Merge tag 'nf-next-26-02-06' of https://git.kernel.org/pub/scm/linux/kernel/git/netfilter/nf-next

Florian Westphal says:

====================
netfilter: updates for net-next

The following patchset contains Netfilter updates for *net-next*:

1) Fix net-next-only use-after-free bug in nf_tables rbtree set:
   Expired elements cannot be released right away after unlink anymore
   because there is no guarantee that the binary-search blob is going to
   be updated.  Spotted by syzkaller.

2) Fix esoteric bug in nf_queue with udp fraglist gro, broken since
   6.11. Patch 3 adds extends the nfqueue selftest for this.

4) Use dedicated slab for flowtable entries, currently the -512 cache
   is used, which is wasteful.  From Qingfang Deng.

5) Recent net-next update extended existing test for ip6ip6 tunnels, add
   the required /config entry.  Test still passed by accident because the
   previous tests network setup gets re-used, so also update the test so
   it will fail in case the ip6ip6 tunnel interface cannot be added.

6) Fix 'nft get element mytable myset { 1.2.3.4 }' on big endian
   platforms, this was broken since code was added in v5.1.

7) Fix nf_tables counter reset support on 32bit platforms, where counter
   reset may cause huge values to appear due to wraparound.
   Broken since reset feature was added in v6.11.  From Anders Grahn.

8-11) update nf_tables rbtree set type to detect partial
   operlaps.  This will eventually speed up nftables userspace: at this
   time userspace does a netlink dump of the set content which slows down
   incremental updates on interval sets.  From Pablo Neira Ayuso.

* tag 'nf-next-26-02-06' of https://git.kernel.org/pub/scm/linux/kernel/git/netfilter/nf-next:
  netfilter: nft_set_rbtree: validate open interval overlap
  netfilter: nft_set_rbtree: validate element belonging to interval
  netfilter: nft_set_rbtree: check for partial overlaps in anonymous sets
  netfilter: nft_set_rbtree: fix bogus EEXIST with NLM_F_CREATE with null interval
  netfilter: nft_counter: fix reset of counters on 32bit archs
  netfilter: nft_set_hash: fix get operation on big endian
  selftests: netfilter: add IPV6_TUNNEL to config
  netfilter: flowtable: dedicated slab for flow entry
  selftests: netfilter: nft_queue.sh: add udp fraglist gro test case
  netfilter: nfnetlink_queue: do shared-unconfirmed check before segmentation
  netfilter: nft_set_rbtree: don't gc elements on insert
====================

Link: https://patch.msgid.link/20260206153048.17570-1-fw@strlen.de
Signed-off-by: Jakub Kicinski <kuba@kernel.org>

3 files changed, 150 insertions, 12 deletions

diff --git a/tools/testing/selftests/net/netfilter/config b/tools/testing/selftests/net/netfilter/config
index 12ce61fa15a8..979cff56e1f5 100644
--- a/tools/testing/selftests/net/netfilter/config
+++ b/tools/testing/selftests/net/netfilter/config
@@ -29,6 +29,7 @@ CONFIG_IP_NF_RAW=m
 CONFIG_IP_SCTP=m
 CONFIG_IPV6=y
 CONFIG_IPV6_MULTIPLE_TABLES=y
+CONFIG_IPV6_TUNNEL=m
 CONFIG_IP_VS=m
 CONFIG_IP_VS_PROTO_TCP=y
 CONFIG_IP_VS_RR=m
diff --git a/tools/testing/selftests/net/netfilter/nft_flowtable.sh b/tools/testing/selftests/net/netfilter/nft_flowtable.sh
index 14d7f67715ed..7a34ef468975 100755
--- a/tools/testing/selftests/net/netfilter/nft_flowtable.sh
+++ b/tools/testing/selftests/net/netfilter/nft_flowtable.sh
@@ -601,14 +601,19 @@ ip -net "$nsr2" link set tun0 up
 ip -net "$nsr2" addr add 192.168.100.2/24 dev tun0
 ip netns exec "$nsr2" sysctl net.ipv4.conf.tun0.forwarding=1 > /dev/null
 
-ip -net "$nsr2" link add name tun6 type ip6tnl local fee1:2::2 remote fee1:2::1
+ip -net "$nsr2" link add name tun6 type ip6tnl local fee1:2::2 remote fee1:2::1 || ret=1
 ip -net "$nsr2" link set tun6 up
 ip -net "$nsr2" addr add fee1:3::2/64 dev tun6 nodad
 
 ip -net "$nsr1" route change default via 192.168.100.2
 ip -net "$nsr2" route change default via 192.168.100.1
-ip -6 -net "$nsr1" route change default via fee1:3::2
-ip -6 -net "$nsr2" route change default via fee1:3::1
+
+# do not use "route change" and delete old default so
+# socat fails to connect in case new default can't be added.
+ip -6 -net "$nsr1" route delete default
+ip -6 -net "$nsr1" route add default via fee1:3::2
+ip -6 -net "$nsr2" route delete default
+ip -6 -net "$nsr2" route add default via fee1:3::1
 ip -net "$ns2" route add default via 10.0.2.1
 ip -6 -net "$ns2" route add default via dead:2::1
 
