int aufs_read_and_write_lock2(struct dentry *d1, struct dentry *d2, int flags)
{
int err;
unsigned int sigen;
struct super_block *sb;
sb = d1->d_sb;
err = si_read_lock(sb, flags);
if (unlikely(err))
goto out;
di_write_lock2_child(d1, d2, au_ftest_lock(flags, DIR));
if (au_ftest_lock(flags, GEN)) {
sigen = au_sigen(sb);
err = au_digen_test(d1, sigen);
AuDebugOn(!err && au_dbrange_test(d1));
if (!err) {
err = au_digen_test(d2, sigen);
AuDebugOn(!err && au_dbrange_test(d2));
}
if (unlikely(err))
aufs_read_and_write_unlock2(d1, d2);
}
out:
return err;
}
int au_alloc_dinfo(struct dentry *dentry)
{
struct au_dinfo *dinfo;
struct super_block *sb;
int nbr;
dinfo = au_cache_alloc_dinfo();
if (unlikely(!dinfo))
goto out;
sb = dentry->d_sb;
nbr = au_sbend(sb) + 1;
if (nbr <= 0)
nbr = 1;
dinfo->di_hdentry = kcalloc(nbr, sizeof(*dinfo->di_hdentry), GFP_NOFS);
if (unlikely(!dinfo->di_hdentry))
goto out_dinfo;
atomic_set(&dinfo->di_generation, au_sigen(sb));
/* smp_mb(); */ /* atomic_set */
au_rw_init_wlock_nested(&dinfo->di_rwsem, AuLsc_DI_CHILD);
dinfo->di_bstart = -1;
dinfo->di_bend = -1;
dinfo->di_bwh = -1;
dinfo->di_bdiropq = -1;
dentry->d_fsdata = dinfo;
dentry->d_op = &aufs_dop;
return 0; /* success */
out_dinfo:
au_cache_free_dinfo(dinfo);
out:
return -ENOMEM;
}
/* dentry and super_block lock. call at entry point */
int aufs_read_lock(struct dentry *dentry, int flags)
{
int err;
struct super_block *sb;
sb = dentry->d_sb;
err = si_read_lock(sb, flags);
if (unlikely(err))
goto out;
if (au_ftest_lock(flags, DW))
di_write_lock_child(dentry);
else
di_read_lock_child(dentry, flags);
if (au_ftest_lock(flags, GEN)) {
err = au_digen_test(dentry, au_sigen(sb));
AuDebugOn(!err && au_dbrange_test(dentry));
if (unlikely(err))
aufs_read_unlock(dentry, flags);
}
out:
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;
err = -EINVAL;
sb = dentry->d_sb;
inode = dentry->d_inode;
aufs_read_lock(dentry, AuLock_FLUSH | AuLock_DW);
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;
AuDebugOn(au_digen(dentry) != sigen);
}
if (inode && au_iigen(inode) != sigen) {
AuDebugOn(IS_ROOT(dentry));
err = au_refresh_hinode(inode, dentry);
if (unlikely(err))
goto out_dgrade;
AuDebugOn(au_iigen(inode) != sigen);
}
di_downgrade_lock(dentry, AuLock_IR);
AuDebugOn(au_digen(dentry) != sigen);
AuDebugOn(inode && au_iigen(inode) != sigen);
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;
}
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;
out_dgrade:
di_downgrade_lock(dentry, AuLock_IR);
out:
aufs_read_unlock(dentry, AuLock_IR);
AuTraceErr(err);
valid = !err;
if (!valid)
AuDbg("%.*s invalid\n", AuDLNPair(dentry));
return valid;
}
/* common function to regular file and dir */
int au_reval_and_lock_fdi(struct file *file, int (*reopen)(struct file *file),
int wlock)
