Merge branch 'ipv4-fib-convert-rtm_newroute-and-rtm_delroute-to-per-netns-rtnl'

Kuniyuki Iwashima says:

====================
ipv4: fib: Convert RTM_NEWROUTE and RTM_DELROUTE to per-netns RTNL.

Patch 1 is misc cleanup.
Patch 2 ~ 8 converts two fib_info hash tables to per-netns.
Patch 9 ~ 12 converts rtnl_lock() to rtnl_net_lcok().

v2: https://lore.kernel.org/20250226192556.21633-1-kuniyu@amazon.com
v1: https://lore.kernel.org/20250225182250.74650-1-kuniyu@amazon.com
====================

Link: https://patch.msgid.link/20250228042328.96624-1-kuniyu@amazon.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>

5 files changed, 159 insertions, 148 deletions

diff --git a/include/net/ip_fib.h b/include/net/ip_fib.h
index a113c11ab56b..e3864b74e92a 100644
--- a/include/net/ip_fib.h
+++ b/include/net/ip_fib.h
@@ -162,6 +162,8 @@ struct fib_info {
 	struct fib_nh		fib_nh[] __counted_by(fib_nhs);
 };
 
+int __net_init fib4_semantics_init(struct net *net);
+void __net_exit fib4_semantics_exit(struct net *net);
 
 #ifdef CONFIG_IP_MULTIPLE_TABLES
 struct fib_rule;
diff --git a/include/net/netns/ipv4.h b/include/net/netns/ipv4.h
index 45ac125e8aeb..650b2dc9199f 100644
--- a/include/net/netns/ipv4.h
+++ b/include/net/netns/ipv4.h
@@ -111,6 +111,9 @@ struct netns_ipv4 {
 #endif
 	struct hlist_head	*fib_table_hash;
 	struct sock		*fibnl;
+	struct hlist_head	*fib_info_hash;
+	unsigned int		fib_info_hash_bits;
+	unsigned int		fib_info_cnt;
 
 	struct sock		*mc_autojoin_sk;
 
diff --git a/net/ipv4/fib_frontend.c b/net/ipv4/fib_frontend.c
index 272e42d81323..6de77415b5b3 100644
--- a/net/ipv4/fib_frontend.c
+++ b/net/ipv4/fib_frontend.c
@@ -553,18 +553,16 @@ static int rtentry_to_fib_config(struct net *net, int cmd, struct rtentry *rt,
 			const struct in_ifaddr *ifa;
 			struct in_device *in_dev;
 
-			in_dev = __in_dev_get_rtnl(dev);
+			in_dev = __in_dev_get_rtnl_net(dev);
 			if (!in_dev)
 				return -ENODEV;
 
 			*colon = ':';
 
-			rcu_read_lock();
-			in_dev_for_each_ifa_rcu(ifa, in_dev) {
+			in_dev_for_each_ifa_rtnl_net(net, ifa, in_dev) {
 				if (strcmp(ifa->ifa_label, devname) == 0)
 					break;
 			}
-			rcu_read_unlock();
 
 			if (!ifa)
 				return -ENODEV;
@@ -635,7 +633,7 @@ int ip_rt_ioctl(struct net *net, unsigned int cmd, struct rtentry *rt)
 		if (!ns_capable(net->user_ns, CAP_NET_ADMIN))
 			return -EPERM;
 
-		rtnl_lock();
+		rtnl_net_lock(net);
 		err = rtentry_to_fib_config(net, cmd, rt, &cfg);
 		if (err == 0) {
 			struct fib_table *tb;
@@ -659,7 +657,7 @@ int ip_rt_ioctl(struct net *net, unsigned int cmd, struct rtentry *rt)
 			/* allocated by rtentry_to_fib_config() */
 			kfree(cfg.fc_mx);
 		}
-		rtnl_unlock();
+		rtnl_net_unlock(net);
 		return err;
 	}
 	return -EINVAL;
@@ -837,19 +835,33 @@ static int rtm_to_fib_config(struct net *net, struct sk_buff *skb,
 		}
 	}
 
