[PATCH 09/32] whiteout: Add vfs_whiteout() and whiteout inode operation

[Jan Blunck <jblunck@suse.de>]

Simply white-out a given directory entry. This functionality is usually used
in the sense of unlink. Therefore the given dentry can still be in-use and
contains an in-use inode. The filesystems inode operation has to do what
unlink or rmdir would in that case. Since the dentry still might be in-use
we have to provide a fresh unhashed dentry that is used as the whiteout
dentry instead. The given dentry is dropped and the whiteout dentry is
rehashed instead.

Signed-off-by: Jan Blunck <jblunck@suse.de>
Signed-off-by: David Woodhouse <dwmw2@infradead.org>
Signed-off-by: Valerie Aurora (Henson) <vaurora@redhat.com>
---
 fs/dcache.c            |    4 +-
 fs/namei.c             |  104 ++++++++++++++++++++++++++++++++++++++++++++++++
 include/linux/dcache.h |    7 +++-
 include/linux/fs.h     |    3 +
 4 files changed, 116 insertions(+), 2 deletions(-)

diff --git a/fs/dcache.c b/fs/dcache.c
index 8bfbcd7..9260c99 100644
--- a/fs/dcache.c
+++ b/fs/dcache.c
@@ -1076,8 +1076,10 @@ struct dentry *d_alloc_name(struct dentry *parent, const char *name)
 /* the caller must hold dcache_lock */
 static void __d_instantiate(struct dentry *dentry, struct inode *inode)
 {
-	if (inode)
+	if (inode) {
+		dentry->d_flags &= ~DCACHE_WHITEOUT;
 		list_add(&dentry->d_alias, &inode->i_dentry);
+	}
 	dentry->d_inode = inode;
 	fsnotify_d_instantiate(dentry, inode);
 }
diff --git a/fs/namei.c b/fs/namei.c
index e19fa2b..9cab708 100644
--- a/fs/namei.c
+++ b/fs/namei.c
@@ -2111,6 +2111,110 @@ SYSCALL_DEFINE2(mkdir, const char __user *, pathname, int, mode)
 	return sys_mkdirat(AT_FDCWD, pathname, mode);
 }
 
+
+/* Checks on the victim for whiteout */
+static inline int may_whiteout(struct inode *dir, struct dentry *victim,
+			       int isdir)
+{
+	int err;
+
+	/* from may_create() */
+	if (IS_DEADDIR(dir))
+		return -ENOENT;
+	err = inode_permission(dir, MAY_WRITE | MAY_EXEC);
+	if (err)
+		return err;
+
+	/* from may_delete() */
+	if (IS_APPEND(dir))
+		return -EPERM;
+	if (!victim->d_inode)
+		return 0;
+	if (check_sticky(dir, victim->d_inode) ||
+	    IS_APPEND(victim->d_inode) ||
+	    IS_IMMUTABLE(victim->d_inode))
+		return -EPERM;
+	if (isdir) {
+		if (!S_ISDIR(victim->d_inode->i_mode))
+			return -ENOTDIR;
+		if (IS_ROOT(victim))
+			return -EBUSY;
+	} else if (S_ISDIR(victim->d_inode->i_mode))
+		return -EISDIR;
+	if (victim->d_flags & DCACHE_NFSFS_RENAMED)
+		return -EBUSY;
+	return 0;
+}
+
+/**
+ * vfs_whiteout: creates a white-out for the given directory entry
+ * @dir: parent inode
+ * @dentry: directory entry to white-out
+ *
+ * Simply white-out a given directory entry. This functionality is usually used
+ * in the sense of unlink. Therefore the given dentry can still be in-use and
+ * contains an in-use inode. The filesystem has to do what unlink or rmdir
+ * would in that case. Since the dentry still might be in-use we have to
+ * provide a fresh unhashed dentry that whiteout can fill the new inode into.
+ * In that case the given dentry is dropped and the fresh dentry containing the
+ * whiteout is rehashed instead. If the given dentry is unused, the whiteout
+ * inode is instantiated into it instead.
+ *
+ * After this returns with success, don't make any assumptions about the inode.
+ * Just dput() it dentry.
+ */
+int vfs_whiteout(struct inode *dir, struct dentry *dentry, int isdir)
+{
+	int err;
+	struct inode *old_inode = dentry->d_inode;
+	struct dentry *parent, *whiteout;
+
+	err = may_whiteout(dir, dentry, isdir);
+	if (err)
+		return err;
+
+	BUG_ON(dentry->d_parent->d_inode != dir);
+
+	if (!dir->i_op || !dir->i_op->whiteout)
+		return -EOPNOTSUPP;
+
+	if (old_inode) {
+		vfs_dq_init(dir);
+
+		mutex_lock(&old_inode->i_mutex);
+		if (isdir)
+			dentry_unhash(dentry);
+		if (d_mountpoint(dentry))
+			err = -EBUSY;
+		else {
+			if (isdir)
+				err = security_inode_rmdir(dir, dentry);
+			else
+				err = security_inode_unlink(dir, dentry);
+		}
+	}
+
+	parent = dget_parent(dentry);
+	whiteout = d_alloc_name(parent, dentry->d_name.name);
+
+	if (!err)
+		err = dir->i_op->whiteout(dir, dentry, whiteout);
+
+	if (old_inode) {
+		mutex_unlock(&old_inode->i_mutex);
+		if (!err) {
+			fsnotify_link_count(old_inode);
+			d_delete(dentry);
+		}
+		if (isdir)
+			dput(dentry);
+	}
+
+	dput(whiteout);
+	dput(parent);
+	return err;
+}
+
 /*
  * We try to drop the dentry early: we should have
  * a usage count of 2 if we're the only user of this
diff --git a/include/linux/dcache.h b/include/linux/dcache.h
index c66d224..e00e95b 100644
--- a/include/linux/dcache.h
+++ b/include/linux/dcache.h
@@ -181,8 +181,8 @@ d_iput:		no		no		no       yes
 #define DCACHE_UNHASHED		0x0010	
 
