kernel: backport overlayfs v11 to 3.0 and 2.6.39
Should fix whiteout issues and missing files when using extroot. SVN-Revision: 29727
This commit is contained in:
Jonas Gorski
parent
c560444a58
commit
f3f1075655
2 changed files with 2593 additions and 2154 deletions
File diff suppressed because it is too large
Load diff
|
|
@ -1,3 +1,283 @@
|
|||
--- /dev/null
|
||||
+++ b/Documentation/filesystems/overlayfs.txt
|
||||
@@ -0,0 +1,199 @@
|
||||
+Written by: Neil Brown <neilb@suse.de>
|
||||
+
|
||||
+Overlay Filesystem
|
||||
+==================
|
||||
+
|
||||
+This document describes a prototype for a new approach to providing
|
||||
+overlay-filesystem functionality in Linux (sometimes referred to as
|
||||
+union-filesystems). An overlay-filesystem tries to present a
|
||||
+filesystem which is the result over overlaying one filesystem on top
|
||||
+of the other.
|
||||
+
|
||||
+The result will inevitably fail to look exactly like a normal
|
||||
+filesystem for various technical reasons. The expectation is that
|
||||
+many use cases will be able to ignore these differences.
|
||||
+
|
||||
+This approach is 'hybrid' because the objects that appear in the
|
||||
+filesystem do not all appear to belong to that filesystem. In many
|
||||
+cases an object accessed in the union will be indistinguishable
|
||||
+from accessing the corresponding object from the original filesystem.
|
||||
+This is most obvious from the 'st_dev' field returned by stat(2).
|
||||
+
|
||||
+While directories will report an st_dev from the overlay-filesystem,
|
||||
+all non-directory objects will report an st_dev from the lower or
|
||||
+upper filesystem that is providing the object. Similarly st_ino will
|
||||
+only be unique when combined with st_dev, and both of these can change
|
||||
+over the lifetime of a non-directory object. Many applications and
|
||||
+tools ignore these values and will not be affected.
|
||||
+
|
||||
+Upper and Lower
|
||||
+---------------
|
||||
+
|
||||
+An overlay filesystem combines two filesystems - an 'upper' filesystem
|
||||
+and a 'lower' filesystem. When a name exists in both filesystems, the
|
||||
+object in the 'upper' filesystem is visible while the object in the
|
||||
+'lower' filesystem is either hidden or, in the case of directories,
|
||||
+merged with the 'upper' object.
|
||||
+
|
||||
+It would be more correct to refer to an upper and lower 'directory
|
||||
+tree' rather than 'filesystem' as it is quite possible for both
|
||||
+directory trees to be in the same filesystem and there is no
|
||||
+requirement that the root of a filesystem be given for either upper or
|
||||
+lower.
|
||||
+
|
||||
+The lower filesystem can be any filesystem supported by Linux and does
|
||||
+not need to be writable. The lower filesystem can even be another
|
||||
+overlayfs. The upper filesystem will normally be writable and if it
|
||||
+is it must support the creation of trusted.* extended attributes, and
|
||||
+must provide valid d_type in readdir responses, at least for symbolic
|
||||
+links - so NFS is not suitable.
|
||||
+
|
||||
+A read-only overlay of two read-only filesystems may use any
|
||||
+filesystem type.
|
||||
+
|
||||
+Directories
|
||||
+-----------
|
||||
+
|
||||
+Overlaying mainly involved directories. If a given name appears in both
|
||||
+upper and lower filesystems and refers to a non-directory in either,
|
||||
+then the lower object is hidden - the name refers only to the upper
|
||||
+object.
|
||||
+
|
||||
+Where both upper and lower objects are directories, a merged directory
|
||||
+is formed.
|
||||
+
|
||||
+At mount time, the two directories given as mount options are combined
|
||||
+into a merged directory:
|
||||
+
|
||||
+ mount -t overlayfs overlayfs -olowerdir=/lower,upperdir=/upper /overlay
|
||||
+
|
||||
+Then whenever a lookup is requested in such a merged directory, the
|
||||
+lookup is performed in each actual directory and the combined result
|
||||
+is cached in the dentry belonging to the overlay filesystem. If both
|
||||
+actual lookups find directories, both are stored and a merged
|
||||
+directory is created, otherwise only one is stored: the upper if it
|
||||
+exists, else the lower.
|
||||
+
|
||||
+Only the lists of names from directories are merged. Other content
|
||||
+such as metadata and extended attributes are reported for the upper
|
||||
+directory only. These attributes of the lower directory are hidden.
|
||||
+
|
||||
+whiteouts and opaque directories
|
||||
+--------------------------------
|
||||
+
|
||||
+In order to support rm and rmdir without changing the lower
|
||||
+filesystem, an overlay filesystem needs to record in the upper filesystem
|
||||
+that files have been removed. This is done using whiteouts and opaque
|
||||
+directories (non-directories are always opaque).
|
||||
+
|
||||
+The overlay filesystem uses extended attributes with a
|
||||
+"trusted.overlay." prefix to record these details.
|
||||
+
|
||||
+A whiteout is created as a symbolic link with target
|
||||
+"(overlay-whiteout)" and with xattr "trusted.overlay.whiteout" set to "y".
