Merge tag 'net-5.13-rc7' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net

Pull networking fixes from Jakub Kicinski:
 "Networking fixes for 5.13-rc7, including fixes from wireless, bpf,
  bluetooth, netfilter and can.

  Current release - regressions:

   - mlxsw: spectrum_qdisc: Pass handle, not band number to find_class()
     to fix modifying offloaded qdiscs

   - lantiq: net: fix duplicated skb in rx descriptor ring

   - rtnetlink: fix regression in bridge VLAN configuration, empty info
     is not an error, bot-generated "fix" was not needed

   - libbpf: s/rx/tx/ typo on umem->rx_ring_setup_done to fix umem
     creation

  Current release - new code bugs:

   - ethtool: fix NULL pointer dereference during module EEPROM dump via
     the new netlink API

   - mlx5e: don't update netdev RQs with PTP-RQ, the special purpose
     queue should not be visible to the stack

   - mlx5e: select special PTP queue only for SKBTX_HW_TSTAMP skbs

   - mlx5e: verify dev is present in get devlink port ndo, avoid a panic

  Previous releases - regressions:

   - neighbour: allow NUD_NOARP entries to be force GCed

   - further fixes for fallout from reorg of WiFi locking (staging:
     rtl8723bs, mac80211, cfg80211)

   - skbuff: fix incorrect msg_zerocopy copy notifications

   - mac80211: fix NULL ptr deref for injected rate info

   - Revert "net/mlx5: Arm only EQs with EQEs" it may cause missed IRQs

  Previous releases - always broken:

   - bpf: more speculative execution fixes

   - netfilter: nft_fib_ipv6: skip ipv6 packets from any to link-local

   - udp: fix race between close() and udp_abort() resulting in a panic

   - fix out of bounds when parsing TCP options before packets are
     validated (in netfilter: synproxy, tc: sch_cake and mptcp)

   - mptcp: improve operation under memory pressure, add missing
     wake-ups

   - mptcp: fix double-lock/soft lookup in subflow_error_report()

   - bridge: fix races (null pointer deref and UAF) in vlan tunnel
     egress

   - ena: fix DMA mapping function issues in XDP

   - rds: fix memory leak in rds_recvmsg

  Misc:

   - vrf: allow larger MTUs

   - icmp: don't send out ICMP messages with a source address of 0.0.0.0

   - cdc_ncm: switch to eth%d interface naming"

* tag 'net-5.13-rc7' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net: (139 commits)
  net: ethernet: fix potential use-after-free in ec_bhf_remove
  selftests/net: Add icmp.sh for testing ICMP dummy address responses
  icmp: don't send out ICMP messages with a source address of 0.0.0.0
  net: ll_temac: Avoid ndo_start_xmit returning NETDEV_TX_BUSY
  net: ll_temac: Fix TX BD buffer overwrite
  net: ll_temac: Add memory-barriers for TX BD access
  net: ll_temac: Make sure to free skb when it is completely used
  MAINTAINERS: add Guvenc as SMC maintainer
  bnxt_en: Call bnxt_ethtool_free() in bnxt_init_one() error path
  bnxt_en: Fix TQM fastpath ring backing store computation
  bnxt_en: Rediscover PHY capabilities after firmware reset
  cxgb4: fix wrong shift.
  mac80211: handle various extensible elements correctly
  mac80211: reset profile_periodicity/ema_ap
  cfg80211: avoid double free of PMSR request
  cfg80211: make certificate generation more robust
  mac80211: minstrel_ht: fix sample time check
  net: qed: Fix memcpy() overflow of qed_dcbx_params()
  net: cdc_eem: fix tx fixup skb leak
  net: hamradio: fix memory leak in mkiss_close
  ...

