[PATCH 09/13 RFC net-next] net: fib: split common nexthop logic to fib_core.c

[Fernando Fernandez Mancera <fmancera@suse.de>]

To enable compiling INET subsystem without IPv4, shared FIB and nexthop
logic must be accessible to IPv6 when IPv4 routing stack is omitted.

This patch creates fib_core.c and move all the functions for common
nexthop initialization and release from fib_semantics.c to fib_core.c.
Note that fib_core.c is under net/core.

Signed-off-by: Fernando Fernandez Mancera <fmancera@suse.de>
---
 include/net/ip_fib.h       |  43 +++++++++++
 include/net/route.h        |   6 ++
 net/core/Makefile          |   2 +-
 net/core/fib_core.c        | 146 +++++++++++++++++++++++++++++++++++++
 net/ipv4/Makefile          |   2 +
 net/ipv4/fib_semantics.c   | 142 ------------------------------------
 net/ipv4/netlink.c         |   2 +
 net/ipv4/nexthop.c         |   2 +-
 net/ipv4/sysctl_net_ipv4.c |   2 +
 net/ipv6/ip6_fib.c         |   2 +
 10 files changed, 205 insertions(+), 144 deletions(-)
 create mode 100644 net/core/fib_core.c

diff --git a/include/net/ip_fib.h b/include/net/ip_fib.h
index 0a35355fb0f3..0c56d8690e00 100644
--- a/include/net/ip_fib.h
+++ b/include/net/ip_fib.h
@@ -250,7 +250,13 @@ int call_fib4_notifiers(struct net *net, enum fib_event_type event_type,
 int __net_init fib4_notifier_init(struct net *net);
 void __net_exit fib4_notifier_exit(struct net *net);
 
+#if IS_ENABLED(CONFIG_IPV4)
 void fib_info_notify_update(struct net *net, struct nl_info *info);
+#else
+static inline void fib_info_notify_update(struct net *net, struct nl_info *info)
+{
+}
+#endif
 int fib_notify(struct net *net, struct notifier_block *nb,
 	       struct netlink_ext_ack *extack);
 
@@ -578,10 +584,23 @@ void fib_select_multipath(struct fib_result *res, int hash,
 void fib_select_path(struct net *net, struct fib_result *res,
 		     struct flowi4 *fl4, const struct sk_buff *skb);
 
+#if IS_ENABLED(CONFIG_IPV4)
 int fib_nh_init(struct net *net, struct fib_nh *fib_nh,
 		struct fib_config *cfg, int nh_weight,
 		struct netlink_ext_ack *extack);
 void fib_nh_release(struct net *net, struct fib_nh *fib_nh);
+#else
+static inline int fib_nh_init(struct net *net, struct fib_nh *fib_nh,
+			      struct fib_config *cfg, int gfp,
+			      struct netlink_ext_ack *extack)
+{
+	return -EAFNOSUPPORT;
+}
+
+static inline void fib_nh_release(struct net *net, struct fib_nh *fib_nh)
+{
+}
+#endif
 int fib_nh_common_init(struct net *net, struct fib_nh_common *nhc,
 		       struct nlattr *fc_encap, u16 fc_encap_type,
 		       void *cfg, gfp_t gfp_flags,
@@ -620,7 +639,13 @@ static inline void fib_combine_itag(u32 *itag, const struct fib_result *res)
 #endif
 }
 
+#if IS_ENABLED(CONFIG_IPV4)
 void fib_flush(struct net *net);
+#else
+static inline void fib_flush(struct net *net)
+{
+}
+#endif
 void free_fib_info(struct fib_info *fi);
 
 static inline void fib_info_hold(struct fib_info *fi)
@@ -658,8 +683,26 @@ int ip_valid_fib_dump_req(struct net *net, const struct nlmsghdr *nlh,
 			  struct fib_dump_filter *filter,
 			  struct netlink_callback *cb);
 
