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, 619 insertions, 0 deletions

diff --git a/net/ipv6/anycast.c b/net/ipv6/anycast.c
new file mode 100644
index 000000000..dacdea7fc
--- /dev/null
+++ b/net/ipv6/anycast.c
@@ -0,0 +1,619 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ *	Anycast support for IPv6
+ *	Linux INET6 implementation
+ *
+ *	Authors:
+ *	David L Stevens (dlstevens@us.ibm.com)
+ *
+ *	based heavily on net/ipv6/mcast.c
+ */
+
+#include <linux/capability.h>
+#include <linux/module.h>
+#include <linux/errno.h>
+#include <linux/types.h>
+#include <linux/random.h>
+#include <linux/string.h>
+#include <linux/socket.h>
+#include <linux/sockios.h>
+#include <linux/net.h>
+#include <linux/in6.h>
+#include <linux/netdevice.h>
+#include <linux/if_arp.h>
+#include <linux/route.h>
+#include <linux/init.h>
+#include <linux/proc_fs.h>
+#include <linux/seq_file.h>
+#include <linux/slab.h>
+
+#include <net/net_namespace.h>
+#include <net/sock.h>
+#include <net/snmp.h>
+
+#include <net/ipv6.h>
+#include <net/protocol.h>
+#include <net/if_inet6.h>
+#include <net/ndisc.h>
+#include <net/addrconf.h>
+#include <net/ip6_route.h>
+
+#include <net/checksum.h>
+
+#define IN6_ADDR_HSIZE_SHIFT	8
+#define IN6_ADDR_HSIZE		BIT(IN6_ADDR_HSIZE_SHIFT)
+/*	anycast address hash table
+ */
+static struct hlist_head inet6_acaddr_lst[IN6_ADDR_HSIZE];
+static DEFINE_SPINLOCK(acaddr_hash_lock);
+
+static int ipv6_dev_ac_dec(struct net_device *dev, const struct in6_addr *addr);
+
+static u32 inet6_acaddr_hash(struct net *net, const struct in6_addr *addr)
+{
+	u32 val = ipv6_addr_hash(addr) ^ net_hash_mix(net);
+
+	return hash_32(val, IN6_ADDR_HSIZE_SHIFT);
+}
+
+/*
+ *	socket join an anycast group
+ */
+
+int ipv6_sock_ac_join(struct sock *sk, int ifindex, const struct in6_addr *addr)
+{
+	struct ipv6_pinfo *np = inet6_sk(sk);
+	struct net_device *dev = NULL;
+	struct inet6_dev *idev;
+	struct ipv6_ac_socklist *pac;
+	struct net *net = sock_net(sk);
+	int	ishost = !net->ipv6.devconf_all->forwarding;
+	int	err = 0;
+
+	ASSERT_RTNL();
+
+	if (!ns_capable(net->user_ns, CAP_NET_ADMIN))
+		return -EPERM;
+	if (ipv6_addr_is_multicast(addr))
+		return -EINVAL;
+
+	if (ifindex)
+		dev = __dev_get_by_index(net, ifindex);
+
+	if (ipv6_chk_addr_and_flags(net, addr, dev, true, 0, IFA_F_TENTATIVE))
+		return -EINVAL;
+
+	pac = sock_kmalloc(sk, sizeof(struct ipv6_ac_socklist), GFP_KERNEL);
+	if (!pac)
+		return -ENOMEM;
+	pac->acl_next = NULL;
+	pac->acl_addr = *addr;
+
+	if (ifindex == 0) {
+		struct rt6_info *rt;
+
+		rt = rt6_lookup(net, addr, NULL, 0, NULL, 0);
+		if (rt) {
+			dev = rt->dst.dev;
+			ip6_rt_put(rt);
+		} else if (ishost) {
+			err = -EADDRNOTAVAIL;
+			goto error;
+		} else {
+			/* router, no matching interface: just pick one */
+			dev = __dev_get_by_flags(net, IFF_UP,
+						 IFF_UP | IFF_LOOPBACK);
+		}
+	}
+
+	if (!dev) {
+		err = -ENODEV;
+		goto error;
+	}
+
+	idev = __in6_dev_get(dev);
+	if (!idev) {
+		if (ifindex)
+			err = -ENODEV;
+		else
+			err = -EADDRNOTAVAIL;
+		goto error;
+	}
+	/* reset ishost, now that we have a specific device */
+	ishost = !idev->cnf.forwarding;
+
+	pac->acl_ifindex = dev->ifindex;
+
+	/* XXX
+	 * For hosts, allow link-local or matching prefix anycasts.
