1 files changed, 97 insertions, 130 deletions

diff --git a/fs/namespace.c b/fs/namespace.c
index 487ba30bb5c6..f8893dc6a989 100644
--- a/fs/namespace.c
+++ b/fs/namespace.c
@@ -15,6 +15,7 @@
 #include <linux/user_namespace.h>
 #include <linux/namei.h>
 #include <linux/security.h>
+#include <linux/cred.h>
 #include <linux/idr.h>
 #include <linux/init.h>		/* init_rootfs */
 #include <linux/fs_struct.h>	/* get_fs_root et.al. */
@@ -24,6 +25,8 @@
 #include <linux/magic.h>
 #include <linux/bootmem.h>
 #include <linux/task_work.h>
+#include <linux/sched/task.h>
+
 #include "pnode.h"
 #include "internal.h"
 
@@ -233,9 +236,7 @@ static struct mount *alloc_vfsmnt(const char *name)
 		INIT_LIST_HEAD(&mnt->mnt_slave_list);
 		INIT_LIST_HEAD(&mnt->mnt_slave);
 		INIT_HLIST_NODE(&mnt->mnt_mp_list);
-#ifdef CONFIG_FSNOTIFY
-		INIT_HLIST_HEAD(&mnt->mnt_fsnotify_marks);
-#endif
+		INIT_LIST_HEAD(&mnt->mnt_umounting);
 		init_fs_pin(&mnt->mnt_umount, drop_mountpoint);
 	}
 	return mnt;
@@ -637,28 +638,6 @@ struct mount *__lookup_mnt(struct vfsmount *mnt, struct dentry *dentry)
 }
 
 /*
- * find the last mount at @dentry on vfsmount @mnt.
- * mount_lock must be held.
- */
-struct mount *__lookup_mnt_last(struct vfsmount *mnt, struct dentry *dentry)
-{
-	struct mount *p, *res = NULL;
-	p = __lookup_mnt(mnt, dentry);
-	if (!p)
-		goto out;
-	if (!(p->mnt.mnt_flags & MNT_UMOUNT))
-		res = p;
-	hlist_for_each_entry_continue(p, mnt_hash) {
-		if (&p->mnt_parent->mnt != mnt || p->mnt_mountpoint != dentry)
-			break;
-		if (!(p->mnt.mnt_flags & MNT_UMOUNT))
-			res = p;
-	}
-out:
-	return res;
-}
-
-/*
  * lookup_mnt - Return the first child mount mounted at path
  *
  * "First" means first mounted chronologically.  If you create the
@@ -878,6 +857,13 @@ void mnt_set_mountpoint(struct mount *mnt,
 	hlist_add_head(&child_mnt->mnt_mp_list, &mp->m_list);
 }
 
+static void __attach_mnt(struct mount *mnt, struct mount *parent)
+{
+	hlist_add_head_rcu(&mnt->mnt_hash,
+			   m_hash(&parent->mnt, mnt->mnt_mountpoint));
+	list_add_tail(&mnt->mnt_child, &parent->mnt_mounts);
+}
+
 /*
  * vfsmount lock must be held for write
  */
@@ -886,28 +872,45 @@ static void attach_mnt(struct mount *mnt,
 			struct mountpoint *mp)
 {
 	mnt_set_mountpoint(parent, mp, mnt);
-	hlist_add_head_rcu(&mnt->mnt_hash, m_hash(&parent->mnt, mp->m_dentry));
-	list_add_tail(&mnt->mnt_child, &parent->mnt_mounts);
+	__attach_mnt(mnt, parent);
 }
 