+#if IS_ENABLED(CONFIG_IPV4)
 int fib_nexthop_info(struct sk_buff *skb, const struct fib_nh_common *nh,
 		     u8 rt_family, unsigned char *flags, bool skip_oif);
 int fib_add_nexthop(struct sk_buff *skb, const struct fib_nh_common *nh,
 		    int nh_weight, u8 rt_family, u32 nh_tclassid);
+#else
+static inline int fib_nexthop_info(struct sk_buff *skb,
+				   const struct fib_nh_common *nh,
+				   u8 rt_family, unsigned char *flags,
+				   bool skip_oif)
+{
+	return 0;
+}
+
+static inline int fib_add_nexthop(struct sk_buff *skb,
+				  const struct fib_nh_common *nh,
+				  int nh_weight, u8 rt_family,
+				  u32 nh_tclassid)
+{
+	return 0;
+}
+#endif
 #endif  /* _NET_FIB_H */
diff --git a/include/net/route.h b/include/net/route.h
index 08adb14224a9..29944be291f8 100644
--- a/include/net/route.h
+++ b/include/net/route.h
@@ -128,7 +128,13 @@ extern struct ip_rt_acct __percpu *ip_rt_acct;
 struct in_device;
 
 int ip_rt_init(void);
+#if IS_ENABLED(CONFIG_IPV4)
 void rt_cache_flush(struct net *net);
+#else
+static inline void rt_cache_flush(struct net *net)
+{
+}
+#endif
 void rt_flush_dev(struct net_device *dev);
 
 static inline void inet_sk_init_flowi4(const struct inet_sock *inet,
diff --git a/net/core/Makefile b/net/core/Makefile
index b3fdcb4e355f..63ebcdc6b9f1 100644
--- a/net/core/Makefile
+++ b/net/core/Makefile
@@ -12,7 +12,7 @@ obj-$(CONFIG_SYSCTL) += sysctl_net_core.o
 obj-y		     += dev.o dev_api.o dev_addr_lists.o dst.o netevent.o \
 			neighbour.o rtnetlink.o utils.o link_watch.o filter.o \
 			sock_diag.o dev_ioctl.o tso.o sock_reuseport.o \
-			fib_notifier.o xdp.o flow_offload.o gro.o \
+			fib_notifier.o fib_core.o xdp.o flow_offload.o gro.o \
 			netdev-genl.o netdev-genl-gen.o netdev_work.o gso.o
 
