mctp: Add initial routing framework

Add a simple routing table, and a couple of route output handlers, and
the mctp packet_type & handler.

Includes changes from Matt Johnston <matt@codeconstruct.com.au>.

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

Author: jk-ozlabs

MAINTAINERS

@@ -11040,6 +11040,7 @@ S:	Maintained
 F:	drivers/net/mctp/
 F:	include/net/mctp.h
 F:	include/net/mctpdevice.h
+F:	include/net/netns/mctp.h
 F:	net/mctp/
 
 MAN-PAGES: MANUAL PAGES FOR LINUX -- Sections 2, 3, 4, 5, and 7

include/net/mctp.h

@@ -11,6 +11,7 @@
 
 #include <linux/bits.h>
 #include <linux/mctp.h>
+#include <net/net_namespace.h>
 
 /* MCTP packet definitions */
 struct mctp_hdr {
@@ -33,6 +34,8 @@ struct mctp_hdr {
 #define MCTP_HDR_TAG_SHIFT	0
 #define MCTP_HDR_TAG_MASK	GENMASK(2, 0)
 
+#define MCTP_HEADER_MAXLEN	4
+
 static inline bool mctp_address_ok(mctp_eid_t eid)
 {
 	return eid >= 8 && eid < 255;
@@ -43,6 +46,78 @@ static inline struct mctp_hdr *mctp_hdr(struct sk_buff *skb)
 	return (struct mctp_hdr *)skb_network_header(skb);
 }
 
+struct mctp_skb_cb {
+	unsigned int	magic;
+	unsigned int	net;
+	mctp_eid_t	src;
+};
+
+/* skb control-block accessors with a little extra debugging for initial
+ * development.
+ *
+ * TODO: remove checks & mctp_skb_cb->magic; replace callers of __mctp_cb
+ * with mctp_cb().
+ *
+ * __mctp_cb() is only for the initial ingress code; we should see ->magic set
+ * at all times after this.
+ */
+static inline struct mctp_skb_cb *__mctp_cb(struct sk_buff *skb)
+{
+	struct mctp_skb_cb *cb = (void *)skb->cb;
+
+	cb->magic = 0x4d435450;
+	return cb;
+}
+
+static inline struct mctp_skb_cb *mctp_cb(struct sk_buff *skb)
+{
+	struct mctp_skb_cb *cb = (void *)skb->cb;
+
+	WARN_ON(cb->magic != 0x4d435450);
+	return (void *)(skb->cb);
+}
+
+/* Route definition.
+ *
+ * These are held in the pernet->mctp.routes list, with RCU protection for
+ * removed routes. We hold a reference to the netdev; routes need to be
+ * dropped on NETDEV_UNREGISTER events.
+ *
+ * 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.
+ */
+struct mctp_route {
+	mctp_eid_t		min, max;
+
+	struct mctp_dev		*dev;
+	unsigned int		mtu;
+	int			(*output)(struct mctp_route *route,
+					  struct sk_buff *skb);
+
+	struct list_head	list;
+	refcount_t		refs;
+	struct rcu_head		rcu;
+};
+
+/* route interfaces */
+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);
+
+/* routing <--> device interface */
+int mctp_route_add_local(struct mctp_dev *mdev, mctp_eid_t addr);
+int mctp_route_remove_local(struct mctp_dev *mdev, mctp_eid_t addr);
+void mctp_route_remove_dev(struct mctp_dev *mdev);
+
+int mctp_routes_init(void);
+void mctp_routes_exit(void);
+
 void mctp_device_init(void);
 void mctp_device_exit(void);
 

include/net/net_namespace.h

@@ -34,6 +34,7 @@
 #include <net/netns/xdp.h>
 #include <net/netns/smc.h>
 #include <net/netns/bpf.h>
+#include <net/netns/mctp.h>
 #include <linux/ns_common.h>
 #include <linux/idr.h>
 #include <linux/skbuff.h>
@@ -167,6 +168,9 @@ struct net {
 #ifdef CONFIG_XDP_SOCKETS
 	struct netns_xdp	xdp;
 #endif
+#if IS_ENABLED(CONFIG_MCTP)
+	struct netns_mctp	mctp;
+#endif
 #if IS_ENABLED(CONFIG_CRYPTO_USER)
 	struct sock		*crypto_nlsk;
 #endif

include/net/netns/mctp.h

@@ -0,0 +1,16 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * MCTP per-net structures
+ */
+
+#ifndef __NETNS_MCTP_H__
+#define __NETNS_MCTP_H__
+
+#include <linux/types.h>
+
+struct netns_mctp {
+	/* Only updated under RTNL, entries freed via RCU */
+	struct list_head routes;
+};
+
+#endif /* __NETNS_MCTP_H__ */

net/mctp/Makefile

@@ -1,3 +1,3 @@
 # SPDX-License-Identifier: GPL-2.0
 obj-$(CONFIG_MCTP) += mctp.o
-mctp-objs := af_mctp.o device.o
+mctp-objs := af_mctp.o device.o route.o

net/mctp/af_mctp.c

@@ -157,10 +157,16 @@ static __init int mctp_init(void)
 	if (rc)
 		goto err_unreg_sock;
 
+	rc = mctp_routes_init();
+	if (rc)
+		goto err_unreg_proto;
+
 	mctp_device_init();
 
 	return 0;
 
+err_unreg_proto:
+	proto_unregister(&mctp_proto);
 err_unreg_sock:
 	sock_unregister(PF_MCTP);
 
@@ -170,6 +176,7 @@ static __init int mctp_init(void)
 static __exit void mctp_exit(void)
 {
 	mctp_device_exit();
+	mctp_routes_exit();
 	proto_unregister(&mctp_proto);
 	sock_unregister(PF_MCTP);
 }

net/mctp/device.c

@@ -197,6 +197,8 @@ static int mctp_rtm_newaddr(struct sk_buff *skb, struct nlmsghdr *nlh,
 
 	kfree(tmp_addrs);
 
+	mctp_route_add_local(mdev, addr->s_addr);
+
 	return 0;
 }
 
@@ -240,6 +242,11 @@ static int mctp_rtm_deladdr(struct sk_buff *skb, struct nlmsghdr *nlh,
 	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--;
@@ -334,6 +341,7 @@ static void mctp_unregister(struct net_device *dev)
 
 	RCU_INIT_POINTER(mdev->dev->mctp_ptr, NULL);
 
+	mctp_route_remove_dev(mdev);
 	kfree(mdev->addrs);
 
 	mctp_dev_destroy(mdev);