/*
* 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 {
umode_t mode;
bool want_excl;
} c;
struct {
const char *symname;
} s;
struct {
umode_t 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,
arg->u.c.want_excl);
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, umode_t 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, umode_t mode,
bool want_excl)
{
struct simple_arg arg = {
.type = Creat,
.u.c = {
.mode = mode,
.want_excl = want_excl
}
};
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;
}
int au_mvdown(struct dentry *dentry, struct aufs_mvdown __user *uarg)
{
int err, e;
unsigned char dmsg;
struct au_mvd_args *args;
struct inode *inode;
inode = d_inode(dentry);
err = -EPERM;
if (unlikely(!capable(CAP_SYS_ADMIN)))
goto out;
err = -ENOMEM;
args = kmalloc(sizeof(*args), GFP_NOFS);
if (unlikely(!args))
goto out;
err = copy_from_user(&args->mvdown, uarg, sizeof(args->mvdown));
if (!err)
err = !access_ok(VERIFY_WRITE, uarg, sizeof(*uarg));
if (unlikely(err)) {
err = -EFAULT;
AuTraceErr(err);
goto out_free;
}
AuDbg("flags 0x%x\n", args->mvdown.flags);
args->mvdown.flags &= ~(AUFS_MVDOWN_ROLOWER_R | AUFS_MVDOWN_ROUPPER_R);
args->mvdown.au_errno = 0;
args->dentry = dentry;
args->inode = inode;
args->sb = dentry->d_sb;
err = -ENOENT;
dmsg = !!(args->mvdown.flags & AUFS_MVDOWN_DMSG);
args->parent = dget_parent(dentry);
args->dir = d_inode(args->parent);
inode_lock_nested(args->dir, I_MUTEX_PARENT);
dput(args->parent);
if (unlikely(args->parent != dentry->d_parent)) {
AU_MVD_PR(dmsg, "parent dir is moved\n");
goto out_dir;
}
inode_lock_nested(inode, I_MUTEX_CHILD);
err = aufs_read_lock(dentry, AuLock_DW | AuLock_FLUSH | AuLock_NOPLMW);
if (unlikely(err))
goto out_inode;
di_write_lock_parent(args->parent);
err = au_mvd_args(dmsg, args);
if (unlikely(err))
goto out_parent;
err = au_do_mvdown(dmsg, args);
if (unlikely(err))
goto out_parent;
au_cpup_attr_timesizes(args->dir);
au_cpup_attr_timesizes(inode);
if (!(args->mvdown.flags & AUFS_MVDOWN_KUPPER))
au_cpup_igen(inode, au_h_iptr(inode, args->mvd_bdst));
/* au_digen_dec(dentry); */
out_parent:
di_write_unlock(args->parent);
aufs_read_unlock(dentry, AuLock_DW);
out_inode:
inode_unlock(inode);
out_dir:
inode_unlock(args->dir);
out_free:
e = copy_to_user(uarg, &args->mvdown, sizeof(args->mvdown));
if (unlikely(e))
err = -EFAULT;
kfree(args);
out:
AuTraceErr(err);
return err;
}
static int au_ii_refresh(struct inode *inode, int *update)
{
int err, e;
umode_t type;
aufs_bindex_t bindex, new_bindex;
struct super_block *sb;
struct au_iinfo *iinfo;
struct au_hinode *p, *q, tmp;
IiMustWriteLock(inode);
*update = 0;
sb = inode->i_sb;
type = inode->i_mode & S_IFMT;
iinfo = au_ii(inode);
err = au_ii_realloc(iinfo, au_sbend(sb) + 1);
if (unlikely(err))
goto out;
AuDebugOn(iinfo->ii_bstart < 0);
p = iinfo->ii_hinode + iinfo->ii_bstart;
for (bindex = iinfo->ii_bstart; bindex <= iinfo->ii_bend;
bindex++, p++) {
if (!p->hi_inode)
continue;
AuDebugOn(type != (p->hi_inode->i_mode & S_IFMT));
new_bindex = au_br_index(sb, p->hi_id);
if (new_bindex == bindex)
continue;
if (new_bindex < 0) {
*update = 1;
au_hiput(p);
p->hi_inode = NULL;
continue;
}
if (new_bindex < iinfo->ii_bstart)
iinfo->ii_bstart = new_bindex;
if (iinfo->ii_bend < new_bindex)
iinfo->ii_bend = new_bindex;
/* swap two lower inode, and loop again */
q = iinfo->ii_hinode + new_bindex;
tmp = *q;
*q = *p;
*p = tmp;
if (tmp.hi_inode) {
bindex--;
p--;
}
}
au_update_ibrange(inode, /*do_put_zero*/0);
e = au_dy_irefresh(inode);
if (unlikely(e && !err))
err = e;
out:
AuTraceErr(err);
return err;
}
static int au_mvd_args_intermediate(const unsigned char dmsg,
struct au_mvd_args *a)
{
int err;
struct au_dinfo *dinfo, *tmp;
/* lookup the next lower positive entry */
err = -ENOMEM;
tmp = au_di_alloc(a->sb, AuLsc_DI_TMP);
if (unlikely(!tmp))
goto out;
a->bfound = -1;
a->bwh = -1;
dinfo = au_di(a->dentry);
au_di_cp(tmp, dinfo);
au_di_swap(tmp, dinfo);
/* returns the number of positive dentries */
err = au_lkup_dentry(a->dentry, a->mvd_bsrc + 1,
/* AuLkup_IGNORE_PERM */ 0);
if (!err)
a->bwh = au_dbwh(a->dentry);
else if (err > 0)
a->bfound = au_dbtop(a->dentry);
au_di_swap(tmp, dinfo);
au_rw_write_unlock(&tmp->di_rwsem);
au_di_free(tmp);
if (unlikely(err < 0))
AU_MVD_PR(dmsg, "failed look-up lower\n");
/*
* here, we have these cases.
