65 files changed, 752 insertions, 220 deletions

diff --git a/fs/afs/cell.c b/fs/afs/cell.c
index bfc1fd22d5b1..1fc578372759 100644
--- a/fs/afs/cell.c
+++ b/fs/afs/cell.c
@@ -10,7 +10,6 @@
  */
 
 #include <linux/module.h>
-#include <linux/sched.h>
 #include <linux/slab.h>
 #include <rxrpc/peer.h>
 #include <rxrpc/connection.h>
diff --git a/fs/afs/dir.c b/fs/afs/dir.c
index 9908462bcadc..b6dc2ebe47a8 100644
--- a/fs/afs/dir.c
+++ b/fs/afs/dir.c
@@ -12,7 +12,6 @@
 #include <linux/kernel.h>
 #include <linux/module.h>
 #include <linux/init.h>
-#include <linux/sched.h>
 #include <linux/slab.h>
 #include <linux/fs.h>
 #include <linux/pagemap.h>
diff --git a/fs/afs/file.c b/fs/afs/file.c
index eeff14c3f748..b17634541f67 100644
--- a/fs/afs/file.c
+++ b/fs/afs/file.c
@@ -12,7 +12,6 @@
 #include <linux/kernel.h>
 #include <linux/module.h>
 #include <linux/init.h>
-#include <linux/sched.h>
 #include <linux/slab.h>
 #include <linux/fs.h>
 #include <linux/pagemap.h>
diff --git a/fs/afs/inode.c b/fs/afs/inode.c
index 6f37754906c2..9d9bca6c28b5 100644
--- a/fs/afs/inode.c
+++ b/fs/afs/inode.c
@@ -16,7 +16,6 @@
 #include <linux/kernel.h>
 #include <linux/module.h>
 #include <linux/init.h>
-#include <linux/sched.h>
 #include <linux/slab.h>
 #include <linux/fs.h>
 #include <linux/pagemap.h>
diff --git a/fs/afs/main.c b/fs/afs/main.c
index 913c689bdb35..f2704ba53857 100644
--- a/fs/afs/main.c
+++ b/fs/afs/main.c
@@ -12,7 +12,6 @@
 #include <linux/module.h>
 #include <linux/moduleparam.h>
 #include <linux/init.h>
-#include <linux/sched.h>
 #include <linux/completion.h>
 #include <rxrpc/rxrpc.h>
 #include <rxrpc/transport.h>
diff --git a/fs/afs/mntpt.c b/fs/afs/mntpt.c
index fdf23b2a2112..68495f0de7b3 100644
--- a/fs/afs/mntpt.c
+++ b/fs/afs/mntpt.c
@@ -12,7 +12,6 @@
 #include <linux/kernel.h>
 #include <linux/module.h>
 #include <linux/init.h>
-#include <linux/sched.h>
 #include <linux/slab.h>
 #include <linux/fs.h>
 #include <linux/pagemap.h>
diff --git a/fs/afs/proc.c b/fs/afs/proc.c
index 86463ec9ccb4..ae6b85b1e484 100644
--- a/fs/afs/proc.c
+++ b/fs/afs/proc.c
@@ -9,7 +9,6 @@
  * 2 of the License, or (at your option) any later version.
  */
 
-#include <linux/sched.h>
 #include <linux/slab.h>
 #include <linux/module.h>
 #include <linux/proc_fs.h>
diff --git a/fs/binfmt_elf.c b/fs/binfmt_elf.c
index 669dbe5b0317..51db1182b27e 100644
--- a/fs/binfmt_elf.c
+++ b/fs/binfmt_elf.c
@@ -76,7 +76,8 @@ static struct linux_binfmt elf_format = {
                 .load_binary    = load_elf_binary,
                 .load_shlib     = load_elf_library,
                 .core_dump      = elf_core_dump,
-                .min_coredump   = ELF_EXEC_PAGESIZE
+                .min_coredump   = ELF_EXEC_PAGESIZE,
+                .hasvdso        = 1
 };
 
 #define BAD_ADDR(x) ((unsigned long)(x) >= TASK_SIZE)
diff --git a/fs/coda/sysctl.c b/fs/coda/sysctl.c
index db3b1a9c9a5b..c57a1fa7cf23 100644
--- a/fs/coda/sysctl.c
+++ b/fs/coda/sysctl.c
@@ -33,8 +33,6 @@
 
 static struct ctl_table_header *fs_table_header;
 
-#define FS_CODA         1       /* Coda file system */
-
 #define CODA_TIMEOUT    3       /* timeout on upcalls to become intrble */
 #define CODA_HARD       5       /* mount type "hard" or "soft" */
 #define CODA_VFS         6       /* vfs statistics */
@@ -183,17 +181,57 @@ static const struct file_operations proc_cache_inv_stats_fops = {
 };
 
 static ctl_table coda_table[] = {
-        {CODA_TIMEOUT, "timeout", &coda_timeout, sizeof(int), 0644, NULL, &proc_dointvec},
-        {CODA_HARD, "hard", &coda_hard, sizeof(int), 0644, NULL, &proc_dointvec},
-        {CODA_VFS, "vfs_stats", NULL, 0, 0644, NULL, &do_reset_coda_vfs_stats},
-        {CODA_CACHE_INV, "cache_inv_stats", NULL, 0, 0644, NULL, &do_reset_coda_cache_inv_stats},
-        {CODA_FAKE_STATFS, "fake_statfs", &coda_fake_statfs, sizeof(int), 0600, NULL, &proc_dointvec},
-        { 0 }
+        {
+                .ctl_name       = CTL_UNNUMBERED,
+                .procname       = "timeout",
+                .data           = &coda_timeout,
+                .maxlen         = sizeof(int),
+                .mode           = 0644,
+                .proc_handler   = &proc_dointvec
+        },
+        {
+                .ctl_name       = CTL_UNNUMBERED,
+                .procname       = "hard",
+                .data           = &coda_hard,
+                .maxlen         = sizeof(int),
+                .mode           = 0644,
+                .proc_handler   = &proc_dointvec
+        },
+        {
+                .ctl_name       = CTL_UNNUMBERED,
+                .procname       = "vfs_stats",
+                .data           = NULL,
+                .maxlen         = 0,
+                .mode           = 0644,
+                .proc_handler   = &do_reset_coda_vfs_stats
+        },
+        {
+                .ctl_name       = CTL_UNNUMBERED,
+                .procname       = "cache_inv_stats",
+                .data           = NULL,
+                .maxlen         = 0,
+                .mode           = 0644,
+                .proc_handler   = &do_reset_coda_cache_inv_stats
+        },
+        {
+                .ctl_name       = CTL_UNNUMBERED,
+                .procname       = "fake_statfs",
+                .data           = &coda_fake_statfs,
+                .maxlen         = sizeof(int),
+                .mode           = 0600,
+                .proc_handler   = &proc_dointvec
+        },
+        {}
 };
 
 static ctl_table fs_table[] = {
-       {FS_CODA, "coda",    NULL, 0, 0555, coda_table},
-       {0}
+        {
+                .ctl_name       = CTL_UNNUMBERED,
+                .procname       = "coda",
+                .mode           = 0555,
+                .child          = coda_table
+        },
+        {}
 };
 
 
@@ -233,7 +271,7 @@ void coda_sysctl_init(void)
 
 #ifdef CONFIG_SYSCTL
         if ( !fs_table_header )
-                fs_table_header = register_sysctl_table(fs_table, 0);
+                fs_table_header = register_sysctl_table(fs_table);
 #endif 
 }
 
diff --git a/fs/dquot.c b/fs/dquot.c
index 9eb166f91489..b16f991662c1 100644
--- a/fs/dquot.c
+++ b/fs/dquot.c
@@ -1841,7 +1841,7 @@ static int __init dquot_init(void)
 
         printk(KERN_NOTICE "VFS: Disk quotas %s\n", __DQUOT_VERSION__);
 
-        register_sysctl_table(sys_table, 0);
+        register_sysctl_table(sys_table);
 
         dquot_cachep = kmem_cache_create("dquot", 
                         sizeof(struct dquot), sizeof(unsigned long) * 4,
diff --git a/fs/ecryptfs/keystore.c b/fs/ecryptfs/keystore.c
index c209f67e7a26..81156e95ef8e 100644
--- a/fs/ecryptfs/keystore.c
+++ b/fs/ecryptfs/keystore.c
@@ -26,7 +26,6 @@
  */
 
 #include <linux/string.h>
-#include <linux/sched.h>
 #include <linux/syscalls.h>
 #include <linux/pagemap.h>
 #include <linux/key.h>
diff --git a/fs/ext3/hash.c b/fs/ext3/hash.c
index deeb27b5ba83..c30e149fbd2e 100644
--- a/fs/ext3/hash.c
+++ b/fs/ext3/hash.c
@@ -11,7 +11,6 @@
 
 #include <linux/fs.h>
 #include <linux/jbd.h>
-#include <linux/sched.h>
 #include <linux/ext3_fs.h>
 #include <linux/cryptohash.h>
 
diff --git a/fs/ext3/resize.c b/fs/ext3/resize.c
index b73cba12f79c..ecf89904c113 100644
--- a/fs/ext3/resize.c
+++ b/fs/ext3/resize.c
@@ -11,7 +11,6 @@
 
 #define EXT3FS_DEBUG
 
-#include <linux/sched.h>
 #include <linux/smp_lock.h>
 #include <linux/ext3_jbd.h>
 
diff --git a/fs/ext4/hash.c b/fs/ext4/hash.c
index a67966385e06..1555024e3b36 100644
--- a/fs/ext4/hash.c
+++ b/fs/ext4/hash.c
@@ -11,7 +11,6 @@
 
 #include <linux/fs.h>
 #include <linux/jbd2.h>
-#include <linux/sched.h>
 #include <linux/ext4_fs.h>
 #include <linux/cryptohash.h>
 
diff --git a/fs/ext4/resize.c b/fs/ext4/resize.c
index 4fe49c3661b2..ea99f6c97f56 100644
--- a/fs/ext4/resize.c
+++ b/fs/ext4/resize.c
@@ -11,7 +11,6 @@
 
