/*
* extended version of au_h_dptr().
* returns a hashed and positive h_dentry in bindex, NULL, or error.
*/
struct dentry *au_h_d_alias(struct dentry *dentry, aufs_bindex_t bindex)
{
struct dentry *h_dentry;
struct inode *inode, *h_inode;
inode = dentry->d_inode;
AuDebugOn(!inode);
h_dentry = NULL;
if (au_dbstart(dentry) <= bindex
&& bindex <= au_dbend(dentry))
h_dentry = au_h_dptr(dentry, bindex);
if (h_dentry && !au_d_hashed_positive(h_dentry)) {
dget(h_dentry);
goto out; /* success */
}
AuDebugOn(bindex < au_ibstart(inode));
AuDebugOn(au_ibend(inode) < bindex);
h_inode = au_h_iptr(inode, bindex);
h_dentry = d_find_alias(h_inode);
if (h_dentry) {
if (!IS_ERR(h_dentry)) {
if (!au_d_hashed_positive(h_dentry))
goto out; /* success */
dput(h_dentry);
} else
goto out;
}
if (au_opt_test(au_mntflags(dentry->d_sb), PLINK)) {
h_dentry = au_plink_lkup(inode, bindex);
AuDebugOn(!h_dentry);
if (!IS_ERR(h_dentry)) {
if (!au_d_hashed_positive(h_dentry))
goto out; /* success */
dput(h_dentry);
h_dentry = NULL;
}
}
out:
AuDbgDentry(h_dentry);
return h_dentry;
}
/*
* when an error happened, remove the created whiteout and revert everything.
*/
static int do_revert(int err, struct inode *dir, aufs_bindex_t bindex,
aufs_bindex_t bwh, struct dentry *wh_dentry,
struct dentry *dentry, struct au_dtime *dt)
{
int rerr;
struct path h_path = {
.dentry = wh_dentry,
.mnt = au_sbr_mnt(dir->i_sb, bindex)
};
rerr = au_wh_unlink_dentry(au_h_iptr(dir, bindex), &h_path, dentry);
if (!rerr) {
au_set_dbwh(dentry, bwh);
au_dtime_revert(dt);
return 0;
}
AuIOErr("%.*s reverting whiteout failed(%d, %d)\n",
AuDLNPair(dentry), err, rerr);
return -EIO;
}
/* ---------------------------------------------------------------------- */
int aufs_unlink(struct inode *dir, struct dentry *dentry)
{
int err;
aufs_bindex_t bwh, bindex, bstart;
struct au_dtime dt;
struct au_pin pin;
struct path h_path;
struct inode *inode, *h_dir;
struct dentry *parent, *wh_dentry;
IMustLock(dir);
err = aufs_read_lock(dentry, AuLock_DW | AuLock_GEN);
if (unlikely(err))
goto out;
err = au_d_hashed_positive(dentry);
if (unlikely(err))
goto out_unlock;
inode = dentry->d_inode;
IMustLock(inode);
err = -EISDIR;
if (unlikely(S_ISDIR(inode->i_mode)))
goto out_unlock; /* possible? */
bstart = au_dbstart(dentry);
bwh = au_dbwh(dentry);
bindex = -1;
parent = dentry->d_parent; /* dir inode is locked */
di_write_lock_parent(parent);
wh_dentry = lock_hdir_create_wh(dentry, /*isdir*/0, &bindex, &dt, &pin);
err = PTR_ERR(wh_dentry);
if (IS_ERR(wh_dentry))
goto out_parent;
h_path.mnt = au_sbr_mnt(dentry->d_sb, bstart);
h_path.dentry = au_h_dptr(dentry, bstart);
dget(h_path.dentry);
if (bindex == bstart) {
h_dir = au_pinned_h_dir(&pin);
err = vfsub_unlink(h_dir, &h_path, /*force*/0);
} else {
/* dir inode is locked */
h_dir = wh_dentry->d_parent->d_inode;
IMustLock(h_dir);
err = 0;
}
if (!err) {
vfsub_drop_nlink(inode);
epilog(dir, dentry, bindex);
/* update target timestamps */
