static inline int __realloc_dentry_private_data(struct dentry *dentry)
{
struct unionfs_dentry_info *info = UNIONFS_D(dentry);
void *p;
int size;
BUG_ON(!info);
size = sizeof(struct path) * sbmax(dentry->d_sb);
p = krealloc(info->lower_paths, size, GFP_ATOMIC);
if (unlikely(!p))
return -ENOMEM;
info->lower_paths = p;
info->bstart = -1;
info->bend = -1;
info->bopaque = -1;
info->bcount = sbmax(dentry->d_sb);
atomic_set(&info->generation,
atomic_read(&UNIONFS_SB(dentry->d_sb)->generation));
memset(info->lower_paths, 0, size);
return 0;
}
static void unionfs_read_inode(struct inode *inode)
{
static struct address_space_operations unionfs_empty_aops;
print_entry_location();
if (!itopd(inode)) {
FISTBUG
("No kernel memory when allocating inode private data!\n");
}
PASSERT(inode->i_sb);
memset(itopd(inode), 0, sizeof(struct unionfs_inode_info));
itopd(inode)->b_start = -1;
itopd(inode)->b_end = -1;
atomic_set(&itopd(inode)->uii_generation,
atomic_read(&stopd(inode->i_sb)->usi_generation));
itopd(inode)->uii_rdlock = SPIN_LOCK_UNLOCKED;
itopd(inode)->uii_rdcount = 1;
itopd(inode)->uii_hashsize = -1;
INIT_LIST_HEAD(&itopd(inode)->uii_readdircache);
if (sbmax(inode->i_sb) > UNIONFS_INLINE_OBJECTS) {
int size =
(sbmax(inode->i_sb) -
UNIONFS_INLINE_OBJECTS) * sizeof(struct inode *);
itohi_ptr(inode) = KMALLOC(size, GFP_UNIONFS);
if (!itohi_ptr(inode)) {
FISTBUG
("No kernel memory when allocating lower-pointer array!\n");
}
memset(itohi_ptr(inode), 0, size);
}
memset(itohi_inline(inode), 0,
UNIONFS_INLINE_OBJECTS * sizeof(struct inode *));
inode->i_version++;
inode->i_op = &unionfs_main_iops;
inode->i_fop = &unionfs_main_fops;
/* I don't think ->a_ops is ever allowed to be NULL */
inode->i_mapping->a_ops = &unionfs_empty_aops;
fist_dprint(7, "setting inode 0x%p a_ops to empty (0x%p)\n",
inode, inode->i_mapping->a_ops);
print_exit_location();
}
/* useful to track vfsmount leaks that could cause EBUSY on unmount */
void __show_branch_counts(const struct super_block *sb,
const char *file, const char *fxn, int line)
{
int i;
struct vfsmount *mnt;
pr_debug("BC:");
for (i = 0; i < sbmax(sb); i++) {
if (likely(sb->s_root))
mnt = UNIONFS_D(sb->s_root)->lower_paths[i].mnt;
else
mnt = NULL;
printk(KERN_CONT "%d:",
(mnt ? atomic_read(&mnt->mnt_count) : -99));
}
printk(KERN_CONT "%s:%s:%d\n", file, fxn, line);
}
/*
* __unionfs_check_{inode,dentry,file} perform exhaustive sanity checking on
* the fan-out of various Unionfs objects. We check that no lower objects
* exist outside the start/end branch range; that all objects within are
* non-NULL (with some allowed exceptions); that for every lower file
* there's a lower dentry+inode; that the start/end ranges match for all
* corresponding lower objects; that open files/symlinks have only one lower
* objects, but directories can have several; and more.
*/
void __unionfs_check_inode(const struct inode *inode,
const char *fname, const char *fxn, int line)
{
int bindex;
int istart, iend;
struct inode *lower_inode;
struct super_block *sb;
int printed_caller = 0;
void *poison_ptr;
/* for inodes now */
BUG_ON(!inode);
sb = inode->i_sb;
istart = ibstart(inode);
iend = ibend(inode);
/* don't check inode if no lower branches */
if (istart < 0 && iend < 0)
return;
if (unlikely(istart > iend)) {
PRINT_CALLER(fname, fxn, line);
pr_debug(" Ci0: inode=%p istart/end=%d:%d\n",
inode, istart, iend);
}
if (unlikely((istart == -1 && iend != -1) ||
(istart != -1 && iend == -1))) {
PRINT_CALLER(fname, fxn, line);
pr_debug(" Ci1: inode=%p istart/end=%d:%d\n",
inode, istart, iend);
}
if (!S_ISDIR(inode->i_mode)) {
if (unlikely(iend != istart)) {
PRINT_CALLER(fname, fxn, line);
pr_debug(" Ci2: inode=%p istart=%d iend=%d\n",
inode, istart, iend);
}
}
for (bindex = sbstart(sb); bindex < sbmax(sb); bindex++) {
if (unlikely(!UNIONFS_I(inode))) {
PRINT_CALLER(fname, fxn, line);
pr_debug(" Ci3: no inode_info %p\n", inode);
return;
}
if (unlikely(!UNIONFS_I(inode)->lower_inodes)) {
PRINT_CALLER(fname, fxn, line);
pr_debug(" Ci4: no lower_inodes %p\n", inode);
return;
}
lower_inode = unionfs_lower_inode_idx(inode, bindex);
if (lower_inode) {
memset(&poison_ptr, POISON_INUSE, sizeof(void *));
if (unlikely(bindex < istart || bindex > iend)) {
PRINT_CALLER(fname, fxn, line);
pr_debug(" Ci5: inode/linode=%p:%p bindex=%d "
"istart/end=%d:%d\n", inode,
lower_inode, bindex, istart, iend);
} else if (unlikely(lower_inode == poison_ptr)) {
/* freed inode! */
PRINT_CALLER(fname, fxn, line);
pr_debug(" Ci6: inode/linode=%p:%p bindex=%d "
"istart/end=%d:%d\n", inode,
lower_inode, bindex, istart, iend);
}
continue;
}
/* if we get here, then lower_inode == NULL */
if (bindex < istart || bindex > iend)
continue;
/*
* directories can have NULL lower inodes in b/t start/end,
* but NOT if at the start/end range.
