[PATCH v2 net-next 4/7] ipv6: Move pcpu cached routes to fib6_nh

[David Ahern <dsahern@kernel.org>]

From: David Ahern <dsahern@gmail.com>

rt6_info are specific instances of a fib entry and are tied to a
device and gateway - ie., a nexthop. Before nexthop objects, IPv6 fib
entries have separate fib6_info for each nexthop in a multipath route,
so the location of the pcpu cache in the fib6_info struct worked.
However, with nexthop objects a fib6_info can point to a set of nexthops
(yet another alignment of ipv6 with ipv4). Accordingly, the pcpu
cache needs to be moved to the fib6_nh struct so the cached entries
are local to the nexthop specification used to create the rt6_info.

Initialization and free of the pcpu entries moved to fib6_nh_init and
fib6_nh_release.

Change in location only, from fib6_info down to fib6_nh; no other
functional change intended.

Signed-off-by: David Ahern <dsahern@gmail.com>
---
 include/net/ip6_fib.h |  3 ++-
 net/ipv6/addrconf.c   |  6 +++---
 net/ipv6/ip6_fib.c    | 33 ++++++---------------------------
 net/ipv6/route.c      | 29 +++++++++++++++++++++++++++--
 4 files changed, 38 insertions(+), 33 deletions(-)

diff --git a/include/net/ip6_fib.h b/include/net/ip6_fib.h
index 40105738e2f6..cf715835a330 100644
--- a/include/net/ip6_fib.h
+++ b/include/net/ip6_fib.h
@@ -131,6 +131,8 @@ struct fib6_nh {
 #ifdef CONFIG_IPV6_ROUTER_PREF
 	unsigned long		last_probe;
 #endif
+
+	struct rt6_info * __percpu *rt6i_pcpu;
 };
 
 struct fib6_info {
@@ -156,7 +158,6 @@ struct fib6_info {
 	struct rt6key			fib6_src;
 	struct rt6key			fib6_prefsrc;
 
-	struct rt6_info * __percpu	*rt6i_pcpu;
 	struct rt6_exception_bucket __rcu *rt6i_exception_bucket;
 
 	u32				fib6_metric;
diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c
index 340a0f06f974..25754175097b 100644
--- a/net/ipv6/addrconf.c
+++ b/net/ipv6/addrconf.c
@@ -6339,16 +6339,16 @@ void addrconf_disable_policy_idev(struct inet6_dev *idev, int val)
 	list_for_each_entry(ifa, &idev->addr_list, if_list) {
 		spin_lock(&ifa->lock);
 		if (ifa->rt) {
-			struct fib6_info *rt = ifa->rt;
+			struct fib6_nh *nh = &ifa->rt->fib6_nh;
 			int cpu;
 
 			rcu_read_lock();
 			ifa->rt->dst_nopolicy = val ? true : false;
-			if (rt->rt6i_pcpu) {
+			if (nh->rt6i_pcpu) {
 				for_each_possible_cpu(cpu) {
 					struct rt6_info **rtp;
 
-					rtp = per_cpu_ptr(rt->rt6i_pcpu, cpu);
+					rtp = per_cpu_ptr(nh->rt6i_pcpu, cpu);
 					addrconf_set_nopolicy(*rtp, val);
 				}
 			}
diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c
index a8919c217cc2..793830b2965d 100644
--- a/net/ipv6/ip6_fib.c
+++ b/net/ipv6/ip6_fib.c
@@ -155,12 +155,6 @@ struct fib6_info *fib6_info_alloc(gfp_t gfp_flags)
 	if (!f6i)
 		return NULL;
 
-	f6i->rt6i_pcpu = alloc_percpu_gfp(struct rt6_info *, gfp_flags);
-	if (!f6i->rt6i_pcpu) {
-		kfree(f6i);
-		return NULL;
-	}
-
 	INIT_LIST_HEAD(&f6i->fib6_siblings);
 	refcount_set(&f6i->fib6_ref, 1);
 
@@ -177,25 +171,6 @@ void fib6_info_destroy_rcu(struct rcu_head *head)
 	bucket = rcu_dereference_protected(f6i->rt6i_exception_bucket, 1);
 	kfree(bucket);
 