+	 * This obviates the need for propagating anycast routes while
+	 * still allowing some non-router anycast participation.
+	 */
+	if (!ipv6_chk_prefix(addr, dev)) {
+		if (ishost)
+			err = -EADDRNOTAVAIL;
+		if (err)
+			goto error;
+	}
+
+	err = __ipv6_dev_ac_inc(idev, addr);
+	if (!err) {
+		pac->acl_next = np->ipv6_ac_list;
+		np->ipv6_ac_list = pac;
+		pac = NULL;
+	}
+
+error:
+	if (pac)
+		sock_kfree_s(sk, pac, sizeof(*pac));
+	return err;
+}
+
+/*
+ *	socket leave an anycast group
+ */
+int ipv6_sock_ac_drop(struct sock *sk, int ifindex, const struct in6_addr *addr)
+{
+	struct ipv6_pinfo *np = inet6_sk(sk);
+	struct net_device *dev;
+	struct ipv6_ac_socklist *pac, *prev_pac;
+	struct net *net = sock_net(sk);
+
+	ASSERT_RTNL();
+
+	prev_pac = NULL;
+	for (pac = np->ipv6_ac_list; pac; pac = pac->acl_next) {
+		if ((ifindex == 0 || pac->acl_ifindex == ifindex) &&
+		     ipv6_addr_equal(&pac->acl_addr, addr))
+			break;
+		prev_pac = pac;
+	}
+	if (!pac)
+		return -ENOENT;
+	if (prev_pac)
+		prev_pac->acl_next = pac->acl_next;
+	else
+		np->ipv6_ac_list = pac->acl_next;
+
+	dev = __dev_get_by_index(net, pac->acl_ifindex);
+	if (dev)
+		ipv6_dev_ac_dec(dev, &pac->acl_addr);
+
+	sock_kfree_s(sk, pac, sizeof(*pac));
+	return 0;
+}
+
+void __ipv6_sock_ac_close(struct sock *sk)
+{
+	struct ipv6_pinfo *np = inet6_sk(sk);
+	struct net_device *dev = NULL;
+	struct ipv6_ac_socklist *pac;
+	struct net *net = sock_net(sk);
+	int	prev_index;
+
+	ASSERT_RTNL();
+	pac = np->ipv6_ac_list;
+	np->ipv6_ac_list = NULL;
+
+	prev_index = 0;
+	while (pac) {
+		struct ipv6_ac_socklist *next = pac->acl_next;
+
+		if (pac->acl_ifindex != prev_index) {
+			dev = __dev_get_by_index(net, pac->acl_ifindex);
+			prev_index = pac->acl_ifindex;
+		}
+		if (dev)
+			ipv6_dev_ac_dec(dev, &pac->acl_addr);
+		sock_kfree_s(sk, pac, sizeof(*pac));
+		pac = next;
+	}
+}
+
+void ipv6_sock_ac_close(struct sock *sk)
+{
+	struct ipv6_pinfo *np = inet6_sk(sk);
+
+	if (!np->ipv6_ac_list)
+		return;
+	rtnl_lock();
+	__ipv6_sock_ac_close(sk);
+	rtnl_unlock();
+}
+
+static void ipv6_add_acaddr_hash(struct net *net, struct ifacaddr6 *aca)
+{
