78 files changed, 998 insertions, 874 deletions
diff --git a/fs/Kconfig b/fs/Kconfig
index 455aa207e67e..d4bf8caad8d0 100644
--- a/fs/Kconfig
+++ b/fs/Kconfig
@@ -109,6 +109,7 @@ source "fs/sysfs/Kconfig"
 config TMPFS
        bool "Virtual memory file system support (former shm fs)"
+        depends on SHMEM
        help
          Tmpfs is a file system which keeps all files in virtual memory.
diff --git a/fs/afs/flock.c b/fs/afs/flock.c
index 3ff8bdd18fb3..0931bc1325eb 100644
--- a/fs/afs/flock.c
+++ b/fs/afs/flock.c
@@ -21,7 +21,7 @@ static void afs_fl_release_private(struct file_lock *fl);
 static struct workqueue_struct *afs_lock_manager;
 static DEFINE_MUTEX(afs_lock_manager_mutex);
-static struct file_lock_operations afs_lock_ops = {
+static const struct file_lock_operations afs_lock_ops = {
        .fl_copy_lock           = afs_fl_copy_lock,
        .fl_release_private     = afs_fl_release_private,
 };
diff --git a/fs/aio.c b/fs/aio.c
index d065b2c3273e..fc21c23b2387 100644
--- a/fs/aio.c
+++ b/fs/aio.c
@@ -24,6 +24,7 @@
 #include <linux/file.h>
 #include <linux/mm.h>
 #include <linux/mman.h>
+#include <linux/mmu_context.h>
 #include <linux/slab.h>
 #include <linux/timer.h>
 #include <linux/aio.h>
@@ -34,7 +35,6 @@
 #include <asm/kmap_types.h>
 #include <asm/uaccess.h>
-#include <asm/mmu_context.h>
 #if DEBUG > 1
 #define dprintk         printk
@@ -595,51 +595,6 @@ static struct kioctx *lookup_ioctx(unsigned long ctx_id)
 }
 /*
- * use_mm
- *      Makes the calling kernel thread take on the specified
- *      mm context.
- *      Called by the retry thread execute retries within the
- *      iocb issuer's mm context, so that copy_from/to_user
- *      operations work seamlessly for aio.
- *      (Note: this routine is intended to be called only
- *      from a kernel thread context)
- */
-static void use_mm(struct mm_struct *mm)
-{
-        struct mm_struct *active_mm;
-        struct task_struct *tsk = current;
-        task_lock(tsk);
-        active_mm = tsk->active_mm;
-        atomic_inc(&mm->mm_count);
-        tsk->mm = mm;
-        tsk->active_mm = mm;
-        switch_mm(active_mm, mm, tsk);
-        task_unlock(tsk);
-        mmdrop(active_mm);
-}
-/*
- * unuse_mm
- *      Reverses the effect of use_mm, i.e. releases the
- *      specified mm context which was earlier taken on
- *      by the calling kernel thread
- *      (Note: this routine is intended to be called only
- *      from a kernel thread context)
- */
-static void unuse_mm(struct mm_struct *mm)
-{
-        struct task_struct *tsk = current;
-        task_lock(tsk);
-        tsk->mm = NULL;
-        /* active_mm is still 'mm' */
-        enter_lazy_tlb(mm, tsk);
-        task_unlock(tsk);
-}
-/*
 * Queue up a kiocb to be retried. Assumes that the kiocb
 * has already been marked as kicked, and places it on
 * the retry run list for the corresponding ioctx, if it
diff --git a/fs/autofs/dirhash.c b/fs/autofs/dirhash.c
index 2316e944a109..e947915109e5 100644
--- a/fs/autofs/dirhash.c
+++ b/fs/autofs/dirhash.c
@@ -90,7 +90,7 @@ struct autofs_dir_ent *autofs_expire(struct super_block *sb,
                        DPRINTK(("autofs: not expirable (not a mounted directory): %s\n", ent->name));
                        continue;
                }
-                while (d_mountpoint(path.dentry) && follow_down(&path));
+                while (d_mountpoint(path.dentry) && follow_down(&path))
                        ;
                umount_ok = may_umount(path.mnt);
                path_put(&path);
diff --git a/fs/befs/linuxvfs.c b/fs/befs/linuxvfs.c
index 615d5496fe0f..dd376c124e71 100644
--- a/fs/befs/linuxvfs.c
+++ b/fs/befs/linuxvfs.c
@@ -842,7 +842,7 @@ befs_fill_super(struct super_block *sb, void *data, int silent)
        sb->s_magic = BEFS_SUPER_MAGIC;
        /* Set real blocksize of fs */
        sb_set_blocksize(sb, (ulong) befs_sb->block_size);
-        sb->s_op = (struct super_operations *) &befs_sops;
+        sb->s_op = &befs_sops;
        root = befs_iget(sb, iaddr2blockno(sb, &(befs_sb->root_dir)));
        if (IS_ERR(root)) {
                ret = PTR_ERR(root);
diff --git a/fs/binfmt_elf.c b/fs/binfmt_elf.c
index 7c1e65d54872..442d94fe255c 100644
--- a/fs/binfmt_elf.c
+++ b/fs/binfmt_elf.c
@@ -1280,9 +1280,6 @@ static int writenote(struct memelfnote *men, struct file *file,
 #define DUMP_WRITE(addr, nr)    \
        if ((size += (nr)) > limit || !dump_write(file, (addr), (nr))) \
                goto end_coredump;
-#define DUMP_SEEK(off)  \
-        if (!dump_seek(file, (off))) \
-                goto end_coredump;
 static void fill_elf_header(struct elfhdr *elf, int segs,
                            u16 machine, u32 flags, u8 osabi)
@@ -2016,7 +2013,8 @@ static int elf_core_dump(long signr, struct pt_regs *regs, struct file *file, un
                goto end_coredump;
        /* Align to page */
-        DUMP_SEEK(dataoff - foffset);
+        if (!dump_seek(file, dataoff - foffset))
+                goto end_coredump;
        for (vma = first_vma(current, gate_vma); vma != NULL;
                        vma = next_vma(vma, gate_vma)) {
@@ -2027,33 +2025,19 @@ static int elf_core_dump(long signr, struct pt_regs *regs, struct file *file, un
                for (addr = vma->vm_start; addr < end; addr += PAGE_SIZE) {
                        struct page *page;
-                        struct vm_area_struct *tmp_vma;
+                        int stop;
-                        if (get_user_pages(current, current->mm, addr, 1, 0, 1,
+                        page = get_dump_page(addr);
-                                                &page, &tmp_vma) <= 0) {
+                        if (page) {
-                                DUMP_SEEK(PAGE_SIZE);
+                                void *kaddr = kmap(page);
-                        } else {
+                                stop = ((size += PAGE_SIZE) > limit) ||
-                                if (page == ZERO_PAGE(0)) {
+                                        !dump_write(file, kaddr, PAGE_SIZE);
-                                        if (!dump_seek(file, PAGE_SIZE)) {
+                                kunmap(page);
-                                                page_cache_release(page);
-                                                goto end_coredump;
-                                        }
-                                } else {
-                                        void *kaddr;
-                                        flush_cache_page(tmp_vma, addr,
-                                                         page_to_pfn(page));
-                                        kaddr = kmap(page);
-                                        if ((size += PAGE_SIZE) > limit ||
-                                            !dump_write(file, kaddr,
-                                            PAGE_SIZE)) {
-                                                kunmap(page);
-                                                page_cache_release(page);
-                                                goto end_coredump;
-                                        }
-                                        kunmap(page);
-                                }
                                page_cache_release(page);
-                        }
+                        } else
+                                stop = !dump_seek(file, PAGE_SIZE);
+                        if (stop)
+                                goto end_coredump;
                }
        }
diff --git a/fs/binfmt_elf_fdpic.c b/fs/binfmt_elf_fdpic.c
index 20fbeced472b..76285471073e 100644
--- a/fs/binfmt_elf_fdpic.c
+++ b/fs/binfmt_elf_fdpic.c
@@ -1325,9 +1325,6 @@ static int writenote(struct memelfnote *men, struct file *file)
 #define DUMP_WRITE(addr, nr)    \
        if ((size += (nr)) > limit || !dump_write(file, (addr), (nr))) \
                goto end_coredump;
-#define DUMP_SEEK(off)  \
-        if (!dump_seek(file, (off))) \
-                goto end_coredump;
 static inline void fill_elf_fdpic_header(struct elfhdr *elf, int segs)
 {
@@ -1518,6 +1515,7 @@ static int elf_fdpic_dump_segments(struct file *file, size_t *size,
                           unsigned long *limit, unsigned long mm_flags)
 {
        struct vm_area_struct *vma;
+        int err = 0;
        for (vma = current->mm->mmap; vma; vma = vma->vm_next) {
                unsigned long addr;
@@ -1525,43 +1523,26 @@ static int elf_fdpic_dump_segments(struct file *file, size_t *size,
                if (!maydump(vma, mm_flags))
                        continue;
-                for (addr = vma->vm_start;
+                for (addr = vma->vm_start; addr < vma->vm_end;
-                     addr < vma->vm_end;
+                                                        addr += PAGE_SIZE) {
-                     addr += PAGE_SIZE
+                        struct page *page = get_dump_page(addr);
-                     ) {
+                        if (page) {
-                        struct vm_area_struct *vma;
+                                void *kaddr = kmap(page);
-                        struct page *page;
+                                *size += PAGE_SIZE;
+                                if (*size > *limit)
-                        if (get_user_pages(current, current->mm, addr, 1, 0, 1,
+                                        err = -EFBIG;
-                                           &page, &vma) <= 0) {
+                                else if (!dump_write(file, kaddr, PAGE_SIZE))
-                                DUMP_SEEK(file->f_pos + PAGE_SIZE);
+                                        err = -EIO;
-                        }
-                        else if (page == ZERO_PAGE(0)) {
-                                page_cache_release(page);
-                                DUMP_SEEK(file->f_pos + PAGE_SIZE);
-                        }
-                        else {
-                                void *kaddr;
-                                flush_cache_page(vma, addr, page_to_pfn(page));
-                                kaddr = kmap(page);
-                                if ((*size += PAGE_SIZE) > *limit ||
-                                    !dump_write(file, kaddr, PAGE_SIZE)
-                                    ) {
-                                        kunmap(page);
-                                        page_cache_release(page);
-                                        return -EIO;
-                                }
                                kunmap(page);
                                page_cache_release(page);
-                        }
+                        } else if (!dump_seek(file, file->f_pos + PAGE_SIZE))
+                                err = -EFBIG;
+                        if (err)
+                                goto out;
                }
        }
+out:
-        return 0;
+        return err;
-end_coredump:
-        return -EFBIG;
 }
 #endif
@@ -1802,7 +1783,8 @@ static int elf_fdpic_core_dump(long signr, struct pt_regs *regs,
                                goto end_coredump;
        }
-        DUMP_SEEK(dataoff);
+        if (!dump_seek(file, dataoff))
+                goto end_coredump;
        if (elf_fdpic_dump_segments(file, &size, &limit, mm_flags) < 0)
                goto end_coredump;
diff --git a/fs/block_dev.c b/fs/block_dev.c
index 71e7e03ac343..5d1ed50bd46c 100644
--- a/fs/block_dev.c
+++ b/fs/block_dev.c
@@ -1114,7 +1114,7 @@ EXPORT_SYMBOL(revalidate_disk);
 int check_disk_change(struct block_device *bdev)
 {
        struct gendisk *disk = bdev->bd_disk;
-        struct block_device_operations * bdops = disk->fops;
+        const struct block_device_operations *bdops = disk->fops;
        if (!bdops->media_changed)
                return 0;
diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c
index 8b8192790011..6c4173146bb7 100644
--- a/fs/btrfs/disk-io.c
+++ b/fs/btrfs/disk-io.c
@@ -772,7 +772,7 @@ static void btree_invalidatepage(struct page *page, unsigned long offset)
        }
 }
-static struct address_space_operations btree_aops = {
+static const struct address_space_operations btree_aops = {
        .readpage       = btree_readpage,
        .writepage      = btree_writepage,
        .writepages     = btree_writepages,
diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index 59cba180fe83..9096fd0ca3ca 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -55,13 +55,13 @@ struct btrfs_iget_args {
        struct btrfs_root *root;
 };
-static struct inode_operations btrfs_dir_inode_operations;
+static const struct inode_operations btrfs_dir_inode_operations;
-static struct inode_operations btrfs_symlink_inode_operations;
+static const struct inode_operations btrfs_symlink_inode_operations;
-static struct inode_operations btrfs_dir_ro_inode_operations;
+static const struct inode_operations btrfs_dir_ro_inode_operations;
-static struct inode_operations btrfs_special_inode_operations;
+static const struct inode_operations btrfs_special_inode_operations;
-static struct inode_operations btrfs_file_inode_operations;
+static const struct inode_operations btrfs_file_inode_operations;
-static struct address_space_operations btrfs_aops;
+static const struct address_space_operations btrfs_aops;
-static struct address_space_operations btrfs_symlink_aops;
+static const struct address_space_operations btrfs_symlink_aops;
 static struct file_operations btrfs_dir_file_operations;
 static struct extent_io_ops btrfs_extent_io_ops;
@@ -5201,7 +5201,7 @@ static int btrfs_permission(struct inode *inode, int mask)
        return generic_permission(inode, mask, btrfs_check_acl);
 }
-static struct inode_operations btrfs_dir_inode_operations = {
+static const struct inode_operations btrfs_dir_inode_operations = {
        .getattr        = btrfs_getattr,
        .lookup         = btrfs_lookup,
        .create         = btrfs_create,
@@ -5219,7 +5219,7 @@ static struct inode_operations btrfs_dir_inode_operations = {
        .removexattr    = btrfs_removexattr,
        .permission     = btrfs_permission,
 };
-static struct inode_operations btrfs_dir_ro_inode_operations = {
+static const struct inode_operations btrfs_dir_ro_inode_operations = {
        .lookup         = btrfs_lookup,
        .permission     = btrfs_permission,
 };
@@ -5259,7 +5259,7 @@ static struct extent_io_ops btrfs_extent_io_ops = {
 *
 * For now we're avoiding this by dropping bmap.
 */
-static struct address_space_operations btrfs_aops = {
+static const struct address_space_operations btrfs_aops = {
        .readpage       = btrfs_readpage,
        .writepage      = btrfs_writepage,
        .writepages     = btrfs_writepages,
@@ -5271,14 +5271,14 @@ static struct address_space_operations btrfs_aops = {
        .set_page_dirty = btrfs_set_page_dirty,
 };
-static struct address_space_operations btrfs_symlink_aops = {
+static const struct address_space_operations btrfs_symlink_aops = {
        .readpage       = btrfs_readpage,
        .writepage      = btrfs_writepage,
        .invalidatepage = btrfs_invalidatepage,
        .releasepage    = btrfs_releasepage,
 };
-static struct inode_operations btrfs_file_inode_operations = {
+static const struct inode_operations btrfs_file_inode_operations = {
        .truncate       = btrfs_truncate,
        .getattr        = btrfs_getattr,
        .setattr        = btrfs_setattr,
@@ -5290,7 +5290,7 @@ static struct inode_operations btrfs_file_inode_operations = {
        .fallocate      = btrfs_fallocate,
        .fiemap         = btrfs_fiemap,
 };
-static struct inode_operations btrfs_special_inode_operations = {
+static const struct inode_operations btrfs_special_inode_operations = {
        .getattr        = btrfs_getattr,
        .setattr        = btrfs_setattr,
        .permission     = btrfs_permission,
@@ -5299,7 +5299,7 @@ static struct inode_operations btrfs_special_inode_operations = {
        .listxattr      = btrfs_listxattr,
        .removexattr    = btrfs_removexattr,
 };
-static struct inode_operations btrfs_symlink_inode_operations = {
+static const struct inode_operations btrfs_symlink_inode_operations = {
        .readlink       = generic_readlink,
        .follow_link    = page_follow_link_light,
        .put_link       = page_put_link,
diff --git a/fs/btrfs/super.c b/fs/btrfs/super.c
index 6d6d06cb6dfc..2db17cd66fc5 100644
--- a/fs/btrfs/super.c
+++ b/fs/btrfs/super.c
@@ -51,7 +51,7 @@
 #include "export.h"
 #include "compression.h"
-static struct super_operations btrfs_super_ops;
+static const struct super_operations btrfs_super_ops;
 static void btrfs_put_super(struct super_block *sb)
 {
@@ -675,7 +675,7 @@ static int btrfs_unfreeze(struct super_block *sb)
        return 0;
 }
-static struct super_operations btrfs_super_ops = {
+static const struct super_operations btrfs_super_ops = {
        .delete_inode   = btrfs_delete_inode,
        .put_super      = btrfs_put_super,
        .sync_fs        = btrfs_sync_fs,
diff --git a/fs/btrfs/tree-log.c b/fs/btrfs/tree-log.c
index d91b0de7c502..30c0d45c1b5e 100644
--- a/fs/btrfs/tree-log.c
+++ b/fs/btrfs/tree-log.c
@@ -2605,7 +2605,7 @@ static noinline int copy_items(struct btrfs_trans_handle *trans,
                                                                extent);
                                cs = btrfs_file_extent_offset(src, extent);
                                cl = btrfs_file_extent_num_bytes(src,
-                                                                extent);;
+                                                                extent);
                                if (btrfs_file_extent_compression(src,
                                                                  extent)) {
                                        cs = 0;
diff --git a/fs/cifs/cifs_dfs_ref.c b/fs/cifs/cifs_dfs_ref.c
index 606912d8f2a8..fea9e898c4ba 100644
--- a/fs/cifs/cifs_dfs_ref.c
+++ b/fs/cifs/cifs_dfs_ref.c
@@ -142,7 +142,7 @@ char *cifs_compose_mount_options(const char *sb_mountdata,
        rc = dns_resolve_server_name_to_ip(*devname, &srvIP);
        if (rc != 0) {
                cERROR(1, ("%s: Failed to resolve server part of %s to IP: %d",
-                          __func__, *devname, rc));;
+                          __func__, *devname, rc));
                goto compose_mount_options_err;
        }
        /* md_len = strlen(...) + 12 for 'sep+prefixpath='
@@ -385,7 +385,7 @@ out_err:
        goto out;
 }
-struct inode_operations cifs_dfs_referral_inode_operations = {
+const struct inode_operations cifs_dfs_referral_inode_operations = {
        .follow_link = cifs_dfs_follow_mountpoint,
 };
diff --git a/fs/cifs/cifsfs.c b/fs/cifs/cifsfs.c
index 3610e9958b4c..d79ce2e95c23 100644
--- a/fs/cifs/cifsfs.c
+++ b/fs/cifs/cifsfs.c
@@ -50,7 +50,7 @@
 #define CIFS_MAGIC_NUMBER 0xFF534D42    /* the first four bytes of SMB PDUs */
 #ifdef CONFIG_CIFS_QUOTA
-static struct quotactl_ops cifs_quotactl_ops;
+static const struct quotactl_ops cifs_quotactl_ops;
 #endif /* QUOTA */
 int cifsFYI = 0;
@@ -517,7 +517,7 @@ int cifs_xstate_get(struct super_block *sb, struct fs_quota_stat *qstats)
        return rc;
 }
-static struct quotactl_ops cifs_quotactl_ops = {
+static const struct quotactl_ops cifs_quotactl_ops = {
        .set_xquota     = cifs_xquota_set,
        .get_xquota     = cifs_xquota_get,
        .set_xstate     = cifs_xstate_set,
diff --git a/fs/cifs/cifsfs.h b/fs/cifs/cifsfs.h
index 094325e3f714..ac2b24c192f8 100644
--- a/fs/cifs/cifsfs.h
+++ b/fs/cifs/cifsfs.h
@@ -67,7 +67,7 @@ extern int cifs_setattr(struct dentry *, struct iattr *);
 extern const struct inode_operations cifs_file_inode_ops;
 extern const struct inode_operations cifs_symlink_inode_ops;
-extern struct inode_operations cifs_dfs_referral_inode_operations;
+extern const struct inode_operations cifs_dfs_referral_inode_operations;
 /* Functions related to files and directories */
diff --git a/fs/ecryptfs/ecryptfs_kernel.h b/fs/ecryptfs/ecryptfs_kernel.h
index 00b30a2d5466..542f625312f3 100644
--- a/fs/ecryptfs/ecryptfs_kernel.h
+++ b/fs/ecryptfs/ecryptfs_kernel.h
@@ -582,7 +582,7 @@ extern const struct inode_operations ecryptfs_dir_iops;
 extern const struct inode_operations ecryptfs_symlink_iops;
 extern const struct super_operations ecryptfs_sops;
 extern const struct dentry_operations ecryptfs_dops;
-extern struct address_space_operations ecryptfs_aops;
+extern const struct address_space_operations ecryptfs_aops;
 extern int ecryptfs_verbosity;
 extern unsigned int ecryptfs_message_buf_len;
 extern signed long ecryptfs_message_wait_timeout;
diff --git a/fs/ecryptfs/mmap.c b/fs/ecryptfs/mmap.c
index 5c6bab9786e3..05772aeaa8f4 100644
--- a/fs/ecryptfs/mmap.c
+++ b/fs/ecryptfs/mmap.c
@@ -545,7 +545,7 @@ static sector_t ecryptfs_bmap(struct address_space *mapping, sector_t block)
        return rc;
 }
-struct address_space_operations ecryptfs_aops = {
+const struct address_space_operations ecryptfs_aops = {
        .writepage = ecryptfs_writepage,
        .readpage = ecryptfs_readpage,
        .write_begin = ecryptfs_write_begin,
diff --git a/fs/ext2/xip.c b/fs/ext2/xip.c
index b72b85884223..c18fbf3e4068 100644
--- a/fs/ext2/xip.c
+++ b/fs/ext2/xip.c
@@ -20,7 +20,7 @@ __inode_direct_access(struct inode *inode, sector_t block,
                      void **kaddr, unsigned long *pfn)
 {
        struct block_device *bdev = inode->i_sb->s_bdev;
-        struct block_device_operations *ops = bdev->bd_disk->fops;
+        const struct block_device_operations *ops = bdev->bd_disk->fops;
        sector_t sector;
        sector = block * (PAGE_SIZE / 512); /* ext2 block to bdev sector */
diff --git a/fs/ext3/super.c b/fs/ext3/super.c
index a8d80a7f1105..72743d360509 100644
--- a/fs/ext3/super.c
+++ b/fs/ext3/super.c
@@ -720,7 +720,7 @@ static ssize_t ext3_quota_read(struct super_block *sb, int type, char *data,
 static ssize_t ext3_quota_write(struct super_block *sb, int type,
                                const char *data, size_t len, loff_t off);
-static struct dquot_operations ext3_quota_operations = {
+static const struct dquot_operations ext3_quota_operations = {
        .initialize     = dquot_initialize,
        .drop           = dquot_drop,
        .alloc_space    = dquot_alloc_space,
@@ -737,7 +737,7 @@ static struct dquot_operations ext3_quota_operations = {
        .destroy_dquot  = dquot_destroy,
 };
-static struct quotactl_ops ext3_qctl_operations = {
+static const struct quotactl_ops ext3_qctl_operations = {
        .quota_on       = ext3_quota_on,
        .quota_off      = vfs_quota_off,
        .quota_sync     = vfs_quota_sync,
diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
index 4abd683b963d..3a798737e305 100644
--- a/fs/ext4/inode.c
+++ b/fs/ext4/inode.c
@@ -2337,7 +2337,7 @@ static int __mpage_da_writepage(struct page *page,
                /*
                 * Rest of the page in the page_vec
                 * redirty then and skip then. We will
-                 * try to to write them again after
+                 * try to write them again after
                 * starting a new transaction
                 */
                redirty_page_for_writepage(wbc, page);
diff --git a/fs/ext4/super.c b/fs/ext4/super.c
index a6b1ab734728..df539ba27779 100644
--- a/fs/ext4/super.c
+++ b/fs/ext4/super.c
@@ -964,7 +964,7 @@ static ssize_t ext4_quota_read(struct super_block *sb, int type, char *data,
 static ssize_t ext4_quota_write(struct super_block *sb, int type,
                                const char *data, size_t len, loff_t off);
-static struct dquot_operations ext4_quota_operations = {
+static const struct dquot_operations ext4_quota_operations = {
        .initialize     = dquot_initialize,
        .drop           = dquot_drop,
        .alloc_space    = dquot_alloc_space,
@@ -985,7 +985,7 @@ static struct dquot_operations ext4_quota_operations = {
        .destroy_dquot  = dquot_destroy,
 };
-static struct quotactl_ops ext4_qctl_operations = {
+static const struct quotactl_ops ext4_qctl_operations = {
        .quota_on       = ext4_quota_on,
        .quota_off      = vfs_quota_off,
        .quota_sync     = vfs_quota_sync,
diff --git a/fs/gfs2/rgrp.c b/fs/gfs2/rgrp.c
index 28c590b7c9da..8f1cfb02a6cb 100644
--- a/fs/gfs2/rgrp.c
+++ b/fs/gfs2/rgrp.c
@@ -179,7 +179,7 @@ static inline u64 gfs2_bit_search(const __le64 *ptr, u64 mask, u8 state)
 * always aligned to a 64 bit boundary.
