Merge branch 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/viro/vfs-2.6

* 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/viro/vfs-2.6: (25 commits)
  cifs: remove unnecessary dentry_unhash on rmdir/rename_dir
  ocfs2: remove unnecessary dentry_unhash on rmdir/rename_dir
  exofs: remove unnecessary dentry_unhash on rmdir/rename_dir
  nfs: remove unnecessary dentry_unhash on rmdir/rename_dir
  ext2: remove unnecessary dentry_unhash on rmdir/rename_dir
  ext3: remove unnecessary dentry_unhash on rmdir/rename_dir
  ext4: remove unnecessary dentry_unhash on rmdir/rename_dir
  btrfs: remove unnecessary dentry_unhash in rmdir/rename_dir
  ceph: remove unnecessary dentry_unhash calls
  vfs: clean up vfs_rename_other
  vfs: clean up vfs_rename_dir
  vfs: clean up vfs_rmdir
  vfs: fix vfs_rename_dir for FS_RENAME_DOES_D_MOVE filesystems
  libfs: drop unneeded dentry_unhash
  vfs: update dentry_unhash() comment
  vfs: push dentry_unhash on rename_dir into file systems
  vfs: push dentry_unhash on rmdir into file systems
  vfs: remove dget() from dentry_unhash()
  vfs: dentry_unhash immediately prior to rmdir
  vfs: Block mmapped writes while the fs is frozen
  ...

32 files changed, 316 insertions, 269 deletions

diff --git a/fs/9p/vfs_inode.c b/fs/9p/vfs_inode.c
index 7f6c6770319..8d7f3e69ae2 100644
--- a/fs/9p/vfs_inode.c
+++ b/fs/9p/vfs_inode.c
@@ -814,6 +814,7 @@ int v9fs_vfs_unlink(struct inode *i, struct dentry *d)
 
 int v9fs_vfs_rmdir(struct inode *i, struct dentry *d)
 {
+	dentry_unhash(d);
 	return v9fs_remove(i, d, 1);
 }
 
@@ -839,6 +840,9 @@ v9fs_vfs_rename(struct inode *old_dir, struct dentry *old_dentry,
 	struct p9_fid *newdirfid;
 	struct p9_wstat wstat;
 
+	if (new_dentry->d_inode && S_ISDIR(new_dentry->d_inode->i_mode))
+		dentry_unhash(new_dentry);
+
 	P9_DPRINTK(P9_DEBUG_VFS, "\n");
 	retval = 0;
 	old_inode = old_dentry->d_inode;
diff --git a/fs/Kconfig b/fs/Kconfig
index f6edba2e069..19891aab9c6 100644
--- a/fs/Kconfig
+++ b/fs/Kconfig
@@ -47,7 +47,7 @@ config FS_POSIX_ACL
 	def_bool n
 
 config EXPORTFS
-	bool
+	tristate
 
 config FILE_LOCKING
 	bool "Enable POSIX file locking API" if EXPERT
diff --git a/fs/affs/namei.c b/fs/affs/namei.c
index e3e9efc1fdd..03330e2e390 100644
--- a/fs/affs/namei.c
+++ b/fs/affs/namei.c
@@ -320,6 +320,8 @@ affs_rmdir(struct inode *dir, struct dentry *dentry)
 		 dentry->d_inode->i_ino,
 		 (int)dentry->d_name.len, dentry->d_name.name);
 
+	dentry_unhash(dentry);
+
 	return affs_remove_header(dentry);
 }
 
@@ -417,6 +419,9 @@ affs_rename(struct inode *old_dir, struct dentry *old_dentry,
 	struct buffer_head *bh = NULL;
 	int retval;
 
+	if (new_dentry->d_inode && S_ISDIR(new_dentry->d_inode->i_mode))
+		dentry_unhash(new_dentry);
+
 	pr_debug("AFFS: rename(old=%u,\"%*s\" to new=%u,\"%*s\")\n",
 		 (u32)old_dir->i_ino, (int)old_dentry->d_name.len, old_dentry->d_name.name,
 		 (u32)new_dir->i_ino, (int)new_dentry->d_name.len, new_dentry->d_name.name);
diff --git a/fs/afs/dir.c b/fs/afs/dir.c
index 20c106f2492..2c4e0516004 100644
--- a/fs/afs/dir.c
+++ b/fs/afs/dir.c
@@ -845,6 +845,8 @@ static int afs_rmdir(struct inode *dir, struct dentry *dentry)
 	_enter("{%x:%u},{%s}",
 	       dvnode->fid.vid, dvnode->fid.vnode, dentry->d_name.name);
 
