Merge tag 'net-next-6.3' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-nextgrafted

Pull networking updates from Jakub Kicinski:
 "Core:

   - Add dedicated kmem_cache for typical/small skb->head, avoid having
     to access struct page at kfree time, and improve memory use.

   - Introduce sysctl to set default RPS configuration for new netdevs.

   - Define Netlink protocol specification format which can be used to
     describe messages used by each family and auto-generate parsers.
     Add tools for generating kernel data structures and uAPI headers.

   - Expose all net/core sysctls inside netns.

   - Remove 4s sleep in netpoll if carrier is instantly detected on
     boot.

   - Add configurable limit of MDB entries per port, and port-vlan.

   - Continue populating drop reasons throughout the stack.

   - Retire a handful of legacy Qdiscs and classifiers.

  Protocols:

   - Support IPv4 big TCP (TSO frames larger than 64kB).

   - Add IP_LOCAL_PORT_RANGE socket option, to control local port range
     on socket by socket basis.

   - Track and report in procfs number of MPTCP sockets used.

   - Support mixing IPv4 and IPv6 flows in the in-kernel MPTCP path
     manager.

   - IPv6: don't check net.ipv6.route.max_size and rely on garbage
     collection to free memory (similarly to IPv4).

   - Support Penultimate Segment Pop (PSP) flavor in SRv6 (RFC8986).

   - ICMP: add per-rate limit counters.

   - Add support for user scanning requests in ieee802154.

   - Remove static WEP support.

   - Support minimal Wi-Fi 7 Extremely High Throughput (EHT) rate
     reporting.

   - WiFi 7 EHT channel puncturing support (client & AP).

  BPF:

   - Add a rbtree data structure following the "next-gen data structure"
     precedent set by recently added linked list, that is, by using
     kfunc + kptr instead of adding a new BPF map type.

   - Expose XDP hints via kfuncs with initial support for RX hash and
     timestamp metadata.

   - Add BPF_F_NO_TUNNEL_KEY extension to bpf_skb_set_tunnel_key to
     better support decap on GRE tunnel devices not operating in collect
     metadata.

   - Improve x86 JIT's codegen for PROBE_MEM runtime error checks.

   - Remove the need for trace_printk_lock for bpf_trace_printk and
     bpf_trace_vprintk helpers.

   - Extend libbpf's bpf_tracing.h support for tracing arguments of
     kprobes/uprobes and syscall as a special case.

   - Significantly reduce the search time for module symbols by
     livepatch and BPF.

   - Enable cpumasks to be used as kptrs, which is useful for tracing
     programs tracking which tasks end up running on which CPUs in
     different time intervals.

   - Add support for BPF trampoline on s390x and riscv64.

   - Add capability to export the XDP features supported by the NIC.

   - Add __bpf_kfunc tag for marking kernel functions as kfuncs.

   - Add cgroup.memory=nobpf kernel parameter option to disable BPF
     memory accounting for container environments.

  Netfilter:

   - Remove the CLUSTERIP target. It has been marked as obsolete for
     years, and we still have WARN splats wrt races of the out-of-band
     /proc interface installed by this target.

   - Add 'destroy' commands to nf_tables. They are identical to the
     existing 'delete' commands, but do not return an error if the
     referenced object (set, chain, rule...) did not exist.

  Driver API:

   - Improve cpumask_local_spread() locality to help NICs set the right
     IRQ affinity on AMD platforms.

   - Separate C22 and C45 MDIO bus transactions more clearly.

   - Introduce new DCB table to control DSCP rewrite on egress.

   - Support configuration of Physical Layer Collision Avoidance (PLCA)
     Reconciliation Sublayer (RS) (802.3cg-2019). Modern version of
     shared medium Ethernet.

   - Support for MAC Merge layer (IEEE 802.3-2018 clause 99). Allowing
     preemption of low priority frames by high priority frames.

   - Add support for controlling MACSec offload using netlink SET.

