summaryrefslogtreecommitdiffstats
path: root/kernel/fs/overlayfs
diff options
context:
space:
mode:
authorYunhong Jiang <yunhong.jiang@intel.com>2015-08-04 12:17:53 -0700
committerYunhong Jiang <yunhong.jiang@intel.com>2015-08-04 15:44:42 -0700
commit9ca8dbcc65cfc63d6f5ef3312a33184e1d726e00 (patch)
tree1c9cafbcd35f783a87880a10f85d1a060db1a563 /kernel/fs/overlayfs
parent98260f3884f4a202f9ca5eabed40b1354c489b29 (diff)
Add the rt linux 4.1.3-rt3 as base
Import the rt linux 4.1.3-rt3 as OPNFV kvm base. It's from git://git.kernel.org/pub/scm/linux/kernel/git/rt/linux-rt-devel.git linux-4.1.y-rt and the base is: commit 0917f823c59692d751951bf5ea699a2d1e2f26a2 Author: Sebastian Andrzej Siewior <bigeasy@linutronix.de> Date: Sat Jul 25 12:13:34 2015 +0200 Prepare v4.1.3-rt3 Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de> We lose all the git history this way and it's not good. We should apply another opnfv project repo in future. Change-Id: I87543d81c9df70d99c5001fbdf646b202c19f423 Signed-off-by: Yunhong Jiang <yunhong.jiang@intel.com>
Diffstat (limited to 'kernel/fs/overlayfs')
-rw-r--r--kernel/fs/overlayfs/Kconfig10
-rw-r--r--kernel/fs/overlayfs/Makefile7
-rw-r--r--kernel/fs/overlayfs/copy_up.c416
-rw-r--r--kernel/fs/overlayfs/dir.c951
-rw-r--r--kernel/fs/overlayfs/inode.c436
-rw-r--r--kernel/fs/overlayfs/overlayfs.h199
-rw-r--r--kernel/fs/overlayfs/readdir.c557
-rw-r--r--kernel/fs/overlayfs/super.c1046
8 files changed, 3622 insertions, 0 deletions
diff --git a/kernel/fs/overlayfs/Kconfig b/kernel/fs/overlayfs/Kconfig
new file mode 100644
index 000000000..34355818a
--- /dev/null
+++ b/kernel/fs/overlayfs/Kconfig
@@ -0,0 +1,10 @@
+config OVERLAY_FS
+ tristate "Overlay filesystem support"
+ help
+ An overlay filesystem combines two filesystems - an 'upper' filesystem
+ and a 'lower' filesystem. When a name exists in both filesystems, the
+ object in the 'upper' filesystem is visible while the object in the
+ 'lower' filesystem is either hidden or, in the case of directories,
+ merged with the 'upper' object.
+
+ For more information see Documentation/filesystems/overlayfs.txt
diff --git a/kernel/fs/overlayfs/Makefile b/kernel/fs/overlayfs/Makefile
new file mode 100644
index 000000000..900daed3e
--- /dev/null
+++ b/kernel/fs/overlayfs/Makefile
@@ -0,0 +1,7 @@
+#
+# Makefile for the overlay filesystem.
+#
+
+obj-$(CONFIG_OVERLAY_FS) += overlay.o
+
+overlay-objs := super.o inode.o dir.o readdir.o copy_up.o
diff --git a/kernel/fs/overlayfs/copy_up.c b/kernel/fs/overlayfs/copy_up.c
new file mode 100644
index 000000000..84d693d37
--- /dev/null
+++ b/kernel/fs/overlayfs/copy_up.c
@@ -0,0 +1,416 @@
+/*
+ *
+ * Copyright (C) 2011 Novell Inc.
+ *
+ * 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 <linux/fs.h>
+#include <linux/slab.h>
+#include <linux/file.h>
+#include <linux/splice.h>
+#include <linux/xattr.h>
+#include <linux/security.h>
+#include <linux/uaccess.h>
+#include <linux/sched.h>
+#include <linux/namei.h>
+#include "overlayfs.h"
+
+#define OVL_COPY_UP_CHUNK_SIZE (1 << 20)
+
+int ovl_copy_xattr(struct dentry *old, struct dentry *new)
+{
+ ssize_t list_size, size;
+ char *buf, *name, *value;
+ int error;
+
+ if (!old->d_inode->i_op->getxattr ||
+ !new->d_inode->i_op->getxattr)
+ return 0;
+
+ list_size = vfs_listxattr(old, NULL, 0);
+ if (list_size <= 0) {
+ if (list_size == -EOPNOTSUPP)
+ return 0;
+ return list_size;
+ }
+
+ buf = kzalloc(list_size, GFP_KERNEL);
+ if (!buf)
+ return -ENOMEM;
+
+ error = -ENOMEM;
+ value = kmalloc(XATTR_SIZE_MAX, GFP_KERNEL);
+ if (!value)
+ goto out;
+
+ list_size = vfs_listxattr(old, buf, list_size);
+ if (list_size <= 0) {
+ error = list_size;
+ goto out_free_value;
+ }
+
+ for (name = buf; name < (buf + list_size); name += strlen(name) + 1) {
+ size = vfs_getxattr(old, name, value, XATTR_SIZE_MAX);
+ if (size <= 0) {
+ error = size;
+ goto out_free_value;
+ }
+ error = vfs_setxattr(new, name, value, size, 0);
+ if (error)
+ goto out_free_value;
+ }
+
+out_free_value:
+ kfree(value);
+out:
+ kfree(buf);
+ return error;
+}
+
+static int ovl_copy_up_data(struct path *old, struct path *new, loff_t len)
+{
+ struct file *old_file;
+ struct file *new_file;
+ loff_t old_pos = 0;
+ loff_t new_pos = 0;
+ int error = 0;
+
+ if (len == 0)
+ return 0;
+
+ old_file = ovl_path_open(old, O_RDONLY);
+ if (IS_ERR(old_file))
+ return PTR_ERR(old_file);
+
+ new_file = ovl_path_open(new, O_WRONLY);
+ if (IS_ERR(new_file)) {
+ error = PTR_ERR(new_file);
+ goto out_fput;
+ }
+
+ /* FIXME: copy up sparse files efficiently */
+ while (len) {
+ size_t this_len = OVL_COPY_UP_CHUNK_SIZE;
+ long bytes;
+
+ if (len < this_len)
+ this_len = len;
+
+ if (signal_pending_state(TASK_KILLABLE, current)) {
+ error = -EINTR;
+ break;
+ }
+
+ bytes = do_splice_direct(old_file, &old_pos,
+ new_file, &new_pos,
+ this_len, SPLICE_F_MOVE);
+ if (bytes <= 0) {
+ error = bytes;
+ break;
+ }
+ WARN_ON(old_pos != new_pos);
+
+ len -= bytes;
+ }
+
+ fput(new_file);
+out_fput:
+ fput(old_file);
+ return error;
+}
+
+static char *ovl_read_symlink(struct dentry *realdentry)
+{
+ int res;
+ char *buf;
+ struct inode *inode = realdentry->d_inode;
+ mm_segment_t old_fs;
+
+ res = -EINVAL;
+ if (!inode->i_op->readlink)
+ goto err;
+
+ res = -ENOMEM;
+ buf = (char *) __get_free_page(GFP_KERNEL);
+ if (!buf)
+ goto err;
+
+ old_fs = get_fs();
+ set_fs(get_ds());
+ /* The cast to a user pointer is valid due to the set_fs() */
+ res = inode->i_op->readlink(realdentry,
+ (char __user *)buf, PAGE_SIZE - 1);
+ set_fs(old_fs);
+ if (res < 0) {
+ free_page((unsigned long) buf);
+ goto err;
+ }
+ buf[res] = '\0';
+
+ return buf;
+
+err:
+ return ERR_PTR(res);
+}
+
+static int ovl_set_timestamps(struct dentry *upperdentry, struct kstat *stat)
+{
+ struct iattr attr = {
+ .ia_valid =
+ ATTR_ATIME | ATTR_MTIME | ATTR_ATIME_SET | ATTR_MTIME_SET,
+ .ia_atime = stat->atime,
+ .ia_mtime = stat->mtime,
+ };
+
+ return notify_change(upperdentry, &attr, NULL);
+}
+
+int ovl_set_attr(struct dentry *upperdentry, struct kstat *stat)
+{
+ int err = 0;
+
+ if (!S_ISLNK(stat->mode)) {
+ struct iattr attr = {
+ .ia_valid = ATTR_MODE,
+ .ia_mode = stat->mode,
+ };
+ err = notify_change(upperdentry, &attr, NULL);
+ }
+ if (!err) {
+ struct iattr attr = {
+ .ia_valid = ATTR_UID | ATTR_GID,
+ .ia_uid = stat->uid,
+ .ia_gid = stat->gid,
+ };
+ err = notify_change(upperdentry, &attr, NULL);
+ }
+ if (!err)
+ ovl_set_timestamps(upperdentry, stat);
+
+ return err;
+}
+
+static int ovl_copy_up_locked(struct dentry *workdir, struct dentry *upperdir,
+ struct dentry *dentry, struct path *lowerpath,
+ struct kstat *stat, struct iattr *attr,
+ const char *link)
+{
+ struct inode *wdir = workdir->d_inode;
+ struct inode *udir = upperdir->d_inode;
+ struct dentry *newdentry = NULL;
+ struct dentry *upper = NULL;
+ umode_t mode = stat->mode;
+ int err;
+
+ newdentry = ovl_lookup_temp(workdir, dentry);
+ err = PTR_ERR(newdentry);
+ if (IS_ERR(newdentry))
+ goto out;
+
+ upper = lookup_one_len(dentry->d_name.name, upperdir,
+ dentry->d_name.len);
+ err = PTR_ERR(upper);
+ if (IS_ERR(upper))
+ goto out1;
+
+ /* Can't properly set mode on creation because of the umask */
+ stat->mode &= S_IFMT;
+ err = ovl_create_real(wdir, newdentry, stat, link, NULL, true);
+ stat->mode = mode;
+ if (err)
+ goto out2;
+
+ if (S_ISREG(stat->mode)) {
+ struct path upperpath;
+ ovl_path_upper(dentry, &upperpath);
+ BUG_ON(upperpath.dentry != NULL);
+ upperpath.dentry = newdentry;
+
+ err = ovl_copy_up_data(lowerpath, &upperpath, stat->size);
+ if (err)
+ goto out_cleanup;
+ }
+
+ err = ovl_copy_xattr(lowerpath->dentry, newdentry);
+ if (err)
+ goto out_cleanup;
+
+ mutex_lock(&newdentry->d_inode->i_mutex);
+ err = ovl_set_attr(newdentry, stat);
+ if (!err && attr)
+ err = notify_change(newdentry, attr, NULL);
+ mutex_unlock(&newdentry->d_inode->i_mutex);
+ if (err)
+ goto out_cleanup;
+
+ err = ovl_do_rename(wdir, newdentry, udir, upper, 0);
+ if (err)
+ goto out_cleanup;
+
+ ovl_dentry_update(dentry, newdentry);
+ newdentry = NULL;
+
+ /*
+ * Non-directores become opaque when copied up.
+ */
+ if (!S_ISDIR(stat->mode))
+ ovl_dentry_set_opaque(dentry, true);
+out2:
+ dput(upper);
+out1:
+ dput(newdentry);
+out:
+ return err;
+
+out_cleanup:
+ ovl_cleanup(wdir, newdentry);
+ goto out;
+}
+
+/*
+ * Copy up a single dentry
+ *
+ * Directory renames only allowed on "pure upper" (already created on
+ * upper filesystem, never copied up). Directories which are on lower or
+ * are merged may not be renamed. For these -EXDEV is returned and
+ * userspace has to deal with it. This means, when copying up a
+ * directory we can rely on it and ancestors being stable.
+ *
+ * Non-directory renames start with copy up of source if necessary. The
+ * actual rename will only proceed once the copy up was successful. Copy
+ * up uses upper parent i_mutex for exclusion. Since rename can change
+ * d_parent it is possible that the copy up will lock the old parent. At
+ * that point the file will have already been copied up anyway.
+ */
+int ovl_copy_up_one(struct dentry *parent, struct dentry *dentry,
+ struct path *lowerpath, struct kstat *stat,
+ struct iattr *attr)
+{
+ struct dentry *workdir = ovl_workdir(dentry);
+ int err;
+ struct kstat pstat;
+ struct path parentpath;
+ struct dentry *upperdir;
+ struct dentry *upperdentry;
+ const struct cred *old_cred;
+ struct cred *override_cred;
+ char *link = NULL;
+
+ if (WARN_ON(!workdir))
+ return -EROFS;
+
+ ovl_path_upper(parent, &parentpath);
+ upperdir = parentpath.dentry;
+
+ err = vfs_getattr(&parentpath, &pstat);
+ if (err)
+ return err;
+
+ if (S_ISLNK(stat->mode)) {
+ link = ovl_read_symlink(lowerpath->dentry);
+ if (IS_ERR(link))
+ return PTR_ERR(link);
+ }
+
+ err = -ENOMEM;
+ override_cred = prepare_creds();
+ if (!override_cred)
+ goto out_free_link;
+
+ override_cred->fsuid = stat->uid;
+ override_cred->fsgid = stat->gid;
+ /*
+ * CAP_SYS_ADMIN for copying up extended attributes
+ * CAP_DAC_OVERRIDE for create
+ * CAP_FOWNER for chmod, timestamp update
+ * CAP_FSETID for chmod
+ * CAP_CHOWN for chown
+ * CAP_MKNOD for mknod
+ */
+ cap_raise(override_cred->cap_effective, CAP_SYS_ADMIN);
+ cap_raise(override_cred->cap_effective, CAP_DAC_OVERRIDE);
+ cap_raise(override_cred->cap_effective, CAP_FOWNER);
+ cap_raise(override_cred->cap_effective, CAP_FSETID);
+ cap_raise(override_cred->cap_effective, CAP_CHOWN);
+ cap_raise(override_cred->cap_effective, CAP_MKNOD);
+ old_cred = override_creds(override_cred);
+
+ err = -EIO;
+ if (lock_rename(workdir, upperdir) != NULL) {
+ pr_err("overlayfs: failed to lock workdir+upperdir\n");
+ goto out_unlock;
+ }
+ upperdentry = ovl_dentry_upper(dentry);
+ if (upperdentry) {
+ unlock_rename(workdir, upperdir);
+ err = 0;
+ /* Raced with another copy-up? Do the setattr here */
+ if (attr) {
+ mutex_lock(&upperdentry->d_inode->i_mutex);
+ err = notify_change(upperdentry, attr, NULL);
+ mutex_unlock(&upperdentry->d_inode->i_mutex);
+ }
+ goto out_put_cred;
+ }
+
+ err = ovl_copy_up_locked(workdir, upperdir, dentry, lowerpath,
+ stat, attr, link);
+ if (!err) {
+ /* Restore timestamps on parent (best effort) */
+ ovl_set_timestamps(upperdir, &pstat);
+ }
+out_unlock:
+ unlock_rename(workdir, upperdir);
+out_put_cred:
+ revert_creds(old_cred);
+ put_cred(override_cred);
+
+out_free_link:
+ if (link)
+ free_page((unsigned long) link);
+
+ return err;
+}
+
+int ovl_copy_up(struct dentry *dentry)
+{
+ int err;
+
+ err = 0;
+ while (!err) {
+ struct dentry *next;
+ struct dentry *parent;
+ struct path lowerpath;
+ struct kstat stat;
+ enum ovl_path_type type = ovl_path_type(dentry);
+
+ if (OVL_TYPE_UPPER(type))
+ break;
+
+ next = dget(dentry);
+ /* find the topmost dentry not yet copied up */
+ for (;;) {
+ parent = dget_parent(next);
+
+ type = ovl_path_type(parent);
+ if (OVL_TYPE_UPPER(type))
+ break;
+
+ dput(next);
+ next = parent;
+ }
+
+ ovl_path_lower(next, &lowerpath);
+ err = vfs_getattr(&lowerpath, &stat);
+ if (!err)
+ err = ovl_copy_up_one(parent, next, &lowerpath, &stat, NULL);
+
+ dput(parent);
+ dput(next);
+ }
+
+ return err;
+}
diff --git a/kernel/fs/overlayfs/dir.c b/kernel/fs/overlayfs/dir.c
new file mode 100644
index 000000000..692ceda3b
--- /dev/null
+++ b/kernel/fs/overlayfs/dir.c
@@ -0,0 +1,951 @@
+/*
+ *
+ * Copyright (C) 2011 Novell Inc.