+	dentry_unhash(dentry);
+
 	ret = -ENAMETOOLONG;
 	if (dentry->d_name.len >= AFSNAMEMAX)
 		goto error;
@@ -1146,6 +1148,9 @@ static int afs_rename(struct inode *old_dir, struct dentry *old_dentry,
 	struct key *key;
 	int ret;
 
+	if (new_dentry->d_inode && S_ISDIR(new_dentry->d_inode->i_mode))
+		dentry_unhash(new_dentry);
+
 	vnode = AFS_FS_I(old_dentry->d_inode);
 	orig_dvnode = AFS_FS_I(old_dir);
 	new_dvnode = AFS_FS_I(new_dir);
diff --git a/fs/autofs4/root.c b/fs/autofs4/root.c
index f55ae23b137..87d95a8cddb 100644
--- a/fs/autofs4/root.c
+++ b/fs/autofs4/root.c
@@ -583,6 +583,8 @@ static int autofs4_dir_unlink(struct inode *dir, struct dentry *dentry)
 	if (!autofs4_oz_mode(sbi) && !capable(CAP_SYS_ADMIN))
 		return -EACCES;
 
+	dentry_unhash(dentry);
+
 	if (atomic_dec_and_test(&ino->count)) {
 		p_ino = autofs4_dentry_ino(dentry->d_parent);
 		if (p_ino && dentry->d_parent != dentry)
diff --git a/fs/bfs/dir.c b/fs/bfs/dir.c
index b14cebfd904..c7d1d06b048 100644
--- a/fs/bfs/dir.c
+++ b/fs/bfs/dir.c
@@ -224,6 +224,9 @@ static int bfs_rename(struct inode *old_dir, struct dentry *old_dentry,
 	struct bfs_sb_info *info;
 	int error = -ENOENT;
 
+	if (new_dentry->d_inode && S_ISDIR(new_dentry->d_inode->i_mode))
+		dentry_unhash(new_dentry);
+
 	old_bh = new_bh = NULL;
 	old_inode = old_dentry->d_inode;
 	if (S_ISDIR(old_inode->i_mode))
diff --git a/fs/buffer.c b/fs/buffer.c
index a08bb8e61c6..b0675bfe820 100644
--- a/fs/buffer.c
+++ b/fs/buffer.c
@@ -2331,24 +2331,26 @@ EXPORT_SYMBOL(block_commit_write);
  * page lock we can determine safely if the page is beyond EOF. If it is not
  * beyond EOF, then the page is guaranteed safe against truncation until we
  * unlock the page.
+ *
+ * Direct callers of this function should call vfs_check_frozen() so that page
+ * fault does not busyloop until the fs is thawed.
  */
-int
-block_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf,
-		   get_block_t get_block)
+int __block_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf,
+			 get_block_t get_block)
 {
 	struct page *page = vmf->page;
 	struct inode *inode = vma->vm_file->f_path.dentry->d_inode;
 	unsigned long end;
 	loff_t size;
-	int ret = VM_FAULT_NOPAGE; /* make the VM retry the fault */
+	int ret;
 
 	lock_page(page);
 	size = i_size_read(inode);
 	if ((page->mapping != inode->i_mapping) ||
 	    (page_offset(page) > size)) {
-		/* page got truncated out from underneath us */
-		unlock_page(page);
-		goto out;
+		/* We overload EFAULT to mean page got truncated */
+		ret = -EFAULT;
+		goto out_unlock;
 	}
 
 	/* page is wholly or partially inside EOF */
@@ -2361,18 +2363,41 @@ block_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf,
 	if (!ret)
 		ret = block_commit_write(page, 0, end);
 
