Merge tag 'net-7.1-rc3' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net

Pull networking fixes from Jakub Kicinski:
 "Including fixes from Netfilter, IPsec, Bluetooth and WiFi.

  Current release - fix to a fix:

   - ipmr: add __rcu to netns_ipv4.mrt, make sure we hold the RCU lock
     in all relevant places

  Current release - new code bugs:

   - fixes for the recently added resizable hash tables

   - ipv6: make sure we default IPv6 tunnel drivers to =m now that IPv6
     itself is built in

   - drv: octeontx2-af: fixes for parser/CAM fixes

  Previous releases - regressions:

   - phy: micrel: fix LAN8814 QSGMII soft reset

   - wifi:
       - cw1200: revert "Fix locking in error paths"
       - ath12k: fix crash on WCN7850, due to adding the same queue
         buffer to a list multiple times

  Previous releases - always broken:

   - number of info leak fixes

   - ipv6: implement limits on extension header parsing

   - wifi: number of fixes for missing bound checks in the drivers

   - Bluetooth: fixes for races and locking issues

   - af_unix:
       - fix an issue between garbage collection and PEEK
       - fix yet another issue with OOB data

   - xfrm: esp: avoid in-place decrypt on shared skb frags

   - netfilter: replace skb_try_make_writable() by skb_ensure_writable()

   - openvswitch: vport: fix race between tunnel creation and linking
     leading to invalid memory accesses (type confusion)

   - drv: amd-xgbe: fix PTP addend overflow causing frozen clock

  Misc:

   - sched/isolation: make HK_TYPE_KTHREAD an alias of HK_TYPE_DOMAIN
     (for relevant IPVS change)"

* tag 'net-7.1-rc3' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net: (190 commits)
  net: sparx5: configure serdes for 1000BASE-X in sparx5_port_init()
  net: sparx5: fix wrong chip ids for TSN SKUs
  net: stmmac: dwmac-nuvoton: fix NULL pointer dereference in nvt_set_phy_intf_sel()
  tcp: Fix dst leak in tcp_v6_connect().
  ipmr: Call ipmr_fib_lookup() under RCU.
  net: phy: broadcom: Save PHY counters during suspend
  net/smc: fix missing sk_err when TCP handshake fails
  af_unix: Reject SIOCATMARK on non-stream sockets
  veth: fix OOB txq access in veth_poll() with asymmetric queue counts
  eth: fbnic: fix double-free of PCS on phylink creation failure
  net: ethernet: cortina: Drop half-assembled SKB
  selftests: mptcp: pm: restrict 'unknown' check to pm_nl_ctl
  selftests: mptcp: check output: catch cmd errors
  mptcp: pm: prio: skip closed subflows
  mptcp: pm: ADD_ADDR rtx: return early if no retrans
  mptcp: pm: ADD_ADDR rtx: skip inactive subflows
  mptcp: pm: ADD_ADDR rtx: resched blocked ADD_ADDR quicker
  mptcp: pm: ADD_ADDR rtx: free sk if last
  mptcp: pm: ADD_ADDR rtx: always decrease sk refcount
  mptcp: pm: ADD_ADDR rtx: fix potential data-race
  ...

