mctp: Populate socket implementation

Start filling-out the socket syscalls: bind, sendmsg & recvmsg.

This requires an input route implementation, so we add to
mctp_route_input, allowing lookups on binds & message tags. This just
handles single-packet messages at present, we will add fragmentation in
a future change.

Signed-off-by: Jeremy Kerr <jk@codeconstruct.com.au>
Signed-off-by: David S. Miller <davem@davemloft.net>

include/net/mctp.h

@@ -12,6 +12,7 @@
 #include <linux/bits.h>
 #include <linux/mctp.h>
 #include <net/net_namespace.h>
+#include <net/sock.h>
 
 /* MCTP packet definitions */
 struct mctp_hdr {
@@ -46,6 +47,64 @@ static inline struct mctp_hdr *mctp_hdr(struct sk_buff *skb)
 	return (struct mctp_hdr *)skb_network_header(skb);
 }
 
+/* socket implementation */
+struct mctp_sock {
+	struct sock	sk;
+
+	/* bind() params */
+	int		bind_net;
+	mctp_eid_t	bind_addr;
+	__u8		bind_type;
+
+	/* list of mctp_sk_key, for incoming tag lookup. updates protected
+	 * by sk->net->keys_lock
+	 */
+	struct hlist_head keys;
+};
+
+/* Key for matching incoming packets to sockets or reassembly contexts.
+ * Packets are matched on (src,dest,tag).
+ *
+ * Lifetime requirements:
+ *
+ *  - keys are free()ed via RCU
+ *
+ *  - a mctp_sk_key contains a reference to a struct sock; this is valid
+ *    for the life of the key. On sock destruction (through unhash), the key is
+ *    removed from lists (see below), and will not be observable after a RCU
+ *    grace period.
+ *
+ *    any RX occurring within that grace period may still queue to the socket,
+ *    but will hit the SOCK_DEAD case before the socket is freed.
+ *
+ * - these mctp_sk_keys appear on two lists:
+ *     1) the struct mctp_sock->keys list
+ *     2) the struct netns_mctp->keys list
+ *
+ *        updates to either list are performed under the netns_mctp->keys
+ *        lock.
+ *
+ * - there is a single destruction path for a mctp_sk_key - through socket
+ *   unhash (see mctp_sk_unhash). This performs the list removal under
+ *   keys_lock.
+ */
+struct mctp_sk_key {
+	mctp_eid_t	peer_addr;
+	mctp_eid_t	local_addr;
+	__u8		tag; /* incoming tag match; invert TO for local */
+
+	/* we hold a ref to sk when set */
+	struct sock	*sk;
+
+	/* routing lookup list */
+	struct hlist_node hlist;
+
+	/* per-socket list */
+	struct hlist_node sklist;
+
+	struct rcu_head	rcu;
+};
+
 struct mctp_skb_cb {
 	unsigned int	magic;
 	unsigned int	net;

include/net/netns/mctp.h

@@ -12,6 +12,19 @@ struct netns_mctp {
 	/* Only updated under RTNL, entries freed via RCU */
 	struct list_head routes;
 
+	/* Bound sockets: list of sockets bound by type.
+	 * This list is updated from non-atomic contexts (under bind_lock),
+	 * and read (under rcu) in packet rx
+	 */
+	struct mutex bind_lock;
+	struct hlist_head binds;
+
+	/* tag allocations. This list is read and updated from atomic contexts,
+	 * but elements are free()ed after a RCU grace-period
+	 */
+	spinlock_t keys_lock;
+	struct hlist_head keys;
+
 	/* neighbour table */
 	struct mutex neigh_lock;
 	struct list_head neighbours;

net/mctp/af_mctp.c

@@ -18,10 +18,6 @@
 
 /* socket implementation */
 
-struct mctp_sock {
-	struct sock	sk;
-};
-
 static int mctp_release(struct socket *sock)
 {
 	struct sock *sk = sock->sk;
@@ -36,18 +32,160 @@ static int mctp_release(struct socket *sock)
 
