static int unionfs_create(struct inode *dir, struct dentry *dentry,
umode_t mode, bool want_excl)
{
int err = 0;
struct dentry *lower_dentry = NULL;
struct dentry *lower_parent_dentry = NULL;
struct dentry *parent;
int valid = 0;
unionfs_read_lock(dentry->d_sb, UNIONFS_SMUTEX_CHILD);
parent = unionfs_lock_parent(dentry, UNIONFS_DMUTEX_PARENT);
unionfs_lock_dentry(dentry, UNIONFS_DMUTEX_CHILD);
valid = __unionfs_d_revalidate(dentry, parent, false, 0);
if (unlikely(!valid)) {
err = -ESTALE; /* same as what real_lookup does */
goto out;
}
lower_dentry = find_writeable_branch(dir, dentry);
if (IS_ERR(lower_dentry)) {
err = PTR_ERR(lower_dentry);
goto out;
}
lower_parent_dentry = lock_parent(lower_dentry);
if (IS_ERR(lower_parent_dentry)) {
err = PTR_ERR(lower_parent_dentry);
goto out_unlock;
}
err = vfs_create(lower_parent_dentry->d_inode, lower_dentry, mode,
want_excl);
if (!err) {
err = PTR_ERR(unionfs_interpose(dentry, dir->i_sb, 0));
if (!err) {
unionfs_copy_attr_times(dir);
fsstack_copy_inode_size(dir,
lower_parent_dentry->d_inode);
/* update no. of links on parent directory */
set_nlink(dir, unionfs_get_nlinks(dir));
}
}
out_unlock:
unlock_dir(lower_parent_dentry);
out:
if (!err) {
unionfs_postcopyup_setmnt(dentry);
unionfs_check_inode(dir);
unionfs_check_dentry(dentry);
}
unionfs_unlock_dentry(dentry);
unionfs_unlock_parent(dentry, parent);
unionfs_read_unlock(dentry->d_sb);
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 *dir,
struct dentry *dentry,
/* XXX: pass flags to lower? */
unsigned int flags_unused)
{
struct dentry *ret, *parent;
int err = 0;
unionfs_read_lock(dentry->d_sb, UNIONFS_SMUTEX_CHILD);
parent = unionfs_lock_parent(dentry, UNIONFS_DMUTEX_PARENT);
/*
* As long as we lock/dget the parent, then can skip validating the
* parent now; we may have to rebuild this dentry on the next
* ->d_revalidate, however.
*/
/* allocate dentry private data. We free it in ->d_release */
err = new_dentry_private_data(dentry, UNIONFS_DMUTEX_CHILD);
if (unlikely(err)) {
ret = ERR_PTR(err);
goto out;
}
ret = unionfs_lookup_full(dentry, parent, INTERPOSE_LOOKUP);
if (!IS_ERR(ret)) {
if (ret)
dentry = ret;
/* lookup_full can return multiple positive dentries */
if (dentry->d_inode && !S_ISDIR(dentry->d_inode->i_mode)) {
BUG_ON(dbstart(dentry) < 0);
unionfs_postcopyup_release(dentry);
}
unionfs_copy_attr_times(dentry->d_inode);
}
unionfs_check_inode(dir);
if (!IS_ERR(ret))
unionfs_check_dentry(dentry);
unionfs_check_dentry(parent);
unionfs_unlock_dentry(dentry); /* locked in new_dentry_private data */
out:
unionfs_unlock_parent(dentry, parent);
unionfs_read_unlock(dentry->d_sb);
return ret;
}
/*
* 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)
*/
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);
}
/*
* 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 inode *lower_inode = NULL;
int err = 0;
int bindex, bstart, bend;
int is_file;
const int write_mask = (mask & MAY_WRITE) && !(mask & MAY_READ);
struct inode *inode_grabbed;
inode_grabbed = igrab(inode);
is_file = !S_ISDIR(inode->i_mode);
if (!UNIONFS_I(inode)->lower_inodes) {
if (is_file) /* dirs can be unlinked but chdir'ed to */
err = -ESTALE; /* force revalidate */
goto out;
}
bstart = ibstart(inode);
bend = ibend(inode);
if (unlikely(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.
