152 files changed, 1528 insertions, 1452 deletions

diff --git a/fs/9p/v9fs_vfs.h b/fs/9p/v9fs_vfs.h
index bab0eac873f4..b789f8e597ec 100644
--- a/fs/9p/v9fs_vfs.h
+++ b/fs/9p/v9fs_vfs.h
@@ -59,7 +59,6 @@ void v9fs_stat2inode_dotl(struct p9_stat_dotl *, struct inode *);
 int v9fs_dir_release(struct inode *inode, struct file *filp);
 int v9fs_file_open(struct inode *inode, struct file *file);
 void v9fs_inode2stat(struct inode *inode, struct p9_wstat *stat);
-void v9fs_dentry_release(struct dentry *);
 int v9fs_uflags2omode(int uflags, int extended);
 
 ssize_t v9fs_file_readn(struct file *, char *, char __user *, u32, u64);
diff --git a/fs/9p/vfs_dentry.c b/fs/9p/vfs_dentry.c
index 466d2a4fc5cb..233b7d4ffe5e 100644
--- a/fs/9p/vfs_dentry.c
+++ b/fs/9p/vfs_dentry.c
@@ -86,7 +86,7 @@ static int v9fs_cached_dentry_delete(const struct dentry *dentry)
  *
  */
 
-void v9fs_dentry_release(struct dentry *dentry)
+static void v9fs_dentry_release(struct dentry *dentry)
 {
         struct v9fs_dentry *dent;
         struct p9_fid *temp, *current_fid;
diff --git a/fs/9p/vfs_inode.c b/fs/9p/vfs_inode.c
index 5076eeb95502..b76a40bdf4c2 100644
--- a/fs/9p/vfs_inode.c
+++ b/fs/9p/vfs_inode.c
@@ -699,11 +699,6 @@ struct dentry *v9fs_vfs_lookup(struct inode *dir, struct dentry *dentry,
                 goto error_iput;
 
 inst_out:
-        if (v9ses->cache)
-                d_set_d_op(dentry, &v9fs_cached_dentry_operations);
-        else
-                d_set_d_op(dentry, &v9fs_dentry_operations);
-
         d_add(dentry, inode);
         return NULL;
 
diff --git a/fs/9p/vfs_super.c b/fs/9p/vfs_super.c
index c55c614500ad..dbaabe3b8131 100644
--- a/fs/9p/vfs_super.c
+++ b/fs/9p/vfs_super.c
@@ -141,6 +141,11 @@ static struct dentry *v9fs_mount(struct file_system_type *fs_type, int flags,
         }
         v9fs_fill_super(sb, v9ses, flags, data);
 
+        if (v9ses->cache)
+                sb->s_d_op = &v9fs_cached_dentry_operations;
+        else
+                sb->s_d_op = &v9fs_dentry_operations;
+
         inode = v9fs_get_inode(sb, S_IFDIR | mode);
         if (IS_ERR(inode)) {
                 retval = PTR_ERR(inode);
@@ -217,9 +222,6 @@ static void v9fs_kill_super(struct super_block *s)
 
         P9_DPRINTK(P9_DEBUG_VFS, " %p\n", s);
 
-        if (s->s_root)
-                v9fs_dentry_release(s->s_root); /* clunk root */
-
         kill_anon_super(s);
 
         v9fs_session_cancel(v9ses);
diff --git a/fs/adfs/dir.c b/fs/adfs/dir.c
index bf7693c384f9..3b4a764ed780 100644
--- a/fs/adfs/dir.c
+++ b/fs/adfs/dir.c
@@ -276,7 +276,6 @@ adfs_lookup(struct inode *dir, struct dentry *dentry, struct nameidata *nd)
         struct object_info obj;
         int error;
 
-        d_set_d_op(dentry, &adfs_dentry_operations);
         lock_kernel();
         error = adfs_dir_lookup_byname(dir, &dentry->d_name, &obj);
         if (error == 0) {
diff --git a/fs/adfs/super.c b/fs/adfs/super.c
index a4041b52fbca..2d7954049fbe 100644
--- a/fs/adfs/super.c
+++ b/fs/adfs/super.c
@@ -473,6 +473,7 @@ static int adfs_fill_super(struct super_block *sb, void *data, int silent)
                 asb->s_namelen = ADFS_F_NAME_LEN;
         }
 
+        sb->s_d_op = &adfs_dentry_operations;
         root = adfs_iget(sb, &root_obj);
         sb->s_root = d_alloc_root(root);
         if (!sb->s_root) {
@@ -483,8 +484,7 @@ static int adfs_fill_super(struct super_block *sb, void *data, int silent)
                 kfree(asb->s_map);
                 adfs_error(sb, "get root inode failed\n");
                 goto error;
-        } else
-                d_set_d_op(sb->s_root, &adfs_dentry_operations);
+        }
         unlock_kernel();
         return 0;
 
diff --git a/fs/affs/affs.h b/fs/affs/affs.h
index a8cbdeb34025..0e95f73a7023 100644
--- a/fs/affs/affs.h
+++ b/fs/affs/affs.h
@@ -201,6 +201,7 @@ extern const struct address_space_operations	 affs_aops;
 extern const struct address_space_operations     affs_aops_ofs;
 
 extern const struct dentry_operations    affs_dentry_operations;
+extern const struct dentry_operations    affs_intl_dentry_operations;
 
 static inline void
 affs_set_blocksize(struct super_block *sb, int size)
diff --git a/fs/affs/namei.c b/fs/affs/namei.c
index 944a4042fb65..e3e9efc1fdd8 100644
--- a/fs/affs/namei.c
+++ b/fs/affs/namei.c
@@ -32,7 +32,7 @@ const struct dentry_operations affs_dentry_operations = {
         .d_compare      = affs_compare_dentry,
 };
 
-static const struct dentry_operations affs_intl_dentry_operations = {
+const struct dentry_operations affs_intl_dentry_operations = {
         .d_hash         = affs_intl_hash_dentry,
         .d_compare      = affs_intl_compare_dentry,
 };
@@ -240,7 +240,6 @@ affs_lookup(struct inode *dir, struct dentry *dentry, struct nameidata *nd)
                 if (IS_ERR(inode))
                         return ERR_CAST(inode);
         }
-        d_set_d_op(dentry, AFFS_SB(sb)->s_flags & SF_INTL ? &affs_intl_dentry_operations : &affs_dentry_operations);
         d_add(dentry, inode);
         return NULL;
 }
diff --git a/fs/affs/super.c b/fs/affs/super.c
index d39081bbe7ce..b31507d0f9b9 100644
--- a/fs/affs/super.c
+++ b/fs/affs/super.c
@@ -477,12 +477,16 @@ got_root:
                 goto out_error_noinode;
         }
 
+        if (AFFS_SB(sb)->s_flags & SF_INTL)
+                sb->s_d_op = &affs_intl_dentry_operations;
+        else
+                sb->s_d_op = &affs_dentry_operations;
+
         sb->s_root = d_alloc_root(root_inode);
         if (!sb->s_root) {
                 printk(KERN_ERR "AFFS: Get root inode failed\n");
                 goto out_error;
         }
-        d_set_d_op(sb->s_root, &affs_dentry_operations);
 
         pr_debug("AFFS: s_flags=%lX\n",sb->s_flags);
         return 0;
diff --git a/fs/afs/dir.c b/fs/afs/dir.c
index 34a3263d60a4..e6a4ab980e31 100644
--- a/fs/afs/dir.c
+++ b/fs/afs/dir.c
@@ -62,7 +62,7 @@ const struct inode_operations afs_dir_inode_operations = {
         .setattr        = afs_setattr,
 };
 
-static const struct dentry_operations afs_fs_dentry_operations = {
+const struct dentry_operations afs_fs_dentry_operations = {
         .d_revalidate   = afs_d_revalidate,
         .d_delete       = afs_d_delete,
         .d_release      = afs_d_release,
@@ -582,8 +582,6 @@ static struct dentry *afs_lookup(struct inode *dir, struct dentry *dentry,
         }
 
 success:
-        d_set_d_op(dentry, &afs_fs_dentry_operations);
-
         d_add(dentry, inode);
         _leave(" = 0 { vn=%u u=%u } -> { ino=%lu v=%llu }",
                fid.vnode,
diff --git a/fs/afs/internal.h b/fs/afs/internal.h
index 6d4bc1c8ff60..ab6db5abaf53 100644
--- a/fs/afs/internal.h
+++ b/fs/afs/internal.h
@@ -486,6 +486,7 @@ extern bool afs_cm_incoming_call(struct afs_call *);
  * dir.c
  */
 extern const struct inode_operations afs_dir_inode_operations;
+extern const struct dentry_operations afs_fs_dentry_operations;
 extern const struct file_operations afs_dir_file_operations;
 
 /*
diff --git a/fs/afs/super.c b/fs/afs/super.c
index f901a9d7c111..fb240e8766d6 100644
--- a/fs/afs/super.c
+++ b/fs/afs/super.c
@@ -336,6 +336,7 @@ static int afs_fill_super(struct super_block *sb, void *data)
         if (!root)
                 goto error;
 
+        sb->s_d_op = &afs_fs_dentry_operations;
         sb->s_root = root;
 
         _leave(" = 0");
diff --git a/fs/aio.c b/fs/aio.c
index 8c8f6c5b6d79..5e00f15c54aa 100644
--- a/fs/aio.c
+++ b/fs/aio.c
@@ -798,29 +798,12 @@ static void aio_queue_work(struct kioctx * ctx)
         queue_delayed_work(aio_wq, &ctx->wq, timeout);
 }
 
-
-/*
- * aio_run_iocbs:
- *      Process all pending retries queued on the ioctx
- *      run list.
- * Assumes it is operating within the aio issuer's mm
- * context.
- */
-static inline void aio_run_iocbs(struct kioctx *ctx)
-{
-        int requeue;
-
-        spin_lock_irq(&ctx->ctx_lock);
-
-        requeue = __aio_run_iocbs(ctx);
-        spin_unlock_irq(&ctx->ctx_lock);
-        if (requeue)
-                aio_queue_work(ctx);
-}
-
 /*
- * just like aio_run_iocbs, but keeps running them until
- * the list stays empty
+ * aio_run_all_iocbs:
+ *      Process all pending retries queued on the ioctx
+ *      run list, and keep running them until the list
+ *      stays empty.
+ * Assumes it is operating within the aio issuer's mm context.
  */
 static inline void aio_run_all_iocbs(struct kioctx *ctx)
 {
@@ -1839,7 +1822,7 @@ SYSCALL_DEFINE5(io_getevents, aio_context_t, ctx_id,
         long ret = -EINVAL;
 
         if (likely(ioctx)) {
-                if (likely(min_nr <= nr && min_nr >= 0 && nr >= 0))
+                if (likely(min_nr <= nr && min_nr >= 0))
                         ret = read_events(ioctx, min_nr, nr, events, timeout);
                 put_ioctx(ioctx);
         }
diff --git a/fs/anon_inodes.c b/fs/anon_inodes.c
index 5fd38112a6ca..cbe57f3c4d89 100644
--- a/fs/anon_inodes.c
+++ b/fs/anon_inodes.c
@@ -26,12 +26,6 @@ static struct vfsmount *anon_inode_mnt __read_mostly;
 static struct inode *anon_inode_inode;
 static const struct file_operations anon_inode_fops;
 
-static struct dentry *anon_inodefs_mount(struct file_system_type *fs_type,
-                                int flags, const char *dev_name, void *data)
-{
-        return mount_pseudo(fs_type, "anon_inode:", NULL, ANON_INODE_FS_MAGIC);
-}
-
 /*
  * anon_inodefs_dname() is called from d_path().
  */
@@ -41,14 +35,22 @@ static char *anon_inodefs_dname(struct dentry *dentry, char *buffer, int buflen)
                                 dentry->d_name.name);
 }
 
+static const struct dentry_operations anon_inodefs_dentry_operations = {
+        .d_dname        = anon_inodefs_dname,
+};
+
+static struct dentry *anon_inodefs_mount(struct file_system_type *fs_type,
+                                int flags, const char *dev_name, void *data)
+{
+        return mount_pseudo(fs_type, "anon_inode:", NULL,
+                        &anon_inodefs_dentry_operations, ANON_INODE_FS_MAGIC);
+}
+
 static struct file_system_type anon_inode_fs_type = {
         .name           = "anon_inodefs",
         .mount          = anon_inodefs_mount,
         .kill_sb        = kill_anon_super,
 };
-static const struct dentry_operations anon_inodefs_dentry_operations = {
-        .d_dname        = anon_inodefs_dname,
-};
 
 /*
  * nop .set_page_dirty method so that people can use .page_mkwrite on
@@ -64,9 +66,9 @@ static const struct address_space_operations anon_aops = {
 };
 
 /**
- * anon_inode_getfd - creates a new file instance by hooking it up to an
- *                    anonymous inode, and a dentry that describe the "class"
- *                    of the file
+ * anon_inode_getfile - creates a new file instance by hooking it up to an
+ *                      anonymous inode, and a dentry that describe the "class"
+ *                      of the file
  *
  * @name:    [in]    name of the "class" of the new file
  * @fops:    [in]    file operations for the new file
@@ -113,7 +115,6 @@ struct file *anon_inode_getfile(const char *name,
          */
         ihold(anon_inode_inode);
 
-        d_set_d_op(path.dentry, &anon_inodefs_dentry_operations);
         d_instantiate(path.dentry, anon_inode_inode);
 
         error = -ENFILE;
diff --git a/fs/befs/endian.h b/fs/befs/endian.h
index 6cb84d896d05..27223878ba9f 100644
--- a/fs/befs/endian.h
+++ b/fs/befs/endian.h
@@ -102,22 +102,22 @@ cpu_to_fsrun(const struct super_block *sb, befs_block_run n)
 }
 
 static inline befs_data_stream
-fsds_to_cpu(const struct super_block *sb, befs_disk_data_stream n)
+fsds_to_cpu(const struct super_block *sb, const befs_disk_data_stream *n)
 {
         befs_data_stream data;
         int i;
 
         for (i = 0; i < BEFS_NUM_DIRECT_BLOCKS; ++i)
-                data.direct[i] = fsrun_to_cpu(sb, n.direct[i]);
+                data.direct[i] = fsrun_to_cpu(sb, n->direct[i]);
 
-        data.max_direct_range = fs64_to_cpu(sb, n.max_direct_range);
-        data.indirect = fsrun_to_cpu(sb, n.indirect);
-        data.max_indirect_range = fs64_to_cpu(sb, n.max_indirect_range);
-        data.double_indirect = fsrun_to_cpu(sb, n.double_indirect);
+        data.max_direct_range = fs64_to_cpu(sb, n->max_direct_range);
+        data.indirect = fsrun_to_cpu(sb, n->indirect);
+        data.max_indirect_range = fs64_to_cpu(sb, n->max_indirect_range);
+        data.double_indirect = fsrun_to_cpu(sb, n->double_indirect);
         data.max_double_indirect_range = fs64_to_cpu(sb,
-                                                     n.
+                                                     n->
                                                      max_double_indirect_range);
-        data.size = fs64_to_cpu(sb, n.size);
+        data.size = fs64_to_cpu(sb, n->size);
 
         return data;
 }
diff --git a/fs/befs/linuxvfs.c b/fs/befs/linuxvfs.c
index de93581b79a2..b1d0c794747b 100644
--- a/fs/befs/linuxvfs.c
+++ b/fs/befs/linuxvfs.c
@@ -390,7 +390,7 @@ static struct inode *befs_iget(struct super_block *sb, unsigned long ino)
                 int num_blks;
 
                 befs_ino->i_data.ds =
-                    fsds_to_cpu(sb, raw_inode->data.datastream);
+                    fsds_to_cpu(sb, &raw_inode->data.datastream);
 
                 num_blks = befs_count_blocks(sb, &befs_ino->i_data.ds);
                 inode->i_blocks =
diff --git a/fs/binfmt_elf.c b/fs/binfmt_elf.c
index 6884e198e0c7..d5b640ba6cb1 100644
--- a/fs/binfmt_elf.c
+++ b/fs/binfmt_elf.c
@@ -66,12 +66,11 @@ static int elf_core_dump(struct coredump_params *cprm);
 #define ELF_PAGEALIGN(_v) (((_v) + ELF_MIN_ALIGN - 1) & ~(ELF_MIN_ALIGN - 1))
 
 static struct linux_binfmt elf_format = {
-                .module         = THIS_MODULE,
-                .load_binary    = load_elf_binary,
-                .load_shlib     = load_elf_library,
-                .core_dump      = elf_core_dump,
-                .min_coredump   = ELF_EXEC_PAGESIZE,
-                .hasvdso        = 1
+        .module         = THIS_MODULE,
+        .load_binary    = load_elf_binary,
+        .load_shlib     = load_elf_library,
+        .core_dump      = elf_core_dump,
+        .min_coredump   = ELF_EXEC_PAGESIZE,
 };
 
 #define BAD_ADDR(x) ((unsigned long)(x) >= TASK_SIZE)
@@ -316,8 +315,6 @@ create_elf_tables(struct linux_binprm *bprm, struct elfhdr *exec,
         return 0;
 }
 
-#ifndef elf_map
-
 static unsigned long elf_map(struct file *filep, unsigned long addr,
                 struct elf_phdr *eppnt, int prot, int type,
                 unsigned long total_size)
@@ -354,8 +351,6 @@ static unsigned long elf_map(struct file *filep, unsigned long addr,
         return(map_addr);
 }
 
-#endif /* !elf_map */
-
 static unsigned long total_mapping_size(struct elf_phdr *cmds, int nr)
 {
         int i, first_idx = -1, last_idx = -1;
@@ -421,7 +416,7 @@ static unsigned long load_elf_interp(struct elfhdr *interp_elf_ex,
                 goto out;
 
         retval = kernel_read(interpreter, interp_elf_ex->e_phoff,
-                             (char *)elf_phdata,size);
+                             (char *)elf_phdata, size);
         error = -EIO;
         if (retval != size) {
                 if (retval < 0)
@@ -601,7 +596,7 @@ static int load_elf_binary(struct linux_binprm *bprm, struct pt_regs *regs)
                 goto out;
         if (!elf_check_arch(&loc->elf_ex))
                 goto out;
-        if (!bprm->file->f_op||!bprm->file->f_op->mmap)
+        if (!bprm->file->f_op || !bprm->file->f_op->mmap)
                 goto out;
 
         /* Now read in all of the header information */
@@ -761,8 +756,8 @@ static int load_elf_binary(struct linux_binprm *bprm, struct pt_regs *regs)
                         /* There was a PT_LOAD segment with p_memsz > p_filesz
                            before this one. Map anonymous pages, if needed,
                            and clear the area.  */
-                        retval = set_brk (elf_bss + load_bias,
-                                          elf_brk + load_bias);
+                        retval = set_brk(elf_bss + load_bias,
+                                         elf_brk + load_bias);
                         if (retval) {
                                 send_sig(SIGKILL, current, 0);
                                 goto out_free_dentry;
diff --git a/fs/bio-integrity.c b/fs/bio-integrity.c
index 4d0ff5ee27b8..e49cce234c65 100644
--- a/fs/bio-integrity.c
+++ b/fs/bio-integrity.c
@@ -782,7 +782,12 @@ void __init bio_integrity_init(void)
 {
         unsigned int i;
 
-        kintegrityd_wq = create_workqueue("kintegrityd");
+        /*
+         * kintegrityd won't block much but may burn a lot of CPU cycles.
+         * Make it highpri CPU intensive wq with max concurrency of 1.
+         */
+        kintegrityd_wq = alloc_workqueue("kintegrityd", WQ_MEM_RECLAIM |
+                                         WQ_HIGHPRI | WQ_CPU_INTENSIVE, 1);
         if (!kintegrityd_wq)
                 panic("Failed to create kintegrityd\n");
 
diff --git a/fs/block_dev.c b/fs/block_dev.c
index 771f23527010..fe3f59c14a02 100644
--- a/fs/block_dev.c
+++ b/fs/block_dev.c
@@ -432,9 +432,6 @@ static void init_once(void *foo)
         mutex_init(&bdev->bd_mutex);
         INIT_LIST_HEAD(&bdev->bd_inodes);
         INIT_LIST_HEAD(&bdev->bd_list);
-#ifdef CONFIG_SYSFS
-        INIT_LIST_HEAD(&bdev->bd_holder_list);
-#endif
         inode_init_once(&ei->vfs_inode);
         /* Initialize mutex for freeze. */
         mutex_init(&bdev->bd_fsfreeze_mutex);
@@ -473,7 +470,7 @@ static const struct super_operations bdev_sops = {
 static struct dentry *bd_mount(struct file_system_type *fs_type,
         int flags, const char *dev_name, void *data)
 {
-        return mount_pseudo(fs_type, "bdev:", &bdev_sops, 0x62646576);
+        return mount_pseudo(fs_type, "bdev:", &bdev_sops, NULL, 0x62646576);
 }
 
 static struct file_system_type bd_type = {
@@ -669,7 +666,7 @@ static bool bd_may_claim(struct block_device *bdev, struct block_device *whole,
         else if (bdev->bd_contains == bdev)
                 return true;     /* is a whole device which isn't held */
 
-        else if (whole->bd_holder == bd_claim)
+        else if (whole->bd_holder == bd_may_claim)
                 return true;     /* is a partition of a device that is being partitioned */
         else if (whole->bd_holder != NULL)
                 return false;    /* is a partition of a held device */
@@ -781,439 +778,87 @@ static struct block_device *bd_start_claiming(struct block_device *bdev,
         }
 }
 
-/* releases bdev_lock */
-static void __bd_abort_claiming(struct block_device *whole, void *holder)
-{
-        BUG_ON(whole->bd_claiming != holder);
-        whole->bd_claiming = NULL;
-        wake_up_bit(&whole->bd_claiming, 0);
-
-        spin_unlock(&bdev_lock);
-        bdput(whole);
-}
-
-/**
- * bd_abort_claiming - abort claiming a block device
- * @whole: whole block device returned by bd_start_claiming()
- * @holder: holder trying to claim @bdev
- *
- * Abort a claiming block started by bd_start_claiming().  Note that
- * @whole is not the block device to be claimed but the whole device
- * returned by bd_start_claiming().
- *
- * CONTEXT:
- * Grabs and releases bdev_lock.
- */
-static void bd_abort_claiming(struct block_device *whole, void *holder)
-{
-        spin_lock(&bdev_lock);
-        __bd_abort_claiming(whole, holder);             /* releases bdev_lock */
-}
-
-/* increment holders when we have a legitimate claim. requires bdev_lock */
-static void __bd_claim(struct block_device *bdev, struct block_device *whole,
-                                        void *holder)
-{
-        /* note that for a whole device bd_holders
-         * will be incremented twice, and bd_holder will
-         * be set to bd_claim before being set to holder
-         */
-        whole->bd_holders++;
-        whole->bd_holder = bd_claim;
-        bdev->bd_holders++;
-        bdev->bd_holder = holder;
-}
-
-/**
- * bd_finish_claiming - finish claiming a block device
- * @bdev: block device of interest (passed to bd_start_claiming())
- * @whole: whole block device returned by bd_start_claiming()
- * @holder: holder trying to claim @bdev
- *
- * Finish a claiming block started by bd_start_claiming().
- *
- * CONTEXT:
- * Grabs and releases bdev_lock.
- */
-static void bd_finish_claiming(struct block_device *bdev,
-                                struct block_device *whole, void *holder)
-{
-        spin_lock(&bdev_lock);
-        BUG_ON(!bd_may_claim(bdev, whole, holder));
-        __bd_claim(bdev, whole, holder);
-        __bd_abort_claiming(whole, holder); /* not actually an abort */
-}
-
-/**
- * bd_claim - claim a block device
- * @bdev: block device to claim
- * @holder: holder trying to claim @bdev
- *
- * Try to claim @bdev which must have been opened successfully.
- *
- * CONTEXT:
- * Might sleep.
- *
- * RETURNS:
- * 0 if successful, -EBUSY if @bdev is already claimed.
- */
-int bd_claim(struct block_device *bdev, void *holder)
-{
-        struct block_device *whole = bdev->bd_contains;
-        int res;
-
-        might_sleep();
-
-        spin_lock(&bdev_lock);
-        res = bd_prepare_to_claim(bdev, whole, holder);
-        if (res == 0)
-                __bd_claim(bdev, whole, holder);
-        spin_unlock(&bdev_lock);
-
-        return res;
-}
-EXPORT_SYMBOL(bd_claim);
-
-void bd_release(struct block_device *bdev)
-{
-        spin_lock(&bdev_lock);
-        if (!--bdev->bd_contains->bd_holders)
-                bdev->bd_contains->bd_holder = NULL;
-        if (!--bdev->bd_holders)
-                bdev->bd_holder = NULL;
-        spin_unlock(&bdev_lock);
-}
-
-EXPORT_SYMBOL(bd_release);
-
 #ifdef CONFIG_SYSFS
-/*
- * Functions for bd_claim_by_kobject / bd_release_from_kobject
- *
- *     If a kobject is passed to bd_claim_by_kobject()
- *     and the kobject has a parent directory,
- *     following symlinks are created:
- *        o from the kobject to the claimed bdev
- *        o from "holders" directory of the bdev to the parent of the kobject
- *     bd_release_from_kobject() removes these symlinks.
- *
- *     Example:
- *        If /dev/dm-0 maps to /dev/sda, kobject corresponding to
- *        /sys/block/dm-0/slaves is passed to bd_claim_by_kobject(), then:
- *           /sys/block/dm-0/slaves/sda --> /sys/block/sda
- *           /sys/block/sda/holders/dm-0 --> /sys/block/dm-0
- */
-
 static int add_symlink(struct kobject *from, struct kobject *to)
 {
-        if (!from || !to)
-                return 0;
         return sysfs_create_link(from, to, kobject_name(to));
 }
 
 static void del_symlink(struct kobject *from, struct kobject *to)
 {
-        if (!from || !to)
-                return;
         sysfs_remove_link(from, kobject_name(to));
 }
 
-/*
- * 'struct bd_holder' contains pointers to kobjects symlinked by
- * bd_claim_by_kobject.
- * It's connected to bd_holder_list which is protected by bdev->bd_sem.
- */
-struct bd_holder {
-        struct list_head list;  /* chain of holders of the bdev */
-        int count;              /* references from the holder */
-        struct kobject *sdir;   /* holder object, e.g. "/block/dm-0/slaves" */
-        struct kobject *hdev;   /* e.g. "/block/dm-0" */
-        struct kobject *hdir;   /* e.g. "/block/sda/holders" */
-        struct kobject *sdev;   /* e.g. "/block/sda" */
-};
-
-/*
- * Get references of related kobjects at once.
- * Returns 1 on success. 0 on failure.
- *
- * Should call bd_holder_release_dirs() after successful use.
- */
-static int bd_holder_grab_dirs(struct block_device *bdev,
-                        struct bd_holder *bo)
-{
-        if (!bdev || !bo)
-                return 0;
-
-        bo->sdir = kobject_get(bo->sdir);
-        if (!bo->sdir)
-                return 0;
-
-        bo->hdev = kobject_get(bo->sdir->parent);
-        if (!bo->hdev)
-                goto fail_put_sdir;
-
-        bo->sdev = kobject_get(&part_to_dev(bdev->bd_part)->kobj);
-        if (!bo->sdev)
-                goto fail_put_hdev;
-
-        bo->hdir = kobject_get(bdev->bd_part->holder_dir);
-        if (!bo->hdir)
-                goto fail_put_sdev;
-
-        return 1;
-
-fail_put_sdev:
-        kobject_put(bo->sdev);
-fail_put_hdev:
-        kobject_put(bo->hdev);
-fail_put_sdir:
-        kobject_put(bo->sdir);
-
-        return 0;
-}
-
-/* Put references of related kobjects at once. */
-static void bd_holder_release_dirs(struct bd_holder *bo)
-{
-        kobject_put(bo->hdir);
-        kobject_put(bo->sdev);
-        kobject_put(bo->hdev);
-        kobject_put(bo->sdir);
-}
-
-static struct bd_holder *alloc_bd_holder(struct kobject *kobj)
-{
-        struct bd_holder *bo;
-
-        bo = kzalloc(sizeof(*bo), GFP_KERNEL);
-        if (!bo)
-                return NULL;
-
-        bo->count = 1;
-        bo->sdir = kobj;
-
-        return bo;
-}
-
-static void free_bd_holder(struct bd_holder *bo)
-{
-        kfree(bo);
-}
-
 /**
- * find_bd_holder - find matching struct bd_holder from the block device
+ * bd_link_disk_holder - create symlinks between holding disk and slave bdev
+ * @bdev: the claimed slave bdev
+ * @disk: the holding disk
  *
- * @bdev:       struct block device to be searched
- * @bo:         target struct bd_holder
- *
- * Returns matching entry with @bo in @bdev->bd_holder_list.
- * If found, increment the reference count and return the pointer.
- * If not found, returns NULL.
- */
-static struct bd_holder *find_bd_holder(struct block_device *bdev,
-                                        struct bd_holder *bo)
-{
-        struct bd_holder *tmp;
-
-        list_for_each_entry(tmp, &bdev->bd_holder_list, list)
-                if (tmp->sdir == bo->sdir) {
-                        tmp->count++;
-                        return tmp;
-                }
-
-        return NULL;
-}
-
-/**
- * add_bd_holder - create sysfs symlinks for bd_claim() relationship
- *
- * @bdev:       block device to be bd_claimed
- * @bo:         preallocated and initialized by alloc_bd_holder()
- *
- * Add @bo to @bdev->bd_holder_list, create symlinks.
- *
- * Returns 0 if symlinks are created.
- * Returns -ve if something fails.
- */
-static int add_bd_holder(struct block_device *bdev, struct bd_holder *bo)
-{
-        int err;
-
-        if (!bo)
-                return -EINVAL;
-
-        if (!bd_holder_grab_dirs(bdev, bo))
-                return -EBUSY;
-
-        err = add_symlink(bo->sdir, bo->sdev);
-        if (err)
-                return err;
-
-        err = add_symlink(bo->hdir, bo->hdev);
-        if (err) {
-                del_symlink(bo->sdir, bo->sdev);
-                return err;
-        }
-
-        list_add_tail(&bo->list, &bdev->bd_holder_list);
-        return 0;
-}
-
-/**
- * del_bd_holder - delete sysfs symlinks for bd_claim() relationship
+ * This functions creates the following sysfs symlinks.
  *
- * @bdev:       block device to be bd_claimed
- * @kobj:       holder's kobject
+ * - from "slaves" directory of the holder @disk to the claimed @bdev
+ * - from "holders" directory of the @bdev to the holder @disk
  *
- * If there is matching entry with @kobj in @bdev->bd_holder_list
- * and no other bd_claim() from the same kobject,
- * remove the struct bd_holder from the list, delete symlinks for it.
+ * For example, if /dev/dm-0 maps to /dev/sda and disk for dm-0 is
+ * passed to bd_link_disk_holder(), then:
  *
- * Returns a pointer to the struct bd_holder when it's removed from the list
- * and ready to be freed.
- * Returns NULL if matching claim isn't found or there is other bd_claim()
- * by the same kobject.
- */
-static struct bd_holder *del_bd_holder(struct block_device *bdev,
-                                        struct kobject *kobj)
-{
-        struct bd_holder *bo;
-
-        list_for_each_entry(bo, &bdev->bd_holder_list, list) {
-                if (bo->sdir == kobj) {
-                        bo->count--;
-                        BUG_ON(bo->count < 0);
-                        if (!bo->count) {
-                                list_del(&bo->list);
-                                del_symlink(bo->sdir, bo->sdev);
-                                del_symlink(bo->hdir, bo->hdev);
-                                bd_holder_release_dirs(bo);
-                                return bo;
-                        }
-                        break;
-                }
-        }
-
-        return NULL;
-}
-
-/**
- * bd_claim_by_kobject - bd_claim() with additional kobject signature
+ *   /sys/block/dm-0/slaves/sda --> /sys/block/sda
+ *   /sys/block/sda/holders/dm-0 --> /sys/block/dm-0
  *
- * @bdev:       block device to be claimed
- * @holder:     holder's signature
- * @kobj:       holder's kobject
+ * The caller must have claimed @bdev before calling this function and
+ * ensure that both @bdev and @disk are valid during the creation and
+ * lifetime of these symlinks.
  *
- * Do bd_claim() and if it succeeds, create sysfs symlinks between
- * the bdev and the holder's kobject.
- * Use bd_release_from_kobject() when relesing the claimed bdev.
+ * CONTEXT:
+ * Might sleep.
  *
- * Returns 0 on success. (same as bd_claim())
- * Returns errno on failure.
+ * RETURNS:
+ * 0 on success, -errno on failure.
  */
-static int bd_claim_by_kobject(struct block_device *bdev, void *holder,
-                                struct kobject *kobj)
+int bd_link_disk_holder(struct block_device *bdev, struct gendisk *disk)
 {
-        int err;
-        struct bd_holder *bo, *found;
-
-        if (!kobj)
-                return -EINVAL;
-
-        bo = alloc_bd_holder(kobj);
-        if (!bo)
-                return -ENOMEM;
+        int ret = 0;
 
         mutex_lock(&bdev->bd_mutex);
 
