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, 579 insertions, 0 deletions

diff --git a/include/net/nexthop.h b/include/net/nexthop.h
new file mode 100644
index 000000000..28085b995
--- /dev/null
+++ b/include/net/nexthop.h
@@ -0,0 +1,579 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Generic nexthop implementation
+ *
+ * Copyright (c) 2017-19 Cumulus Networks
+ * Copyright (c) 2017-19 David Ahern <dsa@cumulusnetworks.com>
+ */
+
+#ifndef __LINUX_NEXTHOP_H
+#define __LINUX_NEXTHOP_H
+
+#include <linux/netdevice.h>
+#include <linux/notifier.h>
+#include <linux/route.h>
+#include <linux/types.h>
+#include <net/ip_fib.h>
+#include <net/ip6_fib.h>
+#include <net/netlink.h>
+
+#define NEXTHOP_VALID_USER_FLAGS RTNH_F_ONLINK
+
+struct nexthop;
+
+struct nh_config {
+	u32		nh_id;
+
+	u8		nh_family;
+	u8		nh_protocol;
+	u8		nh_blackhole;
+	u8		nh_fdb;
+	u32		nh_flags;
+
+	int		nh_ifindex;
+	struct net_device *dev;
+
+	union {
+		__be32		ipv4;
+		struct in6_addr	ipv6;
+	} gw;
+
+	struct nlattr	*nh_grp;
+	u16		nh_grp_type;
+	u16		nh_grp_res_num_buckets;
+	unsigned long	nh_grp_res_idle_timer;
+	unsigned long	nh_grp_res_unbalanced_timer;
+	bool		nh_grp_res_has_num_buckets;
+	bool		nh_grp_res_has_idle_timer;
+	bool		nh_grp_res_has_unbalanced_timer;
+
+	struct nlattr	*nh_encap;
+	u16		nh_encap_type;
+
+	u32		nlflags;
+	struct nl_info	nlinfo;
+};
+
+struct nh_info {
+	struct hlist_node	dev_hash;    /* entry on netns devhash */
+	struct nexthop		*nh_parent;
+
+	u8			family;
+	bool			reject_nh;
+	bool			fdb_nh;
+
+	union {
+		struct fib_nh_common	fib_nhc;
+		struct fib_nh		fib_nh;
+		struct fib6_nh		fib6_nh;
+	};
+};
+
+struct nh_res_bucket {
+	struct nh_grp_entry __rcu *nh_entry;
+	atomic_long_t		used_time;
+	unsigned long		migrated_time;
+	bool			occupied;
+	u8			nh_flags;
+};
+
+struct nh_res_table {
+	struct net		*net;
+	u32			nhg_id;
+	struct delayed_work	upkeep_dw;
+
+	/* List of NHGEs that have too few buckets ("uw" for underweight).
+	 * Reclaimed buckets will be given to entries in this list.
+	 */
+	struct list_head	uw_nh_entries;
+	unsigned long		unbalanced_since;
+
+	u32			idle_timer;
+	u32			unbalanced_timer;
+
+	u16			num_nh_buckets;
+	struct nh_res_bucket	nh_buckets[];
+};
+
+struct nh_grp_entry {
+	struct nexthop	*nh;
+	u8		weight;
+
+	union {
+		struct {
+			atomic_t	upper_bound;
+		} hthr;
+		struct {
+			/* Member on uw_nh_entries. */
+			struct list_head	uw_nh_entry;
+
+			u16			count_buckets;
+			u16			wants_buckets;
+		} res;
+	};
+
+	struct list_head nh_list;
+	struct nexthop	*nh_parent;  /* nexthop of group with this entry */
+};
+
+struct nh_group {
+	struct nh_group		*spare; /* spare group for removals */
+	u16			num_nh;
+	bool			is_multipath;
+	bool			hash_threshold;
+	bool			resilient;
+	bool			fdb_nh;
+	bool			has_v4;
+
+	struct nh_res_table __rcu *res_table;
+	struct nh_grp_entry	nh_entries[];
+};
+
+struct nexthop {
+	struct rb_node		rb_node;    /* entry on netns rbtree */
+	struct list_head	fi_list;    /* v4 entries using nh */
+	struct list_head	f6i_list;   /* v6 entries using nh */
+	struct list_head        fdb_list;   /* fdb entries using this nh */
+	struct list_head	grp_list;   /* nh group entries using this nh */
+	struct net		*net;
+
+	u32			id;
+
+	u8			protocol;   /* app managing this nh */
+	u8			nh_flags;
+	bool			is_group;
+
+	refcount_t		refcnt;