+	if (cfg->fc_dst_len > 32) {
+		NL_SET_ERR_MSG(extack, "Invalid prefix length");
+		err = -EINVAL;
+		goto errout;
+	}
+
+	if (cfg->fc_dst_len < 32 && (ntohl(cfg->fc_dst) << cfg->fc_dst_len)) {
+		NL_SET_ERR_MSG(extack, "Invalid prefix for given prefix length");
+		err = -EINVAL;
+		goto errout;
+	}
+
 	if (cfg->fc_nh_id) {
 		if (cfg->fc_oif || cfg->fc_gw_family ||
 		    cfg->fc_encap || cfg->fc_mp) {
 			NL_SET_ERR_MSG(extack,
 				       "Nexthop specification and nexthop id are mutually exclusive");
-			return -EINVAL;
+			err = -EINVAL;
+			goto errout;
 		}
 	}
 
 	if (has_gw && has_via) {
 		NL_SET_ERR_MSG(extack,
 			       "Nexthop configuration can not contain both GATEWAY and VIA");
-		return -EINVAL;
+		err = -EINVAL;
+		goto errout;
 	}
 
 	if (!cfg->fc_table)
@@ -872,20 +884,24 @@ static int inet_rtm_delroute(struct sk_buff *skb, struct nlmsghdr *nlh,
 	if (err < 0)
 		goto errout;
 
+	rtnl_net_lock(net);
+
 	if (cfg.fc_nh_id && !nexthop_find_by_id(net, cfg.fc_nh_id)) {
 		NL_SET_ERR_MSG(extack, "Nexthop id does not exist");
 		err = -EINVAL;
-		goto errout;
+		goto unlock;
 	}
 
 	tb = fib_get_table(net, cfg.fc_table);
 	if (!tb) {
 		NL_SET_ERR_MSG(extack, "FIB table does not exist");
 		err = -ESRCH;
-		goto errout;
+		goto unlock;
 	}
 
 	err = fib_table_delete(net, tb, &cfg, extack);
+unlock:
+	rtnl_net_unlock(net);
 errout:
 	return err;
 }
@@ -902,15 +918,20 @@ static int inet_rtm_newroute(struct sk_buff *skb, struct nlmsghdr *nlh,
 	if (err < 0)
 		goto errout;
 
+	rtnl_net_lock(net);
+
 	tb = fib_new_table(net, cfg.fc_table);
 	if (!tb) {
 		err = -ENOBUFS;
-		goto errout;
+		goto unlock;
 	}
 
 	err = fib_table_insert(net, tb, &cfg, extack);
 	if (!err && cfg.fc_type == RTN_LOCAL)
 		net->ipv4.fib_has_custom_local_routes = true;
+
+unlock:
+	rtnl_net_unlock(net);
 errout:
 	return err;
 }
@@ -1450,7 +1471,7 @@ static int fib_inetaddr_event(struct notifier_block *this, unsigned long event,
 		fib_sync_up(dev, RTNH_F_DEAD);
 #endif
 		atomic_inc(&net->ipv4.dev_addr_genid);
-		rt_cache_flush(dev_net(dev));
+		rt_cache_flush(net);
 		break;
 	case NETDEV_DOWN:
 		fib_del_ifaddr(ifa, NULL);
@@ -1461,7 +1482,7 @@ static int fib_inetaddr_event(struct notifier_block *this, unsigned long event,
 			 */
 			fib_disable_ip(dev, event, true);
 		} else {
-			rt_cache_flush(dev_net(dev));
+			rt_cache_flush(net);
 		}
 		break;
 	}
@@ -1575,7 +1596,7 @@ static void ip_fib_net_exit(struct net *net)
 {
 	int i;
 
