 {
         ssize_t ret;
@@ -20,7 +21,7 @@ ssize_t nfs_dns_resolve_name(char *name, size_t namelen,
 
         ip_len = dns_query(NULL, name, namelen, NULL, &ip_addr, NULL);
         if (ip_len > 0)
-                ret = rpc_pton(ip_addr, ip_len, sa, salen);
+                ret = rpc_pton(net, ip_addr, ip_len, sa, salen);
         else
                 ret = -ESRCH;
         kfree(ip_addr);
@@ -40,15 +41,15 @@ ssize_t nfs_dns_resolve_name(char *name, size_t namelen,
 #include <linux/sunrpc/clnt.h>
 #include <linux/sunrpc/cache.h>
 #include <linux/sunrpc/svcauth.h>
+#include <linux/sunrpc/rpc_pipe_fs.h>
 
 #include "dns_resolve.h"
 #include "cache_lib.h"
+#include "netns.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;
 
@@ -224,7 +225,7 @@ static int nfs_dns_parse(struct cache_detail *cd, char *buf, int buflen)
         len = qword_get(&buf, buf1, sizeof(buf1));
         if (len <= 0)
                 goto out;
-        key.addrlen = rpc_pton(buf1, len,
+        key.addrlen = rpc_pton(cd->net, buf1, len,
                         (struct sockaddr *)&key.addr,
                         sizeof(key.addr));
 
@@ -259,21 +260,6 @@ 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,
@@ -336,8 +322,8 @@ out:
         return ret;
 }
 
-ssize_t nfs_dns_resolve_name(char *name, size_t namelen,
-                struct sockaddr *sa, size_t salen)
+ssize_t nfs_dns_resolve_name(struct net *net, char *name,
+                size_t namelen, struct sockaddr *sa, size_t salen)
 {
         struct nfs_dns_ent key = {
                 .hostname = name,
@@ -345,28 +331,118 @@ ssize_t nfs_dns_resolve_name(char *name, size_t namelen,
         };
         struct nfs_dns_ent *item = NULL;
         ssize_t ret;
+        struct nfs_net *nn = net_generic(net, nfs_net_id);
 
-        ret = do_cache_lookup_wait(&nfs_dns_resolve, &key, &item);
+        ret = do_cache_lookup_wait(nn->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);
+                cache_put(&item->h, nn->nfs_dns_resolve);
         } else if (ret == -ENOENT)
                 ret = -ESRCH;
         return ret;
 }
 
+int nfs_dns_resolver_cache_init(struct net *net)
+{
+        int err = -ENOMEM;
+        struct nfs_net *nn = net_generic(net, nfs_net_id);
+        struct cache_detail *cd;
+        struct cache_head **tbl;
+
+        cd = kzalloc(sizeof(struct cache_detail), GFP_KERNEL);
+        if (cd == NULL)
+                goto err_cd;
+
+        tbl = kzalloc(NFS_DNS_HASHTBL_SIZE * sizeof(struct cache_head *),
+                        GFP_KERNEL);
+        if (tbl == NULL)
+                goto err_tbl;
+
+        cd->owner = THIS_MODULE,
+        cd->hash_size = NFS_DNS_HASHTBL_SIZE,
+        cd->hash_table = tbl,
+        cd->name = "dns_resolve",
+        cd->cache_put = nfs_dns_ent_put,
+        cd->cache_upcall = nfs_dns_upcall,
+        cd->cache_parse = nfs_dns_parse,
+        cd->cache_show = nfs_dns_show,
+        cd->match = nfs_dns_match,
+        cd->init = nfs_dns_ent_init,
+        cd->update = nfs_dns_ent_update,
+        cd->alloc = nfs_dns_ent_alloc,
+
+        nfs_cache_init(cd);
+        err = nfs_cache_register_net(net, cd);
+        if (err)
+                goto err_reg;
+        nn->nfs_dns_resolve = cd;
+        return 0;
+
+err_reg:
+        nfs_cache_destroy(cd);
+        kfree(cd->hash_table);
+err_tbl:
+        kfree(cd);
+err_cd:
+        return err;
+}
+
+void nfs_dns_resolver_cache_destroy(struct net *net)
+{
+        struct nfs_net *nn = net_generic(net, nfs_net_id);
+        struct cache_detail *cd = nn->nfs_dns_resolve;
+
+        nfs_cache_unregister_net(net, cd);
+        nfs_cache_destroy(cd);
+        kfree(cd->hash_table);
+        kfree(cd);
+}
+
+static int rpc_pipefs_event(struct notifier_block *nb, unsigned long event,
+                           void *ptr)
+{
+        struct super_block *sb = ptr;
+        struct net *net = sb->s_fs_info;
+        struct nfs_net *nn = net_generic(net, nfs_net_id);
+        struct cache_detail *cd = nn->nfs_dns_resolve;
+        int ret = 0;
+
+        if (cd == NULL)
+                return 0;
+
+        if (!try_module_get(THIS_MODULE))
+                return 0;
+
+        switch (event) {
+        case RPC_PIPEFS_MOUNT:
+                ret = nfs_cache_register_sb(sb, cd);
+                break;
+        case RPC_PIPEFS_UMOUNT:
+                nfs_cache_unregister_sb(sb, cd);
+                break;
+        default:
+                ret = -ENOTSUPP;
+                break;
+        }
+        module_put(THIS_MODULE);
+        return ret;
+}
+
+static struct notifier_block nfs_dns_resolver_block = {
+        .notifier_call  = rpc_pipefs_event,
+};
+
 int nfs_dns_resolver_init(void)
 {
-        return nfs_cache_register(&nfs_dns_resolve);
+        return rpc_pipefs_notifier_register(&nfs_dns_resolver_block);
 }
 
 void nfs_dns_resolver_destroy(void)
 {
-        nfs_cache_unregister(&nfs_dns_resolve);
+        rpc_pipefs_notifier_unregister(&nfs_dns_resolver_block);
 }
-
 #endif
diff --git a/fs/nfs/dns_resolve.h b/fs/nfs/dns_resolve.h
index 199bb5543a9..2e4f596d292 100644
--- a/fs/nfs/dns_resolve.h
+++ b/fs/nfs/dns_resolve.h
@@ -15,12 +15,22 @@ static inline int nfs_dns_resolver_init(void)
 
 static inline void nfs_dns_resolver_destroy(void)
 {}
+
+static inline int nfs_dns_resolver_cache_init(struct net *net)
+{
+        return 0;
+}
+
+static inline void nfs_dns_resolver_cache_destroy(struct net *net)
+{}
 #else
 extern int nfs_dns_resolver_init(void);
 extern void nfs_dns_resolver_destroy(void);
+extern int nfs_dns_resolver_cache_init(struct net *net);
+extern void nfs_dns_resolver_cache_destroy(struct net *net);
 #endif
 
-extern ssize_t nfs_dns_resolve_name(char *name, size_t namelen,
-                struct sockaddr *sa, size_t salen);
+extern ssize_t nfs_dns_resolve_name(struct net *net, 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 c43a452f7da..4fdaaa63cf1 100644
--- a/fs/nfs/file.c
+++ b/fs/nfs/file.c
@@ -530,6 +530,8 @@ 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;
 
+        wait_on_page_writeback(page);
+
         pagelen = nfs_page_length(page);
         if (pagelen == 0)
                 goto out_unlock;
diff --git a/fs/nfs/fscache.c b/fs/nfs/fscache.c
index 419119c371b..ae65c16b367 100644
--- a/fs/nfs/fscache.c
+++ b/fs/nfs/fscache.c
@@ -327,7 +327,7 @@ void nfs_fscache_reset_inode_cookie(struct inode *inode)
 {
         struct nfs_inode *nfsi = NFS_I(inode);
         struct nfs_server *nfss = NFS_SERVER(inode);
-        struct fscache_cookie *old = nfsi->fscache;
+        NFS_IFDEBUG(struct fscache_cookie *old = nfsi->fscache);
 
         nfs_fscache_inode_lock(inode);
         if (nfsi->fscache) {
diff --git a/fs/nfs/idmap.c b/fs/nfs/idmap.c
index a1bbf7780df..b7f348bb618 100644
--- a/fs/nfs/idmap.c
+++ b/fs/nfs/idmap.c
@@ -34,11 +34,29 @@
  *  SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
  */
 #include <linux/types.h>
-#include <linux/string.h>
-#include <linux/kernel.h>
-#include <linux/slab.h>
+#include <linux/parser.h>
+#include <linux/fs.h>
 #include <linux/nfs_idmap.h>
+#include <net/net_namespace.h>
+#include <linux/sunrpc/rpc_pipe_fs.h>
 #include <linux/nfs_fs.h>
+#include <linux/nfs_fs_sb.h>
+#include <linux/key.h>
+#include <linux/keyctl.h>
+#include <linux/key-type.h>
+#include <keys/user-type.h>
+#include <linux/module.h>
+
+#include "internal.h"
+#include "netns.h"
+
+#define NFS_UINT_MAXLEN 11
+
+/* Default cache timeout is 10 minutes */
+unsigned int nfs_idmap_cache_timeout = 600;
+static const struct cred *id_resolver_cache;
+static struct key_type key_type_id_resolver_legacy;
+
 
 /**
  * nfs_fattr_init_names - initialise the nfs_fattr owner_name/group_name fields
@@ -142,24 +160,7 @@ static int nfs_map_numeric_to_string(__u32 id, char *buf, size_t buflen)
         return snprintf(buf, buflen, "%u", id);
 }
 
-#ifdef CONFIG_NFS_USE_NEW_IDMAPPER
-
-#include <linux/cred.h>
-#include <linux/sunrpc/sched.h>
-#include <linux/nfs4.h>
-#include <linux/nfs_fs_sb.h>
-#include <linux/keyctl.h>
-#include <linux/key-type.h>
-#include <linux/rcupdate.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 = {
+static struct key_type key_type_id_resolver = {
         .name           = "id_resolver",
         .instantiate    = user_instantiate,
         .match          = user_match,
@@ -169,13 +170,14 @@ struct key_type key_type_id_resolver = {
         .read           = user_read,
 };
 
-int nfs_idmap_init(void)
+static int nfs_idmap_init_keyring(void)
 {
         struct cred *cred;
         struct key *keyring;
         int ret = 0;
 
-        printk(KERN_NOTICE "Registering the %s key type\n", key_type_id_resolver.name);
+        printk(KERN_NOTICE "NFS: Registering the %s key type\n",
+                key_type_id_resolver.name);
 
         cred = prepare_kernel_cred(NULL);
         if (!cred)
@@ -211,7 +213,7 @@ failed_put_cred:
         return ret;
 }
 
-void nfs_idmap_quit(void)
+static void nfs_idmap_quit_keyring(void)
 {
         key_revoke(id_resolver_cache->thread_keyring);
         unregister_key_type(&key_type_id_resolver);
@@ -246,8 +248,10 @@ static ssize_t nfs_idmap_get_desc(const char *name, size_t namelen,
         return desclen;
 }
 
-static ssize_t nfs_idmap_request_key(const char *name, size_t namelen,
-                const char *type, void *data, size_t data_size)
+static ssize_t nfs_idmap_request_key(struct key_type *key_type,
+                                     const char *name, size_t namelen,
+                                     const char *type, void *data,
+                                     size_t data_size, struct idmap *idmap)
 {
         const struct cred *saved_cred;
         struct key *rkey;
@@ -260,8 +264,12 @@ static ssize_t nfs_idmap_request_key(const char *name, size_t namelen,
                 goto out;
 
         saved_cred = override_creds(id_resolver_cache);
-        rkey = request_key(&key_type_id_resolver, desc, "");
+        if (idmap)
+                rkey = request_key_with_auxdata(key_type, desc, "", 0, idmap);
+        else
+                rkey = request_key(&key_type_id_resolver, desc, "");
         revert_creds(saved_cred);
+
         kfree(desc);
         if (IS_ERR(rkey)) {
                 ret = PTR_ERR(rkey);
@@ -294,31 +302,46 @@ out:
         return ret;
 }
 
+static ssize_t nfs_idmap_get_key(const char *name, size_t namelen,
+                                 const char *type, void *data,
+                                 size_t data_size, struct idmap *idmap)
+{
+        ssize_t ret = nfs_idmap_request_key(&key_type_id_resolver,
+                                            name, namelen, type, data,
+                                            data_size, NULL);
+        if (ret < 0) {
+                ret = nfs_idmap_request_key(&key_type_id_resolver_legacy,
+                                            name, namelen, type, data,
+                                            data_size, idmap);
+        }
+        return ret;
+}
 
 /* ID -> Name */
-static ssize_t nfs_idmap_lookup_name(__u32 id, const char *type, char *buf, size_t buflen)
+static ssize_t nfs_idmap_lookup_name(__u32 id, const char *type, char *buf,
+                                     size_t buflen, struct idmap *idmap)
 {
         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);
+        ret = nfs_idmap_get_key(id_str, id_len, type, buf, buflen, idmap);
         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)
+static int nfs_idmap_lookup_id(const char *name, size_t namelen, const char *type,
+                               __u32 *id, struct idmap *idmap)
 {
         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);
+        data_size = nfs_idmap_get_key(name, namelen, type, id_str, NFS_UINT_MAXLEN, idmap);
         if (data_size <= 0) {
                 ret = -EINVAL;
         } else {
@@ -328,114 +351,103 @@ static int nfs_idmap_lookup_id(const char *name, size_t namelen,
         return ret;
 }
 
-int nfs_map_name_to_uid(const struct nfs_server *server, const char *name, size_t namelen, __u32 *uid)
-{
-        if (nfs_map_string_to_numeric(name, namelen, uid))
-                return 0;
-        return nfs_idmap_lookup_id(name, namelen, "uid", uid);
-}
-
-int nfs_map_group_to_gid(const struct nfs_server *server, const char *name, size_t namelen, __u32 *gid)
-{
-        if (nfs_map_string_to_numeric(name, namelen, gid))
-                return 0;
-        return nfs_idmap_lookup_id(name, namelen, "gid", gid);
-}
-
-int nfs_map_uid_to_name(const struct nfs_server *server, __u32 uid, char *buf, size_t buflen)
-{
-        int ret = -EINVAL;
-
-        if (!(server->caps & NFS_CAP_UIDGID_NOMAP))
-                ret = nfs_idmap_lookup_name(uid, "user", buf, buflen);
-        if (ret < 0)
-                ret = nfs_map_numeric_to_string(uid, buf, buflen);
-        return ret;
-}
-int nfs_map_gid_to_group(const struct nfs_server *server, __u32 gid, char *buf, size_t buflen)
-{
-        int ret = -EINVAL;
+/* idmap classic begins here */
+module_param(nfs_idmap_cache_timeout, int, 0644);
 
-        if (!(server->caps & NFS_CAP_UIDGID_NOMAP))
-                ret = nfs_idmap_lookup_name(gid, "group", buf, buflen);
-        if (ret < 0)
-                ret = nfs_map_numeric_to_string(gid, buf, buflen);
-        return ret;
-}
-
-#else  /* CONFIG_NFS_USE_NEW_IDMAPPER not defined */
-
-#include <linux/module.h>
-#include <linux/mutex.h>
-#include <linux/init.h>
-#include <linux/socket.h>
-#include <linux/in.h>
-#include <linux/sched.h>
-#include <linux/sunrpc/clnt.h>
-#include <linux/workqueue.h>
-#include <linux/sunrpc/rpc_pipe_fs.h>
-
-#include <linux/nfs_fs.h>
-
-#include "nfs4_fs.h"
-
-#define IDMAP_HASH_SZ          128
-
-/* Default cache timeout is 10 minutes */
-unsigned int nfs_idmap_cache_timeout = 600 * HZ;
-
-static int param_set_idmap_timeout(const char *val, struct kernel_param *kp)
-{
-        char *endp;
-        int num = simple_strtol(val, &endp, 0);
-        int jif = num * HZ;
-        if (endp == val || *endp || num < 0 || jif < num)
-                return -EINVAL;
-        *((int *)kp->arg) = jif;
-        return 0;
-}
-
-module_param_call(idmap_cache_timeout, param_set_idmap_timeout, param_get_int,
-                 &nfs_idmap_cache_timeout, 0644);
-
-struct idmap_hashent {
-        unsigned long           ih_expires;
-        __u32                   ih_id;
-        size_t                  ih_namelen;
-        char                    ih_name[IDMAP_NAMESZ];
+struct idmap {
+        struct rpc_pipe         *idmap_pipe;
+        struct key_construction *idmap_key_cons;
 };
 
-struct idmap_hashtable {
-        __u8                    h_type;
-        struct idmap_hashent    h_entries[IDMAP_HASH_SZ];
+enum {
+        Opt_find_uid, Opt_find_gid, Opt_find_user, Opt_find_group, Opt_find_err
 };
 
-struct idmap {
-        struct dentry           *idmap_dentry;
-        wait_queue_head_t       idmap_wq;
-        struct idmap_msg        idmap_im;
-        struct mutex            idmap_lock;     /* Serializes upcalls */
-        struct mutex            idmap_im_lock;  /* Protects the hashtable */
-        struct idmap_hashtable  idmap_user_hash;
-        struct idmap_hashtable  idmap_group_hash;
+static const match_table_t nfs_idmap_tokens = {
+        { Opt_find_uid, "uid:%s" },
+        { Opt_find_gid, "gid:%s" },
+        { Opt_find_user, "user:%s" },
+        { Opt_find_group, "group:%s" },
+        { Opt_find_err, NULL }
 };
 
+static int nfs_idmap_legacy_upcall(struct key_construction *, const char *, void *);
 static ssize_t idmap_pipe_downcall(struct file *, const char __user *,
                                    size_t);
 static void idmap_pipe_destroy_msg(struct rpc_pipe_msg *);
 
-static unsigned int fnvhash32(const void *, size_t);
-
 static const struct rpc_pipe_ops idmap_upcall_ops = {
         .upcall         = rpc_pipe_generic_upcall,
         .downcall       = idmap_pipe_downcall,
         .destroy_msg    = idmap_pipe_destroy_msg,
 };
 
+static struct key_type key_type_id_resolver_legacy = {
+        .name           = "id_resolver",
+        .instantiate    = user_instantiate,
+        .match          = user_match,
+        .revoke         = user_revoke,
+        .destroy        = user_destroy,
+        .describe       = user_describe,
+        .read           = user_read,
+        .request_key    = nfs_idmap_legacy_upcall,
+};
+
+static void __nfs_idmap_unregister(struct rpc_pipe *pipe)
+{
+        if (pipe->dentry)
+                rpc_unlink(pipe->dentry);
+}
+
+static int __nfs_idmap_register(struct dentry *dir,
+                                     struct idmap *idmap,
+                                     struct rpc_pipe *pipe)
+{
+        struct dentry *dentry;
+
+        dentry = rpc_mkpipe_dentry(dir, "idmap", idmap, pipe);
+        if (IS_ERR(dentry))
+                return PTR_ERR(dentry);
+        pipe->dentry = dentry;
+        return 0;
+}
+
+static void nfs_idmap_unregister(struct nfs_client *clp,
+                                      struct rpc_pipe *pipe)
+{
+        struct net *net = clp->net;
+        struct super_block *pipefs_sb;
+
+        pipefs_sb = rpc_get_sb_net(net);
+        if (pipefs_sb) {
+                __nfs_idmap_unregister(pipe);
+                rpc_put_sb_net(net);
+        }
+}
+
+static int nfs_idmap_register(struct nfs_client *clp,
+                                   struct idmap *idmap,
+                                   struct rpc_pipe *pipe)
+{
+        struct net *net = clp->net;
+        struct super_block *pipefs_sb;
+        int err = 0;
+
+        pipefs_sb = rpc_get_sb_net(net);
+        if (pipefs_sb) {
+                if (clp->cl_rpcclient->cl_dentry)
+                        err = __nfs_idmap_register(clp->cl_rpcclient->cl_dentry,
+                                                   idmap, pipe);
+                rpc_put_sb_net(net);
+        }
+        return err;
+}
+
 int
 nfs_idmap_new(struct nfs_client *clp)
 {
         struct idmap *idmap;
+        struct rpc_pipe *pipe;
         int error;
 
         BUG_ON(clp->cl_idmap != NULL);
@@ -444,19 +456,19 @@ nfs_idmap_new(struct nfs_client *clp)
         if (idmap == NULL)
                 return -ENOMEM;
 
-        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);
+        pipe = rpc_mkpipe_data(&idmap_upcall_ops, 0);
+        if (IS_ERR(pipe)) {
+                error = PTR_ERR(pipe);
                 kfree(idmap);
                 return error;
         }
-
-        mutex_init(&idmap->idmap_lock);
-        mutex_init(&idmap->idmap_im_lock);
-        init_waitqueue_head(&idmap->idmap_wq);
-        idmap->idmap_user_hash.h_type = IDMAP_TYPE_USER;
-        idmap->idmap_group_hash.h_type = IDMAP_TYPE_GROUP;
+        error = nfs_idmap_register(clp, idmap, pipe);
+        if (error) {
+                rpc_destroy_pipe_data(pipe);
+                kfree(idmap);
+                return error;
+        }
+        idmap->idmap_pipe = pipe;
 
         clp->cl_idmap = idmap;
         return 0;
@@ -469,211 +481,220 @@ nfs_idmap_delete(struct nfs_client *clp)
 
         if (!idmap)
                 return;
-        rpc_unlink(idmap->idmap_dentry);
+        nfs_idmap_unregister(clp, idmap->idmap_pipe);
+        rpc_destroy_pipe_data(idmap->idmap_pipe);
         clp->cl_idmap = NULL;
         kfree(idmap);
 }
 
-/*
- * Helper routines for manipulating the hashtable
- */
-static inline struct idmap_hashent *
-idmap_name_hash(struct idmap_hashtable* h, const char *name, size_t len)
-{
-        return &h->h_entries[fnvhash32(name, len) % IDMAP_HASH_SZ];
-}
-
-static struct idmap_hashent *
-idmap_lookup_name(struct idmap_hashtable *h, const char *name, size_t len)
+static int __rpc_pipefs_event(struct nfs_client *clp, unsigned long event,
+                              struct super_block *sb)
 {
-        struct idmap_hashent *he = idmap_name_hash(h, name, len);
+        int err = 0;
 
-        if (he->ih_namelen != len || memcmp(he->ih_name, name, len) != 0)
-                return NULL;
-        if (time_after(jiffies, he->ih_expires))
-                return NULL;
-        return he;
+        switch (event) {
+        case RPC_PIPEFS_MOUNT:
+                BUG_ON(clp->cl_rpcclient->cl_dentry == NULL);
+                err = __nfs_idmap_register(clp->cl_rpcclient->cl_dentry,
+                                                clp->cl_idmap,
+                                                clp->cl_idmap->idmap_pipe);
+                break;
+        case RPC_PIPEFS_UMOUNT:
+                if (clp->cl_idmap->idmap_pipe) {
+                        struct dentry *parent;
+
+                        parent = clp->cl_idmap->idmap_pipe->dentry->d_parent;
+                        __nfs_idmap_unregister(clp->cl_idmap->idmap_pipe);
+                        /*
+                         * Note: This is a dirty hack. SUNRPC hook has been
+                         * called already but simple_rmdir() call for the
+                         * directory returned with error because of idmap pipe
+                         * inside. Thus now we have to remove this directory
+                         * here.
+                         */
+                        if (rpc_rmdir(parent))
+                                printk(KERN_ERR "NFS: %s: failed to remove "
+                                        "clnt dir!\n", __func__);
+                }
+                break;
+        default:
+                printk(KERN_ERR "NFS: %s: unknown event: %ld\n", __func__,
+                        event);
+                return -ENOTSUPP;
+        }
+        return err;
+}
+
+static struct nfs_client *nfs_get_client_for_event(struct net *net, int event)
+{
+        struct nfs_net *nn = net_generic(net, nfs_net_id);
+        struct dentry *cl_dentry;
+        struct nfs_client *clp;
+
+        spin_lock(&nn->nfs_client_lock);
+        list_for_each_entry(clp, &nn->nfs_client_list, cl_share_link) {
+                if (clp->rpc_ops != &nfs_v4_clientops)
+                        continue;
+                cl_dentry = clp->cl_idmap->idmap_pipe->dentry;
+                if (((event == RPC_PIPEFS_MOUNT) && cl_dentry) ||
+                    ((event == RPC_PIPEFS_UMOUNT) && !cl_dentry))
+                        continue;
+                atomic_inc(&clp->cl_count);
+                spin_unlock(&nn->nfs_client_lock);
+                return clp;
+        }
+        spin_unlock(&nn->nfs_client_lock);
+        return NULL;
 }
 
-static inline struct idmap_hashent *
-idmap_id_hash(struct idmap_hashtable* h, __u32 id)
+static int rpc_pipefs_event(struct notifier_block *nb, unsigned long event,
+                            void *ptr)
 {
-        return &h->h_entries[fnvhash32(&id, sizeof(id)) % IDMAP_HASH_SZ];
-}
+        struct super_block *sb = ptr;
+        struct nfs_client *clp;
+        int error = 0;
 
-static struct idmap_hashent *
-idmap_lookup_id(struct idmap_hashtable *h, __u32 id)
-{
-        struct idmap_hashent *he = idmap_id_hash(h, id);
-        if (he->ih_id != id || he->ih_namelen == 0)
-                return NULL;
-        if (time_after(jiffies, he->ih_expires))
-                return NULL;
-        return he;
+        while ((clp = nfs_get_client_for_event(sb->s_fs_info, event))) {
+                error = __rpc_pipefs_event(clp, event, sb);
+                nfs_put_client(clp);
+                if (error)
+                        break;
+        }
+        return error;
 }
 
-/*
- * Routines for allocating new entries in the hashtable.
- * For now, we just have 1 entry per bucket, so it's all
- * pretty trivial.
- */
-static inline struct idmap_hashent *
-idmap_alloc_name(struct idmap_hashtable *h, char *name, size_t len)
-{
-        return idmap_name_hash(h, name, len);
-}
+#define PIPEFS_NFS_PRIO         1
+
+static struct notifier_block nfs_idmap_block = {
+        .notifier_call  = rpc_pipefs_event,
+        .priority       = SUNRPC_PIPEFS_NFS_PRIO,
+};
 
-static inline struct idmap_hashent *
-idmap_alloc_id(struct idmap_hashtable *h, __u32 id)
+int nfs_idmap_init(void)
 {
-        return idmap_id_hash(h, id);
+        int ret;
+        ret = nfs_idmap_init_keyring();
+        if (ret != 0)
+                goto out;
+        ret = rpc_pipefs_notifier_register(&nfs_idmap_block);
+        if (ret != 0)
+                nfs_idmap_quit_keyring();
+out:
+        return ret;
 }
 
-static void
-idmap_update_entry(struct idmap_hashent *he, const char *name,
-                size_t namelen, __u32 id)
+void nfs_idmap_quit(void)
 {
-        he->ih_id = id;
-        memcpy(he->ih_name, name, namelen);
-        he->ih_name[namelen] = '\0';
-        he->ih_namelen = namelen;
-        he->ih_expires = jiffies + nfs_idmap_cache_timeout;
+        rpc_pipefs_notifier_unregister(&nfs_idmap_block);
+        nfs_idmap_quit_keyring();
 }
 
-/*
- * Name -> ID
- */
-static int
-nfs_idmap_id(struct idmap *idmap, struct idmap_hashtable *h,
-                const char *name, size_t namelen, __u32 *id)
+static int nfs_idmap_prepare_message(char *desc, struct idmap_msg *im,
+                                     struct rpc_pipe_msg *msg)
 {
-        struct rpc_pipe_msg msg;
-        struct idmap_msg *im;
-        struct idmap_hashent *he;
-        DECLARE_WAITQUEUE(wq, current);
-        int ret = -EIO;
-
-        im = &idmap->idmap_im;
-
-        /*
-         * String sanity checks
-         * Note that the userland daemon expects NUL terminated strings
-         */
-        for (;;) {
-                if (namelen == 0)
-                        return -EINVAL;
-                if (name[namelen-1] != '\0')
-                        break;
-                namelen--;
-        }
-        if (namelen >= IDMAP_NAMESZ)
-                return -EINVAL;
+        substring_t substr;
+        int token, ret;
 
-        mutex_lock(&idmap->idmap_lock);
-        mutex_lock(&idmap->idmap_im_lock);
-
-        he = idmap_lookup_name(h, name, namelen);
-        if (he != NULL) {
-                *id = he->ih_id;
-                ret = 0;
-                goto out;
-        }
+        memset(im,  0, sizeof(*im));
+        memset(msg, 0, sizeof(*msg));
 
-        memset(im, 0, sizeof(*im));
-        memcpy(im->im_name, name, namelen);
+        im->im_type = IDMAP_TYPE_GROUP;
+        token = match_token(desc, nfs_idmap_tokens, &substr);
 
-        im->im_type = h->h_type;
-        im->im_conv = IDMAP_CONV_NAMETOID;
+        switch (token) {
+        case Opt_find_uid:
+                im->im_type = IDMAP_TYPE_USER;
+        case Opt_find_gid:
+                im->im_conv = IDMAP_CONV_NAMETOID;
+                ret = match_strlcpy(im->im_name, &substr, IDMAP_NAMESZ);
+                break;
 
-        memset(&msg, 0, sizeof(msg));
-        msg.data = im;
-        msg.len = sizeof(*im);
+        case Opt_find_user:
+                im->im_type = IDMAP_TYPE_USER;
+        case Opt_find_group:
+                im->im_conv = IDMAP_CONV_IDTONAME;
+                ret = match_int(&substr, &im->im_id);
+                break;
 
-        add_wait_queue(&idmap->idmap_wq, &wq);
-        if (rpc_queue_upcall(idmap->idmap_dentry->d_inode, &msg) < 0) {
-                remove_wait_queue(&idmap->idmap_wq, &wq);
+        default:
+                ret = -EINVAL;
                 goto out;
         }
 
-        set_current_state(TASK_UNINTERRUPTIBLE);
-        mutex_unlock(&idmap->idmap_im_lock);
-        schedule();
-        __set_current_state(TASK_RUNNING);
-        remove_wait_queue(&idmap->idmap_wq, &wq);
-        mutex_lock(&idmap->idmap_im_lock);
+        msg->data = im;
+        msg->len  = sizeof(struct idmap_msg);
 
-        if (im->im_status & IDMAP_STATUS_SUCCESS) {
-                *id = im->im_id;
-                ret = 0;
-        }
-
- out:
-        memset(im, 0, sizeof(*im));
-        mutex_unlock(&idmap->idmap_im_lock);
-        mutex_unlock(&idmap->idmap_lock);
+out:
         return ret;
 }
 
-/*
- * ID -> Name
- */
-static int
-nfs_idmap_name(struct idmap *idmap, struct idmap_hashtable *h,
-                __u32 id, char *name)
+static int nfs_idmap_legacy_upcall(struct key_construction *cons,
+                                   const char *op,
+                                   void *aux)
 {
-        struct rpc_pipe_msg msg;
+        struct rpc_pipe_msg *msg;
         struct idmap_msg *im;
-        struct idmap_hashent *he;
-        DECLARE_WAITQUEUE(wq, current);
-        int ret = -EIO;
-        unsigned int len;
-
-        im = &idmap->idmap_im;
+        struct idmap *idmap = (struct idmap *)aux;
+        struct key *key = cons->key;
+        int ret;
 
-        mutex_lock(&idmap->idmap_lock);
-        mutex_lock(&idmap->idmap_im_lock);
+        /* msg and im are freed in idmap_pipe_destroy_msg */
+        msg = kmalloc(sizeof(*msg), GFP_KERNEL);
+        if (IS_ERR(msg)) {
+                ret = PTR_ERR(msg);
+                goto out0;
+        }
 
-        he = idmap_lookup_id(h, id);
-        if (he) {
-                memcpy(name, he->ih_name, he->ih_namelen);
-                ret = he->ih_namelen;
-                goto out;
+        im = kmalloc(sizeof(*im), GFP_KERNEL);
+        if (IS_ERR(im)) {
+                ret = PTR_ERR(im);
+                goto out1;
         }
 
-        memset(im, 0, sizeof(*im));
-        im->im_type = h->h_type;
-        im->im_conv = IDMAP_CONV_IDTONAME;
-        im->im_id = id;
+        ret = nfs_idmap_prepare_message(key->description, im, msg);
+        if (ret < 0)
+                goto out2;
 
-        memset(&msg, 0, sizeof(msg));
-        msg.data = im;
-        msg.len = sizeof(*im);
+        idmap->idmap_key_cons = cons;
 
-        add_wait_queue(&idmap->idmap_wq, &wq);
+        ret = rpc_queue_upcall(idmap->idmap_pipe, msg);
+        if (ret < 0)
+                goto out2;
 
-        if (rpc_queue_upcall(idmap->idmap_dentry->d_inode, &msg) < 0) {
-                remove_wait_queue(&idmap->idmap_wq, &wq);
-                goto out;
-        }
+        return ret;
+
+out2:
+        kfree(im);
+out1:
+        kfree(msg);
+out0:
+        key_revoke(cons->key);
+        key_revoke(cons->authkey);
+        return ret;
+}
+
+static int nfs_idmap_instantiate(struct key *key, struct key *authkey, char *data)
+{
+        return key_instantiate_and_link(key, data, strlen(data) + 1,
+                                        id_resolver_cache->thread_keyring,
+                                        authkey);
+}
 
-        set_current_state(TASK_UNINTERRUPTIBLE);
-        mutex_unlock(&idmap->idmap_im_lock);
-        schedule();
-        __set_current_state(TASK_RUNNING);
-        remove_wait_queue(&idmap->idmap_wq, &wq);
-        mutex_lock(&idmap->idmap_im_lock);
-
-        if (im->im_status & IDMAP_STATUS_SUCCESS) {
-                if ((len = strnlen(im->im_name, IDMAP_NAMESZ)) == 0)
-                        goto out;
-                memcpy(name, im->im_name, len);
-                ret = len;
+static int nfs_idmap_read_message(struct idmap_msg *im, struct key *key, struct key *authkey)
+{
+        char id_str[NFS_UINT_MAXLEN];
+        int ret = -EINVAL;
+
+        switch (im->im_conv) {
+        case IDMAP_CONV_NAMETOID:
+                sprintf(id_str, "%d", im->im_id);
+                ret = nfs_idmap_instantiate(key, authkey, id_str);
+                break;
+        case IDMAP_CONV_IDTONAME:
+                ret = nfs_idmap_instantiate(key, authkey, im->im_name);
+                break;
         }
 
- out:
-        memset(im, 0, sizeof(*im));
-        mutex_unlock(&idmap->idmap_im_lock);
-        mutex_unlock(&idmap->idmap_lock);
         return ret;
 }
 
@@ -682,115 +703,51 @@ idmap_pipe_downcall(struct file *filp, const char __user *src, size_t mlen)
 {
         struct rpc_inode *rpci = RPC_I(filp->f_path.dentry->d_inode);
         struct idmap *idmap = (struct idmap *)rpci->private;
-        struct idmap_msg im_in, *im = &idmap->idmap_im;
-        struct idmap_hashtable *h;
-        struct idmap_hashent *he = NULL;
+        struct key_construction *cons = idmap->idmap_key_cons;
+        struct idmap_msg im;
         size_t namelen_in;
         int ret;
 
-        if (mlen != sizeof(im_in))
-                return -ENOSPC;
-
-        if (copy_from_user(&im_in, src, mlen) != 0)
-                return -EFAULT;
-
-        mutex_lock(&idmap->idmap_im_lock);
-
-        ret = mlen;
-        im->im_status = im_in.im_status;
-        /* If we got an error, terminate now, and wake up pending upcalls */
-        if (!(im_in.im_status & IDMAP_STATUS_SUCCESS)) {
-                wake_up(&idmap->idmap_wq);
+        if (mlen != sizeof(im)) {
+                ret = -ENOSPC;
                 goto out;
         }
 
-        /* Sanity checking of strings */
-        ret = -EINVAL;
-        namelen_in = strnlen(im_in.im_name, IDMAP_NAMESZ);
-        if (namelen_in == 0 || namelen_in == IDMAP_NAMESZ)
+        if (copy_from_user(&im, src, mlen) != 0) {
+                ret = -EFAULT;
                 goto out;
+        }
 
-        switch (im_in.im_type) {
-                case IDMAP_TYPE_USER:
-                        h = &idmap->idmap_user_hash;
-                        break;
-                case IDMAP_TYPE_GROUP:
-                        h = &idmap->idmap_group_hash;
-                        break;
-                default:
-                        goto out;
+        if (!(im.im_status & IDMAP_STATUS_SUCCESS)) {
+                ret = mlen;
+                complete_request_key(idmap->idmap_key_cons, -ENOKEY);
+                goto out_incomplete;
         }
 
-        switch (im_in.im_conv) {
-        case IDMAP_CONV_IDTONAME:
-                /* Did we match the current upcall? */
-                if (im->im_conv == IDMAP_CONV_IDTONAME
-                                && im->im_type == im_in.im_type
-                                && im->im_id == im_in.im_id) {
-                        /* Yes: copy string, including the terminating '\0'  */
-                        memcpy(im->im_name, im_in.im_name, namelen_in);
-                        im->im_name[namelen_in] = '\0';
-                        wake_up(&idmap->idmap_wq);
-                }
-                he = idmap_alloc_id(h, im_in.im_id);
-                break;
-        case IDMAP_CONV_NAMETOID:
-                /* Did we match the current upcall? */
-                if (im->im_conv == IDMAP_CONV_NAMETOID
-                                && im->im_type == im_in.im_type
-                                && strnlen(im->im_name, IDMAP_NAMESZ) == namelen_in
-                                && memcmp(im->im_name, im_in.im_name, namelen_in) == 0) {
-                        im->im_id = im_in.im_id;
-                        wake_up(&idmap->idmap_wq);
-                }
-                he = idmap_alloc_name(h, im_in.im_name, namelen_in);
-                break;
-        default:
+        namelen_in = strnlen(im.im_name, IDMAP_NAMESZ);
+        if (namelen_in == 0 || namelen_in == IDMAP_NAMESZ) {
+                ret = -EINVAL;
                 goto out;
         }
 
-        /* If the entry is valid, also copy it to the cache */
-        if (he != NULL)
-                idmap_update_entry(he, im_in.im_name, namelen_in, im_in.im_id);
-        ret = mlen;
+        ret = nfs_idmap_read_message(&im, cons->key, cons->authkey);
+        if (ret >= 0) {
+                key_set_timeout(cons->key, nfs_idmap_cache_timeout);
+                ret = mlen;
+        }
+
 out:
-        mutex_unlock(&idmap->idmap_im_lock);
+        complete_request_key(idmap->idmap_key_cons, ret);
+out_incomplete:
         return ret;
 }
 
 static void
 idmap_pipe_destroy_msg(struct rpc_pipe_msg *msg)
 {
-        struct idmap_msg *im = msg->data;
-        struct idmap *idmap = container_of(im, struct idmap, idmap_im); 
-
-        if (msg->errno >= 0)
-                return;
-        mutex_lock(&idmap->idmap_im_lock);
-        im->im_status = IDMAP_STATUS_LOOKUPFAIL;
-        wake_up(&idmap->idmap_wq);
-        mutex_unlock(&idmap->idmap_im_lock);
-}
-
-/* 
- * Fowler/Noll/Vo hash
- *    http://www.isthe.com/chongo/tech/comp/fnv/
- */
-
-#define FNV_P_32 ((unsigned int)0x01000193) /* 16777619 */
-#define FNV_1_32 ((unsigned int)0x811c9dc5) /* 2166136261 */
-
-static unsigned int fnvhash32(const void *buf, size_t buflen)
-{
-        const unsigned char *p, *end = (const unsigned char *)buf + buflen;
-        unsigned int hash = FNV_1_32;
-
-        for (p = buf; p < end; p++) {
-                hash *= FNV_P_32;
-                hash ^= (unsigned int)*p;
-        }
-
-        return hash;
+        /* Free memory allocated in nfs_idmap_legacy_upcall() */
+        kfree(msg->data);
+        kfree(msg);
 }
 
 int nfs_map_name_to_uid(const struct nfs_server *server, const char *name, size_t namelen, __u32 *uid)
@@ -799,16 +756,16 @@ int nfs_map_name_to_uid(const struct nfs_server *server, const char *name, size_
 
         if (nfs_map_string_to_numeric(name, namelen, uid))
                 return 0;
-        return nfs_idmap_id(idmap, &idmap->idmap_user_hash, name, namelen, uid);
+        return nfs_idmap_lookup_id(name, namelen, "uid", uid, idmap);
 }
 
