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, 483 insertions, 0 deletions

diff --git a/net/sched/act_mpls.c b/net/sched/act_mpls.c
new file mode 100644
index 000000000..6b26bdb99
--- /dev/null
+++ b/net/sched/act_mpls.c
@@ -0,0 +1,483 @@
+// SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause)
+/* Copyright (C) 2019 Netronome Systems, Inc. */
+
+#include <linux/if_arp.h>
+#include <linux/init.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/mpls.h>
+#include <linux/rtnetlink.h>
+#include <linux/skbuff.h>
+#include <linux/tc_act/tc_mpls.h>
+#include <net/mpls.h>
+#include <net/netlink.h>
+#include <net/pkt_sched.h>
+#include <net/pkt_cls.h>
+#include <net/tc_act/tc_mpls.h>
+#include <net/tc_wrapper.h>
+
+static struct tc_action_ops act_mpls_ops;
+
+#define ACT_MPLS_TTL_DEFAULT	255
+
+static __be32 tcf_mpls_get_lse(struct mpls_shim_hdr *lse,
+			       struct tcf_mpls_params *p, bool set_bos)
+{
+	u32 new_lse = 0;
+
+	if (lse)
+		new_lse = be32_to_cpu(lse->label_stack_entry);
+
+	if (p->tcfm_label != ACT_MPLS_LABEL_NOT_SET) {
+		new_lse &= ~MPLS_LS_LABEL_MASK;
+		new_lse |= p->tcfm_label << MPLS_LS_LABEL_SHIFT;
+	}
+	if (p->tcfm_ttl) {
+		new_lse &= ~MPLS_LS_TTL_MASK;
+		new_lse |= p->tcfm_ttl << MPLS_LS_TTL_SHIFT;
+	}
+	if (p->tcfm_tc != ACT_MPLS_TC_NOT_SET) {
+		new_lse &= ~MPLS_LS_TC_MASK;
+		new_lse |= p->tcfm_tc << MPLS_LS_TC_SHIFT;
+	}
+	if (p->tcfm_bos != ACT_MPLS_BOS_NOT_SET) {
+		new_lse &= ~MPLS_LS_S_MASK;
+		new_lse |= p->tcfm_bos << MPLS_LS_S_SHIFT;
+	} else if (set_bos) {
+		new_lse |= 1 << MPLS_LS_S_SHIFT;
+	}
+
+	return cpu_to_be32(new_lse);
+}
+
+TC_INDIRECT_SCOPE int tcf_mpls_act(struct sk_buff *skb,
+				   const struct tc_action *a,
+				   struct tcf_result *res)
+{
+	struct tcf_mpls *m = to_mpls(a);
+	struct tcf_mpls_params *p;
+	__be32 new_lse;
+	int ret, mac_len;
+
+	tcf_lastuse_update(&m->tcf_tm);
+	bstats_update(this_cpu_ptr(m->common.cpu_bstats), skb);
+
+	/* Ensure 'data' points at mac_header prior calling mpls manipulating
+	 * functions.
