Merge branch 'ipv4-Move-location-of-pcpu-route-cache-and-exceptions'

David Ahern says:

====================
ipv4: Move location of pcpu route cache and exceptions

This series moves IPv4 pcpu cached routes from fib_nh to fib_nh_common
to make the caches available for IPv6 nexthops (fib6_nh) with IPv4
routes. This allows a fib6_nh struct to be used with both IPv4 and
and IPv6 routes.

v4
- fixed memleak if encap_type is not set as noticed by Ido

v3
- dropped ipv6 patches for now. Will resubmit those once the existing
  refcnt problem is fixed

v2
- reverted patch 2 to use ifdef CONFIG_IP_ROUTE_CLASSID instead
  of IS_ENABLED(CONFIG_IP_ROUTE_CLASSID) to fix compile issues
  reported by kbuild test robot
====================
Signed-off-by: David S. Miller <davem@davemloft.net>

include/net/ip_fib.h

@@ -96,6 +96,11 @@ struct fib_nh_common {
 
 	int			nhc_weight;
 	atomic_t		nhc_upper_bound;
+
+	/* v4 specific, but allows fib6_nh with v4 routes */
+	struct rtable __rcu * __percpu *nhc_pcpu_rth_output;
+	struct rtable __rcu     *nhc_rth_input;
+	struct fnhe_hash_bucket	__rcu *nhc_exceptions;
 };
 
 struct fib_nh {
@@ -107,9 +112,6 @@ struct fib_nh {
 #endif
 	__be32			nh_saddr;
 	int			nh_saddr_genid;
-	struct rtable __rcu * __percpu *nh_pcpu_rth_output;
-	struct rtable __rcu	*nh_rth_input;
-	struct fnhe_hash_bucket	__rcu *nh_exceptions;
 #define fib_nh_family		nh_common.nhc_family
 #define fib_nh_dev		nh_common.nhc_dev
 #define fib_nh_oif		nh_common.nhc_oif

net/ipv4/fib_semantics.c

@@ -159,12 +159,12 @@ static void rt_fibinfo_free(struct rtable __rcu **rtp)
 	dst_release_immediate(&rt->dst);
 }
 
-static void free_nh_exceptions(struct fib_nh *nh)
+static void free_nh_exceptions(struct fib_nh_common *nhc)
 {
 	struct fnhe_hash_bucket *hash;
 	int i;
 
-	hash = rcu_dereference_protected(nh->nh_exceptions, 1);
+	hash = rcu_dereference_protected(nhc->nhc_exceptions, 1);
 	if (!hash)
 		return;
 	for (i = 0; i < FNHE_HASH_SIZE; i++) {
@@ -212,6 +212,9 @@ void fib_nh_common_release(struct fib_nh_common *nhc)
 		dev_put(nhc->nhc_dev);
 
 	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);
 }
 EXPORT_SYMBOL_GPL(fib_nh_common_release);
 
@@ -222,9 +225,6 @@ void fib_nh_release(struct net *net, struct fib_nh *fib_nh)
 		net->ipv4.fib_num_tclassid_users--;
 #endif
 	fib_nh_common_release(&fib_nh->nh_common);
-	free_nh_exceptions(fib_nh);
-	rt_fibinfo_free_cpus(fib_nh->nh_pcpu_rth_output);
-	rt_fibinfo_free(&fib_nh->nh_rth_input);
 }
 
 /* Release a nexthop info record */
@@ -491,23 +491,35 @@ int fib_nh_common_init(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;
-		int err;
 
 		if (encap_type == LWTUNNEL_ENCAP_NONE) {
 			NL_SET_ERR_MSG(extack, "LWT encap type not specified");
-			return -EINVAL;
+			err = -EINVAL;
+			goto lwt_failure;
 		}
 		err = lwtunnel_build_state(encap_type, encap, nhc->nhc_family,
 					   cfg, &lwtstate, extack);
 		if (err)
-			return 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;
 }
 EXPORT_SYMBOL_GPL(fib_nh_common_init);
 
@@ -515,18 +527,14 @@ int fib_nh_init(struct net *net, struct fib_nh *nh,
 		struct fib_config *cfg, int nh_weight,
 		struct netlink_ext_ack *extack)
 {
-	int err = -ENOMEM;
+	int err;
 
 	nh->fib_nh_family = AF_INET;
 
