Merge tag 'net-7.0-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net

Pull networking fixes from Jakub Kicinski:
 "Including fixes from Netfilter.

  Current release - new code bugs:

   - net: fix backlog_unlock_irq_restore() vs CONFIG_PREEMPT_RT

   - eth: mlx5e: XSK, Fix unintended ICOSQ change

   - phy_port: correctly recompute the port's linkmodes

   - vsock: prevent child netns mode switch from local to global

   - couple of kconfig fixes for new symbols

  Previous releases - regressions:

   - nfc: nci: fix false-positive parameter validation for packet data

   - net: do not delay zero-copy skbs in skb_attempt_defer_free()

  Previous releases - always broken:

   - mctp: ensure our nlmsg responses to user space are zero-initialised

   - ipv6: ioam: fix heap buffer overflow in __ioam6_fill_trace_data()

   - fixes for ICMP rate limiting

  Misc:

   - intel: fix PCI device ID conflict between i40e and ipw2200"

* tag 'net-7.0-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net: (85 commits)
  net: nfc: nci: Fix parameter validation for packet data
  net/mlx5e: Use unsigned for mlx5e_get_max_num_channels
  net/mlx5e: Fix deadlocks between devlink and netdev instance locks
  net/mlx5e: MACsec, add ASO poll loop in macsec_aso_set_arm_event
  net/mlx5: Fix misidentification of write combining CQE during poll loop
  net/mlx5e: Fix misidentification of ASO CQE during poll loop
  net/mlx5: Fix multiport device check over light SFs
  bonding: alb: fix UAF in rlb_arp_recv during bond up/down
  bnge: fix reserving resources from FW
  eth: fbnic: Advertise supported XDP features.
  rds: tcp: fix uninit-value in __inet_bind
  net/rds: Fix NULL pointer dereference in rds_tcp_accept_one
  octeontx2-af: Fix default entries mcam entry action
  net/mlx5e: XSK, Fix unintended ICOSQ change
  ipv6: icmp: icmpv6_xrlim_allow() optimization if net.ipv6.icmp.ratelimit is zero
  ipv4: icmp: icmpv4_xrlim_allow() optimization if net.ipv4.icmp_ratelimit is zero
  ipv6: icmp: remove obsolete code in icmpv6_xrlim_allow()
  inet: move icmp_global_{credit,stamp} to a separate cache line
  icmp: prevent possible overflow in icmp_global_allow()
  selftests/net: packetdrill: add ipv4-mapped-ipv6 tests
  ...

13 files changed, 175 insertions, 29 deletions

diff --git a/tools/testing/selftests/drivers/net/hw/devmem.py b/tools/testing/selftests/drivers/net/hw/devmem.py
index 45c2d49d55b6..ee863e90d1e0 100755
--- a/tools/testing/selftests/drivers/net/hw/devmem.py
+++ b/tools/testing/selftests/drivers/net/hw/devmem.py
@@ -63,12 +63,29 @@ def check_tx_chunks(cfg) -> None:
     ksft_eq(socat.stdout.strip(), "hello\nworld")
 
 
+def check_rx_hds(cfg) -> None:
+    """Test HDS splitting across payload sizes."""
+    require_devmem(cfg)
+
+    for size in [1, 8, 16, 32, 64, 128, 256, 512, 1024, 2048, 4096, 8192]:
+        port = rand_port()
+        listen_cmd = f"{cfg.bin_local} -L -l -f {cfg.ifname} -s {cfg.addr} -p {port}"
+
+        with bkg(listen_cmd, exit_wait=True) as ncdevmem:
+            wait_port_listen(port)
+            cmd(f"dd if=/dev/zero bs={size} count=1 2>/dev/null | " +
+                f"socat -b {size} -u - TCP{cfg.addr_ipver}:{cfg.baddr}:{port},nodelay",
+                host=cfg.remote, shell=True)
+
+        ksft_eq(ncdevmem.ret, 0, f"HDS failed for payload size {size}")
+
+
 def main() -> None:
     with NetDrvEpEnv(__file__) as cfg:
         cfg.bin_local = path.abspath(path.dirname(__file__) + "/ncdevmem")
         cfg.bin_remote = cfg.remote.deploy(cfg.bin_local)
 
