111 lines
3 KiB
Rust
111 lines
3 KiB
Rust
//! Per-child seccomp network filter. No-op on non-Linux.
|
|
|
|
/// Install seccomp BPF filter blocking network syscalls.
|
|
///
|
|
/// # Safety
|
|
///
|
|
/// Must be called in a `pre_exec` context (after `fork`, before `exec`).
|
|
#[cfg(target_os = "linux")]
|
|
pub unsafe fn install_child_network_filter() -> std::io::Result<()> {
|
|
use libc::{
|
|
BPF_ABS, BPF_JEQ, BPF_JMP, BPF_K, BPF_LD, BPF_RET, BPF_W, PR_SET_NO_NEW_PRIVS,
|
|
PR_SET_SECCOMP, SECCOMP_MODE_FILTER, SYS_accept, SYS_accept4, SYS_bind, SYS_connect,
|
|
SYS_listen, SYS_sendmsg, SYS_sendto, prctl, sock_filter, sock_fprog,
|
|
};
|
|
|
|
const SECCOMP_RET_ALLOW: u32 = 0x7fff_0000;
|
|
const SECCOMP_RET_ERRNO: u32 = 0x0005_0000;
|
|
const EPERM_VAL: u32 = 1; // libc::EPERM
|
|
|
|
macro_rules! bpf_stmt {
|
|
($code:expr, $k:expr) => {
|
|
sock_filter {
|
|
code: $code as u16,
|
|
jt: 0,
|
|
jf: 0,
|
|
k: $k as u32,
|
|
}
|
|
};
|
|
}
|
|
|
|
macro_rules! bpf_jump {
|
|
($code:expr, $k:expr, $jt:expr, $jf:expr) => {
|
|
sock_filter {
|
|
code: $code as u16,
|
|
jt: $jt,
|
|
jf: $jf,
|
|
k: $k as u32,
|
|
}
|
|
};
|
|
}
|
|
|
|
const NR_OFFSET: u32 = 0; // seccomp_data.nr offset
|
|
|
|
let blocked_syscalls: &[i64] = &[
|
|
SYS_connect,
|
|
SYS_bind,
|
|
SYS_sendto,
|
|
SYS_sendmsg,
|
|
SYS_listen,
|
|
SYS_accept,
|
|
SYS_accept4,
|
|
];
|
|
|
|
let mut filter: Vec<sock_filter> = Vec::new();
|
|
let total_checks = blocked_syscalls.len();
|
|
|
|
// 1. Load syscall number
|
|
filter.push(bpf_stmt!(BPF_LD | BPF_W | BPF_ABS, NR_OFFSET));
|
|
|
|
// 2. Check each blocked syscall
|
|
for (i, &syscall) in blocked_syscalls.iter().enumerate() {
|
|
let remaining = total_checks - i - 1;
|
|
filter.push(bpf_jump!(
|
|
BPF_JMP | BPF_JEQ | BPF_K,
|
|
syscall,
|
|
remaining as u8 + 1, // match: jump to ERRNO
|
|
0 // no match: check next
|
|
));
|
|
}
|
|
|
|
// 3. Default: ALLOW
|
|
filter.push(bpf_stmt!(BPF_RET | BPF_K, SECCOMP_RET_ALLOW));
|
|
|
|
// 4. Blocked: ERRNO(EPERM)
|
|
filter.push(bpf_stmt!(BPF_RET | BPF_K, SECCOMP_RET_ERRNO | EPERM_VAL));
|
|
|
|
let prog = sock_fprog {
|
|
len: filter.len() as u16,
|
|
filter: filter.as_mut_ptr(),
|
|
};
|
|
|
|
// Must set PR_SET_NO_NEW_PRIVS before applying seccomp filter
|
|
// SAFETY: prctl with PR_SET_NO_NEW_PRIVS is safe in pre_exec context.
|
|
if unsafe { prctl(PR_SET_NO_NEW_PRIVS, 1, 0, 0, 0) } != 0 {
|
|
return Err(std::io::Error::last_os_error());
|
|
}
|
|
|
|
// SAFETY: prog is a valid sock_fprog pointing to our filter array.
|
|
if unsafe {
|
|
prctl(
|
|
PR_SET_SECCOMP,
|
|
SECCOMP_MODE_FILTER as libc::c_ulong,
|
|
&prog as *const _ as libc::c_ulong,
|
|
0,
|
|
0,
|
|
)
|
|
} != 0
|
|
{
|
|
return Err(std::io::Error::last_os_error());
|
|
}
|
|
|
|
Ok(())
|
|
}
|
|
|
|
/// # Safety
|
|
///
|
|
/// No-op on non-Linux.
|
|
#[cfg(not(target_os = "linux"))]
|
|
pub unsafe fn install_child_network_filter() -> std::io::Result<()> {
|
|
Ok(())
|
|
}
|