/* todo: remove this */
static int h_d_revalidate(struct dentry *dentry, struct inode *inode,
struct nameidata *nd, int do_udba)
{
int err;
umode_t mode, h_mode;
aufs_bindex_t bindex, btail, bstart, ibs, ibe;
unsigned char plus, unhashed, is_root, h_plus;
struct inode *h_inode, *h_cached_inode;
struct dentry *h_dentry;
struct qstr *name, *h_name;
err = 0;
plus = 0;
mode = 0;
ibs = -1;
ibe = -1;
unhashed = !!d_unhashed(dentry);
is_root = !!IS_ROOT(dentry);
name = &dentry->d_name;
/*
* Theoretically, REVAL test should be unnecessary in case of INOTIFY.
* But inotify doesn't fire some necessary events,
* IN_ATTRIB for atime/nlink/pageio
* IN_DELETE for NFS dentry
* Let's do REVAL test too.
*/
if (do_udba && inode) {
mode = (inode->i_mode & S_IFMT);
plus = (inode->i_nlink > 0);
ibs = au_ibstart(inode);
ibe = au_ibend(inode);
}
bstart = au_dbstart(dentry);
btail = bstart;
if (inode && S_ISDIR(inode->i_mode))
btail = au_dbtaildir(dentry);
for (bindex = bstart; bindex <= btail; bindex++) {
h_dentry = au_h_dptr(dentry, bindex);
if (!h_dentry)
continue;
AuDbg("b%d, %.*s\n", bindex, AuDLNPair(h_dentry));
h_name = &h_dentry->d_name;
if (unlikely(do_udba
&& !is_root
&& (unhashed != !!d_unhashed(h_dentry)
|| name->len != h_name->len
|| memcmp(name->name, h_name->name, name->len))
)) {
AuDbg("unhash 0x%x 0x%x, %.*s %.*s\n",
unhashed, d_unhashed(h_dentry),
AuDLNPair(dentry), AuDLNPair(h_dentry));
goto err;
}
err = au_do_h_d_reval(h_dentry, nd, dentry, bindex);
if (unlikely(err))
/* do not goto err, to keep the errno */
break;
/* todo: plink too? */
if (!do_udba)
continue;
/* UDBA tests */
h_inode = h_dentry->d_inode;
if (unlikely(!!inode != !!h_inode))
goto err;
h_plus = plus;
h_mode = mode;
h_cached_inode = h_inode;
if (h_inode) {
h_mode = (h_inode->i_mode & S_IFMT);
h_plus = (h_inode->i_nlink > 0);
}
if (inode && ibs <= bindex && bindex <= ibe)
h_cached_inode = au_h_iptr(inode, bindex);
if (unlikely(plus != h_plus
|| mode != h_mode
|| h_cached_inode != h_inode))
goto err;
continue;
err:
err = -EINVAL;
break;
}
return err;
}
int au_opts_verify(struct super_block *sb, unsigned long sb_flags,
unsigned int pending)
{
int err;
aufs_bindex_t bindex, bend;
unsigned char do_plink, skip, do_free;
struct au_branch *br;
struct au_wbr *wbr;
struct dentry *root;
struct inode *dir, *h_dir;
struct au_sbinfo *sbinfo;
struct au_hinode *hdir;
SiMustAnyLock(sb);
sbinfo = au_sbi(sb);
AuDebugOn(!(sbinfo->si_mntflags & AuOptMask_UDBA));
if (!(sb_flags & MS_RDONLY)) {
if (unlikely(!au_br_writable(au_sbr_perm(sb, 0))))
pr_warning("first branch should be rw\n");
if (unlikely(au_opt_test(sbinfo->si_mntflags, SHWH)))
pr_warning("shwh should be used with ro\n");