15 files changed, 386 insertions, 15 deletions

diff --git a/tools/testing/selftests/bpf/test_verifier.c b/tools/testing/selftests/bpf/test_verifier.c
index 1512092e1e68..3a9e332c5e36 100644
--- a/tools/testing/selftests/bpf/test_verifier.c
+++ b/tools/testing/selftests/bpf/test_verifier.c
@@ -1147,7 +1147,7 @@ static void do_test_single(struct bpf_test *test, bool unpriv,
 		}
 	}
 
-	if (test->insn_processed) {
+	if (!unpriv && test->insn_processed) {
 		uint32_t insn_processed;
 		char *proc;
 
diff --git a/tools/testing/selftests/bpf/verifier/and.c b/tools/testing/selftests/bpf/verifier/and.c
index ca8fdb1b3f01..7d7ebee5cc7a 100644
--- a/tools/testing/selftests/bpf/verifier/and.c
+++ b/tools/testing/selftests/bpf/verifier/and.c
@@ -61,6 +61,8 @@
 	BPF_MOV64_IMM(BPF_REG_0, 0),
 	BPF_EXIT_INSN(),
 	},
+	.errstr_unpriv = "R1 !read_ok",
+	.result_unpriv = REJECT,
 	.result = ACCEPT,
 	.retval = 0
 },
diff --git a/tools/testing/selftests/bpf/verifier/bounds.c b/tools/testing/selftests/bpf/verifier/bounds.c
index 8a1caf46ffbc..e061e8799ce2 100644
--- a/tools/testing/selftests/bpf/verifier/bounds.c
+++ b/tools/testing/selftests/bpf/verifier/bounds.c
@@ -508,6 +508,8 @@
 	BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_0, -1),
 	BPF_EXIT_INSN(),
 	},
+	.errstr_unpriv = "R0 invalid mem access 'inv'",
+	.result_unpriv = REJECT,
 	.result = ACCEPT
 },
 {
@@ -528,6 +530,8 @@
 	BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_0, -1),
 	BPF_EXIT_INSN(),
 	},
+	.errstr_unpriv = "R0 invalid mem access 'inv'",
+	.result_unpriv = REJECT,
 	.result = ACCEPT
 },
 {
@@ -569,6 +573,8 @@
 	BPF_MOV64_IMM(BPF_REG_0, 0),
 	BPF_EXIT_INSN(),
 	},
+	.errstr_unpriv = "R0 min value is outside of the allowed memory range",
+	.result_unpriv = REJECT,
 	.fixup_map_hash_8b = { 3 },
 	.result = ACCEPT,
 },
@@ -589,6 +595,8 @@
 	BPF_MOV64_IMM(BPF_REG_0, 0),
 	BPF_EXIT_INSN(),
 	},
+	.errstr_unpriv = "R0 min value is outside of the allowed memory range",
+	.result_unpriv = REJECT,
 	.fixup_map_hash_8b = { 3 },
 	.result = ACCEPT,
 },
@@ -609,6 +617,8 @@
 	BPF_MOV64_IMM(BPF_REG_0, 0),
 	BPF_EXIT_INSN(),
 	},
+	.errstr_unpriv = "R0 min value is outside of the allowed memory range",
+	.result_unpriv = REJECT,
 	.fixup_map_hash_8b = { 3 },
 	.result = ACCEPT,
 },
@@ -674,6 +684,8 @@
 	BPF_MOV64_IMM(BPF_REG_0, 0),
 	BPF_EXIT_INSN(),
 	},
+	.errstr_unpriv = "R0 min value is outside of the allowed memory range",
+	.result_unpriv = REJECT,
 	.fixup_map_hash_8b = { 3 },
 	.result = ACCEPT,
 },
@@ -695,6 +707,8 @@
 	BPF_MOV64_IMM(BPF_REG_0, 0),
 	BPF_EXIT_INSN(),
 	},
+	.errstr_unpriv = "R0 min value is outside of the allowed memory range",
+	.result_unpriv = REJECT,
 	.fixup_map_hash_8b = { 3 },
 	.result = ACCEPT,
 },
diff --git a/tools/testing/selftests/bpf/verifier/dead_code.c b/tools/testing/selftests/bpf/verifier/dead_code.c