 #define EXT4FS_DEBUG
 
-#include <linux/sched.h>
 #include <linux/smp_lock.h>
 #include <linux/ext4_jbd2.h>
 
diff --git a/fs/filesystems.c b/fs/filesystems.c
index e3fa77c6ed56..7a4f61aa05f8 100644
--- a/fs/filesystems.c
+++ b/fs/filesystems.c
@@ -12,7 +12,6 @@
 #include <linux/kmod.h>
 #include <linux/init.h>
 #include <linux/module.h>
-#include <linux/sched.h>        /* for 'current' */
 #include <asm/uaccess.h>
 
 /*
diff --git a/fs/gfs2/bmap.c b/fs/gfs2/bmap.c
index 113f6c9110c7..c53a5d2d0590 100644
--- a/fs/gfs2/bmap.c
+++ b/fs/gfs2/bmap.c
@@ -7,7 +7,6 @@
  * of the GNU General Public License version 2.
  */
 
-#include <linux/sched.h>
 #include <linux/slab.h>
 #include <linux/spinlock.h>
 #include <linux/completion.h>
diff --git a/fs/gfs2/dir.c b/fs/gfs2/dir.c
index c93ca8f361b5..82a1ac7895a2 100644
--- a/fs/gfs2/dir.c
+++ b/fs/gfs2/dir.c
@@ -53,7 +53,6 @@
  * but never before the maximum hash table size has been reached.
  */
 
-#include <linux/sched.h>
 #include <linux/slab.h>
 #include <linux/spinlock.h>
 #include <linux/buffer_head.h>
diff --git a/fs/gfs2/eaops.c b/fs/gfs2/eaops.c
index cd747c00f670..c1f44009853f 100644
--- a/fs/gfs2/eaops.c
+++ b/fs/gfs2/eaops.c
@@ -7,7 +7,6 @@
  * of the GNU General Public License version 2.
  */
 
-#include <linux/sched.h>
 #include <linux/slab.h>
 #include <linux/spinlock.h>
 #include <linux/completion.h>
diff --git a/fs/gfs2/eattr.c b/fs/gfs2/eattr.c
index 0c83c7f4dda8..5b83ca6acab1 100644
--- a/fs/gfs2/eattr.c
+++ b/fs/gfs2/eattr.c
@@ -7,7 +7,6 @@
  * of the GNU General Public License version 2.
  */
 
-#include <linux/sched.h>
 #include <linux/slab.h>
 #include <linux/spinlock.h>
 #include <linux/completion.h>
diff --git a/fs/gfs2/glops.c b/fs/gfs2/glops.c
index c4b0391b7aa2..46af55355513 100644
--- a/fs/gfs2/glops.c
+++ b/fs/gfs2/glops.c
@@ -7,7 +7,6 @@
  * of the GNU General Public License version 2.
  */
 
-#include <linux/sched.h>
 #include <linux/slab.h>
 #include <linux/spinlock.h>
 #include <linux/completion.h>
diff --git a/fs/gfs2/lm.c b/fs/gfs2/lm.c
index e30673dd37e0..cfcc39b86a53 100644
--- a/fs/gfs2/lm.c
+++ b/fs/gfs2/lm.c
@@ -7,7 +7,6 @@
  * of the GNU General Public License version 2.
  */
 
-#include <linux/sched.h>
 #include <linux/slab.h>
 #include <linux/spinlock.h>
 #include <linux/completion.h>
diff --git a/fs/gfs2/main.c b/fs/gfs2/main.c
index 7c1a9e22a526..6e8a59809abf 100644
--- a/fs/gfs2/main.c
+++ b/fs/gfs2/main.c
@@ -7,7 +7,6 @@
  * of the GNU General Public License version 2.
  */
 
-#include <linux/sched.h>
 #include <linux/slab.h>
 #include <linux/spinlock.h>
 #include <linux/completion.h>
diff --git a/fs/gfs2/mount.c b/fs/gfs2/mount.c
index ef3092e29607..32caecd20300 100644
--- a/fs/gfs2/mount.c
+++ b/fs/gfs2/mount.c
@@ -7,7 +7,6 @@
  * of the GNU General Public License version 2.
  */
 
-#include <linux/sched.h>
 #include <linux/slab.h>
 #include <linux/spinlock.h>
 #include <linux/completion.h>
diff --git a/fs/gfs2/ondisk.c b/fs/gfs2/ondisk.c
index f2495f1e21ad..d9ecfd23a49e 100644
--- a/fs/gfs2/ondisk.c
+++ b/fs/gfs2/ondisk.c
@@ -7,7 +7,6 @@
  * of the GNU General Public License version 2.
  */
 
-#include <linux/sched.h>
 #include <linux/slab.h>
 #include <linux/spinlock.h>
 #include <linux/completion.h>
diff --git a/fs/gfs2/ops_dentry.c b/fs/gfs2/ops_dentry.c
index 9187eb174b43..c6bac6b69420 100644
--- a/fs/gfs2/ops_dentry.c
+++ b/fs/gfs2/ops_dentry.c
@@ -7,7 +7,6 @@
  * of the GNU General Public License version 2.
  */
 
-#include <linux/sched.h>
 #include <linux/slab.h>
 #include <linux/spinlock.h>
 #include <linux/completion.h>
diff --git a/fs/gfs2/ops_export.c b/fs/gfs2/ops_export.c
index 4855e8cca622..1de05b63d43a 100644
--- a/fs/gfs2/ops_export.c
+++ b/fs/gfs2/ops_export.c
@@ -7,7 +7,6 @@
  * of the GNU General Public License version 2.
  */
 
-#include <linux/sched.h>
 #include <linux/slab.h>
 #include <linux/spinlock.h>
 #include <linux/completion.h>
diff --git a/fs/gfs2/ops_file.c b/fs/gfs2/ops_file.c
index c996aa739a05..b50180e22779 100644
--- a/fs/gfs2/ops_file.c
+++ b/fs/gfs2/ops_file.c
@@ -7,7 +7,6 @@
  * of the GNU General Public License version 2.
  */
 
-#include <linux/sched.h>
 #include <linux/slab.h>
 #include <linux/spinlock.h>
 #include <linux/completion.h>
diff --git a/fs/gfs2/ops_inode.c b/fs/gfs2/ops_inode.c
index 60f47bf2e8e8..d85f6e05cb95 100644
--- a/fs/gfs2/ops_inode.c
+++ b/fs/gfs2/ops_inode.c
@@ -7,7 +7,6 @@
  * of the GNU General Public License version 2.
  */
 
-#include <linux/sched.h>
 #include <linux/slab.h>
 #include <linux/spinlock.h>
 #include <linux/completion.h>
diff --git a/fs/gfs2/ops_vm.c b/fs/gfs2/ops_vm.c
index 14b380fb0602..aa0dbd2aac1b 100644
--- a/fs/gfs2/ops_vm.c
+++ b/fs/gfs2/ops_vm.c
@@ -7,7 +7,6 @@
  * of the GNU General Public License version 2.
  */
 
-#include <linux/sched.h>
 #include <linux/slab.h>
 #include <linux/spinlock.h>
 #include <linux/completion.h>
diff --git a/fs/gfs2/recovery.c b/fs/gfs2/recovery.c
index d0c806b85c86..8bc182c7e2ef 100644
--- a/fs/gfs2/recovery.c
+++ b/fs/gfs2/recovery.c
@@ -7,7 +7,6 @@
  * of the GNU General Public License version 2.
  */
 
-#include <linux/sched.h>
 #include <linux/slab.h>
 #include <linux/spinlock.h>
 #include <linux/completion.h>
diff --git a/fs/gfs2/rgrp.c b/fs/gfs2/rgrp.c
index ff0846528d54..8d9c08b5c4b6 100644
--- a/fs/gfs2/rgrp.c
+++ b/fs/gfs2/rgrp.c
@@ -7,7 +7,6 @@
  * of the GNU General Public License version 2.
  */
 
-#include <linux/sched.h>
 #include <linux/slab.h>
 #include <linux/spinlock.h>
 #include <linux/completion.h>
diff --git a/fs/gfs2/util.c b/fs/gfs2/util.c
index e5707a9f78c2..601eaa1b9ed6 100644
--- a/fs/gfs2/util.c
+++ b/fs/gfs2/util.c
@@ -7,7 +7,6 @@
  * of the GNU General Public License version 2.
  */
 
-#include <linux/sched.h>
 #include <linux/slab.h>
 #include <linux/spinlock.h>
 #include <linux/completion.h>
diff --git a/fs/hfsplus/catalog.c b/fs/hfsplus/catalog.c
index f2d7c49ce759..ba117c445e78 100644
--- a/fs/hfsplus/catalog.c
+++ b/fs/hfsplus/catalog.c
@@ -8,7 +8,6 @@
  * Handling of catalog records
  */
 
-#include <linux/sched.h>
 
 #include "hfsplus_fs.h"
 #include "hfsplus_raw.h"
diff --git a/fs/hfsplus/dir.c b/fs/hfsplus/dir.c
index 78137007ccc1..80b5682a2273 100644
--- a/fs/hfsplus/dir.c
+++ b/fs/hfsplus/dir.c
@@ -10,7 +10,6 @@
 
 #include <linux/errno.h>
 #include <linux/fs.h>
-#include <linux/sched.h>
 #include <linux/slab.h>
 #include <linux/random.h>
 
diff --git a/fs/hfsplus/super.c b/fs/hfsplus/super.c
index 5a282f64c637..1a97f9293447 100644
--- a/fs/hfsplus/super.c
+++ b/fs/hfsplus/super.c
@@ -11,7 +11,6 @@
 #include <linux/init.h>
 #include <linux/pagemap.h>
 #include <linux/fs.h>
-#include <linux/sched.h>
 #include <linux/slab.h>
 #include <linux/vfs.h>
 #include <linux/nls.h>
diff --git a/fs/jffs2/compr_zlib.c b/fs/jffs2/compr_zlib.c
index 3681d0728ac7..0c1fc6e20b43 100644
--- a/fs/jffs2/compr_zlib.c
+++ b/fs/jffs2/compr_zlib.c
@@ -16,7 +16,6 @@
 #endif
 
