Merge tag 'net-next-6.16' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next

Pull networking updates from Paolo Abeni:
 "Core:

   - Implement the Device Memory TCP transmit path, allowing zero-copy
     data transmission on top of TCP from e.g. GPU memory to the wire.

   - Move all the IPv6 routing tables management outside the RTNL scope,
     under its own lock and RCU. The route control path is now 3x times
     faster.

   - Convert queue related netlink ops to instance lock, reducing again
     the scope of the RTNL lock. This improves the control plane
     scalability.

   - Refactor the software crc32c implementation, removing unneeded
     abstraction layers and improving significantly the related
     micro-benchmarks.

   - Optimize the GRO engine for UDP-tunneled traffic, for a 10%
     performance improvement in related stream tests.

   - Cover more per-CPU storage with local nested BH locking; this is a
     prep work to remove the current per-CPU lock in local_bh_disable()
     on PREMPT_RT.

   - Introduce and use nlmsg_payload helper, combining buffer bounds
     verification with accessing payload carried by netlink messages.

  Netfilter:

   - Rewrite the procfs conntrack table implementation, improving
     considerably the dump performance. A lot of user-space tools still
     use this interface.

   - Implement support for wildcard netdevice in netdev basechain and
     flowtables.

   - Integrate conntrack information into nft trace infrastructure.

   - Export set count and backend name to userspace, for better
     introspection.

  BPF:

   - BPF qdisc support: BPF-qdisc can be implemented with BPF struct_ops
     programs and can be controlled in similar way to traditional qdiscs
     using the "tc qdisc" command.

   - Refactor the UDP socket iterator, addressing long standing issues
     WRT duplicate hits or missed sockets.

  Protocols:

   - Improve TCP receive buffer auto-tuning and increase the default
     upper bound for the receive buffer; overall this improves the
     single flow maximum thoughput on 200Gbs link by over 60%.

   - Add AFS GSSAPI security class to AF_RXRPC; it provides transport
     security for connections to the AFS fileserver and VL server.

   - Improve TCP multipath routing, so that the sources address always
     matches the nexthop device.

   - Introduce SO_PASSRIGHTS for AF_UNIX, to allow disabling SCM_RIGHTS,
     and thus preventing DoS caused by passing around problematic FDs.

   - Retire DCCP socket. DCCP only receives updates for bugs, and major
     distros disable it by default. Its removal allows for better
     organisation of TCP fields to reduce the number of cache lines hit
     in the fast path.

   - Extend TCP drop-reason support to cover PAWS checks.

  Driver API:

   - Reorganize PTP ioctl flag support to require an explicit opt-in for
     the drivers, avoiding the problem of drivers not rejecting new
     unsupported flags.

   - Converted several device drivers to timestamping APIs.

   - Introduce per-PHY ethtool dump helpers, improving the support for
     dump operations targeting PHYs.

  Tests and tooling:

   - Add support for classic netlink in user space C codegen, so that
     ynl-c can now read, create and modify links, routes addresses and
     qdisc layer configuration.

   - Add ynl sub-types for binary attributes, allowing ynl-c to output
     known struct instead of raw binary data, clarifying the classic
     netlink output.

   - Extend MPTCP selftests to improve the code-coverage.

   - Add tests for XDP tail adjustment in AF_XDP.

  New hardware / drivers:

   - OpenVPN virtual driver: offload OpenVPN data channels processing to
     the kernel-space, increasing the data transfer throughput WRT the
     user-space implementation.

   - Renesas glue driver for the gigabit ethernet RZ/V2H(P) SoC.

   - Broadcom asp-v3.0 ethernet driver.

   - AMD Renoir ethernet device.

   - ReakTek MT9888 2.5G ethernet PHY driver.

   - Aeonsemi 10G C45 PHYs driver.

  Drivers:

   - Ethernet high-speed NICs:
       - nVidia/Mellanox (mlx5):
           - refactor the steering table handling to significantly
             reduce the amount of memory used
           - add support for complex matches in H/W flow steering
           - improve flow streeing error handling
           - convert to netdev instance locking
       - Intel (100G, ice, igb, ixgbe, idpf):
           - ice: add switchdev support for LLDP traffic over VF
           - ixgbe: add firmware manipulation and regions devlink support
           - igb: introduce support for frame transmission premption
           - igb: adds persistent NAPI configuration
           - idpf: introduce RDMA support
           - idpf: add initial PTP support
       - Meta (fbnic):
           - extend hardware stats coverage
           - add devlink dev flash support
       - Broadcom (bnxt):
           - add support for RX-side device memory TCP
       - Wangxun (txgbe):
           - implement support for udp tunnel offload
           - complete PTP and SRIOV support for AML 25G/10G devices

   - Ethernet NICs embedded and virtual:
       - Google (gve):
           - add device memory TCP TX support
       - Amazon (ena):
           - support persistent per-NAPI config
       - Airoha:
           - add H/W support for L2 traffic offload
           - add per flow stats for flow offloading
       - RealTek (rtl8211): add support for WoL magic packet
       - Synopsys (stmmac):
           - dwmac-socfpga 1000BaseX support
           - add Loongson-2K3000 support
           - introduce support for hardware-accelerated VLAN stripping
       - Broadcom (bcmgenet):
           - expose more H/W stats
       - Freescale (enetc, dpaa2-eth):
           - enetc: add MAC filter, VLAN filter RSS and loopback support
           - dpaa2-eth: convert to H/W timestamping APIs
       - vxlan: convert FDB table to rhashtable, for better scalabilty
       - veth: apply qdisc backpressure on full ring to reduce TX drops

   - Ethernet switches:
       - Microchip (kzZ88x3): add ETS scheduler support

   - Ethernet PHYs:
       - RealTek (rtl8211):
           - add support for WoL magic packet
           - add support for PHY LEDs

   - CAN:
       - Adds RZ/G3E CANFD support to the rcar_canfd driver.
       - Preparatory work for CAN-XL support.
       - Add self-tests framework with support for CAN physical interfaces.

   - WiFi:
       - mac80211:
           - scan improvements with multi-link operation (MLO)
       - Qualcomm (ath12k):
           - enable AHB support for IPQ5332
           - add monitor interface support to QCN9274
           - add multi-link operation support to WCN7850
           - add 802.11d scan offload support to WCN7850
           - monitor mode for WCN7850, better 6 GHz regulatory
       - Qualcomm (ath11k):
           - restore hibernation support
       - MediaTek (mt76):
           - WiFi-7 improvements
           - implement support for mt7990
       - Intel (iwlwifi):
           - enhanced multi-link single-radio (EMLSR) support on 5 GHz links
           - rework device configuration
       - RealTek (rtw88):
           - improve throughput for RTL8814AU
       - RealTek (rtw89):
           - add multi-link operation support
           - STA/P2P concurrency improvements
           - support different SAR configs by antenna

   - Bluetooth:
       - introduce HCI Driver protocol
       - btintel_pcie: do not generate coredump for diagnostic events
       - btusb: add HCI Drv commands for configuring altsetting
       - btusb: add RTL8851BE device 0x0bda:0xb850
       - btusb: add new VID/PID 13d3/3584 for MT7922
       - btusb: add new VID/PID 13d3/3630 and 13d3/3613 for MT7925
       - btnxpuart: implement host-wakeup feature"

* tag 'net-next-6.16' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next: (1611 commits)
  selftests/bpf: Fix bpf selftest build warning
  selftests: netfilter: Fix skip of wildcard interface test
  net: phy: mscc: Stop clearing the the UDPv4 checksum for L2 frames
  net: openvswitch: Fix the dead loop of MPLS parse
  calipso: Don't call calipso functions for AF_INET sk.
  selftests/tc-testing: Add a test for HFSC eltree double add with reentrant enqueue behaviour on netem
  net_sched: hfsc: Address reentrant enqueue adding class to eltree twice
  octeontx2-pf: QOS: Refactor TC_HTB_LEAF_DEL_LAST callback
  octeontx2-pf: QOS: Perform cache sync on send queue teardown
  net: mana: Add support for Multi Vports on Bare metal
  net: devmem: ncdevmem: remove unused variable
  net: devmem: ksft: upgrade rx test to send 1K data
  net: devmem: ksft: add 5 tuple FS support
  net: devmem: ksft: add exit_wait to make rx test pass
  net: devmem: ksft: add ipv4 support
  net: devmem: preserve sockc_err
  page_pool: fix ugly page_pool formatting
  net: devmem: move list_add to net_devmem_bind_dmabuf.
  selftests: netfilter: nft_queue.sh: include file transfer duration in log message
  net: phy: mscc: Fix memory leak when using one step timestamping
  ...

145 files changed, 9804 insertions, 1453 deletions

diff --git a/tools/Makefile b/tools/Makefile
index 5e1254eb66de..c31cbbd12c45 100644
--- a/tools/Makefile
+++ b/tools/Makefile
@@ -41,6 +41,7 @@ help:
 	@echo '  mm                     - misc mm tools'
 	@echo '  wmi			- WMI interface examples'
 	@echo '  x86_energy_perf_policy - Intel energy policy tool'
+	@echo '  ynl			- ynl headers, library, and python tool'
 	@echo ''
 	@echo 'You can do:'
 	@echo ' $$ make -C tools/ <tool>_install'
@@ -118,11 +119,14 @@ freefall: FORCE
 kvm_stat: FORCE
 	$(call descend,kvm/$@)
 
+ynl: FORCE
+	$(call descend,net/ynl)
+
 all: acpi counter cpupower gpio hv firewire \
 		perf selftests bootconfig spi turbostat usb \
 		virtio mm bpf x86_energy_perf_policy \
 		tmon freefall iio objtool kvm_stat wmi \
-		debugging tracing thermal thermometer thermal-engine
+		debugging tracing thermal thermometer thermal-engine ynl
 
 acpi_install:
 	$(call descend,power/$(@:_install=),install)
@@ -157,13 +161,16 @@ freefall_install:
 kvm_stat_install:
 	$(call descend,kvm/$(@:_install=),install)
 
+ynl_install:
+	$(call descend,net/$(@:_install=),install)
+
 install: acpi_install counter_install cpupower_install gpio_install \
 		hv_install firewire_install iio_install \
 		perf_install selftests_install turbostat_install usb_install \
 		virtio_install mm_install bpf_install x86_energy_perf_policy_install \
 		tmon_install freefall_install objtool_install kvm_stat_install \
 		wmi_install debugging_install intel-speed-select_install \
-		tracing_install thermometer_install thermal-engine_install
+		tracing_install thermometer_install thermal-engine_install ynl_install
 
 acpi_clean:
 	$(call descend,power/acpi,clean)
@@ -214,12 +221,15 @@ freefall_clean:
 build_clean:
 	$(call descend,build,clean)
 
+ynl_clean:
+	$(call descend,net/$(@:_clean=),clean)
+
 clean: acpi_clean counter_clean cpupower_clean hv_clean firewire_clean \
 		perf_clean selftests_clean turbostat_clean bootconfig_clean spi_clean usb_clean virtio_clean \
 		mm_clean bpf_clean iio_clean x86_energy_perf_policy_clean tmon_clean \
 		freefall_clean build_clean libbpf_clean libsubcmd_clean \
 		gpio_clean objtool_clean leds_clean wmi_clean firmware_clean debugging_clean \
 		intel-speed-select_clean tracing_clean thermal_clean thermometer_clean thermal-engine_clean \
-		sched_ext_clean
+		sched_ext_clean ynl_clean
 
 .PHONY: FORCE
diff --git a/tools/include/uapi/asm-generic/socket.h b/tools/include/uapi/asm-generic/socket.h
index aa5016ff3d91..f333a0ac4ee4 100644
--- a/tools/include/uapi/asm-generic/socket.h
+++ b/tools/include/uapi/asm-generic/socket.h
@@ -145,6 +145,8 @@
 
 #define SO_RCVPRIORITY		82
 
+#define SO_PASSRIGHTS		83
+
 #if !defined(__KERNEL__)
 
 #if __BITS_PER_LONG == 64 || (defined(__x86_64__) && defined(__ILP32__))
diff --git a/tools/include/uapi/linux/if_xdp.h b/tools/include/uapi/linux/if_xdp.h
index 42869770776e..44f2bb93e7e6 100644
--- a/tools/include/uapi/linux/if_xdp.h
+++ b/tools/include/uapi/linux/if_xdp.h
@@ -7,8 +7,8 @@
  *	      Magnus Karlsson <magnus.karlsson@intel.com>
  */
 
-#ifndef _LINUX_IF_XDP_H
-#define _LINUX_IF_XDP_H
+#ifndef _UAPI_LINUX_IF_XDP_H
+#define _UAPI_LINUX_IF_XDP_H
 
 #include <linux/types.h>
 
@@ -180,4 +180,4 @@ struct xdp_desc {
 /* TX packet carries valid metadata. */
 #define XDP_TX_METADATA (1 << 1)
 
-#endif /* _LINUX_IF_XDP_H */
+#endif /* _UAPI_LINUX_IF_XDP_H */
diff --git a/tools/include/uapi/linux/netdev.h b/tools/include/uapi/linux/netdev.h
index 7600bf62dbdf..7eb9571786b8 100644
--- a/tools/include/uapi/linux/netdev.h
+++ b/tools/include/uapi/linux/netdev.h
@@ -219,6 +219,7 @@ enum {
 	NETDEV_CMD_QSTATS_GET,
 	NETDEV_CMD_BIND_RX,
 	NETDEV_CMD_NAPI_SET,
+	NETDEV_CMD_BIND_TX,
 
 	__NETDEV_CMD_MAX,
 	NETDEV_CMD_MAX = (__NETDEV_CMD_MAX - 1)
diff --git a/tools/lib/bpf/libbpf.h b/tools/lib/bpf/libbpf.h
index e0605403f977..fdcee6a71e0f 100644
--- a/tools/lib/bpf/libbpf.h
+++ b/tools/lib/bpf/libbpf.h
@@ -1283,6 +1283,7 @@ enum bpf_tc_attach_point {
 	BPF_TC_INGRESS = 1 << 0,
 	BPF_TC_EGRESS  = 1 << 1,
 	BPF_TC_CUSTOM  = 1 << 2,
+	BPF_TC_QDISC   = 1 << 3,
 };
 
 #define BPF_TC_PARENT(a, b) 	\
@@ -1297,9 +1298,11 @@ struct bpf_tc_hook {
 	int ifindex;
 	enum bpf_tc_attach_point attach_point;
 	__u32 parent;
+	__u32 handle;
+	const char *qdisc;
 	size_t :0;
 };
-#define bpf_tc_hook__last_field parent
+#define bpf_tc_hook__last_field qdisc
 
 struct bpf_tc_opts {
 	size_t sz;
diff --git a/tools/lib/bpf/netlink.c b/tools/lib/bpf/netlink.c
index 68a2def17175..c997e69d507f 100644
--- a/tools/lib/bpf/netlink.c
+++ b/tools/lib/bpf/netlink.c
@@ -529,9 +529,9 @@ int bpf_xdp_query_id(int ifindex, int flags, __u32 *prog_id)
 }
 
 
-typedef int (*qdisc_config_t)(struct libbpf_nla_req *req);
+typedef int (*qdisc_config_t)(struct libbpf_nla_req *req, const struct bpf_tc_hook *hook);
 
-static int clsact_config(struct libbpf_nla_req *req)
+static int clsact_config(struct libbpf_nla_req *req, const struct bpf_tc_hook *hook)
 {
 	req->tc.tcm_parent = TC_H_CLSACT;
 	req->tc.tcm_handle = TC_H_MAKE(TC_H_CLSACT, 0);
@@ -539,6 +539,16 @@ static int clsact_config(struct libbpf_nla_req *req)
 	return nlattr_add(req, TCA_KIND, "clsact", sizeof("clsact"));
 }
 
+static int qdisc_config(struct libbpf_nla_req *req, const struct bpf_tc_hook *hook)
+{
+	const char *qdisc = OPTS_GET(hook, qdisc, NULL);
+
+	req->tc.tcm_parent = OPTS_GET(hook, parent, TC_H_ROOT);
+	req->tc.tcm_handle = OPTS_GET(hook, handle, 0);
+
+	return nlattr_add(req, TCA_KIND, qdisc, strlen(qdisc) + 1);
+}
+
 static int attach_point_to_config(struct bpf_tc_hook *hook,
 				  qdisc_config_t *config)
 {
@@ -552,6 +562,9 @@ static int attach_point_to_config(struct bpf_tc_hook *hook,
 		return 0;
 	case BPF_TC_CUSTOM:
 		return -EOPNOTSUPP;
+	case BPF_TC_QDISC:
+		*config = &qdisc_config;
+		return 0;
 	default:
 		return -EINVAL;
 	}
@@ -596,7 +609,7 @@ static int tc_qdisc_modify(struct bpf_tc_hook *hook, int cmd, int flags)
 	req.tc.tcm_family  = AF_UNSPEC;
 	req.tc.tcm_ifindex = OPTS_GET(hook, ifindex, 0);
 
-	ret = config(&req);
+	ret = config(&req, hook);
 	if (ret < 0)
 		return ret;
 
@@ -639,6 +652,7 @@ int bpf_tc_hook_destroy(struct bpf_tc_hook *hook)
 	case BPF_TC_INGRESS:
 	case BPF_TC_EGRESS:
 		return libbpf_err(__bpf_tc_detach(hook, NULL, true));
+	case BPF_TC_QDISC:
 	case BPF_TC_INGRESS | BPF_TC_EGRESS:
 		return libbpf_err(tc_qdisc_delete(hook));
 	case BPF_TC_CUSTOM:
diff --git a/tools/net/ynl/Makefile.deps b/tools/net/ynl/Makefile.deps
index f3269ce39e5b..90686e241157 100644
--- a/tools/net/ynl/Makefile.deps
+++ b/tools/net/ynl/Makefile.deps
@@ -20,13 +20,30 @@ CFLAGS_ethtool:=$(call get_hdr_inc,_LINUX_ETHTOOL_H,ethtool.h) \
 	$(call get_hdr_inc,_LINUX_ETHTOOL_NETLINK_H_,ethtool_netlink.h) \
 	$(call get_hdr_inc,_LINUX_ETHTOOL_NETLINK_GENERATED_H,ethtool_netlink_generated.h)
 CFLAGS_handshake:=$(call get_hdr_inc,_LINUX_HANDSHAKE_H,handshake.h)
+CFLAGS_lockd_netlink:=$(call get_hdr_inc,_LINUX_LOCKD_NETLINK_H,lockd_netlink.h)
 CFLAGS_mptcp_pm:=$(call get_hdr_inc,_LINUX_MPTCP_PM_H,mptcp_pm.h)
 CFLAGS_net_shaper:=$(call get_hdr_inc,_LINUX_NET_SHAPER_H,net_shaper.h)
 CFLAGS_netdev:=$(call get_hdr_inc,_LINUX_NETDEV_H,netdev.h)
 CFLAGS_nl80211:=$(call get_hdr_inc,__LINUX_NL802121_H,nl80211.h)
 CFLAGS_nlctrl:=$(call get_hdr_inc,__LINUX_GENERIC_NETLINK_H,genetlink.h)
 CFLAGS_nfsd:=$(call get_hdr_inc,_LINUX_NFSD_NETLINK_H,nfsd_netlink.h)
+CFLAGS_ovpn:=$(call get_hdr_inc,_LINUX_OVPN_H,ovpn.h)
 CFLAGS_ovs_datapath:=$(call get_hdr_inc,__LINUX_OPENVSWITCH_H,openvswitch.h)
 CFLAGS_ovs_flow:=$(call get_hdr_inc,__LINUX_OPENVSWITCH_H,openvswitch.h)
 CFLAGS_ovs_vport:=$(call get_hdr_inc,__LINUX_OPENVSWITCH_H,openvswitch.h)
+CFLAGS_rt-addr:=$(call get_hdr_inc,__LINUX_RTNETLINK_H,rtnetlink.h) \
+	$(call get_hdr_inc,__LINUX_IF_ADDR_H,if_addr.h)
+CFLAGS_rt-link:=$(call get_hdr_inc,__LINUX_RTNETLINK_H,rtnetlink.h) \
+	$(call get_hdr_inc,_LINUX_IF_LINK_H,if_link.h)
+CFLAGS_rt-neigh:=$(call get_hdr_inc,__LINUX_RTNETLINK_H,rtnetlink.h) \
+	$(call get_hdr_inc,__LINUX_NEIGHBOUR_H,neighbour.h)
+CFLAGS_rt-route:=$(call get_hdr_inc,__LINUX_RTNETLINK_H,rtnetlink.h)
+CFLAGS_rt-rule:=$(call get_hdr_inc,__LINUX_FIB_RULES_H,fib_rules.h)
+CFLAGS_tc:= $(call get_hdr_inc,__LINUX_RTNETLINK_H,rtnetlink.h) \
+	$(call get_hdr_inc,__LINUX_PKT_SCHED_H,pkt_sched.h) \
+	$(call get_hdr_inc,__LINUX_PKT_CLS_H,pkt_cls.h) \
+	$(call get_hdr_inc,_TC_CT_H,tc_act/tc_ct.h) \
+	$(call get_hdr_inc,_TC_MIRRED_H,tc_act/tc_mirred.h) \
+	$(call get_hdr_inc,_TC_SKBEDIT_H,tc_act/tc_skbedit.h) \
+	$(call get_hdr_inc,_TC_TUNNEL_KEY_H,tc_act/tc_tunnel_key.h)
 CFLAGS_tcp_metrics:=$(call get_hdr_inc,_LINUX_TCP_METRICS_H,tcp_metrics.h)
diff --git a/tools/net/ynl/generated/Makefile b/tools/net/ynl/generated/Makefile
index 21f9e299dc75..86e1e4a959a7 100644
--- a/tools/net/ynl/generated/Makefile
+++ b/tools/net/ynl/generated/Makefile
@@ -22,10 +22,9 @@ TOOL:=../pyynl/ynl_gen_c.py
 TOOL_RST:=../pyynl/ynl_gen_rst.py
 
 SPECS_DIR:=../../../../Documentation/netlink/specs
-GENS_PATHS=$(shell grep -nrI --files-without-match \
-		'protocol: netlink' \
-		$(SPECS_DIR))
-GENS=$(patsubst $(SPECS_DIR)/%.yaml,%,${GENS_PATHS})
+SPECS_PATHS=$(wildcard $(SPECS_DIR)/*.yaml)
+GENS_UNSUP=conntrack nftables
+GENS=$(filter-out ${GENS_UNSUP},$(patsubst $(SPECS_DIR)/%.yaml,%,${SPECS_PATHS}))
 SRCS=$(patsubst %,%-user.c,${GENS})
 HDRS=$(patsubst %,%-user.h,${GENS})
 OBJS=$(patsubst %,%-user.o,${GENS})
diff --git a/tools/net/ynl/lib/ynl-priv.h b/tools/net/ynl/lib/ynl-priv.h
index 3c09a7bbfba5..824777d7e05e 100644
--- a/tools/net/ynl/lib/ynl-priv.h
+++ b/tools/net/ynl/lib/ynl-priv.h
@@ -25,6 +25,7 @@ enum ynl_policy_type {
 	YNL_PT_UINT,
 	YNL_PT_NUL_STR,
 	YNL_PT_BITFIELD32,
+	YNL_PT_SUBMSG,
 };
 
 enum ynl_parse_result {
@@ -42,7 +43,10 @@ typedef int (*ynl_parse_cb_t)(const struct nlmsghdr *nlh,
 			      struct ynl_parse_arg *yarg);
 
 struct ynl_policy_attr {
-	enum ynl_policy_type type;
+	enum ynl_policy_type type:8;
+	__u8 is_submsg:1;
+	__u8 is_selector:1;
+	__u16 selector_type;
 	unsigned int len;
 	const char *name;
 	const struct ynl_policy_nest *nest;
@@ -94,12 +98,17 @@ struct ynl_ntf_base_type {
 	unsigned char data[] __attribute__((aligned(8)));
 };
 
+struct nlmsghdr *ynl_msg_start_req(struct ynl_sock *ys, __u32 id, __u16 flags);
+struct nlmsghdr *ynl_msg_start_dump(struct ynl_sock *ys, __u32 id);
+
 struct nlmsghdr *
 ynl_gemsg_start_req(struct ynl_sock *ys, __u32 id, __u8 cmd, __u8 version);
 struct nlmsghdr *
 ynl_gemsg_start_dump(struct ynl_sock *ys, __u32 id, __u8 cmd, __u8 version);
 
 int ynl_attr_validate(struct ynl_parse_arg *yarg, const struct nlattr *attr);
+int ynl_submsg_failed(struct ynl_parse_arg *yarg, const char *field_name,
+		      const char *sel_name);
 
 /* YNL specific helpers used by the auto-generated code */
 
@@ -204,11 +213,15 @@ static inline void *ynl_attr_data_end(const struct nlattr *attr)
 				     NLMSG_HDRLEN + fixed_hdr_sz); attr; \
 	     (attr) = ynl_attr_next(ynl_nlmsg_end_addr(nlh), attr))
 
-#define ynl_attr_for_each_nested(attr, outer)				\
+#define ynl_attr_for_each_nested_off(attr, outer, offset)		\
 	for ((attr) = ynl_attr_first(outer, outer->nla_len,		\
-				     sizeof(struct nlattr)); attr;	\
+				     sizeof(struct nlattr) + offset);	\
+	     attr;							\
 	     (attr) = ynl_attr_next(ynl_attr_data_end(outer), attr))
 
+#define ynl_attr_for_each_nested(attr, outer)				\
+	ynl_attr_for_each_nested_off(attr, outer, 0)
+
 #define ynl_attr_for_each_payload(start, len, attr)			\
 	for ((attr) = ynl_attr_first(start, len, 0); attr;		\
 	     (attr) = ynl_attr_next(start + len, attr))
diff --git a/tools/net/ynl/lib/ynl.c b/tools/net/ynl/lib/ynl.c
index c4da34048ef8..2a169c3c0797 100644
--- a/tools/net/ynl/lib/ynl.c
+++ b/tools/net/ynl/lib/ynl.c
@@ -45,8 +45,39 @@
 #define perr(_ys, _msg)			__yerr(&(_ys)->err, errno, _msg)
 
 /* -- Netlink boiler plate */
+static bool
+ynl_err_walk_is_sel(const struct ynl_policy_nest *policy,
+		    const struct nlattr *attr)
+{
+	unsigned int type = ynl_attr_type(attr);
+
+	return policy && type <= policy->max_attr &&
+		policy->table[type].is_selector;
+}
+
+static const struct ynl_policy_nest *
+ynl_err_walk_sel_policy(const struct ynl_policy_attr *policy_attr,
+			const struct nlattr *selector)
+{
+	const struct ynl_policy_nest *policy = policy_attr->nest;
+	const char *sel;
+	unsigned int i;
+
+	if (!policy_attr->is_submsg)
+		return policy;
+
+	sel = ynl_attr_get_str(selector);
+	for (i = 0; i <= policy->max_attr; i++) {
+		if (!strcmp(sel, policy->table[i].name))
+			return policy->table[i].nest;
+	}
+
+	return NULL;
+}
+
 static int
-ynl_err_walk_report_one(const struct ynl_policy_nest *policy, unsigned int type,
+ynl_err_walk_report_one(const struct ynl_policy_nest *policy,
+			const struct nlattr *selector, unsigned int type,
 			char *str, int str_sz, int *n)
 {
 	if (!policy) {
@@ -67,9 +98,34 @@ ynl_err_walk_report_one(const struct ynl_policy_nest *policy, unsigned int type,
 		return 1;
 	}
 
-	if (*n < str_sz)
-		*n += snprintf(str, str_sz - *n,
-			       ".%s", policy->table[type].name);
+	if (*n < str_sz) {
+		int sz;
+
+		sz = snprintf(str, str_sz - *n,
+			      ".%s", policy->table[type].name);
+		*n += sz;
+		str += sz;
+	}
+
+	if (policy->table[type].is_submsg) {
+		if (!selector) {
+			if (*n < str_sz)
+				*n += snprintf(str, str_sz, "(!selector)");
+			return 1;
+		}
+
+		if (ynl_attr_type(selector) !=
+		    policy->table[type].selector_type) {
+			if (*n < str_sz)
+				*n += snprintf(str, str_sz, "(!=selector)");
+			return 1;
+		}
+
+		if (*n < str_sz)
+			*n += snprintf(str, str_sz - *n, "(%s)",
+				       ynl_attr_get_str(selector));
+	}
+
 	return 0;
 }
 
@@ -78,6 +134,8 @@ ynl_err_walk(struct ynl_sock *ys, void *start, void *end, unsigned int off,
 	     const struct ynl_policy_nest *policy, char *str, int str_sz,
 	     const struct ynl_policy_nest **nest_pol)
 {
+	const struct ynl_policy_nest *next_pol;
+	const struct nlattr *selector = NULL;
 	unsigned int astart_off, aend_off;
 	const struct nlattr *attr;
 	unsigned int data_len;
@@ -96,6 +154,10 @@ ynl_err_walk(struct ynl_sock *ys, void *start, void *end, unsigned int off,
 	ynl_attr_for_each_payload(start, data_len, attr) {
 		astart_off = (char *)attr - (char *)start;
 		aend_off = (char *)ynl_attr_data_end(attr) - (char *)start;
+
+		if (ynl_err_walk_is_sel(policy, attr))
+			selector = attr;
+
 		if (aend_off <= off)
 			continue;
 
@@ -109,16 +171,20 @@ ynl_err_walk(struct ynl_sock *ys, void *start, void *end, unsigned int off,
 
 	type = ynl_attr_type(attr);
 
-	if (ynl_err_walk_report_one(policy, type, str, str_sz, &n))
+	if (ynl_err_walk_report_one(policy, selector, type, str, str_sz, &n))
+		return n;
+
+	next_pol = ynl_err_walk_sel_policy(&policy->table[type], selector);
+	if (!next_pol)
 		return n;
 
 	if (!off) {
 		if (nest_pol)
-			*nest_pol = policy->table[type].nest;
+			*nest_pol = next_pol;
 		return n;
 	}
 
-	if (!policy->table[type].nest) {
+	if (!next_pol) {
 		if (n < str_sz)
 			n += snprintf(str, str_sz, "!nest");
 		return n;
@@ -128,7 +194,7 @@ ynl_err_walk(struct ynl_sock *ys, void *start, void *end, unsigned int off,
 	start =  ynl_attr_data(attr);
 	end = start + ynl_attr_data_len(attr);
 
-	return n + ynl_err_walk(ys, start, end, off, policy->table[type].nest,
+	return n + ynl_err_walk(ys, start, end, off, next_pol,
 				&str[n], str_sz - n, nest_pol);
 }
 
@@ -191,12 +257,12 @@ ynl_ext_ack_check(struct ynl_sock *ys, const struct nlmsghdr *nlh,
 		n = snprintf(bad_attr, sizeof(bad_attr), "%sbad attribute: ",
 			     str ? " (" : "");
 
-		start = ynl_nlmsg_data_offset(ys->nlh, ys->family->hdr_len);
+		start = ynl_nlmsg_data_offset(ys->nlh, ys->req_hdr_len);
 		end = ynl_nlmsg_end_addr(ys->nlh);
 
 		off = ys->err.attr_offs;
 		off -= sizeof(struct nlmsghdr);
-		off -= ys->family->hdr_len;
+		off -= ys->req_hdr_len;
 
 		n += ynl_err_walk(ys, start, end, off, ys->req_policy,
 				  &bad_attr[n], sizeof(bad_attr) - n, NULL);
@@ -216,14 +282,14 @@ ynl_ext_ack_check(struct ynl_sock *ys, const struct nlmsghdr *nlh,
 		n = snprintf(miss_attr, sizeof(miss_attr), "%smissing attribute: ",
 			     bad_attr[0] ? ", " : (str ? " (" : ""));
 
-		start = ynl_nlmsg_data_offset(ys->nlh, ys->family->hdr_len);
+		start = ynl_nlmsg_data_offset(ys->nlh, ys->req_hdr_len);
 		end = ynl_nlmsg_end_addr(ys->nlh);
 
 		nest_pol = ys->req_policy;
 		if (tb[NLMSGERR_ATTR_MISS_NEST]) {
 			off = ynl_attr_get_u32(tb[NLMSGERR_ATTR_MISS_NEST]);
 			off -= sizeof(struct nlmsghdr);
-			off -= ys->family->hdr_len;
+			off -= ys->req_hdr_len;
 
 			n += ynl_err_walk(ys, start, end, off, ys->req_policy,
 					  &miss_attr[n], sizeof(miss_attr) - n,
@@ -231,7 +297,7 @@ ynl_ext_ack_check(struct ynl_sock *ys, const struct nlmsghdr *nlh,
 		}
 
 		n2 = 0;
-		ynl_err_walk_report_one(nest_pol, type, &miss_attr[n],
+		ynl_err_walk_report_one(nest_pol, NULL, type, &miss_attr[n],
 					sizeof(miss_attr) - n, &n2);
 		n += n2;
 
@@ -384,6 +450,15 @@ int ynl_attr_validate(struct ynl_parse_arg *yarg, const struct nlattr *attr)
 	return 0;
 }
 
+int ynl_submsg_failed(struct ynl_parse_arg *yarg, const char *field_name,
+		      const char *sel_name)
+{
+	yerr(yarg->ys, YNL_ERROR_SUBMSG_KEY,
+	     "Parsing error: Sub-message key not set (msg %s, key %s)",
+	     field_name, sel_name);
+	return YNL_PARSE_CB_ERROR;
+}
+
 /* Generic code */
 
 static void ynl_err_reset(struct ynl_sock *ys)
@@ -451,14 +526,14 @@ ynl_gemsg_start(struct ynl_sock *ys, __u32 id, __u16 flags,
 	return nlh;
 }
 
-void ynl_msg_start_req(struct ynl_sock *ys, __u32 id)
+struct nlmsghdr *ynl_msg_start_req(struct ynl_sock *ys, __u32 id, __u16 flags)
 {
-	ynl_msg_start(ys, id, NLM_F_REQUEST | NLM_F_ACK);
+	return ynl_msg_start(ys, id, NLM_F_REQUEST | NLM_F_ACK | flags);
 }
 
-void ynl_msg_start_dump(struct ynl_sock *ys, __u32 id)
+struct nlmsghdr *ynl_msg_start_dump(struct ynl_sock *ys, __u32 id)
 {
-	ynl_msg_start(ys, id, NLM_F_REQUEST | NLM_F_ACK | NLM_F_DUMP);
+	return ynl_msg_start(ys, id, NLM_F_REQUEST | NLM_F_ACK | NLM_F_DUMP);
 }
 
 struct nlmsghdr *
@@ -663,6 +738,7 @@ ynl_sock_create(const struct ynl_family *yf, struct ynl_error *yse)
 	struct sockaddr_nl addr;
 	struct ynl_sock *ys;
 	socklen_t addrlen;
+	int sock_type;
 	int one = 1;
 
 	ys = malloc(sizeof(*ys) + 2 * YNL_SOCKET_BUFFER_SIZE);
@@ -675,7 +751,9 @@ ynl_sock_create(const struct ynl_family *yf, struct ynl_error *yse)
 	ys->rx_buf = &ys->raw_buf[YNL_SOCKET_BUFFER_SIZE];
 	ys->ntf_last_next = &ys->ntf_first;
 
-	ys->socket = socket(AF_NETLINK, SOCK_RAW, NETLINK_GENERIC);
+	sock_type = yf->is_classic ? yf->classic_id : NETLINK_GENERIC;
+
+	ys->socket = socket(AF_NETLINK, SOCK_RAW, sock_type);
 	if (ys->socket < 0) {
 		__perr(yse, "failed to create a netlink socket");
 		goto err_free_sock;
@@ -708,8 +786,9 @@ ynl_sock_create(const struct ynl_family *yf, struct ynl_error *yse)
 	ys->portid = addr.nl_pid;
 	ys->seq = random();
 
-
-	if (ynl_sock_read_family(ys, yf->name)) {
+	if (yf->is_classic) {
+		ys->family_id = yf->classic_id;
+	} else if (ynl_sock_read_family(ys, yf->name)) {
 		if (yse)
 			memcpy(yse, &ys->err, sizeof(*yse));
 		goto err_close_sock;
@@ -791,13 +870,21 @@ static int ynl_ntf_parse(struct ynl_sock *ys, const struct nlmsghdr *nlh)
 	struct ynl_parse_arg yarg = { .ys = ys, };
 	const struct ynl_ntf_info *info;
 	struct ynl_ntf_base_type *rsp;
-	struct genlmsghdr *gehdr;
+	__u32 cmd;
 	int ret;
 
-	gehdr = ynl_nlmsg_data(nlh);
-	if (gehdr->cmd >= ys->family->ntf_info_size)
+	if (ys->family->is_classic) {
+		cmd = nlh->nlmsg_type;
+	} else {
+		struct genlmsghdr *gehdr;
+
+		gehdr = ynl_nlmsg_data(nlh);
+		cmd = gehdr->cmd;
+	}
+
+	if (cmd >= ys->family->ntf_info_size)
 		return YNL_PARSE_CB_ERROR;
-	info = &ys->family->ntf_info[gehdr->cmd];
+	info = &ys->family->ntf_info[cmd];
 	if (!info->cb)
 		return YNL_PARSE_CB_ERROR;
 
@@ -811,7 +898,7 @@ static int ynl_ntf_parse(struct ynl_sock *ys, const struct nlmsghdr *nlh)
 		goto err_free;
 
 	rsp->family = nlh->nlmsg_type;
-	rsp->cmd = gehdr->cmd;
+	rsp->cmd = cmd;
 
 	*ys->ntf_last_next = rsp;
 	ys->ntf_last_next = &rsp->next;
@@ -863,18 +950,23 @@ int ynl_error_parse(struct ynl_parse_arg *yarg, const char *msg)
 static int
 ynl_check_alien(struct ynl_sock *ys, const struct nlmsghdr *nlh, __u32 rsp_cmd)
 {
-	struct genlmsghdr *gehdr;
+	if (ys->family->is_classic) {
+		if (nlh->nlmsg_type != rsp_cmd)
+			return ynl_ntf_parse(ys, nlh);
+	} else {
+		struct genlmsghdr *gehdr;
+
+		if (ynl_nlmsg_data_len(nlh) < sizeof(*gehdr)) {
+			yerr(ys, YNL_ERROR_INV_RESP,
+			     "Kernel responded with truncated message");
+			return -1;
+		}
 
-	if (ynl_nlmsg_data_len(nlh) < sizeof(*gehdr)) {
-		yerr(ys, YNL_ERROR_INV_RESP,
-		     "Kernel responded with truncated message");
-		return -1;
+		gehdr = ynl_nlmsg_data(nlh);
+		if (gehdr->cmd != rsp_cmd)
+			return ynl_ntf_parse(ys, nlh);
 	}
 
-	gehdr = ynl_nlmsg_data(nlh);
-	if (gehdr->cmd != rsp_cmd)
-		return ynl_ntf_parse(ys, nlh);
-
 	return 0;
 }
 
diff --git a/tools/net/ynl/lib/ynl.h b/tools/net/ynl/lib/ynl.h
index 6cd570b283ea..db7c0591a63f 100644
--- a/tools/net/ynl/lib/ynl.h
+++ b/tools/net/ynl/lib/ynl.h
@@ -2,6 +2,7 @@
 #ifndef __YNL_C_H
 #define __YNL_C_H 1
 
+#include <stdbool.h>
 #include <stddef.h>
 #include <linux/genetlink.h>
 #include <linux/types.h>
@@ -22,6 +23,7 @@ enum ynl_error_code {
 	YNL_ERROR_INV_RESP,
 	YNL_ERROR_INPUT_INVALID,
 	YNL_ERROR_INPUT_TOO_BIG,
+	YNL_ERROR_SUBMSG_KEY,
 };
 
 /**
@@ -48,6 +50,8 @@ struct ynl_family {
 /* private: */
 	const char *name;
 	size_t hdr_len;
+	bool is_classic;
+	__u16 classic_id;
 	const struct ynl_ntf_info *ntf_info;
 	unsigned int ntf_info_size;
 };
@@ -77,11 +81,25 @@ struct ynl_sock {
 
 	struct nlmsghdr *nlh;
 	const struct ynl_policy_nest *req_policy;
+	size_t req_hdr_len;
 	unsigned char *tx_buf;
 	unsigned char *rx_buf;
 	unsigned char raw_buf[];
 };
 
+/**
+ * struct ynl_string - parsed individual string
+ * @len: length of the string (excluding terminating character)
+ * @str: value of the string
+ *
+ * Parsed and nul-terminated string. This struct is only used for arrays of
+ * strings. Non-array string members are placed directly in respective types.
+ */
+struct ynl_string {
+	unsigned int len;
+	char str[];
+};
+
 struct ynl_sock *
 ynl_sock_create(const struct ynl_family *yf, struct ynl_error *e);
 void ynl_sock_destroy(struct ynl_sock *ys);
diff --git a/tools/net/ynl/pyynl/cli.py b/tools/net/ynl/pyynl/cli.py
index 794e3c7dcc65..33ccc5c1843b 100755
--- a/tools/net/ynl/pyynl/cli.py
+++ b/tools/net/ynl/pyynl/cli.py
@@ -144,16 +144,17 @@ def main():
             ops = [ (item[0], json.loads(item[1]), args.flags or []) for item in args.multi ]
             reply = ynl.do_multi(ops)
             output(reply)
-    except NlError as e:
-        print(e)
-        exit(1)
 
-    if args.ntf:
-        try:
+        if args.ntf:
             for msg in ynl.poll_ntf(duration=args.duration):
                 output(msg)
-        except KeyboardInterrupt:
-            pass
+    except NlError as e:
+        print(e)
+        exit(1)
+    except KeyboardInterrupt:
+        pass
+    except BrokenPipeError:
+        pass
 
 
 if __name__ == "__main__":
diff --git a/tools/net/ynl/pyynl/lib/__init__.py b/tools/net/ynl/pyynl/lib/__init__.py
index 9137b83e580a..71518b9842ee 100644
--- a/tools/net/ynl/pyynl/lib/__init__.py
+++ b/tools/net/ynl/pyynl/lib/__init__.py
@@ -1,8 +1,9 @@
 # SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause
 
 from .nlspec import SpecAttr, SpecAttrSet, SpecEnumEntry, SpecEnumSet, \
-    SpecFamily, SpecOperation
+    SpecFamily, SpecOperation, SpecSubMessage, SpecSubMessageFormat
 from .ynl import YnlFamily, Netlink, NlError
 
 __all__ = ["SpecAttr", "SpecAttrSet", "SpecEnumEntry", "SpecEnumSet",
-           "SpecFamily", "SpecOperation", "YnlFamily", "Netlink", "NlError"]
+           "SpecFamily", "SpecOperation", "SpecSubMessage", "SpecSubMessageFormat",
+           "YnlFamily", "Netlink", "NlError"]
diff --git a/tools/net/ynl/pyynl/lib/ynl.py b/tools/net/ynl/pyynl/lib/ynl.py
index dcc2c6b298d6..55b59f6c79b8 100644
--- a/tools/net/ynl/pyynl/lib/ynl.py
+++ b/tools/net/ynl/pyynl/lib/ynl.py
@@ -594,7 +594,7 @@ class YnlFamily(SpecFamily):
             scalar_selector = self._get_scalar(attr, value["selector"])
             attr_payload = struct.pack("II", scalar_value, scalar_selector)
         elif attr['type'] == 'sub-message':
-            msg_format = self._resolve_selector(attr, search_attrs)
+            msg_format, _ = self._resolve_selector(attr, search_attrs)
             attr_payload = b''
             if msg_format.fixed_header:
                 attr_payload += self._encode_struct(msg_format.fixed_header, value)
@@ -712,10 +712,10 @@ class YnlFamily(SpecFamily):
             raise Exception(f"No message format for '{value}' in sub-message spec '{sub_msg}'")
 
         spec = sub_msg_spec.formats[value]
-        return spec
+        return spec, value
 
     def _decode_sub_msg(self, attr, attr_spec, search_attrs):
-        msg_format = self._resolve_selector(attr_spec, search_attrs)
+        msg_format, _ = self._resolve_selector(attr_spec, search_attrs)
         decoded = {}
         offset = 0
         if msg_format.fixed_header:
@@ -787,7 +787,7 @@ class YnlFamily(SpecFamily):
 
         return rsp
 
-    def _decode_extack_path(self, attrs, attr_set, offset, target):
+    def _decode_extack_path(self, attrs, attr_set, offset, target, search_attrs):
         for attr in attrs:
             try:
                 attr_spec = attr_set.attrs_by_val[attr.type]
@@ -801,26 +801,37 @@ class YnlFamily(SpecFamily):
             if offset + attr.full_len <= target:
                 offset += attr.full_len
                 continue
-            if attr_spec['type'] != 'nest':
+
+            pathname = attr_spec.name
+            if attr_spec['type'] == 'nest':
+                sub_attrs = self.attr_sets[attr_spec['nested-attributes']]
+                search_attrs = SpaceAttrs(sub_attrs, search_attrs.lookup(attr_spec['name']))
+            elif attr_spec['type'] == 'sub-message':
+                msg_format, value = self._resolve_selector(attr_spec, search_attrs)
+                if msg_format is None:
+                    raise Exception(f"Can't resolve sub-message of {attr_spec['name']} for extack")
+                sub_attrs = self.attr_sets[msg_format.attr_set]
+                pathname += f"({value})"
+            else:
                 raise Exception(f"Can't dive into {attr.type} ({attr_spec['name']}) for extack")
             offset += 4
-            subpath = self._decode_extack_path(NlAttrs(attr.raw),
-                                               self.attr_sets[attr_spec['nested-attributes']],
-                                               offset, target)
+            subpath = self._decode_extack_path(NlAttrs(attr.raw), sub_attrs,
+                                               offset, target, search_attrs)
             if subpath is None:
                 return None
-            return '.' + attr_spec.name + subpath
+            return '.' + pathname + subpath
 
         return None
 
-    def _decode_extack(self, request, op, extack):
+    def _decode_extack(self, request, op, extack, vals):
         if 'bad-attr-offs' not in extack:
             return
 
         msg = self.nlproto.decode(self, NlMsg(request, 0, op.attr_set), op)
         offset = self.nlproto.msghdr_size() + self._struct_size(op.fixed_header)
+        search_attrs = SpaceAttrs(op.attr_set, vals)
         path = self._decode_extack_path(msg.raw_attrs, op.attr_set, offset,
-                                        extack['bad-attr-offs'])
+                                        extack['bad-attr-offs'], search_attrs)
         if path:
             del extack['bad-attr-offs']
             extack['bad-attr'] = path
@@ -1012,7 +1023,7 @@ class YnlFamily(SpecFamily):
         for (method, vals, flags) in ops:
             op = self.ops[method]
             msg = self._encode_message(op, vals, flags, req_seq)
-            reqs_by_seq[req_seq] = (op, msg, flags)
+            reqs_by_seq[req_seq] = (op, vals, msg, flags)
             payload += msg
             req_seq += 1
 
@@ -1027,9 +1038,9 @@ class YnlFamily(SpecFamily):
             self._recv_dbg_print(reply, nms)
             for nl_msg in nms:
                 if nl_msg.nl_seq in reqs_by_seq:
-                    (op, req_msg, req_flags) = reqs_by_seq[nl_msg.nl_seq]
+                    (op, vals, req_msg, req_flags) = reqs_by_seq[nl_msg.nl_seq]
                     if nl_msg.extack:
-                        self._decode_extack(req_msg, op, nl_msg.extack)
+                        self._decode_extack(req_msg, op, nl_msg.extack, vals)
                 else:
                     op = None
                     req_flags = []
diff --git a/tools/net/ynl/pyynl/ynl_gen_c.py b/tools/net/ynl/pyynl/ynl_gen_c.py
index a7f08edbc235..76032e01c2e7 100755
--- a/tools/net/ynl/pyynl/ynl_gen_c.py
+++ b/tools/net/ynl/pyynl/ynl_gen_c.py
@@ -14,6 +14,7 @@ import yaml
 
 sys.path.append(pathlib.Path(__file__).resolve().parent.as_posix())
 from lib import SpecFamily, SpecAttrSet, SpecAttr, SpecOperation, SpecEnumSet, SpecEnumEntry
+from lib import SpecSubMessage, SpecSubMessageFormat
 
 
 def c_upper(name):
@@ -56,11 +57,20 @@ class Type(SpecAttr):
         self.request = False
         self.reply = False
 
+        self.is_selector = False
+
         if 'len' in attr:
             self.len = attr['len']
 
         if 'nested-attributes' in attr:
-            self.nested_attrs = attr['nested-attributes']
+            nested = attr['nested-attributes']
+        elif 'sub-message' in attr:
+            nested = attr['sub-message']
+        else:
+            nested = None
+
+        if nested:
+            self.nested_attrs = nested
             if self.nested_attrs == family.name:
                 self.nested_render_name = c_lower(f"{family.ident_name}")
             else:
@@ -119,7 +129,9 @@ class Type(SpecAttr):
         return c_upper(value)
 
     def resolve(self):
-        if 'name-prefix' in self.attr:
+        if 'parent-sub-message' in self.attr:
+            enum_name = self.attr['parent-sub-message'].enum_name
+        elif 'name-prefix' in self.attr:
             enum_name = f"{self.attr['name-prefix']}{self.name}"
         else:
             enum_name = f"{self.attr_set.name_prefix}{self.name}"
@@ -142,19 +154,19 @@ class Type(SpecAttr):
         return self.is_recursive() and not ri.op
 
     def presence_type(self):
-        return 'bit'
+        return 'present'
 
     def presence_member(self, space, type_filter):
         if self.presence_type() != type_filter:
             return
 
-        if self.presence_type() == 'bit':
+        if self.presence_type() == 'present':
             pfx = '__' if space == 'user' else ''
             return f"{pfx}u32 {self.c_name}:1;"
 
-        if self.presence_type() == 'len':
+        if self.presence_type() in {'len', 'count'}:
             pfx = '__' if space == 'user' else ''
-            return f"{pfx}u32 {self.c_name}_len;"
+            return f"{pfx}u32 {self.c_name};"
 
     def _complex_member_type(self, ri):
         return None
@@ -163,7 +175,7 @@ class Type(SpecAttr):
         return False
 
     def _free_lines(self, ri, var, ref):
-        if self.is_multi_val() or self.presence_type() == 'len':
+        if self.is_multi_val() or self.presence_type() in {'count', 'len'}:
             return [f'free({var}->{ref}{self.c_name});']
         return []
 
@@ -175,21 +187,21 @@ class Type(SpecAttr):
     def arg_member(self, ri):
         member = self._complex_member_type(ri)
         if member:
-            arg = [member + ' *' + self.c_name]
+            spc = ' ' if member[-1] != '*' else ''
+            arg = [member + spc + '*' + self.c_name]
             if self.presence_type() == 'count':
                 arg += ['unsigned int n_' + self.c_name]
             return arg
         raise Exception(f"Struct member not implemented for class type {self.type}")
 
     def struct_member(self, ri):
-        if self.is_multi_val():
-            ri.cw.p(f"unsigned int n_{self.c_name};")
         member = self._complex_member_type(ri)
         if member:
             ptr = '*' if self.is_multi_val() else ''
             if self.is_recursive_for_op(ri):
                 ptr = '*'
-            ri.cw.p(f"{member} {ptr}{self.c_name};")
+            spc = ' ' if member[-1] != '*' else ''
+            ri.cw.p(f"{member}{spc}{ptr}{self.c_name};")
             return
         members = self.arg_member(ri)
         for one in members:
@@ -215,10 +227,9 @@ class Type(SpecAttr):
         cw.p(f'[{self.enum_name}] = {"{"} .name = "{self.name}", {typol}{"}"},')
 
     def _attr_put_line(self, ri, var, line):
-        if self.presence_type() == 'bit':
-            ri.cw.p(f"if ({var}->_present.{self.c_name})")
-        elif self.presence_type() == 'len':
-            ri.cw.p(f"if ({var}->_present.{self.c_name}_len)")
+        presence = self.presence_type()
+        if presence in {'present', 'len'}:
+            ri.cw.p(f"if ({var}->_{presence}.{self.c_name})")
         ri.cw.p(f"{line};")
 
     def _attr_put_simple(self, ri, var, put_type):
@@ -248,7 +259,7 @@ class Type(SpecAttr):
         if not self.is_multi_val():
             ri.cw.p("if (ynl_attr_validate(yarg, attr))")
             ri.cw.p("return YNL_PARSE_CB_ERROR;")
-            if self.presence_type() == 'bit':
+            if self.presence_type() == 'present':
                 ri.cw.p(f"{var}->_present.{self.c_name} = 1;")
 
         if init_lines:
@@ -279,7 +290,8 @@ class Type(SpecAttr):
             presence = f"{var}->{'.'.join(ref[:i] + [''])}_present.{ref[i]}"
             # Every layer below last is a nest, so we know it uses bit presence
             # last layer is "self" and may be a complex type
-            if i == len(ref) - 1 and self.presence_type() != 'bit':
+            if i == len(ref) - 1 and self.presence_type() != 'present':
+                presence = f"{var}->{'.'.join(ref[:i] + [''])}_{self.presence_type()}.{ref[i]}"
                 continue
             code.append(presence + ' = 1;')
         ref_path = '.'.join(ref[:-1])
@@ -355,26 +367,10 @@ class TypeScalar(Type):
         if 'byte-order' in attr:
             self.byte_order_comment = f" /* {attr['byte-order']} */"
 
-        if 'enum' in self.attr:
-            enum = self.family.consts[self.attr['enum']]
-            low, high = enum.value_range()
-            if 'min' not in self.checks:
-                if low != 0 or self.type[0] == 's':
-                    self.checks['min'] = low
-            if 'max' not in self.checks:
-                self.checks['max'] = high
-
-        if 'min' in self.checks and 'max' in self.checks:
-            if self.get_limit('min') > self.get_limit('max'):
-                raise Exception(f'Invalid limit for "{self.name}" min: {self.get_limit("min")} max: {self.get_limit("max")}')
-            self.checks['range'] = True
-
-        low = min(self.get_limit('min', 0), self.get_limit('max', 0))
-        high = max(self.get_limit('min', 0), self.get_limit('max', 0))
-        if low < 0 and self.type[0] == 'u':
-            raise Exception(f'Invalid limit for "{self.name}" negative limit for unsigned type')
-        if low < -32768 or high > 32767:
-            self.checks['full-range'] = True
+        # Classic families have some funny enums, don't bother
+        # computing checks, since we only need them for kernel policies
+        if not family.is_classic():
+            self._init_checks()
 
         # Added by resolve():
         self.is_bitfield = None
@@ -399,6 +395,31 @@ class TypeScalar(Type):
         else:
             self.type_name = '__' + self.type
 
+    def _init_checks(self):
+        if 'enum' in self.attr:
+            enum = self.family.consts[self.attr['enum']]
+            low, high = enum.value_range()
+            if low == None and high == None:
+                self.checks['sparse'] = True
+            else:
+                if 'min' not in self.checks:
+                    if low != 0 or self.type[0] == 's':
+                        self.checks['min'] = low
+                if 'max' not in self.checks:
+                    self.checks['max'] = high
+
+        if 'min' in self.checks and 'max' in self.checks:
+            if self.get_limit('min') > self.get_limit('max'):
+                raise Exception(f'Invalid limit for "{self.name}" min: {self.get_limit("min")} max: {self.get_limit("max")}')
+            self.checks['range'] = True
+
+        low = min(self.get_limit('min', 0), self.get_limit('max', 0))
+        high = max(self.get_limit('min', 0), self.get_limit('max', 0))
+        if low < 0 and self.type[0] == 'u':
+            raise Exception(f'Invalid limit for "{self.name}" negative limit for unsigned type')
+        if low < -32768 or high > 32767:
+            self.checks['full-range'] = True
+
     def _attr_policy(self, policy):
         if 'flags-mask' in self.checks or self.is_bitfield:
             if self.is_bitfield:
@@ -417,6 +438,8 @@ class TypeScalar(Type):
             return f"NLA_POLICY_MIN({policy}, {self.get_limit_str('min')})"
         elif 'max' in self.checks:
             return f"NLA_POLICY_MAX({policy}, {self.get_limit_str('max')})"
+        elif 'sparse' in self.checks:
+            return f"NLA_POLICY_VALIDATE_FN({policy}, &{c_lower(self.enum_name)}_validate)"
         return super()._attr_policy(policy)
 
     def _attr_typol(self):
@@ -463,7 +486,10 @@ class TypeString(Type):
         ri.cw.p(f"char *{self.c_name};")
 
     def _attr_typol(self):
-        return f'.type = YNL_PT_NUL_STR, '
+        typol = f'.type = YNL_PT_NUL_STR, '
+        if self.is_selector:
+            typol += '.is_selector = 1, '
+        return typol
 
     def _attr_policy(self, policy):
         if 'exact-len' in self.checks:
@@ -488,7 +514,7 @@ class TypeString(Type):
         self._attr_put_simple(ri, var, 'str')
 
     def _attr_get(self, ri, var):
-        len_mem = var + '->_present.' + self.c_name + '_len'
+        len_mem = var + '->_len.' + self.c_name
         return [f"{len_mem} = len;",
                 f"{var}->{self.c_name} = malloc(len + 1);",
                 f"memcpy({var}->{self.c_name}, ynl_attr_get_str(attr), len);",
@@ -497,10 +523,10 @@ class TypeString(Type):
                ['unsigned int len;']
 
     def _setter_lines(self, ri, member, presence):
-        return [f"{presence}_len = strlen({self.c_name});",
-                f"{member} = malloc({presence}_len + 1);",
-                f'memcpy({member}, {self.c_name}, {presence}_len);',
-                f'{member}[{presence}_len] = 0;']
+        return [f"{presence} = strlen({self.c_name});",
+                f"{member} = malloc({presence} + 1);",
+                f'memcpy({member}, {self.c_name}, {presence});',
+                f'{member}[{presence}] = 0;']
 
 
 class TypeBinary(Type):
@@ -539,10 +565,10 @@ class TypeBinary(Type):
 
     def attr_put(self, ri, var):
         self._attr_put_line(ri, var, f"ynl_attr_put(nlh, {self.enum_name}, " +
-                            f"{var}->{self.c_name}, {var}->_present.{self.c_name}_len)")
+                            f"{var}->{self.c_name}, {var}->_len.{self.c_name})")
 
     def _attr_get(self, ri, var):
-        len_mem = var + '->_present.' + self.c_name + '_len'
+        len_mem = var + '->_len.' + self.c_name
         return [f"{len_mem} = len;",
                 f"{var}->{self.c_name} = malloc(len);",
                 f"memcpy({var}->{self.c_name}, ynl_attr_data(attr), len);"], \
@@ -550,9 +576,60 @@ class TypeBinary(Type):
                ['unsigned int len;']
 
     def _setter_lines(self, ri, member, presence):
-        return [f"{presence}_len = len;",
-                f"{member} = malloc({presence}_len);",
-                f'memcpy({member}, {self.c_name}, {presence}_len);']
+        return [f"{presence} = len;",
+                f"{member} = malloc({presence});",
+                f'memcpy({member}, {self.c_name}, {presence});']
+
+
+class TypeBinaryStruct(TypeBinary):
+    def struct_member(self, ri):
+        ri.cw.p(f'struct {c_lower(self.get("struct"))} *{self.c_name};')
+
+    def _attr_get(self, ri, var):
+        struct_sz = 'sizeof(struct ' + c_lower(self.get("struct")) + ')'
+        len_mem = var + '->_' + self.presence_type() + '.' + self.c_name
+        return [f"{len_mem} = len;",
+                f"if (len < {struct_sz})",
+                f"{var}->{self.c_name} = calloc(1, {struct_sz});",
+                "else",
+                f"{var}->{self.c_name} = malloc(len);",
+                f"memcpy({var}->{self.c_name}, ynl_attr_data(attr), len);"], \
+               ['len = ynl_attr_data_len(attr);'], \
+               ['unsigned int len;']
+
+
+class TypeBinaryScalarArray(TypeBinary):
+    def arg_member(self, ri):
+        return [f'__{self.get("sub-type")} *{self.c_name}', 'size_t count']
+
+    def presence_type(self):
+        return 'count'
+
+    def struct_member(self, ri):
+        ri.cw.p(f'__{self.get("sub-type")} *{self.c_name};')
+
+    def attr_put(self, ri, var):
+        presence = self.presence_type()
+        ri.cw.block_start(line=f"if ({var}->_{presence}.{self.c_name})")
+        ri.cw.p(f"i = {var}->_{presence}.{self.c_name} * sizeof(__{self.get('sub-type')});")
+        ri.cw.p(f"ynl_attr_put(nlh, {self.enum_name}, " +
+                f"{var}->{self.c_name}, i);")
+        ri.cw.block_end()
+
+    def _attr_get(self, ri, var):
+        len_mem = var + '->_count.' + self.c_name
+        return [f"{len_mem} = len / sizeof(__{self.get('sub-type')});",
+                f"len = {len_mem} * sizeof(__{self.get('sub-type')});",
+                f"{var}->{self.c_name} = malloc(len);",
+                f"memcpy({var}->{self.c_name}, ynl_attr_data(attr), len);"], \
+               ['len = ynl_attr_data_len(attr);'], \
+               ['unsigned int len;']
+
+    def _setter_lines(self, ri, member, presence):
+        return [f"{presence} = count;",
+                f"count *= sizeof(__{self.get('sub-type')});",
+                f"{member} = malloc(count);",
+                f'memcpy({member}, {self.c_name}, count);']
 
 
 class TypeBitfield32(Type):
@@ -608,7 +685,11 @@ class TypeNest(Type):
                             f"{self.enum_name}, {at}{var}->{self.c_name})")
 
     def _attr_get(self, ri, var):
-        get_lines = [f"if ({self.nested_render_name}_parse(&parg, attr))",
+        pns = self.family.pure_nested_structs[self.nested_attrs]
+        args = ["&parg", "attr"]
+        for sel in pns.external_selectors():
+            args.append(f'{var}->{sel.name}')
+        get_lines = [f"if ({self.nested_render_name}_parse({', '.join(args)}))",
                      "return YNL_PARSE_CB_ERROR;"]
         init_lines = [f"parg.rsp_policy = &{self.nested_render_name}_nest;",
                       f"parg.data = &{var}->{self.c_name};"]
@@ -638,22 +719,40 @@ class TypeMultiAttr(Type):
     def _complex_member_type(self, ri):
         if 'type' not in self.attr or self.attr['type'] == 'nest':
             return self.nested_struct_type
+        elif self.attr['type'] == 'binary' and 'struct' in self.attr:
+            return None  # use arg_member()
+        elif self.attr['type'] == 'string':
+            return 'struct ynl_string *'
         elif self.attr['type'] in scalars:
             scalar_pfx = '__' if ri.ku_space == 'user' else ''
             return scalar_pfx + self.attr['type']
         else:
             raise Exception(f"Sub-type {self.attr['type']} not supported yet")
 
+    def arg_member(self, ri):
+        if self.type == 'binary' and 'struct' in self.attr:
+            return [f'struct {c_lower(self.attr["struct"])} *{self.c_name}',
+                    f'unsigned int n_{self.c_name}']
+        return super().arg_member(ri)
+
     def free_needs_iter(self):
-        return 'type' not in self.attr or self.attr['type'] == 'nest'
+        return self.attr['type'] in {'nest', 'string'}
 
     def _free_lines(self, ri, var, ref):
         lines = []
         if self.attr['type'] in scalars:
             lines += [f"free({var}->{ref}{self.c_name});"]
+        elif self.attr['type'] == 'binary':
+            lines += [f"free({var}->{ref}{self.c_name});"]
+        elif self.attr['type'] == 'string':
+            lines += [
+                f"for (i = 0; i < {var}->{ref}_count.{self.c_name}; i++)",
+                f"free({var}->{ref}{self.c_name}[i]);",
+                f"free({var}->{ref}{self.c_name});",
+            ]
         elif 'type' not in self.attr or self.attr['type'] == 'nest':
             lines += [
-                f"for (i = 0; i < {var}->{ref}n_{self.c_name}; i++)",
+                f"for (i = 0; i < {var}->{ref}_count.{self.c_name}; i++)",
                 f'{self.nested_render_name}_free(&{var}->{ref}{self.c_name}[i]);',
                 f"free({var}->{ref}{self.c_name});",
             ]
@@ -673,18 +772,22 @@ class TypeMultiAttr(Type):
     def attr_put(self, ri, var):
         if self.attr['type'] in scalars:
             put_type = self.type
-            ri.cw.p(f"for (i = 0; i < {var}->n_{self.c_name}; i++)")
+            ri.cw.p(f"for (i = 0; i < {var}->_count.{self.c_name}; i++)")
             ri.cw.p(f"ynl_attr_put_{put_type}(nlh, {self.enum_name}, {var}->{self.c_name}[i]);")
+        elif self.attr['type'] == 'binary' and 'struct' in self.attr:
+            ri.cw.p(f"for (i = 0; i < {var}->_count.{self.c_name}; i++)")
+            ri.cw.p(f"ynl_attr_put(nlh, {self.enum_name}, &{var}->{self.c_name}[i], sizeof(struct {c_lower(self.attr['struct'])}));")
+        elif self.attr['type'] == 'string':
+            ri.cw.p(f"for (i = 0; i < {var}->_count.{self.c_name}; i++)")
+            ri.cw.p(f"ynl_attr_put_str(nlh, {self.enum_name}, {var}->{self.c_name}[i]->str);")
         elif 'type' not in self.attr or self.attr['type'] == 'nest':
-            ri.cw.p(f"for (i = 0; i < {var}->n_{self.c_name}; i++)")
+            ri.cw.p(f"for (i = 0; i < {var}->_count.{self.c_name}; i++)")
             self._attr_put_line(ri, var, f"{self.nested_render_name}_put(nlh, " +
                                 f"{self.enum_name}, &{var}->{self.c_name}[i])")
         else:
             raise Exception(f"Put of MultiAttr sub-type {self.attr['type']} not supported yet")
 
     def _setter_lines(self, ri, member, presence):
-        # For multi-attr we have a count, not presence, hack up the presence
-        presence = presence[:-(len('_present.') + len(self.c_name))] + "n_" + self.c_name
         return [f"{member} = {self.c_name};",
                 f"{presence} = n_{self.c_name};"]
 
@@ -702,12 +805,22 @@ class TypeArrayNest(Type):
         elif self.attr['sub-type'] in scalars:
             scalar_pfx = '__' if ri.ku_space == 'user' else ''
             return scalar_pfx + self.attr['sub-type']
+        elif self.attr['sub-type'] == 'binary' and 'exact-len' in self.checks:
+            return None  # use arg_member()
         else:
             raise Exception(f"Sub-type {self.attr['sub-type']} not supported yet")
 
+    def arg_member(self, ri):
+        if self.sub_type == 'binary' and 'exact-len' in self.checks:
+            return [f'unsigned char (*{self.c_name})[{self.checks["exact-len"]}]',
+                    f'unsigned int n_{self.c_name}']
+        return super().arg_member(ri)
+
     def _attr_typol(self):
         if self.attr['sub-type'] in scalars:
             return f'.type = YNL_PT_U{c_upper(self.sub_type[1:])}, '
+        elif self.attr['sub-type'] == 'binary' and 'exact-len' in self.checks:
+            return f'.type = YNL_PT_BINARY, .len = {self.checks["exact-len"]}, '
         else:
             return f'.type = YNL_PT_NEST, .nest = &{self.nested_render_name}_nest, '
 
@@ -717,10 +830,31 @@ class TypeArrayNest(Type):
                      'ynl_attr_for_each_nested(attr2, attr) {',
                      '\tif (ynl_attr_validate(yarg, attr2))',
                      '\t\treturn YNL_PARSE_CB_ERROR;',
-                     f'\t{var}->n_{self.c_name}++;',
+                     f'\t{var}->_count.{self.c_name}++;',
                      '}']
         return get_lines, None, local_vars
 
+    def attr_put(self, ri, var):
+        ri.cw.p(f'array = ynl_attr_nest_start(nlh, {self.enum_name});')
+        if self.sub_type in scalars:
+            put_type = self.sub_type
+            ri.cw.block_start(line=f'for (i = 0; i < {var}->_count.{self.c_name}; i++)')
+            ri.cw.p(f"ynl_attr_put_{put_type}(nlh, i, {var}->{self.c_name}[i]);")
+            ri.cw.block_end()
+        elif self.sub_type == 'binary' and 'exact-len' in self.checks:
+            ri.cw.p(f'for (i = 0; i < {var}->_count.{self.c_name}; i++)')
+            ri.cw.p(f"ynl_attr_put(nlh, i, {var}->{self.c_name}[i], {self.checks['exact-len']});")
+        elif self.sub_type == 'nest':
+            ri.cw.p(f'for (i = 0; i < {var}->_count.{self.c_name}; i++)')
+            ri.cw.p(f"{self.nested_render_name}_put(nlh, i, &{var}->{self.c_name}[i]);")
+        else:
+            raise Exception(f"Put for ArrayNest sub-type {self.attr['sub-type']} not supported, yet")
+        ri.cw.p('ynl_attr_nest_end(nlh, array);')
+
+    def _setter_lines(self, ri, member, presence):
+        return [f"{member} = {self.c_name};",
+                f"{presence} = n_{self.c_name};"]
+
 
 class TypeNestTypeValue(Type):
     def _complex_member_type(self, ri):
@@ -752,14 +886,71 @@ class TypeNestTypeValue(Type):
         return get_lines, init_lines, local_vars
 
 
+class TypeSubMessage(TypeNest):
+    def __init__(self, family, attr_set, attr, value):
+        super().__init__(family, attr_set, attr, value)
+
+        self.selector = Selector(attr, attr_set)
+
+    def _attr_typol(self):
+        typol = f'.type = YNL_PT_NEST, .nest = &{self.nested_render_name}_nest, '
+        typol += '.is_submsg = 1, '
+        # Reverse-parsing of the policy (ynl_err_walk() in ynl.c) does not
+        # support external selectors. No family uses sub-messages with external
+        # selector for requests so this is fine for now.
+        if not self.selector.is_external():
+            typol += f'.selector_type = {self.attr_set[self["selector"]].value} '
+        return typol
+
+    def _attr_get(self, ri, var):
+        sel = c_lower(self['selector'])
+        if self.selector.is_external():
+            sel_var = f"_sel_{sel}"
+        else:
+            sel_var = f"{var}->{sel}"
+        get_lines = [f'if (!{sel_var})',
+                     f'return ynl_submsg_failed(yarg, "%s", "%s");' %
+                        (self.name, self['selector']),
+                    f"if ({self.nested_render_name}_parse(&parg, {sel_var}, attr))",
+                     "return YNL_PARSE_CB_ERROR;"]
+        init_lines = [f"parg.rsp_policy = &{self.nested_render_name}_nest;",
+                      f"parg.data = &{var}->{self.c_name};"]
+        return get_lines, init_lines, None
+
+
+class Selector:
+    def __init__(self, msg_attr, attr_set):
+        self.name = msg_attr["selector"]
+
+        if self.name in attr_set:
+            self.attr = attr_set[self.name]
+            self.attr.is_selector = True
+            self._external = False
+        else:
+            # The selector will need to get passed down thru the structs
+            self.attr = None
+            self._external = True
+
+    def set_attr(self, attr):
+        self.attr = attr
+
+    def is_external(self):
+        return self._external
+
+
 class Struct:
-    def __init__(self, family, space_name, type_list=None, inherited=None):
+    def __init__(self, family, space_name, type_list=None, fixed_header=None,
+                 inherited=None, submsg=None):
         self.family = family
         self.space_name = space_name
         self.attr_set = family.attr_sets[space_name]
         # Use list to catch comparisons with empty sets
         self._inherited = inherited if inherited is not None else []
         self.inherited = []
+        self.fixed_header = None
+        if fixed_header:
+            self.fixed_header = 'struct ' + c_lower(fixed_header)
+        self.submsg = submsg
 
         self.nested = type_list is None
         if family.name == c_lower(space_name):
@@ -809,6 +1000,19 @@ class Struct:
             raise Exception("Inheriting different members not supported")
         self.inherited = [c_lower(x) for x in sorted(self._inherited)]
 
+    def external_selectors(self):
+        sels = []
+        for name, attr in self.attr_list:
+            if isinstance(attr, TypeSubMessage) and attr.selector.is_external():
+                sels.append(attr.selector)
+        return sels
+
+    def free_needs_iter(self):
+        for _, attr in self.attr_list:
+            if attr.free_needs_iter():
+                return True
+        return False
+
 
 class EnumEntry(SpecEnumEntry):
     def __init__(self, enum_set, yaml, prev, value_start):
@@ -862,7 +1066,7 @@ class EnumSet(SpecEnumSet):
         high = max([x.value for x in self.entries.values()])
 
         if high - low + 1 != len(self.entries):
-            raise Exception("Can't get value range for a noncontiguous enum")
+            return None, None
 
         return low, high
 
@@ -909,18 +1113,25 @@ class AttrSet(SpecAttrSet):
         elif elem['type'] == 'string':
             t = TypeString(self.family, self, elem, value)
         elif elem['type'] == 'binary':
-            t = TypeBinary(self.family, self, elem, value)
+            if 'struct' in elem:
+                t = TypeBinaryStruct(self.family, self, elem, value)
+            elif elem.get('sub-type') in scalars:
+                t = TypeBinaryScalarArray(self.family, self, elem, value)
+            else:
+                t = TypeBinary(self.family, self, elem, value)
         elif elem['type'] == 'bitfield32':
             t = TypeBitfield32(self.family, self, elem, value)
         elif elem['type'] == 'nest':
             t = TypeNest(self.family, self, elem, value)
         elif elem['type'] == 'indexed-array' and 'sub-type' in elem:
-            if elem["sub-type"] in ['nest', 'u32']:
+            if elem["sub-type"] in ['binary', 'nest', 'u32']:
                 t = TypeArrayNest(self.family, self, elem, value)
             else:
                 raise Exception(f'new_attr: unsupported sub-type {elem["sub-type"]}')
         elif elem['type'] == 'nest-type-value':
             t = TypeNestTypeValue(self.family, self, elem, value)
+        elif elem['type'] == 'sub-message':
+            t = TypeSubMessage(self.family, self, elem, value)
         else:
             raise Exception(f"No typed class for type {elem['type']}")
 
@@ -932,6 +1143,14 @@ class AttrSet(SpecAttrSet):
 
 class Operation(SpecOperation):
     def __init__(self, family, yaml, req_value, rsp_value):
+        # Fill in missing operation properties (for fixed hdr-only msgs)
+        for mode in ['do', 'dump', 'event']:
+            for direction in ['request', 'reply']:
+                try:
+                    yaml[mode][direction].setdefault('attributes', [])
+                except KeyError:
+                    pass
+
         super().__init__(family, yaml, req_value, rsp_value)
 
         self.render_name = c_lower(family.ident_name + '_' + self.name)
@@ -957,6 +1176,16 @@ class Operation(SpecOperation):
         self.has_ntf = True
 
 
+class SubMessage(SpecSubMessage):
+    def __init__(self, family, yaml):
+        super().__init__(family, yaml)
+
+        self.render_name = c_lower(family.ident_name + '-' + yaml['name'])
+
+    def resolve(self):
+        self.resolve_up(super())
+
+
 class Family(SpecFamily):
     def __init__(self, file_name, exclude_ops):
         # Added by resolve:
@@ -993,9 +1222,6 @@ class Family(SpecFamily):
     def resolve(self):
         self.resolve_up(super())
 
-        if self.yaml.get('protocol', 'genetlink') not in {'genetlink', 'genetlink-c', 'genetlink-legacy'}:
-            raise Exception("Codegen only supported for genetlink")
-
         self.c_name = c_lower(self.ident_name)
         if 'name-prefix' in self.yaml['operations']:
             self.op_prefix = c_upper(self.yaml['operations']['name-prefix'])
@@ -1018,7 +1244,7 @@ class Family(SpecFamily):
 
         # dict space-name -> 'request': set(attrs), 'reply': set(attrs)
         self.root_sets = dict()
-        # dict space-name -> set('request', 'reply')
+        # dict space-name -> Struct
         self.pure_nested_structs = dict()
 
         self._mark_notify()
@@ -1027,6 +1253,7 @@ class Family(SpecFamily):
         self._load_root_sets()
         self._load_nested_sets()
         self._load_attr_use()
+        self._load_selector_passing()
         self._load_hooks()
 
         self.kernel_policy = self.yaml.get('kernel-policy', 'split')
@@ -1042,6 +1269,12 @@ class Family(SpecFamily):
     def new_operation(self, elem, req_value, rsp_value):
         return Operation(self, elem, req_value, rsp_value)
 
+    def new_sub_message(self, elem):
+        return SubMessage(self, elem)
+
+    def is_classic(self):
+        return self.proto == 'netlink-raw'
+
     def _mark_notify(self):
         for op in self.msgs.values():
             if 'notify' in op:
@@ -1091,20 +1324,85 @@ class Family(SpecFamily):
             for _, spec in self.attr_sets[name].items():
                 if 'nested-attributes' in spec:
                     nested = spec['nested-attributes']
-                    # If the unknown nest we hit is recursive it's fine, it'll be a pointer
-                    if self.pure_nested_structs[nested].recursive:
-                        continue
-                    if nested not in pns_key_seen:
-                        # Dicts are sorted, this will make struct last
-                        struct = self.pure_nested_structs.pop(name)
-                        self.pure_nested_structs[name] = struct
-                        finished = False
-                        break
+                elif 'sub-message' in spec:
+                    nested = spec.sub_message
+                else:
+                    continue
+
+                # If the unknown nest we hit is recursive it's fine, it'll be a pointer
+                if self.pure_nested_structs[nested].recursive:
+                    continue
+                if nested not in pns_key_seen:
+                    # Dicts are sorted, this will make struct last
+                    struct = self.pure_nested_structs.pop(name)
+                    self.pure_nested_structs[name] = struct
+                    finished = False
+                    break
             if finished:
                 pns_key_seen.add(name)
             else:
                 pns_key_list.append(name)
 
