[Devel] [PATCH RHEL8 COMMIT] mnt: allow to add a mount into an existing group

Konstantin Khorenko khorenko at virtuozzo.com
Fri May 8 17:43:40 MSK 2020


The commit is pushed to "branch-rh8-4.18.0-80.1.2.vz8.3.x-ovz" and will appear at https://src.openvz.org/scm/ovz/vzkernel.git
after rh8-4.18.0-80.1.2.vz8.3.9
------>
commit 6c0cfbbab61642b5ce6d4cefad810cdd84f9234d
Author: Andrei Vagin <avagin at openvz.org>
Date:   Fri May 8 17:43:40 2020 +0300

    mnt: allow to add a mount into an existing group
    
    Now a shared group can be only inherited from a source mount.
    This patch adds an ability to add a mount into an existing shared
    group.
    
    mount(source, target, NULL, MS_SET_GROUP, NULL)
    
    mount() with the MS_SET_GROUP flag adds the "target" mount into a group
    of the "source" mount. The calling process has to have the CAP_SYS_ADMIN
    capability in namespaces of these mounts. The source and the target
    mounts have to have the same super block.
    
    This new functionality together with "mnt: Tuck mounts under others
    instead of creating shadow/side mounts." allows CRIU to dump and restore
    any set of mount namespaces.
    
    Currently we have a lot of issues about dumping and restoring mount
    namespaces. The bigest problem is that we can't construct mount trees
    directly due to several reasons:
    * groups can't be set, they can be only inherited
    * file systems has to be mounted from the specified user namespaces
    * the mount() syscall doesn't just create one mount -- the mount is
      also propagated to all members of a parent group
    * umount() doesn't detach mounts from all members of a group
      (mounts with children are not umounted)
    * mounts are propagated underneath of existing mounts
    * mount() doesn't allow to make bind-mounts between two namespaces
    * processes can have opened file descriptors to overmounted files
    
    All these operations are non-trivial, making the task of restoring
    a mount namespace practically unsolvable for reasonable time. The
    proposed change allows to restore a mount namespace in a direct
    manner, without any super complex logic.
    
    Cc: Eric W. Biederman <ebiederm at xmission.com>
    Cc: Alexander Viro <viro at zeniv.linux.org.uk>
    Signed-off-by: Andrei Vagin <avagin at openvz.org>
    
    Patch hangs long in lkml without much review:
    https://patchwork.kernel.org/patch/9703885/
    
    But with it we can implement correct mounts restore in vzcriu much
    easier.
    
    Add some restrictions: a) prohibit setting group on non-mnt_root dentry;
    b) prohibit destination mount to be in non-current mntns; c) only super
    or pseudosuper ve can set group.
    
    https://jira.sw.ru/browse/PSBM-58617
    
    Signed-off-by: Pavel Tikhomirov <ptikhomirov at virtuozzo.com>
    
    > Is it OK to have the flag's semantics overloaded?
    1) do_mount is only called from syscall:
    
    sys_osf_mount
       osf_ufs_mount
       osf_procfs_mount
       osf_cdfs_mount
         do_mount
    
    compat_sys_mount
       do_mount
    
    sys_mount
       do_mount
    
    2) previousely MS_SUBMOUNT was explicitly ignored in vz7 in do_mount
    because it is kernel internal flag:
    
    flags &= ~(MS_NOSUID | MS_NOEXEC | MS_NODEV | MS_ACTIVE | MS_BORN |
       MS_NOATIME | MS_NODIRATIME | MS_RELATIME| MS_KERNMOUNT |
       MS_STRICTATIME | MS_NOREMOTELOCK | MS_SUBMOUNT);
    
    in ms and vz8 it is a bit more complex but still ignored. Because it is
    kernel internal flag and userspace can't set it.
    