   - Rework devlink instance refcounts to allow registration and
     de-registration under the instance lock. Split the code into
     multiple files, drop some of the unnecessarily granular locks and
     factor out common parts of netlink operation handling.

   - Add TX frame aggregation parameters (for USB drivers).

   - Add a new attr TCA_EXT_WARN_MSG to report TC (offload) warning
     messages with notifications for debug.

   - Allow offloading of UDP NEW connections via act_ct.

   - Add support for per action HW stats in TC.

   - Support hardware miss to TC action (continue processing in SW from
     a specific point in the action chain).

   - Warn if old Wireless Extension user space interface is used with
     modern cfg80211/mac80211 drivers. Do not support Wireless
     Extensions for Wi-Fi 7 devices at all. Everyone should switch to
     using nl80211 interface instead.

   - Improve the CAN bit timing configuration. Use extack to return
     error messages directly to user space, update the SJW handling,
     including the definition of a new default value that will benefit
     CAN-FD controllers, by increasing their oscillator tolerance.

  New hardware / drivers:

   - Ethernet:
      - nVidia BlueField-3 support (control traffic driver)
      - Ethernet support for imx93 SoCs
      - Motorcomm yt8531 gigabit Ethernet PHY
      - onsemi NCN26000 10BASE-T1S PHY (with support for PLCA)
      - Microchip LAN8841 PHY (incl. cable diagnostics and PTP)
      - Amlogic gxl MDIO mux

   - WiFi:
      - RealTek RTL8188EU (rtl8xxxu)
      - Qualcomm Wi-Fi 7 devices (ath12k)

   - CAN:
      - Renesas R-Car V4H

  Drivers:

   - Bluetooth:
      - Set Per Platform Antenna Gain (PPAG) for Intel controllers.

   - Ethernet NICs:
      - Intel (1G, igc):
         - support TSN / Qbv / packet scheduling features of i226 model
      - Intel (100G, ice):
         - use GNSS subsystem instead of TTY
         - multi-buffer XDP support
         - extend support for GPIO pins to E823 devices
      - nVidia/Mellanox:
         - update the shared buffer configuration on PFC commands
         - implement PTP adjphase function for HW offset control
         - TC support for Geneve and GRE with VF tunnel offload
         - more efficient crypto key management method
         - multi-port eswitch support
      - Netronome/Corigine:
         - add DCB IEEE support
         - support IPsec offloading for NFP3800
      - Freescale/NXP (enetc):
         - support XDP_REDIRECT for XDP non-linear buffers
         - improve reconfig, avoid link flap and waiting for idle
         - support MAC Merge layer
      - Other NICs:
         - sfc/ef100: add basic devlink support for ef100
         - ionic: rx_push mode operation (writing descriptors via MMIO)
         - bnxt: use the auxiliary bus abstraction for RDMA
         - r8169: disable ASPM and reset bus in case of tx timeout
         - cpsw: support QSGMII mode for J721e CPSW9G
         - cpts: support pulse-per-second output
         - ngbe: add an mdio bus driver
         - usbnet: optimize usbnet_bh() by avoiding unnecessary queuing
         - r8152: handle devices with FW with NCM support
         - amd-xgbe: support 10Mbps, 2.5GbE speeds and rx-adaptation
         - virtio-net: support multi buffer XDP
         - virtio/vsock: replace virtio_vsock_pkt with sk_buff
         - tsnep: XDP support

   - Ethernet high-speed switches:
      - nVidia/Mellanox (mlxsw):
         - add support for latency TLV (in FW control messages)
      - Microchip (sparx5):
         - separate explicit and implicit traffic forwarding rules, make
           the implicit rules always active
         - add support for egress DSCP rewrite
         - IS0 VCAP support (Ingress Classification)
         - IS2 VCAP filters (protos, L3 addrs, L4 ports, flags, ToS
           etc.)
         - ES2 VCAP support (Egress Access Control)
         - support for Per-Stream Filtering and Policing (802.1Q,
           8.6.5.1)

