fix(deploy): relay firewall DROP must be appended, not -I-inserted above its ACCEPTs

iptables -I prepends, so the install block's final -I of the blanket DROP
landed it at position 1, above all three ACCEPTs: every packet to
18093/tcp died there (live 2026-10-21: 159 packets on the DROP, 0 on each
ACCEPT). The host's own health probe timed out beside a LISTENing socket
and the whole dankclaw drain aborted at the alertmanager gate twice.

Install now rebuilds the tail: delete any blanket DROP wherever it sits,
keep the ACCEPTs at the head, append the DROP last - converges on hosts
poisoned by the old order. New bats case runs install_signal_relay for
real against an iptables sandbox seeded with the poisoned order (red on
the old code, green on this one).
This commit is contained in:
Frank committed 2026-10-21 16:52:40 -07:00
1 parent bfe4d185bd
commit ce370a5b28
3 files changed
+83 -9

No files matched your search

+58
View File
@@ -559,6 +559,64 @@ assert any('ALERTS' in e for e in exprs), exprs
grep -q -- '--dport 18093 -j DROP' "$handler"
}
@test "the deployer installs the relay firewall with the ACCEPTs deciding before the DROP" {
# Behavioral, run for real against a sandbox that plays the kernel: the
# rule set is a LIST and iptables -I prepends, so the shape this function
# had until 2026-10-21 (-C/-I ACCEPT x3, then -C/-I the blanket DROP)
# landed the DROP at position 1 and every packet died there — the drain
# failed its health gate beside a LISTENing socket twice. Seeding the
# sandbox with that poisoned order also pins the convergent repair: a
# re-deploy must rewrite the tail, not skip because -C finds every rule.
local sandbox="$BATS_TEST_TMPDIR/fw"
mkdir -p "$sandbox/bin"
cat > "$sandbox/bin/iptables" <<'EOF'
#!/usr/bin/env bash
# ordered rule list in $FW_STATE: -C lookup, -I at head, -A at tail, -D delete.
state="${FW_STATE:?}"
touch "$state"
op="$1"; shift
case "$op" in
-C) grep -Fxq -- "$*" "$state" ;;
-I) grep -Fxq -- "$*" "$state" || { { echo "$*"; cat "$state"; } > "$state.new"; mv "$state.new" "$state"; } ;;
-A) grep -Fxq -- "$*" "$state" || echo "$*" >> "$state" ;;
-D) if grep -Fxq -- "$*" "$state"; then
grep -Fxv -- "$*" "$state" > "$state.new"; mv "$state.new" "$state"
else exit 1; fi ;;
*) exit 0 ;;
esac
EOF
chmod +x "$sandbox/bin/iptables"
# Poisoned state exactly as the pre-fix deployer left Dankclaw.
printf '%s\n' \
'INPUT -p tcp --dport 18093 -j DROP' \
'INPUT -p tcp --dport 18093 -s 10.89.0.0/16 -j ACCEPT' \
'INPUT -p tcp --dport 18093 -s 192.168.0.143 -j ACCEPT' \
'INPUT -p tcp --dport 18093 -s 127.0.0.1 -j ACCEPT' \
> "$sandbox/rules"
(
cd "$REPO_ROOT"
export PATH="$sandbox/bin:$PATH" FW_STATE="$sandbox/rules" HOME="$sandbox/home"
mkdir -p "$HOME"
eval "$(sed -n '/^install_signal_relay()/,/^}/p' scripts/deploy-remote.sh)"
run_privileged() { "$@"; }
systemctl() { :; }
curl() { return 0; }
sleep() { :; }
install_signal_relay
)
# Exactly one blanket DROP, and it sits after every ACCEPT.
[ "$(grep -cF -- 'INPUT -p tcp --dport 18093 -j DROP' "$sandbox/rules")" -eq 1 ]
local drop_at total
drop_at="$(grep -nF -- 'INPUT -p tcp --dport 18093 -j DROP' "$sandbox/rules" | cut -d: -f1)"
total="$(wc -l < "$sandbox/rules")"
[ "$drop_at" -eq "$total" ]
local s seen
for s in 127.0.0.1 192.168.0.143 10.89.0.0/16; do
seen="$(grep -nF -- "-s $s -j ACCEPT" "$sandbox/rules" | cut -d: -f1)"
[ -n "$seen" ] && [ "$seen" -lt "$drop_at" ]
done
}
@test "the planner selects alertmanager for its config and relay files" {
run python3 "$REPO_ROOT/scripts/deploy-plan.py" --target dankclaw \
--paths shared/prometheus/alertmanager.yml