openvswitch: enable NSH support

v16->17
- Fixed disputed check code: keep them in nsh_push and nsh_pop
but also add them in __ovs_nla_copy_actions

v15->v16
- Add csum recalculation for nsh_push, nsh_pop and set_nsh
pointed out by Pravin
- Move nsh key into the union with ipv4 and ipv6 and add
check for nsh key in match_validate pointed out by Pravin
- Add nsh check in validate_set and __ovs_nla_copy_actions

v14->v15
- Check size in nsh_hdr_from_nlattr
- Fixed four small issues pointed out By Jiri and Eric

v13->v14
- Rename skb_push_nsh to nsh_push per Dave's comment
- Rename skb_pop_nsh to nsh_pop per Dave's comment

v12->v13
- Fix NSH header length check in set_nsh

v11->v12
- Fix missing changes old comments pointed out
- Fix new comments for v11

v10->v11
- Fix the left three disputable comments for v9
but not fixed in v10.

v9->v10
- Change struct ovs_key_nsh to
struct ovs_nsh_key_base base;
__be32 context[NSH_MD1_CONTEXT_SIZE];
- Fix new comments for v9

v8->v9
- Fix build error reported by daily intel build
because nsh module isn't selected by openvswitch

v7->v8
- Rework nested value and mask for OVS_KEY_ATTR_NSH
- Change pop_nsh to adapt to nsh kernel module
- Fix many issues per comments from Jiri Benc

v6->v7
- Remove NSH GSO patches in v6 because Jiri Benc
reworked it as another patch series and they have
been merged.
- Change it to adapt to nsh kernel module added by NSH
GSO patch series

v5->v6
- Fix the rest comments for v4.
- Add NSH GSO support for VxLAN-gpe + NSH and
Eth + NSH.

v4->v5
- Fix many comments by Jiri Benc and Eric Garver
for v4.

v3->v4
- Add new NSH match field ttl
- Update NSH header to the latest format
which will be final format and won't change
per its author's confirmation.
- Fix comments for v3.

v2->v3
- Change OVS_KEY_ATTR_NSH to nested key to handle
length-fixed attributes and length-variable
attriubte more flexibly.
- Remove struct ovs_action_push_nsh completely
- Add code to handle nested attribute for SET_MASKED
- Change PUSH_NSH to use the nested OVS_KEY_ATTR_NSH
to transfer NSH header data.
- Fix comments and coding style issues by Jiri and Eric

v1->v2
- Change encap_nsh and decap_nsh to push_nsh and pop_nsh
- Dynamically allocate struct ovs_action_push_nsh for
length-variable metadata.

OVS master and 2.8 branch has merged NSH userspace
patch series, this patch is to enable NSH support
in kernel data path in order that OVS can support
NSH in compat mode by porting this.

Signed-off-by: Yi Yang <[e-mail]>
Acked-by: Jiri Benc <[e-mail]>
Acked-by: Eric Garver <[e-mail]>
Acked-by: Pravin Shelar <[e-mail]>
Signed-off-by: David S. Miller <[e-mail]>

include/net/nsh.h

···
 			NSH_FLAGS_MASK | NSH_TTL_MASK | NSH_LEN_MASK);
 }
 
+int nsh_push(struct sk_buff *skb, const struct nshhdr *pushed_nh);
+int nsh_pop(struct sk_buff *skb);
+
 #endif /* __NET_NSH_H */

include/uapi/linux/openvswitch.h

···
 	OVS_KEY_ATTR_CT_LABELS,	/* 16-octet connection tracking label */
 	OVS_KEY_ATTR_CT_ORIG_TUPLE_IPV4,   /* struct ovs_key_ct_tuple_ipv4 */
 	OVS_KEY_ATTR_CT_ORIG_TUPLE_IPV6,   /* struct ovs_key_ct_tuple_ipv6 */
+	OVS_KEY_ATTR_NSH,       /* Nested set of ovs_nsh_key_* */
 
