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, 439 insertions, 0 deletions

diff --git a/net/sched/act_bpf.c b/net/sched/act_bpf.c
new file mode 100644
index 000000000..b0455fda7
--- /dev/null
+++ b/net/sched/act_bpf.c
@@ -0,0 +1,439 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * Copyright (c) 2015 Jiri Pirko <jiri@resnulli.us>
+ */
+
+#include <linux/module.h>
+#include <linux/init.h>
+#include <linux/kernel.h>
+#include <linux/skbuff.h>
+#include <linux/rtnetlink.h>
+#include <linux/filter.h>
+#include <linux/bpf.h>
+
+#include <net/netlink.h>
+#include <net/sock.h>
+#include <net/pkt_sched.h>
+#include <net/pkt_cls.h>
+
+#include <linux/tc_act/tc_bpf.h>
+#include <net/tc_act/tc_bpf.h>
+#include <net/tc_wrapper.h>
+
+#define ACT_BPF_NAME_LEN	256
+
+struct tcf_bpf_cfg {
+	struct bpf_prog *filter;
+	struct sock_filter *bpf_ops;
+	const char *bpf_name;
+	u16 bpf_num_ops;
+	bool is_ebpf;
+};
+
+static struct tc_action_ops act_bpf_ops;
+
+TC_INDIRECT_SCOPE int tcf_bpf_act(struct sk_buff *skb,
+				  const struct tc_action *act,
+				  struct tcf_result *res)
+{
+	bool at_ingress = skb_at_tc_ingress(skb);
+	struct tcf_bpf *prog = to_bpf(act);
+	struct bpf_prog *filter;
+	int action, filter_res;
+
+	tcf_lastuse_update(&prog->tcf_tm);
+	bstats_update(this_cpu_ptr(prog->common.cpu_bstats), skb);
+
+	filter = rcu_dereference(prog->filter);
+	if (at_ingress) {
+		__skb_push(skb, skb->mac_len);
+		bpf_compute_data_pointers(skb);
+		filter_res = bpf_prog_run(filter, skb);
+		__skb_pull(skb, skb->mac_len);
+	} else {
+		bpf_compute_data_pointers(skb);
+		filter_res = bpf_prog_run(filter, skb);
+	}
+	if (unlikely(!skb->tstamp && skb->mono_delivery_time))
+		skb->mono_delivery_time = 0;
+	if (skb_sk_is_prefetched(skb) && filter_res != TC_ACT_OK)
+		skb_orphan(skb);
+
+	/* A BPF program may overwrite the default action opcode.
+	 * Similarly as in cls_bpf, if filter_res == -1 we use the
+	 * default action specified from tc.
+	 *
+	 * In case a different well-known TC_ACT opcode has been
+	 * returned, it will overwrite the default one.
+	 *
+	 * For everything else that is unknown, TC_ACT_UNSPEC is
+	 * returned.
+	 */
+	switch (filter_res) {
+	case TC_ACT_PIPE:
+	case TC_ACT_RECLASSIFY:
+	case TC_ACT_OK:
+	case TC_ACT_REDIRECT:
+		action = filter_res;
+		break;
+	case TC_ACT_SHOT:
+		action = filter_res;
+		qstats_drop_inc(this_cpu_ptr(prog->common.cpu_qstats));
+		break;
+	case TC_ACT_UNSPEC:
+		action = prog->tcf_action;
+		break;
+	default:
+		action = TC_ACT_UNSPEC;
+		break;
+	}
+
+	return action;
+}
+
+static bool tcf_bpf_is_ebpf(const struct tcf_bpf *prog)
+{
+	return !prog->bpf_ops;
+}
+
+static int tcf_bpf_dump_bpf_info(const struct tcf_bpf *prog,