 #include <linux/kernel.h>
-#include <linux/sched.h>
 #include <linux/slab.h>
 #include <linux/zlib.h>
 #include <linux/zutil.h>
diff --git a/fs/jffs2/dir.c b/fs/jffs2/dir.c
index cdbe2fe14e2d..9fa2e27f0641 100644
--- a/fs/jffs2/dir.c
+++ b/fs/jffs2/dir.c
@@ -13,7 +13,6 @@
 
 #include <linux/kernel.h>
 #include <linux/slab.h>
-#include <linux/sched.h>
 #include <linux/fs.h>
 #include <linux/crc32.h>
 #include <linux/jffs2.h>
diff --git a/fs/jffs2/summary.c b/fs/jffs2/summary.c
index 25265965bdc1..30f888414ce7 100644
--- a/fs/jffs2/summary.c
+++ b/fs/jffs2/summary.c
@@ -14,7 +14,6 @@
  */
 
 #include <linux/kernel.h>
-#include <linux/sched.h>
 #include <linux/slab.h>
 #include <linux/mtd/mtd.h>
 #include <linux/pagemap.h>
diff --git a/fs/lockd/host.c b/fs/lockd/host.c
index 22d403208973..ad21c0713efa 100644
--- a/fs/lockd/host.c
+++ b/fs/lockd/host.c
@@ -9,7 +9,6 @@
  */
 
 #include <linux/types.h>
-#include <linux/sched.h>
 #include <linux/slab.h>
 #include <linux/in.h>
 #include <linux/sunrpc/clnt.h>
diff --git a/fs/lockd/svc.c b/fs/lockd/svc.c
index 80fcacc1acf9..50cb8daba4e5 100644
--- a/fs/lockd/svc.c
+++ b/fs/lockd/svc.c
@@ -512,7 +512,7 @@ module_param(nsm_use_hostnames, bool, 0644);
 
 static int __init init_nlm(void)
 {
-        nlm_sysctl_table = register_sysctl_table(nlm_sysctl_root, 0);
+        nlm_sysctl_table = register_sysctl_table(nlm_sysctl_root);
         return nlm_sysctl_table ? 0 : -ENOMEM;
 }
 
diff --git a/fs/nfs/nfs4renewd.c b/fs/nfs/nfs4renewd.c
index 823298561c0a..f5f4430fb2a4 100644
--- a/fs/nfs/nfs4renewd.c
+++ b/fs/nfs/nfs4renewd.c
@@ -43,7 +43,6 @@
  * child task framework of the RPC layer?
  */
 
-#include <linux/sched.h>
 #include <linux/smp_lock.h>
 #include <linux/mm.h>
 #include <linux/pagemap.h>
diff --git a/fs/nfs/sysctl.c b/fs/nfs/sysctl.c
index 3ea50ac64820..fcdcafbb3293 100644
--- a/fs/nfs/sysctl.c
+++ b/fs/nfs/sysctl.c
@@ -75,7 +75,7 @@ static ctl_table nfs_cb_sysctl_root[] = {
 
 int nfs_register_sysctl(void)
 {
-        nfs_callback_sysctl_table = register_sysctl_table(nfs_cb_sysctl_root, 0);
+        nfs_callback_sysctl_table = register_sysctl_table(nfs_cb_sysctl_root);
         if (nfs_callback_sysctl_table == NULL)
                 return -ENOMEM;
         return 0;
diff --git a/fs/nfsd/export.c b/fs/nfsd/export.c
index 49c310b84923..6f24768272a1 100644
--- a/fs/nfsd/export.c
+++ b/fs/nfsd/export.c
@@ -16,7 +16,6 @@
 
 #include <linux/unistd.h>
 #include <linux/slab.h>
-#include <linux/sched.h>
 #include <linux/stat.h>
 #include <linux/in.h>
 #include <linux/seq_file.h>
@@ -190,18 +189,17 @@ static int expkey_show(struct seq_file *m,
                        struct cache_head *h)
 {
         struct svc_expkey *ek ;
+        int i;
 
         if (h ==NULL) {
                 seq_puts(m, "#domain fsidtype fsid [path]\n");
                 return 0;
         }
         ek = container_of(h, struct svc_expkey, h);
-        seq_printf(m, "%s %d 0x%08x", ek->ek_client->name,
-                   ek->ek_fsidtype, ek->ek_fsid[0]);
-        if (ek->ek_fsidtype != 1)
-                seq_printf(m, "%08x", ek->ek_fsid[1]);
-        if (ek->ek_fsidtype == 2)
-                seq_printf(m, "%08x", ek->ek_fsid[2]);
+        seq_printf(m, "%s %d 0x", ek->ek_client->name,
+                   ek->ek_fsidtype);
+        for (i=0; i < key_len(ek->ek_fsidtype)/4; i++)
+                seq_printf(m, "%08x", ek->ek_fsid[i]);
         if (test_bit(CACHE_VALID, &h->flags) && 
             !test_bit(CACHE_NEGATIVE, &h->flags)) {
                 seq_printf(m, " ");
@@ -232,9 +230,8 @@ static inline void expkey_init(struct cache_head *cnew,
         kref_get(&item->ek_client->ref);
         new->ek_client = item->ek_client;
         new->ek_fsidtype = item->ek_fsidtype;
-        new->ek_fsid[0] = item->ek_fsid[0];
-        new->ek_fsid[1] = item->ek_fsid[1];
-        new->ek_fsid[2] = item->ek_fsid[2];
+
+        memcpy(new->ek_fsid, item->ek_fsid, sizeof(new->ek_fsid));
 }
 
 static inline void expkey_update(struct cache_head *cnew,
@@ -363,7 +360,7 @@ static struct svc_export *svc_export_update(struct svc_export *new,
                                             struct svc_export *old);
 static struct svc_export *svc_export_lookup(struct svc_export *);
 
-static int check_export(struct inode *inode, int flags)
+static int check_export(struct inode *inode, int flags, unsigned char *uuid)
 {
 
         /* We currently export only dirs and regular files.
@@ -376,12 +373,13 @@ static int check_export(struct inode *inode, int flags)
         /* There are two requirements on a filesystem to be exportable.
          * 1:  We must be able to identify the filesystem from a number.
          *       either a device number (so FS_REQUIRES_DEV needed)
-         *       or an FSID number (so NFSEXP_FSID needed).
+         *       or an FSID number (so NFSEXP_FSID or ->uuid is needed).
          * 2:  We must be able to find an inode from a filehandle.
          *       This means that s_export_op must be set.
          */
         if (!(inode->i_sb->s_type->fs_flags & FS_REQUIRES_DEV) &&
-            !(flags & NFSEXP_FSID)) {
+            !(flags & NFSEXP_FSID) &&
+            uuid == NULL) {
                 dprintk("exp_export: export of non-dev fs without fsid\n");
                 return -EINVAL;
         }
@@ -406,10 +404,6 @@ fsloc_parse(char **mesg, char *buf, struct nfsd4_fs_locations *fsloc)
         int len;
         int migrated, i, err;
 
-        len = qword_get(mesg, buf, PAGE_SIZE);
-        if (len != 5 || memcmp(buf, "fsloc", 5))
-                return 0;
-
         /* listsize */
         err = get_int(mesg, &fsloc->locations_count);
         if (err)
@@ -520,6 +514,8 @@ static int svc_export_parse(struct cache_detail *cd, char *mesg, int mlen)
         exp.ex_fslocs.locations_count = 0;
         exp.ex_fslocs.migrated = 0;
 
+        exp.ex_uuid = NULL;
+
         /* flags */
         err = get_int(&mesg, &an_int);
         if (err == -ENOENT)
@@ -543,12 +539,33 @@ static int svc_export_parse(struct cache_detail *cd, char *mesg, int mlen)
                 if (err) goto out;
                 exp.ex_fsid = an_int;
 
-                err = check_export(nd.dentry->d_inode, exp.ex_flags);
-                if (err) goto out;
+                while ((len = qword_get(&mesg, buf, PAGE_SIZE)) > 0) {
+                        if (strcmp(buf, "fsloc") == 0)
+                                err = fsloc_parse(&mesg, buf, &exp.ex_fslocs);
+                        else if (strcmp(buf, "uuid") == 0) {
+                                /* expect a 16 byte uuid encoded as \xXXXX... */
+                                len = qword_get(&mesg, buf, PAGE_SIZE);
+                                if (len != 16)
+                                        err  = -EINVAL;
+                                else {
+                                        exp.ex_uuid =
+                                                kmemdup(buf, 16, GFP_KERNEL);
+                                        if (exp.ex_uuid == NULL)
+                                                err = -ENOMEM;
+                                }
+                        } else
+                                /* quietly ignore unknown words and anything
+                                 * following. Newer user-space can try to set
+                                 * new values, then see what the result was.
+                                 */
+                                break;
+                        if (err)
+                                goto out;
+                }
 