+ *
+ * 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 <linux/fs.h>
+#include <linux/namei.h>
+#include <linux/xattr.h>
+#include <linux/security.h>
+#include <linux/cred.h>
+#include "overlayfs.h"
+
+void ovl_cleanup(struct inode *wdir, struct dentry *wdentry)
+{
+ int err;
+
+ dget(wdentry);
+ if (d_is_dir(wdentry))
+ err = ovl_do_rmdir(wdir, wdentry);
+ else
+ err = ovl_do_unlink(wdir, wdentry);
+ dput(wdentry);
+
+ if (err) {
+ pr_err("overlayfs: cleanup of '%pd2' failed (%i)\n",
+ wdentry, err);
+ }
+}
+
+struct dentry *ovl_lookup_temp(struct dentry *workdir, struct dentry *dentry)
+{
+ struct dentry *temp;
+ char name[20];
+
+ snprintf(name, sizeof(name), "#%lx", (unsigned long) dentry);
+
+ temp = lookup_one_len(name, workdir, strlen(name));
+ if (!IS_ERR(temp) && temp->d_inode) {
+ pr_err("overlayfs: workdir/%s already exists\n", name);
+ dput(temp);
+ temp = ERR_PTR(-EIO);
+ }
+
+ return temp;
+}
+
+/* caller holds i_mutex on workdir */
+static struct dentry *ovl_whiteout(struct dentry *workdir,
+ struct dentry *dentry)
+{
+ int err;
+ struct dentry *whiteout;
+ struct inode *wdir = workdir->d_inode;
+
+ whiteout = ovl_lookup_temp(workdir, dentry);
+ if (IS_ERR(whiteout))
+ return whiteout;
+
+ err = ovl_do_whiteout(wdir, whiteout);
+ if (err) {
+ dput(whiteout);
+ whiteout = ERR_PTR(err);
+ }
+
+ return whiteout;
+}
+
+int ovl_create_real(struct inode *dir, struct dentry *newdentry,
+ struct kstat *stat, const char *link,
+ struct dentry *hardlink, bool debug)
+{
+ int err;
+
+ if (newdentry->d_inode)
+ return -ESTALE;
+
+ if (hardlink) {
+ err = ovl_do_link(hardlink, dir, newdentry, debug);
+ } else {
+ switch (stat->mode & S_IFMT) {
+ case S_IFREG:
+ err = ovl_do_create(dir, newdentry, stat->mode, debug);
+ break;
+
+ case S_IFDIR:
+ err = ovl_do_mkdir(dir, newdentry, stat->mode, debug);
+ break;
+
+ case S_IFCHR:
+ case S_IFBLK:
+ case S_IFIFO:
+ case S_IFSOCK:
+ err = ovl_do_mknod(dir, newdentry,
+ stat->mode, stat->rdev, debug);
+ break;
+
+ case S_IFLNK:
+ err = ovl_do_symlink(dir, newdentry, link, debug);
+ break;
+
+ default:
+ err = -EPERM;
+ }
+ }
+ if (!err && WARN_ON(!newdentry->d_inode)) {
+ /*
+ * Not quite sure if non-instantiated dentry is legal or not.
+ * VFS doesn't seem to care so check and warn here.
+ */
+ err = -ENOENT;
+ }
+ return err;
+}
+
+static int ovl_set_opaque(struct dentry *upperdentry)
+{
+ return ovl_do_setxattr(upperdentry, OVL_XATTR_OPAQUE, "y", 1, 0);
+}
+
+static void ovl_remove_opaque(struct dentry *upperdentry)
+{
+ int err;
+
+ err = ovl_do_removexattr(upperdentry, OVL_XATTR_OPAQUE);
+ if (err) {
+ pr_warn("overlayfs: failed to remove opaque from '%s' (%i)\n",
+ upperdentry->d_name.name, err);
+ }
+}
+
+static int ovl_dir_getattr(struct vfsmount *mnt, struct dentry *dentry,
+ struct kstat *stat)
+{
+ int err;
+ enum ovl_path_type type;
+ struct path realpath;
+
+ type = ovl_path_real(dentry, &realpath);
+ err = vfs_getattr(&realpath, stat);
+ if (err)
+ return err;
+
+ stat->dev = dentry->d_sb->s_dev;
+ stat->ino = dentry->d_inode->i_ino;
+
+ /*
+ * It's probably not worth it to count subdirs to get the
+ * correct link count. nlink=1 seems to pacify 'find' and
+ * other utilities.
+ */
+ if (OVL_TYPE_MERGE(type))
+ stat->nlink = 1;
+
+ return 0;
+}
+
+static int ovl_create_upper(struct dentry *dentry, struct inode *inode,
+ struct kstat *stat, const char *link,
+ struct dentry *hardlink)
+{
+ struct dentry *upperdir = ovl_dentry_upper(dentry->d_parent);
+ struct inode *udir = upperdir->d_inode;
+ struct dentry *newdentry;
+ int err;
+
+ mutex_lock_nested(&udir->i_mutex, I_MUTEX_PARENT);
+ newdentry = lookup_one_len(dentry->d_name.name, upperdir,
+ dentry->d_name.len);
+ err = PTR_ERR(newdentry);
+ if (IS_ERR(newdentry))
+ goto out_unlock;
+ err = ovl_create_real(udir, newdentry, stat, link, hardlink, false);
+ if (err)
+ goto out_dput;
+
+ ovl_dentry_version_inc(dentry->d_parent);
+ ovl_dentry_update(dentry, newdentry);
+ ovl_copyattr(newdentry->d_inode, inode);
+ d_instantiate(dentry, inode);
+ newdentry = NULL;
+out_dput:
+ dput(newdentry);
+out_unlock:
+ mutex_unlock(&udir->i_mutex);
+ return err;
+}
+
+static int ovl_lock_rename_workdir(struct dentry *workdir,
+ struct dentry *upperdir)
+{
+ /* Workdir should not be the same as upperdir */
+ if (workdir == upperdir)
+ goto err;
+
+ /* Workdir should not be subdir of upperdir and vice versa */
+ if (lock_rename(workdir, upperdir) != NULL)
+ goto err_unlock;
+
+ return 0;
+
+err_unlock:
+ unlock_rename(workdir, upperdir);
+err:
+ pr_err("overlayfs: failed to lock workdir+upperdir\n");
+ return -EIO;
+}
+
+static struct dentry *ovl_clear_empty(struct dentry *dentry,
+ struct list_head *list)
+{
+ struct dentry *workdir = ovl_workdir(dentry);
+ struct inode *wdir = workdir->d_inode;
+ struct dentry *upperdir = ovl_dentry_upper(dentry->d_parent);
+ struct inode *udir = upperdir->d_inode;
+ struct path upperpath;
+ struct dentry *upper;
+ struct dentry *opaquedir;
+ struct kstat stat;
+ int err;
+
+ if (WARN_ON(!workdir))
+ return ERR_PTR(-EROFS);
+
+ err = ovl_lock_rename_workdir(workdir, upperdir);
+ if (err)
+ goto out;
+
+ ovl_path_upper(dentry, &upperpath);
+ err = vfs_getattr(&upperpath, &stat);
+ if (err)
+ goto out_unlock;
+
+ err = -ESTALE;
+ if (!S_ISDIR(stat.mode))
+ goto out_unlock;
+ upper = upperpath.dentry;
+ if (upper->d_parent->d_inode != udir)
+ goto out_unlock;
+
+ opaquedir = ovl_lookup_temp(workdir, dentry);
+ err = PTR_ERR(opaquedir);
+ if (IS_ERR(opaquedir))
+ goto out_unlock;
+
+ err = ovl_create_real(wdir, opaquedir, &stat, NULL, NULL, true);
+ if (err)
+ goto out_dput;
+
+ err = ovl_copy_xattr(upper, opaquedir);
+ if (err)
+ goto out_cleanup;
+
+ err = ovl_set_opaque(opaquedir);
+ if (err)
+ goto out_cleanup;
+
+ mutex_lock(&opaquedir->d_inode->i_mutex);
+ err = ovl_set_attr(opaquedir, &stat);
+ mutex_unlock(&opaquedir->d_inode->i_mutex);
+ if (err)
+ goto out_cleanup;
+
+ err = ovl_do_rename(wdir, opaquedir, udir, upper, RENAME_EXCHANGE);
+ if (err)
+ goto out_cleanup;
+
+ ovl_cleanup_whiteouts(upper, list);
+ ovl_cleanup(wdir, upper);
+ unlock_rename(workdir, upperdir);
+
+ /* dentry's upper doesn't match now, get rid of it */
+ d_drop(dentry);
+
+ return opaquedir;
+
+out_cleanup:
+ ovl_cleanup(wdir, opaquedir);
+out_dput:
+ dput(opaquedir);
+out_unlock:
+ unlock_rename(workdir, upperdir);
+out:
+ return ERR_PTR(err);
+}
+
+static struct dentry *ovl_check_empty_and_clear(struct dentry *dentry)
+{
+ int err;
+ struct dentry *ret = NULL;
+ LIST_HEAD(list);
+
+ err = ovl_check_empty_dir(dentry, &list);
+ if (err)
+ ret = ERR_PTR(err);
+ else {
+ /*
+ * If no upperdentry then skip clearing whiteouts.
+ *
+ * Can race with copy-up, since we don't hold the upperdir
+ * mutex. Doesn't matter, since copy-up can't create a
+ * non-empty directory from an empty one.
+ */
+ if (ovl_dentry_upper(dentry))
+ ret = ovl_clear_empty(dentry, &list);
+ }
+
+ ovl_cache_free(&list);
+
+ return ret;
+}
+
+static int ovl_create_over_whiteout(struct dentry *dentry, struct inode *inode,
+ struct kstat *stat, const char *link,
+ struct dentry *hardlink)
+{
+ struct dentry *workdir = ovl_workdir(dentry);
+ struct inode *wdir = workdir->d_inode;
+ struct dentry *upperdir = ovl_dentry_upper(dentry->d_parent);
+ struct inode *udir = upperdir->d_inode;
+ struct dentry *upper;
+ struct dentry *newdentry;
+ int err;
+
+ if (WARN_ON(!workdir))
+ return -EROFS;
+
+ err = ovl_lock_rename_workdir(workdir, upperdir);
+ if (err)
+ goto out;
+
+ newdentry = ovl_lookup_temp(workdir, dentry);
+ err = PTR_ERR(newdentry);
+ if (IS_ERR(newdentry))
+ goto out_unlock;
+
+ upper = lookup_one_len(dentry->d_name.name, upperdir,
+ dentry->d_name.len);
+ err = PTR_ERR(upper);
+ if (IS_ERR(upper))
+ goto out_dput;
+
+ err = ovl_create_real(wdir, newdentry, stat, link, hardlink, true);
+ if (err)
+ goto out_dput2;
+
+ if (S_ISDIR(stat->mode)) {
+ err = ovl_set_opaque(newdentry);
+ if (err)
+ goto out_cleanup;
+
+ err = ovl_do_rename(wdir, newdentry, udir, upper,
+ RENAME_EXCHANGE);
+ if (err)
+ goto out_cleanup;
+
+ ovl_cleanup(wdir, upper);
+ } else {
+ err = ovl_do_rename(wdir, newdentry, udir, upper, 0);
+ if (err)
+ goto out_cleanup;
+ }
+ ovl_dentry_version_inc(dentry->d_parent);
+ ovl_dentry_update(dentry, newdentry);
+ ovl_copyattr(newdentry->d_inode, inode);
+ d_instantiate(dentry, inode);
+ newdentry = NULL;
+out_dput2:
+ dput(upper);
+out_dput:
+ dput(newdentry);
+out_unlock:
+ unlock_rename(workdir, upperdir);
+out:
+ return err;
+
+out_cleanup:
+ ovl_cleanup(wdir, newdentry);
+ goto out_dput2;
+}
+
+static int ovl_create_or_link(struct dentry *dentry, int mode, dev_t rdev,
+ const char *link, struct dentry *hardlink)
+{
+ int err;
+ struct inode *inode;
+ struct kstat stat = {
+ .mode = mode,
+ .rdev = rdev,
+ };
+
+ err = -ENOMEM;
+ inode = ovl_new_inode(dentry->d_sb, mode, dentry->d_fsdata);
+ if (!inode)
+ goto out;
+
+ err = ovl_copy_up(dentry->d_parent);
+ if (err)
+ goto out_iput;
+
+ if (!ovl_dentry_is_opaque(dentry)) {
+ err = ovl_create_upper(dentry, inode, &stat, link, hardlink);
+ } else {
+ const struct cred *old_cred;
+ struct cred *override_cred;
+
+ err = -ENOMEM;
+ override_cred = prepare_creds();
+ if (!override_cred)
+ goto out_iput;
+
+ /*
+ * CAP_SYS_ADMIN for setting opaque xattr
+ * CAP_DAC_OVERRIDE for create in workdir, rename
+ * CAP_FOWNER for removing whiteout from sticky dir
+ */
+ cap_raise(override_cred->cap_effective, CAP_SYS_ADMIN);
+ cap_raise(override_cred->cap_effective, CAP_DAC_OVERRIDE);
+ cap_raise(override_cred->cap_effective, CAP_FOWNER);
+ old_cred = override_creds(override_cred);
+
+ err = ovl_create_over_whiteout(dentry, inode, &stat, link,
+ hardlink);
+
+ revert_creds(old_cred);
+ put_cred(override_cred);
+ }
+
+ if (!err)
+ inode = NULL;
+out_iput:
+ iput(inode);
+out:
+ return err;
+}
+
+static int ovl_create_object(struct dentry *dentry, int mode, dev_t rdev,
+ const char *link)
+{
+ int err;
+
+ err = ovl_want_write(dentry);
+ if (!err) {
+ err = ovl_create_or_link(dentry, mode, rdev, link, NULL);
+ ovl_drop_write(dentry);
+ }
+
+ return err;
+}
+
+static int ovl_create(struct inode *dir, struct dentry *dentry, umode_t mode,
+ bool excl)
+{
+ return ovl_create_object(dentry, (mode & 07777) | S_IFREG, 0, NULL);
+}
+
+static int ovl_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode)
+{
+ return ovl_create_object(dentry, (mode & 07777) | S_IFDIR, 0, NULL);
+}
+
+static int ovl_mknod(struct inode *dir, struct dentry *dentry, umode_t mode,
+ dev_t rdev)
+{
+ /* Don't allow creation of "whiteout" on overlay */
+ if (S_ISCHR(mode) && rdev == WHITEOUT_DEV)
+ return -EPERM;
+
+ return ovl_create_object(dentry, mode, rdev, NULL);
+}
+
+static int ovl_symlink(struct inode *dir, struct dentry *dentry,
+ const char *link)
+{
+ return ovl_create_object(dentry, S_IFLNK, 0, link);
+}
+
+static int ovl_link(struct dentry *old, struct inode *newdir,
+ struct dentry *new)
+{
+ int err;
+ struct dentry *upper;
+
+ err = ovl_want_write(old);
+ if (err)
+ goto out;
+
+ err = ovl_copy_up(old);
+ if (err)
+ goto out_drop_write;
+
+ upper = ovl_dentry_upper(old);
+ err = ovl_create_or_link(new, upper->d_inode->i_mode, 0, NULL, upper);
+
+out_drop_write:
+ ovl_drop_write(old);
+out:
+ return err;
+}
+
+static int ovl_remove_and_whiteout(struct dentry *dentry, bool is_dir)
+{
+ struct dentry *workdir = ovl_workdir(dentry);
+ struct inode *wdir = workdir->d_inode;
+ struct dentry *upperdir = ovl_dentry_upper(dentry->d_parent);
+ struct inode *udir = upperdir->d_inode;
+ struct dentry *whiteout;
+ struct dentry *upper;
+ struct dentry *opaquedir = NULL;
+ int err;
+
+ if (WARN_ON(!workdir))
+ return -EROFS;
+
+ if (is_dir) {
+ if (OVL_TYPE_MERGE_OR_LOWER(ovl_path_type(dentry))) {
+ opaquedir = ovl_check_empty_and_clear(dentry);
+ err = PTR_ERR(opaquedir);
+ if (IS_ERR(opaquedir))
+ goto out;
+ } else {
+ LIST_HEAD(list);
+
+ /*
+ * When removing an empty opaque directory, then it
+ * makes no sense to replace it with an exact replica of
+ * itself. But emptiness still needs to be checked.