 #ifdef __KERNEL__
 	OVS_KEY_ATTR_TUNNEL_INFO,  /* struct ip_tunnel_info */
···
 	__be16 src_port;
 	__be16 dst_port;
 	__u8   ipv6_proto;
+};
+
+enum ovs_nsh_key_attr {
+	OVS_NSH_KEY_ATTR_UNSPEC,
+	OVS_NSH_KEY_ATTR_BASE,  /* struct ovs_nsh_key_base. */
+	OVS_NSH_KEY_ATTR_MD1,   /* struct ovs_nsh_key_md1. */
+	OVS_NSH_KEY_ATTR_MD2,   /* variable-length octets for MD type 2. */
+	__OVS_NSH_KEY_ATTR_MAX
+};
+
+#define OVS_NSH_KEY_ATTR_MAX (__OVS_NSH_KEY_ATTR_MAX - 1)
+
+struct ovs_nsh_key_base {
+	__u8 flags;
+	__u8 ttl;
+	__u8 mdtype;
+	__u8 np;
+	__be32 path_hdr;
+};
+
+#define NSH_MD1_CONTEXT_SIZE 4
+
+struct ovs_nsh_key_md1 {
+	__be32 context[NSH_MD1_CONTEXT_SIZE];
 };
 
 /**
···
  * @OVS_ACTION_ATTR_POP_ETH: Pop the outermost Ethernet header off the
  * packet.
  * @OVS_ACTION_ATTR_CT_CLEAR: Clear conntrack state from the packet.
+ * @OVS_ACTION_ATTR_PUSH_NSH: push NSH header to the packet.
+ * @OVS_ACTION_ATTR_POP_NSH: pop the outermost NSH header off the packet.
  *
  * Only a single header can be set with a single %OVS_ACTION_ATTR_SET.  Not all
  * fields within a header are modifiable, e.g. the IPv4 protocol and fragment
···
 	OVS_ACTION_ATTR_PUSH_ETH,     /* struct ovs_action_push_eth. */
 	OVS_ACTION_ATTR_POP_ETH,      /* No argument. */
 	OVS_ACTION_ATTR_CT_CLEAR,     /* No argument. */
+	OVS_ACTION_ATTR_PUSH_NSH,     /* Nested OVS_NSH_KEY_ATTR_*. */
+	OVS_ACTION_ATTR_POP_NSH,      /* No argument. */
 
 	__OVS_ACTION_ATTR_MAX,	      /* Nothing past this will be accepted
 				       * from userspace. */

net/nsh/nsh.c

···
 #include <net/nsh.h>
 #include <net/tun_proto.h>
 
+int nsh_push(struct sk_buff *skb, const struct nshhdr *pushed_nh)
+{
+	struct nshhdr *nh;
+	size_t length = nsh_hdr_len(pushed_nh);
+	u8 next_proto;
+
+	if (skb->mac_len) {
+		next_proto = TUN_P_ETHERNET;
+	} else {
+		next_proto = tun_p_from_eth_p(skb->protocol);
+		if (!next_proto)
+			return -EAFNOSUPPORT;
+	}
+
+	/* Add the NSH header */
+	if (skb_cow_head(skb, length) < 0)
+		return -ENOMEM;
+
+	skb_push(skb, length);
+	nh = (struct nshhdr *)(skb->data);
+	memcpy(nh, pushed_nh, length);
+	nh->np = next_proto;
+	skb_postpush_rcsum(skb, nh, length);
+
+	skb->protocol = htons(ETH_P_NSH);
+	skb_reset_mac_header(skb);
+	skb_reset_network_header(skb);
+	skb_reset_mac_len(skb);
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(nsh_push);
+
+int nsh_pop(struct sk_buff *skb)
+{
+	struct nshhdr *nh;
+	size_t length;
+	__be16 inner_proto;
+
+	if (!pskb_may_pull(skb, NSH_BASE_HDR_LEN))
+		return -ENOMEM;
+	nh = (struct nshhdr *)(skb->data);
+	length = nsh_hdr_len(nh);
+	inner_proto = tun_p_to_eth_p(nh->np);
+	if (!pskb_may_pull(skb, length))
+		return -ENOMEM;
+
+	if (!inner_proto)
+		return -EAFNOSUPPORT;
+
+	skb_pull_rcsum(skb, length);
+	skb_reset_mac_header(skb);
+	skb_reset_network_header(skb);
+	skb_reset_mac_len(skb);
+	skb->protocol = inner_proto;
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(nsh_pop);
+
 static struct sk_buff *nsh_gso_segment(struct sk_buff *skb,
 				       netdev_features_t features)
 {

net/openvswitch/Kconfig

···
 	select MPLS
 	select NET_MPLS_GSO
 	select DST_CACHE
+	select NET_NSH
 	---help---
 	  Open vSwitch is a multilayer Ethernet switch targeted at virtualized
 	  environments.  In addition to supporting a variety of features

net/openvswitch/actions.c

···
 #include "flow.h"
 #include "conntrack.h"
 #include "vport.h"
+#include "flow_netlink.h"
 
