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, 448 insertions, 0 deletions

diff --git a/net/ipv4/ipmr_base.c b/net/ipv4/ipmr_base.c
new file mode 100644
index 000000000..271dc03fc
--- /dev/null
+++ b/net/ipv4/ipmr_base.c
@@ -0,0 +1,448 @@
+/* Linux multicast routing support
+ * Common logic shared by IPv4 [ipmr] and IPv6 [ip6mr] implementation
+ */
+
+#include <linux/rhashtable.h>
+#include <linux/mroute_base.h>
+
+/* Sets everything common except 'dev', since that is done under locking */
+void vif_device_init(struct vif_device *v,
+		     struct net_device *dev,
+		     unsigned long rate_limit,
+		     unsigned char threshold,
+		     unsigned short flags,
+		     unsigned short get_iflink_mask)
+{
+	RCU_INIT_POINTER(v->dev, NULL);
+	v->bytes_in = 0;
+	v->bytes_out = 0;
+	v->pkt_in = 0;
+	v->pkt_out = 0;
+	v->rate_limit = rate_limit;
+	v->flags = flags;
+	v->threshold = threshold;
+	if (v->flags & get_iflink_mask)
+		v->link = dev_get_iflink(dev);
+	else
+		v->link = dev->ifindex;
+}
+EXPORT_SYMBOL(vif_device_init);
+
+struct mr_table *
+mr_table_alloc(struct net *net, u32 id,
+	       struct mr_table_ops *ops,
+	       void (*expire_func)(struct timer_list *t),
+	       void (*table_set)(struct mr_table *mrt,
+				 struct net *net))
+{
+	struct mr_table *mrt;
+	int err;
+
+	mrt = kzalloc(sizeof(*mrt), GFP_KERNEL);
+	if (!mrt)
+		return ERR_PTR(-ENOMEM);
+	mrt->id = id;
+	write_pnet(&mrt->net, net);
+
+	mrt->ops = *ops;
+	err = rhltable_init(&mrt->mfc_hash, mrt->ops.rht_params);
+	if (err) {
+		kfree(mrt);
+		return ERR_PTR(err);
+	}
+	INIT_LIST_HEAD(&mrt->mfc_cache_list);
+	INIT_LIST_HEAD(&mrt->mfc_unres_queue);
+
+	timer_setup(&mrt->ipmr_expire_timer, expire_func, 0);
+
+	mrt->mroute_reg_vif_num = -1;
+	table_set(mrt, net);
+	return mrt;
+}
+EXPORT_SYMBOL(mr_table_alloc);
+
+void *mr_mfc_find_parent(struct mr_table *mrt, void *hasharg, int parent)
+{
+	struct rhlist_head *tmp, *list;
+	struct mr_mfc *c;
+
+	list = rhltable_lookup(&mrt->mfc_hash, hasharg, *mrt->ops.rht_params);
+	rhl_for_each_entry_rcu(c, tmp, list, mnode)
+		if (parent == -1 || parent == c->mfc_parent)
+			return c;
+
+	return NULL;
+}
+EXPORT_SYMBOL(mr_mfc_find_parent);
+
+void *mr_mfc_find_any_parent(struct mr_table *mrt, int vifi)
+{
+	struct rhlist_head *tmp, *list;
+	struct mr_mfc *c;
+
+	list = rhltable_lookup(&mrt->mfc_hash, mrt->ops.cmparg_any,
+			       *mrt->ops.rht_params);
+	rhl_for_each_entry_rcu(c, tmp, list, mnode)
+		if (c->mfc_un.res.ttls[vifi] < 255)
+			return c;
+
+	return NULL;
+}
+EXPORT_SYMBOL(mr_mfc_find_any_parent);
+
+void *mr_mfc_find_any(struct mr_table *mrt, int vifi, void *hasharg)
+{
+	struct rhlist_head *tmp, *list;
+	struct mr_mfc *c, *proxy;
+
+	list = rhltable_lookup(&mrt->mfc_hash, hasharg, *mrt->ops.rht_params);
+	rhl_for_each_entry_rcu(c, tmp, list, mnode) {
+		if (c->mfc_un.res.ttls[vifi] < 255)
