Merge git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net

Cross-merge networking fixes after downstream PR (net-7.0-rc8).

Conflicts:

net/ipv6/seg6_iptunnel.c
  c3812651b522f ("seg6: separate dst_cache for input and output paths in seg6 lwtunnel")
  78723a62b969a ("seg6: add per-route tunnel source address")
https://lore.kernel.org/adZhwtOYfo-0ImSa@sirena.org.uk

net/ipv4/icmp.c
  fde29fd934932 ("ipv4: icmp: fix null-ptr-deref in icmp_build_probe()")
  d98adfbdd5c01 ("ipv4: drop ipv6_stub usage and use direct function calls")
https://lore.kernel.org/adO3dccqnr6j-BL9@sirena.org.uk

Adjacent changes:

drivers/net/ethernet/stmicro/stmmac/chain_mode.c
  51f4e090b9f8 ("net: stmmac: fix integer underflow in chain mode")
  6b4286e05508 ("net: stmmac: rename STMMAC_GET_ENTRY() -> STMMAC_NEXT_ENTRY()")

Signed-off-by: Jakub Kicinski <kuba@kernel.org>

5 files changed, 314 insertions, 18 deletions

diff --git a/tools/testing/selftests/net/Makefile b/tools/testing/selftests/net/Makefile
index 6bced3ed798b..cab74ebdaced 100644
--- a/tools/testing/selftests/net/Makefile
+++ b/tools/testing/selftests/net/Makefile
@@ -92,6 +92,7 @@ TEST_PROGS := \
 	srv6_end_x_next_csid_l3vpn_test.sh \
 	srv6_hencap_red_l3vpn_test.sh \
 	srv6_hl2encap_red_l2vpn_test.sh \
+	srv6_iptunnel_cache.sh \
 	stress_reuseport_listen.sh \
 	tcp_fastopen_backup_key.sh \
 	test_bpf.sh \
diff --git a/tools/testing/selftests/net/forwarding/bridge_vlan_mcast.sh b/tools/testing/selftests/net/forwarding/bridge_vlan_mcast.sh
index 72dfbeaf56b9..e8031f68200a 100755
--- a/tools/testing/selftests/net/forwarding/bridge_vlan_mcast.sh
+++ b/tools/testing/selftests/net/forwarding/bridge_vlan_mcast.sh
@@ -414,6 +414,7 @@ vlmc_querier_intvl_test()
 	bridge vlan add vid 10 dev br1 self pvid untagged
 	ip link set dev $h1 master br1
 	ip link set dev br1 up
+	setup_wait_dev $h1 0
 	bridge vlan add vid 10 dev $h1 master
 	bridge vlan global set vid 10 dev br1 mcast_snooping 1 mcast_querier 1
 	sleep 2
diff --git a/tools/testing/selftests/net/netfilter/nf_queue.c b/tools/testing/selftests/net/netfilter/nf_queue.c
index 116c0ca0eabb..8bbec37f5356 100644
--- a/tools/testing/selftests/net/netfilter/nf_queue.c
+++ b/tools/testing/selftests/net/netfilter/nf_queue.c
@@ -19,6 +19,8 @@ struct options {
 	bool count_packets;
 	bool gso_enabled;
 	bool failopen;
+	bool out_of_order;
+	bool bogus_verdict;
 	int verbose;
 	unsigned int queue_num;
 	unsigned int timeout;
@@ -31,7 +33,7 @@ static struct options opts;
 
 static void help(const char *p)
 {
-	printf("Usage: %s [-c|-v [-vv] ] [-o] [-t timeout] [-q queue_num] [-Qdst_queue ] [ -d ms_delay ] [-G]\n", p);
+	printf("Usage: %s [-c|-v [-vv] ] [-o] [-O] [-b] [-t timeout] [-q queue_num] [-Qdst_queue ] [ -d ms_delay ] [-G]\n", p);
 }
 
 static int parse_attr_cb(const struct nlattr *attr, void *data)
@@ -275,7 +277,9 @@ static int mainloop(void)
 	unsigned int buflen = 64 * 1024 + MNL_SOCKET_BUFFER_SIZE;
 	struct mnl_socket *nl;
 	struct nlmsghdr *nlh;
+	uint32_t ooo_ids[16];
 	unsigned int portid;
+	int ooo_count = 0;
 	char *buf;
 	int ret;
 
