Merge tag 'net-6.1-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net

Pull networking fixes from Jakub Kicinski:
 "Including fixes from netfilter, and wifi.

Current release - regressions:

   - Revert "net/sched: taprio: make qdisc_leaf() see the
     per-netdev-queue pfifo child qdiscs", it may cause crashes when the
     qdisc is reconfigured

   - inet: ping: fix splat due to packet allocation refactoring in inet

   - tcp: clean up kernel listener's reqsk in inet_twsk_purge(), fix UAF
     due to races when per-netns hash table is used

  Current release - new code bugs:

   - eth: adin1110: check in netdev_event that netdev belongs to driver

   - fixes for PTR_ERR() vs NULL bugs in driver code, from Dan and co.

  Previous releases - regressions:

   - ipv4: handle attempt to delete multipath route when fib_info
     contains an nh reference, avoid oob access

   - wifi: fix handful of bugs in the new Multi-BSSID code

   - wifi: mt76: fix rate reporting / throughput regression on mt7915
     and newer, fix checksum offload

   - wifi: iwlwifi: mvm: fix double list_add at
     iwl_mvm_mac_wake_tx_queue (other cases)

   - wifi: mac80211: do not drop packets smaller than the LLC-SNAP
     header on fast-rx

  Previous releases - always broken:

   - ieee802154: don't warn zero-sized raw_sendmsg()

   - ipv6: ping: fix wrong checksum for large frames

   - mctp: prevent double key removal and unref

   - tcp/udp: fix memory leaks and races around IPV6_ADDRFORM

   - hv_netvsc: fix race between VF offering and VF association message

  Misc:

   - remove -Warray-bounds silencing in the drivers, compilers fixed"

* tag 'net-6.1-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net: (73 commits)
  sunhme: fix an IS_ERR() vs NULL check in probe
  net: marvell: prestera: fix a couple NULL vs IS_ERR() checks
  kcm: avoid potential race in kcm_tx_work
  tcp: Clean up kernel listener's reqsk in inet_twsk_purge()
  net: phy: micrel: Fixes FIELD_GET assertion
  openvswitch: add nf_ct_is_confirmed check before assigning the helper
  tcp: Fix data races around icsk->icsk_af_ops.
  ipv6: Fix data races around sk->sk_prot.
  tcp/udp: Call inet6_destroy_sock() in IPv6 sk->sk_destruct().
  udp: Call inet6_destroy_sock() in setsockopt(IPV6_ADDRFORM).
  tcp/udp: Fix memory leak in ipv6_renew_options().
  mctp: prevent double key removal and unref
  selftests: netfilter: Fix nft_fib.sh for all.rp_filter=1
  netfilter: rpfilter/fib: Populate flowic_l3mdev field
  selftests: netfilter: Test reverse path filtering
  net/mlx5: Make ASO poll CQ usable in atomic context
  tcp: cdg: allow tcp_cdg_release() to be called multiple times
  inet: ping: fix recent breakage
  ipv6: ping: fix wrong checksum for large frames
  net: ethernet: ti: am65-cpsw: set correct devlink flavour for unused ports
  ...

4 files changed, 154 insertions, 1 deletions

diff --git a/tools/testing/selftests/net/fib_nexthops.sh b/tools/testing/selftests/net/fib_nexthops.sh
index d5a0dd548989..ee5e98204d3d 100755
--- a/tools/testing/selftests/net/fib_nexthops.sh
+++ b/tools/testing/selftests/net/fib_nexthops.sh
@@ -1223,6 +1223,11 @@ ipv4_fcnal()
 	log_test $rc 0 "Delete nexthop route warning"
 	run_cmd "$IP route delete 172.16.101.1/32 nhid 12"
 	run_cmd "$IP nexthop del id 12"
+
+	run_cmd "$IP nexthop add id 21 via 172.16.1.6 dev veth1"
+	run_cmd "$IP ro add 172.16.101.0/24 nhid 21"
+	run_cmd "$IP ro del 172.16.101.0/24 nexthop via 172.16.1.7 dev veth1 nexthop via 172.16.1.8 dev veth1"
+	log_test $? 2 "Delete multipath route with only nh id based entry"
 }
 