    If we add MS_SET_GROUP with same number as MS_SUBMOUNT but only check it
    in do_mount where it was previousely ignored it looks OK to me.
---
 fs/namespace.c          | 65 +++++++++++++++++++++++++++++++++++++++++++++++++
 include/uapi/linux/fs.h |  6 +++++
 2 files changed, 71 insertions(+)

diff --git a/fs/namespace.c b/fs/namespace.c
index b06fdd118629..2bc53000c026 100644
--- a/fs/namespace.c
+++ b/fs/namespace.c
@@ -2324,6 +2324,69 @@ static inline int tree_contains_unbindable(struct mount *mnt)
 	return 0;
 }
 
+static int do_set_group(struct path *path, const char *sibling_name)
+{
+	struct ve_struct *ve = get_exec_env();
+	struct mount *sibling, *mnt;
+	struct path sibling_path;
+	int err;
+
+	if (!ve_is_super(ve) && !ve->is_pseudosuper)
+		return -EPERM;
+
+	if (!sibling_name || !*sibling_name)
+		return -EINVAL;
+
+	if (path->dentry != path->mnt->mnt_root)
+		return -EINVAL;
+
+	err = kern_path(sibling_name, LOOKUP_FOLLOW, &sibling_path);
+	if (err)
+		return err;
+
+	err = -EINVAL;
+	if (sibling_path.dentry != sibling_path.mnt->mnt_root)
+		goto out_put;
+
+	sibling = real_mount(sibling_path.mnt);
+	mnt = real_mount(path->mnt);
+
+	if (!check_mnt(mnt))
+		goto out_put;
+
+	namespace_lock();
+
+	err = -EPERM;
+	if (!sibling->mnt_ns ||
+	    !ns_capable(sibling->mnt_ns->user_ns, CAP_SYS_ADMIN))
+		goto out_unlock;
+
+	err = -EINVAL;
+	if (sibling->mnt.mnt_sb != mnt->mnt.mnt_sb)
+		goto out_unlock;
+
+	if (IS_MNT_SHARED(mnt) || IS_MNT_SLAVE(mnt))
+		goto out_unlock;
+
+	if (IS_MNT_SLAVE(sibling)) {
+		list_add(&mnt->mnt_slave, &sibling->mnt_slave);
+		mnt->mnt_master = sibling->mnt_master;
+	}
+
+	if (IS_MNT_SHARED(sibling)) {
+		mnt->mnt_group_id = sibling->mnt_group_id;
+		list_add(&mnt->mnt_share, &sibling->mnt_share);
+		set_mnt_shared(mnt);
+	}
+
+	err = 0;
+out_unlock:
+	namespace_unlock();
+out_put:
+	path_put(&sibling_path);
+	return err;
+}
+
 static int do_move_mount(struct path *path, const char *old_name)
 {
 	struct path old_path, parent_path;
@@ -2810,6 +2873,8 @@ long do_mount(const char *dev_name, const char __user *dir_name,
 		retval = do_change_type(&path, flags);
 	else if (flags & MS_MOVE)
 		retval = do_move_mount(&path, dev_name);
+	else if (flags & MS_SET_GROUP)
+		retval = do_set_group(&path, dev_name);
 	else
 		retval = do_new_mount(&path, type_page, sb_flags, mnt_flags,
 				      dev_name, data_page);
diff --git a/include/uapi/linux/fs.h b/include/uapi/linux/fs.h
index 876c308d57c0..699ad890ac76 100644
--- a/include/uapi/linux/fs.h
+++ b/include/uapi/linux/fs.h
@@ -132,6 +132,12 @@ struct inodes_stat_t {
 #define MS_STRICTATIME	(1<<24) /* Always perform atime updates */
 #define MS_LAZYTIME	(1<<25) /* Update the on-disk [acm]times lazily */
 
+/*
+ * Here are commands and flags. Commands are handled in do_mount()
+ * and can intersect with kernel internal flags.
+ */
+#define MS_SET_GROUP	(1<<26) /* Add a mount into a shared group */
+
 /* These sb flags are internal to the kernel */
 #define MS_SUBMOUNT     (1<<26)
 #define MS_NOREMOTELOCK	(1<<27)


More information about the Devel mailing list