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, 400 insertions, 0 deletions

diff --git a/net/sched/act_ctinfo.c b/net/sched/act_ctinfo.c
new file mode 100644
index 000000000..4d15b6a61
--- /dev/null
+++ b/net/sched/act_ctinfo.c
@@ -0,0 +1,400 @@
+// SPDX-License-Identifier: GPL-2.0+
+/* net/sched/act_ctinfo.c  netfilter ctinfo connmark actions
+ *
+ * Copyright (c) 2019 Kevin Darbyshire-Bryant <ldir@darbyshire-bryant.me.uk>
+ */
+
+#include <linux/module.h>
+#include <linux/init.h>
+#include <linux/kernel.h>
+#include <linux/skbuff.h>
+#include <linux/rtnetlink.h>
+#include <linux/pkt_cls.h>
+#include <linux/ip.h>
+#include <linux/ipv6.h>
+#include <net/netlink.h>
+#include <net/pkt_sched.h>
+#include <net/act_api.h>
+#include <net/pkt_cls.h>
+#include <uapi/linux/tc_act/tc_ctinfo.h>
+#include <net/tc_act/tc_ctinfo.h>
+#include <net/tc_wrapper.h>
+
+#include <net/netfilter/nf_conntrack.h>
+#include <net/netfilter/nf_conntrack_core.h>
+#include <net/netfilter/nf_conntrack_ecache.h>
+#include <net/netfilter/nf_conntrack_zones.h>
+
+static struct tc_action_ops act_ctinfo_ops;
+
+static void tcf_ctinfo_dscp_set(struct nf_conn *ct, struct tcf_ctinfo *ca,
+				struct tcf_ctinfo_params *cp,
+				struct sk_buff *skb, int wlen, int proto)
+{
+	u8 dscp, newdscp;
+
+	newdscp = (((READ_ONCE(ct->mark) & cp->dscpmask) >> cp->dscpmaskshift) << 2) &
+		     ~INET_ECN_MASK;
+
+	switch (proto) {
+	case NFPROTO_IPV4:
+		dscp = ipv4_get_dsfield(ip_hdr(skb)) & ~INET_ECN_MASK;
+		if (dscp != newdscp) {
+			if (likely(!skb_try_make_writable(skb, wlen))) {
+				ipv4_change_dsfield(ip_hdr(skb),
+						    INET_ECN_MASK,
+						    newdscp);
+				ca->stats_dscp_set++;
+			} else {
+				ca->stats_dscp_error++;
+			}
+		}
+		break;
+	case NFPROTO_IPV6:
+		dscp = ipv6_get_dsfield(ipv6_hdr(skb)) & ~INET_ECN_MASK;
+		if (dscp != newdscp) {
+			if (likely(!skb_try_make_writable(skb, wlen))) {
+				ipv6_change_dsfield(ipv6_hdr(skb),
+						    INET_ECN_MASK,
+						    newdscp);
+				ca->stats_dscp_set++;
+			} else {
+				ca->stats_dscp_error++;
+			}
+		}
+		break;
+	default:
+		break;
+	}
+}
+
+static void tcf_ctinfo_cpmark_set(struct nf_conn *ct, struct tcf_ctinfo *ca,
+				  struct tcf_ctinfo_params *cp,
+				  struct sk_buff *skb)
+{
+	ca->stats_cpmark_set++;
+	skb->mark = READ_ONCE(ct->mark) & cp->cpmarkmask;
+}
+
+TC_INDIRECT_SCOPE int tcf_ctinfo_act(struct sk_buff *skb,
+				     const struct tc_action *a,
+				     struct tcf_result *res)
+{
+	const struct nf_conntrack_tuple_hash *thash = NULL;
+	struct tcf_ctinfo *ca = to_ctinfo(a);
+	struct nf_conntrack_tuple tuple;
+	struct nf_conntrack_zone zone;
+	enum ip_conntrack_info ctinfo;
+	struct tcf_ctinfo_params *cp;
+	struct nf_conn *ct;
+	int proto, wlen;
+	int action;
+
+	cp = rcu_dereference_bh(ca->params);
+
+	tcf_lastuse_update(&ca->tcf_tm);
+	tcf_action_update_bstats(&ca->common, skb);
+	action = READ_ONCE(ca->tcf_action);
+
+	wlen = skb_network_offset(skb);
