diff --git a/Documentation/filesystems/00-INDEX b/Documentation/filesystems/00-INDEX
index 5717858..2ef035e 100644
--- a/Documentation/filesystems/00-INDEX
+++ b/Documentation/filesystems/00-INDEX
@@ -84,6 +84,8 @@ udf.txt
- info and mount options for the UDF filesystem.
ufs.txt
- info on the ufs filesystem.
+unionfs/
+ - info on the unionfs filesystem
vfat.txt
- info on using the VFAT filesystem used in Windows NT and Windows 95
vfs.txt
diff --git a/Documentation/filesystems/unionfs/00-INDEX b/Documentation/filesystems/unionfs/00-INDEX
new file mode 100644
index 0000000..96fdf67
--- /dev/null
+++ b/Documentation/filesystems/unionfs/00-INDEX
@@ -0,0 +1,10 @@
+00-INDEX
+ - this file.
+concepts.txt
+ - A brief introduction of concepts.
+issues.txt
+ - A summary of known issues with unionfs.
+rename.txt
+ - Information regarding rename operations.
+usage.txt
+ - Usage information and examples.
diff --git a/Documentation/filesystems/unionfs/concepts.txt b/Documentation/filesystems/unionfs/concepts.txt
new file mode 100644
index 0000000..eb74aac
--- /dev/null
+++ b/Documentation/filesystems/unionfs/concepts.txt
@@ -0,0 +1,181 @@
+Unionfs 2.0 CONCEPTS:
+=====================
+
+This file describes the concepts needed by a namespace unification file
+system.
+
+
+Branch Priority:
+================
+
+Each branch is assigned a unique priority - starting from 0 (highest
+priority). No two branches can have the same priority.
+
+
+Branch Mode:
+============
+
+Each branch is assigned a mode - read-write or read-only. This allows
+directories on media mounted read-write to be used in a read-only manner.
+
+
+Whiteouts:
+==========
+
+A whiteout removes a file name from the namespace. Whiteouts are needed when
+one attempts to remove a file on a read-only branch.
+
+Suppose we have a two-branch union, where branch 0 is read-write and branch
+1 is read-only. And a file 'foo' on branch 1:
+
+./b0/
+./b1/
+./b1/foo
+
+The unified view would simply be:
+
+./union/
+./union/foo
+
+Since 'foo' is stored on a read-only branch, it cannot be removed. A
+whiteout is used to remove the name 'foo' from the unified namespace. Again,
+since branch 1 is read-only, the whiteout cannot be created there. So, we
+try on a higher priority (lower numerically) branch and create the whiteout
+there.
+
+./b0/
+./b0/.wh.foo
+./b1/
+./b1/foo
+
+Later, when Unionfs traverses branches (due to lookup or readdir), it
+eliminate 'foo' from the namespace (as well as the whiteout itself.)
+
+
+Duplicate Elimination:
+======================
+
+It is possible for files on different branches to have the same name.
+Unionfs then has to select which instance of the file to show to the user.
+Given the fact that each branch has a priority associated with it, the
+simplest solution is to take the instance from the highest priority
+(numerically lowest value) and "hide" the others.
+
+
+Copyup:
+=======
+
+When a change is made to the contents of a file's data or meta-data, they
+have to be stored somewhere. The best way is to create a copy of the
+original file on a branch that is writable, and then redirect the write
+though to this copy. The copy must be made on a higher priority branch so
+that lookup and readdir return this newer "version" of the file rather than
+the original (see duplicate elimination).
+
+
+Cache Coherency:
+================
+
+Unionfs users often want to be able to modify files and directories directly
+on the lower branches, and have those changes be visible at the Unionfs
+level. This means that data (e.g., pages) and meta-data (dentries, inodes,
+open files, etc.) have to be synchronized between the upper and lower
+layers. In other words, the newest changes from a layer below have to be
+propagated to the Unionfs layer above. If the two layers are not in sync, a
+cache incoherency ensues, which could lead to application failures and even
+oopses. The Linux kernel, however, has a rather limited set of mechanisms
+to ensure this inter-layer cache coherency---so Unionfs has to do most of
+the hard work on its own.
+
+Maintaining Invariants:
+
+The way Unionfs ensures cache coherency is as follows. At each entry point
+to a Unionfs file system method, we call a utility function to validate the
+primary objects of this method. Generally, we call unionfs_file_revalidate
+on open files, and __Unionfs_d_revalidate_chain on dentries (which also
+validates inodes). These utility functions check to see whether the upper
+Unionfs object is in sync with any of the lower objects that it represents.
+The checks we perform include whether the Unionfs superblock has a newer
+generation number, or if any of the lower objects mtime's or ctime's are
+newer. (Note: generation numbers change when branch-management commands are
+issued, so in a way, maintaining cache coherency is also very important for
+branch-management.) If indeed we determine that any Unionfs object is no
+longer in sync with its lower counterparts, then we rebuild that object
+similarly to how we do so for branch-management.
+
+While rebuilding Unionfs's objects, we also purge any page mappings and
+truncate inode pages (see fs/Unionfs/dentry.c:purge_inode_data). This is to
+ensure that Unionfs will re-get the newer data from the lower branches. We
+perform this purging only if the Unionfs operation in question is a reading
+operation; if Unionfs is performing a data writing operation (e.g., ->write,
+->commit_write, etc.) then we do NOT flush the lower mappings/pages: this is
+because (1) a self-deadlock could occur and (2) the upper Unionfs pages are
+considered more authoritative anyway, as they are newer and will overwrite
+any lower pages.
+
+Unionfs maintains the following important invariant regarding mtime's,
+ctime's, and atime's: the upper inode object's times are the max() of all of
+the lower ones. For non-directory objects, there's only one object below,
+so the mapping is simple; for directory objects, there could me multiple
+lower objects and we have to sync up with the newest one of all the lower
+ones. This invariant is important to maintain, especially for directories
+(besides, we need this to be POSIX compliant). A union could comprise
+multiple writable branches, each of which could change. If we don't reflect
+the newest possible mtime/ctime, some applications could fail. For example,
+NFSv2/v3 exports check for newer directory mtimes on the server to determine
+if the client-side attribute cache should be purged.
+
+To maintain these important invariants, of course, Unionfs carefully
+synchronizes upper and lower times in various places. For example, if we
+copy-up a file to a top-level branch, the parent directory where the file
+was copied up to will now have a new mtime: so after a successful copy-up,
+we sync up with the new top-level branch's parent directory mtime.
+
+Implementation:
+
+This cache-coherency implementation is efficient because it defers any
+synchronizing between the upper and lower layers until absolutely needed.
+Consider the example a common situation where users perform a lot of lower
+changes, such as untarring a whole package. While these take place,
+typically the user doesn't access the files via Unionfs; only after the
+lower changes are done, does the user try to access the lower files. With
+our cache-coherency implementation, the entirety of the changes to the lower
+branches will not result in a single CPU cycle spent at the Unionfs level
+until the user invokes a system call that goes through Unionfs.
+
+We have considered two alternate cache-coherency designs. (1) Using the
+dentry/inode notify functionality to register interest in finding out about
+any lower changes. This is a somewhat limited and also a heavy-handed
+approach which could result in many notifications to the Unionfs layer upon
+each small change at the lower layer (imagine a file being modified multiple
+times in rapid succession). (2) Rewriting the VFS to support explicit
+callbacks from lower objects to upper objects. We began exploring such an
+implementation, but found it to be very complicated--it would have resulted
+in massive VFS/MM changes which are unlikely to be accepted by the LKML
+community. We therefore believe that our current cache-coherency design and
+implementation represent the best approach at this time.
+
+Limitations:
+
+Our implementation works in that as long as a user process will have caused
+Unionfs to be called, directly or indirectly, even to just do
+->d_revalidate; then we will have purged the current Unionfs data and the
+process will see the new data. For example, a process that continually
+re-reads the same file's data will see the NEW data as soon as the lower
+file had changed, upon the next read(2) syscall (even if the file is still
+open!) However, this doesn't work when the process re-reads the open file's
+data via mmap(2) (unless the user unmaps/closes the file and remaps/reopens
+it). Once we respond to ->readpage(s), then the kernel maps the page into
+the process's address space and there doesn't appear to be a way to force
+the kernel to invalidate those pages/mappings, and force the process to
+re-issue ->readpage. If there's a way to invalidate active mappings and
+force a ->readpage, let us know please (invalidate_inode_pages2 doesn't do
+the trick).
+
+Our current Unionfs code has to perform many file-revalidation calls. It
+would be really nice if the VFS would export an optional file system hook
+->file_revalidate (similarly to dentry->d_revalidate) that will be called
+before each VFS op that has a "struct file" in it.
+
+
+For more information, see .
diff --git a/Documentation/filesystems/unionfs/issues.txt b/Documentation/filesystems/unionfs/issues.txt
new file mode 100644
index 0000000..3644fea
--- /dev/null
+++ b/Documentation/filesystems/unionfs/issues.txt
@@ -0,0 +1,15 @@
+KNOWN Unionfs 2.0 ISSUES:
+=========================
+
+1. The NFS server returns -EACCES for read-only exports, instead of -EROFS.
+ This means we can't reliably detect a read-only NFS export.
+
+2. Unionfs should not use lookup_one_len() on the underlying f/s as it
+ confuses NFSv4. Currently, unionfs_lookup() passes lookup intents to the
+ lower file-system, this eliminates part of the problem. The remaining
+ calls to lookup_one_len may need to be changed to pass an intent. We are
+ currently introducing VFS changes to fs/namei.c's do_path_lookup() to
+ allow proper file lookup and opening in stackable file systems.
+
+
+For more information, see .
diff --git a/Documentation/filesystems/unionfs/rename.txt b/Documentation/filesystems/unionfs/rename.txt
new file mode 100644
index 0000000..e20bb82
--- /dev/null
+++ b/Documentation/filesystems/unionfs/rename.txt
@@ -0,0 +1,31 @@
+Rename is a complex beast. The following table shows which rename(2) operations
+should succeed and which should fail.
+
+o: success
+E: error (either unionfs or vfs)
+X: EXDEV
+
+none = file does not exist
+file = file is a file
+dir = file is a empty directory
+child= file is a non-empty directory
+wh = file is a directory containing only whiteouts; this makes it logically
+ empty
+
+ none file dir child wh
+file o o E E E
+dir o E o E o
+child X E X E X
+wh o E o E o
+
+
+Renaming directories:
+=====================
+
+Whenever a empty (either physically or logically) directory is being renamed,
+the following sequence of events should take place:
+
+1) Remove whiteouts from both source and destination directory
+2) Rename source to destination
+3) Make destination opaque to prevent anything under it from showing up
+
diff --git a/Documentation/filesystems/unionfs/usage.txt b/Documentation/filesystems/unionfs/usage.txt
new file mode 100644
index 0000000..c035243
--- /dev/null
+++ b/Documentation/filesystems/unionfs/usage.txt
@@ -0,0 +1,97 @@
+Unionfs is a stackable unification file system, which can appear to merge
+the contents of several directories (branches), while keeping their physical
+content separate. Unionfs is useful for unified source tree management,
+merged contents of split CD-ROM, merged separate software package
+directories, data grids, and more. Unionfs allows any mix of read-only and
+read-write branches, as well as insertion and deletion of branches anywhere
+in the fan-out. To maintain Unix semantics, Unionfs handles elimination of
+duplicates, partial-error conditions, and more.
+
+# mount -t unionfs -o branch-option[,union-options[,...]] none MOUNTPOINT
+
+The available branch-option for the mount command is:
+
+ dirs=branch[=ro|=rw][:...]
+
+specifies a separated list of which directories compose the union.
+Directories that come earlier in the list have a higher precedence than
+those which come later. Additionally, read-only or read-write permissions of
+the branch can be specified by appending =ro or =rw (default) to each
+directory.
+
+Syntax:
+
+ dirs=/branch1[=ro|=rw]:/branch2[=ro|=rw]:...:/branchN[=ro|=rw]
+
+Example:
+
+ dirs=/writable_branch=rw:/read-only_branch=ro
+
+
+DYNAMIC BRANCH MANAGEMENT AND REMOUNTS
+======================================
+
+You can remount a union and change its overall mode, or reconfigure the
+branches, as follows.
+
+To downgrade a union from read-write to read-only:
+
+# mount -t unionfs -o remount,ro none MOUNTPOINT
+
+To upgrade a union from read-only to read-write:
+
+# mount -t unionfs -o remount,rw none MOUNTPOINT
+
+To delete a branch /foo, regardless where it is in the current union:
+
+# mount -t unionfs -o remount,del=/foo none MOUNTPOINT
+
+To insert (add) a branch /foo before /bar:
+
+# mount -t unionfs -o remount,add=/bar:/foo none MOUNTPOINT
+
+To insert (add) a branch /foo (with the "rw" mode flag) before /bar:
+
+# mount -t unionfs -o remount,add=/bar:/foo=rw none MOUNTPOINT
+
+To insert (add) a branch /foo (in "rw" mode) at the very beginning (i.e., a
+new highest-priority branch), you can use the above syntax, or use a short
+hand version as follows:
+
+# mount -t unionfs -o remount,add=/foo none MOUNTPOINT
+
+To append a branch to the very end (new lowest-priority branch):
+
+# mount -t unionfs -o remount,add=:/foo none MOUNTPOINT
+
+To append a branch to the very end (new lowest-priority branch), in
+read-only mode:
+
+# mount -t unionfs -o remount,add=:/foo:ro none MOUNTPOINT
+
+Finally, to change the mode of one existing branch, say /foo, from read-only
+to read-write, and change /bar from read-write to read-only:
+
+# mount -t unionfs -o remount,mode=/foo=rw,mode=/bar=ro none MOUNTPOINT
+
+
+CACHE CONSISTENCY
+=================
+
+If you modify any file on any of the lower branches directly, while there is
+a Unionfs 2.0 mounted above any of those branches, you should tell Unionfs
+to purge its caches and re-get the objects. To do that, you have to
+increment the generation number of the superblock using the following
+command:
+
+# mount -t unionfs -o remount,incgen none MOUNTPOINT
+
+Note that the older way of incrementing the generation number using an
+ioctl, is no longer supported in Unionfs 2.0. Ioctls in general are not
+encouraged. Plus, an ioctl is per-file concept, whereas the generation
+number is a per-file-system concept. Worse, such an ioctl requires an open
+file, which then has to be invalidated by the very nature of the generation
+number increase (read: the old generation increase ioctl was pretty racy).
+
+
+For more information, see .
diff --git a/MAINTAINERS b/MAINTAINERS
index 277877a..d694ced 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -3364,6 +3364,15 @@ L: linux-kernel@vger.kernel.org
W: http://www.kernel.dk
S: Maintained
+UNIONFS
+P: Erez Zadok
+M: ezk@cs.sunysb.edu
+P: Josef "Jeff" Sipek
+M: jsipek@cs.sunysb.edu
+L: unionfs@filesystems.org
+W: http://unionfs.filesystems.org
+S: Maintained
+
USB ACM DRIVER
P: Oliver Neukum
M: oliver@neukum.name
diff --git a/fs/Kconfig b/fs/Kconfig
index 3c4886b..ac4dc6d 100644
--- a/fs/Kconfig
+++ b/fs/Kconfig
@@ -1034,6 +1034,41 @@ config CONFIGFS_FS
endmenu
+menu "Layered filesystems"
+
+config ECRYPT_FS
+ tristate "eCrypt filesystem layer support (EXPERIMENTAL)"
+ depends on EXPERIMENTAL && KEYS && CRYPTO && NET
+ help
+ Encrypted filesystem that operates on the VFS layer. See
+ to learn more about
+ eCryptfs. Userspace components are required and can be
+ obtained from .
+
+ To compile this file system support as a module, choose M here: the
+ module will be called ecryptfs.
+
+config UNION_FS
+ tristate "Union file system (EXPERIMENTAL)"
+ depends on EXPERIMENTAL
+ help
+ Unionfs is a stackable unification file system, which appears to
+ merge the contents of several directories (branches), while keeping
+ their physical content separate.
+
+ See for details
+
+config UNION_FS_XATTR
+ bool "Unionfs extended attributes"
+ depends on UNION_FS
+ help
+ Extended attributes are name:value pairs associated with inodes by
+ the kernel or by users (see the attr(5) manual page).
+
+ If unsure, say N.
+
+endmenu
+
menu "Miscellaneous filesystems"
config ADFS_FS
@@ -1086,18 +1121,6 @@ config AFFS_FS
To compile this file system support as a module, choose M here: the
module will be called affs. If unsure, say N.
-config ECRYPT_FS
- tristate "eCrypt filesystem layer support (EXPERIMENTAL)"
- depends on EXPERIMENTAL && KEYS && CRYPTO && NET
- help
- Encrypted filesystem that operates on the VFS layer. See
- to learn more about
- eCryptfs. Userspace components are required and can be
- obtained from .
-
- To compile this file system support as a module, choose M here: the
- module will be called ecryptfs.
-
config HFS_FS
tristate "Apple Macintosh file system support (EXPERIMENTAL)"
depends on BLOCK && EXPERIMENTAL
diff --git a/fs/Makefile b/fs/Makefile
index 9edf411..b490b1a 100644
--- a/fs/Makefile
+++ b/fs/Makefile
@@ -114,3 +114,4 @@ obj-$(CONFIG_HPPFS) += hppfs/
obj-$(CONFIG_DEBUG_FS) += debugfs/
obj-$(CONFIG_OCFS2_FS) += ocfs2/
obj-$(CONFIG_GFS2_FS) += gfs2/
+obj-$(CONFIG_UNION_FS) += unionfs/
diff --git a/fs/drop_caches.c b/fs/drop_caches.c
index 03ea769..6a7aa05 100644
--- a/fs/drop_caches.c
+++ b/fs/drop_caches.c
@@ -3,6 +3,7 @@
*/
#include
+#include
#include
#include
#include
@@ -12,7 +13,7 @@
/* A global variable is a bit ugly, but it keeps the code simple */
int sysctl_drop_caches;
-static void drop_pagecache_sb(struct super_block *sb)
+void drop_pagecache_sb(struct super_block *sb)
{
struct inode *inode;
@@ -24,6 +25,7 @@ static void drop_pagecache_sb(struct super_block *sb)
}
spin_unlock(&inode_lock);
}
+EXPORT_SYMBOL(drop_pagecache_sb);
void drop_pagecache(void)
{
diff --git a/fs/ecryptfs/dentry.c b/fs/ecryptfs/dentry.c
index cb20b96..a8c1686 100644
--- a/fs/ecryptfs/dentry.c
+++ b/fs/ecryptfs/dentry.c
@@ -62,7 +62,7 @@ static int ecryptfs_d_revalidate(struct dentry *dentry, struct nameidata *nd)
struct inode *lower_inode =
ecryptfs_inode_to_lower(dentry->d_inode);
- fsstack_copy_attr_all(dentry->d_inode, lower_inode, NULL);
+ fsstack_copy_attr_all(dentry->d_inode, lower_inode);
}
out:
return rc;
diff --git a/fs/ecryptfs/inode.c b/fs/ecryptfs/inode.c
index 1548be2..d37cc12 100644
--- a/fs/ecryptfs/inode.c
+++ b/fs/ecryptfs/inode.c
@@ -280,7 +280,9 @@ static struct dentry *ecryptfs_lookup(struct inode *dir, struct dentry *dentry,
int rc = 0;
struct dentry *lower_dir_dentry;
struct dentry *lower_dentry;
+ struct dentry *dentry_save;
struct vfsmount *lower_mnt;
+ struct vfsmount *mnt_save;
char *encoded_name;
unsigned int encoded_namelen;
struct ecryptfs_crypt_stat *crypt_stat = NULL;
@@ -308,9 +310,13 @@ static struct dentry *ecryptfs_lookup(struct inode *dir, struct dentry *dentry,
}
ecryptfs_printk(KERN_DEBUG, "encoded_name = [%s]; encoded_namelen "
"= [%d]\n", encoded_name, encoded_namelen);
- lower_dentry = lookup_one_len(encoded_name, lower_dir_dentry,
- encoded_namelen - 1);
+ dentry_save = nd->dentry;
+ mnt_save = nd->mnt;
+ lower_dentry = lookup_one_len_nd(encoded_name, lower_dir_dentry,
+ (encoded_namelen - 1), nd);
kfree(encoded_name);
+ nd->mnt = mnt_save;
+ nd->dentry = dentry_save;
if (IS_ERR(lower_dentry)) {
ecryptfs_printk(KERN_ERR, "ERR from lower_dentry\n");
rc = PTR_ERR(lower_dentry);
@@ -597,9 +603,9 @@ ecryptfs_rename(struct inode *old_dir, struct dentry *old_dentry,
lower_new_dir_dentry->d_inode, lower_new_dentry);
if (rc)
goto out_lock;
- fsstack_copy_attr_all(new_dir, lower_new_dir_dentry->d_inode, NULL);
+ fsstack_copy_attr_all(new_dir, lower_new_dir_dentry->d_inode);
if (new_dir != old_dir)
- fsstack_copy_attr_all(old_dir, lower_old_dir_dentry->d_inode, NULL);
+ fsstack_copy_attr_all(old_dir, lower_old_dir_dentry->d_inode);
out_lock:
unlock_rename(lower_old_dir_dentry, lower_new_dir_dentry);
dput(lower_new_dentry->d_parent);
@@ -892,7 +898,7 @@ static int ecryptfs_setattr(struct dentry *dentry, struct iattr *ia)
}
rc = notify_change(lower_dentry, ia);
out:
- fsstack_copy_attr_all(inode, lower_inode, NULL);
+ fsstack_copy_attr_all(inode, lower_inode);
return rc;
}
diff --git a/fs/ecryptfs/main.c b/fs/ecryptfs/main.c
index fc4a3a2..07c3a58 100644
--- a/fs/ecryptfs/main.c
+++ b/fs/ecryptfs/main.c
@@ -151,7 +151,7 @@ int ecryptfs_interpose(struct dentry *lower_dentry, struct dentry *dentry,
d_add(dentry, inode);
else
d_instantiate(dentry, inode);
- fsstack_copy_attr_all(inode, lower_inode, NULL);
+ fsstack_copy_attr_all(inode, lower_inode);
/* This size will be overwritten for real files w/ headers and
* other metadata */
fsstack_copy_inode_size(inode, lower_inode);
diff --git a/fs/namei.c b/fs/namei.c
index ee60cc4..436e9fa 100644
--- a/fs/namei.c
+++ b/fs/namei.c
@@ -1125,6 +1125,10 @@ static int fastcall do_path_lookup(int dfd, const char *name,
nd->mnt = mntget(fs->rootmnt);
nd->dentry = dget(fs->root);
read_unlock(&fs->lock);
+ } else if (flags & LOOKUP_ONE) {
+ /* nd->mnt and nd->dentry already set, just grab references */
+ mntget(nd->mnt);
+ dget(nd->dentry);
} else if (dfd == AT_FDCWD) {
read_lock(&fs->lock);
nd->mnt = mntget(fs->pwdmnt);
@@ -1293,29 +1297,37 @@ static struct dentry *lookup_hash(struct nameidata *nd)
}
/* SMP-safe */
-struct dentry * lookup_one_len(const char * name, struct dentry * base, int len)
+static inline int __lookup_one_len(const char *name, struct qstr *this, struct dentry *base, int len)
{
unsigned long hash;
- struct qstr this;
unsigned int c;
- this.name = name;
- this.len = len;
+ this->name = name;
+ this->len = len;
if (!len)
- goto access;
+ return -EACCES;
hash = init_name_hash();
while (len--) {
c = *(const unsigned char *)name++;
if (c == '/' || c == '\0')
- goto access;
+ return -EACCES;
hash = partial_name_hash(c, hash);
}
- this.hash = end_name_hash(hash);
+ this->hash = end_name_hash(hash);
+ return 0;
+}
+
+struct dentry *lookup_one_len_nd(const char *name, struct dentry *base,
+ int len, struct nameidata *nd)
+{
+ int err;
+ struct qstr this;
- return __lookup_hash(&this, base, NULL);
-access:
- return ERR_PTR(-EACCES);
+ err = __lookup_one_len(name, &this, base, len);
+ if (err)
+ return ERR_PTR(err);
+ return __lookup_hash(&this, base, nd);
}
/*
@@ -2758,7 +2770,7 @@ EXPORT_SYMBOL(follow_up);
EXPORT_SYMBOL(get_write_access); /* binfmt_aout */
EXPORT_SYMBOL(getname);
EXPORT_SYMBOL(lock_rename);
-EXPORT_SYMBOL(lookup_one_len);
+EXPORT_SYMBOL(lookup_one_len_nd);
EXPORT_SYMBOL(page_follow_link_light);
EXPORT_SYMBOL(page_put_link);
EXPORT_SYMBOL(page_readlink);
diff --git a/fs/stack.c b/fs/stack.c
index 67716f6..56fd0df 100644
--- a/fs/stack.c
+++ b/fs/stack.c
@@ -1,8 +1,20 @@
+/*
+ * Copyright (c) 2003-2007 Erez Zadok
+ * Copyright (c) 2005-2007 Josef 'Jeff' Sipek
+ * Copyright (c) 2003-2007 Stony Brook University
+ * Copyright (c) 2003-2007 The Research Foundation of SUNY
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
#include
#include
#include
-/* does _NOT_ require i_mutex to be held.
+/*
+ * does _NOT_ require i_mutex to be held.
*
* This function cannot be inlined since i_size_{read,write} is rather
* heavy-weight on 32-bit systems
@@ -14,11 +26,11 @@ void fsstack_copy_inode_size(struct inode *dst, const struct inode *src)
}
EXPORT_SYMBOL_GPL(fsstack_copy_inode_size);
-/* copy all attributes; get_nlinks is optional way to override the i_nlink
+/*
+ * copy all attributes; get_nlinks is optional way to override the i_nlink
* copying
*/
-void fsstack_copy_attr_all(struct inode *dest, const struct inode *src,
- int (*get_nlinks)(struct inode *))
+void fsstack_copy_attr_all(struct inode *dest, const struct inode *src)
{
dest->i_mode = src->i_mode;
dest->i_uid = src->i_uid;
@@ -29,14 +41,6 @@ void fsstack_copy_attr_all(struct inode *dest, const struct inode *src,
dest->i_ctime = src->i_ctime;
dest->i_blkbits = src->i_blkbits;
dest->i_flags = src->i_flags;
-
- /*
- * Update the nlinks AFTER updating the above fields, because the
- * get_links callback may depend on them.
- */
- if (!get_nlinks)
- dest->i_nlink = src->i_nlink;
- else
- dest->i_nlink = (*get_nlinks)(dest);
+ dest->i_nlink = src->i_nlink;
}
EXPORT_SYMBOL_GPL(fsstack_copy_attr_all);
diff --git a/fs/unionfs/Makefile b/fs/unionfs/Makefile
new file mode 100644
index 0000000..020b505
--- /dev/null
+++ b/fs/unionfs/Makefile
@@ -0,0 +1,24 @@
+UNIONFS_VERSION="2.1 (for 2.6.21.6)"
+
+EXTRA_CFLAGS += -DUNIONFS_VERSION=\"$(UNIONFS_VERSION)\"
+
+obj-$(CONFIG_UNION_FS) += unionfs.o
+
+unionfs-y := subr.o dentry.o file.o inode.o main.o super.o \
+ rdstate.o copyup.o dirhelper.o rename.o \
+ unlink.o lookup.o commonfops.o dirfops.o sioq.o \
+ mmap.o
+
+unionfs-$(CONFIG_UNION_FS_XATTR) += xattr.o
+
+# If you want debugging output, please uncomment the following line
+# or put your options in a separate file in linux-x.y.z/fs/unionfs/local.mk
+#CONFIG_UNIONFS_DEBUG=y
+
+# Allow users to override debug options in a separate file
+-include fs/unionfs/local.mk
+
+ifeq ($(CONFIG_UNIONFS_DEBUG),y)
+unionfs-y += debug.o
+EXTRA_CFLAGS += -DUNIONFS_DEBUG=1
+endif
diff --git a/fs/unionfs/commonfops.c b/fs/unionfs/commonfops.c
new file mode 100644
index 0000000..d77608e
--- /dev/null
+++ b/fs/unionfs/commonfops.c
@@ -0,0 +1,837 @@
+/*
+ * Copyright (c) 2003-2007 Erez Zadok
+ * Copyright (c) 2003-2006 Charles P. Wright
+ * Copyright (c) 2005-2007 Josef 'Jeff' Sipek
+ * Copyright (c) 2005-2006 Junjiro Okajima
+ * Copyright (c) 2005 Arun M. Krishnakumar
+ * Copyright (c) 2004-2006 David P. Quigley
+ * Copyright (c) 2003-2004 Mohammad Nayyer Zubair
+ * Copyright (c) 2003 Puja Gupta
+ * Copyright (c) 2003 Harikesavan Krishnan
+ * Copyright (c) 2003-2007 Stony Brook University
+ * Copyright (c) 2003-2007 The Research Foundation of SUNY
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include "union.h"
+
+/*
+ * 1) Copyup the file
+ * 2) Rename the file to '.unionfs' - obviously
+ * stolen from NFS's silly rename
+ */
+static int copyup_deleted_file(struct file *file, struct dentry *dentry,
+ int bstart, int bindex)
+{
+ static unsigned int counter;
+ const int i_inosize = sizeof(dentry->d_inode->i_ino) * 2;
+ const int countersize = sizeof(counter) * 2;
+ const int nlen = sizeof(".unionfs") + i_inosize + countersize - 1;
+ char name[nlen + 1];
+ int err;
+ struct dentry *tmp_dentry = NULL;
+ struct dentry *lower_dentry;
+ struct dentry *lower_dir_dentry = NULL;
+
+ lower_dentry = unionfs_lower_dentry_idx(dentry, bstart);
+
+ sprintf(name, ".unionfs%*.*lx",
+ i_inosize, i_inosize, lower_dentry->d_inode->i_ino);
+
+ /*
+ * Loop, looking for an unused temp name to copyup to.
+ *
+ * It's somewhat silly that we look for a free temp tmp name in the
+ * source branch (bstart) instead of the dest branch (bindex), where
+ * the final name will be created. We _will_ catch it if somehow
+ * the name exists in the dest branch, but it'd be nice to catch it
+ * sooner than later.
+ */
+retry:
+ tmp_dentry = NULL;
+ do {
+ char *suffix = name + nlen - countersize;
+
+ dput(tmp_dentry);
+ counter++;
+ sprintf(suffix, "%*.*x", countersize, countersize, counter);
+
+ printk(KERN_DEBUG "unionfs: trying to rename %s to %s\n",
+ dentry->d_name.name, name);
+
+ tmp_dentry = lookup_one_len(name, lower_dentry->d_parent,
+ nlen);
+ if (IS_ERR(tmp_dentry)) {
+ err = PTR_ERR(tmp_dentry);
+ goto out;
+ }
+ /* don't dput here because of do-while condition eval order */
+ } while (tmp_dentry->d_inode != NULL); /* need negative dentry */
+ dput(tmp_dentry);
+
+ err = copyup_named_file(dentry->d_parent->d_inode, file, name, bstart,
+ bindex, file->f_path.dentry->d_inode->i_size);
+ if (err) {
+ if (err == -EEXIST)
+ goto retry;
+ goto out;
+ }
+
+ /* bring it to the same state as an unlinked file */
+ lower_dentry = unionfs_lower_dentry_idx(dentry, dbstart(dentry));
+ if (!unionfs_lower_inode_idx(dentry->d_inode, bindex)) {
+ atomic_inc(&lower_dentry->d_inode->i_count);
+ unionfs_set_lower_inode_idx(dentry->d_inode, bindex,
+ lower_dentry->d_inode);
+ }
+ lower_dir_dentry = lock_parent(lower_dentry);
+ err = vfs_unlink(lower_dir_dentry->d_inode, lower_dentry);
+ unlock_dir(lower_dir_dentry);
+
+out:
+ if (!err)
+ unionfs_check_dentry(dentry);
+ return err;
+}
+
+/*
+ * put all references held by upper struct file and free lower file pointer
+ * array
+ */
+static void cleanup_file(struct file *file)
+{
+ int bindex, bstart, bend;
+ struct file **lower_files;
+ struct file *lower_file;
+ struct super_block *sb = file->f_path.dentry->d_sb;
+
+ lower_files = UNIONFS_F(file)->lower_files;
+ bstart = fbstart(file);
+ bend = fbend(file);
+
+ for (bindex = bstart; bindex <= bend; bindex++) {
+ int i; /* holds (possibly) updated branch index */
+ int old_bid;
+
+ lower_file = unionfs_lower_file_idx(file, bindex);
+ if (!lower_file)
+ continue;
+
+ /*
+ * Find new index of matching branch with an open
+ * file, since branches could have been added or
+ * deleted causing the one with open files to shift.
+ */
+ old_bid = UNIONFS_F(file)->saved_branch_ids[bindex];
+ i = branch_id_to_idx(sb, old_bid);
+ if (i < 0) {
+ printk(KERN_ERR "unionfs: no superblock for "
+ "file %p\n", file);
+ continue;
+ }
+
+ /* decrement count of open files */
+ branchput(sb, i);
+ /*
+ * fput will perform an mntput for us on the correct branch.
+ * Although we're using the file's old branch configuration,
+ * bindex, which is the old index, correctly points to the
+ * right branch in the file's branch list. In other words,
+ * we're going to mntput the correct branch even if branches
+ * have been added/removed.
+ */
+ fput(lower_file);
+ UNIONFS_F(file)->lower_files[bindex] = NULL;
+ UNIONFS_F(file)->saved_branch_ids[bindex] = -1;
+ }
+
+ UNIONFS_F(file)->lower_files = NULL;
+ kfree(lower_files);
+ kfree(UNIONFS_F(file)->saved_branch_ids);
+ /* set to NULL because caller needs to know if to kfree on error */
+ UNIONFS_F(file)->saved_branch_ids = NULL;
+}
+
+/* open all lower files for a given file */
+static int open_all_files(struct file *file)
+{
+ int bindex, bstart, bend, err = 0;
+ struct file *lower_file;
+ struct dentry *lower_dentry;
+ struct dentry *dentry = file->f_path.dentry;
+ struct super_block *sb = dentry->d_sb;
+
+ bstart = dbstart(dentry);
+ bend = dbend(dentry);
+
+ for (bindex = bstart; bindex <= bend; bindex++) {
+ lower_dentry = unionfs_lower_dentry_idx(dentry, bindex);
+ if (!lower_dentry)
+ continue;
+
+ dget(lower_dentry);
+ unionfs_mntget(dentry, bindex);
+ branchget(sb, bindex);
+
+ lower_file =
+ dentry_open(lower_dentry,
+ unionfs_lower_mnt_idx(dentry, bindex),
+ file->f_flags);
+ if (IS_ERR(lower_file)) {
+ err = PTR_ERR(lower_file);
+ goto out;
+ } else
+ unionfs_set_lower_file_idx(file, bindex, lower_file);
+ }
+out:
+ return err;
+}
+
+/* open the highest priority file for a given upper file */
+static int open_highest_file(struct file *file, int willwrite)
+{
+ int bindex, bstart, bend, err = 0;
+ struct file *lower_file;
+ struct dentry *lower_dentry;
+ struct dentry *dentry = file->f_path.dentry;
+ struct inode *parent_inode = dentry->d_parent->d_inode;
+ struct super_block *sb = dentry->d_sb;
+ size_t inode_size = dentry->d_inode->i_size;
+
+ bstart = dbstart(dentry);
+ bend = dbend(dentry);
+
+ lower_dentry = unionfs_lower_dentry(dentry);
+ if (willwrite && IS_WRITE_FLAG(file->f_flags) && is_robranch(dentry)) {
+ for (bindex = bstart - 1; bindex >= 0; bindex--) {
+ err = copyup_file(parent_inode, file, bstart, bindex,
+ inode_size);
+ if (!err)
+ break;
+ }
+ atomic_set(&UNIONFS_F(file)->generation,
+ atomic_read(&UNIONFS_I(dentry->d_inode)->
+ generation));
+ goto out;
+ }
+
+ dget(lower_dentry);
+ unionfs_mntget(dentry, bstart);
+ lower_file = dentry_open(lower_dentry,
+ unionfs_lower_mnt_idx(dentry, bstart),
+ file->f_flags);
+ if (IS_ERR(lower_file)) {
+ err = PTR_ERR(lower_file);
+ goto out;
+ }
+ branchget(sb, bstart);
+ unionfs_set_lower_file(file, lower_file);
+ /* Fix up the position. */
+ lower_file->f_pos = file->f_pos;
+
+ memcpy(&lower_file->f_ra, &file->f_ra, sizeof(struct file_ra_state));
+out:
+ return err;
+}
+
+/* perform a delayed copyup of a read-write file on a read-only branch */
+static int do_delayed_copyup(struct file *file)
+{
+ int bindex, bstart, bend, err = 0;
+ struct dentry *dentry = file->f_path.dentry;
+ struct inode *parent_inode = dentry->d_parent->d_inode;
+ loff_t inode_size = dentry->d_inode->i_size;
+
+ bstart = fbstart(file);
+ bend = fbend(file);
+
+ BUG_ON(!S_ISREG(dentry->d_inode->i_mode));
+
+ unionfs_check_file(file);
+ unionfs_check_dentry(dentry);
+ for (bindex = bstart - 1; bindex >= 0; bindex--) {
+ if (!d_deleted(dentry))
+ err = copyup_file(parent_inode, file, bstart,
+ bindex, inode_size);
+ else
+ err = copyup_deleted_file(file, dentry, bstart,
+ bindex);
+
+ if (!err)
+ break;
+ }
+ if (err || (bstart <= fbstart(file)))
+ goto out;
+ bend = fbend(file);
+ for (bindex = bstart; bindex <= bend; bindex++) {
+ if (unionfs_lower_file_idx(file, bindex)) {
+ branchput(dentry->d_sb, bindex);
+ fput(unionfs_lower_file_idx(file, bindex));
+ unionfs_set_lower_file_idx(file, bindex, NULL);
+ }
+ if (unionfs_lower_mnt_idx(dentry, bindex)) {
+ unionfs_mntput(dentry, bindex);
+ unionfs_set_lower_mnt_idx(dentry, bindex, NULL);
+ }
+ if (unionfs_lower_dentry_idx(dentry, bindex)) {
+ BUG_ON(!dentry->d_inode);
+ iput(unionfs_lower_inode_idx(dentry->d_inode, bindex));
+ unionfs_set_lower_inode_idx(dentry->d_inode, bindex,
+ NULL);
+ dput(unionfs_lower_dentry_idx(dentry, bindex));
+ unionfs_set_lower_dentry_idx(dentry, bindex, NULL);
+ }
+ }
+ /* for reg file, we only open it "once" */
+ fbend(file) = fbstart(file);
+ set_dbend(dentry, dbstart(dentry));
+ ibend(dentry->d_inode) = ibstart(dentry->d_inode);
+
+out:
+ unionfs_check_file(file);
+ unionfs_check_dentry(dentry);
+ return err;
+}
+
+/*
+ * Revalidate the struct file
+ * @file: file to revalidate
+ * @willwrite: 1 if caller may cause changes to the file; 0 otherwise.
+ */
+int unionfs_file_revalidate(struct file *file, int willwrite)
+{
+ struct super_block *sb;
+ struct dentry *dentry;
+ int sbgen, fgen, dgen;
+ int bstart, bend;
+ int size;
+ int err = 0;
+
+ dentry = file->f_path.dentry;
+ unionfs_lock_dentry(dentry);
+ sb = dentry->d_sb;
+
+ /*
+ * First revalidate the dentry inside struct file,
+ * but not unhashed dentries.
+ */
+ if (!d_deleted(dentry) &&
+ !__unionfs_d_revalidate_chain(dentry, NULL, willwrite)) {
+ err = -ESTALE;
+ goto out_nofree;
+ }
+
+ sbgen = atomic_read(&UNIONFS_SB(sb)->generation);
+ dgen = atomic_read(&UNIONFS_D(dentry)->generation);
+ fgen = atomic_read(&UNIONFS_F(file)->generation);
+
+ BUG_ON(sbgen > dgen);
+
+ /*
+ * There are two cases we are interested in. The first is if the
+ * generation is lower than the super-block. The second is if
+ * someone has copied up this file from underneath us, we also need
+ * to refresh things.
+ */
+ if (!d_deleted(dentry) &&
+ (sbgen > fgen || dbstart(dentry) != fbstart(file))) {
+ int orig_brid = /* save orig branch ID */
+ UNIONFS_F(file)->saved_branch_ids[fbstart(file)];
+
+ /* First we throw out the existing files. */
+ cleanup_file(file);
+
+ /* Now we reopen the file(s) as in unionfs_open. */
+ bstart = fbstart(file) = dbstart(dentry);
+ bend = fbend(file) = dbend(dentry);
+
+ size = sizeof(struct file *) * sbmax(sb);
+ UNIONFS_F(file)->lower_files = kzalloc(size, GFP_KERNEL);
+ if (!UNIONFS_F(file)->lower_files) {
+ err = -ENOMEM;
+ goto out;
+ }
+ size = sizeof(int) * sbmax(sb);
+ UNIONFS_F(file)->saved_branch_ids = kzalloc(size, GFP_KERNEL);
+ if (!UNIONFS_F(file)->saved_branch_ids) {
+ err = -ENOMEM;
+ goto out;
+ }
+
+ if (S_ISDIR(dentry->d_inode->i_mode)) {
+ /* We need to open all the files. */
+ err = open_all_files(file);
+ if (err)
+ goto out;
+ } else {
+ int new_brid;
+ /* We only open the highest priority branch. */
+ err = open_highest_file(file, willwrite);
+ if (err)
+ goto out;
+ new_brid = UNIONFS_F(file)->
+ saved_branch_ids[fbstart(file)];
+ if (new_brid != orig_brid && sbgen > fgen) {
+ /*
+ * If we re-opened the file on a different
+ * branch than the original one, and this
+ * was due to a new branch inserted, then
+ * update the mnt counts of the old and new
+ * branches accordingly.
+ */
+ unionfs_mntget(dentry, bstart); /* new branch */
+ unionfs_mntput(sb->s_root, /* orig branch */
+ branch_id_to_idx(sb, orig_brid));
+ }
+ }
+ atomic_set(&UNIONFS_F(file)->generation,
+ atomic_read(&UNIONFS_I(dentry->d_inode)->
+ generation));
+ }
+
+ /* Copyup on the first write to a file on a readonly branch. */
+ if (willwrite && IS_WRITE_FLAG(file->f_flags) &&
+ !IS_WRITE_FLAG(unionfs_lower_file(file)->f_flags) &&
+ is_robranch(dentry)) {
+ printk(KERN_DEBUG "unionfs: do delay copyup of \"%s\"\n",
+ dentry->d_name.name);
+ err = do_delayed_copyup(file);
+ }
+
+out:
+ if (err) {
+ kfree(UNIONFS_F(file)->lower_files);
+ kfree(UNIONFS_F(file)->saved_branch_ids);
+ }
+out_nofree:
+ if (!err)
+ unionfs_check_file(file);
+ unionfs_unlock_dentry(dentry);
+ return err;
+}
+
+/* unionfs_open helper function: open a directory */
+static int __open_dir(struct inode *inode, struct file *file)
+{
+ struct dentry *lower_dentry;
+ struct file *lower_file;
+ int bindex, bstart, bend;
+
+ bstart = fbstart(file) = dbstart(file->f_path.dentry);
+ bend = fbend(file) = dbend(file->f_path.dentry);
+
+ for (bindex = bstart; bindex <= bend; bindex++) {
+ lower_dentry =
+ unionfs_lower_dentry_idx(file->f_path.dentry, bindex);
+ if (!lower_dentry)
+ continue;
+
+ dget(lower_dentry);
+ unionfs_mntget(file->f_path.dentry, bindex);
+ lower_file = dentry_open(lower_dentry,
+ unionfs_lower_mnt_idx(file->f_path.dentry,
+ bindex),
+ file->f_flags);
+ if (IS_ERR(lower_file))
+ return PTR_ERR(lower_file);
+
+ unionfs_set_lower_file_idx(file, bindex, lower_file);
+
+ /*
+ * The branchget goes after the open, because otherwise
+ * we would miss the reference on release.
+ */
+ branchget(inode->i_sb, bindex);
+ }
+
+ return 0;
+}
+
+/* unionfs_open helper function: open a file */
+static int __open_file(struct inode *inode, struct file *file)
+{
+ struct dentry *lower_dentry;
+ struct file *lower_file;
+ int lower_flags;
+ int bindex, bstart, bend;
+
+ lower_dentry = unionfs_lower_dentry(file->f_path.dentry);
+ lower_flags = file->f_flags;
+
+ bstart = fbstart(file) = dbstart(file->f_path.dentry);
+ bend = fbend(file) = dbend(file->f_path.dentry);
+
+ /*
+ * check for the permission for lower file. If the error is
+ * COPYUP_ERR, copyup the file.
+ */
+ if (lower_dentry->d_inode && is_robranch(file->f_path.dentry)) {
+ /*
+ * if the open will change the file, copy it up otherwise
+ * defer it.
+ */
+ if (lower_flags & O_TRUNC) {
+ int size = 0;
+ int err = -EROFS;
+
+ /* copyup the file */
+ for (bindex = bstart - 1; bindex >= 0; bindex--) {
+ err = copyup_file(
+ file->f_path.dentry->d_parent->d_inode,
+ file, bstart, bindex, size);
+ if (!err)
+ break;
+ }
+ return err;
+ } else
+ lower_flags &= ~(OPEN_WRITE_FLAGS);
+ }
+
+ dget(lower_dentry);
+
+ /*
+ * dentry_open will decrement mnt refcnt if err.
+ * otherwise fput() will do an mntput() for us upon file close.