-int nfs_map_group_to_gid(const struct nfs_server *server, const char *name, size_t namelen, __u32 *uid)
+int nfs_map_group_to_gid(const struct nfs_server *server, const char *name, size_t namelen, __u32 *gid)
 {
         struct idmap *idmap = server->nfs_client->cl_idmap;
 
-        if (nfs_map_string_to_numeric(name, namelen, uid))
+        if (nfs_map_string_to_numeric(name, namelen, gid))
                 return 0;
-        return nfs_idmap_id(idmap, &idmap->idmap_group_hash, name, namelen, uid);
+        return nfs_idmap_lookup_id(name, namelen, "gid", gid, idmap);
 }
 
 int nfs_map_uid_to_name(const struct nfs_server *server, __u32 uid, char *buf, size_t buflen)
@@ -817,21 +774,19 @@ int nfs_map_uid_to_name(const struct nfs_server *server, __u32 uid, char *buf, s
         int ret = -EINVAL;
 
         if (!(server->caps & NFS_CAP_UIDGID_NOMAP))
-                ret = nfs_idmap_name(idmap, &idmap->idmap_user_hash, uid, buf);
+                ret = nfs_idmap_lookup_name(uid, "user", buf, buflen, idmap);
         if (ret < 0)
                 ret = nfs_map_numeric_to_string(uid, buf, buflen);
         return ret;
 }
-int nfs_map_gid_to_group(const struct nfs_server *server, __u32 uid, char *buf, size_t buflen)
+int nfs_map_gid_to_group(const struct nfs_server *server, __u32 gid, char *buf, size_t buflen)
 {
         struct idmap *idmap = server->nfs_client->cl_idmap;
         int ret = -EINVAL;
 
         if (!(server->caps & NFS_CAP_UIDGID_NOMAP))
-                ret = nfs_idmap_name(idmap, &idmap->idmap_group_hash, uid, buf);
+                ret = nfs_idmap_lookup_name(gid, "group", buf, buflen, idmap);
         if (ret < 0)
-                ret = nfs_map_numeric_to_string(uid, buf, buflen);
+                ret = nfs_map_numeric_to_string(gid, buf, buflen);
         return ret;
 }
-
-#endif /* CONFIG_NFS_USE_NEW_IDMAPPER */
diff --git a/fs/nfs/inode.c b/fs/nfs/inode.c
index f649fba8c38..7bb4d13c1cd 100644
--- a/fs/nfs/inode.c
+++ b/fs/nfs/inode.c
@@ -39,6 +39,7 @@
 #include <linux/slab.h>
 #include <linux/compat.h>
 #include <linux/freezer.h>
+#include <linux/crc32.h>
 
 #include <asm/system.h>
 #include <asm/uaccess.h>
@@ -51,6 +52,7 @@
 #include "fscache.h"
 #include "dns_resolve.h"
 #include "pnfs.h"
+#include "netns.h"
 
 #define NFSDBG_FACILITY         NFSDBG_VFS
 
@@ -388,9 +390,10 @@ nfs_fhget(struct super_block *sb, struct nfs_fh *fh, struct nfs_fattr *fattr)
                 unlock_new_inode(inode);
         } else
                 nfs_refresh_inode(inode, fattr);
-        dprintk("NFS: nfs_fhget(%s/%Ld ct=%d)\n",
+        dprintk("NFS: nfs_fhget(%s/%Ld fh_crc=0x%08x ct=%d)\n",
                 inode->i_sb->s_id,
                 (long long)NFS_FILEID(inode),
+                nfs_display_fhandle_hash(fh),
                 atomic_read(&inode->i_count));
 
 out:
@@ -401,7 +404,7 @@ out_no_inode:
         goto out;
 }
 
-#define NFS_VALID_ATTRS (ATTR_MODE|ATTR_UID|ATTR_GID|ATTR_SIZE|ATTR_ATIME|ATTR_ATIME_SET|ATTR_MTIME|ATTR_MTIME_SET|ATTR_FILE)
+#define NFS_VALID_ATTRS (ATTR_MODE|ATTR_UID|ATTR_GID|ATTR_SIZE|ATTR_ATIME|ATTR_ATIME_SET|ATTR_MTIME|ATTR_MTIME_SET|ATTR_FILE|ATTR_OPEN)
 
 int
 nfs_setattr(struct dentry *dentry, struct iattr *attr)
@@ -423,7 +426,7 @@ nfs_setattr(struct dentry *dentry, struct iattr *attr)
 
         /* Optimization: if the end result is no change, don't RPC */
         attr->ia_valid &= NFS_VALID_ATTRS;
-        if ((attr->ia_valid & ~ATTR_FILE) == 0)
+        if ((attr->ia_valid & ~(ATTR_FILE|ATTR_OPEN)) == 0)
                 return 0;
 
         /* Write all dirty data */
@@ -1044,6 +1047,67 @@ struct nfs_fh *nfs_alloc_fhandle(void)
         return fh;
 }
 
+#ifdef NFS_DEBUG
+/*
+ * _nfs_display_fhandle_hash - calculate the crc32 hash for the filehandle
+ *                             in the same way that wireshark does
+ *
+ * @fh: file handle
+ *
+ * For debugging only.
+ */
+u32 _nfs_display_fhandle_hash(const struct nfs_fh *fh)
+{
+        /* wireshark uses 32-bit AUTODIN crc and does a bitwise
+         * not on the result */
+        return ~crc32(0xFFFFFFFF, &fh->data[0], fh->size);
+}
+
+/*
+ * _nfs_display_fhandle - display an NFS file handle on the console
+ *
+ * @fh: file handle to display
+ * @caption: display caption
+ *
+ * For debugging only.
+ */
+void _nfs_display_fhandle(const struct nfs_fh *fh, const char *caption)
+{
+        unsigned short i;
+
+        if (fh == NULL || fh->size == 0) {
+                printk(KERN_DEFAULT "%s at %p is empty\n", caption, fh);
+                return;
+        }
+
+        printk(KERN_DEFAULT "%s at %p is %u bytes, crc: 0x%08x:\n",
+               caption, fh, fh->size, _nfs_display_fhandle_hash(fh));
+        for (i = 0; i < fh->size; i += 16) {
+                __be32 *pos = (__be32 *)&fh->data[i];
+
+                switch ((fh->size - i - 1) >> 2) {
+                case 0:
+                        printk(KERN_DEFAULT " %08x\n",
+                                be32_to_cpup(pos));
+                        break;
+                case 1:
+                        printk(KERN_DEFAULT " %08x %08x\n",
+                                be32_to_cpup(pos), be32_to_cpup(pos + 1));
+                        break;
+                case 2:
+                        printk(KERN_DEFAULT " %08x %08x %08x\n",
+                                be32_to_cpup(pos), be32_to_cpup(pos + 1),
+                                be32_to_cpup(pos + 2));
+                        break;
+                default:
+                        printk(KERN_DEFAULT " %08x %08x %08x %08x\n",
+                                be32_to_cpup(pos), be32_to_cpup(pos + 1),
+                                be32_to_cpup(pos + 2), be32_to_cpup(pos + 3));
+                }
+        }
+}
+#endif
+
 /**
  * nfs_inode_attrs_need_update - check if the inode attributes need updating
  * @inode - pointer to inode
@@ -1211,8 +1275,9 @@ static int nfs_update_inode(struct inode *inode, struct nfs_fattr *fattr)
         unsigned long now = jiffies;
         unsigned long save_cache_validity;
 
-        dfprintk(VFS, "NFS: %s(%s/%ld ct=%d info=0x%x)\n",
+        dfprintk(VFS, "NFS: %s(%s/%ld fh_crc=0x%08x ct=%d info=0x%x)\n",
                         __func__, inode->i_sb->s_id, inode->i_ino,
+                        nfs_display_fhandle_hash(NFS_FH(inode)),
                         atomic_read(&inode->i_count), fattr->valid);
 
         if ((fattr->valid & NFS_ATTR_FATTR_FILEID) && nfsi->fileid != fattr->fileid)
@@ -1406,7 +1471,7 @@ static int nfs_update_inode(struct inode *inode, struct nfs_fattr *fattr)
         /*
          * Big trouble! The inode has become a different object.
          */
-        printk(KERN_DEBUG "%s: inode %ld mode changed, %07o to %07o\n",
+        printk(KERN_DEBUG "NFS: %s: inode %ld mode changed, %07o to %07o\n",
                         __func__, inode->i_ino, inode->i_mode, fattr->mode);
  out_err:
         /*
@@ -1495,7 +1560,7 @@ static void init_once(void *foo)
         INIT_LIST_HEAD(&nfsi->open_files);
         INIT_LIST_HEAD(&nfsi->access_cache_entry_lru);
         INIT_LIST_HEAD(&nfsi->access_cache_inode_lru);
-        INIT_RADIX_TREE(&nfsi->nfs_page_tree, GFP_ATOMIC);
+        INIT_LIST_HEAD(&nfsi->commit_list);
         nfsi->npages = 0;
         nfsi->ncommit = 0;
         atomic_set(&nfsi->silly_count, 1);
@@ -1552,6 +1617,28 @@ static void nfsiod_stop(void)
         destroy_workqueue(wq);
 }
 
+int nfs_net_id;
+EXPORT_SYMBOL_GPL(nfs_net_id);
+
+static int nfs_net_init(struct net *net)
+{
+        nfs_clients_init(net);
+        return nfs_dns_resolver_cache_init(net);
+}
+
+static void nfs_net_exit(struct net *net)
+{
+        nfs_dns_resolver_cache_destroy(net);
+        nfs_cleanup_cb_ident_idr(net);
+}
+
+static struct pernet_operations nfs_net_ops = {
+        .init = nfs_net_init,
+        .exit = nfs_net_exit,
+        .id   = &nfs_net_id,
+        .size = sizeof(struct nfs_net),
+};
+
 /*
  * Initialize NFS
  */
@@ -1561,10 +1648,14 @@ static int __init init_nfs_fs(void)
 
         err = nfs_idmap_init();
         if (err < 0)
-                goto out9;
+                goto out10;
 
         err = nfs_dns_resolver_init();
         if (err < 0)
+                goto out9;
+
+        err = register_pernet_subsys(&nfs_net_ops);
+        if (err < 0)
                 goto out8;
 
         err = nfs_fscache_register();
@@ -1600,14 +1691,14 @@ static int __init init_nfs_fs(void)
                 goto out0;
 
 #ifdef CONFIG_PROC_FS
-        rpc_proc_register(&nfs_rpcstat);
+        rpc_proc_register(&init_net, &nfs_rpcstat);
 #endif
         if ((err = register_nfs_fs()) != 0)
                 goto out;
         return 0;
 out:
 #ifdef CONFIG_PROC_FS
-        rpc_proc_unregister("nfs");
+        rpc_proc_unregister(&init_net, "nfs");
 #endif
         nfs_destroy_directcache();
 out0:
@@ -1625,10 +1716,12 @@ out5:
 out6:
         nfs_fscache_unregister();
 out7:
-        nfs_dns_resolver_destroy();
+        unregister_pernet_subsys(&nfs_net_ops);
 out8:
-        nfs_idmap_quit();
+        nfs_dns_resolver_destroy();
 out9:
+        nfs_idmap_quit();
+out10:
         return err;
 }
 
@@ -1640,12 +1733,12 @@ static void __exit exit_nfs_fs(void)
         nfs_destroy_inodecache();
         nfs_destroy_nfspagecache();
         nfs_fscache_unregister();
+        unregister_pernet_subsys(&nfs_net_ops);
         nfs_dns_resolver_destroy();
         nfs_idmap_quit();
 #ifdef CONFIG_PROC_FS
-        rpc_proc_unregister("nfs");
+        rpc_proc_unregister(&init_net, "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 8102db9b926..2476dc69365 100644
--- a/fs/nfs/internal.h
+++ b/fs/nfs/internal.h
@@ -123,6 +123,7 @@ struct nfs_parsed_mount_data {
         } nfs_server;
 
         struct security_mnt_opts lsm_opts;
+        struct net              *net;
 };
 
 /* mount_clnt.c */
@@ -137,20 +138,22 @@ struct nfs_mount_request {
         int                     noresvport;
         unsigned int            *auth_flav_len;
         rpc_authflavor_t        *auth_flavs;
+        struct net              *net;
 };
 
 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 const struct rpc_program nfs_program;
+extern void nfs_clients_init(struct net *net);
 
-extern void nfs_cleanup_cb_ident_idr(void);
+extern void nfs_cleanup_cb_ident_idr(struct net *);
 extern void nfs_put_client(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_ident(struct net *, int);
 extern struct nfs_client *
-nfs4_find_client_sessionid(const struct sockaddr *, struct nfs4_sessionid *);
+nfs4_find_client_sessionid(struct net *, const struct sockaddr *,
+                                struct nfs4_sessionid *);
 extern struct nfs_server *nfs_create_server(
                                         const struct nfs_parsed_mount_data *,
                                         struct nfs_fh *);
@@ -329,6 +332,8 @@ void nfs_retry_commit(struct list_head *page_list,
 void nfs_commit_clear_lock(struct nfs_inode *nfsi);
 void nfs_commitdata_release(void *data);
 void nfs_commit_release_pages(struct nfs_write_data *data);
+void nfs_request_add_commit_list(struct nfs_page *req, struct list_head *head);
+void nfs_request_remove_commit_list(struct nfs_page *req);
 
 #ifdef CONFIG_MIGRATION
 extern int nfs_migrate_page(struct address_space *,
diff --git a/fs/nfs/mount_clnt.c b/fs/nfs/mount_clnt.c
index d4c2d6b7507..8e65c7f1f87 100644
--- a/fs/nfs/mount_clnt.c
+++ b/fs/nfs/mount_clnt.c
@@ -16,7 +16,7 @@
 #include <linux/nfs_fs.h>
 #include "internal.h"
 
-#ifdef RPC_DEBUG
+#ifdef NFS_DEBUG
 # define NFSDBG_FACILITY        NFSDBG_MOUNT
 #endif
 
@@ -67,7 +67,7 @@ enum {
         MOUNTPROC3_EXPORT       = 5,
 };
 
-static struct rpc_program       mnt_program;
+static const struct rpc_program mnt_program;
 
 /*
  * Defined by OpenGroup XNFS Version 3W, chapter 8
@@ -153,7 +153,7 @@ int nfs_mount(struct nfs_mount_request *info)
                 .rpc_resp       = &result,
         };
         struct rpc_create_args args = {
-                .net            = &init_net,
+                .net            = info->net,
                 .protocol       = info->protocol,
                 .address        = info->sap,
                 .addrsize       = info->salen,
@@ -225,7 +225,7 @@ void nfs_umount(const struct nfs_mount_request *info)
                 .to_retries = 2,
         };
         struct rpc_create_args args = {
-                .net            = &init_net,
+                .net            = info->net,
                 .protocol       = IPPROTO_UDP,
                 .address        = info->sap,
                 .addrsize       = info->salen,
@@ -488,19 +488,19 @@ static struct rpc_procinfo mnt3_procedures[] = {
 };
 
 
-static struct rpc_version mnt_version1 = {
+static const struct rpc_version mnt_version1 = {
         .number         = 1,
         .nrprocs        = ARRAY_SIZE(mnt_procedures),
         .procs          = mnt_procedures,
 };
 
-static struct rpc_version mnt_version3 = {
+static const struct rpc_version mnt_version3 = {
         .number         = 3,
         .nrprocs        = ARRAY_SIZE(mnt3_procedures),
         .procs          = mnt3_procedures,
 };
 
-static struct rpc_version *mnt_version[] = {
+static const struct rpc_version *mnt_version[] = {
         NULL,
         &mnt_version1,
         NULL,
@@ -509,7 +509,7 @@ static struct rpc_version *mnt_version[] = {
 
 static struct rpc_stat mnt_stats;
 
-static struct rpc_program mnt_program = {
+static const struct rpc_program mnt_program = {
         .name           = "mount",
         .number         = NFS_MNT_PROGRAM,
         .nrvers         = ARRAY_SIZE(mnt_version),
diff --git a/fs/nfs/namespace.c b/fs/nfs/namespace.c
index 8102391bb37..1807866bb3a 100644
--- a/fs/nfs/namespace.c
+++ b/fs/nfs/namespace.c
@@ -276,7 +276,10 @@ out:
         nfs_free_fattr(fattr);
         nfs_free_fhandle(fh);
 out_nofree:
-        dprintk("<-- nfs_follow_mountpoint() = %p\n", mnt);
+        if (IS_ERR(mnt))
+                dprintk("<-- %s(): error %ld\n", __func__, PTR_ERR(mnt));
+        else
+                dprintk("<-- %s() = %p\n", __func__, mnt);
         return mnt;
 }
 
diff --git a/fs/nfs/netns.h b/fs/nfs/netns.h
new file mode 100644
index 00000000000..aa14ec303e9
--- /dev/null
+++ b/fs/nfs/netns.h
@@ -0,0 +1,27 @@
+#ifndef __NFS_NETNS_H__
+#define __NFS_NETNS_H__
+
+#include <net/net_namespace.h>
+#include <net/netns/generic.h>
+
+struct bl_dev_msg {
+        int32_t status;
+        uint32_t major, minor;
+};
+
+struct nfs_net {
+        struct cache_detail *nfs_dns_resolve;
+        struct rpc_pipe *bl_device_pipe;
+        struct bl_dev_msg bl_mount_reply;
+        wait_queue_head_t bl_wq;
+        struct list_head nfs_client_list;
+        struct list_head nfs_volume_list;
+#ifdef CONFIG_NFS_V4
+        struct idr cb_ident_idr; /* Protected by nfs_client_lock */
+#endif
+        spinlock_t nfs_client_lock;
+};
+
+extern int nfs_net_id;
+
+#endif
diff --git a/fs/nfs/nfs2xdr.c b/fs/nfs/nfs2xdr.c
index 792cb13a430..1f56000fabb 100644
--- a/fs/nfs/nfs2xdr.c
+++ b/fs/nfs/nfs2xdr.c
@@ -1150,7 +1150,7 @@ struct rpc_procinfo	nfs_procedures[] = {
         PROC(STATFS,    fhandle,        statfsres,      0),
 };
 
-struct rpc_version              nfs_version2 = {
+const struct rpc_version nfs_version2 = {
         .number                 = 2,
         .nrprocs                = ARRAY_SIZE(nfs_procedures),
         .procs                  = nfs_procedures
diff --git a/fs/nfs/nfs3acl.c b/fs/nfs/nfs3acl.c
index 7ef23979896..e4498dc351a 100644
--- a/fs/nfs/nfs3acl.c
+++ b/fs/nfs/nfs3acl.c
@@ -192,7 +192,7 @@ struct posix_acl *nfs3_proc_getacl(struct inode *inode, int type)
                 .pages = pages,
         };
         struct nfs3_getaclres res = {
-                0
+                NULL,
         };
         struct rpc_message msg = {
                 .rpc_argp       = &args,
diff --git a/fs/nfs/nfs3proc.c b/fs/nfs/nfs3proc.c
index 91943953a37..5242eae6711 100644
--- a/fs/nfs/nfs3proc.c
+++ b/fs/nfs/nfs3proc.c
@@ -428,6 +428,11 @@ nfs3_proc_unlink_setup(struct rpc_message *msg, struct inode *dir)
         msg->rpc_proc = &nfs3_procedures[NFS3PROC_REMOVE];
 }
 
+static void nfs3_proc_unlink_rpc_prepare(struct rpc_task *task, struct nfs_unlinkdata *data)
+{
+        rpc_call_start(task);
+}
+
 static int
 nfs3_proc_unlink_done(struct rpc_task *task, struct inode *dir)
 {
@@ -445,6 +450,11 @@ nfs3_proc_rename_setup(struct rpc_message *msg, struct inode *dir)
         msg->rpc_proc = &nfs3_procedures[NFS3PROC_RENAME];
 }
 
+static void nfs3_proc_rename_rpc_prepare(struct rpc_task *task, struct nfs_renamedata *data)
+{
+        rpc_call_start(task);
+}
+
 static int
 nfs3_proc_rename_done(struct rpc_task *task, struct inode *old_dir,
                       struct inode *new_dir)
@@ -814,6 +824,11 @@ static void nfs3_proc_read_setup(struct nfs_read_data *data, struct rpc_message
         msg->rpc_proc = &nfs3_procedures[NFS3PROC_READ];
 }
 
+static void nfs3_proc_read_rpc_prepare(struct rpc_task *task, struct nfs_read_data *data)
+{
+        rpc_call_start(task);
+}
+
 static int nfs3_write_done(struct rpc_task *task, struct nfs_write_data *data)
 {
         if (nfs3_async_handle_jukebox(task, data->inode))
@@ -828,6 +843,11 @@ static void nfs3_proc_write_setup(struct nfs_write_data *data, struct rpc_messag
         msg->rpc_proc = &nfs3_procedures[NFS3PROC_WRITE];
 }
 
+static void nfs3_proc_write_rpc_prepare(struct rpc_task *task, struct nfs_write_data *data)
+{
+        rpc_call_start(task);
+}
+
 static int nfs3_commit_done(struct rpc_task *task, struct nfs_write_data *data)
 {
         if (nfs3_async_handle_jukebox(task, data->inode))
@@ -864,9 +884,11 @@ const struct nfs_rpc_ops nfs_v3_clientops = {
         .create         = nfs3_proc_create,
         .remove         = nfs3_proc_remove,
         .unlink_setup   = nfs3_proc_unlink_setup,
+        .unlink_rpc_prepare = nfs3_proc_unlink_rpc_prepare,
         .unlink_done    = nfs3_proc_unlink_done,
         .rename         = nfs3_proc_rename,
         .rename_setup   = nfs3_proc_rename_setup,
+        .rename_rpc_prepare = nfs3_proc_rename_rpc_prepare,
         .rename_done    = nfs3_proc_rename_done,
         .link           = nfs3_proc_link,
         .symlink        = nfs3_proc_symlink,
@@ -879,8 +901,10 @@ const struct nfs_rpc_ops nfs_v3_clientops = {
         .pathconf       = nfs3_proc_pathconf,
         .decode_dirent  = nfs3_decode_dirent,
         .read_setup     = nfs3_proc_read_setup,
+        .read_rpc_prepare = nfs3_proc_read_rpc_prepare,
         .read_done      = nfs3_read_done,
         .write_setup    = nfs3_proc_write_setup,
+        .write_rpc_prepare = nfs3_proc_write_rpc_prepare,
         .write_done     = nfs3_write_done,
         .commit_setup   = nfs3_proc_commit_setup,
         .commit_done    = nfs3_commit_done,
diff --git a/fs/nfs/nfs3xdr.c b/fs/nfs/nfs3xdr.c
index 183c6b123d0..a77cc9a3ce5 100644
--- a/fs/nfs/nfs3xdr.c
+++ b/fs/nfs/nfs3xdr.c
@@ -2461,7 +2461,7 @@ struct rpc_procinfo	nfs3_procedures[] = {
         PROC(COMMIT,            commit,         commit,         5),
 };
 
-struct rpc_version              nfs_version3 = {
+const struct rpc_version nfs_version3 = {
         .number                 = 3,
         .nrprocs                = ARRAY_SIZE(nfs3_procedures),
         .procs                  = nfs3_procedures
@@ -2489,7 +2489,7 @@ static struct rpc_procinfo	nfs3_acl_procedures[] = {
         },
 };
 
-struct rpc_version              nfsacl_version3 = {
+const struct rpc_version nfsacl_version3 = {
         .number                 = 3,
         .nrprocs                = sizeof(nfs3_acl_procedures)/
                                   sizeof(nfs3_acl_procedures[0]),
diff --git a/fs/nfs/nfs4_fs.h b/fs/nfs/nfs4_fs.h
index 4d7d0aedc10..97ecc863dd7 100644
--- a/fs/nfs/nfs4_fs.h
+++ b/fs/nfs/nfs4_fs.h
@@ -20,7 +20,6 @@ enum nfs4_client_state {
         NFS4CLNT_RECLAIM_REBOOT,
         NFS4CLNT_RECLAIM_NOGRACE,
         NFS4CLNT_DELEGRETURN,
-        NFS4CLNT_LAYOUTRECALL,
         NFS4CLNT_SESSION_RESET,
         NFS4CLNT_RECALL_SLOT,
         NFS4CLNT_LEASE_CONFIRM,
@@ -44,7 +43,7 @@ struct nfs4_minor_version_ops {
                         struct nfs4_sequence_args *args,
                         struct nfs4_sequence_res *res,
                         int cache_reply);
-        int     (*validate_stateid)(struct nfs_delegation *,
+        bool    (*match_stateid)(const nfs4_stateid *,
                         const nfs4_stateid *);
         int     (*find_root_sec)(struct nfs_server *, struct nfs_fh *,
                         struct nfs_fsinfo *);
@@ -53,26 +52,25 @@ struct nfs4_minor_version_ops {
         const struct nfs4_state_maintenance_ops *state_renewal_ops;
 };
 
-/*
- * struct rpc_sequence ensures that RPC calls are sent in the exact
- * order that they appear on the list.
- */
-struct rpc_sequence {
-        struct rpc_wait_queue   wait;   /* RPC call delay queue */
-        spinlock_t lock;                /* Protects the list */
-        struct list_head list;          /* Defines sequence of RPC calls */
+struct nfs_unique_id {
+        struct rb_node rb_node;
+        __u64 id;
 };
 
 #define NFS_SEQID_CONFIRMED 1
 struct nfs_seqid_counter {
-        struct rpc_sequence *sequence;
+        int owner_id;
         int flags;
         u32 counter;
+        spinlock_t lock;                /* Protects the list */
+        struct list_head list;          /* Defines sequence of RPC calls */
+        struct rpc_wait_queue   wait;   /* RPC call delay queue */
 };
 
 struct nfs_seqid {
         struct nfs_seqid_counter *sequence;
         struct list_head list;
+        struct rpc_task *task;
 };
 
 static inline void nfs_confirm_seqid(struct nfs_seqid_counter *seqid, int status)
@@ -81,18 +79,12 @@ static inline void nfs_confirm_seqid(struct nfs_seqid_counter *seqid, int status
                 seqid->flags |= NFS_SEQID_CONFIRMED;
 }
 
-struct nfs_unique_id {
-        struct rb_node rb_node;
-        __u64 id;
-};
-
 /*
  * NFS4 state_owners and lock_owners are simply labels for ordered
  * sequences of RPC calls. Their sole purpose is to provide once-only
  * semantics by allowing the server to identify replayed requests.
  */
 struct nfs4_state_owner {
-        struct nfs_unique_id so_owner_id;
         struct nfs_server    *so_server;
         struct list_head     so_lru;
         unsigned long        so_expires;
@@ -105,7 +97,6 @@ struct nfs4_state_owner {
         unsigned long        so_flags;
         struct list_head     so_states;
         struct nfs_seqid_counter so_seqid;
-        struct rpc_sequence  so_sequence;
 };
 
 enum {
@@ -146,8 +137,6 @@ struct nfs4_lock_state {
 #define NFS_LOCK_INITIALIZED 1
         int                     ls_flags;
         struct nfs_seqid_counter        ls_seqid;
-        struct rpc_sequence     ls_sequence;
-        struct nfs_unique_id    ls_id;
         nfs4_stateid            ls_stateid;
         atomic_t                ls_count;
         struct nfs4_lock_owner  ls_owner;
@@ -193,6 +182,7 @@ struct nfs4_exception {
         long timeout;
         int retry;
         struct nfs4_state *state;
+        struct inode *inode;
 };
 
 struct nfs4_state_recovery_ops {
@@ -224,7 +214,7 @@ extern int nfs4_do_close(struct nfs4_state *state, gfp_t gfp_mask, int wait, boo
 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 int nfs4_release_lockowner(struct nfs4_lock_state *);
 extern const struct xattr_handler *nfs4_xattr_handlers[];
 
 #if defined(CONFIG_NFS_V4_1)
@@ -233,12 +223,13 @@ static inline struct nfs4_session *nfs4_get_session(const struct nfs_server *ser
         return server->nfs_client->cl_session;
 }
 
+extern bool nfs4_set_task_privileged(struct rpc_task *task, void *dummy);
 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);
+                struct rpc_task *task);
 extern int nfs41_setup_sequence(struct nfs4_session *session,
                 struct nfs4_sequence_args *args, struct nfs4_sequence_res *res,
-                int cache_reply, struct rpc_task *task);
+                struct 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 *);
@@ -269,7 +260,7 @@ static inline struct nfs4_session *nfs4_get_session(const struct nfs_server *ser
 
 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)
+                struct rpc_task *task)
 {
         return 0;
 }
@@ -319,7 +310,7 @@ static inline void nfs4_schedule_session_recovery(struct nfs4_session *session)
 }
 #endif /* CONFIG_NFS_V4_1 */
 
-extern struct nfs4_state_owner * nfs4_get_state_owner(struct nfs_server *, struct rpc_cred *);
+extern struct nfs4_state_owner *nfs4_get_state_owner(struct nfs_server *, struct rpc_cred *, gfp_t);
 extern void nfs4_put_state_owner(struct nfs4_state_owner *);
 extern void nfs4_purge_state_owners(struct nfs_server *);
 extern struct nfs4_state * nfs4_get_open_state(struct inode *, struct nfs4_state_owner *);
@@ -327,6 +318,8 @@ extern void nfs4_put_open_state(struct nfs4_state *);
 extern void nfs4_close_state(struct nfs4_state *, fmode_t);
 extern void nfs4_close_sync(struct nfs4_state *, fmode_t);
 extern void nfs4_state_set_mode_locked(struct nfs4_state *, fmode_t);
+extern void nfs_inode_find_state_and_recover(struct inode *inode,
+                const nfs4_stateid *stateid);
 extern void nfs4_schedule_lease_recovery(struct nfs_client *);
 extern void nfs4_schedule_state_manager(struct nfs_client *);
 extern void nfs4_schedule_path_down_recovery(struct nfs_client *clp);
@@ -337,7 +330,8 @@ extern void nfs41_handle_server_scope(struct nfs_client *,
                                       struct server_scope **);
 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, pid_t);
+extern void nfs4_select_rw_stateid(nfs4_stateid *, struct nfs4_state *,
+                fmode_t, fl_owner_t, pid_t);
 
 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);
@@ -346,6 +340,8 @@ 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 void nfs4_free_lock_state(struct nfs_server *server, struct nfs4_lock_state *lsp);
+
 extern const nfs4_stateid zero_stateid;
 
 /* nfs4xdr.c */
@@ -357,6 +353,16 @@ struct nfs4_mount_data;
 extern struct svc_version nfs4_callback_version1;
 extern struct svc_version nfs4_callback_version4;
 
+static inline void nfs4_stateid_copy(nfs4_stateid *dst, const nfs4_stateid *src)
+{
+        memcpy(dst, src, sizeof(*dst));
+}
+
+static inline bool nfs4_stateid_match(const nfs4_stateid *dst, const nfs4_stateid *src)
+{
+        return memcmp(dst, src, sizeof(*dst)) == 0;
+}
+
 #else
 
 #define nfs4_close_state(a, b) do { } while (0)
diff --git a/fs/nfs/nfs4filelayout.c b/fs/nfs/nfs4filelayout.c
index 71ec08617e2..634c0bcb4fd 100644
--- a/fs/nfs/nfs4filelayout.c
+++ b/fs/nfs/nfs4filelayout.c
@@ -33,7 +33,10 @@
 #include <linux/nfs_page.h>
 #include <linux/module.h>
 
+#include <linux/sunrpc/metrics.h>
+
 #include "internal.h"
+#include "delegation.h"
 #include "nfs4filelayout.h"
 
 #define NFSDBG_FACILITY         NFSDBG_PNFS_LD
@@ -84,12 +87,27 @@ static int filelayout_async_handle_error(struct rpc_task *task,
                                          struct nfs_client *clp,
                                          int *reset)
 {
+        struct nfs_server *mds_server = NFS_SERVER(state->inode);
+        struct nfs_client *mds_client = mds_server->nfs_client;
+
         if (task->tk_status >= 0)
                 return 0;
-
         *reset = 0;
 
         switch (task->tk_status) {
+        /* MDS state errors */
+        case -NFS4ERR_DELEG_REVOKED:
+        case -NFS4ERR_ADMIN_REVOKED:
+        case -NFS4ERR_BAD_STATEID:
+                nfs_remove_bad_delegation(state->inode);
+        case -NFS4ERR_OPENMODE:
+                nfs4_schedule_stateid_recovery(mds_server, state);
+                goto wait_on_recovery;
+        case -NFS4ERR_EXPIRED:
+                nfs4_schedule_stateid_recovery(mds_server, state);
+                nfs4_schedule_lease_recovery(mds_client);
+                goto wait_on_recovery;
+        /* DS session errors */
         case -NFS4ERR_BADSESSION:
         case -NFS4ERR_BADSLOT:
         case -NFS4ERR_BAD_HIGH_SLOT:
@@ -115,8 +133,14 @@ static int filelayout_async_handle_error(struct rpc_task *task,
                 *reset = 1;
                 break;
         }
+out:
         task->tk_status = 0;
         return -EAGAIN;
+wait_on_recovery:
+        rpc_sleep_on(&mds_client->cl_rpcwaitq, task, NULL);
+        if (test_bit(NFS4CLNT_MANAGER_RUNNING, &mds_client->cl_state) == 0)
+                rpc_wake_up_queued_task(&mds_client->cl_rpcwaitq, task);
+        goto out;
 }
 
 /* NFS_PROTO call done callback routines */
@@ -173,7 +197,7 @@ static void filelayout_read_prepare(struct rpc_task *task, void *data)
 
         if (nfs41_setup_sequence(rdata->ds_clp->cl_session,
                                 &rdata->args.seq_args, &rdata->res.seq_res,
-                                0, task))
+                                task))
                 return;
 
         rpc_call_start(task);
@@ -189,10 +213,18 @@ static void filelayout_read_call_done(struct rpc_task *task, void *data)
         rdata->mds_ops->rpc_call_done(task, data);
 }
 
+static void filelayout_read_count_stats(struct rpc_task *task, void *data)
+{
+        struct nfs_read_data *rdata = (struct nfs_read_data *)data;
+
+        rpc_count_iostats(task, NFS_SERVER(rdata->inode)->client->cl_metrics);
+}
+
 static void filelayout_read_release(void *data)
 {
         struct nfs_read_data *rdata = (struct nfs_read_data *)data;
 
+        put_lseg(rdata->lseg);
         rdata->mds_ops->rpc_release(data);
 }
 
@@ -254,7 +286,7 @@ static void filelayout_write_prepare(struct rpc_task *task, void *data)
 
         if (nfs41_setup_sequence(wdata->ds_clp->cl_session,
                                 &wdata->args.seq_args, &wdata->res.seq_res,
-                                0, task))
+                                task))
                 return;
 
         rpc_call_start(task);
@@ -268,10 +300,18 @@ static void filelayout_write_call_done(struct rpc_task *task, void *data)
         wdata->mds_ops->rpc_call_done(task, data);
 }
 
+static void filelayout_write_count_stats(struct rpc_task *task, void *data)
+{
+        struct nfs_write_data *wdata = (struct nfs_write_data *)data;
+
+        rpc_count_iostats(task, NFS_SERVER(wdata->inode)->client->cl_metrics);
+}
+
 static void filelayout_write_release(void *data)
 {
         struct nfs_write_data *wdata = (struct nfs_write_data *)data;
 
+        put_lseg(wdata->lseg);
         wdata->mds_ops->rpc_release(data);
 }
 
@@ -282,24 +322,28 @@ static void filelayout_commit_release(void *data)
         nfs_commit_release_pages(wdata);
         if (atomic_dec_and_test(&NFS_I(wdata->inode)->commits_outstanding))
                 nfs_commit_clear_lock(NFS_I(wdata->inode));
+        put_lseg(wdata->lseg);
         nfs_commitdata_release(wdata);
 }
 
-struct rpc_call_ops filelayout_read_call_ops = {
+static const struct rpc_call_ops filelayout_read_call_ops = {
         .rpc_call_prepare = filelayout_read_prepare,
         .rpc_call_done = filelayout_read_call_done,
+        .rpc_count_stats = filelayout_read_count_stats,
         .rpc_release = filelayout_read_release,
 };
 
-struct rpc_call_ops filelayout_write_call_ops = {
+static const struct rpc_call_ops filelayout_write_call_ops = {
         .rpc_call_prepare = filelayout_write_prepare,
         .rpc_call_done = filelayout_write_call_done,
+        .rpc_count_stats = filelayout_write_count_stats,
         .rpc_release = filelayout_write_release,
 };
 
-struct rpc_call_ops filelayout_commit_call_ops = {
+static const struct rpc_call_ops filelayout_commit_call_ops = {
         .rpc_call_prepare = filelayout_write_prepare,
         .rpc_call_done = filelayout_write_call_done,
+        .rpc_count_stats = filelayout_write_count_stats,
         .rpc_release = filelayout_commit_release,
 };
 
@@ -367,7 +411,8 @@ filelayout_write_pagelist(struct nfs_write_data *data, int sync)
         idx = nfs4_fl_calc_ds_index(lseg, j);
         ds = nfs4_fl_prepare_ds(lseg, idx);
         if (!ds) {
-                printk(KERN_ERR "%s: prepare_ds failed, use MDS\n", __func__);
+                printk(KERN_ERR "NFS: %s: prepare_ds failed, use MDS\n",
+                        __func__);
                 set_bit(lo_fail_bit(IOMODE_RW), &lseg->pls_layout->plh_flags);
                 set_bit(lo_fail_bit(IOMODE_READ), &lseg->pls_layout->plh_flags);
                 return PNFS_NOT_ATTEMPTED;
@@ -575,7 +620,7 @@ filelayout_decode_layout(struct pnfs_layout_hdr *flo,
                         goto out_err_free;
                 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",
+                        printk(KERN_ERR "NFS: Too big fh %d received %d\n",
                                i, fl->fh_array[i]->size);
                         goto out_err_free;
                 }
@@ -640,14 +685,16 @@ filelayout_alloc_lseg(struct pnfs_layout_hdr *layoutid,
                 int size = (fl->stripe_type == STRIPE_SPARSE) ?
                         fl->dsaddr->ds_num : fl->dsaddr->stripe_count;
 
-                fl->commit_buckets = kcalloc(size, sizeof(struct list_head), gfp_flags);
+                fl->commit_buckets = kcalloc(size, sizeof(struct nfs4_fl_commit_bucket), gfp_flags);
                 if (!fl->commit_buckets) {
                         filelayout_free_lseg(&fl->generic_hdr);
                         return NULL;
                 }
                 fl->number_of_buckets = size;
-                for (i = 0; i < size; i++)
-                        INIT_LIST_HEAD(&fl->commit_buckets[i]);
+                for (i = 0; i < size; i++) {
+                        INIT_LIST_HEAD(&fl->commit_buckets[i].written);
+                        INIT_LIST_HEAD(&fl->commit_buckets[i].committing);
+                }
         }
         return &fl->generic_hdr;
 }
@@ -679,7 +726,7 @@ filelayout_pg_test(struct nfs_pageio_descriptor *pgio, struct nfs_page *prev,
         return (p_stripe == r_stripe);
 }
 
-void
+static void
 filelayout_pg_init_read(struct nfs_pageio_descriptor *pgio,
                         struct nfs_page *req)
 {
@@ -696,7 +743,7 @@ filelayout_pg_init_read(struct nfs_pageio_descriptor *pgio,
                 nfs_pageio_reset_read_mds(pgio);
 }
 
-void
+static void
 filelayout_pg_init_write(struct nfs_pageio_descriptor *pgio,
                          struct nfs_page *req)
 {
@@ -725,11 +772,6 @@ static const struct nfs_pageio_ops filelayout_pg_write_ops = {
         .pg_doio = pnfs_generic_pg_writepages,
 };
 
-static bool filelayout_mark_pnfs_commit(struct pnfs_layout_segment *lseg)
-{
-        return !FILELAYOUT_LSEG(lseg)->commit_through_mds;
-}
-
 static u32 select_bucket_index(struct nfs4_filelayout_segment *fl, u32 j)
 {
         if (fl->stripe_type == STRIPE_SPARSE)
@@ -738,13 +780,49 @@ static u32 select_bucket_index(struct nfs4_filelayout_segment *fl, u32 j)
                 return j;
 }
 