 obj-$(CONFIG_NETDEV_ADDR_LIST_TEST) += dev_addr_lists_test.o
diff --git a/net/core/fib_core.c b/net/core/fib_core.c
new file mode 100644
index 000000000000..93894b5847e9
--- /dev/null
+++ b/net/core/fib_core.c
@@ -0,0 +1,146 @@
+// SPDX-License-Identifier: GPL-2.0-only
+#include <linux/types.h>
+#include <net/lwtunnel.h>
+#include <net/route.h>
+
+static void rt_fibinfo_free(struct rtable __rcu **rtp)
+{
+	struct rtable *rt = rcu_dereference_protected(*rtp, 1);
+
+	if (!rt)
+		return;
+
+	/* Not even needed : RCU_INIT_POINTER(*rtp, NULL);
+	 * because we waited an RCU grace period before calling
+	 * free_fib_info_rcu()
+	 */
+
+	dst_dev_put(&rt->dst);
+	dst_release_immediate(&rt->dst);
+}
+
+static void free_nh_exceptions(struct fib_nh_common *nhc)
+{
+	struct fnhe_hash_bucket *hash;
+	int i;
+
+	hash = rcu_dereference_protected(nhc->nhc_exceptions, 1);
+	if (!hash)
+		return;
+	for (i = 0; i < FNHE_HASH_SIZE; i++) {
+		struct fib_nh_exception *fnhe;
+
+		fnhe = rcu_dereference_protected(hash[i].chain, 1);
+		while (fnhe) {
+			struct fib_nh_exception *next;
+
+			next = rcu_dereference_protected(fnhe->fnhe_next, 1);
+
+			rt_fibinfo_free(&fnhe->fnhe_rth_input);
+			rt_fibinfo_free(&fnhe->fnhe_rth_output);
+
+			kfree(fnhe);
+
+			fnhe = next;
+		}
+	}
+	kfree(hash);
+}
+
+static void rt_fibinfo_free_cpus(struct rtable __rcu * __percpu *rtp)
+{
+	int cpu;
+
+	if (!rtp)
+		return;
+
+	for_each_possible_cpu(cpu) {
+		struct rtable *rt;
+
+		rt = rcu_dereference_protected(*per_cpu_ptr(rtp, cpu), 1);
+		if (rt) {
+			dst_dev_put(&rt->dst);
+			dst_release_immediate(&rt->dst);
+		}
+	}
+	free_percpu(rtp);
+}
+
+void fib_nh_common_release(struct fib_nh_common *nhc)
+{
+	netdev_put(nhc->nhc_dev, &nhc->nhc_dev_tracker);
+	lwtstate_put(nhc->nhc_lwtstate);
+	rt_fibinfo_free_cpus(nhc->nhc_pcpu_rth_output);
+	rt_fibinfo_free(&nhc->nhc_rth_input);
+	free_nh_exceptions(nhc);
+}
+
+int fib_nh_common_init(struct net *net, struct fib_nh_common *nhc,
+		       struct nlattr *encap, u16 encap_type,
+		       void *cfg, gfp_t gfp_flags,
+		       struct netlink_ext_ack *extack)
+{
+	int err;
+
+	nhc->nhc_pcpu_rth_output = alloc_percpu_gfp(struct rtable __rcu *,
+						    gfp_flags);
+	if (!nhc->nhc_pcpu_rth_output)
+		return -ENOMEM;
+
+	if (encap) {
+		struct lwtunnel_state *lwtstate;
+
+		err = lwtunnel_build_state(net, encap_type, encap,
+					   nhc->nhc_family, cfg, &lwtstate,
+					   extack);
+		if (err)
+			goto lwt_failure;
+
+		nhc->nhc_lwtstate = lwtstate_get(lwtstate);
+	}
+
+	return 0;
+
+lwt_failure:
+	rt_fibinfo_free_cpus(nhc->nhc_pcpu_rth_output);
+	nhc->nhc_pcpu_rth_output = NULL;
+	return err;
+}
+
+/* Update the PMTU of exceptions when:
+ * - the new MTU of the first hop becomes smaller than the PMTU
+ * - the old MTU was the same as the PMTU, and it limited discovery of
+ *   larger MTUs on the path. With that limit raised, we can now
+ *   discover larger MTUs
+ * A special case is locked exceptions, for which the PMTU is smaller
+ * than the minimal accepted PMTU:
+ * - if the new MTU is greater than the PMTU, don't make any change
+ * - otherwise, unlock and set PMTU
+ */
+void fib_nhc_update_mtu(struct fib_nh_common *nhc, u32 new, u32 orig)
+{
+	struct fnhe_hash_bucket *bucket;
+	int i;
+
+	bucket = rcu_dereference_protected(nhc->nhc_exceptions, 1);
+	if (!bucket)
+		return;
+
+	for (i = 0; i < FNHE_HASH_SIZE; i++) {
+		struct fib_nh_exception *fnhe;
+
+		for (fnhe = rcu_dereference_protected(bucket[i].chain, 1);
+		     fnhe;
+		     fnhe = rcu_dereference_protected(fnhe->fnhe_next, 1)) {
+			if (fnhe->fnhe_mtu_locked) {
+				if (new <= fnhe->fnhe_pmtu) {
+					fnhe->fnhe_pmtu = new;
+					fnhe->fnhe_mtu_locked = false;
+				}
+			} else if (new < fnhe->fnhe_pmtu ||
+				   orig == fnhe->fnhe_pmtu) {
+				fnhe->fnhe_pmtu = new;
+			}
+		}
+	}
+}
diff --git a/net/ipv4/Makefile b/net/ipv4/Makefile
index 83c25f52eb58..b540d549f25a 100644
--- a/net/ipv4/Makefile
+++ b/net/ipv4/Makefile
@@ -19,7 +19,9 @@ obj-$(CONFIG_IPV4) += route.o ip_input.o ip_fragment.o ip_forward.o ip_options.o
 obj-$(CONFIG_NET_IP_TUNNEL) += ip_tunnel.o
 obj-$(CONFIG_SYSCTL) += sysctl_net_ipv4.o
 obj-$(CONFIG_PROC_FS) += proc.o
+ifeq ($(CONFIG_IPV4),y)
 obj-$(CONFIG_IP_MULTIPLE_TABLES) += fib_rules.o
+endif
 obj-$(CONFIG_IP_MROUTE) += ipmr.o
 obj-$(CONFIG_IP_MROUTE_COMMON) += ipmr_base.o
 obj-$(CONFIG_NET_IPIP) += ipip.o
diff --git a/net/ipv4/fib_semantics.c b/net/ipv4/fib_semantics.c
index 4f3c0740dde9..6ed252e9559e 100644
--- a/net/ipv4/fib_semantics.c
+++ b/net/ipv4/fib_semantics.c
@@ -136,78 +136,6 @@ const struct fib_prop fib_props[RTN_MAX + 1] = {
 	},
 };
 