+ */
+ unionfs_mntget(file->f_path.dentry, bstart);
+ lower_file =
+ dentry_open(lower_dentry,
+ unionfs_lower_mnt_idx(file->f_path.dentry, bstart),
+ lower_flags);
+ if (IS_ERR(lower_file))
+ return PTR_ERR(lower_file);
+
+ unionfs_set_lower_file(file, lower_file);
+ branchget(inode->i_sb, bstart);
+
+ return 0;
+}
+
+int unionfs_open(struct inode *inode, struct file *file)
+{
+ int err = 0;
+ struct file *lower_file = NULL;
+ struct dentry *dentry = NULL;
+ int bindex = 0, bstart = 0, bend = 0;
+ int size;
+
+ unionfs_read_lock(inode->i_sb);
+
+ file->private_data =
+ kzalloc(sizeof(struct unionfs_file_info), GFP_KERNEL);
+ if (!UNIONFS_F(file)) {
+ err = -ENOMEM;
+ goto out_nofree;
+ }
+ fbstart(file) = -1;
+ fbend(file) = -1;
+ atomic_set(&UNIONFS_F(file)->generation,
+ atomic_read(&UNIONFS_I(inode)->generation));
+
+ size = sizeof(struct file *) * sbmax(inode->i_sb);
+ UNIONFS_F(file)->lower_files = kzalloc(size, GFP_KERNEL);
+ if (!UNIONFS_F(file)->lower_files) {
+ err = -ENOMEM;
+ goto out;
+ }
+ size = sizeof(int) * sbmax(inode->i_sb);
+ UNIONFS_F(file)->saved_branch_ids = kzalloc(size, GFP_KERNEL);
+ if (!UNIONFS_F(file)->saved_branch_ids) {
+ err = -ENOMEM;
+ goto out;
+ }
+
+ dentry = file->f_path.dentry;
+ unionfs_lock_dentry(dentry);
+
+ bstart = fbstart(file) = dbstart(dentry);
+ bend = fbend(file) = dbend(dentry);
+
+ /* increment, so that we can flush appropriately */
+ atomic_inc(&UNIONFS_I(dentry->d_inode)->totalopens);
+
+ /*
+ * open all directories and make the unionfs file struct point to
+ * these lower file structs
+ */
+ if (S_ISDIR(inode->i_mode))
+ err = __open_dir(inode, file); /* open a dir */
+ else
+ err = __open_file(inode, file); /* open a file */
+
+ /* freeing the allocated resources, and fput the opened files */
+ if (err) {
+ atomic_dec(&UNIONFS_I(dentry->d_inode)->totalopens);
+ for (bindex = bstart; bindex <= bend; bindex++) {
+ lower_file = unionfs_lower_file_idx(file, bindex);
+ if (!lower_file)
+ continue;
+
+ branchput(file->f_path.dentry->d_sb, bindex);
+ /* fput calls dput for lower_dentry */
+ fput(lower_file);
+ }
+ }
+
+ unionfs_unlock_dentry(dentry);
+
+out:
+ if (err) {
+ kfree(UNIONFS_F(file)->lower_files);
+ kfree(UNIONFS_F(file)->saved_branch_ids);
+ kfree(UNIONFS_F(file));
+ }
+out_nofree:
+ unionfs_read_unlock(inode->i_sb);
+ unionfs_check_inode(inode);
+ if (!err) {
+ unionfs_check_file(file);
+ unionfs_check_dentry(file->f_path.dentry->d_parent);
+ }
+ return err;
+}
+
+/*
+ * release all lower object references & free the file info structure
+ *
+ * No need to grab sb info's rwsem.
+ */
+int unionfs_file_release(struct inode *inode, struct file *file)
+{
+ struct file *lower_file = NULL;
+ struct unionfs_file_info *fileinfo;
+ struct unionfs_inode_info *inodeinfo;
+ struct super_block *sb = inode->i_sb;
+ int bindex, bstart, bend;
+ int fgen, err = 0;
+
+ unionfs_read_lock(sb);
+ /*
+ * Yes, we have to revalidate this file even if it's being released.
+ * This is important for open-but-unlinked files, as well as mmap
+ * support.
+ */
+ if ((err = unionfs_file_revalidate(file, 1)))
+ goto out;
+ unionfs_check_file(file);
+ fileinfo = UNIONFS_F(file);
+ BUG_ON(file->f_path.dentry->d_inode != inode);
+ inodeinfo = UNIONFS_I(inode);
+
+ /* fput all the lower files */
+ fgen = atomic_read(&fileinfo->generation);
+ bstart = fbstart(file);
+ bend = fbend(file);
+
+ for (bindex = bstart; bindex <= bend; bindex++) {
+ lower_file = unionfs_lower_file_idx(file, bindex);
+
+ if (lower_file) {
+ fput(lower_file);
+ branchput(sb, bindex);
+ }
+ }
+ kfree(fileinfo->lower_files);
+ kfree(fileinfo->saved_branch_ids);
+
+ if (fileinfo->rdstate) {
+ fileinfo->rdstate->access = jiffies;
+ printk(KERN_DEBUG "unionfs: saving rdstate with cookie "
+ "%u [%d.%lld]\n",
+ fileinfo->rdstate->cookie,
+ fileinfo->rdstate->bindex,
+ (long long)fileinfo->rdstate->dirpos);
+ spin_lock(&inodeinfo->rdlock);
+ inodeinfo->rdcount++;
+ list_add_tail(&fileinfo->rdstate->cache,
+ &inodeinfo->readdircache);
+ mark_inode_dirty(inode);
+ spin_unlock(&inodeinfo->rdlock);
+ fileinfo->rdstate = NULL;
+ }
+ kfree(fileinfo);
+
+out:
+ unionfs_read_unlock(sb);
+ return err;
+}
+
+/* pass the ioctl to the lower fs */
+static long do_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
+{
+ struct file *lower_file;
+ int err;
+
+ lower_file = unionfs_lower_file(file);
+
+ err = security_file_ioctl(lower_file, cmd, arg);
+ if (err)
+ goto out;
+
+ err = -ENOTTY;
+ if (!lower_file || !lower_file->f_op)
+ goto out;
+ if (lower_file->f_op->unlocked_ioctl) {
+ err = lower_file->f_op->unlocked_ioctl(lower_file, cmd, arg);
+ } else if (lower_file->f_op->ioctl) {
+ lock_kernel();
+ err = lower_file->f_op->ioctl(lower_file->f_path.dentry->d_inode,
+ lower_file, cmd, arg);
+ unlock_kernel();
+ }
+
+out:
+ return err;
+}
+
+/*
+ * return to user-space the branch indices containing the file in question
+ *
+ * We use fd_set and therefore we are limited to the number of the branches
+ * to FD_SETSIZE, which is currently 1024 - plenty for most people
+ */
+static int unionfs_ioctl_queryfile(struct file *file, unsigned int cmd,
+ unsigned long arg)
+{
+ int err = 0;
+ fd_set branchlist;
+ int bstart = 0, bend = 0, bindex = 0;
+ int orig_bstart, orig_bend;
+ struct dentry *dentry, *lower_dentry;
+ struct vfsmount *mnt;
+
+ dentry = file->f_path.dentry;
+ unionfs_lock_dentry(dentry);
+ orig_bstart = dbstart(dentry);
+ orig_bend = dbend(dentry);
+ if ((err = unionfs_partial_lookup(dentry)))
+ goto out;
+ bstart = dbstart(dentry);
+ bend = dbend(dentry);
+
+ FD_ZERO(&branchlist);
+
+ for (bindex = bstart; bindex <= bend; bindex++) {
+ lower_dentry = unionfs_lower_dentry_idx(dentry, bindex);
+ if (!lower_dentry)
+ continue;
+ if (lower_dentry->d_inode)
+ FD_SET(bindex, &branchlist);
+ /* purge any lower objects after partial_lookup */
+ if (bindex < orig_bstart || bindex > orig_bend) {
+ dput(lower_dentry);
+ unionfs_set_lower_dentry_idx(dentry, bindex, NULL);
+ iput(unionfs_lower_inode_idx(dentry->d_inode, bindex));
+ unionfs_set_lower_inode_idx(dentry->d_inode, bindex,
+ NULL);
+ mnt = unionfs_lower_mnt_idx(dentry, bindex);
+ if (!mnt)
+ continue;
+ unionfs_mntput(dentry, bindex);
+ unionfs_set_lower_mnt_idx(dentry, bindex, NULL);
+ }
+ }
+ /* restore original dentry's offsets */
+ set_dbstart(dentry, orig_bstart);
+ set_dbend(dentry, orig_bend);
+ ibstart(dentry->d_inode) = orig_bstart;
+ ibend(dentry->d_inode) = orig_bend;
+
+ err = copy_to_user((void __user *)arg, &branchlist, sizeof(fd_set));
+ if (err)
+ err = -EFAULT;
+
+out:
+ unionfs_unlock_dentry(dentry);
+ return err < 0 ? err : bend;
+}
+
+long unionfs_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
+{
+ long err;
+
+ unionfs_read_lock(file->f_path.dentry->d_sb);
+
+ if ((err = unionfs_file_revalidate(file, 1)))
+ goto out;
+
+ /* check if asked for local commands */
+ switch (cmd) {
+ case UNIONFS_IOCTL_INCGEN:
+ /* Increment the superblock generation count */
+ printk("unionfs: incgen ioctl deprecated; "
+ "use \"-o remount,incgen\"\n");
+ err = -ENOSYS;
+ break;
+
+ case UNIONFS_IOCTL_QUERYFILE:
+ /* Return list of branches containing the given file */
+ err = unionfs_ioctl_queryfile(file, cmd, arg);
+ break;
+
+ default:
+ /* pass the ioctl down */
+ err = do_ioctl(file, cmd, arg);
+ break;
+ }
+
+out:
+ unionfs_read_unlock(file->f_path.dentry->d_sb);
+ unionfs_check_file(file);
+ return err;
+}
+
+int unionfs_flush(struct file *file, fl_owner_t id)
+{
+ int err = 0;
+ struct file *lower_file = NULL;
+ struct dentry *dentry = file->f_path.dentry;
+ int bindex, bstart, bend;
+
+ unionfs_read_lock(dentry->d_sb);
+
+ if ((err = unionfs_file_revalidate(file, 1)))
+ goto out;
+ unionfs_check_file(file);
+
+ if (!atomic_dec_and_test(&UNIONFS_I(dentry->d_inode)->totalopens))
+ goto out;
+
+ unionfs_lock_dentry(dentry);
+
+ bstart = fbstart(file);
+ bend = fbend(file);
+ for (bindex = bstart; bindex <= bend; bindex++) {
+ lower_file = unionfs_lower_file_idx(file, bindex);
+
+ if (lower_file && lower_file->f_op &&
+ lower_file->f_op->flush) {
+ err = lower_file->f_op->flush(lower_file, id);
+ if (err)
+ goto out_lock;
+
+ /* if there are no more refs to the dentry, dput it */
+ if (d_deleted(dentry)) {
+ dput(unionfs_lower_dentry_idx(dentry, bindex));
+ unionfs_set_lower_dentry_idx(dentry, bindex,
+ NULL);
+ }
+ }
+
+ }
+
+ /* on success, update our times */
+ unionfs_copy_attr_times(dentry->d_inode);
+ /* parent time could have changed too (async) */
+ unionfs_copy_attr_times(dentry->d_parent->d_inode);
+
+out_lock:
+ unionfs_unlock_dentry(dentry);
+out:
+ unionfs_read_unlock(dentry->d_sb);
+ unionfs_check_file(file);
+ return err;
+}
diff --git a/fs/unionfs/copyup.c b/fs/unionfs/copyup.c
new file mode 100644
index 0000000..fb7a2de
--- /dev/null
+++ b/fs/unionfs/copyup.c
@@ -0,0 +1,880 @@
+/*
+ * Copyright (c) 2003-2007 Erez Zadok
+ * Copyright (c) 2003-2006 Charles P. Wright
+ * Copyright (c) 2005-2007 Josef 'Jeff' Sipek
+ * Copyright (c) 2005-2006 Junjiro Okajima
+ * Copyright (c) 2005 Arun M. Krishnakumar
+ * Copyright (c) 2004-2006 David P. Quigley
+ * Copyright (c) 2003-2004 Mohammad Nayyer Zubair
+ * Copyright (c) 2003 Puja Gupta
+ * Copyright (c) 2003 Harikesavan Krishnan
+ * Copyright (c) 2003-2007 Stony Brook University
+ * Copyright (c) 2003-2007 The Research Foundation of SUNY
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include "union.h"
+
+/*
+ * For detailed explanation of copyup see:
+ * Documentation/filesystems/unionfs/concepts.txt
+ */
+
+#ifdef CONFIG_UNION_FS_XATTR
+/* copyup all extended attrs for a given dentry */
+static int copyup_xattrs(struct dentry *old_lower_dentry,
+ struct dentry *new_lower_dentry)
+{
+ int err = 0;
+ ssize_t list_size = -1;
+ char *name_list = NULL;
+ char *attr_value = NULL;
+ char *name_list_orig = NULL;
+
+ /* query the actual size of the xattr list */
+ list_size = vfs_listxattr(old_lower_dentry, NULL, 0);
+ if (list_size <= 0) {
+ err = list_size;
+ goto out;
+ }
+
+ /* allocate space for the actual list */
+ name_list = unionfs_xattr_alloc(list_size + 1, XATTR_LIST_MAX);
+ if (!name_list || IS_ERR(name_list)) {
+ err = PTR_ERR(name_list);
+ goto out;
+ }
+
+ name_list_orig = name_list; /* save for kfree at end */
+
+ /* now get the actual xattr list of the source file */
+ list_size = vfs_listxattr(old_lower_dentry, name_list, list_size);
+ if (list_size <= 0) {
+ err = list_size;
+ goto out;
+ }
+
+ /* allocate space to hold each xattr's value */
+ attr_value = unionfs_xattr_alloc(XATTR_SIZE_MAX, XATTR_SIZE_MAX);
+ if (!attr_value || IS_ERR(attr_value)) {
+ err = PTR_ERR(name_list);
+ goto out;
+ }
+
+ /* in a loop, get and set each xattr from src to dst file */
+ while (*name_list) {
+ ssize_t size;
+
+ /* Lock here since vfs_getxattr doesn't lock for us */
+ mutex_lock(&old_lower_dentry->d_inode->i_mutex);
+ size = vfs_getxattr(old_lower_dentry, name_list,
+ attr_value, XATTR_SIZE_MAX);
+ mutex_unlock(&old_lower_dentry->d_inode->i_mutex);
+ if (size < 0) {
+ err = size;
+ goto out;
+ }
+ if (size > XATTR_SIZE_MAX) {
+ err = -E2BIG;
+ goto out;
+ }
+ /* Don't lock here since vfs_setxattr does it for us. */
+ err = vfs_setxattr(new_lower_dentry, name_list, attr_value,
+ size, 0);
+ if (err < 0)
+ goto out;
+ name_list += strlen(name_list) + 1;
+ }
+out:
+ if (name_list_orig)
+ kfree(name_list_orig);
+ if (attr_value)
+ kfree(attr_value);
+ /*
+ * Ignore if xattr isn't supported. Also ignore EPERM because that
+ * requires CAP_SYS_ADMIN for security.* xattrs, but copyup happens
+ * as normal users.
+ */
+ if (err == -ENOTSUPP || err == -EOPNOTSUPP || err == -EPERM)
+ err = 0;
+ return err;
+}
+#endif /* CONFIG_UNION_FS_XATTR */
+
+/*
+ * Determine the mode based on the copyup flags, and the existing dentry.
+ *
+ * Handle file systems which may not support certain options. For example
+ * jffs2 doesn't allow one to chmod a symlink. So we ignore such harmless
+ * errors, rather than propagating them up, which results in copyup errors
+ * and errors returned back to users.
+ */
+static int copyup_permissions(struct super_block *sb,
+ struct dentry *old_lower_dentry,
+ struct dentry *new_lower_dentry)
+{
+ struct inode *i = old_lower_dentry->d_inode;
+ struct iattr newattrs;
+ int err;
+
+ newattrs.ia_atime = i->i_atime;
+ newattrs.ia_mtime = i->i_mtime;
+ newattrs.ia_ctime = i->i_ctime;
+ newattrs.ia_gid = i->i_gid;
+ newattrs.ia_uid = i->i_uid;
+ newattrs.ia_valid = ATTR_CTIME | ATTR_ATIME | ATTR_MTIME |
+ ATTR_ATIME_SET | ATTR_MTIME_SET | ATTR_FORCE |
+ ATTR_GID | ATTR_UID;
+ err = notify_change(new_lower_dentry, &newattrs);
+ if (err)
+ goto out;
+
+ /* now try to change the mode and ignore EOPNOTSUPP on symlinks */
+ newattrs.ia_mode = i->i_mode;
+ newattrs.ia_valid = ATTR_MODE | ATTR_FORCE;
+ err = notify_change(new_lower_dentry, &newattrs);
+ if (err == -EOPNOTSUPP &&
+ S_ISLNK(new_lower_dentry->d_inode->i_mode)) {
+ printk(KERN_WARNING
+ "unionfs: changing \"%s\" symlink mode unsupported\n",
+ new_lower_dentry->d_name.name);
+ err = 0;
+ }
+
+out:
+ return err;
+}
+
+/*
+ * create the new device/file/directory - use copyup_permission to copyup
+ * times, and mode
+ *
+ * if the object being copied up is a regular file, the file is only created,
+ * the contents have to be copied up separately
+ */
+static int __copyup_ndentry(struct dentry *old_lower_dentry,
+ struct dentry *new_lower_dentry,
+ struct dentry *new_lower_parent_dentry,
+ char *symbuf)
+{
+ int err = 0;
+ umode_t old_mode = old_lower_dentry->d_inode->i_mode;
+ struct sioq_args args;
+
+ if (S_ISDIR(old_mode)) {
+ args.mkdir.parent = new_lower_parent_dentry->d_inode;
+ args.mkdir.dentry = new_lower_dentry;
+ args.mkdir.mode = old_mode;
+
+ run_sioq(__unionfs_mkdir, &args);
+ err = args.err;
+ } else if (S_ISLNK(old_mode)) {
+ args.symlink.parent = new_lower_parent_dentry->d_inode;
+ args.symlink.dentry = new_lower_dentry;
+ args.symlink.symbuf = symbuf;
+ args.symlink.mode = old_mode;
+
+ run_sioq(__unionfs_symlink, &args);
+ err = args.err;
+ } else if (S_ISBLK(old_mode) || S_ISCHR(old_mode) ||
+ S_ISFIFO(old_mode) || S_ISSOCK(old_mode)) {
+ args.mknod.parent = new_lower_parent_dentry->d_inode;
+ args.mknod.dentry = new_lower_dentry;
+ args.mknod.mode = old_mode;
+ args.mknod.dev = old_lower_dentry->d_inode->i_rdev;
+
+ run_sioq(__unionfs_mknod, &args);
+ err = args.err;
+ } else if (S_ISREG(old_mode)) {
+ args.create.parent = new_lower_parent_dentry->d_inode;
+ args.create.dentry = new_lower_dentry;
+ args.create.mode = old_mode;
+ args.create.nd = NULL;
+
+ run_sioq(__unionfs_create, &args);
+ err = args.err;
+ } else {
+ printk(KERN_ERR "unionfs: unknown inode type %d\n",
+ old_mode);
+ BUG();
+ }
+
+ return err;
+}
+
+static int __copyup_reg_data(struct dentry *dentry,
+ struct dentry *new_lower_dentry, int new_bindex,
+ struct dentry *old_lower_dentry, int old_bindex,
+ struct file **copyup_file, loff_t len)
+{
+ struct super_block *sb = dentry->d_sb;
+ struct file *input_file;
+ struct file *output_file;
+ struct vfsmount *output_mnt;
+ mm_segment_t old_fs;
+ char *buf = NULL;
+ ssize_t read_bytes, write_bytes;
+ loff_t size;
+ int err = 0;
+
+ /* open old file */
+ unionfs_mntget(dentry, old_bindex);
+ branchget(sb, old_bindex);
+ /* dentry_open calls dput and mntput if it returns an error */
+ input_file = dentry_open(old_lower_dentry,
+ unionfs_lower_mnt_idx(dentry, old_bindex),
+ O_RDONLY | O_LARGEFILE);
+ if (IS_ERR(input_file)) {
+ dput(old_lower_dentry);
+ err = PTR_ERR(input_file);
+ goto out;
+ }
+ if (!input_file->f_op || !input_file->f_op->read) {
+ err = -EINVAL;
+ goto out_close_in;
+ }
+
+ /* open new file */
+ dget(new_lower_dentry);
+ output_mnt = unionfs_mntget(sb->s_root, new_bindex);
+ branchget(sb, new_bindex);
+ output_file = dentry_open(new_lower_dentry, output_mnt,
+ O_RDWR | O_LARGEFILE);
+ if (IS_ERR(output_file)) {
+ err = PTR_ERR(output_file);
+ goto out_close_in2;
+ }
+ if (!output_file->f_op || !output_file->f_op->write) {
+ err = -EINVAL;
+ goto out_close_out;
+ }
+
+ /* allocating a buffer */
+ buf = kmalloc(PAGE_SIZE, GFP_KERNEL);
+ if (!buf) {
+ err = -ENOMEM;
+ goto out_close_out;
+ }
+
+ input_file->f_pos = 0;
+ output_file->f_pos = 0;
+
+ old_fs = get_fs();
+ set_fs(KERNEL_DS);
+
+ size = len;
+ err = 0;
+ do {
+ if (len >= PAGE_SIZE)
+ size = PAGE_SIZE;
+ else if ((len < PAGE_SIZE) && (len > 0))
+ size = len;
+
+ len -= PAGE_SIZE;
+
+ read_bytes =
+ input_file->f_op->read(input_file,
+ (char __user *)buf, size,
+ &input_file->f_pos);
+ if (read_bytes <= 0) {
+ err = read_bytes;
+ break;
+ }
+
+ write_bytes =
+ output_file->f_op->write(output_file,
+ (char __user *)buf,
+ read_bytes,
+ &output_file->f_pos);
+ if ((write_bytes < 0) || (write_bytes < read_bytes)) {
+ err = write_bytes;
+ break;
+ }
+ } while ((read_bytes > 0) && (len > 0));
+
+ set_fs(old_fs);
+
+ kfree(buf);
+
+ if (!err)
+ err = output_file->f_op->fsync(output_file,
+ new_lower_dentry, 0);
+
+ if (err)
+ goto out_close_out;
+
+ if (copyup_file) {
+ *copyup_file = output_file;
+ goto out_close_in;
+ }
+
+out_close_out:
+ fput(output_file);
+
+out_close_in2:
+ branchput(sb, new_bindex);
+
+out_close_in:
+ fput(input_file);
+
+out:
+ branchput(sb, old_bindex);
+
+ return err;
+}
+
+/*
+ * dput the lower references for old and new dentry & clear a lower dentry
+ * pointer
+ */
+static void __clear(struct dentry *dentry, struct dentry *old_lower_dentry,
+ int old_bstart, int old_bend,
+ struct dentry *new_lower_dentry, int new_bindex)
+{
+ /* get rid of the lower dentry and all its traces */
+ unionfs_set_lower_dentry_idx(dentry, new_bindex, NULL);
+ set_dbstart(dentry, old_bstart);
+ set_dbend(dentry, old_bend);
+
+ dput(new_lower_dentry);
+ dput(old_lower_dentry);
+}
+
+/*
+ * Copy up a dentry to a file of specified name.
+ *
+ * @dir: used to pull the ->i_sb to access other branches
+ * @dentry: the non-negative dentry whose lower_inode we should copy
+ * @bstart: the branch of the lower_inode to copy from
+ * @new_bindex: the branch to create the new file in
+ * @name: the name of the file to create
+ * @namelen: length of @name
+ * @copyup_file: the "struct file" to return (optional)
+ * @len: how many bytes to copy-up?
+ */
+int copyup_dentry(struct inode *dir, struct dentry *dentry, int bstart,
+ int new_bindex, const char *name, int namelen,
+ struct file **copyup_file, loff_t len)
+{
+ struct dentry *new_lower_dentry;
+ struct dentry *old_lower_dentry = NULL;
+ struct super_block *sb;
+ int err = 0;
+ int old_bindex;
+ int old_bstart;
+ int old_bend;
+ struct dentry *new_lower_parent_dentry = NULL;
+ mm_segment_t oldfs;
+ char *symbuf = NULL;
+
+ verify_locked(dentry);
+
+ old_bindex = bstart;
+ old_bstart = dbstart(dentry);
+ old_bend = dbend(dentry);
+
+ BUG_ON(new_bindex < 0);
+ BUG_ON(new_bindex >= old_bindex);
+
+ sb = dir->i_sb;
+
+ if ((err = is_robranch_super(sb, new_bindex)))
+ goto out;
+
+ /* Create the directory structure above this dentry. */
+ new_lower_dentry = create_parents(dir, dentry, name, new_bindex);
+ if (IS_ERR(new_lower_dentry)) {
+ err = PTR_ERR(new_lower_dentry);
+ goto out;
+ }
+
+ old_lower_dentry = unionfs_lower_dentry_idx(dentry, old_bindex);
+ /* we conditionally dput this old_lower_dentry at end of function */
+ dget(old_lower_dentry);
+
+ /* For symlinks, we must read the link before we lock the directory. */
+ if (S_ISLNK(old_lower_dentry->d_inode->i_mode)) {
+
+ symbuf = kmalloc(PATH_MAX, GFP_KERNEL);
+ if (!symbuf) {
+ __clear(dentry, old_lower_dentry,
+ old_bstart, old_bend,
+ new_lower_dentry, new_bindex);
+ err = -ENOMEM;
+ goto out_free;
+ }
+
+ oldfs = get_fs();
+ set_fs(KERNEL_DS);
+ err = old_lower_dentry->d_inode->i_op->readlink(
+ old_lower_dentry,
+ (char __user *)symbuf,
+ PATH_MAX);
+ set_fs(oldfs);
+ if (err < 0) {
+ __clear(dentry, old_lower_dentry,
+ old_bstart, old_bend,
+ new_lower_dentry, new_bindex);
+ goto out_free;
+ }
+ symbuf[err] = '\0';
+ }
+
+ /* Now we lock the parent, and create the object in the new branch. */
+ new_lower_parent_dentry = lock_parent(new_lower_dentry);
+
+ /* create the new inode */
+ err = __copyup_ndentry(old_lower_dentry, new_lower_dentry,
+ new_lower_parent_dentry, symbuf);
+
+ if (err) {
+ __clear(dentry, old_lower_dentry,
+ old_bstart, old_bend,
+ new_lower_dentry, new_bindex);
+ goto out_unlock;
+ }
+
+ /* We actually copyup the file here. */
+ if (S_ISREG(old_lower_dentry->d_inode->i_mode))
+ err = __copyup_reg_data(dentry, new_lower_dentry, new_bindex,
+ old_lower_dentry, old_bindex,
+ copyup_file, len);
+ if (err)
+ goto out_unlink;
+
+ /* Set permissions. */
+ if ((err = copyup_permissions(sb, old_lower_dentry,
+ new_lower_dentry)))
+ goto out_unlink;
+
+#ifdef CONFIG_UNION_FS_XATTR
+ /* Selinux uses extended attributes for permissions. */
+ if ((err = copyup_xattrs(old_lower_dentry, new_lower_dentry)))
+ goto out_unlink;
+#endif /* CONFIG_UNION_FS_XATTR */
+
+ /* do not allow files getting deleted to be re-interposed */
+ if (!d_deleted(dentry))
+ unionfs_reinterpose(dentry);
+
+ goto out_unlock;
+
+out_unlink:
+ /*
+ * copyup failed, because we possibly ran out of space or
+ * quota, or something else happened so let's unlink; we don't
+ * really care about the return value of vfs_unlink
+ */
+ vfs_unlink(new_lower_parent_dentry->d_inode, new_lower_dentry);
+
+ if (copyup_file) {
+ /* need to close the file */
+
+ fput(*copyup_file);
+ branchput(sb, new_bindex);
+ }
+
+ /*
+ * TODO: should we reset the error to something like -EIO?
+ *
+ * If we don't reset, the user may get some nonsensical errors, but
+ * on the other hand, if we reset to EIO, we guarantee that the user
+ * will get a "confusing" error message.
+ */
+
+out_unlock:
+ unlock_dir(new_lower_parent_dentry);
+
+out_free:
+ /*
+ * If old_lower_dentry was a directory, we need to dput it. If it
+ * was a file, then it was already dput indirectly by other
+ * functions we call above which operate on regular files.
+ */
+ if (old_lower_dentry && old_lower_dentry->d_inode &&
+ (S_ISDIR(old_lower_dentry->d_inode->i_mode) ||
+ S_ISLNK(old_lower_dentry->d_inode->i_mode)))
+ dput(old_lower_dentry);
+ kfree(symbuf);
+
+ if (err)
+ goto out;
+ if (!S_ISDIR(dentry->d_inode->i_mode)) {
+ unionfs_purge_extras(dentry);
+ if (!unionfs_lower_inode(dentry->d_inode)) {
+ /*
+ * If we got here, then we copied up to an
+ * unlinked-open file, whose name is .unionfsXXXXX.
+ */
+ struct inode *inode = new_lower_dentry->d_inode;
+ atomic_inc(&inode->i_count);
+ unionfs_set_lower_inode_idx(dentry->d_inode,
+ ibstart(dentry->d_inode),
+ inode);
+ }
+ }
+ unionfs_inherit_mnt(dentry);
+ /* sync inode times from copied-up inode to our inode */
+ unionfs_copy_attr_times(dentry->d_inode);
+ unionfs_check_inode(dir);
+ unionfs_check_dentry(dentry);
+out:
+ return err;
+}
+
+/*
+ * This function creates a copy of a file represented by 'file' which
+ * currently resides in branch 'bstart' to branch 'new_bindex.' The copy
+ * will be named "name".
+ */
+int copyup_named_file(struct inode *dir, struct file *file, char *name,
+ int bstart, int new_bindex, loff_t len)
+{
+ int err = 0;
+ struct file *output_file = NULL;
+
+ err = copyup_dentry(dir, file->f_path.dentry, bstart, new_bindex,
+ name, strlen(name), &output_file, len);
+ if (!err) {
+ fbstart(file) = new_bindex;
+ unionfs_set_lower_file_idx(file, new_bindex, output_file);
+ }
+
+ return err;
+}
+
+/*
+ * This function creates a copy of a file represented by 'file' which
+ * currently resides in branch 'bstart' to branch 'new_bindex'.
+ */
+int copyup_file(struct inode *dir, struct file *file, int bstart,
+ int new_bindex, loff_t len)
+{
+ int err = 0;
+ struct file *output_file = NULL;
+ struct dentry *dentry = file->f_path.dentry;
+
+ err = copyup_dentry(dir, dentry, bstart, new_bindex,
+ dentry->d_name.name, dentry->d_name.len,
+ &output_file, len);
+ if (!err) {
+ fbstart(file) = new_bindex;
+ unionfs_set_lower_file_idx(file, new_bindex, output_file);
+ }
+
+ return err;
+}
+
+/* purge a dentry's lower-branch states (dput/mntput, etc.) */
+static void __cleanup_dentry(struct dentry *dentry, int bindex,
+ int old_bstart, int old_bend)
+{
+ int loop_start;
+ int loop_end;
+ int new_bstart = -1;
+ int new_bend = -1;
+ int i;
+
+ loop_start = min(old_bstart, bindex);
+ loop_end = max(old_bend, bindex);
+
+ /*
+ * This loop sets the bstart and bend for the new dentry by
+ * traversing from left to right. It also dputs all negative
+ * dentries except bindex
+ */
+ for (i = loop_start; i <= loop_end; i++) {
+ if (!unionfs_lower_dentry_idx(dentry, i))
+ continue;
+
+ if (i == bindex) {
+ new_bend = i;
+ if (new_bstart < 0)
+ new_bstart = i;
+ continue;
+ }
+
+ if (!unionfs_lower_dentry_idx(dentry, i)->d_inode) {
+ dput(unionfs_lower_dentry_idx(dentry, i));
+ unionfs_set_lower_dentry_idx(dentry, i, NULL);
+
+ unionfs_mntput(dentry, i);
+ unionfs_set_lower_mnt_idx(dentry, i, NULL);
+ } else {
+ if (new_bstart < 0)
+ new_bstart = i;
+ new_bend = i;
+ }
+ }
+
+ if (new_bstart < 0)
+ new_bstart = bindex;
+ if (new_bend < 0)
+ new_bend = bindex;
+ set_dbstart(dentry, new_bstart);
+ set_dbend(dentry, new_bend);
+
+}
+
+/* set lower inode ptr and update bstart & bend if necessary */
+static void __set_inode(struct dentry *upper, struct dentry *lower,
+ int bindex)
+{
+ unionfs_set_lower_inode_idx(upper->d_inode, bindex,
+ igrab(lower->d_inode));
+ if (likely(ibstart(upper->d_inode) > bindex))
+ ibstart(upper->d_inode) = bindex;
+ if (likely(ibend(upper->d_inode) < bindex))
+ ibend(upper->d_inode) = bindex;
+
+}
+
+/* set lower dentry ptr and update bstart & bend if necessary */
+static void __set_dentry(struct dentry *upper, struct dentry *lower,
+ int bindex)
+{
+ unionfs_set_lower_dentry_idx(upper, bindex, lower);
+ if (likely(dbstart(upper) > bindex))
+ set_dbstart(upper, bindex);
+ if (likely(dbend(upper) < bindex))
+ set_dbend(upper, bindex);
+}
+
+/*
+ * This function replicates the directory structure up-to given dentry
+ * in the bindex branch.
+ */
+struct dentry *create_parents(struct inode *dir, struct dentry *dentry,
+ const char *name, int bindex)
+{
+ int err;
+ struct dentry *child_dentry;
+ struct dentry *parent_dentry;
+ struct dentry *lower_parent_dentry = NULL;
+ struct dentry *lower_dentry = NULL;
+ const char *childname;
+ unsigned int childnamelen;
+ int nr_dentry;
+ int count = 0;
+ int old_bstart;
+ int old_bend;
+ struct dentry **path = NULL;
+ struct super_block *sb;
+
+ verify_locked(dentry);
+
+ if ((err = is_robranch_super(dir->i_sb, bindex))) {
+ lower_dentry = ERR_PTR(err);
+ goto out;
+ }
+
+ old_bstart = dbstart(dentry);
+ old_bend = dbend(dentry);
+
+ lower_dentry = ERR_PTR(-ENOMEM);
+
+ /* There is no sense allocating any less than the minimum. */
+ nr_dentry = 1;
+ path = kmalloc(nr_dentry * sizeof(struct dentry *), GFP_KERNEL);
+ if (!path)
+ goto out;
+
+ /* assume the negative dentry of unionfs as the parent dentry */
+ parent_dentry = dentry;
+
+ /*
+ * This loop finds the first parent that exists in the given branch.
+ * We start building the directory structure from there. At the end
+ * of the loop, the following should hold:
+ * - child_dentry is the first nonexistent child
+ * - parent_dentry is the first existent parent
+ * - path[0] is the = deepest child
+ * - path[count] is the first child to create
+ */
+ do {
+ child_dentry = parent_dentry;
+
+ /* find the parent directory dentry in unionfs */
+ parent_dentry = child_dentry->d_parent;
+ unionfs_lock_dentry(parent_dentry);
+
+ /* find out the lower_parent_dentry in the given branch */
+ lower_parent_dentry =
+ unionfs_lower_dentry_idx(parent_dentry, bindex);
+
+ /* grow path table */
+ if (count == nr_dentry) {
+ void *p;
+
+ nr_dentry *= 2;
+ p = krealloc(path, nr_dentry * sizeof(struct dentry *),
+ GFP_KERNEL);
+ if (!p) {
+ lower_dentry = ERR_PTR(-ENOMEM);
+ goto out;
+ }
+ path = p;
+ }
+
+ /* store the child dentry */
+ path[count++] = child_dentry;
+ } while (!lower_parent_dentry);
+ count--;
+
+ sb = dentry->d_sb;
+
+ /*
+ * This code goes between the begin/end labels and basically
+ * emulates a while(child_dentry != dentry), only cleaner and
+ * shorter than what would be a much longer while loop.
+ */
+begin:
+ /* get lower parent dir in the current branch */
+ lower_parent_dentry = unionfs_lower_dentry_idx(parent_dentry, bindex);
+ unionfs_unlock_dentry(parent_dentry);
+
+ /* init the values to lookup */
+ childname = child_dentry->d_name.name;
+ childnamelen = child_dentry->d_name.len;
+
+ if (child_dentry != dentry) {
+ /* lookup child in the underlying file system */
+ lower_dentry = lookup_one_len(childname, lower_parent_dentry,
+ childnamelen);
+ if (IS_ERR(lower_dentry))
+ goto out;
+ } else {
+ /*
+ * Is the name a whiteout of the child name ? lookup the
+ * whiteout child in the underlying file system
+ */
+ lower_dentry = lookup_one_len(name, lower_parent_dentry,
+ strlen(name));
+ if (IS_ERR(lower_dentry))
+ goto out;
+
+ /* Replace the current dentry (if any) with the new one */
+ dput(unionfs_lower_dentry_idx(dentry, bindex));
+ unionfs_set_lower_dentry_idx(dentry, bindex,
+ lower_dentry);
+
+ __cleanup_dentry(dentry, bindex, old_bstart, old_bend);
+ goto out;
+ }
+
+ if (lower_dentry->d_inode) {
+ /*
+ * since this already exists we dput to avoid
+ * multiple references on the same dentry
+ */
+ dput(lower_dentry);
+ } else {
+ struct sioq_args args;
+
+ /* it's a negative dentry, create a new dir */
+ lower_parent_dentry = lock_parent(lower_dentry);
+
+ args.mkdir.parent = lower_parent_dentry->d_inode;
+ args.mkdir.dentry = lower_dentry;
+ args.mkdir.mode = child_dentry->d_inode->i_mode;
+
+ run_sioq(__unionfs_mkdir, &args);
+ err = args.err;
+
+ if (!err)
+ err = copyup_permissions(dir->i_sb, child_dentry,
+ lower_dentry);
+ unlock_dir(lower_parent_dentry);
+ if (err) {
+ struct inode *inode = lower_dentry->d_inode;
+ /*
+ * If we get here, it means that we created a new
+ * dentry+inode, but copying permissions failed.
+ * Therefore, we should delete this inode and dput
+ * the dentry so as not to leave cruft behind.
+ */
+ if (lower_dentry->d_op && lower_dentry->d_op->d_iput)
+ lower_dentry->d_op->d_iput(lower_dentry,
+ inode);
+ else
+ iput(inode);
+ lower_dentry->d_inode = NULL;
+ dput(lower_dentry);
+ lower_dentry = ERR_PTR(err);
+ goto out;
+ }
+
+ }
+
+ __set_inode(child_dentry, lower_dentry, bindex);
+ __set_dentry(child_dentry, lower_dentry, bindex);
+ /*
+ * update times of this dentry, but also the parent, because if
+ * we changed, the parent may have changed too.
+ */
+ unionfs_copy_attr_times(parent_dentry->d_inode);
+ unionfs_copy_attr_times(child_dentry->d_inode);
+
+ parent_dentry = child_dentry;
+ child_dentry = path[--count];
+ goto begin;
+out:
+ /* cleanup any leftover locks from the do/while loop above */
+ if (IS_ERR(lower_dentry))
+ while (count)
+ unionfs_unlock_dentry(path[count--]);
+ kfree(path);
+ return lower_dentry;
+}
+
+/* set lower mnt of dentry+parents to the first parent node that has an mnt */
+void unionfs_inherit_mnt(struct dentry *dentry)
+{
+ struct dentry *parent, *hasone;
+ int bindex = dbstart(dentry);
+
+ if (unionfs_lower_mnt_idx(dentry, bindex))
+ return;
+ hasone = dentry->d_parent;
+ /* this loop should stop at root dentry */
+ while (!unionfs_lower_mnt_idx(hasone, bindex)) {
+ hasone = hasone->d_parent;
+ }
+ parent = dentry;
+ while (!unionfs_lower_mnt_idx(parent, bindex)) {
+ unionfs_set_lower_mnt_idx(parent, bindex,
+ unionfs_mntget(hasone, bindex));
+ parent = parent->d_parent;
+ }
+}
+
+/*
+ * Regular files should have only one lower object(s). On copyup, we may
+ * have leftover objects from previous branches. So purge all such extra
+ * objects and keep only the most recent, leftmost, copied-up one.
+ */
+void unionfs_purge_extras(struct dentry *dentry)
+{
+ int bindex;
+
+ BUG_ON(S_ISDIR(dentry->d_inode->i_mode));
+ for (bindex=dbstart(dentry)+1; bindex<=dbend(dentry); bindex++) {
+ if (unionfs_lower_mnt_idx(dentry, bindex)) {
+ unionfs_mntput(dentry, bindex);
+ unionfs_set_lower_mnt_idx(dentry, bindex, NULL);
+ }
+ if (unionfs_lower_dentry_idx(dentry, bindex)) {
+ dput(unionfs_lower_dentry_idx(dentry, bindex));
+ unionfs_set_lower_dentry_idx(dentry, bindex, NULL);
+ iput(unionfs_lower_inode_idx(dentry->d_inode, bindex));
+ unionfs_set_lower_inode_idx(dentry->d_inode, bindex,
+ NULL);
+ }
+ }
+ bindex = dbstart(dentry);
+ set_dbend(dentry, bindex);
+ ibend(dentry->d_inode) = ibstart(dentry->d_inode) = bindex;
+}
diff --git a/fs/unionfs/debug.c b/fs/unionfs/debug.c
new file mode 100644
index 0000000..94f0e84
--- /dev/null
+++ b/fs/unionfs/debug.c
@@ -0,0 +1,494 @@
+/*
+ * Copyright (c) 2003-2007 Erez Zadok
+ * Copyright (c) 2005-2007 Josef 'Jeff' Sipek
+ * Copyright (c) 2003-2007 Stony Brook University
+ * Copyright (c) 2003-2007 The Research Foundation of SUNY
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include "union.h"
+
+/*
+ * Helper debugging functions for maintainers (and for users to report back
+ * useful information back to maintainers)
+ */
+
+/* it's always useful to know what part of the code called us */
+#define PRINT_CALLER() \
+ do { \
+ if (!printed_caller) { \
+ printk("PC:%s:%s:%d\n",fname,fxn,line); \
+ printed_caller = 1; \
+ } \
+ } while (0)
+
+/*
+ * __unionfs_check_{inode,dentry,file} perform exhaustive sanity checking on
+ * the fan-out of various Unionfs objects. We check that no lower objects
+ * exist outside the start/end branch range; that all objects within are
+ * non-NULL (with some allowed exceptions); that for every lower file
+ * there's a lower dentry+inode; that the start/end ranges match for all
+ * corresponding lower objects; that open files/symlinks have only one lower
+ * objects, but directories can have several; and more.
+ */
+void __unionfs_check_inode(const struct inode *inode,
+ const char *fname, const char *fxn, int line)
+{
+ int bindex;
+ int istart, iend;
+ struct inode *lower_inode;
+ struct super_block *sb;
+ int printed_caller = 0;
+
+ /* for inodes now */
+ BUG_ON(!inode);
+ sb = inode->i_sb;
+ istart = ibstart(inode);
+ iend = ibend(inode);
+ if (istart > iend) {
+ PRINT_CALLER();
+ printk(" Ci0: inode=%p istart/end=%d:%d\n",
+ inode, istart, iend);
+ }
+ if ((istart == -1 && iend != -1) ||
+ (istart != -1 && iend == -1)) {
+ PRINT_CALLER();
+ printk(" Ci1: inode=%p istart/end=%d:%d\n",
+ inode, istart, iend);
+ }
+ if (!S_ISDIR(inode->i_mode)) {
+ if (iend != istart) {
+ PRINT_CALLER();
+ printk(" Ci2: inode=%p istart=%d iend=%d\n",
+ inode, istart, iend);
+ }
+ }
+
+ for (bindex = sbstart(sb); bindex < sbmax(sb); bindex++) {
+ if (!UNIONFS_I(inode)) {
+ PRINT_CALLER();
+ printk(" Ci3: no inode_info %p\n", inode);
+ return;
+ }
+ if (!UNIONFS_I(inode)->lower_inodes) {
+ PRINT_CALLER();
+ printk(" Ci4: no lower_inodes %p\n", inode);
+ return;
+ }
+ lower_inode = unionfs_lower_inode_idx(inode, bindex);
+ if (lower_inode) {
+ if (bindex < istart || bindex > iend) {
+ PRINT_CALLER();
+ printk(" Ci5: inode/linode=%p:%p bindex=%d "
+ "istart/end=%d:%d\n", inode,
+ lower_inode, bindex, istart, iend);
+ } else if ((int)lower_inode == 0x5a5a5a5a) {
+ /* freed inode! */
+ PRINT_CALLER();
+ printk(" Ci6: inode/linode=%p:%p bindex=%d "
+ "istart/end=%d:%d\n", inode,
+ lower_inode, bindex, istart, iend);
+ }
+ } else { /* lower_inode == NULL */
+ if (bindex >= istart && bindex <= iend) {
+ /*
+ * directories can have NULL lower inodes in
+ * b/t start/end, but NOT if at the
+ * start/end range.
+ */
+ if (!(S_ISDIR(inode->i_mode) &&
+ bindex > istart && bindex < iend)) {
+ PRINT_CALLER();
+ printk(" Ci7: inode/linode=%p:%p "
+ "bindex=%d istart/end=%d:%d\n",
+ inode, lower_inode, bindex,
+ istart, iend);
+ }
+ }
+ }
+ }
+}
+
+void __unionfs_check_dentry(const struct dentry *dentry,
+ const char *fname, const char *fxn, int line)
+{
+ int bindex;
+ int dstart, dend, istart, iend;
+ struct dentry *lower_dentry;
+ struct inode *inode, *lower_inode;
+ struct super_block *sb;
+ struct vfsmount *lower_mnt;
+ int printed_caller = 0;
+
+ BUG_ON(!dentry);
+ sb = dentry->d_sb;
+ inode = dentry->d_inode;
+ dstart = dbstart(dentry);
+ dend = dbend(dentry);
+ BUG_ON(dstart > dend);
+
+ if ((dstart == -1 && dend != -1) ||
+ (dstart != -1 && dend == -1)) {
+ PRINT_CALLER();
+ printk(" CD0: dentry=%p dstart/end=%d:%d\n",
+ dentry, dstart, dend);
+ }
+ /*
+ * check for NULL dentries inside the start/end range, or
+ * non-NULL dentries outside the start/end range.
+ */
+ for (bindex = sbstart(sb); bindex < sbmax(sb); bindex++) {
+ lower_dentry = unionfs_lower_dentry_idx(dentry, bindex);
+ if (lower_dentry) {
+ if (bindex < dstart || bindex > dend) {
+ PRINT_CALLER();
+ printk(" CD1: dentry/lower=%p:%p(%p) "
+ "bindex=%d dstart/end=%d:%d\n",
+ dentry, lower_dentry,
+ (lower_dentry ? lower_dentry->d_inode :
+ (void *) 0xffffffff),
+ bindex, dstart, dend);
+ }
+ } else { /* lower_dentry == NULL */
+ if (bindex >= dstart && bindex <= dend) {
+ /*
+ * Directories can have NULL lower inodes in
+ * b/t start/end, but NOT if at the
+ * start/end range. Ignore this rule,
+ * however, if this is a NULL dentry or a
+ * deleted dentry.
+ */
+ if (!d_deleted((struct dentry *) dentry) &&
+ inode &&
+ !(inode && S_ISDIR(inode->i_mode) &&
+ bindex > dstart && bindex < dend)) {
+ PRINT_CALLER();
+ printk(" CD2: dentry/lower=%p:%p(%p) "
+ "bindex=%d dstart/end=%d:%d\n",
+ dentry, lower_dentry,
+ (lower_dentry ?
+ lower_dentry->d_inode :
+ (void *) 0xffffffff),
+ bindex, dstart, dend);
+ }
+ }
+ }
+ }
+
+ /* check for vfsmounts same as for dentries */
+ for (bindex = sbstart(sb); bindex < sbmax(sb); bindex++) {
+ lower_mnt = unionfs_lower_mnt_idx(dentry, bindex);
+ if (lower_mnt) {
+ if (bindex < dstart || bindex > dend) {
+ PRINT_CALLER();
+ printk(" CM0: dentry/lmnt=%p:%p bindex=%d "
+ "dstart/end=%d:%d\n", dentry,
+ lower_mnt, bindex, dstart, dend);
+ }
+ } else { /* lower_mnt == NULL */
+ if (bindex >= dstart && bindex <= dend) {
+ /*
+ * Directories can have NULL lower inodes in
+ * b/t start/end, but NOT if at the
+ * start/end range. Ignore this rule,
+ * however, if this is a NULL dentry.