 struct deferred_action {
 	struct sk_buff *skb;
···
 	return 0;
 }
 
+static int push_nsh(struct sk_buff *skb, struct sw_flow_key *key,
+		    const struct nshhdr *nh)
+{
+	int err;
+
+	err = nsh_push(skb, nh);
+	if (err)
+		return err;
+
+	/* safe right before invalidate_flow_key */
+	key->mac_proto = MAC_PROTO_NONE;
+	invalidate_flow_key(key);
+	return 0;
+}
+
+static int pop_nsh(struct sk_buff *skb, struct sw_flow_key *key)
+{
+	int err;
+
+	err = nsh_pop(skb);
+	if (err)
+		return err;
+
+	/* safe right before invalidate_flow_key */
+	if (skb->protocol == htons(ETH_P_TEB))
+		key->mac_proto = MAC_PROTO_ETHERNET;
+	else
+		key->mac_proto = MAC_PROTO_NONE;
+	invalidate_flow_key(key);
+	return 0;
+}
+
 static void update_ip_l4_checksum(struct sk_buff *skb, struct iphdr *nh,
 				  __be32 addr, __be32 new_addr)
 {
···
 			       mask->ipv6_hlimit);
 		flow_key->ip.ttl = nh->hop_limit;
 	}
+	return 0;
+}
+
+static int set_nsh(struct sk_buff *skb, struct sw_flow_key *flow_key,
+		   const struct nlattr *a)
+{
+	struct nshhdr *nh;
+	size_t length;
+	int err;
+	u8 flags;
+	u8 ttl;
+	int i;
+
+	struct ovs_key_nsh key;
+	struct ovs_key_nsh mask;
+
+	err = nsh_key_from_nlattr(a, &key, &mask);
+	if (err)
+		return err;
+
+	/* Make sure the NSH base header is there */
+	if (!pskb_may_pull(skb, skb_network_offset(skb) + NSH_BASE_HDR_LEN))
+		return -ENOMEM;
+
+	nh = nsh_hdr(skb);
+	length = nsh_hdr_len(nh);
+
+	/* Make sure the whole NSH header is there */
+	err = skb_ensure_writable(skb, skb_network_offset(skb) +
+				       length);
+	if (unlikely(err))
+		return err;
+
+	nh = nsh_hdr(skb);
+	skb_postpull_rcsum(skb, nh, length);
+	flags = nsh_get_flags(nh);
+	flags = OVS_MASKED(flags, key.base.flags, mask.base.flags);
+	flow_key->nsh.base.flags = flags;
+	ttl = nsh_get_ttl(nh);
+	ttl = OVS_MASKED(ttl, key.base.ttl, mask.base.ttl);
+	flow_key->nsh.base.ttl = ttl;
+	nsh_set_flags_and_ttl(nh, flags, ttl);
+	nh->path_hdr = OVS_MASKED(nh->path_hdr, key.base.path_hdr,
+				  mask.base.path_hdr);
+	flow_key->nsh.base.path_hdr = nh->path_hdr;
+	switch (nh->mdtype) {
+	case NSH_M_TYPE1:
+		for (i = 0; i < NSH_MD1_CONTEXT_SIZE; i++) {
+			nh->md1.context[i] =
+			    OVS_MASKED(nh->md1.context[i], key.context[i],
+				       mask.context[i]);
+		}
+		memcpy(flow_key->nsh.context, nh->md1.context,
+		       sizeof(nh->md1.context));
+		break;
+	case NSH_M_TYPE2:
+		memset(flow_key->nsh.context, 0,
+		       sizeof(flow_key->nsh.context));
+		break;
+	default:
+		return -EINVAL;
+	}
+	skb_postpush_rcsum(skb, nh, length);
 	return 0;
 }
 
···
 				   get_mask(a, struct ovs_key_ethernet *));
 		break;
 
