[PATCH 06/38] 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.

XXX - Only whiteout when there is a matching entry in a lower layer.

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                        |   73 ++++++++++++++++++++++++++++++++++++-
 include/linux/dcache.h            |    7 ++++
 include/linux/fs.h                |    2 +
 5 files changed, 93 insertions(+), 3 deletions(-)

diff --git a/Documentation/filesystems/vfs.txt b/Documentation/filesystems/vfs.txt
index 94677e7..964e0fc 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 2.6.34, 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 86d4db1..80f059b 100644
--- a/fs/dcache.c
+++ b/fs/dcache.c
@@ -991,8 +991,10 @@ 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 7552e61..665d394 100644
--- a/fs/namei.c
+++ b/fs/namei.c
@@ -1357,7 +1357,6 @@ static int may_delete(struct inode *dir,struct dentry *victim,int isdir)
 	if (!victim->d_inode)
 		return -ENOENT;
 
-	BUG_ON(victim->d_parent->d_inode != dir);
 	audit_inode_child(victim, dir);
 
 	error = inode_permission(dir, MAY_WRITE | MAY_EXEC);
@@ -2169,6 +2168,78 @@ SYSCALL_DEFINE2(mkdir, const char __user *, pathname, int, mode)
 	return sys_mkdirat(AT_FDCWD, pathname, mode);
 }
 
+/**
+ * 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)
+{
+	struct inode *old_inode = old_dentry->d_inode;
+	struct dentry *parent, *whiteout;
+	int err = 0;
+
+	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 (d_mountpoint(old_dentry)) {
+			mutex_unlock(&old_inode->i_mutex);
+			return -EBUSY;
+		}
+		if (isdir) {
+			dentry_unhash(old_dentry);
+			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;
+}
+
 /*
  * 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 eebb617..7d650a2 100644
--- a/include/linux/dcache.h
+++ b/include/linux/dcache.h
@@ -188,6 +188,8 @@ d_iput:		no		no		no       yes
 
 #define DCACHE_CANT_MOUNT	0x0100
 
+#define DCACHE_WHITEOUT		0x0200	/* Stop lookup in a unioned file system */
+
 extern spinlock_t dcache_lock;
 extern seqlock_t rename_lock;
 
@@ -372,6 +374,11 @@ static inline void dont_mount(struct dentry *dentry)
 	spin_unlock(&dentry->d_lock);
 }
 
+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 eeb49d7..1f80897 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