+	 */
+	if (skb_at_tc_ingress(skb)) {
+		skb_push_rcsum(skb, skb->mac_len);
+		mac_len = skb->mac_len;
+	} else {
+		mac_len = skb_network_header(skb) - skb_mac_header(skb);
+	}
+
+	ret = READ_ONCE(m->tcf_action);
+
+	p = rcu_dereference_bh(m->mpls_p);
+
+	switch (p->tcfm_action) {
+	case TCA_MPLS_ACT_POP:
+		if (skb_mpls_pop(skb, p->tcfm_proto, mac_len,
+				 skb->dev && skb->dev->type == ARPHRD_ETHER))
+			goto drop;
+		break;
+	case TCA_MPLS_ACT_PUSH:
+		new_lse = tcf_mpls_get_lse(NULL, p, !eth_p_mpls(skb_protocol(skb, true)));
+		if (skb_mpls_push(skb, new_lse, p->tcfm_proto, mac_len,
+				  skb->dev && skb->dev->type == ARPHRD_ETHER))
+			goto drop;
+		break;
+	case TCA_MPLS_ACT_MAC_PUSH:
+		if (skb_vlan_tag_present(skb)) {
+			if (__vlan_insert_inner_tag(skb, skb->vlan_proto,
+						    skb_vlan_tag_get(skb),
+						    ETH_HLEN) < 0)
+				goto drop;
+
+			skb->protocol = skb->vlan_proto;
+			__vlan_hwaccel_clear_tag(skb);
+		}
+
+		new_lse = tcf_mpls_get_lse(NULL, p, mac_len ||
+					   !eth_p_mpls(skb->protocol));
+
+		if (skb_mpls_push(skb, new_lse, p->tcfm_proto, 0, false))
+			goto drop;
+		break;
+	case TCA_MPLS_ACT_MODIFY:
+		if (!pskb_may_pull(skb,
+				   skb_network_offset(skb) + MPLS_HLEN))
+			goto drop;
+		new_lse = tcf_mpls_get_lse(mpls_hdr(skb), p, false);
+		if (skb_mpls_update_lse(skb, new_lse))
+			goto drop;
+		break;
+	case TCA_MPLS_ACT_DEC_TTL:
+		if (skb_mpls_dec_ttl(skb))
+			goto drop;
+		break;
+	}
+
+	if (skb_at_tc_ingress(skb))
+		skb_pull_rcsum(skb, skb->mac_len);
+
+	return ret;
+
+drop:
+	qstats_drop_inc(this_cpu_ptr(m->common.cpu_qstats));
+	return TC_ACT_SHOT;
+}
+
+static int valid_label(const struct nlattr *attr,
+		       struct netlink_ext_ack *extack)
+{
+	const u32 *label = nla_data(attr);
+
+	if (nla_len(attr) != sizeof(*label)) {
+		NL_SET_ERR_MSG_MOD(extack, "Invalid MPLS label length");
+		return -EINVAL;
+	}
+
+	if (*label & ~MPLS_LABEL_MASK || *label == MPLS_LABEL_IMPLNULL) {
+		NL_SET_ERR_MSG_MOD(extack, "MPLS label out of range");
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+static const struct nla_policy mpls_policy[TCA_MPLS_MAX + 1] = {
+	[TCA_MPLS_PARMS]	= NLA_POLICY_EXACT_LEN(sizeof(struct tc_mpls)),
+	[TCA_MPLS_PROTO]	= { .type = NLA_U16 },
+	[TCA_MPLS_LABEL]	= NLA_POLICY_VALIDATE_FN(NLA_BINARY,
+							 valid_label),
+	[TCA_MPLS_TC]		= NLA_POLICY_RANGE(NLA_U8, 0, 7),
+	[TCA_MPLS_TTL]		= NLA_POLICY_MIN(NLA_U8, 1),
+	[TCA_MPLS_BOS]		= NLA_POLICY_RANGE(NLA_U8, 0, 1),
+};
+
+static int tcf_mpls_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_mpls_ops.net_id);
+	bool bind = flags & TCA_ACT_FLAGS_BIND;
+	struct nlattr *tb[TCA_MPLS_MAX + 1];
+	struct tcf_chain *goto_ch = NULL;
+	struct tcf_mpls_params *p;
+	struct tc_mpls *parm;
+	bool exists = false;
+	struct tcf_mpls *m;
+	int ret = 0, err;