+ */
+ if (inode &&
+ !(inode && S_ISDIR(inode->i_mode) &&
+ bindex > dstart && bindex < dend)) {
+ PRINT_CALLER();
+ printk(" CM1: dentry/lmnt=%p:%p "
+ "bindex=%d dstart/end=%d:%d\n",
+ dentry, lower_mnt, bindex,
+ dstart, dend);
+ }
+ }
+ }
+ }
+
+ /* for inodes now */
+ if (!inode)
+ return;
+ istart = ibstart(inode);
+ iend = ibend(inode);
+ BUG_ON(istart > iend);
+ if ((istart == -1 && iend != -1) ||
+ (istart != -1 && iend == -1)) {
+ PRINT_CALLER();
+ printk(" CI0: dentry/inode=%p:%p istart/end=%d:%d\n",
+ dentry, inode, istart, iend);
+ }
+ if (istart != dstart) {
+ PRINT_CALLER();
+ printk(" CI1: dentry/inode=%p:%p istart=%d dstart=%d\n",
+ dentry, inode, istart, dstart);
+ }
+ if (iend != dend) {
+ PRINT_CALLER();
+ printk(" CI2: dentry/inode=%p:%p iend=%d dend=%d\n",
+ dentry, inode, iend, dend);
+ }
+
+ if (!S_ISDIR(inode->i_mode)) {
+ if (dend != dstart) {
+ PRINT_CALLER();
+ printk(" CI3: dentry/inode=%p:%p dstart=%d dend=%d\n",
+ dentry, inode, dstart, dend);
+ }
+ if (iend != istart) {
+ PRINT_CALLER();
+ printk(" CI4: dentry/inode=%p:%p istart=%d iend=%d\n",
+ dentry, inode, istart, iend);
+ }
+ }
+
+ for (bindex = sbstart(sb); bindex < sbmax(sb); bindex++) {
+ lower_inode = unionfs_lower_inode_idx(inode, bindex);
+ if (lower_inode) {
+ if (bindex < istart || bindex > iend) {
+ PRINT_CALLER();
+ printk(" CI5: dentry/linode=%p:%p bindex=%d "
+ "istart/end=%d:%d\n", dentry,
+ lower_inode, bindex, istart, iend);
+ } else if ((int)lower_inode == 0x5a5a5a5a) {
+ /* freed inode! */
+ PRINT_CALLER();
+ printk(" CI6: dentry/linode=%p:%p bindex=%d "
+ "istart/end=%d:%d\n", dentry,
+ lower_inode, bindex, istart, iend);
+ }
+ } else { /* lower_inode == NULL */
+ if (bindex >= istart && bindex <= iend) {
+ /*
+ * directories can have NULL lower inodes in
+ * b/t start/end, but NOT if at the
+ * start/end range.
+ */
+ if (!(S_ISDIR(inode->i_mode) &&
+ bindex > istart && bindex < iend)) {
+ PRINT_CALLER();
+ printk(" CI7: dentry/linode=%p:%p "
+ "bindex=%d istart/end=%d:%d\n",
+ dentry, lower_inode, bindex,
+ istart, iend);
+ }
+ }
+ }
+ }
+
+ /*
+ * If it's a directory, then intermediate objects b/t start/end can
+ * be NULL. But, check that all three are NULL: lower dentry, mnt,
+ * and inode.
+ */
+ if (S_ISDIR(inode->i_mode))
+ for (bindex = dstart+1; bindex < dend; bindex++) {
+ lower_inode = unionfs_lower_inode_idx(inode, bindex);
+ lower_dentry = unionfs_lower_dentry_idx(dentry,
+ bindex);
+ lower_mnt = unionfs_lower_mnt_idx(dentry, bindex);
+ if (!((lower_inode && lower_dentry && lower_mnt) ||
+ (!lower_inode && !lower_dentry && !lower_mnt))) {
+ PRINT_CALLER();
+ printk(" Cx: lmnt/ldentry/linode=%p:%p:%p "
+ "bindex=%d dstart/end=%d:%d\n",
+ lower_mnt, lower_dentry, lower_inode,
+ bindex, dstart, dend);
+ }
+ }
+ /* check if lower inode is newer than upper one (it shouldn't) */
+ if (is_newer_lower(dentry)) {
+ PRINT_CALLER();
+ for (bindex=ibstart(inode); bindex <= ibend(inode); bindex++) {
+ lower_inode = unionfs_lower_inode_idx(inode, bindex);
+ if (!lower_inode)
+ continue;
+ printk(" CI8: bindex=%d mtime/lmtime=%lu.%lu/%lu.%lu "
+ "ctime/lctime=%lu.%lu/%lu.%lu\n",
+ bindex,
+ inode->i_mtime.tv_sec,
+ inode->i_mtime.tv_nsec,
+ lower_inode->i_mtime.tv_sec,
+ lower_inode->i_mtime.tv_nsec,
+ inode->i_ctime.tv_sec,
+ inode->i_ctime.tv_nsec,
+ lower_inode->i_ctime.tv_sec,
+ lower_inode->i_ctime.tv_nsec);
+ }
+ }
+}
+
+void __unionfs_check_file(const struct file *file,
+ const char *fname, const char *fxn, int line)
+{
+ int bindex;
+ int dstart, dend, fstart, fend;
+ struct dentry *dentry;
+ struct file *lower_file;
+ struct inode *inode;
+ struct super_block *sb;
+ int printed_caller = 0;
+
+ BUG_ON(!file);
+ dentry = file->f_path.dentry;
+ sb = dentry->d_sb;
+ dstart = dbstart(dentry);
+ dend = dbend(dentry);
+ BUG_ON(dstart > dend);
+ fstart = fbstart(file);
+ fend = fbend(file);
+ BUG_ON(fstart > fend);
+
+ if ((fstart == -1 && fend != -1) ||
+ (fstart != -1 && fend == -1)) {
+ PRINT_CALLER();
+ printk(" CF0: file/dentry=%p:%p fstart/end=%d:%d\n",
+ file, dentry, fstart, fend);
+ }
+ if (fstart != dstart) {
+ PRINT_CALLER();
+ printk(" CF1: file/dentry=%p:%p fstart=%d dstart=%d\n",
+ file, dentry, fstart, dstart);
+ }
+ if (fend != dend) {
+ PRINT_CALLER();
+ printk(" CF2: file/dentry=%p:%p fend=%d dend=%d\n",
+ file, dentry, fend, dend);
+ }
+ inode = dentry->d_inode;
+ if (!S_ISDIR(inode->i_mode)) {
+ if (fend != fstart) {
+ PRINT_CALLER();
+ printk(" CF3: file/inode=%p:%p fstart=%d fend=%d\n",
+ file, inode, fstart, fend);
+ }
+ if (dend != dstart) {
+ PRINT_CALLER();
+ printk(" CF4: file/dentry=%p:%p dstart=%d dend=%d\n",
+ file, dentry, dstart, dend);
+ }
+ }
+
+ /*
+ * check for NULL dentries inside the start/end range, or
+ * non-NULL dentries outside the start/end range.
+ */
+ for (bindex = sbstart(sb); bindex < sbmax(sb); bindex++) {
+ lower_file = unionfs_lower_file_idx(file, bindex);
+ if (lower_file) {
+ if (bindex < fstart || bindex > fend) {
+ PRINT_CALLER();
+ printk(" CF5: file/lower=%p:%p bindex=%d "
+ "fstart/end=%d:%d\n",
+ file, lower_file, bindex, fstart, fend);
+ }
+ } else { /* lower_file == NULL */
+ if (bindex >= fstart && bindex <= fend) {
+ /*
+ * directories can have NULL lower inodes in
+ * b/t start/end, but NOT if at the
+ * start/end range.
+ */
+ if (!(S_ISDIR(inode->i_mode) &&
+ bindex > fstart && bindex < fend)) {
+ PRINT_CALLER();
+ printk(" CF6: file/lower=%p:%p "
+ "bindex=%d fstart/end=%d:%d\n",
+ file, lower_file, bindex,
+ fstart, fend);
+ }
+ }
+ }
+ }
+
+ __unionfs_check_dentry(dentry,fname,fxn,line);
+}
+
+/* useful to track vfsmount leaks that could cause EBUSY on unmount */
+void __show_branch_counts(const struct super_block *sb,
+ const char *file, const char *fxn, int line)
+{
+ int i;
+ struct vfsmount *mnt;
+
+ printk("BC:");
+ for (i=0; is_root)
+ mnt = UNIONFS_D(sb->s_root)->lower_paths[i].mnt;
+ else
+ mnt = NULL;
+ printk("%d:", (mnt ? atomic_read(&mnt->mnt_count) : -99));
+ }
+ printk("%s:%s:%d\n",file,fxn,line);
+}
+
+void __show_inode_times(const struct inode *inode,
+ const char *file, const char *fxn, int line)
+{
+ struct inode *lower_inode;
+ int bindex;
+
+ for (bindex=ibstart(inode); bindex <= ibend(inode); bindex++) {
+ lower_inode = unionfs_lower_inode_idx(inode, bindex);
+ if (!lower_inode)
+ continue;
+ printk("IT(%lu:%d): ", inode->i_ino, bindex);
+ printk("%s:%s:%d ",file,fxn,line);
+ printk("um=%lu/%lu lm=%lu/%lu ",
+ inode->i_mtime.tv_sec, inode->i_mtime.tv_nsec,
+ lower_inode->i_mtime.tv_sec,
+ lower_inode->i_mtime.tv_nsec);
+ printk("uc=%lu/%lu lc=%lu/%lu\n",
+ inode->i_ctime.tv_sec, inode->i_ctime.tv_nsec,
+ lower_inode->i_ctime.tv_sec,
+ lower_inode->i_ctime.tv_nsec);
+ }
+}
+
+void __show_dinode_times(const struct dentry *dentry,
+ const char *file, const char *fxn, int line)
+{
+ struct inode *inode = dentry->d_inode;
+ struct inode *lower_inode;
+ int bindex;
+
+ for (bindex=ibstart(inode); bindex <= ibend(inode); bindex++) {
+ lower_inode = unionfs_lower_inode_idx(inode, bindex);
+ if (!lower_inode)
+ continue;
+ printk("DT(%s:%lu:%d): ", dentry->d_name.name, inode->i_ino, bindex);
+ printk("%s:%s:%d ",file,fxn,line);
+ printk("um=%lu/%lu lm=%lu/%lu ",
+ inode->i_mtime.tv_sec, inode->i_mtime.tv_nsec,
+ lower_inode->i_mtime.tv_sec,
+ lower_inode->i_mtime.tv_nsec);
+ printk("uc=%lu/%lu lc=%lu/%lu\n",
+ inode->i_ctime.tv_sec, inode->i_ctime.tv_nsec,
+ lower_inode->i_ctime.tv_sec,
+ lower_inode->i_ctime.tv_nsec);
+ }
+}
+
+void __show_inode_counts(const struct inode *inode,
+ const char *file, const char *fxn, int line)
+{
+ struct inode *lower_inode;
+ int bindex;
+
+ if (!inode) {
+ printk("SiC: Null inode\n");
+ return;
+ }
+ for (bindex=sbstart(inode->i_sb); bindex <= sbend(inode->i_sb); bindex++) {
+ lower_inode = unionfs_lower_inode_idx(inode, bindex);
+ if (!lower_inode)
+ continue;
+ printk("SIC(%lu:%d:%d): ", inode->i_ino, bindex,
+ atomic_read(&(inode)->i_count));
+ printk("lc=%d ", atomic_read(&(lower_inode)->i_count));
+ printk("%s:%s:%d\n",file,fxn,line);
+ }
+}
diff --git a/fs/unionfs/dentry.c b/fs/unionfs/dentry.c
new file mode 100644
index 0000000..f3c1258
--- /dev/null
+++ b/fs/unionfs/dentry.c
@@ -0,0 +1,480 @@
+/*
+ * Copyright (c) 2003-2007 Erez Zadok
+ * Copyright (c) 2003-2006 Charles P. Wright
+ * Copyright (c) 2005-2007 Josef 'Jeff' Sipek
+ * Copyright (c) 2005-2006 Junjiro Okajima
+ * Copyright (c) 2005 Arun M. Krishnakumar
+ * Copyright (c) 2004-2006 David P. Quigley
+ * Copyright (c) 2003-2004 Mohammad Nayyer Zubair
+ * Copyright (c) 2003 Puja Gupta
+ * Copyright (c) 2003 Harikesavan Krishnan
+ * Copyright (c) 2003-2007 Stony Brook University
+ * Copyright (c) 2003-2007 The Research Foundation of SUNY
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include "union.h"
+
+/*
+ * Revalidate a single dentry.
+ * Assume that dentry's info node is locked.
+ * Assume that parent(s) are all valid already, but
+ * the child may not yet be valid.
+ * Returns 1 if valid, 0 otherwise.
+ */
+static int __unionfs_d_revalidate_one(struct dentry *dentry,
+ struct nameidata *nd)
+{
+ int valid = 1; /* default is valid (1); invalid is 0. */
+ struct dentry *lower_dentry;
+ int bindex, bstart, bend;
+ int sbgen, dgen;
+ int positive = 0;
+ int locked = 0;
+ int interpose_flag;
+ struct nameidata lowernd; /* TODO: be gentler to the stack */
+
+ if (nd)
+ memcpy(&lowernd, nd, sizeof(struct nameidata));
+ else
+ memset(&lowernd, 0, sizeof(struct nameidata));
+
+ verify_locked(dentry);
+
+ /* if the dentry is unhashed, do NOT revalidate */
+ if (d_deleted(dentry)) {
+ printk(KERN_DEBUG "unionfs: unhashed dentry being "
+ "revalidated: %*s\n",
+ dentry->d_name.len, dentry->d_name.name);
+ goto out;
+ }
+
+ BUG_ON(dbstart(dentry) == -1);
+ if (dentry->d_inode)
+ positive = 1;
+ dgen = atomic_read(&UNIONFS_D(dentry)->generation);
+ sbgen = atomic_read(&UNIONFS_SB(dentry->d_sb)->generation);
+ /*
+ * If we are working on an unconnected dentry, then there is no
+ * revalidation to be done, because this file does not exist within
+ * the namespace, and Unionfs operates on the namespace, not data.
+ */
+ if (sbgen != dgen) {
+ struct dentry *result;
+ int pdgen;
+
+ /* The root entry should always be valid */
+ BUG_ON(IS_ROOT(dentry));
+
+ /* We can't work correctly if our parent isn't valid. */
+ pdgen = atomic_read(&UNIONFS_D(dentry->d_parent)->generation);
+ BUG_ON(pdgen != sbgen); /* should never happen here */
+
+ /* Free the pointers for our inodes and this dentry. */
+ bstart = dbstart(dentry);
+ bend = dbend(dentry);
+ if (bstart >= 0) {
+ struct dentry *lower_dentry;
+ for (bindex = bstart; bindex <= bend; bindex++) {
+ lower_dentry =
+ unionfs_lower_dentry_idx(dentry,
+ bindex);
+ dput(lower_dentry);
+ }
+ }
+ set_dbstart(dentry, -1);
+ set_dbend(dentry, -1);
+
+ interpose_flag = INTERPOSE_REVAL_NEG;
+ if (positive) {
+ interpose_flag = INTERPOSE_REVAL;
+ /*
+ * During BRM, the VFS could already hold a lock on
+ * a file being read, so don't lock it again
+ * (deadlock), but if you lock it in this function,
+ * then release it here too.
+ */
+ if (!mutex_is_locked(&dentry->d_inode->i_mutex)) {
+ mutex_lock(&dentry->d_inode->i_mutex);
+ locked = 1;
+ }
+
+ bstart = ibstart(dentry->d_inode);
+ bend = ibend(dentry->d_inode);
+ if (bstart >= 0) {
+ struct inode *lower_inode;
+ for (bindex = bstart; bindex <= bend;
+ bindex++) {
+ lower_inode =
+ unionfs_lower_inode_idx(
+ dentry->d_inode,
+ bindex);
+ iput(lower_inode);
+ }
+ }
+ kfree(UNIONFS_I(dentry->d_inode)->lower_inodes);
+ UNIONFS_I(dentry->d_inode)->lower_inodes = NULL;
+ ibstart(dentry->d_inode) = -1;
+ ibend(dentry->d_inode) = -1;
+ if (locked)
+ mutex_unlock(&dentry->d_inode->i_mutex);
+ }
+
+ result = unionfs_lookup_backend(dentry, &lowernd,
+ interpose_flag);
+ if (result) {
+ if (IS_ERR(result)) {
+ valid = 0;
+ goto out;
+ }
+ /*
+ * current unionfs_lookup_backend() doesn't return
+ * a valid dentry
+ */
+ dput(dentry);
+ dentry = result;
+ }
+
+ if (positive && UNIONFS_I(dentry->d_inode)->stale) {
+ make_bad_inode(dentry->d_inode);
+ d_drop(dentry);
+ valid = 0;
+ goto out;
+ }
+ goto out;
+ }
+
+ /* The revalidation must occur across all branches */
+ bstart = dbstart(dentry);
+ bend = dbend(dentry);
+ BUG_ON(bstart == -1);
+ for (bindex = bstart; bindex <= bend; bindex++) {
+ lower_dentry = unionfs_lower_dentry_idx(dentry, bindex);
+ if (!lower_dentry || !lower_dentry->d_op
+ || !lower_dentry->d_op->d_revalidate)
+ continue;
+ if (!lower_dentry->d_op->d_revalidate(lower_dentry,
+ &lowernd))
+ valid = 0;
+ }
+
+ if (!dentry->d_inode)
+ valid = 0;
+
+ if (valid) {
+ /*
+ * If we get here, and we copy the meta-data from the lower
+ * inode to our inode, then it is vital that we have already
+ * purged all unionfs-level file data. We do that in the
+ * caller (__unionfs_d_revalidate_chain) by calling
+ * purge_inode_data.
+ */
+ unionfs_copy_attr_all(dentry->d_inode,
+ unionfs_lower_inode(dentry->d_inode));
+ fsstack_copy_inode_size(dentry->d_inode,
+ unionfs_lower_inode(dentry->d_inode));
+ }
+
+out:
+ return valid;
+}
+
+/*
+ * Determine if the lower inode objects have changed from below the unionfs
+ * inode. Return 1 if changed, 0 otherwise.
+ */
+int is_newer_lower(const struct dentry *dentry)
+{
+ int bindex;
+ struct inode *inode;
+ struct inode *lower_inode;
+
+ /* ignore if we're called on semi-initialized dentries/inodes */
+ if (!dentry || !UNIONFS_D(dentry))
+ return 0;
+ inode = dentry->d_inode;
+ if (!inode || !UNIONFS_I(inode) ||
+ ibstart(inode) < 0 || ibend(inode) < 0)
+ return 0;
+
+ for (bindex = ibstart(inode); bindex <= ibend(inode); bindex++) {
+ lower_inode = unionfs_lower_inode_idx(inode, bindex);
+ if (!lower_inode)
+ continue;
+ /*
+ * We may want to apply other tests to determine if the
+ * lower inode's data has changed, but checking for changed
+ * ctime and mtime on the lower inode should be enough.
+ */
+ if (timespec_compare(&inode->i_mtime,
+ &lower_inode->i_mtime) < 0) {
+ printk("unionfs: new lower inode mtime "
+ "(bindex=%d, name=%s)\n", bindex,
+ dentry->d_name.name);
+ show_dinode_times(dentry);
+ return 1; /* mtime changed! */
+ }
+ if (timespec_compare(&inode->i_ctime,
+ &lower_inode->i_ctime) < 0) {
+ printk("unionfs: new lower inode ctime "
+ "(bindex=%d, name=%s)\n", bindex,
+ dentry->d_name.name);
+ show_dinode_times(dentry);
+ return 1; /* ctime changed! */
+ }
+ }
+ return 0; /* default: lower is not newer */
+}
+
+/*
+ * Purge/remove/unmap all date pages of a unionfs inode. This is called
+ * when the lower inode has changed, and we have to force processes to get
+ * the new data.
+ *
+ * XXX: Our implementation works in that as long as a user process will have
+ * caused Unionfs to be called, directly or indirectly, even to just do
+ * ->d_revalidate; then we will have purged the current Unionfs data and the
+ * process will see the new data. For example, a process that continually
+ * re-reads the same file's data will see the NEW data as soon as the lower
+ * file had changed, upon the next read(2) syscall (even if the file is
+ * still open!) However, this doesn't work when the process re-reads the
+ * open file's data via mmap(2) (unless the user unmaps/closes the file and
+ * remaps/reopens it). Once we respond to ->readpage(s), then the kernel
+ * maps the page into the process's address space and there doesn't appear
+ * to be a way to force the kernel to invalidate those pages/mappings, and
+ * force the process to re-issue ->readpage. If there's a way to invalidate
+ * active mappings and force a ->readpage, let us know please
+ * (invalidate_inode_pages2 doesn't do the trick).
+ */
+static inline void purge_inode_data(struct dentry *dentry)
+{
+ /* remove all non-private mappings */
+ unmap_mapping_range(dentry->d_inode->i_mapping, 0, 0, 0);
+
+ if (dentry->d_inode->i_data.nrpages)
+ truncate_inode_pages(&dentry->d_inode->i_data, 0);
+}
+
+/*
+ * Revalidate a parent chain of dentries, then the actual node.
+ * Assumes that dentry is locked, but will lock all parents if/when needed.
+ *
+ * If 'willwrite' is 1, and the lower inode times are not in sync, then
+ * *don't* purge_inode_data, as it could deadlock if ->write calls us and we
+ * try to truncate a locked page. Besides, if unionfs is about to write
+ * data to a file, then there's the data unionfs is about to write is more
+ * authoritative than what's below, therefore we can safely overwrite the
+ * lower inode times and data.
+ */
+int __unionfs_d_revalidate_chain(struct dentry *dentry, struct nameidata *nd,
+ int willwrite)
+{
+ int valid = 0; /* default is invalid (0); valid is 1. */
+ struct dentry **chain = NULL; /* chain of dentries to reval */
+ int chain_len = 0;
+ struct dentry *dtmp;
+ int sbgen, dgen, i;
+ int saved_bstart, saved_bend, bindex;
+
+ /* find length of chain needed to revalidate */
+ /* XXX: should I grab some global (dcache?) lock? */
+ chain_len = 0;
+ sbgen = atomic_read(&UNIONFS_SB(dentry->d_sb)->generation);
+ dtmp = dentry->d_parent;
+ dgen = atomic_read(&UNIONFS_D(dtmp)->generation);
+ /* XXX: should we check if is_newer_lower all the way up? */
+ if (is_newer_lower(dtmp)) {
+ /*
+ * Special case: the root dentry's generation number must
+ * always be valid, but its lower inode times don't have to
+ * be, so sync up the times only.
+ */
+ if (IS_ROOT(dtmp))
+ unionfs_copy_attr_times(dtmp->d_inode);
+ else {
+ /*
+ * reset generation number to zero, guaranteed to be
+ * "old"
+ */
+ dgen = 0;
+ atomic_set(&UNIONFS_D(dtmp)->generation, dgen);
+ }
+ purge_inode_data(dtmp);
+ }
+ while (sbgen != dgen) {
+ /* The root entry should always be valid */
+ BUG_ON(IS_ROOT(dtmp));
+ chain_len++;
+ dtmp = dtmp->d_parent;
+ dgen = atomic_read(&UNIONFS_D(dtmp)->generation);
+ }
+ if (chain_len == 0)
+ goto out_this; /* shortcut if parents are OK */
+
+ /*
+ * Allocate array of dentries to reval. We could use linked lists,
+ * but the number of entries we need to alloc here is often small,
+ * and short lived, so locality will be better.
+ */
+ chain = kzalloc(chain_len * sizeof(struct dentry *), GFP_KERNEL);
+ if (!chain) {
+ printk("unionfs: no more memory in %s\n", __FUNCTION__);
+ goto out;
+ }
+
+ /*
+ * lock all dentries in chain, in child to parent order.
+ * if failed, then sleep for a little, then retry.
+ */
+ dtmp = dentry->d_parent;
+ for (i=chain_len-1; i>=0; i--) {
+ chain[i] = dget(dtmp);
+ dtmp = dtmp->d_parent;
+ }
+
+ /*
+ * call __unionfs_d_revalidate_one() on each dentry, but in parent
+ * to child order.
+ */
+ for (i=0; id_sb)->generation);
+ dgen = atomic_read(&UNIONFS_D(chain[i])->generation);
+
+ valid = __unionfs_d_revalidate_one(chain[i], nd);
+ /* XXX: is this the correct mntput condition?! */
+ if (valid && chain_len > 0 &&
+ sbgen != dgen && chain[i]->d_inode &&
+ S_ISDIR(chain[i]->d_inode->i_mode)) {
+ for (bindex = saved_bstart; bindex <= saved_bend;
+ bindex++)
+ unionfs_mntput(chain[i], bindex);
+ }
+ unionfs_unlock_dentry(chain[i]);
+
+ if (!valid)
+ goto out_free;
+ }
+
+
+out_this:
+ /* finally, lock this dentry and revalidate it */
+ verify_locked(dentry);
+ dgen = atomic_read(&UNIONFS_D(dentry)->generation);
+ if (is_newer_lower(dentry)) {
+ /* root dentry special case as aforementioned */
+ if (IS_ROOT(dentry))
+ unionfs_copy_attr_times(dentry->d_inode);
+ else {
+ /*
+ * reset generation number to zero, guaranteed to be
+ * "old"
+ */
+ dgen = 0;
+ atomic_set(&UNIONFS_D(dentry)->generation, dgen);
+ }
+ if (!willwrite)
+ purge_inode_data(dentry);
+ }
+ valid = __unionfs_d_revalidate_one(dentry, nd);
+
+ /*
+ * If __unionfs_d_revalidate_one() succeeded above, then it will
+ * have incremented the refcnt of the mnt's, but also the branch
+ * indices of the dentry will have been updated (to take into
+ * account any branch insertions/deletion. So the current
+ * dbstart/dbend match the current, and new, indices of the mnts
+ * which __unionfs_d_revalidate_one has incremented. Note: the "if"
+ * test below does not depend on whether chain_len was 0 or greater.
+ */
+ if (valid && sbgen != dgen)
+ for (bindex = dbstart(dentry);
+ bindex <= dbend(dentry);
+ bindex++)
+ unionfs_mntput(dentry, bindex);
+
+out_free:
+ /* unlock/dput all dentries in chain and return status */
+ if (chain_len > 0) {
+ for (i=0; id_sb);
+
+ unionfs_lock_dentry(dentry);
+ err = __unionfs_d_revalidate_chain(dentry, nd, 0);
+ unionfs_unlock_dentry(dentry);
+ unionfs_check_dentry(dentry);
+
+ unionfs_read_unlock(dentry->d_sb);
+
+ return err;
+}
+
+/*
+ * At this point no one can reference this dentry, so we don't have to be
+ * careful about concurrent access.
+ */
+static void unionfs_d_release(struct dentry *dentry)
+{
+ int bindex, bstart, bend;
+
+ unionfs_read_lock(dentry->d_sb);
+
+ unionfs_check_dentry(dentry);
+ /* this could be a negative dentry, so check first */
+ if (!UNIONFS_D(dentry)) {
+ printk(KERN_DEBUG "unionfs: dentry without private data: %.*s",
+ dentry->d_name.len, dentry->d_name.name);
+ goto out;
+ } else if (dbstart(dentry) < 0) {
+ /* this is due to a failed lookup */
+ printk(KERN_DEBUG "unionfs: dentry without lower "
+ "dentries: %.*s",
+ dentry->d_name.len, dentry->d_name.name);
+ goto out_free;
+ }
+
+ /* Release all the lower dentries */
+ bstart = dbstart(dentry);
+ bend = dbend(dentry);
+ for (bindex = bstart; bindex <= bend; bindex++) {
+ dput(unionfs_lower_dentry_idx(dentry, bindex));
+ unionfs_set_lower_dentry_idx(dentry, bindex, NULL);
+ /* NULL lower mnt is ok if this is a negative dentry */
+ if (!dentry->d_inode && !unionfs_lower_mnt_idx(dentry,bindex))
+ continue;
+ unionfs_mntput(dentry, bindex);
+ unionfs_set_lower_mnt_idx(dentry, bindex, NULL);
+ }
+ /* free private data (unionfs_dentry_info) here */
+ kfree(UNIONFS_D(dentry)->lower_paths);
+ UNIONFS_D(dentry)->lower_paths = NULL;
+
+out_free:
+ /* No need to unlock it, because it is disappeared. */
+ free_dentry_private_data(dentry);
+
+out:
+ unionfs_read_unlock(dentry->d_sb);
+ return;
+}
+
+struct dentry_operations unionfs_dops = {
+ .d_revalidate = unionfs_d_revalidate,
+ .d_release = unionfs_d_release,
+};
diff --git a/fs/unionfs/dirfops.c b/fs/unionfs/dirfops.c
new file mode 100644
index 0000000..980f125
--- /dev/null
+++ b/fs/unionfs/dirfops.c
@@ -0,0 +1,278 @@
+/*
+ * Copyright (c) 2003-2007 Erez Zadok
+ * Copyright (c) 2003-2006 Charles P. Wright
+ * Copyright (c) 2005-2007 Josef 'Jeff' Sipek
+ * Copyright (c) 2005-2006 Junjiro Okajima
+ * Copyright (c) 2005 Arun M. Krishnakumar
+ * Copyright (c) 2004-2006 David P. Quigley
+ * Copyright (c) 2003-2004 Mohammad Nayyer Zubair
+ * Copyright (c) 2003 Puja Gupta
+ * Copyright (c) 2003 Harikesavan Krishnan
+ * Copyright (c) 2003-2007 Stony Brook University
+ * Copyright (c) 2003-2007 The Research Foundation of SUNY
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include "union.h"
+
+/* Make sure our rdstate is playing by the rules. */
+static void verify_rdstate_offset(struct unionfs_dir_state *rdstate)
+{
+ BUG_ON(rdstate->offset >= DIREOF);
+ BUG_ON(rdstate->cookie >= MAXRDCOOKIE);
+}
+
+struct unionfs_getdents_callback {
+ struct unionfs_dir_state *rdstate;
+ void *dirent;
+ int entries_written;
+ int filldir_called;
+ int filldir_error;
+ filldir_t filldir;
+ struct super_block *sb;
+};
+
+/* based on generic filldir in fs/readir.c */
+static int unionfs_filldir(void *dirent, const char *name, int namelen,
+ loff_t offset, u64 ino, unsigned int d_type)
+{
+ struct unionfs_getdents_callback *buf = dirent;
+ struct filldir_node *found = NULL;
+ int err = 0;
+ int is_wh_entry = 0;
+
+ buf->filldir_called++;
+
+ if ((namelen > UNIONFS_WHLEN) &&
+ !strncmp(name, UNIONFS_WHPFX, UNIONFS_WHLEN)) {
+ name += UNIONFS_WHLEN;
+ namelen -= UNIONFS_WHLEN;
+ is_wh_entry = 1;
+ }
+
+ found = find_filldir_node(buf->rdstate, name, namelen);
+
+ if (found)
+ goto out;
+
+ /* if 'name' isn't a whiteout, filldir it. */
+ if (!is_wh_entry) {
+ off_t pos = rdstate2offset(buf->rdstate);
+ u64 unionfs_ino = ino;
+
+ if (!err) {
+ err = buf->filldir(buf->dirent, name, namelen, pos,
+ unionfs_ino, d_type);
+ buf->rdstate->offset++;
+ verify_rdstate_offset(buf->rdstate);
+ }
+ }
+ /*
+ * If we did fill it, stuff it in our hash, otherwise return an
+ * error.
+ */
+ if (err) {
+ buf->filldir_error = err;
+ goto out;
+ }
+ buf->entries_written++;
+ if ((err = add_filldir_node(buf->rdstate, name, namelen,
+ buf->rdstate->bindex, is_wh_entry)))
+ buf->filldir_error = err;
+
+out:
+ return err;
+}
+
+static int unionfs_readdir(struct file *file, void *dirent, filldir_t filldir)
+{
+ int err = 0;
+ struct file *lower_file = NULL;
+ struct inode *inode = NULL;
+ struct unionfs_getdents_callback buf;
+ struct unionfs_dir_state *uds;
+ int bend;
+ loff_t offset;
+
+ unionfs_read_lock(file->f_path.dentry->d_sb);
+
+ if ((err = unionfs_file_revalidate(file, 0)))
+ goto out;
+
+ inode = file->f_path.dentry->d_inode;
+
+ uds = UNIONFS_F(file)->rdstate;
+ if (!uds) {
+ if (file->f_pos == DIREOF) {
+ goto out;
+ } else if (file->f_pos > 0) {
+ uds = find_rdstate(inode, file->f_pos);
+ if (!uds) {
+ err = -ESTALE;
+ goto out;
+ }
+ UNIONFS_F(file)->rdstate = uds;
+ } else {
+ init_rdstate(file);
+ uds = UNIONFS_F(file)->rdstate;
+ }
+ }
+ bend = fbend(file);
+
+ while (uds->bindex <= bend) {
+ lower_file = unionfs_lower_file_idx(file, uds->bindex);
+ if (!lower_file) {
+ uds->bindex++;
+ uds->dirpos = 0;
+ continue;
+ }
+
+ /* prepare callback buffer */
+ buf.filldir_called = 0;
+ buf.filldir_error = 0;
+ buf.entries_written = 0;
+ buf.dirent = dirent;
+ buf.filldir = filldir;
+ buf.rdstate = uds;
+ buf.sb = inode->i_sb;
+
+ /* Read starting from where we last left off. */
+ offset = vfs_llseek(lower_file, uds->dirpos, SEEK_SET);
+ if (offset < 0) {
+ err = offset;
+ goto out;
+ }
+ err = vfs_readdir(lower_file, unionfs_filldir, &buf);
+
+ /* Save the position for when we continue. */
+ offset = vfs_llseek(lower_file, 0, SEEK_CUR);
+ if (offset < 0) {
+ err = offset;
+ goto out;
+ }
+ uds->dirpos = offset;
+
+ /* Copy the atime. */
+ fsstack_copy_attr_atime(inode, lower_file->f_path.dentry->d_inode);
+
+ if (err < 0)
+ goto out;
+
+ if (buf.filldir_error)
+ break;
+
+ if (!buf.entries_written) {
+ uds->bindex++;
+ uds->dirpos = 0;
+ }
+ }
+
+ if (!buf.filldir_error && uds->bindex >= bend) {
+ /* Save the number of hash entries for next time. */
+ UNIONFS_I(inode)->hashsize = uds->hashentries;
+ free_rdstate(uds);
+ UNIONFS_F(file)->rdstate = NULL;
+ file->f_pos = DIREOF;
+ } else
+ file->f_pos = rdstate2offset(uds);
+
+out:
+ unionfs_read_unlock(file->f_path.dentry->d_sb);
+ return err;
+}
+
+/*
+ * This is not meant to be a generic repositioning function. If you do
+ * things that aren't supported, then we return EINVAL.
+ *
+ * What is allowed:
+ * (1) seeking to the same position that you are currently at
+ * This really has no effect, but returns where you are.
+ * (2) seeking to the beginning of the file
+ * This throws out all state, and lets you begin again.
+ */
+static loff_t unionfs_dir_llseek(struct file *file, loff_t offset, int origin)
+{
+ struct unionfs_dir_state *rdstate;
+ loff_t err;
+
+ unionfs_read_lock(file->f_path.dentry->d_sb);
+
+ if ((err = unionfs_file_revalidate(file, 0)))
+ goto out;
+
+ rdstate = UNIONFS_F(file)->rdstate;
+
+ /*
+ * we let users seek to their current position, but not anywhere
+ * else.
+ */
+ if (!offset) {
+ switch (origin) {
+ case SEEK_SET:
+ if (rdstate) {
+ free_rdstate(rdstate);
+ UNIONFS_F(file)->rdstate = NULL;
+ }
+ init_rdstate(file);
+ err = 0;
+ break;
+ case SEEK_CUR:
+ err = file->f_pos;
+ break;
+ case SEEK_END:
+ /* Unsupported, because we would break everything. */
+ err = -EINVAL;
+ break;
+ }
+ } else {
+ switch (origin) {
+ case SEEK_SET:
+ if (rdstate) {
+ if (offset == rdstate2offset(rdstate))
+ err = offset;
+ else if (file->f_pos == DIREOF)
+ err = DIREOF;
+ else
+ err = -EINVAL;
+ } else {
+ rdstate = find_rdstate(file->f_path.dentry->d_inode,
+ offset);
+ if (rdstate) {
+ UNIONFS_F(file)->rdstate = rdstate;
+ err = rdstate->offset;
+ } else
+ err = -EINVAL;
+ }
+ break;
+ case SEEK_CUR:
+ case SEEK_END:
+ /* Unsupported, because we would break everything. */
+ err = -EINVAL;
+ break;
+ }
+ }
+
+out:
+ unionfs_read_unlock(file->f_path.dentry->d_sb);
+ return err;
+}
+
+/*
+ * Trimmed directory options, we shouldn't pass everything down since
+ * we don't want to operate on partial directories.
+ */
+struct file_operations unionfs_dir_fops = {
+ .llseek = unionfs_dir_llseek,
+ .read = generic_read_dir,
+ .readdir = unionfs_readdir,
+ .unlocked_ioctl = unionfs_ioctl,
+ .open = unionfs_open,
+ .release = unionfs_file_release,
+ .flush = unionfs_flush,
+ .fsync = unionfs_fsync,
+ .fasync = unionfs_fasync,
+};
diff --git a/fs/unionfs/dirhelper.c b/fs/unionfs/dirhelper.c
new file mode 100644
index 0000000..a72f711
--- /dev/null
+++ b/fs/unionfs/dirhelper.c
@@ -0,0 +1,271 @@
+/*
+ * Copyright (c) 2003-2007 Erez Zadok
+ * Copyright (c) 2003-2006 Charles P. Wright
+ * Copyright (c) 2005-2007 Josef 'Jeff' Sipek
+ * Copyright (c) 2005-2006 Junjiro Okajima
+ * Copyright (c) 2005 Arun M. Krishnakumar
+ * Copyright (c) 2004-2006 David P. Quigley
+ * Copyright (c) 2003-2004 Mohammad Nayyer Zubair
+ * Copyright (c) 2003 Puja Gupta
+ * Copyright (c) 2003 Harikesavan Krishnan
+ * Copyright (c) 2003-2007 Stony Brook University
+ * Copyright (c) 2003-2007 The Research Foundation of SUNY
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include "union.h"
+
+/*
+ * Delete all of the whiteouts in a given directory for rmdir.
+ *
+ * lower directory inode should be locked
+ */
+int do_delete_whiteouts(struct dentry *dentry, int bindex,
+ struct unionfs_dir_state *namelist)
+{
+ int err = 0;
+ struct dentry *lower_dir_dentry = NULL;
+ struct dentry *lower_dentry;
+ char *name = NULL, *p;
+ struct inode *lower_dir;
+ int i;
+ struct list_head *pos;
+ struct filldir_node *cursor;
+
+ /* Find out lower parent dentry */
+ lower_dir_dentry = unionfs_lower_dentry_idx(dentry, bindex);
+ BUG_ON(!S_ISDIR(lower_dir_dentry->d_inode->i_mode));
+ lower_dir = lower_dir_dentry->d_inode;
+ BUG_ON(!S_ISDIR(lower_dir->i_mode));
+
+ err = -ENOMEM;
+ name = __getname();
+ if (!name)
+ goto out;
+ strcpy(name, UNIONFS_WHPFX);
+ p = name + UNIONFS_WHLEN;
+
+ err = 0;
+ for (i = 0; !err && i < namelist->size; i++) {
+ list_for_each(pos, &namelist->list[i]) {
+ cursor =
+ list_entry(pos, struct filldir_node,
+ file_list);
+ /* Only operate on whiteouts in this branch. */
+ if (cursor->bindex != bindex)
+ continue;
+ if (!cursor->whiteout)
+ continue;
+
+ strcpy(p, cursor->name);
+ lower_dentry =
+ lookup_one_len(name, lower_dir_dentry,
+ cursor->namelen +
+ UNIONFS_WHLEN);
+ if (IS_ERR(lower_dentry)) {
+ err = PTR_ERR(lower_dentry);
+ break;
+ }
+ if (lower_dentry->d_inode)
+ err = vfs_unlink(lower_dir, lower_dentry);
+ dput(lower_dentry);
+ if (err)
+ break;
+ }
+ }
+
+ __putname(name);
+
+ /* After all of the removals, we should copy the attributes once. */
+ fsstack_copy_attr_times(dentry->d_inode, lower_dir_dentry->d_inode);
+
+out:
+ return err;
+}
+
+/* delete whiteouts in a dir (for rmdir operation) using sioq if necessary */
+int delete_whiteouts(struct dentry *dentry, int bindex,
+ struct unionfs_dir_state *namelist)
+{
+ int err;
+ struct super_block *sb;
+ struct dentry *lower_dir_dentry;
+ struct inode *lower_dir;
+ struct sioq_args args;
+
+ sb = dentry->d_sb;
+
+ BUG_ON(!S_ISDIR(dentry->d_inode->i_mode));
+ BUG_ON(bindex < dbstart(dentry));
+ BUG_ON(bindex > dbend(dentry));
+ err = is_robranch_super(sb, bindex);
+ if (err)
+ goto out;
+
+ lower_dir_dentry = unionfs_lower_dentry_idx(dentry, bindex);
+ BUG_ON(!S_ISDIR(lower_dir_dentry->d_inode->i_mode));
+ lower_dir = lower_dir_dentry->d_inode;
+ BUG_ON(!S_ISDIR(lower_dir->i_mode));
+
+ mutex_lock(&lower_dir->i_mutex);
+ if (!permission(lower_dir, MAY_WRITE | MAY_EXEC, NULL))
+ err = do_delete_whiteouts(dentry, bindex, namelist);
+ else {
+ args.deletewh.namelist = namelist;
+ args.deletewh.dentry = dentry;
+ args.deletewh.bindex = bindex;
+ run_sioq(__delete_whiteouts, &args);
+ err = args.err;
+ }
+ mutex_unlock(&lower_dir->i_mutex);
+
+out:
+ return err;
+}
+
+#define RD_NONE 0
+#define RD_CHECK_EMPTY 1
+/* The callback structure for check_empty. */
+struct unionfs_rdutil_callback {
+ int err;
+ int filldir_called;
+ struct unionfs_dir_state *rdstate;
+ int mode;
+};
+
+/* This filldir function makes sure only whiteouts exist within a directory. */
+static int readdir_util_callback(void *dirent, const char *name, int namelen,
+ loff_t offset, u64 ino, unsigned int d_type)
+{
+ int err = 0;
+ struct unionfs_rdutil_callback *buf = dirent;
+ int whiteout = 0;
+ struct filldir_node *found;
+
+ buf->filldir_called = 1;
+
+ if (name[0] == '.' && (namelen == 1 ||
+ (name[1] == '.' && namelen == 2)))
+ goto out;
+
+ if (namelen > UNIONFS_WHLEN &&
+ !strncmp(name, UNIONFS_WHPFX, UNIONFS_WHLEN)) {
+ namelen -= UNIONFS_WHLEN;
+ name += UNIONFS_WHLEN;
+ whiteout = 1;
+ }
+
+ found = find_filldir_node(buf->rdstate, name, namelen);
+ /* If it was found in the table there was a previous whiteout. */
+ if (found)
+ goto out;
+
+ /*
+ * if it wasn't found and isn't a whiteout, the directory isn't
+ * empty.
+ */
+ err = -ENOTEMPTY;
+ if ((buf->mode == RD_CHECK_EMPTY) && !whiteout)
+ goto out;
+
+ err = add_filldir_node(buf->rdstate, name, namelen,
+ buf->rdstate->bindex, whiteout);
+
+out:
+ buf->err = err;
+ return err;
+}
+
+/* Is a directory logically empty? */
+int check_empty(struct dentry *dentry, struct unionfs_dir_state **namelist)
+{
+ int err = 0;
+ struct dentry *lower_dentry = NULL;
+ struct super_block *sb;
+ struct file *lower_file;
+ struct unionfs_rdutil_callback *buf = NULL;
+ int bindex, bstart, bend, bopaque;
+
+ sb = dentry->d_sb;
+
+
+ BUG_ON(!S_ISDIR(dentry->d_inode->i_mode));
+
+ if ((err = unionfs_partial_lookup(dentry)))
+ goto out;
+
+ bstart = dbstart(dentry);
+ bend = dbend(dentry);
+ bopaque = dbopaque(dentry);
+ if (0 <= bopaque && bopaque < bend)
+ bend = bopaque;
+
+ buf = kmalloc(sizeof(struct unionfs_rdutil_callback), GFP_KERNEL);
+ if (!buf) {
+ err = -ENOMEM;
+ goto out;
+ }
+ buf->err = 0;
+ buf->mode = RD_CHECK_EMPTY;
+ buf->rdstate = alloc_rdstate(dentry->d_inode, bstart);
+ if (!buf->rdstate) {
+ err = -ENOMEM;
+ goto out;
+ }
+
+ /* Process the lower directories with rdutil_callback as a filldir. */
+ for (bindex = bstart; bindex <= bend; bindex++) {
+ lower_dentry = unionfs_lower_dentry_idx(dentry, bindex);
+ if (!lower_dentry)
+ continue;
+ if (!lower_dentry->d_inode)
+ continue;
+ if (!S_ISDIR(lower_dentry->d_inode->i_mode))
+ continue;
+
+ dget(lower_dentry);
+ unionfs_mntget(dentry, bindex);
+ branchget(sb, bindex);
+ lower_file =
+ dentry_open(lower_dentry,
+ unionfs_lower_mnt_idx(dentry, bindex),
+ O_RDONLY);
+ if (IS_ERR(lower_file)) {
+ err = PTR_ERR(lower_file);
+ dput(lower_dentry);
+ branchput(sb, bindex);
+ goto out;
+ }
+
+ do {
+ buf->filldir_called = 0;
+ buf->rdstate->bindex = bindex;
+ err = vfs_readdir(lower_file,
+ readdir_util_callback, buf);
+ if (buf->err)
+ err = buf->err;
+ } while ((err >= 0) && buf->filldir_called);
+
+ /* fput calls dput for lower_dentry */
+ fput(lower_file);
+ branchput(sb, bindex);
+
+ if (err < 0)
+ goto out;
+ }
+
+out:
+ if (buf) {
+ if (namelist && !err)
+ *namelist = buf->rdstate;
+ else if (buf->rdstate)
+ free_rdstate(buf->rdstate);
+ kfree(buf);
+ }
+
+
+ return err;
+}
diff --git a/fs/unionfs/fanout.h b/fs/unionfs/fanout.h
new file mode 100644
index 0000000..e7407f0
--- /dev/null
+++ b/fs/unionfs/fanout.h
@@ -0,0 +1,318 @@
+/*
+ * Copyright (c) 2003-2007 Erez Zadok
+ * Copyright (c) 2003-2006 Charles P. Wright
+ * Copyright (c) 2005-2007 Josef 'Jeff' Sipek
+ * Copyright (c) 2005 Arun M. Krishnakumar
+ * Copyright (c) 2004-2006 David P. Quigley
+ * Copyright (c) 2003-2004 Mohammad Nayyer Zubair
+ * Copyright (c) 2003 Puja Gupta
+ * Copyright (c) 2003 Harikesavan Krishnan
+ * Copyright (c) 2003-2007 Stony Brook University
+ * Copyright (c) 2003-2007 The Research Foundation of SUNY
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#ifndef _FANOUT_H_
+#define _FANOUT_H_
+
+/*
+ * Inode to private data
+ *
+ * Since we use containers and the struct inode is _inside_ the
+ * unionfs_inode_info structure, UNIONFS_I will always (given a non-NULL
+ * inode pointer), return a valid non-NULL pointer.
