Merge branch 'Add-MPLS-actions-to-TC'

John Hurley says:

====================
Add MPLS actions to TC

This patchset introduces a new TC action module that allows the
manipulation of the MPLS headers of packets. The code impliments
functionality including push, pop, and modify.

Also included are tests for the new funtionality. Note that these will
require iproute2 changes to be submitted soon.

NOTE: these patches are applied to net-next along with the patch:
[PATCH net 1/1] net: openvswitch: fix csum updates for MPLS actions
This patch has been accepted into net but, at time of posting, is not yet
in net-next.

v6-v7:
- add extra tests for setting max/min and exceeding range of fields -
  patch 5 (Roman Mashak)
v5-v6:
- add CONFIG_NET_ACT_MPLS to tc-testing config file - patch 5
  (Davide Caratti)
v4-v5:
- move mpls_hdr() call to after skb_ensure_writable - patch 3
  (Willem de Bruijn)
- move mpls_dec_ttl to helper - patch 4 (Willem de Bruijn)
- add iproute2 usage example to commit msg - patch 4 (David Ahern)
- align label validation with mpls core code - patch 4 (David Ahern)
- improve extack message for no proto in mpls pop - patch 4 (David Ahern)
v3-v4:
- refactor and reuse OvS code (Cong Wang)
- use csum API rather than skb_post*rscum to update skb->csum (Cong Wang)
- remove unnecessary warning (Cong Wang)
- add comments to uapi attributes (David Ahern)
- set strict type policy check for TCA_MPLS_UNSPEC (David Ahern)
- expand/improve extack messages (David Ahern)
- add option to manually set BOS
v2-v3:
- remove a few unnecessary line breaks (Jiri Pirko)
- retract hw offload patch from set (resubmit with driver changes) (Jiri)
v1->v2:
- ensure TCA_ID_MPLS does not conflict with TCA_ID_CTINFO (Davide Caratti)
====================

Signed-off-by: David S. Miller <davem@davemloft.net>

5 files changed, 596 insertions, 72 deletions

diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index cdb0ccdaac0b..6f1e31f674a3 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -59,6 +59,7 @@
 #include <linux/errqueue.h>
 #include <linux/prefetch.h>
 #include <linux/if_vlan.h>
+#include <linux/mpls.h>
 
 #include <net/protocol.h>
 #include <net/dst.h>
@@ -66,6 +67,7 @@
 #include <net/checksum.h>
 #include <net/ip6_checksum.h>
 #include <net/xfrm.h>
+#include <net/mpls.h>
 
 #include <linux/uaccess.h>
 #include <trace/events/skb.h>
@@ -5425,6 +5427,173 @@ int skb_vlan_push(struct sk_buff *skb, __be16 vlan_proto, u16 vlan_tci)
 }
 EXPORT_SYMBOL(skb_vlan_push);
 