* bfound == -1
* no positive dentry under bsrc. there are more sub-cases.
* bwh < 0
* there no whiteout, we can safely move-down.
* bwh <= bsrc
* impossible
* bsrc < bwh && bwh < bdst
* there is a whiteout on RO branch. cannot proceed.
* bwh == bdst
* there is a whiteout on the RW target branch. it should
* be removed.
* bdst < bwh
* there is a whiteout somewhere unrelated branch.
* -1 < bfound && bfound <= bsrc
* impossible.
* bfound < bdst
* found, but it is on RO branch between bsrc and bdst. cannot
* proceed.
* bfound == bdst
* found, replace it if AUFS_MVDOWN_FORCE is set. otherwise return
* error.
* bdst < bfound
* found, after we create the file on bdst, it will be hidden.
*/
AuDebugOn(a->bfound == -1
&& a->bwh != -1
&& a->bwh <= a->mvd_bsrc);
AuDebugOn(-1 < a->bfound
&& a->bfound <= a->mvd_bsrc);
err = -EINVAL;
if (a->bfound == -1
&& a->mvd_bsrc < a->bwh
&& a->bwh != -1
&& a->bwh < a->mvd_bdst) {
a->mvd_errno = EAU_MVDOWN_WHITEOUT;
AU_MVD_PR(dmsg, "bsrc %d, bdst %d, bfound %d, bwh %d\n",
a->mvd_bsrc, a->mvd_bdst, a->bfound, a->bwh);
goto out;
} else if (a->bfound != -1 && a->bfound < a->mvd_bdst) {
a->mvd_errno = EAU_MVDOWN_UPPER;
AU_MVD_PR(dmsg, "bdst %d, bfound %d\n",
a->mvd_bdst, a->bfound);
goto out;
}
err = 0; /* success */
out:
AuTraceErr(err);
return err;
}
static int au_mvd_args(const unsigned char dmsg, struct au_mvd_args *a)
{
int err;
struct au_branch *br;
err = -EISDIR;
if (unlikely(S_ISDIR(a->inode->i_mode)))
goto out;
err = -EINVAL;
if (!(a->mvdown.flags & AUFS_MVDOWN_BRID_UPPER))
a->mvd_bsrc = au_ibtop(a->inode);
else {
a->mvd_bsrc = au_br_index(a->sb, a->mvd_src_brid);
if (unlikely(a->mvd_bsrc < 0
|| (a->mvd_bsrc < au_dbtop(a->dentry)
|| au_dbbot(a->dentry) < a->mvd_bsrc
|| !au_h_dptr(a->dentry, a->mvd_bsrc))
|| (a->mvd_bsrc < au_ibtop(a->inode)
|| au_ibbot(a->inode) < a->mvd_bsrc
|| !au_h_iptr(a->inode, a->mvd_bsrc)))) {
a->mvd_errno = EAU_MVDOWN_NOUPPER;
AU_MVD_PR(dmsg, "no upper\n");
goto out;
}
}
if (unlikely(a->mvd_bsrc == au_sbbot(a->sb))) {
a->mvd_errno = EAU_MVDOWN_BOTTOM;
AU_MVD_PR(dmsg, "on the bottom\n");
goto out;
}
a->mvd_h_src_inode = au_h_iptr(a->inode, a->mvd_bsrc);
br = au_sbr(a->sb, a->mvd_bsrc);
err = au_br_rdonly(br);
if (!(a->mvdown.flags & AUFS_MVDOWN_ROUPPER)) {
if (unlikely(err))
goto out;
} else if (!(vfsub_native_ro(a->mvd_h_src_inode)
|| IS_APPEND(a->mvd_h_src_inode))) {
if (err)
a->mvdown.flags |= AUFS_MVDOWN_ROUPPER_R;
/* go on */
} else
goto out;
err = -EINVAL;
if (!(a->mvdown.flags & AUFS_MVDOWN_BRID_LOWER)) {
a->mvd_bdst = find_lower_writable(a);
if (unlikely(a->mvd_bdst < 0)) {
a->mvd_errno = EAU_MVDOWN_BOTTOM;
AU_MVD_PR(dmsg, "no writable lower branch\n");
goto out;
}
} else {
a->mvd_bdst = au_br_index(a->sb, a->mvd_dst_brid);
if (unlikely(a->mvd_bdst < 0
|| au_sbbot(a->sb) < a->mvd_bdst)) {
a->mvd_errno = EAU_MVDOWN_NOLOWERBR;
AU_MVD_PR(dmsg, "no lower brid\n");
goto out;
}
}
err = au_mvd_args_busy(dmsg, a);
if (!err)
err = au_mvd_args_parent(dmsg, a);
if (!err)
err = au_mvd_args_intermediate(dmsg, a);
if (!err)
err = au_mvd_args_exist(dmsg, a);
if (!err)
AuDbg("b%d, b%d\n", a->mvd_bsrc, a->mvd_bdst);
out:
AuTraceErr(err);
return err;
}
int au_refresh_dentry(struct dentry *dentry, struct dentry *parent)