|
||||
+When a whiteout is found in the upper level of a merged directory, any
|
||||
+matching name in the lower level is ignored, and the whiteout itself
|
||||
+is also hidden.
|
||||
+
|
||||
+A directory is made opaque by setting the xattr "trusted.overlay.opaque"
|
||||
+to "y". Where the upper filesystem contains an opaque directory, any
|
||||
+directory in the lower filesystem with the same name is ignored.
|
||||
+
|
||||
+readdir
|
||||
+-------
|
||||
+
|
||||
+When a 'readdir' request is made on a merged directory, the upper and
|
||||
+lower directories are each read and the name lists merged in the
|
||||
+obvious way (upper is read first, then lower - entries that already
|
||||
+exist are not re-added). This merged name list is cached in the
|
||||
+'struct file' and so remains as long as the file is kept open. If the
|
||||
+directory is opened and read by two processes at the same time, they
|
||||
+will each have separate caches. A seekdir to the start of the
|
||||
+directory (offset 0) followed by a readdir will cause the cache to be
|
||||
+discarded and rebuilt.
|
||||
+
|
||||
+This means that changes to the merged directory do not appear while a
|
||||
+directory is being read. This is unlikely to be noticed by many
|
||||
+programs.
|
||||
+
|
||||
+seek offsets are assigned sequentially when the directories are read.
|
||||
+Thus if
|
||||
+ - read part of a directory
|
||||
+ - remember an offset, and close the directory
|
||||
+ - re-open the directory some time later
|
||||
+ - seek to the remembered offset
|
||||
+
|
||||
+there may be little correlation between the old and new locations in
|
||||
+the list of filenames, particularly if anything has changed in the
|
||||
+directory.
|
||||
+
|
||||
+Readdir on directories that are not merged is simply handled by the
|
||||
+underlying directory (upper or lower).
|
||||
+
|
||||
+
|
||||
+Non-directories
|
||||
+---------------
|
||||
+
|
||||
+Objects that are not directories (files, symlinks, device-special
|
||||
+files etc.) are presented either from the upper or lower filesystem as
|
||||
+appropriate. When a file in the lower filesystem is accessed in a way
|
||||
+the requires write-access, such as opening for write access, changing
|
||||
+some metadata etc., the file is first copied from the lower filesystem
|
||||
+to the upper filesystem (copy_up). Note that creating a hard-link
|
||||
+also requires copy_up, though of course creation of a symlink does
|
||||
+not.
|
||||
+
|
||||
+The copy_up may turn out to be unnecessary, for example if the file is
|
||||
+opened for read-write but the data is not modified.
|
||||
+
|
||||
+The copy_up process first makes sure that the containing directory
|
||||
+exists in the upper filesystem - creating it and any parents as
|
||||
+necessary. It then creates the object with the same metadata (owner,
|
||||
+mode, mtime, symlink-target etc.) and then if the object is a file, the
|
||||
+data is copied from the lower to the upper filesystem. Finally any
|
||||
+extended attributes are copied up.
|
||||
+
|
||||
+Once the copy_up is complete, the overlay filesystem simply
|
||||
+provides direct access to the newly created file in the upper
|
||||
+filesystem - future operations on the file are barely noticed by the
|
||||
+overlay filesystem (though an operation on the name of the file such as
|
||||
+rename or unlink will of course be noticed and handled).
|
||||
+
|
||||
+
|
||||
+Non-standard behavior
|
||||
+---------------------
|
||||
+
|
||||
+The copy_up operation essentially creates a new, identical file and
|
||||
+moves it over to the old name. The new file may be on a different
|
||||
+filesystem, so both st_dev and st_ino of the file may change.
|
||||
+
|
||||
+Any open files referring to this inode will access the old data and
|
||||
+metadata. Similarly any file locks obtained before copy_up will not
|
||||
+apply to the copied up file.
|
||||
+
|
||||
+On a file is opened with O_RDONLY fchmod(2), fchown(2), futimesat(2)
|
||||
+and fsetxattr(2) will fail with EROFS.
|
||||
+
|
||||
+If a file with multiple hard links is copied up, then this will
|
||||
+"break" the link. Changes will not be propagated to other names
|
||||
+referring to the same inode.
|
||||
+
|
||||
+Symlinks in /proc/PID/ and /proc/PID/fd which point to a non-directory
|
||||
+object in overlayfs will not contain vaid absolute paths, only
|
||||
+relative paths leading up to the filesystem's root. This will be
|
||||
+fixed in the future.
|
||||
+
|
||||
+Some operations are not atomic, for example a crash during copy_up or
|
||||
+rename will leave the filesystem in an inconsitent state. This will
|
||||
+be addressed in the future.
|
||||
+
|
||||
+Changes to underlying filesystems
|
||||
+---------------------------------
|
||||
+
|
||||
+Offline changes, when the overlay is not mounted, are allowed to either
|
||||
+the upper or the lower trees.
|
||||
+
|
||||
+Changes to the underlying filesystems while part of a mounted overlay
|
||||
+filesystem are not allowed. If the underlying filesystem is changed,
|
||||
+the behavior of the overlay is undefined, though it will not result in
|
||||
+a crash or deadlock.
