netdev - [PATCH net 1/1] netfilter: nf_tables: wait for rcu grace period on net

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [<thread-prev] [day] [month] [year] [list]

Message-Id: <20241106235853.169747-2-pablo@netfilter.org>
Date: Thu,  7 Nov 2024 00:58:53 +0100
From: Pablo Neira Ayuso <pablo@...filter.org>
To: netfilter-devel@...r.kernel.org
Cc: davem@...emloft.net,
	netdev@...r.kernel.org,
	kuba@...nel.org,
	pabeni@...hat.com,
	edumazet@...gle.com,
	fw@...len.de
Subject: [PATCH net 1/1] netfilter: nf_tables: wait for rcu grace period on net_device removal

8c873e219970 ("netfilter: core: free hooks with call_rcu") removed
synchronize_net() call when unregistering basechain hook, however,
net_device removal event handler for the NFPROTO_NETDEV was not updated
to wait for RCU grace period.

Note that 835b803377f5 ("netfilter: nf_tables_netdev: unregister hooks
on net_device removal") does not remove basechain rules on device
removal, I was hinted to remove rules on net_device removal later, see
5ebe0b0eec9d ("netfilter: nf_tables: destroy basechain and rules on
netdevice removal").

Although NETDEV_UNREGISTER event is guaranteed to be handled after
synchronize_net() call, this path needs to wait for rcu grace period via
rcu callback to release basechain hooks if netns is alive because an
ongoing netlink dump could be in progress (sockets hold a reference on
the netns).

Note that nf_tables_pre_exit_net() unregisters and releases basechain
hooks but it is possible to see NETDEV_UNREGISTER at a later stage in
the netns exit path, eg. veth peer device in another netns:

 cleanup_net()
  default_device_exit_batch()
   unregister_netdevice_many_notify()
    notifier_call_chain()
     nf_tables_netdev_event()
      __nft_release_basechain()

In this particular case, same rule of thumb applies: if netns is alive,
then wait for rcu grace period because netlink dump in the other netns
could be in progress. Otherwise, if the other netns is going away then
no netlink dump can be in progress and basechain hooks can be released
inmediately.

While at it, turn WARN_ON() into WARN_ON_ONCE() for the basechain
validation, which should not ever happen.

Fixes: 835b803377f5 ("netfilter: nf_tables_netdev: unregister hooks on net_device removal")
Signed-off-by: Pablo Neira Ayuso <pablo@...filter.org>
---
 include/net/netfilter/nf_tables.h |  2 ++
 net/netfilter/nf_tables_api.c     | 41 +++++++++++++++++++++++++------
 2 files changed, 36 insertions(+), 7 deletions(-)

diff --git a/include/net/netfilter/nf_tables.h b/include/net/netfilter/nf_tables.h
index 91ae20cb7648..8dd8e278843d 100644
--- a/include/net/netfilter/nf_tables.h
+++ b/include/net/netfilter/nf_tables.h
@@ -1120,6 +1120,7 @@ struct nft_chain {
 	char				*name;
 	u16				udlen;
 	u8				*udata;
+	struct rcu_head			rcu_head;
 
 	/* Only used during control plane commit phase: */
 	struct nft_rule_blob		*blob_next;
@@ -1282,6 +1283,7 @@ struct nft_table {
 	struct list_head		sets;
 	struct list_head		objects;
 	struct list_head		flowtables;
+	possible_net_t			net;
 	u64				hgenerator;
 	u64				handle;
 	u32				use;
diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c
index a24fe62650a7..588a2757986c 100644
--- a/net/netfilter/nf_tables_api.c
+++ b/net/netfilter/nf_tables_api.c
@@ -1495,6 +1495,7 @@ static int nf_tables_newtable(struct sk_buff *skb, const struct nfnl_info *info,
 	INIT_LIST_HEAD(&table->sets);
 	INIT_LIST_HEAD(&table->objects);
 	INIT_LIST_HEAD(&table->flowtables);
+	write_pnet(&table->net, net);
 	table->family = family;
 	table->flags = flags;
 	table->handle = ++nft_net->table_handle;
@@ -11430,22 +11431,48 @@ int nft_data_dump(struct sk_buff *skb, int attr, const struct nft_data *data,
 }
 EXPORT_SYMBOL_GPL(nft_data_dump);
 
-int __nft_release_basechain(struct nft_ctx *ctx)
+static void __nft_release_basechain_now(struct nft_ctx *ctx)
 {
 	struct nft_rule *rule, *nr;
 
-	if (WARN_ON(!nft_is_base_chain(ctx->chain)))
-		return 0;
-
-	nf_tables_unregister_hook(ctx->net, ctx->chain->table, ctx->chain);
 	list_for_each_entry_safe(rule, nr, &ctx->chain->rules, list) {
 		list_del(&rule->list);
-		nft_use_dec(&ctx->chain->use);
 		nf_tables_rule_release(ctx, rule);
 	}
+	nf_tables_chain_destroy(ctx->chain);
+}
+
+static void nft_release_basechain_rcu(struct rcu_head *head)
+{
+	struct nft_chain *chain = container_of(head, struct nft_chain, rcu_head);
+	struct nft_ctx ctx = {
+		.family	= chain->table->family,
+		.chain	= chain,
+		.net	= read_pnet(&chain->table->net),
+	};
+
+	__nft_release_basechain_now(&ctx);
+	put_net(ctx.net);
+}
+
+int __nft_release_basechain(struct nft_ctx *ctx)
+{
+	struct nft_rule *rule;
+
+	if (WARN_ON_ONCE(!nft_is_base_chain(ctx->chain)))
+		return 0;
+
+	nf_tables_unregister_hook(ctx->net, ctx->chain->table, ctx->chain);
+	list_for_each_entry(rule, &ctx->chain->rules, list)
+		nft_use_dec(&ctx->chain->use);
+
 	nft_chain_del(ctx->chain);
 	nft_use_dec(&ctx->table->use);
-	nf_tables_chain_destroy(ctx->chain);
+
+	if (maybe_get_net(ctx->net))
+		call_rcu(&ctx->chain->rcu_head, nft_release_basechain_rcu);
+	else
+		__nft_release_basechain_now(ctx);
 
 	return 0;
 }
-- 
2.30.2