13 files changed, 697 insertions, 22 deletions

diff --git a/tools/testing/selftests/drivers/net/hw/Makefile b/tools/testing/selftests/drivers/net/hw/Makefile
index 85ca4d1ecf9e..82809d5b2478 100644
--- a/tools/testing/selftests/drivers/net/hw/Makefile
+++ b/tools/testing/selftests/drivers/net/hw/Makefile
@@ -31,6 +31,7 @@ TEST_PROGS = \
 	hw_stats_l3.sh \
 	hw_stats_l3_gre.sh \
 	iou-zcrx.py \
+	ipsec_vxlan.py \
 	irq.py \
 	loopback.sh \
 	nic_timestamp.py \
diff --git a/tools/testing/selftests/drivers/net/hw/config b/tools/testing/selftests/drivers/net/hw/config
index dd50cb8a7911..8c132ace2b8d 100644
--- a/tools/testing/selftests/drivers/net/hw/config
+++ b/tools/testing/selftests/drivers/net/hw/config
@@ -3,6 +3,10 @@ CONFIG_FAIL_FUNCTION=y
 CONFIG_FAULT_INJECTION=y
 CONFIG_FAULT_INJECTION_DEBUG_FS=y
 CONFIG_FUNCTION_ERROR_INJECTION=y
+CONFIG_INET6_ESP=y
+CONFIG_INET6_ESP_OFFLOAD=y
+CONFIG_INET_ESP=y
+CONFIG_INET_ESP_OFFLOAD=y
 CONFIG_IO_URING=y
 CONFIG_IPV6=y
 CONFIG_IPV6_GRE=y
@@ -14,3 +18,4 @@ CONFIG_NETKIT=y
 CONFIG_NET_SCH_INGRESS=y
 CONFIG_UDMABUF=y
 CONFIG_VXLAN=y
+CONFIG_XFRM_USER=y
diff --git a/tools/testing/selftests/drivers/net/hw/ipsec_vxlan.py b/tools/testing/selftests/drivers/net/hw/ipsec_vxlan.py
new file mode 100755
index 000000000000..0740a4d85240
--- /dev/null
+++ b/tools/testing/selftests/drivers/net/hw/ipsec_vxlan.py
@@ -0,0 +1,204 @@
+#!/usr/bin/env python3
+# SPDX-License-Identifier: GPL-2.0
+"""Traffic test for VXLAN + IPsec crypto-offload."""
+
+import os
+
+from lib.py import ksft_run, ksft_exit, ksft_eq, ksft_ge
+from lib.py import ksft_variants, KsftNamedVariant, KsftSkipEx
+from lib.py import CmdExitFailure, NetDrvEpEnv, cmd, defer, ethtool, ip
+from lib.py import Iperf3Runner
+
+# Inner tunnel addresses - TEST-NET-2 (RFC 5737) / doc prefix (RFC 3849)
+INNER_V4_LOCAL = "198.51.100.1"
+INNER_V4_REMOTE = "198.51.100.2"
+INNER_V6_LOCAL = "2001:db8:100::1"
+INNER_V6_REMOTE = "2001:db8:100::2"
+
+# ESP parameters
+SPI_OUT = "0x1000"
+SPI_IN = "0x1001"
+# 128-bit key + 32-bit salt = 20 bytes hex, 128-bit ICV
+ESP_AEAD = "aead 'rfc4106(gcm(aes))' 0x" + "01" * 20 + " 128"
+
+
+def xfrm(args, host=None):
+    """Runs 'ip xfrm' via shell to preserve parentheses in algo names."""
+    cmd(f"ip xfrm {args}", shell=True, host=host)
+
+
+def check_xfrm_offload_support():
+    """Skips if iproute2 lacks xfrm offload support."""
+    out = cmd("ip xfrm state help", fail=False)
+    if "offload" not in out.stdout + out.stderr:
+        raise KsftSkipEx("iproute2 too old, missing xfrm offload")
+
+
+def check_esp_hw_offload(cfg):
+    """Skips if device lacks esp-hw-offload support."""
+    check_xfrm_offload_support()
+    try:
+        feat = ethtool(f"-k {cfg.ifname}", json=True)[0]
+    except (CmdExitFailure, IndexError) as e:
+        raise KsftSkipEx(f"can't query features: {e}") from e
+    if not feat.get("esp-hw-offload", {}).get("active"):
+        raise KsftSkipEx("Device does not support esp-hw-offload")
+
+
+def get_tx_drops(cfg):
+    """Returns TX dropped counter from the physical device."""
+    stats = ip("-s -s link show dev " + cfg.ifname, json=True)[0]
+    return stats["stats64"]["tx"]["dropped"]
+
+
+def setup_vxlan_ipsec(cfg, outer_ipver, inner_ipver):
+    """Sets up VXLAN tunnel with IPsec transport-mode crypto-offload."""
+    vxlan_name = f"vx{os.getpid()}"
+    local_addr = cfg.addr_v[outer_ipver]
+    remote_addr = cfg.remote_addr_v[outer_ipver]
+
+    if inner_ipver == "4":
+        inner_local = f"{INNER_V4_LOCAL}/24"
+        inner_remote = f"{INNER_V4_REMOTE}/24"
+        addr_extra = ""
+    else:
+        inner_local = f"{INNER_V6_LOCAL}/64"
+        inner_remote = f"{INNER_V6_REMOTE}/64"
+        addr_extra = " nodad"
+
+    if outer_ipver == "6":
+        vxlan_opts = "udp6zerocsumtx udp6zerocsumrx"
+    else:
+        vxlan_opts = "noudpcsum"
+
+    # VXLAN tunnel - local side
+    ip(f"link add {vxlan_name} type vxlan id 100 dstport 4789 {vxlan_opts} "
+       f"local {local_addr} remote {remote_addr} dev {cfg.ifname}")
+    defer(ip, f"link del {vxlan_name}")
+    ip(f"addr add {inner_local} dev {vxlan_name}{addr_extra}")
+    ip(f"link set {vxlan_name} up")
+
+    # VXLAN tunnel - remote side
+    ip(f"link add {vxlan_name} type vxlan id 100 dstport 4789 {vxlan_opts} "
+       f"local {remote_addr} remote {local_addr} dev {cfg.remote_ifname}",
+       host=cfg.remote)
+    defer(ip, f"link del {vxlan_name}", host=cfg.remote)
+    ip(f"addr add {inner_remote} dev {vxlan_name}{addr_extra}",
+       host=cfg.remote)
+    ip(f"link set {vxlan_name} up", host=cfg.remote)
+
+    # xfrm state - local outbound SA
+    xfrm(f"state add src {local_addr} dst {remote_addr} "
+         f"proto esp spi {SPI_OUT} "
+         f"{ESP_AEAD} "
+         f"mode transport offload crypto dev {cfg.ifname} dir out")