-	nh->nh_pcpu_rth_output = alloc_percpu(struct rtable __rcu *);
-	if (!nh->nh_pcpu_rth_output)
-		goto err_out;
-
 	err = fib_nh_common_init(&nh->nh_common, cfg->fc_encap,
 				 cfg->fc_encap_type, cfg, GFP_KERNEL, extack);
 	if (err)
-		goto init_failure;
+		return err;
 
 	nh->fib_nh_oif = cfg->fc_oif;
 	nh->fib_nh_gw_family = cfg->fc_gw_family;
@@ -546,12 +554,6 @@ int fib_nh_init(struct net *net, struct fib_nh *nh,
 	nh->fib_nh_weight = nh_weight;
 #endif
 	return 0;
-
-init_failure:
-	rt_fibinfo_free_cpus(nh->nh_pcpu_rth_output);
-	nh->nh_pcpu_rth_output = NULL;
-err_out:
-	return err;
 }
 
 #ifdef CONFIG_IP_ROUTE_MULTIPATH
@@ -1711,12 +1713,12 @@ static int call_fib_nh_notifiers(struct fib_nh *nh,
  * - if the new MTU is greater than the PMTU, don't make any change
  * - otherwise, unlock and set PMTU
  */
-static void nh_update_mtu(struct fib_nh *nh, u32 new, u32 orig)
+static void nh_update_mtu(struct fib_nh_common *nhc, u32 new, u32 orig)
 {
 	struct fnhe_hash_bucket *bucket;
 	int i;
 
-	bucket = rcu_dereference_protected(nh->nh_exceptions, 1);
+	bucket = rcu_dereference_protected(nhc->nhc_exceptions, 1);
 	if (!bucket)
 		return;
 
@@ -1747,7 +1749,7 @@ void fib_sync_mtu(struct net_device *dev, u32 orig_mtu)
 
 	hlist_for_each_entry(nh, head, nh_hash) {
 		if (nh->fib_nh_dev == dev)
-			nh_update_mtu(nh, dev->mtu, orig_mtu);
+			nh_update_mtu(&nh->nh_common, dev->mtu, orig_mtu);
 	}
 }
 

net/ipv4/route.c

@@ -643,8 +643,9 @@ static void fill_route_from_fnhe(struct rtable *rt, struct fib_nh_exception *fnh
 	}
 }
 
-static void update_or_create_fnhe(struct fib_nh *nh, __be32 daddr, __be32 gw,
-				  u32 pmtu, bool lock, unsigned long expires)
+static void update_or_create_fnhe(struct fib_nh_common *nhc, __be32 daddr,
+				  __be32 gw, u32 pmtu, bool lock,
+				  unsigned long expires)
 {
 	struct fnhe_hash_bucket *hash;
 	struct fib_nh_exception *fnhe;
@@ -653,17 +654,17 @@ static void update_or_create_fnhe(struct fib_nh *nh, __be32 daddr, __be32 gw,
 	unsigned int i;
 	int depth;
 
-	genid = fnhe_genid(dev_net(nh->fib_nh_dev));
+	genid = fnhe_genid(dev_net(nhc->nhc_dev));
 	hval = fnhe_hashfun(daddr);
 
 	spin_lock_bh(&fnhe_lock);
 
-	hash = rcu_dereference(nh->nh_exceptions);
+	hash = rcu_dereference(nhc->nhc_exceptions);
 	if (!hash) {
 		hash = kcalloc(FNHE_HASH_SIZE, sizeof(*hash), GFP_ATOMIC);
 		if (!hash)
 			goto out_unlock;
-		rcu_assign_pointer(nh->nh_exceptions, hash);
+		rcu_assign_pointer(nhc->nhc_exceptions, hash);
 	}
 
 	hash += hval;
@@ -715,13 +716,13 @@ static void update_or_create_fnhe(struct fib_nh *nh, __be32 daddr, __be32 gw,
 		 * stale, so anyone caching it rechecks if this exception
 		 * applies to them.
 		 */
-		rt = rcu_dereference(nh->nh_rth_input);
+		rt = rcu_dereference(nhc->nhc_rth_input);
 		if (rt)
 			rt->dst.obsolete = DST_OBSOLETE_KILL;
 
 		for_each_possible_cpu(i) {
 			struct rtable __rcu **prt;
-			prt = per_cpu_ptr(nh->nh_pcpu_rth_output, i);
+			prt = per_cpu_ptr(nhc->nhc_pcpu_rth_output, i);
 			rt = rcu_dereference(*prt);
 			if (rt)
 				rt->dst.obsolete = DST_OBSOLETE_KILL;
@@ -788,10 +789,8 @@ static void __ip_do_redirect(struct rtable *rt, struct sk_buff *skb, struct flow
 		} else {
 			if (fib_lookup(net, fl4, &res, 0) == 0) {
 				struct fib_nh_common *nhc = FIB_RES_NHC(res);
-				struct fib_nh *nh;
 