index 17fe33a75034..2c8935b3e65d 100644
--- a/tools/testing/selftests/bpf/verifier/dead_code.c
+++ b/tools/testing/selftests/bpf/verifier/dead_code.c
@@ -8,6 +8,8 @@
 	BPF_JMP_IMM(BPF_JGE, BPF_REG_0, 10, -4),
 	BPF_EXIT_INSN(),
 	},
+	.errstr_unpriv = "R9 !read_ok",
+	.result_unpriv = REJECT,
 	.result = ACCEPT,
 	.retval = 7,
 },
diff --git a/tools/testing/selftests/bpf/verifier/jmp32.c b/tools/testing/selftests/bpf/verifier/jmp32.c
index bd5cae4a7f73..1c857b2fbdf0 100644
--- a/tools/testing/selftests/bpf/verifier/jmp32.c
+++ b/tools/testing/selftests/bpf/verifier/jmp32.c
@@ -87,6 +87,8 @@
 	BPF_LDX_MEM(BPF_B, BPF_REG_8, BPF_REG_9, 0),
 	BPF_EXIT_INSN(),
 	},
+	.errstr_unpriv = "R9 !read_ok",
+	.result_unpriv = REJECT,
 	.result = ACCEPT,
 },
 {
@@ -150,6 +152,8 @@
 	BPF_LDX_MEM(BPF_B, BPF_REG_8, BPF_REG_9, 0),
 	BPF_EXIT_INSN(),
 	},
+	.errstr_unpriv = "R9 !read_ok",
+	.result_unpriv = REJECT,
 	.result = ACCEPT,
 },
 {
@@ -213,6 +217,8 @@
 	BPF_LDX_MEM(BPF_B, BPF_REG_8, BPF_REG_9, 0),
 	BPF_EXIT_INSN(),
 	},
+	.errstr_unpriv = "R9 !read_ok",
+	.result_unpriv = REJECT,
 	.result = ACCEPT,
 },
 {
@@ -280,6 +286,8 @@
 	BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_0, 0),
 	BPF_EXIT_INSN(),
 	},
+	.errstr_unpriv = "R0 invalid mem access 'inv'",
+	.result_unpriv = REJECT,
 	.result = ACCEPT,
 	.retval = 2,
 },
@@ -348,6 +356,8 @@
 	BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_0, 0),
 	BPF_EXIT_INSN(),
 	},
+	.errstr_unpriv = "R0 invalid mem access 'inv'",
+	.result_unpriv = REJECT,
 	.result = ACCEPT,
 	.retval = 2,
 },
@@ -416,6 +426,8 @@
 	BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_0, 0),
 	BPF_EXIT_INSN(),
 	},
+	.errstr_unpriv = "R0 invalid mem access 'inv'",
+	.result_unpriv = REJECT,
 	.result = ACCEPT,
 	.retval = 2,
 },
@@ -484,6 +496,8 @@
 	BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_0, 0),
 	BPF_EXIT_INSN(),
 	},
+	.errstr_unpriv = "R0 invalid mem access 'inv'",
+	.result_unpriv = REJECT,
 	.result = ACCEPT,
 	.retval = 2,
 },
@@ -552,6 +566,8 @@
 	BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_0, 0),
 	BPF_EXIT_INSN(),
 	},
+	.errstr_unpriv = "R0 invalid mem access 'inv'",
+	.result_unpriv = REJECT,
 	.result = ACCEPT,
 	.retval = 2,
 },
@@ -620,6 +636,8 @@
 	BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_0, 0),
 	BPF_EXIT_INSN(),
 	},
+	.errstr_unpriv = "R0 invalid mem access 'inv'",
+	.result_unpriv = REJECT,
 	.result = ACCEPT,
 	.retval = 2,
 },
@@ -688,6 +706,8 @@
 	BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_0, 0),
 	BPF_EXIT_INSN(),
 	},
+	.errstr_unpriv = "R0 invalid mem access 'inv'",
+	.result_unpriv = REJECT,
 	.result = ACCEPT,
 	.retval = 2,
 },
@@ -756,6 +776,8 @@
 	BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_0, 0),
 	BPF_EXIT_INSN(),
 	},
+	.errstr_unpriv = "R0 invalid mem access 'inv'",