-                err = fsloc_parse(&mesg, buf, &exp.ex_fslocs);
-                if (err)
-                        goto out;
+                err = check_export(nd.dentry->d_inode, exp.ex_flags,
+                                   exp.ex_uuid);
+                if (err) goto out;
         }
 
         expp = svc_export_lookup(&exp);
@@ -562,6 +579,8 @@ static int svc_export_parse(struct cache_detail *cd, char *mesg, int mlen)
         else
                 exp_put(expp);
  out:
+        nfsd4_fslocs_free(&exp.ex_fslocs);
+        kfree(exp.ex_uuid);
         kfree(exp.ex_path);
         if (nd.dentry)
                 path_release(&nd);
@@ -591,9 +610,19 @@ static int svc_export_show(struct seq_file *m,
         seq_escape(m, exp->ex_client->name, " \t\n\\");
         seq_putc(m, '(');
         if (test_bit(CACHE_VALID, &h->flags) && 
-            !test_bit(CACHE_NEGATIVE, &h->flags))
+            !test_bit(CACHE_NEGATIVE, &h->flags)) {
                 exp_flags(m, exp->ex_flags, exp->ex_fsid,
                           exp->ex_anon_uid, exp->ex_anon_gid, &exp->ex_fslocs);
+                if (exp->ex_uuid) {
+                        int i;
+                        seq_puts(m, ",uuid=");
+                        for (i=0; i<16; i++) {
+                                if ((i&3) == 0 && i)
+                                        seq_putc(m, ':');
+                                seq_printf(m, "%02x", exp->ex_uuid[i]);
+                        }
+                }
+        }
         seq_puts(m, ")\n");
         return 0;
 }
@@ -630,6 +659,8 @@ static void export_update(struct cache_head *cnew, struct cache_head *citem)
         new->ex_anon_uid = item->ex_anon_uid;
         new->ex_anon_gid = item->ex_anon_gid;
         new->ex_fsid = item->ex_fsid;
+        new->ex_uuid = item->ex_uuid;
+        item->ex_uuid = NULL;
         new->ex_path = item->ex_path;
         item->ex_path = NULL;
         new->ex_fslocs.locations = item->ex_fslocs.locations;
@@ -752,11 +783,11 @@ exp_get_key(svc_client *clp, dev_t dev, ino_t ino)
         u32 fsidv[3];
         
         if (old_valid_dev(dev)) {
-                mk_fsid_v0(fsidv, dev, ino);
-                return exp_find_key(clp, 0, fsidv, NULL);
+                mk_fsid(FSID_DEV, fsidv, dev, ino, 0, NULL);
+                return exp_find_key(clp, FSID_DEV, fsidv, NULL);
         }
-        mk_fsid_v3(fsidv, dev, ino);
-        return exp_find_key(clp, 3, fsidv, NULL);
+        mk_fsid(FSID_ENCODE_DEV, fsidv, dev, ino, 0, NULL);
+        return exp_find_key(clp, FSID_ENCODE_DEV, fsidv, NULL);
 }
 
 /*
@@ -767,9 +798,9 @@ exp_get_fsid_key(svc_client *clp, int fsid)
 {
         u32 fsidv[2];
 
-        mk_fsid_v1(fsidv, fsid);
+        mk_fsid(FSID_NUM, fsidv, 0, 0, fsid, NULL);
 
-        return exp_find_key(clp, 1, fsidv, NULL);
+        return exp_find_key(clp, FSID_NUM, fsidv, NULL);
 }
 
 svc_export *
@@ -883,8 +914,8 @@ static int exp_fsid_hash(svc_client *clp, struct svc_export *exp)
         if ((exp->ex_flags & NFSEXP_FSID) == 0)
                 return 0;
 
-        mk_fsid_v1(fsid, exp->ex_fsid);
-        return exp_set_key(clp, 1, fsid, exp);
+        mk_fsid(FSID_NUM, fsid, 0, 0, exp->ex_fsid, NULL);
+        return exp_set_key(clp, FSID_NUM, fsid, exp);
 }
 
 static int exp_hash(struct auth_domain *clp, struct svc_export *exp)
@@ -894,11 +925,11 @@ static int exp_hash(struct auth_domain *clp, struct svc_export *exp)
         dev_t dev = inode->i_sb->s_dev;
 
         if (old_valid_dev(dev)) {
-                mk_fsid_v0(fsid, dev, inode->i_ino);
-                return exp_set_key(clp, 0, fsid, exp);
+                mk_fsid(FSID_DEV, fsid, dev, inode->i_ino, 0, NULL);
+                return exp_set_key(clp, FSID_DEV, fsid, exp);
         }
-        mk_fsid_v3(fsid, dev, inode->i_ino);
-        return exp_set_key(clp, 3, fsid, exp);
+        mk_fsid(FSID_ENCODE_DEV, fsid, dev, inode->i_ino, 0, NULL);
+        return exp_set_key(clp, FSID_ENCODE_DEV, fsid, exp);
 }
 
 static void exp_unhash(struct svc_export *exp)
@@ -977,7 +1008,7 @@ exp_export(struct nfsctl_export *nxp)
                 goto finish;
         }
 
-        err = check_export(nd.dentry->d_inode, nxp->ex_flags);
+        err = check_export(nd.dentry->d_inode, nxp->ex_flags, NULL);
         if (err) goto finish;
 
         err = -ENOMEM;
@@ -1170,9 +1201,9 @@ exp_pseudoroot(struct auth_domain *clp, struct svc_fh *fhp,
         __be32 rv;
         u32 fsidv[2];
 
-        mk_fsid_v1(fsidv, 0);
+        mk_fsid(FSID_NUM, fsidv, 0, 0, 0, NULL);
 
-        exp = exp_find(clp, 1, fsidv, creq);
+        exp = exp_find(clp, FSID_NUM, fsidv, creq);
         if (IS_ERR(exp))
                 return nfserrno(PTR_ERR(exp));
         if (exp == NULL)
diff --git a/fs/nfsd/nfs3xdr.c b/fs/nfsd/nfs3xdr.c
index e695660921ec..6f677988c71d 100644
--- a/fs/nfsd/nfs3xdr.c
+++ b/fs/nfsd/nfs3xdr.c
@@ -149,6 +149,27 @@ decode_sattr3(__be32 *p, struct iattr *iap)
         return p;
 }
 
+static __be32 *encode_fsid(__be32 *p, struct svc_fh *fhp)
+{
+        u64 f;
+        switch(fsid_source(fhp)) {
+        default:
+        case FSIDSOURCE_DEV:
+                p = xdr_encode_hyper(p, (u64)huge_encode_dev
+                                     (fhp->fh_dentry->d_inode->i_sb->s_dev));
+                break;
+        case FSIDSOURCE_FSID:
+                p = xdr_encode_hyper(p, (u64) fhp->fh_export->ex_fsid);
+                break;
+        case FSIDSOURCE_UUID:
+                f = ((u64*)fhp->fh_export->ex_uuid)[0];
+                f ^= ((u64*)fhp->fh_export->ex_uuid)[1];
+                p = xdr_encode_hyper(p, f);
+                break;
+        }
+        return p;
+}
+
 static __be32 *
 encode_fattr3(struct svc_rqst *rqstp, __be32 *p, struct svc_fh *fhp,
               struct kstat *stat)
@@ -169,10 +190,7 @@ encode_fattr3(struct svc_rqst *rqstp, __be32 *p, struct svc_fh *fhp,
         p = xdr_encode_hyper(p, ((u64)stat->blocks) << 9);
         *p++ = htonl((u32) MAJOR(stat->rdev));
         *p++ = htonl((u32) MINOR(stat->rdev));
-        if (is_fsid(fhp, rqstp->rq_reffh))
-                p = xdr_encode_hyper(p, (u64) fhp->fh_export->ex_fsid);
-        else
-                p = xdr_encode_hyper(p, (u64) huge_encode_dev(stat->dev));
+        p = encode_fsid(p, fhp);
         p = xdr_encode_hyper(p, (u64) stat->ino);
         p = encode_time3(p, &stat->atime);
         lease_get_mtime(dentry->d_inode, &time); 
@@ -203,10 +221,7 @@ encode_saved_post_attr(struct svc_rqst *rqstp, __be32 *p, struct svc_fh *fhp)
         p = xdr_encode_hyper(p, ((u64)fhp->fh_post_blocks) << 9);
         *p++ = fhp->fh_post_rdev[0];
         *p++ = fhp->fh_post_rdev[1];
-        if (is_fsid(fhp, rqstp->rq_reffh))
-                p = xdr_encode_hyper(p, (u64) fhp->fh_export->ex_fsid);
-        else
-                p = xdr_encode_hyper(p, (u64)huge_encode_dev(inode->i_sb->s_dev));
+        p = encode_fsid(p, fhp);
         p = xdr_encode_hyper(p, (u64) inode->i_ino);
         p = encode_time3(p, &fhp->fh_post_atime);
         p = encode_time3(p, &fhp->fh_post_mtime);
diff --git a/fs/nfsd/nfs4idmap.c b/fs/nfsd/nfs4idmap.c
index b1902ebaab41..e4a83d727afd 100644
--- a/fs/nfsd/nfs4idmap.c
+++ b/fs/nfsd/nfs4idmap.c
@@ -50,7 +50,6 @@
 #include <linux/sunrpc/cache.h>
 #include <linux/nfsd_idmap.h>
 #include <linux/list.h>
-#include <linux/sched.h>
 #include <linux/time.h>
 #include <linux/seq_file.h>
 #include <linux/sunrpc/svcauth.h>
diff --git a/fs/nfsd/nfs4xdr.c b/fs/nfsd/nfs4xdr.c
index 18aa9440df14..0efba557fb55 100644
--- a/fs/nfsd/nfs4xdr.c
+++ b/fs/nfsd/nfs4xdr.c
@@ -1563,14 +1563,20 @@ nfsd4_encode_fattr(struct svc_fh *fhp, struct svc_export *exp,
                 if (exp->ex_fslocs.migrated) {
                         WRITE64(NFS4_REFERRAL_FSID_MAJOR);
                         WRITE64(NFS4_REFERRAL_FSID_MINOR);
-                } else if (is_fsid(fhp, rqstp->rq_reffh)) {
+                } else switch(fsid_source(fhp)) {
+                case FSIDSOURCE_FSID:
                         WRITE64((u64)exp->ex_fsid);
                         WRITE64((u64)0);
-                } else {
+                        break;
+                case FSIDSOURCE_DEV:
                         WRITE32(0);
                         WRITE32(MAJOR(stat.dev));
                         WRITE32(0);
                         WRITE32(MINOR(stat.dev));
+                        break;
+                case FSIDSOURCE_UUID:
+                        WRITEMEM(exp->ex_uuid, 16);
+                        break;
                 }
         }
         if (bmval0 & FATTR4_WORD0_UNIQUE_HANDLES) {
diff --git a/fs/nfsd/nfsctl.c b/fs/nfsd/nfsctl.c
index eedf2e3990a9..71c686dc7257 100644
--- a/fs/nfsd/nfsctl.c
+++ b/fs/nfsd/nfsctl.c
@@ -123,7 +123,7 @@ static ssize_t nfsctl_transaction_write(struct file *file, const char __user *bu
                 return PTR_ERR(data);
 
         rv =  write_op[ino](file, data, size);
-        if (rv>0) {
+        if (rv >= 0) {
                 simple_transaction_set(file, rv);
                 rv = size;
         }
diff --git a/fs/nfsd/nfsfh.c b/fs/nfsd/nfsfh.c
index a0b4282cb284..c2660cbfcd96 100644
--- a/fs/nfsd/nfsfh.c
+++ b/fs/nfsd/nfsfh.c
@@ -9,7 +9,6 @@
  * ... and again Southern-Winter 2001 to support export_operations
  */
 