+	struct rcu_head		rcu;
+
+	union {
+		struct nh_info	__rcu *nh_info;
+		struct nh_group __rcu *nh_grp;
+	};
+};
+
+enum nexthop_event_type {
+	NEXTHOP_EVENT_DEL,
+	NEXTHOP_EVENT_REPLACE,
+	NEXTHOP_EVENT_RES_TABLE_PRE_REPLACE,
+	NEXTHOP_EVENT_BUCKET_REPLACE,
+};
+
+enum nh_notifier_info_type {
+	NH_NOTIFIER_INFO_TYPE_SINGLE,
+	NH_NOTIFIER_INFO_TYPE_GRP,
+	NH_NOTIFIER_INFO_TYPE_RES_TABLE,
+	NH_NOTIFIER_INFO_TYPE_RES_BUCKET,
+};
+
+struct nh_notifier_single_info {
+	struct net_device *dev;
+	u8 gw_family;
+	union {
+		__be32 ipv4;
+		struct in6_addr ipv6;
+	};
+	u8 is_reject:1,
+	   is_fdb:1,
+	   has_encap:1;
+};
+
+struct nh_notifier_grp_entry_info {
+	u8 weight;
+	u32 id;
+	struct nh_notifier_single_info nh;
+};
+
+struct nh_notifier_grp_info {
+	u16 num_nh;
+	bool is_fdb;
+	struct nh_notifier_grp_entry_info nh_entries[];
+};
+
+struct nh_notifier_res_bucket_info {
+	u16 bucket_index;
+	unsigned int idle_timer_ms;
+	bool force;
+	struct nh_notifier_single_info old_nh;
+	struct nh_notifier_single_info new_nh;
+};
+
+struct nh_notifier_res_table_info {
+	u16 num_nh_buckets;
+	struct nh_notifier_single_info nhs[];
+};
+
+struct nh_notifier_info {
+	struct net *net;
+	struct netlink_ext_ack *extack;
+	u32 id;
+	enum nh_notifier_info_type type;
+	union {
+		struct nh_notifier_single_info *nh;
+		struct nh_notifier_grp_info *nh_grp;
+		struct nh_notifier_res_table_info *nh_res_table;
+		struct nh_notifier_res_bucket_info *nh_res_bucket;
+	};
+};
+
+int register_nexthop_notifier(struct net *net, struct notifier_block *nb,
+			      struct netlink_ext_ack *extack);
+int unregister_nexthop_notifier(struct net *net, struct notifier_block *nb);
+void nexthop_set_hw_flags(struct net *net, u32 id, bool offload, bool trap);
+void nexthop_bucket_set_hw_flags(struct net *net, u32 id, u16 bucket_index,
+				 bool offload, bool trap);
+void nexthop_res_grp_activity_update(struct net *net, u32 id, u16 num_buckets,
+				     unsigned long *activity);
+
+/* caller is holding rcu or rtnl; no reference taken to nexthop */
+struct nexthop *nexthop_find_by_id(struct net *net, u32 id);
+void nexthop_free_rcu(struct rcu_head *head);
+
+static inline bool nexthop_get(struct nexthop *nh)
+{
+	return refcount_inc_not_zero(&nh->refcnt);
+}
+
+static inline void nexthop_put(struct nexthop *nh)
+{
+	if (refcount_dec_and_test(&nh->refcnt))
+		call_rcu(&nh->rcu, nexthop_free_rcu);
+}
+
+static inline bool nexthop_cmp(const struct nexthop *nh1,
+			       const struct nexthop *nh2)
+{
+	return nh1 == nh2;
+}
+
+static inline bool nexthop_is_fdb(const struct nexthop *nh)
+{
+	if (nh->is_group) {
+		const struct nh_group *nh_grp;
+
+		nh_grp = rcu_dereference_rtnl(nh->nh_grp);
+		return nh_grp->fdb_nh;
+	} else {
+		const struct nh_info *nhi;
+
+		nhi = rcu_dereference_rtnl(nh->nh_info);
+		return nhi->fdb_nh;
+	}
+}
+
+static inline bool nexthop_has_v4(const struct nexthop *nh)
+{
+	if (nh->is_group) {
+		struct nh_group *nh_grp;
+
+		nh_grp = rcu_dereference_rtnl(nh->nh_grp);
+		return nh_grp->has_v4;
+	}
+	return false;
+}
+
+static inline bool nexthop_is_multipath(const struct nexthop *nh)
+{
+	if (nh->is_group) {
+		struct nh_group *nh_grp;
+
+		nh_grp = rcu_dereference_rtnl(nh->nh_grp);
+		return nh_grp->is_multipath;
+	}
+	return false;
+}
+
+struct nexthop *nexthop_select_path(struct nexthop *nh, int hash);
+