+	case OVS_KEY_ATTR_NSH:
+		err = set_nsh(skb, flow_key, a);
+		break;
+
 	case OVS_KEY_ATTR_IPV4:
 		err = set_ipv4(skb, flow_key, nla_data(a),
 			       get_mask(a, struct ovs_key_ipv4 *));
···
 
 		case OVS_ACTION_ATTR_POP_ETH:
 			err = pop_eth(skb, key);
+			break;
+
+		case OVS_ACTION_ATTR_PUSH_NSH: {
+			u8 buffer[NSH_HDR_MAX_LEN];
+			struct nshhdr *nh = (struct nshhdr *)buffer;
+
+			err = nsh_hdr_from_nlattr(nla_data(a), nh,
+						  NSH_HDR_MAX_LEN);
+			if (unlikely(err))
+				break;
+			err = push_nsh(skb, key, nh);
+			break;
+		}
+
+		case OVS_ACTION_ATTR_POP_NSH:
+			err = pop_nsh(skb, key);
 			break;
 		}
 

net/openvswitch/flow.c

···
 #include <net/ipv6.h>
 #include <net/mpls.h>
 #include <net/ndisc.h>
+#include <net/nsh.h>
 
 #include "conntrack.h"
 #include "datapath.h"
···
 	return 0;
 }
 
+static int parse_nsh(struct sk_buff *skb, struct sw_flow_key *key)
+{
+	struct nshhdr *nh;
+	unsigned int nh_ofs = skb_network_offset(skb);
+	u8 version, length;
+	int err;
+
+	err = check_header(skb, nh_ofs + NSH_BASE_HDR_LEN);
+	if (unlikely(err))
+		return err;
+
+	nh = nsh_hdr(skb);
+	version = nsh_get_ver(nh);
+	length = nsh_hdr_len(nh);
+
+	if (version != 0)
+		return -EINVAL;
+
+	err = check_header(skb, nh_ofs + length);
+	if (unlikely(err))
+		return err;
+
+	nh = nsh_hdr(skb);
+	key->nsh.base.flags = nsh_get_flags(nh);
+	key->nsh.base.ttl = nsh_get_ttl(nh);
+	key->nsh.base.mdtype = nh->mdtype;
+	key->nsh.base.np = nh->np;
+	key->nsh.base.path_hdr = nh->path_hdr;
+	switch (key->nsh.base.mdtype) {
+	case NSH_M_TYPE1:
+		if (length != NSH_M_TYPE1_LEN)
+			return -EINVAL;
+		memcpy(key->nsh.context, nh->md1.context,
+		       sizeof(nh->md1));
+		break;
+	case NSH_M_TYPE2:
+		memset(key->nsh.context, 0,
+		       sizeof(nh->md1));
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
 /**
  * key_extract - extracts a flow key from an Ethernet frame.
  * @skb: sk_buff that contains the frame, with skb->data pointing to the
···
 				memset(&key->tp, 0, sizeof(key->tp));
 			}
 		}
+	} else if (key->eth.type == htons(ETH_P_NSH)) {
+		error = parse_nsh(skb, key);
+		if (error)
+			return error;
 	}
 	return 0;
 }

net/openvswitch/flow.h

···
 #include <net/inet_ecn.h>
 #include <net/ip_tunnels.h>
 #include <net/dst_metadata.h>
+#include <net/nsh.h>
 
 struct sk_buff;
 
···
 #define OVS_SW_FLOW_KEY_METADATA_SIZE			\
 	(offsetof(struct sw_flow_key, recirc_id) +	\
 	FIELD_SIZEOF(struct sw_flow_key, recirc_id))
+
+struct ovs_key_nsh {
+	struct ovs_nsh_key_base base;
+	__be32 context[NSH_MD1_CONTEXT_SIZE];
+};
 
 struct sw_flow_key {
 	u8 tun_opts[IP_TUNNEL_OPTS_MAX];
···
 				} nd;
 			};
 		} ipv6;
+		struct ovs_key_nsh nsh;         /* network service header */
 	};
 	struct {
 		/* Connection tracking fields not packed above. */

net/openvswitch/flow_netlink.c

···
 #include <net/ndisc.h>
 #include <net/mpls.h>
 #include <net/vxlan.h>
+#include <net/tun_proto.h>
 #include <net/erspan.h>
 
 #include "flow_netlink.h"
···
 		case OVS_ACTION_ATTR_HASH:
 		case OVS_ACTION_ATTR_POP_ETH:
 		case OVS_ACTION_ATTR_POP_MPLS:
+		case OVS_ACTION_ATTR_POP_NSH:
 		case OVS_ACTION_ATTR_POP_VLAN:
 		case OVS_ACTION_ATTR_PUSH_ETH:
 		case OVS_ACTION_ATTR_PUSH_MPLS:
+		case OVS_ACTION_ATTR_PUSH_NSH:
 		case OVS_ACTION_ATTR_PUSH_VLAN:
 		case OVS_ACTION_ATTR_SAMPLE:
 		case OVS_ACTION_ATTR_SET:
···
 			| (1 << OVS_KEY_ATTR_ICMPV6)
 			| (1 << OVS_KEY_ATTR_ARP)
 			| (1 << OVS_KEY_ATTR_ND)
-			| (1 << OVS_KEY_ATTR_MPLS));
+			| (1 << OVS_KEY_ATTR_MPLS)
+			| (1 << OVS_KEY_ATTR_NSH));
 