+ */
+ err = ovl_check_empty_dir(dentry, &list);
+ ovl_cache_free(&list);
+ if (err)
+ goto out;
+ }
+ }
+
+ err = ovl_lock_rename_workdir(workdir, upperdir);
+ if (err)
+ goto out_dput;
+
+ whiteout = ovl_whiteout(workdir, dentry);
+ err = PTR_ERR(whiteout);
+ if (IS_ERR(whiteout))
+ goto out_unlock;
+
+ upper = ovl_dentry_upper(dentry);
+ if (!upper) {
+ upper = lookup_one_len(dentry->d_name.name, upperdir,
+ dentry->d_name.len);
+ err = PTR_ERR(upper);
+ if (IS_ERR(upper))
+ goto kill_whiteout;
+
+ err = ovl_do_rename(wdir, whiteout, udir, upper, 0);
+ dput(upper);
+ if (err)
+ goto kill_whiteout;
+ } else {
+ int flags = 0;
+
+ if (opaquedir)
+ upper = opaquedir;
+ err = -ESTALE;
+ if (upper->d_parent != upperdir)
+ goto kill_whiteout;
+
+ if (is_dir)
+ flags |= RENAME_EXCHANGE;
+
+ err = ovl_do_rename(wdir, whiteout, udir, upper, flags);
+ if (err)
+ goto kill_whiteout;
+
+ if (is_dir)
+ ovl_cleanup(wdir, upper);
+ }
+ ovl_dentry_version_inc(dentry->d_parent);
+out_d_drop:
+ d_drop(dentry);
+ dput(whiteout);
+out_unlock:
+ unlock_rename(workdir, upperdir);
+out_dput:
+ dput(opaquedir);
+out:
+ return err;
+
+kill_whiteout:
+ ovl_cleanup(wdir, whiteout);
+ goto out_d_drop;
+}
+
+static int ovl_remove_upper(struct dentry *dentry, bool is_dir)
+{
+ struct dentry *upperdir = ovl_dentry_upper(dentry->d_parent);
+ struct inode *dir = upperdir->d_inode;
+ struct dentry *upper = ovl_dentry_upper(dentry);
+ int err;
+
+ mutex_lock_nested(&dir->i_mutex, I_MUTEX_PARENT);
+ err = -ESTALE;
+ if (upper->d_parent == upperdir) {
+ /* Don't let d_delete() think it can reset d_inode */
+ dget(upper);
+ if (is_dir)
+ err = vfs_rmdir(dir, upper);
+ else
+ err = vfs_unlink(dir, upper, NULL);
+ dput(upper);
+ ovl_dentry_version_inc(dentry->d_parent);
+ }
+
+ /*
+ * Keeping this dentry hashed would mean having to release
+ * upperpath/lowerpath, which could only be done if we are the
+ * sole user of this dentry. Too tricky... Just unhash for
+ * now.
+ */
+ d_drop(dentry);
+ mutex_unlock(&dir->i_mutex);
+
+ return err;
+}
+
+static inline int ovl_check_sticky(struct dentry *dentry)
+{
+ struct inode *dir = ovl_dentry_real(dentry->d_parent)->d_inode;
+ struct inode *inode = ovl_dentry_real(dentry)->d_inode;
+
+ if (check_sticky(dir, inode))
+ return -EPERM;
+
+ return 0;
+}
+
+static int ovl_do_remove(struct dentry *dentry, bool is_dir)
+{
+ enum ovl_path_type type;
+ int err;
+
+ err = ovl_check_sticky(dentry);
+ if (err)
+ goto out;
+
+ err = ovl_want_write(dentry);
+ if (err)
+ goto out;
+
+ err = ovl_copy_up(dentry->d_parent);
+ if (err)
+ goto out_drop_write;
+
+ type = ovl_path_type(dentry);
+ if (OVL_TYPE_PURE_UPPER(type)) {
+ err = ovl_remove_upper(dentry, is_dir);
+ } else {
+ const struct cred *old_cred;
+ struct cred *override_cred;
+
+ err = -ENOMEM;
+ override_cred = prepare_creds();
+ if (!override_cred)
+ goto out_drop_write;
+
+ /*
+ * CAP_SYS_ADMIN for setting xattr on whiteout, opaque dir
+ * CAP_DAC_OVERRIDE for create in workdir, rename
+ * CAP_FOWNER for removing whiteout from sticky dir
+ * CAP_FSETID for chmod of opaque dir
+ * CAP_CHOWN for chown of opaque dir
+ */
+ cap_raise(override_cred->cap_effective, CAP_SYS_ADMIN);
+ cap_raise(override_cred->cap_effective, CAP_DAC_OVERRIDE);
+ cap_raise(override_cred->cap_effective, CAP_FOWNER);
+ cap_raise(override_cred->cap_effective, CAP_FSETID);
+ cap_raise(override_cred->cap_effective, CAP_CHOWN);
+ old_cred = override_creds(override_cred);
+
+ err = ovl_remove_and_whiteout(dentry, is_dir);
+
+ revert_creds(old_cred);
+ put_cred(override_cred);
+ }
+out_drop_write:
+ ovl_drop_write(dentry);
+out:
+ return err;
+}
+
+static int ovl_unlink(struct inode *dir, struct dentry *dentry)
+{
+ return ovl_do_remove(dentry, false);
+}
+
+static int ovl_rmdir(struct inode *dir, struct dentry *dentry)
+{
+ return ovl_do_remove(dentry, true);
+}
+
+static int ovl_rename2(struct inode *olddir, struct dentry *old,
+ struct inode *newdir, struct dentry *new,
+ unsigned int flags)
+{
+ int err;
+ enum ovl_path_type old_type;
+ enum ovl_path_type new_type;
+ struct dentry *old_upperdir;
+ struct dentry *new_upperdir;
+ struct dentry *olddentry;
+ struct dentry *newdentry;
+ struct dentry *trap;
+ bool old_opaque;
+ bool new_opaque;
+ bool new_create = false;
+ bool cleanup_whiteout = false;
+ bool overwrite = !(flags & RENAME_EXCHANGE);
+ bool is_dir = d_is_dir(old);
+ bool new_is_dir = false;
+ struct dentry *opaquedir = NULL;
+ const struct cred *old_cred = NULL;
+ struct cred *override_cred = NULL;
+
+ err = -EINVAL;
+ if (flags & ~(RENAME_EXCHANGE | RENAME_NOREPLACE))
+ goto out;
+
+ flags &= ~RENAME_NOREPLACE;
+
+ err = ovl_check_sticky(old);
+ if (err)
+ goto out;
+
+ /* Don't copy up directory trees */
+ old_type = ovl_path_type(old);
+ err = -EXDEV;
+ if (OVL_TYPE_MERGE_OR_LOWER(old_type) && is_dir)
+ goto out;
+
+ if (new->d_inode) {
+ err = ovl_check_sticky(new);
+ if (err)
+ goto out;
+
+ if (d_is_dir(new))
+ new_is_dir = true;
+
+ new_type = ovl_path_type(new);
+ err = -EXDEV;
+ if (!overwrite && OVL_TYPE_MERGE_OR_LOWER(new_type) && new_is_dir)
+ goto out;
+
+ err = 0;
+ if (!OVL_TYPE_UPPER(new_type) && !OVL_TYPE_UPPER(old_type)) {
+ if (ovl_dentry_lower(old)->d_inode ==
+ ovl_dentry_lower(new)->d_inode)
+ goto out;
+ }
+ if (OVL_TYPE_UPPER(new_type) && OVL_TYPE_UPPER(old_type)) {
+ if (ovl_dentry_upper(old)->d_inode ==
+ ovl_dentry_upper(new)->d_inode)
+ goto out;
+ }
+ } else {
+ if (ovl_dentry_is_opaque(new))
+ new_type = __OVL_PATH_UPPER;
+ else
+ new_type = __OVL_PATH_UPPER | __OVL_PATH_PURE;
+ }
+
+ err = ovl_want_write(old);
+ if (err)
+ goto out;
+
+ err = ovl_copy_up(old);
+ if (err)
+ goto out_drop_write;
+
+ err = ovl_copy_up(new->d_parent);
+ if (err)
+ goto out_drop_write;
+ if (!overwrite) {
+ err = ovl_copy_up(new);
+ if (err)
+ goto out_drop_write;
+ }
+
+ old_opaque = !OVL_TYPE_PURE_UPPER(old_type);
+ new_opaque = !OVL_TYPE_PURE_UPPER(new_type);
+
+ if (old_opaque || new_opaque) {
+ err = -ENOMEM;
+ override_cred = prepare_creds();
+ if (!override_cred)
+ goto out_drop_write;
+
+ /*
+ * CAP_SYS_ADMIN for setting xattr on whiteout, opaque dir
+ * CAP_DAC_OVERRIDE for create in workdir
+ * CAP_FOWNER for removing whiteout from sticky dir
+ * CAP_FSETID for chmod of opaque dir
+ * CAP_CHOWN for chown of opaque dir
+ */
+ cap_raise(override_cred->cap_effective, CAP_SYS_ADMIN);
+ cap_raise(override_cred->cap_effective, CAP_DAC_OVERRIDE);
+ cap_raise(override_cred->cap_effective, CAP_FOWNER);
+ cap_raise(override_cred->cap_effective, CAP_FSETID);
+ cap_raise(override_cred->cap_effective, CAP_CHOWN);
+ old_cred = override_creds(override_cred);
+ }
+
+ if (overwrite && OVL_TYPE_MERGE_OR_LOWER(new_type) && new_is_dir) {
+ opaquedir = ovl_check_empty_and_clear(new);
+ err = PTR_ERR(opaquedir);
+ if (IS_ERR(opaquedir)) {
+ opaquedir = NULL;
+ goto out_revert_creds;
+ }
+ }
+
+ if (overwrite) {
+ if (old_opaque) {
+ if (new->d_inode || !new_opaque) {
+ /* Whiteout source */
+ flags |= RENAME_WHITEOUT;
+ } else {
+ /* Switch whiteouts */
+ flags |= RENAME_EXCHANGE;
+ }
+ } else if (is_dir && !new->d_inode && new_opaque) {
+ flags |= RENAME_EXCHANGE;
+ cleanup_whiteout = true;
+ }
+ }
+
+ old_upperdir = ovl_dentry_upper(old->d_parent);
+ new_upperdir = ovl_dentry_upper(new->d_parent);
+
+ trap = lock_rename(new_upperdir, old_upperdir);
+
+ olddentry = ovl_dentry_upper(old);
+ newdentry = ovl_dentry_upper(new);
+ if (newdentry) {
+ if (opaquedir) {
+ newdentry = opaquedir;
+ opaquedir = NULL;
+ } else {
+ dget(newdentry);
+ }
+ } else {
+ new_create = true;
+ newdentry = lookup_one_len(new->d_name.name, new_upperdir,
+ new->d_name.len);
+ err = PTR_ERR(newdentry);
+ if (IS_ERR(newdentry))
+ goto out_unlock;
+ }
+
+ err = -ESTALE;
+ if (olddentry->d_parent != old_upperdir)
+ goto out_dput;
+ if (newdentry->d_parent != new_upperdir)
+ goto out_dput;
+ if (olddentry == trap)
+ goto out_dput;
+ if (newdentry == trap)
+ goto out_dput;
+
+ if (is_dir && !old_opaque && new_opaque) {
+ err = ovl_set_opaque(olddentry);
+ if (err)
+ goto out_dput;
+ }
+ if (!overwrite && new_is_dir && old_opaque && !new_opaque) {
+ err = ovl_set_opaque(newdentry);
+ if (err)
+ goto out_dput;
+ }
+
+ if (old_opaque || new_opaque) {
+ err = ovl_do_rename(old_upperdir->d_inode, olddentry,
+ new_upperdir->d_inode, newdentry,
+ flags);
+ } else {
+ /* No debug for the plain case */
+ BUG_ON(flags & ~RENAME_EXCHANGE);
+ err = vfs_rename(old_upperdir->d_inode, olddentry,
+ new_upperdir->d_inode, newdentry,
+ NULL, flags);
+ }
+
+ if (err) {
+ if (is_dir && !old_opaque && new_opaque)
+ ovl_remove_opaque(olddentry);
+ if (!overwrite && new_is_dir && old_opaque && !new_opaque)
+ ovl_remove_opaque(newdentry);
+ goto out_dput;
+ }
+
+ if (is_dir && old_opaque && !new_opaque)
+ ovl_remove_opaque(olddentry);
+ if (!overwrite && new_is_dir && !old_opaque && new_opaque)
+ ovl_remove_opaque(newdentry);
+
+ if (old_opaque != new_opaque) {
+ ovl_dentry_set_opaque(old, new_opaque);
+ if (!overwrite)
+ ovl_dentry_set_opaque(new, old_opaque);
+ }
+
+ if (cleanup_whiteout)
+ ovl_cleanup(old_upperdir->d_inode, newdentry);
+
+ ovl_dentry_version_inc(old->d_parent);
+ ovl_dentry_version_inc(new->d_parent);
+
+out_dput:
+ dput(newdentry);
+out_unlock:
+ unlock_rename(new_upperdir, old_upperdir);
+out_revert_creds:
+ if (old_opaque || new_opaque) {
+ revert_creds(old_cred);
+ put_cred(override_cred);
+ }
+out_drop_write:
+ ovl_drop_write(old);
+out:
+ dput(opaquedir);
+ return err;
+}
+
+const struct inode_operations ovl_dir_inode_operations = {
+ .lookup = ovl_lookup,
+ .mkdir = ovl_mkdir,
+ .symlink = ovl_symlink,
+ .unlink = ovl_unlink,
+ .rmdir = ovl_rmdir,
+ .rename2 = ovl_rename2,
+ .link = ovl_link,
+ .setattr = ovl_setattr,
+ .create = ovl_create,
+ .mknod = ovl_mknod,
+ .permission = ovl_permission,
+ .getattr = ovl_dir_getattr,
+ .setxattr = ovl_setxattr,
+ .getxattr = ovl_getxattr,
+ .listxattr = ovl_listxattr,
+ .removexattr = ovl_removexattr,
+};
diff --git a/kernel/fs/overlayfs/inode.c b/kernel/fs/overlayfs/inode.c
new file mode 100644
index 000000000..04f124884
--- /dev/null
+++ b/kernel/fs/overlayfs/inode.c
@@ -0,0 +1,436 @@
+/*
+ *
+ * Copyright (C) 2011 Novell Inc.
