/* set lower dentry ptr and update bstart & bend if necessary */
static void __set_dentry(struct dentry *upper, struct dentry *lower,
int bindex)
{
unionfs_set_lower_dentry_idx(upper, bindex, lower);
if (likely(dbstart(upper) > bindex))
dbstart(upper) = bindex;
if (likely(dbend(upper) < bindex))
dbend(upper) = bindex;
}
/*
* return to user-space the branch indices containing the file in question
*
* We use fd_set and therefore we are limited to the number of the branches
* to FD_SETSIZE, which is currently 1024 - plenty for most people
*/
static int unionfs_ioctl_queryfile(struct file *file, struct dentry *parent,
unsigned int cmd, unsigned long arg)
{
int err = 0;
fd_set branchlist;
int bstart = 0, bend = 0, bindex = 0;
int orig_bstart, orig_bend;
struct dentry *dentry, *lower_dentry;
struct vfsmount *mnt;
dentry = file->f_path.dentry;
orig_bstart = dbstart(dentry);
orig_bend = dbend(dentry);
err = unionfs_partial_lookup(dentry, parent);
if (err)
goto out;
bstart = dbstart(dentry);
bend = dbend(dentry);
FD_ZERO(&branchlist);
for (bindex = bstart; bindex <= bend; bindex++) {
lower_dentry = unionfs_lower_dentry_idx(dentry, bindex);
if (!lower_dentry)
continue;
if (likely(lower_dentry->d_inode))
FD_SET(bindex, &branchlist);
/* purge any lower objects after partial_lookup */
if (bindex < orig_bstart || bindex > orig_bend) {
dput(lower_dentry);
unionfs_set_lower_dentry_idx(dentry, bindex, NULL);
iput(unionfs_lower_inode_idx(dentry->d_inode, bindex));
unionfs_set_lower_inode_idx(dentry->d_inode, bindex,
NULL);
mnt = unionfs_lower_mnt_idx(dentry, bindex);
if (!mnt)
continue;
unionfs_mntput(dentry, bindex);
unionfs_set_lower_mnt_idx(dentry, bindex, NULL);
}
}
/* restore original dentry's offsets */
dbstart(dentry) = orig_bstart;
dbend(dentry) = orig_bend;
ibstart(dentry->d_inode) = orig_bstart;
ibend(dentry->d_inode) = orig_bend;
err = copy_to_user((void __user *)arg, &branchlist, sizeof(fd_set));
if (unlikely(err))
err = -EFAULT;
out:
return err < 0 ? err : bend;
}
/*
* dput the lower references for old and new dentry & clear a lower dentry
* pointer
*/
static void __clear(struct dentry *dentry, struct dentry *old_lower_dentry,
int old_bstart, int old_bend,
struct dentry *new_lower_dentry, int new_bindex)
{
/* get rid of the lower dentry and all its traces */
unionfs_set_lower_dentry_idx(dentry, new_bindex, NULL);
dbstart(dentry) = old_bstart;
dbend(dentry) = old_bend;
dput(new_lower_dentry);
dput(old_lower_dentry);
}
/* purge a dentry's lower-branch states (dput/mntput, etc.) */
static void __cleanup_dentry(struct dentry *dentry, int bindex,
int old_bstart, int old_bend)
{
int loop_start;
int loop_end;
int new_bstart = -1;
int new_bend = -1;
int i;
loop_start = min(old_bstart, bindex);
loop_end = max(old_bend, bindex);
/*
* This loop sets the bstart and bend for the new dentry by
* traversing from left to right. It also dputs all negative
* dentries except bindex
*/
for (i = loop_start; i <= loop_end; i++) {
if (!unionfs_lower_dentry_idx(dentry, i))
continue;
if (i == bindex) {
new_bend = i;
if (new_bstart < 0)
new_bstart = i;
continue;
}
if (!unionfs_lower_dentry_idx(dentry, i)->d_inode) {
dput(unionfs_lower_dentry_idx(dentry, i));
unionfs_set_lower_dentry_idx(dentry, i, NULL);
unionfs_mntput(dentry, i);
unionfs_set_lower_mnt_idx(dentry, i, NULL);
} else {
if (new_bstart < 0)
new_bstart = i;
new_bend = i;
}
}
if (new_bstart < 0)
new_bstart = bindex;
if (new_bend < 0)
new_bend = bindex;
dbstart(dentry) = new_bstart;
dbend(dentry) = new_bend;
}
/*
* This is a helper function for rename, used when rename ends up with hosed
* over dentries and we need to revert.
*/
static int unionfs_refresh_lower_dentry(struct dentry *dentry,
struct dentry *parent, int bindex)
{
struct dentry *lower_dentry;
struct dentry *lower_parent;
int err = 0;
verify_locked(dentry);
lower_parent = unionfs_lower_dentry_idx(parent, bindex);
BUG_ON(!S_ISDIR(lower_parent->d_inode->i_mode));
lower_dentry = lookup_one_len(dentry->d_name.name, lower_parent,
dentry->d_name.len);
if (IS_ERR(lower_dentry)) {
err = PTR_ERR(lower_dentry);
goto out;
}
dput(unionfs_lower_dentry_idx(dentry, bindex));
iput(unionfs_lower_inode_idx(dentry->d_inode, bindex));
unionfs_set_lower_inode_idx(dentry->d_inode, bindex, NULL);
if (!lower_dentry->d_inode) {
dput(lower_dentry);
unionfs_set_lower_dentry_idx(dentry, bindex, NULL);
} else {
unionfs_set_lower_dentry_idx(dentry, bindex, lower_dentry);
unionfs_set_lower_inode_idx(dentry->d_inode, bindex,
igrab(lower_dentry->d_inode));
}
out:
return err;
}
static void unionfs_d_release(struct dentry *dentry)
{
int bindex, bstart, bend;
/* There is no reason to lock the dentry, because we have the only
* reference, but the printing functions verify that we have a lock
* on the dentry before calling dbstart, etc.
