branch: externals/nftables-mode
commit 94f54f52ec3b19bcb422ee932cc54554d4d65c0a
Author: Trent W. Buck <trentb...@gmail.com>
Commit: Trent W. Buck <trentb...@gmail.com>
reference nftables ruleset
based on the one that was in KB but now slightly different because sigh
---
nftables-host.nft | 158 ++++++++++++++++++++++++++++++++++++++++++++++++++++++
1 file changed, 158 insertions(+)
diff --git a/nftables-host.nft b/nftables-host.nft
new file mode 100644
index 0000000000..ceaa658e62
--- /dev/null
+++ b/nftables-host.nft
@@ -0,0 +1,158 @@
+#!/usr/sbin/nft --file
+# -*- mode: conf; mode: nftables; conf-space-keywords:
"table\\|chain\\|type\\|policy\\|accept\\|drop\\|counter\\|jump"; -*-
+
+#### This -*-nftables-*- ruleset is my /etc/nftables.conf for new hosts.
+#### Ref. http://jengelh.medozas.de/documents/Perfect_Ruleset.pdf
+#### Ref. https://wiki.nftables.org/
+####
+#### GOTCHA: This is written for nft 0.9.1.
+#### Several options have changed, even since 0.9.0!
+####
+#### GOTCHA: "nft --file" does not flush by default.
+#### That is, it acts like "iptables-restore --noflush".
+####
+#### GOTCHA: If your ruleset does "flush; add; flush; add",
+#### it will actually do "flush; flush; add; add".
+#### That is, all the flushes move to the top.
+####
+#### This makes it impossible to do my old trick of
+#### having the ruleset start with a "deny all" policy,
+#### which was useful to make sure that if the firewall failed,
+#### the OS would lock down the whole system.
+#### (See "iptab" for notes about that.)
+####
+#### To achieve that under nft, you instead need to patch
+#### nftables.service to have
+#### OnFailure=nftables-denyall.service, and then write that
+#### unit to load a SEPARATE, DIFFERENT nftables file that
+#### blocks everything. And even then, it won't behave quite
+#### the same.
+####
+#### This also means it is no longer safe to refer to
+#### hostnames in this ruleset, safe in the knowledge that
+#### they can only be resolved via local /etc/hosts. Because
+#### the "deny all" ruleset can't be prepended here, we CANNOT
+#### be sure the real ruleset will only resolve hostnames via
+#### local sources -- so you might add ones that are only in
+#### DNS, and then have the firewall fail to load during early
+#### boot -- leaving you with a "working" host, with no
+#### firewall!
+####
+#### GOTCHA: "list ruleset" here will print the ruleset BEFORE it goes through
the kernel;
+#### "nft list ruleset" later will print the ruleset AFTER it goes
through the kernel.
+#### The difference is usually like "iptables -p tcp" getting an
implied "-m tcp".
+#### However, differences MIGHT indicate a bug! Watch out!
+####
+#### GOTCHA: "table filter" and "chain INPUT" or "chain input" just
+#### conventions and have NO MEANING WHATSOEVER. The actual
+#### meaning comes from the "type filter hook input priority
+#### filter" line.
+####
+#### NOTE: Only create a chain if you use it.
+#### An empty chain is slightly slower than no chain at all.
+#### e.g. most hosts don't need an output chain.
+####
+#### NOTE: iptables ALWAYS counts how many packets/bytes hit every chain and
rule.
+#### nftables makes this OPT IN, e.g. change "accept" to "counter
accept".
+#### iptables-save -c would print "[pkts:bytes] -A ...".
+#### nftables list rulset will print "... counter packgets 12 bytes 34
...".
+####
+#### Since counters are useful during debugging but not production,
+#### I have left them out of this example.
+####
+#### NOTE: "table x" is implicitly "table ip x", which is IPv4 only.
+#### If you want dual-stack, say "table inet x".
+####
+#### NOTE: "iif lo" is resolved at ruleset load time into an interface
+#### NUMBER inside the kernel; whereas "iifname lo" remains a
+#### string. This means that:
+####
+#### * "iifname" is ~10 times slower than "iif" for every
+#### packet considered (strcmp versus ==).
