void di_write_lock2_parent(struct dentry *d1, struct dentry *d2, int isdir)
{
AuDebugOn(d1 == d2
|| d1->d_inode == d2->d_inode
|| d1->d_sb != d2->d_sb);
if (isdir && au_test_subdir(d1, d2)) {
di_write_lock_parent(d1);
di_write_lock_parent2(d2);
} else {
/* there should be no races */
di_write_lock_parent(d2);
di_write_lock_parent2(d1);
}
}
static int do_coo(struct dentry *dentry, aufs_bindex_t bstart)
{
int err;
struct dentry *parent, *h_parent, *h_dentry;
aufs_bindex_t bcpup;
struct inode *h_dir, *h_inode, *dir;
LKTRTrace("%.*s\n", DLNPair(dentry));
DEBUG_ON(IS_ROOT(dentry));
DiMustWriteLock(dentry);
parent = dentry->d_parent; // dget_parent()
di_write_lock_parent(parent);
bcpup = err = find_rw_parent_br(dentry, bstart);
//bcpup = err = find_rw_br(sb, bstart);
if (unlikely(err < 0)) {
err = 0; // stop copyup, it is not an error
goto out;
}
err = 0;
h_parent = au_h_dptr_i(parent, bcpup);
if (!h_parent) {
err = cpup_dirs(dentry, bcpup, NULL);
if (unlikely(err))
goto out;
h_parent = au_h_dptr_i(parent, bcpup);
}
h_dir = h_parent->d_inode;
h_dentry = au_h_dptr_i(dentry, bstart);
h_inode = h_dentry->d_inode;
dir = parent->d_inode;
hdir_lock(h_dir, dir, bcpup);
hi_lock_child(h_inode);
DEBUG_ON(au_h_dptr_i(dentry, bcpup));
err = sio_cpup_simple(dentry, bcpup, -1,
au_flags_cpup(CPUP_DTIME, parent));
TraceErr(err);
i_unlock(h_inode);
hdir_unlock(h_dir, dir, bcpup);
out:
di_write_unlock(parent);
TraceErr(err);
return err;
}
static int au_wr_dir_cpup(struct dentry *dentry, struct dentry *parent,
const unsigned char add_entry, aufs_bindex_t bcpup,
aufs_bindex_t bstart)
{
int err;
struct dentry *h_parent;
struct inode *h_dir;
if (add_entry)
IMustLock(parent->d_inode);
else
di_write_lock_parent(parent);
err = 0;
if (!au_h_dptr(parent, bcpup)) {
if (bstart < bcpup)
err = au_cpdown_dirs(dentry, bcpup);
else
err = au_cpup_dirs(dentry, bcpup);
}
if (!err && add_entry) {
h_parent = au_h_dptr(parent, bcpup);
h_dir = h_parent->d_inode;
mutex_lock_nested(&h_dir->i_mutex, AuLsc_I_PARENT);
err = au_lkup_neg(dentry, bcpup);
/* todo: no unlock here */
mutex_unlock(&h_dir->i_mutex);
AuDbg("bcpup %d\n", bcpup);
if (!err) {
if (!dentry->d_inode)
au_set_h_dptr(dentry, bstart, NULL);
au_update_dbrange(dentry, /*do_put_zero*/0);
}
}
if (!add_entry)
di_write_unlock(parent);
if (!err)
err = bcpup; /* success */
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;
err = au_alive_dir(dentry);
if (unlikely(err))
goto out_unlock;
inode = dentry->d_inode;
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;
}
/*
* when an error happened, remove the created whiteout and revert everything.