-        err = bd_claim(bdev, holder);
-        if (err)
-                goto fail;
+        WARN_ON_ONCE(!bdev->bd_holder || bdev->bd_holder_disk);
 
-        found = find_bd_holder(bdev, bo);
-        if (found)
-                goto fail;
+        /* FIXME: remove the following once add_disk() handles errors */
+        if (WARN_ON(!disk->slave_dir || !bdev->bd_part->holder_dir))
+                goto out_unlock;
 
-        err = add_bd_holder(bdev, bo);
-        if (err)
-                bd_release(bdev);
-        else
-                bo = NULL;
-fail:
-        mutex_unlock(&bdev->bd_mutex);
-        free_bd_holder(bo);
-        return err;
-}
+        ret = add_symlink(disk->slave_dir, &part_to_dev(bdev->bd_part)->kobj);
+        if (ret)
+                goto out_unlock;
 
-/**
- * bd_release_from_kobject - bd_release() with additional kobject signature
- *
- * @bdev:       block device to be released
- * @kobj:       holder's kobject
- *
- * Do bd_release() and remove sysfs symlinks created by bd_claim_by_kobject().
- */
-static void bd_release_from_kobject(struct block_device *bdev,
-                                        struct kobject *kobj)
-{
-        if (!kobj)
-                return;
+        ret = add_symlink(bdev->bd_part->holder_dir, &disk_to_dev(disk)->kobj);
+        if (ret) {
+                del_symlink(disk->slave_dir, &part_to_dev(bdev->bd_part)->kobj);
+                goto out_unlock;
+        }
 
-        mutex_lock(&bdev->bd_mutex);
-        bd_release(bdev);
-        free_bd_holder(del_bd_holder(bdev, kobj));
+        bdev->bd_holder_disk = disk;
+out_unlock:
         mutex_unlock(&bdev->bd_mutex);
+        return ret;
 }
+EXPORT_SYMBOL_GPL(bd_link_disk_holder);
 
-/**
- * bd_claim_by_disk - wrapper function for bd_claim_by_kobject()
- *
- * @bdev:       block device to be claimed
- * @holder:     holder's signature
- * @disk:       holder's gendisk
- *
- * Call bd_claim_by_kobject() with getting @disk->slave_dir.
- */
-int bd_claim_by_disk(struct block_device *bdev, void *holder,
-                        struct gendisk *disk)
+static void bd_unlink_disk_holder(struct block_device *bdev)
 {
-        return bd_claim_by_kobject(bdev, holder, kobject_get(disk->slave_dir));
-}
-EXPORT_SYMBOL_GPL(bd_claim_by_disk);
+        struct gendisk *disk = bdev->bd_holder_disk;
 
-/**
- * bd_release_from_disk - wrapper function for bd_release_from_kobject()
- *
- * @bdev:       block device to be claimed
- * @disk:       holder's gendisk
- *
- * Call bd_release_from_kobject() and put @disk->slave_dir.
- */
-void bd_release_from_disk(struct block_device *bdev, struct gendisk *disk)
-{
-        bd_release_from_kobject(bdev, disk->slave_dir);
-        kobject_put(disk->slave_dir);
-}
-EXPORT_SYMBOL_GPL(bd_release_from_disk);
-#endif
+        bdev->bd_holder_disk = NULL;
+        if (!disk)
+                return;
 
-/*
- * Tries to open block device by device number.  Use it ONLY if you
- * really do not have anything better - i.e. when you are behind a
- * truly sucky interface and all you are given is a device number.  _Never_
- * to be used for internal purposes.  If you ever need it - reconsider
- * your API.
- */
-struct block_device *open_by_devnum(dev_t dev, fmode_t mode)
-{
-        struct block_device *bdev = bdget(dev);
-        int err = -ENOMEM;
-        if (bdev)
-                err = blkdev_get(bdev, mode);
-        return err ? ERR_PTR(err) : bdev;
+        del_symlink(disk->slave_dir, &part_to_dev(bdev->bd_part)->kobj);
+        del_symlink(bdev->bd_part->holder_dir, &disk_to_dev(disk)->kobj);
 }
-
-EXPORT_SYMBOL(open_by_devnum);
+#else
+static inline void bd_unlink_disk_holder(struct block_device *bdev)
+{ }
+#endif
 
 /**
  * flush_disk - invalidates all buffer-cache entries on a disk
@@ -1309,10 +954,11 @@ int check_disk_change(struct block_device *bdev)
 {
         struct gendisk *disk = bdev->bd_disk;
         const struct block_device_operations *bdops = disk->fops;
+        unsigned int events;
 
-        if (!bdops->media_changed)
-                return 0;
-        if (!bdops->media_changed(bdev->bd_disk))
+        events = disk_clear_events(disk, DISK_EVENT_MEDIA_CHANGE |
+                                   DISK_EVENT_EJECT_REQUEST);
+        if (!(events & DISK_EVENT_MEDIA_CHANGE))
                 return 0;
 
         flush_disk(bdev);
@@ -1475,17 +1121,171 @@ static int __blkdev_get(struct block_device *bdev, fmode_t mode, int for_part)
         return ret;
 }
 
-int blkdev_get(struct block_device *bdev, fmode_t mode)
+/**
+ * blkdev_get - open a block device
+ * @bdev: block_device to open
+ * @mode: FMODE_* mask
+ * @holder: exclusive holder identifier
+ *
+ * Open @bdev with @mode.  If @mode includes %FMODE_EXCL, @bdev is
+ * open with exclusive access.  Specifying %FMODE_EXCL with %NULL
+ * @holder is invalid.  Exclusive opens may nest for the same @holder.
+ *
+ * On success, the reference count of @bdev is unchanged.  On failure,
+ * @bdev is put.
+ *
+ * CONTEXT:
+ * Might sleep.
+ *
+ * RETURNS:
+ * 0 on success, -errno on failure.
+ */
+int blkdev_get(struct block_device *bdev, fmode_t mode, void *holder)
 {
-        return __blkdev_get(bdev, mode, 0);
+        struct block_device *whole = NULL;
+        int res;
+
+        WARN_ON_ONCE((mode & FMODE_EXCL) && !holder);
+
+        if ((mode & FMODE_EXCL) && holder) {
+                whole = bd_start_claiming(bdev, holder);
+                if (IS_ERR(whole)) {
+                        bdput(bdev);
+                        return PTR_ERR(whole);
+                }
+        }
+
+        res = __blkdev_get(bdev, mode, 0);
+
+        /* __blkdev_get() may alter read only status, check it afterwards */
+        if (!res && (mode & FMODE_WRITE) && bdev_read_only(bdev)) {
+                __blkdev_put(bdev, mode, 0);
+                res = -EACCES;
+        }
+
+        if (whole) {
+                /* finish claiming */
+                mutex_lock(&bdev->bd_mutex);
+                spin_lock(&bdev_lock);
+
+                if (!res) {
+                        BUG_ON(!bd_may_claim(bdev, whole, holder));
+                        /*
+                         * Note that for a whole device bd_holders
+                         * will be incremented twice, and bd_holder
+                         * will be set to bd_may_claim before being
+                         * set to holder
+                         */
+                        whole->bd_holders++;
+                        whole->bd_holder = bd_may_claim;
+                        bdev->bd_holders++;
+                        bdev->bd_holder = holder;
+                }
+
+                /* tell others that we're done */
+                BUG_ON(whole->bd_claiming != holder);
+                whole->bd_claiming = NULL;
+                wake_up_bit(&whole->bd_claiming, 0);
+
+                spin_unlock(&bdev_lock);
+
+                /*
+                 * Block event polling for write claims.  Any write
+                 * holder makes the write_holder state stick until all
+                 * are released.  This is good enough and tracking
+                 * individual writeable reference is too fragile given
+                 * the way @mode is used in blkdev_get/put().
+                 */
+                if (!res && (mode & FMODE_WRITE) && !bdev->bd_write_holder) {
+                        bdev->bd_write_holder = true;
+                        disk_block_events(bdev->bd_disk);
+                }
+
+                mutex_unlock(&bdev->bd_mutex);
+                bdput(whole);
+        }
+
+        return res;
 }
 EXPORT_SYMBOL(blkdev_get);
 
+/**
+ * blkdev_get_by_path - open a block device by name
+ * @path: path to the block device to open
+ * @mode: FMODE_* mask
+ * @holder: exclusive holder identifier
+ *
+ * Open the blockdevice described by the device file at @path.  @mode
+ * and @holder are identical to blkdev_get().
+ *
+ * On success, the returned block_device has reference count of one.
+ *
+ * CONTEXT:
+ * Might sleep.
+ *
+ * RETURNS:
+ * Pointer to block_device on success, ERR_PTR(-errno) on failure.
+ */
+struct block_device *blkdev_get_by_path(const char *path, fmode_t mode,
+                                        void *holder)
+{
+        struct block_device *bdev;
+        int err;
+
+        bdev = lookup_bdev(path);
+        if (IS_ERR(bdev))
+                return bdev;
+
+        err = blkdev_get(bdev, mode, holder);
+        if (err)
+                return ERR_PTR(err);
+
+        return bdev;
+}
+EXPORT_SYMBOL(blkdev_get_by_path);
+
+/**
+ * blkdev_get_by_dev - open a block device by device number
+ * @dev: device number of block device to open
+ * @mode: FMODE_* mask
+ * @holder: exclusive holder identifier
+ *
+ * Open the blockdevice described by device number @dev.  @mode and
+ * @holder are identical to blkdev_get().
+ *
+ * Use it ONLY if you really do not have anything better - i.e. when
+ * you are behind a truly sucky interface and all you are given is a
+ * device number.  _Never_ to be used for internal purposes.  If you
+ * ever need it - reconsider your API.
+ *
+ * On success, the returned block_device has reference count of one.
+ *
+ * CONTEXT:
+ * Might sleep.
+ *
+ * RETURNS:
+ * Pointer to block_device on success, ERR_PTR(-errno) on failure.
+ */
+struct block_device *blkdev_get_by_dev(dev_t dev, fmode_t mode, void *holder)
+{
+        struct block_device *bdev;
+        int err;
+
+        bdev = bdget(dev);
+        if (!bdev)
+                return ERR_PTR(-ENOMEM);
+
+        err = blkdev_get(bdev, mode, holder);
+        if (err)
+                return ERR_PTR(err);
+
+        return bdev;
+}
+EXPORT_SYMBOL(blkdev_get_by_dev);
+
 static int blkdev_open(struct inode * inode, struct file * filp)
 {
-        struct block_device *whole = NULL;
         struct block_device *bdev;
-        int res;
 
         /*
          * Preserve backwards compatibility and allow large file access
@@ -1506,26 +1306,9 @@ static int blkdev_open(struct inode * inode, struct file * filp)
         if (bdev == NULL)
                 return -ENOMEM;
 
-        if (filp->f_mode & FMODE_EXCL) {
-                whole = bd_start_claiming(bdev, filp);
-                if (IS_ERR(whole)) {
-                        bdput(bdev);
-                        return PTR_ERR(whole);
-                }
-        }
-
         filp->f_mapping = bdev->bd_inode->i_mapping;
 
-        res = blkdev_get(bdev, filp->f_mode);
-
-        if (whole) {
-                if (res == 0)
-                        bd_finish_claiming(bdev, whole, filp);
-                else
-                        bd_abort_claiming(whole, filp);
-        }
-
-        return res;
+        return blkdev_get(bdev, filp->f_mode, filp);
 }
 
 static int __blkdev_put(struct block_device *bdev, fmode_t mode, int for_part)
@@ -1539,6 +1322,7 @@ static int __blkdev_put(struct block_device *bdev, fmode_t mode, int for_part)
                 bdev->bd_part_count--;
 
         if (!--bdev->bd_openers) {
+                WARN_ON_ONCE(bdev->bd_holders);
                 sync_blockdev(bdev);
                 kill_bdev(bdev);
         }
@@ -1569,6 +1353,45 @@ static int __blkdev_put(struct block_device *bdev, fmode_t mode, int for_part)
 
 int blkdev_put(struct block_device *bdev, fmode_t mode)
 {
+        if (mode & FMODE_EXCL) {
+                bool bdev_free;
+
+                /*
+                 * Release a claim on the device.  The holder fields
+                 * are protected with bdev_lock.  bd_mutex is to
+                 * synchronize disk_holder unlinking.
+                 */
+                mutex_lock(&bdev->bd_mutex);
+                spin_lock(&bdev_lock);
+
+                WARN_ON_ONCE(--bdev->bd_holders < 0);
+                WARN_ON_ONCE(--bdev->bd_contains->bd_holders < 0);
+
+                /* bd_contains might point to self, check in a separate step */
+                if ((bdev_free = !bdev->bd_holders))
+                        bdev->bd_holder = NULL;
+                if (!bdev->bd_contains->bd_holders)
+                        bdev->bd_contains->bd_holder = NULL;
+
+                spin_unlock(&bdev_lock);
+
+                /*
+                 * If this was the last claim, remove holder link and
+                 * unblock evpoll if it was a write holder.
+                 */
+                if (bdev_free) {
+                        bd_unlink_disk_holder(bdev);
+                        if (bdev->bd_write_holder) {
+                                disk_unblock_events(bdev->bd_disk);
+                                bdev->bd_write_holder = false;
+                        } else
+                                disk_check_events(bdev->bd_disk);
+                }
+
+                mutex_unlock(&bdev->bd_mutex);
+        } else
+                disk_check_events(bdev->bd_disk);
+
         return __blkdev_put(bdev, mode, 0);
 }
 EXPORT_SYMBOL(blkdev_put);
@@ -1576,8 +1399,7 @@ EXPORT_SYMBOL(blkdev_put);
 static int blkdev_close(struct inode * inode, struct file * filp)
 {
         struct block_device *bdev = I_BDEV(filp->f_mapping->host);
-        if (bdev->bd_holder == filp)
-                bd_release(bdev);
+
         return blkdev_put(bdev, filp->f_mode);
 }
 
@@ -1722,67 +1544,6 @@ fail:
 }
 EXPORT_SYMBOL(lookup_bdev);
 
-/**
- * open_bdev_exclusive  -  open a block device by name and set it up for use
- *
- * @path:       special file representing the block device
- * @mode:       FMODE_... combination to pass be used
- * @holder:     owner for exclusion
- *
- * Open the blockdevice described by the special file at @path, claim it
- * for the @holder.
- */
-struct block_device *open_bdev_exclusive(const char *path, fmode_t mode, void *holder)
-{
-        struct block_device *bdev, *whole;
-        int error;
-
-        bdev = lookup_bdev(path);
-        if (IS_ERR(bdev))
-                return bdev;
-
-        whole = bd_start_claiming(bdev, holder);
-        if (IS_ERR(whole)) {
-                bdput(bdev);
-                return whole;
-        }
-
-        error = blkdev_get(bdev, mode);
-        if (error)
-                goto out_abort_claiming;
-
-        error = -EACCES;
-        if ((mode & FMODE_WRITE) && bdev_read_only(bdev))
-                goto out_blkdev_put;
-
-        bd_finish_claiming(bdev, whole, holder);
-        return bdev;
-
-out_blkdev_put:
-        blkdev_put(bdev, mode);
-out_abort_claiming:
-        bd_abort_claiming(whole, holder);
-        return ERR_PTR(error);
-}
-
-EXPORT_SYMBOL(open_bdev_exclusive);
-
-/**
- * close_bdev_exclusive  -  close a blockdevice opened by open_bdev_exclusive()
- *
- * @bdev:       blockdevice to close
- * @mode:       mode, must match that used to open.
- *
- * This is the counterpart to open_bdev_exclusive().
- */
-void close_bdev_exclusive(struct block_device *bdev, fmode_t mode)
-{
-        bd_release(bdev);
-        blkdev_put(bdev, mode);
-}
-
-EXPORT_SYMBOL(close_bdev_exclusive);
-
 int __invalidate_device(struct block_device *bdev)
 {
         struct super_block *sb = get_super(bdev);
diff --git a/fs/btrfs/export.c b/fs/btrfs/export.c
index 0ccf9a8afcdf..9786963b07e5 100644
--- a/fs/btrfs/export.c
+++ b/fs/btrfs/export.c
@@ -65,7 +65,6 @@ static struct dentry *btrfs_get_dentry(struct super_block *sb, u64 objectid,
 {
         struct btrfs_fs_info *fs_info = btrfs_sb(sb)->fs_info;
         struct btrfs_root *root;
-        struct dentry *dentry;
         struct inode *inode;
         struct btrfs_key key;
         int index;
@@ -108,10 +107,7 @@ static struct dentry *btrfs_get_dentry(struct super_block *sb, u64 objectid,
                 return ERR_PTR(-ESTALE);
         }
 
-        dentry = d_obtain_alias(inode);
-        if (!IS_ERR(dentry))
-                d_set_d_op(dentry, &btrfs_dentry_operations);
-        return dentry;
+        return d_obtain_alias(inode);
 fail:
         srcu_read_unlock(&fs_info->subvol_srcu, index);
         return ERR_PTR(err);
@@ -166,7 +162,6 @@ static struct dentry *btrfs_fh_to_dentry(struct super_block *sb, struct fid *fh,
 static struct dentry *btrfs_get_parent(struct dentry *child)
 {
         struct inode *dir = child->d_inode;
-        struct dentry *dentry;
         struct btrfs_root *root = BTRFS_I(dir)->root;
         struct btrfs_path *path;
         struct extent_buffer *leaf;
@@ -223,10 +218,7 @@ static struct dentry *btrfs_get_parent(struct dentry *child)
 
         key.type = BTRFS_INODE_ITEM_KEY;
         key.offset = 0;
-        dentry = d_obtain_alias(btrfs_iget(root->fs_info->sb, &key, root, NULL));
-        if (!IS_ERR(dentry))
-                d_set_d_op(dentry, &btrfs_dentry_operations);
-        return dentry;
+        return d_obtain_alias(btrfs_iget(root->fs_info->sb, &key, root, NULL));
 fail:
         btrfs_free_path(path);
         return ERR_PTR(ret);
diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index a0ff46a47895..a3798a3aa0d2 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -4084,8 +4084,6 @@ struct inode *btrfs_lookup_dentry(struct inode *dir, struct dentry *dentry)
         int index;
         int ret;
 
-        d_set_d_op(dentry, &btrfs_dentry_operations);
-
         if (dentry->d_name.len > BTRFS_NAME_LEN)
                 return ERR_PTR(-ENAMETOOLONG);
 
@@ -7117,6 +7115,10 @@ static long btrfs_fallocate(struct inode *inode, int mode,
         alloc_start = offset & ~mask;
         alloc_end =  (offset + len + mask) & ~mask;
 
+        /* We only support the FALLOC_FL_KEEP_SIZE mode */
+        if (mode && (mode != FALLOC_FL_KEEP_SIZE))
+                return -EOPNOTSUPP;
+
         /*
          * wait for ordered IO before we have any locks.  We'll loop again
          * below with the locks held.
diff --git a/fs/btrfs/super.c b/fs/btrfs/super.c
index 883c6fa1367e..22acdaa78ce1 100644
--- a/fs/btrfs/super.c
+++ b/fs/btrfs/super.c
@@ -460,6 +460,7 @@ static int btrfs_fill_super(struct super_block *sb,
         sb->s_maxbytes = MAX_LFS_FILESIZE;
         sb->s_magic = BTRFS_SUPER_MAGIC;
         sb->s_op = &btrfs_super_ops;
+        sb->s_d_op = &btrfs_dentry_operations;
         sb->s_export_op = &btrfs_export_ops;
         sb->s_xattr = btrfs_xattr_handlers;
         sb->s_time_gran = 1;
diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c
index 6b9884507837..1718e1a5c320 100644
--- a/fs/btrfs/volumes.c
+++ b/fs/btrfs/volumes.c
@@ -493,7 +493,7 @@ again:
                         continue;
 
                 if (device->bdev) {
-                        close_bdev_exclusive(device->bdev, device->mode);
+                        blkdev_put(device->bdev, device->mode);
                         device->bdev = NULL;
                         fs_devices->open_devices--;
                 }
@@ -527,7 +527,7 @@ static int __btrfs_close_devices(struct btrfs_fs_devices *fs_devices)
 
         list_for_each_entry(device, &fs_devices->devices, dev_list) {
                 if (device->bdev) {
-                        close_bdev_exclusive(device->bdev, device->mode);
+                        blkdev_put(device->bdev, device->mode);
                         fs_devices->open_devices--;
                 }
                 if (device->writeable) {
@@ -584,13 +584,15 @@ static int __btrfs_open_devices(struct btrfs_fs_devices *fs_devices,
         int seeding = 1;
         int ret = 0;
 
+        flags |= FMODE_EXCL;
+
         list_for_each_entry(device, head, dev_list) {
                 if (device->bdev)
                         continue;
                 if (!device->name)
                         continue;
 
-                bdev = open_bdev_exclusive(device->name, flags, holder);
+                bdev = blkdev_get_by_path(device->name, flags, holder);
                 if (IS_ERR(bdev)) {
                         printk(KERN_INFO "open %s failed\n", device->name);
                         goto error;
@@ -642,7 +644,7 @@ static int __btrfs_open_devices(struct btrfs_fs_devices *fs_devices,
 error_brelse:
                 brelse(bh);
 error_close:
-                close_bdev_exclusive(bdev, FMODE_READ);
+                blkdev_put(bdev, flags);
 error:
                 continue;
         }
@@ -688,7 +690,8 @@ int btrfs_scan_one_device(const char *path, fmode_t flags, void *holder,
 
         mutex_lock(&uuid_mutex);
 
-        bdev = open_bdev_exclusive(path, flags, holder);
+        flags |= FMODE_EXCL;
+        bdev = blkdev_get_by_path(path, flags, holder);
 
         if (IS_ERR(bdev)) {
                 ret = PTR_ERR(bdev);
@@ -720,7 +723,7 @@ int btrfs_scan_one_device(const char *path, fmode_t flags, void *holder,
 
         brelse(bh);
 error_close:
-        close_bdev_exclusive(bdev, flags);
+        blkdev_put(bdev, flags);
 error:
         mutex_unlock(&uuid_mutex);
         return ret;
@@ -1183,8 +1186,8 @@ int btrfs_rm_device(struct btrfs_root *root, char *device_path)
                         goto out;
                 }
         } else {
-                bdev = open_bdev_exclusive(device_path, FMODE_READ,
-                                      root->fs_info->bdev_holder);
+                bdev = blkdev_get_by_path(device_path, FMODE_READ | FMODE_EXCL,
+                                          root->fs_info->bdev_holder);
                 if (IS_ERR(bdev)) {
                         ret = PTR_ERR(bdev);
                         goto out;
@@ -1251,7 +1254,7 @@ int btrfs_rm_device(struct btrfs_root *root, char *device_path)
                 root->fs_info->fs_devices->latest_bdev = next_device->bdev;
 
         if (device->bdev) {
-                close_bdev_exclusive(device->bdev, device->mode);
+                blkdev_put(device->bdev, device->mode);
                 device->bdev = NULL;
                 device->fs_devices->open_devices--;
         }
@@ -1294,7 +1297,7 @@ error_brelse:
         brelse(bh);
 error_close:
         if (bdev)
-                close_bdev_exclusive(bdev, FMODE_READ);
+                blkdev_put(bdev, FMODE_READ | FMODE_EXCL);
 out:
         mutex_unlock(&root->fs_info->volume_mutex);
         mutex_unlock(&uuid_mutex);
@@ -1446,7 +1449,8 @@ int btrfs_init_new_device(struct btrfs_root *root, char *device_path)
         if ((sb->s_flags & MS_RDONLY) && !root->fs_info->fs_devices->seeding)
                 return -EINVAL;
 
-        bdev = open_bdev_exclusive(device_path, 0, root->fs_info->bdev_holder);
+        bdev = blkdev_get_by_path(device_path, FMODE_EXCL,
+                                  root->fs_info->bdev_holder);
         if (IS_ERR(bdev))
                 return PTR_ERR(bdev);
 
@@ -1572,7 +1576,7 @@ out:
         mutex_unlock(&root->fs_info->volume_mutex);
         return ret;
 error:
-        close_bdev_exclusive(bdev, 0);
+        blkdev_put(bdev, FMODE_EXCL);
         if (seeding_dev) {
                 mutex_unlock(&uuid_mutex);
                 up_write(&sb->s_umount);
diff --git a/fs/btrfs/volumes.h b/fs/btrfs/volumes.h
index 2740db49eb04..1be781079450 100644
--- a/fs/btrfs/volumes.h
+++ b/fs/btrfs/volumes.h
@@ -50,7 +50,7 @@ struct btrfs_device {
 
         struct block_device *bdev;
 
-        /* the mode sent to open_bdev_exclusive */
+        /* the mode sent to blkdev_get */
         fmode_t mode;
 
         char *name;
diff --git a/fs/ceph/Makefile b/fs/ceph/Makefile
index 9e6c4f2e8ff1..bd352125e829 100644
--- a/fs/ceph/Makefile
+++ b/fs/ceph/Makefile
@@ -2,31 +2,10 @@
 # Makefile for CEPH filesystem.
 #
 
-ifneq ($(KERNELRELEASE),)
-
 obj-$(CONFIG_CEPH_FS) += ceph.o
 
-ceph-objs := super.o inode.o dir.o file.o locks.o addr.o ioctl.o \
+ceph-y := super.o inode.o dir.o file.o locks.o addr.o ioctl.o \
         export.o caps.o snap.o xattr.o \
         mds_client.o mdsmap.o strings.o ceph_frag.o \
         debugfs.o
 
-else
-#Otherwise we were called directly from the command
-# line; invoke the kernel build system.
-
-KERNELDIR ?= /lib/modules/$(shell uname -r)/build
-PWD := $(shell pwd)
-
-default: all
-
-all:
-        $(MAKE) -C $(KERNELDIR) M=$(PWD) CONFIG_CEPH_FS=m modules
-
-modules_install:
-        $(MAKE) -C $(KERNELDIR) M=$(PWD) CONFIG_CEPH_FS=m modules_install
-
-clean:
-        $(MAKE) -C $(KERNELDIR) M=$(PWD) clean
-
-endif
diff --git a/fs/ceph/debugfs.c b/fs/ceph/debugfs.c
index 7ae1b3d55b58..08f65faac112 100644
--- a/fs/ceph/debugfs.c
+++ b/fs/ceph/debugfs.c
@@ -60,10 +60,13 @@ static int mdsc_show(struct seq_file *s, void *p)
         for (rp = rb_first(&mdsc->request_tree); rp; rp = rb_next(rp)) {
                 req = rb_entry(rp, struct ceph_mds_request, r_node);
 
-                if (req->r_request)
-                        seq_printf(s, "%lld\tmds%d\t", req->r_tid, req->r_mds);
-                else
+                if (req->r_request && req->r_session)
+                        seq_printf(s, "%lld\tmds%d\t", req->r_tid,
+                                   req->r_session->s_mds);
+                else if (!req->r_request)
                         seq_printf(s, "%lld\t(no request)\t", req->r_tid);
+                else
+                        seq_printf(s, "%lld\t(no session)\t", req->r_tid);
 
                 seq_printf(s, "%s", ceph_mds_op_name(req->r_op));
 
diff --git a/fs/ceph/dir.c b/fs/ceph/dir.c
index fa7ca04ee816..0bc68de8edd7 100644
--- a/fs/ceph/dir.c
+++ b/fs/ceph/dir.c
@@ -1224,6 +1224,26 @@ void ceph_dentry_lru_del(struct dentry *dn)
         }
 }
 
+/*
+ * Return name hash for a given dentry.  This is dependent on
+ * the parent directory's hash function.
+ */
+unsigned ceph_dentry_hash(struct dentry *dn)
+{
+        struct inode *dir = dn->d_parent->d_inode;
+        struct ceph_inode_info *dci = ceph_inode(dir);
+
+        switch (dci->i_dir_layout.dl_dir_hash) {
+        case 0: /* for backward compat */
+        case CEPH_STR_HASH_LINUX:
+                return dn->d_name.hash;
+
+        default:
+                return ceph_str_hash(dci->i_dir_layout.dl_dir_hash,
+                                     dn->d_name.name, dn->d_name.len);
+        }
+}
+
 const struct file_operations ceph_dir_fops = {
         .read = ceph_read_dir,
         .readdir = ceph_readdir,
diff --git a/fs/ceph/export.c b/fs/ceph/export.c
index 2297d9426992..e41056174bf8 100644
--- a/fs/ceph/export.c
+++ b/fs/ceph/export.c
@@ -59,7 +59,7 @@ static int ceph_encode_fh(struct dentry *dentry, u32 *rawfh, int *max_len,
                 dout("encode_fh %p connectable\n", dentry);
                 cfh->ino = ceph_ino(dentry->d_inode);
                 cfh->parent_ino = ceph_ino(parent->d_inode);
-                cfh->parent_name_hash = parent->d_name.hash;
+                cfh->parent_name_hash = ceph_dentry_hash(parent);
                 *max_len = connected_handle_length;
                 type = 2;
         } else if (*max_len >= handle_length) {
diff --git a/fs/ceph/inode.c b/fs/ceph/inode.c
index e61de4f7b99d..e835eff551e3 100644
--- a/fs/ceph/inode.c
+++ b/fs/ceph/inode.c
@@ -297,6 +297,8 @@ struct inode *ceph_alloc_inode(struct super_block *sb)
         ci->i_release_count = 0;
         ci->i_symlink = NULL;
 
+        memset(&ci->i_dir_layout, 0, sizeof(ci->i_dir_layout));
+
         ci->i_fragtree = RB_ROOT;
         mutex_init(&ci->i_fragtree_mutex);
 
@@ -689,6 +691,8 @@ static int fill_inode(struct inode *inode,
                 inode->i_op = &ceph_dir_iops;
                 inode->i_fop = &ceph_dir_fops;
 
+                ci->i_dir_layout = iinfo->dir_layout;
+
                 ci->i_files = le64_to_cpu(info->files);
                 ci->i_subdirs = le64_to_cpu(info->subdirs);
                 ci->i_rbytes = le64_to_cpu(info->rbytes);
diff --git a/fs/ceph/mds_client.c b/fs/ceph/mds_client.c
index a50fca1e03be..1e30d194a8e3 100644
--- a/fs/ceph/mds_client.c
+++ b/fs/ceph/mds_client.c
@@ -60,7 +60,8 @@ static const struct ceph_connection_operations mds_con_ops;
  * parse individual inode info
  */
 static int parse_reply_info_in(void **p, void *end,
-                               struct ceph_mds_reply_info_in *info)
+                               struct ceph_mds_reply_info_in *info,
+                               int features)
 {
         int err = -EIO;
 
@@ -74,6 +75,12 @@ static int parse_reply_info_in(void **p, void *end,
         info->symlink = *p;
         *p += info->symlink_len;
 
+        if (features & CEPH_FEATURE_DIRLAYOUTHASH)
+                ceph_decode_copy_safe(p, end, &info->dir_layout,
+                                      sizeof(info->dir_layout), bad);
+        else
+                memset(&info->dir_layout, 0, sizeof(info->dir_layout));
+
         ceph_decode_32_safe(p, end, info->xattr_len, bad);
         ceph_decode_need(p, end, info->xattr_len, bad);
         info->xattr_data = *p;
@@ -88,12 +95,13 @@ bad:
  * target inode.
  */
 static int parse_reply_info_trace(void **p, void *end,
-                                  struct ceph_mds_reply_info_parsed *info)
+                                  struct ceph_mds_reply_info_parsed *info,
+                                  int features)
 {
         int err;
 
         if (info->head->is_dentry) {
-                err = parse_reply_info_in(p, end, &info->diri);
+                err = parse_reply_info_in(p, end, &info->diri, features);
                 if (err < 0)
                         goto out_bad;
 
@@ -114,7 +122,7 @@ static int parse_reply_info_trace(void **p, void *end,
         }
 
         if (info->head->is_target) {
-                err = parse_reply_info_in(p, end, &info->targeti);
+                err = parse_reply_info_in(p, end, &info->targeti, features);
                 if (err < 0)
                         goto out_bad;
         }
@@ -134,7 +142,8 @@ out_bad:
  * parse readdir results
  */
 static int parse_reply_info_dir(void **p, void *end,
-                                struct ceph_mds_reply_info_parsed *info)
+                                struct ceph_mds_reply_info_parsed *info,
+                                int features)
 {
         u32 num, i = 0;
         int err;
@@ -182,7 +191,7 @@ static int parse_reply_info_dir(void **p, void *end,
                 *p += sizeof(struct ceph_mds_reply_lease);
 
                 /* inode */
-                err = parse_reply_info_in(p, end, &info->dir_in[i]);
+                err = parse_reply_info_in(p, end, &info->dir_in[i], features);
                 if (err < 0)
                         goto out_bad;
                 i++;
@@ -205,7 +214,8 @@ out_bad:
  * parse fcntl F_GETLK results
  */
 static int parse_reply_info_filelock(void **p, void *end,
-                struct ceph_mds_reply_info_parsed *info)
+                                     struct ceph_mds_reply_info_parsed *info,
+                                     int features)
 {
         if (*p + sizeof(*info->filelock_reply) > end)
                 goto bad;
@@ -225,19 +235,21 @@ bad:
  * parse extra results
  */
 static int parse_reply_info_extra(void **p, void *end,
-                struct ceph_mds_reply_info_parsed *info)
+                                  struct ceph_mds_reply_info_parsed *info,
+                                  int features)
 {
         if (info->head->op == CEPH_MDS_OP_GETFILELOCK)
-                return parse_reply_info_filelock(p, end, info);
+                return parse_reply_info_filelock(p, end, info, features);
         else
-                return parse_reply_info_dir(p, end, info);
+                return parse_reply_info_dir(p, end, info, features);
 }
 