   - Ethernet embedded switches:
      - Marvell (mv88e6xxx):
         - add MAB (port auth) offload support
         - enable PTP receive for mv88e6390
      - NXP (ocelot):
         - support MAC Merge layer
         - support for the the vsc7512 internal copper phys
      - Microchip:
         - lan9303: convert to PHYLINK
         - lan966x: support TC flower filter statistics
         - lan937x: PTP support for KSZ9563/KSZ8563 and LAN937x
         - lan937x: support Credit Based Shaper configuration
         - ksz9477: support Energy Efficient Ethernet
      - other:
         - qca8k: convert to regmap read/write API, use bulk operations
         - rswitch: Improve TX timestamp accuracy

   - Intel WiFi (iwlwifi):
      - EHT (Wi-Fi 7) rate reporting
      - STEP equalizer support: transfer some STEP (connection to radio
        on platforms with integrated wifi) related parameters from the
        BIOS to the firmware.

   - Qualcomm 802.11ax WiFi (ath11k):
      - IPQ5018 support
      - Fine Timing Measurement (FTM) responder role support
      - channel 177 support

   - MediaTek WiFi (mt76):
      - per-PHY LED support
      - mt7996: EHT (Wi-Fi 7) support
      - Wireless Ethernet Dispatch (WED) reset support
      - switch to using page pool allocator

   - RealTek WiFi (rtw89):
      - support new version of Bluetooth co-existance

   - Mobile:
      - rmnet: support TX aggregation"

* tag 'net-next-6.3' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next: (1872 commits)
  page_pool: add a comment explaining the fragment counter usage
  net: ethtool: fix __ethtool_dev_mm_supported() implementation
  ethtool: pse-pd: Fix double word in comments
  xsk: add linux/vmalloc.h to xsk.c
  sefltests: netdevsim: wait for devlink instance after netns removal
  selftest: fib_tests: Always cleanup before exit
  net/mlx5e: Align IPsec ASO result memory to be as required by hardware
  net/mlx5e: TC, Set CT miss to the specific ct action instance
  net/mlx5e: Rename CHAIN_TO_REG to MAPPED_OBJ_TO_REG
  net/mlx5: Refactor tc miss handling to a single function
  net/mlx5: Kconfig: Make tc offload depend on tc skb extension
  net/sched: flower: Support hardware miss to tc action
  net/sched: flower: Move filter handle initialization earlier
  net/sched: cls_api: Support hardware miss to tc action
  net/sched: Rename user cookie and act cookie
  sfc: fix builds without CONFIG_RTC_LIB
  sfc: clean up some inconsistent indentings
  net/mlx4_en: Introduce flexible array to silence overflow warning
  net: lan966x: Fix possible deadlock inside PTP
  net/ulp: Remove redundant ->clone() test in inet_clone_ulp().
  ...