 	/* Always allowed mask fields. */
 	mask_allowed |= ((1 << OVS_KEY_ATTR_TUNNEL)
···
 		}
 	}
 
+	if (match->key->eth.type == htons(ETH_P_NSH)) {
+		key_expected |= 1 << OVS_KEY_ATTR_NSH;
+		if (match->mask &&
+		    match->mask->key.eth.type == htons(0xffff)) {
+			mask_allowed |= 1 << OVS_KEY_ATTR_NSH;
+		}
+	}
+
 	if ((key_attrs & key_expected) != key_expected) {
 		/* Key attributes check failed. */
 		OVS_NLERR(log, "Missing key (keys=%llx, expected=%llx)",
···
 		+ nla_total_size(4);   /* OVS_TUNNEL_KEY_ATTR_ERSPAN_OPTS */
 }
 
+size_t ovs_nsh_key_attr_size(void)
+{
+	/* Whenever adding new OVS_NSH_KEY_ FIELDS, we should consider
+	 * updating this function.
+	 */
+	return  nla_total_size(NSH_BASE_HDR_LEN) /* OVS_NSH_KEY_ATTR_BASE */
+		/* OVS_NSH_KEY_ATTR_MD1 and OVS_NSH_KEY_ATTR_MD2 are
+		 * mutually exclusive, so the bigger one can cover
+		 * the small one.
+		 */
+		+ nla_total_size(NSH_CTX_HDRS_MAX_LEN);
+}
+
 size_t ovs_key_attr_size(void)
 {
 	/* Whenever adding new OVS_KEY_ FIELDS, we should consider
 	 * updating this function.
 	 */
-	BUILD_BUG_ON(OVS_KEY_ATTR_TUNNEL_INFO != 28);
+	BUILD_BUG_ON(OVS_KEY_ATTR_TUNNEL_INFO != 29);
 
 	return    nla_total_size(4)   /* OVS_KEY_ATTR_PRIORITY */
 		+ nla_total_size(0)   /* OVS_KEY_ATTR_TUNNEL */
···
 		+ nla_total_size(4)   /* OVS_KEY_ATTR_CT_MARK */
 		+ nla_total_size(16)  /* OVS_KEY_ATTR_CT_LABELS */
 		+ nla_total_size(40)  /* OVS_KEY_ATTR_CT_ORIG_TUPLE_IPV6 */
+		+ nla_total_size(0)   /* OVS_KEY_ATTR_NSH */
+		  + ovs_nsh_key_attr_size()
 		+ nla_total_size(12)  /* OVS_KEY_ATTR_ETHERNET */
 		+ nla_total_size(2)   /* OVS_KEY_ATTR_ETHERTYPE */
 		+ nla_total_size(4)   /* OVS_KEY_ATTR_VLAN */
···
 	[OVS_TUNNEL_KEY_ATTR_IPV6_SRC]      = { .len = sizeof(struct in6_addr) },
 	[OVS_TUNNEL_KEY_ATTR_IPV6_DST]      = { .len = sizeof(struct in6_addr) },
 	[OVS_TUNNEL_KEY_ATTR_ERSPAN_OPTS]   = { .len = sizeof(u32) },
+};
+
+static const struct ovs_len_tbl
+ovs_nsh_key_attr_lens[OVS_NSH_KEY_ATTR_MAX + 1] = {
+	[OVS_NSH_KEY_ATTR_BASE] = { .len = sizeof(struct ovs_nsh_key_base) },
+	[OVS_NSH_KEY_ATTR_MD1]  = { .len = sizeof(struct ovs_nsh_key_md1) },
+	[OVS_NSH_KEY_ATTR_MD2]  = { .len = OVS_ATTR_VARIABLE },
 };
 
 /* The size of the argument for each %OVS_KEY_ATTR_* Netlink attribute.  */
···
 		.len = sizeof(struct ovs_key_ct_tuple_ipv4) },
 	[OVS_KEY_ATTR_CT_ORIG_TUPLE_IPV6] = {
 		.len = sizeof(struct ovs_key_ct_tuple_ipv6) },
+	[OVS_KEY_ATTR_NSH]       = { .len = OVS_ATTR_NESTED,
+				     .next = ovs_nsh_key_attr_lens, },
 };
 
 static bool check_attr_len(unsigned int attr_len, unsigned int expected_len)
···
 	return 0;
 }
 
