Merge tag 'net-5.16-rc3' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net

Pull networking fixes from Jakub Kicinski:
 "Networking fixes, including fixes from netfilter.

  Current release - regressions:

   - r8169: fix incorrect mac address assignment

   - vlan: fix underflow for the real_dev refcnt when vlan creation
     fails

   - smc: avoid warning of possible recursive locking

  Current release - new code bugs:

   - vsock/virtio: suppress used length validation

   - neigh: fix crash in v6 module initialization error path

  Previous releases - regressions:

   - af_unix: fix change in behavior in read after shutdown

   - igb: fix netpoll exit with traffic, avoid warning

   - tls: fix splice_read() when starting mid-record

   - lan743x: fix deadlock in lan743x_phy_link_status_change()

   - marvell: prestera: fix bridge port operation

  Previous releases - always broken:

   - tcp_cubic: fix spurious Hystart ACK train detections for
     not-cwnd-limited flows

   - nexthop: fix refcount issues when replacing IPv6 groups

   - nexthop: fix null pointer dereference when IPv6 is not enabled

   - phylink: force link down and retrigger resolve on interface change

   - mptcp: fix delack timer length calculation and incorrect early
     clearing

   - ieee802154: handle iftypes as u32, prevent shift-out-of-bounds

   - nfc: virtual_ncidev: change default device permissions

   - netfilter: ctnetlink: fix error codes and flags used for kernel
     side filtering of dumps

   - netfilter: flowtable: fix IPv6 tunnel addr match

   - ncsi: align payload to 32-bit to fix dropped packets

   - iavf: fix deadlock and loss of config during VF interface reset

   - ice: avoid bpf_prog refcount underflow

   - ocelot: fix broken PTP over IP and PTP API violations

  Misc:

   - marvell: mvpp2: increase MTU limit when XDP enabled"

* tag 'net-5.16-rc3' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net: (94 commits)
  net: dsa: microchip: implement multi-bridge support
  net: mscc: ocelot: correctly report the timestamping RX filters in ethtool
  net: mscc: ocelot: set up traps for PTP packets
  net: ptp: add a definition for the UDP port for IEEE 1588 general messages
  net: mscc: ocelot: create a function that replaces an existing VCAP filter
  net: mscc: ocelot: don't downgrade timestamping RX filters in SIOCSHWTSTAMP
  net: hns3: fix incorrect components info of ethtool --reset command
  net: hns3: fix one incorrect value of page pool info when queried by debugfs
  net: hns3: add check NULL address for page pool
  net: hns3: fix VF RSS failed problem after PF enable multi-TCs
  net: qed: fix the array may be out of bound
  net/smc: Don't call clcsock shutdown twice when smc shutdown
  net: vlan: fix underflow for the real_dev refcnt
  ptp: fix filter names in the documentation
  ethtool: ioctl: fix potential NULL deref in ethtool_set_coalesce()
  nfc: virtual_ncidev: change default device permissions
  net/sched: sch_ets: don't peek at classes beyond 'nbands'
  net: stmmac: Disable Tx queues when reconfiguring the interface
  selftests: tls: test for correct proto_ops
  tls: fix replacing proto_ops
  ...