*/
unionfs_lock_dentry(dentry);
/* this could be a negative dentry, so check first */
if (!UNIONFS_D(dentry)) {
printk(KERN_DEBUG "dentry without private data: %.*s",
dentry->d_name.len, dentry->d_name.name);
goto out;
} else if (dbstart(dentry) < 0) {
/* this is due to a failed lookup */
printk(KERN_DEBUG "dentry without hidden dentries : %.*s",
dentry->d_name.len, dentry->d_name.name);
goto out_free;
}
/* Release all the hidden dentries */
bstart = dbstart(dentry);
bend = dbend(dentry);
for (bindex = bstart; bindex <= bend; bindex++) {
dput(unionfs_lower_dentry_idx(dentry, bindex));
mntput(unionfs_lower_mnt_idx(dentry, bindex));
unionfs_set_lower_dentry_idx(dentry, bindex, NULL);
unionfs_set_lower_mnt_idx(dentry, bindex, NULL);
}
/* free private data (unionfs_dentry_info) here */
kfree(UNIONFS_D(dentry)->lower_paths);
UNIONFS_D(dentry)->lower_paths = NULL;
out_free:
/* No need to unlock it, because it is disappeared. */
free_dentry_private_data(UNIONFS_D(dentry));
dentry->d_fsdata = NULL; /* just to be safe */
out:
return;
}
/*
* scan through the lower dentry objects, and set bstart to reflect the
* starting branch
*/
void update_bstart(struct dentry *dentry)
{
int bindex;
int bstart = dbstart(dentry);
int bend = dbend(dentry);
struct dentry *lower_dentry;
for (bindex = bstart; bindex <= bend; bindex++) {
lower_dentry = unionfs_lower_dentry_idx(dentry, bindex);
if (!lower_dentry)
continue;
if (lower_dentry->d_inode) {
dbstart(dentry) = bindex;
break;
}
dput(lower_dentry);
unionfs_set_lower_dentry_idx(dentry, bindex, NULL);
}
}
/*
* 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;
}
struct dentry *unionfs_lookup_backend(struct dentry *dentry, struct nameidata *nd,
int lookupmode)
{
int err = 0;
struct dentry *hidden_dentry = NULL;
struct dentry *wh_hidden_dentry = NULL;
struct dentry *hidden_dir_dentry = NULL;
struct dentry *parent_dentry = NULL;
int bindex, bstart, bend, bopaque;
int dentry_count = 0; /* Number of positive dentries. */
int first_dentry_offset = -1;
struct dentry *first_hidden_dentry = NULL;
struct vfsmount *first_hidden_mnt = NULL;
int locked_parent = 0;
int locked_child = 0;
int opaque;
char *whname = NULL;
const char *name;
int namelen;
/* We should already have a lock on this dentry in the case of a
* partial lookup, or a revalidation. Otherwise it is returned from
* new_dentry_private_data already locked.
*/
if (lookupmode == INTERPOSE_PARTIAL || lookupmode == INTERPOSE_REVAL ||
lookupmode == INTERPOSE_REVAL_NEG)
verify_locked(dentry);
else {
BUG_ON(UNIONFS_D(dentry) != NULL);
locked_child = 1;
}
if (lookupmode != INTERPOSE_PARTIAL)
if ((err = new_dentry_private_data(dentry)))
goto out;
/* must initialize dentry operations */
dentry->d_op = &unionfs_dops;
parent_dentry = dget_parent(dentry);
/* We never partial lookup the root directory. */
if (parent_dentry != dentry) {
unionfs_lock_dentry(parent_dentry);
locked_parent = 1;
} else {
dput(parent_dentry);
parent_dentry = NULL;
goto out;
}
name = dentry->d_name.name;
namelen = dentry->d_name.len;
/* No dentries should get created for possible whiteout names. */
if (!is_validname(name)) {
err = -EPERM;
goto out_free;
}
/* Now start the actual lookup procedure. */
bstart = dbstart(parent_dentry);
bend = dbend(parent_dentry);
bopaque = dbopaque(parent_dentry);
BUG_ON(bstart < 0);
/* It would be ideal if we could convert partial lookups to only have
* to do this work when they really need to. It could probably improve
* performance quite a bit, and maybe simplify the rest of the code.
*/
if (lookupmode == INTERPOSE_PARTIAL) {
bstart++;
if ((bopaque != -1) && (bopaque < bend))
bend = bopaque;
}
for (bindex = bstart; bindex <= bend; bindex++) {
hidden_dentry = unionfs_lower_dentry_idx(dentry, bindex);
if (lookupmode == INTERPOSE_PARTIAL && hidden_dentry)
continue;
BUG_ON(hidden_dentry != NULL);
hidden_dir_dentry = unionfs_lower_dentry_idx(parent_dentry, bindex);
/* if the parent hidden dentry does not exist skip this */
if (!(hidden_dir_dentry && hidden_dir_dentry->d_inode))
continue;
/* also skip it if the parent isn't a directory. */
if (!S_ISDIR(hidden_dir_dentry->d_inode->i_mode))
continue;
/* Reuse the whiteout name because its value doesn't change. */
if (!whname) {
whname = alloc_whname(name, namelen);
if (IS_ERR(whname)) {
err = PTR_ERR(whname);
goto out_free;
}
}
/* check if whiteout exists in this branch: lookup .wh.foo */
wh_hidden_dentry = lookup_one_len(whname, hidden_dir_dentry,
namelen + UNIONFS_WHLEN);
if (IS_ERR(wh_hidden_dentry)) {
dput(first_hidden_dentry);
mntput(first_hidden_mnt);
err = PTR_ERR(wh_hidden_dentry);
goto out_free;
}
if (wh_hidden_dentry->d_inode) {
/* We found a whiteout so lets give up. */
if (S_ISREG(wh_hidden_dentry->d_inode->i_mode)) {
set_dbend(dentry, bindex);
set_dbopaque(dentry, bindex);
dput(wh_hidden_dentry);
break;
}
err = -EIO;
printk(KERN_NOTICE "EIO: Invalid whiteout entry type"
" %d.\n", wh_hidden_dentry->d_inode->i_mode);
dput(wh_hidden_dentry);
dput(first_hidden_dentry);
mntput(first_hidden_mnt);
goto out_free;
}
dput(wh_hidden_dentry);
wh_hidden_dentry = NULL;
/* Now do regular lookup; lookup foo */
nd->dentry = unionfs_lower_dentry_idx(dentry, bindex);
/* FIXME: fix following line for mount point crossing */
nd->mnt = unionfs_lower_mnt_idx(parent_dentry, bindex);
hidden_dentry = lookup_one_len_nd(name, hidden_dir_dentry,
namelen, nd);
if (IS_ERR(hidden_dentry)) {
dput(first_hidden_dentry);
mntput(first_hidden_mnt);
err = PTR_ERR(hidden_dentry);
goto out_free;
}
/* Store the first negative dentry specially, because if they
* are all negative we need this for future creates.