{
int err, ebrange;
unsigned int sigen;
struct au_dinfo *dinfo, *tmp;
struct super_block *sb;
struct inode *inode;
DiMustWriteLock(dentry);
AuDebugOn(IS_ROOT(dentry));
AuDebugOn(!parent->d_inode);
sb = dentry->d_sb;
inode = dentry->d_inode;
sigen = au_sigen(sb);
err = au_digen_test(parent, sigen);
if (unlikely(err))
goto out;
dinfo = au_di(dentry);
err = au_di_realloc(dinfo, au_sbend(sb) + 1);
if (unlikely(err))
goto out;
ebrange = au_dbrange_test(dentry);
if (!ebrange)
ebrange = au_do_refresh_hdentry(dentry, parent);
if (d_unhashed(dentry) || ebrange) {
AuDebugOn(au_dbstart(dentry) < 0 && au_dbend(dentry) >= 0);
if (inode)
err = au_refresh_hinode_self(inode);
au_dbg_verify_dinode(dentry);
if (!err)
goto out_dgen; /* success */
goto out;
}
/* temporary dinfo */
AuDbgDentry(dentry);
err = -ENOMEM;
tmp = au_di_alloc(sb, AuLsc_DI_TMP);
if (unlikely(!tmp))
goto out;
au_di_swap(tmp, dinfo);
/* returns the number of positive dentries */
/*
* if current working dir is removed, it returns an error.
* but the dentry is legal.
*/
err = au_lkup_dentry(dentry, /*bstart*/0, /*type*/0);
AuDbgDentry(dentry);
au_di_swap(tmp, dinfo);
if (err == -ENOENT)
err = 0;
if (err >= 0) {
/* compare/refresh by dinfo */
AuDbgDentry(dentry);
err = au_refresh_by_dinfo(dentry, dinfo, tmp);
au_dbg_verify_dinode(dentry);
AuTraceErr(err);
}
au_rw_write_unlock(&tmp->di_rwsem);
au_di_free(tmp);
if (unlikely(err))
goto out;
out_dgen:
au_update_digen(dentry);
out:
if (unlikely(err && !(dentry->d_flags & DCACHE_NFSFS_RENAMED))) {
AuIOErr("failed refreshing %pd, %d\n", dentry, err);
AuDbgDentry(dentry);
}
AuTraceErr(err);
return err;
}
/* copy-down the file */
static int au_do_cpdown(const unsigned char dmsg, struct au_mvd_args *a)
{
int err;
struct au_cp_generic cpg = {
.dentry = a->dentry,
.bdst = a->mvd_bdst,
.bsrc = a->mvd_bsrc,
.len = -1,
.pin = &a->mvd_pin_dst,
.flags = AuCpup_DTIME | AuCpup_HOPEN
};
AuDbg("b%d, b%d\n", cpg.bsrc, cpg.bdst);
if (a->mvdown.flags & AUFS_MVDOWN_OWLOWER)
au_fset_cpup(cpg.flags, OVERWRITE);
if (a->mvdown.flags & AUFS_MVDOWN_ROLOWER)
au_fset_cpup(cpg.flags, RWDST);
err = au_sio_cpdown_simple(&cpg);
if (unlikely(err))
AU_MVD_PR(dmsg, "cpdown failed\n");
AuTraceErr(err);
return err;
}
/*
* unlink the whiteout on bdst if exist which may be created by UDBA while we
* were sleeping
*/
static int au_do_unlink_wh(const unsigned char dmsg, struct au_mvd_args *a)
{
int err;
struct path h_path;
struct au_branch *br;
struct inode *delegated;
br = au_sbr(a->sb, a->mvd_bdst);
h_path.dentry = au_wh_lkup(a->mvd_h_dst_parent, &a->dentry->d_name, br);
err = PTR_ERR(h_path.dentry);
if (IS_ERR(h_path.dentry)) {
AU_MVD_PR(dmsg, "wh_lkup failed\n");
goto out;
}
err = 0;
if (d_is_positive(h_path.dentry)) {
h_path.mnt = au_br_mnt(br);
delegated = NULL;
err = vfsub_unlink(d_inode(a->mvd_h_dst_parent), &h_path,
&delegated, /*force*/0);
if (unlikely(err == -EWOULDBLOCK)) {
pr_warn("cannot retry for NFSv4 delegation"
" for an internal unlink\n");
iput(delegated);
}
if (unlikely(err))
AU_MVD_PR(dmsg, "wh_unlink failed\n");
}
dput(h_path.dentry);
out:
AuTraceErr(err);
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;
/*
* is it possible?
