switch mnt_hash to hlist

fixes RCU bug - walking through hlist is safe in face of element moves,
since it's self-terminating.  Cyclic lists are not - if we end up jumping
to another hash chain, we'll loop infinitely without ever hitting the
original list head.

[fix for dumb braino folded]

Spotted by: Max Kellermann <mk@cm4all.com>
Cc: stable@vger.kernel.org
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
This commit is contained in:
Al Viro 2014-03-20 21:10:51 -04:00
parent 0b1b901b5a
commit 38129a13e6
4 changed files with 61 additions and 50 deletions

View File

@ -25,7 +25,7 @@ struct mountpoint {
}; };
struct mount { struct mount {
struct list_head mnt_hash; struct hlist_node mnt_hash;
struct mount *mnt_parent; struct mount *mnt_parent;
struct dentry *mnt_mountpoint; struct dentry *mnt_mountpoint;
struct vfsmount mnt; struct vfsmount mnt;

View File

@ -59,7 +59,7 @@ static DEFINE_SPINLOCK(mnt_id_lock);
static int mnt_id_start = 0; static int mnt_id_start = 0;
static int mnt_group_start = 1; static int mnt_group_start = 1;
static struct list_head *mount_hashtable __read_mostly; static struct hlist_head *mount_hashtable __read_mostly;
static struct hlist_head *mountpoint_hashtable __read_mostly; static struct hlist_head *mountpoint_hashtable __read_mostly;
static struct kmem_cache *mnt_cache __read_mostly; static struct kmem_cache *mnt_cache __read_mostly;
static DECLARE_RWSEM(namespace_sem); static DECLARE_RWSEM(namespace_sem);
@ -78,7 +78,7 @@ EXPORT_SYMBOL_GPL(fs_kobj);
*/ */
__cacheline_aligned_in_smp DEFINE_SEQLOCK(mount_lock); __cacheline_aligned_in_smp DEFINE_SEQLOCK(mount_lock);
static inline struct list_head *m_hash(struct vfsmount *mnt, struct dentry *dentry) static inline struct hlist_head *m_hash(struct vfsmount *mnt, struct dentry *dentry)
{ {
unsigned long tmp = ((unsigned long)mnt / L1_CACHE_BYTES); unsigned long tmp = ((unsigned long)mnt / L1_CACHE_BYTES);
tmp += ((unsigned long)dentry / L1_CACHE_BYTES); tmp += ((unsigned long)dentry / L1_CACHE_BYTES);
@ -217,7 +217,7 @@ static struct mount *alloc_vfsmnt(const char *name)
mnt->mnt_writers = 0; mnt->mnt_writers = 0;
#endif #endif
INIT_LIST_HEAD(&mnt->mnt_hash); INIT_HLIST_NODE(&mnt->mnt_hash);
INIT_LIST_HEAD(&mnt->mnt_child); INIT_LIST_HEAD(&mnt->mnt_child);
INIT_LIST_HEAD(&mnt->mnt_mounts); INIT_LIST_HEAD(&mnt->mnt_mounts);
INIT_LIST_HEAD(&mnt->mnt_list); INIT_LIST_HEAD(&mnt->mnt_list);
@ -605,10 +605,10 @@ bool legitimize_mnt(struct vfsmount *bastard, unsigned seq)
*/ */
struct mount *__lookup_mnt(struct vfsmount *mnt, struct dentry *dentry) struct mount *__lookup_mnt(struct vfsmount *mnt, struct dentry *dentry)
{ {
struct list_head *head = m_hash(mnt, dentry); struct hlist_head *head = m_hash(mnt, dentry);
struct mount *p; struct mount *p;
list_for_each_entry_rcu(p, head, mnt_hash) hlist_for_each_entry_rcu(p, head, mnt_hash)
if (&p->mnt_parent->mnt == mnt && p->mnt_mountpoint == dentry) if (&p->mnt_parent->mnt == mnt && p->mnt_mountpoint == dentry)
return p; return p;
return NULL; return NULL;
@ -620,20 +620,16 @@ struct mount *__lookup_mnt(struct vfsmount *mnt, struct dentry *dentry)
*/ */