1 files changed, 219 insertions, 0 deletions

diff --git a/tools/testing/selftests/netfilter/conntrack_vrf.sh b/tools/testing/selftests/netfilter/conntrack_vrf.sh
new file mode 100755
index 000000000000..91f3ef0f1192
--- /dev/null
+++ b/tools/testing/selftests/netfilter/conntrack_vrf.sh
@@ -0,0 +1,219 @@
+#!/bin/sh
+
+# This script demonstrates interaction of conntrack and vrf.
+# The vrf driver calls the netfilter hooks again, with oif/iif
+# pointing at the VRF device.
+#
+# For ingress, this means first iteration has iifname of lower/real
+# device.  In this script, thats veth0.
+# Second iteration is iifname set to vrf device, tvrf in this script.
+#
+# For egress, this is reversed: first iteration has the vrf device,
+# second iteration is done with the lower/real/veth0 device.
+#
+# test_ct_zone_in demonstrates unexpected change of nftables
+# behavior # caused by commit 09e856d54bda5f28 "vrf: Reset skb conntrack
+# connection on VRF rcv"
+#
+# It was possible to assign conntrack zone to a packet (or mark it for
+# `notracking`) in the prerouting chain before conntrack, based on real iif.
+#
+# After the change, the zone assignment is lost and the zone is assigned based
+# on the VRF master interface (in case such a rule exists).
+# assignment is lost. Instead, assignment based on the `iif` matching
+# Thus it is impossible to distinguish packets based on the original
+# interface.
+#
+# test_masquerade_vrf and test_masquerade_veth0 demonstrate the problem
+# that was supposed to be fixed by the commit mentioned above to make sure
+# that any fix to test case 1 won't break masquerade again.
+
+ksft_skip=4
+
+IP0=172.30.30.1
+IP1=172.30.30.2
+PFXL=30
+ret=0
+
+sfx=$(mktemp -u "XXXXXXXX")
+ns0="ns0-$sfx"
+ns1="ns1-$sfx"
+
+cleanup()
+{
+	ip netns pids $ns0 | xargs kill 2>/dev/null
+	ip netns pids $ns1 | xargs kill 2>/dev/null
+
+	ip netns del $ns0 $ns1
+}
+
+nft --version > /dev/null 2>&1
+if [ $? -ne 0 ];then
+	echo "SKIP: Could not run test without nft tool"
+	exit $ksft_skip
+fi
+
+ip -Version > /dev/null 2>&1
+if [ $? -ne 0 ];then
+	echo "SKIP: Could not run test without ip tool"
+	exit $ksft_skip
+fi
+
+ip netns add "$ns0"
+if [ $? -ne 0 ];then
+	echo "SKIP: Could not create net namespace $ns0"
+	exit $ksft_skip
+fi
+ip netns add "$ns1"
+
+trap cleanup EXIT
+
+ip netns exec $ns0 sysctl -q -w net.ipv4.conf.default.rp_filter=0
+ip netns exec $ns0 sysctl -q -w net.ipv4.conf.all.rp_filter=0
+ip netns exec $ns0 sysctl -q -w net.ipv4.conf.all.rp_filter=0
+
+ip link add veth0 netns "$ns0" type veth peer name veth0 netns "$ns1" > /dev/null 2>&1
+if [ $? -ne 0 ];then
+	echo "SKIP: Could not add veth device"
+	exit $ksft_skip
+fi
+
+ip -net $ns0 li add tvrf type vrf table 9876
+if [ $? -ne 0 ];then
+	echo "SKIP: Could not add vrf device"
+	exit $ksft_skip
+fi
+
+ip -net $ns0 li set lo up
+
+ip -net $ns0 li set veth0 master tvrf
+ip -net $ns0 li set tvrf up
+ip -net $ns0 li set veth0 up
+ip -net $ns1 li set veth0 up
+
+ip -net $ns0 addr add $IP0/$PFXL dev veth0
+ip -net $ns1 addr add $IP1/$PFXL dev veth0
+
+ip netns exec $ns1 iperf3 -s > /dev/null 2>&1&
+if [ $? -ne 0 ];then
+	echo "SKIP: Could not start iperf3"
+	exit $ksft_skip
+fi
+
+# test vrf ingress handling.
+# The incoming connection should be placed in conntrack zone 1,
+# as decided by the first iteration of the ruleset.
+test_ct_zone_in()
+{