-        ksft_run([check_rx, check_tx, check_tx_chunks],
+        ksft_run([check_rx, check_tx, check_tx_chunks, check_rx_hds],
                  args=(cfg, ))
     ksft_exit()
 
diff --git a/tools/testing/selftests/drivers/net/hw/ncdevmem.c b/tools/testing/selftests/drivers/net/hw/ncdevmem.c
index 16864c844108..e098d6534c3c 100644
--- a/tools/testing/selftests/drivers/net/hw/ncdevmem.c
+++ b/tools/testing/selftests/drivers/net/hw/ncdevmem.c
@@ -98,6 +98,7 @@ static unsigned int ifindex;
 static unsigned int dmabuf_id;
 static uint32_t tx_dmabuf_id;
 static int waittime_ms = 500;
+static bool fail_on_linear;
 
 /* System state loaded by current_config_load() */
 #define MAX_FLOWS	8
@@ -975,6 +976,11 @@ static int do_server(struct memory_buffer *mem)
 					"SCM_DEVMEM_LINEAR. dmabuf_cmsg->frag_size=%u\n",
 					dmabuf_cmsg->frag_size);
 
+				if (fail_on_linear) {
+					pr_err("received SCM_DEVMEM_LINEAR but --fail-on-linear (-L) set");
+					goto err_close_client;
+				}
+
 				continue;
 			}
 
@@ -1398,8 +1404,11 @@ int main(int argc, char *argv[])
 	int is_server = 0, opt;
 	int ret, err = 1;
 
-	while ((opt = getopt(argc, argv, "ls:c:p:v:q:t:f:z:")) != -1) {
+	while ((opt = getopt(argc, argv, "Lls:c:p:v:q:t:f:z:")) != -1) {
 		switch (opt) {
+		case 'L':
+			fail_on_linear = true;
+			break;
 		case 'l':
 			is_server = 1;
 			break;
diff --git a/tools/testing/selftests/drivers/net/hw/toeplitz.py b/tools/testing/selftests/drivers/net/hw/toeplitz.py
index d288c57894f6..cd7e080e6f84 100755
--- a/tools/testing/selftests/drivers/net/hw/toeplitz.py
+++ b/tools/testing/selftests/drivers/net/hw/toeplitz.py
@@ -19,6 +19,8 @@ from lib.py import ksft_variants, KsftNamedVariant, KsftSkipEx, KsftFailEx
 
 # "define" for the ID of the Toeplitz hash function
 ETH_RSS_HASH_TOP = 1
+# Must match RPS_MAX_CPUS in toeplitz.c
+RPS_MAX_CPUS = 16
 
 
 def _check_rps_and_rfs_not_configured(cfg):
@@ -67,23 +69,24 @@ def _get_irq_cpus(cfg):
     return cpus
 
 
-def _get_unused_cpus(cfg, count=2):
+def _get_unused_rps_cpus(cfg, count=2):
     """
-    Get CPUs that are not used by Rx queues.
-    Returns a list of at least 'count' CPU numbers.
+    Get CPUs that are not used by Rx queues for RPS.
+    Returns a list of at least 'count' CPU numbers within
+    the RPS_MAX_CPUS supported range.
     """
 
     # Get CPUs used by Rx queues
     rx_cpus = set(_get_irq_cpus(cfg))
 
-    # Get total number of CPUs
-    num_cpus = os.cpu_count()
+    # Get total number of CPUs, capped by RPS_MAX_CPUS
+    num_cpus = min(os.cpu_count(), RPS_MAX_CPUS)
 
     # Find unused CPUs
     unused_cpus = [cpu for cpu in range(num_cpus) if cpu not in rx_cpus]
 
     if len(unused_cpus) < count:
-        raise KsftSkipEx(f"Need at {count} CPUs not used by Rx queues, found {len(unused_cpus)}")
+        raise KsftSkipEx(f"Need at least {count} CPUs in range 0..{num_cpus - 1} not used by Rx queues, found {len(unused_cpus)}")
 
     return unused_cpus[:count]
 