*/
if (unlikely(S_ISDIR(inode->i_mode) &&
bindex > istart && bindex < iend))
continue;
PRINT_CALLER(fname, fxn, line);
pr_debug(" Ci7: inode/linode=%p:%p "
"bindex=%d istart/end=%d:%d\n",
inode, lower_inode, bindex, istart, iend);
}
}
void __unionfs_check_file(const struct file *file,
const char *fname, const char *fxn, int line)
{
int bindex;
int dstart, dend, fstart, fend;
struct dentry *dentry;
struct file *lower_file;
struct inode *inode;
struct super_block *sb;
int printed_caller = 0;
BUG_ON(!file);
dentry = file->f_path.dentry;
sb = dentry->d_sb;
dstart = dbstart(dentry);
dend = dbend(dentry);
BUG_ON(dstart > dend);
fstart = fbstart(file);
fend = fbend(file);
BUG_ON(fstart > fend);
if (unlikely((fstart == -1 && fend != -1) ||
(fstart != -1 && fend == -1))) {
PRINT_CALLER(fname, fxn, line);
pr_debug(" CF0: file/dentry=%p:%p fstart/end=%d:%d\n",
file, dentry, fstart, fend);
}
if (unlikely(fstart != dstart)) {
PRINT_CALLER(fname, fxn, line);
pr_debug(" CF1: file/dentry=%p:%p fstart=%d dstart=%d\n",
file, dentry, fstart, dstart);
}
if (unlikely(fend != dend)) {
PRINT_CALLER(fname, fxn, line);
pr_debug(" CF2: file/dentry=%p:%p fend=%d dend=%d\n",
file, dentry, fend, dend);
}
inode = dentry->d_inode;
if (!S_ISDIR(inode->i_mode)) {
if (unlikely(fend != fstart)) {
PRINT_CALLER(fname, fxn, line);
pr_debug(" CF3: file/inode=%p:%p fstart=%d fend=%d\n",
file, inode, fstart, fend);
}
if (unlikely(dend != dstart)) {
PRINT_CALLER(fname, fxn, line);
pr_debug(" CF4: file/dentry=%p:%p dstart=%d dend=%d\n",
file, dentry, dstart, dend);
}
}
/*
* check for NULL dentries inside the start/end range, or
* non-NULL dentries outside the start/end range.
*/
for (bindex = sbstart(sb); bindex < sbmax(sb); bindex++) {
lower_file = unionfs_lower_file_idx(file, bindex);
if (lower_file) {
if (unlikely(bindex < fstart || bindex > fend)) {
PRINT_CALLER(fname, fxn, line);
pr_debug(" CF5: file/lower=%p:%p bindex=%d "
"fstart/end=%d:%d\n", file,
lower_file, bindex, fstart, fend);
}
} else { /* lower_file == NULL */
if (bindex >= fstart && bindex <= fend) {
/*
* directories can have NULL lower inodes in
* b/t start/end, but NOT if at the
* start/end range.
*/
if (unlikely(!(S_ISDIR(inode->i_mode) &&
bindex > fstart &&
bindex < fend))) {
PRINT_CALLER(fname, fxn, line);
pr_debug(" CF6: file/lower=%p:%p "
"bindex=%d fstart/end=%d:%d\n",
file, lower_file, bindex,
fstart, fend);
}
}
}
}
__unionfs_check_dentry(dentry, fname, fxn, line);
}
void __unionfs_check_dentry(const struct dentry *dentry,
const char *fname, const char *fxn, int line)
{
int bindex;
int dstart, dend, istart, iend;
struct dentry *lower_dentry;
struct inode *inode, *lower_inode;
struct super_block *sb;
struct vfsmount *lower_mnt;
int printed_caller = 0;
void *poison_ptr;
BUG_ON(!dentry);
sb = dentry->d_sb;
inode = dentry->d_inode;
dstart = dbstart(dentry);
dend = dbend(dentry);
/* don't check dentry/mnt if no lower branches */
if (dstart < 0 && dend < 0)
goto check_inode;
BUG_ON(dstart > dend);
if (unlikely((dstart == -1 && dend != -1) ||
(dstart != -1 && dend == -1))) {
PRINT_CALLER(fname, fxn, line);
pr_debug(" CD0: dentry=%p dstart/end=%d:%d\n",
dentry, dstart, dend);
}
/*
* check for NULL dentries inside the start/end range, or
* non-NULL dentries outside the start/end range.