1 files changed, 556 insertions, 0 deletions

diff --git a/net/hsr/hsr_netlink.c b/net/hsr/hsr_netlink.c
new file mode 100644
index 000000000..78fe40eb9
--- /dev/null
+++ b/net/hsr/hsr_netlink.c
@@ -0,0 +1,556 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright 2011-2014 Autronica Fire and Security AS
+ *
+ * Author(s):
+ *	2011-2014 Arvid Brodin, arvid.brodin@alten.se
+ *
+ * Routines for handling Netlink messages for HSR and PRP.
+ */
+
+#include "hsr_netlink.h"
+#include <linux/kernel.h>
+#include <net/rtnetlink.h>
+#include <net/genetlink.h>
+#include "hsr_main.h"
+#include "hsr_device.h"
+#include "hsr_framereg.h"
+
+static const struct nla_policy hsr_policy[IFLA_HSR_MAX + 1] = {
+	[IFLA_HSR_SLAVE1]		= { .type = NLA_U32 },
+	[IFLA_HSR_SLAVE2]		= { .type = NLA_U32 },
+	[IFLA_HSR_MULTICAST_SPEC]	= { .type = NLA_U8 },
+	[IFLA_HSR_VERSION]	= { .type = NLA_U8 },
+	[IFLA_HSR_SUPERVISION_ADDR]	= { .len = ETH_ALEN },
+	[IFLA_HSR_SEQ_NR]		= { .type = NLA_U16 },
+	[IFLA_HSR_PROTOCOL]		= { .type = NLA_U8 },
+};
+
+/* Here, it seems a netdevice has already been allocated for us, and the
+ * hsr_dev_setup routine has been executed. Nice!
+ */
+static int hsr_newlink(struct net *src_net, struct net_device *dev,
+		       struct nlattr *tb[], struct nlattr *data[],
+		       struct netlink_ext_ack *extack)
+{
+	enum hsr_version proto_version;
+	unsigned char multicast_spec;
+	u8 proto = HSR_PROTOCOL_HSR;
+	struct net_device *link[2];
+
+	if (!data) {
+		NL_SET_ERR_MSG_MOD(extack, "No slave devices specified");
+		return -EINVAL;
+	}
+	if (!data[IFLA_HSR_SLAVE1]) {
+		NL_SET_ERR_MSG_MOD(extack, "Slave1 device not specified");
+		return -EINVAL;
+	}
+	link[0] = __dev_get_by_index(src_net,
+				     nla_get_u32(data[IFLA_HSR_SLAVE1]));
+	if (!link[0]) {
+		NL_SET_ERR_MSG_MOD(extack, "Slave1 does not exist");
+		return -EINVAL;
+	}
+	if (!data[IFLA_HSR_SLAVE2]) {
+		NL_SET_ERR_MSG_MOD(extack, "Slave2 device not specified");
+		return -EINVAL;
+	}
+	link[1] = __dev_get_by_index(src_net,
+				     nla_get_u32(data[IFLA_HSR_SLAVE2]));
+	if (!link[1]) {
+		NL_SET_ERR_MSG_MOD(extack, "Slave2 does not exist");
+		return -EINVAL;
+	}
+
+	if (link[0] == link[1]) {
+		NL_SET_ERR_MSG_MOD(extack, "Slave1 and Slave2 are same");
+		return -EINVAL;
+	}
+
+	if (!data[IFLA_HSR_MULTICAST_SPEC])
+		multicast_spec = 0;
+	else
+		multicast_spec = nla_get_u8(data[IFLA_HSR_MULTICAST_SPEC]);
+
+	if (data[IFLA_HSR_PROTOCOL])
+		proto = nla_get_u8(data[IFLA_HSR_PROTOCOL]);
+
+	if (proto >= HSR_PROTOCOL_MAX) {
+		NL_SET_ERR_MSG_MOD(extack, "Unsupported protocol");
+		return -EINVAL;
+	}
+
+	if (!data[IFLA_HSR_VERSION]) {
+		proto_version = HSR_V0;
+	} else {
+		if (proto == HSR_PROTOCOL_PRP) {
+			NL_SET_ERR_MSG_MOD(extack, "PRP version unsupported");
+			return -EINVAL;
+		}
+