-struct list_head *filelayout_choose_commit_list(struct nfs_page *req)
+/* The generic layer is about to remove the req from the commit list.
+ * If this will make the bucket empty, it will need to put the lseg reference.
+ */
+static void
+filelayout_clear_request_commit(struct nfs_page *req)
+{
+        struct pnfs_layout_segment *freeme = NULL;
+        struct inode *inode = req->wb_context->dentry->d_inode;
+
+        spin_lock(&inode->i_lock);
+        if (!test_and_clear_bit(PG_COMMIT_TO_DS, &req->wb_flags))
+                goto out;
+        if (list_is_singular(&req->wb_list)) {
+                struct inode *inode = req->wb_context->dentry->d_inode;
+                struct pnfs_layout_segment *lseg;
+
+                /* From here we can find the bucket, but for the moment,
+                 * since there is only one relevant lseg...
+                 */
+                list_for_each_entry(lseg, &NFS_I(inode)->layout->plh_segs, pls_list) {
+                        if (lseg->pls_range.iomode == IOMODE_RW) {
+                                freeme = lseg;
+                                break;
+                        }
+                }
+        }
+out:
+        nfs_request_remove_commit_list(req);
+        spin_unlock(&inode->i_lock);
+        put_lseg(freeme);
+}
+
+static struct list_head *
+filelayout_choose_commit_list(struct nfs_page *req,
+                              struct pnfs_layout_segment *lseg)
 {
-        struct pnfs_layout_segment *lseg = req->wb_commit_lseg;
         struct nfs4_filelayout_segment *fl = FILELAYOUT_LSEG(lseg);
         u32 i, j;
         struct list_head *list;
 
+        if (fl->commit_through_mds)
+                return &NFS_I(req->wb_context->dentry->d_inode)->commit_list;
+
         /* Note that we are calling nfs4_fl_calc_j_index on each page
          * that ends up being committed to a data server.  An attractive
          * alternative is to add a field to nfs_write_data and nfs_page
@@ -754,14 +832,30 @@ struct list_head *filelayout_choose_commit_list(struct nfs_page *req)
         j = nfs4_fl_calc_j_index(lseg,
                                  (loff_t)req->wb_index << PAGE_CACHE_SHIFT);
         i = select_bucket_index(fl, j);
-        list = &fl->commit_buckets[i];
+        list = &fl->commit_buckets[i].written;
         if (list_empty(list)) {
-                /* Non-empty buckets hold a reference on the lseg */
+                /* Non-empty buckets hold a reference on the lseg.  That ref
+                 * is normally transferred to the COMMIT call and released
+                 * there.  It could also be released if the last req is pulled
+                 * off due to a rewrite, in which case it will be done in
+                 * filelayout_remove_commit_req
+                 */
                 get_lseg(lseg);
         }
+        set_bit(PG_COMMIT_TO_DS, &req->wb_flags);
         return list;
 }
 
+static void
+filelayout_mark_request_commit(struct nfs_page *req,
+                struct pnfs_layout_segment *lseg)
+{
+        struct list_head *list;
+
+        list = filelayout_choose_commit_list(req, lseg);
+        nfs_request_add_commit_list(req, list);
+}
+
 static u32 calc_ds_index_from_commit(struct pnfs_layout_segment *lseg, u32 i)
 {
         struct nfs4_filelayout_segment *flseg = FILELAYOUT_LSEG(lseg);
@@ -797,11 +891,12 @@ static int filelayout_initiate_commit(struct nfs_write_data *data, int how)
         idx = calc_ds_index_from_commit(lseg, data->ds_commit_index);
         ds = nfs4_fl_prepare_ds(lseg, idx);
         if (!ds) {
-                printk(KERN_ERR "%s: prepare_ds failed, use MDS\n", __func__);
+                printk(KERN_ERR "NFS: %s: prepare_ds failed, use MDS\n",
+                        __func__);
                 set_bit(lo_fail_bit(IOMODE_RW), &lseg->pls_layout->plh_flags);
                 set_bit(lo_fail_bit(IOMODE_READ), &lseg->pls_layout->plh_flags);
                 prepare_to_resend_writes(data);
-                data->mds_ops->rpc_release(data);
+                filelayout_commit_release(data);
                 return -EAGAIN;
         }
         dprintk("%s ino %lu, how %d\n", __func__, data->inode->i_ino, how);
@@ -817,24 +912,87 @@ static int filelayout_initiate_commit(struct nfs_write_data *data, int how)
 /*
  * This is only useful while we are using whole file layouts.
  */
-static struct pnfs_layout_segment *find_only_write_lseg(struct inode *inode)
+static struct pnfs_layout_segment *
+find_only_write_lseg_locked(struct inode *inode)
 {
-        struct pnfs_layout_segment *lseg, *rv = NULL;
+        struct pnfs_layout_segment *lseg;
 
-        spin_lock(&inode->i_lock);
         list_for_each_entry(lseg, &NFS_I(inode)->layout->plh_segs, pls_list)
                 if (lseg->pls_range.iomode == IOMODE_RW)
-                        rv = get_lseg(lseg);
+                        return lseg;
+        return NULL;
+}
+
+static struct pnfs_layout_segment *find_only_write_lseg(struct inode *inode)
+{
+        struct pnfs_layout_segment *rv;
+
+        spin_lock(&inode->i_lock);
+        rv = find_only_write_lseg_locked(inode);
+        if (rv)
+                get_lseg(rv);
         spin_unlock(&inode->i_lock);
         return rv;
 }
 
-static int alloc_ds_commits(struct inode *inode, struct list_head *list)
+static int
+filelayout_scan_ds_commit_list(struct nfs4_fl_commit_bucket *bucket, int max,
+                spinlock_t *lock)
+{
+        struct list_head *src = &bucket->written;
+        struct list_head *dst = &bucket->committing;
+        struct nfs_page *req, *tmp;
+        int ret = 0;
+
+        list_for_each_entry_safe(req, tmp, src, wb_list) {
+                if (!nfs_lock_request(req))
+                        continue;
+                if (cond_resched_lock(lock))
+                        list_safe_reset_next(req, tmp, wb_list);
+                nfs_request_remove_commit_list(req);
+                clear_bit(PG_COMMIT_TO_DS, &req->wb_flags);
+                nfs_list_add_request(req, dst);
+                ret++;
+                if (ret == max)
+                        break;
+        }
+        return ret;
+}
+
+/* Move reqs from written to committing lists, returning count of number moved.
+ * Note called with i_lock held.
+ */
+static int filelayout_scan_commit_lists(struct inode *inode, int max,
+                spinlock_t *lock)
+{
+        struct pnfs_layout_segment *lseg;
+        struct nfs4_filelayout_segment *fl;
+        int i, rv = 0, cnt;
+
+        lseg = find_only_write_lseg_locked(inode);
+        if (!lseg)
+                goto out_done;
+        fl = FILELAYOUT_LSEG(lseg);
+        if (fl->commit_through_mds)
+                goto out_done;
+        for (i = 0; i < fl->number_of_buckets && max != 0; i++) {
+                cnt = filelayout_scan_ds_commit_list(&fl->commit_buckets[i],
+                                max, lock);
+                max -= cnt;
+                rv += cnt;
+        }
+out_done:
+        return rv;
+}
+
+static unsigned int
+alloc_ds_commits(struct inode *inode, struct list_head *list)
 {
         struct pnfs_layout_segment *lseg;
         struct nfs4_filelayout_segment *fl;
         struct nfs_write_data *data;
         int i, j;
+        unsigned int nreq = 0;
 
         /* Won't need this when non-whole file layout segments are supported
          * instead we will use a pnfs_layout_hdr structure */
@@ -843,28 +1001,27 @@ static int alloc_ds_commits(struct inode *inode, struct list_head *list)
                 return 0;
         fl = FILELAYOUT_LSEG(lseg);
         for (i = 0; i < fl->number_of_buckets; i++) {
-                if (list_empty(&fl->commit_buckets[i]))
+                if (list_empty(&fl->commit_buckets[i].committing))
                         continue;
                 data = nfs_commitdata_alloc();
                 if (!data)
-                        goto out_bad;
+                        break;
                 data->ds_commit_index = i;
                 data->lseg = lseg;
                 list_add(&data->pages, list);
+                nreq++;
         }
-        put_lseg(lseg);
-        return 0;
 
-out_bad:
+        /* Clean up on error */
         for (j = i; j < fl->number_of_buckets; j++) {
-                if (list_empty(&fl->commit_buckets[i]))
+                if (list_empty(&fl->commit_buckets[i].committing))
                         continue;
-                nfs_retry_commit(&fl->commit_buckets[i], lseg);
+                nfs_retry_commit(&fl->commit_buckets[i].committing, lseg);
                 put_lseg(lseg);  /* associated with emptying bucket */
         }
         put_lseg(lseg);
         /* Caller will clean up entries put on list */
-        return -ENOMEM;
+        return nreq;
 }
 
 /* This follows nfs_commit_list pretty closely */
@@ -874,40 +1031,40 @@ filelayout_commit_pagelist(struct inode *inode, struct list_head *mds_pages,
 {
         struct nfs_write_data   *data, *tmp;
         LIST_HEAD(list);
+        unsigned int nreq = 0;
 
         if (!list_empty(mds_pages)) {
                 data = nfs_commitdata_alloc();
-                if (!data)
-                        goto out_bad;
-                data->lseg = NULL;
-                list_add(&data->pages, &list);
+                if (data != NULL) {
+                        data->lseg = NULL;
+                        list_add(&data->pages, &list);
+                        nreq++;
+                } else
+                        nfs_retry_commit(mds_pages, NULL);
         }
 
-        if (alloc_ds_commits(inode, &list))
-                goto out_bad;
+        nreq += alloc_ds_commits(inode, &list);
+
+        if (nreq == 0) {
+                nfs_commit_clear_lock(NFS_I(inode));
+                goto out;
+        }
+
+        atomic_add(nreq, &NFS_I(inode)->commits_outstanding);
 
         list_for_each_entry_safe(data, tmp, &list, pages) {
                 list_del_init(&data->pages);
-                atomic_inc(&NFS_I(inode)->commits_outstanding);
                 if (!data->lseg) {
                         nfs_init_commit(data, mds_pages, NULL);
                         nfs_initiate_commit(data, NFS_CLIENT(inode),
                                             data->mds_ops, how);
                 } else {
-                        nfs_init_commit(data, &FILELAYOUT_LSEG(data->lseg)->commit_buckets[data->ds_commit_index], data->lseg);
+                        nfs_init_commit(data, &FILELAYOUT_LSEG(data->lseg)->commit_buckets[data->ds_commit_index].committing, data->lseg);
                         filelayout_initiate_commit(data, how);
                 }
         }
-        return 0;
- out_bad:
-        list_for_each_entry_safe(data, tmp, &list, pages) {
-                nfs_retry_commit(&data->pages, data->lseg);
-                list_del_init(&data->pages);
-                nfs_commit_free(data);
-        }
-        nfs_retry_commit(mds_pages, NULL);
-        nfs_commit_clear_lock(NFS_I(inode));
-        return -ENOMEM;
+out:
+        return PNFS_ATTEMPTED;
 }
 
 static void
@@ -924,8 +1081,9 @@ static struct pnfs_layoutdriver_type filelayout_type = {
         .free_lseg              = filelayout_free_lseg,
         .pg_read_ops            = &filelayout_pg_read_ops,
         .pg_write_ops           = &filelayout_pg_write_ops,
-        .mark_pnfs_commit       = filelayout_mark_pnfs_commit,
-        .choose_commit_list     = filelayout_choose_commit_list,
+        .mark_request_commit    = filelayout_mark_request_commit,
+        .clear_request_commit   = filelayout_clear_request_commit,
+        .scan_commit_lists      = filelayout_scan_commit_lists,
         .commit_pagelist        = filelayout_commit_pagelist,
         .read_pagelist          = filelayout_read_pagelist,
         .write_pagelist         = filelayout_write_pagelist,
diff --git a/fs/nfs/nfs4filelayout.h b/fs/nfs/nfs4filelayout.h
index 2e42284253f..21190bb1f5e 100644
--- a/fs/nfs/nfs4filelayout.h
+++ b/fs/nfs/nfs4filelayout.h
@@ -74,6 +74,11 @@ struct nfs4_file_layout_dsaddr {
         struct nfs4_pnfs_ds             *ds_list[1];
 };
 
+struct nfs4_fl_commit_bucket {
+        struct list_head written;
+        struct list_head committing;
+};
+
 struct nfs4_filelayout_segment {
         struct pnfs_layout_segment generic_hdr;
         u32 stripe_type;
@@ -84,7 +89,7 @@ struct nfs4_filelayout_segment {
         struct nfs4_file_layout_dsaddr *dsaddr; /* Point to GETDEVINFO data */
         unsigned int num_fh;
         struct nfs_fh **fh_array;
-        struct list_head *commit_buckets; /* Sort commits to ds */
+        struct nfs4_fl_commit_bucket *commit_buckets; /* Sort commits to ds */
         int number_of_buckets;
 };
 
diff --git a/fs/nfs/nfs4filelayoutdev.c b/fs/nfs/nfs4filelayoutdev.c
index 8ae91908f5a..a866bbd2890 100644
--- a/fs/nfs/nfs4filelayoutdev.c
+++ b/fs/nfs/nfs4filelayoutdev.c
@@ -45,7 +45,7 @@
  *   - 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 DEFINE_SPINLOCK(nfs4_ds_cache_lock);
 static LIST_HEAD(nfs4_data_server_cache);
 
 /* Debug routines */
@@ -108,58 +108,40 @@ same_sockaddr(struct sockaddr *addr1, struct sockaddr *addr2)
         return false;
 }
 
-/*
- * Lookup DS by addresses.  The first matching address returns true.
- * nfs4_ds_cache_lock is held
- */
-static struct nfs4_pnfs_ds *
-_data_server_lookup_locked(struct list_head *dsaddrs)
+static bool
+_same_data_server_addrs_locked(const struct list_head *dsaddrs1,
+                               const struct list_head *dsaddrs2)
 {
-        struct nfs4_pnfs_ds *ds;
         struct nfs4_pnfs_ds_addr *da1, *da2;
 
-        list_for_each_entry(da1, dsaddrs, da_node) {
-                list_for_each_entry(ds, &nfs4_data_server_cache, ds_node) {
-                        list_for_each_entry(da2, &ds->ds_addrs, da_node) {
-                                if (same_sockaddr(
-                                        (struct sockaddr *)&da1->da_addr,
-                                        (struct sockaddr *)&da2->da_addr))
-                                        return ds;
-                        }
-                }
+        /* step through both lists, comparing as we go */
+        for (da1 = list_first_entry(dsaddrs1, typeof(*da1), da_node),
+             da2 = list_first_entry(dsaddrs2, typeof(*da2), da_node);
+             da1 != NULL && da2 != NULL;
+             da1 = list_entry(da1->da_node.next, typeof(*da1), da_node),
+             da2 = list_entry(da2->da_node.next, typeof(*da2), da_node)) {
+                if (!same_sockaddr((struct sockaddr *)&da1->da_addr,
+                                   (struct sockaddr *)&da2->da_addr))
+                        return false;
         }
-        return NULL;
+        if (da1 == NULL && da2 == NULL)
+                return true;
+
+        return false;
 }
 
 /*
- * Compare two lists of addresses.
+ * Lookup DS by addresses.  nfs4_ds_cache_lock is held
  */
-static bool
-_data_server_match_all_addrs_locked(struct list_head *dsaddrs1,
-                                    struct list_head *dsaddrs2)
+static struct nfs4_pnfs_ds *
+_data_server_lookup_locked(const struct list_head *dsaddrs)
 {
-        struct nfs4_pnfs_ds_addr *da1, *da2;
-        size_t count1 = 0,
-               count2 = 0;
-
-        list_for_each_entry(da1, dsaddrs1, da_node)
-                count1++;
-
-        list_for_each_entry(da2, dsaddrs2, da_node) {
-                bool found = false;
-                count2++;
-                list_for_each_entry(da1, dsaddrs1, da_node) {
-                        if (same_sockaddr((struct sockaddr *)&da1->da_addr,
-                                (struct sockaddr *)&da2->da_addr)) {
-                                found = true;
-                                break;
-                        }
-                }
-                if (!found)
-                        return false;
-        }
+        struct nfs4_pnfs_ds *ds;
 
-        return (count1 == count2);
+        list_for_each_entry(ds, &nfs4_data_server_cache, ds_node)
+                if (_same_data_server_addrs_locked(&ds->ds_addrs, dsaddrs))
+                        return ds;
+        return NULL;
 }
 
 /*
@@ -356,11 +338,6 @@ nfs4_pnfs_ds_add(struct list_head *dsaddrs, gfp_t gfp_flags)
                 dprintk("%s add new data server %s\n", __func__,
                         ds->ds_remotestr);
         } else {
-                if (!_data_server_match_all_addrs_locked(&tmp_ds->ds_addrs,
-                                                         dsaddrs)) {
-                        dprintk("%s:  multipath address mismatch: %s != %s",
-                                __func__, tmp_ds->ds_remotestr, remotestr);
-                }
                 kfree(remotestr);
                 kfree(ds);
                 atomic_inc(&tmp_ds->ds_count);
@@ -378,7 +355,7 @@ out:
  * Currently only supports ipv4, ipv6 and one multi-path address.
  */
 static struct nfs4_pnfs_ds_addr *
-decode_ds_addr(struct xdr_stream *streamp, gfp_t gfp_flags)
+decode_ds_addr(struct net *net, struct xdr_stream *streamp, gfp_t gfp_flags)
 {
         struct nfs4_pnfs_ds_addr *da = NULL;
         char *buf, *portstr;
@@ -457,7 +434,7 @@ decode_ds_addr(struct xdr_stream *streamp, gfp_t gfp_flags)
 
         INIT_LIST_HEAD(&da->da_node);
 
-        if (!rpc_pton(buf, portstr-buf, (struct sockaddr *)&da->da_addr,
+        if (!rpc_pton(net, buf, portstr-buf, (struct sockaddr *)&da->da_addr,
                       sizeof(da->da_addr))) {
                 dprintk("%s: error parsing address %s\n", __func__, buf);
                 goto out_free_da;
@@ -554,7 +531,7 @@ decode_device(struct inode *ino, struct pnfs_device *pdev, gfp_t gfp_flags)
         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 "
+                printk(KERN_WARNING "NFS: %s: stripe count %d greater than "
                        "supported maximum %d\n", __func__,
                         cnt, NFS4_PNFS_MAX_STRIPE_CNT);
                 goto out_err_free_scratch;
@@ -585,7 +562,7 @@ decode_device(struct inode *ino, struct pnfs_device *pdev, gfp_t gfp_flags)
         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 "
+                printk(KERN_WARNING "NFS: %s: multipath count %d greater than "
                         "supported maximum %d\n", __func__,
                         num, NFS4_PNFS_MAX_MULTI_CNT);
                 goto out_err_free_stripe_indices;
@@ -593,7 +570,7 @@ decode_device(struct inode *ino, struct pnfs_device *pdev, gfp_t gfp_flags)
 
         /* validate stripe indices are all < num */
         if (max_stripe_index >= num) {
-                printk(KERN_WARNING "%s: stripe index %u >= num ds %u\n",
+                printk(KERN_WARNING "NFS: %s: stripe index %u >= num ds %u\n",
                         __func__, max_stripe_index, num);
                 goto out_err_free_stripe_indices;
         }
@@ -625,7 +602,8 @@ decode_device(struct inode *ino, struct pnfs_device *pdev, gfp_t gfp_flags)
 
                 mp_count = be32_to_cpup(p); /* multipath count */
                 for (j = 0; j < mp_count; j++) {
-                        da = decode_ds_addr(&stream, gfp_flags);
+                        da = decode_ds_addr(NFS_SERVER(ino)->nfs_client->net,
+                                            &stream, gfp_flags);
                         if (da)
                                 list_add_tail(&da->da_node, &dsaddrs);
                 }
@@ -686,7 +664,7 @@ decode_and_add_device(struct inode *inode, struct pnfs_device *dev, gfp_t gfp_fl
 
         new = decode_device(inode, dev, gfp_flags);
         if (!new) {
-                printk(KERN_WARNING "%s: Could not decode or add device\n",
+                printk(KERN_WARNING "NFS: %s: Could not decode or add device\n",
                         __func__);
                 return NULL;
         }
@@ -835,7 +813,7 @@ nfs4_fl_prepare_ds(struct pnfs_layout_segment *lseg, u32 ds_idx)
         struct nfs4_pnfs_ds *ds = dsaddr->ds_list[ds_idx];
 
         if (ds == NULL) {
-                printk(KERN_ERR "%s: No data server for offset index %d\n",
+                printk(KERN_ERR "NFS: %s: No data server for offset index %d\n",
                         __func__, ds_idx);
                 return NULL;
         }
diff --git a/fs/nfs/nfs4namespace.c b/fs/nfs/nfs4namespace.c
index bb80c49b653..9c8eca315f4 100644
--- a/fs/nfs/nfs4namespace.c
+++ b/fs/nfs/nfs4namespace.c
@@ -94,13 +94,14 @@ static int nfs4_validate_fspath(struct dentry *dentry,
 }
 
 static size_t nfs_parse_server_name(char *string, size_t len,
-                struct sockaddr *sa, size_t salen)
+                struct sockaddr *sa, size_t salen, struct nfs_server *server)
 {
+        struct net *net = rpc_net_ns(server->client);
         ssize_t ret;
 
-        ret = rpc_pton(string, len, sa, salen);
+        ret = rpc_pton(net, string, len, sa, salen);
         if (ret == 0) {
-                ret = nfs_dns_resolve_name(string, len, sa, salen);
+                ret = nfs_dns_resolve_name(net, string, len, sa, salen);
                 if (ret < 0)
                         ret = 0;
         }
@@ -137,7 +138,8 @@ static struct vfsmount *try_location(struct nfs_clone_mount *mountdata,
                         continue;
 
                 mountdata->addrlen = nfs_parse_server_name(buf->data, buf->len,
-                                mountdata->addr, addr_bufsize);
+                                mountdata->addr, addr_bufsize,
+                                NFS_SB(mountdata->sb));
                 if (mountdata->addrlen == 0)
                         continue;
 
diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c
index caf92d05c3a..e809d2305eb 100644
--- a/fs/nfs/nfs4proc.c
+++ b/fs/nfs/nfs4proc.c
@@ -72,18 +72,21 @@
 
 #define NFS4_MAX_LOOP_ON_RECOVER (10)
 
+static unsigned short max_session_slots = NFS4_DEF_SLOT_TABLE_SIZE;
+
 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 void nfs_fixup_referral_attributes(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);
 #ifdef CONFIG_NFS_V4_1
-static int nfs41_test_stateid(struct nfs_server *, struct nfs4_state *);
-static int nfs41_free_stateid(struct nfs_server *, struct nfs4_state *);
+static int nfs41_test_stateid(struct nfs_server *, nfs4_stateid *);
+static int nfs41_free_stateid(struct nfs_server *, nfs4_stateid *);
 #endif
 /* Prevent leaks of NFSv4 errors into userland */
 static int nfs4_map_errors(int err)
@@ -259,15 +262,28 @@ static int nfs4_handle_exception(struct nfs_server *server, int errorcode, struc
 {
         struct nfs_client *clp = server->nfs_client;
         struct nfs4_state *state = exception->state;
+        struct inode *inode = exception->inode;
         int ret = errorcode;
 
         exception->retry = 0;
         switch(errorcode) {
                 case 0:
                         return 0;
+                case -NFS4ERR_OPENMODE:
+                        if (nfs_have_delegation(inode, FMODE_READ)) {
+                                nfs_inode_return_delegation(inode);
+                                exception->retry = 1;
+                                return 0;
+                        }
+                        if (state == NULL)
+                                break;
+                        nfs4_schedule_stateid_recovery(server, state);
+                        goto wait_on_recovery;
+                case -NFS4ERR_DELEG_REVOKED:
                 case -NFS4ERR_ADMIN_REVOKED:
                 case -NFS4ERR_BAD_STATEID:
-                case -NFS4ERR_OPENMODE:
+                        if (state != NULL)
+                                nfs_remove_bad_delegation(state->inode);
                         if (state == NULL)
                                 break;
                         nfs4_schedule_stateid_recovery(server, state);
@@ -360,16 +376,14 @@ static void renew_lease(const struct nfs_server *server, unsigned long timestamp
  * When updating highest_used_slotid there may be "holes" in the bitmap
  * so we need to scan down from highest_used_slotid to 0 looking for the now
  * highest slotid in use.
- * If none found, highest_used_slotid is set to -1.
+ * If none found, highest_used_slotid is set to NFS4_NO_SLOT.
  *
  * 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, u32 slotid)
 {
-        int slotid = free_slotid;
-
-        BUG_ON(slotid < 0 || slotid >= NFS4_MAX_SLOT_TABLE);
+        BUG_ON(slotid >= NFS4_MAX_SLOT_TABLE);
         /* clear used bit in bitmap */
         __clear_bit(slotid, tbl->used_slots);
 
@@ -379,10 +393,16 @@ nfs4_free_slot(struct nfs4_slot_table *tbl, u8 free_slotid)
                 if (slotid < tbl->max_slots)
                         tbl->highest_used_slotid = slotid;
                 else
-                        tbl->highest_used_slotid = -1;
+                        tbl->highest_used_slotid = NFS4_NO_SLOT;
         }
-        dprintk("%s: free_slotid %u highest_used_slotid %d\n", __func__,
-                free_slotid, tbl->highest_used_slotid);
+        dprintk("%s: slotid %u highest_used_slotid %d\n", __func__,
+                slotid, tbl->highest_used_slotid);
+}
+
+bool nfs4_set_task_privileged(struct rpc_task *task, void *dummy)
+{
+        rpc_task_set_priority(task, RPC_PRIORITY_PRIVILEGED);
+        return true;
 }
 
 /*
@@ -390,16 +410,13 @@ nfs4_free_slot(struct nfs4_slot_table *tbl, u8 free_slotid)
  */
 static void nfs4_check_drain_fc_complete(struct nfs4_session *ses)
 {
-        struct rpc_task *task;
-
         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);
+                rpc_wake_up_first(&ses->fc_slot_table.slot_tbl_waitq,
+                                nfs4_set_task_privileged, NULL);
                 return;
         }
 
-        if (ses->fc_slot_table.highest_used_slotid != -1)
+        if (ses->fc_slot_table.highest_used_slotid != NFS4_NO_SLOT)
                 return;
 
         dprintk("%s COMPLETE: Session Fore Channel Drained\n", __func__);
@@ -412,7 +429,7 @@ static void nfs4_check_drain_fc_complete(struct nfs4_session *ses)
 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)
+            ses->bc_slot_table.highest_used_slotid != NFS4_NO_SLOT)
                 return;
         dprintk("%s COMPLETE: Session Back Channel Drained\n", __func__);
         complete(&ses->bc_slot_table.complete);
@@ -507,25 +524,25 @@ static int nfs4_sequence_done(struct rpc_task *task,
  * nfs4_find_slot looks for an unset bit in the used_slots bitmap.
  * If found, we mark the slot as used, update the highest_used_slotid,
  * and respectively set up the sequence operation args.
- * The slot number is returned if found, or NFS4_MAX_SLOT_TABLE otherwise.
+ * The slot number is returned if found, or NFS4_NO_SLOT otherwise.
  *
  * Note: must be called with under the slot_tbl_lock.
  */
-static u8
+static u32
 nfs4_find_slot(struct nfs4_slot_table *tbl)
 {
-        int slotid;
-        u8 ret_id = NFS4_MAX_SLOT_TABLE;
-        BUILD_BUG_ON((u8)NFS4_MAX_SLOT_TABLE != (int)NFS4_MAX_SLOT_TABLE);
+        u32 slotid;
+        u32 ret_id = NFS4_NO_SLOT;
 
-        dprintk("--> %s used_slots=%04lx highest_used=%d max_slots=%d\n",
+        dprintk("--> %s used_slots=%04lx highest_used=%u max_slots=%u\n",
                 __func__, tbl->used_slots[0], tbl->highest_used_slotid,
                 tbl->max_slots);
         slotid = find_first_zero_bit(tbl->used_slots, tbl->max_slots);
         if (slotid >= tbl->max_slots)
                 goto out;
         __set_bit(slotid, tbl->used_slots);
-        if (slotid > tbl->highest_used_slotid)
+        if (slotid > tbl->highest_used_slotid ||
+                        tbl->highest_used_slotid == NFS4_NO_SLOT)
                 tbl->highest_used_slotid = slotid;
         ret_id = slotid;
 out:
@@ -534,15 +551,25 @@ out:
         return ret_id;
 }
 
+static void nfs41_init_sequence(struct nfs4_sequence_args *args,
+                struct nfs4_sequence_res *res, int cache_reply)
+{
+        args->sa_session = NULL;
+        args->sa_cache_this = 0;
+        if (cache_reply)
+                args->sa_cache_this = 1;
+        res->sr_session = NULL;
+        res->sr_slot = NULL;
+}
+
 int nfs41_setup_sequence(struct nfs4_session *session,
                                 struct nfs4_sequence_args *args,
                                 struct nfs4_sequence_res *res,
-                                int cache_reply,
                                 struct rpc_task *task)
 {
         struct nfs4_slot *slot;
         struct nfs4_slot_table *tbl;
-        u8 slotid;
+        u32 slotid;
 
         dprintk("--> %s\n", __func__);
         /* slot already allocated? */
@@ -570,7 +597,7 @@ int nfs41_setup_sequence(struct nfs4_session *session,
         }
 
         slotid = nfs4_find_slot(tbl);
-        if (slotid == NFS4_MAX_SLOT_TABLE) {
+        if (slotid == NFS4_NO_SLOT) {
                 rpc_sleep_on(&tbl->slot_tbl_waitq, task, NULL);
                 spin_unlock(&tbl->slot_tbl_lock);
                 dprintk("<-- %s: no free slots\n", __func__);
@@ -582,7 +609,6 @@ int nfs41_setup_sequence(struct nfs4_session *session,
         slot = tbl->slots + slotid;
         args->sa_session = session;
         args->sa_slotid = slotid;
-        args->sa_cache_this = cache_reply;
 
         dprintk("<-- %s slotid=%d seqid=%d\n", __func__, slotid, slot->seq_nr);
 
@@ -602,24 +628,19 @@ EXPORT_SYMBOL_GPL(nfs41_setup_sequence);
 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;
 
-        if (session == NULL) {
-                args->sa_session = NULL;
-                res->sr_session = NULL;
+        if (session == NULL)
                 goto out;
-        }
 
         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);
+        ret = nfs41_setup_sequence(session, args, res, task);
 out:
         dprintk("<-- %s status=%d\n", __func__, ret);
         return ret;
@@ -629,7 +650,6 @@ struct nfs41_call_sync_data {
         const struct nfs_server *seq_server;
         struct nfs4_sequence_args *seq_args;
         struct nfs4_sequence_res *seq_res;
-        int cache_reply;
 };
 
 static void nfs41_call_sync_prepare(struct rpc_task *task, void *calldata)
@@ -639,7 +659,7 @@ static void nfs41_call_sync_prepare(struct rpc_task *task, void *calldata)
         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))
+                                data->seq_res, task))
                 return;
         rpc_call_start(task);
 }
@@ -657,12 +677,12 @@ static void nfs41_call_sync_done(struct rpc_task *task, void *calldata)
         nfs41_sequence_done(task, data->seq_res);
 }
 
-struct rpc_call_ops nfs41_call_sync_ops = {
+static const struct rpc_call_ops nfs41_call_sync_ops = {
         .rpc_call_prepare = nfs41_call_sync_prepare,
         .rpc_call_done = nfs41_call_sync_done,
 };
 
-struct rpc_call_ops nfs41_call_priv_sync_ops = {
+static const struct rpc_call_ops nfs41_call_priv_sync_ops = {
         .rpc_call_prepare = nfs41_call_priv_sync_prepare,
         .rpc_call_done = nfs41_call_sync_done,
 };
@@ -672,7 +692,6 @@ static int nfs4_call_sync_sequence(struct rpc_clnt *clnt,
                                    struct rpc_message *msg,
                                    struct nfs4_sequence_args *args,
                                    struct nfs4_sequence_res *res,
-                                   int cache_reply,
                                    int privileged)
 {
         int ret;
@@ -681,7 +700,6 @@ static int nfs4_call_sync_sequence(struct rpc_clnt *clnt,
                 .seq_server = server,
                 .seq_args = args,
                 .seq_res = res,
-                .cache_reply = cache_reply,
         };
         struct rpc_task_setup task_setup = {
                 .rpc_client = clnt,
@@ -690,7 +708,6 @@ static int nfs4_call_sync_sequence(struct rpc_clnt *clnt,
                 .callback_data = &data
         };
 
-        res->sr_slot = NULL;
         if (privileged)
                 task_setup.callback_ops = &nfs41_call_priv_sync_ops;
         task = rpc_run_task(&task_setup);
@@ -710,10 +727,17 @@ int _nfs4_call_sync_session(struct rpc_clnt *clnt,
                             struct nfs4_sequence_res *res,
                             int cache_reply)
 {
-        return nfs4_call_sync_sequence(clnt, server, msg, args, res, cache_reply, 0);
+        nfs41_init_sequence(args, res, cache_reply);
+        return nfs4_call_sync_sequence(clnt, server, msg, args, res, 0);
 }
 
 #else
+static inline
+void nfs41_init_sequence(struct nfs4_sequence_args *args,
+                struct nfs4_sequence_res *res, int cache_reply)
+{
+}
+
 static int nfs4_sequence_done(struct rpc_task *task,
                                struct nfs4_sequence_res *res)
 {
@@ -728,7 +752,7 @@ int _nfs4_call_sync(struct rpc_clnt *clnt,
                     struct nfs4_sequence_res *res,
                     int cache_reply)
 {
-        args->sa_session = res->sr_session = NULL;
+        nfs41_init_sequence(args, res, cache_reply);
         return rpc_call_sync(clnt, msg, 0);
 }
 
@@ -815,20 +839,22 @@ static struct nfs4_opendata *nfs4_opendata_alloc(struct dentry *dentry,
         p->o_arg.open_flags = flags;
         p->o_arg.fmode = fmode & (FMODE_READ|FMODE_WRITE);
         p->o_arg.clientid = server->nfs_client->cl_clientid;
-        p->o_arg.id = sp->so_owner_id.id;
+        p->o_arg.id = sp->so_seqid.owner_id;
         p->o_arg.name = &dentry->d_name;
         p->o_arg.server = server;
         p->o_arg.bitmask = server->attr_bitmask;
         p->o_arg.dir_bitmask = server->cache_consistency_bitmask;
         p->o_arg.claim = NFS4_OPEN_CLAIM_NULL;
-        if (flags & O_CREAT) {
-                u32 *s;
+        if (attrs != NULL && attrs->ia_valid != 0) {
+                __be32 verf[2];
 
                 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;
+
+                verf[0] = jiffies;
+                verf[1] = current->pid;
+                memcpy(p->o_arg.u.verifier.data, verf,
+                                sizeof(p->o_arg.u.verifier.data));
         }
         p->c_arg.fh = &p->o_res.fh;
         p->c_arg.stateid = &p->o_res.stateid;
@@ -878,7 +904,7 @@ static int can_open_cached(struct nfs4_state *state, fmode_t mode, int open_mode
 {
         int ret = 0;
 
-        if (open_mode & O_EXCL)
+        if (open_mode & (O_EXCL|O_TRUNC))
                 goto out;
         switch (mode & (FMODE_READ|FMODE_WRITE)) {
                 case FMODE_READ:
@@ -927,8 +953,8 @@ static void update_open_stateflags(struct nfs4_state *state, fmode_t fmode)
 static void nfs_set_open_stateid_locked(struct nfs4_state *state, nfs4_stateid *stateid, fmode_t fmode)
 {
         if (test_bit(NFS_DELEGATED_STATE, &state->flags) == 0)
-                memcpy(state->stateid.data, stateid->data, sizeof(state->stateid.data));
-        memcpy(state->open_stateid.data, stateid->data, sizeof(state->open_stateid.data));
+                nfs4_stateid_copy(&state->stateid, stateid);
+        nfs4_stateid_copy(&state->open_stateid, stateid);
         switch (fmode) {
                 case FMODE_READ:
                         set_bit(NFS_O_RDONLY_STATE, &state->flags);
@@ -956,7 +982,7 @@ static void __update_open_stateid(struct nfs4_state *state, nfs4_stateid *open_s
          */
         write_seqlock(&state->seqlock);
         if (deleg_stateid != NULL) {
-                memcpy(state->stateid.data, deleg_stateid->data, sizeof(state->stateid.data));
+                nfs4_stateid_copy(&state->stateid, deleg_stateid);
                 set_bit(NFS_DELEGATED_STATE, &state->flags);
         }
         if (open_stateid != NULL)
@@ -987,7 +1013,7 @@ static int update_open_stateid(struct nfs4_state *state, nfs4_stateid *open_stat
 
         if (delegation == NULL)
                 delegation = &deleg_cur->stateid;
-        else if (memcmp(deleg_cur->stateid.data, delegation->data, NFS4_STATEID_SIZE) != 0)
+        else if (!nfs4_stateid_match(&deleg_cur->stateid, delegation))
                 goto no_delegation_unlock;
 
         nfs_mark_delegation_referenced(deleg_cur);
@@ -1026,7 +1052,7 @@ static struct nfs4_state *nfs4_try_open_cached(struct nfs4_opendata *opendata)
         struct nfs4_state *state = opendata->state;
         struct nfs_inode *nfsi = NFS_I(state->inode);
         struct nfs_delegation *delegation;
-        int open_mode = opendata->o_arg.open_flags & O_EXCL;
+        int open_mode = opendata->o_arg.open_flags & (O_EXCL|O_TRUNC);
         fmode_t fmode = opendata->o_arg.fmode;
         nfs4_stateid stateid;
         int ret = -EAGAIN;
@@ -1048,7 +1074,7 @@ static struct nfs4_state *nfs4_try_open_cached(struct nfs4_opendata *opendata)
                         break;
                 }
                 /* Save the delegation */
-                memcpy(stateid.data, delegation->stateid.data, sizeof(stateid.data));
+                nfs4_stateid_copy(&stateid, &delegation->stateid);
                 rcu_read_unlock();
                 ret = nfs_may_open(state->inode, state->owner->so_cred, open_mode);
                 if (ret != 0)
@@ -1090,6 +1116,7 @@ static struct nfs4_state *nfs4_opendata_to_nfs4_state(struct nfs4_opendata *data
         if (state == NULL)
                 goto err_put_inode;
         if (data->o_res.delegation_type != 0) {
+                struct nfs_client *clp = NFS_SERVER(inode)->nfs_client;
                 int delegation_flags = 0;
 
                 rcu_read_lock();
@@ -1101,7 +1128,7 @@ static struct nfs4_state *nfs4_opendata_to_nfs4_state(struct nfs4_opendata *data
                         pr_err_ratelimited("NFS: Broken NFSv4 server %s is "
                                         "returning a delegation for "
                                         "OPEN(CLAIM_DELEGATE_CUR)\n",
-                                        NFS_CLIENT(inode)->cl_server);
+                                        clp->cl_hostname);
                 } else if ((delegation_flags & 1UL<<NFS_DELEGATION_NEED_RECLAIM) == 0)
                         nfs_inode_set_delegation(state->inode,
                                         data->owner->so_cred,
@@ -1210,10 +1237,10 @@ static int nfs4_open_recover(struct nfs4_opendata *opendata, struct nfs4_state *
          * Check if we need to update the current stateid.
          */
         if (test_bit(NFS_DELEGATED_STATE, &state->flags) == 0 &&
-            memcmp(state->stateid.data, state->open_stateid.data, sizeof(state->stateid.data)) != 0) {
+            !nfs4_stateid_match(&state->stateid, &state->open_stateid)) {
                 write_seqlock(&state->seqlock);
                 if (test_bit(NFS_DELEGATED_STATE, &state->flags) == 0)
-                        memcpy(state->stateid.data, state->open_stateid.data, sizeof(state->stateid.data));
+                        nfs4_stateid_copy(&state->stateid, &state->open_stateid);
                 write_sequnlock(&state->seqlock);
         }
         return 0;
@@ -1282,8 +1309,7 @@ static int _nfs4_open_delegation_recall(struct nfs_open_context *ctx, struct nfs
         if (IS_ERR(opendata))
                 return PTR_ERR(opendata);
         opendata->o_arg.claim = NFS4_OPEN_CLAIM_DELEGATE_CUR;
-        memcpy(opendata->o_arg.u.delegation.data, stateid->data,
-                        sizeof(opendata->o_arg.u.delegation.data));
+        nfs4_stateid_copy(&opendata->o_arg.u.delegation, stateid);
         ret = nfs4_open_recover(opendata, state);
         nfs4_opendata_put(opendata);
         return ret;
@@ -1319,8 +1345,11 @@ int nfs4_open_delegation_recall(struct nfs_open_context *ctx, struct nfs4_state
                                  * The show must go on: exit, but mark the
                                  * stateid as needing recovery.
                                  */
+                        case -NFS4ERR_DELEG_REVOKED:
                         case -NFS4ERR_ADMIN_REVOKED:
                         case -NFS4ERR_BAD_STATEID:
+                                nfs_inode_find_state_and_recover(state->inode,
+                                                stateid);
                                 nfs4_schedule_stateid_recovery(server, state);
                         case -EKEYEXPIRED:
                                 /*
@@ -1345,8 +1374,7 @@ static void nfs4_open_confirm_done(struct rpc_task *task, void *calldata)
 
         data->rpc_status = task->tk_status;
         if (data->rpc_status == 0) {
-                memcpy(data->o_res.stateid.data, data->c_res.stateid.data,
-                                sizeof(data->o_res.stateid.data));
+                nfs4_stateid_copy(&data->o_res.stateid, &data->c_res.stateid);
                 nfs_confirm_seqid(&data->owner->so_seqid, 0);
                 renew_lease(data->o_res.server, data->timestamp);
                 data->rpc_done = 1;
@@ -1440,7 +1468,7 @@ static void nfs4_open_prepare(struct rpc_task *task, void *calldata)
                 rcu_read_unlock();
         }
         /* Update sequence id. */
-        data->o_arg.id = sp->so_owner_id.id;
+        data->o_arg.id = sp->so_seqid.owner_id;
         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];
@@ -1449,7 +1477,7 @@ static void nfs4_open_prepare(struct rpc_task *task, void *calldata)
         data->timestamp = jiffies;
         if (nfs4_setup_sequence(data->o_arg.server,
                                 &data->o_arg.seq_args,
-                                &data->o_res.seq_res, 1, task))
+                                &data->o_res.seq_res, task))
                 return;
         rpc_call_start(task);
         return;
@@ -1551,6 +1579,7 @@ static int nfs4_run_open_task(struct nfs4_opendata *data, int isrecover)
         };
         int status;
 