+ *
+ * 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 <linux/fs.h>
+#include <linux/slab.h>
+#include <linux/xattr.h>
+#include "overlayfs.h"
+
+static int ovl_copy_up_last(struct dentry *dentry, struct iattr *attr,
+ bool no_data)
+{
+ int err;
+ struct dentry *parent;
+ struct kstat stat;
+ struct path lowerpath;
+
+ parent = dget_parent(dentry);
+ err = ovl_copy_up(parent);
+ if (err)
+ goto out_dput_parent;
+
+ ovl_path_lower(dentry, &lowerpath);
+ err = vfs_getattr(&lowerpath, &stat);
+ if (err)
+ goto out_dput_parent;
+
+ if (no_data)
+ stat.size = 0;
+
+ err = ovl_copy_up_one(parent, dentry, &lowerpath, &stat, attr);
+
+out_dput_parent:
+ dput(parent);
+ return err;
+}
+
+int ovl_setattr(struct dentry *dentry, struct iattr *attr)
+{
+ int err;
+ struct dentry *upperdentry;
+
+ err = ovl_want_write(dentry);
+ if (err)
+ goto out;
+
+ upperdentry = ovl_dentry_upper(dentry);
+ if (upperdentry) {
+ mutex_lock(&upperdentry->d_inode->i_mutex);
+ err = notify_change(upperdentry, attr, NULL);
+ mutex_unlock(&upperdentry->d_inode->i_mutex);
+ } else {
+ err = ovl_copy_up_last(dentry, attr, false);
+ }
+ ovl_drop_write(dentry);
+out:
+ return err;
+}
+
+static int ovl_getattr(struct vfsmount *mnt, struct dentry *dentry,
+ struct kstat *stat)
+{
+ struct path realpath;
+
+ ovl_path_real(dentry, &realpath);
+ return vfs_getattr(&realpath, stat);
+}
+
+int ovl_permission(struct inode *inode, int mask)
+{
+ struct ovl_entry *oe;
+ struct dentry *alias = NULL;
+ struct inode *realinode;
+ struct dentry *realdentry;
+ bool is_upper;
+ int err;
+
+ if (S_ISDIR(inode->i_mode)) {
+ oe = inode->i_private;
+ } else if (mask & MAY_NOT_BLOCK) {
+ return -ECHILD;
+ } else {
+ /*
+ * For non-directories find an alias and get the info
+ * from there.
+ */
+ alias = d_find_any_alias(inode);
+ if (WARN_ON(!alias))
+ return -ENOENT;
+
+ oe = alias->d_fsdata;
+ }
+
+ realdentry = ovl_entry_real(oe, &is_upper);
+
+ /* Careful in RCU walk mode */
+ realinode = ACCESS_ONCE(realdentry->d_inode);
+ if (!realinode) {
+ WARN_ON(!(mask & MAY_NOT_BLOCK));
+ err = -ENOENT;
+ goto out_dput;
+ }
+
+ if (mask & MAY_WRITE) {
+ umode_t mode = realinode->i_mode;
+
+ /*
+ * Writes will always be redirected to upper layer, so
+ * ignore lower layer being read-only.
+ *
+ * If the overlay itself is read-only then proceed
+ * with the permission check, don't return EROFS.
+ * This will only happen if this is the lower layer of
+ * another overlayfs.
+ *
+ * If upper fs becomes read-only after the overlay was
+ * constructed return EROFS to prevent modification of
+ * upper layer.
+ */
+ err = -EROFS;
+ if (is_upper && !IS_RDONLY(inode) && IS_RDONLY(realinode) &&
+ (S_ISREG(mode) || S_ISDIR(mode) || S_ISLNK(mode)))
+ goto out_dput;
+ }
+
+ err = __inode_permission(realinode, mask);
+out_dput:
+ dput(alias);
+ return err;
+}
+
+
+struct ovl_link_data {
+ struct dentry *realdentry;
+ void *cookie;
+};
+
+static void *ovl_follow_link(struct dentry *dentry, struct nameidata *nd)
+{
+ void *ret;
+ struct dentry *realdentry;
+ struct inode *realinode;
+
+ realdentry = ovl_dentry_real(dentry);
+ realinode = realdentry->d_inode;
+
+ if (WARN_ON(!realinode->i_op->follow_link))
+ return ERR_PTR(-EPERM);
+
+ ret = realinode->i_op->follow_link(realdentry, nd);
+ if (IS_ERR(ret))
+ return ret;
+
+ if (realinode->i_op->put_link) {
+ struct ovl_link_data *data;
+
+ data = kmalloc(sizeof(struct ovl_link_data), GFP_KERNEL);
+ if (!data) {
+ realinode->i_op->put_link(realdentry, nd, ret);
+ return ERR_PTR(-ENOMEM);
+ }
+ data->realdentry = realdentry;
+ data->cookie = ret;
+
+ return data;
+ } else {
+ return NULL;
+ }
+}
+
+static void ovl_put_link(struct dentry *dentry, struct nameidata *nd, void *c)
+{
+ struct inode *realinode;
+ struct ovl_link_data *data = c;
+
+ if (!data)
+ return;
+
+ realinode = data->realdentry->d_inode;
+ realinode->i_op->put_link(data->realdentry, nd, data->cookie);
+ kfree(data);
+}
+
+static int ovl_readlink(struct dentry *dentry, char __user *buf, int bufsiz)
+{
+ struct path realpath;
+ struct inode *realinode;
+
+ ovl_path_real(dentry, &realpath);
+ realinode = realpath.dentry->d_inode;
+
+ if (!realinode->i_op->readlink)
+ return -EINVAL;
+
+ touch_atime(&realpath);
+
+ return realinode->i_op->readlink(realpath.dentry, buf, bufsiz);
+}
+
+
+static bool ovl_is_private_xattr(const char *name)
+{
+ return strncmp(name, OVL_XATTR_PRE_NAME, OVL_XATTR_PRE_LEN) == 0;
+}
+
+int ovl_setxattr(struct dentry *dentry, const char *name,
+ const void *value, size_t size, int flags)
+{
+ int err;
+ struct dentry *upperdentry;
+
+ err = ovl_want_write(dentry);
+ if (err)
+ goto out;
+
+ err = -EPERM;
+ if (ovl_is_private_xattr(name))
+ goto out_drop_write;
+
+ err = ovl_copy_up(dentry);
+ if (err)
+ goto out_drop_write;
+
+ upperdentry = ovl_dentry_upper(dentry);
+ err = vfs_setxattr(upperdentry, name, value, size, flags);
+
+out_drop_write:
+ ovl_drop_write(dentry);
+out:
+ return err;
+}
+
+static bool ovl_need_xattr_filter(struct dentry *dentry,
+ enum ovl_path_type type)
+{
+ if ((type & (__OVL_PATH_PURE | __OVL_PATH_UPPER)) == __OVL_PATH_UPPER)
+ return S_ISDIR(dentry->d_inode->i_mode);
+ else
+ return false;
+}
+
+ssize_t ovl_getxattr(struct dentry *dentry, const char *name,
+ void *value, size_t size)
+{
+ struct path realpath;
+ enum ovl_path_type type = ovl_path_real(dentry, &realpath);
+
+ if (ovl_need_xattr_filter(dentry, type) && ovl_is_private_xattr(name))
+ return -ENODATA;
+
+ return vfs_getxattr(realpath.dentry, name, value, size);
+}
+
+ssize_t ovl_listxattr(struct dentry *dentry, char *list, size_t size)
+{
+ struct path realpath;
+ enum ovl_path_type type = ovl_path_real(dentry, &realpath);
+ ssize_t res;
+ int off;
+
+ res = vfs_listxattr(realpath.dentry, list, size);
+ if (res <= 0 || size == 0)
+ return res;
+
+ if (!ovl_need_xattr_filter(dentry, type))
+ return res;
+
+ /* filter out private xattrs */
+ for (off = 0; off < res;) {
+ char *s = list + off;
+ size_t slen = strlen(s) + 1;
+
+ BUG_ON(off + slen > res);
+
+ if (ovl_is_private_xattr(s)) {
+ res -= slen;
+ memmove(s, s + slen, res - off);
+ } else {
+ off += slen;
+ }
+ }
+
+ return res;
+}
+
+int ovl_removexattr(struct dentry *dentry, const char *name)
+{
+ int err;
+ struct path realpath;
+ enum ovl_path_type type = ovl_path_real(dentry, &realpath);
+
+ err = ovl_want_write(dentry);
+ if (err)
+ goto out;
+
+ err = -ENODATA;
+ if (ovl_need_xattr_filter(dentry, type) && ovl_is_private_xattr(name))
+ goto out_drop_write;
+
+ if (!OVL_TYPE_UPPER(type)) {
+ err = vfs_getxattr(realpath.dentry, name, NULL, 0);
+ if (err < 0)
+ goto out_drop_write;
+
+ err = ovl_copy_up(dentry);
+ if (err)
+ goto out_drop_write;
+
+ ovl_path_upper(dentry, &realpath);
+ }
+
+ err = vfs_removexattr(realpath.dentry, name);
+out_drop_write:
+ ovl_drop_write(dentry);
+out:
+ return err;
+}
+
+static bool ovl_open_need_copy_up(int flags, enum ovl_path_type type,
+ struct dentry *realdentry)
+{
+ if (OVL_TYPE_UPPER(type))
+ return false;
+
+ if (special_file(realdentry->d_inode->i_mode))
+ return false;
+
+ if (!(OPEN_FMODE(flags) & FMODE_WRITE) && !(flags & O_TRUNC))
+ return false;
+
+ return true;
+}
+
+static int ovl_dentry_open(struct dentry *dentry, struct file *file,
+ const struct cred *cred)
+{
+ int err;
+ struct path realpath;
+ enum ovl_path_type type;
+ bool want_write = false;
+
+ type = ovl_path_real(dentry, &realpath);
+ if (ovl_open_need_copy_up(file->f_flags, type, realpath.dentry)) {
+ want_write = true;
+ err = ovl_want_write(dentry);
+ if (err)
+ goto out;
+
+ if (file->f_flags & O_TRUNC)
+ err = ovl_copy_up_last(dentry, NULL, true);
+ else
+ err = ovl_copy_up(dentry);
+ if (err)
+ goto out_drop_write;
+
+ ovl_path_upper(dentry, &realpath);
+ }
+
+ err = vfs_open(&realpath, file, cred);
+out_drop_write:
+ if (want_write)
+ ovl_drop_write(dentry);
+out:
+ return err;
+}
+
+static const struct inode_operations ovl_file_inode_operations = {
+ .setattr = ovl_setattr,
+ .permission = ovl_permission,
+ .getattr = ovl_getattr,
+ .setxattr = ovl_setxattr,
+ .getxattr = ovl_getxattr,
+ .listxattr = ovl_listxattr,
+ .removexattr = ovl_removexattr,
+ .dentry_open = ovl_dentry_open,
+};
+
+static const struct inode_operations ovl_symlink_inode_operations = {
+ .setattr = ovl_setattr,
+ .follow_link = ovl_follow_link,
+ .put_link = ovl_put_link,
+ .readlink = ovl_readlink,
+ .getattr = ovl_getattr,
+ .setxattr = ovl_setxattr,
+ .getxattr = ovl_getxattr,
+ .listxattr = ovl_listxattr,
+ .removexattr = ovl_removexattr,
+};
+
+struct inode *ovl_new_inode(struct super_block *sb, umode_t mode,
+ struct ovl_entry *oe)
+{
+ struct inode *inode;
+
+ inode = new_inode(sb);
+ if (!inode)
+ return NULL;
+
+ mode &= S_IFMT;
+
+ inode->i_ino = get_next_ino();
+ inode->i_mode = mode;
+ inode->i_flags |= S_NOATIME | S_NOCMTIME;
+
+ switch (mode) {
+ case S_IFDIR:
+ inode->i_private = oe;
+ inode->i_op = &ovl_dir_inode_operations;
+ inode->i_fop = &ovl_dir_operations;
+ break;
+
+ case S_IFLNK:
+ inode->i_op = &ovl_symlink_inode_operations;
+ break;
+
+ case S_IFREG:
+ case S_IFSOCK:
+ case S_IFBLK:
+ case S_IFCHR:
+ case S_IFIFO:
+ inode->i_op = &ovl_file_inode_operations;
+ break;
+
+ default:
+ WARN(1, "illegal file type: %i\n", mode);
+ iput(inode);
+ inode = NULL;
+ }
+
+ return inode;
+}
diff --git a/kernel/fs/overlayfs/overlayfs.h b/kernel/fs/overlayfs/overlayfs.h
new file mode 100644
index 000000000..17ac5afc9
--- /dev/null
+++ b/kernel/fs/overlayfs/overlayfs.h
@@ -0,0 +1,199 @@
+/*
+ *
+ * Copyright (C) 2011 Novell Inc.
