net: Initial nexthop code

Barebones start point for nexthops. Implementation for RTM commands,
notifications, management of rbtree for holding nexthops by id, and
kernel side data structures for nexthops and nexthop config.

Nexthops are maintained in an rbtree sorted by id. Similar to routes,
nexthops are configured per namespace using netns_nexthop struct added
to struct net.

Nexthop notifications are sent when a nexthop is added or deleted,
but NOT if the delete is due to a device event or network namespace
teardown (which also involves device events). Applications are
expected to use the device down event to flush nexthops and any
routes used by the nexthops.

Signed-off-by: David Ahern <dsahern@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

include/net/net_namespace.h

@@ -19,6 +19,7 @@
 #include <net/netns/packet.h>
 #include <net/netns/ipv4.h>
 #include <net/netns/ipv6.h>
+#include <net/netns/nexthop.h>
 #include <net/netns/ieee802154_6lowpan.h>
 #include <net/netns/sctp.h>
 #include <net/netns/dccp.h>
@@ -108,6 +109,7 @@ struct net {
 	struct netns_mib	mib;
 	struct netns_packet	packet;
 	struct netns_unix	unx;
+	struct netns_nexthop	nexthop;
 	struct netns_ipv4	ipv4;
 #if IS_ENABLED(CONFIG_IPV6)
 	struct netns_ipv6	ipv6;

include/net/netns/nexthop.h

@@ -0,0 +1,18 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * nexthops in net namespaces
+ */
+
+#ifndef __NETNS_NEXTHOP_H__
+#define __NETNS_NEXTHOP_H__
+
+#include <linux/rbtree.h>
+
+struct netns_nexthop {
+	struct rb_root		rb_root;	/* tree of nexthops by id */
+	struct hlist_head	*devhash;	/* nexthops by device */
+
+	unsigned int		seq;		/* protected by rtnl_mutex */
+	u32			last_id_allocated;
+};
+#endif

include/net/nexthop.h

@@ -0,0 +1,88 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Generic nexthop implementation
+ *
+ * Copyright (c) 2017-19 Cumulus Networks
+ * Copyright (c) 2017-19 David Ahern <dsa@cumulusnetworks.com>
+ */
+
+#ifndef __LINUX_NEXTHOP_H
+#define __LINUX_NEXTHOP_H
+
+#include <linux/netdevice.h>
+#include <linux/types.h>
+#include <net/ip_fib.h>
+#include <net/netlink.h>
+
+#define NEXTHOP_VALID_USER_FLAGS RTNH_F_ONLINK
+
+struct nexthop;
+
+struct nh_config {
+	u32		nh_id;
+
+	u8		nh_family;
+	u8		nh_protocol;
+	u8		nh_blackhole;
+	u32		nh_flags;
+
+	int		nh_ifindex;
+	struct net_device *dev;
+
+	u32		nlflags;
+	struct nl_info	nlinfo;
+};
+
+struct nh_info {
+	struct hlist_node	dev_hash;    /* entry on netns devhash */
+	struct nexthop		*nh_parent;
+
+	u8			family;
+	bool			reject_nh;
+
+	union {
+		struct fib_nh_common	fib_nhc;
+	};
+};
+
+struct nexthop {
+	struct rb_node		rb_node;    /* entry on netns rbtree */
+	struct net		*net;
+
+	u32			id;
+
+	u8			protocol;   /* app managing this nh */
+	u8			nh_flags;
+
+	refcount_t		refcnt;
+	struct rcu_head		rcu;
+
+	union {
+		struct nh_info	__rcu *nh_info;
+	};
+};
+
+/* caller is holding rcu or rtnl; no reference taken to nexthop */
+struct nexthop *nexthop_find_by_id(struct net *net, u32 id);
+void nexthop_free_rcu(struct rcu_head *head);
+
+static inline bool nexthop_get(struct nexthop *nh)
+{
+	return refcount_inc_not_zero(&nh->refcnt);
+}
+
+static inline void nexthop_put(struct nexthop *nh)
+{
+	if (refcount_dec_and_test(&nh->refcnt))
+		call_rcu(&nh->rcu, nexthop_free_rcu);
+}
+
+/* called with rcu lock */
+static inline bool nexthop_is_blackhole(const struct nexthop *nh)
+{
+	const struct nh_info *nhi;
+
+	nhi = rcu_dereference(nh->nh_info);
+	return nhi->reject_nh;
+}
+#endif

net/ipv4/Makefile

@@ -14,7 +14,7 @@ obj-y     := route.o inetpeer.o protocol.o \
 	     udp_offload.o arp.o icmp.o devinet.o af_inet.o igmp.o \
 	     fib_frontend.o fib_semantics.o fib_trie.o fib_notifier.o \
 	     inet_fragment.o ping.o ip_tunnel_core.o gre_offload.o \
-	     metrics.o netlink.o
+	     metrics.o netlink.o nexthop.o
 
 obj-$(CONFIG_BPFILTER) += bpfilter/