*/
for (bindex = sbstart(sb); bindex < sbmax(sb); bindex++) {
lower_dentry = unionfs_lower_dentry_idx(dentry, bindex);
if (lower_dentry) {
if (unlikely(bindex < dstart || bindex > dend)) {
PRINT_CALLER(fname, fxn, line);
pr_debug(" CD1: dentry/lower=%p:%p(%p) "
"bindex=%d dstart/end=%d:%d\n",
dentry, lower_dentry,
(lower_dentry ? lower_dentry->d_inode :
(void *) -1L),
bindex, dstart, dend);
}
} else { /* lower_dentry == NULL */
if (bindex < dstart || bindex > dend)
continue;
/*
* Directories can have NULL lower inodes in b/t
* start/end, but NOT if at the start/end range.
* Ignore this rule, however, if this is a NULL
* dentry or a deleted dentry.
*/
if (unlikely(!d_deleted((struct dentry *) dentry) &&
inode &&
!(inode && S_ISDIR(inode->i_mode) &&
bindex > dstart && bindex < dend))) {
PRINT_CALLER(fname, fxn, line);
pr_debug(" CD2: dentry/lower=%p:%p(%p) "
"bindex=%d dstart/end=%d:%d\n",
dentry, lower_dentry,
(lower_dentry ?
lower_dentry->d_inode :
(void *) -1L),
bindex, dstart, dend);
}
}
}
/* check for vfsmounts same as for dentries */
for (bindex = sbstart(sb); bindex < sbmax(sb); bindex++) {
lower_mnt = unionfs_lower_mnt_idx(dentry, bindex);
if (lower_mnt) {
if (unlikely(bindex < dstart || bindex > dend)) {
PRINT_CALLER(fname, fxn, line);
pr_debug(" CM0: dentry/lmnt=%p:%p bindex=%d "
"dstart/end=%d:%d\n", dentry,
lower_mnt, bindex, dstart, dend);
}
} else { /* lower_mnt == NULL */
if (bindex < dstart || bindex > dend)
continue;
/*
* Directories can have NULL lower inodes in b/t
* start/end, but NOT if at the start/end range.
* Ignore this rule, however, if this is a NULL
* dentry.
*/
if (unlikely(inode &&
!(inode && S_ISDIR(inode->i_mode) &&
bindex > dstart && bindex < dend))) {
PRINT_CALLER(fname, fxn, line);
pr_debug(" CM1: dentry/lmnt=%p:%p "
"bindex=%d dstart/end=%d:%d\n",
dentry, lower_mnt, bindex,
dstart, dend);
}
}
}
check_inode:
/* for inodes now */
if (!inode)
return;
istart = ibstart(inode);
iend = ibend(inode);
/* don't check inode if no lower branches */
if (istart < 0 && iend < 0)
return;
BUG_ON(istart > iend);
if (unlikely((istart == -1 && iend != -1) ||
(istart != -1 && iend == -1))) {
PRINT_CALLER(fname, fxn, line);
pr_debug(" CI0: dentry/inode=%p:%p istart/end=%d:%d\n",
dentry, inode, istart, iend);
}
if (unlikely(istart != dstart)) {
PRINT_CALLER(fname, fxn, line);
pr_debug(" CI1: dentry/inode=%p:%p istart=%d dstart=%d\n",
dentry, inode, istart, dstart);
}
if (unlikely(iend != dend)) {
PRINT_CALLER(fname, fxn, line);
pr_debug(" CI2: dentry/inode=%p:%p iend=%d dend=%d\n",
dentry, inode, iend, dend);
}
if (!S_ISDIR(inode->i_mode)) {
if (unlikely(dend != dstart)) {
PRINT_CALLER(fname, fxn, line);
pr_debug(" CI3: dentry/inode=%p:%p dstart=%d dend=%d\n",
dentry, inode, dstart, dend);
}
if (unlikely(iend != istart)) {
PRINT_CALLER(fname, fxn, line);
pr_debug(" CI4: dentry/inode=%p:%p istart=%d iend=%d\n",
dentry, inode, istart, iend);
}
}
for (bindex = sbstart(sb); bindex < sbmax(sb); bindex++) {
lower_inode = unionfs_lower_inode_idx(inode, bindex);
if (lower_inode) {
memset(&poison_ptr, POISON_INUSE, sizeof(void *));
if (unlikely(bindex < istart || bindex > iend)) {
PRINT_CALLER(fname, fxn, line);
pr_debug(" CI5: dentry/linode=%p:%p bindex=%d "
"istart/end=%d:%d\n", dentry,
lower_inode, bindex, istart, iend);
} else if (unlikely(lower_inode == poison_ptr)) {
/* freed inode! */
PRINT_CALLER(fname, fxn, line);
pr_debug(" CI6: dentry/linode=%p:%p bindex=%d "
"istart/end=%d:%d\n", dentry,
lower_inode, bindex, istart, iend);
}
continue;
}
/* if we get here, then lower_inode == NULL */
if (bindex < istart || bindex > iend)
continue;
/*
* directories can have NULL lower inodes in b/t start/end,
* but NOT if at the start/end range.