+ *
+ * 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 <linux/kernel.h>
+
+struct ovl_entry;
+
+enum ovl_path_type {
+ __OVL_PATH_PURE = (1 << 0),
+ __OVL_PATH_UPPER = (1 << 1),
+ __OVL_PATH_MERGE = (1 << 2),
+};
+
+#define OVL_TYPE_UPPER(type) ((type) & __OVL_PATH_UPPER)
+#define OVL_TYPE_MERGE(type) ((type) & __OVL_PATH_MERGE)
+#define OVL_TYPE_PURE_UPPER(type) ((type) & __OVL_PATH_PURE)
+#define OVL_TYPE_MERGE_OR_LOWER(type) \
+ (OVL_TYPE_MERGE(type) || !OVL_TYPE_UPPER(type))
+
+#define OVL_XATTR_PRE_NAME "trusted.overlay."
+#define OVL_XATTR_PRE_LEN 16
+#define OVL_XATTR_OPAQUE OVL_XATTR_PRE_NAME"opaque"
+
+static inline int ovl_do_rmdir(struct inode *dir, struct dentry *dentry)
+{
+ int err = vfs_rmdir(dir, dentry);
+ pr_debug("rmdir(%pd2) = %i\n", dentry, err);
+ return err;
+}
+
+static inline int ovl_do_unlink(struct inode *dir, struct dentry *dentry)
+{
+ int err = vfs_unlink(dir, dentry, NULL);
+ pr_debug("unlink(%pd2) = %i\n", dentry, err);
+ return err;
+}
+
+static inline int ovl_do_link(struct dentry *old_dentry, struct inode *dir,
+ struct dentry *new_dentry, bool debug)
+{
+ int err = vfs_link(old_dentry, dir, new_dentry, NULL);
+ if (debug) {
+ pr_debug("link(%pd2, %pd2) = %i\n",
+ old_dentry, new_dentry, err);
+ }
+ return err;
+}
+
+static inline int ovl_do_create(struct inode *dir, struct dentry *dentry,
+ umode_t mode, bool debug)
+{
+ int err = vfs_create(dir, dentry, mode, true);
+ if (debug)
+ pr_debug("create(%pd2, 0%o) = %i\n", dentry, mode, err);
+ return err;
+}
+
+static inline int ovl_do_mkdir(struct inode *dir, struct dentry *dentry,
+ umode_t mode, bool debug)
+{
+ int err = vfs_mkdir(dir, dentry, mode);
+ if (debug)
+ pr_debug("mkdir(%pd2, 0%o) = %i\n", dentry, mode, err);
+ return err;
+}
+
+static inline int ovl_do_mknod(struct inode *dir, struct dentry *dentry,
+ umode_t mode, dev_t dev, bool debug)
+{
+ int err = vfs_mknod(dir, dentry, mode, dev);
+ if (debug) {
+ pr_debug("mknod(%pd2, 0%o, 0%o) = %i\n",
+ dentry, mode, dev, err);
+ }
+ return err;
+}
+
+static inline int ovl_do_symlink(struct inode *dir, struct dentry *dentry,
+ const char *oldname, bool debug)
+{
+ int err = vfs_symlink(dir, dentry, oldname);
+ if (debug)
+ pr_debug("symlink(\"%s\", %pd2) = %i\n", oldname, dentry, err);
+ return err;
+}
+
+static inline int ovl_do_setxattr(struct dentry *dentry, const char *name,
+ const void *value, size_t size, int flags)
+{
+ int err = vfs_setxattr(dentry, name, value, size, flags);
+ pr_debug("setxattr(%pd2, \"%s\", \"%*s\", 0x%x) = %i\n",
+ dentry, name, (int) size, (char *) value, flags, err);
+ return err;
+}
+
+static inline int ovl_do_removexattr(struct dentry *dentry, const char *name)
+{
+ int err = vfs_removexattr(dentry, name);
+ pr_debug("removexattr(%pd2, \"%s\") = %i\n", dentry, name, err);
+ return err;
+}
+
+static inline int ovl_do_rename(struct inode *olddir, struct dentry *olddentry,
+ struct inode *newdir, struct dentry *newdentry,
+ unsigned int flags)
+{
+ int err;
+
+ pr_debug("rename2(%pd2, %pd2, 0x%x)\n",
+ olddentry, newdentry, flags);
+
+ err = vfs_rename(olddir, olddentry, newdir, newdentry, NULL, flags);
+
+ if (err) {
+ pr_debug("...rename2(%pd2, %pd2, ...) = %i\n",
+ olddentry, newdentry, err);
+ }
+ return err;
+}
+
+static inline int ovl_do_whiteout(struct inode *dir, struct dentry *dentry)
+{
+ int err = vfs_whiteout(dir, dentry);
+ pr_debug("whiteout(%pd2) = %i\n", dentry, err);
+ return err;
+}
+
+enum ovl_path_type ovl_path_type(struct dentry *dentry);
+u64 ovl_dentry_version_get(struct dentry *dentry);
+void ovl_dentry_version_inc(struct dentry *dentry);
+void ovl_path_upper(struct dentry *dentry, struct path *path);
+void ovl_path_lower(struct dentry *dentry, struct path *path);
+enum ovl_path_type ovl_path_real(struct dentry *dentry, struct path *path);
+int ovl_path_next(int idx, struct dentry *dentry, struct path *path);
+struct dentry *ovl_dentry_upper(struct dentry *dentry);
+struct dentry *ovl_dentry_lower(struct dentry *dentry);
+struct dentry *ovl_dentry_real(struct dentry *dentry);
+struct dentry *ovl_entry_real(struct ovl_entry *oe, bool *is_upper);
+struct ovl_dir_cache *ovl_dir_cache(struct dentry *dentry);
+void ovl_set_dir_cache(struct dentry *dentry, struct ovl_dir_cache *cache);
+struct dentry *ovl_workdir(struct dentry *dentry);
+int ovl_want_write(struct dentry *dentry);
+void ovl_drop_write(struct dentry *dentry);
+bool ovl_dentry_is_opaque(struct dentry *dentry);
+void ovl_dentry_set_opaque(struct dentry *dentry, bool opaque);
+bool ovl_is_whiteout(struct dentry *dentry);
+void ovl_dentry_update(struct dentry *dentry, struct dentry *upperdentry);
+struct dentry *ovl_lookup(struct inode *dir, struct dentry *dentry,
+ unsigned int flags);
+struct file *ovl_path_open(struct path *path, int flags);
+
+struct dentry *ovl_upper_create(struct dentry *upperdir, struct dentry *dentry,
+ struct kstat *stat, const char *link);
+
+/* readdir.c */
+extern const struct file_operations ovl_dir_operations;
+int ovl_check_empty_dir(struct dentry *dentry, struct list_head *list);
+void ovl_cleanup_whiteouts(struct dentry *upper, struct list_head *list);
+void ovl_cache_free(struct list_head *list);
+
+/* inode.c */
+int ovl_setattr(struct dentry *dentry, struct iattr *attr);
+int ovl_permission(struct inode *inode, int mask);
+int ovl_setxattr(struct dentry *dentry, const char *name,
+ const void *value, size_t size, int flags);
+ssize_t ovl_getxattr(struct dentry *dentry, const char *name,
+ void *value, size_t size);
+ssize_t ovl_listxattr(struct dentry *dentry, char *list, size_t size);
+int ovl_removexattr(struct dentry *dentry, const char *name);
+
+struct inode *ovl_new_inode(struct super_block *sb, umode_t mode,
+ struct ovl_entry *oe);
+static inline void ovl_copyattr(struct inode *from, struct inode *to)
+{
+ to->i_uid = from->i_uid;
+ to->i_gid = from->i_gid;
+}
+
+/* dir.c */
+extern const struct inode_operations ovl_dir_inode_operations;
+struct dentry *ovl_lookup_temp(struct dentry *workdir, struct dentry *dentry);
+int ovl_create_real(struct inode *dir, struct dentry *newdentry,
+ struct kstat *stat, const char *link,
+ struct dentry *hardlink, bool debug);
+void ovl_cleanup(struct inode *dir, struct dentry *dentry);
+
+/* copy_up.c */
+int ovl_copy_up(struct dentry *dentry);
+int ovl_copy_up_one(struct dentry *parent, struct dentry *dentry,
+ struct path *lowerpath, struct kstat *stat,
+ struct iattr *attr);
+int ovl_copy_xattr(struct dentry *old, struct dentry *new);
+int ovl_set_attr(struct dentry *upper, struct kstat *stat);
diff --git a/kernel/fs/overlayfs/readdir.c b/kernel/fs/overlayfs/readdir.c
new file mode 100644
index 000000000..907870e81
--- /dev/null
+++ b/kernel/fs/overlayfs/readdir.c
@@ -0,0 +1,557 @@
+/*
+ *
+ * Copyright (C) 2011 Novell Inc.
+ *
+ * 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 <linux/fs.h>
+#include <linux/slab.h>
+#include <linux/namei.h>
+#include <linux/file.h>
+#include <linux/xattr.h>
+#include <linux/rbtree.h>
+#include <linux/security.h>
+#include <linux/cred.h>
+#include "overlayfs.h"
+
+struct ovl_cache_entry {
+ unsigned int len;
+ unsigned int type;
+ u64 ino;
+ struct list_head l_node;
+ struct rb_node node;
+ bool is_whiteout;
+ char name[];
+};
+
+struct ovl_dir_cache {
+ long refcount;
+ u64 version;
+ struct list_head entries;
+};
+
+struct ovl_readdir_data {
+ struct dir_context ctx;
+ bool is_merge;
+ struct rb_root root;
+ struct list_head *list;
+ struct list_head middle;
+ struct dentry *dir;
+ int count;
+ int err;
+};
+
+struct ovl_dir_file {
+ bool is_real;
+ bool is_upper;
+ struct ovl_dir_cache *cache;
+ struct list_head *cursor;
+ struct file *realfile;
+ struct file *upperfile;
+};
+
+static struct ovl_cache_entry *ovl_cache_entry_from_node(struct rb_node *n)
+{
+ return container_of(n, struct ovl_cache_entry, node);
+}
+
+static struct ovl_cache_entry *ovl_cache_entry_find(struct rb_root *root,
+ const char *name, int len)
+{
+ struct rb_node *node = root->rb_node;
+ int cmp;
+
+ while (node) {
+ struct ovl_cache_entry *p = ovl_cache_entry_from_node(node);
+
+ cmp = strncmp(name, p->name, len);
+ if (cmp > 0)
+ node = p->node.rb_right;
+ else if (cmp < 0 || len < p->len)
+ node = p->node.rb_left;
+ else
+ return p;
+ }
+
+ return NULL;
+}
+
+static struct ovl_cache_entry *ovl_cache_entry_new(struct dentry *dir,
+ const char *name, int len,
+ u64 ino, unsigned int d_type)
+{
+ struct ovl_cache_entry *p;
+ size_t size = offsetof(struct ovl_cache_entry, name[len + 1]);
+
+ p = kmalloc(size, GFP_KERNEL);
+ if (!p)
+ return NULL;
+
+ memcpy(p->name, name, len);
+ p->name[len] = '\0';
+ p->len = len;
+ p->type = d_type;
+ p->ino = ino;
+ p->is_whiteout = false;
+
+ if (d_type == DT_CHR) {
+ struct dentry *dentry;
+ const struct cred *old_cred;
+ struct cred *override_cred;
+
+ override_cred = prepare_creds();
+ if (!override_cred) {
+ kfree(p);
+ return NULL;
+ }
+
+ /*
+ * CAP_DAC_OVERRIDE for lookup
+ */
+ cap_raise(override_cred->cap_effective, CAP_DAC_OVERRIDE);
+ old_cred = override_creds(override_cred);
+
+ dentry = lookup_one_len(name, dir, len);
+ if (!IS_ERR(dentry)) {
+ p->is_whiteout = ovl_is_whiteout(dentry);
+ dput(dentry);
+ }
+ revert_creds(old_cred);
+ put_cred(override_cred);
+ }
+ return p;
+}
+
+static int ovl_cache_entry_add_rb(struct ovl_readdir_data *rdd,
+ const char *name, int len, u64 ino,
+ unsigned int d_type)
+{
+ struct rb_node **newp = &rdd->root.rb_node;
+ struct rb_node *parent = NULL;
+ struct ovl_cache_entry *p;
+
+ while (*newp) {
+ int cmp;
