Files
ferrix/crates/integration-tests/tests/import_policy.rs
T
Rayhaan JaufeerallyandClaude Fable 5.1 9ca86ede2f Harden import, the kernel task and the RTR client after review
Three independent reviews (hijack resistance, reliability, code health)
of the whole tree. This is what they found that could let a bad route in
or take the daemon down.

Hijacks:
- A route had two paths on a two-octet session, AS_PATH and AS4_PATH,
  read in two places by two rules. A peer could make the origin checked
  on import differ from the one checked at revalidation, and get an
  RPKI-invalid route into the table. AS4_PATH is now merged into AS_PATH
  once, on receipt (RFC 6793 §4.2.3), and nothing else knows of it.
- The next hop is judged on import: it must be usable, agreed on
  (RFC 8950), and by default the peer itself.
- Our own originated prefixes are not taken from other networks.
- A route for a network the machine is on is never put in the kernel.
- Paths with an AS_SET are refused (RFC 9774).
- A configured peer gets one session, not one per BGP Identifier.
- More IPv6 special-purpose prefixes are bogons.

Reliability:
- A batch of requests the kernel refused could overflow the netlink
  socket and end the daemon. The socket has room now, a lost answer or a
  silent kernel means asking what is there, and neither is fatal.
- Working the routes out again within the grace period after a restart
  no longer drops the routes being kept.
- That work can no longer be put off for ever by interface changes.
- Peers whose sessions keep failing are slowed down.
- Unused attribute sets are swept when they pile up, not only each
  minute.
- Log lines a peer can cause are said once in a while.
- An RTR answer is bounded in size and time; data cannot expire between
  two refreshes.
- The shard of a key is taken from a stirred hash: neighbouring bits of
  the hash proved alike for prefixes in a row. The test that showed it,
  failing one run in sixteen, is deterministic now.

The lab has a phase, hijacks, in which FRR tries the first three.
route::apply is a struct with methods instead of nested closures, and
the kernel task's loop is shorter.

Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
2026-10-02 19:13:40 +02:00

284 lines
10 KiB
Rust

//! What is taken from a peer: the checks every route goes through, and the
//! limit on how many a peer may have.
use std::collections::BTreeSet;
use std::net::Ipv4Addr;
use std::time::Duration;
use bgp_integration_tests::default_policy;
use bgp_integration_tests::test_peer::TestPeer;
use bgp_integration_tests::test_server::TestServer;
use bgp_packet::errors::{BgpError, CeaseSubcode};
use bgp_packet::message::{
AsPathAttribute, Message, NextHopPathAttribute, OriginPathAttribute, PathAttribute,
UpdateMessage,
};
use bgp_primitives::ip_prefix::IpPrefix;
use bgp_server::config::PeerConfig;
use bgp_server::family::FamilySet;
use bgp_server::policy::{ImportPolicy, PrefixSet};
use bgp_server::session::DialState;
use eyre::Result;
use tokio::net::TcpListener;
/// AS numbers as they are on the Internet: the checks refuse the private
/// ones the other tests use.
const LOCAL_ASN: u32 = 1299;
const PEER_ASN: u32 = 3333;
const TIMEOUT: Duration = Duration::from_secs(5);
fn prefix(s: &str) -> IpPrefix {
IpPrefix::try_from(s).unwrap()
}
/// A server with one configured peer, at the address the test connects
/// from, whose routes are judged by `import`. Returns the listener that
/// keeps the server's own dialling occupied.
async fn server_with(import: ImportPolicy) -> Result<(TestServer, TcpListener)> {
let listener = TcpListener::bind((Ipv4Addr::LOCALHOST, 0)).await?;
let endpoint = listener.local_addr()?;
let server = TestServer::start_with(LOCAL_ASN, |c| {
c.accept_unconfigured_peers = false;
c.connect_retry = Duration::from_millis(50);
c.peers = vec![PeerConfig {
name: "r1".into(),
endpoint: endpoint.into(),
remote_asn: PEER_ASN,
hold_time_secs: 90,
local_address: None,
families: FamilySet::supported(),
add_path: None,
import,
role: None,
require_role: false,
}];
})
.await?;
Ok((server, listener))
}
async fn established(server: &TestServer) -> Result<TestPeer> {
let mut peer = TestPeer::connect(server.addr).await?;
peer.handshake(PEER_ASN, Ipv4Addr::new(10, 0, 0, 2), 90)
.await?;
tokio::time::timeout(TIMEOUT, async {
while server.registry.list().is_empty() {
tokio::time::sleep(Duration::from_millis(5)).await;
}
})
.await?;
Ok(peer)
}
/// Announces IPv4 `prefixes` with the AS path `path`.
async fn announce(peer: &mut TestPeer, prefixes: &[&str], path: &[u32]) -> Result<()> {
peer.send(&Message::Update(UpdateMessage {
withdrawn_routes: vec![],
path_attributes: vec![
PathAttribute::Origin(OriginPathAttribute::IGP),
AsPathAttribute::from_asns(path.to_vec()),
PathAttribute::NextHop(NextHopPathAttribute(Ipv4Addr::new(192, 0, 2, 1))),
],
announced_routes: prefixes.iter().map(|p| prefix(p).into()).collect(),
}))
.await
}
/// Waits until the server has dealt with `count` announced routes of the
/// session's, taken or refused, and returns the prefixes in its table.
async fn table_after(server: &TestServer, taken: u64, refused: u64) -> Result<BTreeSet<String>> {
let counters = server.registry.list()[0].counters.clone();
tokio::time::timeout(TIMEOUT, async {
while (counters.routes(), counters.rejected()) != (taken, refused) {
tokio::time::sleep(Duration::from_millis(5)).await;
}
})
.await
.map_err(|_| {
eyre::eyre!(
"the server took {} routes and refused {}; expected {taken} and {refused}",
counters.routes(),
counters.rejected()
)
})?;
Ok(server
.received_routes()
.iter()
.map(|route| route.prefix.to_string())
.collect())
}
fn set(prefixes: &[&str]) -> BTreeSet<String> {
prefixes.iter().map(|p| p.to_string()).collect()
}
/// With nothing configured for a peer but its address and AS, its routes
/// still go through the checks that hold for anyone: only space that is
/// routed on the Internet, nothing too specific, a path that begins with
/// the peer and has no reserved AS in it, and never one that has been
/// through us. Everything a peer sent used to be taken.
#[tokio::test]
async fn test_routes_that_no_peer_should_announce_are_refused() -> Result<()> {
let (server, _listener) = server_with(default_policy()).await?;
let mut peer = established(&server).await?;
// One UPDATE with good and bad prefixes: the good ones are taken.
announce(
&mut peer,
&[
"193.0.0.0/21",
"10.0.0.0/8", // private
"193.0.10.0/25", // more specific than is routed
"0.0.0.0/0", // default
"193.0.16.0/24",
],
&[PEER_ASN],
)
.await?;
assert_eq!(
table_after(&server, 2, 3).await?,
set(&["193.0.0.0/21", "193.0.16.0/24"])
);
// Paths that are refused whatever the prefix: not the peer's own,
// with a private AS in it, and one that has been through us.