|
||||
--- a/MAINTAINERS
|
||||
+++ b/MAINTAINERS
|
||||
@@ -4727,6 +4727,13 @@ F: drivers/scsi/osd/
|
||||
F: include/scsi/osd_*
|
||||
F: fs/exofs/
|
||||
|
||||
+OVERLAYFS FILESYSTEM
|
||||
+M: Miklos Szeredi <miklos@szeredi.hu>
|
||||
+L: linux-fsdevel@vger.kernel.org
|
||||
+S: Supported
|
||||
+F: fs/overlayfs/*
|
||||
+F: Documentation/filesystems/overlayfs.txt
|
||||
+
|
||||
P54 WIRELESS DRIVER
|
||||
M: Christian Lamparter <chunkeey@googlemail.com>
|
||||
L: linux-wireless@vger.kernel.org
|
||||
--- a/fs/Kconfig
|
||||
+++ b/fs/Kconfig
|
||||
@@ -63,6 +63,7 @@ source "fs/quota/Kconfig"
|
||||
|
||||
source "fs/autofs4/Kconfig"
|
||||
source "fs/fuse/Kconfig"
|
||||
+source "fs/overlayfs/Kconfig"
|
||||
|
||||
config CUSE
|
||||
tristate "Character device in Userspace support"
|
||||
--- a/fs/Makefile
|
||||
+++ b/fs/Makefile
|
||||
@@ -105,6 +105,7 @@ obj-$(CONFIG_QNX4FS_FS) += qnx4/
|
||||
obj-$(CONFIG_AUTOFS4_FS) += autofs4/
|
||||
obj-$(CONFIG_ADFS_FS) += adfs/
|
||||
obj-$(CONFIG_FUSE_FS) += fuse/
|
||||
+obj-$(CONFIG_OVERLAYFS_FS) += overlayfs/
|
||||
obj-$(CONFIG_UDF_FS) += udf/
|
||||
obj-$(CONFIG_SUN_OPENPROMFS) += openpromfs/
|
||||
obj-$(CONFIG_OMFS_FS) += omfs/
|
||||
--- a/fs/ecryptfs/main.c
|
||||
+++ b/fs/ecryptfs/main.c
|
||||
@@ -544,6 +544,13 @@ static struct dentry *ecryptfs_mount(str
|
||||
s->s_maxbytes = path.dentry->d_sb->s_maxbytes;
|
||||
s->s_blocksize = path.dentry->d_sb->s_blocksize;
|
||||
s->s_magic = ECRYPTFS_SUPER_MAGIC;
|
||||
+ s->s_stack_depth = path.dentry->d_sb->s_stack_depth + 1;
|
||||
+
|
||||
+ rc = -EINVAL;
|
||||
+ if (s->s_stack_depth > FILESYSTEM_MAX_STACK_DEPTH) {
|
||||
+ printk(KERN_ERR "eCryptfs: maximum fs stacking depth exceeded\n");
|
||||
+ goto out_free;
|
||||
+ }
|
||||
|
||||
inode = ecryptfs_get_inode(path.dentry->d_inode, s);
|
||||
rc = PTR_ERR(inode);
|
||||
--- a/fs/namespace.c
|
||||
+++ b/fs/namespace.c
|
||||
@@ -1492,6 +1492,23 @@ void drop_collected_mounts(struct vfsmou
|
||||
release_mounts(&umount_list);
|
||||
}
|
||||
|
||||
+struct vfsmount *clone_private_mount(struct path *path)
|
||||
+{
|
||||
+ struct vfsmount *mnt;
|
||||
+
|
||||
+ if (IS_MNT_UNBINDABLE(path->mnt))
|
||||
+ return ERR_PTR(-EINVAL);
|
||||
+
|
||||
+ down_read(&namespace_sem);
|
||||
+ mnt = clone_mnt(path->mnt, path->dentry, CL_PRIVATE);
|
||||
+ up_read(&namespace_sem);
|
||||
+ if (!mnt)
|
||||
+ return ERR_PTR(-ENOMEM);
|
||||
+
|
||||
+ return mnt;
|
||||
+}
|
||||
+EXPORT_SYMBOL_GPL(clone_private_mount);
|
||||
+
|
||||
int iterate_mounts(int (*f)(struct vfsmount *, void *), void *arg,
|
||||
struct vfsmount *root)
|
||||
{
|
||||
--- a/fs/open.c
|
||||
+++ b/fs/open.c
|
||||
@@ -666,8 +666,7 @@ static inline int __get_file_write_acces
|
||||
|
|
@ -154,92 +434,6 @@
|
|||
|
||||
static void __put_unused_fd(struct files_struct *files, unsigned int fd)
|
||||
{
|
||||
--- a/include/linux/fs.h
|
||||
+++ b/include/linux/fs.h
|
||||
@@ -1603,6 +1603,7 @@ struct inode_operations {
|
||||
void (*truncate_range)(struct inode *, loff_t, loff_t);
|
||||
int (*fiemap)(struct inode *, struct fiemap_extent_info *, u64 start,
|
||||
u64 len);
|
||||
