Merge tag 'net-6.2-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net

Pull networking fixes from Jakub Kicinski:
 "Including fixes from bpf, netfilter and can.

  Current release - regressions:

   - bpf: synchronize dispatcher update with bpf_dispatcher_xdp_func

   - rxrpc:
      - fix security setting propagation
      - fix null-deref in rxrpc_unuse_local()
      - fix switched parameters in peer tracing

  Current release - new code bugs:

   - rxrpc:
      - fix I/O thread startup getting skipped
      - fix locking issues in rxrpc_put_peer_locked()
      - fix I/O thread stop
      - fix uninitialised variable in rxperf server
      - fix the return value of rxrpc_new_incoming_call()

   - microchip: vcap: fix initialization of value and mask

   - nfp: fix unaligned io read of capabilities word

  Previous releases - regressions:

   - stop in-kernel socket users from corrupting socket's task_frag

   - stream: purge sk_error_queue in sk_stream_kill_queues()

   - openvswitch: fix flow lookup to use unmasked key

   - dsa: mv88e6xxx: avoid reg_lock deadlock in mv88e6xxx_setup_port()

   - devlink:
      - hold region lock when flushing snapshots
      - protect devlink dump by the instance lock

  Previous releases - always broken:

   - bpf:
      - prevent leak of lsm program after failed attach
      - resolve fext program type when checking map compatibility

   - skbuff: account for tail adjustment during pull operations

   - macsec: fix net device access prior to holding a lock

   - bonding: switch back when high prio link up

   - netfilter: flowtable: really fix NAT IPv6 offload

   - enetc: avoid buffer leaks on xdp_do_redirect() failure

   - unix: fix race in SOCK_SEQPACKET's unix_dgram_sendmsg()

   - dsa: microchip: remove IRQF_TRIGGER_FALLING in
     request_threaded_irq"

* tag 'net-6.2-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net: (64 commits)
  net: fec: check the return value of build_skb()
  net: simplify sk_page_frag
  Treewide: Stop corrupting socket's task_frag
  net: Introduce sk_use_task_frag in struct sock.
  mctp: Remove device type check at unregister
  net: dsa: microchip: remove IRQF_TRIGGER_FALLING in request_threaded_irq
  can: kvaser_usb: hydra: help gcc-13 to figure out cmd_len
  can: flexcan: avoid unbalanced pm_runtime_enable warning
  Documentation: devlink: add missing toc entry for etas_es58x devlink doc
  mctp: serial: Fix starting value for frame check sequence
  nfp: fix unaligned io read of capabilities word
  net: stream: purge sk_error_queue in sk_stream_kill_queues()
  myri10ge: Fix an error handling path in myri10ge_probe()
  net: microchip: vcap: Fix initialization of value and mask
  rxrpc: Fix the return value of rxrpc_new_incoming_call()
  rxrpc: rxperf: Fix uninitialised variable
  rxrpc: Fix I/O thread stop
  rxrpc: Fix switched parameters in peer tracing
  rxrpc: Fix locking issues in rxrpc_put_peer_locked()
  rxrpc: Fix I/O thread startup getting skipped
  ...

9 files changed, 340 insertions, 8 deletions

diff --git a/tools/testing/selftests/bpf/config b/tools/testing/selftests/bpf/config
index 612f699dc4f7..63cd4ab70171 100644
--- a/tools/testing/selftests/bpf/config
+++ b/tools/testing/selftests/bpf/config
@@ -16,6 +16,7 @@ CONFIG_CRYPTO_USER_API_HASH=y
 CONFIG_DYNAMIC_FTRACE=y
 CONFIG_FPROBE=y
 CONFIG_FTRACE_SYSCALLS=y
+CONFIG_FUNCTION_ERROR_INJECTION=y
 CONFIG_FUNCTION_TRACER=y
 CONFIG_GENEVE=y
 CONFIG_IKCONFIG=y
diff --git a/tools/testing/selftests/bpf/prog_tests/fexit_bpf2bpf.c b/tools/testing/selftests/bpf/prog_tests/fexit_bpf2bpf.c
index d1e32e792536..20f5fa0fcec9 100644
--- a/tools/testing/selftests/bpf/prog_tests/fexit_bpf2bpf.c
+++ b/tools/testing/selftests/bpf/prog_tests/fexit_bpf2bpf.c
@@ -4,6 +4,8 @@
 #include <network_helpers.h>
 #include <bpf/btf.h>
 #include "bind4_prog.skel.h"
+#include "freplace_progmap.skel.h"
+#include "xdp_dummy.skel.h"
 
 typedef int (*test_cb)(struct bpf_object *obj);
 