{
int err;
unsigned int sigen, figen;
aufs_bindex_t bstart;
unsigned char pseudo_link;
struct dentry *dentry;
struct inode *inode;
err = 0;
dentry = file->f_dentry;
inode = dentry->d_inode;
AuDebugOn(au_special_file(inode->i_mode));
sigen = au_sigen(dentry->d_sb);
fi_write_lock(file);
figen = au_figen(file);
di_write_lock_child(dentry);
bstart = au_dbstart(dentry);
pseudo_link = (bstart != au_ibstart(inode));
if (sigen == figen && !pseudo_link && au_fbstart(file) == bstart) {
if (!wlock) {
di_downgrade_lock(dentry, AuLock_IR);
fi_downgrade_lock(file);
}
goto out; /* success */
}
AuDbg("sigen %d, figen %d\n", sigen, figen);
if (sigen != au_digen(dentry)
|| sigen != au_iigen(inode)) {
err = au_reval_dpath(dentry, sigen);
if (unlikely(err < 0))
goto out;
AuDebugOn(au_digen(dentry) != sigen
|| au_iigen(inode) != sigen);
}
err = refresh_file(file, reopen);
if (!err) {
if (!wlock) {
di_downgrade_lock(dentry, AuLock_IR);
fi_downgrade_lock(file);
}
} else {
di_write_unlock(dentry);
fi_write_unlock(file);
}
out:
return err;
}
static struct dentry *decode_by_ino(struct super_block *sb, ino_t ino,
ino_t dir_ino)
{
struct dentry *dentry, *d;
struct inode *inode;
au_gen_t sigen;
LKTRTrace("i%lu, diri%lu\n",
(unsigned long)ino, (unsigned long)dir_ino);
dentry = NULL;
inode = ilookup(sb, ino);
if (!inode)
goto out;
dentry = ERR_PTR(-ESTALE);
sigen = au_sigen(sb);
if (unlikely(is_bad_inode(inode)
|| IS_DEADDIR(inode)
|| sigen != au_iigen(inode)))
goto out_iput;
dentry = NULL;
if (!dir_ino || S_ISDIR(inode->i_mode))
dentry = d_find_alias(inode);
else {
spin_lock(&dcache_lock);
list_for_each_entry(d, &inode->i_dentry, d_alias)
if (!au_test_anon(d)
&& d->d_parent->d_inode->i_ino == dir_ino) {
dentry = dget_locked(d);
break;
}
spin_unlock(&dcache_lock);
}
if (unlikely(dentry && sigen != au_digen(dentry))) {
dput(dentry);
dentry = ERR_PTR(-ESTALE);
}
out_iput:
iput(inode);
out:
AuTraceErrPtr(dentry);
return dentry;
}
static int test_children_busy(struct dentry *root, aufs_bindex_t bindex,
const unsigned int verbose)
{
int err;
unsigned int sigen;
sigen = au_sigen(root->d_sb);
DiMustNoWaiters(root);
IiMustNoWaiters(root->d_inode);
di_write_unlock(root);
err = test_dentry_busy(root, bindex, sigen, verbose);
if (!err)
err = test_inode_busy(root->d_sb, bindex, sigen, verbose);
di_write_lock_child(root); /* aufs_write_lock() calls ..._child() */
return err;
}
int au_di_init(struct dentry *dentry)
{
int err;
struct super_block *sb;
struct au_dinfo *dinfo;
err = 0;
sb = dentry->d_sb;
dinfo = au_di_alloc(sb, AuLsc_DI_CHILD);
if (dinfo) {
atomic_set(&dinfo->di_generation, au_sigen(sb));
/* smp_mb(); */ /* atomic_set */
dentry->d_fsdata = dinfo;
} else
err = -ENOMEM;
return err;
}
/*
* returns the number of found lower positive dentries,
* otherwise an error.