struct mount *__lookup_mnt_last(struct vfsmount *mnt, struct dentry *dentry) struct mount *__lookup_mnt_last(struct vfsmount *mnt, struct dentry *dentry)
{ {
struct list_head *head = m_hash(mnt, dentry); struct mount *p, *res;
struct mount *p, *res = NULL; res = p = __lookup_mnt(mnt, dentry);
if (!p)
list_for_each_entry(p, head, mnt_hash) goto out;
if (&p->mnt_parent->mnt == mnt && p->mnt_mountpoint == dentry) hlist_for_each_entry_continue(p, mnt_hash) {
goto found;
return res;
found:
res = p;
list_for_each_entry_continue(p, head, mnt_hash) {
if (&p->mnt_parent->mnt != mnt || p->mnt_mountpoint != dentry) if (&p->mnt_parent->mnt != mnt || p->mnt_mountpoint != dentry)
break; break;
res = p; res = p;
} }
out:
return res; return res;
} }
@ -750,7 +746,7 @@ static void detach_mnt(struct mount *mnt, struct path *old_path)
mnt->mnt_parent = mnt; mnt->mnt_parent = mnt;
mnt->mnt_mountpoint = mnt->mnt.mnt_root; mnt->mnt_mountpoint = mnt->mnt.mnt_root;
list_del_init(&mnt->mnt_child); list_del_init(&mnt->mnt_child);
list_del_init(&mnt->mnt_hash); hlist_del_init_rcu(&mnt->mnt_hash);
put_mountpoint(mnt->mnt_mp); put_mountpoint(mnt->mnt_mp);
mnt->mnt_mp = NULL; mnt->mnt_mp = NULL;
} }
@ -777,7 +773,7 @@ static void attach_mnt(struct mount *mnt,
struct mountpoint *mp) struct mountpoint *mp)
{ {
mnt_set_mountpoint(parent, mp, mnt); mnt_set_mountpoint(parent, mp, mnt);
list_add(&mnt->mnt_hash, m_hash(&parent->mnt, mp->m_dentry)); hlist_add_head_rcu(&mnt->mnt_hash, m_hash(&parent->mnt, mp->m_dentry));
list_add_tail(&mnt->mnt_child, &parent->mnt_mounts); list_add_tail(&mnt->mnt_child, &parent->mnt_mounts);
} }
@ -800,9 +796,9 @@ static void commit_tree(struct mount *mnt, struct mount *shadows)
list_splice(&head, n->list.prev); list_splice(&head, n->list.prev);
if (shadows) if (shadows)
list_add(&mnt->mnt_hash, &shadows->mnt_hash); hlist_add_after_rcu(&shadows->mnt_hash, &mnt->mnt_hash);
else else
list_add(&mnt->mnt_hash, hlist_add_head_rcu(&mnt->mnt_hash,
m_hash(&parent->mnt, mnt->mnt_mountpoint)); m_hash(&parent->mnt, mnt->mnt_mountpoint));
list_add_tail(&mnt->mnt_child, &parent->mnt_mounts); list_add_tail(&mnt->mnt_child, &parent->mnt_mounts);
touch_mnt_namespace(n); touch_mnt_namespace(n);
@ -1193,26 +1189,28 @@ int may_umount(struct vfsmount *mnt)
EXPORT_SYMBOL(may_umount); EXPORT_SYMBOL(may_umount);
static LIST_HEAD(unmounted); /* protected by namespace_sem */ static HLIST_HEAD(unmounted); /* protected by namespace_sem */
static void namespace_unlock(void) static void namespace_unlock(void)
{ {
struct mount *mnt; struct mount *mnt;
LIST_HEAD(head); struct hlist_head head = unmounted;
if (likely(list_empty(&unmounted))) { if (likely(hlist_empty(&head))) {
up_write(&namespace_sem); up_write(&namespace_sem);
return; return;
} }
list_splice_init(&unmounted, &head); head.first->pprev = &head.first;
INIT_HLIST_HEAD(&unmounted);
up_write(&namespace_sem); up_write(&namespace_sem);
synchronize_rcu(); synchronize_rcu();
while (!list_empty(&head)) { while (!hlist_empty(&head)) {
mnt = list_first_entry(&head, struct mount, mnt_hash); mnt = hlist_entry(head.first, struct mount, mnt_hash);
list_del_init(&mnt->mnt_hash); hlist_del_init(&mnt->mnt_hash);
if (mnt->mnt_ex_mountpoint.mnt) if (mnt->mnt_ex_mountpoint.mnt)
