[PATCH 05/35] whiteout: Add vfs_whiteout() and whiteout inode operation

[Valerie Aurora <vaurora@redhat.com>]

From: Jan Blunck <jblunck@suse.de>

Whiteout a given directory entry.  File systems that support whiteouts
must implement the new ->whiteout() directory inode operation.

Signed-off-by: Jan Blunck <jblunck@suse.de>
Signed-off-by: David Woodhouse <dwmw2@infradead.org>
Signed-off-by: Valerie Aurora <vaurora@redhat.com>
---
 Documentation/filesystems/vfs.txt |   10 +++-
 fs/dcache.c                       |    4 +-
 fs/namei.c                        |  133 +++++++++++++++++++++++++++++++++++++
 include/linux/dcache.h            |    6 ++
 include/linux/fs.h                |    2 +
 5 files changed, 153 insertions(+), 2 deletions(-)

diff --git a/Documentation/filesystems/vfs.txt b/Documentation/filesystems/vfs.txt
index 3de2f32..8846b4f 100644
--- a/Documentation/filesystems/vfs.txt
+++ b/Documentation/filesystems/vfs.txt
@@ -308,7 +308,7 @@ struct inode_operations
 -----------------------
 
 This describes how the VFS can manipulate an inode in your
-filesystem. As of kernel 2.6.22, the following members are defined:
+filesystem. As of kernel 2.6.33, the following members are defined:
 
 struct inode_operations {
 	int (*create) (struct inode *,struct dentry *,int, struct nameidata *);
@@ -319,6 +319,7 @@ 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);
@@ -382,6 +383,13 @@ otherwise noted.
 	will probably need to call d_instantiate() just as you would
 	in the create() method
 
+  whiteout: called by the rmdir(2) and unlink(2) system calls on a
+        layered file system.  Only required if you want to support
+        whiteouts.  The first dentry passed in is that for the old
+        dentry if it exists, and a negative dentry otherwise.  The
+        second is the dentry for the whiteout itself.  This method
+        must unlink() or rmdir() the original entry if it exists.
+
   rename: called by the rename(2) system call to rename the object to
 	have the parent and name given by the second inode and dentry.
 
diff --git a/fs/dcache.c b/fs/dcache.c
index f1358e5..265015d 100644
--- a/fs/dcache.c
+++ b/fs/dcache.c
@@ -992,8 +992,10 @@ EXPORT_SYMBOL(d_alloc_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 8e4c75f..010927b 100644
--- a/fs/namei.c
+++ b/fs/namei.c
@@ -2165,6 +2165,139 @@ SYSCALL_DEFINE2(mkdir, const char __user *, pathname, int, mode)
 }
 