*/
if (is_file) /* dirs can be unlinked but chdir'ed to */
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 check basic permissions, but we ignore any conditions
* such as readonly file systems or branches marked as
* readonly, because those conditions should lead to a
* copyup taking place later on. However, if user never had
* access to the file, then no copyup could ever take place.
*/
err = __inode_permission(lower_inode, mask);
if (err && err != -EACCES && err != EPERM && bindex > 0) {
umode_t mode = lower_inode->i_mode;
if ((is_robranch_super(inode->i_sb, bindex) ||
__is_rdonly(lower_inode)) &&
(S_ISREG(mode) || S_ISDIR(mode) || S_ISLNK(mode)))
err = 0;
if (IS_COPYUP_ERR(err))
err = 0;
}
/*
* NFS HACK: NFSv2/3 return EACCES on readonly-exported,
* locally readonly-mounted file systems, instead of EROFS
* like other file systems do. So we have no choice here
* but to intercept this and ignore it for NFS branches
* marked readonly. Specifically, we avoid using NFS's own
* "broken" ->permission method, and rely on
* generic_permission() to do basic checking for us.
*/
if (err && err == -EACCES &&
is_robranch_super(inode->i_sb, bindex) &&
lower_inode->i_sb->s_magic == NFS_SUPER_MAGIC)
err = generic_permission(lower_inode, mask);
/*
* 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);
iput(inode_grabbed);
return err;
}
static int unionfs_mknod(struct inode *dir, struct dentry *dentry, umode_t mode,
dev_t dev)
{
int err = 0;
struct dentry *lower_dentry = NULL;
struct dentry *wh_dentry = NULL;
struct dentry *lower_parent_dentry = NULL;
struct dentry *parent;
char *name = NULL;
int valid = 0;
unionfs_read_lock(dentry->d_sb, UNIONFS_SMUTEX_CHILD);
parent = unionfs_lock_parent(dentry, UNIONFS_DMUTEX_PARENT);
unionfs_lock_dentry(dentry, UNIONFS_DMUTEX_CHILD);
valid = __unionfs_d_revalidate(dentry, parent, false, 0);
if (unlikely(!valid)) {
err = -ESTALE;
goto out;
}
/*
* 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);
lower_dentry = find_writeable_branch(dir, dentry);
if (IS_ERR(lower_dentry)) {
err = PTR_ERR(lower_dentry);
goto out;
}
lower_parent_dentry = lock_parent(lower_dentry);
if (IS_ERR(lower_parent_dentry)) {
err = PTR_ERR(lower_parent_dentry);
goto out_unlock;
}
err = vfs_mknod(lower_parent_dentry->d_inode, lower_dentry, mode, dev);
if (!err) {
err = PTR_ERR(unionfs_interpose(dentry, dir->i_sb, 0));
if (!err) {
unionfs_copy_attr_times(dir);
fsstack_copy_inode_size(dir,
lower_parent_dentry->d_inode);
/* update no. of links on parent directory */
set_nlink(dir, unionfs_get_nlinks(dir));
}
}
out_unlock:
unlock_dir(lower_parent_dentry);
out:
dput(wh_dentry);
kfree(name);
if (!err) {
unionfs_postcopyup_setmnt(dentry);
unionfs_check_inode(dir);
unionfs_check_dentry(dentry);
}
unionfs_unlock_dentry(dentry);
unionfs_unlock_parent(dentry, parent);
unionfs_read_unlock(dentry->d_sb);
return err;
}
static int unionfs_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode)
{
int err = 0;
struct dentry *lower_dentry = NULL;
struct dentry *lower_parent_dentry = NULL;
struct dentry *parent;
int bindex = 0, bstart;
char *name = NULL;
int valid;
unionfs_read_lock(dentry->d_sb, UNIONFS_SMUTEX_CHILD);
parent = unionfs_lock_parent(dentry, UNIONFS_DMUTEX_PARENT);
unionfs_lock_dentry(dentry, UNIONFS_DMUTEX_CHILD);
valid = __unionfs_d_revalidate(dentry, parent, false, 0);
if (unlikely(!valid)) {
err = -ESTALE; /* same as what real_lookup does */
goto out;
}
bstart = dbstart(dentry);
lower_dentry = unionfs_lower_dentry(dentry);
/* check for a whiteout in new dentry branch, and delete it */
err = check_unlink_whiteout(dentry, lower_dentry, bstart);
if (err > 0) /* whiteout found and removed successfully */
err = 0;
if (err) {
/* exit if the error returned was NOT -EROFS */
if (!IS_COPYUP_ERR(err))
goto out;
bstart--;
}
/* check if copyup's needed, and mkdir */
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(dir, dentry,
dentry->d_name.name,
bindex);
if (!lower_dentry || IS_ERR(lower_dentry)) {
printk(KERN_ERR "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++) {
/* XXX: use path_put_lowers? */
if (unionfs_lower_dentry_idx(dentry, i)) {
dput(unionfs_lower_dentry_idx(dentry, i));
unionfs_set_lower_dentry_idx(dentry, i, NULL);
}
}
dbend(dentry) = bindex;
/*
* Only INTERPOSE_LOOKUP can return a value other than 0 on
* err.