-	if (unlikely(ret)) {
-		unlock_page(page);
-		if (ret == -ENOMEM)
-			ret = VM_FAULT_OOM;
-		else /* -ENOSPC, -EIO, etc */
-			ret = VM_FAULT_SIGBUS;
-	} else
-		ret = VM_FAULT_LOCKED;
-
-out:
+	if (unlikely(ret < 0))
+		goto out_unlock;
+	/*
+	 * Freezing in progress? We check after the page is marked dirty and
+	 * with page lock held so if the test here fails, we are sure freezing
+	 * code will wait during syncing until the page fault is done - at that
+	 * point page will be dirty and unlocked so freezing code will write it
+	 * and writeprotect it again.
+	 */
+	set_page_dirty(page);
+	if (inode->i_sb->s_frozen != SB_UNFROZEN) {
+		ret = -EAGAIN;
+		goto out_unlock;
+	}
+	return 0;
+out_unlock:
+	unlock_page(page);
 	return ret;
 }
+EXPORT_SYMBOL(__block_page_mkwrite);
+
+int block_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf,
+		   get_block_t get_block)
+{
+	int ret;
+	struct super_block *sb = vma->vm_file->f_path.dentry->d_inode->i_sb;
+
+	/*
+	 * This check is racy but catches the common case. The check in
+	 * __block_page_mkwrite() is reliable.
+	 */
+	vfs_check_frozen(sb, SB_FREEZE_WRITE);
+	ret = __block_page_mkwrite(vma, vmf, get_block);
+	return block_page_mkwrite_return(ret);
+}
 EXPORT_SYMBOL(block_page_mkwrite);
 
 /*
diff --git a/fs/coda/dir.c b/fs/coda/dir.c
index 2b8dae4d121..a46126fd573 100644
--- a/fs/coda/dir.c
+++ b/fs/coda/dir.c
@@ -336,6 +336,8 @@ static int coda_rmdir(struct inode *dir, struct dentry *de)
 	int len = de->d_name.len;
 	int error;
 
+	dentry_unhash(de);
+
 	error = venus_rmdir(dir->i_sb, coda_i2f(dir), name, len);
 	if (!error) {
 		/* VFS may delete the child */
@@ -359,6 +361,9 @@ static int coda_rename(struct inode *old_dir, struct dentry *old_dentry,
 	int new_length = new_dentry->d_name.len;
 	int error;
 
+	if (new_dentry->d_inode && S_ISDIR(new_dentry->d_inode->i_mode))
+		dentry_unhash(new_dentry);
+
 	error = venus_rename(old_dir->i_sb, coda_i2f(old_dir),
 			     coda_i2f(new_dir), old_length, new_length,
 			     (const char *) old_name, (const char *)new_name);
diff --git a/fs/configfs/dir.c b/fs/configfs/dir.c
index 9a37a9b6de3..9d17d350abc 100644
--- a/fs/configfs/dir.c
+++ b/fs/configfs/dir.c
@@ -1359,6 +1359,8 @@ static int configfs_rmdir(struct inode *dir, struct dentry *dentry)
 	struct module *subsys_owner = NULL, *dead_item_owner = NULL;
 	int ret;
 
+	dentry_unhash(dentry);
+
 	if (dentry->d_parent == configfs_sb->s_root)
 		return -EPERM;
 
diff --git a/fs/ecryptfs/inode.c b/fs/ecryptfs/inode.c
index 4d4cc6a90cd..227b409b840 100644
--- a/fs/ecryptfs/inode.c
+++ b/fs/ecryptfs/inode.c
@@ -521,6 +521,8 @@ static int ecryptfs_rmdir(struct inode *dir, struct dentry *dentry)
 	struct dentry *lower_dir_dentry;
 	int rc;
 
+	dentry_unhash(dentry);
+
 	lower_dentry = ecryptfs_dentry_to_lower(dentry);
 	dget(dentry);
 	lower_dir_dentry = lock_parent(lower_dentry);
@@ -571,6 +573,9 @@ ecryptfs_rename(struct inode *old_dir, struct dentry *old_dentry,
 	struct dentry *lower_new_dir_dentry;
 	struct dentry *trap = NULL;
 
+	if (new_dentry->d_inode && S_ISDIR(new_dentry->d_inode->i_mode))
+		dentry_unhash(new_dentry);
+
 	lower_old_dentry = ecryptfs_dentry_to_lower(old_dentry);
 	lower_new_dentry = ecryptfs_dentry_to_lower(new_dentry);
 	dget(lower_old_dentry);
diff --git a/fs/fat/namei_msdos.c b/fs/fat/namei_msdos.c
index 3b222dafd15..be15437c272 100644
--- a/fs/fat/namei_msdos.c
+++ b/fs/fat/namei_msdos.c
@@ -326,6 +326,8 @@ static int msdos_rmdir(struct inode *dir, struct dentry *dentry)
 	struct fat_slot_info sinfo;
 	int err;
 