+	switch (skb_protocol(skb, true)) {
+	case htons(ETH_P_IP):
+		wlen += sizeof(struct iphdr);
+		if (!pskb_may_pull(skb, wlen))
+			goto out;
+
+		proto = NFPROTO_IPV4;
+		break;
+	case htons(ETH_P_IPV6):
+		wlen += sizeof(struct ipv6hdr);
+		if (!pskb_may_pull(skb, wlen))
+			goto out;
+
+		proto = NFPROTO_IPV6;
+		break;
+	default:
+		goto out;
+	}
+
+	ct = nf_ct_get(skb, &ctinfo);
+	if (!ct) { /* look harder, usually ingress */
+		if (!nf_ct_get_tuplepr(skb, skb_network_offset(skb),
+				       proto, cp->net, &tuple))
+			goto out;
+		zone.id = cp->zone;
+		zone.dir = NF_CT_DEFAULT_ZONE_DIR;
+
+		thash = nf_conntrack_find_get(cp->net, &zone, &tuple);
+		if (!thash)
+			goto out;
+
+		ct = nf_ct_tuplehash_to_ctrack(thash);
+	}
+
+	if (cp->mode & CTINFO_MODE_DSCP)
+		if (!cp->dscpstatemask || (READ_ONCE(ct->mark) & cp->dscpstatemask))
+			tcf_ctinfo_dscp_set(ct, ca, cp, skb, wlen, proto);
+
+	if (cp->mode & CTINFO_MODE_CPMARK)
+		tcf_ctinfo_cpmark_set(ct, ca, cp, skb);
+
+	if (thash)
+		nf_ct_put(ct);
+out:
+	return action;
+}
+
+static const struct nla_policy ctinfo_policy[TCA_CTINFO_MAX + 1] = {
+	[TCA_CTINFO_ACT]		  =
+		NLA_POLICY_EXACT_LEN(sizeof(struct tc_ctinfo)),
+	[TCA_CTINFO_ZONE]		  = { .type = NLA_U16 },
+	[TCA_CTINFO_PARMS_DSCP_MASK]	  = { .type = NLA_U32 },
+	[TCA_CTINFO_PARMS_DSCP_STATEMASK] = { .type = NLA_U32 },
+	[TCA_CTINFO_PARMS_CPMARK_MASK]	  = { .type = NLA_U32 },
+};
+
+static int tcf_ctinfo_init(struct net *net, struct nlattr *nla,
+			   struct nlattr *est, struct tc_action **a,
+			   struct tcf_proto *tp, u32 flags,
+			   struct netlink_ext_ack *extack)
+{
+	struct tc_action_net *tn = net_generic(net, act_ctinfo_ops.net_id);
+	bool bind = flags & TCA_ACT_FLAGS_BIND;
+	u32 dscpmask = 0, dscpstatemask, index;
+	struct nlattr *tb[TCA_CTINFO_MAX + 1];
+	struct tcf_ctinfo_params *cp_new;
+	struct tcf_chain *goto_ch = NULL;
+	struct tc_ctinfo *actparm;
+	struct tcf_ctinfo *ci;
+	u8 dscpmaskshift;
+	int ret = 0, err;
+
+	if (!nla) {
+		NL_SET_ERR_MSG_MOD(extack, "ctinfo requires attributes to be passed");
+		return -EINVAL;
+	}
+
+	err = nla_parse_nested(tb, TCA_CTINFO_MAX, nla, ctinfo_policy, extack);
+	if (err < 0)
+		return err;
+
+	if (!tb[TCA_CTINFO_ACT]) {
+		NL_SET_ERR_MSG_MOD(extack,
+				   "Missing required TCA_CTINFO_ACT attribute");
+		return -EINVAL;
+	}
+	actparm = nla_data(tb[TCA_CTINFO_ACT]);
+
+	/* do some basic validation here before dynamically allocating things */
+	/* that we would otherwise have to clean up.			      */
+	if (tb[TCA_CTINFO_PARMS_DSCP_MASK]) {
+		dscpmask = nla_get_u32(tb[TCA_CTINFO_PARMS_DSCP_MASK]);
+		/* need contiguous 6 bit mask */
+		dscpmaskshift = dscpmask ? __ffs(dscpmask) : 0;
+		if ((~0 & (dscpmask >> dscpmaskshift)) != 0x3f) {
+			NL_SET_ERR_MSG_ATTR(extack,
+					    tb[TCA_CTINFO_PARMS_DSCP_MASK],
+					    "dscp mask must be 6 contiguous bits");
+			return -EINVAL;
+		}
+		dscpstatemask = tb[TCA_CTINFO_PARMS_DSCP_STATEMASK] ?