 *
 * The size of the buffer is in bytes, but is it assumed that it is
- * always ok to to read a complete multiple of 64 bits at the end
+ * always ok to read a complete multiple of 64 bits at the end
 * of the block in case the end is no aligned to a natural boundary.
 *
 * Return: the block number (bitmap buffer scope) that was found
diff --git a/fs/hugetlbfs/inode.c b/fs/hugetlbfs/inode.c
index a93b885311d8..06b7c2623f99 100644
--- a/fs/hugetlbfs/inode.c
+++ b/fs/hugetlbfs/inode.c
@@ -507,6 +507,13 @@ static struct inode *hugetlbfs_get_inode(struct super_block *sb, uid_t uid,
                inode->i_atime = inode->i_mtime = inode->i_ctime = CURRENT_TIME;
                INIT_LIST_HEAD(&inode->i_mapping->private_list);
                info = HUGETLBFS_I(inode);
+                /*
+                 * The policy is initialized here even if we are creating a
+                 * private inode because initialization simply creates an
+                 * an empty rb tree and calls spin_lock_init(), later when we
+                 * call mpol_free_shared_policy() it will just return because
+                 * the rb tree will still be empty.
+                 */
                mpol_shared_policy_init(&info->policy, NULL);
                switch (mode & S_IFMT) {
                default:
@@ -931,13 +938,19 @@ static struct file_system_type hugetlbfs_fs_type = {
 static struct vfsmount *hugetlbfs_vfsmount;
-static int can_do_hugetlb_shm(void)
+static int can_do_hugetlb_shm(int creat_flags)
 {
-        return capable(CAP_IPC_LOCK) || in_group_p(sysctl_hugetlb_shm_group);
+        if (creat_flags != HUGETLB_SHMFS_INODE)
+                return 0;
+        if (capable(CAP_IPC_LOCK))
+                return 1;
+        if (in_group_p(sysctl_hugetlb_shm_group))
+                return 1;
+        return 0;
 }
 struct file *hugetlb_file_setup(const char *name, size_t size, int acctflag,
-                                                struct user_struct **user)
+                                struct user_struct **user, int creat_flags)
 {
        int error = -ENOMEM;
        struct file *file;
@@ -949,7 +962,7 @@ struct file *hugetlb_file_setup(const char *name, size_t size, int acctflag,
        if (!hugetlbfs_vfsmount)
                return ERR_PTR(-ENOENT);
-        if (!can_do_hugetlb_shm()) {
+        if (!can_do_hugetlb_shm(creat_flags)) {
                *user = current_user();
                if (user_shm_lock(size, *user)) {
                        WARN_ONCE(1,
diff --git a/fs/inode.c b/fs/inode.c
index b2ba83d2c4e1..f5ff71cb3e2b 100644
--- a/fs/inode.c
+++ b/fs/inode.c
@@ -123,7 +123,7 @@ static void wake_up_inode(struct inode *inode)
 int inode_init_always(struct super_block *sb, struct inode *inode)
 {
        static const struct address_space_operations empty_aops;
-        static struct inode_operations empty_iops;
+        static const struct inode_operations empty_iops;
        static const struct file_operations empty_fops;
        struct address_space *const mapping = &inode->i_data;
@@ -695,13 +695,15 @@ void unlock_new_inode(struct inode *inode)
        }
 #endif
        /*
-         * This is special!  We do not need the spinlock
+         * This is special!  We do not need the spinlock when clearing I_LOCK,
-         * when clearing I_LOCK, because we're guaranteed
+         * because we're guaranteed that nobody else tries to do anything about
-         * that nobody else tries to do anything about the
+         * the state of the inode when it is locked, as we just created it (so
-         * state of the inode when it is locked, as we
+         * there can be no old holders that haven't tested I_LOCK).
-         * just created it (so there can be no old holders
+         * However we must emit the memory barrier so that other CPUs reliably
-         * that haven't tested I_LOCK).
+         * see the clearing of I_LOCK after the other inode initialisation has
+         * completed.
         */
+        smp_mb();
        WARN_ON((inode->i_state & (I_LOCK|I_NEW)) != (I_LOCK|I_NEW));
        inode->i_state &= ~(I_LOCK|I_NEW);
        wake_up_inode(inode);
diff --git a/fs/jffs2/super.c b/fs/jffs2/super.c
index 0035c021395a..9a80e8e595d0 100644
--- a/fs/jffs2/super.c
+++ b/fs/jffs2/super.c
@@ -123,7 +123,7 @@ static struct dentry *jffs2_get_parent(struct dentry *child)
        return d_obtain_alias(jffs2_iget(child->d_inode->i_sb, pino));
 }
-static struct export_operations jffs2_export_ops = {
+static const struct export_operations jffs2_export_ops = {
        .get_parent = jffs2_get_parent,
        .fh_to_dentry = jffs2_fh_to_dentry,
        .fh_to_parent = jffs2_fh_to_parent,
diff --git a/fs/lockd/clntlock.c b/fs/lockd/clntlock.c
index 1f3b0fc0d351..fc9032dc8862 100644
--- a/fs/lockd/clntlock.c
+++ b/fs/lockd/clntlock.c
@@ -166,7 +166,7 @@ __be32 nlmclnt_grant(const struct sockaddr *addr, const struct nlm_lock *lock)
                 */
                if (fl_blocked->fl_u.nfs_fl.owner->pid != lock->svid)
                        continue;
-                if (!nlm_cmp_addr(nlm_addr(block->b_host), addr))
+                if (!rpc_cmp_addr(nlm_addr(block->b_host), addr))
                        continue;
                if (nfs_compare_fh(NFS_FH(fl_blocked->fl_file->f_path.dentry->d_inode) ,fh) != 0)
                        continue;
diff --git a/fs/lockd/clntproc.c b/fs/lockd/clntproc.c
index 4336adba952a..c81249fef11f 100644
--- a/fs/lockd/clntproc.c
+++ b/fs/lockd/clntproc.c
@@ -458,7 +458,7 @@ static void nlmclnt_locks_release_private(struct file_lock *fl)
        nlm_put_lockowner(fl->fl_u.nfs_fl.owner);
 }
-static struct file_lock_operations nlmclnt_lock_ops = {
+static const struct file_lock_operations nlmclnt_lock_ops = {
        .fl_copy_lock = nlmclnt_locks_copy_lock,
        .fl_release_private = nlmclnt_locks_release_private,
 };
diff --git a/fs/lockd/host.c b/fs/lockd/host.c
index 7cb076ac6b45..4600c2037b8b 100644
--- a/fs/lockd/host.c
+++ b/fs/lockd/host.c
@@ -111,7 +111,7 @@ static struct nlm_host *nlm_lookup_host(struct nlm_lookup_host_info *ni)
         */
        chain = &nlm_hosts[nlm_hash_address(ni->sap)];
        hlist_for_each_entry(host, pos, chain, h_hash) {
-                if (!nlm_cmp_addr(nlm_addr(host), ni->sap))
+                if (!rpc_cmp_addr(nlm_addr(host), ni->sap))
                        continue;
                /* See if we have an NSM handle for this client */
@@ -125,7 +125,7 @@ static struct nlm_host *nlm_lookup_host(struct nlm_lookup_host_info *ni)
                if (host->h_server != ni->server)
                        continue;
                if (ni->server &&
-                    !nlm_cmp_addr(nlm_srcaddr(host), ni->src_sap))
+                    !rpc_cmp_addr(nlm_srcaddr(host), ni->src_sap))
                        continue;
                /* Move to head of hash chain. */
diff --git a/fs/lockd/mon.c b/fs/lockd/mon.c
index 30c933188dd7..f956651d0f65 100644
--- a/fs/lockd/mon.c
+++ b/fs/lockd/mon.c
@@ -209,7 +209,7 @@ static struct nsm_handle *nsm_lookup_addr(const struct sockaddr *sap)
        struct nsm_handle *nsm;
        list_for_each_entry(nsm, &nsm_handles, sm_link)
-                if (nlm_cmp_addr(nsm_addr(nsm), sap))
+                if (rpc_cmp_addr(nsm_addr(nsm), sap))
                        return nsm;
        return NULL;
 }
diff --git a/fs/lockd/svclock.c b/fs/lockd/svclock.c
index e577a78d7bac..d1001790fa9a 100644
--- a/fs/lockd/svclock.c
+++ b/fs/lockd/svclock.c
@@ -705,7 +705,7 @@ static int nlmsvc_same_owner(struct file_lock *fl1, struct file_lock *fl2)
        return fl1->fl_owner == fl2->fl_owner && fl1->fl_pid == fl2->fl_pid;
 }
-struct lock_manager_operations nlmsvc_lock_operations = {
+const struct lock_manager_operations nlmsvc_lock_operations = {
        .fl_compare_owner = nlmsvc_same_owner,
        .fl_notify = nlmsvc_notify_blocked,
        .fl_grant = nlmsvc_grant_deferred,
diff --git a/fs/lockd/svcsubs.c b/fs/lockd/svcsubs.c
index 9e4d6aab611b..ad478da7ca63 100644
--- a/fs/lockd/svcsubs.c
+++ b/fs/lockd/svcsubs.c
@@ -417,7 +417,7 @@ EXPORT_SYMBOL_GPL(nlmsvc_unlock_all_by_sb);
 static int
 nlmsvc_match_ip(void *datap, struct nlm_host *host)
 {
-        return nlm_cmp_addr(nlm_srcaddr(host), datap);
+        return rpc_cmp_addr(nlm_srcaddr(host), datap);
 }
 /**
diff --git a/fs/locks.c b/fs/locks.c
index 19ee18a6829b..a8794f233bc9 100644
--- a/fs/locks.c
+++ b/fs/locks.c
@@ -434,7 +434,7 @@ static int lease_mylease_callback(struct file_lock *fl, struct file_lock *try)
        return fl->fl_file == try->fl_file;
 }
-static struct lock_manager_operations lease_manager_ops = {
+static const struct lock_manager_operations lease_manager_ops = {
        .fl_break = lease_break_callback,
        .fl_release_private = lease_release_private_callback,
        .fl_mylease = lease_mylease_callback,
diff --git a/fs/nfs/callback_xdr.c b/fs/nfs/callback_xdr.c
index e5a2dac5f715..76b0aa0f73bf 100644
--- a/fs/nfs/callback_xdr.c
+++ b/fs/nfs/callback_xdr.c
@@ -222,7 +222,7 @@ static unsigned decode_sessionid(struct xdr_stream *xdr,
        p = read_buf(xdr, len);
        if (unlikely(p == NULL))
-                return htonl(NFS4ERR_RESOURCE);;
+                return htonl(NFS4ERR_RESOURCE);
        memcpy(sid->data, p, len);
        return 0;
diff --git a/fs/nfs/nfs4state.c b/fs/nfs/nfs4state.c
index 1434080aefeb..2ef4fecf3984 100644
--- a/fs/nfs/nfs4state.c
+++ b/fs/nfs/nfs4state.c
@@ -638,7 +638,7 @@ static void nfs4_fl_release_lock(struct file_lock *fl)
        nfs4_put_lock_state(fl->fl_u.nfs4_fl.owner);
 }
-static struct file_lock_operations nfs4_fl_lock_ops = {
+static const struct file_lock_operations nfs4_fl_lock_ops = {
        .fl_copy_lock = nfs4_fl_copy_lock,
        .fl_release_private = nfs4_fl_release_lock,
 };
diff --git a/fs/nfsd/export.c b/fs/nfsd/export.c
index d9462643155c..984a5ebcc1d6 100644
--- a/fs/nfsd/export.c
+++ b/fs/nfsd/export.c
@@ -1341,6 +1341,8 @@ exp_pseudoroot(struct svc_rqst *rqstp, struct svc_fh *fhp)
        if (rv)
                goto out;
        rv = check_nfsd_access(exp, rqstp);
+        if (rv)
+                fh_put(fhp);
 out:
        exp_put(exp);
        return rv;
diff --git a/fs/nfsd/nfs3xdr.c b/fs/nfsd/nfs3xdr.c
index 01d4ec1c88e0..edf926e1062f 100644
--- a/fs/nfsd/nfs3xdr.c
+++ b/fs/nfsd/nfs3xdr.c
@@ -814,17 +814,6 @@ encode_entry_baggage(struct nfsd3_readdirres *cd, __be32 *p, const char *name,
        return p;
 }
-static __be32 *
-encode_entryplus_baggage(struct nfsd3_readdirres *cd, __be32 *p,
-                struct svc_fh *fhp)
-{
-        p = encode_post_op_attr(cd->rqstp, p, fhp);
-        *p++ = xdr_one;                 /* yes, a file handle follows */
-        p = encode_fh(p, fhp);
-        fh_put(fhp);
-        return p;
-}
 static int
 compose_entry_fh(struct nfsd3_readdirres *cd, struct svc_fh *fhp,
                const char *name, int namlen)
@@ -836,29 +825,54 @@ compose_entry_fh(struct nfsd3_readdirres *cd, struct svc_fh *fhp,
        dparent = cd->fh.fh_dentry;
        exp  = cd->fh.fh_export;
-        fh_init(fhp, NFS3_FHSIZE);
        if (isdotent(name, namlen)) {
                if (namlen == 2) {
                        dchild = dget_parent(dparent);
                        if (dchild == dparent) {
                                /* filesystem root - cannot return filehandle for ".." */
                                dput(dchild);
-                                return 1;
+                                return -ENOENT;
                        }
                } else
                        dchild = dget(dparent);
        } else
                dchild = lookup_one_len(name, dparent, namlen);
        if (IS_ERR(dchild))
-                return 1;
+                return -ENOENT;
-        if (d_mountpoint(dchild) ||
+        rv = -ENOENT;
-            fh_compose(fhp, exp, dchild, &cd->fh) != 0 ||
+        if (d_mountpoint(dchild))
-            !dchild->d_inode)
+                goto out;
-                rv = 1;
+        rv = fh_compose(fhp, exp, dchild, &cd->fh);
+        if (rv)
+                goto out;
+        if (!dchild->d_inode)
+                goto out;
+        rv = 0;
+out:
        dput(dchild);
        return rv;
 }
+__be32 *encode_entryplus_baggage(struct nfsd3_readdirres *cd, __be32 *p, const char *name, int namlen)
+{
+        struct svc_fh   fh;
+        int err;
+        fh_init(&fh, NFS3_FHSIZE);
+        err = compose_entry_fh(cd, &fh, name, namlen);
+        if (err) {
+                *p++ = 0;
+                *p++ = 0;
+                goto out;
+        }
+        p = encode_post_op_attr(cd->rqstp, p, &fh);
+        *p++ = xdr_one;                 /* yes, a file handle follows */
+        p = encode_fh(p, &fh);
+out:
+        fh_put(&fh);
+        return p;
+}
 /*
 * Encode a directory entry. This one works for both normal readdir
 * and readdirplus.