+int nsh_hdr_from_nlattr(const struct nlattr *attr,
+			struct nshhdr *nh, size_t size)
+{
+	struct nlattr *a;
+	int rem;
+	u8 flags = 0;
+	u8 ttl = 0;
+	int mdlen = 0;
+
+	/* validate_nsh has check this, so we needn't do duplicate check here
+	 */
+	if (size < NSH_BASE_HDR_LEN)
+		return -ENOBUFS;
+
+	nla_for_each_nested(a, attr, rem) {
+		int type = nla_type(a);
+
+		switch (type) {
+		case OVS_NSH_KEY_ATTR_BASE: {
+			const struct ovs_nsh_key_base *base = nla_data(a);
+
+			flags = base->flags;
+			ttl = base->ttl;
+			nh->np = base->np;
+			nh->mdtype = base->mdtype;
+			nh->path_hdr = base->path_hdr;
+			break;
+		}
+		case OVS_NSH_KEY_ATTR_MD1:
+			mdlen = nla_len(a);
+			if (mdlen > size - NSH_BASE_HDR_LEN)
+				return -ENOBUFS;
+			memcpy(&nh->md1, nla_data(a), mdlen);
+			break;
+
+		case OVS_NSH_KEY_ATTR_MD2:
+			mdlen = nla_len(a);
+			if (mdlen > size - NSH_BASE_HDR_LEN)
+				return -ENOBUFS;
+			memcpy(&nh->md2, nla_data(a), mdlen);
+			break;
+
+		default:
+			return -EINVAL;
+		}
+	}
+
+	/* nsh header length  = NSH_BASE_HDR_LEN + mdlen */
+	nh->ver_flags_ttl_len = 0;
+	nsh_set_flags_ttl_len(nh, flags, ttl, NSH_BASE_HDR_LEN + mdlen);
+
+	return 0;
+}
+
+int nsh_key_from_nlattr(const struct nlattr *attr,
+			struct ovs_key_nsh *nsh, struct ovs_key_nsh *nsh_mask)
+{
+	struct nlattr *a;
+	int rem;
+
+	/* validate_nsh has check this, so we needn't do duplicate check here
+	 */
+	nla_for_each_nested(a, attr, rem) {
+		int type = nla_type(a);
+
+		switch (type) {
+		case OVS_NSH_KEY_ATTR_BASE: {
+			const struct ovs_nsh_key_base *base = nla_data(a);
+			const struct ovs_nsh_key_base *base_mask = base + 1;
+
+			nsh->base = *base;
+			nsh_mask->base = *base_mask;
+			break;
+		}
+		case OVS_NSH_KEY_ATTR_MD1: {
+			const struct ovs_nsh_key_md1 *md1 = nla_data(a);
+			const struct ovs_nsh_key_md1 *md1_mask = md1 + 1;
+
+			memcpy(nsh->context, md1->context, sizeof(*md1));
+			memcpy(nsh_mask->context, md1_mask->context,
+			       sizeof(*md1_mask));
+			break;
+		}
+		case OVS_NSH_KEY_ATTR_MD2:
+			/* Not supported yet */
+			return -ENOTSUPP;
+		default:
+			return -EINVAL;
+		}
+	}
+
+	return 0;
+}
+
+static int nsh_key_put_from_nlattr(const struct nlattr *attr,
+				   struct sw_flow_match *match, bool is_mask,
+				   bool is_push_nsh, bool log)
+{
+	struct nlattr *a;
+	int rem;
+	bool has_base = false;
+	bool has_md1 = false;
+	bool has_md2 = false;
+	u8 mdtype = 0;
+	int mdlen = 0;
+
+	if (WARN_ON(is_push_nsh && is_mask))
+		return -EINVAL;
+
+	nla_for_each_nested(a, attr, rem) {
+		int type = nla_type(a);