@@ -649,7 +654,8 @@ ip netns exec "$nsr1" nft -a insert rule inet filter forward 'meta oif tun0.10 a
 ip -net "$nsr1" link add name tun6.10 type ip6tnl local fee1:4::1 remote fee1:4::2
 ip -net "$nsr1" link set tun6.10 up
 ip -net "$nsr1" addr add fee1:5::1/64 dev tun6.10 nodad
-ip -6 -net "$nsr1" route change default via fee1:5::2
+ip -6 -net "$nsr1" route delete default
+ip -6 -net "$nsr1" route add default via fee1:5::2
 ip netns exec "$nsr1" nft -a insert rule inet filter forward 'meta oif tun6.10 accept'
 
 ip -net "$nsr2" link add link veth0 name veth0.10 type vlan id 10
@@ -664,10 +670,11 @@ ip -net "$nsr2" addr add 192.168.200.2/24 dev tun0.10
 ip -net "$nsr2" route change default via 192.168.200.1
 ip netns exec "$nsr2" sysctl net.ipv4.conf.tun0/10.forwarding=1 > /dev/null
 
-ip -net "$nsr2" link add name tun6.10 type ip6tnl local fee1:4::2 remote fee1:4::1
+ip -net "$nsr2" link add name tun6.10 type ip6tnl local fee1:4::2 remote fee1:4::1 || ret=1
 ip -net "$nsr2" link set tun6.10 up
 ip -net "$nsr2" addr add fee1:5::2/64 dev tun6.10 nodad
-ip -6 -net "$nsr2" route change default via fee1:5::1
+ip -6 -net "$nsr2" route delete default
+ip -6 -net "$nsr2" route add default via fee1:5::1
 
 if ! test_tcp_forwarding_nat "$ns1" "$ns2" 1 "IPIP tunnel over vlan"; then
 	echo "FAIL: flow offload for ns1/ns2 with IPIP tunnel over vlan" 1>&2
diff --git a/tools/testing/selftests/net/netfilter/nft_queue.sh b/tools/testing/selftests/net/netfilter/nft_queue.sh
index 6136ceec45e0..139bc1211878 100755
--- a/tools/testing/selftests/net/netfilter/nft_queue.sh
+++ b/tools/testing/selftests/net/netfilter/nft_queue.sh
@@ -510,7 +510,7 @@ EOF
 
 udp_listener_ready()
 {
-	ss -S -N "$1" -uln -o "sport = :12345" | grep -q 12345
+	ss -S -N "$1" -uln -o "sport = :$2" | grep -q "$2"
 }
 
 output_files_written()
@@ -518,7 +518,7 @@ output_files_written()
 	test -s "$1" && test -s "$2"
 }
 
-test_udp_ct_race()
+test_udp_nat_race()
 {
         ip netns exec "$nsrouter" nft -f /dev/stdin <<EOF
 flush ruleset
@@ -545,8 +545,8 @@ EOF
 	ip netns exec "$nsrouter" ./nf_queue -q 12 -d 1000 &
 	local nfqpid=$!
 
-	busywait "$BUSYWAIT_TIMEOUT" udp_listener_ready "$ns2"
-	busywait "$BUSYWAIT_TIMEOUT" udp_listener_ready "$ns3"
+	busywait "$BUSYWAIT_TIMEOUT" udp_listener_ready "$ns2" 12345
+	busywait "$BUSYWAIT_TIMEOUT" udp_listener_ready "$ns3" 12345
 	busywait "$BUSYWAIT_TIMEOUT" nf_queue_wait "$nsrouter" 12
 
 	# Send two packets, one should end up in ns1, other in ns2.
@@ -557,7 +557,7 @@ EOF
 
 	busywait 10000 output_files_written "$TMPFILE1" "$TMPFILE2"
 
-	kill "$nfqpid"
+	kill "$nfqpid" "$rpid1" "$rpid2"
 
 	if ! ip netns exec "$nsrouter" bash -c 'conntrack -L -p udp --dport 12345 2>/dev/null | wc -l | grep -q "^1"'; then
 		echo "FAIL: Expected One udp conntrack entry"
@@ -585,6 +585,135 @@ EOF
 	echo "PASS: both udp receivers got one packet each"
 }
 
