Adding upstream version 6.1.76.upstream/6.1.76upstream

Signed-off-by: Daniel Baumann <daniel.baumann@progress-linux.org>

9 files changed, 3832 insertions, 0 deletions

diff --git a/net/mctp/Kconfig b/net/mctp/Kconfig
new file mode 100644
index 000000000..3a5c0e70d
--- /dev/null
+++ b/net/mctp/Kconfig
@@ -0,0 +1,23 @@
+
+menuconfig MCTP
+	depends on NET
+	bool "MCTP core protocol support"
+	help
+	  Management Component Transport Protocol (MCTP) is an in-system
+	  protocol for communicating between management controllers and
+	  their managed devices (peripherals, host processors, etc.). The
+	  protocol is defined by DMTF specification DSP0236.
+
+	  This option enables core MCTP support. For communicating with other
+	  devices, you'll want to enable a driver for a specific hardware
+	  channel.
+
+config MCTP_TEST
+        bool "MCTP core tests" if !KUNIT_ALL_TESTS
+        depends on MCTP=y && KUNIT=y
+        default KUNIT_ALL_TESTS
+
+config MCTP_FLOWS
+	bool
+	depends on MCTP
+	select SKB_EXTENSIONS
diff --git a/net/mctp/Makefile b/net/mctp/Makefile
new file mode 100644
index 000000000..6cd55233e
--- /dev/null
+++ b/net/mctp/Makefile
@@ -0,0 +1,6 @@
+# SPDX-License-Identifier: GPL-2.0
+obj-$(CONFIG_MCTP) += mctp.o
+mctp-objs := af_mctp.o device.o route.o neigh.o
+
+# tests
+obj-$(CONFIG_MCTP_TEST) += test/utils.o
diff --git a/net/mctp/af_mctp.c b/net/mctp/af_mctp.c
new file mode 100644
index 000000000..3150f3f0c
--- /dev/null
+++ b/net/mctp/af_mctp.c
@@ -0,0 +1,710 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Management Component Transport Protocol (MCTP)
+ *
+ * Copyright (c) 2021 Code Construct
+ * Copyright (c) 2021 Google
+ */
+
+#include <linux/compat.h>
+#include <linux/if_arp.h>
+#include <linux/net.h>
+#include <linux/mctp.h>
+#include <linux/module.h>
+#include <linux/socket.h>
+
+#include <net/mctp.h>
+#include <net/mctpdevice.h>
+#include <net/sock.h>
+
+#define CREATE_TRACE_POINTS
+#include <trace/events/mctp.h>
+
+/* socket implementation */
+
+static void mctp_sk_expire_keys(struct timer_list *timer);
+
+static int mctp_release(struct socket *sock)
+{
+	struct sock *sk = sock->sk;
+
+	if (sk) {
+		sock->sk = NULL;
+		sk->sk_prot->close(sk, 0);
+	}
+
+	return 0;
+}
+
+/* Generic sockaddr checks, padding checks only so far */
+static bool mctp_sockaddr_is_ok(const struct sockaddr_mctp *addr)
+{
+	return !addr->__smctp_pad0 && !addr->__smctp_pad1;
+}
+
+static bool mctp_sockaddr_ext_is_ok(const struct sockaddr_mctp_ext *addr)
+{
+	return !addr->__smctp_pad0[0] &&
+	       !addr->__smctp_pad0[1] &&
+	       !addr->__smctp_pad0[2];
+}
+
+static int mctp_bind(struct socket *sock, struct sockaddr *addr, int addrlen)
+{
+	struct sock *sk = sock->sk;
+	struct mctp_sock *msk = container_of(sk, struct mctp_sock, sk);
+	struct sockaddr_mctp *smctp;
+	int rc;
+
+	if (addrlen < sizeof(*smctp))
+		return -EINVAL;
+
+	if (addr->sa_family != AF_MCTP)
+		return -EAFNOSUPPORT;
+
+	if (!capable(CAP_NET_BIND_SERVICE))
+		return -EACCES;
+
+	/* it's a valid sockaddr for MCTP, cast and do protocol checks */
+	smctp = (struct sockaddr_mctp *)addr;
+
+	if (!mctp_sockaddr_is_ok(smctp))
+		return -EINVAL;
+
+	lock_sock(sk);
+
+	/* TODO: allow rebind */
+	if (sk_hashed(sk)) {
+		rc = -EADDRINUSE;
+		goto out_release;
+	}
+	msk->bind_net = smctp->smctp_network;
+	msk->bind_addr = smctp->smctp_addr.s_addr;
+	msk->bind_type = smctp->smctp_type & 0x7f; /* ignore the IC bit */
+
+	rc = sk->sk_prot->hash(sk);
+
+out_release:
+	release_sock(sk);
+
+	return rc;
+}
+
+static int mctp_sendmsg(struct socket *sock, struct msghdr *msg, size_t len)
+{
+	DECLARE_SOCKADDR(struct sockaddr_mctp *, addr, msg->msg_name);
+	int rc, addrlen = msg->msg_namelen;
+	struct sock *sk = sock->sk;
+	struct mctp_sock *msk = container_of(sk, struct mctp_sock, sk);
+	struct mctp_skb_cb *cb;
+	struct mctp_route *rt;
+	struct sk_buff *skb = NULL;
+	int hlen;
+
+	if (addr) {
+		const u8 tagbits = MCTP_TAG_MASK | MCTP_TAG_OWNER |
+			MCTP_TAG_PREALLOC;
+
+		if (addrlen < sizeof(struct sockaddr_mctp))
+			return -EINVAL;
+		if (addr->smctp_family != AF_MCTP)
+			return -EINVAL;
+		if (!mctp_sockaddr_is_ok(addr))
+			return -EINVAL;
+		if (addr->smctp_tag & ~tagbits)
+			return -EINVAL;
+		/* can't preallocate a non-owned tag */
+		if (addr->smctp_tag & MCTP_TAG_PREALLOC &&
+		    !(addr->smctp_tag & MCTP_TAG_OWNER))
+			return -EINVAL;
+
+	} else {
+		/* TODO: connect()ed sockets */
+		return -EDESTADDRREQ;
+	}
+
+	if (!capable(CAP_NET_RAW))
+		return -EACCES;
+
+	if (addr->smctp_network == MCTP_NET_ANY)
+		addr->smctp_network = mctp_default_net(sock_net(sk));
+
+	/* direct addressing */
+	if (msk->addr_ext && addrlen >= sizeof(struct sockaddr_mctp_ext)) {
+		DECLARE_SOCKADDR(struct sockaddr_mctp_ext *,
+				 extaddr, msg->msg_name);
+		struct net_device *dev;
+
+		rc = -EINVAL;
+		rcu_read_lock();
+		dev = dev_get_by_index_rcu(sock_net(sk), extaddr->smctp_ifindex);
+		/* check for correct halen */
+		if (dev && extaddr->smctp_halen == dev->addr_len) {
+			hlen = LL_RESERVED_SPACE(dev) + sizeof(struct mctp_hdr);
+			rc = 0;
+		}
+		rcu_read_unlock();
+		if (rc)
+			goto err_free;
+		rt = NULL;
+	} else {
+		rt = mctp_route_lookup(sock_net(sk), addr->smctp_network,
+				       addr->smctp_addr.s_addr);
+		if (!rt) {
+			rc = -EHOSTUNREACH;
+			goto err_free;
+		}
+		hlen = LL_RESERVED_SPACE(rt->dev->dev) + sizeof(struct mctp_hdr);
+	}
+
+	skb = sock_alloc_send_skb(sk, hlen + 1 + len,
+				  msg->msg_flags & MSG_DONTWAIT, &rc);
+	if (!skb)
+		return rc;
+
+	skb_reserve(skb, hlen);
+
+	/* set type as fist byte in payload */
+	*(u8 *)skb_put(skb, 1) = addr->smctp_type;
+
+	rc = memcpy_from_msg((void *)skb_put(skb, len), msg, len);
+	if (rc < 0)
+		goto err_free;
+
+	/* set up cb */
+	cb = __mctp_cb(skb);
+	cb->net = addr->smctp_network;
+
+	if (!rt) {
+		/* fill extended address in cb */
+		DECLARE_SOCKADDR(struct sockaddr_mctp_ext *,
+				 extaddr, msg->msg_name);
+
+		if (!mctp_sockaddr_ext_is_ok(extaddr) ||
+		    extaddr->smctp_halen > sizeof(cb->haddr)) {
+			rc = -EINVAL;
+			goto err_free;
+		}
+
+		cb->ifindex = extaddr->smctp_ifindex;
+		/* smctp_halen is checked above */
+		cb->halen = extaddr->smctp_halen;
+		memcpy(cb->haddr, extaddr->smctp_haddr, cb->halen);
+	}
+
+	rc = mctp_local_output(sk, rt, skb, addr->smctp_addr.s_addr,
+			       addr->smctp_tag);
+
+	return rc ? : len;
+
+err_free:
+	kfree_skb(skb);
+	return rc;
+}
+
+static int mctp_recvmsg(struct socket *sock, struct msghdr *msg, size_t len,
+			int flags)
+{
+	DECLARE_SOCKADDR(struct sockaddr_mctp *, addr, msg->msg_name);
+	struct sock *sk = sock->sk;
+	struct mctp_sock *msk = container_of(sk, struct mctp_sock, sk);
+	struct sk_buff *skb;
+	size_t msglen;
+	u8 type;
+	int rc;
+
+	if (flags & ~(MSG_DONTWAIT | MSG_TRUNC | MSG_PEEK))
+		return -EOPNOTSUPP;
+
+	skb = skb_recv_datagram(sk, flags, &rc);
+	if (!skb)
+		return rc;
+
+	if (!skb->len) {
+		rc = 0;
+		goto out_free;
+	}
+
+	/* extract message type, remove from data */
+	type = *((u8 *)skb->data);
+	msglen = skb->len - 1;
+
+	if (len < msglen)
+		msg->msg_flags |= MSG_TRUNC;
+	else
+		len = msglen;
+
+	rc = skb_copy_datagram_msg(skb, 1, msg, len);
+	if (rc < 0)
+		goto out_free;
+
+	sock_recv_cmsgs(msg, sk, skb);
+
+	if (addr) {
+		struct mctp_skb_cb *cb = mctp_cb(skb);
+		/* TODO: expand mctp_skb_cb for header fields? */
+		struct mctp_hdr *hdr = mctp_hdr(skb);
+
+		addr = msg->msg_name;
+		addr->smctp_family = AF_MCTP;
+		addr->__smctp_pad0 = 0;
+		addr->smctp_network = cb->net;
+		addr->smctp_addr.s_addr = hdr->src;
+		addr->smctp_type = type;
+		addr->smctp_tag = hdr->flags_seq_tag &
+					(MCTP_HDR_TAG_MASK | MCTP_HDR_FLAG_TO);
+		addr->__smctp_pad1 = 0;
+		msg->msg_namelen = sizeof(*addr);
+
+		if (msk->addr_ext) {
+			DECLARE_SOCKADDR(struct sockaddr_mctp_ext *, ae,
+					 msg->msg_name);
+			msg->msg_namelen = sizeof(*ae);
+			ae->smctp_ifindex = cb->ifindex;
+			ae->smctp_halen = cb->halen;
+			memset(ae->__smctp_pad0, 0x0, sizeof(ae->__smctp_pad0));
+			memset(ae->smctp_haddr, 0x0, sizeof(ae->smctp_haddr));
+			memcpy(ae->smctp_haddr, cb->haddr, cb->halen);
+		}
+	}
+
+	rc = len;
+
+	if (flags & MSG_TRUNC)
+		rc = msglen;
+
+out_free:
+	skb_free_datagram(sk, skb);
+	return rc;
+}
+
+/* We're done with the key; invalidate, stop reassembly, and remove from lists.
+ */
+static void __mctp_key_remove(struct mctp_sk_key *key, struct net *net,
+			      unsigned long flags, unsigned long reason)
+__releases(&key->lock)
+__must_hold(&net->mctp.keys_lock)
+{
+	struct sk_buff *skb;
+
+	trace_mctp_key_release(key, reason);
+	skb = key->reasm_head;
+	key->reasm_head = NULL;
+	key->reasm_dead = true;
+	key->valid = false;
+	mctp_dev_release_key(key->dev, key);
+	spin_unlock_irqrestore(&key->lock, flags);
+
+	if (!hlist_unhashed(&key->hlist)) {
+		hlist_del_init(&key->hlist);
+		hlist_del_init(&key->sklist);
+		/* unref for the lists */
+		mctp_key_unref(key);
+	}
+
+	kfree_skb(skb);
+}
+
+static int mctp_setsockopt(struct socket *sock, int level, int optname,
+			   sockptr_t optval, unsigned int optlen)
+{
+	struct mctp_sock *msk = container_of(sock->sk, struct mctp_sock, sk);
+	int val;
+
+	if (level != SOL_MCTP)
+		return -EINVAL;
+
+	if (optname == MCTP_OPT_ADDR_EXT) {
+		if (optlen != sizeof(int))
+			return -EINVAL;
+		if (copy_from_sockptr(&val, optval, sizeof(int)))
+			return -EFAULT;
+		msk->addr_ext = val;
+		return 0;
+	}
+
+	return -ENOPROTOOPT;
+}
+
+static int mctp_getsockopt(struct socket *sock, int level, int optname,
+			   char __user *optval, int __user *optlen)
+{
+	struct mctp_sock *msk = container_of(sock->sk, struct mctp_sock, sk);
+	int len, val;
+
+	if (level != SOL_MCTP)
+		return -EINVAL;
+
+	if (get_user(len, optlen))
+		return -EFAULT;
+
+	if (optname == MCTP_OPT_ADDR_EXT) {
+		if (len != sizeof(int))
+			return -EINVAL;
+		val = !!msk->addr_ext;
+		if (copy_to_user(optval, &val, len))
+			return -EFAULT;
+		return 0;
+	}
+
+	return -EINVAL;
+}
+
+static int mctp_ioctl_alloctag(struct mctp_sock *msk, unsigned long arg)
+{
+	struct net *net = sock_net(&msk->sk);
+	struct mctp_sk_key *key = NULL;
+	struct mctp_ioc_tag_ctl ctl;
+	unsigned long flags;
+	u8 tag;
+
+	if (copy_from_user(&ctl, (void __user *)arg, sizeof(ctl)))
+		return -EFAULT;
+
+	if (ctl.tag)
+		return -EINVAL;
+
+	if (ctl.flags)
+		return -EINVAL;
+
+	key = mctp_alloc_local_tag(msk, ctl.peer_addr, MCTP_ADDR_ANY,
+				   true, &tag);
+	if (IS_ERR(key))
+		return PTR_ERR(key);
+
+	ctl.tag = tag | MCTP_TAG_OWNER | MCTP_TAG_PREALLOC;
+	if (copy_to_user((void __user *)arg, &ctl, sizeof(ctl))) {
+		unsigned long fl2;
+		/* Unwind our key allocation: the keys list lock needs to be
+		 * taken before the individual key locks, and we need a valid
+		 * flags value (fl2) to pass to __mctp_key_remove, hence the
+		 * second spin_lock_irqsave() rather than a plain spin_lock().