@@ -929,16 +943,8 @@ encode_entry(struct readdir_cd *ccd, const char *name, int namlen,
                p = encode_entry_baggage(cd, p, name, namlen, ino);
-                /* throw in readdirplus baggage */
+                if (plus)
-                if (plus) {
+                        p = encode_entryplus_baggage(cd, p, name, namlen);
-                        struct svc_fh   fh;
-                        if (compose_entry_fh(cd, &fh, name, namlen) > 0) {
-                                *p++ = 0;
-                                *p++ = 0;
-                        } else
-                                p = encode_entryplus_baggage(cd, p, &fh);
-                }
                num_entry_words = p - cd->buffer;
        } else if (cd->rqstp->rq_respages[pn+1] != NULL) {
                /* temporarily encode entry into next page, then move back to
@@ -951,17 +957,8 @@ encode_entry(struct readdir_cd *ccd, const char *name, int namlen,
                p1 = encode_entry_baggage(cd, p1, name, namlen, ino);
-                /* throw in readdirplus baggage */
+                if (plus)
-                if (plus) {
+                        p = encode_entryplus_baggage(cd, p1, name, namlen);
-                        struct svc_fh   fh;
-                        if (compose_entry_fh(cd, &fh, name, namlen) > 0) {
-                                /* zero out the filehandle */
-                                *p1++ = 0;
-                                *p1++ = 0;
-                        } else
-                                p1 = encode_entryplus_baggage(cd, p1, &fh);
-                }
                /* determine entry word length and lengths to go in pages */
                num_entry_words = p1 - tmp;
diff --git a/fs/nfsd/nfs4acl.c b/fs/nfsd/nfs4acl.c
index 54b8b4140c8f..725d02f210e2 100644
--- a/fs/nfsd/nfs4acl.c
+++ b/fs/nfsd/nfs4acl.c
@@ -321,7 +321,7 @@ _posix_to_nfsv4_one(struct posix_acl *pacl, struct nfs4_acl *acl,
        deny = ~pas.group & pas.other;
        if (deny) {
                ace->type = NFS4_ACE_ACCESS_DENIED_ACE_TYPE;
-                ace->flag = eflag | NFS4_ACE_IDENTIFIER_GROUP;
+                ace->flag = eflag;
                ace->access_mask = deny_mask_from_posix(deny, flags);
                ace->whotype = NFS4_ACL_WHO_GROUP;
                ace++;
@@ -335,7 +335,7 @@ _posix_to_nfsv4_one(struct posix_acl *pacl, struct nfs4_acl *acl,
                if (deny) {
                        ace->type = NFS4_ACE_ACCESS_DENIED_ACE_TYPE;
                        ace->flag = eflag | NFS4_ACE_IDENTIFIER_GROUP;
-                        ace->access_mask = mask_from_posix(deny, flags);
+                        ace->access_mask = deny_mask_from_posix(deny, flags);
                        ace->whotype = NFS4_ACL_WHO_NAMED;
                        ace->who = pa->e_id;
                        ace++;
diff --git a/fs/nfsd/nfs4callback.c b/fs/nfsd/nfs4callback.c
index 3fd23f7aceca..24e8d78f8dde 100644
--- a/fs/nfsd/nfs4callback.c
+++ b/fs/nfsd/nfs4callback.c
@@ -43,25 +43,30 @@
 #include <linux/sunrpc/xdr.h>
 #include <linux/sunrpc/svc.h>
 #include <linux/sunrpc/clnt.h>
+#include <linux/sunrpc/svcsock.h>
 #include <linux/nfsd/nfsd.h>
 #include <linux/nfsd/state.h>
 #include <linux/sunrpc/sched.h>
 #include <linux/nfs4.h>
+#include <linux/sunrpc/xprtsock.h>
 #define NFSDDBG_FACILITY                NFSDDBG_PROC
 #define NFSPROC4_CB_NULL 0
 #define NFSPROC4_CB_COMPOUND 1
+#define NFS4_STATEID_SIZE 16
 /* Index of predefined Linux callback client operations */
 enum {
-        NFSPROC4_CLNT_CB_NULL = 0,
+        NFSPROC4_CLNT_CB_NULL = 0,
        NFSPROC4_CLNT_CB_RECALL,
+        NFSPROC4_CLNT_CB_SEQUENCE,
 };
 enum nfs_cb_opnum4 {
        OP_CB_RECALL            = 4,
+        OP_CB_SEQUENCE          = 11,
 };
 #define NFS4_MAXTAGLEN          20
@@ -70,17 +75,29 @@ enum nfs_cb_opnum4 {
 #define NFS4_dec_cb_null_sz             0
 #define cb_compound_enc_hdr_sz          4
 #define cb_compound_dec_hdr_sz          (3 + (NFS4_MAXTAGLEN >> 2))
+#define sessionid_sz                    (NFS4_MAX_SESSIONID_LEN >> 2)
+#define cb_sequence_enc_sz              (sessionid_sz + 4 +             \
+                                        1 /* no referring calls list yet */)
+#define cb_sequence_dec_sz              (op_dec_sz + sessionid_sz + 4)
 #define op_enc_sz                       1
 #define op_dec_sz                       2
 #define enc_nfs4_fh_sz                  (1 + (NFS4_FHSIZE >> 2))
 #define enc_stateid_sz                  (NFS4_STATEID_SIZE >> 2)
 #define NFS4_enc_cb_recall_sz           (cb_compound_enc_hdr_sz +       \
+                                        cb_sequence_enc_sz +            \
                                        1 + enc_stateid_sz +            \
                                        enc_nfs4_fh_sz)
 #define NFS4_dec_cb_recall_sz           (cb_compound_dec_hdr_sz  +      \
+                                        cb_sequence_dec_sz +            \
                                        op_dec_sz)
+struct nfs4_rpc_args {
+        void                            *args_op;
+        struct nfsd4_cb_sequence        args_seq;
+};
 /*
 * Generic encode routines from fs/nfs/nfs4xdr.c
 */
@@ -137,11 +154,13 @@ xdr_error:                                      \
 } while (0)
 struct nfs4_cb_compound_hdr {
-        int             status;
+        /* args */
-        u32             ident;
+        u32             ident;  /* minorversion 0 only */
        u32             nops;
        __be32          *nops_p;
        u32             minorversion;
+        /* res */
+        int             status;
        u32             taglen;
        char            *tag;
 };
@@ -238,6 +257,27 @@ encode_cb_recall(struct xdr_stream *xdr, struct nfs4_delegation *dp,
        hdr->nops++;
 }
+static void
+encode_cb_sequence(struct xdr_stream *xdr, struct nfsd4_cb_sequence *args,
+                   struct nfs4_cb_compound_hdr *hdr)
+{
+        __be32 *p;
+        if (hdr->minorversion == 0)
+                return;
+        RESERVE_SPACE(1 + NFS4_MAX_SESSIONID_LEN + 20);
+        WRITE32(OP_CB_SEQUENCE);
+        WRITEMEM(args->cbs_clp->cl_sessionid.data, NFS4_MAX_SESSIONID_LEN);
+        WRITE32(args->cbs_clp->cl_cb_seq_nr);
+        WRITE32(0);             /* slotid, always 0 */
+        WRITE32(0);             /* highest slotid always 0 */
+        WRITE32(0);             /* cachethis always 0 */
+        WRITE32(0); /* FIXME: support referring_call_lists */
+        hdr->nops++;
+}
 static int
 nfs4_xdr_enc_cb_null(struct rpc_rqst *req, __be32 *p)
 {
@@ -249,15 +289,19 @@ nfs4_xdr_enc_cb_null(struct rpc_rqst *req, __be32 *p)
 }
 static int
-nfs4_xdr_enc_cb_recall(struct rpc_rqst *req, __be32 *p, struct nfs4_delegation *args)
+nfs4_xdr_enc_cb_recall(struct rpc_rqst *req, __be32 *p,
+                struct nfs4_rpc_args *rpc_args)
 {
        struct xdr_stream xdr;
+        struct nfs4_delegation *args = rpc_args->args_op;
        struct nfs4_cb_compound_hdr hdr = {
                .ident = args->dl_ident,
+                .minorversion = rpc_args->args_seq.cbs_minorversion,
        };
        xdr_init_encode(&xdr, &req->rq_snd_buf, p);
        encode_cb_compound_hdr(&xdr, &hdr);
+        encode_cb_sequence(&xdr, &rpc_args->args_seq, &hdr);
        encode_cb_recall(&xdr, args, &hdr);
        encode_cb_nops(&hdr);
        return 0;
@@ -299,6 +343,57 @@ decode_cb_op_hdr(struct xdr_stream *xdr, enum nfs_opnum4 expected)
        return 0;
 }
+/*
+ * Our current back channel implmentation supports a single backchannel
+ * with a single slot.
+ */
+static int
+decode_cb_sequence(struct xdr_stream *xdr, struct nfsd4_cb_sequence *res,
+                   struct rpc_rqst *rqstp)
+{
+        struct nfs4_sessionid id;
+        int status;
+        u32 dummy;
+        __be32 *p;
+        if (res->cbs_minorversion == 0)
+                return 0;
+        status = decode_cb_op_hdr(xdr, OP_CB_SEQUENCE);
+        if (status)
+                return status;
+        /*
+         * If the server returns different values for sessionID, slotID or
+         * sequence number, the server is looney tunes.
+         */
+        status = -ESERVERFAULT;
+        READ_BUF(NFS4_MAX_SESSIONID_LEN + 16);
+        memcpy(id.data, p, NFS4_MAX_SESSIONID_LEN);
+        p += XDR_QUADLEN(NFS4_MAX_SESSIONID_LEN);
+        if (memcmp(id.data, res->cbs_clp->cl_sessionid.data,
+                   NFS4_MAX_SESSIONID_LEN)) {
+                dprintk("%s Invalid session id\n", __func__);
+                goto out;
+        }
+        READ32(dummy);
+        if (dummy != res->cbs_clp->cl_cb_seq_nr) {
+                dprintk("%s Invalid sequence number\n", __func__);
+                goto out;
+        }
+        READ32(dummy);  /* slotid must be 0 */
+        if (dummy != 0) {
+                dprintk("%s Invalid slotid\n", __func__);
+                goto out;
+        }
+        /* FIXME: process highest slotid and target highest slotid */
+        status = 0;
+out:
+        return status;
+}
 static int
 nfs4_xdr_dec_cb_null(struct rpc_rqst *req, __be32 *p)
 {
@@ -306,7 +401,8 @@ nfs4_xdr_dec_cb_null(struct rpc_rqst *req, __be32 *p)
 }
 static int
-nfs4_xdr_dec_cb_recall(struct rpc_rqst *rqstp, __be32 *p)
+nfs4_xdr_dec_cb_recall(struct rpc_rqst *rqstp, __be32 *p,
+                struct nfsd4_cb_sequence *seq)
 {
        struct xdr_stream xdr;
        struct nfs4_cb_compound_hdr hdr;
@@ -316,6 +412,11 @@ nfs4_xdr_dec_cb_recall(struct rpc_rqst *rqstp, __be32 *p)
        status = decode_cb_compound_hdr(&xdr, &hdr);
        if (status)
                goto out;
+        if (seq) {
+                status = decode_cb_sequence(&xdr, seq, rqstp);
+                if (status)
+                        goto out;
+        }
        status = decode_cb_op_hdr(&xdr, OP_CB_RECALL);
 out:
        return status;
@@ -377,16 +478,15 @@ static int max_cb_time(void)
 int setup_callback_client(struct nfs4_client *clp)
 {
-        struct sockaddr_in      addr;
        struct nfs4_cb_conn *cb = &clp->cl_cb_conn;
        struct rpc_timeout      timeparms = {
                .to_initval     = max_cb_time(),
                .to_retries     = 0,
        };
        struct rpc_create_args args = {
-                .protocol       = IPPROTO_TCP,
+                .protocol       = XPRT_TRANSPORT_TCP,
-                .address        = (struct sockaddr *)&addr,
+                .address        = (struct sockaddr *) &cb->cb_addr,
-                .addrsize       = sizeof(addr),
+                .addrsize       = cb->cb_addrlen,
                .timeout        = &timeparms,
                .program        = &cb_program,
                .prognumber     = cb->cb_prog,
@@ -399,13 +499,10 @@ int setup_callback_client(struct nfs4_client *clp)
        if (!clp->cl_principal && (clp->cl_flavor >= RPC_AUTH_GSS_KRB5))
                return -EINVAL;
+        if (cb->cb_minorversion) {
-        /* Initialize address */
+                args.bc_xprt = clp->cl_cb_xprt;
-        memset(&addr, 0, sizeof(addr));
+                args.protocol = XPRT_TRANSPORT_BC_TCP;
-        addr.sin_family = AF_INET;
+        }
-        addr.sin_port = htons(cb->cb_port);
-        addr.sin_addr.s_addr = htonl(cb->cb_addr);
        /* Create RPC client */
        client = rpc_create(&args);
        if (IS_ERR(client)) {
@@ -439,42 +536,29 @@ static const struct rpc_call_ops nfsd4_cb_probe_ops = {
        .rpc_call_done = nfsd4_cb_probe_done,
 };
-static struct rpc_cred *lookup_cb_cred(struct nfs4_cb_conn *cb)
+static struct rpc_cred *callback_cred;
-{
-        struct auth_cred acred = {
-                .machine_cred = 1
-        };
-        /*
+int set_callback_cred(void)
-         * Note in the gss case this doesn't actually have to wait for a
+{
-         * gss upcall (or any calls to the client); this just creates a
+        callback_cred = rpc_lookup_machine_cred();
-         * non-uptodate cred which the rpc state machine will fill in with
+        if (!callback_cred)
-         * a refresh_upcall later.
+                return -ENOMEM;
-         */
+        return 0;
-        return rpcauth_lookup_credcache(cb->cb_client->cl_auth, &acred,
-                                                        RPCAUTH_LOOKUP_NEW);
 }
 void do_probe_callback(struct nfs4_client *clp)
 {
        struct nfs4_cb_conn *cb = &clp->cl_cb_conn;
        struct rpc_message msg = {
                .rpc_proc       = &nfs4_cb_procedures[NFSPROC4_CLNT_CB_NULL],
                .rpc_argp       = clp,
+                .rpc_cred       = callback_cred
        };
-        struct rpc_cred *cred;
        int status;
-        cred = lookup_cb_cred(cb);
-        if (IS_ERR(cred)) {
-                status = PTR_ERR(cred);
-                goto out;
-        }
-        cb->cb_cred = cred;
-        msg.rpc_cred = cb->cb_cred;
        status = rpc_call_async(cb->cb_client, &msg, RPC_TASK_SOFT,
                                &nfsd4_cb_probe_ops, (void *)clp);
-out:
        if (status) {
                warn_no_callback_path(clp, status);
                put_nfs4_client(clp);
@@ -503,11 +587,95 @@ nfsd4_probe_callback(struct nfs4_client *clp)
        do_probe_callback(clp);
 }
+/*
+ * There's currently a single callback channel slot.
+ * If the slot is available, then mark it busy.  Otherwise, set the
+ * thread for sleeping on the callback RPC wait queue.
+ */
+static int nfsd41_cb_setup_sequence(struct nfs4_client *clp,
+                struct rpc_task *task)
+{
+        struct nfs4_rpc_args *args = task->tk_msg.rpc_argp;
+        u32 *ptr = (u32 *)clp->cl_sessionid.data;
+        int status = 0;
+        dprintk("%s: %u:%u:%u:%u\n", __func__,
+                ptr[0], ptr[1], ptr[2], ptr[3]);
+        if (test_and_set_bit(0, &clp->cl_cb_slot_busy) != 0) {
+                rpc_sleep_on(&clp->cl_cb_waitq, task, NULL);
+                dprintk("%s slot is busy\n", __func__);
+                status = -EAGAIN;
+                goto out;
+        }
+        /*
+         * We'll need the clp during XDR encoding and decoding,
+         * and the sequence during decoding to verify the reply
+         */
+        args->args_seq.cbs_clp = clp;
+        task->tk_msg.rpc_resp = &args->args_seq;
+out:
+        dprintk("%s status=%d\n", __func__, status);
+        return status;
+}
+/*
+ * TODO: cb_sequence should support referring call lists, cachethis, multiple
+ * slots, and mark callback channel down on communication errors.
+ */
+static void nfsd4_cb_prepare(struct rpc_task *task, void *calldata)
+{
+        struct nfs4_delegation *dp = calldata;
+        struct nfs4_client *clp = dp->dl_client;
+        struct nfs4_rpc_args *args = task->tk_msg.rpc_argp;
+        u32 minorversion = clp->cl_cb_conn.cb_minorversion;
+        int status = 0;
+        args->args_seq.cbs_minorversion = minorversion;
+        if (minorversion) {
+                status = nfsd41_cb_setup_sequence(clp, task);
+                if (status) {
+                        if (status != -EAGAIN) {
+                                /* terminate rpc task */
+                                task->tk_status = status;
+                                task->tk_action = NULL;
+                        }
+                        return;
+                }
+        }
+        rpc_call_start(task);
+}
+static void nfsd4_cb_done(struct rpc_task *task, void *calldata)
+{
+        struct nfs4_delegation *dp = calldata;
+        struct nfs4_client *clp = dp->dl_client;
+        dprintk("%s: minorversion=%d\n", __func__,
+                clp->cl_cb_conn.cb_minorversion);
+        if (clp->cl_cb_conn.cb_minorversion) {
+                /* No need for lock, access serialized in nfsd4_cb_prepare */
+                ++clp->cl_cb_seq_nr;
+                clear_bit(0, &clp->cl_cb_slot_busy);
+                rpc_wake_up_next(&clp->cl_cb_waitq);
+                dprintk("%s: freed slot, new seqid=%d\n", __func__,
+                        clp->cl_cb_seq_nr);
+                /* We're done looking into the sequence information */
+                task->tk_msg.rpc_resp = NULL;
+        }
+}
 static void nfsd4_cb_recall_done(struct rpc_task *task, void *calldata)
 {
        struct nfs4_delegation *dp = calldata;
        struct nfs4_client *clp = dp->dl_client;
+        nfsd4_cb_done(task, calldata);
        switch (task->tk_status) {
        case -EIO:
                /* Network partition? */
@@ -520,16 +688,19 @@ static void nfsd4_cb_recall_done(struct rpc_task *task, void *calldata)
                break;
        default:
                /* success, or error we can't handle */
-                return;
+                goto done;
        }
        if (dp->dl_retries--) {
                rpc_delay(task, 2*HZ);
                task->tk_status = 0;
                rpc_restart_call(task);
+                return;
        } else {
                atomic_set(&clp->cl_cb_conn.cb_set, 0);
                warn_no_callback_path(clp, task->tk_status);
        }
+done:
+        kfree(task->tk_msg.rpc_argp);
 }
 static void nfsd4_cb_recall_release(void *calldata)
@@ -542,6 +713,7 @@ static void nfsd4_cb_recall_release(void *calldata)
 }
 static const struct rpc_call_ops nfsd4_cb_recall_ops = {
+        .rpc_call_prepare = nfsd4_cb_prepare,
        .rpc_call_done = nfsd4_cb_recall_done,
        .rpc_release = nfsd4_cb_recall_release,
 };
@@ -554,17 +726,24 @@ nfsd4_cb_recall(struct nfs4_delegation *dp)
 {
        struct nfs4_client *clp = dp->dl_client;
        struct rpc_clnt *clnt = clp->cl_cb_conn.cb_client;
+        struct nfs4_rpc_args *args;
        struct rpc_message msg = {
                .rpc_proc = &nfs4_cb_procedures[NFSPROC4_CLNT_CB_RECALL],
-                .rpc_argp = dp,
+                .rpc_cred = callback_cred
-                .rpc_cred = clp->cl_cb_conn.cb_cred
        };
-        int status;
+        int status = -ENOMEM;
+        args = kzalloc(sizeof(*args), GFP_KERNEL);
+        if (!args)
+                goto out;
+        args->args_op = dp;
+        msg.rpc_argp = args;
        dp->dl_retries = 1;
        status = rpc_call_async(clnt, &msg, RPC_TASK_SOFT,
                                &nfsd4_cb_recall_ops, dp);
+out:
        if (status) {
+                kfree(args);
                put_nfs4_client(clp);
                nfs4_put_delegation(dp);
        }
diff --git a/fs/nfsd/nfs4proc.c b/fs/nfsd/nfs4proc.c
index 7c8801769a3c..bebc0c2e1b0a 100644
--- a/fs/nfsd/nfs4proc.c
+++ b/fs/nfsd/nfs4proc.c
@@ -68,7 +68,6 @@ check_attr_support(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
                   u32 *bmval, u32 *writable)
 {
        struct dentry *dentry = cstate->current_fh.fh_dentry;
-        struct svc_export *exp = cstate->current_fh.fh_export;
        /*
         * Check about attributes are supported by the NFSv4 server or not.
@@ -80,17 +79,13 @@ check_attr_support(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
                return nfserr_attrnotsupp;
        /*
-         * Check FATTR4_WORD0_ACL & FATTR4_WORD0_FS_LOCATIONS can be supported
+         * Check FATTR4_WORD0_ACL can be supported
         * in current environment or not.