 /*
  * parse entire mds reply
  */
 static int parse_reply_info(struct ceph_msg *msg,
-                            struct ceph_mds_reply_info_parsed *info)
+                            struct ceph_mds_reply_info_parsed *info,
+                            int features)
 {
         void *p, *end;
         u32 len;
@@ -250,7 +262,7 @@ static int parse_reply_info(struct ceph_msg *msg,
         /* trace */
         ceph_decode_32_safe(&p, end, len, bad);
         if (len > 0) {
-                err = parse_reply_info_trace(&p, p+len, info);
+                err = parse_reply_info_trace(&p, p+len, info, features);
                 if (err < 0)
                         goto out_bad;
         }
@@ -258,7 +270,7 @@ static int parse_reply_info(struct ceph_msg *msg,
         /* extra */
         ceph_decode_32_safe(&p, end, len, bad);
         if (len > 0) {
-                err = parse_reply_info_extra(&p, p+len, info);
+                err = parse_reply_info_extra(&p, p+len, info, features);
                 if (err < 0)
                         goto out_bad;
         }
@@ -654,7 +666,7 @@ static int __choose_mds(struct ceph_mds_client *mdsc,
                 } else {
                         /* dir + name */
                         inode = dir;
-                        hash = req->r_dentry->d_name.hash;
+                        hash = ceph_dentry_hash(req->r_dentry);
                         is_hash = true;
                 }
         }
@@ -1693,7 +1705,6 @@ static int __prepare_send_request(struct ceph_mds_client *mdsc,
         struct ceph_msg *msg;
         int flags = 0;
 
-        req->r_mds = mds;
         req->r_attempts++;
         if (req->r_inode) {
                 struct ceph_cap *cap =
@@ -1780,6 +1791,8 @@ static int __do_request(struct ceph_mds_client *mdsc,
                 goto finish;
         }
 
+        put_request_session(req);
+
         mds = __choose_mds(mdsc, req);
         if (mds < 0 ||
             ceph_mdsmap_get_state(mdsc->mdsmap, mds) < CEPH_MDS_STATE_ACTIVE) {
@@ -1797,6 +1810,8 @@ static int __do_request(struct ceph_mds_client *mdsc,
                         goto finish;
                 }
         }
+        req->r_session = get_session(session);
+
         dout("do_request mds%d session %p state %s\n", mds, session,
              session_state_name(session->s_state));
         if (session->s_state != CEPH_MDS_SESSION_OPEN &&
@@ -1809,7 +1824,6 @@ static int __do_request(struct ceph_mds_client *mdsc,
         }
 
         /* send request */
-        req->r_session = get_session(session);
         req->r_resend_mds = -1;   /* forget any previous mds hint */
 
         if (req->r_request_started == 0)   /* note request start time */
@@ -1863,7 +1877,6 @@ static void kick_requests(struct ceph_mds_client *mdsc, int mds)
                 if (req->r_session &&
                     req->r_session->s_mds == mds) {
                         dout(" kicking tid %llu\n", req->r_tid);
-                        put_request_session(req);
                         __do_request(mdsc, req);
                 }
         }
@@ -2056,8 +2069,11 @@ static void handle_reply(struct ceph_mds_session *session, struct ceph_msg *msg)
                         goto out;
                 } else  {
                         struct ceph_inode_info *ci = ceph_inode(req->r_inode);
-                        struct ceph_cap *cap =
-                                ceph_get_cap_for_mds(ci, req->r_mds);;
+                        struct ceph_cap *cap = NULL;
+
+                        if (req->r_session)
+                                cap = ceph_get_cap_for_mds(ci,
+                                                   req->r_session->s_mds);
 
                         dout("already using auth");
                         if ((!cap || cap != ci->i_auth_cap) ||
@@ -2101,7 +2117,7 @@ static void handle_reply(struct ceph_mds_session *session, struct ceph_msg *msg)
 
         dout("handle_reply tid %lld result %d\n", tid, result);
         rinfo = &req->r_reply_info;
-        err = parse_reply_info(msg, rinfo);
+        err = parse_reply_info(msg, rinfo, session->s_con.peer_features);
         mutex_unlock(&mdsc->mutex);
 
         mutex_lock(&session->s_mutex);
diff --git a/fs/ceph/mds_client.h b/fs/ceph/mds_client.h
index aabe563b54db..4e3a9cc0bba6 100644
--- a/fs/ceph/mds_client.h
+++ b/fs/ceph/mds_client.h
@@ -35,6 +35,7 @@ struct ceph_cap;
  */
 struct ceph_mds_reply_info_in {
         struct ceph_mds_reply_inode *in;
+        struct ceph_dir_layout dir_layout;
         u32 symlink_len;
         char *symlink;
         u32 xattr_len;
@@ -165,7 +166,6 @@ struct ceph_mds_request {
         struct ceph_mds_client *r_mdsc;
 
         int r_op;                    /* mds op code */
-        int r_mds;
 
         /* operation on what? */
         struct inode *r_inode;              /* arg1 */
diff --git a/fs/ceph/super.c b/fs/ceph/super.c
index 08b460ae0539..bf6f0f34082a 100644
--- a/fs/ceph/super.c
+++ b/fs/ceph/super.c
@@ -428,7 +428,8 @@ struct ceph_fs_client *create_fs_client(struct ceph_mount_options *fsopt,
                 goto fail;
         }
         fsc->client->extra_mon_dispatch = extra_mon_dispatch;
-        fsc->client->supported_features |= CEPH_FEATURE_FLOCK;
+        fsc->client->supported_features |= CEPH_FEATURE_FLOCK |
+                CEPH_FEATURE_DIRLAYOUTHASH;
         fsc->client->monc.want_mdsmap = 1;
 
         fsc->mount_options = fsopt;
@@ -443,13 +444,17 @@ struct ceph_fs_client *create_fs_client(struct ceph_mount_options *fsopt,
                 goto fail_client;
 
         err = -ENOMEM;
-        fsc->wb_wq = create_workqueue("ceph-writeback");
+        /*
+         * The number of concurrent works can be high but they don't need
+         * to be processed in parallel, limit concurrency.
+         */
+        fsc->wb_wq = alloc_workqueue("ceph-writeback", 0, 1);
         if (fsc->wb_wq == NULL)
                 goto fail_bdi;
-        fsc->pg_inv_wq = create_singlethread_workqueue("ceph-pg-invalid");
+        fsc->pg_inv_wq = alloc_workqueue("ceph-pg-invalid", 0, 1);
         if (fsc->pg_inv_wq == NULL)
                 goto fail_wb_wq;
-        fsc->trunc_wq = create_singlethread_workqueue("ceph-trunc");
+        fsc->trunc_wq = alloc_workqueue("ceph-trunc", 0, 1);
         if (fsc->trunc_wq == NULL)
                 goto fail_pg_inv_wq;
 
diff --git a/fs/ceph/super.h b/fs/ceph/super.h
index 4553d8829edb..20b907d76ae2 100644
--- a/fs/ceph/super.h
+++ b/fs/ceph/super.h
@@ -239,6 +239,7 @@ struct ceph_inode_info {
         unsigned i_ceph_flags;
         unsigned long i_release_count;
 
+        struct ceph_dir_layout i_dir_layout;
         struct ceph_file_layout i_layout;
         char *i_symlink;
 
@@ -768,6 +769,7 @@ extern void ceph_dentry_lru_add(struct dentry *dn);
 extern void ceph_dentry_lru_touch(struct dentry *dn);
 extern void ceph_dentry_lru_del(struct dentry *dn);
 extern void ceph_invalidate_dentry_lease(struct dentry *dentry);
+extern unsigned ceph_dentry_hash(struct dentry *dn);
 
 /*
  * our d_ops vary depending on whether the inode is live,
diff --git a/fs/char_dev.c b/fs/char_dev.c
index e5b9df993b93..dca9e5e0f73b 100644
--- a/fs/char_dev.c
+++ b/fs/char_dev.c
@@ -59,7 +59,7 @@ static struct char_device_struct {
 } *chrdevs[CHRDEV_MAJOR_HASH_SIZE];
 
 /* index in the above */
-static inline int major_to_index(int major)
+static inline int major_to_index(unsigned major)
 {
         return major % CHRDEV_MAJOR_HASH_SIZE;
 }
@@ -417,18 +417,6 @@ static int chrdev_open(struct inode *inode, struct file *filp)
         return ret;
 }
 
-int cdev_index(struct inode *inode)
-{
-        int idx;
-        struct kobject *kobj;
-
-        kobj = kobj_lookup(cdev_map, inode->i_rdev, &idx);
-        if (!kobj)
-                return -1;
-        kobject_put(kobj);
-        return idx;
-}
-
 void cd_forget(struct inode *inode)
 {
         spin_lock(&cdev_lock);
@@ -582,7 +570,6 @@ EXPORT_SYMBOL(cdev_init);
 EXPORT_SYMBOL(cdev_alloc);
 EXPORT_SYMBOL(cdev_del);
 EXPORT_SYMBOL(cdev_add);
-EXPORT_SYMBOL(cdev_index);
 EXPORT_SYMBOL(__register_chrdev);
 EXPORT_SYMBOL(__unregister_chrdev);
 EXPORT_SYMBOL(directly_mappable_cdev_bdi);
diff --git a/fs/cifs/cifsfs.c b/fs/cifs/cifsfs.c
index 5e7075d5f139..d9f652a522a6 100644
--- a/fs/cifs/cifsfs.c
+++ b/fs/cifs/cifsfs.c
@@ -174,6 +174,12 @@ cifs_read_super(struct super_block *sb, void *data,
                 goto out_no_root;
         }
 
+        /* do that *after* d_alloc_root() - we want NULL ->d_op for root here */
+        if (cifs_sb_master_tcon(cifs_sb)->nocase)
+                sb->s_d_op = &cifs_ci_dentry_ops;
+        else
+                sb->s_d_op = &cifs_dentry_ops;
+
 #ifdef CONFIG_CIFS_EXPERIMENTAL
         if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_SERVER_INUM) {
                 cFYI(1, "export ops supported");
diff --git a/fs/cifs/dir.c b/fs/cifs/dir.c
index 2e773825835e..1e95dd635632 100644
--- a/fs/cifs/dir.c
+++ b/fs/cifs/dir.c
@@ -130,17 +130,6 @@ cifs_bp_rename_retry:
         return full_path;
 }
 
-static void setup_cifs_dentry(struct cifsTconInfo *tcon,
-                              struct dentry *direntry,
-                              struct inode *newinode)
-{
-        if (tcon->nocase)
-                d_set_d_op(direntry, &cifs_ci_dentry_ops);
-        else
-                d_set_d_op(direntry, &cifs_dentry_ops);
-        d_instantiate(direntry, newinode);
-}
-
 /* Inode operations in similar order to how they appear in Linux file fs.h */
 
 int
@@ -327,7 +316,7 @@ cifs_create_get_file_info:
 
 cifs_create_set_dentry:
         if (rc == 0)
-                setup_cifs_dentry(tcon, direntry, newinode);
+                d_instantiate(direntry, newinode);
         else
                 cFYI(1, "Create worked, get_inode_info failed rc = %d", rc);
 
@@ -418,10 +407,6 @@ int cifs_mknod(struct inode *inode, struct dentry *direntry, int mode,
 
                 rc = cifs_get_inode_info_unix(&newinode, full_path,
                                                 inode->i_sb, xid);
-                if (pTcon->nocase)
-                        d_set_d_op(direntry, &cifs_ci_dentry_ops);
-                else
-                        d_set_d_op(direntry, &cifs_dentry_ops);
 
                 if (rc == 0)
                         d_instantiate(direntry, newinode);
@@ -601,10 +586,6 @@ cifs_lookup(struct inode *parent_dir_inode, struct dentry *direntry,
                                 parent_dir_inode->i_sb, xid, NULL);
 
         if ((rc == 0) && (newInode != NULL)) {
-                if (pTcon->nocase)
-                        d_set_d_op(direntry, &cifs_ci_dentry_ops);
-                else
-                        d_set_d_op(direntry, &cifs_dentry_ops);
                 d_add(direntry, newInode);
                 if (posix_open) {
                         filp = lookup_instantiate_filp(nd, direntry,
@@ -631,10 +612,6 @@ cifs_lookup(struct inode *parent_dir_inode, struct dentry *direntry,
         } else if (rc == -ENOENT) {
                 rc = 0;
                 direntry->d_time = jiffies;
-                if (pTcon->nocase)
-                        d_set_d_op(direntry, &cifs_ci_dentry_ops);
-                else
-                        d_set_d_op(direntry, &cifs_dentry_ops);
                 d_add(direntry, NULL);
         /*      if it was once a directory (but how can we tell?) we could do
                 shrink_dcache_parent(direntry); */
diff --git a/fs/cifs/inode.c b/fs/cifs/inode.c
index 0c7e36910e31..b06b60620240 100644
--- a/fs/cifs/inode.c
+++ b/fs/cifs/inode.c
@@ -1324,10 +1324,6 @@ int cifs_mkdir(struct inode *inode, struct dentry *direntry, int mode)
 /*BB check (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_SET_UID ) to see if need
         to set uid/gid */
                         inc_nlink(inode);
-                        if (pTcon->nocase)
-                                d_set_d_op(direntry, &cifs_ci_dentry_ops);
-                        else
-                                d_set_d_op(direntry, &cifs_dentry_ops);
 
                         cifs_unix_basic_to_fattr(&fattr, pInfo, cifs_sb);
                         cifs_fill_uniqueid(inode->i_sb, &fattr);
@@ -1368,10 +1364,6 @@ mkdir_get_info:
                         rc = cifs_get_inode_info(&newinode, full_path, NULL,
                                                  inode->i_sb, xid, NULL);
 
-                if (pTcon->nocase)
-                        d_set_d_op(direntry, &cifs_ci_dentry_ops);
-                else
-                        d_set_d_op(direntry, &cifs_dentry_ops);
                 d_instantiate(direntry, newinode);
                  /* setting nlink not necessary except in cases where we
                   * failed to get it from the server or was set bogus */
diff --git a/fs/cifs/link.c b/fs/cifs/link.c
index fe2f6a93c49e..306769de2fb5 100644
--- a/fs/cifs/link.c
+++ b/fs/cifs/link.c
@@ -524,10 +524,6 @@ cifs_symlink(struct inode *inode, struct dentry *direntry, const char *symname)
                         cFYI(1, "Create symlink ok, getinodeinfo fail rc = %d",
                               rc);
                 } else {
-                        if (pTcon->nocase)
-                                d_set_d_op(direntry, &cifs_ci_dentry_ops);
-                        else
-                                d_set_d_op(direntry, &cifs_dentry_ops);
                         d_instantiate(direntry, newinode);
                 }
         }
diff --git a/fs/cifs/readdir.c b/fs/cifs/readdir.c
index 76b1b37c9e6b..7f25cc3d2256 100644
--- a/fs/cifs/readdir.c
+++ b/fs/cifs/readdir.c
@@ -102,11 +102,6 @@ cifs_readdir_lookup(struct dentry *parent, struct qstr *name,
                 return NULL;
         }
 
-        if (cifs_sb_master_tcon(CIFS_SB(sb))->nocase)
-                d_set_d_op(dentry, &cifs_ci_dentry_ops);
-        else
-                d_set_d_op(dentry, &cifs_dentry_ops);
-
         alias = d_materialise_unique(dentry, inode);
         if (alias != NULL) {
                 dput(dentry);
diff --git a/fs/coda/cache.c b/fs/coda/cache.c
index 5525e1c660fd..690157876184 100644
--- a/fs/coda/cache.c
+++ b/fs/coda/cache.c
@@ -20,10 +20,9 @@
 #include <linux/spinlock.h>
 
 #include <linux/coda.h>
-#include <linux/coda_linux.h>
 #include <linux/coda_psdev.h>
-#include <linux/coda_fs_i.h>
-#include <linux/coda_cache.h>
+#include "coda_linux.h"
+#include "coda_cache.h"
 
 static atomic_t permission_epoch = ATOMIC_INIT(0);
 
diff --git a/fs/coda/cnode.c b/fs/coda/cnode.c
index 602240569c89..6475877b0763 100644
--- a/fs/coda/cnode.c
+++ b/fs/coda/cnode.c
@@ -7,9 +7,8 @@
 #include <linux/time.h>
 
 #include <linux/coda.h>
-#include <linux/coda_linux.h>
-#include <linux/coda_fs_i.h>
 #include <linux/coda_psdev.h>
+#include "coda_linux.h"
 
 static inline int coda_fideq(struct CodaFid *fid1, struct CodaFid *fid2)
 {
diff --git a/fs/coda/coda_cache.h b/fs/coda/coda_cache.h
new file mode 100644
index 000000000000..c910b5eb1ceb
--- /dev/null
+++ b/fs/coda/coda_cache.h
@@ -0,0 +1,22 @@
+/* Coda filesystem -- Linux Minicache
+ *
+ * Copyright (C) 1989 - 1997 Carnegie Mellon University
+ *
+ * Carnegie Mellon University encourages users of this software to
+ * contribute improvements to the Coda project. Contact Peter Braam
+ * <coda@cs.cmu.edu>
+ */
+
+#ifndef _CFSNC_HEADER_
+#define _CFSNC_HEADER_
+
+/* credential cache */
+void coda_cache_enter(struct inode *inode, int mask);
+void coda_cache_clear_inode(struct inode *);
+void coda_cache_clear_all(struct super_block *sb);
+int coda_cache_check(struct inode *inode, int mask);
+
+/* for downcalls and attributes and lookups */
+void coda_flag_inode_children(struct inode *inode, int flag);
+
+#endif /* _CFSNC_HEADER_ */
diff --git a/fs/coda/coda_fs_i.h b/fs/coda/coda_fs_i.h
new file mode 100644
index 000000000000..e35071b1de0e
--- /dev/null
+++ b/fs/coda/coda_fs_i.h
@@ -0,0 +1,58 @@
+/*
+ *  coda_fs_i.h
+ *
+ *  Copyright (C) 1998 Carnegie Mellon University
+ *
+ */
+
+#ifndef _LINUX_CODA_FS_I
+#define _LINUX_CODA_FS_I
+
+#include <linux/types.h>
+#include <linux/list.h>
+#include <linux/spinlock.h>
+#include <linux/coda.h>
+
+/*
+ * coda fs inode data
+ * c_lock protects accesses to c_flags, c_mapcount, c_cached_epoch, c_uid and
+ * c_cached_perm.
+ * vfs_inode is set only when the inode is created and never changes.
+ * c_fid is set when the inode is created and should be considered immutable.
+ */
+struct coda_inode_info {
+        struct CodaFid     c_fid;       /* Coda identifier */
+        u_short            c_flags;     /* flags (see below) */
+        unsigned int       c_mapcount;  /* nr of times this inode is mapped */
+        unsigned int       c_cached_epoch; /* epoch for cached permissions */
+        vuid_t             c_uid;       /* fsuid for cached permissions */
+        unsigned int       c_cached_perm; /* cached access permissions */
+        spinlock_t         c_lock;
+        struct inode       vfs_inode;
+};
+
+/*
+ * coda fs file private data
+ */
+#define CODA_MAGIC 0xC0DAC0DA
+struct coda_file_info {
+        int                cfi_magic;     /* magic number */
+        struct file       *cfi_container; /* container file for this cnode */
+        unsigned int       cfi_mapcount;  /* nr of times this file is mapped */
+};
+
+#define CODA_FTOC(file) ((struct coda_file_info *)((file)->private_data))
+
+/* flags */
+#define C_VATTR       0x1   /* Validity of vattr in inode */
+#define C_FLUSH       0x2   /* used after a flush */
+#define C_DYING       0x4   /* from venus (which died) */
+#define C_PURGE       0x8
+
+int coda_cnode_make(struct inode **, struct CodaFid *, struct super_block *);
+struct inode *coda_iget(struct super_block *sb, struct CodaFid *fid, struct coda_vattr *attr);
+int coda_cnode_makectl(struct inode **inode, struct super_block *sb);
+struct inode *coda_fid_to_inode(struct CodaFid *fid, struct super_block *sb);
+void coda_replace_fid(struct inode *, struct CodaFid *, struct CodaFid *);
+
+#endif
diff --git a/fs/coda/coda_linux.c b/fs/coda/coda_linux.c
index bf4a3fd3c8e3..2bdbcc11b373 100644
--- a/fs/coda/coda_linux.c
+++ b/fs/coda/coda_linux.c
@@ -17,9 +17,8 @@
 #include <linux/string.h>
 
 #include <linux/coda.h>
-#include <linux/coda_linux.h>
 #include <linux/coda_psdev.h>
-#include <linux/coda_fs_i.h>
+#include "coda_linux.h"
 
 /* initialize the debugging variables */
 int coda_fake_statfs;
diff --git a/fs/coda/coda_linux.h b/fs/coda/coda_linux.h
new file mode 100644
index 000000000000..9b0c5323890b
--- /dev/null
+++ b/fs/coda/coda_linux.h
@@ -0,0 +1,101 @@
+/* 
+ * Coda File System, Linux Kernel module
+ * 
+ * Original version, adapted from cfs_mach.c, (C) Carnegie Mellon University
+ * Linux modifications (C) 1996, Peter J. Braam
+ * Rewritten for Linux 2.1 (C) 1997 Carnegie Mellon University
+ *
+ * Carnegie Mellon University encourages users of this software to
+ * contribute improvements to the Coda project.
+ */
+
+#ifndef _LINUX_CODA_FS
+#define _LINUX_CODA_FS
+
+#include <linux/kernel.h>
+#include <linux/param.h>
+#include <linux/mm.h>
+#include <linux/vmalloc.h>
+#include <linux/slab.h>
+#include <linux/wait.h>         
+#include <linux/types.h>
+#include <linux/fs.h>
+#include "coda_fs_i.h"
+
+/* operations */
+extern const struct inode_operations coda_dir_inode_operations;
+extern const struct inode_operations coda_file_inode_operations;
+extern const struct inode_operations coda_ioctl_inode_operations;
+
+extern const struct dentry_operations coda_dentry_operations;
+
+extern const struct address_space_operations coda_file_aops;
+extern const struct address_space_operations coda_symlink_aops;
+
+extern const struct file_operations coda_dir_operations;
+extern const struct file_operations coda_file_operations;
+extern const struct file_operations coda_ioctl_operations;
+
+/* operations shared over more than one file */
+int coda_open(struct inode *i, struct file *f);
+int coda_release(struct inode *i, struct file *f);
+int coda_permission(struct inode *inode, int mask, unsigned int flags);
+int coda_revalidate_inode(struct dentry *);
+int coda_getattr(struct vfsmount *, struct dentry *, struct kstat *);
+int coda_setattr(struct dentry *, struct iattr *);
+
+/* this file:  heloers */
+char *coda_f2s(struct CodaFid *f);
+int coda_isroot(struct inode *i);
+int coda_iscontrol(const char *name, size_t length);
+
+void coda_vattr_to_iattr(struct inode *, struct coda_vattr *);
+void coda_iattr_to_vattr(struct iattr *, struct coda_vattr *);
+unsigned short coda_flags_to_cflags(unsigned short);
+
+/* sysctl.h */
+void coda_sysctl_init(void);
+void coda_sysctl_clean(void);
+
+#define CODA_ALLOC(ptr, cast, size) do { \
+    if (size < PAGE_SIZE) \
+        ptr = kmalloc((unsigned long) size, GFP_KERNEL); \
+    else \
+        ptr = (cast)vmalloc((unsigned long) size); \
+    if (!ptr) \
+        printk("kernel malloc returns 0 at %s:%d\n", __FILE__, __LINE__); \
+    else memset( ptr, 0, size ); \
+} while (0)
+
+
+#define CODA_FREE(ptr,size) \
+    do { if (size < PAGE_SIZE) kfree((ptr)); else vfree((ptr)); } while (0)
+
+/* inode to cnode access functions */
+
+static inline struct coda_inode_info *ITOC(struct inode *inode)
+{
+        return list_entry(inode, struct coda_inode_info, vfs_inode);
+}
+
+static __inline__ struct CodaFid *coda_i2f(struct inode *inode)
+{
+        return &(ITOC(inode)->c_fid);
+}
+
+static __inline__ char *coda_i2s(struct inode *inode)
+{
+        return coda_f2s(&(ITOC(inode)->c_fid));
+}
+
+/* this will not zap the inode away */
+static __inline__ void coda_flag_inode(struct inode *inode, int flag)
+{
+        struct coda_inode_info *cii = ITOC(inode);
+
+        spin_lock(&cii->c_lock);
+        cii->c_flags |= flag;
+        spin_unlock(&cii->c_lock);
+}               
+
+#endif
diff --git a/fs/coda/dir.c b/fs/coda/dir.c
index 29badd91360f..2b8dae4d121e 100644
--- a/fs/coda/dir.c
+++ b/fs/coda/dir.c
@@ -23,10 +23,9 @@
 #include <asm/uaccess.h>
 
 #include <linux/coda.h>
-#include <linux/coda_linux.h>
 #include <linux/coda_psdev.h>
-#include <linux/coda_fs_i.h>
-#include <linux/coda_cache.h>
+#include "coda_linux.h"
+#include "coda_cache.h"
 
 #include "coda_int.h"
 
@@ -61,7 +60,7 @@ static int coda_return_EIO(void)
 }
 #define CODA_EIO_ERROR ((void *) (coda_return_EIO))
 
-static const struct dentry_operations coda_dentry_operations =
+const struct dentry_operations coda_dentry_operations =
 {
         .d_revalidate   = coda_dentry_revalidate,
         .d_delete       = coda_dentry_delete,
@@ -126,8 +125,6 @@ static struct dentry *coda_lookup(struct inode *dir, struct dentry *entry, struc
                 return ERR_PTR(error);
 
 exit:
-        d_set_d_op(entry, &coda_dentry_operations);
-
         if (inode && (type & CODA_NOCACHE))
                 coda_flag_inode(inode, C_VATTR | C_PURGE);
 
diff --git a/fs/coda/file.c b/fs/coda/file.c
index c8b50ba4366a..0433057be330 100644
--- a/fs/coda/file.c
+++ b/fs/coda/file.c
@@ -21,10 +21,9 @@
 #include <asm/uaccess.h>
 
 #include <linux/coda.h>
-#include <linux/coda_linux.h>
-#include <linux/coda_fs_i.h>
 #include <linux/coda_psdev.h>
 
+#include "coda_linux.h"
 #include "coda_int.h"
 
 static ssize_t
diff --git a/fs/coda/inode.c b/fs/coda/inode.c
index 50dc7d189f56..871b27715465 100644
--- a/fs/coda/inode.c
+++ b/fs/coda/inode.c
@@ -28,10 +28,9 @@
 #include <linux/vmalloc.h>
 
 #include <linux/coda.h>
-#include <linux/coda_linux.h>
 #include <linux/coda_psdev.h>
-#include <linux/coda_fs_i.h>
-#include <linux/coda_cache.h>
+#include "coda_linux.h"
+#include "coda_cache.h"
 
 #include "coda_int.h"
 
@@ -45,7 +44,7 @@ static struct kmem_cache * coda_inode_cachep;
 static struct inode *coda_alloc_inode(struct super_block *sb)
 {
         struct coda_inode_info *ei;
-        ei = (struct coda_inode_info *)kmem_cache_alloc(coda_inode_cachep, GFP_KERNEL);
+        ei = kmem_cache_alloc(coda_inode_cachep, GFP_KERNEL);
         if (!ei)
                 return NULL;
         memset(&ei->c_fid, 0, sizeof(struct CodaFid));
@@ -193,6 +192,7 @@ static int coda_fill_super(struct super_block *sb, void *data, int silent)
         sb->s_blocksize_bits = 12;
         sb->s_magic = CODA_SUPER_MAGIC;
         sb->s_op = &coda_super_operations;
+        sb->s_d_op = &coda_dentry_operations;
         sb->s_bdi = &vc->bdi;
 
         /* get root fid from Venus: this needs the root inode */
diff --git a/fs/coda/pioctl.c b/fs/coda/pioctl.c
index 741f0bd03918..6cbb3afb36dc 100644
--- a/fs/coda/pioctl.c
+++ b/fs/coda/pioctl.c
@@ -19,10 +19,10 @@
 #include <asm/uaccess.h>
 
 #include <linux/coda.h>
-#include <linux/coda_linux.h>
-#include <linux/coda_fs_i.h>
 #include <linux/coda_psdev.h>
 
+#include "coda_linux.h"
+
 /* pioctl ops */
 static int coda_ioctl_permission(struct inode *inode, int mask, unsigned int flags);
 static long coda_pioctl(struct file *filp, unsigned int cmd,
diff --git a/fs/coda/psdev.c b/fs/coda/psdev.c
index 62647a8595e4..8f616e0e252c 100644
--- a/fs/coda/psdev.c
+++ b/fs/coda/psdev.c
@@ -43,10 +43,10 @@
 #include <asm/uaccess.h>
 
 #include <linux/coda.h>
-#include <linux/coda_linux.h>
-#include <linux/coda_fs_i.h>
 #include <linux/coda_psdev.h>
 
+#include "coda_linux.h"
+
 #include "coda_int.h"
 
 /* statistics */
diff --git a/fs/coda/symlink.c b/fs/coda/symlink.c
index af78f007a2b0..ab94ef63caef 100644
--- a/fs/coda/symlink.c
+++ b/fs/coda/symlink.c
@@ -16,9 +16,9 @@
 #include <linux/pagemap.h>
 
 #include <linux/coda.h>
-#include <linux/coda_linux.h>
 #include <linux/coda_psdev.h>
-#include <linux/coda_fs_i.h>
+
+#include "coda_linux.h"
 
 static int coda_symlink_filler(struct file *file, struct page *page)
 {
diff --git a/fs/coda/upcall.c b/fs/coda/upcall.c
index c3563cab9758..9727e0c52579 100644
--- a/fs/coda/upcall.c
+++ b/fs/coda/upcall.c
@@ -33,10 +33,9 @@
 #include <linux/vfs.h>
 
 #include <linux/coda.h>
-#include <linux/coda_linux.h>
 #include <linux/coda_psdev.h>
-#include <linux/coda_fs_i.h>
-#include <linux/coda_cache.h>
+#include "coda_linux.h"
+#include "coda_cache.h"
 
 #include "coda_int.h"
 
diff --git a/fs/configfs/configfs_internal.h b/fs/configfs/configfs_internal.h
index 026cf68553a4..82bda8fdfc1c 100644
--- a/fs/configfs/configfs_internal.h
+++ b/fs/configfs/configfs_internal.h
@@ -90,6 +90,7 @@ extern const struct file_operations configfs_file_operations;
 extern const struct file_operations bin_fops;
 extern const struct inode_operations configfs_dir_inode_operations;
 extern const struct inode_operations configfs_symlink_inode_operations;
+extern const struct dentry_operations configfs_dentry_ops;
 
 extern int configfs_symlink(struct inode *dir, struct dentry *dentry,
                             const char *symname);
diff --git a/fs/configfs/dir.c b/fs/configfs/dir.c
index 36637a8c1ed3..90ff3cb10de3 100644
--- a/fs/configfs/dir.c
+++ b/fs/configfs/dir.c
@@ -72,7 +72,7 @@ static int configfs_d_delete(const struct dentry *dentry)
         return 1;
 }
 
-static const struct dentry_operations configfs_dentry_ops = {
+const struct dentry_operations configfs_dentry_ops = {
         .d_iput         = configfs_d_iput,
         /* simple_delete_dentry() isn't exported */
         .d_delete       = configfs_d_delete,
@@ -442,7 +442,6 @@ static int configfs_attach_attr(struct configfs_dirent * sd, struct dentry * den
                 return error;
         }
 
