mctp: Implement extended addressing

This change allows an extended address struct - struct sockaddr_mctp_ext
- to be passed to sendmsg/recvmsg. This allows userspace to specify
output ifindex and physical address information (for sendmsg) or receive
the input ifindex/physaddr for incoming messages (for recvmsg). This is
typically used by userspace for MCTP address discovery and assignment
operations.

The extended addressing facility is conditional on a new sockopt:
MCTP_OPT_ADDR_EXT; userspace must explicitly enable addressing before
the kernel will consume/populate the extended address data.

Includes a fix for an uninitialised var:
Reported-by: kernel test robot <lkp@intel.com>

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

include/linux/socket.h

@@ -365,6 +365,7 @@ struct ucred {
 #define SOL_TLS		282
 #define SOL_XDP		283
 #define SOL_MPTCP	284
+#define SOL_MCTP	285
 
 /* IPX options */
 #define IPX_TYPE	1

include/net/mctp.h

@@ -11,6 +11,7 @@
 
 #include <linux/bits.h>
 #include <linux/mctp.h>
+#include <linux/netdevice.h>
 #include <net/net_namespace.h>
 #include <net/sock.h>
 
@@ -58,6 +59,9 @@ struct mctp_sock {
 	mctp_eid_t	bind_addr;
 	__u8		bind_type;
 
+	/* sendmsg()/recvmsg() uses struct sockaddr_mctp_ext */
+	bool		addr_ext;
+
 	/* list of mctp_sk_key, for incoming tag lookup. updates protected
 	 * by sk->net->keys_lock
 	 */
@@ -153,7 +157,10 @@ struct mctp_sk_key {
 struct mctp_skb_cb {
 	unsigned int	magic;
 	unsigned int	net;
+	int		ifindex; /* extended/direct addressing if set */
 	mctp_eid_t	src;
+	unsigned char	halen;
+	unsigned char	haddr[MAX_ADDR_LEN];
 };
 
 /* skb control-block accessors with a little extra debugging for initial
@@ -177,6 +184,7 @@ static inline struct mctp_skb_cb *mctp_cb(struct sk_buff *skb)
 {
 	struct mctp_skb_cb *cb = (void *)skb->cb;
 
+	BUILD_BUG_ON(sizeof(struct mctp_skb_cb) > sizeof(skb->cb));
 	WARN_ON(cb->magic != 0x4d435450);
 	return (void *)(skb->cb);
 }
@@ -189,8 +197,7 @@ static inline struct mctp_skb_cb *mctp_cb(struct sk_buff *skb)
  *
  * Updates to the route table are performed under rtnl; all reads under RCU,
  * so routes cannot be referenced over a RCU grace period. Specifically: A
- * caller cannot block between mctp_route_lookup and passing the route to
- * mctp_do_route.
+ * caller cannot block between mctp_route_lookup and mctp_route_release()
  */
 struct mctp_route {
 	mctp_eid_t		min, max;
@@ -210,8 +217,6 @@ struct mctp_route {
 struct mctp_route *mctp_route_lookup(struct net *net, unsigned int dnet,
 				     mctp_eid_t daddr);
 
-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);
 

include/uapi/linux/mctp.h

@@ -11,6 +11,7 @@
 
 #include <linux/types.h>
 #include <linux/socket.h>
+#include <linux/netdevice.h>
 
 typedef __u8			mctp_eid_t;
 
@@ -28,6 +29,14 @@ struct sockaddr_mctp {
 	__u8			__smctp_pad1;
 };
 
+struct sockaddr_mctp_ext {
+	struct sockaddr_mctp	smctp_base;
+	int			smctp_ifindex;
+	__u8			smctp_halen;
+	__u8			__smctp_pad0[3];
+	__u8			smctp_haddr[MAX_ADDR_LEN];
+};
+
 #define MCTP_NET_ANY		0x0
 
 #define MCTP_ADDR_NULL		0x00
@@ -36,4 +45,6 @@ struct sockaddr_mctp {
 #define MCTP_TAG_MASK		0x07
 #define MCTP_TAG_OWNER		0x08
 
+#define MCTP_OPT_ADDR_EXT	1
+
 #endif /* __UAPI_MCTP_H */

net/mctp/af_mctp.c

@@ -77,6 +77,7 @@ static int mctp_sendmsg(struct socket *sock, struct msghdr *msg, size_t len)
 	const int hlen = MCTP_HEADER_MAXLEN + sizeof(struct mctp_hdr);
 	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;
@@ -100,11 +101,6 @@ static int mctp_sendmsg(struct socket *sock, struct msghdr *msg, size_t len)
 	if (addr->smctp_network == MCTP_NET_ANY)
 		addr->smctp_network = mctp_default_net(sock_net(sk));
 
-	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)
@@ -116,26 +112,53 @@ static int mctp_sendmsg(struct socket *sock, struct msghdr *msg, size_t len)
 	*(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;
-	}
+	if (rc < 0)
+		goto err_free;
 
 	/* set up cb */
 	cb = __mctp_cb(skb);
 	cb->net = addr->smctp_network;
 
+	/* direct addressing */
+	if (msk->addr_ext && addrlen >= sizeof(struct sockaddr_mctp_ext)) {
+		DECLARE_SOCKADDR(struct sockaddr_mctp_ext *,
+				 extaddr, msg->msg_name);
+
+		if (extaddr->smctp_halen > sizeof(cb->haddr)) {
+			rc = -EINVAL;
+			goto err_free;
+		}
+
+		cb->ifindex = extaddr->smctp_ifindex;
+		cb->halen = extaddr->smctp_halen;
+		memcpy(cb->haddr, extaddr->smctp_haddr, cb->halen);
+
+		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;
+		}
+	}
+
 	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;
@@ -181,6 +204,16 @@ static int mctp_recvmsg(struct socket *sock, struct msghdr *msg, size_t len,
 		addr->smctp_tag = hdr->flags_seq_tag &
 					(MCTP_HDR_TAG_MASK | MCTP_HDR_FLAG_TO);
 		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_haddr, 0x0, sizeof(ae->smctp_haddr));
+			memcpy(ae->smctp_haddr, cb->haddr, cb->halen);
+		}
 	}
 
 	rc = len;
@@ -196,12 +229,45 @@ static int mctp_recvmsg(struct socket *sock, struct msghdr *msg, size_t len,
 static int mctp_setsockopt(struct socket *sock, int level, int optname,
 			   sockptr_t optval, unsigned int optlen)
 {
-	return -EINVAL;
+	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;
 }