if (bindex == bstart) {
vfsub_update_h_iattr(&h_path, /*did*/NULL); /*ignore*/
inode->i_ctime = h_path.dentry->d_inode->i_ctime;
} else
/* todo: this timestamp may be reverted later */
inode->i_ctime = h_dir->i_ctime;
goto out_unpin; /* success */
}
/* revert */
if (wh_dentry) {
int rerr;
rerr = do_revert(err, dir, bindex, bwh, wh_dentry, dentry, &dt);
if (rerr)
err = rerr;
}
out_unpin:
au_unpin(&pin);
dput(wh_dentry);
dput(h_path.dentry);
out_parent:
di_write_unlock(parent);
out_unlock:
aufs_read_unlock(dentry, AuLock_DW);
out:
return err;
}
int aufs_rename(struct inode *_src_dir, struct dentry *_src_dentry,
struct inode *_dst_dir, struct dentry *_dst_dentry)
{
int err, flags;
/* reduce stack space */
struct au_ren_args *a;
AuDbg("%.*s, %.*s\n", AuDLNPair(_src_dentry), AuDLNPair(_dst_dentry));
IMustLock(_src_dir);
IMustLock(_dst_dir);
err = -ENOMEM;
BUILD_BUG_ON(sizeof(*a) > PAGE_SIZE);
a = kzalloc(sizeof(*a), GFP_NOFS);
if (unlikely(!a))
goto out;
a->src_dir = _src_dir;
a->src_dentry = _src_dentry;
a->src_inode = a->src_dentry->d_inode;
a->src_parent = a->src_dentry->d_parent; /* dir inode is locked */
a->dst_dir = _dst_dir;
a->dst_dentry = _dst_dentry;
a->dst_inode = a->dst_dentry->d_inode;
a->dst_parent = a->dst_dentry->d_parent; /* dir inode is locked */
if (a->dst_inode) {
IMustLock(a->dst_inode);
au_igrab(a->dst_inode);
}
err = -ENOTDIR;
flags = AuLock_FLUSH | AuLock_NOPLM | AuLock_GEN;
if (S_ISDIR(a->src_inode->i_mode)) {
au_fset_ren(a->flags, ISDIR);
if (unlikely(a->dst_inode && !S_ISDIR(a->dst_inode->i_mode)))
goto out_free;
err = aufs_read_and_write_lock2(a->dst_dentry, a->src_dentry,
AuLock_DIR | flags);
} else
err = aufs_read_and_write_lock2(a->dst_dentry, a->src_dentry,
flags);
if (unlikely(err))
goto out_free;
err = au_d_hashed_positive(a->src_dentry);
if (unlikely(err))
goto out_unlock;
err = -ENOENT;
if (a->dst_inode) {
/*
* If it is a dir, VFS unhash dst_dentry before this
* function. It means we cannot rely upon d_unhashed().
*/
if (unlikely(!a->dst_inode->i_nlink))
goto out_unlock;
if (!S_ISDIR(a->dst_inode->i_mode)) {
err = au_d_hashed_positive(a->dst_dentry);
if (unlikely(err))
goto out_unlock;
} else if (unlikely(IS_DEADDIR(a->dst_inode)))
goto out_unlock;
} else if (unlikely(d_unhashed(a->dst_dentry)))
goto out_unlock;
au_fset_ren(a->flags, ISSAMEDIR); /* temporary */
di_write_lock_parent(a->dst_parent);
/* which branch we process */
err = au_ren_wbr(a);
if (unlikely(err < 0))
goto out_parent;
a->br = au_sbr(a->dst_dentry->d_sb, a->btgt);
a->h_path.mnt = a->br->br_mnt;
/* are they available to be renamed */
err = au_ren_may_dir(a);
if (unlikely(err))
goto out_children;
/* prepare the writable parent dir on the same branch */
if (a->dst_bstart == a->btgt) {
au_fset_ren(a->flags, WHDST);
} else {
err = au_cpup_dirs(a->dst_dentry, a->btgt);
if (unlikely(err))
goto out_children;
}
if (a->src_dir != a->dst_dir) {
/*
* this temporary unlock is safe,
* because both dir->i_mutex are locked.