+	dentry_unhash(dentry);
+
 	lock_super(sb);
 	/*
 	 * Check whether the directory is not in use, then check
@@ -457,6 +459,9 @@ static int do_msdos_rename(struct inode *old_dir, unsigned char *old_name,
 	old_inode = old_dentry->d_inode;
 	new_inode = new_dentry->d_inode;
 
+	if (new_inode && S_ISDIR(new_inode->i_mode))
+		dentry_unhash(new_dentry);
+
 	err = fat_scan(old_dir, old_name, &old_sinfo);
 	if (err) {
 		err = -EIO;
diff --git a/fs/fat/namei_vfat.c b/fs/fat/namei_vfat.c
index 20b4ea53fdc..c61a6789f36 100644
--- a/fs/fat/namei_vfat.c
+++ b/fs/fat/namei_vfat.c
@@ -824,6 +824,8 @@ static int vfat_rmdir(struct inode *dir, struct dentry *dentry)
 	struct fat_slot_info sinfo;
 	int err;
 
+	dentry_unhash(dentry);
+
 	lock_super(sb);
 
 	err = fat_dir_empty(inode);
@@ -931,6 +933,9 @@ static int vfat_rename(struct inode *old_dir, struct dentry *old_dentry,
 	int err, is_dir, update_dotdot, corrupt = 0;
 	struct super_block *sb = old_dir->i_sb;
 
+	if (new_dentry->d_inode && S_ISDIR(new_dentry->d_inode->i_mode))
+		dentry_unhash(new_dentry);
+
 	old_sinfo.bh = sinfo.bh = dotdot_bh = NULL;
 	old_inode = old_dentry->d_inode;
 	new_inode = new_dentry->d_inode;
diff --git a/fs/fuse/dir.c b/fs/fuse/dir.c
index b32eb29a4e6..0d0e3faddcf 100644
--- a/fs/fuse/dir.c
+++ b/fs/fuse/dir.c
@@ -667,6 +667,8 @@ static int fuse_rmdir(struct inode *dir, struct dentry *entry)
 	if (IS_ERR(req))
 		return PTR_ERR(req);
 
+	dentry_unhash(entry);
+
 	req->in.h.opcode = FUSE_RMDIR;
 	req->in.h.nodeid = get_node_id(dir);
 	req->in.numargs = 1;
@@ -691,6 +693,10 @@ static int fuse_rename(struct inode *olddir, struct dentry *oldent,
 	struct fuse_rename_in inarg;
 	struct fuse_conn *fc = get_fuse_conn(olddir);
 	struct fuse_req *req = fuse_get_req(fc);
+
+	if (newent->d_inode && S_ISDIR(newent->d_inode->i_mode))
+		dentry_unhash(newent);
+
 	if (IS_ERR(req))
 		return PTR_ERR(req);
 
diff --git a/fs/hfs/dir.c b/fs/hfs/dir.c
index b4d70b13be9..1cb70cdba2c 100644
--- a/fs/hfs/dir.c
+++ b/fs/hfs/dir.c
@@ -253,6 +253,9 @@ static int hfs_remove(struct inode *dir, struct dentry *dentry)
 	struct inode *inode = dentry->d_inode;
 	int res;
 
+	if (S_ISDIR(inode->i_mode))
+		dentry_unhash(dentry);
+
 	if (S_ISDIR(inode->i_mode) && inode->i_size != 2)
 		return -ENOTEMPTY;
 	res = hfs_cat_delete(inode->i_ino, dir, &dentry->d_name);
@@ -283,6 +286,9 @@ static int hfs_rename(struct inode *old_dir, struct dentry *old_dentry,
 
 	/* Unlink destination if it already exists */
 	if (new_dentry->d_inode) {
+		if (S_ISDIR(new_dentry->d_inode->i_mode))
+			dentry_unhash(new_dentry);
+
 		res = hfs_remove(new_dir, new_dentry);
 		if (res)
 			return res;
diff --git a/fs/hfsplus/dir.c b/fs/hfsplus/dir.c
index 4df5059c25d..b28835091dd 100644
--- a/fs/hfsplus/dir.c
+++ b/fs/hfsplus/dir.c
@@ -370,6 +370,8 @@ static int hfsplus_rmdir(struct inode *dir, struct dentry *dentry)
 	struct inode *inode = dentry->d_inode;
 	int res;
 