+    defer(xfrm, f"state del src {local_addr} dst {remote_addr} "
+                f"proto esp spi {SPI_OUT}")
+
+    # xfrm state - local inbound SA
+    xfrm(f"state add src {remote_addr} dst {local_addr} "
+         f"proto esp spi {SPI_IN} "
+         f"{ESP_AEAD} "
+         f"mode transport offload crypto dev {cfg.ifname} dir in")
+    defer(xfrm, f"state del src {remote_addr} dst {local_addr} "
+                f"proto esp spi {SPI_IN}")
+
+    # xfrm state - remote outbound SA (mirror, software crypto)
+    xfrm(f"state add src {remote_addr} dst {local_addr} "
+         f"proto esp spi {SPI_IN} "
+         f"{ESP_AEAD} "
+         f"mode transport",
+         host=cfg.remote)
+    defer(xfrm, f"state del src {remote_addr} dst {local_addr} "
+                f"proto esp spi {SPI_IN}", host=cfg.remote)
+
+    # xfrm state - remote inbound SA (mirror, software crypto)
+    xfrm(f"state add src {local_addr} dst {remote_addr} "
+         f"proto esp spi {SPI_OUT} "
+         f"{ESP_AEAD} "
+         f"mode transport",
+         host=cfg.remote)
+    defer(xfrm, f"state del src {local_addr} dst {remote_addr} "
+                f"proto esp spi {SPI_OUT}", host=cfg.remote)
+
+    # xfrm policy - local out
+    xfrm(f"policy add src {local_addr} dst {remote_addr} "
+         f"proto udp dport 4789 dir out "
+         f"tmpl src {local_addr} dst {remote_addr} proto esp mode transport")
+    defer(xfrm, f"policy del src {local_addr} dst {remote_addr} "
+                f"proto udp dport 4789 dir out")
+
+    # xfrm policy - local in
+    xfrm(f"policy add src {remote_addr} dst {local_addr} "
+         f"proto udp dport 4789 dir in "
+         f"tmpl src {remote_addr} dst {local_addr} proto esp mode transport")
+    defer(xfrm, f"policy del src {remote_addr} dst {local_addr} "
+                f"proto udp dport 4789 dir in")
+
+    # xfrm policy - remote out
+    xfrm(f"policy add src {remote_addr} dst {local_addr} "
+         f"proto udp dport 4789 dir out "
+         f"tmpl src {remote_addr} dst {local_addr} proto esp mode transport",
+         host=cfg.remote)
+    defer(xfrm, f"policy del src {remote_addr} dst {local_addr} "
+                f"proto udp dport 4789 dir out", host=cfg.remote)
+
+    # xfrm policy - remote in
+    xfrm(f"policy add src {local_addr} dst {remote_addr} "
+         f"proto udp dport 4789 dir in "
+         f"tmpl src {local_addr} dst {remote_addr} proto esp mode transport",
+         host=cfg.remote)
+    defer(xfrm, f"policy del src {local_addr} dst {remote_addr} "
+                f"proto udp dport 4789 dir in", host=cfg.remote)
+
+
+def _vxlan_ipsec_variants():
+    """Generates outer/inner IP version variants."""
+    for outer in ["4", "6"]:
+        for inner in ["4", "6"]:
+            yield KsftNamedVariant(f"outer_v{outer}_inner_v{inner}", outer, inner)
+
+
+@ksft_variants(_vxlan_ipsec_variants())
+def test_vxlan_ipsec_crypto_offload(cfg, outer_ipver, inner_ipver):
+    """Tests VXLAN+IPsec crypto-offload has no TX drops."""
+    cfg.require_ipver(outer_ipver)
+    check_esp_hw_offload(cfg)
+
+    setup_vxlan_ipsec(cfg, outer_ipver, inner_ipver)
+
+    if inner_ipver == "4":
+        inner_local = INNER_V4_LOCAL
+        inner_remote = INNER_V4_REMOTE
+        ping = "ping"
+    else:
+        inner_local = INNER_V6_LOCAL
+        inner_remote = INNER_V6_REMOTE
+        ping = "ping -6"
+
+    cmd(f"{ping} -c 1 -W 2 {inner_remote}")
+
+    drops_before = get_tx_drops(cfg)
+
+    runner = Iperf3Runner(cfg, server_ip=inner_local,
+                          client_ip=inner_remote)
+    bw_gbps = runner.measure_bandwidth(reverse=True)
+
+    cfg.wait_hw_stats_settle()
+    drops_after = get_tx_drops(cfg)
+
+    ksft_eq(drops_after - drops_before, 0,
+            comment="TX drops during VXLAN+IPsec")
+    ksft_ge(bw_gbps, 0.1,
+            comment="Minimum 100Mbps over VXLAN+IPsec")
+
+
+def main():
+    """Runs VXLAN+IPsec crypto-offload GSO selftest."""
+    with NetDrvEpEnv(__file__, nsim_test=False) as cfg:
+        ksft_run([test_vxlan_ipsec_crypto_offload], args=(cfg,))
+    ksft_exit()
+
+
+if __name__ == "__main__":
+    main()
diff --git a/tools/testing/selftests/drivers/net/lib/py/load.py b/tools/testing/selftests/drivers/net/lib/py/load.py
index f181fa2d38fc..e24660e5c27f 100644
--- a/tools/testing/selftests/drivers/net/lib/py/load.py
+++ b/tools/testing/selftests/drivers/net/lib/py/load.py
@@ -48,7 +48,10 @@ class Iperf3Runner:
         Starts the iperf3 client with the configured options.
         """
         cmdline = self._build_client(streams, duration, reverse)
-        return cmd(cmdline, background=background, host=self.env.remote)
+        kwargs = {"background": background, "host": self.env.remote}
+        if not background:
+            kwargs["timeout"] = duration + 5
+        return cmd(cmdline, **kwargs)
 
