Merge tag 'nf-next-24-08-23' of git://git.kernel.org/pub/scm/linux/kernel/git/netfilter/nf-next

Pablo Neira Ayuso says:

====================
Netfilter updates for net-next

The following batch contains Netfilter updates for net-next:

Patch #1 fix checksum calculation in nfnetlink_queue with SCTP,
	 segment GSO packet since skb_zerocopy() does not support
	 GSO_BY_FRAGS, from Antonio Ojea.

Patch #2 extend nfnetlink_queue coverage to handle SCTP packets,
	 from Antonio Ojea.

Patch #3 uses consume_skb() instead of kfree_skb() in nfnetlink,
         from Donald Hunter.

Patch #4 adds a dedicate commit list for sets to speed up
	 intra-transaction lookups, from Florian Westphal.

Patch #5 skips removal of element from abort path for the pipapo
         backend, ditching the shadow copy of this datastructure
	 is sufficient.

Patch #6 moves nf_ct_netns_get() out of nf_conncount_init() to
	 let users of conncoiunt decide when to enable conntrack,
	 this is needed by openvswitch, from Xin Long.

Patch #7 pass context to all nft_parse_register_load() in
	 preparation for the next patch.

Patches #8 and #9 reject loads from uninitialized registers from
	 control plane to remove register initialization from
	 datapath. From Florian Westphal.

* tag 'nf-next-24-08-23' of git://git.kernel.org/pub/scm/linux/kernel/git/netfilter/nf-next:
  netfilter: nf_tables: don't initialize registers in nft_do_chain()
  netfilter: nf_tables: allow loads only when register is initialized
  netfilter: nf_tables: pass context structure to nft_parse_register_load
  netfilter: move nf_ct_netns_get out of nf_conncount_init
  netfilter: nf_tables: do not remove elements if set backend implements .abort
  netfilter: nf_tables: store new sets in dedicated list
  netfilter: nfnetlink: convert kfree_skb to consume_skb
  selftests: netfilter: nft_queue.sh: sctp coverage
  netfilter: nfnetlink_queue: unbreak SCTP traffic
====================

Link: https://patch.msgid.link/20240822221939.157858-1-pablo@netfilter.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>

tools/testing/selftests/net/netfilter/config

@@ -87,3 +87,5 @@ CONFIG_XFRM_USER=m
 CONFIG_XFRM_STATISTICS=y
 CONFIG_NET_PKTGEN=m
 CONFIG_TUN=m
+CONFIG_INET_DIAG=m
+CONFIG_SCTP_DIAG=m

tools/testing/selftests/net/netfilter/nft_queue.sh

@@ -25,6 +25,9 @@ cleanup()
 }
 
 checktool "nft --version" "test without nft tool"
+checktool "socat -h" "run test without socat"
+
+modprobe -q sctp
 
 trap cleanup EXIT
 
@@ -265,7 +268,6 @@ test_tcp_forward()
 
 test_tcp_localhost()
 {
-	dd conv=sparse status=none if=/dev/zero bs=1M count=200 of="$TMPINPUT"
 	timeout 5 ip netns exec "$nsrouter" socat -u TCP-LISTEN:12345 STDOUT >/dev/null &
 	local rpid=$!
 
@@ -375,6 +377,82 @@ EOF
 	wait 2>/dev/null
 }
 
+sctp_listener_ready()
+{
+	ss -S -N "$1" -ln -o "sport = :12345" | grep -q 12345
+}
+
+test_sctp_forward()
+{
+	ip netns exec "$nsrouter" nft -f /dev/stdin <<EOF
+flush ruleset
+table inet sctpq {
+        chain forward {
+        type filter hook forward priority 0; policy accept;
+                sctp dport 12345 queue num 10
+        }
+}
+EOF
+	timeout 60 ip netns exec "$ns2" socat -u SCTP-LISTEN:12345 STDOUT > "$TMPFILE1" &
+	local rpid=$!
+
+	busywait "$BUSYWAIT_TIMEOUT" sctp_listener_ready "$ns2"
+
+	ip netns exec "$nsrouter" ./nf_queue -q 10 -G -t "$timeout" &
+	local nfqpid=$!
+
+	ip netns exec "$ns1" socat -u STDIN SCTP:10.0.2.99:12345 <"$TMPINPUT" >/dev/null
+
+	if ! ip netns exec "$nsrouter" nft delete table inet sctpq; then
+		echo "FAIL:  Could not delete sctpq table"
+		exit 1
+	fi
+
+	wait "$rpid" && echo "PASS: sctp and nfqueue in forward chain"
+
+	if ! diff -u "$TMPINPUT" "$TMPFILE1" ; then
+		echo "FAIL: lost packets?!" 1>&2
+		exit 1
+	fi
+}
+
+test_sctp_output()
+{
+        ip netns exec "$ns1" nft -f /dev/stdin <<EOF
+table inet sctpq {
+        chain output {
+        type filter hook output priority 0; policy accept;
+                sctp dport 12345 queue num 11
+        }
+}
+EOF
+	# reduce test file size, software segmentation causes sk wmem increase.
+	dd conv=sparse status=none if=/dev/zero bs=1M count=50 of="$TMPINPUT"
+
+	timeout 60 ip netns exec "$ns2" socat -u SCTP-LISTEN:12345 STDOUT > "$TMPFILE1" &
+	local rpid=$!
+
+	busywait "$BUSYWAIT_TIMEOUT" sctp_listener_ready "$ns2"
+
+	ip netns exec "$ns1" ./nf_queue -q 11 -t "$timeout" &
+	local nfqpid=$!
+
+	ip netns exec "$ns1" socat -u STDIN SCTP:10.0.2.99:12345 <"$TMPINPUT" >/dev/null
+
+	if ! ip netns exec "$ns1" nft delete table inet sctpq; then
+		echo "FAIL:  Could not delete sctpq table"
+		exit 1
+	fi
+
+	# must wait before checking completeness of output file.
+	wait "$rpid" && echo "PASS: sctp and nfqueue in output chain with GSO"
+
+	if ! diff -u "$TMPINPUT" "$TMPFILE1" ; then
+		echo "FAIL: lost packets?!" 1>&2
+		exit 1
+	fi
+}
+
 test_queue_removal()
 {
 	read tainted_then < /proc/sys/kernel/tainted
@@ -443,11 +521,16 @@ test_queue 10
 # same.  We queue to a second program as well.
 load_ruleset "filter2" 20
 test_queue 20
+ip netns exec "$ns1" nft flush ruleset
 
 test_tcp_forward
 test_tcp_localhost
 test_tcp_localhost_connectclose
 test_tcp_localhost_requeue
+test_sctp_forward
+test_sctp_output
+
+# should be last, adds vrf device in ns1 and changes routes
 test_icmp_vrf
 test_queue_removal