+        nfs41_init_sequence(&o_arg->seq_args, &o_res->seq_res, 1);
         kref_get(&data->kref);
         data->rpc_done = 0;
         data->rpc_status = 0;
@@ -1712,15 +1741,32 @@ static int nfs4_open_expired(struct nfs4_state_owner *sp, struct nfs4_state *sta
 }
 
 #if defined(CONFIG_NFS_V4_1)
-static int nfs41_open_expired(struct nfs4_state_owner *sp, struct nfs4_state *state)
+static int nfs41_check_expired_stateid(struct nfs4_state *state, nfs4_stateid *stateid, unsigned int flags)
 {
-        int status;
+        int status = NFS_OK;
         struct nfs_server *server = NFS_SERVER(state->inode);
 
-        status = nfs41_test_stateid(server, state);
-        if (status == NFS_OK)
-                return 0;
-        nfs41_free_stateid(server, state);
+        if (state->flags & flags) {
+                status = nfs41_test_stateid(server, stateid);
+                if (status != NFS_OK) {
+                        nfs41_free_stateid(server, stateid);
+                        state->flags &= ~flags;
+                }
+        }
+        return status;
+}
+
+static int nfs41_open_expired(struct nfs4_state_owner *sp, struct nfs4_state *state)
+{
+        int deleg_status, open_status;
+        int deleg_flags = 1 << NFS_DELEGATED_STATE;
+        int open_flags = (1 << NFS_O_RDONLY_STATE) | (1 << NFS_O_WRONLY_STATE) | (1 << NFS_O_RDWR_STATE);
+
+        deleg_status = nfs41_check_expired_stateid(state, &state->stateid, deleg_flags);
+        open_status = nfs41_check_expired_stateid(state,  &state->open_stateid, open_flags);
+
+        if ((deleg_status == NFS_OK) && (open_status == NFS_OK))
+                return NFS_OK;
         return nfs4_open_expired(sp, state);
 }
 #endif
@@ -1754,7 +1800,8 @@ static int _nfs4_do_open(struct inode *dir, struct dentry *dentry, fmode_t fmode
 
         /* Protect against reboot recovery conflicts */
         status = -ENOMEM;
-        if (!(sp = nfs4_get_state_owner(server, cred))) {
+        sp = nfs4_get_state_owner(server, cred, GFP_KERNEL);
+        if (sp == NULL) {
                 dprintk("nfs4_do_open: nfs4_get_state_owner failed!\n");
                 goto out_err;
         }
@@ -1829,7 +1876,7 @@ static struct nfs4_state *nfs4_do_open(struct inode *dir, struct dentry *dentry,
                  * the user though...
                  */
                 if (status == -NFS4ERR_BAD_SEQID) {
-                        printk(KERN_WARNING "NFS: v4 server %s "
+                        pr_warn_ratelimited("NFS: v4 server %s "
                                         " returned a bad sequence-id error!\n",
                                         NFS_SERVER(dir)->nfs_client->cl_hostname);
                         exception.retry = 1;
@@ -1882,12 +1929,14 @@ static int _nfs4_do_setattr(struct inode *inode, struct rpc_cred *cred,
 
         nfs_fattr_init(fattr);
 
-        if (nfs4_copy_delegation_stateid(&arg.stateid, inode)) {
+        if (state != NULL) {
+                nfs4_select_rw_stateid(&arg.stateid, state, FMODE_WRITE,
+                                current->files, current->tgid);
+        } else if (nfs4_copy_delegation_stateid(&arg.stateid, inode,
+                                FMODE_WRITE)) {
                 /* Use that stateid */
-        } else if (state != NULL) {
-                nfs4_copy_stateid(&arg.stateid, state, current->files, current->tgid);
         } else
-                memcpy(&arg.stateid, &zero_stateid, sizeof(arg.stateid));
+                nfs4_stateid_copy(&arg.stateid, &zero_stateid);
 
         status = nfs4_call_sync(server->client, server, &msg, &arg.seq_args, &res.seq_res, 1);
         if (status == 0 && state != NULL)
@@ -1900,7 +1949,10 @@ static int nfs4_do_setattr(struct inode *inode, struct rpc_cred *cred,
                            struct nfs4_state *state)
 {
         struct nfs_server *server = NFS_SERVER(inode);
-        struct nfs4_exception exception = { };
+        struct nfs4_exception exception = {
+                .state = state,
+                .inode = inode,
+        };
         int err;
         do {
                 err = nfs4_handle_exception(server,
@@ -1954,6 +2006,7 @@ static void nfs4_close_done(struct rpc_task *task, void *data)
         struct nfs4_state *state = calldata->state;
         struct nfs_server *server = NFS_SERVER(calldata->inode);
 
+        dprintk("%s: begin!\n", __func__);
         if (!nfs4_sequence_done(task, &calldata->res.seq_res))
                 return;
         /* hmm. we are done with the inode, and in the process of freeing
@@ -1981,6 +2034,7 @@ static void nfs4_close_done(struct rpc_task *task, void *data)
         }
         nfs_release_seqid(calldata->arg.seqid);
         nfs_refresh_inode(calldata->inode, calldata->res.fattr);
+        dprintk("%s: done, ret = %d!\n", __func__, task->tk_status);
 }
 
 static void nfs4_close_prepare(struct rpc_task *task, void *data)
@@ -1989,6 +2043,7 @@ static void nfs4_close_prepare(struct rpc_task *task, void *data)
         struct nfs4_state *state = calldata->state;
         int call_close = 0;
 
+        dprintk("%s: begin!\n", __func__);
         if (nfs_wait_on_sequence(calldata->arg.seqid, task) != 0)
                 return;
 
@@ -2013,7 +2068,7 @@ static void nfs4_close_prepare(struct rpc_task *task, void *data)
         if (!call_close) {
                 /* Note: exit _without_ calling nfs4_close_done */
                 task->tk_action = NULL;
-                return;
+                goto out;
         }
 
         if (calldata->arg.fmode == 0) {
@@ -2022,17 +2077,20 @@ static void nfs4_close_prepare(struct rpc_task *task, void *data)
                     pnfs_roc_drain(calldata->inode, &calldata->roc_barrier)) {
                         rpc_sleep_on(&NFS_SERVER(calldata->inode)->roc_rpcwaitq,
                                      task, NULL);
-                        return;
+                        goto out;
                 }
         }
 
         nfs_fattr_init(calldata->res.fattr);
         calldata->timestamp = jiffies;
         if (nfs4_setup_sequence(NFS_SERVER(calldata->inode),
-                                &calldata->arg.seq_args, &calldata->res.seq_res,
-                                1, task))
-                return;
+                                &calldata->arg.seq_args,
+                                &calldata->res.seq_res,
+                                task))
+                goto out;
         rpc_call_start(task);
+out:
+        dprintk("%s: done!\n", __func__);
 }
 
 static const struct rpc_call_ops nfs4_close_ops = {
@@ -2074,6 +2132,7 @@ int nfs4_do_close(struct nfs4_state *state, gfp_t gfp_mask, int wait, bool roc)
         calldata = kzalloc(sizeof(*calldata), gfp_mask);
         if (calldata == NULL)
                 goto out;
+        nfs41_init_sequence(&calldata->arg.seq_args, &calldata->res.seq_res, 1);
         calldata->inode = state->inode;
         calldata->state = state;
         calldata->arg.fh = NFS_FH(state->inode);
@@ -2182,6 +2241,7 @@ static int _nfs4_server_capabilities(struct nfs_server *server, struct nfs_fh *f
                 server->cache_consistency_bitmask[0] &= FATTR4_WORD0_CHANGE|FATTR4_WORD0_SIZE;
                 server->cache_consistency_bitmask[1] &= FATTR4_WORD1_TIME_METADATA|FATTR4_WORD1_TIME_MODIFY;
                 server->acl_bitmask = res.acl_bitmask;
+                server->fh_expire_type = res.fh_expire_type;
         }
 
         return status;
@@ -2303,7 +2363,6 @@ static int nfs4_proc_get_root(struct nfs_server *server, struct nfs_fh *fhandle,
         return nfs4_map_errors(status);
 }
 
-static void nfs_fixup_referral_attributes(struct nfs_fattr *fattr);
 /*
  * Get locations and (maybe) other attributes of a referral.
  * Note that we'll actually follow the referral later when
@@ -2420,6 +2479,10 @@ nfs4_proc_setattr(struct dentry *dentry, struct nfs_fattr *fattr,
                 }
         }
 
+        /* Deal with open(O_TRUNC) */
+        if (sattr->ia_valid & ATTR_OPEN)
+                sattr->ia_valid &= ~(ATTR_MTIME|ATTR_CTIME|ATTR_OPEN);
+
         status = nfs4_do_setattr(inode, cred, fattr, sattr, state);
         if (status == 0)
                 nfs_setattr_update_inode(inode, sattr);
@@ -2494,7 +2557,7 @@ static int _nfs4_proc_access(struct inode *inode, struct nfs_access_entry *entry
         struct nfs_server *server = NFS_SERVER(inode);
         struct nfs4_accessargs args = {
                 .fh = NFS_FH(inode),
-                .bitmask = server->attr_bitmask,
+                .bitmask = server->cache_consistency_bitmask,
         };
         struct nfs4_accessres res = {
                 .server = server,
@@ -2712,8 +2775,18 @@ 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];
+        nfs41_init_sequence(&args->seq_args, &res->seq_res, 1);
+}
+
+static void nfs4_proc_unlink_rpc_prepare(struct rpc_task *task, struct nfs_unlinkdata *data)
+{
+        if (nfs4_setup_sequence(NFS_SERVER(data->dir),
+                                &data->args.seq_args,
+                                &data->res.seq_res,
+                                task))
+                return;
+        rpc_call_start(task);
 }
 
 static int nfs4_proc_unlink_done(struct rpc_task *task, struct inode *dir)
@@ -2738,6 +2811,17 @@ static void nfs4_proc_rename_setup(struct rpc_message *msg, struct inode *dir)
         msg->rpc_proc = &nfs4_procedures[NFSPROC4_CLNT_RENAME];
         arg->bitmask = server->attr_bitmask;
         res->server = server;
+        nfs41_init_sequence(&arg->seq_args, &res->seq_res, 1);
+}
+
+static void nfs4_proc_rename_rpc_prepare(struct rpc_task *task, struct nfs_renamedata *data)
+{
+        if (nfs4_setup_sequence(NFS_SERVER(data->old_dir),
+                                &data->args.seq_args,
+                                &data->res.seq_res,
+                                task))
+                return;
+        rpc_call_start(task);
 }
 
 static int nfs4_proc_rename_done(struct rpc_task *task, struct inode *old_dir,
@@ -3232,6 +3316,17 @@ static void nfs4_proc_read_setup(struct nfs_read_data *data, struct rpc_message
         data->timestamp   = jiffies;
         data->read_done_cb = nfs4_read_done_cb;
         msg->rpc_proc = &nfs4_procedures[NFSPROC4_CLNT_READ];
+        nfs41_init_sequence(&data->args.seq_args, &data->res.seq_res, 0);
+}
+
+static void nfs4_proc_read_rpc_prepare(struct rpc_task *task, struct nfs_read_data *data)
+{
+        if (nfs4_setup_sequence(NFS_SERVER(data->inode),
+                                &data->args.seq_args,
+                                &data->res.seq_res,
+                                task))
+                return;
+        rpc_call_start(task);
 }
 
 /* Reset the the nfs_read_data to send the read to the MDS. */
@@ -3305,6 +3400,17 @@ static void nfs4_proc_write_setup(struct nfs_write_data *data, struct rpc_messag
         data->timestamp   = jiffies;
 
         msg->rpc_proc = &nfs4_procedures[NFSPROC4_CLNT_WRITE];
+        nfs41_init_sequence(&data->args.seq_args, &data->res.seq_res, 1);
+}
+
+static void nfs4_proc_write_rpc_prepare(struct rpc_task *task, struct nfs_write_data *data)
+{
+        if (nfs4_setup_sequence(NFS_SERVER(data->inode),
+                                &data->args.seq_args,
+                                &data->res.seq_res,
+                                task))
+                return;
+        rpc_call_start(task);
 }
 
 static int nfs4_commit_done_cb(struct rpc_task *task, struct nfs_write_data *data)
@@ -3339,6 +3445,7 @@ static void nfs4_proc_commit_setup(struct nfs_write_data *data, struct rpc_messa
                 data->write_done_cb = nfs4_commit_done_cb;
         data->res.server = server;
         msg->rpc_proc = &nfs4_procedures[NFSPROC4_CLNT_COMMIT];
+        nfs41_init_sequence(&data->args.seq_args, &data->res.seq_res, 1);
 }
 
 struct nfs4_renewdata {
@@ -3714,8 +3821,11 @@ nfs4_async_handle_error(struct rpc_task *task, const struct nfs_server *server,
         if (task->tk_status >= 0)
                 return 0;
         switch(task->tk_status) {
+                case -NFS4ERR_DELEG_REVOKED:
                 case -NFS4ERR_ADMIN_REVOKED:
                 case -NFS4ERR_BAD_STATEID:
+                        if (state != NULL)
+                                nfs_remove_bad_delegation(state->inode);
                 case -NFS4ERR_OPENMODE:
                         if (state == NULL)
                                 break;
@@ -3764,6 +3874,16 @@ wait_on_recovery:
         return -EAGAIN;
 }
 
+static void nfs4_construct_boot_verifier(struct nfs_client *clp,
+                                         nfs4_verifier *bootverf)
+{
+        __be32 verf[2];
+
+        verf[0] = htonl((u32)clp->cl_boot_time.tv_sec);
+        verf[1] = htonl((u32)clp->cl_boot_time.tv_nsec);
+        memcpy(bootverf->data, verf, sizeof(bootverf->data));
+}
+
 int nfs4_proc_setclientid(struct nfs_client *clp, u32 program,
                 unsigned short port, struct rpc_cred *cred,
                 struct nfs4_setclientid_res *res)
@@ -3780,15 +3900,13 @@ int nfs4_proc_setclientid(struct nfs_client *clp, u32 program,
                 .rpc_resp = res,
                 .rpc_cred = cred,
         };
-        __be32 *p;
         int loop = 0;
         int status;
 
-        p = (__be32*)sc_verifier.data;
-        *p++ = htonl((u32)clp->cl_boot_time.tv_sec);
-        *p = htonl((u32)clp->cl_boot_time.tv_nsec);
+        nfs4_construct_boot_verifier(clp, &sc_verifier);
 
         for(;;) {
+                rcu_read_lock();
                 setclientid.sc_name_len = scnprintf(setclientid.sc_name,
                                 sizeof(setclientid.sc_name), "%s/%s %s %s %u",
                                 clp->cl_ipaddr,
@@ -3805,6 +3923,7 @@ int nfs4_proc_setclientid(struct nfs_client *clp, u32 program,
                 setclientid.sc_uaddr_len = scnprintf(setclientid.sc_uaddr,
                                 sizeof(setclientid.sc_uaddr), "%s.%u.%u",
                                 clp->cl_ipaddr, port >> 8, port & 255);
+                rcu_read_unlock();
 
                 status = rpc_call_sync(clp->cl_rpcclient, &msg, RPC_TASK_TIMEOUT);
                 if (status != -NFS4ERR_CLID_INUSE)
@@ -3891,7 +4010,7 @@ static void nfs4_delegreturn_prepare(struct rpc_task *task, void *data)
 
         if (nfs4_setup_sequence(d_data->res.server,
                                 &d_data->args.seq_args,
-                                &d_data->res.seq_res, 1, task))
+                                &d_data->res.seq_res, task))
                 return;
         rpc_call_start(task);
 }
@@ -3925,11 +4044,12 @@ static int _nfs4_proc_delegreturn(struct inode *inode, struct rpc_cred *cred, co
         data = kzalloc(sizeof(*data), GFP_NOFS);
         if (data == NULL)
                 return -ENOMEM;
+        nfs41_init_sequence(&data->args.seq_args, &data->res.seq_res, 1);
         data->args.fhandle = &data->fh;
         data->args.stateid = &data->stateid;
         data->args.bitmask = server->attr_bitmask;
         nfs_copy_fh(&data->fh, NFS_FH(inode));
-        memcpy(&data->stateid, stateid, sizeof(data->stateid));
+        nfs4_stateid_copy(&data->stateid, stateid);
         data->res.fattr = &data->fattr;
         data->res.server = server;
         nfs_fattr_init(data->res.fattr);
@@ -4016,7 +4136,7 @@ static int _nfs4_proc_getlk(struct nfs4_state *state, int cmd, struct file_lock
         if (status != 0)
                 goto out;
         lsp = request->fl_u.nfs4_fl.owner;
-        arg.lock_owner.id = lsp->ls_id.id;
+        arg.lock_owner.id = lsp->ls_seqid.owner_id;
         arg.lock_owner.s_dev = server->s_dev;
         status = nfs4_call_sync(server->client, server, &msg, &arg.seq_args, &res.seq_res, 1);
         switch (status) {
@@ -4112,9 +4232,8 @@ static void nfs4_locku_done(struct rpc_task *task, void *data)
                 return;
         switch (task->tk_status) {
                 case 0:
-                        memcpy(calldata->lsp->ls_stateid.data,
-                                        calldata->res.stateid.data,
-                                        sizeof(calldata->lsp->ls_stateid.data));
+                        nfs4_stateid_copy(&calldata->lsp->ls_stateid,
+                                        &calldata->res.stateid);
                         renew_lease(calldata->server, calldata->timestamp);
                         break;
                 case -NFS4ERR_BAD_STATEID:
@@ -4142,7 +4261,7 @@ static void nfs4_locku_prepare(struct rpc_task *task, void *data)
         calldata->timestamp = jiffies;
         if (nfs4_setup_sequence(calldata->server,
                                 &calldata->arg.seq_args,
-                                &calldata->res.seq_res, 1, task))
+                                &calldata->res.seq_res, task))
                 return;
         rpc_call_start(task);
 }
@@ -4182,6 +4301,7 @@ static struct rpc_task *nfs4_do_unlck(struct file_lock *fl,
                 return ERR_PTR(-ENOMEM);
         }
 
+        nfs41_init_sequence(&data->arg.seq_args, &data->res.seq_res, 1);
         msg.rpc_argp = &data->arg;
         msg.rpc_resp = &data->res;
         task_setup_data.callback_data = data;
@@ -4261,7 +4381,7 @@ static struct nfs4_lockdata *nfs4_alloc_lockdata(struct file_lock *fl,
                 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.id = lsp->ls_seqid.owner_id;
         p->arg.lock_owner.s_dev = server->s_dev;
         p->res.lock_seqid = p->arg.lock_seqid;
         p->lsp = lsp;
@@ -4297,7 +4417,7 @@ static void nfs4_lock_prepare(struct rpc_task *task, void *calldata)
         data->timestamp = jiffies;
         if (nfs4_setup_sequence(data->server,
                                 &data->arg.seq_args,
-                                &data->res.seq_res, 1, task))
+                                &data->res.seq_res, task))
                 return;
         rpc_call_start(task);
         dprintk("%s: done!, ret = %d\n", __func__, data->rpc_status);
@@ -4326,8 +4446,7 @@ static void nfs4_lock_done(struct rpc_task *task, void *calldata)
                         goto out;
         }
         if (data->rpc_status == 0) {
-                memcpy(data->lsp->ls_stateid.data, data->res.stateid.data,
-                                        sizeof(data->lsp->ls_stateid.data));
+                nfs4_stateid_copy(&data->lsp->ls_stateid, &data->res.stateid);
                 data->lsp->ls_flags |= NFS_LOCK_INITIALIZED;
                 renew_lease(NFS_SERVER(data->ctx->dentry->d_inode), data->timestamp);
         }
@@ -4415,6 +4534,7 @@ static int _nfs4_do_setlk(struct nfs4_state *state, int cmd, struct file_lock *f
                         data->arg.reclaim = NFS_LOCK_RECLAIM;
                 task_setup_data.callback_ops = &nfs4_recover_lock_ops;
         }
+        nfs41_init_sequence(&data->arg.seq_args, &data->res.seq_res, 1);
         msg.rpc_argp = &data->arg;
         msg.rpc_resp = &data->res;
         task_setup_data.callback_data = data;
@@ -4479,15 +4599,34 @@ out:
 }
 
 #if defined(CONFIG_NFS_V4_1)
-static int nfs41_lock_expired(struct nfs4_state *state, struct file_lock *request)
+static int nfs41_check_expired_locks(struct nfs4_state *state)
 {
-        int status;
+        int status, ret = NFS_OK;
+        struct nfs4_lock_state *lsp;
         struct nfs_server *server = NFS_SERVER(state->inode);
 
-        status = nfs41_test_stateid(server, state);
+        list_for_each_entry(lsp, &state->lock_states, ls_locks) {
+                if (lsp->ls_flags & NFS_LOCK_INITIALIZED) {
+                        status = nfs41_test_stateid(server, &lsp->ls_stateid);
+                        if (status != NFS_OK) {
+                                nfs41_free_stateid(server, &lsp->ls_stateid);
+                                lsp->ls_flags &= ~NFS_LOCK_INITIALIZED;
+                                ret = status;
+                        }
+                }
+        };
+
+        return ret;
+}
+
+static int nfs41_lock_expired(struct nfs4_state *state, struct file_lock *request)
+{
+        int status = NFS_OK;
+
+        if (test_bit(LK_STATE_IN_USE, &state->flags))
+                status = nfs41_check_expired_locks(state);
         if (status == NFS_OK)
-                return 0;
-        nfs41_free_stateid(server, state);
+                return status;
         return nfs4_lock_expired(state, request);
 }
 #endif
@@ -4523,7 +4662,8 @@ static int _nfs4_proc_setlk(struct nfs4_state *state, int cmd, struct file_lock
         /* Note: we always want to sleep here! */
         request->fl_flags = fl_flags | FL_SLEEP;
         if (do_vfs_lock(request->fl_file, request) < 0)
-                printk(KERN_WARNING "%s: VFS is out of sync with lock manager!\n", __func__);
+                printk(KERN_WARNING "NFS: %s: VFS is out of sync with lock "
+                        "manager!\n", __func__);
 out_unlock:
         up_read(&nfsi->rwsem);
 out:
@@ -4533,7 +4673,9 @@ out:
 
 static int nfs4_proc_setlk(struct nfs4_state *state, int cmd, struct file_lock *request)
 {
-        struct nfs4_exception exception = { };
+        struct nfs4_exception exception = {
+                .state = state,
+        };
         int err;
 
         do {
@@ -4603,8 +4745,8 @@ int nfs4_lock_delegation_recall(struct nfs4_state *state, struct file_lock *fl)
                 err = _nfs4_do_setlk(state, F_SETLK, fl, NFS_LOCK_NEW);
                 switch (err) {
                         default:
-                                printk(KERN_ERR "%s: unhandled error %d.\n",
-                                                __func__, err);
+                                printk(KERN_ERR "NFS: %s: unhandled error "
+                                        "%d.\n", __func__, err);
                         case 0:
                         case -ESTALE:
                                 goto out;
@@ -4626,6 +4768,7 @@ int nfs4_lock_delegation_recall(struct nfs4_state *state, struct file_lock *fl)
                                  * The show must go on: exit, but mark the
                                  * stateid as needing recovery.
                                  */
+                        case -NFS4ERR_DELEG_REVOKED:
                         case -NFS4ERR_ADMIN_REVOKED:
                         case -NFS4ERR_BAD_STATEID:
                         case -NFS4ERR_OPENMODE:
@@ -4655,33 +4798,44 @@ out:
         return err;
 }
 
+struct nfs_release_lockowner_data {
+        struct nfs4_lock_state *lsp;
+        struct nfs_server *server;
+        struct nfs_release_lockowner_args args;
+};
+
 static void nfs4_release_lockowner_release(void *calldata)
 {
+        struct nfs_release_lockowner_data *data = calldata;
+        nfs4_free_lock_state(data->server, data->lsp);
         kfree(calldata);
 }
 
-const struct rpc_call_ops nfs4_release_lockowner_ops = {
+static 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)
+int nfs4_release_lockowner(struct nfs4_lock_state *lsp)
 {
         struct nfs_server *server = lsp->ls_state->owner->so_server;
-        struct nfs_release_lockowner_args *args;
+        struct nfs_release_lockowner_data *data;
         struct rpc_message msg = {
                 .rpc_proc = &nfs4_procedures[NFSPROC4_CLNT_RELEASE_LOCKOWNER],
         };
 
         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);
+                return -EINVAL;
+        data = kmalloc(sizeof(*data), GFP_NOFS);
+        if (!data)
+                return -ENOMEM;
+        data->lsp = lsp;
+        data->server = server;
+        data->args.lock_owner.clientid = server->nfs_client->cl_clientid;
+        data->args.lock_owner.id = lsp->ls_seqid.owner_id;
+        data->args.lock_owner.s_dev = server->s_dev;
+        msg.rpc_argp = &data->args;
+        rpc_call_async(server->client, &msg, 0, &nfs4_release_lockowner_ops, data);
+        return 0;
 }
 
 #define XATTR_NAME_NFSV4_ACL "system.nfs4_acl"
@@ -4727,11 +4881,11 @@ static void nfs_fixup_referral_attributes(struct nfs_fattr *fattr)
         if (!(((fattr->valid & NFS_ATTR_FATTR_MOUNTED_ON_FILEID) ||
                (fattr->valid & NFS_ATTR_FATTR_FILEID)) &&
               (fattr->valid & NFS_ATTR_FATTR_FSID) &&
-              (fattr->valid & NFS_ATTR_FATTR_V4_REFERRAL)))
+              (fattr->valid & NFS_ATTR_FATTR_V4_LOCATIONS)))
                 return;
 
         fattr->valid |= NFS_ATTR_FATTR_TYPE | NFS_ATTR_FATTR_MODE |
-                NFS_ATTR_FATTR_NLINK;
+                NFS_ATTR_FATTR_NLINK | NFS_ATTR_FATTR_V4_REFERRAL;
         fattr->mode = S_IFDIR | S_IRUGO | S_IXUGO;
         fattr->nlink = 2;
 }
@@ -4798,7 +4952,8 @@ static int _nfs4_proc_secinfo(struct inode *dir, const struct qstr *name, struct
         return status;
 }
 
-int nfs4_proc_secinfo(struct inode *dir, const struct qstr *name, struct nfs4_secinfo_flavors *flavors)
+static int nfs4_proc_secinfo(struct inode *dir, const struct qstr *name,
+                struct nfs4_secinfo_flavors *flavors)
 {
         struct nfs4_exception exception = { };
         int err;
@@ -4852,6 +5007,7 @@ int nfs4_proc_exchange_id(struct nfs_client *clp, struct rpc_cred *cred)
 {
         nfs4_verifier verifier;
         struct nfs41_exchange_id_args args = {
+                .verifier = &verifier,
                 .client = clp,
                 .flags = EXCHGID4_FLAG_SUPP_MOVED_REFER,
         };
@@ -4865,15 +5021,11 @@ int nfs4_proc_exchange_id(struct nfs_client *clp, struct rpc_cred *cred)
                 .rpc_resp = &res,
                 .rpc_cred = cred,
         };
-        __be32 *p;
 
         dprintk("--> %s\n", __func__);
         BUG_ON(clp == NULL);
 
-        p = (u32 *)verifier.data;
-        *p++ = htonl((u32)clp->cl_boot_time.tv_sec);
-        *p = htonl((u32)clp->cl_boot_time.tv_nsec);
-        args.verifier = &verifier;
+        nfs4_construct_boot_verifier(clp, &verifier);
 
         args.id_len = scnprintf(args.id, sizeof(args.id),
                                 "%s/%s.%s/%u",
@@ -4888,11 +5040,24 @@ int nfs4_proc_exchange_id(struct nfs_client *clp, struct rpc_cred *cred)
                 goto out;
         }
 
+        res.impl_id = kzalloc(sizeof(struct nfs41_impl_id), GFP_KERNEL);
+        if (unlikely(!res.impl_id)) {
+                status = -ENOMEM;
+                goto out_server_scope;
+        }
+
         status = rpc_call_sync(clp->cl_rpcclient, &msg, RPC_TASK_TIMEOUT);
         if (!status)
                 status = nfs4_check_cl_exchange_flags(clp->cl_exchange_flags);
 
         if (!status) {
+                /* use the most recent implementation id */
+                kfree(clp->impl_id);
+                clp->impl_id = res.impl_id;
+        } else
+                kfree(res.impl_id);
+
+        if (!status) {
                 if (clp->server_scope &&
                     !nfs41_same_server_scope(clp->server_scope,
                                              res.server_scope)) {
@@ -4908,8 +5073,16 @@ int nfs4_proc_exchange_id(struct nfs_client *clp, struct rpc_cred *cred)
                         goto out;
                 }
         }
+
+out_server_scope:
         kfree(res.server_scope);
 out:
+        if (clp->impl_id)
+                dprintk("%s: Server Implementation ID: "
+                        "domain: %s, name: %s, date: %llu,%u\n",
+                        __func__, clp->impl_id->domain, clp->impl_id->name,
+                        clp->impl_id->date.seconds,
+                        clp->impl_id->date.nseconds);
         dprintk("<-- %s status= %d\n", __func__, status);
         return status;
 }
@@ -4933,7 +5106,7 @@ static void nfs4_get_lease_time_prepare(struct rpc_task *task,
            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->res->lr_seq_res, task);
 
         BUG_ON(ret == -EAGAIN);
         rpc_call_start(task);
@@ -4966,7 +5139,7 @@ static void nfs4_get_lease_time_done(struct rpc_task *task, void *calldata)
         dprintk("<-- %s\n", __func__);
 }
 
-struct rpc_call_ops nfs4_get_lease_time_ops = {
+static const struct rpc_call_ops nfs4_get_lease_time_ops = {
         .rpc_call_prepare = nfs4_get_lease_time_prepare,
         .rpc_call_done = nfs4_get_lease_time_done,
 };
@@ -4997,6 +5170,7 @@ int nfs4_proc_get_lease_time(struct nfs_client *clp, struct nfs_fsinfo *fsinfo)
         };
         int status;
 
+        nfs41_init_sequence(&args.la_seq_args, &res.lr_seq_res, 0);
         dprintk("--> %s\n", __func__);
         task = rpc_run_task(&task_setup);
 
@@ -5113,13 +5287,13 @@ struct nfs4_session *nfs4_alloc_session(struct nfs_client *clp)
                 return NULL;
 
         tbl = &session->fc_slot_table;
-        tbl->highest_used_slotid = -1;
+        tbl->highest_used_slotid = NFS4_NO_SLOT;
         spin_lock_init(&tbl->slot_tbl_lock);
         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;
+        tbl->highest_used_slotid = NFS4_NO_SLOT;
         spin_lock_init(&tbl->slot_tbl_lock);
         rpc_init_wait_queue(&tbl->slot_tbl_waitq, "BackChannel Slot table");
         init_completion(&tbl->complete);
@@ -5132,11 +5306,16 @@ struct nfs4_session *nfs4_alloc_session(struct nfs_client *clp)
 
 void nfs4_destroy_session(struct nfs4_session *session)
 {
+        struct rpc_xprt *xprt;
+
         nfs4_proc_destroy_session(session);
+
+        rcu_read_lock();
+        xprt = rcu_dereference(session->clp->cl_rpcclient->cl_xprt);
+        rcu_read_unlock();
         dprintk("%s Destroy backchannel for xprt %p\n",
-                __func__, session->clp->cl_rpcclient->cl_xprt);
-        xprt_destroy_backchannel(session->clp->cl_rpcclient->cl_xprt,
-                                NFS41_BC_MIN_CALLBACKS);
+                __func__, xprt);
+        xprt_destroy_backchannel(xprt, NFS41_BC_MIN_CALLBACKS);
         nfs4_destroy_slot_tables(session);
         kfree(session);
 }
@@ -5164,7 +5343,7 @@ static void nfs4_init_channel_attrs(struct nfs41_create_session_args *args)
         args->fc_attrs.max_rqst_sz = mxrqst_sz;
         args->fc_attrs.max_resp_sz = mxresp_sz;
         args->fc_attrs.max_ops = NFS4_MAX_OPS;
-        args->fc_attrs.max_reqs = session->clp->cl_rpcclient->cl_xprt->max_reqs;
+        args->fc_attrs.max_reqs = max_session_slots;
 
         dprintk("%s: Fore Channel : max_rqst_sz=%u max_resp_sz=%u "
                 "max_ops=%u max_reqs=%u\n",
@@ -5204,6 +5383,8 @@ static int nfs4_verify_fore_channel_attrs(struct nfs41_create_session_args *args
                 return -EINVAL;
         if (rcvd->max_reqs == 0)
                 return -EINVAL;
+        if (rcvd->max_reqs > NFS4_MAX_SLOT_TABLE)
+                rcvd->max_reqs = NFS4_MAX_SLOT_TABLE;
         return 0;
 }
 
@@ -5219,9 +5400,9 @@ static int nfs4_verify_back_channel_attrs(struct nfs41_create_session_args *args
         if (rcvd->max_resp_sz_cached > sent->max_resp_sz_cached)
                 return -EINVAL;
         /* These would render the backchannel useless: */
-        if (rcvd->max_ops  == 0)
+        if (rcvd->max_ops != sent->max_ops)
                 return -EINVAL;
-        if (rcvd->max_reqs == 0)
+        if (rcvd->max_reqs != sent->max_reqs)
                 return -EINVAL;
         return 0;
 }
@@ -5324,7 +5505,7 @@ int nfs4_proc_destroy_session(struct nfs4_session *session)
 
         if (status)
                 printk(KERN_WARNING
-                        "Got error %d from the server on DESTROY_SESSION. "
+                        "NFS: Got error %d from the server on DESTROY_SESSION. "
                         "Session has been destroyed regardless...\n", status);
 
         dprintk("<-- nfs4_proc_destroy_session\n");
@@ -5447,7 +5628,7 @@ static void nfs41_sequence_prepare(struct rpc_task *task, void *data)
         args = task->tk_msg.rpc_argp;
         res = task->tk_msg.rpc_resp;
 
-        if (nfs41_setup_sequence(clp->cl_session, args, res, 0, task))
+        if (nfs41_setup_sequence(clp->cl_session, args, res, task))
                 return;
         rpc_call_start(task);
 }
@@ -5479,6 +5660,7 @@ static struct rpc_task *_nfs41_proc_sequence(struct nfs_client *clp, struct rpc_
                 nfs_put_client(clp);
                 return ERR_PTR(-ENOMEM);
         }
+        nfs41_init_sequence(&calldata->args, &calldata->res, 0);
         msg.rpc_argp = &calldata->args;
         msg.rpc_resp = &calldata->res;
         calldata->clp = clp;
@@ -5540,7 +5722,7 @@ static void nfs4_reclaim_complete_prepare(struct rpc_task *task, void *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))
+                                &calldata->res.seq_res, task))
                 return;
 
         rpc_call_start(task);
@@ -5619,6 +5801,7 @@ static int nfs41_proc_reclaim_complete(struct nfs_client *clp)
         calldata->clp = clp;
         calldata->arg.one_fs = 0;
 
+        nfs41_init_sequence(&calldata->arg.seq_args, &calldata->res.seq_res, 0);
         msg.rpc_argp = &calldata->arg;
         msg.rpc_resp = &calldata->res;
         task_setup_data.callback_data = calldata;
@@ -5650,7 +5833,7 @@ nfs4_layoutget_prepare(struct rpc_task *task, void *calldata)
          * to be no way to prevent it completely.
          */
         if (nfs4_setup_sequence(server, &lgp->args.seq_args,
-                                &lgp->res.seq_res, 0, task))
+                                &lgp->res.seq_res, task))
                 return;
         if (pnfs_choose_layoutget_stateid(&lgp->args.stateid,
                                           NFS_I(lgp->args.inode)->layout,
@@ -5725,6 +5908,7 @@ int nfs4_proc_layoutget(struct nfs4_layoutget *lgp)
 
         lgp->res.layoutp = &lgp->args.layout;
         lgp->res.seq_res.sr_slot = NULL;
+        nfs41_init_sequence(&lgp->args.seq_args, &lgp->res.seq_res, 0);
         task = rpc_run_task(&task_setup_data);
         if (IS_ERR(task))
                 return PTR_ERR(task);
@@ -5745,7 +5929,7 @@ nfs4_layoutreturn_prepare(struct rpc_task *task, void *calldata)
 
         dprintk("--> %s\n", __func__);
         if (nfs41_setup_sequence(lrp->clp->cl_session, &lrp->args.seq_args,
-                                &lrp->res.seq_res, 0, task))
+                                &lrp->res.seq_res, task))
                 return;
         rpc_call_start(task);
 }
@@ -5811,6 +5995,7 @@ int nfs4_proc_layoutreturn(struct nfs4_layoutreturn *lrp)
         int status;
 
         dprintk("--> %s\n", __func__);
+        nfs41_init_sequence(&lrp->args.seq_args, &lrp->res.seq_res, 1);
         task = rpc_run_task(&task_setup_data);
         if (IS_ERR(task))
                 return PTR_ERR(task);
@@ -5911,7 +6096,7 @@ static void nfs4_layoutcommit_prepare(struct rpc_task *task, void *calldata)
         struct nfs_server *server = NFS_SERVER(data->args.inode);
 
         if (nfs4_setup_sequence(server, &data->args.seq_args,
-                                &data->res.seq_res, 1, task))
+                                &data->res.seq_res, task))
                 return;
         rpc_call_start(task);
 }
@@ -5998,6 +6183,7 @@ nfs4_proc_layoutcommit(struct nfs4_layoutcommit_data *data, bool sync)
                 data->args.lastbytewritten,
                 data->args.inode->i_ino);
 
