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, 522 insertions, 0 deletions

diff --git a/net/ipv6/fib6_rules.c b/net/ipv6/fib6_rules.c
new file mode 100644
index 000000000..7c2003833
--- /dev/null
+++ b/net/ipv6/fib6_rules.c
@@ -0,0 +1,522 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * net/ipv6/fib6_rules.c	IPv6 Routing Policy Rules
+ *
+ * Copyright (C)2003-2006 Helsinki University of Technology
+ * Copyright (C)2003-2006 USAGI/WIDE Project
+ *
+ * Authors
+ *	Thomas Graf		<tgraf@suug.ch>
+ *	Ville Nuorvala		<vnuorval@tcs.hut.fi>
+ */
+
+#include <linux/netdevice.h>
+#include <linux/notifier.h>
+#include <linux/export.h>
+#include <linux/indirect_call_wrapper.h>
+
+#include <net/fib_rules.h>
+#include <net/inet_dscp.h>
+#include <net/ipv6.h>
+#include <net/addrconf.h>
+#include <net/ip6_route.h>
+#include <net/netlink.h>
+
+struct fib6_rule {
+	struct fib_rule		common;
+	struct rt6key		src;
+	struct rt6key		dst;
+	dscp_t			dscp;
+};
+
+static bool fib6_rule_matchall(const struct fib_rule *rule)
+{
+	struct fib6_rule *r = container_of(rule, struct fib6_rule, common);
+
+	if (r->dst.plen || r->src.plen || r->dscp)
+		return false;
+	return fib_rule_matchall(rule);
+}
+
+bool fib6_rule_default(const struct fib_rule *rule)
+{
+	if (!fib6_rule_matchall(rule) || rule->action != FR_ACT_TO_TBL ||
+	    rule->l3mdev)
+		return false;
+	if (rule->table != RT6_TABLE_LOCAL && rule->table != RT6_TABLE_MAIN)
+		return false;
+	return true;
+}
+EXPORT_SYMBOL_GPL(fib6_rule_default);
+
+int fib6_rules_dump(struct net *net, struct notifier_block *nb,
+		    struct netlink_ext_ack *extack)
+{
+	return fib_rules_dump(net, nb, AF_INET6, extack);
+}
+
+unsigned int fib6_rules_seq_read(struct net *net)
+{
+	return fib_rules_seq_read(net, AF_INET6);
+}
+
+/* called with rcu lock held; no reference taken on fib6_info */
+int fib6_lookup(struct net *net, int oif, struct flowi6 *fl6,
+		struct fib6_result *res, int flags)
+{
+	int err;
+
+	if (net->ipv6.fib6_has_custom_rules) {
+		struct fib_lookup_arg arg = {
+			.lookup_ptr = fib6_table_lookup,
+			.lookup_data = &oif,
+			.result = res,
+			.flags = FIB_LOOKUP_NOREF,
+		};
+
+		l3mdev_update_flow(net, flowi6_to_flowi(fl6));
+
+		err = fib_rules_lookup(net->ipv6.fib6_rules_ops,
+				       flowi6_to_flowi(fl6), flags, &arg);
+	} else {
+		err = fib6_table_lookup(net, net->ipv6.fib6_local_tbl, oif,
+					fl6, res, flags);
+		if (err || res->f6i == net->ipv6.fib6_null_entry)
+			err = fib6_table_lookup(net, net->ipv6.fib6_main_tbl,
+						oif, fl6, res, flags);
+	}
+
+	return err;
+}
+
+struct dst_entry *fib6_rule_lookup(struct net *net, struct flowi6 *fl6,
+				   const struct sk_buff *skb,
+				   int flags, pol_lookup_t lookup)
+{
+	if (net->ipv6.fib6_has_custom_rules) {
+		struct fib6_result res = {};
+		struct fib_lookup_arg arg = {
+			.lookup_ptr = lookup,
+			.lookup_data = skb,
+			.result = &res,
+			.flags = FIB_LOOKUP_NOREF,
+		};
+
+		/* update flow if oif or iif point to device enslaved to l3mdev */
+		l3mdev_update_flow(net, flowi6_to_flowi(fl6));
+
+		fib_rules_lookup(net->ipv6.fib6_rules_ops,
+				 flowi6_to_flowi(fl6), flags, &arg);
+
+		if (res.rt6)
+			return &res.rt6->dst;
+	} else {
+		struct rt6_info *rt;
+
+		rt = pol_lookup_func(lookup,
+			     net, net->ipv6.fib6_local_tbl, fl6, skb, flags);
+		if (rt != net->ipv6.ip6_null_entry && rt->dst.error != -EAGAIN)
+			return &rt->dst;
+		ip6_rt_put_flags(rt, flags);
+		rt = pol_lookup_func(lookup,
+			     net, net->ipv6.fib6_main_tbl, fl6, skb, flags);
+		if (rt->dst.error != -EAGAIN)
+			return &rt->dst;
+		ip6_rt_put_flags(rt, flags);
+	}
+
+	if (!(flags & RT6_LOOKUP_F_DST_NOREF))
+		dst_hold(&net->ipv6.ip6_null_entry->dst);
+	return &net->ipv6.ip6_null_entry->dst;
+}
+
+static int fib6_rule_saddr(struct net *net, struct fib_rule *rule, int flags,
+			   struct flowi6 *flp6, const struct net_device *dev)
+{
+	struct fib6_rule *r = (struct fib6_rule *)rule;
+
+	/* If we need to find a source address for this traffic,
+	 * we check the result if it meets requirement of the rule.