+ struct file *(*open)(struct dentry *, int flags, const struct cred *);
|
||||
} ____cacheline_aligned;
|
||||
|
||||
struct seq_file;
|
||||
@@ -1998,6 +1999,7 @@ extern long do_sys_open(int dfd, const c
|
||||
extern struct file *filp_open(const char *, int, int);
|
||||
extern struct file *file_open_root(struct dentry *, struct vfsmount *,
|
||||
const char *, int);
|
||||
+extern struct file *vfs_open(struct path *, int flags, const struct cred *);
|
||||
extern struct file * dentry_open(struct dentry *, struct vfsmount *, int,
|
||||
const struct cred *);
|
||||
extern int filp_close(struct file *, fl_owner_t id);
|
||||
--- a/fs/splice.c
|
||||
+++ b/fs/splice.c
|
||||
@@ -1300,6 +1300,7 @@ long do_splice_direct(struct file *in, l
|
||||
|
||||
return ret;
|
||||
}
|
||||
+EXPORT_SYMBOL(do_splice_direct);
|
||||
|
||||
static int splice_pipe_to_pipe(struct pipe_inode_info *ipipe,
|
||||
struct pipe_inode_info *opipe,
|
||||
--- a/fs/namespace.c
|
||||
+++ b/fs/namespace.c
|
||||
@@ -1492,6 +1492,23 @@ void drop_collected_mounts(struct vfsmou
|
||||
release_mounts(&umount_list);
|
||||
}
|
||||
|
||||
+struct vfsmount *clone_private_mount(struct path *path)
|
||||
+{
|
||||
+ struct vfsmount *mnt;
|
||||
+
|
||||
+ if (IS_MNT_UNBINDABLE(path->mnt))
|
||||
+ return ERR_PTR(-EINVAL);
|
||||
+
|
||||
+ down_read(&namespace_sem);
|
||||
+ mnt = clone_mnt(path->mnt, path->dentry, CL_PRIVATE);
|
||||
+ up_read(&namespace_sem);
|
||||
+ if (!mnt)
|
||||
+ return ERR_PTR(-ENOMEM);
|
||||
+
|
||||
+ return mnt;
|
||||
+}
|
||||
+EXPORT_SYMBOL_GPL(clone_private_mount);
|
||||
+
|
||||
int iterate_mounts(int (*f)(struct vfsmount *, void *), void *arg,
|
||||
struct vfsmount *root)
|
||||
{
|
||||
--- a/include/linux/mount.h
|
||||
+++ b/include/linux/mount.h
|
||||
@@ -100,6 +100,9 @@ extern void mnt_pin(struct vfsmount *mnt
|
||||
extern void mnt_unpin(struct vfsmount *mnt);
|
||||
extern int __mnt_is_readonly(struct vfsmount *mnt);
|
||||
|
||||
+struct path;
|
||||
+extern struct vfsmount *clone_private_mount(struct path *path);
|
||||
+
|
||||
extern struct vfsmount *do_kern_mount(const char *fstype, int flags,
|
||||
const char *name, void *data);
|
||||
|
||||
--- a/fs/Kconfig
|
||||
+++ b/fs/Kconfig
|
||||
@@ -63,6 +63,7 @@ source "fs/quota/Kconfig"
|
||||
|
||||
source "fs/autofs4/Kconfig"
|
||||
source "fs/fuse/Kconfig"
|
||||
+source "fs/overlayfs/Kconfig"
|
||||
|
||||
config CUSE
|
||||
tristate "Character device in Userspace support"
|
||||
--- a/fs/Makefile
|
||||
+++ b/fs/Makefile
|
||||
@@ -105,6 +105,7 @@ obj-$(CONFIG_QNX4FS_FS) += qnx4/
|
||||
obj-$(CONFIG_AUTOFS4_FS) += autofs4/
|
||||
obj-$(CONFIG_ADFS_FS) += adfs/
|
||||
obj-$(CONFIG_FUSE_FS) += fuse/
|
||||
+obj-$(CONFIG_OVERLAYFS_FS) += overlayfs/
|
||||
obj-$(CONFIG_UDF_FS) += udf/
|
||||
obj-$(CONFIG_SUN_OPENPROMFS) += openpromfs/
|
||||
obj-$(CONFIG_OMFS_FS) += omfs/
|
||||
--- /dev/null
|
||||
+++ b/fs/overlayfs/Kconfig
|
||||
@@ -0,0 +1,4 @@
|
||||
|
|
@ -645,7 +839,7 @@
|
|||
+}
|
||||
--- /dev/null
|
||||
+++ b/fs/overlayfs/dir.c
|
||||
@@ -0,0 +1,607 @@
|
||||
@@ -0,0 +1,596 @@
|
||||
+/*
|
||||
+ *
|
||||
+ * Copyright (C) 2011 Novell Inc.