*/
static int do_revert(int err, struct inode *dir, aufs_bindex_t bindex,
aufs_bindex_t bwh, struct dentry *wh_dentry,
struct dentry *dentry, struct au_dtime *dt)
{
int rerr;
struct path h_path = {
.dentry = wh_dentry,
.mnt = au_sbr_mnt(dir->i_sb, bindex)
};
rerr = au_wh_unlink_dentry(au_h_iptr(dir, bindex), &h_path, dentry);
if (!rerr) {
au_set_dbwh(dentry, bwh);
au_dtime_revert(dt);
return 0;
}
AuIOErr("%.*s reverting whiteout failed(%d, %d)\n",
AuDLNPair(dentry), err, rerr);
return -EIO;
}
/* ---------------------------------------------------------------------- */
int aufs_unlink(struct inode *dir, struct dentry *dentry)
{
int err;
aufs_bindex_t bwh, bindex, bstart;
struct au_dtime dt;
struct au_pin pin;
struct path h_path;
struct inode *inode, *h_dir;
struct dentry *parent, *wh_dentry;
IMustLock(dir);
err = aufs_read_lock(dentry, AuLock_DW | AuLock_GEN);
if (unlikely(err))
goto out;
err = au_d_hashed_positive(dentry);
if (unlikely(err))
goto out_unlock;
inode = dentry->d_inode;
IMustLock(inode);
err = -EISDIR;
if (unlikely(S_ISDIR(inode->i_mode)))
goto out_unlock; /* possible? */
bstart = au_dbstart(dentry);
bwh = au_dbwh(dentry);
bindex = -1;
parent = dentry->d_parent; /* dir inode is locked */
di_write_lock_parent(parent);
wh_dentry = lock_hdir_create_wh(dentry, /*isdir*/0, &bindex, &dt, &pin);
err = PTR_ERR(wh_dentry);
if (IS_ERR(wh_dentry))
goto out_parent;
h_path.mnt = au_sbr_mnt(dentry->d_sb, bstart);
h_path.dentry = au_h_dptr(dentry, bstart);
dget(h_path.dentry);
if (bindex == bstart) {
h_dir = au_pinned_h_dir(&pin);
err = vfsub_unlink(h_dir, &h_path, /*force*/0);
} else {
/* dir inode is locked */
h_dir = wh_dentry->d_parent->d_inode;
IMustLock(h_dir);
err = 0;
}
if (!err) {
vfsub_drop_nlink(inode);
epilog(dir, dentry, bindex);
/* update target timestamps */
if (bindex == bstart) {
vfsub_update_h_iattr(&h_path, /*did*/NULL); /*ignore*/
inode->i_ctime = h_path.dentry->d_inode->i_ctime;
} else
/* todo: this timestamp may be reverted later */
inode->i_ctime = h_dir->i_ctime;
goto out_unpin; /* success */
}
/* revert */
if (wh_dentry) {
int rerr;
rerr = do_revert(err, dir, bindex, bwh, wh_dentry, dentry, &dt);
if (rerr)
err = rerr;
}
out_unpin:
au_unpin(&pin);
dput(wh_dentry);
dput(h_path.dentry);
out_parent:
di_write_unlock(parent);
out_unlock:
aufs_read_unlock(dentry, AuLock_DW);
out:
return err;
}
int aufs_rename(struct inode *_src_dir, struct dentry *_src_dentry,
struct inode *_dst_dir, struct dentry *_dst_dentry)
{
int err, flags;
/* reduce stack space */
struct au_ren_args *a;
AuDbg("%.*s, %.*s\n", AuDLNPair(_src_dentry), AuDLNPair(_dst_dentry));
IMustLock(_src_dir);
IMustLock(_dst_dir);
err = -ENOMEM;
BUILD_BUG_ON(sizeof(*a) > PAGE_SIZE);
a = kzalloc(sizeof(*a), GFP_NOFS);
if (unlikely(!a))
goto out;
a->src_dir = _src_dir;
a->src_dentry = _src_dentry;
a->src_inode = a->src_dentry->d_inode;
a->src_parent = a->src_dentry->d_parent; /* dir inode is locked */
a->dst_dir = _dst_dir;
a->dst_dentry = _dst_dentry;
a->dst_inode = a->dst_dentry->d_inode;
a->dst_parent = a->dst_dentry->d_parent; /* dir inode is locked */
if (a->dst_inode) {
IMustLock(a->dst_inode);
au_igrab(a->dst_inode);
}
err = -ENOTDIR;
flags = AuLock_FLUSH | AuLock_NOPLM | AuLock_GEN;
if (S_ISDIR(a->src_inode->i_mode)) {
au_fset_ren(a->flags, ISDIR);
if (unlikely(a->dst_inode && !S_ISDIR(a->dst_inode->i_mode)))
goto out_free;
err = aufs_read_and_write_lock2(a->dst_dentry, a->src_dentry,
AuLock_DIR | flags);
} else
err = aufs_read_and_write_lock2(a->dst_dentry, a->src_dentry,
flags);
if (unlikely(err))
goto out_free;
err = au_d_hashed_positive(a->src_dentry);
if (unlikely(err))
goto out_unlock;
err = -ENOENT;
if (a->dst_inode) {
/*
* If it is a dir, VFS unhash dst_dentry before this
* function. It means we cannot rely upon d_unhashed().