+		 */
+		spin_lock_irqsave(&net->mctp.keys_lock, flags);
+		spin_lock_irqsave(&key->lock, fl2);
+		__mctp_key_remove(key, net, fl2, MCTP_TRACE_KEY_DROPPED);
+		mctp_key_unref(key);
+		spin_unlock_irqrestore(&net->mctp.keys_lock, flags);
+		return -EFAULT;
+	}
+
+	mctp_key_unref(key);
+	return 0;
+}
+
+static int mctp_ioctl_droptag(struct mctp_sock *msk, unsigned long arg)
+{
+	struct net *net = sock_net(&msk->sk);
+	struct mctp_ioc_tag_ctl ctl;
+	unsigned long flags, fl2;
+	struct mctp_sk_key *key;
+	struct hlist_node *tmp;
+	int rc;
+	u8 tag;
+
+	if (copy_from_user(&ctl, (void __user *)arg, sizeof(ctl)))
+		return -EFAULT;
+
+	if (ctl.flags)
+		return -EINVAL;
+
+	/* Must be a local tag, TO set, preallocated */
+	if ((ctl.tag & ~MCTP_TAG_MASK) != (MCTP_TAG_OWNER | MCTP_TAG_PREALLOC))
+		return -EINVAL;
+
+	tag = ctl.tag & MCTP_TAG_MASK;
+	rc = -EINVAL;
+
+	spin_lock_irqsave(&net->mctp.keys_lock, flags);
+	hlist_for_each_entry_safe(key, tmp, &msk->keys, sklist) {
+		/* we do an irqsave here, even though we know the irq state,
+		 * so we have the flags to pass to __mctp_key_remove
+		 */
+		spin_lock_irqsave(&key->lock, fl2);
+		if (key->manual_alloc &&
+		    ctl.peer_addr == key->peer_addr &&
+		    tag == key->tag) {
+			__mctp_key_remove(key, net, fl2,
+					  MCTP_TRACE_KEY_DROPPED);
+			rc = 0;
+		} else {
+			spin_unlock_irqrestore(&key->lock, fl2);
+		}
+	}
+	spin_unlock_irqrestore(&net->mctp.keys_lock, flags);
+
+	return rc;
+}
+
+static int mctp_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg)
+{
+	struct mctp_sock *msk = container_of(sock->sk, struct mctp_sock, sk);
+
+	switch (cmd) {
+	case SIOCMCTPALLOCTAG:
+		return mctp_ioctl_alloctag(msk, arg);
+	case SIOCMCTPDROPTAG:
+		return mctp_ioctl_droptag(msk, arg);
+	}
+
+	return -EINVAL;
+}
+
+#ifdef CONFIG_COMPAT
+static int mctp_compat_ioctl(struct socket *sock, unsigned int cmd,
+			     unsigned long arg)
+{
+	void __user *argp = compat_ptr(arg);
+
+	switch (cmd) {
+	/* These have compatible ptr layouts */
+	case SIOCMCTPALLOCTAG:
+	case SIOCMCTPDROPTAG:
+		return mctp_ioctl(sock, cmd, (unsigned long)argp);
+	}
+
+	return -ENOIOCTLCMD;
+}
+#endif
+
+static const struct proto_ops mctp_dgram_ops = {
+	.family		= PF_MCTP,
+	.release	= mctp_release,
+	.bind		= mctp_bind,
+	.connect	= sock_no_connect,
+	.socketpair	= sock_no_socketpair,
+	.accept		= sock_no_accept,
+	.getname	= sock_no_getname,
+	.poll		= datagram_poll,
+	.ioctl		= mctp_ioctl,
+	.gettstamp	= sock_gettstamp,
+	.listen		= sock_no_listen,
+	.shutdown	= sock_no_shutdown,
+	.setsockopt	= mctp_setsockopt,
+	.getsockopt	= mctp_getsockopt,
+	.sendmsg	= mctp_sendmsg,
+	.recvmsg	= mctp_recvmsg,
+	.mmap		= sock_no_mmap,
+	.sendpage	= sock_no_sendpage,
+#ifdef CONFIG_COMPAT
+	.compat_ioctl	= mctp_compat_ioctl,
+#endif
+};
+
+static void mctp_sk_expire_keys(struct timer_list *timer)
+{
+	struct mctp_sock *msk = container_of(timer, struct mctp_sock,
+					     key_expiry);
+	struct net *net = sock_net(&msk->sk);
+	unsigned long next_expiry, flags, fl2;
+	struct mctp_sk_key *key;
+	struct hlist_node *tmp;
+	bool next_expiry_valid = false;
+
+	spin_lock_irqsave(&net->mctp.keys_lock, flags);
+
+	hlist_for_each_entry_safe(key, tmp, &msk->keys, sklist) {
+		/* don't expire. manual_alloc is immutable, no locking
+		 * required.
+		 */
+		if (key->manual_alloc)
+			continue;
+
+		spin_lock_irqsave(&key->lock, fl2);
+		if (!time_after_eq(key->expiry, jiffies)) {
+			__mctp_key_remove(key, net, fl2,
+					  MCTP_TRACE_KEY_TIMEOUT);
+			continue;
+		}
+
+		if (next_expiry_valid) {
+			if (time_before(key->expiry, next_expiry))
+				next_expiry = key->expiry;
+		} else {
+			next_expiry = key->expiry;
+			next_expiry_valid = true;
+		}
+		spin_unlock_irqrestore(&key->lock, fl2);
+	}
+
+	spin_unlock_irqrestore(&net->mctp.keys_lock, flags);
+
+	if (next_expiry_valid)
+		mod_timer(timer, next_expiry);
+}
+
+static int mctp_sk_init(struct sock *sk)
+{
+	struct mctp_sock *msk = container_of(sk, struct mctp_sock, sk);
+
+	INIT_HLIST_HEAD(&msk->keys);
+	timer_setup(&msk->key_expiry, mctp_sk_expire_keys, 0);
+	return 0;
+}
+
+static void mctp_sk_close(struct sock *sk, long timeout)
+{
+	sk_common_release(sk);
+}
+
+static int mctp_sk_hash(struct sock *sk)
+{
+	struct net *net = sock_net(sk);
+
+	mutex_lock(&net->mctp.bind_lock);
+	sk_add_node_rcu(sk, &net->mctp.binds);
+	mutex_unlock(&net->mctp.bind_lock);
+
+	return 0;
+}
+
+static void mctp_sk_unhash(struct sock *sk)
+{
+	struct mctp_sock *msk = container_of(sk, struct mctp_sock, sk);
+	struct net *net = sock_net(sk);
+	unsigned long flags, fl2;
+	struct mctp_sk_key *key;
+	struct hlist_node *tmp;
+
+	/* remove from any type-based binds */
+	mutex_lock(&net->mctp.bind_lock);
+	sk_del_node_init_rcu(sk);
+	mutex_unlock(&net->mctp.bind_lock);
+
+	/* remove tag allocations */
+	spin_lock_irqsave(&net->mctp.keys_lock, flags);
+	hlist_for_each_entry_safe(key, tmp, &msk->keys, sklist) {
+		spin_lock_irqsave(&key->lock, fl2);
+		__mctp_key_remove(key, net, fl2, MCTP_TRACE_KEY_CLOSED);
+	}
+	sock_set_flag(sk, SOCK_DEAD);
+	spin_unlock_irqrestore(&net->mctp.keys_lock, flags);
+
+	/* Since there are no more tag allocations (we have removed all of the
+	 * keys), stop any pending expiry events. the timer cannot be re-queued
+	 * as the sk is no longer observable
+	 */
+	del_timer_sync(&msk->key_expiry);
+}
+
+static void mctp_sk_destruct(struct sock *sk)
+{
+	skb_queue_purge(&sk->sk_receive_queue);
+}
+
+static struct proto mctp_proto = {
+	.name		= "MCTP",
+	.owner		= THIS_MODULE,
+	.obj_size	= sizeof(struct mctp_sock),
+	.init		= mctp_sk_init,
+	.close		= mctp_sk_close,
+	.hash		= mctp_sk_hash,
+	.unhash		= mctp_sk_unhash,
+};
+
+static int mctp_pf_create(struct net *net, struct socket *sock,
+			  int protocol, int kern)
+{
+	const struct proto_ops *ops;
+	struct proto *proto;
+	struct sock *sk;
+	int rc;
+
+	if (protocol)
+		return -EPROTONOSUPPORT;
+
+	/* only datagram sockets are supported */
+	if (sock->type != SOCK_DGRAM)
+		return -ESOCKTNOSUPPORT;
+
+	proto = &mctp_proto;
+	ops = &mctp_dgram_ops;
+
+	sock->state = SS_UNCONNECTED;
+	sock->ops = ops;
+
+	sk = sk_alloc(net, PF_MCTP, GFP_KERNEL, proto, kern);
+	if (!sk)
+		return -ENOMEM;
+
+	sock_init_data(sock, sk);
+	sk->sk_destruct = mctp_sk_destruct;
+
+	rc = 0;
+	if (sk->sk_prot->init)
+		rc = sk->sk_prot->init(sk);
+
+	if (rc)
+		goto err_sk_put;
+
+	return 0;
+
+err_sk_put:
+	sock_orphan(sk);
+	sock_put(sk);
+	return rc;
+}
+
+static struct net_proto_family mctp_pf = {
+	.family = PF_MCTP,
+	.create = mctp_pf_create,
+	.owner = THIS_MODULE,
+};
+
+static __init int mctp_init(void)
+{
+	int rc;
+
+	/* ensure our uapi tag definitions match the header format */
+	BUILD_BUG_ON(MCTP_TAG_OWNER != MCTP_HDR_FLAG_TO);
+	BUILD_BUG_ON(MCTP_TAG_MASK != MCTP_HDR_TAG_MASK);
+
+	pr_info("mctp: management component transport protocol core\n");
+
+	rc = sock_register(&mctp_pf);
+	if (rc)
+		return rc;
+
+	rc = proto_register(&mctp_proto, 0);
+	if (rc)
+		goto err_unreg_sock;
+
+	rc = mctp_routes_init();
+	if (rc)
+		goto err_unreg_proto;
+
+	rc = mctp_neigh_init();
+	if (rc)
+		goto err_unreg_routes;
+
+	mctp_device_init();
+
+	return 0;
+
+err_unreg_routes:
+	mctp_routes_exit();
+err_unreg_proto:
+	proto_unregister(&mctp_proto);
+err_unreg_sock:
+	sock_unregister(PF_MCTP);
+
+	return rc;
+}
+
+static __exit void mctp_exit(void)
+{
+	mctp_device_exit();
+	mctp_neigh_exit();
+	mctp_routes_exit();
+	proto_unregister(&mctp_proto);
+	sock_unregister(PF_MCTP);
+}
+
+subsys_initcall(mctp_init);
+module_exit(mctp_exit);
+
+MODULE_DESCRIPTION("MCTP core");
+MODULE_LICENSE("GPL v2");
+MODULE_AUTHOR("Jeremy Kerr <jk@codeconstruct.com.au>");
+
+MODULE_ALIAS_NETPROTO(PF_MCTP);
diff --git a/net/mctp/device.c b/net/mctp/device.c
new file mode 100644
index 000000000..acb97b257
--- /dev/null
+++ b/net/mctp/device.c
@@ -0,0 +1,548 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Management Component Transport Protocol (MCTP) - device implementation.
+ *
+ * Copyright (c) 2021 Code Construct
+ * Copyright (c) 2021 Google
+ */
+
+#include <linux/if_arp.h>
+#include <linux/if_link.h>
+#include <linux/mctp.h>
+#include <linux/netdevice.h>
+#include <linux/rcupdate.h>
+#include <linux/rtnetlink.h>
+
+#include <net/addrconf.h>
+#include <net/netlink.h>
+#include <net/mctp.h>
+#include <net/mctpdevice.h>
+#include <net/sock.h>
+
+struct mctp_dump_cb {
+	int h;
+	int idx;
+	size_t a_idx;
+};
+
+/* unlocked: caller must hold rcu_read_lock.
+ * Returned mctp_dev has its refcount incremented, or NULL if unset.
+ */
+struct mctp_dev *__mctp_dev_get(const struct net_device *dev)
+{
+	struct mctp_dev *mdev = rcu_dereference(dev->mctp_ptr);
+
+	/* RCU guarantees that any mdev is still live.
+	 * Zero refcount implies a pending free, return NULL.
+	 */
+	if (mdev)
+		if (!refcount_inc_not_zero(&mdev->refs))
+			return NULL;
+	return mdev;
+}
+
+/* Returned mctp_dev does not have refcount incremented. The returned pointer
+ * remains live while rtnl_lock is held, as that prevents mctp_unregister()
+ */
+struct mctp_dev *mctp_dev_get_rtnl(const struct net_device *dev)
+{
+	return rtnl_dereference(dev->mctp_ptr);
+}
+
+static int mctp_addrinfo_size(void)
+{
+	return NLMSG_ALIGN(sizeof(struct ifaddrmsg))
+		+ nla_total_size(1) // IFA_LOCAL
+		+ nla_total_size(1) // IFA_ADDRESS
+		;
+}
+
+/* flag should be NLM_F_MULTI for dump calls */
+static int mctp_fill_addrinfo(struct sk_buff *skb,
+			      struct mctp_dev *mdev, mctp_eid_t eid,
+			      int msg_type, u32 portid, u32 seq, int flag)
+{
+	struct ifaddrmsg *hdr;
+	struct nlmsghdr *nlh;
+
+	nlh = nlmsg_put(skb, portid, seq,
+			msg_type, sizeof(*hdr), flag);
+	if (!nlh)
+		return -EMSGSIZE;
+
+	hdr = nlmsg_data(nlh);
+	hdr->ifa_family = AF_MCTP;
+	hdr->ifa_prefixlen = 0;
+	hdr->ifa_flags = 0;
+	hdr->ifa_scope = 0;
+	hdr->ifa_index = mdev->dev->ifindex;
+
+	if (nla_put_u8(skb, IFA_LOCAL, eid))
+		goto cancel;
+
+	if (nla_put_u8(skb, IFA_ADDRESS, eid))
+		goto cancel;
+
+	nlmsg_end(skb, nlh);
+
+	return 0;
+
+cancel:
+	nlmsg_cancel(skb, nlh);
+	return -EMSGSIZE;
+}
+
+static int mctp_dump_dev_addrinfo(struct mctp_dev *mdev, struct sk_buff *skb,
+				  struct netlink_callback *cb)
+{
+	struct mctp_dump_cb *mcb = (void *)cb->ctx;
+	u32 portid, seq;
+	int rc = 0;
+
+	portid = NETLINK_CB(cb->skb).portid;
+	seq = cb->nlh->nlmsg_seq;
+	for (; mcb->a_idx < mdev->num_addrs; mcb->a_idx++) {
+		rc = mctp_fill_addrinfo(skb, mdev, mdev->addrs[mcb->a_idx],
+					RTM_NEWADDR, portid, seq, NLM_F_MULTI);
+		if (rc < 0)
+			break;
+	}
+
+	return rc;
+}
+
+static int mctp_dump_addrinfo(struct sk_buff *skb, struct netlink_callback *cb)
+{
+	struct mctp_dump_cb *mcb = (void *)cb->ctx;
+	struct net *net = sock_net(skb->sk);
+	struct hlist_head *head;
+	struct net_device *dev;
+	struct ifaddrmsg *hdr;
+	struct mctp_dev *mdev;
+	int ifindex;
+	int idx = 0, rc;
+
+	hdr = nlmsg_data(cb->nlh);
+	// filter by ifindex if requested
+	ifindex = hdr->ifa_index;
+
+	rcu_read_lock();
+	for (; mcb->h < NETDEV_HASHENTRIES; mcb->h++, mcb->idx = 0) {
+		idx = 0;
+		head = &net->dev_index_head[mcb->h];
+		hlist_for_each_entry_rcu(dev, head, index_hlist) {
+			if (idx >= mcb->idx &&
+			    (ifindex == 0 || ifindex == dev->ifindex)) {
+				mdev = __mctp_dev_get(dev);
+				if (mdev) {
+					rc = mctp_dump_dev_addrinfo(mdev,
+								    skb, cb);
+					mctp_dev_put(mdev);
+					// Error indicates full buffer, this
+					// callback will get retried.