+	u8 mpls_ttl = 0;
+	u32 index;
+
+	if (!nla) {
+		NL_SET_ERR_MSG_MOD(extack, "Missing netlink attributes");
+		return -EINVAL;
+	}
+
+	err = nla_parse_nested(tb, TCA_MPLS_MAX, nla, mpls_policy, extack);
+	if (err < 0)
+		return err;
+
+	if (!tb[TCA_MPLS_PARMS]) {
+		NL_SET_ERR_MSG_MOD(extack, "No MPLS params");
+		return -EINVAL;
+	}
+	parm = nla_data(tb[TCA_MPLS_PARMS]);
+	index = parm->index;
+
+	/* Verify parameters against action type. */
+	switch (parm->m_action) {
+	case TCA_MPLS_ACT_POP:
+		if (!tb[TCA_MPLS_PROTO]) {
+			NL_SET_ERR_MSG_MOD(extack, "Protocol must be set for MPLS pop");
+			return -EINVAL;
+		}
+		if (!eth_proto_is_802_3(nla_get_be16(tb[TCA_MPLS_PROTO]))) {
+			NL_SET_ERR_MSG_MOD(extack, "Invalid protocol type for MPLS pop");
+			return -EINVAL;
+		}
+		if (tb[TCA_MPLS_LABEL] || tb[TCA_MPLS_TTL] || tb[TCA_MPLS_TC] ||
+		    tb[TCA_MPLS_BOS]) {
+			NL_SET_ERR_MSG_MOD(extack, "Label, TTL, TC or BOS cannot be used with MPLS pop");
+			return -EINVAL;
+		}
+		break;
+	case TCA_MPLS_ACT_DEC_TTL:
+		if (tb[TCA_MPLS_PROTO] || tb[TCA_MPLS_LABEL] ||
+		    tb[TCA_MPLS_TTL] || tb[TCA_MPLS_TC] || tb[TCA_MPLS_BOS]) {
+			NL_SET_ERR_MSG_MOD(extack, "Label, TTL, TC, BOS or protocol cannot be used with MPLS dec_ttl");
+			return -EINVAL;
+		}
+		break;
+	case TCA_MPLS_ACT_PUSH:
+	case TCA_MPLS_ACT_MAC_PUSH:
+		if (!tb[TCA_MPLS_LABEL]) {
+			NL_SET_ERR_MSG_MOD(extack, "Label is required for MPLS push");
+			return -EINVAL;
+		}
+		if (tb[TCA_MPLS_PROTO] &&
+		    !eth_p_mpls(nla_get_be16(tb[TCA_MPLS_PROTO]))) {
+			NL_SET_ERR_MSG_MOD(extack, "Protocol must be an MPLS type for MPLS push");
+			return -EPROTONOSUPPORT;
+		}
+		/* Push needs a TTL - if not specified, set a default value. */
+		if (!tb[TCA_MPLS_TTL]) {
+#if IS_ENABLED(CONFIG_MPLS)
+			mpls_ttl = net->mpls.default_ttl ?
+				   net->mpls.default_ttl : ACT_MPLS_TTL_DEFAULT;
+#else
+			mpls_ttl = ACT_MPLS_TTL_DEFAULT;
+#endif
+		}
+		break;
+	case TCA_MPLS_ACT_MODIFY:
+		if (tb[TCA_MPLS_PROTO]) {
+			NL_SET_ERR_MSG_MOD(extack, "Protocol cannot be used with MPLS modify");
+			return -EINVAL;
+		}
+		break;
+	default:
+		NL_SET_ERR_MSG_MOD(extack, "Unknown MPLS action");
+		return -EINVAL;
+	}
+
+	err = tcf_idr_check_alloc(tn, &index, a, bind);
+	if (err < 0)
+		return err;
+	exists = err;
+	if (exists && bind)
+		return 0;
+
+	if (!exists) {
+		ret = tcf_idr_create(tn, index, est, a,
+				     &act_mpls_ops, bind, true, flags);
+		if (ret) {
+			tcf_idr_cleanup(tn, index);
+			return ret;
+		}
+
+		ret = ACT_P_CREATED;
+	} else if (!(flags & TCA_ACT_FLAGS_REPLACE)) {
+		tcf_idr_release(*a, bind);
+		return -EEXIST;
+	}
+
+	err = tcf_action_check_ctrlact(parm->action, tp, &goto_ch, extack);
+	if (err < 0)
+		goto release_idr;
+
+	m = to_mpls(*a);
+
+	p = kzalloc(sizeof(*p), GFP_KERNEL);
+	if (!p) {