-        d_set_d_op(dentry, &configfs_dentry_ops);
         d_rehash(dentry);
 
         return 0;
@@ -489,7 +488,6 @@ static struct dentry * configfs_lookup(struct inode *dir,
                  */
                 if (dentry->d_name.len > NAME_MAX)
                         return ERR_PTR(-ENAMETOOLONG);
-                d_set_d_op(dentry, &configfs_dentry_ops);
                 d_add(dentry, NULL);
                 return NULL;
         }
@@ -683,7 +681,6 @@ static int create_default_group(struct config_group *parent_group,
         ret = -ENOMEM;
         child = d_alloc(parent, &name);
         if (child) {
-                d_set_d_op(child, &configfs_dentry_ops);
                 d_add(child, NULL);
 
                 ret = configfs_attach_group(&parent_group->cg_item,
@@ -1681,7 +1678,6 @@ int configfs_register_subsystem(struct configfs_subsystem *subsys)
         err = -ENOMEM;
         dentry = d_alloc(configfs_sb->s_root, &name);
         if (dentry) {
-                d_set_d_op(dentry, &configfs_dentry_ops);
                 d_add(dentry, NULL);
 
                 err = configfs_attach_group(sd->s_element, &group->cg_item,
diff --git a/fs/configfs/mount.c b/fs/configfs/mount.c
index 7d3607febe1c..ecc62178beda 100644
--- a/fs/configfs/mount.c
+++ b/fs/configfs/mount.c
@@ -101,6 +101,7 @@ static int configfs_fill_super(struct super_block *sb, void *data, int silent)
         configfs_root_group.cg_item.ci_dentry = root;
         root->d_fsdata = &configfs_root;
         sb->s_root = root;
+        sb->s_d_op = &configfs_dentry_ops; /* the rest get that */
         return 0;
 }
 
diff --git a/fs/cramfs/inode.c b/fs/cramfs/inode.c
index 32fd5fe9ca0e..e141939080f0 100644
--- a/fs/cramfs/inode.c
+++ b/fs/cramfs/inode.c
@@ -34,57 +34,81 @@ static const struct address_space_operations cramfs_aops;
 static DEFINE_MUTEX(read_mutex);
 
 
-/* These two macros may change in future, to provide better st_ino
-   semantics. */
-#define CRAMINO(x)      (((x)->offset && (x)->size)?(x)->offset<<2:1)
+/* These macros may change in future, to provide better st_ino semantics. */
 #define OFFSET(x)       ((x)->i_ino)
 
-static void setup_inode(struct inode *inode, struct cramfs_inode * cramfs_inode)
+static unsigned long cramino(struct cramfs_inode *cino, unsigned int offset)
 {
+        if (!cino->offset)
+                return offset + 1;
+        if (!cino->size)
+                return offset + 1;
+
+        /*
+         * The file mode test fixes buggy mkcramfs implementations where
+         * cramfs_inode->offset is set to a non zero value for entries
+         * which did not contain data, like devices node and fifos.
+         */
+        switch (cino->mode & S_IFMT) {
+        case S_IFREG:
+        case S_IFDIR:
+        case S_IFLNK:
+                return cino->offset << 2;
+        default:
+                break;
+        }
+        return offset + 1;
+}
+
+static struct inode *get_cramfs_inode(struct super_block *sb,
+        struct cramfs_inode *cramfs_inode, unsigned int offset)
+{
+        struct inode *inode;
         static struct timespec zerotime;
+
+        inode = iget_locked(sb, cramino(cramfs_inode, offset));
+        if (!inode)
+                return ERR_PTR(-ENOMEM);
+        if (!(inode->i_state & I_NEW))
+                return inode;
+
+        switch (cramfs_inode->mode & S_IFMT) {
+        case S_IFREG:
+                inode->i_fop = &generic_ro_fops;
+                inode->i_data.a_ops = &cramfs_aops;
+                break;
+        case S_IFDIR:
+                inode->i_op = &cramfs_dir_inode_operations;
+                inode->i_fop = &cramfs_directory_operations;
+                break;
+        case S_IFLNK:
+                inode->i_op = &page_symlink_inode_operations;
+                inode->i_data.a_ops = &cramfs_aops;
+                break;
+        default:
+                init_special_inode(inode, cramfs_inode->mode,
+                                old_decode_dev(cramfs_inode->size));
+        }
+
         inode->i_mode = cramfs_inode->mode;
         inode->i_uid = cramfs_inode->uid;
-        inode->i_size = cramfs_inode->size;
-        inode->i_blocks = (cramfs_inode->size - 1) / 512 + 1;
         inode->i_gid = cramfs_inode->gid;
+
+        /* if the lower 2 bits are zero, the inode contains data */
+        if (!(inode->i_ino & 3)) {
+                inode->i_size = cramfs_inode->size;
+                inode->i_blocks = (cramfs_inode->size - 1) / 512 + 1;
+        }
+
         /* Struct copy intentional */
         inode->i_mtime = inode->i_atime = inode->i_ctime = zerotime;
         /* inode->i_nlink is left 1 - arguably wrong for directories,
            but it's the best we can do without reading the directory
            contents.  1 yields the right result in GNU find, even
            without -noleaf option. */
-        if (S_ISREG(inode->i_mode)) {
-                inode->i_fop = &generic_ro_fops;
-                inode->i_data.a_ops = &cramfs_aops;
-        } else if (S_ISDIR(inode->i_mode)) {
-                inode->i_op = &cramfs_dir_inode_operations;
-                inode->i_fop = &cramfs_directory_operations;
-        } else if (S_ISLNK(inode->i_mode)) {
-                inode->i_op = &page_symlink_inode_operations;
-                inode->i_data.a_ops = &cramfs_aops;
-        } else {
-                init_special_inode(inode, inode->i_mode,
-                        old_decode_dev(cramfs_inode->size));
-        }
-}
 
-static struct inode *get_cramfs_inode(struct super_block *sb,
-                                struct cramfs_inode * cramfs_inode)
-{
-        struct inode *inode;
-        if (CRAMINO(cramfs_inode) == 1) {
-                inode = new_inode(sb);
-                if (inode) {
-                        inode->i_ino = 1;
-                        setup_inode(inode, cramfs_inode);
-                }
-        } else {
-                inode = iget_locked(sb, CRAMINO(cramfs_inode));
-                if (inode && (inode->i_state & I_NEW)) {
-                        setup_inode(inode, cramfs_inode);
-                        unlock_new_inode(inode);
-                }
-        }
+        unlock_new_inode(inode);
+
         return inode;
 }
 
@@ -265,6 +289,9 @@ static int cramfs_fill_super(struct super_block *sb, void *data, int silent)
                 printk(KERN_ERR "cramfs: root is not a directory\n");
                 goto out;
         }
+        /* correct strange, hard-coded permissions of mkcramfs */
+        super.root.mode |= (S_IRUSR | S_IXUSR | S_IRGRP | S_IXGRP | S_IROTH | S_IXOTH);
+
         root_offset = super.root.offset << 2;
         if (super.flags & CRAMFS_FLAG_FSID_VERSION_2) {
                 sbi->size=super.size;
@@ -289,7 +316,7 @@ static int cramfs_fill_super(struct super_block *sb, void *data, int silent)
 
         /* Set it all up.. */
         sb->s_op = &cramfs_ops;
-        root = get_cramfs_inode(sb, &super.root);
+        root = get_cramfs_inode(sb, &super.root, 0);
         if (!root)
                 goto out;
         sb->s_root = d_alloc_root(root);
@@ -365,7 +392,7 @@ static int cramfs_readdir(struct file *filp, void *dirent, filldir_t filldir)
                  */
                 namelen = de->namelen << 2;
                 memcpy(buf, name, namelen);
-                ino = CRAMINO(de);
+                ino = cramino(de, OFFSET(inode) + offset);
                 mode = de->mode;
                 mutex_unlock(&read_mutex);
                 nextoffset = offset + sizeof(*de) + namelen;
@@ -404,8 +431,9 @@ static struct dentry * cramfs_lookup(struct inode *dir, struct dentry *dentry, s
                 struct cramfs_inode *de;
                 char *name;
                 int namelen, retval;
+                int dir_off = OFFSET(dir) + offset;
 
-                de = cramfs_read(dir->i_sb, OFFSET(dir) + offset, sizeof(*de)+CRAMFS_MAXPATHLEN);
+                de = cramfs_read(dir->i_sb, dir_off, sizeof(*de)+CRAMFS_MAXPATHLEN);
                 name = (char *)(de+1);
 
                 /* Try to take advantage of sorted directories */
@@ -436,7 +464,7 @@ static struct dentry * cramfs_lookup(struct inode *dir, struct dentry *dentry, s
                 if (!retval) {
                         struct cramfs_inode entry = *de;
                         mutex_unlock(&read_mutex);
-                        d_add(dentry, get_cramfs_inode(dir->i_sb, &entry));
+                        d_add(dentry, get_cramfs_inode(dir->i_sb, &entry, dir_off));
                         return NULL;
                 }
                 /* else (retval < 0) */
diff --git a/fs/dcache.c b/fs/dcache.c
index 5699d4c027cb..0c6d5c549d84 100644
--- a/fs/dcache.c
+++ b/fs/dcache.c
@@ -1320,6 +1320,7 @@ struct dentry *d_alloc(struct dentry * parent, const struct qstr *name)
                 __dget_dlock(parent);
                 dentry->d_parent = parent;
                 dentry->d_sb = parent->d_sb;
+                d_set_d_op(dentry, dentry->d_sb->s_d_op);
                 list_add(&dentry->d_u.d_child, &parent->d_subdirs);
                 spin_unlock(&parent->d_lock);
         }
@@ -1335,6 +1336,7 @@ struct dentry *d_alloc_pseudo(struct super_block *sb, const struct qstr *name)
         struct dentry *dentry = d_alloc(NULL, name);
         if (dentry) {
                 dentry->d_sb = sb;
+                d_set_d_op(dentry, dentry->d_sb->s_d_op);
                 dentry->d_parent = dentry;
                 dentry->d_flags |= DCACHE_DISCONNECTED;
         }
@@ -1507,6 +1509,7 @@ struct dentry * d_alloc_root(struct inode * root_inode)
                 res = d_alloc(NULL, &name);
                 if (res) {
                         res->d_sb = root_inode->i_sb;
+                        d_set_d_op(res, res->d_sb->s_d_op);
                         res->d_parent = res;
                         d_instantiate(res, root_inode);
                 }
@@ -1567,6 +1570,7 @@ struct dentry *d_obtain_alias(struct inode *inode)
         /* attach a disconnected dentry */
         spin_lock(&tmp->d_lock);
         tmp->d_sb = inode->i_sb;
+        d_set_d_op(tmp, tmp->d_sb->s_d_op);
         tmp->d_inode = inode;
         tmp->d_flags |= DCACHE_DISCONNECTED;
         list_add(&tmp->d_alias, &inode->i_dentry);
@@ -1966,7 +1970,7 @@ out:
 /**
  * d_validate - verify dentry provided from insecure source (deprecated)
  * @dentry: The dentry alleged to be valid child of @dparent
- * @dparent: The parent dentry (known to be valid)
+ * @parent: The parent dentry (known to be valid)
  *
  * An insecure source has sent us a dentry, here we verify it and dget() it.
  * This is used by ncpfs in its readdir implementation.
@@ -2449,8 +2453,7 @@ static int prepend_name(char **buffer, int *buflen, struct qstr *name)
 }
 
 /**
- * Prepend path string to a buffer
- *
+ * prepend_path - Prepend path string to a buffer
  * @path: the dentry/vfsmount to report
  * @root: root vfsmnt/dentry (may be modified by this function)
  * @buffer: pointer to the end of the buffer
diff --git a/fs/ecryptfs/inode.c b/fs/ecryptfs/inode.c
index 337352a94751..64ff02330752 100644
--- a/fs/ecryptfs/inode.c
+++ b/fs/ecryptfs/inode.c
@@ -441,7 +441,6 @@ static struct dentry *ecryptfs_lookup(struct inode *ecryptfs_dir_inode,
         struct qstr lower_name;
         int rc = 0;
 
-        d_set_d_op(ecryptfs_dentry, &ecryptfs_dops);
         if ((ecryptfs_dentry->d_name.len == 1
              && !strcmp(ecryptfs_dentry->d_name.name, "."))
             || (ecryptfs_dentry->d_name.len == 2
diff --git a/fs/ecryptfs/main.c b/fs/ecryptfs/main.c
index 351038675376..d3b28abdd6aa 100644
--- a/fs/ecryptfs/main.c
+++ b/fs/ecryptfs/main.c
@@ -141,25 +141,12 @@ int ecryptfs_init_persistent_file(struct dentry *ecryptfs_dentry)
         return rc;
 }
 
-/**
- * ecryptfs_interpose
- * @lower_dentry: Existing dentry in the lower filesystem
- * @dentry: ecryptfs' dentry
- * @sb: ecryptfs's super_block
- * @flags: flags to govern behavior of interpose procedure
- *
- * Interposes upper and lower dentries.
- *
- * Returns zero on success; non-zero otherwise
- */
-int ecryptfs_interpose(struct dentry *lower_dentry, struct dentry *dentry,
-                       struct super_block *sb, u32 flags)
+static struct inode *ecryptfs_get_inode(struct inode *lower_inode,
+                       struct super_block *sb)
 {
-        struct inode *lower_inode;
         struct inode *inode;
         int rc = 0;
 
-        lower_inode = lower_dentry->d_inode;
         if (lower_inode->i_sb != ecryptfs_superblock_to_lower(sb)) {
                 rc = -EXDEV;
                 goto out;
@@ -189,17 +176,38 @@ int ecryptfs_interpose(struct dentry *lower_dentry, struct dentry *dentry,
         if (special_file(lower_inode->i_mode))
                 init_special_inode(inode, lower_inode->i_mode,
                                    lower_inode->i_rdev);
-        d_set_d_op(dentry, &ecryptfs_dops);
         fsstack_copy_attr_all(inode, lower_inode);
         /* This size will be overwritten for real files w/ headers and
          * other metadata */
         fsstack_copy_inode_size(inode, lower_inode);
+        return inode;
+out:
+        return ERR_PTR(rc);
+}
+
+/**
+ * ecryptfs_interpose
+ * @lower_dentry: Existing dentry in the lower filesystem
+ * @dentry: ecryptfs' dentry
+ * @sb: ecryptfs's super_block
+ * @flags: flags to govern behavior of interpose procedure
+ *
+ * Interposes upper and lower dentries.
+ *
+ * Returns zero on success; non-zero otherwise
+ */
+int ecryptfs_interpose(struct dentry *lower_dentry, struct dentry *dentry,
+                       struct super_block *sb, u32 flags)
+{
+        struct inode *lower_inode = lower_dentry->d_inode;
+        struct inode *inode = ecryptfs_get_inode(lower_inode, sb);
+        if (IS_ERR(inode))
+                return PTR_ERR(inode);
         if (flags & ECRYPTFS_INTERPOSE_FLAG_D_ADD)
                 d_add(dentry, inode);
         else
                 d_instantiate(dentry, inode);
-out:
-        return rc;
+        return 0;
 }
 
 enum { ecryptfs_opt_sig, ecryptfs_opt_ecryptfs_sig,
@@ -492,59 +500,11 @@ struct kmem_cache *ecryptfs_sb_info_cache;
 static struct file_system_type ecryptfs_fs_type;
 
 /**
- * ecryptfs_read_super
- * @sb: The ecryptfs super block
- * @dev_name: The path to mount over
- *
- * Read the super block of the lower filesystem, and use
- * ecryptfs_interpose to create our initial inode and super block
- * struct.
- */
-static int ecryptfs_read_super(struct super_block *sb, const char *dev_name)
-{
-        struct path path;
-        int rc;
-
-        rc = kern_path(dev_name, LOOKUP_FOLLOW | LOOKUP_DIRECTORY, &path);
-        if (rc) {
-                ecryptfs_printk(KERN_WARNING, "path_lookup() failed\n");
-                goto out;
-        }
-        if (path.dentry->d_sb->s_type == &ecryptfs_fs_type) {
-                rc = -EINVAL;
-                printk(KERN_ERR "Mount on filesystem of type "
-                        "eCryptfs explicitly disallowed due to "
-                        "known incompatibilities\n");
-                goto out_free;
-        }
-        ecryptfs_set_superblock_lower(sb, path.dentry->d_sb);
-        sb->s_maxbytes = path.dentry->d_sb->s_maxbytes;
-        sb->s_blocksize = path.dentry->d_sb->s_blocksize;
-        ecryptfs_set_dentry_lower(sb->s_root, path.dentry);
-        ecryptfs_set_dentry_lower_mnt(sb->s_root, path.mnt);
-        rc = ecryptfs_interpose(path.dentry, sb->s_root, sb, 0);
-        if (rc)
-                goto out_free;
-        rc = 0;
-        goto out;
-out_free:
-        path_put(&path);
-out:
-        return rc;
-}
-
-/**
  * ecryptfs_get_sb
  * @fs_type
  * @flags
  * @dev_name: The path to mount over
  * @raw_data: The options passed into the kernel
- *
- * The whole ecryptfs_get_sb process is broken into 3 functions:
- * ecryptfs_parse_options(): handle options passed to ecryptfs, if any
- * ecryptfs_read_super(): this accesses the lower filesystem and uses
- *                        ecryptfs_interpose to perform most of the linking
- * ecryptfs_interpose(): links the lower filesystem into ecryptfs (inode.c)
  */
 static struct dentry *ecryptfs_mount(struct file_system_type *fs_type, int flags,
                         const char *dev_name, void *raw_data)
@@ -553,6 +513,8 @@ static struct dentry *ecryptfs_mount(struct file_system_type *fs_type, int flags
         struct ecryptfs_sb_info *sbi;
         struct ecryptfs_dentry_info *root_info;
         const char *err = "Getting sb failed";
+        struct inode *inode;
+        struct path path;
         int rc;
 
         sbi = kmem_cache_zalloc(ecryptfs_sb_info_cache, GFP_KERNEL);
@@ -575,10 +537,8 @@ static struct dentry *ecryptfs_mount(struct file_system_type *fs_type, int flags
 
         s->s_flags = flags;
         rc = bdi_setup_and_register(&sbi->bdi, "ecryptfs", BDI_CAP_MAP_COPY);
-        if (rc) {
-                deactivate_locked_super(s);
-                goto out;
-        }
+        if (rc)
+                goto out1;
 
         ecryptfs_set_superblock_private(s, sbi);
         s->s_bdi = &sbi->bdi;
@@ -586,34 +546,54 @@ static struct dentry *ecryptfs_mount(struct file_system_type *fs_type, int flags
         /* ->kill_sb() will take care of sbi after that point */
         sbi = NULL;
         s->s_op = &ecryptfs_sops;
+        s->s_d_op = &ecryptfs_dops;
 
-        rc = -ENOMEM;
-        s->s_root = d_alloc(NULL, &(const struct qstr) {
-                             .hash = 0,.name = "/",.len = 1});
+        err = "Reading sb failed";
+        rc = kern_path(dev_name, LOOKUP_FOLLOW | LOOKUP_DIRECTORY, &path);
+        if (rc) {
+                ecryptfs_printk(KERN_WARNING, "kern_path() failed\n");
+                goto out1;
+        }
+        if (path.dentry->d_sb->s_type == &ecryptfs_fs_type) {
+                rc = -EINVAL;
+                printk(KERN_ERR "Mount on filesystem of type "
+                        "eCryptfs explicitly disallowed due to "
+                        "known incompatibilities\n");
+                goto out_free;
+        }
+        ecryptfs_set_superblock_lower(s, path.dentry->d_sb);
+        s->s_maxbytes = path.dentry->d_sb->s_maxbytes;
+        s->s_blocksize = path.dentry->d_sb->s_blocksize;
+
+        inode = ecryptfs_get_inode(path.dentry->d_inode, s);
+        rc = PTR_ERR(inode);
+        if (IS_ERR(inode))
+                goto out_free;
+
+        s->s_root = d_alloc_root(inode);
         if (!s->s_root) {
-                deactivate_locked_super(s);
-                goto out;
+                iput(inode);
+                rc = -ENOMEM;
+                goto out_free;
         }
-        d_set_d_op(s->s_root, &ecryptfs_dops);
-        s->s_root->d_sb = s;
-        s->s_root->d_parent = s->s_root;
 
+        rc = -ENOMEM;
         root_info = kmem_cache_zalloc(ecryptfs_dentry_info_cache, GFP_KERNEL);
-        if (!root_info) {
-                deactivate_locked_super(s);
-                goto out;
-        }
+        if (!root_info)
+                goto out_free;
+
         /* ->kill_sb() will take care of root_info */
         ecryptfs_set_dentry_private(s->s_root, root_info);
+        ecryptfs_set_dentry_lower(s->s_root, path.dentry);
+        ecryptfs_set_dentry_lower_mnt(s->s_root, path.mnt);
+
         s->s_flags |= MS_ACTIVE;
-        rc = ecryptfs_read_super(s, dev_name);
-        if (rc) {
-                deactivate_locked_super(s);
-                err = "Reading sb failed";
-                goto out;
-        }
         return dget(s->s_root);
 
+out_free:
+        path_put(&path);
+out1:
+        deactivate_locked_super(s);
 out:
         if (sbi) {
                 ecryptfs_destroy_mount_crypt_stat(&sbi->mount_crypt_stat);
diff --git a/fs/eventpoll.c b/fs/eventpoll.c
index 8cf07242067d..cc8a9b7d6064 100644
--- a/fs/eventpoll.c
+++ b/fs/eventpoll.c
@@ -217,7 +217,7 @@ struct ep_send_events_data {
  * Configuration options available inside /proc/sys/fs/epoll/
  */
 /* Maximum number of epoll watched descriptors, per user */
-static int max_user_watches __read_mostly;
+static long max_user_watches __read_mostly;
 
 /*
  * This mutex is used to serialize ep_free() and eventpoll_release_file().
@@ -240,16 +240,18 @@ static struct kmem_cache *pwq_cache __read_mostly;
 
 #include <linux/sysctl.h>
 
-static int zero;
+static long zero;
+static long long_max = LONG_MAX;
 
 ctl_table epoll_table[] = {
         {
                 .procname       = "max_user_watches",
                 .data           = &max_user_watches,
-                .maxlen         = sizeof(int),
+                .maxlen         = sizeof(max_user_watches),
                 .mode           = 0644,
-                .proc_handler   = proc_dointvec_minmax,
+                .proc_handler   = proc_doulongvec_minmax,
                 .extra1         = &zero,
+                .extra2         = &long_max,
         },
         { }
 };
@@ -561,7 +563,7 @@ static int ep_remove(struct eventpoll *ep, struct epitem *epi)
         /* At this point it is safe to free the eventpoll item */
         kmem_cache_free(epi_cache, epi);
 
-        atomic_dec(&ep->user->epoll_watches);
+        atomic_long_dec(&ep->user->epoll_watches);
 
         return 0;
 }
@@ -898,11 +900,12 @@ static int ep_insert(struct eventpoll *ep, struct epoll_event *event,
 {
         int error, revents, pwake = 0;
         unsigned long flags;
+        long user_watches;
         struct epitem *epi;
         struct ep_pqueue epq;
 
-        if (unlikely(atomic_read(&ep->user->epoll_watches) >=
-                     max_user_watches))
+        user_watches = atomic_long_read(&ep->user->epoll_watches);
+        if (unlikely(user_watches >= max_user_watches))
                 return -ENOSPC;
         if (!(epi = kmem_cache_alloc(epi_cache, GFP_KERNEL)))
                 return -ENOMEM;
@@ -966,7 +969,7 @@ static int ep_insert(struct eventpoll *ep, struct epoll_event *event,
 
         spin_unlock_irqrestore(&ep->lock, flags);
 
-        atomic_inc(&ep->user->epoll_watches);
+        atomic_long_inc(&ep->user->epoll_watches);
 
         /* We have to call this outside the lock */
         if (pwake)
@@ -1426,6 +1429,7 @@ static int __init eventpoll_init(void)
          */
         max_user_watches = (((si.totalram - si.totalhigh) / 25) << PAGE_SHIFT) /
                 EP_ITEM_COST;
+        BUG_ON(max_user_watches < 0);
 
         /* Initialize the structure used to perform safe poll wait head wake ups */
         ep_nested_calls_init(&poll_safewake_ncalls);
diff --git a/fs/ext3/super.c b/fs/ext3/super.c
index b7d0554631e4..7aa767d4f06f 100644
--- a/fs/ext3/super.c
+++ b/fs/ext3/super.c
@@ -364,7 +364,7 @@ static struct block_device *ext3_blkdev_get(dev_t dev, struct super_block *sb)
         struct block_device *bdev;
         char b[BDEVNAME_SIZE];
 
-        bdev = open_by_devnum(dev, FMODE_READ|FMODE_WRITE);
+        bdev = blkdev_get_by_dev(dev, FMODE_READ|FMODE_WRITE|FMODE_EXCL, sb);
         if (IS_ERR(bdev))
                 goto fail;
         return bdev;
@@ -381,8 +381,7 @@ fail:
  */
 static int ext3_blkdev_put(struct block_device *bdev)
 {
-        bd_release(bdev);
-        return blkdev_put(bdev, FMODE_READ|FMODE_WRITE);
+        return blkdev_put(bdev, FMODE_READ|FMODE_WRITE|FMODE_EXCL);
 }
 
 static int ext3_blkdev_remove(struct ext3_sb_info *sbi)
@@ -2162,13 +2161,6 @@ static journal_t *ext3_get_dev_journal(struct super_block *sb,
         if (bdev == NULL)
                 return NULL;
 
-        if (bd_claim(bdev, sb)) {
-                ext3_msg(sb, KERN_ERR,
-                        "error: failed to claim external journal device");
-                blkdev_put(bdev, FMODE_READ|FMODE_WRITE);
-                return NULL;
-        }
-
         blocksize = sb->s_blocksize;
         hblock = bdev_logical_block_size(bdev);
         if (blocksize < hblock) {
diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h
index bab2387fba43..1de65f572033 100644
--- a/fs/ext4/ext4.h
+++ b/fs/ext4/ext4.h
@@ -561,7 +561,7 @@ struct ext4_new_group_data {
 #define EXT4_IOC32_SETVERSION_OLD       FS_IOC32_SETVERSION
 #endif
 
-/* Max physical block we can addres w/o extents */
+/* Max physical block we can address w/o extents */
 #define EXT4_MAX_BLOCK_FILE_PHYS        0xFFFFFFFF
 
 /*
diff --git a/fs/ext4/extents.c b/fs/ext4/extents.c
index e910720e8bb8..c4068f6abf03 100644
--- a/fs/ext4/extents.c
+++ b/fs/ext4/extents.c
@@ -2845,14 +2845,14 @@ fix_extent_len:
  * to an uninitialized extent.
  *
  * Writing to an uninitized extent may result in splitting the uninitialized
- * extent into multiple /intialized unintialized extents (up to three)
+ * extent into multiple /initialized uninitialized extents (up to three)
  * There are three possibilities:
  *   a> There is no split required: Entire extent should be uninitialized
  *   b> Splits in two extents: Write is happening at either end of the extent
  *   c> Splits in three extents: Somone is writing in middle of the extent
  *
  * One of more index blocks maybe needed if the extent tree grow after
- * the unintialized extent split. To prevent ENOSPC occur at the IO
+ * the uninitialized extent split. To prevent ENOSPC occur at the IO
  * complete, we need to split the uninitialized extent before DIO submit
  * the IO. The uninitialized extent called at this time will be split
  * into three uninitialized extent(at most). After IO complete, the part
@@ -3644,6 +3644,10 @@ long ext4_fallocate(struct inode *inode, int mode, loff_t offset, loff_t len)
         struct ext4_map_blocks map;
         unsigned int credits, blkbits = inode->i_blkbits;
 
+        /* We only support the FALLOC_FL_KEEP_SIZE mode */
+        if (mode && (mode != FALLOC_FL_KEEP_SIZE))
+                return -EOPNOTSUPP;
+
         /*
          * currently supporting (pre)allocate mode for extent-based
          * files _only_
diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
index e80fc513eacc..9f7f9e49914f 100644
--- a/fs/ext4/inode.c
+++ b/fs/ext4/inode.c
@@ -39,6 +39,7 @@
 #include <linux/bio.h>
 #include <linux/workqueue.h>
 #include <linux/kernel.h>
+#include <linux/printk.h>
 #include <linux/slab.h>
 #include <linux/ratelimit.h>
 
@@ -3379,7 +3380,7 @@ int ext4_alloc_da_blocks(struct inode *inode)
          * doing I/O at all.
          *
          * We could call write_cache_pages(), and then redirty all of
-         * the pages by calling redirty_page_for_writeback() but that
+         * the pages by calling redirty_page_for_writepage() but that
          * would be ugly in the extreme.  So instead we would need to
          * replicate parts of the code in the above functions,
          * simplifying them becuase we wouldn't actually intend to
@@ -3737,7 +3738,7 @@ static int ext4_set_bh_endio(struct buffer_head *bh, struct inode *inode)
 retry:
         io_end = ext4_init_io_end(inode, GFP_ATOMIC);
         if (!io_end) {
-                pr_warning_ratelimited("%s: allocation fail\n", __func__);
+                pr_warn_ratelimited("%s: allocation fail\n", __func__);
                 schedule();
                 goto retry;
         }
@@ -3761,9 +3762,9 @@ retry:
  * preallocated extents, and those write extend the file, no need to
  * fall back to buffered IO.
  *
- * For holes, we fallocate those blocks, mark them as unintialized
+ * For holes, we fallocate those blocks, mark them as uninitialized
  * If those blocks were preallocated, we mark sure they are splited, but
- * still keep the range to write as unintialized.
+ * still keep the range to write as uninitialized.
  *
  * The unwrritten extents will be converted to written when DIO is completed.
  * For async direct IO, since the IO may still pending when return, we
diff --git a/fs/ext4/super.c b/fs/ext4/super.c
index 29c80f6d8b27..cb10a06775e4 100644
--- a/fs/ext4/super.c
+++ b/fs/ext4/super.c
@@ -657,7 +657,7 @@ static struct block_device *ext4_blkdev_get(dev_t dev, struct super_block *sb)
         struct block_device *bdev;
         char b[BDEVNAME_SIZE];
 
-        bdev = open_by_devnum(dev, FMODE_READ|FMODE_WRITE);
+        bdev = blkdev_get_by_dev(dev, FMODE_READ|FMODE_WRITE|FMODE_EXCL, sb);
         if (IS_ERR(bdev))
                 goto fail;
         return bdev;
@@ -673,8 +673,7 @@ fail:
  */
 static int ext4_blkdev_put(struct block_device *bdev)
 {
-        bd_release(bdev);
-        return blkdev_put(bdev, FMODE_READ|FMODE_WRITE);
+        return blkdev_put(bdev, FMODE_READ|FMODE_WRITE|FMODE_EXCL);
 }
 
 static int ext4_blkdev_remove(struct ext4_sb_info *sbi)
@@ -3778,13 +3777,6 @@ static journal_t *ext4_get_dev_journal(struct super_block *sb,
         if (bdev == NULL)
                 return NULL;
 
-        if (bd_claim(bdev, sb)) {
-                ext4_msg(sb, KERN_ERR,
-                        "failed to claim external journal device");
-                blkdev_put(bdev, FMODE_READ|FMODE_WRITE);
-                return NULL;
-        }
-
         blocksize = sb->s_blocksize;
         hblock = bdev_logical_block_size(bdev);
         if (blocksize < hblock) {
diff --git a/fs/fat/fat.h b/fs/fat/fat.h
index d75a77f85c28..f50408901f7e 100644
--- a/fs/fat/fat.h
+++ b/fs/fat/fat.h
@@ -319,7 +319,8 @@ extern struct inode *fat_build_inode(struct super_block *sb,
                         struct msdos_dir_entry *de, loff_t i_pos);
 extern int fat_sync_inode(struct inode *inode);
 extern int fat_fill_super(struct super_block *sb, void *data, int silent,
-                        const struct inode_operations *fs_dir_inode_ops, int isvfat);
+                        const struct inode_operations *fs_dir_inode_ops,
+                        int isvfat, void (*setup)(struct super_block *));
 
 extern int fat_flush_inodes(struct super_block *sb, struct inode *i1,
                             struct inode *i2);
diff --git a/fs/fat/inode.c b/fs/fat/inode.c
index 206351af7c58..86753fe10bd1 100644
--- a/fs/fat/inode.c
+++ b/fs/fat/inode.c
@@ -703,7 +703,6 @@ static struct dentry *fat_fh_to_dentry(struct super_block *sb,
                 struct fid *fid, int fh_len, int fh_type)
 {
         struct inode *inode = NULL;
-        struct dentry *result;
         u32 *fh = fid->raw;
 
         if (fh_len < 5 || fh_type != 3)
@@ -748,10 +747,7 @@ static struct dentry *fat_fh_to_dentry(struct super_block *sb,
          * the fat_iget lookup again.  If that fails, then we are totally out
          * of luck.  But all that is for another day
          */
-        result = d_obtain_alias(inode);
-        if (!IS_ERR(result))
-                d_set_d_op(result, sb->s_root->d_op);
-        return result;
+        return d_obtain_alias(inode);
 }
 
 static int
@@ -799,8 +795,6 @@ static struct dentry *fat_get_parent(struct dentry *child)
         brelse(bh);
 
         parent = d_obtain_alias(inode);
-        if (!IS_ERR(parent))
-                d_set_d_op(parent, sb->s_root->d_op);
 out:
         unlock_super(sb);
 
@@ -1244,7 +1238,8 @@ static int fat_read_root(struct inode *inode)
  * Read the super block of an MS-DOS FS.
  */
 int fat_fill_super(struct super_block *sb, void *data, int silent,
-                   const struct inode_operations *fs_dir_inode_ops, int isvfat)
+                   const struct inode_operations *fs_dir_inode_ops, int isvfat,
+                   void (*setup)(struct super_block *))
 {
         struct inode *root_inode = NULL, *fat_inode = NULL;
         struct buffer_head *bh;
@@ -1280,6 +1275,8 @@ int fat_fill_super(struct super_block *sb, void *data, int silent,
         if (error)
                 goto out_fail;
 