}
if (au_opt_test((sbinfo->si_mntflags | pending), UDBA_HNOTIFY)
&& !au_opt_test(sbinfo->si_mntflags, XINO))
pr_warning("udba=*notify requires xino\n");
err = 0;
root = sb->s_root;
dir = root->d_inode;
do_plink = !!au_opt_test(sbinfo->si_mntflags, PLINK);
bend = au_sbend(sb);
for (bindex = 0; !err && bindex <= bend; bindex++) {
skip = 0;
h_dir = au_h_iptr(dir, bindex);
br = au_sbr(sb, bindex);
do_free = 0;
wbr = br->br_wbr;
if (wbr)
wbr_wh_read_lock(wbr);
switch (br->br_perm) {
case AuBrPerm_RO:
case AuBrPerm_ROWH:
case AuBrPerm_RR:
case AuBrPerm_RRWH:
do_free = !!wbr;
skip = (!wbr
|| (!wbr->wbr_whbase
&& !wbr->wbr_plink
&& !wbr->wbr_orph));
break;
case AuBrPerm_RWNoLinkWH:
/* skip = (!br->br_whbase && !br->br_orph); */
skip = (!wbr || !wbr->wbr_whbase);
if (skip && wbr) {
if (do_plink)
skip = !!wbr->wbr_plink;
else
skip = !wbr->wbr_plink;
}
break;
case AuBrPerm_RW:
/* skip = (br->br_whbase && br->br_ohph); */
skip = (wbr && wbr->wbr_whbase);
if (skip) {
if (do_plink)
skip = !!wbr->wbr_plink;
else
skip = !wbr->wbr_plink;
}
break;
default:
BUG();
}
if (wbr)
wbr_wh_read_unlock(wbr);
if (skip)
continue;
hdir = au_hi(dir, bindex);
au_hn_imtx_lock_nested(hdir, AuLsc_I_PARENT);
if (wbr)
wbr_wh_write_lock(wbr);
err = au_wh_init(au_h_dptr(root, bindex), br, sb);
if (wbr)
wbr_wh_write_unlock(wbr);
au_hn_imtx_unlock(hdir);
if (!err && do_free) {
kfree(wbr);
br->br_wbr = NULL;
}
}
return err;
}
static int aufs_permission(struct inode *inode, int mask)
{
int err;
aufs_bindex_t bindex, bend;
const unsigned char isdir = !!S_ISDIR(inode->i_mode),
write_mask = !!(mask & (MAY_WRITE | MAY_APPEND));
struct inode *h_inode;
struct super_block *sb;
struct au_branch *br;
sb = inode->i_sb;
si_read_lock(sb, AuLock_FLUSH);
ii_read_lock_child(inode);
#if 0
err = au_iigen_test(inode, au_sigen(sb));
if (unlikely(err))
goto out;
#endif
if (!isdir || write_mask) {
err = au_busy_or_stale();
h_inode = au_h_iptr(inode, au_ibstart(inode));
if (unlikely(!h_inode
|| (h_inode->i_mode & S_IFMT)
!= (inode->i_mode & S_IFMT)))
goto out;
err = 0;
bindex = au_ibstart(inode);
br = au_sbr(sb, bindex);
err = h_permission(h_inode, mask, br->br_mnt, br->br_perm);
if (write_mask
&& !err
&& !special_file(h_inode->i_mode)) {
/* test whether the upper writable branch exists */
err = -EROFS;
for (; bindex >= 0; bindex--)
if (!au_br_rdonly(au_sbr(sb, bindex))) {
err = 0;
break;
}
}
goto out;
}
/* non-write to dir */
err = 0;
bend = au_ibend(inode);
for (bindex = au_ibstart(inode); !err && bindex <= bend; bindex++) {
h_inode = au_h_iptr(inode, bindex);
if (h_inode) {
err = au_busy_or_stale();
if (unlikely(!S_ISDIR(h_inode->i_mode)))
break;