+	.result_unpriv = REJECT,
 	.result = ACCEPT,
 	.retval = 2,
 },
diff --git a/tools/testing/selftests/bpf/verifier/jset.c b/tools/testing/selftests/bpf/verifier/jset.c
index 8dcd4e0383d5..11fc68da735e 100644
--- a/tools/testing/selftests/bpf/verifier/jset.c
+++ b/tools/testing/selftests/bpf/verifier/jset.c
@@ -82,8 +82,8 @@
 	BPF_EXIT_INSN(),
 	},
 	.prog_type = BPF_PROG_TYPE_SOCKET_FILTER,
-	.retval_unpriv = 1,
-	.result_unpriv = ACCEPT,
+	.errstr_unpriv = "R9 !read_ok",
+	.result_unpriv = REJECT,
 	.retval = 1,
 	.result = ACCEPT,
 },
@@ -141,7 +141,8 @@
 	BPF_EXIT_INSN(),
 	},
 	.prog_type = BPF_PROG_TYPE_SOCKET_FILTER,
-	.result_unpriv = ACCEPT,
+	.errstr_unpriv = "R9 !read_ok",
+	.result_unpriv = REJECT,
 	.result = ACCEPT,
 },
 {
@@ -162,6 +163,7 @@
 	BPF_EXIT_INSN(),
 	},
 	.prog_type = BPF_PROG_TYPE_SOCKET_FILTER,
-	.result_unpriv = ACCEPT,
+	.errstr_unpriv = "R9 !read_ok",
+	.result_unpriv = REJECT,
 	.result = ACCEPT,
 },
diff --git a/tools/testing/selftests/bpf/verifier/unpriv.c b/tools/testing/selftests/bpf/verifier/unpriv.c
index bd436df5cc32..111801aea5e3 100644
--- a/tools/testing/selftests/bpf/verifier/unpriv.c
+++ b/tools/testing/selftests/bpf/verifier/unpriv.c
@@ -420,6 +420,8 @@
 	BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_7, 0),
 	BPF_EXIT_INSN(),
 	},
+	.errstr_unpriv = "R7 invalid mem access 'inv'",
+	.result_unpriv = REJECT,
 	.result = ACCEPT,
 	.retval = 0,
 },
diff --git a/tools/testing/selftests/bpf/verifier/value_ptr_arith.c b/tools/testing/selftests/bpf/verifier/value_ptr_arith.c
index 7ae2859d495c..a3e593ddfafc 100644
--- a/tools/testing/selftests/bpf/verifier/value_ptr_arith.c
+++ b/tools/testing/selftests/bpf/verifier/value_ptr_arith.c
@@ -120,7 +120,7 @@
 	.fixup_map_array_48b = { 1 },
 	.result = ACCEPT,
 	.result_unpriv = REJECT,
-	.errstr_unpriv = "R2 tried to add from different maps, paths or scalars",
+	.errstr_unpriv = "R2 pointer comparison prohibited",
 	.retval = 0,
 },
 {
@@ -159,7 +159,8 @@
 	BPF_MOV64_IMM(BPF_REG_0, 0),
 	BPF_EXIT_INSN(),
 	// fake-dead code; targeted from branch A to
-	// prevent dead code sanitization
+	// prevent dead code sanitization, rejected
+	// via branch B however
 	BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_0, 0),
 	BPF_MOV64_IMM(BPF_REG_0, 0),
 	BPF_EXIT_INSN(),
@@ -167,7 +168,7 @@
 	.fixup_map_array_48b = { 1 },
 	.result = ACCEPT,
 	.result_unpriv = REJECT,
-	.errstr_unpriv = "R2 tried to add from different maps, paths or scalars",
+	.errstr_unpriv = "R0 invalid mem access 'inv'",
 	.retval = 0,
 },
 {
diff --git a/tools/testing/selftests/net/fib_tests.sh b/tools/testing/selftests/net/fib_tests.sh
index 76d9487fb03c..5abe92d55b69 100755
--- a/tools/testing/selftests/net/fib_tests.sh
+++ b/tools/testing/selftests/net/fib_tests.sh
@@ -1384,12 +1384,37 @@ ipv4_rt_replace()
 	ipv4_rt_replace_mpath
 }
 
