Merge tag 'net-6.2-final' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net

Pull networking fixes from Jakub Kicinski:
 "Fixes from the main networking tree only, probably because all
  sub-trees have backed off and haven't submitted their changes.

  None of the fixes here are particularly scary and no outstanding
  regressions. In an ideal world the "current release" sections would be
  empty at this stage but that never happens.

  Current release - regressions:

   - fix unwanted sign extension in netdev_stats_to_stats64()

  Current release - new code bugs:

   - initialize net->notrefcnt_tracker earlier

   - devlink: fix netdev notifier chain corruption

   - nfp: make sure mbox accesses in IPsec code are atomic

   - ice: fix check for weight and priority of a scheduling node

  Previous releases - regressions:

   - ice: xsk: fix cleaning of XDP_TX frame, prevent inf loop

   - igb: fix I2C bit banging config with external thermal sensor

  Previous releases - always broken:

   - sched: tcindex: update imperfect hash filters respecting rcu

   - mpls: fix stale pointer if allocation fails during device rename

   - dccp/tcp: avoid negative sk_forward_alloc by ipv6_pinfo.pktoptions

   - remove WARN_ON_ONCE(sk->sk_forward_alloc) from
     sk_stream_kill_queues()

   - af_key: fix heap information leak

   - ipv6: fix socket connection with DSCP (correct interpretation of
     the tclass field vs fib rule matching)

   - tipc: fix kernel warning when sending SYN message

   - vmxnet3: read RSS information from the correct descriptor (eop)"

* tag 'net-6.2-final' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net: (35 commits)
  devlink: Fix netdev notifier chain corruption
  igb: conditionalize I2C bit banging on external thermal sensor support
  net: mpls: fix stale pointer if allocation fails during device rename
  net/sched: tcindex: search key must be 16 bits
  tipc: fix kernel warning when sending SYN message
  igb: Fix PPS input and output using 3rd and 4th SDP
  net: use a bounce buffer for copying skb->mark
  ixgbe: add double of VLAN header when computing the max MTU
  i40e: add double of VLAN header when computing the max MTU
  ixgbe: allow to increase MTU to 3K with XDP enabled
  net: stmmac: Restrict warning on disabling DMA store and fwd mode
  net/sched: act_ctinfo: use percpu stats
  net: stmmac: fix order of dwmac5 FlexPPS parametrization sequence
  ice: fix lost multicast packets in promisc mode
  ice: Fix check for weight and priority of a scheduling node
  bnxt_en: Fix mqprio and XDP ring checking logic
  net: Fix unwanted sign extension in netdev_stats_to_stats64()
  net/usb: kalmia: Don't pass act_len in usb_bulk_msg error path
  net: openvswitch: fix possible memory leak in ovs_meter_cmd_set()
  af_key: Fix heap information leak
  ...

2 files changed, 177 insertions, 2 deletions

diff --git a/tools/testing/selftests/net/fib_rule_tests.sh b/tools/testing/selftests/net/fib_rule_tests.sh
index c245476fa29d..63c3eaec8d30 100755
--- a/tools/testing/selftests/net/fib_rule_tests.sh
+++ b/tools/testing/selftests/net/fib_rule_tests.sh
@@ -10,8 +10,10 @@ ret=0
 
 PAUSE_ON_FAIL=${PAUSE_ON_FAIL:=no}
 IP="ip -netns testns"
+IP_PEER="ip -netns peerns"
 
 RTABLE=100
+RTABLE_PEER=101
 GW_IP4=192.51.100.2
 SRC_IP=192.51.100.3
 GW_IP6=2001:db8:1::2
@@ -20,7 +22,9 @@ SRC_IP6=2001:db8:1::3
 DEV_ADDR=192.51.100.1
 DEV_ADDR6=2001:db8:1::1
 DEV=dummy0
-TESTS="fib_rule6 fib_rule4"
+TESTS="fib_rule6 fib_rule4 fib_rule6_connect fib_rule4_connect"
+
+SELFTEST_PATH=""
 
 log_test()
 {
@@ -52,6 +56,31 @@ log_section()
 	echo "######################################################################"
 }
 
+check_nettest()
+{
+	if which nettest > /dev/null 2>&1; then
+		return 0
+	fi
+
+	# Add the selftest directory to PATH if not already done
+	if [ "${SELFTEST_PATH}" = "" ]; then
+		SELFTEST_PATH="$(dirname $0)"
+		PATH="${PATH}:${SELFTEST_PATH}"
+
+		# Now retry with the new path
+		if which nettest > /dev/null 2>&1; then
+			return 0
+		fi
+
+		if [ "${ret}" -eq 0 ]; then
+			ret="${ksft_skip}"
+		fi
+		echo "nettest not found (try 'make -C ${SELFTEST_PATH} nettest')"
+	fi
+
+	return 1
+}
+
 setup()
 {
 	set -e
@@ -72,6 +101,39 @@ cleanup()
 	ip netns del testns
 }
 