+		err = -ENOMEM;
+		goto put_chain;
+	}
+
+	p->tcfm_action = parm->m_action;
+	p->tcfm_label = tb[TCA_MPLS_LABEL] ? nla_get_u32(tb[TCA_MPLS_LABEL]) :
+					     ACT_MPLS_LABEL_NOT_SET;
+	p->tcfm_tc = tb[TCA_MPLS_TC] ? nla_get_u8(tb[TCA_MPLS_TC]) :
+				       ACT_MPLS_TC_NOT_SET;
+	p->tcfm_ttl = tb[TCA_MPLS_TTL] ? nla_get_u8(tb[TCA_MPLS_TTL]) :
+					 mpls_ttl;
+	p->tcfm_bos = tb[TCA_MPLS_BOS] ? nla_get_u8(tb[TCA_MPLS_BOS]) :
+					 ACT_MPLS_BOS_NOT_SET;
+	p->tcfm_proto = tb[TCA_MPLS_PROTO] ? nla_get_be16(tb[TCA_MPLS_PROTO]) :
+					     htons(ETH_P_MPLS_UC);
+
+	spin_lock_bh(&m->tcf_lock);
+	goto_ch = tcf_action_set_ctrlact(*a, parm->action, goto_ch);
+	p = rcu_replace_pointer(m->mpls_p, p, lockdep_is_held(&m->tcf_lock));
+	spin_unlock_bh(&m->tcf_lock);
+
+	if (goto_ch)
+		tcf_chain_put_by_act(goto_ch);
+	if (p)
+		kfree_rcu(p, 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 void tcf_mpls_cleanup(struct tc_action *a)
+{
+	struct tcf_mpls *m = to_mpls(a);
+	struct tcf_mpls_params *p;
+
+	p = rcu_dereference_protected(m->mpls_p, 1);
+	if (p)
+		kfree_rcu(p, rcu);
+}
+
+static int tcf_mpls_dump(struct sk_buff *skb, struct tc_action *a,
+			 int bind, int ref)
+{
+	unsigned char *b = skb_tail_pointer(skb);
+	struct tcf_mpls *m = to_mpls(a);
+	struct tcf_mpls_params *p;
+	struct tc_mpls opt = {
+		.index    = m->tcf_index,
+		.refcnt   = refcount_read(&m->tcf_refcnt) - ref,
+		.bindcnt  = atomic_read(&m->tcf_bindcnt) - bind,
+	};
+	struct tcf_t t;
+
+	spin_lock_bh(&m->tcf_lock);
+	opt.action = m->tcf_action;
+	p = rcu_dereference_protected(m->mpls_p, lockdep_is_held(&m->tcf_lock));
+	opt.m_action = p->tcfm_action;
+
+	if (nla_put(skb, TCA_MPLS_PARMS, sizeof(opt), &opt))
+		goto nla_put_failure;
+
+	if (p->tcfm_label != ACT_MPLS_LABEL_NOT_SET &&
+	    nla_put_u32(skb, TCA_MPLS_LABEL, p->tcfm_label))
+		goto nla_put_failure;
+
+	if (p->tcfm_tc != ACT_MPLS_TC_NOT_SET &&
+	    nla_put_u8(skb, TCA_MPLS_TC, p->tcfm_tc))
+		goto nla_put_failure;
+
+	if (p->tcfm_ttl && nla_put_u8(skb, TCA_MPLS_TTL, p->tcfm_ttl))
+		goto nla_put_failure;
+
+	if (p->tcfm_bos != ACT_MPLS_BOS_NOT_SET &&
+	    nla_put_u8(skb, TCA_MPLS_BOS, p->tcfm_bos))
+		goto nla_put_failure;
+
+	if (nla_put_be16(skb, TCA_MPLS_PROTO, p->tcfm_proto))
+		goto nla_put_failure;
+
+	tcf_tm_dump(&t, &m->tcf_tm);
+
+	if (nla_put_64bit(skb, TCA_MPLS_TM, sizeof(t), &t, TCA_MPLS_PAD))
+		goto nla_put_failure;
+
+	spin_unlock_bh(&m->tcf_lock);
+
+	return skb->len;
+
+nla_put_failure:
+	spin_unlock_bh(&m->tcf_lock);
+	nlmsg_trim(skb, b);
+	return -EMSGSIZE;
+}
+
+static int tcf_mpls_offload_act_setup(struct tc_action *act, void *entry_data,
+				      u32 *index_inc, bool bind,
+				      struct netlink_ext_ack *extack)
+{
+	if (bind) {
+		struct flow_action_entry *entry = entry_data;
+
+		switch (tcf_mpls_action(act)) {