@@ -500,6 +502,50 @@ cleanup:
 	bind4_prog__destroy(skel);
 }
 
+static void test_func_replace_progmap(void)
+{
+	struct bpf_cpumap_val value = { .qsize = 1 };
+	struct freplace_progmap *skel = NULL;
+	struct xdp_dummy *tgt_skel = NULL;
+	__u32 key = 0;
+	int err;
+
+	skel = freplace_progmap__open();
+	if (!ASSERT_OK_PTR(skel, "prog_open"))
+		return;
+
+	tgt_skel = xdp_dummy__open_and_load();
+	if (!ASSERT_OK_PTR(tgt_skel, "tgt_prog_load"))
+		goto out;
+
+	err = bpf_program__set_attach_target(skel->progs.xdp_cpumap_prog,
+					     bpf_program__fd(tgt_skel->progs.xdp_dummy_prog),
+					     "xdp_dummy_prog");
+	if (!ASSERT_OK(err, "set_attach_target"))
+		goto out;
+
+	err = freplace_progmap__load(skel);
+	if (!ASSERT_OK(err, "obj_load"))
+		goto out;
+
+	/* Prior to fixing the kernel, loading the PROG_TYPE_EXT 'redirect'
+	 * program above will cause the map owner type of 'cpumap' to be set to
+	 * PROG_TYPE_EXT. This in turn will cause the bpf_map_update_elem()
+	 * below to fail, because the program we are inserting into the map is
+	 * of PROG_TYPE_XDP. After fixing the kernel, the initial ownership will
+	 * be correctly resolved to the *target* of the PROG_TYPE_EXT program
+	 * (i.e., PROG_TYPE_XDP) and the map update will succeed.
+	 */
+	value.bpf_prog.fd = bpf_program__fd(skel->progs.xdp_drop_prog);
+	err = bpf_map_update_elem(bpf_map__fd(skel->maps.cpu_map),
+				  &key, &value, 0);
+	ASSERT_OK(err, "map_update");
+
+out:
+	xdp_dummy__destroy(tgt_skel);
+	freplace_progmap__destroy(skel);
+}
+
 /* NOTE: affect other tests, must run in serial mode */
 void serial_test_fexit_bpf2bpf(void)
 {
@@ -525,4 +571,6 @@ void serial_test_fexit_bpf2bpf(void)
 		test_func_replace_global_func();
 	if (test__start_subtest("fentry_to_cgroup_bpf"))
 		test_fentry_to_cgroup_bpf();
+	if (test__start_subtest("func_replace_progmap"))
+		test_func_replace_progmap();
 }
diff --git a/tools/testing/selftests/bpf/progs/freplace_progmap.c b/tools/testing/selftests/bpf/progs/freplace_progmap.c
new file mode 100644
index 000000000000..81b56b9aa7d6
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/freplace_progmap.c
@@ -0,0 +1,24 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <linux/bpf.h>
+#include <bpf/bpf_helpers.h>
+
+struct {
+	__uint(type, BPF_MAP_TYPE_CPUMAP);
+	__type(key, __u32);
+	__type(value, struct bpf_cpumap_val);
+	__uint(max_entries, 1);
+} cpu_map SEC(".maps");
+
+SEC("xdp/cpumap")
+int xdp_drop_prog(struct xdp_md *ctx)
+{
+	return XDP_DROP;
+}
+
+SEC("freplace")
+int xdp_cpumap_prog(struct xdp_md *ctx)
+{
+	return bpf_redirect_map(&cpu_map, 0, XDP_PASS);
+}
+
+char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/rcu_read_lock.c b/tools/testing/selftests/bpf/progs/rcu_read_lock.c
index 125f908024d3..5cecbdbbb16e 100644
--- a/tools/testing/selftests/bpf/progs/rcu_read_lock.c
+++ b/tools/testing/selftests/bpf/progs/rcu_read_lock.c
@@ -288,13 +288,13 @@ out:
 SEC("?fentry.s/" SYS_PREFIX "sys_getpgid")
 int task_untrusted_non_rcuptr(void *ctx)
 {
-	struct task_struct *task, *last_wakee;
+	struct task_struct *task, *group_leader;
 