+				 struct sk_buff *skb)
+{
+	struct nlattr *nla;
+
+	if (nla_put_u16(skb, TCA_ACT_BPF_OPS_LEN, prog->bpf_num_ops))
+		return -EMSGSIZE;
+
+	nla = nla_reserve(skb, TCA_ACT_BPF_OPS, prog->bpf_num_ops *
+			  sizeof(struct sock_filter));
+	if (nla == NULL)
+		return -EMSGSIZE;
+
+	memcpy(nla_data(nla), prog->bpf_ops, nla_len(nla));
+
+	return 0;
+}
+
+static int tcf_bpf_dump_ebpf_info(const struct tcf_bpf *prog,
+				  struct sk_buff *skb)
+{
+	struct nlattr *nla;
+
+	if (prog->bpf_name &&
+	    nla_put_string(skb, TCA_ACT_BPF_NAME, prog->bpf_name))
+		return -EMSGSIZE;
+
+	if (nla_put_u32(skb, TCA_ACT_BPF_ID, prog->filter->aux->id))
+		return -EMSGSIZE;
+
+	nla = nla_reserve(skb, TCA_ACT_BPF_TAG, sizeof(prog->filter->tag));
+	if (nla == NULL)
+		return -EMSGSIZE;
+
+	memcpy(nla_data(nla), prog->filter->tag, nla_len(nla));
+
+	return 0;
+}
+
+static int tcf_bpf_dump(struct sk_buff *skb, struct tc_action *act,
+			int bind, int ref)
+{
+	unsigned char *tp = skb_tail_pointer(skb);
+	struct tcf_bpf *prog = to_bpf(act);
+	struct tc_act_bpf opt = {
+		.index   = prog->tcf_index,
+		.refcnt  = refcount_read(&prog->tcf_refcnt) - ref,
+		.bindcnt = atomic_read(&prog->tcf_bindcnt) - bind,
+	};
+	struct tcf_t tm;
+	int ret;
+
+	spin_lock_bh(&prog->tcf_lock);
+	opt.action = prog->tcf_action;
+	if (nla_put(skb, TCA_ACT_BPF_PARMS, sizeof(opt), &opt))
+		goto nla_put_failure;
+
+	if (tcf_bpf_is_ebpf(prog))
+		ret = tcf_bpf_dump_ebpf_info(prog, skb);
+	else
+		ret = tcf_bpf_dump_bpf_info(prog, skb);
+	if (ret)
+		goto nla_put_failure;
+
+	tcf_tm_dump(&tm, &prog->tcf_tm);
+	if (nla_put_64bit(skb, TCA_ACT_BPF_TM, sizeof(tm), &tm,
+			  TCA_ACT_BPF_PAD))
+		goto nla_put_failure;
+
+	spin_unlock_bh(&prog->tcf_lock);
+	return skb->len;
+
+nla_put_failure:
+	spin_unlock_bh(&prog->tcf_lock);
+	nlmsg_trim(skb, tp);
+	return -1;
+}
+
+static const struct nla_policy act_bpf_policy[TCA_ACT_BPF_MAX + 1] = {
+	[TCA_ACT_BPF_PARMS]	= { .len = sizeof(struct tc_act_bpf) },
+	[TCA_ACT_BPF_FD]	= { .type = NLA_U32 },
+	[TCA_ACT_BPF_NAME]	= { .type = NLA_NUL_STRING,
+				    .len = ACT_BPF_NAME_LEN },
+	[TCA_ACT_BPF_OPS_LEN]	= { .type = NLA_U16 },
+	[TCA_ACT_BPF_OPS]	= { .type = NLA_BINARY,
+				    .len = sizeof(struct sock_filter) * BPF_MAXINSNS },
+};
+
+static int tcf_bpf_init_from_ops(struct nlattr **tb, struct tcf_bpf_cfg *cfg)
+{
+	struct sock_filter *bpf_ops;
+	struct sock_fprog_kern fprog_tmp;
+	struct bpf_prog *fp;
+	u16 bpf_size, bpf_num_ops;
+	int ret;
+
+	bpf_num_ops = nla_get_u16(tb[TCA_ACT_BPF_OPS_LEN]);
+	if (bpf_num_ops	> BPF_MAXINSNS || bpf_num_ops == 0)
+		return -EINVAL;
+
+	bpf_size = bpf_num_ops * sizeof(*bpf_ops);
+	if (bpf_size != nla_len(tb[TCA_ACT_BPF_OPS]))
