umount: Do not allow unmounting rootfs.

Andrew Vagin <avagin@parallels.com> writes:

> #define _GNU_SOURCE
> #include <sys/types.h>
> #include <sys/stat.h>
> #include <fcntl.h>
> #include <sched.h>
> #include <unistd.h>
> #include <sys/mount.h>
>
> int main(int argc, char **argv)
> {
> 	int fd;
>
> 	fd = open("/proc/self/ns/mnt", O_RDONLY);
> 	if (fd < 0)
> 	   return 1;
> 	   while (1) {
> 	   	 if (umount2("/", MNT_DETACH) ||
> 		        setns(fd, CLONE_NEWNS))
> 					break;
> 					}
>
> 					return 0;
> }
>
> root@ubuntu:/home/avagin# gcc -Wall nsenter.c -o nsenter
> root@ubuntu:/home/avagin# strace ./nsenter
> execve("./nsenter", ["./nsenter"], [/* 22 vars */]) = 0
> ...
> open("/proc/self/ns/mnt", O_RDONLY)     = 3
> umount("/", MNT_DETACH)                 = 0
> setns(3, 131072)                        = 0
> umount("/", MNT_DETACH
>
causes:

> [  260.548301] ------------[ cut here ]------------
> [  260.550941] kernel BUG at /build/buildd/linux-3.13.0/fs/pnode.c:372!
> [  260.552068] invalid opcode: 0000 [#1] SMP
> [  260.552068] Modules linked in: xt_CHECKSUM iptable_mangle xt_tcpudp xt_addrtype xt_conntrack ipt_MASQUERADE iptable_nat nf_conntrack_ipv4 nf_defrag_ipv4 nf_nat_ipv4 nf_nat nf_conntrack bridge stp llc dm_thin_pool dm_persistent_data dm_bufio dm_bio_prison iptable_filter ip_tables x_tables crct10dif_pclmul crc32_pclmul ghash_clmulni_intel binfmt_misc nfsd auth_rpcgss nfs_acl aesni_intel nfs lockd aes_x86_64 sunrpc fscache lrw gf128mul glue_helper ablk_helper cryptd serio_raw ppdev parport_pc lp parport btrfs xor raid6_pq libcrc32c psmouse floppy
> [  260.552068] CPU: 0 PID: 1723 Comm: nsenter Not tainted 3.13.0-30-generic #55-Ubuntu
> [  260.552068] Hardware name: Bochs Bochs, BIOS Bochs 01/01/2011
> [  260.552068] task: ffff8800376097f0 ti: ffff880074824000 task.ti: ffff880074824000
> [  260.552068] RIP: 0010:[<ffffffff811e9483>]  [<ffffffff811e9483>] propagate_umount+0x123/0x130
> [  260.552068] RSP: 0018:ffff880074825e98  EFLAGS: 00010246
> [  260.552068] RAX: ffff88007c741140 RBX: 0000000000000002 RCX: ffff88007c741190
> [  260.552068] RDX: ffff88007c741190 RSI: ffff880074825ec0 RDI: ffff880074825ec0
> [  260.552068] RBP: ffff880074825eb0 R08: 00000000000172e0 R09: ffff88007fc172e0
> [  260.552068] R10: ffffffff811cc642 R11: ffffea0001d59000 R12: ffff88007c741140
> [  260.552068] R13: ffff88007c741140 R14: ffff88007c741140 R15: 0000000000000000
> [  260.552068] FS:  00007fd5c7e41740(0000) GS:ffff88007fc00000(0000) knlGS:0000000000000000
> [  260.552068] CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
> [  260.552068] CR2: 00007fd5c7968050 CR3: 0000000070124000 CR4: 00000000000406f0
> [  260.552068] Stack:
> [  260.552068]  0000000000000002 0000000000000002 ffff88007c631000 ffff880074825ed8
> [  260.552068]  ffffffff811dcfac ffff88007c741140 0000000000000002 ffff88007c741160
> [  260.552068]  ffff880074825f38 ffffffff811dd12b ffffffff811cc642 0000000075640000
> [  260.552068] Call Trace:
> [  260.552068]  [<ffffffff811dcfac>] umount_tree+0x20c/0x260
> [  260.552068]  [<ffffffff811dd12b>] do_umount+0x12b/0x300
> [  260.552068]  [<ffffffff811cc642>] ? final_putname+0x22/0x50
> [  260.552068]  [<ffffffff811cc849>] ? putname+0x29/0x40
> [  260.552068]  [<ffffffff811dd88c>] SyS_umount+0xdc/0x100
> [  260.552068]  [<ffffffff8172aeff>] tracesys+0xe1/0xe6
> [  260.552068] Code: 89 50 08 48 8b 50 08 48 89 02 49 89 45 08 e9 72 ff ff ff 0f 1f 44 00 00 4c 89 e6 4c 89 e7 e8 f5 f6 ff ff 48 89 c3 e9 39 ff ff ff <0f> 0b 66 2e 0f 1f 84 00 00 00 00 00 90 66 66 66 66 90 55 b8 01
> [  260.552068] RIP  [<ffffffff811e9483>] propagate_umount+0x123/0x130
> [  260.552068]  RSP <ffff880074825e98>
> [  260.611451] ---[ end trace 11c33d85f1d4c652 ]--

Which in practice is totally uninteresting.  Only the global root user can
do it, and it is just a stupid thing to do.

However that is no excuse to allow a silly way to oops the kernel.

We can avoid this silly problem by setting MNT_LOCKED on the rootfs
mount point and thus avoid needing any special cases in the unmount
code.

Signed-off-by: "Eric W. Biederman" <ebiederm@xmission.com>

fs/namespace.c

@@ -3011,6 +3011,7 @@ static void __init init_mount_tree(void)
 
 	root.mnt = mnt;
 	root.dentry = mnt->mnt_root;
+	mnt->mnt_flags |= MNT_LOCKED;
 
 	set_fs_pwd(current->fs, &root);
 	set_fs_root(current->fs, &root);