 	task = bpf_get_current_task_btf();
 	bpf_rcu_read_lock();
-	/* the pointer last_wakee marked as untrusted */
-	last_wakee = task->real_parent->last_wakee;
-	(void)bpf_task_storage_get(&map_a, last_wakee, 0, 0);
+	/* the pointer group_leader marked as untrusted */
+	group_leader = task->real_parent->group_leader;
+	(void)bpf_task_storage_get(&map_a, group_leader, 0, 0);
 	bpf_rcu_read_unlock();
 	return 0;
 }
diff --git a/tools/testing/selftests/bpf/progs/task_kfunc_failure.c b/tools/testing/selftests/bpf/progs/task_kfunc_failure.c
index 87fa1db9d9b5..1b47b94dbca0 100644
--- a/tools/testing/selftests/bpf/progs/task_kfunc_failure.c
+++ b/tools/testing/selftests/bpf/progs/task_kfunc_failure.c
@@ -73,7 +73,7 @@ int BPF_PROG(task_kfunc_acquire_trusted_walked, struct task_struct *task, u64 cl
 	struct task_struct *acquired;
 
 	/* Can't invoke bpf_task_acquire() on a trusted pointer obtained from walking a struct. */
-	acquired = bpf_task_acquire(task->last_wakee);
+	acquired = bpf_task_acquire(task->group_leader);
 	bpf_task_release(acquired);
 
 	return 0;
diff --git a/tools/testing/selftests/drivers/net/bonding/Makefile b/tools/testing/selftests/drivers/net/bonding/Makefile
index 0f3921908b07..8e3b786a748f 100644
--- a/tools/testing/selftests/drivers/net/bonding/Makefile
+++ b/tools/testing/selftests/drivers/net/bonding/Makefile
@@ -7,7 +7,8 @@ TEST_PROGS := \
 	bond-lladdr-target.sh \
 	dev_addr_lists.sh \
 	mode-1-recovery-updelay.sh \
-	mode-2-recovery-updelay.sh
+	mode-2-recovery-updelay.sh \
+	option_prio.sh
 