-#include <linux/sched.h>
 #include <linux/slab.h>
 #include <linux/smp_lock.h>
 #include <linux/fs.h>
@@ -119,9 +118,6 @@ fh_verify(struct svc_rqst *rqstp, struct svc_fh *fhp, int type, int access)
 
         dprintk("nfsd: fh_verify(%s)\n", SVCFH_fmt(fhp));
 
-        /* keep this filehandle for possible reference  when encoding attributes */
-        rqstp->rq_reffh = fh;
-
         if (!fhp->fh_dentry) {
                 __u32 *datap=NULL;
                 __u32 tfh[3];           /* filehandle fragment for oldstyle filehandles */
@@ -146,10 +142,10 @@ fh_verify(struct svc_rqst *rqstp, struct svc_fh *fhp, int type, int access)
                         }
                         len = key_len(fh->fh_fsid_type) / 4;
                         if (len == 0) goto out;
-                        if  (fh->fh_fsid_type == 2) {
+                        if  (fh->fh_fsid_type == FSID_MAJOR_MINOR) {
                                 /* deprecated, convert to type 3 */
-                                len = 3;
-                                fh->fh_fsid_type = 3;
+                                len = key_len(FSID_ENCODE_DEV)/4;
+                                fh->fh_fsid_type = FSID_ENCODE_DEV;
                                 fh->fh_fsid[0] = new_encode_dev(MKDEV(ntohl(fh->fh_fsid[0]), ntohl(fh->fh_fsid[1])));
                                 fh->fh_fsid[1] = fh->fh_fsid[2];
                         }
@@ -164,8 +160,9 @@ fh_verify(struct svc_rqst *rqstp, struct svc_fh *fhp, int type, int access)
                         /* assume old filehandle format */
                         xdev = old_decode_dev(fh->ofh_xdev);
                         xino = u32_to_ino_t(fh->ofh_xino);
-                        mk_fsid_v0(tfh, xdev, xino);
-                        exp = exp_find(rqstp->rq_client, 0, tfh, &rqstp->rq_chandle);
+                        mk_fsid(FSID_DEV, tfh, xdev, xino, 0, NULL);
+                        exp = exp_find(rqstp->rq_client, FSID_DEV, tfh,
+                                       &rqstp->rq_chandle);
                 }
 
                 if (IS_ERR(exp) && (PTR_ERR(exp) == -EAGAIN
@@ -212,7 +209,7 @@ fh_verify(struct svc_rqst *rqstp, struct svc_fh *fhp, int type, int access)
                                 fileid_type = 2;
                 } else
                         fileid_type = fh->fh_fileid_type;
-                
+
                 if (fileid_type == 0)
                         dentry = dget(exp->ex_dentry);
                 else {
@@ -292,7 +289,7 @@ static inline int _fh_update(struct dentry *dentry, struct svc_export *exp,
                              __u32 *datap, int *maxsize)
 {
         struct export_operations *nop = exp->ex_mnt->mnt_sb->s_export_op;
-        
+
         if (dentry == exp->ex_dentry) {
                 *maxsize = 0;
                 return 0;
@@ -317,7 +314,8 @@ static inline void _fh_update_old(struct dentry *dentry,
 }
 
 __be32
-fh_compose(struct svc_fh *fhp, struct svc_export *exp, struct dentry *dentry, struct svc_fh *ref_fh)
+fh_compose(struct svc_fh *fhp, struct svc_export *exp, struct dentry *dentry,
+           struct svc_fh *ref_fh)
 {
         /* ref_fh is a reference file handle.
          * if it is non-null and for the same filesystem, then we should compose
@@ -327,12 +325,13 @@ fh_compose(struct svc_fh *fhp, struct svc_export *exp, struct dentry *dentry, st
          *
          */
 
-        u8 ref_fh_version = 0;
-        u8 ref_fh_fsid_type = 0;
+        u8 version = 1;
+        u8 fsid_type = 0;
         struct inode * inode = dentry->d_inode;
         struct dentry *parent = dentry->d_parent;
         __u32 *datap;
         dev_t ex_dev = exp->ex_dentry->d_inode->i_sb->s_dev;
+        int root_export = (exp->ex_dentry == exp->ex_dentry->d_sb->s_root);
 
         dprintk("nfsd: fh_compose(exp %02x:%02x/%ld %s/%s, ino=%ld)\n",
                 MAJOR(ex_dev), MINOR(ex_dev),
@@ -340,57 +339,64 @@ fh_compose(struct svc_fh *fhp, struct svc_export *exp, struct dentry *dentry, st
                 parent->d_name.name, dentry->d_name.name,
                 (inode ? inode->i_ino : 0));
 
+        /* Choose filehandle version and fsid type based on
+         * the reference filehandle (if it is in the same export)
+         * or the export options.
+         */
         if (ref_fh && ref_fh->fh_export == exp) {
-                ref_fh_version = ref_fh->fh_handle.fh_version;
-                if (ref_fh_version == 0xca)
-                        ref_fh_fsid_type = 0;
+                version = ref_fh->fh_handle.fh_version;
+                if (version == 0xca)
+                        fsid_type = FSID_DEV;
                 else
-                        ref_fh_fsid_type = ref_fh->fh_handle.fh_fsid_type;
-                if (ref_fh_fsid_type > 3)
-                        ref_fh_fsid_type = 0;
-
-                /* make sure ref_fh type works for given export */
-                if (ref_fh_fsid_type == 1 &&
-                    !(exp->ex_flags & NFSEXP_FSID)) {
-                        /* if we don't have an fsid, we cannot provide one... */
-                        ref_fh_fsid_type = 0;
+                        fsid_type = ref_fh->fh_handle.fh_fsid_type;
+                /* We know this version/type works for this export
+                 * so there is no need for further checks.
+                 */
+        } else if (exp->ex_uuid) {
+                if (fhp->fh_maxsize >= 64) {
+                        if (root_export)
+                                fsid_type = FSID_UUID16;
+                        else
+                                fsid_type = FSID_UUID16_INUM;
+                } else {
+                        if (root_export)
+                                fsid_type = FSID_UUID8;
+                        else
+                                fsid_type = FSID_UUID4_INUM;
                 }
         } else if (exp->ex_flags & NFSEXP_FSID)
-                ref_fh_fsid_type = 1;
-
-        if (!old_valid_dev(ex_dev) && ref_fh_fsid_type == 0) {
+                fsid_type = FSID_NUM;
+        else if (!old_valid_dev(ex_dev))
                 /* for newer device numbers, we must use a newer fsid format */
-                ref_fh_version = 1;
-                ref_fh_fsid_type = 3;
-        }
-        if (old_valid_dev(ex_dev) &&
-            (ref_fh_fsid_type == 2 || ref_fh_fsid_type == 3))
-                /* must use type1 for smaller device numbers */
-                ref_fh_fsid_type = 0;
+                fsid_type = FSID_ENCODE_DEV;
+        else
+                fsid_type = FSID_DEV;
 
         if (ref_fh == fhp)
                 fh_put(ref_fh);
 
         if (fhp->fh_locked || fhp->fh_dentry) {
                 printk(KERN_ERR "fh_compose: fh %s/%s not initialized!\n",
-                        parent->d_name.name, dentry->d_name.name);
+                       parent->d_name.name, dentry->d_name.name);
         }
         if (fhp->fh_maxsize < NFS_FHSIZE)
                 printk(KERN_ERR "fh_compose: called with maxsize %d! %s/%s\n",
-                       fhp->fh_maxsize, parent->d_name.name, dentry->d_name.name);
+                       fhp->fh_maxsize,
+                       parent->d_name.name, dentry->d_name.name);
 
         fhp->fh_dentry = dget(dentry); /* our internal copy */
         fhp->fh_export = exp;
         cache_get(&exp->h);
 
-        if (ref_fh_version == 0xca) {
+        if (version == 0xca) {
                 /* old style filehandle please */
                 memset(&fhp->fh_handle.fh_base, 0, NFS_FHSIZE);
                 fhp->fh_handle.fh_size = NFS_FHSIZE;
                 fhp->fh_handle.ofh_dcookie = 0xfeebbaca;
                 fhp->fh_handle.ofh_dev =  old_encode_dev(ex_dev);
                 fhp->fh_handle.ofh_xdev = fhp->fh_handle.ofh_dev;
-                fhp->fh_handle.ofh_xino = ino_t_to_u32(exp->ex_dentry->d_inode->i_ino);
+                fhp->fh_handle.ofh_xino =
+                        ino_t_to_u32(exp->ex_dentry->d_inode->i_ino);
                 fhp->fh_handle.ofh_dirino = ino_t_to_u32(parent_ino(dentry));
                 if (inode)
                         _fh_update_old(dentry, exp, &fhp->fh_handle);
@@ -399,38 +405,12 @@ fh_compose(struct svc_fh *fhp, struct svc_export *exp, struct dentry *dentry, st
                 fhp->fh_handle.fh_version = 1;
                 fhp->fh_handle.fh_auth_type = 0;
                 datap = fhp->fh_handle.fh_auth+0;
-                fhp->fh_handle.fh_fsid_type = ref_fh_fsid_type;
-                switch (ref_fh_fsid_type) {
-                        case 0:
-                                /*
-                                 * fsid_type 0:
-                                 * 2byte major, 2byte minor, 4byte inode
-                                 */
-                                mk_fsid_v0(datap, ex_dev,
-                                        exp->ex_dentry->d_inode->i_ino);
-                                break;
-                        case 1:
-                                /* fsid_type 1 == 4 bytes filesystem id */
-                                mk_fsid_v1(datap, exp->ex_fsid);
-                                break;
-                        case 2:
-                                /*
-                                 * fsid_type 2:
-                                 * 4byte major, 4byte minor, 4byte inode
-                                 */
-                                mk_fsid_v2(datap, ex_dev,
-                                        exp->ex_dentry->d_inode->i_ino);
-                                break;
-                        case 3:
-                                /*
-                                 * fsid_type 3:
-                                 * 4byte devicenumber, 4byte inode
-                                 */
-                                mk_fsid_v3(datap, ex_dev,
-                                        exp->ex_dentry->d_inode->i_ino);
-                                break;
-                }
-                len = key_len(ref_fh_fsid_type);
+                fhp->fh_handle.fh_fsid_type = fsid_type;
+                mk_fsid(fsid_type, datap, ex_dev,
+                        exp->ex_dentry->d_inode->i_ino,
+                        exp->ex_fsid, exp->ex_uuid);
+
+                len = key_len(fsid_type);
                 datap += len/4;
                 fhp->fh_handle.fh_size = 4 + len;
 
