/* 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->pin,
.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;
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 (h_path.dentry->d_inode) {
h_path.mnt = au_br_mnt(br);
err = vfsub_unlink(a->mvd_h_dst_parent->d_inode, &h_path,
/*force*/0);
if (unlikely(err))
AU_MVD_PR(dmsg, "wh_unlink failed\n");
}
dput(h_path.dentry);
out:
AuTraceErr(err);
return err;
}
static void au_ren_rev_cpup(int err, struct au_ren_args *a)
{
int rerr;
a->h_path.dentry = a->dst_h_dentry;
rerr = vfsub_unlink(a->dst_h_dir, &a->h_path, /*force*/0);
au_set_h_dptr(a->src_dentry, a->btgt, NULL);
au_set_dbstart(a->src_dentry, a->src_bstart);
if (rerr)
RevertFailure("unlink %.*s", AuDLNPair(a->dst_h_dentry));
}
static int do_unlink_wh(struct inode *h_dir, struct path *h_path)
{
int force;
/*
* forces superio when the dir has a sticky bit.
* this may be a violation of unix fs semantics.
*/
force = (h_dir->i_mode & S_ISVTX)
&& !uid_eq(current_fsuid(), h_path->dentry->d_inode->i_uid);
return vfsub_unlink(h_dir, h_path, force);
}
/*
* unlink the topmost h_dentry
* Note: the target file MAY be modified by UDBA between this mutex_unlock() and
* mutex_lock() in vfs_unlink(). in this case, such changes may be lost.
*/
static int au_do_unlink(const unsigned char dmsg, struct au_mvd_args *a)
{
int err;
struct path h_path;
h_path.mnt = au_sbr_mnt(a->sb, a->mvd_bsrc);
h_path.dentry = au_h_dptr(a->dentry, a->mvd_bsrc);
err = vfsub_unlink(a->mvd_h_src_dir, &h_path, /*force*/0);
if (unlikely(err))
AU_MVD_PR(dmsg, "unlink failed\n");
AuTraceErr(err);
return err;
}
static void au_wh_clean(struct inode *h_dir, struct path *whpath,
const int isdir)
{
int err;
if (!whpath->dentry->d_inode)
return;
if (isdir)
err = vfsub_rmdir(h_dir, whpath);
else
err = vfsub_unlink(h_dir, whpath, /*force*/0);
if (unlikely(err))
pr_warn("failed removing %.*s (%d), ignored.\n",
AuDLNPair(whpath->dentry), err);
}
/*
* unlink the topmost h_dentry
*/
static int au_do_unlink(const unsigned char dmsg, struct au_mvd_args *a)
{
int err;
struct path h_path;
struct inode *delegated;
h_path.mnt = au_sbr_mnt(a->sb, a->mvd_bsrc);
h_path.dentry = au_h_dptr(a->dentry, a->mvd_bsrc);
delegated = NULL;
err = vfsub_unlink(a->mvd_h_src_dir, &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, "unlink failed\n");
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 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_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;
}
/*
* 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, a->bsrc,
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;
}
/* create a pseudo-link */
static int do_whplink(struct qstr *tgt, struct dentry *h_parent,
struct dentry *h_dentry, struct au_branch *br)
{
int err;
struct path h_path = {
.mnt = br->br_mnt
};
struct inode *h_dir;
h_dir = h_parent->d_inode;
again:
h_path.dentry = au_lkup_one(tgt, h_parent, br, /*nd*/NULL);
err = PTR_ERR(h_path.dentry);
if (IS_ERR(h_path.dentry))
goto out;
err = 0;
/* wh.plink dir is not monitored */
if (h_path.dentry->d_inode
&& h_path.dentry->d_inode != h_dentry->d_inode) {
err = vfsub_unlink(h_dir, &h_path, /*force*/0);
dput(h_path.dentry);
h_path.dentry = NULL;
if (!err)
goto again;
}
if (!err && !h_path.dentry->d_inode)
err = vfsub_link(h_dentry, h_dir, &h_path);
dput(h_path.dentry);
out:
return err;
}
struct do_whplink_args {
int *errp;
struct qstr *tgt;
struct dentry *h_parent;
struct dentry *h_dentry;
struct au_branch *br;
};
static void call_do_whplink(void *args)
{
struct do_whplink_args *a = args;
*a->errp = do_whplink(a->tgt, a->h_parent, a->h_dentry, a->br);
}
static int whplink(struct dentry *h_dentry, struct inode *inode,
aufs_bindex_t bindex, struct au_branch *br)
{
int err, wkq_err;
struct au_wbr *wbr;
struct dentry *h_parent;
struct inode *h_dir;
char a[PLINK_NAME_LEN];
struct qstr tgtname = {
.name = a
};
wbr = au_sbr(inode->i_sb, bindex)->br_wbr;
h_parent = wbr->wbr_plink;
h_dir = h_parent->d_inode;
tgtname.len = plink_name(a, sizeof(a), inode, bindex);
/* always superio. */
mutex_lock_nested(&h_dir->i_mutex, AuLsc_I_CHILD2);
if (!au_test_wkq(current)) {
struct do_whplink_args args = {
.errp = &err,
.tgt = &tgtname,
.h_parent = h_parent,
.h_dentry = h_dentry,
.br = br
};
wkq_err = au_wkq_wait(call_do_whplink, &args);
if (unlikely(wkq_err))
err = wkq_err;
} else
/*
* 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;
}
int aufs_unlink(struct inode *dir, struct dentry *dentry)
{
int err, dlgt;
struct inode *inode, *hidden_dir;
struct dentry *parent, *wh_dentry, *hidden_dentry, *hidden_parent;
struct dtime dt;
aufs_bindex_t bwh, bindex, bstart;
LKTRTrace("i%lu, %.*s\n", dir->i_ino, DLNPair(dentry));
IMustLock(dir);
inode = dentry->d_inode;
if (unlikely(!inode))
return -ENOENT; // possible?
