From: Kuniyuki Iwashima <kuniyu@amazon.com>
To: "David S. Miller" <davem@davemloft.net>,
Eric Dumazet <edumazet@google.com>,
Jakub Kicinski <kuba@kernel.org>, Paolo Abeni <pabeni@redhat.com>,
Simon Horman <horms@kernel.org>
Cc: Andrew Lunn <andrew+netdev@lunn.ch>,
Marc Kleine-Budde <mkl@pengutronix.de>,
Vincent Mailhol <mailhol.vincent@wanadoo.fr>,
"Daniel Borkmann" <daniel@iogearbox.net>,
Nikolay Aleksandrov <razor@blackwall.org>,
Kuniyuki Iwashima <kuniyu@amazon.com>,
Kuniyuki Iwashima <kuni1840@gmail.com>, <netdev@vger.kernel.org>
Subject: [PATCH v3 net-next 01/10] rtnetlink: Remove __rtnl_link_unregister().
Date: Wed, 6 Nov 2024 18:28:51 -0800 [thread overview]
Message-ID: <20241107022900.70287-2-kuniyu@amazon.com> (raw)
In-Reply-To: <20241107022900.70287-1-kuniyu@amazon.com>
rtnl_link_unregister() holds RTNL and calls __rtnl_link_unregister(),
where we call synchronize_srcu() to wait inflight RTM_NEWLINK requests
for per-netns RTNL.
We put synchronize_srcu() in __rtnl_link_unregister() due to ifb.ko
and dummy.ko.
However, rtnl_newlink() will acquire SRCU before RTNL later in this
series. Then, lockdep will detect the deadlock:
rtnl_link_unregister() rtnl_newlink()
---- ----
lock(rtnl_mutex);
lock(&ops->srcu);
lock(rtnl_mutex);
sync(&ops->srcu);
To avoid the problem, we must call synchronize_srcu() before RTNL in
rtnl_link_unregister().
As a preparation, let's remove __rtnl_link_unregister().
Signed-off-by: Kuniyuki Iwashima <kuniyu@amazon.com>
---
drivers/net/dummy.c | 6 +++++-
drivers/net/ifb.c | 6 +++++-
include/net/rtnetlink.h | 1 -
net/core/rtnetlink.c | 32 ++++++++++----------------------
4 files changed, 20 insertions(+), 25 deletions(-)
diff --git a/drivers/net/dummy.c b/drivers/net/dummy.c
index e9c5e1e11fa0..72618b6af44e 100644
--- a/drivers/net/dummy.c
+++ b/drivers/net/dummy.c
@@ -166,6 +166,7 @@ static int __init dummy_init_one(void)
static int __init dummy_init_module(void)
{
+ bool need_unregister = false;
int i, err = 0;
down_write(&pernet_ops_rwsem);
@@ -179,12 +180,15 @@ static int __init dummy_init_module(void)
cond_resched();
}
if (err < 0)
- __rtnl_link_unregister(&dummy_link_ops);
+ need_unregister = true;
out:
rtnl_unlock();
up_write(&pernet_ops_rwsem);
+ if (need_unregister)
+ rtnl_link_unregister(&dummy_link_ops);
+
return err;
}
diff --git a/drivers/net/ifb.c b/drivers/net/ifb.c
index 2c1b5def4a0b..a4b9ec4e8f30 100644
--- a/drivers/net/ifb.c
+++ b/drivers/net/ifb.c
@@ -424,6 +424,7 @@ static int __init ifb_init_one(int index)
static int __init ifb_init_module(void)
{
+ bool need_unregister = false;
int i, err;
down_write(&pernet_ops_rwsem);
@@ -437,12 +438,15 @@ static int __init ifb_init_module(void)
cond_resched();
}
if (err)
- __rtnl_link_unregister(&ifb_link_ops);
+ need_unregister = true;
out:
rtnl_unlock();
up_write(&pernet_ops_rwsem);
+ if (need_unregister)
+ rtnl_link_unregister(&ifb_link_ops);
+
return err;
}
diff --git a/include/net/rtnetlink.h b/include/net/rtnetlink.h
index b260c0cc9671..3ebfcc6e56fd 100644
--- a/include/net/rtnetlink.h
+++ b/include/net/rtnetlink.h
@@ -165,7 +165,6 @@ struct rtnl_link_ops {
};
int __rtnl_link_register(struct rtnl_link_ops *ops);
-void __rtnl_link_unregister(struct rtnl_link_ops *ops);
int rtnl_link_register(struct rtnl_link_ops *ops);
void rtnl_link_unregister(struct rtnl_link_ops *ops);
diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c
index 3b33810d92a8..634732fe4c64 100644
--- a/net/core/rtnetlink.c
+++ b/net/core/rtnetlink.c
@@ -568,27 +568,6 @@ static void __rtnl_kill_links(struct net *net, struct rtnl_link_ops *ops)
unregister_netdevice_many(&list_kill);
}
-/**
- * __rtnl_link_unregister - Unregister rtnl_link_ops from rtnetlink.