@@ -457,7 +437,7 @@ fh_update(struct svc_fh *fhp)
 {
         struct dentry *dentry;
         __u32 *datap;
-        
+
         if (!fhp->fh_dentry)
                 goto out_bad;
 
@@ -534,3 +514,22 @@ char * SVCFH_fmt(struct svc_fh *fhp)
                 fh->fh_base.fh_pad[5]);
         return buf;
 }
+
+enum fsid_source fsid_source(struct svc_fh *fhp)
+{
+        if (fhp->fh_handle.fh_version != 1)
+                return FSIDSOURCE_DEV;
+        switch(fhp->fh_handle.fh_fsid_type) {
+        case FSID_DEV:
+        case FSID_ENCODE_DEV:
+        case FSID_MAJOR_MINOR:
+                return FSIDSOURCE_DEV;
+        case FSID_NUM:
+                return FSIDSOURCE_FSID;
+        default:
+                if (fhp->fh_export->ex_flags & NFSEXP_FSID)
+                        return FSIDSOURCE_FSID;
+                else
+                        return FSIDSOURCE_UUID;
+        }
+}
diff --git a/fs/nfsd/nfsxdr.c b/fs/nfsd/nfsxdr.c
index 6555c50d9006..0c24b9e24fe8 100644
--- a/fs/nfsd/nfsxdr.c
+++ b/fs/nfsd/nfsxdr.c
@@ -153,6 +153,7 @@ encode_fattr(struct svc_rqst *rqstp, __be32 *p, struct svc_fh *fhp,
         struct dentry   *dentry = fhp->fh_dentry;
         int type;
         struct timespec time;
+        u32 f;
 
         type = (stat->mode & S_IFMT);
 
@@ -173,10 +174,22 @@ encode_fattr(struct svc_rqst *rqstp, __be32 *p, struct svc_fh *fhp,
         else
                 *p++ = htonl(0xffffffff);
         *p++ = htonl((u32) stat->blocks);
-        if (is_fsid(fhp, rqstp->rq_reffh))
-                *p++ = htonl((u32) fhp->fh_export->ex_fsid);
-        else
+        switch (fsid_source(fhp)) {
+        default:
+        case FSIDSOURCE_DEV:
                 *p++ = htonl(new_encode_dev(stat->dev));
+                break;
+        case FSIDSOURCE_FSID:
+                *p++ = htonl((u32) fhp->fh_export->ex_fsid);
+                break;
+        case FSIDSOURCE_UUID:
+                f = ((u32*)fhp->fh_export->ex_uuid)[0];
+                f ^= ((u32*)fhp->fh_export->ex_uuid)[1];
+                f ^= ((u32*)fhp->fh_export->ex_uuid)[2];
+                f ^= ((u32*)fhp->fh_export->ex_uuid)[3];
+                *p++ = htonl(f);
+                break;
+        }
         *p++ = htonl((u32) stat->ino);
         *p++ = htonl((u32) stat->atime.tv_sec);
         *p++ = htonl(stat->atime.tv_nsec ? stat->atime.tv_nsec / 1000 : 0);
diff --git a/fs/ntfs/sysctl.c b/fs/ntfs/sysctl.c
index 1c23138d00b3..4847fbfb0107 100644
--- a/fs/ntfs/sysctl.c
+++ b/fs/ntfs/sysctl.c
@@ -33,20 +33,28 @@
 #include "sysctl.h"
 #include "debug.h"
 
-#define FS_NTFS 1
-
 /* Definition of the ntfs sysctl. */
 static ctl_table ntfs_sysctls[] = {
-        { FS_NTFS, "ntfs-debug",                /* Binary and text IDs. */
-          &debug_msgs,sizeof(debug_msgs),       /* Data pointer and size. */
-          0644, NULL, &proc_dointvec },         /* Mode, child, proc handler. */
-        { 0 }
+        {
+                .ctl_name       = CTL_UNNUMBERED,       /* Binary and text IDs. */
+                .procname       = "ntfs-debug",
+                .data           = &debug_msgs,          /* Data pointer and size. */
+                .maxlen         = sizeof(debug_msgs),
+                .mode           = 0644,                 /* Mode, proc handler. */
+                .proc_handler   = &proc_dointvec
+        },
+        {}
 };
 
 /* Define the parent directory /proc/sys/fs. */
 static ctl_table sysctls_root[] = {
-        { CTL_FS, "fs", NULL, 0, 0555, ntfs_sysctls },
-        { 0 }
+        {
+                .ctl_name       = CTL_FS,
+                .procname       = "fs",
+                .mode           = 0555,
+                .child          = ntfs_sysctls
+        },
+        {}
 };
 
 /* Storage for the sysctls header. */
@@ -62,17 +70,9 @@ int ntfs_sysctl(int add)
 {
         if (add) {
                 BUG_ON(sysctls_root_table);
-                sysctls_root_table = register_sysctl_table(sysctls_root, 0);
+                sysctls_root_table = register_sysctl_table(sysctls_root);
                 if (!sysctls_root_table)
                         return -ENOMEM;
-#ifdef CONFIG_PROC_FS
-                /*
-                 * If the proc filesystem is in use and we are a module, need
-                 * to set the owner of our proc entry to our module. In the
-                 * non-modular case, THIS_MODULE is NULL, so this is ok.
-                 */
-                ntfs_sysctls[0].de->owner = THIS_MODULE;
-#endif
         } else {
                 BUG_ON(!sysctls_root_table);
                 unregister_sysctl_table(sysctls_root_table);
diff --git a/fs/ocfs2/cluster/nodemanager.c b/fs/ocfs2/cluster/nodemanager.c
index b17333a0606b..9f5ad0f01ce0 100644
--- a/fs/ocfs2/cluster/nodemanager.c
+++ b/fs/ocfs2/cluster/nodemanager.c
@@ -55,7 +55,7 @@ static ctl_table ocfs2_nm_table[] = {
 
 static ctl_table ocfs2_mod_table[] = {
         {
-                .ctl_name       = KERN_OCFS2_NM,
+                .ctl_name       = FS_OCFS2_NM,
                 .procname       = "nm",
                 .data           = NULL,
                 .maxlen         = 0,
@@ -67,7 +67,7 @@ static ctl_table ocfs2_mod_table[] = {
 
 static ctl_table ocfs2_kern_table[] = {
         {
-                .ctl_name       = KERN_OCFS2,
+                .ctl_name       = FS_OCFS2,
                 .procname       = "ocfs2",
                 .data           = NULL,
                 .maxlen         = 0,
@@ -922,7 +922,7 @@ static int __init init_o2nm(void)
         o2hb_init();
         o2net_init();
 
-        ocfs2_table_header = register_sysctl_table(ocfs2_root_table, 0);
+        ocfs2_table_header = register_sysctl_table(ocfs2_root_table);
         if (!ocfs2_table_header) {
                 printk(KERN_ERR "nodemanager: unable to register sysctl\n");
                 ret = -ENOMEM; /* or something. */
diff --git a/fs/ocfs2/cluster/nodemanager.h b/fs/ocfs2/cluster/nodemanager.h
index 8fb23cacc2f5..070522138ae2 100644
--- a/fs/ocfs2/cluster/nodemanager.h
+++ b/fs/ocfs2/cluster/nodemanager.h
@@ -33,8 +33,7 @@
 #include <linux/configfs.h>
 #include <linux/rbtree.h>
 
-#define KERN_OCFS2              988
-#define KERN_OCFS2_NM           1
+#define FS_OCFS2_NM             1
 
 const char *o2nm_get_hb_ctl_path(void);
 
diff --git a/fs/proc/Makefile b/fs/proc/Makefile
index f6c776272572..a6b3a8f878f0 100644
--- a/fs/proc/Makefile
+++ b/fs/proc/Makefile
@@ -8,7 +8,7 @@ proc-y			:= nommu.o task_nommu.o
 proc-$(CONFIG_MMU)      := mmu.o task_mmu.o
 
 proc-y       += inode.o root.o base.o generic.o array.o \
-                proc_tty.o proc_misc.o
+                proc_tty.o proc_misc.o proc_sysctl.o
 
 proc-$(CONFIG_PROC_KCORE)       += kcore.o
 proc-$(CONFIG_PROC_VMCORE)      += vmcore.o
diff --git a/fs/proc/generic.c b/fs/proc/generic.c
index 0cdc00d9d97e..775fb21294d8 100644
--- a/fs/proc/generic.c
+++ b/fs/proc/generic.c
@@ -32,7 +32,7 @@ static loff_t proc_file_lseek(struct file *, loff_t, int);
 
 DEFINE_SPINLOCK(proc_subdir_lock);
 
-int proc_match(int len, const char *name, struct proc_dir_entry *de)
+static int proc_match(int len, const char *name, struct proc_dir_entry *de)
 {
         if (de->namelen != len)
                 return 0;
diff --git a/fs/proc/inode.c b/fs/proc/inode.c
index f6722be37dde..c372eb151a3a 100644
--- a/fs/proc/inode.c
+++ b/fs/proc/inode.c
@@ -161,6 +161,7 @@ struct inode *proc_get_inode(struct super_block *sb, unsigned int ino,
         if (!inode)
                 goto out_ino;
 