+ struct ovl_cache_entry *tmp;
+
+ parent = *newp;
+ tmp = ovl_cache_entry_from_node(*newp);
+ cmp = strncmp(name, tmp->name, len);
+ if (cmp > 0)
+ newp = &tmp->node.rb_right;
+ else if (cmp < 0 || len < tmp->len)
+ newp = &tmp->node.rb_left;
+ else
+ return 0;
+ }
+
+ p = ovl_cache_entry_new(rdd->dir, name, len, ino, d_type);
+ if (p == NULL)
+ return -ENOMEM;
+
+ list_add_tail(&p->l_node, rdd->list);
+ rb_link_node(&p->node, parent, newp);
+ rb_insert_color(&p->node, &rdd->root);
+
+ return 0;
+}
+
+static int ovl_fill_lower(struct ovl_readdir_data *rdd,
+ const char *name, int namelen,
+ loff_t offset, u64 ino, unsigned int d_type)
+{
+ struct ovl_cache_entry *p;
+
+ p = ovl_cache_entry_find(&rdd->root, name, namelen);
+ if (p) {
+ list_move_tail(&p->l_node, &rdd->middle);
+ } else {
+ p = ovl_cache_entry_new(rdd->dir, name, namelen, ino, d_type);
+ if (p == NULL)
+ rdd->err = -ENOMEM;
+ else
+ list_add_tail(&p->l_node, &rdd->middle);
+ }
+
+ return rdd->err;
+}
+
+void ovl_cache_free(struct list_head *list)
+{
+ struct ovl_cache_entry *p;
+ struct ovl_cache_entry *n;
+
+ list_for_each_entry_safe(p, n, list, l_node)
+ kfree(p);
+
+ INIT_LIST_HEAD(list);
+}
+
+static void ovl_cache_put(struct ovl_dir_file *od, struct dentry *dentry)
+{
+ struct ovl_dir_cache *cache = od->cache;
+
+ WARN_ON(cache->refcount <= 0);
+ cache->refcount--;
+ if (!cache->refcount) {
+ if (ovl_dir_cache(dentry) == cache)
+ ovl_set_dir_cache(dentry, NULL);
+
+ ovl_cache_free(&cache->entries);
+ kfree(cache);
+ }
+}
+
+static int ovl_fill_merge(struct dir_context *ctx, const char *name,
+ int namelen, loff_t offset, u64 ino,
+ unsigned int d_type)
+{
+ struct ovl_readdir_data *rdd =
+ container_of(ctx, struct ovl_readdir_data, ctx);
+
+ rdd->count++;
+ if (!rdd->is_merge)
+ return ovl_cache_entry_add_rb(rdd, name, namelen, ino, d_type);
+ else
+ return ovl_fill_lower(rdd, name, namelen, offset, ino, d_type);
+}
+
+static inline int ovl_dir_read(struct path *realpath,
+ struct ovl_readdir_data *rdd)
+{
+ struct file *realfile;
+ int err;
+
+ realfile = ovl_path_open(realpath, O_RDONLY | O_DIRECTORY);
+ if (IS_ERR(realfile))
+ return PTR_ERR(realfile);
+
+ rdd->dir = realpath->dentry;
+ rdd->ctx.pos = 0;
+ do {
+ rdd->count = 0;
+ rdd->err = 0;
+ err = iterate_dir(realfile, &rdd->ctx);
+ if (err >= 0)
+ err = rdd->err;
+ } while (!err && rdd->count);
+ fput(realfile);
+
+ return err;
+}
+
+static void ovl_dir_reset(struct file *file)
+{
+ struct ovl_dir_file *od = file->private_data;
+ struct ovl_dir_cache *cache = od->cache;
+ struct dentry *dentry = file->f_path.dentry;
+ enum ovl_path_type type = ovl_path_type(dentry);
+
+ if (cache && ovl_dentry_version_get(dentry) != cache->version) {
+ ovl_cache_put(od, dentry);
+ od->cache = NULL;
+ od->cursor = NULL;
+ }
+ WARN_ON(!od->is_real && !OVL_TYPE_MERGE(type));
+ if (od->is_real && OVL_TYPE_MERGE(type))
+ od->is_real = false;
+}
+
+static int ovl_dir_read_merged(struct dentry *dentry, struct list_head *list)
+{
+ int err;
+ struct path realpath;
+ struct ovl_readdir_data rdd = {
+ .ctx.actor = ovl_fill_merge,
+ .list = list,
+ .root = RB_ROOT,
+ .is_merge = false,
+ };
+ int idx, next;
+
+ for (idx = 0; idx != -1; idx = next) {
+ next = ovl_path_next(idx, dentry, &realpath);
+
+ if (next != -1) {
+ err = ovl_dir_read(&realpath, &rdd);
+ if (err)
+ break;
+ } else {
+ /*
+ * Insert lowest layer entries before upper ones, this
+ * allows offsets to be reasonably constant
+ */
+ list_add(&rdd.middle, rdd.list);
+ rdd.is_merge = true;
+ err = ovl_dir_read(&realpath, &rdd);
+ list_del(&rdd.middle);
+ }
+ }
+ return err;
+}
+
+static void ovl_seek_cursor(struct ovl_dir_file *od, loff_t pos)
+{
+ struct list_head *p;
+ loff_t off = 0;
+
+ list_for_each(p, &od->cache->entries) {
+ if (off >= pos)
+ break;
+ off++;
+ }
+ /* Cursor is safe since the cache is stable */
+ od->cursor = p;
+}
+
+static struct ovl_dir_cache *ovl_cache_get(struct dentry *dentry)
+{
+ int res;
+ struct ovl_dir_cache *cache;
+
+ cache = ovl_dir_cache(dentry);
+ if (cache && ovl_dentry_version_get(dentry) == cache->version) {
+ cache->refcount++;
+ return cache;
+ }
+ ovl_set_dir_cache(dentry, NULL);
+
+ cache = kzalloc(sizeof(struct ovl_dir_cache), GFP_KERNEL);
+ if (!cache)
+ return ERR_PTR(-ENOMEM);
+
+ cache->refcount = 1;
+ INIT_LIST_HEAD(&cache->entries);
+
+ res = ovl_dir_read_merged(dentry, &cache->entries);
+ if (res) {
+ ovl_cache_free(&cache->entries);
+ kfree(cache);
+ return ERR_PTR(res);
+ }
+
+ cache->version = ovl_dentry_version_get(dentry);
+ ovl_set_dir_cache(dentry, cache);
+
+ return cache;
+}
+
+static int ovl_iterate(struct file *file, struct dir_context *ctx)
+{
+ struct ovl_dir_file *od = file->private_data;
+ struct dentry *dentry = file->f_path.dentry;
+ struct ovl_cache_entry *p;
+
+ if (!ctx->pos)
+ ovl_dir_reset(file);
+
+ if (od->is_real)
+ return iterate_dir(od->realfile, ctx);
+
+ if (!od->cache) {
+ struct ovl_dir_cache *cache;
+
+ cache = ovl_cache_get(dentry);
+ if (IS_ERR(cache))
+ return PTR_ERR(cache);
+
+ od->cache = cache;
+ ovl_seek_cursor(od, ctx->pos);
+ }
+
+ while (od->cursor != &od->cache->entries) {
+ p = list_entry(od->cursor, struct ovl_cache_entry, l_node);
+ if (!p->is_whiteout)
+ if (!dir_emit(ctx, p->name, p->len, p->ino, p->type))
+ break;
+ od->cursor = p->l_node.next;
+ ctx->pos++;
+ }
+ return 0;
+}
+
+static loff_t ovl_dir_llseek(struct file *file, loff_t offset, int origin)
+{
+ loff_t res;
+ struct ovl_dir_file *od = file->private_data;
+
+ mutex_lock(&file_inode(file)->i_mutex);
+ if (!file->f_pos)
+ ovl_dir_reset(file);
+
+ if (od->is_real) {
+ res = vfs_llseek(od->realfile, offset, origin);
+ file->f_pos = od->realfile->f_pos;
+ } else {
+ res = -EINVAL;
+
+ switch (origin) {
+ case SEEK_CUR:
+ offset += file->f_pos;
+ break;
+ case SEEK_SET:
+ break;
+ default:
+ goto out_unlock;
+ }
+ if (offset < 0)
+ goto out_unlock;
+
+ if (offset != file->f_pos) {
+ file->f_pos = offset;
+ if (od->cache)
+ ovl_seek_cursor(od, offset);
+ }
+ res = offset;
+ }
+out_unlock:
+ mutex_unlock(&file_inode(file)->i_mutex);
+
+ return res;
+}
+
+static int ovl_dir_fsync(struct file *file, loff_t start, loff_t end,
+ int datasync)
+{
+ struct ovl_dir_file *od = file->private_data;
+ struct dentry *dentry = file->f_path.dentry;
+ struct file *realfile = od->realfile;
+
+ /*
+ * Need to check if we started out being a lower dir, but got copied up
+ */
+ if (!od->is_upper && OVL_TYPE_UPPER(ovl_path_type(dentry))) {
+ struct inode *inode = file_inode(file);
+
+ realfile = lockless_dereference(od->upperfile);
+ if (!realfile) {
+ struct path upperpath;
+
+ ovl_path_upper(dentry, &upperpath);
+ realfile = ovl_path_open(&upperpath, O_RDONLY);
+ smp_mb__before_spinlock();
+ mutex_lock(&inode->i_mutex);
+ if (!od->upperfile) {
+ if (IS_ERR(realfile)) {
+ mutex_unlock(&inode->i_mutex);
+ return PTR_ERR(realfile);
+ }
+ od->upperfile = realfile;
+ } else {
+ /* somebody has beaten us to it */
+ if (!IS_ERR(realfile))
+ fput(realfile);
+ realfile = od->upperfile;
+ }
+ mutex_unlock(&inode->i_mutex);
+ }
+ }
+
+ return vfs_fsync_range(realfile, start, end, datasync);
+}
+
+static int ovl_dir_release(struct inode *inode, struct file *file)
+{
+ struct ovl_dir_file *od = file->private_data;
+
+ if (od->cache) {
+ mutex_lock(&inode->i_mutex);
+ ovl_cache_put(od, file->f_path.dentry);
+ mutex_unlock(&inode->i_mutex);
+ }
+ fput(od->realfile);
+ if (od->upperfile)
+ fput(od->upperfile);
+ kfree(od);
+
+ return 0;
+}
+
+static int ovl_dir_open(struct inode *inode, struct file *file)
+{
+ struct path realpath;
+ struct file *realfile;
+ struct ovl_dir_file *od;
+ enum ovl_path_type type;
+
+ od = kzalloc(sizeof(struct ovl_dir_file), GFP_KERNEL);
+ if (!od)
+ return -ENOMEM;
+
+ type = ovl_path_real(file->f_path.dentry, &realpath);
+ realfile = ovl_path_open(&realpath, file->f_flags);
+ if (IS_ERR(realfile)) {
+ kfree(od);
+ return PTR_ERR(realfile);
+ }
+ od->realfile = realfile;
+ od->is_real = !OVL_TYPE_MERGE(type);
+ od->is_upper = OVL_TYPE_UPPER(type);
+ file->private_data = od;
+
+ return 0;
+}
+
+const struct file_operations ovl_dir_operations = {
+ .read = generic_read_dir,
+ .open = ovl_dir_open,
+ .iterate = ovl_iterate,
+ .llseek = ovl_dir_llseek,
+ .fsync = ovl_dir_fsync,
+ .release = ovl_dir_release,
+};
+
+int ovl_check_empty_dir(struct dentry *dentry, struct list_head *list)
+{
+ int err;
+ struct ovl_cache_entry *p;
+
+ err = ovl_dir_read_merged(dentry, list);
+ if (err)
+ return err;
+
+ err = 0;
+
+ list_for_each_entry(p, list, l_node) {
+ if (p->is_whiteout)
+ continue;
+
+ if (p->name[0] == '.') {
+ if (p->len == 1)
+ continue;
+ if (p->len == 2 && p->name[1] == '.')
+ continue;
+ }
+ err = -ENOTEMPTY;
+ break;
+ }
+
+ return err;
+}
+
+void ovl_cleanup_whiteouts(struct dentry *upper, struct list_head *list)
+{
+ struct ovl_cache_entry *p;
+
+ mutex_lock_nested(&upper->d_inode->i_mutex, I_MUTEX_CHILD);
+ list_for_each_entry(p, list, l_node) {
+ struct dentry *dentry;
+
+ if (!p->is_whiteout)
+ continue;
+
+ dentry = lookup_one_len(p->name, upper, p->len);
+ if (IS_ERR(dentry)) {
+ pr_err("overlayfs: lookup '%s/%.*s' failed (%i)\n",
+ upper->d_name.name, p->len, p->name,
+ (int) PTR_ERR(dentry));
+ continue;
+ }
+ ovl_cleanup(upper->d_inode, dentry);
+ dput(dentry);
+ }
+ mutex_unlock(&upper->d_inode->i_mutex);
+}
diff --git a/kernel/fs/overlayfs/super.c b/kernel/fs/overlayfs/super.c
new file mode 100644
index 000000000..bf8537c7f
--- /dev/null
+++ b/kernel/fs/overlayfs/super.c
@@ -0,0 +1,1046 @@
+/*
+ *
+ * Copyright (C) 2011 Novell Inc.