+	 */
+	if ((rule->flags & FIB_RULE_FIND_SADDR) &&
+	    r->src.plen && !(flags & RT6_LOOKUP_F_HAS_SADDR)) {
+		struct in6_addr saddr;
+
+		if (ipv6_dev_get_saddr(net, dev, &flp6->daddr,
+				       rt6_flags2srcprefs(flags), &saddr))
+			return -EAGAIN;
+
+		if (!ipv6_prefix_equal(&saddr, &r->src.addr, r->src.plen))
+			return -EAGAIN;
+
+		flp6->saddr = saddr;
+	}
+
+	return 0;
+}
+
+static int fib6_rule_action_alt(struct fib_rule *rule, struct flowi *flp,
+				int flags, struct fib_lookup_arg *arg)
+{
+	struct fib6_result *res = arg->result;
+	struct flowi6 *flp6 = &flp->u.ip6;
+	struct net *net = rule->fr_net;
+	struct fib6_table *table;
+	int err, *oif;
+	u32 tb_id;
+
+	switch (rule->action) {
+	case FR_ACT_TO_TBL:
+		break;
+	case FR_ACT_UNREACHABLE:
+		return -ENETUNREACH;
+	case FR_ACT_PROHIBIT:
+		return -EACCES;
+	case FR_ACT_BLACKHOLE:
+	default:
+		return -EINVAL;
+	}
+
+	tb_id = fib_rule_get_table(rule, arg);
+	table = fib6_get_table(net, tb_id);
+	if (!table)
+		return -EAGAIN;
+
+	oif = (int *)arg->lookup_data;
+	err = fib6_table_lookup(net, table, *oif, flp6, res, flags);
+	if (!err && res->f6i != net->ipv6.fib6_null_entry)
+		err = fib6_rule_saddr(net, rule, flags, flp6,
+				      res->nh->fib_nh_dev);
+	else
+		err = -EAGAIN;
+
+	return err;
+}
+
+static int __fib6_rule_action(struct fib_rule *rule, struct flowi *flp,
+			      int flags, struct fib_lookup_arg *arg)
+{
+	struct fib6_result *res = arg->result;
+	struct flowi6 *flp6 = &flp->u.ip6;
+	struct rt6_info *rt = NULL;
+	struct fib6_table *table;
+	struct net *net = rule->fr_net;
+	pol_lookup_t lookup = arg->lookup_ptr;
+	int err = 0;
+	u32 tb_id;
+
+	switch (rule->action) {
+	case FR_ACT_TO_TBL:
+		break;
+	case FR_ACT_UNREACHABLE:
+		err = -ENETUNREACH;
+		rt = net->ipv6.ip6_null_entry;
+		goto discard_pkt;
+	default:
+	case FR_ACT_BLACKHOLE:
+		err = -EINVAL;
+		rt = net->ipv6.ip6_blk_hole_entry;
+		goto discard_pkt;
+	case FR_ACT_PROHIBIT:
+		err = -EACCES;
+		rt = net->ipv6.ip6_prohibit_entry;
+		goto discard_pkt;
+	}
+
+	tb_id = fib_rule_get_table(rule, arg);
+	table = fib6_get_table(net, tb_id);
+	if (!table) {
+		err = -EAGAIN;
+		goto out;
+	}
+
+	rt = pol_lookup_func(lookup,
+			     net, table, flp6, arg->lookup_data, flags);
+	if (rt != net->ipv6.ip6_null_entry) {
+		err = fib6_rule_saddr(net, rule, flags, flp6,
+				      ip6_dst_idev(&rt->dst)->dev);
+
+		if (err == -EAGAIN)
+			goto again;
+
+		err = rt->dst.error;
+		if (err != -EAGAIN)
+			goto out;
+	}
+again:
+	ip6_rt_put_flags(rt, flags);
+	err = -EAGAIN;
+	rt = NULL;
+	goto out;
+
+discard_pkt:
+	if (!(flags & RT6_LOOKUP_F_DST_NOREF))
+		dst_hold(&rt->dst);
+out:
+	res->rt6 = rt;
+	return err;
+}
+
+INDIRECT_CALLABLE_SCOPE int fib6_rule_action(struct fib_rule *rule,
+					     struct flowi *flp, int flags,
+					     struct fib_lookup_arg *arg)
+{
+	if (arg->lookup_ptr == fib6_table_lookup)
+		return fib6_rule_action_alt(rule, flp, flags, arg);
+
+	return __fib6_rule_action(rule, flp, flags, arg);
+}
+
+INDIRECT_CALLABLE_SCOPE bool fib6_rule_suppress(struct fib_rule *rule,
+						int flags,