-				nh = container_of(nhc, struct fib_nh, nh_common);
-				update_or_create_fnhe(nh, fl4->daddr, new_gw,
+				update_or_create_fnhe(nhc, fl4->daddr, new_gw,
 						0, false,
 						jiffies + ip_rt_gc_timeout);
 			}
@@ -1039,10 +1038,8 @@ static void __ip_rt_update_pmtu(struct rtable *rt, struct flowi4 *fl4, u32 mtu)
 	rcu_read_lock();
 	if (fib_lookup(dev_net(dst->dev), fl4, &res, 0) == 0) {
 		struct fib_nh_common *nhc = FIB_RES_NHC(res);
-		struct fib_nh *nh;
 
-		nh = container_of(nhc, struct fib_nh, nh_common);
-		update_or_create_fnhe(nh, fl4->daddr, 0, mtu, lock,
+		update_or_create_fnhe(nhc, fl4->daddr, 0, mtu, lock,
 				      jiffies + ip_rt_mtu_expires);
 	}
 	rcu_read_unlock();
@@ -1328,7 +1325,7 @@ static unsigned int ipv4_mtu(const struct dst_entry *dst)
 	return mtu - lwtunnel_headroom(dst->lwtstate, mtu);
 }
 
-static void ip_del_fnhe(struct fib_nh *nh, __be32 daddr)
+static void ip_del_fnhe(struct fib_nh_common *nhc, __be32 daddr)
 {
 	struct fnhe_hash_bucket *hash;
 	struct fib_nh_exception *fnhe, __rcu **fnhe_p;
@@ -1336,7 +1333,7 @@ static void ip_del_fnhe(struct fib_nh *nh, __be32 daddr)
 
 	spin_lock_bh(&fnhe_lock);
 
-	hash = rcu_dereference_protected(nh->nh_exceptions,
+	hash = rcu_dereference_protected(nhc->nhc_exceptions,
 					 lockdep_is_held(&fnhe_lock));
 	hash += hval;
 
@@ -1362,9 +1359,10 @@ static void ip_del_fnhe(struct fib_nh *nh, __be32 daddr)
 	spin_unlock_bh(&fnhe_lock);
 }
 
-static struct fib_nh_exception *find_exception(struct fib_nh *nh, __be32 daddr)
+static struct fib_nh_exception *find_exception(struct fib_nh_common *nhc,
+					       __be32 daddr)
 {
-	struct fnhe_hash_bucket *hash = rcu_dereference(nh->nh_exceptions);
+	struct fnhe_hash_bucket *hash = rcu_dereference(nhc->nhc_exceptions);
 	struct fib_nh_exception *fnhe;
 	u32 hval;
 
@@ -1378,7 +1376,7 @@ static struct fib_nh_exception *find_exception(struct fib_nh *nh, __be32 daddr)
 		if (fnhe->fnhe_daddr == daddr) {
 			if (fnhe->fnhe_expires &&
 			    time_after(jiffies, fnhe->fnhe_expires)) {
-				ip_del_fnhe(nh, daddr);
+				ip_del_fnhe(nhc, daddr);
 				break;
 			}
 			return fnhe;
@@ -1405,10 +1403,9 @@ u32 ip_mtu_from_fib_result(struct fib_result *res, __be32 daddr)
 		mtu = fi->fib_mtu;
 
 	if (likely(!mtu)) {
-		struct fib_nh *nh = container_of(nhc, struct fib_nh, nh_common);
 		struct fib_nh_exception *fnhe;
 
-		fnhe = find_exception(nh, daddr);
+		fnhe = find_exception(nhc, daddr);
 		if (fnhe && !time_after_eq(jiffies, fnhe->fnhe_expires))
 			mtu = fnhe->fnhe_pmtu;
 	}
@@ -1469,15 +1466,15 @@ static bool rt_bind_exception(struct rtable *rt, struct fib_nh_exception *fnhe,
 	return ret;
 }
 
-static bool rt_cache_route(struct fib_nh *nh, struct rtable *rt)
+static bool rt_cache_route(struct fib_nh_common *nhc, struct rtable *rt)
 {
 	struct rtable *orig, *prev, **p;
 	bool ret = true;
 
 	if (rt_is_input_route(rt)) {
-		p = (struct rtable **)&nh->nh_rth_input;
+		p = (struct rtable **)&nhc->nhc_rth_input;
 	} else {
-		p = (struct rtable **)raw_cpu_ptr(nh->nh_pcpu_rth_output);
+		p = (struct rtable **)raw_cpu_ptr(nhc->nhc_pcpu_rth_output);
 	}
 	orig = *p;
 
@@ -1574,7 +1571,6 @@ static void rt_set_nexthop(struct rtable *rt, __be32 daddr,
 
 	if (fi) {
 		struct fib_nh_common *nhc = FIB_RES_NHC(*res);
-		struct fib_nh *nh;
 
 		if (nhc->nhc_gw_family && nhc->nhc_scope == RT_SCOPE_LINK) {
 			rt->rt_gw_family = nhc->nhc_gw_family;
@@ -1587,15 +1583,19 @@ static void rt_set_nexthop(struct rtable *rt, __be32 daddr,
 
 		ip_dst_init_metrics(&rt->dst, fi->fib_metrics);
 