*/
int au_refresh_hdentry(struct dentry *dentry, mode_t type)
{
int npositive, err;
unsigned int sigen;
aufs_bindex_t bstart;
struct au_dinfo *dinfo;
struct super_block *sb;
struct dentry *parent;
DiMustWriteLock(dentry);
sb = dentry->d_sb;
AuDebugOn(IS_ROOT(dentry));
sigen = au_sigen(sb);
parent = dget_parent(dentry);
AuDebugOn(au_digen(parent) != sigen
|| au_iigen(parent->d_inode) != sigen);
dinfo = au_di(dentry);
err = au_di_realloc(dinfo, au_sbend(sb) + 1);
npositive = err;
if (unlikely(err))
goto out;
au_do_refresh_hdentry(dinfo->di_hdentry + dinfo->di_bstart, dinfo,
parent);
npositive = 0;
bstart = au_dbstart(parent);
if (type != S_IFDIR && dinfo->di_bstart == bstart)
goto out_dgen; /* success */
npositive = au_lkup_dentry(dentry, bstart, type, /*nd*/NULL);
if (npositive < 0)
goto out;
if (dinfo->di_bwh >= 0 && dinfo->di_bwh <= dinfo->di_bstart)
d_drop(dentry);
out_dgen:
au_update_digen(dentry);
out:
dput(parent);
AuTraceErr(npositive);
return npositive;
}
static aufs_bindex_t si_nfsd_read_lock(struct super_block *sb,
struct au_nfsd_si_lock *nsi_lock)
{
aufs_bindex_t bindex;
si_read_lock(sb, AuLock_FLUSH);
/* branch id may be wrapped around */
bindex = au_br_index(sb, nsi_lock->br_id);
if (bindex >= 0 && nsi_lock->sigen + AUFS_BRANCH_MAX > au_sigen(sb))
goto out; /* success */
if (!nsi_lock->force_lock)
si_read_unlock(sb);
bindex = -1;
out:
return bindex;
}
int au_alloc_dinfo(struct dentry *dentry)
{
struct au_dinfo *dinfo;
struct super_block *sb;
int nbr;
LKTRTrace("%.*s\n", AuDLNPair(dentry));
AuDebugOn(dentry->d_fsdata);
dinfo = au_cache_alloc_dinfo();
if (dinfo) {
sb = dentry->d_sb;
nbr = au_sbend(sb) + 1;
if (nbr <= 0)
nbr = 1;
dinfo->di_hdentry = kcalloc(nbr, sizeof(*dinfo->di_hdentry),
GFP_NOFS);
if (dinfo->di_hdentry) {
au_h_dentry_init_all(dinfo->di_hdentry, nbr);
atomic_set(&dinfo->di_generation, au_sigen(sb));
/* smp_mb(); */ /* atomic_set */
au_rw_init_wlock_nested(&dinfo->di_rwsem,
AuLsc_DI_CHILD);
au_dbg_locked_di_reg(dentry, AuLock_DW, AuLsc_DI_CHILD);
dinfo->di_bstart = -1;
dinfo->di_bend = -1;
dinfo->di_bwh = -1;
dinfo->di_bdiropq = -1;
dentry->d_fsdata = dinfo;
dentry->d_op = &aufs_dop;
return 0; /* success */
}
au_cache_free_dinfo(dinfo);
}
AuTraceErr(-ENOMEM);
return -ENOMEM;
}
/*
* 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;
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;
}
inode = NULL;
if (d_really_is_positive(dentry))
inode = d_inode(dentry);
if (unlikely(inode && is_bad_inode(inode))) {
err = -EINVAL;
AuTraceErr(err);
goto out_dgrade;
}
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 | LOOKUP_EMPTY))
&& inode
&& !(inode->i_state && I_LINKABLE)
&& (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;
}
static struct dentry *aufs_lookup(struct inode *dir, struct dentry *dentry,
unsigned int flags)
{
struct dentry *ret, *parent;
struct inode *inode;
struct super_block *sb;
int err, npositive;
IMustLock(dir);
/* todo: support rcu-walk? */
ret = ERR_PTR(-ECHILD);
if (flags & LOOKUP_RCU)
goto out;
ret = ERR_PTR(-ENAMETOOLONG);
if (unlikely(dentry->d_name.len > AUFS_MAX_NAMELEN))
goto out;
sb = dir->i_sb;
