/*
* BKL held by caller.
* dentry->d_inode->i_mutex locked
*/
ssize_t unionfs_listxattr(struct dentry *dentry, char *list, size_t size)
{
struct dentry *lower_dentry = NULL;
struct dentry *parent;
int err = -EOPNOTSUPP;
char *encoded_list = NULL;
bool 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);
if (unlikely(!valid)) {
err = -ESTALE;
goto out;
}
lower_dentry = unionfs_lower_dentry(dentry);
encoded_list = list;
err = vfs_listxattr(lower_dentry, encoded_list, size);
out:
unionfs_check_dentry(dentry);
unionfs_unlock_dentry(dentry);
unionfs_unlock_parent(dentry, parent);
unionfs_read_unlock(dentry->d_sb);
return err;
}
static ssize_t unionfs_write(struct file *file, const char __user *buf,
size_t count, loff_t *ppos)
{
int err = 0;
struct file *lower_file;
struct dentry *dentry = file->f_path.dentry;
struct dentry *parent;
unionfs_read_lock(dentry->d_sb, UNIONFS_SMUTEX_PARENT);
parent = unionfs_lock_parent(dentry, UNIONFS_DMUTEX_PARENT);
unionfs_lock_dentry(dentry, UNIONFS_DMUTEX_CHILD);
err = unionfs_file_revalidate(file, parent, true);
if (unlikely(err))
goto out;
lower_file = unionfs_lower_file(file);
err = vfs_write(lower_file, buf, count, ppos);
/* update our inode times+sizes upon a successful lower write */
if (err >= 0) {
fsstack_copy_inode_size(dentry->d_inode,
lower_file->f_path.dentry->d_inode);
fsstack_copy_attr_times(dentry->d_inode,
lower_file->f_path.dentry->d_inode);
UNIONFS_F(file)->wrote_to_file = true; /* for delayed copyup */
unionfs_check_file(file);
}
out:
unionfs_unlock_dentry(dentry);
unionfs_unlock_parent(dentry, parent);
unionfs_read_unlock(dentry->d_sb);
return err;
}
/*
* BKL held by caller.
* dentry->d_inode->i_mutex locked
*/
int unionfs_setxattr(struct dentry *dentry, const char *name,
const void *value, size_t size, int flags)
{
struct dentry *lower_dentry = NULL;
struct dentry *parent;
int err = -EOPNOTSUPP;
bool 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);
if (unlikely(!valid)) {
err = -ESTALE;
goto out;
}
lower_dentry = unionfs_lower_dentry(dentry);
err = vfs_setxattr(lower_dentry, (char *) name, (void *) value,
size, flags);
out:
unionfs_check_dentry(dentry);
unionfs_unlock_dentry(dentry);
unionfs_unlock_parent(dentry, parent);
unionfs_read_unlock(dentry->d_sb);
return err;
}
static int unionfs_readlink(struct dentry *dentry, char __user *buf,
int bufsiz)
{
int err;
struct dentry *parent;
unionfs_read_lock(dentry->d_sb, UNIONFS_SMUTEX_CHILD);
parent = unionfs_lock_parent(dentry, UNIONFS_DMUTEX_PARENT);
unionfs_lock_dentry(dentry, UNIONFS_DMUTEX_CHILD);
if (unlikely(!__unionfs_d_revalidate(dentry, parent, false, 0))) {
err = -ESTALE;
goto out;
}
err = __unionfs_readlink(dentry, buf, bufsiz);
out:
unionfs_check_dentry(dentry);
unionfs_unlock_dentry(dentry);
unionfs_unlock_parent(dentry, parent);
unionfs_read_unlock(dentry->d_sb);
return err;
}
static ssize_t unionfs_splice_write(struct pipe_inode_info *pipe,
struct file *file, loff_t *ppos,
size_t len, unsigned int flags)
{
ssize_t err = 0;
struct file *lower_file;
struct dentry *dentry = file->f_path.dentry;
struct dentry *parent;
unionfs_read_lock(dentry->d_sb, UNIONFS_SMUTEX_PARENT);
