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, 683 insertions, 0 deletions

diff --git a/net/sched/cls_route.c b/net/sched/cls_route.c
new file mode 100644
index 000000000..d0c53724d
--- /dev/null
+++ b/net/sched/cls_route.c
@@ -0,0 +1,683 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * net/sched/cls_route.c	ROUTE4 classifier.
+ *
+ * Authors:	Alexey Kuznetsov, <kuznet@ms2.inr.ac.ru>
+ */
+
+#include <linux/module.h>
+#include <linux/slab.h>
+#include <linux/types.h>
+#include <linux/kernel.h>
+#include <linux/string.h>
+#include <linux/errno.h>
+#include <linux/skbuff.h>
+#include <net/dst.h>
+#include <net/route.h>
+#include <net/netlink.h>
+#include <net/act_api.h>
+#include <net/pkt_cls.h>
+#include <net/tc_wrapper.h>
+
+/*
+ * 1. For now we assume that route tags < 256.
+ *    It allows to use direct table lookups, instead of hash tables.
+ * 2. For now we assume that "from TAG" and "fromdev DEV" statements
+ *    are mutually  exclusive.
+ * 3. "to TAG from ANY" has higher priority, than "to ANY from XXX"
+ */
+struct route4_fastmap {
+	struct route4_filter		*filter;
+	u32				id;
+	int				iif;
+};
+
+struct route4_head {
+	struct route4_fastmap		fastmap[16];
+	struct route4_bucket __rcu	*table[256 + 1];
+	struct rcu_head			rcu;
+};
+
+struct route4_bucket {
+	/* 16 FROM buckets + 16 IIF buckets + 1 wildcard bucket */
+	struct route4_filter __rcu	*ht[16 + 16 + 1];
+	struct rcu_head			rcu;
+};
+
+struct route4_filter {
+	struct route4_filter __rcu	*next;
+	u32			id;
+	int			iif;
+
+	struct tcf_result	res;
+	struct tcf_exts		exts;
+	u32			handle;
+	struct route4_bucket	*bkt;
+	struct tcf_proto	*tp;
+	struct rcu_work		rwork;
+};
+
+#define ROUTE4_FAILURE ((struct route4_filter *)(-1L))
+
+static inline int route4_fastmap_hash(u32 id, int iif)
+{
+	return id & 0xF;
+}
+
+static DEFINE_SPINLOCK(fastmap_lock);
+static void
+route4_reset_fastmap(struct route4_head *head)
+{
+	spin_lock_bh(&fastmap_lock);
+	memset(head->fastmap, 0, sizeof(head->fastmap));
+	spin_unlock_bh(&fastmap_lock);
+}
+
+static void
+route4_set_fastmap(struct route4_head *head, u32 id, int iif,
+		   struct route4_filter *f)
+{
+	int h = route4_fastmap_hash(id, iif);
+
+	/* fastmap updates must look atomic to aling id, iff, filter */
+	spin_lock_bh(&fastmap_lock);
+	head->fastmap[h].id = id;
+	head->fastmap[h].iif = iif;
+	head->fastmap[h].filter = f;
+	spin_unlock_bh(&fastmap_lock);
+}
+
+static inline int route4_hash_to(u32 id)
+{
+	return id & 0xFF;
+}
+
+static inline int route4_hash_from(u32 id)
+{
+	return (id >> 16) & 0xF;
+}
+
+static inline int route4_hash_iif(int iif)
+{
+	return 16 + ((iif >> 16) & 0xF);
+}
+
+static inline int route4_hash_wild(void)
+{
+	return 32;
+}
+
+#define ROUTE4_APPLY_RESULT()					\
+{								\
+	*res = f->res;						\
+	if (tcf_exts_has_actions(&f->exts)) {			\
+		int r = tcf_exts_exec(skb, &f->exts, res);	\
+		if (r < 0) {					\
+			dont_cache = 1;				\
+			continue;				\
+		}						\
+		return r;					\
+	} else if (!dont_cache)					\
+		route4_set_fastmap(head, id, iif, f);		\
+	return 0;						\
+}
+
+TC_INDIRECT_SCOPE int route4_classify(struct sk_buff *skb,