err = si_read_lock(sb, AuLock_FLUSH | AuLock_NOPLM);
ret = ERR_PTR(err);
if (unlikely(err))
goto out;
err = au_di_init(dentry);
ret = ERR_PTR(err);
if (unlikely(err))
goto out_si;
inode = NULL;
npositive = 0; /* suppress a warning */
parent = dentry->d_parent; /* dir inode is locked */
di_read_lock_parent(parent, AuLock_IR);
err = au_alive_dir(parent);
if (!err)
err = au_digen_test(parent, au_sigen(sb));
if (!err) {
/* regardless LOOKUP_CREATE, always ALLOW_NEG */
npositive = au_lkup_dentry(dentry, au_dbtop(parent),
AuLkup_ALLOW_NEG);
err = npositive;
}
di_read_unlock(parent, AuLock_IR);
ret = ERR_PTR(err);
if (unlikely(err < 0))
goto out_unlock;
if (npositive) {
inode = au_new_inode(dentry, /*must_new*/0);
if (IS_ERR(inode)) {
ret = (void *)inode;
inode = NULL;
goto out_unlock;
}
}
if (inode)
atomic_inc(&inode->i_count);
ret = d_splice_alias(inode, dentry);
#if 0
if (unlikely(d_need_lookup(dentry))) {
spin_lock(&dentry->d_lock);
dentry->d_flags &= ~DCACHE_NEED_LOOKUP;
spin_unlock(&dentry->d_lock);
} else
#endif
if (inode) {
if (!IS_ERR(ret)) {
iput(inode);
if (ret && ret != dentry)
ii_write_unlock(inode);
} else {
ii_write_unlock(inode);
iput(inode);
inode = NULL;
}
}
out_unlock:
di_write_unlock(dentry);
out_si:
si_read_unlock(sb);
out:
return ret;
}
static int aufs_permission(struct inode *inode, int mask)
{
int err;
aufs_bindex_t bindex, bend;
const unsigned char isdir = !!S_ISDIR(inode->i_mode),
write_mask = !!(mask & (MAY_WRITE | MAY_APPEND));
struct inode *h_inode;
struct super_block *sb;
struct au_branch *br;
/* todo: support rcu-walk? */
if (mask & MAY_NOT_BLOCK)
return -ECHILD;
sb = inode->i_sb;
si_read_lock(sb, AuLock_FLUSH);
ii_read_lock_child(inode);
#if 0
err = au_iigen_test(inode, au_sigen(sb));
if (unlikely(err))
goto out;
#endif
if (!isdir || write_mask) {
err = au_busy_or_stale();
h_inode = au_h_iptr(inode, au_ibstart(inode));
if (unlikely(!h_inode
|| (h_inode->i_mode & S_IFMT)
!= (inode->i_mode & S_IFMT)))
goto out;
err = 0;
bindex = au_ibstart(inode);
br = au_sbr(sb, bindex);
err = h_permission(h_inode, mask, br->br_mnt, br->br_perm);
if (write_mask
&& !err
&& !special_file(h_inode->i_mode)) {
/* test whether the upper writable branch exists */
err = -EROFS;
for (; bindex >= 0; bindex--)
if (!au_br_rdonly(au_sbr(sb, bindex))) {
err = 0;
break;
}
}
goto out;
}
/* non-write to dir */
err = 0;
bend = au_ibend(inode);
for (bindex = au_ibstart(inode); !err && bindex <= bend; bindex++) {
h_inode = au_h_iptr(inode, bindex);
if (h_inode) {
err = au_busy_or_stale();
if (unlikely(!S_ISDIR(h_inode->i_mode)))
break;
br = au_sbr(sb, bindex);
err = h_permission(h_inode, mask, br->br_mnt,
br->br_perm);
}
}
out:
ii_read_unlock(inode);
si_read_unlock(sb);
return err;
}
static struct dentry *aufs_lookup(struct inode *dir, struct dentry *dentry,
struct nameidata *nd)
{
struct dentry *ret, *parent;
struct inode *inode;
struct super_block *sb;
int err, npositive, lc_idx;
IMustLock(dir);
sb = dir->i_sb;
err = si_read_lock(sb, AuLock_FLUSH | AuLock_NOPLM);
ret = ERR_PTR(err);
if (unlikely(err))
goto out;
ret = ERR_PTR(-ENAMETOOLONG);
if (unlikely(dentry->d_name.len > AUFS_MAX_NAMELEN))