+        setup(sb); /* flavour-specific stuff that needs options */
+
         error = -EIO;
         sb_min_blocksize(sb, 512);
         bh = sb_bread(sb, 0);
diff --git a/fs/fat/namei_msdos.c b/fs/fat/namei_msdos.c
index 35ffe43afa4b..711499040eb6 100644
--- a/fs/fat/namei_msdos.c
+++ b/fs/fat/namei_msdos.c
@@ -227,11 +227,7 @@ static struct dentry *msdos_lookup(struct inode *dir, struct dentry *dentry,
         }
 out:
         unlock_super(sb);
-        d_set_d_op(dentry, &msdos_dentry_operations);
-        dentry = d_splice_alias(inode, dentry);
-        if (dentry)
-                d_set_d_op(dentry, &msdos_dentry_operations);
-        return dentry;
+        return d_splice_alias(inode, dentry);
 
 error:
         unlock_super(sb);
@@ -661,21 +657,16 @@ static const struct inode_operations msdos_dir_inode_operations = {
         .getattr        = fat_getattr,
 };
 
-static int msdos_fill_super(struct super_block *sb, void *data, int silent)
+static void setup(struct super_block *sb)
 {
-        int res;
-
-        lock_super(sb);
-        res = fat_fill_super(sb, data, silent, &msdos_dir_inode_operations, 0);
-        if (res) {
-                unlock_super(sb);
-                return res;
-        }
-
+        sb->s_d_op = &msdos_dentry_operations;
         sb->s_flags |= MS_NOATIME;
-        d_set_d_op(sb->s_root, &msdos_dentry_operations);
-        unlock_super(sb);
-        return 0;
+}
+
+static int msdos_fill_super(struct super_block *sb, void *data, int silent)
+{
+        return fat_fill_super(sb, data, silent, &msdos_dir_inode_operations,
+                             0, setup);
 }
 
 static struct dentry *msdos_mount(struct file_system_type *fs_type,
diff --git a/fs/fat/namei_vfat.c b/fs/fat/namei_vfat.c
index e3ffc5e12332..f88f752babd9 100644
--- a/fs/fat/namei_vfat.c
+++ b/fs/fat/namei_vfat.c
@@ -772,13 +772,10 @@ static struct dentry *vfat_lookup(struct inode *dir, struct dentry *dentry,
 
 out:
         unlock_super(sb);
-        d_set_d_op(dentry, sb->s_root->d_op);
         dentry->d_time = dentry->d_parent->d_inode->i_version;
         dentry = d_splice_alias(inode, dentry);
-        if (dentry) {
-                d_set_d_op(dentry, sb->s_root->d_op);
+        if (dentry)
                 dentry->d_time = dentry->d_parent->d_inode->i_version;
-        }
         return dentry;
 
 error:
@@ -1066,24 +1063,18 @@ static const struct inode_operations vfat_dir_inode_operations = {
         .getattr        = fat_getattr,
 };
 
-static int vfat_fill_super(struct super_block *sb, void *data, int silent)
+static void setup(struct super_block *sb)
 {
-        int res;
-
-        lock_super(sb);
-        res = fat_fill_super(sb, data, silent, &vfat_dir_inode_operations, 1);
-        if (res) {
-                unlock_super(sb);
-                return res;
-        }
-
         if (MSDOS_SB(sb)->options.name_check != 's')
-                d_set_d_op(sb->s_root, &vfat_ci_dentry_ops);
+                sb->s_d_op = &vfat_ci_dentry_ops;
         else
-                d_set_d_op(sb->s_root, &vfat_dentry_ops);
+                sb->s_d_op = &vfat_dentry_ops;
+}
 
-        unlock_super(sb);
-        return 0;
+static int vfat_fill_super(struct super_block *sb, void *data, int silent)
+{
+        return fat_fill_super(sb, data, silent, &vfat_dir_inode_operations,
+                             1, setup);
 }
 
 static struct dentry *vfat_mount(struct file_system_type *fs_type,
diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c
index 3d06ccc953aa..59c6e4956786 100644
--- a/fs/fs-writeback.c
+++ b/fs/fs-writeback.c
@@ -84,13 +84,9 @@ static inline struct inode *wb_inode(struct list_head *head)
         return list_entry(head, struct inode, i_wb_list);
 }
 
-static void bdi_queue_work(struct backing_dev_info *bdi,
-                struct wb_writeback_work *work)
+/* Wakeup flusher thread or forker thread to fork it. Requires bdi->wb_lock. */
+static void bdi_wakeup_flusher(struct backing_dev_info *bdi)
 {
-        trace_writeback_queue(bdi, work);
-
-        spin_lock_bh(&bdi->wb_lock);
-        list_add_tail(&work->list, &bdi->work_list);
         if (bdi->wb.task) {
                 wake_up_process(bdi->wb.task);
         } else {
@@ -98,15 +94,26 @@ static void bdi_queue_work(struct backing_dev_info *bdi,
                  * The bdi thread isn't there, wake up the forker thread which
                  * will create and run it.
                  */
-                trace_writeback_nothread(bdi, work);
                 wake_up_process(default_backing_dev_info.wb.task);
         }
+}
+
+static void bdi_queue_work(struct backing_dev_info *bdi,
+                           struct wb_writeback_work *work)
+{
+        trace_writeback_queue(bdi, work);
+
+        spin_lock_bh(&bdi->wb_lock);
+        list_add_tail(&work->list, &bdi->work_list);
+        if (!bdi->wb.task)
+                trace_writeback_nothread(bdi, work);
+        bdi_wakeup_flusher(bdi);
         spin_unlock_bh(&bdi->wb_lock);
 }
 
 static void
 __bdi_start_writeback(struct backing_dev_info *bdi, long nr_pages,
-                bool range_cyclic, bool for_background)
+                      bool range_cyclic)
 {
         struct wb_writeback_work *work;
 
@@ -126,7 +133,6 @@ __bdi_start_writeback(struct backing_dev_info *bdi, long nr_pages,
         work->sync_mode = WB_SYNC_NONE;
         work->nr_pages  = nr_pages;
         work->range_cyclic = range_cyclic;
-        work->for_background = for_background;
 
         bdi_queue_work(bdi, work);
 }
@@ -144,7 +150,7 @@ __bdi_start_writeback(struct backing_dev_info *bdi, long nr_pages,
  */
 void bdi_start_writeback(struct backing_dev_info *bdi, long nr_pages)
 {
-        __bdi_start_writeback(bdi, nr_pages, true, false);
+        __bdi_start_writeback(bdi, nr_pages, true);
 }
 
 /**
@@ -152,13 +158,21 @@ void bdi_start_writeback(struct backing_dev_info *bdi, long nr_pages)
  * @bdi: the backing device to write from
  *
  * Description:
- *   This does WB_SYNC_NONE background writeback. The IO is only
- *   started when this function returns, we make no guarentees on
- *   completion. Caller need not hold sb s_umount semaphore.
+ *   This makes sure WB_SYNC_NONE background writeback happens. When
+ *   this function returns, it is only guaranteed that for given BDI
+ *   some IO is happening if we are over background dirty threshold.
+ *   Caller need not hold sb s_umount semaphore.
  */
 void bdi_start_background_writeback(struct backing_dev_info *bdi)
 {
-        __bdi_start_writeback(bdi, LONG_MAX, true, true);
+        /*
+         * We just wake up the flusher thread. It will perform background
+         * writeback as soon as there is no other work to do.
+         */
+        trace_writeback_wake_background(bdi);
+        spin_lock_bh(&bdi->wb_lock);
+        bdi_wakeup_flusher(bdi);
+        spin_unlock_bh(&bdi->wb_lock);
 }
 
 /*
@@ -616,6 +630,7 @@ static long wb_writeback(struct bdi_writeback *wb,
         };
         unsigned long oldest_jif;
         long wrote = 0;
+        long write_chunk;
         struct inode *inode;
 
         if (wbc.for_kupdate) {
@@ -628,6 +643,24 @@ static long wb_writeback(struct bdi_writeback *wb,
                 wbc.range_end = LLONG_MAX;
         }
 
+        /*
+         * WB_SYNC_ALL mode does livelock avoidance by syncing dirty
+         * inodes/pages in one big loop. Setting wbc.nr_to_write=LONG_MAX
+         * here avoids calling into writeback_inodes_wb() more than once.
+         *
+         * The intended call sequence for WB_SYNC_ALL writeback is:
+         *
+         *      wb_writeback()
+         *          __writeback_inodes_sb()     <== called only once
+         *              write_cache_pages()     <== called once for each inode
+         *                   (quickly) tag currently dirty pages
+         *                   (maybe slowly) sync all tagged pages
+         */
+        if (wbc.sync_mode == WB_SYNC_NONE)
+                write_chunk = MAX_WRITEBACK_PAGES;
+        else
+                write_chunk = LONG_MAX;
+
         wbc.wb_start = jiffies; /* livelock avoidance */
         for (;;) {
                 /*
@@ -637,6 +670,16 @@ static long wb_writeback(struct bdi_writeback *wb,
                         break;
 
                 /*
+                 * Background writeout and kupdate-style writeback may
+                 * run forever. Stop them if there is other work to do
+                 * so that e.g. sync can proceed. They'll be restarted
+                 * after the other works are all done.
+                 */
+                if ((work->for_background || work->for_kupdate) &&
+                    !list_empty(&wb->bdi->work_list))
+                        break;
+
+                /*
                  * For background writeout, stop when we are below the
                  * background dirty threshold
                  */
@@ -644,7 +687,7 @@ static long wb_writeback(struct bdi_writeback *wb,
                         break;
 
                 wbc.more_io = 0;
-                wbc.nr_to_write = MAX_WRITEBACK_PAGES;
+                wbc.nr_to_write = write_chunk;
                 wbc.pages_skipped = 0;
 
                 trace_wbc_writeback_start(&wbc, wb->bdi);
@@ -654,8 +697,8 @@ static long wb_writeback(struct bdi_writeback *wb,
                         writeback_inodes_wb(wb, &wbc);
                 trace_wbc_writeback_written(&wbc, wb->bdi);
 
-                work->nr_pages -= MAX_WRITEBACK_PAGES - wbc.nr_to_write;
-                wrote += MAX_WRITEBACK_PAGES - wbc.nr_to_write;
+                work->nr_pages -= write_chunk - wbc.nr_to_write;
+                wrote += write_chunk - wbc.nr_to_write;
 
                 /*
                  * If we consumed everything, see if we have more
@@ -670,7 +713,7 @@ static long wb_writeback(struct bdi_writeback *wb,
                 /*
                  * Did we write something? Try for more
                  */
-                if (wbc.nr_to_write < MAX_WRITEBACK_PAGES)
+                if (wbc.nr_to_write < write_chunk)
                         continue;
                 /*
                  * Nothing written. Wait for some inode to
@@ -718,6 +761,23 @@ static unsigned long get_nr_dirty_pages(void)
                 get_nr_dirty_inodes();
 }
 
+static long wb_check_background_flush(struct bdi_writeback *wb)
+{
+        if (over_bground_thresh()) {
+
+                struct wb_writeback_work work = {
+                        .nr_pages       = LONG_MAX,
+                        .sync_mode      = WB_SYNC_NONE,
+                        .for_background = 1,
+                        .range_cyclic   = 1,
+                };
+
+                return wb_writeback(wb, &work);
+        }
+
+        return 0;
+}
+
 static long wb_check_old_data_flush(struct bdi_writeback *wb)
 {
         unsigned long expired;
@@ -787,6 +847,7 @@ long wb_do_writeback(struct bdi_writeback *wb, int force_wait)
          * Check for periodic writeback, kupdated() style
          */
         wrote += wb_check_old_data_flush(wb);
+        wrote += wb_check_background_flush(wb);
         clear_bit(BDI_writeback_running, &wb->bdi->state);
 
         return wrote;
@@ -873,7 +934,7 @@ void wakeup_flusher_threads(long nr_pages)
         list_for_each_entry_rcu(bdi, &bdi_list, bdi_list) {
                 if (!bdi_has_dirty_io(bdi))
                         continue;
-                __bdi_start_writeback(bdi, nr_pages, false, false);
+                __bdi_start_writeback(bdi, nr_pages, false);
         }
         rcu_read_unlock();
 }
@@ -1164,7 +1225,7 @@ EXPORT_SYMBOL(writeback_inodes_sb_nr_if_idle);
  * @sb: the superblock
  *
  * This function writes and waits on any dirty inode belonging to this
- * super_block. The number of pages synced is returned.
+ * super_block.
  */
 void sync_inodes_sb(struct super_block *sb)
 {
@@ -1242,11 +1303,11 @@ int sync_inode(struct inode *inode, struct writeback_control *wbc)
 EXPORT_SYMBOL(sync_inode);
 
 /**
- * sync_inode - write an inode to disk
+ * sync_inode_metadata - write an inode to disk
  * @inode: the inode to sync
  * @wait: wait for I/O to complete.
  *
- * Write an inode to disk and adjust it's dirty state after completion.
+ * Write an inode to disk and adjust its dirty state after completion.
  *
  * Note: only writes the actual inode, no associated data or other metadata.
  */
diff --git a/fs/fuse/dir.c b/fs/fuse/dir.c
index 042af7346ec1..bfed8447ed80 100644
--- a/fs/fuse/dir.c
+++ b/fs/fuse/dir.c
@@ -350,7 +350,6 @@ static struct dentry *fuse_lookup(struct inode *dir, struct dentry *entry,
         }
 
         entry = newent ? newent : entry;
-        d_set_d_op(entry, &fuse_dentry_operations);
         if (outarg_valid)
                 fuse_change_entry_timeout(entry, &outarg);
         else
diff --git a/fs/fuse/inode.c b/fs/fuse/inode.c
index f62b32cffea9..9e3f68cc1bd1 100644
--- a/fs/fuse/inode.c
+++ b/fs/fuse/inode.c
@@ -617,10 +617,8 @@ static struct dentry *fuse_get_dentry(struct super_block *sb,
                 goto out_iput;
 
         entry = d_obtain_alias(inode);
-        if (!IS_ERR(entry) && get_node_id(inode) != FUSE_ROOT_ID) {
-                d_set_d_op(entry, &fuse_dentry_operations);
+        if (!IS_ERR(entry) && get_node_id(inode) != FUSE_ROOT_ID)
                 fuse_invalidate_entry_cache(entry);
-        }
 
         return entry;
 
@@ -719,10 +717,8 @@ static struct dentry *fuse_get_parent(struct dentry *child)
         }
 
         parent = d_obtain_alias(inode);
-        if (!IS_ERR(parent) && get_node_id(inode) != FUSE_ROOT_ID) {
-                d_set_d_op(parent, &fuse_dentry_operations);
+        if (!IS_ERR(parent) && get_node_id(inode) != FUSE_ROOT_ID)
                 fuse_invalidate_entry_cache(parent);
-        }
 
         return parent;
 }
@@ -989,6 +985,8 @@ static int fuse_fill_super(struct super_block *sb, void *data, int silent)
                 iput(root);
                 goto err_put_conn;
         }
+        /* only now - we want root dentry with NULL ->d_op */
+        sb->s_d_op = &fuse_dentry_operations;
 
         init_req = fuse_request_alloc();
         if (!init_req)
diff --git a/fs/gfs2/export.c b/fs/gfs2/export.c
index 97012ecff560..9023db8184f9 100644
--- a/fs/gfs2/export.c
+++ b/fs/gfs2/export.c
@@ -126,12 +126,7 @@ static int gfs2_get_name(struct dentry *parent, char *name,
 
 static struct dentry *gfs2_get_parent(struct dentry *child)
 {
-        struct dentry *dentry;
-
-        dentry = d_obtain_alias(gfs2_lookupi(child->d_inode, &gfs2_qdotdot, 1));
-        if (!IS_ERR(dentry))
-                d_set_d_op(dentry, &gfs2_dops);
-        return dentry;
+        return d_obtain_alias(gfs2_lookupi(child->d_inode, &gfs2_qdotdot, 1));
 }
 
 static struct dentry *gfs2_get_dentry(struct super_block *sb,
@@ -139,7 +134,6 @@ static struct dentry *gfs2_get_dentry(struct super_block *sb,
 {
         struct gfs2_sbd *sdp = sb->s_fs_info;
         struct inode *inode;
-        struct dentry *dentry;
 
         inode = gfs2_ilookup(sb, inum->no_addr);
         if (inode) {
@@ -156,10 +150,7 @@ static struct dentry *gfs2_get_dentry(struct super_block *sb,
                 return ERR_CAST(inode);
 
 out_inode:
-        dentry = d_obtain_alias(inode);
-        if (!IS_ERR(dentry))
-                d_set_d_op(dentry, &gfs2_dops);
-        return dentry;
+        return d_obtain_alias(inode);
 }
 
 static struct dentry *gfs2_fh_to_dentry(struct super_block *sb, struct fid *fid,
diff --git a/fs/gfs2/ops_fstype.c b/fs/gfs2/ops_fstype.c
index 2aeabd4218cc..777927ce6f79 100644
--- a/fs/gfs2/ops_fstype.c
+++ b/fs/gfs2/ops_fstype.c
@@ -440,7 +440,6 @@ static int gfs2_lookup_root(struct super_block *sb, struct dentry **dptr,
                 iput(inode);
                 return -ENOMEM;
         }
-        d_set_d_op(dentry, &gfs2_dops);
         *dptr = dentry;
         return 0;
 }
@@ -1106,6 +1105,7 @@ static int fill_super(struct super_block *sb, struct gfs2_args *args, int silent
 
         sb->s_magic = GFS2_MAGIC;
         sb->s_op = &gfs2_super_ops;
+        sb->s_d_op = &gfs2_dops;
         sb->s_export_op = &gfs2_export_ops;
         sb->s_xattr = gfs2_xattr_handlers;
         sb->s_qcop = &gfs2_quotactl_ops;
@@ -1268,7 +1268,7 @@ static struct dentry *gfs2_mount(struct file_system_type *fs_type, int flags,
 {
         struct block_device *bdev;
         struct super_block *s;
-        fmode_t mode = FMODE_READ;
+        fmode_t mode = FMODE_READ | FMODE_EXCL;
         int error;
         struct gfs2_args args;
         struct gfs2_sbd *sdp;
@@ -1276,7 +1276,7 @@ static struct dentry *gfs2_mount(struct file_system_type *fs_type, int flags,
         if (!(flags & MS_RDONLY))
                 mode |= FMODE_WRITE;
 
-        bdev = open_bdev_exclusive(dev_name, mode, fs_type);
+        bdev = blkdev_get_by_path(dev_name, mode, fs_type);
         if (IS_ERR(bdev))
                 return ERR_CAST(bdev);
 
@@ -1298,7 +1298,7 @@ static struct dentry *gfs2_mount(struct file_system_type *fs_type, int flags,
                 goto error_bdev;
 
         if (s->s_root)
-                close_bdev_exclusive(bdev, mode);
+                blkdev_put(bdev, mode);
 
         memset(&args, 0, sizeof(args));
         args.ar_quota = GFS2_QUOTA_DEFAULT;
@@ -1342,7 +1342,7 @@ error_super:
         deactivate_locked_super(s);
         return ERR_PTR(error);
 error_bdev:
-        close_bdev_exclusive(bdev, mode);
+        blkdev_put(bdev, mode);
         return ERR_PTR(error);
 }
 
diff --git a/fs/gfs2/ops_inode.c b/fs/gfs2/ops_inode.c
index 1501db4f0e6d..040b5a2e6556 100644
--- a/fs/gfs2/ops_inode.c
+++ b/fs/gfs2/ops_inode.c
@@ -106,8 +106,6 @@ static struct dentry *gfs2_lookup(struct inode *dir, struct dentry *dentry,
 {
         struct inode *inode = NULL;
 
-        d_set_d_op(dentry, &gfs2_dops);
-
         inode = gfs2_lookupi(dir, &dentry->d_name, 0);
         if (inode && IS_ERR(inode))
                 return ERR_CAST(inode);
@@ -1427,6 +1425,10 @@ static long gfs2_fallocate(struct inode *inode, int mode, loff_t offset,
         loff_t next = (offset + len - 1) >> sdp->sd_sb.sb_bsize_shift;
         next = (next + 1) << sdp->sd_sb.sb_bsize_shift;
 
+        /* We only support the FALLOC_FL_KEEP_SIZE mode */
+        if (mode && (mode != FALLOC_FL_KEEP_SIZE))
+                return -EOPNOTSUPP;
+
         offset = (offset >> sdp->sd_sb.sb_bsize_shift) <<
                  sdp->sd_sb.sb_bsize_shift;
 
diff --git a/fs/hfs/dir.c b/fs/hfs/dir.c
index ea4aefe7c652..afa66aaa2237 100644
--- a/fs/hfs/dir.c
+++ b/fs/hfs/dir.c
@@ -25,8 +25,6 @@ static struct dentry *hfs_lookup(struct inode *dir, struct dentry *dentry,
         struct inode *inode = NULL;
         int res;
 
-        d_set_d_op(dentry, &hfs_dentry_operations);
-
         hfs_find_init(HFS_SB(dir->i_sb)->cat_tree, &fd);
         hfs_cat_build_key(dir->i_sb, fd.search_key, dir->i_ino, &dentry->d_name);
         res = hfs_brec_read(&fd, &rec, sizeof(rec));
diff --git a/fs/hfs/super.c b/fs/hfs/super.c
index 0bef62aa4f42..1b55f704fb22 100644
--- a/fs/hfs/super.c
+++ b/fs/hfs/super.c
@@ -429,13 +429,12 @@ static int hfs_fill_super(struct super_block *sb, void *data, int silent)
         if (!root_inode)
                 goto bail_no_root;
 
+        sb->s_d_op = &hfs_dentry_operations;
         res = -ENOMEM;
         sb->s_root = d_alloc_root(root_inode);
         if (!sb->s_root)
                 goto bail_iput;
 
-        d_set_d_op(sb->s_root, &hfs_dentry_operations);
-
         /* everything's okay */
         return 0;
 
diff --git a/fs/hfsplus/dir.c b/fs/hfsplus/dir.c
index f896dc843026..4df5059c25da 100644
--- a/fs/hfsplus/dir.c
+++ b/fs/hfsplus/dir.c
@@ -37,7 +37,6 @@ static struct dentry *hfsplus_lookup(struct inode *dir, struct dentry *dentry,
 
         sb = dir->i_sb;
 
-        d_set_d_op(dentry, &hfsplus_dentry_operations);
         dentry->d_fsdata = NULL;
         hfs_find_init(HFSPLUS_SB(sb)->cat_tree, &fd);
         hfsplus_cat_build_key(sb, fd.search_key, dir->i_ino, &dentry->d_name);
diff --git a/fs/hfsplus/super.c b/fs/hfsplus/super.c
index 6ee6ad20acf2..9a3b4795f43c 100644
--- a/fs/hfsplus/super.c
+++ b/fs/hfsplus/super.c
@@ -444,13 +444,13 @@ static int hfsplus_fill_super(struct super_block *sb, void *data, int silent)
                 err = PTR_ERR(root);
                 goto cleanup;
         }
+        sb->s_d_op = &hfsplus_dentry_operations;
         sb->s_root = d_alloc_root(root);
         if (!sb->s_root) {
                 iput(root);
                 err = -ENOMEM;
                 goto cleanup;
         }
-        d_set_d_op(sb->s_root, &hfsplus_dentry_operations);
 
         str.len = sizeof(HFSP_HIDDENDIR_NAME) - 1;
         str.name = HFSP_HIDDENDIR_NAME;
diff --git a/fs/hostfs/hostfs_kern.c b/fs/hostfs/hostfs_kern.c
index d3244d949a4e..2638c834ed28 100644
--- a/fs/hostfs/hostfs_kern.c
+++ b/fs/hostfs/hostfs_kern.c
@@ -612,7 +612,6 @@ struct dentry *hostfs_lookup(struct inode *ino, struct dentry *dentry,
                 goto out_put;
 
         d_add(dentry, inode);
-        d_set_d_op(dentry, &hostfs_dentry_ops);
         return NULL;
 
  out_put:
@@ -922,6 +921,7 @@ static int hostfs_fill_sb_common(struct super_block *sb, void *d, int silent)
         sb->s_blocksize_bits = 10;
         sb->s_magic = HOSTFS_SUPER_MAGIC;
         sb->s_op = &hostfs_sbops;
+        sb->s_d_op = &hostfs_dentry_ops;
         sb->s_maxbytes = MAX_LFS_FILESIZE;
 
         /* NULL is printed as <NULL> by sprintf: avoid that. */
diff --git a/fs/hpfs/dentry.c b/fs/hpfs/dentry.c
index 32c13a94e1e9..05d4816e4e77 100644
--- a/fs/hpfs/dentry.c
+++ b/fs/hpfs/dentry.c
@@ -58,12 +58,7 @@ static int hpfs_compare_dentry(const struct dentry *parent,
         return 0;
 }
 
-static const struct dentry_operations hpfs_dentry_operations = {
+const struct dentry_operations hpfs_dentry_operations = {
         .d_hash         = hpfs_hash_dentry,
         .d_compare      = hpfs_compare_dentry,
 };
-
-void hpfs_set_dentry_operations(struct dentry *dentry)
-{
-        d_set_d_op(dentry, &hpfs_dentry_operations);
-}
diff --git a/fs/hpfs/dir.c b/fs/hpfs/dir.c
index 2338130cceba..d32f63a569f7 100644
--- a/fs/hpfs/dir.c
+++ b/fs/hpfs/dir.c
@@ -298,7 +298,6 @@ struct dentry *hpfs_lookup(struct inode *dir, struct dentry *dentry, struct name
 
         end:
         end_add:
-        hpfs_set_dentry_operations(dentry);
         unlock_kernel();
         d_add(dentry, result);
         return NULL;
diff --git a/fs/hpfs/hpfs_fn.h b/fs/hpfs/hpfs_fn.h
index 2fee17d0d9ab..1c43dbea55e8 100644
--- a/fs/hpfs/hpfs_fn.h
+++ b/fs/hpfs/hpfs_fn.h
@@ -233,7 +233,7 @@ void hpfs_mark_4buffers_dirty(struct quad_buffer_head *);
 
 /* dentry.c */
 
-void hpfs_set_dentry_operations(struct dentry *);
+extern const struct dentry_operations hpfs_dentry_operations;
 
 /* dir.c */
 
diff --git a/fs/hpfs/super.c b/fs/hpfs/super.c
index 49935ba78db8..b30426b1fc97 100644
--- a/fs/hpfs/super.c
+++ b/fs/hpfs/super.c
@@ -550,6 +550,7 @@ static int hpfs_fill_super(struct super_block *s, void *options, int silent)
         /* Fill superblock stuff */
         s->s_magic = HPFS_SUPER_MAGIC;
         s->s_op = &hpfs_sops;
+        s->s_d_op = &hpfs_dentry_operations;
 
         sbi->sb_root = superblock->root;
         sbi->sb_fs_size = superblock->n_sectors;
@@ -651,7 +652,6 @@ static int hpfs_fill_super(struct super_block *s, void *options, int silent)
                 iput(root);
                 goto bail0;
         }
-        hpfs_set_dentry_operations(s->s_root);
 
         /*
          * find the root directory's . pointer & finish filling in the inode
diff --git a/fs/isofs/inode.c b/fs/isofs/inode.c
index 844a7903c72f..a0f3833c0dbf 100644
--- a/fs/isofs/inode.c
+++ b/fs/isofs/inode.c
@@ -939,17 +939,18 @@ root_found:
                 goto out_iput;
         }
 
-        /* get the root dentry */
-        s->s_root = d_alloc_root(inode);
-        if (!(s->s_root))
-                goto out_no_root;
-
         table = 0;
         if (joliet_level)
                 table += 2;
         if (opt.check == 'r')
                 table++;
-        d_set_d_op(s->s_root, &isofs_dentry_ops[table]);
+
+        s->s_d_op = &isofs_dentry_ops[table];
+
+        /* get the root dentry */
+        s->s_root = d_alloc_root(inode);
+        if (!(s->s_root))
+                goto out_no_root;
 
         kfree(opt.iocharset);
 
diff --git a/fs/isofs/namei.c b/fs/isofs/namei.c
index 679a849c3b27..4fb3e8074fd4 100644
--- a/fs/isofs/namei.c
+++ b/fs/isofs/namei.c
@@ -172,8 +172,6 @@ struct dentry *isofs_lookup(struct inode *dir, struct dentry *dentry, struct nam
         struct inode *inode;
         struct page *page;
 
-        d_set_d_op(dentry, dir->i_sb->s_root->d_op);
-
         page = alloc_page(GFP_USER);
         if (!page)
                 return ERR_PTR(-ENOMEM);
diff --git a/fs/jbd/transaction.c b/fs/jbd/transaction.c
index 846a3f314111..5b2e4c30a2a1 100644
--- a/fs/jbd/transaction.c
+++ b/fs/jbd/transaction.c
@@ -207,7 +207,7 @@ repeat_locked:
          * the committing transaction.  Really, we only need to give it
          * committing_transaction->t_outstanding_credits plus "enough" for
          * the log control blocks.
-         * Also, this test is inconsitent with the matching one in
+         * Also, this test is inconsistent with the matching one in
          * journal_extend().
          */
         if (__log_space_left(journal) < jbd_space_needed(journal)) {
diff --git a/fs/jbd2/transaction.c b/fs/jbd2/transaction.c
index 394893242ae3..faad2bd787c7 100644
--- a/fs/jbd2/transaction.c
+++ b/fs/jbd2/transaction.c
@@ -251,7 +251,7 @@ repeat:
          * the committing transaction.  Really, we only need to give it
          * committing_transaction->t_outstanding_credits plus "enough" for
          * the log control blocks.
-         * Also, this test is inconsitent with the matching one in
+         * Also, this test is inconsistent with the matching one in
          * jbd2_journal_extend().
          */
         if (__jbd2_log_space_left(journal) < jbd_space_needed(journal)) {
diff --git a/fs/jfs/jfs_logmgr.c b/fs/jfs/jfs_logmgr.c
index e1b8493b9aaa..278e3fb40b71 100644
--- a/fs/jfs/jfs_logmgr.c
+++ b/fs/jfs/jfs_logmgr.c
@@ -1120,16 +1120,13 @@ int lmLogOpen(struct super_block *sb)
          * file systems to log may have n-to-1 relationship;
          */
 
-        bdev = open_by_devnum(sbi->logdev, FMODE_READ|FMODE_WRITE);
+        bdev = blkdev_get_by_dev(sbi->logdev, FMODE_READ|FMODE_WRITE|FMODE_EXCL,
+                                 log);
         if (IS_ERR(bdev)) {
                 rc = -PTR_ERR(bdev);
                 goto free;
         }
 
-        if ((rc = bd_claim(bdev, log))) {
-                goto close;
-        }
-
         log->bdev = bdev;
         memcpy(log->uuid, sbi->loguuid, sizeof(log->uuid));
 
@@ -1137,7 +1134,7 @@ int lmLogOpen(struct super_block *sb)
          * initialize log:
          */
         if ((rc = lmLogInit(log)))
-                goto unclaim;
+                goto close;
 
         list_add(&log->journal_list, &jfs_external_logs);
 
@@ -1163,11 +1160,8 @@ journal_found:
         list_del(&log->journal_list);
         lbmLogShutdown(log);
 
-      unclaim:
-        bd_release(bdev);
-
       close:            /* close external log device */
-        blkdev_put(bdev, FMODE_READ|FMODE_WRITE);
+        blkdev_put(bdev, FMODE_READ|FMODE_WRITE|FMODE_EXCL);
 
       free:             /* free log descriptor */
         mutex_unlock(&jfs_log_mutex);
@@ -1512,8 +1506,7 @@ int lmLogClose(struct super_block *sb)
         bdev = log->bdev;
         rc = lmLogShutdown(log);
 
-        bd_release(bdev);
-        blkdev_put(bdev, FMODE_READ|FMODE_WRITE);
+        blkdev_put(bdev, FMODE_READ|FMODE_WRITE|FMODE_EXCL);
 
         kfree(log);
 
diff --git a/fs/jfs/namei.c b/fs/jfs/namei.c
index 4414e3a42264..81ead850ddb6 100644
--- a/fs/jfs/namei.c
+++ b/fs/jfs/namei.c
@@ -1465,9 +1465,6 @@ static struct dentry *jfs_lookup(struct inode *dip, struct dentry *dentry, struc
 
         jfs_info("jfs_lookup: name = %s", name);
 
-        if (JFS_SBI(dip->i_sb)->mntflag & JFS_OS2)
-                d_set_d_op(dentry, &jfs_ci_dentry_operations);
-
         if ((name[0] == '.') && (len == 1))
                 inum = dip->i_ino;
         else if (strcmp(name, "..") == 0)
@@ -1492,12 +1489,7 @@ static struct dentry *jfs_lookup(struct inode *dip, struct dentry *dentry, struc
                 return ERR_CAST(ip);
         }
 