+ */
+static inline struct unionfs_inode_info *UNIONFS_I(const struct inode *inode)
+{
+ return container_of(inode, struct unionfs_inode_info, vfs_inode);
+}
+
+#define ibstart(ino) (UNIONFS_I(ino)->bstart)
+#define ibend(ino) (UNIONFS_I(ino)->bend)
+
+/* Superblock to private data */
+#define UNIONFS_SB(super) ((struct unionfs_sb_info *)(super)->s_fs_info)
+#define sbstart(sb) 0
+#define sbend(sb) (UNIONFS_SB(sb)->bend)
+#define sbmax(sb) (UNIONFS_SB(sb)->bend + 1)
+#define sbhbid(sb) (UNIONFS_SB(sb)->high_branch_id)
+
+/* File to private Data */
+#define UNIONFS_F(file) ((struct unionfs_file_info *)((file)->private_data))
+#define fbstart(file) (UNIONFS_F(file)->bstart)
+#define fbend(file) (UNIONFS_F(file)->bend)
+
+/* macros to manipulate branch IDs in stored in our superblock */
+static inline int branch_id(struct super_block *sb, int index)
+{
+ return UNIONFS_SB(sb)->data[index].branch_id;
+}
+
+static inline void set_branch_id(struct super_block *sb, int index, int val)
+{
+ UNIONFS_SB(sb)->data[index].branch_id = val;
+}
+
+static inline void new_branch_id(struct super_block *sb, int index)
+{
+ set_branch_id(sb, index, ++UNIONFS_SB(sb)->high_branch_id);
+}
+
+/*
+ * Find new index of matching branch with an existing superblock of a known
+ * (possibly old) id. This is needed because branches could have been
+ * added/deleted causing the branches of any open files to shift.
+ *
+ * @sb: the new superblock which may have new/different branch IDs
+ * @id: the old/existing id we're looking for
+ * Returns index of newly found branch (0 or greater), -1 otherwise.
+ */
+static inline int branch_id_to_idx(struct super_block *sb, int id)
+{
+ int i;
+ for (i = 0; i < sbmax(sb); i++) {
+ if (branch_id(sb, i) == id)
+ return i;
+ }
+ /* in the non-ODF code, this should really never happen */
+ printk(KERN_WARNING "unionfs: cannot find branch with id %d\n", id);
+ return -1;
+}
+
+/* File to lower file. */
+static inline struct file *unionfs_lower_file(const struct file *f)
+{
+ return UNIONFS_F(f)->lower_files[fbstart(f)];
+}
+
+static inline struct file *unionfs_lower_file_idx(const struct file *f,
+ int index)
+{
+ return UNIONFS_F(f)->lower_files[index];
+}
+
+static inline void unionfs_set_lower_file_idx(struct file *f, int index,
+ struct file *val)
+{
+ UNIONFS_F(f)->lower_files[index] = val;
+ /* save branch ID (may be redundant?) */
+ UNIONFS_F(f)->saved_branch_ids[index] =
+ branch_id((f)->f_dentry->d_sb, index);
+}
+
+static inline void unionfs_set_lower_file(struct file *f, struct file *val)
+{
+ unionfs_set_lower_file_idx((f), fbstart(f), (val));
+}
+
+/* Inode to lower inode. */
+static inline struct inode *unionfs_lower_inode(const struct inode *i)
+{
+ return UNIONFS_I(i)->lower_inodes[ibstart(i)];
+}
+
+static inline struct inode *unionfs_lower_inode_idx(const struct inode *i,
+ int index)
+{
+ return UNIONFS_I(i)->lower_inodes[index];
+}
+
+static inline void unionfs_set_lower_inode_idx(struct inode *i, int index,
+ struct inode *val)
+{
+ UNIONFS_I(i)->lower_inodes[index] = val;
+}
+
+static inline void unionfs_set_lower_inode(struct inode *i, struct inode *val)
+{
+ UNIONFS_I(i)->lower_inodes[ibstart(i)] = val;
+}
+
+/* Superblock to lower superblock. */
+static inline struct super_block *unionfs_lower_super(
+ const struct super_block *sb)
+{
+ return UNIONFS_SB(sb)->data[sbstart(sb)].sb;
+}
+
+static inline struct super_block *unionfs_lower_super_idx(
+ const struct super_block *sb,
+ int index)
+{
+ return UNIONFS_SB(sb)->data[index].sb;
+}
+
+static inline void unionfs_set_lower_super_idx(struct super_block *sb,
+ int index,
+ struct super_block *val)
+{
+ UNIONFS_SB(sb)->data[index].sb = val;
+}
+
+static inline void unionfs_set_lower_super(struct super_block *sb,
+ struct super_block *val)
+{
+ UNIONFS_SB(sb)->data[sbstart(sb)].sb = val;
+}
+
+/* Branch count macros. */
+static inline int branch_count(const struct super_block *sb, int index)
+{
+ return atomic_read(&UNIONFS_SB(sb)->data[index].open_files);
+}
+
+static inline void set_branch_count(struct super_block *sb, int index, int val)
+{
+ atomic_set(&UNIONFS_SB(sb)->data[index].open_files, val);
+}
+
+static inline void branchget(struct super_block *sb, int index)
+{
+ atomic_inc(&UNIONFS_SB(sb)->data[index].open_files);
+}
+
+static inline void branchput(struct super_block *sb, int index)
+{
+ atomic_dec(&UNIONFS_SB(sb)->data[index].open_files);
+}
+
+/* Dentry macros */
+static inline struct unionfs_dentry_info *UNIONFS_D(const struct dentry *dent)
+{
+ return dent->d_fsdata;
+}
+
+static inline int dbstart(const struct dentry *dent)
+{
+ return UNIONFS_D(dent)->bstart;
+}
+
+static inline void set_dbstart(struct dentry *dent, int val)
+{
+ UNIONFS_D(dent)->bstart = val;
+}
+
+static inline int dbend(const struct dentry *dent)
+{
+ return UNIONFS_D(dent)->bend;
+}
+
+static inline void set_dbend(struct dentry *dent, int val)
+{
+ UNIONFS_D(dent)->bend = val;
+}
+
+static inline int dbopaque(const struct dentry *dent)
+{
+ return UNIONFS_D(dent)->bopaque;
+}
+
+static inline void set_dbopaque(struct dentry *dent, int val)
+{
+ UNIONFS_D(dent)->bopaque = val;
+}
+
+static inline void unionfs_set_lower_dentry_idx(struct dentry *dent, int index,
+ struct dentry *val)
+{
+ UNIONFS_D(dent)->lower_paths[index].dentry = val;
+}
+
+static inline struct dentry *unionfs_lower_dentry_idx(
+ const struct dentry *dent,
+ int index)
+{
+ return UNIONFS_D(dent)->lower_paths[index].dentry;
+}
+
+static inline struct dentry *unionfs_lower_dentry(const struct dentry *dent)
+{
+ return unionfs_lower_dentry_idx(dent, dbstart(dent));
+}
+
+static inline void unionfs_set_lower_mnt_idx(struct dentry *dent, int index,
+ struct vfsmount *mnt)
+{
+ UNIONFS_D(dent)->lower_paths[index].mnt = mnt;
+}
+
+static inline struct vfsmount *unionfs_lower_mnt_idx(
+ const struct dentry *dent,
+ int index)
+{
+ return UNIONFS_D(dent)->lower_paths[index].mnt;
+}
+
+static inline struct vfsmount *unionfs_lower_mnt(const struct dentry *dent)
+{
+ return unionfs_lower_mnt_idx(dent, dbstart(dent));
+}
+
+/* Macros for locking a dentry. */
+static inline void unionfs_lock_dentry(struct dentry *d)
+{
+ mutex_lock(&UNIONFS_D(d)->lock);
+}
+
+static inline void unionfs_unlock_dentry(struct dentry *d)
+{
+ mutex_unlock(&UNIONFS_D(d)->lock);
+}
+
+static inline void verify_locked(struct dentry *d)
+{
+ BUG_ON(!mutex_is_locked(&UNIONFS_D(d)->lock));
+}
+
+/* copy a/m/ctime from the lower branch with the newest times */
+static inline void unionfs_copy_attr_times(struct inode *upper)
+{
+ int bindex;
+ struct inode *lower;
+
+ if (!upper)
+ return;
+ for (bindex=ibstart(upper); bindex <= ibend(upper); bindex++) {
+ lower = unionfs_lower_inode_idx(upper, bindex);
+ if (!lower)
+ continue; /* not all lower dir objects may exist */
+ if (timespec_compare(&upper->i_mtime, &lower->i_mtime) < 0)
+ upper->i_mtime = lower->i_mtime;
+ if (timespec_compare(&upper->i_ctime, &lower->i_ctime) < 0)
+ upper->i_ctime = lower->i_ctime;
+ if (timespec_compare(&upper->i_atime, &lower->i_atime) < 0)
+ upper->i_atime = lower->i_atime;
+ /* XXX: should we notify_change on our upper inode? */
+ }
+}
+
+/*
+ * A unionfs/fanout version of fsstack_copy_attr_all. Uses a
+ * unionfs_get_nlinks to properly calcluate the number of links to a file.
+ * Also, copies the max() of all a/m/ctimes for all lower inodes (which is
+ * important if the lower inode is a directory type)
+ */
+static inline void unionfs_copy_attr_all(struct inode *dest,
+ const struct inode *src)
+{
+ dest->i_mode = src->i_mode;
+ dest->i_uid = src->i_uid;
+ dest->i_gid = src->i_gid;
+ dest->i_rdev = src->i_rdev;
+
+ unionfs_copy_attr_times(dest);
+
+ dest->i_blkbits = src->i_blkbits;
+ dest->i_flags = src->i_flags;
+
+ /*
+ * Update the nlinks AFTER updating the above fields, because the
+ * get_links callback may depend on them.
+ */
+ dest->i_nlink = unionfs_get_nlinks(dest);
+}
+
+#endif /* not _FANOUT_H */
diff --git a/fs/unionfs/file.c b/fs/unionfs/file.c
new file mode 100644
index 0000000..3f6b2d0
--- /dev/null
+++ b/fs/unionfs/file.c
@@ -0,0 +1,250 @@
+/*
+ * Copyright (c) 2003-2007 Erez Zadok
+ * Copyright (c) 2003-2006 Charles P. Wright
+ * Copyright (c) 2005-2007 Josef 'Jeff' Sipek
+ * Copyright (c) 2005-2006 Junjiro Okajima
+ * Copyright (c) 2005 Arun M. Krishnakumar
+ * Copyright (c) 2004-2006 David P. Quigley
+ * Copyright (c) 2003-2004 Mohammad Nayyer Zubair
+ * Copyright (c) 2003 Puja Gupta
+ * Copyright (c) 2003 Harikesavan Krishnan
+ * Copyright (c) 2003-2007 Stony Brook University
+ * Copyright (c) 2003-2007 The Research Foundation of SUNY
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include "union.h"
+
+static ssize_t unionfs_read(struct file *file, char __user *buf,
+ size_t count, loff_t *ppos)
+{
+ int err;
+
+ unionfs_read_lock(file->f_path.dentry->d_sb);
+ if ((err = unionfs_file_revalidate(file, 0)))
+ goto out;
+ unionfs_check_file(file);
+
+ err = do_sync_read(file, buf, count, ppos);
+
+ if (err >= 0)
+ touch_atime(unionfs_lower_mnt(file->f_path.dentry),
+ unionfs_lower_dentry(file->f_path.dentry));
+
+out:
+ unionfs_read_unlock(file->f_path.dentry->d_sb);
+ unionfs_check_file(file);
+ return err;
+}
+
+static ssize_t unionfs_aio_read(struct kiocb *iocb, const struct iovec *iov,
+ unsigned long nr_segs, loff_t pos)
+{
+ int err = 0;
+ struct file *file = iocb->ki_filp;
+
+ unionfs_read_lock(file->f_path.dentry->d_sb);
+ if ((err = unionfs_file_revalidate(file, 0)))
+ goto out;
+ unionfs_check_file(file);
+
+ err = generic_file_aio_read(iocb, iov, nr_segs, pos);
+
+ if (err == -EIOCBQUEUED)
+ err = wait_on_sync_kiocb(iocb);
+
+ if (err >= 0)
+ touch_atime(unionfs_lower_mnt(file->f_path.dentry),
+ unionfs_lower_dentry(file->f_path.dentry));
+
+out:
+ unionfs_read_unlock(file->f_path.dentry->d_sb);
+ unionfs_check_file(file);
+ return err;
+}
+
+static ssize_t unionfs_write(struct file *file, const char __user *buf,
+ size_t count, loff_t *ppos)
+{
+ int err = 0;
+
+ unionfs_read_lock(file->f_path.dentry->d_sb);
+ if ((err = unionfs_file_revalidate(file, 1)))
+ goto out;
+ unionfs_check_file(file);
+
+ err = do_sync_write(file, buf, count, ppos);
+ /* update our inode times upon a successful lower write */
+ if (err >= 0) {
+ unionfs_copy_attr_times(file->f_path.dentry->d_inode);
+ unionfs_check_file(file);
+ }
+
+out:
+ unionfs_read_unlock(file->f_path.dentry->d_sb);
+ return err;
+}
+
+static int unionfs_file_readdir(struct file *file, void *dirent,
+ filldir_t filldir)
+{
+ return -ENOTDIR;
+}
+
+static int unionfs_mmap(struct file *file, struct vm_area_struct *vma)
+{
+ int err = 0;
+ int willwrite;
+ struct file *lower_file;
+
+ unionfs_read_lock(file->f_path.dentry->d_sb);
+
+ /* This might be deferred to mmap's writepage */
+ willwrite = ((vma->vm_flags | VM_SHARED | VM_WRITE) == vma->vm_flags);
+ if ((err = unionfs_file_revalidate(file, willwrite)))
+ goto out;
+ unionfs_check_file(file);
+
+ /*
+ * File systems which do not implement ->writepage may use
+ * generic_file_readonly_mmap as their ->mmap op. If you call
+ * generic_file_readonly_mmap with VM_WRITE, you'd get an -EINVAL.
+ * But we cannot call the lower ->mmap op, so we can't tell that
+ * writeable mappings won't work. Therefore, our only choice is to
+ * check if the lower file system supports the ->writepage, and if
+ * not, return EINVAL (the same error that
+ * generic_file_readonly_mmap returns in that case).
+ */
+ lower_file = unionfs_lower_file(file);
+ if (willwrite && !lower_file->f_mapping->a_ops->writepage) {
+ err = -EINVAL;
+ printk("unionfs: branch %d file system does not support "
+ "writeable mmap\n", fbstart(file));
+ } else {
+ err = generic_file_mmap(file, vma);
+ if (err)
+ printk("unionfs: generic_file_mmap failed %d\n", err);
+ }
+
+out:
+ unionfs_read_unlock(file->f_path.dentry->d_sb);
+ if (!err) {
+ /* copyup could cause parent dir times to change */
+ unionfs_copy_attr_times(file->f_path.dentry->d_parent->d_inode);
+ unionfs_check_file(file);
+ unionfs_check_dentry(file->f_path.dentry->d_parent);
+ }
+ return err;
+}
+
+int unionfs_fsync(struct file *file, struct dentry *dentry, int datasync)
+{
+ int bindex, bstart, bend;
+ struct file *lower_file;
+ struct dentry *lower_dentry;
+ struct inode *lower_inode, *inode;
+ int err = -EINVAL;
+
+ unionfs_read_lock(file->f_path.dentry->d_sb);
+ if ((err = unionfs_file_revalidate(file, 1)))
+ goto out;
+ unionfs_check_file(file);
+
+ bstart = fbstart(file);
+ bend = fbend(file);
+ if (bstart < 0 || bend < 0)
+ goto out;
+
+ inode = dentry->d_inode;
+ if (!inode) {
+ printk(KERN_ERR
+ "unionfs: null lower inode in unionfs_fsync\n");
+ goto out;
+ }
+ for (bindex = bstart; bindex <= bend; bindex++) {
+ lower_inode = unionfs_lower_inode_idx(inode, bindex);
+ if (!lower_inode || !lower_inode->i_fop->fsync)
+ continue;
+ lower_file = unionfs_lower_file_idx(file, bindex);
+ lower_dentry = unionfs_lower_dentry_idx(dentry, bindex);
+ mutex_lock(&lower_inode->i_mutex);
+ err = lower_inode->i_fop->fsync(lower_file,
+ lower_dentry,
+ datasync);
+ mutex_unlock(&lower_inode->i_mutex);
+ if (err)
+ goto out;
+ }
+
+ unionfs_copy_attr_times(inode);
+
+out:
+ unionfs_read_unlock(file->f_path.dentry->d_sb);
+ unionfs_check_file(file);
+ return err;
+}
+
+int unionfs_fasync(int fd, struct file *file, int flag)
+{
+ int bindex, bstart, bend;
+ struct file *lower_file;
+ struct dentry *dentry;
+ struct inode *lower_inode, *inode;
+ int err = 0;
+
+ unionfs_read_lock(file->f_path.dentry->d_sb);
+ if ((err = unionfs_file_revalidate(file, 1)))
+ goto out;
+ unionfs_check_file(file);
+
+ bstart = fbstart(file);
+ bend = fbend(file);
+ if (bstart < 0 || bend < 0)
+ goto out;
+
+ dentry = file->f_path.dentry;
+ inode = dentry->d_inode;
+ if (!inode) {
+ printk(KERN_ERR
+ "unionfs: null lower inode in unionfs_fasync\n");
+ goto out;
+ }
+ for (bindex = bstart; bindex <= bend; bindex++) {
+ lower_inode = unionfs_lower_inode_idx(inode, bindex);
+ if (!lower_inode || !lower_inode->i_fop->fasync)
+ continue;
+ lower_file = unionfs_lower_file_idx(file, bindex);
+ mutex_lock(&lower_inode->i_mutex);
+ err = lower_inode->i_fop->fasync(fd, lower_file, flag);
+ mutex_unlock(&lower_inode->i_mutex);
+ if (err)
+ goto out;
+ }
+
+ unionfs_copy_attr_times(inode);
+
+out:
+ unionfs_read_unlock(file->f_path.dentry->d_sb);
+ unionfs_check_file(file);
+ return err;
+}
+
+struct file_operations unionfs_main_fops = {
+ .llseek = generic_file_llseek,
+ .read = unionfs_read,
+ .aio_read = unionfs_aio_read,
+ .write = unionfs_write,
+ .aio_write = generic_file_aio_write,
+ .readdir = unionfs_file_readdir,
+ .unlocked_ioctl = unionfs_ioctl,
+ .mmap = unionfs_mmap,
+ .open = unionfs_open,
+ .flush = unionfs_flush,
+ .release = unionfs_file_release,
+ .fsync = unionfs_fsync,
+ .fasync = unionfs_fasync,
+ .sendfile = generic_file_sendfile,
+};
diff --git a/fs/unionfs/inode.c b/fs/unionfs/inode.c
new file mode 100644
index 0000000..c772fbd
--- /dev/null
+++ b/fs/unionfs/inode.c
@@ -0,0 +1,1219 @@
+/*
+ * Copyright (c) 2003-2007 Erez Zadok
+ * Copyright (c) 2003-2006 Charles P. Wright
+ * Copyright (c) 2005-2007 Josef 'Jeff' Sipek
+ * Copyright (c) 2005-2006 Junjiro Okajima
+ * Copyright (c) 2005 Arun M. Krishnakumar
+ * Copyright (c) 2004-2006 David P. Quigley
+ * Copyright (c) 2003-2004 Mohammad Nayyer Zubair
+ * Copyright (c) 2003 Puja Gupta
+ * Copyright (c) 2003 Harikesavan Krishnan
+ * Copyright (c) 2003-2007 Stony Brook University
+ * Copyright (c) 2003-2007 The Research Foundation of SUNY
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include "union.h"
+
+static int unionfs_create(struct inode *parent, struct dentry *dentry,
+ int mode, struct nameidata *nd)
+{
+ int err = 0;
+ struct dentry *lower_dentry = NULL;
+ struct dentry *wh_dentry = NULL;
+ struct dentry *new_lower_dentry;
+ struct dentry *lower_parent_dentry = NULL;
+ int bindex = 0, bstart;
+ char *name = NULL;
+ int valid = 0;
+
+ unionfs_read_lock(dentry->d_sb);
+ unionfs_lock_dentry(dentry);
+
+ unionfs_lock_dentry(dentry->d_parent);
+ valid = __unionfs_d_revalidate_chain(dentry->d_parent, nd, 0);
+ unionfs_unlock_dentry(dentry->d_parent);
+ if (!valid) {
+ err = -ESTALE; /* same as what real_lookup does */
+ goto out;
+ }
+ valid = __unionfs_d_revalidate_chain(dentry, nd, 0);
+ /*
+ * It's only a bug if this dentry was not negative and couldn't be
+ * revalidated (shouldn't happen).
+ */
+ BUG_ON(!valid && dentry->d_inode);
+
+ /* We start out in the leftmost branch. */
+ bstart = dbstart(dentry);
+ lower_dentry = unionfs_lower_dentry(dentry);
+
+ /*
+ * check if whiteout exists in this branch, i.e. lookup .wh.foo
+ * first.
+ */
+ name = alloc_whname(dentry->d_name.name, dentry->d_name.len);
+ if (IS_ERR(name)) {
+ err = PTR_ERR(name);
+ goto out;
+ }
+
+ wh_dentry = lookup_one_len(name, lower_dentry->d_parent,
+ dentry->d_name.len + UNIONFS_WHLEN);
+ if (IS_ERR(wh_dentry)) {
+ err = PTR_ERR(wh_dentry);
+ wh_dentry = NULL;
+ goto out;
+ }
+
+ if (wh_dentry->d_inode) {
+ /*
+ * .wh.foo has been found.
+ * First truncate it and then rename it to foo (hence having
+ * the same overall effect as a normal create.
+ */
+ struct dentry *lower_dir_dentry;
+ struct iattr newattrs;
+
+ mutex_lock(&wh_dentry->d_inode->i_mutex);
+ newattrs.ia_valid = ATTR_CTIME | ATTR_MODE | ATTR_ATIME
+ | ATTR_MTIME | ATTR_UID | ATTR_GID | ATTR_FORCE
+ | ATTR_KILL_SUID | ATTR_KILL_SGID;
+
+ newattrs.ia_mode = mode & ~current->fs->umask;
+ newattrs.ia_uid = current->fsuid;
+ newattrs.ia_gid = current->fsgid;
+
+ if (wh_dentry->d_inode->i_size != 0) {
+ newattrs.ia_valid |= ATTR_SIZE;
+ newattrs.ia_size = 0;
+ }
+
+ err = notify_change(wh_dentry, &newattrs);
+
+ mutex_unlock(&wh_dentry->d_inode->i_mutex);
+
+ if (err)
+ printk(KERN_WARNING "unionfs: %s:%d: notify_change "
+ "failed: %d, ignoring..\n",
+ __FILE__, __LINE__, err);
+
+ new_lower_dentry = unionfs_lower_dentry(dentry);
+ dget(new_lower_dentry);
+
+ lower_dir_dentry = dget_parent(wh_dentry);
+ lock_rename(lower_dir_dentry, lower_dir_dentry);
+
+ if (!(err = is_robranch_super(dentry->d_sb, bstart))) {
+ err = vfs_rename(lower_dir_dentry->d_inode,
+ wh_dentry,
+ lower_dir_dentry->d_inode,
+ new_lower_dentry);
+ }
+ if (!err) {
+ fsstack_copy_attr_times(parent,
+ new_lower_dentry->d_parent->
+ d_inode);
+ fsstack_copy_inode_size(parent,
+ new_lower_dentry->d_parent->
+ d_inode);
+ parent->i_nlink = unionfs_get_nlinks(parent);
+ }
+
+ unlock_rename(lower_dir_dentry, lower_dir_dentry);
+ dput(lower_dir_dentry);
+
+ dput(new_lower_dentry);
+
+ if (err) {
+ /* exit if the error returned was NOT -EROFS */
+ if (!IS_COPYUP_ERR(err))
+ goto out;
+ /*
+ * We were not able to create the file in this
+ * branch, so, we try to create it in one branch to
+ * left
+ */
+ bstart--;
+ } else {
+ /*
+ * reset the unionfs dentry to point to the .wh.foo
+ * entry.
+ */
+
+ /* Discard any old reference. */
+ dput(unionfs_lower_dentry(dentry));
+
+ /* Trade one reference to another. */
+ unionfs_set_lower_dentry_idx(dentry, bstart,
+ wh_dentry);
+ wh_dentry = NULL;
+
+ /*
+ * Only INTERPOSE_LOOKUP can return a value other
+ * than 0 on err.
+ */
+ err = PTR_ERR(unionfs_interpose(dentry,
+ parent->i_sb, 0));
+ goto out;
+ }
+ }
+
+ for (bindex = bstart; bindex >= 0; bindex--) {
+ lower_dentry = unionfs_lower_dentry_idx(dentry, bindex);
+ if (!lower_dentry) {
+ /*
+ * if lower_dentry is NULL, create the entire
+ * dentry directory structure in branch 'bindex'.
+ * lower_dentry will NOT be null when bindex == bstart
+ * because lookup passed as a negative unionfs dentry
+ * pointing to a lone negative underlying dentry.
+ */
+ lower_dentry = create_parents(parent, dentry,
+ dentry->d_name.name,
+ bindex);
+ if (!lower_dentry || IS_ERR(lower_dentry)) {
+ if (IS_ERR(lower_dentry))
+ err = PTR_ERR(lower_dentry);
+ continue;
+ }
+ }
+
+ lower_parent_dentry = lock_parent(lower_dentry);
+ if (IS_ERR(lower_parent_dentry)) {
+ err = PTR_ERR(lower_parent_dentry);
+ goto out;
+ }
+ /* We shouldn't create things in a read-only branch. */
+ if (!(err = is_robranch_super(dentry->d_sb, bindex)))
+ err = vfs_create(lower_parent_dentry->d_inode,
+ lower_dentry, mode, nd);
+
+ if (err || !lower_dentry->d_inode) {
+ unlock_dir(lower_parent_dentry);
+
+ /* break out of for loop if the error wasn't -EROFS */
+ if (!IS_COPYUP_ERR(err))
+ break;
+ } else {
+ /*
+ * Only INTERPOSE_LOOKUP can return a value other
+ * than 0 on err.
+ */
+ err = PTR_ERR(unionfs_interpose(dentry,
+ parent->i_sb, 0));
+ if (!err) {
+ unionfs_copy_attr_times(parent);
+ fsstack_copy_inode_size(parent,
+ lower_parent_dentry->
+ d_inode);
+ /* update no. of links on parent directory */
+ parent->i_nlink = unionfs_get_nlinks(parent);
+ }
+ unlock_dir(lower_parent_dentry);
+ break;
+ }
+ }
+
+out:
+ dput(wh_dentry);
+ kfree(name);
+
+ if (!err)
+ unionfs_inherit_mnt(dentry);
+ unionfs_unlock_dentry(dentry);
+ unionfs_read_unlock(dentry->d_sb);
+
+ unionfs_check_inode(parent);
+ if (!err)
+ unionfs_check_dentry(dentry->d_parent);
+ unionfs_check_dentry(dentry);
+ return err;
+}
+
+/*
+ * unionfs_lookup is the only special function which takes a dentry, yet we
+ * do NOT want to call __unionfs_d_revalidate_chain because by definition,
+ * we don't have a valid dentry here yet.
+ */
+static struct dentry *unionfs_lookup(struct inode *parent,
+ struct dentry *dentry,
+ struct nameidata *nd)
+{
+ struct path path_save;
+ struct dentry *ret;
+
+ unionfs_read_lock(dentry->d_sb);
+
+ /* save the dentry & vfsmnt from namei */
+ if (nd) {
+ path_save.dentry = nd->dentry;
+ path_save.mnt = nd->mnt;
+ }
+
+ /* The locking is done by unionfs_lookup_backend. */
+ ret = unionfs_lookup_backend(dentry, nd, INTERPOSE_LOOKUP);
+
+ /* restore the dentry & vfsmnt in namei */
+ if (nd) {
+ nd->dentry = path_save.dentry;
+ nd->mnt = path_save.mnt;
+ }
+ if (!IS_ERR(ret)) {
+ if (ret)
+ dentry = ret;
+ /* parent times may have changed */
+ unionfs_copy_attr_times(dentry->d_parent->d_inode);
+ }
+
+ unionfs_check_inode(parent);
+ unionfs_check_dentry(dentry);
+ unionfs_check_dentry(dentry->d_parent);
+ unionfs_read_unlock(dentry->d_sb);
+
+ return ret;
+}
+
+static int unionfs_link(struct dentry *old_dentry, struct inode *dir,
+ struct dentry *new_dentry)
+{
+ int err = 0;
+ struct dentry *lower_old_dentry = NULL;
+ struct dentry *lower_new_dentry = NULL;
+ struct dentry *lower_dir_dentry = NULL;
+ struct dentry *whiteout_dentry;
+ char *name = NULL;
+
+ unionfs_read_lock(old_dentry->d_sb);
+ unionfs_double_lock_dentry(new_dentry, old_dentry);
+
+ if (!__unionfs_d_revalidate_chain(old_dentry, NULL, 0)) {
+ err = -ESTALE;
+ goto out;
+ }
+ if (new_dentry->d_inode &&
+ !__unionfs_d_revalidate_chain(new_dentry, NULL, 0)) {
+ err = -ESTALE;
+ goto out;
+ }
+
+ lower_new_dentry = unionfs_lower_dentry(new_dentry);
+
+ /*
+ * check if whiteout exists in the branch of new dentry, i.e. lookup
+ * .wh.foo first. If present, delete it
+ */
+ name = alloc_whname(new_dentry->d_name.name, new_dentry->d_name.len);
+ if (IS_ERR(name)) {
+ err = PTR_ERR(name);
+ goto out;
+ }
+
+ whiteout_dentry = lookup_one_len(name, lower_new_dentry->d_parent,
+ new_dentry->d_name.len +
+ UNIONFS_WHLEN);
+ if (IS_ERR(whiteout_dentry)) {
+ err = PTR_ERR(whiteout_dentry);
+ goto out;
+ }
+
+ if (!whiteout_dentry->d_inode) {
+ dput(whiteout_dentry);
+ whiteout_dentry = NULL;
+ } else {
+ /* found a .wh.foo entry, unlink it and then call vfs_link() */
+ lower_dir_dentry = lock_parent(whiteout_dentry);
+ err = is_robranch_super(new_dentry->d_sb, dbstart(new_dentry));
+ if (!err)
+ err = vfs_unlink(lower_dir_dentry->d_inode,
+ whiteout_dentry);
+
+ fsstack_copy_attr_times(dir, lower_dir_dentry->d_inode);
+ dir->i_nlink = unionfs_get_nlinks(dir);
+ unlock_dir(lower_dir_dentry);
+ lower_dir_dentry = NULL;
+ dput(whiteout_dentry);
+ if (err)
+ goto out;
+ }
+
+ if (dbstart(old_dentry) != dbstart(new_dentry)) {
+ lower_new_dentry = create_parents(dir, new_dentry,
+ new_dentry->d_name.name,
+ dbstart(old_dentry));
+ err = PTR_ERR(lower_new_dentry);
+ if (IS_COPYUP_ERR(err))
+ goto docopyup;
+ if (!lower_new_dentry || IS_ERR(lower_new_dentry))
+ goto out;
+ }
+ lower_new_dentry = unionfs_lower_dentry(new_dentry);
+ lower_old_dentry = unionfs_lower_dentry(old_dentry);
+
+ BUG_ON(dbstart(old_dentry) != dbstart(new_dentry));
+ lower_dir_dentry = lock_parent(lower_new_dentry);
+ if (!(err = is_robranch(old_dentry)))
+ err = vfs_link(lower_old_dentry, lower_dir_dentry->d_inode,
+ lower_new_dentry);
+ unlock_dir(lower_dir_dentry);
+
+docopyup:
+ if (IS_COPYUP_ERR(err)) {
+ int old_bstart = dbstart(old_dentry);
+ int bindex;
+
+ for (bindex = old_bstart - 1; bindex >= 0; bindex--) {
+ err = copyup_dentry(old_dentry->d_parent->d_inode,
+ old_dentry, old_bstart,
+ bindex, old_dentry->d_name.name,
+ old_dentry->d_name.len, NULL,
+ old_dentry->d_inode->i_size);
+ if (!err) {
+ lower_new_dentry =
+ create_parents(dir, new_dentry,
+ new_dentry->d_name.name,
+ bindex);
+ lower_old_dentry =
+ unionfs_lower_dentry(old_dentry);
+ lower_dir_dentry =
+ lock_parent(lower_new_dentry);
+ /* do vfs_link */
+ err = vfs_link(lower_old_dentry,
+ lower_dir_dentry->d_inode,
+ lower_new_dentry);
+ unlock_dir(lower_dir_dentry);
+ goto check_link;
+ }
+ }
+ goto out;
+ }
+
+check_link:
+ if (err || !lower_new_dentry->d_inode)
+ goto out;
+
+ /* Its a hard link, so use the same inode */
+ new_dentry->d_inode = igrab(old_dentry->d_inode);
+ d_instantiate(new_dentry, new_dentry->d_inode);
+ unionfs_copy_attr_all(dir, lower_new_dentry->d_parent->d_inode);
+ fsstack_copy_inode_size(dir, lower_new_dentry->d_parent->d_inode);
+
+ /* propagate number of hard-links */
+ old_dentry->d_inode->i_nlink = unionfs_get_nlinks(old_dentry->d_inode);
+ /* new dentry's ctime may have changed due to hard-link counts */
+ unionfs_copy_attr_times(new_dentry->d_inode);
+
+out:
+ if (!new_dentry->d_inode)
+ d_drop(new_dentry);
+
+ kfree(name);
+ if (!err)
+ unionfs_inherit_mnt(new_dentry);
+
+ unionfs_unlock_dentry(new_dentry);
+ unionfs_unlock_dentry(old_dentry);
+
+ unionfs_check_inode(dir);
+ unionfs_check_dentry(new_dentry);
+ unionfs_check_dentry(old_dentry);
+ unionfs_read_unlock(old_dentry->d_sb);
+
+ return err;
+}
+
+static int unionfs_symlink(struct inode *dir, struct dentry *dentry,
+ const char *symname)
+{
+ int err = 0;
+ struct dentry *lower_dentry = NULL;
+ struct dentry *whiteout_dentry = NULL;
+ struct dentry *lower_dir_dentry = NULL;
+ umode_t mode;
+ int bindex = 0, bstart;
+ char *name = NULL;
+
+ unionfs_read_lock(dentry->d_sb);
+ unionfs_lock_dentry(dentry);
+
+ if (dentry->d_inode &&
+ !__unionfs_d_revalidate_chain(dentry, NULL, 0)) {
+ err = -ESTALE;
+ goto out;
+ }
+
+ /* We start out in the leftmost branch. */
+ bstart = dbstart(dentry);
+
+ lower_dentry = unionfs_lower_dentry(dentry);
+
+ /*
+ * check if whiteout exists in this branch, i.e. lookup .wh.foo
+ * first. If present, delete it
+ */
+ name = alloc_whname(dentry->d_name.name, dentry->d_name.len);
+ if (IS_ERR(name)) {
+ err = PTR_ERR(name);
+ goto out;
+ }
+
+ whiteout_dentry =
+ lookup_one_len(name, lower_dentry->d_parent,
+ dentry->d_name.len + UNIONFS_WHLEN);
+ if (IS_ERR(whiteout_dentry)) {
+ err = PTR_ERR(whiteout_dentry);
+ goto out;
+ }
+
+ if (!whiteout_dentry->d_inode) {
+ dput(whiteout_dentry);
+ whiteout_dentry = NULL;
+ } else {
+ /*
+ * found a .wh.foo entry, unlink it and then call
+ * vfs_symlink().
+ */
+ lower_dir_dentry = lock_parent(whiteout_dentry);
+
+ if (!(err = is_robranch_super(dentry->d_sb, bstart)))
+ err = vfs_unlink(lower_dir_dentry->d_inode,
+ whiteout_dentry);
+ dput(whiteout_dentry);
+
+ fsstack_copy_attr_times(dir, lower_dir_dentry->d_inode);
+ /* propagate number of hard-links */
+ dir->i_nlink = unionfs_get_nlinks(dir);
+
+ unlock_dir(lower_dir_dentry);
+
+ if (err) {
+ /* exit if the error returned was NOT -EROFS */
+ if (!IS_COPYUP_ERR(err))
+ goto out;
+ /*
+ * should now try to create symlink in the another
+ * branch.
+ */
+ bstart--;
+ }
+ }
+
+ /*
+ * deleted whiteout if it was present, now do a normal vfs_symlink()
+ * with possible recursive directory creation
+ */
+ for (bindex = bstart; bindex >= 0; bindex--) {
+ lower_dentry = unionfs_lower_dentry_idx(dentry, bindex);
+ if (!lower_dentry) {
+ /*
+ * if lower_dentry is NULL, create the entire
+ * dentry directory structure in branch 'bindex'.
+ * lower_dentry will NOT be null when bindex ==
+ * bstart because lookup passed as a negative
+ * unionfs dentry pointing to a lone negative
+ * underlying dentry
+ */
+ lower_dentry = create_parents(dir, dentry,
+ dentry->d_name.name,
+ bindex);
+ if (!lower_dentry || IS_ERR(lower_dentry)) {
+ if (IS_ERR(lower_dentry))
+ err = PTR_ERR(lower_dentry);
+
+ printk(KERN_DEBUG "unionfs: lower dentry "
+ "NULL (or error) for bindex = %d\n",
+ bindex);
+ continue;
+ }
+ }
+
+ lower_dir_dentry = lock_parent(lower_dentry);
+
+ if (!(err = is_robranch_super(dentry->d_sb, bindex))) {
+ mode = S_IALLUGO;
+ err =
+ vfs_symlink(lower_dir_dentry->d_inode,
+ lower_dentry, symname, mode);
+ }
+ unlock_dir(lower_dir_dentry);
+
+ if (err || !lower_dentry->d_inode) {
+ /*
+ * break out of for loop if error returned was NOT
+ * -EROFS.
+ */
+ if (!IS_COPYUP_ERR(err))
+ break;
+ } else {
+ /*
+ * Only INTERPOSE_LOOKUP can return a value other
+ * than 0 on err.
+ */
+ err = PTR_ERR(unionfs_interpose(dentry,
+ dir->i_sb, 0));
+ if (!err) {
+ fsstack_copy_attr_times(dir,
+ lower_dir_dentry->
+ d_inode);
+ fsstack_copy_inode_size(dir,
+ lower_dir_dentry->
+ d_inode);
+ /*
+ * update number of links on parent
+ * directory.
+ */
+ dir->i_nlink = unionfs_get_nlinks(dir);
+ }
+ break;
+ }
+ }
+
+out:
+ if (!dentry->d_inode)
+ d_drop(dentry);
+
+ kfree(name);
+ if (!err)
+ unionfs_inherit_mnt(dentry);
+ unionfs_unlock_dentry(dentry);
+
+ unionfs_check_inode(dir);
+ unionfs_check_dentry(dentry);
+ unionfs_read_unlock(dentry->d_sb);
+
+ return err;
+}
+
+static int unionfs_mkdir(struct inode *parent, struct dentry *dentry, int mode)
+{
+ int err = 0;
+ struct dentry *lower_dentry = NULL, *whiteout_dentry = NULL;
+ struct dentry *lower_parent_dentry = NULL;
+ int bindex = 0, bstart;
+ char *name = NULL;
+ int whiteout_unlinked = 0;
+ struct sioq_args args;
+
+ unionfs_read_lock(dentry->d_sb);
+ unionfs_lock_dentry(dentry);
+
+ if (dentry->d_inode &&
+ !__unionfs_d_revalidate_chain(dentry, NULL, 0)) {
+ err = -ESTALE;
+ goto out;
+ }
+
+ bstart = dbstart(dentry);
+
+ lower_dentry = unionfs_lower_dentry(dentry);
+
+ /*
+ * check if whiteout exists in this branch, i.e. lookup .wh.foo
+ * first.
+ */
+ name = alloc_whname(dentry->d_name.name, dentry->d_name.len);
+ if (IS_ERR(name)) {
+ err = PTR_ERR(name);
+ goto out;
+ }
+
+ whiteout_dentry = lookup_one_len(name, lower_dentry->d_parent,
+ dentry->d_name.len + UNIONFS_WHLEN);
+ if (IS_ERR(whiteout_dentry)) {
+ err = PTR_ERR(whiteout_dentry);
+ goto out;
+ }
+
+ if (!whiteout_dentry->d_inode) {
+ dput(whiteout_dentry);
+ whiteout_dentry = NULL;
+ } else {
+ lower_parent_dentry = lock_parent(whiteout_dentry);
+
+ /* found a.wh.foo entry, remove it then do vfs_mkdir */
+ if (!(err = is_robranch_super(dentry->d_sb, bstart))) {
+ args.unlink.parent = lower_parent_dentry->d_inode;
+ args.unlink.dentry = whiteout_dentry;
+ run_sioq(__unionfs_unlink, &args);
+ err = args.err;
+ }
+ dput(whiteout_dentry);
+
+ unlock_dir(lower_parent_dentry);
+
+ if (err) {
+ /* exit if the error returned was NOT -EROFS */
+ if (!IS_COPYUP_ERR(err))
+ goto out;
+ bstart--;
+ } else
+ whiteout_unlinked = 1;
+ }
+
+ for (bindex = bstart; bindex >= 0; bindex--) {
+ int i;
+ int bend = dbend(dentry);
+
+ if (is_robranch_super(dentry->d_sb, bindex))
+ continue;
+
+ lower_dentry = unionfs_lower_dentry_idx(dentry, bindex);
+ if (!lower_dentry) {
+ lower_dentry = create_parents(parent, dentry,
+ dentry->d_name.name,
+ bindex);
+ if (!lower_dentry || IS_ERR(lower_dentry)) {
+ printk(KERN_DEBUG "unionfs: lower dentry "
+ " NULL for bindex = %d\n", bindex);
+ continue;
+ }
+ }
+
+ lower_parent_dentry = lock_parent(lower_dentry);
+
+ if (IS_ERR(lower_parent_dentry)) {
+ err = PTR_ERR(lower_parent_dentry);
+ goto out;
+ }
+
+ err = vfs_mkdir(lower_parent_dentry->d_inode, lower_dentry,
+ mode);
+
+ unlock_dir(lower_parent_dentry);
+
+ /* did the mkdir succeed? */
+ if (err)
+ break;
+
+ for (i = bindex + 1; i < bend; i++) {
+ if (unionfs_lower_dentry_idx(dentry, i)) {
+ dput(unionfs_lower_dentry_idx(dentry, i));
+ unionfs_set_lower_dentry_idx(dentry, i, NULL);
+ }
+ }
+ set_dbend(dentry, bindex);
+
+ /*
+ * Only INTERPOSE_LOOKUP can return a value other than 0 on
+ * err.
+ */
+ err = PTR_ERR(unionfs_interpose(dentry, parent->i_sb, 0));
+ if (!err) {
+ unionfs_copy_attr_times(parent);
+ fsstack_copy_inode_size(parent,
+ lower_parent_dentry->d_inode);
+
+ /* update number of links on parent directory */
+ parent->i_nlink = unionfs_get_nlinks(parent);
+ }
+
+ err = make_dir_opaque(dentry, dbstart(dentry));
+ if (err) {
+ printk(KERN_ERR "unionfs: mkdir: error creating "
+ ".wh.__dir_opaque: %d\n", err);
+ goto out;
+ }
+
+ /* we are done! */
+ break;
+ }
+
+out:
+ if (!dentry->d_inode)
+ d_drop(dentry);
+
+ kfree(name);
+
+ if (!err)
+ unionfs_copy_attr_times(dentry->d_inode);
+ unionfs_unlock_dentry(dentry);
+ unionfs_check_inode(parent);
+ unionfs_check_dentry(dentry);
+ unionfs_read_unlock(dentry->d_sb);
+
+ return err;
+}
+
+static int unionfs_mknod(struct inode *dir, struct dentry *dentry, int mode,
+ dev_t dev)
+{
+ int err = 0;
+ struct dentry *lower_dentry = NULL, *whiteout_dentry = NULL;
+ struct dentry *lower_parent_dentry = NULL;
+ int bindex = 0, bstart;
+ char *name = NULL;
+ int whiteout_unlinked = 0;
+
+ unionfs_read_lock(dentry->d_sb);
+ unionfs_lock_dentry(dentry);
+
+ if (dentry->d_inode &&
+ !__unionfs_d_revalidate_chain(dentry, NULL, 0)) {
+ err = -ESTALE;
+ goto out;
+ }
+
+ bstart = dbstart(dentry);
+
+ lower_dentry = unionfs_lower_dentry(dentry);
+
+ /*
+ * check if whiteout exists in this branch, i.e. lookup .wh.foo
+ * first.
+ */
+ name = alloc_whname(dentry->d_name.name, dentry->d_name.len);
+ if (IS_ERR(name)) {
+ err = PTR_ERR(name);
+ goto out;
+ }
+
+ whiteout_dentry = lookup_one_len(name, lower_dentry->d_parent,
+ dentry->d_name.len + UNIONFS_WHLEN);
+ if (IS_ERR(whiteout_dentry)) {
+ err = PTR_ERR(whiteout_dentry);
+ goto out;
+ }
+
+ if (!whiteout_dentry->d_inode) {
+ dput(whiteout_dentry);
+ whiteout_dentry = NULL;
+ } else {
+ /* found .wh.foo, unlink it */
+ lower_parent_dentry = lock_parent(whiteout_dentry);
+
+ /* found a.wh.foo entry, remove it then do vfs_mkdir */
+ if (!(err = is_robranch_super(dentry->d_sb, bstart)))
+ err = vfs_unlink(lower_parent_dentry->d_inode,
+ whiteout_dentry);
+ dput(whiteout_dentry);
+
+ unlock_dir(lower_parent_dentry);
+
+ if (err) {
+ if (!IS_COPYUP_ERR(err))
+ goto out;
+ bstart--;
+ } else
+ whiteout_unlinked = 1;
+ }
+
+ for (bindex = bstart; bindex >= 0; bindex--) {
+ if (is_robranch_super(dentry->d_sb, bindex))
+ continue;
+
+ lower_dentry = unionfs_lower_dentry_idx(dentry, bindex);
+ if (!lower_dentry) {
+ lower_dentry = create_parents(dir, dentry,
+ dentry->d_name.name,
+ bindex);
+ if (IS_ERR(lower_dentry)) {
+ printk(KERN_DEBUG "unionfs: failed to create "
+ "parents on %d, err = %ld\n",
+ bindex, PTR_ERR(lower_dentry));
+ continue;
+ }
+ }
+
+ lower_parent_dentry = lock_parent(lower_dentry);
+ if (IS_ERR(lower_parent_dentry)) {
+ err = PTR_ERR(lower_parent_dentry);
+ goto out;
+ }
+
+ err = vfs_mknod(lower_parent_dentry->d_inode,
+ lower_dentry, mode, dev);
+
+ if (err) {
+ unlock_dir(lower_parent_dentry);
+ break;
+ }
+
+ /*
+ * Only INTERPOSE_LOOKUP can return a value other than 0 on
+ * err.