+		proto_version = nla_get_u8(data[IFLA_HSR_VERSION]);
+		if (proto_version > HSR_V1) {
+			NL_SET_ERR_MSG_MOD(extack,
+					   "Only HSR version 0/1 supported");
+			return -EINVAL;
+		}
+	}
+
+	if (proto == HSR_PROTOCOL_PRP)
+		proto_version = PRP_V1;
+
+	return hsr_dev_finalize(dev, link, multicast_spec, proto_version, extack);
+}
+
+static void hsr_dellink(struct net_device *dev, struct list_head *head)
+{
+	struct hsr_priv *hsr = netdev_priv(dev);
+
+	del_timer_sync(&hsr->prune_timer);
+	del_timer_sync(&hsr->announce_timer);
+
+	hsr_debugfs_term(hsr);
+	hsr_del_ports(hsr);
+
+	hsr_del_self_node(hsr);
+	hsr_del_nodes(&hsr->node_db);
+
+	unregister_netdevice_queue(dev, head);
+}
+
+static int hsr_fill_info(struct sk_buff *skb, const struct net_device *dev)
+{
+	struct hsr_priv *hsr = netdev_priv(dev);
+	u8 proto = HSR_PROTOCOL_HSR;
+	struct hsr_port *port;
+
+	port = hsr_port_get_hsr(hsr, HSR_PT_SLAVE_A);
+	if (port) {
+		if (nla_put_u32(skb, IFLA_HSR_SLAVE1, port->dev->ifindex))
+			goto nla_put_failure;
+	}
+
+	port = hsr_port_get_hsr(hsr, HSR_PT_SLAVE_B);
+	if (port) {
+		if (nla_put_u32(skb, IFLA_HSR_SLAVE2, port->dev->ifindex))
+			goto nla_put_failure;
+	}
+
+	if (nla_put(skb, IFLA_HSR_SUPERVISION_ADDR, ETH_ALEN,
+		    hsr->sup_multicast_addr) ||
+	    nla_put_u16(skb, IFLA_HSR_SEQ_NR, hsr->sequence_nr))
+		goto nla_put_failure;
+	if (hsr->prot_version == PRP_V1)
+		proto = HSR_PROTOCOL_PRP;
+	if (nla_put_u8(skb, IFLA_HSR_PROTOCOL, proto))
+		goto nla_put_failure;
+
+	return 0;
+
+nla_put_failure:
+	return -EMSGSIZE;
+}
+
+static struct rtnl_link_ops hsr_link_ops __read_mostly = {
+	.kind		= "hsr",
+	.maxtype	= IFLA_HSR_MAX,
+	.policy		= hsr_policy,
+	.priv_size	= sizeof(struct hsr_priv),
+	.setup		= hsr_dev_setup,
+	.newlink	= hsr_newlink,
+	.dellink	= hsr_dellink,
+	.fill_info	= hsr_fill_info,
+};
+
+/* attribute policy */
+static const struct nla_policy hsr_genl_policy[HSR_A_MAX + 1] = {
+	[HSR_A_NODE_ADDR] = { .len = ETH_ALEN },
+	[HSR_A_NODE_ADDR_B] = { .len = ETH_ALEN },
+	[HSR_A_IFINDEX] = { .type = NLA_U32 },
+	[HSR_A_IF1_AGE] = { .type = NLA_U32 },
+	[HSR_A_IF2_AGE] = { .type = NLA_U32 },
+	[HSR_A_IF1_SEQ] = { .type = NLA_U16 },
+	[HSR_A_IF2_SEQ] = { .type = NLA_U16 },
+};
+
+static struct genl_family hsr_genl_family;
+
+static const struct genl_multicast_group hsr_mcgrps[] = {
+	{ .name = "hsr-network", },
+};
+
+/* This is called if for some node with MAC address addr, we only get frames
+ * over one of the slave interfaces. This would indicate an open network ring
+ * (i.e. a link has failed somewhere).
+ */
+void hsr_nl_ringerror(struct hsr_priv *hsr, unsigned char addr[ETH_ALEN],
+		      struct hsr_port *port)
+{
+	struct sk_buff *skb;
+	void *msg_head;
+	struct hsr_port *master;
+	int res;
+
+	skb = genlmsg_new(NLMSG_GOODSIZE, GFP_ATOMIC);