*/
if (!hidden_dentry->d_inode) {
if (!first_hidden_dentry && (dbstart(dentry) == -1)) {
first_hidden_dentry = hidden_dentry;
/* FIXME: following line needs to be changed
* to allow mountpoint crossing
*/
first_hidden_mnt = mntget(
unionfs_lower_mnt_idx(parent_dentry,
bindex));
first_dentry_offset = bindex;
} else
dput(hidden_dentry);
continue;
}
/* number of positive dentries */
dentry_count++;
/* store underlying dentry */
if (dbstart(dentry) == -1)
set_dbstart(dentry, bindex);
unionfs_set_lower_dentry_idx(dentry, bindex, hidden_dentry);
/* FIXME: the following line needs to get fixed to allow
* mountpoint crossing
*/
unionfs_set_lower_mnt_idx(dentry, bindex,
mntget(unionfs_lower_mnt_idx(parent_dentry, bindex)));
set_dbend(dentry, bindex);
/* update parent directory's atime with the bindex */
fsstack_copy_attr_atime(parent_dentry->d_inode,
hidden_dir_dentry->d_inode);
/* We terminate file lookups here. */
if (!S_ISDIR(hidden_dentry->d_inode->i_mode)) {
if (lookupmode == INTERPOSE_PARTIAL)
continue;
if (dentry_count == 1)
goto out_positive;
/* This can only happen with mixed D-*-F-* */
BUG_ON(!S_ISDIR(unionfs_lower_dentry(dentry)->d_inode->i_mode));
continue;
}
opaque = is_opaque_dir(dentry, bindex);
if (opaque < 0) {
dput(first_hidden_dentry);
mntput(first_hidden_mnt);
err = opaque;
goto out_free;
} else if (opaque) {
set_dbend(dentry, bindex);
set_dbopaque(dentry, bindex);
break;
}
}
if (dentry_count)
goto out_positive;
else
goto out_negative;
out_negative:
if (lookupmode == INTERPOSE_PARTIAL)
goto out;
/* If we've only got negative dentries, then use the leftmost one. */
if (lookupmode == INTERPOSE_REVAL) {
if (dentry->d_inode)
UNIONFS_I(dentry->d_inode)->stale = 1;
goto out;
}
/* This should only happen if we found a whiteout. */
if (first_dentry_offset == -1) {
nd->dentry = dentry;
/* FIXME: fix following line for mount point crossing */
nd->mnt = unionfs_lower_mnt_idx(parent_dentry, bindex);
first_hidden_dentry = lookup_one_len_nd(name, hidden_dir_dentry,
namelen, nd);
first_dentry_offset = bindex;
if (IS_ERR(first_hidden_dentry)) {
err = PTR_ERR(first_hidden_dentry);
goto out;
}
/* FIXME: the following line needs to be changed to allow
* mountpoint crossing
*/
first_hidden_mnt = mntget(unionfs_lower_mnt_idx(dentry, bindex));
}
unionfs_set_lower_dentry_idx(dentry, first_dentry_offset, first_hidden_dentry);
unionfs_set_lower_mnt_idx(dentry, first_dentry_offset, first_hidden_mnt);
set_dbstart(dentry, first_dentry_offset);
set_dbend(dentry, first_dentry_offset);
if (lookupmode == INTERPOSE_REVAL_NEG)
BUG_ON(dentry->d_inode != NULL);
else
d_add(dentry, NULL);
goto out;
/* This part of the code is for positive dentries. */
out_positive:
BUG_ON(dentry_count <= 0);
/* If we're holding onto the first negative dentry & corresponding
* vfsmount - throw it out.
*/
dput(first_hidden_dentry);
mntput(first_hidden_mnt);
/* Partial lookups need to reinterpose, or throw away older negs. */
if (lookupmode == INTERPOSE_PARTIAL) {
if (dentry->d_inode) {
unionfs_reinterpose(dentry);
goto out;
}
/* This somehow turned positive, so it is as if we had a
* negative revalidation.
*/
lookupmode = INTERPOSE_REVAL_NEG;
update_bstart(dentry);
bstart = dbstart(dentry);
bend = dbend(dentry);
}
err = unionfs_interpose(dentry, dentry->d_sb, lookupmode);
if (err)
goto out_drop;
goto out;
out_drop:
d_drop(dentry);
out_free:
/* should dput all the underlying dentries on error condition */
bstart = dbstart(dentry);
if (bstart >= 0) {
bend = dbend(dentry);
for (bindex = bstart; bindex <= bend; bindex++) {
dput(unionfs_lower_dentry_idx(dentry, bindex));
mntput(unionfs_lower_mnt_idx(dentry, bindex));
}
}
kfree(UNIONFS_D(dentry)->lower_paths);
UNIONFS_D(dentry)->lower_paths = NULL;
set_dbstart(dentry, -1);
set_dbend(dentry, -1);
out:
if (!err && UNIONFS_D(dentry)) {
BUG_ON(dbend(dentry) > UNIONFS_D(dentry)->bcount);
BUG_ON(dbend(dentry) > sbmax(dentry->d_sb));
BUG_ON(dbstart(dentry) < 0);
}
kfree(whname);
if (locked_parent)
unionfs_unlock_dentry(parent_dentry);
dput(parent_dentry);
if (locked_child)
unionfs_unlock_dentry(dentry);
return ERR_PTR(err);
}
/*
* Main rename code. This is sufficiently complex, that it's documented in
* Documentation/filesystems/unionfs/rename.txt. This routine calls
* __unionfs_rename() above to perform some of the work.
*/
static int do_unionfs_rename(struct inode *old_dir,
struct dentry *old_dentry,
struct dentry *old_parent,
struct inode *new_dir,
struct dentry *new_dentry,
struct dentry *new_parent)
{
int err = 0;
int bindex, bwh_old;
int old_bstart, old_bend;
int new_bstart, new_bend;
int do_copyup = -1;
int local_err = 0;
int eio = 0;
int revert = 0;
old_bstart = dbstart(old_dentry);
bwh_old = old_bstart;
old_bend = dbend(old_dentry);
new_bstart = dbstart(new_dentry);
new_bend = dbend(new_dentry);
/* Rename source to destination. */
err = __unionfs_rename(old_dir, old_dentry, old_parent,
new_dir, new_dentry, new_parent,
old_bstart);
if (err) {
if (!IS_COPYUP_ERR(err))
goto out;
do_copyup = old_bstart - 1;
} else {
revert = 1;
}
/*
* Unlink all instances of destination that exist to the left of
* bstart of source. On error, revert back, goto out.