+# checks that cached input route on VRF port is deleted
+# when VRF is deleted
+ipv4_local_rt_cache()
+{
+	run_cmd "ip addr add 10.0.0.1/32 dev lo"
+	run_cmd "ip netns add test-ns"
+	run_cmd "ip link add veth-outside type veth peer name veth-inside"
+	run_cmd "ip link add vrf-100 type vrf table 1100"
+	run_cmd "ip link set veth-outside master vrf-100"
+	run_cmd "ip link set veth-inside netns test-ns"
+	run_cmd "ip link set veth-outside up"
+	run_cmd "ip link set vrf-100 up"
+	run_cmd "ip route add 10.1.1.1/32 dev veth-outside table 1100"
+	run_cmd "ip netns exec test-ns ip link set veth-inside up"
+	run_cmd "ip netns exec test-ns ip addr add 10.1.1.1/32 dev veth-inside"
+	run_cmd "ip netns exec test-ns ip route add 10.0.0.1/32 dev veth-inside"
+	run_cmd "ip netns exec test-ns ip route add default via 10.0.0.1"
+	run_cmd "ip netns exec test-ns ping 10.0.0.1 -c 1 -i 1"
+	run_cmd "ip link delete vrf-100"
+
+	# if we do not hang test is a success
+	log_test $? 0 "Cached route removed from VRF port device"
+}
+
 ipv4_route_test()
 {
 	route_setup
 