+        nfs41_init_sequence(&data->args.seq_args, &data->res.seq_res, 1);
         task = rpc_run_task(&task_setup_data);
         if (IS_ERR(task))
                 return PTR_ERR(task);
@@ -6091,11 +6277,12 @@ out_freepage:
 out:
         return err;
 }
-static int _nfs41_test_stateid(struct nfs_server *server, struct nfs4_state *state)
+
+static int _nfs41_test_stateid(struct nfs_server *server, nfs4_stateid *stateid)
 {
         int status;
         struct nfs41_test_stateid_args args = {
-                .stateid = &state->stateid,
+                .stateid = stateid,
         };
         struct nfs41_test_stateid_res res;
         struct rpc_message msg = {
@@ -6103,28 +6290,31 @@ static int _nfs41_test_stateid(struct nfs_server *server, struct nfs4_state *sta
                 .rpc_argp = &args,
                 .rpc_resp = &res,
         };
-        args.seq_args.sa_session = res.seq_res.sr_session = NULL;
-        status = nfs4_call_sync_sequence(server->client, server, &msg, &args.seq_args, &res.seq_res, 0, 1);
+
+        nfs41_init_sequence(&args.seq_args, &res.seq_res, 0);
+        status = nfs4_call_sync_sequence(server->client, server, &msg, &args.seq_args, &res.seq_res, 1);
+
+        if (status == NFS_OK)
+                return res.status;
         return status;
 }
 
-static int nfs41_test_stateid(struct nfs_server *server, struct nfs4_state *state)
+static int nfs41_test_stateid(struct nfs_server *server, nfs4_stateid *stateid)
 {
         struct nfs4_exception exception = { };
         int err;
         do {
                 err = nfs4_handle_exception(server,
-                                _nfs41_test_stateid(server, state),
+                                _nfs41_test_stateid(server, stateid),
                                 &exception);
         } while (exception.retry);
         return err;
 }
 
-static int _nfs4_free_stateid(struct nfs_server *server, struct nfs4_state *state)
+static int _nfs4_free_stateid(struct nfs_server *server, nfs4_stateid *stateid)
 {
-        int status;
         struct nfs41_free_stateid_args args = {
-                .stateid = &state->stateid,
+                .stateid = stateid,
         };
         struct nfs41_free_stateid_res res;
         struct rpc_message msg = {
@@ -6133,25 +6323,46 @@ static int _nfs4_free_stateid(struct nfs_server *server, struct nfs4_state *stat
                 .rpc_resp = &res,
         };
 
-        args.seq_args.sa_session = res.seq_res.sr_session = NULL;
-        status = nfs4_call_sync_sequence(server->client, server, &msg, &args.seq_args, &res.seq_res, 0, 1);
-        return status;
+        nfs41_init_sequence(&args.seq_args, &res.seq_res, 0);
+        return nfs4_call_sync_sequence(server->client, server, &msg, &args.seq_args, &res.seq_res, 1);
 }
 
-static int nfs41_free_stateid(struct nfs_server *server, struct nfs4_state *state)
+static int nfs41_free_stateid(struct nfs_server *server, nfs4_stateid *stateid)
 {
         struct nfs4_exception exception = { };
         int err;
         do {
                 err = nfs4_handle_exception(server,
-                                _nfs4_free_stateid(server, state),
+                                _nfs4_free_stateid(server, stateid),
                                 &exception);
         } while (exception.retry);
         return err;
 }
+
+static bool nfs41_match_stateid(const nfs4_stateid *s1,
+                const nfs4_stateid *s2)
+{
+        if (memcmp(s1->other, s2->other, sizeof(s1->other)) != 0)
+                return false;
+
+        if (s1->seqid == s2->seqid)
+                return true;
+        if (s1->seqid == 0 || s2->seqid == 0)
+                return true;
+
+        return false;
+}
+
 #endif /* CONFIG_NFS_V4_1 */
 
-struct nfs4_state_recovery_ops nfs40_reboot_recovery_ops = {
+static bool nfs4_match_stateid(const nfs4_stateid *s1,
+                const nfs4_stateid *s2)
+{
+        return nfs4_stateid_match(s1, s2);
+}
+
+
+static const struct nfs4_state_recovery_ops nfs40_reboot_recovery_ops = {
         .owner_flag_bit = NFS_OWNER_RECLAIM_REBOOT,
         .state_flag_bit = NFS_STATE_RECLAIM_REBOOT,
         .recover_open   = nfs4_open_reclaim,
@@ -6161,7 +6372,7 @@ struct nfs4_state_recovery_ops nfs40_reboot_recovery_ops = {
 };
 
 #if defined(CONFIG_NFS_V4_1)
-struct nfs4_state_recovery_ops nfs41_reboot_recovery_ops = {
+static const struct nfs4_state_recovery_ops nfs41_reboot_recovery_ops = {
         .owner_flag_bit = NFS_OWNER_RECLAIM_REBOOT,
         .state_flag_bit = NFS_STATE_RECLAIM_REBOOT,
         .recover_open   = nfs4_open_reclaim,
@@ -6172,7 +6383,7 @@ struct nfs4_state_recovery_ops nfs41_reboot_recovery_ops = {
 };
 #endif /* CONFIG_NFS_V4_1 */
 
-struct nfs4_state_recovery_ops nfs40_nograce_recovery_ops = {
+static const struct nfs4_state_recovery_ops nfs40_nograce_recovery_ops = {
         .owner_flag_bit = NFS_OWNER_RECLAIM_NOGRACE,
         .state_flag_bit = NFS_STATE_RECLAIM_NOGRACE,
         .recover_open   = nfs4_open_expired,
@@ -6182,7 +6393,7 @@ struct nfs4_state_recovery_ops nfs40_nograce_recovery_ops = {
 };
 
 #if defined(CONFIG_NFS_V4_1)
-struct nfs4_state_recovery_ops nfs41_nograce_recovery_ops = {
+static const struct nfs4_state_recovery_ops nfs41_nograce_recovery_ops = {
         .owner_flag_bit = NFS_OWNER_RECLAIM_NOGRACE,
         .state_flag_bit = NFS_STATE_RECLAIM_NOGRACE,
         .recover_open   = nfs41_open_expired,
@@ -6192,14 +6403,14 @@ struct nfs4_state_recovery_ops nfs41_nograce_recovery_ops = {
 };
 #endif /* CONFIG_NFS_V4_1 */
 
-struct nfs4_state_maintenance_ops nfs40_state_renewal_ops = {
+static const struct nfs4_state_maintenance_ops nfs40_state_renewal_ops = {
         .sched_state_renewal = nfs4_proc_async_renew,
         .get_state_renewal_cred_locked = nfs4_get_renew_cred_locked,
         .renew_lease = nfs4_proc_renew,
 };
 
 #if defined(CONFIG_NFS_V4_1)
-struct nfs4_state_maintenance_ops nfs41_state_renewal_ops = {
+static const struct nfs4_state_maintenance_ops nfs41_state_renewal_ops = {
         .sched_state_renewal = nfs41_proc_async_sequence,
         .get_state_renewal_cred_locked = nfs4_get_machine_cred_locked,
         .renew_lease = nfs4_proc_sequence,
@@ -6209,7 +6420,7 @@ struct nfs4_state_maintenance_ops nfs41_state_renewal_ops = {
 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,
+        .match_stateid = nfs4_match_stateid,
         .find_root_sec = nfs4_find_root_sec,
         .reboot_recovery_ops = &nfs40_reboot_recovery_ops,
         .nograce_recovery_ops = &nfs40_nograce_recovery_ops,
@@ -6220,7 +6431,7 @@ static const struct nfs4_minor_version_ops nfs_v4_0_minor_ops = {
 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,
+        .match_stateid = nfs41_match_stateid,
         .find_root_sec = nfs41_find_root_sec,
         .reboot_recovery_ops = &nfs41_reboot_recovery_ops,
         .nograce_recovery_ops = &nfs41_nograce_recovery_ops,
@@ -6260,9 +6471,11 @@ const struct nfs_rpc_ops nfs_v4_clientops = {
         .create         = nfs4_proc_create,
         .remove         = nfs4_proc_remove,
         .unlink_setup   = nfs4_proc_unlink_setup,
+        .unlink_rpc_prepare = nfs4_proc_unlink_rpc_prepare,
         .unlink_done    = nfs4_proc_unlink_done,
         .rename         = nfs4_proc_rename,
         .rename_setup   = nfs4_proc_rename_setup,
+        .rename_rpc_prepare = nfs4_proc_rename_rpc_prepare,
         .rename_done    = nfs4_proc_rename_done,
         .link           = nfs4_proc_link,
         .symlink        = nfs4_proc_symlink,
@@ -6276,8 +6489,10 @@ const struct nfs_rpc_ops nfs_v4_clientops = {
         .set_capabilities = nfs4_server_capabilities,
         .decode_dirent  = nfs4_decode_dirent,
         .read_setup     = nfs4_proc_read_setup,
+        .read_rpc_prepare = nfs4_proc_read_rpc_prepare,
         .read_done      = nfs4_read_done,
         .write_setup    = nfs4_proc_write_setup,
+        .write_rpc_prepare = nfs4_proc_write_rpc_prepare,
         .write_done     = nfs4_write_done,
         .commit_setup   = nfs4_proc_commit_setup,
         .commit_done    = nfs4_commit_done,
@@ -6301,6 +6516,10 @@ const struct xattr_handler *nfs4_xattr_handlers[] = {
         NULL
 };
 
+module_param(max_session_slots, ushort, 0644);
+MODULE_PARM_DESC(max_session_slots, "Maximum number of outstanding NFSv4.1 "
+                "requests the client will negotiate");
+
 /*
  * Local variables:
  *  c-basic-offset: 8
diff --git a/fs/nfs/nfs4state.c b/fs/nfs/nfs4state.c
index 45392032e7b..0f43414eb25 100644
--- a/fs/nfs/nfs4state.c
+++ b/fs/nfs/nfs4state.c
@@ -146,6 +146,11 @@ struct rpc_cred *nfs4_get_renew_cred_locked(struct nfs_client *clp)
         struct rpc_cred *cred = NULL;
         struct nfs_server *server;
 
+        /* Use machine credentials if available */
+        cred = nfs4_get_machine_cred_locked(clp);
+        if (cred != NULL)
+                goto out;
+
         rcu_read_lock();
         list_for_each_entry_rcu(server, &clp->cl_superblocks, client_link) {
                 cred = nfs4_get_renew_cred_server_locked(server);
@@ -153,6 +158,8 @@ struct rpc_cred *nfs4_get_renew_cred_locked(struct nfs_client *clp)
                         break;
         }
         rcu_read_unlock();
+
+out:
         return cred;
 }
 
@@ -190,30 +197,29 @@ static int nfs41_setup_state_renewal(struct nfs_client *clp)
 static void nfs4_end_drain_session(struct nfs_client *clp)
 {
         struct nfs4_session *ses = clp->cl_session;
+        struct nfs4_slot_table *tbl;
         int max_slots;
 
         if (ses == NULL)
                 return;
+        tbl = &ses->fc_slot_table;
         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;
+                spin_lock(&tbl->slot_tbl_lock);
+                max_slots = tbl->max_slots;
                 while (max_slots--) {
-                        struct rpc_task *task;
-
-                        task = rpc_wake_up_next(&ses->fc_slot_table.
-                                                slot_tbl_waitq);
-                        if (!task)
+                        if (rpc_wake_up_first(&tbl->slot_tbl_waitq,
+                                                nfs4_set_task_privileged,
+                                                NULL) == NULL)
                                 break;
-                        rpc_task_set_priority(task, RPC_PRIORITY_PRIVILEGED);
                 }
-                spin_unlock(&ses->fc_slot_table.slot_tbl_lock);
+                spin_unlock(&tbl->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) {
+        if (tbl->highest_used_slotid != NFS4_NO_SLOT) {
                 INIT_COMPLETION(tbl->complete);
                 spin_unlock(&tbl->slot_tbl_lock);
                 return wait_for_completion_interruptible(&tbl->complete);
@@ -317,62 +323,6 @@ out:
         return cred;
 }
 
-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;
-        __u64 mask = ~0ULL;
-
-        if (maxbits < 64)
-                mask = (1ULL << maxbits) - 1ULL;
-
-        /* Ensure distribution is more or less flat */
-        get_random_bytes(&new->id, sizeof(new->id));
-        new->id &= mask;
-        if (new->id < minval)
-                new->id += minval;
-retry:
-        p = &root->rb_node;
-        parent = NULL;
-
-        while (*p != NULL) {
-                parent = *p;
-                pos = rb_entry(parent, struct nfs_unique_id, rb_node);
-
-                if (new->id < pos->id)
-                        p = &(*p)->rb_left;
-                else if (new->id > pos->id)
-                        p = &(*p)->rb_right;
-                else
-                        goto id_exists;
-        }
-        rb_link_node(&new->rb_node, parent, p);
-        rb_insert_color(&new->rb_node, root);
-        return;
-id_exists:
-        for (;;) {
-                new->id++;
-                if (new->id < minval || (new->id & mask) != new->id) {
-                        new->id = minval;
-                        break;
-                }
-                parent = rb_next(parent);
-                if (parent == NULL)
-                        break;
-                pos = rb_entry(parent, struct nfs_unique_id, rb_node);
-                if (new->id < pos->id)
-                        break;
-        }
-        goto retry;
-}
-
-static void nfs_free_unique_id(struct rb_root *root, struct nfs_unique_id *id)
-{
-        rb_erase(&id->rb_node, root);
-}
-
 static struct nfs4_state_owner *
 nfs4_find_state_owner_locked(struct nfs_server *server, struct rpc_cred *cred)
 {
@@ -405,6 +355,7 @@ nfs4_insert_state_owner_locked(struct nfs4_state_owner *new)
         struct rb_node **p = &server->state_owners.rb_node,
                        *parent = NULL;
         struct nfs4_state_owner *sp;
+        int err;
 
         while (*p != NULL) {
                 parent = *p;
@@ -421,8 +372,9 @@ nfs4_insert_state_owner_locked(struct nfs4_state_owner *new)
                         return sp;
                 }
         }
-        nfs_alloc_unique_id_locked(&server->openowner_id,
-                                        &new->so_owner_id, 1, 64);
+        err = ida_get_new(&server->openowner_id, &new->so_seqid.owner_id);
+        if (err)
+                return ERR_PTR(err);
         rb_link_node(&new->so_server_node, parent, p);
         rb_insert_color(&new->so_server_node, &server->state_owners);
         return new;
@@ -435,7 +387,23 @@ nfs4_remove_state_owner_locked(struct nfs4_state_owner *sp)
 
         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);
+        ida_remove(&server->openowner_id, sp->so_seqid.owner_id);
+}
+
+static void
+nfs4_init_seqid_counter(struct nfs_seqid_counter *sc)
+{
+        sc->flags = 0;
+        sc->counter = 0;
+        spin_lock_init(&sc->lock);
+        INIT_LIST_HEAD(&sc->list);
+        rpc_init_wait_queue(&sc->wait, "Seqid_waitqueue");
+}
+
+static void
+nfs4_destroy_seqid_counter(struct nfs_seqid_counter *sc)
+{
+        rpc_destroy_wait_queue(&sc->wait);
 }
 
 /*
@@ -444,19 +412,20 @@ nfs4_remove_state_owner_locked(struct nfs4_state_owner *sp)
  *
  */
 static struct nfs4_state_owner *
-nfs4_alloc_state_owner(void)
+nfs4_alloc_state_owner(struct nfs_server *server,
+                struct rpc_cred *cred,
+                gfp_t gfp_flags)
 {
         struct nfs4_state_owner *sp;
 
-        sp = kzalloc(sizeof(*sp),GFP_NOFS);
+        sp = kzalloc(sizeof(*sp), gfp_flags);
         if (!sp)
                 return NULL;
+        sp->so_server = server;
+        sp->so_cred = get_rpccred(cred);
         spin_lock_init(&sp->so_lock);
         INIT_LIST_HEAD(&sp->so_states);
-        rpc_init_wait_queue(&sp->so_sequence.wait, "Seqid_waitqueue");
-        sp->so_seqid.sequence = &sp->so_sequence;
-        spin_lock_init(&sp->so_sequence.lock);
-        INIT_LIST_HEAD(&sp->so_sequence.list);
+        nfs4_init_seqid_counter(&sp->so_seqid);
         atomic_set(&sp->so_count, 1);
         INIT_LIST_HEAD(&sp->so_lru);
         return sp;
@@ -478,7 +447,7 @@ nfs4_drop_state_owner(struct nfs4_state_owner *sp)
 
 static void nfs4_free_state_owner(struct nfs4_state_owner *sp)
 {
-        rpc_destroy_wait_queue(&sp->so_sequence.wait);
+        nfs4_destroy_seqid_counter(&sp->so_seqid);
         put_rpccred(sp->so_cred);
         kfree(sp);
 }
@@ -516,7 +485,8 @@ static void nfs4_gc_state_owners(struct nfs_server *server)
  * 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 rpc_cred *cred,
+                                              gfp_t gfp_flags)
 {
         struct nfs_client *clp = server->nfs_client;
         struct nfs4_state_owner *sp, *new;
@@ -526,20 +496,18 @@ struct nfs4_state_owner *nfs4_get_state_owner(struct nfs_server *server,
         spin_unlock(&clp->cl_lock);
         if (sp != NULL)
                 goto out;
-        new = nfs4_alloc_state_owner();
+        new = nfs4_alloc_state_owner(server, cred, gfp_flags);
         if (new == NULL)
                 goto out;
-        new->so_server = server;
-        new->so_cred = cred;
-        spin_lock(&clp->cl_lock);
-        sp = nfs4_insert_state_owner_locked(new);
-        spin_unlock(&clp->cl_lock);
-        if (sp == new)
-                get_rpccred(cred);
-        else {
-                rpc_destroy_wait_queue(&new->so_sequence.wait);
-                kfree(new);
-        }
+        do {
+                if (ida_pre_get(&server->openowner_id, gfp_flags) == 0)
+                        break;
+                spin_lock(&clp->cl_lock);
+                sp = nfs4_insert_state_owner_locked(new);
+                spin_unlock(&clp->cl_lock);
+        } while (sp == ERR_PTR(-EAGAIN));
+        if (sp != new)
+                nfs4_free_state_owner(new);
 out:
         nfs4_gc_state_owners(server);
         return sp;
@@ -795,15 +763,11 @@ static struct nfs4_lock_state *nfs4_alloc_lock_state(struct nfs4_state *state, f
 {
         struct nfs4_lock_state *lsp;
         struct nfs_server *server = state->owner->so_server;
-        struct nfs_client *clp = server->nfs_client;
 
         lsp = kzalloc(sizeof(*lsp), GFP_NOFS);
         if (lsp == NULL)
                 return NULL;
-        rpc_init_wait_queue(&lsp->ls_sequence.wait, "lock_seqid_waitqueue");
-        spin_lock_init(&lsp->ls_sequence.lock);
-        INIT_LIST_HEAD(&lsp->ls_sequence.list);
-        lsp->ls_seqid.sequence = &lsp->ls_sequence;
+        nfs4_init_seqid_counter(&lsp->ls_seqid);
         atomic_set(&lsp->ls_count, 1);
         lsp->ls_state = state;
         lsp->ls_owner.lo_type = type;
@@ -815,25 +779,22 @@ static struct nfs4_lock_state *nfs4_alloc_lock_state(struct nfs4_state *state, f
                 lsp->ls_owner.lo_u.posix_owner = fl_owner;
                 break;
         default:
-                kfree(lsp);
-                return NULL;
+                goto out_free;
         }
-        spin_lock(&clp->cl_lock);
-        nfs_alloc_unique_id_locked(&server->lockowner_id, &lsp->ls_id, 1, 64);
-        spin_unlock(&clp->cl_lock);
+        lsp->ls_seqid.owner_id = ida_simple_get(&server->lockowner_id, 0, 0, GFP_NOFS);
+        if (lsp->ls_seqid.owner_id < 0)
+                goto out_free;
         INIT_LIST_HEAD(&lsp->ls_locks);
         return lsp;
+out_free:
+        kfree(lsp);
+        return NULL;
 }
 
-static void nfs4_free_lock_state(struct nfs4_lock_state *lsp)
+void nfs4_free_lock_state(struct nfs_server *server, struct nfs4_lock_state *lsp)
 {
-        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(&server->lockowner_id, &lsp->ls_id);
-        spin_unlock(&clp->cl_lock);
-        rpc_destroy_wait_queue(&lsp->ls_sequence.wait);
+        ida_simple_remove(&server->lockowner_id, lsp->ls_seqid.owner_id);
+        nfs4_destroy_seqid_counter(&lsp->ls_seqid);
         kfree(lsp);
 }
 
@@ -865,7 +826,7 @@ static struct nfs4_lock_state *nfs4_get_lock_state(struct nfs4_state *state, fl_
         }
         spin_unlock(&state->state_lock);
         if (new != NULL)
-                nfs4_free_lock_state(new);
+                nfs4_free_lock_state(state->owner->so_server, new);
         return lsp;
 }
 
@@ -886,9 +847,11 @@ 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);
+        if (lsp->ls_flags & NFS_LOCK_INITIALIZED) {
+                if (nfs4_release_lockowner(lsp) == 0)
+                        return;
+        }
+        nfs4_free_lock_state(lsp->ls_state->owner->so_server, lsp);
 }
 
 static void nfs4_fl_copy_lock(struct file_lock *dst, struct file_lock *src)
@@ -918,7 +881,8 @@ int nfs4_set_lock_state(struct nfs4_state *state, struct file_lock *fl)
         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);
+                lsp = nfs4_get_lock_state(state, NULL, fl->fl_pid,
+                                NFS4_FLOCK_LOCK_TYPE);
         else
                 return -EINVAL;
         if (lsp == NULL)
@@ -928,28 +892,49 @@ int nfs4_set_lock_state(struct nfs4_state *state, struct file_lock *fl)
         return 0;
 }
 
-/*
- * 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, pid_t fl_pid)
+static bool nfs4_copy_lock_stateid(nfs4_stateid *dst, struct nfs4_state *state,
+                fl_owner_t fl_owner, pid_t fl_pid)
 {
         struct nfs4_lock_state *lsp;
-        int seq;
+        bool ret = false;
 
-        do {
-                seq = read_seqbegin(&state->seqlock);
-                memcpy(dst, &state->stateid, sizeof(*dst));
-        } while (read_seqretry(&state->seqlock, seq));
         if (test_bit(LK_STATE_IN_USE, &state->flags) == 0)
-                return;
+                goto out;
 
         spin_lock(&state->state_lock);
         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));
+        if (lsp != NULL && (lsp->ls_flags & NFS_LOCK_INITIALIZED) != 0) {
+                nfs4_stateid_copy(dst, &lsp->ls_stateid);
+                ret = true;
+        }
         spin_unlock(&state->state_lock);
         nfs4_put_lock_state(lsp);
+out:
+        return ret;
+}
+
+static void nfs4_copy_open_stateid(nfs4_stateid *dst, struct nfs4_state *state)
+{
+        int seq;
+
+        do {
+                seq = read_seqbegin(&state->seqlock);
+                nfs4_stateid_copy(dst, &state->stateid);
+        } while (read_seqretry(&state->seqlock, seq));
+}
+
+/*
+ * Byte-range lock aware utility to initialize the stateid of read/write
+ * requests.
+ */
+void nfs4_select_rw_stateid(nfs4_stateid *dst, struct nfs4_state *state,
+                fmode_t fmode, fl_owner_t fl_owner, pid_t fl_pid)
+{
+        if (nfs4_copy_delegation_stateid(dst, state->inode, fmode))
+                return;
+        if (nfs4_copy_lock_stateid(dst, state, fl_owner, fl_pid))
+                return;
+        nfs4_copy_open_stateid(dst, state);
 }
 
 struct nfs_seqid *nfs_alloc_seqid(struct nfs_seqid_counter *counter, gfp_t gfp_mask)
@@ -960,20 +945,28 @@ struct nfs_seqid *nfs_alloc_seqid(struct nfs_seqid_counter *counter, gfp_t gfp_m
         if (new != NULL) {
                 new->sequence = counter;
                 INIT_LIST_HEAD(&new->list);
+                new->task = NULL;
         }
         return new;
 }
 
 void nfs_release_seqid(struct nfs_seqid *seqid)
 {
-        if (!list_empty(&seqid->list)) {
-                struct rpc_sequence *sequence = seqid->sequence->sequence;
+        struct nfs_seqid_counter *sequence;
 
-                spin_lock(&sequence->lock);
-                list_del_init(&seqid->list);
-                spin_unlock(&sequence->lock);
-                rpc_wake_up(&sequence->wait);
+        if (list_empty(&seqid->list))
+                return;
+        sequence = seqid->sequence;
+        spin_lock(&sequence->lock);
+        list_del_init(&seqid->list);
+        if (!list_empty(&sequence->list)) {
+                struct nfs_seqid *next;
+
+                next = list_first_entry(&sequence->list,
+                                struct nfs_seqid, list);
+                rpc_wake_up_queued_task(&sequence->wait, next->task);
         }
+        spin_unlock(&sequence->lock);
 }
 
 void nfs_free_seqid(struct nfs_seqid *seqid)
@@ -989,14 +982,14 @@ void nfs_free_seqid(struct nfs_seqid *seqid)
  */
 static void nfs_increment_seqid(int status, struct nfs_seqid *seqid)
 {
-        BUG_ON(list_first_entry(&seqid->sequence->sequence->list, struct nfs_seqid, list) != seqid);
+        BUG_ON(list_first_entry(&seqid->sequence->list, struct nfs_seqid, list) != seqid);
         switch (status) {
                 case 0:
                         break;
                 case -NFS4ERR_BAD_SEQID:
                         if (seqid->sequence->flags & NFS_SEQID_CONFIRMED)
                                 return;
-                        printk(KERN_WARNING "NFS: v4 server returned a bad"
+                        pr_warn_ratelimited("NFS: v4 server returned a bad"
                                         " sequence-id error on an"
                                         " unconfirmed sequence %p!\n",
                                         seqid->sequence);
@@ -1040,10 +1033,11 @@ void nfs_increment_lock_seqid(int status, struct nfs_seqid *seqid)
 
 int nfs_wait_on_sequence(struct nfs_seqid *seqid, struct rpc_task *task)
 {
-        struct rpc_sequence *sequence = seqid->sequence->sequence;
+        struct nfs_seqid_counter *sequence = seqid->sequence;
         int status = 0;
 
         spin_lock(&sequence->lock);
+        seqid->task = task;
         if (list_empty(&seqid->list))
                 list_add_tail(&seqid->list, &sequence->list);
         if (list_first_entry(&sequence->list, struct nfs_seqid, list) == seqid)
@@ -1072,19 +1066,28 @@ static void nfs4_clear_state_manager_bit(struct nfs_client *clp)
 void nfs4_schedule_state_manager(struct nfs_client *clp)
 {
         struct task_struct *task;
+        char buf[INET6_ADDRSTRLEN + sizeof("-manager") + 1];
 
         if (test_and_set_bit(NFS4CLNT_MANAGER_RUNNING, &clp->cl_state) != 0)
                 return;
         __module_get(THIS_MODULE);
         atomic_inc(&clp->cl_count);
-        task = kthread_run(nfs4_run_state_manager, clp, "%s-manager",
-                                rpc_peeraddr2str(clp->cl_rpcclient,
-                                                        RPC_DISPLAY_ADDR));
-        if (!IS_ERR(task))
-                return;
-        nfs4_clear_state_manager_bit(clp);
-        nfs_put_client(clp);
-        module_put(THIS_MODULE);
+
+        /* The rcu_read_lock() is not strictly necessary, as the state
+         * manager is the only thread that ever changes the rpc_xprt
+         * after it's initialized.  At this point, we're single threaded. */
+        rcu_read_lock();
+        snprintf(buf, sizeof(buf), "%s-manager",
+                        rpc_peeraddr2str(clp->cl_rpcclient, RPC_DISPLAY_ADDR));
+        rcu_read_unlock();
+        task = kthread_run(nfs4_run_state_manager, clp, buf);
+        if (IS_ERR(task)) {
+                printk(KERN_ERR "%s: kthread_run: %ld\n",
+                        __func__, PTR_ERR(task));
+                nfs4_clear_state_manager_bit(clp);
+                nfs_put_client(clp);
+                module_put(THIS_MODULE);
+        }
 }
 
 /*
@@ -1098,10 +1101,25 @@ void nfs4_schedule_lease_recovery(struct nfs_client *clp)
                 set_bit(NFS4CLNT_CHECK_LEASE, &clp->cl_state);
         nfs4_schedule_state_manager(clp);
 }
+EXPORT_SYMBOL_GPL(nfs4_schedule_lease_recovery);
+
+/*
+ * nfs40_handle_cb_pathdown - return all delegations after NFS4ERR_CB_PATH_DOWN
+ * @clp: client to process
+ *
+ * Set the NFS4CLNT_LEASE_EXPIRED state in order to force a
+ * resend of the SETCLIENTID and hence re-establish the
+ * callback channel. Then return all existing delegations.
+ */
+static void nfs40_handle_cb_pathdown(struct nfs_client *clp)
+{
+        set_bit(NFS4CLNT_LEASE_EXPIRED, &clp->cl_state);
+        nfs_expire_all_delegations(clp);
+}
 
 void nfs4_schedule_path_down_recovery(struct nfs_client *clp)
 {
-        nfs_handle_cb_pathdown(clp);
+        nfs40_handle_cb_pathdown(clp);
         nfs4_schedule_state_manager(clp);
 }
 
@@ -1132,11 +1150,37 @@ void nfs4_schedule_stateid_recovery(const struct nfs_server *server, struct nfs4
 {
         struct nfs_client *clp = server->nfs_client;
 
-        if (test_and_clear_bit(NFS_DELEGATED_STATE, &state->flags))
-                nfs_async_inode_return_delegation(state->inode, &state->stateid);
         nfs4_state_mark_reclaim_nograce(clp, state);
         nfs4_schedule_state_manager(clp);
 }
+EXPORT_SYMBOL_GPL(nfs4_schedule_stateid_recovery);
+
+void nfs_inode_find_state_and_recover(struct inode *inode,
+                const nfs4_stateid *stateid)
+{
+        struct nfs_client *clp = NFS_SERVER(inode)->nfs_client;
+        struct nfs_inode *nfsi = NFS_I(inode);
+        struct nfs_open_context *ctx;
+        struct nfs4_state *state;
+        bool found = false;
+
+        spin_lock(&inode->i_lock);
+        list_for_each_entry(ctx, &nfsi->open_files, list) {
+                state = ctx->state;
+                if (state == NULL)
+                        continue;
+                if (!test_bit(NFS_DELEGATED_STATE, &state->flags))
+                        continue;
+                if (!nfs4_stateid_match(&state->stateid, stateid))
+                        continue;
+                nfs4_state_mark_reclaim_nograce(clp, state);
+                found = true;
+        }
+        spin_unlock(&inode->i_lock);
+        if (found)
+                nfs4_schedule_state_manager(clp);
+}
+
 
 static int nfs4_reclaim_locks(struct nfs4_state *state, const struct nfs4_state_recovery_ops *ops)
 {
@@ -1175,8 +1219,8 @@ static int nfs4_reclaim_locks(struct nfs4_state *state, const struct nfs4_state_
                         case -NFS4ERR_CONN_NOT_BOUND_TO_SESSION:
                                 goto out;
                         default:
-                                printk(KERN_ERR "%s: unhandled error %d. Zeroing state\n",
-                                                __func__, status);
+                                printk(KERN_ERR "NFS: %s: unhandled error %d. "
+                                        "Zeroing state\n", __func__, status);
                         case -ENOMEM:
                         case -NFS4ERR_DENIED:
                         case -NFS4ERR_RECLAIM_BAD:
@@ -1222,8 +1266,9 @@ restart:
                                 spin_lock(&state->state_lock);
                                 list_for_each_entry(lock, &state->lock_states, ls_locks) {
                                         if (!(lock->ls_flags & NFS_LOCK_INITIALIZED))
-                                                printk("%s: Lock reclaim failed!\n",
-                                                        __func__);
+                                                pr_warn_ratelimited("NFS: "
+                                                        "%s: Lock reclaim "
+                                                        "failed!\n", __func__);
                                 }
                                 spin_unlock(&state->state_lock);
                                 nfs4_put_open_state(state);
@@ -1232,8 +1277,8 @@ restart:
                 }
                 switch (status) {
                         default:
-                                printk(KERN_ERR "%s: unhandled error %d. Zeroing state\n",
-                                                __func__, status);
+                                printk(KERN_ERR "NFS: %s: unhandled error %d. "
+                                        "Zeroing state\n", __func__, status);
                         case -ENOENT:
                         case -ENOMEM:
                         case -ESTALE:
@@ -1241,8 +1286,8 @@ restart:
                                  * Open state on this file cannot be recovered
                                  * All we can do is revert to using the zero stateid.
                                  */
-                                memset(state->stateid.data, 0,
-                                        sizeof(state->stateid.data));
+                                memset(&state->stateid, 0,
+                                        sizeof(state->stateid));
                                 /* Mark the file as being 'closed' */
                                 state->state = 0;
                                 break;
@@ -1420,7 +1465,7 @@ static int nfs4_recovery_handle_error(struct nfs_client *clp, int error)
                 case 0:
                         break;
                 case -NFS4ERR_CB_PATH_DOWN:
-                        nfs_handle_cb_pathdown(clp);
+                        nfs40_handle_cb_pathdown(clp);
                         break;
                 case -NFS4ERR_NO_GRACE:
                         nfs4_state_end_reclaim_reboot(clp);
@@ -1801,7 +1846,7 @@ static void nfs4_state_manager(struct nfs_client *clp)
         } while (atomic_read(&clp->cl_count) > 1);
         return;
 out_error:
-        printk(KERN_WARNING "Error: state manager failed on NFSv4 server %s"
+        pr_warn_ratelimited("NFS: state manager failed on NFSv4 server %s"
                         " with error %d\n", clp->cl_hostname, -status);
         nfs4_end_drain_session(clp);
         nfs4_clear_state_manager_bit(clp);
diff --git a/fs/nfs/nfs4xdr.c b/fs/nfs/nfs4xdr.c
index 33bd8d0f745..c74fdb114b4 100644
--- a/fs/nfs/nfs4xdr.c
+++ b/fs/nfs/nfs4xdr.c
@@ -44,6 +44,8 @@
 #include <linux/pagemap.h>
 #include <linux/proc_fs.h>
 #include <linux/kdev_t.h>
+#include <linux/module.h>
+#include <linux/utsname.h>
 #include <linux/sunrpc/clnt.h>
 #include <linux/sunrpc/msg_prot.h>
 #include <linux/sunrpc/gss_api.h>
@@ -271,7 +273,12 @@ static int nfs4_stat_to_errno(int);
                                 1 /* flags */ + \
                                 1 /* spa_how */ + \
                                 0 /* SP4_NONE (for now) */ + \
-                                1 /* zero implemetation id array */)
+                                1 /* implementation id array of size 1 */ + \
+                                1 /* nii_domain */ + \
+                                XDR_QUADLEN(NFS4_OPAQUE_LIMIT) + \
+                                1 /* nii_name */ + \
+                                XDR_QUADLEN(NFS4_OPAQUE_LIMIT) + \
+                                3 /* nii_date */)
 #define decode_exchange_id_maxsz (op_decode_hdr_maxsz + \
                                 2 /* eir_clientid */ + \
                                 1 /* eir_sequenceid */ + \
@@ -284,7 +291,11 @@ static int nfs4_stat_to_errno(int);
                                 /* eir_server_scope<> */ \
                                 XDR_QUADLEN(NFS4_OPAQUE_LIMIT) + 1 + \
                                 1 /* eir_server_impl_id array length */ + \
-                                0 /* ignored eir_server_impl_id contents */)
+                                1 /* nii_domain */ + \
+                                XDR_QUADLEN(NFS4_OPAQUE_LIMIT) + \
+                                1 /* nii_name */ + \
+                                XDR_QUADLEN(NFS4_OPAQUE_LIMIT) + \
+                                3 /* nii_date */)
 #define encode_channel_attrs_maxsz  (6 + 1 /* ca_rdma_ird.len (0) */)
 #define decode_channel_attrs_maxsz  (6 + \
                                      1 /* ca_rdma_ird.len */ + \
@@ -838,6 +849,12 @@ const u32 nfs41_maxread_overhead = ((RPC_MAX_HEADER_WITH_AUTH +
                                     XDR_UNIT);
 #endif /* CONFIG_NFS_V4_1 */
 
+static unsigned short send_implementation_id = 1;
+
+module_param(send_implementation_id, ushort, 0644);
+MODULE_PARM_DESC(send_implementation_id,
+                "Send implementation ID with NFSv4.1 exchange_id");
+
 static const umode_t nfs_type2fmt[] = {
         [NF4BAD] = 0,
         [NF4REG] = S_IFREG,
@@ -868,15 +885,44 @@ static __be32 *reserve_space(struct xdr_stream *xdr, size_t nbytes)
         return p;
 }
 
+static void encode_opaque_fixed(struct xdr_stream *xdr, const void *buf, size_t len)
+{
+        __be32 *p;
+
+        p = xdr_reserve_space(xdr, len);
+        xdr_encode_opaque_fixed(p, buf, len);
+}
+
 static void encode_string(struct xdr_stream *xdr, unsigned int len, const char *str)
 {
         __be32 *p;
 
-        p = xdr_reserve_space(xdr, 4 + len);
-        BUG_ON(p == NULL);
+        p = reserve_space(xdr, 4 + len);
         xdr_encode_opaque(p, str, len);
 }
 
+static void encode_uint32(struct xdr_stream *xdr, u32 n)
+{
+        __be32 *p;
+
+        p = reserve_space(xdr, 4);
+        *p = cpu_to_be32(n);
+}
+
+static void encode_uint64(struct xdr_stream *xdr, u64 n)
+{
+        __be32 *p;
+
+        p = reserve_space(xdr, 8);
+        xdr_encode_hyper(p, n);
+}
+
+static void encode_nfs4_seqid(struct xdr_stream *xdr,
+                const struct nfs_seqid *seqid)
+{
+        encode_uint32(xdr, seqid->sequence->counter);
+}
+
 static void encode_compound_hdr(struct xdr_stream *xdr,
                                 struct rpc_rqst *req,
                                 struct compound_hdr *hdr)
@@ -889,28 +935,37 @@ static void encode_compound_hdr(struct xdr_stream *xdr,
          * but this is not required as a MUST for the server to do so. */
         hdr->replen = RPC_REPHDRSIZE + auth->au_rslack + 3 + hdr->taglen;
 
-        dprintk("encode_compound: tag=%.*s\n", (int)hdr->taglen, hdr->tag);
         BUG_ON(hdr->taglen > NFS4_MAXTAGLEN);
-        p = reserve_space(xdr, 4 + hdr->taglen + 8);
-        p = xdr_encode_opaque(p, hdr->tag, hdr->taglen);
+        encode_string(xdr, hdr->taglen, hdr->tag);
+        p = reserve_space(xdr, 8);
         *p++ = cpu_to_be32(hdr->minorversion);
         hdr->nops_p = p;
         *p = cpu_to_be32(hdr->nops);
 }
 
+static void encode_op_hdr(struct xdr_stream *xdr, enum nfs_opnum4 op,
+                uint32_t replen,
+                struct compound_hdr *hdr)
+{
+        encode_uint32(xdr, op);
+        hdr->nops++;
+        hdr->replen += replen;
+}
+
 static void encode_nops(struct compound_hdr *hdr)
 {
         BUG_ON(hdr->nops > NFS4_MAX_OPS);
         *hdr->nops_p = htonl(hdr->nops);
 }
 
-static void encode_nfs4_verifier(struct xdr_stream *xdr, const nfs4_verifier *verf)
+static void encode_nfs4_stateid(struct xdr_stream *xdr, const nfs4_stateid *stateid)
 {
-        __be32 *p;
+        encode_opaque_fixed(xdr, stateid, NFS4_STATEID_SIZE);
+}
 