* yes, it happend (in linux-3.3-rcN) but I don't know why.
* there may exist a problem somewhere else.
*/
err = -EINVAL;
if (unlikely(a->dst_parent->d_inode == a->src_dentry->d_inode))
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;
}
/*
* if valid returns 1, otherwise 0.
*/
static int aufs_d_revalidate(struct dentry *dentry, struct nameidata *nd)
{
int valid, err;
unsigned int sigen;
unsigned char do_udba;
struct super_block *sb;
struct inode *inode;
valid = 1;
sb = dentry->d_sb;
inode = dentry->d_inode;
/*
* 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;
goto out;
}
sigen = au_sigen(sb);
if (au_digen(dentry) != sigen) {
AuDebugOn(IS_ROOT(dentry));
if (inode)
err = au_reval_dpath(dentry, sigen);
if (unlikely(err))
goto out_dgrade;
}
if (inode && au_iigen(inode) != sigen) {
AuDebugOn(IS_ROOT(dentry));
err = au_refresh_hinode(inode, dentry);
if (unlikely(err))
goto out_dgrade;
}
di_downgrade_lock(dentry, AuLock_IR);
err = -EINVAL;
do_udba = !au_opt_test(au_mntflags(sb), UDBA_NONE);
if (do_udba && inode) {
aufs_bindex_t bstart = au_ibstart(inode);
if (bstart >= 0
&& au_test_higen(inode, au_h_iptr(inode, bstart)))
goto out_inval;
}
err = h_d_revalidate(dentry, inode, nd, do_udba);
if (unlikely(!err && do_udba && au_dbstart(dentry) < 0))
/* both of real entry and whiteout found */
err = -EIO;
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("%.*s invalid, %d\n", AuDLNPair(dentry), valid);
return valid;
}
static struct dentry *
aufs_decode_fh(struct super_block *sb, __u32 *fh, int fh_len, int fh_type,
int (*acceptable)(void *context, struct dentry *de),
void *context)
{
struct dentry *dentry;
ino_t ino, dir_ino;
aufs_bindex_t bindex;
struct au_nfsd_si_lock nsi_lock = {
.sigen = fh[Fh_sigen],
.br_id = fh[Fh_br_id],
.force_lock = 0
};
LKTRTrace("%d, fh{br_id %u, sigen %u, i%u, diri%u, g%u}\n",
fh_type, fh[Fh_br_id], fh[Fh_sigen], fh[Fh_ino],
fh[Fh_dir_ino], fh[Fh_igen]);
AuDebugOn(fh_len < Fh_tail);
dentry = ERR_PTR(-ESTALE);
/* branch id may be wrapped around */
bindex = si_nfsd_read_lock(sb, &nsi_lock);
if (unlikely(bindex < 0))
goto out;
nsi_lock.force_lock = 1;
/* is this inode still cached? */
ino = decode_ino(fh + Fh_ino);
AuDebugOn(ino == AUFS_ROOT_INO);
dir_ino = decode_ino(fh + Fh_dir_ino);
dentry = decode_by_ino(sb, ino, dir_ino);
if (IS_ERR(dentry))
goto out_unlock;
if (dentry)
goto accept;
/* is the parent dir cached? */
dentry = decode_by_dir_ino(sb, ino, dir_ino, &nsi_lock);
if (IS_ERR(dentry))
goto out_unlock;
if (dentry)
goto accept;
/* lookup path */
dentry = decode_by_path(sb, bindex, ino, fh, fh_len, &nsi_lock);
if (IS_ERR(dentry))
goto out_unlock;
if (unlikely(!dentry))
goto out_unlock;
accept:
LKTRLabel(accept);
if (dentry->d_inode->i_generation == fh[Fh_igen]
&& acceptable(context, dentry))
goto out_unlock; /* success */
LKTRLabel(stale);
dput(dentry);
dentry = ERR_PTR(-ESTALE);
out_unlock:
LKTRLabel(out_unlock);
si_read_unlock(sb);
out:
LKTRLabel(out);
if (0 && IS_ERR(dentry))
dentry = ERR_PTR(-ESTALE);
AuTraceErrPtr(dentry);
return dentry;
}
#if LINUX_VERSION_CODE >= KERNEL_VERSION(2, 6, 24)
static struct dentry *
aufs_fh_to_dentry(struct super_block *sb, struct fid *fid, int fh_len,
int fh_type)
{
return aufs_decode_fh(sb, fid->raw, fh_len, fh_type, h_acceptable,