+ip netns exec $ns0 nft -f - <<EOF
+table testct {
+	chain rawpre {
+		type filter hook prerouting priority raw;
+
+		iif { veth0, tvrf } counter meta nftrace set 1
+		iif veth0 counter ct zone set 1 counter return
+		iif tvrf counter ct zone set 2 counter return
+		ip protocol icmp counter
+		notrack counter
+	}
+
+	chain rawout {
+		type filter hook output priority raw;
+
+		oif veth0 counter ct zone set 1 counter return
+		oif tvrf counter ct zone set 2 counter return
+		notrack counter
+	}
+}
+EOF
+	ip netns exec $ns1 ping -W 1 -c 1 -I veth0 $IP0 > /dev/null
+
+	# should be in zone 1, not zone 2
+	count=$(ip netns exec $ns0 conntrack -L -s $IP1 -d $IP0 -p icmp --zone 1 2>/dev/null | wc -l)
+	if [ $count -eq 1 ]; then
+		echo "PASS: entry found in conntrack zone 1"
+	else
+		echo "FAIL: entry not found in conntrack zone 1"
+		count=$(ip netns exec $ns0 conntrack -L -s $IP1 -d $IP0 -p icmp --zone 2 2> /dev/null | wc -l)
+		if [ $count -eq 1 ]; then
+			echo "FAIL: entry found in zone 2 instead"
+		else
+			echo "FAIL: entry not in zone 1 or 2, dumping table"
+			ip netns exec $ns0 conntrack -L
+			ip netns exec $ns0 nft list ruleset
+		fi
+	fi
+}
+
+# add masq rule that gets evaluated w. outif set to vrf device.
+# This tests the first iteration of the packet through conntrack,
+# oifname is the vrf device.
+test_masquerade_vrf()
+{
+	ip netns exec $ns0 conntrack -F 2>/dev/null
+
+ip netns exec $ns0 nft -f - <<EOF
+flush ruleset
+table ip nat {
+	chain postrouting {
+		type nat hook postrouting priority 0;
+		# NB: masquerade should always be combined with 'oif(name) bla',
+		# lack of this is intentional here, we want to exercise double-snat.
+		ip saddr 172.30.30.0/30 counter masquerade random
+	}
+}
+EOF
+	ip netns exec $ns0 ip vrf exec tvrf iperf3 -t 1 -c $IP1 >/dev/null
+	if [ $? -ne 0 ]; then
+		echo "FAIL: iperf3 connect failure with masquerade + sport rewrite on vrf device"
+		ret=1
+		return
+	fi
+
+	# must also check that nat table was evaluated on second (lower device) iteration.
+	ip netns exec $ns0 nft list table ip nat |grep -q 'counter packets 2'
+	if [ $? -eq 0 ]; then
+		echo "PASS: iperf3 connect with masquerade + sport rewrite on vrf device"
+	else
+		echo "FAIL: vrf masq rule has unexpected counter value"
+		ret=1
+	fi
+}
+
+# add masq rule that gets evaluated w. outif set to veth device.
+# This tests the 2nd iteration of the packet through conntrack,
+# oifname is the lower device (veth0 in this case).
+test_masquerade_veth()
+{
+	ip netns exec $ns0 conntrack -F 2>/dev/null
+ip netns exec $ns0 nft -f - <<EOF
+flush ruleset
+table ip nat {
+	chain postrouting {
+		type nat hook postrouting priority 0;
+		meta oif veth0 ip saddr 172.30.30.0/30 counter masquerade random
+	}
+}
+EOF
+	ip netns exec $ns0 ip vrf exec tvrf iperf3 -t 1 -c $IP1 > /dev/null
+	if [ $? -ne 0 ]; then
+		echo "FAIL: iperf3 connect failure with masquerade + sport rewrite on veth device"
+		ret=1
+		return
+	fi
+
+	# must also check that nat table was evaluated on second (lower device) iteration.
+	ip netns exec $ns0 nft list table ip nat |grep -q 'counter packets 2'
+	if [ $? -eq 0 ]; then
+		echo "PASS: iperf3 connect with masquerade + sport rewrite on veth device"
+	else
+		echo "FAIL: vrf masq rule has unexpected counter value"
+		ret=1
+	fi
+}
+
+test_ct_zone_in
+test_masquerade_vrf
+test_masquerade_veth
+
+exit $ret