+    def _load_nested_set_nest(self, spec):
+        inherit = set()
+        nested = spec['nested-attributes']
+        if nested not in self.root_sets:
+            if nested not in self.pure_nested_structs:
+                self.pure_nested_structs[nested] = \
+                    Struct(self, nested, inherited=inherit,
+                           fixed_header=spec.get('fixed-header'))
+        else:
+            raise Exception(f'Using attr set as root and nested not supported - {nested}')
+
+        if 'type-value' in spec:
+            if nested in self.root_sets:
+                raise Exception("Inheriting members to a space used as root not supported")
+            inherit.update(set(spec['type-value']))
+        elif spec['type'] == 'indexed-array':
+            inherit.add('idx')
+        self.pure_nested_structs[nested].set_inherited(inherit)
+
+        return nested
+
+    def _load_nested_set_submsg(self, spec):
+        # Fake the struct type for the sub-message itself
+        # its not a attr_set but codegen wants attr_sets.
+        submsg = self.sub_msgs[spec["sub-message"]]
+        nested = submsg.name
+
+        attrs = []
+        for name, fmt in submsg.formats.items():
+            attr = {
+                "name": name,
+                "parent-sub-message": spec,
+            }
+            if 'attribute-set' in fmt:
+                attr |= {
+                    "type": "nest",
+                    "nested-attributes": fmt['attribute-set'],
+                }
+                if 'fixed-header' in fmt:
+                    attr |= { "fixed-header": fmt["fixed-header"] }
+            elif 'fixed-header' in fmt:
+                attr |= {
+                    "type": "binary",
+                    "struct": fmt["fixed-header"],
+                }
+            else:
+                attr["type"] = "flag"
+            attrs.append(attr)
+
+        self.attr_sets[nested] = AttrSet(self, {
+            "name": nested,
+            "name-pfx": self.name + '-' + spec.name + '-',
+            "attributes": attrs
+        })
+
+        if nested not in self.pure_nested_structs:
+            self.pure_nested_structs[nested] = Struct(self, nested, submsg=submsg)
+
+        return nested
+
     def _load_nested_sets(self):
         attr_set_queue = list(self.root_sets.keys())
         attr_set_seen = set(self.root_sets.keys())
@@ -1112,37 +1410,32 @@ class Family(SpecFamily):
         while len(attr_set_queue):
             a_set = attr_set_queue.pop(0)
             for attr, spec in self.attr_sets[a_set].items():
-                if 'nested-attributes' not in spec:
+                if 'nested-attributes' in spec:
+                    nested = self._load_nested_set_nest(spec)
+                elif 'sub-message' in spec:
+                    nested = self._load_nested_set_submsg(spec)
+                else:
                     continue
 
-                nested = spec['nested-attributes']
                 if nested not in attr_set_seen:
                     attr_set_queue.append(nested)
                     attr_set_seen.add(nested)
 
-                inherit = set()
-                if nested not in self.root_sets:
-                    if nested not in self.pure_nested_structs:
-                        self.pure_nested_structs[nested] = Struct(self, nested, inherited=inherit)
-                else:
-                    raise Exception(f'Using attr set as root and nested not supported - {nested}')
-
-                if 'type-value' in spec:
-                    if nested in self.root_sets:
-                        raise Exception("Inheriting members to a space used as root not supported")
-                    inherit.update(set(spec['type-value']))
-                elif spec['type'] == 'indexed-array':
-                    inherit.add('idx')
-                self.pure_nested_structs[nested].set_inherited(inherit)
-
         for root_set, rs_members in self.root_sets.items():
             for attr, spec in self.attr_sets[root_set].items():
                 if 'nested-attributes' in spec:
                     nested = spec['nested-attributes']
+                elif 'sub-message' in spec:
+                    nested = spec.sub_message
+                else:
+                    nested = None
+
+                if nested:
                     if attr in rs_members['request']:
                         self.pure_nested_structs[nested].request = True
                     if attr in rs_members['reply']:
                         self.pure_nested_structs[nested].reply = True
+
                     if spec.is_multi_val():
                         child = self.pure_nested_structs.get(nested)
                         child.in_multi_val = True
@@ -1152,20 +1445,26 @@ class Family(SpecFamily):
         # Propagate the request / reply / recursive
         for attr_set, struct in reversed(self.pure_nested_structs.items()):
             for _, spec in self.attr_sets[attr_set].items():
-                if 'nested-attributes' in spec:
-                    child_name = spec['nested-attributes']
-                    struct.child_nests.add(child_name)
-                    child = self.pure_nested_structs.get(child_name)
-                    if child:
-                        if not child.recursive:
-                            struct.child_nests.update(child.child_nests)
-                        child.request |= struct.request
-                        child.reply |= struct.reply
-                        if spec.is_multi_val():
-                            child.in_multi_val = True
                 if attr_set in struct.child_nests:
                     struct.recursive = True
 
+                if 'nested-attributes' in spec:
+                    child_name = spec['nested-attributes']
+                elif 'sub-message' in spec:
+                    child_name = spec.sub_message
+                else:
+                    continue
+
+                struct.child_nests.add(child_name)
+                child = self.pure_nested_structs.get(child_name)
+                if child:
+                    if not child.recursive:
+                        struct.child_nests.update(child.child_nests)
+                    child.request |= struct.request
+                    child.reply |= struct.reply
+                    if spec.is_multi_val():
+                        child.in_multi_val = True
+
         self._sort_pure_types()
 
     def _load_attr_use(self):
@@ -1184,6 +1483,30 @@ class Family(SpecFamily):
                 if attr in rs_members['reply']:
                     spec.set_reply()
 
+    def _load_selector_passing(self):
+        def all_structs():
+            for k, v in reversed(self.pure_nested_structs.items()):
+                yield k, v
+            for k, _ in self.root_sets.items():
+                yield k, None  # we don't have a struct, but it must be terminal
+
+        for attr_set, struct in all_structs():
+            for _, spec in self.attr_sets[attr_set].items():
+                if 'nested-attributes' in spec:
+                    child_name = spec['nested-attributes']
+                elif 'sub-message' in spec:
+                    child_name = spec.sub_message
+                else:
+                    continue
+
+                child = self.pure_nested_structs.get(child_name)
+                for selector in child.external_selectors():
+                    if selector.name in self.attr_sets[attr_set]:
+                        sel_attr = self.attr_sets[attr_set][selector.name]
+                        selector.set_attr(sel_attr)
+                    else:
+                        raise Exception("Passing selector thru more than one layer not supported")
+
     def _load_global_policy(self):
         global_set = set()
         attr_set_name = None
@@ -1233,12 +1556,19 @@ class RenderInfo:
         self.op_mode = op_mode
         self.op = op
 
-        self.fixed_hdr = None
+        fixed_hdr = op.fixed_header if op else None
+        self.fixed_hdr_len = 'ys->family->hdr_len'
         if op and op.fixed_header:
-            self.fixed_hdr = 'struct ' + c_lower(op.fixed_header)
+            if op.fixed_header != family.fixed_header:
+                if family.is_classic():
+                    self.fixed_hdr_len = f"sizeof(struct {c_lower(fixed_hdr)})"
+                else:
+                    raise Exception(f"Per-op fixed header not supported, yet")
+
 
         # 'do' and 'dump' response parsing is identical
         self.type_consistent = True
+        self.type_oneside = False
         if op_mode != 'do' and 'dump' in op:
             if 'do' in op:
                 if ('reply' in op['do']) != ('reply' in op["dump"]):
@@ -1246,7 +1576,8 @@ class RenderInfo:
                 elif 'reply' in op['do'] and op["do"]["reply"] != op["dump"]["reply"]:
                     self.type_consistent = False
             else:
-                self.type_consistent = False
+                self.type_consistent = True
+                self.type_oneside = True
 
         self.attr_set = attr_set
         if not self.attr_set:
@@ -1264,15 +1595,26 @@ class RenderInfo:
 
         self.struct = dict()
         if op_mode == 'notify':
-            op_mode = 'do'
+            op_mode = 'do' if 'do' in op else 'dump'
         for op_dir in ['request', 'reply']:
             if op:
                 type_list = []
                 if op_dir in op[op_mode]:
                     type_list = op[op_mode][op_dir]['attributes']
-                self.struct[op_dir] = Struct(family, self.attr_set, type_list=type_list)
+                self.struct[op_dir] = Struct(family, self.attr_set,
+                                             fixed_header=fixed_hdr,
+                                             type_list=type_list)
         if op_mode == 'event':
-            self.struct['reply'] = Struct(family, self.attr_set, type_list=op['event']['attributes'])
+            self.struct['reply'] = Struct(family, self.attr_set,
+                                          fixed_header=fixed_hdr,
+                                          type_list=op['event']['attributes'])
+
+    def type_empty(self, key):
+        return len(self.struct[key].attr_list) == 0 and \
+            self.struct['request'].fixed_header is None
+
+    def needs_nlflags(self, direction):
+        return self.op_mode == 'do' and direction == 'request' and self.family.is_classic()
 
 
 class CodeWriter:
@@ -1330,6 +1672,7 @@ class CodeWriter:
         if self._silent_block:
             ind += 1
         self._silent_block = line.endswith(')') and CodeWriter._is_cond(line)
+        self._silent_block |= line.strip() == 'else'
         if line[0] == '#':
             ind = 0
         if add_ind:
@@ -1540,7 +1883,9 @@ def op_prefix(ri, direction, deref=False):
         suffix += f"{direction_to_suffix[direction]}"
     else:
         if direction == 'request':
-            suffix += '_req_dump'
+            suffix += '_req'
+            if not ri.type_oneside:
+                suffix += '_dump'
         else:
             if ri.type_consistent:
                 if deref:
@@ -1584,11 +1929,37 @@ def print_dump_prototype(ri):
     print_prototype(ri, "request")
 
 
+def put_typol_submsg(cw, struct):
+    cw.block_start(line=f'const struct ynl_policy_attr {struct.render_name}_policy[] =')
+
+    i = 0
+    for name, arg in struct.member_list():
+        nest = ""
+        if arg.type == 'nest':
+            nest = f" .nest = &{arg.nested_render_name}_nest,"
+        cw.p('[%d] = { .type = YNL_PT_SUBMSG, .name = "%s",%s },' %
+             (i, name, nest))
+        i += 1
+
+    cw.block_end(line=';')
+    cw.nl()
+
+    cw.block_start(line=f'const struct ynl_policy_nest {struct.render_name}_nest =')
+    cw.p(f'.max_attr = {i - 1},')
+    cw.p(f'.table = {struct.render_name}_policy,')
+    cw.block_end(line=';')
+    cw.nl()
+
+
 def put_typol_fwd(cw, struct):
     cw.p(f'extern const struct ynl_policy_nest {struct.render_name}_nest;')
 
 
 def put_typol(cw, struct):
+    if struct.submsg:
+        put_typol_submsg(cw, struct)
+        return
+
     type_max = struct.attr_set.max_name
     cw.block_start(line=f'const struct ynl_policy_attr {struct.render_name}_policy[{type_max} + 1] =')
 
@@ -1674,13 +2045,24 @@ def put_req_nested(ri, struct):
     local_vars = []
     init_lines = []
 
-    local_vars.append('struct nlattr *nest;')
-    init_lines.append("nest = ynl_attr_nest_start(nlh, attr_type);")
-
+    if struct.submsg is None:
+        local_vars.append('struct nlattr *nest;')
+        init_lines.append("nest = ynl_attr_nest_start(nlh, attr_type);")
+    if struct.fixed_header:
+        local_vars.append('void *hdr;')
+        struct_sz = f'sizeof({struct.fixed_header})'
+        init_lines.append(f"hdr = ynl_nlmsg_put_extra_header(nlh, {struct_sz});")
+        init_lines.append(f"memcpy(hdr, &obj->_hdr, {struct_sz});")
+
+    has_anest = False
+    has_count = False
     for _, arg in struct.member_list():
-        if arg.presence_type() == 'count':
-            local_vars.append('unsigned int i;')
-            break
+        has_anest |= arg.type == 'indexed-array'
+        has_count |= arg.presence_type() == 'count'
+    if has_anest:
+        local_vars.append('struct nlattr *array;')
+    if has_count:
+        local_vars.append('unsigned int i;')
 
     put_req_nested_prototype(ri, struct, suffix='')
     ri.cw.block_start()
@@ -1692,7 +2074,8 @@ def put_req_nested(ri, struct):
     for _, arg in struct.member_list():
         arg.attr_put(ri, "obj")
 
-    ri.cw.p("ynl_attr_nest_end(nlh, nest);")
+    if struct.submsg is None:
+        ri.cw.p("ynl_attr_nest_end(nlh, nest);")
 
     ri.cw.nl()
     ri.cw.p('return 0;')
@@ -1701,19 +2084,27 @@ def put_req_nested(ri, struct):
 
 
 def _multi_parse(ri, struct, init_lines, local_vars):
+    if struct.fixed_header:
+        local_vars += ['void *hdr;']
     if struct.nested:
-        iter_line = "ynl_attr_for_each_nested(attr, nested)"
+        if struct.fixed_header:
+            iter_line = f"ynl_attr_for_each_nested_off(attr, nested, sizeof({struct.fixed_header}))"
+        else:
+            iter_line = "ynl_attr_for_each_nested(attr, nested)"
     else:
-        if ri.fixed_hdr:
-            local_vars += ['void *hdr;']
         iter_line = "ynl_attr_for_each(attr, nlh, yarg->ys->family->hdr_len)"
+        if ri.op.fixed_header != ri.family.fixed_header:
+            if ri.family.is_classic():
+                iter_line = f"ynl_attr_for_each(attr, nlh, sizeof({struct.fixed_header}))"
+            else:
+                raise Exception(f"Per-op fixed header not supported, yet")
 
     array_nests = set()
     multi_attrs = set()
     needs_parg = False
     for arg, aspec in struct.member_list():
         if aspec['type'] == 'indexed-array' and 'sub-type' in aspec:
-            if aspec["sub-type"] == 'nest':
+            if aspec["sub-type"] in {'binary', 'nest'}:
                 local_vars.append(f'const struct nlattr *attr_{aspec.c_name};')
                 array_nests.add(arg)
             elif aspec['sub-type'] in scalars:
@@ -1724,6 +2115,7 @@ def _multi_parse(ri, struct, init_lines, local_vars):
         if 'multi-attr' in aspec:
             multi_attrs.add(arg)
         needs_parg |= 'nested-attributes' in aspec
+        needs_parg |= 'sub-message' in aspec
     if array_nests or multi_attrs:
         local_vars.append('int i;')
     if needs_parg:
@@ -1745,9 +2137,14 @@ def _multi_parse(ri, struct, init_lines, local_vars):
     for arg in struct.inherited:
         ri.cw.p(f'dst->{arg} = {arg};')
 
-    if ri.fixed_hdr:
-        ri.cw.p('hdr = ynl_nlmsg_data_offset(nlh, sizeof(struct genlmsghdr));')
-        ri.cw.p(f"memcpy(&dst->_hdr, hdr, sizeof({ri.fixed_hdr}));")
+    if struct.fixed_header:
+        if struct.nested:
+            ri.cw.p('hdr = ynl_attr_data(nested);')
+        elif ri.family.is_classic():
+            ri.cw.p('hdr = ynl_nlmsg_data(nlh);')
+        else:
+            ri.cw.p('hdr = ynl_nlmsg_data_offset(nlh, sizeof(struct genlmsghdr));')
+        ri.cw.p(f"memcpy(&dst->_hdr, hdr, sizeof({struct.fixed_header}));")
     for anest in sorted(all_multi):
         aspec = struct[anest]
         ri.cw.p(f"if (dst->{aspec.c_name})")
@@ -1772,7 +2169,7 @@ def _multi_parse(ri, struct, init_lines, local_vars):
 
         ri.cw.block_start(line=f"if (n_{aspec.c_name})")
         ri.cw.p(f"dst->{aspec.c_name} = calloc(n_{aspec.c_name}, sizeof(*dst->{aspec.c_name}));")
-        ri.cw.p(f"dst->n_{aspec.c_name} = n_{aspec.c_name};")
+        ri.cw.p(f"dst->_count.{aspec.c_name} = n_{aspec.c_name};")
         ri.cw.p('i = 0;')
         if 'nested-attributes' in aspec:
             ri.cw.p(f"parg.rsp_policy = &{aspec.nested_render_name}_nest;")
@@ -1783,6 +2180,9 @@ def _multi_parse(ri, struct, init_lines, local_vars):
             ri.cw.p('return YNL_PARSE_CB_ERROR;')
         elif aspec.sub_type in scalars:
             ri.cw.p(f"dst->{aspec.c_name}[i] = ynl_attr_get_{aspec.sub_type}(attr);")
+        elif aspec.sub_type == 'binary' and 'exact-len' in aspec.checks:
+            # Length is validated by typol
+            ri.cw.p(f'memcpy(dst->{aspec.c_name}[i], ynl_attr_data(attr), {aspec.checks["exact-len"]});')
         else:
             raise Exception(f"Nest parsing type not supported in {aspec['name']}")
         ri.cw.p('i++;')
@@ -1794,7 +2194,7 @@ def _multi_parse(ri, struct, init_lines, local_vars):
         aspec = struct[anest]
         ri.cw.block_start(line=f"if (n_{aspec.c_name})")
         ri.cw.p(f"dst->{aspec.c_name} = calloc(n_{aspec.c_name}, sizeof(*dst->{aspec.c_name}));")
-        ri.cw.p(f"dst->n_{aspec.c_name} = n_{aspec.c_name};")
+        ri.cw.p(f"dst->_count.{aspec.c_name} = n_{aspec.c_name};")
         ri.cw.p('i = 0;')
         if 'nested-attributes' in aspec:
             ri.cw.p(f"parg.rsp_policy = &{aspec.nested_render_name}_nest;")
@@ -1806,8 +2206,22 @@ def _multi_parse(ri, struct, init_lines, local_vars):
             ri.cw.p('return YNL_PARSE_CB_ERROR;')
         elif aspec.type in scalars:
             ri.cw.p(f"dst->{aspec.c_name}[i] = ynl_attr_get_{aspec.type}(attr);")
+        elif aspec.type == 'binary' and 'struct' in aspec:
+            ri.cw.p('size_t len = ynl_attr_data_len(attr);')
+            ri.cw.nl()
+            ri.cw.p(f'if (len > sizeof(dst->{aspec.c_name}[0]))')
+            ri.cw.p(f'len = sizeof(dst->{aspec.c_name}[0]);')
+            ri.cw.p(f"memcpy(&dst->{aspec.c_name}[i], ynl_attr_data(attr), len);")
+        elif aspec.type == 'string':
+            ri.cw.p('unsigned int len;')
+            ri.cw.nl()
+            ri.cw.p('len = strnlen(ynl_attr_get_str(attr), ynl_attr_data_len(attr));')
+            ri.cw.p(f'dst->{aspec.c_name}[i] = malloc(sizeof(struct ynl_string) + len + 1);')
+            ri.cw.p(f"dst->{aspec.c_name}[i]->len = len;")
+            ri.cw.p(f"memcpy(dst->{aspec.c_name}[i]->str, ynl_attr_get_str(attr), len);")
+            ri.cw.p(f"dst->{aspec.c_name}[i]->str[len] = 0;")
         else:
-            raise Exception('Nest parsing type not supported yet')
+            raise Exception(f'Nest parsing of type {aspec.type} not supported yet')
         ri.cw.p('i++;')
         ri.cw.block_end()
         ri.cw.block_end()
@@ -1822,9 +2236,49 @@ def _multi_parse(ri, struct, init_lines, local_vars):
     ri.cw.nl()
 
 
+def parse_rsp_submsg(ri, struct):
+    parse_rsp_nested_prototype(ri, struct, suffix='')
+
+    var = 'dst'
+    local_vars = {'const struct nlattr *attr = nested;',
+                  f'{struct.ptr_name}{var} = yarg->data;',
+                  'struct ynl_parse_arg parg;'}
+
+    for _, arg in struct.member_list():
+        _, _, l_vars = arg._attr_get(ri, var)
+        local_vars |= set(l_vars) if l_vars else set()
+
+    ri.cw.block_start()
+    ri.cw.write_func_lvar(list(local_vars))
+    ri.cw.p('parg.ys = yarg->ys;')
+    ri.cw.nl()
+
+    first = True
+    for name, arg in struct.member_list():
+        kw = 'if' if first else 'else if'
+        first = False
+
+        ri.cw.block_start(line=f'{kw} (!strcmp(sel, "{name}"))')
+        get_lines, init_lines, _ = arg._attr_get(ri, var)
+        for line in init_lines or []:
+            ri.cw.p(line)
+        for line in get_lines:
+            ri.cw.p(line)
+        if arg.presence_type() == 'present':
+            ri.cw.p(f"{var}->_present.{arg.c_name} = 1;")
+        ri.cw.block_end()
+    ri.cw.p('return 0;')
+    ri.cw.block_end()
+    ri.cw.nl()
+
+
 def parse_rsp_nested_prototype(ri, struct, suffix=';'):
     func_args = ['struct ynl_parse_arg *yarg',
                  'const struct nlattr *nested']
+    for sel in struct.external_selectors():
+        func_args.append('const char *_sel_' + sel.name)
+    if struct.submsg:
+        func_args.insert(1, 'const char *sel')
     for arg in struct.inherited:
         func_args.append('__u32 ' + arg)
 
@@ -1833,6 +2287,9 @@ def parse_rsp_nested_prototype(ri, struct, suffix=';'):
 
 
 def parse_rsp_nested(ri, struct):
+    if struct.submsg:
+        return parse_rsp_submsg(ri, struct)
+
     parse_rsp_nested_prototype(ri, struct, suffix='')
 
     local_vars = ['const struct nlattr *attr;',
@@ -1885,7 +2342,7 @@ def print_req(ri):
         ret_err = 'NULL'
         local_vars += [f'{type_name(ri, rdir(direction))} *rsp;']
 
-    if ri.fixed_hdr:
+    if ri.struct["request"].fixed_header:
         local_vars += ['size_t hdr_len;',
                        'void *hdr;']
 
@@ -1898,14 +2355,18 @@ def print_req(ri):
     ri.cw.block_start()
     ri.cw.write_func_lvar(local_vars)
 
-    ri.cw.p(f"nlh = ynl_gemsg_start_req(ys, {ri.nl.get_family_id()}, {ri.op.enum_name}, 1);")
+    if ri.family.is_classic():
+        ri.cw.p(f"nlh = ynl_msg_start_req(ys, {ri.op.enum_name}, req->_nlmsg_flags);")
+    else:
+        ri.cw.p(f"nlh = ynl_gemsg_start_req(ys, {ri.nl.get_family_id()}, {ri.op.enum_name}, 1);")
 
     ri.cw.p(f"ys->req_policy = &{ri.struct['request'].render_name}_nest;")
+    ri.cw.p(f"ys->req_hdr_len = {ri.fixed_hdr_len};")
     if 'reply' in ri.op[ri.op_mode]:
         ri.cw.p(f"yrs.yarg.rsp_policy = &{ri.struct['reply'].render_name}_nest;")
     ri.cw.nl()
 
-    if ri.fixed_hdr:
+    if ri.struct['request'].fixed_header:
         ri.cw.p("hdr_len = sizeof(req->_hdr);")
         ri.cw.p("hdr = ynl_nlmsg_put_extra_header(nlh, hdr_len);")
         ri.cw.p("memcpy(hdr, &req->_hdr, hdr_len);")
@@ -1951,7 +2412,7 @@ def print_dump(ri):
                   'struct nlmsghdr *nlh;',
                   'int err;']
 
-    if ri.fixed_hdr:
+    if ri.struct['request'].fixed_header:
         local_vars += ['size_t hdr_len;',
                        'void *hdr;']
 
@@ -1967,9 +2428,12 @@ def print_dump(ri):
     else:
         ri.cw.p(f'yds.rsp_cmd = {ri.op.rsp_value};')
     ri.cw.nl()
-    ri.cw.p(f"nlh = ynl_gemsg_start_dump(ys, {ri.nl.get_family_id()}, {ri.op.enum_name}, 1);")
+    if ri.family.is_classic():
+        ri.cw.p(f"nlh = ynl_msg_start_dump(ys, {ri.op.enum_name});")
+    else:
+        ri.cw.p(f"nlh = ynl_gemsg_start_dump(ys, {ri.nl.get_family_id()}, {ri.op.enum_name}, 1);")
 
-    if ri.fixed_hdr:
+    if ri.struct['request'].fixed_header:
         ri.cw.p("hdr_len = sizeof(req->_hdr);")
         ri.cw.p("hdr = ynl_nlmsg_put_extra_header(nlh, hdr_len);")
         ri.cw.p("memcpy(hdr, &req->_hdr, hdr_len);")
@@ -1977,6 +2441,7 @@ def print_dump(ri):
 
     if "request" in ri.op[ri.op_mode]:
         ri.cw.p(f"ys->req_policy = &{ri.struct['request'].render_name}_nest;")
+        ri.cw.p(f"ys->req_hdr_len = {ri.fixed_hdr_len};")
         ri.cw.nl()
         for _, attr in ri.struct["request"].member_list():
             attr.attr_put(ri, "req")
@@ -2022,32 +2487,45 @@ def print_free_prototype(ri, direction, suffix=';'):
     ri.cw.write_func_prot('void', f"{name}_free", [f"struct {struct_name} *{arg}"], suffix=suffix)
 
 
+def print_nlflags_set(ri, direction):
+    name = op_prefix(ri, direction)
+    ri.cw.write_func_prot(f'static inline void', f"{name}_set_nlflags",
+                          [f"struct {name} *req", "__u16 nl_flags"])
+    ri.cw.block_start()
+    ri.cw.p('req->_nlmsg_flags = nl_flags;')
+    ri.cw.block_end()
+    ri.cw.nl()
+
+
 def _print_type(ri, direction, struct):
     suffix = f'_{ri.type_name}{direction_to_suffix[direction]}'
     if not direction and ri.type_name_conflict:
         suffix += '_'
 
-    if ri.op_mode == 'dump':
+    if ri.op_mode == 'dump' and not ri.type_oneside:
         suffix += '_dump'
 
     ri.cw.block_start(line=f"struct {ri.family.c_name}{suffix}")
 
-    if ri.fixed_hdr:
-        ri.cw.p(ri.fixed_hdr + ' _hdr;')
+    if ri.needs_nlflags(direction):
+        ri.cw.p('__u16 _nlmsg_flags;')
+        ri.cw.nl()
+    if struct.fixed_header:
+        ri.cw.p(struct.fixed_header + ' _hdr;')
         ri.cw.nl()
 
-    meta_started = False
-    for _, attr in struct.member_list():
-        for type_filter in ['len', 'bit']:
+    for type_filter in ['present', 'len', 'count']:
+        meta_started = False
+        for _, attr in struct.member_list():
             line = attr.presence_member(ri.ku_space, type_filter)
             if line:
                 if not meta_started:
                     ri.cw.block_start(line=f"struct")
                     meta_started = True
                 ri.cw.p(line)
-    if meta_started:
-        ri.cw.block_end(line='_present;')
-        ri.cw.nl()
+        if meta_started:
+            ri.cw.block_end(line=f'_{type_filter};')
+    ri.cw.nl()
 
     for arg in struct.inherited:
         ri.cw.p(f"__u32 {arg};")
@@ -2071,6 +2549,9 @@ def print_type_helpers(ri, direction, deref=False):
     print_free_prototype(ri, direction)
     ri.cw.nl()
 
+    if ri.needs_nlflags(direction):
+        print_nlflags_set(ri, direction)
+
     if ri.ku_space == 'user' and direction == 'request':
         for _, attr in ri.struct[direction].member_list():
             attr.setter(ri, ri.attr_set, direction, deref=deref)
@@ -2078,7 +2559,7 @@ def print_type_helpers(ri, direction, deref=False):
 
 
 def print_req_type_helpers(ri):
-    if len(ri.struct["request"].attr_list) == 0:
+    if ri.type_empty("request"):
         return
     print_alloc_wrapper(ri, "request")
     print_type_helpers(ri, "request")
@@ -2101,7 +2582,7 @@ def print_parse_prototype(ri, direction, terminate=True):
 
 
 def print_req_type(ri):
-    if len(ri.struct["request"].attr_list) == 0:
+    if ri.type_empty("request"):
         return
     print_type(ri, "request")
 
@@ -2139,11 +2620,9 @@ def print_wrapped_type(ri):
 
 
 def _free_type_members_iter(ri, struct):
-    for _, attr in struct.member_list():
-        if attr.free_needs_iter():
-            ri.cw.p('unsigned int i;')
-            ri.cw.nl()
-            break
+    if struct.free_needs_iter():
+        ri.cw.p('unsigned int i;')
+        ri.cw.nl()
 
 
 def _free_type_members(ri, var, struct, ref=''):
@@ -2280,6 +2759,46 @@ def print_kernel_policy_ranges(family, cw):
             cw.nl()
 
 
+def print_kernel_policy_sparse_enum_validates(family, cw):
+    first = True
+    for _, attr_set in family.attr_sets.items():
+        if attr_set.subset_of:
+            continue
+
+        for _, attr in attr_set.items():
+            if not attr.request:
+                continue
+            if not attr.enum_name:
+                continue
+            if 'sparse' not in attr.checks:
+                continue
+
+            if first:
+                cw.p('/* Sparse enums validation callbacks */')
+                first = False
+
+            sign = '' if attr.type[0] == 'u' else '_signed'
+            suffix = 'ULL' if attr.type[0] == 'u' else 'LL'
+            cw.write_func_prot('static int', f'{c_lower(attr.enum_name)}_validate',
+                               ['const struct nlattr *attr', 'struct netlink_ext_ack *extack'])
+            cw.block_start()
+            cw.block_start(line=f'switch (nla_get_{attr["type"]}(attr))')
+            enum = family.consts[attr['enum']]
+            first_entry = True
+            for entry in enum.entries.values():
+                if first_entry:
+                    first_entry = False
+                else:
+                    cw.p('fallthrough;')
+                cw.p(f'case {entry.c_name}:')
+            cw.p('return 0;')
+            cw.block_end()
+            cw.p('NL_SET_ERR_MSG_ATTR(extack, attr, "invalid enum value");')
+            cw.p('return -EINVAL;')
+            cw.block_end()
+            cw.nl()
+
+
 def print_kernel_op_table_fwd(family, cw, terminate):
     exported = not kernel_can_gen_family_struct(family)
 
@@ -2739,7 +3258,11 @@ def render_uapi(family, cw):
 
 
 def _render_user_ntf_entry(ri, op):
-    ri.cw.block_start(line=f"[{op.enum_name}] = ")
+    if not ri.family.is_classic():
+        ri.cw.block_start(line=f"[{op.enum_name}] = ")
+    else:
+        crud_op = ri.family.req_by_value[op.rsp_value]
+        ri.cw.block_start(line=f"[{crud_op.enum_name}] = ")
     ri.cw.p(f".alloc_sz\t= sizeof({type_name(ri, 'event')}),")
     ri.cw.p(f".cb\t\t= {op_prefix(ri, 'reply', deref=True)}_parse,")
     ri.cw.p(f".policy\t\t= &{ri.struct['reply'].render_name}_nest,")
@@ -2754,7 +3277,7 @@ def render_user_family(family, cw, prototype):
         return
 
     if family.ntfs:
-        cw.block_start(line=f"static const struct ynl_ntf_info {family['name']}_ntf_info[] = ")
+        cw.block_start(line=f"static const struct ynl_ntf_info {family.c_name}_ntf_info[] = ")
         for ntf_op_name, ntf_op in family.ntfs.items():
             if 'notify' in ntf_op:
                 op = family.ops[ntf_op['notify']]
@@ -2774,13 +3297,19 @@ def render_user_family(family, cw, prototype):
 
     cw.block_start(f'{symbol} = ')
     cw.p(f'.name\t\t= "{family.c_name}",')
-    if family.fixed_header:
+    if family.is_classic():
+        cw.p(f'.is_classic\t= true,')
+        cw.p(f'.classic_id\t= {family.get("protonum")},')
+    if family.is_classic():
+        if family.fixed_header:
+            cw.p(f'.hdr_len\t= sizeof(struct {c_lower(family.fixed_header)}),')
+    elif family.fixed_header:
         cw.p(f'.hdr_len\t= sizeof(struct genlmsghdr) + sizeof(struct {c_lower(family.fixed_header)}),')
     else:
         cw.p('.hdr_len\t= sizeof(struct genlmsghdr),')
     if family.ntfs:
-        cw.p(f".ntf_info\t= {family['name']}_ntf_info,")
-        cw.p(f".ntf_info_size\t= YNL_ARRAY_SIZE({family['name']}_ntf_info),")
+        cw.p(f".ntf_info\t= {family.c_name}_ntf_info,")
+        cw.p(f".ntf_info_size\t= YNL_ARRAY_SIZE({family.c_name}_ntf_info),")
     cw.block_end(line=';')
 
 
@@ -2887,7 +3416,7 @@ def main():
             cw.p(f'#include "{hdr_file}"')
             cw.p('#include "ynl.h"')
         headers = []
-    for definition in parsed['definitions']:
+    for definition in parsed['definitions'] + parsed['attribute-sets']:
         if 'header' in definition:
             headers.append(definition['header'])
     if args.mode == 'user':
@@ -2941,6 +3470,7 @@ def main():
             print_kernel_family_struct_hdr(parsed, cw)
         else:
             print_kernel_policy_ranges(parsed, cw)
+            print_kernel_policy_sparse_enum_validates(parsed, cw)
 
             for _, struct in sorted(parsed.pure_nested_structs.items()):
                 if struct.request:
@@ -3009,7 +3539,7 @@ def main():
                     ri = RenderInfo(cw, parsed, args.mode, op, 'dump')
                     print_req_type(ri)
                     print_req_type_helpers(ri)
-                    if not ri.type_consistent:
+                    if not ri.type_consistent or ri.type_oneside:
                         print_rsp_type(ri)
                     print_wrapped_type(ri)
                     print_dump_prototype(ri)
@@ -3047,8 +3577,7 @@ def main():
                     has_recursive_nests = True
             if has_recursive_nests:
                 cw.nl()
-            for name in parsed.pure_nested_structs:
-                struct = Struct(parsed, name)
+            for struct in parsed.pure_nested_structs.values():
                 put_typol(cw, struct)
             for name in parsed.root_sets:
                 struct = Struct(parsed, name)
@@ -3087,7 +3616,7 @@ def main():
                 if 'dump' in op:
                     cw.p(f"/* {op.enum_name} - dump */")
                     ri = RenderInfo(cw, parsed, args.mode, op, "dump")
-                    if not ri.type_consistent:
+                    if not ri.type_consistent or ri.type_oneside:
                         parse_rsp_msg(ri, deref=True)
                     print_req_free(ri)
                     print_dump_type_free(ri)
diff --git a/tools/net/ynl/pyynl/ynl_gen_rst.py b/tools/net/ynl/pyynl/ynl_gen_rst.py
index 6c56d0d726b4..0cb6348e28d3 100755
--- a/tools/net/ynl/pyynl/ynl_gen_rst.py
+++ b/tools/net/ynl/pyynl/ynl_gen_rst.py
@@ -392,7 +392,7 @@ def parse_arguments() -> argparse.Namespace:
 
 
 def parse_yaml_file(filename: str) -> str:
-    """Transform the YAML specified by filename into a rst-formmated string"""
+    """Transform the YAML specified by filename into an RST-formatted string"""
     with open(filename, "r", encoding="utf-8") as spec_file:
         yaml_data = yaml.safe_load(spec_file)
         content = parse_yaml(yaml_data)
diff --git a/tools/net/ynl/samples/.gitignore b/tools/net/ynl/samples/.gitignore
index dda6686257a7..7f5fca7682d7 100644
--- a/tools/net/ynl/samples/.gitignore
+++ b/tools/net/ynl/samples/.gitignore
@@ -2,4 +2,8 @@ ethtool
 devlink
 netdev
 ovs
-page-pool
\ No newline at end of file
+page-pool
+rt-addr
+rt-link
+rt-route
+tc
diff --git a/tools/net/ynl/samples/devlink.c b/tools/net/ynl/samples/devlink.c
index d2611d7ebab4..ac9dfb01f280 100644
--- a/tools/net/ynl/samples/devlink.c
+++ b/tools/net/ynl/samples/devlink.c
@@ -22,6 +22,7 @@ int main(int argc, char **argv)
 	ynl_dump_foreach(devs, d) {
 		struct devlink_info_get_req *info_req;
 		struct devlink_info_get_rsp *info_rsp;
+		unsigned i;
 
 		printf("%s/%s:\n", d->bus_name, d->dev_name);
 
@@ -34,11 +35,11 @@ int main(int argc, char **argv)
 		if (!info_rsp)
 			goto err_free_devs;
 
-		if (info_rsp->_present.info_driver_name_len)
+		if (info_rsp->_len.info_driver_name)
 			printf("    driver: %s\n", info_rsp->info_driver_name);
-		if (info_rsp->n_info_version_running)
+		if (info_rsp->_count.info_version_running)
 			printf("    running fw:\n");
-		for (unsigned i = 0; i < info_rsp->n_info_version_running; i++)
+		for (i = 0; i < info_rsp->_count.info_version_running; i++)
 			printf("        %s: %s\n",
 			       info_rsp->info_version_running[i].info_version_name,
 			       info_rsp->info_version_running[i].info_version_value);
diff --git a/tools/net/ynl/samples/rt-addr.c b/tools/net/ynl/samples/rt-addr.c
new file mode 100644
index 000000000000..2edde5c36b18
--- /dev/null
+++ b/tools/net/ynl/samples/rt-addr.c
@@ -0,0 +1,80 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <stdio.h>
+#include <string.h>
+
+#include <ynl.h>
+
+#include <arpa/inet.h>
+#include <net/if.h>
+
+#include "rt-addr-user.h"
+
+static void rt_addr_print(struct rt_addr_getaddr_rsp *a)
+{
+	char ifname[IF_NAMESIZE];
+	char addr_str[64];
+	const char *addr;
+	const char *name;
+
+	name = if_indextoname(a->_hdr.ifa_index, ifname);
+	if (name)
+		printf("%16s: ", name);
+
+	switch (a->_len.address) {
+	case 4:
+		addr = inet_ntop(AF_INET, a->address,
+				 addr_str, sizeof(addr_str));
+		break;
+	case 16:
+		addr = inet_ntop(AF_INET6, a->address,
+				 addr_str, sizeof(addr_str));
+		break;
+	default:
+		addr = NULL;
+		break;
+	}
+	if (addr)
+		printf("%s", addr);
+	else
+		printf("[%d]", a->_len.address);
+
+	printf("\n");
+}
+
+int main(int argc, char **argv)
+{
+	struct rt_addr_getaddr_list *rsp;
+	struct rt_addr_getaddr_req *req;
+	struct ynl_error yerr;
+	struct ynl_sock *ys;
+
+	ys = ynl_sock_create(&ynl_rt_addr_family, &yerr);
+	if (!ys) {
+		fprintf(stderr, "YNL: %s\n", yerr.msg);
+		return 1;
+	}
+
+	req = rt_addr_getaddr_req_alloc();
+	if (!req)
+		goto err_destroy;
+
+	rsp = rt_addr_getaddr_dump(ys, req);
+	rt_addr_getaddr_req_free(req);
+	if (!rsp)
+		goto err_close;
+
+	if (ynl_dump_empty(rsp))
+		fprintf(stderr, "Error: no addresses reported\n");
+	ynl_dump_foreach(rsp, addr)
+		rt_addr_print(addr);
+	rt_addr_getaddr_list_free(rsp);
+
+	ynl_sock_destroy(ys);
+	return 0;
+
+err_close:
+	fprintf(stderr, "YNL: %s\n", ys->err.msg);
+err_destroy:
+	ynl_sock_destroy(ys);
+	return 2;
+}
diff --git a/tools/net/ynl/samples/rt-link.c b/tools/net/ynl/samples/rt-link.c
new file mode 100644
index 000000000000..acdd4b4a0f74
--- /dev/null
+++ b/tools/net/ynl/samples/rt-link.c
@@ -0,0 +1,184 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <stdio.h>
+#include <string.h>
+
+#include <ynl.h>
+
+#include <arpa/inet.h>
+#include <net/if.h>
+
+#include "rt-link-user.h"
+
+static void rt_link_print(struct rt_link_getlink_rsp *r)
+{
+	unsigned int i;
+
+	printf("%3d: ", r->_hdr.ifi_index);
+
+	if (r->_len.ifname)
+		printf("%16s: ", r->ifname);
+
+	if (r->_present.mtu)
+		printf("mtu %5d  ", r->mtu);
+
+	if (r->linkinfo._len.kind)
+		printf("kind %-8s  ", r->linkinfo.kind);
+	else
+		printf("     %8s  ", "");
+
+	if (r->prop_list._count.alt_ifname) {
+		printf("altname ");
+		for (i = 0; i < r->prop_list._count.alt_ifname; i++)
+			printf("%s ", r->prop_list.alt_ifname[i]->str);
+		printf(" ");
+	}
+
+	if (r->linkinfo._present.data && r->linkinfo.data._present.netkit) {
+		struct rt_link_linkinfo_netkit_attrs *netkit;
+		const char *name;
+
+		netkit = &r->linkinfo.data.netkit;
+		printf("primary %d  ", netkit->primary);
+
+		name = NULL;
+		if (netkit->_present.policy)
+			name = rt_link_netkit_policy_str(netkit->policy);
+		if (name)
+			printf("policy %s  ", name);
+	}
+
+	printf("\n");
+}
+
+static int rt_link_create_netkit(struct ynl_sock *ys)
+{
+	struct rt_link_getlink_ntf *ntf_gl;
+	struct rt_link_newlink_req *req;
+	struct ynl_ntf_base_type *ntf;
+	int ret;
+
+	req = rt_link_newlink_req_alloc();
+	if (!req) {
+		fprintf(stderr, "Can't alloc req\n");
+		return -1;
+	}
+
+	/* rtnetlink doesn't provide info about the created object.
+	 * It expects us to set the ECHO flag and the dig the info out
+	 * of the notifications...
+	 */
+	rt_link_newlink_req_set_nlflags(req, NLM_F_CREATE | NLM_F_ECHO);
+
+	rt_link_newlink_req_set_linkinfo_kind(req, "netkit");
+
+	/* Test error messages */
+	rt_link_newlink_req_set_linkinfo_data_netkit_policy(req, 10);
+	ret = rt_link_newlink(ys, req);
+	if (ret) {
+		printf("Testing error message for policy being bad:\n\t%s\n", ys->err.msg);
+	} else {
+		fprintf(stderr,	"Warning: unexpected success creating netkit with bad attrs\n");
+		goto created;
+	}
+
+	rt_link_newlink_req_set_linkinfo_data_netkit_policy(req, NETKIT_DROP);
+
+	ret = rt_link_newlink(ys, req);
+created:
+	rt_link_newlink_req_free(req);
+	if (ret) {
+		fprintf(stderr, "YNL: %s\n", ys->err.msg);
+		return -1;
+	}
+
+	if (!ynl_has_ntf(ys)) {
+		fprintf(stderr,
+			"Warning: interface created but received no notification, won't delete the interface\n");
+		return 0;
+	}
+
+	ntf = ynl_ntf_dequeue(ys);
+	if (ntf->cmd !=	RTM_NEWLINK) {
+		fprintf(stderr,
+			"Warning: unexpected notification type, won't delete the interface\n");
+		return 0;
+	}
+	ntf_gl = (void *)ntf;
+	ret = ntf_gl->obj._hdr.ifi_index;
+	ynl_ntf_free(ntf);
+
+	return ret;
+}
+
+static void rt_link_del(struct ynl_sock *ys, int ifindex)
+{
+	struct rt_link_dellink_req *req;
+
+	req = rt_link_dellink_req_alloc();
+	if (!req) {
+		fprintf(stderr, "Can't alloc req\n");
+		return;
+	}
+
+	req->_hdr.ifi_index = ifindex;
+	if (rt_link_dellink(ys, req))
+		fprintf(stderr, "YNL: %s\n", ys->err.msg);
+	else
+		fprintf(stderr,
+			"Trying to delete a Netkit interface (ifindex %d)\n",
+			ifindex);
+
+	rt_link_dellink_req_free(req);
+}
+
+int main(int argc, char **argv)
+{
+	struct rt_link_getlink_req_dump *req;
+	struct rt_link_getlink_list *rsp;
+	struct ynl_error yerr;
+	struct ynl_sock *ys;
+	int created = 0;
+
+	ys = ynl_sock_create(&ynl_rt_link_family, &yerr);
+	if (!ys) {
+		fprintf(stderr, "YNL: %s\n", yerr.msg);
+		return 1;
+	}
+
+	if (argc > 1) {
+		fprintf(stderr, "Trying to create a Netkit interface\n");
+		created = rt_link_create_netkit(ys);
+		if (created < 0)
+			goto err_destroy;
+	}
+
+	req = rt_link_getlink_req_dump_alloc();
+	if (!req)
+		goto err_del_ifc;
+
+	rsp = rt_link_getlink_dump(ys, req);
+	rt_link_getlink_req_dump_free(req);
+	if (!rsp)
+		goto err_close;
+
+	if (ynl_dump_empty(rsp))
+		fprintf(stderr, "Error: no links reported\n");
+	ynl_dump_foreach(rsp, link)
+		rt_link_print(link);
+	rt_link_getlink_list_free(rsp);
+
+	if (created)
+		rt_link_del(ys, created);
+
+	ynl_sock_destroy(ys);
+	return 0;
+
+err_close:
+	fprintf(stderr, "YNL: %s\n", ys->err.msg);
+err_del_ifc:
+	if (created)
+		rt_link_del(ys, created);
+err_destroy:
+	ynl_sock_destroy(ys);
+	return 2;
+}
diff --git a/tools/net/ynl/samples/rt-route.c b/tools/net/ynl/samples/rt-route.c
new file mode 100644
index 000000000000..7427104a96df
--- /dev/null
+++ b/tools/net/ynl/samples/rt-route.c
@@ -0,0 +1,80 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <stdio.h>
+#include <string.h>
+
+#include <ynl.h>
+
+#include <arpa/inet.h>
+#include <net/if.h>
+
+#include "rt-route-user.h"
+
+static void rt_route_print(struct rt_route_getroute_rsp *r)
+{
+	char ifname[IF_NAMESIZE];
+	char route_str[64];
+	const char *route;
+	const char *name;
+
+	/* Ignore local */
+	if (r->_hdr.rtm_table == RT_TABLE_LOCAL)
+		return;
+
+	if (r->_present.oif) {
+		name = if_indextoname(r->oif, ifname);
+		if (name)
+			printf("oif: %-16s ", name);
+	}
+
+	if (r->_len.dst) {
+		route = inet_ntop(r->_hdr.rtm_family, r->dst,
+				  route_str, sizeof(route_str));
+		printf("dst: %s/%d", route, r->_hdr.rtm_dst_len);
+	}
+
+	if (r->_len.gateway) {
+		route = inet_ntop(r->_hdr.rtm_family, r->gateway,
+				  route_str, sizeof(route_str));
+		printf("gateway: %s ", route);
+	}
+
+	printf("\n");
+}
+
+int main(int argc, char **argv)
+{
+	struct rt_route_getroute_req_dump *req;
+	struct rt_route_getroute_list *rsp;
+	struct ynl_error yerr;
+	struct ynl_sock *ys;
+
+	ys = ynl_sock_create(&ynl_rt_route_family, &yerr);
+	if (!ys) {
+		fprintf(stderr, "YNL: %s\n", yerr.msg);
+		return 1;
+	}
+
+	req = rt_route_getroute_req_dump_alloc();
+	if (!req)
+		goto err_destroy;
+
+	rsp = rt_route_getroute_dump(ys, req);
+	rt_route_getroute_req_dump_free(req);
+	if (!rsp)
+		goto err_close;
+
+	if (ynl_dump_empty(rsp))
+		fprintf(stderr, "Error: no routeesses reported\n");
+	ynl_dump_foreach(rsp, route)
+		rt_route_print(route);
+	rt_route_getroute_list_free(rsp);
+
+	ynl_sock_destroy(ys);
+	return 0;
+
+err_close:
+	fprintf(stderr, "YNL: %s\n", ys->err.msg);
+err_destroy:
+	ynl_sock_destroy(ys);
+	return 2;
+}
diff --git a/tools/net/ynl/samples/tc.c b/tools/net/ynl/samples/tc.c
new file mode 100644
index 000000000000..0bfff0fdd792
--- /dev/null
+++ b/tools/net/ynl/samples/tc.c
@@ -0,0 +1,80 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <stdio.h>
+#include <string.h>
+
+#include <ynl.h>
+
+#include <net/if.h>
+
+#include "tc-user.h"
+
+static void tc_qdisc_print(struct tc_getqdisc_rsp *q)
+{
+	char ifname[IF_NAMESIZE];
+	const char *name;
+
+	name = if_indextoname(q->_hdr.tcm_ifindex, ifname);
+	if (name)
+		printf("%16s: ", name);
+
+	if (q->_len.kind) {
+		printf("%s  ", q->kind);
+
+		if (q->options._present.fq_codel) {
+			struct tc_fq_codel_attrs *fq_codel;
+			struct tc_fq_codel_xstats *stats;
+
+			fq_codel = &q->options.fq_codel;
+			stats = q->stats2.app.fq_codel;
+
+			if (fq_codel->_present.limit)
+				printf("limit: %dp ", fq_codel->limit);
+			if (fq_codel->_present.target)
+				printf("target: %dms ",
+				       (fq_codel->target + 500) / 1000);
+			if (q->stats2.app._len.fq_codel)
+				printf("new_flow_cnt: %d ",
+				       stats->qdisc_stats.new_flow_count);
+		}
+	}
+
+	printf("\n");
+}
+
+int main(int argc, char **argv)
+{
+	struct tc_getqdisc_req_dump *req;
+	struct tc_getqdisc_list *rsp;
+	struct ynl_error yerr;
+	struct ynl_sock *ys;
+
+	ys = ynl_sock_create(&ynl_tc_family, &yerr);
+	if (!ys) {
+		fprintf(stderr, "YNL: %s\n", yerr.msg);
+		return 1;
+	}
+
+	req = tc_getqdisc_req_dump_alloc();
+	if (!req)
+		goto err_destroy;
+
+	rsp = tc_getqdisc_dump(ys, req);
+	tc_getqdisc_req_dump_free(req);
+	if (!rsp)
+		goto err_close;
+
+	if (ynl_dump_empty(rsp))
+		fprintf(stderr, "Error: no addresses reported\n");
+	ynl_dump_foreach(rsp, qdisc)
+		tc_qdisc_print(qdisc);
+	tc_getqdisc_list_free(rsp);
+
+	ynl_sock_destroy(ys);
+	return 0;
+
+err_close:
+	fprintf(stderr, "YNL: %s\n", ys->err.msg);
+err_destroy:
+	ynl_sock_destroy(ys);
+	return 2;
+}
diff --git a/tools/testing/selftests/Makefile b/tools/testing/selftests/Makefile
index 84e7f4ed4c97..6aa11cd3db42 100644
--- a/tools/testing/selftests/Makefile
+++ b/tools/testing/selftests/Makefile
@@ -67,11 +67,13 @@ TARGETS += mseal_system_mappings
 TARGETS += nci
 TARGETS += net
 TARGETS += net/af_unix
+TARGETS += net/can
 TARGETS += net/forwarding
 TARGETS += net/hsr
 TARGETS += net/mptcp
 TARGETS += net/netfilter
 TARGETS += net/openvswitch
+TARGETS += net/ovpn
 TARGETS += net/packetdrill
 TARGETS += net/rds
 TARGETS += net/tcp_ao
diff --git a/tools/testing/selftests/bpf/config b/tools/testing/selftests/bpf/config
index c378d5d07e02..3201a962b3dc 100644
--- a/tools/testing/selftests/bpf/config
+++ b/tools/testing/selftests/bpf/config
@@ -71,8 +71,10 @@ CONFIG_NET_IPGRE=y
 CONFIG_NET_IPGRE_DEMUX=y
 CONFIG_NET_IPIP=y
 CONFIG_NET_MPLS_GSO=y
+CONFIG_NET_SCH_BPF=y
 CONFIG_NET_SCH_FQ=y
 CONFIG_NET_SCH_INGRESS=y
+CONFIG_NET_SCH_HTB=y
 CONFIG_NET_SCHED=y
 CONFIG_NETDEVSIM=y
 CONFIG_NETFILTER=y
diff --git a/tools/testing/selftests/bpf/prog_tests/bpf_qdisc.c b/tools/testing/selftests/bpf/prog_tests/bpf_qdisc.c
new file mode 100644
index 000000000000..730357cd0c9a
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/bpf_qdisc.c
@@ -0,0 +1,231 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <linux/pkt_sched.h>
+#include <linux/rtnetlink.h>
+#include <test_progs.h>
+
+#include "network_helpers.h"
+#include "bpf_qdisc_fifo.skel.h"
+#include "bpf_qdisc_fq.skel.h"
+#include "bpf_qdisc_fail__incompl_ops.skel.h"
+
+#define LO_IFINDEX 1
+
+static const unsigned int total_bytes = 10 * 1024 * 1024;
+
+static void do_test(char *qdisc)
+{
+	DECLARE_LIBBPF_OPTS(bpf_tc_hook, hook, .ifindex = LO_IFINDEX,
+			    .attach_point = BPF_TC_QDISC,
+			    .parent = TC_H_ROOT,
+			    .handle = 0x8000000,
+			    .qdisc = qdisc);
+	int srv_fd = -1, cli_fd = -1;
+	int err;
+
+	err = bpf_tc_hook_create(&hook);
+	if (!ASSERT_OK(err, "attach qdisc"))
+		return;
+
+	srv_fd = start_server(AF_INET6, SOCK_STREAM, NULL, 0, 0);
+	if (!ASSERT_OK_FD(srv_fd, "start server"))
+		goto done;
+
+	cli_fd = connect_to_fd(srv_fd, 0);
+	if (!ASSERT_OK_FD(cli_fd, "connect to client"))
+		goto done;
+
+	err = send_recv_data(srv_fd, cli_fd, total_bytes);
+	ASSERT_OK(err, "send_recv_data");
+
+done:
+	if (srv_fd != -1)
+		close(srv_fd);
+	if (cli_fd != -1)
+		close(cli_fd);
+
+	bpf_tc_hook_destroy(&hook);
+}
+
+static void test_fifo(void)
+{
+	struct bpf_qdisc_fifo *fifo_skel;
+
+	fifo_skel = bpf_qdisc_fifo__open_and_load();
+	if (!ASSERT_OK_PTR(fifo_skel, "bpf_qdisc_fifo__open_and_load"))
+		return;
+
+	if (!ASSERT_OK(bpf_qdisc_fifo__attach(fifo_skel), "bpf_qdisc_fifo__attach"))
+		goto out;
+
+	do_test("bpf_fifo");
+out:
+	bpf_qdisc_fifo__destroy(fifo_skel);
+}
+
+static void test_fq(void)
+{
+	struct bpf_qdisc_fq *fq_skel;
+
+	fq_skel = bpf_qdisc_fq__open_and_load();
+	if (!ASSERT_OK_PTR(fq_skel, "bpf_qdisc_fq__open_and_load"))
+		return;
+
+	if (!ASSERT_OK(bpf_qdisc_fq__attach(fq_skel), "bpf_qdisc_fq__attach"))
+		goto out;
+
+	do_test("bpf_fq");
+out:
+	bpf_qdisc_fq__destroy(fq_skel);
+}
+
+static void test_qdisc_attach_to_mq(void)
+{
+	DECLARE_LIBBPF_OPTS(bpf_tc_hook, hook,
+			    .attach_point = BPF_TC_QDISC,
+			    .parent = TC_H_MAKE(1 << 16, 1),
+			    .handle = 0x11 << 16,
+			    .qdisc = "bpf_fifo");
+	struct bpf_qdisc_fifo *fifo_skel;
+	int err;
+
+	fifo_skel = bpf_qdisc_fifo__open_and_load();
+	if (!ASSERT_OK_PTR(fifo_skel, "bpf_qdisc_fifo__open_and_load"))
+		return;
+
+	if (!ASSERT_OK(bpf_qdisc_fifo__attach(fifo_skel), "bpf_qdisc_fifo__attach"))
+		goto out;
+
+	SYS(out, "ip link add veth0 type veth peer veth1");
+	hook.ifindex = if_nametoindex("veth0");
+	SYS(out, "tc qdisc add dev veth0 root handle 1: mq");
+
+	err = bpf_tc_hook_create(&hook);
+	ASSERT_OK(err, "attach qdisc");
+
+	bpf_tc_hook_destroy(&hook);
+
+	SYS(out, "tc qdisc delete dev veth0 root mq");
+out:
+	bpf_qdisc_fifo__destroy(fifo_skel);
+}
+
+static void test_qdisc_attach_to_non_root(void)
+{
+	DECLARE_LIBBPF_OPTS(bpf_tc_hook, hook, .ifindex = LO_IFINDEX,
+			    .attach_point = BPF_TC_QDISC,
+			    .parent = TC_H_MAKE(1 << 16, 1),
+			    .handle = 0x11 << 16,
+			    .qdisc = "bpf_fifo");
+	struct bpf_qdisc_fifo *fifo_skel;
+	int err;
+
+	fifo_skel = bpf_qdisc_fifo__open_and_load();
+	if (!ASSERT_OK_PTR(fifo_skel, "bpf_qdisc_fifo__open_and_load"))
+		return;
+
+	if (!ASSERT_OK(bpf_qdisc_fifo__attach(fifo_skel), "bpf_qdisc_fifo__attach"))
+		goto out;
+
+	SYS(out, "tc qdisc add dev lo root handle 1: htb");
+	SYS(out_del_htb, "tc class add dev lo parent 1: classid 1:1 htb rate 75Kbit");
+
+	err = bpf_tc_hook_create(&hook);
+	if (!ASSERT_ERR(err, "attach qdisc"))
+		bpf_tc_hook_destroy(&hook);
+
+out_del_htb:
+	SYS(out, "tc qdisc delete dev lo root htb");
+out:
+	bpf_qdisc_fifo__destroy(fifo_skel);
+}
+
+static void test_incompl_ops(void)
+{
+	struct bpf_qdisc_fail__incompl_ops *skel;
+	struct bpf_link *link;
+
+	skel = bpf_qdisc_fail__incompl_ops__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "bpf_qdisc_fifo__open_and_load"))
+		return;
+
+	link = bpf_map__attach_struct_ops(skel->maps.test);
+	if (!ASSERT_ERR_PTR(link, "bpf_map__attach_struct_ops"))
+		bpf_link__destroy(link);
+
+	bpf_qdisc_fail__incompl_ops__destroy(skel);
+}
+
+static int get_default_qdisc(char *qdisc_name)
+{
+	FILE *f;
+	int num;
+
+	f = fopen("/proc/sys/net/core/default_qdisc", "r");
+	if (!f)
+		return -errno;
+
+	num = fscanf(f, "%s", qdisc_name);
+	fclose(f);
+
+	return num == 1 ? 0 : -EFAULT;
+}
+
+static void test_default_qdisc_attach_to_mq(void)
+{
+	char default_qdisc[IFNAMSIZ] = {};
+	struct bpf_qdisc_fifo *fifo_skel;
+	struct netns_obj *netns = NULL;
+	int err;
+
+	fifo_skel = bpf_qdisc_fifo__open_and_load();
+	if (!ASSERT_OK_PTR(fifo_skel, "bpf_qdisc_fifo__open_and_load"))
+		return;
+
+	if (!ASSERT_OK(bpf_qdisc_fifo__attach(fifo_skel), "bpf_qdisc_fifo__attach"))
+		goto out;
+
+	err = get_default_qdisc(default_qdisc);
+	if (!ASSERT_OK(err, "read sysctl net.core.default_qdisc"))
+		goto out;
+
+	err = write_sysctl("/proc/sys/net/core/default_qdisc", "bpf_fifo");
+	if (!ASSERT_OK(err, "write sysctl net.core.default_qdisc"))
+		goto out;
+
+	netns = netns_new("bpf_qdisc_ns", true);
+	if (!ASSERT_OK_PTR(netns, "netns_new"))
+		goto out;
+
+	SYS(out, "ip link add veth0 type veth peer veth1");
+	SYS(out, "tc qdisc add dev veth0 root handle 1: mq");
+
+	ASSERT_EQ(fifo_skel->bss->init_called, true, "init_called");
+
+	SYS(out, "tc qdisc delete dev veth0 root mq");
+out:
+	netns_free(netns);
+	if (default_qdisc[0])
+		write_sysctl("/proc/sys/net/core/default_qdisc", default_qdisc);
+
+	bpf_qdisc_fifo__destroy(fifo_skel);
+}
+
+void test_ns_bpf_qdisc(void)
+{
+	if (test__start_subtest("fifo"))
+		test_fifo();
+	if (test__start_subtest("fq"))
+		test_fq();
+	if (test__start_subtest("attach to mq"))
+		test_qdisc_attach_to_mq();
+	if (test__start_subtest("attach to non root"))
+		test_qdisc_attach_to_non_root();
+	if (test__start_subtest("incompl_ops"))
+		test_incompl_ops();
+}
+
+void serial_test_bpf_qdisc_default(void)
+{
+	test_default_qdisc_attach_to_mq();
+}
diff --git a/tools/testing/selftests/bpf/prog_tests/sock_iter_batch.c b/tools/testing/selftests/bpf/prog_tests/sock_iter_batch.c
index d56e18b25528..a4517bee34d5 100644
--- a/tools/testing/selftests/bpf/prog_tests/sock_iter_batch.c
+++ b/tools/testing/selftests/bpf/prog_tests/sock_iter_batch.c
@@ -7,14 +7,433 @@
 
 #define TEST_NS "sock_iter_batch_netns"
 
+static const int init_batch_size = 16;
 static const int nr_soreuse = 4;
 
+struct iter_out {
+	int idx;
+	__u64 cookie;
+} __packed;
+
+struct sock_count {
+	__u64 cookie;
+	int count;
+};
+
+static int insert(__u64 cookie, struct sock_count counts[], int counts_len)
+{
+	int insert = -1;
+	int i = 0;
+
+	for (; i < counts_len; i++) {
+		if (!counts[i].cookie) {
+			insert = i;
+		} else if (counts[i].cookie == cookie) {
+			insert = i;
+			break;
+		}
+	}
+	if (insert < 0)
+		return insert;
+
+	counts[insert].cookie = cookie;
+	counts[insert].count++;
+
+	return counts[insert].count;
+}
+
+static int read_n(int iter_fd, int n, struct sock_count counts[],
+		  int counts_len)
+{
+	struct iter_out out;
+	int nread = 1;
+	int i = 0;
+
+	for (; nread > 0 && (n < 0 || i < n); i++) {
+		nread = read(iter_fd, &out, sizeof(out));
+		if (!nread || !ASSERT_EQ(nread, sizeof(out), "nread"))
+			break;
+		ASSERT_GE(insert(out.cookie, counts, counts_len), 0, "insert");
+	}
+
+	ASSERT_TRUE(n < 0 || i == n, "n < 0 || i == n");
+
+	return i;
+}
+
+static __u64 socket_cookie(int fd)
+{
+	__u64 cookie;
+	socklen_t cookie_len = sizeof(cookie);
+
+	if (!ASSERT_OK(getsockopt(fd, SOL_SOCKET, SO_COOKIE, &cookie,
+				  &cookie_len), "getsockopt(SO_COOKIE)"))
+		return 0;
+	return cookie;
+}
+
+static bool was_seen(int fd, struct sock_count counts[], int counts_len)
+{
+	__u64 cookie = socket_cookie(fd);
+	int i = 0;
+
+	for (; cookie && i < counts_len; i++)
+		if (cookie == counts[i].cookie)
+			return true;
+
+	return false;
+}
+
+static int get_seen_socket(int *fds, struct sock_count counts[], int n)
+{
+	int i = 0;
+
+	for (; i < n; i++)
+		if (was_seen(fds[i], counts, n))
+			return i;
+	return -1;
+}
+
+static int get_nth_socket(int *fds, int fds_len, struct bpf_link *link, int n)
+{
+	int i, nread, iter_fd;
+	int nth_sock_idx = -1;
+	struct iter_out out;
+
+	iter_fd = bpf_iter_create(bpf_link__fd(link));
+	if (!ASSERT_OK_FD(iter_fd, "bpf_iter_create"))
+		return -1;
+
+	for (; n >= 0; n--) {
+		nread = read(iter_fd, &out, sizeof(out));
+		if (!nread || !ASSERT_GE(nread, 1, "nread"))
+			goto done;
+	}
+
+	for (i = 0; i < fds_len && nth_sock_idx < 0; i++)
+		if (fds[i] >= 0 && socket_cookie(fds[i]) == out.cookie)
+			nth_sock_idx = i;
+done:
+	close(iter_fd);
+	return nth_sock_idx;
+}
+
+static int get_seen_count(int fd, struct sock_count counts[], int n)
+{
+	__u64 cookie = socket_cookie(fd);
+	int count = 0;
+	int i = 0;
+
+	for (; cookie && !count && i < n; i++)
+		if (cookie == counts[i].cookie)
+			count = counts[i].count;
+
+	return count;
+}
+
+static void check_n_were_seen_once(int *fds, int fds_len, int n,
+				   struct sock_count counts[], int counts_len)
+{
+	int seen_once = 0;
+	int seen_cnt;
+	int i = 0;
+
+	for (; i < fds_len; i++) {
+		/* Skip any sockets that were closed or that weren't seen
+		 * exactly once.
+		 */
+		if (fds[i] < 0)
+			continue;
+		seen_cnt = get_seen_count(fds[i], counts, counts_len);
+		if (seen_cnt && ASSERT_EQ(seen_cnt, 1, "seen_cnt"))
+			seen_once++;
+	}
+
+	ASSERT_EQ(seen_once, n, "seen_once");
+}
+
+static void remove_seen(int family, int sock_type, const char *addr, __u16 port,
+			int *socks, int socks_len, struct sock_count *counts,
+			int counts_len, struct bpf_link *link, int iter_fd)
+{
+	int close_idx;
+
+	/* Iterate through the first socks_len - 1 sockets. */
+	read_n(iter_fd, socks_len - 1, counts, counts_len);
+
+	/* Make sure we saw socks_len - 1 sockets exactly once. */
+	check_n_were_seen_once(socks, socks_len, socks_len - 1, counts,
+			       counts_len);
+
+	/* Close a socket we've already seen to remove it from the bucket. */
+	close_idx = get_seen_socket(socks, counts, counts_len);
+	if (!ASSERT_GE(close_idx, 0, "close_idx"))
+		return;
+	close(socks[close_idx]);
+	socks[close_idx] = -1;
+
+	/* Iterate through the rest of the sockets. */
+	read_n(iter_fd, -1, counts, counts_len);
+
+	/* Make sure the last socket wasn't skipped and that there were no
+	 * repeats.
+	 */
+	check_n_were_seen_once(socks, socks_len, socks_len - 1, counts,
+			       counts_len);
+}
+
+static void remove_unseen(int family, int sock_type, const char *addr,
+			  __u16 port, int *socks, int socks_len,
+			  struct sock_count *counts, int counts_len,
+			  struct bpf_link *link, int iter_fd)
+{
+	int close_idx;
+
+	/* Iterate through the first socket. */
+	read_n(iter_fd, 1, counts, counts_len);
+
+	/* Make sure we saw a socket from fds. */
+	check_n_were_seen_once(socks, socks_len, 1, counts, counts_len);
+
+	/* Close what would be the next socket in the bucket to exercise the
+	 * condition where we need to skip past the first cookie we remembered.
+	 */
+	close_idx = get_nth_socket(socks, socks_len, link, 1);
+	if (!ASSERT_GE(close_idx, 0, "close_idx"))
+		return;
+	close(socks[close_idx]);
+	socks[close_idx] = -1;
+
+	/* Iterate through the rest of the sockets. */
+	read_n(iter_fd, -1, counts, counts_len);
+
+	/* Make sure the remaining sockets were seen exactly once and that we
+	 * didn't repeat the socket that was already seen.
+	 */
+	check_n_were_seen_once(socks, socks_len, socks_len - 1, counts,
+			       counts_len);
+}
+
+static void remove_all(int family, int sock_type, const char *addr,
+		       __u16 port, int *socks, int socks_len,
+		       struct sock_count *counts, int counts_len,
+		       struct bpf_link *link, int iter_fd)
+{
+	int close_idx, i;
+
+	/* Iterate through the first socket. */
+	read_n(iter_fd, 1, counts, counts_len);
+
+	/* Make sure we saw a socket from fds. */
+	check_n_were_seen_once(socks, socks_len, 1, counts, counts_len);
+
+	/* Close all remaining sockets to exhaust the list of saved cookies and
+	 * exit without putting any sockets into the batch on the next read.
+	 */
+	for (i = 0; i < socks_len - 1; i++) {
+		close_idx = get_nth_socket(socks, socks_len, link, 1);
+		if (!ASSERT_GE(close_idx, 0, "close_idx"))
+			return;
+		close(socks[close_idx]);
+		socks[close_idx] = -1;
+	}
+
+	/* Make sure there are no more sockets returned */
+	ASSERT_EQ(read_n(iter_fd, -1, counts, counts_len), 0, "read_n");
+}
+
+static void add_some(int family, int sock_type, const char *addr, __u16 port,
+		     int *socks, int socks_len, struct sock_count *counts,
+		     int counts_len, struct bpf_link *link, int iter_fd)
+{
+	int *new_socks = NULL;
+
+	/* Iterate through the first socks_len - 1 sockets. */
+	read_n(iter_fd, socks_len - 1, counts, counts_len);
+
+	/* Make sure we saw socks_len - 1 sockets exactly once. */
+	check_n_were_seen_once(socks, socks_len, socks_len - 1, counts,
+			       counts_len);
+
+	/* Double the number of sockets in the bucket. */
+	new_socks = start_reuseport_server(family, sock_type, addr, port, 0,
+					   socks_len);
+	if (!ASSERT_OK_PTR(new_socks, "start_reuseport_server"))
+		goto done;
+
+	/* Iterate through the rest of the sockets. */
+	read_n(iter_fd, -1, counts, counts_len);
+
+	/* Make sure each of the original sockets was seen exactly once. */
+	check_n_were_seen_once(socks, socks_len, socks_len, counts,
+			       counts_len);
+done:
+	free_fds(new_socks, socks_len);
+}
+
+static void force_realloc(int family, int sock_type, const char *addr,
+			  __u16 port, int *socks, int socks_len,
+			  struct sock_count *counts, int counts_len,
+			  struct bpf_link *link, int iter_fd)
+{
+	int *new_socks = NULL;
+
+	/* Iterate through the first socket just to initialize the batch. */
+	read_n(iter_fd, 1, counts, counts_len);
+
+	/* Double the number of sockets in the bucket to force a realloc on the
+	 * next read.
+	 */
+	new_socks = start_reuseport_server(family, sock_type, addr, port, 0,
+					   socks_len);
+	if (!ASSERT_OK_PTR(new_socks, "start_reuseport_server"))
+		goto done;
+
+	/* Iterate through the rest of the sockets. */
+	read_n(iter_fd, -1, counts, counts_len);
+
+	/* Make sure each socket from the first set was seen exactly once. */
+	check_n_were_seen_once(socks, socks_len, socks_len, counts,
+			       counts_len);
+done:
+	free_fds(new_socks, socks_len);
+}
+
+struct test_case {
+	void (*test)(int family, int sock_type, const char *addr, __u16 port,
+		     int *socks, int socks_len, struct sock_count *counts,
+		     int counts_len, struct bpf_link *link, int iter_fd);
+	const char *description;
+	int init_socks;
+	int max_socks;
+	int sock_type;
+	int family;
+};
+
+static struct test_case resume_tests[] = {
+	{
+		.description = "udp: resume after removing a seen socket",
+		.init_socks = nr_soreuse,
+		.max_socks = nr_soreuse,
+		.sock_type = SOCK_DGRAM,
+		.family = AF_INET6,
+		.test = remove_seen,
+	},
+	{
+		.description = "udp: resume after removing one unseen socket",
+		.init_socks = nr_soreuse,
+		.max_socks = nr_soreuse,
+		.sock_type = SOCK_DGRAM,
+		.family = AF_INET6,
+		.test = remove_unseen,
+	},
+	{
+		.description = "udp: resume after removing all unseen sockets",
+		.init_socks = nr_soreuse,
+		.max_socks = nr_soreuse,
+		.sock_type = SOCK_DGRAM,
+		.family = AF_INET6,
+		.test = remove_all,
+	},
+	{
+		.description = "udp: resume after adding a few sockets",
+		.init_socks = nr_soreuse,
+		.max_socks = nr_soreuse,
+		.sock_type = SOCK_DGRAM,
+		/* Use AF_INET so that new sockets are added to the head of the
+		 * bucket's list.
+		 */
+		.family = AF_INET,
+		.test = add_some,
+	},
+	{
+		.description = "udp: force a realloc to occur",
+		.init_socks = init_batch_size,
+		.max_socks = init_batch_size * 2,
+		.sock_type = SOCK_DGRAM,
+		/* Use AF_INET6 so that new sockets are added to the tail of the
+		 * bucket's list, needing to be added to the next batch to force
+		 * a realloc.
+		 */
+		.family = AF_INET6,
+		.test = force_realloc,
+	},
+};
+
+static void do_resume_test(struct test_case *tc)
+{
+	struct sock_iter_batch *skel = NULL;
+	static const __u16 port = 10001;
+	struct bpf_link *link = NULL;
+	struct sock_count *counts;
+	int err, iter_fd = -1;
+	const char *addr;
+	int *fds = NULL;
+	int local_port;
+
+	counts = calloc(tc->max_socks, sizeof(*counts));
+	if (!ASSERT_OK_PTR(counts, "counts"))
+		goto done;
+	skel = sock_iter_batch__open();
+	if (!ASSERT_OK_PTR(skel, "sock_iter_batch__open"))
+		goto done;
+
+	/* Prepare a bucket of sockets in the kernel hashtable */
+	addr = tc->family == AF_INET6 ? "::1" : "127.0.0.1";
+	fds = start_reuseport_server(tc->family, tc->sock_type, addr, port, 0,
+				     tc->init_socks);
+	if (!ASSERT_OK_PTR(fds, "start_reuseport_server"))
+		goto done;
+	local_port = get_socket_local_port(*fds);
+	if (!ASSERT_GE(local_port, 0, "get_socket_local_port"))
+		goto done;
+	skel->rodata->ports[0] = ntohs(local_port);
+	skel->rodata->sf = tc->family;
+
+	err = sock_iter_batch__load(skel);
+	if (!ASSERT_OK(err, "sock_iter_batch__load"))
+		goto done;
+
+	link = bpf_program__attach_iter(tc->sock_type == SOCK_STREAM ?
+					skel->progs.iter_tcp_soreuse :
+					skel->progs.iter_udp_soreuse,
+					NULL);
+	if (!ASSERT_OK_PTR(link, "bpf_program__attach_iter"))
+		goto done;
+
+	iter_fd = bpf_iter_create(bpf_link__fd(link));
+	if (!ASSERT_OK_FD(iter_fd, "bpf_iter_create"))
+		goto done;
+
+	tc->test(tc->family, tc->sock_type, addr, port, fds, tc->init_socks,
+		 counts, tc->max_socks, link, iter_fd);
+done:
+	free(counts);
+	free_fds(fds, tc->init_socks);
+	if (iter_fd >= 0)
+		close(iter_fd);
+	bpf_link__destroy(link);
+	sock_iter_batch__destroy(skel);
+}
+
+static void do_resume_tests(void)
+{
+	int i;
+
+	for (i = 0; i < ARRAY_SIZE(resume_tests); i++) {
+		if (test__start_subtest(resume_tests[i].description)) {
+			do_resume_test(&resume_tests[i]);
+		}
+	}
+}
+
 static void do_test(int sock_type, bool onebyone)
 {
 	int err, i, nread, to_read, total_read, iter_fd = -1;
-	int first_idx, second_idx, indices[nr_soreuse];
+	struct iter_out outputs[nr_soreuse];
 	struct bpf_link *link = NULL;
 	struct sock_iter_batch *skel;
+	int first_idx, second_idx;
 	int *fds[2] = {};
 
 	skel = sock_iter_batch__open();
@@ -34,6 +453,7 @@ static void do_test(int sock_type, bool onebyone)
 			goto done;
 		skel->rodata->ports[i] = ntohs(local_port);
 	}
+	skel->rodata->sf = AF_INET6;
 
 	err = sock_iter_batch__load(skel);
 	if (!ASSERT_OK(err, "sock_iter_batch__load"))
@@ -55,38 +475,38 @@ static void do_test(int sock_type, bool onebyone)
 	 * from a bucket and leave one socket out from
 	 * that bucket on purpose.
 	 */
-	to_read = (nr_soreuse - 1) * sizeof(*indices);
+	to_read = (nr_soreuse - 1) * sizeof(*outputs);
 	total_read = 0;
 	first_idx = -1;
 	do {
-		nread = read(iter_fd, indices, onebyone ? sizeof(*indices) : to_read);
-		if (nread <= 0 || nread % sizeof(*indices))
+		nread = read(iter_fd, outputs, onebyone ? sizeof(*outputs) : to_read);
+		if (nread <= 0 || nread % sizeof(*outputs))
 			break;
 		total_read += nread;
 
 		if (first_idx == -1)
-			first_idx = indices[0];
-		for (i = 0; i < nread / sizeof(*indices); i++)
-			ASSERT_EQ(indices[i], first_idx, "first_idx");
+			first_idx = outputs[0].idx;
+		for (i = 0; i < nread / sizeof(*outputs); i++)
+			ASSERT_EQ(outputs[i].idx, first_idx, "first_idx");
 	} while (total_read < to_read);
-	ASSERT_EQ(nread, onebyone ? sizeof(*indices) : to_read, "nread");
+	ASSERT_EQ(nread, onebyone ? sizeof(*outputs) : to_read, "nread");
 	ASSERT_EQ(total_read, to_read, "total_read");
 
 	free_fds(fds[first_idx], nr_soreuse);
 	fds[first_idx] = NULL;
 
 	/* Read the "whole" second bucket */
-	to_read = nr_soreuse * sizeof(*indices);
+	to_read = nr_soreuse * sizeof(*outputs);
 	total_read = 0;
 	second_idx = !first_idx;
 	do {
-		nread = read(iter_fd, indices, onebyone ? sizeof(*indices) : to_read);
-		if (nread <= 0 || nread % sizeof(*indices))
+		nread = read(iter_fd, outputs, onebyone ? sizeof(*outputs) : to_read);
+		if (nread <= 0 || nread % sizeof(*outputs))
 			break;
 		total_read += nread;
 