+					if (rc < 0)
+						goto out;
+				}
+			}
+			idx++;
+			// reset for next iteration
+			mcb->a_idx = 0;
+		}
+	}
+out:
+	rcu_read_unlock();
+	mcb->idx = idx;
+
+	return skb->len;
+}
+
+static void mctp_addr_notify(struct mctp_dev *mdev, mctp_eid_t eid, int msg_type,
+			     struct sk_buff *req_skb, struct nlmsghdr *req_nlh)
+{
+	u32 portid = NETLINK_CB(req_skb).portid;
+	struct net *net = dev_net(mdev->dev);
+	struct sk_buff *skb;
+	int rc = -ENOBUFS;
+
+	skb = nlmsg_new(mctp_addrinfo_size(), GFP_KERNEL);
+	if (!skb)
+		goto out;
+
+	rc = mctp_fill_addrinfo(skb, mdev, eid, msg_type,
+				portid, req_nlh->nlmsg_seq, 0);
+	if (rc < 0) {
+		WARN_ON_ONCE(rc == -EMSGSIZE);
+		goto out;
+	}
+
+	rtnl_notify(skb, net, portid, RTNLGRP_MCTP_IFADDR, req_nlh, GFP_KERNEL);
+	return;
+out:
+	kfree_skb(skb);
+	rtnl_set_sk_err(net, RTNLGRP_MCTP_IFADDR, rc);
+}
+
+static const struct nla_policy ifa_mctp_policy[IFA_MAX + 1] = {
+	[IFA_ADDRESS]		= { .type = NLA_U8 },
+	[IFA_LOCAL]		= { .type = NLA_U8 },
+};
+
+static int mctp_rtm_newaddr(struct sk_buff *skb, struct nlmsghdr *nlh,
+			    struct netlink_ext_ack *extack)
+{
+	struct net *net = sock_net(skb->sk);
+	struct nlattr *tb[IFA_MAX + 1];
+	struct net_device *dev;
+	struct mctp_addr *addr;
+	struct mctp_dev *mdev;
+	struct ifaddrmsg *ifm;
+	unsigned long flags;
+	u8 *tmp_addrs;
+	int rc;
+
+	rc = nlmsg_parse(nlh, sizeof(*ifm), tb, IFA_MAX, ifa_mctp_policy,
+			 extack);
+	if (rc < 0)
+		return rc;
+
+	ifm = nlmsg_data(nlh);
+
+	if (tb[IFA_LOCAL])
+		addr = nla_data(tb[IFA_LOCAL]);
+	else if (tb[IFA_ADDRESS])
+		addr = nla_data(tb[IFA_ADDRESS]);
+	else
+		return -EINVAL;
+
+	/* find device */
+	dev = __dev_get_by_index(net, ifm->ifa_index);
+	if (!dev)
+		return -ENODEV;
+
+	mdev = mctp_dev_get_rtnl(dev);
+	if (!mdev)
+		return -ENODEV;
+
+	if (!mctp_address_unicast(addr->s_addr))
+		return -EINVAL;
+
+	/* Prevent duplicates. Under RTNL so don't need to lock for reading */
+	if (memchr(mdev->addrs, addr->s_addr, mdev->num_addrs))
+		return -EEXIST;
+
+	tmp_addrs = kmalloc(mdev->num_addrs + 1, GFP_KERNEL);
+	if (!tmp_addrs)
+		return -ENOMEM;
+	memcpy(tmp_addrs, mdev->addrs, mdev->num_addrs);
+	tmp_addrs[mdev->num_addrs] = addr->s_addr;
+
+	/* Lock to write */
+	spin_lock_irqsave(&mdev->addrs_lock, flags);
+	mdev->num_addrs++;
+	swap(mdev->addrs, tmp_addrs);
+	spin_unlock_irqrestore(&mdev->addrs_lock, flags);
+
+	kfree(tmp_addrs);
+
+	mctp_addr_notify(mdev, addr->s_addr, RTM_NEWADDR, skb, nlh);
+	mctp_route_add_local(mdev, addr->s_addr);
+
+	return 0;
+}
+
+static int mctp_rtm_deladdr(struct sk_buff *skb, struct nlmsghdr *nlh,
+			    struct netlink_ext_ack *extack)
+{
+	struct net *net = sock_net(skb->sk);
+	struct nlattr *tb[IFA_MAX + 1];
+	struct net_device *dev;
+	struct mctp_addr *addr;
+	struct mctp_dev *mdev;
+	struct ifaddrmsg *ifm;
+	unsigned long flags;
+	u8 *pos;
+	int rc;
+
+	rc = nlmsg_parse(nlh, sizeof(*ifm), tb, IFA_MAX, ifa_mctp_policy,
+			 extack);
+	if (rc < 0)
+		return rc;
+
+	ifm = nlmsg_data(nlh);
+
+	if (tb[IFA_LOCAL])
+		addr = nla_data(tb[IFA_LOCAL]);
+	else if (tb[IFA_ADDRESS])
+		addr = nla_data(tb[IFA_ADDRESS]);
+	else
+		return -EINVAL;
+
+	/* find device */
+	dev = __dev_get_by_index(net, ifm->ifa_index);
+	if (!dev)
+		return -ENODEV;
+
+	mdev = mctp_dev_get_rtnl(dev);
+	if (!mdev)
+		return -ENODEV;
+
+	pos = memchr(mdev->addrs, addr->s_addr, mdev->num_addrs);
+	if (!pos)
+		return -ENOENT;
+
+	rc = mctp_route_remove_local(mdev, addr->s_addr);
+	// we can ignore -ENOENT in the case a route was already removed
+	if (rc < 0 && rc != -ENOENT)
+		return rc;
+
+	spin_lock_irqsave(&mdev->addrs_lock, flags);
+	memmove(pos, pos + 1, mdev->num_addrs - 1 - (pos - mdev->addrs));
+	mdev->num_addrs--;
+	spin_unlock_irqrestore(&mdev->addrs_lock, flags);
+
+	mctp_addr_notify(mdev, addr->s_addr, RTM_DELADDR, skb, nlh);
+
+	return 0;
+}
+
+void mctp_dev_hold(struct mctp_dev *mdev)
+{
+	refcount_inc(&mdev->refs);
+}
+
+void mctp_dev_put(struct mctp_dev *mdev)
+{
+	if (mdev && refcount_dec_and_test(&mdev->refs)) {
+		kfree(mdev->addrs);
+		dev_put(mdev->dev);
+		kfree_rcu(mdev, rcu);
+	}
+}
+
+void mctp_dev_release_key(struct mctp_dev *dev, struct mctp_sk_key *key)
+	__must_hold(&key->lock)
+{
+	if (!dev)
+		return;
+	if (dev->ops && dev->ops->release_flow)
+		dev->ops->release_flow(dev, key);
+	key->dev = NULL;
+	mctp_dev_put(dev);
+}
+
+void mctp_dev_set_key(struct mctp_dev *dev, struct mctp_sk_key *key)
+	__must_hold(&key->lock)
+{
+	mctp_dev_hold(dev);
+	key->dev = dev;
+}
+
+static struct mctp_dev *mctp_add_dev(struct net_device *dev)
+{
+	struct mctp_dev *mdev;
+
+	ASSERT_RTNL();
+
+	mdev = kzalloc(sizeof(*mdev), GFP_KERNEL);
+	if (!mdev)
+		return ERR_PTR(-ENOMEM);
+
+	spin_lock_init(&mdev->addrs_lock);
+
+	mdev->net = mctp_default_net(dev_net(dev));
+
+	/* associate to net_device */
+	refcount_set(&mdev->refs, 1);
+	rcu_assign_pointer(dev->mctp_ptr, mdev);
+
+	dev_hold(dev);
+	mdev->dev = dev;
+
+	return mdev;
+}
+
+static int mctp_fill_link_af(struct sk_buff *skb,
+			     const struct net_device *dev, u32 ext_filter_mask)
+{
+	struct mctp_dev *mdev;
+
+	mdev = mctp_dev_get_rtnl(dev);
+	if (!mdev)
+		return -ENODATA;
+	if (nla_put_u32(skb, IFLA_MCTP_NET, mdev->net))
+		return -EMSGSIZE;
+	return 0;
+}
+
+static size_t mctp_get_link_af_size(const struct net_device *dev,
+				    u32 ext_filter_mask)
+{
+	struct mctp_dev *mdev;
+	unsigned int ret;
+
+	/* caller holds RCU */
+	mdev = __mctp_dev_get(dev);
+	if (!mdev)
+		return 0;
+	ret = nla_total_size(4); /* IFLA_MCTP_NET */
+	mctp_dev_put(mdev);
+	return ret;
+}
+
+static const struct nla_policy ifla_af_mctp_policy[IFLA_MCTP_MAX + 1] = {
+	[IFLA_MCTP_NET]		= { .type = NLA_U32 },
+};
+
+static int mctp_set_link_af(struct net_device *dev, const struct nlattr *attr,
+			    struct netlink_ext_ack *extack)
+{
+	struct nlattr *tb[IFLA_MCTP_MAX + 1];
+	struct mctp_dev *mdev;
+	int rc;
+
+	rc = nla_parse_nested(tb, IFLA_MCTP_MAX, attr, ifla_af_mctp_policy,
+			      NULL);
+	if (rc)
+		return rc;
+
+	mdev = mctp_dev_get_rtnl(dev);
+	if (!mdev)
+		return 0;
+
+	if (tb[IFLA_MCTP_NET])
+		WRITE_ONCE(mdev->net, nla_get_u32(tb[IFLA_MCTP_NET]));
+
+	return 0;
+}
+
+/* Matches netdev types that should have MCTP handling */
+static bool mctp_known(struct net_device *dev)
+{
+	/* only register specific types (inc. NONE for TUN devices) */
+	return dev->type == ARPHRD_MCTP ||
+		   dev->type == ARPHRD_LOOPBACK ||
+		   dev->type == ARPHRD_NONE;
+}
+
+static void mctp_unregister(struct net_device *dev)
+{
+	struct mctp_dev *mdev;
+
+	mdev = mctp_dev_get_rtnl(dev);
+	if (!mdev)
+		return;
+
+	RCU_INIT_POINTER(mdev->dev->mctp_ptr, NULL);
+
+	mctp_route_remove_dev(mdev);
+	mctp_neigh_remove_dev(mdev);
+
+	mctp_dev_put(mdev);
+}
+
+static int mctp_register(struct net_device *dev)
+{
+	struct mctp_dev *mdev;
+
+	/* Already registered? */
+	if (rtnl_dereference(dev->mctp_ptr))
+		return 0;
+
+	/* only register specific types */
+	if (!mctp_known(dev))
+		return 0;
+
+	mdev = mctp_add_dev(dev);
+	if (IS_ERR(mdev))
+		return PTR_ERR(mdev);
+
+	return 0;
+}
+
+static int mctp_dev_notify(struct notifier_block *this, unsigned long event,
+			   void *ptr)
+{
+	struct net_device *dev = netdev_notifier_info_to_dev(ptr);
+	int rc;
+
+	switch (event) {
+	case NETDEV_REGISTER:
+		rc = mctp_register(dev);
+		if (rc)
+			return notifier_from_errno(rc);
+		break;
+	case NETDEV_UNREGISTER:
+		mctp_unregister(dev);
+		break;
+	}
+
+	return NOTIFY_OK;
+}
+
+static int mctp_register_netdevice(struct net_device *dev,
+				   const struct mctp_netdev_ops *ops)
+{
+	struct mctp_dev *mdev;
+
+	mdev = mctp_add_dev(dev);
+	if (IS_ERR(mdev))
+		return PTR_ERR(mdev);
+
+	mdev->ops = ops;
+
+	return register_netdevice(dev);
+}
+
+int mctp_register_netdev(struct net_device *dev,
+			 const struct mctp_netdev_ops *ops)
+{
+	int rc;
+
+	rtnl_lock();
+	rc = mctp_register_netdevice(dev, ops);
+	rtnl_unlock();
+
+	return rc;
+}
+EXPORT_SYMBOL_GPL(mctp_register_netdev);
+
+void mctp_unregister_netdev(struct net_device *dev)
+{
+	unregister_netdev(dev);
+}
+EXPORT_SYMBOL_GPL(mctp_unregister_netdev);
+
+static struct rtnl_af_ops mctp_af_ops = {
+	.family = AF_MCTP,
+	.fill_link_af = mctp_fill_link_af,
+	.get_link_af_size = mctp_get_link_af_size,
+	.set_link_af = mctp_set_link_af,
+};
+
+static struct notifier_block mctp_dev_nb = {
+	.notifier_call = mctp_dev_notify,
+	.priority = ADDRCONF_NOTIFY_PRIORITY,
+};
+
+void __init mctp_device_init(void)
+{
+	register_netdevice_notifier(&mctp_dev_nb);
+
+	rtnl_register_module(THIS_MODULE, PF_MCTP, RTM_GETADDR,
+			     NULL, mctp_dump_addrinfo, 0);
+	rtnl_register_module(THIS_MODULE, PF_MCTP, RTM_NEWADDR,
+			     mctp_rtm_newaddr, NULL, 0);
+	rtnl_register_module(THIS_MODULE, PF_MCTP, RTM_DELADDR,
+			     mctp_rtm_deladdr, NULL, 0);
+	rtnl_af_register(&mctp_af_ops);
+}
+
+void __exit mctp_device_exit(void)
+{
+	rtnl_af_unregister(&mctp_af_ops);
+	rtnl_unregister(PF_MCTP, RTM_DELADDR);
+	rtnl_unregister(PF_MCTP, RTM_NEWADDR);
+	rtnl_unregister(PF_MCTP, RTM_GETADDR);
+
+	unregister_netdevice_notifier(&mctp_dev_nb);
+}
diff --git a/net/mctp/neigh.c b/net/mctp/neigh.c
new file mode 100644
index 000000000..ffa0f9e09
--- /dev/null
+++ b/net/mctp/neigh.c
@@ -0,0 +1,343 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Management Component Transport Protocol (MCTP) - routing
+ * implementation.
+ *
+ * This is currently based on a simple routing table, with no dst cache. The
+ * number of routes should stay fairly small, so the lookup cost is small.
+ *
+ * Copyright (c) 2021 Code Construct
+ * Copyright (c) 2021 Google
+ */
+
+#include <linux/idr.h>
+#include <linux/mctp.h>
+#include <linux/netdevice.h>
+#include <linux/rtnetlink.h>
+#include <linux/skbuff.h>
+
+#include <net/mctp.h>
+#include <net/mctpdevice.h>
+#include <net/netlink.h>
+#include <net/sock.h>
+
+static int mctp_neigh_add(struct mctp_dev *mdev, mctp_eid_t eid,
+			  enum mctp_neigh_source source,
+			  size_t lladdr_len, const void *lladdr)
+{
+	struct net *net = dev_net(mdev->dev);
+	struct mctp_neigh *neigh;
+	int rc;
+
+	mutex_lock(&net->mctp.neigh_lock);
+	if (mctp_neigh_lookup(mdev, eid, NULL) == 0) {
+		rc = -EEXIST;
+		goto out;
+	}
+
+	if (lladdr_len > sizeof(neigh->ha)) {
+		rc = -EINVAL;
+		goto out;
+	}
+
+	neigh = kzalloc(sizeof(*neigh), GFP_KERNEL);
+	if (!neigh) {
+		rc = -ENOMEM;
+		goto out;
+	}
+	INIT_LIST_HEAD(&neigh->list);
+	neigh->dev = mdev;
+	mctp_dev_hold(neigh->dev);
+	neigh->eid = eid;
+	neigh->source = source;
+	memcpy(neigh->ha, lladdr, lladdr_len);
+
+	list_add_rcu(&neigh->list, &net->mctp.neighbours);
+	rc = 0;
+out:
+	mutex_unlock(&net->mctp.neigh_lock);
+	return rc;
+}
+
+static void __mctp_neigh_free(struct rcu_head *rcu)
+{
+	struct mctp_neigh *neigh = container_of(rcu, struct mctp_neigh, rcu);
+
+	mctp_dev_put(neigh->dev);
+	kfree(neigh);
+}
+
+/* Removes all neighbour entries referring to a device */
+void mctp_neigh_remove_dev(struct mctp_dev *mdev)
+{
+	struct net *net = dev_net(mdev->dev);
+	struct mctp_neigh *neigh, *tmp;
+
+	mutex_lock(&net->mctp.neigh_lock);
+	list_for_each_entry_safe(neigh, tmp, &net->mctp.neighbours, list) {
+		if (neigh->dev == mdev) {
+			list_del_rcu(&neigh->list);
+			/* TODO: immediate RTM_DELNEIGH */
+			call_rcu(&neigh->rcu, __mctp_neigh_free);
+		}
+	}
+
+	mutex_unlock(&net->mctp.neigh_lock);
+}
+
+static int mctp_neigh_remove(struct mctp_dev *mdev, mctp_eid_t eid,
+			     enum mctp_neigh_source source)
+{
+	struct net *net = dev_net(mdev->dev);
+	struct mctp_neigh *neigh, *tmp;
+	bool dropped = false;
+
+	mutex_lock(&net->mctp.neigh_lock);
+	list_for_each_entry_safe(neigh, tmp, &net->mctp.neighbours, list) {
+		if (neigh->dev == mdev && neigh->eid == eid &&
+		    neigh->source == source) {
+			list_del_rcu(&neigh->list);
+			/* TODO: immediate RTM_DELNEIGH */
+			call_rcu(&neigh->rcu, __mctp_neigh_free);
+			dropped = true;
+		}
+	}
+
+	mutex_unlock(&net->mctp.neigh_lock);
+	return dropped ? 0 : -ENOENT;
+}
+
+static const struct nla_policy nd_mctp_policy[NDA_MAX + 1] = {
+	[NDA_DST]		= { .type = NLA_U8 },
+	[NDA_LLADDR]		= { .type = NLA_BINARY, .len = MAX_ADDR_LEN },
+};
+
+static int mctp_rtm_newneigh(struct sk_buff *skb, struct nlmsghdr *nlh,
+			     struct netlink_ext_ack *extack)
+{
+	struct net *net = sock_net(skb->sk);
+	struct net_device *dev;
+	struct mctp_dev *mdev;
+	struct ndmsg *ndm;
+	struct nlattr *tb[NDA_MAX + 1];
+	int rc;
+	mctp_eid_t eid;
+	void *lladdr;
+	int lladdr_len;
+
+	rc = nlmsg_parse(nlh, sizeof(*ndm), tb, NDA_MAX, nd_mctp_policy,
+			 extack);
+	if (rc < 0) {
+		NL_SET_ERR_MSG(extack, "lladdr too large?");
+		return rc;
+	}
+
+	if (!tb[NDA_DST]) {
+		NL_SET_ERR_MSG(extack, "Neighbour EID must be specified");
+		return -EINVAL;
+	}
+
+	if (!tb[NDA_LLADDR]) {
+		NL_SET_ERR_MSG(extack, "Neighbour lladdr must be specified");
+		return -EINVAL;
+	}
+
+	eid = nla_get_u8(tb[NDA_DST]);
+	if (!mctp_address_unicast(eid)) {
+		NL_SET_ERR_MSG(extack, "Invalid neighbour EID");
+		return -EINVAL;
+	}
+
+	lladdr = nla_data(tb[NDA_LLADDR]);
+	lladdr_len = nla_len(tb[NDA_LLADDR]);
+
+	ndm = nlmsg_data(nlh);
+
+	dev = __dev_get_by_index(net, ndm->ndm_ifindex);
+	if (!dev)
+		return -ENODEV;
+
+	mdev = mctp_dev_get_rtnl(dev);
+	if (!mdev)
+		return -ENODEV;
+
+	if (lladdr_len != dev->addr_len) {
+		NL_SET_ERR_MSG(extack, "Wrong lladdr length");
+		return -EINVAL;
+	}
+
+	return mctp_neigh_add(mdev, eid, MCTP_NEIGH_STATIC,
+			lladdr_len, lladdr);
+}
+
+static int mctp_rtm_delneigh(struct sk_buff *skb, struct nlmsghdr *nlh,
+			     struct netlink_ext_ack *extack)
+{
+	struct net *net = sock_net(skb->sk);
+	struct nlattr *tb[NDA_MAX + 1];
+	struct net_device *dev;
+	struct mctp_dev *mdev;
+	struct ndmsg *ndm;
+	int rc;
+	mctp_eid_t eid;
+
+	rc = nlmsg_parse(nlh, sizeof(*ndm), tb, NDA_MAX, nd_mctp_policy,
+			 extack);
+	if (rc < 0) {
+		NL_SET_ERR_MSG(extack, "incorrect format");
+		return rc;
+	}
+
+	if (!tb[NDA_DST]) {
+		NL_SET_ERR_MSG(extack, "Neighbour EID must be specified");
+		return -EINVAL;
+	}
+	eid = nla_get_u8(tb[NDA_DST]);
+
+	ndm = nlmsg_data(nlh);
+	dev = __dev_get_by_index(net, ndm->ndm_ifindex);
+	if (!dev)
+		return -ENODEV;
+
+	mdev = mctp_dev_get_rtnl(dev);
+	if (!mdev)
+		return -ENODEV;
+
+	return mctp_neigh_remove(mdev, eid, MCTP_NEIGH_STATIC);
+}
+
+static int mctp_fill_neigh(struct sk_buff *skb, u32 portid, u32 seq, int event,
+			   unsigned int flags, struct mctp_neigh *neigh)
+{
+	struct net_device *dev = neigh->dev->dev;
+	struct nlmsghdr *nlh;
+	struct ndmsg *hdr;
+
+	nlh = nlmsg_put(skb, portid, seq, event, sizeof(*hdr), flags);
+	if (!nlh)
+		return -EMSGSIZE;
+
+	hdr = nlmsg_data(nlh);
+	hdr->ndm_family = AF_MCTP;
+	hdr->ndm_ifindex = dev->ifindex;
+	hdr->ndm_state = 0; // TODO other state bits?