+        PROC_I(inode)->fd = 0;
         PROC_I(inode)->pde = de;
         if (de) {
                 if (de->mode) {
diff --git a/fs/proc/internal.h b/fs/proc/internal.h
index 277dcd66ebe2..c932aa65e198 100644
--- a/fs/proc/internal.h
+++ b/fs/proc/internal.h
@@ -11,6 +11,8 @@
 
 #include <linux/proc_fs.h>
 
+extern int proc_sys_init(void);
+
 struct vmalloc_info {
         unsigned long   used;
         unsigned long   largest_chunk;
diff --git a/fs/proc/proc_sysctl.c b/fs/proc/proc_sysctl.c
new file mode 100644
index 000000000000..20e8cbb34364
--- /dev/null
+++ b/fs/proc/proc_sysctl.c
@@ -0,0 +1,479 @@
+/*
+ * /proc/sys support
+ */
+
+#include <linux/sysctl.h>
+#include <linux/proc_fs.h>
+#include <linux/security.h>
+#include "internal.h"
+
+static struct dentry_operations proc_sys_dentry_operations;
+static const struct file_operations proc_sys_file_operations;
+static struct inode_operations proc_sys_inode_operations;
+
+static void proc_sys_refresh_inode(struct inode *inode, struct ctl_table *table)
+{
+        /* Refresh the cached information bits in the inode */
+        if (table) {
+                inode->i_uid = 0;
+                inode->i_gid = 0;
+                inode->i_mode = table->mode;
+                if (table->proc_handler) {
+                        inode->i_mode |= S_IFREG;
+                        inode->i_nlink = 1;
+                } else {
+                        inode->i_mode |= S_IFDIR;
+                        inode->i_nlink = 0;     /* It is too hard to figure out */
+                }
+        }
+}
+
+static struct inode *proc_sys_make_inode(struct inode *dir, struct ctl_table *table)
+{
+        struct inode *inode;
+        struct proc_inode *dir_ei, *ei;
+        int depth;
+
+        inode = new_inode(dir->i_sb);
+        if (!inode)
+                goto out;
+
+        /* A directory is always one deeper than it's parent */
+        dir_ei = PROC_I(dir);
+        depth = dir_ei->fd + 1;
+
+        ei = PROC_I(inode);
+        ei->fd = depth;
+        inode->i_mtime = inode->i_atime = inode->i_ctime = CURRENT_TIME;
+        inode->i_op = &proc_sys_inode_operations;
+        inode->i_fop = &proc_sys_file_operations;
+        inode->i_flags |= S_PRIVATE; /* tell selinux to ignore this inode */
+        proc_sys_refresh_inode(inode, table);
+out:
+        return inode;
+}
+
+static struct dentry *proc_sys_ancestor(struct dentry *dentry, int depth)
+{
+        for (;;) {
+                struct proc_inode *ei;
+
+                ei = PROC_I(dentry->d_inode);
+                if (ei->fd == depth)
+                        break; /* found */
+
+                dentry = dentry->d_parent;
+        }
+        return dentry;
+}
+
+static struct ctl_table *proc_sys_lookup_table_one(struct ctl_table *table,
+                                                        struct qstr *name)
+{
+        int len;
+        for ( ; table->ctl_name || table->procname; table++) {
+
+                if (!table->procname)
+                        continue;
+
+                len = strlen(table->procname);
+                if (len != name->len)
+                        continue;
+
+                if (memcmp(table->procname, name->name, len) != 0)
+                        continue;
+
+                /* I have a match */
+                return table;
+        }
+        return NULL;
+}
+
+static struct ctl_table *proc_sys_lookup_table(struct dentry *dentry,
+                                                struct ctl_table *table)
+{
+        struct dentry *ancestor;
+        struct proc_inode *ei;
+        int depth, i;
+
+        ei = PROC_I(dentry->d_inode);
+        depth = ei->fd;
+
+        if (depth == 0)
+                return table;
+
+        for (i = 1; table && (i <= depth); i++) {
+                ancestor = proc_sys_ancestor(dentry, i);
+                table = proc_sys_lookup_table_one(table, &ancestor->d_name);
+                if (table)
+                        table = table->child;
+        }
+        return table;
+
+}
+static struct ctl_table *proc_sys_lookup_entry(struct dentry *dparent,
+                                                struct qstr *name,
+                                                struct ctl_table *table)
+{
+        table = proc_sys_lookup_table(dparent, table);
+        if (table)
+                table = proc_sys_lookup_table_one(table, name);
+        return table;
+}
+
+static struct ctl_table *do_proc_sys_lookup(struct dentry *parent,
+                                                struct qstr *name,
+                                                struct ctl_table_header **ptr)
+{
+        struct ctl_table_header *head;
+        struct ctl_table *table = NULL;
+
+        for (head = sysctl_head_next(NULL); head;
+                        head = sysctl_head_next(head)) {
+                table = proc_sys_lookup_entry(parent, name, head->ctl_table);
+                if (table)
+                        break;
+        }
+        *ptr = head;
+        return table;
+}
+
+static struct dentry *proc_sys_lookup(struct inode *dir, struct dentry *dentry,
+                                        struct nameidata *nd)
+{
+        struct ctl_table_header *head;
+        struct inode *inode;
+        struct dentry *err;
+        struct ctl_table *table;
+
+        err = ERR_PTR(-ENOENT);
+        table = do_proc_sys_lookup(dentry->d_parent, &dentry->d_name, &head);
+        if (!table)
+                goto out;
+
+        err = ERR_PTR(-ENOMEM);
+        inode = proc_sys_make_inode(dir, table);
+        if (!inode)
+                goto out;
+
+        err = NULL;
+        dentry->d_op = &proc_sys_dentry_operations;
+        d_add(dentry, inode);
+
+out:
+        sysctl_head_finish(head);
+        return err;
+}
+
+static ssize_t proc_sys_read(struct file *filp, char __user *buf,
+                                size_t count, loff_t *ppos)
+{
+        struct dentry *dentry = filp->f_dentry;
+        struct ctl_table_header *head;
+        struct ctl_table *table;
+        ssize_t error, res;
+
+        table = do_proc_sys_lookup(dentry->d_parent, &dentry->d_name, &head);
+        /* Has the sysctl entry disappeared on us? */
+        error = -ENOENT;
+        if (!table)
+                goto out;
+
+        /* Has the sysctl entry been replaced by a directory? */
+        error = -EISDIR;
+        if (!table->proc_handler)
+                goto out;
+
+        /*
+         * At this point we know that the sysctl was not unregistered
+         * and won't be until we finish.
+         */
+        error = -EPERM;
+        if (sysctl_perm(table, MAY_READ))
+                goto out;
+
+        /* careful: calling conventions are nasty here */
+        res = count;
+        error = table->proc_handler(table, 0, filp, buf, &res, ppos);
+        if (!error)
+                error = res;
+out:
+        sysctl_head_finish(head);
+
+        return error;
+}
+
+static ssize_t proc_sys_write(struct file *filp, const char __user *buf,
+                                size_t count, loff_t *ppos)
+{
+        struct dentry *dentry = filp->f_dentry;
+        struct ctl_table_header *head;
+        struct ctl_table *table;
+        ssize_t error, res;
+
+        table = do_proc_sys_lookup(dentry->d_parent, &dentry->d_name, &head);
+        /* Has the sysctl entry disappeared on us? */
+        error = -ENOENT;
+        if (!table)
+                goto out;
+
+        /* Has the sysctl entry been replaced by a directory? */
+        error = -EISDIR;
+        if (!table->proc_handler)
+                goto out;
+
+        /*
+         * At this point we know that the sysctl was not unregistered
+         * and won't be until we finish.
+         */
+        error = -EPERM;
+        if (sysctl_perm(table, MAY_WRITE))
+                goto out;
+
+        /* careful: calling conventions are nasty here */
+        res = count;
+        error = table->proc_handler(table, 1, filp, (char __user *)buf,
+                                    &res, ppos);
+        if (!error)
+                error = res;
+out:
+        sysctl_head_finish(head);
+
+        return error;
+}
+
+
+static int proc_sys_fill_cache(struct file *filp, void *dirent,
+                                filldir_t filldir, struct ctl_table *table)
+{
+        struct ctl_table_header *head;
+        struct ctl_table *child_table = NULL;
+        struct dentry *child, *dir = filp->f_path.dentry;
+        struct inode *inode;
+        struct qstr qname;
+        ino_t ino = 0;
+        unsigned type = DT_UNKNOWN;
+        int ret;
+
+        qname.name = table->procname;
+        qname.len  = strlen(table->procname);
+        qname.hash = full_name_hash(qname.name, qname.len);
+
+        /* Suppress duplicates.
+         * Only fill a directory entry if it is the value that
+         * an ordinary lookup of that name returns.  Hide all
+         * others.
+         *
+         * If we ever cache this translation in the dcache
+         * I should do a dcache lookup first.  But for now
+         * it is just simpler not to.
+         */
+        ret = 0;
+        child_table = do_proc_sys_lookup(dir, &qname, &head);
+        sysctl_head_finish(head);
+        if (child_table != table)
+                return 0;
+
+        child = d_lookup(dir, &qname);
+        if (!child) {
+                struct dentry *new;
+                new = d_alloc(dir, &qname);
+                if (new) {
+                        inode = proc_sys_make_inode(dir->d_inode, table);
+                        if (!inode)
+                                child = ERR_PTR(-ENOMEM);
+                        else {
+                                new->d_op = &proc_sys_dentry_operations;
+                                d_add(new, inode);
+                        }
+                        if (child)
+                                dput(new);
+                        else
+                                child = new;
+                }
+        }
+        if (!child || IS_ERR(child) || !child->d_inode)
+                goto end_instantiate;
+        inode = child->d_inode;
+        if (inode) {
+                ino  = inode->i_ino;
+                type = inode->i_mode >> 12;
+        }
+        dput(child);
+end_instantiate:
+        if (!ino)
+                ino= find_inode_number(dir, &qname);
+        if (!ino)
+                ino = 1;
+        return filldir(dirent, qname.name, qname.len, filp->f_pos, ino, type);
+}
+
+static int proc_sys_readdir(struct file *filp, void *dirent, filldir_t filldir)
+{
+        struct dentry *dentry = filp->f_dentry;
+        struct inode *inode = dentry->d_inode;
+        struct ctl_table_header *head = NULL;
+        struct ctl_table *table;
+        unsigned long pos;
+        int ret;
+
+        ret = -ENOTDIR;
+        if (!S_ISDIR(inode->i_mode))
+                goto out;
+
+        ret = 0;
+        /* Avoid a switch here: arm builds fail with missing __cmpdi2 */
+        if (filp->f_pos == 0) {
+                if (filldir(dirent, ".", 1, filp->f_pos,
+                                inode->i_ino, DT_DIR) < 0)
+                        goto out;
+                filp->f_pos++;
+        }
+        if (filp->f_pos == 1) {
+                if (filldir(dirent, "..", 2, filp->f_pos,
+                                parent_ino(dentry), DT_DIR) < 0)
+                        goto out;
+                filp->f_pos++;
+        }
+        pos = 2;
+
+        /* - Find each instance of the directory
+         * - Read all entries in each instance
+         * - Before returning an entry to user space lookup the entry
+         *   by name and if I find a different entry don't return
+         *   this one because it means it is a buried dup.
+         * For sysctl this should only happen for directory entries.
+         */
+        for (head = sysctl_head_next(NULL); head; head = sysctl_head_next(head)) {
+                table = proc_sys_lookup_table(dentry, head->ctl_table);
+
+                if (!table)
+                        continue;
+
+                for (; table->ctl_name || table->procname; table++, pos++) {
+                        /* Can't do anything without a proc name */
+                        if (!table->procname)
+                                continue;
+
+                        if (pos < filp->f_pos)
+                                continue;
+
+                        if (proc_sys_fill_cache(filp, dirent, filldir, table) < 0)
+                                goto out;
+                        filp->f_pos = pos + 1;
+                }
+        }
+        ret = 1;
+out:
+        sysctl_head_finish(head);
+        return ret;
+}
+
+static int proc_sys_permission(struct inode *inode, int mask, struct nameidata *nd)
+{
+        /*
+         * sysctl entries that are not writeable,
+         * are _NOT_ writeable, capabilities or not.
+         */
+        struct ctl_table_header *head;
+        struct ctl_table *table;
+        struct dentry *dentry;
+        int mode;
+        int depth;
+        int error;
+
+        head = NULL;
+        depth = PROC_I(inode)->fd;
+
+        /* First check the cached permissions, in case we don't have
+         * enough information to lookup the sysctl table entry.
+         */
+        error = -EACCES;
+        mode = inode->i_mode;
+
+        if (current->euid == 0)
+                mode >>= 6;
+        else if (in_group_p(0))
+                mode >>= 3;
+
+        if ((mode & mask & (MAY_READ|MAY_WRITE|MAY_EXEC)) == mask)
+                error = 0;
+
+        /* If we can't get a sysctl table entry the permission
+         * checks on the cached mode will have to be enough.
+         */
+        if (!nd || !depth)
+                goto out;
+
+        dentry = nd->dentry;
+        table = do_proc_sys_lookup(dentry->d_parent, &dentry->d_name, &head);
+
+        /* If the entry does not exist deny permission */
+        error = -EACCES;
+        if (!table)
+                goto out;
+
+        /* Use the permissions on the sysctl table entry */
+        error = sysctl_perm(table, mask);
+out:
+        sysctl_head_finish(head);
+        return error;
+}
+
+static int proc_sys_setattr(struct dentry *dentry, struct iattr *attr)
+{
+        struct inode *inode = dentry->d_inode;
+        int error;
+
+        if (attr->ia_valid & (ATTR_MODE | ATTR_UID | ATTR_GID))
+                return -EPERM;
+
+        error = inode_change_ok(inode, attr);
+        if (!error) {
+                error = security_inode_setattr(dentry, attr);
+                if (!error)
+                        error = inode_setattr(inode, attr);
+        }
+
+        return error;
+}
+
+/* I'm lazy and don't distinguish between files and directories,
+ * until access time.
+ */
+static const struct file_operations proc_sys_file_operations = {
+        .read           = proc_sys_read,
+        .write          = proc_sys_write,
+        .readdir        = proc_sys_readdir,
+};
+
+static struct inode_operations proc_sys_inode_operations = {
+        .lookup         = proc_sys_lookup,
+        .permission     = proc_sys_permission,
+        .setattr        = proc_sys_setattr,
+};
+
+static int proc_sys_revalidate(struct dentry *dentry, struct nameidata *nd)
+{
+        struct ctl_table_header *head;
+        struct ctl_table *table;
+        table = do_proc_sys_lookup(dentry->d_parent, &dentry->d_name, &head);
+        proc_sys_refresh_inode(dentry->d_inode, table);
+        sysctl_head_finish(head);
+        return !!table;
+}
+
+static struct dentry_operations proc_sys_dentry_operations = {
+        .d_revalidate   = proc_sys_revalidate,
+};
+
+static struct proc_dir_entry *proc_sys_root;
+
+int proc_sys_init(void)
+{
+        proc_sys_root = proc_mkdir("sys", NULL);
+        proc_sys_root->proc_iops = &proc_sys_inode_operations;
+        proc_sys_root->proc_fops = &proc_sys_file_operations;
+        proc_sys_root->nlink = 0;
+        return 0;
+}
diff --git a/fs/proc/root.c b/fs/proc/root.c
index af154458b540..5834a744c2a9 100644
--- a/fs/proc/root.c
+++ b/fs/proc/root.c
@@ -23,10 +23,6 @@
 