parent = unionfs_lock_parent(dentry, UNIONFS_DMUTEX_PARENT);
unionfs_lock_dentry(dentry, UNIONFS_DMUTEX_CHILD);
err = unionfs_file_revalidate(file, parent, true);
if (unlikely(err))
goto out;
lower_file = unionfs_lower_file(file);
err = vfs_splice_from(pipe, lower_file, ppos, len, flags);
/* update our inode times+sizes upon a successful lower write */
if (err >= 0) {
fsstack_copy_inode_size(dentry->d_inode,
lower_file->f_path.dentry->d_inode);
fsstack_copy_attr_times(dentry->d_inode,
lower_file->f_path.dentry->d_inode);
unionfs_check_file(file);
}
out:
unionfs_unlock_dentry(dentry);
unionfs_unlock_parent(dentry, parent);
unionfs_read_unlock(dentry->d_sb);
return err;
}
static ssize_t unionfs_read(struct file *file, char __user *buf,
size_t count, loff_t *ppos)
{
int err;
struct file *lower_file;
struct dentry *dentry = file->f_path.dentry;
struct dentry *parent;
unionfs_read_lock(dentry->d_sb, UNIONFS_SMUTEX_PARENT);
parent = unionfs_lock_parent(dentry, UNIONFS_DMUTEX_PARENT);
unionfs_lock_dentry(dentry, UNIONFS_DMUTEX_CHILD);
err = unionfs_file_revalidate(file, parent, false);
if (unlikely(err))
goto out;
lower_file = unionfs_lower_file(file);
err = vfs_read(lower_file, buf, count, ppos);
/* update our inode atime upon a successful lower read */
if (err >= 0) {
fsstack_copy_attr_atime(dentry->d_inode,
lower_file->f_path.dentry->d_inode);
unionfs_check_file(file);
}
out:
unionfs_unlock_dentry(dentry);
unionfs_unlock_parent(dentry, parent);
unionfs_read_unlock(dentry->d_sb);
return err;
}
/* this @nd *IS* still used */
static void unionfs_put_link(struct dentry *dentry, struct nameidata *nd,
void *cookie)
{
struct dentry *parent;
char *buf;
unionfs_read_lock(dentry->d_sb, UNIONFS_SMUTEX_CHILD);
parent = unionfs_lock_parent(dentry, UNIONFS_DMUTEX_PARENT);
unionfs_lock_dentry(dentry, UNIONFS_DMUTEX_CHILD);
if (unlikely(!__unionfs_d_revalidate(dentry, parent, false)))
printk(KERN_ERR
"unionfs: put_link failed to revalidate dentry\n");
unionfs_check_dentry(dentry);
#if 0
/* XXX: can't run this check b/c this fxn can receive a poisoned 'nd' PTR */
unionfs_check_nd(nd);
#endif
buf = nd_get_link(nd);
if (!IS_ERR(buf))
kfree(buf);
unionfs_unlock_dentry(dentry);
unionfs_unlock_parent(dentry, parent);
unionfs_read_unlock(dentry->d_sb);
}
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;
}
int unionfs_fsync(struct file *file, struct dentry *dentry, int datasync)
{
int bindex, bstart, bend;
struct file *lower_file;
struct dentry *lower_dentry;
struct dentry *parent;
struct inode *lower_inode, *inode;
int err = -EINVAL;
unionfs_read_lock(dentry->d_sb, UNIONFS_SMUTEX_PARENT);
parent = unionfs_lock_parent(dentry, UNIONFS_DMUTEX_PARENT);
unionfs_lock_dentry(dentry, UNIONFS_DMUTEX_CHILD);
err = unionfs_file_revalidate(file, parent, true);
if (unlikely(err))
goto out;
unionfs_check_file(file);
bstart = fbstart(file);
bend = fbend(file);
if (bstart < 0 || bend < 0)
goto out;
inode = dentry->d_inode;
if (unlikely(!inode)) {
printk(KERN_ERR
"unionfs: null lower inode in unionfs_fsync\n");
goto out;
}
for (bindex = bstart; bindex <= bend; bindex++) {
lower_inode = unionfs_lower_inode_idx(inode, bindex);
if (!lower_inode || !lower_inode->i_fop->fsync)