 ipv4_grp_fcnal()
diff --git a/tools/testing/selftests/netfilter/Makefile b/tools/testing/selftests/netfilter/Makefile
index 600e3a19d5e2..4504ee07be08 100644
--- a/tools/testing/selftests/netfilter/Makefile
+++ b/tools/testing/selftests/netfilter/Makefile
@@ -6,7 +6,7 @@ TEST_PROGS := nft_trans_stress.sh nft_fib.sh nft_nat.sh bridge_brouter.sh \
 	nft_concat_range.sh nft_conntrack_helper.sh \
 	nft_queue.sh nft_meta.sh nf_nat_edemux.sh \
 	ipip-conntrack-mtu.sh conntrack_tcp_unreplied.sh \
-	conntrack_vrf.sh nft_synproxy.sh
+	conntrack_vrf.sh nft_synproxy.sh rpath.sh
 
 CFLAGS += $(shell pkg-config --cflags libmnl 2>/dev/null || echo "-I/usr/include/libmnl")
 LDLIBS = -lmnl
diff --git a/tools/testing/selftests/netfilter/nft_fib.sh b/tools/testing/selftests/netfilter/nft_fib.sh
index fd76b69635a4..dff476e45e77 100755
--- a/tools/testing/selftests/netfilter/nft_fib.sh
+++ b/tools/testing/selftests/netfilter/nft_fib.sh
@@ -188,6 +188,7 @@ test_ping() {
 ip netns exec ${nsrouter} sysctl net.ipv6.conf.all.forwarding=1 > /dev/null
 ip netns exec ${nsrouter} sysctl net.ipv4.conf.veth0.forwarding=1 > /dev/null
 ip netns exec ${nsrouter} sysctl net.ipv4.conf.veth1.forwarding=1 > /dev/null
+ip netns exec ${nsrouter} sysctl net.ipv4.conf.all.rp_filter=0 > /dev/null
 ip netns exec ${nsrouter} sysctl net.ipv4.conf.veth0.rp_filter=0 > /dev/null
 