*/
err = PTR_ERR(unionfs_interpose(dentry, dir->i_sb, 0));
if (!err) {
unionfs_copy_attr_times(dir);
fsstack_copy_inode_size(dir,
lower_parent_dentry->d_inode);
/* update number of links on parent directory */
set_nlink(dir, unionfs_get_nlinks(dir));
}
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_postcopyup_setmnt(dentry);
}
unionfs_check_inode(dir);
unionfs_check_dentry(dentry);
unionfs_unlock_dentry(dentry);
unionfs_unlock_parent(dentry, parent);
unionfs_read_unlock(dentry->d_sb);
return err;
}
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 *old_parent, *new_parent;
char *name = NULL;
bool valid;
unionfs_read_lock(old_dentry->d_sb, UNIONFS_SMUTEX_CHILD);
old_parent = dget_parent(old_dentry);
new_parent = dget_parent(new_dentry);
unionfs_double_lock_parents(old_parent, new_parent);
unionfs_double_lock_dentry(old_dentry, new_dentry);
valid = __unionfs_d_revalidate(old_dentry, old_parent, false, 0);
if (unlikely(!valid)) {
err = -ESTALE;
goto out;
}
if (new_dentry->d_inode) {
valid = __unionfs_d_revalidate(new_dentry, new_parent, false, 0);
if (unlikely(!valid)) {
err = -ESTALE;
goto out;
}
}
lower_new_dentry = unionfs_lower_dentry(new_dentry);
/* check for a whiteout in new dentry branch, and delete it */
err = check_unlink_whiteout(new_dentry, lower_new_dentry,
dbstart(new_dentry));
if (err > 0) { /* whiteout found and removed successfully */
lower_dir_dentry = dget_parent(lower_new_dentry);
fsstack_copy_attr_times(dir, lower_dir_dentry->d_inode);
dput(lower_dir_dentry);
set_nlink(dir, unionfs_get_nlinks(dir));
err = 0;
}
if (err)
goto out;
/* check if parent hierachy is needed, then link in same branch */
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);
err = is_robranch(old_dentry);
if (!err) {
/* see Documentation/filesystems/unionfs/issues.txt */
lockdep_off();
err = vfs_link(lower_old_dentry, lower_dir_dentry->d_inode,
lower_new_dentry);
lockdep_on();
}
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_parent->d_inode,
old_dentry, old_bstart,
bindex, old_dentry->d_name.name,
old_dentry->d_name.len, NULL,
i_size_read(old_dentry->d_inode));
if (err)
continue;
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);
/* see Documentation/filesystems/unionfs/issues.txt */
lockdep_off();
/* do vfs_link */
err = vfs_link(lower_old_dentry,
lower_dir_dentry->d_inode,
lower_new_dentry);
lockdep_on();
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_add(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 */
set_nlink(old_dentry->d_inode,
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_postcopyup_setmnt(new_dentry);
unionfs_check_inode(dir);
unionfs_check_dentry(new_dentry);
unionfs_check_dentry(old_dentry);
unionfs_double_unlock_dentry(old_dentry, new_dentry);
unionfs_double_unlock_parents(old_parent, new_parent);
dput(new_parent);
dput(old_parent);
unionfs_read_unlock(old_dentry->d_sb);
return err;
}
/*
* 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);
err = is_robranch_super(dir->i_sb, bindex);
if (err) {
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 (unlikely(!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 = dget_parent(child_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 (unlikely(!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);
dput(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) {
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.