*/
if (unlikely(S_ISDIR(inode->i_mode) &&
bindex > istart && bindex < iend))
continue;
PRINT_CALLER(fname, fxn, line);
pr_debug(" CI7: dentry/linode=%p:%p "
"bindex=%d istart/end=%d:%d\n",
dentry, lower_inode, bindex, istart, iend);
}
/*
* If it's a directory, then intermediate objects b/t start/end can
* be NULL. But, check that all three are NULL: lower dentry, mnt,
* and inode.
*/
if (dstart >= 0 && dend >= 0 && S_ISDIR(inode->i_mode))
for (bindex = dstart+1; bindex < dend; bindex++) {
lower_inode = unionfs_lower_inode_idx(inode, bindex);
lower_dentry = unionfs_lower_dentry_idx(dentry,
bindex);
lower_mnt = unionfs_lower_mnt_idx(dentry, bindex);
if (unlikely(!((lower_inode && lower_dentry &&
lower_mnt) ||
(!lower_inode &&
!lower_dentry && !lower_mnt)))) {
PRINT_CALLER(fname, fxn, line);
pr_debug(" Cx: lmnt/ldentry/linode=%p:%p:%p "
"bindex=%d dstart/end=%d:%d\n",
lower_mnt, lower_dentry, lower_inode,
bindex, dstart, dend);
}
}
/* check if lower inode is newer than upper one (it shouldn't) */
if (unlikely(is_newer_lower(dentry) && !is_negative_lower(dentry))) {
PRINT_CALLER(fname, fxn, line);
for (bindex = ibstart(inode); bindex <= ibend(inode);
bindex++) {
lower_inode = unionfs_lower_inode_idx(inode, bindex);
if (unlikely(!lower_inode))
continue;
pr_debug(" CI8: bindex=%d mtime/lmtime=%lu.%lu/%lu.%lu "
"ctime/lctime=%lu.%lu/%lu.%lu\n",
bindex,
inode->i_mtime.tv_sec,
inode->i_mtime.tv_nsec,
lower_inode->i_mtime.tv_sec,
lower_inode->i_mtime.tv_nsec,
inode->i_ctime.tv_sec,
inode->i_ctime.tv_nsec,
lower_inode->i_ctime.tv_sec,
lower_inode->i_ctime.tv_nsec);
}
}
}
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);
}
/* This must be called with the super block already locked. */
int unionfs_ioctl_delbranch(struct super_block *sb, unsigned long arg)
{
struct dentry *hidden_dentry;
struct inode *hidden_inode;
struct super_block *hidden_sb;
struct vfsmount *hidden_mnt;
struct dentry *root_dentry;
struct inode *root_inode;
int err = 0;
int pmindex, i, gen;
print_entry("branch = %lu ", arg);
lock_dentry(sb->s_root);
err = -EBUSY;
if (sbmax(sb) == 1)
goto out;
err = -EINVAL;
if (arg < 0 || arg > stopd(sb)->b_end)
goto out;
err = -EBUSY;
if (branch_count(sb, arg))
goto out;
if ((err = newputmap(sb)))
goto out;
pmindex = stopd(sb)->usi_lastputmap;
pmindex -= stopd(sb)->usi_firstputmap;
atomic_inc(&stopd(sb)->usi_generation);
gen = atomic_read(&stopd(sb)->usi_generation);
root_dentry = sb->s_root;
root_inode = sb->s_root->d_inode;
hidden_dentry = dtohd_index(root_dentry, arg);
hidden_mnt = stohiddenmnt_index(sb, arg);
hidden_inode = itohi_index(root_inode, arg);
hidden_sb = stohs_index(sb, arg);
DPUT(hidden_dentry);
iput(hidden_inode);
mntput(hidden_mnt);
for (i = arg; i <= (sbend(sb) - 1); i++) {
set_branch_count(sb, i, branch_count(sb, i + 1));
set_stohiddenmnt_index(sb, i, stohiddenmnt_index(sb, i + 1));
set_stohs_index(sb, i, stohs_index(sb, i + 1));
set_branchperms(sb, i, branchperms(sb, i + 1));
set_dtohd_index(root_dentry, i,
dtohd_index(root_dentry, i + 1));
set_itohi_index(root_inode, i, itohi_index(root_inode, i + 1));
stopd(sb)->usi_putmaps[pmindex]->map[i + 1] = i;
}
set_dtohd_index(root_dentry, sbend(sb), NULL);
set_itohi_index(root_inode, sbend(sb), NULL);
set_stohiddenmnt_index(sb, sbend(sb), NULL);
set_stohs_index(sb, sbend(sb), NULL);
stopd(sb)->b_end--;
set_dbend(root_dentry, dbend(root_dentry) - 1);
dtopd(root_dentry)->udi_bcount--;
itopd(root_inode)->b_end--;
atomic_set(&dtopd(root_dentry)->udi_generation, gen);
atomic_set(&itopd(root_inode)->uii_generation, gen);
fixputmaps(sb);
/* This doesn't open a file, so we might have to free the map here. */
if (atomic_read(&stopd(sb)->usi_putmaps[pmindex]->count) == 0) {
KFREE(stopd(sb)->usi_putmaps[pmindex]);
stopd(sb)->usi_putmaps[pmindex] = NULL;
}
out:
unlock_dentry(sb->s_root);
print_exit_status(err);
return err;
}
/*
* Connect a unionfs inode dentry/inode with several lower ones. This is
* the classic stackable file system "vnode interposition" action.