br = au_sbr(sb, bindex);
err = h_permission(h_inode, mask, br->br_mnt,
br->br_perm);
}
}
out:
ii_read_unlock(inode);
si_read_unlock(sb);
return err;
}
int au_opts_verify(struct super_block *sb, unsigned long sb_flags,
unsigned int pending)
{
int err, fhsm;
aufs_bindex_t bindex, bend;
unsigned char do_plink, skip, do_free;
struct au_branch *br;
struct au_wbr *wbr;
struct dentry *root;
struct inode *dir, *h_dir;
struct au_sbinfo *sbinfo;
struct au_hinode *hdir;
SiMustAnyLock(sb);
sbinfo = au_sbi(sb);
AuDebugOn(!(sbinfo->si_mntflags & AuOptMask_UDBA));
if (!(sb_flags & MS_RDONLY)) {
if (unlikely(!au_br_writable(au_sbr_perm(sb, 0))))
pr_warn("first branch should be rw\n");
if (unlikely(au_opt_test(sbinfo->si_mntflags, SHWH)))
pr_warn("shwh should be used with ro\n");
}
if (au_opt_test((sbinfo->si_mntflags | pending), UDBA_HNOTIFY)
&& !au_opt_test(sbinfo->si_mntflags, XINO))
pr_warn("udba=*notify requires xino\n");
if (au_opt_test(sbinfo->si_mntflags, DIRPERM1))
pr_warn("dirperm1 breaks the protection"
" by the permission bits on the lower branch\n");
err = 0;
fhsm = 0;
root = sb->s_root;
dir = root->d_inode;
do_plink = !!au_opt_test(sbinfo->si_mntflags, PLINK);
bend = au_sbend(sb);
for (bindex = 0; !err && bindex <= bend; bindex++) {
skip = 0;
h_dir = au_h_iptr(dir, bindex);
br = au_sbr(sb, bindex);
if ((br->br_perm & AuBrAttr_ICEX)
&& !h_dir->i_op->listxattr)
br->br_perm &= ~AuBrAttr_ICEX;
#if 0
if ((br->br_perm & AuBrAttr_ICEX_SEC)
&& (au_br_sb(br)->s_flags & MS_NOSEC))
br->br_perm &= ~AuBrAttr_ICEX_SEC;
#endif
do_free = 0;
wbr = br->br_wbr;
if (wbr)
wbr_wh_read_lock(wbr);
if (!au_br_writable(br->br_perm)) {
do_free = !!wbr;
skip = (!wbr
|| (!wbr->wbr_whbase
&& !wbr->wbr_plink
&& !wbr->wbr_orph));
} else if (!au_br_wh_linkable(br->br_perm)) {
/* skip = (!br->br_whbase && !br->br_orph); */
skip = (!wbr || !wbr->wbr_whbase);
if (skip && wbr) {
if (do_plink)
skip = !!wbr->wbr_plink;
else
skip = !wbr->wbr_plink;
}
} else {
/* skip = (br->br_whbase && br->br_ohph); */
skip = (wbr && wbr->wbr_whbase);
if (skip) {
if (do_plink)
skip = !!wbr->wbr_plink;
else
skip = !wbr->wbr_plink;
}
}
if (wbr)
wbr_wh_read_unlock(wbr);
if (au_br_fhsm(br->br_perm)) {
fhsm++;
AuDebugOn(!br->br_fhsm);
}
if (skip)
continue;
hdir = au_hi(dir, bindex);
au_hn_imtx_lock_nested(hdir, AuLsc_I_PARENT);
if (wbr)
wbr_wh_write_lock(wbr);
err = au_wh_init(br, sb);
if (wbr)
wbr_wh_write_unlock(wbr);
au_hn_imtx_unlock(hdir);
if (!err && do_free) {
kfree(wbr);
br->br_wbr = NULL;
}
}
if (fhsm >= 2) {
au_fset_si(sbinfo, FHSM);
for (bindex = bend; bindex >= 0; bindex--) {
br = au_sbr(sb, bindex);
if (au_br_fhsm(br->br_perm)) {
au_fhsm_set_bottom(sb, bindex);