+			return c;
+
+		/* It's ok if the vifi is part of the static tree */
+		proxy = mr_mfc_find_any_parent(mrt, c->mfc_parent);
+		if (proxy && proxy->mfc_un.res.ttls[vifi] < 255)
+			return c;
+	}
+
+	return mr_mfc_find_any_parent(mrt, vifi);
+}
+EXPORT_SYMBOL(mr_mfc_find_any);
+
+#ifdef CONFIG_PROC_FS
+void *mr_vif_seq_idx(struct net *net, struct mr_vif_iter *iter, loff_t pos)
+{
+	struct mr_table *mrt = iter->mrt;
+
+	for (iter->ct = 0; iter->ct < mrt->maxvif; ++iter->ct) {
+		if (!VIF_EXISTS(mrt, iter->ct))
+			continue;
+		if (pos-- == 0)
+			return &mrt->vif_table[iter->ct];
+	}
+	return NULL;
+}
+EXPORT_SYMBOL(mr_vif_seq_idx);
+
+void *mr_vif_seq_next(struct seq_file *seq, void *v, loff_t *pos)
+{
+	struct mr_vif_iter *iter = seq->private;
+	struct net *net = seq_file_net(seq);
+	struct mr_table *mrt = iter->mrt;
+
+	++*pos;
+	if (v == SEQ_START_TOKEN)
+		return mr_vif_seq_idx(net, iter, 0);
+
+	while (++iter->ct < mrt->maxvif) {
+		if (!VIF_EXISTS(mrt, iter->ct))
+			continue;
+		return &mrt->vif_table[iter->ct];
+	}
+	return NULL;
+}
+EXPORT_SYMBOL(mr_vif_seq_next);
+
+void *mr_mfc_seq_idx(struct net *net,
+		     struct mr_mfc_iter *it, loff_t pos)
+{
+	struct mr_table *mrt = it->mrt;
+	struct mr_mfc *mfc;
+
+	rcu_read_lock();
+	it->cache = &mrt->mfc_cache_list;
+	list_for_each_entry_rcu(mfc, &mrt->mfc_cache_list, list)
+		if (pos-- == 0)
+			return mfc;
+	rcu_read_unlock();
+
+	spin_lock_bh(it->lock);
+	it->cache = &mrt->mfc_unres_queue;
+	list_for_each_entry(mfc, it->cache, list)
+		if (pos-- == 0)
+			return mfc;
+	spin_unlock_bh(it->lock);
+
+	it->cache = NULL;
+	return NULL;
+}
+EXPORT_SYMBOL(mr_mfc_seq_idx);
+
+void *mr_mfc_seq_next(struct seq_file *seq, void *v,
+		      loff_t *pos)
+{
+	struct mr_mfc_iter *it = seq->private;
+	struct net *net = seq_file_net(seq);
+	struct mr_table *mrt = it->mrt;
+	struct mr_mfc *c = v;
+
+	++*pos;
+
+	if (v == SEQ_START_TOKEN)
+		return mr_mfc_seq_idx(net, seq->private, 0);
+
+	if (c->list.next != it->cache)
+		return list_entry(c->list.next, struct mr_mfc, list);
+
+	if (it->cache == &mrt->mfc_unres_queue)
+		goto end_of_list;
+
+	/* exhausted cache_array, show unresolved */
+	rcu_read_unlock();
+	it->cache = &mrt->mfc_unres_queue;
+
+	spin_lock_bh(it->lock);
+	if (!list_empty(it->cache))
+		return list_first_entry(it->cache, struct mr_mfc, list);
+
+end_of_list:
+	spin_unlock_bh(it->lock);
+	it->cache = NULL;
+
+	return NULL;
+}
+EXPORT_SYMBOL(mr_mfc_seq_next);
+#endif
+
+int mr_fill_mroute(struct mr_table *mrt, struct sk_buff *skb,
+		   struct mr_mfc *c, struct rtmsg *rtm)
+{
+	struct net_device *vif_dev;
+	struct rta_mfc_stats mfcs;
+	struct nlattr *mp_attr;
+	struct rtnexthop *nhp;
+	unsigned long lastuse;
+	int ct;
+
+	/* If cache is unresolved, don't try to parse IIF and OIF */
+	if (c->mfc_parent >= MAXVIFS) {
+		rtm->rtm_flags |= RTNH_F_UNRESOLVED;
