Files
ferrix/crates/integration-tests/tests/import_policy.rs
T
Rayhaan JaufeerallyandClaude Fable 5.1 cbf0df1eef Policy scripts: the operator's own rules for routes, in Rhai
A new crate, bgp-policy, runs functions of a script on routes: on their
way in, after the general checks of a peer's import and before the
checks that can change (RPKI, next hop reachability); and on their way
out to a peer. A function is given the route and the peer, may refuse
the route, and may change its communities, large communities,
LOCAL_PREF and MED, and on the way out prepend our AS:

    fn from_peer(route, peer) {
        if route.has_community("65535:666") { return false; }
        route.add_community(LEARNED_FROM[peer.role]);
        route.local_pref = PREFERENCE[peer.role];
        true
    }

Configuration: policy { path | source, import_function, export_function }
and, for a peer, import { function } and export { function }. The script
is compiled at startup; `bgp --check` reads it and says which function
is whose. A function that fails on a route has refused it. Scripts have
no files, network or clock, and are stopped after 200,000 steps.

Route selection now goes by a LOCAL_PREF on a route from an external
peer: the decoder never lets a peer's own through, so one that is there
was set by policy.

What it costs was measured before it was built on (benches/policy.rs):
a call that tests a few communities and changes two takes 1 to 3
microseconds, some two hundred times what Rust would. So a function is
asked once for the routes of an UPDATE, which share their attributes,
unless it asks for the prefix. One peer sending 1.23 M routes over a
session: 0.37 s without a function, 0.80 s with one that marks and
ranks every route, 3.4 s if it also looks at the prefix.

Export applies to what is announced, which today is what the daemon
originates; learned routes are not passed on yet.

Tested by unit tests of the crate, sessions end to end, a fuzz target on
the example script (testdata/policy.rhai), and a lab phase in which a
script changes which of FRR's and BIRD's route is chosen and what each
of them is told.

Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
2026-10-02 21:09:39 +02:00

286 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,
import_hook: None,
export_hook: None,
}];
})
.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(())
}