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

Pull networking fixes from David Miller:

 1) Sanity check URB networking device parameters to avoid divide by
    zero, from Oliver Neukum.

 2) Disable global multicast filter in NCSI, otherwise LLDP and IPV6
    don't work properly. Longer term this needs a better fix tho. From
    Vijay Khemka.

 3) Small fixes to selftests (use ping when ping6 is not present, etc.)
    from David Ahern.

 4) Bring back rt_uses_gateway member of struct rtable, it's semantics
    were not well understood and trying to remove it broke things. From
    David Ahern.

 5) Move usbnet snaity checking, ignore endpoints with invalid
    wMaxPacketSize. From Bjørn Mork.

 6) Missing Kconfig deps for sja1105 driver, from Mao Wenan.

 7) Various small fixes to the mlx5 DR steering code, from Alaa Hleihel,
    Alex Vesker, and Yevgeny Kliteynik

 8) Missing CAP_NET_RAW checks in various places, from Ori Nimron.

 9) Fix crash when removing sch_cbs entry while offloading is enabled,
    from Vinicius Costa Gomes.

10) Signedness bug fixes, generally in looking at the result given by
    of_get_phy_mode() and friends. From Dan Crapenter.

11) Disable preemption around BPF_PROG_RUN() calls, from Eric Dumazet.

12) Don't create VRF ipv6 rules if ipv6 is disabled, from David Ahern.

13) Fix quantization code in tcp_bbr, from Kevin Yang.

* git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net: (127 commits)
  net: tap: clean up an indentation issue
  nfp: abm: fix memory leak in nfp_abm_u32_knode_replace
  tcp: better handle TCP_USER_TIMEOUT in SYN_SENT state
  sk_buff: drop all skb extensions on free and skb scrubbing
  tcp_bbr: fix quantization code to not raise cwnd if not probing bandwidth
  mlxsw: spectrum_flower: Fail in case user specifies multiple mirror actions
  Documentation: Clarify trap's description
  mlxsw: spectrum: Clear VLAN filters during port initialization
  net: ena: clean up indentation issue
  NFC: st95hf: clean up indentation issue
  net: phy: micrel: add Asym Pause workaround for KSZ9021
  net: socionext: ave: Avoid using netdev_err() before calling register_netdev()
  ptp: correctly disable flags on old ioctls
  lib: dimlib: fix help text typos
  net: dsa: microchip: Always set regmap stride to 1
  nfp: flower: fix memory leak in nfp_flower_spawn_vnic_reprs
  nfp: flower: prevent memory leak in nfp_flower_spawn_phy_reprs
  net/sched: Set default of CONFIG_NET_TC_SKB_EXT to N
  vrf: Do not attempt to create IPv6 mcast rule if IPv6 is disabled
  net: sched: sch_sfb: don't call qdisc_put() while holding tree lock
  ...

9 files changed, 148 insertions, 32 deletions

diff --git a/tools/lib/bpf/btf_dump.c b/tools/lib/bpf/btf_dump.c
index 715967762312..ede55fec3618 100644
--- a/tools/lib/bpf/btf_dump.c
+++ b/tools/lib/bpf/btf_dump.c
@@ -48,6 +48,8 @@ struct btf_dump_type_aux_state {
 	__u8 fwd_emitted: 1;
 	/* whether unique non-duplicate name was already assigned */
 	__u8 name_resolved: 1;
+	/* whether type is referenced from any other type */
+	__u8 referenced: 1;
 };
 
 struct btf_dump {
@@ -173,6 +175,7 @@ void btf_dump__free(struct btf_dump *d)
 	free(d);
 }
 
+static int btf_dump_mark_referenced(struct btf_dump *d);
 static int btf_dump_order_type(struct btf_dump *d, __u32 id, bool through_ptr);
 static void btf_dump_emit_type(struct btf_dump *d, __u32 id, __u32 cont_id);
 
@@ -213,6 +216,11 @@ int btf_dump__dump_type(struct btf_dump *d, __u32 id)
 		/* VOID is special */
 		d->type_states[0].order_state = ORDERED;
 		d->type_states[0].emit_state = EMITTED;
+
+		/* eagerly determine referenced types for anon enums */
+		err = btf_dump_mark_referenced(d);
+		if (err)
+			return err;
 	}
 
 	d->emit_queue_cnt = 0;
@@ -226,6 +234,79 @@ int btf_dump__dump_type(struct btf_dump *d, __u32 id)
 	return 0;
 }
 