break;
}
}
} else {
au_fclr_si(sbinfo, FHSM);
au_fhsm_set_bottom(sb, -1);
}
return err;
}
static int au_cpdown_dir(struct dentry *dentry, aufs_bindex_t bdst,
struct au_pin *pin,
struct dentry *h_parent, void *arg)
{
int err, rerr;
aufs_bindex_t bopq, bstart;
struct path h_path;
struct dentry *parent;
struct inode *h_dir, *h_inode, *inode, *dir;
unsigned int *flags = arg;
bstart = au_dbstart(dentry);
/* dentry is di-locked */
parent = dget_parent(dentry);
dir = parent->d_inode;
h_dir = h_parent->d_inode;
AuDebugOn(h_dir != au_h_iptr(dir, bdst));
IMustLock(h_dir);
err = au_lkup_neg(dentry, bdst, /*wh*/0);
if (unlikely(err < 0))
goto out;
h_path.dentry = au_h_dptr(dentry, bdst);
h_path.mnt = au_sbr_mnt(dentry->d_sb, bdst);
err = vfsub_sio_mkdir(au_h_iptr(dir, bdst), &h_path,
S_IRWXU | S_IRUGO | S_IXUGO);
if (unlikely(err))
goto out_put;
au_fset_cpdown(*flags, MADE_DIR);
bopq = au_dbdiropq(dentry);
au_fclr_cpdown(*flags, WHED);
au_fclr_cpdown(*flags, DIROPQ);
if (au_dbwh(dentry) == bdst)
au_fset_cpdown(*flags, WHED);
if (!au_ftest_cpdown(*flags, PARENT_OPQ) && bopq <= bdst)
au_fset_cpdown(*flags, PARENT_OPQ);
h_inode = h_path.dentry->d_inode;
mutex_lock_nested(&h_inode->i_mutex, AuLsc_I_CHILD);
if (au_ftest_cpdown(*flags, WHED)) {
err = au_cpdown_dir_opq(dentry, bdst, flags);
if (unlikely(err)) {
mutex_unlock(&h_inode->i_mutex);
goto out_dir;
}
}
err = au_cpdown_attr(&h_path, au_h_dptr(dentry, bstart));
mutex_unlock(&h_inode->i_mutex);
if (unlikely(err))
goto out_opq;
if (au_ftest_cpdown(*flags, WHED)) {
err = au_cpdown_dir_wh(dentry, h_parent, dir, bdst);
if (unlikely(err))
goto out_opq;
}
inode = dentry->d_inode;
if (au_ibend(inode) < bdst)
au_set_ibend(inode, bdst);
au_set_h_iptr(inode, bdst, au_igrab(h_inode),
au_hi_flags(inode, /*isdir*/1));
au_fhsm_wrote(dentry->d_sb, bdst, /*force*/0);
goto out; /* success */
/* revert */
out_opq:
if (au_ftest_cpdown(*flags, DIROPQ)) {
mutex_lock_nested(&h_inode->i_mutex, AuLsc_I_CHILD);
rerr = au_diropq_remove(dentry, bdst);
mutex_unlock(&h_inode->i_mutex);
if (unlikely(rerr)) {
AuIOErr("failed removing diropq for %.*s b%d (%d)\n",
AuDLNPair(dentry), bdst, rerr);
err = -EIO;
goto out;
}
}
out_dir:
if (au_ftest_cpdown(*flags, MADE_DIR)) {
rerr = vfsub_sio_rmdir(au_h_iptr(dir, bdst), &h_path);
if (unlikely(rerr)) {
AuIOErr("failed removing %.*s b%d (%d)\n",
AuDLNPair(dentry), bdst, rerr);
err = -EIO;
}
}
out_put:
au_set_h_dptr(dentry, bdst, NULL);
if (au_dbend(dentry) == bdst)
au_update_dbend(dentry);
out:
dput(parent);
return err;
}
/*
* initial procedure of adding a new entry.
* prepare writable branch and the parent dir, lock it,
* and lookup whiteout for the new entry.