*/
di_write_unlock(a->dst_parent);
di_write_lock_parent(a->src_parent);
err = au_wr_dir_need_wh(a->src_dentry,
au_ftest_ren(a->flags, ISDIR),
&a->btgt);
di_write_unlock(a->src_parent);
di_write_lock2_parent(a->src_parent, a->dst_parent, /*isdir*/1);
au_fclr_ren(a->flags, ISSAMEDIR);
} else
err = au_wr_dir_need_wh(a->src_dentry,
au_ftest_ren(a->flags, ISDIR),
&a->btgt);
if (unlikely(err < 0))
goto out_children;
if (err)
au_fset_ren(a->flags, WHSRC);
/* lock them all */
err = au_ren_lock(a);
if (unlikely(err))
goto out_children;
if (!au_opt_test(au_mntflags(a->dst_dir->i_sb), UDBA_NONE))
err = au_may_ren(a);
else if (unlikely(a->dst_dentry->d_name.len > AUFS_MAX_NAMELEN))
err = -ENAMETOOLONG;
if (unlikely(err))
goto out_hdir;
/* store timestamps to be revertible */
au_ren_dt(a);
/* here we go */
err = do_rename(a);
if (unlikely(err))
goto out_dt;
/* update dir attributes */
au_ren_refresh_dir(a);
/* dput/iput all lower dentries */
au_ren_refresh(a);
goto out_hdir; /* success */
out_dt:
au_ren_rev_dt(err, a);
out_hdir:
au_ren_unlock(a);
out_children:
au_nhash_wh_free(&a->whlist);
if (err && a->dst_inode && a->dst_bstart != a->btgt) {
AuDbg("bstart %d, btgt %d\n", a->dst_bstart, a->btgt);
au_set_h_dptr(a->dst_dentry, a->btgt, NULL);
au_set_dbstart(a->dst_dentry, a->dst_bstart);
}
out_parent:
if (!err)
d_move(a->src_dentry, a->dst_dentry);
else {
au_update_dbstart(a->dst_dentry);
if (!a->dst_inode)
d_drop(a->dst_dentry);
}
if (au_ftest_ren(a->flags, ISSAMEDIR))
di_write_unlock(a->dst_parent);
else
di_write_unlock2(a->src_parent, a->dst_parent);
out_unlock:
aufs_read_and_write_unlock2(a->dst_dentry, a->src_dentry);
out_free:
iput(a->dst_inode);
if (a->thargs)
au_whtmp_rmdir_free(a->thargs);
kfree(a);
out:
AuTraceErr(err);
return err;
}
int aufs_link(struct dentry *src_dentry, struct inode *dir,
struct dentry *dentry)
{
int err, rerr;
struct au_dtime dt;
struct au_link_args *a;
struct dentry *wh_dentry, *h_src_dentry;
struct inode *inode;
struct super_block *sb;
struct au_wr_dir_args wr_dir_args = {
/* .force_btgt = -1, */
.flags = AuWrDir_ADD_ENTRY
};
IMustLock(dir);
inode = src_dentry->d_inode;
IMustLock(inode);
err = -ENOMEM;
a = kzalloc(sizeof(*a), GFP_NOFS);
if (unlikely(!a))
goto out;
a->parent = dentry->d_parent; /* dir inode is locked */
err = aufs_read_and_write_lock2(dentry, src_dentry,
AuLock_NOPLM | AuLock_GEN);
if (unlikely(err))
goto out_kfree;
err = au_d_hashed_positive(src_dentry);
if (unlikely(err))
goto out_unlock;
err = au_d_may_add(dentry);
if (unlikely(err))
goto out_unlock;
a->src_parent = dget_parent(src_dentry);
wr_dir_args.force_btgt = au_ibstart(inode);
