On 4/5/2022 6:11 AM, Roberto Sassu wrote:
Introduce a new LSM to protect pinned objects in a bpf filesystem
This is *not an LSM*. Do not call it an LSM. It is a set of
eBPF programs. We have all the opportunities for confusion
that we need. I suggested that you call this a BPF security
module (BSM) earlier today. You have any number of things
you can call this that won't be objectionable.
instance. This is useful for example to ensure that an LSM will always
enforce its policy, even despite root tries to unload the corresponding
eBPF program.
How is this going to ensure that SELinux enforces its policy?
AppArmor has no eBPF program that corresponds to its policy,
neither does any other existing LSM, save BPF. Your claim is
nonsensical in the face of LSM behavior.
Achieve the protection by denying inode unlink and unmount of the
protected bpf filesystem instance. Since protected inodes hold a
reference of the link of loaded programs (e.g. LSM hooks), denying
operations on them will prevent the ref count of the links from reaching
zero, ensuring that the programs remain always active.
Enable the protection only for the instance created by the user space
counterpart of the LSM, and don't interfere with other instances, so
that their behavior remains unchanged.
Suggested-by: Djalal Harouni <tixxdz@xxxxxxxxx>
Signed-off-by: Roberto Sassu <roberto.sassu@xxxxxxxxxx>
---
.gitignore | 4 +++
Makefile | 18 ++++++++++++++
bpffs_lsm_kern.c | 63 ++++++++++++++++++++++++++++++++++++++++++++++++
bpffs_lsm_user.c | 60 +++++++++++++++++++++++++++++++++++++++++++++
4 files changed, 145 insertions(+)
create mode 100644 .gitignore
create mode 100644 Makefile
create mode 100644 bpffs_lsm_kern.c
create mode 100644 bpffs_lsm_user.c
diff --git a/.gitignore b/.gitignore
new file mode 100644
index 000000000000..7fa02964f1dc
--- /dev/null
+++ b/.gitignore
@@ -0,0 +1,4 @@
+*.o
+vmlinux.h
+bpffs_lsm_kern.skel.h
+bpffs_lsm_user
diff --git a/Makefile b/Makefile
new file mode 100644
index 000000000000..c3d805759db3
--- /dev/null
+++ b/Makefile
@@ -0,0 +1,18 @@
+# SPDX-License-Identifier: GPL-2.0
+all: bpffs_lsm_user
+
+clean:
+ rm -rf bpffs_lsm.skel.h vmlinux.h bpffs_lsm_kern.o bpffs_lsm_user
+
+vmlinux.h:
+ /usr/sbin/bpftool btf dump file /sys/kernel/btf/vmlinux format c > \
+ vmlinux.h
+
+bpffs_lsm_kern.skel.h: bpffs_lsm_kern.o
+ bpftool gen skeleton $< > $@
+
+bpffs_lsm_kern.o: bpffs_lsm_kern.c vmlinux.h
+ clang -Wall -Werror -g -O2 -target bpf -c $< -o $@
+
+bpffs_lsm_user: bpffs_lsm_user.c bpffs_lsm_kern.skel.h bpffs_lsm_kern.o
+ cc -Wall -Werror -g -o $@ $< -lbpf
diff --git a/bpffs_lsm_kern.c b/bpffs_lsm_kern.c
new file mode 100644
index 000000000000..b3ccb2a75c95
--- /dev/null
+++ b/bpffs_lsm_kern.c
@@ -0,0 +1,63 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (C) 2022 Huawei Technologies Duesseldorf GmbH
+ *
+ * Authors:
+ * Roberto Sassu <roberto.sassu@xxxxxxxxxx>
+ *
+ * Implement an LSM to protect a bpf filesystem instance.