-	ASSERT_RTNL();
+	ASSERT_RTNL_NET(net);
 #ifdef CONFIG_IP_MULTIPLE_TABLES
 	RCU_INIT_POINTER(net->ipv4.fib_main, NULL);
 	RCU_INIT_POINTER(net->ipv4.fib_default, NULL);
@@ -1615,9 +1636,15 @@ static int __net_init fib_net_init(struct net *net)
 	error = ip_fib_net_init(net);
 	if (error < 0)
 		goto out;
+
+	error = fib4_semantics_init(net);
+	if (error)
+		goto out_semantics;
+
 	error = nl_fib_lookup_init(net);
 	if (error < 0)
 		goto out_nlfl;
+
 	error = fib_proc_init(net);
 	if (error < 0)
 		goto out_proc;
@@ -1627,9 +1654,11 @@ out:
 out_proc:
 	nl_fib_lookup_exit(net);
 out_nlfl:
-	rtnl_lock();
+	fib4_semantics_exit(net);
+out_semantics:
+	rtnl_net_lock(net);
 	ip_fib_net_exit(net);
-	rtnl_unlock();
+	rtnl_net_unlock(net);
 	goto out;
 }
 
@@ -1644,10 +1673,15 @@ static void __net_exit fib_net_exit_batch(struct list_head *net_list)
 	struct net *net;
 
 	rtnl_lock();
-	list_for_each_entry(net, net_list, exit_list)
+	list_for_each_entry(net, net_list, exit_list) {
+		__rtnl_net_lock(net);
 		ip_fib_net_exit(net);
-
+		__rtnl_net_unlock(net);
+	}
 	rtnl_unlock();
+
+	list_for_each_entry(net, net_list, exit_list)
+		fib4_semantics_exit(net);
 }
 
 static struct pernet_operations fib_net_ops = {
@@ -1658,9 +1692,9 @@ static struct pernet_operations fib_net_ops = {
 
 static const struct rtnl_msg_handler fib_rtnl_msg_handlers[] __initconst = {
 	{.protocol = PF_INET, .msgtype = RTM_NEWROUTE,
-	 .doit = inet_rtm_newroute},
+	 .doit = inet_rtm_newroute, .flags = RTNL_FLAG_DOIT_PERNET},
 	{.protocol = PF_INET, .msgtype = RTM_DELROUTE,
-	 .doit = inet_rtm_delroute},
+	 .doit = inet_rtm_delroute, .flags = RTNL_FLAG_DOIT_PERNET},
 	{.protocol = PF_INET, .msgtype = RTM_GETROUTE, .dumpit = inet_dump_fib,
 	 .flags = RTNL_FLAG_DUMP_UNLOCKED | RTNL_FLAG_DUMP_SPLIT_NLM_DONE},
 };
diff --git a/net/ipv4/fib_semantics.c b/net/ipv4/fib_semantics.c
index d2cee5c314f5..f68bb9e34c34 100644
--- a/net/ipv4/fib_semantics.c
+++ b/net/ipv4/fib_semantics.c
@@ -50,12 +50,6 @@
 
 #include "fib_lookup.h"
 
-static struct hlist_head *fib_info_hash;
-static struct hlist_head *fib_info_laddrhash;
-static unsigned int fib_info_hash_size;
-static unsigned int fib_info_hash_bits;
-static unsigned int fib_info_cnt;
-
 /* for_nexthops and change_nexthops only used when nexthop object
  * is not set in a fib_info. The logic within can reference fib_nh.
  */
@@ -258,8 +252,7 @@ void fib_release_info(struct fib_info *fi)
 	ASSERT_RTNL();
 	if (fi && refcount_dec_and_test(&fi->fib_treeref)) {
 		hlist_del(&fi->fib_hash);
-
-		fib_info_cnt--;
+		fi->fib_net->ipv4.fib_info_cnt--;
 
 		if (fi->fib_prefsrc)
 			hlist_del(&fi->fib_lhash);
@@ -335,11 +328,12 @@ static unsigned int fib_info_hashfn_1(int init_val, u8 protocol, u8 scope,
 static unsigned int fib_info_hashfn_result(const struct net *net,
 					   unsigned int val)
 {
-	return hash_32(val ^ net_hash_mix(net), fib_info_hash_bits);
+	return hash_32(val ^ net_hash_mix(net), net->ipv4.fib_info_hash_bits);
 }
 