     def measure_bandwidth(self, reverse=False):
         """
diff --git a/tools/testing/selftests/net/Makefile b/tools/testing/selftests/net/Makefile
index a275ed584026..f3da38c54d27 100644
--- a/tools/testing/selftests/net/Makefile
+++ b/tools/testing/selftests/net/Makefile
@@ -96,6 +96,7 @@ TEST_PROGS := \
 	srv6_hl2encap_red_l2vpn_test.sh \
 	srv6_iptunnel_cache.sh \
 	stress_reuseport_listen.sh \
+	tcp_ecmp_failover.sh \
 	tcp_fastopen_backup_key.sh \
 	test_bpf.sh \
 	test_bridge_backup_port.sh \
diff --git a/tools/testing/selftests/net/mptcp/mptcp_lib.sh b/tools/testing/selftests/net/mptcp/mptcp_lib.sh
index 5fea7e7df628..989a5975dcea 100644
--- a/tools/testing/selftests/net/mptcp/mptcp_lib.sh
+++ b/tools/testing/selftests/net/mptcp/mptcp_lib.sh
@@ -474,20 +474,24 @@ mptcp_lib_wait_local_port_listen() {
 	wait_local_port_listen "${@}" "tcp"
 }
 
+# $1: error file, $2: cmd, $3: expected msg, [$4: expected error]
 mptcp_lib_check_output() {
 	local err="${1}"
 	local cmd="${2}"
 	local expected="${3}"
+	local exp_error="${4:-0}"
 	local cmd_ret=0
 	local out
 
-	if ! out=$(${cmd} 2>"${err}"); then
-		cmd_ret=${?}
-	fi
+	out=$(${cmd} 2>"${err}") || cmd_ret=1
 
-	if [ ${cmd_ret} -ne 0 ]; then
-		mptcp_lib_pr_fail "command execution '${cmd}' stderr"
-		cat "${err}"
+	if [ "${cmd_ret}" != "${exp_error}" ]; then
+		mptcp_lib_pr_fail "unexpected returned code for '${cmd}', info:"
+		if [ "${exp_error}" = 0 ]; then
+			cat "${err}"
+		else
+			echo "${out}"
+		fi
 		return 2
 	elif [ "${out}" = "${expected}" ]; then
 		return 0
diff --git a/tools/testing/selftests/net/mptcp/pm_netlink.sh b/tools/testing/selftests/net/mptcp/pm_netlink.sh
index 123d9d7a0278..04594dfc22b1 100755
--- a/tools/testing/selftests/net/mptcp/pm_netlink.sh
+++ b/tools/testing/selftests/net/mptcp/pm_netlink.sh
@@ -122,10 +122,12 @@ check()
 	local cmd="$1"
 	local expected="$2"
 	local msg="$3"
+	local exp_error="$4"
 	local rc=0
 
 	mptcp_lib_print_title "$msg"
-	mptcp_lib_check_output "${err}" "${cmd}" "${expected}" || rc=${?}
+	mptcp_lib_check_output "${err}" "${cmd}" "${expected}" "${exp_error}" ||
+		rc=${?}
 	if [ ${rc} -eq 2 ]; then
 		mptcp_lib_result_fail "${msg} # error ${rc}"
 		ret=${KSFT_FAIL}
@@ -158,13 +160,13 @@ check "show_endpoints" \
 			    "3,10.0.1.3,signal backup")" "dump addrs"
 
 del_endpoint 2
-check "get_endpoint 2" "" "simple del addr"
+check "get_endpoint 2" "" "simple del addr" 1
 check "show_endpoints" \
 	"$(format_endpoints "1,10.0.1.1" \
 			    "3,10.0.1.3,signal backup")" "dump addrs after del"
 
 add_endpoint 10.0.1.3 2>/dev/null
-check "get_endpoint 4" "" "duplicate addr"
+check "get_endpoint 4" "" "duplicate addr" 1
 
 add_endpoint 10.0.1.4 flags signal
 check "get_endpoint 4" "$(format_endpoints "4,10.0.1.4,signal")" "id addr increment"
@@ -173,7 +175,7 @@ for i in $(seq 5 9); do
 	add_endpoint "10.0.1.${i}" flags signal >/dev/null 2>&1
 done
 check "get_endpoint 9" "$(format_endpoints "9,10.0.1.9,signal")" "hard addr limit"
-check "get_endpoint 10" "" "above hard addr limit"
+check "get_endpoint 10" "" "above hard addr limit" 1
 
 del_endpoint 9
 for i in $(seq 10 255); do
@@ -192,9 +194,13 @@ check "show_endpoints" \
 flush_endpoint
 check "show_endpoints" "" "flush addrs"
 