+	if (!skb)
+		goto fail;
+
+	msg_head = genlmsg_put(skb, 0, 0, &hsr_genl_family, 0,
+			       HSR_C_RING_ERROR);
+	if (!msg_head)
+		goto nla_put_failure;
+
+	res = nla_put(skb, HSR_A_NODE_ADDR, ETH_ALEN, addr);
+	if (res < 0)
+		goto nla_put_failure;
+
+	res = nla_put_u32(skb, HSR_A_IFINDEX, port->dev->ifindex);
+	if (res < 0)
+		goto nla_put_failure;
+
+	genlmsg_end(skb, msg_head);
+	genlmsg_multicast(&hsr_genl_family, skb, 0, 0, GFP_ATOMIC);
+
+	return;
+
+nla_put_failure:
+	kfree_skb(skb);
+
+fail:
+	rcu_read_lock();
+	master = hsr_port_get_hsr(hsr, HSR_PT_MASTER);
+	netdev_warn(master->dev, "Could not send HSR ring error message\n");
+	rcu_read_unlock();
+}
+
+/* This is called when we haven't heard from the node with MAC address addr for
+ * some time (just before the node is removed from the node table/list).
+ */
+void hsr_nl_nodedown(struct hsr_priv *hsr, unsigned char addr[ETH_ALEN])
+{
+	struct sk_buff *skb;
+	void *msg_head;
+	struct hsr_port *master;
+	int res;
+
+	skb = genlmsg_new(NLMSG_GOODSIZE, GFP_ATOMIC);
+	if (!skb)
+		goto fail;
+
+	msg_head = genlmsg_put(skb, 0, 0, &hsr_genl_family, 0, HSR_C_NODE_DOWN);
+	if (!msg_head)
+		goto nla_put_failure;
+
+	res = nla_put(skb, HSR_A_NODE_ADDR, ETH_ALEN, addr);
+	if (res < 0)
+		goto nla_put_failure;
+
+	genlmsg_end(skb, msg_head);
+	genlmsg_multicast(&hsr_genl_family, skb, 0, 0, GFP_ATOMIC);
+
+	return;
+
+nla_put_failure:
+	kfree_skb(skb);
+
+fail:
+	rcu_read_lock();
+	master = hsr_port_get_hsr(hsr, HSR_PT_MASTER);
+	netdev_warn(master->dev, "Could not send HSR node down\n");
+	rcu_read_unlock();
+}
+
+/* HSR_C_GET_NODE_STATUS lets userspace query the internal HSR node table
+ * about the status of a specific node in the network, defined by its MAC
+ * address.
+ *
+ * Input: hsr ifindex, node mac address
+ * Output: hsr ifindex, node mac address (copied from request),
+ *	   age of latest frame from node over slave 1, slave 2 [ms]
+ */
+static int hsr_get_node_status(struct sk_buff *skb_in, struct genl_info *info)
+{
+	/* For receiving */
+	struct nlattr *na;
+	struct net_device *hsr_dev;
+
+	/* For sending */
+	struct sk_buff *skb_out;
+	void *msg_head;
+	struct hsr_priv *hsr;
+	struct hsr_port *port;
+	unsigned char hsr_node_addr_b[ETH_ALEN];
+	int hsr_node_if1_age;
+	u16 hsr_node_if1_seq;
+	int hsr_node_if2_age;
+	u16 hsr_node_if2_seq;
+	int addr_b_ifindex;
+	int res;
+
+	if (!info)
+		goto invalid;
+
+	na = info->attrs[HSR_A_IFINDEX];
+	if (!na)
+		goto invalid;
+	na = info->attrs[HSR_A_NODE_ADDR];
+	if (!na)
+		goto invalid;
+
+	rcu_read_lock();
+	hsr_dev = dev_get_by_index_rcu(genl_info_net(info),
+				       nla_get_u32(info->attrs[HSR_A_IFINDEX]));
+	if (!hsr_dev)
+		goto rcu_unlock;
+	if (!is_hsr_master(hsr_dev))
+		goto rcu_unlock;
+
+	/* Send reply */