+		return -ENOENT;
+	}
+
+	rcu_read_lock();
+	vif_dev = rcu_dereference(mrt->vif_table[c->mfc_parent].dev);
+	if (vif_dev && nla_put_u32(skb, RTA_IIF, vif_dev->ifindex) < 0) {
+		rcu_read_unlock();
+		return -EMSGSIZE;
+	}
+	rcu_read_unlock();
+
+	if (c->mfc_flags & MFC_OFFLOAD)
+		rtm->rtm_flags |= RTNH_F_OFFLOAD;
+
+	mp_attr = nla_nest_start_noflag(skb, RTA_MULTIPATH);
+	if (!mp_attr)
+		return -EMSGSIZE;
+
+	rcu_read_lock();
+	for (ct = c->mfc_un.res.minvif; ct < c->mfc_un.res.maxvif; ct++) {
+		struct vif_device *vif = &mrt->vif_table[ct];
+
+		vif_dev = rcu_dereference(vif->dev);
+		if (vif_dev && c->mfc_un.res.ttls[ct] < 255) {
+
+			nhp = nla_reserve_nohdr(skb, sizeof(*nhp));
+			if (!nhp) {
+				rcu_read_unlock();
+				nla_nest_cancel(skb, mp_attr);
+				return -EMSGSIZE;
+			}
+
+			nhp->rtnh_flags = 0;
+			nhp->rtnh_hops = c->mfc_un.res.ttls[ct];
+			nhp->rtnh_ifindex = vif_dev->ifindex;
+			nhp->rtnh_len = sizeof(*nhp);
+		}
+	}
+	rcu_read_unlock();
+
+	nla_nest_end(skb, mp_attr);
+
+	lastuse = READ_ONCE(c->mfc_un.res.lastuse);
+	lastuse = time_after_eq(jiffies, lastuse) ? jiffies - lastuse : 0;
+
+	mfcs.mfcs_packets = c->mfc_un.res.pkt;
+	mfcs.mfcs_bytes = c->mfc_un.res.bytes;
+	mfcs.mfcs_wrong_if = c->mfc_un.res.wrong_if;
+	if (nla_put_64bit(skb, RTA_MFC_STATS, sizeof(mfcs), &mfcs, RTA_PAD) ||
+	    nla_put_u64_64bit(skb, RTA_EXPIRES, jiffies_to_clock_t(lastuse),
+			      RTA_PAD))
+		return -EMSGSIZE;
+
+	rtm->rtm_type = RTN_MULTICAST;
+	return 1;
+}
+EXPORT_SYMBOL(mr_fill_mroute);
+
+static bool mr_mfc_uses_dev(const struct mr_table *mrt,
+			    const struct mr_mfc *c,
+			    const struct net_device *dev)
+{
+	int ct;
+
+	for (ct = c->mfc_un.res.minvif; ct < c->mfc_un.res.maxvif; ct++) {
+		const struct net_device *vif_dev;
+		const struct vif_device *vif;
+
+		vif = &mrt->vif_table[ct];
+		vif_dev = rcu_access_pointer(vif->dev);
+		if (vif_dev && c->mfc_un.res.ttls[ct] < 255 &&
+		    vif_dev == dev)
+			return true;
+	}
+	return false;
+}
+
+int mr_table_dump(struct mr_table *mrt, struct sk_buff *skb,
+		  struct netlink_callback *cb,
+		  int (*fill)(struct mr_table *mrt, struct sk_buff *skb,
+			      u32 portid, u32 seq, struct mr_mfc *c,
+			      int cmd, int flags),
+		  spinlock_t *lock, struct fib_dump_filter *filter)
+{
+	unsigned int e = 0, s_e = cb->args[1];
+	unsigned int flags = NLM_F_MULTI;
+	struct mr_mfc *mfc;
+	int err;
+
+	if (filter->filter_set)
+		flags |= NLM_F_DUMP_FILTERED;
+
+	list_for_each_entry_rcu(mfc, &mrt->mfc_cache_list, list) {
+		if (e < s_e)
+			goto next_entry;
+		if (filter->dev &&
+		    !mr_mfc_uses_dev(mrt, mfc, filter->dev))
+			goto next_entry;
+
+		err = fill(mrt, skb, NETLINK_CB(cb->skb).portid,
+			   cb->nlh->nlmsg_seq, mfc, RTM_NEWROUTE, flags);
+		if (err < 0)
+			goto out;
+next_entry:
+		e++;
+	}
+
+	spin_lock_bh(lock);