+/* Update the ethertype of hdr and the skb csum value if required. */
+static void skb_mod_eth_type(struct sk_buff *skb, struct ethhdr *hdr,
+			     __be16 ethertype)
+{
+	if (skb->ip_summed == CHECKSUM_COMPLETE) {
+		__be16 diff[] = { ~hdr->h_proto, ethertype };
+
+		skb->csum = csum_partial((char *)diff, sizeof(diff), skb->csum);
+	}
+
+	hdr->h_proto = ethertype;
+}
+
+/**
+ * skb_mpls_push() - push a new MPLS header after the mac header
+ *
+ * @skb: buffer
+ * @mpls_lse: MPLS label stack entry to push
+ * @mpls_proto: ethertype of the new MPLS header (expects 0x8847 or 0x8848)
+ *
+ * Expects skb->data at mac header.
+ *
+ * Returns 0 on success, -errno otherwise.
+ */
+int skb_mpls_push(struct sk_buff *skb, __be32 mpls_lse, __be16 mpls_proto)
+{
+	struct mpls_shim_hdr *lse;
+	int err;
+
+	if (unlikely(!eth_p_mpls(mpls_proto)))
+		return -EINVAL;
+
+	/* Networking stack does not allow simultaneous Tunnel and MPLS GSO. */
+	if (skb->encapsulation)
+		return -EINVAL;
+
+	err = skb_cow_head(skb, MPLS_HLEN);
+	if (unlikely(err))
+		return err;
+
+	if (!skb->inner_protocol) {
+		skb_set_inner_network_header(skb, skb->mac_len);
+		skb_set_inner_protocol(skb, skb->protocol);
+	}
+
+	skb_push(skb, MPLS_HLEN);
+	memmove(skb_mac_header(skb) - MPLS_HLEN, skb_mac_header(skb),
+		skb->mac_len);
+	skb_reset_mac_header(skb);
+	skb_set_network_header(skb, skb->mac_len);
+
+	lse = mpls_hdr(skb);
+	lse->label_stack_entry = mpls_lse;
+	skb_postpush_rcsum(skb, lse, MPLS_HLEN);
+
+	if (skb->dev && skb->dev->type == ARPHRD_ETHER)
+		skb_mod_eth_type(skb, eth_hdr(skb), mpls_proto);
+	skb->protocol = mpls_proto;
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(skb_mpls_push);
+
+/**
+ * skb_mpls_pop() - pop the outermost MPLS header
+ *
+ * @skb: buffer
+ * @next_proto: ethertype of header after popped MPLS header
+ *
+ * Expects skb->data at mac header.
+ *
+ * Returns 0 on success, -errno otherwise.
+ */
+int skb_mpls_pop(struct sk_buff *skb, __be16 next_proto)
+{
+	int err;
+
+	if (unlikely(!eth_p_mpls(skb->protocol)))
+		return -EINVAL;
+
+	err = skb_ensure_writable(skb, skb->mac_len + MPLS_HLEN);
+	if (unlikely(err))
+		return err;
+
+	skb_postpull_rcsum(skb, mpls_hdr(skb), MPLS_HLEN);
+	memmove(skb_mac_header(skb) + MPLS_HLEN, skb_mac_header(skb),
+		skb->mac_len);
+
+	__skb_pull(skb, MPLS_HLEN);
+	skb_reset_mac_header(skb);
+	skb_set_network_header(skb, skb->mac_len);
+
+	if (skb->dev && skb->dev->type == ARPHRD_ETHER) {
+		struct ethhdr *hdr;
+
+		/* use mpls_hdr() to get ethertype to account for VLANs. */
+		hdr = (struct ethhdr *)((void *)mpls_hdr(skb) - ETH_HLEN);
+		skb_mod_eth_type(skb, hdr, next_proto);
+	}
+	skb->protocol = next_proto;
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(skb_mpls_pop);
+
+/**
+ * skb_mpls_update_lse() - modify outermost MPLS header and update csum
+ *
+ * @skb: buffer
+ * @mpls_lse: new MPLS label stack entry to update to
+ *
+ * Expects skb->data at mac header.
+ *
+ * Returns 0 on success, -errno otherwise.
+ */
+int skb_mpls_update_lse(struct sk_buff *skb, __be32 mpls_lse)
+{
+	int err;
+
+	if (unlikely(!eth_p_mpls(skb->protocol)))
+		return -EINVAL;
+
+	err = skb_ensure_writable(skb, skb->mac_len + MPLS_HLEN);
+	if (unlikely(err))
+		return err;
+
+	if (skb->ip_summed == CHECKSUM_COMPLETE) {
+		__be32 diff[] = { ~mpls_hdr(skb)->label_stack_entry, mpls_lse };
+
+		skb->csum = csum_partial((char *)diff, sizeof(diff), skb->csum);
+	}
+
+	mpls_hdr(skb)->label_stack_entry = mpls_lse;
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(skb_mpls_update_lse);
+
+/**
+ * skb_mpls_dec_ttl() - decrement the TTL of the outermost MPLS header
+ *
+ * @skb: buffer
+ *
+ * Expects skb->data at mac header.
+ *
+ * Returns 0 on success, -errno otherwise.
+ */
+int skb_mpls_dec_ttl(struct sk_buff *skb)
+{
+	u32 lse;
+	u8 ttl;
+
+	if (unlikely(!eth_p_mpls(skb->protocol)))
+		return -EINVAL;
+
+	lse = be32_to_cpu(mpls_hdr(skb)->label_stack_entry);
+	ttl = (lse & MPLS_LS_TTL_MASK) >> MPLS_LS_TTL_SHIFT;
+	if (!--ttl)
+		return -EINVAL;
+
+	lse &= ~MPLS_LS_TTL_MASK;
+	lse |= ttl << MPLS_LS_TTL_SHIFT;
+
+	return skb_mpls_update_lse(skb, cpu_to_be32(lse));
+}
+EXPORT_SYMBOL_GPL(skb_mpls_dec_ttl);
+
 /**
  * alloc_skb_with_frags - allocate skb with page frags
  *
diff --git a/net/openvswitch/actions.c b/net/openvswitch/actions.c
index bd131469e4ca..3572e11b6f21 100644
--- a/net/openvswitch/actions.c
+++ b/net/openvswitch/actions.c
@@ -160,49 +160,14 @@ static int do_execute_actions(struct datapath *dp, struct sk_buff *skb,
 			      struct sw_flow_key *key,
 			      const struct nlattr *attr, int len);
 