path_put(&mnt->mnt_ex_mountpoint); path_put(&mnt->mnt_ex_mountpoint);
mntput(&mnt->mnt); mntput(&mnt->mnt);
@ -1233,16 +1231,19 @@ static inline void namespace_lock(void)
*/ */
void umount_tree(struct mount *mnt, int how) void umount_tree(struct mount *mnt, int how)
{ {
LIST_HEAD(tmp_list); HLIST_HEAD(tmp_list);
struct mount *p; struct mount *p;
struct mount *last = NULL;
for (p = mnt; p; p = next_mnt(p, mnt)) for (p = mnt; p; p = next_mnt(p, mnt)) {
list_move(&p->mnt_hash, &tmp_list); hlist_del_init_rcu(&p->mnt_hash);
hlist_add_head(&p->mnt_hash, &tmp_list);
}
if (how) if (how)
propagate_umount(&tmp_list); propagate_umount(&tmp_list);
list_for_each_entry(p, &tmp_list, mnt_hash) { hlist_for_each_entry(p, &tmp_list, mnt_hash) {
list_del_init(&p->mnt_expire); list_del_init(&p->mnt_expire);
list_del_init(&p->mnt_list); list_del_init(&p->mnt_list);
__touch_mnt_namespace(p->mnt_ns); __touch_mnt_namespace(p->mnt_ns);
@ -1260,8 +1261,13 @@ void umount_tree(struct mount *mnt, int how)
p->mnt_mp = NULL; p->mnt_mp = NULL;
} }
change_mnt_propagation(p, MS_PRIVATE); change_mnt_propagation(p, MS_PRIVATE);
last = p;
}
if (last) {
last->mnt_hash.next = unmounted.first;
unmounted.first = tmp_list.first;
unmounted.first->pprev = &unmounted.first;
} }
list_splice(&tmp_list, &unmounted);
} }
static void shrink_submounts(struct mount *mnt); static void shrink_submounts(struct mount *mnt);
@ -1645,8 +1651,9 @@ static int attach_recursive_mnt(struct mount *source_mnt,
struct mountpoint *dest_mp, struct mountpoint *dest_mp,
struct path *parent_path) struct path *parent_path)
{ {
LIST_HEAD(tree_list); HLIST_HEAD(tree_list);
struct mount *child, *p; struct mount *child, *p;
struct hlist_node *n;
int err; int err;
if (IS_MNT_SHARED(dest_mnt)) { if (IS_MNT_SHARED(dest_mnt)) {
@ -1671,9 +1678,9 @@ static int attach_recursive_mnt(struct mount *source_mnt,
commit_tree(source_mnt, NULL); commit_tree(source_mnt, NULL);
} }
list_for_each_entry_safe(child, p, &tree_list, mnt_hash) { hlist_for_each_entry_safe(child, n, &tree_list, mnt_hash) {
struct mount *q; struct mount *q;
list_del_init(&child->mnt_hash); hlist_del_init(&child->mnt_hash);
q = __lookup_mnt_last(&child->mnt_parent->mnt, q = __lookup_mnt_last(&child->mnt_parent->mnt,
child->mnt_mountpoint); child->mnt_mountpoint);
commit_tree(child, q); commit_tree(child, q);
@ -2818,7 +2825,7 @@ void __init mnt_init(void)
0, SLAB_HWCACHE_ALIGN | SLAB_PANIC, NULL); 0, SLAB_HWCACHE_ALIGN | SLAB_PANIC, NULL);
mount_hashtable = alloc_large_system_hash("Mount-cache", mount_hashtable = alloc_large_system_hash("Mount-cache",
sizeof(struct list_head), sizeof(struct hlist_head),
mhash_entries, 19, mhash_entries, 19,
0, 0,
&m_hash_shift, &m_hash_mask, 0, 0); &m_hash_shift, &m_hash_mask, 0, 0);
@ -2832,7 +2839,7 @@ void __init mnt_init(void)
panic("Failed to allocate mount hash table\n"); panic("Failed to allocate mount hash table\n");
for (u = 0; u <= m_hash_mask; u++) for (u = 0; u <= m_hash_mask; u++)
INIT_LIST_HEAD(&mount_hashtable[u]); INIT_HLIST_HEAD(&mount_hashtable[u]);
for (u = 0; u <= mp_hash_mask; u++) for (u = 0; u <= mp_hash_mask; u++)
INIT_HLIST_HEAD(&mountpoint_hashtable[u]); INIT_HLIST_HEAD(&mountpoint_hashtable[u]);