-        p = xdr_reserve_space(xdr, NFS4_VERIFIER_SIZE);
-        BUG_ON(p == NULL);
-        xdr_encode_opaque_fixed(p, verf->data, NFS4_VERIFIER_SIZE);
+static void encode_nfs4_verifier(struct xdr_stream *xdr, const nfs4_verifier *verf)
+{
+        encode_opaque_fixed(xdr, verf->data, NFS4_VERIFIER_SIZE);
 }
 
 static void encode_attrs(struct xdr_stream *xdr, const struct iattr *iap, const struct nfs_server *server)
@@ -1023,7 +1078,7 @@ static void encode_attrs(struct xdr_stream *xdr, const struct iattr *iap, const
          * Now we backfill the bitmap and the attribute buffer length.
          */
         if (len != ((char *)p - (char *)q) + 4) {
-                printk(KERN_ERR "nfs: Attr length error, %u != %Zu\n",
+                printk(KERN_ERR "NFS: Attr length error, %u != %Zu\n",
                                 len, ((char *)p - (char *)q) + 4);
                 BUG();
         }
@@ -1037,46 +1092,33 @@ static void encode_attrs(struct xdr_stream *xdr, const struct iattr *iap, const
 
 static void encode_access(struct xdr_stream *xdr, u32 access, struct compound_hdr *hdr)
 {
-        __be32 *p;
-
-        p = reserve_space(xdr, 8);
-        *p++ = cpu_to_be32(OP_ACCESS);
-        *p = cpu_to_be32(access);
-        hdr->nops++;
-        hdr->replen += decode_access_maxsz;
+        encode_op_hdr(xdr, OP_ACCESS, decode_access_maxsz, hdr);
+        encode_uint32(xdr, access);
 }
 
 static void encode_close(struct xdr_stream *xdr, const struct nfs_closeargs *arg, struct compound_hdr *hdr)
 {
-        __be32 *p;
-
-        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;
+        encode_op_hdr(xdr, OP_CLOSE, decode_close_maxsz, hdr);
+        encode_nfs4_seqid(xdr, arg->seqid);
+        encode_nfs4_stateid(xdr, arg->stateid);
 }
 
 static void encode_commit(struct xdr_stream *xdr, const struct nfs_writeargs *args, struct compound_hdr *hdr)
 {
         __be32 *p;
 
-        p = reserve_space(xdr, 16);
-        *p++ = cpu_to_be32(OP_COMMIT);
+        encode_op_hdr(xdr, OP_COMMIT, decode_commit_maxsz, hdr);
+        p = reserve_space(xdr, 12);
         p = xdr_encode_hyper(p, args->offset);
         *p = cpu_to_be32(args->count);
-        hdr->nops++;
-        hdr->replen += decode_commit_maxsz;
 }
 
 static void encode_create(struct xdr_stream *xdr, const struct nfs4_create_arg *create, struct compound_hdr *hdr)
 {
         __be32 *p;
 
-        p = reserve_space(xdr, 8);
-        *p++ = cpu_to_be32(OP_CREATE);
-        *p = cpu_to_be32(create->ftype);
+        encode_op_hdr(xdr, OP_CREATE, decode_create_maxsz, hdr);
+        encode_uint32(xdr, create->ftype);
 
         switch (create->ftype) {
         case NF4LNK:
@@ -1096,9 +1138,6 @@ static void encode_create(struct xdr_stream *xdr, const struct nfs4_create_arg *
         }
 
         encode_string(xdr, create->name->len, create->name->name);
-        hdr->nops++;
-        hdr->replen += decode_create_maxsz;
-
         encode_attrs(xdr, create->attrs, create->server);
 }
 
@@ -1106,25 +1145,21 @@ static void encode_getattr_one(struct xdr_stream *xdr, uint32_t bitmap, struct c
 {
         __be32 *p;
 
-        p = reserve_space(xdr, 12);
-        *p++ = cpu_to_be32(OP_GETATTR);
+        encode_op_hdr(xdr, OP_GETATTR, decode_getattr_maxsz, hdr);
+        p = reserve_space(xdr, 8);
         *p++ = cpu_to_be32(1);
         *p = cpu_to_be32(bitmap);
-        hdr->nops++;
-        hdr->replen += decode_getattr_maxsz;
 }
 
 static void encode_getattr_two(struct xdr_stream *xdr, uint32_t bm0, uint32_t bm1, struct compound_hdr *hdr)
 {
         __be32 *p;
 
-        p = reserve_space(xdr, 16);
-        *p++ = cpu_to_be32(OP_GETATTR);
+        encode_op_hdr(xdr, OP_GETATTR, decode_getattr_maxsz, hdr);
+        p = reserve_space(xdr, 12);
         *p++ = cpu_to_be32(2);
         *p++ = cpu_to_be32(bm0);
         *p = cpu_to_be32(bm1);
-        hdr->nops++;
-        hdr->replen += decode_getattr_maxsz;
 }
 
 static void
@@ -1134,8 +1169,7 @@ encode_getattr_three(struct xdr_stream *xdr,
 {
         __be32 *p;
 
-        p = reserve_space(xdr, 4);
-        *p = cpu_to_be32(OP_GETATTR);
+        encode_op_hdr(xdr, OP_GETATTR, decode_getattr_maxsz, hdr);
         if (bm2) {
                 p = reserve_space(xdr, 16);
                 *p++ = cpu_to_be32(3);
@@ -1152,8 +1186,6 @@ encode_getattr_three(struct xdr_stream *xdr,
                 *p++ = cpu_to_be32(1);
                 *p = cpu_to_be32(bm0);
         }
-        hdr->nops++;
-        hdr->replen += decode_getattr_maxsz;
 }
 
 static void encode_getfattr(struct xdr_stream *xdr, const u32* bitmask, struct compound_hdr *hdr)
@@ -1179,23 +1211,13 @@ static void encode_fs_locations(struct xdr_stream *xdr, const u32* bitmask, stru
 
 static void encode_getfh(struct xdr_stream *xdr, struct compound_hdr *hdr)
 {
-        __be32 *p;
-
-        p = reserve_space(xdr, 4);
-        *p = cpu_to_be32(OP_GETFH);
-        hdr->nops++;
-        hdr->replen += decode_getfh_maxsz;
+        encode_op_hdr(xdr, OP_GETFH, decode_getfh_maxsz, hdr);
 }
 
 static void encode_link(struct xdr_stream *xdr, const struct qstr *name, struct compound_hdr *hdr)
 {
-        __be32 *p;
-
-        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;
+        encode_op_hdr(xdr, OP_LINK, decode_link_maxsz, hdr);
+        encode_string(xdr, name->len, name->name);
 }
 
 static inline int nfs4_lock_type(struct file_lock *fl, int block)
@@ -1232,79 +1254,60 @@ static void encode_lock(struct xdr_stream *xdr, const struct nfs_lock_args *args
 {
         __be32 *p;
 
-        p = reserve_space(xdr, 32);
-        *p++ = cpu_to_be32(OP_LOCK);
+        encode_op_hdr(xdr, OP_LOCK, decode_lock_maxsz, hdr);
+        p = reserve_space(xdr, 28);
         *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){
-                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_nfs4_seqid(xdr, args->open_seqid);
+                encode_nfs4_stateid(xdr, args->open_stateid);
+                encode_nfs4_seqid(xdr, args->lock_seqid);
                 encode_lockowner(xdr, &args->lock_owner);
         }
         else {
-                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);
+                encode_nfs4_stateid(xdr, args->lock_stateid);
+                encode_nfs4_seqid(xdr, args->lock_seqid);
         }
-        hdr->nops++;
-        hdr->replen += decode_lock_maxsz;
 }
 
 static void encode_lockt(struct xdr_stream *xdr, const struct nfs_lockt_args *args, struct compound_hdr *hdr)
 {
         __be32 *p;
 
-        p = reserve_space(xdr, 24);
-        *p++ = cpu_to_be32(OP_LOCKT);
+        encode_op_hdr(xdr, OP_LOCKT, decode_lockt_maxsz, hdr);
+        p = reserve_space(xdr, 20);
         *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;
 }
 
 static void encode_locku(struct xdr_stream *xdr, const struct nfs_locku_args *args, struct compound_hdr *hdr)
 {
         __be32 *p;
 
-        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);
+        encode_op_hdr(xdr, OP_LOCKU, decode_locku_maxsz, hdr);
+        encode_uint32(xdr, nfs4_lock_type(args->fl, 0));
+        encode_nfs4_seqid(xdr, args->seqid);
+        encode_nfs4_stateid(xdr, args->stateid);
+        p = reserve_space(xdr, 16);
         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_op_hdr(xdr, OP_RELEASE_LOCKOWNER, decode_release_lockowner_maxsz, hdr);
         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;
-
-        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;
+        encode_op_hdr(xdr, OP_LOOKUP, decode_lookup_maxsz, hdr);
+        encode_string(xdr, name->len, name->name);
 }
 
 static void encode_share_access(struct xdr_stream *xdr, fmode_t fmode)
@@ -1335,9 +1338,7 @@ 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
  */
-        p = reserve_space(xdr, 8);
-        *p++ = cpu_to_be32(OP_OPEN);
-        *p = cpu_to_be32(arg->seqid->sequence->counter);
+        encode_nfs4_seqid(xdr, arg->seqid);
         encode_share_access(xdr, arg->fmode);
         p = reserve_space(xdr, 32);
         p = xdr_encode_hyper(p, arg->clientid);
@@ -1437,14 +1438,15 @@ static inline void encode_claim_delegate_cur(struct xdr_stream *xdr, const struc
 {
         __be32 *p;
 
-        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);
+        p = reserve_space(xdr, 4);
+        *p = cpu_to_be32(NFS4_OPEN_CLAIM_DELEGATE_CUR);
+        encode_nfs4_stateid(xdr, stateid);
         encode_string(xdr, name->len, name->name);
 }
 
 static void encode_open(struct xdr_stream *xdr, const struct nfs_openargs *arg, struct compound_hdr *hdr)
 {
+        encode_op_hdr(xdr, OP_OPEN, decode_open_maxsz, hdr);
         encode_openhdr(xdr, arg);
         encode_opentype(xdr, arg);
         switch (arg->claim) {
@@ -1460,88 +1462,64 @@ static void encode_open(struct xdr_stream *xdr, const struct nfs_openargs *arg,
         default:
                 BUG();
         }
-        hdr->nops++;
-        hdr->replen += decode_open_maxsz;
 }
 
 static void encode_open_confirm(struct xdr_stream *xdr, const struct nfs_open_confirmargs *arg, struct compound_hdr *hdr)
 {
-        __be32 *p;
-
-        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;
+        encode_op_hdr(xdr, OP_OPEN_CONFIRM, decode_open_confirm_maxsz, hdr);
+        encode_nfs4_stateid(xdr, arg->stateid);
+        encode_nfs4_seqid(xdr, arg->seqid);
 }
 
 static void encode_open_downgrade(struct xdr_stream *xdr, const struct nfs_closeargs *arg, struct compound_hdr *hdr)
 {
-        __be32 *p;
-
-        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_op_hdr(xdr, OP_OPEN_DOWNGRADE, decode_open_downgrade_maxsz, hdr);
+        encode_nfs4_stateid(xdr, arg->stateid);
+        encode_nfs4_seqid(xdr, arg->seqid);
         encode_share_access(xdr, arg->fmode);
-        hdr->nops++;
-        hdr->replen += decode_open_downgrade_maxsz;
 }
 
 static void
 encode_putfh(struct xdr_stream *xdr, const struct nfs_fh *fh, struct compound_hdr *hdr)
 {
-        int len = fh->size;
-        __be32 *p;
-
-        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;
+        encode_op_hdr(xdr, OP_PUTFH, decode_putfh_maxsz, hdr);
+        encode_string(xdr, fh->size, fh->data);
 }
 
 static void encode_putrootfh(struct xdr_stream *xdr, struct compound_hdr *hdr)
 {
-        __be32 *p;
-
-        p = reserve_space(xdr, 4);
-        *p = cpu_to_be32(OP_PUTROOTFH);
-        hdr->nops++;
-        hdr->replen += decode_putrootfh_maxsz;
+        encode_op_hdr(xdr, OP_PUTROOTFH, decode_putrootfh_maxsz, hdr);
 }
 
-static void encode_stateid(struct xdr_stream *xdr, const struct nfs_open_context *ctx, const struct nfs_lock_context *l_ctx, int zero_seqid)
+static void encode_open_stateid(struct xdr_stream *xdr,
+                const struct nfs_open_context *ctx,
+                const struct nfs_lock_context *l_ctx,
+                fmode_t fmode,
+                int zero_seqid)
 {
         nfs4_stateid stateid;
-        __be32 *p;
 
-        p = reserve_space(xdr, NFS4_STATEID_SIZE);
         if (ctx->state != NULL) {
-                nfs4_copy_stateid(&stateid, ctx->state, l_ctx->lockowner, l_ctx->pid);
+                nfs4_select_rw_stateid(&stateid, ctx->state,
+                                fmode, l_ctx->lockowner, l_ctx->pid);
                 if (zero_seqid)
-                        stateid.stateid.seqid = 0;
-                xdr_encode_opaque_fixed(p, stateid.data, NFS4_STATEID_SIZE);
+                        stateid.seqid = 0;
+                encode_nfs4_stateid(xdr, &stateid);
         } else
-                xdr_encode_opaque_fixed(p, zero_stateid.data, NFS4_STATEID_SIZE);
+                encode_nfs4_stateid(xdr, &zero_stateid);
 }
 
 static void encode_read(struct xdr_stream *xdr, const struct nfs_readargs *args, struct compound_hdr *hdr)
 {
         __be32 *p;
 
-        p = reserve_space(xdr, 4);
-        *p = cpu_to_be32(OP_READ);
-
-        encode_stateid(xdr, args->context, args->lock_context,
-                       hdr->minorversion);
+        encode_op_hdr(xdr, OP_READ, decode_read_maxsz, hdr);
+        encode_open_stateid(xdr, args->context, args->lock_context,
+                        FMODE_READ, hdr->minorversion);
 
         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)
@@ -1551,7 +1529,7 @@ static void encode_readdir(struct xdr_stream *xdr, const struct nfs4_readdir_arg
                 FATTR4_WORD1_MOUNTED_ON_FILEID,
         };
         uint32_t dircount = readdir->count >> 1;
-        __be32 *p;
+        __be32 *p, verf[2];
 
         if (readdir->plus) {
                 attrs[0] |= FATTR4_WORD0_TYPE|FATTR4_WORD0_CHANGE|FATTR4_WORD0_SIZE|
@@ -1566,80 +1544,54 @@ static void encode_readdir(struct xdr_stream *xdr, const struct nfs4_readdir_arg
         if (!(readdir->bitmask[1] & FATTR4_WORD1_MOUNTED_ON_FILEID))
                 attrs[0] |= FATTR4_WORD0_FILEID;
 
-        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);
+        encode_op_hdr(xdr, OP_READDIR, decode_readdir_maxsz, hdr);
+        encode_uint64(xdr, readdir->cookie);
+        encode_nfs4_verifier(xdr, &readdir->verifier);
+        p = reserve_space(xdr, 20);
         *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;
+        memcpy(verf, readdir->verifier.data, sizeof(verf));
         dprintk("%s: cookie = %Lu, verifier = %08x:%08x, bitmap = %08x:%08x\n",
                         __func__,
                         (unsigned long long)readdir->cookie,
-                        ((u32 *)readdir->verifier.data)[0],
-                        ((u32 *)readdir->verifier.data)[1],
+                        verf[0], verf[1],
                         attrs[0] & readdir->bitmask[0],
                         attrs[1] & readdir->bitmask[1]);
 }
 
 static void encode_readlink(struct xdr_stream *xdr, const struct nfs4_readlink *readlink, struct rpc_rqst *req, struct compound_hdr *hdr)
 {
-        __be32 *p;
-
-        p = reserve_space(xdr, 4);
-        *p = cpu_to_be32(OP_READLINK);
-        hdr->nops++;
-        hdr->replen += decode_readlink_maxsz;
+        encode_op_hdr(xdr, OP_READLINK, decode_readlink_maxsz, hdr);
 }
 
 static void encode_remove(struct xdr_stream *xdr, const struct qstr *name, struct compound_hdr *hdr)
 {
-        __be32 *p;
-
-        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;
+        encode_op_hdr(xdr, OP_REMOVE, decode_remove_maxsz, hdr);
+        encode_string(xdr, name->len, name->name);
 }
 
 static void encode_rename(struct xdr_stream *xdr, const struct qstr *oldname, const struct qstr *newname, struct compound_hdr *hdr)
 {
-        __be32 *p;
-
-        p = reserve_space(xdr, 4);
-        *p = cpu_to_be32(OP_RENAME);
+        encode_op_hdr(xdr, OP_RENAME, decode_rename_maxsz, hdr);
         encode_string(xdr, oldname->len, oldname->name);
         encode_string(xdr, newname->len, newname->name);
-        hdr->nops++;
-        hdr->replen += decode_rename_maxsz;
 }
 
-static void encode_renew(struct xdr_stream *xdr, const struct nfs_client *client_stateid, struct compound_hdr *hdr)
+static void encode_renew(struct xdr_stream *xdr, clientid4 clid,
+                         struct compound_hdr *hdr)
 {
-        __be32 *p;
-
-        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;
+        encode_op_hdr(xdr, OP_RENEW, decode_renew_maxsz, hdr);
+        encode_uint64(xdr, clid);
 }
 
 static void
 encode_restorefh(struct xdr_stream *xdr, struct compound_hdr *hdr)
 {
-        __be32 *p;
-
-        p = reserve_space(xdr, 4);
-        *p = cpu_to_be32(OP_RESTOREFH);
-        hdr->nops++;
-        hdr->replen += decode_restorefh_maxsz;
+        encode_op_hdr(xdr, OP_RESTOREFH, decode_restorefh_maxsz, hdr);
 }
 
 static void
@@ -1647,9 +1599,8 @@ encode_setacl(struct xdr_stream *xdr, struct nfs_setaclargs *arg, struct compoun
 {
         __be32 *p;
 
-        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);
+        encode_op_hdr(xdr, OP_SETATTR, decode_setacl_maxsz, hdr);
+        encode_nfs4_stateid(xdr, &zero_stateid);
         p = reserve_space(xdr, 2*4);
         *p++ = cpu_to_be32(1);
         *p = cpu_to_be32(FATTR4_WORD0_ACL);
@@ -1657,30 +1608,18 @@ encode_setacl(struct xdr_stream *xdr, struct nfs_setaclargs *arg, struct compoun
         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;
 }
 
 static void
 encode_savefh(struct xdr_stream *xdr, struct compound_hdr *hdr)
 {
-        __be32 *p;
-
-        p = reserve_space(xdr, 4);
-        *p = cpu_to_be32(OP_SAVEFH);
-        hdr->nops++;
-        hdr->replen += decode_savefh_maxsz;
+        encode_op_hdr(xdr, OP_SAVEFH, decode_savefh_maxsz, hdr);
 }
 
 static void encode_setattr(struct xdr_stream *xdr, const struct nfs_setattrargs *arg, const struct nfs_server *server, struct compound_hdr *hdr)
 {
-        __be32 *p;
-
-        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_op_hdr(xdr, OP_SETATTR, decode_setattr_maxsz, hdr);
+        encode_nfs4_stateid(xdr, &arg->stateid);
         encode_attrs(xdr, arg->iap, server);
 }
 
@@ -1688,9 +1627,8 @@ static void encode_setclientid(struct xdr_stream *xdr, const struct nfs4_setclie
 {
         __be32 *p;
 
-        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_op_hdr(xdr, OP_SETCLIENTID, decode_setclientid_maxsz, hdr);
+        encode_nfs4_verifier(xdr, setclientid->sc_verifier);
 
         encode_string(xdr, setclientid->sc_name_len, setclientid->sc_name);
         p = reserve_space(xdr, 4);
@@ -1699,31 +1637,23 @@ static void encode_setclientid(struct xdr_stream *xdr, const struct nfs4_setclie
         encode_string(xdr, setclientid->sc_uaddr_len, setclientid->sc_uaddr);
         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 nfs4_setclientid_res *arg, struct compound_hdr *hdr)
 {
-        __be32 *p;
-
-        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;
+        encode_op_hdr(xdr, OP_SETCLIENTID_CONFIRM,
+                        decode_setclientid_confirm_maxsz, hdr);
+        encode_uint64(xdr, arg->clientid);
+        encode_nfs4_verifier(xdr, &arg->confirm);
 }
 
 static void encode_write(struct xdr_stream *xdr, const struct nfs_writeargs *args, struct compound_hdr *hdr)
 {
         __be32 *p;
 
-        p = reserve_space(xdr, 4);
-        *p = cpu_to_be32(OP_WRITE);
-
-        encode_stateid(xdr, args->context, args->lock_context,
-                       hdr->minorversion);
+        encode_op_hdr(xdr, OP_WRITE, decode_write_maxsz, hdr);
+        encode_open_stateid(xdr, args->context, args->lock_context,
+                        FMODE_WRITE, hdr->minorversion);
 
         p = reserve_space(xdr, 16);
         p = xdr_encode_hyper(p, args->offset);
@@ -1731,32 +1661,18 @@ static void encode_write(struct xdr_stream *xdr, const struct nfs_writeargs *arg
         *p = cpu_to_be32(args->count);
 
         xdr_write_pages(xdr, args->pages, args->pgbase, args->count);
-        hdr->nops++;
-        hdr->replen += decode_write_maxsz;
 }
 
 static void encode_delegreturn(struct xdr_stream *xdr, const nfs4_stateid *stateid, struct compound_hdr *hdr)
 {
-        __be32 *p;
-
-        p = reserve_space(xdr, 4+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;
+        encode_op_hdr(xdr, OP_DELEGRETURN, decode_delegreturn_maxsz, hdr);
+        encode_nfs4_stateid(xdr, stateid);
 }
 
 static void encode_secinfo(struct xdr_stream *xdr, const struct qstr *name, struct compound_hdr *hdr)
 {
-        int len = name->len;
-        __be32 *p;
-
-        p = reserve_space(xdr, 8 + len);
-        *p++ = cpu_to_be32(OP_SECINFO);
-        xdr_encode_opaque(p, name->name, len);
-        hdr->nops++;
-        hdr->replen += decode_secinfo_maxsz;
+        encode_op_hdr(xdr, OP_SECINFO, decode_secinfo_maxsz, hdr);
+        encode_string(xdr, name->len, name->name);
 }
 
 #if defined(CONFIG_NFS_V4_1)
@@ -1766,19 +1682,39 @@ static void encode_exchange_id(struct xdr_stream *xdr,
                                struct compound_hdr *hdr)
 {
         __be32 *p;
+        char impl_name[NFS4_OPAQUE_LIMIT];
+        int len = 0;
 
-        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_op_hdr(xdr, OP_EXCHANGE_ID, decode_exchange_id_maxsz, hdr);
+        encode_nfs4_verifier(xdr, args->verifier);
 
         encode_string(xdr, args->id_len, args->id);
 
         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;
+
+        if (send_implementation_id &&
+            sizeof(CONFIG_NFS_V4_1_IMPLEMENTATION_ID_DOMAIN) > 1 &&
+            sizeof(CONFIG_NFS_V4_1_IMPLEMENTATION_ID_DOMAIN)
+                <= NFS4_OPAQUE_LIMIT + 1)
+                len = snprintf(impl_name, sizeof(impl_name), "%s %s %s %s",
+                               utsname()->sysname, utsname()->release,
+                               utsname()->version, utsname()->machine);
+
+        if (len > 0) {
+                *p = cpu_to_be32(1);    /* implementation id array length=1 */
+
+                encode_string(xdr,
+                        sizeof(CONFIG_NFS_V4_1_IMPLEMENTATION_ID_DOMAIN) - 1,
+                        CONFIG_NFS_V4_1_IMPLEMENTATION_ID_DOMAIN);
+                encode_string(xdr, len, impl_name);
+                /* just send zeros for nii_date - the date is in nii_name */
+                p = reserve_space(xdr, 12);
+                p = xdr_encode_hyper(p, 0);
+                *p = cpu_to_be32(0);
+        } else
+                *p = cpu_to_be32(0);    /* implementation id array length=0 */
 }
 
 static void encode_create_session(struct xdr_stream *xdr,
@@ -1801,8 +1737,8 @@ static void encode_create_session(struct xdr_stream *xdr,
         len = scnprintf(machine_name, sizeof(machine_name), "%s",
                         clp->cl_ipaddr);
 
-        p = reserve_space(xdr, 20 + 2*28 + 20 + len + 12);
-        *p++ = cpu_to_be32(OP_CREATE_SESSION);
+        encode_op_hdr(xdr, OP_CREATE_SESSION, decode_create_session_maxsz, hdr);
+        p = reserve_space(xdr, 16 + 2*28 + 20 + len + 12);
         p = xdr_encode_hyper(p, clp->cl_clientid);
         *p++ = cpu_to_be32(clp->cl_seqid);                      /*Sequence id */
         *p++ = cpu_to_be32(args->flags);                        /*flags */
@@ -1835,33 +1771,22 @@ static void encode_create_session(struct xdr_stream *xdr,
         *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;
 }
 
 static void encode_destroy_session(struct xdr_stream *xdr,
                                    struct nfs4_session *session,
                                    struct compound_hdr *hdr)
 {
-        __be32 *p;
-        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;
+        encode_op_hdr(xdr, OP_DESTROY_SESSION, decode_destroy_session_maxsz, hdr);
+        encode_opaque_fixed(xdr, session->sess_id.data, NFS4_MAX_SESSIONID_LEN);
 }
 
 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;
+        encode_op_hdr(xdr, OP_RECLAIM_COMPLETE, decode_reclaim_complete_maxsz, hdr);
+        encode_uint32(xdr, args->one_fs);
 }
 #endif /* CONFIG_NFS_V4_1 */
 
@@ -1883,8 +1808,7 @@ static void encode_sequence(struct xdr_stream *xdr,
         WARN_ON(args->sa_slotid == NFS4_MAX_SLOT_TABLE);
         slot = tp->slots + args->sa_slotid;
 
-        p = reserve_space(xdr, 4 + NFS4_MAX_SESSIONID_LEN + 16);
-        *p++ = cpu_to_be32(OP_SEQUENCE);
+        encode_op_hdr(xdr, OP_SEQUENCE, decode_sequence_maxsz, hdr);
 
         /*
          * Sessionid + seqid + slotid + max slotid + cache_this
@@ -1898,13 +1822,12 @@ 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);
+        p = reserve_space(xdr, NFS4_MAX_SESSIONID_LEN + 16);
         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 */
 }
 
@@ -1919,14 +1842,12 @@ encode_getdevicelist(struct xdr_stream *xdr,
                 .data = "dummmmmy",
         };
 
-        p = reserve_space(xdr, 20);
-        *p++ = cpu_to_be32(OP_GETDEVICELIST);
+        encode_op_hdr(xdr, OP_GETDEVICELIST, decode_getdevicelist_maxsz, hdr);
+        p = reserve_space(xdr, 16);
         *p++ = cpu_to_be32(args->layoutclass);
         *p++ = cpu_to_be32(NFS4_PNFS_GETDEVLIST_MAXNUM);
         xdr_encode_hyper(p, 0ULL);                          /* cookie */
         encode_nfs4_verifier(xdr, &dummy);
-        hdr->nops++;
-        hdr->replen += decode_getdevicelist_maxsz;
 }
 
 static void
@@ -1936,15 +1857,13 @@ encode_getdeviceinfo(struct xdr_stream *xdr,
 {
         __be32 *p;
 
-        p = reserve_space(xdr, 16 + NFS4_DEVICEID4_SIZE);
-        *p++ = cpu_to_be32(OP_GETDEVICEINFO);
+        encode_op_hdr(xdr, OP_GETDEVICEINFO, decode_getdeviceinfo_maxsz, hdr);
+        p = reserve_space(xdr, 12 + NFS4_DEVICEID4_SIZE);
         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
@@ -1954,16 +1873,16 @@ encode_layoutget(struct xdr_stream *xdr,
 {
         __be32 *p;
 
-        p = reserve_space(xdr, 44 + NFS4_STATEID_SIZE);
-        *p++ = cpu_to_be32(OP_LAYOUTGET);
+        encode_op_hdr(xdr, OP_LAYOUTGET, decode_layoutget_maxsz, hdr);
+        p = reserve_space(xdr, 36);
         *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);
+        encode_nfs4_stateid(xdr, &args->stateid);
+        encode_uint32(xdr, args->maxcount);
 
         dprintk("%s: 1st type:0x%x iomode:%d off:%lu len:%lu mc:%d\n",
                 __func__,
@@ -1972,8 +1891,6 @@ encode_layoutget(struct xdr_stream *xdr,
                 (unsigned long)args->range.offset,
                 (unsigned long)args->range.length,
                 args->maxcount);
-        hdr->nops++;
-        hdr->replen += decode_layoutget_maxsz;
 }
 
 static int
@@ -1987,13 +1904,14 @@ encode_layoutcommit(struct xdr_stream *xdr,
         dprintk("%s: lbw: %llu type: %d\n", __func__, args->lastbytewritten,
                 NFS_SERVER(args->inode)->pnfs_curr_ld->id);
 
-        p = reserve_space(xdr, 44 + NFS4_STATEID_SIZE);
-        *p++ = cpu_to_be32(OP_LAYOUTCOMMIT);
+        encode_op_hdr(xdr, OP_LAYOUTCOMMIT, decode_layoutcommit_maxsz, hdr);
+        p = reserve_space(xdr, 20);
         /* Only whole file layouts */
         p = xdr_encode_hyper(p, 0); /* offset */
         p = xdr_encode_hyper(p, args->lastbytewritten + 1);     /* length */
-        *p++ = cpu_to_be32(0); /* reclaim */
-        p = xdr_encode_opaque_fixed(p, args->stateid.data, NFS4_STATEID_SIZE);
+        *p = cpu_to_be32(0); /* reclaim */
+        encode_nfs4_stateid(xdr, &args->stateid);
+        p = reserve_space(xdr, 20);
         *p++ = cpu_to_be32(1); /* newoffset = TRUE */
         p = xdr_encode_hyper(p, args->lastbytewritten);
         *p++ = cpu_to_be32(0); /* Never send time_modify_changed */
@@ -2002,13 +1920,9 @@ encode_layoutcommit(struct xdr_stream *xdr,
         if (NFS_SERVER(inode)->pnfs_curr_ld->encode_layoutcommit)
                 NFS_SERVER(inode)->pnfs_curr_ld->encode_layoutcommit(
                         NFS_I(inode)->layout, xdr, args);
-        else {
-                p = reserve_space(xdr, 4);
-                *p = cpu_to_be32(0); /* no layout-type payload */
-        }
+        else
+                encode_uint32(xdr, 0); /* no layout-type payload */
 
-        hdr->nops++;
-        hdr->replen += decode_layoutcommit_maxsz;
         return 0;
 }
 
@@ -2019,27 +1933,23 @@ encode_layoutreturn(struct xdr_stream *xdr,
 {
         __be32 *p;
 
-        p = reserve_space(xdr, 20);
-        *p++ = cpu_to_be32(OP_LAYOUTRETURN);
+        encode_op_hdr(xdr, OP_LAYOUTRETURN, decode_layoutreturn_maxsz, hdr);
+        p = reserve_space(xdr, 16);
         *p++ = cpu_to_be32(0);          /* reclaim. always 0 for now */
         *p++ = cpu_to_be32(args->layout_type);
         *p++ = cpu_to_be32(IOMODE_ANY);
         *p = cpu_to_be32(RETURN_FILE);
-        p = reserve_space(xdr, 16 + NFS4_STATEID_SIZE);
+        p = reserve_space(xdr, 16);
         p = xdr_encode_hyper(p, 0);
         p = xdr_encode_hyper(p, NFS4_MAX_UINT64);
         spin_lock(&args->inode->i_lock);
-        xdr_encode_opaque_fixed(p, &args->stateid.data, NFS4_STATEID_SIZE);
+        encode_nfs4_stateid(xdr, &args->stateid);
         spin_unlock(&args->inode->i_lock);
         if (NFS_SERVER(args->inode)->pnfs_curr_ld->encode_layoutreturn) {
                 NFS_SERVER(args->inode)->pnfs_curr_ld->encode_layoutreturn(
                         NFS_I(args->inode)->layout, xdr, args);
-        } else {
-                p = reserve_space(xdr, 4);
-                *p = cpu_to_be32(0);
-        }
-        hdr->nops++;
-        hdr->replen += decode_layoutreturn_maxsz;
+        } else
+                encode_uint32(xdr, 0);
 }
 
 static int
@@ -2047,12 +1957,8 @@ encode_secinfo_no_name(struct xdr_stream *xdr,
                        const struct nfs41_secinfo_no_name_args *args,
                        struct compound_hdr *hdr)
 {
-        __be32 *p;
-        p = reserve_space(xdr, 8);
-        *p++ = cpu_to_be32(OP_SECINFO_NO_NAME);
-        *p++ = cpu_to_be32(args->style);
-        hdr->nops++;
-        hdr->replen += decode_secinfo_no_name_maxsz;
+        encode_op_hdr(xdr, OP_SECINFO_NO_NAME, decode_secinfo_no_name_maxsz, hdr);
+        encode_uint32(xdr, args->style);
         return 0;
 }
 
@@ -2060,26 +1966,17 @@ static void encode_test_stateid(struct xdr_stream *xdr,
                                 struct nfs41_test_stateid_args *args,
                                 struct compound_hdr *hdr)
 {
-        __be32 *p;
-
-        p = reserve_space(xdr, 8 + NFS4_STATEID_SIZE);
-        *p++ = cpu_to_be32(OP_TEST_STATEID);
-        *p++ = cpu_to_be32(1);
-        xdr_encode_opaque_fixed(p, args->stateid->data, NFS4_STATEID_SIZE);
-        hdr->nops++;
-        hdr->replen += decode_test_stateid_maxsz;
+        encode_op_hdr(xdr, OP_TEST_STATEID, decode_test_stateid_maxsz, hdr);
+        encode_uint32(xdr, 1);
+        encode_nfs4_stateid(xdr, args->stateid);
 }
 
 static void encode_free_stateid(struct xdr_stream *xdr,
                                 struct nfs41_free_stateid_args *args,
                                 struct compound_hdr *hdr)
 {
-        __be32 *p;
-        p = reserve_space(xdr, 4 + NFS4_STATEID_SIZE);
-        *p++ = cpu_to_be32(OP_FREE_STATEID);
-        xdr_encode_opaque_fixed(p, args->stateid->data, NFS4_STATEID_SIZE);
-        hdr->nops++;
-        hdr->replen += decode_free_stateid_maxsz;
+        encode_op_hdr(xdr, OP_FREE_STATEID, decode_free_stateid_maxsz, hdr);
+        encode_nfs4_stateid(xdr, args->stateid);
 }
 #endif /* CONFIG_NFS_V4_1 */
 
@@ -2633,6 +2530,7 @@ static void nfs4_xdr_enc_server_caps(struct rpc_rqst *req,
         encode_sequence(xdr, &args->seq_args, &hdr);
         encode_putfh(xdr, args->fhandle, &hdr);
         encode_getattr_one(xdr, FATTR4_WORD0_SUPPORTED_ATTRS|
+                           FATTR4_WORD0_FH_EXPIRE_TYPE|
                            FATTR4_WORD0_LINK_SUPPORT|
                            FATTR4_WORD0_SYMLINK_SUPPORT|
                            FATTR4_WORD0_ACLSUPPORT, &hdr);
@@ -2650,7 +2548,7 @@ static void nfs4_xdr_enc_renew(struct rpc_rqst *req, struct xdr_stream *xdr,
         };
 
         encode_compound_hdr(xdr, req, &hdr);
-        encode_renew(xdr, clp, &hdr);
+        encode_renew(xdr, clp->cl_clientid, &hdr);
         encode_nops(&hdr);
 }
 
@@ -3180,6 +3078,28 @@ out_overflow:
         return -EIO;
 }
 
+static int decode_attr_fh_expire_type(struct xdr_stream *xdr,
+                                      uint32_t *bitmap, uint32_t *type)
+{
+        __be32 *p;
+
+        *type = 0;
+        if (unlikely(bitmap[0] & (FATTR4_WORD0_FH_EXPIRE_TYPE - 1U)))
+                return -EIO;
+        if (likely(bitmap[0] & FATTR4_WORD0_FH_EXPIRE_TYPE)) {
+                p = xdr_inline_decode(xdr, 4);
+                if (unlikely(!p))
+                        goto out_overflow;
+                *type = be32_to_cpup(p);
+                bitmap[0] &= ~FATTR4_WORD0_FH_EXPIRE_TYPE;
+        }
+        dprintk("%s: expire type=0x%x\n", __func__, *type);
+        return 0;
+out_overflow:
+        print_overflow_msg(__func__, xdr);
+        return -EIO;
+}
+
 static int decode_attr_change(struct xdr_stream *xdr, uint32_t *bitmap, uint64_t *change)
 {
         __be32 *p;
@@ -3513,16 +3433,17 @@ static int decode_pathname(struct xdr_stream *xdr, struct nfs4_pathname *path)
         n = be32_to_cpup(p);
         if (n == 0)
                 goto root_path;
-        dprintk("path ");
+        dprintk("pathname4: ");
         path->ncomponents = 0;
         while (path->ncomponents < n) {
                 struct nfs4_string *component = &path->components[path->ncomponents];
                 status = decode_opaque_inline(xdr, &component->len, &component->data);
                 if (unlikely(status != 0))
                         goto out_eio;
-                if (path->ncomponents != n)
-                        dprintk("/");
-                dprintk("%s", component->data);
+                ifdebug (XDR)
+                        pr_cont("%s%.*s ",
+                                (path->ncomponents != n ? "/ " : ""),
+                                component->len, component->data);
                 if (path->ncomponents < NFS4_PATHNAME_MAXCOMPONENTS)
                         path->ncomponents++;
                 else {
@@ -3531,14 +3452,13 @@ static int decode_pathname(struct xdr_stream *xdr, struct nfs4_pathname *path)
                 }
         }
 out:
-        dprintk("\n");
         return status;
 root_path:
 /* a root pathname is sent as a zero component4 */
         path->ncomponents = 1;
         path->components[0].len=0;
         path->components[0].data=NULL;
-        dprintk("path /\n");
+        dprintk("pathname4: /\n");
         goto out;
 out_eio:
         dprintk(" status %d", status);
@@ -3560,7 +3480,11 @@ static int decode_attr_fs_locations(struct xdr_stream *xdr, uint32_t *bitmap, st
         status = 0;
         if (unlikely(!(bitmap[0] & FATTR4_WORD0_FS_LOCATIONS)))
                 goto out;
-        dprintk("%s: fsroot ", __func__);
+        status = -EIO;
+        /* Ignore borken servers that return unrequested attrs */
+        if (unlikely(res == NULL))
+                goto out;
+        dprintk("%s: fsroot:\n", __func__);
         status = decode_pathname(xdr, &res->fs_path);
         if (unlikely(status != 0))
                 goto out;
@@ -3581,7 +3505,7 @@ static int decode_attr_fs_locations(struct xdr_stream *xdr, uint32_t *bitmap, st
                 m = be32_to_cpup(p);
 
                 loc->nservers = 0;
-                dprintk("%s: servers ", __func__);
+                dprintk("%s: servers:\n", __func__);
                 while (loc->nservers < m) {
                         struct nfs4_string *server = &loc->servers[loc->nservers];
                         status = decode_opaque_inline(xdr, &server->len, &server->data);
@@ -3613,7 +3537,7 @@ static int decode_attr_fs_locations(struct xdr_stream *xdr, uint32_t *bitmap, st
                         res->nlocations++;
         }
         if (res->nlocations != 0)
-                status = NFS_ATTR_FATTR_V4_REFERRAL;
+                status = NFS_ATTR_FATTR_V4_LOCATIONS;
 out:
         dprintk("%s: fs_locations done, error = %d\n", __func__, status);
         return status;
@@ -4157,7 +4081,7 @@ static int decode_opaque_fixed(struct xdr_stream *xdr, void *buf, size_t len)
 
 static int decode_stateid(struct xdr_stream *xdr, nfs4_stateid *stateid)
 {
-        return decode_opaque_fixed(xdr, stateid->data, NFS4_STATEID_SIZE);
+        return decode_opaque_fixed(xdr, stateid, NFS4_STATEID_SIZE);
 }
 
 static int decode_close(struct xdr_stream *xdr, struct nfs_closeres *res)
@@ -4174,7 +4098,7 @@ static int decode_close(struct xdr_stream *xdr, struct nfs_closeres *res)
 
 static int decode_verifier(struct xdr_stream *xdr, void *verifier)
 {
-        return decode_opaque_fixed(xdr, verifier, 8);
+        return decode_opaque_fixed(xdr, verifier, NFS4_VERIFIER_SIZE);
 }
 
 static int decode_commit(struct xdr_stream *xdr, struct nfs_writeres *res)
@@ -4224,6 +4148,9 @@ static int decode_server_caps(struct xdr_stream *xdr, struct nfs4_server_caps_re
                 goto xdr_error;
         if ((status = decode_attr_supported(xdr, bitmap, res->attr_bitmask)) != 0)
                 goto xdr_error;
+        if ((status = decode_attr_fh_expire_type(xdr, bitmap,
+                                                 &res->fh_expire_type)) != 0)
+                goto xdr_error;
         if ((status = decode_attr_link_support(xdr, bitmap, &res->has_links)) != 0)
                 goto xdr_error;
         if ((status = decode_attr_symlink_support(xdr, bitmap, &res->has_symlinks)) != 0)
@@ -4294,6 +4221,7 @@ xdr_error:
 
 static int decode_getfattr_attrs(struct xdr_stream *xdr, uint32_t *bitmap,
                 struct nfs_fattr *fattr, struct nfs_fh *fh,
+                struct nfs4_fs_locations *fs_loc,
                 const struct nfs_server *server)
 {
         int status;
@@ -4341,9 +4269,7 @@ static int decode_getfattr_attrs(struct xdr_stream *xdr, uint32_t *bitmap,
                 goto xdr_error;
         fattr->valid |= status;
 