*/
if (unlikely(!a->dst_inode->i_nlink))
goto out_unlock;
if (!S_ISDIR(a->dst_inode->i_mode)) {
err = au_d_hashed_positive(a->dst_dentry);
if (unlikely(err))
goto out_unlock;
} else if (unlikely(IS_DEADDIR(a->dst_inode)))
goto out_unlock;
} else if (unlikely(d_unhashed(a->dst_dentry)))
goto out_unlock;
au_fset_ren(a->flags, ISSAMEDIR); /* temporary */
di_write_lock_parent(a->dst_parent);
/* which branch we process */
err = au_ren_wbr(a);
if (unlikely(err < 0))
goto out_parent;
a->br = au_sbr(a->dst_dentry->d_sb, a->btgt);
a->h_path.mnt = a->br->br_mnt;
/* are they available to be renamed */
err = au_ren_may_dir(a);
if (unlikely(err))
goto out_children;
/* prepare the writable parent dir on the same branch */
if (a->dst_bstart == a->btgt) {
au_fset_ren(a->flags, WHDST);
} else {
err = au_cpup_dirs(a->dst_dentry, a->btgt);
if (unlikely(err))
goto out_children;
}
if (a->src_dir != a->dst_dir) {
/*
* this temporary unlock is safe,
* because both dir->i_mutex are locked.
*/
di_write_unlock(a->dst_parent);
di_write_lock_parent(a->src_parent);
err = au_wr_dir_need_wh(a->src_dentry,
au_ftest_ren(a->flags, ISDIR),
&a->btgt);
di_write_unlock(a->src_parent);
di_write_lock2_parent(a->src_parent, a->dst_parent, /*isdir*/1);
au_fclr_ren(a->flags, ISSAMEDIR);
} else
err = au_wr_dir_need_wh(a->src_dentry,
au_ftest_ren(a->flags, ISDIR),
&a->btgt);
if (unlikely(err < 0))
goto out_children;
if (err)
au_fset_ren(a->flags, WHSRC);
/* lock them all */
err = au_ren_lock(a);
if (unlikely(err))
goto out_children;
if (!au_opt_test(au_mntflags(a->dst_dir->i_sb), UDBA_NONE))
err = au_may_ren(a);
else if (unlikely(a->dst_dentry->d_name.len > AUFS_MAX_NAMELEN))
err = -ENAMETOOLONG;
if (unlikely(err))
goto out_hdir;
/* store timestamps to be revertible */
au_ren_dt(a);
/* here we go */
err = do_rename(a);
if (unlikely(err))
goto out_dt;
/* update dir attributes */
au_ren_refresh_dir(a);
/* dput/iput all lower dentries */
au_ren_refresh(a);
goto out_hdir; /* success */
out_dt:
au_ren_rev_dt(err, a);
out_hdir:
au_ren_unlock(a);
out_children:
au_nhash_wh_free(&a->whlist);
if (err && a->dst_inode && a->dst_bstart != a->btgt) {
AuDbg("bstart %d, btgt %d\n", a->dst_bstart, a->btgt);
au_set_h_dptr(a->dst_dentry, a->btgt, NULL);
au_set_dbstart(a->dst_dentry, a->dst_bstart);
}
out_parent:
if (!err)
d_move(a->src_dentry, a->dst_dentry);
else {
au_update_dbstart(a->dst_dentry);
if (!a->dst_inode)
d_drop(a->dst_dentry);
}
if (au_ftest_ren(a->flags, ISSAMEDIR))
di_write_unlock(a->dst_parent);
else
di_write_unlock2(a->src_parent, a->dst_parent);
out_unlock:
aufs_read_and_write_unlock2(a->dst_dentry, a->src_dentry);
out_free:
iput(a->dst_inode);
if (a->thargs)
au_whtmp_rmdir_free(a->thargs);
kfree(a);
out:
AuTraceErr(err);
return err;
}
int au_mvdown(struct dentry *dentry, struct aufs_mvdown __user *uarg)
{