/*context*/NULL);
}
#endif /* KERNEL_VERSION */
/* ---------------------------------------------------------------------- */
static int aufs_encode_fh(struct dentry *dentry, __u32 *fh, int *max_len,
int connectable)
{
int err;
aufs_bindex_t bindex, bend;
struct super_block *sb, *h_sb;
struct inode *inode;
struct dentry *parent, *h_parent;
struct au_branch *br;
LKTRTrace("%.*s, max %d, conn %d\n",
AuDLNPair(dentry), *max_len, connectable);
AuDebugOn(au_test_anon(dentry));
parent = NULL;
err = -ENOSPC;
if (unlikely(*max_len <= Fh_tail)) {
AuWarn1("NFSv2 client (max_len %d)?\n", *max_len);
goto out;
}
err = 0; //FILEID_ROOT;
if (IS_ROOT(dentry)) {
AuDebugOn(dentry->d_inode->i_ino != AUFS_ROOT_INO);
goto out;
}
err = -EIO;
h_parent = NULL;
sb = dentry->d_sb;
aufs_read_lock(dentry, AuLock_FLUSH | AuLock_IR);
parent = dget_parent(dentry);
di_read_lock_parent(parent, !AuLock_IR);
inode = dentry->d_inode;
AuDebugOn(!inode);
#ifdef CONFIG_AUFS_DEBUG
{
unsigned int mnt_flags = au_mntflags(sb);
if (unlikely(!au_opt_test_xino(mnt_flags)))
AuWarn1("NFS-exporting requires xino\n");
if (unlikely(0 && !au_opt_test(mnt_flags, UDBA_INOTIFY)))
AuWarn1("udba=inotify is recommended "
"for NFS-exporting\n");
}
#endif
bend = au_dbtaildir(parent);
for (bindex = au_dbstart(parent); bindex <= bend; bindex++) {
h_parent = au_h_dptr(parent, bindex);
if (h_parent) {
dget(h_parent);
break;
}
}
if (unlikely(!h_parent))
goto out_unlock;
LKTRTrace("b%d\n", bindex);
err = -EPERM;
br = au_sbr(sb, bindex);
h_sb = br->br_mnt->mnt_sb;
if (unlikely(!h_sb->s_export_op)) {
AuErr1("%s branch is not exportable\n", au_sbtype(h_sb));
goto out_dput;
}
fh[Fh_br_id] = br->br_id;
fh[Fh_sigen] = au_sigen(sb);
encode_ino(fh + Fh_ino, inode->i_ino);
encode_ino(fh + Fh_dir_ino, parent->d_inode->i_ino);
fh[Fh_igen] = inode->i_generation;
#if LINUX_VERSION_CODE < KERNEL_VERSION(2, 6, 24)
/* it should be set at exporting time */
if (unlikely(!h_sb->s_export_op->find_exported_dentry)) {
AuWarn("set default find_exported_dentry for %s\n",
au_sbtype(h_sb));
h_sb->s_export_op->find_exported_dentry = find_exported_dentry;
}
#endif
*max_len -= Fh_tail;
fh[Fh_h_type] = au_call_encode_fh(h_parent, fh + Fh_tail, max_len,
/*connectable or subtreecheck*/0);
err = fh[Fh_h_type];
*max_len += Fh_tail;
/* todo: macros? */
if (err != 255)
err = 99;
else
AuWarn1("%s encode_fh failed\n", au_sbtype(h_sb));
out_dput:
dput(h_parent);
out_unlock:
di_read_unlock(parent, !AuLock_IR);
dput(parent);
aufs_read_unlock(dentry, AuLock_IR);
out:
AuTraceErr(err);
if (unlikely(err < 0))
err = 255;
return err;
}
static int h_permission(struct inode *h_inode, int mask,
struct path *h_path, int brperm)
{
int err;
const unsigned char write_mask = !!(mask & (MAY_WRITE | MAY_APPEND));
err = -EPERM;
if (write_mask && IS_IMMUTABLE(h_inode))
goto out;
err = -EACCES;
if (((mask & MAY_EXEC)
&& S_ISREG(h_inode->i_mode)
&& (path_noexec(h_path)
|| !(h_inode->i_mode & S_IXUGO))))
goto out;
/*
* - skip the lower fs test in the case of write to ro branch.
* - nfs dir permission write check is optimized, but a policy for
* link/rename requires a real check.
* - nfs always sets SB_POSIXACL regardless its mount option 'noacl.'
* in this case, generic_permission() returns -EOPNOTSUPP.