*
* @sb: unionfs's super_block
*/
struct dentry *unionfs_interpose(struct dentry *dentry, struct super_block *sb,
int flag)
{
int err = 0;
struct inode *inode;
int need_fill_inode = 1;
struct dentry *spliced = NULL;
verify_locked(dentry);
/*
* We allocate our new inode below, by calling iget.
* iget will call our read_inode which will initialize some
* of the new inode's fields
*/
/*
* On revalidate we've already got our own inode and just need
* to fix it up.
*/
if (flag == INTERPOSE_REVAL) {
inode = dentry->d_inode;
UNIONFS_I(inode)->bstart = -1;
UNIONFS_I(inode)->bend = -1;
atomic_set(&UNIONFS_I(inode)->generation,
atomic_read(&UNIONFS_SB(sb)->generation));
UNIONFS_I(inode)->lower_inodes =
kcalloc(sbmax(sb), sizeof(struct inode *), GFP_KERNEL);
if (unlikely(!UNIONFS_I(inode)->lower_inodes)) {
err = -ENOMEM;
goto out;
}
} else {
/* get unique inode number for unionfs */
inode = iget(sb, iunique(sb, UNIONFS_ROOT_INO));
if (!inode) {
err = -EACCES;
goto out;
}
if (atomic_read(&inode->i_count) > 1)
goto skip;
}
need_fill_inode = 0;
unionfs_fill_inode(dentry, inode);
skip:
/* only (our) lookup wants to do a d_add */
switch (flag) {
case INTERPOSE_DEFAULT:
/* for operations which create new inodes */
d_add(dentry, inode);
break;
case INTERPOSE_REVAL_NEG:
d_instantiate(dentry, inode);
break;
case INTERPOSE_LOOKUP:
spliced = d_splice_alias(inode, dentry);
if (spliced && spliced != dentry) {
/*
* d_splice can return a dentry if it was
* disconnected and had to be moved. We must ensure
* that the private data of the new dentry is
* correct and that the inode info was filled
* properly. Finally we must return this new
* dentry.
*/
spliced->d_op = &unionfs_dops;
spliced->d_fsdata = dentry->d_fsdata;
dentry->d_fsdata = NULL;
dentry = spliced;
if (need_fill_inode) {
need_fill_inode = 0;
unionfs_fill_inode(dentry, inode);
}
goto out_spliced;
} else if (!spliced) {
if (need_fill_inode) {
need_fill_inode = 0;
unionfs_fill_inode(dentry, inode);
goto out_spliced;
}
}
break;
case INTERPOSE_REVAL:
/* Do nothing. */
break;
default:
printk(KERN_CRIT "unionfs: invalid interpose flag passed!\n");
BUG();
}
goto out;
out_spliced:
if (!err)
return spliced;
out:
return ERR_PTR(err);
}
/* allocate new dentry private data, free old one if necessary */
int new_dentry_private_data(struct dentry *dentry)
{
int newsize;
int oldsize = 0;
struct unionfs_dentry_info *info = UNIONFS_D(dentry);
spin_lock(&dentry->d_lock);
if (!info) {
dentry->d_fsdata = kmem_cache_alloc(unionfs_dentry_cachep,
GFP_ATOMIC);
info = UNIONFS_D(dentry);
if (!info)
goto out;
mutex_init(&info->lock);
mutex_lock(&info->lock);
info->lower_paths = NULL;
} else
oldsize = sizeof(struct path) * info->bcount;
info->bstart = -1;
info->bend = -1;
info->bopaque = -1;
info->bcount = sbmax(dentry->d_sb);
atomic_set(&info->generation,
atomic_read(&UNIONFS_SB(dentry->d_sb)->generation));
newsize = sizeof(struct path) * sbmax(dentry->d_sb);
/* Don't reallocate when we already have enough space. */
/* It would be ideal if we could actually use the slab macros to
* determine what our object sizes is, but those are not exported.