+ */
+ err = PTR_ERR(unionfs_interpose(dentry, dir->i_sb, 0));
+ if (!err) {
+ fsstack_copy_attr_times(dir,
+ lower_parent_dentry->d_inode);
+ fsstack_copy_inode_size(dir,
+ lower_parent_dentry->d_inode);
+ /* update number of links on parent directory */
+ dir->i_nlink = unionfs_get_nlinks(dir);
+ }
+ unlock_dir(lower_parent_dentry);
+
+ break;
+ }
+
+out:
+ if (!dentry->d_inode)
+ d_drop(dentry);
+
+ kfree(name);
+
+ if (!err)
+ unionfs_inherit_mnt(dentry);
+ unionfs_unlock_dentry(dentry);
+
+ unionfs_check_inode(dir);
+ unionfs_check_dentry(dentry);
+ unionfs_read_unlock(dentry->d_sb);
+
+ return err;
+}
+
+static int unionfs_readlink(struct dentry *dentry, char __user *buf,
+ int bufsiz)
+{
+ int err;
+ struct dentry *lower_dentry;
+
+ unionfs_read_lock(dentry->d_sb);
+ unionfs_lock_dentry(dentry);
+
+ if (!__unionfs_d_revalidate_chain(dentry, NULL, 0)) {
+ err = -ESTALE;
+ goto out;
+ }
+
+ lower_dentry = unionfs_lower_dentry(dentry);
+
+ if (!lower_dentry->d_inode->i_op ||
+ !lower_dentry->d_inode->i_op->readlink) {
+ err = -EINVAL;
+ goto out;
+ }
+
+ err = lower_dentry->d_inode->i_op->readlink(lower_dentry,
+ buf, bufsiz);
+ if (err > 0)
+ fsstack_copy_attr_atime(dentry->d_inode,
+ lower_dentry->d_inode);
+
+out:
+ unionfs_unlock_dentry(dentry);
+ unionfs_check_dentry(dentry);
+ unionfs_read_unlock(dentry->d_sb);
+
+ return err;
+}
+
+/*
+ * unionfs_follow_link takes a dentry, but it is simple. It only needs to
+ * allocate some memory and then call our ->readlink method. Our
+ * unionfs_readlink *does* lock our dentry and revalidate the dentry.
+ * Therefore, we do not have to lock our dentry here, to prevent a deadlock;
+ * nor do we need to revalidate it either. It is safe to not lock our
+ * dentry here, nor revalidate it, because unionfs_follow_link does not do
+ * anything (prior to calling ->readlink) which could become inconsistent
+ * due to branch management.
+ */
+static void *unionfs_follow_link(struct dentry *dentry, struct nameidata *nd)
+{
+ char *buf;
+ int len = PAGE_SIZE, err;
+ mm_segment_t old_fs;
+
+ unionfs_read_lock(dentry->d_sb);
+
+ /* This is freed by the put_link method assuming a successful call. */
+ buf = kmalloc(len, GFP_KERNEL);
+ if (!buf) {
+ err = -ENOMEM;
+ goto out;
+ }
+
+ /* read the symlink, and then we will follow it */
+ old_fs = get_fs();
+ set_fs(KERNEL_DS);
+ err = dentry->d_inode->i_op->readlink(dentry, (char __user *)buf, len);
+ set_fs(old_fs);
+ if (err < 0) {
+ kfree(buf);
+ buf = NULL;
+ goto out;
+ }
+ buf[err] = 0;
+ nd_set_link(nd, buf);
+ err = 0;
+
+out:
+ unionfs_check_dentry(dentry);
+ unionfs_read_unlock(dentry->d_sb);
+ return ERR_PTR(err);
+}
+
+/* FIXME: We may not have to lock here */
+static void unionfs_put_link(struct dentry *dentry, struct nameidata *nd,
+ void *cookie)
+{
+ unionfs_read_lock(dentry->d_sb);
+
+ unionfs_lock_dentry(dentry);
+ if (!__unionfs_d_revalidate_chain(dentry, nd, 0))
+ printk("unionfs: put_link failed to revalidate dentry\n");
+ unionfs_unlock_dentry(dentry);
+
+ unionfs_check_dentry(dentry);
+ kfree(nd_get_link(nd));
+ unionfs_read_unlock(dentry->d_sb);
+}
+
+/*
+ * Basically copied from the kernel vfs permission(), but we've changed
+ * the following:
+ * (1) the IS_RDONLY check is skipped, and
+ * (2) We return 0 (success) if the non-leftmost branch is mounted
+ * readonly, to allow copyup to work.
+ * (3) we do call security_inode_permission, and therefore security inside
+ * SELinux, etc. are performed.
+ */
+static int inode_permission(struct super_block *sb, struct inode *inode, int mask,
+ struct nameidata *nd, int bindex)
+{
+ int retval, submask;
+
+ if (mask & MAY_WRITE) {
+ umode_t mode = inode->i_mode;
+ /* The first branch is allowed to be really readonly. */
+ if (bindex == 0 &&
+ IS_RDONLY(inode) &&
+ (S_ISREG(mode) || S_ISDIR(mode) || S_ISLNK(mode)))
+ return -EROFS;
+ /*
+ * Nobody gets write access to an immutable file.
+ */
+ if (IS_IMMUTABLE(inode))
+ return -EACCES;
+ /*
+ * For all other branches than the first one, we ignore
+ * EROFS or if the branch is mounted as readonly, to let
+ * copyup take place.
+ */
+ if (bindex > 0 &&
+ is_robranch_super(sb, bindex) &&
+ (S_ISREG(mode) || S_ISDIR(mode) || S_ISLNK(mode)))
+ return 0;
+ }
+
+ /* Ordinary permission routines do not understand MAY_APPEND. */
+ submask = mask & ~MAY_APPEND;
+ if (inode->i_op && inode->i_op->permission)
+ retval = inode->i_op->permission(inode, submask, nd);
+ else
+ retval = generic_permission(inode, submask, NULL);
+
+ if (retval && retval != -EROFS) /* ignore EROFS */
+ return retval;
+
+ retval = security_inode_permission(inode, mask, nd);
+ return ((retval == -EROFS) ? 0 : retval); /* ignore EROFS */
+}
+
+/*
+ * Don't grab the superblock read-lock in unionfs_permission, which prevents
+ * a deadlock with the branch-management "add branch" code (which grabbed
+ * the write lock). It is safe to not grab the read lock here, because even
+ * with branch management taking place, there is no chance that
+ * unionfs_permission, or anything it calls, will use stale branch
+ * information.
+ */
+static int unionfs_permission(struct inode *inode, int mask,
+ struct nameidata *nd)
+{
+ struct inode *lower_inode = NULL;
+ int err = 0;
+ int bindex, bstart, bend;
+ const int is_file = !S_ISDIR(inode->i_mode);
+ const int write_mask = (mask & MAY_WRITE) && !(mask & MAY_READ);
+
+ bstart = ibstart(inode);
+ bend = ibend(inode);
+ if (bstart < 0 || bend < 0) {
+ /*
+ * With branch-management, we can get a stale inode here.
+ * If so, we return ESTALE back to link_path_walk, which
+ * would discard the dcache entry and re-lookup the
+ * dentry+inode. This should be equivalent to issuing
+ * __unionfs_d_revalidate_chain on nd.dentry here.
+ */
+ err = -ESTALE; /* force revalidate */
+ goto out;
+ }
+
+ for (bindex = bstart; bindex <= bend; bindex++) {
+ lower_inode = unionfs_lower_inode_idx(inode, bindex);
+ if (!lower_inode)
+ continue;
+
+ /*
+ * check the condition for D-F-D underlying files/directories,
+ * we don't have to check for files, if we are checking for
+ * directories.
+ */
+ if (!is_file && !S_ISDIR(lower_inode->i_mode))
+ continue;
+
+ /*
+ * We use our own special version of permission, such that
+ * only the first branch returns -EROFS.
+ */
+ err = inode_permission(inode->i_sb, lower_inode, mask, nd, bindex);
+
+ /*
+ * The permissions are an intersection of the overall directory
+ * permissions, so we fail if one fails.
+ */
+ if (err)
+ goto out;
+
+ /* only the leftmost file matters. */
+ if (is_file || write_mask) {
+ if (is_file && write_mask) {
+ err = get_write_access(lower_inode);
+ if (!err)
+ put_write_access(lower_inode);
+ }
+ break;
+ }
+ }
+ /* sync times which may have changed (asynchronously) below */
+ unionfs_copy_attr_times(inode);
+
+out:
+ unionfs_check_inode(inode);
+ return err;
+}
+
+static int unionfs_setattr(struct dentry *dentry, struct iattr *ia)
+{
+ int err = 0;
+ struct dentry *lower_dentry;
+ struct inode *inode = NULL;
+ struct inode *lower_inode = NULL;
+ int bstart, bend, bindex;
+ int i;
+ int copyup = 0;
+
+ unionfs_read_lock(dentry->d_sb);
+ unionfs_lock_dentry(dentry);
+
+ if (!__unionfs_d_revalidate_chain(dentry, NULL, 0)) {
+ err = -ESTALE;
+ goto out;
+ }
+
+ bstart = dbstart(dentry);
+ bend = dbend(dentry);
+ inode = dentry->d_inode;
+
+ for (bindex = bstart; (bindex <= bend) || (bindex == bstart);
+ bindex++) {
+ lower_dentry = unionfs_lower_dentry_idx(dentry, bindex);
+ if (!lower_dentry)
+ continue;
+ BUG_ON(lower_dentry->d_inode == NULL);
+
+ /* If the file is on a read only branch */
+ if (is_robranch_super(dentry->d_sb, bindex)
+ || IS_RDONLY(lower_dentry->d_inode)) {
+ if (copyup || (bindex != bstart))
+ continue;
+ /* Only if its the leftmost file, copyup the file */
+ for (i = bstart - 1; i >= 0; i--) {
+ loff_t size = dentry->d_inode->i_size;
+ if (ia->ia_valid & ATTR_SIZE)
+ size = ia->ia_size;
+ err = copyup_dentry(dentry->d_parent->d_inode,
+ dentry, bstart, i,
+ dentry->d_name.name,
+ dentry->d_name.len,
+ NULL, size);
+
+ if (!err) {
+ copyup = 1;
+ lower_dentry =
+ unionfs_lower_dentry(dentry);
+ break;
+ }
+ /*
+ * if error is in the leftmost branch, pass
+ * it up.
+ */
+ if (i == 0)
+ goto out;
+ }
+
+ }
+ err = notify_change(lower_dentry, ia);
+ if (err)
+ goto out;
+ break;
+ }
+
+ /* for mmap */
+ if (ia->ia_valid & ATTR_SIZE) {
+ if (ia->ia_size != i_size_read(inode)) {
+ err = vmtruncate(inode, ia->ia_size);
+ if (err)
+ printk("unionfs_setattr: vmtruncate failed\n");
+ }
+ }
+
+ /* get the size from the first lower inode */
+ lower_inode = unionfs_lower_inode(inode);
+ unionfs_copy_attr_all(inode, lower_inode);
+ fsstack_copy_inode_size(inode, lower_inode);
+ /* if setattr succeeded, then parent dir may have changed */
+ unionfs_copy_attr_times(dentry->d_parent->d_inode);
+out:
+ unionfs_unlock_dentry(dentry);
+ unionfs_check_dentry(dentry);
+ unionfs_check_dentry(dentry->d_parent);
+ unionfs_read_unlock(dentry->d_sb);
+
+ return err;
+}
+
+struct inode_operations unionfs_symlink_iops = {
+ .readlink = unionfs_readlink,
+ .permission = unionfs_permission,
+ .follow_link = unionfs_follow_link,
+ .setattr = unionfs_setattr,
+ .put_link = unionfs_put_link,
+};
+
+struct inode_operations unionfs_dir_iops = {
+ .create = unionfs_create,
+ .lookup = unionfs_lookup,
+ .link = unionfs_link,
+ .unlink = unionfs_unlink,
+ .symlink = unionfs_symlink,
+ .mkdir = unionfs_mkdir,
+ .rmdir = unionfs_rmdir,
+ .mknod = unionfs_mknod,
+ .rename = unionfs_rename,
+ .permission = unionfs_permission,
+ .setattr = unionfs_setattr,
+#ifdef CONFIG_UNION_FS_XATTR
+ .setxattr = unionfs_setxattr,
+ .getxattr = unionfs_getxattr,
+ .removexattr = unionfs_removexattr,
+ .listxattr = unionfs_listxattr,
+#endif /* CONFIG_UNION_FS_XATTR */
+};
+
+struct inode_operations unionfs_main_iops = {
+ .permission = unionfs_permission,
+ .setattr = unionfs_setattr,
+#ifdef CONFIG_UNION_FS_XATTR
+ .setxattr = unionfs_setxattr,
+ .getxattr = unionfs_getxattr,
+ .removexattr = unionfs_removexattr,
+ .listxattr = unionfs_listxattr,
+#endif /* CONFIG_UNION_FS_XATTR */
+};
diff --git a/fs/unionfs/lookup.c b/fs/unionfs/lookup.c
new file mode 100644
index 0000000..da991b3
--- /dev/null
+++ b/fs/unionfs/lookup.c
@@ -0,0 +1,577 @@
+/*
+ * Copyright (c) 2003-2007 Erez Zadok
+ * Copyright (c) 2003-2006 Charles P. Wright
+ * Copyright (c) 2005-2007 Josef 'Jeff' Sipek
+ * Copyright (c) 2005-2006 Junjiro Okajima
+ * Copyright (c) 2005 Arun M. Krishnakumar
+ * Copyright (c) 2004-2006 David P. Quigley
+ * Copyright (c) 2003-2004 Mohammad Nayyer Zubair
+ * Copyright (c) 2003 Puja Gupta
+ * Copyright (c) 2003 Harikesavan Krishnan
+ * Copyright (c) 2003-2007 Stony Brook University
+ * Copyright (c) 2003-2007 The Research Foundation of SUNY
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include "union.h"
+
+static int realloc_dentry_private_data(struct dentry *dentry);
+
+/* is the filename valid == !(whiteout for a file or opaque dir marker) */
+static int is_validname(const char *name)
+{
+ if (!strncmp(name, UNIONFS_WHPFX, UNIONFS_WHLEN))
+ return 0;
+ if (!strncmp(name, UNIONFS_DIR_OPAQUE_NAME,
+ sizeof(UNIONFS_DIR_OPAQUE_NAME) - 1))
+ return 0;
+ return 1;
+}
+
+/* The rest of these are utility functions for lookup. */
+static noinline int is_opaque_dir(struct dentry *dentry, int bindex)
+{
+ int err = 0;
+ struct dentry *lower_dentry;
+ struct dentry *wh_lower_dentry;
+ struct inode *lower_inode;
+ struct sioq_args args;
+
+ lower_dentry = unionfs_lower_dentry_idx(dentry, bindex);
+ lower_inode = lower_dentry->d_inode;
+
+ BUG_ON(!S_ISDIR(lower_inode->i_mode));
+
+ mutex_lock(&lower_inode->i_mutex);
+
+ if (!permission(lower_inode, MAY_EXEC, NULL))
+ wh_lower_dentry =
+ lookup_one_len(UNIONFS_DIR_OPAQUE, lower_dentry,
+ sizeof(UNIONFS_DIR_OPAQUE) - 1);
+ else {
+ args.is_opaque.dentry = lower_dentry;
+ run_sioq(__is_opaque_dir, &args);
+ wh_lower_dentry = args.ret;
+ }
+
+ mutex_unlock(&lower_inode->i_mutex);
+
+ if (IS_ERR(wh_lower_dentry)) {
+ err = PTR_ERR(wh_lower_dentry);
+ goto out;
+ }
+
+ /* This is an opaque dir iff wh_lower_dentry is positive */
+ err = !!wh_lower_dentry->d_inode;
+
+ dput(wh_lower_dentry);
+out:
+ return err;
+}
+
+/*
+ * Main (and complex) driver function for Unionfs's lookup
+ *
+ * Returns: NULL (ok), ERR_PTR if an error occurred, or a non-null non-error
+ * PTR if d_splice returned a different dentry.
+ */
+struct dentry *unionfs_lookup_backend(struct dentry *dentry,
+ struct nameidata *nd, int lookupmode)
+{
+ int err = 0;
+ struct dentry *lower_dentry = NULL;
+ struct dentry *wh_lower_dentry = NULL;
+ struct dentry *lower_dir_dentry = NULL;
+ struct dentry *parent_dentry = NULL;
+ struct dentry *d_interposed = NULL;
+ int bindex, bstart, bend, bopaque;
+ int dentry_count = 0; /* Number of positive dentries. */
+ int first_dentry_offset = -1; /* -1 is uninitialized */
+ struct dentry *first_dentry = NULL;
+ struct dentry *first_lower_dentry = NULL;
+ struct vfsmount *first_lower_mnt = NULL;
+ int locked_parent = 0;
+ int locked_child = 0;
+ int allocated_new_info = 0;
+ int opaque;
+ char *whname = NULL;
+ const char *name;
+ int namelen;
+
+ /*
+ * We should already have a lock on this dentry in the case of a
+ * partial lookup, or a revalidation. Otherwise it is returned from
+ * new_dentry_private_data already locked.
+ */
+ if (lookupmode == INTERPOSE_PARTIAL || lookupmode == INTERPOSE_REVAL ||
+ lookupmode == INTERPOSE_REVAL_NEG)
+ verify_locked(dentry);
+ else {
+ BUG_ON(UNIONFS_D(dentry) != NULL);
+ locked_child = 1;
+ }
+
+ switch(lookupmode) {
+ case INTERPOSE_PARTIAL:
+ break;
+ case INTERPOSE_LOOKUP:
+ if ((err = new_dentry_private_data(dentry)))
+ goto out;
+ allocated_new_info = 1;
+ break;
+ default:
+ if ((err = realloc_dentry_private_data(dentry)))
+ goto out;
+ allocated_new_info = 1;
+ break;
+ }
+
+ /* must initialize dentry operations */
+ dentry->d_op = &unionfs_dops;
+
+ parent_dentry = dget_parent(dentry);
+ /* We never partial lookup the root directory. */
+ if (parent_dentry != dentry) {
+ unionfs_lock_dentry(parent_dentry);
+ locked_parent = 1;
+ } else {
+ dput(parent_dentry);
+ parent_dentry = NULL;
+ goto out;
+ }
+
+ name = dentry->d_name.name;
+ namelen = dentry->d_name.len;
+
+ /* No dentries should get created for possible whiteout names. */
+ if (!is_validname(name)) {
+ err = -EPERM;
+ goto out_free;
+ }
+
+ /* Now start the actual lookup procedure. */
+ bstart = dbstart(parent_dentry);
+ bend = dbend(parent_dentry);
+ bopaque = dbopaque(parent_dentry);
+ BUG_ON(bstart < 0);
+
+ /*
+ * It would be ideal if we could convert partial lookups to only have
+ * to do this work when they really need to. It could probably improve
+ * performance quite a bit, and maybe simplify the rest of the code.
+ */
+ if (lookupmode == INTERPOSE_PARTIAL) {
+ bstart++;
+ if ((bopaque != -1) && (bopaque < bend))
+ bend = bopaque;
+ }
+
+ for (bindex = bstart; bindex <= bend; bindex++) {
+ lower_dentry = unionfs_lower_dentry_idx(dentry, bindex);
+ if (lookupmode == INTERPOSE_PARTIAL && lower_dentry)
+ continue;
+ BUG_ON(lower_dentry != NULL);
+
+ lower_dir_dentry =
+ unionfs_lower_dentry_idx(parent_dentry, bindex);
+
+ /* if the parent lower dentry does not exist skip this */
+ if (!(lower_dir_dentry && lower_dir_dentry->d_inode))
+ continue;
+
+ /* also skip it if the parent isn't a directory. */
+ if (!S_ISDIR(lower_dir_dentry->d_inode->i_mode))
+ continue;
+
+ /* Reuse the whiteout name because its value doesn't change. */
+ if (!whname) {
+ whname = alloc_whname(name, namelen);
+ if (IS_ERR(whname)) {
+ err = PTR_ERR(whname);
+ goto out_free;
+ }
+ }
+
+ /* check if whiteout exists in this branch: lookup .wh.foo */
+ wh_lower_dentry = lookup_one_len(whname, lower_dir_dentry,
+ namelen + UNIONFS_WHLEN);
+ if (IS_ERR(wh_lower_dentry)) {
+ dput(first_lower_dentry);
+ unionfs_mntput(first_dentry, first_dentry_offset);
+ err = PTR_ERR(wh_lower_dentry);
+ goto out_free;
+ }
+
+ if (wh_lower_dentry->d_inode) {
+ /* We found a whiteout so lets give up. */
+ if (S_ISREG(wh_lower_dentry->d_inode->i_mode)) {
+ set_dbend(dentry, bindex);
+ set_dbopaque(dentry, bindex);
+ dput(wh_lower_dentry);
+ break;
+ }
+ err = -EIO;
+ printk(KERN_NOTICE "unionfs: EIO: invalid whiteout "
+ "entry type %d.\n",
+ wh_lower_dentry->d_inode->i_mode);
+ dput(wh_lower_dentry);
+ dput(first_lower_dentry);
+ unionfs_mntput(first_dentry, first_dentry_offset);
+ goto out_free;
+ }
+
+ dput(wh_lower_dentry);
+ wh_lower_dentry = NULL;
+
+ /* Now do regular lookup; lookup foo */
+ nd->dentry = unionfs_lower_dentry_idx(dentry, bindex);
+ /* FIXME: fix following line for mount point crossing */
+ nd->mnt = unionfs_lower_mnt_idx(parent_dentry, bindex);
+
+ lower_dentry = lookup_one_len_nd(name, lower_dir_dentry,
+ namelen, nd);
+ if (IS_ERR(lower_dentry)) {
+ dput(first_lower_dentry);
+ unionfs_mntput(first_dentry, first_dentry_offset);
+ err = PTR_ERR(lower_dentry);
+ goto out_free;
+ }
+
+ /*
+ * Store the first negative dentry specially, because if they
+ * are all negative we need this for future creates.
+ */
+ if (!lower_dentry->d_inode) {
+ if (!first_lower_dentry && (dbstart(dentry) == -1)) {
+ first_lower_dentry = lower_dentry;
+ /*
+ * FIXME: following line needs to be changed
+ * to allow mount-point crossing
+ */
+ first_dentry = parent_dentry;
+ first_lower_mnt =
+ unionfs_mntget(parent_dentry, bindex);
+ first_dentry_offset = bindex;
+ } else
+ dput(lower_dentry);
+
+ continue;
+ }
+
+ /* number of positive dentries */
+ dentry_count++;
+
+ /* store underlying dentry */
+ if (dbstart(dentry) == -1)
+ set_dbstart(dentry, bindex);
+ unionfs_set_lower_dentry_idx(dentry, bindex, lower_dentry);
+ /*
+ * FIXME: the following line needs to get fixed to allow
+ * mount-point crossing
+ */
+ unionfs_set_lower_mnt_idx(dentry, bindex,
+ unionfs_mntget(parent_dentry,
+ bindex));
+ set_dbend(dentry, bindex);
+
+ /* update parent directory's atime with the bindex */
+ fsstack_copy_attr_atime(parent_dentry->d_inode,
+ lower_dir_dentry->d_inode);
+
+ /* We terminate file lookups here. */
+ if (!S_ISDIR(lower_dentry->d_inode->i_mode)) {
+ if (lookupmode == INTERPOSE_PARTIAL)
+ continue;
+ if (dentry_count == 1)
+ goto out_positive;
+ /* This can only happen with mixed D-*-F-* */
+ BUG_ON(!S_ISDIR(unionfs_lower_dentry(dentry)->
+ d_inode->i_mode));
+ continue;
+ }
+
+ opaque = is_opaque_dir(dentry, bindex);
+ if (opaque < 0) {
+ dput(first_lower_dentry);
+ unionfs_mntput(first_dentry, first_dentry_offset);
+ err = opaque;
+ goto out_free;
+ } else if (opaque) {
+ set_dbend(dentry, bindex);
+ set_dbopaque(dentry, bindex);
+ break;
+ }
+ }
+
+ if (dentry_count)
+ goto out_positive;
+ else
+ goto out_negative;
+
+out_negative:
+ if (lookupmode == INTERPOSE_PARTIAL)
+ goto out;
+
+ /* If we've only got negative dentries, then use the leftmost one. */
+ if (lookupmode == INTERPOSE_REVAL) {
+ if (dentry->d_inode)
+ UNIONFS_I(dentry->d_inode)->stale = 1;
+ goto out;
+ }
+ /* This should only happen if we found a whiteout. */
+ if (first_dentry_offset == -1) {
+ nd->dentry = dentry;
+ /* FIXME: fix following line for mount point crossing */
+ nd->mnt = unionfs_lower_mnt_idx(parent_dentry, bindex);
+
+ first_lower_dentry =
+ lookup_one_len_nd(name, lower_dir_dentry,
+ namelen, nd);
+ first_dentry_offset = bindex;
+ if (IS_ERR(first_lower_dentry)) {
+ err = PTR_ERR(first_lower_dentry);
+ goto out;
+ }
+
+ /*
+ * FIXME: the following line needs to be changed to allow
+ * mount-point crossing
+ */
+ first_dentry = dentry;
+ first_lower_mnt = unionfs_mntget(dentry->d_sb->s_root,
+ bindex);
+ }
+ unionfs_set_lower_dentry_idx(dentry, first_dentry_offset,
+ first_lower_dentry);
+ unionfs_set_lower_mnt_idx(dentry, first_dentry_offset,
+ first_lower_mnt);
+ set_dbstart(dentry, first_dentry_offset);
+ set_dbend(dentry, first_dentry_offset);
+
+ if (lookupmode == INTERPOSE_REVAL_NEG)
+ BUG_ON(dentry->d_inode != NULL);
+ else
+ d_add(dentry, NULL);
+ goto out;
+
+/* This part of the code is for positive dentries. */
+out_positive:
+ BUG_ON(dentry_count <= 0);
+
+ /*
+ * If we're holding onto the first negative dentry & corresponding
+ * vfsmount - throw it out.
+ */
+ dput(first_lower_dentry);
+ unionfs_mntput(first_dentry, first_dentry_offset);
+
+ /* Partial lookups need to re-interpose, or throw away older negs. */
+ if (lookupmode == INTERPOSE_PARTIAL) {
+ if (dentry->d_inode) {
+ unionfs_reinterpose(dentry);
+ goto out;
+ }
+
+ /*
+ * This somehow turned positive, so it is as if we had a
+ * negative revalidation.
+ */
+ lookupmode = INTERPOSE_REVAL_NEG;
+
+ update_bstart(dentry);
+ bstart = dbstart(dentry);
+ bend = dbend(dentry);
+ }
+
+ /*
+ * Interpose can return a dentry if d_splice returned a different
+ * dentry.
+ */
+ d_interposed = unionfs_interpose(dentry, dentry->d_sb, lookupmode);
+ if (IS_ERR(d_interposed))
+ err = PTR_ERR(d_interposed);
+ else if (d_interposed)
+ dentry = d_interposed;
+
+ if (err)
+ goto out_drop;
+
+ goto out;
+
+out_drop:
+ d_drop(dentry);
+
+out_free:
+ /* should dput all the underlying dentries on error condition */
+ bstart = dbstart(dentry);
+ if (bstart >= 0) {
+ bend = dbend(dentry);
+ for (bindex = bstart; bindex <= bend; bindex++) {
+ dput(unionfs_lower_dentry_idx(dentry, bindex));
+ unionfs_mntput(dentry, bindex);
+ }
+ }
+ kfree(UNIONFS_D(dentry)->lower_paths);
+ UNIONFS_D(dentry)->lower_paths = NULL;
+ set_dbstart(dentry, -1);
+ set_dbend(dentry, -1);
+
+out:
+ if (!err && UNIONFS_D(dentry)) {
+ BUG_ON(dbend(dentry) > UNIONFS_D(dentry)->bcount);
+ BUG_ON(dbend(dentry) > sbmax(dentry->d_sb));
+ BUG_ON(dbstart(dentry) < 0);
+ }
+ kfree(whname);
+ if (locked_parent)
+ unionfs_unlock_dentry(parent_dentry);
+ dput(parent_dentry);
+ if (locked_child || (err && allocated_new_info))
+ unionfs_unlock_dentry(dentry);
+ if (!err && d_interposed)
+ return d_interposed;
+ return ERR_PTR(err);
+}
+
+/*
+ * This is a utility function that fills in a unionfs dentry.
+ *
+ * Returns: 0 (ok), or -ERRNO if an error occurred.
+ */
+int unionfs_partial_lookup(struct dentry *dentry)
+{
+ struct dentry *tmp;
+ struct nameidata nd = { .flags = 0 };
+ int err = -ENOSYS;
+
+ tmp = unionfs_lookup_backend(dentry, &nd, INTERPOSE_PARTIAL);
+ if (!tmp) {
+ err = 0;
+ goto out;
+ }
+ if (IS_ERR(tmp)) {
+ err = PTR_ERR(tmp);
+ goto out;
+ }
+ /* need to change the interface */
+ BUG_ON(tmp != dentry);
+out:
+ return err;
+}
+
+/* The dentry cache is just so we have properly sized dentries. */
+static struct kmem_cache *unionfs_dentry_cachep;
+int unionfs_init_dentry_cache(void)
+{
+ unionfs_dentry_cachep =
+ kmem_cache_create("unionfs_dentry",
+ sizeof(struct unionfs_dentry_info),
+ 0, SLAB_RECLAIM_ACCOUNT, NULL, NULL);
+
+ return (unionfs_dentry_cachep ? 0 : -ENOMEM);
+}
+
+void unionfs_destroy_dentry_cache(void)
+{
+ if (unionfs_dentry_cachep)
+ kmem_cache_destroy(unionfs_dentry_cachep);
+}
+
+void free_dentry_private_data(struct dentry *dentry)
+{
+ if (!dentry || !dentry->d_fsdata)
+ return;
+ kmem_cache_free(unionfs_dentry_cachep, dentry->d_fsdata);
+ dentry->d_fsdata = NULL;
+}
+
+static inline int __realloc_dentry_private_data(struct dentry *dentry)
+{
+ struct unionfs_dentry_info *info = UNIONFS_D(dentry);
+ void *p;
+ int size;
+
+ BUG_ON(!info);
+
+ size = sizeof(struct path) * sbmax(dentry->d_sb);
+ p = krealloc(info->lower_paths, size, GFP_ATOMIC);
+ if (!p)
+ return -ENOMEM;
+
+ info->lower_paths = p;
+
+ info->bstart = -1;
+ info->bend = -1;
+ info->bopaque = -1;
+ info->bcount = sbmax(dentry->d_sb);
+ atomic_set(&info->generation,
+ atomic_read(&UNIONFS_SB(dentry->d_sb)->generation));
+
+ memset(info->lower_paths, 0, size);
+
+ return 0;
+}
+
+/* UNIONFS_D(dentry)->lock must be locked */
+static int realloc_dentry_private_data(struct dentry *dentry)
+{
+ if (!__realloc_dentry_private_data(dentry))
+ return 0;
+
+ kfree(UNIONFS_D(dentry)->lower_paths);
+ free_dentry_private_data(dentry);
+ return -ENOMEM;
+}
+
+/* allocate new dentry private data */
+int new_dentry_private_data(struct dentry *dentry)
+{
+ struct unionfs_dentry_info *info = UNIONFS_D(dentry);
+
+ BUG_ON(info);
+
+ info = kmem_cache_alloc(unionfs_dentry_cachep, GFP_ATOMIC);
+ if (!info)
+ return -ENOMEM;
+
+ mutex_init(&info->lock);
+ mutex_lock(&info->lock);
+
+ info->lower_paths = NULL;
+
+ dentry->d_fsdata = info;
+
+ if (!__realloc_dentry_private_data(dentry))
+ return 0;
+
+ mutex_unlock(&info->lock);
+ free_dentry_private_data(dentry);
+ return -ENOMEM;
+}
+
+/*
+ * scan through the lower dentry objects, and set bstart to reflect the
+ * starting branch
+ */
+void update_bstart(struct dentry *dentry)
+{
+ int bindex;
+ int bstart = dbstart(dentry);
+ int bend = dbend(dentry);
+ struct dentry *lower_dentry;
+
+ for (bindex = bstart; bindex <= bend; bindex++) {
+ lower_dentry = unionfs_lower_dentry_idx(dentry, bindex);
+ if (!lower_dentry)
+ continue;
+ if (lower_dentry->d_inode) {
+ set_dbstart(dentry, bindex);
+ break;
+ }
+ dput(lower_dentry);
+ unionfs_set_lower_dentry_idx(dentry, bindex, NULL);
+ }
+}
diff --git a/fs/unionfs/main.c b/fs/unionfs/main.c
new file mode 100644
index 0000000..e437edb
--- /dev/null
+++ b/fs/unionfs/main.c
@@ -0,0 +1,762 @@
+/*
+ * Copyright (c) 2003-2007 Erez Zadok
+ * Copyright (c) 2003-2006 Charles P. Wright
+ * Copyright (c) 2005-2007 Josef 'Jeff' Sipek
+ * Copyright (c) 2005-2006 Junjiro Okajima
+ * Copyright (c) 2005 Arun M. Krishnakumar
+ * Copyright (c) 2004-2006 David P. Quigley
+ * Copyright (c) 2003-2004 Mohammad Nayyer Zubair
+ * Copyright (c) 2003 Puja Gupta
+ * Copyright (c) 2003 Harikesavan Krishnan
+ * Copyright (c) 2003-2007 Stony Brook University
+ * Copyright (c) 2003-2007 The Research Foundation of SUNY
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include "union.h"
+#include
+#include
+
+/*
+ * Connect a unionfs inode dentry/inode with several lower ones. This is
+ * the classic stackable file system "vnode interposition" action.
+ *
+ * @sb: unionfs's super_block
+ */
+struct dentry *unionfs_interpose(struct dentry *dentry, struct super_block *sb,
+ int flag)
+{
+ struct inode *lower_inode;
+ struct dentry *lower_dentry;
+ int err = 0;
+ struct inode *inode;
+ int is_negative_dentry = 1;
+ int bindex, bstart, bend;
+ int skipped = 1;
+ struct dentry *spliced = NULL;
+
+ verify_locked(dentry);
+
+ bstart = dbstart(dentry);
+ bend = dbend(dentry);
+
+ /* Make sure that we didn't get a negative dentry. */
+ for (bindex = bstart; bindex <= bend; bindex++) {
+ if (unionfs_lower_dentry_idx(dentry, bindex) &&
+ unionfs_lower_dentry_idx(dentry, bindex)->d_inode) {
+ is_negative_dentry = 0;
+ break;
+ }
+ }
+ BUG_ON(is_negative_dentry);
+
+ /*
+ * We allocate our new inode below, by calling iget.
+ * iget will call our read_inode which will initialize some
+ * of the new inode's fields
+ */
+
+ /*
+ * On revalidate we've already got our own inode and just need
+ * to fix it up.
+ */
+ if (flag == INTERPOSE_REVAL) {
+ inode = dentry->d_inode;
+ UNIONFS_I(inode)->bstart = -1;
+ UNIONFS_I(inode)->bend = -1;
+ atomic_set(&UNIONFS_I(inode)->generation,
+ atomic_read(&UNIONFS_SB(sb)->generation));
+
+ UNIONFS_I(inode)->lower_inodes =
+ kcalloc(sbmax(sb), sizeof(struct inode *), GFP_KERNEL);
+ if (!UNIONFS_I(inode)->lower_inodes) {
+ err = -ENOMEM;
+ goto out;
+ }
+ } else {
+ /* get unique inode number for unionfs */
+ inode = iget(sb, iunique(sb, UNIONFS_ROOT_INO));
+ if (!inode) {
+ err = -EACCES;
+ goto out;
+ }
+ if (atomic_read(&inode->i_count) > 1)
+ goto skip;
+ }
+
+fill_i_info:
+ skipped = 0;
+ for (bindex = bstart; bindex <= bend; bindex++) {
+ lower_dentry = unionfs_lower_dentry_idx(dentry, bindex);
+ if (!lower_dentry) {
+ unionfs_set_lower_inode_idx(inode, bindex, NULL);
+ continue;
+ }
+
+ /* Initialize the lower inode to the new lower inode. */
+ if (!lower_dentry->d_inode)
+ continue;
+
+ unionfs_set_lower_inode_idx(inode, bindex,
+ igrab(lower_dentry->d_inode));
+ }
+
+ ibstart(inode) = dbstart(dentry);
+ ibend(inode) = dbend(dentry);
+
+ /* Use attributes from the first branch. */
+ lower_inode = unionfs_lower_inode(inode);
+
+ /* Use different set of inode ops for symlinks & directories */
+ if (S_ISLNK(lower_inode->i_mode))
+ inode->i_op = &unionfs_symlink_iops;
+ else if (S_ISDIR(lower_inode->i_mode))
+ inode->i_op = &unionfs_dir_iops;
+
+ /* Use different set of file ops for directories */
+ if (S_ISDIR(lower_inode->i_mode))
+ inode->i_fop = &unionfs_dir_fops;
+
+ /* properly initialize special inodes */
+ if (S_ISBLK(lower_inode->i_mode) || S_ISCHR(lower_inode->i_mode) ||
+ S_ISFIFO(lower_inode->i_mode) || S_ISSOCK(lower_inode->i_mode))
+ init_special_inode(inode, lower_inode->i_mode,
+ lower_inode->i_rdev);
+
+ /* all well, copy inode attributes */
+ unionfs_copy_attr_all(inode, lower_inode);
+ fsstack_copy_inode_size(inode, lower_inode);
+
+ if (spliced)
+ goto out_spliced;
+skip:
+ /* only (our) lookup wants to do a d_add */
+ switch (flag) {
+ case INTERPOSE_DEFAULT:
+ case INTERPOSE_REVAL_NEG:
+ d_instantiate(dentry, inode);
+ break;
+ case INTERPOSE_LOOKUP:
+ spliced = d_splice_alias(inode, dentry);
+ if (IS_ERR(spliced))
+ err = PTR_ERR(spliced);
+
+ /*
+ * d_splice can return a dentry if it was disconnected and
+ * had to be moved. We must ensure that the private data of
+ * the new dentry is correct and that the inode info was
+ * filled properly. Finally we must return this new dentry.
+ */
+ else if (spliced && spliced != dentry) {
+ spliced->d_op = &unionfs_dops;
+ spliced->d_fsdata = dentry->d_fsdata;
+ dentry->d_fsdata = NULL;
+ dentry = spliced;
+ if (skipped)
+ goto fill_i_info;
+ goto out_spliced;
+ }
+ break;
+ case INTERPOSE_REVAL:
+ /* Do nothing. */
+ break;
+ default:
+ printk(KERN_ERR "unionfs: invalid interpose flag passed!");
+ BUG();
+ }
+ goto out;
+
+out_spliced:
+ if (!err)
+ return spliced;
+out:
+ return ERR_PTR(err);
+}
+
+/* like interpose above, but for an already existing dentry */
+void unionfs_reinterpose(struct dentry *dentry)
+{
+ struct dentry *lower_dentry;
+ struct inode *inode;
+ int bindex, bstart, bend;
+
+ verify_locked(dentry);
+
+ /* This is pre-allocated inode */
+ inode = dentry->d_inode;
+
+ bstart = dbstart(dentry);
+ bend = dbend(dentry);
+ for (bindex = bstart; bindex <= bend; bindex++) {
+ lower_dentry = unionfs_lower_dentry_idx(dentry, bindex);
+ if (!lower_dentry)
+ continue;
+
+ if (!lower_dentry->d_inode)
+ continue;
+ if (unionfs_lower_inode_idx(inode, bindex))
+ continue;
+ unionfs_set_lower_inode_idx(inode, bindex,
+ igrab(lower_dentry->d_inode));
+ }
+ ibstart(inode) = dbstart(dentry);
+ ibend(inode) = dbend(dentry);
+}
+
+/*
+ * make sure the branch we just looked up (nd) makes sense:
+ *
+ * 1) we're not trying to stack unionfs on top of unionfs
+ * 2) it exists
+ * 3) is a directory
+ */
+int check_branch(struct nameidata *nd)
+{
+ /* XXX: remove in ODF code -- stacking unions allowed there */
+ if (!strcmp(nd->dentry->d_sb->s_type->name, "unionfs"))
+ return -EINVAL;
+ if (!nd->dentry->d_inode)
+ return -ENOENT;
+ if (!S_ISDIR(nd->dentry->d_inode->i_mode))
+ return -ENOTDIR;
+ return 0;
+}
+
+/* checks if two lower_dentries have overlapping branches */
+static int is_branch_overlap(struct dentry *dent1, struct dentry *dent2)
+{
+ struct dentry *dent = NULL;
+
+ dent = dent1;
+ while ((dent != dent2) && (dent->d_parent != dent))
+ dent = dent->d_parent;
+
+ if (dent == dent2)
+ return 1;
+
+ dent = dent2;
+ while ((dent != dent1) && (dent->d_parent != dent))
+ dent = dent->d_parent;
+
+ return (dent == dent1);
+}
+
+/*
+ * Parse branch mode helper function
+ */
+int __parse_branch_mode(const char *name)
+{
+ if (!name)
+ return 0;
+ if (!strcmp(name, "ro"))
+ return MAY_READ;
+ if (!strcmp(name, "rw"))
+ return (MAY_READ | MAY_WRITE);
+ return 0;
+}
+
+/*
+ * Parse "ro" or "rw" options, but default to "rw" of no mode options
+ * was specified.
+ */
+int parse_branch_mode(const char *name)
+{
+ int perms = __parse_branch_mode(name);
+
+ if (perms == 0)
+ perms = MAY_READ | MAY_WRITE;
+ return perms;
+}
+
+/*
+ * parse the dirs= mount argument
+ *
+ * We don't need to lock the superblock private data's rwsem, as we get
+ * called only by unionfs_read_super - it is still a long time before anyone
+ * can even get a reference to us.
+ */
+static int parse_dirs_option(struct super_block *sb, struct unionfs_dentry_info
+ *lower_root_info, char *options)
+{
+ struct nameidata nd;
+ char *name;
+ int err = 0;
+ int branches = 1;
+ int bindex = 0;
+ int i = 0;
+ int j = 0;
+ struct dentry *dent1;
+ struct dentry *dent2;
+
+ if (options[0] == '\0') {
+ printk(KERN_WARNING "unionfs: no branches specified\n");
+ err = -EINVAL;
+ goto out;
+ }
+
+ /*
+ * Each colon means we have a separator, this is really just a rough
+ * guess, since strsep will handle empty fields for us.
+ */
+ for (i = 0; options[i]; i++)
+ if (options[i] == ':')
+ branches++;
+
+ /* allocate space for underlying pointers to lower dentry */
+ UNIONFS_SB(sb)->data =
+ kcalloc(branches, sizeof(struct unionfs_data), GFP_KERNEL);
+ if (!UNIONFS_SB(sb)->data) {
+ err = -ENOMEM;
+ goto out;
+ }
+
+ lower_root_info->lower_paths =
+ kcalloc(branches, sizeof(struct path), GFP_KERNEL);
+ if (!lower_root_info->lower_paths) {
+ err = -ENOMEM;
+ goto out;
+ }
+
+ /* now parsing a string such as "b1:b2=rw:b3=ro:b4" */
+ branches = 0;
+ while ((name = strsep(&options, ":")) != NULL) {
+ int perms;
+ char *mode = strchr(name, '=');
+
+ if (!name)
+ continue;
+ if (!*name) { /* bad use of ':' (extra colons) */
+ err = -EINVAL;
+ goto out;
+ }
+
+ branches++;
+
+ /* strip off '=' if any */
+ if (mode)
+ *mode++ = '\0';
+
+ perms = parse_branch_mode(mode);
+ if (!bindex && !(perms & MAY_WRITE)) {
+ err = -EINVAL;
+ goto out;
+ }
+
+ err = path_lookup(name, LOOKUP_FOLLOW, &nd);
+ if (err) {
+ printk(KERN_WARNING "unionfs: error accessing "
+ "lower directory '%s' (error %d)\n",
+ name, err);
+ goto out;
+ }
+
+ if ((err = check_branch(&nd))) {
+ printk(KERN_WARNING "unionfs: lower directory "
+ "'%s' is not a valid branch\n", name);
+ path_release(&nd);
+ goto out;
+ }
+
+ lower_root_info->lower_paths[bindex].dentry = nd.dentry;
+ lower_root_info->lower_paths[bindex].mnt = nd.mnt;
+
+ set_branchperms(sb, bindex, perms);
+ set_branch_count(sb, bindex, 0);
+ new_branch_id(sb, bindex);
+
+ if (lower_root_info->bstart < 0)
+ lower_root_info->bstart = bindex;
+ lower_root_info->bend = bindex;
+ bindex++;
+ }
+
+ if (branches == 0) {
+ printk(KERN_WARNING "unionfs: no branches specified\n");
+ err = -EINVAL;
+ goto out;
+ }
+
+ BUG_ON(branches != (lower_root_info->bend + 1));
+
+ /*
+ * Ensure that no overlaps exist in the branches.
+ *
+ * This test is required because the Linux kernel has no support
+ * currently for ensuring coherency between stackable layers and
+ * branches. If we were to allow overlapping branches, it would be
+ * possible, for example, to delete a file via one branch, which
+ * would not be reflected in another branch. Such incoherency could
+ * lead to inconsistencies and even kernel oopses. Rather than
+ * implement hacks to work around some of these cache-coherency
+ * problems, we prevent branch overlapping, for now. A complete
+ * solution will involve proper kernel/VFS support for cache
+ * coherency, at which time we could safely remove this
+ * branch-overlapping test.
+ */
+ for (i = 0; i < branches; i++) {
+ dent1 = lower_root_info->lower_paths[i].dentry;
+ for (j = i + 1; j < branches; j++) {
+ dent2 = lower_root_info->lower_paths[j].dentry;
+ if (is_branch_overlap(dent1, dent2)) {
+ printk(KERN_WARNING "unionfs: branches %d and "
+ "%d overlap\n", i, j);
+ err = -EINVAL;
+ goto out;
+ }
+ }
+ }
+
+out:
+ if (err) {
+ for (i = 0; i < branches; i++)
+ if (lower_root_info->lower_paths[i].dentry) {
+ dput(lower_root_info->lower_paths[i].dentry);
+ /* initialize: can't use unionfs_mntput here */
+ mntput(lower_root_info->lower_paths[i].mnt);
+ }
+
+ kfree(lower_root_info->lower_paths);
+ kfree(UNIONFS_SB(sb)->data);
+
+ /*
+ * MUST clear the pointers to prevent potential double free if
+ * the caller dies later on
+ */
+ lower_root_info->lower_paths = NULL;
+ UNIONFS_SB(sb)->data = NULL;
+ }
+ return err;
+}
+
+/*
+ * Parse mount options. See the manual page for usage instructions.
+ *
+ * Returns the dentry object of the lower-level (lower) directory;
+ * We want to mount our stackable file system on top of that lower directory.
