[v2,net-next] net: initialize init_net earlier

Commit Message

Eric Dumazet Feb. 5, 2022, 5:01 p.m. UTC

From: Eric Dumazet <[e-mail]>

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 <[e-mail]>
---
 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(-)

Comments

[e-mail] Feb. 6, 2022, 11:10 a.m. UTC | #1

Hello:

This patch was applied to netdev/net-next.git (master)
by David S. Miller <[e-mail]>:

On Sat,  5 Feb 2022 09:01:25 -0800 you wrote:
> From: Eric Dumazet <[e-mail]>
> 
> 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.
> 
> [...]

Here is the summary with links:
  - [v2,net-next] net: initialize init_net earlier
    https://git.kernel.org/netdev/net-next/c/9c1be1935fb6

You are awesome, thank you!

Patch

diff --git a/include/net/net_namespace.h b/include/net/net_namespace.h
index 5b61c462e534be468c81d2b0f4ef586b209dd4b8..374cc7b260fcdf15a8fc2c709d0b0fc6d99e8c5c 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 65fa2e41a9c0904131525d504f3ec86add44f141..ada50f5a15e4397e45b0e5c06bab051b1ce193d9 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 1eaa0b88e3ba5d800484656f2c3420af57050294..f662c6a7d7b49b836a05efc74aeffc7fc9e4e147 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 8711350085d6b55a4f3da19bc69e521f9efb7861..0ec2f5906a27c7f930e832835682d69a32e3c8e1 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;
@@ -1087,7 +1081,7 @@  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;
 
@@ -1108,6 +1102,9 @@  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");
@@ -1122,12 +1119,8 @@  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);