*/
if ((write_mask && !au_br_writable(brperm))
|| (au_test_nfs(h_inode->i_sb) && S_ISDIR(h_inode->i_mode)
&& write_mask && !(mask & MAY_READ))
|| !h_inode->i_op->permission) {
/* AuLabel(generic_permission); */
/* AuDbg("get_acl %pf\n", h_inode->i_op->get_acl); */
err = generic_permission(h_inode, mask);
if (err == -EOPNOTSUPP && au_test_nfs_noacl(h_inode))
err = h_inode->i_op->permission(h_inode, mask);
AuTraceErr(err);
} else {
/* AuLabel(h_inode->permission); */
err = h_inode->i_op->permission(h_inode, mask);
AuTraceErr(err);
}
if (!err)
err = devcgroup_inode_permission(h_inode, mask);
if (!err)
err = security_inode_permission(h_inode, mask);
#if 0
if (!err) {
/* todo: do we need to call ima_path_check()? */
struct path h_path = {
.dentry =
.mnt = h_mnt
};
err = ima_path_check(&h_path,
mask & (MAY_READ | MAY_WRITE | MAY_EXEC),
IMA_COUNT_LEAVE);
}
#endif
out:
return err;
}
static int au_cmoo(struct dentry *dentry)
{
int err, cmoo;
unsigned int udba;
struct path h_path;
struct au_pin pin;
struct au_cp_generic cpg = {
.dentry = dentry,
.bdst = -1,
.bsrc = -1,
.len = -1,
.pin = &pin,
.flags = AuCpup_DTIME | AuCpup_HOPEN
};
struct inode *inode, *delegated;
struct super_block *sb;
struct au_sbinfo *sbinfo;
struct au_fhsm *fhsm;
pid_t pid;
struct au_branch *br;
struct dentry *parent;
struct au_hinode *hdir;
DiMustWriteLock(dentry);
inode = dentry->d_inode;
IiMustWriteLock(inode);
err = 0;
if (IS_ROOT(dentry))
goto out;
cpg.bsrc = au_dbstart(dentry);
if (!cpg.bsrc)
goto out;
sb = dentry->d_sb;
sbinfo = au_sbi(sb);
fhsm = &sbinfo->si_fhsm;
pid = au_fhsm_pid(fhsm);
if (pid
&& (current->pid == pid
|| current->real_parent->pid == pid))
goto out;
br = au_sbr(sb, cpg.bsrc);
cmoo = au_br_cmoo(br->br_perm);
if (!cmoo)
goto out;
if (!S_ISREG(inode->i_mode))
cmoo &= AuBrAttr_COO_ALL;
if (!cmoo)
goto out;
parent = dget_parent(dentry);
di_write_lock_parent(parent);
err = au_wbr_do_copyup_bu(dentry, cpg.bsrc - 1);
cpg.bdst = err;
if (unlikely(err < 0)) {
err = 0; /* there is no upper writable branch */
goto out_dgrade;
}
AuDbg("bsrc %d, bdst %d\n", cpg.bsrc, cpg.bdst);
/* do not respect the coo attrib for the target branch */
err = au_cpup_dirs(dentry, cpg.bdst);
if (unlikely(err))
goto out_dgrade;
di_downgrade_lock(parent, AuLock_IR);
udba = au_opt_udba(sb);
err = au_pin(&pin, dentry, cpg.bdst, udba,
AuPin_DI_LOCKED | AuPin_MNT_WRITE);
if (unlikely(err))
goto out_parent;
err = au_sio_cpup_simple(&cpg);
au_unpin(&pin);
if (unlikely(err))
goto out_parent;
if (!(cmoo & AuBrWAttr_MOO))
goto out_parent; /* success */
err = au_pin(&pin, dentry, cpg.bsrc, udba,
AuPin_DI_LOCKED | AuPin_MNT_WRITE);
if (unlikely(err))
goto out_parent;
h_path.mnt = au_br_mnt(br);
h_path.dentry = au_h_dptr(dentry, cpg.bsrc);
hdir = au_hi(parent->d_inode, cpg.bsrc);
delegated = NULL;
err = vfsub_unlink(hdir->hi_inode, &h_path, &delegated, /*force*/1);
au_unpin(&pin);
/* todo: keep h_dentry or not? */
if (unlikely(err == -EWOULDBLOCK)) {
pr_warn("cannot retry for NFSv4 delegation"
" for an internal unlink\n");
iput(delegated);
}
if (unlikely(err)) {
pr_err("unlink %pd after coo failed (%d), ignored\n",
dentry, err);
err = 0;
}
goto out_parent; /* success */
out_dgrade:
di_downgrade_lock(parent, AuLock_IR);
out_parent:
di_read_unlock(parent, AuLock_IR);
dput(parent);
out:
AuTraceErr(err);
return err;
}
int au_do_open(struct file *file, int (*open)(struct file *file, int flags),
struct au_fidir *fidir)
{
int err;
struct dentry *dentry;
struct au_finfo *finfo;
err = au_finfo_init(file, fidir);
if (unlikely(err))
goto out;
dentry = file->f_path.dentry;
di_write_lock_child(dentry);
err = au_cmoo(dentry);
di_downgrade_lock(dentry, AuLock_IR);
if (!err)
err = open(file, vfsub_file_flags(file));
di_read_unlock(dentry, AuLock_IR);