 TEST_FILES := \
 	lag_lib.sh \
diff --git a/tools/testing/selftests/drivers/net/bonding/option_prio.sh b/tools/testing/selftests/drivers/net/bonding/option_prio.sh
new file mode 100755
index 000000000000..c32eebff5005
--- /dev/null
+++ b/tools/testing/selftests/drivers/net/bonding/option_prio.sh
@@ -0,0 +1,245 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+#
+# Test bonding option prio
+#
+
+ALL_TESTS="
+	prio_arp_ip_target_test
+	prio_miimon_test
+"
+
+REQUIRE_MZ=no
+REQUIRE_JQ=no
+NUM_NETIFS=0
+lib_dir=$(dirname "$0")
+source "$lib_dir"/net_forwarding_lib.sh
+
+destroy()
+{
+	ip link del bond0 &>/dev/null
+	ip link del br0 &>/dev/null
+	ip link del veth0 &>/dev/null
+	ip link del veth1 &>/dev/null
+	ip link del veth2 &>/dev/null
+	ip netns del ns1 &>/dev/null
+	ip link del veth3 &>/dev/null
+}
+
+cleanup()
+{
+	pre_cleanup
+
+	destroy
+}
+
+skip()
+{
+        local skip=1
+	ip link add name bond0 type bond mode 1 miimon 100 &>/dev/null
+	ip link add name veth0 type veth peer name veth0_p
+	ip link set veth0 master bond0
+
+	# check if iproute support prio option
+	ip link set dev veth0 type bond_slave prio 10
+	[[ $? -ne 0 ]] && skip=0
+
+	# check if bonding support prio option
+	ip -d link show veth0 | grep -q "prio 10"
+	[[ $? -ne 0 ]] && skip=0
+
+	ip link del bond0 &>/dev/null
+	ip link del veth0
+
+	return $skip
+}
+
+active_slave=""
+check_active_slave()
+{
+	local target_active_slave=$1
+	active_slave="$(cat /sys/class/net/bond0/bonding/active_slave)"
+	test "$active_slave" = "$target_active_slave"
+	check_err $? "Current active slave is $active_slave but not $target_active_slave"
+}
+
+
+# Test bonding prio option with mode=$mode monitor=$monitor
+# and primary_reselect=$primary_reselect
+prio_test()
+{
+	RET=0
+
+	local monitor=$1
+	local mode=$2
+	local primary_reselect=$3
+
+	local bond_ip4="192.169.1.2"
+	local peer_ip4="192.169.1.1"
+	local bond_ip6="2009:0a:0b::02"
+	local peer_ip6="2009:0a:0b::01"
+
+
+	# create veths
+	ip link add name veth0 type veth peer name veth0_p
+	ip link add name veth1 type veth peer name veth1_p
+	ip link add name veth2 type veth peer name veth2_p
+
+	# create bond
+	if [[ "$monitor" == "miimon" ]];then
+		ip link add name bond0 type bond mode $mode miimon 100 primary veth1 primary_reselect $primary_reselect
+	elif [[ "$monitor" == "arp_ip_target" ]];then
+		ip link add name bond0 type bond mode $mode arp_interval 1000 arp_ip_target $peer_ip4 primary veth1 primary_reselect $primary_reselect
+	elif [[ "$monitor" == "ns_ip6_target" ]];then
+		ip link add name bond0 type bond mode $mode arp_interval 1000 ns_ip6_target $peer_ip6 primary veth1 primary_reselect $primary_reselect
+	fi
+	ip link set bond0 up
+	ip link set veth0 master bond0
+	ip link set veth1 master bond0
+	ip link set veth2 master bond0
+	# check bonding member prio value
+	ip link set dev veth0 type bond_slave prio 0
+	ip link set dev veth1 type bond_slave prio 10
+	ip link set dev veth2 type bond_slave prio 11
+	ip -d link show veth0 | grep -q 'prio 0'
+	check_err $? "veth0 prio is not 0"
+	ip -d link show veth1 | grep -q 'prio 10'
+	check_err $? "veth0 prio is not 10"
+	ip -d link show veth2 | grep -q 'prio 11'
+	check_err $? "veth0 prio is not 11"
+
+	ip link set veth0 up
+	ip link set veth1 up
+	ip link set veth2 up
+	ip link set veth0_p up
+	ip link set veth1_p up
+	ip link set veth2_p up
+
+	# prepare ping target
+	ip link add name br0 type bridge
+	ip link set br0 up
+	ip link set veth0_p master br0
+	ip link set veth1_p master br0
+	ip link set veth2_p master br0
+	ip link add name veth3 type veth peer name veth3_p
+	ip netns add ns1
+	ip link set veth3_p master br0 up
+	ip link set veth3 netns ns1 up
+	ip netns exec ns1 ip addr add $peer_ip4/24 dev veth3
+	ip netns exec ns1 ip addr add $peer_ip6/64 dev veth3
+	ip addr add $bond_ip4/24 dev bond0
+	ip addr add $bond_ip6/64 dev bond0
+	sleep 5
+
+	ping $peer_ip4 -c5 -I bond0 &>/dev/null
+	check_err $? "ping failed 1."
+	ping6 $peer_ip6 -c5 -I bond0 &>/dev/null
+	check_err $? "ping6 failed 1."
+
+	# active salve should be the primary slave
+	check_active_slave veth1
+
+	# active slave should be the higher prio slave
+	ip link set $active_slave down
+	ping $peer_ip4 -c5 -I bond0 &>/dev/null
+	check_err $? "ping failed 2."
+	check_active_slave veth2
+
+	# when only 1 slave is up
+	ip link set $active_slave down
+	ping $peer_ip4 -c5 -I bond0 &>/dev/null
+	check_err $? "ping failed 3."
+	check_active_slave veth0
+
+	# when a higher prio slave change to up
+	ip link set veth2 up
+	ping $peer_ip4 -c5 -I bond0 &>/dev/null
+	check_err $? "ping failed 4."
+	case $primary_reselect in
+		"0")
+			check_active_slave "veth2"
+			;;
+		"1")
+			check_active_slave "veth0"
+			;;
+		"2")
+			check_active_slave "veth0"
+			;;
+	esac
+	local pre_active_slave=$active_slave
+
+	# when the primary slave change to up
+	ip link set veth1 up
+	ping $peer_ip4 -c5 -I bond0 &>/dev/null
+	check_err $? "ping failed 5."
+	case $primary_reselect in
+		"0")
+			check_active_slave "veth1"
+			;;
+		"1")
+			check_active_slave "$pre_active_slave"
+			;;
+		"2")
+			check_active_slave "$pre_active_slave"
+			ip link set $active_slave down
+			ping $peer_ip4 -c5 -I bond0 &>/dev/null
+			check_err $? "ping failed 6."
+			check_active_slave "veth1"
+			;;
+	esac
+
+	# Test changing bond salve prio
+	if [[ "$primary_reselect" == "0" ]];then
+		ip link set dev veth0 type bond_slave prio 1000000
+		ip link set dev veth1 type bond_slave prio 0
+		ip link set dev veth2 type bond_slave prio -50
+		ip -d link show veth0 | grep -q 'prio 1000000'
+		check_err $? "veth0 prio is not 1000000"
+		ip -d link show veth1 | grep -q 'prio 0'
+		check_err $? "veth1 prio is not 0"
+		ip -d link show veth2 | grep -q 'prio -50'
+		check_err $? "veth3 prio is not -50"
+		check_active_slave "veth1"
+
+		ip link set $active_slave down
+		ping $peer_ip4 -c5 -I bond0 &>/dev/null
+		check_err $? "ping failed 7."
+		check_active_slave "veth0"
+	fi
+
+	cleanup
+
+	log_test "prio_test" "Test bonding option 'prio' with mode=$mode monitor=$monitor and primary_reselect=$primary_reselect"
+}
+
+prio_miimon_test()
+{
+	local mode
+	local primary_reselect
+
+	for mode in 1 5 6; do
+		for primary_reselect in 0 1 2; do
+			prio_test "miimon" $mode $primary_reselect
+		done
+	done
+}
+
+prio_arp_ip_target_test()
+{
+	local primary_reselect
+
+	for primary_reselect in 0 1 2; do
+		prio_test "arp_ip_target" 1 $primary_reselect
+	done
+}
+
+if skip;then
+	log_test_skip "option_prio.sh" "Current iproute doesn't support 'prio'."
+	exit 0
+fi
+
+trap cleanup EXIT
+
+tests_run
+
+exit "$EXIT_STATUS"
diff --git a/tools/testing/selftests/drivers/net/netdevsim/devlink.sh b/tools/testing/selftests/drivers/net/netdevsim/devlink.sh
index 9de1d123f4f5..a08c02abde12 100755
--- a/tools/testing/selftests/drivers/net/netdevsim/devlink.sh
+++ b/tools/testing/selftests/drivers/net/netdevsim/devlink.sh
@@ -496,8 +496,8 @@ dummy_reporter_test()
 