-static inline unsigned int fib_info_hashfn(struct fib_info *fi)
+static struct hlist_head *fib_info_hash_bucket(struct fib_info *fi)
 {
+	struct net *net = fi->fib_net;
 	unsigned int val;
 
 	val = fib_info_hashfn_1(fi->fib_nhs, fi->fib_protocol,
@@ -354,7 +348,70 @@ static inline unsigned int fib_info_hashfn(struct fib_info *fi)
 		} endfor_nexthops(fi)
 	}
 
-	return fib_info_hashfn_result(fi->fib_net, val);
+	return &net->ipv4.fib_info_hash[fib_info_hashfn_result(net, val)];
+}
+
+static struct hlist_head *fib_info_laddrhash_bucket(const struct net *net,
+						    __be32 val)
+{
+	unsigned int hash_bits = net->ipv4.fib_info_hash_bits;
+	u32 slot;
+
+	slot = hash_32(net_hash_mix(net) ^ (__force u32)val, hash_bits);
+
+	return &net->ipv4.fib_info_hash[(1 << hash_bits) + slot];
+}
+
+static struct hlist_head *fib_info_hash_alloc(unsigned int hash_bits)
+{
+	/* The second half is used for prefsrc */
+	return kvcalloc((1 << hash_bits) * 2, sizeof(struct hlist_head *),
+			GFP_KERNEL);
+}
+
+static void fib_info_hash_free(struct hlist_head *head)
+{
+	kvfree(head);
+}
+
+static void fib_info_hash_grow(struct net *net)
+{
+	unsigned int old_size = 1 << net->ipv4.fib_info_hash_bits;
+	struct hlist_head *new_info_hash, *old_info_hash;
+	unsigned int i;
+
+	if (net->ipv4.fib_info_cnt < old_size)
+		return;
+
+	new_info_hash = fib_info_hash_alloc(net->ipv4.fib_info_hash_bits + 1);
+	if (!new_info_hash)
+		return;
+
+	old_info_hash = net->ipv4.fib_info_hash;
+	net->ipv4.fib_info_hash = new_info_hash;
+	net->ipv4.fib_info_hash_bits += 1;
+
+	for (i = 0; i < old_size; i++) {
+		struct hlist_head *head = &old_info_hash[i];
+		struct hlist_node *n;
+		struct fib_info *fi;
+
+		hlist_for_each_entry_safe(fi, n, head, fib_hash)
+			hlist_add_head(&fi->fib_hash, fib_info_hash_bucket(fi));
+	}
+
+	for (i = 0; i < old_size; i++) {
+		struct hlist_head *lhead = &old_info_hash[old_size + i];
+		struct hlist_node *n;
+		struct fib_info *fi;
+
+		hlist_for_each_entry_safe(fi, n, lhead, fib_lhash)
+			hlist_add_head(&fi->fib_lhash,
+				       fib_info_laddrhash_bucket(fi->fib_net,
+								 fi->fib_prefsrc));
+	}
+
+	fib_info_hash_free(old_info_hash);
 }
 
 /* no metrics, only nexthop id */
@@ -370,13 +427,12 @@ static struct fib_info *fib_find_info_nh(struct net *net,
 				 (__force u32)cfg->fc_prefsrc,
 				 cfg->fc_priority);
 	hash = fib_info_hashfn_result(net, hash);
-	head = &fib_info_hash[hash];
+	head = &net->ipv4.fib_info_hash[hash];
 
 	hlist_for_each_entry(fi, head, fib_hash) {
-		if (!net_eq(fi->fib_net, net))
-			continue;
 		if (!fi->nh || fi->nh->id != cfg->fc_nh_id)
 			continue;
+
 		if (cfg->fc_protocol == fi->fib_protocol &&
 		    cfg->fc_scope == fi->fib_scope &&
 		    cfg->fc_prefsrc == fi->fib_prefsrc &&
@@ -392,18 +448,13 @@ static struct fib_info *fib_find_info_nh(struct net *net,
 