+ */
+
+#include "vmlinux.h"
+#include <errno.h>
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_tracing.h>
+#include <bpf/bpf_core_read.h>
+
+char _license[] SEC("license") = "GPL";
+
+uint32_t monitored_pid = 0;
+
+struct {
+ __uint(type, BPF_MAP_TYPE_INODE_STORAGE);
+ __uint(map_flags, BPF_F_NO_PREALLOC);
+ __type(key, int);
+ __type(value, sizeof(uint8_t));
+} inode_storage_map SEC(".maps");
+
+SEC("lsm/sb_set_mnt_opts")
+int BPF_PROG(sb_set_mnt_opts, struct super_block *sb, void *mnt_opts,
+ unsigned long kern_flags, unsigned long *set_kern_flags)
+{
+ u32 pid;
+
+ pid = bpf_get_current_pid_tgid() >> 32;
+ if (pid != monitored_pid)
+ return 0;
+
+ if (!bpf_inode_storage_get(&inode_storage_map, sb->s_root->d_inode, 0,
+ BPF_LOCAL_STORAGE_GET_F_CREATE))
+ return -EPERM;
+
+ return 0;
+}
+
+SEC("lsm/inode_unlink")
+int BPF_PROG(inode_unlink, struct inode *dir, struct dentry *dentry)
+{
+ if (bpf_inode_storage_get(&inode_storage_map,
+ dir->i_sb->s_root->d_inode, 0, 0))
+ return -EPERM;
+
+ return 0;
+}
+
+SEC("lsm/sb_umount")
+int BPF_PROG(sb_umount, struct vfsmount *mnt, int flags)
+{
+ if (bpf_inode_storage_get(&inode_storage_map,
+ mnt->mnt_sb->s_root->d_inode, 0, 0))
+ return -EPERM;
+
+ return 0;
+}
diff --git a/bpffs_lsm_user.c b/bpffs_lsm_user.c
new file mode 100644
index 000000000000..e20180cc5db9
--- /dev/null
+++ b/bpffs_lsm_user.c
@@ -0,0 +1,60 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (C) 2022 Huawei Technologies Duesseldorf GmbH
+ *
+ * Author: Roberto Sassu <roberto.sassu@xxxxxxxxxx>
+ *
+ * Implement the user space side of the LSM for bpffs.
+ */
+
+#include <fcntl.h>
+#include <unistd.h>
+#include <stdio.h>
+#include <errno.h>
+#include <stdlib.h>
+#include <unistd.h>
+#include <limits.h>
+#include <sys/mount.h>
+#include <sys/stat.h>
+
+#include "bpffs_lsm_kern.skel.h"
+
+#define MOUNT_FLAGS (MS_NOSUID | MS_NODEV | MS_NOEXEC | MS_RELATIME)
+
+int main(int argc, char *argv[])
+{
+ char mntpoint[] = "/tmp/bpf_private_mountXXXXXX";
+ char path[PATH_MAX];
+ struct bpffs_lsm_kern *skel;
+ int ret, i;
+
+ skel = bpffs_lsm_kern__open_and_load();
+ if (!skel)
+ return -EINVAL;
+
+ ret = bpffs_lsm_kern__attach(skel);
+ if (ret < 0)
+ goto out_destroy;
+
+ mkdtemp(mntpoint);
+
+ skel->bss->monitored_pid = getpid();
+ ret = mount(mntpoint, mntpoint, "bpf", MOUNT_FLAGS, NULL);
+ skel->bss->monitored_pid = 0;
+
+ if (ret < 0)
+ goto out_destroy;
+
+ for (i = 0; i < skel->skeleton->prog_cnt; i++) {
+ snprintf(path, sizeof(path), "%s/%s", mntpoint,
+ skel->skeleton->progs[i].name);
+ ret = bpf_link__pin(*skel->skeleton->progs[i].link, path);
+ if (ret < 0)
+ goto out_destroy;
+ }
+
+ ret = 0;
+out_destroy:
+ bpffs_lsm_kern__destroy(skel);
+ return ret;
+}