-add_endpoint 10.0.1.1 flags unknown
-check "show_endpoints" "$(format_endpoints "1,10.0.1.1")" "ignore unknown flags"
-flush_endpoint
+# "unknown" flag is only supported by pm_nl_ctl
+if ! mptcp_lib_is_ip_mptcp; then
+	add_endpoint 10.0.1.1 flags unknown
+	check "show_endpoints" "$(format_endpoints "1,10.0.1.1")" \
+	      "ignore unknown flags"
+	flush_endpoint
+fi
 
 set_limits 9 1 2>/dev/null
 check "get_limits" "${default_limits}" "rcv addrs above hard limit"
diff --git a/tools/testing/selftests/net/openvswitch/openvswitch.sh b/tools/testing/selftests/net/openvswitch/openvswitch.sh
index b327d3061ed5..3cdd953f6813 100755
--- a/tools/testing/selftests/net/openvswitch/openvswitch.sh
+++ b/tools/testing/selftests/net/openvswitch/openvswitch.sh
@@ -26,6 +26,7 @@ tests="
 	netlink_checks				ovsnl: validate netlink attrs and settings
 	upcall_interfaces			ovs: test the upcall interfaces
 	tunnel_metadata				ovs: test extraction of tunnel metadata
+	tunnel_refcount				ovs: test tunnel vport reference cleanup
 	drop_reason				drop: test drop reasons are emitted
 	psample					psample: Sampling packets with psample"
 
@@ -830,6 +831,42 @@ test_tunnel_metadata() {
 	return 0
 }
 
+test_tunnel_refcount() {
+	sbxname="test_tunnel_refcount"
+	sbx_add "${sbxname}" || return 1
+
+	ovs_sbx "${sbxname}" ip netns add trefns || return 1
+	on_exit "ovs_sbx ${sbxname} ip netns del trefns"
+
+	for tun_type in gre vxlan geneve; do
+		info "testing ${tun_type} tunnel vport refcount"
+
+		ovs_sbx "${sbxname}" ip netns exec trefns \
+			python3 $ovs_base/ovs-dpctl.py \
+			add-dp dp-${tun_type} || return 1
+
+		ovs_sbx "${sbxname}" ip netns exec trefns \
+			python3 $ovs_base/ovs-dpctl.py \
+			add-if --no-lwt -t ${tun_type} \
+			dp-${tun_type} ovs-${tun_type}0 || return 1
+
+		ovs_wait ip -netns trefns link show \
+			ovs-${tun_type}0 >/dev/null 2>&1 || return 1
+
+		info "deleting dp - may hang if reference counting is broken"
+		ovs_sbx "${sbxname}" ip netns exec trefns \
+			python3 $ovs_base/ovs-dpctl.py \
+			del-dp dp-${tun_type} &
+
+		dev_removed() {
+			! ip -netns trefns link show "$1" >/dev/null 2>&1
+		}
+		ovs_wait dev_removed dp-${tun_type} || return 1
+		ovs_wait dev_removed ovs-${tun_type}0 || return 1
+	done
+	return 0
+}
+
 run_test() {
 	(
 	tname="$1"
diff --git a/tools/testing/selftests/net/openvswitch/ovs-dpctl.py b/tools/testing/selftests/net/openvswitch/ovs-dpctl.py
index 848f61fdcee0..bbe35e2718d2 100644
--- a/tools/testing/selftests/net/openvswitch/ovs-dpctl.py
+++ b/tools/testing/selftests/net/openvswitch/ovs-dpctl.py
@@ -11,7 +11,6 @@ import logging
 import math
 import multiprocessing
 import re
-import socket
 import struct
 import sys
 import time
@@ -2069,7 +2068,7 @@ class OvsVport(GenericNetlinkSocket):
         elif vport_type == "internal":
             return OvsVport.OVS_VPORT_TYPE_INTERNAL
         elif vport_type == "gre":
-            return OvsVport.OVS_VPORT_TYPE_INTERNAL
+            return OvsVport.OVS_VPORT_TYPE_GRE
         elif vport_type == "vxlan":
             return OvsVport.OVS_VPORT_TYPE_VXLAN
         elif vport_type == "geneve":
@@ -2121,6 +2120,7 @@ class OvsVport(GenericNetlinkSocket):
         )
 
         TUNNEL_DEFAULTS = [("geneve", 6081),
+                           ("gre", 0),
                            ("vxlan", 4789)]
 
         for tnl in TUNNEL_DEFAULTS:
@@ -2129,9 +2129,13 @@ class OvsVport(GenericNetlinkSocket):
                     dport = tnl[1]
 