+ *
+ * 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 <linux/fs.h>
+#include <linux/namei.h>
+#include <linux/xattr.h>
+#include <linux/security.h>
+#include <linux/mount.h>
+#include <linux/slab.h>
+#include <linux/parser.h>
+#include <linux/module.h>
+#include <linux/sched.h>
+#include <linux/statfs.h>
+#include <linux/seq_file.h>
+#include "overlayfs.h"
+
+MODULE_AUTHOR("Miklos Szeredi <miklos@szeredi.hu>");
+MODULE_DESCRIPTION("Overlay filesystem");
+MODULE_LICENSE("GPL");
+
+#define OVERLAYFS_SUPER_MAGIC 0x794c7630
+
+struct ovl_config {
+ char *lowerdir;
+ char *upperdir;
+ char *workdir;
+};
+
+/* private information held for overlayfs's superblock */
+struct ovl_fs {
+ struct vfsmount *upper_mnt;
+ unsigned numlower;
+ struct vfsmount **lower_mnt;
+ struct dentry *workdir;
+ long lower_namelen;
+ /* pathnames of lower and upper dirs, for show_options */
+ struct ovl_config config;
+};
+
+struct ovl_dir_cache;
+
+/* private information held for every overlayfs dentry */
+struct ovl_entry {
+ struct dentry *__upperdentry;
+ struct ovl_dir_cache *cache;
+ union {
+ struct {
+ u64 version;
+ bool opaque;
+ };
+ struct rcu_head rcu;
+ };
+ unsigned numlower;
+ struct path lowerstack[];
+};
+
+#define OVL_MAX_STACK 500
+
+static struct dentry *__ovl_dentry_lower(struct ovl_entry *oe)
+{
+ return oe->numlower ? oe->lowerstack[0].dentry : NULL;
+}
+
+enum ovl_path_type ovl_path_type(struct dentry *dentry)
+{
+ struct ovl_entry *oe = dentry->d_fsdata;
+ enum ovl_path_type type = 0;
+
+ if (oe->__upperdentry) {
+ type = __OVL_PATH_UPPER;
+
+ if (oe->numlower) {
+ if (S_ISDIR(dentry->d_inode->i_mode))
+ type |= __OVL_PATH_MERGE;
+ } else if (!oe->opaque) {
+ type |= __OVL_PATH_PURE;
+ }
+ } else {
+ if (oe->numlower > 1)
+ type |= __OVL_PATH_MERGE;
+ }
+ return type;
+}
+
+static struct dentry *ovl_upperdentry_dereference(struct ovl_entry *oe)
+{
+ return lockless_dereference(oe->__upperdentry);
+}
+
+void ovl_path_upper(struct dentry *dentry, struct path *path)
+{
+ struct ovl_fs *ofs = dentry->d_sb->s_fs_info;
+ struct ovl_entry *oe = dentry->d_fsdata;
+
+ path->mnt = ofs->upper_mnt;
+ path->dentry = ovl_upperdentry_dereference(oe);
+}
+
+enum ovl_path_type ovl_path_real(struct dentry *dentry, struct path *path)
+{
+ enum ovl_path_type type = ovl_path_type(dentry);
+
+ if (!OVL_TYPE_UPPER(type))
+ ovl_path_lower(dentry, path);
+ else
+ ovl_path_upper(dentry, path);
+
+ return type;
+}
+
+struct dentry *ovl_dentry_upper(struct dentry *dentry)
+{
+ struct ovl_entry *oe = dentry->d_fsdata;
+
+ return ovl_upperdentry_dereference(oe);
+}
+
+struct dentry *ovl_dentry_lower(struct dentry *dentry)
+{
+ struct ovl_entry *oe = dentry->d_fsdata;
+
+ return __ovl_dentry_lower(oe);
+}
+
+struct dentry *ovl_dentry_real(struct dentry *dentry)
+{
+ struct ovl_entry *oe = dentry->d_fsdata;
+ struct dentry *realdentry;
+
+ realdentry = ovl_upperdentry_dereference(oe);
+ if (!realdentry)
+ realdentry = __ovl_dentry_lower(oe);
+
+ return realdentry;
+}
+
+struct dentry *ovl_entry_real(struct ovl_entry *oe, bool *is_upper)
+{
+ struct dentry *realdentry;
+
+ realdentry = ovl_upperdentry_dereference(oe);
+ if (realdentry) {
+ *is_upper = true;
+ } else {
+ realdentry = __ovl_dentry_lower(oe);
+ *is_upper = false;
+ }
+ return realdentry;
+}
+
+struct ovl_dir_cache *ovl_dir_cache(struct dentry *dentry)
+{
+ struct ovl_entry *oe = dentry->d_fsdata;
+
+ return oe->cache;
+}
+
+void ovl_set_dir_cache(struct dentry *dentry, struct ovl_dir_cache *cache)
+{
+ struct ovl_entry *oe = dentry->d_fsdata;
+
+ oe->cache = cache;
+}
+
+void ovl_path_lower(struct dentry *dentry, struct path *path)
+{
+ struct ovl_entry *oe = dentry->d_fsdata;
+
+ *path = oe->numlower ? oe->lowerstack[0] : (struct path) { NULL, NULL };
+}
+
+int ovl_want_write(struct dentry *dentry)
+{
+ struct ovl_fs *ofs = dentry->d_sb->s_fs_info;
+ return mnt_want_write(ofs->upper_mnt);
+}
+
+void ovl_drop_write(struct dentry *dentry)
+{
+ struct ovl_fs *ofs = dentry->d_sb->s_fs_info;
+ mnt_drop_write(ofs->upper_mnt);
+}
+
+struct dentry *ovl_workdir(struct dentry *dentry)
+{
+ struct ovl_fs *ofs = dentry->d_sb->s_fs_info;
+ return ofs->workdir;
+}
+
+bool ovl_dentry_is_opaque(struct dentry *dentry)
+{
+ struct ovl_entry *oe = dentry->d_fsdata;
+ return oe->opaque;
+}
+
+void ovl_dentry_set_opaque(struct dentry *dentry, bool opaque)
+{
+ struct ovl_entry *oe = dentry->d_fsdata;
+ oe->opaque = opaque;
+}
+
+void ovl_dentry_update(struct dentry *dentry, struct dentry *upperdentry)
+{
+ struct ovl_entry *oe = dentry->d_fsdata;
+
+ WARN_ON(!mutex_is_locked(&upperdentry->d_parent->d_inode->i_mutex));
+ WARN_ON(oe->__upperdentry);
+ BUG_ON(!upperdentry->d_inode);
+ /*
+ * Make sure upperdentry is consistent before making it visible to
+ * ovl_upperdentry_dereference().
+ */
+ smp_wmb();
+ oe->__upperdentry = upperdentry;
+}
+
+void ovl_dentry_version_inc(struct dentry *dentry)
+{
+ struct ovl_entry *oe = dentry->d_fsdata;
+
+ WARN_ON(!mutex_is_locked(&dentry->d_inode->i_mutex));
+ oe->version++;
+}
+
+u64 ovl_dentry_version_get(struct dentry *dentry)
+{
+ struct ovl_entry *oe = dentry->d_fsdata;
+
+ WARN_ON(!mutex_is_locked(&dentry->d_inode->i_mutex));
+ return oe->version;
+}
+
+bool ovl_is_whiteout(struct dentry *dentry)
+{
+ struct inode *inode = dentry->d_inode;
+
+ return inode && IS_WHITEOUT(inode);
+}
+
+static bool ovl_is_opaquedir(struct dentry *dentry)
+{
+ int res;
+ char val;
+ struct inode *inode = dentry->d_inode;
+
+ if (!S_ISDIR(inode->i_mode) || !inode->i_op->getxattr)
+ return false;
+
+ res = inode->i_op->getxattr(dentry, OVL_XATTR_OPAQUE, &val, 1);
+ if (res == 1 && val == 'y')
+ return true;
+
+ return false;
+}
+
+static void ovl_dentry_release(struct dentry *dentry)
+{
+ struct ovl_entry *oe = dentry->d_fsdata;
+
+ if (oe) {
+ unsigned int i;
+
+ dput(oe->__upperdentry);
+ for (i = 0; i < oe->numlower; i++)
+ dput(oe->lowerstack[i].dentry);
+ kfree_rcu(oe, rcu);
+ }
+}
+
+static const struct dentry_operations ovl_dentry_operations = {
+ .d_release = ovl_dentry_release,
+};
+
+static struct ovl_entry *ovl_alloc_entry(unsigned int numlower)
+{
+ size_t size = offsetof(struct ovl_entry, lowerstack[numlower]);
+ struct ovl_entry *oe = kzalloc(size, GFP_KERNEL);
+
+ if (oe)
+ oe->numlower = numlower;
+
+ return oe;
+}
+
+static inline struct dentry *ovl_lookup_real(struct dentry *dir,
+ struct qstr *name)
+{
+ struct dentry *dentry;
+
+ mutex_lock(&dir->d_inode->i_mutex);
+ dentry = lookup_one_len(name->name, dir, name->len);
+ mutex_unlock(&dir->d_inode->i_mutex);
+
+ if (IS_ERR(dentry)) {
+ if (PTR_ERR(dentry) == -ENOENT)
+ dentry = NULL;
+ } else if (!dentry->d_inode) {
+ dput(dentry);
+ dentry = NULL;
+ }
+ return dentry;
+}
+
+/*
+ * Returns next layer in stack starting from top.
+ * Returns -1 if this is the last layer.
+ */
+int ovl_path_next(int idx, struct dentry *dentry, struct path *path)
+{
+ struct ovl_entry *oe = dentry->d_fsdata;
+
+ BUG_ON(idx < 0);
+ if (idx == 0) {
+ ovl_path_upper(dentry, path);
+ if (path->dentry)
+ return oe->numlower ? 1 : -1;
+ idx++;
+ }
+ BUG_ON(idx > oe->numlower);
+ *path = oe->lowerstack[idx - 1];
+
+ return (idx < oe->numlower) ? idx + 1 : -1;
+}
+
+struct dentry *ovl_lookup(struct inode *dir, struct dentry *dentry,
+ unsigned int flags)
+{
+ struct ovl_entry *oe;
+ struct ovl_entry *poe = dentry->d_parent->d_fsdata;
+ struct path *stack = NULL;
+ struct dentry *upperdir, *upperdentry = NULL;
+ unsigned int ctr = 0;
+ struct inode *inode = NULL;
+ bool upperopaque = false;
+ struct dentry *this, *prev = NULL;
+ unsigned int i;
+ int err;
+
+ upperdir = ovl_upperdentry_dereference(poe);
+ if (upperdir) {
+ this = ovl_lookup_real(upperdir, &dentry->d_name);
+ err = PTR_ERR(this);
+ if (IS_ERR(this))
+ goto out;
+
+ if (this) {
+ if (ovl_is_whiteout(this)) {
+ dput(this);
+ this = NULL;
+ upperopaque = true;
+ } else if (poe->numlower && ovl_is_opaquedir(this)) {
+ upperopaque = true;
+ }
+ }
+ upperdentry = prev = this;
+ }
+
+ if (!upperopaque && poe->numlower) {
+ err = -ENOMEM;
+ stack = kcalloc(poe->numlower, sizeof(struct path), GFP_KERNEL);
+ if (!stack)
+ goto out_put_upper;
+ }
+
+ for (i = 0; !upperopaque && i < poe->numlower; i++) {
+ bool opaque = false;
+ struct path lowerpath = poe->lowerstack[i];
+
+ this = ovl_lookup_real(lowerpath.dentry, &dentry->d_name);
+ err = PTR_ERR(this);
+ if (IS_ERR(this)) {
+ /*
+ * If it's positive, then treat ENAMETOOLONG as ENOENT.
+ */
+ if (err == -ENAMETOOLONG && (upperdentry || ctr))
+ continue;
+ goto out_put;
+ }
+ if (!this)
+ continue;
+ if (ovl_is_whiteout(this)) {
+ dput(this);
+ break;
+ }
+ /*
+ * Only makes sense to check opaque dir if this is not the
+ * lowermost layer.
+ */
+ if (i < poe->numlower - 1 && ovl_is_opaquedir(this))
+ opaque = true;
+
+ if (prev && (!S_ISDIR(prev->d_inode->i_mode) ||
+ !S_ISDIR(this->d_inode->i_mode))) {
+ /*
+ * FIXME: check for upper-opaqueness maybe better done
+ * in remove code.
+ */
+ if (prev == upperdentry)
+ upperopaque = true;
+ dput(this);
+ break;
+ }
+ /*
+ * If this is a non-directory then stop here.
+ */
+ if (!S_ISDIR(this->d_inode->i_mode))
+ opaque = true;
+
+ stack[ctr].dentry = this;
+ stack[ctr].mnt = lowerpath.mnt;
+ ctr++;
+ prev = this;
+ if (opaque)
+ break;
+ }
+
+ oe = ovl_alloc_entry(ctr);
+ err = -ENOMEM;
+ if (!oe)
+ goto out_put;
+
+ if (upperdentry || ctr) {
+ struct dentry *realdentry;
+
+ realdentry = upperdentry ? upperdentry : stack[0].dentry;
+
+ err = -ENOMEM;
+ inode = ovl_new_inode(dentry->d_sb, realdentry->d_inode->i_mode,
+ oe);
+ if (!inode)
+ goto out_free_oe;
+ ovl_copyattr(realdentry->d_inode, inode);
+ }
+
+ oe->opaque = upperopaque;
+ oe->__upperdentry = upperdentry;
+ memcpy(oe->lowerstack, stack, sizeof(struct path) * ctr);
+ kfree(stack);
+ dentry->d_fsdata = oe;
+ d_add(dentry, inode);
+
+ return NULL;
+
+out_free_oe:
+ kfree(oe);
+out_put:
+ for (i = 0; i < ctr; i++)
+ dput(stack[i].dentry);
+ kfree(stack);
+out_put_upper:
+ dput(upperdentry);
+out:
+ return ERR_PTR(err);
+}
+
+struct file *ovl_path_open(struct path *path, int flags)
+{
+ return dentry_open(path, flags, current_cred());
+}
+
+static void ovl_put_super(struct super_block *sb)
+{
+ struct ovl_fs *ufs = sb->s_fs_info;
+ unsigned i;
+
+ dput(ufs->workdir);
+ mntput(ufs->upper_mnt);
+ for (i = 0; i < ufs->numlower; i++)
+ mntput(ufs->lower_mnt[i]);
+
+ kfree(ufs->config.lowerdir);
+ kfree(ufs->config.upperdir);
+ kfree(ufs->config.workdir);
+ kfree(ufs);
+}
+
+/**
+ * ovl_statfs
+ * @sb: The overlayfs super block
+ * @buf: The struct kstatfs to fill in with stats
+ *
+ * Get the filesystem statistics. As writes always target the upper layer
+ * filesystem pass the statfs to the upper filesystem (if it exists)
+ */
+static int ovl_statfs(struct dentry *dentry, struct kstatfs *buf)
+{
+ struct ovl_fs *ofs = dentry->d_sb->s_fs_info;
+ struct dentry *root_dentry = dentry->d_sb->s_root;
+ struct path path;
+ int err;
+
+ ovl_path_real(root_dentry, &path);
+
+ err = vfs_statfs(&path, buf);
+ if (!err) {
+ buf->f_namelen = max(buf->f_namelen, ofs->lower_namelen);
+ buf->f_type = OVERLAYFS_SUPER_MAGIC;
+ }
+
+ return err;
+}
+
+/**
+ * ovl_show_options
+ *
+ * Prints the mount options for a given superblock.
+ * Returns zero; does not fail.