|
||||
|
|
@ -663,17 +857,6 @@
|
|||
+
|
||||
+static const char *ovl_whiteout_symlink = "(overlay-whiteout)";
|
||||
+
|
||||
+static struct dentry *ovl_lookup(struct inode *dir, struct dentry *dentry,
|
||||
+ struct nameidata *nd)
|
||||
+{
|
||||
+ int err = ovl_do_lookup(dentry);
|
||||
+
|
||||
+ if (err)
|
||||
+ return ERR_PTR(err);
|
||||
+
|
||||
+ return NULL;
|
||||
+}
|
||||
+
|
||||
+static int ovl_whiteout(struct dentry *upperdir, struct dentry *dentry)
|
||||
+{
|
||||
+ int err;
|
||||
|
|
@ -1255,7 +1438,7 @@
|
|||
+};
|
||||
--- /dev/null
|
||||
+++ b/fs/overlayfs/inode.c
|
||||
@@ -0,0 +1,375 @@
|
||||
@@ -0,0 +1,384 @@
|
||||
+/*
|
||||
+ *
|
||||
+ * Copyright (C) 2011 Novell Inc.
|
||||
|
|
@ -1348,9 +1531,18 @@
|
|||
+ /*
|
||||
+ * Writes will always be redirected to upper layer, so
|
||||
+ * ignore lower layer being read-only.
|
||||
+ *
|
||||
+ * If the overlay itself is read-only then proceed
|
||||
+ * with the permission check, don't return EROFS.
|
||||
+ * This will only happen if this is the lower layer of
|
||||
+ * another overlayfs.
|
||||
+ *
|
||||
+ * If upper fs becomes read-only after the overlay was
|
||||
+ * constructed return EROFS to prevent modification of
|
||||
+ * upper layer.
|
||||
+ */
|
||||
+ err = -EROFS;
|
||||
+ if (is_upper && IS_RDONLY(realinode) &&
|
||||
+ if (is_upper && !IS_RDONLY(inode) && IS_RDONLY(realinode) &&
|
||||
+ (S_ISREG(mode) || S_ISDIR(mode) || S_ISLNK(mode)))
|
||||
+ goto out_dput;
|
||||
+
|
||||
|
|
@ -1633,7 +1825,7 @@
|
|||
+}
|
||||
--- /dev/null
|
||||
+++ b/fs/overlayfs/overlayfs.h
|
||||
@@ -0,0 +1,62 @@
|
||||
@@ -0,0 +1,63 @@
|
||||
+/*
|
||||
+ *
|
||||
+ * Copyright (C) 2011 Novell Inc.
|
||||
|
|
@ -1669,7 +1861,8 @@
|
|||
+void ovl_dentry_set_opaque(struct dentry *dentry, bool opaque);
|
||||
+bool ovl_is_whiteout(struct dentry *dentry);
|
||||
+void ovl_dentry_update(struct dentry *dentry, struct dentry *upperdentry);
|
||||
+int ovl_do_lookup(struct dentry *dentry);
|
||||
+struct dentry *ovl_lookup(struct inode *dir, struct dentry *dentry,
|
||||
+ struct nameidata *nd);
|
||||
+
|
||||
+struct dentry *ovl_upper_create(struct dentry *upperdir, struct dentry *dentry,
|
||||
+ struct kstat *stat, const char *link);
|
||||
|
|
@ -1866,8 +2059,8 @@
|
|||
+ return ovl_cache_entry_add_rb(rdd, name, namelen, ino, d_type);
|
||||
+}
|
||||
+
|
||||
+static int ovl_dir_read(struct path *realpath, struct ovl_readdir_data *rdd,
|
||||
+ filldir_t filler)
|
||||
+static inline int ovl_dir_read(struct path *realpath,
|
||||
+ struct ovl_readdir_data *rdd, filldir_t filler)
|
||||
+{
|
||||
+ struct file *realfile;
|
||||
+ int err;
|
||||
|
|
@ -1947,7 +2140,7 @@
|
|||
+ return 0;
|
||||
+}
|
||||
+
|
||||
+static int ovl_dir_read_merged(struct path *upperpath, struct path *lowerpath,
|
||||
+static inline int ovl_dir_read_merged(struct path *upperpath, struct path *lowerpath,
|
||||
+ struct ovl_readdir_data *rdd)
|
||||
+{
|
||||
+ int err;
|
||||
|
|
@ -2259,7 +2452,7 @@
|
|||
+}
|
||||
--- /dev/null
|
||||
+++ b/fs/overlayfs/super.c
|
||||
@@ -0,0 +1,625 @@
|
||||
@@ -0,0 +1,656 @@
|
||||
+/*
|
||||
+ *
|
||||
+ * Copyright (C) 2011 Novell Inc.