-static void rt_fibinfo_free(struct rtable __rcu **rtp)
-{
-	struct rtable *rt = rcu_dereference_protected(*rtp, 1);
-
-	if (!rt)
-		return;
-
-	/* Not even needed : RCU_INIT_POINTER(*rtp, NULL);
-	 * because we waited an RCU grace period before calling
-	 * free_fib_info_rcu()
-	 */
-
-	dst_dev_put(&rt->dst);
-	dst_release_immediate(&rt->dst);
-}
-
-static void free_nh_exceptions(struct fib_nh_common *nhc)
-{
-	struct fnhe_hash_bucket *hash;
-	int i;
-
-	hash = rcu_dereference_protected(nhc->nhc_exceptions, 1);
-	if (!hash)
-		return;
-	for (i = 0; i < FNHE_HASH_SIZE; i++) {
-		struct fib_nh_exception *fnhe;
-
-		fnhe = rcu_dereference_protected(hash[i].chain, 1);
-		while (fnhe) {
-			struct fib_nh_exception *next;
-
-			next = rcu_dereference_protected(fnhe->fnhe_next, 1);
-
-			rt_fibinfo_free(&fnhe->fnhe_rth_input);
-			rt_fibinfo_free(&fnhe->fnhe_rth_output);
-
-			kfree(fnhe);
-
-			fnhe = next;
-		}
-	}
-	kfree(hash);
-}
-
-static void rt_fibinfo_free_cpus(struct rtable __rcu * __percpu *rtp)
-{
-	int cpu;
-
-	if (!rtp)
-		return;
-
-	for_each_possible_cpu(cpu) {
-		struct rtable *rt;
-
-		rt = rcu_dereference_protected(*per_cpu_ptr(rtp, cpu), 1);
-		if (rt) {
-			dst_dev_put(&rt->dst);
-			dst_release_immediate(&rt->dst);
-		}
-	}
-	free_percpu(rtp);
-}
-
-void fib_nh_common_release(struct fib_nh_common *nhc)
-{
-	netdev_put(nhc->nhc_dev, &nhc->nhc_dev_tracker);
-	lwtstate_put(nhc->nhc_lwtstate);
-	rt_fibinfo_free_cpus(nhc->nhc_pcpu_rth_output);
-	rt_fibinfo_free(&nhc->nhc_rth_input);
-	free_nh_exceptions(nhc);
-}
-
 void fib_nh_release(struct net *net, struct fib_nh *fib_nh)
 {
 #ifdef CONFIG_IP_ROUTE_CLASSID
@@ -607,38 +535,6 @@ static int fib_detect_death(struct fib_info *fi, int order,
 	return 1;
 }
 
-int fib_nh_common_init(struct net *net, struct fib_nh_common *nhc,
-		       struct nlattr *encap, u16 encap_type,
-		       void *cfg, gfp_t gfp_flags,
-		       struct netlink_ext_ack *extack)
-{
-	int err;
-
-	nhc->nhc_pcpu_rth_output = alloc_percpu_gfp(struct rtable __rcu *,
-						    gfp_flags);
-	if (!nhc->nhc_pcpu_rth_output)
-		return -ENOMEM;
-
-	if (encap) {
-		struct lwtunnel_state *lwtstate;
-
-		err = lwtunnel_build_state(net, encap_type, encap,
-					   nhc->nhc_family, cfg, &lwtstate,
-					   extack);
-		if (err)
-			goto lwt_failure;
-
-		nhc->nhc_lwtstate = lwtstate_get(lwtstate);
-	}
-
-	return 0;
-
-lwt_failure:
-	rt_fibinfo_free_cpus(nhc->nhc_pcpu_rth_output);
-	nhc->nhc_pcpu_rth_output = NULL;
-	return err;
-}
-
 int fib_nh_init(struct net *net, struct fib_nh *nh,
 		struct fib_config *cfg, int nh_weight,
 		struct netlink_ext_ack *extack)
@@ -1864,44 +1760,6 @@ static int call_fib_nh_notifiers(struct fib_nh *nh,
 	return NOTIFY_DONE;
 }
 