+ */
+static int ovl_show_options(struct seq_file *m, struct dentry *dentry)
+{
+ struct super_block *sb = dentry->d_sb;
+ struct ovl_fs *ufs = sb->s_fs_info;
+
+ seq_printf(m, ",lowerdir=%s", ufs->config.lowerdir);
+ if (ufs->config.upperdir) {
+ seq_printf(m, ",upperdir=%s", ufs->config.upperdir);
+ seq_printf(m, ",workdir=%s", ufs->config.workdir);
+ }
+ return 0;
+}
+
+static int ovl_remount(struct super_block *sb, int *flags, char *data)
+{
+ struct ovl_fs *ufs = sb->s_fs_info;
+
+ if (!(*flags & MS_RDONLY) && (!ufs->upper_mnt || !ufs->workdir))
+ return -EROFS;
+
+ return 0;
+}
+
+static const struct super_operations ovl_super_operations = {
+ .put_super = ovl_put_super,
+ .statfs = ovl_statfs,
+ .show_options = ovl_show_options,
+ .remount_fs = ovl_remount,
+};
+
+enum {
+ OPT_LOWERDIR,
+ OPT_UPPERDIR,
+ OPT_WORKDIR,
+ OPT_ERR,
+};
+
+static const match_table_t ovl_tokens = {
+ {OPT_LOWERDIR, "lowerdir=%s"},
+ {OPT_UPPERDIR, "upperdir=%s"},
+ {OPT_WORKDIR, "workdir=%s"},
+ {OPT_ERR, NULL}
+};
+
+static char *ovl_next_opt(char **s)
+{
+ char *sbegin = *s;
+ char *p;
+
+ if (sbegin == NULL)
+ return NULL;
+
+ for (p = sbegin; *p; p++) {
+ if (*p == '\\') {
+ p++;
+ if (!*p)
+ break;
+ } else if (*p == ',') {
+ *p = '\0';
+ *s = p + 1;
+ return sbegin;
+ }
+ }
+ *s = NULL;
+ return sbegin;
+}
+
+static int ovl_parse_opt(char *opt, struct ovl_config *config)
+{
+ char *p;
+
+ while ((p = ovl_next_opt(&opt)) != NULL) {
+ int token;
+ substring_t args[MAX_OPT_ARGS];
+
+ if (!*p)
+ continue;
+
+ token = match_token(p, ovl_tokens, args);
+ switch (token) {
+ case OPT_UPPERDIR:
+ kfree(config->upperdir);
+ config->upperdir = match_strdup(&args[0]);
+ if (!config->upperdir)
+ return -ENOMEM;
+ break;
+
+ case OPT_LOWERDIR:
+ kfree(config->lowerdir);
+ config->lowerdir = match_strdup(&args[0]);
+ if (!config->lowerdir)
+ return -ENOMEM;
+ break;
+
+ case OPT_WORKDIR:
+ kfree(config->workdir);
+ config->workdir = match_strdup(&args[0]);
+ if (!config->workdir)
+ return -ENOMEM;
+ break;
+
+ default:
+ pr_err("overlayfs: unrecognized mount option \"%s\" or missing value\n", p);
+ return -EINVAL;
+ }
+ }
+
+ /* Workdir is useless in non-upper mount */
+ if (!config->upperdir && config->workdir) {
+ pr_info("overlayfs: option \"workdir=%s\" is useless in a non-upper mount, ignore\n",
+ config->workdir);
+ kfree(config->workdir);
+ config->workdir = NULL;
+ }
+
+ return 0;
+}
+
+#define OVL_WORKDIR_NAME "work"
+
+static struct dentry *ovl_workdir_create(struct vfsmount *mnt,
+ struct dentry *dentry)
+{
+ struct inode *dir = dentry->d_inode;
+ struct dentry *work;
+ int err;
+ bool retried = false;
+
+ err = mnt_want_write(mnt);
+ if (err)
+ return ERR_PTR(err);
+
+ mutex_lock_nested(&dir->i_mutex, I_MUTEX_PARENT);
+retry:
+ work = lookup_one_len(OVL_WORKDIR_NAME, dentry,
+ strlen(OVL_WORKDIR_NAME));
+
+ if (!IS_ERR(work)) {
+ struct kstat stat = {
+ .mode = S_IFDIR | 0,
+ };
+
+ if (work->d_inode) {
+ err = -EEXIST;
+ if (retried)
+ goto out_dput;
+
+ retried = true;
+ ovl_cleanup(dir, work);
+ dput(work);
+ goto retry;
+ }
+
+ err = ovl_create_real(dir, work, &stat, NULL, NULL, true);
+ if (err)
+ goto out_dput;
+ }
+out_unlock:
+ mutex_unlock(&dir->i_mutex);
+ mnt_drop_write(mnt);
+
+ return work;
+
+out_dput:
+ dput(work);
+ work = ERR_PTR(err);
+ goto out_unlock;
+}
+
+static void ovl_unescape(char *s)
+{
+ char *d = s;
+
+ for (;; s++, d++) {
+ if (*s == '\\')
+ s++;
+ *d = *s;
+ if (!*s)
+ break;
+ }
+}
+
+static bool ovl_is_allowed_fs_type(struct dentry *root)
+{
+ const struct dentry_operations *dop = root->d_op;
+
+ /*
+ * We don't support:
+ * - automount filesystems
+ * - filesystems with revalidate (FIXME for lower layer)
+ * - filesystems with case insensitive names
+ */
+ if (dop &&
+ (dop->d_manage || dop->d_automount ||
+ dop->d_revalidate || dop->d_weak_revalidate ||
+ dop->d_compare || dop->d_hash)) {
+ return false;
+ }
+ return true;
+}
+
+static int ovl_mount_dir_noesc(const char *name, struct path *path)
+{
+ int err = -EINVAL;
+
+ if (!*name) {
+ pr_err("overlayfs: empty lowerdir\n");
+ goto out;
+ }
+ err = kern_path(name, LOOKUP_FOLLOW, path);
+ if (err) {
+ pr_err("overlayfs: failed to resolve '%s': %i\n", name, err);
+ goto out;
+ }
+ err = -EINVAL;
+ if (!ovl_is_allowed_fs_type(path->dentry)) {
+ pr_err("overlayfs: filesystem on '%s' not supported\n", name);
+ goto out_put;
+ }
+ if (!S_ISDIR(path->dentry->d_inode->i_mode)) {
+ pr_err("overlayfs: '%s' not a directory\n", name);
+ goto out_put;
+ }
+ return 0;
+
+out_put:
+ path_put(path);
+out:
+ return err;
+}
+
+static int ovl_mount_dir(const char *name, struct path *path)
+{
+ int err = -ENOMEM;
+ char *tmp = kstrdup(name, GFP_KERNEL);
+
+ if (tmp) {
+ ovl_unescape(tmp);
+ err = ovl_mount_dir_noesc(tmp, path);
+ kfree(tmp);
+ }
+ return err;
+}
+
+static int ovl_lower_dir(const char *name, struct path *path, long *namelen,
+ int *stack_depth)
+{
+ int err;
+ struct kstatfs statfs;
+
+ err = ovl_mount_dir_noesc(name, path);
+ if (err)
+ goto out;
+
+ err = vfs_statfs(path, &statfs);
+ if (err) {
+ pr_err("overlayfs: statfs failed on '%s'\n", name);
+ goto out_put;
+ }
+ *namelen = max(*namelen, statfs.f_namelen);
+ *stack_depth = max(*stack_depth, path->mnt->mnt_sb->s_stack_depth);
+
+ return 0;
+
+out_put:
+ path_put(path);
+out:
+ return err;
+}
+
+/* Workdir should not be subdir of upperdir and vice versa */
+static bool ovl_workdir_ok(struct dentry *workdir, struct dentry *upperdir)
+{
+ bool ok = false;
+
+ if (workdir != upperdir) {
+ ok = (lock_rename(workdir, upperdir) == NULL);
+ unlock_rename(workdir, upperdir);
+ }
+ return ok;
+}
+
+static unsigned int ovl_split_lowerdirs(char *str)
+{
+ unsigned int ctr = 1;
+ char *s, *d;
+
+ for (s = d = str;; s++, d++) {
+ if (*s == '\\') {
+ s++;
+ } else if (*s == ':') {
+ *d = '\0';
+ ctr++;
+ continue;
+ }
+ *d = *s;
+ if (!*s)
+ break;
+ }
+ return ctr;
+}
+
+static int ovl_fill_super(struct super_block *sb, void *data, int silent)
+{
+ struct path upperpath = { NULL, NULL };
+ struct path workpath = { NULL, NULL };
+ struct dentry *root_dentry;
+ struct ovl_entry *oe;
+ struct ovl_fs *ufs;
+ struct path *stack = NULL;
+ char *lowertmp;
+ char *lower;
+ unsigned int numlower;
+ unsigned int stacklen = 0;
+ unsigned int i;
+ int err;
+
+ err = -ENOMEM;
+ ufs = kzalloc(sizeof(struct ovl_fs), GFP_KERNEL);
+ if (!ufs)
+ goto out;
+
+ err = ovl_parse_opt((char *) data, &ufs->config);
+ if (err)
+ goto out_free_config;
+
+ err = -EINVAL;
+ if (!ufs->config.lowerdir) {
+ pr_err("overlayfs: missing 'lowerdir'\n");
+ goto out_free_config;
+ }
+
+ sb->s_stack_depth = 0;
+ if (ufs->config.upperdir) {
+ if (!ufs->config.workdir) {
+ pr_err("overlayfs: missing 'workdir'\n");
+ goto out_free_config;
+ }
+
+ err = ovl_mount_dir(ufs->config.upperdir, &upperpath);
+ if (err)
+ goto out_free_config;
+
+ /* Upper fs should not be r/o */
+ if (upperpath.mnt->mnt_sb->s_flags & MS_RDONLY) {
+ pr_err("overlayfs: upper fs is r/o, try multi-lower layers mount\n");
+ err = -EINVAL;
+ goto out_put_upperpath;
+ }
+
+ err = ovl_mount_dir(ufs->config.workdir, &workpath);
+ if (err)
+ goto out_put_upperpath;
+
+ err = -EINVAL;
+ if (upperpath.mnt != workpath.mnt) {
+ pr_err("overlayfs: workdir and upperdir must reside under the same mount\n");
+ goto out_put_workpath;
+ }
+ if (!ovl_workdir_ok(workpath.dentry, upperpath.dentry)) {
+ pr_err("overlayfs: workdir and upperdir must be separate subtrees\n");
+ goto out_put_workpath;
+ }
+ sb->s_stack_depth = upperpath.mnt->mnt_sb->s_stack_depth;
+ }
+ err = -ENOMEM;
+ lowertmp = kstrdup(ufs->config.lowerdir, GFP_KERNEL);
+ if (!lowertmp)
+ goto out_put_workpath;
+
+ err = -EINVAL;
+ stacklen = ovl_split_lowerdirs(lowertmp);
+ if (stacklen > OVL_MAX_STACK) {
+ pr_err("overlayfs: too many lower directries, limit is %d\n",
+ OVL_MAX_STACK);
+ goto out_free_lowertmp;
+ } else if (!ufs->config.upperdir && stacklen == 1) {
+ pr_err("overlayfs: at least 2 lowerdir are needed while upperdir nonexistent\n");
+ goto out_free_lowertmp;
+ }
+
+ stack = kcalloc(stacklen, sizeof(struct path), GFP_KERNEL);
+ if (!stack)
+ goto out_free_lowertmp;
+
+ lower = lowertmp;
+ for (numlower = 0; numlower < stacklen; numlower++) {
+ err = ovl_lower_dir(lower, &stack[numlower],
+ &ufs->lower_namelen, &sb->s_stack_depth);
+ if (err)
+ goto out_put_lowerpath;
+
+ lower = strchr(lower, '\0') + 1;
+ }
+
+ err = -EINVAL;
+ sb->s_stack_depth++;
+ if (sb->s_stack_depth > FILESYSTEM_MAX_STACK_DEPTH) {
+ pr_err("overlayfs: maximum fs stacking depth exceeded\n");
+ goto out_put_lowerpath;
+ }
+
+ if (ufs->config.upperdir) {
+ ufs->upper_mnt = clone_private_mount(&upperpath);
+ err = PTR_ERR(ufs->upper_mnt);
+ if (IS_ERR(ufs->upper_mnt)) {
+ pr_err("overlayfs: failed to clone upperpath\n");
+ goto out_put_lowerpath;
+ }
+
+ ufs->workdir = ovl_workdir_create(ufs->upper_mnt, workpath.dentry);
+ err = PTR_ERR(ufs->workdir);
+ if (IS_ERR(ufs->workdir)) {
+ pr_warn("overlayfs: failed to create directory %s/%s (errno: %i); mounting read-only\n",
+ ufs->config.workdir, OVL_WORKDIR_NAME, -err);
+ sb->s_flags |= MS_RDONLY;
+ ufs->workdir = NULL;
+ }
+ }
+
+ err = -ENOMEM;
+ ufs->lower_mnt = kcalloc(numlower, sizeof(struct vfsmount *), GFP_KERNEL);
+ if (ufs->lower_mnt == NULL)
+ goto out_put_workdir;
+ for (i = 0; i < numlower; i++) {
+ struct vfsmount *mnt = clone_private_mount(&stack[i]);
+
+ err = PTR_ERR(mnt);
+ if (IS_ERR(mnt)) {
+ pr_err("overlayfs: failed to clone lowerpath\n");
+ goto out_put_lower_mnt;
+ }
+ /*
+ * Make lower_mnt R/O. That way fchmod/fchown on lower file
+ * will fail instead of modifying lower fs.
+ */
+ mnt->mnt_flags |= MNT_READONLY;
+
+ ufs->lower_mnt[ufs->numlower] = mnt;
+ ufs->numlower++;
+ }
+
+ /* If the upper fs is nonexistent, we mark overlayfs r/o too */
+ if (!ufs->upper_mnt)
+ sb->s_flags |= MS_RDONLY;
+
+ sb->s_d_op = &ovl_dentry_operations;
+
+ err = -ENOMEM;
+ oe = ovl_alloc_entry(numlower);
+ if (!oe)
+ goto out_put_lower_mnt;
+
+ root_dentry = d_make_root(ovl_new_inode(sb, S_IFDIR, oe));
+ if (!root_dentry)
+ goto out_free_oe;
+
+ mntput(upperpath.mnt);
+ for (i = 0; i < numlower; i++)
+ mntput(stack[i].mnt);
+ path_put(&workpath);
+ kfree(lowertmp);
+
+ oe->__upperdentry = upperpath.dentry;
+ for (i = 0; i < numlower; i++) {
+ oe->lowerstack[i].dentry = stack[i].dentry;
+ oe->lowerstack[i].mnt = ufs->lower_mnt[i];
+ }
+
+ root_dentry->d_fsdata = oe;
+
+ sb->s_magic = OVERLAYFS_SUPER_MAGIC;
+ sb->s_op = &ovl_super_operations;
+ sb->s_root = root_dentry;
+ sb->s_fs_info = ufs;
+
+ return 0;
+
+out_free_oe:
+ kfree(oe);
+out_put_lower_mnt:
+ for (i = 0; i < ufs->numlower; i++)
+ mntput(ufs->lower_mnt[i]);
+ kfree(ufs->lower_mnt);
+out_put_workdir:
+ dput(ufs->workdir);
+ mntput(ufs->upper_mnt);
+out_put_lowerpath:
+ for (i = 0; i < numlower; i++)
+ path_put(&stack[i]);
+ kfree(stack);
+out_free_lowertmp:
+ kfree(lowertmp);
+out_put_workpath:
+ path_put(&workpath);
+out_put_upperpath:
+ path_put(&upperpath);
+out_free_config:
+ kfree(ufs->config.lowerdir);
+ kfree(ufs->config.upperdir);
+ kfree(ufs->config.workdir);
+ kfree(ufs);
+out:
+ return err;
+}
+
+static struct dentry *ovl_mount(struct file_system_type *fs_type, int flags,
+ const char *dev_name, void *raw_data)
+{
+ return mount_nodev(fs_type, flags, raw_data, ovl_fill_super);
+}
+
+static struct file_system_type ovl_fs_type = {
+ .owner = THIS_MODULE,
+ .name = "overlay",
+ .mount = ovl_mount,
+ .kill_sb = kill_anon_super,
+};
+MODULE_ALIAS_FS("overlay");
+
+static int __init ovl_init(void)
+{
+ return register_filesystem(&ovl_fs_type);
+}
+
+static void __exit ovl_exit(void)
+{
+ unregister_filesystem(&ovl_fs_type);
+}
+
+module_init(ovl_init);
+module_exit(ovl_exit);