+	skb_out = genlmsg_new(NLMSG_GOODSIZE, GFP_ATOMIC);
+	if (!skb_out) {
+		res = -ENOMEM;
+		goto fail;
+	}
+
+	msg_head = genlmsg_put(skb_out, NETLINK_CB(skb_in).portid,
+			       info->snd_seq, &hsr_genl_family, 0,
+			       HSR_C_SET_NODE_STATUS);
+	if (!msg_head) {
+		res = -ENOMEM;
+		goto nla_put_failure;
+	}
+
+	res = nla_put_u32(skb_out, HSR_A_IFINDEX, hsr_dev->ifindex);
+	if (res < 0)
+		goto nla_put_failure;
+
+	hsr = netdev_priv(hsr_dev);
+	res = hsr_get_node_data(hsr,
+				(unsigned char *)
+				nla_data(info->attrs[HSR_A_NODE_ADDR]),
+					 hsr_node_addr_b,
+					 &addr_b_ifindex,
+					 &hsr_node_if1_age,
+					 &hsr_node_if1_seq,
+					 &hsr_node_if2_age,
+					 &hsr_node_if2_seq);
+	if (res < 0)
+		goto nla_put_failure;
+
+	res = nla_put(skb_out, HSR_A_NODE_ADDR, ETH_ALEN,
+		      nla_data(info->attrs[HSR_A_NODE_ADDR]));
+	if (res < 0)
+		goto nla_put_failure;
+
+	if (addr_b_ifindex > -1) {
+		res = nla_put(skb_out, HSR_A_NODE_ADDR_B, ETH_ALEN,
+			      hsr_node_addr_b);
+		if (res < 0)
+			goto nla_put_failure;
+
+		res = nla_put_u32(skb_out, HSR_A_ADDR_B_IFINDEX,
+				  addr_b_ifindex);
+		if (res < 0)
+			goto nla_put_failure;
+	}
+
+	res = nla_put_u32(skb_out, HSR_A_IF1_AGE, hsr_node_if1_age);
+	if (res < 0)
+		goto nla_put_failure;
+	res = nla_put_u16(skb_out, HSR_A_IF1_SEQ, hsr_node_if1_seq);
+	if (res < 0)
+		goto nla_put_failure;
+	port = hsr_port_get_hsr(hsr, HSR_PT_SLAVE_A);
+	if (port)
+		res = nla_put_u32(skb_out, HSR_A_IF1_IFINDEX,
+				  port->dev->ifindex);
+	if (res < 0)
+		goto nla_put_failure;
+
+	res = nla_put_u32(skb_out, HSR_A_IF2_AGE, hsr_node_if2_age);
+	if (res < 0)
+		goto nla_put_failure;
+	res = nla_put_u16(skb_out, HSR_A_IF2_SEQ, hsr_node_if2_seq);
+	if (res < 0)
+		goto nla_put_failure;
+	port = hsr_port_get_hsr(hsr, HSR_PT_SLAVE_B);
+	if (port)
+		res = nla_put_u32(skb_out, HSR_A_IF2_IFINDEX,
+				  port->dev->ifindex);
+	if (res < 0)
+		goto nla_put_failure;
+
+	rcu_read_unlock();
+
+	genlmsg_end(skb_out, msg_head);
+	genlmsg_unicast(genl_info_net(info), skb_out, info->snd_portid);
+
+	return 0;
+
+rcu_unlock:
+	rcu_read_unlock();
+invalid:
+	netlink_ack(skb_in, nlmsg_hdr(skb_in), -EINVAL, NULL);
+	return 0;
+
+nla_put_failure:
+	kfree_skb(skb_out);
+	/* Fall through */
+
+fail:
+	rcu_read_unlock();
+	return res;
+}
+
+/* Get a list of MacAddressA of all nodes known to this node (including self).
+ */
+static int hsr_get_node_list(struct sk_buff *skb_in, struct genl_info *info)
+{
+	unsigned char addr[ETH_ALEN];
+	struct net_device *hsr_dev;
+	struct sk_buff *skb_out;
+	struct hsr_priv *hsr;
+	bool restart = false;
+	struct nlattr *na;
+	void *pos = NULL;
+	void *msg_head;
+	int res;
+
+	if (!info)
+		goto invalid;
+
+	na = info->attrs[HSR_A_IFINDEX];
+	if (!na)
+		goto invalid;
+
+	rcu_read_lock();