+	list_for_each_entry(mfc, &mrt->mfc_unres_queue, list) {
+		if (e < s_e)
+			goto next_entry2;
+		if (filter->dev &&
+		    !mr_mfc_uses_dev(mrt, mfc, filter->dev))
+			goto next_entry2;
+
+		err = fill(mrt, skb, NETLINK_CB(cb->skb).portid,
+			   cb->nlh->nlmsg_seq, mfc, RTM_NEWROUTE, flags);
+		if (err < 0) {
+			spin_unlock_bh(lock);
+			goto out;
+		}
+next_entry2:
+		e++;
+	}
+	spin_unlock_bh(lock);
+	err = 0;
+out:
+	cb->args[1] = e;
+	return err;
+}
+EXPORT_SYMBOL(mr_table_dump);
+
+int mr_rtm_dumproute(struct sk_buff *skb, struct netlink_callback *cb,
+		     struct mr_table *(*iter)(struct net *net,
+					      struct mr_table *mrt),
+		     int (*fill)(struct mr_table *mrt,
+				 struct sk_buff *skb,
+				 u32 portid, u32 seq, struct mr_mfc *c,
+				 int cmd, int flags),
+		     spinlock_t *lock, struct fib_dump_filter *filter)
+{
+	unsigned int t = 0, s_t = cb->args[0];
+	struct net *net = sock_net(skb->sk);
+	struct mr_table *mrt;
+	int err;
+
+	/* multicast does not track protocol or have route type other
+	 * than RTN_MULTICAST
+	 */
+	if (filter->filter_set) {
+		if (filter->protocol || filter->flags ||
+		    (filter->rt_type && filter->rt_type != RTN_MULTICAST))
+			return skb->len;
+	}
+
+	rcu_read_lock();
+	for (mrt = iter(net, NULL); mrt; mrt = iter(net, mrt)) {
+		if (t < s_t)
+			goto next_table;
+
+		err = mr_table_dump(mrt, skb, cb, fill, lock, filter);
+		if (err < 0)
+			break;
+		cb->args[1] = 0;
+next_table:
+		t++;
+	}
+	rcu_read_unlock();
+
+	cb->args[0] = t;
+
+	return skb->len;
+}
+EXPORT_SYMBOL(mr_rtm_dumproute);
+
+int mr_dump(struct net *net, struct notifier_block *nb, unsigned short family,
+	    int (*rules_dump)(struct net *net,
+			      struct notifier_block *nb,
+			      struct netlink_ext_ack *extack),
+	    struct mr_table *(*mr_iter)(struct net *net,
+					struct mr_table *mrt),
+	    struct netlink_ext_ack *extack)
+{
+	struct mr_table *mrt;
+	int err;
+
+	err = rules_dump(net, nb, extack);
+	if (err)
+		return err;
+
+	for (mrt = mr_iter(net, NULL); mrt; mrt = mr_iter(net, mrt)) {
+		struct vif_device *v = &mrt->vif_table[0];
+		struct net_device *vif_dev;
+		struct mr_mfc *mfc;
+		int vifi;
+
+		/* Notifiy on table VIF entries */
+		rcu_read_lock();
+		for (vifi = 0; vifi < mrt->maxvif; vifi++, v++) {
+			vif_dev = rcu_dereference(v->dev);
+			if (!vif_dev)
+				continue;
+
+			err = mr_call_vif_notifier(nb, family,
+						   FIB_EVENT_VIF_ADD, v,
+						   vif_dev, vifi,
+						   mrt->id, extack);
+			if (err)
+				break;
+		}
+		rcu_read_unlock();
+
+		if (err)
+			return err;
+
+		/* Notify on table MFC entries */
+		list_for_each_entry_rcu(mfc, &mrt->mfc_cache_list, list) {
+			err = mr_call_mfc_notifier(nb, family,
+						   FIB_EVENT_ENTRY_ADD,
+						   mfc, mrt->id, extack);
+			if (err)
+				return err;
+		}
+	}
+
+	return 0;
+}
+EXPORT_SYMBOL(mr_dump);