+/*
+ * Mark all types that are referenced from any other type. This is used to
+ * determine top-level anonymous enums that need to be emitted as an
+ * independent type declarations.
+ * Anonymous enums come in two flavors: either embedded in a struct's field
+ * definition, in which case they have to be declared inline as part of field
+ * type declaration; or as a top-level anonymous enum, typically used for
+ * declaring global constants. It's impossible to distinguish between two
+ * without knowning whether given enum type was referenced from other type:
+ * top-level anonymous enum won't be referenced by anything, while embedded
+ * one will.
+ */
+static int btf_dump_mark_referenced(struct btf_dump *d)
+{
+	int i, j, n = btf__get_nr_types(d->btf);
+	const struct btf_type *t;
+	__u16 vlen;
+
+	for (i = 1; i <= n; i++) {
+		t = btf__type_by_id(d->btf, i);
+		vlen = btf_vlen(t);
+
+		switch (btf_kind(t)) {
+		case BTF_KIND_INT:
+		case BTF_KIND_ENUM:
+		case BTF_KIND_FWD:
+			break;
+
+		case BTF_KIND_VOLATILE:
+		case BTF_KIND_CONST:
+		case BTF_KIND_RESTRICT:
+		case BTF_KIND_PTR:
+		case BTF_KIND_TYPEDEF:
+		case BTF_KIND_FUNC:
+		case BTF_KIND_VAR:
+			d->type_states[t->type].referenced = 1;
+			break;
+
+		case BTF_KIND_ARRAY: {
+			const struct btf_array *a = btf_array(t);
+
+			d->type_states[a->index_type].referenced = 1;
+			d->type_states[a->type].referenced = 1;
+			break;
+		}
+		case BTF_KIND_STRUCT:
+		case BTF_KIND_UNION: {
+			const struct btf_member *m = btf_members(t);
+
+			for (j = 0; j < vlen; j++, m++)
+				d->type_states[m->type].referenced = 1;
+			break;
+		}
+		case BTF_KIND_FUNC_PROTO: {
+			const struct btf_param *p = btf_params(t);
+
+			for (j = 0; j < vlen; j++, p++)
+				d->type_states[p->type].referenced = 1;
+			break;
+		}
+		case BTF_KIND_DATASEC: {
+			const struct btf_var_secinfo *v = btf_var_secinfos(t);
+
+			for (j = 0; j < vlen; j++, v++)
+				d->type_states[v->type].referenced = 1;
+			break;
+		}
+		default:
+			return -EINVAL;
+		}
+	}
+	return 0;
+}
 static int btf_dump_add_emit_queue_id(struct btf_dump *d, __u32 id)
 {
 	__u32 *new_queue;
@@ -395,7 +476,12 @@ static int btf_dump_order_type(struct btf_dump *d, __u32 id, bool through_ptr)
 	}
 	case BTF_KIND_ENUM:
 	case BTF_KIND_FWD:
-		if (t->name_off != 0) {
+		/*
+		 * non-anonymous or non-referenced enums are top-level
+		 * declarations and should be emitted. Same logic can be
+		 * applied to FWDs, it won't hurt anyways.
+		 */
+		if (t->name_off != 0 || !tstate->referenced) {
 			err = btf_dump_add_emit_queue_id(d, id);
 			if (err)
 				return err;
@@ -536,11 +622,6 @@ static void btf_dump_emit_type(struct btf_dump *d, __u32 id, __u32 cont_id)
 	t = btf__type_by_id(d->btf, id);
 	kind = btf_kind(t);
 
-	if (top_level_def && t->name_off == 0) {
-		pr_warning("unexpected nameless definition, id:[%u]\n", id);
-		return;
-	}
-
 	if (tstate->emit_state == EMITTING) {
 		if (tstate->fwd_emitted)
 			return;
@@ -1167,6 +1248,7 @@ static void btf_dump_emit_type_chain(struct btf_dump *d,
 				return;
 			}
 