 static int mctp_bind(struct socket *sock, struct sockaddr *addr, int addrlen)
 {
-	return 0;
+	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;
+
+	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)
 {
-	return 0;
+	DECLARE_SOCKADDR(struct sockaddr_mctp *, addr, msg->msg_name);
+	const int hlen = MCTP_HEADER_MAXLEN + sizeof(struct mctp_hdr);
+	int rc, addrlen = msg->msg_namelen;
+	struct sock *sk = sock->sk;
+	struct mctp_skb_cb *cb;
+	struct mctp_route *rt;
+	struct sk_buff *skb;
+
+	if (addr) {
+		if (addrlen < sizeof(struct sockaddr_mctp))
+			return -EINVAL;
+		if (addr->smctp_family != AF_MCTP)
+			return -EINVAL;
+		if (addr->smctp_tag & ~(MCTP_TAG_MASK | MCTP_TAG_OWNER))
+			return -EINVAL;
+
+	} else {
+		/* TODO: connect()ed sockets */
+		return -EDESTADDRREQ;
+	}
+
+	if (!capable(CAP_NET_RAW))
+		return -EACCES;
+
+	rt = mctp_route_lookup(sock_net(sk), addr->smctp_network,
+			       addr->smctp_addr.s_addr);
+	if (!rt)
+		return -EHOSTUNREACH;
+
+	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) {
+		kfree_skb(skb);
+		return rc;
+	}
+
+	/* set up cb */
+	cb = __mctp_cb(skb);
+	cb->net = addr->smctp_network;
+
+	rc = mctp_local_output(sk, rt, skb, addr->smctp_addr.s_addr,
+			       addr->smctp_tag);
+
+	return rc ? : len;
 }
 
 static int mctp_recvmsg(struct socket *sock, struct msghdr *msg, size_t len,
 			int flags)
 {
-	return 0;
+	DECLARE_SOCKADDR(struct sockaddr_mctp *, addr, msg->msg_name);
+	struct sock *sk = 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, flags & MSG_DONTWAIT, &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_ts_and_drops(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);
+
+		hdr = mctp_hdr(skb);
+		addr = msg->msg_name;
+		addr->smctp_family = AF_MCTP;
+		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);
+		msg->msg_namelen = sizeof(*addr);
+	}
+
+	rc = len;
+
+	if (flags & MSG_TRUNC)
+		rc = msglen;
+
+out_free:
+	skb_free_datagram(sk, skb);
+	return rc;
 }
 
 static int mctp_setsockopt(struct socket *sock, int level, int optname,
@@ -83,16 +221,63 @@ static const struct proto_ops mctp_dgram_ops = {
 	.sendpage	= sock_no_sendpage,
 };
 
+static int mctp_sk_init(struct sock *sk)
+{
+	struct mctp_sock *msk = container_of(sk, struct mctp_sock, sk);
+
+	INIT_HLIST_HEAD(&msk->keys);
+	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);
+	struct mctp_sk_key *key;
+	struct hlist_node *tmp;
+	unsigned long flags;
+
+	/* 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) {
+		hlist_del_rcu(&key->sklist);
+		hlist_del_rcu(&key->hlist);
+		kfree_rcu(key, rcu);
+	}
+	spin_unlock_irqrestore(&net->mctp.keys_lock, flags);
+
+	synchronize_rcu();
+}
+
 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,
@@ -147,6 +332,10 @@ 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);

net/mctp/route.c

@@ -30,10 +30,139 @@ static int mctp_route_discard(struct mctp_route *route, struct sk_buff *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 (msk->bind_addr != MCTP_ADDR_ANY &&
+		    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 (key->local_addr != local)
+		return false;
+
+	if (key->peer_addr != peer)
+		return false;
+
+	if (key->tag != tag)
+		return false;
+
+	return true;
+}
+
+static struct mctp_sk_key *mctp_lookup_key(struct net *net, struct sk_buff *skb,
+					   mctp_eid_t peer)
+{
+	struct mctp_sk_key *key, *ret;
+	struct mctp_hdr *mh;
+	u8 tag;
+
+	WARN_ON(!rcu_read_lock_held());
+
+	mh = mctp_hdr(skb);
+	tag = mh->flags_seq_tag & (MCTP_HDR_TAG_MASK | MCTP_HDR_FLAG_TO);
+
+	ret = NULL;
+
+	hlist_for_each_entry_rcu(key, &net->mctp.keys, hlist) {
+		if (mctp_key_match(key, mh->dest, peer, tag)) {
+			ret = key;
+			break;
+		}
+	}
+
+	return ret;
+}
+
 static int mctp_route_input(struct mctp_route *route, struct sk_buff *skb)
 {
-	/* -> to local stack */
+	struct net *net = dev_net(skb->dev);
-	/* TODO: socket lookup, reassemble */
+	struct mctp_sk_key *key;
+	struct mctp_sock *msk;
+	struct mctp_hdr *mh;
+
+	msk = NULL;
+
+	/* 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 drop;
+
+	/* grab header, advance data ptr */
+	mh = mctp_hdr(skb);
+	skb_pull(skb, sizeof(struct mctp_hdr));
+
+	if (mh->ver != 1)
+		goto drop;
+
+	/* TODO: reassembly */
+	if ((mh->flags_seq_tag & (MCTP_HDR_FLAG_SOM | MCTP_HDR_FLAG_EOM))
+				!= (MCTP_HDR_FLAG_SOM | MCTP_HDR_FLAG_EOM))
+		goto drop;
+
+	rcu_read_lock();
+	/* 1. lookup socket matching (src,dest,tag) */
+	key = mctp_lookup_key(net, skb, mh->src);
+
+	/* 2. lookup socket macthing (BCAST,dest,tag) */
+	if (!key)
+		key = mctp_lookup_key(net, skb, MCTP_ADDR_ANY);
+
+	/* 3. SOM? -> lookup bound socket, conditionally (!EOM) create
+	 * mapping for future (1)/(2).
+	 */
+	if (key)
+		msk = container_of(key->sk, struct mctp_sock, sk);
+	else if (!msk && (mh->flags_seq_tag & MCTP_HDR_FLAG_SOM))
+		msk = mctp_lookup_bind(net, skb);
+
+	if (!msk)
+		goto unlock_drop;
+
+	sock_queue_rcv_skb(&msk->sk, skb);
+
+	rcu_read_unlock();
+
+	return 0;
+
+unlock_drop:
+	rcu_read_unlock();
+drop:
 	kfree_skb(skb);
 	return 0;
 }
@@ -91,6 +220,80 @@ static struct mctp_route *mctp_route_alloc(void)
 	return rt;
 }
 