announce(&mut peer, &["194.0.1.0/24"], &[174, PEER_ASN]).await?;
announce(&mut peer, &["194.0.2.0/24"], &[PEER_ASN, 64512]).await?;
announce(&mut peer, &["194.0.3.0/24"], &[PEER_ASN, LOCAL_ASN, 174]).await?;
assert_eq!(
table_after(&server, 2, 6).await?,
set(&["193.0.0.0/21", "193.0.16.0/24"])
);
Ok(())
}
/// A route that is refused takes the place of the one the peer had
/// announced before, which goes: the peer no longer has the old route,
/// and the new one is not acceptable.
#[tokio::test]
async fn test_a_refused_route_replaces_the_one_that_was_taken() -> Result<()> {
let (server, _listener) = server_with(default_policy()).await?;
let mut peer = established(&server).await?;
announce(&mut peer, &["193.0.0.0/21", "193.0.16.0/24"], &[PEER_ASN]).await?;
assert_eq!(table_after(&server, 2, 0).await?.len(), 2);
announce(&mut peer, &["193.0.0.0/21"], &[PEER_ASN, 64512]).await?;
assert_eq!(table_after(&server, 1, 1).await?, set(&["193.0.16.0/24"]));
Ok(())
}
/// A peer with a list of what it may announce is held to it: its own
/// prefixes, originated by the AS numbers given.
#[tokio::test]
async fn test_a_peer_is_held_to_its_prefix_list_and_origins() -> Result<()> {
let mut prefixes = PrefixSet::default();
prefixes.allow(prefix("193.0.0.0/21"), 24);
let (server, _listener) = server_with(ImportPolicy {
prefixes: Some(prefixes),
origin_asns: Some([PEER_ASN, 2121].into()),
..default_policy()
})
.await?;
let mut peer = established(&server).await?;
// Its own, and a more specific that the list allows.
announce(&mut peer, &["193.0.0.0/21", "193.0.4.0/24"], &[PEER_ASN]).await?;
// A customer of its that is listed as an origin.
announce(&mut peer, &["193.0.6.0/24"], &[PEER_ASN, 2121]).await?;
// Someone else's prefix, as a hijack or a leak would be.
announce(&mut peer, &["8.8.8.0/24"], &[PEER_ASN]).await?;
// Its own prefix, but passed on from an origin that is not listed.
announce(&mut peer, &["193.0.7.0/24"], &[PEER_ASN, 15169]).await?;
assert_eq!(
table_after(&server, 3, 2).await?,
set(&["193.0.0.0/21", "193.0.4.0/24", "193.0.6.0/24"])
);
Ok(())
}
/// A peer that sends more routes than it is allowed is cut off and told
/// why, and kept down for a while: neither its connections are taken nor
/// is it dialled. A session that came straight back would only fill up
/// again.
#[tokio::test]
async fn test_a_peer_over_its_limit_is_cut_off_and_kept_down() -> Result<()> {
let (server, listener) = server_with(ImportPolicy {
max_prefixes: Some(3),
hold_down: Duration::from_millis(1500),
..default_policy()
})
.await?;
// The server dials the peer as well; that connection is left unanswered
// until the end.
let dialled = tokio::time::timeout(TIMEOUT, listener.accept()).await??;
let mut peer = established(&server).await?;
// Refused routes do not count towards the limit, and replacing a
// route does not either.
announce(
&mut peer,
&["193.0.0.0/24", "193.0.1.0/24", "10.0.0.0/8"],
&[PEER_ASN],
)
.await?;
announce(&mut peer, &["193.0.1.0/24", "193.0.2.0/24"], &[PEER_ASN]).await?;
assert_eq!(table_after(&server, 3, 1).await?.len(), 3);
announce(&mut peer, &["193.0.3.0/24"], &[PEER_ASN]).await?;
let notification = tokio::time::timeout(TIMEOUT, async {
loop {
if let Message::Notification(notification) = peer.recv().await? {
return Ok::<_, eyre::Report>(notification);
}
}
})
.await??;
assert_eq!(
notification.error,
BgpError::Cease(CeaseSubcode::MaxPrefixes)
);
drop(peer);
tokio::time::timeout(TIMEOUT, async {
while !server.received_routes().is_empty() {
tokio::time::sleep(Duration::from_millis(5)).await;
}
})
.await?;
// Held down: a new connection gets nothing.
let mut early = TestPeer::connect(server.addr).await?;
assert!(
matches!(
tokio::time::timeout(TIMEOUT, early.recv()).await,
Ok(Err(_))
),
"a peer that is held down is not answered"
);
// Nor is it dialled: once the connection the server had open to it is
// gone, the dialer waits out the hold-down and says so.
drop(dialled);
let reason = tokio::time::timeout(TIMEOUT, async {
loop {
if let Some((_, DialState::Backoff { last_error, .. })) =
server.registry.configured_peers().into_iter().next()
&& last_error.contains("held down")
{
return last_error;
}
tokio::time::sleep(Duration::from_millis(10)).await;
}
})
.await?;
assert!(reason.contains("limit of routes"), "{reason}");
// When the time is up the peer is dialled again, and taken back.
tokio::time::timeout(TIMEOUT, listener.accept()).await??;
let mut later = TestPeer::connect(server.addr).await?;
later
.handshake(PEER_ASN, Ipv4Addr::new(10, 0, 0, 2), 90)
.await?;
Ok(())
}