|
||||
|
|
@ -2510,7 +2703,7 @@
|
|||
+ return kzalloc(sizeof(struct ovl_entry), GFP_KERNEL);
|
||||
+}
|
||||
+
|
||||
+static struct dentry *ovl_lookup_real(struct dentry *dir, struct qstr *name)
|
||||
+static inline struct dentry *ovl_lookup_real(struct dentry *dir, struct qstr *name)
|
||||
+{
|
||||
+ struct dentry *dentry;
|
||||
+
|
||||
|
|
@ -2528,7 +2721,7 @@
|
|||
+ return dentry;
|
||||
+}
|
||||
+
|
||||
+int ovl_do_lookup(struct dentry *dentry)
|
||||
+static int ovl_do_lookup(struct dentry *dentry)
|
||||
+{
|
||||
+ struct ovl_entry *oe;
|
||||
+ struct dentry *upperdir;
|
||||
|
|
@ -2625,6 +2818,17 @@
|
|||
+ return err;
|
||||
+}
|
||||
+
|
||||
+struct dentry *ovl_lookup(struct inode *dir, struct dentry *dentry,
|
||||
+ struct nameidata *nd)
|
||||
+{
|
||||
+ int err = ovl_do_lookup(dentry);
|
||||
+
|
||||
+ if (err)
|
||||
+ return ERR_PTR(err);
|
||||
+
|
||||
+ return NULL;
|
||||
+}
|
||||
+
|
||||
+static void ovl_put_super(struct super_block *sb)
|
||||
+{
|
||||
+ struct ovl_fs *ufs = sb->s_fs_info;
|
||||
|
|
@ -2796,6 +3000,16 @@
|
|||
+ !S_ISDIR(lowerpath.dentry->d_inode->i_mode))
|
||||
+ goto out_put_lowerpath;
|
||||
+
|
||||
+ sb->s_stack_depth = max(upperpath.mnt->mnt_sb->s_stack_depth,
|
||||
+ lowerpath.mnt->mnt_sb->s_stack_depth) + 1;
|
||||
+
|
||||
+ err = -EINVAL;
|
||||
+ if (sb->s_stack_depth > FILESYSTEM_MAX_STACK_DEPTH) {
|
||||
+ printk(KERN_ERR "overlayfs: maximum fs stacking depth exceeded\n");
|
||||
+ goto out_put_lowerpath;
|
||||
+ }
|
||||
+
|
||||
+
|
||||
+ ufs->upper_mnt = clone_private_mount(&upperpath);
|
||||
+ err = PTR_ERR(ufs->upper_mnt);
|
||||
+ if (IS_ERR(ufs->upper_mnt)) {
|
||||
|
|
@ -2810,6 +3024,16 @@
|
|||
+ goto out_put_upper_mnt;
|
||||
+ }
|
||||
+
|
||||
+ /*
|
||||
+ * Make lower_mnt R/O. That way fchmod/fchown on lower file
|
||||
+ * will fail instead of modifying lower fs.
|
||||
+ */
|
||||
+ ufs->lower_mnt->mnt_flags |= MNT_READONLY;
|
||||
+
|
||||
+ /* If the upper fs is r/o, we mark overlayfs r/o too */
|
||||
+ if (ufs->upper_mnt->mnt_sb->s_flags & MS_RDONLY)
|
||||
+ sb->s_flags |= MS_RDONLY;
|
||||
+
|
||||
+ if (!(sb->s_flags & MS_RDONLY)) {
|
||||
+ err = mnt_want_write(ufs->upper_mnt);
|
||||
+ if (err)
|
||||
|
|
@ -2885,189 +3109,68 @@
|
|||
+
|
||||
+module_init(ovl_init);
|
||||
+module_exit(ovl_exit);
|
||||
--- /dev/null
|
||||
+++ b/Documentation/filesystems/overlayfs.txt
|
||||
@@ -0,0 +1,167 @@
|
||||
+Written by: Neil Brown <neilb@suse.de>
|
||||
+
|
||||
+Overlay Filesystem
|
||||
+==================
|
||||
+
|
||||
+This document describes a prototype for a new approach to providing
|
||||
+overlay-filesystem functionality in Linux (sometimes referred to as
|
||||
+union-filesystems). An overlay-filesystem tries to present a
|
||||
+filesystem which is the result over overlaying one filesystem on top
|
||||
+of the other.
|
||||
+
|
||||
+The result will inevitably fail to look exactly like a normal
|
||||
+filesystem for various technical reasons. The expectation is that
|
||||
+many use cases will be able to ignore these differences.
|
||||
+
|
||||
+This approach is 'hybrid' because the objects that appear in the
|
||||
+filesystem do not all appear to belong to that filesystem. In many
|
||||
+cases an object accessed in the union will be indistinguishable
|
||||
+from accessing the corresponding object from the original filesystem.
|
||||
+This is most obvious from the 'st_dev' field returned by stat(2).
|
||||
+
|
||||
+While directories will report an st_dev from the overlay-filesystem,
|
||||
+all non-directory objects will report an st_dev from the lower or
|
||||
+upper filesystem that is providing the object. Similarly st_ino will
|
||||
+only be unique when combined with st_dev, and both of these can change
|
||||
+over the lifetime of a non-directory object. Many applications and
|
||||
+tools ignore these values and will not be affected.
|
||||
+
|
||||
+Upper and Lower
|
||||
+---------------
|
||||
+
|
||||
+An overlay filesystem combines two filesystems - an 'upper' filesystem
|
||||
+and a 'lower' filesystem. When a name exists in both filesystems, the
|
||||
+object in the 'upper' filesystem is visible while the object in the
|
||||
+'lower' filesystem is either hidden or, in the case of directories,
|
||||
+merged with the 'upper' object.
|
||||
+
|
||||
+It would be more correct to refer to an upper and lower 'directory
|
||||
+tree' rather than 'filesystem' as it is quite possible for both
|
||||
+directory trees to be in the same filesystem and there is no
|
||||
+requirement that the root of a filesystem be given for either upper or
|
||||
+lower.