continue;
lower_file = unionfs_lower_file_idx(file, bindex);
lower_dentry = unionfs_lower_dentry_idx(dentry, bindex);
mutex_lock(&lower_inode->i_mutex);
err = lower_inode->i_fop->fsync(lower_file,
lower_dentry,
datasync);
if (!err && bindex == bstart)
fsstack_copy_attr_times(inode, lower_inode);
mutex_unlock(&lower_inode->i_mutex);
if (err)
goto out;
}
out:
if (!err)
unionfs_check_file(file);
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;
}
static void *unionfs_follow_link(struct dentry *dentry, struct nameidata *nd)
{
char *buf;
int len = PAGE_SIZE, err;
mm_segment_t old_fs;
struct dentry *parent;
unionfs_read_lock(dentry->d_sb, UNIONFS_SMUTEX_CHILD);
parent = unionfs_lock_parent(dentry, UNIONFS_DMUTEX_PARENT);
unionfs_lock_dentry(dentry, UNIONFS_DMUTEX_CHILD);
/* This is freed by the put_link method assuming a successful call. */
buf = kmalloc(len, GFP_KERNEL);
if (unlikely(!buf)) {
err = -ENOMEM;
goto out;
}
/* read the symlink, and then we will follow it */
old_fs = get_fs();
set_fs(KERNEL_DS);
err = __unionfs_readlink(dentry, buf, len);
set_fs(old_fs);
if (err < 0) {
kfree(buf);
buf = NULL;
goto out;
}
buf[err] = 0;
nd_set_link(nd, buf);
err = 0;
out:
if (err >= 0) {
unionfs_check_nd(nd);
unionfs_check_dentry(dentry);
}
unionfs_unlock_dentry(dentry);
unionfs_unlock_parent(dentry, parent);
unionfs_read_unlock(dentry->d_sb);
return ERR_PTR(err);
}
/* this @nd *IS* still used */
static void unionfs_put_link(struct dentry *dentry, struct nameidata *nd,
void *cookie)
{
struct dentry *parent;
unionfs_read_lock(dentry->d_sb, UNIONFS_SMUTEX_CHILD);
parent = unionfs_lock_parent(dentry, UNIONFS_DMUTEX_PARENT);
unionfs_lock_dentry(dentry, UNIONFS_DMUTEX_CHILD);
if (unlikely(!__unionfs_d_revalidate(dentry, parent, false)))
printk(KERN_ERR
"unionfs: put_link failed to revalidate dentry\n");
unionfs_check_dentry(dentry);
unionfs_check_nd(nd);
kfree(nd_get_link(nd));
unionfs_unlock_dentry(dentry);
unionfs_unlock_parent(dentry, parent);
unionfs_read_unlock(dentry->d_sb);
}
long unionfs_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
{
long err;
struct dentry *dentry = file->f_path.dentry;
struct dentry *parent;
unionfs_read_lock(dentry->d_sb, UNIONFS_SMUTEX_PARENT);
parent = unionfs_lock_parent(dentry, UNIONFS_DMUTEX_PARENT);
unionfs_lock_dentry(dentry, UNIONFS_DMUTEX_CHILD);
err = unionfs_file_revalidate(file, parent, true);
if (unlikely(err))
goto out;
/* check if asked for local commands */
switch (cmd) {
case UNIONFS_IOCTL_INCGEN:
/* Increment the superblock generation count */
pr_info("unionfs: incgen ioctl deprecated; "
"use \"-o remount,incgen\"\n");
err = -ENOSYS;
break;
case UNIONFS_IOCTL_QUERYFILE:
/* Return list of branches containing the given file */
err = unionfs_ioctl_queryfile(file, parent, cmd, arg);
break;
default:
/* pass the ioctl down */
err = do_ioctl(file, cmd, arg);
break;
}
out:
unionfs_check_file(file);
unionfs_unlock_dentry(dentry);
unionfs_unlock_parent(dentry, parent);
unionfs_read_unlock(dentry->d_sb);
return err;
}
int unionfs_flush(struct file *file, fl_owner_t id)
{
int err = 0;
struct file *lower_file = NULL;
struct dentry *dentry = file->f_path.dentry;
