From: Jan Blunck <jblunck@xxxxxxx>
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@xxxxxxx>
Signed-off-by: David Woodhouse <dwmw2@xxxxxxxxxxxxx>
Signed-off-by: Valerie Aurora <vaurora@xxxxxxxxxx>
---
Documentation/filesystems/vfs.txt | 10 ++++
fs/dcache.c | 1
fs/namei.c | 89 +++++++++++++++++++++++++++++++++++++
include/linux/dcache.h | 6 ++
include/linux/fs.h | 2 +
5 files changed, 106 insertions(+), 2 deletions(-)
diff --git a/Documentation/filesystems/vfs.txt b/Documentation/filesystems/vfs.txt
index 88b9f55..d9a43db 100644
--- a/Documentation/filesystems/vfs.txt
+++ b/Documentation/filesystems/vfs.txt
@@ -316,7 +316,7 @@ 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 *);
@@ -327,6 +327,7 @@ 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);
@@ -391,6 +392,13 @@ 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 37f72ee..06ba068 100644
--- a/fs/dcache.c
+++ b/fs/dcache.c
@@ -1371,6 +1371,7 @@ static void __d_instantiate(struct dentry *dentry, struct inode *inode)
{
spin_lock(&dentry->d_lock);
if (inode) {
+ dentry->d_flags &= ~DCACHE_WHITEOUT;
if (unlikely(IS_AUTOMOUNT(inode)))
dentry->d_flags |= DCACHE_NEED_AUTOMOUNT;
list_add(&dentry->d_alias, &inode->i_dentry);
diff --git a/fs/namei.c b/fs/namei.c
index 272bead..99ca663 100644
--- a/fs/namei.c
+++ b/fs/namei.c
@@ -1838,7 +1838,6 @@ 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);
@@ -2552,6 +2551,94 @@ 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;
+ bool do_dput = false;
+ 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)
+ err = security_inode_rmdir(dir, old_dentry);
+ else
+ err = security_inode_unlink(dir, old_dentry);
+ if (err)
+ goto error_unlock;
+ }
+
+ parent = dget_parent(old_dentry);
+ err = -ENOMEM;
+ whiteout = d_alloc_name(parent, old_dentry->d_name.name);
+ if (!whiteout)
+ goto error_put_parent;
+
+ if (old_inode && isdir) {
+ dentry_unhash(old_dentry);
+ do_dput = true;
+ }
+
+ err = dir->i_op->whiteout(dir, old_dentry, whiteout);
+ if (err)
+ goto error_put_whiteout;
+
+ if (old_inode) {
+ mutex_unlock(&old_inode->i_mutex);
+ fsnotify_link_count(old_inode);
+ d_delete(old_dentry);
+ if (do_dput)
+ dput(old_dentry);
+ }
+
+ dput(whiteout);
+ dput(parent);
+ return err;
+
+error_put_whiteout:
+ dput(whiteout);
+error_put_parent:
+ dput(parent);
+error_unlock:
+ if (old_inode)
+ mutex_unlock(&old_inode->i_mutex);
+ if (do_dput)
+ dput(old_dentry);
+ return err;
+}
+
/*
* The dentry_unhash() helper will 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 19d90a5..98187cf 100644
--- a/include/linux/dcache.h
+++ b/include/linux/dcache.h
@@ -207,6 +207,7 @@ struct dentry_operations {
#define DCACHE_CANT_MOUNT 0x0100
#define DCACHE_GENOCIDE 0x0200
+#define DCACHE_WHITEOUT 0x0400 /* Stop lookup in a unioned file system */
#define DCACHE_OP_HASH 0x1000
#define DCACHE_OP_COMPARE 0x2000
@@ -411,6 +412,11 @@ static inline bool d_managed(struct dentry *dentry)
return dentry->d_flags & DCACHE_MANAGED_DENTRY;
}
+static inline int d_is_whiteout(struct dentry *dentry)
+{
+ return dentry->d_flags & DCACHE_WHITEOUT;
+}
+
static inline bool d_mountpoint(struct dentry *dentry)
{
return dentry->d_flags & DCACHE_MOUNTED;
diff --git a/include/linux/fs.h b/include/linux/fs.h
index 1429326..134b5d7 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -208,6 +208,7 @@ 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_NOSEC (1<<28)
#define MS_BORN (1<<29)
#define MS_ACTIVE (1<<30)
@@ -1601,6 +1602,7 @@ 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 *);
void (*truncate) (struct inode *);
--
To unsubscribe from this list: send the line "unsubscribe linux-fsdevel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