-		for (i = 0; i < nread / sizeof(*indices); i++)
-			ASSERT_EQ(indices[i], second_idx, "second_idx");
+		for (i = 0; i < nread / sizeof(*outputs); i++)
+			ASSERT_EQ(outputs[i].idx, second_idx, "second_idx");
 	} while (total_read <= to_read);
 	ASSERT_EQ(nread, 0, "nread");
 	/* Both so_reuseport ports should be in different buckets, so
@@ -128,6 +548,7 @@ void test_sock_iter_batch(void)
 		do_test(SOCK_DGRAM, true);
 		do_test(SOCK_DGRAM, false);
 	}
+	do_resume_tests();
 	close_netns(nstoken);
 
 done:
diff --git a/tools/testing/selftests/bpf/progs/bpf_qdisc_common.h b/tools/testing/selftests/bpf/progs/bpf_qdisc_common.h
new file mode 100644
index 000000000000..3754f581b328
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/bpf_qdisc_common.h
@@ -0,0 +1,27 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+#ifndef _BPF_QDISC_COMMON_H
+#define _BPF_QDISC_COMMON_H
+
+#define NET_XMIT_SUCCESS        0x00
+#define NET_XMIT_DROP           0x01    /* skb dropped                  */
+#define NET_XMIT_CN             0x02    /* congestion notification      */
+
+#define TC_PRIO_CONTROL  7
+#define TC_PRIO_MAX      15
+
+#define private(name) SEC(".data." #name) __hidden __attribute__((aligned(8)))
+
+struct bpf_sk_buff_ptr;
+
+static struct qdisc_skb_cb *qdisc_skb_cb(const struct sk_buff *skb)
+{
+	return (struct qdisc_skb_cb *)skb->cb;
+}
+
+static inline unsigned int qdisc_pkt_len(const struct sk_buff *skb)
+{
+	return qdisc_skb_cb(skb)->pkt_len;
+}
+
+#endif
diff --git a/tools/testing/selftests/bpf/progs/bpf_qdisc_fail__incompl_ops.c b/tools/testing/selftests/bpf/progs/bpf_qdisc_fail__incompl_ops.c
new file mode 100644
index 000000000000..f188062ed730
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/bpf_qdisc_fail__incompl_ops.c
@@ -0,0 +1,41 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <vmlinux.h>
+#include "bpf_experimental.h"
+#include "bpf_qdisc_common.h"
+
+char _license[] SEC("license") = "GPL";
+
+SEC("struct_ops")
+int BPF_PROG(bpf_qdisc_test_enqueue, struct sk_buff *skb, struct Qdisc *sch,
+	     struct bpf_sk_buff_ptr *to_free)
+{
+	bpf_qdisc_skb_drop(skb, to_free);
+	return NET_XMIT_DROP;
+}
+
+SEC("struct_ops")
+struct sk_buff *BPF_PROG(bpf_qdisc_test_dequeue, struct Qdisc *sch)
+{
+	return NULL;
+}
+
+SEC("struct_ops")
+void BPF_PROG(bpf_qdisc_test_reset, struct Qdisc *sch)
+{
+}
+
+SEC("struct_ops")
+void BPF_PROG(bpf_qdisc_test_destroy, struct Qdisc *sch)
+{
+}
+
+SEC(".struct_ops")
+struct Qdisc_ops test = {
+	.enqueue   = (void *)bpf_qdisc_test_enqueue,
+	.dequeue   = (void *)bpf_qdisc_test_dequeue,
+	.reset     = (void *)bpf_qdisc_test_reset,
+	.destroy   = (void *)bpf_qdisc_test_destroy,
+	.id        = "bpf_qdisc_test",
+};
+
diff --git a/tools/testing/selftests/bpf/progs/bpf_qdisc_fifo.c b/tools/testing/selftests/bpf/progs/bpf_qdisc_fifo.c
new file mode 100644
index 000000000000..1de2be3e370b
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/bpf_qdisc_fifo.c
@@ -0,0 +1,126 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <vmlinux.h>
+#include "bpf_experimental.h"
+#include "bpf_qdisc_common.h"
+
+char _license[] SEC("license") = "GPL";
+
+struct skb_node {
+	struct sk_buff __kptr * skb;
+	struct bpf_list_node node;
+};
+
+private(A) struct bpf_spin_lock q_fifo_lock;
+private(A) struct bpf_list_head q_fifo __contains(skb_node, node);
+
+bool init_called;
+
+SEC("struct_ops/bpf_fifo_enqueue")
+int BPF_PROG(bpf_fifo_enqueue, struct sk_buff *skb, struct Qdisc *sch,
+	     struct bpf_sk_buff_ptr *to_free)
+{
+	struct skb_node *skbn;
+	u32 pkt_len;
+
+	if (sch->q.qlen == sch->limit)
+		goto drop;
+
+	skbn = bpf_obj_new(typeof(*skbn));
+	if (!skbn)
+		goto drop;
+
+	pkt_len = qdisc_pkt_len(skb);
+
+	sch->q.qlen++;
+	skb = bpf_kptr_xchg(&skbn->skb, skb);
+	if (skb)
+		bpf_qdisc_skb_drop(skb, to_free);
+
+	bpf_spin_lock(&q_fifo_lock);
+	bpf_list_push_back(&q_fifo, &skbn->node);
+	bpf_spin_unlock(&q_fifo_lock);
+
+	sch->qstats.backlog += pkt_len;
+	return NET_XMIT_SUCCESS;
+drop:
+	bpf_qdisc_skb_drop(skb, to_free);
+	return NET_XMIT_DROP;
+}
+
+SEC("struct_ops/bpf_fifo_dequeue")
+struct sk_buff *BPF_PROG(bpf_fifo_dequeue, struct Qdisc *sch)
+{
+	struct bpf_list_node *node;
+	struct sk_buff *skb = NULL;
+	struct skb_node *skbn;
+
+	bpf_spin_lock(&q_fifo_lock);
+	node = bpf_list_pop_front(&q_fifo);
+	bpf_spin_unlock(&q_fifo_lock);
+	if (!node)
+		return NULL;
+
+	skbn = container_of(node, struct skb_node, node);
+	skb = bpf_kptr_xchg(&skbn->skb, skb);
+	bpf_obj_drop(skbn);
+	if (!skb)
+		return NULL;
+
+	sch->qstats.backlog -= qdisc_pkt_len(skb);
+	bpf_qdisc_bstats_update(sch, skb);
+	sch->q.qlen--;
+
+	return skb;
+}
+
+SEC("struct_ops/bpf_fifo_init")
+int BPF_PROG(bpf_fifo_init, struct Qdisc *sch, struct nlattr *opt,
+	     struct netlink_ext_ack *extack)
+{
+	sch->limit = 1000;
+	init_called = true;
+	return 0;
+}
+
+SEC("struct_ops/bpf_fifo_reset")
+void BPF_PROG(bpf_fifo_reset, struct Qdisc *sch)
+{
+	struct bpf_list_node *node;
+	struct skb_node *skbn;
+	int i;
+
+	bpf_for(i, 0, sch->q.qlen) {
+		struct sk_buff *skb = NULL;
+
+		bpf_spin_lock(&q_fifo_lock);
+		node = bpf_list_pop_front(&q_fifo);
+		bpf_spin_unlock(&q_fifo_lock);
+
+		if (!node)
+			break;
+
+		skbn = container_of(node, struct skb_node, node);
+		skb = bpf_kptr_xchg(&skbn->skb, skb);
+		if (skb)
+			bpf_kfree_skb(skb);
+		bpf_obj_drop(skbn);
+	}
+	sch->q.qlen = 0;
+}
+
+SEC("struct_ops")
+void BPF_PROG(bpf_fifo_destroy, struct Qdisc *sch)
+{
+}
+
+SEC(".struct_ops")
+struct Qdisc_ops fifo = {
+	.enqueue   = (void *)bpf_fifo_enqueue,
+	.dequeue   = (void *)bpf_fifo_dequeue,
+	.init      = (void *)bpf_fifo_init,
+	.reset     = (void *)bpf_fifo_reset,
+	.destroy   = (void *)bpf_fifo_destroy,
+	.id        = "bpf_fifo",
+};
+
diff --git a/tools/testing/selftests/bpf/progs/bpf_qdisc_fq.c b/tools/testing/selftests/bpf/progs/bpf_qdisc_fq.c
new file mode 100644
index 000000000000..1a3233a275c7
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/bpf_qdisc_fq.c
@@ -0,0 +1,756 @@
+// SPDX-License-Identifier: GPL-2.0
+
+/* bpf_fq is intended for testing the bpf qdisc infrastructure and not a direct
+ * copy of sch_fq. bpf_fq implements the scheduling algorithm of sch_fq before
+ * 29f834aa326e ("net_sched: sch_fq: add 3 bands and WRR scheduling") was
+ * introduced. It gives each flow a fair chance to transmit packets in a
+ * round-robin fashion. Note that for flow pacing, bpf_fq currently only
+ * respects skb->tstamp but not skb->sk->sk_pacing_rate. In addition, if there
+ * are multiple bpf_fq instances, they will have a shared view of flows and
+ * configuration since some key data structure such as fq_prio_flows,
+ * fq_nonprio_flows, and fq_bpf_data are global.
+ *
+ * To use bpf_fq alone without running selftests, use the following commands.
+ *
+ * 1. Register bpf_fq to the kernel
+ *     bpftool struct_ops register bpf_qdisc_fq.bpf.o /sys/fs/bpf
+ * 2. Add bpf_fq to an interface
+ *     tc qdisc add dev <interface name> root handle <handle> bpf_fq
+ * 3. Delete bpf_fq attached to the interface
+ *     tc qdisc delete dev <interface name> root
+ * 4. Unregister bpf_fq
+ *     bpftool struct_ops unregister name fq
+ *
+ * The qdisc name, bpf_fq, used in tc commands is defined by Qdisc_ops.id.
+ * The struct_ops_map_name, fq, used in the bpftool command is the name of the
+ * Qdisc_ops.
+ *
+ * SEC(".struct_ops")
+ * struct Qdisc_ops fq = {
+ *         ...
+ *         .id        = "bpf_fq",
+ * };
+ */
+
+#include <vmlinux.h>
+#include <errno.h>
+#include <bpf/bpf_helpers.h>
+#include "bpf_experimental.h"
+#include "bpf_qdisc_common.h"
+
+char _license[] SEC("license") = "GPL";
+
+#define NSEC_PER_USEC 1000L
+#define NSEC_PER_SEC 1000000000L
+
+#define NUM_QUEUE (1 << 20)
+
+struct fq_bpf_data {
+	u32 quantum;
+	u32 initial_quantum;
+	u32 flow_refill_delay;
+	u32 flow_plimit;
+	u64 horizon;
+	u32 orphan_mask;
+	u32 timer_slack;
+	u64 time_next_delayed_flow;
+	u64 unthrottle_latency_ns;
+	u8 horizon_drop;
+	u32 new_flow_cnt;
+	u32 old_flow_cnt;
+	u64 ktime_cache;
+};
+
+enum {
+	CLS_RET_PRIO	= 0,
+	CLS_RET_NONPRIO = 1,
+	CLS_RET_ERR	= 2,
+};
+
+struct skb_node {
+	u64 tstamp;
+	struct sk_buff __kptr * skb;
+	struct bpf_rb_node node;
+};
+
+struct fq_flow_node {
+	int credit;
+	u32 qlen;
+	u64 age;
+	u64 time_next_packet;
+	struct bpf_list_node list_node;
+	struct bpf_rb_node rb_node;
+	struct bpf_rb_root queue __contains(skb_node, node);
+	struct bpf_spin_lock lock;
+	struct bpf_refcount refcount;
+};
+
+struct dequeue_nonprio_ctx {
+	bool stop_iter;
+	u64 expire;
+	u64 now;
+};
+
+struct remove_flows_ctx {
+	bool gc_only;
+	u32 reset_cnt;
+	u32 reset_max;
+};
+
+struct unset_throttled_flows_ctx {
+	bool unset_all;
+	u64 now;
+};
+
+struct fq_stashed_flow {
+	struct fq_flow_node __kptr * flow;
+};
+
+struct {
+	__uint(type, BPF_MAP_TYPE_HASH);
+	__type(key, __u64);
+	__type(value, struct fq_stashed_flow);
+	__uint(max_entries, NUM_QUEUE);
+} fq_nonprio_flows SEC(".maps");
+
+struct {
+	__uint(type, BPF_MAP_TYPE_HASH);
+	__type(key, __u64);
+	__type(value, struct fq_stashed_flow);
+	__uint(max_entries, 1);
+} fq_prio_flows SEC(".maps");
+
+private(A) struct bpf_spin_lock fq_delayed_lock;
+private(A) struct bpf_rb_root fq_delayed __contains(fq_flow_node, rb_node);
+
+private(B) struct bpf_spin_lock fq_new_flows_lock;
+private(B) struct bpf_list_head fq_new_flows __contains(fq_flow_node, list_node);
+
+private(C) struct bpf_spin_lock fq_old_flows_lock;
+private(C) struct bpf_list_head fq_old_flows __contains(fq_flow_node, list_node);
+
+private(D) struct fq_bpf_data q;
+
+/* Wrapper for bpf_kptr_xchg that expects NULL dst */
+static void bpf_kptr_xchg_back(void *map_val, void *ptr)
+{
+	void *ret;
+
+	ret = bpf_kptr_xchg(map_val, ptr);
+	if (ret)
+		bpf_obj_drop(ret);
+}
+
+static bool skbn_tstamp_less(struct bpf_rb_node *a, const struct bpf_rb_node *b)
+{
+	struct skb_node *skbn_a;
+	struct skb_node *skbn_b;
+
+	skbn_a = container_of(a, struct skb_node, node);
+	skbn_b = container_of(b, struct skb_node, node);
+
+	return skbn_a->tstamp < skbn_b->tstamp;
+}
+
+static bool fn_time_next_packet_less(struct bpf_rb_node *a, const struct bpf_rb_node *b)
+{
+	struct fq_flow_node *flow_a;
+	struct fq_flow_node *flow_b;
+
+	flow_a = container_of(a, struct fq_flow_node, rb_node);
+	flow_b = container_of(b, struct fq_flow_node, rb_node);
+
+	return flow_a->time_next_packet < flow_b->time_next_packet;
+}
+
+static void
+fq_flows_add_head(struct bpf_list_head *head, struct bpf_spin_lock *lock,
+		  struct fq_flow_node *flow, u32 *flow_cnt)
+{
+	bpf_spin_lock(lock);
+	bpf_list_push_front(head, &flow->list_node);
+	bpf_spin_unlock(lock);
+	*flow_cnt += 1;
+}
+
+static void
+fq_flows_add_tail(struct bpf_list_head *head, struct bpf_spin_lock *lock,
+		  struct fq_flow_node *flow, u32 *flow_cnt)
+{
+	bpf_spin_lock(lock);
+	bpf_list_push_back(head, &flow->list_node);
+	bpf_spin_unlock(lock);
+	*flow_cnt += 1;
+}
+
+static void
+fq_flows_remove_front(struct bpf_list_head *head, struct bpf_spin_lock *lock,
+		      struct bpf_list_node **node, u32 *flow_cnt)
+{
+	bpf_spin_lock(lock);
+	*node = bpf_list_pop_front(head);
+	bpf_spin_unlock(lock);
+	*flow_cnt -= 1;
+}
+
+static bool
+fq_flows_is_empty(struct bpf_list_head *head, struct bpf_spin_lock *lock)
+{
+	struct bpf_list_node *node;
+
+	bpf_spin_lock(lock);
+	node = bpf_list_pop_front(head);
+	if (node) {
+		bpf_list_push_front(head, node);
+		bpf_spin_unlock(lock);
+		return false;
+	}
+	bpf_spin_unlock(lock);
+
+	return true;
+}
+
+/* flow->age is used to denote the state of the flow (not-detached, detached, throttled)
+ * as well as the timestamp when the flow is detached.
+ *
+ * 0: not-detached
+ * 1 - (~0ULL-1): detached
+ * ~0ULL: throttled
+ */
+static void fq_flow_set_detached(struct fq_flow_node *flow)
+{
+	flow->age = bpf_jiffies64();
+}
+
+static bool fq_flow_is_detached(struct fq_flow_node *flow)
+{
+	return flow->age != 0 && flow->age != ~0ULL;
+}
+
+static bool sk_listener(struct sock *sk)
+{
+	return (1 << sk->__sk_common.skc_state) & (TCPF_LISTEN | TCPF_NEW_SYN_RECV);
+}
+
+static void fq_gc(void);
+
+static int fq_new_flow(void *flow_map, struct fq_stashed_flow **sflow, u64 hash)
+{
+	struct fq_stashed_flow tmp = {};
+	struct fq_flow_node *flow;
+	int ret;
+
+	flow = bpf_obj_new(typeof(*flow));
+	if (!flow)
+		return -ENOMEM;
+
+	flow->credit = q.initial_quantum,
+	flow->qlen = 0,
+	flow->age = 1,
+	flow->time_next_packet = 0,
+
+	ret = bpf_map_update_elem(flow_map, &hash, &tmp, 0);
+	if (ret == -ENOMEM || ret == -E2BIG) {
+		fq_gc();
+		bpf_map_update_elem(&fq_nonprio_flows, &hash, &tmp, 0);
+	}
+
+	*sflow = bpf_map_lookup_elem(flow_map, &hash);
+	if (!*sflow) {
+		bpf_obj_drop(flow);
+		return -ENOMEM;
+	}
+
+	bpf_kptr_xchg_back(&(*sflow)->flow, flow);
+	return 0;
+}
+
+static int
+fq_classify(struct sk_buff *skb, struct fq_stashed_flow **sflow)
+{
+	struct sock *sk = skb->sk;
+	int ret = CLS_RET_NONPRIO;
+	u64 hash = 0;
+
+	if ((skb->priority & TC_PRIO_MAX) == TC_PRIO_CONTROL) {
+		*sflow = bpf_map_lookup_elem(&fq_prio_flows, &hash);
+		ret = CLS_RET_PRIO;
+	} else {
+		if (!sk || sk_listener(sk)) {
+			hash = bpf_skb_get_hash(skb) & q.orphan_mask;
+			/* Avoid collision with an existing flow hash, which
+			 * only uses the lower 32 bits of hash, by setting the
+			 * upper half of hash to 1.
+			 */
+			hash |= (1ULL << 32);
+		} else if (sk->__sk_common.skc_state == TCP_CLOSE) {
+			hash = bpf_skb_get_hash(skb) & q.orphan_mask;
+			hash |= (1ULL << 32);
+		} else {
+			hash = sk->__sk_common.skc_hash;
+		}
+		*sflow = bpf_map_lookup_elem(&fq_nonprio_flows, &hash);
+	}
+
+	if (!*sflow)
+		ret = fq_new_flow(&fq_nonprio_flows, sflow, hash) < 0 ?
+		      CLS_RET_ERR : CLS_RET_NONPRIO;
+
+	return ret;
+}
+
+static bool fq_packet_beyond_horizon(struct sk_buff *skb)
+{
+	return (s64)skb->tstamp > (s64)(q.ktime_cache + q.horizon);
+}
+
+SEC("struct_ops/bpf_fq_enqueue")
+int BPF_PROG(bpf_fq_enqueue, struct sk_buff *skb, struct Qdisc *sch,
+	     struct bpf_sk_buff_ptr *to_free)
+{
+	struct fq_flow_node *flow = NULL, *flow_copy;
+	struct fq_stashed_flow *sflow;
+	u64 time_to_send, jiffies;
+	struct skb_node *skbn;
+	int ret;
+
+	if (sch->q.qlen >= sch->limit)
+		goto drop;
+
+	if (!skb->tstamp) {
+		time_to_send = q.ktime_cache = bpf_ktime_get_ns();
+	} else {
+		if (fq_packet_beyond_horizon(skb)) {
+			q.ktime_cache = bpf_ktime_get_ns();
+			if (fq_packet_beyond_horizon(skb)) {
+				if (q.horizon_drop)
+					goto drop;
+
+				skb->tstamp = q.ktime_cache + q.horizon;
+			}
+		}
+		time_to_send = skb->tstamp;
+	}
+
+	ret = fq_classify(skb, &sflow);
+	if (ret == CLS_RET_ERR)
+		goto drop;
+
+	flow = bpf_kptr_xchg(&sflow->flow, flow);
+	if (!flow)
+		goto drop;
+
+	if (ret == CLS_RET_NONPRIO) {
+		if (flow->qlen >= q.flow_plimit) {
+			bpf_kptr_xchg_back(&sflow->flow, flow);
+			goto drop;
+		}
+
+		if (fq_flow_is_detached(flow)) {
+			flow_copy = bpf_refcount_acquire(flow);
+
+			jiffies = bpf_jiffies64();
+			if ((s64)(jiffies - (flow_copy->age + q.flow_refill_delay)) > 0) {
+				if (flow_copy->credit < q.quantum)
+					flow_copy->credit = q.quantum;
+			}
+			flow_copy->age = 0;
+			fq_flows_add_tail(&fq_new_flows, &fq_new_flows_lock, flow_copy,
+					  &q.new_flow_cnt);
+		}
+	}
+
+	skbn = bpf_obj_new(typeof(*skbn));
+	if (!skbn) {
+		bpf_kptr_xchg_back(&sflow->flow, flow);
+		goto drop;
+	}
+
+	skbn->tstamp = skb->tstamp = time_to_send;
+
+	sch->qstats.backlog += qdisc_pkt_len(skb);
+
+	skb = bpf_kptr_xchg(&skbn->skb, skb);
+	if (skb)
+		bpf_qdisc_skb_drop(skb, to_free);
+
+	bpf_spin_lock(&flow->lock);
+	bpf_rbtree_add(&flow->queue, &skbn->node, skbn_tstamp_less);
+	bpf_spin_unlock(&flow->lock);
+
+	flow->qlen++;
+	bpf_kptr_xchg_back(&sflow->flow, flow);
+
+	sch->q.qlen++;
+	return NET_XMIT_SUCCESS;
+
+drop:
+	bpf_qdisc_skb_drop(skb, to_free);
+	sch->qstats.drops++;
+	return NET_XMIT_DROP;
+}
+
+static int fq_unset_throttled_flows(u32 index, struct unset_throttled_flows_ctx *ctx)
+{
+	struct bpf_rb_node *node = NULL;
+	struct fq_flow_node *flow;
+
+	bpf_spin_lock(&fq_delayed_lock);
+
+	node = bpf_rbtree_first(&fq_delayed);
+	if (!node) {
+		bpf_spin_unlock(&fq_delayed_lock);
+		return 1;
+	}
+
+	flow = container_of(node, struct fq_flow_node, rb_node);
+	if (!ctx->unset_all && flow->time_next_packet > ctx->now) {
+		q.time_next_delayed_flow = flow->time_next_packet;
+		bpf_spin_unlock(&fq_delayed_lock);
+		return 1;
+	}
+
+	node = bpf_rbtree_remove(&fq_delayed, &flow->rb_node);
+
+	bpf_spin_unlock(&fq_delayed_lock);
+
+	if (!node)
+		return 1;
+
+	flow = container_of(node, struct fq_flow_node, rb_node);
+	flow->age = 0;
+	fq_flows_add_tail(&fq_old_flows, &fq_old_flows_lock, flow, &q.old_flow_cnt);
+
+	return 0;
+}
+
+static void fq_flow_set_throttled(struct fq_flow_node *flow)
+{
+	flow->age = ~0ULL;
+
+	if (q.time_next_delayed_flow > flow->time_next_packet)
+		q.time_next_delayed_flow = flow->time_next_packet;
+
+	bpf_spin_lock(&fq_delayed_lock);
+	bpf_rbtree_add(&fq_delayed, &flow->rb_node, fn_time_next_packet_less);
+	bpf_spin_unlock(&fq_delayed_lock);
+}
+
+static void fq_check_throttled(u64 now)
+{
+	struct unset_throttled_flows_ctx ctx = {
+		.unset_all = false,
+		.now = now,
+	};
+	unsigned long sample;
+
+	if (q.time_next_delayed_flow > now)
+		return;
+
+	sample = (unsigned long)(now - q.time_next_delayed_flow);
+	q.unthrottle_latency_ns -= q.unthrottle_latency_ns >> 3;
+	q.unthrottle_latency_ns += sample >> 3;
+
+	q.time_next_delayed_flow = ~0ULL;
+	bpf_loop(NUM_QUEUE, fq_unset_throttled_flows, &ctx, 0);
+}
+
+static struct sk_buff*
+fq_dequeue_nonprio_flows(u32 index, struct dequeue_nonprio_ctx *ctx)
+{
+	u64 time_next_packet, time_to_send;
+	struct bpf_rb_node *rb_node;
+	struct sk_buff *skb = NULL;
+	struct bpf_list_head *head;
+	struct bpf_list_node *node;
+	struct bpf_spin_lock *lock;
+	struct fq_flow_node *flow;
+	struct skb_node *skbn;
+	bool is_empty;
+	u32 *cnt;
+
+	if (q.new_flow_cnt) {
+		head = &fq_new_flows;
+		lock = &fq_new_flows_lock;
+		cnt = &q.new_flow_cnt;
+	} else if (q.old_flow_cnt) {
+		head = &fq_old_flows;
+		lock = &fq_old_flows_lock;
+		cnt = &q.old_flow_cnt;
+	} else {
+		if (q.time_next_delayed_flow != ~0ULL)
+			ctx->expire = q.time_next_delayed_flow;
+		goto break_loop;
+	}
+
+	fq_flows_remove_front(head, lock, &node, cnt);
+	if (!node)
+		goto break_loop;
+
+	flow = container_of(node, struct fq_flow_node, list_node);
+	if (flow->credit <= 0) {
+		flow->credit += q.quantum;
+		fq_flows_add_tail(&fq_old_flows, &fq_old_flows_lock, flow, &q.old_flow_cnt);
+		return NULL;
+	}
+
+	bpf_spin_lock(&flow->lock);
+	rb_node = bpf_rbtree_first(&flow->queue);
+	if (!rb_node) {
+		bpf_spin_unlock(&flow->lock);
+		is_empty = fq_flows_is_empty(&fq_old_flows, &fq_old_flows_lock);
+		if (head == &fq_new_flows && !is_empty) {
+			fq_flows_add_tail(&fq_old_flows, &fq_old_flows_lock, flow, &q.old_flow_cnt);
+		} else {
+			fq_flow_set_detached(flow);
+			bpf_obj_drop(flow);
+		}
+		return NULL;
+	}
+
+	skbn = container_of(rb_node, struct skb_node, node);
+	time_to_send = skbn->tstamp;
+
+	time_next_packet = (time_to_send > flow->time_next_packet) ?
+		time_to_send : flow->time_next_packet;
+	if (ctx->now < time_next_packet) {
+		bpf_spin_unlock(&flow->lock);
+		flow->time_next_packet = time_next_packet;
+		fq_flow_set_throttled(flow);
+		return NULL;
+	}
+
+	rb_node = bpf_rbtree_remove(&flow->queue, rb_node);
+	bpf_spin_unlock(&flow->lock);
+
+	if (!rb_node)
+		goto add_flow_and_break;
+
+	skbn = container_of(rb_node, struct skb_node, node);
+	skb = bpf_kptr_xchg(&skbn->skb, skb);
+	bpf_obj_drop(skbn);
+
+	if (!skb)
+		goto add_flow_and_break;
+
+	flow->credit -= qdisc_skb_cb(skb)->pkt_len;
+	flow->qlen--;
+
+add_flow_and_break:
+	fq_flows_add_head(head, lock, flow, cnt);
+
+break_loop:
+	ctx->stop_iter = true;
+	return skb;
+}
+
+static struct sk_buff *fq_dequeue_prio(void)
+{
+	struct fq_flow_node *flow = NULL;
+	struct fq_stashed_flow *sflow;
+	struct bpf_rb_node *rb_node;
+	struct sk_buff *skb = NULL;
+	struct skb_node *skbn;
+	u64 hash = 0;
+
+	sflow = bpf_map_lookup_elem(&fq_prio_flows, &hash);
+	if (!sflow)
+		return NULL;
+
+	flow = bpf_kptr_xchg(&sflow->flow, flow);
+	if (!flow)
+		return NULL;
+
+	bpf_spin_lock(&flow->lock);
+	rb_node = bpf_rbtree_first(&flow->queue);
+	if (!rb_node) {
+		bpf_spin_unlock(&flow->lock);
+		goto out;
+	}
+
+	skbn = container_of(rb_node, struct skb_node, node);
+	rb_node = bpf_rbtree_remove(&flow->queue, &skbn->node);
+	bpf_spin_unlock(&flow->lock);
+
+	if (!rb_node)
+		goto out;
+
+	skbn = container_of(rb_node, struct skb_node, node);
+	skb = bpf_kptr_xchg(&skbn->skb, skb);
+	bpf_obj_drop(skbn);
+
+out:
+	bpf_kptr_xchg_back(&sflow->flow, flow);
+
+	return skb;
+}
+
+SEC("struct_ops/bpf_fq_dequeue")
+struct sk_buff *BPF_PROG(bpf_fq_dequeue, struct Qdisc *sch)
+{
+	struct dequeue_nonprio_ctx cb_ctx = {};
+	struct sk_buff *skb = NULL;
+	int i;
+
+	if (!sch->q.qlen)
+		goto out;
+
+	skb = fq_dequeue_prio();
+	if (skb)
+		goto dequeue;
+
+	q.ktime_cache = cb_ctx.now = bpf_ktime_get_ns();
+	fq_check_throttled(q.ktime_cache);
+	bpf_for(i, 0, sch->limit) {
+		skb = fq_dequeue_nonprio_flows(i, &cb_ctx);
+		if (cb_ctx.stop_iter)
+			break;
+	};
+
+	if (skb) {
+dequeue:
+		sch->q.qlen--;
+		sch->qstats.backlog -= qdisc_pkt_len(skb);
+		bpf_qdisc_bstats_update(sch, skb);
+		return skb;
+	}
+
+	if (cb_ctx.expire)
+		bpf_qdisc_watchdog_schedule(sch, cb_ctx.expire, q.timer_slack);
+out:
+	return NULL;
+}
+
+static int fq_remove_flows_in_list(u32 index, void *ctx)
+{
+	struct bpf_list_node *node;
+	struct fq_flow_node *flow;
+
+	bpf_spin_lock(&fq_new_flows_lock);
+	node = bpf_list_pop_front(&fq_new_flows);
+	bpf_spin_unlock(&fq_new_flows_lock);
+	if (!node) {
+		bpf_spin_lock(&fq_old_flows_lock);
+		node = bpf_list_pop_front(&fq_old_flows);
+		bpf_spin_unlock(&fq_old_flows_lock);
+		if (!node)
+			return 1;
+	}
+
+	flow = container_of(node, struct fq_flow_node, list_node);
+	bpf_obj_drop(flow);
+
+	return 0;
+}
+
+extern unsigned CONFIG_HZ __kconfig;
+
+/* limit number of collected flows per round */
+#define FQ_GC_MAX 8
+#define FQ_GC_AGE (3*CONFIG_HZ)
+
+static bool fq_gc_candidate(struct fq_flow_node *flow)
+{
+	u64 jiffies = bpf_jiffies64();
+
+	return fq_flow_is_detached(flow) &&
+	       ((s64)(jiffies - (flow->age + FQ_GC_AGE)) > 0);
+}
+
+static int
+fq_remove_flows(struct bpf_map *flow_map, u64 *hash,
+		struct fq_stashed_flow *sflow, struct remove_flows_ctx *ctx)
+{
+	if (sflow->flow &&
+	    (!ctx->gc_only || fq_gc_candidate(sflow->flow))) {
+		bpf_map_delete_elem(flow_map, hash);
+		ctx->reset_cnt++;
+	}
+
+	return ctx->reset_cnt < ctx->reset_max ? 0 : 1;
+}
+
+static void fq_gc(void)
+{
+	struct remove_flows_ctx cb_ctx = {
+		.gc_only = true,
+		.reset_cnt = 0,
+		.reset_max = FQ_GC_MAX,
+	};
+
+	bpf_for_each_map_elem(&fq_nonprio_flows, fq_remove_flows, &cb_ctx, 0);
+}
+
+SEC("struct_ops/bpf_fq_reset")
+void BPF_PROG(bpf_fq_reset, struct Qdisc *sch)
+{
+	struct unset_throttled_flows_ctx utf_ctx = {
+		.unset_all = true,
+	};
+	struct remove_flows_ctx rf_ctx = {
+		.gc_only = false,
+		.reset_cnt = 0,
+		.reset_max = NUM_QUEUE,
+	};
+	struct fq_stashed_flow *sflow;
+	u64 hash = 0;
+
+	sch->q.qlen = 0;
+	sch->qstats.backlog = 0;
+
+	bpf_for_each_map_elem(&fq_nonprio_flows, fq_remove_flows, &rf_ctx, 0);
+
+	rf_ctx.reset_cnt = 0;
+	bpf_for_each_map_elem(&fq_prio_flows, fq_remove_flows, &rf_ctx, 0);
+	fq_new_flow(&fq_prio_flows, &sflow, hash);
+
+	bpf_loop(NUM_QUEUE, fq_remove_flows_in_list, NULL, 0);
+	q.new_flow_cnt = 0;
+	q.old_flow_cnt = 0;
+
+	bpf_loop(NUM_QUEUE, fq_unset_throttled_flows, &utf_ctx, 0);
+}
+
+SEC("struct_ops/bpf_fq_init")
+int BPF_PROG(bpf_fq_init, struct Qdisc *sch, struct nlattr *opt,
+	     struct netlink_ext_ack *extack)
+{
+	struct net_device *dev = sch->dev_queue->dev;
+	u32 psched_mtu = dev->mtu + dev->hard_header_len;
+	struct fq_stashed_flow *sflow;
+	u64 hash = 0;
+
+	if (fq_new_flow(&fq_prio_flows, &sflow, hash) < 0)
+		return -ENOMEM;
+
+	sch->limit = 10000;
+	q.initial_quantum = 10 * psched_mtu;
+	q.quantum = 2 * psched_mtu;
+	q.flow_refill_delay = 40;
+	q.flow_plimit = 100;
+	q.horizon = 10ULL * NSEC_PER_SEC;
+	q.horizon_drop = 1;
+	q.orphan_mask = 1024 - 1;
+	q.timer_slack = 10 * NSEC_PER_USEC;
+	q.time_next_delayed_flow = ~0ULL;
+	q.unthrottle_latency_ns = 0ULL;
+	q.new_flow_cnt = 0;
+	q.old_flow_cnt = 0;
+
+	return 0;
+}
+
+SEC("struct_ops")
+void BPF_PROG(bpf_fq_destroy, struct Qdisc *sch)
+{
+}
+
+SEC(".struct_ops")
+struct Qdisc_ops fq = {
+	.enqueue   = (void *)bpf_fq_enqueue,
+	.dequeue   = (void *)bpf_fq_dequeue,
+	.reset     = (void *)bpf_fq_reset,
+	.init      = (void *)bpf_fq_init,
+	.destroy   = (void *)bpf_fq_destroy,
+	.id        = "bpf_fq",
+};
diff --git a/tools/testing/selftests/bpf/progs/bpf_tracing_net.h b/tools/testing/selftests/bpf/progs/bpf_tracing_net.h
index 659694162739..17db400f0e0d 100644
--- a/tools/testing/selftests/bpf/progs/bpf_tracing_net.h
+++ b/tools/testing/selftests/bpf/progs/bpf_tracing_net.h
@@ -128,6 +128,7 @@
 #define sk_refcnt		__sk_common.skc_refcnt
 #define sk_state		__sk_common.skc_state
 #define sk_net			__sk_common.skc_net
+#define sk_rcv_saddr		__sk_common.skc_rcv_saddr
 #define sk_v6_daddr		__sk_common.skc_v6_daddr
 #define sk_v6_rcv_saddr		__sk_common.skc_v6_rcv_saddr
 #define sk_flags		__sk_common.skc_flags
diff --git a/tools/testing/selftests/bpf/progs/setget_sockopt.c b/tools/testing/selftests/bpf/progs/setget_sockopt.c
index 0107a24b7522..d330b1511979 100644
--- a/tools/testing/selftests/bpf/progs/setget_sockopt.c
+++ b/tools/testing/selftests/bpf/progs/setget_sockopt.c
@@ -83,6 +83,14 @@ struct loop_ctx {
 	struct sock *sk;
 };
 
+static bool sk_is_tcp(struct sock *sk)
+{
+	return (sk->__sk_common.skc_family == AF_INET ||
+		sk->__sk_common.skc_family == AF_INET6) &&
+		sk->sk_type == SOCK_STREAM &&
+		sk->sk_protocol == IPPROTO_TCP;
+}
+
 static int bpf_test_sockopt_flip(void *ctx, struct sock *sk,
 				 const struct sockopt_test *t,
 				 int level)
@@ -91,6 +99,9 @@ static int bpf_test_sockopt_flip(void *ctx, struct sock *sk,
 
 	opt = t->opt;
 
+	if (opt == SO_TXREHASH && !sk_is_tcp(sk))
+		return 0;
+
 	if (bpf_getsockopt(ctx, level, opt, &old, sizeof(old)))
 		return 1;
 	/* kernel initialized txrehash to 255 */
diff --git a/tools/testing/selftests/bpf/progs/sock_iter_batch.c b/tools/testing/selftests/bpf/progs/sock_iter_batch.c
index 96531b0d9d55..8f483337e103 100644
--- a/tools/testing/selftests/bpf/progs/sock_iter_batch.c
+++ b/tools/testing/selftests/bpf/progs/sock_iter_batch.c
@@ -17,6 +17,12 @@ static bool ipv6_addr_loopback(const struct in6_addr *a)
 		a->s6_addr32[2] | (a->s6_addr32[3] ^ bpf_htonl(1))) == 0;
 }
 
+static bool ipv4_addr_loopback(__be32 a)
+{
+	return a == bpf_ntohl(0x7f000001);
+}
+
+volatile const unsigned int sf;
 volatile const __u16 ports[2];
 unsigned int bucket[2];
 
@@ -26,16 +32,20 @@ int iter_tcp_soreuse(struct bpf_iter__tcp *ctx)
 	struct sock *sk = (struct sock *)ctx->sk_common;
 	struct inet_hashinfo *hinfo;
 	unsigned int hash;
+	__u64 sock_cookie;
 	struct net *net;
 	int idx;
 
 	if (!sk)
 		return 0;
 
+	sock_cookie = bpf_get_socket_cookie(sk);
 	sk = bpf_core_cast(sk, struct sock);
-	if (sk->sk_family != AF_INET6 ||
+	if (sk->sk_family != sf ||
 	    sk->sk_state != TCP_LISTEN ||
-	    !ipv6_addr_loopback(&sk->sk_v6_rcv_saddr))
+	    sk->sk_family == AF_INET6 ?
+	    !ipv6_addr_loopback(&sk->sk_v6_rcv_saddr) :
+	    !ipv4_addr_loopback(sk->sk_rcv_saddr))
 		return 0;
 
 	if (sk->sk_num == ports[0])
@@ -52,6 +62,7 @@ int iter_tcp_soreuse(struct bpf_iter__tcp *ctx)
 	hinfo = net->ipv4.tcp_death_row.hashinfo;
 	bucket[idx] = hash & hinfo->lhash2_mask;
 	bpf_seq_write(ctx->meta->seq, &idx, sizeof(idx));
+	bpf_seq_write(ctx->meta->seq, &sock_cookie, sizeof(sock_cookie));
 
 	return 0;
 }
@@ -63,14 +74,18 @@ int iter_udp_soreuse(struct bpf_iter__udp *ctx)
 {
 	struct sock *sk = (struct sock *)ctx->udp_sk;
 	struct udp_table *udptable;
+	__u64 sock_cookie;
 	int idx;
 
 	if (!sk)
 		return 0;
 
+	sock_cookie = bpf_get_socket_cookie(sk);
 	sk = bpf_core_cast(sk, struct sock);
-	if (sk->sk_family != AF_INET6 ||
-	    !ipv6_addr_loopback(&sk->sk_v6_rcv_saddr))
+	if (sk->sk_family != sf ||
+	    sk->sk_family == AF_INET6 ?
+	    !ipv6_addr_loopback(&sk->sk_v6_rcv_saddr) :
+	    !ipv4_addr_loopback(sk->sk_rcv_saddr))
 		return 0;
 
 	if (sk->sk_num == ports[0])
@@ -84,6 +99,7 @@ int iter_udp_soreuse(struct bpf_iter__udp *ctx)
 	udptable = sk->sk_net.net->ipv4.udp_table;
 	bucket[idx] = udp_sk(sk)->udp_portaddr_hash & udptable->mask;
 	bpf_seq_write(ctx->meta->seq, &idx, sizeof(idx));
+	bpf_seq_write(ctx->meta->seq, &sock_cookie, sizeof(sock_cookie));
 
 	return 0;
 }
diff --git a/tools/testing/selftests/bpf/progs/xsk_xdp_progs.c b/tools/testing/selftests/bpf/progs/xsk_xdp_progs.c
index ccde6a4c6319..683306db8594 100644
--- a/tools/testing/selftests/bpf/progs/xsk_xdp_progs.c
+++ b/tools/testing/selftests/bpf/progs/xsk_xdp_progs.c
@@ -4,6 +4,8 @@
 #include <linux/bpf.h>
 #include <bpf/bpf_helpers.h>
 #include <linux/if_ether.h>
+#include <linux/ip.h>
+#include <linux/errno.h>
 #include "xsk_xdp_common.h"
 
 struct {
@@ -14,6 +16,7 @@ struct {
 } xsk SEC(".maps");
 
 static unsigned int idx;
+int adjust_value = 0;
 int count = 0;
 
 SEC("xdp.frags") int xsk_def_prog(struct xdp_md *xdp)
@@ -70,4 +73,51 @@ SEC("xdp") int xsk_xdp_shared_umem(struct xdp_md *xdp)
 	return bpf_redirect_map(&xsk, idx, XDP_DROP);
 }
 
+SEC("xdp.frags") int xsk_xdp_adjust_tail(struct xdp_md *xdp)
+{
+	__u32 buff_len, curr_buff_len;
+	int ret;
+
+	buff_len = bpf_xdp_get_buff_len(xdp);
+	if (buff_len == 0)
+		return XDP_DROP;
+
+	ret = bpf_xdp_adjust_tail(xdp, adjust_value);
+	if (ret < 0) {
+		/* Handle unsupported cases */
+		if (ret == -EOPNOTSUPP) {
+			/* Set adjust_value to -EOPNOTSUPP to indicate to userspace that this case
+			 * is unsupported
+			 */
+			adjust_value = -EOPNOTSUPP;
+			return bpf_redirect_map(&xsk, 0, XDP_DROP);
+		}
+
+		return XDP_DROP;
+	}
+
+	curr_buff_len = bpf_xdp_get_buff_len(xdp);
+	if (curr_buff_len != buff_len + adjust_value)
+		return XDP_DROP;
+
+	if (curr_buff_len > buff_len) {
+		__u32 *pkt_data = (void *)(long)xdp->data;
+		__u32 len, words_to_end, seq_num;
+
+		len = curr_buff_len - PKT_HDR_ALIGN;
+		words_to_end = len / sizeof(*pkt_data) - 1;
+		seq_num = words_to_end;
+
+		/* Convert sequence number to network byte order. Store this in the last 4 bytes of
+		 * the packet. Use 'adjust_value' to determine the position at the end of the
+		 * packet for storing the sequence number.
+		 */
+		seq_num = __constant_htonl(words_to_end);
+		bpf_xdp_store_bytes(xdp, curr_buff_len - sizeof(seq_num), &seq_num,
+				    sizeof(seq_num));
+	}
+
+	return bpf_redirect_map(&xsk, 0, XDP_DROP);
+}
+
 char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/xsk_xdp_common.h b/tools/testing/selftests/bpf/xsk_xdp_common.h
index 5a6f36f07383..45810ff552da 100644
--- a/tools/testing/selftests/bpf/xsk_xdp_common.h
+++ b/tools/testing/selftests/bpf/xsk_xdp_common.h
@@ -4,6 +4,7 @@
 #define XSK_XDP_COMMON_H_
 
 #define MAX_SOCKETS 2
+#define PKT_HDR_ALIGN (sizeof(struct ethhdr) + 2) /* Just to align the data in the packet */
 
 struct xdp_info {
 	__u64 count;
diff --git a/tools/testing/selftests/bpf/xskxceiver.c b/tools/testing/selftests/bpf/xskxceiver.c
index 11f047b8af75..0ced4026ee44 100644
--- a/tools/testing/selftests/bpf/xskxceiver.c
+++ b/tools/testing/selftests/bpf/xskxceiver.c
@@ -524,6 +524,8 @@ static void __test_spec_init(struct test_spec *test, struct ifobject *ifobj_tx,
 	test->nb_sockets = 1;
 	test->fail = false;
 	test->set_ring = false;
+	test->adjust_tail = false;
+	test->adjust_tail_support = false;
 	test->mtu = MAX_ETH_PKT_SIZE;
 	test->xdp_prog_rx = ifobj_rx->xdp_progs->progs.xsk_def_prog;
 	test->xskmap_rx = ifobj_rx->xdp_progs->maps.xsk;
@@ -757,14 +759,15 @@ static struct pkt_stream *pkt_stream_clone(struct pkt_stream *pkt_stream)
 	return pkt_stream_generate(pkt_stream->nb_pkts, pkt_stream->pkts[0].len);
 }
 
-static void pkt_stream_replace(struct test_spec *test, u32 nb_pkts, u32 pkt_len)
+static void pkt_stream_replace_ifobject(struct ifobject *ifobj, u32 nb_pkts, u32 pkt_len)
 {
-	struct pkt_stream *pkt_stream;
+	ifobj->xsk->pkt_stream = pkt_stream_generate(nb_pkts, pkt_len);
+}
 
-	pkt_stream = pkt_stream_generate(nb_pkts, pkt_len);
-	test->ifobj_tx->xsk->pkt_stream = pkt_stream;
-	pkt_stream = pkt_stream_generate(nb_pkts, pkt_len);
-	test->ifobj_rx->xsk->pkt_stream = pkt_stream;
+static void pkt_stream_replace(struct test_spec *test, u32 nb_pkts, u32 pkt_len)
+{
+	pkt_stream_replace_ifobject(test->ifobj_tx, nb_pkts, pkt_len);
+	pkt_stream_replace_ifobject(test->ifobj_rx, nb_pkts, pkt_len);
 }
 
 static void __pkt_stream_replace_half(struct ifobject *ifobj, u32 pkt_len,
@@ -991,6 +994,31 @@ static bool is_metadata_correct(struct pkt *pkt, void *buffer, u64 addr)
 	return true;
 }
 
+static bool is_adjust_tail_supported(struct xsk_xdp_progs *skel_rx)
+{
+	struct bpf_map *data_map;
+	int adjust_value = 0;
+	int key = 0;
+	int ret;
+
+	data_map = bpf_object__find_map_by_name(skel_rx->obj, "xsk_xdp_.bss");
+	if (!data_map || !bpf_map__is_internal(data_map)) {
+		ksft_print_msg("Error: could not find bss section of XDP program\n");
+		exit_with_error(errno);
+	}
+
+	ret = bpf_map_lookup_elem(bpf_map__fd(data_map), &key, &adjust_value);
+	if (ret) {
+		ksft_print_msg("Error: bpf_map_lookup_elem failed with error %d\n", ret);
+		exit_with_error(errno);
+	}
+
+	/* Set the 'adjust_value' variable to -EOPNOTSUPP in the XDP program if the adjust_tail
+	 * helper is not supported. Skip the adjust_tail test case in this scenario.
+	 */
+	return adjust_value != -EOPNOTSUPP;
+}
+
 static bool is_frag_valid(struct xsk_umem_info *umem, u64 addr, u32 len, u32 expected_pkt_nb,
 			  u32 bytes_processed)
 {
@@ -1767,8 +1795,13 @@ static void *worker_testapp_validate_rx(void *arg)
 
 	if (!err && ifobject->validation_func)
 		err = ifobject->validation_func(ifobject);
-	if (err)
-		report_failure(test);
+
+	if (err) {
+		if (test->adjust_tail && !is_adjust_tail_supported(ifobject->xdp_progs))
+			test->adjust_tail_support = false;
+		else
+			report_failure(test);
+	}
 
 	pthread_exit(NULL);
 }
@@ -2515,6 +2548,71 @@ static int testapp_hw_sw_max_ring_size(struct test_spec *test)
 	return testapp_validate_traffic(test);
 }
 
+static int testapp_xdp_adjust_tail(struct test_spec *test, int adjust_value)
+{
+	struct xsk_xdp_progs *skel_rx = test->ifobj_rx->xdp_progs;
+	struct xsk_xdp_progs *skel_tx = test->ifobj_tx->xdp_progs;
+
+	test_spec_set_xdp_prog(test, skel_rx->progs.xsk_xdp_adjust_tail,
+			       skel_tx->progs.xsk_xdp_adjust_tail,
+			       skel_rx->maps.xsk, skel_tx->maps.xsk);
+
+	skel_rx->bss->adjust_value = adjust_value;
+
+	return testapp_validate_traffic(test);
+}
+
+static int testapp_adjust_tail(struct test_spec *test, u32 value, u32 pkt_len)
+{
+	int ret;
+
+	test->adjust_tail_support = true;
+	test->adjust_tail = true;
+	test->total_steps = 1;
+
+	pkt_stream_replace_ifobject(test->ifobj_tx, DEFAULT_BATCH_SIZE, pkt_len);
+	pkt_stream_replace_ifobject(test->ifobj_rx, DEFAULT_BATCH_SIZE, pkt_len + value);
+
+	ret = testapp_xdp_adjust_tail(test, value);
+	if (ret)
+		return ret;
+
+	if (!test->adjust_tail_support) {
+		ksft_test_result_skip("%s %sResize pkt with bpf_xdp_adjust_tail() not supported\n",
+				      mode_string(test), busy_poll_string(test));
+		return TEST_SKIP;
+	}
+
+	return 0;
+}
+
+static int testapp_adjust_tail_shrink(struct test_spec *test)
+{
+	/* Shrink by 4 bytes for testing purpose */
+	return testapp_adjust_tail(test, -4, MIN_PKT_SIZE * 2);
+}
+
+static int testapp_adjust_tail_shrink_mb(struct test_spec *test)
+{
+	test->mtu = MAX_ETH_JUMBO_SIZE;
+	/* Shrink by the frag size */
+	return testapp_adjust_tail(test, -XSK_UMEM__MAX_FRAME_SIZE, XSK_UMEM__LARGE_FRAME_SIZE * 2);
+}
+
+static int testapp_adjust_tail_grow(struct test_spec *test)
+{
+	/* Grow by 4 bytes for testing purpose */
+	return testapp_adjust_tail(test, 4, MIN_PKT_SIZE * 2);
+}
+
+static int testapp_adjust_tail_grow_mb(struct test_spec *test)
+{
+	test->mtu = MAX_ETH_JUMBO_SIZE;
+	/* Grow by (frag_size - last_frag_Size) - 1 to stay inside the last fragment */
+	return testapp_adjust_tail(test, (XSK_UMEM__MAX_FRAME_SIZE / 2) - 1,
+				   XSK_UMEM__LARGE_FRAME_SIZE * 2);
+}
+
 static void run_pkt_test(struct test_spec *test)
 {
 	int ret;
@@ -2621,6 +2719,10 @@ static const struct test_spec tests[] = {
 	{.name = "TOO_MANY_FRAGS", .test_func = testapp_too_many_frags},
 	{.name = "HW_SW_MIN_RING_SIZE", .test_func = testapp_hw_sw_min_ring_size},
 	{.name = "HW_SW_MAX_RING_SIZE", .test_func = testapp_hw_sw_max_ring_size},
+	{.name = "XDP_ADJUST_TAIL_SHRINK", .test_func = testapp_adjust_tail_shrink},
+	{.name = "XDP_ADJUST_TAIL_SHRINK_MULTI_BUFF", .test_func = testapp_adjust_tail_shrink_mb},
+	{.name = "XDP_ADJUST_TAIL_GROW", .test_func = testapp_adjust_tail_grow},
+	{.name = "XDP_ADJUST_TAIL_GROW_MULTI_BUFF", .test_func = testapp_adjust_tail_grow_mb},
 	};
 
 static void print_tests(void)
diff --git a/tools/testing/selftests/bpf/xskxceiver.h b/tools/testing/selftests/bpf/xskxceiver.h
index e46e823f6a1a..67fc44b2813b 100644
--- a/tools/testing/selftests/bpf/xskxceiver.h
+++ b/tools/testing/selftests/bpf/xskxceiver.h
@@ -173,6 +173,8 @@ struct test_spec {
 	u16 nb_sockets;
 	bool fail;
 	bool set_ring;
+	bool adjust_tail;
+	bool adjust_tail_support;
 	enum test_mode mode;
 	char name[MAX_TEST_NAME_SIZE];
 };
diff --git a/tools/testing/selftests/drivers/net/.gitignore b/tools/testing/selftests/drivers/net/.gitignore
index ec746f374e85..d634d8395d90 100644
--- a/tools/testing/selftests/drivers/net/.gitignore
+++ b/tools/testing/selftests/drivers/net/.gitignore
@@ -1,2 +1,2 @@
 # SPDX-License-Identifier: GPL-2.0-only
-xdp_helper
+napi_id_helper
diff --git a/tools/testing/selftests/drivers/net/Makefile b/tools/testing/selftests/drivers/net/Makefile
index 0c95bd944d56..be780bcb73a3 100644
--- a/tools/testing/selftests/drivers/net/Makefile
+++ b/tools/testing/selftests/drivers/net/Makefile
@@ -3,12 +3,14 @@ CFLAGS += $(KHDR_INCLUDES)
 
 TEST_INCLUDES := $(wildcard lib/py/*.py) \
 		 $(wildcard lib/sh/*.sh) \
-		 ../../net/net_helper.sh \
 		 ../../net/lib.sh \
 
-TEST_GEN_FILES := xdp_helper
+TEST_GEN_FILES := \
+	napi_id_helper \
+# end of TEST_GEN_FILES
 
 TEST_PROGS := \
+	napi_id.py \
 	netcons_basic.sh \
 	netcons_fragmented_msg.sh \
 	netcons_overflow.sh \
diff --git a/tools/testing/selftests/drivers/net/hw/Makefile b/tools/testing/selftests/drivers/net/hw/Makefile
index 07cddb19ba35..df2c047ffa90 100644
--- a/tools/testing/selftests/drivers/net/hw/Makefile
+++ b/tools/testing/selftests/drivers/net/hw/Makefile
@@ -15,12 +15,11 @@ TEST_PROGS = \
 	iou-zcrx.py \
 	irq.py \
 	loopback.sh \
-	nic_link_layer.py \
-	nic_performance.py \
 	pp_alloc_fail.py \
 	rss_ctx.py \
 	rss_input_xfrm.py \
 	tso.py \
+	xsk_reconfig.py \
 	#
 
 TEST_FILES := \
diff --git a/tools/testing/selftests/drivers/net/hw/devmem.py b/tools/testing/selftests/drivers/net/hw/devmem.py
index 3947e9157115..7947650210a0 100755
--- a/tools/testing/selftests/drivers/net/hw/devmem.py
+++ b/tools/testing/selftests/drivers/net/hw/devmem.py
@@ -1,6 +1,7 @@
 #!/usr/bin/env python3
 # SPDX-License-Identifier: GPL-2.0
 
+from os import path
 from lib.py import ksft_run, ksft_exit
 from lib.py import ksft_eq, KsftSkipEx
 from lib.py import NetDrvEpEnv
@@ -10,8 +11,7 @@ from lib.py import ksft_disruptive
 
 def require_devmem(cfg):
     if not hasattr(cfg, "_devmem_probed"):
-        port = rand_port()
-        probe_command = f"./ncdevmem -f {cfg.ifname}"
+        probe_command = f"{cfg.bin_local} -f {cfg.ifname}"
         cfg._devmem_supported = cmd(probe_command, fail=False, shell=True).ret == 0
         cfg._devmem_probed = True
 
@@ -21,22 +21,55 @@ def require_devmem(cfg):
 
 @ksft_disruptive
 def check_rx(cfg) -> None:
-    cfg.require_ipver("6")
     require_devmem(cfg)
 
     port = rand_port()
-    listen_cmd = f"./ncdevmem -l -f {cfg.ifname} -s {cfg.addr_v['6']} -p {port}"
+    socat = f"socat -u - TCP{cfg.addr_ipver}:{cfg.addr}:{port},bind={cfg.remote_addr}:{port}"
+    listen_cmd = f"{cfg.bin_local} -l -f {cfg.ifname} -s {cfg.addr} -p {port} -c {cfg.remote_addr} -v 7"
+
+    with bkg(listen_cmd, exit_wait=True) as ncdevmem:
+        wait_port_listen(port)
+        cmd(f"yes $(echo -e \x01\x02\x03\x04\x05\x06) | \
+            head -c 1K | {socat}", host=cfg.remote, shell=True)
+
+    ksft_eq(ncdevmem.ret, 0)
+
+
+@ksft_disruptive
+def check_tx(cfg) -> None:
+    require_devmem(cfg)
+
+    port = rand_port()
+    listen_cmd = f"socat -U - TCP{cfg.addr_ipver}-LISTEN:{port}"
 
     with bkg(listen_cmd) as socat:
         wait_port_listen(port)
-        cmd(f"echo -e \"hello\\nworld\"| socat -u - TCP6:[{cfg.addr_v['6']}]:{port}", host=cfg.remote, shell=True)
+        cmd(f"echo -e \"hello\\nworld\"| {cfg.bin_remote} -f {cfg.ifname} -s {cfg.addr} -p {port}", host=cfg.remote, shell=True)
+
+    ksft_eq(socat.stdout.strip(), "hello\nworld")
+
+
+@ksft_disruptive
+def check_tx_chunks(cfg) -> None:
+    cfg.require_ipver("6")
+    require_devmem(cfg)
+
+    port = rand_port()
+    listen_cmd = f"socat -U - TCP6-LISTEN:{port}"
+
+    with bkg(listen_cmd, exit_wait=True) as socat:
+        wait_port_listen(port)
+        cmd(f"echo -e \"hello\\nworld\"| {cfg.bin_remote} -f {cfg.ifname} -s {cfg.addr_v['6']} -p {port} -z 3", host=cfg.remote, shell=True)
 
     ksft_eq(socat.stdout.strip(), "hello\nworld")
 
 
 def main() -> None:
     with NetDrvEpEnv(__file__) as cfg:
-        ksft_run([check_rx],
+        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],
                  args=(cfg, ))
     ksft_exit()
 
diff --git a/tools/testing/selftests/drivers/net/hw/iou-zcrx.c b/tools/testing/selftests/drivers/net/hw/iou-zcrx.c
index c26b4180eddd..62456df947bc 100644
--- a/tools/testing/selftests/drivers/net/hw/iou-zcrx.c
+++ b/tools/testing/selftests/drivers/net/hw/iou-zcrx.c
@@ -37,8 +37,8 @@
 
 #include <liburing.h>
 
-#define PAGE_SIZE (4096)
-#define AREA_SIZE (8192 * PAGE_SIZE)
+static long page_size;
+#define AREA_SIZE (8192 * page_size)
 #define SEND_SIZE (512 * 4096)
 #define min(a, b) \
 	({ \
@@ -66,7 +66,7 @@ static int cfg_oneshot_recvs;
 static int cfg_send_size = SEND_SIZE;
 static struct sockaddr_in6 cfg_addr;
 
-static char payload[SEND_SIZE] __attribute__((aligned(PAGE_SIZE)));
+static char *payload;
 static void *area_ptr;
 static void *ring_ptr;
 static size_t ring_size;
@@ -114,8 +114,8 @@ static inline size_t get_refill_ring_size(unsigned int rq_entries)
 
 	ring_size = rq_entries * sizeof(struct io_uring_zcrx_rqe);
 	/* add space for the header (head/tail/etc.) */
-	ring_size += PAGE_SIZE;
-	return ALIGN_UP(ring_size, 4096);
+	ring_size += page_size;
+	return ALIGN_UP(ring_size, page_size);
 }
 
 static void setup_zcrx(struct io_uring *ring)
@@ -219,7 +219,7 @@ static void process_accept(struct io_uring *ring, struct io_uring_cqe *cqe)
 
 	connfd = cqe->res;
 	if (cfg_oneshot)
-		add_recvzc_oneshot(ring, connfd, PAGE_SIZE);
+		add_recvzc_oneshot(ring, connfd, page_size);
 	else
 		add_recvzc(ring, connfd);
 }
@@ -245,7 +245,7 @@ static void process_recvzc(struct io_uring *ring, struct io_uring_cqe *cqe)
 
 	if (cfg_oneshot) {
 		if (cqe->res == 0 && cqe->flags == 0 && cfg_oneshot_recvs) {
-			add_recvzc_oneshot(ring, connfd, PAGE_SIZE);
+			add_recvzc_oneshot(ring, connfd, page_size);
 			cfg_oneshot_recvs--;
 		}
 	} else if (!(cqe->flags & IORING_CQE_F_MORE)) {
@@ -260,7 +260,7 @@ static void process_recvzc(struct io_uring *ring, struct io_uring_cqe *cqe)
 
 	for (i = 0; i < n; i++) {
 		if (*(data + i) != payload[(received + i)])
-			error(1, 0, "payload mismatch at ", i);
+			error(1, 0, "payload mismatch at %d", i);
 	}
 	received += n;
 
@@ -354,7 +354,7 @@ static void run_client(void)
 		chunk = min_t(ssize_t, cfg_payload_len, to_send);
 		res = send(fd, src, chunk, 0);
 		if (res < 0)
-			error(1, 0, "send(): %d", sent);
+			error(1, 0, "send(): %zd", sent);
 		sent += res;
 		to_send -= res;
 	}
@@ -370,7 +370,7 @@ static void usage(const char *filepath)
 
 static void parse_opts(int argc, char **argv)
 {
-	const int max_payload_len = sizeof(payload) -
+	const int max_payload_len = SEND_SIZE -
 				    sizeof(struct ipv6hdr) -
 				    sizeof(struct tcphdr) -
 				    40 /* max tcp options */;
@@ -443,6 +443,13 @@ int main(int argc, char **argv)
 	const char *cfg_test = argv[argc - 1];
 	int i;
 
+	page_size = sysconf(_SC_PAGESIZE);
+	if (page_size < 0)
+		return 1;
+
+	if (posix_memalign((void **)&payload, page_size, SEND_SIZE))
+		return 1;
+
 	parse_opts(argc, argv);
 
 	for (i = 0; i < SEND_SIZE; i++)
diff --git a/tools/testing/selftests/drivers/net/hw/iou-zcrx.py b/tools/testing/selftests/drivers/net/hw/iou-zcrx.py
index 6a0378e06cab..9c03fd777f3d 100755
--- a/tools/testing/selftests/drivers/net/hw/iou-zcrx.py
+++ b/tools/testing/selftests/drivers/net/hw/iou-zcrx.py
@@ -5,13 +5,12 @@ import re
 from os import path
 from lib.py import ksft_run, ksft_exit
 from lib.py import NetDrvEpEnv
-from lib.py import bkg, cmd, ethtool, wait_port_listen
+from lib.py import bkg, cmd, defer, ethtool, rand_port, wait_port_listen
 
 
-def _get_rx_ring_entries(cfg):
-    output = ethtool(f"-g {cfg.ifname}", host=cfg.remote).stdout
-    values = re.findall(r'RX:\s+(\d+)', output)
-    return int(values[1])
+def _get_current_settings(cfg):
+    output = ethtool(f"-g {cfg.ifname}", json=True, host=cfg.remote)[0]
+    return (output['rx'], output['hds-thresh'])
 
 
 def _get_combined_channels(cfg):
@@ -20,8 +19,21 @@ def _get_combined_channels(cfg):
     return int(values[1])
 
 
-def _set_flow_rule(cfg, chan):
-    output = ethtool(f"-N {cfg.ifname} flow-type tcp6 dst-port 9999 action {chan}", host=cfg.remote).stdout
+def _create_rss_ctx(cfg, chan):
+    output = ethtool(f"-X {cfg.ifname} context new start {chan} equal 1", host=cfg.remote).stdout
+    values = re.search(r'New RSS context is (\d+)', output).group(1)
+    ctx_id = int(values)
+    return (ctx_id, defer(ethtool, f"-X {cfg.ifname} delete context {ctx_id}", host=cfg.remote))
+
+
+def _set_flow_rule(cfg, port, chan):
+    output = ethtool(f"-N {cfg.ifname} flow-type tcp6 dst-port {port} action {chan}", host=cfg.remote).stdout
+    values = re.search(r'ID (\d+)', output).group(1)
+    return int(values)
+
+
+def _set_flow_rule_rss(cfg, port, ctx_id):
+    output = ethtool(f"-N {cfg.ifname} flow-type tcp6 dst-port {port} context {ctx_id}", host=cfg.remote).stdout
     values = re.search(r'ID (\d+)', output).group(1)
     return int(values)
 
@@ -32,24 +44,29 @@ def test_zcrx(cfg) -> None:
     combined_chans = _get_combined_channels(cfg)
     if combined_chans < 2:
         raise KsftSkipEx('at least 2 combined channels required')
-    rx_ring = _get_rx_ring_entries(cfg)
-
-    try:
-        ethtool(f"-G {cfg.ifname} tcp-data-split on", host=cfg.remote)
-        ethtool(f"-G {cfg.ifname} rx 64", host=cfg.remote)
-        ethtool(f"-X {cfg.ifname} equal {combined_chans - 1}", host=cfg.remote)
-        flow_rule_id = _set_flow_rule(cfg, combined_chans - 1)
-
-        rx_cmd = f"{cfg.bin_remote} -s -p 9999 -i {cfg.ifname} -q {combined_chans - 1}"
-        tx_cmd = f"{cfg.bin_local} -c -h {cfg.remote_addr_v['6']} -p 9999 -l 12840"
-        with bkg(rx_cmd, host=cfg.remote, exit_wait=True):
-            wait_port_listen(9999, proto="tcp", host=cfg.remote)
-            cmd(tx_cmd)
-    finally:
-        ethtool(f"-N {cfg.ifname} delete {flow_rule_id}", host=cfg.remote)
-        ethtool(f"-X {cfg.ifname} default", host=cfg.remote)
-        ethtool(f"-G {cfg.ifname} rx {rx_ring}", host=cfg.remote)
-        ethtool(f"-G {cfg.ifname} tcp-data-split auto", host=cfg.remote)
+    (rx_ring, hds_thresh) = _get_current_settings(cfg)
+    port = rand_port()
+
+    ethtool(f"-G {cfg.ifname} tcp-data-split on", host=cfg.remote)
+    defer(ethtool, f"-G {cfg.ifname} tcp-data-split auto", host=cfg.remote)
+
+    ethtool(f"-G {cfg.ifname} hds-thresh 0", host=cfg.remote)
+    defer(ethtool, f"-G {cfg.ifname} hds-thresh {hds_thresh}", host=cfg.remote)
+
+    ethtool(f"-G {cfg.ifname} rx 64", host=cfg.remote)
+    defer(ethtool, f"-G {cfg.ifname} rx {rx_ring}", host=cfg.remote)
+
+    ethtool(f"-X {cfg.ifname} equal {combined_chans - 1}", host=cfg.remote)
+    defer(ethtool, f"-X {cfg.ifname} default", host=cfg.remote)
+
+    flow_rule_id = _set_flow_rule(cfg, port, combined_chans - 1)
+    defer(ethtool, f"-N {cfg.ifname} delete {flow_rule_id}", host=cfg.remote)
+
+    rx_cmd = f"{cfg.bin_remote} -s -p {port} -i {cfg.ifname} -q {combined_chans - 1}"
+    tx_cmd = f"{cfg.bin_local} -c -h {cfg.remote_addr_v['6']} -p {port} -l 12840"
+    with bkg(rx_cmd, host=cfg.remote, exit_wait=True):
+        wait_port_listen(port, proto="tcp", host=cfg.remote)
+        cmd(tx_cmd)
 
 
 def test_zcrx_oneshot(cfg) -> None:
@@ -58,24 +75,61 @@ def test_zcrx_oneshot(cfg) -> None:
     combined_chans = _get_combined_channels(cfg)
     if combined_chans < 2:
         raise KsftSkipEx('at least 2 combined channels required')
-    rx_ring = _get_rx_ring_entries(cfg)
-
-    try:
-        ethtool(f"-G {cfg.ifname} tcp-data-split on", host=cfg.remote)
-        ethtool(f"-G {cfg.ifname} rx 64", host=cfg.remote)
-        ethtool(f"-X {cfg.ifname} equal {combined_chans - 1}", host=cfg.remote)
-        flow_rule_id = _set_flow_rule(cfg, combined_chans - 1)
-
-        rx_cmd = f"{cfg.bin_remote} -s -p 9999 -i {cfg.ifname} -q {combined_chans - 1} -o 4"
-        tx_cmd = f"{cfg.bin_local} -c -h {cfg.remote_addr_v['6']} -p 9999 -l 4096 -z 16384"
-        with bkg(rx_cmd, host=cfg.remote, exit_wait=True):
-            wait_port_listen(9999, proto="tcp", host=cfg.remote)
-            cmd(tx_cmd)
-    finally:
-        ethtool(f"-N {cfg.ifname} delete {flow_rule_id}", host=cfg.remote)
-        ethtool(f"-X {cfg.ifname} default", host=cfg.remote)
-        ethtool(f"-G {cfg.ifname} rx {rx_ring}", host=cfg.remote)
-        ethtool(f"-G {cfg.ifname} tcp-data-split auto", host=cfg.remote)
+    (rx_ring, hds_thresh) = _get_current_settings(cfg)
+    port = rand_port()
+
+    ethtool(f"-G {cfg.ifname} tcp-data-split on", host=cfg.remote)
+    defer(ethtool, f"-G {cfg.ifname} tcp-data-split auto", host=cfg.remote)
+
+    ethtool(f"-G {cfg.ifname} hds-thresh 0", host=cfg.remote)
+    defer(ethtool, f"-G {cfg.ifname} hds-thresh {hds_thresh}", host=cfg.remote)
+
+    ethtool(f"-G {cfg.ifname} rx 64", host=cfg.remote)
+    defer(ethtool, f"-G {cfg.ifname} rx {rx_ring}", host=cfg.remote)
+
+    ethtool(f"-X {cfg.ifname} equal {combined_chans - 1}", host=cfg.remote)
+    defer(ethtool, f"-X {cfg.ifname} default", host=cfg.remote)
+
+    flow_rule_id = _set_flow_rule(cfg, port, combined_chans - 1)
+    defer(ethtool, f"-N {cfg.ifname} delete {flow_rule_id}", host=cfg.remote)
+
+    rx_cmd = f"{cfg.bin_remote} -s -p {port} -i {cfg.ifname} -q {combined_chans - 1} -o 4"
+    tx_cmd = f"{cfg.bin_local} -c -h {cfg.remote_addr_v['6']} -p {port} -l 4096 -z 16384"
+    with bkg(rx_cmd, host=cfg.remote, exit_wait=True):
+        wait_port_listen(port, proto="tcp", host=cfg.remote)
+        cmd(tx_cmd)
+
+
+def test_zcrx_rss(cfg) -> None:
+    cfg.require_ipver('6')
+
+    combined_chans = _get_combined_channels(cfg)
+    if combined_chans < 2:
+        raise KsftSkipEx('at least 2 combined channels required')
+    (rx_ring, hds_thresh) = _get_current_settings(cfg)
+    port = rand_port()
+
+    ethtool(f"-G {cfg.ifname} tcp-data-split on", host=cfg.remote)
+    defer(ethtool, f"-G {cfg.ifname} tcp-data-split auto", host=cfg.remote)
+
+    ethtool(f"-G {cfg.ifname} hds-thresh 0", host=cfg.remote)
+    defer(ethtool, f"-G {cfg.ifname} hds-thresh {hds_thresh}", host=cfg.remote)
+
+    ethtool(f"-G {cfg.ifname} rx 64", host=cfg.remote)
+    defer(ethtool, f"-G {cfg.ifname} rx {rx_ring}", host=cfg.remote)
+
+    ethtool(f"-X {cfg.ifname} equal {combined_chans - 1}", host=cfg.remote)
+    defer(ethtool, f"-X {cfg.ifname} default", host=cfg.remote)
+
+    (ctx_id, delete_ctx) = _create_rss_ctx(cfg, combined_chans - 1)
+    flow_rule_id = _set_flow_rule_rss(cfg, port, ctx_id)
+    defer(ethtool, f"-N {cfg.ifname} delete {flow_rule_id}", host=cfg.remote)
+
+    rx_cmd = f"{cfg.bin_remote} -s -p {port} -i {cfg.ifname} -q {combined_chans - 1}"
+    tx_cmd = f"{cfg.bin_local} -c -h {cfg.remote_addr_v['6']} -p {port} -l 12840"
+    with bkg(rx_cmd, host=cfg.remote, exit_wait=True):
+        wait_port_listen(port, proto="tcp", host=cfg.remote)
+        cmd(tx_cmd)
 
 
 def main() -> None:
diff --git a/tools/testing/selftests/drivers/net/hw/lib/py/__init__.py b/tools/testing/selftests/drivers/net/hw/lib/py/__init__.py
index 399789a9676a..b582885786f5 100644
--- a/tools/testing/selftests/drivers/net/hw/lib/py/__init__.py
+++ b/tools/testing/selftests/drivers/net/hw/lib/py/__init__.py
@@ -9,7 +9,6 @@ try:
     sys.path.append(KSFT_DIR.as_posix())
     from net.lib.py import *
     from drivers.net.lib.py import *
-    from .linkconfig import LinkConfig
 except ModuleNotFoundError as e:
     ksft_pr("Failed importing `net` library from kernel sources")
     ksft_pr(str(e))
diff --git a/tools/testing/selftests/drivers/net/hw/lib/py/linkconfig.py b/tools/testing/selftests/drivers/net/hw/lib/py/linkconfig.py
deleted file mode 100644
index 79fde603cbbc..000000000000
--- a/tools/testing/selftests/drivers/net/hw/lib/py/linkconfig.py
+++ /dev/null
@@ -1,222 +0,0 @@
-# SPDX-License-Identifier: GPL-2.0
-
-from lib.py import cmd, ethtool, ip
-from lib.py import ksft_pr, ksft_eq, KsftSkipEx
-from typing import Optional
-import re
-import time
-import json
-
-#The LinkConfig class is implemented to handle the link layer configurations.
-#Required minimum ethtool version is 6.10
-
-class LinkConfig:
-    """Class for handling the link layer configurations"""
-    def __init__(self, cfg: object) -> None:
-        self.cfg = cfg
-        self.partner_netif = self.get_partner_netif_name()
-
-        """Get the initial link configuration of local interface"""
-        self.common_link_modes = self.get_common_link_modes()
-
-    def get_partner_netif_name(self) -> Optional[str]:
-        partner_netif = None
-        try:
-            if not self.verify_link_up():
-                return None
-            """Get partner interface name"""
-            partner_json_output = ip("addr show", json=True, host=self.cfg.remote)
-            for interface in partner_json_output:
-                for addr in interface.get('addr_info', []):
-                    if addr.get('local') == self.cfg.remote_addr:
-                        partner_netif = interface['ifname']
-                        ksft_pr(f"Partner Interface name: {partner_netif}")
-            if partner_netif is None:
-                ksft_pr("Unable to get the partner interface name")
-        except Exception as e:
-            print(f"Unexpected error occurred while getting partner interface name: {e}")
-        self.partner_netif = partner_netif
-        return partner_netif
-
-    def verify_link_up(self) -> bool:
-        """Verify whether the local interface link is up"""
-        with open(f"/sys/class/net/{self.cfg.ifname}/operstate", "r") as fp:
-            link_state = fp.read().strip()
-
-        if link_state == "down":
-            ksft_pr(f"Link state of interface {self.cfg.ifname} is DOWN")
-            return False
-        else:
-            return True
-
-    def reset_interface(self, local: bool = True, remote: bool = True) -> bool:
-        ksft_pr("Resetting interfaces in local and remote")
-        if remote:
-            if self.verify_link_up():
-                if self.partner_netif is not None:
-                    ifname = self.partner_netif
-                    link_up_cmd = f"ip link set up {ifname}"
-                    link_down_cmd = f"ip link set down {ifname}"
-                    reset_cmd = f"{link_down_cmd} && sleep 5 && {link_up_cmd}"
-                    try:
-                        cmd(reset_cmd, host=self.cfg.remote)
-                    except Exception as e:
-                        ksft_pr(f"Unexpected error occurred while resetting remote: {e}")
-                else:
-                    ksft_pr("Partner interface not available")
-        if local:
-            ifname = self.cfg.ifname
-            link_up_cmd = f"ip link set up {ifname}"
-            link_down_cmd = f"ip link set down {ifname}"
-            reset_cmd = f"{link_down_cmd} && sleep 5 && {link_up_cmd}"
-            try:
-                cmd(reset_cmd)
-            except Exception as e:
-                ksft_pr(f"Unexpected error occurred while resetting local: {e}")
-        time.sleep(10)
-        if self.verify_link_up() and self.get_ethtool_field("link-detected"):
-            ksft_pr("Local and remote interfaces reset to original state")
-            return True
-        else:
-            ksft_pr("Error occurred after resetting interfaces. Link is DOWN.")
-            return False
-
-    def set_speed_and_duplex(self, speed: str, duplex: str, autoneg: bool = True) -> bool:
-        """Set the speed and duplex state for the interface"""
-        autoneg_state = "on" if autoneg is True else "off"
-        process = None
-        try:
-            process = ethtool(f"--change {self.cfg.ifname} speed {speed} duplex {duplex} autoneg {autoneg_state}")
-        except Exception as e:
-            ksft_pr(f"Unexpected error occurred while setting speed/duplex: {e}")
-        if process is None or process.ret != 0:
-            return False
-        else:
-            ksft_pr(f"Speed: {speed} Mbps, Duplex: {duplex} set for Interface: {self.cfg.ifname}")
-            return True
-
-    def verify_speed_and_duplex(self, expected_speed: str, expected_duplex: str) -> bool:
-        if not self.verify_link_up():
-            return False
-        """Verifying the speed and duplex state for the interface"""
-        with open(f"/sys/class/net/{self.cfg.ifname}/speed", "r") as fp:
-            actual_speed = fp.read().strip()
-        with open(f"/sys/class/net/{self.cfg.ifname}/duplex", "r") as fp:
-            actual_duplex = fp.read().strip()
-
-        ksft_eq(actual_speed, expected_speed)
-        ksft_eq(actual_duplex, expected_duplex)
-        return True
-
-    def set_autonegotiation_state(self, state: str, remote: bool = False) -> bool:
-        common_link_modes = self.common_link_modes
-        speeds, duplex_modes = self.get_speed_duplex_values(self.common_link_modes)
-        speed = speeds[0]
-        duplex = duplex_modes[0]
-        if not speed or not duplex:
-            ksft_pr("No speed or duplex modes found")
-            return False
-
-        speed_duplex_cmd = f"speed {speed} duplex {duplex}" if state == "off" else ""
-        if remote:
-            if not self.verify_link_up():
-                return False
-            """Set the autonegotiation state for the partner"""
-            command = f"-s {self.partner_netif} {speed_duplex_cmd} autoneg {state}"
-            partner_autoneg_change = None
-            """Set autonegotiation state for interface in remote pc"""
-            try:
-                partner_autoneg_change = ethtool(command, host=self.cfg.remote)
-            except Exception as e:
-                ksft_pr(f"Unexpected error occurred while changing auto-neg in remote: {e}")
-            if partner_autoneg_change is None or partner_autoneg_change.ret != 0:
-                ksft_pr(f"Not able to set autoneg parameter for interface {self.partner_netif}.")
-                return False
-            ksft_pr(f"Autoneg set as {state} for {self.partner_netif}")
-        else:
-            """Set the autonegotiation state for the interface"""
-            try:
-                process = ethtool(f"-s {self.cfg.ifname} {speed_duplex_cmd} autoneg {state}")
-                if process.ret != 0:
-                    ksft_pr(f"Not able to set autoneg parameter for interface {self.cfg.ifname}")
-                    return False
-            except Exception as e:
-                ksft_pr(f"Unexpected error occurred while changing auto-neg in local: {e}")
-                return False
-            ksft_pr(f"Autoneg set as {state} for {self.cfg.ifname}")
-        return True
-
-    def check_autoneg_supported(self, remote: bool = False) -> bool:
-        if not remote:
-            local_autoneg = self.get_ethtool_field("supports-auto-negotiation")
-            if local_autoneg is None:
-                ksft_pr(f"Unable to fetch auto-negotiation status for interface {self.cfg.ifname}")
-            """Return autoneg status of the local interface"""
-            return local_autoneg
-        else:
-            if not self.verify_link_up():
-                raise KsftSkipEx("Link is DOWN")
-            """Check remote auto-negotiation support status"""
-            partner_autoneg = False
-            if self.partner_netif is not None:
-                partner_autoneg = self.get_ethtool_field("supports-auto-negotiation", remote=True)
-                if partner_autoneg is None:
-                    ksft_pr(f"Unable to fetch auto-negotiation status for interface {self.partner_netif}")
-            return partner_autoneg
-
-    def get_common_link_modes(self) -> set[str]:
-        common_link_modes = []
-        """Populate common link modes"""
-        link_modes = self.get_ethtool_field("supported-link-modes")
-        partner_link_modes = self.get_ethtool_field("link-partner-advertised-link-modes")
-        if link_modes is None:
-            raise KsftSkipEx(f"Link modes not available for {self.cfg.ifname}")
-        if partner_link_modes is None:
-            raise KsftSkipEx(f"Partner link modes not available for {self.cfg.ifname}")
-        common_link_modes = set(link_modes) and set(partner_link_modes)
-        return common_link_modes
-
-    def get_speed_duplex_values(self, link_modes: list[str]) -> tuple[list[str], list[str]]:
-        speed = []
-        duplex = []
-        """Check the link modes"""
-        for data in link_modes:
-            parts = data.split('/')
-            speed_value = re.match(r'\d+', parts[0])
-            if speed_value:
-                speed.append(speed_value.group())
-            else:
-                ksft_pr(f"No speed value found for interface {self.ifname}")
-                return None, None
-            duplex.append(parts[1].lower())
-        return speed, duplex
-
-    def get_ethtool_field(self, field: str, remote: bool = False) -> Optional[str]:
-        process = None
-        if not remote:
-            """Get the ethtool field value for the local interface"""
-            try:
-                process = ethtool(self.cfg.ifname, json=True)
-            except Exception as e:
-                ksft_pr("Required minimum ethtool version is 6.10")
-                ksft_pr(f"Unexpected error occurred while getting ethtool field in local: {e}")
-                return None
-        else:
-            if not self.verify_link_up():
-                return None
-            """Get the ethtool field value for the remote interface"""
-            self.cfg.require_cmd("ethtool", remote=True)
-            if self.partner_netif is None:
-                ksft_pr(f"Partner interface name is unavailable.")
-                return None
-            try:
-                process = ethtool(self.partner_netif, json=True, host=self.cfg.remote)
-            except Exception as e:
-                ksft_pr("Required minimum ethtool version is 6.10")
-                ksft_pr(f"Unexpected error occurred while getting ethtool field in remote: {e}")
-                return None
-        json_data = process[0]
-        """Check if the field exist in the json data"""
-        if field not in json_data:
-            raise KsftSkipEx(f'Field {field} does not exist in the output of interface {json_data["ifname"]}')
-        return json_data[field]
diff --git a/tools/testing/selftests/drivers/net/hw/ncdevmem.c b/tools/testing/selftests/drivers/net/hw/ncdevmem.c
index 9d48004ff1a1..02e4d3d7ded2 100644
--- a/tools/testing/selftests/drivers/net/hw/ncdevmem.c
+++ b/tools/testing/selftests/drivers/net/hw/ncdevmem.c
@@ -9,22 +9,31 @@
  *     ncdevmem -s <server IP> [-c <client IP>] -f eth1 -l -p 5201
  *
  *     On client:
- *     echo -n "hello\nworld" | nc -s <server IP> 5201 -p 5201
+ *     echo -n "hello\nworld" | \
+ *		ncdevmem -s <server IP> [-c <client IP>] -p 5201 -f eth1
  *
- * Test data validation:
+ * Note this is compatible with regular netcat. i.e. the sender or receiver can
+ * be replaced with regular netcat to test the RX or TX path in isolation.
+ *
+ * Test data validation (devmem TCP on RX only):
  *
  *     On server:
  *     ncdevmem -s <server IP> [-c <client IP>] -f eth1 -l -p 5201 -v 7
  *
  *     On client:
  *     yes $(echo -e \\x01\\x02\\x03\\x04\\x05\\x06) | \
- *             tr \\n \\0 | \
- *             head -c 5G | \
+ *             head -c 1G | \
  *             nc <server IP> 5201 -p 5201
  *
+ * Test data validation (devmem TCP on RX and TX, validation happens on RX):
  *
- * Note this is compatible with regular netcat. i.e. the sender or receiver can
- * be replaced with regular netcat to test the RX or TX path in isolation.
+ *	On server:
+ *	ncdevmem -s <server IP> [-c <client IP>] -l -p 5201 -v 8 -f eth1
+ *
+ *	On client:
+ *	yes $(echo -e \\x01\\x02\\x03\\x04\\x05\\x06\\x07) | \
+ *		head -c 1M | \
+ *		ncdevmem -s <server IP> [-c <client IP>] -p 5201 -f eth1
  */
 #define _GNU_SOURCE
 #define __EXPORTED_HEADERS__
@@ -40,15 +49,18 @@
 #include <fcntl.h>
 #include <malloc.h>
 #include <error.h>
+#include <poll.h>
 