 struct proc_dir_entry *proc_net, *proc_net_stat, *proc_bus, *proc_root_fs, *proc_root_driver;
 
-#ifdef CONFIG_SYSCTL
-struct proc_dir_entry *proc_sys_root;
-#endif
-
 static int proc_get_sb(struct file_system_type *fs_type,
         int flags, const char *dev_name, void *data, struct vfsmount *mnt)
 {
@@ -71,13 +67,6 @@ void __init proc_root_init(void)
 #ifdef CONFIG_SYSVIPC
         proc_mkdir("sysvipc", NULL);
 #endif
-#ifdef CONFIG_SYSCTL
-        proc_sys_root = proc_mkdir("sys", NULL);
-#endif
-#if defined(CONFIG_BINFMT_MISC) || defined(CONFIG_BINFMT_MISC_MODULE)
-        proc_mkdir("sys/fs", NULL);
-        proc_mkdir("sys/fs/binfmt_misc", NULL);
-#endif
         proc_root_fs = proc_mkdir("fs", NULL);
         proc_root_driver = proc_mkdir("driver", NULL);
         proc_mkdir("fs/nfsd", NULL); /* somewhere for the nfsd filesystem to be mounted */
@@ -90,6 +79,9 @@ void __init proc_root_init(void)
         proc_device_tree_init();
 #endif
         proc_bus = proc_mkdir("bus", NULL);
+#ifdef CONFIG_SYSCTL
+        proc_sys_init();
+#endif
 }
 
 static int proc_root_getattr(struct vfsmount *mnt, struct dentry *dentry, struct kstat *stat
diff --git a/fs/smbfs/symlink.c b/fs/smbfs/symlink.c
index e4bf3456d07e..fea20ceb8a5f 100644
--- a/fs/smbfs/symlink.c
+++ b/fs/smbfs/symlink.c
@@ -6,7 +6,6 @@
  *  Please add a note about your changes to smbfs in the ChangeLog file.
  */
 
-#include <linux/sched.h>
 #include <linux/kernel.h>
 #include <linux/errno.h>
 #include <linux/fcntl.h>
diff --git a/fs/ufs/balloc.c b/fs/ufs/balloc.c
index 0e97a4f79c31..bcc44084e004 100644
--- a/fs/ufs/balloc.c
+++ b/fs/ufs/balloc.c
@@ -16,7 +16,6 @@
 #include <linux/quotaops.h>
 #include <linux/buffer_head.h>
 #include <linux/capability.h>
-#include <linux/sched.h>
 #include <linux/bitops.h>
 #include <asm/byteorder.h>
 
diff --git a/fs/ufs/dir.c b/fs/ufs/dir.c
index a6c0ca9f48bf..4890ddf1518e 100644
--- a/fs/ufs/dir.c
+++ b/fs/ufs/dir.c
@@ -20,7 +20,6 @@
 #include <linux/fs.h>
 #include <linux/ufs_fs.h>
 #include <linux/smp_lock.h>
-#include <linux/sched.h>
 
 #include "swab.h"
 #include "util.h"
diff --git a/fs/xattr_acl.c b/fs/xattr_acl.c
index 789a2559bd54..c6ad7c7e3ee9 100644
--- a/fs/xattr_acl.c
+++ b/fs/xattr_acl.c
@@ -6,7 +6,6 @@
  */
 
 #include <linux/module.h>
-#include <linux/sched.h>
 #include <linux/slab.h>
 #include <linux/fs.h>
 #include <linux/posix_acl_xattr.h>
diff --git a/fs/xfs/linux-2.6/kmem.c b/fs/xfs/linux-2.6/kmem.c
index 004baf600611..ed2b16dff914 100644
--- a/fs/xfs/linux-2.6/kmem.c
+++ b/fs/xfs/linux-2.6/kmem.c
@@ -15,7 +15,6 @@
  * along with this program; if not, write the Free Software Foundation,
  * Inc.,  51 Franklin St, Fifth Floor, Boston, MA  02110-1301  USA
  */
-#include <linux/sched.h>
 #include <linux/mm.h>
 #include <linux/vmalloc.h>
 #include <linux/highmem.h>
diff --git a/fs/xfs/linux-2.6/xfs_sysctl.c b/fs/xfs/linux-2.6/xfs_sysctl.c
index 5c46c35a97a5..cd6eaa44aa2b 100644
--- a/fs/xfs/linux-2.6/xfs_sysctl.c
+++ b/fs/xfs/linux-2.6/xfs_sysctl.c
@@ -251,7 +251,7 @@ static ctl_table xfs_root_table[] = {
 void
 xfs_sysctl_register(void)
 {
-        xfs_table_header = register_sysctl_table(xfs_root_table, 0);
+        xfs_table_header = register_sysctl_table(xfs_root_table);
 }
 
 void