-        status = decode_attr_fs_locations(xdr, bitmap, container_of(fattr,
-                                                struct nfs4_fs_locations,
-                                                fattr));
+        status = decode_attr_fs_locations(xdr, bitmap, fs_loc);
         if (status < 0)
                 goto xdr_error;
         fattr->valid |= status;
@@ -4407,7 +4333,8 @@ xdr_error:
 }
 
 static int decode_getfattr_generic(struct xdr_stream *xdr, struct nfs_fattr *fattr,
-                struct nfs_fh *fh, const struct nfs_server *server)
+                struct nfs_fh *fh, struct nfs4_fs_locations *fs_loc,
+                const struct nfs_server *server)
 {
         __be32 *savep;
         uint32_t attrlen,
@@ -4426,7 +4353,7 @@ static int decode_getfattr_generic(struct xdr_stream *xdr, struct nfs_fattr *fat
         if (status < 0)
                 goto xdr_error;
 
-        status = decode_getfattr_attrs(xdr, bitmap, fattr, fh, server);
+        status = decode_getfattr_attrs(xdr, bitmap, fattr, fh, fs_loc, server);
         if (status < 0)
                 goto xdr_error;
 
@@ -4439,7 +4366,7 @@ xdr_error:
 static int decode_getfattr(struct xdr_stream *xdr, struct nfs_fattr *fattr,
                 const struct nfs_server *server)
 {
-        return decode_getfattr_generic(xdr, fattr, NULL, server);
+        return decode_getfattr_generic(xdr, fattr, NULL, NULL, server);
 }
 
 /*
@@ -4463,8 +4390,8 @@ static int decode_first_pnfs_layout_type(struct xdr_stream *xdr,
                 return 0;
         }
         if (num > 1)
-                printk(KERN_INFO "%s: Warning: Multiple pNFS layout drivers "
-                        "per filesystem not supported\n", __func__);
+                printk(KERN_INFO "NFS: %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);
@@ -4863,17 +4790,16 @@ static int decode_readdir(struct xdr_stream *xdr, struct rpc_rqst *req, struct n
         size_t          hdrlen;
         u32             recvd, pglen = rcvbuf->page_len;
         int             status;
+        __be32          verf[2];
 
         status = decode_op_hdr(xdr, OP_READDIR);
         if (!status)
                 status = decode_verifier(xdr, readdir->verifier.data);
         if (unlikely(status))
                 return status;
+        memcpy(verf, readdir->verifier.data, sizeof(verf));
         dprintk("%s: verifier = %08x:%08x\n",
-                        __func__,
-                        ((u32 *)readdir->verifier.data)[0],
-                        ((u32 *)readdir->verifier.data)[1]);
-
+                        __func__, verf[0], verf[1]);
 
         hdrlen = (char *) xdr->p - (char *) iov->iov_base;
         recvd = rcvbuf->len - hdrlen;
@@ -5120,7 +5046,7 @@ static int decode_write(struct xdr_stream *xdr, struct nfs_writeres *res)
                 goto out_overflow;
         res->count = be32_to_cpup(p++);
         res->verf->committed = be32_to_cpup(p++);
-        memcpy(res->verf->verifier, p, 8);
+        memcpy(res->verf->verifier, p, NFS4_VERIFIER_SIZE);
         return 0;
 out_overflow:
         print_overflow_msg(__func__, xdr);
@@ -5214,6 +5140,7 @@ static int decode_exchange_id(struct xdr_stream *xdr,
         char *dummy_str;
         int status;
         struct nfs_client *clp = res->client;
+        uint32_t impl_id_count;
 
         status = decode_op_hdr(xdr, OP_EXCHANGE_ID);
         if (status)
@@ -5255,11 +5182,38 @@ static int decode_exchange_id(struct xdr_stream *xdr,
         memcpy(res->server_scope->server_scope, dummy_str, dummy);
         res->server_scope->server_scope_sz = dummy;
 
-        /* Throw away Implementation id array */
-        status = decode_opaque_inline(xdr, &dummy, &dummy_str);
-        if (unlikely(status))
-                return status;
+        /* Implementation Id */
+        p = xdr_inline_decode(xdr, 4);
+        if (unlikely(!p))
+                goto out_overflow;
+        impl_id_count = be32_to_cpup(p++);
+
+        if (impl_id_count) {
+                /* nii_domain */
+                status = decode_opaque_inline(xdr, &dummy, &dummy_str);
+                if (unlikely(status))
+                        return status;
+                if (unlikely(dummy > NFS4_OPAQUE_LIMIT))
+                        return -EIO;
+                memcpy(res->impl_id->domain, dummy_str, dummy);
 
+                /* nii_name */
+                status = decode_opaque_inline(xdr, &dummy, &dummy_str);
+                if (unlikely(status))
+                        return status;
+                if (unlikely(dummy > NFS4_OPAQUE_LIMIT))
+                        return -EIO;
+                memcpy(res->impl_id->name, dummy_str, dummy);
+
+                /* nii_date */
+                p = xdr_inline_decode(xdr, 12);
+                if (unlikely(!p))
+                        goto out_overflow;
+                p = xdr_decode_hyper(p, &res->impl_id->date.seconds);
+                res->impl_id->date.nseconds = be32_to_cpup(p);
+
+                /* if there's more than one entry, ignore the rest */
+        }
         return 0;
 out_overflow:
         print_overflow_msg(__func__, xdr);
@@ -5285,8 +5239,8 @@ static int decode_chan_attrs(struct xdr_stream *xdr,
         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);
+                printk(KERN_WARNING "NFS: %s: Invalid rdma channel attrs "
+                        "count %u\n", __func__, nr_attrs);
                 return -EINVAL;
         }
         if (nr_attrs == 1) {
@@ -5436,14 +5390,14 @@ static int decode_getdevicelist(struct xdr_stream *xdr,
         p += 2;
 
         /* Read verifier */
-        p = xdr_decode_opaque_fixed(p, verftemp.verifier, 8);
+        p = xdr_decode_opaque_fixed(p, verftemp.verifier, NFS4_VERIFIER_SIZE);
 
         res->num_devs = be32_to_cpup(p);
 
         dprintk("%s: num_dev %d\n", __func__, res->num_devs);
 
         if (res->num_devs > NFS4_PNFS_GETDEVLIST_MAXNUM) {
-                printk(KERN_ERR "%s too many result dev_num %u\n",
+                printk(KERN_ERR "NFS: %s too many result dev_num %u\n",
                                 __func__, res->num_devs);
                 return -EIO;
         }
@@ -5537,11 +5491,14 @@ static int decode_layoutget(struct xdr_stream *xdr, struct rpc_rqst *req,
         status = decode_op_hdr(xdr, OP_LAYOUTGET);
         if (status)
                 return status;
-        p = xdr_inline_decode(xdr, 8 + NFS4_STATEID_SIZE);
+        p = xdr_inline_decode(xdr, 4);
+        if (unlikely(!p))
+                goto out_overflow;
+        res->return_on_close = be32_to_cpup(p);
+        decode_stateid(xdr, &res->stateid);
+        p = xdr_inline_decode(xdr, 4);
         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",
@@ -5666,7 +5623,8 @@ static int decode_test_stateid(struct xdr_stream *xdr,
         if (unlikely(!p))
                 goto out_overflow;
         res->status = be32_to_cpup(p++);
-        return res->status;
+
+        return status;
 out_overflow:
         print_overflow_msg(__func__, xdr);
 out:
@@ -6583,8 +6541,9 @@ static int nfs4_xdr_dec_fs_locations(struct rpc_rqst *req,
         if (status)
                 goto out;
         xdr_enter_page(xdr, PAGE_SIZE);
-        status = decode_getfattr(xdr, &res->fs_locations->fattr,
-                                 res->fs_locations->server);
+        status = decode_getfattr_generic(xdr, &res->fs_locations->fattr,
+                                         NULL, res->fs_locations,
+                                         res->fs_locations->server);
 out:
         return status;
 }
@@ -6964,7 +6923,7 @@ int nfs4_decode_dirent(struct xdr_stream *xdr, struct nfs_entry *entry,
                 goto out_overflow;
 
         if (decode_getfattr_attrs(xdr, bitmap, entry->fattr, entry->fh,
-                                        entry->server) < 0)
+                                  NULL, entry->server) < 0)
                 goto out_overflow;
         if (entry->fattr->valid & NFS_ATTR_FATTR_MOUNTED_ON_FILEID)
                 entry->ino = entry->fattr->mounted_on_fileid;
@@ -7112,7 +7071,7 @@ struct rpc_procinfo	nfs4_procedures[] = {
 #endif /* CONFIG_NFS_V4_1 */
 };
 
-struct rpc_version              nfs_version4 = {
+const struct rpc_version nfs_version4 = {
         .number                 = 4,
         .nrprocs                = ARRAY_SIZE(nfs4_procedures),
         .procs                  = nfs4_procedures
diff --git a/fs/nfs/nfsroot.c b/fs/nfs/nfsroot.c
index c4744e1d513..cd3c910d2d1 100644
--- a/fs/nfs/nfsroot.c
+++ b/fs/nfs/nfsroot.c
@@ -104,7 +104,7 @@ static char nfs_export_path[NFS_MAXPATHLEN + 1] __initdata = "";
 /* server:export path string passed to super.c */
 static char nfs_root_device[NFS_MAXPATHLEN + 1] __initdata = "";
 
-#ifdef RPC_DEBUG
+#ifdef NFS_DEBUG
 /*
  * When the "nfsrootdebug" kernel command line option is specified,
  * enable debugging messages for NFSROOT.
diff --git a/fs/nfs/objlayout/objio_osd.c b/fs/nfs/objlayout/objio_osd.c
index 55d01280a60..4bff4a3dab4 100644
--- a/fs/nfs/objlayout/objio_osd.c
+++ b/fs/nfs/objlayout/objio_osd.c
@@ -137,6 +137,7 @@ static int objio_devices_lookup(struct pnfs_layout_hdr *pnfslay,
         struct objio_dev_ent *ode;
         struct osd_dev *od;
         struct osd_dev_info odi;
+        bool retry_flag = true;
         int err;
 
         ode = _dev_list_find(NFS_SERVER(pnfslay->plh_inode), d_id);
@@ -171,10 +172,18 @@ static int objio_devices_lookup(struct pnfs_layout_hdr *pnfslay,
                 goto out;
         }
 
+retry_lookup:
         od = osduld_info_lookup(&odi);
         if (unlikely(IS_ERR(od))) {
                 err = PTR_ERR(od);
                 dprintk("%s: osduld_info_lookup => %d\n", __func__, err);
+                if (err == -ENODEV && retry_flag) {
+                        err = objlayout_autologin(deviceaddr);
+                        if (likely(!err)) {
+                                retry_flag = false;
+                                goto retry_lookup;
+                        }
+                }
                 goto out;
         }
 
@@ -205,25 +214,36 @@ static void copy_single_comp(struct ore_components *oc, unsigned c,
 int __alloc_objio_seg(unsigned numdevs, gfp_t gfp_flags,
                        struct objio_segment **pseg)
 {
-        struct __alloc_objio_segment {
-                struct objio_segment olseg;
-                struct ore_dev *ods[numdevs];
-                struct ore_comp comps[numdevs];
-        } *aolseg;
-
-        aolseg = kzalloc(sizeof(*aolseg), gfp_flags);
-        if (unlikely(!aolseg)) {
+/*      This is the in memory structure of the objio_segment
+ *
+ *      struct __alloc_objio_segment {
+ *              struct objio_segment olseg;
+ *              struct ore_dev *ods[numdevs];
+ *              struct ore_comp comps[numdevs];
+ *      } *aolseg;
+ *      NOTE: The code as above compiles and runs perfectly. It is elegant,
+ *      type safe and compact. At some Past time Linus has decided he does not
+ *      like variable length arrays, For the sake of this principal we uglify
+ *      the code as below.
+ */
+        struct objio_segment *lseg;
+        size_t lseg_size = sizeof(*lseg) +
+                        numdevs * sizeof(lseg->oc.ods[0]) +
+                        numdevs * sizeof(*lseg->oc.comps);
+
+        lseg = kzalloc(lseg_size, gfp_flags);
+        if (unlikely(!lseg)) {
                 dprintk("%s: Faild allocation numdevs=%d size=%zd\n", __func__,
-                        numdevs, sizeof(*aolseg));
+                        numdevs, lseg_size);
                 return -ENOMEM;
         }
 
-        aolseg->olseg.oc.numdevs = numdevs;
-        aolseg->olseg.oc.single_comp = EC_MULTPLE_COMPS;
-        aolseg->olseg.oc.comps = aolseg->comps;
-        aolseg->olseg.oc.ods = aolseg->ods;
+        lseg->oc.numdevs = numdevs;
+        lseg->oc.single_comp = EC_MULTPLE_COMPS;
+        lseg->oc.ods = (void *)(lseg + 1);
+        lseg->oc.comps = (void *)(lseg->oc.ods + numdevs);
 
-        *pseg = &aolseg->olseg;
+        *pseg = lseg;
         return 0;
 }
 
@@ -582,10 +602,10 @@ objlayout_init(void)
 
         if (ret)
                 printk(KERN_INFO
-                        "%s: Registering OSD pNFS Layout Driver failed: error=%d\n",
+                        "NFS: %s: Registering OSD pNFS Layout Driver failed: error=%d\n",
                         __func__, ret);
         else
-                printk(KERN_INFO "%s: Registered OSD pNFS Layout Driver\n",
+                printk(KERN_INFO "NFS: %s: Registered OSD pNFS Layout Driver\n",
                         __func__);
         return ret;
 }
@@ -594,7 +614,7 @@ static void __exit
 objlayout_exit(void)
 {
         pnfs_unregister_layoutdriver(&objlayout_type);
-        printk(KERN_INFO "%s: Unregistered OSD pNFS Layout Driver\n",
+        printk(KERN_INFO "NFS: %s: Unregistered OSD pNFS Layout Driver\n",
                __func__);
 }
 
diff --git a/fs/nfs/objlayout/objlayout.c b/fs/nfs/objlayout/objlayout.c
index b3c29039f5b..8d45f1c318c 100644
--- a/fs/nfs/objlayout/objlayout.c
+++ b/fs/nfs/objlayout/objlayout.c
@@ -37,6 +37,9 @@
  *  SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
  */
 
+#include <linux/kmod.h>
+#include <linux/moduleparam.h>
+#include <linux/ratelimit.h>
 #include <scsi/osd_initiator.h>
 #include "objlayout.h"
 
@@ -156,7 +159,7 @@ last_byte_offset(u64 start, u64 len)
         return end > start ? end - 1 : NFS4_MAX_UINT64;
 }
 
-void _fix_verify_io_params(struct pnfs_layout_segment *lseg,
+static void _fix_verify_io_params(struct pnfs_layout_segment *lseg,
                            struct page ***p_pages, unsigned *p_pgbase,
                            u64 offset, unsigned long count)
 {
@@ -490,9 +493,9 @@ encode_accumulated_error(struct objlayout *objlay, __be32 *p)
                         if (!ioerr->oer_errno)
                                 continue;
 
-                        printk(KERN_ERR "%s: err[%d]: errno=%d is_write=%d "
-                                "dev(%llx:%llx) par=0x%llx obj=0x%llx "
-                                "offset=0x%llx length=0x%llx\n",
+                        printk(KERN_ERR "NFS: %s: err[%d]: errno=%d "
+                                "is_write=%d dev(%llx:%llx) par=0x%llx "
+                                "obj=0x%llx offset=0x%llx length=0x%llx\n",
                                 __func__, i, ioerr->oer_errno,
                                 ioerr->oer_iswrite,
                                 _DEVID_LO(&ioerr->oer_component.oid_device_id),
@@ -651,3 +654,134 @@ void objlayout_put_deviceinfo(struct pnfs_osd_deviceaddr *deviceaddr)
         __free_page(odi->page);
         kfree(odi);
 }
+
+enum {
+        OBJLAYOUT_MAX_URI_LEN = 256, OBJLAYOUT_MAX_OSDNAME_LEN = 64,
+        OBJLAYOUT_MAX_SYSID_HEX_LEN = OSD_SYSTEMID_LEN * 2 + 1,
+        OSD_LOGIN_UPCALL_PATHLEN  = 256
+};
+
+static char osd_login_prog[OSD_LOGIN_UPCALL_PATHLEN] = "/sbin/osd_login";
+
+module_param_string(osd_login_prog, osd_login_prog, sizeof(osd_login_prog),
+                    0600);
+MODULE_PARM_DESC(osd_login_prog, "Path to the osd_login upcall program");
+
+struct __auto_login {
+        char uri[OBJLAYOUT_MAX_URI_LEN];
+        char osdname[OBJLAYOUT_MAX_OSDNAME_LEN];
+        char systemid_hex[OBJLAYOUT_MAX_SYSID_HEX_LEN];
+};
+
+static int __objlayout_upcall(struct __auto_login *login)
+{
+        static char *envp[] = { "HOME=/",
+                "TERM=linux",
+                "PATH=/sbin:/usr/sbin:/bin:/usr/bin",
+                NULL
+        };
+        char *argv[8];
+        int ret;
+
+        if (unlikely(!osd_login_prog[0])) {
+                dprintk("%s: osd_login_prog is disabled\n", __func__);
+                return -EACCES;
+        }
+
+        dprintk("%s uri: %s\n", __func__, login->uri);
+        dprintk("%s osdname %s\n", __func__, login->osdname);
+        dprintk("%s systemid_hex %s\n", __func__, login->systemid_hex);
+
+        argv[0] = (char *)osd_login_prog;
+        argv[1] = "-u";
+        argv[2] = login->uri;
+        argv[3] = "-o";
+        argv[4] = login->osdname;
+        argv[5] = "-s";
+        argv[6] = login->systemid_hex;
+        argv[7] = NULL;
+
+        ret = call_usermodehelper(argv[0], argv, envp, UMH_WAIT_PROC);
+        /*
+         * 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 objlayoutdriver.osd_login_prog module parameter once
+         * the problem has been fixed.
+         */
+        if (ret == -ENOENT || ret == -EACCES) {
+                printk(KERN_ERR "PNFS-OBJ: %s was not found please set "
+                        "objlayoutdriver.osd_login_prog kernel parameter!\n",
+                        osd_login_prog);
+                osd_login_prog[0] = '\0';
+        }
+        dprintk("%s %s return value: %d\n", __func__, osd_login_prog, ret);
+
+        return ret;
+}
+
+/* Assume dest is all zeros */
+static void __copy_nfsS_and_zero_terminate(struct nfs4_string s,
+                                           char *dest, int max_len,
+                                           const char *var_name)
+{
+        if (!s.len)
+                return;
+
+        if (s.len >= max_len) {
+                pr_warn_ratelimited(
+                        "objlayout_autologin: %s: s.len(%d) >= max_len(%d)",
+                        var_name, s.len, max_len);
+                s.len = max_len - 1; /* space for null terminator */
+        }
+
+        memcpy(dest, s.data, s.len);
+}
+
+/* Assume sysid is all zeros */
+static void _sysid_2_hex(struct nfs4_string s,
+                  char sysid[OBJLAYOUT_MAX_SYSID_HEX_LEN])
+{
+        int i;
+        char *cur;
+
+        if (!s.len)
+                return;
+
+        if (s.len != OSD_SYSTEMID_LEN) {
+                pr_warn_ratelimited(
+                    "objlayout_autologin: systemid_len(%d) != OSD_SYSTEMID_LEN",
+                    s.len);
+                if (s.len > OSD_SYSTEMID_LEN)
+                        s.len = OSD_SYSTEMID_LEN;
+        }
+
+        cur = sysid;
+        for (i = 0; i < s.len; i++)
+                cur = hex_byte_pack(cur, s.data[i]);
+}
+
+int objlayout_autologin(struct pnfs_osd_deviceaddr *deviceaddr)
+{
+        int rc;
+        struct __auto_login login;
+
+        if (!deviceaddr->oda_targetaddr.ota_netaddr.r_addr.len)
+                return -ENODEV;
+
+        memset(&login, 0, sizeof(login));
+        __copy_nfsS_and_zero_terminate(
+                deviceaddr->oda_targetaddr.ota_netaddr.r_addr,
+                login.uri, sizeof(login.uri), "URI");
+
+        __copy_nfsS_and_zero_terminate(
+                deviceaddr->oda_osdname,
+                login.osdname, sizeof(login.osdname), "OSDNAME");
+
+        _sysid_2_hex(deviceaddr->oda_systemid, login.systemid_hex);
+
+        rc = __objlayout_upcall(&login);
+        if (rc > 0) /* script returns positive values */
+                rc = -ENODEV;
+
+        return rc;
+}
diff --git a/fs/nfs/objlayout/objlayout.h b/fs/nfs/objlayout/objlayout.h
index 8ec34727ed2..880ba086be9 100644
--- a/fs/nfs/objlayout/objlayout.h
+++ b/fs/nfs/objlayout/objlayout.h
@@ -184,4 +184,6 @@ extern void objlayout_encode_layoutreturn(
         struct xdr_stream *,
         const struct nfs4_layoutreturn_args *);
 
+extern int objlayout_autologin(struct pnfs_osd_deviceaddr *deviceaddr);
+
 #endif /* _OBJLAYOUT_H */
diff --git a/fs/nfs/pagelist.c b/fs/nfs/pagelist.c
index 5668f7c54c4..d21fceaa9f6 100644
--- a/fs/nfs/pagelist.c
+++ b/fs/nfs/pagelist.c
@@ -13,6 +13,7 @@
 #include <linux/file.h>
 #include <linux/sched.h>
 #include <linux/sunrpc/clnt.h>
+#include <linux/nfs.h>
 #include <linux/nfs3.h>
 #include <linux/nfs4.h>
 #include <linux/nfs_page.h>
@@ -106,36 +107,6 @@ void nfs_unlock_request(struct nfs_page *req)
         nfs_release_request(req);
 }
 
-/**
- * nfs_set_page_tag_locked - Tag a request as locked
- * @req:
- */
-int nfs_set_page_tag_locked(struct nfs_page *req)
-{
-        if (!nfs_lock_request_dontget(req))
-                return 0;
-        if (test_bit(PG_MAPPED, &req->wb_flags))
-                radix_tree_tag_set(&NFS_I(req->wb_context->dentry->d_inode)->nfs_page_tree, req->wb_index, NFS_PAGE_TAG_LOCKED);
-        return 1;
-}
-
-/**
- * nfs_clear_page_tag_locked - Clear request tag and wake up sleepers
- */
-void nfs_clear_page_tag_locked(struct nfs_page *req)
-{
-        if (test_bit(PG_MAPPED, &req->wb_flags)) {
-                struct inode *inode = req->wb_context->dentry->d_inode;
-                struct nfs_inode *nfsi = NFS_I(inode);
-
-                spin_lock(&inode->i_lock);
-                radix_tree_tag_clear(&nfsi->nfs_page_tree, req->wb_index, NFS_PAGE_TAG_LOCKED);
-                nfs_unlock_request(req);
-                spin_unlock(&inode->i_lock);
-        } else
-                nfs_unlock_request(req);
-}
-
 /*
  * nfs_clear_request - Free up all resources allocated to the request
  * @req:
@@ -425,67 +396,6 @@ void nfs_pageio_cond_complete(struct nfs_pageio_descriptor *desc, pgoff_t index)
         }
 }
 
-#define NFS_SCAN_MAXENTRIES 16
-/**
- * nfs_scan_list - Scan a list for matching requests
- * @nfsi: NFS inode
- * @dst: Destination list
- * @idx_start: lower bound of page->index to scan
- * @npages: idx_start + npages sets the upper bound to scan.
- * @tag: tag to scan for
- *
- * Moves elements from one of the inode request lists.
- * If the number of requests is set to 0, the entire address_space
- * starting at index idx_start, is scanned.
- * The requests are *not* checked to ensure that they form a contiguous set.
- * You must be holding the inode's i_lock when calling this function
- */
-int nfs_scan_list(struct nfs_inode *nfsi,
-                struct list_head *dst, pgoff_t idx_start,
-                unsigned int npages, int tag)
-{
-        struct nfs_page *pgvec[NFS_SCAN_MAXENTRIES];
-        struct nfs_page *req;
-        pgoff_t idx_end;
-        int found, i;
-        int res;
-        struct list_head *list;
-
-        res = 0;
-        if (npages == 0)
-                idx_end = ~0;
-        else
-                idx_end = idx_start + npages - 1;
-
-        for (;;) {
-                found = radix_tree_gang_lookup_tag(&nfsi->nfs_page_tree,
-                                (void **)&pgvec[0], idx_start,
-                                NFS_SCAN_MAXENTRIES, tag);
-                if (found <= 0)
-                        break;
-                for (i = 0; i < found; i++) {
-                        req = pgvec[i];
-                        if (req->wb_index > idx_end)
-                                goto out;
-                        idx_start = req->wb_index + 1;
-                        if (nfs_set_page_tag_locked(req)) {
-                                kref_get(&req->wb_kref);
-                                radix_tree_tag_clear(&nfsi->nfs_page_tree,
-                                                req->wb_index, tag);
-                                list = pnfs_choose_commit_list(req, dst);
-                                nfs_list_add_request(req, list);
-                                res++;
-                                if (res == INT_MAX)
-                                        goto out;
-                        }
-                }
-                /* for latency reduction */
-                cond_resched_lock(&nfsi->vfs_inode.i_lock);
-        }
-out:
-        return res;
-}
-
 int __init nfs_init_nfspagecache(void)
 {
         nfs_page_cachep = kmem_cache_create("nfs_page",
diff --git a/fs/nfs/pnfs.c b/fs/nfs/pnfs.c
index 17149a49006..b5d45158694 100644
--- a/fs/nfs/pnfs.c
+++ b/fs/nfs/pnfs.c
@@ -101,8 +101,8 @@ set_pnfs_layoutdriver(struct nfs_server *server, const struct nfs_fh *mntfh,
                 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);
+                printk(KERN_ERR "NFS: %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);
@@ -122,8 +122,8 @@ set_pnfs_layoutdriver(struct nfs_server *server, const struct nfs_fh *mntfh,
         server->pnfs_curr_ld = ld_type;
         if (ld_type->set_layoutdriver
             && ld_type->set_layoutdriver(server, mntfh)) {
-                printk(KERN_ERR "%s: Error initializing pNFS layout driver %u.\n",
-                                __func__, id);
+                printk(KERN_ERR "NFS: %s: Error initializing pNFS layout "
+                        "driver %u.\n", __func__, id);
                 module_put(ld_type->owner);
                 goto out_no_driver;
         }
@@ -143,11 +143,11 @@ pnfs_register_layoutdriver(struct pnfs_layoutdriver_type *ld_type)
         struct pnfs_layoutdriver_type *tmp;
 
         if (ld_type->id == 0) {
-                printk(KERN_ERR "%s id 0 is reserved\n", __func__);
+                printk(KERN_ERR "NFS: %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 "
+                printk(KERN_ERR "NFS: %s Layout driver must provide "
                        "alloc_lseg and free_lseg.\n", __func__);
                 return status;
         }
@@ -160,7 +160,7 @@ pnfs_register_layoutdriver(struct pnfs_layoutdriver_type *ld_type)
                 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",
+                printk(KERN_ERR "NFS: %s Module with id %d already loaded!\n",
                         __func__, ld_type->id);
         }
         spin_unlock(&pnfs_spinlock);
@@ -496,12 +496,12 @@ pnfs_set_layout_stateid(struct pnfs_layout_hdr *lo, const nfs4_stateid *new,
 {
         u32 oldseq, newseq;
 
-        oldseq = be32_to_cpu(lo->plh_stateid.stateid.seqid);
-        newseq = be32_to_cpu(new->stateid.seqid);
+        oldseq = be32_to_cpu(lo->plh_stateid.seqid);
+        newseq = be32_to_cpu(new->seqid);
         if ((int)(newseq - oldseq) > 0) {
-                memcpy(&lo->plh_stateid, &new->stateid, sizeof(new->stateid));
+                nfs4_stateid_copy(&lo->plh_stateid, new);
                 if (update_barrier) {
-                        u32 new_barrier = be32_to_cpu(new->stateid.seqid);
+                        u32 new_barrier = be32_to_cpu(new->seqid);
 
                         if ((int)(new_barrier - lo->plh_barrier))
                                 lo->plh_barrier = new_barrier;
@@ -525,7 +525,7 @@ 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)
+            (int)(lo->plh_barrier - be32_to_cpu(stateid->seqid)) >= 0)
                 return true;
         return lo->plh_block_lgets ||
                 test_bit(NFS_LAYOUT_DESTROYED, &lo->plh_flags) ||
@@ -549,11 +549,10 @@ pnfs_choose_layoutget_stateid(nfs4_stateid *dst, struct pnfs_layout_hdr *lo,
 
                 do {
                         seq = read_seqbegin(&open_state->seqlock);
-                        memcpy(dst->data, open_state->stateid.data,
-                               sizeof(open_state->stateid.data));
+                        nfs4_stateid_copy(dst, &open_state->stateid);
                 } while (read_seqretry(&open_state->seqlock, seq));
         } else
-                memcpy(dst->data, lo->plh_stateid.data, sizeof(lo->plh_stateid.data));
+                nfs4_stateid_copy(dst, &lo->plh_stateid);
         spin_unlock(&lo->plh_inode->i_lock);
         dprintk("<-- %s\n", __func__);
         return status;
@@ -590,7 +589,7 @@ send_layoutget(struct pnfs_layout_hdr *lo,
         max_resp_sz = server->nfs_client->cl_session->fc_attrs.max_resp_sz;
         max_pages = max_resp_sz >> PAGE_SHIFT;
 
-        pages = kzalloc(max_pages * sizeof(struct page *), gfp_flags);
+        pages = kcalloc(max_pages, sizeof(struct page *), gfp_flags);
         if (!pages)
                 goto out_err_free;
 
@@ -760,7 +759,7 @@ bool pnfs_roc_drain(struct inode *ino, u32 *barrier)
                 }
         if (!found) {
                 struct pnfs_layout_hdr *lo = nfsi->layout;
-                u32 current_seqid = be32_to_cpu(lo->plh_stateid.stateid.seqid);
+                u32 current_seqid = be32_to_cpu(lo->plh_stateid.seqid);
 
                 /* Since close does not return a layout stateid for use as
                  * a barrier, we choose the worst-case barrier.
@@ -966,8 +965,7 @@ pnfs_update_layout(struct inode *ino,
         }
 
         /* 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)) {
+        if (test_bit(NFS_LAYOUT_BULK_RECALL, &lo->plh_flags)) {
                 dprintk("%s matches recall, use MDS\n", __func__);
                 goto out_unlock;
         }
@@ -1032,7 +1030,6 @@ pnfs_layout_process(struct nfs4_layoutget *lgp)
         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;
 
         /* Inject layout blob into I/O device driver */
@@ -1048,8 +1045,7 @@ pnfs_layout_process(struct nfs4_layoutget *lgp)
         }
 
         spin_lock(&ino->i_lock);
-        if (test_bit(NFS4CLNT_LAYOUTRECALL, &clp->cl_state) ||
-            test_bit(NFS_LAYOUT_BULK_RECALL, &lo->plh_flags)) {
+        if (test_bit(NFS_LAYOUT_BULK_RECALL, &lo->plh_flags)) {
                 dprintk("%s forget reply due to recall\n", __func__);
                 goto out_forget_reply;
         }
@@ -1214,6 +1210,7 @@ void pnfs_ld_write_done(struct nfs_write_data *data)
                 }
                 data->task.tk_status = pnfs_write_done_resend_to_mds(data->inode, &data->pages);
         }
+        put_lseg(data->lseg);
         data->mds_ops->rpc_release(data);
 }
 EXPORT_SYMBOL_GPL(pnfs_ld_write_done);
@@ -1227,6 +1224,7 @@ pnfs_write_through_mds(struct nfs_pageio_descriptor *desc,
                 nfs_list_add_request(data->req, &desc->pg_list);
         nfs_pageio_reset_write_mds(desc);
         desc->pg_recoalesce = 1;
+        put_lseg(data->lseg);
         nfs_writedata_release(data);
 }
 
@@ -1327,6 +1325,7 @@ void pnfs_ld_read_done(struct nfs_read_data *data)
                 data->mds_ops->rpc_call_done(&data->task, data);
         } else
                 pnfs_ld_handle_read_error(data);
+        put_lseg(data->lseg);
         data->mds_ops->rpc_release(data);
 }
 EXPORT_SYMBOL_GPL(pnfs_ld_read_done);
@@ -1530,8 +1529,7 @@ pnfs_layoutcommit_inode(struct inode *inode, bool sync)
         end_pos = nfsi->layout->plh_lwb;
         nfsi->layout->plh_lwb = 0;
 
-        memcpy(&data->args.stateid.data, nfsi->layout->plh_stateid.data,
-                sizeof(nfsi->layout->plh_stateid.data));
+        nfs4_stateid_copy(&data->args.stateid, &nfsi->layout->plh_stateid);
         spin_unlock(&inode->i_lock);
 
         data->args.inode = inode;
diff --git a/fs/nfs/pnfs.h b/fs/nfs/pnfs.h
index 53d593a0a4f..442ebf68eee 100644
--- a/fs/nfs/pnfs.h
+++ b/fs/nfs/pnfs.h
@@ -94,11 +94,10 @@ struct pnfs_layoutdriver_type {
         const struct nfs_pageio_ops *pg_read_ops;
         const struct nfs_pageio_ops *pg_write_ops;
 
-        /* Returns true if layoutdriver wants to divert this request to
-         * driver's commit routine.
-         */
-        bool (*mark_pnfs_commit)(struct pnfs_layout_segment *lseg);
-        struct list_head * (*choose_commit_list) (struct nfs_page *req);
+        void (*mark_request_commit) (struct nfs_page *req,
+                                        struct pnfs_layout_segment *lseg);
+        void (*clear_request_commit) (struct nfs_page *req);
+        int (*scan_commit_lists) (struct inode *inode, int max, spinlock_t *lock);
         int (*commit_pagelist)(struct inode *inode, struct list_head *mds_pages, int how);
 
         /*
@@ -229,7 +228,6 @@ struct nfs4_deviceid_node {
         atomic_t                        ref;
 };
 
-void nfs4_print_deviceid(const struct nfs4_deviceid *dev_id);
 struct nfs4_deviceid_node *nfs4_find_get_deviceid(const struct pnfs_layoutdriver_type *, const struct nfs_client *, const struct nfs4_deviceid *);
 void nfs4_delete_deviceid(const struct pnfs_layoutdriver_type *, const struct nfs_client *, const struct nfs4_deviceid *);
 void nfs4_init_deviceid_node(struct nfs4_deviceid_node *,
@@ -262,20 +260,6 @@ static inline int pnfs_enabled_sb(struct nfs_server *nfss)
         return nfss->pnfs_curr_ld != NULL;
 }
 
-static inline void
-pnfs_mark_request_commit(struct nfs_page *req, struct pnfs_layout_segment *lseg)
-{
-        if (lseg) {
-                struct pnfs_layoutdriver_type *ld;
-
-                ld = NFS_SERVER(req->wb_page->mapping->host)->pnfs_curr_ld;
-                if (ld->mark_pnfs_commit && ld->mark_pnfs_commit(lseg)) {
-                        set_bit(PG_PNFS_COMMIT, &req->wb_flags);
-                        req->wb_commit_lseg = get_lseg(lseg);
-                }
-        }
-}
-
 static inline int
 pnfs_commit_list(struct inode *inode, struct list_head *mds_pages, int how)
 {
@@ -284,27 +268,42 @@ pnfs_commit_list(struct inode *inode, struct list_head *mds_pages, int how)
         return NFS_SERVER(inode)->pnfs_curr_ld->commit_pagelist(inode, mds_pages, how);
 }
 
-static inline struct list_head *
-pnfs_choose_commit_list(struct nfs_page *req, struct list_head *mds)
+static inline bool
+pnfs_mark_request_commit(struct nfs_page *req, struct pnfs_layout_segment *lseg)
 {
-        struct list_head *rv;
+        struct inode *inode = req->wb_context->dentry->d_inode;
+        struct pnfs_layoutdriver_type *ld = NFS_SERVER(inode)->pnfs_curr_ld;
 
-        if (test_and_clear_bit(PG_PNFS_COMMIT, &req->wb_flags)) {
-                struct inode *inode = req->wb_commit_lseg->pls_layout->plh_inode;
+        if (lseg == NULL || ld->mark_request_commit == NULL)
+                return false;
+        ld->mark_request_commit(req, lseg);
+        return true;
+}
 
-                set_bit(NFS_INO_PNFS_COMMIT, &NFS_I(inode)->flags);
-                rv = NFS_SERVER(inode)->pnfs_curr_ld->choose_commit_list(req);
-                /* matched by ref taken when PG_PNFS_COMMIT is set */
-                put_lseg(req->wb_commit_lseg);
-        } else
-                rv = mds;
-        return rv;
+static inline bool
+pnfs_clear_request_commit(struct nfs_page *req)
+{
+        struct inode *inode = req->wb_context->dentry->d_inode;
+        struct pnfs_layoutdriver_type *ld = NFS_SERVER(inode)->pnfs_curr_ld;
+
+        if (ld == NULL || ld->clear_request_commit == NULL)
+                return false;
+        ld->clear_request_commit(req);
+        return true;
 }
 
-static inline void pnfs_clear_request_commit(struct nfs_page *req)
+static inline int
+pnfs_scan_commit_lists(struct inode *inode, int max, spinlock_t *lock)
 {
-        if (test_and_clear_bit(PG_PNFS_COMMIT, &req->wb_flags))
-                put_lseg(req->wb_commit_lseg);
+        struct pnfs_layoutdriver_type *ld = NFS_SERVER(inode)->pnfs_curr_ld;
+        int ret;
+
+        if (ld == NULL || ld->scan_commit_lists == NULL)
+                return 0;
+        ret = ld->scan_commit_lists(inode, max, lock);
+        if (ret != 0)
+                set_bit(NFS_INO_PNFS_COMMIT, &NFS_I(inode)->flags);
+        return ret;
 }
 
 /* Should the pNFS client commit and return the layout upon a setattr */
@@ -328,6 +327,13 @@ static inline int pnfs_return_layout(struct inode *ino)
         return 0;
 }
 
+#ifdef NFS_DEBUG
+void nfs4_print_deviceid(const struct nfs4_deviceid *dev_id);
+#else
+static inline void nfs4_print_deviceid(const struct nfs4_deviceid *dev_id)
+{
+}
+#endif /* NFS_DEBUG */
 #else  /* CONFIG_NFS_V4_1 */
 
 static inline void pnfs_destroy_all_layouts(struct nfs_client *clp)
@@ -400,35 +406,35 @@ static inline bool pnfs_pageio_init_write(struct nfs_pageio_descriptor *pgio, st
         return false;
 }
 
-static inline void
-pnfs_mark_request_commit(struct nfs_page *req, struct pnfs_layout_segment *lseg)
-{
-}
-
 static inline int
 pnfs_commit_list(struct inode *inode, struct list_head *mds_pages, int how)
 {
         return PNFS_NOT_ATTEMPTED;
 }
 
-static inline struct list_head *
-pnfs_choose_commit_list(struct nfs_page *req, struct list_head *mds)
+static inline bool
+pnfs_mark_request_commit(struct nfs_page *req, struct pnfs_layout_segment *lseg)
 {
-        return mds;
+        return false;
 }
 
-static inline void pnfs_clear_request_commit(struct nfs_page *req)
+static inline bool
+pnfs_clear_request_commit(struct nfs_page *req)
 {
+        return false;
 }
 
-static inline int pnfs_layoutcommit_inode(struct inode *inode, bool sync)
+static inline int
+pnfs_scan_commit_lists(struct inode *inode, int max, spinlock_t *lock)
 {
         return 0;
 }
 