 #include <arpa/inet.h>
 #include <sys/socket.h>
 #include <sys/mman.h>
 #include <sys/ioctl.h>
 #include <sys/syscall.h>
+#include <sys/time.h>
 
 #include <linux/memfd.h>
 #include <linux/dma-buf.h>
+#include <linux/errqueue.h>
 #include <linux/udmabuf.h>
 #include <linux/types.h>
 #include <linux/netlink.h>
@@ -70,6 +82,9 @@
 #define MSG_SOCK_DEVMEM 0x2000000
 #endif
 
+#define MAX_IOV 1024
+
+static size_t max_chunk;
 static char *server_ip;
 static char *client_ip;
 static char *port;
@@ -79,6 +94,8 @@ static int num_queues = -1;
 static char *ifname;
 static unsigned int ifindex;
 static unsigned int dmabuf_id;
+static uint32_t tx_dmabuf_id;
+static int waittime_ms = 500;
 
 struct memory_buffer {
 	int fd;
@@ -92,6 +109,8 @@ struct memory_buffer {
 struct memory_provider {
 	struct memory_buffer *(*alloc)(size_t size);
 	void (*free)(struct memory_buffer *ctx);
+	void (*memcpy_to_device)(struct memory_buffer *dst, size_t off,
+				 void *src, int n);
 	void (*memcpy_from_device)(void *dst, struct memory_buffer *src,
 				   size_t off, int n);
 };
@@ -152,6 +171,20 @@ static void udmabuf_free(struct memory_buffer *ctx)
 	free(ctx);
 }
 
+static void udmabuf_memcpy_to_device(struct memory_buffer *dst, size_t off,
+				     void *src, int n)
+{
+	struct dma_buf_sync sync = {};
+
+	sync.flags = DMA_BUF_SYNC_START | DMA_BUF_SYNC_WRITE;
+	ioctl(dst->fd, DMA_BUF_IOCTL_SYNC, &sync);
+
+	memcpy(dst->buf_mem + off, src, n);
+
+	sync.flags = DMA_BUF_SYNC_END | DMA_BUF_SYNC_WRITE;
+	ioctl(dst->fd, DMA_BUF_IOCTL_SYNC, &sync);
+}
+
 static void udmabuf_memcpy_from_device(void *dst, struct memory_buffer *src,
 				       size_t off, int n)
 {
@@ -169,6 +202,7 @@ static void udmabuf_memcpy_from_device(void *dst, struct memory_buffer *src,
 static struct memory_provider udmabuf_memory_provider = {
 	.alloc = udmabuf_alloc,
 	.free = udmabuf_free,
+	.memcpy_to_device = udmabuf_memcpy_to_device,
 	.memcpy_from_device = udmabuf_memcpy_from_device,
 };
 
@@ -187,14 +221,16 @@ void validate_buffer(void *line, size_t size)
 {
 	static unsigned char seed = 1;
 	unsigned char *ptr = line;
-	int errors = 0;
+	unsigned char expected;
+	static int errors;
 	size_t i;
 
 	for (i = 0; i < size; i++) {
-		if (ptr[i] != seed) {
+		expected = seed ? seed : '\n';
+		if (ptr[i] != expected) {
 			fprintf(stderr,
 				"Failed validation: expected=%u, actual=%u, index=%lu\n",
-				seed, ptr[i], i);
+				expected, ptr[i], i);
 			errors++;
 			if (errors > 20)
 				error(1, 0, "validation failed.");
@@ -337,7 +373,8 @@ static int configure_flow_steering(struct sockaddr_in6 *server_sin)
 		server_addr = strrchr(server_addr, ':') + 1;
 	}
 
-	return run_command("sudo ethtool -N %s flow-type %s %s %s dst-ip %s %s %s dst-port %s queue %d >&2",
+	/* Try configure 5-tuple */
+	if (run_command("sudo ethtool -N %s flow-type %s %s %s dst-ip %s %s %s dst-port %s queue %d >&2",
 			   ifname,
 			   type,
 			   client_ip ? "src-ip" : "",
@@ -345,7 +382,17 @@ static int configure_flow_steering(struct sockaddr_in6 *server_sin)
 			   server_addr,
 			   client_ip ? "src-port" : "",
 			   client_ip ? port : "",
-			   port, start_queue);
+			   port, start_queue))
+		/* If that fails, try configure 3-tuple */
+		if (run_command("sudo ethtool -N %s flow-type %s dst-ip %s dst-port %s queue %d >&2",
+				ifname,
+				type,
+				server_addr,
+				port, start_queue))
+			/* If that fails, return error */
+			return -1;
+
+	return 0;
 }
 
 static int bind_rx_queue(unsigned int ifindex, unsigned int dmabuf_fd,
@@ -393,6 +440,49 @@ err_close:
 	return -1;
 }
 
+static int bind_tx_queue(unsigned int ifindex, unsigned int dmabuf_fd,
+			 struct ynl_sock **ys)
+{
+	struct netdev_bind_tx_req *req = NULL;
+	struct netdev_bind_tx_rsp *rsp = NULL;
+	struct ynl_error yerr;
+
+	*ys = ynl_sock_create(&ynl_netdev_family, &yerr);
+	if (!*ys) {
+		fprintf(stderr, "YNL: %s\n", yerr.msg);
+		return -1;
+	}
+
+	req = netdev_bind_tx_req_alloc();
+	netdev_bind_tx_req_set_ifindex(req, ifindex);
+	netdev_bind_tx_req_set_fd(req, dmabuf_fd);
+
+	rsp = netdev_bind_tx(*ys, req);
+	if (!rsp) {
+		perror("netdev_bind_tx");
+		goto err_close;
+	}
+
+	if (!rsp->_present.id) {
+		perror("id not present");
+		goto err_close;
+	}
+
+	fprintf(stderr, "got tx dmabuf id=%d\n", rsp->id);
+	tx_dmabuf_id = rsp->id;
+
+	netdev_bind_tx_req_free(req);
+	netdev_bind_tx_rsp_free(rsp);
+
+	return 0;
+
+err_close:
+	fprintf(stderr, "YNL failed: %s\n", (*ys)->err.msg);
+	netdev_bind_tx_req_free(req);
+	ynl_sock_destroy(*ys);
+	return -1;
+}
+
 static void enable_reuseaddr(int fd)
 {
 	int opt = 1;
@@ -447,10 +537,9 @@ static struct netdev_queue_id *create_queues(void)
 	return queues;
 }
 
-int do_server(struct memory_buffer *mem)
+static int do_server(struct memory_buffer *mem)
 {
 	char ctrl_data[sizeof(int) * 20000];
-	struct netdev_queue_id *queues;
 	size_t non_page_aligned_frags = 0;
 	struct sockaddr_in6 client_addr;
 	struct sockaddr_in6 server_sin;
@@ -674,13 +763,216 @@ void run_devmem_tests(void)
 	provider->free(mem);
 }
 
+static uint64_t gettimeofday_ms(void)
+{
+	struct timeval tv;
+
+	gettimeofday(&tv, NULL);
+	return (tv.tv_sec * 1000ULL) + (tv.tv_usec / 1000ULL);
+}
+
+static int do_poll(int fd)
+{
+	struct pollfd pfd;
+	int ret;
+
+	pfd.revents = 0;
+	pfd.fd = fd;
+
+	ret = poll(&pfd, 1, waittime_ms);
+	if (ret == -1)
+		error(1, errno, "poll");
+
+	return ret && (pfd.revents & POLLERR);
+}
+
+static void wait_compl(int fd)
+{
+	int64_t tstop = gettimeofday_ms() + waittime_ms;
+	char control[CMSG_SPACE(100)] = {};
+	struct sock_extended_err *serr;
+	struct msghdr msg = {};
+	struct cmsghdr *cm;
+	__u32 hi, lo;
+	int ret;
+
+	msg.msg_control = control;
+	msg.msg_controllen = sizeof(control);
+
+	while (gettimeofday_ms() < tstop) {
+		if (!do_poll(fd))
+			continue;
+
+		ret = recvmsg(fd, &msg, MSG_ERRQUEUE);
+		if (ret < 0) {
+			if (errno == EAGAIN)
+				continue;
+			error(1, errno, "recvmsg(MSG_ERRQUEUE)");
+			return;
+		}
+		if (msg.msg_flags & MSG_CTRUNC)
+			error(1, 0, "MSG_CTRUNC\n");
+
+		for (cm = CMSG_FIRSTHDR(&msg); cm; cm = CMSG_NXTHDR(&msg, cm)) {
+			if (cm->cmsg_level != SOL_IP &&
+			    cm->cmsg_level != SOL_IPV6)
+				continue;
+			if (cm->cmsg_level == SOL_IP &&
+			    cm->cmsg_type != IP_RECVERR)
+				continue;
+			if (cm->cmsg_level == SOL_IPV6 &&
+			    cm->cmsg_type != IPV6_RECVERR)
+				continue;
+
+			serr = (void *)CMSG_DATA(cm);
+			if (serr->ee_origin != SO_EE_ORIGIN_ZEROCOPY)
+				error(1, 0, "wrong origin %u", serr->ee_origin);
+			if (serr->ee_errno != 0)
+				error(1, 0, "wrong errno %d", serr->ee_errno);
+
+			hi = serr->ee_data;
+			lo = serr->ee_info;
+
+			fprintf(stderr, "tx complete [%d,%d]\n", lo, hi);
+			return;
+		}
+	}
+
+	error(1, 0, "did not receive tx completion");
+}
+
+static int do_client(struct memory_buffer *mem)
+{
+	char ctrl_data[CMSG_SPACE(sizeof(__u32))];
+	struct sockaddr_in6 server_sin;
+	struct sockaddr_in6 client_sin;
+	struct ynl_sock *ys = NULL;
+	struct iovec iov[MAX_IOV];
+	struct msghdr msg = {};
+	ssize_t line_size = 0;
+	struct cmsghdr *cmsg;
+	char *line = NULL;
+	unsigned long mid;
+	size_t len = 0;
+	int socket_fd;
+	__u32 ddmabuf;
+	int opt = 1;
+	int ret;
+
+	ret = parse_address(server_ip, atoi(port), &server_sin);
+	if (ret < 0)
+		error(1, 0, "parse server address");
+
+	socket_fd = socket(AF_INET6, SOCK_STREAM, 0);
+	if (socket_fd < 0)
+		error(1, socket_fd, "create socket");
+
+	enable_reuseaddr(socket_fd);
+
+	ret = setsockopt(socket_fd, SOL_SOCKET, SO_BINDTODEVICE, ifname,
+			 strlen(ifname) + 1);
+	if (ret)
+		error(1, errno, "bindtodevice");
+
+	if (bind_tx_queue(ifindex, mem->fd, &ys))
+		error(1, 0, "Failed to bind\n");
+
+	if (client_ip) {
+		ret = parse_address(client_ip, atoi(port), &client_sin);
+		if (ret < 0)
+			error(1, 0, "parse client address");
+
+		ret = bind(socket_fd, &client_sin, sizeof(client_sin));
+		if (ret)
+			error(1, errno, "bind");
+	}
+
+	ret = setsockopt(socket_fd, SOL_SOCKET, SO_ZEROCOPY, &opt, sizeof(opt));
+	if (ret)
+		error(1, errno, "set sock opt");
+
+	fprintf(stderr, "Connect to %s %d (via %s)\n", server_ip,
+		ntohs(server_sin.sin6_port), ifname);
+
+	ret = connect(socket_fd, &server_sin, sizeof(server_sin));
+	if (ret)
+		error(1, errno, "connect");
+
+	while (1) {
+		free(line);
+		line = NULL;
+		line_size = getline(&line, &len, stdin);
+
+		if (line_size < 0)
+			break;
+
+		if (max_chunk) {
+			msg.msg_iovlen =
+				(line_size + max_chunk - 1) / max_chunk;
+			if (msg.msg_iovlen > MAX_IOV)
+				error(1, 0,
+				      "can't partition %zd bytes into maximum of %d chunks",
+				      line_size, MAX_IOV);
+
+			for (int i = 0; i < msg.msg_iovlen; i++) {
+				iov[i].iov_base = (void *)(i * max_chunk);
+				iov[i].iov_len = max_chunk;
+			}
+
+			iov[msg.msg_iovlen - 1].iov_len =
+				line_size - (msg.msg_iovlen - 1) * max_chunk;
+		} else {
+			iov[0].iov_base = 0;
+			iov[0].iov_len = line_size;
+			msg.msg_iovlen = 1;
+		}
+
+		msg.msg_iov = iov;
+		provider->memcpy_to_device(mem, 0, line, line_size);
+
+		msg.msg_control = ctrl_data;
+		msg.msg_controllen = sizeof(ctrl_data);
+
+		cmsg = CMSG_FIRSTHDR(&msg);
+		cmsg->cmsg_level = SOL_SOCKET;
+		cmsg->cmsg_type = SCM_DEVMEM_DMABUF;
+		cmsg->cmsg_len = CMSG_LEN(sizeof(__u32));
+
+		ddmabuf = tx_dmabuf_id;
+
+		*((__u32 *)CMSG_DATA(cmsg)) = ddmabuf;
+
+		ret = sendmsg(socket_fd, &msg, MSG_ZEROCOPY);
+		if (ret < 0)
+			error(1, errno, "Failed sendmsg");
+
+		fprintf(stderr, "sendmsg_ret=%d\n", ret);
+
+		if (ret != line_size)
+			error(1, errno, "Did not send all bytes %d vs %zd", ret,
+			      line_size);
+
+		wait_compl(socket_fd);
+	}
+
+	fprintf(stderr, "%s: tx ok\n", TEST_PREFIX);
+
+	free(line);
+	close(socket_fd);
+
+	if (ys)
+		ynl_sock_destroy(ys);
+
+	return 0;
+}
+
 int main(int argc, char *argv[])
 {
 	struct memory_buffer *mem;
 	int is_server = 0, opt;
 	int ret;
 
-	while ((opt = getopt(argc, argv, "ls:c:p:v:q:t:f:")) != -1) {
+	while ((opt = getopt(argc, argv, "ls:c:p:v:q:t:f:z:")) != -1) {
 		switch (opt) {
 		case 'l':
 			is_server = 1;
@@ -706,6 +998,9 @@ int main(int argc, char *argv[])
 		case 'f':
 			ifname = optarg;
 			break;
+		case 'z':
+			max_chunk = atoi(optarg);
+			break;
 		case '?':
 			fprintf(stderr, "unknown option: %c\n", optopt);
 			break;
@@ -717,6 +1012,8 @@ int main(int argc, char *argv[])
 
 	ifindex = if_nametoindex(ifname);
 
+	fprintf(stderr, "using ifindex=%u\n", ifindex);
+
 	if (!server_ip && !client_ip) {
 		if (start_queue < 0 && num_queues < 0) {
 			num_queues = rxq_num(ifindex);
@@ -767,7 +1064,7 @@ int main(int argc, char *argv[])
 		error(1, 0, "Missing -p argument\n");
 
 	mem = provider->alloc(getpagesize() * NUM_PAGES);
-	ret = is_server ? do_server(mem) : 1;
+	ret = is_server ? do_server(mem) : do_client(mem);
 	provider->free(mem);
 
 	return ret;
diff --git a/tools/testing/selftests/drivers/net/hw/nic_link_layer.py b/tools/testing/selftests/drivers/net/hw/nic_link_layer.py
deleted file mode 100644
index efd921180532..000000000000
--- a/tools/testing/selftests/drivers/net/hw/nic_link_layer.py
+++ /dev/null
@@ -1,113 +0,0 @@
-#!/usr/bin/env python3
-# SPDX-License-Identifier: GPL-2.0
-
-#Introduction:
-#This file has basic link layer tests for generic NIC drivers.
-#The test comprises of auto-negotiation, speed and duplex checks.
-#
-#Setup:
-#Connect the DUT PC with NIC card to partner pc back via ethernet medium of your choice(RJ45, T1)
-#
-#        DUT PC                                              Partner PC
-#┌───────────────────────┐                         ┌──────────────────────────┐
-#│                       │                         │                          │
-#│                       │                         │                          │
-#│           ┌───────────┐                         │                          │
-#│           │DUT NIC    │         Eth             │                          │
-#│           │Interface ─┼─────────────────────────┼─    any eth Interface    │
-#│           └───────────┘                         │                          │
-#│                       │                         │                          │
-#│                       │                         │                          │
-#└───────────────────────┘                         └──────────────────────────┘
-#
-#Configurations:
-#Required minimum ethtool version is 6.10 (supports json)
-#Default values:
-#time_delay = 8 #time taken to wait for transitions to happen, in seconds.
-
-import time
-import argparse
-from lib.py import ksft_run, ksft_exit, ksft_pr, ksft_eq
-from lib.py import KsftFailEx, KsftSkipEx
-from lib.py import NetDrvEpEnv
-from lib.py import LinkConfig
-
-def _pre_test_checks(cfg: object, link_config: LinkConfig) -> None:
-    if link_config.partner_netif is None:
-        KsftSkipEx("Partner interface is not available")
-    if not link_config.check_autoneg_supported() or not link_config.check_autoneg_supported(remote=True):
-        KsftSkipEx(f"Auto-negotiation not supported for interface {cfg.ifname} or {link_config.partner_netif}")
-    if not link_config.verify_link_up():
-        raise KsftSkipEx(f"Link state of interface {cfg.ifname} is DOWN")
-
-def verify_autonegotiation(cfg: object, expected_state: str, link_config: LinkConfig) -> None:
-    if not link_config.verify_link_up():
-        raise KsftSkipEx(f"Link state of interface {cfg.ifname} is DOWN")
-    """Verifying the autonegotiation state in partner"""
-    partner_autoneg_output = link_config.get_ethtool_field("auto-negotiation", remote=True)
-    if partner_autoneg_output is None:
-        KsftSkipEx(f"Auto-negotiation state not available for interface {link_config.partner_netif}")
-    partner_autoneg_state = "on" if partner_autoneg_output is True else "off"
-
-    ksft_eq(partner_autoneg_state, expected_state)
-
-    """Verifying the autonegotiation state of local"""
-    autoneg_output = link_config.get_ethtool_field("auto-negotiation")
-    if autoneg_output is None:
-        KsftSkipEx(f"Auto-negotiation state not available for interface {cfg.ifname}")
-    actual_state = "on" if autoneg_output is True else "off"
-
-    ksft_eq(actual_state, expected_state)
-
-    """Verifying the link establishment"""
-    link_available = link_config.get_ethtool_field("link-detected")
-    if link_available is None:
-        KsftSkipEx(f"Link status not available for interface {cfg.ifname}")
-    if link_available != True:
-        raise KsftSkipEx("Link not established at interface {cfg.ifname} after changing auto-negotiation")
-
-def test_autonegotiation(cfg: object, link_config: LinkConfig, time_delay: int) -> None:
-    _pre_test_checks(cfg, link_config)
-    for state in ["off", "on"]:
-        if not link_config.set_autonegotiation_state(state, remote=True):
-            raise KsftSkipEx(f"Unable to set auto-negotiation state for interface {link_config.partner_netif}")
-        if not link_config.set_autonegotiation_state(state):
-            raise KsftSkipEx(f"Unable to set auto-negotiation state for interface {cfg.ifname}")
-        time.sleep(time_delay)
-        verify_autonegotiation(cfg, state, link_config)
-
-def test_network_speed(cfg: object, link_config: LinkConfig, time_delay: int) -> None:
-    _pre_test_checks(cfg, link_config)
-    common_link_modes = link_config.common_link_modes
-    if not common_link_modes:
-        KsftSkipEx("No common link modes exist")
-    speeds, duplex_modes = link_config.get_speed_duplex_values(common_link_modes)
-
-    if speeds and duplex_modes and len(speeds) == len(duplex_modes):
-        for idx in range(len(speeds)):
-            speed = speeds[idx]
-            duplex = duplex_modes[idx]
-            if not link_config.set_speed_and_duplex(speed, duplex):
-                raise KsftFailEx(f"Unable to set speed and duplex parameters for {cfg.ifname}")
-            time.sleep(time_delay)
-            if not link_config.verify_speed_and_duplex(speed, duplex):
-                raise KsftSkipEx(f"Error occurred while verifying speed and duplex states for interface {cfg.ifname}")
-    else:
-        if not speeds or not duplex_modes:
-            KsftSkipEx(f"No supported speeds or duplex modes found for interface {cfg.ifname}")
-        else:
-            KsftSkipEx("Mismatch in the number of speeds and duplex modes")
-
-def main() -> None:
-    parser = argparse.ArgumentParser(description="Run basic link layer tests for NIC driver")
-    parser.add_argument('--time-delay', type=int, default=8, help='Time taken to wait for transitions to happen(in seconds). Default is 8 seconds.')
-    args = parser.parse_args()
-    time_delay = args.time_delay
-    with NetDrvEpEnv(__file__, nsim_test=False) as cfg:
-        link_config = LinkConfig(cfg)
-        ksft_run(globs=globals(), case_pfx={"test_"}, args=(cfg, link_config, time_delay,))
-        link_config.reset_interface()
-    ksft_exit()
-
-if __name__ == "__main__":
-    main()
diff --git a/tools/testing/selftests/drivers/net/hw/nic_performance.py b/tools/testing/selftests/drivers/net/hw/nic_performance.py
deleted file mode 100644
index 201403b76ea3..000000000000
--- a/tools/testing/selftests/drivers/net/hw/nic_performance.py
+++ /dev/null
@@ -1,137 +0,0 @@
-#!/usr/bin/env python3
-# SPDX-License-Identifier: GPL-2.0
-
-#Introduction:
-#This file has basic performance test for generic NIC drivers.
-#The test comprises of throughput check for TCP and UDP streams.
-#
-#Setup:
-#Connect the DUT PC with NIC card to partner pc back via ethernet medium of your choice(RJ45, T1)
-#
-#        DUT PC                                              Partner PC
-#┌───────────────────────┐                         ┌──────────────────────────┐
-#│                       │                         │                          │
-#│                       │                         │                          │
-#│           ┌───────────┐                         │                          │
-#│           │DUT NIC    │         Eth             │                          │
-#│           │Interface ─┼─────────────────────────┼─    any eth Interface    │
-#│           └───────────┘                         │                          │
-#│                       │                         │                          │
-#│                       │                         │                          │
-#└───────────────────────┘                         └──────────────────────────┘
-#
-#Configurations:
-#To prevent interruptions, Add ethtool, ip to the sudoers list in remote PC and get the ssh key from remote.
-#Required minimum ethtool version is 6.10
-#Change the below configuration based on your hw needs.
-# """Default values"""
-#time_delay = 8 #time taken to wait for transitions to happen, in seconds.
-#test_duration = 10  #performance test duration for the throughput check, in seconds.
-#send_throughput_threshold = 80 #percentage of send throughput required to pass the check
-#receive_throughput_threshold = 50 #percentage of receive throughput required to pass the check
-
-import time
-import json
-import argparse
-from lib.py import ksft_run, ksft_exit, ksft_pr, ksft_true
-from lib.py import KsftFailEx, KsftSkipEx, GenerateTraffic
-from lib.py import NetDrvEpEnv, bkg, wait_port_listen
-from lib.py import cmd
-from lib.py import LinkConfig
-
-class TestConfig:
-    def __init__(self, time_delay: int, test_duration: int, send_throughput_threshold: int, receive_throughput_threshold: int) -> None:
-        self.time_delay = time_delay
-        self.test_duration = test_duration
-        self.send_throughput_threshold = send_throughput_threshold
-        self.receive_throughput_threshold = receive_throughput_threshold
-
-def _pre_test_checks(cfg: object, link_config: LinkConfig) -> None:
-    if not link_config.verify_link_up():
-        KsftSkipEx(f"Link state of interface {cfg.ifname} is DOWN")
-    common_link_modes = link_config.common_link_modes
-    if common_link_modes is None:
-        KsftSkipEx("No common link modes found")
-    if link_config.partner_netif == None:
-        KsftSkipEx("Partner interface is not available")
-    if link_config.check_autoneg_supported():
-        KsftSkipEx("Auto-negotiation not supported by local")
-    if link_config.check_autoneg_supported(remote=True):
-        KsftSkipEx("Auto-negotiation not supported by remote")
-    cfg.require_cmd("iperf3", remote=True)
-
-def check_throughput(cfg: object, link_config: LinkConfig, test_config: TestConfig, protocol: str, traffic: GenerateTraffic) -> None:
-    common_link_modes = link_config.common_link_modes
-    speeds, duplex_modes = link_config.get_speed_duplex_values(common_link_modes)
-    """Test duration in seconds"""
-    duration = test_config.test_duration
-
-    ksft_pr(f"{protocol} test")
-    test_type = "-u" if protocol == "UDP" else ""
-
-    send_throughput = []
-    receive_throughput = []
-    for idx in range(0, len(speeds)):
-        if link_config.set_speed_and_duplex(speeds[idx], duplex_modes[idx]) == False:
-            raise KsftFailEx(f"Not able to set speed and duplex parameters for {cfg.ifname}")
-        time.sleep(test_config.time_delay)
-        if not link_config.verify_link_up():
-            raise KsftSkipEx(f"Link state of interface {cfg.ifname} is DOWN")
-
-        send_command=f"{test_type} -b 0 -t {duration} --json"
-        receive_command=f"{test_type} -b 0 -t {duration} --reverse --json"
-
-        send_result = traffic.run_remote_test(cfg, command=send_command)
-        if send_result.ret != 0:
-            raise KsftSkipEx("Error occurred during data transmit: {send_result.stdout}")
-
-        send_output = send_result.stdout
-        send_data = json.loads(send_output)
-
-        """Convert throughput to Mbps"""
-        send_throughput.append(round(send_data['end']['sum_sent']['bits_per_second'] / 1e6, 2))
-        ksft_pr(f"{protocol}: Send throughput: {send_throughput[idx]} Mbps")
-
-        receive_result = traffic.run_remote_test(cfg, command=receive_command)
-        if receive_result.ret != 0:
-            raise KsftSkipEx("Error occurred during data receive: {receive_result.stdout}")
-
-        receive_output = receive_result.stdout
-        receive_data = json.loads(receive_output)
-
-        """Convert throughput to Mbps"""
-        receive_throughput.append(round(receive_data['end']['sum_received']['bits_per_second'] / 1e6, 2))
-        ksft_pr(f"{protocol}: Receive throughput: {receive_throughput[idx]} Mbps")
-
-    """Check whether throughput is not below the threshold (default values set at start)"""
-    for idx in range(0, len(speeds)):
-        send_threshold = float(speeds[idx]) * float(test_config.send_throughput_threshold / 100)
-        receive_threshold = float(speeds[idx]) * float(test_config.receive_throughput_threshold / 100)
-        ksft_true(send_throughput[idx] >= send_threshold, f"{protocol}: Send throughput is below threshold for {speeds[idx]} Mbps in {duplex_modes[idx]} duplex")
-        ksft_true(receive_throughput[idx] >= receive_threshold, f"{protocol}: Receive throughput is below threshold for {speeds[idx]} Mbps in {duplex_modes[idx]} duplex")
-
-def test_tcp_throughput(cfg: object, link_config: LinkConfig, test_config: TestConfig, traffic: GenerateTraffic) -> None:
-    _pre_test_checks(cfg, link_config)
-    check_throughput(cfg, link_config, test_config, 'TCP', traffic)
-
-def test_udp_throughput(cfg: object, link_config: LinkConfig, test_config: TestConfig, traffic: GenerateTraffic) -> None:
-    _pre_test_checks(cfg, link_config)
-    check_throughput(cfg, link_config, test_config, 'UDP', traffic)
-
-def main() -> None:
-    parser = argparse.ArgumentParser(description="Run basic performance test for NIC driver")
-    parser.add_argument('--time-delay', type=int, default=8, help='Time taken to wait for transitions to happen(in seconds). Default is 8 seconds.')
-    parser.add_argument('--test-duration', type=int, default=10, help='Performance test duration for the throughput check, in seconds. Default is 10 seconds.')
-    parser.add_argument('--stt', type=int, default=80, help='Send throughput Threshold: Percentage of send throughput upon actual throughput required to pass the throughput check (in percentage). Default is 80.')
-    parser.add_argument('--rtt', type=int, default=50, help='Receive throughput Threshold: Percentage of receive throughput upon actual throughput required to pass the throughput check (in percentage). Default is 50.')
-    args=parser.parse_args()
-    test_config = TestConfig(args.time_delay, args.test_duration, args.stt, args.rtt)
-    with NetDrvEpEnv(__file__, nsim_test=False) as cfg:
-        traffic = GenerateTraffic(cfg)
-        link_config = LinkConfig(cfg)
-        ksft_run(globs=globals(), case_pfx={"test_"}, args=(cfg, link_config, test_config, traffic,  ))
-        link_config.reset_interface()
-    ksft_exit()
-
-if __name__ == "__main__":
-    main()
diff --git a/tools/testing/selftests/drivers/net/hw/rss_input_xfrm.py b/tools/testing/selftests/drivers/net/hw/rss_input_xfrm.py
index 53bb08cc29ec..f439c434ba36 100755
--- a/tools/testing/selftests/drivers/net/hw/rss_input_xfrm.py
+++ b/tools/testing/selftests/drivers/net/hw/rss_input_xfrm.py
@@ -32,6 +32,11 @@ def test_rss_input_xfrm(cfg, ipver):
     if multiprocessing.cpu_count() < 2:
         raise KsftSkipEx("Need at least two CPUs to test symmetric RSS hash")
 
+    cfg.require_cmd("socat", remote=True)
+
+    if not hasattr(socket, "SO_INCOMING_CPU"):
+        raise KsftSkipEx("socket.SO_INCOMING_CPU was added in Python 3.11")
+
     input_xfrm = cfg.ethnl.rss_get(
         {'header': {'dev-name': cfg.ifname}}).get('input_xfrm')
 
diff --git a/tools/testing/selftests/drivers/net/hw/xsk_reconfig.py b/tools/testing/selftests/drivers/net/hw/xsk_reconfig.py
new file mode 100755
index 000000000000..d19d1d518208
--- /dev/null
+++ b/tools/testing/selftests/drivers/net/hw/xsk_reconfig.py
@@ -0,0 +1,60 @@
+#!/usr/bin/env python3
+# SPDX-License-Identifier: GPL-2.0
+
+# This is intended to be run on a virtio-net guest interface.
+# The test binds the XDP socket to the interface without setting
+# the fill ring to trigger delayed refill_work. This helps to
+# make it easier to reproduce the deadlock when XDP program,
+# XDP socket bind/unbind, rx ring resize race with refill_work on
+# the buggy kernel.
+#
+# The Qemu command to setup virtio-net
+# -netdev tap,id=hostnet1,vhost=on,script=no,downscript=no
+# -device virtio-net-pci,netdev=hostnet1,iommu_platform=on,disable-legacy=on
+
+from lib.py import ksft_exit, ksft_run
+from lib.py import KsftSkipEx, KsftFailEx
+from lib.py import NetDrvEnv
+from lib.py import bkg, ip, cmd, ethtool
+import time
+
+def _get_rx_ring_entries(cfg):
+    output = ethtool(f"-g {cfg.ifname}", json=True)
+    return output[0]["rx"]
+
+def setup_xsk(cfg, xdp_queue_id = 0) -> bkg:
+    # Probe for support
+    xdp = cmd(f'{cfg.net_lib_dir / "xdp_helper"} - -', fail=False)
+    if xdp.ret == 255:
+        raise KsftSkipEx('AF_XDP unsupported')
+    elif xdp.ret > 0:
+        raise KsftFailEx('unable to create AF_XDP socket')
+
+    try:
+        return bkg(f'{cfg.net_lib_dir / "xdp_helper"} {cfg.ifindex} ' \
+                   '{xdp_queue_id} -z', ksft_wait=3)
+    except:
+        raise KsftSkipEx('Failed to bind XDP socket in zerocopy.\n' \
+                         'Please consider adding iommu_platform=on ' \
+                         'when setting up virtio-net-pci')
+
+def check_xdp_bind(cfg):
+    with setup_xsk(cfg):
+        ip(f"link set dev %s xdp obj %s sec xdp" %
+           (cfg.ifname, cfg.net_lib_dir / "xdp_dummy.bpf.o"))
+        ip(f"link set dev %s xdp off" % cfg.ifname)
+
+def check_rx_resize(cfg):
+    with setup_xsk(cfg):
+        rx_ring = _get_rx_ring_entries(cfg)
+        ethtool(f"-G %s rx %d" % (cfg.ifname, rx_ring // 2))
+        ethtool(f"-G %s rx %d" % (cfg.ifname, rx_ring))
+
+def main():
+    with NetDrvEnv(__file__, nsim_test=False) as cfg:
+        ksft_run([check_xdp_bind, check_rx_resize],
+                 args=(cfg, ))
+    ksft_exit()
+
+if __name__ == "__main__":
+    main()
diff --git a/tools/testing/selftests/drivers/net/lib/py/env.py b/tools/testing/selftests/drivers/net/lib/py/env.py
index ad5ff645183a..3bccddf8cbc5 100644
--- a/tools/testing/selftests/drivers/net/lib/py/env.py
+++ b/tools/testing/selftests/drivers/net/lib/py/env.py
@@ -12,7 +12,7 @@ from .remote import Remote
 
 class NetDrvEnvBase:
     """
-    Base class for a NIC / host envirnoments
+    Base class for a NIC / host environments
 
     Attributes:
       test_dir: Path to the source directory of the test
diff --git a/tools/testing/selftests/drivers/net/lib/py/load.py b/tools/testing/selftests/drivers/net/lib/py/load.py
index da5af2c680fa..d9c10613ae67 100644
--- a/tools/testing/selftests/drivers/net/lib/py/load.py
+++ b/tools/testing/selftests/drivers/net/lib/py/load.py
@@ -2,7 +2,7 @@
 
 import time
 
-from lib.py import ksft_pr, cmd, ip, rand_port, wait_port_listen, bkg
+from lib.py import ksft_pr, cmd, ip, rand_port, wait_port_listen
 
 class GenerateTraffic:
     def __init__(self, env, port=None):
@@ -23,24 +23,6 @@ class GenerateTraffic:
             self.stop(verbose=True)
             raise Exception("iperf3 traffic did not ramp up")
 
-    def run_remote_test(self, env: object, port=None, command=None):
-        if port is None:
-            port = rand_port()
-        try:
-            server_cmd = f"iperf3 -s 1 -p {port} --one-off"
-            with bkg(server_cmd, host=env.remote):
-                #iperf3 opens TCP connection as default in server
-                #-u to be specified in client command for UDP
-                wait_port_listen(port, host=env.remote)
-        except Exception as e:
-            raise Exception(f"Unexpected error occurred while running server command: {e}")
-        try:
-            client_cmd = f"iperf3 -c {env.remote_addr} -p {port} {command}"
-            proc = cmd(client_cmd)
-            return proc
-        except Exception as e:
-            raise Exception(f"Unexpected error occurred while running client command: {e}")
-
     def _wait_pkts(self, pkt_cnt=None, pps=None):
         """
         Wait until we've seen pkt_cnt or until traffic ramps up to pps.
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 3c96b022954d..29b01b8e2215 100644
--- a/tools/testing/selftests/drivers/net/lib/sh/lib_netcons.sh
+++ b/tools/testing/selftests/drivers/net/lib/sh/lib_netcons.sh
@@ -33,7 +33,6 @@ NSIM_DEV_SYS_NEW="/sys/bus/netdevsim/new_device"
 
 # Used to create and delete namespaces
 source "${LIBDIR}"/../../../../net/lib.sh
-source "${LIBDIR}"/../../../../net/net_helper.sh
 
 # Create netdevsim interfaces
 create_ifaces() {
diff --git a/tools/testing/selftests/drivers/net/napi_id.py b/tools/testing/selftests/drivers/net/napi_id.py
new file mode 100755
index 000000000000..356bac46ba04
--- /dev/null
+++ b/tools/testing/selftests/drivers/net/napi_id.py
@@ -0,0 +1,23 @@
+#!/usr/bin/env python3
+# SPDX-License-Identifier: GPL-2.0
+
+from lib.py import ksft_run, ksft_exit
+from lib.py import ksft_eq, NetDrvEpEnv
+from lib.py import bkg, cmd, rand_port, NetNSEnter
+
+def test_napi_id(cfg) -> None:
+    port = rand_port()
+    listen_cmd = f"{cfg.test_dir}/napi_id_helper {cfg.addr_v['4']} {port}"
+
+    with bkg(listen_cmd, ksft_wait=3) as server:
+        cmd(f"echo a | socat - TCP:{cfg.addr_v['4']}:{port}", host=cfg.remote, shell=True)
+
+    ksft_eq(0, server.ret)
+
+def main() -> None:
+    with NetDrvEpEnv(__file__) as cfg:
+        ksft_run([test_napi_id], args=(cfg,))
+    ksft_exit()
+
+if __name__ == "__main__":
+    main()
diff --git a/tools/testing/selftests/drivers/net/napi_id_helper.c b/tools/testing/selftests/drivers/net/napi_id_helper.c
new file mode 100644
index 000000000000..eecd610c2109
--- /dev/null
+++ b/tools/testing/selftests/drivers/net/napi_id_helper.c
@@ -0,0 +1,83 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <errno.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <unistd.h>
+#include <arpa/inet.h>
+#include <sys/socket.h>
+
+#include "../../net/lib/ksft.h"
+
+int main(int argc, char *argv[])
+{
+	struct sockaddr_in address;
+	unsigned int napi_id;
+	unsigned int port;
+	socklen_t optlen;
+	char buf[1024];
+	int opt = 1;
+	int server;
+	int client;
+	int ret;
+
+	server = socket(AF_INET, SOCK_STREAM, IPPROTO_TCP);
+	if (server < 0) {
+		perror("socket creation failed");
+		if (errno == EAFNOSUPPORT)
+			return -1;
+		return 1;
+	}
+
+	port = atoi(argv[2]);
+
+	if (setsockopt(server, SOL_SOCKET, SO_REUSEADDR, &opt, sizeof(opt))) {
+		perror("setsockopt");
+		return 1;
+	}
+
+	address.sin_family = AF_INET;
+	inet_pton(AF_INET, argv[1], &address.sin_addr);
+	address.sin_port = htons(port);
+
+	if (bind(server, (struct sockaddr *)&address, sizeof(address)) < 0) {
+		perror("bind failed");
+		return 1;
+	}
+
+	if (listen(server, 1) < 0) {
+		perror("listen");
+		return 1;
+	}
+
+	ksft_ready();
+
+	client = accept(server, NULL, 0);
+	if (client < 0) {
+		perror("accept");
+		return 1;
+	}
+
+	optlen = sizeof(napi_id);
+	ret = getsockopt(client, SOL_SOCKET, SO_INCOMING_NAPI_ID, &napi_id,
+			 &optlen);
+	if (ret != 0) {
+		perror("getsockopt");
+		return 1;
+	}
+
+	read(client, buf, 1024);
+
+	ksft_wait();
+
+	if (napi_id == 0) {
+		fprintf(stderr, "napi ID is 0\n");
+		return 1;
+	}
+
+	close(client);
+	close(server);
+
+	return 0;
+}
diff --git a/tools/testing/selftests/drivers/net/netdevsim/peer.sh b/tools/testing/selftests/drivers/net/netdevsim/peer.sh
index aed62d9e6c0a..1bb46ec435d4 100755
--- a/tools/testing/selftests/drivers/net/netdevsim/peer.sh
+++ b/tools/testing/selftests/drivers/net/netdevsim/peer.sh
@@ -1,7 +1,7 @@
 #!/bin/bash
 # SPDX-License-Identifier: GPL-2.0-only
 
-source ../../../net/net_helper.sh
+source ../../../net/lib.sh
 
 NSIM_DEV_1_ID=$((256 + RANDOM % 256))
 NSIM_DEV_1_SYS=/sys/bus/netdevsim/devices/netdevsim$NSIM_DEV_1_ID
diff --git a/tools/testing/selftests/drivers/net/ping.py b/tools/testing/selftests/drivers/net/ping.py
index af8df2313a3b..e0f114612c1a 100755
--- a/tools/testing/selftests/drivers/net/ping.py
+++ b/tools/testing/selftests/drivers/net/ping.py
@@ -50,6 +50,16 @@ def _test_tcp(cfg) -> None:
         cmd(f"echo {test_string} | socat -t 2 -u STDIN TCP:{cfg.remote_baddr}:{port}", shell=True)
     ksft_eq(nc.stdout.strip(), test_string)
 
+def _schedule_checksum_reset(cfg, netnl) -> None:
+    features = ethtool(f"-k {cfg.ifname}", json=True)
+    setting = ""
+    for side in ["tx", "rx"]:
+        f = features[0][side + "-checksumming"]
+        if not f["fixed"]:
+            setting += " " + side
+            setting += " " + ("on" if f["requested"] or f["active"] else "off")
+    defer(ethtool, f" -K {cfg.ifname} " + setting)
+
 def _set_offload_checksum(cfg, netnl, on) -> None:
     try:
         ethtool(f" -K {cfg.ifname} rx {on} tx {on} ")
@@ -139,6 +149,7 @@ def set_interface_init(cfg) -> None:
 def test_default_v4(cfg, netnl) -> None:
     cfg.require_ipver("4")
 
+    _schedule_checksum_reset(cfg, netnl)
     _set_offload_checksum(cfg, netnl, "off")
     _test_v4(cfg)
     _test_tcp(cfg)
@@ -149,6 +160,7 @@ def test_default_v4(cfg, netnl) -> None:
 def test_default_v6(cfg, netnl) -> None:
     cfg.require_ipver("6")
 
+    _schedule_checksum_reset(cfg, netnl)
     _set_offload_checksum(cfg, netnl, "off")
     _test_v6(cfg)
     _test_tcp(cfg)
@@ -157,6 +169,7 @@ def test_default_v6(cfg, netnl) -> None:
     _test_tcp(cfg)
 
 def test_xdp_generic_sb(cfg, netnl) -> None:
+    _schedule_checksum_reset(cfg, netnl)
     _set_xdp_generic_sb_on(cfg)
     _set_offload_checksum(cfg, netnl, "off")
     _test_v4(cfg)
@@ -168,6 +181,7 @@ def test_xdp_generic_sb(cfg, netnl) -> None:
     _test_tcp(cfg)
 
 def test_xdp_generic_mb(cfg, netnl) -> None:
+    _schedule_checksum_reset(cfg, netnl)
     _set_xdp_generic_mb_on(cfg)
     _set_offload_checksum(cfg, netnl, "off")
     _test_v4(cfg)
@@ -179,6 +193,7 @@ def test_xdp_generic_mb(cfg, netnl) -> None:
     _test_tcp(cfg)
 
 def test_xdp_native_sb(cfg, netnl) -> None:
+    _schedule_checksum_reset(cfg, netnl)
     _set_xdp_native_sb_on(cfg)
     _set_offload_checksum(cfg, netnl, "off")
     _test_v4(cfg)
@@ -190,6 +205,7 @@ def test_xdp_native_sb(cfg, netnl) -> None:
     _test_tcp(cfg)
 
 def test_xdp_native_mb(cfg, netnl) -> None:
+    _schedule_checksum_reset(cfg, netnl)
     _set_xdp_native_mb_on(cfg)
     _set_offload_checksum(cfg, netnl, "off")
     _test_v4(cfg)
diff --git a/tools/testing/selftests/drivers/net/queues.py b/tools/testing/selftests/drivers/net/queues.py
index 06abd3f233e1..236005290a33 100755
--- a/tools/testing/selftests/drivers/net/queues.py
+++ b/tools/testing/selftests/drivers/net/queues.py
@@ -26,13 +26,13 @@ def nl_get_queues(cfg, nl, qtype='rx'):
 
 def check_xsk(cfg, nl, xdp_queue_id=0) -> None:
     # Probe for support
-    xdp = cmd(f'{cfg.test_dir / "xdp_helper"} - -', fail=False)
+    xdp = cmd(f'{cfg.net_lib_dir / "xdp_helper"} - -', fail=False)
     if xdp.ret == 255:
         raise KsftSkipEx('AF_XDP unsupported')
     elif xdp.ret > 0:
         raise KsftFailEx('unable to create AF_XDP socket')
 
-    with bkg(f'{cfg.test_dir / "xdp_helper"} {cfg.ifindex} {xdp_queue_id}',
+    with bkg(f'{cfg.net_lib_dir / "xdp_helper"} {cfg.ifindex} {xdp_queue_id}',
              ksft_wait=3):
 
         rx = tx = False
diff --git a/tools/testing/selftests/drivers/net/team/Makefile b/tools/testing/selftests/drivers/net/team/Makefile
index 2d5a76d99181..eaf6938f100e 100644
--- a/tools/testing/selftests/drivers/net/team/Makefile
+++ b/tools/testing/selftests/drivers/net/team/Makefile
@@ -1,7 +1,7 @@
 # SPDX-License-Identifier: GPL-2.0
 # Makefile for net selftests
 
-TEST_PROGS := dev_addr_lists.sh
+TEST_PROGS := dev_addr_lists.sh propagation.sh
 
 TEST_INCLUDES := \
 	../bonding/lag_lib.sh \
diff --git a/tools/testing/selftests/drivers/net/team/config b/tools/testing/selftests/drivers/net/team/config
index b5e3a3aad4bf..636b3525b679 100644
--- a/tools/testing/selftests/drivers/net/team/config
+++ b/tools/testing/selftests/drivers/net/team/config
@@ -1,5 +1,6 @@
 CONFIG_DUMMY=y
 CONFIG_IPV6=y
 CONFIG_MACVLAN=y
+CONFIG_NETDEVSIM=m
 CONFIG_NET_TEAM=y
 CONFIG_NET_TEAM_MODE_LOADBALANCE=y
diff --git a/tools/testing/selftests/drivers/net/team/propagation.sh b/tools/testing/selftests/drivers/net/team/propagation.sh
new file mode 100755
index 000000000000..4bea75b79878
--- /dev/null
+++ b/tools/testing/selftests/drivers/net/team/propagation.sh
@@ -0,0 +1,80 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+
+set -e
+
+NSIM_LRO_ID=$((256 + RANDOM % 256))
+NSIM_LRO_SYS=/sys/bus/netdevsim/devices/netdevsim$NSIM_LRO_ID
+
+NSIM_DEV_SYS_NEW=/sys/bus/netdevsim/new_device
+NSIM_DEV_SYS_DEL=/sys/bus/netdevsim/del_device
+
+cleanup()
+{
+	set +e
+	ip link del dummyteam &>/dev/null
+	ip link del team0 &>/dev/null
+	echo $NSIM_LRO_ID > $NSIM_DEV_SYS_DEL
+	modprobe -r netdevsim
+}
+
+# Trigger LRO propagation to the lower.
+# https://lore.kernel.org/netdev/aBvOpkIoxcr9PfDg@mini-arch/
+team_lro()
+{
+	# using netdevsim because it supports NETIF_F_LRO
+	NSIM_LRO_NAME=$(find $NSIM_LRO_SYS/net -maxdepth 1 -type d ! \
+		-path $NSIM_LRO_SYS/net -exec basename {} \;)
+
+	ip link add name team0 type team
+	ip link set $NSIM_LRO_NAME down
+	ip link set dev $NSIM_LRO_NAME master team0
+	ip link set team0 up
+	ethtool -K team0 large-receive-offload off
+
+	ip link del team0
+}
+
+# Trigger promisc propagation to the lower during IFLA_MASTER.
+# https://lore.kernel.org/netdev/20250506032328.3003050-1-sdf@fomichev.me/
+team_promisc()
+{
+	ip link add name dummyteam type dummy
+	ip link add name team0 type team
+	ip link set dummyteam down
+	ip link set team0 promisc on
+	ip link set dev dummyteam master team0
+	ip link set team0 up
+
+	ip link del team0
+	ip link del dummyteam
+}
+
+# Trigger promisc propagation to the lower via netif_change_flags (aka
+# ndo_change_rx_flags).
+# https://lore.kernel.org/netdev/20250514220319.3505158-1-stfomichev@gmail.com/
+team_change_flags()
+{
+	ip link add name dummyteam type dummy
+	ip link add name team0 type team
+	ip link set dummyteam down
+	ip link set dev dummyteam master team0
+	ip link set team0 up
+	ip link set team0 promisc on
+
+	# Make sure we can add more L2 addresses without any issues.
+	ip link add link team0 address 00:00:00:00:00:01 team0.1 type macvlan
+	ip link set team0.1 up
+
+	ip link del team0.1
+	ip link del team0
+	ip link del dummyteam
+}
+
+trap cleanup EXIT
+modprobe netdevsim || :
+echo $NSIM_LRO_ID > $NSIM_DEV_SYS_NEW
+udevadm settle
+team_lro
+team_promisc
+team_change_flags
diff --git a/tools/testing/selftests/nci/nci_dev.c b/tools/testing/selftests/nci/nci_dev.c
index 1562aa7d60b0..6dec59d64083 100644
--- a/tools/testing/selftests/nci/nci_dev.c
+++ b/tools/testing/selftests/nci/nci_dev.c
@@ -1,6 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0-only
 /*
- * Copyright (C) 2021 Samsung Electrnoics
+ * Copyright (C) 2021 Samsung Electronics
  * Bongsu Jeon <bongsu.jeon@samsung.com>
  *
  * Test code for nci
diff --git a/tools/testing/selftests/net/Makefile b/tools/testing/selftests/net/Makefile
index 70a38f485d4d..ea84b88bcb30 100644
--- a/tools/testing/selftests/net/Makefile
+++ b/tools/testing/selftests/net/Makefile
@@ -115,7 +115,7 @@ YNL_GEN_FILES := busy_poller netlink-dumps
 TEST_GEN_FILES += $(YNL_GEN_FILES)
 
 TEST_FILES := settings
-TEST_FILES += in_netns.sh lib.sh net_helper.sh setup_loopback.sh setup_veth.sh
+TEST_FILES += in_netns.sh lib.sh setup_loopback.sh setup_veth.sh
 
 TEST_GEN_FILES += $(patsubst %.c,%.o,$(wildcard *.bpf.c))
 
diff --git a/tools/testing/selftests/net/af_unix/scm_rights.c b/tools/testing/selftests/net/af_unix/scm_rights.c
index d66336256580..8b015f16c03d 100644
--- a/tools/testing/selftests/net/af_unix/scm_rights.c
+++ b/tools/testing/selftests/net/af_unix/scm_rights.c
@@ -23,6 +23,7 @@ FIXTURE_VARIANT(scm_rights)
 	int type;
 	int flags;
 	bool test_listener;
+	bool disabled;
 };
 
 FIXTURE_VARIANT_ADD(scm_rights, dgram)
@@ -31,6 +32,16 @@ FIXTURE_VARIANT_ADD(scm_rights, dgram)
 	.type = SOCK_DGRAM,
 	.flags = 0,
 	.test_listener = false,
+	.disabled = false,
+};
+
+FIXTURE_VARIANT_ADD(scm_rights, dgram_disabled)
+{
+	.name = "UNIX ",
+	.type = SOCK_DGRAM,
+	.flags = 0,
+	.test_listener = false,
+	.disabled = true,
 };
 
 FIXTURE_VARIANT_ADD(scm_rights, stream)
@@ -39,6 +50,16 @@ FIXTURE_VARIANT_ADD(scm_rights, stream)
 	.type = SOCK_STREAM,
 	.flags = 0,
 	.test_listener = false,
+	.disabled = false,
+};
+
+FIXTURE_VARIANT_ADD(scm_rights, stream_disabled)
+{
+	.name = "UNIX-STREAM ",
+	.type = SOCK_STREAM,
+	.flags = 0,
+	.test_listener = false,
+	.disabled = true,
 };
 
 FIXTURE_VARIANT_ADD(scm_rights, stream_oob)
@@ -47,6 +68,16 @@ FIXTURE_VARIANT_ADD(scm_rights, stream_oob)
 	.type = SOCK_STREAM,
 	.flags = MSG_OOB,
 	.test_listener = false,
+	.disabled = false,
+};
+
+FIXTURE_VARIANT_ADD(scm_rights, stream_oob_disabled)
+{
+	.name = "UNIX-STREAM ",
+	.type = SOCK_STREAM,
+	.flags = MSG_OOB,
+	.test_listener = false,
+	.disabled = true,
 };
 
 FIXTURE_VARIANT_ADD(scm_rights, stream_listener)
@@ -55,6 +86,16 @@ FIXTURE_VARIANT_ADD(scm_rights, stream_listener)
 	.type = SOCK_STREAM,
 	.flags = 0,
 	.test_listener = true,
+	.disabled = false,
+};
+
+FIXTURE_VARIANT_ADD(scm_rights, stream_listener_disabled)
+{
+	.name = "UNIX-STREAM ",
+	.type = SOCK_STREAM,
+	.flags = 0,
+	.test_listener = true,
+	.disabled = true,
 };
 
 FIXTURE_VARIANT_ADD(scm_rights, stream_listener_oob)
@@ -63,6 +104,16 @@ FIXTURE_VARIANT_ADD(scm_rights, stream_listener_oob)
 	.type = SOCK_STREAM,
 	.flags = MSG_OOB,
 	.test_listener = true,
+	.disabled = false,
+};
+
+FIXTURE_VARIANT_ADD(scm_rights, stream_listener_oob_disabled)
+{
+	.name = "UNIX-STREAM ",
+	.type = SOCK_STREAM,
+	.flags = MSG_OOB,
+	.test_listener = true,
+	.disabled = true,
 };
 
 static int count_sockets(struct __test_metadata *_metadata,
@@ -105,6 +156,9 @@ FIXTURE_SETUP(scm_rights)
 	ret = unshare(CLONE_NEWNET);
 	ASSERT_EQ(0, ret);
 
+	if (variant->disabled)
+		return;
+
 	ret = count_sockets(_metadata, variant);
 	ASSERT_EQ(0, ret);
 }
@@ -113,6 +167,9 @@ FIXTURE_TEARDOWN(scm_rights)
 {
 	int ret;
 
+	if (variant->disabled)
+		return;
+
 	sleep(1);
 
 	ret = count_sockets(_metadata, variant);
@@ -121,6 +178,7 @@ FIXTURE_TEARDOWN(scm_rights)
 
 static void create_listeners(struct __test_metadata *_metadata,
 			     FIXTURE_DATA(scm_rights) *self,
+			     const FIXTURE_VARIANT(scm_rights) *variant,
 			     int n)
 {
 	struct sockaddr_un addr = {
@@ -140,6 +198,12 @@ static void create_listeners(struct __test_metadata *_metadata,
 		ret = listen(self->fd[i], -1);
 		ASSERT_EQ(0, ret);
 
+		if (variant->disabled) {
+			ret = setsockopt(self->fd[i], SOL_SOCKET, SO_PASSRIGHTS,
+					 &(int){0}, sizeof(int));
+			ASSERT_EQ(0, ret);
+		}
+
 		addrlen = sizeof(addr);
 		ret = getsockname(self->fd[i], (struct sockaddr *)&addr, &addrlen);
 		ASSERT_EQ(0, ret);
@@ -164,6 +228,12 @@ static void create_socketpairs(struct __test_metadata *_metadata,
 	for (i = 0; i < n * 2; i += 2) {
 		ret = socketpair(AF_UNIX, variant->type, 0, self->fd + i);
 		ASSERT_EQ(0, ret);
+
+		if (variant->disabled) {
+			ret = setsockopt(self->fd[i], SOL_SOCKET, SO_PASSRIGHTS,
+					 &(int){0}, sizeof(int));
+			ASSERT_EQ(0, ret);
+		}
 	}
 }
 
@@ -175,7 +245,7 @@ static void __create_sockets(struct __test_metadata *_metadata,
 	ASSERT_LE(n * 2, sizeof(self->fd) / sizeof(self->fd[0]));
 
 	if (variant->test_listener)
-		create_listeners(_metadata, self, n);
+		create_listeners(_metadata, self, variant, n);
 	else
 		create_socketpairs(_metadata, self, variant, n);
 }
@@ -230,7 +300,13 @@ void __send_fd(struct __test_metadata *_metadata,
 	int ret;
 
 	ret = sendmsg(self->fd[receiver * 2 + 1], &msg, variant->flags);
-	ASSERT_EQ(MSGLEN, ret);
+
+	if (variant->disabled) {
+		ASSERT_EQ(-1, ret);
+		ASSERT_EQ(-EPERM, -errno);
+	} else {
+		ASSERT_EQ(MSGLEN, ret);
+	}
 }
 
 #define create_sockets(n)					\
diff --git a/tools/testing/selftests/net/bareudp.sh b/tools/testing/selftests/net/bareudp.sh
index f366cadbc5e8..4046131e7888 100755
--- a/tools/testing/selftests/net/bareudp.sh
+++ b/tools/testing/selftests/net/bareudp.sh
@@ -106,26 +106,16 @@
 # |                                                                       |
 # +-----------------------------------------------------------------------+
 
+. ./lib.sh
+
 ERR=4 # Return 4 by default, which is the SKIP code for kselftest
 PING6="ping"
 PAUSE_ON_FAIL="no"
 
-readonly NS0=$(mktemp -u ns0-XXXXXXXX)
-readonly NS1=$(mktemp -u ns1-XXXXXXXX)
-readonly NS2=$(mktemp -u ns2-XXXXXXXX)
-readonly NS3=$(mktemp -u ns3-XXXXXXXX)
-
 # Exit the script after having removed the network namespaces it created
-#
-# Parameters:
-#
-#   * The list of network namespaces to delete before exiting.
-#
 exit_cleanup()
 {
-	for ns in "$@"; do
-		ip netns delete "${ns}" 2>/dev/null || true
-	done
+	cleanup_all_ns
 
 	if [ "${ERR}" -eq 4 ]; then
 		echo "Error: Setting up the testing environment failed." >&2
@@ -140,17 +130,7 @@ exit_cleanup()
 # namespaces created by this script are deleted.
 create_namespaces()
 {
-	ip netns add "${NS0}" || exit_cleanup
-	ip netns add "${NS1}" || exit_cleanup "${NS0}"
-	ip netns add "${NS2}" || exit_cleanup "${NS0}" "${NS1}"
-	ip netns add "${NS3}" || exit_cleanup "${NS0}" "${NS1}" "${NS2}"
-}
-
-# The trap function handler
-#
-exit_cleanup_all()
-{
-	exit_cleanup "${NS0}" "${NS1}" "${NS2}" "${NS3}"
+	setup_ns NS0 NS1 NS2 NS3 || exit_cleanup
 }
 
 # Configure a network interface using a host route
@@ -188,10 +168,6 @@ iface_config()
 #
 setup_underlay()
 {
-	for ns in "${NS0}" "${NS1}" "${NS2}" "${NS3}"; do
-		ip -netns "${ns}" link set dev lo up
-	done;
-
 	ip link add name veth01 netns "${NS0}" type veth peer name veth10 netns "${NS1}"
 	ip link add name veth12 netns "${NS1}" type veth peer name veth21 netns "${NS2}"
 	ip link add name veth23 netns "${NS2}" type veth peer name veth32 netns "${NS3}"
@@ -234,14 +210,6 @@ setup_overlay_ipv4()
 	ip netns exec "${NS2}" sysctl -qw net.ipv4.ip_forward=1
 	ip -netns "${NS1}" route add 192.0.2.100/32 via 192.0.2.10
 	ip -netns "${NS2}" route add 192.0.2.103/32 via 192.0.2.33
-
-	# The intermediate namespaces don't have routes for the reverse path,
-	# as it will be handled by tc. So we need to ensure that rp_filter is
-	# not going to block the traffic.
-	ip netns exec "${NS1}" sysctl -qw net.ipv4.conf.all.rp_filter=0
-	ip netns exec "${NS2}" sysctl -qw net.ipv4.conf.all.rp_filter=0
-	ip netns exec "${NS1}" sysctl -qw net.ipv4.conf.default.rp_filter=0
-	ip netns exec "${NS2}" sysctl -qw net.ipv4.conf.default.rp_filter=0
 }
 
 setup_overlay_ipv6()
@@ -521,13 +489,10 @@ done
 
 check_features
 
-# Create namespaces before setting up the exit trap.
-# Otherwise, exit_cleanup_all() could delete namespaces that were not created
-# by this script.
-create_namespaces
-
 set -e
-trap exit_cleanup_all EXIT
+trap exit_cleanup EXIT
+
+create_namespaces
 
 setup_underlay
 setup_overlay_ipv4
diff --git a/tools/testing/selftests/net/busy_poll_test.sh b/tools/testing/selftests/net/busy_poll_test.sh
index 7db292ec4884..7d2d40812074 100755
--- a/tools/testing/selftests/net/busy_poll_test.sh
+++ b/tools/testing/selftests/net/busy_poll_test.sh
@@ -1,6 +1,6 @@
 #!/bin/bash
 # SPDX-License-Identifier: GPL-2.0
-source net_helper.sh
+source lib.sh
 
 NSIM_SV_ID=$((256 + RANDOM % 256))
 NSIM_SV_SYS=/sys/bus/netdevsim/devices/netdevsim$NSIM_SV_ID
diff --git a/tools/testing/selftests/net/can/.gitignore b/tools/testing/selftests/net/can/.gitignore
new file mode 100644
index 000000000000..764a53fc837f
--- /dev/null
+++ b/tools/testing/selftests/net/can/.gitignore
@@ -0,0 +1,2 @@
+# SPDX-License-Identifier: GPL-2.0-only
+test_raw_filter
diff --git a/tools/testing/selftests/net/can/Makefile b/tools/testing/selftests/net/can/Makefile
new file mode 100644
index 000000000000..5b82e60a03e7
--- /dev/null
+++ b/tools/testing/selftests/net/can/Makefile
@@ -0,0 +1,11 @@
+# SPDX-License-Identifier: GPL-2.0
+
+top_srcdir = ../../../../..
+
+CFLAGS += -Wall -Wl,--no-as-needed -O2 -g -I$(top_srcdir)/usr/include $(KHDR_INCLUDES)
+
+TEST_PROGS := test_raw_filter.sh
+
+TEST_GEN_FILES := test_raw_filter
+
+include ../../lib.mk
diff --git a/tools/testing/selftests/net/can/test_raw_filter.c b/tools/testing/selftests/net/can/test_raw_filter.c
new file mode 100644
index 000000000000..4101c36390fd
--- /dev/null
+++ b/tools/testing/selftests/net/can/test_raw_filter.c
@@ -0,0 +1,405 @@
+// SPDX-License-Identifier: (GPL-2.0-only OR BSD-3-Clause)
+/*
+ * Copyright (c) 2011 Volkswagen Group Electronic Research
+ * All rights reserved.
+ */
+
+#include <stdio.h>
+#include <stdlib.h>
+#include <unistd.h>
+#include <string.h>
+
+#include <sys/types.h>
+#include <sys/socket.h>
+#include <sys/ioctl.h>
+#include <sys/time.h>
+#include <net/if.h>
+#include <linux/if.h>
+
+#include <linux/can.h>
+#include <linux/can/raw.h>
+
+#include "../../kselftest_harness.h"
+
+#define ID 0x123
+
+char CANIF[IFNAMSIZ];
+
+static int send_can_frames(int sock, int testcase)
+{
+	struct can_frame frame;
+
+	frame.can_dlc = 1;
+	frame.data[0] = testcase;
+
+	frame.can_id = ID;
+	if (write(sock, &frame, sizeof(frame)) < 0)
+		goto write_err;
+
+	frame.can_id = (ID | CAN_RTR_FLAG);
+	if (write(sock, &frame, sizeof(frame)) < 0)
+		goto write_err;
+
+	frame.can_id = (ID | CAN_EFF_FLAG);
+	if (write(sock, &frame, sizeof(frame)) < 0)
+		goto write_err;
+
+	frame.can_id = (ID | CAN_EFF_FLAG | CAN_RTR_FLAG);
+	if (write(sock, &frame, sizeof(frame)) < 0)
+		goto write_err;
+
+	return 0;
+
+write_err:
+	perror("write");
+	return 1;
+}
+
+FIXTURE(can_filters) {
+	int sock;
+};
+
+FIXTURE_SETUP(can_filters)
+{
+	struct sockaddr_can addr;
+	struct ifreq ifr;
+	int recv_own_msgs = 1;
+	int s, ret;
+
+	s = socket(PF_CAN, SOCK_RAW, CAN_RAW);
+	ASSERT_GE(s, 0)
+		TH_LOG("failed to create CAN_RAW socket: %d", errno);
+
+	strncpy(ifr.ifr_name, CANIF, sizeof(ifr.ifr_name));
+	ret = ioctl(s, SIOCGIFINDEX, &ifr);
+	ASSERT_GE(ret, 0)
+		TH_LOG("failed SIOCGIFINDEX: %d", errno);
+
+	addr.can_family = AF_CAN;
+	addr.can_ifindex = ifr.ifr_ifindex;
+
+	setsockopt(s, SOL_CAN_RAW, CAN_RAW_RECV_OWN_MSGS,
+		   &recv_own_msgs, sizeof(recv_own_msgs));
+
+	ret = bind(s, (struct sockaddr *)&addr, sizeof(addr));
+	ASSERT_EQ(ret, 0)
+		TH_LOG("failed bind socket: %d", errno);
+
+	self->sock = s;
+}
+
+FIXTURE_TEARDOWN(can_filters)
+{
+	close(self->sock);
+}
+
+FIXTURE_VARIANT(can_filters) {
+	int testcase;
+	canid_t id;
+	canid_t mask;
+	int exp_num_rx;
+	canid_t exp_flags[];
+};
+
+/* Receive all frames when filtering for the ID in standard frame format */
+FIXTURE_VARIANT_ADD(can_filters, base) {
+	.testcase = 1,
+	.id = ID,
+	.mask = CAN_SFF_MASK,
+	.exp_num_rx = 4,
+	.exp_flags = {
+		0,
+		CAN_RTR_FLAG,
+		CAN_EFF_FLAG,
+		CAN_EFF_FLAG | CAN_RTR_FLAG,
+	},
+};
+
+/* Ignore EFF flag in filter ID if not covered by filter mask */
+FIXTURE_VARIANT_ADD(can_filters, base_eff) {
+	.testcase = 2,
+	.id = ID | CAN_EFF_FLAG,
+	.mask = CAN_SFF_MASK,
+	.exp_num_rx = 4,
+	.exp_flags = {
+		0,
+		CAN_RTR_FLAG,
+		CAN_EFF_FLAG,
+		CAN_EFF_FLAG | CAN_RTR_FLAG,
+	},
+};
+
+/* Ignore RTR flag in filter ID if not covered by filter mask */
+FIXTURE_VARIANT_ADD(can_filters, base_rtr) {
+	.testcase = 3,
+	.id = ID | CAN_RTR_FLAG,
+	.mask = CAN_SFF_MASK,
+	.exp_num_rx = 4,
+	.exp_flags = {
+		0,
+		CAN_RTR_FLAG,
+		CAN_EFF_FLAG,
+		CAN_EFF_FLAG | CAN_RTR_FLAG,
+	},
+};
+
+/* Ignore EFF and RTR flags in filter ID if not covered by filter mask */
+FIXTURE_VARIANT_ADD(can_filters, base_effrtr) {
+	.testcase = 4,
+	.id = ID | CAN_EFF_FLAG | CAN_RTR_FLAG,
+	.mask = CAN_SFF_MASK,
+	.exp_num_rx = 4,
+	.exp_flags = {
+		0,
+		CAN_RTR_FLAG,
+		CAN_EFF_FLAG,
+		CAN_EFF_FLAG | CAN_RTR_FLAG,
+	},
+};
+
+/* Receive only SFF frames when expecting no EFF flag */
+FIXTURE_VARIANT_ADD(can_filters, filter_eff) {
+	.testcase = 5,
+	.id = ID,
+	.mask = CAN_SFF_MASK | CAN_EFF_FLAG,
+	.exp_num_rx = 2,
+	.exp_flags = {
+		0,
+		CAN_RTR_FLAG,
+	},
+};
+
+/* Receive only EFF frames when filter id and filter mask include EFF flag */
+FIXTURE_VARIANT_ADD(can_filters, filter_eff_eff) {
+	.testcase = 6,
+	.id = ID | CAN_EFF_FLAG,
+	.mask = CAN_SFF_MASK | CAN_EFF_FLAG,
+	.exp_num_rx = 2,
+	.exp_flags = {
+		CAN_EFF_FLAG,
+		CAN_EFF_FLAG | CAN_RTR_FLAG,
+	},
+};
+
+/* Receive only SFF frames when expecting no EFF flag, ignoring RTR flag */
+FIXTURE_VARIANT_ADD(can_filters, filter_eff_rtr) {
+	.testcase = 7,
+	.id = ID | CAN_RTR_FLAG,
+	.mask = CAN_SFF_MASK | CAN_EFF_FLAG,
+	.exp_num_rx = 2,
+	.exp_flags = {
+		0,
+		CAN_RTR_FLAG,
+	},
+};
+
+/* Receive only EFF frames when filter id and filter mask include EFF flag,
+ * ignoring RTR flag
+ */
+FIXTURE_VARIANT_ADD(can_filters, filter_eff_effrtr) {
+	.testcase = 8,
+	.id = ID | CAN_EFF_FLAG | CAN_RTR_FLAG,
+	.mask = CAN_SFF_MASK | CAN_EFF_FLAG,
+	.exp_num_rx = 2,
+	.exp_flags = {
+		CAN_EFF_FLAG,
+		CAN_EFF_FLAG | CAN_RTR_FLAG,
+	},
+};
+
+/* Receive no remote frames when filtering for no RTR flag */
+FIXTURE_VARIANT_ADD(can_filters, filter_rtr) {
+	.testcase = 9,
+	.id = ID,
+	.mask = CAN_SFF_MASK | CAN_RTR_FLAG,
+	.exp_num_rx = 2,
+	.exp_flags = {
+		0,
+		CAN_EFF_FLAG,
+	},
+};
+
+/* Receive no remote frames when filtering for no RTR flag, ignoring EFF flag */
+FIXTURE_VARIANT_ADD(can_filters, filter_rtr_eff) {
+	.testcase = 10,
+	.id = ID | CAN_EFF_FLAG,
+	.mask = CAN_SFF_MASK | CAN_RTR_FLAG,
+	.exp_num_rx = 2,
+	.exp_flags = {
+		0,
+		CAN_EFF_FLAG,
+	},
+};
+
+/* Receive only remote frames when filter includes RTR flag */
+FIXTURE_VARIANT_ADD(can_filters, filter_rtr_rtr) {
+	.testcase = 11,
+	.id = ID | CAN_RTR_FLAG,
+	.mask = CAN_SFF_MASK | CAN_RTR_FLAG,
+	.exp_num_rx = 2,
+	.exp_flags = {
+		CAN_RTR_FLAG,
+		CAN_EFF_FLAG | CAN_RTR_FLAG,
+	},
+};
+
+/* Receive only remote frames when filter includes RTR flag, ignoring EFF
+ * flag
+ */
+FIXTURE_VARIANT_ADD(can_filters, filter_rtr_effrtr) {
+	.testcase = 12,
+	.id = ID | CAN_EFF_FLAG | CAN_RTR_FLAG,
+	.mask = CAN_SFF_MASK | CAN_RTR_FLAG,
+	.exp_num_rx = 2,
+	.exp_flags = {
+		CAN_RTR_FLAG,
+		CAN_EFF_FLAG | CAN_RTR_FLAG,
+	},
+};
+
+/* Receive only SFF data frame when filtering for no flags */
+FIXTURE_VARIANT_ADD(can_filters, filter_effrtr) {
+	.testcase = 13,
+	.id = ID,
+	.mask = CAN_SFF_MASK | CAN_EFF_FLAG | CAN_RTR_FLAG,
+	.exp_num_rx = 1,
+	.exp_flags = {
+		0,
+	},
+};
+
+/* Receive only EFF data frame when filtering for EFF but no RTR flag */
+FIXTURE_VARIANT_ADD(can_filters, filter_effrtr_eff) {
+	.testcase = 14,
+	.id = ID | CAN_EFF_FLAG,
+	.mask = CAN_SFF_MASK | CAN_EFF_FLAG | CAN_RTR_FLAG,
+	.exp_num_rx = 1,
+	.exp_flags = {
+		CAN_EFF_FLAG,
+	},
+};
+
+/* Receive only SFF remote frame when filtering for RTR but no EFF flag */
+FIXTURE_VARIANT_ADD(can_filters, filter_effrtr_rtr) {
+	.testcase = 15,
+	.id = ID | CAN_RTR_FLAG,
+	.mask = CAN_SFF_MASK | CAN_EFF_FLAG | CAN_RTR_FLAG,
+	.exp_num_rx = 1,
+	.exp_flags = {
+		CAN_RTR_FLAG,
+	},
+};
+
+/* Receive only EFF remote frame when filtering for EFF and RTR flag */
+FIXTURE_VARIANT_ADD(can_filters, filter_effrtr_effrtr) {
+	.testcase = 16,
+	.id = ID | CAN_EFF_FLAG | CAN_RTR_FLAG,
+	.mask = CAN_SFF_MASK | CAN_EFF_FLAG | CAN_RTR_FLAG,
+	.exp_num_rx = 1,
+	.exp_flags = {
+		CAN_EFF_FLAG | CAN_RTR_FLAG,
+	},
+};
+
+/* Receive only SFF data frame when filtering for no EFF flag and no RTR flag
+ * but based on EFF mask
+ */
+FIXTURE_VARIANT_ADD(can_filters, eff) {
+	.testcase = 17,
+	.id = ID,
+	.mask = CAN_EFF_MASK | CAN_EFF_FLAG | CAN_RTR_FLAG,
+	.exp_num_rx = 1,
+	.exp_flags = {
+		0,
+	},
+};
+
+/* Receive only EFF data frame when filtering for EFF flag and no RTR flag but
+ * based on EFF mask
+ */
+FIXTURE_VARIANT_ADD(can_filters, eff_eff) {
+	.testcase = 18,
+	.id = ID | CAN_EFF_FLAG,
+	.mask = CAN_EFF_MASK | CAN_EFF_FLAG | CAN_RTR_FLAG,
+	.exp_num_rx = 1,
+	.exp_flags = {
+		CAN_EFF_FLAG,
+	},
+};
+
+/* This test verifies that the raw CAN filters work, by checking if only frames
+ * with the expected set of flags are received. For each test case, the given
+ * filter (id and mask) is added and four CAN frames are sent with every
+ * combination of set/unset EFF/RTR flags.
+ */
+TEST_F(can_filters, test_filter)
+{
+	struct can_filter rfilter;
+	int ret;
+
+	rfilter.can_id = variant->id;
+	rfilter.can_mask = variant->mask;
+	setsockopt(self->sock, SOL_CAN_RAW, CAN_RAW_FILTER,
+		   &rfilter, sizeof(rfilter));
+
+	TH_LOG("filters: can_id = 0x%08X can_mask = 0x%08X",
+		rfilter.can_id, rfilter.can_mask);
+
+	ret = send_can_frames(self->sock, variant->testcase);
+	ASSERT_EQ(ret, 0)
+		TH_LOG("failed to send CAN frames");
+
+	for (int i = 0; i <= variant->exp_num_rx; i++) {
+		struct can_frame frame;
+		struct timeval tv = {
+			.tv_sec = 0,
+			.tv_usec = 50000, /* 50ms timeout */
+		};
+		fd_set rdfs;
+
+		FD_ZERO(&rdfs);
+		FD_SET(self->sock, &rdfs);
+
+		ret = select(self->sock + 1, &rdfs, NULL, NULL, &tv);
+		ASSERT_GE(ret, 0)
+			TH_LOG("failed select for frame %d, err: %d)", i, errno);
+
+		ret = FD_ISSET(self->sock, &rdfs);
+		if (i == variant->exp_num_rx) {
+			ASSERT_EQ(ret, 0)
+				TH_LOG("too many frames received");
+		} else {
+			ASSERT_NE(ret, 0)
+				TH_LOG("too few frames received");
+
+			ret = read(self->sock, &frame, sizeof(frame));
+			ASSERT_GE(ret, 0)
+				TH_LOG("failed to read frame %d, err: %d", i, errno);
+
+			TH_LOG("rx: can_id = 0x%08X rx = %d", frame.can_id, i);
+
+			ASSERT_EQ(ID, frame.can_id & CAN_SFF_MASK)
+				TH_LOG("received wrong can_id");
+			ASSERT_EQ(variant->testcase, frame.data[0])
+				TH_LOG("received wrong test case");
+
+			ASSERT_EQ(frame.can_id & ~CAN_ERR_MASK,
+				  variant->exp_flags[i])
+				TH_LOG("received unexpected flags");
+		}
+	}
+}
+
+int main(int argc, char **argv)
+{
+	char *ifname = getenv("CANIF");
+
+	if (!ifname) {
+		printf("CANIF environment variable must contain the test interface\n");
+		return KSFT_FAIL;
+	}
+
+	strncpy(CANIF, ifname, sizeof(CANIF) - 1);
+
+	return test_harness_run(argc, argv);
+}
diff --git a/tools/testing/selftests/net/can/test_raw_filter.sh b/tools/testing/selftests/net/can/test_raw_filter.sh
new file mode 100755
index 000000000000..276d6c06ac95
--- /dev/null
+++ b/tools/testing/selftests/net/can/test_raw_filter.sh
@@ -0,0 +1,45 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+
+ALL_TESTS="
+	test_raw_filter
+"
+
+net_dir=$(dirname $0)/..
+source $net_dir/lib.sh
+
+export CANIF=${CANIF:-"vcan0"}
+BITRATE=${BITRATE:-500000}
+
+setup()
+{
+	if [[ $CANIF == vcan* ]]; then
+		ip link add name $CANIF type vcan || exit $ksft_skip
+	else
+		ip link set dev $CANIF type can bitrate $BITRATE || exit $ksft_skip
+	fi
+	ip link set dev $CANIF up
+	pwd
+}
+
+cleanup()
+{
+	ip link set dev $CANIF down
+	if [[ $CANIF == vcan* ]]; then
+		ip link delete $CANIF
+	fi
+}
+
+test_raw_filter()
+{
+	./test_raw_filter
+	check_err $?
+	log_test "test_raw_filter"
+}
+
+trap cleanup EXIT
+setup
+
+tests_run
+
+exit $EXIT_STATUS
diff --git a/tools/testing/selftests/net/config b/tools/testing/selftests/net/config
index 130d532b7e67..3cfef5153823 100644
--- a/tools/testing/selftests/net/config
+++ b/tools/testing/selftests/net/config
@@ -33,7 +33,6 @@ CONFIG_NETFILTER_ADVANCED=y
 CONFIG_NF_CONNTRACK=m
 CONFIG_IPV6_MROUTE=y
 CONFIG_IPV6_SIT=y
-CONFIG_IP_DCCP=m
 CONFIG_NF_NAT=m
 CONFIG_IP6_NF_IPTABLES=m
 CONFIG_IP_NF_IPTABLES=m
diff --git a/tools/testing/selftests/net/fib_rule_tests.sh b/tools/testing/selftests/net/fib_rule_tests.sh
index c7cea556b416..5fbdd2a0b537 100755
--- a/tools/testing/selftests/net/fib_rule_tests.sh
+++ b/tools/testing/selftests/net/fib_rule_tests.sh
@@ -516,10 +516,7 @@ fib_rule4_test()
 	fib_rule4_test_match_n_redirect "$match" "$match" "$getnomatch" \
 		"oif redirect to table" "oif no redirect to table"
 