                 if not lwt:
+                    if tnl[0] == "gre":
+                        # GRE tunnels have no options.
+                        break
+
                     vportopt = OvsVport.ovs_vport_msg.vportopts()
                     vportopt["attrs"].append(
-                        ["OVS_TUNNEL_ATTR_DST_PORT", socket.htons(dport)]
+                        ["OVS_TUNNEL_ATTR_DST_PORT", dport]
                     )
                     msg["attrs"].append(
                         ["OVS_VPORT_ATTR_OPTIONS", vportopt]
@@ -2145,6 +2149,9 @@ class OvsVport(GenericNetlinkSocket):
                                  geneve_port=dport,
                                  geneve_collect_metadata=True,
                                  geneve_udp_zero_csum6_rx=1)
+                    elif tnl[0] == "gre":
+                        ipr.link("add", ifname=vport_ifname, kind="gretap",
+                                 gre_collect_metadata=True)
                     elif tnl[0] == "vxlan":
                         ipr.link("add", ifname=vport_ifname, kind=tnl[0],
                                  vxlan_learning=0, vxlan_collect_metadata=1,
@@ -2563,7 +2570,7 @@ def print_ovsdp_full(dp_lookup_rep, ifindex, ndb=NDB(), vpl=OvsVport()):
             if vpo:
                 dpo = vpo.get_attr("OVS_TUNNEL_ATTR_DST_PORT")
                 if dpo:
-                    opts += " tnl-dport:%s" % socket.ntohs(dpo)
+                    opts += " tnl-dport:%s" % dpo
             print(
                 "  port %d: %s (%s%s)"
                 % (
@@ -2632,7 +2639,7 @@ def main(argv):
         "--ptype",
         type=str,
         default="netdev",
-        choices=["netdev", "internal", "geneve", "vxlan"],
+        choices=["netdev", "internal", "gre", "geneve", "vxlan"],
         help="Interface type (default netdev)",
     )
     addifcmd.add_argument(
@@ -2645,7 +2652,7 @@ def main(argv):
     addifcmd.add_argument(
         "-l",
         "--lwt",
-        type=bool,
+        action=argparse.BooleanOptionalAction,
         default=True,
         help="Use LWT infrastructure instead of vport (default true)."
     )
diff --git a/tools/testing/selftests/net/ovpn/test.sh b/tools/testing/selftests/net/ovpn/test.sh
index b50dbe45a4d0..c06e3135fbef 100755
--- a/tools/testing/selftests/net/ovpn/test.sh
+++ b/tools/testing/selftests/net/ovpn/test.sh
@@ -98,10 +98,10 @@ ovpn_run_basic_traffic() {
 		sleep 0.3
 		ovpn_cmd_ok "send baseline traffic to peer ${p}" \
 			ip netns exec ovpn_peer0 \
-			ping -qfc 500 -w 3 5.5.5.$((p + 1))
+			ping -qfc 100 -w 3 5.5.5.$((p + 1))
 		ovpn_cmd_ok "send large-payload traffic to peer ${p}" \
 			ip netns exec ovpn_peer0 \
-			ping -qfc 500 -s 3000 -w 3 5.5.5.$((p + 1))
+			ping -qfc 100 -s 3000 -w 3 5.5.5.$((p + 1))
 