+####
+#### * If you load a ruleset with "iif foo" before foo exists,
+#### the load will fail, LEAVING YOU UNPROTECTED!
+####
+#### * If you load a ruleset with "iif foo" and then foo is
+#### removed and readded (e.g. ppp0 for a flaky ADSL link),
+#### what happens?
+####
+#### * Rule of thumb: always use "iifname" (not "iif").
+
+
+# NOTE: this will remove *ALL* tables --- including tables set up by
+# other things (e.g. sshguard)!
+#
+# In theory you can flush just your own rules, e.g.
+#
+# flush table inet my_filter
+#
+# FIXME: I tried that, and I got locked out of SSH!
+# What it did was remove all the rules, but NOT the chains, so
+# the default-deny policy dropped EVERYTHING!!!
+## NOTE: we add+delete each table (not "flush ruleset"), because
+## otherwise we would wipe out sshguard table.
+#flush ruleset
+add table inet my_filter # idempotent
+delete table inet my_filter # not idempotent
+
+
+table inet my_filter {
+ chain my_input {
+ type filter hook input priority filter
+ policy drop
+ # Typically 99%+ of packets are part of an already-established flow.
+ # Allow those first, so we're a fast, stateful firewall.
+ # After this only "ct state new" (or "ct state untracked") will remain.
+ # FIXME: is a vmap here better (more efficient) than two separate
rules?
+ # NOTE: {established or related: accept} does not match correctly!
+ ct state vmap { established: accept, related: accept, invalid: drop }
+
+ # Loopback traffic is needed for e.g. NFS RPC, and for debugging.
+ iiftype loopback accept
+
+ # Allow *some* kinds of IPv4/ICMP and IPv6/ICMPv6.
+ icmp type echo-request accept
+ icmpv6 type { echo-request, nd-neighbor-solicit, nd-router-advert,
nd-neighbor-advert } accept
+
+ # YOUR RULES HERE.
+ # NOTE: service names resolve via nss (/etc/hosts) only in nft 0.9.1+!
+ ##FOR "router" EXAMPLE### NOTE: a single rule CAN match "allow 53/tcp
and 53/udp", but it's UGLY, so we don't.
+ ##FOR "router" EXAMPLE### NOTE: I assume you used systemd (networkd or
udev) to rename "enp0s0f0" to "lan".
+ ##FOR "router" EXAMPLE### NOTE: "iif foo" must exist at ruleset load
time.
+ ##FOR "router" EXAMPLE### If your ruleset starts BEFORE udev
and/or systemd-networkd are READY=1,
+ ##FOR "router" EXAMPLE### consider using 'iifname lan' instead
of "iif lan".
+ tcp dport ssh accept
+ tcp dport { http, https } accept
+ ##FOR "router" EXAMPLE##iif enp11s0 tcp dport domain accept
+ ##FOR "router" EXAMPLE##iif enp11s0 udp dport { domain, ntp, bootps }
accept
+
+ # Finally, politely reject all other attempts.
+ # Omit to use the default policy ("policy drop", above) instead.
+ reject
+ }
+
+ # A host can't route unless you explicitly enable it, e.g.:
+ #
+ # sysctl net/ipv4/ip_forward=1
+ # sysctl net/ipv6/conf/all/forwarding=1
+ #
+ # We create a "deny all" inet filter forward chain anyway, as
+ # defense-in-depth against someone enabling routing ACCIDENTALLY.
+ chain my_forward {
+ type filter hook forward priority filter
+ policy drop
+ }
+
+ # We want output to be "allow all", so we don't even create a chain.
+ #chain my_output {
+ # type filter hook output priority filter
+ # policy accept
+ #}
+
+}
+
+# This is here to aid debugging.
+# Note that its output WILL NOT MATCH a later "nft list rulset".
+# Also, it is buggy, e.g. the ICMPv6_RFC4890_policy it prints has gibberish in
v0.9.1.
+list ruleset