         */
        if (bmval[0] & FATTR4_WORD0_ACL) {
                if (!IS_POSIXACL(dentry->d_inode))
                        return nfserr_attrnotsupp;
        }
-        if (bmval[0] & FATTR4_WORD0_FS_LOCATIONS) {
-                if (exp->ex_fslocs.locations == NULL)
-                        return nfserr_attrnotsupp;
-        }
        /*
         * According to spec, read-only attributes return ERR_INVAL.
@@ -123,6 +118,35 @@ nfsd4_check_open_attributes(struct svc_rqst *rqstp,
        return status;
 }
+static int
+is_create_with_attrs(struct nfsd4_open *open)
+{
+        return open->op_create == NFS4_OPEN_CREATE
+                && (open->op_createmode == NFS4_CREATE_UNCHECKED
+                    || open->op_createmode == NFS4_CREATE_GUARDED
+                    || open->op_createmode == NFS4_CREATE_EXCLUSIVE4_1);
+}
+/*
+ * if error occurs when setting the acl, just clear the acl bit
+ * in the returned attr bitmap.
+ */
+static void
+do_set_nfs4_acl(struct svc_rqst *rqstp, struct svc_fh *fhp,
+                struct nfs4_acl *acl, u32 *bmval)
+{
+        __be32 status;
+        status = nfsd4_set_nfs4_acl(rqstp, fhp, acl);
+        if (status)
+                /*
+                 * We should probably fail the whole open at this point,
+                 * but we've already created the file, so it's too late;
+                 * So this seems the least of evils:
+                 */
+                bmval[0] &= ~FATTR4_WORD0_ACL;
+}
 static inline void
 fh_dup2(struct svc_fh *dst, struct svc_fh *src)
 {
@@ -206,6 +230,9 @@ do_open_lookup(struct svc_rqst *rqstp, struct svc_fh *current_fh, struct nfsd4_o
        if (status)
                goto out;
+        if (is_create_with_attrs(open) && open->op_acl != NULL)
+                do_set_nfs4_acl(rqstp, &resfh, open->op_acl, open->op_bmval);
        set_change_info(&open->op_cinfo, current_fh);
        fh_dup2(current_fh, &resfh);
@@ -536,12 +563,17 @@ nfsd4_create(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
                status = nfserr_badtype;
        }
-        if (!status) {
+        if (status)
-                fh_unlock(&cstate->current_fh);
+                goto out;
-                set_change_info(&create->cr_cinfo, &cstate->current_fh);
-                fh_dup2(&cstate->current_fh, &resfh);
+        if (create->cr_acl != NULL)
-        }
+                do_set_nfs4_acl(rqstp, &resfh, create->cr_acl,
+                                create->cr_bmval);
+        fh_unlock(&cstate->current_fh);
+        set_change_info(&create->cr_cinfo, &cstate->current_fh);
+        fh_dup2(&cstate->current_fh, &resfh);
+out:
        fh_put(&resfh);
        return status;
 }
@@ -947,34 +979,6 @@ static struct nfsd4_operation nfsd4_ops[];
 static const char *nfsd4_op_name(unsigned opnum);
 /*
- * This is a replay of a compound for which no cache entry pages
- * were used. Encode the sequence operation, and if cachethis is FALSE
- * encode the uncache rep error on the next operation.
- */
-static __be32
-nfsd4_enc_uncached_replay(struct nfsd4_compoundargs *args,
-                         struct nfsd4_compoundres *resp)
-{
-        struct nfsd4_op *op;
-        dprintk("--> %s resp->opcnt %d ce_cachethis %u \n", __func__,
-                resp->opcnt, resp->cstate.slot->sl_cache_entry.ce_cachethis);
-        /* Encode the replayed sequence operation */
-        BUG_ON(resp->opcnt != 1);
-        op = &args->ops[resp->opcnt - 1];
-        nfsd4_encode_operation(resp, op);
-        /*return nfserr_retry_uncached_rep in next operation. */
-        if (resp->cstate.slot->sl_cache_entry.ce_cachethis == 0) {
-                op = &args->ops[resp->opcnt++];
-                op->status = nfserr_retry_uncached_rep;
-                nfsd4_encode_operation(resp, op);
-        }
-        return op->status;
-}
-/*
 * Enforce NFSv4.1 COMPOUND ordering rules.
 *
 * TODO:
@@ -1083,13 +1087,10 @@ nfsd4_proc_compound(struct svc_rqst *rqstp,
                        BUG_ON(op->status == nfs_ok);
 encode_op:
-                /* Only from SEQUENCE or CREATE_SESSION */
+                /* Only from SEQUENCE */
                if (resp->cstate.status == nfserr_replay_cache) {
                        dprintk("%s NFS4.1 replay from cache\n", __func__);
-                        if (nfsd4_not_cached(resp))
+                        status = op->status;
-                                status = nfsd4_enc_uncached_replay(args, resp);
-                        else
-                                status = op->status;
                        goto out;
                }
                if (op->status == nfserr_replay_me) {
diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c
index 980a216a48c8..2153f9bdbebd 100644
--- a/fs/nfsd/nfs4state.c
+++ b/fs/nfsd/nfs4state.c
@@ -55,6 +55,7 @@
 #include <linux/lockd/bind.h>
 #include <linux/module.h>
 #include <linux/sunrpc/svcauth_gss.h>
+#include <linux/sunrpc/clnt.h>
 #define NFSDDBG_FACILITY                NFSDDBG_PROC
@@ -413,36 +414,65 @@ gen_sessionid(struct nfsd4_session *ses)
 }
 /*
- * Give the client the number of slots it requests bound by
+ * The protocol defines ca_maxresponssize_cached to include the size of
- * NFSD_MAX_SLOTS_PER_SESSION and by sv_drc_max_pages.
+ * the rpc header, but all we need to cache is the data starting after
+ * the end of the initial SEQUENCE operation--the rest we regenerate
+ * each time.  Therefore we can advertise a ca_maxresponssize_cached
+ * value that is the number of bytes in our cache plus a few additional
+ * bytes.  In order to stay on the safe side, and not promise more than
+ * we can cache, those additional bytes must be the minimum possible: 24
+ * bytes of rpc header (xid through accept state, with AUTH_NULL
+ * verifier), 12 for the compound header (with zero-length tag), and 44
+ * for the SEQUENCE op response:
+ */
+#define NFSD_MIN_HDR_SEQ_SZ  (24 + 12 + 44)
+/*
+ * Give the client the number of ca_maxresponsesize_cached slots it
+ * requests, of size bounded by NFSD_SLOT_CACHE_SIZE,
+ * NFSD_MAX_MEM_PER_SESSION, and nfsd_drc_max_mem. Do not allow more
+ * than NFSD_MAX_SLOTS_PER_SESSION.
 *
- * If we run out of pages (sv_drc_pages_used == sv_drc_max_pages) we
+ * If we run out of reserved DRC memory we should (up to a point)
- * should (up to a point) re-negotiate active sessions and reduce their
+ * re-negotiate active sessions and reduce their slot usage to make
- * slot usage to make rooom for new connections. For now we just fail the
+ * rooom for new connections. For now we just fail the create session.
- * create session.
 */
-static int set_forechannel_maxreqs(struct nfsd4_channel_attrs *fchan)
+static int set_forechannel_drc_size(struct nfsd4_channel_attrs *fchan)
 {
-        int status = 0, np = fchan->maxreqs * NFSD_PAGES_PER_SLOT;
+        int mem, size = fchan->maxresp_cached;
        if (fchan->maxreqs < 1)
                return nfserr_inval;
-        else if (fchan->maxreqs > NFSD_MAX_SLOTS_PER_SESSION)
-                fchan->maxreqs = NFSD_MAX_SLOTS_PER_SESSION;
-        spin_lock(&nfsd_serv->sv_lock);
+        if (size < NFSD_MIN_HDR_SEQ_SZ)
-        if (np + nfsd_serv->sv_drc_pages_used > nfsd_serv->sv_drc_max_pages)
+                size = NFSD_MIN_HDR_SEQ_SZ;
-                np = nfsd_serv->sv_drc_max_pages - nfsd_serv->sv_drc_pages_used;
+        size -= NFSD_MIN_HDR_SEQ_SZ;
-        nfsd_serv->sv_drc_pages_used += np;
+        if (size > NFSD_SLOT_CACHE_SIZE)
-        spin_unlock(&nfsd_serv->sv_lock);
+                size = NFSD_SLOT_CACHE_SIZE;
+        /* bound the maxreqs by NFSD_MAX_MEM_PER_SESSION */
+        mem = fchan->maxreqs * size;
+        if (mem > NFSD_MAX_MEM_PER_SESSION) {
+                fchan->maxreqs = NFSD_MAX_MEM_PER_SESSION / size;
+                if (fchan->maxreqs > NFSD_MAX_SLOTS_PER_SESSION)
+                        fchan->maxreqs = NFSD_MAX_SLOTS_PER_SESSION;
+                mem = fchan->maxreqs * size;
+        }
-        if (np <= 0) {
+        spin_lock(&nfsd_drc_lock);
-                status = nfserr_resource;
+        /* bound the total session drc memory ussage */
-                fchan->maxreqs = 0;
+        if (mem + nfsd_drc_mem_used > nfsd_drc_max_mem) {
-        } else
+                fchan->maxreqs = (nfsd_drc_max_mem - nfsd_drc_mem_used) / size;
-                fchan->maxreqs = np / NFSD_PAGES_PER_SLOT;
+                mem = fchan->maxreqs * size;
+        }
+        nfsd_drc_mem_used += mem;
+        spin_unlock(&nfsd_drc_lock);
-        return status;
+        if (fchan->maxreqs == 0)
+                return nfserr_serverfault;
+        fchan->maxresp_cached = size + NFSD_MIN_HDR_SEQ_SZ;
+        return 0;
 }
 /*
@@ -466,36 +496,41 @@ static int init_forechannel_attrs(struct svc_rqst *rqstp,
                fchan->maxresp_sz = maxcount;
        session_fchan->maxresp_sz = fchan->maxresp_sz;
-        /* Set the max response cached size our default which is
-         * a multiple of PAGE_SIZE and small */
-        session_fchan->maxresp_cached = NFSD_PAGES_PER_SLOT * PAGE_SIZE;
-        fchan->maxresp_cached = session_fchan->maxresp_cached;
        /* Use the client's maxops if possible */
        if (fchan->maxops > NFSD_MAX_OPS_PER_COMPOUND)
                fchan->maxops = NFSD_MAX_OPS_PER_COMPOUND;
        session_fchan->maxops = fchan->maxops;
-        /* try to use the client requested number of slots */
-        if (fchan->maxreqs > NFSD_MAX_SLOTS_PER_SESSION)
-                fchan->maxreqs = NFSD_MAX_SLOTS_PER_SESSION;
        /* FIXME: Error means no more DRC pages so the server should
         * recover pages from existing sessions. For now fail session
         * creation.
         */
-        status = set_forechannel_maxreqs(fchan);
+        status = set_forechannel_drc_size(fchan);
+        session_fchan->maxresp_cached = fchan->maxresp_cached;
        session_fchan->maxreqs = fchan->maxreqs;
+        dprintk("%s status %d\n", __func__, status);
        return status;
 }
+static void
+free_session_slots(struct nfsd4_session *ses)
+{
+        int i;
+        for (i = 0; i < ses->se_fchannel.maxreqs; i++)
+                kfree(ses->se_slots[i]);
+}
 static int
 alloc_init_session(struct svc_rqst *rqstp, struct nfs4_client *clp,
                   struct nfsd4_create_session *cses)
 {
        struct nfsd4_session *new, tmp;
-        int idx, status = nfserr_resource, slotsize;
+        struct nfsd4_slot *sp;
+        int idx, slotsize, cachesize, i;
+        int status;
        memset(&tmp, 0, sizeof(tmp));
@@ -506,14 +541,27 @@ alloc_init_session(struct svc_rqst *rqstp, struct nfs4_client *clp,
        if (status)
                goto out;
-        /* allocate struct nfsd4_session and slot table in one piece */
+        BUILD_BUG_ON(NFSD_MAX_SLOTS_PER_SESSION * sizeof(struct nfsd4_slot)
-        slotsize = tmp.se_fchannel.maxreqs * sizeof(struct nfsd4_slot);
+                     + sizeof(struct nfsd4_session) > PAGE_SIZE);
+        status = nfserr_serverfault;
+        /* allocate struct nfsd4_session and slot table pointers in one piece */
+        slotsize = tmp.se_fchannel.maxreqs * sizeof(struct nfsd4_slot *);
        new = kzalloc(sizeof(*new) + slotsize, GFP_KERNEL);
        if (!new)
                goto out;
        memcpy(new, &tmp, sizeof(*new));
+        /* allocate each struct nfsd4_slot and data cache in one piece */
+        cachesize = new->se_fchannel.maxresp_cached - NFSD_MIN_HDR_SEQ_SZ;
+        for (i = 0; i < new->se_fchannel.maxreqs; i++) {
+                sp = kzalloc(sizeof(*sp) + cachesize, GFP_KERNEL);
+                if (!sp)
+                        goto out_free;
+                new->se_slots[i] = sp;
+        }
        new->se_client = clp;
        gen_sessionid(new);
        idx = hash_sessionid(&new->se_sessionid);
@@ -530,6 +578,10 @@ alloc_init_session(struct svc_rqst *rqstp, struct nfs4_client *clp,
        status = nfs_ok;
 out:
        return status;
+out_free:
+        free_session_slots(new);
+        kfree(new);
+        goto out;
 }
 /* caller must hold sessionid_lock */
@@ -572,19 +624,16 @@ release_session(struct nfsd4_session *ses)
        nfsd4_put_session(ses);
 }
-static void nfsd4_release_respages(struct page **respages, short resused);
 void
 free_session(struct kref *kref)
 {
        struct nfsd4_session *ses;
-        int i;
        ses = container_of(kref, struct nfsd4_session, se_ref);
-        for (i = 0; i < ses->se_fchannel.maxreqs; i++) {
+        spin_lock(&nfsd_drc_lock);
-                struct nfsd4_cache_entry *e = &ses->se_slots[i].sl_cache_entry;
+        nfsd_drc_mem_used -= ses->se_fchannel.maxreqs * NFSD_SLOT_CACHE_SIZE;
-                nfsd4_release_respages(e->ce_respages, e->ce_resused);
+        spin_unlock(&nfsd_drc_lock);
-        }
+        free_session_slots(ses);
        kfree(ses);
 }
@@ -647,18 +696,14 @@ shutdown_callback_client(struct nfs4_client *clp)
                clp->cl_cb_conn.cb_client = NULL;
                rpc_shutdown_client(clnt);
        }
-        if (clp->cl_cb_conn.cb_cred) {
-                put_rpccred(clp->cl_cb_conn.cb_cred);
-                clp->cl_cb_conn.cb_cred = NULL;
-        }
 }
 static inline void
 free_client(struct nfs4_client *clp)
 {
        shutdown_callback_client(clp);
-        nfsd4_release_respages(clp->cl_slot.sl_cache_entry.ce_respages,
+        if (clp->cl_cb_xprt)
-                             clp->cl_slot.sl_cache_entry.ce_resused);
+                svc_xprt_put(clp->cl_cb_xprt);
        if (clp->cl_cred.cr_group_info)
                put_group_info(clp->cl_cred.cr_group_info);
        kfree(clp->cl_principal);
@@ -714,25 +759,6 @@ expire_client(struct nfs4_client *clp)
        put_nfs4_client(clp);
 }
-static struct nfs4_client *create_client(struct xdr_netobj name, char *recdir)
-{
-        struct nfs4_client *clp;
-        clp = alloc_client(name);
-        if (clp == NULL)
-                return NULL;
-        memcpy(clp->cl_recdir, recdir, HEXDIR_LEN);
-        atomic_set(&clp->cl_count, 1);
-        atomic_set(&clp->cl_cb_conn.cb_set, 0);
-        INIT_LIST_HEAD(&clp->cl_idhash);
-        INIT_LIST_HEAD(&clp->cl_strhash);
-        INIT_LIST_HEAD(&clp->cl_openowners);
-        INIT_LIST_HEAD(&clp->cl_delegations);
-        INIT_LIST_HEAD(&clp->cl_sessions);
-        INIT_LIST_HEAD(&clp->cl_lru);
-        return clp;
-}
 static void copy_verf(struct nfs4_client *target, nfs4_verifier *source)
 {
        memcpy(target->cl_verifier.data, source->data,
@@ -795,6 +821,46 @@ static void gen_confirm(struct nfs4_client *clp)
        *p++ = i++;
 }
+static struct nfs4_client *create_client(struct xdr_netobj name, char *recdir,
+                struct svc_rqst *rqstp, nfs4_verifier *verf)
+{
+        struct nfs4_client *clp;
+        struct sockaddr *sa = svc_addr(rqstp);
+        char *princ;
+        clp = alloc_client(name);
+        if (clp == NULL)
+                return NULL;
+        princ = svc_gss_principal(rqstp);
+        if (princ) {
+                clp->cl_principal = kstrdup(princ, GFP_KERNEL);
+                if (clp->cl_principal == NULL) {
+                        free_client(clp);
+                        return NULL;
+                }
+        }
+        memcpy(clp->cl_recdir, recdir, HEXDIR_LEN);
+        atomic_set(&clp->cl_count, 1);
+        atomic_set(&clp->cl_cb_conn.cb_set, 0);
+        INIT_LIST_HEAD(&clp->cl_idhash);
+        INIT_LIST_HEAD(&clp->cl_strhash);
+        INIT_LIST_HEAD(&clp->cl_openowners);
+        INIT_LIST_HEAD(&clp->cl_delegations);
+        INIT_LIST_HEAD(&clp->cl_sessions);
+        INIT_LIST_HEAD(&clp->cl_lru);
+        clear_bit(0, &clp->cl_cb_slot_busy);
+        rpc_init_wait_queue(&clp->cl_cb_waitq, "Backchannel slot table");
+        copy_verf(clp, verf);
+        rpc_copy_addr((struct sockaddr *) &clp->cl_addr, sa);
+        clp->cl_flavor = rqstp->rq_flavor;
+        copy_cred(&clp->cl_cred, &rqstp->rq_cred);
+        gen_confirm(clp);
+        return clp;
+}
 static int check_name(struct xdr_netobj name)
 {
        if (name.len == 0) 
@@ -902,93 +968,40 @@ find_unconfirmed_client_by_str(const char *dname, unsigned int hashval,
        return NULL;
 }
-/* a helper function for parse_callback */
-static int
-parse_octet(unsigned int *lenp, char **addrp)
-{
-        unsigned int len = *lenp;
-        char *p = *addrp;
-        int n = -1;
-        char c;
-        for (;;) {
-                if (!len)
-                        break;
-                len--;
-                c = *p++;
-                if (c == '.')