 		wait "${tcpdump_pid1}" || return 1
 		wait "${tcpdump_pid2}" || return 1
diff --git a/tools/testing/selftests/net/tcp_ecmp_failover.sh b/tools/testing/selftests/net/tcp_ecmp_failover.sh
new file mode 100755
index 000000000000..5768aa8bff6a
--- /dev/null
+++ b/tools/testing/selftests/net/tcp_ecmp_failover.sh
@@ -0,0 +1,216 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+#
+# Copyright 2026 Google LLC.
+#
+# This test verifies TCP flow failover between ECMP routes
+# upon carrier loss on the active device.
+#
+#   socat  ----------------------------->  socat
+#                        |
+#           .-- veth-c1 -|- veth-s1 --.
+#   dummy0 -|            |            |-- dummy0
+#           '-- veth-c2 -|- veth-s2 --'
+#                        |
+#
+
+REQUIRE_JQ=no
+REQUIRE_MZ=no
+NUM_NETIFS=0
+
+source forwarding/lib.sh
+
+CLIENT_IP="10.0.59.1"
+SERVER_IP="10.0.92.1"
+CLIENT_IP6="2001:db8:5a9a::1"
+SERVER_IP6="2001:db8:9292::1"
+
+setup_server()
+{
+	IP="ip -n $server"
+	NS_EXEC="ip netns exec $server"
+
+	$IP link add dummy0 type dummy
+	$IP link set dummy0 up
+
+	$IP -4 addr add $SERVER_IP/32 dev dummy0
+	$IP -6 addr add $SERVER_IP6/128 dev dummy0 nodad
+
+	$IP link set veth-s1 up
+	$IP link set veth-s2 up
+
+	$IP -4 addr add 192.168.1.2/24 dev veth-s1
+	$IP -4 addr add 192.168.2.2/24 dev veth-s2
+
+	$IP -4 route add $CLIENT_IP/32 \
+		nexthop via 192.168.1.1 dev veth-s1 weight 1 \
+		nexthop via 192.168.2.1 dev veth-s2 weight 1
+
+	$IP -6 addr add 2001:db8:1::2/64 dev veth-s1 nodad
+	$IP -6 addr add 2001:db8:2::2/64 dev veth-s2 nodad
+
+	$IP -6 route add $CLIENT_IP6/128 \
+		nexthop via 2001:db8:1::1 dev veth-s1 weight 1 \
+		nexthop via 2001:db8:2::1 dev veth-s2 weight 1
+}
+
+setup_client()
+{
+	IP="ip -n $client"
+	NS_EXEC="ip netns exec $client"
+
+	$IP link add dummy0 type dummy
+	$IP link set dummy0 up
+
+	$IP -4 addr add $CLIENT_IP/32 dev dummy0
+	$IP -6 addr add $CLIENT_IP6/128 dev dummy0 nodad
+
+	$IP link set veth-c1 up
+	$IP link set veth-c2 up
+
+	$IP -4 addr add 192.168.1.1/24 dev veth-c1
+	$IP -4 addr add 192.168.2.1/24 dev veth-c2
+
+	$IP -4 route add $SERVER_IP/32 \
+		nexthop via 192.168.1.2 dev veth-c1 weight 1 \
+		nexthop via 192.168.2.2 dev veth-c2 weight 1
+
+	$IP -6 addr add 2001:db8:1::1/64 dev veth-c1 nodad
+	$IP -6 addr add 2001:db8:2::1/64 dev veth-c2 nodad
+
+	$IP -6 route add $SERVER_IP6/128 \
+		nexthop via 2001:db8:1::2 dev veth-c1 weight 1 \
+		nexthop via 2001:db8:2::2 dev veth-c2 weight 1
+
+	# By default, tcp_retries1=3 triggers a route refresh
+	# after 3 retransmits (~5s).  Ensure this never occurs
+	# for test stability.
+	$NS_EXEC sysctl -qw net.ipv4.tcp_retries1=100
+
+	# When NETDEV_CHANGE is issued for a dev tied to an ECMP
+	# route, RTNH_F_LINKDOWN is flagged and the sernum is
+	# bumped to invalidate the route via sk_dst_check().
+	#
+	# Without ignore_routes_with_linkdown=1, subsequent
+	# lookups may still select the same RTNH_F_LINKDOWN route.
+	$NS_EXEC sysctl -qw net.ipv4.conf.veth-c1.ignore_routes_with_linkdown=1
+	$NS_EXEC sysctl -qw net.ipv4.conf.veth-c2.ignore_routes_with_linkdown=1
+
+	$NS_EXEC sysctl -qw net.ipv6.conf.veth-c1.ignore_routes_with_linkdown=1
+	$NS_EXEC sysctl -qw net.ipv6.conf.veth-c2.ignore_routes_with_linkdown=1
+}
+
+setup()
+{
+	setup_ns client server
+
+	ip -n "$client" link add veth-c1 type veth peer veth-s1 netns "$server"
+	ip -n "$client" link add veth-c2 type veth peer veth-s2 netns "$server"
+
+	setup_server
+	setup_client
+}
+
+cleanup()
+{
+	cleanup_all_ns > /dev/null 2>&1
+}
+
+tcp_ecmp_failover()
+{
+	local pf=$1; shift
+	local server_ip=$1; shift
+	local client_ip=$1; shift
+
+	RET=0
+
+	tcpdump_start veth-s1 "$server"
+	tcpdump_start veth-s2 "$server"
+
+	ip netns exec "$server" \
+		socat -u TCP-LISTEN:8080,pf="$pf",bind="$server_ip",reuseaddr /dev/null &
+	server_pid=$!
+
+	# Wait for server to start listening.
+	# Sometimes client fails without this sleep.
+	sleep 1
+
+	ip netns exec "$client" \
+		socat -u /dev/zero TCP:"$server_ip":8080,pf="$pf",bind="$client_ip" &
+	client_pid=$!
+
+	# To capture enough packets.
+	sleep 3
+
+	tcpdump_stop veth-s1
+	tcpdump_stop veth-s2
+
+	pkts_s1=$(tcpdump_show veth-s1 | wc -l)
+	pkts_s2=$(tcpdump_show veth-s2 | wc -l)
+
+	tcpdump_cleanup veth-s1
+	tcpdump_cleanup veth-s2
+
+	# Detect the device chosen by the client
+	if [ "$pkts_s1" -gt "$pkts_s2" ]; then
+		veth_down=veth-s1
+		veth_up=veth-s2
+	else
+		veth_down=veth-s2
+		veth_up=veth-s1
+	fi
+
+	# Taking down $veth_down causes its peer to lose carrier,
+	# triggering NETDEV_CHANGE.  This flags RTNH_F_LINKDOWN
+	# and bumps the sernum for the route associated with that
+	# peer, invalidating the cached dst in the TCP socket.
+	#
+	# Consequently, sk_dst_check() fails, forcing the subsequent
+	# lookup to select the remaining healthy route via $veth_up.
+	ip -n "$server" link set "$veth_down" down
+
+	tcpdump_start "$veth_up" "$server"
+
+	# To capture enough packets.
+	sleep  3
+
+	tcpdump_stop "$veth_up"
+
+	kill -9 "$client_pid" > /dev/null 2>&1
+	kill -9 "$server_pid" > /dev/null 2>&1
+	wait 2> /dev/null
+
+	pkts=$(tcpdump_show $veth_up | wc -l)
+
+	tcpdump_cleanup "$veth_up"
+
+	if [ "$pkts" -lt 1000 ]; then
+		RET=$ksft_fail
+	fi
+}
+
+test_ipv4()
+{
+	setup
+	tcp_ecmp_failover IPv4 $SERVER_IP $CLIENT_IP
+	log_test "TCP IPv4 failover"
+	cleanup
+}
+
+test_ipv6()
+{
+	setup
+	tcp_ecmp_failover IPv6 "[$SERVER_IP6]" "[$CLIENT_IP6]"
+	log_test "TCP IPv6 failover"
+	cleanup
+}
+
+require_command socat
+require_command tcpdump
+
+trap cleanup EXIT
+
+test_ipv4
+test_ipv6
+
+exit "$EXIT_STATUS"
diff --git a/tools/testing/selftests/net/tls.c b/tools/testing/selftests/net/tls.c
index 9e2ccea13d70..30a236b8e9f7 100644
--- a/tools/testing/selftests/net/tls.c
+++ b/tools/testing/selftests/net/tls.c
@@ -946,6 +946,49 @@ TEST_F(tls, peek_and_splice)
 	EXPECT_EQ(memcmp(mem_send, mem_recv, send_len), 0);
 }
 