+			next_id = decls->ids[decls->cnt - 1];
 			next_t = btf__type_by_id(d->btf, next_id);
 			multidim = btf_is_array(next_t);
 			/* we need space if we have named non-pointer */
diff --git a/tools/lib/bpf/xsk.c b/tools/lib/bpf/xsk.c
index 842c4fd55859..24fa313524fb 100644
--- a/tools/lib/bpf/xsk.c
+++ b/tools/lib/bpf/xsk.c
@@ -65,7 +65,6 @@ struct xsk_socket {
 	int xsks_map_fd;
 	__u32 queue_id;
 	char ifname[IFNAMSIZ];
-	bool zc;
 };
 
 struct xsk_nl_info {
@@ -491,7 +490,6 @@ int xsk_socket__create(struct xsk_socket **xsk_ptr, const char *ifname,
 	void *rx_map = NULL, *tx_map = NULL;
 	struct sockaddr_xdp sxdp = {};
 	struct xdp_mmap_offsets off;
-	struct xdp_options opts;
 	struct xsk_socket *xsk;
 	socklen_t optlen;
 	int err;
@@ -611,15 +609,6 @@ int xsk_socket__create(struct xsk_socket **xsk_ptr, const char *ifname,
 
 	xsk->prog_fd = -1;
 
-	optlen = sizeof(opts);
-	err = getsockopt(xsk->fd, SOL_XDP, XDP_OPTIONS, &opts, &optlen);
-	if (err) {
-		err = -errno;
-		goto out_mmap_tx;
-	}
-
-	xsk->zc = opts.flags & XDP_OPTIONS_ZEROCOPY;
-
 	if (!(xsk->config.libbpf_flags & XSK_LIBBPF_FLAGS__INHIBIT_PROG_LOAD)) {
 		err = xsk_setup_xdp_prog(xsk);
 		if (err)
diff --git a/tools/testing/selftests/bpf/prog_tests/tcp_rtt.c b/tools/testing/selftests/bpf/prog_tests/tcp_rtt.c
index fdc0b3614a9e..a82da555b1b0 100644
--- a/tools/testing/selftests/bpf/prog_tests/tcp_rtt.c
+++ b/tools/testing/selftests/bpf/prog_tests/tcp_rtt.c
@@ -203,14 +203,24 @@ static int start_server(void)
 	return fd;
 }
 
+static pthread_mutex_t server_started_mtx = PTHREAD_MUTEX_INITIALIZER;
+static pthread_cond_t server_started = PTHREAD_COND_INITIALIZER;
+
 static void *server_thread(void *arg)
 {
 	struct sockaddr_storage addr;
 	socklen_t len = sizeof(addr);
 	int fd = *(int *)arg;
 	int client_fd;
+	int err;
+
+	err = listen(fd, 1);
+
+	pthread_mutex_lock(&server_started_mtx);
+	pthread_cond_signal(&server_started);
+	pthread_mutex_unlock(&server_started_mtx);
 
-	if (CHECK_FAIL(listen(fd, 1)) < 0) {
+	if (CHECK_FAIL(err < 0)) {
 		perror("Failed to listed on socket");
 		return NULL;
 	}
@@ -248,7 +258,14 @@ void test_tcp_rtt(void)
 	if (CHECK_FAIL(server_fd < 0))
 		goto close_cgroup_fd;
 