+		return -EINVAL;
+
+	bpf_ops = kmemdup(nla_data(tb[TCA_ACT_BPF_OPS]), bpf_size, GFP_KERNEL);
+	if (bpf_ops == NULL)
+		return -ENOMEM;
+
+	fprog_tmp.len = bpf_num_ops;
+	fprog_tmp.filter = bpf_ops;
+
+	ret = bpf_prog_create(&fp, &fprog_tmp);
+	if (ret < 0) {
+		kfree(bpf_ops);
+		return ret;
+	}
+
+	cfg->bpf_ops = bpf_ops;
+	cfg->bpf_num_ops = bpf_num_ops;
+	cfg->filter = fp;
+	cfg->is_ebpf = false;
+
+	return 0;
+}
+
+static int tcf_bpf_init_from_efd(struct nlattr **tb, struct tcf_bpf_cfg *cfg)
+{
+	struct bpf_prog *fp;
+	char *name = NULL;
+	u32 bpf_fd;
+
+	bpf_fd = nla_get_u32(tb[TCA_ACT_BPF_FD]);
+
+	fp = bpf_prog_get_type(bpf_fd, BPF_PROG_TYPE_SCHED_ACT);
+	if (IS_ERR(fp))
+		return PTR_ERR(fp);
+
+	if (tb[TCA_ACT_BPF_NAME]) {
+		name = nla_memdup(tb[TCA_ACT_BPF_NAME], GFP_KERNEL);
+		if (!name) {
+			bpf_prog_put(fp);
+			return -ENOMEM;
+		}
+	}
+
+	cfg->bpf_name = name;
+	cfg->filter = fp;
+	cfg->is_ebpf = true;
+
+	return 0;
+}
+
+static void tcf_bpf_cfg_cleanup(const struct tcf_bpf_cfg *cfg)
+{
+	struct bpf_prog *filter = cfg->filter;
+
+	if (filter) {
+		if (cfg->is_ebpf)
+			bpf_prog_put(filter);
+		else
+			bpf_prog_destroy(filter);
+	}
+
+	kfree(cfg->bpf_ops);
+	kfree(cfg->bpf_name);
+}
+
+static void tcf_bpf_prog_fill_cfg(const struct tcf_bpf *prog,
+				  struct tcf_bpf_cfg *cfg)
+{
+	cfg->is_ebpf = tcf_bpf_is_ebpf(prog);
+	/* updates to prog->filter are prevented, since it's called either
+	 * with tcf lock or during final cleanup in rcu callback
+	 */
+	cfg->filter = rcu_dereference_protected(prog->filter, 1);
+
+	cfg->bpf_ops = prog->bpf_ops;
+	cfg->bpf_name = prog->bpf_name;
+}
+
+static int tcf_bpf_init(struct net *net, struct nlattr *nla,
+			struct nlattr *est, struct tc_action **act,
+			struct tcf_proto *tp, u32 flags,
+			struct netlink_ext_ack *extack)
+{
+	struct tc_action_net *tn = net_generic(net, act_bpf_ops.net_id);
+	bool bind = flags & TCA_ACT_FLAGS_BIND;
+	struct nlattr *tb[TCA_ACT_BPF_MAX + 1];
+	struct tcf_chain *goto_ch = NULL;
+	struct tcf_bpf_cfg cfg, old;
+	struct tc_act_bpf *parm;
+	struct tcf_bpf *prog;
+	bool is_bpf, is_ebpf;
+	int ret, res = 0;
+	u32 index;
+
+	if (!nla)
+		return -EINVAL;
+
+	ret = nla_parse_nested_deprecated(tb, TCA_ACT_BPF_MAX, nla,
+					  act_bpf_policy, NULL);
+	if (ret < 0)
+		return ret;
+
+	if (!tb[TCA_ACT_BPF_PARMS])
+		return -EINVAL;
+
+	parm = nla_data(tb[TCA_ACT_BPF_PARMS]);
+	index = parm->index;
+	ret = tcf_idr_check_alloc(tn, &index, act, bind);
+	if (!ret) {
+		ret = tcf_idr_create(tn, index, est, act,
+				     &act_bpf_ops, bind, true, flags);
+		if (ret < 0) {
+			tcf_idr_cleanup(tn, index);
+			return ret;
+		}
+
+		res = ACT_P_CREATED;
+	} else if (ret > 0) {