*/
fsstack_copy_attr_times(parent_dentry->d_inode,
lower_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)
dput(path[count--]);
kfree(path);
return 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;
err = is_robranch_super(sb, new_bindex);
if (err)
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 (unlikely(!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. */
err = copyup_permissions(sb, old_lower_dentry, new_lower_dentry);
if (err)
goto out_unlink;
#ifdef CONFIG_UNION_FS_XATTR
/* Selinux uses extended attributes for permissions. */
err = copyup_xattrs(old_lower_dentry, new_lower_dentry);
if (err)
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 not a file, then 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_ISREG(old_lower_dentry->d_inode->i_mode))
dput(old_lower_dentry);
kfree(symbuf);
if (err) {
/*
* if directory creation succeeded, but inode copyup failed,
* then purge new dentries.
*/
if (dbstart(dentry) < old_bstart &&
ibstart(dentry->d_inode) > dbstart(dentry))
__clear(dentry, NULL, old_bstart, old_bend,
unionfs_lower_dentry(dentry), dbstart(dentry));
goto out;
}
if (!S_ISDIR(dentry->d_inode->i_mode)) {
unionfs_postcopyup_release(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_postcopyup_setmnt(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;
}
int unionfs_open(struct inode *inode, struct file *file)
{
int err = 0;
struct file *lower_file = NULL;
struct dentry *dentry = file->f_path.dentry;
struct dentry *parent;
int bindex = 0, bstart = 0, bend = 0;
int size;
int valid = 0;
unionfs_read_lock(inode->i_sb, UNIONFS_SMUTEX_PARENT);
parent = unionfs_lock_parent(dentry, UNIONFS_DMUTEX_PARENT);
unionfs_lock_dentry(dentry, UNIONFS_DMUTEX_CHILD);
/* don't open unhashed/deleted files */
if (d_deleted(dentry)) {
err = -ENOENT;
goto out_nofree;
}
/* XXX: should I change 'false' below to the 'willwrite' flag? */
valid = __unionfs_d_revalidate(dentry, parent, false);
if (unlikely(!valid)) {
err = -ESTALE;
goto out_nofree;
}
file->private_data =
kzalloc(sizeof(struct unionfs_file_info), GFP_KERNEL);
if (unlikely(!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 (unlikely(!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 (unlikely(!UNIONFS_F(file)->saved_branch_ids)) {
err = -ENOMEM;
goto out;
}
bstart = fbstart(file) = dbstart(dentry);
bend = fbend(file) = dbend(dentry);
/*
* 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, parent); /* open a file */
/* freeing the allocated resources, and fput the opened files */
if (err) {
for (bindex = bstart; bindex <= bend; bindex++) {
lower_file = unionfs_lower_file_idx(file, bindex);
if (!lower_file)
continue;
branchput(dentry->d_sb, bindex);
/* fput calls dput for lower_dentry */
fput(lower_file);
}
}
out:
if (err) {
kfree(UNIONFS_F(file)->lower_files);
kfree(UNIONFS_F(file)->saved_branch_ids);
kfree(UNIONFS_F(file));
}
out_nofree:
if (!err) {
unionfs_postcopyup_setmnt(dentry);
unionfs_copy_attr_times(inode);
unionfs_check_file(file);
unionfs_check_inode(inode);
}
unionfs_unlock_dentry(dentry);
unionfs_unlock_parent(dentry, parent);
unionfs_read_unlock(inode->i_sb);
return err;
}
static int unionfs_mmap(struct file *file, struct vm_area_struct *vma)
{
int err = 0;
bool willwrite;
struct file *lower_file;
struct dentry *dentry = file->f_path.dentry;
struct dentry *parent;
struct vm_operations_struct *saved_vm_ops = NULL;
unionfs_read_lock(dentry->d_sb, UNIONFS_SMUTEX_PARENT);
parent = unionfs_lock_parent(dentry, UNIONFS_DMUTEX_PARENT);
unionfs_lock_dentry(dentry, UNIONFS_DMUTEX_CHILD);
/* This might be deferred to mmap's writepage */
willwrite = ((vma->vm_flags | VM_SHARED | VM_WRITE) == vma->vm_flags);
err = unionfs_file_revalidate(file, parent, willwrite);
if (unlikely(err))
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(KERN_ERR "unionfs: branch %d file system does not "
"support writeable mmap\n", fbstart(file));
goto out;
}
/*
* find and save lower vm_ops.