+	hsr_dev = dev_get_by_index_rcu(genl_info_net(info),
+				       nla_get_u32(info->attrs[HSR_A_IFINDEX]));
+	if (!hsr_dev)
+		goto rcu_unlock;
+	if (!is_hsr_master(hsr_dev))
+		goto rcu_unlock;
+
+restart:
+	/* Send reply */
+	skb_out = genlmsg_new(GENLMSG_DEFAULT_SIZE, GFP_ATOMIC);
+	if (!skb_out) {
+		res = -ENOMEM;
+		goto fail;
+	}
+
+	msg_head = genlmsg_put(skb_out, NETLINK_CB(skb_in).portid,
+			       info->snd_seq, &hsr_genl_family, 0,
+			       HSR_C_SET_NODE_LIST);
+	if (!msg_head) {
+		res = -ENOMEM;
+		goto nla_put_failure;
+	}
+
+	if (!restart) {
+		res = nla_put_u32(skb_out, HSR_A_IFINDEX, hsr_dev->ifindex);
+		if (res < 0)
+			goto nla_put_failure;
+	}
+
+	hsr = netdev_priv(hsr_dev);
+
+	if (!pos)
+		pos = hsr_get_next_node(hsr, NULL, addr);
+	while (pos) {
+		res = nla_put(skb_out, HSR_A_NODE_ADDR, ETH_ALEN, addr);
+		if (res < 0) {
+			if (res == -EMSGSIZE) {
+				genlmsg_end(skb_out, msg_head);
+				genlmsg_unicast(genl_info_net(info), skb_out,
+						info->snd_portid);
+				restart = true;
+				goto restart;
+			}
+			goto nla_put_failure;
+		}
+		pos = hsr_get_next_node(hsr, pos, addr);
+	}
+	rcu_read_unlock();
+
+	genlmsg_end(skb_out, msg_head);
+	genlmsg_unicast(genl_info_net(info), skb_out, info->snd_portid);
+
+	return 0;
+
+rcu_unlock:
+	rcu_read_unlock();
+invalid:
+	netlink_ack(skb_in, nlmsg_hdr(skb_in), -EINVAL, NULL);
+	return 0;
+
+nla_put_failure:
+	nlmsg_free(skb_out);
+	/* Fall through */
+
+fail:
+	rcu_read_unlock();
+	return res;
+}
+
+static const struct genl_small_ops hsr_ops[] = {
+	{
+		.cmd = HSR_C_GET_NODE_STATUS,
+		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
+		.flags = 0,
+		.doit = hsr_get_node_status,
+		.dumpit = NULL,
+	},
+	{
+		.cmd = HSR_C_GET_NODE_LIST,
+		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
+		.flags = 0,
+		.doit = hsr_get_node_list,
+		.dumpit = NULL,
+	},
+};
+
+static struct genl_family hsr_genl_family __ro_after_init = {
+	.hdrsize = 0,
+	.name = "HSR",
+	.version = 1,
+	.maxattr = HSR_A_MAX,
+	.policy = hsr_genl_policy,
+	.netnsok = true,
+	.module = THIS_MODULE,
+	.small_ops = hsr_ops,
+	.n_small_ops = ARRAY_SIZE(hsr_ops),
+	.resv_start_op = HSR_C_SET_NODE_LIST + 1,
+	.mcgrps = hsr_mcgrps,
+	.n_mcgrps = ARRAY_SIZE(hsr_mcgrps),
+};
+
+int __init hsr_netlink_init(void)
+{
+	int rc;
+
+	rc = rtnl_link_register(&hsr_link_ops);
+	if (rc)
+		goto fail_rtnl_link_register;
+
+	rc = genl_register_family(&hsr_genl_family);
+	if (rc)
+		goto fail_genl_register_family;
+
+	hsr_debugfs_create_root();
+	return 0;
+
+fail_genl_register_family:
+	rtnl_link_unregister(&hsr_link_ops);
+fail_rtnl_link_register:
+
+	return rc;
+}
+
+void __exit hsr_netlink_exit(void)
+{
+	genl_unregister_family(&hsr_genl_family);
+	rtnl_link_unregister(&hsr_link_ops);
+}
+
+MODULE_ALIAS_RTNL_LINK("hsr");