+	unsigned int hash = inet6_acaddr_hash(net, &aca->aca_addr);
+
+	spin_lock(&acaddr_hash_lock);
+	hlist_add_head_rcu(&aca->aca_addr_lst, &inet6_acaddr_lst[hash]);
+	spin_unlock(&acaddr_hash_lock);
+}
+
+static void ipv6_del_acaddr_hash(struct ifacaddr6 *aca)
+{
+	spin_lock(&acaddr_hash_lock);
+	hlist_del_init_rcu(&aca->aca_addr_lst);
+	spin_unlock(&acaddr_hash_lock);
+}
+
+static void aca_get(struct ifacaddr6 *aca)
+{
+	refcount_inc(&aca->aca_refcnt);
+}
+
+static void aca_free_rcu(struct rcu_head *h)
+{
+	struct ifacaddr6 *aca = container_of(h, struct ifacaddr6, rcu);
+
+	fib6_info_release(aca->aca_rt);
+	kfree(aca);
+}
+
+static void aca_put(struct ifacaddr6 *ac)
+{
+	if (refcount_dec_and_test(&ac->aca_refcnt)) {
+		call_rcu(&ac->rcu, aca_free_rcu);
+	}
+}
+
+static struct ifacaddr6 *aca_alloc(struct fib6_info *f6i,
+				   const struct in6_addr *addr)
+{
+	struct ifacaddr6 *aca;
+
+	aca = kzalloc(sizeof(*aca), GFP_ATOMIC);
+	if (!aca)
+		return NULL;
+
+	aca->aca_addr = *addr;
+	fib6_info_hold(f6i);
+	aca->aca_rt = f6i;
+	INIT_HLIST_NODE(&aca->aca_addr_lst);
+	aca->aca_users = 1;
+	/* aca_tstamp should be updated upon changes */
+	aca->aca_cstamp = aca->aca_tstamp = jiffies;
+	refcount_set(&aca->aca_refcnt, 1);
+
+	return aca;
+}
+
+/*
+ *	device anycast group inc (add if not found)
+ */
+int __ipv6_dev_ac_inc(struct inet6_dev *idev, const struct in6_addr *addr)
+{
+	struct ifacaddr6 *aca;
+	struct fib6_info *f6i;
+	struct net *net;
+	int err;
+
+	ASSERT_RTNL();
+
+	write_lock_bh(&idev->lock);
+	if (idev->dead) {
+		err = -ENODEV;
+		goto out;
+	}
+
+	for (aca = idev->ac_list; aca; aca = aca->aca_next) {
+		if (ipv6_addr_equal(&aca->aca_addr, addr)) {
+			aca->aca_users++;
+			err = 0;
+			goto out;
+		}
+	}
+
+	net = dev_net(idev->dev);
+	f6i = addrconf_f6i_alloc(net, idev, addr, true, GFP_ATOMIC);
+	if (IS_ERR(f6i)) {
+		err = PTR_ERR(f6i);
+		goto out;
+	}
+	aca = aca_alloc(f6i, addr);
+	if (!aca) {
+		fib6_info_release(f6i);
+		err = -ENOMEM;
+		goto out;
+	}
+
+	aca->aca_next = idev->ac_list;
+	idev->ac_list = aca;
+
+	/* Hold this for addrconf_join_solict() below before we unlock,
+	 * it is already exposed via idev->ac_list.