+	dentry_unhash(dentry);
+
 	if (inode->i_size != 2)
 		return -ENOTEMPTY;
 
@@ -467,10 +469,12 @@ static int hfsplus_rename(struct inode *old_dir, struct dentry *old_dentry,
 
 	/* Unlink destination if it already exists */
 	if (new_dentry->d_inode) {
-		if (S_ISDIR(new_dentry->d_inode->i_mode))
+		if (S_ISDIR(new_dentry->d_inode->i_mode)) {
+			dentry_unhash(new_dentry);
 			res = hfsplus_rmdir(new_dir, new_dentry);
-		else
+		} else {
 			res = hfsplus_unlink(new_dir, new_dentry);
+		}
 		if (res)
 			return res;
 	}
diff --git a/fs/hostfs/hostfs_kern.c b/fs/hostfs/hostfs_kern.c
index 2638c834ed2..e6816b9e690 100644
--- a/fs/hostfs/hostfs_kern.c
+++ b/fs/hostfs/hostfs_kern.c
@@ -683,6 +683,8 @@ int hostfs_rmdir(struct inode *ino, struct dentry *dentry)
 	char *file;
 	int err;
 
+	dentry_unhash(dentry);
+
 	if ((file = dentry_name(dentry)) == NULL)
 		return -ENOMEM;
 	err = do_rmdir(file);
@@ -736,6 +738,9 @@ int hostfs_rename(struct inode *from_ino, struct dentry *from,
 	char *from_name, *to_name;
 	int err;
 
+	if (to->d_inode && S_ISDIR(to->d_inode->i_mode))
+		dentry_unhash(to);
+
 	if ((from_name = dentry_name(from)) == NULL)
 		return -ENOMEM;
 	if ((to_name = dentry_name(to)) == NULL) {
diff --git a/fs/hpfs/namei.c b/fs/hpfs/namei.c
index 1f05839c27a..ff0ce21c086 100644
--- a/fs/hpfs/namei.c
+++ b/fs/hpfs/namei.c
@@ -395,7 +395,6 @@ again:
 
 		dentry_unhash(dentry);
 		if (!d_unhashed(dentry)) {
-			dput(dentry);
 			hpfs_unlock(dir->i_sb);
 			return -ENOSPC;
 		}
@@ -403,7 +402,6 @@ again:
 		    !S_ISREG(inode->i_mode) ||
 		    get_write_access(inode)) {
 			d_rehash(dentry);
-			dput(dentry);
 		} else {
 			struct iattr newattrs;
 			/*printk("HPFS: truncating file before delete.\n");*/
@@ -411,7 +409,6 @@ again:
 			newattrs.ia_valid = ATTR_SIZE | ATTR_CTIME;
 			err = notify_change(dentry, &newattrs);
 			put_write_access(inode);
-			dput(dentry);
 			if (!err)
 				goto again;
 		}
@@ -442,6 +439,8 @@ static int hpfs_rmdir(struct inode *dir, struct dentry *dentry)
 	int err;
 	int r;
 
+	dentry_unhash(dentry);
+
 	hpfs_adjust_length(name, &len);
 	hpfs_lock(dir->i_sb);
 	err = -ENOENT;
@@ -535,6 +534,10 @@ static int hpfs_rename(struct inode *old_dir, struct dentry *old_dentry,
 	struct buffer_head *bh;
 	struct fnode *fnode;
 	int err;
+
+	if (new_inode && S_ISDIR(new_inode->i_mode))
+		dentry_unhash(new_dentry);
+
 	if ((err = hpfs_chk_name(new_name, &new_len))) return err;
 	err = 0;
 	hpfs_adjust_length(old_name, &old_len);
diff --git a/fs/jffs2/dir.c b/fs/jffs2/dir.c
index 82faddd1f32..05f73328b28 100644
--- a/fs/jffs2/dir.c
+++ b/fs/jffs2/dir.c
@@ -609,6 +609,8 @@ static int jffs2_rmdir (struct inode *dir_i, struct dentry *dentry)
 	int ret;
 	uint32_t now = get_seconds();
 
+	dentry_unhash(dentry);
+
 	for (fd = f->dents ; fd; fd = fd->next) {
 		if (fd->ino)
 			return -ENOTEMPTY;
@@ -784,6 +786,9 @@ static int jffs2_rename (struct inode *old_dir_i, struct dentry *old_dentry,
 	uint8_t type;
 	uint32_t now;
 