@@ -308,6 +312,9 @@ static int mainloop(void)
 
 		ret = mnl_cb_run(buf, ret, 0, portid, queue_cb, NULL);
 		if (ret < 0) {
+			/* bogus verdict mode will generate ENOENT error messages */
+			if (opts.bogus_verdict && errno == ENOENT)
+				continue;
 			perror("mnl_cb_run");
 			exit(EXIT_FAILURE);
 		}
@@ -316,10 +323,35 @@ static int mainloop(void)
 		if (opts.delay_ms)
 			sleep_ms(opts.delay_ms);
 
-		nlh = nfq_build_verdict(buf, id, opts.queue_num, opts.verdict);
-		if (mnl_socket_sendto(nl, nlh, nlh->nlmsg_len) < 0) {
-			perror("mnl_socket_sendto");
-			exit(EXIT_FAILURE);
+		if (opts.bogus_verdict) {
+			for (int i = 0; i < 50; i++) {
+				nlh = nfq_build_verdict(buf, id + 0x7FFFFFFF + i,
+							opts.queue_num, opts.verdict);
+				mnl_socket_sendto(nl, nlh, nlh->nlmsg_len);
+			}
+		}
+
+		if (opts.out_of_order) {
+			ooo_ids[ooo_count] = id;
+			if (ooo_count >= 15) {
+				for (ooo_count; ooo_count >= 0; ooo_count--) {
+					nlh = nfq_build_verdict(buf, ooo_ids[ooo_count],
+								opts.queue_num, opts.verdict);
+					if (mnl_socket_sendto(nl, nlh, nlh->nlmsg_len) < 0) {
+						perror("mnl_socket_sendto");
+						exit(EXIT_FAILURE);
+					}
+				}
+				ooo_count = 0;
+			} else {
+				ooo_count++;
+			}
+		} else {
+			nlh = nfq_build_verdict(buf, id, opts.queue_num, opts.verdict);
+			if (mnl_socket_sendto(nl, nlh, nlh->nlmsg_len) < 0) {
+				perror("mnl_socket_sendto");
+				exit(EXIT_FAILURE);
+			}
 		}
 	}
 
@@ -332,7 +364,7 @@ static void parse_opts(int argc, char **argv)
 {
 	int c;
 
-	while ((c = getopt(argc, argv, "chvot:q:Q:d:G")) != -1) {
+	while ((c = getopt(argc, argv, "chvoObt:q:Q:d:G")) != -1) {
 		switch (c) {
 		case 'c':
 			opts.count_packets = true;
@@ -375,6 +407,12 @@ static void parse_opts(int argc, char **argv)
 		case 'v':
 			opts.verbose++;
 			break;
+		case 'O':
+			opts.out_of_order = true;
+			break;
+		case 'b':
+			opts.bogus_verdict = true;
+			break;
 		}
 	}
 
diff --git a/tools/testing/selftests/net/netfilter/nft_queue.sh b/tools/testing/selftests/net/netfilter/nft_queue.sh
index ea766bdc5d04..d80390848e85 100755
--- a/tools/testing/selftests/net/netfilter/nft_queue.sh
+++ b/tools/testing/selftests/net/netfilter/nft_queue.sh
@@ -11,6 +11,7 @@ ret=0
 timeout=5
 