+	 */
+	aca_get(aca);
+	write_unlock_bh(&idev->lock);
+
+	ipv6_add_acaddr_hash(net, aca);
+
+	ip6_ins_rt(net, f6i);
+
+	addrconf_join_solict(idev->dev, &aca->aca_addr);
+
+	aca_put(aca);
+	return 0;
+out:
+	write_unlock_bh(&idev->lock);
+	return err;
+}
+
+/*
+ *	device anycast group decrement
+ */
+int __ipv6_dev_ac_dec(struct inet6_dev *idev, const struct in6_addr *addr)
+{
+	struct ifacaddr6 *aca, *prev_aca;
+
+	ASSERT_RTNL();
+
+	write_lock_bh(&idev->lock);
+	prev_aca = NULL;
+	for (aca = idev->ac_list; aca; aca = aca->aca_next) {
+		if (ipv6_addr_equal(&aca->aca_addr, addr))
+			break;
+		prev_aca = aca;
+	}
+	if (!aca) {
+		write_unlock_bh(&idev->lock);
+		return -ENOENT;
+	}
+	if (--aca->aca_users > 0) {
+		write_unlock_bh(&idev->lock);
+		return 0;
+	}
+	if (prev_aca)
+		prev_aca->aca_next = aca->aca_next;
+	else
+		idev->ac_list = aca->aca_next;
+	write_unlock_bh(&idev->lock);
+	ipv6_del_acaddr_hash(aca);
+	addrconf_leave_solict(idev, &aca->aca_addr);
+
+	ip6_del_rt(dev_net(idev->dev), aca->aca_rt, false);
+
+	aca_put(aca);
+	return 0;
+}
+
+/* called with rtnl_lock() */
+static int ipv6_dev_ac_dec(struct net_device *dev, const struct in6_addr *addr)
+{
+	struct inet6_dev *idev = __in6_dev_get(dev);
+
+	if (!idev)
+		return -ENODEV;
+	return __ipv6_dev_ac_dec(idev, addr);
+}
+
+void ipv6_ac_destroy_dev(struct inet6_dev *idev)
+{
+	struct ifacaddr6 *aca;
+
+	write_lock_bh(&idev->lock);
+	while ((aca = idev->ac_list) != NULL) {
+		idev->ac_list = aca->aca_next;
+		write_unlock_bh(&idev->lock);
+
+		ipv6_del_acaddr_hash(aca);
+
+		addrconf_leave_solict(idev, &aca->aca_addr);
+
+		ip6_del_rt(dev_net(idev->dev), aca->aca_rt, false);
+
+		aca_put(aca);
+
+		write_lock_bh(&idev->lock);
+	}
+	write_unlock_bh(&idev->lock);
+}
+
+/*
+ *	check if the interface has this anycast address
+ *	called with rcu_read_lock()
+ */
+static bool ipv6_chk_acast_dev(struct net_device *dev, const struct in6_addr *addr)
+{
+	struct inet6_dev *idev;
+	struct ifacaddr6 *aca;
+
+	idev = __in6_dev_get(dev);
+	if (idev) {
+		read_lock_bh(&idev->lock);
+		for (aca = idev->ac_list; aca; aca = aca->aca_next)
+			if (ipv6_addr_equal(&aca->aca_addr, addr))
+				break;
+		read_unlock_bh(&idev->lock);
+		return aca != NULL;
+	}
+	return false;
+}
+
+/*
+ *	check if given interface (or any, if dev==0) has this anycast address
+ */
+bool ipv6_chk_acast_addr(struct net *net, struct net_device *dev,
+			 const struct in6_addr *addr)
+{
+	struct net_device *nh_dev;
+	struct ifacaddr6 *aca;
+	bool found = false;
+
+	rcu_read_lock();
+	if (dev)
+		found = ipv6_chk_acast_dev(dev, addr);
+	else {
+		unsigned int hash = inet6_acaddr_hash(net, addr);
+
+		hlist_for_each_entry_rcu(aca, &inet6_acaddr_lst[hash],
+					 aca_addr_lst) {
+			nh_dev = fib6_info_nh_dev(aca->aca_rt);
+			if (!nh_dev || !net_eq(dev_net(nh_dev), net))
+				continue;
+			if (ipv6_addr_equal(&aca->aca_addr, addr)) {
+				found = true;
+				break;
+			}
+		}
+	}
+	rcu_read_unlock();
+	return found;
+}
+
+/*	check if this anycast address is link-local on given interface or
+ *	is global
+ */
+bool ipv6_chk_acast_addr_src(struct net *net, struct net_device *dev,
+			     const struct in6_addr *addr)
+{
+	return ipv6_chk_acast_addr(net,
+				   (ipv6_addr_type(addr) & IPV6_ADDR_LINKLOCAL ?