+	if (new_dentry->d_inode && S_ISDIR(new_dentry->d_inode->i_mode))
+		dentry_unhash(new_dentry);
+
 	/* The VFS will check for us and prevent trying to rename a
 	 * file over a directory and vice versa, but if it's a directory,
 	 * the VFS can't check whether the victim is empty. The filesystem
diff --git a/fs/jfs/namei.c b/fs/jfs/namei.c
index eaaf2b511e8..865df16a6cf 100644
--- a/fs/jfs/namei.c
+++ b/fs/jfs/namei.c
@@ -360,6 +360,8 @@ static int jfs_rmdir(struct inode *dip, struct dentry *dentry)
 
 	jfs_info("jfs_rmdir: dip:0x%p name:%s", dip, dentry->d_name.name);
 
+	dentry_unhash(dentry);
+
 	/* Init inode for quota operations. */
 	dquot_initialize(dip);
 	dquot_initialize(ip);
@@ -1095,6 +1097,9 @@ static int jfs_rename(struct inode *old_dir, struct dentry *old_dentry,
 	jfs_info("jfs_rename: %s %s", old_dentry->d_name.name,
 		 new_dentry->d_name.name);
 
+	if (new_dentry->d_inode && S_ISDIR(new_dentry->d_inode->i_mode))
+		dentry_unhash(new_dentry);
+
 	dquot_initialize(old_dir);
 	dquot_initialize(new_dir);
 
diff --git a/fs/logfs/dir.c b/fs/logfs/dir.c
index 9ed89d1663f..f34c9cde9e9 100644
--- a/fs/logfs/dir.c
+++ b/fs/logfs/dir.c
@@ -273,6 +273,8 @@ static int logfs_rmdir(struct inode *dir, struct dentry *dentry)
 {
 	struct inode *inode = dentry->d_inode;
 
+	dentry_unhash(dentry);
+
 	if (!logfs_empty_dir(inode))
 		return -ENOTEMPTY;
 
@@ -622,6 +624,9 @@ static int logfs_rename_cross(struct inode *old_dir, struct dentry *old_dentry,
 	loff_t pos;
 	int err;
 
+	if (new_dentry->d_inode && S_ISDIR(new_dentry->d_inode->i_mode))
+		dentry_unhash(new_dentry);
+
 	/* 1. locate source dd */
 	err = logfs_get_dd(old_dir, old_dentry, &dd, &pos);
 	if (err)
diff --git a/fs/minix/namei.c b/fs/minix/namei.c
index 6e6777f1b4b..f60aed8db9c 100644
--- a/fs/minix/namei.c
+++ b/fs/minix/namei.c
@@ -168,6 +168,8 @@ static int minix_rmdir(struct inode * dir, struct dentry *dentry)
 	struct inode * inode = dentry->d_inode;
 	int err = -ENOTEMPTY;
 
+	dentry_unhash(dentry);
+
 	if (minix_empty_dir(inode)) {
 		err = minix_unlink(dir, dentry);
 		if (!err) {
@@ -190,6 +192,9 @@ static int minix_rename(struct inode * old_dir, struct dentry *old_dentry,
 	struct minix_dir_entry * old_de;
 	int err = -ENOENT;
 
+	if (new_inode && S_ISDIR(new_inode->i_mode))
+		dentry_unhash(new_dentry);
+
 	old_de = minix_find_entry(old_dentry, &old_page);
 	if (!old_de)
 		goto out;
diff --git a/fs/namei.c b/fs/namei.c
index 6ff858c049c..2358b326b22 100644
--- a/fs/namei.c
+++ b/fs/namei.c
@@ -391,79 +391,28 @@ void path_put(struct path *path)
 }
 EXPORT_SYMBOL(path_put);
 