+		int i;
+
+		if (type > OVS_NSH_KEY_ATTR_MAX) {
+			OVS_NLERR(log, "nsh attr %d is out of range max %d",
+				  type, OVS_NSH_KEY_ATTR_MAX);
+			return -EINVAL;
+		}
+
+		if (!check_attr_len(nla_len(a),
+				    ovs_nsh_key_attr_lens[type].len)) {
+			OVS_NLERR(
+			    log,
+			    "nsh attr %d has unexpected len %d expected %d",
+			    type,
+			    nla_len(a),
+			    ovs_nsh_key_attr_lens[type].len
+			);
+			return -EINVAL;
+		}
+
+		switch (type) {
+		case OVS_NSH_KEY_ATTR_BASE: {
+			const struct ovs_nsh_key_base *base = nla_data(a);
+
+			has_base = true;
+			mdtype = base->mdtype;
+			SW_FLOW_KEY_PUT(match, nsh.base.flags,
+					base->flags, is_mask);
+			SW_FLOW_KEY_PUT(match, nsh.base.ttl,
+					base->ttl, is_mask);
+			SW_FLOW_KEY_PUT(match, nsh.base.mdtype,
+					base->mdtype, is_mask);
+			SW_FLOW_KEY_PUT(match, nsh.base.np,
+					base->np, is_mask);
+			SW_FLOW_KEY_PUT(match, nsh.base.path_hdr,
+					base->path_hdr, is_mask);
+			break;
+		}
+		case OVS_NSH_KEY_ATTR_MD1: {
+			const struct ovs_nsh_key_md1 *md1 = nla_data(a);
+
+			has_md1 = true;
+			for (i = 0; i < NSH_MD1_CONTEXT_SIZE; i++)
+				SW_FLOW_KEY_PUT(match, nsh.context[i],
+						md1->context[i], is_mask);
+			break;
+		}
+		case OVS_NSH_KEY_ATTR_MD2:
+			if (!is_push_nsh) /* Not supported MD type 2 yet */
+				return -ENOTSUPP;
+
+			has_md2 = true;
+			mdlen = nla_len(a);
+			if (mdlen > NSH_CTX_HDRS_MAX_LEN || mdlen <= 0) {
+				OVS_NLERR(
+				    log,
+				    "Invalid MD length %d for MD type %d",
+				    mdlen,
+				    mdtype
+				);
+				return -EINVAL;
+			}
+			break;
+		default:
+			OVS_NLERR(log, "Unknown nsh attribute %d",
+				  type);
+			return -EINVAL;
+		}
+	}
+
+	if (rem > 0) {
+		OVS_NLERR(log, "nsh attribute has %d unknown bytes.", rem);
+		return -EINVAL;
+	}
+
+	if (has_md1 && has_md2) {
+		OVS_NLERR(
+		    1,
+		    "invalid nsh attribute: md1 and md2 are exclusive."
+		);
+		return -EINVAL;
+	}
+
+	if (!is_mask) {
+		if ((has_md1 && mdtype != NSH_M_TYPE1) ||
+		    (has_md2 && mdtype != NSH_M_TYPE2)) {
+			OVS_NLERR(1, "nsh attribute has unmatched MD type %d.",
+				  mdtype);
+			return -EINVAL;
+		}
+
+		if (is_push_nsh &&
+		    (!has_base || (!has_md1 && !has_md2))) {
+			OVS_NLERR(
+			    1,
+			    "push_nsh: missing base or metadata attributes"
+			);
+			return -EINVAL;
+		}
+	}
+
+	return 0;
+}
+
 static int ovs_key_from_nlattrs(struct net *net, struct sw_flow_match *match,
 				u64 attrs, const struct nlattr **a,
 				bool is_mask, bool log)
···
 				arp_key->arp_tha, ETH_ALEN, is_mask);
 