-static void update_ethertype(struct sk_buff *skb, struct ethhdr *hdr,
-			     __be16 ethertype)
-{
-	if (skb->ip_summed == CHECKSUM_COMPLETE) {
-		__be16 diff[] = { ~(hdr->h_proto), ethertype };
-
-		skb->csum = csum_partial((char *)diff, sizeof(diff), skb->csum);
-	}
-
-	hdr->h_proto = ethertype;
-}
-
 static int push_mpls(struct sk_buff *skb, struct sw_flow_key *key,
 		     const struct ovs_action_push_mpls *mpls)
 {
-	struct mpls_shim_hdr *new_mpls_lse;
-
-	/* Networking stack do not allow simultaneous Tunnel and MPLS GSO. */
-	if (skb->encapsulation)
-		return -ENOTSUPP;
-
-	if (skb_cow_head(skb, MPLS_HLEN) < 0)
-		return -ENOMEM;
-
-	if (!skb->inner_protocol) {
-		skb_set_inner_network_header(skb, skb->mac_len);
-		skb_set_inner_protocol(skb, skb->protocol);
-	}
-
-	skb_push(skb, MPLS_HLEN);
-	memmove(skb_mac_header(skb) - MPLS_HLEN, skb_mac_header(skb),
-		skb->mac_len);
-	skb_reset_mac_header(skb);
-	skb_set_network_header(skb, skb->mac_len);
-
-	new_mpls_lse = mpls_hdr(skb);
-	new_mpls_lse->label_stack_entry = mpls->mpls_lse;
-
-	skb_postpush_rcsum(skb, new_mpls_lse, MPLS_HLEN);
+	int err;
 
-	if (ovs_key_mac_proto(key) == MAC_PROTO_ETHERNET)
-		update_ethertype(skb, eth_hdr(skb), mpls->mpls_ethertype);
-	skb->protocol = mpls->mpls_ethertype;
+	err = skb_mpls_push(skb, mpls->mpls_lse, mpls->mpls_ethertype);
+	if (err)
+		return err;
 
 	invalidate_flow_key(key);
 	return 0;
@@ -213,31 +178,10 @@ static int pop_mpls(struct sk_buff *skb, struct sw_flow_key *key,
 {
 	int err;
 
-	err = skb_ensure_writable(skb, skb->mac_len + MPLS_HLEN);
-	if (unlikely(err))
+	err = skb_mpls_pop(skb, ethertype);
+	if (err)
 		return err;
 
-	skb_postpull_rcsum(skb, mpls_hdr(skb), MPLS_HLEN);
-
-	memmove(skb_mac_header(skb) + MPLS_HLEN, skb_mac_header(skb),
-		skb->mac_len);
-
-	__skb_pull(skb, MPLS_HLEN);
-	skb_reset_mac_header(skb);
-	skb_set_network_header(skb, skb->mac_len);
-
-	if (ovs_key_mac_proto(key) == MAC_PROTO_ETHERNET) {
-		struct ethhdr *hdr;
-
-		/* mpls_hdr() is used to locate the ethertype field correctly in the
-		 * presence of VLAN tags.
-		 */
-		hdr = (struct ethhdr *)((void *)mpls_hdr(skb) - ETH_HLEN);
-		update_ethertype(skb, hdr, ethertype);
-	}
-	if (eth_p_mpls(skb->protocol))
-		skb->protocol = ethertype;
-
 	invalidate_flow_key(key);
 	return 0;
 }
@@ -249,19 +193,12 @@ static int set_mpls(struct sk_buff *skb, struct sw_flow_key *flow_key,
 	__be32 lse;
 	int err;
 
-	err = skb_ensure_writable(skb, skb->mac_len + MPLS_HLEN);
-	if (unlikely(err))
-		return err;
-
 	stack = mpls_hdr(skb);
 	lse = OVS_MASKED(stack->label_stack_entry, *mpls_lse, *mask);
-	if (skb->ip_summed == CHECKSUM_COMPLETE) {
-		__be32 diff[] = { ~(stack->label_stack_entry), lse };
-
-		skb->csum = csum_partial((char *)diff, sizeof(diff), skb->csum);
-	}
+	err = skb_mpls_update_lse(skb, lse);
+	if (err)
+		return err;
 
-	stack->label_stack_entry = lse;
 	flow_key->mpls.top_lse = lse;
 	return 0;
 }
diff --git a/net/sched/Kconfig b/net/sched/Kconfig
index 360fdd3eaa77..731f5fbc2a3c 100644
--- a/net/sched/Kconfig
+++ b/net/sched/Kconfig
@@ -842,6 +842,17 @@ config NET_ACT_CSUM
 	  To compile this code as a module, choose M here: the
 	  module will be called act_csum.
 