*/
if (oldsize) {
int minsize = malloc_sizes[0].cs_size;
if (!newsize || ((oldsize < newsize) && (newsize > minsize))) {
kfree(info->lower_paths);
info->lower_paths = NULL;
}
}
if (!info->lower_paths && newsize) {
info->lower_paths = kmalloc(newsize, GFP_ATOMIC);
if (!info->lower_paths)
goto out_free;
}
memset(info->lower_paths, 0, (oldsize > newsize ? oldsize : newsize));
spin_unlock(&dentry->d_lock);
return 0;
out_free:
kfree(info->lower_paths);
out:
free_dentry_private_data(info);
dentry->d_fsdata = NULL;
spin_unlock(&dentry->d_lock);
return -ENOMEM;
}
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;
}
/*
* Helper function for unionfs_file_revalidate/locked.
* Expects dentry/parent to be locked already, and revalidated.
*/
static int __unionfs_file_revalidate(struct file *file, struct dentry *dentry,
struct dentry *parent,
struct super_block *sb, int sbgen,
int dgen, bool willwrite)
{
int fgen;
int bstart, bend, orig_brid;
int size;
int err = 0;
fgen = atomic_read(&UNIONFS_F(file)->generation);
/*
* There are two cases we are interested in. The first is if the
* generation is lower than the super-block. The second is if
* someone has copied up this file from underneath us, we also need
* to refresh things.
*/
if (d_deleted(dentry) ||
(sbgen <= fgen &&
dbstart(dentry) == fbstart(file) &&
unionfs_lower_file(file)))
goto out_may_copyup;
/* save orig branch ID */
orig_brid = UNIONFS_F(file)->saved_branch_ids[fbstart(file)];
/* First we throw out the existing files. */
cleanup_file(file);
/* Now we reopen the file(s) as in unionfs_open. */
bstart = fbstart(file) = dbstart(dentry);
bend = fbend(file) = dbend(dentry);
size = sizeof(struct file *) * sbmax(sb);
UNIONFS_F(file)->lower_files = kzalloc(size, GFP_KERNEL);
if (unlikely(!UNIONFS_F(file)->lower_files)) {
err = -ENOMEM;
goto out;
}
size = sizeof(int) * sbmax(sb);
UNIONFS_F(file)->saved_branch_ids = kzalloc(size, GFP_KERNEL);
if (unlikely(!UNIONFS_F(file)->saved_branch_ids)) {
err = -ENOMEM;
goto out;
}
if (S_ISDIR(dentry->d_inode->i_mode)) {
/* We need to open all the files. */
err = open_all_files(file);
if (err)
goto out;
} else {
int new_brid;
/* We only open the highest priority branch. */
err = open_highest_file(file, willwrite);
if (err)
goto out;
new_brid = UNIONFS_F(file)->saved_branch_ids[fbstart(file)];
if (unlikely(new_brid != orig_brid && sbgen > fgen)) {
/*
* If we re-opened the file on a different branch
* than the original one, and this was due to a new
* branch inserted, then update the mnt counts of
* the old and new branches accordingly.
*/
unionfs_mntget(dentry, bstart);
unionfs_mntput(sb->s_root,
branch_id_to_idx(sb, orig_brid));
}
/* regular files have only one open lower file */
fbend(file) = fbstart(file);
}
atomic_set(&UNIONFS_F(file)->generation,
atomic_read(&UNIONFS_I(dentry->d_inode)->generation));
out_may_copyup:
/* Copyup on the first write to a file on a readonly branch. */
if (willwrite && IS_WRITE_FLAG(file->f_flags) &&
!IS_WRITE_FLAG(unionfs_lower_file(file)->f_flags) &&
is_robranch(dentry)) {
pr_debug("unionfs: do delay copyup of \"%s\"\n",
dentry->d_name.name);
err = do_delayed_copyup(file, parent);
/* regular files have only one open lower file */
if (!err && !S_ISDIR(dentry->d_inode->i_mode))
fbend(file) = fbstart(file);
}
out:
if (err) {
kfree(UNIONFS_F(file)->lower_files);
kfree(UNIONFS_F(file)->saved_branch_ids);
}
return err;
}
int new_dentry_private_data(struct dentry *dentry)
{
int newsize;
int oldsize = 0;
spin_lock(&dentry->d_lock);
if (!dtopd_nocheck(dentry)) {
dtopd_lhs(dentry) = (struct unionfs_dentry_info *)
kmem_cache_alloc(unionfs_dentry_cachep, SLAB_ATOMIC);
if (!dtopd_nocheck(dentry))
goto out;
init_MUTEX_LOCKED(&dtopd_nocheck(dentry)->udi_sem);
#ifdef TRACKLOCK
printk("INITLOCK:%p\n", dentry);
#endif
dtohd_ptr(dentry) = NULL;
} else {
oldsize = sizeof(struct dentry *) * dtopd(dentry)->udi_bcount;
}
dtopd_nocheck(dentry)->udi_bstart = -1;
dtopd_nocheck(dentry)->udi_bend = -1;
dtopd_nocheck(dentry)->udi_bopaque = -1;
dtopd_nocheck(dentry)->udi_bcount = sbmax(dentry->d_sb);
atomic_set(&dtopd_nocheck(dentry)->udi_generation,
atomic_read(&stopd(dentry->d_sb)->usi_generation));
newsize = sizeof(struct dentry *) * sbmax(dentry->d_sb);
/* Don't reallocate when we already have enough space. */
/* It would be ideal if we could actually use the slab macros to
* determine what our object sizes is, but those are not exported.