 		attrs &= ~(1 << OVS_KEY_ATTR_ARP);
+	}
+
+	if (attrs & (1 << OVS_KEY_ATTR_NSH)) {
+		if (nsh_key_put_from_nlattr(a[OVS_KEY_ATTR_NSH], match,
+					    is_mask, false, log) < 0)
+			return -EINVAL;
+		attrs &= ~(1 << OVS_KEY_ATTR_NSH);
 	}
 
 	if (attrs & (1 << OVS_KEY_ATTR_MPLS)) {
···
 	return 0;
 }
 
+static int nsh_key_to_nlattr(const struct ovs_key_nsh *nsh, bool is_mask,
+			     struct sk_buff *skb)
+{
+	struct nlattr *start;
+
+	start = nla_nest_start(skb, OVS_KEY_ATTR_NSH);
+	if (!start)
+		return -EMSGSIZE;
+
+	if (nla_put(skb, OVS_NSH_KEY_ATTR_BASE, sizeof(nsh->base), &nsh->base))
+		goto nla_put_failure;
+
+	if (is_mask || nsh->base.mdtype == NSH_M_TYPE1) {
+		if (nla_put(skb, OVS_NSH_KEY_ATTR_MD1,
+			    sizeof(nsh->context), nsh->context))
+			goto nla_put_failure;
+	}
+
+	/* Don't support MD type 2 yet */
+
+	nla_nest_end(skb, start);
+
+	return 0;
+
+nla_put_failure:
+	return -EMSGSIZE;
+}
+
 static int __ovs_nla_put_key(const struct sw_flow_key *swkey,
 			     const struct sw_flow_key *output, bool is_mask,
 			     struct sk_buff *skb)
···
 		ipv6_key->ipv6_tclass = output->ip.tos;
 		ipv6_key->ipv6_hlimit = output->ip.ttl;
 		ipv6_key->ipv6_frag = output->ip.frag;
+	} else if (swkey->eth.type == htons(ETH_P_NSH)) {
+		if (nsh_key_to_nlattr(&output->nsh, is_mask, skb))
+			goto nla_put_failure;
 	} else if (swkey->eth.type == htons(ETH_P_ARP) ||
 		   swkey->eth.type == htons(ETH_P_RARP)) {
 		struct ovs_key_arp *arp_key;
···
 	return err;
 }
 
+static bool validate_nsh(const struct nlattr *attr, bool is_mask,
+			 bool is_push_nsh, bool log)
+{
+	struct sw_flow_match match;
+	struct sw_flow_key key;
+	int ret = 0;
+
+	ovs_match_init(&match, &key, true, NULL);
+	ret = nsh_key_put_from_nlattr(attr, &match, is_mask,
+				      is_push_nsh, log);
+	return !ret;
+}
+
 /* Return false if there are any non-masked bits set.
  * Mask follows data immediately, before any netlink padding.
  */
···
 
 		break;
 
+	case OVS_KEY_ATTR_NSH:
+		if (eth_type != htons(ETH_P_NSH))
+			return -EINVAL;
+		if (!validate_nsh(nla_data(a), masked, false, log))
+			return -EINVAL;
+		break;
+
 	default:
 		return -EINVAL;
 	}
···
 			[OVS_ACTION_ATTR_TRUNC] = sizeof(struct ovs_action_trunc),
 			[OVS_ACTION_ATTR_PUSH_ETH] = sizeof(struct ovs_action_push_eth),
 			[OVS_ACTION_ATTR_POP_ETH] = 0,
+			[OVS_ACTION_ATTR_PUSH_NSH] = (u32)-1,
+			[OVS_ACTION_ATTR_POP_NSH] = 0,
 		};
 		const struct ovs_action_push_vlan *vlan;
 		int type = nla_type(a);
···
 				return -EINVAL;
 			mac_proto = MAC_PROTO_ETHERNET;
 			break;
+
+		case OVS_ACTION_ATTR_PUSH_NSH:
+			if (mac_proto != MAC_PROTO_ETHERNET) {
+				u8 next_proto;
+
+				next_proto = tun_p_from_eth_p(eth_type);
+				if (!next_proto)
+					return -EINVAL;
+			}
+			mac_proto = MAC_PROTO_NONE;
+			if (!validate_nsh(nla_data(a), false, true, true))
+				return -EINVAL;
+			break;
+
+		case OVS_ACTION_ATTR_POP_NSH: {
+			__be16 inner_proto;
+
+			if (eth_type != htons(ETH_P_NSH))
+				return -EINVAL;
+			inner_proto = tun_p_to_eth_p(key->nsh.base.np);
+			if (!inner_proto)
+				return -EINVAL;
+			if (key->nsh.base.np == TUN_P_ETHERNET)
+				mac_proto = MAC_PROTO_ETHERNET;
+			else
+				mac_proto = MAC_PROTO_NONE;
+			break;
+		}
 
 		default:
 			OVS_NLERR(log, "Unknown Action type %d", type);

net/openvswitch/flow_netlink.h

···
 void ovs_nla_free_flow_actions(struct sw_flow_actions *);
 void ovs_nla_free_flow_actions_rcu(struct sw_flow_actions *);
 
+int nsh_key_from_nlattr(const struct nlattr *attr, struct ovs_key_nsh *nsh,
+			struct ovs_key_nsh *nsh_mask);
+int nsh_hdr_from_nlattr(const struct nlattr *attr, struct nshhdr *nh,
+			size_t size);
+
 #endif /* flow_netlink.h */