 /*
+ * Checks on the victim for whiteout.  We must both be able to delete
+ * the victim directory entry (if it exists) and create a new
+ * directory entry, so this function is a combination of the checks
+ * from may_create() and may_delete().
+ */
+static inline int may_whiteout(struct inode *dir, struct dentry *victim,
+			       int isdir)
+{
+	int err;
+
+	/*
+	 * From may_create().  We don't have to do this check for a
+	 * simple delete because the directory must exist if we are
+	 * trying to delete something from it.  For a whiteout, the
+	 * dir may be empty and thus potentially unlinked by this point.
+	 */
+	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: create a whiteout for the given directory entry
+ * @dir: parent inode
+ * @dentry: directory entry to whiteout
+ *
+ * Create a whiteout for the given directory entry.  A whiteout
+ * prevents lookup from dropping down to a lower layer of a union
+ * mounted file system.
+ *
+ * There are two important cases: (a) The directory entry to be
+ * whited-out may already exist, in which case it must first be
+ * deleted before we create the whiteout, and (b) no such directory
+ * entry exists and we only have to create the whiteout itself.
+ *
+ * The caller must pass in a dentry for the directory entry to be
+ * whited-out - a positive one if it exists, and a negative if not.
+ * When this function returns, the caller should dput() the old, now
+ * defunct dentry it passed in.  The dentry for the whiteout itself is
+ * created inside this function.
+ */
+static int vfs_whiteout(struct inode *dir, struct dentry *old_dentry, int isdir)
+{
+	int err;
+	struct inode *old_inode = old_dentry->d_inode;
+	struct dentry *parent, *whiteout;
+
+	err = may_whiteout(dir, old_dentry, isdir);
+	if (err)
+		return err;
+
+	BUG_ON(old_dentry->d_parent->d_inode != dir);
+
+	if (!dir->i_op || !dir->i_op->whiteout)
+		return -EOPNOTSUPP;
+
+	/*
+	 * If the old dentry is positive, then we have to delete this
+	 * entry before we create the whiteout.  The file system
+	 * ->whiteout() op does the actual delete, but we do all the
+	 * VFS-level checks and changes here.
+	 */
+	if (old_inode) {
+		mutex_lock(&old_inode->i_mutex);
+		if (isdir)
+			dentry_unhash(old_dentry);
+		if (d_mountpoint(old_dentry))
+			err = -EBUSY;
+		else {
+			if (isdir)
+				err = security_inode_rmdir(dir, old_dentry);
+			else
+				err = security_inode_unlink(dir, old_dentry);
+		}
+	}
+
+	parent = dget_parent(old_dentry);
+	whiteout = d_alloc_name(parent, old_dentry->d_name.name);
+
+	if (!err)
+		err = dir->i_op->whiteout(dir, old_dentry, whiteout);
+
+	if (old_inode) {
+		mutex_unlock(&old_inode->i_mutex);
+		if (!err) {
+			fsnotify_link_count(old_inode);
+			d_delete(old_dentry);
+		}
+		if (isdir)
+			dput(old_dentry);
+	}
+
+	dput(whiteout);
+	dput(parent);
+	return err;
+}
+
+int path_whiteout(struct path *dir_path, struct dentry *dentry, int isdir)
+{
+	int error = mnt_want_write(dir_path->mnt);
+
+	if (!error) {
+		error = vfs_whiteout(dir_path->dentry->d_inode, dentry, isdir);
+		mnt_drop_write(dir_path->mnt);
+	}
+
+	return error;
+}
+EXPORT_SYMBOL(path_whiteout);
+
+/*
  * We try to drop the dentry early: we should have
  * a usage count of 2 if we're the only user of this
  * dentry, and if that is true (possibly after pruning
diff --git a/include/linux/dcache.h b/include/linux/dcache.h
index 30b93b2..7648b49 100644
--- a/include/linux/dcache.h
+++ b/include/linux/dcache.h
@@ -183,6 +183,7 @@ d_iput:		no		no		no       yes
 #define DCACHE_INOTIFY_PARENT_WATCHED	0x0020 /* Parent inode is watched by inotify */
 
 #define DCACHE_COOKIE		0x0040	/* For use by dcookie subsystem */
+#define DCACHE_WHITEOUT		0x0080	/* This negative dentry is a whiteout */
 
 #define DCACHE_FSNOTIFY_PARENT_WATCHED	0x0080 /* Parent inode is watched by some fsnotify listener */
 
@@ -358,6 +359,11 @@ static inline int d_unlinked(struct dentry *dentry)
 	return d_unhashed(dentry) && !IS_ROOT(dentry);
 }
 
+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 234ebc2..21102f9 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -209,6 +209,7 @@ struct inodes_stat_t {
 #define MS_KERNMOUNT	(1<<22) /* this is a kern_mount call */
 #define MS_I_VERSION	(1<<23) /* Update inode I_version field */
 #define MS_STRICTATIME	(1<<24) /* Always perform atime updates */
+#define MS_WHITEOUT	(1<<25) /* FS supports whiteout filetype */
 #define MS_ACTIVE	(1<<30)
 #define MS_NOUSER	(1<<31)
 
@@ -1527,6 +1528,7 @@ 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);
-- 
1.6.3.3