-        dentry = d_splice_alias(ip, dentry);
-
-        if (dentry && (JFS_SBI(dip->i_sb)->mntflag & JFS_OS2))
-                d_set_d_op(dentry, &jfs_ci_dentry_operations);
-
-        return dentry;
+        return d_splice_alias(ip, dentry);
 }
 
 static struct inode *jfs_nfs_get_inode(struct super_block *sb,
diff --git a/fs/jfs/super.c b/fs/jfs/super.c
index 3150d766e0d4..eeca48a031ab 100644
--- a/fs/jfs/super.c
+++ b/fs/jfs/super.c
@@ -515,6 +515,9 @@ static int jfs_fill_super(struct super_block *sb, void *data, int silent)
 
         sb->s_magic = JFS_SUPER_MAGIC;
 
+        if (sbi->mntflag & JFS_OS2)
+                sb->s_d_op = &jfs_ci_dentry_operations;
+
         inode = jfs_iget(sb, ROOT_I);
         if (IS_ERR(inode)) {
                 ret = PTR_ERR(inode);
@@ -524,9 +527,6 @@ static int jfs_fill_super(struct super_block *sb, void *data, int silent)
         if (!sb->s_root)
                 goto out_no_root;
 
-        if (sbi->mntflag & JFS_OS2)
-                d_set_d_op(sb->s_root, &jfs_ci_dentry_operations);
-
         /* logical blocks are represented by 40 bits in pxd_t, etc. */
         sb->s_maxbytes = ((u64) sb->s_blocksize) << 40;
 #if BITS_PER_LONG == 32
diff --git a/fs/libfs.c b/fs/libfs.c
index 889311e3d06b..c88eab55aec9 100644
--- a/fs/libfs.c
+++ b/fs/libfs.c
@@ -217,7 +217,8 @@ static const struct super_operations simple_super_operations = {
  * will never be mountable)
  */
 struct dentry *mount_pseudo(struct file_system_type *fs_type, char *name,
-        const struct super_operations *ops, unsigned long magic)
+        const struct super_operations *ops,
+        const struct dentry_operations *dops, unsigned long magic)
 {
         struct super_block *s = sget(fs_type, NULL, set_anon_super, NULL);
         struct dentry *dentry;
@@ -254,6 +255,7 @@ struct dentry *mount_pseudo(struct file_system_type *fs_type, char *name,
         dentry->d_parent = dentry;
         d_instantiate(dentry, root);
         s->s_root = dentry;
+        s->s_d_op = dops;
         s->s_flags |= MS_ACTIVE;
         return dget(s->s_root);
 
diff --git a/fs/logfs/dev_bdev.c b/fs/logfs/dev_bdev.c
index 92ca6fbe09bd..723bc5bca09a 100644
--- a/fs/logfs/dev_bdev.c
+++ b/fs/logfs/dev_bdev.c
@@ -300,7 +300,7 @@ static int bdev_write_sb(struct super_block *sb, struct page *page)
 
 static void bdev_put_device(struct logfs_super *s)
 {
-        close_bdev_exclusive(s->s_bdev, FMODE_READ|FMODE_WRITE);
+        blkdev_put(s->s_bdev, FMODE_READ|FMODE_WRITE|FMODE_EXCL);
 }
 
 static int bdev_can_write_buf(struct super_block *sb, u64 ofs)
@@ -325,13 +325,14 @@ int logfs_get_sb_bdev(struct logfs_super *p, struct file_system_type *type,
 {
         struct block_device *bdev;
 
-        bdev = open_bdev_exclusive(devname, FMODE_READ|FMODE_WRITE, type);
+        bdev = blkdev_get_by_path(devname, FMODE_READ|FMODE_WRITE|FMODE_EXCL,
+                                  type);
         if (IS_ERR(bdev))
                 return PTR_ERR(bdev);
 
         if (MAJOR(bdev->bd_dev) == MTD_BLOCK_MAJOR) {
                 int mtdnr = MINOR(bdev->bd_dev);
-                close_bdev_exclusive(bdev, FMODE_READ|FMODE_WRITE);
+                blkdev_put(bdev, FMODE_READ|FMODE_WRITE|FMODE_EXCL);
                 return logfs_get_sb_mtd(p, mtdnr);
         }
 
diff --git a/fs/minix/namei.c b/fs/minix/namei.c
index 1b9e07728a9f..ce7337ddfdbf 100644
--- a/fs/minix/namei.c
+++ b/fs/minix/namei.c
@@ -23,8 +23,6 @@ static struct dentry *minix_lookup(struct inode * dir, struct dentry *dentry, st
         struct inode * inode = NULL;
         ino_t ino;
 
-        d_set_d_op(dentry, dir->i_sb->s_root->d_op);
-
         if (dentry->d_name.len > minix_sb(dir->i_sb)->s_namelen)
                 return ERR_PTR(-ENAMETOOLONG);
 
diff --git a/fs/mpage.c b/fs/mpage.c
index fd56ca2ea556..d78455a81ec9 100644
--- a/fs/mpage.c
+++ b/fs/mpage.c
@@ -40,7 +40,7 @@
  * status of that page is hard.  See end_buffer_async_read() for the details.
  * There is no point in duplicating all that complexity.
  */
-static void mpage_end_io_read(struct bio *bio, int err)
+static void mpage_end_io(struct bio *bio, int err)
 {
         const int uptodate = test_bit(BIO_UPTODATE, &bio->bi_flags);
         struct bio_vec *bvec = bio->bi_io_vec + bio->bi_vcnt - 1;
@@ -50,44 +50,29 @@ static void mpage_end_io_read(struct bio *bio, int err)
 
                 if (--bvec >= bio->bi_io_vec)
                         prefetchw(&bvec->bv_page->flags);
-
-                if (uptodate) {
-                        SetPageUptodate(page);
-                } else {
-                        ClearPageUptodate(page);
-                        SetPageError(page);
-                }
-                unlock_page(page);
-        } while (bvec >= bio->bi_io_vec);
-        bio_put(bio);
-}
-
-static void mpage_end_io_write(struct bio *bio, int err)
-{
-        const int uptodate = test_bit(BIO_UPTODATE, &bio->bi_flags);
-        struct bio_vec *bvec = bio->bi_io_vec + bio->bi_vcnt - 1;
-
-        do {
-                struct page *page = bvec->bv_page;
-
-                if (--bvec >= bio->bi_io_vec)
-                        prefetchw(&bvec->bv_page->flags);
-
-                if (!uptodate){
-                        SetPageError(page);
-                        if (page->mapping)
-                                set_bit(AS_EIO, &page->mapping->flags);
+                if (bio_data_dir(bio) == READ) {
+                        if (uptodate) {
+                                SetPageUptodate(page);
+                        } else {
+                                ClearPageUptodate(page);
+                                SetPageError(page);
+                        }
+                        unlock_page(page);
+                } else { /* bio_data_dir(bio) == WRITE */
+                        if (!uptodate) {
+                                SetPageError(page);
+                                if (page->mapping)
+                                        set_bit(AS_EIO, &page->mapping->flags);
+                        }
+                        end_page_writeback(page);
                 }
-                end_page_writeback(page);
         } while (bvec >= bio->bi_io_vec);
         bio_put(bio);
 }
 
 static struct bio *mpage_bio_submit(int rw, struct bio *bio)
 {
-        bio->bi_end_io = mpage_end_io_read;
-        if (rw == WRITE)
-                bio->bi_end_io = mpage_end_io_write;
+        bio->bi_end_io = mpage_end_io;
         submit_bio(rw, bio);
         return NULL;
 }
diff --git a/fs/namei.c b/fs/namei.c
index 24ece10470b6..86643302079e 100644
--- a/fs/namei.c
+++ b/fs/namei.c
@@ -479,6 +479,14 @@ static int nameidata_dentry_drop_rcu(struct nameidata *nd, struct dentry *dentry
         struct fs_struct *fs = current->fs;
         struct dentry *parent = nd->path.dentry;
 
+        /*
+         * It can be possible to revalidate the dentry that we started
+         * the path walk with. force_reval_path may also revalidate the
+         * dentry already committed to the nameidata.
+         */
+        if (unlikely(parent == dentry))
+                return nameidata_drop_rcu(nd);
+
         BUG_ON(!(nd->flags & LOOKUP_RCU));
         if (nd->root.mnt) {
                 spin_lock(&fs->lock);
@@ -583,6 +591,13 @@ void release_open_intent(struct nameidata *nd)
                 fput(nd->intent.open.file);
 }
 
+/*
+ * Call d_revalidate and handle filesystems that request rcu-walk
+ * to be dropped. This may be called and return in rcu-walk mode,
+ * regardless of success or error. If -ECHILD is returned, the caller
+ * must return -ECHILD back up the path walk stack so path walk may
+ * be restarted in ref-walk mode.
+ */
 static int d_revalidate(struct dentry *dentry, struct nameidata *nd)
 {
         int status;
@@ -673,6 +688,9 @@ force_reval_path(struct path *path, struct nameidata *nd)
                 return 0;
 
         if (!status) {
+                /* Don't d_invalidate in rcu-walk mode */
+                if (nameidata_drop_rcu(nd))
+                        return -ECHILD;
                 d_invalidate(dentry);
                 status = -ESTALE;
         }
@@ -1950,8 +1968,9 @@ int may_open(struct path *path, int acc_mode, int flag)
         return break_lease(inode, flag);
 }
 
-static int handle_truncate(struct path *path)
+static int handle_truncate(struct file *filp)
 {
+        struct path *path = &filp->f_path;
         struct inode *inode = path->dentry->d_inode;
         int error = get_write_access(inode);
         if (error)
@@ -1965,7 +1984,7 @@ static int handle_truncate(struct path *path)
         if (!error) {
                 error = do_truncate(path->dentry, 0,
                                     ATTR_MTIME|ATTR_CTIME|ATTR_OPEN,
-                                    NULL);
+                                    filp);
         }
         put_write_access(inode);
         return error;
@@ -2063,7 +2082,7 @@ static struct file *finish_open(struct nameidata *nd,
         }
         if (!IS_ERR(filp)) {
                 if (will_truncate) {
-                        error = handle_truncate(&nd->path);
+                        error = handle_truncate(filp);
                         if (error) {
                                 fput(filp);
                                 filp = ERR_PTR(error);
@@ -2104,11 +2123,13 @@ static struct file *do_last(struct nameidata *nd, struct path *path,
                 dir = nd->path.dentry;
         case LAST_DOT:
                 if (need_reval_dot(dir)) {
-                        error = d_revalidate(nd->path.dentry, nd);
-                        if (!error)
-                                error = -ESTALE;
-                        if (error < 0)
+                        int status = d_revalidate(nd->path.dentry, nd);
+                        if (!status)
+                                status = -ESTALE;
+                        if (status < 0) {
+                                error = status;
                                 goto exit;
+                        }
                 }
                 /* fallthrough */
         case LAST_ROOT:
diff --git a/fs/ncpfs/dir.c b/fs/ncpfs/dir.c
index 28f136d4aaec..f6946bb5cb55 100644
--- a/fs/ncpfs/dir.c
+++ b/fs/ncpfs/dir.c
@@ -21,9 +21,7 @@
 #include <asm/uaccess.h>
 #include <asm/byteorder.h>
 
-#include <linux/ncp_fs.h>
-
-#include "ncplib_kernel.h"
+#include "ncp_fs.h"
 
 static void ncp_read_volume_list(struct file *, void *, filldir_t,
                                 struct ncp_cache_control *);
@@ -82,7 +80,7 @@ static int ncp_compare_dentry(const struct dentry *, const struct inode *,
                 unsigned int, const char *, const struct qstr *);
 static int ncp_delete_dentry(const struct dentry *);
 
-static const struct dentry_operations ncp_dentry_operations =
+const struct dentry_operations ncp_dentry_operations =
 {
         .d_revalidate   = ncp_lookup_validate,
         .d_hash         = ncp_hash_dentry,
@@ -90,14 +88,6 @@ static const struct dentry_operations ncp_dentry_operations =
         .d_delete       = ncp_delete_dentry,
 };
 
-const struct dentry_operations ncp_root_dentry_operations =
-{
-        .d_hash         = ncp_hash_dentry,
-        .d_compare      = ncp_compare_dentry,
-        .d_delete       = ncp_delete_dentry,
-};
-
-
 #define ncp_namespace(i)        (NCP_SERVER(i)->name_space[NCP_FINFO(i)->volNumber])
 
 static inline int ncp_preserve_entry_case(struct inode *i, __u32 nscreator)
@@ -309,6 +299,9 @@ ncp_lookup_validate(struct dentry *dentry, struct nameidata *nd)
         int res, val = 0, len;
         __u8 __name[NCP_MAXPATHLEN + 1];
 
+        if (dentry == dentry->d_sb->s_root)
+                return 1;
+
         if (nd->flags & LOOKUP_RCU)
                 return -ECHILD;
 
@@ -637,7 +630,6 @@ ncp_fill_cache(struct file *filp, void *dirent, filldir_t filldir,
                 entry->ino = iunique(dir->i_sb, 2);
                 inode = ncp_iget(dir->i_sb, entry);
                 if (inode) {
-                        d_set_d_op(newdent, &ncp_dentry_operations);
                         d_instantiate(newdent, inode);
                         if (!hashed)
                                 d_rehash(newdent);
@@ -893,7 +885,6 @@ static struct dentry *ncp_lookup(struct inode *dir, struct dentry *dentry, struc
         if (inode) {
                 ncp_new_dentry(dentry);
 add_entry:
-                d_set_d_op(dentry, &ncp_dentry_operations);
                 d_add(dentry, inode);
                 error = 0;
         }
diff --git a/fs/ncpfs/file.c b/fs/ncpfs/file.c
index cb50aaf981df..0ed65e0c3dfe 100644
--- a/fs/ncpfs/file.c
+++ b/fs/ncpfs/file.c
@@ -18,8 +18,7 @@
 #include <linux/vmalloc.h>
 #include <linux/sched.h>
 
-#include <linux/ncp_fs.h>
-#include "ncplib_kernel.h"
+#include "ncp_fs.h"
 
 static int ncp_fsync(struct file *file, int datasync)
 {
diff --git a/fs/ncpfs/inode.c b/fs/ncpfs/inode.c
index 9b39a5dd4131..00a1d1c3d3a4 100644
--- a/fs/ncpfs/inode.c
+++ b/fs/ncpfs/inode.c
@@ -31,11 +31,9 @@
 #include <linux/seq_file.h>
 #include <linux/namei.h>
 
-#include <linux/ncp_fs.h>
-
 #include <net/sock.h>
 
-#include "ncplib_kernel.h"
+#include "ncp_fs.h"
 #include "getopt.h"
 
 #define NCP_DEFAULT_FILE_MODE 0600
@@ -544,6 +542,7 @@ static int ncp_fill_super(struct super_block *sb, void *raw_data, int silent)
         sb->s_blocksize_bits = 10;
         sb->s_magic = NCP_SUPER_MAGIC;
         sb->s_op = &ncp_sops;
+        sb->s_d_op = &ncp_dentry_operations;
         sb->s_bdi = &server->bdi;
 
         server = NCP_SBP(sb);
@@ -723,7 +722,6 @@ static int ncp_fill_super(struct super_block *sb, void *raw_data, int silent)
         sb->s_root = d_alloc_root(root_inode);
         if (!sb->s_root)
                 goto out_no_root;
-        d_set_d_op(sb->s_root, &ncp_root_dentry_operations);
         return 0;
 
 out_no_root:
diff --git a/fs/ncpfs/ioctl.c b/fs/ncpfs/ioctl.c
index d40a547e3377..790e92a9ec63 100644
--- a/fs/ncpfs/ioctl.c
+++ b/fs/ncpfs/ioctl.c
@@ -20,11 +20,9 @@
 #include <linux/vmalloc.h>
 #include <linux/sched.h>
 
-#include <linux/ncp_fs.h>
-
 #include <asm/uaccess.h>
 
-#include "ncplib_kernel.h"
+#include "ncp_fs.h"
 
 /* maximum limit for ncp_objectname_ioctl */
 #define NCP_OBJECT_NAME_MAX_LEN 4096
diff --git a/fs/ncpfs/mmap.c b/fs/ncpfs/mmap.c
index 56f5b3a0e1ee..a7c07b44b100 100644
--- a/fs/ncpfs/mmap.c
+++ b/fs/ncpfs/mmap.c
@@ -16,12 +16,12 @@
 #include <linux/mman.h>
 #include <linux/string.h>
 #include <linux/fcntl.h>
-#include <linux/ncp_fs.h>
 
-#include "ncplib_kernel.h"
 #include <asm/uaccess.h>
 #include <asm/system.h>
 
+#include "ncp_fs.h"
+
 /*
  * Fill in the supplied page for mmap
  * XXX: how are we excluding truncate/invalidate here? Maybe need to lock
diff --git a/fs/ncpfs/ncp_fs.h b/fs/ncpfs/ncp_fs.h
new file mode 100644
index 000000000000..31831afe1c3b
--- /dev/null
+++ b/fs/ncpfs/ncp_fs.h
@@ -0,0 +1,98 @@
+#include <linux/ncp_fs.h>
+#include "ncp_fs_i.h"
+#include "ncp_fs_sb.h"
+
+/* define because it is easy to change PRINTK to {*}PRINTK */
+#define PRINTK(format, args...) printk(KERN_DEBUG format , ## args)
+
+#undef NCPFS_PARANOIA
+#ifdef NCPFS_PARANOIA
+#define PPRINTK(format, args...) PRINTK(format , ## args)
+#else
+#define PPRINTK(format, args...)
+#endif
+
+#ifndef DEBUG_NCP
+#define DEBUG_NCP 0
+#endif
+#if DEBUG_NCP > 0
+#define DPRINTK(format, args...) PRINTK(format , ## args)
+#else
+#define DPRINTK(format, args...)
+#endif
+#if DEBUG_NCP > 1
+#define DDPRINTK(format, args...) PRINTK(format , ## args)
+#else
+#define DDPRINTK(format, args...)
+#endif
+
+#define NCP_MAX_RPC_TIMEOUT (6*HZ)
+
+
+struct ncp_entry_info {
+        struct nw_info_struct   i;
+        ino_t                   ino;
+        int                     opened;
+        int                     access;
+        unsigned int            volume;
+        __u8                    file_handle[6];
+};
+
+static inline struct ncp_server *NCP_SBP(const struct super_block *sb)
+{
+        return sb->s_fs_info;
+}
+
+#define NCP_SERVER(inode)       NCP_SBP((inode)->i_sb)
+static inline struct ncp_inode_info *NCP_FINFO(const struct inode *inode)
+{
+        return container_of(inode, struct ncp_inode_info, vfs_inode);
+}
+
+/* linux/fs/ncpfs/inode.c */
+int ncp_notify_change(struct dentry *, struct iattr *);
+struct inode *ncp_iget(struct super_block *, struct ncp_entry_info *);
+void ncp_update_inode(struct inode *, struct ncp_entry_info *);
+void ncp_update_inode2(struct inode *, struct ncp_entry_info *);
+
+/* linux/fs/ncpfs/dir.c */
+extern const struct inode_operations ncp_dir_inode_operations;
+extern const struct file_operations ncp_dir_operations;
+extern const struct dentry_operations ncp_dentry_operations;
+int ncp_conn_logged_in(struct super_block *);
+int ncp_date_dos2unix(__le16 time, __le16 date);
+void ncp_date_unix2dos(int unix_date, __le16 * time, __le16 * date);
+
+/* linux/fs/ncpfs/ioctl.c */
+long ncp_ioctl(struct file *, unsigned int, unsigned long);
+long ncp_compat_ioctl(struct file *, unsigned int, unsigned long);
+
+/* linux/fs/ncpfs/sock.c */
+int ncp_request2(struct ncp_server *server, int function,
+        void* reply, int max_reply_size);
+static inline int ncp_request(struct ncp_server *server, int function) {
+        return ncp_request2(server, function, server->packet, server->packet_size);
+}
+int ncp_connect(struct ncp_server *server);
+int ncp_disconnect(struct ncp_server *server);
+void ncp_lock_server(struct ncp_server *server);
+void ncp_unlock_server(struct ncp_server *server);
+
+/* linux/fs/ncpfs/symlink.c */
+#if defined(CONFIG_NCPFS_EXTRAS) || defined(CONFIG_NCPFS_NFS_NS)
+extern const struct address_space_operations ncp_symlink_aops;
+int ncp_symlink(struct inode*, struct dentry*, const char*);
+#endif
+
+/* linux/fs/ncpfs/file.c */
+extern const struct inode_operations ncp_file_inode_operations;
+extern const struct file_operations ncp_file_operations;
+int ncp_make_open(struct inode *, int);
+
+/* linux/fs/ncpfs/mmap.c */
+int ncp_mmap(struct file *, struct vm_area_struct *);
+
+/* linux/fs/ncpfs/ncplib_kernel.c */
+int ncp_make_closed(struct inode *);
+
+#include "ncplib_kernel.h"
diff --git a/fs/ncpfs/ncp_fs_i.h b/fs/ncpfs/ncp_fs_i.h
new file mode 100644
index 000000000000..4b0bec477846
--- /dev/null
+++ b/fs/ncpfs/ncp_fs_i.h
@@ -0,0 +1,29 @@
+/*
+ *  ncp_fs_i.h
+ *
+ *  Copyright (C) 1995 Volker Lendecke
+ *
+ */
+
+#ifndef _LINUX_NCP_FS_I
+#define _LINUX_NCP_FS_I
+
+/*
+ * This is the ncpfs part of the inode structure. This must contain
+ * all the information we need to work with an inode after creation.
+ */
+struct ncp_inode_info {
+        __le32  dirEntNum;
+        __le32  DosDirNum;
+        __u8    volNumber;
+        __le32  nwattr;
+        struct mutex open_mutex;
+        atomic_t        opened;
+        int     access;
+        int     flags;
+#define NCPI_KLUDGE_SYMLINK     0x0001
+        __u8    file_handle[6];
+        struct inode vfs_inode;
+};
+
+#endif  /* _LINUX_NCP_FS_I */
diff --git a/fs/ncpfs/ncp_fs_sb.h b/fs/ncpfs/ncp_fs_sb.h
new file mode 100644
index 000000000000..4af803f13516
--- /dev/null
+++ b/fs/ncpfs/ncp_fs_sb.h
@@ -0,0 +1,176 @@
+/*
+ *  ncp_fs_sb.h
+ *
+ *  Copyright (C) 1995, 1996 by Volker Lendecke
+ *
+ */
+
+#ifndef _NCP_FS_SB
+#define _NCP_FS_SB
+
+#include <linux/types.h>
+#include <linux/ncp_mount.h>
+#include <linux/net.h>
+#include <linux/mutex.h>
+#include <linux/backing-dev.h>
+#include <linux/workqueue.h>
+
+#define NCP_DEFAULT_OPTIONS 0           /* 2 for packet signatures */
+
+struct sock;
+
+struct ncp_mount_data_kernel {
+        unsigned long    flags;         /* NCP_MOUNT_* flags */
+        unsigned int     int_flags;     /* internal flags */
+#define NCP_IMOUNT_LOGGEDIN_POSSIBLE    0x0001
+        __kernel_uid32_t mounted_uid;   /* Who may umount() this filesystem? */
+        struct pid      *wdog_pid;      /* Who cares for our watchdog packets? */
+        unsigned int     ncp_fd;        /* The socket to the ncp port */
+        unsigned int     time_out;      /* How long should I wait after
+                                           sending a NCP request? */
+        unsigned int     retry_count;   /* And how often should I retry? */
+        unsigned char    mounted_vol[NCP_VOLNAME_LEN + 1];
+        __kernel_uid32_t uid;
+        __kernel_gid32_t gid;
+        __kernel_mode_t  file_mode;
+        __kernel_mode_t  dir_mode;
+        int              info_fd;
+};
+
+struct ncp_server {
+
+        struct ncp_mount_data_kernel m; /* Nearly all of the mount data is of
+                                           interest for us later, so we store
+                                           it completely. */
+
+        __u8 name_space[NCP_NUMBER_OF_VOLUMES + 2];
+
+        struct file *ncp_filp;  /* File pointer to ncp socket */
+        struct socket *ncp_sock;/* ncp socket */
+        struct file *info_filp;
+        struct socket *info_sock;
+
+        u8 sequence;
+        u8 task;
+        u16 connection;         /* Remote connection number */
+
+        u8 completion;          /* Status message from server */
+        u8 conn_status;         /* Bit 4 = 1 ==> Server going down, no
+                                   requests allowed anymore.
+                                   Bit 0 = 1 ==> Server is down. */
+
+        int buffer_size;        /* Negotiated bufsize */
+
+        int reply_size;         /* Size of last reply */
+
+        int packet_size;
+        unsigned char *packet;  /* Here we prepare requests and
+                                   receive replies */
+        unsigned char *txbuf;   /* Storage for current request */
+        unsigned char *rxbuf;   /* Storage for reply to current request */
+
+        int lock;               /* To prevent mismatch in protocols. */
+        struct mutex mutex;
+
+        int current_size;       /* for packet preparation */
+        int has_subfunction;
+        int ncp_reply_size;
+
+        int root_setuped;
+        struct mutex root_setup_lock;
+
+        /* info for packet signing */
+        int sign_wanted;        /* 1=Server needs signed packets */
+        int sign_active;        /* 0=don't do signing, 1=do */
+        char sign_root[8];      /* generated from password and encr. key */
+        char sign_last[16];     
+
+        /* Authentication info: NDS or BINDERY, username */
+        struct {
+                int     auth_type;
+                size_t  object_name_len;
+                void*   object_name;
+                int     object_type;
+        } auth;
+        /* Password info */
+        struct {
+                size_t  len;
+                void*   data;
+        } priv;
+        struct rw_semaphore auth_rwsem;
+
+        /* nls info: codepage for volume and charset for I/O */
+        struct nls_table *nls_vol;
+        struct nls_table *nls_io;
+
+        /* maximum age in jiffies */
+        atomic_t dentry_ttl;
+
+        /* miscellaneous */
+        unsigned int flags;
+
+        spinlock_t requests_lock;       /* Lock accesses to tx.requests, tx.creq and rcv.creq when STREAM mode */
+
+        void (*data_ready)(struct sock* sk, int len);
+        void (*error_report)(struct sock* sk);
+        void (*write_space)(struct sock* sk);   /* STREAM mode only */
+        struct {
+                struct work_struct tq;          /* STREAM/DGRAM: data/error ready */
+                struct ncp_request_reply* creq; /* STREAM/DGRAM: awaiting reply from this request */
+                struct mutex creq_mutex;        /* DGRAM only: lock accesses to rcv.creq */
+
+                unsigned int state;             /* STREAM only: receiver state */
+                struct {
+                        __u32 magic __packed;
+                        __u32 len __packed;
+                        __u16 type __packed;
+                        __u16 p1 __packed;
+                        __u16 p2 __packed;
+                        __u16 p3 __packed;
+                        __u16 type2 __packed;
+                } buf;                          /* STREAM only: temporary buffer */
+                unsigned char* ptr;             /* STREAM only: pointer to data */
+                size_t len;                     /* STREAM only: length of data to receive */
+        } rcv;
+        struct {
+                struct list_head requests;      /* STREAM only: queued requests */
+                struct work_struct tq;          /* STREAM only: transmitter ready */
+                struct ncp_request_reply* creq; /* STREAM only: currently transmitted entry */
+        } tx;
+        struct timer_list timeout_tm;           /* DGRAM only: timeout timer */
+        struct work_struct timeout_tq;          /* DGRAM only: associated queue, we run timers from process context */
+        int timeout_last;                       /* DGRAM only: current timeout length */
+        int timeout_retries;                    /* DGRAM only: retries left */
+        struct {
+                size_t len;
+                __u8 data[128];
+        } unexpected_packet;
+        struct backing_dev_info bdi;
+};
+
+extern void ncp_tcp_rcv_proc(struct work_struct *work);
+extern void ncp_tcp_tx_proc(struct work_struct *work);
+extern void ncpdgram_rcv_proc(struct work_struct *work);
+extern void ncpdgram_timeout_proc(struct work_struct *work);
+extern void ncpdgram_timeout_call(unsigned long server);
+extern void ncp_tcp_data_ready(struct sock* sk, int len);
+extern void ncp_tcp_write_space(struct sock* sk);
+extern void ncp_tcp_error_report(struct sock* sk);
+
+#define NCP_FLAG_UTF8   1
+
+#define NCP_CLR_FLAG(server, flag)      ((server)->flags &= ~(flag))
+#define NCP_SET_FLAG(server, flag)      ((server)->flags |= (flag))
+#define NCP_IS_FLAG(server, flag)       ((server)->flags & (flag))
+
+static inline int ncp_conn_valid(struct ncp_server *server)
+{
+        return ((server->conn_status & 0x11) == 0);
+}
+
+static inline void ncp_invalidate_conn(struct ncp_server *server)
+{
+        server->conn_status |= 0x01;
+}
+
+#endif
diff --git a/fs/ncpfs/ncplib_kernel.c b/fs/ncpfs/ncplib_kernel.c
index a95615a0b6ac..981a95617fc9 100644
--- a/fs/ncpfs/ncplib_kernel.c
+++ b/fs/ncpfs/ncplib_kernel.c
@@ -11,7 +11,7 @@
 
 
 
-#include "ncplib_kernel.h"
+#include "ncp_fs.h"
 
 static inline void assert_server_locked(struct ncp_server *server)
 {
diff --git a/fs/ncpfs/ncplib_kernel.h b/fs/ncpfs/ncplib_kernel.h
index 1220df75ff22..09881e6aa5ad 100644
--- a/fs/ncpfs/ncplib_kernel.h
+++ b/fs/ncpfs/ncplib_kernel.h
@@ -32,8 +32,6 @@
 #include <linux/ctype.h>
 #endif /* CONFIG_NCPFS_NLS */
 
-#include <linux/ncp_fs.h>
-
 #define NCP_MIN_SYMLINK_SIZE    8
 #define NCP_MAX_SYMLINK_SIZE    512
 
diff --git a/fs/ncpfs/ncpsign_kernel.c b/fs/ncpfs/ncpsign_kernel.c
index d8b2d7e6910b..08907599dcd2 100644
--- a/fs/ncpfs/ncpsign_kernel.c
+++ b/fs/ncpfs/ncpsign_kernel.c
@@ -11,6 +11,7 @@
 #include <linux/string.h>
 #include <linux/ncp.h>
 #include <linux/bitops.h>
+#include "ncp_fs.h"
 #include "ncpsign_kernel.h"
 
 /* i386: 32-bit, little endian, handles mis-alignment */
diff --git a/fs/ncpfs/ncpsign_kernel.h b/fs/ncpfs/ncpsign_kernel.h
index 6451a68381cc..d9a1438bb1f6 100644
--- a/fs/ncpfs/ncpsign_kernel.h
+++ b/fs/ncpfs/ncpsign_kernel.h
@@ -8,8 +8,6 @@
 #ifndef _NCPSIGN_KERNEL_H
 #define _NCPSIGN_KERNEL_H
 
-#include <linux/ncp_fs.h>
-
 #ifdef CONFIG_NCPFS_PACKET_SIGNING
 void __sign_packet(struct ncp_server *server, const char *data, size_t size, __u32 totalsize, void *sign_buff);
 int sign_verify_reply(struct ncp_server *server, const char *data, size_t size, __u32 totalsize, const void *sign_buff);
diff --git a/fs/ncpfs/sock.c b/fs/ncpfs/sock.c
index 668bd267346e..3a1587222c8a 100644
--- a/fs/ncpfs/sock.c
+++ b/fs/ncpfs/sock.c
@@ -28,7 +28,7 @@
 #include <linux/poll.h>
 #include <linux/file.h>
 
-#include <linux/ncp_fs.h>
+#include "ncp_fs.h"
 
 #include "ncpsign_kernel.h"
 
diff --git a/fs/ncpfs/symlink.c b/fs/ncpfs/symlink.c
index c634fd17b337..661f861d80c6 100644
--- a/fs/ncpfs/symlink.c
+++ b/fs/ncpfs/symlink.c
@@ -25,13 +25,11 @@
 
 #include <linux/errno.h>
 #include <linux/fs.h>
-#include <linux/ncp_fs.h>
 #include <linux/time.h>
 #include <linux/slab.h>
 #include <linux/mm.h>
 #include <linux/stat.h>
-#include "ncplib_kernel.h"
-
+#include "ncp_fs.h"
 
 /* these magic numbers must appear in the symlink file -- this makes it a bit
    more resilient against the magic attributes being set on random files. */
diff --git a/fs/nfs/dir.c b/fs/nfs/dir.c
index abe4f0c8dc5f..df8c03a02161 100644
--- a/fs/nfs/dir.c
+++ b/fs/nfs/dir.c
@@ -439,7 +439,6 @@ void nfs_prime_dcache(struct dentry *parent, struct nfs_entry *entry)
         if (dentry == NULL)
                 return;
 
-        d_set_d_op(dentry, NFS_PROTO(dir)->dentry_ops);
         inode = nfs_fhget(dentry->d_sb, entry->fh, entry->fattr);
         if (IS_ERR(inode))
                 goto out;
@@ -1193,8 +1192,6 @@ static struct dentry *nfs_lookup(struct inode *dir, struct dentry * dentry, stru
         if (dentry->d_name.len > NFS_SERVER(dir)->namelen)
                 goto out;
 