goto out_si;
err = au_di_init(dentry);
ret = ERR_PTR(err);
if (unlikely(err))
goto out_si;
inode = NULL;
npositive = 0; /* suppress a warning */
parent = dentry->d_parent; /* dir inode is locked */
di_read_lock_parent(parent, AuLock_IR);
err = au_alive_dir(parent);
if (!err)
err = au_digen_test(parent, au_sigen(sb));
if (!err) {
npositive = au_lkup_dentry(dentry, au_dbstart(parent),
/*type*/0, nd);
err = npositive;
}
di_read_unlock(parent, AuLock_IR);
ret = ERR_PTR(err);
if (unlikely(err < 0))
goto out_unlock;
if (npositive) {
inode = au_new_inode(dentry, /*must_new*/0);
ret = (void *)inode;
}
if (IS_ERR(inode)) {
inode = NULL;
goto out_unlock;
}
ret = d_splice_alias(inode, dentry);
if (unlikely(IS_ERR(ret) && inode)) {
ii_write_unlock(inode);
lc_idx = AuLcNonDir_IIINFO;
if (S_ISLNK(inode->i_mode))
lc_idx = AuLcSymlink_IIINFO;
else if (S_ISDIR(inode->i_mode))
lc_idx = AuLcDir_IIINFO;
au_rw_class(&au_ii(inode)->ii_rwsem, au_lc_key + lc_idx);
iput(inode);
}
out_unlock:
di_write_unlock(dentry);
if (unlikely(IS_ERR(ret) && inode)) {
lc_idx = AuLcNonDir_DIINFO;
if (S_ISLNK(inode->i_mode))
lc_idx = AuLcSymlink_DIINFO;
else if (S_ISDIR(inode->i_mode))
lc_idx = AuLcDir_DIINFO;
au_rw_class(&au_di(dentry)->di_rwsem, au_lc_key + lc_idx);
}
out_si:
si_read_unlock(sb);
out:
return ret;
}
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, /*nd*/NULL);
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 %.*s, %d\n",
AuDLNPair(dentry), err);
AuDbgDentry(dentry);
}
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 = 0;
if (unlikely(!au_di(dentry)))
goto out;
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;
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 (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, nd, do_udba);
if (unlikely(!err && do_udba && au_dbstart(dentry) < 0)) {
err = -EIO;
AuDbg("both of real entry and whiteout found, %.*s, err %d\n",
AuDLNPair(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("%.*s invalid, %d\n", AuDLNPair(dentry), valid);
d_drop(dentry);
}
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 struct dentry *
aufs_fh_to_dentry(struct super_block *sb, struct fid *fid, int fh_len,
int fh_type)
{
struct dentry *dentry;
__u32 *fh = fid->raw;
ino_t ino, dir_ino;
aufs_bindex_t bindex;
struct au_nfsd_si_lock nsi_lock = {
.force_lock = 0
};
dentry = ERR_PTR(-ESTALE);
/* it should never happen, but the file handle is unreliable */
if (unlikely(fh_len < Fh_tail))
goto out;
nsi_lock.sigen = fh[Fh_sigen];
nsi_lock.br_id = fh[Fh_br_id];
/* 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);
/* it should never happen */
if (unlikely(ino == AUFS_ROOT_INO))
goto out;
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))
/* todo?: make it ESTALE */
goto out_unlock;
accept:
if (dentry->d_inode->i_generation == fh[Fh_igen])
goto out_unlock; /* success */
dput(dentry);
dentry = ERR_PTR(-ESTALE);
out_unlock:
si_read_unlock(sb);
out:
AuTraceErrPtr(dentry);
return dentry;
}
#if 0 /* reserved for future use */
/* support subtreecheck option */
static struct dentry *aufs_fh_to_parent(struct super_block *sb, struct fid *fid,