@@ -181,7 +184,7 @@ def test(cfg, proto_flag, ipver, grp):
         ksft_pr(f"RSS using CPUs: {irq_cpus}")
     elif grp == "rps":
         # Get CPUs not used by Rx queues and configure them for RPS
-        rps_cpus = _get_unused_cpus(cfg, count=2)
+        rps_cpus = _get_unused_rps_cpus(cfg, count=2)
         rps_mask = _configure_rps(cfg, rps_cpus)
         defer(_configure_rps, cfg, [])
         rx_cmd += ["-r", rps_mask]
diff --git a/tools/testing/selftests/drivers/net/lib/sh/lib_netcons.sh b/tools/testing/selftests/drivers/net/lib/sh/lib_netcons.sh
index b6093bcf2b06..02dcdeb723be 100644
--- a/tools/testing/selftests/drivers/net/lib/sh/lib_netcons.sh
+++ b/tools/testing/selftests/drivers/net/lib/sh/lib_netcons.sh
@@ -249,8 +249,8 @@ function listen_port_and_save_to() {
 		SOCAT_MODE="UDP6-LISTEN"
 	fi
 
-	# Just wait for 2 seconds
-	timeout 2 ip netns exec "${NAMESPACE}" \
+	# Just wait for 3 seconds
+	timeout 3 ip netns exec "${NAMESPACE}" \
 		socat "${SOCAT_MODE}":"${PORT}",fork "${OUTPUT}" 2> /dev/null
 }
 
diff --git a/tools/testing/selftests/drivers/net/mlxsw/tc_restrictions.sh b/tools/testing/selftests/drivers/net/mlxsw/tc_restrictions.sh
index 0441a18f098b..aac8ef490feb 100755
--- a/tools/testing/selftests/drivers/net/mlxsw/tc_restrictions.sh
+++ b/tools/testing/selftests/drivers/net/mlxsw/tc_restrictions.sh
@@ -317,7 +317,7 @@ police_limits_test()
 
 	tc filter add dev $swp1 ingress pref 1 proto ip handle 101 \
 		flower skip_sw \
-		action police rate 0.5kbit burst 1m conform-exceed drop/ok
+		action police rate 0.5kbit burst 2k conform-exceed drop/ok
 	check_fail $? "Incorrect success to add police action with too low rate"
 
 	tc filter add dev $swp1 ingress pref 1 proto ip handle 101 \
@@ -327,7 +327,7 @@ police_limits_test()
 
 	tc filter add dev $swp1 ingress pref 1 proto ip handle 101 \
 		flower skip_sw \
-		action police rate 1.5kbit burst 1m conform-exceed drop/ok
+		action police rate 1.5kbit burst 2k conform-exceed drop/ok
 	check_err $? "Failed to add police action with low rate"
 
 	tc filter del dev $swp1 ingress protocol ip pref 1 handle 101 flower
diff --git a/tools/testing/selftests/net/forwarding/bridge_mdb_max.sh b/tools/testing/selftests/net/forwarding/bridge_mdb_max.sh
index 3da9d93ab36f..625162fd7e8b 100755
--- a/tools/testing/selftests/net/forwarding/bridge_mdb_max.sh
+++ b/tools/testing/selftests/net/forwarding/bridge_mdb_max.sh
@@ -28,6 +28,7 @@ ALL_TESTS="
 	test_8021d
 	test_8021q
 	test_8021qvs
+	test_mdb_count_warning
 "
 
 NUM_NETIFS=4
@@ -83,8 +84,6 @@ switch_create_8021q()
 {
 	local br_flags=$1; shift
 
-	log_info "802.1q $br_flags${br_flags:+ }tests"
-
 	ip link add name br0 type bridge vlan_filtering 1 vlan_default_pvid 0 \
 		mcast_snooping 1 $br_flags \
 		mcast_igmp_version 3 mcast_mld_version 2
@@ -106,6 +105,7 @@ switch_create_8021q()
 
 switch_create_8021qvs()
 {
+	log_info "802.1q mcast_vlan_snooping 1 tests"
 	switch_create_8021q "mcast_vlan_snooping 1"
 	bridge vlan global set dev br0 vid 10 mcast_igmp_version 3
 	bridge vlan global set dev br0 vid 10 mcast_mld_version 2
@@ -1272,6 +1272,76 @@ test_8021qvs_toggle_vlan_snooping()
 	test_toggle_vlan_snooping_permanent
 }
 