*/
for (bindex = old_bstart - 1; bindex >= new_bstart; bindex--) {
struct dentry *unlink_dentry;
struct dentry *unlink_dir_dentry;
BUG_ON(bindex < 0);
unlink_dentry = unionfs_lower_dentry_idx(new_dentry, bindex);
if (!unlink_dentry)
continue;
unlink_dir_dentry = lock_parent(unlink_dentry);
err = is_robranch_super(old_dir->i_sb, bindex);
if (!err)
err = vfs_unlink(unlink_dir_dentry->d_inode,
unlink_dentry);
fsstack_copy_attr_times(new_parent->d_inode,
unlink_dir_dentry->d_inode);
/* propagate number of hard-links */
new_parent->d_inode->i_nlink =
unionfs_get_nlinks(new_parent->d_inode);
unlock_dir(unlink_dir_dentry);
if (!err) {
if (bindex != new_bstart) {
dput(unlink_dentry);
unionfs_set_lower_dentry_idx(new_dentry,
bindex, NULL);
}
} else if (IS_COPYUP_ERR(err)) {
do_copyup = bindex - 1;
} else if (revert) {
goto revert;
}
}
if (do_copyup != -1) {
for (bindex = do_copyup; bindex >= 0; bindex--) {
/*
* copyup the file into some left directory, so that
* you can rename it
*/
err = copyup_dentry(old_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 copyup failed, try next branch to the left */
if (err)
continue;
bwh_old = bindex;
err = __unionfs_rename(old_dir, old_dentry, old_parent,
new_dir, new_dentry, new_parent,
bindex);
break;
}
}
/* make it opaque */
if (S_ISDIR(old_dentry->d_inode->i_mode)) {
err = make_dir_opaque(old_dentry, dbstart(old_dentry));
if (err)
goto revert;
}
/*
* Create whiteout for source, only if:
* (1) There is more than one underlying instance of source.
* (2) We did a copy_up
*/
if ((old_bstart != old_bend) || (do_copyup != -1)) {
if (bwh_old < 0) {
printk(KERN_ERR "unionfs: rename error (bwh_old=%d)\n",
bwh_old);
err = -EIO;
goto out;
}
err = create_whiteout(old_dentry, bwh_old);
if (err) {
/* can't fix anything now, so we exit with -EIO */
printk(KERN_ERR "unionfs: can't create a whiteout for "
"%s in rename!\n", old_dentry->d_name.name);
err = -EIO;
}
}
out:
return err;
revert:
/* Do revert here. */
local_err = unionfs_refresh_lower_dentry(new_dentry, new_parent,
old_bstart);
if (local_err) {
printk(KERN_ERR "unionfs: revert failed in rename: "
"the new refresh failed\n");
eio = -EIO;
}
local_err = unionfs_refresh_lower_dentry(old_dentry, old_parent,
old_bstart);
if (local_err) {
printk(KERN_ERR "unionfs: revert failed in rename: "
"the old refresh failed\n");
eio = -EIO;
goto revert_out;
}
if (!unionfs_lower_dentry_idx(new_dentry, bindex) ||
!unionfs_lower_dentry_idx(new_dentry, bindex)->d_inode) {
printk(KERN_ERR "unionfs: revert failed in rename: "
"the object disappeared from under us!\n");
eio = -EIO;
goto revert_out;
}
if (unionfs_lower_dentry_idx(old_dentry, bindex) &&
unionfs_lower_dentry_idx(old_dentry, bindex)->d_inode) {
printk(KERN_ERR "unionfs: revert failed in rename: "
"the object was created underneath us!\n");
eio = -EIO;
goto revert_out;
}
local_err = __unionfs_rename(new_dir, new_dentry, new_parent,
old_dir, old_dentry, old_parent,
old_bstart);
/* If we can't fix it, then we cop-out with -EIO. */
if (local_err) {
printk(KERN_ERR "unionfs: revert failed in rename!\n");
eio = -EIO;
}
local_err = unionfs_refresh_lower_dentry(new_dentry, new_parent,
bindex);
if (local_err)
eio = -EIO;
local_err = unionfs_refresh_lower_dentry(old_dentry, old_parent,
bindex);
if (local_err)
eio = -EIO;
revert_out:
if (eio)
err = eio;
return err;
}
/* This function replicates the directory structure upto given dentry
* in the bindex branch.
*/
static struct dentry *create_parents_named(struct inode *dir,
struct dentry *dentry,
const char *name, int bindex)
{
int err;
struct dentry *child_dentry;
struct dentry *parent_dentry;
struct dentry *hidden_parent_dentry = NULL;
struct dentry *hidden_dentry = NULL;
const char *childname;
unsigned int childnamelen;
int old_kmalloc_size;
int kmalloc_size;
int num_dentry;
int count;
int old_bstart;
int old_bend;
struct dentry **path = NULL;
struct dentry **tmp_path;
struct super_block *sb;
verify_locked(dentry);
/* There is no sense allocating any less than the minimum. */
kmalloc_size = malloc_sizes[0].cs_size;
num_dentry = kmalloc_size / sizeof(struct dentry *);
if ((err = is_robranch_super(dir->i_sb, bindex))) {
hidden_dentry = ERR_PTR(err);
goto out;
}
old_bstart = dbstart(dentry);
old_bend = dbend(dentry);
hidden_dentry = ERR_PTR(-ENOMEM);
path = kzalloc(kmalloc_size, GFP_KERNEL);
if (!path)
goto out;
/* assume the negative dentry of unionfs as the parent dentry */
parent_dentry = dentry;
count = 0;
/* This loop finds the first parent that exists in the given branch.
* We start building the directory structure from there. At the end
* of the loop, the following should hold:
* - child_dentry is the first nonexistent child
* - parent_dentry is the first existent parent
* - path[0] is the = deepest child
* - path[count] is the first child to create
*/
do {
child_dentry = parent_dentry;
/* find the parent directory dentry in unionfs */
parent_dentry = child_dentry->d_parent;
unionfs_lock_dentry(parent_dentry);
/* find out the hidden_parent_dentry in the given branch */
hidden_parent_dentry = unionfs_lower_dentry_idx(parent_dentry, bindex);
/* store the child dentry */
path[count++] = child_dentry;
/* grow path table */
if (count == num_dentry) {
old_kmalloc_size = kmalloc_size;
kmalloc_size *= 2;
num_dentry = kmalloc_size / sizeof(struct dentry *);
tmp_path = kzalloc(kmalloc_size, GFP_KERNEL);
if (!tmp_path) {
hidden_dentry = ERR_PTR(-ENOMEM);
goto out;
}
memcpy(tmp_path, path, old_kmalloc_size);
kfree(path);
path = tmp_path;
tmp_path = NULL;
}
} while (!hidden_parent_dentry);
count--;
sb = dentry->d_sb;
/* This is basically while(child_dentry != dentry). This loop is
* horrible to follow and should be replaced with cleaner code.
*/
while (1) {
/* get hidden parent dir in the current branch */
hidden_parent_dentry = unionfs_lower_dentry_idx(parent_dentry, bindex);
unionfs_unlock_dentry(parent_dentry);
/* init the values to lookup */
childname = child_dentry->d_name.name;
childnamelen = child_dentry->d_name.len;
if (child_dentry != dentry) {
/* lookup child in the underlying file system */
hidden_dentry =
lookup_one_len(childname, hidden_parent_dentry,
childnamelen);
if (IS_ERR(hidden_dentry))
goto out;
} else {
/* is the name a whiteout of the childname ?