- * @ops: struct rtnl_link_ops * to unregister
- *
- * The caller must hold the rtnl_mutex and guarantee net_namespace_list
- * integrity (hold pernet_ops_rwsem for writing to close the race
- * with setup_net() and cleanup_net()).
- */
-void __rtnl_link_unregister(struct rtnl_link_ops *ops)
-{
- struct net *net;
-
- list_del_rcu(&ops->list);
- synchronize_srcu(&ops->srcu);
- cleanup_srcu_struct(&ops->srcu);
-
- for_each_net(net)
- __rtnl_kill_links(net, ops);
-}
-EXPORT_SYMBOL_GPL(__rtnl_link_unregister);
-
/* Return with the rtnl_lock held when there are no network
* devices unregistering in any network namespace.
*/
@@ -617,10 +596,19 @@ static void rtnl_lock_unregistering_all(void)
*/
void rtnl_link_unregister(struct rtnl_link_ops *ops)
{
+ struct net *net;
+
/* Close the race with setup_net() and cleanup_net() */
down_write(&pernet_ops_rwsem);
rtnl_lock_unregistering_all();
- __rtnl_link_unregister(ops);
+
+ list_del_rcu(&ops->list);
+ synchronize_srcu(&ops->srcu);
+ cleanup_srcu_struct(&ops->srcu);
+
+ for_each_net(net)
+ __rtnl_kill_links(net, ops);
+
rtnl_unlock();
up_write(&pernet_ops_rwsem);
}
--
2.39.5 (Apple Git-154)
next prev parent reply other threads:[~2024-11-07 2:29 UTC|newest]
Thread overview: 12+ messages / expand[flat|nested] mbox.gz Atom feed top
2024-11-07 2:28 [PATCH v3 net-next 00/10] rtnetlink: Convert rtnl_newlink() to per-netns RTNL Kuniyuki Iwashima
2024-11-07 2:28 ` Kuniyuki Iwashima [this message]
2024-11-07 2:28 ` [PATCH v3 net-next 02/10] rtnetlink: Protect link_ops by mutex Kuniyuki Iwashima
2024-11-07 2:28 ` [PATCH v3 net-next 03/10] rtnetlink: Remove __rtnl_link_register() Kuniyuki Iwashima
2024-11-07 2:28 ` [PATCH v3 net-next 04/10] rtnetlink: Introduce struct rtnl_nets and helpers Kuniyuki Iwashima
2024-11-07 2:28 ` [PATCH v3 net-next 06/10] veth: Set VETH_INFO_PEER to veth_link_ops.peer_type Kuniyuki Iwashima
2024-11-07 2:28 ` [PATCH v3 net-next 07/10] vxcan: Set VXCAN_INFO_PEER to vxcan_link_ops.peer_type Kuniyuki Iwashima
2024-11-07 2:28 ` [PATCH v3 net-next 08/10] netkit: Set IFLA_NETKIT_PEER_INFO to netkit_link_ops.peer_type Kuniyuki Iwashima
2024-11-07 2:28 ` [PATCH v3 net-next 09/10] rtnetlink: Convert RTM_NEWLINK to per-netns RTNL Kuniyuki Iwashima
2024-11-07 2:29 ` [PATCH v3 net-next 10/10] rtnetlink: Register rtnl_dellink() and rtnl_setlink() with RTNL_FLAG_DOIT_PERNET_WIP Kuniyuki Iwashima
2024-11-07 23:53 ` [PATCH v3 net-next 00/10] rtnetlink: Convert rtnl_newlink() to per-netns RTNL Jakub Kicinski
2024-11-08 0:02 ` Kuniyuki Iwashima
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20241107022900.70287-2-kuniyu@amazon.com \
--to=kuniyu@amazon.com \
--cc=andrew+netdev@lunn.ch \
--cc=daniel@iogearbox.net \
--cc=davem@davemloft.net \
--cc=edumazet@google.com \
--cc=horms@kernel.org \
--cc=kuba@kernel.org \
--cc=kuni1840@gmail.com \
--cc=mailhol.vincent@wanadoo.fr \
--cc=mkl@pengutronix.de \
--cc=netdev@vger.kernel.org \
--cc=pabeni@redhat.com \
--cc=razor@blackwall.org \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).