|
||||
+
|
||||
+The lower filesystem can be any filesystem supported by Linux and does
|
||||
+not need to be writable. The lower filesystem can even be another
|
||||
+overlayfs. The upper filesystem will normally be writable and if it
|
||||
+is it must support the creation of trusted.* extended attributes, and
|
||||
+must provide valid d_type in readdir responses, at least for symbolic
|
||||
+links - so NFS is not suitable.
|
||||
+
|
||||
+A read-only overlay of two read-only filesystems may use any
|
||||
+filesystem type.
|
||||
+
|
||||
+Directories
|
||||
+-----------
|
||||
+
|
||||
+Overlaying mainly involved directories. If a given name appears in both
|
||||
+upper and lower filesystems and refers to a non-directory in either,
|
||||
+then the lower object is hidden - the name refers only to the upper
|
||||
+object.
|
||||
+
|
||||
+Where both upper and lower objects are directories, a merged directory
|
||||
+is formed.
|
||||
+
|
||||
+At mount time, the two directories given as mount options are combined
|
||||
+into a merged directory:
|
||||
+
|
||||
+ mount -t overlayfs overlayfs -olowerdir=/lower,upperdir=/upper /overlay
|
||||
+
|
||||
+Then whenever a lookup is requested in such a merged directory, the
|
||||
+lookup is performed in each actual directory and the combined result
|
||||
+is cached in the dentry belonging to the overlay filesystem. If both
|
||||
+actual lookups find directories, both are stored and a merged
|
||||
+directory is created, otherwise only one is stored: the upper if it
|
||||
+exists, else the lower.
|
||||
+
|
||||
+Only the lists of names from directories are merged. Other content
|
||||
+such as metadata and extended attributes are reported for the upper
|
||||
+directory only. These attributes of the lower directory are hidden.
|
||||
+
|
||||
+whiteouts and opaque directories
|
||||
+--------------------------------
|
||||
+
|
||||
+In order to support rm and rmdir without changing the lower
|
||||
+filesystem, an overlay filesystem needs to record in the upper filesystem
|
||||
+that files have been removed. This is done using whiteouts and opaque
|
||||
+directories (non-directories are always opaque).
|
||||
+
|
||||
+The overlay filesystem uses extended attributes with a
|
||||
+"trusted.overlay." prefix to record these details.
|
||||
+
|
||||
+A whiteout is created as a symbolic link with target
|
||||
+"(overlay-whiteout)" and with xattr "trusted.overlay.whiteout" set to "y".
|
||||
+When a whiteout is found in the upper level of a merged directory, any
|
||||
+matching name in the lower level is ignored, and the whiteout itself
|
||||
+is also hidden.
|
||||
+
|
||||
+A directory is made opaque by setting the xattr "trusted.overlay.opaque"
|
||||
+to "y". Where the upper filesystem contains an opaque directory, any
|
||||
+directory in the lower filesystem with the same name is ignored.
|
||||
+
|
||||
+readdir
|
||||
+-------
|
||||
+
|
||||
+When a 'readdir' request is made on a merged directory, the upper and
|
||||
+lower directories are each read and the name lists merged in the
|
||||
+obvious way (upper is read first, then lower - entries that already
|
||||
+exist are not re-added). This merged name list is cached in the
|
||||
+'struct file' and so remains as long as the file is kept open. If the
|
||||
+directory is opened and read by two processes at the same time, they
|
||||
+will each have separate caches. A seekdir to the start of the
|
||||
+directory (offset 0) followed by a readdir will cause the cache to be
|
||||
+discarded and rebuilt.
|
||||
+
|
||||
+This means that changes to the merged directory do not appear while a
|
||||
+directory is being read. This is unlikely to be noticed by many
|
||||
+programs.
|
||||
+
|
||||
+seek offsets are assigned sequentially when the directories are read.
|
||||
+Thus if
|
||||
+ - read part of a directory
|
||||
+ - remember an offset, and close the directory
|
||||
+ - re-open the directory some time later
|
||||
+ - seek to the remembered offset
|
||||
+
|
||||
+there may be little correlation between the old and new locations in
|
||||
+the list of filenames, particularly if anything has changed in the
|
||||
+directory.
|
||||
+
|
||||
+Readdir on directories that are not merged is simply handled by the
|
||||
+underlying directory (upper or lower).
|
||||
+
|
||||
+
|
||||
+Non-directories
|
||||
+---------------
|
||||
+
|
||||
+Objects that are not directories (files, symlinks, device-special
|
||||
+files etc.) are presented either from the upper or lower filesystem as
|
||||
+appropriate. When a file in the lower filesystem is accessed in a way
|
||||
+the requires write-access, such as opening for write access, changing
|
||||
+some metadata etc., the file is first copied from the lower filesystem
|
||||
+to the upper filesystem (copy_up). Note that creating a hard-link
|
||||
+also requires copy_up, though of course creation of a symlink does
|
||||
+not.
