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

Cross-merge networking fixes after downstream PR.

No conflicts (or adjacent changes of note).

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

4 files changed, 292 insertions, 18 deletions

diff --git a/tools/testing/selftests/netfilter/Makefile b/tools/testing/selftests/netfilter/Makefile
index 321db8850da0..ef90aca4cc96 100644
--- a/tools/testing/selftests/netfilter/Makefile
+++ b/tools/testing/selftests/netfilter/Makefile
@@ -6,13 +6,14 @@ 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 rpath.sh nft_audit.sh
+	conntrack_vrf.sh nft_synproxy.sh rpath.sh nft_audit.sh \
+	conntrack_sctp_collision.sh
 
 HOSTPKG_CONFIG := pkg-config
 
 CFLAGS += $(shell $(HOSTPKG_CONFIG) --cflags libmnl 2>/dev/null)
 LDLIBS += $(shell $(HOSTPKG_CONFIG) --libs libmnl 2>/dev/null || echo -lmnl)
 
-TEST_GEN_FILES =  nf-queue connect_close audit_logread
+TEST_GEN_FILES =  nf-queue connect_close audit_logread sctp_collision
 
 include ../lib.mk
diff --git a/tools/testing/selftests/netfilter/conntrack_sctp_collision.sh b/tools/testing/selftests/netfilter/conntrack_sctp_collision.sh
new file mode 100755
index 000000000000..a924e595cfd8
--- /dev/null
+++ b/tools/testing/selftests/netfilter/conntrack_sctp_collision.sh
@@ -0,0 +1,89 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+#
+# Testing For SCTP COLLISION SCENARIO as Below:
+#
+#   14:35:47.655279 IP CLIENT_IP.PORT > SERVER_IP.PORT: sctp (1) [INIT] [init tag: 2017837359]
+#   14:35:48.353250 IP SERVER_IP.PORT > CLIENT_IP.PORT: sctp (1) [INIT] [init tag: 1187206187]
+#   14:35:48.353275 IP CLIENT_IP.PORT > SERVER_IP.PORT: sctp (1) [INIT ACK] [init tag: 2017837359]
+#   14:35:48.353283 IP SERVER_IP.PORT > CLIENT_IP.PORT: sctp (1) [COOKIE ECHO]
+#   14:35:48.353977 IP CLIENT_IP.PORT > SERVER_IP.PORT: sctp (1) [COOKIE ACK]
+#   14:35:48.855335 IP SERVER_IP.PORT > CLIENT_IP.PORT: sctp (1) [INIT ACK] [init tag: 164579970]
+#
+# TOPO: SERVER_NS (link0)<--->(link1) ROUTER_NS (link2)<--->(link3) CLIENT_NS
+
+CLIENT_NS=$(mktemp -u client-XXXXXXXX)
+CLIENT_IP="198.51.200.1"
+CLIENT_PORT=1234
+
+SERVER_NS=$(mktemp -u server-XXXXXXXX)
+SERVER_IP="198.51.100.1"
+SERVER_PORT=1234
+
+ROUTER_NS=$(mktemp -u router-XXXXXXXX)
+CLIENT_GW="198.51.200.2"
+SERVER_GW="198.51.100.2"
+
+# setup the topo
+setup() {
+	ip net add $CLIENT_NS
+	ip net add $SERVER_NS
+	ip net add $ROUTER_NS
+	ip -n $SERVER_NS link add link0 type veth peer name link1 netns $ROUTER_NS