 	ipv4_rt_add
 	ipv4_rt_replace
+	ipv4_local_rt_cache
 
 	route_cleanup
 }
diff --git a/tools/testing/selftests/net/icmp.sh b/tools/testing/selftests/net/icmp.sh
new file mode 100755
index 000000000000..e4b04cd1644a
--- /dev/null
+++ b/tools/testing/selftests/net/icmp.sh
@@ -0,0 +1,74 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+
+# Test for checking ICMP response with dummy address instead of 0.0.0.0.
+# Sets up two namespaces like:
+# +----------------------+                          +--------------------+
+# | ns1                  |    v4-via-v6 routes:     | ns2                |
+# |                      |                  '       |                    |
+# |             +--------+   -> 172.16.1.0/24 ->    +--------+           |
+# |             | veth0  +--------------------------+  veth0 |           |
+# |             +--------+   <- 172.16.0.0/24 <-    +--------+           |
+# |           172.16.0.1 |                          | 2001:db8:1::2/64   |
+# |     2001:db8:1::2/64 |                          |                    |
+# +----------------------+                          +--------------------+
+#
+# And then tries to ping 172.16.1.1 from ns1. This results in a "net
+# unreachable" message being sent from ns2, but there is no IPv4 address set in
+# that address space, so the kernel should substitute the dummy address
+# 192.0.0.8 defined in RFC7600.
+
+NS1=ns1
+NS2=ns2
+H1_IP=172.16.0.1/32
+H1_IP6=2001:db8:1::1
+RT1=172.16.1.0/24
+PINGADDR=172.16.1.1
+RT2=172.16.0.0/24
+H2_IP6=2001:db8:1::2
+
+TMPFILE=$(mktemp)
+
+cleanup()
+{
+    rm -f "$TMPFILE"
+    ip netns del $NS1
+    ip netns del $NS2
+}
+
+trap cleanup EXIT
+
+# Namespaces
+ip netns add $NS1
+ip netns add $NS2
+
+# Connectivity
+ip -netns $NS1 link add veth0 type veth peer name veth0 netns $NS2
+ip -netns $NS1 link set dev veth0 up
+ip -netns $NS2 link set dev veth0 up
+ip -netns $NS1 addr add $H1_IP dev veth0
+ip -netns $NS1 addr add $H1_IP6/64 dev veth0 nodad
+ip -netns $NS2 addr add $H2_IP6/64 dev veth0 nodad
+ip -netns $NS1 route add $RT1 via inet6 $H2_IP6
+ip -netns $NS2 route add $RT2 via inet6 $H1_IP6
+
+# Make sure ns2 will respond with ICMP unreachable
+ip netns exec $NS2 sysctl -qw net.ipv4.icmp_ratelimit=0 net.ipv4.ip_forward=1
+
+# Run the test - a ping runs in the background, and we capture ICMP responses
+# with tcpdump; -c 1 means it should exit on the first ping, but add a timeout
+# in case something goes wrong
+ip netns exec $NS1 ping -w 3 -i 0.5 $PINGADDR >/dev/null &
+ip netns exec $NS1 timeout 10 tcpdump -tpni veth0 -c 1 'icmp and icmp[icmptype] != icmp-echo' > $TMPFILE 2>/dev/null
+
+# Parse response and check for dummy address
+# tcpdump output looks like:
+# IP 192.0.0.8 > 172.16.0.1: ICMP net 172.16.1.1 unreachable, length 92
+RESP_IP=$(awk '{print $2}' < $TMPFILE)
+if [[ "$RESP_IP" != "192.0.0.8" ]]; then
+    echo "FAIL - got ICMP response from $RESP_IP, should be 192.0.0.8"
+    exit 1
+else
+    echo "OK"
+    exit 0
+fi
diff --git a/tools/testing/selftests/net/mptcp/mptcp_connect.sh b/tools/testing/selftests/net/mptcp/mptcp_connect.sh
index 9ca5f1ba461e..2b495dc8d78e 100755
--- a/tools/testing/selftests/net/mptcp/mptcp_connect.sh
+++ b/tools/testing/selftests/net/mptcp/mptcp_connect.sh
@@ -197,9 +197,6 @@ ip -net "$ns4" link set ns4eth3 up
 ip -net "$ns4" route add default via 10.0.3.2
 ip -net "$ns4" route add default via dead:beef:3::2
 