+static inline unsigned int nexthop_num_path(const struct nexthop *nh)
+{
+	unsigned int rc = 1;
+
+	if (nh->is_group) {
+		struct nh_group *nh_grp;
+
+		nh_grp = rcu_dereference_rtnl(nh->nh_grp);
+		if (nh_grp->is_multipath)
+			rc = nh_grp->num_nh;
+	}
+
+	return rc;
+}
+
+static inline
+struct nexthop *nexthop_mpath_select(const struct nh_group *nhg, int nhsel)
+{
+	/* for_nexthops macros in fib_semantics.c grabs a pointer to
+	 * the nexthop before checking nhsel
+	 */
+	if (nhsel >= nhg->num_nh)
+		return NULL;
+
+	return nhg->nh_entries[nhsel].nh;
+}
+
+static inline
+int nexthop_mpath_fill_node(struct sk_buff *skb, struct nexthop *nh,
+			    u8 rt_family)
+{
+	struct nh_group *nhg = rtnl_dereference(nh->nh_grp);
+	int i;
+
+	for (i = 0; i < nhg->num_nh; i++) {
+		struct nexthop *nhe = nhg->nh_entries[i].nh;
+		struct nh_info *nhi = rcu_dereference_rtnl(nhe->nh_info);
+		struct fib_nh_common *nhc = &nhi->fib_nhc;
+		int weight = nhg->nh_entries[i].weight;
+
+		if (fib_add_nexthop(skb, nhc, weight, rt_family, 0) < 0)
+			return -EMSGSIZE;
+	}
+
+	return 0;
+}
+
+/* called with rcu lock */
+static inline bool nexthop_is_blackhole(const struct nexthop *nh)
+{
+	const struct nh_info *nhi;
+
+	if (nh->is_group) {
+		struct nh_group *nh_grp;
+
+		nh_grp = rcu_dereference_rtnl(nh->nh_grp);
+		if (nh_grp->num_nh > 1)
+			return false;
+
+		nh = nh_grp->nh_entries[0].nh;
+	}
+
+	nhi = rcu_dereference_rtnl(nh->nh_info);
+	return nhi->reject_nh;
+}
+
+static inline void nexthop_path_fib_result(struct fib_result *res, int hash)
+{
+	struct nh_info *nhi;
+	struct nexthop *nh;
+
+	nh = nexthop_select_path(res->fi->nh, hash);
+	nhi = rcu_dereference(nh->nh_info);
+	res->nhc = &nhi->fib_nhc;
+}
+
+/* called with rcu read lock or rtnl held */
+static inline
+struct fib_nh_common *nexthop_fib_nhc(struct nexthop *nh, int nhsel)
+{
+	struct nh_info *nhi;
+
+	BUILD_BUG_ON(offsetof(struct fib_nh, nh_common) != 0);
+	BUILD_BUG_ON(offsetof(struct fib6_nh, nh_common) != 0);
+
+	if (nh->is_group) {
+		struct nh_group *nh_grp;
+
+		nh_grp = rcu_dereference_rtnl(nh->nh_grp);
+		if (nh_grp->is_multipath) {
+			nh = nexthop_mpath_select(nh_grp, nhsel);
+			if (!nh)
+				return NULL;
+		}
+	}
+
+	nhi = rcu_dereference_rtnl(nh->nh_info);
+	return &nhi->fib_nhc;
+}
+
+/* called from fib_table_lookup with rcu_lock */
+static inline
+struct fib_nh_common *nexthop_get_nhc_lookup(const struct nexthop *nh,
+					     int fib_flags,
+					     const struct flowi4 *flp,
+					     int *nhsel)
+{
+	struct nh_info *nhi;
+
+	if (nh->is_group) {
+		struct nh_group *nhg = rcu_dereference(nh->nh_grp);
+		int i;
+
+		for (i = 0; i < nhg->num_nh; i++) {
+			struct nexthop *nhe = nhg->nh_entries[i].nh;
+
+			nhi = rcu_dereference(nhe->nh_info);
+			if (fib_lookup_good_nhc(&nhi->fib_nhc, fib_flags, flp)) {
+				*nhsel = i;
+				return &nhi->fib_nhc;
+			}
+		}
+	} else {
+		nhi = rcu_dereference(nh->nh_info);
+		if (fib_lookup_good_nhc(&nhi->fib_nhc, fib_flags, flp)) {
+			*nhsel = 0;
+			return &nhi->fib_nhc;
+		}
+	}
+
+	return NULL;
+}
+
+static inline bool nexthop_uses_dev(const struct nexthop *nh,
+				    const struct net_device *dev)
+{
+	struct nh_info *nhi;
+
+	if (nh->is_group) {
+		struct nh_group *nhg = rcu_dereference(nh->nh_grp);
+		int i;
+
+		for (i = 0; i < nhg->num_nh; i++) {
+			struct nexthop *nhe = nhg->nh_entries[i].nh;