int err, e;
unsigned char dmsg;
struct au_mvd_args *args;
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 = d_inode(dentry);
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);
mutex_lock_nested(&args->dir->i_mutex, 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;
}
mutex_lock_nested(&args->inode->i_mutex, I_MUTEX_CHILD);
err = aufs_read_lock(dentry, AuLock_DW | AuLock_FLUSH);
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(args->inode);
au_cpup_igen(args->inode, au_h_iptr(args->inode, args->mvd_bdst));
/* au_digen_dec(dentry); */
out_parent:
di_write_unlock(args->parent);
aufs_read_unlock(dentry, AuLock_DW);
out_inode:
mutex_unlock(&args->inode->i_mutex);
out_dir:
mutex_unlock(&args->dir->i_mutex);
out_free:
e = copy_to_user(uarg, &args->mvdown, sizeof(args->mvdown));
if (unlikely(e))
err = -EFAULT;
kfree(args);
out:
AuTraceErr(err);
return err;
}
int aufs_mkdir(struct inode *dir, struct dentry *dentry, int mode)
{
int err, rerr;
aufs_bindex_t bindex;
unsigned char diropq;
struct path h_path;
struct dentry *wh_dentry, *parent, *opq_dentry;
struct mutex *h_mtx;
struct super_block *sb;
struct {
struct au_pin pin;
struct au_dtime dt;
} *a; /* reduce the stack usage */
struct au_wr_dir_args wr_dir_args = {
.force_btgt = -1,
.flags = AuWrDir_ADD_ENTRY | AuWrDir_ISDIR
};
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_may_add(dentry);
if (unlikely(err))
goto out_unlock;
parent = dentry->d_parent; /* dir inode is locked */
di_write_lock_parent(parent);
wh_dentry = lock_hdir_lkup_wh(dentry, &a->dt, /*src_dentry*/NULL,
&a->pin, &wr_dir_args);
err = PTR_ERR(wh_dentry);
if (IS_ERR(wh_dentry))
goto out_parent;
sb = dentry->d_sb;
bindex = au_dbstart(dentry);
h_path.dentry = au_h_dptr(dentry, bindex);
h_path.mnt = au_sbr_mnt(sb, bindex);
err = vfsub_mkdir(au_pinned_h_dir(&a->pin), &h_path, mode);
if (unlikely(err))
goto out_unpin;
/* make the dir opaque */
diropq = 0;
h_mtx = &h_path.dentry->d_inode->i_mutex;
if (wh_dentry
|| au_opt_test(au_mntflags(sb), ALWAYS_DIROPQ)) {
mutex_lock_nested(h_mtx, AuLsc_I_CHILD);
opq_dentry = au_diropq_create(dentry, bindex);
mutex_unlock(h_mtx);
err = PTR_ERR(opq_dentry);
if (IS_ERR(opq_dentry))
goto out_dir;
dput(opq_dentry);
diropq = 1;
}
err = epilog(dir, bindex, wh_dentry, dentry);
if (!err) {
inc_nlink(dir);
goto out_unpin; /* success */
}
/* revert */
if (diropq) {
AuLabel(revert opq);
mutex_lock_nested(h_mtx, AuLsc_I_CHILD);
rerr = au_diropq_remove(dentry, bindex);
mutex_unlock(h_mtx);
if (rerr) {
AuIOErr("%.*s reverting diropq failed(%d, %d)\n",
AuDLNPair(dentry), err, rerr);
err = -EIO;
}
}
out_dir:
AuLabel(revert dir);
rerr = vfsub_rmdir(au_pinned_h_dir(&a->pin), &h_path);
if (rerr) {
AuIOErr("%.*s reverting dir failed(%d, %d)\n",
AuDLNPair(dentry), err, rerr);
err = -EIO;
}
au_dtime_revert(&a->dt);
out_unpin:
au_unpin(&a->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_free:
kfree(a);
out:
return err;
}
static int au_ready_to_write_wh(struct file *file, loff_t len,
aufs_bindex_t bcpup, struct au_pin *pin)
{
int err;
struct inode *inode, *h_inode;
struct dentry *h_dentry, *hi_wh;
struct au_cp_generic cpg = {
.dentry = file->f_dentry,
.bdst = bcpup,
.bsrc = -1,
.len = len,
.pin = pin
};
au_update_dbstart(cpg.dentry);
inode = cpg.dentry->d_inode;
h_inode = NULL;
if (au_dbstart(cpg.dentry) <= bcpup
&& au_dbend(cpg.dentry) >= bcpup) {
h_dentry = au_h_dptr(cpg.dentry, bcpup);
if (h_dentry)
h_inode = h_dentry->d_inode;
}
hi_wh = au_hi_wh(inode, bcpup);
if (!hi_wh && !h_inode)
err = au_sio_cpup_wh(&cpg, file);
else
/* already copied-up after unlink */
err = au_reopen_wh(file, bcpup, hi_wh);
if (!err
&& inode->i_nlink > 1
&& au_opt_test(au_mntflags(cpg.dentry->d_sb), PLINK))
au_plink_append(inode, bcpup, au_h_dptr(cpg.dentry, bcpup));
return err;
}
/*
* prepare the @file for writing.
*/
int au_ready_to_write(struct file *file, loff_t len, struct au_pin *pin)
{
int err;
aufs_bindex_t dbstart;
struct dentry *parent, *h_dentry;
struct inode *inode;
struct super_block *sb;
struct file *h_file;
struct au_cp_generic cpg = {
.dentry = file->f_dentry,
.bdst = -1,
.bsrc = -1,
.len = len,
.pin = pin,
.flags = AuCpup_DTIME
};
sb = cpg.dentry->d_sb;
inode = cpg.dentry->d_inode;
AuDebugOn(au_special_file(inode->i_mode));
cpg.bsrc = au_fbstart(file);
err = au_test_ro(sb, cpg.bsrc, inode);
if (!err && (au_hf_top(file)->f_mode & FMODE_WRITE)) {
err = au_pin(pin, cpg.dentry, cpg.bsrc, AuOpt_UDBA_NONE,
/*flags*/0);
goto out;
}
/* need to cpup or reopen */
parent = dget_parent(cpg.dentry);
di_write_lock_parent(parent);
err = AuWbrCopyup(au_sbi(sb), cpg.dentry);
cpg.bdst = err;
if (unlikely(err < 0))
goto out_dgrade;
err = 0;
if (!d_unhashed(cpg.dentry) && !au_h_dptr(parent, cpg.bdst)) {
err = au_cpup_dirs(cpg.dentry, cpg.bdst);
if (unlikely(err))
goto out_dgrade;
}
err = au_pin(pin, cpg.dentry, cpg.bdst, AuOpt_UDBA_NONE,
AuPin_DI_LOCKED | AuPin_MNT_WRITE);
if (unlikely(err))
goto out_dgrade;
h_dentry = au_hf_top(file)->f_dentry;
dbstart = au_dbstart(cpg.dentry);
if (dbstart <= cpg.bdst) {
h_dentry = au_h_dptr(cpg.dentry, cpg.bdst);
AuDebugOn(!h_dentry);
cpg.bsrc = cpg.bdst;
}
if (dbstart <= cpg.bdst /* just reopen */
|| !d_unhashed(cpg.dentry) /* copyup and reopen */
) {
h_file = au_h_open_pre(cpg.dentry, cpg.bsrc, /*force_wr*/0);
if (IS_ERR(h_file))
err = PTR_ERR(h_file);
else {
di_downgrade_lock(parent, AuLock_IR);
if (dbstart > cpg.bdst)
err = au_sio_cpup_simple(&cpg);
if (!err)
err = au_reopen_nondir(file);
au_h_open_post(cpg.dentry, cpg.bsrc, h_file);
}
} else { /* copyup as wh and reopen */
/*
* since writable hfsplus branch is not supported,
* h_open_pre/post() are unnecessary.