finfo = au_fi(file);
if (!err) {
finfo->fi_file = file;
au_sphl_add(&finfo->fi_hlist,
&au_sbi(file->f_path.dentry->d_sb)->si_files);
}
fi_write_unlock(file);
if (unlikely(err)) {
finfo->fi_hdir = NULL;
au_finfo_fin(file);
}
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;
}
int aufs_rmdir(struct inode *dir, struct dentry *dentry)
{
int err, rmdir_later;
aufs_bindex_t bwh, bindex, bstart;
struct au_dtime dt;
struct au_pin pin;
struct inode *inode;
struct dentry *parent, *wh_dentry, *h_dentry;
struct au_whtmp_rmdir *args;
IMustLock(dir);
err = aufs_read_lock(dentry, AuLock_DW | AuLock_FLUSH | AuLock_GEN);
if (unlikely(err))
goto out;
/* VFS already unhashes it */
inode = dentry->d_inode;
err = -ENOENT;
if (unlikely(!inode || !inode->i_nlink
|| IS_DEADDIR(inode)))
goto out_unlock;
IMustLock(inode);
err = -ENOTDIR;
if (unlikely(!S_ISDIR(inode->i_mode)))
goto out_unlock; /* possible? */
err = -ENOMEM;
args = au_whtmp_rmdir_alloc(dir->i_sb, GFP_NOFS);
if (unlikely(!args))
goto out_unlock;
parent = dentry->d_parent; /* dir inode is locked */
di_write_lock_parent(parent);
err = au_test_empty(dentry, &args->whlist);
if (unlikely(err))
goto out_parent;
bstart = au_dbstart(dentry);
bwh = au_dbwh(dentry);
bindex = -1;
wh_dentry = lock_hdir_create_wh(dentry, /*isdir*/1, &bindex, &dt, &pin);
err = PTR_ERR(wh_dentry);
if (IS_ERR(wh_dentry))
goto out_parent;
h_dentry = au_h_dptr(dentry, bstart);
dget(h_dentry);
rmdir_later = 0;
if (bindex == bstart) {
err = renwh_and_rmdir(dentry, bstart, &args->whlist, dir);
if (err > 0) {
rmdir_later = err;
err = 0;
}
} else {
/* stop monitoring */
au_hn_free(au_hi(inode, bstart));
/* dir inode is locked */
IMustLock(wh_dentry->d_parent->d_inode);
err = 0;
}
if (!err) {
vfsub_dead_dir(inode);
au_set_dbdiropq(dentry, -1);
epilog(dir, dentry, bindex);
if (rmdir_later) {
au_whtmp_kick_rmdir(dir, bstart, h_dentry, args);
args = NULL;
}
goto out_unpin; /* success */
}
/* revert */
AuLabel(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_dentry);
out_parent:
di_write_unlock(parent);
if (args)
au_whtmp_rmdir_free(args);
out_unlock:
aufs_read_unlock(dentry, AuLock_DW);
out:
AuTraceErr(err);
return err;
}
/* lock them all */
static int au_do_lock(const unsigned char dmsg, struct au_mvd_args *a)
{
int err;
struct dentry *h_trap;
a->mvd_h_src_sb = au_sbr_sb(a->sb, a->mvd_bsrc);
a->mvd_h_dst_sb = au_sbr_sb(a->sb, a->mvd_bdst);
err = au_pin(&a->mvd_pin_dst, a->dentry, a->mvd_bdst,
au_opt_udba(a->sb),
AuPin_MNT_WRITE | AuPin_DI_LOCKED);
AuTraceErr(err);
if (unlikely(err)) {
AU_MVD_PR(dmsg, "pin_dst failed\n");
goto out;
}
if (a->mvd_h_src_sb != a->mvd_h_dst_sb) {
a->rename_lock = 0;
au_pin_init(&a->mvd_pin_src, a->dentry, a->mvd_bsrc,
AuLsc_DI_PARENT, AuLsc_I_PARENT3,
au_opt_udba(a->sb),
AuPin_MNT_WRITE | AuPin_DI_LOCKED);
err = au_do_pin(&a->mvd_pin_src);
AuTraceErr(err);
a->mvd_h_src_dir = d_inode(a->mvd_h_src_parent);
if (unlikely(err)) {
AU_MVD_PR(dmsg, "pin_src failed\n");
goto out_dst;
}
goto out; /* success */
}
a->rename_lock = 1;
au_pin_hdir_unlock(&a->mvd_pin_dst);
err = au_pin(&a->mvd_pin_src, a->dentry, a->mvd_bsrc,
au_opt_udba(a->sb),
AuPin_MNT_WRITE | AuPin_DI_LOCKED);
AuTraceErr(err);
a->mvd_h_src_dir = d_inode(a->mvd_h_src_parent);
if (unlikely(err)) {
AU_MVD_PR(dmsg, "pin_src failed\n");
au_pin_hdir_lock(&a->mvd_pin_dst);
goto out_dst;
}
au_pin_hdir_unlock(&a->mvd_pin_src);
h_trap = vfsub_lock_rename(a->mvd_h_src_parent, a->mvd_hdir_src,
a->mvd_h_dst_parent, a->mvd_hdir_dst);
if (h_trap) {
err = (h_trap != a->mvd_h_src_parent);
if (err)
err = (h_trap != a->mvd_h_dst_parent);
}
BUG_ON(err); /* it should never happen */
if (unlikely(a->mvd_h_src_dir != au_pinned_h_dir(&a->mvd_pin_src))) {
err = -EBUSY;
AuTraceErr(err);