+setup_peer()
+{
+	set -e
+
+	ip netns add peerns
+	$IP_PEER link set dev lo up
+
+	ip link add name veth0 netns testns type veth \
+		peer name veth1 netns peerns
+	$IP link set dev veth0 up
+	$IP_PEER link set dev veth1 up
+
+	$IP address add 192.0.2.10 peer 192.0.2.11/32 dev veth0
+	$IP_PEER address add 192.0.2.11 peer 192.0.2.10/32 dev veth1
+
+	$IP address add 2001:db8::10 peer 2001:db8::11/128 dev veth0 nodad
+	$IP_PEER address add 2001:db8::11 peer 2001:db8::10/128 dev veth1 nodad
+
+	$IP_PEER address add 198.51.100.11/32 dev lo
+	$IP route add table $RTABLE_PEER 198.51.100.11/32 via 192.0.2.11
+
+	$IP_PEER address add 2001:db8::1:11/128 dev lo
+	$IP route add table $RTABLE_PEER 2001:db8::1:11/128 via 2001:db8::11
+
+	set +e
+}
+
+cleanup_peer()
+{
+	$IP link del dev veth0
+	ip netns del peerns
+}
+
 fib_check_iproute_support()
 {
 	ip rule help 2>&1 | grep -q $1
@@ -190,6 +252,37 @@ fib_rule6_test()
 	fi
 }
 
+# Verify that the IPV6_TCLASS option of UDPv6 and TCPv6 sockets is properly
+# taken into account when connecting the socket and when sending packets.
+fib_rule6_connect_test()
+{
+	local dsfield
+
+	if ! check_nettest; then
+		echo "SKIP: Could not run test without nettest tool"
+		return
+	fi
+
+	setup_peer
+	$IP -6 rule add dsfield 0x04 table $RTABLE_PEER
+
+	# Combine the base DS Field value (0x04) with all possible ECN values
+	# (Not-ECT: 0, ECT(1): 1, ECT(0): 2, CE: 3).
+	# The ECN bits shouldn't influence the result of the test.
+	for dsfield in 0x04 0x05 0x06 0x07; do
+		nettest -q -6 -B -t 5 -N testns -O peerns -U -D \
+			-Q "${dsfield}" -l 2001:db8::1:11 -r 2001:db8::1:11
+		log_test $? 0 "rule6 dsfield udp connect (dsfield ${dsfield})"
+
+		nettest -q -6 -B -t 5 -N testns -O peerns -Q "${dsfield}" \
+			-l 2001:db8::1:11 -r 2001:db8::1:11
+		log_test $? 0 "rule6 dsfield tcp connect (dsfield ${dsfield})"
+	done
+
+	$IP -6 rule del dsfield 0x04 table $RTABLE_PEER
+	cleanup_peer
+}
+
 fib_rule4_del()
 {
 	$IP rule del $1
@@ -296,6 +389,37 @@ fib_rule4_test()
 	fi
 }
 
+# Verify that the IP_TOS option of UDPv4 and TCPv4 sockets is properly taken
+# into account when connecting the socket and when sending packets.
+fib_rule4_connect_test()
+{
+	local dsfield
+
+	if ! check_nettest; then
+		echo "SKIP: Could not run test without nettest tool"
+		return
+	fi
+
+	setup_peer
+	$IP -4 rule add dsfield 0x04 table $RTABLE_PEER
+
+	# Combine the base DS Field value (0x04) with all possible ECN values
+	# (Not-ECT: 0, ECT(1): 1, ECT(0): 2, CE: 3).
+	# The ECN bits shouldn't influence the result of the test.
+	for dsfield in 0x04 0x05 0x06 0x07; do
+		nettest -q -B -t 5 -N testns -O peerns -D -U -Q "${dsfield}" \
+			-l 198.51.100.11 -r 198.51.100.11
+		log_test $? 0 "rule4 dsfield udp connect (dsfield ${dsfield})"
+
+		nettest -q -B -t 5 -N testns -O peerns -Q "${dsfield}" \
+			-l 198.51.100.11 -r 198.51.100.11
+		log_test $? 0 "rule4 dsfield tcp connect (dsfield ${dsfield})"
+	done
+
+	$IP -4 rule del dsfield 0x04 table $RTABLE_PEER
+	cleanup_peer
+}
+
 run_fibrule_tests()
 {
 	log_section "IPv4 fib rule"
@@ -345,6 +469,8 @@ do
 	case $t in
 	fib_rule6_test|fib_rule6)		fib_rule6_test;;
 	fib_rule4_test|fib_rule4)		fib_rule4_test;;
+	fib_rule6_connect_test|fib_rule6_connect)	fib_rule6_connect_test;;
+	fib_rule4_connect_test|fib_rule4_connect)	fib_rule4_connect_test;;
 