-static void attach_shadowed(struct mount *mnt,
-			struct mount *parent,
-			struct mount *shadows)
+void mnt_change_mountpoint(struct mount *parent, struct mountpoint *mp, struct mount *mnt)
 {
-	if (shadows) {
-		hlist_add_behind_rcu(&mnt->mnt_hash, &shadows->mnt_hash);
-		list_add(&mnt->mnt_child, &shadows->mnt_child);
-	} else {
-		hlist_add_head_rcu(&mnt->mnt_hash,
-				m_hash(&parent->mnt, mnt->mnt_mountpoint));
-		list_add_tail(&mnt->mnt_child, &parent->mnt_mounts);
-	}
+	struct mountpoint *old_mp = mnt->mnt_mp;
+	struct dentry *old_mountpoint = mnt->mnt_mountpoint;
+	struct mount *old_parent = mnt->mnt_parent;
+
+	list_del_init(&mnt->mnt_child);
+	hlist_del_init(&mnt->mnt_mp_list);
+	hlist_del_init_rcu(&mnt->mnt_hash);
+
+	attach_mnt(mnt, parent, mp);
+
+	put_mountpoint(old_mp);
+
+	/*
+	 * Safely avoid even the suggestion this code might sleep or
+	 * lock the mount hash by taking advantage of the knowledge that
+	 * mnt_change_mountpoint will not release the final reference
+	 * to a mountpoint.
+	 *
+	 * During mounting, the mount passed in as the parent mount will
+	 * continue to use the old mountpoint and during unmounting, the
+	 * old mountpoint will continue to exist until namespace_unlock,
+	 * which happens well after mnt_change_mountpoint.
+	 */
+	spin_lock(&old_mountpoint->d_lock);
+	old_mountpoint->d_lockref.count--;
+	spin_unlock(&old_mountpoint->d_lock);
+
+	mnt_add_count(old_parent, -1);
 }
 
 /*
  * vfsmount lock must be held for write
  */
-static void commit_tree(struct mount *mnt, struct mount *shadows)
+static void commit_tree(struct mount *mnt)
 {
 	struct mount *parent = mnt->mnt_parent;
 	struct mount *m;
@@ -925,7 +928,7 @@ static void commit_tree(struct mount *mnt, struct mount *shadows)
 	n->mounts += n->pending_mounts;
 	n->pending_mounts = 0;
 
-	attach_shadowed(mnt, parent, shadows);
+	__attach_mnt(mnt, parent);
 	touch_mnt_namespace(n);
 }
 
@@ -989,6 +992,21 @@ vfs_kern_mount(struct file_system_type *type, int flags, const char *name, void
 }
 EXPORT_SYMBOL_GPL(vfs_kern_mount);
 
+struct vfsmount *
+vfs_submount(const struct dentry *mountpoint, struct file_system_type *type,
+	     const char *name, void *data)
+{
+	/* Until it is worked out how to pass the user namespace
+	 * through from the parent mount to the submount don't support
+	 * unprivileged mounts with submounts.
+	 */
+	if (mountpoint->d_sb->s_user_ns != &init_user_ns)
+		return ERR_PTR(-EPERM);
+
+	return vfs_kern_mount(type, MS_SUBMOUNT, name, data);
+}
+EXPORT_SYMBOL_GPL(vfs_submount);
+
 static struct mount *clone_mnt(struct mount *old, struct dentry *root,
 					int flag)
 {
@@ -1220,65 +1238,6 @@ struct vfsmount *mnt_clone_internal(const struct path *path)
 	return &p->mnt;
 }
 
-static inline void mangle(struct seq_file *m, const char *s)
-{
-	seq_escape(m, s, " \t\n\\");
-}
-
-/*
- * Simple .show_options callback for filesystems which don't want to
- * implement more complex mount option showing.
- *
- * See also save_mount_options().
- */
-int generic_show_options(struct seq_file *m, struct dentry *root)
-{
-	const char *options;
-
-	rcu_read_lock();
-	options = rcu_dereference(root->d_sb->s_options);
-
-	if (options != NULL && options[0]) {
-		seq_putc(m, ',');
-		mangle(m, options);
-	}
-	rcu_read_unlock();
-
-	return 0;
-}
-EXPORT_SYMBOL(generic_show_options);
-
-/*
- * If filesystem uses generic_show_options(), this function should be
- * called from the fill_super() callback.
- *
- * The .remount_fs callback usually needs to be handled in a special
- * way, to make sure, that previous options are not overwritten if the
- * remount fails.
- *
- * Also note, that if the filesystem's .remount_fs function doesn't
- * reset all options to their default value, but changes only newly
- * given options, then the displayed options will not reflect reality
- * any more.
- */
-void save_mount_options(struct super_block *sb, char *options)
-{
-	BUG_ON(sb->s_options);
-	rcu_assign_pointer(sb->s_options, kstrdup(options, GFP_KERNEL));
-}
-EXPORT_SYMBOL(save_mount_options);
-
-void replace_mount_options(struct super_block *sb, char *options)
-{
-	char *old = sb->s_options;
-	rcu_assign_pointer(sb->s_options, options);
-	if (old) {
-		synchronize_rcu();
-		kfree(old);
-	}
-}
-EXPORT_SYMBOL(replace_mount_options);
-
 #ifdef CONFIG_PROC_FS
 /* iterator; we want it to have access to namespace_sem, thus here... */
 static void *m_start(struct seq_file *m, loff_t *pos)
@@ -1639,7 +1598,7 @@ out_unlock:
 	namespace_unlock();
 }
 