-/**
- * nameidata_drop_rcu - drop this nameidata out of rcu-walk
- * @nd: nameidata pathwalk data to drop
- * Returns: 0 on success, -ECHILD on failure
- *
+/*
  * Path walking has 2 modes, rcu-walk and ref-walk (see
- * Documentation/filesystems/path-lookup.txt). __drop_rcu* functions attempt
- * to drop out of rcu-walk mode and take normal reference counts on dentries
- * and vfsmounts to transition to rcu-walk mode. __drop_rcu* functions take
- * refcounts at the last known good point before rcu-walk got stuck, so
- * ref-walk may continue from there. If this is not successful (eg. a seqcount
- * has changed), then failure is returned and path walk restarts from the
- * beginning in ref-walk mode.
- *
- * nameidata_drop_rcu attempts to drop the current nd->path and nd->root into
- * ref-walk. Must be called from rcu-walk context.
+ * Documentation/filesystems/path-lookup.txt).  In situations when we can't
+ * continue in RCU mode, we attempt to drop out of rcu-walk mode and grab
+ * normal reference counts on dentries and vfsmounts to transition to rcu-walk
+ * mode.  Refcounts are grabbed at the last known good point before rcu-walk
+ * got stuck, so ref-walk may continue from there. If this is not successful
+ * (eg. a seqcount has changed), then failure is returned and it's up to caller
+ * to restart the path walk from the beginning in ref-walk mode.
  */
-static int nameidata_drop_rcu(struct nameidata *nd)
-{
-	struct fs_struct *fs = current->fs;
-	struct dentry *dentry = nd->path.dentry;
-	int want_root = 0;
-
-	BUG_ON(!(nd->flags & LOOKUP_RCU));
-	if (nd->root.mnt && !(nd->flags & LOOKUP_ROOT)) {
-		want_root = 1;
-		spin_lock(&fs->lock);
-		if (nd->root.mnt != fs->root.mnt ||
-				nd->root.dentry != fs->root.dentry)
-			goto err_root;
-	}
-	spin_lock(&dentry->d_lock);
-	if (!__d_rcu_to_refcount(dentry, nd->seq))
-		goto err;
-	BUG_ON(nd->inode != dentry->d_inode);
-	spin_unlock(&dentry->d_lock);
-	if (want_root) {
-		path_get(&nd->root);
-		spin_unlock(&fs->lock);
-	}
-	mntget(nd->path.mnt);
-
-	rcu_read_unlock();
-	br_read_unlock(vfsmount_lock);
-	nd->flags &= ~LOOKUP_RCU;
-	return 0;
-err:
-	spin_unlock(&dentry->d_lock);
-err_root:
-	if (want_root)
-		spin_unlock(&fs->lock);
-	return -ECHILD;
-}
-
-/* Try to drop out of rcu-walk mode if we were in it, otherwise do nothing.  */
-static inline int nameidata_drop_rcu_maybe(struct nameidata *nd)
-{
-	if (nd->flags & LOOKUP_RCU)
-		return nameidata_drop_rcu(nd);
-	return 0;
-}
 
 /**
- * nameidata_dentry_drop_rcu - drop nameidata and dentry out of rcu-walk
- * @nd: nameidata pathwalk data to drop
- * @dentry: dentry to drop
+ * unlazy_walk - try to switch to ref-walk mode.
+ * @nd: nameidata pathwalk data
+ * @dentry: child of nd->path.dentry or NULL
  * Returns: 0 on success, -ECHILD on failure
  *
- * nameidata_dentry_drop_rcu attempts to drop the current nd->path and nd->root,
- * and dentry into ref-walk. @dentry must be a path found by a do_lookup call on
- * @nd. Must be called from rcu-walk context.
+ * unlazy_walk attempts to legitimize the current nd->path, nd->root and dentry
+ * for ref-walk mode.  @dentry must be a path found by a do_lookup call on
+ * @nd or NULL.  Must be called from rcu-walk context.
  */
-static int nameidata_dentry_drop_rcu(struct nameidata *nd, struct dentry *dentry)
+static int unlazy_walk(struct nameidata *nd, struct dentry *dentry)
 {
 	struct fs_struct *fs = current->fs;
 	struct dentry *parent = nd->path.dentry;
@@ -478,18 +427,25 @@ static int nameidata_dentry_drop_rcu(struct nameidata *nd, struct dentry *dentry
 			goto err_root;
 	}
 	spin_lock(&parent->d_lock);
-	spin_lock_nested(&dentry->d_lock, DENTRY_D_LOCK_NESTED);
-	if (!__d_rcu_to_refcount(dentry, nd->seq))
-		goto err;
-	/*
-	 * If the sequence check on the child dentry passed, then the child has
-	 * not been removed from its parent. This means the parent dentry must
-	 * be valid and able to take a reference at this point.
-	 */
-	BUG_ON(!IS_ROOT(dentry) && dentry->d_parent != parent);
-	BUG_ON(!parent->d_count);
-	parent->d_count++;
-	spin_unlock(&dentry->d_lock);
+	if (!dentry) {
+		if (!__d_rcu_to_refcount(parent, nd->seq))
+			goto err_parent;
+		BUG_ON(nd->inode != parent->d_inode);
+	} else {
+		spin_lock_nested(&dentry->d_lock, DENTRY_D_LOCK_NESTED);
+		if (!__d_rcu_to_refcount(dentry, nd->seq))
+			goto err_child;
+		/*
+		 * If the sequence check on the child dentry passed, then
+		 * the child has not been removed from its parent. This
+		 * means the parent dentry must be valid and able to take
+		 * a reference at this point.
+		 */
+		BUG_ON(!IS_ROOT(dentry) && dentry->d_parent != parent);
+		BUG_ON(!parent->d_count);
+		parent->d_count++;
+		spin_unlock(&dentry->d_lock);
+	}
 	spin_unlock(&parent->d_lock);
 	if (want_root) {
 		path_get(&nd->root);
@@ -501,8 +457,10 @@ static int nameidata_dentry_drop_rcu(struct nameidata *nd, struct dentry *dentry
 	br_read_unlock(vfsmount_lock);
 	nd->flags &= ~LOOKUP_RCU;
 	return 0;
-err:
+
+err_child:
 	spin_unlock(&dentry->d_lock);
+err_parent:
 	spin_unlock(&parent->d_lock);
 err_root:
 	if (want_root)
@@ -510,59 +468,6 @@ err_root:
 	return -ECHILD;
 }
 