struct dentry *parent;
int bindex, bstart, bend;
unionfs_read_lock(dentry->d_sb, UNIONFS_SMUTEX_PARENT);
parent = unionfs_lock_parent(dentry, UNIONFS_DMUTEX_PARENT);
unionfs_lock_dentry(dentry, UNIONFS_DMUTEX_CHILD);
err = unionfs_file_revalidate(file, parent,
UNIONFS_F(file)->wrote_to_file);
if (unlikely(err))
goto out;
unionfs_check_file(file);
bstart = fbstart(file);
bend = fbend(file);
for (bindex = bstart; bindex <= bend; bindex++) {
lower_file = unionfs_lower_file_idx(file, bindex);
if (lower_file && lower_file->f_op &&
lower_file->f_op->flush) {
err = lower_file->f_op->flush(lower_file, id);
if (err)
goto out;
}
}
out:
if (!err)
unionfs_check_file(file);
unionfs_unlock_dentry(dentry);
unionfs_unlock_parent(dentry, parent);
unionfs_read_unlock(dentry->d_sb);
return err;
}
static int unionfs_readdir(struct file *file, void *dirent, filldir_t filldir)
{
int err = 0;
struct file *lower_file = NULL;
struct dentry *dentry = file->f_path.dentry;
struct dentry *parent;
struct inode *inode = NULL;
struct unionfs_getdents_callback buf;
struct unionfs_dir_state *uds;
int bend;
loff_t offset;
unionfs_read_lock(dentry->d_sb, UNIONFS_SMUTEX_PARENT);
parent = unionfs_lock_parent(dentry, UNIONFS_DMUTEX_PARENT);
unionfs_lock_dentry(dentry, UNIONFS_DMUTEX_CHILD);
err = unionfs_file_revalidate(file, parent, false);
if (unlikely(err))
goto out;
inode = dentry->d_inode;
uds = UNIONFS_F(file)->rdstate;
if (!uds) {
if (file->f_pos == DIREOF) {
goto out;
} else if (file->f_pos > 0) {
uds = find_rdstate(inode, file->f_pos);
if (unlikely(!uds)) {
err = -ESTALE;
goto out;
}
UNIONFS_F(file)->rdstate = uds;
} else {
init_rdstate(file);
uds = UNIONFS_F(file)->rdstate;
}
}
bend = fbend(file);
while (uds->bindex <= bend) {
lower_file = unionfs_lower_file_idx(file, uds->bindex);
if (!lower_file) {
uds->bindex++;
uds->dirpos = 0;
continue;
}
/* prepare callback buffer */
buf.filldir_called = 0;
buf.filldir_error = 0;
buf.entries_written = 0;
buf.dirent = dirent;
buf.filldir = filldir;
buf.rdstate = uds;
buf.sb = inode->i_sb;
/* Read starting from where we last left off. */
offset = vfs_llseek(lower_file, uds->dirpos, SEEK_SET);
if (offset < 0) {
err = offset;
goto out;
}
err = vfs_readdir(lower_file, unionfs_filldir, &buf);
/* Save the position for when we continue. */
offset = vfs_llseek(lower_file, 0, SEEK_CUR);
if (offset < 0) {
err = offset;
goto out;
}
uds->dirpos = offset;
/* Copy the atime. */
fsstack_copy_attr_atime(inode,
lower_file->f_path.dentry->d_inode);
if (err < 0)
goto out;
if (buf.filldir_error)
break;
if (!buf.entries_written) {
uds->bindex++;
uds->dirpos = 0;
}
}
if (!buf.filldir_error && uds->bindex >= bend) {
/* Save the number of hash entries for next time. */
UNIONFS_I(inode)->hashsize = uds->hashentries;
free_rdstate(uds);
UNIONFS_F(file)->rdstate = NULL;
file->f_pos = DIREOF;
} else {
file->f_pos = rdstate2offset(uds);
}
out:
if (!err)
unionfs_check_file(file);
unionfs_unlock_dentry(dentry);
unionfs_unlock_parent(dentry, parent);
unionfs_read_unlock(dentry->d_sb);
return err;
}
/*
* This is not meant to be a generic repositioning function. If you do
* things that aren't supported, then we return EINVAL.