 static struct fib_info *fib_find_info(struct fib_info *nfi)
 {
-	struct hlist_head *head;
+	struct hlist_head *head = fib_info_hash_bucket(nfi);
 	struct fib_info *fi;
-	unsigned int hash;
-
-	hash = fib_info_hashfn(nfi);
-	head = &fib_info_hash[hash];
 
 	hlist_for_each_entry(fi, head, fib_hash) {
-		if (!net_eq(fi->fib_net, nfi->fib_net))
-			continue;
 		if (fi->fib_nhs != nfi->fib_nhs)
 			continue;
+
 		if (nfi->fib_protocol == fi->fib_protocol &&
 		    nfi->fib_scope == fi->fib_scope &&
 		    nfi->fib_prefsrc == fi->fib_prefsrc &&
@@ -1239,64 +1290,6 @@ int fib_check_nh(struct net *net, struct fib_nh *nh, u32 table, u8 scope,
 	return err;
 }
 
-static struct hlist_head *
-fib_info_laddrhash_bucket(const struct net *net, __be32 val)
-{
-	u32 slot = hash_32(net_hash_mix(net) ^ (__force u32)val,
-			   fib_info_hash_bits);
-
-	return &fib_info_laddrhash[slot];
-}
-
-static void fib_info_hash_move(struct hlist_head *new_info_hash,
-			       struct hlist_head *new_laddrhash,
-			       unsigned int new_size)
-{
-	struct hlist_head *old_info_hash, *old_laddrhash;
-	unsigned int old_size = fib_info_hash_size;
-	unsigned int i;
-
-	ASSERT_RTNL();
-	old_info_hash = fib_info_hash;
-	old_laddrhash = fib_info_laddrhash;
-	fib_info_hash_size = new_size;
-	fib_info_hash_bits = ilog2(new_size);
-
-	for (i = 0; i < old_size; i++) {
-		struct hlist_head *head = &fib_info_hash[i];
-		struct hlist_node *n;
-		struct fib_info *fi;
-
-		hlist_for_each_entry_safe(fi, n, head, fib_hash) {
-			struct hlist_head *dest;
-			unsigned int new_hash;
-
-			new_hash = fib_info_hashfn(fi);
-			dest = &new_info_hash[new_hash];
-			hlist_add_head(&fi->fib_hash, dest);
-		}
-	}
-	fib_info_hash = new_info_hash;
-
-	fib_info_laddrhash = new_laddrhash;
-	for (i = 0; i < old_size; i++) {
-		struct hlist_head *lhead = &old_laddrhash[i];
-		struct hlist_node *n;
-		struct fib_info *fi;
-
-		hlist_for_each_entry_safe(fi, n, lhead, fib_lhash) {
-			struct hlist_head *ldest;
-
-			ldest = fib_info_laddrhash_bucket(fi->fib_net,
-							  fi->fib_prefsrc);
-			hlist_add_head(&fi->fib_lhash, ldest);
-		}
-	}
-
-	kvfree(old_info_hash);
-	kvfree(old_laddrhash);
-}
-
 __be32 fib_info_update_nhc_saddr(struct net *net, struct fib_nh_common *nhc,
 				 unsigned char scope)
 {
@@ -1409,32 +1402,14 @@ struct fib_info *fib_create_info(struct fib_config *cfg,
 	}
 #endif
 
-	err = -ENOBUFS;
-
-	if (fib_info_cnt >= fib_info_hash_size) {
-		unsigned int new_size = fib_info_hash_size << 1;
-		struct hlist_head *new_info_hash;
-		struct hlist_head *new_laddrhash;
-		size_t bytes;
-
-		if (!new_size)
-			new_size = 16;
-		bytes = (size_t)new_size * sizeof(struct hlist_head *);
-		new_info_hash = kvzalloc(bytes, GFP_KERNEL);
-		new_laddrhash = kvzalloc(bytes, GFP_KERNEL);
-		if (!new_info_hash || !new_laddrhash) {
-			kvfree(new_info_hash);
-			kvfree(new_laddrhash);
-		} else {
-			fib_info_hash_move(new_info_hash, new_laddrhash, new_size);
-		}
-		if (!fib_info_hash_size)
-			goto failure;
-	}
+	fib_info_hash_grow(net);
 