-		nh = container_of(nhc, struct fib_nh, nh_common);
 #ifdef CONFIG_IP_ROUTE_CLASSID
-		rt->dst.tclassid = nh->nh_tclassid;
+		{
+			struct fib_nh *nh;
+
+			nh = container_of(nhc, struct fib_nh, nh_common);
+			rt->dst.tclassid = nh->nh_tclassid;
+		}
 #endif
-		rt->dst.lwtstate = lwtstate_get(nh->fib_nh_lws);
+		rt->dst.lwtstate = lwtstate_get(nhc->nhc_lwtstate);
 		if (unlikely(fnhe))
 			cached = rt_bind_exception(rt, fnhe, daddr, do_cache);
 		else if (do_cache)
-			cached = rt_cache_route(nh, rt);
+			cached = rt_cache_route(nhc, rt);
 		if (unlikely(!cached)) {
 			/* Routes we intend to cache in nexthop exception or
 			 * FIB nexthop have the DST_NOCACHE bit clear.
@@ -1756,7 +1756,6 @@ static int __mkroute_input(struct sk_buff *skb,
 	struct net_device *dev = nhc->nhc_dev;
 	struct fib_nh_exception *fnhe;
 	struct rtable *rth;
-	struct fib_nh *nh;
 	int err;
 	struct in_device *out_dev;
 	bool do_cache;
@@ -1804,13 +1803,12 @@ static int __mkroute_input(struct sk_buff *skb,
 		}
 	}
 
-	nh = container_of(nhc, struct fib_nh, nh_common);
-	fnhe = find_exception(nh, daddr);
+	fnhe = find_exception(nhc, daddr);
 	if (do_cache) {
 		if (fnhe)
 			rth = rcu_dereference(fnhe->fnhe_rth_input);
 		else
-			rth = rcu_dereference(nh->nh_rth_input);
+			rth = rcu_dereference(nhc->nhc_rth_input);
 		if (rt_cache_valid(rth)) {
 			skb_dst_set_noref(skb, &rth->dst);
 			goto out;
@@ -2105,10 +2103,8 @@ out:	return err;
 	if (res->fi) {
 		if (!itag) {
 			struct fib_nh_common *nhc = FIB_RES_NHC(*res);
-			struct fib_nh *nh;
 
-			nh = container_of(nhc, struct fib_nh, nh_common);
-			rth = rcu_dereference(nh->nh_rth_input);
+			rth = rcu_dereference(nhc->nhc_rth_input);
 			if (rt_cache_valid(rth)) {
 				skb_dst_set_noref(skb, &rth->dst);
 				err = 0;
@@ -2139,7 +2135,6 @@ out:	return err;
 
 	if (do_cache) {
 		struct fib_nh_common *nhc = FIB_RES_NHC(*res);
-		struct fib_nh *nh;
 
 		rth->dst.lwtstate = lwtstate_get(nhc->nhc_lwtstate);
 		if (lwtunnel_input_redirect(rth->dst.lwtstate)) {
@@ -2148,8 +2143,7 @@ out:	return err;
 			rth->dst.input = lwtunnel_input;
 		}
 
-		nh = container_of(nhc, struct fib_nh, nh_common);
-		if (unlikely(!rt_cache_route(nh, rth)))
+		if (unlikely(!rt_cache_route(nhc, rth)))
 			rt_add_uncached_list(rth);
 	}
 	skb_dst_set(skb, &rth->dst);
@@ -2321,10 +2315,9 @@ static struct rtable *__mkroute_output(const struct fib_result *res,
 	do_cache &= fi != NULL;
 	if (fi) {
 		struct fib_nh_common *nhc = FIB_RES_NHC(*res);
-		struct fib_nh *nh = container_of(nhc, struct fib_nh, nh_common);
 		struct rtable __rcu **prth;
 
-		fnhe = find_exception(nh, fl4->daddr);
+		fnhe = find_exception(nhc, fl4->daddr);
 		if (!do_cache)
 			goto add;
 		if (fnhe) {
@@ -2337,7 +2330,7 @@ static struct rtable *__mkroute_output(const struct fib_result *res,
 				do_cache = false;
 				goto add;
 			}
-			prth = raw_cpu_ptr(nh->nh_pcpu_rth_output);
+			prth = raw_cpu_ptr(nhc->nhc_pcpu_rth_output);
 		}
 		rth = rcu_dereference(*prth);
 		if (rt_cache_valid(rth) && dst_hold_safe(&rth->dst))