*
* What is allowed:
* (1) seeking to the same position that you are currently at
* This really has no effect, but returns where you are.
* (2) seeking to the beginning of the file
* This throws out all state, and lets you begin again.
*/
static loff_t unionfs_dir_llseek(struct file *file, loff_t offset, int origin)
{
struct unionfs_dir_state *rdstate;
struct dentry *dentry = file->f_path.dentry;
struct dentry *parent;
loff_t err;
unionfs_read_lock(dentry->d_sb, UNIONFS_SMUTEX_PARENT);
parent = unionfs_lock_parent(dentry, UNIONFS_DMUTEX_PARENT);
unionfs_lock_dentry(dentry, UNIONFS_DMUTEX_CHILD);
err = unionfs_file_revalidate(file, parent, false);
if (unlikely(err))
goto out;
rdstate = UNIONFS_F(file)->rdstate;
/*
* we let users seek to their current position, but not anywhere
* else.
*/
if (!offset) {
switch (origin) {
case SEEK_SET:
if (rdstate) {
free_rdstate(rdstate);
UNIONFS_F(file)->rdstate = NULL;
}
init_rdstate(file);
err = 0;
break;
case SEEK_CUR:
err = file->f_pos;
break;
case SEEK_END:
/* Unsupported, because we would break everything. */
err = -EINVAL;
break;
}
} else {
switch (origin) {
case SEEK_SET:
if (rdstate) {
if (offset == rdstate2offset(rdstate))
err = offset;
else if (file->f_pos == DIREOF)
err = DIREOF;
else
err = -EINVAL;
} else {
struct inode *inode;
inode = dentry->d_inode;
rdstate = find_rdstate(inode, offset);
if (rdstate) {
UNIONFS_F(file)->rdstate = rdstate;
err = rdstate->offset;
} else {
err = -EINVAL;
}
}
break;
case SEEK_CUR:
case SEEK_END:
/* Unsupported, because we would break everything. */
err = -EINVAL;
break;
}
}
out:
if (!err)
unionfs_check_file(file);
unionfs_unlock_dentry(dentry);
unionfs_unlock_parent(dentry, parent);
unionfs_read_unlock(dentry->d_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;
}
static int unionfs_setattr(struct dentry *dentry, struct iattr *ia)
{
int err = 0;
struct dentry *lower_dentry;
struct dentry *parent;
struct inode *inode;
struct inode *lower_inode;
int bstart, bend, bindex;
loff_t size;
struct iattr lower_ia;
/* check if user has permission to change inode */
err = inode_change_ok(dentry->d_inode, ia);
if (err)
goto out_err;
unionfs_read_lock(dentry->d_sb, UNIONFS_SMUTEX_CHILD);
parent = unionfs_lock_parent(dentry, UNIONFS_DMUTEX_PARENT);
unionfs_lock_dentry(dentry, UNIONFS_DMUTEX_CHILD);
if (unlikely(!__unionfs_d_revalidate(dentry, parent, false, 0))) {
err = -ESTALE;
goto out;
}
bstart = dbstart(dentry);
bend = dbend(dentry);
inode = dentry->d_inode;
/*
* mode change is for clearing setuid/setgid. Allow lower filesystem
* to reinterpret it in its own way.