+ */
+static struct unionfs_dentry_info *unionfs_parse_options(
+ struct super_block *sb,
+ char *options)
+{
+ struct unionfs_dentry_info *lower_root_info;
+ char *optname;
+ int err = 0;
+ int bindex;
+ int dirsfound = 0;
+
+ /* allocate private data area */
+ err = -ENOMEM;
+ lower_root_info =
+ kzalloc(sizeof(struct unionfs_dentry_info), GFP_KERNEL);
+ if (!lower_root_info)
+ goto out_error;
+ lower_root_info->bstart = -1;
+ lower_root_info->bend = -1;
+ lower_root_info->bopaque = -1;
+
+ while ((optname = strsep(&options, ",")) != NULL) {
+ char *optarg;
+ char *endptr;
+ int intval;
+
+ if (!optname || !*optname)
+ continue;
+
+ optarg = strchr(optname, '=');
+ if (optarg)
+ *optarg++ = '\0';
+
+ /*
+ * All of our options take an argument now. Insert ones that
+ * don't, above this check.
+ */
+ if (!optarg) {
+ printk("unionfs: %s requires an argument.\n", optname);
+ err = -EINVAL;
+ goto out_error;
+ }
+
+ if (!strcmp("dirs", optname)) {
+ if (++dirsfound > 1) {
+ printk(KERN_WARNING
+ "unionfs: multiple dirs specified\n");
+ err = -EINVAL;
+ goto out_error;
+ }
+ err = parse_dirs_option(sb, lower_root_info, optarg);
+ if (err)
+ goto out_error;
+ continue;
+ }
+
+ /* All of these options require an integer argument. */
+ intval = simple_strtoul(optarg, &endptr, 0);
+ if (*endptr) {
+ printk(KERN_WARNING
+ "unionfs: invalid %s option '%s'\n",
+ optname, optarg);
+ err = -EINVAL;
+ goto out_error;
+ }
+
+ err = -EINVAL;
+ printk(KERN_WARNING
+ "unionfs: unrecognized option '%s'\n", optname);
+ goto out_error;
+ }
+ if (dirsfound != 1) {
+ printk(KERN_WARNING "unionfs: dirs option required\n");
+ err = -EINVAL;
+ goto out_error;
+ }
+ goto out;
+
+out_error:
+ if (lower_root_info && lower_root_info->lower_paths) {
+ for (bindex = lower_root_info->bstart;
+ bindex >= 0 && bindex <= lower_root_info->bend;
+ bindex++) {
+ struct dentry *d;
+ struct vfsmount *m;
+
+ d = lower_root_info->lower_paths[bindex].dentry;
+ m = lower_root_info->lower_paths[bindex].mnt;
+
+ dput(d);
+ /* initializing: can't use unionfs_mntput here */
+ mntput(m);
+ }
+ }
+
+ kfree(lower_root_info->lower_paths);
+ kfree(lower_root_info);
+
+ kfree(UNIONFS_SB(sb)->data);
+ UNIONFS_SB(sb)->data = NULL;
+
+ lower_root_info = ERR_PTR(err);
+out:
+ return lower_root_info;
+}
+
+/*
+ * our custom d_alloc_root work-alike
+ *
+ * we can't use d_alloc_root if we want to use our own interpose function
+ * unchanged, so we simply call our own "fake" d_alloc_root
+ */
+static struct dentry *unionfs_d_alloc_root(struct super_block *sb)
+{
+ struct dentry *ret = NULL;
+
+ if (sb) {
+ static const struct qstr name = {.name = "/",.len = 1 };
+
+ ret = d_alloc(NULL, &name);
+ if (ret) {
+ ret->d_op = &unionfs_dops;
+ ret->d_sb = sb;
+ ret->d_parent = ret;
+ }
+ }
+ return ret;
+}
+
+/*
+ * There is no need to lock the unionfs_super_info's rwsem as there is no
+ * way anyone can have a reference to the superblock at this point in time.
+ */
+static int unionfs_read_super(struct super_block *sb, void *raw_data,
+ int silent)
+{
+ int err = 0;
+ struct unionfs_dentry_info *lower_root_info = NULL;
+ int bindex, bstart, bend;
+
+ if (!raw_data) {
+ printk(KERN_WARNING
+ "unionfs: read_super: missing data argument\n");
+ err = -EINVAL;
+ goto out;
+ }
+
+ /* Allocate superblock private data */
+ sb->s_fs_info = kzalloc(sizeof(struct unionfs_sb_info), GFP_KERNEL);
+ if (!UNIONFS_SB(sb)) {
+ printk(KERN_WARNING "unionfs: read_super: out of memory\n");
+ err = -ENOMEM;
+ goto out;
+ }
+
+ UNIONFS_SB(sb)->bend = -1;
+ atomic_set(&UNIONFS_SB(sb)->generation, 1);
+ init_rwsem(&UNIONFS_SB(sb)->rwsem);
+ UNIONFS_SB(sb)->high_branch_id = -1; /* -1 == invalid branch ID */
+
+ lower_root_info = unionfs_parse_options(sb, raw_data);
+ if (IS_ERR(lower_root_info)) {
+ printk(KERN_WARNING
+ "unionfs: read_super: error while parsing options "
+ "(err = %ld)\n", PTR_ERR(lower_root_info));
+ err = PTR_ERR(lower_root_info);
+ lower_root_info = NULL;
+ goto out_free;
+ }
+ if (lower_root_info->bstart == -1) {
+ err = -ENOENT;
+ goto out_free;
+ }
+
+ /* set the lower superblock field of upper superblock */
+ bstart = lower_root_info->bstart;
+ BUG_ON(bstart != 0);
+ sbend(sb) = bend = lower_root_info->bend;
+ for (bindex = bstart; bindex <= bend; bindex++) {
+ struct dentry *d = lower_root_info->lower_paths[bindex].dentry;
+ unionfs_set_lower_super_idx(sb, bindex, d->d_sb);
+ }
+
+ /* max Bytes is the maximum bytes from highest priority branch */
+ sb->s_maxbytes = unionfs_lower_super_idx(sb, 0)->s_maxbytes;
+
+ sb->s_op = &unionfs_sops;
+
+ /* See comment next to the definition of unionfs_d_alloc_root */
+ sb->s_root = unionfs_d_alloc_root(sb);
+ if (!sb->s_root) {
+ err = -ENOMEM;
+ goto out_dput;
+ }
+
+ /* link the upper and lower dentries */
+ sb->s_root->d_fsdata = NULL;
+ if ((err = new_dentry_private_data(sb->s_root)))
+ goto out_freedpd;
+
+ /* Set the lower dentries for s_root */
+ for (bindex = bstart; bindex <= bend; bindex++) {
+ struct dentry *d;
+ struct vfsmount *m;
+
+ d = lower_root_info->lower_paths[bindex].dentry;
+ m = lower_root_info->lower_paths[bindex].mnt;
+
+ unionfs_set_lower_dentry_idx(sb->s_root, bindex, d);
+ unionfs_set_lower_mnt_idx(sb->s_root, bindex, m);
+ }
+ set_dbstart(sb->s_root, bstart);
+ set_dbend(sb->s_root, bend);
+
+ /* Set the generation number to one, since this is for the mount. */
+ atomic_set(&UNIONFS_D(sb->s_root)->generation, 1);
+
+ /*
+ * Call interpose to create the upper level inode. Only
+ * INTERPOSE_LOOKUP can return a value other than 0 on err.
+ */
+ err = PTR_ERR(unionfs_interpose(sb->s_root, sb, 0));
+ unionfs_unlock_dentry(sb->s_root);
+ if (!err)
+ goto out;
+ /* else fall through */
+
+out_freedpd:
+ if (UNIONFS_D(sb->s_root)) {
+ kfree(UNIONFS_D(sb->s_root)->lower_paths);
+ free_dentry_private_data(sb->s_root);
+ }
+ dput(sb->s_root);
+
+out_dput:
+ if (lower_root_info && !IS_ERR(lower_root_info)) {
+ for (bindex = lower_root_info->bstart;
+ bindex <= lower_root_info->bend; bindex++) {
+ struct dentry *d;
+ struct vfsmount *m;
+
+ d = lower_root_info->lower_paths[bindex].dentry;
+ m = lower_root_info->lower_paths[bindex].mnt;
+
+ dput(d);
+ /* initializing: can't use unionfs_mntput here */
+ mntput(m);
+ }
+ kfree(lower_root_info->lower_paths);
+ kfree(lower_root_info);
+ lower_root_info = NULL;
+ }
+
+out_free:
+ kfree(UNIONFS_SB(sb)->data);
+ kfree(UNIONFS_SB(sb));
+ sb->s_fs_info = NULL;
+
+out:
+ if (lower_root_info && !IS_ERR(lower_root_info)) {
+ kfree(lower_root_info->lower_paths);
+ kfree(lower_root_info);
+ }
+ return err;
+}
+
+static int unionfs_get_sb(struct file_system_type *fs_type,
+ int flags, const char *dev_name,
+ void *raw_data, struct vfsmount *mnt)
+{
+ return get_sb_nodev(fs_type, flags, raw_data, unionfs_read_super, mnt);
+}
+
+static struct file_system_type unionfs_fs_type = {
+ .owner = THIS_MODULE,
+ .name = "unionfs",
+ .get_sb = unionfs_get_sb,
+ .kill_sb = generic_shutdown_super,
+ .fs_flags = FS_REVAL_DOT,
+};
+
+static int __init init_unionfs_fs(void)
+{
+ int err;
+
+ printk("Registering unionfs " UNIONFS_VERSION "\n");
+
+ if ((err = unionfs_init_filldir_cache()))
+ goto out;
+ if ((err = unionfs_init_inode_cache()))
+ goto out;
+ if ((err = unionfs_init_dentry_cache()))
+ goto out;
+ if ((err = init_sioq()))
+ goto out;
+ err = register_filesystem(&unionfs_fs_type);
+out:
+ if (err) {
+ stop_sioq();
+ unionfs_destroy_filldir_cache();
+ unionfs_destroy_inode_cache();
+ unionfs_destroy_dentry_cache();
+ }
+ return err;
+}
+
+static void __exit exit_unionfs_fs(void)
+{
+ stop_sioq();
+ unionfs_destroy_filldir_cache();
+ unionfs_destroy_inode_cache();
+ unionfs_destroy_dentry_cache();
+ unregister_filesystem(&unionfs_fs_type);
+ printk("Completed unionfs module unload.\n");
+}
+
+MODULE_AUTHOR("Erez Zadok, Filesystems and Storage Lab, Stony Brook University"
+ " (http://www.fsl.cs.sunysb.edu)");
+MODULE_DESCRIPTION("Unionfs " UNIONFS_VERSION
+ " (http://unionfs.filesystems.org)");
+MODULE_LICENSE("GPL");
+
+module_init(init_unionfs_fs);
+module_exit(exit_unionfs_fs);
diff --git a/fs/unionfs/mmap.c b/fs/unionfs/mmap.c
new file mode 100644
index 0000000..5629dcc
--- /dev/null
+++ b/fs/unionfs/mmap.c
@@ -0,0 +1,378 @@
+/*
+ * Copyright (c) 2003-2007 Erez Zadok
+ * Copyright (c) 2003-2006 Charles P. Wright
+ * Copyright (c) 2005-2007 Josef 'Jeff' Sipek
+ * Copyright (c) 2005-2006 Junjiro Okajima
+ * Copyright (c) 2006 Shaya Potter
+ * Copyright (c) 2005 Arun M. Krishnakumar
+ * Copyright (c) 2004-2006 David P. Quigley
+ * Copyright (c) 2003-2004 Mohammad Nayyer Zubair
+ * Copyright (c) 2003 Puja Gupta
+ * Copyright (c) 2003 Harikesavan Krishnan
+ * Copyright (c) 2003-2007 Stony Brook University
+ * Copyright (c) 2003-2007 The Research Foundation of SUNY
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include "union.h"
+
+/*
+ * Unionfs doesn't implement ->writepages, which is OK with the VFS and
+ * keeps our code simpler and smaller. Nevertheless, somehow, our own
+ * ->writepage must be called so we can sync the upper pages with the lower
+ * pages: otherwise data changed at the upper layer won't get written to the
+ * lower layer.
+ *
+ * Some lower file systems (e.g., NFS) expect the VFS to call its writepages
+ * only, which in turn will call generic_writepages and invoke each of the
+ * lower file system's ->writepage. NFS in particular uses the
+ * wbc->fs_private field in its nfs_writepage, which is set in its
+ * nfs_writepages. So if we don't call the lower nfs_writepages first, then
+ * NFS's nfs_writepage will dereference a NULL wbc->fs_private and cause an
+ * OOPS. If, however, we implement a unionfs_writepages and then we do call
+ * the lower nfs_writepages, then we "lose control" over the pages we're
+ * trying to write to the lower file system: we won't be writing our own
+ * new/modified data from the upper pages to the lower pages, and any
+ * mmap-based changes are lost.
+ *
+ * This is a fundamental cache-coherency problem in Linux. The kernel isn't
+ * able to support such stacking abstractions cleanly. One possible clean
+ * way would be that a lower file system's ->writepage method have some sort
+ * of a callback to validate if any upper pages for the same file+offset
+ * exist and have newer content in them.
+ *
+ * This whole NULL ptr dereference is triggered at the lower file system
+ * (NFS) because the wbc->for_writepages is set to 1. Therefore, to avoid
+ * this NULL pointer dereference, we set this flag to 0 and restore it upon
+ * exit. This probably means that we're slightly less efficient in writing
+ * pages out, doing them one at a time, but at least we avoid the oops until
+ * such day as Linux can better support address_space_ops in a stackable
+ * fashion.
+ */
+static int unionfs_writepage(struct page *page, struct writeback_control *wbc)
+{
+ int err = -EIO;
+ struct inode *inode;
+ struct inode *lower_inode;
+ struct page *lower_page;
+ char *kaddr, *lower_kaddr;
+ int saved_for_writepages = wbc->for_writepages;
+
+ inode = page->mapping->host;
+ lower_inode = unionfs_lower_inode(inode);
+
+ /*
+ * find lower page (returns a locked page)
+ *
+ * NOTE: we used to call grab_cache_page(), but that was unnecessary
+ * as it would have tried to create a new lower page if it didn't
+ * exist, leading to deadlocks (esp. under memory-pressure
+ * conditions, when it is really a bad idea to *consume* more
+ * memory). Instead, we assume the lower page exists, and if we can
+ * find it, then we ->writepage on it; if we can't find it, then it
+ * couldn't have disappeared unless the kernel already flushed it,
+ * in which case we're still OK. This is especially correct if
+ * wbc->sync_mode is WB_SYNC_NONE (as per
+ * Documentation/filesystems/vfs.txt). If we can't flush our page
+ * because we can't find a lower page, then at least we re-mark our
+ * page as dirty, and return AOP_WRITEPAGE_ACTIVATE as the VFS
+ * expects us to. (Note, if in the future it'd turn out that we
+ * have to find a lower page no matter what, then we'd have to
+ * resort to RAIF's page pointer flipping trick.)
+ */
+ lower_page = find_lock_page(lower_inode->i_mapping, page->index);
+ if (!lower_page) {
+ err = AOP_WRITEPAGE_ACTIVATE;
+ set_page_dirty(page);
+ goto out;
+ }
+
+ /* get page address, and encode it */
+ kaddr = kmap(page);
+ lower_kaddr = kmap(lower_page);
+
+ memcpy(lower_kaddr, kaddr, PAGE_CACHE_SIZE);
+
+ kunmap(page);
+ kunmap(lower_page);
+
+ BUG_ON(!lower_inode->i_mapping->a_ops->writepage);
+
+ /* workaround for some lower file systems: see big comment on top */
+ if (wbc->for_writepages /* && !wbc->fs_private */)
+ wbc->for_writepages = 0;
+
+ /* call lower writepage (expects locked page) */
+ clear_page_dirty_for_io(lower_page); /* emulate VFS behavior */
+ err = lower_inode->i_mapping->a_ops->writepage(lower_page, wbc);
+ wbc->for_writepages = saved_for_writepages; /* restore value */
+
+ /* b/c find_lock_page locked it and ->writepage unlocks on success */
+ if (err)
+ unlock_page(lower_page);
+ /* b/c grab_cache_page increased refcnt */
+ page_cache_release(lower_page);
+
+ if (err < 0) {
+ ClearPageUptodate(page);
+ goto out;
+ }
+ if (err == AOP_WRITEPAGE_ACTIVATE) {
+ /*
+ * Lower file systems such as ramfs and tmpfs, may return
+ * AOP_WRITEPAGE_ACTIVATE so that the VM won't try to
+ * (pointlessly) write the page again for a while. But
+ * those lower file systems also set the page dirty bit back
+ * again. So we mimic that behaviour here.
+ */
+ if (PageDirty(lower_page))
+ set_page_dirty(page);
+ goto out;
+ }
+
+ /* all is well */
+ SetPageUptodate(page);
+ /* lower mtimes has changed: update ours */
+ unionfs_copy_attr_times(inode);
+
+ unlock_page(page);
+
+out:
+ return err;
+}
+
+/*
+ * readpage is called from generic_page_read and the fault handler.
+ * If your file system uses generic_page_read for the read op, it
+ * must implement readpage.
+ *
+ * Readpage expects a locked page, and must unlock it.
+ */
+static int unionfs_do_readpage(struct file *file, struct page *page)
+{
+ int err = -EIO;
+ struct file *lower_file;
+ struct inode *inode;
+ mm_segment_t old_fs;
+ char *page_data = NULL;
+ loff_t offset;
+
+ if (UNIONFS_F(file) == NULL) {
+ err = -ENOENT;
+ goto out;
+ }
+
+ lower_file = unionfs_lower_file(file);
+ /* FIXME: is this assertion right here? */
+ BUG_ON(lower_file == NULL);
+
+ inode = file->f_path.dentry->d_inode;
+
+ page_data = (char *) kmap(page);
+ /*
+ * Use vfs_read because some lower file systems don't have a
+ * readpage method, and some file systems (esp. distributed ones)
+ * don't like their pages to be accessed directly. Using vfs_read
+ * may be a little slower, but a lot safer, as the VFS does a lot of
+ * the necessary magic for us.
+ */
+ offset = lower_file->f_pos = (page->index << PAGE_CACHE_SHIFT);
+ old_fs = get_fs();
+ set_fs(KERNEL_DS);
+ err = vfs_read(lower_file, page_data, PAGE_CACHE_SIZE,
+ &lower_file->f_pos);
+ set_fs(old_fs);
+
+ kunmap(page);
+
+ if (err < 0)
+ goto out;
+ err = 0;
+
+ /* if vfs_read succeeded above, sync up our times */
+ unionfs_copy_attr_times(inode);
+
+ flush_dcache_page(page);
+
+out:
+ if (err == 0)
+ SetPageUptodate(page);
+ else
+ ClearPageUptodate(page);
+
+ return err;
+}
+
+static int unionfs_readpage(struct file *file, struct page *page)
+{
+ int err;
+
+ unionfs_read_lock(file->f_path.dentry->d_sb);
+ if ((err = unionfs_file_revalidate(file, 0)))
+ goto out;
+ unionfs_check_file(file);
+
+ err = unionfs_do_readpage(file, page);
+
+ if (!err) {
+ touch_atime(unionfs_lower_mnt(file->f_path.dentry),
+ unionfs_lower_dentry(file->f_path.dentry));
+ unionfs_copy_attr_times(file->f_path.dentry->d_inode);
+ }
+
+ /*
+ * we have to unlock our page, b/c we _might_ have gotten a locked
+ * page. but we no longer have to wakeup on our page here, b/c
+ * UnlockPage does it
+ */
+out:
+ unlock_page(page);
+ unionfs_check_file(file);
+ unionfs_read_unlock(file->f_path.dentry->d_sb);
+
+ return err;
+}
+
+static int unionfs_prepare_write(struct file *file, struct page *page,
+ unsigned from, unsigned to)
+{
+ int err;
+
+ unionfs_read_lock(file->f_path.dentry->d_sb);
+ /*
+ * This is the only place where we unconditionally copy the lower
+ * attribute times before calling unionfs_file_revalidate. The
+ * reason is that our ->write calls do_sync_write which in turn will
+ * call our ->prepare_write and then ->commit_write. Before our
+ * ->write is called, the lower mtimes are in sync, but by the time
+ * the VFS calls our ->commit_write, the lower mtimes have changed.
+ * Therefore, the only reasonable time for us to sync up from the
+ * changed lower mtimes, and avoid an invariant violation warning,
+ * is here, in ->prepare_write.
+ */
+ unionfs_copy_attr_times(file->f_path.dentry->d_inode);
+ err = unionfs_file_revalidate(file, 1);
+ unionfs_check_file(file);
+ unionfs_read_unlock(file->f_path.dentry->d_sb);
+
+ return err;
+}
+
+static int unionfs_commit_write(struct file *file, struct page *page,
+ unsigned from, unsigned to)
+{
+ int err = -ENOMEM;
+ struct inode *inode, *lower_inode;
+ struct file *lower_file = NULL;
+ loff_t pos;
+ unsigned bytes = to - from;
+ char *page_data = NULL;
+ mm_segment_t old_fs;
+
+ BUG_ON(file == NULL);
+
+ unionfs_read_lock(file->f_path.dentry->d_sb);
+ if ((err = unionfs_file_revalidate(file, 1)))
+ goto out;
+ unionfs_check_file(file);
+
+ inode = page->mapping->host;
+ lower_inode = unionfs_lower_inode(inode);
+
+ if (UNIONFS_F(file) != NULL)
+ lower_file = unionfs_lower_file(file);
+
+ /* FIXME: is this assertion right here? */
+ BUG_ON(lower_file == NULL);
+
+ page_data = (char *)kmap(page);
+ lower_file->f_pos = (page->index << PAGE_CACHE_SHIFT) + from;
+
+ /*
+ * SP: I use vfs_write instead of copying page data and the
+ * prepare_write/commit_write combo because file system's like
+ * GFS/OCFS2 don't like things touching those directly,
+ * calling the underlying write op, while a little bit slower, will
+ * call all the FS specific code as well
+ */
+ old_fs = get_fs();
+ set_fs(KERNEL_DS);
+ err = vfs_write(lower_file, page_data + from, bytes,
+ &lower_file->f_pos);
+ set_fs(old_fs);
+
+ kunmap(page);
+
+ if (err < 0)
+ goto out;
+
+ inode->i_blocks = lower_inode->i_blocks;
+ /* we may have to update i_size */
+ pos = ((loff_t) page->index << PAGE_CACHE_SHIFT) + to;
+ if (pos > i_size_read(inode))
+ i_size_write(inode, pos);
+ /* if vfs_write succeeded above, sync up our times */
+ unionfs_copy_attr_times(inode);
+ mark_inode_dirty_sync(inode);
+
+out:
+ if (err < 0)
+ ClearPageUptodate(page);
+
+ unionfs_read_unlock(file->f_path.dentry->d_sb);
+ unionfs_check_file(file);
+ return err; /* assume all is ok */
+}
+
+static void unionfs_sync_page(struct page *page)
+{
+ struct inode *inode;
+ struct inode *lower_inode;
+ struct page *lower_page;
+ struct address_space *mapping;
+
+ inode = page->mapping->host;
+ lower_inode = unionfs_lower_inode(inode);
+
+ /*
+ * Find lower page (returns a locked page).
+ *
+ * NOTE: we used to call grab_cache_page(), but that was unnecessary
+ * as it would have tried to create a new lower page if it didn't
+ * exist, leading to deadlocks. All our sync_page method needs to
+ * do is ensure that pending I/O gets done.
+ */
+ lower_page = find_lock_page(lower_inode->i_mapping, page->index);
+ if (!lower_page) {
+ printk(KERN_DEBUG "unionfs: find_lock_page failed\n");
+ goto out;
+ }
+
+ /* do the actual sync */
+ mapping = lower_page->mapping;
+ /*
+ * XXX: can we optimize ala RAIF and set the lower page to be
+ * discarded after a successful sync_page?
+ */
+ if (mapping && mapping->a_ops && mapping->a_ops->sync_page)
+ mapping->a_ops->sync_page(lower_page);
+
+ /* b/c find_lock_page locked it */
+ unlock_page(lower_page);
+ /* b/c find_lock_page increased refcnt */
+ page_cache_release(lower_page);
+
+out:
+ return;
+}
+
+struct address_space_operations unionfs_aops = {
+ .writepage = unionfs_writepage,
+ .readpage = unionfs_readpage,
+ .prepare_write = unionfs_prepare_write,
+ .commit_write = unionfs_commit_write,
+ .sync_page = unionfs_sync_page,
+};
diff --git a/fs/unionfs/rdstate.c b/fs/unionfs/rdstate.c
new file mode 100644
index 0000000..5c9d14b
--- /dev/null
+++ b/fs/unionfs/rdstate.c
@@ -0,0 +1,282 @@
+/*
+ * Copyright (c) 2003-2007 Erez Zadok
+ * Copyright (c) 2003-2006 Charles P. Wright
+ * Copyright (c) 2005-2007 Josef 'Jeff' Sipek
+ * Copyright (c) 2005-2006 Junjiro Okajima
+ * Copyright (c) 2005 Arun M. Krishnakumar
+ * Copyright (c) 2004-2006 David P. Quigley
+ * Copyright (c) 2003-2004 Mohammad Nayyer Zubair
+ * Copyright (c) 2003 Puja Gupta
+ * Copyright (c) 2003 Harikesavan Krishnan
+ * Copyright (c) 2003-2007 Stony Brook University
+ * Copyright (c) 2003-2007 The Research Foundation of SUNY
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include "union.h"
+
+/* This file contains the routines for maintaining readdir state. */
+
+/*
+ * There are two structures here, rdstate which is a hash table
+ * of the second structure which is a filldir_node.
+ */
+
+/*
+ * This is a struct kmem_cache for filldir nodes, because we allocate a lot
+ * of them and they shouldn't waste memory. If the node has a small name
+ * (as defined by the dentry structure), then we use an inline name to
+ * preserve kmalloc space.
+ */
+static struct kmem_cache *unionfs_filldir_cachep;
+
+int unionfs_init_filldir_cache(void)
+{
+ unionfs_filldir_cachep =
+ kmem_cache_create("unionfs_filldir",
+ sizeof(struct filldir_node), 0,
+ SLAB_RECLAIM_ACCOUNT, NULL, NULL);
+
+ return (unionfs_filldir_cachep ? 0 : -ENOMEM);
+}
+
+void unionfs_destroy_filldir_cache(void)
+{
+ if (unionfs_filldir_cachep)
+ kmem_cache_destroy(unionfs_filldir_cachep);
+}
+
+/*
+ * This is a tuning parameter that tells us roughly how big to make the
+ * hash table in directory entries per page. This isn't perfect, but
+ * at least we get a hash table size that shouldn't be too overloaded.
+ * The following averages are based on my home directory.
+ * 14.44693 Overall
+ * 12.29 Single Page Directories
+ * 117.93 Multi-page directories
+ */
+#define DENTPAGE 4096
+#define DENTPERONEPAGE 12
+#define DENTPERPAGE 118
+#define MINHASHSIZE 1
+static int guesstimate_hash_size(struct inode *inode)
+{
+ struct inode *lower_inode;
+ int bindex;
+ int hashsize = MINHASHSIZE;
+
+ if (UNIONFS_I(inode)->hashsize > 0)
+ return UNIONFS_I(inode)->hashsize;
+
+ for (bindex = ibstart(inode); bindex <= ibend(inode); bindex++) {
+ if (!(lower_inode = unionfs_lower_inode_idx(inode, bindex)))
+ continue;
+
+ if (lower_inode->i_size == DENTPAGE)
+ hashsize += DENTPERONEPAGE;
+ else
+ hashsize += (lower_inode->i_size / DENTPAGE) *
+ DENTPERPAGE;
+ }
+
+ return hashsize;
+}
+
+int init_rdstate(struct file *file)
+{
+ BUG_ON(sizeof(loff_t) !=
+ (sizeof(unsigned int) + sizeof(unsigned int)));
+ BUG_ON(UNIONFS_F(file)->rdstate != NULL);
+
+ UNIONFS_F(file)->rdstate = alloc_rdstate(file->f_path.dentry->d_inode,
+ fbstart(file));
+
+ return (UNIONFS_F(file)->rdstate ? 0 : -ENOMEM);
+}
+
+struct unionfs_dir_state *find_rdstate(struct inode *inode, loff_t fpos)
+{
+ struct unionfs_dir_state *rdstate = NULL;
+ struct list_head *pos;
+
+ spin_lock(&UNIONFS_I(inode)->rdlock);
+ list_for_each(pos, &UNIONFS_I(inode)->readdircache) {
+ struct unionfs_dir_state *r =
+ list_entry(pos, struct unionfs_dir_state, cache);
+ if (fpos == rdstate2offset(r)) {
+ UNIONFS_I(inode)->rdcount--;
+ list_del(&r->cache);
+ rdstate = r;
+ break;
+ }
+ }
+ spin_unlock(&UNIONFS_I(inode)->rdlock);
+ return rdstate;
+}
+
+struct unionfs_dir_state *alloc_rdstate(struct inode *inode, int bindex)
+{
+ int i = 0;
+ int hashsize;
+ unsigned long mallocsize = sizeof(struct unionfs_dir_state);
+ struct unionfs_dir_state *rdstate;
+
+ hashsize = guesstimate_hash_size(inode);
+ mallocsize += hashsize * sizeof(struct list_head);
+ mallocsize = __roundup_pow_of_two(mallocsize);
+
+ /* This should give us about 500 entries anyway. */
+ if (mallocsize > PAGE_SIZE)
+ mallocsize = PAGE_SIZE;
+
+ hashsize = (mallocsize - sizeof(struct unionfs_dir_state)) /
+ sizeof(struct list_head);
+
+ rdstate = kmalloc(mallocsize, GFP_KERNEL);
+ if (!rdstate)
+ return NULL;
+
+ spin_lock(&UNIONFS_I(inode)->rdlock);
+ if (UNIONFS_I(inode)->cookie >= (MAXRDCOOKIE - 1))
+ UNIONFS_I(inode)->cookie = 1;
+ else
+ UNIONFS_I(inode)->cookie++;
+
+ rdstate->cookie = UNIONFS_I(inode)->cookie;
+ spin_unlock(&UNIONFS_I(inode)->rdlock);
+ rdstate->offset = 1;
+ rdstate->access = jiffies;
+ rdstate->bindex = bindex;
+ rdstate->dirpos = 0;
+ rdstate->hashentries = 0;
+ rdstate->size = hashsize;
+ for (i = 0; i < rdstate->size; i++)
+ INIT_LIST_HEAD(&rdstate->list[i]);
+
+ return rdstate;
+}
+
+static void free_filldir_node(struct filldir_node *node)
+{
+ if (node->namelen >= DNAME_INLINE_LEN_MIN)
+ kfree(node->name);
+ kmem_cache_free(unionfs_filldir_cachep, node);
+}
+
+void free_rdstate(struct unionfs_dir_state *state)
+{
+ struct filldir_node *tmp;
+ int i;
+
+ for (i = 0; i < state->size; i++) {
+ struct list_head *head = &(state->list[i]);
+ struct list_head *pos, *n;
+
+ /* traverse the list and deallocate space */
+ list_for_each_safe(pos, n, head) {
+ tmp = list_entry(pos, struct filldir_node, file_list);
+ list_del(&tmp->file_list);
+ free_filldir_node(tmp);
+ }
+ }
+
+ kfree(state);
+}
+
+struct filldir_node *find_filldir_node(struct unionfs_dir_state *rdstate,
+ const char *name, int namelen)
+{
+ int index;
+ unsigned int hash;
+ struct list_head *head;
+ struct list_head *pos;
+ struct filldir_node *cursor = NULL;
+ int found = 0;
+
+ BUG_ON(namelen <= 0);
+
+ hash = full_name_hash(name, namelen);
+ index = hash % rdstate->size;
+
+ head = &(rdstate->list[index]);
+ list_for_each(pos, head) {
+ cursor = list_entry(pos, struct filldir_node, file_list);
+
+ if (cursor->namelen == namelen && cursor->hash == hash &&
+ !strncmp(cursor->name, name, namelen)) {
+ /*
+ * a duplicate exists, and hence no need to create
+ * entry to the list
+ */
+ found = 1;
+
+ /*
+ * if the duplicate is in this branch, then the file
+ * system is corrupted.
+ */
+ if (cursor->bindex == rdstate->bindex) {
+ printk(KERN_DEBUG "unionfs: filldir: possible "
+ "I/O error: a file is duplicated "
+ "in the same branch %d: %s\n",
+ rdstate->bindex, cursor->name);
+ }
+ break;
+ }
+ }
+
+ if (!found)
+ cursor = NULL;
+
+ return cursor;
+}
+
+int add_filldir_node(struct unionfs_dir_state *rdstate, const char *name,
+ int namelen, int bindex, int whiteout)
+{
+ struct filldir_node *new;
+ unsigned int hash;
+ int index;
+ int err = 0;
+ struct list_head *head;
+
+ BUG_ON(namelen <= 0);
+
+ hash = full_name_hash(name, namelen);
+ index = hash % rdstate->size;
+ head = &(rdstate->list[index]);
+
+ new = kmem_cache_alloc(unionfs_filldir_cachep, GFP_KERNEL);
+ if (!new) {
+ err = -ENOMEM;
+ goto out;
+ }
+
+ INIT_LIST_HEAD(&new->file_list);
+ new->namelen = namelen;
+ new->hash = hash;
+ new->bindex = bindex;
+ new->whiteout = whiteout;
+
+ if (namelen < DNAME_INLINE_LEN_MIN)
+ new->name = new->iname;
+ else {
+ new->name = kmalloc(namelen + 1, GFP_KERNEL);
+ if (!new->name) {
+ kmem_cache_free(unionfs_filldir_cachep, new);
+ new = NULL;
+ goto out;
+ }
+ }
+
+ memcpy(new->name, name, namelen);
+ new->name[namelen] = '\0';
+
+ rdstate->hashentries++;
+
+ list_add(&(new->file_list), head);
+out:
+ return err;
+}
diff --git a/fs/unionfs/rename.c b/fs/unionfs/rename.c
new file mode 100644
index 0000000..1761f8b
--- /dev/null
+++ b/fs/unionfs/rename.c
@@ -0,0 +1,521 @@
+/*
+ * Copyright (c) 2003-2007 Erez Zadok
+ * Copyright (c) 2003-2006 Charles P. Wright
+ * Copyright (c) 2005-2007 Josef 'Jeff' Sipek
+ * Copyright (c) 2005-2006 Junjiro Okajima
+ * Copyright (c) 2005 Arun M. Krishnakumar
+ * Copyright (c) 2004-2006 David P. Quigley
+ * Copyright (c) 2003-2004 Mohammad Nayyer Zubair
+ * Copyright (c) 2003 Puja Gupta
+ * Copyright (c) 2003 Harikesavan Krishnan
+ * Copyright (c) 2003-2007 Stony Brook University
+ * Copyright (c) 2003-2007 The Research Foundation of SUNY
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include "union.h"
+
+static int __unionfs_rename(struct inode *old_dir, struct dentry *old_dentry,
+ struct inode *new_dir, struct dentry *new_dentry,
+ int bindex, struct dentry **wh_old)
+{
+ int err = 0;
+ struct dentry *lower_old_dentry;
+ struct dentry *lower_new_dentry;
+ struct dentry *lower_old_dir_dentry;
+ struct dentry *lower_new_dir_dentry;
+ struct dentry *lower_wh_dentry;
+ struct dentry *lower_wh_dir_dentry;
+ char *wh_name = NULL;
+
+ lower_new_dentry = unionfs_lower_dentry_idx(new_dentry, bindex);
+ lower_old_dentry = unionfs_lower_dentry_idx(old_dentry, bindex);
+
+ if (!lower_new_dentry) {
+ lower_new_dentry =
+ create_parents(new_dentry->d_parent->d_inode,
+ new_dentry, new_dentry->d_name.name,
+ bindex);
+ if (IS_ERR(lower_new_dentry)) {
+ printk(KERN_DEBUG "unionfs: error creating directory "
+ "tree for rename, bindex = %d, err = %ld\n",
+ bindex, PTR_ERR(lower_new_dentry));
+ err = PTR_ERR(lower_new_dentry);
+ goto out;
+ }
+ }
+
+ wh_name = alloc_whname(new_dentry->d_name.name,
+ new_dentry->d_name.len);
+ if (IS_ERR(wh_name)) {
+ err = PTR_ERR(wh_name);
+ goto out;
+ }
+
+ lower_wh_dentry = lookup_one_len(wh_name, lower_new_dentry->d_parent,
+ new_dentry->d_name.len +
+ UNIONFS_WHLEN);
+ if (IS_ERR(lower_wh_dentry)) {
+ err = PTR_ERR(lower_wh_dentry);
+ goto out;
+ }
+
+ if (lower_wh_dentry->d_inode) {
+ /* get rid of the whiteout that is existing */
+ if (lower_new_dentry->d_inode) {
+ printk(KERN_WARNING "unionfs: both a whiteout and a "
+ "dentry exist when doing a rename!\n");
+ err = -EIO;
+
+ dput(lower_wh_dentry);
+ goto out;
+ }
+
+ lower_wh_dir_dentry = lock_parent(lower_wh_dentry);
+ if (!(err = is_robranch_super(old_dentry->d_sb, bindex)))
+ err = vfs_unlink(lower_wh_dir_dentry->d_inode,
+ lower_wh_dentry);
+
+ dput(lower_wh_dentry);
+ unlock_dir(lower_wh_dir_dentry);
+ if (err)
+ goto out;
+ } else
+ dput(lower_wh_dentry);
+
+ dget(lower_old_dentry);
+ lower_old_dir_dentry = dget_parent(lower_old_dentry);
+ lower_new_dir_dentry = dget_parent(lower_new_dentry);
+
+ lock_rename(lower_old_dir_dentry, lower_new_dir_dentry);
+
+ err = is_robranch_super(old_dentry->d_sb, bindex);
+ if (err)
+ goto out_unlock;
+
+ /*
+ * ready to whiteout for old_dentry. caller will create the actual
+ * whiteout, and must dput(*wh_old)
+ */
+ if (wh_old) {
+ char *whname;
+ whname = alloc_whname(old_dentry->d_name.name,
+ old_dentry->d_name.len);
+ err = PTR_ERR(whname);
+ if (IS_ERR(whname))
+ goto out_unlock;
+ *wh_old = lookup_one_len(whname, lower_old_dir_dentry,
+ old_dentry->d_name.len +
+ UNIONFS_WHLEN);
+ kfree(whname);
+ err = PTR_ERR(*wh_old);
+ if (IS_ERR(*wh_old)) {
+ *wh_old = NULL;
+ goto out_unlock;
+ }
+ }
+
+ err = vfs_rename(lower_old_dir_dentry->d_inode, lower_old_dentry,
+ lower_new_dir_dentry->d_inode, lower_new_dentry);
+
+out_unlock:
+ unlock_rename(lower_old_dir_dentry, lower_new_dir_dentry);
+
+ dput(lower_old_dir_dentry);
+ dput(lower_new_dir_dentry);
+ dput(lower_old_dentry);
+
+out:
+ if (!err) {
+ /* Fixup the new_dentry. */
+ if (bindex < dbstart(new_dentry))
+ set_dbstart(new_dentry, bindex);
+ else if (bindex > dbend(new_dentry))
+ set_dbend(new_dentry, bindex);
+ }
+
+ kfree(wh_name);
+
+ return err;
+}
+
+/*
+ * Main rename code. This is sufficiently complex, that it's documented in
+ * Documentation/filesystems/unionfs/rename.txt. This routine calls
+ * __unionfs_rename() above to perform some of the work.
+ */
+static int do_unionfs_rename(struct inode *old_dir,
+ struct dentry *old_dentry,
+ struct inode *new_dir,
+ struct dentry *new_dentry)
+{
+ int err = 0;
+ int bindex, bwh_old;
+ int old_bstart, old_bend;
+ int new_bstart, new_bend;
+ int do_copyup = -1;
+ struct dentry *parent_dentry;
+ int local_err = 0;
+ int eio = 0;
+ int revert = 0;
+ struct dentry *wh_old = NULL;
+
+ old_bstart = dbstart(old_dentry);
+ bwh_old = old_bstart;
+ old_bend = dbend(old_dentry);
+ parent_dentry = old_dentry->d_parent;
+
+ new_bstart = dbstart(new_dentry);
+ new_bend = dbend(new_dentry);
+
+ /* Rename source to destination. */
+ err = __unionfs_rename(old_dir, old_dentry, new_dir, new_dentry,
+ old_bstart, &wh_old);
+ if (err) {
+ if (!IS_COPYUP_ERR(err))
+ goto out;
+ do_copyup = old_bstart - 1;
+ } else
+ revert = 1;
+
+ /*
+ * Unlink all instances of destination that exist to the left of
+ * bstart of source. On error, revert back, goto out.
+ */
+ for (bindex = old_bstart - 1; bindex >= new_bstart; bindex--) {
+ struct dentry *unlink_dentry;
+ struct dentry *unlink_dir_dentry;
+
+ unlink_dentry = unionfs_lower_dentry_idx(new_dentry, bindex);
+ if (!unlink_dentry)
+ continue;
+
+ unlink_dir_dentry = lock_parent(unlink_dentry);
+ if (!(err = is_robranch_super(old_dir->i_sb, bindex)))
+ err = vfs_unlink(unlink_dir_dentry->d_inode,
+ unlink_dentry);
+
+ fsstack_copy_attr_times(new_dentry->d_parent->d_inode,
+ unlink_dir_dentry->d_inode);
+ /* propagate number of hard-links */
+ new_dentry->d_parent->d_inode->i_nlink =
+ unionfs_get_nlinks(new_dentry->d_parent->d_inode);
+
+ unlock_dir(unlink_dir_dentry);
+ if (!err) {
+ if (bindex != new_bstart) {
+ dput(unlink_dentry);
+ unionfs_set_lower_dentry_idx(new_dentry,
+ bindex, NULL);
+ }
+ } else if (IS_COPYUP_ERR(err)) {
+ do_copyup = bindex - 1;
+ } else if (revert) {
+ dput(wh_old);
+ goto revert;
+ }
+ }
+
+ if (do_copyup != -1) {
+ for (bindex = do_copyup; bindex >= 0; bindex--) {
+ /*
+ * copyup the file into some left directory, so that
+ * you can rename it
+ */
+ err = copyup_dentry(old_dentry->d_parent->d_inode,
+ old_dentry, old_bstart, bindex,
+ old_dentry->d_name.name,
+ old_dentry->d_name.len,
+ NULL, old_dentry->d_inode->i_size);
+ /* if copyup failed, try next branch to the left */
+ if (err)
+ continue;
+ dput(wh_old);
+ bwh_old = bindex;
+ err = __unionfs_rename(old_dir, old_dentry,
+ new_dir, new_dentry,
+ bindex, &wh_old);
+ break;
+ }
+ }
+
+ /* make it opaque */
+ if (S_ISDIR(old_dentry->d_inode->i_mode)) {
+ err = make_dir_opaque(old_dentry, dbstart(old_dentry));
+ if (err)
+ goto revert;
+ }
+
+ /*
+ * Create whiteout for source, only if:
+ * (1) There is more than one underlying instance of source.
+ * (2) We did a copy_up
+ */
+ if ((old_bstart != old_bend) || (do_copyup != -1)) {
+ struct dentry *lower_parent;
+ if (!wh_old || wh_old->d_inode || bwh_old < 0) {
+ printk(KERN_ERR "unionfs: rename error "
+ "(wh_old=%p/%p bwh_old=%d)\n", wh_old,
+ (wh_old ? wh_old->d_inode : NULL), bwh_old);
+ err = -EIO;
+ goto out;
+ }
+ lower_parent = lock_parent(wh_old);
+ local_err = vfs_create(lower_parent->d_inode, wh_old, S_IRUGO,
+ NULL);
+ unlock_dir(lower_parent);
+ if (!local_err)
+ set_dbopaque(old_dentry, bwh_old);
+ else {
+ /*
+ * we can't fix anything now, so we cop-out and use
+ * -EIO.
+ */
+ printk(KERN_ERR "unionfs: can't create a whiteout for "
+ "the source in rename!\n");
+ err = -EIO;
+ }
+ }
+
+out:
+ dput(wh_old);
+ return err;
+
+revert:
+ /* Do revert here. */
+ local_err = unionfs_refresh_lower_dentry(new_dentry, old_bstart);
+ if (local_err) {
+ printk(KERN_WARNING "unionfs: revert failed in rename: "
+ "the new refresh failed.\n");
+ eio = -EIO;
+ }
+
+ local_err = unionfs_refresh_lower_dentry(old_dentry, old_bstart);
+ if (local_err) {
+ printk(KERN_WARNING "unionfs: revert failed in rename: "
+ "the old refresh failed.\n");
+ eio = -EIO;
+ goto revert_out;
+ }
+
+ if (!unionfs_lower_dentry_idx(new_dentry, bindex) ||
+ !unionfs_lower_dentry_idx(new_dentry, bindex)->d_inode) {
+ printk(KERN_WARNING "unionfs: revert failed in rename: "
+ "the object disappeared from under us!\n");
+ eio = -EIO;
+ goto revert_out;
+ }
+
+ if (unionfs_lower_dentry_idx(old_dentry, bindex) &&
+ unionfs_lower_dentry_idx(old_dentry, bindex)->d_inode) {
+ printk(KERN_WARNING "unionfs: revert failed in rename: "
+ "the object was created underneath us!\n");
+ eio = -EIO;
+ goto revert_out;
+ }
+
+ local_err = __unionfs_rename(new_dir, new_dentry,
+ old_dir, old_dentry, old_bstart, NULL);
+
+ /* If we can't fix it, then we cop-out with -EIO. */
+ if (local_err) {
+ printk(KERN_WARNING "unionfs: revert failed in rename!\n");
+ eio = -EIO;
+ }
+
+ local_err = unionfs_refresh_lower_dentry(new_dentry, bindex);
+ if (local_err)
+ eio = -EIO;
+ local_err = unionfs_refresh_lower_dentry(old_dentry, bindex);
+ if (local_err)
+ eio = -EIO;
+
+revert_out:
+ if (eio)
+ err = eio;
+ return err;
+}
+
+static struct dentry *lookup_whiteout(struct dentry *dentry)
+{
+ char *whname;
+ int bindex = -1, bstart = -1, bend = -1;
+ struct dentry *parent, *lower_parent, *wh_dentry;
+
+ whname = alloc_whname(dentry->d_name.name, dentry->d_name.len);
+ if (IS_ERR(whname))
+ return (void *)whname;
+
+ parent = dget_parent(dentry);
+ unionfs_lock_dentry(parent);
+ bstart = dbstart(parent);
+ bend = dbend(parent);
+ wh_dentry = ERR_PTR(-ENOENT);
+ for (bindex = bstart; bindex <= bend; bindex++) {
+ lower_parent = unionfs_lower_dentry_idx(parent, bindex);
+ if (!lower_parent)
+ continue;
+ wh_dentry = lookup_one_len(whname, lower_parent,
+ dentry->d_name.len + UNIONFS_WHLEN);
+ if (IS_ERR(wh_dentry))
+ continue;
+ if (wh_dentry->d_inode)
+ break;
+ dput(wh_dentry);
+ wh_dentry = ERR_PTR(-ENOENT);
+ }
+ unionfs_unlock_dentry(parent);
+ dput(parent);
+ kfree(whname);
+ return wh_dentry;
+}
+
+/*
+ * We can't copyup a directory, because it may involve huge numbers of
+ * children, etc. Doing that in the kernel would be bad, so instead we
+ * return EXDEV to the user-space utility that caused this, and let the
+ * user-space recurse and ask us to copy up each file separately.