-	pthread_create(&tid, NULL, server_thread, (void *)&server_fd);
+	if (CHECK_FAIL(pthread_create(&tid, NULL, server_thread,
+				      (void *)&server_fd)))
+		goto close_cgroup_fd;
+
+	pthread_mutex_lock(&server_started_mtx);
+	pthread_cond_wait(&server_started, &server_started_mtx);
+	pthread_mutex_unlock(&server_started_mtx);
+
 	CHECK_FAIL(run_test(cgroup_fd, server_fd));
 	close(server_fd);
 close_cgroup_fd:
diff --git a/tools/testing/selftests/bpf/progs/strobemeta.h b/tools/testing/selftests/bpf/progs/strobemeta.h
index 8a399bdfd920..067eb625d01c 100644
--- a/tools/testing/selftests/bpf/progs/strobemeta.h
+++ b/tools/testing/selftests/bpf/progs/strobemeta.h
@@ -413,7 +413,10 @@ static __always_inline void *read_map_var(struct strobemeta_cfg *cfg,
 #else
 #pragma unroll
 #endif
-	for (int i = 0; i < STROBE_MAX_MAP_ENTRIES && i < map.cnt; ++i) {
+	for (int i = 0; i < STROBE_MAX_MAP_ENTRIES; ++i) {
+		if (i >= map.cnt)
+			break;
+
 		descr->key_lens[i] = 0;
 		len = bpf_probe_read_str(payload, STROBE_MAX_STR_LEN,
 					 map.entries[i].key);
diff --git a/tools/testing/selftests/bpf/test_sysctl.c b/tools/testing/selftests/bpf/test_sysctl.c
index 4f8ec1f10a80..a320e3844b17 100644
--- a/tools/testing/selftests/bpf/test_sysctl.c
+++ b/tools/testing/selftests/bpf/test_sysctl.c
@@ -1385,7 +1385,6 @@ static int fixup_sysctl_value(const char *buf, size_t buf_len,
 		uint8_t raw[sizeof(uint64_t)];
 		uint64_t num;
 	} value = {};
-	uint8_t c, i;
 
 	if (buf_len > sizeof(value)) {
 		log_err("Value is too big (%zd) to use in fixup", buf_len);
diff --git a/tools/testing/selftests/drivers/net/mlxsw/devlink_trap_l2_drops.sh b/tools/testing/selftests/drivers/net/mlxsw/devlink_trap_l2_drops.sh
index 5dcdfa20fc6c..126caf28b529 100755
--- a/tools/testing/selftests/drivers/net/mlxsw/devlink_trap_l2_drops.sh
+++ b/tools/testing/selftests/drivers/net/mlxsw/devlink_trap_l2_drops.sh
@@ -224,13 +224,6 @@ ingress_vlan_filter_test()
 	local vid=10
 
 	bridge vlan add vid $vid dev $swp2 master
-	# During initialization the firmware enables all the VLAN filters and
-	# the driver does not turn them off since the traffic will be discarded
-	# by the STP filter whose default is DISCARD state. Add the VID on the
-	# ingress bridge port and then remove it to make sure it is not member
-	# in the VLAN.
-	bridge vlan add vid $vid dev $swp1 master
-	bridge vlan del vid $vid dev $swp1 master
 
 	RET=0
 
diff --git a/tools/testing/selftests/net/fib_nexthop_multiprefix.sh b/tools/testing/selftests/net/fib_nexthop_multiprefix.sh
index e6828732843e..9dc35a16e415 100755
--- a/tools/testing/selftests/net/fib_nexthop_multiprefix.sh
+++ b/tools/testing/selftests/net/fib_nexthop_multiprefix.sh
@@ -15,6 +15,8 @@
 PAUSE_ON_FAIL=no
 VERBOSE=0
 
+which ping6 > /dev/null 2>&1 && ping6=$(which ping6) || ping6=$(which ping)
+
 ################################################################################
 # helpers
 
@@ -200,7 +202,7 @@ validate_v6_exception()
 	local rc
 
 	if [ ${ping_sz} != "0" ]; then
-		run_cmd ip netns exec h0 ping6 -s ${ping_sz} -c5 -w5 ${dst}
+		run_cmd ip netns exec h0 ${ping6} -s ${ping_sz} -c5 -w5 ${dst}
 	fi
 
 	if [ "$VERBOSE" = "1" ]; then
@@ -243,7 +245,7 @@ do
 		run_cmd taskset -c ${c} ip netns exec h0 ping -c1 -w1 172.16.10${i}.1
 		[ $? -ne 0 ] && printf "\nERROR: ping to h${i} failed\n" && ret=1
 
-		run_cmd taskset -c ${c} ip netns exec h0 ping6 -c1 -w1 2001:db8:10${i}::1
+		run_cmd taskset -c ${c} ip netns exec h0 ${ping6} -c1 -w1 2001:db8:10${i}::1
 		[ $? -ne 0 ] && printf "\nERROR: ping6 to h${i} failed\n" && ret=1
 
 		[ $ret -ne 0 ] && break
diff --git a/tools/testing/selftests/net/fib_nexthops.sh b/tools/testing/selftests/net/fib_nexthops.sh
index f9ebeac1e6f2..796670ebc65b 100755
--- a/tools/testing/selftests/net/fib_nexthops.sh
+++ b/tools/testing/selftests/net/fib_nexthops.sh
@@ -940,6 +940,20 @@ basic()
 	run_cmd "$IP nexthop add id 104 group 1 dev veth1"
 	log_test $? 2 "Nexthop group and device"
 