*/
static struct dentry*
lock_hdir_lkup_wh(struct dentry *dentry, struct au_dtime *dt,
struct dentry *src_dentry, struct au_pin *pin,
struct au_wr_dir_args *wr_dir_args)
{
struct dentry *wh_dentry, *h_parent;
struct super_block *sb;
struct au_branch *br;
int err;
unsigned int udba;
aufs_bindex_t bcpup;
AuDbg("%.*s\n", AuDLNPair(dentry));
err = au_wr_dir(dentry, src_dentry, wr_dir_args);
bcpup = err;
wh_dentry = ERR_PTR(err);
if (unlikely(err < 0))
goto out;
sb = dentry->d_sb;
udba = au_opt_udba(sb);
err = au_pin(pin, dentry, bcpup, udba,
AuPin_DI_LOCKED | AuPin_MNT_WRITE);
wh_dentry = ERR_PTR(err);
if (unlikely(err))
goto out;
h_parent = au_pinned_h_parent(pin);
if (udba != AuOpt_UDBA_NONE
&& au_dbstart(dentry) == bcpup)
err = au_may_add(dentry, bcpup, h_parent,
au_ftest_wrdir(wr_dir_args->flags, ISDIR));
else if (unlikely(dentry->d_name.len > AUFS_MAX_NAMELEN))
err = -ENAMETOOLONG;
wh_dentry = ERR_PTR(err);
if (unlikely(err))
goto out_unpin;
br = au_sbr(sb, bcpup);
if (dt) {
struct path tmp = {
.dentry = h_parent,
.mnt = br->br_mnt
};
au_dtime_store(dt, au_pinned_parent(pin), &tmp);
}
wh_dentry = NULL;
if (bcpup != au_dbwh(dentry))
goto out; /* success */
wh_dentry = au_wh_lkup(h_parent, &dentry->d_name, br);
out_unpin:
if (IS_ERR(wh_dentry))
au_unpin(pin);
out:
return wh_dentry;
}
/* ---------------------------------------------------------------------- */
enum { Mknod, Symlink, Creat };
struct simple_arg {
int type;
union {
struct {
int mode;
struct nameidata *nd;
} c;
struct {
const char *symname;
} s;
struct {
int mode;
dev_t dev;
} m;
} u;
};
static int add_simple(struct inode *dir, struct dentry *dentry,
struct simple_arg *arg)
{
int err;
aufs_bindex_t bstart;
unsigned char created;
struct au_dtime dt;
struct au_pin pin;
struct path h_path;
struct dentry *wh_dentry, *parent;
struct inode *h_dir;
struct au_wr_dir_args wr_dir_args = {
.force_btgt = -1,
.flags = AuWrDir_ADD_ENTRY
};
AuDbg("%.*s\n", AuDLNPair(dentry));
IMustLock(dir);
parent = dentry->d_parent; /* dir inode is locked */
err = aufs_read_lock(dentry, AuLock_DW | AuLock_GEN);
if (unlikely(err))
goto out;
err = au_d_may_add(dentry);
if (unlikely(err))
goto out_unlock;
di_write_lock_parent(parent);
wh_dentry = lock_hdir_lkup_wh(dentry, &dt, /*src_dentry*/NULL, &pin,
&wr_dir_args);
err = PTR_ERR(wh_dentry);
if (IS_ERR(wh_dentry))
goto out_parent;
bstart = au_dbstart(dentry);
h_path.dentry = au_h_dptr(dentry, bstart);
h_path.mnt = au_sbr_mnt(dentry->d_sb, bstart);
h_dir = au_pinned_h_dir(&pin);
switch (arg->type) {
case Creat:
err = vfsub_create(h_dir, &h_path, arg->u.c.mode);
break;
case Symlink:
err = vfsub_symlink(h_dir, &h_path, arg->u.s.symname);
break;
case Mknod:
err = vfsub_mknod(h_dir, &h_path, arg->u.m.mode, arg->u.m.dev);
break;
default:
BUG();
}
created = !err;
if (!err)
err = epilog(dir, bstart, wh_dentry, dentry);
/* revert */
if (unlikely(created && err && h_path.dentry->d_inode)) {
int rerr;
rerr = vfsub_unlink(h_dir, &h_path, /*force*/0);
if (rerr) {
AuIOErr("%.*s revert failure(%d, %d)\n",
AuDLNPair(dentry), err, rerr);
err = -EIO;
}
au_dtime_revert(&dt);
}
au_unpin(&pin);
dput(wh_dentry);
out_parent:
di_write_unlock(parent);
out_unlock:
if (unlikely(err)) {