di_write_lock_parent(a->parent);
wr_dir_args.force_btgt = au_wbr(dentry, wr_dir_args.force_btgt);
wh_dentry = lock_hdir_lkup_wh(dentry, &dt, src_dentry, &a->pin,
&wr_dir_args);
err = PTR_ERR(wh_dentry);
if (IS_ERR(wh_dentry))
goto out_parent;
err = 0;
sb = dentry->d_sb;
a->bdst = au_dbstart(dentry);
a->h_path.dentry = au_h_dptr(dentry, a->bdst);
a->h_path.mnt = au_sbr_mnt(sb, a->bdst);
a->bsrc = au_ibstart(inode);
h_src_dentry = au_h_d_alias(src_dentry, a->bsrc);
if (!h_src_dentry) {
a->bsrc = au_dbstart(src_dentry);
h_src_dentry = au_h_d_alias(src_dentry, a->bsrc);
AuDebugOn(!h_src_dentry);
} else if (IS_ERR(h_src_dentry))
goto out_parent;
if (au_opt_test(au_mntflags(sb), PLINK)) {
if (a->bdst < a->bsrc
/* && h_src_dentry->d_sb != a->h_path.dentry->d_sb */)
err = au_cpup_or_link(src_dentry, a);
else
err = vfsub_link(h_src_dentry, au_pinned_h_dir(&a->pin),
&a->h_path);
dput(h_src_dentry);
} else {
/*
* copyup src_dentry to the branch we process,
* and then link(2) to it.
*/
dput(h_src_dentry);
if (a->bdst < a->bsrc
/* && h_src_dentry->d_sb != a->h_path.dentry->d_sb */) {
au_unpin(&a->pin);
di_write_unlock(a->parent);
err = au_cpup_before_link(src_dentry, a);
di_write_lock_parent(a->parent);
if (!err)
err = au_pin(&a->pin, dentry, a->bdst,
au_opt_udba(sb),
AuPin_DI_LOCKED | AuPin_MNT_WRITE);
if (unlikely(err))
goto out_wh;
}
if (!err) {
h_src_dentry = au_h_dptr(src_dentry, a->bdst);
err = -ENOENT;
if (h_src_dentry && h_src_dentry->d_inode)
err = vfsub_link(h_src_dentry,
au_pinned_h_dir(&a->pin),
&a->h_path);
}
}
if (unlikely(err))
goto out_unpin;
if (wh_dentry) {
a->h_path.dentry = wh_dentry;
err = au_wh_unlink_dentry(au_pinned_h_dir(&a->pin), &a->h_path,
dentry);
if (unlikely(err))
goto out_revert;
}
dir->i_version++;
if (au_ibstart(dir) == au_dbstart(dentry))
au_cpup_attr_timesizes(dir);
inc_nlink(inode);
inode->i_ctime = dir->i_ctime;
d_instantiate(dentry, au_igrab(inode));
if (d_unhashed(a->h_path.dentry))
/* some filesystem calls d_drop() */
d_drop(dentry);
goto out_unpin; /* success */
out_revert:
rerr = vfsub_unlink(au_pinned_h_dir(&a->pin), &a->h_path, /*force*/0);
if (unlikely(rerr)) {
AuIOErr("%.*s reverting failed(%d, %d)\n",
AuDLNPair(dentry), err, rerr);
err = -EIO;
}
au_dtime_revert(&dt);
out_unpin:
au_unpin(&a->pin);
out_wh:
dput(wh_dentry);
out_parent:
di_write_unlock(a->parent);
dput(a->src_parent);
out_unlock:
if (unlikely(err)) {
au_update_dbstart(dentry);
d_drop(dentry);
}
aufs_read_and_write_unlock2(dentry, src_dentry);
out_kfree:
kfree(a);
out:
return err;
}
/*
* when an error happened, remove the created whiteout and revert everything.