-/* Try to drop out of rcu-walk mode if we were in it, otherwise do nothing.  */
-static inline int nameidata_dentry_drop_rcu_maybe(struct nameidata *nd, struct dentry *dentry)
-{
-	if (nd->flags & LOOKUP_RCU) {
-		if (unlikely(nameidata_dentry_drop_rcu(nd, dentry))) {
-			nd->flags &= ~LOOKUP_RCU;
-			if (!(nd->flags & LOOKUP_ROOT))
-				nd->root.mnt = NULL;
-			rcu_read_unlock();
-			br_read_unlock(vfsmount_lock);
-			return -ECHILD;
-		}
-	}
-	return 0;
-}
-
-/**
- * nameidata_drop_rcu_last - drop nameidata ending path walk out of rcu-walk
- * @nd: nameidata pathwalk data to drop
- * Returns: 0 on success, -ECHILD on failure
- *
- * nameidata_drop_rcu_last attempts to drop the current nd->path into ref-walk.
- * nd->path should be the final element of the lookup, so nd->root is discarded.
- * Must be called from rcu-walk context.
- */
-static int nameidata_drop_rcu_last(struct nameidata *nd)
-{
-	struct dentry *dentry = nd->path.dentry;
-
-	BUG_ON(!(nd->flags & LOOKUP_RCU));
-	nd->flags &= ~LOOKUP_RCU;
-	if (!(nd->flags & LOOKUP_ROOT))
-		nd->root.mnt = NULL;
-	spin_lock(&dentry->d_lock);
-	if (!__d_rcu_to_refcount(dentry, nd->seq))
-		goto err_unlock;
-	BUG_ON(nd->inode != dentry->d_inode);
-	spin_unlock(&dentry->d_lock);
-
-	mntget(nd->path.mnt);
-
-	rcu_read_unlock();
-	br_read_unlock(vfsmount_lock);
-
-	return 0;
-
-err_unlock:
-	spin_unlock(&dentry->d_lock);
-	rcu_read_unlock();
-	br_read_unlock(vfsmount_lock);
-	return -ECHILD;
-}
-
 /**
  * release_open_intent - free up open intent resources
  * @nd: pointer to nameidata
@@ -606,26 +511,39 @@ do_revalidate(struct dentry *dentry, struct nameidata *nd)
 	return dentry;
 }
 
-/*
- * handle_reval_path - force revalidation of a dentry
- *
- * In some situations the path walking code will trust dentries without
- * revalidating them. This causes problems for filesystems that depend on
- * d_revalidate to handle file opens (e.g. NFSv4). When FS_REVAL_DOT is set
- * (which indicates that it's possible for the dentry to go stale), force
- * a d_revalidate call before proceeding.
+/**
+ * complete_walk - successful completion of path walk
+ * @nd:  pointer nameidata
  *
- * Returns 0 if the revalidation was successful. If the revalidation fails,
- * either return the error returned by d_revalidate or -ESTALE if the
- * revalidation it just retu