+mdb_count_check_warn()
+{
+	local msg=$1; shift
+
+	dmesg | grep -q "WARNING:.*br_multicast_port_ngroups_dec.*"
+	check_fail $? "$msg"
+}
+
+test_mdb_count_mcast_vlan_snooping_flush()
+{
+	RET=0
+
+	# check if we already have a warning
+	mdb_count_check_warn "Check MDB entries count warning before test"
+
+	bridge mdb add dev br0 port "$swp1" grp 239.0.0.1 permanent vid 10
+	ip link set dev br0 down
+	ip link set dev br0 type bridge mcast_vlan_snooping 1
+	bridge mdb flush dev br0
+
+	mdb_count_check_warn "Check MDB entries count warning after test"
+
+	ip link set dev br0 type bridge mcast_vlan_snooping 0
+	ip link set dev br0 up
+
+	log_test "MDB count warning: mcast_vlan_snooping and MDB flush"
+}
+
+test_mdb_count_mcast_snooping_flush()
+{
+	RET=0
+
+	# check if we already have a warning
+	mdb_count_check_warn "Check MDB entries count warning before test"
+
+	bridge mdb add dev br0 port "$swp1" grp 239.0.0.1 permanent vid 10
+	ip link set dev br0 type bridge mcast_snooping 0
+	ip link set dev br0 type bridge mcast_vlan_snooping 1
+	bridge mdb flush dev br0
+
+	mdb_count_check_warn "Check MDB entries count warning after test"
+
+	ip link set dev br0 type bridge mcast_vlan_snooping 0
+	ip link set dev br0 type bridge mcast_snooping 1
+
+	log_test "MDB count warning: mcast_snooping and MDB flush"
+}
+
+test_mdb_count_vlan_state_flush()
+{
+	RET=0
+
+	# check if we already have a warning
+	mdb_count_check_warn "Check MDB entries count warning before test"
+
+	bridge mdb add dev br0 port "$swp1" grp 239.0.0.1 permanent vid 10
+	ip link set dev br0 down
+	bridge vlan set vid 10 dev "$swp1" state blocking
+	ip link set dev br0 type bridge mcast_vlan_snooping 1
+	ip link set dev br0 up
+	bridge mdb flush dev br0
+
+	mdb_count_check_warn "Check MDB entries count warning after test"
+
+	bridge vlan set vid 10 dev "$swp1" state forwarding
+	ip link set dev br0 type bridge mcast_vlan_snooping 0
+
+	log_test "MDB count warning: disabled vlan state and MDB flush"
+}
+
 # test groups
 
 test_8021d()
@@ -1297,6 +1367,7 @@ test_8021q()
 {
 	# Tests for vlan_filtering 1 mcast_vlan_snooping 0.
 
+	log_info "802.1q tests"
 	switch_create_8021q
 	setup_wait
 
@@ -1334,6 +1405,21 @@ test_8021qvs()
 	switch_destroy
 }
 
+test_mdb_count_warning()
+{
+	# Tests for mdb_n_entries warning
+
+	log_info "MDB count warning tests"
+	switch_create_8021q
+	setup_wait
+
+	test_mdb_count_mcast_vlan_snooping_flush
+	test_mdb_count_mcast_snooping_flush
+	test_mdb_count_vlan_state_flush
+
+	switch_destroy
+}
+
 if ! bridge link help 2>&1 | grep -q "mcast_max_groups"; then
 	echo "SKIP: iproute2 too old, missing bridge \"mcast_max_groups\" support"
 	exit $ksft_skip
diff --git a/tools/testing/selftests/net/forwarding/pedit_dsfield.sh b/tools/testing/selftests/net/forwarding/pedit_dsfield.sh
index af008fbf2725..eb2d8034de9c 100755
--- a/tools/testing/selftests/net/forwarding/pedit_dsfield.sh
+++ b/tools/testing/selftests/net/forwarding/pedit_dsfield.sh
@@ -98,12 +98,20 @@ setup_prepare()
 	h1_create
 	h2_create
 	switch_create
+
+	if [ -f /proc/sys/net/bridge/bridge-nf-call-iptables ]; then
+		sysctl_set net.bridge.bridge-nf-call-iptables 0
+	fi
 }
 