+/* 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->sk = &msk->sk;
+
+	/* 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);
+}
+
+/* Allocate a locally-owned tag value for (saddr, daddr), and reserve
+ * it for the socket msk
+ */
+static int mctp_alloc_local_tag(struct mctp_sock *msk,
+				mctp_eid_t saddr, mctp_eid_t daddr, u8 *tagp)
+{
+	struct net *net = sock_net(&msk->sk);
+	struct netns_mctp *mns = &net->mctp;
+	struct mctp_sk_key *key, *tmp;
+	unsigned long flags;
+	int rc = -EAGAIN;
+	u8 tagbits;
+
+	/* be optimistic, alloc now */
+	key = kzalloc(sizeof(*key), GFP_KERNEL);
+	if (!key)
+		return -ENOMEM;
+	key->local_addr = saddr;
+	key->peer_addr = daddr;
+
+	/* 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) {
+		/* if we don't own the tag, it can't conflict */
+		if (tmp->tag & MCTP_HDR_FLAG_TO)
+			continue;
+
+		if ((tmp->peer_addr == daddr ||
+		     tmp->peer_addr == MCTP_ADDR_ANY) &&
+		    tmp->local_addr == saddr)
+			tagbits &= ~(1 << tmp->tag);
+
+		if (!tagbits)
+			break;
+	}
+
+	if (tagbits) {
+		key->tag = __ffs(tagbits);
+		mctp_reserve_tag(net, key, msk);
+		*tagp = key->tag;
+		rc = 0;
+	}
+
+	spin_unlock_irqrestore(&mns->keys_lock, flags);
+
+	if (!tagbits)
+		kfree(key);
+
+	return rc;
+}
+
 /* routing lookups */
 static bool mctp_rt_match_eid(struct mctp_route *rt,
 			      unsigned int net, mctp_eid_t eid)
@@ -140,11 +343,13 @@ int mctp_do_route(struct mctp_route *rt, struct sk_buff *skb)
 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_hdr *hdr;
 	unsigned long flags;
 	mctp_eid_t saddr;
 	int rc;
+	u8 tag;
 
 	if (WARN_ON(!rt->dev))
 		return -EINVAL;
@@ -162,6 +367,15 @@ int mctp_local_output(struct sock *sk, struct mctp_route *rt,
 	if (rc)
 		return rc;
 
+	if (req_tag & MCTP_HDR_FLAG_TO) {
+		rc = mctp_alloc_local_tag(msk, saddr, daddr, &tag);
+		if (rc)
+			return rc;
+		tag |= MCTP_HDR_FLAG_TO;
+	} else {
+		tag = req_tag;
+	}
+
 	/* TODO: we have the route MTU here; packetise */
 
 	skb_reset_transport_header(skb);
@@ -171,8 +385,10 @@ int mctp_local_output(struct sock *sk, struct mctp_route *rt,
 	hdr->ver = 1;
 	hdr->dest = daddr;
 	hdr->src = saddr;
-	hdr->flags_seq_tag = MCTP_HDR_FLAG_SOM | MCTP_HDR_FLAG_EOM; /* TODO */
+	hdr->flags_seq_tag = MCTP_HDR_FLAG_SOM | MCTP_HDR_FLAG_EOM | /* TODO */
+		tag;
 
+	skb->dev = rt->dev->dev;
 	skb->protocol = htons(ETH_P_MCTP);
 	skb->priority = 0;
 
@@ -529,6 +745,10 @@ 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);
 	return 0;
 }