+	if (neigh->source == MCTP_NEIGH_STATIC)
+		hdr->ndm_state |= NUD_PERMANENT;
+	hdr->ndm_flags = 0;
+	hdr->ndm_type = RTN_UNICAST; // TODO: is loopback RTN_LOCAL?
+
+	if (nla_put_u8(skb, NDA_DST, neigh->eid))
+		goto cancel;
+
+	if (nla_put(skb, NDA_LLADDR, dev->addr_len, neigh->ha))
+		goto cancel;
+
+	nlmsg_end(skb, nlh);
+
+	return 0;
+cancel:
+	nlmsg_cancel(skb, nlh);
+	return -EMSGSIZE;
+}
+
+static int mctp_rtm_getneigh(struct sk_buff *skb, struct netlink_callback *cb)
+{
+	struct net *net = sock_net(skb->sk);
+	int rc, idx, req_ifindex;
+	struct mctp_neigh *neigh;
+	struct ndmsg *ndmsg;
+	struct {
+		int idx;
+	} *cbctx = (void *)cb->ctx;
+
+	ndmsg = nlmsg_data(cb->nlh);
+	req_ifindex = ndmsg->ndm_ifindex;
+
+	idx = 0;
+	rcu_read_lock();
+	list_for_each_entry_rcu(neigh, &net->mctp.neighbours, list) {
+		if (idx < cbctx->idx)
+			goto cont;
+
+		rc = 0;
+		if (req_ifindex == 0 || req_ifindex == neigh->dev->dev->ifindex)
+			rc = mctp_fill_neigh(skb, NETLINK_CB(cb->skb).portid,
+					     cb->nlh->nlmsg_seq,
+					     RTM_NEWNEIGH, NLM_F_MULTI, neigh);
+
+		if (rc)
+			break;
+cont:
+		idx++;
+	}
+	rcu_read_unlock();
+
+	cbctx->idx = idx;
+	return skb->len;
+}
+
+int mctp_neigh_lookup(struct mctp_dev *mdev, mctp_eid_t eid, void *ret_hwaddr)
+{
+	struct net *net = dev_net(mdev->dev);
+	struct mctp_neigh *neigh;
+	int rc = -EHOSTUNREACH; // TODO: or ENOENT?
+
+	rcu_read_lock();
+	list_for_each_entry_rcu(neigh, &net->mctp.neighbours, list) {
+		if (mdev == neigh->dev && eid == neigh->eid) {
+			if (ret_hwaddr)
+				memcpy(ret_hwaddr, neigh->ha,
+				       sizeof(neigh->ha));
+			rc = 0;
+			break;
+		}
+	}
+	rcu_read_unlock();
+	return rc;
+}
+
+/* namespace registration */
+static int __net_init mctp_neigh_net_init(struct net *net)
+{
+	struct netns_mctp *ns = &net->mctp;
+
+	INIT_LIST_HEAD(&ns->neighbours);
+	mutex_init(&ns->neigh_lock);
+	return 0;
+}
+
+static void __net_exit mctp_neigh_net_exit(struct net *net)
+{
+	struct netns_mctp *ns = &net->mctp;
+	struct mctp_neigh *neigh;
+
+	list_for_each_entry(neigh, &ns->neighbours, list)
+		call_rcu(&neigh->rcu, __mctp_neigh_free);
+}
+
+/* net namespace implementation */
+
+static struct pernet_operations mctp_net_ops = {
+	.init = mctp_neigh_net_init,
+	.exit = mctp_neigh_net_exit,
+};
+
+int __init mctp_neigh_init(void)
+{
+	rtnl_register_module(THIS_MODULE, PF_MCTP, RTM_NEWNEIGH,
+			     mctp_rtm_newneigh, NULL, 0);
+	rtnl_register_module(THIS_MODULE, PF_MCTP, RTM_DELNEIGH,
+			     mctp_rtm_delneigh, NULL, 0);
+	rtnl_register_module(THIS_MODULE, PF_MCTP, RTM_GETNEIGH,
+			     NULL, mctp_rtm_getneigh, 0);
+
+	return register_pernet_subsys(&mctp_net_ops);
+}
+
+void __exit mctp_neigh_exit(void)
+{
+	unregister_pernet_subsys(&mctp_net_ops);
+	rtnl_unregister(PF_MCTP, RTM_GETNEIGH);
+	rtnl_unregister(PF_MCTP, RTM_DELNEIGH);
+	rtnl_unregister(PF_MCTP, RTM_NEWNEIGH);
+}
diff --git a/net/mctp/route.c b/net/mctp/route.c
new file mode 100644
index 000000000..68be8f2b6
--- /dev/null
+++ b/net/mctp/route.c
@@ -0,0 +1,1432 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Management Component Transport Protocol (MCTP) - routing
+ * implementation.
+ *
+ * This is currently based on a simple routing table, with no dst cache. The
+ * number of routes should stay fairly small, so the lookup cost is small.
+ *
+ * Copyright (c) 2021 Code Construct
+ * Copyright (c) 2021 Google
+ */
+
+#include <linux/idr.h>
+#include <linux/kconfig.h>
+#include <linux/mctp.h>
+#include <linux/netdevice.h>
+#include <linux/rtnetlink.h>
+#include <linux/skbuff.h>
+
+#include <uapi/linux/if_arp.h>
+
+#include <net/mctp.h>
+#include <net/mctpdevice.h>
+#include <net/netlink.h>
+#include <net/sock.h>
+
+#include <trace/events/mctp.h>
+
+static const unsigned int mctp_message_maxlen = 64 * 1024;
+static const unsigned long mctp_key_lifetime = 6 * CONFIG_HZ;
+
+static void mctp_flow_prepare_output(struct sk_buff *skb, struct mctp_dev *dev);
+
+/* route output callbacks */
+static int mctp_route_discard(struct mctp_route *route, struct sk_buff *skb)
+{
+	kfree_skb(skb);
+	return 0;
+}
+
+static struct mctp_sock *mctp_lookup_bind(struct net *net, struct sk_buff *skb)
+{
+	struct mctp_skb_cb *cb = mctp_cb(skb);
+	struct mctp_hdr *mh;
+	struct sock *sk;
+	u8 type;
+
+	WARN_ON(!rcu_read_lock_held());
+
+	/* TODO: look up in skb->cb? */
+	mh = mctp_hdr(skb);
+
+	if (!skb_headlen(skb))
+		return NULL;
+
+	type = (*(u8 *)skb->data) & 0x7f;
+
+	sk_for_each_rcu(sk, &net->mctp.binds) {
+		struct mctp_sock *msk = container_of(sk, struct mctp_sock, sk);
+
+		if (msk->bind_net != MCTP_NET_ANY && msk->bind_net != cb->net)
+			continue;
+
+		if (msk->bind_type != type)
+			continue;
+
+		if (!mctp_address_matches(msk->bind_addr, mh->dest))
+			continue;
+
+		return msk;
+	}
+
+	return NULL;
+}
+
+static bool mctp_key_match(struct mctp_sk_key *key, mctp_eid_t local,
+			   mctp_eid_t peer, u8 tag)
+{
+	if (!mctp_address_matches(key->local_addr, local))
+		return false;
+
+	if (key->peer_addr != peer)
+		return false;
+
+	if (key->tag != tag)
+		return false;
+
+	return true;
+}
+
+/* returns a key (with key->lock held, and refcounted), or NULL if no such
+ * key exists.
+ */
+static struct mctp_sk_key *mctp_lookup_key(struct net *net, struct sk_buff *skb,
+					   mctp_eid_t peer,
+					   unsigned long *irqflags)
+	__acquires(&key->lock)
+{
+	struct mctp_sk_key *key, *ret;
+	unsigned long flags;
+	struct mctp_hdr *mh;
+	u8 tag;
+
+	mh = mctp_hdr(skb);
+	tag = mh->flags_seq_tag & (MCTP_HDR_TAG_MASK | MCTP_HDR_FLAG_TO);
+
+	ret = NULL;
+	spin_lock_irqsave(&net->mctp.keys_lock, flags);
+
+	hlist_for_each_entry(key, &net->mctp.keys, hlist) {
+		if (!mctp_key_match(key, mh->dest, peer, tag))
+			continue;
+
+		spin_lock(&key->lock);
+		if (key->valid) {
+			refcount_inc(&key->refs);
+			ret = key;
+			break;
+		}
+		spin_unlock(&key->lock);
+	}
+
+	if (ret) {
+		spin_unlock(&net->mctp.keys_lock);
+		*irqflags = flags;
+	} else {
+		spin_unlock_irqrestore(&net->mctp.keys_lock, flags);
+	}
+
+	return ret;
+}
+
+static struct mctp_sk_key *mctp_key_alloc(struct mctp_sock *msk,
+					  mctp_eid_t local, mctp_eid_t peer,
+					  u8 tag, gfp_t gfp)
+{
+	struct mctp_sk_key *key;
+
+	key = kzalloc(sizeof(*key), gfp);
+	if (!key)
+		return NULL;
+
+	key->peer_addr = peer;
+	key->local_addr = local;
+	key->tag = tag;
+	key->sk = &msk->sk;
+	key->valid = true;
+	spin_lock_init(&key->lock);
+	refcount_set(&key->refs, 1);
+	sock_hold(key->sk);
+
+	return key;
+}
+
+void mctp_key_unref(struct mctp_sk_key *key)
+{
+	unsigned long flags;
+
+	if (!refcount_dec_and_test(&key->refs))
+		return;
+
+	/* even though no refs exist here, the lock allows us to stay
+	 * consistent with the locking requirement of mctp_dev_release_key
+	 */
+	spin_lock_irqsave(&key->lock, flags);
+	mctp_dev_release_key(key->dev, key);
+	spin_unlock_irqrestore(&key->lock, flags);
+
+	sock_put(key->sk);
+	kfree(key);
+}
+
+static int mctp_key_add(struct mctp_sk_key *key, struct mctp_sock *msk)
+{
+	struct net *net = sock_net(&msk->sk);
+	struct mctp_sk_key *tmp;
+	unsigned long flags;
+	int rc = 0;
+
+	spin_lock_irqsave(&net->mctp.keys_lock, flags);
+
+	if (sock_flag(&msk->sk, SOCK_DEAD)) {
+		rc = -EINVAL;
+		goto out_unlock;
+	}
+
+	hlist_for_each_entry(tmp, &net->mctp.keys, hlist) {
+		if (mctp_key_match(tmp, key->local_addr, key->peer_addr,
+				   key->tag)) {
+			spin_lock(&tmp->lock);
+			if (tmp->valid)
+				rc = -EEXIST;
+			spin_unlock(&tmp->lock);
+			if (rc)
+				break;
+		}
+	}
+
+	if (!rc) {
+		refcount_inc(&key->refs);
+		key->expiry = jiffies + mctp_key_lifetime;
+		timer_reduce(&msk->key_expiry, key->expiry);
+
+		hlist_add_head(&key->hlist, &net->mctp.keys);
+		hlist_add_head(&key->sklist, &msk->keys);
+	}
+
+out_unlock:
+	spin_unlock_irqrestore(&net->mctp.keys_lock, flags);
+
+	return rc;
+}
+
+/* Helper for mctp_route_input().
+ * We're done with the key; unlock and unref the key.
+ * For the usual case of automatic expiry we remove the key from lists.
+ * In the case that manual allocation is set on a key we release the lock
+ * and local ref, reset reassembly, but don't remove from lists.