+	# Tests to ensure that flushing works as expected.
+	run_cmd "$IP nexthop add id 105 blackhole proto 99"
+	run_cmd "$IP nexthop add id 106 blackhole proto 100"
+	run_cmd "$IP nexthop add id 107 blackhole proto 99"
+	run_cmd "$IP nexthop flush proto 99"
+	check_nexthop "id 105" ""
+	check_nexthop "id 106" "id 106 blackhole proto 100"
+	check_nexthop "id 107" ""
+	run_cmd "$IP nexthop flush proto 100"
+	check_nexthop "id 106" ""
+
+	run_cmd "$IP nexthop flush proto 100"
+	log_test $? 0 "Test proto flush"
+
 	run_cmd "$IP nexthop add id 104 group 1 blackhole"
 	log_test $? 2 "Nexthop group and blackhole"
 
diff --git a/tools/testing/selftests/net/fib_tests.sh b/tools/testing/selftests/net/fib_tests.sh
index 4465fc2dae14..c4ba0ff4a53f 100755
--- a/tools/testing/selftests/net/fib_tests.sh
+++ b/tools/testing/selftests/net/fib_tests.sh
@@ -9,7 +9,7 @@ ret=0
 ksft_skip=4
 
 # all tests in this script. Can be overridden with -t option
-TESTS="unregister down carrier nexthop ipv6_rt ipv4_rt ipv6_addr_metric ipv4_addr_metric ipv6_route_metrics ipv4_route_metrics ipv4_route_v6_gw rp_filter"
+TESTS="unregister down carrier nexthop suppress ipv6_rt ipv4_rt ipv6_addr_metric ipv4_addr_metric ipv6_route_metrics ipv4_route_metrics ipv4_route_v6_gw rp_filter"
 
 VERBOSE=0
 PAUSE_ON_FAIL=no
@@ -17,6 +17,8 @@ PAUSE=no
 IP="ip -netns ns1"
 NS_EXEC="ip netns exec ns1"
 
+which ping6 > /dev/null 2>&1 && ping6=$(which ping6) || ping6=$(which ping)
+
 log_test()
 {
 	local rc=$1
@@ -614,6 +616,20 @@ fib_nexthop_test()
 	cleanup
 }
 
+fib_suppress_test()
+{
+	$IP link add dummy1 type dummy
+	$IP link set dummy1 up
+	$IP -6 route add default dev dummy1
+	$IP -6 rule add table main suppress_prefixlength 0
+	ping -f -c 1000 -W 1 1234::1 || true
+	$IP -6 rule del table main suppress_prefixlength 0
+	$IP link del dummy1
+
+	# If we got here without crashing, we're good.
+	return 0
+}
+
 ################################################################################
 # Tests on route add and replace
 
@@ -1086,7 +1102,7 @@ ipv6_route_metrics_test()
 	log_test $rc 0 "Multipath route with mtu metric"
 
 	$IP -6 ro add 2001:db8:104::/64 via 2001:db8:101::2 mtu 1300
-	run_cmd "ip netns exec ns1 ping6 -w1 -c1 -s 1500 2001:db8:104::1"
+	run_cmd "ip netns exec ns1 ${ping6} -w1 -c1 -s 1500 2001:db8:104::1"
 	log_test $? 0 "Using route with mtu metric"
 
 	run_cmd "$IP -6 ro add 2001:db8:114::/64 via  2001:db8:101::2  congctl lock foo"
@@ -1591,6 +1607,7 @@ do
 	fib_carrier_test|carrier)	fib_carrier_test;;
 	fib_rp_filter_test|rp_filter)	fib_rp_filter_test;;
 	fib_nexthop_test|nexthop)	fib_nexthop_test;;
+	fib_suppress_test|suppress)	fib_suppress_test;;
 	ipv6_route_test|ipv6_rt)	ipv6_route_test;;
 	ipv4_route_test|ipv4_rt)	ipv4_route_test;;
 	ipv6_addr_metric)		ipv6_addr_metric_test;;