[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <20250410022004.8668-2-kuniyu@amazon.com>
Date: Wed, 9 Apr 2025 19:19:22 -0700
From: Kuniyuki Iwashima <kuniyu@...zon.com>
To: "David S. Miller" <davem@...emloft.net>, Eric Dumazet
<edumazet@...gle.com>, Jakub Kicinski <kuba@...nel.org>, Paolo Abeni
<pabeni@...hat.com>
CC: Simon Horman <horms@...nel.org>, Kuniyuki Iwashima <kuniyu@...zon.com>,
Kuniyuki Iwashima <kuni1840@...il.com>, <netdev@...r.kernel.org>
Subject: [PATCH v1 net-next 01/14] net: Factorise setup_net() and cleanup_net().
When we roll back the changes made by struct pernet_operations.init(),
we execute mostly identical sequences in three places.
* setup_net()
* cleanup_net()
* free_exit_list()
The only difference between the first two is which list and RCU helpers
to use.
In setup_net(), an ops could fail on the way, so we need to perform a
reverse walk from its previous ops in pernet_list. OTOH, in cleanup_net(),
we iterate the full list from tail to head.
The former passes the failed ops to list_for_each_entry_continue_reverse().
It's tricky, but we can reuse it for the latter if we pass list_entry() of
the head node.
Also, synchronize_rcu() and synchronize_rcu_expedited() can be easily
switched by an argument.
Let's factorise the rollback part in setup_net() and cleanup_net().
In the next patch, ops_undo_list() will be reused for free_exit_list(),
and then two arguments (ops_list and hold_rtnl) will differ.
Signed-off-by: Kuniyuki Iwashima <kuniyu@...zon.com>
---
net/core/net_namespace.c | 106 +++++++++++++++++++--------------------
1 file changed, 51 insertions(+), 55 deletions(-)
diff --git a/net/core/net_namespace.c b/net/core/net_namespace.c
index b0dfdf791ece..2612339efd71 100644
--- a/net/core/net_namespace.c
+++ b/net/core/net_namespace.c
@@ -188,6 +188,53 @@ static void ops_free_list(const struct pernet_operations *ops,
}
}
+static void ops_undo_list(const struct list_head *ops_list,
+ const struct pernet_operations *ops,
+ struct list_head *net_exit_list,
+ bool expedite_rcu, bool hold_rtnl)
+{
+ const struct pernet_operations *saved_ops;
+
+ if (!ops)
+ ops = list_entry(ops_list, typeof(*ops), list);
+
+ saved_ops = ops;
+
+ list_for_each_entry_continue_reverse(ops, ops_list, list)
+ ops_pre_exit_list(ops, net_exit_list);
+
+ /* Another CPU might be rcu-iterating the list, wait for it.
+ * This needs to be before calling the exit() notifiers, so the
+ * rcu_barrier() after ops_undo_list() isn't sufficient alone.
+ * Also the pre_exit() and exit() methods need this barrier.
+ */
+ if (expedite_rcu)
+ synchronize_rcu_expedited();
+ else
+ synchronize_rcu();
+
+ if (hold_rtnl) {
+ LIST_HEAD(dev_kill_list);
+
+ ops = saved_ops;
+ rtnl_lock();
+ list_for_each_entry_continue_reverse(ops, ops_list, list) {
+ if (ops->exit_batch_rtnl)
+ ops->exit_batch_rtnl(net_exit_list, &dev_kill_list);
+ }
+ unregister_netdevice_many(&dev_kill_list);
+ rtnl_unlock();
+ }
+
+ ops = saved_ops;
+ list_for_each_entry_continue_reverse(ops, ops_list, list)
+ ops_exit_list(ops, net_exit_list);
+
+ ops = saved_ops;
+ list_for_each_entry_continue_reverse(ops, ops_list, list)
+ ops_free_list(ops, net_exit_list);
+}
+
/* should be called with nsid_lock held */
static int alloc_netid(struct net *net, struct net *peer, int reqid)
{
@@ -351,9 +398,8 @@ static __net_init void preinit_net(struct net *net, struct user_namespace *user_
static __net_init int setup_net(struct net *net)
{
/* Must be called with pernet_ops_rwsem held */
- const struct pernet_operations *ops, *saved_ops;
+ const struct pernet_operations *ops;
LIST_HEAD(net_exit_list);
- LIST_HEAD(dev_kill_list);
int error = 0;
preempt_disable();
@@ -376,29 +422,7 @@ static __net_init int setup_net(struct net *net)
* for the pernet modules whose init functions did not fail.
*/
list_add(&net->exit_list, &net_exit_list);
- saved_ops = ops;
- list_for_each_entry_continue_reverse(ops, &pernet_list, list)
- ops_pre_exit_list(ops, &net_exit_list);
-
- synchronize_rcu();
-
- ops = saved_ops;
- rtnl_lock();
- list_for_each_entry_continue_reverse(ops, &pernet_list, list) {
- if (ops->exit_batch_rtnl)
- ops->exit_batch_rtnl(&net_exit_list, &dev_kill_list);
- }
- unregister_netdevice_many(&dev_kill_list);
- rtnl_unlock();
-
- ops = saved_ops;
- list_for_each_entry_continue_reverse(ops, &pernet_list, list)
- ops_exit_list(ops, &net_exit_list);
-
- ops = saved_ops;
- list_for_each_entry_continue_reverse(ops, &pernet_list, list)
- ops_free_list(ops, &net_exit_list);
-
+ ops_undo_list(&pernet_list, ops, &net_exit_list, false, true);
rcu_barrier();
goto out;
}
@@ -594,11 +618,9 @@ struct task_struct *cleanup_net_task;
static void cleanup_net(struct work_struct *work)
{
- const struct pernet_operations *ops;
- struct net *net, *tmp, *last;
struct llist_node *net_kill_list;
+ struct net *net, *tmp, *last;
LIST_HEAD(net_exit_list);
- LIST_HEAD(dev_kill_list);
cleanup_net_task = current;
@@ -629,33 +651,7 @@ static void cleanup_net(struct work_struct *work)
list_add_tail(&net->exit_list, &net_exit_list);
}
- /* Run all of the network namespace pre_exit methods */
- list_for_each_entry_reverse(ops, &pernet_list, list)
- ops_pre_exit_list(ops, &net_exit_list);
-
- /*
- * Another CPU might be rcu-iterating the list, wait for it.
- * This needs to be before calling the exit() notifiers, so
- * the rcu_barrier() below isn't sufficient alone.
- * Also the pre_exit() and exit() methods need this barrier.
- */
- synchronize_rcu_expedited();
-
- rtnl_lock();
- list_for_each_entry_reverse(ops, &pernet_list, list) {
- if (ops->exit_batch_rtnl)
- ops->exit_batch_rtnl(&net_exit_list, &dev_kill_list);
- }
- unregister_netdevice_many(&dev_kill_list);
- rtnl_unlock();
-
- /* Run all of the network namespace exit methods */
- list_for_each_entry_reverse(ops, &pernet_list, list)
- ops_exit_list(ops, &net_exit_list);
-
- /* Free the net generic variables */
- list_for_each_entry_reverse(ops, &pernet_list, list)
- ops_free_list(ops, &net_exit_list);
+ ops_undo_list(&pernet_list, NULL, &net_exit_list, true, true);
up_read(&pernet_ops_rwsem);
--
2.49.0
Powered by blists - more mailing lists