-                        break;
-                if ((c < '0') || (c > '9')) {
-                        n = -1;
-                        break;
-                }
-                if (n < 0)
-                        n = 0;
-                n = (n * 10) + (c - '0');
-                if (n > 255) {
-                        n = -1;
-                        break;
-                }
-        }
-        *lenp = len;
-        *addrp = p;
-        return n;
-}
-/* parse and set the setclientid ipv4 callback address */
-static int
-parse_ipv4(unsigned int addr_len, char *addr_val, unsigned int *cbaddrp, unsigned short *cbportp)
-{
-        int temp = 0;
-        u32 cbaddr = 0;
-        u16 cbport = 0;
-        u32 addrlen = addr_len;
-        char *addr = addr_val;
-        int i, shift;
-        /* ipaddress */
-        shift = 24;
-        for(i = 4; i > 0  ; i--) {
-                if ((temp = parse_octet(&addrlen, &addr)) < 0) {
-                        return 0;
-                }
-                cbaddr |= (temp << shift);
-                if (shift > 0)
-                shift -= 8;
-        }
-        *cbaddrp = cbaddr;
-        /* port */
-        shift = 8;
-        for(i = 2; i > 0  ; i--) {
-                if ((temp = parse_octet(&addrlen, &addr)) < 0) {
-                        return 0;
-                }
-                cbport |= (temp << shift);
-                if (shift > 0)
-                        shift -= 8;
-        }
-        *cbportp = cbport;
-        return 1;
-}
 static void
-gen_callback(struct nfs4_client *clp, struct nfsd4_setclientid *se)
+gen_callback(struct nfs4_client *clp, struct nfsd4_setclientid *se, u32 scopeid)
 {
        struct nfs4_cb_conn *cb = &clp->cl_cb_conn;
+        unsigned short expected_family;
-        /* Currently, we only support tcp for the callback channel */
-        if ((se->se_callback_netid_len != 3) || memcmp((char *)se->se_callback_netid_val, "tcp", 3))
+        /* Currently, we only support tcp and tcp6 for the callback channel */
+        if (se->se_callback_netid_len == 3 &&
+            !memcmp(se->se_callback_netid_val, "tcp", 3))
+                expected_family = AF_INET;
+        else if (se->se_callback_netid_len == 4 &&
+                 !memcmp(se->se_callback_netid_val, "tcp6", 4))
+                expected_family = AF_INET6;
+        else
                goto out_err;
-        if ( !(parse_ipv4(se->se_callback_addr_len, se->se_callback_addr_val,
+        cb->cb_addrlen = rpc_uaddr2sockaddr(se->se_callback_addr_val,
-                         &cb->cb_addr, &cb->cb_port)))
+                                            se->se_callback_addr_len,
+                                            (struct sockaddr *) &cb->cb_addr,
+                                            sizeof(cb->cb_addr));
+        if (!cb->cb_addrlen || cb->cb_addr.ss_family != expected_family)
                goto out_err;
+        if (cb->cb_addr.ss_family == AF_INET6)
+                ((struct sockaddr_in6 *) &cb->cb_addr)->sin6_scope_id = scopeid;
        cb->cb_minorversion = 0;
        cb->cb_prog = se->se_callback_prog;
        cb->cb_ident = se->se_callback_ident;
        return;
 out_err:
+        cb->cb_addr.ss_family = AF_UNSPEC;
+        cb->cb_addrlen = 0;
        dprintk(KERN_INFO "NFSD: this client (clientid %08x/%08x) "
                "will not receive delegations\n",
                clp->cl_clientid.cl_boot, clp->cl_clientid.cl_id);
@@ -996,175 +1009,87 @@ out_err:
        return;
 }
-void
-nfsd4_set_statp(struct svc_rqst *rqstp, __be32 *statp)
-{
-        struct nfsd4_compoundres *resp = rqstp->rq_resp;
-        resp->cstate.statp = statp;
-}
 /*
- * Dereference the result pages.
+ * Cache a reply. nfsd4_check_drc_limit() has bounded the cache size.
 */
-static void
+void
-nfsd4_release_respages(struct page **respages, short resused)
+nfsd4_store_cache_entry(struct nfsd4_compoundres *resp)
 {
-        int i;
+        struct nfsd4_slot *slot = resp->cstate.slot;
+        unsigned int base;
-        dprintk("--> %s\n", __func__);
+        dprintk("--> %s slot %p\n", __func__, slot);
-        for (i = 0; i < resused; i++) {
-                if (!respages[i])
-                        continue;
-                put_page(respages[i]);
-                respages[i] = NULL;
-        }
-}
-static void
+        slot->sl_opcnt = resp->opcnt;
-nfsd4_copy_pages(struct page **topages, struct page **frompages, short count)
+        slot->sl_status = resp->cstate.status;
-{
-        int i;
-        for (i = 0; i < count; i++) {
+        if (nfsd4_not_cached(resp)) {
-                topages[i] = frompages[i];
+                slot->sl_datalen = 0;
-                if (!topages[i])
+                return;
-                        continue;
-                get_page(topages[i]);
        }
+        slot->sl_datalen = (char *)resp->p - (char *)resp->cstate.datap;
+        base = (char *)resp->cstate.datap -
+                                        (char *)resp->xbuf->head[0].iov_base;
+        if (read_bytes_from_xdr_buf(resp->xbuf, base, slot->sl_data,
+                                    slot->sl_datalen))
+                WARN("%s: sessions DRC could not cache compound\n", __func__);
+        return;
 }
 /*
- * Cache the reply pages up to NFSD_PAGES_PER_SLOT + 1, clearing the previous
+ * Encode the replay sequence operation from the slot values.
- * pages. We add a page to NFSD_PAGES_PER_SLOT for the case where the total
+ * If cachethis is FALSE encode the uncached rep error on the next
- * length of the XDR response is less than se_fmaxresp_cached
+ * operation which sets resp->p and increments resp->opcnt for
- * (NFSD_PAGES_PER_SLOT * PAGE_SIZE) but the xdr_buf pages is used for a
+ * nfs4svc_encode_compoundres.
- * of the reply (e.g. readdir).
 *
- * Store the base and length of the rq_req.head[0] page
- * of the NFSv4.1 data, just past the rpc header.
 */
-void
+static __be32
-nfsd4_store_cache_entry(struct nfsd4_compoundres *resp)
+nfsd4_enc_sequence_replay(struct nfsd4_compoundargs *args,
+                          struct nfsd4_compoundres *resp)
 {
-        struct nfsd4_cache_entry *entry = &resp->cstate.slot->sl_cache_entry;
+        struct nfsd4_op *op;
-        struct svc_rqst *rqstp = resp->rqstp;
+        struct nfsd4_slot *slot = resp->cstate.slot;
-        struct nfsd4_compoundargs *args = rqstp->rq_argp;
-        struct nfsd4_op *op = &args->ops[resp->opcnt];
-        struct kvec *resv = &rqstp->rq_res.head[0];
-        dprintk("--> %s entry %p\n", __func__, entry);
-        /* Don't cache a failed OP_SEQUENCE. */
-        if (resp->opcnt == 1 && op->opnum == OP_SEQUENCE && resp->cstate.status)
-                return;
-        nfsd4_release_respages(entry->ce_respages, entry->ce_resused);
+        dprintk("--> %s resp->opcnt %d cachethis %u \n", __func__,
-        entry->ce_opcnt = resp->opcnt;
+                resp->opcnt, resp->cstate.slot->sl_cachethis);
-        entry->ce_status = resp->cstate.status;
-        /*
+        /* Encode the replayed sequence operation */
-         * Don't need a page to cache just the sequence operation - the slot
+        op = &args->ops[resp->opcnt - 1];
-         * does this for us!
+        nfsd4_encode_operation(resp, op);
-         */
-        if (nfsd4_not_cached(resp)) {
+        /* Return nfserr_retry_uncached_rep in next operation. */
-                entry->ce_resused = 0;
+        if (args->opcnt > 1 && slot->sl_cachethis == 0) {
-                entry->ce_rpchdrlen = 0;
+                op = &args->ops[resp->opcnt++];
-                dprintk("%s Just cache SEQUENCE. ce_cachethis %d\n", __func__,
+                op->status = nfserr_retry_uncached_rep;
-                        resp->cstate.slot->sl_cache_entry.ce_cachethis);
+                nfsd4_encode_operation(resp, op);
-                return;
-        }
-        entry->ce_resused = rqstp->rq_resused;
-        if (entry->ce_resused > NFSD_PAGES_PER_SLOT + 1)
-                entry->ce_resused = NFSD_PAGES_PER_SLOT + 1;
-        nfsd4_copy_pages(entry->ce_respages, rqstp->rq_respages,
-                         entry->ce_resused);
-        entry->ce_datav.iov_base = resp->cstate.statp;
-        entry->ce_datav.iov_len = resv->iov_len - ((char *)resp->cstate.statp -
-                                (char *)page_address(rqstp->rq_respages[0]));
-        /* Current request rpc header length*/
-        entry->ce_rpchdrlen = (char *)resp->cstate.statp -
-                                (char *)page_address(rqstp->rq_respages[0]);
-}
-/*
- * We keep the rpc header, but take the nfs reply from the replycache.
- */
-static int
-nfsd41_copy_replay_data(struct nfsd4_compoundres *resp,
-                        struct nfsd4_cache_entry *entry)
-{
-        struct svc_rqst *rqstp = resp->rqstp;
-        struct kvec *resv = &resp->rqstp->rq_res.head[0];
-        int len;
-        /* Current request rpc header length*/
-        len = (char *)resp->cstate.statp -
-                        (char *)page_address(rqstp->rq_respages[0]);
-        if (entry->ce_datav.iov_len + len > PAGE_SIZE) {
-                dprintk("%s v41 cached reply too large (%Zd).\n", __func__,
-                        entry->ce_datav.iov_len);
-                return 0;
        }
-        /* copy the cached reply nfsd data past the current rpc header */
+        return op->status;
-        memcpy((char *)resv->iov_base + len, entry->ce_datav.iov_base,
-                entry->ce_datav.iov_len);
-        resv->iov_len = len + entry->ce_datav.iov_len;
-        return 1;
 }
 /*
- * Keep the first page of the replay. Copy the NFSv4.1 data from the first
+ * The sequence operation is not cached because we can use the slot and
- * cached page.  Replace any futher replay pages from the cache.
+ * session values.
 */
 __be32
 nfsd4_replay_cache_entry(struct nfsd4_compoundres *resp,
                         struct nfsd4_sequence *seq)
 {
-        struct nfsd4_cache_entry *entry = &resp->cstate.slot->sl_cache_entry;
+        struct nfsd4_slot *slot = resp->cstate.slot;
        __be32 status;
-        dprintk("--> %s entry %p\n", __func__, entry);
+        dprintk("--> %s slot %p\n", __func__, slot);
-        /*
-         * If this is just the sequence operation, we did not keep
-         * a page in the cache entry because we can just use the
-         * slot info stored in struct nfsd4_sequence that was checked
-         * against the slot in nfsd4_sequence().
-         *
-         * This occurs when seq->cachethis is FALSE, or when the client
-         * session inactivity timer fires and a solo sequence operation
-         * is sent (lease renewal).
-         */
-        if (seq && nfsd4_not_cached(resp)) {
-                seq->maxslots = resp->cstate.session->se_fchannel.maxreqs;
-                return nfs_ok;
-        }
-        if (!nfsd41_copy_replay_data(resp, entry)) {
-                /*
-                 * Not enough room to use the replay rpc header, send the
-                 * cached header. Release all the allocated result pages.
-                 */
-                svc_free_res_pages(resp->rqstp);
-                nfsd4_copy_pages(resp->rqstp->rq_respages, entry->ce_respages,
-                        entry->ce_resused);
-        } else {
-                /* Release all but the first allocated result page */
-                resp->rqstp->rq_resused--;
+        /* Either returns 0 or nfserr_retry_uncached */
-                svc_free_res_pages(resp->rqstp);
+        status = nfsd4_enc_sequence_replay(resp->rqstp->rq_argp, resp);
+        if (status == nfserr_retry_uncached_rep)
+                return status;
-                nfsd4_copy_pages(&resp->rqstp->rq_respages[1],
+        /* The sequence operation has been encoded, cstate->datap set. */
-                                 &entry->ce_respages[1],
+        memcpy(resp->cstate.datap, slot->sl_data, slot->sl_datalen);
-                                 entry->ce_resused - 1);
-        }
-        resp->rqstp->rq_resused = entry->ce_resused;
+        resp->opcnt = slot->sl_opcnt;
-        resp->opcnt = entry->ce_opcnt;
+        resp->p = resp->cstate.datap + XDR_QUADLEN(slot->sl_datalen);
-        resp->cstate.iovlen = entry->ce_datav.iov_len + entry->ce_rpchdrlen;
+        status = slot->sl_status;
-        status = entry->ce_status;
        return status;
 }
@@ -1194,13 +1119,15 @@ nfsd4_exchange_id(struct svc_rqst *rqstp,
        int status;
        unsigned int            strhashval;
        char                    dname[HEXDIR_LEN];
+        char                    addr_str[INET6_ADDRSTRLEN];
        nfs4_verifier           verf = exid->verifier;
-        u32                     ip_addr = svc_addr_in(rqstp)->sin_addr.s_addr;
+        struct sockaddr         *sa = svc_addr(rqstp);
+        rpc_ntop(sa, addr_str, sizeof(addr_str));
        dprintk("%s rqstp=%p exid=%p clname.len=%u clname.data=%p "
-                " ip_addr=%u flags %x, spa_how %d\n",
+                "ip_addr=%s flags %x, spa_how %d\n",
                __func__, rqstp, exid, exid->clname.len, exid->clname.data,
-                ip_addr, exid->flags, exid->spa_how);
+                addr_str, exid->flags, exid->spa_how);
        if (!check_name(exid->clname) || (exid->flags & ~EXCHGID4_FLAG_MASK_A))
                return nfserr_inval;
@@ -1281,28 +1208,23 @@ nfsd4_exchange_id(struct svc_rqst *rqstp,
 out_new:
        /* Normal case */
-        new = create_client(exid->clname, dname);
+        new = create_client(exid->clname, dname, rqstp, &verf);
        if (new == NULL) {
-                status = nfserr_resource;
+                status = nfserr_serverfault;
                goto out;
        }
-        copy_verf(new, &verf);
-        copy_cred(&new->cl_cred, &rqstp->rq_cred);
-        new->cl_addr = ip_addr;
        gen_clid(new);
-        gen_confirm(new);
        add_to_unconfirmed(new, strhashval);
 out_copy:
        exid->clientid.cl_boot = new->cl_clientid.cl_boot;
        exid->clientid.cl_id = new->cl_clientid.cl_id;
-        new->cl_slot.sl_seqid = 0;
        exid->seqid = 1;
        nfsd4_set_ex_flags(new, exid);
        dprintk("nfsd4_exchange_id seqid %d flags %x\n",
-                new->cl_slot.sl_seqid, new->cl_exchange_flags);
+                new->cl_cs_slot.sl_seqid, new->cl_exchange_flags);
        status = nfs_ok;
 out:
@@ -1313,40 +1235,60 @@ error:
 }
 static int
-check_slot_seqid(u32 seqid, struct nfsd4_slot *slot)
+check_slot_seqid(u32 seqid, u32 slot_seqid, int slot_inuse)
 {
-        dprintk("%s enter. seqid %d slot->sl_seqid %d\n", __func__, seqid,
+        dprintk("%s enter. seqid %d slot_seqid %d\n", __func__, seqid,
-                slot->sl_seqid);
+                slot_seqid);
        /* The slot is in use, and no response has been sent. */
-        if (slot->sl_inuse) {
+        if (slot_inuse) {
-                if (seqid == slot->sl_seqid)
+                if (seqid == slot_seqid)
                        return nfserr_jukebox;
                else
                        return nfserr_seq_misordered;
        }
        /* Normal */
-        if (likely(seqid == slot->sl_seqid + 1))
+        if (likely(seqid == slot_seqid + 1))
                return nfs_ok;
        /* Replay */
-        if (seqid == slot->sl_seqid)
+        if (seqid == slot_seqid)
                return nfserr_replay_cache;
        /* Wraparound */
-        if (seqid == 1 && (slot->sl_seqid + 1) == 0)
+        if (seqid == 1 && (slot_seqid + 1) == 0)
                return nfs_ok;
        /* Misordered replay or misordered new request */
        return nfserr_seq_misordered;
 }
+/*
+ * Cache the create session result into the create session single DRC
+ * slot cache by saving the xdr structure. sl_seqid has been set.
+ * Do this for solo or embedded create session operations.
+ */
+static void
+nfsd4_cache_create_session(struct nfsd4_create_session *cr_ses,
+                           struct nfsd4_clid_slot *slot, int nfserr)
+{
+        slot->sl_status = nfserr;
+        memcpy(&slot->sl_cr_ses, cr_ses, sizeof(*cr_ses));
+}
+static __be32
+nfsd4_replay_create_session(struct nfsd4_create_session *cr_ses,
+                            struct nfsd4_clid_slot *slot)
+{
+        memcpy(cr_ses, &slot->sl_cr_ses, sizeof(*cr_ses));
+        return slot->sl_status;
+}
 __be32
 nfsd4_create_session(struct svc_rqst *rqstp,
                     struct nfsd4_compound_state *cstate,
                     struct nfsd4_create_session *cr_ses)
 {
-        u32 ip_addr = svc_addr_in(rqstp)->sin_addr.s_addr;
+        struct sockaddr *sa = svc_addr(rqstp);
-        struct nfsd4_compoundres *resp = rqstp->rq_resp;
        struct nfs4_client *conf, *unconf;
-        struct nfsd4_slot *slot = NULL;
+        struct nfsd4_clid_slot *cs_slot = NULL;
        int status = 0;
        nfs4_lock_state();
@@ -1354,40 +1296,38 @@ nfsd4_create_session(struct svc_rqst *rqstp,
        conf = find_confirmed_client(&cr_ses->clientid);
        if (conf) {
-                slot = &conf->cl_slot;
+                cs_slot = &conf->cl_cs_slot;
-                status = check_slot_seqid(cr_ses->seqid, slot);
+                status = check_slot_seqid(cr_ses->seqid, cs_slot->sl_seqid, 0);
                if (status == nfserr_replay_cache) {
                        dprintk("Got a create_session replay! seqid= %d\n",
-                                slot->sl_seqid);
+                                cs_slot->sl_seqid);
-                        cstate->slot = slot;
-                        cstate->status = status;
                        /* Return the cached reply status */
-                        status = nfsd4_replay_cache_entry(resp, NULL);
+                        status = nfsd4_replay_create_session(cr_ses, cs_slot);
                        goto out;
-                } else if (cr_ses->seqid != conf->cl_slot.sl_seqid + 1) {
+                } else if (cr_ses->seqid != cs_slot->sl_seqid + 1) {
                        status = nfserr_seq_misordered;
                        dprintk("Sequence misordered!\n");
                        dprintk("Expected seqid= %d but got seqid= %d\n",
-                                slot->sl_seqid, cr_ses->seqid);
+                                cs_slot->sl_seqid, cr_ses->seqid);
                        goto out;
                }
-                conf->cl_slot.sl_seqid++;
+                cs_slot->sl_seqid++;
        } else if (unconf) {
                if (!same_creds(&unconf->cl_cred, &rqstp->rq_cred) ||
-                    (ip_addr != unconf->cl_addr)) {
+                    !rpc_cmp_addr(sa, (struct sockaddr *) &unconf->cl_addr)) {
                        status = nfserr_clid_inuse;
                        goto out;
                }
-                slot = &unconf->cl_slot;
+                cs_slot = &unconf->cl_cs_slot;
-                status = check_slot_seqid(cr_ses->seqid, slot);
+                status = check_slot_seqid(cr_ses->seqid, cs_slot->sl_seqid, 0);
                if (status) {
                        /* an unconfirmed replay returns misordered */
                        status = nfserr_seq_misordered;
-                        goto out;
+                        goto out_cache;
                }
-                slot->sl_seqid++; /* from 0 to 1 */
+                cs_slot->sl_seqid++; /* from 0 to 1 */
                move_to_confirmed(unconf);
                /*
@@ -1396,6 +1336,19 @@ nfsd4_create_session(struct svc_rqst *rqstp,
                cr_ses->flags &= ~SESSION4_PERSIST;
                cr_ses->flags &= ~SESSION4_RDMA;
+                if (cr_ses->flags & SESSION4_BACK_CHAN) {
+                        unconf->cl_cb_xprt = rqstp->rq_xprt;
+                        svc_xprt_get(unconf->cl_cb_xprt);
+                        rpc_copy_addr(
+                                (struct sockaddr *)&unconf->cl_cb_conn.cb_addr,
+                                sa);
+                        unconf->cl_cb_conn.cb_addrlen = svc_addr_len(sa);
+                        unconf->cl_cb_conn.cb_minorversion =
+                                cstate->minorversion;
+                        unconf->cl_cb_conn.cb_prog = cr_ses->callback_prog;
+                        unconf->cl_cb_seq_nr = 1;
+                        nfsd4_probe_callback(unconf);
+                }
                conf = unconf;
        } else {
                status = nfserr_stale_clientid;
@@ -1408,12 +1361,11 @@ nfsd4_create_session(struct svc_rqst *rqstp,
        memcpy(cr_ses->sessionid.data, conf->cl_sessionid.data,
               NFS4_MAX_SESSIONID_LEN);
-        cr_ses->seqid = slot->sl_seqid;
+        cr_ses->seqid = cs_slot->sl_seqid;
-        slot->sl_inuse = true;
+out_cache:
-        cstate->slot = slot;
+        /* cache solo and embedded create sessions under the state lock */
-        /* Ensure a page is used for the cache */
+        nfsd4_cache_create_session(cr_ses, cs_slot, status);
-        slot->sl_cache_entry.ce_cachethis = 1;
 out:
        nfs4_unlock_state();
        dprintk("%s returns %d\n", __func__, ntohl(status));
@@ -1478,18 +1430,23 @@ nfsd4_sequence(struct svc_rqst *rqstp,
        if (seq->slotid >= session->se_fchannel.maxreqs)
                goto out;
-        slot = &session->se_slots[seq->slotid];
+        slot = session->se_slots[seq->slotid];
        dprintk("%s: slotid %d\n", __func__, seq->slotid);
-        status = check_slot_seqid(seq->seqid, slot);
+        /* We do not negotiate the number of slots yet, so set the
+         * maxslots to the session maxreqs which is used to encode
+         * sr_highest_slotid and the sr_target_slot id to maxslots */
+        seq->maxslots = session->se_fchannel.maxreqs;
+        status = check_slot_seqid(seq->seqid, slot->sl_seqid, slot->sl_inuse);
        if (status == nfserr_replay_cache) {
                cstate->slot = slot;
                cstate->session = session;
                /* Return the cached reply status and set cstate->status
-                 * for nfsd4_svc_encode_compoundres processing */
+                 * for nfsd4_proc_compound processing */
                status = nfsd4_replay_cache_entry(resp, seq);
                cstate->status = nfserr_replay_cache;
-                goto replay_cache;
+                goto out;
        }
        if (status)
                goto out;
@@ -1497,23 +1454,23 @@ nfsd4_sequence(struct svc_rqst *rqstp,
        /* Success! bump slot seqid */
        slot->sl_inuse = true;
        slot->sl_seqid = seq->seqid;
-        slot->sl_cache_entry.ce_cachethis = seq->cachethis;
+        slot->sl_cachethis = seq->cachethis;
-        /* Always set the cache entry cachethis for solo sequence */
-        if (nfsd4_is_solo_sequence(resp))
-                slot->sl_cache_entry.ce_cachethis = 1;
        cstate->slot = slot;
        cstate->session = session;
-replay_cache:
+        /* Hold a session reference until done processing the compound:
-        /* Renew the clientid on success and on replay.
