Merge branch 'rtnetlink-per-netns-rtnl'

Kuniyuki Iwashima says:

====================
rtnetlink: Per-netns RTNL.

rtnl_lock() is a "Big Kernel Lock" in the networking slow path and
serialised all rtnetlink requests until 4.13.

Since RTNL_FLAG_DOIT_UNLOCKED and RTNL_FLAG_DUMP_UNLOCKED have been
introduced in 4.14 and 6.9, respectively, rtnetlink message handlers
are ready to be converted to RTNL-less/free.

15 out of 44 dumpit()s have been converted to RCU so far, and the
progress is pretty good.  We can now dump various major network
resources without RTNL.

12 out of 87 doit()s have been converted, but most of the converted
doit()s are also on the reader side of RTNL; their message types are
RTM_GET*.

So, most of RTM_(NEW|DEL|SET)* operations are still serialised by RTNL.

For example, one of our services creates 2K netns and a small number
of network interfaces in each netns that require too many writer-side
rtnetlink requests, and setting up a single host takes 10+ minutes.

RTNL is still a huge pain for network configuration paths, and we need
more granular locking, given converting all doit()s would be unfeasible.

Actually, most RTNL users do not need to freeze multiple netns, and such
users can be protected by per-netns RTNL mutex.  The exceptions would be
RTM_NEWLINK, RTM_DELLINK, and RTM_SETLINK.  (See [0] and [1])

This series is the first step of the per-netns RTNL conversion that
gradually replaces rtnl_lock() with rtnl_net_lock(net) under
CONFIG_DEBUG_NET_SMALL_RTNL.

[0]: https://netdev.bots.linux.dev/netconf/2024/index.html
[1]: https://lpc.events/event/18/contributions/1959/
====================

Link: https://patch.msgid.link/20241004221031.77743-1-kuniyu@amazon.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>

1 files changed, 131 insertions, 0 deletions

diff --git a/net/core/rtnl_net_debug.c b/net/core/rtnl_net_debug.c
new file mode 100644
index 000000000000..e90a32242e22
--- /dev/null
+++ b/net/core/rtnl_net_debug.c
@@ -0,0 +1,131 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/* Copyright Amazon.com Inc. or its affiliates. */
+
+#include <linux/init.h>
+#include <linux/netdevice.h>
+#include <linux/notifier.h>
+#include <linux/rtnetlink.h>
+#include <net/net_namespace.h>
+#include <net/netns/generic.h>
+
+static int rtnl_net_debug_event(struct notifier_block *nb,
+				unsigned long event, void *ptr)
+{
+	struct net_device *dev = netdev_notifier_info_to_dev(ptr);
+	struct net *net = dev_net(dev);
+	enum netdev_cmd cmd = event;
+
+	/* Keep enum and don't add default to trigger -Werror=switch */
+	switch (cmd) {
+	case NETDEV_UP:
+	case NETDEV_DOWN:
+	case NETDEV_REBOOT:
+	case NETDEV_CHANGE:
+	case NETDEV_REGISTER:
+	case NETDEV_UNREGISTER:
+	case NETDEV_CHANGEMTU:
+	case NETDEV_CHANGEADDR:
+	case NETDEV_PRE_CHANGEADDR:
+	case NETDEV_GOING_DOWN:
+	case NETDEV_CHANGENAME:
+	case NETDEV_FEAT_CHANGE:
+	case NETDEV_BONDING_FAILOVER:
+	case NETDEV_PRE_UP:
+	case NETDEV_PRE_TYPE_CHANGE:
+	case NETDEV_POST_TYPE_CHANGE:
+	case NETDEV_POST_INIT:
+	case NETDEV_PRE_UNINIT:
+	case NETDEV_RELEASE:
+	case NETDEV_NOTIFY_PEERS:
+	case NETDEV_JOIN:
+	case NETDEV_CHANGEUPPER:
+	case NETDEV_RESEND_IGMP:
+	case NETDEV_PRECHANGEMTU:
+	case NETDEV_CHANGEINFODATA:
+	case NETDEV_BONDING_INFO:
+	case NETDEV_PRECHANGEUPPER:
+	case NETDEV_CHANGELOWERSTATE:
+	case NETDEV_UDP_TUNNEL_PUSH_INFO:
+	case NETDEV_UDP_TUNNEL_DROP_INFO:
+	case NETDEV_CHANGE_TX_QUEUE_LEN:
+	case NETDEV_CVLAN_FILTER_PUSH_INFO:
+	case NETDEV_CVLAN_FILTER_DROP_INFO:
+	case NETDEV_SVLAN_FILTER_PUSH_INFO:
+	case NETDEV_SVLAN_FILTER_DROP_INFO:
+	case NETDEV_OFFLOAD_XSTATS_ENABLE:
+	case NETDEV_OFFLOAD_XSTATS_DISABLE:
+	case NETDEV_OFFLOAD_XSTATS_REPORT_USED:
+	case NETDEV_OFFLOAD_XSTATS_REPORT_DELTA:
+	case NETDEV_XDP_FEAT_CHANGE:
+		ASSERT_RTNL();
+		break;
+
+	/* Once an event fully supports RTNL_NET, move it here
+	 * and remove "if (0)" below.
+	 *
+	 * case NETDEV_XXX:
+	 *	ASSERT_RTNL_NET(net);
+	 *	break;
+	 */
+	}
+
+	/* Just to avoid unused-variable error for dev and net. */
+	if (0)
+		ASSERT_RTNL_NET(net);
+
+	return NOTIFY_DONE;
+}
+
+static int rtnl_net_debug_net_id;
+
+static int __net_init rtnl_net_debug_net_init(struct net *net)
+{
+	struct notifier_block *nb;
+
+	nb = net_generic(net, rtnl_net_debug_net_id);
+	nb->notifier_call = rtnl_net_debug_event;
+
+	return register_netdevice_notifier_net(net, nb);
+}
+
+static void __net_exit rtnl_net_debug_net_exit(struct net *net)
+{
+	struct notifier_block *nb;
+
+	nb = net_generic(net, rtnl_net_debug_net_id);
+	unregister_netdevice_notifier_net(net, nb);
+}
+
+static struct pernet_operations rtnl_net_debug_net_ops __net_initdata = {
+	.init = rtnl_net_debug_net_init,
+	.exit = rtnl_net_debug_net_exit,
+	.id = &rtnl_net_debug_net_id,
+	.size = sizeof(struct notifier_block),
+};
+
+static struct notifier_block rtnl_net_debug_block = {
+	.notifier_call = rtnl_net_debug_event,
+};
+
+static int __init rtnl_net_debug_init(void)
+{
+	int ret;
+
+	ret = register_pernet_device(&rtnl_net_debug_net_ops);
+	if (ret)
+		return ret;
+
+	ret = register_netdevice_notifier(&rtnl_net_debug_block);
+	if (ret)
+		unregister_pernet_subsys(&rtnl_net_debug_net_ops);
+
+	return ret;
+}
+
+static void __exit rtnl_net_debug_exit(void)
+{
+	unregister_netdevice_notifier(&rtnl_net_debug_block);
+	unregister_pernet_device(&rtnl_net_debug_net_ops);
+}
+
+subsys_initcall(rtnl_net_debug_init);