+		/* Don't override defaults. */
+		if (bind)
+			return 0;
+
+		if (!(flags & TCA_ACT_FLAGS_REPLACE)) {
+			tcf_idr_release(*act, bind);
+			return -EEXIST;
+		}
+	} else {
+		return ret;
+	}
+
+	ret = tcf_action_check_ctrlact(parm->action, tp, &goto_ch, extack);
+	if (ret < 0)
+		goto release_idr;
+
+	is_bpf = tb[TCA_ACT_BPF_OPS_LEN] && tb[TCA_ACT_BPF_OPS];
+	is_ebpf = tb[TCA_ACT_BPF_FD];
+
+	if (is_bpf == is_ebpf) {
+		ret = -EINVAL;
+		goto put_chain;
+	}
+
+	memset(&cfg, 0, sizeof(cfg));
+
+	ret = is_bpf ? tcf_bpf_init_from_ops(tb, &cfg) :
+		       tcf_bpf_init_from_efd(tb, &cfg);
+	if (ret < 0)
+		goto put_chain;
+
+	prog = to_bpf(*act);
+
+	spin_lock_bh(&prog->tcf_lock);
+	if (res != ACT_P_CREATED)
+		tcf_bpf_prog_fill_cfg(prog, &old);
+
+	prog->bpf_ops = cfg.bpf_ops;
+	prog->bpf_name = cfg.bpf_name;
+
+	if (cfg.bpf_num_ops)
+		prog->bpf_num_ops = cfg.bpf_num_ops;
+
+	goto_ch = tcf_action_set_ctrlact(*act, parm->action, goto_ch);
+	rcu_assign_pointer(prog->filter, cfg.filter);
+	spin_unlock_bh(&prog->tcf_lock);
+
+	if (goto_ch)
+		tcf_chain_put_by_act(goto_ch);
+
+	if (res != ACT_P_CREATED) {
+		/* make sure the program being replaced is no longer executing */
+		synchronize_rcu();
+		tcf_bpf_cfg_cleanup(&old);
+	}
+
+	return res;
+
+put_chain:
+	if (goto_ch)
+		tcf_chain_put_by_act(goto_ch);
+
+release_idr:
+	tcf_idr_release(*act, bind);
+	return ret;
+}
+
+static void tcf_bpf_cleanup(struct tc_action *act)
+{
+	struct tcf_bpf_cfg tmp;
+
+	tcf_bpf_prog_fill_cfg(to_bpf(act), &tmp);
+	tcf_bpf_cfg_cleanup(&tmp);
+}
+
+static struct tc_action_ops act_bpf_ops __read_mostly = {
+	.kind		=	"bpf",
+	.id		=	TCA_ID_BPF,
+	.owner		=	THIS_MODULE,
+	.act		=	tcf_bpf_act,
+	.dump		=	tcf_bpf_dump,
+	.cleanup	=	tcf_bpf_cleanup,
+	.init		=	tcf_bpf_init,
+	.size		=	sizeof(struct tcf_bpf),
+};
+
+static __net_init int bpf_init_net(struct net *net)
+{
+	struct tc_action_net *tn = net_generic(net, act_bpf_ops.net_id);
+
+	return tc_action_net_init(net, tn, &act_bpf_ops);
+}
+
+static void __net_exit bpf_exit_net(struct list_head *net_list)
+{
+	tc_action_net_exit(net_list, act_bpf_ops.net_id);
+}
+
+static struct pernet_operations bpf_net_ops = {
+	.init = bpf_init_net,
+	.exit_batch = bpf_exit_net,
+	.id   = &act_bpf_ops.net_id,
+	.size = sizeof(struct tc_action_net),
+};
+
+static int __init bpf_init_module(void)
+{
+	return tcf_register_action(&act_bpf_ops, &bpf_net_ops);
+}
+
+static void __exit bpf_cleanup_module(void)
+{
+	tcf_unregister_action(&act_bpf_ops, &bpf_net_ops);
+}
+
+module_init(bpf_init_module);
+module_exit(bpf_cleanup_module);
+
+MODULE_AUTHOR("Jiri Pirko <jiri@resnulli.us>");
+MODULE_DESCRIPTION("TC BPF based action");
+MODULE_LICENSE("GPL v2");