 	check_reporter_info dummy healthy 3 3 10 true
 
-	echo 8192> $DEBUGFS_DIR/health/binary_len
-	check_fail $? "Failed set dummy reporter binary len to 8192"
+	echo 8192 > $DEBUGFS_DIR/health/binary_len
+	check_err $? "Failed set dummy reporter binary len to 8192"
 
 	local dump=$(devlink health dump show $DL_HANDLE reporter dummy -j)
 	check_err $? "Failed show dump of dummy reporter"
diff --git a/tools/testing/selftests/drivers/net/netdevsim/devlink_trap.sh b/tools/testing/selftests/drivers/net/netdevsim/devlink_trap.sh
index 109900c817be..b64d98ca0df7 100755
--- a/tools/testing/selftests/drivers/net/netdevsim/devlink_trap.sh
+++ b/tools/testing/selftests/drivers/net/netdevsim/devlink_trap.sh
@@ -47,6 +47,17 @@ if [ -d "${NETDEVSIM_PATH}/devices/netdevsim${DEV_ADDR}" ]; then
 	exit 1
 fi
 
+check_netdev_down()
+{
+	state=$(cat /sys/class/net/${NETDEV}/flags)
+
+	if [ $((state & 1)) -ne 0 ]; then
+		echo "WARNING: unexpected interface UP, disable NetworkManager?"
+
+		ip link set dev $NETDEV down
+	fi
+}
+
 init_test()
 {
 	RET=0
@@ -151,6 +162,7 @@ trap_stats_test()
 
 	RET=0
 
+	check_netdev_down
 	for trap_name in $(devlink_traps_get); do
 		devlink_trap_stats_idle_test $trap_name
 		check_err $? "Stats of trap $trap_name not idle when netdev down"
@@ -254,6 +266,7 @@ trap_group_stats_test()
 
 	RET=0
 
+	check_netdev_down
 	for group_name in $(devlink_trap_groups_get); do
 		devlink_trap_group_stats_idle_test $group_name
 		check_err $? "Stats of trap group $group_name not idle when netdev down"