+	ip -n $CLIENT_NS link add link3 type veth peer name link2 netns $ROUTER_NS
+
+	ip -n $SERVER_NS link set link0 up
+	ip -n $SERVER_NS addr add $SERVER_IP/24 dev link0
+	ip -n $SERVER_NS route add $CLIENT_IP dev link0 via $SERVER_GW
+
+	ip -n $ROUTER_NS link set link1 up
+	ip -n $ROUTER_NS link set link2 up
+	ip -n $ROUTER_NS addr add $SERVER_GW/24 dev link1
+	ip -n $ROUTER_NS addr add $CLIENT_GW/24 dev link2
+	ip net exec $ROUTER_NS sysctl -wq net.ipv4.ip_forward=1
+
+	ip -n $CLIENT_NS link set link3 up
+	ip -n $CLIENT_NS addr add $CLIENT_IP/24 dev link3
+	ip -n $CLIENT_NS route add $SERVER_IP dev link3 via $CLIENT_GW
+
+	# simulate the delay on OVS upcall by setting up a delay for INIT_ACK with
+	# tc on $SERVER_NS side
+	tc -n $SERVER_NS qdisc add dev link0 root handle 1: htb
+	tc -n $SERVER_NS class add dev link0 parent 1: classid 1:1 htb rate 100mbit
+	tc -n $SERVER_NS filter add dev link0 parent 1: protocol ip u32 match ip protocol 132 \
+		0xff match u8 2 0xff at 32 flowid 1:1
+	tc -n $SERVER_NS qdisc add dev link0 parent 1:1 handle 10: netem delay 1200ms
+
+	# simulate the ctstate check on OVS nf_conntrack
+	ip net exec $ROUTER_NS iptables -A FORWARD -m state --state INVALID,UNTRACKED -j DROP
+	ip net exec $ROUTER_NS iptables -A INPUT -p sctp -j DROP
+
+	# use a smaller number for assoc's max_retrans to reproduce the issue
+	modprobe sctp
+	ip net exec $CLIENT_NS sysctl -wq net.sctp.association_max_retrans=3
+}
+
+cleanup() {
+	ip net exec $CLIENT_NS pkill sctp_collision 2>&1 >/dev/null
+	ip net exec $SERVER_NS pkill sctp_collision 2>&1 >/dev/null
+	ip net del "$CLIENT_NS"
+	ip net del "$SERVER_NS"
+	ip net del "$ROUTER_NS"
+}
+
+do_test() {
+	ip net exec $SERVER_NS ./sctp_collision server \
+		$SERVER_IP $SERVER_PORT $CLIENT_IP $CLIENT_PORT &
+	ip net exec $CLIENT_NS ./sctp_collision client \
+		$CLIENT_IP $CLIENT_PORT $SERVER_IP $SERVER_PORT
+}
+
+# NOTE: one way to work around the issue is set a smaller hb_interval
+# ip net exec $CLIENT_NS sysctl -wq net.sctp.hb_interval=3500
+
+# run the test case
+trap cleanup EXIT
+setup && \
+echo "Test for SCTP Collision in nf_conntrack:" && \
+do_test && echo "PASS!"
+exit $?
diff --git a/tools/testing/selftests/netfilter/nft_audit.sh b/tools/testing/selftests/netfilter/nft_audit.sh
index 83c271b1c735..bb34329e02a7 100755
--- a/tools/testing/selftests/netfilter/nft_audit.sh
+++ b/tools/testing/selftests/netfilter/nft_audit.sh
@@ -12,10 +12,11 @@ nft --version >/dev/null 2>&1 || {
 }
 