 	help) echo "Test names: $TESTS"; exit 0;;
 
diff --git a/tools/testing/selftests/net/nettest.c b/tools/testing/selftests/net/nettest.c
index 7900fa98eccb..ee9a72982705 100644
--- a/tools/testing/selftests/net/nettest.c
+++ b/tools/testing/selftests/net/nettest.c
@@ -87,6 +87,7 @@ struct sock_args {
 	int use_setsockopt;
 	int use_freebind;
 	int use_cmsg;
+	uint8_t dsfield;
 	const char *dev;
 	const char *server_dev;
 	int ifindex;
@@ -580,6 +581,36 @@ static int set_reuseaddr(int sd)
 	return rc;
 }
 
+static int set_dsfield(int sd, int version, int dsfield)
+{
+	if (!dsfield)
+		return 0;
+
+	switch (version) {
+	case AF_INET:
+		if (setsockopt(sd, SOL_IP, IP_TOS, &dsfield,
+			       sizeof(dsfield)) < 0) {
+			log_err_errno("setsockopt(IP_TOS)");
+			return -1;
+		}
+		break;
+
+	case AF_INET6:
+		if (setsockopt(sd, SOL_IPV6, IPV6_TCLASS, &dsfield,
+			       sizeof(dsfield)) < 0) {
+			log_err_errno("setsockopt(IPV6_TCLASS)");
+			return -1;
+		}
+		break;
+
+	default:
+		log_error("Invalid address family\n");
+		return -1;
+	}
+
+	return 0;
+}
+
 static int str_to_uint(const char *str, int min, int max, unsigned int *value)
 {
 	int number;
@@ -1317,6 +1348,9 @@ static int msock_init(struct sock_args *args, int server)
 		       (char *)&one, sizeof(one)) < 0)
 		log_err_errno("Setting SO_BROADCAST error");
 
+	if (set_dsfield(sd, AF_INET, args->dsfield) != 0)
+		goto out_err;
+
 	if (args->dev && bind_to_device(sd, args->dev) != 0)
 		goto out_err;
 	else if (args->use_setsockopt &&
@@ -1445,6 +1479,9 @@ static int lsock_init(struct sock_args *args)
 	if (set_reuseport(sd) != 0)
 		goto err;
 
+	if (set_dsfield(sd, args->version, args->dsfield) != 0)
+		goto err;
+
 	if (args->dev && bind_to_device(sd, args->dev) != 0)
 		goto err;
 	else if (args->use_setsockopt &&
@@ -1658,6 +1695,9 @@ static int connectsock(void *addr, socklen_t alen, struct sock_args *args)
 	if (set_reuseport(sd) != 0)
 		goto err;
 
+	if (set_dsfield(sd, args->version, args->dsfield) != 0)
+		goto err;
+
 	if (args->dev && bind_to_device(sd, args->dev) != 0)
 		goto err;
 	else if (args->use_setsockopt &&
@@ -1862,7 +1902,7 @@ static int ipc_parent(int cpid, int fd, struct sock_args *args)
 	return client_status;
 }
 
-#define GETOPT_STR  "sr:l:c:p:t:g:P:DRn:M:X:m:d:I:BN:O:SUCi6xL:0:1:2:3:Fbqf"
+#define GETOPT_STR  "sr:l:c:Q:p:t:g:P:DRn:M:X:m:d:I:BN:O:SUCi6xL:0:1:2:3:Fbqf"
 #define OPT_FORCE_BIND_KEY_IFINDEX 1001
 #define OPT_NO_BIND_KEY_IFINDEX 1002
 
@@ -1893,6 +1933,8 @@ static void print_usage(char *prog)
 	"    -D|R          datagram (D) / raw (R) socket (default stream)\n"
 	"    -l addr       local address to bind to in server mode\n"
 	"    -c addr       local address to bind to in client mode\n"
+	"    -Q dsfield    DS Field value of the socket (the IP_TOS or\n"
+	"                  IPV6_TCLASS socket option)\n"
 	"    -x            configure XFRM policy on socket\n"
 	"\n"
 	"    -d dev        bind socket to given device name\n"
@@ -1971,6 +2013,13 @@ int main(int argc, char *argv[])
 			args.has_local_ip = 1;
 			args.client_local_addr_str = optarg;
 			break;
+		case 'Q':
+			if (str_to_uint(optarg, 0, 255, &tmp) != 0) {
+				fprintf(stderr, "Invalid DS Field\n");
+				return 1;
+			}
+			args.dsfield = tmp;
+			break;
 		case 'p':
 			if (str_to_uint(optarg, 1, 65535, &tmp) != 0) {
 				fprintf(stderr, "Invalid port\n");