+ */
+static int may_rename_dir(struct dentry *dentry)
+{
+ int err, bstart;
+
+ err = check_empty(dentry, NULL);
+ if (err == -ENOTEMPTY) {
+ if (is_robranch(dentry))
+ return -EXDEV;
+ } else if (err)
+ return err;
+
+ bstart = dbstart(dentry);
+ if (dbend(dentry) == bstart || dbopaque(dentry) == bstart)
+ return 0;
+
+ set_dbstart(dentry, bstart + 1);
+ err = check_empty(dentry, NULL);
+ set_dbstart(dentry, bstart);
+ if (err == -ENOTEMPTY)
+ err = -EXDEV;
+ return err;
+}
+
+int unionfs_rename(struct inode *old_dir, struct dentry *old_dentry,
+ struct inode *new_dir, struct dentry *new_dentry)
+{
+ int err = 0;
+ struct dentry *wh_dentry;
+
+ unionfs_read_lock(old_dentry->d_sb);
+ unionfs_double_lock_dentry(old_dentry, new_dentry);
+
+ if (!__unionfs_d_revalidate_chain(old_dentry, NULL, 0)) {
+ err = -ESTALE;
+ goto out;
+ }
+ if (!d_deleted(new_dentry) && new_dentry->d_inode &&
+ !__unionfs_d_revalidate_chain(new_dentry, NULL, 0)) {
+ err = -ESTALE;
+ goto out;
+ }
+
+ if (!S_ISDIR(old_dentry->d_inode->i_mode))
+ err = unionfs_partial_lookup(old_dentry);
+ else
+ err = may_rename_dir(old_dentry);
+
+ if (err)
+ goto out;
+
+ err = unionfs_partial_lookup(new_dentry);
+ if (err)
+ goto out;
+
+ /*
+ * if new_dentry is already lower because of whiteout,
+ * simply override it even if the whited-out dir is not empty.
+ */
+ wh_dentry = lookup_whiteout(new_dentry);
+ if (!IS_ERR(wh_dentry))
+ dput(wh_dentry);
+ else if (new_dentry->d_inode) {
+ if (S_ISDIR(old_dentry->d_inode->i_mode) !=
+ S_ISDIR(new_dentry->d_inode->i_mode)) {
+ err = S_ISDIR(old_dentry->d_inode->i_mode) ?
+ -ENOTDIR : -EISDIR;
+ goto out;
+ }
+
+ if (S_ISDIR(new_dentry->d_inode->i_mode)) {
+ struct unionfs_dir_state *namelist;
+ /* check if this unionfs directory is empty or not */
+ err = check_empty(new_dentry, &namelist);
+ if (err)
+ goto out;
+
+ if (!is_robranch(new_dentry))
+ err = delete_whiteouts(new_dentry,
+ dbstart(new_dentry),
+ namelist);
+
+ free_rdstate(namelist);
+
+ if (err)
+ goto out;
+ }
+ }
+ err = do_unionfs_rename(old_dir, old_dentry, new_dir, new_dentry);
+out:
+ if (err)
+ /* clear the new_dentry stuff created */
+ d_drop(new_dentry);
+ else {
+ /*
+ * force re-lookup since the dir on ro branch is not renamed,
+ * and lower dentries still indicate the un-renamed ones.
+ */
+ if (S_ISDIR(old_dentry->d_inode->i_mode))
+ atomic_dec(&UNIONFS_D(old_dentry)->generation);
+ else
+ unionfs_purge_extras(old_dentry);
+ if (new_dentry->d_inode &&
+ !S_ISDIR(new_dentry->d_inode->i_mode)) {
+ unionfs_purge_extras(new_dentry);
+ unionfs_inherit_mnt(new_dentry);
+ if (!unionfs_lower_inode(new_dentry->d_inode)) {
+ /*
+ * If we get here, it means that no copyup
+ * was needed, and that a file by the old
+ * name already existing on the destination
+ * branch; that file got renamed earlier in
+ * this function, so all we need to do here
+ * is set the lower inode.
+ */
+ struct inode *inode;
+ inode = unionfs_lower_inode(
+ old_dentry->d_inode);
+ atomic_inc(&inode->i_count);
+ unionfs_set_lower_inode_idx(
+ new_dentry->d_inode,
+ dbstart(new_dentry), inode);
+ }
+
+ }
+ /* if all of this renaming succeeded, update our times */
+ unionfs_copy_attr_times(old_dir);
+ unionfs_copy_attr_times(new_dir);
+ unionfs_copy_attr_times(old_dentry->d_inode);
+ unionfs_copy_attr_times(new_dentry->d_inode);
+ unionfs_check_inode(old_dir);
+ unionfs_check_inode(new_dir);
+ unionfs_check_dentry(old_dentry);
+ unionfs_check_dentry(new_dentry);
+ }
+
+ unionfs_unlock_dentry(new_dentry);
+ unionfs_unlock_dentry(old_dentry);
+ unionfs_read_unlock(old_dentry->d_sb);
+ return err;
+}
diff --git a/fs/unionfs/sioq.c b/fs/unionfs/sioq.c
new file mode 100644
index 0000000..478041d
--- /dev/null
+++ b/fs/unionfs/sioq.c
@@ -0,0 +1,123 @@
+/*
+ * Copyright (c) 2003-2007 Erez Zadok
+ * Copyright (c) 2003-2006 Charles P. Wright
+ * Copyright (c) 2005-2007 Josef 'Jeff' Sipek
+ * Copyright (c) 2005-2006 Junjiro Okajima
+ * Copyright (c) 2005 Arun M. Krishnakumar
+ * Copyright (c) 2004-2006 David P. Quigley
+ * Copyright (c) 2003-2004 Mohammad Nayyer Zubair
+ * Copyright (c) 2003 Puja Gupta
+ * Copyright (c) 2003 Harikesavan Krishnan
+ * Copyright (c) 2003-2007 Stony Brook University
+ * Copyright (c) 2003-2007 The Research Foundation of SUNY
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include "union.h"
+
+/*
+ * Super-user IO work Queue - sometimes we need to perform actions which
+ * would fail due to the unix permissions on the parent directory (e.g.,
+ * rmdir a directory which appears empty, but in reality contains
+ * whiteouts).
+ */
+
+static struct workqueue_struct *superio_workqueue;
+
+int __init init_sioq(void)
+{
+ int err;
+
+ superio_workqueue = create_workqueue("unionfs_siod");
+ if (!IS_ERR(superio_workqueue))
+ return 0;
+
+ err = PTR_ERR(superio_workqueue);
+ printk(KERN_ERR "unionfs: create_workqueue failed %d\n", err);
+ superio_workqueue = NULL;
+ return err;
+}
+
+void stop_sioq(void)
+{
+ if (superio_workqueue)
+ destroy_workqueue(superio_workqueue);
+}
+
+void run_sioq(work_func_t func, struct sioq_args *args)
+{
+ INIT_WORK(&args->work, func);
+
+ init_completion(&args->comp);
+ while (!queue_work(superio_workqueue, &args->work)) {
+ /* TODO: do accounting if needed */
+ schedule();
+ }
+ wait_for_completion(&args->comp);
+}
+
+void __unionfs_create(struct work_struct *work)
+{
+ struct sioq_args *args = container_of(work, struct sioq_args, work);
+ struct create_args *c = &args->create;
+
+ args->err = vfs_create(c->parent, c->dentry, c->mode, c->nd);
+ complete(&args->comp);
+}
+
+void __unionfs_mkdir(struct work_struct *work)
+{
+ struct sioq_args *args = container_of(work, struct sioq_args, work);
+ struct mkdir_args *m = &args->mkdir;
+
+ args->err = vfs_mkdir(m->parent, m->dentry, m->mode);
+ complete(&args->comp);
+}
+
+void __unionfs_mknod(struct work_struct *work)
+{
+ struct sioq_args *args = container_of(work, struct sioq_args, work);
+ struct mknod_args *m = &args->mknod;
+
+ args->err = vfs_mknod(m->parent, m->dentry, m->mode, m->dev);
+ complete(&args->comp);
+}
+
+void __unionfs_symlink(struct work_struct *work)
+{
+ struct sioq_args *args = container_of(work, struct sioq_args, work);
+ struct symlink_args *s = &args->symlink;
+
+ args->err = vfs_symlink(s->parent, s->dentry, s->symbuf, s->mode);
+ complete(&args->comp);
+}
+
+void __unionfs_unlink(struct work_struct *work)
+{
+ struct sioq_args *args = container_of(work, struct sioq_args, work);
+ struct unlink_args *u = &args->unlink;
+
+ args->err = vfs_unlink(u->parent, u->dentry);
+ complete(&args->comp);
+}
+
+void __delete_whiteouts(struct work_struct *work)
+{
+ struct sioq_args *args = container_of(work, struct sioq_args, work);
+ struct deletewh_args *d = &args->deletewh;
+
+ args->err = do_delete_whiteouts(d->dentry, d->bindex, d->namelist);
+ complete(&args->comp);
+}
+
+void __is_opaque_dir(struct work_struct *work)
+{
+ struct sioq_args *args = container_of(work, struct sioq_args, work);
+
+ args->ret = lookup_one_len(UNIONFS_DIR_OPAQUE, args->is_opaque.dentry,
+ sizeof(UNIONFS_DIR_OPAQUE) - 1);
+ complete(&args->comp);
+}
diff --git a/fs/unionfs/sioq.h b/fs/unionfs/sioq.h
new file mode 100644
index 0000000..e180756
--- /dev/null
+++ b/fs/unionfs/sioq.h
@@ -0,0 +1,96 @@
+/*
+ * Copyright (c) 2003-2007 Erez Zadok
+ * Copyright (c) 2003-2006 Charles P. Wright
+ * Copyright (c) 2005-2007 Josef 'Jeff' Sipek
+ * Copyright (c) 2005-2006 Junjiro Okajima
+ * Copyright (c) 2005 Arun M. Krishnakumar
+ * Copyright (c) 2004-2006 David P. Quigley
+ * Copyright (c) 2003-2004 Mohammad Nayyer Zubair
+ * Copyright (c) 2003 Puja Gupta
+ * Copyright (c) 2003 Harikesavan Krishnan
+ * Copyright (c) 2003-2007 Stony Brook University
+ * Copyright (c) 2003-2007 The Research Foundation of SUNY
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#ifndef _SIOQ_H
+#define _SIOQ_H
+
+struct deletewh_args {
+ struct unionfs_dir_state *namelist;
+ struct dentry *dentry;
+ int bindex;
+};
+
+struct is_opaque_args {
+ struct dentry *dentry;
+};
+
+struct create_args {
+ struct inode *parent;
+ struct dentry *dentry;
+ umode_t mode;
+ struct nameidata *nd;
+};
+
+struct mkdir_args {
+ struct inode *parent;
+ struct dentry *dentry;
+ umode_t mode;
+};
+
+struct mknod_args {
+ struct inode *parent;
+ struct dentry *dentry;
+ umode_t mode;
+ dev_t dev;
+};
+
+struct symlink_args {
+ struct inode *parent;
+ struct dentry *dentry;
+ char *symbuf;
+ umode_t mode;
+};
+
+struct unlink_args {
+ struct inode *parent;
+ struct dentry *dentry;
+};
+
+
+struct sioq_args {
+ struct completion comp;
+ struct work_struct work;
+ int err;
+ void *ret;
+
+ union {
+ struct deletewh_args deletewh;
+ struct is_opaque_args is_opaque;
+ struct create_args create;
+ struct mkdir_args mkdir;
+ struct mknod_args mknod;
+ struct symlink_args symlink;
+ struct unlink_args unlink;
+ };
+};
+
+/* Extern definitions for SIOQ functions */
+extern int __init init_sioq(void);
+extern void stop_sioq(void);
+extern void run_sioq(work_func_t func, struct sioq_args *args);
+
+/* Extern definitions for our privilege escalation helpers */
+extern void __unionfs_create(struct work_struct *work);
+extern void __unionfs_mkdir(struct work_struct *work);
+extern void __unionfs_mknod(struct work_struct *work);
+extern void __unionfs_symlink(struct work_struct *work);
+extern void __unionfs_unlink(struct work_struct *work);
+extern void __delete_whiteouts(struct work_struct *work);
+extern void __is_opaque_dir(struct work_struct *work);
+
+#endif /* not _SIOQ_H */
diff --git a/fs/unionfs/subr.c b/fs/unionfs/subr.c
new file mode 100644
index 0000000..5db9e62
--- /dev/null
+++ b/fs/unionfs/subr.c
@@ -0,0 +1,240 @@
+/*
+ * Copyright (c) 2003-2007 Erez Zadok
+ * Copyright (c) 2003-2006 Charles P. Wright
+ * Copyright (c) 2005-2007 Josef 'Jeff' Sipek
+ * Copyright (c) 2005-2006 Junjiro Okajima
+ * Copyright (c) 2005 Arun M. Krishnakumar
+ * Copyright (c) 2004-2006 David P. Quigley
+ * Copyright (c) 2003-2004 Mohammad Nayyer Zubair
+ * Copyright (c) 2003 Puja Gupta
+ * Copyright (c) 2003 Harikesavan Krishnan
+ * Copyright (c) 2003-2007 Stony Brook University
+ * Copyright (c) 2003-2007 The Research Foundation of SUNY
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include "union.h"
+
+/*
+ * Pass an unionfs dentry and an index. It will try to create a whiteout
+ * for the filename in dentry, and will try in branch 'index'. On error,
+ * it will proceed to a branch to the left.
+ */
+int create_whiteout(struct dentry *dentry, int start)
+{
+ int bstart, bend, bindex;
+ struct dentry *lower_dir_dentry;
+ struct dentry *lower_dentry;
+ struct dentry *lower_wh_dentry;
+ char *name = NULL;
+ int err = -EINVAL;
+
+ verify_locked(dentry);
+
+ bstart = dbstart(dentry);
+ bend = dbend(dentry);
+
+ /* create dentry's whiteout equivalent */
+ name = alloc_whname(dentry->d_name.name, dentry->d_name.len);
+ if (IS_ERR(name)) {
+ err = PTR_ERR(name);
+ goto out;
+ }
+
+ for (bindex = start; bindex >= 0; bindex--) {
+ lower_dentry = unionfs_lower_dentry_idx(dentry, bindex);
+
+ if (!lower_dentry) {
+ /*
+ * if lower dentry is not present, create the
+ * entire lower dentry directory structure and go
+ * ahead. Since we want to just create whiteout, we
+ * only want the parent dentry, and hence get rid of
+ * this dentry.
+ */
+ lower_dentry = create_parents(dentry->d_inode,
+ dentry,
+ dentry->d_name.name,
+ bindex);
+ if (!lower_dentry || IS_ERR(lower_dentry)) {
+ printk(KERN_DEBUG "unionfs: create_parents "
+ "failed for bindex = %d\n", bindex);
+ continue;
+ }
+ }
+
+ lower_wh_dentry =
+ lookup_one_len(name, lower_dentry->d_parent,
+ dentry->d_name.len + UNIONFS_WHLEN);
+ if (IS_ERR(lower_wh_dentry))
+ continue;
+
+ /*
+ * The whiteout already exists. This used to be impossible,
+ * but now is possible because of opaqueness.
+ */
+ if (lower_wh_dentry->d_inode) {
+ dput(lower_wh_dentry);
+ err = 0;
+ goto out;
+ }
+
+ lower_dir_dentry = lock_parent(lower_wh_dentry);
+ if (!(err = is_robranch_super(dentry->d_sb, bindex)))
+ err = vfs_create(lower_dir_dentry->d_inode,
+ lower_wh_dentry,
+ ~current->fs->umask & S_IRWXUGO,
+ NULL);
+ unlock_dir(lower_dir_dentry);
+ dput(lower_wh_dentry);
+
+ if (!err || !IS_COPYUP_ERR(err))
+ break;
+ }
+
+ /* set dbopaque so that lookup will not proceed after this branch */
+ if (!err)
+ set_dbopaque(dentry, bindex);
+
+out:
+ kfree(name);
+ return err;
+}
+
+/*
+ * This is a helper function for rename, which ends up with hosed over
+ * dentries when it needs to revert.
+ */
+int unionfs_refresh_lower_dentry(struct dentry *dentry, int bindex)
+{
+ struct dentry *lower_dentry;
+ struct dentry *lower_parent;
+ int err = 0;
+
+ verify_locked(dentry);
+
+ unionfs_lock_dentry(dentry->d_parent);
+ lower_parent = unionfs_lower_dentry_idx(dentry->d_parent, bindex);
+ unionfs_unlock_dentry(dentry->d_parent);
+
+ BUG_ON(!S_ISDIR(lower_parent->d_inode->i_mode));
+
+ lower_dentry = lookup_one_len(dentry->d_name.name, lower_parent,
+ dentry->d_name.len);
+ if (IS_ERR(lower_dentry)) {
+ err = PTR_ERR(lower_dentry);
+ goto out;
+ }
+
+ dput(unionfs_lower_dentry_idx(dentry, bindex));
+ iput(unionfs_lower_inode_idx(dentry->d_inode, bindex));
+ unionfs_set_lower_inode_idx(dentry->d_inode, bindex, NULL);
+
+ if (!lower_dentry->d_inode) {
+ dput(lower_dentry);
+ unionfs_set_lower_dentry_idx(dentry, bindex, NULL);
+ } else {
+ unionfs_set_lower_dentry_idx(dentry, bindex, lower_dentry);
+ unionfs_set_lower_inode_idx(dentry->d_inode, bindex,
+ igrab(lower_dentry->d_inode));
+ }
+
+out:
+ return err;
+}
+
+int make_dir_opaque(struct dentry *dentry, int bindex)
+{
+ int err = 0;
+ struct dentry *lower_dentry, *diropq;
+ struct inode *lower_dir;
+
+ lower_dentry = unionfs_lower_dentry_idx(dentry, bindex);
+ lower_dir = lower_dentry->d_inode;
+ BUG_ON(!S_ISDIR(dentry->d_inode->i_mode) ||
+ !S_ISDIR(lower_dir->i_mode));
+
+ mutex_lock(&lower_dir->i_mutex);
+ diropq = lookup_one_len(UNIONFS_DIR_OPAQUE, lower_dentry,
+ sizeof(UNIONFS_DIR_OPAQUE) - 1);
+ if (IS_ERR(diropq)) {
+ err = PTR_ERR(diropq);
+ goto out;
+ }
+
+ if (!diropq->d_inode)
+ err = vfs_create(lower_dir, diropq, S_IRUGO, NULL);
+ if (!err)
+ set_dbopaque(dentry, bindex);
+
+ dput(diropq);
+
+out:
+ mutex_unlock(&lower_dir->i_mutex);
+ return err;
+}
+
+/*
+ * returns the sum of the n_link values of all the underlying inodes of the
+ * passed inode
+ */
+int unionfs_get_nlinks(const struct inode *inode)
+{
+ int sum_nlinks = 0;
+ int dirs = 0;
+ int bindex;
+ struct inode *lower_inode;
+
+ /* don't bother to do all the work since we're unlinked */
+ if (inode->i_nlink == 0)
+ return 0;
+
+ if (!S_ISDIR(inode->i_mode))
+ return unionfs_lower_inode(inode)->i_nlink;
+
+ for (bindex = ibstart(inode); bindex <= ibend(inode); bindex++) {
+ lower_inode = unionfs_lower_inode_idx(inode, bindex);
+
+ /* ignore files */
+ if (!lower_inode || !S_ISDIR(lower_inode->i_mode))
+ continue;
+
+ BUG_ON(lower_inode->i_nlink < 0);
+
+ /* A deleted directory. */
+ if (lower_inode->i_nlink == 0)
+ continue;
+ dirs++;
+
+ /*
+ * A broken directory...
+ *
+ * Some filesystems don't properly set the number of links
+ * on empty directories
+ */
+ if (lower_inode->i_nlink == 1)
+ sum_nlinks += 2;
+ else
+ sum_nlinks += (lower_inode->i_nlink - 2);
+ }
+
+ return (!dirs ? 0 : sum_nlinks + 2);
+}
+
+/* construct whiteout filename */
+char *alloc_whname(const char *name, int len)
+{
+ char *buf;
+
+ buf = kmalloc(len + UNIONFS_WHLEN + 1, GFP_KERNEL);
+ if (!buf)
+ return ERR_PTR(-ENOMEM);
+
+ strcpy(buf, UNIONFS_WHPFX);
+ strlcat(buf, name, len + UNIONFS_WHLEN + 1);
+
+ return buf;
+}
diff --git a/fs/unionfs/super.c b/fs/unionfs/super.c
new file mode 100644
index 0000000..f4118df
--- /dev/null
+++ b/fs/unionfs/super.c
@@ -0,0 +1,1007 @@
+/*
+ * Copyright (c) 2003-2007 Erez Zadok
+ * Copyright (c) 2003-2006 Charles P. Wright
+ * Copyright (c) 2005-2007 Josef 'Jeff' Sipek
+ * Copyright (c) 2005-2006 Junjiro Okajima
+ * Copyright (c) 2005 Arun M. Krishnakumar
+ * Copyright (c) 2004-2006 David P. Quigley
+ * Copyright (c) 2003-2004 Mohammad Nayyer Zubair
+ * Copyright (c) 2003 Puja Gupta
+ * Copyright (c) 2003 Harikesavan Krishnan
+ * Copyright (c) 2003-2007 Stony Brook University
+ * Copyright (c) 2003-2007 The Research Foundation of SUNY
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include "union.h"
+
+/*
+ * The inode cache is used with alloc_inode for both our inode info and the
+ * vfs inode.
+ */
+static struct kmem_cache *unionfs_inode_cachep;
+
+static void unionfs_read_inode(struct inode *inode)
+{
+ extern struct address_space_operations unionfs_aops;
+ int size;
+ struct unionfs_inode_info *info = UNIONFS_I(inode);
+
+ unionfs_read_lock(inode->i_sb);
+
+ memset(info, 0, offsetof(struct unionfs_inode_info, vfs_inode));
+ info->bstart = -1;
+ info->bend = -1;
+ atomic_set(&info->generation,
+ atomic_read(&UNIONFS_SB(inode->i_sb)->generation));
+ spin_lock_init(&info->rdlock);
+ info->rdcount = 1;
+ info->hashsize = -1;
+ INIT_LIST_HEAD(&info->readdircache);
+
+ size = sbmax(inode->i_sb) * sizeof(struct inode *);
+ info->lower_inodes = kzalloc(size, GFP_KERNEL);
+ if (!info->lower_inodes) {
+ printk(KERN_ERR "unionfs: no kernel memory when allocating "
+ "lower-pointer array!\n");
+ BUG();
+ }
+
+ inode->i_version++;
+ inode->i_op = &unionfs_main_iops;
+ inode->i_fop = &unionfs_main_fops;
+
+ inode->i_mapping->a_ops = &unionfs_aops;
+
+ unionfs_read_unlock(inode->i_sb);
+}
+
+/*
+ * we now define delete_inode, because there are two VFS paths that may
+ * destroy an inode: one of them calls clear inode before doing everything
+ * else that's needed, and the other is fine. This way we truncate the inode
+ * size (and its pages) and then clear our own inode, which will do an iput
+ * on our and the lower inode.
+ *
+ * No need to lock sb info's rwsem.
+ */
+static void unionfs_delete_inode(struct inode *inode)
+{
+ inode->i_size = 0; /* every f/s seems to do that */
+
+ if (inode->i_data.nrpages)
+ truncate_inode_pages(&inode->i_data, 0);
+
+ clear_inode(inode);
+}
+
+/*
+ * final actions when unmounting a file system
+ *
+ * No need to lock rwsem.
+ */
+static void unionfs_put_super(struct super_block *sb)
+{
+ int bindex, bstart, bend;
+ struct unionfs_sb_info *spd;
+ int leaks = 0;
+
+ spd = UNIONFS_SB(sb);
+ if (!spd)
+ return;
+
+ bstart = sbstart(sb);
+ bend = sbend(sb);
+
+ /* Make sure we have no leaks of branchget/branchput. */
+ for (bindex = bstart; bindex <= bend; bindex++)
+ if (branch_count(sb, bindex) != 0) {
+ printk("unionfs: branch %d has %d references left!\n",
+ bindex, branch_count(sb, bindex));
+ leaks = 1;
+ }
+ BUG_ON(leaks != 0);
+
+ kfree(spd->data);
+ kfree(spd);
+ sb->s_fs_info = NULL;
+}
+
+/*
+ * Since people use this to answer the "How big of a file can I write?"
+ * question, we report the size of the highest priority branch as the size of
+ * the union.
+ */
+static int unionfs_statfs(struct dentry *dentry, struct kstatfs *buf)
+{
+ int err = 0;
+ struct super_block *sb;
+ struct dentry *lower_dentry;
+
+ sb = dentry->d_sb;
+
+ unionfs_read_lock(sb);
+ unionfs_lock_dentry(dentry);
+
+ if (!__unionfs_d_revalidate_chain(dentry, NULL, 0)) {
+ err = -ESTALE;
+ goto out;
+ }
+ unionfs_check_dentry(dentry);
+
+ lower_dentry = unionfs_lower_dentry(sb->s_root);
+ err = vfs_statfs(lower_dentry, buf);
+
+ /* set return buf to our f/s to avoid confusing user-level utils */
+ buf->f_type = UNIONFS_SUPER_MAGIC;
+ /*
+ * Our maximum file name can is shorter by a few bytes because every
+ * file name could potentially be whited-out.
+ *
+ * XXX: this restriction goes away with ODF.
+ */
+ buf->f_namelen -= UNIONFS_WHLEN;
+
+ /*
+ * reset two fields to avoid confusing user-land.
+ * XXX: is this still necessary?
+ */
+ memset(&buf->f_fsid, 0, sizeof(__kernel_fsid_t));
+ memset(&buf->f_spare, 0, sizeof(buf->f_spare));
+
+out:
+ unionfs_unlock_dentry(dentry);
+ unionfs_check_dentry(dentry);
+ unionfs_read_unlock(sb);
+ return err;
+}
+
+/* handle mode changing during remount */
+static noinline int do_remount_mode_option(char *optarg, int cur_branches,
+ struct unionfs_data *new_data,
+ struct path *new_lower_paths)
+{
+ int err = -EINVAL;
+ int perms, idx;
+ char *modename = strchr(optarg, '=');
+ struct nameidata nd;
+
+ /* by now, optarg contains the branch name */
+ if (!*optarg) {
+ printk("unionfs: no branch specified for mode change.\n");
+ goto out;
+ }
+ if (!modename) {
+ printk("unionfs: branch \"%s\" requires a mode.\n", optarg);
+ goto out;
+ }
+ *modename++ = '\0';
+ perms = __parse_branch_mode(modename);
+ if (perms == 0) {
+ printk("unionfs: invalid mode \"%s\" for \"%s\".\n",
+ modename, optarg);
+ goto out;
+ }
+
+ /*
+ * Find matching branch index. For now, this assumes that nothing
+ * has been mounted on top of this Unionfs stack. Once we have /odf
+ * and cache-coherency resolved, we'll address the branch-path
+ * uniqueness.
+ */
+ err = path_lookup(optarg, LOOKUP_FOLLOW, &nd);
+ if (err) {
+ printk(KERN_WARNING "unionfs: error accessing "
+ "lower directory \"%s\" (error %d)\n",
+ optarg, err);
+ goto out;
+ }
+ for (idx=0; idx 0) {
+ err = -EBUSY;
+ goto out;
+ }
+
+ /*
+ * Now we have to delete the branch. First, release any handles it
+ * has. Then, move the remaining array indexes past "idx" in
+ * new_data and new_lower_paths one to the left. Finally, adjust
+ * cur_branches.
+ */
+ pathput(&new_lower_paths[idx]);
+
+ if (idx < cur_branches - 1) {
+ /* if idx==cur_branches-1, we delete last branch: easy */
+ memmove(&new_data[idx], &new_data[idx+1],
+ (cur_branches - 1 - idx) *
+ sizeof(struct unionfs_data));
+ memmove(&new_lower_paths[idx], &new_lower_paths[idx+1],
+ (cur_branches - 1 - idx) * sizeof(struct path));
+ }
+
+ err = 0;
+out:
+ return err;
+}
+
+/* handle branch insertion during remount */
+static noinline int do_remount_add_option(char *optarg, int cur_branches,
+ struct unionfs_data *new_data,
+ struct path *new_lower_paths,
+ int *high_branch_id)
+{
+ int err = -EINVAL;
+ int perms;
+ int idx = 0; /* default: insert at beginning */
+ char *new_branch , *modename = NULL;
+ struct nameidata nd;
+
+ /*
+ * optarg can be of several forms:
+ *
+ * /bar:/foo insert /foo before /bar
+ * /bar:/foo=ro insert /foo in ro mode before /bar
+ * /foo insert /foo in the beginning (prepend)
+ * :/foo insert /foo at the end (append)
+ */
+ if (*optarg == ':') { /* append? */
+ new_branch = optarg + 1; /* skip ':' */
+ idx = cur_branches;
+ goto found_insertion_point;
+ }
+ new_branch = strchr(optarg, ':');
+ if (!new_branch) { /* prepend? */
+ new_branch = optarg;
+ goto found_insertion_point;
+ }
+ *new_branch++ = '\0'; /* holds path+mode of new branch */
+
+ /*
+ * Find matching branch index. For now, this assumes that nothing
+ * has been mounted on top of this Unionfs stack. Once we have /odf
+ * and cache-coherency resolved, we'll address the branch-path
+ * uniqueness.
+ */
+ err = path_lookup(optarg, LOOKUP_FOLLOW, &nd);
+ if (err) {
+ printk(KERN_WARNING "unionfs: error accessing "
+ "lower directory \"%s\" (error %d)\n",
+ optarg, err);
+ goto out;
+ }
+ for (idx=0; idx < cur_branches; idx++)
+ if (nd.mnt == new_lower_paths[idx].mnt &&
+ nd.dentry == new_lower_paths[idx].dentry)
+ break;
+ path_release(&nd); /* no longer needed */
+ if (idx == cur_branches) {
+ printk(KERN_WARNING "unionfs: branch \"%s\" "
+ "not found\n", optarg);
+ err = -ENOENT;
+ goto out;
+ }
+
+ /*
+ * At this point idx will hold the index where the new branch should
+ * be inserted before.
+ */
+found_insertion_point:
+ /* find the mode for the new branch */
+ if (new_branch)
+ modename = strchr(new_branch, '=');
+ if (modename)
+ *modename++ = '\0';
+ perms = parse_branch_mode(modename);
+
+ if (!new_branch || !*new_branch) {
+ printk(KERN_WARNING "unionfs: null new branch\n");
+ err = -EINVAL;
+ goto out;
+ }
+ err = path_lookup(new_branch, LOOKUP_FOLLOW, &nd);
+ if (err) {
+ printk(KERN_WARNING "unionfs: error accessing "
+ "lower directory \"%s\" (error %d)\n",
+ new_branch, err);
+ goto out;
+ }
+ /*
+ * It's probably safe to check_mode the new branch to insert. Note:
+ * we don't allow inserting branches which are unionfs's by
+ * themselves (check_branch returns EINVAL in that case). This is
+ * because this code base doesn't support stacking unionfs: the ODF
+ * code base supports that correctly.
+ */
+ if ((err = check_branch(&nd))) {
+ printk(KERN_WARNING "unionfs: lower directory "
+ "\"%s\" is not a valid branch\n", optarg);
+ path_release(&nd);
+ goto out;
+ }
+
+ /*
+ * Now we have to insert the new branch. But first, move the bits
+ * to make space for the new branch, if needed. Finally, adjust
+ * cur_branches.
+ * We don't release nd here; it's kept until umount/remount.
+ */
+ if (idx < cur_branches) {
+ /* if idx==cur_branches, we append: easy */
+ memmove(&new_data[idx+1], &new_data[idx],
+ (cur_branches - idx) * sizeof(struct unionfs_data));
+ memmove(&new_lower_paths[idx+1], &new_lower_paths[idx],
+ (cur_branches - idx) * sizeof(struct path));
+ }
+ new_lower_paths[idx].dentry = nd.dentry;
+ new_lower_paths[idx].mnt = nd.mnt;
+
+ new_data[idx].sb = nd.dentry->d_sb;
+ atomic_set(&new_data[idx].open_files, 0);
+ new_data[idx].branchperms = perms;
+ new_data[idx].branch_id = ++*high_branch_id; /* assign new branch ID */
+
+ err = 0;
+out:
+ return err;
+}
+
+
+/*
+ * Support branch management options on remount.
+ *
+ * See Documentation/filesystems/unionfs/ for details.
+ *
+ * @flags: numeric mount options
+ * @options: mount options string
+ *
+ * This function can rearrange a mounted union dynamically, adding and
+ * removing branches, including changing branch modes. Clearly this has to
+ * be done safely and atomically. Luckily, the VFS already calls this
+ * function with lock_super(sb) and lock_kernel() held, preventing
+ * concurrent mixing of new mounts, remounts, and unmounts. Moreover,
+ * do_remount_sb(), our caller function, already called shrink_dcache_sb(sb)
+ * to purge dentries/inodes from our superblock, and also called
+ * fsync_super(sb) to purge any dirty pages. So we're good.
+ *
+ * XXX: however, our remount code may also need to invalidate mapped pages
+ * so as to force them to be re-gotten from the (newly reconfigured) lower
+ * branches. This has to wait for proper mmap and cache coherency support
+ * in the VFS.
+ *
+ */
+static int unionfs_remount_fs(struct super_block *sb, int *flags,
+ char *options)
+{
+ int err = 0;
+ int i;
+ char *optionstmp, *tmp_to_free; /* kstrdup'ed of "options" */
+ char *optname;
+ int cur_branches = 0; /* no. of current branches */
+ int new_branches = 0; /* no. of branches actually left in the end */
+ int add_branches; /* est. no. of branches to add */
+ int del_branches; /* est. no. of branches to del */
+ int max_branches; /* max possible no. of branches */
+ struct unionfs_data *new_data = NULL, *tmp_data = NULL;
+ struct path *new_lower_paths = NULL, *tmp_lower_paths = NULL;
+ struct inode **new_lower_inodes = NULL;
+ int new_high_branch_id; /* new high branch ID */
+ int old_ibstart, old_ibend;
+ int size; /* memory allocation size, temp var */
+
+ unionfs_write_lock(sb);
+
+ /*
+ * The VFS will take care of "ro" and "rw" flags, so anything else
+ * is an error. So we need to check if any other flags may have
+ * been passed (none are allowed/supported as of now).
+ */
+ if ((*flags & ~MS_RDONLY) != 0) {
+ printk(KERN_WARNING
+ "unionfs: remount flags 0x%x unsupported\n", *flags);
+ err = -EINVAL;
+ goto out_error;
+ }
+
+ /*
+ * If 'options' is NULL, it's probably because the user just changed
+ * the union to a "ro" or "rw" and the VFS took care of it. So
+ * nothing to do and we're done.
+ */
+ if (!options || options[0] == '\0')
+ goto out_error;
+
+ /*
+ * Find out how many branches we will have in the end, counting
+ * "add" and "del" commands. Copy the "options" string because
+ * strsep modifies the string and we need it later.
+ */
+ optionstmp = tmp_to_free = kstrdup(options, GFP_KERNEL);
+ if (!optionstmp) {
+ err = -ENOMEM;
+ goto out_free;
+ }
+ new_branches = cur_branches = sbmax(sb); /* current no. branches */
+ add_branches = del_branches = 0;
+ new_high_branch_id = sbhbid(sb); /* save current high_branch_id */
+ while ((optname = strsep(&optionstmp, ",")) != NULL) {
+ char *optarg;
+
+ if (!optname || !*optname)
+ continue;
+
+ optarg = strchr(optname, '=');
+ if (optarg)
+ *optarg++ = '\0';
+
+ if (!strcmp("add", optname))
+ add_branches++;
+ else if (!strcmp("del", optname))
+ del_branches++;
+ }
+ kfree(tmp_to_free);
+ /* after all changes, will we have at least one branch left? */
+ if ((new_branches + add_branches - del_branches) < 1) {
+ printk(KERN_WARNING
+ "unionfs: no branches left after remount\n");
+ err = -EINVAL;
+ goto out_free;
+ }
+
+ /*
+ * Since we haven't actually parsed all the add/del options, nor
+ * have we checked them for errors, we don't know for sure how many
+ * branches we will have after all changes have taken place. In
+ * fact, the total number of branches left could be less than what
+ * we have now. So we need to allocate space for a temporary
+ * placeholder that is at least as large as the maximum number of
+ * branches we *could* have, which is the current number plus all
+ * the additions. Once we're done with these temp placeholders, we
+ * may have to re-allocate the final size, copy over from the temp,
+ * and then free the temps (done near the end of this function).
+ */
+ max_branches = cur_branches + add_branches;
+ /* allocate space for new pointers to lower dentry */
+ tmp_data = kcalloc(max_branches,
+ sizeof(struct unionfs_data), GFP_KERNEL);
+ if (!tmp_data) {
+ err = -ENOMEM;
+ goto out_free;
+ }
+ /* allocate space for new pointers to lower paths */
+ tmp_lower_paths = kcalloc(max_branches,
+ sizeof(struct path), GFP_KERNEL);
+ if (!tmp_lower_paths) {
+ err = -ENOMEM;
+ goto out_free;
+ }
+ /* copy current info into new placeholders, incrementing refcnts */
+ memcpy(tmp_data, UNIONFS_SB(sb)->data,
+ cur_branches * sizeof(struct unionfs_data));
+ memcpy(tmp_lower_paths, UNIONFS_D(sb->s_root)->lower_paths,
+ cur_branches * sizeof(struct path));
+ for (i=0; i UNIONFS_MAX_BRANCHES) {
+ printk("unionfs: command exceeds "
+ "%d branches\n", UNIONFS_MAX_BRANCHES);
+ err = -E2BIG;
+ goto out_release;
+ }
+ continue;
+ }
+ if (!strcmp("del", optname)) {
+ err = do_remount_del_option(optarg, new_branches,
+ tmp_data,
+ tmp_lower_paths);
+ if (err)
+ goto out_release;
+ new_branches--;
+ continue;
+ }
+ if (!strcmp("mode", optname)) {
+ err = do_remount_mode_option(optarg, new_branches,
+ tmp_data,
+ tmp_lower_paths);
+ if (err)
+ goto out_release;
+ continue;
+ }
+
+ /*
+ * When you use "mount -o remount,ro", mount(8) will
+ * reportedly pass the original dirs= string from
+ * /proc/mounts. So for now, we have to ignore dirs= and
+ * not consider it an error, unless we want to allow users
+ * to pass dirs= in remount. Note that to allow the VFS to
+ * actually process the ro/rw remount options, we have to
+ * return 0 from this function.
+ */
+ if (!strcmp("dirs", optname)) {
+ printk(KERN_WARNING
+ "unionfs: remount ignoring option \"%s\".\n",
+ optname);
+ continue;
+ }
+
+ err = -EINVAL;
+ printk(KERN_WARNING
+ "unionfs: unrecognized option \"%s\"\n", optname);
+ goto out_release;
+ }
+
+out_no_change:
+
+ /******************************************************************
+ * WE'RE ALMOST DONE: check if leftmost branch might be read-only,
+ * see if we need to allocate a small-sized new vector, copy the
+ * vectors to their correct place, release the refcnt of the older
+ * ones, and return. Also handle invalidating any pages that will
+ * have to be re-read.
+ *******************************************************************/
+
+ if (!(tmp_data[0].branchperms & MAY_WRITE)) {
+ printk("unionfs: leftmost branch cannot be read-only "
+ "(use \"remount,ro\" to create a read-only union)\n");
+ err = -EINVAL;
+ goto out_release;
+ }
+
+ /* (re)allocate space for new pointers to lower dentry */
+ size = new_branches * sizeof(struct unionfs_data);
+ new_data = krealloc(tmp_data, size, GFP_KERNEL);
+ if (!new_data) {
+ err = -ENOMEM;
+ goto out_release;
+ }
+ /* allocate space for new pointers to lower paths */
+ size = new_branches * sizeof(struct path);
+ new_lower_paths = krealloc(tmp_lower_paths, size, GFP_KERNEL);
+ if (!new_lower_paths) {
+ err = -ENOMEM;
+ goto out_release;
+ }
+ /* allocate space for new pointers to lower inodes */
+ new_lower_inodes = kcalloc(new_branches,
+ sizeof(struct inode *), GFP_KERNEL);
+ if (!new_lower_inodes) {
+ err = -ENOMEM;
+ goto out_release;
+ }
+
+ /*
+ * OK, just before we actually put the new set of branches in place,
+ * we need to ensure that our own f/s has no dirty objects left.
+ * Luckily, do_remount_sb() already calls shrink_dcache_sb(sb) and
+ * fsync_super(sb), taking care of dentries, inodes, and dirty
+ * pages. So all that's left is for us to invalidate any leftover
+ * (non-dirty) pages to ensure that they will be re-read from the
+ * new lower branches (and to support mmap).
+ */
+
+ /*
+ * Now we call drop_pagecache_sb() to invalidate all pages in this
+ * super. This function calls invalidate_inode_pages(mapping),
+ * which calls invalidate_mapping_pages(): the latter, however, will
+ * not invalidate pages which are dirty, locked, under writeback, or
+ * mapped into page tables. We shouldn't have to worry about dirty
+ * or under-writeback pages, because do_remount_sb() called
+ * fsync_super() which would not have returned until all dirty pages
+ * were flushed.
+ *
+ * But do we have to worry about locked pages? Is there any chance
+ * that in here we'll get locked pages?
+ *
+ * XXX: what about pages mapped into pagetables? Are these pages
+ * which user processes may have mmap(2)'ed? If so, then we need to
+ * invalidate those too, no? Maybe we'll have to write our own
+ * version of invalidate_mapping_pages() which also handled mapped
+ * pages.
+ *
+ * XXX: Alternatively, maybe we should call truncate_inode_pages(),
+ * which use two passes over the pages list, and will truncate all
+ * pages.
+ */
+ drop_pagecache_sb(sb);
+
+ /* copy new vectors into their correct place */
+ tmp_data = UNIONFS_SB(sb)->data;
+ UNIONFS_SB(sb)->data = new_data;
+ new_data = NULL; /* so don't free good pointers below */
+ tmp_lower_paths = UNIONFS_D(sb->s_root)->lower_paths;
+ UNIONFS_D(sb->s_root)->lower_paths = new_lower_paths;
+ new_lower_paths = NULL; /* so don't free good pointers below */
+
+ /* update our unionfs_sb_info and root dentry index of last branch */
+ i = sbmax(sb); /* save no. of branches to release at end */
+ sbend(sb) = new_branches - 1;
+ set_dbend(sb->s_root, new_branches - 1);
+ old_ibstart = ibstart(sb->s_root->d_inode);
+ old_ibend = ibend(sb->s_root->d_inode);
+ ibend(sb->s_root->d_inode) = new_branches - 1;
+ UNIONFS_D(sb->s_root)->bcount = new_branches;
+ new_branches = i; /* no. of branches to release below */
+
+ /*
+ * Update lower inodes: 3 steps
+ * 1. grab ref on all new lower inodes
+ */
+ for (i=dbstart(sb->s_root); i<=dbend(sb->s_root); i++) {
+ struct dentry *lower_dentry =
+ unionfs_lower_dentry_idx(sb->s_root, i);
+ igrab(lower_dentry->d_inode);
+ new_lower_inodes[i] = lower_dentry->d_inode;
+ }
+ /* 2. release reference on all older lower inodes */
+ for (i=old_ibstart; i<=old_ibend; i++) {
+ iput(unionfs_lower_inode_idx(sb->s_root->d_inode, i));
+ unionfs_set_lower_inode_idx(sb->s_root->d_inode, i, NULL);
+ }
+ kfree(UNIONFS_I(sb->s_root->d_inode)->lower_inodes);
+ /* 3. update root dentry's inode to new lower_inodes array */
+ UNIONFS_I(sb->s_root->d_inode)->lower_inodes = new_lower_inodes;
+ new_lower_inodes = NULL;
+
+ /* maxbytes may have changed */
+ sb->s_maxbytes = unionfs_lower_super_idx(sb, 0)->s_maxbytes;
+ /* update high branch ID */
+ sbhbid(sb) = new_high_branch_id;
+
+ /* update our sb->generation for revalidating objects */
+ i = atomic_inc_return(&UNIONFS_SB(sb)->generation);
+ atomic_set(&UNIONFS_D(sb->s_root)->generation, i);
+ atomic_set(&UNIONFS_I(sb->s_root->d_inode)->generation, i);
+ if (!(*flags & MS_SILENT))
+ printk("unionfs: new generation number %d\n", i);
+ /* finally, update the root dentry's times */
+ unionfs_copy_attr_times(sb->s_root->d_inode);
+ err = 0; /* reset to success */
+
+ /*
+ * The code above falls through to the next label, and releases the
+ * refcnts of the older ones (stored in tmp_*): if we fell through
+ * here, it means success. However, if we jump directly to this
+ * label from any error above, then an error occurred after we
+ * grabbed various refcnts, and so we have to release the
+ * temporarily constructed structures.
+ */
+out_release:
+ /* no need to cleanup/release anything in tmp_data */
+ if (tmp_lower_paths)
+ for (i=0; is_root);
+ return err;
+}
+
+/*
+ * Called by iput() when the inode reference count reached zero
+ * and the inode is not hashed anywhere. Used to clear anything
+ * that needs to be, before the inode is completely destroyed and put
+ * on the inode free list.
+ *
+ * No need to lock sb info's rwsem.
+ */
+static void unionfs_clear_inode(struct inode *inode)
+{
+ int bindex, bstart, bend;
+ struct inode *lower_inode;
+ struct list_head *pos, *n;
+ struct unionfs_dir_state *rdstate;
+
+ list_for_each_safe(pos, n, &UNIONFS_I(inode)->readdircache) {
+ rdstate = list_entry(pos, struct unionfs_dir_state, cache);
+ list_del(&rdstate->cache);
+ free_rdstate(rdstate);
+ }
+
+ /*
+ * Decrement a reference to a lower_inode, which was incremented
+ * by our read_inode when it was created initially.