 logfile=$(mktemp)
+rulefile=$(mktemp)
 echo "logging into $logfile"
 ./audit_logread >"$logfile" &
 logread_pid=$!
-trap 'kill $logread_pid; rm -f $logfile' EXIT
+trap 'kill $logread_pid; rm -f $logfile $rulefile' EXIT
 exec 3<"$logfile"
 
 do_test() { # (cmd, log)
@@ -26,12 +27,14 @@ do_test() { # (cmd, log)
 	res=$(diff -a -u <(echo "$2") - <&3)
 	[ $? -eq 0 ] && { echo "OK"; return; }
 	echo "FAIL"
-	echo "$res"
-	((RC++))
+	grep -v '^\(---\|+++\|@@\)' <<< "$res"
+	((RC--))
 }
 
 nft flush ruleset
 
+# adding tables, chains and rules
+
 for table in t1 t2; do
 	do_test "nft add table $table" \
 	"table=$table family=2 entries=1 op=nft_register_table"
@@ -62,6 +65,48 @@ for table in t1 t2; do
 	"table=$table family=2 entries=6 op=nft_register_rule"
 done
 
+for ((i = 0; i < 500; i++)); do
+	echo "add rule t2 c3 counter accept comment \"rule $i\""
+done >$rulefile
+do_test "nft -f $rulefile" \
+'table=t2 family=2 entries=500 op=nft_register_rule'
+
+# adding sets and elements
+
+settype='type inet_service; counter'
+setelem='{ 22, 80, 443 }'
+setblock="{ $settype; elements = $setelem; }"
+do_test "nft add set t1 s $setblock" \
+"table=t1 family=2 entries=4 op=nft_register_set"
+
+do_test "nft add set t1 s2 $setblock; add set t1 s3 { $settype; }" \
+"table=t1 family=2 entries=5 op=nft_register_set"
+
+do_test "nft add element t1 s3 $setelem" \
+"table=t1 family=2 entries=3 op=nft_register_setelem"
+
+# adding counters
+
+do_test 'nft add counter t1 c1' \
+'table=t1 family=2 entries=1 op=nft_register_obj'
+
+do_test 'nft add counter t2 c1; add counter t2 c2' \
+'table=t2 family=2 entries=2 op=nft_register_obj'
+
+# adding/updating quotas
+
+do_test 'nft add quota t1 q1 { 10 bytes }' \
+'table=t1 family=2 entries=1 op=nft_register_obj'
+
+do_test 'nft add quota t2 q1 { 10 bytes }; add quota t2 q2 { 10 bytes }' \
+'table=t2 family=2 entries=2 op=nft_register_obj'
+
+# changing the quota value triggers obj update path
+do_test 'nft add quota t1 q1 { 20 bytes }' \
+'table=t1 family=2 entries=1 op=nft_register_obj'
+
+# resetting rules
+
 do_test 'nft reset rules t1 c2' \
 'table=t1 family=2 entries=3 op=nft_reset_rule'
 
@@ -70,19 +115,6 @@ do_test 'nft reset rules table t1' \
 table=t1 family=2 entries=3 op=nft_reset_rule
 table=t1 family=2 entries=3 op=nft_reset_rule'
 
-do_test 'nft reset rules' \
-'table=t1 family=2 entries=3 op=nft_reset_rule
-table=t1 family=2 entries=3 op=nft_reset_rule
-table=t1 family=2 entries=3 op=nft_reset_rule
-table=t2 family=2 entries=3 op=nft_reset_rule
-table=t2 family=2 entries=3 op=nft_reset_rule
-table=t2 family=2 entries=3 op=nft_reset_rule'
-
-for ((i = 0; i < 500; i++)); do
-	echo "add rule t2 c3 counter accept comment \"rule $i\""
-done | do_test 'nft -f -' \
-'table=t2 family=2 entries=500 op=nft_register_rule'
-
 do_test 'nft reset rules t2 c3' \
 'table=t2 family=2 entries=189 op=nft_reset_rule
 table=t2 family=2 entries=188 op=nft_reset_rule
@@ -105,4 +137,57 @@ table=t2 family=2 entries=180 op=nft_reset_rule
 table=t2 family=2 entries=188 op=nft_reset_rule
 table=t2 family=2 entries=135 op=nft_reset_rule'
 