 SCTP_TEST_TIMEOUT=60
+STRESS_TEST_TIMEOUT=30
 
 cleanup()
 {
@@ -719,6 +720,74 @@ EOF
 	fi
 }
 
+check_tainted()
+{
+	local msg="$1"
+
+	if [ "$tainted_then" -ne 0 ];then
+		return
+	fi
+
+	read tainted_now < /proc/sys/kernel/tainted
+	if [ "$tainted_now" -eq 0 ];then
+		echo "PASS: $msg"
+	else
+		echo "TAINT: $msg"
+		dmesg
+		ret=1
+	fi
+}
+
+test_queue_stress()
+{
+	read tainted_then < /proc/sys/kernel/tainted
+	local i
+
+        ip netns exec "$nsrouter" nft -f /dev/stdin <<EOF
+flush ruleset
+table inet t {
+	chain forward {
+		type filter hook forward priority 0; policy accept;
+
+		queue flags bypass to numgen random mod 8
+	}
+}
+EOF
+	timeout "$STRESS_TEST_TIMEOUT" ip netns exec "$ns2" \
+		socat -u UDP-LISTEN:12345,fork,pf=ipv4 STDOUT > /dev/null &
+
+	timeout "$STRESS_TEST_TIMEOUT" ip netns exec "$ns3" \
+		socat -u UDP-LISTEN:12345,fork,pf=ipv4 STDOUT > /dev/null &
+
+	for i in $(seq 0 7); do
+		ip netns exec "$nsrouter" timeout "$STRESS_TEST_TIMEOUT" \
+			./nf_queue -q $i -t 2 -O -b > /dev/null &
+	done
+
+	ip netns exec "$ns1" timeout "$STRESS_TEST_TIMEOUT" \
+		ping -q -f 10.0.2.99 > /dev/null 2>&1 &
+	ip netns exec "$ns1" timeout "$STRESS_TEST_TIMEOUT" \
+		ping -q -f 10.0.3.99 > /dev/null 2>&1 &
+	ip netns exec "$ns1" timeout "$STRESS_TEST_TIMEOUT" \
+		ping -q -f "dead:2::99" > /dev/null 2>&1 &
+	ip netns exec "$ns1" timeout "$STRESS_TEST_TIMEOUT" \
+		ping -q -f "dead:3::99" > /dev/null 2>&1 &
+
+	busywait "$BUSYWAIT_TIMEOUT" udp_listener_ready "$ns2" 12345
+	busywait "$BUSYWAIT_TIMEOUT" udp_listener_ready "$ns3" 12345
+
+	for i in $(seq 1 4);do
+		ip netns exec "$ns1" timeout "$STRESS_TEST_TIMEOUT" \
+			socat -u STDIN UDP-DATAGRAM:10.0.2.99:12345 < /dev/zero > /dev/null &
+		ip netns exec "$ns1" timeout "$STRESS_TEST_TIMEOUT" \
+			socat -u STDIN UDP-DATAGRAM:10.0.3.99:12345 < /dev/zero > /dev/null &
+	done
+
+	wait
+
+	check_tainted "concurrent queueing"
+}
+
 test_queue_removal()
 {
 	read tainted_then < /proc/sys/kernel/tainted
@@ -742,18 +811,7 @@ EOF
 
 	ip netns exec "$ns1" nft flush ruleset
 
-	if [ "$tainted_then" -ne 0 ];then
-		return
-	fi
-
-	read tainted_now < /proc/sys/kernel/tainted
-	if [ "$tainted_now" -eq 0 ];then
-		echo "PASS: queue program exiting while packets queued"
-	else
-		echo "TAINT: queue program exiting while packets queued"
-		dmesg
-		ret=1
-	fi
+	check_tainted "queue program exiting while packets queued"
 }
 
 ip netns exec "$nsrouter" sysctl net.ipv6.conf.all.forwarding=1 > /dev/null
@@ -799,6 +857,7 @@ test_sctp_forward
 test_sctp_output
 test_udp_nat_race
 test_udp_gro_ct
+test_queue_stress
 