+
+			nhi = rcu_dereference(nhe->nh_info);
+			if (nhc_l3mdev_matches_dev(&nhi->fib_nhc, dev))
+				return true;
+		}
+	} else {
+		nhi = rcu_dereference(nh->nh_info);
+		if (nhc_l3mdev_matches_dev(&nhi->fib_nhc, dev))
+			return true;
+	}
+
+	return false;
+}
+
+static inline unsigned int fib_info_num_path(const struct fib_info *fi)
+{
+	if (unlikely(fi->nh))
+		return nexthop_num_path(fi->nh);
+
+	return fi->fib_nhs;
+}
+
+int fib_check_nexthop(struct nexthop *nh, u8 scope,
+		      struct netlink_ext_ack *extack);
+
+static inline struct fib_nh_common *fib_info_nhc(struct fib_info *fi, int nhsel)
+{
+	if (unlikely(fi->nh))
+		return nexthop_fib_nhc(fi->nh, nhsel);
+
+	return &fi->fib_nh[nhsel].nh_common;
+}
+
+/* only used when fib_nh is built into fib_info */
+static inline struct fib_nh *fib_info_nh(struct fib_info *fi, int nhsel)
+{
+	WARN_ON(fi->nh);
+
+	return &fi->fib_nh[nhsel];
+}
+
+/*
+ * IPv6 variants
+ */
+int fib6_check_nexthop(struct nexthop *nh, struct fib6_config *cfg,
+		       struct netlink_ext_ack *extack);
+
+/* Caller should either hold rcu_read_lock(), or RTNL. */
+static inline struct fib6_nh *nexthop_fib6_nh(struct nexthop *nh)
+{
+	struct nh_info *nhi;
+
+	if (nh->is_group) {
+		struct nh_group *nh_grp;
+
+		nh_grp = rcu_dereference_rtnl(nh->nh_grp);
+		nh = nexthop_mpath_select(nh_grp, 0);
+		if (!nh)
+			return NULL;
+	}
+
+	nhi = rcu_dereference_rtnl(nh->nh_info);
+	if (nhi->family == AF_INET6)
+		return &nhi->fib6_nh;
+
+	return NULL;
+}
+
+/* Variant of nexthop_fib6_nh().
+ * Caller should either hold rcu_read_lock_bh(), or RTNL.
+ */
+static inline struct fib6_nh *nexthop_fib6_nh_bh(struct nexthop *nh)
+{
+	struct nh_info *nhi;
+
+	if (nh->is_group) {
+		struct nh_group *nh_grp;
+
+		nh_grp = rcu_dereference_bh_rtnl(nh->nh_grp);
+		nh = nexthop_mpath_select(nh_grp, 0);
+		if (!nh)
+			return NULL;
+	}
+
+	nhi = rcu_dereference_bh_rtnl(nh->nh_info);
+	if (nhi->family == AF_INET6)
+		return &nhi->fib6_nh;
+
+	return NULL;
+}
+
+static inline struct net_device *fib6_info_nh_dev(struct fib6_info *f6i)
+{
+	struct fib6_nh *fib6_nh;
+
+	fib6_nh = f6i->nh ? nexthop_fib6_nh(f6i->nh) : f6i->fib6_nh;
+	return fib6_nh->fib_nh_dev;
+}
+
+static inline void nexthop_path_fib6_result(struct fib6_result *res, int hash)
+{
+	struct nexthop *nh = res->f6i->nh;
+	struct nh_info *nhi;
+
+	nh = nexthop_select_path(nh, hash);
+
+	nhi = rcu_dereference_rtnl(nh->nh_info);
+	if (nhi->reject_nh) {
+		res->fib6_type = RTN_BLACKHOLE;
+		res->fib6_flags |= RTF_REJECT;
+		res->nh = nexthop_fib6_nh(nh);
+	} else {
+		res->nh = &nhi->fib6_nh;
+	}
+}
+
+int nexthop_for_each_fib6_nh(struct nexthop *nh,
+			     int (*cb)(struct fib6_nh *nh, void *arg),
+			     void *arg);
+
+static inline int nexthop_get_family(struct nexthop *nh)
+{
+	struct nh_info *nhi = rcu_dereference_rtnl(nh->nh_info);
+
+	return nhi->family;
+}
+
+static inline
+struct fib_nh_common *nexthop_fdb_nhc(struct nexthop *nh)
+{
+	struct nh_info *nhi = rcu_dereference_rtnl(nh->nh_info);
+
+	return &nhi->fib_nhc;
+}
+
+static inline struct fib_nh_common *nexthop_path_fdb_result(struct nexthop *nh,
+							    int hash)
+{
+	struct nh_info *nhi;
+	struct nexthop *nhp;
+
+	nhp = nexthop_select_path(nh, hash);
+	if (unlikely(!nhp))
+		return NULL;
+	nhi = rcu_dereference(nhp->nh_info);
+	return &nhi->fib_nhc;
+}
+#endif