+				    dev : NULL),
+				   addr);
+}
+
+#ifdef CONFIG_PROC_FS
+struct ac6_iter_state {
+	struct seq_net_private p;
+	struct net_device *dev;
+	struct inet6_dev *idev;
+};
+
+#define ac6_seq_private(seq)	((struct ac6_iter_state *)(seq)->private)
+
+static inline struct ifacaddr6 *ac6_get_first(struct seq_file *seq)
+{
+	struct ifacaddr6 *im = NULL;
+	struct ac6_iter_state *state = ac6_seq_private(seq);
+	struct net *net = seq_file_net(seq);
+
+	state->idev = NULL;
+	for_each_netdev_rcu(net, state->dev) {
+		struct inet6_dev *idev;
+		idev = __in6_dev_get(state->dev);
+		if (!idev)
+			continue;
+		read_lock_bh(&idev->lock);
+		im = idev->ac_list;
+		if (im) {
+			state->idev = idev;
+			break;
+		}
+		read_unlock_bh(&idev->lock);
+	}
+	return im;
+}
+
+static struct ifacaddr6 *ac6_get_next(struct seq_file *seq, struct ifacaddr6 *im)
+{
+	struct ac6_iter_state *state = ac6_seq_private(seq);
+
+	im = im->aca_next;
+	while (!im) {
+		if (likely(state->idev != NULL))
+			read_unlock_bh(&state->idev->lock);
+
+		state->dev = next_net_device_rcu(state->dev);
+		if (!state->dev) {
+			state->idev = NULL;
+			break;
+		}
+		state->idev = __in6_dev_get(state->dev);
+		if (!state->idev)
+			continue;
+		read_lock_bh(&state->idev->lock);
+		im = state->idev->ac_list;
+	}
+	return im;
+}
+
+static struct ifacaddr6 *ac6_get_idx(struct seq_file *seq, loff_t pos)
+{
+	struct ifacaddr6 *im = ac6_get_first(seq);
+	if (im)
+		while (pos && (im = ac6_get_next(seq, im)) != NULL)
+			--pos;
+	return pos ? NULL : im;
+}
+
+static void *ac6_seq_start(struct seq_file *seq, loff_t *pos)
+	__acquires(RCU)
+{
+	rcu_read_lock();
+	return ac6_get_idx(seq, *pos);
+}
+
+static void *ac6_seq_next(struct seq_file *seq, void *v, loff_t *pos)
+{
+	struct ifacaddr6 *im = ac6_get_next(seq, v);
+
+	++*pos;
+	return im;
+}
+
+static void ac6_seq_stop(struct seq_file *seq, void *v)
+	__releases(RCU)
+{
+	struct ac6_iter_state *state = ac6_seq_private(seq);
+
+	if (likely(state->idev != NULL)) {
+		read_unlock_bh(&state->idev->lock);
+		state->idev = NULL;
+	}
+	rcu_read_unlock();
+}
+
+static int ac6_seq_show(struct seq_file *seq, void *v)
+{
+	struct ifacaddr6 *im = (struct ifacaddr6 *)v;
+	struct ac6_iter_state *state = ac6_seq_private(seq);
+
+	seq_printf(seq, "%-4d %-15s %pi6 %5d\n",
+		   state->dev->ifindex, state->dev->name,
+		   &im->aca_addr, im->aca_users);
+	return 0;
+}
+
+static const struct seq_operations ac6_seq_ops = {
+	.start	=	ac6_seq_start,
+	.next	=	ac6_seq_next,
+	.stop	=	ac6_seq_stop,
+	.show	=	ac6_seq_show,
+};
+
+int __net_init ac6_proc_init(struct net *net)
+{
+	if (!proc_create_net("anycast6", 0444, net->proc_net, &ac6_seq_ops,
+			sizeof(struct ac6_iter_state)))
+		return -ENOMEM;
+
+	return 0;
+}
+
+void ac6_proc_exit(struct net *net)
+{
+	remove_proc_entry("anycast6", net->proc_net);
+}
+#endif
+
+/*	Init / cleanup code
+ */
+int __init ipv6_anycast_init(void)
+{
+	int i;
+
+	for (i = 0; i < IN6_ADDR_HSIZE; i++)
+		INIT_HLIST_HEAD(&inet6_acaddr_lst[i]);
+	return 0;
+}
+
+void ipv6_anycast_cleanup(void)
+{
+	int i;
+
+	spin_lock(&acaddr_hash_lock);
+	for (i = 0; i < IN6_ADDR_HSIZE; i++)
+		WARN_ON(!hlist_empty(&inet6_acaddr_lst[i]));
+	spin_unlock(&acaddr_hash_lock);
+}