 cleanup()
 {
 	pre_cleanup
 
+	if [ -f /proc/sys/net/bridge/bridge-nf-call-iptables ]; then
+		sysctl_restore net.bridge.bridge-nf-call-iptables
+	fi
+
 	switch_destroy
 	h2_destroy
 	h1_destroy
diff --git a/tools/testing/selftests/net/forwarding/pedit_ip.sh b/tools/testing/selftests/net/forwarding/pedit_ip.sh
index d14efb2d23b2..9235674627ab 100755
--- a/tools/testing/selftests/net/forwarding/pedit_ip.sh
+++ b/tools/testing/selftests/net/forwarding/pedit_ip.sh
@@ -91,12 +91,20 @@ setup_prepare()
 	h1_create
 	h2_create
 	switch_create
+
+	if [ -f /proc/sys/net/bridge/bridge-nf-call-iptables ]; then
+		sysctl_set net.bridge.bridge-nf-call-iptables 0
+	fi
 }
 
 cleanup()
 {
 	pre_cleanup
 
+	if [ -f /proc/sys/net/bridge/bridge-nf-call-iptables ]; then
+		sysctl_restore net.bridge.bridge-nf-call-iptables
+	fi
+
 	switch_destroy
 	h2_destroy
 	h1_destroy
diff --git a/tools/testing/selftests/net/forwarding/tc_actions.sh b/tools/testing/selftests/net/forwarding/tc_actions.sh
index ea89e558672d..86edbc7e2489 100755
--- a/tools/testing/selftests/net/forwarding/tc_actions.sh
+++ b/tools/testing/selftests/net/forwarding/tc_actions.sh
@@ -223,7 +223,7 @@ mirred_egress_to_ingress_tcp_test()
 		ip_proto icmp \
 			action drop
 
-	ip vrf exec v$h1 ncat --recv-only -w10 -l -p 12345 -o $mirred_e2i_tf2 &
+	ip vrf exec v$h1 ncat --recv-only -w10 -l -p 12345 > $mirred_e2i_tf2 &
 	local rpid=$!
 	ip vrf exec v$h1 ncat -w1 --send-only 192.0.2.2 12345 <$mirred_e2i_tf1
 	wait -n $rpid
diff --git a/tools/testing/selftests/net/forwarding/vxlan_bridge_1d.sh b/tools/testing/selftests/net/forwarding/vxlan_bridge_1d.sh
index b43816dd998c..457f41d5e584 100755
--- a/tools/testing/selftests/net/forwarding/vxlan_bridge_1d.sh
+++ b/tools/testing/selftests/net/forwarding/vxlan_bridge_1d.sh
@@ -567,6 +567,21 @@ vxlan_encapped_ping_do()
 	local inner_tos=$1; shift
 	local outer_tos=$1; shift
 