-        d_set_d_op(dentry, NFS_PROTO(dir)->dentry_ops);
-
         /*
          * If we're doing an exclusive create, optimize away the lookup
          * but don't hash the dentry.
@@ -1338,7 +1335,6 @@ static struct dentry *nfs_atomic_lookup(struct inode *dir, struct dentry *dentry
                 res = ERR_PTR(-ENAMETOOLONG);
                 goto out;
         }
-        d_set_d_op(dentry, NFS_PROTO(dir)->dentry_ops);
 
         /* Let vfs_create() deal with O_EXCL. Instantiate, but don't hash
          * the dentry. */
@@ -1410,11 +1406,15 @@ no_open:
 static int nfs_open_revalidate(struct dentry *dentry, struct nameidata *nd)
 {
         struct dentry *parent = NULL;
-        struct inode *inode = dentry->d_inode;
+        struct inode *inode;
         struct inode *dir;
         struct nfs_open_context *ctx;
         int openflags, ret = 0;
 
+        if (nd->flags & LOOKUP_RCU)
+                return -ECHILD;
+
+        inode = dentry->d_inode;
         if (!is_atomic_open(nd) || d_mountpoint(dentry))
                 goto no_open;
 
@@ -1583,6 +1583,7 @@ static int nfs_create(struct inode *dir, struct dentry *dentry, int mode,
 {
         struct iattr attr;
         int error;
+        int open_flags = 0;
 
         dfprintk(VFS, "NFS: create(%s/%ld), %s\n",
                         dir->i_sb->s_id, dir->i_ino, dentry->d_name.name);
@@ -1590,7 +1591,10 @@ static int nfs_create(struct inode *dir, struct dentry *dentry, int mode,
         attr.ia_mode = mode;
         attr.ia_valid = ATTR_MODE;
 
-        error = NFS_PROTO(dir)->create(dir, dentry, &attr, 0, NULL);
+        if ((nd->flags & LOOKUP_CREATE) != 0)
+                open_flags = nd->intent.open.flags;
+
+        error = NFS_PROTO(dir)->create(dir, dentry, &attr, open_flags, NULL);
         if (error != 0)
                 goto out_err;
         return 0;
diff --git a/fs/nfs/getroot.c b/fs/nfs/getroot.c
index 5596c6a2881e..b5ffe8fa291f 100644
--- a/fs/nfs/getroot.c
+++ b/fs/nfs/getroot.c
@@ -119,9 +119,6 @@ struct dentry *nfs_get_root(struct super_block *sb, struct nfs_fh *mntfh)
         }
 
         security_d_instantiate(ret, inode);
-
-        if (ret->d_op == NULL)
-                d_set_d_op(ret, server->nfs_client->rpc_ops->dentry_ops);
 out:
         nfs_free_fattr(fsinfo.fattr);
         return ret;
@@ -227,9 +224,6 @@ struct dentry *nfs4_get_root(struct super_block *sb, struct nfs_fh *mntfh)
 
         security_d_instantiate(ret, inode);
 
-        if (ret->d_op == NULL)
-                d_set_d_op(ret, server->nfs_client->rpc_ops->dentry_ops);
-
 out:
         nfs_free_fattr(fattr);
         dprintk("<-- nfs4_get_root()\n");
diff --git a/fs/nfs/super.c b/fs/nfs/super.c
index 0f9ea73e7789..b68c8607770f 100644
--- a/fs/nfs/super.c
+++ b/fs/nfs/super.c
@@ -2202,6 +2202,7 @@ static int nfs_set_super(struct super_block *s, void *data)
 
         s->s_flags = sb_mntdata->mntflags;
         s->s_fs_info = server;
+        s->s_d_op = server->nfs_client->rpc_ops->dentry_ops;
         ret = set_anon_super(s, server);
         if (ret == 0)
                 server->s_dev = s->s_dev;
diff --git a/fs/nfsd/vfs.c b/fs/nfsd/vfs.c
index 3a359023c9f7..230b79fbf005 100644
--- a/fs/nfsd/vfs.c
+++ b/fs/nfsd/vfs.c
@@ -845,11 +845,6 @@ nfsd_splice_actor(struct pipe_inode_info *pipe, struct pipe_buffer *buf,
         struct page **pp = rqstp->rq_respages + rqstp->rq_resused;
         struct page *page = buf->page;
         size_t size;
-        int ret;
-
-        ret = buf->ops->confirm(pipe, buf);
-        if (unlikely(ret))
-                return ret;
 
         size = sd->len;
 
diff --git a/fs/nilfs2/super.c b/fs/nilfs2/super.c
index 70dfdd532b83..0994f6a76c07 100644
--- a/fs/nilfs2/super.c
+++ b/fs/nilfs2/super.c
@@ -1163,14 +1163,14 @@ nilfs_mount(struct file_system_type *fs_type, int flags,
 {
         struct nilfs_super_data sd;
         struct super_block *s;
-        fmode_t mode = FMODE_READ;
+        fmode_t mode = FMODE_READ | FMODE_EXCL;
         struct dentry *root_dentry;
         int err, s_new = false;
 
         if (!(flags & MS_RDONLY))
                 mode |= FMODE_WRITE;
 
-        sd.bdev = open_bdev_exclusive(dev_name, mode, fs_type);
+        sd.bdev = blkdev_get_by_path(dev_name, mode, fs_type);
         if (IS_ERR(sd.bdev))
                 return ERR_CAST(sd.bdev);
 
@@ -1249,7 +1249,7 @@ nilfs_mount(struct file_system_type *fs_type, int flags,
         }
 
         if (!s_new)
-                close_bdev_exclusive(sd.bdev, mode);
+                blkdev_put(sd.bdev, mode);
 
         return root_dentry;
 
@@ -1258,7 +1258,7 @@ nilfs_mount(struct file_system_type *fs_type, int flags,
 
  failed:
         if (!s_new)
-                close_bdev_exclusive(sd.bdev, mode);
+                blkdev_put(sd.bdev, mode);
         return ERR_PTR(err);
 }
 
diff --git a/fs/notify/fanotify/Kconfig b/fs/notify/fanotify/Kconfig
index 3ac36b7bf6b9..7dceff005a67 100644
--- a/fs/notify/fanotify/Kconfig
+++ b/fs/notify/fanotify/Kconfig
@@ -6,7 +6,7 @@ config FANOTIFY
         ---help---
            Say Y here to enable fanotify suport.  fanotify is a file access
            notification system which differs from inotify in that it sends
-           and open file descriptor to the userspace listener along with
+           an open file descriptor to the userspace listener along with
            the event.
 
            If unsure, say Y.
diff --git a/fs/ocfs2/cluster/heartbeat.c b/fs/ocfs2/cluster/heartbeat.c
index a6cc05302e9f..b108e863d8f6 100644
--- a/fs/ocfs2/cluster/heartbeat.c
+++ b/fs/ocfs2/cluster/heartbeat.c
@@ -1729,7 +1729,7 @@ static ssize_t o2hb_region_dev_write(struct o2hb_region *reg,
                 goto out;
 
         reg->hr_bdev = I_BDEV(filp->f_mapping->host);
-        ret = blkdev_get(reg->hr_bdev, FMODE_WRITE | FMODE_READ);
+        ret = blkdev_get(reg->hr_bdev, FMODE_WRITE | FMODE_READ, NULL);
         if (ret) {
                 reg->hr_bdev = NULL;
                 goto out;
diff --git a/fs/ocfs2/export.c b/fs/ocfs2/export.c
index 6adafa576065..5dbc3062b4fd 100644
--- a/fs/ocfs2/export.c
+++ b/fs/ocfs2/export.c
@@ -137,9 +137,7 @@ check_gen:
         }
 
         result = d_obtain_alias(inode);
-        if (!IS_ERR(result))
-                d_set_d_op(result, &ocfs2_dentry_ops);
-        else
+        if (IS_ERR(result))
                 mlog_errno(PTR_ERR(result));
 
 bail:
@@ -175,8 +173,6 @@ static struct dentry *ocfs2_get_parent(struct dentry *child)
         }
 
         parent = d_obtain_alias(ocfs2_iget(OCFS2_SB(dir->i_sb), blkno, 0, 0));
-        if (!IS_ERR(parent))
-                d_set_d_op(parent, &ocfs2_dentry_ops);
 
 bail_unlock:
         ocfs2_inode_unlock(dir, 0);
diff --git a/fs/ocfs2/file.c b/fs/ocfs2/file.c
index bdadbae09094..63e3fca266e0 100644
--- a/fs/ocfs2/file.c
+++ b/fs/ocfs2/file.c
@@ -1995,6 +1995,7 @@ static long ocfs2_fallocate(struct inode *inode, int mode, loff_t offset,
         struct ocfs2_super *osb = OCFS2_SB(inode->i_sb);
         struct ocfs2_space_resv sr;
         int change_size = 1;
+        int cmd = OCFS2_IOC_RESVSP64;
 
         if (!ocfs2_writes_unwritten_extents(osb))
                 return -EOPNOTSUPP;
@@ -2005,12 +2006,15 @@ static long ocfs2_fallocate(struct inode *inode, int mode, loff_t offset,
         if (mode & FALLOC_FL_KEEP_SIZE)
                 change_size = 0;
 
+        if (mode & FALLOC_FL_PUNCH_HOLE)
+                cmd = OCFS2_IOC_UNRESVSP64;
+
         sr.l_whence = 0;
         sr.l_start = (s64)offset;
         sr.l_len = (s64)len;
 
-        return __ocfs2_change_file_space(NULL, inode, offset,
-                                         OCFS2_IOC_RESVSP64, &sr, change_size);
+        return __ocfs2_change_file_space(NULL, inode, offset, cmd, &sr,
+                                         change_size);
 }
 
 int ocfs2_check_range_for_refcount(struct inode *inode, loff_t pos,
diff --git a/fs/ocfs2/inode.c b/fs/ocfs2/inode.c
index f935fd6600dd..4068c6c4c6f6 100644
--- a/fs/ocfs2/inode.c
+++ b/fs/ocfs2/inode.c
@@ -434,7 +434,7 @@ static int ocfs2_read_locked_inode(struct inode *inode,
          * #1 and #2 can be simply solved by never taking the lock
          * here for system files (which are the only type we read
          * during mount). It's a heavier approach, but our main
-         * concern is user-accesible files anyway.
+         * concern is user-accessible files anyway.
          *
          * #3 works itself out because we'll eventually take the
          * cluster lock before trusting anything anyway.
diff --git a/fs/ocfs2/namei.c b/fs/ocfs2/namei.c
index 30c523144452..849fb4a2e814 100644
--- a/fs/ocfs2/namei.c
+++ b/fs/ocfs2/namei.c
@@ -147,7 +147,6 @@ static struct dentry *ocfs2_lookup(struct inode *dir, struct dentry *dentry,
         spin_unlock(&oi->ip_lock);
 
 bail_add:
-        d_set_d_op(dentry, &ocfs2_dentry_ops);
         ret = d_splice_alias(inode, dentry);
 
         if (inode) {
@@ -415,7 +414,6 @@ static int ocfs2_mknod(struct inode *dir,
                 mlog_errno(status);
                 goto leave;
         }
-        d_set_d_op(dentry, &ocfs2_dentry_ops);
 
         status = ocfs2_add_entry(handle, dentry, inode,
                                  OCFS2_I(inode)->ip_blkno, parent_fe_bh,
@@ -743,7 +741,6 @@ static int ocfs2_link(struct dentry *old_dentry,
         }
 
         ihold(inode);
-        d_set_d_op(dentry, &ocfs2_dentry_ops);
         d_instantiate(dentry, inode);
 
 out_commit:
@@ -1797,7 +1794,6 @@ static int ocfs2_symlink(struct inode *dir,
                 mlog_errno(status);
                 goto bail;
         }
-        d_set_d_op(dentry, &ocfs2_dentry_ops);
 
         status = ocfs2_add_entry(handle, dentry, inode,
                                  le64_to_cpu(fe->i_blkno), parent_fe_bh,
@@ -2462,7 +2458,6 @@ int ocfs2_mv_orphaned_inode_to_new(struct inode *dir,
                 goto out_commit;
         }
 
-        d_set_d_op(dentry, &ocfs2_dentry_ops);
         d_instantiate(dentry, inode);
         status = 0;
 out_commit:
diff --git a/fs/ocfs2/suballoc.c b/fs/ocfs2/suballoc.c
index 5fed60de7630..71998d4d61d5 100644
--- a/fs/ocfs2/suballoc.c
+++ b/fs/ocfs2/suballoc.c
@@ -1916,7 +1916,7 @@ static int ocfs2_claim_suballoc_bits(struct ocfs2_alloc_context *ac,
         if (res->sr_bg_blkno) {
                 /* Attempt to short-circuit the usual search mechanism
                  * by jumping straight to the most recently used
-                 * allocation group. This helps us mantain some
+                 * allocation group. This helps us maintain some
                  * contiguousness across allocations. */
                 status = ocfs2_search_one_group(ac, handle, bits_wanted,
                                                 min_bits, res, &bits_left);
diff --git a/fs/ocfs2/super.c b/fs/ocfs2/super.c
index 17ff46fa8a10..06d1f749ca89 100644
--- a/fs/ocfs2/super.c
+++ b/fs/ocfs2/super.c
@@ -2097,6 +2097,7 @@ static int ocfs2_initialize_super(struct super_block *sb,
 
         sb->s_fs_info = osb;
         sb->s_op = &ocfs2_sops;
+        sb->s_d_op = &ocfs2_dentry_ops;
         sb->s_export_op = &ocfs2_export_ops;
         sb->s_qcop = &ocfs2_quotactl_ops;
         sb->dq_op = &ocfs2_quota_operations;
diff --git a/fs/open.c b/fs/open.c
index 4197b9ed023d..5b6ef7e2859e 100644
--- a/fs/open.c
+++ b/fs/open.c
@@ -223,7 +223,12 @@ int do_fallocate(struct file *file, int mode, loff_t offset, loff_t len)
                 return -EINVAL;
 
         /* Return error if mode is not supported */
-        if (mode && !(mode & FALLOC_FL_KEEP_SIZE))
+        if (mode & ~(FALLOC_FL_KEEP_SIZE | FALLOC_FL_PUNCH_HOLE))
+                return -EOPNOTSUPP;
+
+        /* Punch hole must have keep size set */
+        if ((mode & FALLOC_FL_PUNCH_HOLE) &&
+            !(mode & FALLOC_FL_KEEP_SIZE))
                 return -EOPNOTSUPP;
 
         if (!(file->f_mode & FMODE_WRITE))
diff --git a/fs/partitions/check.c b/fs/partitions/check.c
index 0a8b0ad0c7e2..9c21119512b9 100644
--- a/fs/partitions/check.c
+++ b/fs/partitions/check.c
@@ -237,6 +237,13 @@ ssize_t part_size_show(struct device *dev,
         return sprintf(buf, "%llu\n",(unsigned long long)p->nr_sects);
 }
 
+ssize_t part_ro_show(struct device *dev,
+                       struct device_attribute *attr, char *buf)
+{
+        struct hd_struct *p = dev_to_part(dev);
+        return sprintf(buf, "%d\n", p->policy ? 1 : 0);
+}
+
 ssize_t part_alignment_offset_show(struct device *dev,
                                    struct device_attribute *attr, char *buf)
 {
@@ -312,6 +319,7 @@ ssize_t part_fail_store(struct device *dev,
 static DEVICE_ATTR(partition, S_IRUGO, part_partition_show, NULL);
 static DEVICE_ATTR(start, S_IRUGO, part_start_show, NULL);
 static DEVICE_ATTR(size, S_IRUGO, part_size_show, NULL);
+static DEVICE_ATTR(ro, S_IRUGO, part_ro_show, NULL);
 static DEVICE_ATTR(alignment_offset, S_IRUGO, part_alignment_offset_show, NULL);
 static DEVICE_ATTR(discard_alignment, S_IRUGO, part_discard_alignment_show,
                    NULL);
@@ -326,6 +334,7 @@ static struct attribute *part_attrs[] = {
         &dev_attr_partition.attr,
         &dev_attr_start.attr,
         &dev_attr_size.attr,
+        &dev_attr_ro.attr,
         &dev_attr_alignment_offset.attr,
         &dev_attr_discard_alignment.attr,
         &dev_attr_stat.attr,
@@ -372,6 +381,11 @@ static void delete_partition_rcu_cb(struct rcu_head *head)
         put_device(part_to_dev(part));
 }
 
+void __delete_partition(struct hd_struct *part)
+{
+        call_rcu(&part->rcu_head, delete_partition_rcu_cb);
+}
+
 void delete_partition(struct gendisk *disk, int partno)
 {
         struct disk_part_tbl *ptbl = disk->part_tbl;
@@ -390,7 +404,7 @@ void delete_partition(struct gendisk *disk, int partno)
         kobject_put(part->holder_dir);
         device_del(part_to_dev(part));
 
-        call_rcu(&part->rcu_head, delete_partition_rcu_cb);
+        hd_struct_put(part);
 }
 
 static ssize_t whole_disk_show(struct device *dev,
@@ -489,6 +503,7 @@ struct hd_struct *add_partition(struct gendisk *disk, int partno,
         if (!dev_get_uevent_suppress(ddev))
                 kobject_uevent(&pdev->kobj, KOBJ_ADD);
 
+        hd_ref_init(p);
         return p;
 
 out_free_info:
@@ -507,65 +522,6 @@ out_put:
         return ERR_PTR(err);
 }
 
-/* Not exported, helper to add_disk(). */
-void register_disk(struct gendisk *disk)
-{
-        struct device *ddev = disk_to_dev(disk);
-        struct block_device *bdev;
-        struct disk_part_iter piter;
-        struct hd_struct *part;
-        int err;
-
-        ddev->parent = disk->driverfs_dev;
-
-        dev_set_name(ddev, disk->disk_name);
-
-        /* delay uevents, until we scanned partition table */
-        dev_set_uevent_suppress(ddev, 1);
-
-        if (device_add(ddev))
-                return;
-        if (!sysfs_deprecated) {
-                err = sysfs_create_link(block_depr, &ddev->kobj,
-                                        kobject_name(&ddev->kobj));
-                if (err) {
-                        device_del(ddev);
-                        return;
-                }
-        }
-        disk->part0.holder_dir = kobject_create_and_add("holders", &ddev->kobj);
-        disk->slave_dir = kobject_create_and_add("slaves", &ddev->kobj);
-
-        /* No minors to use for partitions */
-        if (!disk_partitionable(disk))
-                goto exit;
-
-        /* No such device (e.g., media were just removed) */
-        if (!get_capacity(disk))
-                goto exit;
-
-        bdev = bdget_disk(disk, 0);
-        if (!bdev)
-                goto exit;
-
-        bdev->bd_invalidated = 1;
-        err = blkdev_get(bdev, FMODE_READ);
-        if (err < 0)
-                goto exit;
-        blkdev_put(bdev, FMODE_READ);
-
-exit:
-        /* announce disk after possible partitions are created */
-        dev_set_uevent_suppress(ddev, 0);
-        kobject_uevent(&ddev->kobj, KOBJ_ADD);
-
-        /* announce possible partitions */
-        disk_part_iter_init(&piter, disk, 0);
-        while ((part = disk_part_iter_next(&piter)))
-                kobject_uevent(&part_to_dev(part)->kobj, KOBJ_ADD);
-        disk_part_iter_exit(&piter);
-}
-
 static bool disk_unlock_native_capacity(struct gendisk *disk)
 {
         const struct block_device_operations *bdops = disk->fops;
@@ -728,33 +684,3 @@ fail:
 }
 
 EXPORT_SYMBOL(read_dev_sector);
-
-void del_gendisk(struct gendisk *disk)
-{
-        struct disk_part_iter piter;
-        struct hd_struct *part;
-
-        /* invalidate stuff */
-        disk_part_iter_init(&piter, disk,
-                             DISK_PITER_INCL_EMPTY | DISK_PITER_REVERSE);
-        while ((part = disk_part_iter_next(&piter))) {
-                invalidate_partition(disk, part->partno);
-                delete_partition(disk, part->partno);
-        }
-        disk_part_iter_exit(&piter);
-
-        invalidate_partition(disk, 0);
-        blk_free_devt(disk_to_dev(disk)->devt);
-        set_capacity(disk, 0);
-        disk->flags &= ~GENHD_FL_UP;
-        unlink_gendisk(disk);
-        part_stat_set_all(&disk->part0, 0);
-        disk->part0.stamp = 0;
-
-        kobject_put(disk->part0.holder_dir);
-        kobject_put(disk->slave_dir);
-        disk->driverfs_dev = NULL;
-        if (!sysfs_deprecated)
-                sysfs_remove_link(block_depr, dev_name(disk_to_dev(disk)));
-        device_del(disk_to_dev(disk));
-}
diff --git a/fs/pipe.c b/fs/pipe.c
index 68f1f8e4e23b..e2e95fb46a1e 100644
--- a/fs/pipe.c
+++ b/fs/pipe.c
@@ -441,7 +441,7 @@ redo:
                         break;
                 }
                 if (do_wakeup) {
-                        wake_up_interruptible_sync(&pipe->wait);
+                        wake_up_interruptible_sync_poll(&pipe->wait, POLLOUT);
                         kill_fasync(&pipe->fasync_writers, SIGIO, POLL_OUT);
                 }
                 pipe_wait(pipe);
@@ -450,7 +450,7 @@ redo:
 
         /* Signal writers asynchronously that there is more room. */
         if (do_wakeup) {
-                wake_up_interruptible_sync(&pipe->wait);
+                wake_up_interruptible_sync_poll(&pipe->wait, POLLOUT);
                 kill_fasync(&pipe->fasync_writers, SIGIO, POLL_OUT);
         }
         if (ret > 0)
@@ -612,7 +612,7 @@ redo2:
                         break;
                 }
                 if (do_wakeup) {
-                        wake_up_interruptible_sync(&pipe->wait);
+                        wake_up_interruptible_sync_poll(&pipe->wait, POLLIN);
                         kill_fasync(&pipe->fasync_readers, SIGIO, POLL_IN);
                         do_wakeup = 0;
                 }
@@ -623,7 +623,7 @@ redo2:
 out:
         mutex_unlock(&inode->i_mutex);
         if (do_wakeup) {
-                wake_up_interruptible_sync(&pipe->wait);
+                wake_up_interruptible_sync_poll(&pipe->wait, POLLIN);
                 kill_fasync(&pipe->fasync_readers, SIGIO, POLL_IN);
         }
         if (ret > 0)
@@ -715,7 +715,7 @@ pipe_release(struct inode *inode, int decr, int decw)
         if (!pipe->readers && !pipe->writers) {
                 free_pipe_info(inode);
         } else {
-                wake_up_interruptible_sync(&pipe->wait);
+                wake_up_interruptible_sync_poll(&pipe->wait, POLLIN | POLLOUT);
                 kill_fasync(&pipe->fasync_readers, SIGIO, POLL_IN);
                 kill_fasync(&pipe->fasync_writers, SIGIO, POLL_OUT);
         }
@@ -1004,7 +1004,6 @@ struct file *create_write_pipe(int flags)
                 goto err_inode;
         path.mnt = mntget(pipe_mnt);
 
-        d_set_d_op(path.dentry, &pipefs_dentry_operations);
         d_instantiate(path.dentry, inode);
 
         err = -ENFILE;
@@ -1266,7 +1265,8 @@ static const struct super_operations pipefs_ops = {
 static struct dentry *pipefs_mount(struct file_system_type *fs_type,
                          int flags, const char *dev_name, void *data)
 {
-        return mount_pseudo(fs_type, "pipe:", &pipefs_ops, PIPEFS_MAGIC);
+        return mount_pseudo(fs_type, "pipe:", &pipefs_ops,
+                        &pipefs_dentry_operations, PIPEFS_MAGIC);
 }
 
 static struct file_system_type pipe_fs_type = {
diff --git a/fs/proc/Makefile b/fs/proc/Makefile
index 288a49e098bf..df434c5f28fb 100644
--- a/fs/proc/Makefile
+++ b/fs/proc/Makefile
@@ -10,12 +10,12 @@ proc-$(CONFIG_MMU)	:= mmu.o task_mmu.o
 proc-y       += inode.o root.o base.o generic.o array.o \
                 proc_tty.o
 proc-y  += cmdline.o
+proc-y  += consoles.o
 proc-y  += cpuinfo.o
 proc-y  += devices.o
 proc-y  += interrupts.o
 proc-y  += loadavg.o
 proc-y  += meminfo.o
-proc-y  += proc_console.o
 proc-y  += stat.o
 proc-y  += uptime.o
 proc-y  += version.o
diff --git a/fs/proc/array.c b/fs/proc/array.c
index fff6572676ae..df2b703b9d0f 100644
--- a/fs/proc/array.c
+++ b/fs/proc/array.c
@@ -95,7 +95,7 @@ static inline void task_name(struct seq_file *m, struct task_struct *p)
 
         get_task_comm(tcomm, p);
 
-        seq_printf(m, "Name:\t");
+        seq_puts(m, "Name:\t");
         end = m->buf + m->size;
         buf = m->buf + m->count;
         name = tcomm;
@@ -122,7 +122,7 @@ static inline void task_name(struct seq_file *m, struct task_struct *p)
                 buf++;
         }
         m->count = buf - m->buf;
-        seq_printf(m, "\n");
+        seq_putc(m, '\n');
 }
 
 /*
@@ -208,7 +208,7 @@ static inline void task_state(struct seq_file *m, struct pid_namespace *ns,
                 seq_printf(m, "%d ", GROUP_AT(group_info, g));
         put_cred(cred);
 
-        seq_printf(m, "\n");
+        seq_putc(m, '\n');
 }
 
 static void render_sigset_t(struct seq_file *m, const char *header,
@@ -216,7 +216,7 @@ static void render_sigset_t(struct seq_file *m, const char *header,
 {
         int i;
 
-        seq_printf(m, "%s", header);
+        seq_puts(m, header);
 
         i = _NSIG;
         do {
@@ -230,7 +230,7 @@ static void render_sigset_t(struct seq_file *m, const char *header,
                 seq_printf(m, "%x", x);
         } while (i >= 4);
 
-        seq_printf(m, "\n");
+        seq_putc(m, '\n');
 }
 
 static void collect_sigign_sigcatch(struct task_struct *p, sigset_t *ign,
@@ -291,12 +291,12 @@ static void render_cap_t(struct seq_file *m, const char *header,
 {
         unsigned __capi;
 
-        seq_printf(m, "%s", header);
+        seq_puts(m, header);
         CAP_FOR_EACH_U32(__capi) {
                 seq_printf(m, "%08x",
                            a->cap[(_KERNEL_CAPABILITY_U32S-1) - __capi]);
         }
-        seq_printf(m, "\n");
+        seq_putc(m, '\n');
 }
 
 static inline void task_cap(struct seq_file *m, struct task_struct *p)
@@ -329,12 +329,12 @@ static inline void task_context_switch_counts(struct seq_file *m,
 
 static void task_cpus_allowed(struct seq_file *m, struct task_struct *task)
 {
-        seq_printf(m, "Cpus_allowed:\t");
+        seq_puts(m, "Cpus_allowed:\t");
         seq_cpumask(m, &task->cpus_allowed);
-        seq_printf(m, "\n");
-        seq_printf(m, "Cpus_allowed_list:\t");
+        seq_putc(m, '\n');
+        seq_puts(m, "Cpus_allowed_list:\t");
         seq_cpumask_list(m, &task->cpus_allowed);
-        seq_printf(m, "\n");
+        seq_putc(m, '\n');
 }
 
 int proc_pid_status(struct seq_file *m, struct pid_namespace *ns,
@@ -535,15 +535,15 @@ int proc_tgid_stat(struct seq_file *m, struct pid_namespace *ns,
 int proc_pid_statm(struct seq_file *m, struct pid_namespace *ns,
                         struct pid *pid, struct task_struct *task)
 {
-        int size = 0, resident = 0, shared = 0, text = 0, lib = 0, data = 0;
+        unsigned long size = 0, resident = 0, shared = 0, text = 0, data = 0;
         struct mm_struct *mm = get_task_mm(task);
 
         if (mm) {
                 size = task_statm(mm, &shared, &text, &data, &resident);
                 mmput(mm);
         }
-        seq_printf(m, "%d %d %d %d %d %d %d\n",
-                        size, resident, shared, text, lib, data, 0);
+        seq_printf(m, "%lu %lu %lu %lu 0 %lu 0\n",
+                        size, resident, shared, text, data);
 
         return 0;
 }
diff --git a/fs/proc/base.c b/fs/proc/base.c
index b20962c71a52..9d096e82b201 100644
--- a/fs/proc/base.c
+++ b/fs/proc/base.c
@@ -373,26 +373,20 @@ static int lstats_show_proc(struct seq_file *m, void *v)
                 return -ESRCH;
         seq_puts(m, "Latency Top version : v0.1\n");
         for (i = 0; i < 32; i++) {
-                if (task->latency_record[i].backtrace[0]) {
+                struct latency_record *lr = &task->latency_record[i];
+                if (lr->backtrace[0]) {
                         int q;
-                        seq_printf(m, "%i %li %li ",
-                                task->latency_record[i].count,
-                                task->latency_record[i].time,
-                                task->latency_record[i].max);
+                        seq_printf(m, "%i %li %li",
+                                   lr->count, lr->time, lr->max);
                         for (q = 0; q < LT_BACKTRACEDEPTH; q++) {
-                                char sym[KSYM_SYMBOL_LEN];
-                                char *c;
-                                if (!task->latency_record[i].backtrace[q])
+                                unsigned long bt = lr->backtrace[q];
+                                if (!bt)
                                         break;
-                                if (task->latency_record[i].backtrace[q] == ULONG_MAX)
+                                if (bt == ULONG_MAX)
                                         break;
-                                sprint_symbol(sym, task->latency_record[i].backtrace[q]);
-                                c = strchr(sym, '+');
-                                if (c)
-                                        *c = 0;
-                                seq_printf(m, "%s ", sym);
+                                seq_printf(m, " %ps", (void *)bt);
                         }
-                        seq_printf(m, "\n");
+                        seq_putc(m, '\n');
                 }
 
         }
@@ -751,14 +745,7 @@ static int proc_single_show(struct seq_file *m, void *v)
 
 static int proc_single_open(struct inode *inode, struct file *filp)
 {
-        int ret;
-        ret = single_open(filp, proc_single_show, NULL);
-        if (!ret) {
-                struct seq_file *m = filp->private_data;
-
-                m->private = inode;
-        }
-        return ret;
+        return single_open(filp, proc_single_show, inode);
 }
 
 static const struct file_operations proc_single_file_operations = {
@@ -1164,7 +1151,7 @@ static ssize_t oom_score_adj_write(struct file *file, const char __user *buf,
                 goto err_task_lock;
         }
 
-        if (oom_score_adj < task->signal->oom_score_adj &&
+        if (oom_score_adj < task->signal->oom_score_adj_min &&
                         !capable(CAP_SYS_RESOURCE)) {
                 err = -EACCES;
                 goto err_sighand;
@@ -1177,6 +1164,8 @@ static ssize_t oom_score_adj_write(struct file *file, const char __user *buf,
                         atomic_dec(&task->mm->oom_disable_count);
         }
         task->signal->oom_score_adj = oom_score_adj;
+        if (has_capability_noaudit(current, CAP_SYS_RESOURCE))
+                task->signal->oom_score_adj_min = oom_score_adj;
         /*
          * Scale /proc/pid/oom_adj appropriately ensuring that OOM_DISABLE is
          * always attainable.
@@ -1386,15 +1375,7 @@ sched_write(struct file *file, const char __user *buf,
 
 static int sched_open(struct inode *inode, struct file *filp)
 {
-        int ret;
-
-        ret = single_open(filp, sched_show, NULL);
-        if (!ret) {
-                struct seq_file *m = filp->private_data;
-
-                m->private = inode;
-        }
-        return ret;
+        return single_open(filp, sched_show, inode);
 }
 
 static const struct file_operations proc_pid_sched_operations = {
@@ -1530,15 +1511,7 @@ static int comm_show(struct seq_file *m, void *v)
 
 static int comm_open(struct inode *inode, struct file *filp)
 {
-        int ret;
-
-        ret = single_open(filp, comm_show, NULL);
-        if (!ret) {
-                struct seq_file *m = filp->private_data;
-
-                m->private = inode;
-        }
-        return ret;
+        return single_open(filp, comm_show, inode);
 }
 
 static const struct file_operations proc_pid_set_comm_operations = {
diff --git a/fs/proc/proc_console.c b/fs/proc/consoles.c
index 8a707609f528..eafc22ab1fdd 100644
--- a/fs/proc/proc_console.c
+++ b/fs/proc/consoles.c
@@ -106,9 +106,9 @@ static const struct file_operations proc_consoles_operations = {
         .release        = seq_release,
 };
 