+				      const struct tcf_proto *tp,
+				      struct tcf_result *res)
+{
+	struct route4_head *head = rcu_dereference_bh(tp->root);
+	struct dst_entry *dst;
+	struct route4_bucket *b;
+	struct route4_filter *f;
+	u32 id, h;
+	int iif, dont_cache = 0;
+
+	dst = skb_dst(skb);
+	if (!dst)
+		goto failure;
+
+	id = dst->tclassid;
+
+	iif = inet_iif(skb);
+
+	h = route4_fastmap_hash(id, iif);
+
+	spin_lock(&fastmap_lock);
+	if (id == head->fastmap[h].id &&
+	    iif == head->fastmap[h].iif &&
+	    (f = head->fastmap[h].filter) != NULL) {
+		if (f == ROUTE4_FAILURE) {
+			spin_unlock(&fastmap_lock);
+			goto failure;
+		}
+
+		*res = f->res;
+		spin_unlock(&fastmap_lock);
+		return 0;
+	}
+	spin_unlock(&fastmap_lock);
+
+	h = route4_hash_to(id);
+
+restart:
+	b = rcu_dereference_bh(head->table[h]);
+	if (b) {
+		for (f = rcu_dereference_bh(b->ht[route4_hash_from(id)]);
+		     f;
+		     f = rcu_dereference_bh(f->next))
+			if (f->id == id)
+				ROUTE4_APPLY_RESULT();
+
+		for (f = rcu_dereference_bh(b->ht[route4_hash_iif(iif)]);
+		     f;
+		     f = rcu_dereference_bh(f->next))
+			if (f->iif == iif)
+				ROUTE4_APPLY_RESULT();
+
+		for (f = rcu_dereference_bh(b->ht[route4_hash_wild()]);
+		     f;
+		     f = rcu_dereference_bh(f->next))
+			ROUTE4_APPLY_RESULT();
+	}
+	if (h < 256) {
+		h = 256;
+		id &= ~0xFFFF;
+		goto restart;
+	}
+
+	if (!dont_cache)
+		route4_set_fastmap(head, id, iif, ROUTE4_FAILURE);
+failure:
+	return -1;
+}
+
+static inline u32 to_hash(u32 id)
+{
+	u32 h = id & 0xFF;
+
+	if (id & 0x8000)
+		h += 256;
+	return h;
+}
+
+static inline u32 from_hash(u32 id)
+{
+	id &= 0xFFFF;
+	if (id == 0xFFFF)
+		return 32;
+	if (!(id & 0x8000)) {
+		if (id > 255)
+			return 256;
+		return id & 0xF;
+	}
+	return 16 + (id & 0xF);
+}
+
+static void *route4_get(struct tcf_proto *tp, u32 handle)
+{
+	struct route4_head *head = rtnl_dereference(tp->root);
+	struct route4_bucket *b;
+	struct route4_filter *f;
+	unsigned int h1, h2;
+
+	h1 = to_hash(handle);
+	if (h1 > 256)
+		return NULL;
+
+	h2 = from_hash(handle >> 16);
+	if (h2 > 32)
+		return NULL;
+
+	b = rtnl_dereference(head->table[h1]);
+	if (b) {
+		for (f = rtnl_dereference(b->ht[h2]);
+		     f;
+		     f = rtnl_dereference(f->next))
+			if (f->handle == handle)
+				return f;
+	}
+	return NULL;
+}
+
+static int route4_init(struct tcf_proto *tp)
+{
+	struct route4_head *head;
+
+	head = kzalloc(sizeof(struct route4_head), GFP_KERNEL);
+	if (head == NULL)
+		return -ENOBUFS;
+
+	rcu_assign_pointer(tp->root, head);
+	return 0;
+}
+
+static void __route4_delete_filter(struct route4_filter *f)
+{
+	tcf_exts_destroy(&f->exts);
+	tcf_exts_put_net(&f->exts);
+	kfree(f);
+}
+
+static void route4_delete_filter_work(struct work_struct *work)
+{
+	struct route4_filter *f = container_of(to_rcu_work(work),
+					       struct route4_filter,
+					       rwork);
+	rtnl_lock();
+	__route4_delete_filter(f);
+	rtnl_unlock();
+}
+
+static void route4_queue_work(struct route4_filter *f)
+{
+	tcf_queue_work(&f->rwork, route4_delete_filter_work);
+}
+
+static void route4_destroy(struct tcf_proto *tp, bool rtnl_held,