+# resetting sets and elements
+
+elem=(22 ,80 ,443)
+relem=""
+for i in {1..3}; do
+	relem+="${elem[((i - 1))]}"
+	do_test "nft reset element t1 s { $relem }" \
+	"table=t1 family=2 entries=$i op=nft_reset_setelem"
+done
+
+do_test 'nft reset set t1 s' \
+'table=t1 family=2 entries=3 op=nft_reset_setelem'
+
+# deleting rules
+
+readarray -t handles < <(nft -a list chain t1 c1 | \
+			 sed -n 's/.*counter.* handle \(.*\)$/\1/p')
+
+do_test "nft delete rule t1 c1 handle ${handles[0]}" \
+'table=t1 family=2 entries=1 op=nft_unregister_rule'
+
+cmd='delete rule t1 c1 handle'
+do_test "nft $cmd ${handles[1]}; $cmd ${handles[2]}" \
+'table=t1 family=2 entries=2 op=nft_unregister_rule'
+
+do_test 'nft flush chain t1 c2' \
+'table=t1 family=2 entries=3 op=nft_unregister_rule'
+
+do_test 'nft flush table t2' \
+'table=t2 family=2 entries=509 op=nft_unregister_rule'
+
+# deleting chains
+
+do_test 'nft delete chain t2 c2' \
+'table=t2 family=2 entries=1 op=nft_unregister_chain'
+
+# deleting sets and elements
+
+do_test 'nft delete element t1 s { 22 }' \
+'table=t1 family=2 entries=1 op=nft_unregister_setelem'
+
+do_test 'nft delete element t1 s { 80, 443 }' \
+'table=t1 family=2 entries=2 op=nft_unregister_setelem'
+
+do_test 'nft flush set t1 s2' \
+'table=t1 family=2 entries=3 op=nft_unregister_setelem'
+
+do_test 'nft delete set t1 s2' \
+'table=t1 family=2 entries=1 op=nft_unregister_set'
+
+do_test 'nft delete set t1 s3' \
+'table=t1 family=2 entries=1 op=nft_unregister_set'
+
 exit $RC
diff --git a/tools/testing/selftests/netfilter/sctp_collision.c b/tools/testing/selftests/netfilter/sctp_collision.c
new file mode 100644
index 000000000000..21bb1cfd8a85
--- /dev/null
+++ b/tools/testing/selftests/netfilter/sctp_collision.c
@@ -0,0 +1,99 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <unistd.h>
+#include <arpa/inet.h>
+
+int main(int argc, char *argv[])
+{
+	struct sockaddr_in saddr = {}, daddr = {};
+	int sd, ret, len = sizeof(daddr);
+	struct timeval tv = {25, 0};
+	char buf[] = "hello";
+
+	if (argc != 6 || (strcmp(argv[1], "server") && strcmp(argv[1], "client"))) {
+		printf("%s <server|client> <LOCAL_IP> <LOCAL_PORT> <REMOTE_IP> <REMOTE_PORT>\n",
+		       argv[0]);
+		return -1;
+	}
+
+	sd = socket(AF_INET, SOCK_SEQPACKET, IPPROTO_SCTP);
+	if (sd < 0) {
+		printf("Failed to create sd\n");
+		return -1;
+	}
+
+	saddr.sin_family = AF_INET;
+	saddr.sin_addr.s_addr = inet_addr(argv[2]);
+	saddr.sin_port = htons(atoi(argv[3]));
+
+	ret = bind(sd, (struct sockaddr *)&saddr, sizeof(saddr));
+	if (ret < 0) {
+		printf("Failed to bind to address\n");
+		goto out;
+	}
+
+	ret = listen(sd, 5);
+	if (ret < 0) {
+		printf("Failed to listen on port\n");
+		goto out;
+	}
+
+	daddr.sin_family = AF_INET;
+	daddr.sin_addr.s_addr = inet_addr(argv[4]);
+	daddr.sin_port = htons(atoi(argv[5]));
+
+	/* make test shorter than 25s */
+	ret = setsockopt(sd, SOL_SOCKET, SO_RCVTIMEO, &tv, sizeof(tv));
+	if (ret < 0) {
+		printf("Failed to setsockopt SO_RCVTIMEO\n");
+		goto out;
+	}
+
+	if (!strcmp(argv[1], "server")) {
+		sleep(1); /* wait a bit for client's INIT */
+		ret = connect(sd, (struct sockaddr *)&daddr, len);
+		if (ret < 0) {
+			printf("Failed to connect to peer\n");
+			goto out;
+		}
+		ret = recvfrom(sd, buf, sizeof(buf), 0, (struct sockaddr *)&daddr, &len);
+		if (ret < 0) {
+			printf("Failed to recv msg %d\n", ret);
+			goto out;
+		}
+		ret = sendto(sd, buf, strlen(buf) + 1, 0, (struct sockaddr *)&daddr, len);
+		if (ret < 0) {
+			printf("Failed to send msg %d\n", ret);
+			goto out;
+		}
+		printf("Server: sent! %d\n", ret);
+	}
+
+	if (!strcmp(argv[1], "client")) {
+		usleep(300000); /* wait a bit for server's listening */
+		ret = connect(sd, (struct sockaddr *)&daddr, len);
+		if (ret < 0) {
+			printf("Failed to connect to peer\n");
+			goto out;
+		}
+		sleep(1); /* wait a bit for server's delayed INIT_ACK to reproduce the issue */
+		ret = sendto(sd, buf, strlen(buf) + 1, 0, (struct sockaddr *)&daddr, len);
+		if (ret < 0) {
+			printf("Failed to send msg %d\n", ret);
+			goto out;
+		}
+		ret = recvfrom(sd, buf, sizeof(buf), 0, (struct sockaddr *)&daddr, &len);
+		if (ret < 0) {
+			printf("Failed to recv msg %d\n", ret);
+			goto out;
+		}
+		printf("Client: rcvd! %d\n", ret);
+	}
+	ret = 0;
+out:
+	close(sd);
+	return ret;
+}