+# Make sure UDPGRO aggregated packets don't lose
+# their skb->nfct entry when nfqueue passes the
+# skb to userspace with software gso segmentation on.
+test_udp_gro_ct()
+{
+	local errprefix="FAIL: test_udp_gro_ct:"
+
+	ip netns exec "$nsrouter" conntrack -F 2>/dev/null
+
+        ip netns exec "$nsrouter" nft -f /dev/stdin <<EOF
+flush ruleset
+table inet udpq {
+	# Number of packets/bytes queued to userspace
+	counter toqueue { }
+	# Number of packets/bytes reinjected from userspace with 'ct new' intact
+	counter fromqueue { }
+	# These two counters should be identical and not 0.
+
+	chain prerouting {
+		type filter hook prerouting priority -300; policy accept;
+
+		# userspace sends small packets, if < 1000, UDPGRO did
+		# not kick in, but test needs a 'new' conntrack with udpgro skb.
+		meta iifname veth0 meta l4proto udp meta length > 1000 accept
+
+		# don't pick up non-gso packets and don't queue them to
+		# userspace.
+		notrack
+	}
+
+        chain postrouting {
+		type filter hook postrouting priority 0; policy accept;
+
+		# Only queue unconfirmed fraglist gro skbs to userspace.
+		udp dport 12346 ct status ! confirmed counter name "toqueue" mark set 1 queue num 1
+        }
+
+	chain validate {
+		type filter hook postrouting priority 1; policy accept;
+		# ... and only count those that were reinjected with the
+		# skb->nfct intact.
+		mark 1 counter name "fromqueue"
+	}
+}
+EOF
+	timeout 10 ip netns exec "$ns2" socat UDP-LISTEN:12346,fork,pf=ipv4 OPEN:"$TMPFILE1",trunc &
+	local rpid=$!
+
+	ip netns exec "$nsrouter" ./nf_queue -G -c -q 1 -t 2 > "$TMPFILE2" &
+	local nfqpid=$!
+
+	ip netns exec "$nsrouter" ethtool -K "veth0" rx-udp-gro-forwarding on rx-gro-list on generic-receive-offload on
+
+	busywait "$BUSYWAIT_TIMEOUT" udp_listener_ready "$ns2" 12346
+	busywait "$BUSYWAIT_TIMEOUT" nf_queue_wait "$nsrouter" 1
+
+	local bs=512
+	local count=$(((32 * 1024 * 1024) / bs))
+	dd if=/dev/zero bs="$bs" count="$count" 2>/dev/null | for i in $(seq 1 16); do
+		timeout 5 ip netns exec "$ns1" \
+			socat -u -b 512 STDIN UDP-DATAGRAM:10.0.2.99:12346,reuseport,bind=0.0.0.0:55221 &
+	done
+
+	busywait 10000 test -s "$TMPFILE1"
+
+	kill "$rpid"
+
+	wait
+
+	local p
+	local b
+	local pqueued
+	local bqueued
+
+	c=$(ip netns exec "$nsrouter" nft list counter inet udpq "toqueue" | grep packets)
+	read p pqueued b bqueued <<EOF
+$c
+EOF
+	local preinject
+	local breinject
+	c=$(ip netns exec "$nsrouter" nft list counter inet udpq "fromqueue" | grep packets)
+	read p preinject b breinject <<EOF
+$c
+EOF
+	ip netns exec "$nsrouter" ethtool -K "veth0" rx-udp-gro-forwarding off
+	ip netns exec "$nsrouter" ethtool -K "veth1" rx-udp-gro-forwarding off
+
+	if [ "$pqueued" -eq 0 ];then
+		# happens when gro did not build at least on aggregate
+		echo "SKIP: No packets were queued"
+		return
+	fi
+
+	local saw_ct_entry=0
+	if ip netns exec "$nsrouter" bash -c 'conntrack -L -p udp --dport 12346 2>/dev/null | wc -l | grep -q "^1"'; then
+		saw_ct_entry=1
+	else
+		echo "$errprefix Expected udp conntrack entry"
+		ip netns exec "$nsrouter" conntrack -L
+		ret=1
+	fi
+
+	if [ "$pqueued" -ge "$preinject" ] ;then
+		echo "$errprefix Expected software segmentation to occur, had $pqueued and $preinject"
+		ret=1
+		return
+	fi
+
+	# sw segmentation adds extra udp and ip headers.
+	local breinject_expect=$((preinject * (512 + 20 + 8)))
+
+	if [ "$breinject" -eq "$breinject_expect" ]; then
+		if [ "$saw_ct_entry" -eq 1 ];then
+			echo "PASS: fraglist gro skb passed with conntrack entry"
+		else
+			echo "$errprefix fraglist gro skb passed without conntrack entry"
+			ret=1
+		fi
+	else
+		echo "$errprefix Counter mismatch, conntrack entry dropped by nfqueue? Queued: $pqueued, $bqueued. Post-queue: $preinject, $breinject. Expected $breinject_expect"
+		ret=1
+	fi
+
+	if ! ip netns exec "$nsrouter" nft delete table inet udpq; then
+		echo "$errprefix: Could not delete udpq table"
+		ret=1
+	fi
+}
+
 test_queue_removal()
 {
 	read tainted_then < /proc/sys/kernel/tainted
@@ -663,7 +792,8 @@ test_tcp_localhost_connectclose
 test_tcp_localhost_requeue
 test_sctp_forward
 test_sctp_output
-test_udp_ct_race
+test_udp_nat_race
+test_udp_gro_ct
 
 # should be last, adds vrf device in ns1 and changes routes
 test_icmp_vrf