+			   struct netlink_ext_ack *extack)
+{
+	struct route4_head *head = rtnl_dereference(tp->root);
+	int h1, h2;
+
+	if (head == NULL)
+		return;
+
+	for (h1 = 0; h1 <= 256; h1++) {
+		struct route4_bucket *b;
+
+		b = rtnl_dereference(head->table[h1]);
+		if (b) {
+			for (h2 = 0; h2 <= 32; h2++) {
+				struct route4_filter *f;
+
+				while ((f = rtnl_dereference(b->ht[h2])) != NULL) {
+					struct route4_filter *next;
+
+					next = rtnl_dereference(f->next);
+					RCU_INIT_POINTER(b->ht[h2], next);
+					tcf_unbind_filter(tp, &f->res);
+					if (tcf_exts_get_net(&f->exts))
+						route4_queue_work(f);
+					else
+						__route4_delete_filter(f);
+				}
+			}
+			RCU_INIT_POINTER(head->table[h1], NULL);
+			kfree_rcu(b, rcu);
+		}
+	}
+	kfree_rcu(head, rcu);
+}
+
+static int route4_delete(struct tcf_proto *tp, void *arg, bool *last,
+			 bool rtnl_held, struct netlink_ext_ack *extack)
+{
+	struct route4_head *head = rtnl_dereference(tp->root);
+	struct route4_filter *f = arg;
+	struct route4_filter __rcu **fp;
+	struct route4_filter *nf;
+	struct route4_bucket *b;
+	unsigned int h = 0;
+	int i, h1;
+
+	if (!head || !f)
+		return -EINVAL;
+
+	h = f->handle;
+	b = f->bkt;
+
+	fp = &b->ht[from_hash(h >> 16)];
+	for (nf = rtnl_dereference(*fp); nf;
+	     fp = &nf->next, nf = rtnl_dereference(*fp)) {
+		if (nf == f) {
+			/* unlink it */
+			RCU_INIT_POINTER(*fp, rtnl_dereference(f->next));
+
+			/* Remove any fastmap lookups that might ref filter
+			 * notice we unlink'd the filter so we can't get it
+			 * back in the fastmap.
+			 */
+			route4_reset_fastmap(head);
+
+			/* Delete it */
+			tcf_unbind_filter(tp, &f->res);
+			tcf_exts_get_net(&f->exts);
+			tcf_queue_work(&f->rwork, route4_delete_filter_work);
+
+			/* Strip RTNL protected tree */
+			for (i = 0; i <= 32; i++) {
+				struct route4_filter *rt;
+
+				rt = rtnl_dereference(b->ht[i]);
+				if (rt)
+					goto out;
+			}
+
+			/* OK, session has no flows */
+			RCU_INIT_POINTER(head->table[to_hash(h)], NULL);
+			kfree_rcu(b, rcu);
+			break;
+		}
+	}
+
+out:
+	*last = true;
+	for (h1 = 0; h1 <= 256; h1++) {
+		if (rcu_access_pointer(head->table[h1])) {
+			*last = false;
+			break;
+		}
+	}
+
+	return 0;
+}
+
+static const struct nla_policy route4_policy[TCA_ROUTE4_MAX + 1] = {
+	[TCA_ROUTE4_CLASSID]	= { .type = NLA_U32 },
+	[TCA_ROUTE4_TO]		= { .type = NLA_U32 },
+	[TCA_ROUTE4_FROM]	= { .type = NLA_U32 },
+	[TCA_ROUTE4_IIF]	= { .type = NLA_U32 },
+};
+
+static int route4_set_parms(struct net *net, struct tcf_proto *tp,
+			    unsigned long base, struct route4_filter *f,
+			    u32 handle, struct route4_head *head,
+			    struct nlattr **tb, struct nlattr *est, int new,
+			    u32 flags, struct netlink_ext_ack *extack)
+{
+	u32 id = 0, to = 0, nhandle = 0x8000;
+	struct route4_filter *fp;
+	unsigned int h1;
+	struct route4_bucket *b;
+	int err;
+
+	err = tcf_exts_validate(net, tp, tb, est, &f->exts, flags, extack);
+	if (err < 0)
+		return err;
+
+	if (tb[TCA_ROUTE4_TO]) {
+		if (new && handle & 0x8000)
+			return -EINVAL;
+		to = nla_get_u32(tb[TCA_ROUTE4_TO]);
+		if (to > 0xFF)
+			return -EINVAL;
+		nhandle = to;