*/
err = au_ready_to_write_wh(file, len, cpg.bdst, pin);
di_downgrade_lock(parent, AuLock_IR);
}
if (!err) {
au_pin_set_parent_lflag(pin, /*lflag*/0);
goto out_dput; /* success */
}
au_unpin(pin);
goto out_unlock;
out_dgrade:
di_downgrade_lock(parent, AuLock_IR);
out_unlock:
di_read_unlock(parent, AuLock_IR);
out_dput:
dput(parent);
out:
return err;
}
/* ---------------------------------------------------------------------- */
int au_do_flush(struct file *file, fl_owner_t id,
int (*flush)(struct file *file, fl_owner_t id))
{
int err;
struct super_block *sb;
struct inode *inode;
inode = file_inode(file);
sb = inode->i_sb;
si_noflush_read_lock(sb);
fi_read_lock(file);
ii_read_lock_child(inode);
err = flush(file, id);
au_cpup_attr_timesizes(inode);
ii_read_unlock(inode);
fi_read_unlock(file);
si_read_unlock(sb);
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;
}
/*
* 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_rmdir(struct inode *dir, struct dentry *dentry)
{
int err, rmdir_later;
struct inode *inode, *hidden_dir;
struct dentry *parent, *wh_dentry, *hidden_dentry, *hidden_parent;
struct dtime dt;
aufs_bindex_t bwh, bindex, bstart;
struct rmdir_whtmp_arg *arg;
struct aufs_nhash *whlist;
LKTRTrace("i%lu, %.*s\n", dir->i_ino, DLNPair(dentry));
IMustLock(dir);
inode = dentry->d_inode;
if (unlikely(!inode))
return -ENOENT; // possible?
IMustLock(inode);
whlist = nhash_new(GFP_KERNEL);
err = PTR_ERR(whlist);
if (IS_ERR(whlist))
goto out;
err = -ENOMEM;
arg = kmalloc(sizeof(*arg), GFP_KERNEL);
//arg = NULL;
if (unlikely(!arg))
goto out_whlist;
aufs_read_lock(dentry, AUFS_D_WLOCK);
parent = dentry->d_parent;
di_write_lock_parent(parent);
err = test_empty(dentry, whlist);
//err = -1;
if (unlikely(err))
goto out_arg;
bstart = dbstart(dentry);
bwh = dbwh(dentry);
bindex = -1;
wh_dentry = lock_hdir_create_wh(dentry, /*isdir*/ 1, &bindex, &dt);
//wh_dentry = ERR_PTR(-1);
err = PTR_ERR(wh_dentry);
if (IS_ERR(wh_dentry))
goto out_arg;
hidden_dentry = au_h_dptr(dentry);
dget(hidden_dentry);
hidden_parent = hidden_dentry->d_parent;
hidden_dir = hidden_parent->d_inode;
rmdir_later = 0;
if (bindex == bstart) {
IMustLock(hidden_dir);
err = renwh_and_rmdir(dentry, bstart, whlist, dir);
//err = -1;
if (err > 0) {
rmdir_later = err;
err = 0;
}
} 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) {
au_reset_hinotify(inode, /*flags*/0);
inode->i_nlink = 0;
set_dbdiropq(dentry, -1);
epilog(dir, dentry, bindex);
if (rmdir_later) {
kick_rmdir_whtmp(hidden_dentry, whlist, bstart, dir,
inode, arg);
arg = NULL;
}
goto out_unlock; /* success */
}
/* revert */
LKTRLabel(revert);
if (wh_dentry) {
int rerr;
rerr = do_revert(err, wh_dentry, dentry, bwh, &dt,
need_dlgt(dir->i_sb));
if (rerr)
err = rerr;
}
out_unlock:
hdir_unlock(hidden_dir, dir, bindex);
dput(wh_dentry);
dput(hidden_dentry);
out_arg:
di_write_unlock(parent);
aufs_read_unlock(dentry, AUFS_D_WLOCK);
kfree(arg);
out_whlist:
nhash_del(whlist);
out:
TraceErr(err);
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;
}
/*
* prepare the @file for writing.