+	local ipv4hdr=$(:
+		    )"45:"$(                      : IP version + IHL
+		    )"$inner_tos:"$(              : IP TOS
+		    )"00:54:"$(                   : IP total length
+		    )"99:83:"$(                   : IP identification
+		    )"40:00:"$(                   : IP flags + frag off
+		    )"40:"$(                      : IP TTL
+		    )"01:"$(                      : IP proto
+		    )"CHECKSUM:"$(                : IP header csum
+		    )"c0:00:02:03:"$(             : IP saddr: 192.0.2.3
+		    )"c0:00:02:01"$(              : IP daddr: 192.0.2.1
+		)
+	local checksum=$(payload_template_calc_checksum "$ipv4hdr")
+	ipv4hdr=$(payload_template_expand_checksum "$ipv4hdr" $checksum)
+
 	$MZ $dev -c $count -d 100msec -q \
 		-b $next_hop_mac -B $dest_ip \
 		-t udp tos=$outer_tos,sp=23456,dp=$VXPORT,p=$(:
@@ -577,16 +592,7 @@ vxlan_encapped_ping_do()
 		    )"$dest_mac:"$(               : ETH daddr
 		    )"$(mac_get w2):"$(           : ETH saddr
 		    )"08:00:"$(                   : ETH type
-		    )"45:"$(                      : IP version + IHL
-		    )"$inner_tos:"$(              : IP TOS
-		    )"00:54:"$(                   : IP total length
-		    )"99:83:"$(                   : IP identification
-		    )"40:00:"$(                   : IP flags + frag off
-		    )"40:"$(                      : IP TTL
-		    )"01:"$(                      : IP proto
-		    )"00:00:"$(                   : IP header csum
-		    )"c0:00:02:03:"$(             : IP saddr: 192.0.2.3
-		    )"c0:00:02:01:"$(             : IP daddr: 192.0.2.1
+		    )"$ipv4hdr:"$(                : IPv4 header
 		    )"08:"$(                      : ICMP type
 		    )"00:"$(                      : ICMP code
 		    )"8b:f2:"$(                   : ICMP csum
diff --git a/tools/testing/selftests/net/forwarding/vxlan_bridge_1d_ipv6.sh b/tools/testing/selftests/net/forwarding/vxlan_bridge_1d_ipv6.sh
index a603f7b0a08f..e642feeada0e 100755
--- a/tools/testing/selftests/net/forwarding/vxlan_bridge_1d_ipv6.sh
+++ b/tools/testing/selftests/net/forwarding/vxlan_bridge_1d_ipv6.sh
@@ -695,7 +695,7 @@ vxlan_encapped_ping_do()
 		    )"6"$(			  : IP version
 		    )"$inner_tos"$(               : Traffic class
 		    )"0:00:00:"$(                 : Flow label
-		    )"00:08:"$(                   : Payload length
+		    )"00:03:"$(                   : Payload length
 		    )"3a:"$(                      : Next header
 		    )"04:"$(                      : Hop limit
 		    )"$saddr:"$(		  : IP saddr
diff --git a/tools/testing/selftests/net/lib.sh b/tools/testing/selftests/net/lib.sh
index 0ec131b339bc..b40694573f4c 100644
--- a/tools/testing/selftests/net/lib.sh
+++ b/tools/testing/selftests/net/lib.sh
@@ -577,7 +577,7 @@ ip_link_has_flag()
 	local flag=$1; shift
 
 	local state=$(ip -j link show "$name" |
-		      jq --arg flag "$flag" 'any(.[].flags.[]; . == $flag)')
+		      jq --arg flag "$flag" 'any(.[].flags[]; . == $flag)')
 	[[ $state == true ]]
 }
 
diff --git a/tools/testing/selftests/net/packetdrill/ksft_runner.sh b/tools/testing/selftests/net/packetdrill/ksft_runner.sh
index b34e5cf0112e..0a97d5ae3469 100755
--- a/tools/testing/selftests/net/packetdrill/ksft_runner.sh
+++ b/tools/testing/selftests/net/packetdrill/ksft_runner.sh
@@ -13,6 +13,15 @@ declare -A ip_args=(
 		-D TFO_COOKIE_ZERO=b7c12350a90dc8f5
 		-D CMSG_LEVEL_IP=SOL_IP
 		-D CMSG_TYPE_RECVERR=IP_RECVERR"
+	[ipv4-mapped-ipv6]="--ip_version=ipv4-mapped-ipv6
+		--local_ip=192.168.0.1
+		--gateway_ip=192.168.0.1
+		--netmask_ip=255.255.0.0
+		--remote_ip=192.0.2.1
+		-D TFO_COOKIE=3021b9d889017eeb
+		-D TFO_COOKIE_ZERO=b7c12350a90dc8f5
+		-D CMSG_LEVEL_IP=SOL_IPV6
+		-D CMSG_TYPE_RECVERR=IPV6_RECVERR"
 	[ipv6]="--ip_version=ipv6
 		--mtu=1520
 		--local_ip=fd3d:0a0b:17d6::1
@@ -45,7 +54,7 @@ fi
 
 ip_versions=$(grep -E '^--ip_version=' $script | cut -d '=' -f 2)
 if [[ -z $ip_versions ]]; then
-	ip_versions="ipv4 ipv6"
+	ip_versions="ipv4 ipv6 ipv4-mapped-ipv6"
 elif [[ ! "$ip_versions" =~ ^ipv[46]$ ]]; then
 	ktap_exit_fail_msg "Too many or unsupported --ip_version: $ip_versions"
 	exit "$KSFT_FAIL"