+ */
+static void __mctp_key_done_in(struct mctp_sk_key *key, struct net *net,
+			       unsigned long flags, unsigned long reason)
+__releases(&key->lock)
+{
+	struct sk_buff *skb;
+
+	trace_mctp_key_release(key, reason);
+	skb = key->reasm_head;
+	key->reasm_head = NULL;
+
+	if (!key->manual_alloc) {
+		key->reasm_dead = true;
+		key->valid = false;
+		mctp_dev_release_key(key->dev, key);
+	}
+	spin_unlock_irqrestore(&key->lock, flags);
+
+	if (!key->manual_alloc) {
+		spin_lock_irqsave(&net->mctp.keys_lock, flags);
+		if (!hlist_unhashed(&key->hlist)) {
+			hlist_del_init(&key->hlist);
+			hlist_del_init(&key->sklist);
+			mctp_key_unref(key);
+		}
+		spin_unlock_irqrestore(&net->mctp.keys_lock, flags);
+	}
+
+	/* and one for the local reference */
+	mctp_key_unref(key);
+
+	kfree_skb(skb);
+}
+
+#ifdef CONFIG_MCTP_FLOWS
+static void mctp_skb_set_flow(struct sk_buff *skb, struct mctp_sk_key *key)
+{
+	struct mctp_flow *flow;
+
+	flow = skb_ext_add(skb, SKB_EXT_MCTP);
+	if (!flow)
+		return;
+
+	refcount_inc(&key->refs);
+	flow->key = key;
+}
+
+static void mctp_flow_prepare_output(struct sk_buff *skb, struct mctp_dev *dev)
+{
+	struct mctp_sk_key *key;
+	struct mctp_flow *flow;
+
+	flow = skb_ext_find(skb, SKB_EXT_MCTP);
+	if (!flow)
+		return;
+
+	key = flow->key;
+
+	if (WARN_ON(key->dev && key->dev != dev))
+		return;
+
+	mctp_dev_set_key(dev, key);
+}
+#else
+static void mctp_skb_set_flow(struct sk_buff *skb, struct mctp_sk_key *key) {}
+static void mctp_flow_prepare_output(struct sk_buff *skb, struct mctp_dev *dev) {}
+#endif
+
+static int mctp_frag_queue(struct mctp_sk_key *key, struct sk_buff *skb)
+{
+	struct mctp_hdr *hdr = mctp_hdr(skb);
+	u8 exp_seq, this_seq;
+
+	this_seq = (hdr->flags_seq_tag >> MCTP_HDR_SEQ_SHIFT)
+		& MCTP_HDR_SEQ_MASK;
+
+	if (!key->reasm_head) {
+		key->reasm_head = skb;
+		key->reasm_tailp = &(skb_shinfo(skb)->frag_list);
+		key->last_seq = this_seq;
+		return 0;
+	}
+
+	exp_seq = (key->last_seq + 1) & MCTP_HDR_SEQ_MASK;
+
+	if (this_seq != exp_seq)
+		return -EINVAL;
+
+	if (key->reasm_head->len + skb->len > mctp_message_maxlen)
+		return -EINVAL;
+
+	skb->next = NULL;
+	skb->sk = NULL;
+	*key->reasm_tailp = skb;
+	key->reasm_tailp = &skb->next;
+
+	key->last_seq = this_seq;
+
+	key->reasm_head->data_len += skb->len;
+	key->reasm_head->len += skb->len;
+	key->reasm_head->truesize += skb->truesize;
+
+	return 0;
+}
+
+static int mctp_route_input(struct mctp_route *route, struct sk_buff *skb)
+{
+	struct mctp_sk_key *key, *any_key = NULL;
+	struct net *net = dev_net(skb->dev);
+	struct mctp_sock *msk;
+	struct mctp_hdr *mh;
+	unsigned long f;
+	u8 tag, flags;
+	int rc;
+
+	msk = NULL;
+	rc = -EINVAL;
+
+	/* we may be receiving a locally-routed packet; drop source sk
+	 * accounting
+	 */
+	skb_orphan(skb);
+
+	/* ensure we have enough data for a header and a type */
+	if (skb->len < sizeof(struct mctp_hdr) + 1)
+		goto out;
+
+	/* grab header, advance data ptr */
+	mh = mctp_hdr(skb);
+	skb_pull(skb, sizeof(struct mctp_hdr));
+
+	if (mh->ver != 1)
+		goto out;
+
+	flags = mh->flags_seq_tag & (MCTP_HDR_FLAG_SOM | MCTP_HDR_FLAG_EOM);
+	tag = mh->flags_seq_tag & (MCTP_HDR_TAG_MASK | MCTP_HDR_FLAG_TO);
+
+	rcu_read_lock();
+
+	/* lookup socket / reasm context, exactly matching (src,dest,tag).
+	 * we hold a ref on the key, and key->lock held.
+	 */
+	key = mctp_lookup_key(net, skb, mh->src, &f);
+
+	if (flags & MCTP_HDR_FLAG_SOM) {
+		if (key) {
+			msk = container_of(key->sk, struct mctp_sock, sk);
+		} else {
+			/* first response to a broadcast? do a more general
+			 * key lookup to find the socket, but don't use this
+			 * key for reassembly - we'll create a more specific
+			 * one for future packets if required (ie, !EOM).
+			 */
+			any_key = mctp_lookup_key(net, skb, MCTP_ADDR_ANY, &f);
+			if (any_key) {
+				msk = container_of(any_key->sk,
+						   struct mctp_sock, sk);
+				spin_unlock_irqrestore(&any_key->lock, f);
+			}
+		}
+
+		if (!key && !msk && (tag & MCTP_HDR_FLAG_TO))
+			msk = mctp_lookup_bind(net, skb);
+
+		if (!msk) {
+			rc = -ENOENT;
+			goto out_unlock;
+		}
+
+		/* single-packet message? deliver to socket, clean up any
+		 * pending key.
+		 */
+		if (flags & MCTP_HDR_FLAG_EOM) {
+			sock_queue_rcv_skb(&msk->sk, skb);
+			if (key) {
+				/* we've hit a pending reassembly; not much we
+				 * can do but drop it
+				 */
+				__mctp_key_done_in(key, net, f,
+						   MCTP_TRACE_KEY_REPLIED);
+				key = NULL;
+			}
+			rc = 0;
+			goto out_unlock;
+		}
+
+		/* broadcast response or a bind() - create a key for further
+		 * packets for this message
+		 */
+		if (!key) {
+			key = mctp_key_alloc(msk, mh->dest, mh->src,
+					     tag, GFP_ATOMIC);
+			if (!key) {
+				rc = -ENOMEM;
+				goto out_unlock;
+			}
+
+			/* we can queue without the key lock here, as the
+			 * key isn't observable yet
+			 */
+			mctp_frag_queue(key, skb);
+
+			/* if the key_add fails, we've raced with another
+			 * SOM packet with the same src, dest and tag. There's
+			 * no way to distinguish future packets, so all we
+			 * can do is drop; we'll free the skb on exit from
+			 * this function.
+			 */
+			rc = mctp_key_add(key, msk);
+			if (!rc)
+				trace_mctp_key_acquire(key);
+
+			/* we don't need to release key->lock on exit, so
+			 * clean up here and suppress the unlock via
+			 * setting to NULL
+			 */
+			mctp_key_unref(key);
+			key = NULL;
+
+		} else {
+			if (key->reasm_head || key->reasm_dead) {
+				/* duplicate start? drop everything */
+				__mctp_key_done_in(key, net, f,
+						   MCTP_TRACE_KEY_INVALIDATED);
+				rc = -EEXIST;
+				key = NULL;
+			} else {
+				rc = mctp_frag_queue(key, skb);
+			}
+		}
+
+	} else if (key) {
+		/* this packet continues a previous message; reassemble
+		 * using the message-specific key
+		 */
+
+		/* we need to be continuing an existing reassembly... */
+		if (!key->reasm_head)
+			rc = -EINVAL;
+		else
+			rc = mctp_frag_queue(key, skb);
+
+		/* end of message? deliver to socket, and we're done with
+		 * the reassembly/response key
+		 */
+		if (!rc && flags & MCTP_HDR_FLAG_EOM) {
+			sock_queue_rcv_skb(key->sk, key->reasm_head);
+			key->reasm_head = NULL;
+			__mctp_key_done_in(key, net, f, MCTP_TRACE_KEY_REPLIED);
+			key = NULL;
+		}
+
+	} else {
+		/* not a start, no matching key */
+		rc = -ENOENT;
+	}
+
+out_unlock:
+	rcu_read_unlock();
+	if (key) {
+		spin_unlock_irqrestore(&key->lock, f);
+		mctp_key_unref(key);
+	}
+	if (any_key)
+		mctp_key_unref(any_key);
+out:
+	if (rc)
+		kfree_skb(skb);
+	return rc;
+}
+
+static unsigned int mctp_route_mtu(struct mctp_route *rt)
+{
+	return rt->mtu ?: READ_ONCE(rt->dev->dev->mtu);
+}
+
+static int mctp_route_output(struct mctp_route *route, struct sk_buff *skb)
+{
+	struct mctp_skb_cb *cb = mctp_cb(skb);
+	struct mctp_hdr *hdr = mctp_hdr(skb);
+	char daddr_buf[MAX_ADDR_LEN];
+	char *daddr = NULL;
+	unsigned int mtu;
+	int rc;
+
+	skb->protocol = htons(ETH_P_MCTP);
+
+	mtu = READ_ONCE(skb->dev->mtu);
+	if (skb->len > mtu) {
+		kfree_skb(skb);
+		return -EMSGSIZE;
+	}
+
+	if (cb->ifindex) {
+		/* direct route; use the hwaddr we stashed in sendmsg */
+		if (cb->halen != skb->dev->addr_len) {
+			/* sanity check, sendmsg should have already caught this */
+			kfree_skb(skb);
+			return -EMSGSIZE;
+		}
+		daddr = cb->haddr;
+	} else {
+		/* If lookup fails let the device handle daddr==NULL */
+		if (mctp_neigh_lookup(route->dev, hdr->dest, daddr_buf) == 0)
+			daddr = daddr_buf;
+	}
+
+	rc = dev_hard_header(skb, skb->dev, ntohs(skb->protocol),
+			     daddr, skb->dev->dev_addr, skb->len);
+	if (rc < 0) {
+		kfree_skb(skb);
+		return -EHOSTUNREACH;
+	}
+
+	mctp_flow_prepare_output(skb, route->dev);
+
+	rc = dev_queue_xmit(skb);
+	if (rc)
+		rc = net_xmit_errno(rc);
+
+	return rc;
+}
+
+/* route alloc/release */
+static void mctp_route_release(struct mctp_route *rt)
+{
+	if (refcount_dec_and_test(&rt->refs)) {
+		mctp_dev_put(rt->dev);
+		kfree_rcu(rt, rcu);
+	}
+}
+
+/* returns a route with the refcount at 1 */
+static struct mctp_route *mctp_route_alloc(void)
+{
+	struct mctp_route *rt;
+
+	rt = kzalloc(sizeof(*rt), GFP_KERNEL);
+	if (!rt)
+		return NULL;
+
+	INIT_LIST_HEAD(&rt->list);
+	refcount_set(&rt->refs, 1);
+	rt->output = mctp_route_discard;
+
+	return rt;
+}
+
+unsigned int mctp_default_net(struct net *net)
+{
+	return READ_ONCE(net->mctp.default_net);
+}
+
+int mctp_default_net_set(struct net *net, unsigned int index)
+{
+	if (index == 0)
+		return -EINVAL;
+	WRITE_ONCE(net->mctp.default_net, index);
+	return 0;
+}
+
+/* tag management */
+static void mctp_reserve_tag(struct net *net, struct mctp_sk_key *key,
+			     struct mctp_sock *msk)
+{
+	struct netns_mctp *mns = &net->mctp;
+
+	lockdep_assert_held(&mns->keys_lock);
+
+	key->expiry = jiffies + mctp_key_lifetime;
+	timer_reduce(&msk->key_expiry, key->expiry);
+
+	/* we hold the net->key_lock here, allowing updates to both
+	 * then net and sk
+	 */
+	hlist_add_head_rcu(&key->hlist, &mns->keys);
+	hlist_add_head_rcu(&key->sklist, &msk->keys);
+	refcount_inc(&key->refs);
+}
+
+/* Allocate a locally-owned tag value for (saddr, daddr), and reserve
+ * it for the socket msk
+ */
+struct mctp_sk_key *mctp_alloc_local_tag(struct mctp_sock *msk,
+					 mctp_eid_t daddr, mctp_eid_t saddr,
+					 bool manual, u8 *tagp)
+{
+	struct net *net = sock_net(&msk->sk);
+	struct netns_mctp *mns = &net->mctp;
+	struct mctp_sk_key *key, *tmp;
+	unsigned long flags;
+	u8 tagbits;
+
+	/* for NULL destination EIDs, we may get a response from any peer */
+	if (daddr == MCTP_ADDR_NULL)
+		daddr = MCTP_ADDR_ANY;
+
+	/* be optimistic, alloc now */
+	key = mctp_key_alloc(msk, saddr, daddr, 0, GFP_KERNEL);
+	if (!key)
+		return ERR_PTR(-ENOMEM);
+
+	/* 8 possible tag values */
+	tagbits = 0xff;
+
+	spin_lock_irqsave(&mns->keys_lock, flags);
+
+	/* Walk through the existing keys, looking for potential conflicting
+	 * tags. If we find a conflict, clear that bit from tagbits
+	 */
+	hlist_for_each_entry(tmp, &mns->keys, hlist) {
+		/* We can check the lookup fields (*_addr, tag) without the
+		 * lock held, they don't change over the lifetime of the key.
+		 */
+
+		/* if we don't own the tag, it can't conflict */
+		if (tmp->tag & MCTP_HDR_FLAG_TO)
+			continue;
+
+		if (!(mctp_address_matches(tmp->peer_addr, daddr) &&
+		      mctp_address_matches(tmp->local_addr, saddr)))
+			continue;
+
+		spin_lock(&tmp->lock);
+		/* key must still be valid. If we find a match, clear the
+		 * potential tag value
+		 */
+		if (tmp->valid)
+			tagbits &= ~(1 << tmp->tag);
+		spin_unlock(&tmp->lock);
+
+		if (!tagbits)
+			break;
+	}
+
+	if (tagbits) {
+		key->tag = __ffs(tagbits);
+		mctp_reserve_tag(net, key, msk);
+		trace_mctp_key_acquire(key);
+
+		key->manual_alloc = manual;
+		*tagp = key->tag;
+	}
+
+	spin_unlock_irqrestore(&mns->keys_lock, flags);
+
+	if (!tagbits) {
+		kfree(key);
+		return ERR_PTR(-EBUSY);
+	}
+
+	return key;
+}
+
+static struct mctp_sk_key *mctp_lookup_prealloc_tag(struct mctp_sock *msk,
+						    mctp_eid_t daddr,
+						    u8 req_tag, u8 *tagp)
+{
+	struct net *net = sock_net(&msk->sk);
+	struct netns_mctp *mns = &net->mctp;
+	struct mctp_sk_key *key, *tmp;