*
* XXX: the VFS should have a cleaner way of finding the lower vm_ops
*/
if (!UNIONFS_F(file)->lower_vm_ops) {
err = lower_file->f_op->mmap(lower_file, vma);
if (err) {
printk(KERN_ERR "unionfs: lower mmap failed %d\n", err);
goto out;
}
saved_vm_ops = vma->vm_ops;
err = do_munmap(current->mm, vma->vm_start,
vma->vm_end - vma->vm_start);
if (err) {
printk(KERN_ERR "unionfs: do_munmap failed %d\n", err);
goto out;
}
}
file->f_mapping->a_ops = &unionfs_dummy_aops;
err = generic_file_mmap(file, vma);
file->f_mapping->a_ops = &unionfs_aops;
if (err) {
printk(KERN_ERR "unionfs: generic_file_mmap failed %d\n", err);
goto out;
}
vma->vm_ops = &unionfs_vm_ops;
if (!UNIONFS_F(file)->lower_vm_ops)
UNIONFS_F(file)->lower_vm_ops = saved_vm_ops;
out:
if (!err) {
/* copyup could cause parent dir times to change */
unionfs_copy_attr_times(parent->d_inode);
unionfs_check_file(file);
}
unionfs_unlock_dentry(dentry);
unionfs_unlock_parent(dentry, parent);
unionfs_read_unlock(dentry->d_sb);
return err;
}
/*
* The locking rules in unionfs_rename are complex. We could use a simpler
* superblock-level name-space lock for renames and copy-ups.
*/
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;
struct dentry *old_parent, *new_parent;
int valid = true;
unionfs_read_lock(old_dentry->d_sb, UNIONFS_SMUTEX_CHILD);
old_parent = dget_parent(old_dentry);
new_parent = dget_parent(new_dentry);
/* un/lock parent dentries only if they differ from old/new_dentry */
if (old_parent != old_dentry &&
old_parent != new_dentry)
unionfs_lock_dentry(old_parent, UNIONFS_DMUTEX_REVAL_PARENT);
if (new_parent != old_dentry &&
new_parent != new_dentry &&
new_parent != old_parent)
unionfs_lock_dentry(new_parent, UNIONFS_DMUTEX_REVAL_CHILD);
unionfs_double_lock_dentry(old_dentry, new_dentry);
valid = __unionfs_d_revalidate(old_dentry, old_parent, false);
if (!valid) {
err = -ESTALE;
goto out;
}
if (!d_deleted(new_dentry) && new_dentry->d_inode) {
valid = __unionfs_d_revalidate(new_dentry, new_parent, false);
if (!valid) {
err = -ESTALE;
goto out;
}
}
if (!S_ISDIR(old_dentry->d_inode->i_mode))
err = unionfs_partial_lookup(old_dentry, old_parent);
else
err = may_rename_dir(old_dentry, old_parent);
if (err)
goto out;
err = unionfs_partial_lookup(new_dentry, new_parent);
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 = find_first_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 = NULL;
/* check if this unionfs directory is empty or not */
err = check_empty(new_dentry, new_parent, &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, old_parent,
new_dir, new_dentry, new_parent);
if (err)
goto out;
/*
* 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_postcopyup_release(old_dentry);
if (new_dentry->d_inode && !S_ISDIR(new_dentry->d_inode->i_mode)) {
unionfs_postcopyup_release(new_dentry);
unionfs_postcopyup_setmnt(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);
igrab(inode);
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_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);
out:
if (err) /* clear the new_dentry stuff created */
d_drop(new_dentry);
unionfs_double_unlock_dentry(old_dentry, new_dentry);
if (new_parent != old_dentry &&
new_parent != new_dentry &&
new_parent != old_parent)
unionfs_unlock_dentry(new_parent);
if (old_parent != old_dentry &&
old_parent != new_dentry)
unionfs_unlock_dentry(old_parent);
dput(new_parent);
dput(old_parent);
unionfs_read_unlock(old_dentry->d_sb);
return err;
}