Merge branch 'ipv4-fib-remove-rtnl-in-fib_net_exit_batch'

Kuniyuki Iwashima says:

====================
ipv4: fib: Remove RTNL in fib_net_exit_batch().

Currently, we flush all IPv4 routes at ->exit_batch() during
netns dismantle, which requires an extra RTNL.

IPv4 routes are not added from the fast path unlike IPv6, so
we can flush routes before default_device_exit_batch().

However, there is implicit ordering between ip_fib_net_exit()
and default_device_exit_batch().

This series detangles it and moves ip_fib_net_exit() to
 ->exit_rtnl() to save the RTNL dance.

The same change for IPv6 will need more work.
====================

Link: https://patch.msgid.link/20260612063225.455191-1-kuniyu@google.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>

2 files changed, 20 insertions, 27 deletions

diff --git a/net/ipv4/fib_frontend.c b/net/ipv4/fib_frontend.c
index ceeb87b13b93..c7d1f31650d7 100644
--- a/net/ipv4/fib_frontend.c
+++ b/net/ipv4/fib_frontend.c
@@ -88,7 +88,8 @@ struct fib_table *fib_new_table(struct net *net, u32 id)
 	if (id == RT_TABLE_LOCAL && !net->ipv4.fib_has_custom_rules)
 		alias = fib_new_table(net, RT_TABLE_MAIN);
 
-	tb = fib_trie_table(id, alias);
+	if (check_net(net))
+		tb = fib_trie_table(id, alias);
 	if (!tb)
 		return NULL;
 
@@ -1606,7 +1607,7 @@ static void ip_fib_net_exit(struct net *net)
 		struct fib_table *tb;
 
 		hlist_for_each_entry_safe(tb, tmp, head, tb_hlist) {
-			hlist_del(&tb->tb_hlist);
+			hlist_del_rcu(&tb->tb_hlist);
 			fib_table_flush(net, tb, true);
 			fib_free_table(tb);
 		}
@@ -1615,9 +1616,6 @@ static void ip_fib_net_exit(struct net *net)
 #ifdef CONFIG_IP_MULTIPLE_TABLES
 	fib4_rules_exit(net);
 #endif
-
-	kfree(net->ipv4.fib_table_hash);
-	fib4_notifier_exit(net);
 }
 
 static int __net_init fib_net_init(struct net *net)
@@ -1653,35 +1651,36 @@ out_semantics:
 	rtnl_net_lock(net);
 	ip_fib_net_exit(net);
 	rtnl_net_unlock(net);
+
+	kfree(net->ipv4.fib_table_hash);
+	fib4_notifier_exit(net);
 	goto out;
 }
 
-static void __net_exit fib_net_exit(struct net *net)
+static void __net_exit fib_net_pre_exit(struct net *net)
 {
 	fib_proc_exit(net);
 	nl_fib_lookup_exit(net);
 }
 
-static void __net_exit fib_net_exit_batch(struct list_head *net_list)
+static void __net_exit fib_net_exit_rtnl(struct net *net,
+					 struct list_head *dev_kill_list)
 {
-	struct net *net;
-
-	rtnl_lock();
-	list_for_each_entry(net, net_list, exit_list) {
-		__rtnl_net_lock(net);
-		ip_fib_net_exit(net);
-		__rtnl_net_unlock(net);
-	}
-	rtnl_unlock();
+	ip_fib_net_exit(net);
+}
 
-	list_for_each_entry(net, net_list, exit_list)
-		fib4_semantics_exit(net);
+static void __net_exit fib_net_exit(struct net *net)
+{
+	kfree(net->ipv4.fib_table_hash);
+	fib4_notifier_exit(net);
+	fib4_semantics_exit(net);
 }
 
 static struct pernet_operations fib_net_ops = {
 	.init = fib_net_init,
+	.pre_exit = fib_net_pre_exit,
+	.exit_rtnl = fib_net_exit_rtnl,
 	.exit = fib_net_exit,
-	.exit_batch = fib_net_exit_batch,
 };
 
 static const struct rtnl_msg_handler fib_rtnl_msg_handlers[] __initconst = {
diff --git a/net/ipv4/fib_trie.c b/net/ipv4/fib_trie.c
index 1308213791f1..07068207b888 100644
--- a/net/ipv4/fib_trie.c
+++ b/net/ipv4/fib_trie.c
@@ -2046,18 +2046,12 @@ int fib_table_flush(struct net *net, struct fib_table *tb, bool flush_all)
 		hlist_for_each_entry_safe(fa, tmp, &n->leaf, fa_list) {
 			struct fib_info *fi = fa->fa_info;
 
-			if (!fi || tb->tb_id != fa->tb_id ||
-			    (!(fi->fib_flags & RTNH_F_DEAD) &&
-			     !fib_props[fa->fa_type].error)) {
+			if (!fi || tb->tb_id != fa->tb_id) {
 				slen = fa->fa_slen;
 				continue;
 			}
 
-			/* When not flushing the entire table, skip error
-			 * routes that are not marked for deletion.
-			 */
-			if (!flush_all && fib_props[fa->fa_type].error &&
-			    !(fi->fib_flags & RTNH_F_DEAD)) {
+			if (!flush_all && !(fi->fib_flags & RTNH_F_DEAD)) {
 				slen = fa->fa_slen;
 				continue;
 			}