 #define DCACHE_INOTIFY_PARENT_WATCHED	0x0020 /* Parent inode is watched */
-
 #define DCACHE_COOKIE		0x0040	/* For use by dcookie subsystem */
+#define DCACHE_WHITEOUT		0x0080	/* This negative dentry is a whiteout */
 
 extern spinlock_t dcache_lock;
 extern seqlock_t rename_lock;
@@ -351,6 +351,11 @@ static inline int d_unhashed(struct dentry *dentry)
 	return (dentry->d_flags & DCACHE_UNHASHED);
 }
 
+static inline int d_is_whiteout(struct dentry *dentry)
+{
+	return (dentry->d_flags & DCACHE_WHITEOUT);
+}
+
 static inline struct dentry *dget_parent(struct dentry *dentry)
 {
 	struct dentry *ret;
diff --git a/include/linux/fs.h b/include/linux/fs.h
index 92734c0..5950616 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -141,6 +141,7 @@ struct inodes_stat_t {
 #define MS_RELATIME	(1<<21)	/* Update atime relative to mtime/ctime. */
 #define MS_KERNMOUNT	(1<<22) /* this is a kern_mount call */
 #define MS_I_VERSION	(1<<23) /* Update inode I_version field */
+#define MS_WHITEOUT	(1<<26) /* fs does support white-out filetype */
 #define MS_ACTIVE	(1<<30)
 #define MS_NOUSER	(1<<31)
 
@@ -1241,6 +1242,7 @@ extern int vfs_link(struct dentry *, struct inode *, struct dentry *);
 extern int vfs_rmdir(struct inode *, struct dentry *);
 extern int vfs_unlink(struct inode *, struct dentry *);
 extern int vfs_rename(struct inode *, struct dentry *, struct inode *, struct dentry *);
+extern int vfs_whiteout(struct inode *, struct dentry *, int);
 
 /*
  * VFS dentry helper functions.
@@ -1345,6 +1347,7 @@ struct inode_operations {
 	int (*mkdir) (struct inode *,struct dentry *,int);
 	int (*rmdir) (struct inode *,struct dentry *);
 	int (*mknod) (struct inode *,struct dentry *,int,dev_t);
+	int (*whiteout) (struct inode *, struct dentry *, struct dentry *);
 	int (*rename) (struct inode *, struct dentry *,
 			struct inode *, struct dentry *);
 	int (*readlink) (struct dentry *, char __user *,int);
-- 
1.6.1.3