au_update_dbstart(dentry);
d_drop(dentry);
}
aufs_read_unlock(dentry, AuLock_DW);
out:
return err;
}
int aufs_mknod(struct inode *dir, struct dentry *dentry, int mode, dev_t dev)
{
struct simple_arg arg = {
.type = Mknod,
.u.m = {
.mode = mode,
.dev = dev
}
};
return add_simple(dir, dentry, &arg);
}
int aufs_symlink(struct inode *dir, struct dentry *dentry, const char *symname)
{
struct simple_arg arg = {
.type = Symlink,
.u.s.symname = symname
};
return add_simple(dir, dentry, &arg);
}
int aufs_create(struct inode *dir, struct dentry *dentry, int mode,
struct nameidata *nd)
{
struct simple_arg arg = {
.type = Creat,
.u.c = {
.mode = mode,
.nd = nd
}
};
return add_simple(dir, dentry, &arg);
}
/* ---------------------------------------------------------------------- */
struct au_link_args {
aufs_bindex_t bdst, bsrc;
struct au_pin pin;
struct path h_path;
struct dentry *src_parent, *parent;
};
static int au_cpup_before_link(struct dentry *src_dentry,
struct au_link_args *a)
{
int err;
struct dentry *h_src_dentry;
struct mutex *h_mtx;
struct file *h_file;
di_read_lock_parent(a->src_parent, AuLock_IR);
err = au_test_and_cpup_dirs(src_dentry, a->bdst);
if (unlikely(err))
goto out;
h_src_dentry = au_h_dptr(src_dentry, a->bsrc);
h_mtx = &h_src_dentry->d_inode->i_mutex;
err = au_pin(&a->pin, src_dentry, a->bdst,
au_opt_udba(src_dentry->d_sb),
AuPin_DI_LOCKED | AuPin_MNT_WRITE);
if (unlikely(err))
goto out;
mutex_lock_nested(h_mtx, AuLsc_I_CHILD);
h_file = au_h_open_pre(src_dentry, a->bsrc);
if (IS_ERR(h_file)) {
err = PTR_ERR(h_file);
h_file = NULL;
} else
err = au_sio_cpup_simple(src_dentry, a->bdst, -1,
AuCpup_DTIME /* | AuCpup_KEEPLINO */);
mutex_unlock(h_mtx);
au_h_open_post(src_dentry, a->bsrc, h_file);
au_unpin(&a->pin);
out:
di_read_unlock(a->src_parent, AuLock_IR);
return err;
}
static int au_cpup_or_link(struct dentry *src_dentry, struct au_link_args *a)
{
int err;
unsigned char plink;
struct inode *h_inode, *inode;
struct dentry *h_src_dentry;
struct super_block *sb;
struct file *h_file;
plink = 0;
h_inode = NULL;
sb = src_dentry->d_sb;
inode = src_dentry->d_inode;
if (au_ibstart(inode) <= a->bdst)
h_inode = au_h_iptr(inode, a->bdst);
if (!h_inode || !h_inode->i_nlink) {
/* copyup src_dentry as the name of dentry. */
au_set_dbstart(src_dentry, a->bdst);
au_set_h_dptr(src_dentry, a->bdst, dget(a->h_path.dentry));
h_inode = au_h_dptr(src_dentry, a->bsrc)->d_inode;
mutex_lock_nested(&h_inode->i_mutex, AuLsc_I_CHILD);
h_file = au_h_open_pre(src_dentry, a->bsrc);
if (IS_ERR(h_file)) {
err = PTR_ERR(h_file);
h_file = NULL;
} else
err = au_sio_cpup_single(src_dentry, a->bdst, a->bsrc,
-1, AuCpup_KEEPLINO,
a->parent);
mutex_unlock(&h_inode->i_mutex);
au_h_open_post(src_dentry, a->bsrc, h_file);
au_set_h_dptr(src_dentry, a->bdst, NULL);
au_set_dbstart(src_dentry, a->bsrc);
} else {
/* the inode of src_dentry already exists on a.bdst branch */
h_src_dentry = d_find_alias(h_inode);
if (!h_src_dentry && au_plink_test(inode)) {
plink = 1;
h_src_dentry = au_plink_lkup(inode, a->bdst);
err = PTR_ERR(h_src_dentry);
if (IS_ERR(h_src_dentry))
goto out;
if (unlikely(!h_src_dentry->d_inode)) {
dput(h_src_dentry);
h_src_dentry = NULL;
}
}
if (h_src_dentry) {