 sleep 3
diff --git a/tools/testing/selftests/netfilter/rpath.sh b/tools/testing/selftests/netfilter/rpath.sh
new file mode 100755
index 000000000000..2d8da7bd8ab7
--- /dev/null
+++ b/tools/testing/selftests/netfilter/rpath.sh
@@ -0,0 +1,147 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+
+# return code to signal skipped test
+ksft_skip=4
+
+# search for legacy iptables (it uses the xtables extensions
+if iptables-legacy --version >/dev/null 2>&1; then
+	iptables='iptables-legacy'
+elif iptables --version >/dev/null 2>&1; then
+	iptables='iptables'
+else
+	iptables=''
+fi
+
+if ip6tables-legacy --version >/dev/null 2>&1; then
+	ip6tables='ip6tables-legacy'
+elif ! ip6tables --version >/dev/null 2>&1; then
+	ip6tables='ip6tables'
+else
+	ip6tables=''
+fi
+
+if nft --version >/dev/null 2>&1; then
+	nft='nft'
+else
+	nft=''
+fi
+
+if [ -z "$iptables$ip6tables$nft" ]; then
+	echo "SKIP: Test needs iptables, ip6tables or nft"
+	exit $ksft_skip
+fi
+
+sfx=$(mktemp -u "XXXXXXXX")
+ns1="ns1-$sfx"
+ns2="ns2-$sfx"
+trap "ip netns del $ns1; ip netns del $ns2" EXIT
+
+# create two netns, disable rp_filter in ns2 and
+# keep IPv6 address when moving into VRF
+ip netns add "$ns1"
+ip netns add "$ns2"
+ip netns exec "$ns2" sysctl -q net.ipv4.conf.all.rp_filter=0
+ip netns exec "$ns2" sysctl -q net.ipv4.conf.default.rp_filter=0
+ip netns exec "$ns2" sysctl -q net.ipv6.conf.all.keep_addr_on_down=1
+
+# a standard connection between the netns, should not trigger rp filter
+ip -net "$ns1" link add v0 type veth peer name v0 netns "$ns2"
+ip -net "$ns1" link set v0 up; ip -net "$ns2" link set v0 up
+ip -net "$ns1" a a 192.168.23.2/24 dev v0
+ip -net "$ns2" a a 192.168.23.1/24 dev v0
+ip -net "$ns1" a a fec0:23::2/64 dev v0 nodad
+ip -net "$ns2" a a fec0:23::1/64 dev v0 nodad
+
+# rp filter testing: ns1 sends packets via v0 which ns2 would route back via d0
+ip -net "$ns2" link add d0 type dummy
+ip -net "$ns2" link set d0 up
+ip -net "$ns1" a a 192.168.42.2/24 dev v0
+ip -net "$ns2" a a 192.168.42.1/24 dev d0
+ip -net "$ns1" a a fec0:42::2/64 dev v0 nodad
+ip -net "$ns2" a a fec0:42::1/64 dev d0 nodad
+
+# firewall matches to test
+ip netns exec "$ns2" "$iptables" -t raw -A PREROUTING -s 192.168.0.0/16 -m rpfilter
+ip netns exec "$ns2" "$ip6tables" -t raw -A PREROUTING -s fec0::/16 -m rpfilter
+ip netns exec "$ns2" nft -f - <<EOF
+table inet t {
+	chain c {
+		type filter hook prerouting priority raw;
+		ip saddr 192.168.0.0/16 fib saddr . iif oif exists counter
+		ip6 saddr fec0::/16 fib saddr . iif oif exists counter
+	}
+}
+EOF
+
+die() {
+	echo "FAIL: $*"
+	#ip netns exec "$ns2" "$iptables" -t raw -vS
+	#ip netns exec "$ns2" "$ip6tables" -t raw -vS
+	#ip netns exec "$ns2" nft list ruleset
+	exit 1
+}
+
+# check rule counters, return true if rule did not match
+ipt_zero_rule() { # (command)
+	[ -n "$1" ] || return 0
+	ip netns exec "$ns2" "$1" -t raw -vS | grep -q -- "-m rpfilter -c 0 0"
+}
+nft_zero_rule() { # (family)
+	[ -n "$nft" ] || return 0
+	ip netns exec "$ns2" "$nft" list chain inet t c | \
+		grep -q "$1 saddr .* counter packets 0 bytes 0"
+}
+
+netns_ping() { # (netns, args...)
+	local netns="$1"
+	shift
+	ip netns exec "$netns" ping -q -c 1 -W 1 "$@" >/dev/null
+}
+
+testrun() {
+	# clear counters first
+	[ -n "$iptables" ] && ip netns exec "$ns2" "$iptables" -t raw -Z
+	[ -n "$ip6tables" ] && ip netns exec "$ns2" "$ip6tables" -t raw -Z
+	if [ -n "$nft" ]; then
+		(
+			echo "delete table inet t";
+			ip netns exec "$ns2" nft -s list table inet t;
+		) | ip netns exec "$ns2" nft -f -
+	fi
+
+	# test 1: martian traffic should fail rpfilter matches
+	netns_ping "$ns1" -I v0 192.168.42.1 && \
+		die "martian ping 192.168.42.1 succeeded"
+	netns_ping "$ns1" -I v0 fec0:42::1 && \
+		die "martian ping fec0:42::1 succeeded"
+
+	ipt_zero_rule "$iptables" || die "iptables matched martian"
+	ipt_zero_rule "$ip6tables" || die "ip6tables matched martian"
+	nft_zero_rule ip || die "nft IPv4 matched martian"
+	nft_zero_rule ip6 || die "nft IPv6 matched martian"
+
+	# test 2: rpfilter match should pass for regular traffic
+	netns_ping "$ns1" 192.168.23.1 || \
+		die "regular ping 192.168.23.1 failed"
+	netns_ping "$ns1" fec0:23::1 || \
+		die "regular ping fec0:23::1 failed"
+
+	ipt_zero_rule "$iptables" && die "iptables match not effective"
+	ipt_zero_rule "$ip6tables" && die "ip6tables match not effective"
+	nft_zero_rule ip && die "nft IPv4 match not effective"
+	nft_zero_rule ip6 && die "nft IPv6 match not effective"
+
+}
+
+testrun
+
+# repeat test with vrf device in $ns2
+ip -net "$ns2" link add vrf0 type vrf table 10
+ip -net "$ns2" link set vrf0 up
+ip -net "$ns2" link set v0 master vrf0
+
+testrun
+
+echo "PASS: netfilter reverse path match works as intended"
+exit 0