+	}
+
+	if (tb[TCA_ROUTE4_FROM]) {
+		if (tb[TCA_ROUTE4_IIF])
+			return -EINVAL;
+		id = nla_get_u32(tb[TCA_ROUTE4_FROM]);
+		if (id > 0xFF)
+			return -EINVAL;
+		nhandle |= id << 16;
+	} else if (tb[TCA_ROUTE4_IIF]) {
+		id = nla_get_u32(tb[TCA_ROUTE4_IIF]);
+		if (id > 0x7FFF)
+			return -EINVAL;
+		nhandle |= (id | 0x8000) << 16;
+	} else
+		nhandle |= 0xFFFF << 16;
+
+	if (handle && new) {
+		nhandle |= handle & 0x7F00;
+		if (nhandle != handle)
+			return -EINVAL;
+	}
+
+	if (!nhandle) {
+		NL_SET_ERR_MSG(extack, "Replacing with handle of 0 is invalid");
+		return -EINVAL;
+	}
+
+	h1 = to_hash(nhandle);
+	b = rtnl_dereference(head->table[h1]);
+	if (!b) {
+		b = kzalloc(sizeof(struct route4_bucket), GFP_KERNEL);
+		if (b == NULL)
+			return -ENOBUFS;
+
+		rcu_assign_pointer(head->table[h1], b);
+	} else {
+		unsigned int h2 = from_hash(nhandle >> 16);
+
+		for (fp = rtnl_dereference(b->ht[h2]);
+		     fp;
+		     fp = rtnl_dereference(fp->next))
+			if (fp->handle == f->handle)
+				return -EEXIST;
+	}
+
+	if (tb[TCA_ROUTE4_TO])
+		f->id = to;
+
+	if (tb[TCA_ROUTE4_FROM])
+		f->id = to | id<<16;
+	else if (tb[TCA_ROUTE4_IIF])
+		f->iif = id;
+
+	f->handle = nhandle;
+	f->bkt = b;
+	f->tp = tp;
+
+	if (tb[TCA_ROUTE4_CLASSID]) {
+		f->res.classid = nla_get_u32(tb[TCA_ROUTE4_CLASSID]);
+		tcf_bind_filter(tp, &f->res, base);
+	}
+
+	return 0;
+}
+
+static int route4_change(struct net *net, struct sk_buff *in_skb,
+			 struct tcf_proto *tp, unsigned long base, u32 handle,
+			 struct nlattr **tca, void **arg, u32 flags,
+			 struct netlink_ext_ack *extack)
+{
+	struct route4_head *head = rtnl_dereference(tp->root);
+	struct route4_filter __rcu **fp;
+	struct route4_filter *fold, *f1, *pfp, *f = NULL;
+	struct route4_bucket *b;
+	struct nlattr *opt = tca[TCA_OPTIONS];
+	struct nlattr *tb[TCA_ROUTE4_MAX + 1];
+	unsigned int h, th;
+	int err;
+	bool new = true;
+
+	if (!handle) {
+		NL_SET_ERR_MSG(extack, "Creating with handle of 0 is invalid");
+		return -EINVAL;
+	}
+
+	if (opt == NULL)
+		return -EINVAL;
+
+	err = nla_parse_nested_deprecated(tb, TCA_ROUTE4_MAX, opt,
+					  route4_policy, NULL);
+	if (err < 0)
+		return err;
+
+	fold = *arg;
+	if (fold && fold->handle != handle)
+			return -EINVAL;
+
+	err = -ENOBUFS;
+	f = kzalloc(sizeof(struct route4_filter), GFP_KERNEL);
+	if (!f)
+		goto errout;
+
+	err = tcf_exts_init(&f->exts, net, TCA_ROUTE4_ACT, TCA_ROUTE4_POLICE);
+	if (err < 0)
+		goto errout;
+
+	if (fold) {
+		f->id = fold->id;
+		f->iif = fold->iif;
+		f->res = fold->res;
+		f->handle = fold->handle;
+
+		f->tp = fold->tp;
+		f->bkt = fold->bkt;
+		new = false;
+	}
+
+	err = route4_set_parms(net, tp, base, f, handle, head, tb,
+			       tca[TCA_RATE], new, flags, extack);
+	if (err < 0)
+		goto errout;
+
+	h = from_hash(f->handle >> 16);
+	fp = &f->bkt->ht[h];
+	for (pfp = rtnl_dereference(*fp);
+	     (f1 = rtnl_dereference(*fp)) != NULL;
+	     fp = &f1->next)
+		if (f->handle < f1->handle)
+			break;
+
+	tcf_block_netif_keep_dst(tp->chain->block);
+	rcu_assign_pointer(f->next, f1);
+	rcu_assign_pointer(*fp, f);
+
+	if (fold) {
+		th = to_hash(fold->handle);