err = vfsub_link(h_src_dentry, au_pinned_h_dir(&a->pin),
&a->h_path);
dput(h_src_dentry);
} else {
AuIOErr("no dentry found for hi%lu on b%d\n",
h_inode->i_ino, a->bdst);
err = -EIO;
}
}
if (!err && !plink)
au_plink_append(inode, a->bdst, a->h_path.dentry);
out:
AuTraceErr(err);
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("%.*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 inode *inode, *h_dir;
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 = 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, &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);
err = vfsub_unlink(h_dir, &a->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(&a->h_path, /*did*/NULL);
/*ignore*/
inode->i_ctime = a->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,
&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;
}
/*
* if valid returns 1, otherwise 0.
*/
static int aufs_d_revalidate(struct dentry *dentry, unsigned int flags)
{
int valid, err;
unsigned int sigen;
unsigned char do_udba;
struct super_block *sb;
struct inode *inode;
/* todo: support rcu-walk? */
if (flags & LOOKUP_RCU)
return -ECHILD;
valid = 0;
if (unlikely(!au_di(dentry)))
goto out;
inode = dentry->d_inode;
if (inode && is_bad_inode(inode))
goto out;
valid = 1;
sb = dentry->d_sb;
/*
* todo: very ugly
* i_mutex of parent dir may be held,
* but we should not return 'invalid' due to busy.
*/
err = aufs_read_lock(dentry, AuLock_FLUSH | AuLock_DW | AuLock_NOPLM);
if (unlikely(err)) {
valid = err;
AuTraceErr(err);
goto out;
}
if (unlikely(au_dbrange_test(dentry))) {
err = -EINVAL;
AuTraceErr(err);
goto out_dgrade;
}
sigen = au_sigen(sb);
if (au_digen_test(dentry, sigen)) {
AuDebugOn(IS_ROOT(dentry));
err = au_reval_dpath(dentry, sigen);
if (unlikely(err)) {
AuTraceErr(err);
goto out_dgrade;
}
}
di_downgrade_lock(dentry, AuLock_IR);
err = -EINVAL;
if (!(flags & LOOKUP_OPEN)
&& inode
&& (IS_DEADDIR(inode) || !inode->i_nlink))
goto out_inval;
do_udba = !au_opt_test(au_mntflags(sb), UDBA_NONE);
if (do_udba && inode) {
aufs_bindex_t bstart = au_ibstart(inode);
struct inode *h_inode;
if (bstart >= 0) {
h_inode = au_h_iptr(inode, bstart);
if (h_inode && au_test_higen(inode, h_inode))
goto out_inval;
}
}
err = h_d_revalidate(dentry, inode, flags, do_udba);
if (unlikely(!err && do_udba && au_dbstart(dentry) < 0)) {
err = -EIO;
AuDbg("both of real entry and whiteout found, %p, err %d\n",
dentry, err);
}
goto out_inval;
out_dgrade:
di_downgrade_lock(dentry, AuLock_IR);
out_inval:
aufs_read_unlock(dentry, AuLock_IR);
AuTraceErr(err);
valid = !err;
out:
if (!valid) {
AuDbg("%pd invalid, %d\n", dentry, valid);
d_drop(dentry);
}
return valid;
}
/* todo: remove this */
static int h_d_revalidate(struct dentry *dentry, struct inode *inode,
unsigned int flags, int do_udba)
{
int err;
umode_t mode, h_mode;
aufs_bindex_t bindex, btail, bstart, ibs, ibe;
unsigned char plus, unhashed, is_root, h_plus, h_nfs;
struct inode *h_inode, *h_cached_inode;
struct dentry *h_dentry;
struct qstr *name, *h_name;
err = 0;
plus = 0;
mode = 0;
ibs = -1;
ibe = -1;
unhashed = !!d_unhashed(dentry);
is_root = !!IS_ROOT(dentry);
name = &dentry->d_name;
/*
* Theoretically, REVAL test should be unnecessary in case of
* {FS,I}NOTIFY.