-         * Hold a session reference until done processing the compound:
         * nfsd4_put_session called only if the cstate slot is set.
         */
-        renew_client(session->se_client);
        nfsd4_get_session(session);
 out:
        spin_unlock(&sessionid_lock);
+        /* Renew the clientid on success and on replay */
+        if (cstate->session) {
+                nfs4_lock_state();
+                renew_client(session->se_client);
+                nfs4_unlock_state();
+        }
        dprintk("%s: return %d\n", __func__, ntohl(status));
        return status;
 }
@@ -1522,7 +1479,7 @@ __be32
 nfsd4_setclientid(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
                  struct nfsd4_setclientid *setclid)
 {
-        struct sockaddr_in      *sin = svc_addr_in(rqstp);
+        struct sockaddr         *sa = svc_addr(rqstp);
        struct xdr_netobj       clname = { 
                .len = setclid->se_namelen,
                .data = setclid->se_name,
@@ -1531,7 +1488,6 @@ nfsd4_setclientid(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
        unsigned int            strhashval;
        struct nfs4_client      *conf, *unconf, *new;
        __be32                  status;
-        char                    *princ;
        char                    dname[HEXDIR_LEN];
        
        if (!check_name(clname))
@@ -1554,8 +1510,11 @@ nfsd4_setclientid(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
                /* RFC 3530 14.2.33 CASE 0: */
                status = nfserr_clid_inuse;
                if (!same_creds(&conf->cl_cred, &rqstp->rq_cred)) {
-                        dprintk("NFSD: setclientid: string in use by client"
+                        char addr_str[INET6_ADDRSTRLEN];
-                                " at %pI4\n", &conf->cl_addr);
+                        rpc_ntop((struct sockaddr *) &conf->cl_addr, addr_str,
+                                 sizeof(addr_str));
+                        dprintk("NFSD: setclientid: string in use by client "
+                                "at %s\n", addr_str);
                        goto out;
                }
        }
@@ -1573,7 +1532,7 @@ nfsd4_setclientid(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
                 */
                if (unconf)
                        expire_client(unconf);
-                new = create_client(clname, dname);
+                new = create_client(clname, dname, rqstp, &clverifier);
                if (new == NULL)
                        goto out;
                gen_clid(new);
@@ -1590,7 +1549,7 @@ nfsd4_setclientid(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
                         */
                        expire_client(unconf);
                }
-                new = create_client(clname, dname);
+                new = create_client(clname, dname, rqstp, &clverifier);
                if (new == NULL)
                        goto out;
                copy_clid(new, conf);
@@ -1600,7 +1559,7 @@ nfsd4_setclientid(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
                 * probable client reboot; state will be removed if
                 * confirmed.
                 */
-                new = create_client(clname, dname);
+                new = create_client(clname, dname, rqstp, &clverifier);
                if (new == NULL)
                        goto out;
                gen_clid(new);
@@ -1611,25 +1570,12 @@ nfsd4_setclientid(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
                 * confirmed.
                 */
                expire_client(unconf);
-                new = create_client(clname, dname);
+                new = create_client(clname, dname, rqstp, &clverifier);
                if (new == NULL)
                        goto out;
                gen_clid(new);
        }
-        copy_verf(new, &clverifier);
+        gen_callback(new, setclid, rpc_get_scope_id(sa));
-        new->cl_addr = sin->sin_addr.s_addr;
-        new->cl_flavor = rqstp->rq_flavor;
-        princ = svc_gss_principal(rqstp);
-        if (princ) {
-                new->cl_principal = kstrdup(princ, GFP_KERNEL);
-                if (new->cl_principal == NULL) {
-                        free_client(new);
-                        goto out;
-                }
-        }
-        copy_cred(&new->cl_cred, &rqstp->rq_cred);
-        gen_confirm(new);
-        gen_callback(new, setclid);
        add_to_unconfirmed(new, strhashval);
        setclid->se_clientid.cl_boot = new->cl_clientid.cl_boot;
        setclid->se_clientid.cl_id = new->cl_clientid.cl_id;
@@ -1651,7 +1597,7 @@ nfsd4_setclientid_confirm(struct svc_rqst *rqstp,
                         struct nfsd4_compound_state *cstate,
                         struct nfsd4_setclientid_confirm *setclientid_confirm)
 {
-        struct sockaddr_in *sin = svc_addr_in(rqstp);
+        struct sockaddr *sa = svc_addr(rqstp);
        struct nfs4_client *conf, *unconf;
        nfs4_verifier confirm = setclientid_confirm->sc_confirm; 
        clientid_t * clid = &setclientid_confirm->sc_clientid;
@@ -1670,9 +1616,9 @@ nfsd4_setclientid_confirm(struct svc_rqst *rqstp,
        unconf = find_unconfirmed_client(clid);
        status = nfserr_clid_inuse;
-        if (conf && conf->cl_addr != sin->sin_addr.s_addr)
+        if (conf && !rpc_cmp_addr((struct sockaddr *) &conf->cl_addr, sa))
                goto out;
-        if (unconf && unconf->cl_addr != sin->sin_addr.s_addr)
+        if (unconf && !rpc_cmp_addr((struct sockaddr *) &unconf->cl_addr, sa))
                goto out;
        /*
@@ -2163,7 +2109,7 @@ int nfsd_change_deleg_cb(struct file_lock **onlist, int arg)
                return -EAGAIN;
 }
-static struct lock_manager_operations nfsd_lease_mng_ops = {
+static const struct lock_manager_operations nfsd_lease_mng_ops = {
        .fl_break = nfsd_break_deleg_cb,
        .fl_release_private = nfsd_release_deleg_cb,
        .fl_copy_lock = nfsd_copy_lock_deleg_cb,
@@ -3368,7 +3314,7 @@ nfs4_transform_lock_offset(struct file_lock *lock)
 /* Hack!: For now, we're defining this just so we can use a pointer to it
 * as a unique cookie to identify our (NFSv4's) posix locks. */
-static struct lock_manager_operations nfsd_posix_mng_ops  = {
+static const struct lock_manager_operations nfsd_posix_mng_ops  = {
 };
 static inline void
@@ -4072,7 +4018,7 @@ set_max_delegations(void)
 /* initialization to perform when the nfsd service is started: */
-static void
+static int
 __nfs4_state_start(void)
 {
        unsigned long grace_time;
@@ -4084,19 +4030,26 @@ __nfs4_state_start(void)
        printk(KERN_INFO "NFSD: starting %ld-second grace period\n",
               grace_time/HZ);
        laundry_wq = create_singlethread_workqueue("nfsd4");
+        if (laundry_wq == NULL)
+                return -ENOMEM;
        queue_delayed_work(laundry_wq, &laundromat_work, grace_time);
        set_max_delegations();
+        return set_callback_cred();
 }
-void
+int
 nfs4_state_start(void)
 {
+        int ret;
        if (nfs4_init)
-                return;
+                return 0;
        nfsd4_load_reboot_recovery_data();
-        __nfs4_state_start();
+        ret = __nfs4_state_start();
+        if (ret)
+                return ret;
        nfs4_init = 1;
-        return;
+        return 0;
 }
 time_t
diff --git a/fs/nfsd/nfs4xdr.c b/fs/nfsd/nfs4xdr.c
index 2dcc7feaa6ff..0fbd50cee1f6 100644
--- a/fs/nfsd/nfs4xdr.c
+++ b/fs/nfsd/nfs4xdr.c
@@ -1599,7 +1599,8 @@ static __be32 nfsd4_encode_fs_location4(struct nfsd4_fs_location *location,
 static char *nfsd4_path(struct svc_rqst *rqstp, struct svc_export *exp, __be32 *stat)
 {
        struct svc_fh tmp_fh;
-        char *path, *rootpath;
+        char *path = NULL, *rootpath;
+        size_t rootlen;
        fh_init(&tmp_fh, NFS4_FHSIZE);
        *stat = exp_pseudoroot(rqstp, &tmp_fh);
@@ -1609,14 +1610,18 @@ static char *nfsd4_path(struct svc_rqst *rqstp, struct svc_export *exp, __be32 *
        path = exp->ex_pathname;
-        if (strncmp(path, rootpath, strlen(rootpath))) {
+        rootlen = strlen(rootpath);
+        if (strncmp(path, rootpath, rootlen)) {
                dprintk("nfsd: fs_locations failed;"
                        "%s is not contained in %s\n", path, rootpath);
                *stat = nfserr_notsupp;
-                return NULL;
+                path = NULL;
+                goto out;
        }
+        path += rootlen;
-        return path + strlen(rootpath);
+out:
+        fh_put(&tmp_fh);
+        return path;
 }
 /*
@@ -1793,11 +1798,6 @@ nfsd4_encode_fattr(struct svc_fh *fhp, struct svc_export *exp,
                                goto out_nfserr;
                }
        }
-        if (bmval0 & FATTR4_WORD0_FS_LOCATIONS) {
-                if (exp->ex_fslocs.locations == NULL) {
-                        bmval0 &= ~FATTR4_WORD0_FS_LOCATIONS;
-                }
-        }
        if ((buflen -= 16) < 0)
                goto out_resource;
@@ -1825,8 +1825,6 @@ nfsd4_encode_fattr(struct svc_fh *fhp, struct svc_export *exp,
                        goto out_resource;
                if (!aclsupport)
                        word0 &= ~FATTR4_WORD0_ACL;
-                if (!exp->ex_fslocs.locations)
-                        word0 &= ~FATTR4_WORD0_FS_LOCATIONS;
                if (!word2) {
                        WRITE32(2);
                        WRITE32(word0);
@@ -3064,6 +3062,7 @@ nfsd4_encode_sequence(struct nfsd4_compoundres *resp, int nfserr,
        WRITE32(0);
        ADJUST_ARGS();
+        resp->cstate.datap = p; /* DRC cache data pointer */
        return 0;
 }
@@ -3166,7 +3165,7 @@ static int nfsd4_check_drc_limit(struct nfsd4_compoundres *resp)
                return status;
        session = resp->cstate.session;
-        if (session == NULL || slot->sl_cache_entry.ce_cachethis == 0)
+        if (session == NULL || slot->sl_cachethis == 0)
                return status;
        if (resp->opcnt >= args->opcnt)
@@ -3291,6 +3290,7 @@ nfs4svc_encode_compoundres(struct svc_rqst *rqstp, __be32 *p, struct nfsd4_compo
        /*
         * All that remains is to write the tag and operation count...
         */
+        struct nfsd4_compound_state *cs = &resp->cstate;
        struct kvec *iov;
        p = resp->tagp;
        *p++ = htonl(resp->taglen);
@@ -3304,17 +3304,11 @@ nfs4svc_encode_compoundres(struct svc_rqst *rqstp, __be32 *p, struct nfsd4_compo
                iov = &rqstp->rq_res.head[0];
        iov->iov_len = ((char*)resp->p) - (char*)iov->iov_base;
        BUG_ON(iov->iov_len > PAGE_SIZE);
-        if (nfsd4_has_session(&resp->cstate)) {
+        if (nfsd4_has_session(cs) && cs->status != nfserr_replay_cache) {
-                if (resp->cstate.status == nfserr_replay_cache &&
+                nfsd4_store_cache_entry(resp);
-                                !nfsd4_not_cached(resp)) {
+                dprintk("%s: SET SLOT STATE TO AVAILABLE\n", __func__);
-                        iov->iov_len = resp->cstate.iovlen;
+                resp->cstate.slot->sl_inuse = false;
-                } else {
+                nfsd4_put_session(resp->cstate.session);
-                        nfsd4_store_cache_entry(resp);
-                        dprintk("%s: SET SLOT STATE TO AVAILABLE\n", __func__);
-                        resp->cstate.slot->sl_inuse = 0;
-                }
-                if (resp->cstate.session)
-                        nfsd4_put_session(resp->cstate.session);
        }
        return 1;
 }
diff --git a/fs/nfsd/nfsctl.c b/fs/nfsd/nfsctl.c
index 7e906c5b7671..00388d2a3c99 100644
--- a/fs/nfsd/nfsctl.c
+++ b/fs/nfsd/nfsctl.c
@@ -174,12 +174,13 @@ static const struct file_operations exports_operations = {
 };
 extern int nfsd_pool_stats_open(struct inode *inode, struct file *file);
+extern int nfsd_pool_stats_release(struct inode *inode, struct file *file);
 static struct file_operations pool_stats_operations = {
        .open           = nfsd_pool_stats_open,
        .read           = seq_read,
        .llseek         = seq_lseek,
-        .release        = seq_release,
+        .release        = nfsd_pool_stats_release,
        .owner          = THIS_MODULE,
 };
@@ -776,10 +777,7 @@ static ssize_t write_pool_threads(struct file *file, char *buf, size_t size)
                size -= len;
                mesg += len;
        }
+        rv = mesg - buf;
-        mutex_unlock(&nfsd_mutex);
-        return (mesg-buf);
 out_free:
        kfree(nthreads);
        mutex_unlock(&nfsd_mutex);
diff --git a/fs/nfsd/nfsfh.c b/fs/nfsd/nfsfh.c
index 8847f3fbfc1e..01965b2f3a76 100644
--- a/fs/nfsd/nfsfh.c
+++ b/fs/nfsd/nfsfh.c
@@ -397,44 +397,51 @@ static inline void _fh_update_old(struct dentry *dentry,
                fh->ofh_dirino = 0;
 }
-__be32
+static bool is_root_export(struct svc_export *exp)
-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.
+        return exp->ex_path.dentry == exp->ex_path.dentry->d_sb->s_root;
-         * if it is non-null and for the same filesystem, then we should compose
+}
-         * a filehandle which is of the same version, where possible.
-         * Currently, that means that if ref_fh->fh_handle.fh_version == 0xca
-         * Then create a 32byte filehandle using nfs_fhbase_old
-         *
-         */
-        u8 version;
+static struct super_block *exp_sb(struct svc_export *exp)
-        u8 fsid_type = 0;
+{
-        struct inode * inode = dentry->d_inode;
+        return exp->ex_path.dentry->d_inode->i_sb;
-        struct dentry *parent = dentry->d_parent;
+}
-        __u32 *datap;
-        dev_t ex_dev = exp->ex_path.dentry->d_inode->i_sb->s_dev;
-        int root_export = (exp->ex_path.dentry == exp->ex_path.dentry->d_sb->s_root);
-        dprintk("nfsd: fh_compose(exp %02x:%02x/%ld %s/%s, ino=%ld)\n",
+static bool fsid_type_ok_for_exp(u8 fsid_type, struct svc_export *exp)
-                MAJOR(ex_dev), MINOR(ex_dev),
+{
-                (long) exp->ex_path.dentry->d_inode->i_ino,
+        switch (fsid_type) {
-                parent->d_name.name, dentry->d_name.name,
+        case FSID_DEV:
-                (inode ? inode->i_ino : 0));
+                if (!old_valid_dev(exp_sb(exp)->s_dev))
+                        return 0;
+                /* FALL THROUGH */
+        case FSID_MAJOR_MINOR:
+        case FSID_ENCODE_DEV:
+                return exp_sb(exp)->s_type->fs_flags & FS_REQUIRES_DEV;
+        case FSID_NUM:
+                return exp->ex_flags & NFSEXP_FSID;
+        case FSID_UUID8:
+        case FSID_UUID16:
+                if (!is_root_export(exp))
+                        return 0;
+                /* fall through */
+        case FSID_UUID4_INUM:
+        case FSID_UUID16_INUM:
+                return exp->ex_uuid != NULL;
+        }
+        return 1;
+}
-        /* Choose filehandle version and fsid type based on
-         * the reference filehandle (if it is in the same export)
+static void set_version_and_fsid_type(struct svc_fh *fhp, struct svc_export *exp, struct svc_fh *ref_fh)
-         * or the export options.
+{
-         */
+        u8 version;
- retry:
+        u8 fsid_type;
+retry:
        version = 1;
        if (ref_fh && ref_fh->fh_export == exp) {
                version = ref_fh->fh_handle.fh_version;
                fsid_type = ref_fh->fh_handle.fh_fsid_type;
-                if (ref_fh == fhp)
-                        fh_put(ref_fh);
                ref_fh = NULL;
                switch (version) {
@@ -447,58 +454,66 @@ fh_compose(struct svc_fh *fhp, struct svc_export *exp, struct dentry *dentry,
                        goto retry;
                }
-                /* Need to check that this type works for this
+                /*
-                 * export point.  As the fsid -> filesystem mapping
+                 * As the fsid -> filesystem mapping was guided by
-                 * was guided by user-space, there is no guarantee
+                 * user-space, there is no guarantee that the filesystem
-                 * that the filesystem actually supports that fsid
+                 * actually supports that fsid type. If it doesn't we
-                 * type. If it doesn't we loop around again without
+                 * loop around again without ref_fh set.
-                 * ref_fh set.
                 */
-                switch(fsid_type) {
+                if (!fsid_type_ok_for_exp(fsid_type, exp))
-                case FSID_DEV:
+                        goto retry;
-                        if (!old_valid_dev(ex_dev))
-                                goto retry;
-                        /* FALL THROUGH */
-                case FSID_MAJOR_MINOR:
-                case FSID_ENCODE_DEV:
-                        if (!(exp->ex_path.dentry->d_inode->i_sb->s_type->fs_flags
-                              & FS_REQUIRES_DEV))
-                                goto retry;
-                        break;
-                case FSID_NUM:
-                        if (! (exp->ex_flags & NFSEXP_FSID))
-                                goto retry;
-                        break;
-                case FSID_UUID8:
-                case FSID_UUID16:
-                        if (!root_export)
-                                goto retry;
-                        /* fall through */
-                case FSID_UUID4_INUM:
-                case FSID_UUID16_INUM:
-                        if (exp->ex_uuid == NULL)
-                                goto retry;
-                        break;
-                }
        } else if (exp->ex_flags & NFSEXP_FSID) {
                fsid_type = FSID_NUM;
        } else if (exp->ex_uuid) {
                if (fhp->fh_maxsize >= 64) {
-                        if (root_export)
+                        if (is_root_export(exp))
                                fsid_type = FSID_UUID16;
                        else
                                fsid_type = FSID_UUID16_INUM;
                } else {
-                        if (root_export)
+                        if (is_root_export(exp))
                                fsid_type = FSID_UUID8;
                        else
                                fsid_type = FSID_UUID4_INUM;
                }
-        } else if (!old_valid_dev(ex_dev))
+        } else if (!old_valid_dev(exp_sb(exp)->s_dev))
                /* for newer device numbers, we must use a newer fsid format */
                fsid_type = FSID_ENCODE_DEV;
        else
                fsid_type = FSID_DEV;
+        fhp->fh_handle.fh_version = version;
+        if (version)
+                fhp->fh_handle.fh_fsid_type = fsid_type;
+}
+__be32
+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
+         * a filehandle which is of the same version, where possible.