-	# Enable forwarding and disable rp_filter as all the addresses are in
-	# the same subnet and egress device == ingress device.
 	ip netns exec $testns sysctl -qw net.ipv4.ip_forward=1
-	ip netns exec $testns sysctl -qw net.ipv4.conf.$DEV.rp_filter=0
 	match="from $SRC_IP iif $DEV"
 	getnomatch="from $SRC_IP iif lo"
 	fib_rule4_test_match_n_redirect "$match" "$match" "$getnomatch" \
diff --git a/tools/testing/selftests/net/fib_tests.sh b/tools/testing/selftests/net/fib_tests.sh
index 3ea6f886a210..a94b73a53f72 100755
--- a/tools/testing/selftests/net/fib_tests.sh
+++ b/tools/testing/selftests/net/fib_tests.sh
@@ -11,7 +11,7 @@ TESTS="unregister down carrier nexthop suppress ipv6_notify ipv4_notify \
        ipv6_rt ipv4_rt ipv6_addr_metric ipv4_addr_metric ipv6_route_metrics \
        ipv4_route_metrics ipv4_route_v6_gw rp_filter ipv4_del_addr \
        ipv6_del_addr ipv4_mangle ipv6_mangle ipv4_bcast_neigh fib6_gc_test \
-       ipv4_mpath_list ipv6_mpath_list"
+       ipv4_mpath_list ipv6_mpath_list ipv4_mpath_balance ipv6_mpath_balance"
 
 VERBOSE=0
 PAUSE_ON_FAIL=no
@@ -1085,6 +1085,35 @@ route_setup()
 	set +e
 }
 
+forwarding_cleanup()
+{
+	cleanup_ns $ns3
+
+	route_cleanup
+}
+
+# extend route_setup with an ns3 reachable through ns2 over both devices
+forwarding_setup()
+{
+	forwarding_cleanup
+
+	route_setup
+
+	setup_ns ns3
+
+	ip link add veth5 netns $ns3 type veth peer name veth6 netns $ns2
+	ip -netns $ns3 link set veth5 up
+	ip -netns $ns2 link set veth6 up
+
+	ip -netns $ns3 -4 addr add dev veth5 172.16.105.1/24
+	ip -netns $ns2 -4 addr add dev veth6 172.16.105.2/24
+	ip -netns $ns3 -4 route add 172.16.100.0/22 via 172.16.105.2
+
+	ip -netns $ns3 -6 addr add dev veth5 2001:db8:105::1/64 nodad
+	ip -netns $ns2 -6 addr add dev veth6 2001:db8:105::2/64 nodad
+	ip -netns $ns3 -6 route add 2001:db8:101::/33 via 2001:db8:105::2
+}
+
 # assumption is that basic add of a single path route works
 # otherwise just adding an address on an interface is broken
 ipv6_rt_add()
@@ -2531,9 +2560,6 @@ ipv4_mpath_list_test()
 	run_cmd "ip -n $ns2 route add 203.0.113.0/24
 		nexthop via 172.16.201.2 nexthop via 172.16.202.2"
 	run_cmd "ip netns exec $ns2 sysctl -qw net.ipv4.fib_multipath_hash_policy=1"
-	run_cmd "ip netns exec $ns2 sysctl -qw net.ipv4.conf.veth2.rp_filter=0"
-	run_cmd "ip netns exec $ns2 sysctl -qw net.ipv4.conf.all.rp_filter=0"
-	run_cmd "ip netns exec $ns2 sysctl -qw net.ipv4.conf.default.rp_filter=0"
 	set +e
 
 	local dmac=$(ip -n $ns2 -j link show dev veth2 | jq -r '.[]["address"]')
@@ -2600,6 +2626,93 @@ ipv6_mpath_list_test()
 	route_cleanup
 }
 
+tc_set_flower_counter__saddr_syn() {
+	tc_set_flower_counter $1 $2 $3 "src_ip $4 ip_proto tcp tcp_flags 0x2"
+}
+
+ip_mpath_balance_dep_check()
+{
+	if [ ! -x "$(command -v socat)" ]; then
+		echo "socat command not found. Skipping test"
+		return 1
+	fi
+
+	if [ ! -x "$(command -v jq)" ]; then
+		echo "jq command not found. Skipping test"
+		return 1
+	fi
+}
+
+ip_mpath_balance() {
+	local -r ipver=$1
+	local -r daddr=$2
+	local -r num_conn=20
+
+	for i in $(seq 1 $num_conn); do
+		ip netns exec $ns3 socat $ipver TCP-LISTEN:8000 STDIO >/dev/null &
+		sleep 0.02
+		echo -n a | ip netns exec $ns1 socat $ipver STDIO TCP:$daddr:8000
+	done
+
+	local -r syn0="$(tc_get_flower_counter $ns1 veth1)"
+	local -r syn1="$(tc_get_flower_counter $ns1 veth3)"
+	local -r syns=$((syn0+syn1))
+
+	[ "$VERBOSE" = "1" ] && echo "multipath: syns seen: ($syn0,$syn1)"
+
+	[[ $syns -ge $num_conn ]] && [[ $syn0 -gt 0 ]] && [[ $syn1 -gt 0 ]]
+}
+
+ipv4_mpath_balance_test()
+{
+	echo
+	echo "IPv4 multipath load balance test"
+
+	ip_mpath_balance_dep_check || return 1
+	forwarding_setup
+
+	$IP route add 172.16.105.1 \
+		nexthop via 172.16.101.2 \
+		nexthop via 172.16.103.2
+
+	ip netns exec $ns1 \
+		sysctl -q -w net.ipv4.fib_multipath_hash_policy=1
+
+	tc_set_flower_counter__saddr_syn $ns1 4 veth1 172.16.101.1
+	tc_set_flower_counter__saddr_syn $ns1 4 veth3 172.16.103.1
+
+	ip_mpath_balance -4 172.16.105.1
+
+	log_test $? 0 "IPv4 multipath loadbalance"
+
+	forwarding_cleanup
+}
+
+ipv6_mpath_balance_test()
+{
+	echo
+	echo "IPv6 multipath load balance test"
+
+	ip_mpath_balance_dep_check || return 1
+	forwarding_setup
+
+	$IP route add 2001:db8:105::1\
+		nexthop via 2001:db8:101::2 \
+		nexthop via 2001:db8:103::2
+
+	ip netns exec $ns1 \
+		sysctl -q -w net.ipv6.fib_multipath_hash_policy=1
+
+	tc_set_flower_counter__saddr_syn $ns1 6 veth1 2001:db8:101::1
+	tc_set_flower_counter__saddr_syn $ns1 6 veth3 2001:db8:103::1
+
+	ip_mpath_balance -6 "[2001:db8:105::1]"
+
+	log_test $? 0 "IPv6 multipath loadbalance"
+
+	forwarding_cleanup
+}
+
 ################################################################################
 # usage
 
@@ -2683,6 +2796,8 @@ do
 	fib6_gc_test|ipv6_gc)		fib6_gc_test;;
 	ipv4_mpath_list)		ipv4_mpath_list_test;;
 	ipv6_mpath_list)		ipv6_mpath_list_test;;
+	ipv4_mpath_balance)		ipv4_mpath_balance_test;;
+	ipv6_mpath_balance)		ipv6_mpath_balance_test;;
 
 	help) echo "Test names: $TESTS"; exit 0;;
 	esac
diff --git a/tools/testing/selftests/net/forwarding/bridge_igmp.sh b/tools/testing/selftests/net/forwarding/bridge_igmp.sh
index e6a3e04fd83f..d4e7dd659354 100755
--- a/tools/testing/selftests/net/forwarding/bridge_igmp.sh
+++ b/tools/testing/selftests/net/forwarding/bridge_igmp.sh
@@ -1,10 +1,24 @@
 #!/bin/bash
 # SPDX-License-Identifier: GPL-2.0
 
-ALL_TESTS="v2reportleave_test v3include_test v3inc_allow_test v3inc_is_include_test \
-	   v3inc_is_exclude_test v3inc_to_exclude_test v3exc_allow_test v3exc_is_include_test \
-	   v3exc_is_exclude_test v3exc_to_exclude_test v3inc_block_test v3exc_block_test \
-	   v3exc_timeout_test v3star_ex_auto_add_test"
+ALL_TESTS="
+	v2reportleave_test
+	v3include_test
+	v3inc_allow_test
+	v3inc_is_include_test
+	v3inc_is_exclude_test
+	v3inc_to_exclude_test
+	v3exc_allow_test
+	v3exc_is_include_test
+	v3exc_is_exclude_test
+	v3exc_to_exclude_test
+	v3inc_block_test
+	v3exc_block_test
+	v3exc_timeout_test
+	v3star_ex_auto_add_test
+	v2per_vlan_snooping_port_stp_test
+	v2per_vlan_snooping_vlan_stp_test
+"
 NUM_NETIFS=4
 CHECK_TC="yes"
 TEST_GROUP="239.10.10.10"
@@ -554,6 +568,64 @@ v3star_ex_auto_add_test()
 	v3cleanup $swp2 $TEST_GROUP
 }
 
+v2per_vlan_snooping_stp_test()
+{
+	local is_port=$1
+
+	local msg="port"
+	[[ $is_port -ne 1 ]] && msg="vlan"
+
+	ip link set br0 up type bridge vlan_filtering 1 \
+					mcast_igmp_version 2 \
+					mcast_snooping 1 \
+					mcast_vlan_snooping 1 \
+					mcast_querier 1 \
+					mcast_stats_enabled 1
+	bridge vlan global set vid 1 dev br0 \
+					mcast_snooping 1 \
+					mcast_querier 1 \
+					mcast_query_interval 100 \
+					mcast_startup_query_count 0
+	[[ $is_port -eq 1 ]] && bridge link set dev $swp1 state 0
+	[[ $is_port -ne 1 ]] && bridge vlan set vid 1 dev $swp1 state 4
+	sleep 5
+	local tx_s=$(ip -j -p stats show dev $swp1 \
+			group xstats_slave subgroup bridge suite mcast \
+			| jq '.[]["multicast"]["igmp_queries"]["tx_v2"]')
+
+	[[ $is_port -eq 1 ]] && bridge link set dev $swp1 state 3
+	[[ $is_port -ne 1 ]] && bridge vlan set vid 1 dev $swp1 state 3
+	sleep 5
+	local tx_e=$(ip -j -p stats show dev $swp1 \
+			group xstats_slave subgroup bridge suite mcast \
+			| jq '.[]["multicast"]["igmp_queries"]["tx_v2"]')
+
+	RET=0
+	local tx=$(expr $tx_e - $tx_s)
+	test $tx -gt 0
+	check_err $? "No IGMP queries after STP state becomes forwarding"
+	log_test "per vlan snooping with $msg stp state change"
+
+	# restore settings
+	bridge vlan global set vid 1 dev br0 \
+					mcast_querier 0 \
+					mcast_query_interval 12500 \
+					mcast_startup_query_count 2
+	ip link set br0 up type bridge vlan_filtering 0 \
+					mcast_vlan_snooping 0 \
+					mcast_stats_enabled 0
+}
+
+v2per_vlan_snooping_port_stp_test()
+{
+	v2per_vlan_snooping_stp_test 1
+}
+
+v2per_vlan_snooping_vlan_stp_test()
+{
+	v2per_vlan_snooping_stp_test 0
+}
+
 trap cleanup EXIT
 
 setup_prepare
diff --git a/tools/testing/selftests/net/forwarding/bridge_mld.sh b/tools/testing/selftests/net/forwarding/bridge_mld.sh
index f84ab2e65754..4cacef5a813a 100755
--- a/tools/testing/selftests/net/forwarding/bridge_mld.sh
+++ b/tools/testing/selftests/net/forwarding/bridge_mld.sh
@@ -1,10 +1,23 @@
 #!/bin/bash
 # SPDX-License-Identifier: GPL-2.0
 
-ALL_TESTS="mldv2include_test mldv2inc_allow_test mldv2inc_is_include_test mldv2inc_is_exclude_test \
-	   mldv2inc_to_exclude_test mldv2exc_allow_test mldv2exc_is_include_test \
-	   mldv2exc_is_exclude_test mldv2exc_to_exclude_test mldv2inc_block_test \
-	   mldv2exc_block_test mldv2exc_timeout_test mldv2star_ex_auto_add_test"
+ALL_TESTS="
+	mldv2include_test
+	mldv2inc_allow_test
+	mldv2inc_is_include_test
+	mldv2inc_is_exclude_test
+	mldv2inc_to_exclude_test
+	mldv2exc_allow_test
+	mldv2exc_is_include_test
+	mldv2exc_is_exclude_test
+	mldv2exc_to_exclude_test
+	mldv2inc_block_test
+	mldv2exc_block_test
+	mldv2exc_timeout_test
+	mldv2star_ex_auto_add_test
+	mldv2per_vlan_snooping_port_stp_test
+	mldv2per_vlan_snooping_vlan_stp_test
+"
 NUM_NETIFS=4
 CHECK_TC="yes"
 TEST_GROUP="ff02::cc"
@@ -554,6 +567,66 @@ mldv2star_ex_auto_add_test()
 	mldv2cleanup $swp2
 }
 
+mldv2per_vlan_snooping_stp_test()
+{
+	local is_port=$1
+
+	local msg="port"
+	[[ $is_port -ne 1 ]] && msg="vlan"
+
+	ip link set br0 up type bridge vlan_filtering 1 \
+					mcast_mld_version 2 \
+					mcast_snooping 1 \
+					mcast_vlan_snooping 1 \
+					mcast_querier 1 \
+					mcast_stats_enabled 1
+	bridge vlan global set vid 1 dev br0 \
+					mcast_mld_version 2 \
+					mcast_snooping 1 \
+					mcast_querier 1 \
+					mcast_query_interval 100 \
+					mcast_startup_query_count 0
+
+	[[ $is_port -eq 1 ]] && bridge link set dev $swp1 state 0
+	[[ $is_port -ne 1 ]] && bridge vlan set vid 1 dev $swp1 state 4
+	sleep 5
+	local tx_s=$(ip -j -p stats show dev $swp1 \
+			group xstats_slave subgroup bridge suite mcast \
+			| jq '.[]["multicast"]["mld_queries"]["tx_v2"]')
+	[[ $is_port -eq 1 ]] && bridge link set dev $swp1 state 3
+	[[ $is_port -ne 1 ]] && bridge vlan set vid 1 dev $swp1 state 3
+	sleep 5
+	local tx_e=$(ip -j -p stats show dev $swp1 \
+			group xstats_slave subgroup bridge suite mcast \
+			| jq '.[]["multicast"]["mld_queries"]["tx_v2"]')
+
+	RET=0
+	local tx=$(expr $tx_e - $tx_s)
+	test $tx -gt 0
+	check_err $? "No MLD queries after STP state becomes forwarding"
+	log_test "per vlan snooping with $msg stp state change"
+
+	# restore settings
+	bridge vlan global set vid 1 dev br0 \
+					mcast_querier 0 \
+					mcast_query_interval 12500 \
+					mcast_startup_query_count 2 \
+					mcast_mld_version 1
+	ip link set br0 up type bridge vlan_filtering 0 \
+					mcast_vlan_snooping 0 \
+					mcast_stats_enabled 0
+}
+
+mldv2per_vlan_snooping_port_stp_test()
+{
+	mldv2per_vlan_snooping_stp_test 1
+}
+
+mldv2per_vlan_snooping_vlan_stp_test()
+{
+	mldv2per_vlan_snooping_stp_test 0
+}
+
 trap cleanup EXIT
 
 setup_prepare
diff --git a/tools/testing/selftests/net/forwarding/config b/tools/testing/selftests/net/forwarding/config
index 8d7a1a004b7c..18fd69d8d937 100644
--- a/tools/testing/selftests/net/forwarding/config
+++ b/tools/testing/selftests/net/forwarding/config
@@ -1,6 +1,7 @@
 CONFIG_BRIDGE=m
 CONFIG_VLAN_8021Q=m
 CONFIG_BRIDGE_VLAN_FILTERING=y
+CONFIG_BRIDGE_IGMP_SNOOPING=y
 CONFIG_NET_L3_MASTER_DEV=y
 CONFIG_IPV6_MULTIPLE_TABLES=y
 CONFIG_NET_VRF=m
diff --git a/tools/testing/selftests/net/icmp_redirect.sh b/tools/testing/selftests/net/icmp_redirect.sh
index d6f0e449c029..b13c89a99ecb 100755
--- a/tools/testing/selftests/net/icmp_redirect.sh
+++ b/tools/testing/selftests/net/icmp_redirect.sh
@@ -178,8 +178,6 @@ setup()
 		else
 			ip netns exec $ns sysctl -q -w net.ipv4.ip_forward=1
 			ip netns exec $ns sysctl -q -w net.ipv4.conf.all.send_redirects=1
-			ip netns exec $ns sysctl -q -w net.ipv4.conf.default.rp_filter=0
-			ip netns exec $ns sysctl -q -w net.ipv4.conf.all.rp_filter=0
 
 			ip netns exec $ns sysctl -q -w net.ipv6.conf.all.forwarding=1
 			ip netns exec $ns sysctl -q -w net.ipv6.route.mtu_expires=10
diff --git a/tools/testing/selftests/net/ipv6_route_update_soft_lockup.sh b/tools/testing/selftests/net/ipv6_route_update_soft_lockup.sh
index a6b2b1f9c641..c6866e42f95c 100755
--- a/tools/testing/selftests/net/ipv6_route_update_soft_lockup.sh
+++ b/tools/testing/selftests/net/ipv6_route_update_soft_lockup.sh
@@ -69,7 +69,6 @@
 # which can affect the conditions needed to trigger a soft lockup.
 
 source lib.sh
-source net_helper.sh
 
 TEST_DURATION=300
 ROUTING_TABLE_REFRESH_PERIOD=0.01
diff --git a/tools/testing/selftests/net/lib.sh b/tools/testing/selftests/net/lib.sh
index 701905eeff66..006fdadcc4b9 100644
--- a/tools/testing/selftests/net/lib.sh
+++ b/tools/testing/selftests/net/lib.sh
@@ -217,6 +217,8 @@ setup_ns()
 			return $ksft_skip
 		fi
 		ip -n "${!ns_name}" link set lo up
+		ip netns exec "${!ns_name}" sysctl -wq net.ipv4.conf.all.rp_filter=0
+		ip netns exec "${!ns_name}" sysctl -wq net.ipv4.conf.default.rp_filter=0
 		ns_list+=("${!ns_name}")
 	done
 	NS_LIST+=("${ns_list[@]}")
@@ -270,6 +272,30 @@ tc_rule_handle_stats_get()
 		  .options.actions[0].stats$selector"
 }
 
+# attach a qdisc with two children match/no-match and a flower filter to match
+tc_set_flower_counter() {
+	local -r ns=$1
+	local -r ipver=$2
+	local -r dev=$3
+	local -r flower_expr=$4
+
+	tc -n $ns qdisc add dev $dev root handle 1: prio bands 2 \
+			priomap 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
+
+	tc -n $ns qdisc add dev $dev parent 1:1 handle 11: pfifo
+	tc -n $ns qdisc add dev $dev parent 1:2 handle 12: pfifo
+
+	tc -n $ns filter add dev $dev parent 1: protocol ipv$ipver \
+			flower $flower_expr classid 1:2
+}
+
+tc_get_flower_counter() {
+	local -r ns=$1
+	local -r dev=$2
+
+	tc -n $ns -j -s qdisc show dev $dev handle 12: | jq .[0].packets
+}
+
 ret_set_ksft_status()
 {
 	local ksft_status=$1; shift
@@ -569,3 +595,24 @@ bridge_vlan_add()
 	bridge vlan add "$@"
 	defer bridge vlan del "$@"
 }
+
+wait_local_port_listen()
+{
+	local listener_ns="${1}"
+	local port="${2}"
+	local protocol="${3}"
+	local pattern
+	local i
+
+	pattern=":$(printf "%04X" "${port}") "
+
+	# for tcp protocol additionally check the socket state
+	[ ${protocol} = "tcp" ] && pattern="${pattern}0A"
+	for i in $(seq 10); do
+		if ip netns exec "${listener_ns}" awk '{print $2" "$4}' \
+		   /proc/net/"${protocol}"* | grep -q "${pattern}"; then
+			break
+		fi
+		sleep 0.1
+	done
+}
diff --git a/tools/testing/selftests/net/lib/.gitignore b/tools/testing/selftests/net/lib/.gitignore
index 1ebc6187f421..bbc97d6bf556 100644
--- a/tools/testing/selftests/net/lib/.gitignore
+++ b/tools/testing/selftests/net/lib/.gitignore
@@ -1,2 +1,3 @@
 # SPDX-License-Identifier: GPL-2.0-only
 csum
+xdp_helper
diff --git a/tools/testing/selftests/net/lib/Makefile b/tools/testing/selftests/net/lib/Makefile
index c22623b9a2a5..88c4bc461459 100644
--- a/tools/testing/selftests/net/lib/Makefile
+++ b/tools/testing/selftests/net/lib/Makefile
@@ -10,6 +10,7 @@ TEST_FILES += ../../../../net/ynl
 
 TEST_GEN_FILES += csum
 TEST_GEN_FILES += $(patsubst %.c,%.o,$(wildcard *.bpf.c))
+TEST_GEN_FILES += xdp_helper
 
 TEST_INCLUDES := $(wildcard py/*.py sh/*.sh)
 
diff --git a/tools/testing/selftests/net/lib/ksft.h b/tools/testing/selftests/net/lib/ksft.h
new file mode 100644
index 000000000000..17dc34a612c6
--- /dev/null
+++ b/tools/testing/selftests/net/lib/ksft.h
@@ -0,0 +1,56 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#if !defined(__NET_KSFT_H__)
+#define __NET_KSFT_H__
+
+#include <stdio.h>
+#include <stdlib.h>
+#include <unistd.h>
+
+static inline void ksft_ready(void)
+{
+	const char msg[7] = "ready\n";
+	char *env_str;
+	int fd;
+
+	env_str = getenv("KSFT_READY_FD");
+	if (env_str) {
+		fd = atoi(env_str);
+		if (!fd) {
+			fprintf(stderr, "invalid KSFT_READY_FD = '%s'\n",
+				env_str);
+			return;
+		}
+	} else {
+		fd = STDOUT_FILENO;
+	}
+
+	write(fd, msg, sizeof(msg));
+	if (fd != STDOUT_FILENO)
+		close(fd);
+}
+
+static inline void ksft_wait(void)
+{
+	char *env_str;
+	char byte;
+	int fd;
+
+	env_str = getenv("KSFT_WAIT_FD");
+	if (env_str) {
+		fd = atoi(env_str);
+		if (!fd) {
+			fprintf(stderr, "invalid KSFT_WAIT_FD = '%s'\n",
+				env_str);
+			return;
+		}
+	} else {
+		/* Not running in KSFT env, wait for input from STDIN instead */
+		fd = STDIN_FILENO;
+	}
+
+	read(fd, &byte, sizeof(byte));
+	if (fd != STDIN_FILENO)
+		close(fd);
+}
+
+#endif
diff --git a/tools/testing/selftests/net/lib/py/ksft.py b/tools/testing/selftests/net/lib/py/ksft.py
index 3cfad0fd4570..61287c203b6e 100644
--- a/tools/testing/selftests/net/lib/py/ksft.py
+++ b/tools/testing/selftests/net/lib/py/ksft.py
@@ -3,6 +3,7 @@
 import builtins
 import functools
 import inspect
+import signal
 import sys
 import time
 import traceback
@@ -26,6 +27,10 @@ class KsftXfailEx(Exception):
     pass
 
 
+class KsftTerminate(KeyboardInterrupt):
+    pass
+
+
 def ksft_pr(*objs, **kwargs):
     print("#", *objs, **kwargs)
 
@@ -193,6 +198,17 @@ def ksft_setup(env):
     return env
 
 
+def _ksft_intr(signum, frame):
+    # ksft runner.sh sends 2 SIGTERMs in a row on a timeout
+    # if we don't ignore the second one it will stop us from handling cleanup
+    global term_cnt
+    term_cnt += 1
+    if term_cnt == 1:
+        raise KsftTerminate()
+    else:
+        ksft_pr(f"Ignoring SIGTERM (cnt: {term_cnt}), already exiting...")
+
+
 def ksft_run(cases=None, globs=None, case_pfx=None, args=()):
     cases = cases or []
 
@@ -205,6 +221,10 @@ def ksft_run(cases=None, globs=None, case_pfx=None, args=()):
                     cases.append(value)
                     break
 
+    global term_cnt
+    term_cnt = 0
+    prev_sigterm = signal.signal(signal.SIGTERM, _ksft_intr)
+
     totals = {"pass": 0, "fail": 0, "skip": 0, "xfail": 0}
 
     print("TAP version 13")
@@ -233,7 +253,7 @@ def ksft_run(cases=None, globs=None, case_pfx=None, args=()):
             for line in tb.strip().split('\n'):
                 ksft_pr("Exception|", line)
             if stop:
-                ksft_pr("Stopping tests due to KeyboardInterrupt.")
+                ksft_pr(f"Stopping tests due to {type(e).__name__}.")
             KSFT_RESULT = False
             cnt_key = 'fail'
 
@@ -248,6 +268,8 @@ def ksft_run(cases=None, globs=None, case_pfx=None, args=()):
         if stop:
             break
 
+    signal.signal(signal.SIGTERM, prev_sigterm)
+
     print(
         f"# Totals: pass:{totals['pass']} fail:{totals['fail']} xfail:{totals['xfail']} xpass:0 skip:{totals['skip']} error:0"
     )
diff --git a/tools/testing/selftests/net/lib/py/ynl.py b/tools/testing/selftests/net/lib/py/ynl.py
index 8986c584cb37..6329ae805abf 100644
--- a/tools/testing/selftests/net/lib/py/ynl.py
+++ b/tools/testing/selftests/net/lib/py/ynl.py
@@ -39,12 +39,12 @@ class EthtoolFamily(YnlFamily):
 
 class RtnlFamily(YnlFamily):
     def __init__(self, recv_size=0):
-        super().__init__((SPEC_PATH / Path('rt_link.yaml')).as_posix(),
+        super().__init__((SPEC_PATH / Path('rt-link.yaml')).as_posix(),
                          schema='', recv_size=recv_size)
 
 class RtnlAddrFamily(YnlFamily):
     def __init__(self, recv_size=0):
-        super().__init__((SPEC_PATH / Path('rt_addr.yaml')).as_posix(),
+        super().__init__((SPEC_PATH / Path('rt-addr.yaml')).as_posix(),
                          schema='', recv_size=recv_size)
 
 class NetdevFamily(YnlFamily):
diff --git a/tools/testing/selftests/drivers/net/xdp_helper.c b/tools/testing/selftests/net/lib/xdp_helper.c
index aeed25914104..eb025a9f35b1 100644
--- a/tools/testing/selftests/drivers/net/xdp_helper.c
+++ b/tools/testing/selftests/net/lib/xdp_helper.c
@@ -11,55 +11,16 @@
 #include <net/if.h>
 #include <inttypes.h>
 
+#include "ksft.h"
+
 #define UMEM_SZ (1U << 16)
 #define NUM_DESC (UMEM_SZ / 2048)
 
-/* Move this to a common header when reused! */
-static void ksft_ready(void)
-{
-	const char msg[7] = "ready\n";
-	char *env_str;
-	int fd;
-
-	env_str = getenv("KSFT_READY_FD");
-	if (env_str) {
-		fd = atoi(env_str);
-		if (!fd) {
-			fprintf(stderr, "invalid KSFT_READY_FD = '%s'\n",
-				env_str);
-			return;
-		}
-	} else {
-		fd = STDOUT_FILENO;
-	}
-
-	write(fd, msg, sizeof(msg));
-	if (fd != STDOUT_FILENO)
-		close(fd);
-}
 
-static void ksft_wait(void)
+static void print_usage(const char *bin)
 {
-	char *env_str;
-	char byte;
-	int fd;
-
-	env_str = getenv("KSFT_WAIT_FD");
-	if (env_str) {
-		fd = atoi(env_str);
-		if (!fd) {
-			fprintf(stderr, "invalid KSFT_WAIT_FD = '%s'\n",
-				env_str);
-			return;
-		}
-	} else {
-		/* Not running in KSFT env, wait for input from STDIN instead */
-		fd = STDIN_FILENO;
-	}
-
-	read(fd, &byte, sizeof(byte));
-	if (fd != STDIN_FILENO)
-		close(fd);
+	fprintf(stderr, "Usage: %s ifindex queue_id [-z]\n\n"
+		"where:\n\t-z: force zerocopy mode", bin);
 }
 
 /* this is a simple helper program that creates an XDP socket and does the
@@ -77,12 +38,13 @@ int main(int argc, char **argv)
 	struct sockaddr_xdp sxdp = { 0 };
 	int num_desc = NUM_DESC;
 	void *umem_area;
+	int retry = 0;
 	int ifindex;
 	int sock_fd;
 	int queue;
 
-	if (argc != 3) {
-		fprintf(stderr, "Usage: %s ifindex queue_id\n", argv[0]);
+	if (argc != 3 && argc != 4) {
+		print_usage(argv[0]);
 		return 1;
 	}
 
@@ -132,11 +94,29 @@ int main(int argc, char **argv)
 	sxdp.sxdp_queue_id = queue;
 	sxdp.sxdp_flags = 0;
 
-	if (bind(sock_fd, (struct sockaddr *)&sxdp, sizeof(sxdp)) != 0) {
-		munmap(umem_area, UMEM_SZ);
-		perror("bind failed");
-		close(sock_fd);
-		return 1;
+	if (argc > 3) {
+		if (!strcmp(argv[3], "-z")) {
+			sxdp.sxdp_flags = XDP_ZEROCOPY;
+		} else {
+			print_usage(argv[0]);
+			return 1;
+		}
+	}
+
+	while (1) {
+		if (bind(sock_fd, (struct sockaddr *)&sxdp, sizeof(sxdp)) == 0)
+			break;
+
+		if (errno == EBUSY && retry < 3) {
+			retry++;
+			sleep(1);
+			continue;
+		} else {
+			perror("bind failed");
+			munmap(umem_area, UMEM_SZ);
+			close(sock_fd);
+			return 1;
+		}
 	}
 
 	ksft_ready();
diff --git a/tools/testing/selftests/net/mptcp/Makefile b/tools/testing/selftests/net/mptcp/Makefile
index 340e1a777e16..e47788bfa671 100644
--- a/tools/testing/selftests/net/mptcp/Makefile
+++ b/tools/testing/selftests/net/mptcp/Makefile
@@ -11,7 +11,7 @@ TEST_GEN_FILES = mptcp_connect pm_nl_ctl mptcp_sockopt mptcp_inq mptcp_diag
 
 TEST_FILES := mptcp_lib.sh settings
 
-TEST_INCLUDES := ../lib.sh $(wildcard ../lib/sh/*.sh) ../net_helper.sh
+TEST_INCLUDES := ../lib.sh $(wildcard ../lib/sh/*.sh)
 
 EXTRA_CLEAN := *.pcap
 
diff --git a/tools/testing/selftests/net/mptcp/diag.sh b/tools/testing/selftests/net/mptcp/diag.sh
index e7a75341f0f3..7a3cb4c09e45 100755
--- a/tools/testing/selftests/net/mptcp/diag.sh
+++ b/tools/testing/selftests/net/mptcp/diag.sh
@@ -225,6 +225,37 @@ chk_dump_one()
 	fi
 }
 
+chk_dump_subflow()
+{
+	local inet_diag_token
+	local subflow_line
+	local ss_output
+	local ss_token
+	local msg
+
+	ss_output=$(ss -tniN $ns)
+
+	subflow_line=$(echo "$ss_output" | \
+		       grep -m1 -Eo '[0-9.]+:[0-9].+ +[0-9.]+:[0-9.]+')
+
+	ss_token=$(echo "$ss_output" | grep -m1 -Eo 'token:[^ ]+')
+
+	inet_diag_token=$(ip netns exec $ns ./mptcp_diag -s "$subflow_line" | \
+			  grep -Eo 'token:[^ ]+')
+
+	msg="....chk dump_subflow"
+
+	mptcp_lib_print_title "$msg"
+	if [ -n "$ss_token" ] && [ "$ss_token" = "$inet_diag_token" ]; then
+		mptcp_lib_pr_ok
+		mptcp_lib_result_pass "${msg}"
+	else
+		mptcp_lib_pr_fail "expected $ss_token found $inet_diag_token"
+		mptcp_lib_result_fail "${msg}"
+		ret=${KSFT_FAIL}
+	fi
+}
+
 msk_info_get_value()
 {
 	local port="${1}"
@@ -316,6 +347,7 @@ chk_msk_fallback_nr 0 "....chk no fallback"
 chk_msk_inuse 2
 chk_msk_cestab 2
 chk_dump_one
+chk_dump_subflow
 flush_pids
 
 chk_msk_inuse 0 "2->0"
diff --git a/tools/testing/selftests/net/mptcp/mptcp_connect.c b/tools/testing/selftests/net/mptcp/mptcp_connect.c
index c83a8b47bbdf..ac1349c4b9e5 100644
--- a/tools/testing/selftests/net/mptcp/mptcp_connect.c
+++ b/tools/testing/selftests/net/mptcp/mptcp_connect.c
@@ -180,13 +180,26 @@ static void xgetnameinfo(const struct sockaddr *addr, socklen_t addrlen,
 }
 
 static void xgetaddrinfo(const char *node, const char *service,
-			 const struct addrinfo *hints,
+			 struct addrinfo *hints,
 			 struct addrinfo **res)
 {
+again:
 	int err = getaddrinfo(node, service, hints, res);
 
 	if (err) {
-		const char *errstr = getxinfo_strerr(err);
+		const char *errstr;
+
+		/* glibc starts to support MPTCP since v2.42.
+		 * For older versions, use IPPROTO_TCP to resolve,
+		 * and use TCP/MPTCP to create socket.
+		 * Link: https://sourceware.org/git/?p=glibc.git;a=commit;h=a8e9022e0f82
+		 */
+		if (err == EAI_SOCKTYPE) {
+			hints->ai_protocol = IPPROTO_TCP;
+			goto again;
+		}
+
+		errstr = getxinfo_strerr(err);
 
 		fprintf(stderr, "Fatal: getaddrinfo(%s:%s): %s\n",
 			node ? node : "", service ? service : "", errstr);
@@ -292,7 +305,7 @@ static int sock_listen_mptcp(const char * const listenaddr,
 {
 	int sock = -1;
 	struct addrinfo hints = {
-		.ai_protocol = IPPROTO_TCP,
+		.ai_protocol = IPPROTO_MPTCP,
 		.ai_socktype = SOCK_STREAM,
 		.ai_flags = AI_PASSIVE | AI_NUMERICHOST
 	};
@@ -356,7 +369,7 @@ static int sock_connect_mptcp(const char * const remoteaddr,
 			      int infd, struct wstate *winfo)
 {
 	struct addrinfo hints = {
-		.ai_protocol = IPPROTO_TCP,
+		.ai_protocol = IPPROTO_MPTCP,
 		.ai_socktype = SOCK_STREAM,
 	};
 	struct addrinfo *a, *addr;
diff --git a/tools/testing/selftests/net/mptcp/mptcp_diag.c b/tools/testing/selftests/net/mptcp/mptcp_diag.c
index 284286c524cf..e084796e804d 100644
--- a/tools/testing/selftests/net/mptcp/mptcp_diag.c
+++ b/tools/testing/selftests/net/mptcp/mptcp_diag.c
@@ -8,6 +8,7 @@
 #include <sys/socket.h>
 #include <netinet/in.h>
 #include <linux/tcp.h>
+#include <arpa/inet.h>
 
 #include <unistd.h>
 #include <stdlib.h>
@@ -19,6 +20,15 @@
 #define IPPROTO_MPTCP 262
 #endif
 
+#define parse_rtattr_nested(tb, max, rta) \
+	(parse_rtattr_flags((tb), (max), RTA_DATA(rta), RTA_PAYLOAD(rta), \
+			    NLA_F_NESTED))
+
+struct params {
+	__u32 target_token;
+	char subflow_addrs[1024];
+};
+
 struct mptcp_info {
 	__u8	mptcpi_subflows;
 	__u8	mptcpi_add_addr_signal;
@@ -46,6 +56,37 @@ struct mptcp_info {
 	__u32	mptcpi_last_ack_recv;
 };
 
+enum {
+	MPTCP_SUBFLOW_ATTR_UNSPEC,
+	MPTCP_SUBFLOW_ATTR_TOKEN_REM,
+	MPTCP_SUBFLOW_ATTR_TOKEN_LOC,
+	MPTCP_SUBFLOW_ATTR_RELWRITE_SEQ,
+	MPTCP_SUBFLOW_ATTR_MAP_SEQ,
+	MPTCP_SUBFLOW_ATTR_MAP_SFSEQ,
+	MPTCP_SUBFLOW_ATTR_SSN_OFFSET,
+	MPTCP_SUBFLOW_ATTR_MAP_DATALEN,
+	MPTCP_SUBFLOW_ATTR_FLAGS,
+	MPTCP_SUBFLOW_ATTR_ID_REM,
+	MPTCP_SUBFLOW_ATTR_ID_LOC,
+	MPTCP_SUBFLOW_ATTR_PAD,
+
+	__MPTCP_SUBFLOW_ATTR_MAX
+};
+
+#define MPTCP_SUBFLOW_ATTR_MAX (__MPTCP_SUBFLOW_ATTR_MAX - 1)
+
+#define MPTCP_SUBFLOW_FLAG_MCAP_REM		_BITUL(0)
+#define MPTCP_SUBFLOW_FLAG_MCAP_LOC		_BITUL(1)
+#define MPTCP_SUBFLOW_FLAG_JOIN_REM		_BITUL(2)
+#define MPTCP_SUBFLOW_FLAG_JOIN_LOC		_BITUL(3)
+#define MPTCP_SUBFLOW_FLAG_BKUP_REM		_BITUL(4)
+#define MPTCP_SUBFLOW_FLAG_BKUP_LOC		_BITUL(5)
+#define MPTCP_SUBFLOW_FLAG_FULLY_ESTABLISHED	_BITUL(6)
+#define MPTCP_SUBFLOW_FLAG_CONNECTED		_BITUL(7)
+#define MPTCP_SUBFLOW_FLAG_MAPVALID		_BITUL(8)
+
+#define rta_getattr(type, value)		(*(type *)RTA_DATA(value))
+
 static void die_perror(const char *msg)
 {
 	perror(msg);
@@ -54,11 +95,13 @@ static void die_perror(const char *msg)
 
 static void die_usage(int r)
 {
-	fprintf(stderr, "Usage: mptcp_diag -t\n");
+	fprintf(stderr, "Usage:\n"
+			"mptcp_diag -t <token>\n"
+			"mptcp_diag -s \"<saddr>:<sport> <daddr>:<dport>\"\n");
 	exit(r);
 }
 
-static void send_query(int fd, __u32 token)
+static void send_query(int fd, struct inet_diag_req_v2 *r, __u32 proto)
 {
 	struct sockaddr_nl nladdr = {
 		.nl_family = AF_NETLINK
@@ -72,31 +115,26 @@ static void send_query(int fd, __u32 token)
 			.nlmsg_type = SOCK_DIAG_BY_FAMILY,
 			.nlmsg_flags = NLM_F_REQUEST
 		},
-		.r = {
-			.sdiag_family = AF_INET,
-			/* Real proto is set via INET_DIAG_REQ_PROTOCOL */
-			.sdiag_protocol = IPPROTO_TCP,
-			.id.idiag_cookie[0] = token,
-		}
+		.r = *r
 	};
 	struct rtattr rta_proto;
 	struct iovec iov[6];
-	int iovlen = 1;
-	__u32 proto;
-
-	req.r.idiag_ext |= (1 << (INET_DIAG_INFO - 1));
-	proto = IPPROTO_MPTCP;
-	rta_proto.rta_type = INET_DIAG_REQ_PROTOCOL;
-	rta_proto.rta_len = RTA_LENGTH(sizeof(proto));
+	int iovlen = 0;
 
-	iov[0] = (struct iovec) {
+	iov[iovlen++] = (struct iovec) {
 		.iov_base = &req,
 		.iov_len = sizeof(req)
 	};
-	iov[iovlen] = (struct iovec){ &rta_proto, sizeof(rta_proto)};
-	iov[iovlen + 1] = (struct iovec){ &proto, sizeof(proto)};
-	req.nlh.nlmsg_len += RTA_LENGTH(sizeof(proto));
-	iovlen += 2;
+
+	if (proto == IPPROTO_MPTCP) {
+		rta_proto.rta_type = INET_DIAG_REQ_PROTOCOL;
+		rta_proto.rta_len = RTA_LENGTH(sizeof(proto));
+
+		iov[iovlen++] = (struct iovec){ &rta_proto, sizeof(rta_proto)};
+		iov[iovlen++] = (struct iovec){ &proto, sizeof(proto)};
+		req.nlh.nlmsg_len += RTA_LENGTH(sizeof(proto));
+	}
+
 	struct msghdr msg = {
 		.msg_name = &nladdr,
 		.msg_namelen = sizeof(nladdr),
@@ -160,7 +198,67 @@ static void print_info_msg(struct mptcp_info *info)
 	printf("bytes_acked:      %llu\n", info->mptcpi_bytes_acked);
 }
 
-static void parse_nlmsg(struct nlmsghdr *nlh)
+/*
+ * 'print_subflow_info' is from 'mptcp_subflow_info'
+ * which is a function in 'misc/ss.c' of iproute2.
+ */
+static void print_subflow_info(struct rtattr *tb[])
+{
+	u_int32_t flags = 0;
+
+	printf("It's a mptcp subflow, the subflow info:\n");
+	if (tb[MPTCP_SUBFLOW_ATTR_FLAGS]) {
+		char caps[32 + 1] = { 0 }, *cap = &caps[0];
+
+		flags = rta_getattr(__u32, tb[MPTCP_SUBFLOW_ATTR_FLAGS]);
+
+		if (flags & MPTCP_SUBFLOW_FLAG_MCAP_REM)
+			*cap++ = 'M';
+		if (flags & MPTCP_SUBFLOW_FLAG_MCAP_LOC)
+			*cap++ = 'm';
+		if (flags & MPTCP_SUBFLOW_FLAG_JOIN_REM)
+			*cap++ = 'J';
+		if (flags & MPTCP_SUBFLOW_FLAG_JOIN_LOC)
+			*cap++ = 'j';
+		if (flags & MPTCP_SUBFLOW_FLAG_BKUP_REM)
+			*cap++ = 'B';
+		if (flags & MPTCP_SUBFLOW_FLAG_BKUP_LOC)
+			*cap++ = 'b';
+		if (flags & MPTCP_SUBFLOW_FLAG_FULLY_ESTABLISHED)
+			*cap++ = 'e';
+		if (flags & MPTCP_SUBFLOW_FLAG_CONNECTED)
+			*cap++ = 'c';
+		if (flags & MPTCP_SUBFLOW_FLAG_MAPVALID)
+			*cap++ = 'v';
+
+		if (flags)
+			printf(" flags:%s", caps);
+	}
+	if (tb[MPTCP_SUBFLOW_ATTR_TOKEN_REM] &&
+	    tb[MPTCP_SUBFLOW_ATTR_TOKEN_LOC] &&
+	    tb[MPTCP_SUBFLOW_ATTR_ID_REM] &&
+	    tb[MPTCP_SUBFLOW_ATTR_ID_LOC])
+		printf(" token:%04x(id:%u)/%04x(id:%u)",
+		       rta_getattr(__u32, tb[MPTCP_SUBFLOW_ATTR_TOKEN_REM]),
+		       rta_getattr(__u8, tb[MPTCP_SUBFLOW_ATTR_ID_REM]),
+		       rta_getattr(__u32, tb[MPTCP_SUBFLOW_ATTR_TOKEN_LOC]),
+		       rta_getattr(__u8, tb[MPTCP_SUBFLOW_ATTR_ID_LOC]));
+	if (tb[MPTCP_SUBFLOW_ATTR_MAP_SEQ])
+		printf(" seq:%llu",
+		       rta_getattr(__u64, tb[MPTCP_SUBFLOW_ATTR_MAP_SEQ]));
+	if (tb[MPTCP_SUBFLOW_ATTR_MAP_SFSEQ])
+		printf(" sfseq:%u",
+		       rta_getattr(__u32, tb[MPTCP_SUBFLOW_ATTR_MAP_SFSEQ]));
+	if (tb[MPTCP_SUBFLOW_ATTR_SSN_OFFSET])
+		printf(" ssnoff:%u",
+		       rta_getattr(__u32, tb[MPTCP_SUBFLOW_ATTR_SSN_OFFSET]));
+	if (tb[MPTCP_SUBFLOW_ATTR_MAP_DATALEN])
+		printf(" maplen:%u",
+		       rta_getattr(__u32, tb[MPTCP_SUBFLOW_ATTR_MAP_DATALEN]));
+	printf("\n");
+}
+
+static void parse_nlmsg(struct nlmsghdr *nlh, __u32 proto)
 {
 	struct inet_diag_msg *r = NLMSG_DATA(nlh);
 	struct rtattr *tb[INET_DIAG_MAX + 1];
@@ -169,7 +267,7 @@ static void parse_nlmsg(struct nlmsghdr *nlh)
 			   nlh->nlmsg_len - NLMSG_LENGTH(sizeof(*r)),
 			   NLA_F_NESTED);
 
-	if (tb[INET_DIAG_INFO]) {
+	if (proto == IPPROTO_MPTCP && tb[INET_DIAG_INFO]) {
 		int len = RTA_PAYLOAD(tb[INET_DIAG_INFO]);
 		struct mptcp_info *info;
 
@@ -183,11 +281,28 @@ static void parse_nlmsg(struct nlmsghdr *nlh)
 		}
 		print_info_msg(info);
 	}
+	if (proto == IPPROTO_TCP && tb[INET_DIAG_ULP_INFO]) {
+		struct rtattr *ulpinfo[INET_ULP_INFO_MAX + 1] = { 0 };
+
+		parse_rtattr_nested(ulpinfo, INET_ULP_INFO_MAX,
+				    tb[INET_DIAG_ULP_INFO]);
+
+		if (ulpinfo[INET_ULP_INFO_MPTCP]) {
+			struct rtattr *sfinfo[MPTCP_SUBFLOW_ATTR_MAX + 1] = { 0 };
+
+			parse_rtattr_nested(sfinfo, MPTCP_SUBFLOW_ATTR_MAX,
+					    ulpinfo[INET_ULP_INFO_MPTCP]);
+			print_subflow_info(sfinfo);
+		} else {
+			printf("It's a normal TCP!\n");
+		}
+	}
 }
 
-static void recv_nlmsg(int fd, struct nlmsghdr *nlh)
+static void recv_nlmsg(int fd, __u32 proto)
 {
 	char rcv_buff[8192];
+	struct nlmsghdr *nlh = (struct nlmsghdr *)rcv_buff;
 	struct sockaddr_nl rcv_nladdr = {
 		.nl_family = AF_NETLINK
 	};
@@ -204,7 +319,6 @@ static void recv_nlmsg(int fd, struct nlmsghdr *nlh)
 	int len;
 
 	len = recvmsg(fd, &rcv_msg, 0);
-	nlh = (struct nlmsghdr *)rcv_buff;
 
 	while (NLMSG_OK(nlh, len)) {
 		if (nlh->nlmsg_type == NLMSG_DONE) {
@@ -218,40 +332,84 @@ static void recv_nlmsg(int fd, struct nlmsghdr *nlh)
 			       -(err->error), strerror(-(err->error)));
 			break;
 		}
-		parse_nlmsg(nlh);
+		parse_nlmsg(nlh, proto);
 		nlh = NLMSG_NEXT(nlh, len);
 	}
 }
 
 static void get_mptcpinfo(__u32 token)
 {
-	struct nlmsghdr *nlh = NULL;
+	struct inet_diag_req_v2 r = {
+		.sdiag_family           = AF_INET,
+		/* Real proto is set via INET_DIAG_REQ_PROTOCOL */
+		.sdiag_protocol         = IPPROTO_TCP,
+		.idiag_ext              = 1 << (INET_DIAG_INFO - 1),
+		.id.idiag_cookie[0]     = token,
+	};
+	__u32 proto = IPPROTO_MPTCP;
 	int fd;
 
 	fd = socket(AF_NETLINK, SOCK_RAW, NETLINK_SOCK_DIAG);
 	if (fd < 0)
 		die_perror("Netlink socket");
 
-	send_query(fd, token);
-	recv_nlmsg(fd, nlh);
+	send_query(fd, &r, proto);
+	recv_nlmsg(fd, proto);
 
 	close(fd);
 }
 
-static void parse_opts(int argc, char **argv, __u32 *target_token)
+static void get_subflow_info(char *subflow_addrs)
+{
+	struct inet_diag_req_v2 r = {
+		.sdiag_family           = AF_INET,
+		.sdiag_protocol         = IPPROTO_TCP,
+		.idiag_ext              = 1 << (INET_DIAG_INFO - 1),
+		.id.idiag_cookie[0]     = INET_DIAG_NOCOOKIE,
+		.id.idiag_cookie[1]     = INET_DIAG_NOCOOKIE,
+	};
+	char saddr[64], daddr[64];
+	int sport, dport;
+	int ret;
+	int fd;
+
+	ret = sscanf(subflow_addrs, "%[^:]:%d %[^:]:%d", saddr, &sport, daddr, &dport);
+	if (ret != 4)
+		die_perror("IP PORT Pairs has style problems!");
+
+	printf("%s:%d -> %s:%d\n", saddr, sport, daddr, dport);
+
+	fd = socket(AF_NETLINK, SOCK_RAW, NETLINK_SOCK_DIAG);
+	if (fd < 0)
+		die_perror("Netlink socket");
+
+	r.id.idiag_sport = htons(sport);
+	r.id.idiag_dport = htons(dport);
+
+	inet_pton(AF_INET, saddr, &r.id.idiag_src);
+	inet_pton(AF_INET, daddr, &r.id.idiag_dst);
+	send_query(fd, &r, IPPROTO_TCP);
+	recv_nlmsg(fd, IPPROTO_TCP);
+}
+
+static void parse_opts(int argc, char **argv, struct params *p)
 {
 	int c;
 
 	if (argc < 2)
 		die_usage(1);
 
-	while ((c = getopt(argc, argv, "ht:")) != -1) {
+	while ((c = getopt(argc, argv, "ht:s:")) != -1) {
 		switch (c) {
 		case 'h':
 			die_usage(0);
 			break;
 		case 't':
-			sscanf(optarg, "%x", target_token);
+			sscanf(optarg, "%x", &p->target_token);
+			break;
+		case 's':
+			strncpy(p->subflow_addrs, optarg,
+				sizeof(p->subflow_addrs) - 1);
 			break;
 		default:
 			die_usage(1);
@@ -262,10 +420,15 @@ static void parse_opts(int argc, char **argv, __u32 *target_token)
 
 int main(int argc, char *argv[])
 {
-	__u32 target_token;
+	struct params p = { 0 };
+
+	parse_opts(argc, argv, &p);
+
+	if (p.target_token)
+		get_mptcpinfo(p.target_token);
 
-	parse_opts(argc, argv, &target_token);
-	get_mptcpinfo(target_token);
+	if (p.subflow_addrs[0] != '\0')
+		get_subflow_info(p.subflow_addrs);
 
 	return 0;
 }
diff --git a/tools/testing/selftests/net/mptcp/mptcp_inq.c b/tools/testing/selftests/net/mptcp/mptcp_inq.c
index 218aac467321..3cf1e2a612ce 100644
--- a/tools/testing/selftests/net/mptcp/mptcp_inq.c
+++ b/tools/testing/selftests/net/mptcp/mptcp_inq.c
@@ -72,13 +72,21 @@ static const char *getxinfo_strerr(int err)
 }
 
 static void xgetaddrinfo(const char *node, const char *service,
-			 const struct addrinfo *hints,
+			 struct addrinfo *hints,
 			 struct addrinfo **res)
 {
+again:
 	int err = getaddrinfo(node, service, hints, res);
 
 	if (err) {
-		const char *errstr = getxinfo_strerr(err);
+		const char *errstr;
+
+		if (err == EAI_SOCKTYPE) {
+			hints->ai_protocol = IPPROTO_TCP;
+			goto again;
+		}
+
+		errstr = getxinfo_strerr(err);
 
 		fprintf(stderr, "Fatal: getaddrinfo(%s:%s): %s\n",
 			node ? node : "", service ? service : "", errstr);
@@ -91,7 +99,7 @@ static int sock_listen_mptcp(const char * const listenaddr,
 {
 	int sock = -1;
 	struct addrinfo hints = {
-		.ai_protocol = IPPROTO_TCP,
+		.ai_protocol = IPPROTO_MPTCP,
 		.ai_socktype = SOCK_STREAM,
 		.ai_flags = AI_PASSIVE | AI_NUMERICHOST
 	};
@@ -136,7 +144,7 @@ static int sock_connect_mptcp(const char * const remoteaddr,
 			      const char * const port, int proto)
 {
 	struct addrinfo hints = {
-		.ai_protocol = IPPROTO_TCP,
+		.ai_protocol = IPPROTO_MPTCP,
 		.ai_socktype = SOCK_STREAM,
 	};
 	struct addrinfo *a, *addr;
diff --git a/tools/testing/selftests/net/mptcp/mptcp_join.sh b/tools/testing/selftests/net/mptcp/mptcp_join.sh
index befa66f5a366..b8af65373b3a 100755
--- a/tools/testing/selftests/net/mptcp/mptcp_join.sh
+++ b/tools/testing/selftests/net/mptcp/mptcp_join.sh
@@ -62,6 +62,7 @@ unset sflags
 unset fastclose
 unset fullmesh
 unset speed
+unset join_syn_rej
 unset join_csum_ns1
 unset join_csum_ns2
 unset join_fail_nr
@@ -1403,6 +1404,7 @@ chk_join_nr()
 	local syn_nr=$1
 	local syn_ack_nr=$2
 	local ack_nr=$3
+	local syn_rej=${join_syn_rej:-0}
 	local csum_ns1=${join_csum_ns1:-0}
 	local csum_ns2=${join_csum_ns2:-0}
 	local fail_nr=${join_fail_nr:-0}
@@ -1468,6 +1470,15 @@ chk_join_nr()
 		fail_test "got $count JOIN[s] ack HMAC failure expected 0"
 	fi
 
+	count=$(mptcp_lib_get_counter ${ns1} "MPTcpExtMPJoinRejected")
+	if [ -z "$count" ]; then
+		rc=${KSFT_SKIP}
+	elif [ "$count" != "$syn_rej" ]; then
+		rc=${KSFT_FAIL}
+		print_check "syn rejected"
+		fail_test "got $count JOIN[s] syn rejected expected $syn_rej"
+	fi
+
 	print_results "join Rx" ${rc}
 
 	join_syn_tx="${join_syn_tx:-${syn_nr}}" \
@@ -1963,7 +1974,8 @@ subflows_tests()
 		pm_nl_set_limits $ns2 0 1
 		pm_nl_add_endpoint $ns2 10.0.3.2 flags subflow
 		run_tests $ns1 $ns2 10.0.1.1
-		chk_join_nr 1 1 0
+		join_syn_rej=1 \
+			chk_join_nr 1 1 0
 	fi
 
 	# subflow
@@ -1992,7 +2004,8 @@ subflows_tests()
 		pm_nl_add_endpoint $ns2 10.0.3.2 flags subflow
 		pm_nl_add_endpoint $ns2 10.0.2.2 flags subflow
 		run_tests $ns1 $ns2 10.0.1.1
-		chk_join_nr 2 2 1
+		join_syn_rej=1 \
+			chk_join_nr 2 2 1
 	fi
 
 	# single subflow, dev
@@ -3061,7 +3074,8 @@ syncookies_tests()
 		pm_nl_add_endpoint $ns2 10.0.3.2 flags subflow
 		pm_nl_add_endpoint $ns2 10.0.2.2 flags subflow
 		run_tests $ns1 $ns2 10.0.1.1
-		chk_join_nr 2 1 1
+		join_syn_rej=1 \
+			chk_join_nr 2 1 1
 	fi
 
 	# test signal address with cookies
@@ -3545,7 +3559,8 @@ userspace_tests()
 		pm_nl_set_limits $ns2 1 1
 		pm_nl_add_endpoint $ns2 10.0.3.2 flags subflow
 		run_tests $ns1 $ns2 10.0.1.1
-		chk_join_nr 1 1 0
+		join_syn_rej=1 \
+			chk_join_nr 1 1 0
 	fi
 
 	# userspace pm type does not send join
@@ -3568,7 +3583,8 @@ userspace_tests()
 		pm_nl_add_endpoint $ns2 10.0.3.2 flags subflow
 		sflags=backup speed=slow \
 			run_tests $ns1 $ns2 10.0.1.1
-		chk_join_nr 1 1 0
+		join_syn_rej=1 \
+			chk_join_nr 1 1 0
 		chk_prio_nr 0 0 0 0
 	fi
 
diff --git a/tools/testing/selftests/net/mptcp/mptcp_lib.sh b/tools/testing/selftests/net/mptcp/mptcp_lib.sh
index 051e289d7967..09cd24b2ae46 100644
--- a/tools/testing/selftests/net/mptcp/mptcp_lib.sh
+++ b/tools/testing/selftests/net/mptcp/mptcp_lib.sh
@@ -2,7 +2,6 @@
 # SPDX-License-Identifier: GPL-2.0
 
 . "$(dirname "${0}")/../lib.sh"
-. "$(dirname "${0}")/../net_helper.sh"
 
 readonly KSFT_PASS=0
 readonly KSFT_FAIL=1
@@ -331,12 +330,15 @@ mptcp_lib_result_print_all_tap() {
 
 # get the value of keyword $1 in the line marked by keyword $2
 mptcp_lib_get_info_value() {
-	grep "${2}" | sed -n 's/.*\('"${1}"':\)\([0-9a-f:.]*\).*$/\2/p;q'
+	grep "${2}" 2>/dev/null |
+		sed -n 's/.*\('"${1}"':\)\([0-9a-f:.]*\).*$/\2/p;q'
+		# the ';q' at the end limits to the first matched entry.
 }
 
 # $1: info name ; $2: evts_ns ; [$3: event type; [$4: addr]]
 mptcp_lib_evts_get_info() {
-	grep "${4:-}" "${2}" | mptcp_lib_get_info_value "${1}" "^type:${3:-1},"
+	grep "${4:-}" "${2}" 2>/dev/null |
+		mptcp_lib_get_info_value "${1}" "^type:${3:-1},"
 }
 
 # $1: PID
@@ -476,8 +478,6 @@ mptcp_lib_ns_init() {
 	local netns
 	for netns in "${@}"; do
 		ip netns exec "${!netns}" sysctl -q net.mptcp.enabled=1
-		ip netns exec "${!netns}" sysctl -q net.ipv4.conf.all.rp_filter=0
-		ip netns exec "${!netns}" sysctl -q net.ipv4.conf.default.rp_filter=0
 	done
 }
 
diff --git a/tools/testing/selftests/net/mptcp/mptcp_sockopt.c b/tools/testing/selftests/net/mptcp/mptcp_sockopt.c
index 926b0be87c99..9934a68df237 100644
--- a/tools/testing/selftests/net/mptcp/mptcp_sockopt.c
+++ b/tools/testing/selftests/net/mptcp/mptcp_sockopt.c
@@ -159,13 +159,21 @@ static const char *getxinfo_strerr(int err)
 }
 
 static void xgetaddrinfo(const char *node, const char *service,
-			 const struct addrinfo *hints,
+			 struct addrinfo *hints,
 			 struct addrinfo **res)
 {
+again:
 	int err = getaddrinfo(node, service, hints, res);
 
 	if (err) {
-		const char *errstr = getxinfo_strerr(err);
+		const char *errstr;
+
+		if (err == EAI_SOCKTYPE) {
+			hints->ai_protocol = IPPROTO_TCP;
+			goto again;
+		}
+
+		errstr = getxinfo_strerr(err);
 
 		fprintf(stderr, "Fatal: getaddrinfo(%s:%s): %s\n",
 			node ? node : "", service ? service : "", errstr);
@@ -178,7 +186,7 @@ static int sock_listen_mptcp(const char * const listenaddr,
 {
 	int sock = -1;
 	struct addrinfo hints = {
-		.ai_protocol = IPPROTO_TCP,
+		.ai_protocol = IPPROTO_MPTCP,
 		.ai_socktype = SOCK_STREAM,
 		.ai_flags = AI_PASSIVE | AI_NUMERICHOST
 	};
@@ -223,7 +231,7 @@ static int sock_connect_mptcp(const char * const remoteaddr,
 			      const char * const port, int proto)
 {
 	struct addrinfo hints = {
-		.ai_protocol = IPPROTO_TCP,
+		.ai_protocol = IPPROTO_MPTCP,
 		.ai_socktype = SOCK_STREAM,
 	};
 	struct addrinfo *a, *addr;
diff --git a/tools/testing/selftests/net/net_helper.sh b/tools/testing/selftests/net/net_helper.sh
deleted file mode 100644
index 6596fe03c77f..000000000000
--- a/tools/testing/selftests/net/net_helper.sh
+++ /dev/null
@@ -1,25 +0,0 @@
-#!/bin/bash
-# SPDX-License-Identifier: GPL-2.0
-#
-# Helper functions
-
-wait_local_port_listen()
-{
-	local listener_ns="${1}"
-	local port="${2}"
-	local protocol="${3}"
-	local pattern
-	local i
-
-	pattern=":$(printf "%04X" "${port}") "
-
-	# for tcp protocol additionally check the socket state
-	[ ${protocol} = "tcp" ] && pattern="${pattern}0A"
-	for i in $(seq 10); do
-		if ip netns exec "${listener_ns}" awk '{print $2" "$4}' \
-		   /proc/net/"${protocol}"* | grep -q "${pattern}"; then
-			break
-		fi
-		sleep 0.1
-	done
-}
diff --git a/tools/testing/selftests/net/netfilter/Makefile b/tools/testing/selftests/net/netfilter/Makefile
index ffe161fac8b5..e9b2f553588d 100644
--- a/tools/testing/selftests/net/netfilter/Makefile
+++ b/tools/testing/selftests/net/netfilter/Makefile
@@ -12,6 +12,7 @@ TEST_PROGS += conntrack_dump_flush.sh
 TEST_PROGS += conntrack_icmp_related.sh
 TEST_PROGS += conntrack_ipip_mtu.sh
 TEST_PROGS += conntrack_tcp_unreplied.sh
+TEST_PROGS += conntrack_resize.sh
 TEST_PROGS += conntrack_sctp_collision.sh
 TEST_PROGS += conntrack_vrf.sh
 TEST_PROGS += conntrack_reverse_clash.sh
@@ -23,6 +24,7 @@ TEST_PROGS += nft_concat_range.sh
 TEST_PROGS += nft_conntrack_helper.sh
 TEST_PROGS += nft_fib.sh
 TEST_PROGS += nft_flowtable.sh
+TEST_PROGS += nft_interface_stress.sh
 TEST_PROGS += nft_meta.sh
 TEST_PROGS += nft_nat.sh
 TEST_PROGS += nft_nat_zones.sh
diff --git a/tools/testing/selftests/net/netfilter/br_netfilter.sh b/tools/testing/selftests/net/netfilter/br_netfilter.sh
index 1559ba275105..011de8763094 100755
--- a/tools/testing/selftests/net/netfilter/br_netfilter.sh
+++ b/tools/testing/selftests/net/netfilter/br_netfilter.sh
@@ -60,9 +60,6 @@ bcast_ping()
 	done
 }
 
-ip netns exec "$ns0" sysctl -q net.ipv4.conf.all.rp_filter=0
-ip netns exec "$ns0" sysctl -q net.ipv4.conf.default.rp_filter=0
-
 if ! ip link add veth1 netns "$ns0" type veth peer name eth0 netns "$ns1"; then
 	echo "SKIP: Can't create veth device"
 	exit $ksft_skip
diff --git a/tools/testing/selftests/net/netfilter/bridge_brouter.sh b/tools/testing/selftests/net/netfilter/bridge_brouter.sh
index 2549b6590693..ea76f2bc2f59 100755
--- a/tools/testing/selftests/net/netfilter/bridge_brouter.sh
+++ b/tools/testing/selftests/net/netfilter/bridge_brouter.sh
@@ -22,8 +22,6 @@ trap cleanup EXIT
 
 setup_ns nsbr ns1 ns2
 
-ip netns exec "$nsbr" sysctl -q net.ipv4.conf.default.rp_filter=0
-ip netns exec "$nsbr" sysctl -q net.ipv4.conf.all.rp_filter=0
 if ! ip link add veth0 netns "$nsbr" type veth peer name eth0 netns "$ns1"; then
 	echo "SKIP: Can't create veth device"
 	exit $ksft_skip
diff --git a/tools/testing/selftests/net/netfilter/config b/tools/testing/selftests/net/netfilter/config
index 43d8b500d391..363646f4fefe 100644
--- a/tools/testing/selftests/net/netfilter/config
+++ b/tools/testing/selftests/net/netfilter/config
@@ -46,6 +46,7 @@ CONFIG_NETFILTER_XT_MATCH_STATE=m
 CONFIG_NETFILTER_XT_MATCH_STRING=m
 CONFIG_NETFILTER_XT_TARGET_REDIRECT=m
 CONFIG_NF_CONNTRACK=m
+CONFIG_NF_CONNTRACK_PROCFS=y
 CONFIG_NF_CONNTRACK_EVENTS=y
 CONFIG_NF_CONNTRACK_FTP=m
 CONFIG_NF_CONNTRACK_MARK=y
diff --git a/tools/testing/selftests/net/netfilter/conntrack_resize.sh b/tools/testing/selftests/net/netfilter/conntrack_resize.sh
new file mode 100755
index 000000000000..9e033e80219e
--- /dev/null
+++ b/tools/testing/selftests/net/netfilter/conntrack_resize.sh
@@ -0,0 +1,427 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+
+source lib.sh
+
+checktool "conntrack --version" "run test without conntrack"
+checktool "nft --version" "run test without nft tool"
+
+init_net_max=0
+ct_buckets=0
+tmpfile=""
+tmpfile_proc=""
+tmpfile_uniq=""
+ret=0
+
+insert_count=2000
+[ "$KSFT_MACHINE_SLOW" = "yes" ] && insert_count=400
+
+modprobe -q nf_conntrack
+if ! sysctl -q net.netfilter.nf_conntrack_max >/dev/null;then
+	echo "SKIP: conntrack sysctls not available"
+	exit $KSFT_SKIP
+fi
+
+init_net_max=$(sysctl -n net.netfilter.nf_conntrack_max) || exit 1
+ct_buckets=$(sysctl -n net.netfilter.nf_conntrack_buckets) || exit 1
+
+cleanup() {
+	cleanup_all_ns
+
+	rm -f "$tmpfile" "$tmpfile_proc" "$tmpfile_uniq"
+
+	# restore original sysctl setting
+	sysctl -q net.netfilter.nf_conntrack_max=$init_net_max
+	sysctl -q net.netfilter.nf_conntrack_buckets=$ct_buckets
+}
+trap cleanup EXIT
+
+check_max_alias()
+{
+	local expected="$1"
+	# old name, expected to alias to the first, i.e. changing one
+	# changes the other as well.
+	local lv=$(sysctl -n net.nf_conntrack_max)
+
+	if [ $expected -ne "$lv" ];then
+		echo "nf_conntrack_max sysctls should have identical values"
+		exit 1
+	fi
+}
+
+insert_ctnetlink() {
+	local ns="$1"
+	local count="$2"
+	local i=0
+	local bulk=16
+
+	while [ $i -lt $count ] ;do
+		ip netns exec "$ns" bash -c "for i in \$(seq 1 $bulk); do \
+			if ! conntrack -I -s \$((\$RANDOM%256)).\$((\$RANDOM%256)).\$((\$RANDOM%256)).\$((\$RANDOM%255+1)) \
+					  -d \$((\$RANDOM%256)).\$((\$RANDOM%256)).\$((\$RANDOM%256)).\$((\$RANDOM%255+1)) \
+					  --protonum 17 --timeout 3600 --status ASSURED,SEEN_REPLY --sport \$RANDOM --dport 53; then \
+					  return;\
+			fi & \
+		done ; wait" 2>/dev/null
+
+		i=$((i+bulk))
+	done
+}
+
+check_ctcount() {
+	local ns="$1"
+	local count="$2"
+	local msg="$3"
+
+	local now=$(ip netns exec "$ns" conntrack -C)
+
+	if [ $now -ne "$count" ] ;then
+		echo "expected $count entries in $ns, not $now: $msg"
+		exit 1
+	fi
+
+	echo "PASS: got $count connections: $msg"
+}
+
+ctresize() {
+	local duration="$1"
+	local now=$(date +%s)
+	local end=$((now + duration))
+
+	while [ $now -lt $end ]; do
+		sysctl -q net.netfilter.nf_conntrack_buckets=$RANDOM
+		now=$(date +%s)
+	done
+}
+
+do_rsleep() {
+	local limit="$1"
+	local r=$RANDOM
+
+	r=$((r%limit))
+	sleep "$r"
+}
+
+ct_flush_once() {
+	local ns="$1"
+
+	ip netns exec "$ns" conntrack -F 2>/dev/null
+}
+
+ctflush() {
+	local ns="$1"
+	local duration="$2"
+	local now=$(date +%s)
+	local end=$((now + duration))
+
+	do_rsleep "$duration"
+
+        while [ $now -lt $end ]; do
+		ct_flush_once "$ns"
+		do_rsleep "$duration"
+		now=$(date +%s)
+        done
+}
+
+ctflood()
+{
+	local ns="$1"
+	local duration="$2"
+	local msg="$3"
+	local now=$(date +%s)
+	local end=$((now + duration))
+	local j=0
+	local k=0
+
+        while [ $now -lt $end ]; do
+		j=$((j%256))
+		k=$((k%256))
+
+		ip netns exec "$ns" bash -c \
+			"j=$j k=$k; for i in \$(seq 1 254); do ping -q -c 1 127.\$k.\$j.\$i & done; wait" >/dev/null 2>&1
+
+		j=$((j+1))
+
+		if [ $j -eq 256 ];then
+			k=$((k+1))
+		fi
+
+		now=$(date +%s)
+	done
+
+	wait
+}
+
+# dump to /dev/null.  We don't want dumps to cause infinite loops
+# or use-after-free even when conntrack table is altered while dumps
+# are in progress.
+ct_nulldump()
+{
+	local ns="$1"
+
+	ip netns exec "$ns" conntrack -L > /dev/null 2>&1 &
+
+	# Don't require /proc support in conntrack
+	if [ -r /proc/self/net/nf_conntrack ] ; then
+		ip netns exec "$ns" bash -c "wc -l < /proc/self/net/nf_conntrack" > /dev/null &
+	fi
+
+	wait
+}
+
+check_taint()
+{
+	local tainted_then="$1"
+	local msg="$2"
+
+	local tainted_now=0
+
+	if [ "$tainted_then" -ne 0 ];then
+		return
+	fi
+
+	read tainted_now < /proc/sys/kernel/tainted
+
+	if [ "$tainted_now" -eq 0 ];then
+		echo "PASS: $msg"
+	else
+		echo "TAINT: $msg"
+		dmesg
+		exit 1
+	fi
+}
+
+insert_flood()
+{
+	local n="$1"
+	local r=0
+
+	r=$((RANDOM%$insert_count))
+
+	ctflood "$n" "$timeout" "floodresize" &
+	insert_ctnetlink "$n" "$r" &
+	ctflush "$n" "$timeout" &
+	ct_nulldump "$n" &
+
+	wait
+}
+
+test_floodresize_all()
+{
+	local timeout=20
+	local n=""
+	local tainted_then=""
+
+	read tainted_then < /proc/sys/kernel/tainted
+
+	for n in "$nsclient1" "$nsclient2";do
+		insert_flood "$n" &
+	done
+
+	# resize table constantly while flood/insert/dump/flushs
+	# are happening in parallel.
+	ctresize "$timeout"
+
+	# wait for subshells to complete, everything is limited
+	# by $timeout.
+	wait
+
+	check_taint "$tainted_then" "resize+flood"
+}
+
+check_dump()
+{
+	local ns="$1"
+	local protoname="$2"
+	local c=0
+	local proto=0
+	local proc=0
+	local unique=""
+	local lret=0
+
+	# NOTE: assumes timeouts are large enough to not have
+	# expirations in all following tests.
+	l=$(ip netns exec "$ns" conntrack -L 2>/dev/null | sort | tee "$tmpfile" | wc -l)
+	c=$(ip netns exec "$ns" conntrack -C)
+
+	if [ "$c" -eq 0 ]; then
+		echo "FAIL: conntrack count for $ns is 0"
+		lret=1
+	fi
+
+	if [ "$c" -ne "$l" ]; then
+		echo "FAIL: conntrack count inconsistency for $ns -L: $c != $l"
+		lret=1
+	fi
+
+	# check the dump we retrieved is free of duplicated entries.
+	unique=$(uniq "$tmpfile" | tee "$tmpfile_uniq" | wc -l)
+	if [ "$l" -ne "$unique" ]; then
+		echo "FAIL: listing contained redundant entries for $ns: $l != $unique"
+		diff -u "$tmpfile" "$tmpfile_uniq"
+		lret=1
+	fi
+
+	# we either inserted icmp or only udp, hence, --proto should return same entry count as without filter.
+	proto=$(ip netns exec "$ns" conntrack -L --proto $protoname 2>/dev/null | sort | uniq | tee "$tmpfile_uniq" | wc -l)
+	if [ "$l" -ne "$proto" ]; then
+		echo "FAIL: dump inconsistency for $ns -L --proto $protoname: $l != $proto"
+		diff -u "$tmpfile" "$tmpfile_uniq"
+		lret=1
+	fi
+
+	if [ -r /proc/self/net/nf_conntrack ] ; then
+		proc=$(ip netns exec "$ns" bash -c "sort < /proc/self/net/nf_conntrack | tee \"$tmpfile_proc\" | wc -l")
+
+		if [ "$l" -ne "$proc" ]; then
+			echo "FAIL: proc inconsistency for $ns: $l != $proc"
+			lret=1
+		fi
+
+		proc=$(uniq "$tmpfile_proc" | tee "$tmpfile_uniq" | wc -l)
+		if [ "$l" -ne "$proc" ]; then
+			echo "FAIL: proc inconsistency after uniq filter for $ns: $l != $proc"
+			diff -u "$tmpfile_proc" "$tmpfile_uniq"
+			lret=1
+		fi
+	fi
+
+	if [ $lret -eq 0 ];then
+		echo "PASS: dump in netns $ns had same entry count (-C $c, -L $l, -p $proto, /proc $proc)"
+	else
+		echo "FAIL: dump in netns $ns had different entry count (-C $c, -L $l, -p $proto, /proc $proc)"
+		ret=1
+	fi
+}
+
+test_dump_all()
+{
+	local timeout=3
+	local tainted_then=""
+
+	read tainted_then < /proc/sys/kernel/tainted
+
+	ct_flush_once "$nsclient1"
+	ct_flush_once "$nsclient2"
+
+	ip netns exec "$nsclient1" sysctl -q net.netfilter.nf_conntrack_icmp_timeout=3600
+
+	ctflood "$nsclient1" $timeout "dumpall" &
+	insert_ctnetlink "$nsclient2" $insert_count
+
+	wait
+
+	check_dump "$nsclient1" "icmp"
+	check_dump "$nsclient2" "udp"
+
+	check_taint "$tainted_then" "test parallel conntrack dumps"
+}
+
+check_sysctl_immutable()
+{
+	local ns="$1"
+	local name="$2"
+	local failhard="$3"
+	local o=0
+	local n=0
+
+	o=$(ip netns exec "$ns" sysctl -n "$name" 2>/dev/null)
+	n=$((o+1))
+
+	# return value isn't reliable, need to read it back
+	ip netns exec "$ns" sysctl -q "$name"=$n 2>/dev/null >/dev/null
+
+	n=$(ip netns exec "$ns" sysctl -n "$name" 2>/dev/null)
+
+	[ -z "$n" ] && return 1
+
+	if [ $o -ne $n ]; then
+		if [ $failhard -gt 0 ] ;then
+			echo "FAIL: net.$name should not be changeable from namespace (now $n)"
+			ret=1
+		fi
+		return 0
+	fi
+
+	return 1
+}
+
+test_conntrack_max_limit()
+{
+	sysctl -q net.netfilter.nf_conntrack_max=100
+	insert_ctnetlink "$nsclient1" 101
+
+	# check netns is clamped by init_net, i.e., either netns follows
+	# init_net value, or a higher pernet limit (compared to init_net) is ignored.
+	check_ctcount "$nsclient1" 100 "netns conntrack_max is init_net bound"
+
+	sysctl -q net.netfilter.nf_conntrack_max=$init_net_max
+}
+
+test_conntrack_disable()
+{
+	local timeout=2
+
+	# disable conntrack pickups
+	ip netns exec "$nsclient1" nft flush table ip test_ct
+
+	ct_flush_once "$nsclient1"
+	ct_flush_once "$nsclient2"
+
+	ctflood "$nsclient1" "$timeout" "conntrack disable"
+	ip netns exec "$nsclient2" ping -q -c 1 127.0.0.1 >/dev/null 2>&1
+
+	# Disabled, should not have picked up any connection.
+	check_ctcount "$nsclient1" 0 "conntrack disabled"
+
+	# This one is still active, expect 1 connection.
+	check_ctcount "$nsclient2" 1 "conntrack enabled"
+}
+
+init_net_max=$(sysctl -n net.netfilter.nf_conntrack_max)
+
+check_max_alias $init_net_max
+
+sysctl -q net.netfilter.nf_conntrack_max="262000"
+check_max_alias 262000
+
+setup_ns nsclient1 nsclient2
+
+# check this only works from init_net
+for n in netfilter.nf_conntrack_buckets netfilter.nf_conntrack_expect_max net.nf_conntrack_max;do
+	check_sysctl_immutable "$nsclient1" "net.$n" 1
+done
+
+# won't work on older kernels. If it works, check that the netns obeys the limit
+if check_sysctl_immutable "$nsclient1" net.netfilter.nf_conntrack_max 0;then
+	# subtest: if pernet is changeable, check that reducing it in pernet
+	# limits the pernet entries.  Inverse, pernet clamped by a lower init_net
+	# setting, is already checked by "test_conntrack_max_limit" test.
+
+	ip netns exec "$nsclient1" sysctl -q net.netfilter.nf_conntrack_max=1
+	insert_ctnetlink "$nsclient1" 2
+	check_ctcount "$nsclient1" 1 "netns conntrack_max is pernet bound"
+	ip netns exec "$nsclient1" sysctl -q net.netfilter.nf_conntrack_max=$init_net_max
+fi
+
+for n in "$nsclient1" "$nsclient2";do
+# enable conntrack in both namespaces
+ip netns exec "$n" nft -f - <<EOF
+table ip test_ct {
+	chain input {
+		type filter hook input priority 0
+		ct state new counter
+	}
+}
+EOF
+done
+
+tmpfile=$(mktemp)
+tmpfile_proc=$(mktemp)
+tmpfile_uniq=$(mktemp)
+test_conntrack_max_limit
+test_dump_all
+test_floodresize_all
+test_conntrack_disable
+
+exit $ret
diff --git a/tools/testing/selftests/net/netfilter/conntrack_vrf.sh b/tools/testing/selftests/net/netfilter/conntrack_vrf.sh
index e95ecb37c2b1..207b79932d91 100755
--- a/tools/testing/selftests/net/netfilter/conntrack_vrf.sh
+++ b/tools/testing/selftests/net/netfilter/conntrack_vrf.sh
@@ -32,7 +32,6 @@ source lib.sh
 