+	unsigned long flags;
+
+	req_tag &= ~(MCTP_TAG_PREALLOC | MCTP_TAG_OWNER);
+	key = NULL;
+
+	spin_lock_irqsave(&mns->keys_lock, flags);
+
+	hlist_for_each_entry(tmp, &mns->keys, hlist) {
+		if (tmp->tag != req_tag)
+			continue;
+
+		if (!mctp_address_matches(tmp->peer_addr, daddr))
+			continue;
+
+		if (!tmp->manual_alloc)
+			continue;
+
+		spin_lock(&tmp->lock);
+		if (tmp->valid) {
+			key = tmp;
+			refcount_inc(&key->refs);
+			spin_unlock(&tmp->lock);
+			break;
+		}
+		spin_unlock(&tmp->lock);
+	}
+	spin_unlock_irqrestore(&mns->keys_lock, flags);
+
+	if (!key)
+		return ERR_PTR(-ENOENT);
+
+	if (tagp)
+		*tagp = key->tag;
+
+	return key;
+}
+
+/* routing lookups */
+static bool mctp_rt_match_eid(struct mctp_route *rt,
+			      unsigned int net, mctp_eid_t eid)
+{
+	return READ_ONCE(rt->dev->net) == net &&
+		rt->min <= eid && rt->max >= eid;
+}
+
+/* compares match, used for duplicate prevention */
+static bool mctp_rt_compare_exact(struct mctp_route *rt1,
+				  struct mctp_route *rt2)
+{
+	ASSERT_RTNL();
+	return rt1->dev->net == rt2->dev->net &&
+		rt1->min == rt2->min &&
+		rt1->max == rt2->max;
+}
+
+struct mctp_route *mctp_route_lookup(struct net *net, unsigned int dnet,
+				     mctp_eid_t daddr)
+{
+	struct mctp_route *tmp, *rt = NULL;
+
+	rcu_read_lock();
+
+	list_for_each_entry_rcu(tmp, &net->mctp.routes, list) {
+		/* TODO: add metrics */
+		if (mctp_rt_match_eid(tmp, dnet, daddr)) {
+			if (refcount_inc_not_zero(&tmp->refs)) {
+				rt = tmp;
+				break;
+			}
+		}
+	}
+
+	rcu_read_unlock();
+
+	return rt;
+}
+
+static struct mctp_route *mctp_route_lookup_null(struct net *net,
+						 struct net_device *dev)
+{
+	struct mctp_route *tmp, *rt = NULL;
+
+	rcu_read_lock();
+
+	list_for_each_entry_rcu(tmp, &net->mctp.routes, list) {
+		if (tmp->dev->dev == dev && tmp->type == RTN_LOCAL &&
+		    refcount_inc_not_zero(&tmp->refs)) {
+			rt = tmp;
+			break;
+		}
+	}
+
+	rcu_read_unlock();
+
+	return rt;
+}
+
+static int mctp_do_fragment_route(struct mctp_route *rt, struct sk_buff *skb,
+				  unsigned int mtu, u8 tag)
+{
+	const unsigned int hlen = sizeof(struct mctp_hdr);
+	struct mctp_hdr *hdr, *hdr2;
+	unsigned int pos, size, headroom;
+	struct sk_buff *skb2;
+	int rc;
+	u8 seq;
+
+	hdr = mctp_hdr(skb);
+	seq = 0;
+	rc = 0;
+
+	if (mtu < hlen + 1) {
+		kfree_skb(skb);
+		return -EMSGSIZE;
+	}
+
+	/* keep same headroom as the original skb */
+	headroom = skb_headroom(skb);
+
+	/* we've got the header */
+	skb_pull(skb, hlen);
+
+	for (pos = 0; pos < skb->len;) {
+		/* size of message payload */
+		size = min(mtu - hlen, skb->len - pos);
+
+		skb2 = alloc_skb(headroom + hlen + size, GFP_KERNEL);
+		if (!skb2) {
+			rc = -ENOMEM;
+			break;
+		}
+
+		/* generic skb copy */
+		skb2->protocol = skb->protocol;
+		skb2->priority = skb->priority;
+		skb2->dev = skb->dev;
+		memcpy(skb2->cb, skb->cb, sizeof(skb2->cb));
+
+		if (skb->sk)
+			skb_set_owner_w(skb2, skb->sk);
+
+		/* establish packet */
+		skb_reserve(skb2, headroom);
+		skb_reset_network_header(skb2);
+		skb_put(skb2, hlen + size);
+		skb2->transport_header = skb2->network_header + hlen;
+
+		/* copy header fields, calculate SOM/EOM flags & seq */
+		hdr2 = mctp_hdr(skb2);
+		hdr2->ver = hdr->ver;
+		hdr2->dest = hdr->dest;
+		hdr2->src = hdr->src;
+		hdr2->flags_seq_tag = tag &
+			(MCTP_HDR_TAG_MASK | MCTP_HDR_FLAG_TO);
+
+		if (pos == 0)
+			hdr2->flags_seq_tag |= MCTP_HDR_FLAG_SOM;
+
+		if (pos + size == skb->len)
+			hdr2->flags_seq_tag |= MCTP_HDR_FLAG_EOM;
+
+		hdr2->flags_seq_tag |= seq << MCTP_HDR_SEQ_SHIFT;
+
+		/* copy message payload */
+		skb_copy_bits(skb, pos, skb_transport_header(skb2), size);
+
+		/* do route */
+		rc = rt->output(rt, skb2);
+		if (rc)
+			break;
+
+		seq = (seq + 1) & MCTP_HDR_SEQ_MASK;
+		pos += size;
+	}
+
+	consume_skb(skb);
+	return rc;
+}
+
+int mctp_local_output(struct sock *sk, struct mctp_route *rt,
+		      struct sk_buff *skb, mctp_eid_t daddr, u8 req_tag)
+{
+	struct mctp_sock *msk = container_of(sk, struct mctp_sock, sk);
+	struct mctp_skb_cb *cb = mctp_cb(skb);
+	struct mctp_route tmp_rt = {0};
+	struct mctp_sk_key *key;
+	struct mctp_hdr *hdr;
+	unsigned long flags;
+	unsigned int mtu;
+	mctp_eid_t saddr;
+	bool ext_rt;
+	int rc;
+	u8 tag;
+
+	rc = -ENODEV;
+
+	if (rt) {
+		ext_rt = false;
+		if (WARN_ON(!rt->dev))
+			goto out_release;
+
+	} else if (cb->ifindex) {
+		struct net_device *dev;
+
+		ext_rt = true;
+		rt = &tmp_rt;
+
+		rcu_read_lock();
+		dev = dev_get_by_index_rcu(sock_net(sk), cb->ifindex);
+		if (!dev) {
+			rcu_read_unlock();
+			return rc;
+		}
+		rt->dev = __mctp_dev_get(dev);
+		rcu_read_unlock();
+
+		if (!rt->dev)
+			goto out_release;
+
+		/* establish temporary route - we set up enough to keep
+		 * mctp_route_output happy
+		 */
+		rt->output = mctp_route_output;
+		rt->mtu = 0;
+
+	} else {
+		return -EINVAL;
+	}
+
+	spin_lock_irqsave(&rt->dev->addrs_lock, flags);
+	if (rt->dev->num_addrs == 0) {
+		rc = -EHOSTUNREACH;
+	} else {
+		/* use the outbound interface's first address as our source */
+		saddr = rt->dev->addrs[0];
+		rc = 0;
+	}
+	spin_unlock_irqrestore(&rt->dev->addrs_lock, flags);
+
+	if (rc)
+		goto out_release;
+
+	if (req_tag & MCTP_TAG_OWNER) {
+		if (req_tag & MCTP_TAG_PREALLOC)
+			key = mctp_lookup_prealloc_tag(msk, daddr,
+						       req_tag, &tag);
+		else
+			key = mctp_alloc_local_tag(msk, daddr, saddr,
+						   false, &tag);
+
+		if (IS_ERR(key)) {
+			rc = PTR_ERR(key);
+			goto out_release;
+		}
+		mctp_skb_set_flow(skb, key);
+		/* done with the key in this scope */
+		mctp_key_unref(key);
+		tag |= MCTP_HDR_FLAG_TO;
+	} else {
+		key = NULL;
+		tag = req_tag & MCTP_TAG_MASK;
+	}
+
+	skb->protocol = htons(ETH_P_MCTP);
+	skb->priority = 0;
+	skb_reset_transport_header(skb);
+	skb_push(skb, sizeof(struct mctp_hdr));
+	skb_reset_network_header(skb);
+	skb->dev = rt->dev->dev;
+
+	/* cb->net will have been set on initial ingress */
+	cb->src = saddr;
+
+	/* set up common header fields */
+	hdr = mctp_hdr(skb);
+	hdr->ver = 1;
+	hdr->dest = daddr;
+	hdr->src = saddr;
+
+	mtu = mctp_route_mtu(rt);
+
+	if (skb->len + sizeof(struct mctp_hdr) <= mtu) {
+		hdr->flags_seq_tag = MCTP_HDR_FLAG_SOM |
+			MCTP_HDR_FLAG_EOM | tag;
+		rc = rt->output(rt, skb);
+	} else {
+		rc = mctp_do_fragment_route(rt, skb, mtu, tag);
+	}
+
+out_release:
+	if (!ext_rt)
+		mctp_route_release(rt);
+
+	mctp_dev_put(tmp_rt.dev);
+
+	return rc;
+}
+
+/* route management */
+static int mctp_route_add(struct mctp_dev *mdev, mctp_eid_t daddr_start,
+			  unsigned int daddr_extent, unsigned int mtu,
+			  unsigned char type)
+{
+	int (*rtfn)(struct mctp_route *rt, struct sk_buff *skb);
+	struct net *net = dev_net(mdev->dev);
+	struct mctp_route *rt, *ert;
+
+	if (!mctp_address_unicast(daddr_start))
+		return -EINVAL;
+
+	if (daddr_extent > 0xff || daddr_start + daddr_extent >= 255)
+		return -EINVAL;
+
+	switch (type) {
+	case RTN_LOCAL:
+		rtfn = mctp_route_input;
+		break;
+	case RTN_UNICAST:
+		rtfn = mctp_route_output;
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	rt = mctp_route_alloc();
+	if (!rt)
+		return -ENOMEM;
+
+	rt->min = daddr_start;
+	rt->max = daddr_start + daddr_extent;
+	rt->mtu = mtu;
+	rt->dev = mdev;
+	mctp_dev_hold(rt->dev);
+	rt->type = type;
+	rt->output = rtfn;
+
+	ASSERT_RTNL();
+	/* Prevent duplicate identical routes. */
+	list_for_each_entry(ert, &net->mctp.routes, list) {
+		if (mctp_rt_compare_exact(rt, ert)) {
+			mctp_route_release(rt);
+			return -EEXIST;
+		}
+	}
+
+	list_add_rcu(&rt->list, &net->mctp.routes);
+
+	return 0;
+}
+
+static int mctp_route_remove(struct mctp_dev *mdev, mctp_eid_t daddr_start,
+			     unsigned int daddr_extent, unsigned char type)
+{
+	struct net *net = dev_net(mdev->dev);
+	struct mctp_route *rt, *tmp;
+	mctp_eid_t daddr_end;
+	bool dropped;
+
+	if (daddr_extent > 0xff || daddr_start + daddr_extent >= 255)
+		return -EINVAL;
+
+	daddr_end = daddr_start + daddr_extent;
+	dropped = false;
+
+	ASSERT_RTNL();
+
+	list_for_each_entry_safe(rt, tmp, &net->mctp.routes, list) {
+		if (rt->dev == mdev &&
+		    rt->min == daddr_start && rt->max == daddr_end &&
+		    rt->type == type) {
+			list_del_rcu(&rt->list);
+			/* TODO: immediate RTM_DELROUTE */
+			mctp_route_release(rt);
+			dropped = true;
+		}
+	}
+
+	return dropped ? 0 : -ENOENT;
+}
+
+int mctp_route_add_local(struct mctp_dev *mdev, mctp_eid_t addr)
+{
+	return mctp_route_add(mdev, addr, 0, 0, RTN_LOCAL);
+}
+
+int mctp_route_remove_local(struct mctp_dev *mdev, mctp_eid_t addr)
+{
+	return mctp_route_remove(mdev, addr, 0, RTN_LOCAL);
+}
+
+/* removes all entries for a given device */
+void mctp_route_remove_dev(struct mctp_dev *mdev)
+{
+	struct net *net = dev_net(mdev->dev);
+	struct mctp_route *rt, *tmp;
+
+	ASSERT_RTNL();
+	list_for_each_entry_safe(rt, tmp, &net->mctp.routes, list) {
+		if (rt->dev == mdev) {
+			list_del_rcu(&rt->list);
+			/* TODO: immediate RTM_DELROUTE */
+			mctp_route_release(rt);
+		}
+	}
+}
+
+/* Incoming packet-handling */
+
+static int mctp_pkttype_receive(struct sk_buff *skb, struct net_device *dev,
+				struct packet_type *pt,
+				struct net_device *orig_dev)
+{
+	struct net *net = dev_net(dev);
+	struct mctp_dev *mdev;
+	struct mctp_skb_cb *cb;
+	struct mctp_route *rt;
+	struct mctp_hdr *mh;
+
+	rcu_read_lock();
+	mdev = __mctp_dev_get(dev);
+	rcu_read_unlock();
+	if (!mdev) {
+		/* basic non-data sanity checks */
+		goto err_drop;
+	}
+
+	if (!pskb_may_pull(skb, sizeof(struct mctp_hdr)))
+		goto err_drop;
+
+	skb_reset_transport_header(skb);
+	skb_reset_network_header(skb);
+
+	/* We have enough for a header; decode and route */
+	mh = mctp_hdr(skb);
+	if (mh->ver < MCTP_VER_MIN || mh->ver > MCTP_VER_MAX)
+		goto err_drop;
+
+	/* source must be valid unicast or null; drop reserved ranges and
+	 * broadcast
+	 */
+	if (!(mctp_address_unicast(mh->src) || mctp_address_null(mh->src)))
+		goto err_drop;
+
+	/* dest address: as above, but allow broadcast */
+	if (!(mctp_address_unicast(mh->dest) || mctp_address_null(mh->dest) ||
+	      mctp_address_broadcast(mh->dest)))
+		goto err_drop;
+
+	/* MCTP drivers must populate halen/haddr */
+	if (dev->type == ARPHRD_MCTP) {
+		cb = mctp_cb(skb);
+	} else {
+		cb = __mctp_cb(skb);
+		cb->halen = 0;
+	}
+	cb->net = READ_ONCE(mdev->net);
+	cb->ifindex = dev->ifindex;
+
+	rt = mctp_route_lookup(net, cb->net, mh->dest);
+
+	/* NULL EID, but addressed to our physical address */
+	if (!rt && mh->dest == MCTP_ADDR_NULL && skb->pkt_type == PACKET_HOST)
+		rt = mctp_route_lookup_null(net, dev);
+
+	if (!rt)
+		goto err_drop;
+
+	rt->output(rt, skb);
+	mctp_route_release(rt);
+	mctp_dev_put(mdev);
+
+	return NET_RX_SUCCESS;
+
+err_drop:
+	kfree_skb(skb);
+	mctp_dev_put(mdev);
+	return NET_RX_DROP;
+}
+
+static struct packet_type mctp_packet_type = {
+	.type = cpu_to_be16(ETH_P_MCTP),
+	.func = mctp_pkttype_receive,
+};
+
+/* netlink interface */
+
+static const struct nla_policy rta_mctp_policy[RTA_MAX + 1] = {
+	[RTA_DST]		= { .type = NLA_U8 },
+	[RTA_METRICS]		= { .type = NLA_NESTED },
+	[RTA_OIF]		= { .type = NLA_U32 },
+};
+
+/* Common part for RTM_NEWROUTE and RTM_DELROUTE parsing.
+ * tb must hold RTA_MAX+1 elements.