View File

@ -220,14 +220,14 @@ static struct mount *get_source(struct mount *dest,
* @tree_list : list of heads of trees to be attached. * @tree_list : list of heads of trees to be attached.
*/ */
int propagate_mnt(struct mount *dest_mnt, struct mountpoint *dest_mp, int propagate_mnt(struct mount *dest_mnt, struct mountpoint *dest_mp,
struct mount *source_mnt, struct list_head *tree_list) struct mount *source_mnt, struct hlist_head *tree_list)
{ {
struct user_namespace *user_ns = current->nsproxy->mnt_ns->user_ns; struct user_namespace *user_ns = current->nsproxy->mnt_ns->user_ns;
struct mount *m, *child; struct mount *m, *child;
int ret = 0; int ret = 0;
struct mount *prev_dest_mnt = dest_mnt; struct mount *prev_dest_mnt = dest_mnt;
struct mount *prev_src_mnt = source_mnt; struct mount *prev_src_mnt = source_mnt;
LIST_HEAD(tmp_list); HLIST_HEAD(tmp_list);
for (m = propagation_next(dest_mnt, dest_mnt); m; for (m = propagation_next(dest_mnt, dest_mnt); m;
m = propagation_next(m, dest_mnt)) { m = propagation_next(m, dest_mnt)) {
@ -246,27 +246,29 @@ int propagate_mnt(struct mount *dest_mnt, struct mountpoint *dest_mp,
child = copy_tree(source, source->mnt.mnt_root, type); child = copy_tree(source, source->mnt.mnt_root, type);
if (IS_ERR(child)) { if (IS_ERR(child)) {
ret = PTR_ERR(child); ret = PTR_ERR(child);
list_splice(tree_list, tmp_list.prev); tmp_list = *tree_list;
tmp_list.first->pprev = &tmp_list.first;
INIT_HLIST_HEAD(tree_list);
goto out; goto out;
} }
if (is_subdir(dest_mp->m_dentry, m->mnt.mnt_root)) { if (is_subdir(dest_mp->m_dentry, m->mnt.mnt_root)) {
mnt_set_mountpoint(m, dest_mp, child); mnt_set_mountpoint(m, dest_mp, child);
list_add_tail(&child->mnt_hash, tree_list); hlist_add_head(&child->mnt_hash, tree_list);
} else { } else {
/* /*
* This can happen if the parent mount was bind mounted * This can happen if the parent mount was bind mounted
* on some subdirectory of a shared/slave mount. * on some subdirectory of a shared/slave mount.
*/ */
list_add_tail(&child->mnt_hash, &tmp_list); hlist_add_head(&child->mnt_hash, &tmp_list);
} }
prev_dest_mnt = m; prev_dest_mnt = m;
prev_src_mnt = child; prev_src_mnt = child;
} }
out: out:
lock_mount_hash(); lock_mount_hash();
while (!list_empty(&tmp_list)) { while (!hlist_empty(&tmp_list)) {
child = list_first_entry(&tmp_list, struct mount, mnt_hash); child = hlist_entry(tmp_list.first, struct mount, mnt_hash);
umount_tree(child, 0); umount_tree(child, 0);
} }
unlock_mount_hash(); unlock_mount_hash();
@ -338,8 +340,10 @@ static void __propagate_umount(struct mount *mnt)
* umount the child only if the child has no * umount the child only if the child has no
* other children * other children
*/ */
if (child && list_empty(&child->mnt_mounts)) if (child && list_empty(&child->mnt_mounts)) {
list_move_tail(&child->mnt_hash, &mnt->mnt_hash); hlist_del_init_rcu(&child->mnt_hash);
hlist_add_before_rcu(&child->mnt_hash, &mnt->mnt_hash);
}
} }
} }
@ -350,11 +354,11 @@ static void __propagate_umount(struct mount *mnt)
* *
* vfsmount lock must be held for write * vfsmount lock must be held for write
*/ */
int propagate_umount(struct list_head *list) int propagate_umount(struct hlist_head *list)
{ {
struct mount *mnt; struct mount *mnt;
list_for_each_entry(mnt, list, mnt_hash) hlist_for_each_entry(mnt, list, mnt_hash)
__propagate_umount(mnt); __propagate_umount(mnt);
return 0; return 0;
} }

View File

@ -36,8 +36,8 @@ static inline void set_mnt_shared(struct mount *mnt)
void change_mnt_propagation(struct mount *, int); void change_mnt_propagation(struct mount *, int);
int propagate_mnt(struct mount *, struct mountpoint *, struct mount *, int propagate_mnt(struct mount *, struct mountpoint *, struct mount *,
struct list_head *); struct hlist_head *);
int propagate_umount(struct list_head *); int propagate_umount(struct hlist_head *);
int propagate_mount_busy(struct mount *, int); int propagate_mount_busy(struct mount *, int);
void mnt_release_group_id(struct mount *); void mnt_release_group_id(struct mount *);
int get_dominating_id(struct mount *mnt, const struct path *root); int get_dominating_id(struct mount *mnt, const struct path *root);