 IP0=172.30.30.1
 IP1=172.30.30.2
-DUMMYNET=10.9.9
 PFXL=30
 ret=0
 
@@ -52,11 +51,6 @@ trap cleanup EXIT
 
 setup_ns ns0 ns1
 
-ip netns exec "$ns0" sysctl -q -w net.ipv4.conf.default.rp_filter=0
-ip netns exec "$ns0" sysctl -q -w net.ipv4.conf.all.rp_filter=0
-ip netns exec "$ns0" sysctl -q -w net.ipv4.conf.all.rp_filter=0
-ip netns exec "$ns0" sysctl -q -w net.ipv4.conf.all.forwarding=1
-
 if ! ip link add veth0 netns "$ns0" type veth peer name veth0 netns "$ns1" > /dev/null 2>&1; then
 	echo "SKIP: Could not add veth device"
 	exit $ksft_skip
@@ -67,18 +61,13 @@ if ! ip -net "$ns0" li add tvrf type vrf table 9876; then
 	exit $ksft_skip
 fi
 
-ip -net "$ns0" link add dummy0 type dummy
-
 ip -net "$ns0" li set veth0 master tvrf
-ip -net "$ns0" li set dummy0 master tvrf
 ip -net "$ns0" li set tvrf up
 ip -net "$ns0" li set veth0 up
-ip -net "$ns0" li set dummy0 up
 ip -net "$ns1" li set veth0 up
 
 ip -net "$ns0" addr add $IP0/$PFXL dev veth0
 ip -net "$ns1" addr add $IP1/$PFXL dev veth0
-ip -net "$ns0" addr add $DUMMYNET.1/$PFXL dev dummy0
 
 listener_ready()
 {
@@ -219,35 +208,9 @@ EOF
 	fi
 }
 
-test_fib()
-{
-ip netns exec "$ns0" nft -f - <<EOF
-flush ruleset
-table ip t {
-	counter fibcount { }
-
-	chain prerouting {
-		type filter hook prerouting priority 0;
-		meta iifname veth0 ip daddr $DUMMYNET.2 fib daddr oif dummy0 counter name fibcount notrack
-	}
-}
-EOF
-	ip -net "$ns1" route add 10.9.9.0/24 via "$IP0" dev veth0
-	ip netns exec "$ns1" ping -q -w 1 -c 1 "$DUMMYNET".2 > /dev/null
-
-	if ip netns exec "$ns0" nft list counter t fibcount | grep -q "packets 1"; then
-		echo "PASS: fib lookup returned exepected output interface"
-	else
-		echo "FAIL: fib lookup did not return exepected output interface"
-		ret=1
-		return
-	fi
-}
-
 test_ct_zone_in
 test_masquerade_vrf "default"
 test_masquerade_vrf "pfifo"
 test_masquerade_veth
-test_fib
 
 exit $ret
diff --git a/tools/testing/selftests/net/netfilter/ipvs.sh b/tools/testing/selftests/net/netfilter/ipvs.sh
index d3edb16cd4b3..6af2ea3ad6b8 100755
--- a/tools/testing/selftests/net/netfilter/ipvs.sh
+++ b/tools/testing/selftests/net/netfilter/ipvs.sh
@@ -129,9 +129,6 @@ test_dr() {
 	# avoid incorrect arp response
 	ip netns exec "${ns2}" sysctl -qw net.ipv4.conf.all.arp_ignore=1
 	ip netns exec "${ns2}" sysctl -qw net.ipv4.conf.all.arp_announce=2
-	# avoid reverse route lookup
-	ip netns exec "${ns2}" sysctl -qw  net.ipv4.conf.all.rp_filter=0
-	ip netns exec "${ns2}" sysctl -qw  net.ipv4.conf.veth21.rp_filter=0
 	ip netns exec "${ns2}" ip addr add "${vip_v4}/32" dev lo:1
 
 	test_service
@@ -167,9 +164,6 @@ test_tun() {
 	ip netns exec "${ns2}" ip link set tunl0 up
 	ip netns exec "${ns2}" sysctl -qw net.ipv4.conf.all.arp_ignore=1
 	ip netns exec "${ns2}" sysctl -qw net.ipv4.conf.all.arp_announce=2
-	ip netns exec "${ns2}" sysctl -qw net.ipv4.conf.all.rp_filter=0
-	ip netns exec "${ns2}" sysctl -qw net.ipv4.conf.tunl0.rp_filter=0
-	ip netns exec "${ns2}" sysctl -qw net.ipv4.conf.veth21.rp_filter=0
 	ip netns exec "${ns2}" ip addr add "${vip_v4}/32" dev lo:1
 
 	test_service
diff --git a/tools/testing/selftests/net/netfilter/nft_concat_range.sh b/tools/testing/selftests/net/netfilter/nft_concat_range.sh
index 1f5979c1510c..efea93cf23d4 100755
--- a/tools/testing/selftests/net/netfilter/nft_concat_range.sh
+++ b/tools/testing/selftests/net/netfilter/nft_concat_range.sh
@@ -15,10 +15,12 @@ source lib.sh
 # Available test groups:
 # - reported_issues: check for issues that were reported in the past
 # - correctness: check that packets match given entries, and only those
+# - correctness_large: same but with additional non-matching entries
 # - concurrency: attempt races between insertion, deletion and lookup
 # - timeout: check that packets match entries until they expire
 # - performance: estimate matching rate, compare with rbtree and hash baselines
-TESTS="reported_issues correctness concurrency timeout"
+TESTS="reported_issues correctness correctness_large concurrency timeout"
+
 [ -n "$NFT_CONCAT_RANGE_TESTS" ] && TESTS="${NFT_CONCAT_RANGE_TESTS}"
 
 # Set types, defined by TYPE_ variables below
@@ -1257,9 +1259,7 @@ send_nomatch() {
 # - add ranged element, check that packets match it
 # - check that packets outside range don't match it
 # - remove some elements, check that packets don't match anymore
-test_correctness() {
-	setup veth send_"${proto}" set || return ${ksft_skip}
-
+test_correctness_main() {
 	range_size=1
 	for i in $(seq "${start}" $((start + count))); do
 		end=$((start + range_size))
@@ -1293,6 +1293,163 @@ test_correctness() {
 	done
 }
 
+test_correctness() {
+	setup veth send_"${proto}" set || return ${ksft_skip}
+
+	test_correctness_main
+}
+
+# Repeat the correctness tests, but add extra non-matching entries.
+# This exercises the more compact '4 bit group' representation that
+# gets picked when the default 8-bit representation exceed
+# NFT_PIPAPO_LT_SIZE_HIGH bytes of memory.
+# See usage of NFT_PIPAPO_LT_SIZE_HIGH in pipapo_lt_bits_adjust().
+#
+# The format() helper is way too slow when generating lots of
+# entries so its not used here.
+test_correctness_large() {
+	setup veth send_"${proto}" set || return ${ksft_skip}
+	# number of dummy (filler) entries to add.
+	local dcount=16385
+
+	(
+	echo -n "add element inet filter test { "
+
+	case "$type_spec" in
+	"ether_addr . ipv4_addr")
+		for i in $(seq 1 $dcount); do
+			[ $i -gt 1 ] && echo ", "
+			format_mac $((1000000 + i))
+			printf ". 172.%i.%i.%i " $((RANDOM%256)) $((RANDOM%256)) $((i%256))
+		done
+		;;
+	"inet_proto . ipv6_addr")
+		for i in $(seq 1 $dcount); do
+			[ $i -gt 1 ] && echo ", "
+			printf "%i . " $((RANDOM%256))
+			format_addr6 $((1000000 + i))
+		done
+		;;
+	"inet_service . inet_proto")
+		# smaller key sizes, need more entries to hit the
+		# 4-bit threshold.
+		dcount=65536
+		for i in $(seq 1 $dcount); do
+			local proto=$((RANDOM%256))
+
+			# Test uses UDP to match, as it also fails when matching
+			# an entry that doesn't exist, so skip 'udp' entries
+			# to not trigger a wrong failure.
+			[ $proto -eq 17 ] && proto=18
+			[ $i -gt 1 ] && echo ", "
+			printf "%i . %i " $(((i%65534) + 1)) $((proto))
+		done
+		;;
+	"inet_service . ipv4_addr")
+		dcount=32768
+		for i in $(seq 1 $dcount); do
+			[ $i -gt 1 ] && echo ", "
+			printf "%i . 172.%i.%i.%i " $(((RANDOM%65534) + 1)) $((RANDOM%256)) $((RANDOM%256)) $((i%256))
+		done
+		;;
+	"ipv4_addr . ether_addr")
+		for i in $(seq 1 $dcount); do
+			[ $i -gt 1 ] && echo ", "
+			printf "172.%i.%i.%i . " $((RANDOM%256)) $((RANDOM%256)) $((i%256))
+			format_mac $((1000000 + i))
+		done
+		;;
+	"ipv4_addr . inet_service")
+		dcount=32768
+		for i in $(seq 1 $dcount); do
+			[ $i -gt 1 ] && echo ", "
+			printf "172.%i.%i.%i . %i" $((RANDOM%256)) $((RANDOM%256)) $((i%256)) $(((RANDOM%65534) + 1))
+		done
+		;;
+	"ipv4_addr . inet_service . ether_addr . inet_proto . ipv4_addr")
+		dcount=65536
+		for i in $(seq 1 $dcount); do
+			[ $i -gt 1 ] && echo ", "
+			printf "172.%i.%i.%i . %i . " $((RANDOM%256)) $((RANDOM%256)) $((i%256)) $(((RANDOM%65534) + 1))
+			format_mac $((1000000 + i))
+			printf ". %i . 192.168.%i.%i" $((RANDOM%256)) $((RANDOM%256)) $((i%256))
+		done
+		;;
+	"ipv4_addr . inet_service . inet_proto")
+		for i in $(seq 1 $dcount); do
+			[ $i -gt 1 ] && echo ", "
+			printf "172.%i.%i.%i . %i . %i " $((RANDOM%256)) $((RANDOM%256)) $((i%256)) $(((RANDOM%65534) + 1)) $((RANDOM%256))
+		done
+		;;
+	"ipv4_addr . inet_service . inet_proto . ipv4_addr")
+		for i in $(seq 1 $dcount); do
+			[ $i -gt 1 ] && echo ", "
+			printf "172.%i.%i.%i . %i . %i . 192.168.%i.%i " $((RANDOM%256)) $((RANDOM%256)) $((i%256)) $(((RANDOM%65534) + 1)) $((RANDOM%256)) $((RANDOM%256)) $((RANDOM%256))
+		done
+		;;
+	"ipv4_addr . inet_service . ipv4_addr")
+		dcount=32768
+		for i in $(seq 1 $dcount); do
+			[ $i -gt 1 ] && echo ", "
+			printf "172.%i.%i.%i . %i . 192.168.%i.%i " $((RANDOM%256)) $((RANDOM%256)) $((i%256)) $(((RANDOM%65534) + 1)) $((RANDOM%256)) $((RANDOM%256))
+		done
+		;;
+	"ipv6_addr . ether_addr")
+		for i in $(seq 1 $dcount); do
+			[ $i -gt 1 ] && echo ", "
+			format_addr6 $((i + 1000000))
+			echo -n " . "
+			format_mac $((1000000 + i))
+		done
+		;;
+	"ipv6_addr . inet_service")
+		dcount=32768
+		for i in $(seq 1 $dcount); do
+			[ $i -gt 1 ] && echo ", "
+			format_addr6 $((i + 1000000))
+			echo -n " .  $(((RANDOM%65534) + 1))"
+		done
+		;;
+	"ipv6_addr . inet_service . ether_addr")
+		dcount=32768
+		for i in $(seq 1 $dcount); do
+			[ $i -gt 1 ] && echo ", "
+			format_addr6 $((i + 1000000))
+			echo -n " .  $(((RANDOM%65534) + 1)) . "
+			format_mac $((i + 1000000))
+		done
+		;;
+	"ipv6_addr . inet_service . ether_addr . inet_proto")
+		dcount=65536
+		for i in $(seq 1 $dcount); do
+			[ $i -gt 1 ] && echo ", "
+			format_addr6 $((i + 1000000))
+			echo -n " .  $(((RANDOM%65534) + 1)) . "
+			format_mac $((i + 1000000))
+			echo -n " .  $((RANDOM%256))"
+		done
+		;;
+	"ipv6_addr . inet_service . ipv6_addr . inet_service")
+		dcount=32768
+		for i in $(seq 1 $dcount); do
+			[ $i -gt 1 ] && echo ", "
+			format_addr6 $((i + 1000000))
+			echo -n " .  $(((RANDOM%65534) + 1)) . "
+			format_addr6 $((i + 2123456))
+			echo -n " .  $((RANDOM%256))"
+		done
+		;;
+	*)
+		"Unhandled $type_spec"
+		return 1
+	esac
+	echo -n "}"
+
+	) | nft -f - || return 1
+
+	test_correctness_main
+}
+
 # Concurrency test template:
 # - add all the elements
 # - start a thread for each physical thread that:
diff --git a/tools/testing/selftests/net/netfilter/nft_fib.sh b/tools/testing/selftests/net/netfilter/nft_fib.sh
index ce1451c275fd..9929a9ffef65 100755
--- a/tools/testing/selftests/net/netfilter/nft_fib.sh
+++ b/tools/testing/selftests/net/netfilter/nft_fib.sh
@@ -3,6 +3,10 @@
 # This tests the fib expression.
 #
 # Kselftest framework requirement - SKIP code is 4.
+#
+#  10.0.1.99     10.0.1.1           10.0.2.1         10.0.2.99
+# dead:1::99    dead:1::1          dead:2::1        dead:2::99
+# ns1 <-------> [ veth0 ] nsrouter [veth1] <-------> ns2
 
 source lib.sh
 
@@ -45,6 +49,19 @@ table inet filter {
 EOF
 }
 
+load_input_ruleset() {
+	local netns=$1
+
+ip netns exec "$netns" nft -f /dev/stdin <<EOF
+table inet filter {
+	chain input {
+		type filter hook input priority 0; policy accept;
+	        fib saddr . iif oif missing counter log prefix "$netns nft_rpfilter: " drop
+	}
+}
+EOF
+}
+
 load_pbr_ruleset() {
 	local netns=$1
 
@@ -59,6 +76,89 @@ table inet filter {
 EOF
 }
 
+load_type_ruleset() {
+	local netns=$1
+
+	for family in ip ip6;do
+ip netns exec "$netns" nft -f /dev/stdin <<EOF
+table $family filter {
+	chain type_match_in {
+		fib daddr type local counter comment "daddr configured on other iface"
+		fib daddr . iif type local counter comment "daddr configured on iif"
+		fib daddr type unicast counter comment "daddr not local"
+		fib daddr . iif type unicast counter comment "daddr not configured on iif"
+	}
+
+	chain type_match_out {
+		fib daddr type unicast counter
+		fib daddr . oif type unicast counter
+		fib daddr type local counter
+		fib daddr . oif type local counter
+	}
+
+	chain prerouting {
+		type filter hook prerouting priority 0;
+		icmp type echo-request counter jump type_match_in
+		icmpv6 type echo-request counter jump type_match_in
+	}
+
+	chain input {
+		type filter hook input priority 0;
+		icmp type echo-request counter jump type_match_in
+		icmpv6 type echo-request counter jump type_match_in
+	}
+
+	chain forward {
+		type filter hook forward priority 0;
+		icmp type echo-request counter jump type_match_in
+		icmpv6 type echo-request counter jump type_match_in
+	}
+
+	chain output {
+		type filter hook output priority 0;
+		icmp type echo-request counter jump type_match_out
+		icmpv6 type echo-request counter jump type_match_out
+	}
+
+	chain postrouting {
+		type filter hook postrouting priority 0;
+		icmp type echo-request counter jump type_match_out
+		icmpv6 type echo-request counter jump type_match_out
+	}
+}
+EOF
+done
+}
+
+reload_type_ruleset() {
+	ip netns exec "$1" nft flush table ip filter
+	ip netns exec "$1" nft flush table ip6 filter
+	load_type_ruleset "$1"
+}
+
+check_fib_type_counter_family() {
+	local family="$1"
+	local want="$2"
+	local ns="$3"
+	local chain="$4"
+	local what="$5"
+	local errmsg="$6"
+
+	if ! ip netns exec "$ns" nft list chain "$family" filter "$chain" | grep "$what" | grep -q "packets $want";then
+		echo "Netns $ns $family fib type counter doesn't match expected packet count of $want for $what $errmsg" 1>&2
+		ip netns exec "$ns" nft list chain "$family" filter "$chain"
+		ret=1
+		return 1
+	fi
+
+	return 0
+}
+
+check_fib_type_counter() {
+	check_fib_type_counter_family "ip" "$@" || return 1
+	check_fib_type_counter_family "ip6" "$@" || return 1
+}
+
 load_ruleset_count() {
 	local netns=$1
 
@@ -77,6 +177,7 @@ check_drops() {
 	if dmesg | grep -q ' nft_rpfilter: ';then
 		dmesg | grep ' nft_rpfilter: '
 		echo "FAIL: rpfilter did drop packets"
+		ret=1
 		return 1
 	fi
 
@@ -151,19 +252,506 @@ test_ping() {
   return 0
 }
 
+test_ping_unreachable() {
+  local daddr4=$1
+  local daddr6=$2
+
+  if ip netns exec "$ns1" ping -c 1 -w 1 -q "$daddr4" > /dev/null; then
+	echo "FAIL: ${ns1} could reach $daddr4" 1>&2
+	return 1
+  fi
+
+  if ip netns exec "$ns1" ping -c 1 -w 1 -q "$daddr6" > /dev/null; then
+	echo "FAIL: ${ns1} could reach $daddr6" 1>&2
+	return 1
+  fi
+
+  return 0
+}
+
+test_fib_type() {
+	local notice="$1"
+	local errmsg="addr-on-if"
+	local lret=0
+
+	if ! load_type_ruleset "$nsrouter";then
+		echo "SKIP: Could not load fib type ruleset"
+		[ $ret -eq 0 ] && ret=$ksft_skip
+		return
+	fi
+
+	# makes router receive packet for addresses configured on incoming
+	# interface.
+	test_ping 10.0.1.1 dead:1::1 || return 1
+
+	# expectation: triggers all 'local' in prerouting/input.
+	check_fib_type_counter 2 "$nsrouter" "type_match_in" "fib daddr type local" "$errmsg" || lret=1
+	check_fib_type_counter 2 "$nsrouter" "type_match_in" "fib daddr . iif type local" "$errmsg" || lret=1
+
+	reload_type_ruleset "$nsrouter"
+	# makes router receive packet for address configured on a different (but local)
+	# interface.
+	test_ping 10.0.2.1 dead:2::1 || return 1
+
+	# expectation: triggers 'unicast' in prerouting/input for daddr . iif and local for 'daddr'.
+	errmsg="addr-on-host"
+	check_fib_type_counter 2 "$nsrouter" "type_match_in" "fib daddr type local" "$errmsg" || lret=1
+	check_fib_type_counter 2 "$nsrouter" "type_match_in" "fib daddr . iif type unicast" "$errmsg" || lret=1
+
+	reload_type_ruleset "$nsrouter"
+	test_ping 10.0.2.99 dead:2::99 || return 1
+	errmsg="addr-on-otherhost"
+	check_fib_type_counter 2 "$nsrouter" "type_match_in" "fib daddr type unicast" "$errmsg" || lret=1
+	check_fib_type_counter 2 "$nsrouter" "type_match_in" "fib daddr . iif type unicast" "$errmsg" || lret=1
+
+	if [ $lret -eq 0 ];then
+		echo "PASS: fib expression address types match ($notice)"
+	else
+		echo "FAIL: fib expression address types match ($notice)"
+		ret=1
+	fi
+}
+
+test_fib_vrf_dev_add_dummy()
+{
+	if ! ip -net "$nsrouter" link add dummy0 type dummy ;then
+		echo "SKIP: VRF tests: dummy device type not supported"
+		return 1
+	fi
+
+	if ! ip -net "$nsrouter" link add tvrf type vrf table 9876;then
+		echo "SKIP: VRF tests: vrf device type not supported"
+		return 1
+	fi
+
+	ip -net "$nsrouter" link set dummy0 master tvrf
+	ip -net "$nsrouter" link set dummy0 up
+	ip -net "$nsrouter" link set tvrf up
+}
+
+load_ruleset_vrf()
+{
+# Due to the many different possible combinations using named counters
+# or one-rule-per-expected-result is complex.
+#
+# Instead, add dynamic sets for the fib modes
+# (fib address type, fib output interface lookup .. ),
+# and then add the obtained fib results to them.
+#
+# The test is successful if the sets contain the expected results
+# and no unexpected extra entries existed.
+ip netns exec "$nsrouter" nft -f - <<EOF
+flush ruleset
+table inet t {
+	set fibif4 {
+		typeof meta iif . ip daddr . fib daddr oif
+		flags dynamic
+		counter
+	}
+
+	set fibif4iif {
+		typeof meta iif . ip daddr . fib daddr . iif oif
+		flags dynamic
+		counter
+	}
+
+	set fibif6 {
+		typeof meta iif . ip6 daddr . fib daddr oif
+		flags dynamic
+		counter
+	}
+
+	set fibif6iif {
+		typeof meta iif . ip6 daddr . fib daddr . iif oif
+		flags dynamic
+		counter
+	}
+
+	set fibtype4 {
+		typeof meta iif . ip daddr . fib daddr type
+		flags dynamic
+		counter
+	}
+
+	set fibtype4iif {
+		typeof meta iif . ip daddr . fib daddr . iif type
+		flags dynamic
+		counter
+	}
+
+	set fibtype6 {
+		typeof meta iif . ip6 daddr . fib daddr type
+		flags dynamic
+		counter
+	}
+
+	set fibtype6iif {
+		typeof meta iif . ip6 daddr . fib daddr . iif type
+		flags dynamic
+		counter
+	}
+
+	chain fib_test {
+		meta nfproto ipv4 jump {
+			add @fibif4 { meta iif . ip daddr . fib daddr oif }
+			add @fibif4iif { meta iif . ip daddr . fib daddr . iif oif }
+			add @fibtype4 { meta iif . ip daddr . fib daddr type }
+			add @fibtype4iif { meta iif . ip daddr . fib daddr . iif type }
+
+			add @fibif4 { meta iif . ip saddr . fib saddr oif }
+			add @fibif4iif { meta iif . ip saddr . fib saddr . iif oif }
+		}
+
+		meta nfproto ipv6 jump {
+			add @fibif6    { meta iif . ip6 daddr . fib daddr oif }
+			add @fibif6iif { meta iif . ip6 daddr . fib daddr . iif oif }
+			add @fibtype6    { meta iif . ip6 daddr . fib daddr type }
+			add @fibtype6iif { meta iif . ip6 daddr . fib daddr . iif type }
+
+			add @fibif6 { meta iif . ip6 saddr . fib saddr oif }
+			add @fibif6iif { meta iif . ip6 saddr . fib saddr . iif oif }
+		}
+	}
+
+	chain prerouting {
+		type filter hook prerouting priority 0;
+		icmp type echo-request counter jump fib_test
+
+		# neighbour discovery to be ignored.
+		icmpv6 type echo-request counter jump fib_test
+	}
+}
+EOF
+
+if [ $? -ne 0 ] ;then
+	echo "SKIP: Could not load ruleset for fib vrf test"
+	[ $ret -eq 0 ] && ret=$ksft_skip
+	return 1
+fi
+}
+
+check_type()
+{
+	local setname="$1"
+	local iifname="$2"
+	local addr="$3"
+	local type="$4"
+	local count="$5"
+
+	[ -z "$count" ] && count=1
+
+	if ! ip netns exec "$nsrouter" nft get element inet t "$setname" { "$iifname" . "$addr" . "$type" } |grep -q "counter packets $count";then
+		echo "FAIL: did not find $iifname . $addr . $type in $setname"
+		ip netns exec "$nsrouter" nft list set inet t "$setname"
+		ret=1
+		return 1
+	fi
+
+	# delete the entry, this allows to check if anything unexpected appeared
+	# at the end of the test run: all dynamic sets should be empty by then.
+	if ! ip netns exec "$nsrouter" nft delete element inet t "$setname" { "$iifname" . "$addr" . "$type" } ; then
+		echo "FAIL: can't delete $iifname . $addr . $type in $setname"
+		ip netns exec "$nsrouter" nft list set inet t "$setname"
+		ret=1
+		return 1
+	fi
+
+	return 0
+}
+
+check_local()
+{
+	check_type $@ "local" 1
+}
+
+check_unicast()
+{
+	check_type $@ "unicast" 1
+}
+
+check_rpf()
+{
+	check_type $@
+}
+
+check_fib_vrf_sets_empty()
+{
+	local setname=""
+	local lret=0
+
+	# A non-empty set means that we have seen unexpected packets OR
+	# that a fib lookup provided unexpected results.
+	for setname in "fibif4" "fibif4iif" "fibif6" "fibif6iif" \
+		       "fibtype4" "fibtype4iif" "fibtype6" "fibtype6iif";do
+		if ip netns exec "$nsrouter" nft list set inet t "$setname" | grep -q elements;then
+			echo "FAIL: $setname not empty"
+	                ip netns exec "$nsrouter" nft list set inet t "$setname"
+			ret=1
+			lret=1
+		fi
+	done
+
+	return $lret
+}
+
+check_fib_vrf_type()
+{
+	local msg="$1"
+
+	local addr
+	# the incoming interface is always veth0.  As its not linked to a VRF,
+	# the 'tvrf' device should NOT show up anywhere.
+	local ifname="veth0"
+	local lret=0
+
+	# local_veth0, local_veth1
+	for addr in "10.0.1.1" "10.0.2.1"; do
+		check_local fibtype4  "$ifname" "$addr" || lret=1
+		check_type  fibif4    "$ifname" "$addr" "0" || lret=1
+	done
+	for addr in "dead:1::1" "dead:2::1";do
+		check_local fibtype6  "$ifname" "$addr" || lret=1
+		check_type  fibif6    "$ifname" "$addr" "0" || lret=1
+	done
+
+	# when restricted to the incoming interface, 10.0.1.1 should
+	# be 'local', but 10.0.2.1 unicast.
+	check_local fibtype4iif   "$ifname" "10.0.1.1" || lret=1
+	check_unicast fibtype4iif "$ifname" "10.0.2.1" || lret=1
+
+	# same for the ipv6 addresses.
+	check_local fibtype6iif   "$ifname" "dead:1::1" || lret=1
+	check_unicast fibtype6iif "$ifname" "dead:2::1" || lret=1
+
+	# None of these addresses should find a valid route when restricting
+	# to the incoming interface (we ask for daddr - 10.0.1.1/2.1 are
+	# reachable via 'lo'.
+	for addr in "10.0.1.1" "10.0.2.1" "10.9.9.1" "10.9.9.2";do
+		check_type fibif4iif "$ifname" "$addr" "0" || lret=1
+	done
+
+	# expect default route (veth1), dummy0 is part of VRF but iif isn't.
+	for addr in "10.9.9.1" "10.9.9.2";do
+		check_unicast fibtype4    "$ifname" "$addr" || lret=1
+		check_unicast fibtype4iif "$ifname" "$addr" || lret=1
+		check_type fibif4 "$ifname" "$addr" "veth1" || lret=1
+	done
+	for addr in "dead:9::1" "dead:9::2";do
+		check_unicast fibtype6    "$ifname" "$addr" || lret=1
+		check_unicast fibtype6iif "$ifname" "$addr" || lret=1
+		check_type fibif6 "$ifname" "$addr" "veth1" || lret=1
+	done
+
+	# same for the IPv6 equivalent addresses.
+	for addr in "dead:1::1" "dead:2::1" "dead:9::1" "dead:9::2";do
+		check_type  fibif6iif "$ifname" "$addr" "0" || lret=1
+	done
+
+	check_unicast fibtype4    "$ifname" "10.0.2.99" || lret=1
+	check_unicast fibtype4iif "$ifname" "10.0.2.99" || lret=1
+	check_unicast fibtype6    "$ifname" "dead:2::99" || lret=1
+	check_unicast fibtype6iif "$ifname" "dead:2::99" || lret=1
+
+	check_type fibif4 "$ifname" "10.0.2.99" "veth1" || lret=1
+	check_type fibif4iif "$ifname" "10.0.2.99" 0 || lret=1
+	check_type fibif6 "$ifname" "dead:2::99" "veth1" || lret=1
+	check_type fibif6iif "$ifname" "dead:2::99" 0 || lret=1
+
+	check_rpf  fibif4    "$ifname" "10.0.1.99" "veth0" 5 || lret=1
+	check_rpf  fibif4iif "$ifname" "10.0.1.99" "veth0" 5 || lret=1
+	check_rpf  fibif6    "$ifname" "dead:1::99" "veth0" 5 || lret=1
+	check_rpf  fibif6iif "$ifname" "dead:1::99" "veth0" 5 || lret=1
+
+	check_fib_vrf_sets_empty || lret=1
+
+	if [ $lret -eq 0 ];then
+		echo "PASS: $msg"
+	else
+		echo "FAIL: $msg"
+		ret=1
+	fi
+}
+
+check_fib_veth_vrf_type()
+{
+	local msg="$1"
+
+	local addr
+	local ifname
+	local setname
+	local lret=0
+
+	# as veth0 is now part of tvrf interface, packets will be seen
+	# twice, once with iif veth0, then with iif tvrf.
+
+	for ifname in "veth0" "tvrf"; do
+		for addr in "10.0.1.1" "10.9.9.1"; do
+			check_local fibtype4  "$ifname" "$addr" || lret=1
+			# addr local, but nft_fib doesn't return routes with RTN_LOCAL.
+			check_type  fibif4    "$ifname" "$addr" 0 || lret=1
+			check_type  fibif4iif "$ifname" "$addr" 0 || lret=1
+		done
+
+		for addr in "dead:1::1" "dead:9::1"; do
+			check_local fibtype6 "$ifname" "$addr" || lret=1
+			# same, address is local but no route is returned for lo.
+			check_type  fibif6    "$ifname" "$addr" 0 || lret=1
+			check_type  fibif6iif "$ifname" "$addr" 0 || lret=1
+		done
+
+		for t in fibtype4 fibtype4iif; do
+			check_unicast "$t" "$ifname" 10.9.9.2 || lret=1
+		done
+		for t in fibtype6 fibtype6iif; do
+			check_unicast "$t" "$ifname" dead:9::2 || lret=1
+		done
+
+		check_unicast fibtype4iif "$ifname" "10.9.9.1" || lret=1
+		check_unicast fibtype6iif "$ifname" "dead:9::1" || lret=1
+
+		check_unicast fibtype4    "$ifname" "10.0.2.99" || lret=1
+		check_unicast fibtype4iif "$ifname" "10.0.2.99" || lret=1
+
+		check_unicast fibtype6    "$ifname" "dead:2::99" || lret=1
+		check_unicast fibtype6iif "$ifname" "dead:2::99" || lret=1
+
+		check_type fibif4    "$ifname"  "10.0.2.99" "veth1" || lret=1
+		check_type fibif6    "$ifname" "dead:2::99" "veth1" || lret=1
+		check_type fibif4    "$ifname"   "10.9.9.2" "dummy0" || lret=1
+		check_type fibif6    "$ifname"  "dead:9::2" "dummy0" || lret=1
+
+		# restricted to iif -- MUST NOT provide result, its != $ifname.
+		check_type fibif4iif "$ifname"  "10.0.2.99" 0 || lret=1
+		check_type fibif6iif "$ifname" "dead:2::99" 0 || lret=1
+
+		check_rpf  fibif4 "$ifname" "10.0.1.99" "veth0" 4 || lret=1
+		check_rpf  fibif6 "$ifname" "dead:1::99" "veth0" 4 || lret=1
+		check_rpf  fibif4iif "$ifname" "10.0.1.99" "$ifname" 4 || lret=1
+		check_rpf  fibif6iif "$ifname" "dead:1::99" "$ifname" 4 || lret=1
+	done
+
+	check_local fibtype4iif "veth0" "10.0.1.1" || lret=1
+	check_local fibtype6iif "veth0" "dead:1::1" || lret=1
+
+	check_unicast fibtype4iif "tvrf" "10.0.1.1" || lret=1
+	check_unicast fibtype6iif "tvrf" "dead:1::1" || lret=1
+
+	# 10.9.9.2 should not provide a result for iif veth, but
+	# should when iif is tvrf.
+	# This is because its reachable via dummy0 which is part of
+	# tvrf.  iif veth0 MUST conceal the dummy0 result (i.e. return oif 0).
+	check_type fibif4iif "veth0" "10.9.9.2" 0 || lret=1
+	check_type fibif6iif "veth0"  "dead:9::2" 0 || lret=1
+
+	check_type fibif4iif "tvrf" "10.9.9.2" "tvrf" || lret=1
+	check_type fibif6iif "tvrf" "dead:9::2" "tvrf" || lret=1
+
+	check_fib_vrf_sets_empty || lret=1
+
+	if [ $lret -eq 0 ];then
+		echo "PASS: $msg"
+	else
+		echo "FAIL: $msg"
+		ret=1
+	fi
+}
+
+# Extends nsrouter config by adding dummy0+vrf.
+#
+#  10.0.1.99     10.0.1.1           10.0.2.1         10.0.2.99
+# dead:1::99    dead:1::1          dead:2::1        dead:2::99
+# ns1 <-------> [ veth0 ] nsrouter [veth1] <-------> ns2
+#                         [dummy0]
+#                         10.9.9.1
+#                        dead:9::1
+#                          [tvrf]
+test_fib_vrf()
+{
+	local cntname=""
+
+	if ! test_fib_vrf_dev_add_dummy; then
+		[ $ret -eq 0 ] && ret=$ksft_skip
+		return
+	fi
+
+	ip -net "$nsrouter" addr add "10.9.9.1"/24 dev dummy0
+	ip -net "$nsrouter" addr add "dead:9::1"/64 dev dummy0 nodad
+
+	ip -net "$nsrouter" route add default via 10.0.2.99
+	ip -net "$nsrouter" route add default via dead:2::99
+
+	load_ruleset_vrf || return
+
+	# no echo reply for these addresses: The dummy interface is part of tvrf,
+	# but veth0 (incoming interface) isn't linked to it.
+	test_ping_unreachable "10.9.9.1" "dead:9::1" &
+	test_ping_unreachable "10.9.9.2" "dead:9::2" &
+
+	# expect replies from these.
+	test_ping "10.0.1.1" "dead:1::1"
+	test_ping "10.0.2.1" "dead:2::1"
+	test_ping "10.0.2.99" "dead:2::99"
+
+	wait
+
+	check_fib_vrf_type "fib expression address types match (iif not in vrf)"
+
+	# second round: this time, make veth0 (rx interface) part of the vrf.
+	# 10.9.9.1 / dead:9::1 become reachable from ns1, while ns2
+	# becomes unreachable.
+	ip -net "$nsrouter" link set veth0 master tvrf
+	ip -net "$nsrouter" addr add dead:1::1/64 dev veth0 nodad
+
+	# this reload should not be needed, but in case
+	# there is some error (missing or unexpected entry) this will prevent them
+	# from leaking into round 2.
+	load_ruleset_vrf || return
+
+	test_ping "10.0.1.1" "dead:1::1"
+	test_ping "10.9.9.1" "dead:9::1"
+
+	# ns2 should no longer be reachable (veth1 not in vrf)
+	test_ping_unreachable "10.0.2.99" "dead:2::99" &
+
+	# vrf via dummy0, but host doesn't exist
+	test_ping_unreachable "10.9.9.2" "dead:9::2" &
+
+	wait
+
+	check_fib_veth_vrf_type "fib expression address types match (iif in vrf)"
+}
+
 ip netns exec "$nsrouter" sysctl net.ipv6.conf.all.forwarding=1 > /dev/null
 ip netns exec "$nsrouter" sysctl net.ipv4.conf.veth0.forwarding=1 > /dev/null
 ip netns exec "$nsrouter" sysctl net.ipv4.conf.veth1.forwarding=1 > /dev/null
-ip netns exec "$nsrouter" sysctl net.ipv4.conf.all.rp_filter=0 > /dev/null
-ip netns exec "$nsrouter" sysctl net.ipv4.conf.veth0.rp_filter=0 > /dev/null
 
 test_ping 10.0.2.1 dead:2::1 || exit 1
-check_drops || exit 1
+check_drops
 
 test_ping 10.0.2.99 dead:2::99 || exit 1
+check_drops
+
+[ $ret -eq 0 ] && echo "PASS: fib expression did not cause unwanted packet drops"
+
+load_input_ruleset "$ns1"
+
+test_ping 127.0.0.1 ::1
+check_drops
+
+test_ping 10.0.1.99 dead:1::99
+check_drops
+
+[ $ret -eq 0 ] && echo "PASS: fib expression did not discard loopback packets"
+
+load_input_ruleset "$ns1"
+
+test_ping 127.0.0.1 ::1 || exit 1
 check_drops || exit 1
 
-echo "PASS: fib expression did not cause unwanted packet drops"
+test_ping 10.0.1.99 dead:1::99 || exit 1
+check_drops || exit 1
+
+echo "PASS: fib expression did not discard loopback packets"
 
 ip netns exec "$nsrouter" nft flush table inet filter
 
@@ -213,7 +801,7 @@ ip -net "$nsrouter" addr del dead:2::1/64 dev veth0
 # ... pbr ruleset for the router, check iif+oif.
 if ! load_pbr_ruleset "$nsrouter";then
 	echo "SKIP: Could not load fib forward ruleset"
-	exit $ksft_skip
+	[ "$ret" -eq 0 ] && ret=$ksft_skip
 fi
 
 ip -net "$nsrouter" rule add from all table 128
@@ -224,11 +812,36 @@ ip -net "$nsrouter" route add table 129 to 10.0.2.0/24 dev veth1
 # drop main ipv4 table
 ip -net "$nsrouter" -4 rule delete table main
 
-if ! test_ping 10.0.2.99 dead:2::99;then
-	ip -net "$nsrouter" nft list ruleset
-	echo "FAIL: fib mismatch in pbr setup"
-	exit 1
+if test_ping 10.0.2.99 dead:2::99;then
+	echo "PASS: fib expression forward check with policy based routing"
+else
+	echo "FAIL: fib expression forward check with policy based routing"
+	ret=1
 fi
 
-echo "PASS: fib expression forward check with policy based routing"
-exit 0
+test_fib_type "policy routing"
+ip netns exec "$nsrouter" nft delete table ip filter
+ip netns exec "$nsrouter" nft delete table ip6 filter
+
+# Un-do policy routing changes
+ip -net "$nsrouter" rule del from all table 128
+ip -net "$nsrouter" rule del from all iif veth0 table 129
+
+ip -net "$nsrouter" route del table 128 to 10.0.1.0/24 dev veth0
+ip -net "$nsrouter" route del table 129 to 10.0.2.0/24 dev veth1
+
+ip -net "$ns1" -4 route del default
+ip -net "$ns1" -6 route del default
+
+ip -net "$ns1" -4 route add default via 10.0.1.1
+ip -net "$ns1" -6 route add default via dead:1::1
+
+ip -net "$nsrouter" -4 rule add from all table main priority 32766
+
+test_fib_type "default table"
+ip netns exec "$nsrouter" nft delete table ip filter
+ip netns exec "$nsrouter" nft delete table ip6 filter
+
+test_fib_vrf
+
+exit $ret
diff --git a/tools/testing/selftests/net/netfilter/nft_interface_stress.sh b/tools/testing/selftests/net/netfilter/nft_interface_stress.sh
new file mode 100755
index 000000000000..5ff7be9daeee
--- /dev/null
+++ b/tools/testing/selftests/net/netfilter/nft_interface_stress.sh
@@ -0,0 +1,154 @@
+#!/bin/bash -e
+#
+# SPDX-License-Identifier: GPL-2.0
+#
+# Torture nftables' netdevice notifier callbacks and related code by frequent
+# renaming of interfaces which netdev-family chains and flowtables hook into.
+
+source lib.sh
+
+checktool "nft --version" "run test without nft tool"
+checktool "iperf3 --version" "run test without iperf3 tool"
+
+# how many seconds to torture the kernel?
+# default to 80% of max run time but don't exceed 48s
+TEST_RUNTIME=$((${kselftest_timeout:-60} * 8 / 10))
+[[ $TEST_RUNTIME -gt 48 ]] && TEST_RUNTIME=48
+
+trap "cleanup_all_ns" EXIT
+
+setup_ns nsc nsr nss
+
+ip -net $nsc link add cr0 type veth peer name rc0 netns $nsr
+ip -net $nsc addr add 10.0.0.1/24 dev cr0
+ip -net $nsc link set cr0 up
+ip -net $nsc route add default via 10.0.0.2
+
+ip -net $nss link add sr0 type veth peer name rs0 netns $nsr
+ip -net $nss addr add 10.1.0.1/24 dev sr0
+ip -net $nss link set sr0 up
+ip -net $nss route add default via 10.1.0.2
+
+ip -net $nsr addr add 10.0.0.2/24 dev rc0
+ip -net $nsr link set rc0 up
+ip -net $nsr addr add 10.1.0.2/24 dev rs0
+ip -net $nsr link set rs0 up
+ip netns exec $nsr sysctl -q net.ipv4.ip_forward=1
+ip netns exec $nsr sysctl -q net.ipv4.conf.all.forwarding=1
+
+{
+	echo "table netdev t {"
+	for ((i = 0; i < 10; i++)); do
+		cat <<-EOF
+		chain chain_rc$i {
+			type filter hook ingress device rc$i priority 0
+			counter
+		}
+		chain chain_rs$i {
+			type filter hook ingress device rs$i priority 0
+			counter
+		}
+		EOF
+	done
+	echo "}"
+	echo "table ip t {"
+	for ((i = 0; i < 10; i++)); do
+		cat <<-EOF
+		flowtable ft_${i} {
+			hook ingress priority 0
+			devices = { rc$i, rs$i }
+		}
+		EOF
+	done
+	echo "chain c {"
+	echo "type filter hook forward priority 0"
+	for ((i = 0; i < 10; i++)); do
+		echo -n "iifname rc$i oifname rs$i "
+		echo    "ip protocol tcp counter flow add @ft_${i}"
+	done
+	echo "counter"
+	echo "}"
+	echo "}"
+} | ip netns exec $nsr nft -f - || {
+	echo "SKIP: Could not load nft ruleset"
+	exit $ksft_skip
+}
+
+for ((o=0, n=1; ; o=n, n++, n %= 10)); do
+	ip -net $nsr link set rc$o name rc$n
+	ip -net $nsr link set rs$o name rs$n
+done &
+rename_loop_pid=$!
+
+while true; do ip netns exec $nsr nft list ruleset >/dev/null 2>&1; done &
+nft_list_pid=$!
+
+ip netns exec $nsr nft monitor >/dev/null &
+nft_monitor_pid=$!
+
+ip netns exec $nss iperf3 --server --daemon -1
+summary_expr='s,^\[SUM\] .* \([0-9\.]\+\) Kbits/sec .* receiver,\1,p'
+rate=$(ip netns exec $nsc iperf3 \
+	--format k -c 10.1.0.1 --time $TEST_RUNTIME \
+	--length 56 --parallel 10 -i 0 | sed -n "$summary_expr")
+
+kill $nft_list_pid
+kill $nft_monitor_pid
+kill $rename_loop_pid
+wait
+
+wildcard_prep() {
+	ip netns exec $nsr nft -f - <<EOF
+table ip t {
+	flowtable ft_wild {
+		hook ingress priority 0
+		devices = { wild* }
+	}
+}
+EOF
+}
+
+if ! wildcard_prep; then
+	echo "SKIP wildcard tests: not supported by host's nft?"
+else
+	for ((i = 0; i < 100; i++)); do
+		ip -net $nsr link add wild$i type dummy &
+	done
+	wait
+	for ((i = 80; i < 100; i++)); do
+		ip -net $nsr link del wild$i &
+	done
+	for ((i = 0; i < 80; i++)); do
+		ip -net $nsr link del wild$i &
+	done
+	wait
+	for ((i = 0; i < 100; i += 10)); do
+		(
+		for ((j = 0; j < 10; j++)); do
+			ip -net $nsr link add wild$((i + j)) type dummy
+		done
+		for ((j = 0; j < 10; j++)); do
+			ip -net $nsr link del wild$((i + j))
+		done
+		) &
+	done
+	wait
+fi
+
+[[ $(</proc/sys/kernel/tainted) -eq 0 ]] || {
+	echo "FAIL: Kernel is tainted!"
+	exit $ksft_fail
+}
+
+[[ $rate -gt 0 ]] || {
+	echo "FAIL: Zero throughput in iperf3"
+	exit $ksft_fail
+}
+
+[[ -f /sys/kernel/debug/kmemleak && \
+   -n $(</sys/kernel/debug/kmemleak) ]] && {
+	echo "FAIL: non-empty kmemleak report"
+	exit $ksft_fail
+}
+
+exit $ksft_pass
diff --git a/tools/testing/selftests/net/netfilter/nft_nat_zones.sh b/tools/testing/selftests/net/netfilter/nft_nat_zones.sh
index 3b81d88bdde3..9f200f80253a 100755
--- a/tools/testing/selftests/net/netfilter/nft_nat_zones.sh
+++ b/tools/testing/selftests/net/netfilter/nft_nat_zones.sh
@@ -88,7 +88,6 @@ for i in $(seq 1 "$maxclients");do
   echo netns exec "$cl" sysctl -q net.ipv4.tcp_syn_retries=2
   echo netns exec "$gw" ip link set "veth$i" up
   echo netns exec "$gw" sysctl -q net.ipv4.conf.veth"$i".arp_ignore=2
-  echo netns exec "$gw" sysctl -q net.ipv4.conf.veth"$i".rp_filter=0
 
   # clients have same IP addresses.
   echo netns exec "$cl" ip addr add 10.1.0.3/24 dev eth0
@@ -178,7 +177,6 @@ fi
 
 ip netns exec "$gw" sysctl -q net.ipv4.conf.all.forwarding=1 > /dev/null
 ip netns exec "$gw" sysctl -q net.ipv6.conf.all.forwarding=1 > /dev/null
-ip netns exec "$gw" sysctl -q net.ipv4.conf.all.rp_filter=0 >/dev/null
 
 # useful for debugging: allows to use 'ping' from clients to gateway.
 ip netns exec "$gw" sysctl -q net.ipv4.fwmark_reflect=1 > /dev/null
diff --git a/tools/testing/selftests/net/netfilter/nft_queue.sh b/tools/testing/selftests/net/netfilter/nft_queue.sh
index 784d1b46912b..6136ceec45e0 100755
--- a/tools/testing/selftests/net/netfilter/nft_queue.sh
+++ b/tools/testing/selftests/net/netfilter/nft_queue.sh
@@ -10,6 +10,8 @@ source lib.sh
 ret=0
 timeout=5
 
+SCTP_TEST_TIMEOUT=60
+
 cleanup()
 {
 	ip netns pids "$ns1" | xargs kill 2>/dev/null
@@ -40,7 +42,7 @@ TMPFILE3=$(mktemp)
 
 TMPINPUT=$(mktemp)
 COUNT=200
-[ "$KSFT_MACHINE_SLOW" = "yes" ] && COUNT=25
+[ "$KSFT_MACHINE_SLOW" = "yes" ] && COUNT=$((COUNT/8))
 dd conv=sparse status=none if=/dev/zero bs=1M count=$COUNT of="$TMPINPUT"
 
 if ! ip link add veth0 netns "$nsrouter" type veth peer name eth0 netns "$ns1" > /dev/null 2>&1; then
@@ -275,9 +277,11 @@ test_tcp_forward()
 	busywait "$BUSYWAIT_TIMEOUT" listener_ready "$ns2"
 	busywait "$BUSYWAIT_TIMEOUT" nf_queue_wait "$nsrouter" 2
 
+	local tthen=$(date +%s)
+
 	ip netns exec "$ns1" socat -u STDIN TCP:10.0.2.99:12345 <"$TMPINPUT" >/dev/null
 
-	wait "$rpid" && echo "PASS: tcp and nfqueue in forward chain"
+	wait_and_check_retval "$rpid" "tcp and nfqueue in forward chain" "$tthen"
 	kill "$nfqpid"
 }
 
@@ -288,13 +292,14 @@ test_tcp_localhost()
 
 	ip netns exec "$nsrouter" ./nf_queue -q 3 &
 	local nfqpid=$!
+	local tthen=$(date +%s)
 
 	busywait "$BUSYWAIT_TIMEOUT" listener_ready "$nsrouter"
 	busywait "$BUSYWAIT_TIMEOUT" nf_queue_wait "$nsrouter" 3
 
 	ip netns exec "$nsrouter" socat -u STDIN TCP:127.0.0.1:12345 <"$TMPINPUT" >/dev/null
 
-	wait "$rpid" && echo "PASS: tcp via loopback"
+	wait_and_check_retval "$rpid" "tcp via loopback" "$tthen"
 	kill "$nfqpid"
 }
 
@@ -417,6 +422,23 @@ check_output_files()
 	fi
 }
 
+wait_and_check_retval()
+{
+	local rpid="$1"
+	local msg="$2"
+	local tthen="$3"
+	local tnow=$(date +%s)
+
+	if wait "$rpid";then
+		echo -n "PASS: "
+	else
+		echo -n "FAIL: "
+		ret=1
+	fi
+
+	printf "%s (duration: %ds)\n" "$msg" $((tnow-tthen))
+}
+
 test_sctp_forward()
 {
 	ip netns exec "$nsrouter" nft -f /dev/stdin <<EOF
@@ -428,13 +450,14 @@ table inet sctpq {
         }
 }
 EOF
-	timeout 60 ip netns exec "$ns2" socat -u SCTP-LISTEN:12345 STDOUT > "$TMPFILE1" &
+	timeout "$SCTP_TEST_TIMEOUT" ip netns exec "$ns2" socat -u SCTP-LISTEN:12345 STDOUT > "$TMPFILE1" &
 	local rpid=$!
 
 	busywait "$BUSYWAIT_TIMEOUT" sctp_listener_ready "$ns2"
 
 	ip netns exec "$nsrouter" ./nf_queue -q 10 -G &
 	local nfqpid=$!
+	local tthen=$(date +%s)
 
 	ip netns exec "$ns1" socat -u STDIN SCTP:10.0.2.99:12345 <"$TMPINPUT" >/dev/null
 
@@ -443,7 +466,7 @@ EOF
 		exit 1
 	fi
 
-	wait "$rpid" && echo "PASS: sctp and nfqueue in forward chain"
+	wait_and_check_retval "$rpid" "sctp and nfqueue in forward chain" "$tthen"
 	kill "$nfqpid"
 
 	check_output_files "$TMPINPUT" "$TMPFILE1" "sctp forward"
@@ -462,13 +485,14 @@ EOF
 	# reduce test file size, software segmentation causes sk wmem increase.
 	dd conv=sparse status=none if=/dev/zero bs=1M count=$((COUNT/2)) of="$TMPINPUT"
 
-	timeout 60 ip netns exec "$ns2" socat -u SCTP-LISTEN:12345 STDOUT > "$TMPFILE1" &
+	timeout "$SCTP_TEST_TIMEOUT" ip netns exec "$ns2" socat -u SCTP-LISTEN:12345 STDOUT > "$TMPFILE1" &
 	local rpid=$!
 
 	busywait "$BUSYWAIT_TIMEOUT" sctp_listener_ready "$ns2"
 
 	ip netns exec "$ns1" ./nf_queue -q 11 &
 	local nfqpid=$!
+	local tthen=$(date +%s)
 
 	ip netns exec "$ns1" socat -u STDIN SCTP:10.0.2.99:12345 <"$TMPINPUT" >/dev/null
 
@@ -478,7 +502,7 @@ EOF
 	fi
 
 	# must wait before checking completeness of output file.
-	wait "$rpid" && echo "PASS: sctp and nfqueue in output chain with GSO"
+	wait_and_check_retval "$rpid" "sctp and nfqueue in output chain with GSO" "$tthen"
 	kill "$nfqpid"
 
 	check_output_files "$TMPINPUT" "$TMPFILE1" "sctp output"
diff --git a/tools/testing/selftests/net/netfilter/rpath.sh b/tools/testing/selftests/net/netfilter/rpath.sh
index 86ec4e68594d..24ad41d526d9 100755
--- a/tools/testing/selftests/net/netfilter/rpath.sh
+++ b/tools/testing/selftests/net/netfilter/rpath.sh
@@ -1,8 +1,7 @@
 #!/bin/bash
 # SPDX-License-Identifier: GPL-2.0
 
-# return code to signal skipped test
-ksft_skip=4
+source lib.sh
 
 # search for legacy iptables (it uses the xtables extensions
 if iptables-legacy --version >/dev/null 2>&1; then
@@ -32,17 +31,10 @@ if [ -z "$iptables$ip6tables$nft" ]; then
 	exit $ksft_skip
 fi
 
-sfx=$(mktemp -u "XXXXXXXX")
-ns1="ns1-$sfx"
-ns2="ns2-$sfx"
-trap "ip netns del $ns1; ip netns del $ns2" EXIT
-
-# create two netns, disable rp_filter in ns2 and
-# keep IPv6 address when moving into VRF
-ip netns add "$ns1"
-ip netns add "$ns2"
-ip netns exec "$ns2" sysctl -q net.ipv4.conf.all.rp_filter=0
-ip netns exec "$ns2" sysctl -q net.ipv4.conf.default.rp_filter=0
+trap cleanup_all_ns EXIT
+
+# create two netns, keep IPv6 address when moving into VRF
+setup_ns ns1 ns2
 ip netns exec "$ns2" sysctl -q net.ipv6.conf.all.keep_addr_on_down=1
 