|
||||
+
|
||||
+The copy_up process first makes sure that the containing directory
|
||||
+exists in the upper filesystem - creating it and any parents as
|
||||
+necessary. It then creates the object with the same metadata (owner,
|
||||
+mode, mtime, symlink-target etc.) and then if the object is a file, the
|
||||
+data is copied from the lower to the upper filesystem. Finally any
|
||||
+extended attributes are copied up.
|
||||
+
|
||||
+Once the copy_up is complete, the overlay filesystem simply
|
||||
+provides direct access to the newly created file in the upper
|
||||
+filesystem - future operations on the file are barely noticed by the
|
||||
+overlay filesystem (though an operation on the name of the file such as
|
||||
+rename or unlink will of course be noticed and handled).
|
||||
+
|
||||
+Changes to underlying filesystems
|
||||
+---------------------------------
|
||||
+
|
||||
+Offline changes, when the overlay is not mounted, are allowed to either
|
||||
+the upper or the lower trees.
|
||||
+
|
||||
+Changes to the underlying filesystems while part of a mounted overlay
|
||||
+filesystem are not allowed. This is not yet enforced, but will be in
|
||||
+the future.
|
||||
--- a/MAINTAINERS
|
||||
+++ b/MAINTAINERS
|
||||
@@ -4727,6 +4727,13 @@ F: drivers/scsi/osd/
|
||||
F: include/scsi/osd_*
|
||||
F: fs/exofs/
|
||||
--- a/fs/splice.c
|
||||
+++ b/fs/splice.c
|
||||
@@ -1300,6 +1300,7 @@ long do_splice_direct(struct file *in, l
|
||||
|
||||
+OVERLAYFS FILESYSTEM
|
||||
+M: Miklos Szeredi <miklos@szeredi.hu>
|
||||
+L: linux-fsdevel@vger.kernel.org
|
||||
+S: Supported
|
||||
+F: fs/overlayfs/*
|
||||
+F: Documentation/filesystems/overlayfs.txt
|
||||
return ret;
|
||||
}
|
||||
+EXPORT_SYMBOL(do_splice_direct);
|
||||
|
||||
static int splice_pipe_to_pipe(struct pipe_inode_info *ipipe,
|
||||
struct pipe_inode_info *opipe,
|
||||
--- a/include/linux/fs.h
|
||||
+++ b/include/linux/fs.h
|
||||
@@ -480,6 +480,12 @@ struct iattr {
|
||||
*/
|
||||
#include <linux/quota.h>
|
||||
|
||||
+/*
|
||||
+ * Maximum number of layers of fs stack. Needs to be limited to
|
||||
+ * prevent kernel stack overflow
|
||||
+ */
|
||||
+#define FILESYSTEM_MAX_STACK_DEPTH 2
|
||||
+
|
||||
P54 WIRELESS DRIVER
|
||||
M: Christian Lamparter <chunkeey@googlemail.com>
|
||||
L: linux-wireless@vger.kernel.org
|
||||
/**
|
||||
* enum positive_aop_returns - aop return codes with specific semantics
|
||||
*
|
||||
@@ -1438,6 +1444,11 @@ struct super_block {
|
||||
* Saved pool identifier for cleancache (-1 means none)
|
||||
*/
|
||||
int cleancache_poolid;
|
||||
+
|
||||
+ /*
|
||||
+ * Indicates how deep in a filesystem stack this SB is
|
||||
+ */
|
||||
+ int s_stack_depth;
|
||||
};
|
||||
|
||||
extern struct timespec current_fs_time(struct super_block *sb);
|
||||
@@ -1603,6 +1614,7 @@ struct inode_operations {
|
||||
void (*truncate_range)(struct inode *, loff_t, loff_t);
|
||||
int (*fiemap)(struct inode *, struct fiemap_extent_info *, u64 start,
|
||||
u64 len);
|
||||
+ struct file *(*open)(struct dentry *, int flags, const struct cred *);
|
||||
} ____cacheline_aligned;
|
||||
|
||||
struct seq_file;
|
||||
@@ -1998,6 +2010,7 @@ extern long do_sys_open(int dfd, const c
|
||||
extern struct file *filp_open(const char *, int, int);
|
||||
extern struct file *file_open_root(struct dentry *, struct vfsmount *,
|
||||
const char *, int);
|
||||
+extern struct file *vfs_open(struct path *, int flags, const struct cred *);
|
||||
extern struct file * dentry_open(struct dentry *, struct vfsmount *, int,
|
||||
const struct cred *);
|
||||
extern int filp_close(struct file *, fl_owner_t id);
|
||||
--- a/include/linux/mount.h
|
||||
+++ b/include/linux/mount.h
|
||||
@@ -100,6 +100,9 @@ extern void mnt_pin(struct vfsmount *mnt
|
||||
extern void mnt_unpin(struct vfsmount *mnt);
|
||||
extern int __mnt_is_readonly(struct vfsmount *mnt);
|
||||
|
||||
+struct path;
|
||||
+extern struct vfsmount *clone_private_mount(struct path *path);
|
||||
+
|
||||
extern struct vfsmount *do_kern_mount(const char *fstype, int flags,
|
||||
const char *name, void *data);
|
||||
|
||||
Loading…
Reference in a new issue