-static int register_proc_consoles(void)
+static int __init proc_consoles_init(void)
 {
         proc_create("consoles", 0, NULL, &proc_consoles_operations);
         return 0;
 }
-module_init(register_proc_consoles);
+module_init(proc_consoles_init);
diff --git a/fs/proc/devices.c b/fs/proc/devices.c
index 59ee7da959c9..b14347167c35 100644
--- a/fs/proc/devices.c
+++ b/fs/proc/devices.c
@@ -9,14 +9,14 @@ static int devinfo_show(struct seq_file *f, void *v)
 
         if (i < CHRDEV_MAJOR_HASH_SIZE) {
                 if (i == 0)
-                        seq_printf(f, "Character devices:\n");
+                        seq_puts(f, "Character devices:\n");
                 chrdev_show(f, i);
         }
 #ifdef CONFIG_BLOCK
         else {
                 i -= CHRDEV_MAJOR_HASH_SIZE;
                 if (i == 0)
-                        seq_printf(f, "\nBlock devices:\n");
+                        seq_puts(f, "\nBlock devices:\n");
                 blkdev_show(f, i);
         }
 #endif
diff --git a/fs/proc/generic.c b/fs/proc/generic.c
index f766be29d2c7..01e07f2a188f 100644
--- a/fs/proc/generic.c
+++ b/fs/proc/generic.c
@@ -425,13 +425,10 @@ struct dentry *proc_lookup_de(struct proc_dir_entry *de, struct inode *dir,
                 if (de->namelen != dentry->d_name.len)
                         continue;
                 if (!memcmp(dentry->d_name.name, de->name, de->namelen)) {
-                        unsigned int ino;
-
-                        ino = de->low_ino;
                         pde_get(de);
                         spin_unlock(&proc_subdir_lock);
                         error = -EINVAL;
-                        inode = proc_get_inode(dir->i_sb, ino, de);
+                        inode = proc_get_inode(dir->i_sb, de);
                         goto out_unlock;
                 }
         }
@@ -768,12 +765,7 @@ EXPORT_SYMBOL(proc_create_data);
 
 static void free_proc_entry(struct proc_dir_entry *de)
 {
-        unsigned int ino = de->low_ino;
-
-        if (ino < PROC_DYNAMIC_FIRST)
-                return;
-
-        release_inode_number(ino);
+        release_inode_number(de->low_ino);
 
         if (S_ISLNK(de->mode))
                 kfree(de->data);
@@ -834,12 +826,9 @@ void remove_proc_entry(const char *name, struct proc_dir_entry *parent)
 
                 wait_for_completion(de->pde_unload_completion);
 
-                goto continue_removing;
+                spin_lock(&de->pde_unload_lock);
         }
-        spin_unlock(&de->pde_unload_lock);
 
-continue_removing:
-        spin_lock(&de->pde_unload_lock);
         while (!list_empty(&de->pde_openers)) {
                 struct pde_opener *pdeo;
 
diff --git a/fs/proc/inode.c b/fs/proc/inode.c
index 6bcb926b101b..176ce4cda68a 100644
--- a/fs/proc/inode.c
+++ b/fs/proc/inode.c
@@ -416,12 +416,11 @@ static const struct file_operations proc_reg_file_ops_no_compat = {
 };
 #endif
 
-struct inode *proc_get_inode(struct super_block *sb, unsigned int ino,
-                                struct proc_dir_entry *de)
+struct inode *proc_get_inode(struct super_block *sb, struct proc_dir_entry *de)
 {
         struct inode * inode;
 
-        inode = iget_locked(sb, ino);
+        inode = iget_locked(sb, de->low_ino);
         if (!inode)
                 return NULL;
         if (inode->i_state & I_NEW) {
@@ -471,7 +470,7 @@ int proc_fill_super(struct super_block *s)
         s->s_time_gran = 1;
         
         pde_get(&proc_root);
-        root_inode = proc_get_inode(s, PROC_ROOT_INO, &proc_root);
+        root_inode = proc_get_inode(s, &proc_root);
         if (!root_inode)
                 goto out_no_root;
         root_inode->i_uid = 0;
diff --git a/fs/proc/internal.h b/fs/proc/internal.h
index 1f24a3eddd12..9ad561ded409 100644
--- a/fs/proc/internal.h
+++ b/fs/proc/internal.h
@@ -96,7 +96,8 @@ extern spinlock_t proc_subdir_lock;
 struct dentry *proc_pid_lookup(struct inode *dir, struct dentry * dentry, struct nameidata *);
 int proc_pid_readdir(struct file * filp, void * dirent, filldir_t filldir);
 unsigned long task_vsize(struct mm_struct *);
-int task_statm(struct mm_struct *, int *, int *, int *, int *);
+unsigned long task_statm(struct mm_struct *,
+        unsigned long *, unsigned long *, unsigned long *, unsigned long *);
 void task_mem(struct seq_file *, struct mm_struct *);
 
 static inline struct proc_dir_entry *pde_get(struct proc_dir_entry *pde)
@@ -108,7 +109,7 @@ void pde_put(struct proc_dir_entry *pde);
 
 extern struct vfsmount *proc_mnt;
 int proc_fill_super(struct super_block *);
-struct inode *proc_get_inode(struct super_block *, unsigned int, struct proc_dir_entry *);
+struct inode *proc_get_inode(struct super_block *, struct proc_dir_entry *);
 
 /*
  * These are generic /proc routines that use the internal
diff --git a/fs/proc/kcore.c b/fs/proc/kcore.c
index 6f37c391468d..d245cb23dd72 100644
--- a/fs/proc/kcore.c
+++ b/fs/proc/kcore.c
@@ -558,7 +558,7 @@ static int open_kcore(struct inode *inode, struct file *filp)
 static const struct file_operations proc_kcore_operations = {
         .read           = read_kcore,
         .open           = open_kcore,
-        .llseek         = generic_file_llseek,
+        .llseek         = default_llseek,
 };
 
 #ifdef CONFIG_MEMORY_HOTPLUG
diff --git a/fs/proc/meminfo.c b/fs/proc/meminfo.c
index a65239cfd97e..ed257d141568 100644
--- a/fs/proc/meminfo.c
+++ b/fs/proc/meminfo.c
@@ -101,6 +101,9 @@ static int meminfo_proc_show(struct seq_file *m, void *v)
 #ifdef CONFIG_MEMORY_FAILURE
                 "HardwareCorrupted: %5lu kB\n"
 #endif
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+                "AnonHugePages:  %8lu kB\n"
+#endif
                 ,
                 K(i.totalram),
                 K(i.freeram),
@@ -128,7 +131,12 @@ static int meminfo_proc_show(struct seq_file *m, void *v)
                 K(i.freeswap),
                 K(global_page_state(NR_FILE_DIRTY)),
                 K(global_page_state(NR_WRITEBACK)),
-                K(global_page_state(NR_ANON_PAGES)),
+                K(global_page_state(NR_ANON_PAGES)
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+                  + global_page_state(NR_ANON_TRANSPARENT_HUGEPAGES) *
+                  HPAGE_PMD_NR
+#endif
+                  ),
                 K(global_page_state(NR_FILE_MAPPED)),
                 K(global_page_state(NR_SHMEM)),
                 K(global_page_state(NR_SLAB_RECLAIMABLE) +
@@ -151,6 +159,10 @@ static int meminfo_proc_show(struct seq_file *m, void *v)
 #ifdef CONFIG_MEMORY_FAILURE
                 ,atomic_long_read(&mce_bad_pages) << (PAGE_SHIFT - 10)
 #endif
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+                ,K(global_page_state(NR_ANON_TRANSPARENT_HUGEPAGES) *
+                   HPAGE_PMD_NR)
+#endif
                 );
 
         hugetlb_report_meminfo(m);
diff --git a/fs/proc/page.c b/fs/proc/page.c
index 3b8b45660331..6d8e6a9e93ab 100644
--- a/fs/proc/page.c
+++ b/fs/proc/page.c
@@ -40,7 +40,7 @@ static ssize_t kpagecount_read(struct file *file, char __user *buf,
                         ppage = pfn_to_page(pfn);
                 else
                         ppage = NULL;
-                if (!ppage)
+                if (!ppage || PageSlab(ppage))
                         pcount = 0;
                 else
                         pcount = page_mapcount(ppage);
@@ -116,15 +116,17 @@ u64 stable_page_flags(struct page *page)
         if (PageHuge(page))
                 u |= 1 << KPF_HUGE;
 
-        u |= kpf_copy_bit(k, KPF_LOCKED,        PG_locked);
-
         /*
-         * Caveats on high order pages:
-         * PG_buddy will only be set on the head page; SLUB/SLQB do the same
-         * for PG_slab; SLOB won't set PG_slab at all on compound pages.
+         * Caveats on high order pages: page->_count will only be set
+         * -1 on the head page; SLUB/SLQB do the same for PG_slab;
+         * SLOB won't set PG_slab at all on compound pages.
          */
+        if (PageBuddy(page))
+                u |= 1 << KPF_BUDDY;
+
+        u |= kpf_copy_bit(k, KPF_LOCKED,        PG_locked);
+
         u |= kpf_copy_bit(k, KPF_SLAB,          PG_slab);
-        u |= kpf_copy_bit(k, KPF_BUDDY,         PG_buddy);
 
         u |= kpf_copy_bit(k, KPF_ERROR,         PG_error);
         u |= kpf_copy_bit(k, KPF_DIRTY,         PG_dirty);
diff --git a/fs/proc/proc_tty.c b/fs/proc/proc_tty.c
index 83adcc869437..cb761f010300 100644
--- a/fs/proc/proc_tty.c
+++ b/fs/proc/proc_tty.c
@@ -36,27 +36,27 @@ static void show_tty_range(struct seq_file *m, struct tty_driver *p,
         }
         switch (p->type) {
         case TTY_DRIVER_TYPE_SYSTEM:
-                seq_printf(m, "system");
+                seq_puts(m, "system");
                 if (p->subtype == SYSTEM_TYPE_TTY)
-                        seq_printf(m, ":/dev/tty");
+                        seq_puts(m, ":/dev/tty");
                 else if (p->subtype == SYSTEM_TYPE_SYSCONS)
-                        seq_printf(m, ":console");
+                        seq_puts(m, ":console");
                 else if (p->subtype == SYSTEM_TYPE_CONSOLE)
-                        seq_printf(m, ":vtmaster");
+                        seq_puts(m, ":vtmaster");
                 break;
         case TTY_DRIVER_TYPE_CONSOLE:
-                seq_printf(m, "console");
+                seq_puts(m, "console");
                 break;
         case TTY_DRIVER_TYPE_SERIAL:
-                seq_printf(m, "serial");
+                seq_puts(m, "serial");
                 break;
         case TTY_DRIVER_TYPE_PTY:
                 if (p->subtype == PTY_TYPE_MASTER)
-                        seq_printf(m, "pty:master");
+                        seq_puts(m, "pty:master");
                 else if (p->subtype == PTY_TYPE_SLAVE)
-                        seq_printf(m, "pty:slave");
+                        seq_puts(m, "pty:slave");
                 else
-                        seq_printf(m, "pty");
+                        seq_puts(m, "pty");
                 break;
         default:
                 seq_printf(m, "type:%d.%d", p->type, p->subtype);
@@ -74,19 +74,19 @@ static int show_tty_driver(struct seq_file *m, void *v)
                 /* pseudo-drivers first */
                 seq_printf(m, "%-20s /dev/%-8s ", "/dev/tty", "tty");
                 seq_printf(m, "%3d %7d ", TTYAUX_MAJOR, 0);
-                seq_printf(m, "system:/dev/tty\n");
+                seq_puts(m, "system:/dev/tty\n");
                 seq_printf(m, "%-20s /dev/%-8s ", "/dev/console", "console");
                 seq_printf(m, "%3d %7d ", TTYAUX_MAJOR, 1);
-                seq_printf(m, "system:console\n");
+                seq_puts(m, "system:console\n");
 #ifdef CONFIG_UNIX98_PTYS
                 seq_printf(m, "%-20s /dev/%-8s ", "/dev/ptmx", "ptmx");
                 seq_printf(m, "%3d %7d ", TTYAUX_MAJOR, 2);
-                seq_printf(m, "system\n");
+                seq_puts(m, "system\n");
 #endif
 #ifdef CONFIG_VT
                 seq_printf(m, "%-20s /dev/%-8s ", "/dev/vc/0", "vc/0");
                 seq_printf(m, "%3d %7d ", TTY_MAJOR, 0);
-                seq_printf(m, "system:vtmaster\n");
+                seq_puts(m, "system:vtmaster\n");
 #endif
         }
 
diff --git a/fs/proc/softirqs.c b/fs/proc/softirqs.c
index 37994737c983..62604be9f58d 100644
--- a/fs/proc/softirqs.c
+++ b/fs/proc/softirqs.c
@@ -10,16 +10,16 @@ static int show_softirqs(struct seq_file *p, void *v)
 {
         int i, j;
 
-        seq_printf(p, "                    ");
+        seq_puts(p, "                    ");
         for_each_possible_cpu(i)
                 seq_printf(p, "CPU%-8d", i);
-        seq_printf(p, "\n");
+        seq_putc(p, '\n');
 
         for (i = 0; i < NR_SOFTIRQS; i++) {
                 seq_printf(p, "%12s:", softirq_to_name[i]);
                 for_each_possible_cpu(j)
                         seq_printf(p, " %10u", kstat_softirqs_cpu(i, j));
-                seq_printf(p, "\n");
+                seq_putc(p, '\n');
         }
         return 0;
 }
diff --git a/fs/proc/stat.c b/fs/proc/stat.c
index e15a19c93bae..1cffa2b8a2fc 100644
--- a/fs/proc/stat.c
+++ b/fs/proc/stat.c
@@ -126,7 +126,7 @@ static int show_stat(struct seq_file *p, void *v)
 
         for (i = 0; i < NR_SOFTIRQS; i++)
                 seq_printf(p, " %u", per_softirq_sums[i]);
-        seq_printf(p, "\n");
+        seq_putc(p, '\n');
 
         return 0;
 }
diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c
index c126c83b9a45..60b914860f81 100644
--- a/fs/proc/task_mmu.c
+++ b/fs/proc/task_mmu.c
@@ -66,8 +66,9 @@ unsigned long task_vsize(struct mm_struct *mm)
         return PAGE_SIZE * mm->total_vm;
 }
 
-int task_statm(struct mm_struct *mm, int *shared, int *text,
-               int *data, int *resident)
+unsigned long task_statm(struct mm_struct *mm,
+                         unsigned long *shared, unsigned long *text,
+                         unsigned long *data, unsigned long *resident)
 {
         *shared = get_mm_counter(mm, MM_FILEPAGES);
         *text = (PAGE_ALIGN(mm->end_code) - (mm->start_code & PAGE_MASK))
@@ -417,7 +418,8 @@ static int show_smap(struct seq_file *m, void *v)
                    "Anonymous:      %8lu kB\n"
                    "Swap:           %8lu kB\n"
                    "KernelPageSize: %8lu kB\n"
-                   "MMUPageSize:    %8lu kB\n",
+                   "MMUPageSize:    %8lu kB\n"
+                   "Locked:         %8lu kB\n",
                    (vma->vm_end - vma->vm_start) >> 10,
                    mss.resident >> 10,
                    (unsigned long)(mss.pss >> (10 + PSS_SHIFT)),
@@ -429,7 +431,9 @@ static int show_smap(struct seq_file *m, void *v)
                    mss.anonymous >> 10,
                    mss.swap >> 10,
                    vma_kernel_pagesize(vma) >> 10,
-                   vma_mmu_pagesize(vma) >> 10);
+                   vma_mmu_pagesize(vma) >> 10,
+                   (vma->vm_flags & VM_LOCKED) ?
+                        (unsigned long)(mss.pss >> (10 + PSS_SHIFT)) : 0);
 
         if (m->count < m->size)  /* vma is copied successfully */
                 m->version = (vma != get_gate_vma(task)) ? vma->vm_start : 0;
diff --git a/fs/proc/task_nommu.c b/fs/proc/task_nommu.c
index cb6306e63843..b535d3e5d5f1 100644
--- a/fs/proc/task_nommu.c
+++ b/fs/proc/task_nommu.c
@@ -92,13 +92,14 @@ unsigned long task_vsize(struct mm_struct *mm)
         return vsize;
 }
 
-int task_statm(struct mm_struct *mm, int *shared, int *text,
-               int *data, int *resident)
+unsigned long task_statm(struct mm_struct *mm,
+                         unsigned long *shared, unsigned long *text,
+                         unsigned long *data, unsigned long *resident)
 {
         struct vm_area_struct *vma;
         struct vm_region *region;
         struct rb_node *p;
-        int size = kobjsize(mm);
+        unsigned long size = kobjsize(mm);
 
         down_read(&mm->mmap_sem);
         for (p = rb_first(&mm->mm_rb); p; p = rb_next(p)) {
diff --git a/fs/read_write.c b/fs/read_write.c
index 5d431bacbea9..5520f8ad5504 100644
--- a/fs/read_write.c
+++ b/fs/read_write.c
@@ -30,18 +30,9 @@ const struct file_operations generic_ro_fops = {
 
 EXPORT_SYMBOL(generic_ro_fops);
 
-static int
-__negative_fpos_check(struct file *file, loff_t pos, size_t count)
+static inline int unsigned_offsets(struct file *file)
 {
-        /*
-         * pos or pos+count is negative here, check overflow.
-         * too big "count" will be caught in rw_verify_area().
-         */
-        if ((pos < 0) && (pos + count < pos))
-                return -EOVERFLOW;
-        if (file->f_mode & FMODE_UNSIGNED_OFFSET)
-                return 0;
-        return -EINVAL;
+        return file->f_mode & FMODE_UNSIGNED_OFFSET;
 }
 
 /**
@@ -75,7 +66,7 @@ generic_file_llseek_unlocked(struct file *file, loff_t offset, int origin)
                 break;
         }
 
-        if (offset < 0 && __negative_fpos_check(file, offset, 0))
+        if (offset < 0 && !unsigned_offsets(file))
                 return -EINVAL;
         if (offset > inode->i_sb->s_maxbytes)
                 return -EINVAL;
@@ -152,7 +143,7 @@ loff_t default_llseek(struct file *file, loff_t offset, int origin)
                         offset += file->f_pos;
         }
         retval = -EINVAL;
-        if (offset >= 0 || !__negative_fpos_check(file, offset, 0)) {
+        if (offset >= 0 || unsigned_offsets(file)) {
                 if (offset != file->f_pos) {
                         file->f_pos = offset;
                         file->f_version = 0;
@@ -252,9 +243,13 @@ int rw_verify_area(int read_write, struct file *file, loff_t *ppos, size_t count
         if (unlikely((ssize_t) count < 0))
                 return retval;
         pos = *ppos;
-        if (unlikely((pos < 0) || (loff_t) (pos + count) < 0)) {
-                retval = __negative_fpos_check(file, pos, count);
-                if (retval)
+        if (unlikely(pos < 0)) {
+                if (!unsigned_offsets(file))
+                        return retval;
+                if (count >= -pos) /* both values are in 0..LLONG_MAX */
+                        return -EOVERFLOW;
+        } else if (unlikely((loff_t) (pos + count) < 0)) {
+                if (!unsigned_offsets(file))
                         return retval;
         }
 
diff --git a/fs/reiserfs/journal.c b/fs/reiserfs/journal.c
index d31bce1a9f90..3eea859e6990 100644
--- a/fs/reiserfs/journal.c
+++ b/fs/reiserfs/journal.c
@@ -2551,8 +2551,6 @@ static int release_journal_dev(struct super_block *super,
         result = 0;
 
         if (journal->j_dev_bd != NULL) {
-                if (journal->j_dev_bd->bd_dev != super->s_dev)
-                        bd_release(journal->j_dev_bd);
                 result = blkdev_put(journal->j_dev_bd, journal->j_dev_mode);
                 journal->j_dev_bd = NULL;
         }
@@ -2570,7 +2568,7 @@ static int journal_init_dev(struct super_block *super,
 {
         int result;
         dev_t jdev;
-        fmode_t blkdev_mode = FMODE_READ | FMODE_WRITE;
+        fmode_t blkdev_mode = FMODE_READ | FMODE_WRITE | FMODE_EXCL;
         char b[BDEVNAME_SIZE];
 
         result = 0;
@@ -2584,7 +2582,10 @@ static int journal_init_dev(struct super_block *super,
 
         /* there is no "jdev" option and journal is on separate device */
         if ((!jdev_name || !jdev_name[0])) {
-                journal->j_dev_bd = open_by_devnum(jdev, blkdev_mode);
+                if (jdev == super->s_dev)
+                        blkdev_mode &= ~FMODE_EXCL;
+                journal->j_dev_bd = blkdev_get_by_dev(jdev, blkdev_mode,
+                                                      journal);
                 journal->j_dev_mode = blkdev_mode;
                 if (IS_ERR(journal->j_dev_bd)) {
                         result = PTR_ERR(journal->j_dev_bd);
@@ -2593,22 +2594,14 @@ static int journal_init_dev(struct super_block *super,
                                          "cannot init journal device '%s': %i",
                                          __bdevname(jdev, b), result);
                         return result;
-                } else if (jdev != super->s_dev) {
-                        result = bd_claim(journal->j_dev_bd, journal);
-                        if (result) {
-                                blkdev_put(journal->j_dev_bd, blkdev_mode);
-                                return result;
-                        }
-
+                } else if (jdev != super->s_dev)
                         set_blocksize(journal->j_dev_bd, super->s_blocksize);
-                }
 
                 return 0;
         }
 
         journal->j_dev_mode = blkdev_mode;
-        journal->j_dev_bd = open_bdev_exclusive(jdev_name,
-                                                blkdev_mode, journal);
+        journal->j_dev_bd = blkdev_get_by_path(jdev_name, blkdev_mode, journal);
         if (IS_ERR(journal->j_dev_bd)) {
                 result = PTR_ERR(journal->j_dev_bd);
                 journal->j_dev_bd = NULL;
diff --git a/fs/reiserfs/prints.c b/fs/reiserfs/prints.c
index adbc6f538515..45de98b59466 100644
--- a/fs/reiserfs/prints.c
+++ b/fs/reiserfs/prints.c
@@ -586,13 +586,13 @@ void print_block(struct buffer_head *bh, ...)	//int print_mode, int first, int l
         va_list args;
         int mode, first, last;
 
-        va_start(args, bh);
-
         if (!bh) {
                 printk("print_block: buffer is NULL\n");
                 return;
         }
 
+        va_start(args, bh);
+
         mode = va_arg(args, int);
         first = va_arg(args, int);
         last = va_arg(args, int);
diff --git a/fs/select.c b/fs/select.c
index b7b10aa30861..e56560d2b08a 100644
--- a/fs/select.c
+++ b/fs/select.c
@@ -306,6 +306,8 @@ static int poll_select_copy_remaining(struct timespec *end_time, void __user *p,
                 rts.tv_sec = rts.tv_nsec = 0;
 
         if (timeval) {
+                if (sizeof(rtv) > sizeof(rtv.tv_sec) + sizeof(rtv.tv_usec))
+                        memset(&rtv, 0, sizeof(rtv));
                 rtv.tv_sec = rts.tv_sec;
                 rtv.tv_usec = rts.tv_nsec / NSEC_PER_USEC;
 
diff --git a/fs/splice.c b/fs/splice.c
index ce2f02579e35..50a5d978da16 100644
--- a/fs/splice.c
+++ b/fs/splice.c
@@ -682,19 +682,14 @@ static int pipe_to_sendpage(struct pipe_inode_info *pipe,
 {
         struct file *file = sd->u.file;
         loff_t pos = sd->pos;
-        int ret, more;
-
-        ret = buf->ops->confirm(pipe, buf);
-        if (!ret) {
-                more = (sd->flags & SPLICE_F_MORE) || sd->len < sd->total_len;
-                if (file->f_op && file->f_op->sendpage)
-                        ret = file->f_op->sendpage(file, buf->page, buf->offset,
-                                                   sd->len, &pos, more);
-                else
-                        ret = -EINVAL;
-        }
+        int more;
 
-        return ret;
+        if (!likely(file->f_op && file->f_op->sendpage))
+                return -EINVAL;
+
+        more = (sd->flags & SPLICE_F_MORE) || sd->len < sd->total_len;
+        return file->f_op->sendpage(file, buf->page, buf->offset,
+                                    sd->len, &pos, more);
 }
 
 /*
@@ -727,13 +722,6 @@ int pipe_to_file(struct pipe_inode_info *pipe, struct pipe_buffer *buf,
         void *fsdata;
         int ret;
 
-        /*
-         * make sure the data in this buffer is uptodate
-         */
-        ret = buf->ops->confirm(pipe, buf);
-        if (unlikely(ret))
-                return ret;
-
         offset = sd->pos & ~PAGE_CACHE_MASK;
 
         this_len = sd->len;
@@ -805,12 +793,17 @@ int splice_from_pipe_feed(struct pipe_inode_info *pipe, struct splice_desc *sd,
                 if (sd->len > sd->total_len)
                         sd->len = sd->total_len;
 
-                ret = actor(pipe, buf, sd);
-                if (ret <= 0) {
+                ret = buf->ops->confirm(pipe, buf);
+                if (unlikely(ret)) {
                         if (ret == -ENODATA)
                                 ret = 0;
                         return ret;
                 }
+
+                ret = actor(pipe, buf, sd);
+                if (ret <= 0)
+                        return ret;
+
                 buf->offset += ret;
                 buf->len -= ret;
 
@@ -1044,10 +1037,6 @@ static int write_pipe_buf(struct pipe_inode_info *pipe, struct pipe_buffer *buf,
         int ret;
         void *data;
 
-        ret = buf->ops->confirm(pipe, buf);
-        if (ret)
-                return ret;
-
         data = buf->ops->map(pipe, buf, 0);
         ret = kernel_write(sd->u.file, data + buf->offset, sd->len, sd->pos);
         buf->ops->unmap(pipe, buf, data);
@@ -1495,10 +1484,6 @@ static int pipe_to_user(struct pipe_inode_info *pipe, struct pipe_buffer *buf,
         char *src;
         int ret;
 
-        ret = buf->ops->confirm(pipe, buf);
-        if (unlikely(ret))
-                return ret;
-
         /*
          * See if we can use the atomic maps, by prefaulting in the
          * pages and doing an atomic copy
diff --git a/fs/super.c b/fs/super.c
index 823e061faa87..4f6a3571a634 100644
--- a/fs/super.c
+++ b/fs/super.c
@@ -767,13 +767,13 @@ struct dentry *mount_bdev(struct file_system_type *fs_type,
 {
         struct block_device *bdev;
         struct super_block *s;
-        fmode_t mode = FMODE_READ;
+        fmode_t mode = FMODE_READ | FMODE_EXCL;
         int error = 0;
 
         if (!(flags & MS_RDONLY))
                 mode |= FMODE_WRITE;
 
-        bdev = open_bdev_exclusive(dev_name, mode, fs_type);
+        bdev = blkdev_get_by_path(dev_name, mode, fs_type);
         if (IS_ERR(bdev))
                 return ERR_CAST(bdev);
 
@@ -802,13 +802,13 @@ struct dentry *mount_bdev(struct file_system_type *fs_type,
 
                 /*
                  * s_umount nests inside bd_mutex during
-                 * __invalidate_device().  close_bdev_exclusive()
-                 * acquires bd_mutex and can't be called under
-                 * s_umount.  Drop s_umount temporarily.  This is safe
-                 * as we're holding an active reference.
+                 * __invalidate_device().  blkdev_put() acquires
+                 * bd_mutex and can't be called under s_umount.  Drop
+                 * s_umount temporarily.  This is safe as we're
+                 * holding an active reference.
                  */
                 up_write(&s->s_umount);
-                close_bdev_exclusive(bdev, mode);
+                blkdev_put(bdev, mode);
                 down_write(&s->s_umount);
         } else {
                 char b[BDEVNAME_SIZE];
@@ -832,7 +832,7 @@ struct dentry *mount_bdev(struct file_system_type *fs_type,
 error_s:
         error = PTR_ERR(s);
 error_bdev:
-        close_bdev_exclusive(bdev, mode);
+        blkdev_put(bdev, mode);
 error:
         return ERR_PTR(error);
 }
@@ -863,7 +863,8 @@ void kill_block_super(struct super_block *sb)
         bdev->bd_super = NULL;
         generic_shutdown_super(sb);
         sync_blockdev(bdev);
-        close_bdev_exclusive(bdev, mode);
+        WARN_ON_ONCE(!(mode & FMODE_EXCL));
+        blkdev_put(bdev, mode | FMODE_EXCL);
 }
 
 EXPORT_SYMBOL(kill_block_super);
diff --git a/fs/sysv/namei.c b/fs/sysv/namei.c
index b5e68da2db32..b427b1208c26 100644
--- a/fs/sysv/namei.c
+++ b/fs/sysv/namei.c
@@ -48,7 +48,6 @@ static struct dentry *sysv_lookup(struct inode * dir, struct dentry * dentry, st
         struct inode * inode = NULL;
         ino_t ino;
 
-        d_set_d_op(dentry, dir->i_sb->s_root->d_op);
         if (dentry->d_name.len > SYSV_NAMELEN)
                 return ERR_PTR(-ENAMETOOLONG);
         ino = sysv_inode_by_name(dentry);
diff --git a/fs/sysv/super.c b/fs/sysv/super.c
index 76712aefc4ab..f60c196913ea 100644
--- a/fs/sysv/super.c
+++ b/fs/sysv/super.c
@@ -332,6 +332,10 @@ static int complete_read_super(struct super_block *sb, int silent, int size)
         sb->s_magic = SYSV_MAGIC_BASE + sbi->s_type;
         /* set up enough so that it can read an inode */
         sb->s_op = &sysv_sops;
+        if (sbi->s_forced_ro)
+                sb->s_flags |= MS_RDONLY;
+        if (sbi->s_truncate)
+                sb->s_d_op = &sysv_dentry_operations;
         root_inode = sysv_iget(sb, SYSV_ROOT_INO);
         if (IS_ERR(root_inode)) {
                 printk("SysV FS: get root inode failed\n");
@@ -343,10 +347,6 @@ static int complete_read_super(struct super_block *sb, int silent, int size)
                 printk("SysV FS: get root dentry failed\n");
                 return 0;
         }
-        if (sbi->s_forced_ro)
-                sb->s_flags |= MS_RDONLY;
-        if (sbi->s_truncate)
-                d_set_d_op(sb->s_root, &sysv_dentry_operations);
         return 1;
 }
 
diff --git a/fs/xfs/linux-2.6/xfs_iops.c b/fs/xfs/linux-2.6/xfs_iops.c
index 94d5fd6a2973..da54403633b6 100644
--- a/fs/xfs/linux-2.6/xfs_iops.c
+++ b/fs/xfs/linux-2.6/xfs_iops.c
@@ -516,6 +516,7 @@ xfs_vn_fallocate(
         loff_t          new_size = 0;
         xfs_flock64_t   bf;
         xfs_inode_t     *ip = XFS_I(inode);
+        int             cmd = XFS_IOC_RESVSP;
 
         /* preallocation on directories not yet supported */
         error = -ENODEV;
@@ -528,6 +529,9 @@ xfs_vn_fallocate(
 
         xfs_ilock(ip, XFS_IOLOCK_EXCL);
 
+        if (mode & FALLOC_FL_PUNCH_HOLE)
+                cmd = XFS_IOC_UNRESVSP;
+
         /* check the new inode size is valid before allocating */
         if (!(mode & FALLOC_FL_KEEP_SIZE) &&
             offset + len > i_size_read(inode)) {
@@ -537,8 +541,7 @@ xfs_vn_fallocate(
                         goto out_unlock;
         }
 
-        error = -xfs_change_file_space(ip, XFS_IOC_RESVSP, &bf,
-                                       0, XFS_ATTR_NOLOCK);
+        error = -xfs_change_file_space(ip, cmd, &bf, 0, XFS_ATTR_NOLOCK);
         if (error)
                 goto out_unlock;
 
diff --git a/fs/xfs/linux-2.6/xfs_super.c b/fs/xfs/linux-2.6/xfs_super.c
index c51faaa5e291..bd07f7339366 100644
--- a/fs/xfs/linux-2.6/xfs_super.c
+++ b/fs/xfs/linux-2.6/xfs_super.c
@@ -606,7 +606,8 @@ xfs_blkdev_get(
 {
         int                     error = 0;
 
-        *bdevp = open_bdev_exclusive(name, FMODE_READ|FMODE_WRITE, mp);
+        *bdevp = blkdev_get_by_path(name, FMODE_READ|FMODE_WRITE|FMODE_EXCL,
+                                    mp);
         if (IS_ERR(*bdevp)) {
                 error = PTR_ERR(*bdevp);
                 printk("XFS: Invalid device [%s], error=%d\n", name, error);
@@ -620,7 +621,7 @@ xfs_blkdev_put(
         struct block_device     *bdev)
 {
         if (bdev)
-                close_bdev_exclusive(bdev, FMODE_READ|FMODE_WRITE);
+                blkdev_put(bdev, FMODE_READ|FMODE_WRITE|FMODE_EXCL);
 }
 
 /*
@@ -947,7 +948,7 @@ out_reclaim:
  * Slab object creation initialisation for the XFS inode.
  * This covers only the idempotent fields in the XFS inode;
  * all other fields need to be initialised on allocation
- * from the slab. This avoids the need to repeatedly intialise
+ * from the slab. This avoids the need to repeatedly initialise
  * fields in the xfs inode that left in the initialise state
  * when freeing the inode.
  */