*/
if (ia->ia_valid & (ATTR_KILL_SUID | ATTR_KILL_SGID))
ia->ia_valid &= ~ATTR_MODE;
lower_dentry = unionfs_lower_dentry(dentry);
if (!lower_dentry) { /* should never happen after above revalidate */
err = -EINVAL;
goto out;
}
/*
* Get the lower inode directly from lower dentry, in case ibstart
* is -1 (which happens when the file is open but unlinked.
*/
lower_inode = lower_dentry->d_inode;
/* check if user has permission to change lower inode */
err = inode_change_ok(lower_inode, ia);
if (err)
goto out;
/* copyup if the file is on a read only branch */
if (is_robranch_super(dentry->d_sb, bstart)
|| __is_rdonly(lower_inode)) {
/* check if we have a branch to copy up to */
if (bstart <= 0) {
err = -EACCES;
goto out;
}
if (ia->ia_valid & ATTR_SIZE)
size = ia->ia_size;
else
size = i_size_read(inode);
/* copyup to next available branch */
for (bindex = bstart - 1; bindex >= 0; bindex--) {
err = copyup_dentry(parent->d_inode,
dentry, bstart, bindex,
dentry->d_name.name,
dentry->d_name.len,
NULL, size);
if (!err)
break;
}
if (err)
goto out;
/* get updated lower_dentry/inode after copyup */
lower_dentry = unionfs_lower_dentry(dentry);
lower_inode = unionfs_lower_inode(inode);
/*
* check for whiteouts in writeable branch, and remove them
* if necessary.
*/
if (lower_dentry) {
err = check_unlink_whiteout(dentry, lower_dentry,
bindex);
if (err > 0) /* ignore if whiteout found and removed */
err = 0;
}
}
/*
* If shrinking, first truncate upper level to cancel writing dirty
* pages beyond the new eof; and also if its' maxbytes is more
* limiting (fail with -EFBIG before making any change to the lower
* level). There is no need to vmtruncate the upper level
* afterwards in the other cases: we fsstack_copy_inode_size from
* the lower level.
*/
if (ia->ia_valid & ATTR_SIZE) {
err = inode_newsize_ok(inode, ia->ia_size);
if (err)
goto out;
truncate_setsize(inode, ia->ia_size);
}
/* notify the (possibly copied-up) lower inode */
/*
* Note: we use lower_dentry->d_inode, because lower_inode may be
* unlinked (no inode->i_sb and i_ino==0. This happens if someone
* tries to open(), unlink(), then ftruncate() a file.
*/
/* prepare our own lower struct iattr (with our own lower file) */
memcpy(&lower_ia, ia, sizeof(lower_ia));
if (ia->ia_valid & ATTR_FILE) {
lower_ia.ia_file = unionfs_lower_file(ia->ia_file);
BUG_ON(!lower_ia.ia_file); // XXX?
}
mutex_lock(&lower_dentry->d_inode->i_mutex);
err = notify_change(lower_dentry, &lower_ia);
mutex_unlock(&lower_dentry->d_inode->i_mutex);
if (err)
goto out;
/* get attributes from the first lower inode */
if (ibstart(inode) >= 0)
unionfs_copy_attr_all(inode, lower_inode);
/*
* unionfs_copy_attr_all will copy the lower times to our inode if
* the lower ones are newer (useful for cache coherency). However,
* ->setattr is the only place in which we may have to copy the
* lower inode times absolutely, to support utimes(2).