-# use TCP syn cookies, even if no flooding was detected.
-ip netns exec "$ns2" sysctl -q net.ipv4.tcp_syncookies=2
-
 set_ethtool_flags() {
 	local ns="$1"
 	local dev="$2"
@@ -737,6 +734,14 @@ for sender in $ns1 $ns2 $ns3 $ns4;do
 		exit $ret
 	fi
 
+	# ns1<->ns2 is not subject to reordering/tc delays. Use it to test
+	# mptcp syncookie support.
+	if [ $sender = $ns1 ]; then
+		ip netns exec "$ns2" sysctl -q net.ipv4.tcp_syncookies=2
+	else
+		ip netns exec "$ns2" sysctl -q net.ipv4.tcp_syncookies=1
+	fi
+
 	run_tests "$ns2" $sender 10.0.1.2
 	run_tests "$ns2" $sender dead:beef:1::2
 	run_tests "$ns2" $sender 10.0.2.1
diff --git a/tools/testing/selftests/net/udpgro_fwd.sh b/tools/testing/selftests/net/udpgro_fwd.sh
index a8fa64136282..7f26591f236b 100755
--- a/tools/testing/selftests/net/udpgro_fwd.sh
+++ b/tools/testing/selftests/net/udpgro_fwd.sh
@@ -1,4 +1,4 @@
-#!/bin/sh
+#!/bin/bash
 # SPDX-License-Identifier: GPL-2.0
 
 readonly BASE="ns-$(mktemp -u XXXXXX)"
diff --git a/tools/testing/selftests/net/veth.sh b/tools/testing/selftests/net/veth.sh
index 2fedc0781ce8..11d7cdb898c0 100755
--- a/tools/testing/selftests/net/veth.sh
+++ b/tools/testing/selftests/net/veth.sh
@@ -18,7 +18,8 @@ ret=0
 
 cleanup() {
 	local ns
-	local -r jobs="$(jobs -p)"
+	local jobs
+	readonly jobs="$(jobs -p)"
 	[ -n "${jobs}" ] && kill -1 ${jobs} 2>/dev/null
 	rm -f $STATS
 
@@ -108,7 +109,7 @@ chk_gro() {
 
 if [ ! -f ../bpf/xdp_dummy.o ]; then
 	echo "Missing xdp_dummy helper. Build bpf selftest first"
-	exit -1
+	exit 1
 fi
 
 create_ns
diff --git a/tools/testing/selftests/netfilter/Makefile b/tools/testing/selftests/netfilter/Makefile
index 3171069a6b46..cd6430b39982 100644
--- a/tools/testing/selftests/netfilter/Makefile
+++ b/tools/testing/selftests/netfilter/Makefile
@@ -1,7 +1,7 @@
 # SPDX-License-Identifier: GPL-2.0
 # Makefile for netfilter selftests
 