IMustLock(inode);
aufs_read_lock(dentry, AUFS_D_WLOCK);
parent = dentry->d_parent;
di_write_lock_parent(parent);
bstart = dbstart(dentry);
bwh = dbwh(dentry);
bindex = -1;
wh_dentry = lock_hdir_create_wh(dentry, /*isdir*/0, &bindex, &dt);
//wh_dentry = ERR_PTR(-1);
err = PTR_ERR(wh_dentry);
if (IS_ERR(wh_dentry))
goto out;
dlgt = need_dlgt(dir->i_sb);
hidden_dentry = au_h_dptr(dentry);
dget(hidden_dentry);
hidden_parent = hidden_dentry->d_parent;
hidden_dir = hidden_parent->d_inode;
if (bindex == bstart) {
err = vfsub_unlink(hidden_dir, hidden_dentry, dlgt);
//err = -1;
} else {
DEBUG_ON(!wh_dentry);
hidden_parent = wh_dentry->d_parent;
DEBUG_ON(hidden_parent != au_h_dptr_i(parent, bindex));
hidden_dir = hidden_parent->d_inode;
IMustLock(hidden_dir);
err = 0;
}
if (!err) {
inode->i_nlink--;
epilog(dir, dentry, bindex);
goto out_unlock; /* success */
}
/* revert */
if (wh_dentry) {
int rerr;
rerr = do_revert(err, wh_dentry, dentry, bwh, &dt, dlgt);
if (rerr)
err = rerr;
}
out_unlock:
hdir_unlock(hidden_dir, dir, bindex);
dput(wh_dentry);
dput(hidden_dentry);
out:
di_write_unlock(parent);
aufs_read_unlock(dentry, AUFS_D_WLOCK);
TraceErr(err);
return err;
}
/*
* copyup the deleted file for writing.
*/
static int cpup_wh_file(struct file *file, aufs_bindex_t bdst, loff_t len)
{
int err;
struct dentry *dentry, *parent, *hidden_parent, *tmp_dentry;
struct dentry *hidden_dentry_bstart, *hidden_dentry_bdst;
struct inode *hidden_dir;
aufs_bindex_t bstart;
struct aufs_dinfo *dinfo;
struct dtime dt;
struct lkup_args lkup;
struct super_block *sb;
dentry = file->f_dentry;
LKTRTrace("%.*s, bdst %d, len %Lu\n", DLNPair(dentry), bdst, len);
DEBUG_ON(S_ISDIR(dentry->d_inode->i_mode)
|| !(file->f_mode & FMODE_WRITE));
DiMustWriteLock(dentry);
parent = dentry->d_parent;
IiMustAnyLock(parent->d_inode);
hidden_parent = au_h_dptr_i(parent, bdst);
DEBUG_ON(!hidden_parent);
hidden_dir = hidden_parent->d_inode;
DEBUG_ON(!hidden_dir);
IMustLock(hidden_dir);
sb = parent->d_sb;
lkup.nfsmnt = au_nfsmnt(sb, bdst);
lkup.dlgt = need_dlgt(sb);
tmp_dentry = lkup_whtmp(hidden_parent, &dentry->d_name, &lkup);
//if (LktrCond) {dput(tmp_dentry); tmp_dentry = ERR_PTR(-1);}
err = PTR_ERR(tmp_dentry);
if (IS_ERR(tmp_dentry))
goto out;
dtime_store(&dt, parent, hidden_parent);
dinfo = dtodi(dentry);
bstart = dinfo->di_bstart;
hidden_dentry_bdst = dinfo->di_hdentry[0 + bdst].hd_dentry;
hidden_dentry_bstart = dinfo->di_hdentry[0 + bstart].hd_dentry;
dinfo->di_bstart = bdst;
dinfo->di_hdentry[0 + bdst].hd_dentry = tmp_dentry;
dinfo->di_hdentry[0 + bstart].hd_dentry = au_h_fptr(file)->f_dentry;
err = cpup_single(dentry, bdst, bstart, len,
au_flags_cpup(!CPUP_DTIME, parent));
//if (LktrCond) err = -1;
if (!err)
err = au_reopen_nondir(file);
//err = -1;
if (unlikely(err)) {
dinfo->di_hdentry[0 + bstart].hd_dentry = hidden_dentry_bstart;
dinfo->di_hdentry[0 + bdst].hd_dentry = hidden_dentry_bdst;
dinfo->di_bstart = bstart;
goto out_tmp;
}
DEBUG_ON(!d_unhashed(dentry));
err = vfsub_unlink(hidden_dir, tmp_dentry, lkup.dlgt);
//if (LktrCond) err = -1;
if (unlikely(err)) {
IOErr("failed remove copied-up tmp file %.*s(%d)\n",
DLNPair(tmp_dentry), err);
err = -EIO;
}
dtime_revert(&dt, !CPUP_LOCKED_GHDIR);
out_tmp:
dput(tmp_dentry);
out:
TraceErr(err);
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;
}