+         * Currently, that means that if ref_fh->fh_handle.fh_version == 0xca
+         * Then create a 32byte filehandle using nfs_fhbase_old
+         *
+         */
+        struct inode * inode = dentry->d_inode;
+        struct dentry *parent = dentry->d_parent;
+        __u32 *datap;
+        dev_t ex_dev = exp_sb(exp)->s_dev;
+        dprintk("nfsd: fh_compose(exp %02x:%02x/%ld %s/%s, ino=%ld)\n",
+                MAJOR(ex_dev), MINOR(ex_dev),
+                (long) exp->ex_path.dentry->d_inode->i_ino,
+                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.
+         */
+         set_version_and_fsid_type(fhp, exp, ref_fh);
        if (ref_fh == fhp)
                fh_put(ref_fh);
@@ -516,7 +531,7 @@ fh_compose(struct svc_fh *fhp, struct svc_export *exp, struct dentry *dentry,
        fhp->fh_export = exp;
        cache_get(&exp->h);
-        if (version == 0xca) {
+        if (fhp->fh_handle.fh_version == 0xca) {
                /* old style filehandle please */
                memset(&fhp->fh_handle.fh_base, 0, NFS_FHSIZE);
                fhp->fh_handle.fh_size = NFS_FHSIZE;
@@ -530,22 +545,22 @@ fh_compose(struct svc_fh *fhp, struct svc_export *exp, struct dentry *dentry,
                        _fh_update_old(dentry, exp, &fhp->fh_handle);
        } else {
                int len;
-                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 = fsid_type;
+                mk_fsid(fhp->fh_handle.fh_fsid_type, datap, ex_dev,
-                mk_fsid(fsid_type, datap, ex_dev,
                        exp->ex_path.dentry->d_inode->i_ino,
                        exp->ex_fsid, exp->ex_uuid);
-                len = key_len(fsid_type);
+                len = key_len(fhp->fh_handle.fh_fsid_type);
                datap += len/4;
                fhp->fh_handle.fh_size = 4 + len;
                if (inode)
                        _fh_update(fhp, exp, dentry);
-                if (fhp->fh_handle.fh_fileid_type == 255)
+                if (fhp->fh_handle.fh_fileid_type == 255) {
+                        fh_put(fhp);
                        return nfserr_opnotsupp;
+                }
        }
        return 0;
@@ -639,8 +654,7 @@ enum fsid_source fsid_source(struct svc_fh *fhp)
        case FSID_DEV:
        case FSID_ENCODE_DEV:
        case FSID_MAJOR_MINOR:
-                if (fhp->fh_export->ex_path.dentry->d_inode->i_sb->s_type->fs_flags
+                if (exp_sb(fhp->fh_export)->s_type->fs_flags & FS_REQUIRES_DEV)
-                    & FS_REQUIRES_DEV)
                        return FSIDSOURCE_DEV;
                break;
        case FSID_NUM:
diff --git a/fs/nfsd/nfssvc.c b/fs/nfsd/nfssvc.c
index 24d58adfe5fd..67ea83eedd43 100644
--- a/fs/nfsd/nfssvc.c
+++ b/fs/nfsd/nfssvc.c
@@ -34,6 +34,7 @@
 #include <linux/nfsd/syscall.h>
 #include <linux/lockd/bind.h>
 #include <linux/nfsacl.h>
+#include <linux/seq_file.h>
 #define NFSDDBG_FACILITY        NFSDDBG_SVC
@@ -66,6 +67,16 @@ struct timeval			nfssvc_boot;
 DEFINE_MUTEX(nfsd_mutex);
 struct svc_serv                 *nfsd_serv;
+/*
+ * nfsd_drc_lock protects nfsd_drc_max_pages and nfsd_drc_pages_used.
+ * nfsd_drc_max_pages limits the total amount of memory available for
+ * version 4.1 DRC caches.
+ * nfsd_drc_pages_used tracks the current version 4.1 DRC memory usage.
+ */
+spinlock_t      nfsd_drc_lock;
+unsigned int    nfsd_drc_max_mem;
+unsigned int    nfsd_drc_mem_used;
 #if defined(CONFIG_NFSD_V2_ACL) || defined(CONFIG_NFSD_V3_ACL)
 static struct svc_stat  nfsd_acl_svcstats;
 static struct svc_version *     nfsd_acl_version[] = {
@@ -235,13 +246,12 @@ void nfsd_reset_versions(void)
 */
 static void set_max_drc(void)
 {
-        /* The percent of nr_free_buffer_pages used by the V4.1 server DRC */
+        #define NFSD_DRC_SIZE_SHIFT     10
-        #define NFSD_DRC_SIZE_SHIFT     7
+        nfsd_drc_max_mem = (nr_free_buffer_pages()
-        nfsd_serv->sv_drc_max_pages = nr_free_buffer_pages()
+                                        >> NFSD_DRC_SIZE_SHIFT) * PAGE_SIZE;
-                                                >> NFSD_DRC_SIZE_SHIFT;
+        nfsd_drc_mem_used = 0;
-        nfsd_serv->sv_drc_pages_used = 0;
+        spin_lock_init(&nfsd_drc_lock);
-        dprintk("%s svc_drc_max_pages %u\n", __func__,
+        dprintk("%s nfsd_drc_max_mem %u \n", __func__, nfsd_drc_max_mem);
-                nfsd_serv->sv_drc_max_pages);
 }
 int nfsd_create_serv(void)
@@ -401,7 +411,9 @@ nfsd_svc(unsigned short port, int nrservs)
        error = nfsd_racache_init(2*nrservs);
        if (error<0)
                goto out;
-        nfs4_state_start();
+        error = nfs4_state_start();
+        if (error)
+                goto out;
        nfsd_reset_versions();
@@ -569,10 +581,6 @@ nfsd_dispatch(struct svc_rqst *rqstp, __be32 *statp)
                + rqstp->rq_res.head[0].iov_len;
        rqstp->rq_res.head[0].iov_len += sizeof(__be32);
-        /* NFSv4.1 DRC requires statp */
-        if (rqstp->rq_vers == 4)
-                nfsd4_set_statp(rqstp, statp);
        /* Now call the procedure handler, and encode NFS status. */
        nfserr = proc->pc_func(rqstp, rqstp->rq_argp, rqstp->rq_resp);
        nfserr = map_new_errors(rqstp->rq_vers, nfserr);
@@ -607,7 +615,25 @@ nfsd_dispatch(struct svc_rqst *rqstp, __be32 *statp)
 int nfsd_pool_stats_open(struct inode *inode, struct file *file)
 {
-        if (nfsd_serv == NULL)
+        int ret;
+        mutex_lock(&nfsd_mutex);
+        if (nfsd_serv == NULL) {
+                mutex_unlock(&nfsd_mutex);
                return -ENODEV;
-        return svc_pool_stats_open(nfsd_serv, file);
+        }
+        /* bump up the psudo refcount while traversing */
+        svc_get(nfsd_serv);
+        ret = svc_pool_stats_open(nfsd_serv, file);
+        mutex_unlock(&nfsd_mutex);
+        return ret;
+}
+int nfsd_pool_stats_release(struct inode *inode, struct file *file)
+{
+        int ret = seq_release(inode, file);
+        mutex_lock(&nfsd_mutex);
+        /* this function really, really should have been called svc_put() */
+        svc_destroy(nfsd_serv);
+        mutex_unlock(&nfsd_mutex);
+        return ret;
 }
diff --git a/fs/nfsd/vfs.c b/fs/nfsd/vfs.c
index 8fa09bfbcba7..a293f0273263 100644
--- a/fs/nfsd/vfs.c
+++ b/fs/nfsd/vfs.c
@@ -89,6 +89,12 @@ struct raparm_hbucket {
 #define RAPARM_HASH_MASK        (RAPARM_HASH_SIZE-1)
 static struct raparm_hbucket    raparm_hash[RAPARM_HASH_SIZE];
+static inline int
+nfsd_v4client(struct svc_rqst *rq)
+{
+    return rq->rq_prog == NFS_PROGRAM && rq->rq_vers == 4;
+}
 /* 
 * Called from nfsd_lookup and encode_dirent. Check if we have crossed 
 * a mount point.
@@ -115,7 +121,8 @@ nfsd_cross_mnt(struct svc_rqst *rqstp, struct dentry **dpp,
                path_put(&path);
                goto out;
        }
-        if ((exp->ex_flags & NFSEXP_CROSSMOUNT) || EX_NOHIDE(exp2)) {
+        if (nfsd_v4client(rqstp) ||
+                (exp->ex_flags & NFSEXP_CROSSMOUNT) || EX_NOHIDE(exp2)) {
                /* successfully crossed mount point */
                /*
                 * This is subtle: path.dentry is *not* on path.mnt
diff --git a/fs/nilfs2/btnode.c b/fs/nilfs2/btnode.c
index c668bca579c1..6a2711f4c321 100644
--- a/fs/nilfs2/btnode.c
+++ b/fs/nilfs2/btnode.c
@@ -46,7 +46,7 @@ void nilfs_btnode_cache_init_once(struct address_space *btnc)
        INIT_LIST_HEAD(&btnc->i_mmap_nonlinear);
 }
-static struct address_space_operations def_btnode_aops = {
+static const struct address_space_operations def_btnode_aops = {
        .sync_page              = block_sync_page,
 };
diff --git a/fs/nilfs2/file.c b/fs/nilfs2/file.c
index 6bd84a0d8238..fc8278c77cdd 100644
--- a/fs/nilfs2/file.c
+++ b/fs/nilfs2/file.c
@@ -151,7 +151,7 @@ struct file_operations nilfs_file_operations = {
        .splice_read    = generic_file_splice_read,
 };
-struct inode_operations nilfs_file_inode_operations = {
+const struct inode_operations nilfs_file_inode_operations = {
        .truncate       = nilfs_truncate,
        .setattr        = nilfs_setattr,
        .permission     = nilfs_permission,
diff --git a/fs/nilfs2/gcinode.c b/fs/nilfs2/gcinode.c
index 1b3c2bb20da9..e6de0a27ab5d 100644
--- a/fs/nilfs2/gcinode.c
+++ b/fs/nilfs2/gcinode.c
@@ -52,7 +52,7 @@
 #include "dat.h"
 #include "ifile.h"
-static struct address_space_operations def_gcinode_aops = {
+static const struct address_space_operations def_gcinode_aops = {
        .sync_page              = block_sync_page,
 };
diff --git a/fs/nilfs2/inode.c b/fs/nilfs2/inode.c
index 807e584b163d..2d2c501deb54 100644
--- a/fs/nilfs2/inode.c
+++ b/fs/nilfs2/inode.c
@@ -238,7 +238,7 @@ nilfs_direct_IO(int rw, struct kiocb *iocb, const struct iovec *iov,
        return size;
 }
-struct address_space_operations nilfs_aops = {
+const struct address_space_operations nilfs_aops = {
        .writepage              = nilfs_writepage,
        .readpage               = nilfs_readpage,
        .sync_page              = block_sync_page,
diff --git a/fs/nilfs2/mdt.c b/fs/nilfs2/mdt.c
index 156bf6091a96..b18c4998f8d0 100644
--- a/fs/nilfs2/mdt.c
+++ b/fs/nilfs2/mdt.c
@@ -427,12 +427,12 @@ nilfs_mdt_write_page(struct page *page, struct writeback_control *wbc)
 }
-static struct address_space_operations def_mdt_aops = {
+static const struct address_space_operations def_mdt_aops = {
        .writepage              = nilfs_mdt_write_page,
        .sync_page              = block_sync_page,
 };
-static struct inode_operations def_mdt_iops;
+static const struct inode_operations def_mdt_iops;
 static struct file_operations def_mdt_fops;
 /*
diff --git a/fs/nilfs2/namei.c b/fs/nilfs2/namei.c
index df70dadb336f..ed02e886fa79 100644
--- a/fs/nilfs2/namei.c
+++ b/fs/nilfs2/namei.c
@@ -448,7 +448,7 @@ out:
        return err;
 }
-struct inode_operations nilfs_dir_inode_operations = {
+const struct inode_operations nilfs_dir_inode_operations = {
        .create         = nilfs_create,
        .lookup         = nilfs_lookup,
        .link           = nilfs_link,
@@ -462,12 +462,12 @@ struct inode_operations nilfs_dir_inode_operations = {
        .permission     = nilfs_permission,
 };
-struct inode_operations nilfs_special_inode_operations = {
+const struct inode_operations nilfs_special_inode_operations = {
        .setattr        = nilfs_setattr,
        .permission     = nilfs_permission,
 };
-struct inode_operations nilfs_symlink_inode_operations = {
+const struct inode_operations nilfs_symlink_inode_operations = {
        .readlink       = generic_readlink,
        .follow_link    = page_follow_link_light,
        .put_link       = page_put_link,
diff --git a/fs/nilfs2/nilfs.h b/fs/nilfs2/nilfs.h
index 724c63766e82..bad7368782d0 100644
--- a/fs/nilfs2/nilfs.h
+++ b/fs/nilfs2/nilfs.h
@@ -295,12 +295,12 @@ void nilfs_clear_gcdat_inode(struct the_nilfs *);
 * Inodes and files operations
 */
 extern struct file_operations nilfs_dir_operations;
-extern struct inode_operations nilfs_file_inode_operations;
+extern const struct inode_operations nilfs_file_inode_operations;
 extern struct file_operations nilfs_file_operations;
-extern struct address_space_operations nilfs_aops;
+extern const struct address_space_operations nilfs_aops;
-extern struct inode_operations nilfs_dir_inode_operations;
+extern const struct inode_operations nilfs_dir_inode_operations;
-extern struct inode_operations nilfs_special_inode_operations;
+extern const struct inode_operations nilfs_special_inode_operations;
-extern struct inode_operations nilfs_symlink_inode_operations;
+extern const struct inode_operations nilfs_symlink_inode_operations;
 /*
 * filesystem type
diff --git a/fs/nilfs2/super.c b/fs/nilfs2/super.c
index 55f3d6b60732..644e66727dd0 100644
--- a/fs/nilfs2/super.c
+++ b/fs/nilfs2/super.c
@@ -504,7 +504,7 @@ static int nilfs_show_options(struct seq_file *seq, struct vfsmount *vfs)
        return 0;
 }
-static struct super_operations nilfs_sops = {
+static const struct super_operations nilfs_sops = {
        .alloc_inode    = nilfs_alloc_inode,
        .destroy_inode  = nilfs_destroy_inode,
        .dirty_inode    = nilfs_dirty_inode,
@@ -560,7 +560,7 @@ nilfs_fh_to_parent(struct super_block *sb, struct fid *fid, int fh_len,
                                    nilfs_nfs_get_inode);
 }
-static struct export_operations nilfs_export_ops = {
+static const struct export_operations nilfs_export_ops = {
        .fh_to_dentry = nilfs_fh_to_dentry,
        .fh_to_parent = nilfs_fh_to_parent,
        .get_parent = nilfs_get_parent,
diff --git a/fs/ntfs/layout.h b/fs/ntfs/layout.h
index 50931b1ce4b9..8b2549f672bf 100644
--- a/fs/ntfs/layout.h
+++ b/fs/ntfs/layout.h
@@ -829,7 +829,7 @@ enum {
        /* Note, FILE_ATTR_VALID_SET_FLAGS masks out the old DOS VolId, the
           F_A_DEVICE, F_A_DIRECTORY, F_A_SPARSE_FILE, F_A_REPARSE_POINT,
           F_A_COMPRESSED, and F_A_ENCRYPTED and preserves the rest.  This mask
-           is used to to obtain all flags that are valid for setting. */
+           is used to obtain all flags that are valid for setting. */
        /*
         * The flag FILE_ATTR_DUP_FILENAME_INDEX_PRESENT is present in all
         * FILENAME_ATTR attributes but not in the STANDARD_INFORMATION
diff --git a/fs/ntfs/malloc.h b/fs/ntfs/malloc.h
index cd0be3f5c3cd..a44b14cbceeb 100644
--- a/fs/ntfs/malloc.h
+++ b/fs/ntfs/malloc.h
@@ -47,7 +47,7 @@ static inline void *__ntfs_malloc(unsigned long size, gfp_t gfp_mask)
                return kmalloc(PAGE_SIZE, gfp_mask & ~__GFP_HIGHMEM);
                /* return (void *)__get_free_page(gfp_mask); */
        }
-        if (likely(size >> PAGE_SHIFT < num_physpages))
+        if (likely((size >> PAGE_SHIFT) < totalram_pages))
                return __vmalloc(size, gfp_mask, PAGE_KERNEL);
        return NULL;
 }
diff --git a/fs/ocfs2/quota.h b/fs/ocfs2/quota.h
index 3fb96fcd4c81..e5df9d170b0c 100644
--- a/fs/ocfs2/quota.h
+++ b/fs/ocfs2/quota.h
@@ -109,7 +109,7 @@ void ocfs2_unlock_global_qf(struct ocfs2_mem_dqinfo *oinfo, int ex);
 int ocfs2_read_quota_block(struct inode *inode, u64 v_block,
                           struct buffer_head **bh);
-extern struct dquot_operations ocfs2_quota_operations;
+extern const struct dquot_operations ocfs2_quota_operations;
 extern struct quota_format_type ocfs2_quota_format;
 int ocfs2_quota_setup(void);
diff --git a/fs/ocfs2/quota_global.c b/fs/ocfs2/quota_global.c
index 44f2a5e1d042..3cf0ec0acdd5 100644
--- a/fs/ocfs2/quota_global.c
+++ b/fs/ocfs2/quota_global.c
@@ -154,7 +154,7 @@ static int ocfs2_get_quota_block(struct inode *inode, int block,
                err = -EIO;
                mlog_errno(err);
        }
-        return err;;
+        return err;
 }
 /* Read data from global quotafile - avoid pagecache and such because we cannot
@@ -849,7 +849,7 @@ static void ocfs2_destroy_dquot(struct dquot *dquot)
        kmem_cache_free(ocfs2_dquot_cachep, dquot);
 }
-struct dquot_operations ocfs2_quota_operations = {
+const struct dquot_operations ocfs2_quota_operations = {
        .initialize     = dquot_initialize,
        .drop           = dquot_drop,
        .alloc_space    = dquot_alloc_space,
diff --git a/fs/ocfs2/super.c b/fs/ocfs2/super.c
index a3f8871d21fd..faca4720aa47 100644
--- a/fs/ocfs2/super.c
+++ b/fs/ocfs2/super.c
@@ -965,7 +965,7 @@ static int ocfs2_quota_off(struct super_block *sb, int type, int remount)
        return vfs_quota_disable(sb, type, DQUOT_LIMITS_ENABLED);
 }
-static struct quotactl_ops ocfs2_quotactl_ops = {
+static const struct quotactl_ops ocfs2_quotactl_ops = {
        .quota_on       = ocfs2_quota_on,
        .quota_off      = ocfs2_quota_off,
        .quota_sync     = vfs_quota_sync,
diff --git a/fs/omfs/dir.c b/fs/omfs/dir.c
index c7275cfbdcfb..3680bae335b5 100644
--- a/fs/omfs/dir.c
+++ b/fs/omfs/dir.c
@@ -489,7 +489,7 @@ out:
        return ret;
 }
-struct inode_operations omfs_dir_inops = {
+const struct inode_operations omfs_dir_inops = {
        .lookup = omfs_lookup,
        .mkdir = omfs_mkdir,
        .rename = omfs_rename,
diff --git a/fs/omfs/file.c b/fs/omfs/file.c
index d17e774eaf45..4845fbb18e6e 100644
--- a/fs/omfs/file.c
+++ b/fs/omfs/file.c
@@ -333,11 +333,11 @@ struct file_operations omfs_file_operations = {
        .splice_read = generic_file_splice_read,
 };
-struct inode_operations omfs_file_inops = {
+const struct inode_operations omfs_file_inops = {
        .truncate = omfs_truncate
 };
-struct address_space_operations omfs_aops = {
+const struct address_space_operations omfs_aops = {
        .readpage = omfs_readpage,
        .readpages = omfs_readpages,
        .writepage = omfs_writepage,
diff --git a/fs/omfs/inode.c b/fs/omfs/inode.c
index 379ae5fb4411..f3b7c1541f3a 100644
--- a/fs/omfs/inode.c
+++ b/fs/omfs/inode.c
@@ -278,7 +278,7 @@ static int omfs_statfs(struct dentry *dentry, struct kstatfs *buf)
        return 0;
 }
-static struct super_operations omfs_sops = {
+static const struct super_operations omfs_sops = {
        .write_inode    = omfs_write_inode,
        .delete_inode   = omfs_delete_inode,
        .put_super      = omfs_put_super,
diff --git a/fs/omfs/omfs.h b/fs/omfs/omfs.h
index 2bc0f0670406..df71039945ac 100644
--- a/fs/omfs/omfs.h
+++ b/fs/omfs/omfs.h
@@ -45,15 +45,15 @@ extern int omfs_clear_range(struct super_block *sb, u64 block, int count);
 /* dir.c */
 extern struct file_operations omfs_dir_operations;
-extern struct inode_operations omfs_dir_inops;
+extern const struct inode_operations omfs_dir_inops;
 extern int omfs_make_empty(struct inode *inode, struct super_block *sb);
 extern int omfs_is_bad(struct omfs_sb_info *sbi, struct omfs_header *header,
                        u64 fsblock);
 /* file.c */
 extern struct file_operations omfs_file_operations;
-extern struct inode_operations omfs_file_inops;
+extern const struct inode_operations omfs_file_inops;