+ */
+static int mctp_route_nlparse(struct sk_buff *skb, struct nlmsghdr *nlh,
+			      struct netlink_ext_ack *extack,
+			      struct nlattr **tb, struct rtmsg **rtm,
+			      struct mctp_dev **mdev, mctp_eid_t *daddr_start)
+{
+	struct net *net = sock_net(skb->sk);
+	struct net_device *dev;
+	unsigned int ifindex;
+	int rc;
+
+	rc = nlmsg_parse(nlh, sizeof(struct rtmsg), tb, RTA_MAX,
+			 rta_mctp_policy, extack);
+	if (rc < 0) {
+		NL_SET_ERR_MSG(extack, "incorrect format");
+		return rc;
+	}
+
+	if (!tb[RTA_DST]) {
+		NL_SET_ERR_MSG(extack, "dst EID missing");
+		return -EINVAL;
+	}
+	*daddr_start = nla_get_u8(tb[RTA_DST]);
+
+	if (!tb[RTA_OIF]) {
+		NL_SET_ERR_MSG(extack, "ifindex missing");
+		return -EINVAL;
+	}
+	ifindex = nla_get_u32(tb[RTA_OIF]);
+
+	*rtm = nlmsg_data(nlh);
+	if ((*rtm)->rtm_family != AF_MCTP) {
+		NL_SET_ERR_MSG(extack, "route family must be AF_MCTP");
+		return -EINVAL;
+	}
+
+	dev = __dev_get_by_index(net, ifindex);
+	if (!dev) {
+		NL_SET_ERR_MSG(extack, "bad ifindex");
+		return -ENODEV;
+	}
+	*mdev = mctp_dev_get_rtnl(dev);
+	if (!*mdev)
+		return -ENODEV;
+
+	if (dev->flags & IFF_LOOPBACK) {
+		NL_SET_ERR_MSG(extack, "no routes to loopback");
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+static const struct nla_policy rta_metrics_policy[RTAX_MAX + 1] = {
+	[RTAX_MTU]		= { .type = NLA_U32 },
+};
+
+static int mctp_newroute(struct sk_buff *skb, struct nlmsghdr *nlh,
+			 struct netlink_ext_ack *extack)
+{
+	struct nlattr *tb[RTA_MAX + 1];
+	struct nlattr *tbx[RTAX_MAX + 1];
+	mctp_eid_t daddr_start;
+	struct mctp_dev *mdev;
+	struct rtmsg *rtm;
+	unsigned int mtu;
+	int rc;
+
+	rc = mctp_route_nlparse(skb, nlh, extack, tb,
+				&rtm, &mdev, &daddr_start);
+	if (rc < 0)
+		return rc;
+
+	if (rtm->rtm_type != RTN_UNICAST) {
+		NL_SET_ERR_MSG(extack, "rtm_type must be RTN_UNICAST");
+		return -EINVAL;
+	}
+
+	mtu = 0;
+	if (tb[RTA_METRICS]) {
+		rc = nla_parse_nested(tbx, RTAX_MAX, tb[RTA_METRICS],
+				      rta_metrics_policy, NULL);
+		if (rc < 0)
+			return rc;
+		if (tbx[RTAX_MTU])
+			mtu = nla_get_u32(tbx[RTAX_MTU]);
+	}
+
+	if (rtm->rtm_type != RTN_UNICAST)
+		return -EINVAL;
+
+	rc = mctp_route_add(mdev, daddr_start, rtm->rtm_dst_len, mtu,
+			    rtm->rtm_type);
+	return rc;
+}
+
+static int mctp_delroute(struct sk_buff *skb, struct nlmsghdr *nlh,
+			 struct netlink_ext_ack *extack)
+{
+	struct nlattr *tb[RTA_MAX + 1];
+	mctp_eid_t daddr_start;
+	struct mctp_dev *mdev;
+	struct rtmsg *rtm;
+	int rc;
+
+	rc = mctp_route_nlparse(skb, nlh, extack, tb,
+				&rtm, &mdev, &daddr_start);
+	if (rc < 0)
+		return rc;
+
+	/* we only have unicast routes */
+	if (rtm->rtm_type != RTN_UNICAST)
+		return -EINVAL;
+
+	rc = mctp_route_remove(mdev, daddr_start, rtm->rtm_dst_len, RTN_UNICAST);
+	return rc;
+}
+
+static int mctp_fill_rtinfo(struct sk_buff *skb, struct mctp_route *rt,
+			    u32 portid, u32 seq, int event, unsigned int flags)
+{
+	struct nlmsghdr *nlh;
+	struct rtmsg *hdr;
+	void *metrics;
+
+	nlh = nlmsg_put(skb, portid, seq, event, sizeof(*hdr), flags);
+	if (!nlh)
+		return -EMSGSIZE;
+
+	hdr = nlmsg_data(nlh);
+	hdr->rtm_family = AF_MCTP;
+
+	/* we use the _len fields as a number of EIDs, rather than
+	 * a number of bits in the address
+	 */
+	hdr->rtm_dst_len = rt->max - rt->min;
+	hdr->rtm_src_len = 0;
+	hdr->rtm_tos = 0;
+	hdr->rtm_table = RT_TABLE_DEFAULT;
+	hdr->rtm_protocol = RTPROT_STATIC; /* everything is user-defined */
+	hdr->rtm_scope = RT_SCOPE_LINK; /* TODO: scope in mctp_route? */
+	hdr->rtm_type = rt->type;
+
+	if (nla_put_u8(skb, RTA_DST, rt->min))
+		goto cancel;
+
+	metrics = nla_nest_start_noflag(skb, RTA_METRICS);
+	if (!metrics)
+		goto cancel;
+
+	if (rt->mtu) {
+		if (nla_put_u32(skb, RTAX_MTU, rt->mtu))
+			goto cancel;
+	}
+
+	nla_nest_end(skb, metrics);
+
+	if (rt->dev) {
+		if (nla_put_u32(skb, RTA_OIF, rt->dev->dev->ifindex))
+			goto cancel;
+	}
+
+	/* TODO: conditional neighbour physaddr? */
+
+	nlmsg_end(skb, nlh);
+
+	return 0;
+
+cancel:
+	nlmsg_cancel(skb, nlh);
+	return -EMSGSIZE;
+}
+
+static int mctp_dump_rtinfo(struct sk_buff *skb, struct netlink_callback *cb)
+{
+	struct net *net = sock_net(skb->sk);
+	struct mctp_route *rt;
+	int s_idx, idx;
+
+	/* TODO: allow filtering on route data, possibly under
+	 * cb->strict_check
+	 */
+
+	/* TODO: change to struct overlay */
+	s_idx = cb->args[0];
+	idx = 0;
+
+	rcu_read_lock();
+	list_for_each_entry_rcu(rt, &net->mctp.routes, list) {
+		if (idx++ < s_idx)
+			continue;
+		if (mctp_fill_rtinfo(skb, rt,
+				     NETLINK_CB(cb->skb).portid,
+				     cb->nlh->nlmsg_seq,
+				     RTM_NEWROUTE, NLM_F_MULTI) < 0)
+			break;
+	}
+
+	rcu_read_unlock();
+	cb->args[0] = idx;
+
+	return skb->len;
+}
+
+/* net namespace implementation */
+static int __net_init mctp_routes_net_init(struct net *net)
+{
+	struct netns_mctp *ns = &net->mctp;
+
+	INIT_LIST_HEAD(&ns->routes);
+	INIT_HLIST_HEAD(&ns->binds);
+	mutex_init(&ns->bind_lock);
+	INIT_HLIST_HEAD(&ns->keys);
+	spin_lock_init(&ns->keys_lock);
+	WARN_ON(mctp_default_net_set(net, MCTP_INITIAL_DEFAULT_NET));
+	return 0;
+}
+
+static void __net_exit mctp_routes_net_exit(struct net *net)
+{
+	struct mctp_route *rt;
+
+	rcu_read_lock();
+	list_for_each_entry_rcu(rt, &net->mctp.routes, list)
+		mctp_route_release(rt);
+	rcu_read_unlock();
+}
+
+static struct pernet_operations mctp_net_ops = {
+	.init = mctp_routes_net_init,
+	.exit = mctp_routes_net_exit,
+};
+
+int __init mctp_routes_init(void)
+{
+	dev_add_pack(&mctp_packet_type);
+
+	rtnl_register_module(THIS_MODULE, PF_MCTP, RTM_GETROUTE,
+			     NULL, mctp_dump_rtinfo, 0);
+	rtnl_register_module(THIS_MODULE, PF_MCTP, RTM_NEWROUTE,
+			     mctp_newroute, NULL, 0);
+	rtnl_register_module(THIS_MODULE, PF_MCTP, RTM_DELROUTE,
+			     mctp_delroute, NULL, 0);
+
+	return register_pernet_subsys(&mctp_net_ops);
+}
+
+void mctp_routes_exit(void)
+{
+	unregister_pernet_subsys(&mctp_net_ops);
+	rtnl_unregister(PF_MCTP, RTM_DELROUTE);
+	rtnl_unregister(PF_MCTP, RTM_NEWROUTE);
+	rtnl_unregister(PF_MCTP, RTM_GETROUTE);
+	dev_remove_pack(&mctp_packet_type);
+}
+
+#if IS_ENABLED(CONFIG_MCTP_TEST)
+#include "test/route-test.c"
+#endif
diff --git a/net/mctp/test/route-test.c b/net/mctp/test/route-test.c
new file mode 100644
index 000000000..92ea4158f
--- /dev/null
+++ b/net/mctp/test/route-test.c
@@ -0,0 +1,684 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <kunit/test.h>
+
+#include "utils.h"
+
+struct mctp_test_route {
+	struct mctp_route	rt;
+	struct sk_buff_head	pkts;
+};
+
+static int mctp_test_route_output(struct mctp_route *rt, struct sk_buff *skb)
+{
+	struct mctp_test_route *test_rt = container_of(rt, struct mctp_test_route, rt);
+
+	skb_queue_tail(&test_rt->pkts, skb);
+
+	return 0;
+}
+
+/* local version of mctp_route_alloc() */
+static struct mctp_test_route *mctp_route_test_alloc(void)
+{
+	struct mctp_test_route *rt;
+
+	rt = kzalloc(sizeof(*rt), GFP_KERNEL);
+	if (!rt)
+		return NULL;
+
+	INIT_LIST_HEAD(&rt->rt.list);
+	refcount_set(&rt->rt.refs, 1);
+	rt->rt.output = mctp_test_route_output;
+
+	skb_queue_head_init(&rt->pkts);
+
+	return rt;
+}
+
+static struct mctp_test_route *mctp_test_create_route(struct net *net,
+						      struct mctp_dev *dev,
+						      mctp_eid_t eid,
+						      unsigned int mtu)
+{
+	struct mctp_test_route *rt;
+
+	rt = mctp_route_test_alloc();
+	if (!rt)
+		return NULL;
+
+	rt->rt.min = eid;
+	rt->rt.max = eid;
+	rt->rt.mtu = mtu;
+	rt->rt.type = RTN_UNSPEC;
+	if (dev)
+		mctp_dev_hold(dev);
+	rt->rt.dev = dev;
+
+	list_add_rcu(&rt->rt.list, &net->mctp.routes);
+
+	return rt;
+}
+
+static void mctp_test_route_destroy(struct kunit *test,
+				    struct mctp_test_route *rt)
+{
+	unsigned int refs;
+
+	rtnl_lock();
+	list_del_rcu(&rt->rt.list);
+	rtnl_unlock();
+
+	skb_queue_purge(&rt->pkts);
+	if (rt->rt.dev)
+		mctp_dev_put(rt->rt.dev);
+
+	refs = refcount_read(&rt->rt.refs);
+	KUNIT_ASSERT_EQ_MSG(test, refs, 1, "route ref imbalance");
+
+	kfree_rcu(&rt->rt, rcu);
+}
+
+static struct sk_buff *mctp_test_create_skb(const struct mctp_hdr *hdr,
+					    unsigned int data_len)
+{
+	size_t hdr_len = sizeof(*hdr);
+	struct sk_buff *skb;
+	unsigned int i;
+	u8 *buf;
+
+	skb = alloc_skb(hdr_len + data_len, GFP_KERNEL);
+	if (!skb)
+		return NULL;
+
+	memcpy(skb_put(skb, hdr_len), hdr, hdr_len);
+
+	buf = skb_put(skb, data_len);
+	for (i = 0; i < data_len; i++)
+		buf[i] = i & 0xff;
+
+	return skb;
+}
+
+static struct sk_buff *__mctp_test_create_skb_data(const struct mctp_hdr *hdr,
+						   const void *data,
+						   size_t data_len)
+{
+	size_t hdr_len = sizeof(*hdr);
+	struct sk_buff *skb;
+
+	skb = alloc_skb(hdr_len + data_len, GFP_KERNEL);
+	if (!skb)
+		return NULL;
+
+	memcpy(skb_put(skb, hdr_len), hdr, hdr_len);
+	memcpy(skb_put(skb, data_len), data, data_len);
+
+	return skb;
+}
+
+#define mctp_test_create_skb_data(h, d) \
+	__mctp_test_create_skb_data(h, d, sizeof(*d))
+
+struct mctp_frag_test {
+	unsigned int mtu;
+	unsigned int msgsize;
+	unsigned int n_frags;
+};
+
+static void mctp_test_fragment(struct kunit *test)
+{
+	const struct mctp_frag_test *params;
+	int rc, i, n, mtu, msgsize;
+	struct mctp_test_route *rt;
+	struct sk_buff *skb;
+	struct mctp_hdr hdr;
+	u8 seq;
+
+	params = test->param_value;
+	mtu = params->mtu;
+	msgsize = params->msgsize;
+
+	hdr.ver = 1;
+	hdr.src = 8;
+	hdr.dest = 10;
+	hdr.flags_seq_tag = MCTP_HDR_FLAG_TO;
+
+	skb = mctp_test_create_skb(&hdr, msgsize);
+	KUNIT_ASSERT_TRUE(test, skb);
+
+	rt = mctp_test_create_route(&init_net, NULL, 10, mtu);
+	KUNIT_ASSERT_TRUE(test, rt);
+
+	rc = mctp_do_fragment_route(&rt->rt, skb, mtu, MCTP_TAG_OWNER);
+	KUNIT_EXPECT_FALSE(test, rc);
+
+	n = rt->pkts.qlen;
+
+	KUNIT_EXPECT_EQ(test, n, params->n_frags);
+
+	for (i = 0;; i++) {
+		struct mctp_hdr *hdr2;
+		struct sk_buff *skb2;
+		u8 tag_mask, seq2;
+		bool first, last;
+
+		first = i == 0;
+		last = i == (n - 1);
+
+		skb2 = skb_dequeue(&rt->pkts);
+
+		if (!skb2)
+			break;
+
+		hdr2 = mctp_hdr(skb2);
+
+		tag_mask = MCTP_HDR_TAG_MASK | MCTP_HDR_FLAG_TO;
+
+		KUNIT_EXPECT_EQ(test, hdr2->ver, hdr.ver);
+		KUNIT_EXPECT_EQ(test, hdr2->src, hdr.src);
+		KUNIT_EXPECT_EQ(test, hdr2->dest, hdr.dest);
+		KUNIT_EXPECT_EQ(test, hdr2->flags_seq_tag & tag_mask,
+				hdr.flags_seq_tag & tag_mask);
+
+		KUNIT_EXPECT_EQ(test,
+				!!(hdr2->flags_seq_tag & MCTP_HDR_FLAG_SOM), first);
+		KUNIT_EXPECT_EQ(test,
+				!!(hdr2->flags_seq_tag & MCTP_HDR_FLAG_EOM), last);
+
+		seq2 = (hdr2->flags_seq_tag >> MCTP_HDR_SEQ_SHIFT) &
+			MCTP_HDR_SEQ_MASK;
+
+		if (first) {
+			seq = seq2;
+		} else {
+			seq++;
+			KUNIT_EXPECT_EQ(test, seq2, seq & MCTP_HDR_SEQ_MASK);
+		}
+
+		if (!last)
+			KUNIT_EXPECT_EQ(test, skb2->len, mtu);
+		else
+			KUNIT_EXPECT_LE(test, skb2->len, mtu);
+
+		kfree_skb(skb2);
+	}
+
+	mctp_test_route_destroy(test, rt);
+}
+
+static const struct mctp_frag_test mctp_frag_tests[] = {
+	{.mtu = 68, .msgsize = 63, .n_frags = 1},
+	{.mtu = 68, .msgsize = 64, .n_frags = 1},
+	{.mtu = 68, .msgsize = 65, .n_frags = 2},
+	{.mtu = 68, .msgsize = 66, .n_frags = 2},
+	{.mtu = 68, .msgsize = 127, .n_frags = 2},
+	{.mtu = 68, .msgsize = 128, .n_frags = 2},
+	{.mtu = 68, .msgsize = 129, .n_frags = 3},
+	{.mtu = 68, .msgsize = 130, .n_frags = 3},
+};
+
+static void mctp_frag_test_to_desc(const struct mctp_frag_test *t, char *desc)
+{
+	sprintf(desc, "mtu %d len %d -> %d frags",
+		t->msgsize, t->mtu, t->n_frags);
+}
+
+KUNIT_ARRAY_PARAM(mctp_frag, mctp_frag_tests, mctp_frag_test_to_desc);
+
+struct mctp_rx_input_test {
+	struct mctp_hdr hdr;
+	bool input;
+};
+
+static void mctp_test_rx_input(struct kunit *test)
+{
+	const struct mctp_rx_input_test *params;
+	struct mctp_test_route *rt;
+	struct mctp_test_dev *dev;
+	struct sk_buff *skb;
+
+	params = test->param_value;
+
+	dev = mctp_test_create_dev();
+	KUNIT_ASSERT_NOT_ERR_OR_NULL(test, dev);
+
+	rt = mctp_test_create_route(&init_net, dev->mdev, 8, 68);
+	KUNIT_ASSERT_NOT_ERR_OR_NULL(test, rt);
+
+	skb = mctp_test_create_skb(&params->hdr, 1);
+	KUNIT_ASSERT_NOT_ERR_OR_NULL(test, skb);
+
+	__mctp_cb(skb);
+
+	mctp_pkttype_receive(skb, dev->ndev, &mctp_packet_type, NULL);
+
+	KUNIT_EXPECT_EQ(test, !!rt->pkts.qlen, params->input);
+
+	mctp_test_route_destroy(test, rt);
+	mctp_test_destroy_dev(dev);
+}
+
+#define RX_HDR(_ver, _src, _dest, _fst) \
+	{ .ver = _ver, .src = _src, .dest = _dest, .flags_seq_tag = _fst }
+
+/* we have a route for EID 8 only */
+static const struct mctp_rx_input_test mctp_rx_input_tests[] = {
+	{ .hdr = RX_HDR(1, 10, 8, 0), .input = true },