vfsub_unlock_rename(a->mvd_h_src_parent, a->mvd_hdir_src,
a->mvd_h_dst_parent, a->mvd_hdir_dst);
au_pin_hdir_lock(&a->mvd_pin_src);
au_unpin(&a->mvd_pin_src);
au_pin_hdir_lock(&a->mvd_pin_dst);
goto out_dst;
}
goto out; /* success */
out_dst:
au_unpin(&a->mvd_pin_dst);
out:
AuTraceErr(err);
return err;
}
static int __init aufs_init(void)
{
int err, i;
char *p;
au_debug_init();
#ifdef CONFIG_AUFS_INO_T_64
BUILD_BUG_ON(sizeof(ino_t) != sizeof(long long));
#else
BUILD_BUG_ON(sizeof(ino_t) != sizeof(int));
#endif
p = au_esc_chars;
for (i = 1; i <= ' '; i++)
*p++ = i;
*p++ = '\\';
*p++ = '\x7f';
*p = 0;
au_dir_roflags = au_file_roflags(O_DIRECTORY | O_LARGEFILE);
err = -EINVAL;
if (unlikely(aufs_nwkq <= 0))
goto out;
err = sysaufs_init();
if (unlikely(err))
goto out;
err = au_wkq_init();
if (unlikely(err))
goto out_sysaufs;
err = au_inotify_init();
if (unlikely(err))
goto out_wkq;
err = au_sysrq_init();
if (unlikely(err))
goto out_inotify;
err = create_cache();
if (unlikely(err))
goto out_sysrq;
err = register_filesystem(&aufs_fs_type);
if (unlikely(err))
goto out_cache;
pr_info(AUFS_NAME " " AUFS_VERSION "\n");
return 0; /* success */
out_cache:
destroy_cache();
out_sysrq:
au_sysrq_fin();
out_inotify:
au_inotify_fin();
out_wkq:
au_wkq_fin();
out_sysaufs:
sysaufs_fin();
out:
AuTraceErr(err);
return err;
}
static int au_wbr_fd(struct path *path, struct aufs_wbr_fd __user *arg)
{
int err, fd;
aufs_bindex_t wbi, bindex, bend;
struct file *h_file;
struct super_block *sb;
struct dentry *root;
struct au_branch *br;
struct aufs_wbr_fd wbrfd = {
.oflags = au_dir_roflags,
.brid = -1
};
const int valid = O_RDONLY | O_NONBLOCK | O_LARGEFILE | O_DIRECTORY
| O_NOATIME | O_CLOEXEC;
AuDebugOn(wbrfd.oflags & ~valid);
if (arg) {
err = copy_from_user(&wbrfd, arg, sizeof(wbrfd));
if (unlikely(err)) {
err = -EFAULT;
goto out;
}
err = -EINVAL;
AuDbg("wbrfd{0%o, %d}\n", wbrfd.oflags, wbrfd.brid);
wbrfd.oflags |= au_dir_roflags;
AuDbg("0%o\n", wbrfd.oflags);
if (unlikely(wbrfd.oflags & ~valid))
goto out;
}
fd = get_unused_fd();
err = fd;
if (unlikely(fd < 0))
goto out;
h_file = ERR_PTR(-EINVAL);
wbi = 0;
br = NULL;
sb = path->dentry->d_sb;
root = sb->s_root;
aufs_read_lock(root, AuLock_IR);
bend = au_sbend(sb);
if (wbrfd.brid >= 0) {
wbi = au_br_index(sb, wbrfd.brid);
if (unlikely(wbi < 0 || wbi > bend))
goto out_unlock;
}
h_file = ERR_PTR(-ENOENT);
br = au_sbr(sb, wbi);
if (!au_br_writable(br->br_perm)) {
if (arg)
goto out_unlock;
bindex = wbi + 1;
wbi = -1;
for (; bindex <= bend; bindex++) {
br = au_sbr(sb, bindex);
if (au_br_writable(br->br_perm)) {
wbi = bindex;
br = au_sbr(sb, wbi);
break;
}
}
}
AuDbg("wbi %d\n", wbi);
if (wbi >= 0)
h_file = au_h_open(root, wbi, wbrfd.oflags, NULL,
/*force_wr*/0);
out_unlock:
aufs_read_unlock(root, AuLock_IR);
err = PTR_ERR(h_file);
if (IS_ERR(h_file))
goto out_fd;
atomic_dec(&br->br_count); /* cf. au_h_open() */
fd_install(fd, h_file);
err = fd;
goto out; /* success */
out_fd:
put_unused_fd(fd);
out:
AuTraceErr(err);
return err;
}
/* ---------------------------------------------------------------------- */
long aufs_ioctl_dir(struct file *file, unsigned int cmd, unsigned long arg)
{
long err;
struct dentry *dentry;
switch (cmd) {
case AUFS_CTL_RDU:
case AUFS_CTL_RDU_INO:
err = au_rdu_ioctl(file, cmd, arg);
break;
case AUFS_CTL_WBR_FD:
err = au_wbr_fd(&file->f_path, (void __user *)arg);
break;
case AUFS_CTL_IBUSY:
err = au_ibusy_ioctl(file, arg);
break;
case AUFS_CTL_BRINFO:
err = au_brinfo_ioctl(file, arg);
break;
case AUFS_CTL_FHSM_FD:
dentry = file->f_dentry;
if (IS_ROOT(dentry))
err = au_fhsm_fd(dentry->d_sb, arg);
else
err = -ENOTTY;
break;
default:
/* do not call the lower */
AuDbg("0x%x\n", cmd);
err = -ENOTTY;
}
AuTraceErr(err);
return err;
}