+ */
+ bstart = ibstart(inode);
+ bend = ibend(inode);
+ if (bstart >= 0) {
+ for (bindex = bstart; bindex <= bend; bindex++) {
+ lower_inode = unionfs_lower_inode_idx(inode, bindex);
+ if (!lower_inode)
+ continue;
+ iput(lower_inode);
+ }
+ }
+
+ kfree(UNIONFS_I(inode)->lower_inodes);
+ UNIONFS_I(inode)->lower_inodes = NULL;
+}
+
+static struct inode *unionfs_alloc_inode(struct super_block *sb)
+{
+ struct unionfs_inode_info *i;
+
+ i = kmem_cache_alloc(unionfs_inode_cachep, GFP_KERNEL);
+ if (!i)
+ return NULL;
+
+ /* memset everything up to the inode to 0 */
+ memset(i, 0, offsetof(struct unionfs_inode_info, vfs_inode));
+
+ i->vfs_inode.i_version = 1;
+ return &i->vfs_inode;
+}
+
+static void unionfs_destroy_inode(struct inode *inode)
+{
+ kmem_cache_free(unionfs_inode_cachep, UNIONFS_I(inode));
+}
+
+/* unionfs inode cache constructor */
+static void init_once(void *v, struct kmem_cache *cachep, unsigned long flags)
+{
+ struct unionfs_inode_info *i = v;
+
+ inode_init_once(&i->vfs_inode);
+}
+
+int unionfs_init_inode_cache(void)
+{
+ int err = 0;
+
+ unionfs_inode_cachep =
+ kmem_cache_create("unionfs_inode_cache",
+ sizeof(struct unionfs_inode_info), 0,
+ SLAB_RECLAIM_ACCOUNT, init_once, NULL);
+ if (!unionfs_inode_cachep)
+ err = -ENOMEM;
+ return err;
+}
+
+/* unionfs inode cache destructor */
+void unionfs_destroy_inode_cache(void)
+{
+ if (unionfs_inode_cachep)
+ kmem_cache_destroy(unionfs_inode_cachep);
+}
+
+/*
+ * Called when we have a dirty inode, right here we only throw out
+ * parts of our readdir list that are too old.
+ *
+ * No need to grab sb info's rwsem.
+ */
+static int unionfs_write_inode(struct inode *inode, int sync)
+{
+ struct list_head *pos, *n;
+ struct unionfs_dir_state *rdstate;
+
+ spin_lock(&UNIONFS_I(inode)->rdlock);
+ list_for_each_safe(pos, n, &UNIONFS_I(inode)->readdircache) {
+ rdstate = list_entry(pos, struct unionfs_dir_state, cache);
+ /* We keep this list in LRU order. */
+ if ((rdstate->access + RDCACHE_JIFFIES) > jiffies)
+ break;
+ UNIONFS_I(inode)->rdcount--;
+ list_del(&rdstate->cache);
+ free_rdstate(rdstate);
+ }
+ spin_unlock(&UNIONFS_I(inode)->rdlock);
+
+ return 0;
+}
+
+/*
+ * Used only in nfs, to kill any pending RPC tasks, so that subsequent
+ * code can actually succeed and won't leave tasks that need handling.
+ */
+static void unionfs_umount_begin(struct vfsmount *mnt, int flags)
+{
+ struct super_block *sb, *lower_sb;
+ struct vfsmount *lower_mnt;
+ int bindex, bstart, bend;
+
+ if (!(flags & MNT_FORCE))
+ /*
+ * we are not being MNT_FORCE'd, therefore we should emulate
+ * old behavior
+ */
+ return;
+
+ sb = mnt->mnt_sb;
+
+ unionfs_read_lock(sb);
+
+ bstart = sbstart(sb);
+ bend = sbend(sb);
+ for (bindex = bstart; bindex <= bend; bindex++) {
+ lower_mnt = unionfs_lower_mnt_idx(sb->s_root, bindex);
+ lower_sb = unionfs_lower_super_idx(sb, bindex);
+
+ if (lower_mnt && lower_sb && lower_sb->s_op &&
+ lower_sb->s_op->umount_begin)
+ lower_sb->s_op->umount_begin(lower_mnt, flags);
+ }
+
+ unionfs_read_unlock(sb);
+}
+
+static int unionfs_show_options(struct seq_file *m, struct vfsmount *mnt)
+{
+ struct super_block *sb = mnt->mnt_sb;
+ int ret = 0;
+ char *tmp_page;
+ char *path;
+ int bindex, bstart, bend;
+ int perms;
+
+ unionfs_read_lock(sb);
+
+ unionfs_lock_dentry(sb->s_root);
+
+ tmp_page = (char*) __get_free_page(GFP_KERNEL);
+ if (!tmp_page) {
+ ret = -ENOMEM;
+ goto out;
+ }
+
+ bstart = sbstart(sb);
+ bend = sbend(sb);
+
+ seq_printf(m, ",dirs=");
+ for (bindex = bstart; bindex <= bend; bindex++) {
+ path = d_path(unionfs_lower_dentry_idx(sb->s_root, bindex),
+ unionfs_lower_mnt_idx(sb->s_root, bindex),
+ tmp_page, PAGE_SIZE);
+ if (IS_ERR(path)) {
+ ret = PTR_ERR(path);
+ goto out;
+ }
+
+ perms = branchperms(sb, bindex);
+
+ seq_printf(m, "%s=%s", path,
+ perms & MAY_WRITE ? "rw" : "ro");
+ if (bindex != bend)
+ seq_printf(m, ":");
+ }
+
+out:
+ free_page((unsigned long) tmp_page);
+
+ unionfs_unlock_dentry(sb->s_root);
+
+ unionfs_read_unlock(sb);
+
+ return ret;
+}
+
+struct super_operations unionfs_sops = {
+ .read_inode = unionfs_read_inode,
+ .delete_inode = unionfs_delete_inode,
+ .put_super = unionfs_put_super,
+ .statfs = unionfs_statfs,
+ .remount_fs = unionfs_remount_fs,
+ .clear_inode = unionfs_clear_inode,
+ .umount_begin = unionfs_umount_begin,
+ .show_options = unionfs_show_options,
+ .write_inode = unionfs_write_inode,
+ .alloc_inode = unionfs_alloc_inode,
+ .destroy_inode = unionfs_destroy_inode,
+};
diff --git a/fs/unionfs/union.h b/fs/unionfs/union.h
new file mode 100644
index 0000000..ba0ff50
--- /dev/null
+++ b/fs/unionfs/union.h
@@ -0,0 +1,581 @@
+/*
+ * Copyright (c) 2003-2007 Erez Zadok
+ * Copyright (c) 2003-2006 Charles P. Wright
+ * Copyright (c) 2005-2007 Josef 'Jeff' Sipek
+ * Copyright (c) 2005 Arun M. Krishnakumar
+ * Copyright (c) 2004-2006 David P. Quigley
+ * Copyright (c) 2003-2004 Mohammad Nayyer Zubair
+ * Copyright (c) 2003 Puja Gupta
+ * Copyright (c) 2003 Harikesavan Krishnan
+ * Copyright (c) 2003-2007 Stony Brook University
+ * Copyright (c) 2003-2007 The Research Foundation of SUNY
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#ifndef _UNION_H_
+#define _UNION_H_
+
+#include
+#include
+#include
+#include
+#include
+#include
+#include
+#include
+#include
+#include
+#include
+#include
+#include
+#include
+#include
+#include
+#include
+#include
+#include
+#include
+#include
+#include
+#include
+#include
+#include
+
+#include
+#include
+
+#include
+
+/* the file system name */
+#define UNIONFS_NAME "unionfs"
+
+/* unionfs root inode number */
+#define UNIONFS_ROOT_INO 1
+
+/* number of times we try to get a unique temporary file name */
+#define GET_TMPNAM_MAX_RETRY 5
+
+/* maximum number of branches we support, to avoid memory blowup */
+#define UNIONFS_MAX_BRANCHES 128
+
+/* Operations vectors defined in specific files. */
+extern struct file_operations unionfs_main_fops;
+extern struct file_operations unionfs_dir_fops;
+extern struct inode_operations unionfs_main_iops;
+extern struct inode_operations unionfs_dir_iops;
+extern struct inode_operations unionfs_symlink_iops;
+extern struct super_operations unionfs_sops;
+extern struct dentry_operations unionfs_dops;
+
+/* How long should an entry be allowed to persist */
+#define RDCACHE_JIFFIES (5*HZ)
+
+/* file private data. */
+struct unionfs_file_info {
+ int bstart;
+ int bend;
+ atomic_t generation;
+
+ struct unionfs_dir_state *rdstate;
+ struct file **lower_files;
+ int *saved_branch_ids; /* IDs of branches when file was opened */
+};
+
+/* unionfs inode data in memory */
+struct unionfs_inode_info {
+ int bstart;
+ int bend;
+ atomic_t generation;
+ int stale;
+ /* Stuff for readdir over NFS. */
+ spinlock_t rdlock;
+ struct list_head readdircache;
+ int rdcount;
+ int hashsize;
+ int cookie;
+
+ /* The lower inodes */
+ struct inode **lower_inodes;
+ /* to keep track of reads/writes for unlinks before closes */
+ atomic_t totalopens;
+
+ struct inode vfs_inode;
+};
+
+/* unionfs dentry data in memory */
+struct unionfs_dentry_info {
+ /*
+ * The semaphore is used to lock the dentry as soon as we get into a
+ * unionfs function from the VFS. Our lock ordering is that children
+ * go before their parents.
+ */
+ struct mutex lock;
+ int bstart;
+ int bend;
+ int bopaque;
+ int bcount;
+ atomic_t generation;
+ struct path *lower_paths;
+};
+
+/* These are the pointers to our various objects. */
+struct unionfs_data {
+ struct super_block *sb;
+ atomic_t open_files; /* number of open files on branch */
+ int branchperms;
+ int branch_id; /* unique branch ID at re/mount time */
+};
+
+/* unionfs super-block data in memory */
+struct unionfs_sb_info {
+ int bend;
+
+ atomic_t generation;
+
+ /*
+ * This rwsem is used to make sure that a branch management
+ * operation...
+ * 1) will not begin before all currently in-flight operations
+ * complete
+ * 2) any new operations do not execute until the currently
+ * running branch management operation completes
+ */
+ struct rw_semaphore rwsem;
+ int high_branch_id; /* last unique branch ID given */
+ struct unionfs_data *data;
+};
+
+/*
+ * structure for making the linked list of entries by readdir on left branch
+ * to compare with entries on right branch
+ */
+struct filldir_node {
+ struct list_head file_list; /* list for directory entries */
+ char *name; /* name entry */
+ int hash; /* name hash */
+ int namelen; /* name len since name is not 0 terminated */
+
+ /*
+ * we can check for duplicate whiteouts and files in the same branch
+ * in order to return -EIO.
+ */
+ int bindex;
+
+ /* is this a whiteout entry? */
+ int whiteout;
+
+ /* Inline name, so we don't need to separately kmalloc small ones */
+ char iname[DNAME_INLINE_LEN_MIN];
+};
+
+/* Directory hash table. */
+struct unionfs_dir_state {
+ unsigned int cookie; /* the cookie, based off of rdversion */
+ unsigned int offset; /* The entry we have returned. */
+ int bindex;
+ loff_t dirpos; /* offset within the lower level directory */
+ int size; /* How big is the hash table? */
+ int hashentries; /* How many entries have been inserted? */
+ unsigned long access;
+
+ /* This cache list is used when the inode keeps us around. */
+ struct list_head cache;
+ struct list_head list[0];
+};
+
+/* externs needed for fanout.h or sioq.h */
+extern int unionfs_get_nlinks(const struct inode *inode);
+
+/* include miscellaneous macros */
+#include "fanout.h"
+#include "sioq.h"
+
+/* externs for cache creation/deletion routines */
+extern void unionfs_destroy_filldir_cache(void);
+extern int unionfs_init_filldir_cache(void);
+extern int unionfs_init_inode_cache(void);
+extern void unionfs_destroy_inode_cache(void);
+extern int unionfs_init_dentry_cache(void);
+extern void unionfs_destroy_dentry_cache(void);
+
+/* Initialize and free readdir-specific state. */
+extern int init_rdstate(struct file *file);
+extern struct unionfs_dir_state *alloc_rdstate(struct inode *inode,
+ int bindex);
+extern struct unionfs_dir_state *find_rdstate(struct inode *inode,
+ loff_t fpos);
+extern void free_rdstate(struct unionfs_dir_state *state);
+extern int add_filldir_node(struct unionfs_dir_state *rdstate,
+ const char *name, int namelen, int bindex,
+ int whiteout);
+extern struct filldir_node *find_filldir_node(struct unionfs_dir_state *rdstate,
+ const char *name, int namelen);
+
+extern struct dentry **alloc_new_dentries(int objs);
+extern struct unionfs_data *alloc_new_data(int objs);
+
+/* We can only use 32-bits of offset for rdstate --- blech! */
+#define DIREOF (0xfffff)
+#define RDOFFBITS 20 /* This is the number of bits in DIREOF. */
+#define MAXRDCOOKIE (0xfff)
+/* Turn an rdstate into an offset. */
+static inline off_t rdstate2offset(struct unionfs_dir_state *buf)
+{
+ off_t tmp;
+
+ tmp = ((buf->cookie & MAXRDCOOKIE) << RDOFFBITS)
+ | (buf->offset & DIREOF);
+ return tmp;
+}
+
+#define unionfs_read_lock(sb) down_read(&UNIONFS_SB(sb)->rwsem)
+#define unionfs_read_unlock(sb) up_read(&UNIONFS_SB(sb)->rwsem)
+#define unionfs_write_lock(sb) down_write(&UNIONFS_SB(sb)->rwsem)
+#define unionfs_write_unlock(sb) up_write(&UNIONFS_SB(sb)->rwsem)
+
+static inline void unionfs_double_lock_dentry(struct dentry *d1,
+ struct dentry *d2)
+{
+ if (d2 < d1) {
+ struct dentry *tmp = d1;
+ d1 = d2;
+ d2 = tmp;
+ }
+ unionfs_lock_dentry(d1);
+ unionfs_lock_dentry(d2);
+}
+
+extern int new_dentry_private_data(struct dentry *dentry);
+extern void free_dentry_private_data(struct dentry *dentry);
+extern void update_bstart(struct dentry *dentry);
+
+/*
+ * EXTERNALS:
+ */
+
+/* replicates the directory structure up to given dentry in given branch */
+extern struct dentry *create_parents(struct inode *dir, struct dentry *dentry,
+ const char *name, int bindex);
+extern int make_dir_opaque(struct dentry *dir, int bindex);
+
+/* partial lookup */
+extern int unionfs_partial_lookup(struct dentry *dentry);
+
+/*
+ * Pass an unionfs dentry and an index and it will try to create a whiteout
+ * in branch 'index'.
+ *
+ * On error, it will proceed to a branch to the left
+ */
+extern int create_whiteout(struct dentry *dentry, int start);
+/* copies a file from dbstart to newbindex branch */
+extern int copyup_file(struct inode *dir, struct file *file, int bstart,
+ int newbindex, loff_t size);
+extern int copyup_named_file(struct inode *dir, struct file *file,
+ char *name, int bstart, int new_bindex,
+ loff_t len);
+/* copies a dentry from dbstart to newbindex branch */
+extern int copyup_dentry(struct inode *dir, struct dentry *dentry,
+ int bstart, int new_bindex, const char *name,
+ int namelen, struct file **copyup_file, loff_t len);
+/* helper functions for post-copyup cleanup */
+extern void unionfs_inherit_mnt(struct dentry *dentry);
+extern void unionfs_purge_extras(struct dentry *dentry);
+
+extern int remove_whiteouts(struct dentry *dentry,
+ struct dentry *lower_dentry, int bindex);
+
+extern int do_delete_whiteouts(struct dentry *dentry, int bindex,
+ struct unionfs_dir_state *namelist);
+
+/* Is this directory empty: 0 if it is empty, -ENOTEMPTY if not. */
+extern int check_empty(struct dentry *dentry,
+ struct unionfs_dir_state **namelist);
+/* Delete whiteouts from this directory in branch bindex. */
+extern int delete_whiteouts(struct dentry *dentry, int bindex,
+ struct unionfs_dir_state *namelist);
+
+/* Re-lookup a lower dentry. */
+extern int unionfs_refresh_lower_dentry(struct dentry *dentry, int bindex);
+
+extern void unionfs_reinterpose(struct dentry *this_dentry);
+extern struct super_block *unionfs_duplicate_super(struct super_block *sb);
+
+/* Locking functions. */
+extern int unionfs_setlk(struct file *file, int cmd, struct file_lock *fl);
+extern int unionfs_getlk(struct file *file, struct file_lock *fl);
+
+/* Common file operations. */
+extern int unionfs_file_revalidate(struct file *file, int willwrite);
+extern int unionfs_open(struct inode *inode, struct file *file);
+extern int unionfs_file_release(struct inode *inode, struct file *file);
+extern int unionfs_flush(struct file *file, fl_owner_t id);
+extern long unionfs_ioctl(struct file *file, unsigned int cmd,
+ unsigned long arg);
+extern int unionfs_fsync(struct file *file, struct dentry *dentry,
+ int datasync);
+extern int unionfs_fasync(int fd, struct file *file, int flag);
+
+/* Inode operations */
+extern int unionfs_rename(struct inode *old_dir, struct dentry *old_dentry,
+ struct inode *new_dir, struct dentry *new_dentry);
+extern int unionfs_unlink(struct inode *dir, struct dentry *dentry);
+extern int unionfs_rmdir(struct inode *dir, struct dentry *dentry);
+
+extern int __unionfs_d_revalidate_chain(struct dentry *dentry,
+ struct nameidata *nd, int willwrite);
+extern int is_newer_lower(const struct dentry *dentry);
+
+/* The values for unionfs_interpose's flag. */
+#define INTERPOSE_DEFAULT 0
+#define INTERPOSE_LOOKUP 1
+#define INTERPOSE_REVAL 2
+#define INTERPOSE_REVAL_NEG 3
+#define INTERPOSE_PARTIAL 4
+
+extern struct dentry *unionfs_interpose(struct dentry *this_dentry,
+ struct super_block *sb, int flag);
+
+#ifdef CONFIG_UNION_FS_XATTR
+/* Extended attribute functions. */
+extern void *unionfs_xattr_alloc(size_t size, size_t limit);
+
+extern ssize_t unionfs_getxattr(struct dentry *dentry, const char *name,
+ void *value, size_t size);
+extern int unionfs_removexattr(struct dentry *dentry, const char *name);
+extern ssize_t unionfs_listxattr(struct dentry *dentry, char *list,
+ size_t size);
+extern int unionfs_setxattr(struct dentry *dentry, const char *name,
+ const void *value, size_t size, int flags);
+#endif /* CONFIG_UNION_FS_XATTR */
+
+/* The root directory is unhashed, but isn't deleted. */
+static inline int d_deleted(struct dentry *d)
+{
+ return d_unhashed(d) && (d != d->d_sb->s_root);
+}
+
+struct dentry *unionfs_lookup_backend(struct dentry *dentry,
+ struct nameidata *nd, int lookupmode);
+
+/* unionfs_permission, check if we should bypass error to facilitate copyup */
+#define IS_COPYUP_ERR(err) ((err) == -EROFS)
+
+/* unionfs_open, check if we need to copyup the file */
+#define OPEN_WRITE_FLAGS (O_WRONLY | O_RDWR | O_APPEND)
+#define IS_WRITE_FLAG(flag) ((flag) & OPEN_WRITE_FLAGS)
+
+static inline int branchperms(const struct super_block *sb, int index)
+{
+ BUG_ON(index < 0);
+ return UNIONFS_SB(sb)->data[index].branchperms;
+}
+
+static inline int set_branchperms(struct super_block *sb, int index, int perms)
+{
+ BUG_ON(index < 0);
+ UNIONFS_SB(sb)->data[index].branchperms = perms;
+ return perms;
+}
+
+/* Is this file on a read-only branch? */
+static inline int is_robranch_super(const struct super_block *sb, int index)
+{
+ int ret;
+
+ ret = (!(branchperms(sb, index) & MAY_WRITE)) ? -EROFS : 0;
+ return ret;
+}
+
+/* Is this file on a read-only branch? */
+static inline int is_robranch_idx(const struct dentry *dentry, int index)
+{
+ int err = 0;
+
+ BUG_ON(index < 0);
+
+ if ((!(branchperms(dentry->d_sb, index) & MAY_WRITE)) ||
+ IS_RDONLY(unionfs_lower_dentry_idx(dentry, index)->d_inode))
+ err = -EROFS;
+ return err;
+}
+
+static inline int is_robranch(const struct dentry *dentry)
+{
+ int index;
+
+ index = UNIONFS_D(dentry)->bstart;
+ BUG_ON(index < 0);
+
+ return is_robranch_idx(dentry, index);
+}
+
+/* What do we use for whiteouts. */
+#define UNIONFS_WHPFX ".wh."
+#define UNIONFS_WHLEN 4
+/*
+ * If a directory contains this file, then it is opaque. We start with the
+ * .wh. flag so that it is blocked by lookup.
+ */
+#define UNIONFS_DIR_OPAQUE_NAME "__dir_opaque"
+#define UNIONFS_DIR_OPAQUE UNIONFS_WHPFX UNIONFS_DIR_OPAQUE_NAME
+
+#ifndef DEFAULT_POLLMASK
+#define DEFAULT_POLLMASK (POLLIN | POLLOUT | POLLRDNORM | POLLWRNORM)
+#endif /* not DEFAULT_POLLMASK */
+
+/*
+ * EXTERNALS:
+ */
+extern char *alloc_whname(const char *name, int len);
+extern int check_branch(struct nameidata *nd);
+extern int __parse_branch_mode(const char *name);
+extern int parse_branch_mode(const char *name);
+
+/*
+ * These two functions are here because it is kind of daft to copy and paste
+ * the contents of the two functions to 32+ places in unionfs
+ */
+static inline struct dentry *lock_parent(struct dentry *dentry)
+{
+ struct dentry *dir = dget(dentry->d_parent);
+
+ mutex_lock(&dir->d_inode->i_mutex);
+ return dir;
+}
+
+static inline void unlock_dir(struct dentry *dir)
+{
+ mutex_unlock(&dir->d_inode->i_mutex);
+ dput(dir);
+}
+
+static inline struct vfsmount *unionfs_mntget(struct dentry *dentry,
+ int bindex)
+{
+ struct vfsmount *mnt;
+
+ if (!dentry) {
+ if (bindex < 0)
+ return NULL;
+ if (!dentry && bindex >= 0) {
+#ifdef UNIONFS_DEBUG
+ printk(KERN_DEBUG
+ "unionfs_mntget: dentry=%p bindex=%d\n",
+ dentry, bindex);
+#endif /* UNIONFS_DEBUG */
+ return NULL;
+ }
+ }
+ mnt = unionfs_lower_mnt_idx(dentry, bindex);
+ if (!mnt) {
+ if (bindex < 0)
+ return NULL;
+ if (!mnt && bindex >= 0) {
+#ifdef UNIONFS_DEBUG
+ printk(KERN_DEBUG
+ "unionfs_mntget: mnt=%p bindex=%d\n",
+ mnt, bindex);
+#endif /* UNIONFS_DEBUG */
+ return NULL;
+ }
+ }
+ mnt = mntget(mnt);
+ return mnt;
+}
+
+static inline void unionfs_mntput(struct dentry *dentry, int bindex)
+{
+ struct vfsmount *mnt;
+
+ if (!dentry) {
+ if (bindex < 0)
+ return;
+ if (!dentry && bindex >= 0) {
+#ifdef UNIONFS_DEBUG
+ printk(KERN_DEBUG
+ "unionfs_mntput: dentry=%p bindex=%d\n",
+ dentry, bindex);
+#endif /* UNIONFS_DEBUG */
+ return;
+ }
+ }
+ mnt = unionfs_lower_mnt_idx(dentry, bindex);
+ if (!mnt) {
+ if (bindex < 0)
+ return;
+ if (!mnt && bindex >= 0) {
+#ifdef UNIONFS_DEBUG
+ /*
+ * Directories can have NULL lower objects in
+ * between start/end, but NOT if at the start/end
+ * range. We cannot verify that this dentry is a
+ * type=DIR, because it may already be a negative
+ * dentry. But if dbstart is greater than dbend, we
+ * know that this couldn't have been a regular file:
+ * it had to have been a directory.
+ */
+ if (!(bindex > dbstart(dentry) && bindex < dbend(dentry)))
+ printk(KERN_WARNING
+ "unionfs_mntput: mnt=%p bindex=%d\n",
+ mnt, bindex);
+#endif /* UNIONFS_DEBUG */
+ return;
+ }
+ }
+ mntput(mnt);
+}
+
+#ifdef UNIONFS_DEBUG
+
+/* useful for tracking code reachability */
+#define UDBG printk("DBG:%s:%s:%d\n",__FILE__,__FUNCTION__,__LINE__)
+
+#define unionfs_check_inode(i) __unionfs_check_inode((i), \
+ __FILE__,__FUNCTION__,__LINE__)
+#define unionfs_check_dentry(d) __unionfs_check_dentry((d), \
+ __FILE__,__FUNCTION__,__LINE__)
+#define unionfs_check_file(f) __unionfs_check_file((f), \
+ __FILE__,__FUNCTION__,__LINE__)
+#define show_branch_counts(sb) __show_branch_counts((sb), \
+ __FILE__,__FUNCTION__,__LINE__)
+#define show_inode_times(i) __show_inode_times((i), \
+ __FILE__,__FUNCTION__,__LINE__)
+#define show_dinode_times(d) __show_dinode_times((d), \
+ __FILE__,__FUNCTION__,__LINE__)
+#define show_inode_counts(i) __show_inode_counts((i), \
+ __FILE__,__FUNCTION__,__LINE__)
+
+extern void __unionfs_check_inode(const struct inode *inode, const char *fname,
+ const char *fxn, int line);
+extern void __unionfs_check_dentry(const struct dentry *dentry,
+ const char *fname, const char *fxn,
+ int line);
+extern void __unionfs_check_file(const struct file *file,
+ const char *fname, const char *fxn, int line);
+extern void __show_branch_counts(const struct super_block *sb,
+ const char *file, const char *fxn, int line);
+extern void __show_inode_times(const struct inode *inode,
+ const char *file, const char *fxn, int line);
+extern void __show_dinode_times(const struct dentry *dentry,
+ const char *file, const char *fxn, int line);
+extern void __show_inode_counts(const struct inode *inode,
+ const char *file, const char *fxn, int line);
+
+#else /* not UNIONFS_DEBUG */
+
+/* we leave useful hooks for these check functions throughout the code */
+#define unionfs_check_inode(i)
+#define unionfs_check_dentry(d)
+#define unionfs_check_file(f)
+#define show_branch_counts(sb)
+#define show_inode_times(i)
+#define show_dinode_times(d)
+#define show_inode_counts(i)
+
+#endif /* not UNIONFS_DEBUG */
+
+#endif /* not _UNION_H_ */
diff --git a/fs/unionfs/unlink.c b/fs/unionfs/unlink.c
new file mode 100644
index 0000000..47bebab
--- /dev/null
+++ b/fs/unionfs/unlink.c
@@ -0,0 +1,192 @@
+/*
+ * Copyright (c) 2003-2007 Erez Zadok
+ * Copyright (c) 2003-2006 Charles P. Wright
+ * Copyright (c) 2005-2007 Josef 'Jeff' Sipek
+ * Copyright (c) 2005-2006 Junjiro Okajima
+ * Copyright (c) 2005 Arun M. Krishnakumar
+ * Copyright (c) 2004-2006 David P. Quigley
+ * Copyright (c) 2003-2004 Mohammad Nayyer Zubair
+ * Copyright (c) 2003 Puja Gupta
+ * Copyright (c) 2003 Harikesavan Krishnan
+ * Copyright (c) 2003-2007 Stony Brook University
+ * Copyright (c) 2003-2007 The Research Foundation of SUNY
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include "union.h"
+
+/* unlink a file by creating a whiteout */
+static int unionfs_unlink_whiteout(struct inode *dir, struct dentry *dentry)
+{
+ struct dentry *lower_dentry;
+ struct dentry *lower_dir_dentry;
+ int bindex;
+ int err = 0;
+
+ if ((err = unionfs_partial_lookup(dentry)))
+ goto out;
+
+ bindex = dbstart(dentry);
+
+ lower_dentry = unionfs_lower_dentry_idx(dentry, bindex);
+ if (!lower_dentry)
+ goto out;
+
+ lower_dir_dentry = lock_parent(lower_dentry);
+
+ /* avoid destroying the lower inode if the file is in use */
+ dget(lower_dentry);
+ if (!(err = is_robranch_super(dentry->d_sb, bindex)))
+ err = vfs_unlink(lower_dir_dentry->d_inode, lower_dentry);
+ /* if vfs_unlink succeeded, update our inode's times */
+ if (!err)
+ unionfs_copy_attr_times(dentry->d_inode);
+ dput(lower_dentry);
+ fsstack_copy_attr_times(dir, lower_dir_dentry->d_inode);
+ unlock_dir(lower_dir_dentry);
+
+ if (err && !IS_COPYUP_ERR(err))
+ goto out;
+
+ if (err) {
+ if (dbstart(dentry) == 0)
+ goto out;
+ err = create_whiteout(dentry, dbstart(dentry) - 1);
+ } else if (dbopaque(dentry) != -1)
+ /* There is a lower lower-priority file with the same name. */
+ err = create_whiteout(dentry, dbopaque(dentry));
+ else
+ err = create_whiteout(dentry, dbstart(dentry));
+
+out:
+ if (!err)
+ dentry->d_inode->i_nlink--;
+
+ /* We don't want to leave negative leftover dentries for revalidate. */
+ if (!err && (dbopaque(dentry) != -1))
+ update_bstart(dentry);
+
+ return err;
+}
+
+int unionfs_unlink(struct inode *dir, struct dentry *dentry)
+{
+ int err = 0;
+
+ unionfs_read_lock(dentry->d_sb);
+ unionfs_lock_dentry(dentry);
+
+ if (!__unionfs_d_revalidate_chain(dentry, NULL, 0)) {
+ err = -ESTALE;
+ goto out;
+ }
+ unionfs_check_dentry(dentry);
+
+ err = unionfs_unlink_whiteout(dir, dentry);
+ /* call d_drop so the system "forgets" about us */
+ if (!err) {
+ if (!S_ISDIR(dentry->d_inode->i_mode))
+ unionfs_purge_extras(dentry);
+ d_drop(dentry);
+ /*
+ * if unlink/whiteout succeeded, parent dir mtime has
+ * changed
+ */
+ unionfs_copy_attr_times(dir);
+ }
+
+out:
+ if (!err) {
+ unionfs_check_dentry(dentry);
+ unionfs_check_inode(dir);
+ }
+ unionfs_unlock_dentry(dentry);
+ unionfs_read_unlock(dentry->d_sb);
+ return err;
+}
+
+static int unionfs_rmdir_first(struct inode *dir, struct dentry *dentry,
+ struct unionfs_dir_state *namelist)
+{
+ int err;
+ struct dentry *lower_dentry;
+ struct dentry *lower_dir_dentry = NULL;
+
+ /* Here we need to remove whiteout entries. */
+ err = delete_whiteouts(dentry, dbstart(dentry), namelist);
+ if (err)
+ goto out;
+
+ lower_dentry = unionfs_lower_dentry(dentry);
+
+ lower_dir_dentry = lock_parent(lower_dentry);
+
+ /* avoid destroying the lower inode if the file is in use */
+ dget(lower_dentry);
+ if (!(err = is_robranch(dentry)))
+ err = vfs_rmdir(lower_dir_dentry->d_inode, lower_dentry);
+ dput(lower_dentry);
+
+ fsstack_copy_attr_times(dir, lower_dir_dentry->d_inode);
+ /* propagate number of hard-links */
+ dentry->d_inode->i_nlink = unionfs_get_nlinks(dentry->d_inode);
+
+out:
+ if (lower_dir_dentry)
+ unlock_dir(lower_dir_dentry);
+ return err;
+}
+
+int unionfs_rmdir(struct inode *dir, struct dentry *dentry)
+{
+ int err = 0;
+ struct unionfs_dir_state *namelist = NULL;
+
+ unionfs_read_lock(dentry->d_sb);
+ unionfs_lock_dentry(dentry);
+
+ if (!__unionfs_d_revalidate_chain(dentry, NULL, 0)) {
+ err = -ESTALE;
+ goto out;
+ }
+ unionfs_check_dentry(dentry);
+
+ /* check if this unionfs directory is empty or not */
+ err = check_empty(dentry, &namelist);
+ if (err)
+ goto out;
+
+ err = unionfs_rmdir_first(dir, dentry, namelist);
+ /* create whiteout */
+ if (!err)
+ err = create_whiteout(dentry, dbstart(dentry));
+ else {
+ int new_err;
+
+ if (dbstart(dentry) == 0)
+ goto out;
+
+ /* exit if the error returned was NOT -EROFS */
+ if (!IS_COPYUP_ERR(err))
+ goto out;
+
+ new_err = create_whiteout(dentry, dbstart(dentry) - 1);
+ if (new_err != -EEXIST)
+ err = new_err;
+ }
+
+out:
+ /* call d_drop so the system "forgets" about us */
+ if (!err)
+ d_drop(dentry);
+
+ if (namelist)
+ free_rdstate(namelist);
+
+ unionfs_unlock_dentry(dentry);
+ unionfs_read_unlock(dentry->d_sb);
+ return err;
+}
diff --git a/fs/unionfs/xattr.c b/fs/unionfs/xattr.c
new file mode 100644
index 0000000..ee7da13
--- /dev/null
+++ b/fs/unionfs/xattr.c
@@ -0,0 +1,153 @@
+/*
+ * Copyright (c) 2003-2007 Erez Zadok
+ * Copyright (c) 2003-2006 Charles P. Wright
+ * Copyright (c) 2005-2007 Josef 'Jeff' Sipek
+ * Copyright (c) 2005-2006 Junjiro Okajima
+ * Copyright (c) 2005 Arun M. Krishnakumar
+ * Copyright (c) 2004-2006 David P. Quigley
+ * Copyright (c) 2003-2004 Mohammad Nayyer Zubair
+ * Copyright (c) 2003 Puja Gupta
+ * Copyright (c) 2003 Harikesavan Krishnan
+ * Copyright (c) 2003-2007 Stony Brook University
+ * Copyright (c) 2003-2007 The Research Foundation of SUNY
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include "union.h"
+
+/* This is lifted from fs/xattr.c */
+void *unionfs_xattr_alloc(size_t size, size_t limit)
+{
+ void *ptr;
+
+ if (size > limit)
+ return ERR_PTR(-E2BIG);
+
+ if (!size) /* size request, no buffer is needed */
+ return NULL;
+
+ ptr = kmalloc(size, GFP_KERNEL);
+ if (!ptr)
+ return ERR_PTR(-ENOMEM);
+ return ptr;
+}
+
+/*
+ * BKL held by caller.
+ * dentry->d_inode->i_mutex locked
+ */
+ssize_t unionfs_getxattr(struct dentry *dentry, const char *name, void *value,
+ size_t size)
+{
+ struct dentry *lower_dentry = NULL;
+ int err = -EOPNOTSUPP;
+
+ unionfs_read_lock(dentry->d_sb);
+ unionfs_lock_dentry(dentry);
+
+ if (!__unionfs_d_revalidate_chain(dentry, NULL, 0)) {
+ err = -ESTALE;
+ goto out;
+ }
+
+ lower_dentry = unionfs_lower_dentry(dentry);
+
+ err = vfs_getxattr(lower_dentry, (char*) name, value, size);
+
+out:
+ unionfs_unlock_dentry(dentry);
+ unionfs_check_dentry(dentry);
+ unionfs_read_unlock(dentry->d_sb);
+ return err;
+}
+
+/*
+ * BKL held by caller.
+ * dentry->d_inode->i_mutex locked
+ */
+int unionfs_setxattr(struct dentry *dentry, const char *name,
+ const void *value, size_t size, int flags)
+{
+ struct dentry *lower_dentry = NULL;
+ int err = -EOPNOTSUPP;
+
+ unionfs_read_lock(dentry->d_sb);
+ unionfs_lock_dentry(dentry);
+
+ if (!__unionfs_d_revalidate_chain(dentry, NULL, 0)) {
+ err = -ESTALE;
+ goto out;
+ }
+
+ lower_dentry = unionfs_lower_dentry(dentry);
+
+ err = vfs_setxattr(lower_dentry, (char*) name, (void*) value,
+ size, flags);
+
+out:
+ unionfs_unlock_dentry(dentry);
+ unionfs_check_dentry(dentry);
+ unionfs_read_unlock(dentry->d_sb);
+ return err;
+}
+
+/*
+ * BKL held by caller.
+ * dentry->d_inode->i_mutex locked
+ */
+int unionfs_removexattr(struct dentry *dentry, const char *name)
+{
+ struct dentry *lower_dentry = NULL;
+ int err = -EOPNOTSUPP;
+
+ unionfs_read_lock(dentry->d_sb);
+ unionfs_lock_dentry(dentry);
+
+ if (!__unionfs_d_revalidate_chain(dentry, NULL, 0)) {
+ err = -ESTALE;
+ goto out;
+ }
+
+ lower_dentry = unionfs_lower_dentry(dentry);
+
+ err = vfs_removexattr(lower_dentry, (char*) name);
+
+out:
+ unionfs_unlock_dentry(dentry);
+ unionfs_check_dentry(dentry);
+ unionfs_read_unlock(dentry->d_sb);
+ return err;
+}
+
+/*
+ * BKL held by caller.
+ * dentry->d_inode->i_mutex locked
+ */
+ssize_t unionfs_listxattr(struct dentry *dentry, char *list, size_t size)
+{
+ struct dentry *lower_dentry = NULL;
+ int err = -EOPNOTSUPP;
+ char *encoded_list = NULL;
+
+ unionfs_read_lock(dentry->d_sb);
+ unionfs_lock_dentry(dentry);
+
+ if (!__unionfs_d_revalidate_chain(dentry, NULL, 0)) {
+ err = -ESTALE;
+ goto out;
+ }
+
+ lower_dentry = unionfs_lower_dentry(dentry);
+
+ encoded_list = list;
+ err = vfs_listxattr(lower_dentry, encoded_list, size);
+
+out:
+ unionfs_unlock_dentry(dentry);
+ unionfs_check_dentry(dentry);
+ unionfs_read_unlock(dentry->d_sb);
+ return err;
+}
diff --git a/include/linux/fs_stack.h b/include/linux/fs_stack.h
index bb516ce..2599c5b 100644
--- a/include/linux/fs_stack.h
+++ b/include/linux/fs_stack.h
@@ -1,17 +1,28 @@
+/*
+ * Copyright (c) 2003-2007 Erez Zadok
+ * Copyright (c) 2005-2007 Josef 'Jeff' Sipek
+ * Copyright (c) 2003-2007 Stony Brook University
+ * Copyright (c) 2003-2007 The Research Foundation of SUNY
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
#ifndef _LINUX_FS_STACK_H
#define _LINUX_FS_STACK_H
-/* This file defines generic functions used primarily by stackable
+/*
+ * This file defines generic functions used primarily by stackable
* filesystems; none of these functions require i_mutex to be held.
*/
#include
/* externs for fs/stack.c */
-extern void fsstack_copy_attr_all(struct inode *dest, const struct inode *src,
- int (*get_nlinks)(struct inode *));
-
-extern void fsstack_copy_inode_size(struct inode *dst, const struct inode *src);
+extern void fsstack_copy_attr_all(struct inode *dest, const struct inode *src);
+extern void fsstack_copy_inode_size(struct inode *dst,
+ const struct inode *src);
/* inlines */
static inline void fsstack_copy_attr_atime(struct inode *dest,
@@ -28,4 +39,4 @@ static inline void fsstack_copy_attr_times(struct inode *dest,
dest->i_ctime = src->i_ctime;
}
-#endif /* _LINUX_FS_STACK_H */
+#endif /* not _LINUX_FS_STACK_H */
diff --git a/include/linux/magic.h b/include/linux/magic.h
index a9c6567..a6751f6 100644
--- a/include/linux/magic.h
+++ b/include/linux/magic.h
@@ -35,6 +35,8 @@
#define REISER2FS_SUPER_MAGIC_STRING "ReIsEr2Fs"
#define REISER2FS_JR_SUPER_MAGIC_STRING "ReIsEr3Fs"
+#define UNIONFS_SUPER_MAGIC 0xf15f083d
+
#define SMB_SUPER_MAGIC 0x517B
#define USBDEVICE_SUPER_MAGIC 0x9fa2
diff --git a/include/linux/mm.h b/include/linux/mm.h
index 60e0e4a..c680669 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -1157,6 +1157,7 @@ int drop_caches_sysctl_handler(struct ctl_table *, int, struct file *,
void __user *, size_t *, loff_t *);
unsigned long shrink_slab(unsigned long scanned, gfp_t gfp_mask,
unsigned long lru_pages);
+extern void drop_pagecache_sb(struct super_block *);
void drop_pagecache(void);
void drop_slab(void);
diff --git a/include/linux/namei.h b/include/linux/namei.h
index d39a5a6..5e4a22d 100644
--- a/include/linux/namei.h
+++ b/include/linux/namei.h
@@ -3,6 +3,7 @@
#include
#include
+#include
struct vfsmount;
@@ -47,6 +48,7 @@ enum {LAST_NORM, LAST_ROOT, LAST_DOT, LAST_DOTDOT, LAST_BIND};
* - internal "there are more path compnents" flag
* - locked when lookup done with dcache_lock held
* - dentry cache is untrusted; force a real lookup
+ * - lookup path from given dentry/vfsmount pair
*/
#define LOOKUP_FOLLOW 1
#define LOOKUP_DIRECTORY 2
@@ -54,6 +56,7 @@ enum {LAST_NORM, LAST_ROOT, LAST_DOT, LAST_DOTDOT, LAST_BIND};
#define LOOKUP_PARENT 16
#define LOOKUP_NOALT 32
#define LOOKUP_REVAL 64
+#define LOOKUP_ONE 128
/*
* Intent data
*/
@@ -81,7 +84,14 @@ extern struct file *lookup_instantiate_filp(struct nameidata *nd, struct dentry
extern struct file *nameidata_to_filp(struct nameidata *nd, int flags);
extern void release_open_intent(struct nameidata *);
-extern struct dentry * lookup_one_len(const char *, struct dentry *, int);
+extern struct dentry * lookup_one_len_nd(const char *, struct dentry *,
+ int, struct nameidata *);
+
+static inline struct dentry *lookup_one_len(const char *name,
+ struct dentry *dir, int len)
+{
+ return lookup_one_len_nd(name, dir, len, NULL);
+}
extern int follow_down(struct vfsmount **, struct dentry **);
extern int follow_up(struct vfsmount **, struct dentry **);
@@ -99,4 +109,16 @@ static inline char *nd_get_link(struct nameidata *nd)
return nd->saved_names[nd->depth];
}
+static inline void pathget(struct path *path)
+{
+ mntget(path->mnt);
+ dget(path->dentry);
+}
+
+static inline void pathput(struct path *path)
+{
+ dput(path->dentry);
+ mntput(path->mnt);
+}
+
#endif /* _LINUX_NAMEI_H */
diff --git a/include/linux/slab.h b/include/linux/slab.h
index 1ef822e..5f54979 100644
--- a/include/linux/slab.h
+++ b/include/linux/slab.h
@@ -72,6 +72,7 @@ static inline void *kmem_cache_alloc_node(struct kmem_cache *cachep,
*/
void *__kmalloc(size_t, gfp_t);
void *__kzalloc(size_t, gfp_t);
+void * __must_check krealloc(const void *, size_t, gfp_t);
void kfree(const void *);
unsigned int ksize(const void *);
diff --git a/include/linux/union_fs.h b/include/linux/union_fs.h
new file mode 100644
index 0000000..d13eb48
--- /dev/null
+++ b/include/linux/union_fs.h
@@ -0,0 +1,25 @@
+/*
+ * Copyright (c) 2003-2007 Erez Zadok
+ * Copyright (c) 2005-2007 Josef 'Jeff' Sipek
+ * Copyright (c) 2003-2007 Stony Brook University
+ * Copyright (c) 2003-2007 The Research Foundation of SUNY
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#ifndef _LINUX_UNION_FS_H
+#define _LINUX_UNION_FS_H
+
+/*
+ * DEFINITIONS FOR USER AND KERNEL CODE:
+ */
+# define UNIONFS_IOCTL_INCGEN _IOR(0x15, 11, int)
+# define UNIONFS_IOCTL_QUERYFILE _IOR(0x15, 15, int)
+
+/* We don't support normal remount, but unionctl uses it. */
+# define UNIONFS_REMOUNT_MAGIC 0x4a5a4380
+
+#endif /* _LINUX_UNIONFS_H */
+
diff --git a/mm/slab.c b/mm/slab.c
index 4cbac24..d288d8c 100644
--- a/mm/slab.c
+++ b/mm/slab.c
@@ -3736,6 +3736,53 @@ void *__kmalloc(size_t size, gfp_t flags)
EXPORT_SYMBOL(__kmalloc);
#endif
+
+/**
+ * krealloc - reallocate memory. The contents will remain unchanged.
+ * @p: object to reallocate memory for.
+ * @new_size: how many bytes of memory are required.
+ * @flags: the type of memory to allocate.
+ *
+ * The contents of the object pointed to are preserved up to the
+ * lesser of the new and old sizes. If @p is %NULL, krealloc()
+ * behaves exactly like kmalloc(). If @size is 0 and @p is not a
+ * %NULL pointer, the object pointed to is freed.
+ */
+void *krealloc(const void *p, size_t new_size, gfp_t flags)
+{
+ struct kmem_cache *cache, *new_cache;
+ void *ret;
+
+ if (unlikely(!p))
+ return kmalloc_track_caller(new_size, flags);
+
+ if (unlikely(!new_size)) {
+ kfree(p);
+ return NULL;
+ }
+
+ cache = virt_to_cache(p);
+ new_cache = __find_general_cachep(new_size, flags);
+
+ /*
+ * If new size fits in the current cache, bail out.
+ */
+ if (likely(cache == new_cache))
+ return (void *)p;
+
+ /*
+ * We are on the slow-path here so do not use __cache_alloc
+ * because it bloats kernel text.
+ */
+ ret = kmalloc_track_caller(new_size, flags);
+ if (ret) {
+ memcpy(ret, p, min(new_size, ksize(p)));
+ kfree(p);
+ }
+ return ret;
+}
+EXPORT_SYMBOL(krealloc);
+
/**
* kmem_cache_free - Deallocate an object
* @cachep: The cache the allocation was from.
diff --git a/mm/slob.c b/mm/slob.c
index c683d35..fec651b 100644
--- a/mm/slob.c
+++ b/mm/slob.c
@@ -181,6 +181,39 @@ void *__kmalloc(size_t size, gfp_t gfp)
}
EXPORT_SYMBOL(__kmalloc);
+/**
+ * krealloc - reallocate memory. The contents will remain unchanged.
+ *
+ * @p: object to reallocate memory for.
+ * @new_size: how many bytes of memory are required.
+ * @flags: the type of memory to allocate.
+ *
+ * The contents of the object pointed to are preserved up to the
+ * lesser of the new and old sizes. If @p is %NULL, krealloc()
+ * behaves exactly like kmalloc(). If @size is 0 and @p is not a
+ * %NULL pointer, the object pointed to is freed.
+ */
+void *krealloc(const void *p, size_t new_size, gfp_t flags)
+{
+ void *ret;
+
+ if (unlikely(!p))
+ return kmalloc_track_caller(new_size, flags);
+
+ if (unlikely(!new_size)) {
+ kfree(p);
+ return NULL;
+ }
+
+ ret = kmalloc_track_caller(new_size, flags);
+ if (ret) {
+ memcpy(ret, p, min(new_size, ksize(p)));
+ kfree(p);
+ }
+ return ret;
+}
+EXPORT_SYMBOL(krealloc);
+
void kfree(const void *block)
{
bigblock_t *bb, **last = &bigblocks;