 	fi = kzalloc(struct_size(fi, fib_nh, nhs), GFP_KERNEL);
-	if (!fi)
+	if (!fi) {
+		err = -ENOBUFS;
 		goto failure;
+	}
+
 	fi->fib_metrics = ip_fib_metrics_init(cfg->fc_mx, cfg->fc_mx_len, extack);
 	if (IS_ERR(fi->fib_metrics)) {
 		err = PTR_ERR(fi->fib_metrics);
@@ -1571,9 +1546,9 @@ link_it:
 	refcount_set(&fi->fib_treeref, 1);
 	refcount_set(&fi->fib_clntref, 1);
 
-	fib_info_cnt++;
-	hlist_add_head(&fi->fib_hash,
-		       &fib_info_hash[fib_info_hashfn(fi)]);
+	net->ipv4.fib_info_cnt++;
+	hlist_add_head(&fi->fib_hash, fib_info_hash_bucket(fi));
+
 	if (fi->fib_prefsrc) {
 		struct hlist_head *head;
 
@@ -1855,7 +1830,7 @@ int fib_sync_down_addr(struct net_device *dev, __be32 local)
 	struct fib_info *fi;
 	int ret = 0;
 
-	if (!fib_info_laddrhash || local == 0)
+	if (!local)
 		return 0;
 
 	head = fib_info_laddrhash_bucket(net, local);
@@ -2257,3 +2232,22 @@ check_saddr:
 			fl4->saddr = inet_select_addr(l3mdev, 0, RT_SCOPE_LINK);
 	}
 }
+
+int __net_init fib4_semantics_init(struct net *net)
+{
+	unsigned int hash_bits = 4;
+
+	net->ipv4.fib_info_hash = fib_info_hash_alloc(hash_bits);
+	if (!net->ipv4.fib_info_hash)
+		return -ENOMEM;
+
+	net->ipv4.fib_info_hash_bits = hash_bits;
+	net->ipv4.fib_info_cnt = 0;
+
+	return 0;
+}
+
+void __net_exit fib4_semantics_exit(struct net *net)
+{
+	fib_info_hash_free(net->ipv4.fib_info_hash);
+}
diff --git a/net/ipv4/fib_trie.c b/net/ipv4/fib_trie.c
index d6411ac81096..59a6f0a9638f 100644
--- a/net/ipv4/fib_trie.c
+++ b/net/ipv4/fib_trie.c
@@ -1187,22 +1187,6 @@ static int fib_insert_alias(struct trie *t, struct key_vector *tp,
 	return 0;
 }
 
-static bool fib_valid_key_len(u32 key, u8 plen, struct netlink_ext_ack *extack)
-{
-	if (plen > KEYLENGTH) {
-		NL_SET_ERR_MSG(extack, "Invalid prefix length");
-		return false;
-	}
-
-	if ((plen < KEYLENGTH) && (key << plen)) {
-		NL_SET_ERR_MSG(extack,
-			       "Invalid prefix for given prefix length");
-		return false;
-	}
-
-	return true;
-}
-
 static void fib_remove_alias(struct trie *t, struct key_vector *tp,
 			     struct key_vector *l, struct fib_alias *old);
 
@@ -1223,9 +1207,6 @@ int fib_table_insert(struct net *net, struct fib_table *tb,
 
 	key = ntohl(cfg->fc_dst);
 
-	if (!fib_valid_key_len(key, plen, extack))
-		return -EINVAL;
-
 	pr_debug("Insert table=%u %08x/%d\n", tb->tb_id, key, plen);
 
 	fi = fib_create_info(cfg, extack);
@@ -1717,9 +1698,6 @@ int fib_table_delete(struct net *net, struct fib_table *tb,
 
 	key = ntohl(cfg->fc_dst);
 
-	if (!fib_valid_key_len(key, plen, extack))
-		return -EINVAL;
-
 	l = fib_find_node(t, &tp, key);
 	if (!l)
 		return -ESRCH;