+		case TCA_MPLS_ACT_PUSH:
+			entry->id = FLOW_ACTION_MPLS_PUSH;
+			entry->mpls_push.proto = tcf_mpls_proto(act);
+			entry->mpls_push.label = tcf_mpls_label(act);
+			entry->mpls_push.tc = tcf_mpls_tc(act);
+			entry->mpls_push.bos = tcf_mpls_bos(act);
+			entry->mpls_push.ttl = tcf_mpls_ttl(act);
+			break;
+		case TCA_MPLS_ACT_POP:
+			entry->id = FLOW_ACTION_MPLS_POP;
+			entry->mpls_pop.proto = tcf_mpls_proto(act);
+			break;
+		case TCA_MPLS_ACT_MODIFY:
+			entry->id = FLOW_ACTION_MPLS_MANGLE;
+			entry->mpls_mangle.label = tcf_mpls_label(act);
+			entry->mpls_mangle.tc = tcf_mpls_tc(act);
+			entry->mpls_mangle.bos = tcf_mpls_bos(act);
+			entry->mpls_mangle.ttl = tcf_mpls_ttl(act);
+			break;
+		case TCA_MPLS_ACT_DEC_TTL:
+			NL_SET_ERR_MSG_MOD(extack, "Offload not supported when \"dec_ttl\" option is used");
+			return -EOPNOTSUPP;
+		case TCA_MPLS_ACT_MAC_PUSH:
+			NL_SET_ERR_MSG_MOD(extack, "Offload not supported when \"mac_push\" option is used");
+			return -EOPNOTSUPP;
+		default:
+			NL_SET_ERR_MSG_MOD(extack, "Unsupported MPLS mode offload");
+			return -EOPNOTSUPP;
+		}
+		*index_inc = 1;
+	} else {
+		struct flow_offload_action *fl_action = entry_data;
+
+		switch (tcf_mpls_action(act)) {
+		case TCA_MPLS_ACT_PUSH:
+			fl_action->id = FLOW_ACTION_MPLS_PUSH;
+			break;
+		case TCA_MPLS_ACT_POP:
+			fl_action->id = FLOW_ACTION_MPLS_POP;
+			break;
+		case TCA_MPLS_ACT_MODIFY:
+			fl_action->id = FLOW_ACTION_MPLS_MANGLE;
+			break;
+		default:
+			return -EOPNOTSUPP;
+		}
+	}
+
+	return 0;
+}
+
+static struct tc_action_ops act_mpls_ops = {
+	.kind		=	"mpls",
+	.id		=	TCA_ID_MPLS,
+	.owner		=	THIS_MODULE,
+	.act		=	tcf_mpls_act,
+	.dump		=	tcf_mpls_dump,
+	.init		=	tcf_mpls_init,
+	.cleanup	=	tcf_mpls_cleanup,
+	.offload_act_setup =	tcf_mpls_offload_act_setup,
+	.size		=	sizeof(struct tcf_mpls),
+};
+
+static __net_init int mpls_init_net(struct net *net)
+{
+	struct tc_action_net *tn = net_generic(net, act_mpls_ops.net_id);
+
+	return tc_action_net_init(net, tn, &act_mpls_ops);
+}
+
+static void __net_exit mpls_exit_net(struct list_head *net_list)
+{
+	tc_action_net_exit(net_list, act_mpls_ops.net_id);
+}
+
+static struct pernet_operations mpls_net_ops = {
+	.init = mpls_init_net,
+	.exit_batch = mpls_exit_net,
+	.id   = &act_mpls_ops.net_id,
+	.size = sizeof(struct tc_action_net),
+};
+
+static int __init mpls_init_module(void)
+{
+	return tcf_register_action(&act_mpls_ops, &mpls_net_ops);
+}
+
+static void __exit mpls_cleanup_module(void)
+{
+	tcf_unregister_action(&act_mpls_ops, &mpls_net_ops);
+}
+
+module_init(mpls_init_module);
+module_exit(mpls_cleanup_module);
+
+MODULE_SOFTDEP("post: mpls_gso");
+MODULE_AUTHOR("Netronome Systems <oss-drivers@netronome.com>");
+MODULE_LICENSE("GPL");
+MODULE_DESCRIPTION("MPLS manipulation actions");