If a container manager restricts its unprivileged (user namespaced)
children by a device cgroup, it is not necessary to deny mknod()
anymore. Thus, user space applications may map devices on different
locations in the file system by using mknod() inside the container.
A use case for this, we also use in GyroidOS, is to run virsh for
VMs inside an unprivileged container. virsh creates device nodes,
e.g., "/var/run/libvirt/qemu/11-fgfg.dev/null" which currently fails
in a non-initial userns, even if a cgroup device white list with the
corresponding major, minor of /dev/null exists. Thus, in this case
the usual bind mounts or pre populated device nodes under /dev are
not sufficient.
To circumvent this limitation, allow mknod() by checking CAP_MKNOD
in the userns by implementing the security_inode_mknod_nscap(). The
hook implementation checks if the corresponding permission flag
BPF_DEVCG_ACC_MKNOD_UNS is set for the device in the bpf program.
To avoid to create unusable inodes in user space the hook also checks
SB_I_NODEV on the corresponding super block.
Further, the security_sb_alloc_userns() hook is implemented using
cgroup_bpf_current_enabled() to allow usage of device nodes on super
blocks mounted by a guarded task.
Signed-off-by: Michael Weiß <michael.weiss@xxxxxxxxxxxxxxxxxxx>
---
security/device_cgroup/lsm.c | 27 +++++++++++++++++++++++++++
1 file changed, 27 insertions(+)
diff --git a/security/device_cgroup/lsm.c b/security/device_cgroup/lsm.c
index a963536d0a15..6bc984d9c9d1 100644
--- a/security/device_cgroup/lsm.c
+++ b/security/device_cgroup/lsm.c
@@ -66,10 +66,37 @@ static int devcg_inode_mknod(struct inode *dir, struct dentry *dentry,
return __devcg_inode_mknod(mode, dev, DEVCG_ACC_MKNOD);
}
+#ifdef CONFIG_CGROUP_BPF
+static int devcg_sb_alloc_userns(struct super_block *sb)
+{
+ if (cgroup_bpf_current_enabled(CGROUP_DEVICE))
+ return 0;
+
+ return -EPERM;
+}
+
+static int devcg_inode_mknod_nscap(struct inode *dir, struct dentry *dentry,
+ umode_t mode, dev_t dev)
+{
+ if (!cgroup_bpf_current_enabled(CGROUP_DEVICE))
+ return -EPERM;
+
+ // avoid to create unusable inodes in user space
+ if (dentry->d_sb->s_iflags & SB_I_NODEV)
+ return -EPERM;
+
+ return __devcg_inode_mknod(mode, dev, BPF_DEVCG_ACC_MKNOD_UNS);
+}
+#endif /* CONFIG_CGROUP_BPF */
+
static struct security_hook_list devcg_hooks[] __ro_after_init = {
LSM_HOOK_INIT(inode_permission, devcg_inode_permission),
LSM_HOOK_INIT(inode_mknod, devcg_inode_mknod),
LSM_HOOK_INIT(dev_permission, devcg_dev_permission),
+#ifdef CONFIG_CGROUP_BPF
+ LSM_HOOK_INIT(sb_alloc_userns, devcg_sb_alloc_userns),
+ LSM_HOOK_INIT(inode_mknod_nscap, devcg_inode_mknod_nscap),
+#endif
};
static int __init devcgroup_init(void)
--
2.30.2