*/
if (oldsize) {
int minsize = malloc_sizes[0].cs_size;
if (!newsize || ((oldsize < newsize) && (newsize > minsize))) {
KFREE(dtohd_ptr(dentry));
dtohd_ptr(dentry) = NULL;
}
}
if (!dtohd_ptr(dentry) && newsize) {
dtohd_ptr(dentry) = KMALLOC(newsize, GFP_ATOMIC);
if (!dtohd_ptr(dentry))
goto out;
}
if (oldsize > newsize)
memset(dtohd_ptr(dentry), 0, oldsize);
else
memset(dtohd_ptr(dentry), 0, newsize);
spin_unlock(&dentry->d_lock);
return 0;
out:
free_dentry_private_data(dtopd_nocheck(dentry));
dtopd_lhs(dentry) = NULL;
spin_unlock(&dentry->d_lock);
return -ENOMEM;
}
struct dentry *unionfs_lookup_backend(struct dentry *dentry, 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;
int locked_parent = 0;
int locked_child = 0;
int opaque;
char *whname = NULL;
const char *name;
int namelen;
print_entry("mode = %d", lookupmode);
/* 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(dtopd_nocheck(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 = GET_PARENT(dentry);
/* We never partial lookup the root directory. */
if (parent_dentry != dentry) {
lock_dentry(parent_dentry);
locked_parent = 1;
} else {
DPUT(parent_dentry);
parent_dentry = NULL;
goto out;
}
fist_print_dentry("IN unionfs_lookup (parent)", parent_dentry);
fist_print_dentry("IN unionfs_lookup (child)", dentry);
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;
}
fist_dprint(8, "bstart = %d, bend = %d\n", bstart, bend);
for (bindex = bstart; bindex <= bend; bindex++) {
hidden_dentry = dtohd_index(dentry, bindex);
if (lookupmode == INTERPOSE_PARTIAL && hidden_dentry)
continue;
BUG_ON(hidden_dentry != NULL);
hidden_dir_dentry = dtohd_index(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 + WHLEN);
if (IS_ERR(wh_hidden_dentry)) {
DPUT(first_hidden_dentry);
err = PTR_ERR(wh_hidden_dentry);
goto out_free;
}
if (wh_hidden_dentry->d_inode) {
/* We found a whiteout so lets give up. */
fist_dprint(8, "whiteout found in %d\n", bindex);
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);
goto out_free;
}
DPUT(wh_hidden_dentry);
wh_hidden_dentry = NULL;
/* Now do regular lookup; lookup foo */
hidden_dentry = LOOKUP_ONE_LEN(name, hidden_dir_dentry,
namelen);
fist_print_generic_dentry("hidden result", hidden_dentry);
if (IS_ERR(hidden_dentry)) {
DPUT(first_hidden_dentry);
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;
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);
set_dtohd_index(dentry, bindex, hidden_dentry);
set_dbend(dentry, bindex);
/* update parent directory's atime with the bindex */
fist_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(dtohd(dentry)->d_inode->i_mode));
continue;
}
opaque = is_opaque_dir(dentry, bindex);
if (opaque < 0) {
DPUT(first_hidden_dentry);
err = opaque;
goto out_free;
}
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) {
itopd(dentry->d_inode)->uii_stale = 1;
}
goto out;
}
/* This should only happen if we found a whiteout. */
if (first_dentry_offset == -1) {
first_hidden_dentry = LOOKUP_ONE_LEN(name, hidden_dir_dentry,
namelen);
first_dentry_offset = bindex;
if (IS_ERR(first_hidden_dentry)) {
err = PTR_ERR(first_hidden_dentry);
goto out;
}
}
set_dtohd_index(dentry, first_dentry_offset, first_hidden_dentry);
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 throw it out. */
DPUT(first_hidden_dentry);
/* 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;
fist_checkinode(dentry->d_inode, "unionfs_lookup OUT: child");
fist_checkinode(parent_dentry->d_inode, "unionfs_lookup OUT: dir");
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(dtohd_index(dentry, bindex));
}
KFREE(dtohd_ptr(dentry));
dtohd_ptr(dentry) = NULL;
set_dbstart(dentry, -1);
set_dbend(dentry, -1);
out:
if (!err && dtopd(dentry)) {
BUG_ON(dbend(dentry) > dtopd(dentry)->udi_bcount);
BUG_ON(dbend(dentry) > sbmax(dentry->d_sb));
BUG_ON(dbstart(dentry) < 0);
}
KFREE(whname);
fist_print_dentry("OUT unionfs_lookup (parent)", parent_dentry);
fist_print_dentry("OUT unionfs_lookup (child)", dentry);
if (locked_parent)
unlock_dentry(parent_dentry);
DPUT(parent_dentry);
if (locked_child)
unlock_dentry(dentry);
print_exit_status(err);
return ERR_PTR(err);
}
/* sb we pass is unionfs's super_block */
int unionfs_interpose(struct dentry *dentry, struct super_block *sb, int flag)
{
struct inode *hidden_inode;
struct dentry *hidden_dentry;
int err = 0;
struct inode *inode;
int is_negative_dentry = 1;
int bindex, bstart, bend;
print_entry("flag = %d", flag);
verify_locked(dentry);
fist_print_dentry("In unionfs_interpose", dentry);
bstart = dbstart(dentry);
bend = dbend(dentry);
/* Make sure that we didn't get a negative dentry. */
for (bindex = bstart; bindex <= bend; bindex++) {
if (dtohd_index(dentry, bindex) &&
dtohd_index(dentry, bindex)->d_inode) {
is_negative_dentry = 0;
break;
}
}
BUG_ON(is_negative_dentry);
/* We allocate our new inode below, by calling iget.