+		h = from_hash(fold->handle >> 16);
+		b = rtnl_dereference(head->table[th]);
+		if (b) {
+			fp = &b->ht[h];
+			for (pfp = rtnl_dereference(*fp); pfp;
+			     fp = &pfp->next, pfp = rtnl_dereference(*fp)) {
+				if (pfp == fold) {
+					rcu_assign_pointer(*fp, fold->next);
+					break;
+				}
+			}
+		}
+	}
+
+	route4_reset_fastmap(head);
+	*arg = f;
+	if (fold) {
+		tcf_unbind_filter(tp, &fold->res);
+		tcf_exts_get_net(&fold->exts);
+		tcf_queue_work(&fold->rwork, route4_delete_filter_work);
+	}
+	return 0;
+
+errout:
+	if (f)
+		tcf_exts_destroy(&f->exts);
+	kfree(f);
+	return err;
+}
+
+static void route4_walk(struct tcf_proto *tp, struct tcf_walker *arg,
+			bool rtnl_held)
+{
+	struct route4_head *head = rtnl_dereference(tp->root);
+	unsigned int h, h1;
+
+	if (head == NULL || arg->stop)
+		return;
+
+	for (h = 0; h <= 256; h++) {
+		struct route4_bucket *b = rtnl_dereference(head->table[h]);
+
+		if (b) {
+			for (h1 = 0; h1 <= 32; h1++) {
+				struct route4_filter *f;
+
+				for (f = rtnl_dereference(b->ht[h1]);
+				     f;
+				     f = rtnl_dereference(f->next)) {
+					if (!tc_cls_stats_dump(tp, arg, f))
+						return;
+				}
+			}
+		}
+	}
+}
+
+static int route4_dump(struct net *net, struct tcf_proto *tp, void *fh,
+		       struct sk_buff *skb, struct tcmsg *t, bool rtnl_held)
+{
+	struct route4_filter *f = fh;
+	struct nlattr *nest;
+	u32 id;
+
+	if (f == NULL)
+		return skb->len;
+
+	t->tcm_handle = f->handle;
+
+	nest = nla_nest_start_noflag(skb, TCA_OPTIONS);
+	if (nest == NULL)
+		goto nla_put_failure;
+
+	if (!(f->handle & 0x8000)) {
+		id = f->id & 0xFF;
+		if (nla_put_u32(skb, TCA_ROUTE4_TO, id))
+			goto nla_put_failure;
+	}
+	if (f->handle & 0x80000000) {
+		if ((f->handle >> 16) != 0xFFFF &&
+		    nla_put_u32(skb, TCA_ROUTE4_IIF, f->iif))
+			goto nla_put_failure;
+	} else {
+		id = f->id >> 16;
+		if (nla_put_u32(skb, TCA_ROUTE4_FROM, id))
+			goto nla_put_failure;
+	}
+	if (f->res.classid &&
+	    nla_put_u32(skb, TCA_ROUTE4_CLASSID, f->res.classid))
+		goto nla_put_failure;
+
+	if (tcf_exts_dump(skb, &f->exts) < 0)
+		goto nla_put_failure;
+
+	nla_nest_end(skb, nest);
+
+	if (tcf_exts_dump_stats(skb, &f->exts) < 0)
+		goto nla_put_failure;
+
+	return skb->len;
+
+nla_put_failure:
+	nla_nest_cancel(skb, nest);
+	return -1;
+}
+
+static void route4_bind_class(void *fh, u32 classid, unsigned long cl, void *q,
+			      unsigned long base)
+{
+	struct route4_filter *f = fh;
+
+	tc_cls_bind_class(classid, cl, q, &f->res, base);
+}
+
+static struct tcf_proto_ops cls_route4_ops __read_mostly = {
+	.kind		=	"route",
+	.classify	=	route4_classify,
+	.init		=	route4_init,
+	.destroy	=	route4_destroy,
+	.get		=	route4_get,
+	.change		=	route4_change,
+	.delete		=	route4_delete,
+	.walk		=	route4_walk,
+	.dump		=	route4_dump,
+	.bind_class	=	route4_bind_class,
+	.owner		=	THIS_MODULE,
+};
+
+static int __init init_route4(void)
+{
+	return register_tcf_proto_ops(&cls_route4_ops);
+}
+
+static void __exit exit_route4(void)
+{
+	unregister_tcf_proto_ops(&cls_route4_ops);
+}
+
+module_init(init_route4)
+module_exit(exit_route4)
+MODULE_LICENSE("GPL");