-/* 
+/*
  * Is the caller allowed to modify his namespace?
  */
 static inline bool may_mount(void)
@@ -1764,7 +1723,6 @@ struct mount *copy_tree(struct mount *mnt, struct dentry *dentry,
 			continue;
 
 		for (s = r; s; s = next_mnt(s, r)) {
-			struct mount *t = NULL;
 			if (!(flag & CL_COPY_UNBINDABLE) &&
 			    IS_MNT_UNBINDABLE(s)) {
 				s = skip_mnt_tree(s);
@@ -1786,14 +1744,7 @@ struct mount *copy_tree(struct mount *mnt, struct dentry *dentry,
 				goto out;
 			lock_mount_hash();
 			list_add_tail(&q->mnt_list, &res->mnt_list);
-			mnt_set_mountpoint(parent, p->mnt_mp, q);
-			if (!list_empty(&parent->mnt_mounts)) {
-				t = list_last_entry(&parent->mnt_mounts,
-					struct mount, mnt_child);
-				if (t->mnt_mp != p->mnt_mp)
-					t = NULL;
-			}
-			attach_shadowed(q, parent, t);
+			attach_mnt(q, parent, p->mnt_mp);
 			unlock_mount_hash();
 		}
 	}
@@ -1992,10 +1943,18 @@ static int attach_recursive_mnt(struct mount *source_mnt,
 {
 	HLIST_HEAD(tree_list);
 	struct mnt_namespace *ns = dest_mnt->mnt_ns;
+	struct mountpoint *smp;
 	struct mount *child, *p;
 	struct hlist_node *n;
 	int err;
 
+	/* Preallocate a mountpoint in case the new mounts need
+	 * to be tucked under other mounts.
+	 */
+	smp = get_mountpoint(source_mnt->mnt.mnt_root);
+	if (IS_ERR(smp))
+		return PTR_ERR(smp);
+
 	/* Is there space to add these mounts to the mount namespace? */
 	if (!parent_path) {
 		err = count_mounts(ns, source_mnt);
@@ -2022,16 +1981,19 @@ static int attach_recursive_mnt(struct mount *source_mnt,
 		touch_mnt_namespace(source_mnt->mnt_ns);
 	} else {
 		mnt_set_mountpoint(dest_mnt, dest_mp, source_mnt);
-		commit_tree(source_mnt, NULL);
+		commit_tree(source_mnt);
 	}
 
 	hlist_for_each_entry_safe(child, n, &tree_list, mnt_hash) {
 		struct mount *q;
 		hlist_del_init(&child->mnt_hash);
-		q = __lookup_mnt_last(&child->mnt_parent->mnt,
-				      child->mnt_mountpoint);
-		commit_tree(child, q);
+		q = __lookup_mnt(&child->mnt_parent->mnt,
+				 child->mnt_mountpoint);
+		if (q)
+			mnt_change_mountpoint(child, smp, q);
+		commit_tree(child);
 	}
+	put_mountpoint(smp);
 	unlock_mount_hash();
 
 	return 0;
@@ -2046,6 +2008,11 @@ static int attach_recursive_mnt(struct mount *source_mnt,
 	cleanup_group_ids(source_mnt, NULL);
  out:
 	ns->pending_mounts = 0;
+
+	read_seqlock_excl(&mount_lock);
+	put_mountpoint(smp);
+	read_sequnlock_excl(&mount_lock);
+
 	return err;
 }
 