 # should be last, adds vrf device in ns1 and changes routes
 test_icmp_vrf
diff --git a/tools/testing/selftests/net/srv6_iptunnel_cache.sh b/tools/testing/selftests/net/srv6_iptunnel_cache.sh
new file mode 100755
index 000000000000..62638ab679d9
--- /dev/null
+++ b/tools/testing/selftests/net/srv6_iptunnel_cache.sh
@@ -0,0 +1,197 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+#
+# author: Andrea Mayer <andrea.mayer@uniroma2.it>
+
+# This test verifies that the seg6 lwtunnel does not share the dst_cache
+# between the input (forwarding) and output (locally generated) paths.
+#
+# A shared dst_cache allows a forwarded packet to populate the cache and a
+# subsequent locally generated packet to silently reuse that entry, bypassing
+# its own route lookup. To expose this, the SID is made reachable only for
+# forwarded traffic (via an ip rule matching iif) and blackholed for everything
+# else. A local ping on ns_router must always hit the blackhole;
+# if it succeeds after a forwarded packet has populated the
+# cache, the bug is confirmed.
+#
+# Both forwarded and local packets are pinned to the same CPU with taskset,
+# since dst_cache is per-cpu.
+#
+#
+# +--------------------+                        +--------------------+
+# |      ns_src        |                        |      ns_dst        |
+# |                    |                        |                    |
+# |  veth-s0           |                        |           veth-d0  |
+# |  fd00::1/64        |                        |        fd01::2/64  |
+# +-------+------------+                        +----------+---------+
+#         |                                                |
+#         |            +--------------------+              |
+#         |            |     ns_router      |              |
+#         |            |                    |              |
+#         +------------+ veth-r0    veth-r1 +--------------+
+#                      | fd00::2    fd01::1 |
+#                      +--------------------+
+#
+#
+# ns_router: encap (main table)
+# +---------+---------------------------------------+
+# | dst     | action                                |
+# +---------+---------------------------------------+
+# | cafe::1 | encap seg6 mode encap segs fc00::100  |
+# +---------+---------------------------------------+
+#
+# ns_router: post-encap SID resolution
+# +-------+------------+----------------------------+
+# | table | dst        | action                     |
+# +-------+------------+----------------------------+
+# | 100   | fc00::100  | via fd01::2 dev veth-r1    |
+# +-------+------------+----------------------------+
+# | main  | fc00::100  | blackhole                  |
+# +-------+------------+----------------------------+
+#
+# ns_router: ip rule
+# +------------------+------------------------------+
+# | match            | action                       |
+# +------------------+------------------------------+
+# | iif veth-r0      | lookup 100                   |
+# +------------------+------------------------------+
+#
+# ns_dst: SRv6 decap (main table)
+# +--------------+----------------------------------+
+# | SID          | action                           |
+# +--------------+----------------------------------+
+# | fc00::100    | End.DT6 table 255 (local)        |
+# +--------------+----------------------------------+
+
+source lib.sh
+
+readonly SID="fc00::100"
+readonly DEST="cafe::1"
+
+readonly SRC_MAC="02:00:00:00:00:01"
+readonly RTR_R0_MAC="02:00:00:00:00:02"
+readonly RTR_R1_MAC="02:00:00:00:00:03"
