Received-SPF: pass (google.com: domain of linux-kernel-owner@vger.kernel.org designates 2620:137:e000::1:20 as permitted sender) client-ip=2620:137:e000::1:20;
From:   Sasha Levin <sashal@kernel.org>
To:     linux-kernel@vger.kernel.org, stable@vger.kernel.org
Cc:     Eric Dumazet <edumazet@google.com>,
        "David S . Miller" <davem@davemloft.net>,
        Sasha Levin <sashal@kernel.org>, kuba@kernel.org,
        pabeni@redhat.com, akpm@linux-foundation.org, mhiramat@kernel.org,
        rostedt@goodmis.org, vbabka@suse.cz, ahalaney@redhat.com,
        wangkefeng.wang@huawei.com, linux@rasmusvillemoes.dk,
        keescook@chromium.org, mark-pk.tsai@mediatek.com,
        valentin.schneider@arm.com, peterz@infradead.org,
        bigeasy@linutronix.de, toke@redhat.com, imagedong@tencent.com,
        petrm@nvidia.com, memxor@gmail.com, arnd@arndb.de,
        changbin.du@intel.com, yajun.deng@linux.dev, hmukos@yandex-team.ru,
        netdev@vger.kernel.org
Subject: [PATCH AUTOSEL 5.17 046/149] net: initialize init_net earlier
Date:   Fri,  1 Apr 2022 10:23:53 -0400
Message-Id: <20220401142536.1948161-46-sashal@kernel.org>
In-Reply-To: <20220401142536.1948161-1-sashal@kernel.org>
References: <20220401142536.1948161-1-sashal@kernel.org>
MIME-Version: 1.0
Content-Transfer-Encoding: 8bit
Precedence: bulk

From: Eric Dumazet <edumazet@google.com>

[ Upstream commit 9c1be1935fb68b2413796cdc03d019b8cf35ab51 ]

While testing a patch that will follow later
("net: add netns refcount tracker to struct nsproxy")
I found that devtmpfs_init() was called before init_net
was initialized.

This is a bug, because devtmpfs_setup() calls
ksys_unshare(CLONE_NEWNS);

This has the effect of increasing init_net refcount,
which will be later overwritten to 1, as part of setup_net(&init_net)

We had too many prior patches [1] trying to work around the root cause.

Really, make sure init_net is in BSS section, and that net_ns_init()
is called earlier at boot time.

Note that another patch ("vfs: add netns refcount tracker
to struct fs_context") also will need net_ns_init() being called
before vfs_caches_init()

As a bonus, this patch saves around 4KB in .data section.

[1]

f8c46cb39079 ("netns: do not call pernet ops for not yet set up init_net namespace")
b5082df8019a ("net: Initialise init_net.count to 1")
734b65417b24 ("net: Statically initialize init_net.dev_base_head")

v2: fixed a build error reported by kernel build bots (CONFIG_NET=n)

Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 include/net/net_namespace.h |  6 ++++++
 init/main.c                 |  2 ++
 net/core/dev.c              |  3 +--
 net/core/net_namespace.c    | 17 +++++------------
 4 files changed, 14 insertions(+), 14 deletions(-)

diff --git a/include/net/net_namespace.h b/include/net/net_namespace.h
index 5b61c462e534..374cc7b260fc 100644
--- a/include/net/net_namespace.h
+++ b/include/net/net_namespace.h
@@ -513,4 +513,10 @@ static inline void fnhe_genid_bump(struct net *net)
 	atomic_inc(&net->fnhe_genid);
 }
 
+#ifdef CONFIG_NET
+void net_ns_init(void);
+#else
+static inline void net_ns_init(void) {}
+#endif
+
 #endif /* __NET_NET_NAMESPACE_H */
diff --git a/init/main.c b/init/main.c
index 65fa2e41a9c0..ada50f5a15e4 100644
--- a/init/main.c
+++ b/init/main.c
@@ -99,6 +99,7 @@
 #include <linux/kcsan.h>
 #include <linux/init_syscalls.h>
 #include <linux/stackdepot.h>
+#include <net/net_namespace.h>
 
 #include <asm/io.h>
 #include <asm/bugs.h>
@@ -1116,6 +1117,7 @@ asmlinkage __visible void __init __no_sanitize_address start_kernel(void)
 	key_init();
 	security_init();
 	dbg_late_init();
+	net_ns_init();
 	vfs_caches_init();
 	pagecache_init();
 	signals_init();
diff --git a/net/core/dev.c b/net/core/dev.c
index 1baab07820f6..91cf709c98b3 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -10732,8 +10732,7 @@ static int __net_init netdev_init(struct net *net)
 	BUILD_BUG_ON(GRO_HASH_BUCKETS >
 		     8 * sizeof_field(struct napi_struct, gro_bitmask));
 
-	if (net != &init_net)
-		INIT_LIST_HEAD(&net->dev_base_head);
+	INIT_LIST_HEAD(&net->dev_base_head);
 
 	net->dev_name_head = netdev_create_hash();
 	if (net->dev_name_head == NULL)
diff --git a/net/core/net_namespace.c b/net/core/net_namespace.c
index a5b5bb99c644..212e65add951 100644
--- a/net/core/net_namespace.c
+++ b/net/core/net_namespace.c
@@ -44,13 +44,7 @@ EXPORT_SYMBOL_GPL(net_rwsem);
 static struct key_tag init_net_key_domain = { .usage = REFCOUNT_INIT(1) };
 #endif
 
-struct net init_net = {
-	.ns.count	= REFCOUNT_INIT(1),
-	.dev_base_head	= LIST_HEAD_INIT(init_net.dev_base_head),
-#ifdef CONFIG_KEYS
-	.key_domain	= &init_net_key_domain,
-#endif
-};
+struct net init_net;
 EXPORT_SYMBOL(init_net);
 
 static bool init_net_initialized;
@@ -1084,7 +1078,7 @@ static void rtnl_net_notifyid(struct net *net, int cmd, int id, u32 portid,
 	rtnl_set_sk_err(net, RTNLGRP_NSID, err);
 }
 
-static int __init net_ns_init(void)
+void __init net_ns_init(void)
 {
 	struct net_generic *ng;
 
@@ -1105,6 +1099,9 @@ static int __init net_ns_init(void)
 
 	rcu_assign_pointer(init_net.gen, ng);
 
+#ifdef CONFIG_KEYS
+	init_net.key_domain = &init_net_key_domain;
+#endif
 	down_write(&pernet_ops_rwsem);
 	if (setup_net(&init_net, &init_user_ns))
 		panic("Could not setup the initial network namespace");
@@ -1119,12 +1116,8 @@ static int __init net_ns_init(void)
 		      RTNL_FLAG_DOIT_UNLOCKED);
 	rtnl_register(PF_UNSPEC, RTM_GETNSID, rtnl_net_getid, rtnl_net_dumpid,
 		      RTNL_FLAG_DOIT_UNLOCKED);
-
-	return 0;
 }
 
-pure_initcall(net_ns_init);
-
 static void free_exit_list(struct pernet_operations *ops, struct list_head *net_exit_list)
 {
 	ops_pre_exit_list(ops, net_exit_list);
-- 
2.34.1