 # a standard connection between the netns, should not trigger rp filter
diff --git a/tools/testing/selftests/net/ovpn/.gitignore b/tools/testing/selftests/net/ovpn/.gitignore
new file mode 100644
index 000000000000..ee44c081ca7c
--- /dev/null
+++ b/tools/testing/selftests/net/ovpn/.gitignore
@@ -0,0 +1,2 @@
+# SPDX-License-Identifier: GPL-2.0+
+ovpn-cli
diff --git a/tools/testing/selftests/net/ovpn/Makefile b/tools/testing/selftests/net/ovpn/Makefile
new file mode 100644
index 000000000000..e0926d76b4c8
--- /dev/null
+++ b/tools/testing/selftests/net/ovpn/Makefile
@@ -0,0 +1,32 @@
+# SPDX-License-Identifier: GPL-2.0
+# Copyright (C) 2020-2025 OpenVPN, Inc.
+#
+CFLAGS = -pedantic -Wextra -Wall -Wl,--no-as-needed -g -O0 -ggdb $(KHDR_INCLUDES)
+VAR_CFLAGS = $(shell pkg-config --cflags libnl-3.0 libnl-genl-3.0 2>/dev/null)
+ifeq ($(VAR_CFLAGS),)
+VAR_CFLAGS = -I/usr/include/libnl3
+endif
+CFLAGS += $(VAR_CFLAGS)
+
+
+LDLIBS = -lmbedtls -lmbedcrypto
+VAR_LDLIBS = $(shell pkg-config --libs libnl-3.0 libnl-genl-3.0 2>/dev/null)
+ifeq ($(VAR_LDLIBS),)
+VAR_LDLIBS = -lnl-genl-3 -lnl-3
+endif
+LDLIBS += $(VAR_LDLIBS)
+
+
+TEST_FILES = common.sh
+
+TEST_PROGS = test.sh \
+	test-large-mtu.sh \
+	test-chachapoly.sh \
+	test-tcp.sh \
+	test-float.sh \
+	test-close-socket.sh \
+	test-close-socket-tcp.sh
+
+TEST_GEN_FILES := ovpn-cli
+
+include ../../lib.mk
diff --git a/tools/testing/selftests/net/ovpn/common.sh b/tools/testing/selftests/net/ovpn/common.sh
new file mode 100644
index 000000000000..88869c675d03
--- /dev/null
+++ b/tools/testing/selftests/net/ovpn/common.sh
@@ -0,0 +1,108 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+# Copyright (C) 2020-2025 OpenVPN, Inc.
+#
+#  Author:	Antonio Quartulli <antonio@openvpn.net>
+
+UDP_PEERS_FILE=${UDP_PEERS_FILE:-udp_peers.txt}
+TCP_PEERS_FILE=${TCP_PEERS_FILE:-tcp_peers.txt}
+OVPN_CLI=${OVPN_CLI:-./ovpn-cli}
+ALG=${ALG:-aes}
+PROTO=${PROTO:-UDP}
+FLOAT=${FLOAT:-0}
+
+LAN_IP="11.11.11.11"
+
+create_ns() {
+	ip netns add peer${1}
+}
+
+setup_ns() {
+	MODE="P2P"
+
+	if [ ${1} -eq 0 ]; then
+		MODE="MP"
+		for p in $(seq 1 ${NUM_PEERS}); do
+			ip link add veth${p} netns peer0 type veth peer name veth${p} netns peer${p}
+
+			ip -n peer0 addr add 10.10.${p}.1/24 dev veth${p}
+			ip -n peer0 addr add fd00:0:0:${p}::1/64 dev veth${p}
+			ip -n peer0 link set veth${p} up
+
+			ip -n peer${p} addr add 10.10.${p}.2/24 dev veth${p}
+			ip -n peer${p} addr add fd00:0:0:${p}::2/64 dev veth${p}
+			ip -n peer${p} link set veth${p} up
+		done
+	fi
+
+	ip netns exec peer${1} ${OVPN_CLI} new_iface tun${1} $MODE
+	ip -n peer${1} addr add ${2} dev tun${1}
+	# add a secondary IP to peer 1, to test a LAN behind a client
+	if [ ${1} -eq 1 -a -n "${LAN_IP}" ]; then
+		ip -n peer${1} addr add ${LAN_IP} dev tun${1}
+		ip -n peer0 route add ${LAN_IP} via $(echo ${2} |sed -e s'!/.*!!') dev tun0
+	fi
+	if [ -n "${3}" ]; then
+		ip -n peer${1} link set mtu ${3} dev tun${1}
+	fi
+	ip -n peer${1} link set tun${1} up
+}
+
+add_peer() {
+	if [ "${PROTO}" == "UDP" ]; then
+		if [ ${1} -eq 0 ]; then
+			ip netns exec peer0 ${OVPN_CLI} new_multi_peer tun0 1 ${UDP_PEERS_FILE}
+
+			for p in $(seq 1 ${NUM_PEERS}); do
+				ip netns exec peer0 ${OVPN_CLI} new_key tun0 ${p} 1 0 ${ALG} 0 \
+					data64.key
+			done
+		else
+			RADDR=$(awk "NR == ${1} {print \$2}" ${UDP_PEERS_FILE})
+			RPORT=$(awk "NR == ${1} {print \$3}" ${UDP_PEERS_FILE})
+			LPORT=$(awk "NR == ${1} {print \$5}" ${UDP_PEERS_FILE})
+			ip netns exec peer${1} ${OVPN_CLI} new_peer tun${1} ${1} ${LPORT} \
+				${RADDR} ${RPORT}
+			ip netns exec peer${1} ${OVPN_CLI} new_key tun${1} ${1} 1 0 ${ALG} 1 \
+				data64.key
+		fi
+	else
+		if [ ${1} -eq 0 ]; then
+			(ip netns exec peer0 ${OVPN_CLI} listen tun0 1 ${TCP_PEERS_FILE} && {
+				for p in $(seq 1 ${NUM_PEERS}); do
+					ip netns exec peer0 ${OVPN_CLI} new_key tun0 ${p} 1 0 \
+						${ALG} 0 data64.key
+				done
+			}) &
+			sleep 5
+		else
+			ip netns exec peer${1} ${OVPN_CLI} connect tun${1} ${1} 10.10.${1}.1 1 \
+				data64.key
+		fi
+	fi
+}
+
+cleanup() {
+	# some ovpn-cli processes sleep in background so they need manual poking
+	killall $(basename ${OVPN_CLI}) 2>/dev/null || true
+
+	# netns peer0 is deleted without erasing ifaces first
+	for p in $(seq 1 10); do
+		ip -n peer${p} link set tun${p} down 2>/dev/null || true
+		ip netns exec peer${p} ${OVPN_CLI} del_iface tun${p} 2>/dev/null || true
+	done
+	for p in $(seq 1 10); do
+		ip -n peer0 link del veth${p} 2>/dev/null || true
+	done
+	for p in $(seq 0 10); do
+		ip netns del peer${p} 2>/dev/null || true
+	done
+}
+
+if [ "${PROTO}" == "UDP" ]; then
+	NUM_PEERS=${NUM_PEERS:-$(wc -l ${UDP_PEERS_FILE} | awk '{print $1}')}
+else
+	NUM_PEERS=${NUM_PEERS:-$(wc -l ${TCP_PEERS_FILE} | awk '{print $1}')}
+fi
+
+
diff --git a/tools/testing/selftests/net/ovpn/config b/tools/testing/selftests/net/ovpn/config
new file mode 100644
index 000000000000..71946ba9fa17
--- /dev/null
+++ b/tools/testing/selftests/net/ovpn/config
@@ -0,0 +1,10 @@
+CONFIG_NET=y
+CONFIG_INET=y
+CONFIG_STREAM_PARSER=y
+CONFIG_NET_UDP_TUNNEL=y
+CONFIG_DST_CACHE=y
+CONFIG_CRYPTO=y
+CONFIG_CRYPTO_AES=y
+CONFIG_CRYPTO_GCM=y
+CONFIG_CRYPTO_CHACHA20POLY1305=y
+CONFIG_OVPN=m
diff --git a/tools/testing/selftests/net/ovpn/data64.key b/tools/testing/selftests/net/ovpn/data64.key
new file mode 100644
index 000000000000..a99e88c4e290
--- /dev/null
+++ b/tools/testing/selftests/net/ovpn/data64.key
@@ -0,0 +1,5 @@
+jRqMACN7d7/aFQNT8S7jkrBD8uwrgHbG5OQZP2eu4R1Y7tfpS2bf5RHv06Vi163CGoaIiTX99R3B
+ia9ycAH8Wz1+9PWv51dnBLur9jbShlgZ2QHLtUc4a/gfT7zZwULXuuxdLnvR21DDeMBaTbkgbai9
+uvAa7ne1liIgGFzbv+Bas4HDVrygxIxuAnP5Qgc3648IJkZ0QEXPF+O9f0n5+QIvGCxkAUVx+5K6
+KIs+SoeWXnAopELmoGSjUpFtJbagXK82HfdqpuUxT2Tnuef0/14SzVE/vNleBNu2ZbyrSAaah8tE
+BofkPJUBFY+YQcfZNM5Dgrw3i+Bpmpq/gpdg5w==
diff --git a/tools/testing/selftests/net/ovpn/ovpn-cli.c b/tools/testing/selftests/net/ovpn/ovpn-cli.c
new file mode 100644
index 000000000000..de9c26f98b2e
--- /dev/null
+++ b/tools/testing/selftests/net/ovpn/ovpn-cli.c
@@ -0,0 +1,2383 @@
+// SPDX-License-Identifier: GPL-2.0
+/*  OpenVPN data channel accelerator
+ *
+ *  Copyright (C) 2020-2025 OpenVPN, Inc.
+ *
+ *  Author:	Antonio Quartulli <antonio@openvpn.net>
+ */
+
+#include <stdio.h>
+#include <inttypes.h>
+#include <stdbool.h>
+#include <string.h>
+#include <errno.h>
+#include <unistd.h>
+#include <arpa/inet.h>
+#include <net/if.h>
+#include <netinet/in.h>
+#include <time.h>
+
+#include <linux/ovpn.h>
+#include <linux/types.h>
+#include <linux/netlink.h>
+
+#include <netlink/socket.h>
+#include <netlink/netlink.h>
+#include <netlink/genl/genl.h>
+#include <netlink/genl/family.h>
+#include <netlink/genl/ctrl.h>
+
+#include <mbedtls/base64.h>
+#include <mbedtls/error.h>
+
+#include <sys/socket.h>
+
+/* defines to make checkpatch happy */
+#define strscpy strncpy
+#define __always_unused __attribute__((__unused__))
+
+/* libnl < 3.5.0 does not set the NLA_F_NESTED on its own, therefore we
+ * have to explicitly do it to prevent the kernel from failing upon
+ * parsing of the message
+ */
+#define nla_nest_start(_msg, _type) \
+	nla_nest_start(_msg, (_type) | NLA_F_NESTED)
+
+/* libnl < 3.11.0 does not implement nla_get_uint() */
+uint64_t ovpn_nla_get_uint(struct nlattr *attr)
+{
+	if (nla_len(attr) == sizeof(uint32_t))
+		return nla_get_u32(attr);
+	else
+		return nla_get_u64(attr);
+}
+
+typedef int (*ovpn_nl_cb)(struct nl_msg *msg, void *arg);
+
+enum ovpn_key_direction {
+	KEY_DIR_IN = 0,
+	KEY_DIR_OUT,
+};
+
+#define KEY_LEN (256 / 8)
+#define NONCE_LEN 8
+
+#define PEER_ID_UNDEF 0x00FFFFFF
+#define MAX_PEERS 10
+
+struct nl_ctx {
+	struct nl_sock *nl_sock;
+	struct nl_msg *nl_msg;
+	struct nl_cb *nl_cb;
+
+	int ovpn_dco_id;
+};
+
+enum ovpn_cmd {
+	CMD_INVALID,
+	CMD_NEW_IFACE,
+	CMD_DEL_IFACE,
+	CMD_LISTEN,
+	CMD_CONNECT,
+	CMD_NEW_PEER,
+	CMD_NEW_MULTI_PEER,
+	CMD_SET_PEER,
+	CMD_DEL_PEER,
+	CMD_GET_PEER,
+	CMD_NEW_KEY,
+	CMD_DEL_KEY,
+	CMD_GET_KEY,
+	CMD_SWAP_KEYS,
+	CMD_LISTEN_MCAST,
+};
+
+struct ovpn_ctx {
+	enum ovpn_cmd cmd;
+
+	__u8 key_enc[KEY_LEN];
+	__u8 key_dec[KEY_LEN];
+	__u8 nonce[NONCE_LEN];
+
+	enum ovpn_cipher_alg cipher;
+
+	sa_family_t sa_family;
+
+	unsigned long peer_id;
+	unsigned long lport;
+
+	union {
+		struct sockaddr_in in4;
+		struct sockaddr_in6 in6;
+	} remote;
+
+	union {
+		struct sockaddr_in in4;
+		struct sockaddr_in6 in6;
+	} peer_ip;
+
+	bool peer_ip_set;
+
+	unsigned int ifindex;
+	char ifname[IFNAMSIZ];
+	enum ovpn_mode mode;
+	bool mode_set;
+
+	int socket;
+	int cli_sockets[MAX_PEERS];
+
+	__u32 keepalive_interval;
+	__u32 keepalive_timeout;
+
+	enum ovpn_key_direction key_dir;
+	enum ovpn_key_slot key_slot;
+	int key_id;
+
+	const char *peers_file;
+};
+
+static int ovpn_nl_recvmsgs(struct nl_ctx *ctx)
+{
+	int ret;
+
+	ret = nl_recvmsgs(ctx->nl_sock, ctx->nl_cb);
+
+	switch (ret) {
+	case -NLE_INTR:
+		fprintf(stderr,
+			"netlink received interrupt due to signal - ignoring\n");
+		break;
+	case -NLE_NOMEM:
+		fprintf(stderr, "netlink out of memory error\n");
+		break;
+	case -NLE_AGAIN:
+		fprintf(stderr,
+			"netlink reports blocking read - aborting wait\n");
+		break;
+	default:
+		if (ret)
+			fprintf(stderr, "netlink reports error (%d): %s\n",
+				ret, nl_geterror(-ret));
+		break;
+	}
+
+	return ret;
+}
+
+static struct nl_ctx *nl_ctx_alloc_flags(struct ovpn_ctx *ovpn, int cmd,
+					 int flags)
+{
+	struct nl_ctx *ctx;
+	int err, ret;
+
+	ctx = calloc(1, sizeof(*ctx));
+	if (!ctx)
+		return NULL;
+
+	ctx->nl_sock = nl_socket_alloc();
+	if (!ctx->nl_sock) {
+		fprintf(stderr, "cannot allocate netlink socket\n");
+		goto err_free;
+	}
+
+	nl_socket_set_buffer_size(ctx->nl_sock, 8192, 8192);
+
+	ret = genl_connect(ctx->nl_sock);
+	if (ret) {
+		fprintf(stderr, "cannot connect to generic netlink: %s\n",
+			nl_geterror(ret));
+		goto err_sock;
+	}
+
+	/* enable Extended ACK for detailed error reporting */
+	err = 1;
+	setsockopt(nl_socket_get_fd(ctx->nl_sock), SOL_NETLINK, NETLINK_EXT_ACK,
+		   &err, sizeof(err));
+
+	ctx->ovpn_dco_id = genl_ctrl_resolve(ctx->nl_sock, OVPN_FAMILY_NAME);
+	if (ctx->ovpn_dco_id < 0) {
+		fprintf(stderr, "cannot find ovpn_dco netlink component: %d\n",
+			ctx->ovpn_dco_id);
+		goto err_free;
+	}
+
+	ctx->nl_msg = nlmsg_alloc();
+	if (!ctx->nl_msg) {
+		fprintf(stderr, "cannot allocate netlink message\n");
+		goto err_sock;
+	}
+
+	ctx->nl_cb = nl_cb_alloc(NL_CB_DEFAULT);
+	if (!ctx->nl_cb) {
+		fprintf(stderr, "failed to allocate netlink callback\n");
+		goto err_msg;
+	}
+
+	nl_socket_set_cb(ctx->nl_sock, ctx->nl_cb);
+
+	genlmsg_put(ctx->nl_msg, 0, 0, ctx->ovpn_dco_id, 0, flags, cmd, 0);
+
+	if (ovpn->ifindex > 0)
+		NLA_PUT_U32(ctx->nl_msg, OVPN_A_IFINDEX, ovpn->ifindex);
+
+	return ctx;
+nla_put_failure:
+err_msg:
+	nlmsg_free(ctx->nl_msg);
+err_sock:
+	nl_socket_free(ctx->nl_sock);
+err_free:
+	free(ctx);
+	return NULL;
+}
+
+static struct nl_ctx *nl_ctx_alloc(struct ovpn_ctx *ovpn, int cmd)
+{
+	return nl_ctx_alloc_flags(ovpn, cmd, 0);
+}
+
+static void nl_ctx_free(struct nl_ctx *ctx)
+{
+	if (!ctx)
+		return;
+
+	nl_socket_free(ctx->nl_sock);
+	nlmsg_free(ctx->nl_msg);
+	nl_cb_put(ctx->nl_cb);
+	free(ctx);
+}
+
+static int ovpn_nl_cb_error(struct sockaddr_nl (*nla)__always_unused,
+			    struct nlmsgerr *err, void *arg)
+{
+	struct nlmsghdr *nlh = (struct nlmsghdr *)err - 1;
+	struct nlattr *tb_msg[NLMSGERR_ATTR_MAX + 1];
+	int len = nlh->nlmsg_len;
+	struct nlattr *attrs;
+	int *ret = arg;
+	int ack_len = sizeof(*nlh) + sizeof(int) + sizeof(*nlh);
+
+	*ret = err->error;
+
+	if (!(nlh->nlmsg_flags & NLM_F_ACK_TLVS))
+		return NL_STOP;
+
+	if (!(nlh->nlmsg_flags & NLM_F_CAPPED))
+		ack_len += err->msg.nlmsg_len - sizeof(*nlh);
+
+	if (len <= ack_len)
+		return NL_STOP;
+
+	attrs = (void *)((uint8_t *)nlh + ack_len);
+	len -= ack_len;
+
+	nla_parse(tb_msg, NLMSGERR_ATTR_MAX, attrs, len, NULL);
+	if (tb_msg[NLMSGERR_ATTR_MSG]) {
+		len = strnlen((char *)nla_data(tb_msg[NLMSGERR_ATTR_MSG]),
+			      nla_len(tb_msg[NLMSGERR_ATTR_MSG]));
+		fprintf(stderr, "kernel error: %*s\n", len,
+			(char *)nla_data(tb_msg[NLMSGERR_ATTR_MSG]));
+	}
+
+	if (tb_msg[NLMSGERR_ATTR_MISS_NEST]) {
+		fprintf(stderr, "missing required nesting type %u\n",
+			nla_get_u32(tb_msg[NLMSGERR_ATTR_MISS_NEST]));
+	}
+
+	if (tb_msg[NLMSGERR_ATTR_MISS_TYPE]) {
+		fprintf(stderr, "missing required attribute type %u\n",
+			nla_get_u32(tb_msg[NLMSGERR_ATTR_MISS_TYPE]));
+	}
+
+	return NL_STOP;
+}
+
+static int ovpn_nl_cb_finish(struct nl_msg (*msg)__always_unused,
+			     void *arg)
+{
+	int *status = arg;
+
+	*status = 0;
+	return NL_SKIP;
+}
+
+static int ovpn_nl_cb_ack(struct nl_msg (*msg)__always_unused,
+			  void *arg)
+{
+	int *status = arg;
+
+	*status = 0;
+	return NL_STOP;
+}
+
+static int ovpn_nl_msg_send(struct nl_ctx *ctx, ovpn_nl_cb cb)
+{
+	int status = 1;
+
+	nl_cb_err(ctx->nl_cb, NL_CB_CUSTOM, ovpn_nl_cb_error, &status);
+	nl_cb_set(ctx->nl_cb, NL_CB_FINISH, NL_CB_CUSTOM, ovpn_nl_cb_finish,
+		  &status);
+	nl_cb_set(ctx->nl_cb, NL_CB_ACK, NL_CB_CUSTOM, ovpn_nl_cb_ack, &status);
+
+	if (cb)
+		nl_cb_set(ctx->nl_cb, NL_CB_VALID, NL_CB_CUSTOM, cb, ctx);
+
+	nl_send_auto_complete(ctx->nl_sock, ctx->nl_msg);
+
+	while (status == 1)
+		ovpn_nl_recvmsgs(ctx);
+
+	if (status < 0)
+		fprintf(stderr, "failed to send netlink message: %s (%d)\n",
+			strerror(-status), status);
+
+	return status;
+}
+
+static int ovpn_parse_key(const char *file, struct ovpn_ctx *ctx)
+{
+	int idx_enc, idx_dec, ret = -1;
+	unsigned char *ckey = NULL;
+	__u8 *bkey = NULL;
+	size_t olen = 0;
+	long ckey_len;
+	FILE *fp;
+
+	fp = fopen(file, "r");
+	if (!fp) {
+		fprintf(stderr, "cannot open: %s\n", file);
+		return -1;
+	}
+
+	/* get file size */
+	fseek(fp, 0L, SEEK_END);
+	ckey_len = ftell(fp);
+	rewind(fp);
+
+	/* if the file is longer, let's just read a portion */
+	if (ckey_len > 256)
+		ckey_len = 256;
+
+	ckey = malloc(ckey_len);
+	if (!ckey)
+		goto err;
+
+	ret = fread(ckey, 1, ckey_len, fp);
+	if (ret != ckey_len) {
+		fprintf(stderr,
+			"couldn't read enough data from key file: %dbytes read\n",
+			ret);
+		goto err;
+	}
+
+	olen = 0;
+	ret = mbedtls_base64_decode(NULL, 0, &olen, ckey, ckey_len);
+	if (ret != MBEDTLS_ERR_BASE64_BUFFER_TOO_SMALL) {
+		char buf[256];
+
+		mbedtls_strerror(ret, buf, sizeof(buf));
+		fprintf(stderr, "unexpected base64 error1: %s (%d)\n", buf,
+			ret);
+
+		goto err;
+	}
+
+	bkey = malloc(olen);
+	if (!bkey) {
+		fprintf(stderr, "cannot allocate binary key buffer\n");
+		goto err;
+	}
+
+	ret = mbedtls_base64_decode(bkey, olen, &olen, ckey, ckey_len);
+	if (ret) {
+		char buf[256];
+
+		mbedtls_strerror(ret, buf, sizeof(buf));
+		fprintf(stderr, "unexpected base64 error2: %s (%d)\n", buf,
+			ret);
+
+		goto err;
+	}
+
+	if (olen < 2 * KEY_LEN + NONCE_LEN) {
+		fprintf(stderr,
+			"not enough data in key file, found %zdB but needs %dB\n",
+			olen, 2 * KEY_LEN + NONCE_LEN);
+		goto err;
+	}
+
+	switch (ctx->key_dir) {
+	case KEY_DIR_IN:
+		idx_enc = 0;
+		idx_dec = 1;
+		break;
+	case KEY_DIR_OUT:
+		idx_enc = 1;
+		idx_dec = 0;
+		break;
+	default:
+		goto err;
+	}
+
+	memcpy(ctx->key_enc, bkey + KEY_LEN * idx_enc, KEY_LEN);
+	memcpy(ctx->key_dec, bkey + KEY_LEN * idx_dec, KEY_LEN);
+	memcpy(ctx->nonce, bkey + 2 * KEY_LEN, NONCE_LEN);
+
+	ret = 0;
+
+err:
+	fclose(fp);
+	free(bkey);
+	free(ckey);
+
+	return ret;
+}
+
+static int ovpn_parse_cipher(const char *cipher, struct ovpn_ctx *ctx)
+{
+	if (strcmp(cipher, "aes") == 0)
+		ctx->cipher = OVPN_CIPHER_ALG_AES_GCM;
+	else if (strcmp(cipher, "chachapoly") == 0)
+		ctx->cipher = OVPN_CIPHER_ALG_CHACHA20_POLY1305;
+	else if (strcmp(cipher, "none") == 0)
+		ctx->cipher = OVPN_CIPHER_ALG_NONE;
+	else
+		return -ENOTSUP;
+
+	return 0;
+}
+
+static int ovpn_parse_key_direction(const char *dir, struct ovpn_ctx *ctx)
+{
+	int in_dir;
+
+	in_dir = strtoll(dir, NULL, 10);
+	switch (in_dir) {
+	case KEY_DIR_IN:
+	case KEY_DIR_OUT:
+		ctx->key_dir = in_dir;
+		break;
+	default:
+		fprintf(stderr,
+			"invalid key direction provided. Can be 0 or 1 only\n");
+		return -1;
+	}
+
+	return 0;
+}
+
+static int ovpn_socket(struct ovpn_ctx *ctx, sa_family_t family, int proto)
+{
+	struct sockaddr_storage local_sock = { 0 };
+	struct sockaddr_in6 *in6;
+	struct sockaddr_in *in;
+	int ret, s, sock_type;
+	size_t sock_len;
+
+	if (proto == IPPROTO_UDP)
+		sock_type = SOCK_DGRAM;
+	else if (proto == IPPROTO_TCP)
+		sock_type = SOCK_STREAM;
+	else
+		return -EINVAL;
+
+	s = socket(family, sock_type, 0);
+	if (s < 0) {
+		perror("cannot create socket");
+		return -1;
+	}
+
+	switch (family) {
+	case AF_INET:
+		in = (struct sockaddr_in *)&local_sock;
+		in->sin_family = family;
+		in->sin_port = htons(ctx->lport);
+		in->sin_addr.s_addr = htonl(INADDR_ANY);
+		sock_len = sizeof(*in);
+		break;
+	case AF_INET6:
+		in6 = (struct sockaddr_in6 *)&local_sock;
+		in6->sin6_family = family;
+		in6->sin6_port = htons(ctx->lport);
+		in6->sin6_addr = in6addr_any;
+		sock_len = sizeof(*in6);
+		break;
+	default:
+		return -1;
+	}
+
+	int opt = 1;
+
+	ret = setsockopt(s, SOL_SOCKET, SO_REUSEADDR, &opt, sizeof(opt));
+
+	if (ret < 0) {
+		perror("setsockopt for SO_REUSEADDR");
+		return ret;
+	}
+
+	ret = setsockopt(s, SOL_SOCKET, SO_REUSEPORT, &opt, sizeof(opt));
+	if (ret < 0) {
+		perror("setsockopt for SO_REUSEPORT");
+		return ret;
+	}
+
+	if (family == AF_INET6) {
+		opt = 0;
+		if (setsockopt(s, IPPROTO_IPV6, IPV6_V6ONLY, &opt,
+			       sizeof(opt))) {
+			perror("failed to set IPV6_V6ONLY");
+			return -1;
+		}
+	}
+
+	ret = bind(s, (struct sockaddr *)&local_sock, sock_len);
+	if (ret < 0) {
+		perror("cannot bind socket");
+		goto err_socket;
+	}
+
+	ctx->socket = s;
+	ctx->sa_family = family;
+	return 0;
+
+err_socket:
+	close(s);
+	return -1;
+}
+
+static int ovpn_udp_socket(struct ovpn_ctx *ctx, sa_family_t family)
+{
+	return ovpn_socket(ctx, family, IPPROTO_UDP);
+}
+
+static int ovpn_listen(struct ovpn_ctx *ctx, sa_family_t family)
+{
+	int ret;
+
+	ret = ovpn_socket(ctx, family, IPPROTO_TCP);
+	if (ret < 0)
+		return ret;
+
+	ret = listen(ctx->socket, 10);
+	if (ret < 0) {
+		perror("listen");
+		close(ctx->socket);
+		return -1;
+	}
+
+	return 0;
+}
+
+static int ovpn_accept(struct ovpn_ctx *ctx)
+{
+	socklen_t socklen;
+	int ret;
+
+	socklen = sizeof(ctx->remote);
+	ret = accept(ctx->socket, (struct sockaddr *)&ctx->remote, &socklen);
+	if (ret < 0) {
+		perror("accept");
+		goto err;
+	}
+
+	fprintf(stderr, "Connection received!\n");
+
+	switch (socklen) {
+	case sizeof(struct sockaddr_in):
+	case sizeof(struct sockaddr_in6):
+		break;
+	default:
+		fprintf(stderr, "error: expecting IPv4 or IPv6 connection\n");
+		close(ret);
+		ret = -EINVAL;
+		goto err;
+	}
+
+	return ret;
+err:
+	close(ctx->socket);
+	return ret;
+}
+
+static int ovpn_connect(struct ovpn_ctx *ovpn)
+{
+	socklen_t socklen;
+	int s, ret;
+
+	s = socket(ovpn->remote.in4.sin_family, SOCK_STREAM, 0);
+	if (s < 0) {
+		perror("cannot create socket");
+		return -1;
+	}
+
+	switch (ovpn->remote.in4.sin_family) {
+	case AF_INET:
+		socklen = sizeof(struct sockaddr_in);
+		break;
+	case AF_INET6:
+		socklen = sizeof(struct sockaddr_in6);
+		break;
+	default:
+		return -EOPNOTSUPP;
+	}
+
+	ret = connect(s, (struct sockaddr *)&ovpn->remote, socklen);
+	if (ret < 0) {
+		perror("connect");
+		goto err;
+	}
+
+	fprintf(stderr, "connected\n");
+
+	ovpn->socket = s;
+
+	return 0;
+err:
+	close(s);
+	return ret;
+}
+
+static int ovpn_new_peer(struct ovpn_ctx *ovpn, bool is_tcp)
+{
+	struct nlattr *attr;
+	struct nl_ctx *ctx;
+	int ret = -1;
+
+	ctx = nl_ctx_alloc(ovpn, OVPN_CMD_PEER_NEW);
+	if (!ctx)
+		return -ENOMEM;
+
+	attr = nla_nest_start(ctx->nl_msg, OVPN_A_PEER);
+	NLA_PUT_U32(ctx->nl_msg, OVPN_A_PEER_ID, ovpn->peer_id);
+	NLA_PUT_U32(ctx->nl_msg, OVPN_A_PEER_SOCKET, ovpn->socket);
+
+	if (!is_tcp) {
+		switch (ovpn->remote.in4.sin_family) {
+		case AF_INET:
+			NLA_PUT_U32(ctx->nl_msg, OVPN_A_PEER_REMOTE_IPV4,
+				    ovpn->remote.in4.sin_addr.s_addr);
+			NLA_PUT_U16(ctx->nl_msg, OVPN_A_PEER_REMOTE_PORT,
+				    ovpn->remote.in4.sin_port);
+			break;
+		case AF_INET6:
+			NLA_PUT(ctx->nl_msg, OVPN_A_PEER_REMOTE_IPV6,
+				sizeof(ovpn->remote.in6.sin6_addr),
+				&ovpn->remote.in6.sin6_addr);
+			NLA_PUT_U32(ctx->nl_msg,
+				    OVPN_A_PEER_REMOTE_IPV6_SCOPE_ID,
+				    ovpn->remote.in6.sin6_scope_id);
+			NLA_PUT_U16(ctx->nl_msg, OVPN_A_PEER_REMOTE_PORT,
+				    ovpn->remote.in6.sin6_port);
+			break;
+		default:
+			fprintf(stderr,
+				"Invalid family for remote socket address\n");
+			goto nla_put_failure;
+		}
+	}
+
+	if (ovpn->peer_ip_set) {
+		switch (ovpn->peer_ip.in4.sin_family) {
+		case AF_INET:
+			NLA_PUT_U32(ctx->nl_msg, OVPN_A_PEER_VPN_IPV4,
+				    ovpn->peer_ip.in4.sin_addr.s_addr);
+			break;
+		case AF_INET6:
+			NLA_PUT(ctx->nl_msg, OVPN_A_PEER_VPN_IPV6,
+				sizeof(struct in6_addr),
+				&ovpn->peer_ip.in6.sin6_addr);
+			break;
+		default:
+			fprintf(stderr, "Invalid family for peer address\n");
+			goto nla_put_failure;
+		}
+	}
+
+	nla_nest_end(ctx->nl_msg, attr);
+
+	ret = ovpn_nl_msg_send(ctx, NULL);
+nla_put_failure:
+	nl_ctx_free(ctx);
+	return ret;
+}
+
+static int ovpn_set_peer(struct ovpn_ctx *ovpn)
+{
+	struct nlattr *attr;
+	struct nl_ctx *ctx;
+	int ret = -1;
+
+	ctx = nl_ctx_alloc(ovpn, OVPN_CMD_PEER_SET);
+	if (!ctx)
+		return -ENOMEM;
+
+	attr = nla_nest_start(ctx->nl_msg, OVPN_A_PEER);
+	NLA_PUT_U32(ctx->nl_msg, OVPN_A_PEER_ID, ovpn->peer_id);
+	NLA_PUT_U32(ctx->nl_msg, OVPN_A_PEER_KEEPALIVE_INTERVAL,
+		    ovpn->keepalive_interval);
+	NLA_PUT_U32(ctx->nl_msg, OVPN_A_PEER_KEEPALIVE_TIMEOUT,
+		    ovpn->keepalive_timeout);
+	nla_nest_end(ctx->nl_msg, attr);
+
+	ret = ovpn_nl_msg_send(ctx, NULL);
+nla_put_failure:
+	nl_ctx_free(ctx);
+	return ret;
+}
+
+static int ovpn_del_peer(struct ovpn_ctx *ovpn)
+{
+	struct nlattr *attr;
+	struct nl_ctx *ctx;
+	int ret = -1;
+
+	ctx = nl_ctx_alloc(ovpn, OVPN_CMD_PEER_DEL);
+	if (!ctx)
+		return -ENOMEM;
+
+	attr = nla_nest_start(ctx->nl_msg, OVPN_A_PEER);
+	NLA_PUT_U32(ctx->nl_msg, OVPN_A_PEER_ID, ovpn->peer_id);
+	nla_nest_end(ctx->nl_msg, attr);
+
+	ret = ovpn_nl_msg_send(ctx, NULL);
+nla_put_failure:
+	nl_ctx_free(ctx);
+	return ret;
+}
+
+static int ovpn_handle_peer(struct nl_msg *msg, void (*arg)__always_unused)
+{
+	struct nlattr *pattrs[OVPN_A_PEER_MAX + 1];
+	struct genlmsghdr *gnlh = nlmsg_data(nlmsg_hdr(msg));
+	struct nlattr *attrs[OVPN_A_MAX + 1];
+	__u16 rport = 0, lport = 0;
+
+	nla_parse(attrs, OVPN_A_MAX, genlmsg_attrdata(gnlh, 0),
+		  genlmsg_attrlen(gnlh, 0), NULL);
+
+	if (!attrs[OVPN_A_PEER]) {
+		fprintf(stderr, "no packet content in netlink message\n");
+		return NL_SKIP;
+	}
+
+	nla_parse(pattrs, OVPN_A_PEER_MAX, nla_data(attrs[OVPN_A_PEER]),
+		  nla_len(attrs[OVPN_A_PEER]), NULL);
+
+	if (pattrs[OVPN_A_PEER_ID])
+		fprintf(stderr, "* Peer %u\n",
+			nla_get_u32(pattrs[OVPN_A_PEER_ID]));
+
+	if (pattrs[OVPN_A_PEER_SOCKET_NETNSID])
+		fprintf(stderr, "\tsocket NetNS ID: %d\n",
+			nla_get_s32(pattrs[OVPN_A_PEER_SOCKET_NETNSID]));
+
+	if (pattrs[OVPN_A_PEER_VPN_IPV4]) {
+		char buf[INET_ADDRSTRLEN];
+
+		inet_ntop(AF_INET, nla_data(pattrs[OVPN_A_PEER_VPN_IPV4]),
+			  buf, sizeof(buf));
+		fprintf(stderr, "\tVPN IPv4: %s\n", buf);
+	}
+
+	if (pattrs[OVPN_A_PEER_VPN_IPV6]) {
+		char buf[INET6_ADDRSTRLEN];
+
+		inet_ntop(AF_INET6, nla_data(pattrs[OVPN_A_PEER_VPN_IPV6]),
+			  buf, sizeof(buf));
+		fprintf(stderr, "\tVPN IPv6: %s\n", buf);
+	}
+
+	if (pattrs[OVPN_A_PEER_LOCAL_PORT])
+		lport = ntohs(nla_get_u16(pattrs[OVPN_A_PEER_LOCAL_PORT]));
+
+	if (pattrs[OVPN_A_PEER_REMOTE_PORT])
+		rport = ntohs(nla_get_u16(pattrs[OVPN_A_PEER_REMOTE_PORT]));
+
+	if (pattrs[OVPN_A_PEER_REMOTE_IPV6]) {
+		void *ip = pattrs[OVPN_A_PEER_REMOTE_IPV6];
+		char buf[INET6_ADDRSTRLEN];
+		int scope_id = -1;
+
+		if (pattrs[OVPN_A_PEER_REMOTE_IPV6_SCOPE_ID]) {
+			void *p = pattrs[OVPN_A_PEER_REMOTE_IPV6_SCOPE_ID];
+
+			scope_id = nla_get_u32(p);
+		}
+
+		inet_ntop(AF_INET6, nla_data(ip), buf, sizeof(buf));
+		fprintf(stderr, "\tRemote: %s:%hu (scope-id: %u)\n", buf, rport,
+			scope_id);
+
+		if (pattrs[OVPN_A_PEER_LOCAL_IPV6]) {
+			void *ip = pattrs[OVPN_A_PEER_LOCAL_IPV6];
+
+			inet_ntop(AF_INET6, nla_data(ip), buf, sizeof(buf));
+			fprintf(stderr, "\tLocal: %s:%hu\n", buf, lport);
+		}
+	}
+
+	if (pattrs[OVPN_A_PEER_REMOTE_IPV4]) {
+		void *ip = pattrs[OVPN_A_PEER_REMOTE_IPV4];
+		char buf[INET_ADDRSTRLEN];
+
+		inet_ntop(AF_INET, nla_data(ip), buf, sizeof(buf));
+		fprintf(stderr, "\tRemote: %s:%hu\n", buf, rport);
+
+		if (pattrs[OVPN_A_PEER_LOCAL_IPV4]) {
+			void *p = pattrs[OVPN_A_PEER_LOCAL_IPV4];
+
+			inet_ntop(AF_INET, nla_data(p), buf, sizeof(buf));
+			fprintf(stderr, "\tLocal: %s:%hu\n", buf, lport);
+		}
+	}
+
+	if (pattrs[OVPN_A_PEER_KEEPALIVE_INTERVAL]) {
+		void *p = pattrs[OVPN_A_PEER_KEEPALIVE_INTERVAL];
+
+		fprintf(stderr, "\tKeepalive interval: %u sec\n",
+			nla_get_u32(p));
+	}
+
+	if (pattrs[OVPN_A_PEER_KEEPALIVE_TIMEOUT])
+		fprintf(stderr, "\tKeepalive timeout: %u sec\n",
+			nla_get_u32(pattrs[OVPN_A_PEER_KEEPALIVE_TIMEOUT]));
+
+	if (pattrs[OVPN_A_PEER_VPN_RX_BYTES])
+		fprintf(stderr, "\tVPN RX bytes: %" PRIu64 "\n",
+			ovpn_nla_get_uint(pattrs[OVPN_A_PEER_VPN_RX_BYTES]));
+
+	if (pattrs[OVPN_A_PEER_VPN_TX_BYTES])
+		fprintf(stderr, "\tVPN TX bytes: %" PRIu64 "\n",
+			ovpn_nla_get_uint(pattrs[OVPN_A_PEER_VPN_TX_BYTES]));
+
+	if (pattrs[OVPN_A_PEER_VPN_RX_PACKETS])
+		fprintf(stderr, "\tVPN RX packets: %" PRIu64 "\n",
+			ovpn_nla_get_uint(pattrs[OVPN_A_PEER_VPN_RX_PACKETS]));
+
+	if (pattrs[OVPN_A_PEER_VPN_TX_PACKETS])
+		fprintf(stderr, "\tVPN TX packets: %" PRIu64 "\n",
+			ovpn_nla_get_uint(pattrs[OVPN_A_PEER_VPN_TX_PACKETS]));
+
+	if (pattrs[OVPN_A_PEER_LINK_RX_BYTES])
+		fprintf(stderr, "\tLINK RX bytes: %" PRIu64 "\n",
+			ovpn_nla_get_uint(pattrs[OVPN_A_PEER_LINK_RX_BYTES]));
+
+	if (pattrs[OVPN_A_PEER_LINK_TX_BYTES])
+		fprintf(stderr, "\tLINK TX bytes: %" PRIu64 "\n",
+			ovpn_nla_get_uint(pattrs[OVPN_A_PEER_LINK_TX_BYTES]));
+
+	if (pattrs[OVPN_A_PEER_LINK_RX_PACKETS])
+		fprintf(stderr, "\tLINK RX packets: %" PRIu64 "\n",
+			ovpn_nla_get_uint(pattrs[OVPN_A_PEER_LINK_RX_PACKETS]));
+
+	if (pattrs[OVPN_A_PEER_LINK_TX_PACKETS])
+		fprintf(stderr, "\tLINK TX packets: %" PRIu64 "\n",
+			ovpn_nla_get_uint(pattrs[OVPN_A_PEER_LINK_TX_PACKETS]));
+
+	return NL_SKIP;
+}
+
+static int ovpn_get_peer(struct ovpn_ctx *ovpn)
+{
+	int flags = 0, ret = -1;
+	struct nlattr *attr;
+	struct nl_ctx *ctx;
+
+	if (ovpn->peer_id == PEER_ID_UNDEF)
+		flags = NLM_F_DUMP;
+
+	ctx = nl_ctx_alloc_flags(ovpn, OVPN_CMD_PEER_GET, flags);
+	if (!ctx)
+		return -ENOMEM;
+
+	if (ovpn->peer_id != PEER_ID_UNDEF) {
+		attr = nla_nest_start(ctx->nl_msg, OVPN_A_PEER);
+		NLA_PUT_U32(ctx->nl_msg, OVPN_A_PEER_ID, ovpn->peer_id);
+		nla_nest_end(ctx->nl_msg, attr);
+	}
+
+	ret = ovpn_nl_msg_send(ctx, ovpn_handle_peer);
+nla_put_failure:
+	nl_ctx_free(ctx);
+	return ret;
+}
+
+static int ovpn_new_key(struct ovpn_ctx *ovpn)
+{
+	struct nlattr *keyconf, *key_dir;
+	struct nl_ctx *ctx;
+	int ret = -1;
+
+	ctx = nl_ctx_alloc(ovpn, OVPN_CMD_KEY_NEW);
+	if (!ctx)
+		return -ENOMEM;
+
+	keyconf = nla_nest_start(ctx->nl_msg, OVPN_A_KEYCONF);
+	NLA_PUT_U32(ctx->nl_msg, OVPN_A_KEYCONF_PEER_ID, ovpn->peer_id);
+	NLA_PUT_U32(ctx->nl_msg, OVPN_A_KEYCONF_SLOT, ovpn->key_slot);
+	NLA_PUT_U32(ctx->nl_msg, OVPN_A_KEYCONF_KEY_ID, ovpn->key_id);
+	NLA_PUT_U32(ctx->nl_msg, OVPN_A_KEYCONF_CIPHER_ALG, ovpn->cipher);
+
+	key_dir = nla_nest_start(ctx->nl_msg, OVPN_A_KEYCONF_ENCRYPT_DIR);
+	NLA_PUT(ctx->nl_msg, OVPN_A_KEYDIR_CIPHER_KEY, KEY_LEN, ovpn->key_enc);
+	NLA_PUT(ctx->nl_msg, OVPN_A_KEYDIR_NONCE_TAIL, NONCE_LEN, ovpn->nonce);
+	nla_nest_end(ctx->nl_msg, key_dir);
+
+	key_dir = nla_nest_start(ctx->nl_msg, OVPN_A_KEYCONF_DECRYPT_DIR);
+	NLA_PUT(ctx->nl_msg, OVPN_A_KEYDIR_CIPHER_KEY, KEY_LEN, ovpn->key_dec);
+	NLA_PUT(ctx->nl_msg, OVPN_A_KEYDIR_NONCE_TAIL, NONCE_LEN, ovpn->nonce);
+	nla_nest_end(ctx->nl_msg, key_dir);
+
+	nla_nest_end(ctx->nl_msg, keyconf);
+
+	ret = ovpn_nl_msg_send(ctx, NULL);
+nla_put_failure:
+	nl_ctx_free(ctx);
+	return ret;
+}
+
+static int ovpn_del_key(struct ovpn_ctx *ovpn)
+{
+	struct nlattr *keyconf;
+	struct nl_ctx *ctx;
+	int ret = -1;
+
+	ctx = nl_ctx_alloc(ovpn, OVPN_CMD_KEY_DEL);
+	if (!ctx)
+		return -ENOMEM;
+
+	keyconf = nla_nest_start(ctx->nl_msg, OVPN_A_KEYCONF);
+	NLA_PUT_U32(ctx->nl_msg, OVPN_A_KEYCONF_PEER_ID, ovpn->peer_id);
+	NLA_PUT_U32(ctx->nl_msg, OVPN_A_KEYCONF_SLOT, ovpn->key_slot);
+	nla_nest_end(ctx->nl_msg, keyconf);
+
+	ret = ovpn_nl_msg_send(ctx, NULL);
+nla_put_failure:
+	nl_ctx_free(ctx);
+	return ret;
+}
+
+static int ovpn_handle_key(struct nl_msg *msg, void (*arg)__always_unused)
+{
+	struct nlattr *kattrs[OVPN_A_KEYCONF_MAX + 1];
+	struct genlmsghdr *gnlh = nlmsg_data(nlmsg_hdr(msg));
+	struct nlattr *attrs[OVPN_A_MAX + 1];
+
+	nla_parse(attrs, OVPN_A_MAX, genlmsg_attrdata(gnlh, 0),
+		  genlmsg_attrlen(gnlh, 0), NULL);
+
+	if (!attrs[OVPN_A_KEYCONF]) {
+		fprintf(stderr, "no packet content in netlink message\n");
+		return NL_SKIP;
+	}
+
+	nla_parse(kattrs, OVPN_A_KEYCONF_MAX, nla_data(attrs[OVPN_A_KEYCONF]),
+		  nla_len(attrs[OVPN_A_KEYCONF]), NULL);
+
+	if (kattrs[OVPN_A_KEYCONF_PEER_ID])
+		fprintf(stderr, "* Peer %u\n",
+			nla_get_u32(kattrs[OVPN_A_KEYCONF_PEER_ID]));
+	if (kattrs[OVPN_A_KEYCONF_SLOT]) {
+		fprintf(stderr, "\t- Slot: ");
+		switch (nla_get_u32(kattrs[OVPN_A_KEYCONF_SLOT])) {
+		case OVPN_KEY_SLOT_PRIMARY:
+			fprintf(stderr, "primary\n");
+			break;
+		case OVPN_KEY_SLOT_SECONDARY:
+			fprintf(stderr, "secondary\n");
+			break;
+		default:
+			fprintf(stderr, "invalid (%u)\n",
+				nla_get_u32(kattrs[OVPN_A_KEYCONF_SLOT]));
+			break;
+		}
+	}
+	if (kattrs[OVPN_A_KEYCONF_KEY_ID])
+		fprintf(stderr, "\t- Key ID: %u\n",
+			nla_get_u32(kattrs[OVPN_A_KEYCONF_KEY_ID]));
+	if (kattrs[OVPN_A_KEYCONF_CIPHER_ALG]) {
+		fprintf(stderr, "\t- Cipher: ");
+		switch (nla_get_u32(kattrs[OVPN_A_KEYCONF_CIPHER_ALG])) {
+		case OVPN_CIPHER_ALG_NONE:
+			fprintf(stderr, "none\n");
+			break;
+		case OVPN_CIPHER_ALG_AES_GCM:
+			fprintf(stderr, "aes-gcm\n");
+			break;
+		case OVPN_CIPHER_ALG_CHACHA20_POLY1305:
+			fprintf(stderr, "chacha20poly1305\n");
+			break;
+		default:
+			fprintf(stderr, "invalid (%u)\n",
+				nla_get_u32(kattrs[OVPN_A_KEYCONF_CIPHER_ALG]));
+			break;
+		}
+	}
+
+	return NL_SKIP;
+}
+
+static int ovpn_get_key(struct ovpn_ctx *ovpn)
+{
+	struct nlattr *keyconf;
+	struct nl_ctx *ctx;
+	int ret = -1;
+
+	ctx = nl_ctx_alloc(ovpn, OVPN_CMD_KEY_GET);
+	if (!ctx)
+		return -ENOMEM;
+
+	keyconf = nla_nest_start(ctx->nl_msg, OVPN_A_KEYCONF);
+	NLA_PUT_U32(ctx->nl_msg, OVPN_A_KEYCONF_PEER_ID, ovpn->peer_id);
+	NLA_PUT_U32(ctx->nl_msg, OVPN_A_KEYCONF_SLOT, ovpn->key_slot);
+	nla_nest_end(ctx->nl_msg, keyconf);
+
+	ret = ovpn_nl_msg_send(ctx, ovpn_handle_key);
+nla_put_failure:
+	nl_ctx_free(ctx);
+	return ret;
+}
+
+static int ovpn_swap_keys(struct ovpn_ctx *ovpn)
+{
+	struct nl_ctx *ctx;
+	struct nlattr *kc;
+	int ret = -1;
+
+	ctx = nl_ctx_alloc(ovpn, OVPN_CMD_KEY_SWAP);
+	if (!ctx)
+		return -ENOMEM;
+
+	kc = nla_nest_start(ctx->nl_msg, OVPN_A_KEYCONF);
+	NLA_PUT_U32(ctx->nl_msg, OVPN_A_KEYCONF_PEER_ID, ovpn->peer_id);
+	nla_nest_end(ctx->nl_msg, kc);
+
+	ret = ovpn_nl_msg_send(ctx, NULL);
+nla_put_failure:
+	nl_ctx_free(ctx);
+	return ret;
+}
+
+/* Helper function used to easily add attributes to a rtnl message */
+static int ovpn_addattr(struct nlmsghdr *n, int maxlen, int type,
+			const void *data, int alen)
+{
+	int len = RTA_LENGTH(alen);
+	struct rtattr *rta;
+
+	if ((int)(NLMSG_ALIGN(n->nlmsg_len) + RTA_ALIGN(len)) > maxlen)	{
+		fprintf(stderr, "%s: rtnl: message exceeded bound of %d\n",
+			__func__, maxlen);
+		return -EMSGSIZE;
+	}
+
+	rta = nlmsg_tail(n);
+	rta->rta_type = type;
+	rta->rta_len = len;
+
+	if (!data)
+		memset(RTA_DATA(rta), 0, alen);
+	else
+		memcpy(RTA_DATA(rta), data, alen);
+
+	n->nlmsg_len = NLMSG_ALIGN(n->nlmsg_len) + RTA_ALIGN(len);
+
+	return 0;
+}
+
+static struct rtattr *ovpn_nest_start(struct nlmsghdr *msg, size_t max_size,
+				      int attr)
+{
+	struct rtattr *nest = nlmsg_tail(msg);
+
+	if (ovpn_addattr(msg, max_size, attr, NULL, 0) < 0)
+		return NULL;
+
+	return nest;
+}
+
+static void ovpn_nest_end(struct nlmsghdr *msg, struct rtattr *nest)
+{
+	nest->rta_len = (uint8_t *)nlmsg_tail(msg) - (uint8_t *)nest;
+}
+
+#define RT_SNDBUF_SIZE (1024 * 2)
+#define RT_RCVBUF_SIZE (1024 * 4)
+
+/* Open RTNL socket */
+static int ovpn_rt_socket(void)
+{
+	int sndbuf = RT_SNDBUF_SIZE, rcvbuf = RT_RCVBUF_SIZE, fd;
+
+	fd = socket(AF_NETLINK, SOCK_RAW, NETLINK_ROUTE);
+	if (fd < 0) {
+		fprintf(stderr, "%s: cannot open netlink socket\n", __func__);
+		return fd;
+	}
+
+	if (setsockopt(fd, SOL_SOCKET, SO_SNDBUF, &sndbuf,
+		       sizeof(sndbuf)) < 0) {
+		fprintf(stderr, "%s: SO_SNDBUF\n", __func__);
+		close(fd);
+		return -1;
+	}
+
+	if (setsockopt(fd, SOL_SOCKET, SO_RCVBUF, &rcvbuf,
+		       sizeof(rcvbuf)) < 0) {
+		fprintf(stderr, "%s: SO_RCVBUF\n", __func__);
+		close(fd);
+		return -1;
+	}
+
+	return fd;
+}
+
+/* Bind socket to Netlink subsystem */
+static int ovpn_rt_bind(int fd, uint32_t groups)
+{
+	struct sockaddr_nl local = { 0 };
+	socklen_t addr_len;
+
+	local.nl_family = AF_NETLINK;
+	local.nl_groups = groups;
+
+	if (bind(fd, (struct sockaddr *)&local, sizeof(local)) < 0) {
+		fprintf(stderr, "%s: cannot bind netlink socket: %d\n",
+			__func__, errno);
+		return -errno;
+	}
+
+	addr_len = sizeof(local);
+	if (getsockname(fd, (struct sockaddr *)&local, &addr_len) < 0) {
+		fprintf(stderr, "%s: cannot getsockname: %d\n", __func__,
+			errno);
+		return -errno;
+	}
+
+	if (addr_len != sizeof(local)) {
+		fprintf(stderr, "%s: wrong address length %d\n", __func__,
+			addr_len);
+		return -EINVAL;
+	}
+
+	if (local.nl_family != AF_NETLINK) {
+		fprintf(stderr, "%s: wrong address family %d\n", __func__,
+			local.nl_family);
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+typedef int (*ovpn_parse_reply_cb)(struct nlmsghdr *msg, void *arg);
+
+/* Send Netlink message and run callback on reply (if specified) */
+static int ovpn_rt_send(struct nlmsghdr *payload, pid_t peer,
+			unsigned int groups, ovpn_parse_reply_cb cb,
+			void *arg_cb)
+{
+	int len, rem_len, fd, ret, rcv_len;
+	struct sockaddr_nl nladdr = { 0 };
+	struct nlmsgerr *err;
+	struct nlmsghdr *h;
+	char buf[1024 * 16];
+	struct iovec iov = {
+		.iov_base = payload,
+		.iov_len = payload->nlmsg_len,
+	};
+	struct msghdr nlmsg = {
+		.msg_name = &nladdr,
+		.msg_namelen = sizeof(nladdr),
+		.msg_iov = &iov,
+		.msg_iovlen = 1,
+	};
+
+	nladdr.nl_family = AF_NETLINK;
+	nladdr.nl_pid = peer;
+	nladdr.nl_groups = groups;
+
+	payload->nlmsg_seq = time(NULL);
+
+	/* no need to send reply */
+	if (!cb)
+		payload->nlmsg_flags |= NLM_F_ACK;
+
+	fd = ovpn_rt_socket();
+	if (fd < 0) {
+		fprintf(stderr, "%s: can't open rtnl socket\n", __func__);
+		return -errno;
+	}
+
+	ret = ovpn_rt_bind(fd, 0);
+	if (ret < 0) {
+		fprintf(stderr, "%s: can't bind rtnl socket\n", __func__);
+		ret = -errno;
+		goto out;
+	}
+
+	ret = sendmsg(fd, &nlmsg, 0);
+	if (ret < 0) {
+		fprintf(stderr, "%s: rtnl: error on sendmsg()\n", __func__);
+		ret = -errno;
+		goto out;
+	}
+
+	/* prepare buffer to store RTNL replies */
+	memset(buf, 0, sizeof(buf));
+	iov.iov_base = buf;
+
+	while (1) {
+		/*
+		 * iov_len is modified by recvmsg(), therefore has to be initialized before
+		 * using it again
+		 */
+		iov.iov_len = sizeof(buf);
+		rcv_len = recvmsg(fd, &nlmsg, 0);
+		if (rcv_len < 0) {
+			if (errno == EINTR || errno == EAGAIN) {
+				fprintf(stderr, "%s: interrupted call\n",
+					__func__);
+				continue;
+			}
+			fprintf(stderr, "%s: rtnl: error on recvmsg()\n",
+				__func__);
+			ret = -errno;
+			goto out;
+		}
+
+		if (rcv_len == 0) {
+			fprintf(stderr,
+				"%s: rtnl: socket reached unexpected EOF\n",
+				__func__);
+			ret = -EIO;
+			goto out;
+		}
+
+		if (nlmsg.msg_namelen != sizeof(nladdr)) {
+			fprintf(stderr,
+				"%s: sender address length: %u (expected %zu)\n",
+				__func__, nlmsg.msg_namelen, sizeof(nladdr));
+			ret = -EIO;
+			goto out;
+		}
+
+		h = (struct nlmsghdr *)buf;
+		while (rcv_len >= (int)sizeof(*h)) {
+			len = h->nlmsg_len;
+			rem_len = len - sizeof(*h);
+
+			if (rem_len < 0 || len > rcv_len) {
+				if (nlmsg.msg_flags & MSG_TRUNC) {
+					fprintf(stderr, "%s: truncated message\n",
+						__func__);
+					ret = -EIO;
+					goto out;
+				}
+				fprintf(stderr, "%s: malformed message: len=%d\n",
+					__func__, len);
+				ret = -EIO;
+				goto out;
+			}
+
+			if (h->nlmsg_type == NLMSG_DONE) {
+				ret = 0;
+				goto out;
+			}
+
+			if (h->nlmsg_type == NLMSG_ERROR) {
+				err = (struct nlmsgerr *)NLMSG_DATA(h);
+				if (rem_len < (int)sizeof(struct nlmsgerr)) {
+					fprintf(stderr, "%s: ERROR truncated\n",
+						__func__);
+					ret = -EIO;
+					goto out;
+				}
+
+				if (err->error) {
+					fprintf(stderr, "%s: (%d) %s\n",
+						__func__, err->error,
+						strerror(-err->error));
+					ret = err->error;
+					goto out;
+				}
+
+				ret = 0;
+				if (cb)	{
+					int r = cb(h, arg_cb);
+
+					if (r <= 0)
+						ret = r;
+				}
+				goto out;
+			}
+
+			if (cb) {
+				int r = cb(h, arg_cb);
+
+				if (r <= 0) {
+					ret = r;
+					goto out;
+				}
+			} else {
+				fprintf(stderr, "%s: RTNL: unexpected reply\n",
+					__func__);
+			}
+
+			rcv_len -= NLMSG_ALIGN(len);
+			h = (struct nlmsghdr *)((uint8_t *)h +
+						NLMSG_ALIGN(len));
+		}
+
+		if (nlmsg.msg_flags & MSG_TRUNC) {
+			fprintf(stderr, "%s: message truncated\n", __func__);
+			continue;
+		}
+
+		if (rcv_len) {
+			fprintf(stderr, "%s: rtnl: %d not parsed bytes\n",
+				__func__, rcv_len);
+			ret = -1;
+			goto out;
+		}
+	}
+out:
+	close(fd);
+
+	return ret;
+}
+
+struct ovpn_link_req {
+	struct nlmsghdr n;
+	struct ifinfomsg i;
+	char buf[256];
+};
+
+static int ovpn_new_iface(struct ovpn_ctx *ovpn)
+{
+	struct rtattr *linkinfo, *data;
+	struct ovpn_link_req req = { 0 };
+	int ret = -1;
+
+	fprintf(stdout, "Creating interface %s with mode %u\n", ovpn->ifname,
+		ovpn->mode);
+
+	req.n.nlmsg_len = NLMSG_LENGTH(sizeof(req.i));
+	req.n.nlmsg_flags = NLM_F_REQUEST | NLM_F_CREATE | NLM_F_EXCL;
+	req.n.nlmsg_type = RTM_NEWLINK;
+
+	if (ovpn_addattr(&req.n, sizeof(req), IFLA_IFNAME, ovpn->ifname,
+			 strlen(ovpn->ifname) + 1) < 0)
+		goto err;
+
+	linkinfo = ovpn_nest_start(&req.n, sizeof(req), IFLA_LINKINFO);
+	if (!linkinfo)
+		goto err;
+
+	if (ovpn_addattr(&req.n, sizeof(req), IFLA_INFO_KIND, OVPN_FAMILY_NAME,
+			 strlen(OVPN_FAMILY_NAME) + 1) < 0)
+		goto err;
+
+	if (ovpn->mode_set) {
+		data = ovpn_nest_start(&req.n, sizeof(req), IFLA_INFO_DATA);
+		if (!data)
+			goto err;
+
+		if (ovpn_addattr(&req.n, sizeof(req), IFLA_OVPN_MODE,
+				 &ovpn->mode, sizeof(uint8_t)) < 0)
+			goto err;
+
+		ovpn_nest_end(&req.n, data);
+	}
+
+	ovpn_nest_end(&req.n, linkinfo);
+
+	req.i.ifi_family = AF_PACKET;
+
+	ret = ovpn_rt_send(&req.n, 0, 0, NULL, NULL);
+err:
+	return ret;
+}
+
+static int ovpn_del_iface(struct ovpn_ctx *ovpn)
+{
+	struct ovpn_link_req req = { 0 };
+
+	fprintf(stdout, "Deleting interface %s ifindex %u\n", ovpn->ifname,
+		ovpn->ifindex);
+
+	req.n.nlmsg_len = NLMSG_LENGTH(sizeof(req.i));
+	req.n.nlmsg_flags = NLM_F_REQUEST;
+	req.n.nlmsg_type = RTM_DELLINK;
+
+	req.i.ifi_family = AF_PACKET;
+	req.i.ifi_index = ovpn->ifindex;
+
+	return ovpn_rt_send(&req.n, 0, 0, NULL, NULL);
+}
+
+static int nl_seq_check(struct nl_msg (*msg)__always_unused,
+			void (*arg)__always_unused)
+{
+	return NL_OK;
+}
+
+struct mcast_handler_args {
+	const char *group;
+	int id;
+};
+
+static int mcast_family_handler(struct nl_msg *msg, void *arg)
+{
+	struct mcast_handler_args *grp = arg;
+	struct nlattr *tb[CTRL_ATTR_MAX + 1];
+	struct genlmsghdr *gnlh = nlmsg_data(nlmsg_hdr(msg));
+	struct nlattr *mcgrp;
+	int rem_mcgrp;
+
+	nla_parse(tb, CTRL_ATTR_MAX, genlmsg_attrdata(gnlh, 0),
+		  genlmsg_attrlen(gnlh, 0), NULL);
+
+	if (!tb[CTRL_ATTR_MCAST_GROUPS])
+		return NL_SKIP;
+
+	nla_for_each_nested(mcgrp, tb[CTRL_ATTR_MCAST_GROUPS], rem_mcgrp) {
+		struct nlattr *tb_mcgrp[CTRL_ATTR_MCAST_GRP_MAX + 1];
+
+		nla_parse(tb_mcgrp, CTRL_ATTR_MCAST_GRP_MAX,
+			  nla_data(mcgrp), nla_len(mcgrp), NULL);
+
+		if (!tb_mcgrp[CTRL_ATTR_MCAST_GRP_NAME] ||
+		    !tb_mcgrp[CTRL_ATTR_MCAST_GRP_ID])
+			continue;
+		if (strncmp(nla_data(tb_mcgrp[CTRL_ATTR_MCAST_GRP_NAME]),
+			    grp->group, nla_len(tb_mcgrp[CTRL_ATTR_MCAST_GRP_NAME])))
+			continue;
+		grp->id = nla_get_u32(tb_mcgrp[CTRL_ATTR_MCAST_GRP_ID]);
+		break;
+	}
+
+	return NL_SKIP;
+}
+
+static int mcast_error_handler(struct sockaddr_nl (*nla)__always_unused,
+			       struct nlmsgerr *err, void *arg)
+{
+	int *ret = arg;
+
+	*ret = err->error;
+	return NL_STOP;
+}
+
+static int mcast_ack_handler(struct nl_msg (*msg)__always_unused, void *arg)
+{
+	int *ret = arg;
+
+	*ret = 0;
+	return NL_STOP;
+}
+
+static int ovpn_handle_msg(struct nl_msg *msg, void *arg)
+{
+	struct genlmsghdr *gnlh = nlmsg_data(nlmsg_hdr(msg));
+	struct nlattr *attrs[OVPN_A_MAX + 1];
+	struct nlmsghdr *nlh = nlmsg_hdr(msg);
+	char ifname[IF_NAMESIZE];
+	int *ret = arg;
+	__u32 ifindex;
+
+	fprintf(stderr, "received message from ovpn-dco\n");
+
+	*ret = -1;
+
+	if (!genlmsg_valid_hdr(nlh, 0)) {
+		fprintf(stderr, "invalid header\n");
+		return NL_STOP;
+	}
+
+	if (nla_parse(attrs, OVPN_A_MAX, genlmsg_attrdata(gnlh, 0),
+		      genlmsg_attrlen(gnlh, 0), NULL)) {
+		fprintf(stderr, "received bogus data from ovpn-dco\n");
+		return NL_STOP;
+	}
+
+	if (!attrs[OVPN_A_IFINDEX]) {
+		fprintf(stderr, "no ifindex in this message\n");
+		return NL_STOP;
+	}
+
+	ifindex = nla_get_u32(attrs[OVPN_A_IFINDEX]);
+	if (!if_indextoname(ifindex, ifname)) {
+		fprintf(stderr, "cannot resolve ifname for ifindex: %u\n",
+			ifindex);
+		return NL_STOP;
+	}
+
+	switch (gnlh->cmd) {
+	case OVPN_CMD_PEER_DEL_NTF:
+		fprintf(stdout, "received CMD_PEER_DEL_NTF\n");
+		break;
+	case OVPN_CMD_KEY_SWAP_NTF:
+		fprintf(stdout, "received CMD_KEY_SWAP_NTF\n");
+		break;
+	default:
+		fprintf(stderr, "received unknown command: %d\n", gnlh->cmd);
+		return NL_STOP;
+	}
+
+	*ret = 0;
+	return NL_OK;
+}
+
+static int ovpn_get_mcast_id(struct nl_sock *sock, const char *family,
+			     const char *group)
+{
+	struct nl_msg *msg;
+	struct nl_cb *cb;
+	int ret, ctrlid;
+	struct mcast_handler_args grp = {
+		.group = group,
+		.id = -ENOENT,
+	};
+
+	msg = nlmsg_alloc();
+	if (!msg)
+		return -ENOMEM;
+
+	cb = nl_cb_alloc(NL_CB_DEFAULT);
+	if (!cb) {
+		ret = -ENOMEM;
+		goto out_fail_cb;
+	}
+
+	ctrlid = genl_ctrl_resolve(sock, "nlctrl");
+
+	genlmsg_put(msg, 0, 0, ctrlid, 0, 0, CTRL_CMD_GETFAMILY, 0);
+
+	ret = -ENOBUFS;
+	NLA_PUT_STRING(msg, CTRL_ATTR_FAMILY_NAME, family);
+
+	ret = nl_send_auto_complete(sock, msg);
+	if (ret < 0)
+		goto nla_put_failure;
+
+	ret = 1;
+
+	nl_cb_err(cb, NL_CB_CUSTOM, mcast_error_handler, &ret);
+	nl_cb_set(cb, NL_CB_ACK, NL_CB_CUSTOM, mcast_ack_handler, &ret);
+	nl_cb_set(cb, NL_CB_VALID, NL_CB_CUSTOM, mcast_family_handler, &grp);
+
+	while (ret > 0)
+		nl_recvmsgs(sock, cb);
+
+	if (ret == 0)
+		ret = grp.id;
+ nla_put_failure:
+	nl_cb_put(cb);
+ out_fail_cb:
+	nlmsg_free(msg);
+	return ret;
+}
+
+static int ovpn_listen_mcast(void)
+{
+	struct nl_sock *sock;
+	struct nl_cb *cb;
+	int mcid, ret;
+
+	sock = nl_socket_alloc();
+	if (!sock) {
+		fprintf(stderr, "cannot allocate netlink socket\n");
+		goto err_free;
+	}
+
+	nl_socket_set_buffer_size(sock, 8192, 8192);
+
+	ret = genl_connect(sock);
+	if (ret < 0) {
+		fprintf(stderr, "cannot connect to generic netlink: %s\n",
+			nl_geterror(ret));
+		goto err_free;
+	}
+
+	mcid = ovpn_get_mcast_id(sock, OVPN_FAMILY_NAME, OVPN_MCGRP_PEERS);
+	if (mcid < 0) {
+		fprintf(stderr, "cannot get mcast group: %s\n",
+			nl_geterror(mcid));
+		goto err_free;
+	}
+
+	ret = nl_socket_add_membership(sock, mcid);
+	if (ret) {
+		fprintf(stderr, "failed to join mcast group: %d\n", ret);
+		goto err_free;
+	}
+
+	ret = 1;
+	cb = nl_cb_alloc(NL_CB_DEFAULT);
+	nl_cb_set(cb, NL_CB_SEQ_CHECK, NL_CB_CUSTOM, nl_seq_check, NULL);
+	nl_cb_set(cb, NL_CB_VALID, NL_CB_CUSTOM, ovpn_handle_msg, &ret);
+	nl_cb_err(cb, NL_CB_CUSTOM, ovpn_nl_cb_error, &ret);
+
+	while (ret == 1) {
+		int err = nl_recvmsgs(sock, cb);
+
+		if (err < 0) {
+			fprintf(stderr,
+				"cannot receive netlink message: (%d) %s\n",
+				err, nl_geterror(-err));
+			ret = -1;
+			break;
+		}
+	}
+
+	nl_cb_put(cb);
+err_free:
+	nl_socket_free(sock);
+	return ret;
+}
+
+static void usage(const char *cmd)
+{
+	fprintf(stderr,
+		"Usage %s <command> <iface> [arguments..]\n",
+		cmd);
+	fprintf(stderr, "where <command> can be one of the following\n\n");
+
+	fprintf(stderr, "* new_iface <iface> [mode]: create new ovpn interface\n");
+	fprintf(stderr, "\tiface: ovpn interface name\n");
+	fprintf(stderr, "\tmode:\n");
+	fprintf(stderr, "\t\t- P2P for peer-to-peer mode (i.e. client)\n");
+	fprintf(stderr, "\t\t- MP for multi-peer mode (i.e. server)\n");
+
+	fprintf(stderr, "* del_iface <iface>: delete ovpn interface\n");
+	fprintf(stderr, "\tiface: ovpn interface name\n");
+
+	fprintf(stderr,
+		"* listen <iface> <lport> <peers_file> [ipv6]: listen for incoming peer TCP connections\n");
+	fprintf(stderr, "\tiface: ovpn interface name\n");
+	fprintf(stderr, "\tlport: TCP port to listen to\n");
+	fprintf(stderr,
+		"\tpeers_file: file containing one peer per line: Line format:\n");
+	fprintf(stderr, "\t\t<peer_id> <vpnaddr>\n");
+	fprintf(stderr,
+		"\tipv6: whether the socket should listen to the IPv6 wildcard address\n");
+
+	fprintf(stderr,
+		"* connect <iface> <peer_id> <raddr> <rport> [key_file]: start connecting peer of TCP-based VPN session\n");
+	fprintf(stderr, "\tiface: ovpn interface name\n");
+	fprintf(stderr, "\tpeer_id: peer ID of the connecting peer\n");
+	fprintf(stderr, "\traddr: peer IP address to connect to\n");
+	fprintf(stderr, "\trport: peer TCP port to connect to\n");
+	fprintf(stderr,
+		"\tkey_file: file containing the symmetric key for encryption\n");
+
+	fprintf(stderr,
+		"* new_peer <iface> <peer_id> <lport> <raddr> <rport> [vpnaddr]: add new peer\n");
+	fprintf(stderr, "\tiface: ovpn interface name\n");
+	fprintf(stderr, "\tlport: local UDP port to bind to\n");
+	fprintf(stderr,
+		"\tpeer_id: peer ID to be used in data packets to/from this peer\n");
+	fprintf(stderr, "\traddr: peer IP address\n");
+	fprintf(stderr, "\trport: peer UDP port\n");
+	fprintf(stderr, "\tvpnaddr: peer VPN IP\n");
+
+	fprintf(stderr,
+		"* new_multi_peer <iface> <lport> <peers_file>: add multiple peers as listed in the file\n");
+	fprintf(stderr, "\tiface: ovpn interface name\n");
+	fprintf(stderr, "\tlport: local UDP port to bind to\n");
+	fprintf(stderr,
+		"\tpeers_file: text file containing one peer per line. Line format:\n");
+	fprintf(stderr, "\t\t<peer_id> <raddr> <rport> <vpnaddr>\n");
+
+	fprintf(stderr,
+		"* set_peer <iface> <peer_id> <keepalive_interval> <keepalive_timeout>: set peer attributes\n");
+	fprintf(stderr, "\tiface: ovpn interface name\n");
+	fprintf(stderr, "\tpeer_id: peer ID of the peer to modify\n");
+	fprintf(stderr,
+		"\tkeepalive_interval: interval for sending ping messages\n");
+	fprintf(stderr,
+		"\tkeepalive_timeout: time after which a peer is timed out\n");
+
+	fprintf(stderr, "* del_peer <iface> <peer_id>: delete peer\n");
+	fprintf(stderr, "\tiface: ovpn interface name\n");
+	fprintf(stderr, "\tpeer_id: peer ID of the peer to delete\n");
+
+	fprintf(stderr, "* get_peer <iface> [peer_id]: retrieve peer(s) status\n");
+	fprintf(stderr, "\tiface: ovpn interface name\n");
+	fprintf(stderr,
+		"\tpeer_id: peer ID of the peer to query. All peers are returned if omitted\n");
+
+	fprintf(stderr,
+		"* new_key <iface> <peer_id> <slot> <key_id> <cipher> <key_dir> <key_file>: set data channel key\n");
+	fprintf(stderr, "\tiface: ovpn interface name\n");
+	fprintf(stderr,
+		"\tpeer_id: peer ID of the peer to configure the key for\n");
+	fprintf(stderr, "\tslot: either 1 (primary) or 2 (secondary)\n");
+	fprintf(stderr, "\tkey_id: an ID from 0 to 7\n");
+	fprintf(stderr,
+		"\tcipher: cipher to use, supported: aes (AES-GCM), chachapoly (CHACHA20POLY1305)\n");
+	fprintf(stderr,
+		"\tkey_dir: key direction, must 0 on one host and 1 on the other\n");
+	fprintf(stderr, "\tkey_file: file containing the pre-shared key\n");
+
+	fprintf(stderr,
+		"* del_key <iface> <peer_id> [slot]: erase existing data channel key\n");
+	fprintf(stderr, "\tiface: ovpn interface name\n");
+	fprintf(stderr, "\tpeer_id: peer ID of the peer to modify\n");
+	fprintf(stderr, "\tslot: slot to erase. PRIMARY if omitted\n");
+
+	fprintf(stderr,
+		"* get_key <iface> <peer_id> <slot>: retrieve non sensible key data\n");
+	fprintf(stderr, "\tiface: ovpn interface name\n");
+	fprintf(stderr, "\tpeer_id: peer ID of the peer to query\n");
+	fprintf(stderr, "\tslot: either 1 (primary) or 2 (secondary)\n");
+
+	fprintf(stderr,
+		"* swap_keys <iface> <peer_id>: swap content of primary and secondary key slots\n");
+	fprintf(stderr, "\tiface: ovpn interface name\n");
+	fprintf(stderr, "\tpeer_id: peer ID of the peer to modify\n");
+
+	fprintf(stderr,
+		"* listen_mcast: listen to ovpn netlink multicast messages\n");
+}
+
+static int ovpn_parse_remote(struct ovpn_ctx *ovpn, const char *host,
+			     const char *service, const char *vpnip)
+{
+	int ret;
+	struct addrinfo *result;
+	struct addrinfo hints = {
+		.ai_family = ovpn->sa_family,
+		.ai_socktype = SOCK_DGRAM,
+		.ai_protocol = IPPROTO_UDP
+	};
+
+	if (host) {
+		ret = getaddrinfo(host, service, &hints, &result);
+		if (ret) {
+			fprintf(stderr, "getaddrinfo on remote error: %s\n",
+				gai_strerror(ret));
+			return -1;
+		}
+
+		if (!(result->ai_family == AF_INET &&
+		      result->ai_addrlen == sizeof(struct sockaddr_in)) &&
+		    !(result->ai_family == AF_INET6 &&
+		      result->ai_addrlen == sizeof(struct sockaddr_in6))) {
+			ret = -EINVAL;
+			goto out;
+		}
+
+		memcpy(&ovpn->remote, result->ai_addr, result->ai_addrlen);
+	}
+
+	if (vpnip) {
+		ret = getaddrinfo(vpnip, NULL, &hints, &result);
+		if (ret) {
+			fprintf(stderr, "getaddrinfo on vpnip error: %s\n",
+				gai_strerror(ret));
+			return -1;
+		}
+
+		if (!(result->ai_family == AF_INET &&
+		      result->ai_addrlen == sizeof(struct sockaddr_in)) &&
+		    !(result->ai_family == AF_INET6 &&
+		      result->ai_addrlen == sizeof(struct sockaddr_in6))) {
+			ret = -EINVAL;
+			goto out;
+		}
+
+		memcpy(&ovpn->peer_ip, result->ai_addr, result->ai_addrlen);
+		ovpn->sa_family = result->ai_family;
+
+		ovpn->peer_ip_set = true;
+	}
+
+	ret = 0;
+out:
+	freeaddrinfo(result);
+	return ret;
+}
+
+static int ovpn_parse_new_peer(struct ovpn_ctx *ovpn, const char *peer_id,
+			       const char *raddr, const char *rport,
+			       const char *vpnip)
+{
+	ovpn->peer_id = strtoul(peer_id, NULL, 10);
+	if (errno == ERANGE || ovpn->peer_id > PEER_ID_UNDEF) {
+		fprintf(stderr, "peer ID value out of range\n");
+		return -1;
+	}
+
+	return ovpn_parse_remote(ovpn, raddr, rport, vpnip);
+}
+
+static int ovpn_parse_key_slot(const char *arg, struct ovpn_ctx *ovpn)
+{
+	int slot = strtoul(arg, NULL, 10);
+
+	if (errno == ERANGE || slot < 1 || slot > 2) {
+		fprintf(stderr, "key slot out of range\n");
+		return -1;
+	}
+
+	switch (slot) {
+	case 1:
+		ovpn->key_slot = OVPN_KEY_SLOT_PRIMARY;
+		break;
+	case 2:
+		ovpn->key_slot = OVPN_KEY_SLOT_SECONDARY;
+		break;
+	}
+
+	return 0;
+}
+
+static int ovpn_send_tcp_data(int socket)
+{
+	uint16_t len = htons(1000);
+	uint8_t buf[1002];
+	int ret;
+
+	memcpy(buf, &len, sizeof(len));
+	memset(buf + sizeof(len), 0x86, sizeof(buf) - sizeof(len));
+
+	ret = send(socket, buf, sizeof(buf), MSG_NOSIGNAL);
+
+	fprintf(stdout, "Sent %u bytes over TCP socket\n", ret);
+
+	return ret > 0 ? 0 : ret;
+}
+
+static int ovpn_recv_tcp_data(int socket)
+{
+	uint8_t buf[1002];
+	uint16_t len;
+	int ret;
+
+	ret = recv(socket, buf, sizeof(buf), MSG_NOSIGNAL);
+
+	if (ret < 2) {
+		fprintf(stderr, ">>>> Error while reading TCP data: %d\n", ret);
+		return ret;
+	}
+
+	memcpy(&len, buf, sizeof(len));
+	len = ntohs(len);
+
+	fprintf(stdout, ">>>> Received %u bytes over TCP socket, header: %u\n",
+		ret, len);
+
+	return 0;
+}
+
+static enum ovpn_cmd ovpn_parse_cmd(const char *cmd)
+{
+	if (!strcmp(cmd, "new_iface"))
+		return CMD_NEW_IFACE;
+
+	if (!strcmp(cmd, "del_iface"))
+		return CMD_DEL_IFACE;
+
+	if (!strcmp(cmd, "listen"))
+		return CMD_LISTEN;
+
+	if (!strcmp(cmd, "connect"))
+		return CMD_CONNECT;
+
+	if (!strcmp(cmd, "new_peer"))
+		return CMD_NEW_PEER;
+
+	if (!strcmp(cmd, "new_multi_peer"))
+		return CMD_NEW_MULTI_PEER;
+
+	if (!strcmp(cmd, "set_peer"))
+		return CMD_SET_PEER;
+
+	if (!strcmp(cmd, "del_peer"))
+		return CMD_DEL_PEER;
+
+	if (!strcmp(cmd, "get_peer"))
+		return CMD_GET_PEER;
+
+	if (!strcmp(cmd, "new_key"))
+		return CMD_NEW_KEY;
+
+	if (!strcmp(cmd, "del_key"))
+		return CMD_DEL_KEY;
+
+	if (!strcmp(cmd, "get_key"))
+		return CMD_GET_KEY;
+
+	if (!strcmp(cmd, "swap_keys"))
+		return CMD_SWAP_KEYS;
+
+	if (!strcmp(cmd, "listen_mcast"))
+		return CMD_LISTEN_MCAST;
+
+	return CMD_INVALID;
+}
+
+/* Send process to background and waits for signal.
+ *
+ * This helper is called at the end of commands
+ * creating sockets, so that the latter stay alive
+ * along with the process that created them.
+ *
+ * A signal is expected to be delivered in order to
+ * terminate the waiting processes
+ */
+static void ovpn_waitbg(void)
+{
+	daemon(1, 1);
+	pause();
+}
+
+static int ovpn_run_cmd(struct ovpn_ctx *ovpn)
+{
+	char peer_id[10], vpnip[INET6_ADDRSTRLEN], laddr[128], lport[10];
+	char raddr[128], rport[10];
+	int n, ret;
+	FILE *fp;
+
+	switch (ovpn->cmd) {
+	case CMD_NEW_IFACE:
+		ret = ovpn_new_iface(ovpn);
+		break;
+	case CMD_DEL_IFACE:
+		ret = ovpn_del_iface(ovpn);
+		break;
+	case CMD_LISTEN:
+		ret = ovpn_listen(ovpn, ovpn->sa_family);
+		if (ret < 0) {
+			fprintf(stderr, "cannot listen on TCP socket\n");
+			return ret;
+		}
+
+		fp = fopen(ovpn->peers_file, "r");
+		if (!fp) {
+			fprintf(stderr, "cannot open file: %s\n",
+				ovpn->peers_file);
+			return -1;
+		}
+
+		int num_peers = 0;
+
+		while ((n = fscanf(fp, "%s %s\n", peer_id, vpnip)) == 2) {
+			struct ovpn_ctx peer_ctx = { 0 };
+
+			if (num_peers == MAX_PEERS) {
+				fprintf(stderr, "max peers reached!\n");
+				return -E2BIG;
+			}
+
+			peer_ctx.ifindex = ovpn->ifindex;
+			peer_ctx.sa_family = ovpn->sa_family;
+
+			peer_ctx.socket = ovpn_accept(ovpn);
+			if (peer_ctx.socket < 0) {
+				fprintf(stderr, "cannot accept connection!\n");
+				return -1;
+			}
+
+			/* store peer sockets to test TCP I/O */
+			ovpn->cli_sockets[num_peers] = peer_ctx.socket;
+
+			ret = ovpn_parse_new_peer(&peer_ctx, peer_id, NULL,
+						  NULL, vpnip);
+			if (ret < 0) {
+				fprintf(stderr, "error while parsing line\n");
+				return -1;
+			}
+
+			ret = ovpn_new_peer(&peer_ctx, true);
+			if (ret < 0) {
+				fprintf(stderr,
+					"cannot add peer to VPN: %s %s\n",
+					peer_id, vpnip);
+				return ret;
+			}
+			num_peers++;
+		}
+
+		for (int i = 0; i < num_peers; i++) {
+			ret = ovpn_recv_tcp_data(ovpn->cli_sockets[i]);
+			if (ret < 0)
+				break;
+		}
+		ovpn_waitbg();
+		break;
+	case CMD_CONNECT:
+		ret = ovpn_connect(ovpn);
+		if (ret < 0) {
+			fprintf(stderr, "cannot connect TCP socket\n");
+			return ret;
+		}
+
+		ret = ovpn_new_peer(ovpn, true);
+		if (ret < 0) {
+			fprintf(stderr, "cannot add peer to VPN\n");
+			close(ovpn->socket);
+			return ret;
+		}
+
+		if (ovpn->cipher != OVPN_CIPHER_ALG_NONE) {
+			ret = ovpn_new_key(ovpn);
+			if (ret < 0) {
+				fprintf(stderr, "cannot set key\n");
+				return ret;
+			}
+		}
+
+		ret = ovpn_send_tcp_data(ovpn->socket);
+		ovpn_waitbg();
+		break;
+	case CMD_NEW_PEER:
+		ret = ovpn_udp_socket(ovpn, AF_INET6);
+		if (ret < 0)
+			return ret;
+
+		ret = ovpn_new_peer(ovpn, false);
+		ovpn_waitbg();
+		break;
+	case CMD_NEW_MULTI_PEER:
+		ret = ovpn_udp_socket(ovpn, AF_INET6);
+		if (ret < 0)
+			return ret;
+
+		fp = fopen(ovpn->peers_file, "r");
+		if (!fp) {
+			fprintf(stderr, "cannot open file: %s\n",
+				ovpn->peers_file);
+			return -1;
+		}
+
+		while ((n = fscanf(fp, "%s %s %s %s %s %s\n", peer_id, laddr,
+				   lport, raddr, rport, vpnip)) == 6) {
+			struct ovpn_ctx peer_ctx = { 0 };
+
+			peer_ctx.ifindex = ovpn->ifindex;
+			peer_ctx.socket = ovpn->socket;
+			peer_ctx.sa_family = AF_UNSPEC;
+
+			ret = ovpn_parse_new_peer(&peer_ctx, peer_id, raddr,
+						  rport, vpnip);
+			if (ret < 0) {
+				fprintf(stderr, "error while parsing line\n");
+				return -1;
+			}
+
+			ret = ovpn_new_peer(&peer_ctx, false);
+			if (ret < 0) {
+				fprintf(stderr,
+					"cannot add peer to VPN: %s %s %s %s\n",
+					peer_id, raddr, rport, vpnip);
+				return ret;
+			}
+		}
+		ovpn_waitbg();
+		break;
+	case CMD_SET_PEER:
+		ret = ovpn_set_peer(ovpn);
+		break;
+	case CMD_DEL_PEER:
+		ret = ovpn_del_peer(ovpn);
+		break;
+	case CMD_GET_PEER:
+		if (ovpn->peer_id == PEER_ID_UNDEF)
+			fprintf(stderr, "List of peers connected to: %s\n",
+				ovpn->ifname);
+
+		ret = ovpn_get_peer(ovpn);
+		break;
+	case CMD_NEW_KEY:
+		ret = ovpn_new_key(ovpn);
+		break;
+	case CMD_DEL_KEY:
+		ret = ovpn_del_key(ovpn);
+		break;
+	case CMD_GET_KEY:
+		ret = ovpn_get_key(ovpn);
+		break;
+	case CMD_SWAP_KEYS:
+		ret = ovpn_swap_keys(ovpn);
+		break;
+	case CMD_LISTEN_MCAST:
+		ret = ovpn_listen_mcast();
+		break;
+	case CMD_INVALID:
+		break;
+	}
+
+	return ret;
+}
+
+static int ovpn_parse_cmd_args(struct ovpn_ctx *ovpn, int argc, char *argv[])
+{
+	int ret;
+
+	/* no args required for LISTEN_MCAST */
+	if (ovpn->cmd == CMD_LISTEN_MCAST)
+		return 0;
+
+	/* all commands need an ifname */
+	if (argc < 3)
+		return -EINVAL;
+
+	strscpy(ovpn->ifname, argv[2], IFNAMSIZ - 1);
+	ovpn->ifname[IFNAMSIZ - 1] = '\0';
+
+	/* all commands, except NEW_IFNAME, needs an ifindex */
+	if (ovpn->cmd != CMD_NEW_IFACE) {
+		ovpn->ifindex = if_nametoindex(ovpn->ifname);
+		if (!ovpn->ifindex) {
+			fprintf(stderr, "cannot find interface: %s\n",
+				strerror(errno));
+			return -1;
+		}
+	}
+
+	switch (ovpn->cmd) {
+	case CMD_NEW_IFACE:
+		if (argc < 4)
+			break;
+
+		if (!strcmp(argv[3], "P2P")) {
+			ovpn->mode = OVPN_MODE_P2P;
+		} else if (!strcmp(argv[3], "MP")) {
+			ovpn->mode = OVPN_MODE_MP;
+		} else {
+			fprintf(stderr, "Cannot parse iface mode: %s\n",
+				argv[3]);
+			return -1;
+		}
+		ovpn->mode_set = true;
+		break;
+	case CMD_DEL_IFACE:
+		break;
+	case CMD_LISTEN:
+		if (argc < 5)
+			return -EINVAL;
+
+		ovpn->lport = strtoul(argv[3], NULL, 10);
+		if (errno == ERANGE || ovpn->lport > 65535) {
+			fprintf(stderr, "lport value out of range\n");
+			return -1;
+		}
+
+		ovpn->peers_file = argv[4];
+
+		if (argc > 5 && !strcmp(argv[5], "ipv6"))
+			ovpn->sa_family = AF_INET6;
+		break;
+	case CMD_CONNECT:
+		if (argc < 6)
+			return -EINVAL;
+
+		ovpn->sa_family = AF_INET;
+
+		ret = ovpn_parse_new_peer(ovpn, argv[3], argv[4], argv[5],
+					  NULL);
+		if (ret < 0) {
+			fprintf(stderr, "Cannot parse remote peer data\n");
+			return -1;
+		}
+
+		if (argc > 6) {
+			ovpn->key_slot = OVPN_KEY_SLOT_PRIMARY;
+			ovpn->key_id = 0;
+			ovpn->cipher = OVPN_CIPHER_ALG_AES_GCM;
+			ovpn->key_dir = KEY_DIR_OUT;
+
+			ret = ovpn_parse_key(argv[6], ovpn);
+			if (ret)
+				return -1;
+		}
+		break;
+	case CMD_NEW_PEER:
+		if (argc < 7)
+			return -EINVAL;
+
+		ovpn->lport = strtoul(argv[4], NULL, 10);
+		if (errno == ERANGE || ovpn->lport > 65535) {
+			fprintf(stderr, "lport value out of range\n");
+			return -1;
+		}
+
+		const char *vpnip = (argc > 7) ? argv[7] : NULL;
+
+		ret = ovpn_parse_new_peer(ovpn, argv[3], argv[5], argv[6],
+					  vpnip);
+		if (ret < 0)
+			return -1;
+		break;
+	case CMD_NEW_MULTI_PEER:
+		if (argc < 5)
+			return -EINVAL;
+
+		ovpn->lport = strtoul(argv[3], NULL, 10);
+		if (errno == ERANGE || ovpn->lport > 65535) {
+			fprintf(stderr, "lport value out of range\n");
+			return -1;
+		}
+
+		ovpn->peers_file = argv[4];
+		break;
+	case CMD_SET_PEER:
+		if (argc < 6)
+			return -EINVAL;
+
+		ovpn->peer_id = strtoul(argv[3], NULL, 10);
+		if (errno == ERANGE || ovpn->peer_id > PEER_ID_UNDEF) {
+			fprintf(stderr, "peer ID value out of range\n");
+			return -1;
+		}
+
+		ovpn->keepalive_interval = strtoul(argv[4], NULL, 10);
+		if (errno == ERANGE) {
+			fprintf(stderr,
+				"keepalive interval value out of range\n");
+			return -1;
+		}
+
+		ovpn->keepalive_timeout = strtoul(argv[5], NULL, 10);
+		if (errno == ERANGE) {
+			fprintf(stderr,
+				"keepalive interval value out of range\n");
+			return -1;
+		}
+		break;
+	case CMD_DEL_PEER:
+		if (argc < 4)
+			return -EINVAL;
+
+		ovpn->peer_id = strtoul(argv[3], NULL, 10);
+		if (errno == ERANGE || ovpn->peer_id > PEER_ID_UNDEF) {
+			fprintf(stderr, "peer ID value out of range\n");
+			return -1;
+		}
+		break;
+	case CMD_GET_PEER:
+		ovpn->peer_id = PEER_ID_UNDEF;
+		if (argc > 3) {
+			ovpn->peer_id = strtoul(argv[3], NULL, 10);
+			if (errno == ERANGE || ovpn->peer_id > PEER_ID_UNDEF) {
+				fprintf(stderr, "peer ID value out of range\n");
+				return -1;
+			}
+		}
+		break;
+	case CMD_NEW_KEY:
+		if (argc < 9)
+			return -EINVAL;
+
+		ovpn->peer_id = strtoul(argv[3], NULL, 10);
+		if (errno == ERANGE) {
+			fprintf(stderr, "peer ID value out of range\n");
+			return -1;
+		}
+
+		ret = ovpn_parse_key_slot(argv[4], ovpn);
+		if (ret)
+			return -1;
+
+		ovpn->key_id = strtoul(argv[5], NULL, 10);
+		if (errno == ERANGE || ovpn->key_id > 2) {
+			fprintf(stderr, "key ID out of range\n");
+			return -1;
+		}
+
+		ret = ovpn_parse_cipher(argv[6], ovpn);
+		if (ret < 0)
+			return -1;
+
+		ret = ovpn_parse_key_direction(argv[7], ovpn);
+		if (ret < 0)
+			return -1;
+
+		ret = ovpn_parse_key(argv[8], ovpn);
+		if (ret)
+			return -1;
+		break;
+	case CMD_DEL_KEY:
+		if (argc < 4)
+			return -EINVAL;
+
+		ovpn->peer_id = strtoul(argv[3], NULL, 10);
+		if (errno == ERANGE) {
+			fprintf(stderr, "peer ID value out of range\n");
+			return -1;
+		}
+
+		ret = ovpn_parse_key_slot(argv[4], ovpn);
+		if (ret)
+			return ret;
+		break;
+	case CMD_GET_KEY:
+		if (argc < 5)
+			return -EINVAL;
+
+		ovpn->peer_id = strtoul(argv[3], NULL, 10);
+		if (errno == ERANGE) {
+			fprintf(stderr, "peer ID value out of range\n");
+			return -1;
+		}
+
+		ret = ovpn_parse_key_slot(argv[4], ovpn);
+		if (ret)
+			return ret;
+		break;
+	case CMD_SWAP_KEYS:
+		if (argc < 4)
+			return -EINVAL;
+
+		ovpn->peer_id = strtoul(argv[3], NULL, 10);
+		if (errno == ERANGE) {
+			fprintf(stderr, "peer ID value out of range\n");
+			return -1;
+		}
+		break;
+	case CMD_LISTEN_MCAST:
+		break;
+	case CMD_INVALID:
+		break;
+	}
+
+	return 0;
+}
+
+int main(int argc, char *argv[])
+{
+	struct ovpn_ctx ovpn;
+	int ret;
+
+	if (argc < 2) {
+		usage(argv[0]);
+		return -1;
+	}
+
+	memset(&ovpn, 0, sizeof(ovpn));
+	ovpn.sa_family = AF_UNSPEC;
+	ovpn.cipher = OVPN_CIPHER_ALG_NONE;
+
+	ovpn.cmd = ovpn_parse_cmd(argv[1]);
+	if (ovpn.cmd == CMD_INVALID) {
+		fprintf(stderr, "Error: unknown command.\n\n");
+		usage(argv[0]);
+		return -1;
+	}
+
+	ret = ovpn_parse_cmd_args(&ovpn, argc, argv);
+	if (ret < 0) {
+		fprintf(stderr, "Error: invalid arguments.\n\n");
+		if (ret == -EINVAL)
+			usage(argv[0]);
+		return ret;
+	}
+
+	ret = ovpn_run_cmd(&ovpn);
+	if (ret)
+		fprintf(stderr, "Cannot execute command: %s (%d)\n",
+			strerror(-ret), ret);
+
+	return ret;
+}
diff --git a/tools/testing/selftests/net/ovpn/tcp_peers.txt b/tools/testing/selftests/net/ovpn/tcp_peers.txt
new file mode 100644
index 000000000000..d753eebe8716
--- /dev/null
+++ b/tools/testing/selftests/net/ovpn/tcp_peers.txt
@@ -0,0 +1,5 @@
+1 5.5.5.2
+2 5.5.5.3
+3 5.5.5.4
+4 5.5.5.5
+5 5.5.5.6
diff --git a/tools/testing/selftests/net/ovpn/test-chachapoly.sh b/tools/testing/selftests/net/ovpn/test-chachapoly.sh
new file mode 100755
index 000000000000..32504079a2b8
--- /dev/null
+++ b/tools/testing/selftests/net/ovpn/test-chachapoly.sh
@@ -0,0 +1,9 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+# Copyright (C) 2025 OpenVPN, Inc.
+#
+#  Author:	Antonio Quartulli <antonio@openvpn.net>
+
+ALG="chachapoly"
+
+source test.sh
diff --git a/tools/testing/selftests/net/ovpn/test-close-socket-tcp.sh b/tools/testing/selftests/net/ovpn/test-close-socket-tcp.sh
new file mode 100755
index 000000000000..093d44772ffd
--- /dev/null
+++ b/tools/testing/selftests/net/ovpn/test-close-socket-tcp.sh
@@ -0,0 +1,9 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+# Copyright (C) 2025 OpenVPN, Inc.
+#
+#  Author:	Antonio Quartulli <antonio@openvpn.net>
+
+PROTO="TCP"
+
+source test-close-socket.sh
diff --git a/tools/testing/selftests/net/ovpn/test-close-socket.sh b/tools/testing/selftests/net/ovpn/test-close-socket.sh
new file mode 100755
index 000000000000..5e48a8b67928
--- /dev/null
+++ b/tools/testing/selftests/net/ovpn/test-close-socket.sh
@@ -0,0 +1,45 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+# Copyright (C) 2020-2025 OpenVPN, Inc.
+#
+#  Author:	Antonio Quartulli <antonio@openvpn.net>
+
+#set -x
+set -e
+
+source ./common.sh
+
+cleanup
+
+modprobe -q ovpn || true
+
+for p in $(seq 0 ${NUM_PEERS}); do
+	create_ns ${p}
+done
+
+for p in $(seq 0 ${NUM_PEERS}); do
+	setup_ns ${p} 5.5.5.$((${p} + 1))/24
+done
+
+for p in $(seq 0 ${NUM_PEERS}); do
+	add_peer ${p}
+done
+
+for p in $(seq 1 ${NUM_PEERS}); do
+	ip netns exec peer0 ${OVPN_CLI} set_peer tun0 ${p} 60 120
+	ip netns exec peer${p} ${OVPN_CLI} set_peer tun${p} ${p} 60 120
+done
+
+sleep 1
+
+for p in $(seq 1 ${NUM_PEERS}); do
+	ip netns exec peer0 ping -qfc 500 -w 3 5.5.5.$((${p} + 1))
+done
+
+ip netns exec peer0 iperf3 -1 -s &
+sleep 1
+ip netns exec peer1 iperf3 -Z -t 3 -c 5.5.5.1
+
+cleanup
+
+modprobe -r ovpn || true
diff --git a/tools/testing/selftests/net/ovpn/test-float.sh b/tools/testing/selftests/net/ovpn/test-float.sh
new file mode 100755
index 000000000000..ba5d725e18b0
--- /dev/null
+++ b/tools/testing/selftests/net/ovpn/test-float.sh
@@ -0,0 +1,9 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+# Copyright (C) 2025 OpenVPN, Inc.
+#
+#  Author:	Antonio Quartulli <antonio@openvpn.net>
+
+FLOAT="1"
+
+source test.sh
diff --git a/tools/testing/selftests/net/ovpn/test-tcp.sh b/tools/testing/selftests/net/ovpn/test-tcp.sh
new file mode 100755
index 000000000000..ba3f1f315a34
--- /dev/null
+++ b/tools/testing/selftests/net/ovpn/test-tcp.sh
@@ -0,0 +1,9 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+# Copyright (C) 2025 OpenVPN, Inc.
+#
+#  Author:	Antonio Quartulli <antonio@openvpn.net>
+
+PROTO="TCP"
+
+source test.sh
diff --git a/tools/testing/selftests/net/ovpn/test.sh b/tools/testing/selftests/net/ovpn/test.sh
new file mode 100755
index 000000000000..e8acdc303307
--- /dev/null
+++ b/tools/testing/selftests/net/ovpn/test.sh
@@ -0,0 +1,117 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+# Copyright (C) 2020-2025 OpenVPN, Inc.
+#
+#  Author:	Antonio Quartulli <antonio@openvpn.net>
+
+#set -x
+set -e
+
+source ./common.sh
+
+cleanup
+
+modprobe -q ovpn || true
+
+for p in $(seq 0 ${NUM_PEERS}); do
+	create_ns ${p}
+done
+
+for p in $(seq 0 ${NUM_PEERS}); do
+	setup_ns ${p} 5.5.5.$((${p} + 1))/24 ${MTU}
+done
+
+for p in $(seq 0 ${NUM_PEERS}); do
+	add_peer ${p}
+done
+
+for p in $(seq 1 ${NUM_PEERS}); do
+	ip netns exec peer0 ${OVPN_CLI} set_peer tun0 ${p} 60 120
+	ip netns exec peer${p} ${OVPN_CLI} set_peer tun${p} ${p} 60 120
+done
+
+sleep 1
+
+for p in $(seq 1 ${NUM_PEERS}); do
+	ip netns exec peer0 ping -qfc 500 -w 3 5.5.5.$((${p} + 1))
+	ip netns exec peer0 ping -qfc 500 -s 3000 -w 3 5.5.5.$((${p} + 1))
+done
+
+# ping LAN behind client 1
+ip netns exec peer0 ping -qfc 500 -w 3 ${LAN_IP}
+
+if [ "$FLOAT" == "1" ]; then
+	# make clients float..
+	for p in $(seq 1 ${NUM_PEERS}); do
+		ip -n peer${p} addr del 10.10.${p}.2/24 dev veth${p}
+		ip -n peer${p} addr add 10.10.${p}.3/24 dev veth${p}
+	done
+	for p in $(seq 1 ${NUM_PEERS}); do
+		ip netns exec peer${p} ping -qfc 500 -w 3 5.5.5.1
+	done
+fi
+
+ip netns exec peer0 iperf3 -1 -s &
+sleep 1
+ip netns exec peer1 iperf3 -Z -t 3 -c 5.5.5.1
+
+echo "Adding secondary key and then swap:"
+for p in $(seq 1 ${NUM_PEERS}); do
+	ip netns exec peer0 ${OVPN_CLI} new_key tun0 ${p} 2 1 ${ALG} 0 data64.key
+	ip netns exec peer${p} ${OVPN_CLI} new_key tun${p} ${p} 2 1 ${ALG} 1 data64.key
+	ip netns exec peer${p} ${OVPN_CLI} swap_keys tun${p} ${p}
+done
+
+sleep 1
+
+echo "Querying all peers:"
+ip netns exec peer0 ${OVPN_CLI} get_peer tun0
+ip netns exec peer1 ${OVPN_CLI} get_peer tun1
+
+echo "Querying peer 1:"
+ip netns exec peer0 ${OVPN_CLI} get_peer tun0 1
+
+echo "Querying non-existent peer 10:"
+ip netns exec peer0 ${OVPN_CLI} get_peer tun0 10 || true
+
+echo "Deleting peer 1:"
+ip netns exec peer0 ${OVPN_CLI} del_peer tun0 1
+ip netns exec peer1 ${OVPN_CLI} del_peer tun1 1
+
+echo "Querying keys:"
+for p in $(seq 2 ${NUM_PEERS}); do
+	ip netns exec peer${p} ${OVPN_CLI} get_key tun${p} ${p} 1
+	ip netns exec peer${p} ${OVPN_CLI} get_key tun${p} ${p} 2
+done
+
+echo "Deleting peer while sending traffic:"
+(ip netns exec peer2 ping -qf -w 4 5.5.5.1)&
+sleep 2
+ip netns exec peer0 ${OVPN_CLI} del_peer tun0 2
+# following command fails in TCP mode
+# (both ends get conn reset when one peer disconnects)
+ip netns exec peer2 ${OVPN_CLI} del_peer tun2 2 || true
+
+echo "Deleting keys:"
+for p in $(seq 3 ${NUM_PEERS}); do
+	ip netns exec peer${p} ${OVPN_CLI} del_key tun${p} ${p} 1
+	ip netns exec peer${p} ${OVPN_CLI} del_key tun${p} ${p} 2
+done
+
+echo "Setting timeout to 3s MP:"
+for p in $(seq 3 ${NUM_PEERS}); do
+	ip netns exec peer0 ${OVPN_CLI} set_peer tun0 ${p} 3 3 || true
+	ip netns exec peer${p} ${OVPN_CLI} set_peer tun${p} ${p} 0 0
+done
+# wait for peers to timeout
+sleep 5
+
+echo "Setting timeout to 3s P2P:"
+for p in $(seq 3 ${NUM_PEERS}); do
+	ip netns exec peer${p} ${OVPN_CLI} set_peer tun${p} ${p} 3 3
+done
+sleep 5
+
+cleanup
+
+modprobe -r ovpn || true
diff --git a/tools/testing/selftests/net/ovpn/udp_peers.txt b/tools/testing/selftests/net/ovpn/udp_peers.txt
new file mode 100644
index 000000000000..e9773ddf875c
--- /dev/null
+++ b/tools/testing/selftests/net/ovpn/udp_peers.txt
@@ -0,0 +1,6 @@
+1 10.10.1.1 1 10.10.1.2 1 5.5.5.2
+2 10.10.2.1 1 10.10.2.2 1 5.5.5.3
+3 10.10.3.1 1 10.10.3.2 1 5.5.5.4
+4 fd00:0:0:4::1 1 fd00:0:0:4::2 1 5.5.5.5
+5 fd00:0:0:5::1 1 fd00:0:0:5::2 1 5.5.5.6
+6 fd00:0:0:6::1 1 fd00:0:0:6::2 1 5.5.5.7
diff --git a/tools/testing/selftests/net/pmtu.sh b/tools/testing/selftests/net/pmtu.sh
index 66be7699c72c..88e914c4eef9 100755
--- a/tools/testing/selftests/net/pmtu.sh
+++ b/tools/testing/selftests/net/pmtu.sh
@@ -205,7 +205,6 @@
 #	Check that PMTU exceptions are created for both paths.
 