+	{ .hdr = RX_HDR(1, 10, 9, 0), .input = false }, /* no input route */
+	{ .hdr = RX_HDR(2, 10, 8, 0), .input = false }, /* invalid version */
+};
+
+static void mctp_rx_input_test_to_desc(const struct mctp_rx_input_test *t,
+				       char *desc)
+{
+	sprintf(desc, "{%x,%x,%x,%x}", t->hdr.ver, t->hdr.src, t->hdr.dest,
+		t->hdr.flags_seq_tag);
+}
+
+KUNIT_ARRAY_PARAM(mctp_rx_input, mctp_rx_input_tests,
+		  mctp_rx_input_test_to_desc);
+
+/* set up a local dev, route on EID 8, and a socket listening on type 0 */
+static void __mctp_route_test_init(struct kunit *test,
+				   struct mctp_test_dev **devp,
+				   struct mctp_test_route **rtp,
+				   struct socket **sockp)
+{
+	struct sockaddr_mctp addr = {0};
+	struct mctp_test_route *rt;
+	struct mctp_test_dev *dev;
+	struct socket *sock;
+	int rc;
+
+	dev = mctp_test_create_dev();
+	KUNIT_ASSERT_NOT_ERR_OR_NULL(test, dev);
+
+	rt = mctp_test_create_route(&init_net, dev->mdev, 8, 68);
+	KUNIT_ASSERT_NOT_ERR_OR_NULL(test, rt);
+
+	rc = sock_create_kern(&init_net, AF_MCTP, SOCK_DGRAM, 0, &sock);
+	KUNIT_ASSERT_EQ(test, rc, 0);
+
+	addr.smctp_family = AF_MCTP;
+	addr.smctp_network = MCTP_NET_ANY;
+	addr.smctp_addr.s_addr = 8;
+	addr.smctp_type = 0;
+	rc = kernel_bind(sock, (struct sockaddr *)&addr, sizeof(addr));
+	KUNIT_ASSERT_EQ(test, rc, 0);
+
+	*rtp = rt;
+	*devp = dev;
+	*sockp = sock;
+}
+
+static void __mctp_route_test_fini(struct kunit *test,
+				   struct mctp_test_dev *dev,
+				   struct mctp_test_route *rt,
+				   struct socket *sock)
+{
+	sock_release(sock);
+	mctp_test_route_destroy(test, rt);
+	mctp_test_destroy_dev(dev);
+}
+
+struct mctp_route_input_sk_test {
+	struct mctp_hdr hdr;
+	u8 type;
+	bool deliver;
+};
+
+static void mctp_test_route_input_sk(struct kunit *test)
+{
+	const struct mctp_route_input_sk_test *params;
+	struct sk_buff *skb, *skb2;
+	struct mctp_test_route *rt;
+	struct mctp_test_dev *dev;
+	struct socket *sock;
+	int rc;
+
+	params = test->param_value;
+
+	__mctp_route_test_init(test, &dev, &rt, &sock);
+
+	skb = mctp_test_create_skb_data(&params->hdr, &params->type);
+	KUNIT_ASSERT_NOT_ERR_OR_NULL(test, skb);
+
+	skb->dev = dev->ndev;
+	__mctp_cb(skb);
+
+	rc = mctp_route_input(&rt->rt, skb);
+
+	if (params->deliver) {
+		KUNIT_EXPECT_EQ(test, rc, 0);
+
+		skb2 = skb_recv_datagram(sock->sk, MSG_DONTWAIT, &rc);
+		KUNIT_EXPECT_NOT_ERR_OR_NULL(test, skb2);
+		KUNIT_EXPECT_EQ(test, skb->len, 1);
+
+		skb_free_datagram(sock->sk, skb2);
+
+	} else {
+		KUNIT_EXPECT_NE(test, rc, 0);
+		skb2 = skb_recv_datagram(sock->sk, MSG_DONTWAIT, &rc);
+		KUNIT_EXPECT_NULL(test, skb2);
+	}
+
+	__mctp_route_test_fini(test, dev, rt, sock);
+}
+
+#define FL_S	(MCTP_HDR_FLAG_SOM)
+#define FL_E	(MCTP_HDR_FLAG_EOM)
+#define FL_TO	(MCTP_HDR_FLAG_TO)
+#define FL_T(t)	((t) & MCTP_HDR_TAG_MASK)
+
+static const struct mctp_route_input_sk_test mctp_route_input_sk_tests[] = {
+	{ .hdr = RX_HDR(1, 10, 8, FL_S | FL_E | FL_TO), .type = 0, .deliver = true },
+	{ .hdr = RX_HDR(1, 10, 8, FL_S | FL_E | FL_TO), .type = 1, .deliver = false },
+	{ .hdr = RX_HDR(1, 10, 8, FL_S | FL_E), .type = 0, .deliver = false },
+	{ .hdr = RX_HDR(1, 10, 8, FL_E | FL_TO), .type = 0, .deliver = false },
+	{ .hdr = RX_HDR(1, 10, 8, FL_TO), .type = 0, .deliver = false },
+	{ .hdr = RX_HDR(1, 10, 8, 0), .type = 0, .deliver = false },
+};
+
+static void mctp_route_input_sk_to_desc(const struct mctp_route_input_sk_test *t,
+					char *desc)
+{
+	sprintf(desc, "{%x,%x,%x,%x} type %d", t->hdr.ver, t->hdr.src,
+		t->hdr.dest, t->hdr.flags_seq_tag, t->type);
+}
+
+KUNIT_ARRAY_PARAM(mctp_route_input_sk, mctp_route_input_sk_tests,
+		  mctp_route_input_sk_to_desc);
+
+struct mctp_route_input_sk_reasm_test {
+	const char *name;
+	struct mctp_hdr hdrs[4];
+	int n_hdrs;
+	int rx_len;
+};
+
+static void mctp_test_route_input_sk_reasm(struct kunit *test)
+{
+	const struct mctp_route_input_sk_reasm_test *params;
+	struct sk_buff *skb, *skb2;
+	struct mctp_test_route *rt;
+	struct mctp_test_dev *dev;
+	struct socket *sock;
+	int i, rc;
+	u8 c;
+
+	params = test->param_value;
+
+	__mctp_route_test_init(test, &dev, &rt, &sock);
+
+	for (i = 0; i < params->n_hdrs; i++) {
+		c = i;
+		skb = mctp_test_create_skb_data(&params->hdrs[i], &c);
+		KUNIT_ASSERT_NOT_ERR_OR_NULL(test, skb);
+
+		skb->dev = dev->ndev;
+		__mctp_cb(skb);
+
+		rc = mctp_route_input(&rt->rt, skb);
+	}
+
+	skb2 = skb_recv_datagram(sock->sk, MSG_DONTWAIT, &rc);
+
+	if (params->rx_len) {
+		KUNIT_EXPECT_NOT_ERR_OR_NULL(test, skb2);
+		KUNIT_EXPECT_EQ(test, skb2->len, params->rx_len);
+		skb_free_datagram(sock->sk, skb2);
+
+	} else {
+		KUNIT_EXPECT_NULL(test, skb2);
+	}
+
+	__mctp_route_test_fini(test, dev, rt, sock);
+}
+
+#define RX_FRAG(f, s) RX_HDR(1, 10, 8, FL_TO | (f) | ((s) << MCTP_HDR_SEQ_SHIFT))
+
+static const struct mctp_route_input_sk_reasm_test mctp_route_input_sk_reasm_tests[] = {
+	{
+		.name = "single packet",
+		.hdrs = {
+			RX_FRAG(FL_S | FL_E, 0),
+		},
+		.n_hdrs = 1,
+		.rx_len = 1,
+	},
+	{
+		.name = "single packet, offset seq",
+		.hdrs = {
+			RX_FRAG(FL_S | FL_E, 1),
+		},
+		.n_hdrs = 1,
+		.rx_len = 1,
+	},
+	{
+		.name = "start & end packets",
+		.hdrs = {
+			RX_FRAG(FL_S, 0),
+			RX_FRAG(FL_E, 1),
+		},
+		.n_hdrs = 2,
+		.rx_len = 2,
+	},
+	{
+		.name = "start & end packets, offset seq",
+		.hdrs = {
+			RX_FRAG(FL_S, 1),
+			RX_FRAG(FL_E, 2),
+		},
+		.n_hdrs = 2,
+		.rx_len = 2,
+	},
+	{
+		.name = "start & end packets, out of order",
+		.hdrs = {
+			RX_FRAG(FL_E, 1),
+			RX_FRAG(FL_S, 0),
+		},
+		.n_hdrs = 2,
+		.rx_len = 0,
+	},
+	{
+		.name = "start, middle & end packets",
+		.hdrs = {
+			RX_FRAG(FL_S, 0),
+			RX_FRAG(0,    1),
+			RX_FRAG(FL_E, 2),
+		},
+		.n_hdrs = 3,
+		.rx_len = 3,
+	},
+	{
+		.name = "missing seq",
+		.hdrs = {
+			RX_FRAG(FL_S, 0),
+			RX_FRAG(FL_E, 2),
+		},
+		.n_hdrs = 2,
+		.rx_len = 0,
+	},
+	{
+		.name = "seq wrap",
+		.hdrs = {
+			RX_FRAG(FL_S, 3),
+			RX_FRAG(FL_E, 0),
+		},
+		.n_hdrs = 2,
+		.rx_len = 2,
+	},
+};
+
+static void mctp_route_input_sk_reasm_to_desc(
+				const struct mctp_route_input_sk_reasm_test *t,
+				char *desc)
+{
+	sprintf(desc, "%s", t->name);
+}
+
+KUNIT_ARRAY_PARAM(mctp_route_input_sk_reasm, mctp_route_input_sk_reasm_tests,
+		  mctp_route_input_sk_reasm_to_desc);
+
+struct mctp_route_input_sk_keys_test {
+	const char	*name;
+	mctp_eid_t	key_peer_addr;
+	mctp_eid_t	key_local_addr;
+	u8		key_tag;
+	struct mctp_hdr hdr;
+	bool		deliver;
+};
+
+/* test packet rx in the presence of various key configurations */
+static void mctp_test_route_input_sk_keys(struct kunit *test)
+{
+	const struct mctp_route_input_sk_keys_test *params;
+	struct mctp_test_route *rt;
+	struct sk_buff *skb, *skb2;
+	struct mctp_test_dev *dev;
+	struct mctp_sk_key *key;
+	struct netns_mctp *mns;
+	struct mctp_sock *msk;
+	struct socket *sock;
+	unsigned long flags;
+	int rc;
+	u8 c;
+
+	params = test->param_value;
+
+	dev = mctp_test_create_dev();
+	KUNIT_ASSERT_NOT_ERR_OR_NULL(test, dev);
+
+	rt = mctp_test_create_route(&init_net, dev->mdev, 8, 68);
+	KUNIT_ASSERT_NOT_ERR_OR_NULL(test, rt);
+
+	rc = sock_create_kern(&init_net, AF_MCTP, SOCK_DGRAM, 0, &sock);
+	KUNIT_ASSERT_EQ(test, rc, 0);
+
+	msk = container_of(sock->sk, struct mctp_sock, sk);
+	mns = &sock_net(sock->sk)->mctp;
+
+	/* set the incoming tag according to test params */
+	key = mctp_key_alloc(msk, params->key_local_addr, params->key_peer_addr,
+			     params->key_tag, GFP_KERNEL);
+
+	KUNIT_ASSERT_NOT_ERR_OR_NULL(test, key);
+
+	spin_lock_irqsave(&mns->keys_lock, flags);
+	mctp_reserve_tag(&init_net, key, msk);
+	spin_unlock_irqrestore(&mns->keys_lock, flags);
+
+	/* create packet and route */
+	c = 0;
+	skb = mctp_test_create_skb_data(&params->hdr, &c);
+	KUNIT_ASSERT_NOT_ERR_OR_NULL(test, skb);
+
+	skb->dev = dev->ndev;
+	__mctp_cb(skb);
+
+	rc = mctp_route_input(&rt->rt, skb);
+
+	/* (potentially) receive message */
+	skb2 = skb_recv_datagram(sock->sk, MSG_DONTWAIT, &rc);
+
+	if (params->deliver)
+		KUNIT_EXPECT_NOT_ERR_OR_NULL(test, skb2);
+	else
+		KUNIT_EXPECT_PTR_EQ(test, skb2, NULL);
+
+	if (skb2)
+		skb_free_datagram(sock->sk, skb2);
+
+	mctp_key_unref(key);
+	__mctp_route_test_fini(test, dev, rt, sock);
+}
+
+static const struct mctp_route_input_sk_keys_test mctp_route_input_sk_keys_tests[] = {
+	{
+		.name = "direct match",
+		.key_peer_addr = 9,
+		.key_local_addr = 8,
+		.key_tag = 1,
+		.hdr = RX_HDR(1, 9, 8, FL_S | FL_E | FL_T(1)),
+		.deliver = true,
+	},
+	{
+		.name = "flipped src/dest",
+		.key_peer_addr = 8,
+		.key_local_addr = 9,
+		.key_tag = 1,
+		.hdr = RX_HDR(1, 9, 8, FL_S | FL_E | FL_T(1)),
+		.deliver = false,
+	},
+	{
+		.name = "peer addr mismatch",
+		.key_peer_addr = 9,
+		.key_local_addr = 8,
+		.key_tag = 1,
+		.hdr = RX_HDR(1, 10, 8, FL_S | FL_E | FL_T(1)),
+		.deliver = false,
+	},
+	{
+		.name = "tag value mismatch",
+		.key_peer_addr = 9,
+		.key_local_addr = 8,
+		.key_tag = 1,
+		.hdr = RX_HDR(1, 9, 8, FL_S | FL_E | FL_T(2)),
+		.deliver = false,
+	},
+	{
+		.name = "TO mismatch",
+		.key_peer_addr = 9,
+		.key_local_addr = 8,
+		.key_tag = 1,
+		.hdr = RX_HDR(1, 9, 8, FL_S | FL_E | FL_T(1) | FL_TO),
+		.deliver = false,
+	},
+	{
+		.name = "broadcast response",
+		.key_peer_addr = MCTP_ADDR_ANY,
+		.key_local_addr = 8,
+		.key_tag = 1,
+		.hdr = RX_HDR(1, 11, 8, FL_S | FL_E | FL_T(1)),
+		.deliver = true,
+	},
+	{
+		.name = "any local match",
+		.key_peer_addr = 12,
+		.key_local_addr = MCTP_ADDR_ANY,
+		.key_tag = 1,
+		.hdr = RX_HDR(1, 12, 8, FL_S | FL_E | FL_T(1)),
+		.deliver = true,
+	},
+};
+
+static void mctp_route_input_sk_keys_to_desc(
+				const struct mctp_route_input_sk_keys_test *t,
+				char *desc)
+{
+	sprintf(desc, "%s", t->name);
+}
+
+KUNIT_ARRAY_PARAM(mctp_route_input_sk_keys, mctp_route_input_sk_keys_tests,
+		  mctp_route_input_sk_keys_to_desc);
+
+static struct kunit_case mctp_test_cases[] = {
+	KUNIT_CASE_PARAM(mctp_test_fragment, mctp_frag_gen_params),
+	KUNIT_CASE_PARAM(mctp_test_rx_input, mctp_rx_input_gen_params),
+	KUNIT_CASE_PARAM(mctp_test_route_input_sk, mctp_route_input_sk_gen_params),
+	KUNIT_CASE_PARAM(mctp_test_route_input_sk_reasm,
+			 mctp_route_input_sk_reasm_gen_params),
+	KUNIT_CASE_PARAM(mctp_test_route_input_sk_keys,
+			 mctp_route_input_sk_keys_gen_params),
+	{}
+};
+
+static struct kunit_suite mctp_test_suite = {
+	.name = "mctp",
+	.test_cases = mctp_test_cases,
+};
+
+kunit_test_suite(mctp_test_suite);
diff --git a/net/mctp/test/utils.c b/net/mctp/test/utils.c
new file mode 100644
index 000000000..e03ba66bb
--- /dev/null
+++ b/net/mctp/test/utils.c
@@ -0,0 +1,66 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <linux/netdevice.h>
+#include <linux/mctp.h>
+#include <linux/if_arp.h>
+
+#include <net/mctpdevice.h>
+#include <net/pkt_sched.h>
+
+#include "utils.h"
+
+static netdev_tx_t mctp_test_dev_tx(struct sk_buff *skb,
+				    struct net_device *ndev)
+{
+	kfree_skb(skb);
+	return NETDEV_TX_OK;
+}
+
+static const struct net_device_ops mctp_test_netdev_ops = {
+	.ndo_start_xmit = mctp_test_dev_tx,
+};
+
+static void mctp_test_dev_setup(struct net_device *ndev)
+{
+	ndev->type = ARPHRD_MCTP;
+	ndev->mtu = MCTP_DEV_TEST_MTU;
+	ndev->hard_header_len = 0;
+	ndev->addr_len = 0;
+	ndev->tx_queue_len = DEFAULT_TX_QUEUE_LEN;
+	ndev->flags = IFF_NOARP;
+	ndev->netdev_ops = &mctp_test_netdev_ops;
+	ndev->needs_free_netdev = true;
+}
+
+struct mctp_test_dev *mctp_test_create_dev(void)
+{
+	struct mctp_test_dev *dev;
+	struct net_device *ndev;
+	int rc;
+
+	ndev = alloc_netdev(sizeof(*dev), "mctptest%d", NET_NAME_ENUM,
+			    mctp_test_dev_setup);
+	if (!ndev)
+		return NULL;
+
+	dev = netdev_priv(ndev);
+	dev->ndev = ndev;
+
+	rc = register_netdev(ndev);
+	if (rc) {
+		free_netdev(ndev);
+		return NULL;
+	}
+
+	rcu_read_lock();
+	dev->mdev = __mctp_dev_get(ndev);
+	rcu_read_unlock();
+
+	return dev;
+}
+
+void mctp_test_destroy_dev(struct mctp_test_dev *dev)
+{
+	mctp_dev_put(dev->mdev);
+	unregister_netdev(dev->ndev);
+}
diff --git a/net/mctp/test/utils.h b/net/mctp/test/utils.h
new file mode 100644
index 000000000..df6aa1c03
--- /dev/null
+++ b/net/mctp/test/utils.h
@@ -0,0 +1,20 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+#ifndef __NET_MCTP_TEST_UTILS_H
+#define __NET_MCTP_TEST_UTILS_H
+
+#include <kunit/test.h>
+
+#define MCTP_DEV_TEST_MTU	68
+
+struct mctp_test_dev {
+	struct net_device *ndev;
+	struct mctp_dev *mdev;
+};
+
+struct mctp_test_dev;
+
+struct mctp_test_dev *mctp_test_create_dev(void);
+void mctp_test_destroy_dev(struct mctp_test_dev *dev);
+
+#endif /* __NET_MCTP_TEST_UTILS_H */