*/
static int do_revert(int err, struct inode *dir, aufs_bindex_t bindex,
aufs_bindex_t bwh, struct dentry *wh_dentry,
struct dentry *dentry, struct au_dtime *dt)
{
int rerr;
struct path h_path = {
.dentry = wh_dentry,
.mnt = au_sbr_mnt(dir->i_sb, bindex)
};
rerr = au_wh_unlink_dentry(au_h_iptr(dir, bindex), &h_path, dentry);
if (!rerr) {
au_set_dbwh(dentry, bwh);
au_dtime_revert(dt);
return 0;
}
AuIOErr("%pd reverting whiteout failed(%d, %d)\n", dentry, err, rerr);
return -EIO;
}
/* ---------------------------------------------------------------------- */
int aufs_unlink(struct inode *dir, struct dentry *dentry)
{
int err;
aufs_bindex_t bwh, bindex, bstart;
struct inode *inode, *h_dir, *delegated;
struct dentry *parent, *wh_dentry;
/* to reuduce stack size */
struct {
struct au_dtime dt;
struct au_pin pin;
struct path h_path;
} *a;
IMustLock(dir);
err = -ENOMEM;
a = kmalloc(sizeof(*a), GFP_NOFS);
if (unlikely(!a))
goto out;
err = aufs_read_lock(dentry, AuLock_DW | AuLock_GEN);
if (unlikely(err))
goto out_free;
err = au_d_hashed_positive(dentry);
if (unlikely(err))
goto out_unlock;
inode = d_inode(dentry);
IMustLock(inode);
err = -EISDIR;
if (unlikely(d_is_dir(dentry)))
goto out_unlock; /* possible? */
bstart = au_dbstart(dentry);
bwh = au_dbwh(dentry);
bindex = -1;
parent = dentry->d_parent; /* dir inode is locked */
di_write_lock_parent(parent);
wh_dentry = lock_hdir_create_wh(dentry, /*isdir*/0, &bindex, &a->dt,
&a->pin);
err = PTR_ERR(wh_dentry);
if (IS_ERR(wh_dentry))
goto out_parent;
a->h_path.mnt = au_sbr_mnt(dentry->d_sb, bstart);
a->h_path.dentry = au_h_dptr(dentry, bstart);
dget(a->h_path.dentry);
if (bindex == bstart) {
h_dir = au_pinned_h_dir(&a->pin);
delegated = NULL;
err = vfsub_unlink(h_dir, &a->h_path, &delegated, /*force*/0);
if (unlikely(err == -EWOULDBLOCK)) {
pr_warn("cannot retry for NFSv4 delegation"
" for an internal unlink\n");
iput(delegated);
}
} else {
/* dir inode is locked */
h_dir = d_inode(wh_dentry->d_parent);
IMustLock(h_dir);
err = 0;
}
if (!err) {
vfsub_drop_nlink(inode);
epilog(dir, dentry, bindex);
/* update target timestamps */
if (bindex == bstart) {
vfsub_update_h_iattr(&a->h_path, /*did*/NULL);
/*ignore*/
inode->i_ctime = d_inode(a->h_path.dentry)->i_ctime;
} else
/* todo: this timestamp may be reverted later */
inode->i_ctime = h_dir->i_ctime;
goto out_unpin; /* success */
}
/* revert */
if (wh_dentry) {
int rerr;
rerr = do_revert(err, dir, bindex, bwh, wh_dentry, dentry,
&a->dt);
if (rerr)
err = rerr;
}
out_unpin:
au_unpin(&a->pin);
dput(wh_dentry);
dput(a->h_path.dentry);
out_parent:
di_write_unlock(parent);
out_unlock:
aufs_read_unlock(dentry, AuLock_DW);
out_free:
kfree(a);
out:
return err;
}