@@ -2185,7 +2152,7 @@ static int do_loopback(struct path *path, const char *old_name,
 
 	err = -EINVAL;
 	if (mnt_ns_loop(old_path.dentry))
-		goto out; 
+		goto out;
 
 	mp = lock_mount(path);
 	err = PTR_ERR(mp);
@@ -2794,7 +2761,7 @@ long do_mount(const char *dev_name, const char __user *dir_name,
 
 	flags &= ~(MS_NOSUID | MS_NOEXEC | MS_NODEV | MS_ACTIVE | MS_BORN |
 		   MS_NOATIME | MS_NODIRATIME | MS_RELATIME| MS_KERNMOUNT |
-		   MS_STRICTATIME | MS_NOREMOTELOCK);
+		   MS_STRICTATIME | MS_NOREMOTELOCK | MS_SUBMOUNT);
 
 	if (flags & MS_REMOUNT)
 		retval = do_remount(&path, flags & ~MS_REMOUNT, mnt_flags,
@@ -3213,7 +3180,6 @@ static void __init init_mount_tree(void)
 
 void __init mnt_init(void)
 {
-	unsigned u;
 	int err;
 
 	mnt_cache = kmem_cache_create("mnt_cache", sizeof(struct mount),
@@ -3222,22 +3188,17 @@ void __init mnt_init(void)
 	mount_hashtable = alloc_large_system_hash("Mount-cache",
 				sizeof(struct hlist_head),
 				mhash_entries, 19,
-				0,
+				HASH_ZERO,
 				&m_hash_shift, &m_hash_mask, 0, 0);
 	mountpoint_hashtable = alloc_large_system_hash("Mountpoint-cache",
 				sizeof(struct hlist_head),
 				mphash_entries, 19,
-				0,
+				HASH_ZERO,
 				&mp_hash_shift, &mp_hash_mask, 0, 0);
 
 	if (!mount_hashtable || !mountpoint_hashtable)
 		panic("Failed to allocate mount hash table\n");
 
-	for (u = 0; u <= m_hash_mask; u++)
-		INIT_HLIST_HEAD(&mount_hashtable[u]);
-	for (u = 0; u <= mp_hash_mask; u++)
-		INIT_HLIST_HEAD(&mountpoint_hashtable[u]);
-
 	kernfs_init();
 
 	err = sysfs_init();
@@ -3437,8 +3398,9 @@ static void mntns_put(struct ns_common *ns)
 static int mntns_install(struct nsproxy *nsproxy, struct ns_common *ns)
 {
 	struct fs_struct *fs = current->fs;
-	struct mnt_namespace *mnt_ns = to_mnt_ns(ns);
+	struct mnt_namespace *mnt_ns = to_mnt_ns(ns), *old_mnt_ns;
 	struct path root;
+	int err;
 
 	if (!ns_capable(mnt_ns->user_ns, CAP_SYS_ADMIN) ||
 	    !ns_capable(current_user_ns(), CAP_SYS_CHROOT) ||
@@ -3449,15 +3411,20 @@ static int mntns_install(struct nsproxy *nsproxy, struct ns_common *ns)
 		return -EINVAL;
 
 	get_mnt_ns(mnt_ns);
-	put_mnt_ns(nsproxy->mnt_ns);
+	old_mnt_ns = nsproxy->mnt_ns;
 	nsproxy->mnt_ns = mnt_ns;
 
 	/* Find the root */
-	root.mnt    = &mnt_ns->root->mnt;
-	root.dentry = mnt_ns->root->mnt.mnt_root;
-	path_get(&root);
-	while(d_mountpoint(root.dentry) && follow_down_one(&root))
-		;
+	err = vfs_path_lookup(mnt_ns->root->mnt.mnt_root, &mnt_ns->root->mnt,
+				"/", LOOKUP_DOWN, &root);
+	if (err) {
+		/* revert to old namespace */
+		nsproxy->mnt_ns = old_mnt_ns;
+		put_mnt_ns(mnt_ns);
+		return err;
+	}
+
+	put_mnt_ns(old_mnt_ns);
 
 	/* Update the pwd and root */
 	set_fs_pwd(fs, &root);