-/* Update the PMTU of exceptions when:
- * - the new MTU of the first hop becomes smaller than the PMTU
- * - the old MTU was the same as the PMTU, and it limited discovery of
- *   larger MTUs on the path. With that limit raised, we can now
- *   discover larger MTUs
- * A special case is locked exceptions, for which the PMTU is smaller
- * than the minimal accepted PMTU:
- * - if the new MTU is greater than the PMTU, don't make any change
- * - otherwise, unlock and set PMTU
- */
-void fib_nhc_update_mtu(struct fib_nh_common *nhc, u32 new, u32 orig)
-{
-	struct fnhe_hash_bucket *bucket;
-	int i;
-
-	bucket = rcu_dereference_protected(nhc->nhc_exceptions, 1);
-	if (!bucket)
-		return;
-
-	for (i = 0; i < FNHE_HASH_SIZE; i++) {
-		struct fib_nh_exception *fnhe;
-
-		for (fnhe = rcu_dereference_protected(bucket[i].chain, 1);
-		     fnhe;
-		     fnhe = rcu_dereference_protected(fnhe->fnhe_next, 1)) {
-			if (fnhe->fnhe_mtu_locked) {
-				if (new <= fnhe->fnhe_pmtu) {
-					fnhe->fnhe_pmtu = new;
-					fnhe->fnhe_mtu_locked = false;
-				}
-			} else if (new < fnhe->fnhe_pmtu ||
-				   orig == fnhe->fnhe_pmtu) {
-				fnhe->fnhe_pmtu = new;
-			}
-		}
-	}
-}
-
 void fib_sync_mtu(struct net_device *dev, u32 orig_mtu)
 {
 	struct hlist_head *head = fib_nh_head(dev);
diff --git a/net/ipv4/netlink.c b/net/ipv4/netlink.c
index b920e1bdcf58..57d4dca16d3e 100644
--- a/net/ipv4/netlink.c
+++ b/net/ipv4/netlink.c
@@ -16,10 +16,12 @@ int rtm_getroute_parse_ip_proto(struct nlattr *attr, u8 *ip_proto, u8 family,
 	case IPPROTO_TCP:
 	case IPPROTO_UDP:
 		return 0;
+#if IS_ENABLED(CONFIG_IPV4)
 	case IPPROTO_ICMP:
 		if (family != AF_INET)
 			break;
 		return 0;
+#endif
 #if IS_ENABLED(CONFIG_IPV6)
 	case IPPROTO_ICMPV6:
 		if (family != AF_INET6)
diff --git a/net/ipv4/nexthop.c b/net/ipv4/nexthop.c
index 6205bd57aa85..b113a31f6150 100644
--- a/net/ipv4/nexthop.c
+++ b/net/ipv4/nexthop.c
@@ -1414,7 +1414,7 @@ static bool nexthop_is_good_nh(const struct nexthop *nh)
 
 	switch (nhi->family) {
 	case AF_INET:
-		return ipv4_good_nh(&nhi->fib_nh);
+		return IS_ENABLED(CONFIG_IPV4) && ipv4_good_nh(&nhi->fib_nh);
 	case AF_INET6:
 		return IS_ENABLED(CONFIG_IPV6) && ipv6_good_nh(&nhi->fib6_nh);
 	}
diff --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c
index ca1180dba1de..9c343c9566b7 100644
--- a/net/ipv4/sysctl_net_ipv4.c
+++ b/net/ipv4/sysctl_net_ipv4.c
@@ -613,6 +613,7 @@ static struct ctl_table ipv4_table[] = {
 		.mode		= 0644,
 		.proc_handler	= proc_doulongvec_minmax,
 	},
+#if IS_ENABLED(CONFIG_IPV4)
 	{
 		.procname	= "fib_sync_mem",
 		.data		= &sysctl_fib_sync_mem,
@@ -622,6 +623,7 @@ static struct ctl_table ipv4_table[] = {
 		.extra1		= &sysctl_fib_sync_mem_min,
 		.extra2		= &sysctl_fib_sync_mem_max,
 	},
+#endif
 };
 
 static struct ctl_table ipv4_net_table[] = {
diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c
index a130cdfaebfb..8b5f855c8dcb 100644
--- a/net/ipv6/ip6_fib.c
+++ b/net/ipv6/ip6_fib.c
@@ -645,9 +645,11 @@ static int inet6_dump_fib(struct sk_buff *skb, struct netlink_callback *cb)
 
 	rcu_read_lock();
 	if (cb->strict_check) {
+#if IS_ENABLED(CONFIG_IPV4)
 		err = ip_valid_fib_dump_req(net, nlh, &arg.filter, cb);
 		if (err < 0)
 			goto unlock;
+#endif
 	} else if (nlmsg_len(nlh) >= sizeof(struct rtmsg)) {
 		struct rtmsg *rtm = nlmsg_data(nlh);
 
-- 
2.54.0