+			nla_get_u32(tb[TCA_CTINFO_PARMS_DSCP_STATEMASK]) : 0;
+		/* mask & statemask must not overlap */
+		if (dscpmask & dscpstatemask) {
+			NL_SET_ERR_MSG_ATTR(extack,
+					    tb[TCA_CTINFO_PARMS_DSCP_STATEMASK],
+					    "dscp statemask must not overlap dscp mask");
+			return -EINVAL;
+		}
+	}
+
+	/* done the validation:now to the actual action allocation */
+	index = actparm->index;
+	err = tcf_idr_check_alloc(tn, &index, a, bind);
+	if (!err) {
+		ret = tcf_idr_create_from_flags(tn, index, est, a,
+						&act_ctinfo_ops, bind, flags);
+		if (ret) {
+			tcf_idr_cleanup(tn, index);
+			return ret;
+		}
+		ret = ACT_P_CREATED;
+	} else if (err > 0) {
+		if (bind) /* don't override defaults */
+			return 0;
+		if (!(flags & TCA_ACT_FLAGS_REPLACE)) {
+			tcf_idr_release(*a, bind);
+			return -EEXIST;
+		}
+	} else {
+		return err;
+	}
+
+	err = tcf_action_check_ctrlact(actparm->action, tp, &goto_ch, extack);
+	if (err < 0)
+		goto release_idr;
+
+	ci = to_ctinfo(*a);
+
+	cp_new = kzalloc(sizeof(*cp_new), GFP_KERNEL);
+	if (unlikely(!cp_new)) {
+		err = -ENOMEM;
+		goto put_chain;
+	}
+
+	cp_new->net = net;
+	cp_new->zone = tb[TCA_CTINFO_ZONE] ?
+			nla_get_u16(tb[TCA_CTINFO_ZONE]) : 0;
+	if (dscpmask) {
+		cp_new->dscpmask = dscpmask;
+		cp_new->dscpmaskshift = dscpmaskshift;
+		cp_new->dscpstatemask = dscpstatemask;
+		cp_new->mode |= CTINFO_MODE_DSCP;
+	}
+
+	if (tb[TCA_CTINFO_PARMS_CPMARK_MASK]) {
+		cp_new->cpmarkmask =
+				nla_get_u32(tb[TCA_CTINFO_PARMS_CPMARK_MASK]);
+		cp_new->mode |= CTINFO_MODE_CPMARK;
+	}
+
+	spin_lock_bh(&ci->tcf_lock);
+	goto_ch = tcf_action_set_ctrlact(*a, actparm->action, goto_ch);
+	cp_new = rcu_replace_pointer(ci->params, cp_new,
+				     lockdep_is_held(&ci->tcf_lock));
+	spin_unlock_bh(&ci->tcf_lock);
+
+	if (goto_ch)
+		tcf_chain_put_by_act(goto_ch);
+	if (cp_new)
+		kfree_rcu(cp_new, rcu);
+
+	return ret;
+
+put_chain:
+	if (goto_ch)
+		tcf_chain_put_by_act(goto_ch);
+release_idr:
+	tcf_idr_release(*a, bind);
+	return err;
+}
+
+static int tcf_ctinfo_dump(struct sk_buff *skb, struct tc_action *a,
+			   int bind, int ref)
+{
+	struct tcf_ctinfo *ci = to_ctinfo(a);
+	struct tc_ctinfo opt = {
+		.index   = ci->tcf_index,
+		.refcnt  = refcount_read(&ci->tcf_refcnt) - ref,
+		.bindcnt = atomic_read(&ci->tcf_bindcnt) - bind,
+	};
+	unsigned char *b = skb_tail_pointer(skb);
+	struct tcf_ctinfo_params *cp;
+	struct tcf_t t;
+
+	spin_lock_bh(&ci->tcf_lock);
+	cp = rcu_dereference_protected(ci->params,
+				       lockdep_is_held(&ci->tcf_lock));
+
+	tcf_tm_dump(&t, &ci->tcf_tm);
+	if (nla_put_64bit(skb, TCA_CTINFO_TM, sizeof(t), &t, TCA_CTINFO_PAD))