*/
if (ia->ia_valid & ATTR_MTIME_SET)
inode->i_mtime = lower_inode->i_mtime;
if (ia->ia_valid & ATTR_CTIME)
inode->i_ctime = lower_inode->i_ctime;
if (ia->ia_valid & ATTR_ATIME_SET)
inode->i_atime = lower_inode->i_atime;
fsstack_copy_inode_size(inode, lower_inode);
out:
if (!err)
unionfs_check_dentry(dentry);
unionfs_unlock_dentry(dentry);
unionfs_unlock_parent(dentry, parent);
unionfs_read_unlock(dentry->d_sb);
out_err:
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_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;
}
/*
* release all lower object references & free the file info structure
*
* No need to grab sb info's rwsem.
*/
int unionfs_file_release(struct inode *inode, struct file *file)
{
struct file *lower_file = NULL;
struct unionfs_file_info *fileinfo;
struct unionfs_inode_info *inodeinfo;
struct super_block *sb = inode->i_sb;
struct dentry *dentry = file->f_path.dentry;
struct dentry *parent;
int bindex, bstart, bend;
int fgen, err = 0;
/*
* Since mm/memory.c:might_fault() (under PROVE_LOCKING) was
* modified in 2.6.29-rc1 to call might_lock_read on mmap_sem, this
* has been causing false positives in file system stacking layers.
* In particular, our ->mmap is called after sys_mmap2 already holds
* mmap_sem, then we lock our own mutexes; but earlier, it's
* possible for lockdep to have locked our mutexes first, and then
* we call a lower ->readdir which could call might_fault. The
* different ordering of the locks is what lockdep complains about
* -- unnecessarily. Therefore, we have no choice but to tell
* lockdep to temporarily turn off lockdep here. Note: the comments
* inside might_sleep also suggest that it would have been
* nicer to only annotate paths that needs that might_lock_read.
*/
lockdep_off();
unionfs_read_lock(sb, UNIONFS_SMUTEX_PARENT);
parent = unionfs_lock_parent(dentry, UNIONFS_DMUTEX_PARENT);
unionfs_lock_dentry(dentry, UNIONFS_DMUTEX_CHILD);
/*
* We try to revalidate, but the VFS ignores return return values
* from file->release, so we must always try to succeed here,
* including to do the kfree and dput below. So if revalidation
* failed, all we can do is print some message and keep going.
*/
err = unionfs_file_revalidate(file, parent,
UNIONFS_F(file)->wrote_to_file);
if (!err)
unionfs_check_file(file);
fileinfo = UNIONFS_F(file);
BUG_ON(file->f_path.dentry->d_inode != inode);
inodeinfo = UNIONFS_I(inode);
/* fput all the lower files */
fgen = atomic_read(&fileinfo->generation);
bstart = fbstart(file);
bend = fbend(file);
for (bindex = bstart; bindex <= bend; bindex++) {
lower_file = unionfs_lower_file_idx(file, bindex);
if (lower_file) {
unionfs_set_lower_file_idx(file, bindex, NULL);
fput(lower_file);
branchput(sb, bindex);
}
/* if there are no more refs to the dentry, dput it */
if (d_deleted(dentry)) {
dput(unionfs_lower_dentry_idx(dentry, bindex));
unionfs_set_lower_dentry_idx(dentry, bindex, NULL);
}
}
kfree(fileinfo->lower_files);
kfree(fileinfo->saved_branch_ids);
if (fileinfo->rdstate) {
fileinfo->rdstate->access = jiffies;
spin_lock(&inodeinfo->rdlock);
inodeinfo->rdcount++;
list_add_tail(&fileinfo->rdstate->cache,
&inodeinfo->readdircache);
mark_inode_dirty(inode);
spin_unlock(&inodeinfo->rdlock);
fileinfo->rdstate = NULL;
}
kfree(fileinfo);
unionfs_unlock_dentry(dentry);
unionfs_unlock_parent(dentry, parent);
unionfs_read_unlock(sb);
lockdep_on();
return err;
}