+TEST_F(tls, splice_to_pipe_small)
+{
+	int send_len = TLS_PAYLOAD_MAX_LEN;
+	char mem_send[TLS_PAYLOAD_MAX_LEN];
+	char mem_recv[TLS_PAYLOAD_MAX_LEN];
+	size_t total = 0;
+	int p[2];
+
+	memrnd(mem_send, sizeof(mem_send));
+
+	ASSERT_GE(pipe(p), 0);
+
+	/* Shrink pipe to 1 page (typically 4096 bytes) to force multiple
+	 * splice iterations for a 16384-byte TLS record.
+	 */
+	EXPECT_GE(fcntl(p[1], F_SETPIPE_SZ, 4096), 4096);
+
+	EXPECT_EQ(send(self->fd, mem_send, send_len, 0), send_len);
+
+	while (total < (size_t)send_len) {
+		ssize_t spliced, drained;
+
+		spliced = splice(self->cfd, NULL, p[1], NULL,
+				 send_len - total, 0);
+		EXPECT_GT(spliced, 0);
+		if (spliced <= 0)
+			break;
+
+		drained = read(p[0], mem_recv + total, spliced);
+		EXPECT_EQ(drained, spliced);
+		if (drained <= 0)
+			break;
+
+		total += drained;
+	}
+
+	EXPECT_EQ(total, (size_t)send_len);
+	EXPECT_EQ(memcmp(mem_send, mem_recv, send_len), 0);
+
+	close(p[0]);
+	close(p[1]);
+}
+
 #define MAX_FRAGS 48
 TEST_F(tls, splice_short)
 {
diff --git a/tools/testing/selftests/tc-testing/tc-tests/infra/qdiscs.json b/tools/testing/selftests/tc-testing/tc-tests/infra/qdiscs.json
index eefadd0546d3..b1f856cf62c1 100644
--- a/tools/testing/selftests/tc-testing/tc-tests/infra/qdiscs.json
+++ b/tools/testing/selftests/tc-testing/tc-tests/infra/qdiscs.json
@@ -1136,5 +1136,153 @@
         "teardown": [
             "$TC qdisc del dev $DUMMY handle 1: root"
         ]
+    },
+    {
+        "id": "7a5f",
+        "name": "Force red to dequeue from its child's gso_skb with qfq leaf",
+        "category": [
+            "qdisc",
+            "tbf",
+            "red",
+            "qfq"
+        ],
+        "plugins": {
+            "requires": "nsPlugin"
+        },
+        "setup": [
+            "$IP link set dev $DUMMY up || true",
+            "$IP addr add 10.10.11.10/24 dev $DUMMY || true",
+            "$TC qdisc add dev $DUMMY root handle 1: tbf rate 88bit burst 1661b peakrate 2257333 minburst 1024 limit 7b",
+            "$TC qdisc add dev $DUMMY parent 1: handle 2: red limit 757 min 16 max 24 avpkt 16",
+            "$TC qdisc add dev $DUMMY parent 2: handle 3: qfq",
+            "$TC class add dev $DUMMY classid 3:1 parent 3: qfq maxpkt 512 weight 1",
+            "$TC filter add dev $DUMMY parent 3: protocol ip prio 1 matchall classid 3:1 action ok"
+        ],
+        "cmdUnderTest": "ping -c 1 10.10.10.1 -W0.01 -I$DUMMY || true",
+        "expExitCode": "0",
+        "verifyCmd": "$TC -s -j qdisc ls dev $DUMMY parent 1:",
+        "matchJSON": [
+            {
+                "kind": "red",
+                "handle": "2:",
+                "bytes": 98,
+                "packets": 1,
+                "backlog": 0,
+                "qlen": 0
+            }
+        ],
+        "teardown": [
+            "$TC qdisc del dev $DUMMY handle 1: root"
+        ]
+    },
+    {
+        "id": "cdae",
+        "name": "Force sfb to dequeue from its child's gso_skb with qfq leaf",
+        "category": [
+            "qdisc",
+            "tbf",
+            "sfb",
+            "qfq"
+        ],
+        "plugins": {
+            "requires": "nsPlugin"
+        },
+        "setup": [
+            "$IP link set dev $DUMMY up || true",
+            "$IP addr