+						struct fib_lookup_arg *arg)
+{
+	struct fib6_result *res = arg->result;
+	struct rt6_info *rt = res->rt6;
+	struct net_device *dev = NULL;
+
+	if (!rt)
+		return false;
+
+	if (rt->rt6i_idev)
+		dev = rt->rt6i_idev->dev;
+
+	/* do not accept result if the route does
+	 * not meet the required prefix length
+	 */
+	if (rt->rt6i_dst.plen <= rule->suppress_prefixlen)
+		goto suppress_route;
+
+	/* do not accept result if the route uses a device
+	 * belonging to a forbidden interface group
+	 */
+	if (rule->suppress_ifgroup != -1 && dev && dev->group == rule->suppress_ifgroup)
+		goto suppress_route;
+
+	return false;
+
+suppress_route:
+	ip6_rt_put_flags(rt, flags);
+	return true;
+}
+
+INDIRECT_CALLABLE_SCOPE int fib6_rule_match(struct fib_rule *rule,
+					    struct flowi *fl, int flags)
+{
+	struct fib6_rule *r = (struct fib6_rule *) rule;
+	struct flowi6 *fl6 = &fl->u.ip6;
+
+	if (r->dst.plen &&
+	    !ipv6_prefix_equal(&fl6->daddr, &r->dst.addr, r->dst.plen))
+		return 0;
+
+	/*
+	 * If FIB_RULE_FIND_SADDR is set and we do not have a
+	 * source address for the traffic, we defer check for
+	 * source address.
+	 */
+	if (r->src.plen) {
+		if (flags & RT6_LOOKUP_F_HAS_SADDR) {
+			if (!ipv6_prefix_equal(&fl6->saddr, &r->src.addr,
+					       r->src.plen))
+				return 0;
+		} else if (!(r->common.flags & FIB_RULE_FIND_SADDR))
+			return 0;
+	}
+
+	if (r->dscp && r->dscp != ip6_dscp(fl6->flowlabel))
+		return 0;
+
+	if (rule->ip_proto && (rule->ip_proto != fl6->flowi6_proto))
+		return 0;
+
+	if (fib_rule_port_range_set(&rule->sport_range) &&
+	    !fib_rule_port_inrange(&rule->sport_range, fl6->fl6_sport))
+		return 0;
+
+	if (fib_rule_port_range_set(&rule->dport_range) &&
+	    !fib_rule_port_inrange(&rule->dport_range, fl6->fl6_dport))
+		return 0;
+
+	return 1;
+}
+
+static int fib6_rule_configure(struct fib_rule *rule, struct sk_buff *skb,
+			       struct fib_rule_hdr *frh,
+			       struct nlattr **tb,
+			       struct netlink_ext_ack *extack)
+{
+	int err = -EINVAL;
+	struct net *net = sock_net(skb->sk);
+	struct fib6_rule *rule6 = (struct fib6_rule *) rule;
+
+	if (!inet_validate_dscp(frh->tos)) {
+		NL_SET_ERR_MSG(extack,
+			       "Invalid dsfield (tos): ECN bits must be 0");
+		goto errout;
+	}
+	rule6->dscp = inet_dsfield_to_dscp(frh->tos);
+
+	if (rule->action == FR_ACT_TO_TBL && !rule->l3mdev) {
+		if (rule->table == RT6_TABLE_UNSPEC) {
+			NL_SET_ERR_MSG(extack, "Invalid table");
+			goto errout;
+		}
+
+		if (fib6_new_table(net, rule->table) == NULL) {
+			err = -ENOBUFS;
+			goto errout;
+		}
+	}
+
+	if (frh->src_len)
+		rule6->src.addr = nla_get_in6_addr(tb[FRA_SRC]);
+
+	if (frh->dst_len)
+		rule6->dst.addr = nla_get_in6_addr(tb[FRA_DST]);
+
+	rule6->src.plen = frh->src_len;
+	rule6->dst.plen = frh->dst_len;
+
+	if (fib_rule_requires_fldissect(rule))
+		net->ipv6.fib6_rules_require_fldissect++;
+
+	net->ipv6.fib6_has_custom_rules = true;
+	err = 0;
+errout:
+	return err;
+}
+
+static int fib6_rule_delete(struct fib_rule *rule)
+{
+	struct net *net = rule->fr_net;
+
+	if (net->ipv6.fib6_rules_require_fldissect &&