-extern struct address_space_operations omfs_aops;
+extern const struct address_space_operations omfs_aops;
 extern void omfs_make_empty_table(struct buffer_head *bh, int offset);
 extern int omfs_shrink_inode(struct inode *inode);
diff --git a/fs/partitions/check.c b/fs/partitions/check.c
index fbeaddf595d3..7b685e10cbad 100644
--- a/fs/partitions/check.c
+++ b/fs/partitions/check.c
@@ -581,7 +581,7 @@ try_scan:
                }
                if (from + size > get_capacity(disk)) {
-                        struct block_device_operations *bdops = disk->fops;
+                        const struct block_device_operations *bdops = disk->fops;
                        unsigned long long capacity;
                        printk(KERN_WARNING
diff --git a/fs/proc/base.c b/fs/proc/base.c
index 6f742f6658a9..55c4c805a756 100644
--- a/fs/proc/base.c
+++ b/fs/proc/base.c
@@ -447,7 +447,7 @@ static int proc_oom_score(struct task_struct *task, char *buffer)
        do_posix_clock_monotonic_gettime(&uptime);
        read_lock(&tasklist_lock);
-        points = badness(task, uptime.tv_sec);
+        points = badness(task->group_leader, uptime.tv_sec);
        read_unlock(&tasklist_lock);
        return sprintf(buffer, "%lu\n", points);
 }
@@ -999,11 +999,17 @@ static ssize_t oom_adjust_read(struct file *file, char __user *buf,
        struct task_struct *task = get_proc_task(file->f_path.dentry->d_inode);
        char buffer[PROC_NUMBUF];
        size_t len;
-        int oom_adjust;
+        int oom_adjust = OOM_DISABLE;
+        unsigned long flags;
        if (!task)
                return -ESRCH;
-        oom_adjust = task->oomkilladj;
+        if (lock_task_sighand(task, &flags)) {
+                oom_adjust = task->signal->oom_adj;
+                unlock_task_sighand(task, &flags);
+        }
        put_task_struct(task);
        len = snprintf(buffer, sizeof(buffer), "%i\n", oom_adjust);
@@ -1015,32 +1021,44 @@ static ssize_t oom_adjust_write(struct file *file, const char __user *buf,
                                size_t count, loff_t *ppos)
 {
        struct task_struct *task;
-        char buffer[PROC_NUMBUF], *end;
+        char buffer[PROC_NUMBUF];
-        int oom_adjust;
+        long oom_adjust;
+        unsigned long flags;
+        int err;
        memset(buffer, 0, sizeof(buffer));
        if (count > sizeof(buffer) - 1)
                count = sizeof(buffer) - 1;
        if (copy_from_user(buffer, buf, count))
                return -EFAULT;
-        oom_adjust = simple_strtol(buffer, &end, 0);
+        err = strict_strtol(strstrip(buffer), 0, &oom_adjust);
+        if (err)
+                return -EINVAL;
        if ((oom_adjust < OOM_ADJUST_MIN || oom_adjust > OOM_ADJUST_MAX) &&
             oom_adjust != OOM_DISABLE)
                return -EINVAL;
-        if (*end == '\n')
-                end++;
        task = get_proc_task(file->f_path.dentry->d_inode);
        if (!task)
                return -ESRCH;
-        if (oom_adjust < task->oomkilladj && !capable(CAP_SYS_RESOURCE)) {
+        if (!lock_task_sighand(task, &flags)) {
+                put_task_struct(task);
+                return -ESRCH;
+        }
+        if (oom_adjust < task->signal->oom_adj && !capable(CAP_SYS_RESOURCE)) {
+                unlock_task_sighand(task, &flags);
                put_task_struct(task);
                return -EACCES;
        }
-        task->oomkilladj = oom_adjust;
+        task->signal->oom_adj = oom_adjust;
+        unlock_task_sighand(task, &flags);
        put_task_struct(task);
-        if (end - buffer == 0)
-                return -EIO;
+        return count;
-        return end - buffer;
 }
 static const struct file_operations proc_oom_adjust_operations = {
diff --git a/fs/proc/kcore.c b/fs/proc/kcore.c
index 59b43a068872..f06f45b42181 100644
--- a/fs/proc/kcore.c
+++ b/fs/proc/kcore.c
@@ -328,43 +328,12 @@ read_kcore(struct file *file, char __user *buffer, size_t buflen, loff_t *fpos)
                                return -EFAULT;
                } else if (is_vmalloc_addr((void *)start)) {
                        char * elf_buf;
-                        struct vm_struct *m;
-                        unsigned long curstart = start;
-                        unsigned long cursize = tsz;
                        elf_buf = kzalloc(tsz, GFP_KERNEL);
                        if (!elf_buf)
                                return -ENOMEM;
+                        vread(elf_buf, (char *)start, tsz);
-                        read_lock(&vmlist_lock);
+                        /* we have to zero-fill user buffer even if no read */
-                        for (m=vmlist; m && cursize; m=m->next) {
-                                unsigned long vmstart;
-                                unsigned long vmsize;
-                                unsigned long msize = m->size - PAGE_SIZE;
-                                if (((unsigned long)m->addr + msize) < 
-                                                                curstart)
-                                        continue;
-                                if ((unsigned long)m->addr > (curstart + 
-                                                                cursize))
-                                        break;
-                                vmstart = (curstart < (unsigned long)m->addr ? 
-                                        (unsigned long)m->addr : curstart);
-                                if (((unsigned long)m->addr + msize) > 
-                                                        (curstart + cursize))
-                                        vmsize = curstart + cursize - vmstart;
-                                else
-                                        vmsize = (unsigned long)m->addr + 
-                                                        msize - vmstart;
-                                curstart = vmstart + vmsize;
-                                cursize -= vmsize;
-                                /* don't dump ioremap'd stuff! (TA) */
-                                if (m->flags & VM_IOREMAP)
-                                        continue;
-                                memcpy(elf_buf + (vmstart - start),
-                                        (char *)vmstart, vmsize);
-                        }
-                        read_unlock(&vmlist_lock);
                        if (copy_to_user(buffer, elf_buf, tsz)) {
                                kfree(elf_buf);
                                return -EFAULT;
diff --git a/fs/proc/meminfo.c b/fs/proc/meminfo.c
index d5c410d47fae..171e052c07b3 100644
--- a/fs/proc/meminfo.c
+++ b/fs/proc/meminfo.c
@@ -81,9 +81,11 @@ static int meminfo_proc_show(struct seq_file *m, void *v)
                "Writeback:      %8lu kB\n"
                "AnonPages:      %8lu kB\n"
                "Mapped:         %8lu kB\n"
+                "Shmem:          %8lu kB\n"
                "Slab:           %8lu kB\n"
                "SReclaimable:   %8lu kB\n"
                "SUnreclaim:     %8lu kB\n"
+                "KernelStack:    %8lu kB\n"
                "PageTables:     %8lu kB\n"
 #ifdef CONFIG_QUICKLIST
                "Quicklists:     %8lu kB\n"
@@ -124,10 +126,12 @@ static int meminfo_proc_show(struct seq_file *m, void *v)
                K(global_page_state(NR_WRITEBACK)),
                K(global_page_state(NR_ANON_PAGES)),
                K(global_page_state(NR_FILE_MAPPED)),
+                K(global_page_state(NR_SHMEM)),
                K(global_page_state(NR_SLAB_RECLAIMABLE) +
                                global_page_state(NR_SLAB_UNRECLAIMABLE)),
                K(global_page_state(NR_SLAB_RECLAIMABLE)),
                K(global_page_state(NR_SLAB_UNRECLAIMABLE)),
+                global_page_state(NR_KERNEL_STACK) * THREAD_SIZE / 1024,
                K(global_page_state(NR_PAGETABLE)),
 #ifdef CONFIG_QUICKLIST
                K(quicklist_total_size()),
diff --git a/fs/proc/page.c b/fs/proc/page.c
index 2707c6c7a20f..2281c2cbfe2b 100644
--- a/fs/proc/page.c
+++ b/fs/proc/page.c
@@ -2,6 +2,7 @@
 #include <linux/compiler.h>
 #include <linux/fs.h>
 #include <linux/init.h>
+#include <linux/ksm.h>
 #include <linux/mm.h>
 #include <linux/mmzone.h>
 #include <linux/proc_fs.h>
@@ -95,6 +96,8 @@ static const struct file_operations proc_kpagecount_operations = {
 #define KPF_UNEVICTABLE         18
 #define KPF_NOPAGE              20
+#define KPF_KSM                 21
 /* kernel hacking assistances
 * WARNING: subject to change, never rely on them!
 */
@@ -137,6 +140,8 @@ static u64 get_uflags(struct page *page)
                u |= 1 << KPF_MMAP;
        if (PageAnon(page))
                u |= 1 << KPF_ANON;
+        if (PageKsm(page))
+                u |= 1 << KPF_KSM;
        /*
         * compound pages: export both head/tail info
diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c
index 9bd8be1d235c..59e98fea34a4 100644
--- a/fs/proc/task_mmu.c
+++ b/fs/proc/task_mmu.c
@@ -465,6 +465,10 @@ static int clear_refs_pte_range(pmd_t *pmd, unsigned long addr,
        return 0;
 }
+#define CLEAR_REFS_ALL 1
+#define CLEAR_REFS_ANON 2
+#define CLEAR_REFS_MAPPED 3
 static ssize_t clear_refs_write(struct file *file, const char __user *buf,
                                size_t count, loff_t *ppos)
 {
@@ -472,13 +476,15 @@ static ssize_t clear_refs_write(struct file *file, const char __user *buf,
        char buffer[PROC_NUMBUF], *end;
        struct mm_struct *mm;
        struct vm_area_struct *vma;
+        int type;
        memset(buffer, 0, sizeof(buffer));
        if (count > sizeof(buffer) - 1)
                count = sizeof(buffer) - 1;
        if (copy_from_user(buffer, buf, count))
                return -EFAULT;
-        if (!simple_strtol(buffer, &end, 0))
+        type = simple_strtol(buffer, &end, 0);
+        if (type < CLEAR_REFS_ALL || type > CLEAR_REFS_MAPPED)
                return -EINVAL;
        if (*end == '\n')
                end++;
@@ -494,9 +500,23 @@ static ssize_t clear_refs_write(struct file *file, const char __user *buf,
                down_read(&mm->mmap_sem);
                for (vma = mm->mmap; vma; vma = vma->vm_next) {
                        clear_refs_walk.private = vma;
-                        if (!is_vm_hugetlb_page(vma))
+                        if (is_vm_hugetlb_page(vma))
-                                walk_page_range(vma->vm_start, vma->vm_end,
+                                continue;
-                                                &clear_refs_walk);
+                        /*
+                         * Writing 1 to /proc/pid/clear_refs affects all pages.
+                         *
+                         * Writing 2 to /proc/pid/clear_refs only affects
+                         * Anonymous pages.
+                         *
+                         * Writing 3 to /proc/pid/clear_refs only affects file
+                         * mapped pages.
+                         */
+                        if (type == CLEAR_REFS_ANON && vma->vm_file)
+                                continue;
+                        if (type == CLEAR_REFS_MAPPED && !vma->vm_file)
+                                continue;
+                        walk_page_range(vma->vm_start, vma->vm_end,
+                                        &clear_refs_walk);
                }
                flush_tlb_mm(mm);
                up_read(&mm->mmap_sem);
diff --git a/fs/quota/dquot.c b/fs/quota/dquot.c
index 38f7bd559f35..39b49c42a7ed 100644
--- a/fs/quota/dquot.c
+++ b/fs/quota/dquot.c
@@ -1839,7 +1839,7 @@ EXPORT_SYMBOL(dquot_commit_info);
 /*
 * Definitions of diskquota operations.
 */
-struct dquot_operations dquot_operations = {
+const struct dquot_operations dquot_operations = {
        .initialize     = dquot_initialize,
        .drop           = dquot_drop,
        .alloc_space    = dquot_alloc_space,
@@ -2461,7 +2461,7 @@ out:
 }
 EXPORT_SYMBOL(vfs_set_dqinfo);
-struct quotactl_ops vfs_quotactl_ops = {
+const struct quotactl_ops vfs_quotactl_ops = {
        .quota_on       = vfs_quota_on,
        .quota_off      = vfs_quota_off,
        .quota_sync     = vfs_quota_sync,
diff --git a/fs/reiserfs/super.c b/fs/reiserfs/super.c
index 7adea74d6a8a..f0ad05f38022 100644
--- a/fs/reiserfs/super.c
+++ b/fs/reiserfs/super.c
@@ -612,7 +612,7 @@ static int reiserfs_mark_dquot_dirty(struct dquot *);
 static int reiserfs_write_info(struct super_block *, int);
 static int reiserfs_quota_on(struct super_block *, int, int, char *, int);
-static struct dquot_operations reiserfs_quota_operations = {
+static const struct dquot_operations reiserfs_quota_operations = {
        .initialize = dquot_initialize,
        .drop = dquot_drop,
        .alloc_space = dquot_alloc_space,
@@ -629,7 +629,7 @@ static struct dquot_operations reiserfs_quota_operations = {
        .destroy_dquot  = dquot_destroy,
 };
-static struct quotactl_ops reiserfs_qctl_operations = {
+static const struct quotactl_ops reiserfs_qctl_operations = {
        .quota_on = reiserfs_quota_on,
        .quota_off = vfs_quota_off,
        .quota_sync = vfs_quota_sync,
diff --git a/fs/romfs/super.c b/fs/romfs/super.c
index 4ab3c03d8f95..47f132df0c3f 100644
--- a/fs/romfs/super.c
+++ b/fs/romfs/super.c
@@ -284,7 +284,7 @@ static const struct file_operations romfs_dir_operations = {
        .readdir        = romfs_readdir,
 };
-static struct inode_operations romfs_dir_inode_operations = {
+static const struct inode_operations romfs_dir_inode_operations = {
        .lookup         = romfs_lookup,
 };
diff --git a/fs/squashfs/super.c b/fs/squashfs/super.c
index cb5fc57e370b..6c197ef53add 100644
--- a/fs/squashfs/super.c
+++ b/fs/squashfs/super.c
@@ -44,7 +44,7 @@
 #include "squashfs.h"
 static struct file_system_type squashfs_fs_type;
-static struct super_operations squashfs_super_ops;
+static const struct super_operations squashfs_super_ops;
 static int supported_squashfs_filesystem(short major, short minor, short comp)
 {
@@ -444,7 +444,7 @@ static struct file_system_type squashfs_fs_type = {
        .fs_flags = FS_REQUIRES_DEV
 };
-static struct super_operations squashfs_super_ops = {
+static const struct super_operations squashfs_super_ops = {
        .alloc_inode = squashfs_alloc_inode,
        .destroy_inode = squashfs_destroy_inode,
        .statfs = squashfs_statfs,
diff --git a/fs/super.c b/fs/super.c
index b03fea8fbfb6..0e7207b9815c 100644
--- a/fs/super.c
+++ b/fs/super.c
@@ -54,7 +54,7 @@ DEFINE_SPINLOCK(sb_lock);
 static struct super_block *alloc_super(struct file_system_type *type)
 {
        struct super_block *s = kzalloc(sizeof(struct super_block),  GFP_USER);
-        static struct super_operations default_op;
+        static const struct super_operations default_op;
        if (s) {
                if (security_sb_alloc(s)) {
diff --git a/fs/ubifs/xattr.c b/fs/ubifs/xattr.c
index 7998cc378250..195830f47569 100644
--- a/fs/ubifs/xattr.c
+++ b/fs/ubifs/xattr.c
@@ -79,7 +79,7 @@ enum {
 };
 static const struct inode_operations none_inode_operations;
-static struct address_space_operations none_address_operations;
+static const struct address_space_operations none_address_operations;
 static const struct file_operations none_file_operations;
 /**
diff --git a/fs/xfs/linux-2.6/xfs_quotaops.c b/fs/xfs/linux-2.6/xfs_quotaops.c
index cb6e2cca214f..9e41f91aa269 100644
--- a/fs/xfs/linux-2.6/xfs_quotaops.c
+++ b/fs/xfs/linux-2.6/xfs_quotaops.c
@@ -150,7 +150,7 @@ xfs_fs_set_xquota(
        return -xfs_qm_scall_setqlim(mp, id, xfs_quota_type(type), fdq);
 }
-struct quotactl_ops xfs_quotactl_operations = {
+const struct quotactl_ops xfs_quotactl_operations = {
        .quota_sync             = xfs_fs_quota_sync,
        .get_xstate             = xfs_fs_get_xstate,
        .set_xstate             = xfs_fs_set_xstate,
diff --git a/fs/xfs/linux-2.6/xfs_super.c b/fs/xfs/linux-2.6/xfs_super.c
index 5d7c60ac77b4..bdd41c8c342f 100644
--- a/fs/xfs/linux-2.6/xfs_super.c
+++ b/fs/xfs/linux-2.6/xfs_super.c
@@ -67,7 +67,7 @@
 #include <linux/freezer.h>
 #include <linux/parser.h>
-static struct super_operations xfs_super_operations;
+static const struct super_operations xfs_super_operations;
 static kmem_zone_t *xfs_ioend_zone;
 mempool_t *xfs_ioend_pool;
@@ -1536,7 +1536,7 @@ xfs_fs_get_sb(
                           mnt);
 }
-static struct super_operations xfs_super_operations = {
+static const struct super_operations xfs_super_operations = {
        .alloc_inode            = xfs_fs_alloc_inode,
        .destroy_inode          = xfs_fs_destroy_inode,
        .write_inode            = xfs_fs_write_inode,
diff --git a/fs/xfs/linux-2.6/xfs_super.h b/fs/xfs/linux-2.6/xfs_super.h
index 5a2ea3a21781..18175ebd58ed 100644
--- a/fs/xfs/linux-2.6/xfs_super.h
+++ b/fs/xfs/linux-2.6/xfs_super.h
@@ -93,7 +93,7 @@ extern void xfs_blkdev_issue_flush(struct xfs_buftarg *);
 extern const struct export_operations xfs_export_operations;
 extern struct xattr_handler *xfs_xattr_handlers[];
-extern struct quotactl_ops xfs_quotactl_operations;
+extern const struct quotactl_ops xfs_quotactl_operations;
 #define XFS_M(sb)               ((struct xfs_mount *)((sb)->s_fs_info))
diff --git a/fs/xfs/xfs_fs.h b/fs/xfs/xfs_fs.h
index c4ea51b55dce..f52ac276277e 100644
--- a/fs/xfs/xfs_fs.h
+++ b/fs/xfs/xfs_fs.h
@@ -117,7 +117,7 @@ struct getbmapx {
 #define BMV_IF_VALID    \
        (BMV_IF_ATTRFORK|BMV_IF_NO_DMAPI_READ|BMV_IF_PREALLOC|BMV_IF_DELALLOC)
-/*      bmv_oflags values - returned for for each non-header segment */
+/*      bmv_oflags values - returned for each non-header segment */
 #define BMV_OF_PREALLOC         0x1     /* segment = unwritten pre-allocation */
 #define BMV_OF_DELALLOC         0x2     /* segment = delayed allocation */
 #define BMV_OF_LAST             0x4     /* segment is the last in the file */