+		goto nla_put_failure;
+
+	opt.action = ci->tcf_action;
+	if (nla_put(skb, TCA_CTINFO_ACT, sizeof(opt), &opt))
+		goto nla_put_failure;
+
+	if (nla_put_u16(skb, TCA_CTINFO_ZONE, cp->zone))
+		goto nla_put_failure;
+
+	if (cp->mode & CTINFO_MODE_DSCP) {
+		if (nla_put_u32(skb, TCA_CTINFO_PARMS_DSCP_MASK,
+				cp->dscpmask))
+			goto nla_put_failure;
+		if (nla_put_u32(skb, TCA_CTINFO_PARMS_DSCP_STATEMASK,
+				cp->dscpstatemask))
+			goto nla_put_failure;
+	}
+
+	if (cp->mode & CTINFO_MODE_CPMARK) {
+		if (nla_put_u32(skb, TCA_CTINFO_PARMS_CPMARK_MASK,
+				cp->cpmarkmask))
+			goto nla_put_failure;
+	}
+
+	if (nla_put_u64_64bit(skb, TCA_CTINFO_STATS_DSCP_SET,
+			      ci->stats_dscp_set, TCA_CTINFO_PAD))
+		goto nla_put_failure;
+
+	if (nla_put_u64_64bit(skb, TCA_CTINFO_STATS_DSCP_ERROR,
+			      ci->stats_dscp_error, TCA_CTINFO_PAD))
+		goto nla_put_failure;
+
+	if (nla_put_u64_64bit(skb, TCA_CTINFO_STATS_CPMARK_SET,
+			      ci->stats_cpmark_set, TCA_CTINFO_PAD))
+		goto nla_put_failure;
+
+	spin_unlock_bh(&ci->tcf_lock);
+	return skb->len;
+
+nla_put_failure:
+	spin_unlock_bh(&ci->tcf_lock);
+	nlmsg_trim(skb, b);
+	return -1;
+}
+
+static void tcf_ctinfo_cleanup(struct tc_action *a)
+{
+	struct tcf_ctinfo *ci = to_ctinfo(a);
+	struct tcf_ctinfo_params *cp;
+
+	cp = rcu_dereference_protected(ci->params, 1);
+	if (cp)
+		kfree_rcu(cp, rcu);
+}
+
+static struct tc_action_ops act_ctinfo_ops = {
+	.kind	= "ctinfo",
+	.id	= TCA_ID_CTINFO,
+	.owner	= THIS_MODULE,
+	.act	= tcf_ctinfo_act,
+	.dump	= tcf_ctinfo_dump,
+	.init	= tcf_ctinfo_init,
+	.cleanup= tcf_ctinfo_cleanup,
+	.size	= sizeof(struct tcf_ctinfo),
+};
+
+static __net_init int ctinfo_init_net(struct net *net)
+{
+	struct tc_action_net *tn = net_generic(net, act_ctinfo_ops.net_id);
+
+	return tc_action_net_init(net, tn, &act_ctinfo_ops);
+}
+
+static void __net_exit ctinfo_exit_net(struct list_head *net_list)
+{
+	tc_action_net_exit(net_list, act_ctinfo_ops.net_id);
+}
+
+static struct pernet_operations ctinfo_net_ops = {
+	.init		= ctinfo_init_net,
+	.exit_batch	= ctinfo_exit_net,
+	.id		= &act_ctinfo_ops.net_id,
+	.size		= sizeof(struct tc_action_net),
+};
+
+static int __init ctinfo_init_module(void)
+{
+	return tcf_register_action(&act_ctinfo_ops, &ctinfo_net_ops);
+}
+
+static void __exit ctinfo_cleanup_module(void)
+{
+	tcf_unregister_action(&act_ctinfo_ops, &ctinfo_net_ops);
+}
+
+module_init(ctinfo_init_module);
+module_exit(ctinfo_cleanup_module);
+MODULE_AUTHOR("Kevin Darbyshire-Bryant <ldir@darbyshire-bryant.me.uk>");
+MODULE_DESCRIPTION("Connection tracking mark actions");
+MODULE_LICENSE("GPL");