+	    fib_rule_requires_fldissect(rule))
+		net->ipv6.fib6_rules_require_fldissect--;
+
+	return 0;
+}
+
+static int fib6_rule_compare(struct fib_rule *rule, struct fib_rule_hdr *frh,
+			     struct nlattr **tb)
+{
+	struct fib6_rule *rule6 = (struct fib6_rule *) rule;
+
+	if (frh->src_len && (rule6->src.plen != frh->src_len))
+		return 0;
+
+	if (frh->dst_len && (rule6->dst.plen != frh->dst_len))
+		return 0;
+
+	if (frh->tos && inet_dscp_to_dsfield(rule6->dscp) != frh->tos)
+		return 0;
+
+	if (frh->src_len &&
+	    nla_memcmp(tb[FRA_SRC], &rule6->src.addr, sizeof(struct in6_addr)))
+		return 0;
+
+	if (frh->dst_len &&
+	    nla_memcmp(tb[FRA_DST], &rule6->dst.addr, sizeof(struct in6_addr)))
+		return 0;
+
+	return 1;
+}
+
+static int fib6_rule_fill(struct fib_rule *rule, struct sk_buff *skb,
+			  struct fib_rule_hdr *frh)
+{
+	struct fib6_rule *rule6 = (struct fib6_rule *) rule;
+
+	frh->dst_len = rule6->dst.plen;
+	frh->src_len = rule6->src.plen;
+	frh->tos = inet_dscp_to_dsfield(rule6->dscp);
+
+	if ((rule6->dst.plen &&
+	     nla_put_in6_addr(skb, FRA_DST, &rule6->dst.addr)) ||
+	    (rule6->src.plen &&
+	     nla_put_in6_addr(skb, FRA_SRC, &rule6->src.addr)))
+		goto nla_put_failure;
+	return 0;
+
+nla_put_failure:
+	return -ENOBUFS;
+}
+
+static size_t fib6_rule_nlmsg_payload(struct fib_rule *rule)
+{
+	return nla_total_size(16) /* dst */
+	       + nla_total_size(16); /* src */
+}
+
+static const struct fib_rules_ops __net_initconst fib6_rules_ops_template = {
+	.family			= AF_INET6,
+	.rule_size		= sizeof(struct fib6_rule),
+	.addr_size		= sizeof(struct in6_addr),
+	.action			= fib6_rule_action,
+	.match			= fib6_rule_match,
+	.suppress		= fib6_rule_suppress,
+	.configure		= fib6_rule_configure,
+	.delete			= fib6_rule_delete,
+	.compare		= fib6_rule_compare,
+	.fill			= fib6_rule_fill,
+	.nlmsg_payload		= fib6_rule_nlmsg_payload,
+	.nlgroup		= RTNLGRP_IPV6_RULE,
+	.owner			= THIS_MODULE,
+	.fro_net		= &init_net,
+};
+
+static int __net_init fib6_rules_net_init(struct net *net)
+{
+	struct fib_rules_ops *ops;
+	int err;
+
+	ops = fib_rules_register(&fib6_rules_ops_template, net);
+	if (IS_ERR(ops))
+		return PTR_ERR(ops);
+
+	err = fib_default_rule_add(ops, 0, RT6_TABLE_LOCAL, 0);
+	if (err)
+		goto out_fib6_rules_ops;
+
+	err = fib_default_rule_add(ops, 0x7FFE, RT6_TABLE_MAIN, 0);
+	if (err)
+		goto out_fib6_rules_ops;
+
+	net->ipv6.fib6_rules_ops = ops;
+	net->ipv6.fib6_rules_require_fldissect = 0;
+out:
+	return err;
+
+out_fib6_rules_ops:
+	fib_rules_unregister(ops);
+	goto out;
+}
+
+static void __net_exit fib6_rules_net_exit_batch(struct list_head *net_list)
+{
+	struct net *net;
+
+	rtnl_lock();
+	list_for_each_entry(net, net_list, exit_list) {
+		fib_rules_unregister(net->ipv6.fib6_rules_ops);
+		cond_resched();
+	}
+	rtnl_unlock();
+}
+
+static struct pernet_operations fib6_rules_net_ops = {
+	.init = fib6_rules_net_init,
+	.exit_batch = fib6_rules_net_exit_batch,
+};
+
+int __init fib6_rules_init(void)
+{
+	return register_pernet_subsys(&fib6_rules_net_ops);
+}
+
+
+void fib6_rules_cleanup(void)
+{
+	unregister_pernet_subsys(&fib6_rules_net_ops);
+}