*/
int au_ready_to_write(struct file *file, loff_t len)
{
int err;
struct dentry *dentry, *parent, *hidden_dentry, *hidden_parent;
struct inode *hidden_inode, *hidden_dir, *inode, *dir;
struct super_block *sb;
aufs_bindex_t bstart, bcpup;
dentry = file->f_dentry;
LKTRTrace("%.*s, len %Ld\n", DLNPair(dentry), len);
FiMustWriteLock(file);
sb = dentry->d_sb;
bstart = fbstart(file);
DEBUG_ON(ftobr(file, bstart) != stobr(sb, bstart));
inode = dentry->d_inode;
ii_read_lock_child(inode);
LKTRTrace("rdonly %d, bstart %d\n", test_ro(sb, bstart, inode), bstart);
err = test_ro(sb, bstart, inode);
ii_read_unlock(inode);
if (!err && (au_h_fptr(file)->f_mode & FMODE_WRITE))
return 0;
/* need to cpup */
parent = dentry->d_parent; // dget_parent()
di_write_lock_child(dentry);
di_write_lock_parent(parent);
bcpup = err = find_rw_parent_br(dentry, bstart);
//bcpup = err = find_rw_br(sb, bstart);
if (unlikely(err < 0))
goto out_unlock;
err = 0;
hidden_parent = au_h_dptr_i(parent, bcpup);
if (!hidden_parent) {
err = cpup_dirs(dentry, bcpup, NULL);
//if (LktrCond) err = -1;
if (unlikely(err))
goto out_unlock;
hidden_parent = au_h_dptr_i(parent, bcpup);
}
hidden_dir = hidden_parent->d_inode;
hidden_dentry = au_h_fptr(file)->f_dentry;
hidden_inode = hidden_dentry->d_inode;
dir = parent->d_inode;
hdir_lock(hidden_dir, dir, bcpup);
hi_lock_child(hidden_inode);
if (d_unhashed(dentry) || d_unhashed(hidden_dentry)
/* || !hidden_inode->i_nlink */) {
if (!au_test_perm(hidden_dir, MAY_EXEC | MAY_WRITE,
need_dlgt(sb)))
err = cpup_wh_file(file, bcpup, len);
else {
struct cpup_wh_file_args args = {
.errp = &err,
.file = file,
.bdst = bcpup,
.len = len
};
au_wkq_wait(call_cpup_wh_file, &args, /*dlgt*/0);
}
//if (LktrCond) err = -1;
TraceErr(err);
} else {
if (!au_h_dptr_i(dentry, bcpup))
/*
* prepare the @file for writing.
*/
int au_ready_to_write(struct file *file, loff_t len, struct au_pin *pin)
{
int err;
aufs_bindex_t bstart, bcpup;
struct dentry *dentry, *parent, *h_dentry;
struct inode *h_inode, *inode;
struct super_block *sb;
dentry = file->f_dentry;
sb = dentry->d_sb;
inode = dentry->d_inode;
AuDebugOn(au_special_file(inode->i_mode));
bstart = au_fbstart(file);
err = au_test_ro(sb, bstart, inode);
if (!err && (au_h_fptr(file, bstart)->f_mode & FMODE_WRITE)) {
err = au_pin(pin, dentry, bstart, AuOpt_UDBA_NONE, /*flags*/0);
goto out;
}
/* need to cpup */
parent = dget_parent(dentry);
di_write_lock_parent(parent);
err = AuWbrCopyup(au_sbi(sb), dentry);
bcpup = err;
if (unlikely(err < 0))
goto out_dgrade;
err = 0;
if (!au_h_dptr(parent, bcpup)) {
err = au_cpup_dirs(dentry, bcpup);
if (unlikely(err))
goto out_dgrade;
}
err = au_pin(pin, dentry, bcpup, AuOpt_UDBA_NONE,
AuPin_DI_LOCKED | AuPin_MNT_WRITE);
if (unlikely(err))
goto out_dgrade;
h_dentry = au_h_fptr(file, bstart)->f_dentry;
h_inode = h_dentry->d_inode;
mutex_lock_nested(&h_inode->i_mutex, AuLsc_I_CHILD);
if (d_unhashed(dentry) /* || d_unhashed(h_dentry) */
/* || !h_inode->i_nlink */) {
err = au_ready_to_write_wh(file, len, bcpup);
di_downgrade_lock(parent, AuLock_IR);
} else {
di_downgrade_lock(parent, AuLock_IR);
if (!au_h_dptr(dentry, bcpup))
err = au_sio_cpup_simple(dentry, bcpup, len,
AuCpup_DTIME);
if (!err)
err = au_reopen_nondir(file);
}
mutex_unlock(&h_inode->i_mutex);
if (!err) {
au_pin_set_parent_lflag(pin, /*lflag*/0);
goto out_dput; /* success */
}
au_unpin(pin);
goto out_unlock;
out_dgrade:
di_downgrade_lock(parent, AuLock_IR);
out_unlock:
di_read_unlock(parent, AuLock_IR);
out_dput:
dput(parent);
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;
}
/*
* prepare the @file for writing.