* lookup the whiteout child in the underlying file system
*/
hidden_dentry =
lookup_one_len(name, hidden_parent_dentry,
strlen(name));
if (IS_ERR(hidden_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, hidden_dentry);
__cleanup_dentry(dentry, bindex, old_bstart, old_bend);
break;
}
if (hidden_dentry->d_inode) {
/* since this already exists we dput to avoid
* multiple references on the same dentry
*/
dput(hidden_dentry);
} else {
struct sioq_args args;
/* its a negative dentry, create a new dir */
hidden_parent_dentry = lock_parent(hidden_dentry);
args.mkdir.parent = hidden_parent_dentry->d_inode;
args.mkdir.dentry = hidden_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, hidden_dentry);
unlock_dir(hidden_parent_dentry);
if (err) {
dput(hidden_dentry);
hidden_dentry = ERR_PTR(err);
goto out;
}
}
__set_inode(child_dentry, hidden_dentry, bindex);
__set_dentry(child_dentry, hidden_dentry, bindex);
parent_dentry = child_dentry;
child_dentry = path[--count];
}
out:
kfree(path);
return hidden_dentry;
}
/*
* 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;
}
static int do_unionfs_rename(struct inode *old_dir,
struct dentry *old_dentry,
struct inode *new_dir,
struct dentry *new_dentry)
{
int err = 0;
int bindex, bwh_old;
int old_bstart, old_bend;
int new_bstart, new_bend;
int do_copyup = -1;
struct dentry *parent_dentry;
int local_err = 0;
int eio = 0;
int revert = 0;
struct dentry *wh_old = NULL;
old_bstart = dbstart(old_dentry);
bwh_old = old_bstart;
old_bend = dbend(old_dentry);
parent_dentry = old_dentry->d_parent;
new_bstart = dbstart(new_dentry);
new_bend = dbend(new_dentry);
/* Rename source to destination. */
err = do_rename(old_dir, old_dentry, new_dir, new_dentry, old_bstart,
&wh_old);
if (err) {
if (!IS_COPYUP_ERR(err))
goto out;
do_copyup = old_bstart - 1;
} else
revert = 1;
/* Unlink all instances of destination that exist to the left of
* bstart of source. On error, revert back, goto out.
*/
for (bindex = old_bstart - 1; bindex >= new_bstart; bindex--) {
struct dentry *unlink_dentry;
struct dentry *unlink_dir_dentry;
unlink_dentry = unionfs_lower_dentry_idx(new_dentry, bindex);
if (!unlink_dentry)
continue;
unlink_dir_dentry = lock_parent(unlink_dentry);
if (!(err = is_robranch_super(old_dir->i_sb, bindex)))
err = vfs_unlink(unlink_dir_dentry->d_inode,
unlink_dentry);
fsstack_copy_attr_times(new_dentry->d_parent->d_inode,
unlink_dir_dentry->d_inode);
/* propagate number of hard-links */
new_dentry->d_parent->d_inode->i_nlink =
unionfs_get_nlinks(new_dentry->d_parent->d_inode);
unlock_dir(unlink_dir_dentry);
if (!err) {
if (bindex != new_bstart) {
dput(unlink_dentry);
unionfs_set_lower_dentry_idx(new_dentry, bindex, NULL);
}
} else if (IS_COPYUP_ERR(err)) {
do_copyup = bindex - 1;
} else if (revert) {
dput(wh_old);
goto revert;
}
}
if (do_copyup != -1) {
for (bindex = do_copyup; bindex >= 0; bindex--) {
/* copyup the file into some left directory, so that
* you can rename it
*/
err = copyup_dentry(old_dentry->d_parent->d_inode,
old_dentry, old_bstart, bindex, NULL,
old_dentry->d_inode->i_size);
if (!err) {
dput(wh_old);
bwh_old = bindex;
err = do_rename(old_dir, old_dentry, new_dir,
new_dentry, bindex, &wh_old);
break;
}
}
}
/* make it opaque */
if (S_ISDIR(old_dentry->d_inode->i_mode)) {
err = make_dir_opaque(old_dentry, dbstart(old_dentry));
if (err)
goto revert;
}
/* Create whiteout for source, only if:
* (1) There is more than one underlying instance of source.
* (2) We did a copy_up
*/
if ((old_bstart != old_bend) || (do_copyup != -1)) {
struct dentry *hidden_parent;
BUG_ON(!wh_old || wh_old->d_inode || bwh_old < 0);
hidden_parent = lock_parent(wh_old);
local_err = vfs_create(hidden_parent->d_inode, wh_old, S_IRUGO,
NULL);
unlock_dir(hidden_parent);
if (!local_err)
set_dbopaque(old_dentry, bwh_old);
else {
/* We can't fix anything now, so we cop-out and use -EIO. */
printk(KERN_ERR "We can't create a whiteout for the "
"source in rename!\n");
err = -EIO;
}
}
out:
dput(wh_old);
return err;
revert:
/* Do revert here. */
local_err = unionfs_refresh_hidden_dentry(new_dentry, old_bstart);
if (local_err) {
printk(KERN_WARNING "Revert failed in rename: the new refresh "
"failed.\n");
eio = -EIO;
}
local_err = unionfs_refresh_hidden_dentry(old_dentry, old_bstart);
if (local_err) {
printk(KERN_WARNING "Revert failed in rename: the old refresh "
"failed.\n");
eio = -EIO;
goto revert_out;
}
if (!unionfs_lower_dentry_idx(new_dentry, bindex) ||
!unionfs_lower_dentry_idx(new_dentry, bindex)->d_inode) {
printk(KERN_WARNING "Revert failed in rename: the object "
"disappeared from under us!\n");
eio = -EIO;
goto revert_out;
}
if (unionfs_lower_dentry_idx(old_dentry, bindex) &&
unionfs_lower_dentry_idx(old_dentry, bindex)->d_inode) {
printk(KERN_WARNING "Revert failed in rename: the object was "
"created underneath us!\n");
eio = -EIO;
goto revert_out;
}
local_err = do_rename(new_dir, new_dentry, old_dir, old_dentry, old_bstart,
NULL);
/* If we can't fix it, then we cop-out with -EIO. */
if (local_err) {
printk(KERN_WARNING "Revert failed in rename!\n");
eio = -EIO;
}
local_err = unionfs_refresh_hidden_dentry(new_dentry, bindex);
if (local_err)
eio = -EIO;
local_err = unionfs_refresh_hidden_dentry(old_dentry, bindex);
if (local_err)
eio = -EIO;
revert_out:
if (eio)
err = eio;
return err;
}
/*
* There is no need to lock the unionfs_super_info's rwsem as there is no
* way anyone can have a reference to the superblock at this point in time.