+readonly DST_MAC="02:00:00:00:00:04"
+
+cleanup()
+{
+	cleanup_ns "${NS_SRC}" "${NS_RTR}" "${NS_DST}"
+}
+
+check_prerequisites()
+{
+	if ! command -v ip &>/dev/null; then
+		echo "SKIP: ip tool not found"
+		exit "${ksft_skip}"
+	fi
+
+	if ! command -v ping &>/dev/null; then
+		echo "SKIP: ping not found"
+		exit "${ksft_skip}"
+	fi
+
+	if ! command -v sysctl &>/dev/null; then
+		echo "SKIP: sysctl not found"
+		exit "${ksft_skip}"
+	fi
+
+	if ! command -v taskset &>/dev/null; then
+		echo "SKIP: taskset not found"
+		exit "${ksft_skip}"
+	fi
+}
+
+setup()
+{
+	setup_ns NS_SRC NS_RTR NS_DST
+
+	ip link add veth-s0 netns "${NS_SRC}" type veth \
+		peer name veth-r0 netns "${NS_RTR}"
+	ip link add veth-r1 netns "${NS_RTR}" type veth \
+		peer name veth-d0 netns "${NS_DST}"
+
+	ip -n "${NS_SRC}" link set veth-s0 address "${SRC_MAC}"
+	ip -n "${NS_RTR}" link set veth-r0 address "${RTR_R0_MAC}"
+	ip -n "${NS_RTR}" link set veth-r1 address "${RTR_R1_MAC}"
+	ip -n "${NS_DST}" link set veth-d0 address "${DST_MAC}"
+
+	# ns_src
+	ip -n "${NS_SRC}" link set veth-s0 up
+	ip -n "${NS_SRC}" addr add fd00::1/64 dev veth-s0 nodad
+	ip -n "${NS_SRC}" -6 route add "${DEST}"/128 via fd00::2
+
+	# ns_router
+	ip -n "${NS_RTR}" link set veth-r0 up
+	ip -n "${NS_RTR}" addr add fd00::2/64 dev veth-r0 nodad
+	ip -n "${NS_RTR}" link set veth-r1 up
+	ip -n "${NS_RTR}" addr add fd01::1/64 dev veth-r1 nodad
+	ip netns exec "${NS_RTR}" sysctl -qw net.ipv6.conf.all.forwarding=1
+
+	ip -n "${NS_RTR}" -6 route add "${DEST}"/128 \
+		encap seg6 mode encap segs "${SID}" dev veth-r0
+	ip -n "${NS_RTR}" -6 route add "${SID}"/128 table 100 \
+		via fd01::2 dev veth-r1
+	ip -n "${NS_RTR}" -6 route add blackhole "${SID}"/128
+	ip -n "${NS_RTR}" -6 rule add iif veth-r0 lookup 100
+
+	# ns_dst
+	ip -n "${NS_DST}" link set veth-d0 up
+	ip -n "${NS_DST}" addr add fd01::2/64 dev veth-d0 nodad
+	ip -n "${NS_DST}" addr add "${DEST}"/128 dev lo nodad
+	ip -n "${NS_DST}" -6 route add "${SID}"/128 \
+		encap seg6local action End.DT6 table 255 dev veth-d0
+	ip -n "${NS_DST}" -6 route add fd00::/64 via fd01::1
+
+	# static neighbors
+	ip -n "${NS_SRC}" -6 neigh add fd00::2 dev veth-s0 \
+		lladdr "${RTR_R0_MAC}" nud permanent
+	ip -n "${NS_RTR}" -6 neigh add fd00::1 dev veth-r0 \
+		lladdr "${SRC_MAC}" nud permanent
+	ip -n "${NS_RTR}" -6 neigh add fd01::2 dev veth-r1 \
+		lladdr "${DST_MAC}" nud permanent
+	ip -n "${NS_DST}" -6 neigh add fd01::1 dev veth-d0 \
+		lladdr "${RTR_R1_MAC}" nud permanent
+}
+
+test_cache_isolation()
+{
+	RET=0
+
+	# local ping with empty cache: must fail (SID is blackholed)
+	if ip netns exec "${NS_RTR}" taskset -c 0 \
+			ping -c 1 -W 2 "${DEST}" &>/dev/null; then
+		echo "SKIP: local ping succeeded, topology broken"
+		exit "${ksft_skip}"
+	fi
+
+	# forward from ns_src to populate the input cache
+	if ! ip netns exec "${NS_SRC}" taskset -c 0 \
+			ping -c 1 -W 2 "${DEST}" &>/dev/null; then
+		echo "SKIP: forwarded ping failed, topology broken"
+		exit "${ksft_skip}"
+	fi
+
+	# local ping again: must still fail; if the output path reuses
+	# the input cache, it bypasses the blackhole and the ping succeeds
+	if ip netns exec "${NS_RTR}" taskset -c 0 \
+			ping -c 1 -W 2 "${DEST}" &>/dev/null; then
+		echo "FAIL: output path used dst cached by input path"
+		RET="${ksft_fail}"
+	else
+		echo "PASS: output path dst_cache is independent"
+	fi
+
+	return "${RET}"
+}
+
+if [ "$(id -u)" -ne 0 ]; then
+	echo "SKIP: Need root privileges"
+	exit "${ksft_skip}"
+fi
+
+trap cleanup EXIT
+
+check_prerequisites
+setup
+test_cache_isolation
+exit "${RET}"