-TEST_PROGS := nft_trans_stress.sh nft_nat.sh bridge_brouter.sh \
+TEST_PROGS := nft_trans_stress.sh nft_fib.sh nft_nat.sh bridge_brouter.sh \
 	conntrack_icmp_related.sh nft_flowtable.sh ipvs.sh \
 	nft_concat_range.sh nft_conntrack_helper.sh \
 	nft_queue.sh nft_meta.sh nf_nat_edemux.sh \
diff --git a/tools/testing/selftests/netfilter/nft_fib.sh b/tools/testing/selftests/netfilter/nft_fib.sh
new file mode 100755
index 000000000000..6caf6ac8c285
--- /dev/null
+++ b/tools/testing/selftests/netfilter/nft_fib.sh
@@ -0,0 +1,221 @@
+#!/bin/bash
+#
+# This tests the fib expression.
+#
+# Kselftest framework requirement - SKIP code is 4.
+ksft_skip=4
+ret=0
+
+sfx=$(mktemp -u "XXXXXXXX")
+ns1="ns1-$sfx"
+ns2="ns2-$sfx"
+nsrouter="nsrouter-$sfx"
+timeout=4
+
+log_netns=$(sysctl -n net.netfilter.nf_log_all_netns)
+
+cleanup()
+{
+	ip netns del ${ns1}
+	ip netns del ${ns2}
+	ip netns del ${nsrouter}
+
+	[ $log_netns -eq 0 ] && sysctl -q net.netfilter.nf_log_all_netns=$log_netns
+}
+
+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 ${nsrouter}
+if [ $? -ne 0 ];then
+	echo "SKIP: Could not create net namespace"
+	exit $ksft_skip
+fi
+
+trap cleanup EXIT
+
+dmesg | grep -q ' nft_rpfilter: '
+if [ $? -eq 0 ]; then
+	dmesg -c | grep ' nft_rpfilter: '
+	echo "WARN: a previous test run has failed" 1>&2
+fi
+
+sysctl -q net.netfilter.nf_log_all_netns=1
+ip netns add ${ns1}
+ip netns add ${ns2}
+
+load_ruleset() {
+	local netns=$1
+
+ip netns exec ${netns} nft -f /dev/stdin <<EOF
+table inet filter {
+	chain prerouting {
+		type filter hook prerouting priority 0; policy accept;
+	        fib saddr . iif oif missing counter log prefix "$netns nft_rpfilter: " drop
+	}
+}
+EOF
+}
+
+load_ruleset_count() {
+	local netns=$1
+
+ip netns exec ${netns} nft -f /dev/stdin <<EOF
+table inet filter {
+	chain prerouting {
+		type filter hook prerouting priority 0; policy accept;
+		ip daddr 1.1.1.1 fib saddr . iif oif missing counter drop
+		ip6 daddr 1c3::c01d fib saddr . iif oif missing counter drop
+	}
+}
+EOF
+}
+
+check_drops() {
+	dmesg | grep -q ' nft_rpfilter: '
+	if [ $? -eq 0 ]; then
+		dmesg | grep ' nft_rpfilter: '
+		echo "FAIL: rpfilter did drop packets"
+		return 1
+	fi
+
+	return 0
+}
+
+check_fib_counter() {
+	local want=$1
+	local ns=$2
+	local address=$3
+
+	line=$(ip netns exec ${ns} nft list table inet filter | grep 'fib saddr . iif' | grep $address | grep "packets $want" )
+	ret=$?
+
+	if [ $ret -ne 0 ];then
+		echo "Netns $ns fib counter doesn't match expected packet count of $want for $address" 1>&2
+		ip netns exec ${ns} nft list table inet filter
+		return 1
+	fi
+
+	if [ $want -gt 0 ]; then
+		echo "PASS: fib expression did drop packets for $address"
+	fi
+
+	return 0
+}
+
+load_ruleset ${nsrouter}
+load_ruleset ${ns1}
+load_ruleset ${ns2}
+
+ip link add veth0 netns ${nsrouter} type veth peer name eth0 netns ${ns1} > /dev/null 2>&1
+if [ $? -ne 0 ];then
+    echo "SKIP: No virtual ethernet pair device support in kernel"
+    exit $ksft_skip
+fi
+ip link add veth1 netns ${nsrouter} type veth peer name eth0 netns ${ns2}
+
+ip -net ${nsrouter} link set lo up
+ip -net ${nsrouter} link set veth0 up
+ip -net ${nsrouter} addr add 10.0.1.1/24 dev veth0
+ip -net ${nsrouter} addr add dead:1::1/64 dev veth0
+
+ip -net ${nsrouter} link set veth1 up
+ip -net ${nsrouter} addr add 10.0.2.1/24 dev veth1
+ip -net ${nsrouter} addr add dead:2::1/64 dev veth1
+
+ip -net ${ns1} link set lo up
+ip -net ${ns1} link set eth0 up
+
+ip -net ${ns2} link set lo up
+ip -net ${ns2} link set eth0 up
+
+ip -net ${ns1} addr add 10.0.1.99/24 dev eth0
+ip -net ${ns1} addr add dead:1::99/64 dev eth0
+ip -net ${ns1} route add default via 10.0.1.1
+ip -net ${ns1} route add default via dead:1::1
+
+ip -net ${ns2} addr add 10.0.2.99/24 dev eth0
+ip -net ${ns2} addr add dead:2::99/64 dev eth0
+ip -net ${ns2} route add default via 10.0.2.1
+ip -net ${ns2} route add default via dead:2::1
+
+test_ping() {
+  local daddr4=$1
+  local daddr6=$2
+
+  ip netns exec ${ns1} ping -c 1 -q $daddr4 > /dev/null
+  ret=$?
+  if [ $ret -ne 0 ];then
+	check_drops
+	echo "FAIL: ${ns1} cannot reach $daddr4, ret $ret" 1>&2
+	return 1
+  fi
+
+  ip netns exec ${ns1} ping -c 3 -q $daddr6 > /dev/null
+  ret=$?
+  if [ $ret -ne 0 ];then
+	check_drops
+	echo "FAIL: ${ns1} cannot reach $daddr6, ret $ret" 1>&2
+	return 1
+  fi
+
+  return 0
+}
+
+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
+
+sleep 3
+
+test_ping 10.0.2.1 dead:2::1 || exit 1
+check_drops || exit 1
+
+test_ping 10.0.2.99 dead:2::99 || exit 1
+check_drops || exit 1
+
+echo "PASS: fib expression did not cause unwanted packet drops"
+
+ip netns exec ${nsrouter} nft flush table inet filter
+
+ip -net ${ns1} route del default
+ip -net ${ns1} -6 route del default
+
+ip -net ${ns1} addr del 10.0.1.99/24 dev eth0
+ip -net ${ns1} addr del dead:1::99/64 dev eth0
+
+ip -net ${ns1} addr add 10.0.2.99/24 dev eth0
+ip -net ${ns1} addr add dead:2::99/64 dev eth0
+
+ip -net ${ns1} route add default via 10.0.2.1
+ip -net ${ns1} -6 route add default via dead:2::1
+
+ip -net ${nsrouter} addr add dead:2::1/64 dev veth0
+
+# switch to ruleset that doesn't log, this time
+# its expected that this does drop the packets.
+load_ruleset_count ${nsrouter}
+
+# ns1 has a default route, but nsrouter does not.
+# must not check return value, ping to 1.1.1.1 will
+# fail.
+check_fib_counter 0 ${nsrouter} 1.1.1.1 || exit 1
+check_fib_counter 0 ${nsrouter} 1c3::c01d || exit 1
+
+ip netns exec ${ns1} ping -c 1 -W 1 -q 1.1.1.1 > /dev/null
+check_fib_counter 1 ${nsrouter} 1.1.1.1 || exit 1
+
+sleep 2
+ip netns exec ${ns1} ping -c 3 -q 1c3::c01d > /dev/null
+check_fib_counter 3 ${nsrouter} 1c3::c01d || exit 1
+
+exit 0