int fh_len, int fh_type)
{
struct dentry *parent;
__u32 *fh = fid->raw;
ino_t dir_ino;
dir_ino = decode_ino(fh + Fh_dir_ino);
parent = decode_by_ino(sb, dir_ino, 0);
if (IS_ERR(parent))
goto out;
if (!parent)
parent = decode_by_path(sb, au_br_index(sb, fh[Fh_br_id]),
dir_ino, fh, fh_len);
out:
AuTraceErrPtr(parent);
return parent;
}
#endif
/* ---------------------------------------------------------------------- */
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;
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 = 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
if (unlikely(!au_opt_test(au_mntflags(sb), XINO)))
AuWarn1("NFS-exporting requires xino\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;
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;
*max_len -= Fh_tail;
fh[Fh_h_type] = exportfs_encode_fh(h_parent, (void *)(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:
if (unlikely(err < 0))
err = 255;
return err;
}
void au_update_digen(struct dentry *dentry)
{
atomic_set(&au_di(dentry)->di_generation, au_sigen(dentry->d_sb));
/* smp_mb(); */ /* atomic_set */
}
static struct dentry *aufs_lookup(struct inode *dir, struct dentry *dentry,
unsigned int flags)
{
struct dentry *ret, *parent;
struct inode *inode;
struct super_block *sb;
int err, npositive;
IMustLock(dir);
/* todo: support rcu-walk? */
ret = ERR_PTR(-ECHILD);
if (flags & LOOKUP_RCU)
goto out;
ret = ERR_PTR(-ENAMETOOLONG);
if (unlikely(dentry->d_name.len > AUFS_MAX_NAMELEN))
goto out;
sb = dir->i_sb;
err = si_read_lock(sb, AuLock_FLUSH | AuLock_NOPLM);
ret = ERR_PTR(err);
if (unlikely(err))
goto out;
err = au_di_init(dentry);
ret = ERR_PTR(err);
if (unlikely(err))
goto out_si;
inode = NULL;
npositive = 0; /* suppress a warning */
parent = dentry->d_parent; /* dir inode is locked */
di_read_lock_parent(parent, AuLock_IR);
err = au_alive_dir(parent);
if (!err)
err = au_digen_test(parent, au_sigen(sb));
if (!err) {
npositive = au_lkup_dentry(dentry, au_dbstart(parent),
/*type*/0);
err = npositive;
}
di_read_unlock(parent, AuLock_IR);
ret = ERR_PTR(err);
if (unlikely(err < 0))
goto out_unlock;
if (npositive) {
inode = au_new_inode(dentry, /*must_new*/0);
if (IS_ERR(inode)) {
ret = (void *)inode;
inode = NULL;
goto out_unlock;
}
}
if (inode)
atomic_inc(&inode->i_count);
ret = d_splice_alias(inode, dentry);
#if 0
if (unlikely(d_need_lookup(dentry))) {
spin_lock(&dentry->d_lock);
dentry->d_flags &= ~DCACHE_NEED_LOOKUP;
spin_unlock(&dentry->d_lock);
} else
#endif
if (inode) {
if (!IS_ERR(ret)) {
iput(inode);
if (ret && ret != dentry)
ii_write_unlock(inode);
} else {
ii_write_unlock(inode);
iput(inode);
inode = NULL;
}
}
out_unlock:
di_write_unlock(dentry);
if (inode) {
/* verbose coding for lock class name */
if (unlikely(S_ISLNK(inode->i_mode)))
au_rw_class(&au_di(dentry)->di_rwsem,
au_lc_key + AuLcSymlink_DIINFO);
else if (unlikely(S_ISDIR(inode->i_mode)))
au_rw_class(&au_di(dentry)->di_rwsem,
au_lc_key + AuLcDir_DIINFO);
else /* likely */
au_rw_class(&au_di(dentry)->di_rwsem,
au_lc_key + AuLcNonDir_DIINFO);
}
out_si:
si_read_unlock(sb);
out:
return ret;
}