*/
static int unionfs_read_super(struct super_block *sb, void *raw_data,
int silent)
{
int err = 0;
struct unionfs_dentry_info *lower_root_info = NULL;
int bindex, bstart, bend;
struct inode *inode = NULL;
if (!raw_data) {
printk(KERN_ERR
"unionfs: read_super: missing data argument\n");
err = -EINVAL;
goto out;
}
/* Allocate superblock private data */
sb->s_fs_info = kzalloc(sizeof(struct unionfs_sb_info), GFP_KERNEL);
if (unlikely(!UNIONFS_SB(sb))) {
printk(KERN_CRIT "unionfs: read_super: out of memory\n");
err = -ENOMEM;
goto out;
}
UNIONFS_SB(sb)->bend = -1;
atomic_set(&UNIONFS_SB(sb)->generation, 1);
init_rwsem(&UNIONFS_SB(sb)->rwsem);
UNIONFS_SB(sb)->high_branch_id = -1; /* -1 == invalid branch ID */
lower_root_info = unionfs_parse_options(sb, raw_data);
if (IS_ERR(lower_root_info)) {
printk(KERN_ERR
"unionfs: read_super: error while parsing options "
"(err = %ld)\n", PTR_ERR(lower_root_info));
err = PTR_ERR(lower_root_info);
lower_root_info = NULL;
goto out_free;
}
if (lower_root_info->bstart == -1) {
err = -ENOENT;
goto out_free;
}
/* set the lower superblock field of upper superblock */
bstart = lower_root_info->bstart;
BUG_ON(bstart != 0);
sbend(sb) = bend = lower_root_info->bend;
for (bindex = bstart; bindex <= bend; bindex++) {
struct dentry *d = lower_root_info->lower_paths[bindex].dentry;
atomic_inc(&d->d_sb->s_active);
unionfs_set_lower_super_idx(sb, bindex, d->d_sb);
}
/* max Bytes is the maximum bytes from highest priority branch */
sb->s_maxbytes = unionfs_lower_super_idx(sb, 0)->s_maxbytes;
/*
* Our c/m/atime granularity is 1 ns because we may stack on file
* systems whose granularity is as good. This is important for our
* time-based cache coherency.
*/
sb->s_time_gran = 1;
sb->s_op = &unionfs_sops;
/* get a new inode and allocate our root dentry */
inode = unionfs_iget(sb, iunique(sb, UNIONFS_ROOT_INO));
if (IS_ERR(inode)) {
err = PTR_ERR(inode);
goto out_dput;
}
sb->s_root = d_make_root(inode);
if (unlikely(!sb->s_root)) {
err = -ENOMEM;
goto out_iput;
}
d_set_d_op(sb->s_root, &unionfs_dops);
/* link the upper and lower dentries */
sb->s_root->d_fsdata = NULL;
err = new_dentry_private_data(sb->s_root, UNIONFS_DMUTEX_ROOT);
if (unlikely(err))
goto out_freedpd;
/* if get here: cannot have error */
/* Set the lower dentries for s_root */
for (bindex = bstart; bindex <= bend; bindex++) {
struct dentry *d;
struct vfsmount *m;
d = lower_root_info->lower_paths[bindex].dentry;
m = lower_root_info->lower_paths[bindex].mnt;
unionfs_set_lower_dentry_idx(sb->s_root, bindex, d);
unionfs_set_lower_mnt_idx(sb->s_root, bindex, m);
}
dbstart(sb->s_root) = bstart;
dbend(sb->s_root) = bend;
/* Set the generation number to one, since this is for the mount. */
atomic_set(&UNIONFS_D(sb->s_root)->generation, 1);
if (atomic_read(&inode->i_count) <= 1)
unionfs_fill_inode(sb->s_root, inode);
/*
* No need to call interpose because we already have a positive
* dentry, which was instantiated by d_alloc_root. Just need to
* d_rehash it.
*/
d_rehash(sb->s_root);
unionfs_unlock_dentry(sb->s_root);
goto out; /* all is well */
out_freedpd:
if (UNIONFS_D(sb->s_root)) {
kfree(UNIONFS_D(sb->s_root)->lower_paths);
free_dentry_private_data(sb->s_root);
}
dput(sb->s_root);
out_iput:
iput(inode);
out_dput:
if (lower_root_info && !IS_ERR(lower_root_info)) {
for (bindex = lower_root_info->bstart;
bindex <= lower_root_info->bend; bindex++) {
struct dentry *d;
d = lower_root_info->lower_paths[bindex].dentry;
/* drop refs we took earlier */
atomic_dec(&d->d_sb->s_active);
path_put(&lower_root_info->lower_paths[bindex]);
}
kfree(lower_root_info->lower_paths);
kfree(lower_root_info);
lower_root_info = NULL;
}
out_free:
kfree(UNIONFS_SB(sb)->data);
kfree(UNIONFS_SB(sb));
sb->s_fs_info = NULL;
out:
if (lower_root_info && !IS_ERR(lower_root_info)) {
kfree(lower_root_info->lower_paths);
kfree(lower_root_info);
}
return err;
}
/*
* Main (and complex) driver function for Unionfs's lookup
*
* Returns: NULL (ok), ERR_PTR if an error occurred, or a non-null non-error
* PTR if d_splice returned a different dentry.
*
* If lookupmode is INTERPOSE_PARTIAL/REVAL/REVAL_NEG, the passed dentry's
* inode info must be locked. If lookupmode is INTERPOSE_LOOKUP (i.e., a
* newly looked-up dentry), then unionfs_lookup_backend will return a locked
* dentry's info, which the caller must unlock.
*/
struct dentry *unionfs_lookup_full(struct dentry *dentry,
struct dentry *parent, int lookupmode)
{
int err = 0;
struct dentry *lower_dentry = NULL;
struct vfsmount *lower_mnt;
struct vfsmount *lower_dir_mnt;
struct dentry *wh_lower_dentry = NULL;
struct dentry *lower_dir_dentry = NULL;
struct dentry *d_interposed = NULL;
int bindex, bstart, bend, bopaque;
int opaque, num_positive = 0;
const char *name;
int namelen;
int pos_start, pos_end;
/*
* We should already have a lock on this dentry in the case of a
* partial lookup, or a revalidation. Otherwise it is returned from
* new_dentry_private_data already locked.