 source lib.sh
-source net_helper.sh
 
 PAUSE_ON_FAIL=no
 VERBOSE=0
diff --git a/tools/testing/selftests/net/reuseport_addr_any.c b/tools/testing/selftests/net/reuseport_addr_any.c
index b8475cb29be7..1c43401a1c80 100644
--- a/tools/testing/selftests/net/reuseport_addr_any.c
+++ b/tools/testing/selftests/net/reuseport_addr_any.c
@@ -9,7 +9,6 @@
 #include <arpa/inet.h>
 #include <errno.h>
 #include <error.h>
-#include <linux/dccp.h>
 #include <linux/in.h>
 #include <linux/unistd.h>
 #include <stdbool.h>
@@ -21,10 +20,6 @@
 #include <sys/socket.h>
 #include <unistd.h>
 
-#ifndef SOL_DCCP
-#define SOL_DCCP 269
-#endif
-
 static const char *IP4_ADDR = "127.0.0.1";
 static const char *IP6_ADDR = "::1";
 static const char *IP4_MAPPED6 = "::ffff:127.0.0.1";
@@ -86,15 +81,6 @@ static void build_rcv_fd(int family, int proto, int *rcv_fds, int count,
 
 		if (proto == SOCK_STREAM && listen(rcv_fds[i], 10))
 			error(1, errno, "tcp: failed to listen on receive port");
-		else if (proto == SOCK_DCCP) {
-			if (setsockopt(rcv_fds[i], SOL_DCCP,
-					DCCP_SOCKOPT_SERVICE,
-					&(int) {htonl(42)}, sizeof(int)))
-				error(1, errno, "failed to setsockopt");
-
-			if (listen(rcv_fds[i], 10))
-				error(1, errno, "dccp: failed to listen on receive port");
-		}
 	}
 }
 
@@ -148,11 +134,6 @@ static int connect_and_send(int family, int proto)
 	if (fd < 0)
 		error(1, errno, "failed to create send socket");
 
-	if (proto == SOCK_DCCP &&
-		setsockopt(fd, SOL_DCCP, DCCP_SOCKOPT_SERVICE,
-				&(int){htonl(42)}, sizeof(int)))
-		error(1, errno, "failed to setsockopt");
-
 	if (bind(fd, saddr, sz))
 		error(1, errno, "failed to bind send socket");
 
@@ -175,7 +156,7 @@ static int receive_once(int epfd, int proto)
 	if (i < 0)
 		error(1, errno, "epoll_wait failed");
 
-	if (proto == SOCK_STREAM || proto == SOCK_DCCP) {
+	if (proto == SOCK_STREAM) {
 		fd = accept(ev.data.fd, NULL, NULL);
 		if (fd < 0)
 			error(1, errno, "failed to accept");
@@ -243,20 +224,6 @@ static void run_one_test(int fam_send, int fam_rcv, int proto,
 
 static void test_proto(int proto, const char *proto_str)
 {
-	if (proto == SOCK_DCCP) {
-		int test_fd;
-
-		test_fd = socket(AF_INET, proto, 0);
-		if (test_fd < 0) {
-			if (errno == ESOCKTNOSUPPORT) {
-				fprintf(stderr, "DCCP not supported: skipping DCCP tests\n");
-				return;
-			} else
-				error(1, errno, "failed to create a DCCP socket");
-		}
-		close(test_fd);
-	}
-
 	fprintf(stderr, "%s IPv4 ... ", proto_str);
 	run_one_test(AF_INET, AF_INET, proto, IP4_ADDR);
 
@@ -271,7 +238,6 @@ int main(void)
 {
 	test_proto(SOCK_DGRAM, "UDP");
 	test_proto(SOCK_STREAM, "TCP");
-	test_proto(SOCK_DCCP, "DCCP");
 
 	fprintf(stderr, "SUCCESS\n");
 	return 0;
diff --git a/tools/testing/selftests/net/srv6_end_dt46_l3vpn_test.sh b/tools/testing/selftests/net/srv6_end_dt46_l3vpn_test.sh
index 02d617040793..a5e959a080bb 100755
--- a/tools/testing/selftests/net/srv6_end_dt46_l3vpn_test.sh
+++ b/tools/testing/selftests/net/srv6_end_dt46_l3vpn_test.sh
@@ -285,11 +285,6 @@ setup_hs()
 	ip netns exec ${hsname} sysctl -wq net.ipv6.conf.all.accept_dad=0
 	ip netns exec ${hsname} sysctl -wq net.ipv6.conf.default.accept_dad=0
 
-	# disable the rp_filter otherwise the kernel gets confused about how
-	# to route decap ipv4 packets.
-	ip netns exec ${rtname} sysctl -wq net.ipv4.conf.all.rp_filter=0
-	ip netns exec ${rtname} sysctl -wq net.ipv4.conf.default.rp_filter=0
-
 	ip -netns ${hsname} link add veth0 type veth peer name ${rtveth}
 	ip -netns ${hsname} link set ${rtveth} netns ${rtname}
 	ip -netns ${hsname} addr add ${IPv6_HS_NETWORK}::${hid}/64 dev veth0 nodad
diff --git a/tools/testing/selftests/net/srv6_end_dt4_l3vpn_test.sh b/tools/testing/selftests/net/srv6_end_dt4_l3vpn_test.sh
index 79fb81e63c59..a649dba3cb77 100755
--- a/tools/testing/selftests/net/srv6_end_dt4_l3vpn_test.sh
+++ b/tools/testing/selftests/net/srv6_end_dt4_l3vpn_test.sh
@@ -250,11 +250,6 @@ setup_hs()
 	eval local rtname=\${rt_${rid}}
 	local rtveth=veth-t${tid}
 
-	# disable the rp_filter otherwise the kernel gets confused about how
-	# to route decap ipv4 packets.
-	ip netns exec ${rtname} sysctl -wq net.ipv4.conf.all.rp_filter=0
-	ip netns exec ${rtname} sysctl -wq net.ipv4.conf.default.rp_filter=0
-
 	ip -netns ${hsname} link add veth0 type veth peer name ${rtveth}
 	ip -netns ${hsname} link set ${rtveth} netns ${rtname}
 	ip -netns ${hsname} addr add ${IPv4_HS_NETWORK}.${hid}/24 dev veth0
diff --git a/tools/testing/selftests/net/srv6_end_flavors_test.sh b/tools/testing/selftests/net/srv6_end_flavors_test.sh
index 50563443a4ad..318487eda671 100755
--- a/tools/testing/selftests/net/srv6_end_flavors_test.sh
+++ b/tools/testing/selftests/net/srv6_end_flavors_test.sh
@@ -399,7 +399,7 @@ __get_srv6_rtcfg_id()
 
 # Given the description of a router <id:op> as an input, the function returns
 # the <op> token which represents the operation (e.g. End behavior with or
-# withouth flavors) configured for the node.
+# without flavors) configured for the node.
 
 # Note that when the operation represents an End behavior with a list of
 # flavors, the output is the ordered version of that list.
@@ -480,7 +480,7 @@ setup_rt_local_sids()
 
 
 	# all SIDs start with a common locator. Routes and SRv6 Endpoint
-	# behavior instaces are grouped together in the 'localsid' table.
+	# behavior instances are grouped together in the 'localsid' table.
 	ip -netns "${nsname}" -6 rule \
 		add to "${LOCATOR_SERVICE}::/16" \
 		lookup "${LOCALSID_TABLE_ID}" prio 999
diff --git a/tools/testing/selftests/net/srv6_end_next_csid_l3vpn_test.sh b/tools/testing/selftests/net/srv6_end_next_csid_l3vpn_test.sh
index 87e414cc417c..ba730655a7bf 100755
--- a/tools/testing/selftests/net/srv6_end_next_csid_l3vpn_test.sh
+++ b/tools/testing/selftests/net/srv6_end_next_csid_l3vpn_test.sh
@@ -245,10 +245,8 @@
 # that adopted in the use cases already examined (of course, it is necessary to
 # consider the different SIDs/C-SIDs).
 
-# Kselftest framework requirement - SKIP code is 4.
-readonly ksft_skip=4
+source lib.sh
 
-readonly RDMSUFF="$(mktemp -u XXXXXXXX)"
 readonly DUMMY_DEVNAME="dum0"
 readonly VRF_TID=100
 readonly VRF_DEVNAME="vrf-${VRF_TID}"
@@ -376,32 +374,18 @@ test_command_or_ksft_skip()
 	fi
 }
 
-get_nodename()
-{
-	local name="$1"
-
-	echo "${name}-${RDMSUFF}"
-}
-
 get_rtname()
 {
 	local rtid="$1"
 
-	get_nodename "rt-${rtid}"
+	echo "rt_${rtid}"
 }
 
 get_hsname()
 {
 	local hsid="$1"
 
-	get_nodename "hs-${hsid}"
-}
-
-__create_namespace()
-{
-	local name="$1"
-
-	ip netns add "${name}"
+	echo "hs_${hsid}"
 }
 
 create_router()
@@ -410,8 +394,7 @@ create_router()
 	local nsname
 
 	nsname="$(get_rtname "${rtid}")"
-
-	__create_namespace "${nsname}"
+	setup_ns "${nsname}"
 }
 
 create_host()
@@ -420,28 +403,12 @@ create_host()
 	local nsname
 
 	nsname="$(get_hsname "${hsid}")"
-
-	__create_namespace "${nsname}"
+	setup_ns "${nsname}"
 }
 
 cleanup()
 {
-	local nsname
-	local i
-
-	# destroy routers
-	for i in ${ROUTERS}; do
-		nsname="$(get_rtname "${i}")"
-
-		ip netns del "${nsname}" &>/dev/null || true
-	done
-
-	# destroy hosts
-	for i in ${HOSTS}; do
-		nsname="$(get_hsname "${i}")"
-
-		ip netns del "${nsname}" &>/dev/null || true
-	done
+	cleanup_all_ns
 
 	# check whether the setup phase was completed successfully or not. In
 	# case of an error during the setup phase of the testing environment,
@@ -462,10 +429,10 @@ add_link_rt_pairs()
 	local nsname
 	local neigh_nsname
 
-	nsname="$(get_rtname "${rt}")"
+	eval nsname=\${$(get_rtname "${rt}")}
 
 	for neigh in ${rt_neighs}; do
-		neigh_nsname="$(get_rtname "${neigh}")"
+		eval neigh_nsname=\${$(get_rtname "${neigh}")}
 
 		ip link add "veth-rt-${rt}-${neigh}" netns "${nsname}" \
 			type veth peer name "veth-rt-${neigh}-${rt}" \
@@ -497,7 +464,7 @@ setup_rt_networking()
 	local devname
 	local neigh
 
-	nsname="$(get_rtname "${rt}")"
+	eval nsname=\${$(get_rtname "${rt}")}
 
 	for neigh in ${rt_neighs}; do
 		devname="veth-rt-${rt}-${neigh}"
@@ -518,9 +485,6 @@ setup_rt_networking()
 	ip netns exec "${nsname}" sysctl -wq net.ipv6.conf.all.accept_dad=0
 	ip netns exec "${nsname}" sysctl -wq net.ipv6.conf.default.accept_dad=0
 	ip netns exec "${nsname}" sysctl -wq net.ipv6.conf.all.forwarding=1
-
-	ip netns exec "${nsname}" sysctl -wq net.ipv4.conf.all.rp_filter=0
-	ip netns exec "${nsname}" sysctl -wq net.ipv4.conf.default.rp_filter=0
 	ip netns exec "${nsname}" sysctl -wq net.ipv4.ip_forward=1
 }
 
@@ -596,7 +560,7 @@ setup_rt_local_sids()
 	local lcnode_func_prefix
 	local lcblock_prefix
 
-	nsname="$(get_rtname "${rt}")"
+	eval nsname=\${$(get_rtname "${rt}")}
 
 	for neigh in ${rt_neighs}; do
 		devname="veth-rt-${rt}-${neigh}"
@@ -668,8 +632,8 @@ __setup_l3vpn()
 	local rtsrc_nsname
 	local rtdst_nsname
 
-	rtsrc_nsname="$(get_rtname "${src}")"
-	rtdst_nsname="$(get_rtname "${dst}")"
+	eval rtsrc_nsname=\${$(get_rtname "${src}")}
+	eval rtdst_nsname=\${$(get_rtname "${dst}")}
 
 	container="${LCBLOCK_ADDR}"
 
@@ -744,8 +708,8 @@ setup_hs()
 	local hsname
 	local rtname
 
-	hsname="$(get_hsname "${hs}")"
-	rtname="$(get_rtname "${rt}")"
+	eval hsname=\${$(get_hsname "${hs}")}
+	eval rtname=\${$(get_rtname "${rt}")}
 
 	ip netns exec "${hsname}" sysctl -wq net.ipv6.conf.all.accept_dad=0
 	ip netns exec "${hsname}" sysctl -wq net.ipv6.conf.default.accept_dad=0
@@ -791,11 +755,6 @@ setup_hs()
 	ip netns exec "${rtname}" \
 		sysctl -wq net.ipv4.conf."${RT2HS_DEVNAME}".proxy_arp=1
 
-	# disable the rp_filter otherwise the kernel gets confused about how
-	# to route decap ipv4 packets.
-	ip netns exec "${rtname}" \
-		sysctl -wq net.ipv4.conf."${RT2HS_DEVNAME}".rp_filter=0
-
 	ip netns exec "${rtname}" sh -c "echo 1 > /proc/sys/net/vrf/strict_mode"
 }
 
@@ -880,7 +839,7 @@ check_rt_connectivity()
 	local prefix
 	local rtsrc_nsname
 
-	rtsrc_nsname="$(get_rtname "${rtsrc}")"
+	eval rtsrc_nsname=\${$(get_rtname "${rtsrc}")}
 
 	prefix="$(get_network_prefix "${rtsrc}" "${rtdst}")"
 
@@ -903,7 +862,7 @@ check_hs_ipv6_connectivity()
 	local hsdst="$2"
 	local hssrc_nsname
 
-	hssrc_nsname="$(get_hsname "${hssrc}")"
+	eval hssrc_nsname=\${$(get_hsname "${hssrc}")}
 
 	ip netns exec "${hssrc_nsname}" ping -c 1 -W "${PING_TIMEOUT_SEC}" \
 		"${IPv6_HS_NETWORK}::${hsdst}" >/dev/null 2>&1
@@ -915,7 +874,7 @@ check_hs_ipv4_connectivity()
 	local hsdst="$2"
 	local hssrc_nsname
 
-	hssrc_nsname="$(get_hsname "${hssrc}")"
+	eval hssrc_nsname=\${$(get_hsname "${hssrc}")}
 
 	ip netns exec "${hssrc_nsname}" ping -c 1 -W "${PING_TIMEOUT_SEC}" \
 		"${IPv4_HS_NETWORK}.${hsdst}" >/dev/null 2>&1
@@ -1025,7 +984,7 @@ rt_x_nextcsid_end_behavior_test()
 	local nsname
 	local ret
 
-	nsname="$(get_rtname "${rt}")"
+	eval nsname=\${$(get_rtname "${rt}")}
 
 	__nextcsid_end_behavior_test "${nsname}" "add" "${blen}" "${flen}"
 	ret="$?"
diff --git a/tools/testing/selftests/net/srv6_end_x_next_csid_l3vpn_test.sh b/tools/testing/selftests/net/srv6_end_x_next_csid_l3vpn_test.sh
index c79cb8ede17f..4b86040c58c6 100755
--- a/tools/testing/selftests/net/srv6_end_x_next_csid_l3vpn_test.sh
+++ b/tools/testing/selftests/net/srv6_end_x_next_csid_l3vpn_test.sh
@@ -287,10 +287,8 @@
 # packet using the SRv6 End.DT46 behavior (associated with the SID fcff:1::d46)
 # and sends it to the host hs-1.
 
-# Kselftest framework requirement - SKIP code is 4.
-readonly ksft_skip=4
+source lib.sh
 
-readonly RDMSUFF="$(mktemp -u XXXXXXXX)"
 readonly DUMMY_DEVNAME="dum0"
 readonly VRF_TID=100
 readonly VRF_DEVNAME="vrf-${VRF_TID}"
@@ -418,32 +416,18 @@ test_command_or_ksft_skip()
 	fi
 }
 
-get_nodename()
-{
-	local name="$1"
-
-	echo "${name}-${RDMSUFF}"
-}
-
 get_rtname()
 {
 	local rtid="$1"
 
-	get_nodename "rt-${rtid}"
+	echo "rt_${rtid}"
 }
 
 get_hsname()
 {
 	local hsid="$1"
 
-	get_nodename "hs-${hsid}"
-}
-
-__create_namespace()
-{
-	local name="$1"
-
-	ip netns add "${name}"
+	echo "hs_${hsid}"
 }
 
 create_router()
@@ -452,15 +436,12 @@ create_router()
 	local nsname
 
 	nsname="$(get_rtname "${rtid}")"
+	setup_ns "${nsname}"
 
-	__create_namespace "${nsname}"
-
+	eval nsname=\${$(get_rtname "${rtid}")}
 	ip netns exec "${nsname}" sysctl -wq net.ipv6.conf.all.accept_dad=0
 	ip netns exec "${nsname}" sysctl -wq net.ipv6.conf.default.accept_dad=0
 	ip netns exec "${nsname}" sysctl -wq net.ipv6.conf.all.forwarding=1
-
-	ip netns exec "${nsname}" sysctl -wq net.ipv4.conf.all.rp_filter=0
-	ip netns exec "${nsname}" sysctl -wq net.ipv4.conf.default.rp_filter=0
 	ip netns exec "${nsname}" sysctl -wq net.ipv4.ip_forward=1
 }
 
@@ -470,29 +451,12 @@ create_host()
 	local nsname
 
 	nsname="$(get_hsname "${hsid}")"
-
-	__create_namespace "${nsname}"
+	setup_ns "${nsname}"
 }
 
 cleanup()
 {
-	local nsname
-	local i
-
-	# destroy routers
-	for i in ${ROUTERS}; do
-		nsname="$(get_rtname "${i}")"
-
-		ip netns del "${nsname}" &>/dev/null || true
-	done
-
-	# destroy hosts
-	for i in ${HOSTS}; do
-		nsname="$(get_hsname "${i}")"
-
-		ip netns del "${nsname}" &>/dev/null || true
-	done
-
+	cleanup_all_ns
 	# check whether the setup phase was completed successfully or not. In
 	# case of an error during the setup phase of the testing environment,
 	# the selftest is considered as "skipped".
@@ -512,10 +476,10 @@ add_link_rt_pairs()
 	local nsname
 	local neigh_nsname
 
-	nsname="$(get_rtname "${rt}")"
+	eval nsname=\${$(get_rtname "${rt}")}
 
 	for neigh in ${rt_neighs}; do
-		neigh_nsname="$(get_rtname "${neigh}")"
+		eval neigh_nsname=\${$(get_rtname "${neigh}")}
 
 		ip link add "veth-rt-${rt}-${neigh}" netns "${nsname}" \
 			type veth peer name "veth-rt-${neigh}-${rt}" \
@@ -547,7 +511,7 @@ setup_rt_networking()
 	local devname
 	local neigh
 
-	nsname="$(get_rtname "${rt}")"
+	eval nsname=\${$(get_rtname "${rt}")}
 
 	for neigh in ${rt_neighs}; do
 		devname="veth-rt-${rt}-${neigh}"
@@ -631,7 +595,7 @@ set_end_x_nextcsid()
 	local rt="$1"
 	local adj="$2"
 
-	nsname="$(get_rtname "${rt}")"
+	eval nsname=\${$(get_rtname "${rt}")}
 	net_prefix="$(get_network_prefix "${rt}" "${adj}")"
 	lcnode_func_prefix="$(build_lcnode_func_prefix "${rt}")"
 
@@ -650,7 +614,7 @@ set_underlay_sids_reachability()
 	local rt="$1"
 	local rt_neighs="$2"
 
-	nsname="$(get_rtname "${rt}")"
+	eval nsname=\${$(get_rtname "${rt}")}
 
 	for neigh in ${rt_neighs}; do
 		devname="veth-rt-${rt}-${neigh}"
@@ -685,7 +649,7 @@ setup_rt_local_sids()
 	local lcnode_func_prefix
 	local lcblock_prefix
 
-	nsname="$(get_rtname "${rt}")"
+	eval nsname=\${$(get_rtname "${rt}")}
 
         set_underlay_sids_reachability "${rt}" "${rt_neighs}"
 
@@ -728,8 +692,8 @@ __setup_l3vpn()
 	local rtsrc_nsname
 	local rtdst_nsname
 
-	rtsrc_nsname="$(get_rtname "${src}")"
-	rtdst_nsname="$(get_rtname "${dst}")"
+	eval rtsrc_nsname=\${$(get_rtname "${src}")}
+	eval rtdst_nsname=\${$(get_rtname "${dst}")}
 
 	container="${LCBLOCK_ADDR}"
 
@@ -804,8 +768,8 @@ setup_hs()
 	local hsname
 	local rtname
 
-	hsname="$(get_hsname "${hs}")"
-	rtname="$(get_rtname "${rt}")"
+	eval hsname=\${$(get_hsname "${hs}")}
+	eval rtname=\${$(get_rtname "${rt}")}
 
 	ip netns exec "${hsname}" sysctl -wq net.ipv6.conf.all.accept_dad=0
 	ip netns exec "${hsname}" sysctl -wq net.ipv6.conf.default.accept_dad=0
@@ -851,11 +815,6 @@ setup_hs()
 	ip netns exec "${rtname}" \
 		sysctl -wq net.ipv4.conf."${RT2HS_DEVNAME}".proxy_arp=1
 
-	# disable the rp_filter otherwise the kernel gets confused about how
-	# to route decap ipv4 packets.
-	ip netns exec "${rtname}" \
-		sysctl -wq net.ipv4.conf."${RT2HS_DEVNAME}".rp_filter=0
-
 	ip netns exec "${rtname}" sh -c "echo 1 > /proc/sys/net/vrf/strict_mode"
 }
 
@@ -947,7 +906,7 @@ check_rt_connectivity()
 	local prefix
 	local rtsrc_nsname
 
-	rtsrc_nsname="$(get_rtname "${rtsrc}")"
+	eval rtsrc_nsname=\${$(get_rtname "${rtsrc}")}
 
 	prefix="$(get_network_prefix "${rtsrc}" "${rtdst}")"
 
@@ -970,7 +929,7 @@ check_hs_ipv6_connectivity()
 	local hsdst="$2"
 	local hssrc_nsname
 
-	hssrc_nsname="$(get_hsname "${hssrc}")"
+	eval hssrc_nsname=\${$(get_hsname "${hssrc}")}
 
 	ip netns exec "${hssrc_nsname}" ping -c 1 -W "${PING_TIMEOUT_SEC}" \
 		"${IPv6_HS_NETWORK}::${hsdst}" >/dev/null 2>&1
@@ -982,7 +941,7 @@ check_hs_ipv4_connectivity()
 	local hsdst="$2"
 	local hssrc_nsname
 
-	hssrc_nsname="$(get_hsname "${hssrc}")"
+	eval hssrc_nsname=\${$(get_hsname "${hssrc}")}
 
 	ip netns exec "${hssrc_nsname}" ping -c 1 -W "${PING_TIMEOUT_SEC}" \
 		"${IPv4_HS_NETWORK}.${hsdst}" >/dev/null 2>&1
@@ -1093,7 +1052,7 @@ rt_x_nextcsid_end_x_behavior_test()
 	local nsname
 	local ret
 
-	nsname="$(get_rtname "${rt}")"
+	eval nsname=\${$(get_rtname "${rt}")}
 
 	__nextcsid_end_x_behavior_test "${nsname}" "add" "${blen}" "${flen}"
 	ret="$?"
diff --git a/tools/testing/selftests/net/srv6_hencap_red_l3vpn_test.sh b/tools/testing/selftests/net/srv6_hencap_red_l3vpn_test.sh
index 28a775654b92..3efce1718c5f 100755
--- a/tools/testing/selftests/net/srv6_hencap_red_l3vpn_test.sh
+++ b/tools/testing/selftests/net/srv6_hencap_red_l3vpn_test.sh
@@ -166,10 +166,8 @@
 #  hs-4->hs-3 |IPv6 DA=fcff:1::e|SRH SIDs=fcff:3::d46|IPv6|...| (i.d)
 #
 
-# Kselftest framework requirement - SKIP code is 4.
-readonly ksft_skip=4
+source lib.sh
 
-readonly RDMSUFF="$(mktemp -u XXXXXXXX)"
 readonly VRF_TID=100
 readonly VRF_DEVNAME="vrf-${VRF_TID}"
 readonly RT2HS_DEVNAME="veth-t${VRF_TID}"
@@ -248,32 +246,18 @@ test_command_or_ksft_skip()
 	fi
 }
 
-get_nodename()
-{
-	local name="$1"
-
-	echo "${name}-${RDMSUFF}"
-}
-
 get_rtname()
 {
 	local rtid="$1"
 
-	get_nodename "rt-${rtid}"
+	echo "rt_${rtid}"
 }
 
 get_hsname()
 {
 	local hsid="$1"
 
-	get_nodename "hs-${hsid}"
-}
-
-__create_namespace()
-{
-	local name="$1"
-
-	ip netns add "${name}"
+	echo "hs_${hsid}"
 }
 
 create_router()
@@ -282,8 +266,7 @@ create_router()
 	local nsname
 
 	nsname="$(get_rtname "${rtid}")"
-
-	__create_namespace "${nsname}"
+	setup_ns "${nsname}"
 }
 
 create_host()
@@ -292,29 +275,12 @@ create_host()
 	local nsname
 
 	nsname="$(get_hsname "${hsid}")"
-
-	__create_namespace "${nsname}"
+	setup_ns "${nsname}"
 }
 
 cleanup()
 {
-	local nsname
-	local i
-
-	# destroy routers
-	for i in ${ROUTERS}; do
-		nsname="$(get_rtname "${i}")"
-
-		ip netns del "${nsname}" &>/dev/null || true
-	done
-
-	# destroy hosts
-	for i in ${HOSTS}; do
-		nsname="$(get_hsname "${i}")"
-
-		ip netns del "${nsname}" &>/dev/null || true
-	done
-
+	cleanup_all_ns
 	# check whether the setup phase was completed successfully or not. In
 	# case of an error during the setup phase of the testing environment,
 	# the selftest is considered as "skipped".
@@ -334,10 +300,10 @@ add_link_rt_pairs()
 	local nsname
 	local neigh_nsname
 
-	nsname="$(get_rtname "${rt}")"
+	eval nsname=\${$(get_rtname "${rt}")}
 
 	for neigh in ${rt_neighs}; do
-		neigh_nsname="$(get_rtname "${neigh}")"
+		eval neigh_nsname=\${$(get_rtname "${neigh}")}
 
 		ip link add "veth-rt-${rt}-${neigh}" netns "${nsname}" \
 			type veth peer name "veth-rt-${neigh}-${rt}" \
@@ -369,7 +335,7 @@ setup_rt_networking()
 	local devname
 	local neigh
 
-	nsname="$(get_rtname "${rt}")"
+	eval nsname=\${$(get_rtname "${rt}")}
 
 	for neigh in ${rt_neighs}; do
 		devname="veth-rt-${rt}-${neigh}"
@@ -387,9 +353,6 @@ setup_rt_networking()
 	ip netns exec "${nsname}" sysctl -wq net.ipv6.conf.all.accept_dad=0
 	ip netns exec "${nsname}" sysctl -wq net.ipv6.conf.default.accept_dad=0
 	ip netns exec "${nsname}" sysctl -wq net.ipv6.conf.all.forwarding=1
-
-	ip netns exec "${nsname}" sysctl -wq net.ipv4.conf.all.rp_filter=0
-	ip netns exec "${nsname}" sysctl -wq net.ipv4.conf.default.rp_filter=0
 	ip netns exec "${nsname}" sysctl -wq net.ipv4.ip_forward=1
 }
 
@@ -403,7 +366,7 @@ setup_rt_local_sids()
 	local nsname
 	local neigh
 
-	nsname="$(get_rtname "${rt}")"
+	eval nsname=\${$(get_rtname "${rt}")}
 
 	for neigh in ${rt_neighs}; do
 		devname="veth-rt-${rt}-${neigh}"
@@ -469,7 +432,7 @@ __setup_rt_policy()
 	local policy=''
 	local n
 
-	nsname="$(get_rtname "${encap_rt}")"
+	eval nsname=\${$(get_rtname "${encap_rt}")}
 
 	for n in ${end_rts}; do
 		policy="${policy}${VPN_LOCATOR_SERVICE}:${n}::${END_FUNC},"
@@ -516,8 +479,8 @@ setup_hs()
 	local hsname
 	local rtname
 
-	hsname="$(get_hsname "${hs}")"
-	rtname="$(get_rtname "${rt}")"
+	eval hsname=\${$(get_hsname "${hs}")}
+	eval rtname=\${$(get_rtname "${rt}")}
 
 	ip netns exec "${hsname}" sysctl -wq net.ipv6.conf.all.accept_dad=0
 	ip netns exec "${hsname}" sysctl -wq net.ipv6.conf.default.accept_dad=0
@@ -555,11 +518,6 @@ setup_hs()
 	ip netns exec "${rtname}" \
 		sysctl -wq net.ipv4.conf."${RT2HS_DEVNAME}".proxy_arp=1
 
-	# disable the rp_filter otherwise the kernel gets confused about how
-	# to route decap ipv4 packets.
-	ip netns exec "${rtname}" \
-		sysctl -wq net.ipv4.conf."${RT2HS_DEVNAME}".rp_filter=0
-
 	ip netns exec "${rtname}" sh -c "echo 1 > /proc/sys/net/vrf/strict_mode"
 }
 
@@ -656,7 +614,7 @@ check_rt_connectivity()
 	local prefix
 	local rtsrc_nsname
 
-	rtsrc_nsname="$(get_rtname "${rtsrc}")"
+	eval rtsrc_nsname=\${$(get_rtname "${rtsrc}")}
 
 	prefix="$(get_network_prefix "${rtsrc}" "${rtdst}")"
 
@@ -679,7 +637,7 @@ check_hs_ipv6_connectivity()
 	local hsdst="$2"
 	local hssrc_nsname
 
-	hssrc_nsname="$(get_hsname "${hssrc}")"
+	eval hssrc_nsname=\${$(get_hsname "${hssrc}")}
 
 	ip netns exec "${hssrc_nsname}" ping -c 1 -W "${PING_TIMEOUT_SEC}" \
 		"${IPv6_HS_NETWORK}::${hsdst}" >/dev/null 2>&1
@@ -691,7 +649,7 @@ check_hs_ipv4_connectivity()
 	local hsdst="$2"
 	local hssrc_nsname
 
-	hssrc_nsname="$(get_hsname "${hssrc}")"
+	eval hssrc_nsname=\${$(get_hsname "${hssrc}")}
 
 	ip netns exec "${hssrc_nsname}" ping -c 1 -W "${PING_TIMEOUT_SEC}" \
 		"${IPv4_HS_NETWORK}.${hsdst}" >/dev/null 2>&1
diff --git a/tools/testing/selftests/net/srv6_hl2encap_red_l2vpn_test.sh b/tools/testing/selftests/net/srv6_hl2encap_red_l2vpn_test.sh
index cb4177d41b21..cabc70538ffe 100755
--- a/tools/testing/selftests/net/srv6_hl2encap_red_l2vpn_test.sh
+++ b/tools/testing/selftests/net/srv6_hl2encap_red_l2vpn_test.sh
@@ -116,10 +116,8 @@
 #  hs-2->hs-1 |IPv6 DA=fcff:4::e|SRH SIDs=fcff:3::e,fcff:1::d2|eth|...| (i.b)
 #
 
-# Kselftest framework requirement - SKIP code is 4.
-readonly ksft_skip=4
+source lib.sh
 
-readonly RDMSUFF="$(mktemp -u XXXXXXXX)"
 readonly DUMMY_DEVNAME="dum0"
 readonly RT2HS_DEVNAME="veth-hs"
 readonly HS_VETH_NAME="veth0"
@@ -199,32 +197,18 @@ test_command_or_ksft_skip()
 	fi
 }
 
-get_nodename()
-{
-	local name="$1"
-
-	echo "${name}-${RDMSUFF}"
-}
-
 get_rtname()
 {
 	local rtid="$1"
 
-	get_nodename "rt-${rtid}"
+	echo "rt_${rtid}"
 }
 
 get_hsname()
 {
 	local hsid="$1"
 
-	get_nodename "hs-${hsid}"
-}
-
-__create_namespace()
-{
-	local name="$1"
-
-	ip netns add "${name}"
+	echo "hs_${hsid}"
 }
 
 create_router()
@@ -233,8 +217,7 @@ create_router()
 	local nsname
 
 	nsname="$(get_rtname "${rtid}")"
-
-	__create_namespace "${nsname}"
+	setup_ns "${nsname}"
 }
 
 create_host()
@@ -243,28 +226,12 @@ create_host()
 	local nsname
 
 	nsname="$(get_hsname "${hsid}")"
-
-	__create_namespace "${nsname}"
+	setup_ns "${nsname}"
 }
 
 cleanup()
 {
-	local nsname
-	local i
-
-	# destroy routers
-	for i in ${ROUTERS}; do
-		nsname="$(get_rtname "${i}")"
-
-		ip netns del "${nsname}" &>/dev/null || true
-	done
-
-	# destroy hosts
-	for i in ${HOSTS}; do
-		nsname="$(get_hsname "${i}")"
-
-		ip netns del "${nsname}" &>/dev/null || true
-	done
+	cleanup_all_ns
 
 	# check whether the setup phase was completed successfully or not. In
 	# case of an error during the setup phase of the testing environment,
@@ -285,10 +252,10 @@ add_link_rt_pairs()
 	local nsname
 	local neigh_nsname
 
-	nsname="$(get_rtname "${rt}")"
+	eval nsname=\${$(get_rtname "${rt}")}
 
 	for neigh in ${rt_neighs}; do
-		neigh_nsname="$(get_rtname "${neigh}")"
+		eval neigh_nsname=\${$(get_rtname "${neigh}")}
 
 		ip link add "veth-rt-${rt}-${neigh}" netns "${nsname}" \
 			type veth peer name "veth-rt-${neigh}-${rt}" \
@@ -320,7 +287,7 @@ setup_rt_networking()
 	local devname
 	local neigh
 
-	nsname="$(get_rtname "${rt}")"
+	eval nsname=\${$(get_rtname "${rt}")}
 
 	for neigh in ${rt_neighs}; do
 		devname="veth-rt-${rt}-${neigh}"
@@ -341,9 +308,6 @@ setup_rt_networking()
 	ip netns exec "${nsname}" sysctl -wq net.ipv6.conf.all.accept_dad=0
 	ip netns exec "${nsname}" sysctl -wq net.ipv6.conf.default.accept_dad=0
 	ip netns exec "${nsname}" sysctl -wq net.ipv6.conf.all.forwarding=1
-
-	ip netns exec "${nsname}" sysctl -wq net.ipv4.conf.all.rp_filter=0
-	ip netns exec "${nsname}" sysctl -wq net.ipv4.conf.default.rp_filter=0
 	ip netns exec "${nsname}" sysctl -wq net.ipv4.ip_forward=1
 }
 
@@ -357,7 +321,7 @@ setup_rt_local_sids()
 	local nsname
 	local neigh
 
-	nsname="$(get_rtname "${rt}")"
+	eval nsname=\${$(get_rtname "${rt}")}
 
 	for neigh in ${rt_neighs}; do
 		devname="veth-rt-${rt}-${neigh}"
@@ -407,7 +371,7 @@ __setup_rt_policy()
 	local policy=''
 	local n
 
-	nsname="$(get_rtname "${encap_rt}")"
+	eval nsname=\${$(get_rtname "${encap_rt}")}
 
 	for n in ${end_rts}; do
 		policy="${policy}${VPN_LOCATOR_SERVICE}:${n}::${END_FUNC},"
@@ -446,7 +410,7 @@ setup_decap()
 	local rt="$1"
 	local nsname
 
-	nsname="$(get_rtname "${rt}")"
+	eval nsname=\${$(get_rtname "${rt}")}
 
 	# Local End.DX2 behavior
 	ip -netns "${nsname}" -6 route \
@@ -463,8 +427,8 @@ setup_hs()
 	local hsname
 	local rtname
 
-	hsname="$(get_hsname "${hs}")"
-	rtname="$(get_rtname "${rt}")"
+	eval hsname=\${$(get_hsname "${hs}")}
+	eval rtname=\${$(get_rtname "${rt}")}
 
 	ip netns exec "${hsname}" sysctl -wq net.ipv6.conf.all.accept_dad=0
 	ip netns exec "${hsname}" sysctl -wq net.ipv6.conf.default.accept_dad=0
@@ -486,11 +450,6 @@ setup_hs()
 		add "${IPv4_HS_NETWORK}.254/24" dev "${RT2HS_DEVNAME}"
 
 	ip -netns "${rtname}" link set "${RT2HS_DEVNAME}" up
-
-	# disable the rp_filter otherwise the kernel gets confused about how
-	# to route decap ipv4 packets.
-	ip netns exec "${rtname}" \
-		sysctl -wq net.ipv4.conf."${RT2HS_DEVNAME}".rp_filter=0
 }
 
 # set an auto-generated mac address
@@ -508,7 +467,7 @@ set_mac_address()
 	local ifname="$4"
 	local nsname
 
-	nsname=$(get_nodename "${nodename}")
+	eval nsname=\${${nodename}}
 
 	ip -netns "${nsname}" link set dev "${ifname}" down
 
@@ -532,7 +491,7 @@ set_host_l2peer()
 	local hssrc_name
 	local ipaddr
 
-	hssrc_name="$(get_hsname "${hssrc}")"
+	eval hssrc_name=\${$(get_hsname "${hssrc}")}
 
 	if [ "${proto}" -eq 6 ]; then
 		ipaddr="${ipprefix}::${hsdst}"
@@ -562,7 +521,7 @@ setup_l2vpn()
 	local rtdst="${hsdst}"
 
 	# set fixed mac for source node and the neigh MAC address
-	set_mac_address "hs-${hssrc}" "${hssrc}" "${hssrc}" "${HS_VETH_NAME}"
+	set_mac_address "hs_${hssrc}" "${hssrc}" "${hssrc}" "${HS_VETH_NAME}"
 	set_host_l2peer "${hssrc}" "${hsdst}" "${IPv6_HS_NETWORK}" 6
 	set_host_l2peer "${hssrc}" "${hsdst}" "${IPv4_HS_NETWORK}" 4
 
@@ -570,7 +529,7 @@ setup_l2vpn()
 	# to the mac address of the remote peer (L2 VPN destination host).
 	# Otherwise, traffic coming from the source host is dropped at the
 	# ingress router.
-	set_mac_address "rt-${rtsrc}" "${hsdst}" 254 "${RT2HS_DEVNAME}"
+	set_mac_address "rt_${rtsrc}" "${hsdst}" 254 "${RT2HS_DEVNAME}"
 
 	# set the SRv6 Policies at the ingress router
 	setup_rt_policy_ipv6 "${hsdst}" "${rtsrc}" "${end_rts}" "${rtdst}" \
@@ -647,7 +606,7 @@ check_rt_connectivity()
 	local prefix
 	local rtsrc_nsname
 
-	rtsrc_nsname="$(get_rtname "${rtsrc}")"
+	eval rtsrc_nsname=\${$(get_rtname "${rtsrc}")}
 
 	prefix="$(get_network_prefix "${rtsrc}" "${rtdst}")"
 
@@ -670,7 +629,7 @@ check_hs_ipv6_connectivity()
 	local hsdst="$2"
 	local hssrc_nsname
 
-	hssrc_nsname="$(get_hsname "${hssrc}")"
+	eval hssrc_nsname=\${$(get_hsname "${hssrc}")}
 
 	ip netns exec "${hssrc_nsname}" ping -c 1 -W "${PING_TIMEOUT_SEC}" \
 		"${IPv6_HS_NETWORK}::${hsdst}" >/dev/null 2>&1
@@ -682,7 +641,7 @@ check_hs_ipv4_connectivity()
 	local hsdst="$2"
 	local hssrc_nsname
 
-	hssrc_nsname="$(get_hsname "${hssrc}")"
+	eval hssrc_nsname=\${$(get_hsname "${hssrc}")}
 
 	ip netns exec "${hssrc_nsname}" ping -c 1 -W "${PING_TIMEOUT_SEC}" \
 		"${IPv4_HS_NETWORK}.${hsdst}" >/dev/null 2>&1
diff --git a/tools/testing/selftests/net/test_bridge_neigh_suppress.sh b/tools/testing/selftests/net/test_bridge_neigh_suppress.sh
index 02b986c9c247..9067197c9055 100755
--- a/tools/testing/selftests/net/test_bridge_neigh_suppress.sh
+++ b/tools/testing/selftests/net/test_bridge_neigh_suppress.sh
@@ -51,7 +51,9 @@ ret=0
 # All tests in this script. Can be overridden with -t option.
 TESTS="
 	neigh_suppress_arp
+	neigh_suppress_uc_arp
 	neigh_suppress_ns
+	neigh_suppress_uc_ns
 	neigh_vlan_suppress_arp
 	neigh_vlan_suppress_ns
 "
@@ -388,6 +390,52 @@ neigh_suppress_arp()
 	neigh_suppress_arp_common $vid $sip $tip
 }
 
+neigh_suppress_uc_arp_common()
+{
+	local vid=$1; shift
+	local sip=$1; shift
+	local tip=$1; shift
+	local tmac
+
+	echo
+	echo "Unicast ARP, per-port ARP suppression - VLAN $vid"
+	echo "-----------------------------------------------"
+
+	run_cmd "bridge -n $sw1 link set dev vx0 neigh_suppress on"
+	run_cmd "bridge -n $sw1 -d link show dev vx0 | grep \"neigh_suppress on\""
+	log_test $? 0 "\"neigh_suppress\" is on"
+
+	tmac=$(ip -n $h2 -j -p link show eth0.$vid | jq -r '.[]["address"]')
+	run_cmd "bridge -n $sw1 fdb replace $tmac dev vx0 master static vlan $vid"
+	run_cmd "ip -n $sw1 neigh replace $tip lladdr $tmac nud permanent dev br0.$vid"
+
+	run_cmd "tc -n $h1 qdisc replace dev eth0.$vid clsact"
+	run_cmd "tc -n $h1 filter replace dev eth0.$vid ingress pref 1 handle 101 proto arp flower arp_sip $tip arp_op reply action pass"
+
+	run_cmd "tc -n $h2 qdisc replace dev eth0.$vid clsact"
+	run_cmd "tc -n $h2 filter replace dev eth0.$vid egress pref 1 handle 101 proto arp flower arp_tip $sip arp_op reply action pass"
+
+	run_cmd "ip netns exec $h1 mausezahn eth0.$vid -c 1 -a own -b $tmac -t arp 'request sip=$sip, tip=$tip, tmac=$tmac' -q"
+	tc_check_packets $h1 "dev eth0.$vid ingress" 101 1
+	log_test $? 0 "Unicast ARP, suppression on, h1 filter"
+	tc_check_packets $h2 "dev eth0.$vid egress" 101 1
+	log_test $? 0 "Unicast ARP, suppression on, h2 filter"
+}
+
+neigh_suppress_uc_arp()
+{
+	local vid=10
+	local sip=192.0.2.1
+	local tip=192.0.2.2
+
+	neigh_suppress_uc_arp_common $vid $sip $tip
+
+	vid=20
+	sip=192.0.2.17
+	tip=192.0.2.18
+	neigh_suppress_uc_arp_common $vid $sip $tip
+}
+
 neigh_suppress_ns_common()
 {
 	local vid=$1; shift
@@ -494,6 +542,78 @@ neigh_suppress_ns()
 	neigh_suppress_ns_common $vid $saddr $daddr $maddr
 }
 
+icmpv6_header_get()
+{
+	local csum=$1; shift
+	local tip=$1; shift
+	local type
+	local p
+
+	# Type 135 (Neighbor Solicitation), hex format
+	type="87"
+	p=$(:
+		)"$type:"$(                     : ICMPv6.type
+		)"00:"$(                        : ICMPv6.code
+		)"$csum:"$(                     : ICMPv6.checksum
+		)"00:00:00:00:"$(               : Reserved
+	        )"$tip:"$(	                : Target Address
+		)
+	echo $p
+}
+
+neigh_suppress_uc_ns_common()
+{
+	local vid=$1; shift
+	local sip=$1; shift
+	local dip=$1; shift
+	local full_dip=$1; shift
+	local csum=$1; shift
+	local tmac
+
+	echo
+	echo "Unicast NS, per-port NS suppression - VLAN $vid"
+	echo "---------------------------------------------"
+
+	run_cmd "bridge -n $sw1 link set dev vx0 neigh_suppress on"
+	run_cmd "bridge -n $sw1 -d link show dev vx0 | grep \"neigh_suppress on\""
+	log_test $? 0 "\"neigh_suppress\" is on"
+
+	tmac=$(ip -n $h2 -j -p link show eth0.$vid | jq -r '.[]["address"]')
+	run_cmd "bridge -n $sw1 fdb replace $tmac dev vx0 master static vlan $vid"
+	run_cmd "ip -n $sw1 -6 neigh replace $dip lladdr $tmac nud permanent dev br0.$vid"
+
+	run_cmd "tc -n $h1 qdisc replace dev eth0.$vid clsact"
+	run_cmd "tc -n $h1 filter replace dev eth0.$vid ingress pref 1 handle 101 proto ipv6 flower ip_proto icmpv6 src_ip $dip type 136 code 0 action pass"
+
+	run_cmd "tc -n $h2 qdisc replace dev eth0.$vid clsact"
+	run_cmd "tc -n $h2 filter replace dev eth0.$vid egress pref 1 handle 101 proto ipv6 flower ip_proto icmpv6 dst_ip $sip type 136 code 0 action pass"
+
+	run_cmd "ip netns exec $h1 mausezahn -6 eth0.$vid -c 1 -a own -b $tmac -A $sip -B $dip -t ip hop=255,next=58,payload=$(icmpv6_header_get $csum $full_dip) -q"
+	tc_check_packets $h1 "dev eth0.$vid ingress" 101 1
+	log_test $? 0 "Unicast NS, suppression on, h1 filter"
+	tc_check_packets $h2 "dev eth0.$vid egress" 101 1
+	log_test $? 0 "Unicast NS, suppression on, h2 filter"
+}
+
+neigh_suppress_uc_ns()
+{
+	local vid=10
+	local saddr=2001:db8:1::1
+	local daddr=2001:db8:1::2
+	local full_daddr=20:01:0d:b8:00:01:00:00:00:00:00:00:00:00:00:02
+	local csum="ef:79"
+
+	neigh_suppress_uc_ns_common $vid $saddr $daddr $full_daddr $csum
+
+	vid=20
+	saddr=2001:db8:2::1
+	daddr=2001:db8:2::2
+	full_daddr=20:01:0d:b8:00:02:00:00:00:00:00:00:00:00:00:02
+	csum="ef:76"
+
+	neigh_suppress_uc_ns_common $vid $saddr $daddr $full_daddr $csum
+}
+
 neigh_vlan_suppress_arp()
 {
 	local vid1=10
@@ -825,6 +945,11 @@ if [ ! -x "$(command -v jq)" ]; then
 	exit $ksft_skip
 fi
 
+if [ ! -x "$(command -v mausezahn)" ]; then
+	echo "SKIP: Could not run test without mausezahn tool"
+	exit $ksft_skip
+fi
+
 bridge link help 2>&1 | grep -q "neigh_vlan_suppress"
 if [ $? -ne 0 ]; then
    echo "SKIP: iproute2 bridge too old, missing per-VLAN neighbor suppression support"
diff --git a/tools/testing/selftests/net/udpgro.sh b/tools/testing/selftests/net/udpgro.sh
index d5ffd8c9172e..1dc337c709f8 100755
--- a/tools/testing/selftests/net/udpgro.sh
+++ b/tools/testing/selftests/net/udpgro.sh
@@ -3,7 +3,7 @@
 #
 # Run a series of udpgro functional tests.
 
-source net_helper.sh
+source lib.sh
 
 readonly PEER_NS="ns-peer-$(mktemp -u XXXXXX)"
 
diff --git a/tools/testing/selftests/net/udpgro_bench.sh b/tools/testing/selftests/net/udpgro_bench.sh
index 815fad8c53a8..54fa4821bc5e 100755
--- a/tools/testing/selftests/net/udpgro_bench.sh
+++ b/tools/testing/selftests/net/udpgro_bench.sh
@@ -3,7 +3,7 @@
 #
 # Run a series of udpgro benchmarks
 
-source net_helper.sh
+source lib.sh
 
 readonly PEER_NS="ns-peer-$(mktemp -u XXXXXX)"
 
diff --git a/tools/testing/selftests/net/udpgro_frglist.sh b/tools/testing/selftests/net/udpgro_frglist.sh
index 5f3d1a110d11..9a2cfec1153e 100755
--- a/tools/testing/selftests/net/udpgro_frglist.sh
+++ b/tools/testing/selftests/net/udpgro_frglist.sh
@@ -3,7 +3,7 @@
 #
 # Run a series of udpgro benchmarks
 
-source net_helper.sh
+source lib.sh
 
 readonly PEER_NS="ns-peer-$(mktemp -u XXXXXX)"
 
diff --git a/tools/testing/selftests/net/udpgro_fwd.sh b/tools/testing/selftests/net/udpgro_fwd.sh
index f22f6c66997e..a39fdc4aa2ff 100755
--- a/tools/testing/selftests/net/udpgro_fwd.sh
+++ b/tools/testing/selftests/net/udpgro_fwd.sh
@@ -1,7 +1,7 @@
 #!/bin/bash
 # SPDX-License-Identifier: GPL-2.0
 
-source net_helper.sh
+source lib.sh
 
 BPF_FILE="lib/xdp_dummy.bpf.o"
 readonly BASE="ns-$(mktemp -u XXXXXX)"
diff --git a/tools/testing/selftests/tc-testing/tc-tests/infra/qdiscs.json b/tools/testing/selftests/tc-testing/tc-tests/infra/qdiscs.json
index ddc97ecd8b39..9aa44d8176d9 100644
--- a/tools/testing/selftests/tc-testing/tc-tests/infra/qdiscs.json
+++ b/tools/testing/selftests/tc-testing/tc-tests/infra/qdiscs.json
@@ -600,5 +600,40 @@
         "matchPattern": "qdisc hfsc",
         "matchCount": "1",
         "teardown": ["$TC qdisc del dev $DEV1 root handle 1: drr"]
+    },
+    {
+        "id": "309e",
+        "name": "Test HFSC eltree double add with reentrant enqueue behaviour on netem",
+        "category": [
+            "qdisc",
+            "hfsc"
+        ],
+        "plugins": {
+            "requires": "nsPlugin"
+        },
+        "setup": [
+            "$IP link set dev $DUMMY up || true",
+            "$IP addr add 10.10.11.10/24 dev $DUMMY || true",
+            "$TC qdisc add dev $DUMMY root handle 1: tbf rate 8bit burst 100b latency 1s",
+            "$TC qdisc add dev $DUMMY parent 1:0 handle 2:0 hfsc",
+            "ping -I $DUMMY -f -c10 -s48 -W0.001 10.10.11.1 || true",
+            "$TC class add dev $DUMMY parent 2:0 classid 2:1 hfsc rt m2 20Kbit",
+            "$TC qdisc add dev $DUMMY parent 2:1 handle 3:0 netem duplicate 100%",
+            "$TC class add dev $DUMMY parent 2:0 classid 2:2 hfsc rt m2 20Kbit",
+            "$TC filter add dev $DUMMY parent 2:0 protocol ip prio 1 u32 match ip dst 10.10.11.2/32 flowid 2:1",
+            "$TC filter add dev $DUMMY parent 2:0 protocol ip prio 2 u32 match ip dst 10.10.11.3/32 flowid 2:2",
+            "ping -c 1 10.10.11.2 -I$DUMMY > /dev/null || true",
+            "$TC filter del dev $DUMMY parent 2:0 protocol ip prio 1",
+            "$TC class del dev $DUMMY classid 2:1",
+            "ping -c 1 10.10.11.3 -I$DUMMY > /dev/null || true"
+        ],
+        "cmdUnderTest": "$TC class change dev $DUMMY parent 2:0 classid 2:2 hfsc sc m2 20Kbit",
+        "expExitCode": "0",
+        "verifyCmd": "$TC -j class ls dev $DUMMY classid 2:1",
+        "matchJSON": [],
+        "teardown": [
+            "$TC qdisc del dev $DUMMY handle 1:0 root",
+            "$IP addr del 10.10.10.10/24 dev $DUMMY || true"
+        ]
     }
 ]
diff --git a/tools/testing/selftests/tc-testing/tdc.sh b/tools/testing/selftests/tc-testing/tdc.sh
index cddff1772e10..589b18ed758a 100755
--- a/tools/testing/selftests/tc-testing/tdc.sh
+++ b/tools/testing/selftests/tc-testing/tdc.sh
@@ -31,6 +31,10 @@ try_modprobe act_skbedit
 try_modprobe act_skbmod
 try_modprobe act_tunnel_key
 try_modprobe act_vlan
+try_modprobe act_ife
+try_modprobe act_meta_mark
+try_modprobe act_meta_skbtcindex
+try_modprobe act_meta_skbprio
 try_modprobe cls_basic
 try_modprobe cls_bpf
 try_modprobe cls_cgroup
diff --git a/tools/testing/selftests/wireguard/netns.sh b/tools/testing/selftests/wireguard/netns.sh
index 55500f901fbc..a8f550aecb35 100755
--- a/tools/testing/selftests/wireguard/netns.sh
+++ b/tools/testing/selftests/wireguard/netns.sh
@@ -611,6 +611,35 @@ n0 wg set wg0 peer "$pub2" allowed-ips "$allowedips"
 } < <(n0 wg show wg0 allowed-ips)
 ip0 link del wg0
 
+allowedips=( )
+for i in {1..197}; do
+        allowedips+=( 192.168.0.$i )
+        allowedips+=( abcd::$i )
+done
+saved_ifs="$IFS"
+IFS=,
+allowedips="${allowedips[*]}"
+IFS="$saved_ifs"
+ip0 link add wg0 type wireguard
+n0 wg set wg0 peer "$pub1" allowed-ips "$allowedips"
+n0 wg set wg0 peer "$pub1" allowed-ips -192.168.0.1/32,-192.168.0.20/32,-192.168.0.100/32,-abcd::1/128,-abcd::20/128,-abcd::100/128
+{
+	read -r pub allowedips
+	[[ $pub == "$pub1" ]]
+	i=0
+	for ip in $allowedips; do
+		[[ $ip != "192.168.0.1" ]]
+		[[ $ip != "192.168.0.20" ]]
+		[[ $ip != "192.168.0.100" ]]
+		[[ $ip != "abcd::1" ]]
+		[[ $ip != "abcd::20" ]]
+		[[ $ip != "abcd::100" ]]
+		((++i))
+	done
+	((i == 388))
+} < <(n0 wg show wg0 allowed-ips)
+ip0 link del wg0
+
 ! n0 wg show doesnotexist || false
 
 ip0 link add wg0 type wireguard
diff --git a/tools/testing/selftests/wireguard/qemu/Makefile b/tools/testing/selftests/wireguard/qemu/Makefile
index 35856b11c143..791d21b736a5 100644
--- a/tools/testing/selftests/wireguard/qemu/Makefile
+++ b/tools/testing/selftests/wireguard/qemu/Makefile
@@ -43,7 +43,7 @@ $(eval $(call tar_download,IPROUTE2,iproute2,5.17.0,.tar.gz,https://www.kernel.o
 $(eval $(call tar_download,IPTABLES,iptables,1.8.7,.tar.bz2,https://www.netfilter.org/projects/iptables/files/,c109c96bb04998cd44156622d36f8e04b140701ec60531a10668cfdff5e8d8f0))
 $(eval $(call tar_download,NMAP,nmap,7.92,.tgz,https://nmap.org/dist/,064183ea642dc4c12b1ab3b5358ce1cef7d2e7e11ffa2849f16d339f5b717117))
 $(eval $(call tar_download,IPUTILS,iputils,s20190709,.tar.gz,https://github.com/iputils/iputils/archive/s20190709.tar.gz/#,a15720dd741d7538dd2645f9f516d193636ae4300ff7dbc8bfca757bf166490a))
-$(eval $(call tar_download,WIREGUARD_TOOLS,wireguard-tools,1.0.20210914,.tar.xz,https://git.zx2c4.com/wireguard-tools/snapshot/,97ff31489217bb265b7ae850d3d0f335ab07d2652ba1feec88b734bc96bd05ac))
+$(eval $(call tar_download,WIREGUARD_TOOLS,wireguard-tools,1.0.20250521,.tar.xz,https://git.zx2c4.com/wireguard-tools/snapshot/,b6f2628b85b1b23cc06517ec9c74f82d52c4cdbd020f3dd2f00c972a1782950e))
 
 export CFLAGS := -O3 -pipe
 ifeq ($(HOST_ARCH),$(ARCH))
@@ -401,6 +401,7 @@ $(BASH_PATH)/.installed: $(BASH_TAR)
 	flock -s $<.lock tar -C $(BUILD_PATH) -xf $<
 	touch $@
 
+$(BASH_PATH)/bash: export CFLAGS_FOR_BUILD += -std=gnu17
 $(BASH_PATH)/bash: | $(BASH_PATH)/.installed $(USERSPACE_DEPS)
 	cd $(BASH_PATH) && ./configure --prefix=/ $(CROSS_COMPILE_FLAG) --without-bash-malloc --disable-debugger --disable-help-builtin --disable-history --disable-progcomp --disable-readline --disable-mem-scramble
 	$(MAKE) -C $(BASH_PATH)
diff --git a/tools/testing/selftests/wireguard/qemu/debug.config b/tools/testing/selftests/wireguard/qemu/debug.config
index c305d2f613f0..5d39f43dd667 100644
--- a/tools/testing/selftests/wireguard/qemu/debug.config
+++ b/tools/testing/selftests/wireguard/qemu/debug.config
@@ -22,7 +22,6 @@ CONFIG_HAVE_ARCH_KASAN=y
 CONFIG_KASAN=y
 CONFIG_KASAN_INLINE=y
 CONFIG_UBSAN=y
-CONFIG_UBSAN_SANITIZE_ALL=y
 CONFIG_DEBUG_KMEMLEAK=y
 CONFIG_DEBUG_STACK_USAGE=y
 CONFIG_DEBUG_SHIRQ=y
diff --git a/tools/testing/vsock/timeout.c b/tools/testing/vsock/timeout.c
index 44aee49b6cee..1453d38e08bb 100644
--- a/tools/testing/vsock/timeout.c
+++ b/tools/testing/vsock/timeout.c
@@ -21,6 +21,7 @@
 #include <stdbool.h>
 #include <unistd.h>
 #include <stdio.h>
+#include <time.h>
 #include "timeout.h"
 
 static volatile bool timeout;
@@ -28,6 +29,8 @@ static volatile bool timeout;
 /* SIGALRM handler function.  Do not use sleep(2), alarm(2), or
  * setitimer(2) while using this API - they may interfere with each
  * other.
+ *
+ * If you need to sleep, please use timeout_sleep() provided by this API.
  */
 void sigalrm(int signo)
 {
@@ -58,3 +61,18 @@ void timeout_end(void)
 	alarm(0);
 	timeout = false;
 }
+
+/* Sleep in a timeout section.
+ *
+ * nanosleep(2) can be used with this API since POSIX.1 explicitly
+ * specifies that it does not interact with signals.
+ */
+int timeout_usleep(useconds_t usec)
+{
+	struct timespec ts = {
+		.tv_sec = usec / 1000000,
+		.tv_nsec = (usec % 1000000) * 1000,
+	};
+
+	return nanosleep(&ts, NULL);
+}
diff --git a/tools/testing/vsock/timeout.h b/tools/testing/vsock/timeout.h
index ecb7c840e65a..1c3fcad87a49 100644
--- a/tools/testing/vsock/timeout.h
+++ b/tools/testing/vsock/timeout.h
@@ -11,5 +11,6 @@ void sigalrm(int signo);
 void timeout_begin(unsigned int seconds);
 void timeout_check(const char *operation);
 void timeout_end(void);
+int timeout_usleep(useconds_t usec);
 
 #endif /* TIMEOUT_H */
diff --git a/tools/testing/vsock/util.c b/tools/testing/vsock/util.c
index de25892f865f..0c7e9cbcbc85 100644
--- a/tools/testing/vsock/util.c
+++ b/tools/testing/vsock/util.c
@@ -17,6 +17,7 @@
 #include <assert.h>
 #include <sys/epoll.h>
 #include <sys/mman.h>
+#include <linux/sockios.h>
 
 #include "timeout.h"
 #include "control.h"
@@ -96,6 +97,30 @@ void vsock_wait_remote_close(int fd)
 	close(epollfd);
 }
 
+/* Wait until transport reports no data left to be sent.
+ * Return false if transport does not implement the unsent_bytes() callback.
+ */
+bool vsock_wait_sent(int fd)
+{
+	int ret, sock_bytes_unsent;
+
+	timeout_begin(TIMEOUT);
+	do {
+		ret = ioctl(fd, SIOCOUTQ, &sock_bytes_unsent);
+		if (ret < 0) {
+			if (errno == EOPNOTSUPP)
+				break;
+
+			perror("ioctl(SIOCOUTQ)");
+			exit(EXIT_FAILURE);
+		}
+		timeout_check("SIOCOUTQ");
+	} while (sock_bytes_unsent != 0);
+	timeout_end();
+
+	return !ret;
+}
+
 /* Create socket <type>, bind to <cid, port> and return the file descriptor. */
 int vsock_bind(unsigned int cid, unsigned int port, int type)
 {
@@ -798,3 +823,16 @@ void enable_so_zerocopy_check(int fd)
 	setsockopt_int_check(fd, SOL_SOCKET, SO_ZEROCOPY, 1,
 			     "setsockopt SO_ZEROCOPY");
 }
+
+void enable_so_linger(int fd, int timeout)
+{
+	struct linger optval = {
+		.l_onoff = 1,
+		.l_linger = timeout
+	};
+
+	if (setsockopt(fd, SOL_SOCKET, SO_LINGER, &optval, sizeof(optval))) {
+		perror("setsockopt(SO_LINGER)");
+		exit(EXIT_FAILURE);
+	}
+}
diff --git a/tools/testing/vsock/util.h b/tools/testing/vsock/util.h
index d1f765ce3eee..5e2db67072d5 100644
--- a/tools/testing/vsock/util.h
+++ b/tools/testing/vsock/util.h
@@ -54,6 +54,7 @@ int vsock_stream_listen(unsigned int cid, unsigned int port);
 int vsock_seqpacket_accept(unsigned int cid, unsigned int port,
 			   struct sockaddr_vm *clientaddrp);
 void vsock_wait_remote_close(int fd);
+bool vsock_wait_sent(int fd);
 void send_buf(int fd, const void *buf, size_t len, int flags,
 	      ssize_t expected_ret);
 void recv_buf(int fd, void *buf, size_t len, int flags, ssize_t expected_ret);
@@ -79,4 +80,5 @@ void setsockopt_int_check(int fd, int level, int optname, int val,
 void setsockopt_timeval_check(int fd, int level, int optname,
 			      struct timeval val, char const *errmsg);
 void enable_so_zerocopy_check(int fd);
+void enable_so_linger(int fd, int timeout);
 #endif /* UTIL_H */
diff --git a/tools/testing/vsock/vsock_test.c b/tools/testing/vsock/vsock_test.c
index 613551132a96..f669baaa0dca 100644
--- a/tools/testing/vsock/vsock_test.c
+++ b/tools/testing/vsock/vsock_test.c
@@ -21,7 +21,6 @@
 #include <poll.h>
 #include <signal.h>
 #include <sys/ioctl.h>
-#include <linux/sockios.h>
 #include <linux/time64.h>
 
 #include "vsock_test_zerocopy.h"
@@ -1058,18 +1057,39 @@ static void sigpipe(int signo)
 	have_sigpipe = 1;
 }
 
+#define SEND_SLEEP_USEC (10 * 1000)
+
 static void test_stream_check_sigpipe(int fd)
 {
 	ssize_t res;
 
 	have_sigpipe = 0;
 
-	res = send(fd, "A", 1, 0);
-	if (res != -1) {
-		fprintf(stderr, "expected send(2) failure, got %zi\n", res);
-		exit(EXIT_FAILURE);
+	/* When the other peer calls shutdown(SHUT_RD), there is a chance that
+	 * the send() call could occur before the message carrying the close
+	 * information arrives over the transport. In such cases, the send()
+	 * might still succeed. To avoid this race, let's retry the send() call
+	 * a few times, ensuring the test is more reliable.
+	 */
+	timeout_begin(TIMEOUT);
+	while(1) {
+		res = send(fd, "A", 1, 0);
+		if (res == -1 && errno != EINTR)
+			break;
+
+		/* Sleep a little before trying again to avoid flooding the
+		 * other peer and filling its receive buffer, causing
+		 * false-negative.
+		 */
+		timeout_usleep(SEND_SLEEP_USEC);
+		timeout_check("send");
 	}
+	timeout_end();
 
+	if (errno != EPIPE) {
+		fprintf(stderr, "unexpected send(2) errno %d\n", errno);
+		exit(EXIT_FAILURE);
+	}
 	if (!have_sigpipe) {
 		fprintf(stderr, "SIGPIPE expected\n");
 		exit(EXIT_FAILURE);
@@ -1077,12 +1097,21 @@ static void test_stream_check_sigpipe(int fd)
 
 	have_sigpipe = 0;
 
-	res = send(fd, "A", 1, MSG_NOSIGNAL);
-	if (res != -1) {
-		fprintf(stderr, "expected send(2) failure, got %zi\n", res);
-		exit(EXIT_FAILURE);
+	timeout_begin(TIMEOUT);
+	while(1) {
+		res = send(fd, "A", 1, MSG_NOSIGNAL);
+		if (res == -1 && errno != EINTR)
+			break;
+
+		timeout_usleep(SEND_SLEEP_USEC);
+		timeout_check("send");
 	}
+	timeout_end();
 
+	if (errno != EPIPE) {
+		fprintf(stderr, "unexpected send(2) errno %d\n", errno);
+		exit(EXIT_FAILURE);
+	}
 	if (have_sigpipe) {
 		fprintf(stderr, "SIGPIPE not expected\n");
 		exit(EXIT_FAILURE);
@@ -1250,7 +1279,7 @@ static void test_unsent_bytes_server(const struct test_opts *opts, int type)
 static void test_unsent_bytes_client(const struct test_opts *opts, int type)
 {
 	unsigned char buf[MSG_BUF_IOCTL_LEN];
-	int ret, fd, sock_bytes_unsent;
+	int fd;
 
 	fd = vsock_connect(opts->peer_cid, opts->peer_port, type);
 	if (fd < 0) {
@@ -1267,22 +1296,12 @@ static void test_unsent_bytes_client(const struct test_opts *opts, int type)
 	/* SIOCOUTQ isn't guaranteed to instantly track sent data. Even though
 	 * the "RECEIVED" message means that the other side has received the
 	 * data, there can be a delay in our kernel before updating the "unsent
-	 * bytes" counter. Repeat SIOCOUTQ until it returns 0.
+	 * bytes" counter. vsock_wait_sent() will repeat SIOCOUTQ until it
+	 * returns 0.
 	 */
-	timeout_begin(TIMEOUT);
-	do {
-		ret = ioctl(fd, SIOCOUTQ, &sock_bytes_unsent);
-		if (ret < 0) {
-			if (errno == EOPNOTSUPP) {
-				fprintf(stderr, "Test skipped, SIOCOUTQ not supported.\n");
-				break;
-			}
-			perror("ioctl");
-			exit(EXIT_FAILURE);
-		}
-		timeout_check("SIOCOUTQ");
-	} while (sock_bytes_unsent != 0);
-	timeout_end();
+	if (!vsock_wait_sent(fd))
+		fprintf(stderr, "Test skipped, SIOCOUTQ not supported.\n");
+
 	close(fd);
 }
 
@@ -1794,10 +1813,6 @@ static void test_stream_connect_retry_server(const struct test_opts *opts)
 
 static void test_stream_linger_client(const struct test_opts *opts)
 {
-	struct linger optval = {
-		.l_onoff = 1,
-		.l_linger = 1
-	};
 	int fd;
 
 	fd = vsock_stream_connect(opts->peer_cid, opts->peer_port);
@@ -1806,15 +1821,58 @@ static void test_stream_linger_client(const struct test_opts *opts)
 		exit(EXIT_FAILURE);
 	}
 
-	if (setsockopt(fd, SOL_SOCKET, SO_LINGER, &optval, sizeof(optval))) {
-		perror("setsockopt(SO_LINGER)");
+	enable_so_linger(fd, 1);
+	close(fd);
+}
+
+static void test_stream_linger_server(const struct test_opts *opts)
+{
+	int fd;
+
+	fd = vsock_stream_accept(VMADDR_CID_ANY, opts->peer_port, NULL);
+	if (fd < 0) {
+		perror("accept");
 		exit(EXIT_FAILURE);
 	}
 
+	vsock_wait_remote_close(fd);
 	close(fd);
 }
 
-static void test_stream_linger_server(const struct test_opts *opts)
+/* Half of the default to not risk timing out the control channel */
+#define LINGER_TIMEOUT	(TIMEOUT / 2)
+
+static void test_stream_nolinger_client(const struct test_opts *opts)
+{
+	bool waited;
+	time_t ns;
+	int fd;
+
+	fd = vsock_stream_connect(opts->peer_cid, opts->peer_port);
+	if (fd < 0) {
+		perror("connect");
+		exit(EXIT_FAILURE);
+	}
+
+	enable_so_linger(fd, LINGER_TIMEOUT);
+	send_byte(fd, 1, 0); /* Left unread to expose incorrect behaviour. */
+	waited = vsock_wait_sent(fd);
+
+	ns = current_nsec();
+	close(fd);
+	ns = current_nsec() - ns;
+
+	if (!waited) {
+		fprintf(stderr, "Test skipped, SIOCOUTQ not supported.\n");
+	} else if (DIV_ROUND_UP(ns, NSEC_PER_SEC) >= LINGER_TIMEOUT) {
+		fprintf(stderr, "Unexpected lingering\n");
+		exit(EXIT_FAILURE);
+	}
+
+	control_writeln("DONE");
+}
+
+static void test_stream_nolinger_server(const struct test_opts *opts)
 {
 	int fd;
 
@@ -1824,7 +1882,7 @@ static void test_stream_linger_server(const struct test_opts *opts)
 		exit(EXIT_FAILURE);
 	}
 
-	vsock_wait_remote_close(fd);
+	control_expectln("DONE");
 	close(fd);
 }
 
@@ -1988,6 +2046,11 @@ static struct test_case test_cases[] = {
 		.run_client = test_stream_linger_client,
 		.run_server = test_stream_linger_server,
 	},
+	{
+		.name = "SOCK_STREAM SO_LINGER close() on unread",
+		.run_client = test_stream_nolinger_client,
+		.run_server = test_stream_nolinger_server,
+	},
 	{},
 };