* But {fs,i}notify doesn't fire some necessary events,
* IN_ATTRIB for atime/nlink/pageio
* IN_DELETE for NFS dentry
* Let's do REVAL test too.
*/
if (do_udba && inode) {
mode = (inode->i_mode & S_IFMT);
plus = (inode->i_nlink > 0);
ibs = au_ibstart(inode);
ibe = au_ibend(inode);
}
bstart = au_dbstart(dentry);
btail = bstart;
if (inode && S_ISDIR(inode->i_mode))
btail = au_dbtaildir(dentry);
for (bindex = bstart; bindex <= btail; bindex++) {
h_dentry = au_h_dptr(dentry, bindex);
if (!h_dentry)
continue;
AuDbg("b%d, %pd\n", bindex, h_dentry);
h_nfs = !!au_test_nfs(h_dentry->d_sb);
spin_lock(&h_dentry->d_lock);
h_name = &h_dentry->d_name;
if (unlikely(do_udba
&& !is_root
&& ((!h_nfs
&& (unhashed != !!d_unhashed(h_dentry)
|| name->len != h_name->len
|| memcmp(name->name, h_name->name,
name->len)))
|| (h_nfs
&& !(flags & LOOKUP_OPEN)
&& (h_dentry->d_flags
& DCACHE_NFSFS_RENAMED)))
)) {
AuDbg("unhash 0x%x 0x%x, %pd %pd\n",
unhashed, d_unhashed(h_dentry),
dentry, h_dentry);
spin_unlock(&h_dentry->d_lock);
goto err;
}
spin_unlock(&h_dentry->d_lock);
err = au_do_h_d_reval(h_dentry, flags, dentry, bindex);
if (unlikely(err))
/* do not goto err, to keep the errno */
break;
/* todo: plink too? */
if (!do_udba)
continue;
/* UDBA tests */
h_inode = h_dentry->d_inode;
if (unlikely(!!inode != !!h_inode))
goto err;
h_plus = plus;
h_mode = mode;
h_cached_inode = h_inode;
if (h_inode) {
h_mode = (h_inode->i_mode & S_IFMT);
h_plus = (h_inode->i_nlink > 0);
}
if (inode && ibs <= bindex && bindex <= ibe)
h_cached_inode = au_h_iptr(inode, bindex);
if (!h_nfs) {
if (unlikely(plus != h_plus))
goto err;
} else {
if (unlikely(!(h_dentry->d_flags & DCACHE_NFSFS_RENAMED)
&& !is_root
&& !IS_ROOT(h_dentry)
&& unhashed != d_unhashed(h_dentry)))
goto err;
}
if (unlikely(mode != h_mode
|| h_cached_inode != h_inode))
goto err;
continue;
err:
err = -EINVAL;
break;
}
AuTraceErr(err);
return err;
}