*/
verify_locked(dentry);
verify_locked(parent);
/* must initialize dentry operations */
dentry->d_op = &unionfs_dops;
/* We never partial lookup the root directory. */
if (IS_ROOT(dentry))
goto out;
name = dentry->d_name.name;
namelen = dentry->d_name.len;
/* No dentries should get created for possible whiteout names. */
if (!is_validname(name)) {
err = -EPERM;
goto out_free;
}
/* Now start the actual lookup procedure. */
bstart = dbstart(parent);
bend = dbend(parent);
bopaque = dbopaque(parent);
BUG_ON(bstart < 0);
/* adjust bend to bopaque if needed */
if ((bopaque >= 0) && (bopaque < bend))
bend = bopaque;
/* lookup all possible dentries */
for (bindex = bstart; bindex <= bend; bindex++) {
lower_dentry = unionfs_lower_dentry_idx(dentry, bindex);
lower_mnt = unionfs_lower_mnt_idx(dentry, bindex);
/* skip if we already have a positive lower dentry */
if (lower_dentry) {
if (dbstart(dentry) < 0)
dbstart(dentry) = bindex;
if (bindex > dbend(dentry))
dbend(dentry) = bindex;
if (lower_dentry->d_inode)
num_positive++;
continue;
}
lower_dir_dentry =
unionfs_lower_dentry_idx(parent, bindex);
/* if the lower dentry's parent does not exist, skip this */
if (!lower_dir_dentry || !lower_dir_dentry->d_inode)
continue;
/* also skip it if the parent isn't a directory. */
if (!S_ISDIR(lower_dir_dentry->d_inode->i_mode))
continue; /* XXX: should be BUG_ON */
/* check for whiteouts: stop lookup if found */
wh_lower_dentry = lookup_whiteout(name, lower_dir_dentry);
if (IS_ERR(wh_lower_dentry)) {
err = PTR_ERR(wh_lower_dentry);
goto out_free;
}
if (wh_lower_dentry->d_inode) {
dbend(dentry) = dbopaque(dentry) = bindex;
if (dbstart(dentry) < 0)
dbstart(dentry) = bindex;
dput(wh_lower_dentry);
break;
}
dput(wh_lower_dentry);
/* Now do regular lookup; lookup @name */
lower_dir_mnt = unionfs_lower_mnt_idx(parent, bindex);
lower_mnt = NULL; /* XXX: needed? */
lower_dentry = __lookup_one(lower_dir_dentry, lower_dir_mnt,
name, &lower_mnt);
if (IS_ERR(lower_dentry)) {
err = PTR_ERR(lower_dentry);
goto out_free;
}
unionfs_set_lower_dentry_idx(dentry, bindex, lower_dentry);
if (!lower_mnt)
lower_mnt = unionfs_mntget(dentry->d_sb->s_root,
bindex);
unionfs_set_lower_mnt_idx(dentry, bindex, lower_mnt);
/* adjust dbstart/end */
if (dbstart(dentry) < 0)
dbstart(dentry) = bindex;
if (bindex > dbend(dentry))
dbend(dentry) = bindex;
/*
* We always store the lower dentries above, and update
* dbstart/dbend, even if the whole unionfs dentry is
* negative (i.e., no lower inodes).
*/
if (!lower_dentry->d_inode)
continue;
num_positive++;
/*
* check if we just found an opaque directory, if so, stop
* lookups here.
*/
if (!S_ISDIR(lower_dentry->d_inode->i_mode))
continue;
opaque = is_opaque_dir(dentry, bindex);
if (opaque < 0) {
err = opaque;
goto out_free;
} else if (opaque) {
dbend(dentry) = dbopaque(dentry) = bindex;
break;
}
dbend(dentry) = bindex;
/* update parent directory's atime with the bindex */
fsstack_copy_attr_atime(parent->d_inode,
lower_dir_dentry->d_inode);
}
/* sanity checks, then decide if to process a negative dentry */
BUG_ON(dbstart(dentry) < 0 && dbend(dentry) >= 0);
BUG_ON(dbstart(dentry) >= 0 && dbend(dentry) < 0);
if (num_positive > 0)
goto out_positive;
/*** handle NEGATIVE dentries ***/
/*
* If negative, keep only first lower negative dentry, to save on
* memory.
*/
if (dbstart(dentry) < dbend(dentry)) {
path_put_lowers(dentry, dbstart(dentry) + 1,
dbend(dentry), false);
dbend(dentry) = dbstart(dentry);
}
if (lookupmode == INTERPOSE_PARTIAL)
goto out;
if (lookupmode == INTERPOSE_LOOKUP) {
/*
* If all we found was a whiteout in the first available
* branch, then create a negative dentry for a possibly new
* file to be created.
*/
if (dbopaque(dentry) < 0)
goto out;
/* XXX: need to get mnt here */
bindex = dbstart(dentry);
if (unionfs_lower_dentry_idx(dentry, bindex))
goto out;
lower_dir_dentry =
unionfs_lower_dentry_idx(parent, bindex);
if (!lower_dir_dentry || !lower_dir_dentry->d_inode)
goto out;
if (!S_ISDIR(lower_dir_dentry->d_inode->i_mode))
goto out; /* XXX: should be BUG_ON */
/* XXX: do we need to cross bind mounts here? */
lower_dentry = lookup_one_len(name, lower_dir_dentry, namelen);
if (IS_ERR(lower_dentry)) {
err = PTR_ERR(lower_dentry);
goto out;
}
/* XXX: need to mntget/mntput as needed too! */
unionfs_set_lower_dentry_idx(dentry, bindex, lower_dentry);
/* XXX: wrong mnt for crossing bind mounts! */
lower_mnt = unionfs_mntget(dentry->d_sb->s_root, bindex);
unionfs_set_lower_mnt_idx(dentry, bindex, lower_mnt);
goto out;
}
/* if we're revalidating a positive dentry, don't make it negative */
if (lookupmode != INTERPOSE_REVAL)
d_add(dentry, NULL);
goto out;
out_positive:
/*** handle POSITIVE dentries ***/
/*
* This unionfs dentry is positive (at least one lower inode
* exists), so scan entire dentry from beginning to end, and remove
* any negative lower dentries, if any. Then, update dbstart/dbend
* to reflect the start/end of positive dentries.
*/
pos_start = pos_end = -1;
for (bindex = bstart; bindex <= bend; bindex++) {
lower_dentry = unionfs_lower_dentry_idx(dentry,
bindex);
if (lower_dentry && lower_dentry->d_inode) {
if (pos_start < 0)
pos_start = bindex;
if (bindex > pos_end)
pos_end = bindex;
continue;
}
path_put_lowers(dentry, bindex, bindex, false);
}
if (pos_start >= 0)
dbstart(dentry) = pos_start;
if (pos_end >= 0)
dbend(dentry) = pos_end;
/* Partial lookups need to re-interpose, or throw away older negs. */
if (lookupmode == INTERPOSE_PARTIAL) {
if (dentry->d_inode) {
unionfs_reinterpose(dentry);
goto out;
}
/*
* This dentry was positive, so it is as if we had a
* negative revalidation.
*/
lookupmode = INTERPOSE_REVAL_NEG;
update_bstart(dentry);
}
/*
* Interpose can return a dentry if d_splice returned a different
* dentry.