-static inline void nfs4_deviceid_purge_client(struct nfs_client *ncl)
+static inline int pnfs_layoutcommit_inode(struct inode *inode, bool sync)
 {
+        return 0;
 }
+
 #endif /* CONFIG_NFS_V4_1 */
 
 #endif /* FS_NFS_PNFS_H */
diff --git a/fs/nfs/pnfs_dev.c b/fs/nfs/pnfs_dev.c
index 4f359d2a26e..73f701f1f4d 100644
--- a/fs/nfs/pnfs_dev.c
+++ b/fs/nfs/pnfs_dev.c
@@ -43,6 +43,7 @@
 static struct hlist_head nfs4_deviceid_cache[NFS4_DEVICE_ID_HASH_SIZE];
 static DEFINE_SPINLOCK(nfs4_deviceid_lock);
 
+#ifdef NFS_DEBUG
 void
 nfs4_print_deviceid(const struct nfs4_deviceid *id)
 {
@@ -52,6 +53,7 @@ nfs4_print_deviceid(const struct nfs4_deviceid *id)
                 p[0], p[1], p[2], p[3]);
 }
 EXPORT_SYMBOL_GPL(nfs4_print_deviceid);
+#endif
 
 static inline u32
 nfs4_deviceid_hash(const struct nfs4_deviceid *id)
@@ -92,7 +94,7 @@ _lookup_deviceid(const struct pnfs_layoutdriver_type *ld,
  * @clp nfs_client associated with deviceid
  * @id deviceid to look up
  */
-struct nfs4_deviceid_node *
+static struct nfs4_deviceid_node *
 _find_get_deviceid(const struct pnfs_layoutdriver_type *ld,
                    const struct nfs_client *clp, const struct nfs4_deviceid *id,
                    long hash)
diff --git a/fs/nfs/proc.c b/fs/nfs/proc.c
index 0c672588fe5..b63b6f4d14f 100644
--- a/fs/nfs/proc.c
+++ b/fs/nfs/proc.c
@@ -358,6 +358,11 @@ nfs_proc_unlink_setup(struct rpc_message *msg, struct inode *dir)
         msg->rpc_proc = &nfs_procedures[NFSPROC_REMOVE];
 }
 
+static void nfs_proc_unlink_rpc_prepare(struct rpc_task *task, struct nfs_unlinkdata *data)
+{
+        rpc_call_start(task);
+}
+
 static int nfs_proc_unlink_done(struct rpc_task *task, struct inode *dir)
 {
         if (nfs_async_handle_expired_key(task))
@@ -372,6 +377,11 @@ nfs_proc_rename_setup(struct rpc_message *msg, struct inode *dir)
         msg->rpc_proc = &nfs_procedures[NFSPROC_RENAME];
 }
 
+static void nfs_proc_rename_rpc_prepare(struct rpc_task *task, struct nfs_renamedata *data)
+{
+        rpc_call_start(task);
+}
+
 static int
 nfs_proc_rename_done(struct rpc_task *task, struct inode *old_dir,
                      struct inode *new_dir)
@@ -651,6 +661,11 @@ static void nfs_proc_read_setup(struct nfs_read_data *data, struct rpc_message *
         msg->rpc_proc = &nfs_procedures[NFSPROC_READ];
 }
 
+static void nfs_proc_read_rpc_prepare(struct rpc_task *task, struct nfs_read_data *data)
+{
+        rpc_call_start(task);
+}
+
 static int nfs_write_done(struct rpc_task *task, struct nfs_write_data *data)
 {
         if (nfs_async_handle_expired_key(task))
@@ -668,6 +683,11 @@ static void nfs_proc_write_setup(struct nfs_write_data *data, struct rpc_message
         msg->rpc_proc = &nfs_procedures[NFSPROC_WRITE];
 }
 
+static void nfs_proc_write_rpc_prepare(struct rpc_task *task, struct nfs_write_data *data)
+{
+        rpc_call_start(task);
+}
+
 static void
 nfs_proc_commit_setup(struct nfs_write_data *data, struct rpc_message *msg)
 {
@@ -721,9 +741,11 @@ const struct nfs_rpc_ops nfs_v2_clientops = {
         .create         = nfs_proc_create,
         .remove         = nfs_proc_remove,
         .unlink_setup   = nfs_proc_unlink_setup,
+        .unlink_rpc_prepare = nfs_proc_unlink_rpc_prepare,
         .unlink_done    = nfs_proc_unlink_done,
         .rename         = nfs_proc_rename,
         .rename_setup   = nfs_proc_rename_setup,
+        .rename_rpc_prepare = nfs_proc_rename_rpc_prepare,
         .rename_done    = nfs_proc_rename_done,
         .link           = nfs_proc_link,
         .symlink        = nfs_proc_symlink,
@@ -736,8 +758,10 @@ const struct nfs_rpc_ops nfs_v2_clientops = {
         .pathconf       = nfs_proc_pathconf,
         .decode_dirent  = nfs2_decode_dirent,
         .read_setup     = nfs_proc_read_setup,
+        .read_rpc_prepare = nfs_proc_read_rpc_prepare,
         .read_done      = nfs_read_done,
         .write_setup    = nfs_proc_write_setup,
+        .write_rpc_prepare = nfs_proc_write_rpc_prepare,
         .write_done     = nfs_write_done,
         .commit_setup   = nfs_proc_commit_setup,
         .lock           = nfs_proc_lock,
diff --git a/fs/nfs/read.c b/fs/nfs/read.c
index cfa175c223d..cc1f758a7ee 100644
--- a/fs/nfs/read.c
+++ b/fs/nfs/read.c
@@ -66,7 +66,6 @@ void nfs_readdata_free(struct nfs_read_data *p)
 
 void nfs_readdata_release(struct nfs_read_data *rdata)
 {
-        put_lseg(rdata->lseg);
         put_nfs_open_context(rdata->args.context);
         nfs_readdata_free(rdata);
 }
@@ -465,23 +464,14 @@ static void nfs_readpage_release_partial(void *calldata)
         nfs_readdata_release(calldata);
 }
 
-#if defined(CONFIG_NFS_V4_1)
 void nfs_read_prepare(struct rpc_task *task, void *calldata)
 {
         struct nfs_read_data *data = calldata;
-
-        if (nfs4_setup_sequence(NFS_SERVER(data->inode),
-                                &data->args.seq_args, &data->res.seq_res,
-                                0, task))
-                return;
-        rpc_call_start(task);
+        NFS_PROTO(data->inode)->read_rpc_prepare(task, data);
 }
-#endif /* CONFIG_NFS_V4_1 */
 
 static const struct rpc_call_ops nfs_read_partial_ops = {
-#if defined(CONFIG_NFS_V4_1)
         .rpc_call_prepare = nfs_read_prepare,
-#endif /* CONFIG_NFS_V4_1 */
         .rpc_call_done = nfs_readpage_result_partial,
         .rpc_release = nfs_readpage_release_partial,
 };
@@ -545,9 +535,7 @@ static void nfs_readpage_release_full(void *calldata)
 }
 
 static const struct rpc_call_ops nfs_read_full_ops = {
-#if defined(CONFIG_NFS_V4_1)
         .rpc_call_prepare = nfs_read_prepare,
-#endif /* CONFIG_NFS_V4_1 */
         .rpc_call_done = nfs_readpage_result_full,
         .rpc_release = nfs_readpage_release_full,
 };
diff --git a/fs/nfs/super.c b/fs/nfs/super.c
index 3dfa4f112c0..ccc4cdb1efe 100644
--- a/fs/nfs/super.c
+++ b/fs/nfs/super.c
@@ -52,6 +52,8 @@
 #include <linux/nfs_xdr.h>
 #include <linux/magic.h>
 #include <linux/parser.h>
+#include <linux/nsproxy.h>
+#include <linux/rcupdate.h>
 
 #include <asm/system.h>
 #include <asm/uaccess.h>
@@ -79,7 +81,6 @@ enum {
         Opt_cto, Opt_nocto,
         Opt_ac, Opt_noac,
         Opt_lock, Opt_nolock,
-        Opt_v2, Opt_v3, Opt_v4,
         Opt_udp, Opt_tcp, Opt_rdma,
         Opt_acl, Opt_noacl,
         Opt_rdirplus, Opt_nordirplus,
@@ -97,10 +98,10 @@ enum {
         Opt_namelen,
         Opt_mountport,
         Opt_mountvers,
-        Opt_nfsvers,
         Opt_minorversion,
 
         /* Mount options that take string arguments */
+        Opt_nfsvers,
         Opt_sec, Opt_proto, Opt_mountproto, Opt_mounthost,
         Opt_addr, Opt_mountaddr, Opt_clientaddr,
         Opt_lookupcache,
@@ -132,9 +133,6 @@ static const match_table_t nfs_mount_option_tokens = {
         { Opt_noac, "noac" },
         { Opt_lock, "lock" },
         { Opt_nolock, "nolock" },
-        { Opt_v2, "v2" },
-        { Opt_v3, "v3" },
-        { Opt_v4, "v4" },
         { Opt_udp, "udp" },
         { Opt_tcp, "tcp" },
         { Opt_rdma, "rdma" },
@@ -163,9 +161,10 @@ static const match_table_t nfs_mount_option_tokens = {
         { Opt_namelen, "namlen=%s" },
         { Opt_mountport, "mountport=%s" },
         { Opt_mountvers, "mountvers=%s" },
+        { Opt_minorversion, "minorversion=%s" },
+
         { Opt_nfsvers, "nfsvers=%s" },
         { Opt_nfsvers, "vers=%s" },
-        { Opt_minorversion, "minorversion=%s" },
 
         { Opt_sec, "sec=%s" },
         { Opt_proto, "proto=%s" },
@@ -179,6 +178,9 @@ static const match_table_t nfs_mount_option_tokens = {
         { Opt_fscache_uniq, "fsc=%s" },
         { Opt_local_lock, "local_lock=%s" },
 
+        /* The following needs to be listed after all other options */
+        { Opt_nfsvers, "v%s" },
+
         { Opt_err, NULL }
 };
 
@@ -259,6 +261,22 @@ static match_table_t nfs_local_lock_tokens = {
         { Opt_local_lock_err, NULL }
 };
 
+enum {
+        Opt_vers_2, Opt_vers_3, Opt_vers_4, Opt_vers_4_0,
+        Opt_vers_4_1,
+
+        Opt_vers_err
+};
+
+static match_table_t nfs_vers_tokens = {
+        { Opt_vers_2, "2" },
+        { Opt_vers_3, "3" },
+        { Opt_vers_4, "4" },
+        { Opt_vers_4_0, "4.0" },
+        { Opt_vers_4_1, "4.1" },
+
+        { Opt_vers_err, NULL }
+};
 
 static void nfs_umount_begin(struct super_block *);
 static int  nfs_statfs(struct dentry *, struct kstatfs *);
@@ -620,7 +638,6 @@ static void nfs_show_nfsv4_options(struct seq_file *m, struct nfs_server *nfss,
         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,
@@ -629,6 +646,15 @@ static void nfs_show_nfsv4_options(struct seq_file *m, struct nfs_server *nfss,
 }
 #endif
 
+static void nfs_show_nfs_version(struct seq_file *m,
+                unsigned int version,
+                unsigned int minorversion)
+{
+        seq_printf(m, ",vers=%u", version);
+        if (version == 4)
+                seq_printf(m, ".%u", minorversion);
+}
+
 /*
  * Describe the mount options in force on this server representation
  */
@@ -656,7 +682,7 @@ static void nfs_show_mount_options(struct seq_file *m, struct nfs_server *nfss,
         u32 version = clp->rpc_ops->version;
         int local_flock, local_fcntl;
 
-        seq_printf(m, ",vers=%u", version);
+        nfs_show_nfs_version(m, version, clp->cl_minorversion);
         seq_printf(m, ",rsize=%u", nfss->rsize);
         seq_printf(m, ",wsize=%u", nfss->wsize);
         if (nfss->bsize != 0)
@@ -676,8 +702,10 @@ static void nfs_show_mount_options(struct seq_file *m, struct nfs_server *nfss,
                 else
                         seq_puts(m, nfs_infop->nostr);
         }
+        rcu_read_lock();
         seq_printf(m, ",proto=%s",
                    rpc_peeraddr2str(nfss->client, RPC_DISPLAY_NETID));
+        rcu_read_unlock();
         if (version == 4) {
                 if (nfss->port != NFS_PORT)
                         seq_printf(m, ",port=%u", nfss->port);
@@ -726,9 +754,11 @@ static int nfs_show_options(struct seq_file *m, struct dentry *root)
 
         nfs_show_mount_options(m, nfss, 0);
 
+        rcu_read_lock();
         seq_printf(m, ",addr=%s",
                         rpc_peeraddr2str(nfss->nfs_client->cl_rpcclient,
                                                         RPC_DISPLAY_ADDR));
+        rcu_read_unlock();
 
         return 0;
 }
@@ -745,7 +775,6 @@ static void show_sessions(struct seq_file *m, struct nfs_server *server) {}
 #endif
 #endif
 
-#ifdef CONFIG_NFS_V4
 #ifdef CONFIG_NFS_V4_1
 static void show_pnfs(struct seq_file *m, struct nfs_server *server)
 {
@@ -755,9 +784,26 @@ static void show_pnfs(struct seq_file *m, struct nfs_server *server)
         else
                 seq_printf(m, "not configured");
 }
+
+static void show_implementation_id(struct seq_file *m, struct nfs_server *nfss)
+{
+        if (nfss->nfs_client && nfss->nfs_client->impl_id) {
+                struct nfs41_impl_id *impl_id = nfss->nfs_client->impl_id;
+                seq_printf(m, "\n\timpl_id:\tname='%s',domain='%s',"
+                           "date='%llu,%u'",
+                           impl_id->name, impl_id->domain,
+                           impl_id->date.seconds, impl_id->date.nseconds);
+        }
+}
 #else
-static void show_pnfs(struct seq_file *m, struct nfs_server *server) {}
+#ifdef CONFIG_NFS_V4
+static void show_pnfs(struct seq_file *m, struct nfs_server *server)
+{
+}
 #endif
+static void show_implementation_id(struct seq_file *m, struct nfs_server *nfss)
+{
+}
 #endif
 
 static int nfs_show_devname(struct seq_file *m, struct dentry *root)
@@ -806,6 +852,8 @@ static int nfs_show_stats(struct seq_file *m, struct dentry *root)
 
         seq_printf(m, "\n\tage:\t%lu", (jiffies - nfss->mount_time) / HZ);
 
+        show_implementation_id(m, nfss);
+
         seq_printf(m, "\n\tcaps:\t");
         seq_printf(m, "caps=0x%x", nfss->caps);
         seq_printf(m, ",wtmult=%u", nfss->wtmult);
@@ -908,6 +956,7 @@ static struct nfs_parsed_mount_data *nfs_alloc_parsed_mount_data(unsigned int ve
                 data->auth_flavor_len   = 1;
                 data->version           = version;
                 data->minorversion      = 0;
+                data->net               = current->nsproxy->net_ns;
                 security_init_mnt_opts(&data->lsm_opts);
         }
         return data;
@@ -1052,6 +1101,40 @@ static int nfs_parse_security_flavors(char *value,
         return 1;
 }
 
+static int nfs_parse_version_string(char *string,
+                struct nfs_parsed_mount_data *mnt,
+                substring_t *args)
+{
+        mnt->flags &= ~NFS_MOUNT_VER3;
+        switch (match_token(string, nfs_vers_tokens, args)) {
+        case Opt_vers_2:
+                mnt->version = 2;
+                break;
+        case Opt_vers_3:
+                mnt->flags |= NFS_MOUNT_VER3;
+                mnt->version = 3;
+                break;
+        case Opt_vers_4:
+                /* Backward compatibility option. In future,
+                 * the mount program should always supply
+                 * a NFSv4 minor version number.
+                 */
+                mnt->version = 4;
+                break;
+        case Opt_vers_4_0:
+                mnt->version = 4;
+                mnt->minorversion = 0;
+                break;
+        case Opt_vers_4_1:
+                mnt->version = 4;
+                mnt->minorversion = 1;
+                break;
+        default:
+                return 0;
+        }
+        return 1;
+}
+
 static int nfs_get_option_str(substring_t args[], char **option)
 {
         kfree(*option);
@@ -1157,18 +1240,6 @@ static int nfs_parse_mount_options(char *raw,
                         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;
                         mnt->nfs_server.protocol = XPRT_TRANSPORT_UDP;
@@ -1295,26 +1366,6 @@ static int nfs_parse_mount_options(char *raw,
                                 goto out_invalid_value;
                         mnt->mount_server.version = option;
                         break;
-                case Opt_nfsvers:
-                        if (nfs_get_option_ul(args, &option))
-                                goto out_invalid_value;
-                        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 (nfs_get_option_ul(args, &option))
                                 goto out_invalid_value;
@@ -1326,6 +1377,15 @@ static int nfs_parse_mount_options(char *raw,
                 /*
                  * options that take text values
                  */
+                case Opt_nfsvers:
+                        string = match_strdup(args);
+                        if (string == NULL)
+                                goto out_nomem;
+                        rc = nfs_parse_version_string(string, mnt, args);
+                        kfree(string);
+                        if (!rc)
+                                goto out_invalid_value;
+                        break;
                 case Opt_sec:
                         string = match_strdup(args);
                         if (string == NULL)
@@ -1405,7 +1465,7 @@ static int nfs_parse_mount_options(char *raw,
                         if (string == NULL)
                                 goto out_nomem;
                         mnt->nfs_server.addrlen =
-                                rpc_pton(string, strlen(string),
+                                rpc_pton(mnt->net, string, strlen(string),
                                         (struct sockaddr *)
                                         &mnt->nfs_server.address,
                                         sizeof(mnt->nfs_server.address));
@@ -1427,7 +1487,7 @@ static int nfs_parse_mount_options(char *raw,
                         if (string == NULL)
                                 goto out_nomem;
                         mnt->mount_server.addrlen =
-                                rpc_pton(string, strlen(string),
+                                rpc_pton(mnt->net, string, strlen(string),
                                         (struct sockaddr *)
                                         &mnt->mount_server.address,
                                         sizeof(mnt->mount_server.address));
@@ -1516,6 +1576,9 @@ static int nfs_parse_mount_options(char *raw,
         if (!sloppy && invalid_option)
                 return 0;
 
+        if (mnt->minorversion && mnt->version != 4)
+                goto out_minorversion_mismatch;
+
         /*
          * verify that any proto=/mountproto= options match the address
          * familiies in the addr=/mountaddr= options.
@@ -1549,6 +1612,10 @@ out_invalid_address:
 out_invalid_value:
         printk(KERN_INFO "NFS: bad mount option value specified: %s\n", p);
         return 0;
+out_minorversion_mismatch:
+        printk(KERN_INFO "NFS: mount option vers=%u does not support "
+                         "minorversion=%u\n", mnt->version, mnt->minorversion);
+        return 0;
 out_nomem:
         printk(KERN_INFO "NFS: not enough memory to parse option\n");
         return 0;
@@ -1622,6 +1689,7 @@ static int nfs_try_mount(struct nfs_parsed_mount_data *args,
                 .noresvport     = args->flags & NFS_MOUNT_NORESVPORT,
                 .auth_flav_len  = &server_authlist_len,
                 .auth_flavs     = server_authlist,
+                .net            = args->net,
         };
         int status;
 
@@ -2047,7 +2115,7 @@ static inline void nfs_initialise_sb(struct super_block *sb)
 
         /* We probably want something more informative here */
         snprintf(sb->s_id, sizeof(sb->s_id),
-                 "%x:%x", MAJOR(sb->s_dev), MINOR(sb->s_dev));
+                 "%u:%u", MAJOR(sb->s_dev), MINOR(sb->s_dev));
 
         if (sb->s_blocksize == 0)
                 sb->s_blocksize = nfs_block_bits(server->wsize,
@@ -2499,12 +2567,6 @@ static int nfs4_validate_text_mount_data(void *options,
                 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,
@@ -2663,8 +2725,7 @@ nfs4_remote_mount(struct file_system_type *fs_type, int flags,
         if (!s->s_root) {
                 /* initial superblock/root creation */
                 nfs4_fill_super(s);
-                nfs_fscache_get_super_cookie(
-                        s, data ? data->fscache_uniq : NULL, NULL);
+                nfs_fscache_get_super_cookie(s, data->fscache_uniq, NULL);
         }
 
         mntroot = nfs4_get_root(s, mntfh, dev_name);
diff --git a/fs/nfs/sysctl.c b/fs/nfs/sysctl.c
index 978aaeb8a09..ad4d2e787b2 100644
--- a/fs/nfs/sysctl.c
+++ b/fs/nfs/sysctl.c
@@ -32,7 +32,6 @@ static ctl_table nfs_cb_sysctls[] = {
                 .extra1 = (int *)&nfs_set_port_min,
                 .extra2 = (int *)&nfs_set_port_max,
         },
-#ifndef CONFIG_NFS_USE_NEW_IDMAPPER
         {
                 .procname = "idmap_cache_timeout",
                 .data = &nfs_idmap_cache_timeout,
@@ -40,7 +39,6 @@ static ctl_table nfs_cb_sysctls[] = {
                 .mode = 0644,
                 .proc_handler = proc_dointvec_jiffies,
         },
-#endif /* CONFIG_NFS_USE_NEW_IDMAPPER */
 #endif
         {
                 .procname       = "nfs_mountpoint_timeout",
diff --git a/fs/nfs/unlink.c b/fs/nfs/unlink.c
index 4f9319a2e56..3210a03342f 100644
--- a/fs/nfs/unlink.c
+++ b/fs/nfs/unlink.c
@@ -20,15 +20,6 @@
 #include "iostat.h"
 #include "delegation.h"
 
-struct nfs_unlinkdata {
-        struct hlist_node list;
-        struct nfs_removeargs args;
-        struct nfs_removeres res;
-        struct inode *dir;
-        struct rpc_cred *cred;
-        struct nfs_fattr dir_attr;
-};
-
 /**
  * nfs_free_unlinkdata - release data from a sillydelete operation.
  * @data: pointer to unlink structure.
@@ -107,25 +98,16 @@ static void nfs_async_unlink_release(void *calldata)
         nfs_sb_deactive(sb);
 }
 
-#if defined(CONFIG_NFS_V4_1)
-void nfs_unlink_prepare(struct rpc_task *task, void *calldata)
+static 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, &data->args.seq_args,
-                                &data->res.seq_res, 1, task))
-                return;
-        rpc_call_start(task);
+        NFS_PROTO(data->dir)->unlink_rpc_prepare(task, data);
 }
-#endif /* CONFIG_NFS_V4_1 */
 
 static const struct rpc_call_ops nfs_unlink_ops = {
         .rpc_call_done = nfs_async_unlink_done,
         .rpc_release = nfs_async_unlink_release,
-#if defined(CONFIG_NFS_V4_1)
         .rpc_call_prepare = nfs_unlink_prepare,
-#endif /* CONFIG_NFS_V4_1 */
 };
 
 static int nfs_do_call_unlink(struct dentry *parent, struct inode *dir, struct nfs_unlinkdata *data)
@@ -341,18 +323,6 @@ nfs_cancel_async_unlink(struct dentry *dentry)
         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
@@ -403,25 +373,16 @@ static void nfs_async_rename_release(void *calldata)
         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);
+        NFS_PROTO(data->old_dir)->rename_rpc_prepare(task, data);
 }
-#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 */
 };
 
 /**
diff --git a/fs/nfs/write.c b/fs/nfs/write.c
index 834f0fe96f8..2c68818f68a 100644
--- a/fs/nfs/write.c
+++ b/fs/nfs/write.c
@@ -100,7 +100,6 @@ void nfs_writedata_free(struct nfs_write_data *p)
 
 void nfs_writedata_release(struct nfs_write_data *wdata)
 {
-        put_lseg(wdata->lseg);
         put_nfs_open_context(wdata->args.context);
         nfs_writedata_free(wdata);
 }
@@ -236,10 +235,10 @@ static struct nfs_page *nfs_find_and_lock_request(struct page *page, bool nonblo
                 req = nfs_page_find_request_locked(page);
                 if (req == NULL)
                         break;
-                if (nfs_set_page_tag_locked(req))
+                if (nfs_lock_request_dontget(req))
                         break;
                 /* Note: If we hold the page lock, as is the case in nfs_writepage,
-                 *       then the call to nfs_set_page_tag_locked() will always
+                 *       then the call to nfs_lock_request_dontget() will always
                  *       succeed provided that someone hasn't already marked the
                  *       request as dirty (in which case we don't care).
                  */
@@ -375,21 +374,14 @@ out_err:
 /*
  * Insert a write request into an inode
  */
-static int nfs_inode_add_request(struct inode *inode, struct nfs_page *req)
+static void nfs_inode_add_request(struct inode *inode, struct nfs_page *req)
 {
         struct nfs_inode *nfsi = NFS_I(inode);
-        int error;
-
-        error = radix_tree_preload(GFP_NOFS);
-        if (error != 0)
-                goto out;
 
         /* Lock the request! */
         nfs_lock_request_dontget(req);
 
         spin_lock(&inode->i_lock);
-        error = radix_tree_insert(&nfsi->nfs_page_tree, req->wb_index, req);
-        BUG_ON(error);
         if (!nfsi->npages && nfs_have_delegation(inode, FMODE_WRITE))
                 inode->i_version++;
         set_bit(PG_MAPPED, &req->wb_flags);
@@ -397,12 +389,7 @@ static int nfs_inode_add_request(struct inode *inode, struct nfs_page *req)
         set_page_private(req->wb_page, (unsigned long)req);
         nfsi->npages++;
         kref_get(&req->wb_kref);
-        radix_tree_tag_set(&nfsi->nfs_page_tree, req->wb_index,
-                                NFS_PAGE_TAG_LOCKED);
         spin_unlock(&inode->i_lock);
-        radix_tree_preload_end();
-out:
-        return error;
 }
 
 /*
@@ -419,7 +406,6 @@ static void nfs_inode_remove_request(struct nfs_page *req)
         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--;
         spin_unlock(&inode->i_lock);
         nfs_release_request(req);
@@ -432,39 +418,90 @@ nfs_mark_request_dirty(struct nfs_page *req)
 }
 
 #if defined(CONFIG_NFS_V3) || defined(CONFIG_NFS_V4)
-/*
- * Add a request to the inode's commit list.
+/**
+ * nfs_request_add_commit_list - add request to a commit list
+ * @req: pointer to a struct nfs_page
+ * @head: commit list head
+ *
+ * This sets the PG_CLEAN bit, updates the inode global count of
+ * number of outstanding requests requiring a commit as well as
+ * the MM page stats.
+ *
+ * The caller must _not_ hold the inode->i_lock, but must be
+ * holding the nfs_page lock.
  */
-static void
-nfs_mark_request_commit(struct nfs_page *req, struct pnfs_layout_segment *lseg)
+void
+nfs_request_add_commit_list(struct nfs_page *req, struct list_head *head)
 {
         struct inode *inode = req->wb_context->dentry->d_inode;
-        struct nfs_inode *nfsi = NFS_I(inode);
 
-        spin_lock(&inode->i_lock);
         set_bit(PG_CLEAN, &(req)->wb_flags);
-        radix_tree_tag_set(&nfsi->nfs_page_tree,
-                        req->wb_index,
-                        NFS_PAGE_TAG_COMMIT);
-        nfsi->ncommit++;
+        spin_lock(&inode->i_lock);
+        nfs_list_add_request(req, head);
+        NFS_I(inode)->ncommit++;
         spin_unlock(&inode->i_lock);
-        pnfs_mark_request_commit(req, lseg);
         inc_zone_page_state(req->wb_page, NR_UNSTABLE_NFS);
         inc_bdi_stat(req->wb_page->mapping->backing_dev_info, BDI_RECLAIMABLE);
         __mark_inode_dirty(inode, I_DIRTY_DATASYNC);
 }
+EXPORT_SYMBOL_GPL(nfs_request_add_commit_list);
 
-static int
+/**
+ * nfs_request_remove_commit_list - Remove request from a commit list
+ * @req: pointer to a nfs_page
+ *
+ * This clears the PG_CLEAN bit, and updates the inode global count of
+ * number of outstanding requests requiring a commit
+ * It does not update the MM page stats.
+ *
+ * The caller _must_ hold the inode->i_lock and the nfs_page lock.
+ */
+void
+nfs_request_remove_commit_list(struct nfs_page *req)
+{
+        struct inode *inode = req->wb_context->dentry->d_inode;
+
+        if (!test_and_clear_bit(PG_CLEAN, &(req)->wb_flags))
+                return;
+        nfs_list_remove_request(req);
+        NFS_I(inode)->ncommit--;
+}
+EXPORT_SYMBOL_GPL(nfs_request_remove_commit_list);
+
+
+/*
+ * Add a request to the inode's commit list.
+ */
+static void
+nfs_mark_request_commit(struct nfs_page *req, struct pnfs_layout_segment *lseg)
+{
+        struct inode *inode = req->wb_context->dentry->d_inode;
+
+        if (pnfs_mark_request_commit(req, lseg))
+                return;
+        nfs_request_add_commit_list(req, &NFS_I(inode)->commit_list);
+}
+
+static void
+nfs_clear_page_commit(struct page *page)
+{
+        dec_zone_page_state(page, NR_UNSTABLE_NFS);
+        dec_bdi_stat(page->mapping->backing_dev_info, BDI_RECLAIMABLE);
+}
+
+static void
 nfs_clear_request_commit(struct nfs_page *req)
 {
-        struct page *page = req->wb_page;
+        if (test_bit(PG_CLEAN, &req->wb_flags)) {
+                struct inode *inode = req->wb_context->dentry->d_inode;
 
-        if (test_and_clear_bit(PG_CLEAN, &(req)->wb_flags)) {
-                dec_zone_page_state(page, NR_UNSTABLE_NFS);
-                dec_bdi_stat(page->mapping->backing_dev_info, BDI_RECLAIMABLE);
-                return 1;
+                if (!pnfs_clear_request_commit(req)) {
+                        spin_lock(&inode->i_lock);
+                        nfs_request_remove_commit_list(req);
+                        spin_unlock(&inode->i_lock);
+                }
+                nfs_clear_page_commit(req->wb_page);
         }
-        return 0;
 }
 
 static inline
@@ -491,15 +528,14 @@ int nfs_reschedule_unstable_write(struct nfs_page *req,
         return 0;
 }
 #else
-static inline void
+static void
 nfs_mark_request_commit(struct nfs_page *req, struct pnfs_layout_segment *lseg)
 {
 }
 
-static inline int
+static void
 nfs_clear_request_commit(struct nfs_page *req)
 {
-        return 0;
 }
 
 static inline
@@ -520,46 +556,65 @@ int nfs_reschedule_unstable_write(struct nfs_page *req,
 static int
 nfs_need_commit(struct nfs_inode *nfsi)
 {
-        return radix_tree_tagged(&nfsi->nfs_page_tree, NFS_PAGE_TAG_COMMIT);
+        return nfsi->ncommit > 0;
+}
+
+/* i_lock held by caller */
+static int
+nfs_scan_commit_list(struct list_head *src, struct list_head *dst, int max,
+                spinlock_t *lock)
+{
+        struct nfs_page *req, *tmp;
+        int ret = 0;
+
+        list_for_each_entry_safe(req, tmp, src, wb_list) {
+                if (!nfs_lock_request(req))
+                        continue;
+                if (cond_resched_lock(lock))
+                        list_safe_reset_next(req, tmp, wb_list);
+                nfs_request_remove_commit_list(req);
+                nfs_list_add_request(req, dst);
+                ret++;
+                if (ret == max)
+                        break;
+        }
+        return ret;
 }
 
 /*
  * nfs_scan_commit - Scan an inode for commit requests
  * @inode: NFS inode to scan
  * @dst: destination list
- * @idx_start: lower bound of page->index to scan.
- * @npages: idx_start + npages sets the upper bound to scan.
  *
  * Moves requests from the inode's 'commit' request list.
  * The requests are *not* checked to ensure that they form a contiguous set.
  */
 static int
-nfs_scan_commit(struct inode *inode, struct list_head *dst, pgoff_t idx_start, unsigned int npages)
+nfs_scan_commit(struct inode *inode, struct list_head *dst)
 {
         struct nfs_inode *nfsi = NFS_I(inode);
-        int ret;
-
-        if (!nfs_need_commit(nfsi))
-                return 0;
+        int ret = 0;
 
         spin_lock(&inode->i_lock);
-        ret = nfs_scan_list(nfsi, dst, idx_start, npages, NFS_PAGE_TAG_COMMIT);
-        if (ret > 0)
-                nfsi->ncommit -= ret;
-        spin_unlock(&inode->i_lock);
-
-        if (nfs_need_commit(NFS_I(inode)))
-                __mark_inode_dirty(inode, I_DIRTY_DATASYNC);
+        if (nfsi->ncommit > 0) {
+                const int max = INT_MAX;
 
+                ret = nfs_scan_commit_list(&nfsi->commit_list, dst, max,
+                                &inode->i_lock);
+                ret += pnfs_scan_commit_lists(inode, max - ret,
+                                &inode->i_lock);
+        }
+        spin_unlock(&inode->i_lock);
         return ret;
 }
+
 #else
 static inline int nfs_need_commit(struct nfs_inode *nfsi)
 {
         return 0;
 }
 
-static inline int nfs_scan_commit(struct inode *inode, struct list_head *dst, pgoff_t idx_start, unsigned int npages)
+static inline int nfs_scan_commit(struct inode *inode, struct list_head *dst)
 {
         return 0;
 }
@@ -604,7 +659,7 @@ static struct nfs_page *nfs_try_to_update_request(struct inode *inode,
                     || end < req->wb_offset)
                         goto out_flushme;
 
-                if (nfs_set_page_tag_locked(req))
+                if (nfs_lock_request_dontget(req))
                         break;
 
                 /* The request is locked, so wait and then retry */
@@ -616,13 +671,6 @@ 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) != NULL) {
-                NFS_I(inode)->ncommit--;
-                pnfs_clear_request_commit(req);
-        }
-
         /* Okay, the request matches. Update the region */
         if (offset < req->wb_offset) {
                 req->wb_offset = offset;
@@ -634,6 +682,7 @@ static struct nfs_page *nfs_try_to_update_request(struct inode *inode,
                 req->wb_bytes = rqend - req->wb_offset;
 out_unlock:
         spin_unlock(&inode->i_lock);
+        nfs_clear_request_commit(req);
         return req;
 out_flushme:
         spin_unlock(&inode->i_lock);
@@ -655,7 +704,6 @@ static struct nfs_page * nfs_setup_write_request(struct nfs_open_context* ctx,
 {
         struct inode *inode = page->mapping->host;
         struct nfs_page *req;
-        int error;
 
         req = nfs_try_to_update_request(inode, page, offset, bytes);
         if (req != NULL)
@@ -663,11 +711,7 @@ static struct nfs_page * nfs_setup_write_request(struct nfs_open_context* ctx,
         req = nfs_create_request(ctx, inode, page, offset, bytes);
         if (IS_ERR(req))
                 goto out;
-        error = nfs_inode_add_request(inode, req);
-        if (error != 0) {
-                nfs_release_request(req);
-                req = ERR_PTR(error);
-        }
+        nfs_inode_add_request(inode, req);
 out:
         return req;
 }
@@ -684,7 +728,7 @@ static int nfs_writepage_setup(struct nfs_open_context *ctx, struct page *page,
         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);
+        nfs_unlock_request(req);
         return 0;
 }
 
@@ -777,7 +821,7 @@ static void nfs_writepage_release(struct nfs_page *req,
 
         if (PageError(req->wb_page) || !nfs_reschedule_unstable_write(req, data))
                 nfs_inode_remove_request(req);
-        nfs_clear_page_tag_locked(req);
+        nfs_unlock_request(req);
         nfs_end_page_writeback(page);
 }
 
@@ -925,7 +969,7 @@ static void nfs_redirty_request(struct nfs_page *req)
         struct page *page = req->wb_page;
 
         nfs_mark_request_dirty(req);
-        nfs_clear_page_tag_locked(req);
+        nfs_unlock_request(req);
         nfs_end_page_writeback(page);
 }
 
@@ -1128,23 +1172,14 @@ out:
         nfs_writedata_release(calldata);
 }
 
-#if defined(CONFIG_NFS_V4_1)
 void nfs_write_prepare(struct rpc_task *task, void *calldata)
 {
         struct nfs_write_data *data = calldata;
-
-        if (nfs4_setup_sequence(NFS_SERVER(data->inode),
-                                &data->args.seq_args,
-                                &data->res.seq_res, 1, task))
-                return;
-        rpc_call_start(task);
+        NFS_PROTO(data->inode)->write_rpc_prepare(task, data);
 }
-#endif /* CONFIG_NFS_V4_1 */
 
 static const struct rpc_call_ops nfs_write_partial_ops = {
-#if defined(CONFIG_NFS_V4_1)
         .rpc_call_prepare = nfs_write_prepare,
-#endif /* CONFIG_NFS_V4_1 */
         .rpc_call_done = nfs_writeback_done_partial,
         .rpc_release = nfs_writeback_release_partial,
 };
@@ -1199,16 +1234,14 @@ static void nfs_writeback_release_full(void *calldata)
 remove_request:
                 nfs_inode_remove_request(req);
         next:
-                nfs_clear_page_tag_locked(req);
+                nfs_unlock_request(req);
                 nfs_end_page_writeback(page);
         }
         nfs_writedata_release(calldata);
 }
 
 static const struct rpc_call_ops nfs_write_full_ops = {
-#if defined(CONFIG_NFS_V4_1)
         .rpc_call_prepare = nfs_write_prepare,
-#endif /* CONFIG_NFS_V4_1 */
         .rpc_call_done = nfs_writeback_done_full,
         .rpc_release = nfs_writeback_release_full,
 };
@@ -1325,7 +1358,6 @@ void nfs_commitdata_release(void *data)
 {
         struct nfs_write_data *wdata = data;
 
-        put_lseg(wdata->lseg);
         put_nfs_open_context(wdata->args.context);
         nfs_commit_free(wdata);
 }
@@ -1411,7 +1443,7 @@ void nfs_retry_commit(struct list_head *page_list,
                 dec_zone_page_state(req->wb_page, NR_UNSTABLE_NFS);
                 dec_bdi_stat(req->wb_page->mapping->backing_dev_info,
                              BDI_RECLAIMABLE);
-                nfs_clear_page_tag_locked(req);
+                nfs_unlock_request(req);
         }
 }
 EXPORT_SYMBOL_GPL(nfs_retry_commit);
@@ -1460,7 +1492,7 @@ void nfs_commit_release_pages(struct nfs_write_data *data)
         while (!list_empty(&data->pages)) {
                 req = nfs_list_entry(data->pages.next);
                 nfs_list_remove_request(req);
-                nfs_clear_request_commit(req);
+                nfs_clear_page_commit(req->wb_page);
 
                 dprintk("NFS:       commit (%s/%lld %d@%lld)",
                         req->wb_context->dentry->d_sb->s_id,
@@ -1486,7 +1518,7 @@ void nfs_commit_release_pages(struct nfs_write_data *data)
                 dprintk(" mismatch\n");
                 nfs_mark_request_dirty(req);
         next:
-                nfs_clear_page_tag_locked(req);
+                nfs_unlock_request(req);
         }
 }
 EXPORT_SYMBOL_GPL(nfs_commit_release_pages);
@@ -1501,9 +1533,7 @@ static void nfs_commit_release(void *calldata)
 }
 
 static const struct rpc_call_ops nfs_commit_ops = {
-#if defined(CONFIG_NFS_V4_1)
         .rpc_call_prepare = nfs_write_prepare,
-#endif /* CONFIG_NFS_V4_1 */
         .rpc_call_done = nfs_commit_done,
         .rpc_release = nfs_commit_release,
 };
@@ -1517,7 +1547,7 @@ int nfs_commit_inode(struct inode *inode, int how)
         res = nfs_commit_set_lock(NFS_I(inode), may_wait);
         if (res <= 0)
                 goto out_mark_dirty;
-        res = nfs_scan_commit(inode, &head, 0, 0);
+        res = nfs_scan_commit(inode, &head);
         if (res) {
                 int error;
 
@@ -1635,6 +1665,7 @@ int nfs_wb_page_cancel(struct inode *inode, struct page *page)
                 if (req == NULL)
                         break;
                 if (nfs_lock_request_dontget(req)) {
+                        nfs_clear_request_commit(req);
                         nfs_inode_remove_request(req);
                         /*
                          * In case nfs_inode_remove_request has marked the