+config NET_ACT_MPLS
+	tristate "MPLS manipulation"
+	depends on NET_CLS_ACT
+	help
+	  Say Y here to push or pop MPLS headers.
+
+	  If unsure, say N.
+
+	  To compile this code as a module, choose M here: the
+	  module will be called act_mpls.
+
 config NET_ACT_VLAN
         tristate "Vlan manipulation"
         depends on NET_CLS_ACT
diff --git a/net/sched/Makefile b/net/sched/Makefile
index d54bfcbd7981..c26603606c22 100644
--- a/net/sched/Makefile
+++ b/net/sched/Makefile
@@ -18,6 +18,7 @@ obj-$(CONFIG_NET_ACT_PEDIT)	+= act_pedit.o
 obj-$(CONFIG_NET_ACT_SIMP)	+= act_simple.o
 obj-$(CONFIG_NET_ACT_SKBEDIT)	+= act_skbedit.o
 obj-$(CONFIG_NET_ACT_CSUM)	+= act_csum.o
+obj-$(CONFIG_NET_ACT_MPLS)	+= act_mpls.o
 obj-$(CONFIG_NET_ACT_VLAN)	+= act_vlan.o
 obj-$(CONFIG_NET_ACT_BPF)	+= act_bpf.o
 obj-$(CONFIG_NET_ACT_CONNMARK)	+= act_connmark.o
diff --git a/net/sched/act_mpls.c b/net/sched/act_mpls.c
new file mode 100644
index 000000000000..ca2597ce4ac9
--- /dev/null
+++ b/net/sched/act_mpls.c
@@ -0,0 +1,406 @@
+// SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause)
+/* Copyright (C) 2019 Netronome Systems, Inc. */
+
+#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>
+
+static unsigned int mpls_net_id;
+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);
+}
+
+static 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;
+
+	tcf_lastuse_update(&m->tcf_tm);
+	bstats_cpu_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);
+
+	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))
+			goto drop;
+		break;
+	case TCA_MPLS_ACT_PUSH:
+		new_lse = tcf_mpls_get_lse(NULL, p, !eth_p_mpls(skb->protocol));
+		if (skb_mpls_push(skb, new_lse, p->tcfm_proto))
+			goto drop;
+		break;
+	case TCA_MPLS_ACT_MODIFY:
+		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 (*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_UNSPEC]	= { .strict_start_type = TCA_MPLS_UNSPEC + 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_U32, 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,
+			 int ovr, int bind, bool rtnl_held,
+			 struct tcf_proto *tp, struct netlink_ext_ack *extack)
+{
+	struct tc_action_net *tn = net_generic(net, mpls_net_id);
+	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;
+
+	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]);
+
+	/* 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:
+		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, &parm->index, a, bind);
+	if (err < 0)
+		return err;
+	exists = err;
+	if (exists && bind)
+		return 0;
+
+	if (!exists) {
+		ret = tcf_idr_create(tn, parm->index, est, a,
+				     &act_mpls_ops, bind, true);
+		if (ret) {
+			tcf_idr_cleanup(tn, parm->index);
+			return ret;
+		}
+
+		ret = ACT_P_CREATED;
+	} else if (!ovr) {
+		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);
+	rcu_swap_protected(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);
+
+	if (ret == ACT_P_CREATED)
+		tcf_idr_insert(tn, *a);
+	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_walker(struct net *net, struct sk_buff *skb,
+			   struct netlink_callback *cb, int type,
+			   const struct tc_action_ops *ops,
+			   struct netlink_ext_ack *extack)
+{
+	struct tc_action_net *tn = net_generic(net, mpls_net_id);
+
+	return tcf_generic_walker(tn, skb, cb, type, ops, extack);
+}
+
+static int tcf_mpls_search(struct net *net, struct tc_action **a, u32 index)
+{
+	struct tc_action_net *tn = net_generic(net, mpls_net_id);
+
+	return tcf_idr_search(tn, a, index);
+}
+
+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,
+	.walk		=	tcf_mpls_walker,
+	.lookup		=	tcf_mpls_search,
+	.size		=	sizeof(struct tcf_mpls),
+};
+
+static __net_init int mpls_init_net(struct net *net)
+{
+	struct tc_action_net *tn = net_generic(net, mpls_net_id);
+
+	return tc_action_net_init(tn, &act_mpls_ops);
+}
+
+static void __net_exit mpls_exit_net(struct list_head *net_list)
+{
+	tc_action_net_exit(net_list, mpls_net_id);
+}
+
+static struct pernet_operations mpls_net_ops = {
+	.init = mpls_init_net,
+	.exit_batch = mpls_exit_net,
+	.id   = &mpls_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_AUTHOR("Netronome Systems <oss-drivers@netronome.com>");
+MODULE_LICENSE("GPL");
+MODULE_DESCRIPTION("MPLS manipulation actions");