*/
d_interposed = unionfs_interpose(dentry, dentry->d_sb, lookupmode);
if (IS_ERR(d_interposed))
err = PTR_ERR(d_interposed);
else if (d_interposed)
dentry = d_interposed;
if (!err)
goto out;
d_drop(dentry);
out_free:
/* should dput/mntput all the underlying dentries on error condition */
if (dbstart(dentry) >= 0)
path_put_lowers_all(dentry, false);
/* free lower_paths unconditionally */
kfree(UNIONFS_D(dentry)->lower_paths);
UNIONFS_D(dentry)->lower_paths = NULL;
out:
if (dentry && UNIONFS_D(dentry)) {
BUG_ON(dbstart(dentry) < 0 && dbend(dentry) >= 0);
BUG_ON(dbstart(dentry) >= 0 && dbend(dentry) < 0);
}
if (d_interposed && UNIONFS_D(d_interposed)) {
BUG_ON(dbstart(d_interposed) < 0 && dbend(d_interposed) >= 0);
BUG_ON(dbstart(d_interposed) >= 0 && dbend(d_interposed) < 0);
}
if (!err && d_interposed)
return d_interposed;
return ERR_PTR(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;
}
/*
* our custom d_alloc_root work-alike
*
* we can't use d_alloc_root if we want to use our own interpose function
* unchanged, so we simply call our own "fake" d_alloc_root
*/
static struct dentry *unionfs_d_alloc_root(struct super_block *sb)
{
struct dentry *ret = NULL;
if (sb) {
static const struct qstr name = {
.name = "/",
.len = 1
};
ret = d_alloc(NULL, &name);
if (likely(ret)) {
ret->d_op = &unionfs_dops;
ret->d_sb = sb;
ret->d_parent = ret;
}
}
return ret;
}
/*
* There is no need to lock the unionfs_super_info's rwsem as there is no
* way anyone can have a reference to the superblock at this point in time.
*/
static int unionfs_read_super(struct super_block *sb, void *raw_data,
int silent)
{
int err = 0;
struct unionfs_dentry_info *lower_root_info = NULL;
int bindex, bstart, bend;
if (!raw_data) {
printk(KERN_ERR
"unionfs: read_super: missing data argument\n");
err = -EINVAL;
goto out;
}
/* Allocate superblock private data */
sb->s_fs_info = kzalloc(sizeof(struct unionfs_sb_info), GFP_KERNEL);
if (unlikely(!UNIONFS_SB(sb))) {
printk(KERN_CRIT "unionfs: read_super: out of memory\n");
err = -ENOMEM;
goto out;
}
UNIONFS_SB(sb)->bend = -1;
atomic_set(&UNIONFS_SB(sb)->generation, 1);
init_rwsem(&UNIONFS_SB(sb)->rwsem);
UNIONFS_SB(sb)->high_branch_id = -1; /* -1 == invalid branch ID */
lower_root_info = unionfs_parse_options(sb, raw_data);
if (IS_ERR(lower_root_info)) {
printk(KERN_ERR
"unionfs: read_super: error while parsing options "
"(err = %ld)\n", PTR_ERR(lower_root_info));
err = PTR_ERR(lower_root_info);
lower_root_info = NULL;
goto out_free;
}
if (lower_root_info->bstart == -1) {
err = -ENOENT;
goto out_free;
}
/* set the lower superblock field of upper superblock */
bstart = lower_root_info->bstart;
BUG_ON(bstart != 0);
sbend(sb) = bend = lower_root_info->bend;
for (bindex = bstart; bindex <= bend; bindex++) {
struct dentry *d = lower_root_info->lower_paths[bindex].dentry;
atomic_inc(&d->d_sb->s_active);
unionfs_set_lower_super_idx(sb, bindex, d->d_sb);
}
/* max Bytes is the maximum bytes from highest priority branch */
sb->s_maxbytes = unionfs_lower_super_idx(sb, 0)->s_maxbytes;
/*
* Our c/m/atime granularity is 1 ns because we may stack on file
* systems whose granularity is as good. This is important for our
* time-based cache coherency.
*/
sb->s_time_gran = 1;
sb->s_op = &unionfs_sops;
/* See comment next to the definition of unionfs_d_alloc_root */
sb->s_root = unionfs_d_alloc_root(sb);
if (unlikely(!sb->s_root)) {
err = -ENOMEM;
goto out_dput;
}
/* link the upper and lower dentries */
sb->s_root->d_fsdata = NULL;
err = new_dentry_private_data(sb->s_root, UNIONFS_DMUTEX_ROOT);
if (unlikely(err))
goto out_freedpd;
/* Set the lower dentries for s_root */
for (bindex = bstart; bindex <= bend; bindex++) {
struct dentry *d;
struct vfsmount *m;
d = lower_root_info->lower_paths[bindex].dentry;
m = lower_root_info->lower_paths[bindex].mnt;
unionfs_set_lower_dentry_idx(sb->s_root, bindex, d);
unionfs_set_lower_mnt_idx(sb->s_root, bindex, m);
}
dbstart(sb->s_root) = bstart;
dbend(sb->s_root) = bend;
/* Set the generation number to one, since this is for the mount. */
atomic_set(&UNIONFS_D(sb->s_root)->generation, 1);
/*
* Call interpose to create the upper level inode. Only
* INTERPOSE_LOOKUP can return a value other than 0 on err.
*/
err = PTR_ERR(unionfs_interpose(sb->s_root, sb, 0));
unionfs_unlock_dentry(sb->s_root);
if (!err)
goto out;
/* else fall through */
out_freedpd:
if (UNIONFS_D(sb->s_root)) {
kfree(UNIONFS_D(sb->s_root)->lower_paths);
free_dentry_private_data(sb->s_root);
}
dput(sb->s_root);
out_dput:
if (lower_root_info && !IS_ERR(lower_root_info)) {
for (bindex = lower_root_info->bstart;
bindex <= lower_root_info->bend; bindex++) {
struct dentry *d;
struct vfsmount *m;
d = lower_root_info->lower_paths[bindex].dentry;
m = lower_root_info->lower_paths[bindex].mnt;
dput(d);
/* initializing: can't use unionfs_mntput here */
mntput(m);
/* drop refs we took earlier */
atomic_dec(&d->d_sb->s_active);
}
kfree(lower_root_info->lower_paths);
kfree(lower_root_info);
lower_root_info = NULL;
}
out_free:
kfree(UNIONFS_SB(sb)->data);
kfree(UNIONFS_SB(sb));
sb->s_fs_info = NULL;
out:
if (lower_root_info && !IS_ERR(lower_root_info)) {
kfree(lower_root_info->lower_paths);
kfree(lower_root_info);
}
return err;
}