* iget will call our read_inode which will initialize some
* of the new inode's fields
*/
/* On revalidate we've already got our own inode and just need
* to fix it up. */
if (flag == INTERPOSE_REVAL) {
inode = dentry->d_inode;
itopd(inode)->b_start = -1;
itopd(inode)->b_end = -1;
atomic_set(&itopd(inode)->uii_generation,
atomic_read(&stopd(sb)->usi_generation));
itohi_ptr(inode) =
KZALLOC(sbmax(sb) * sizeof(struct inode *), GFP_KERNEL);
if (!itohi_ptr(inode)) {
err = -ENOMEM;
goto out;
}
} else {
ino_t ino;
/* get unique inode number for unionfs */
#ifdef UNIONFS_IMAP
if (stopd(sb)->usi_persistent) {
err = read_uin(sb, bindex,
dtohd_index(dentry,
bindex)->d_inode->i_ino,
O_CREAT, &ino);
if (err)
goto out;
} else
#endif
ino = iunique(sb, UNIONFS_ROOT_INO);
inode = IGET(sb, ino);
if (!inode) {
err = -EACCES; /* should be impossible??? */
goto out;
}
}
down(&inode->i_sem);
if (atomic_read(&inode->i_count) > 1)
goto skip;
for (bindex = bstart; bindex <= bend; bindex++) {
hidden_dentry = dtohd_index(dentry, bindex);
if (!hidden_dentry) {
set_itohi_index(inode, bindex, NULL);
continue;
}
/* Initialize the hidden inode to the new hidden inode. */
if (!hidden_dentry->d_inode)
continue;
set_itohi_index(inode, bindex, IGRAB(hidden_dentry->d_inode));
}
ibstart(inode) = dbstart(dentry);
ibend(inode) = dbend(dentry);
/* Use attributes from the first branch. */
hidden_inode = itohi(inode);
/* Use different set of inode ops for symlinks & directories */
if (S_ISLNK(hidden_inode->i_mode))
inode->i_op = &unionfs_symlink_iops;
else if (S_ISDIR(hidden_inode->i_mode))
inode->i_op = &unionfs_dir_iops;
/* Use different set of file ops for directories */
if (S_ISDIR(hidden_inode->i_mode))
inode->i_fop = &unionfs_dir_fops;
/* properly initialize special inodes */
if (S_ISBLK(hidden_inode->i_mode) || S_ISCHR(hidden_inode->i_mode) ||
S_ISFIFO(hidden_inode->i_mode) || S_ISSOCK(hidden_inode->i_mode))
init_special_inode(inode, hidden_inode->i_mode,
hidden_inode->i_rdev);
/* Fix our inode's address operations to that of the lower inode (Unionfs is FiST-Lite) */
if (inode->i_mapping->a_ops != hidden_inode->i_mapping->a_ops) {
fist_dprint(7, "fixing inode 0x%p a_ops (0x%p -> 0x%p)\n",
inode, inode->i_mapping->a_ops,
hidden_inode->i_mapping->a_ops);
inode->i_mapping->a_ops = hidden_inode->i_mapping->a_ops;
}
/* all well, copy inode attributes */
fist_copy_attr_all(inode, hidden_inode);
skip:
/* only (our) lookup wants to do a d_add */
switch (flag) {
case INTERPOSE_DEFAULT:
case INTERPOSE_REVAL_NEG:
d_instantiate(dentry, inode);
break;
case INTERPOSE_LOOKUP:
err = PTR_ERR(d_splice_alias(inode, dentry));
break;
case INTERPOSE_REVAL:
/* Do nothing. */
break;
default:
printk(KERN_ERR "Invalid interpose flag passed!");
BUG();
}
fist_print_dentry("Leaving unionfs_interpose", dentry);
fist_print_inode("Leaving unionfs_interpose", inode);
up(&inode->i_sem);
out:
print_exit_status(err);
return err;
}