-	if (f6i->rt6i_pcpu) {
-		int cpu;
-
-		for_each_possible_cpu(cpu) {
-			struct rt6_info **ppcpu_rt;
-			struct rt6_info *pcpu_rt;
-
-			ppcpu_rt = per_cpu_ptr(f6i->rt6i_pcpu, cpu);
-			pcpu_rt = *ppcpu_rt;
-			if (pcpu_rt) {
-				dst_dev_put(&pcpu_rt->dst);
-				dst_release(&pcpu_rt->dst);
-				*ppcpu_rt = NULL;
-			}
-		}
-
-		free_percpu(f6i->rt6i_pcpu);
-	}
-
 	fib6_nh_release(&f6i->fib6_nh);
 
 	ip_fib_metrics_put(f6i->fib6_metrics);
@@ -902,8 +877,12 @@ static struct fib6_node *fib6_add_1(struct net *net,
 static void fib6_drop_pcpu_from(struct fib6_info *f6i,
 				const struct fib6_table *table)
 {
+	struct fib6_nh *fib6_nh = &f6i->fib6_nh;
 	int cpu;
 
+	if (!rcu_access_pointer(fib6_nh->rt6i_pcpu))
+		return;
+
 	/* release the reference to this fib entry from
 	 * all of its cached pcpu routes
 	 */
@@ -911,7 +890,7 @@ static void fib6_drop_pcpu_from(struct fib6_info *f6i,
 		struct rt6_info **ppcpu_rt;
 		struct rt6_info *pcpu_rt;
 
-		ppcpu_rt = per_cpu_ptr(f6i->rt6i_pcpu, cpu);
+		ppcpu_rt = per_cpu_ptr(fib6_nh->rt6i_pcpu, cpu);
 		pcpu_rt = *ppcpu_rt;
 		if (pcpu_rt) {
 			struct fib6_info *from;
@@ -951,7 +930,7 @@ static void fib6_purge_rt(struct fib6_info *rt, struct fib6_node *fn,
 				    lockdep_is_held(&table->tb6_lock));
 		}
 
-		if (rt->rt6i_pcpu)
+		if (rt->fib6_nh.rt6i_pcpu)
 			fib6_drop_pcpu_from(rt, table);
 	}
 }
diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index 9c0127a44f9f..32c526d008e2 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -1273,7 +1273,7 @@ static struct rt6_info *rt6_get_pcpu_route(const struct fib6_result *res)
 {
 	struct rt6_info *pcpu_rt, **p;
 
-	p = this_cpu_ptr(res->f6i->rt6i_pcpu);
+	p = this_cpu_ptr(res->nh->rt6i_pcpu);
 	pcpu_rt = *p;
 
 	if (pcpu_rt)
@@ -1294,7 +1294,7 @@ static struct rt6_info *rt6_make_pcpu_route(struct net *net,
 	}
 
 	dst_hold(&pcpu_rt->dst);
-	p = this_cpu_ptr(res->f6i->rt6i_pcpu);
+	p = this_cpu_ptr(res->nh->rt6i_pcpu);
 	prev = cmpxchg(p, NULL, pcpu_rt);
 	BUG_ON(prev);
 
@@ -3063,6 +3063,12 @@ int fib6_nh_init(struct net *net, struct fib6_nh *fib6_nh,
 	    !netif_carrier_ok(dev))
 		fib6_nh->fib_nh_flags |= RTNH_F_LINKDOWN;
 
+	fib6_nh->rt6i_pcpu = alloc_percpu_gfp(struct rt6_info *, gfp_flags);
+	if (!fib6_nh->rt6i_pcpu) {
+		err = -ENOMEM;
+		goto out;
+	}
+
 	err = fib_nh_common_init(&fib6_nh->nh_common, cfg->fc_encap,
 				 cfg->fc_encap_type, cfg, gfp_flags, extack);
 	if (err)
@@ -3087,6 +3093,25 @@ int fib6_nh_init(struct net *net, struct fib6_nh *fib6_nh,
 
 void fib6_nh_release(struct fib6_nh *fib6_nh)
 {
+	if (fib6_nh->rt6i_pcpu) {
+		int cpu;
+
+		for_each_possible_cpu(cpu) {
+			struct rt6_info **ppcpu_rt;
+			struct rt6_info *pcpu_rt;
+
+			ppcpu_rt = per_cpu_ptr(fib6_nh->rt6i_pcpu, cpu);
+			pcpu_rt = *ppcpu_rt;
+			if (pcpu_rt) {
+				dst_dev_put(&pcpu_rt->dst);
+				dst_release(&pcpu_rt->dst);
+				*ppcpu_rt = NULL;
+			}
+		}
+
+		free_percpu(fib6_nh->rt6i_pcpu);
+	}
+
 	fib_nh_common_release(&fib6_nh->nh_common);
 }
 
-- 
2.11.0