*/
int au_ready_to_write(struct file *file, loff_t len, struct au_pin *pin)
{
int err;
aufs_bindex_t bstart, bcpup, dbstart;
struct dentry *dentry, *parent, *h_dentry;
struct inode *h_inode, *inode;
struct super_block *sb;
struct file *h_file;
dentry = file->f_dentry;
sb = dentry->d_sb;
inode = dentry->d_inode;
AuDebugOn(au_special_file(inode->i_mode));
bstart = au_fbstart(file);
err = au_test_ro(sb, bstart, inode);
if (!err && (au_hf_top(file)->f_mode & FMODE_WRITE)) {
err = au_pin(pin, dentry, bstart, AuOpt_UDBA_NONE, /*flags*/0);
goto out;
}
/* need to cpup or reopen */
parent = dget_parent(dentry);
di_write_lock_parent(parent);
err = AuWbrCopyup(au_sbi(sb), dentry);
bcpup = err;
if (unlikely(err < 0))
goto out_dgrade;
err = 0;
if (!d_unhashed(dentry) && !au_h_dptr(parent, bcpup)) {
err = au_cpup_dirs(dentry, bcpup);
if (unlikely(err))
goto out_dgrade;
}
err = au_pin(pin, dentry, bcpup, AuOpt_UDBA_NONE,
AuPin_DI_LOCKED | AuPin_MNT_WRITE);
if (unlikely(err))
goto out_dgrade;
h_dentry = au_hf_top(file)->f_dentry;
h_inode = h_dentry->d_inode;
dbstart = au_dbstart(dentry);
if (dbstart <= bcpup) {
h_dentry = au_h_dptr(dentry, bcpup);
AuDebugOn(!h_dentry);
h_inode = h_dentry->d_inode;
AuDebugOn(!h_inode);
bstart = bcpup;
}
if (dbstart <= bcpup /* just reopen */
|| !d_unhashed(dentry) /* copyup and reopen */
) {
mutex_lock_nested(&h_inode->i_mutex, AuLsc_I_CHILD);
h_file = au_h_open_pre(dentry, bstart);
if (IS_ERR(h_file)) {
err = PTR_ERR(h_file);
h_file = NULL;
} else {
di_downgrade_lock(parent, AuLock_IR);
if (dbstart > bcpup)
err = au_sio_cpup_simple(dentry, bcpup, len,
AuCpup_DTIME);
if (!err)
err = au_reopen_nondir(file);
}
mutex_unlock(&h_inode->i_mutex);
au_h_open_post(dentry, bstart, h_file);
} else { /* copyup as wh and reopen */
/*
* since writable hfsplus branch is not supported,
* h_open_pre/post() are unnecessary.
*/
mutex_lock_nested(&h_inode->i_mutex, AuLsc_I_CHILD);
err = au_ready_to_write_wh(file, len, bcpup);
di_downgrade_lock(parent, AuLock_IR);
mutex_unlock(&h_inode->i_mutex);
}
if (!err) {
au_pin_set_parent_lflag(pin, /*lflag*/0);
goto out_dput; /* success */
}
au_unpin(pin);
goto out_unlock;
out_dgrade:
di_downgrade_lock(parent, AuLock_IR);
out_unlock:
di_read_unlock(parent, AuLock_IR);
out_dput:
dput(parent);
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;
}
