From d5ec8d91f82ef78405b506737952dec8af95a95b Mon Sep 17 00:00:00 2001 From: Kuniyuki Iwashima Date: Thu, 7 Nov 2024 16:48:14 -0800 Subject: rtnetlink: Remove __rtnl_link_unregister(). 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 Link: https://patch.msgid.link/20241108004823.29419-2-kuniyu@amazon.com Signed-off-by: Jakub Kicinski --- include/net/rtnetlink.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include') 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); -- cgit v1.2.3 From 6b57ff21a3109b1dba2d286ff415463e6fb1fca3 Mon Sep 17 00:00:00 2001 From: Kuniyuki Iwashima Date: Thu, 7 Nov 2024 16:48:15 -0800 Subject: rtnetlink: Protect link_ops by mutex. rtnl_link_unregister() holds RTNL and calls synchronize_srcu(), but rtnl_newlink() will acquire SRCU frist and then RTNL. Then, we need to unlink ops and call synchronize_srcu() outside of RTNL to avoid the deadlock. rtnl_link_unregister() rtnl_newlink() ---- ---- lock(rtnl_mutex); lock(&ops->srcu); lock(rtnl_mutex); sync(&ops->srcu); Let's move as such and add a mutex to protect link_ops. Now, link_ops is protected by its dedicated mutex and rtnl_link_register() no longer needs to hold RTNL. While at it, we move the initialisation of ops->dellink and ops->srcu out of the mutex scope. Signed-off-by: Kuniyuki Iwashima Link: https://patch.msgid.link/20241108004823.29419-3-kuniyu@amazon.com Signed-off-by: Jakub Kicinski --- include/net/rtnetlink.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/net/rtnetlink.h b/include/net/rtnetlink.h index 3ebfcc6e56fd..7559020f760c 100644 --- a/include/net/rtnetlink.h +++ b/include/net/rtnetlink.h @@ -71,7 +71,7 @@ static inline int rtnl_msg_family(const struct nlmsghdr *nlh) /** * struct rtnl_link_ops - rtnetlink link operations * - * @list: Used internally, protected by RTNL and SRCU + * @list: Used internally, protected by link_ops_mutex and SRCU * @srcu: Used internally * @kind: Identifier * @netns_refund: Physical device, move to init_net on netns exit -- cgit v1.2.3 From 68297dbb967f87c3c92af9d2f652270f57c547c7 Mon Sep 17 00:00:00 2001 From: Kuniyuki Iwashima Date: Thu, 7 Nov 2024 16:48:16 -0800 Subject: rtnetlink: Remove __rtnl_link_register() link_ops is protected by link_ops_mutex and no longer needs RTNL, so we have no reason to have __rtnl_link_register() separately. Let's remove it and call rtnl_link_register() from ifb.ko and dummy.ko. Note that both modules' init() work on init_net only, so we need not export pernet_ops_rwsem and can use rtnl_net_lock() there. Signed-off-by: Kuniyuki Iwashima Link: https://patch.msgid.link/20241108004823.29419-4-kuniyu@amazon.com Signed-off-by: Jakub Kicinski --- include/net/rtnetlink.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include') diff --git a/include/net/rtnetlink.h b/include/net/rtnetlink.h index 7559020f760c..ef7c11f0d74c 100644 --- a/include/net/rtnetlink.h +++ b/include/net/rtnetlink.h @@ -164,8 +164,6 @@ struct rtnl_link_ops { int *prividx, int attr); }; -int __rtnl_link_register(struct rtnl_link_ops *ops); - int rtnl_link_register(struct rtnl_link_ops *ops); void rtnl_link_unregister(struct rtnl_link_ops *ops); -- cgit v1.2.3 From 28690e5361c05fd4ef0ca3a17d1c667cba790554 Mon Sep 17 00:00:00 2001 From: Kuniyuki Iwashima Date: Thu, 7 Nov 2024 16:48:18 -0800 Subject: rtnetlink: Add peer_type in struct rtnl_link_ops. In ops->newlink(), veth, vxcan, and netkit call rtnl_link_get_net() with a net pointer, which is the first argument of ->newlink(). rtnl_link_get_net() could return another netns based on IFLA_NET_NS_PID and IFLA_NET_NS_FD in the peer device's attributes. We want to get it and fill rtnl_nets->nets[] in advance in rtnl_newlink() for per-netns RTNL. All of the three get the peer netns in the same way: 1. Call rtnl_nla_parse_ifinfomsg() 2. Call ops->validate() (vxcan doesn't have) 3. Call rtnl_link_get_net_tb() Let's add a new field peer_type to struct rtnl_link_ops and prefetch netns in the peer ifla to add it to rtnl_nets in rtnl_newlink(). Signed-off-by: Kuniyuki Iwashima Reviewed-by: Eric Dumazet Reviewed-by: Nikolay Aleksandrov Link: https://patch.msgid.link/20241108004823.29419-6-kuniyu@amazon.com Signed-off-by: Jakub Kicinski --- include/net/rtnetlink.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/net/rtnetlink.h b/include/net/rtnetlink.h index ef7c11f0d74c..bef76abcff8d 100644 --- a/include/net/rtnetlink.h +++ b/include/net/rtnetlink.h @@ -75,6 +75,7 @@ static inline int rtnl_msg_family(const struct nlmsghdr *nlh) * @srcu: Used internally * @kind: Identifier * @netns_refund: Physical device, move to init_net on netns exit + * @peer_type: Peer device specific netlink attribute number (e.g. VETH_INFO_PEER) * @maxtype: Highest device specific netlink attribute number * @policy: Netlink policy for device specific attribute validation * @validate: Optional validation function for netlink/changelink parameters @@ -116,6 +117,7 @@ struct rtnl_link_ops { void (*setup)(struct net_device *dev); bool netns_refund; + const u16 peer_type; unsigned int maxtype; const struct nla_policy *policy; int (*validate)(struct nlattr *tb[], -- cgit v1.2.3 From 636af13f213bf9b28a34254327934bc72a797754 Mon Sep 17 00:00:00 2001 From: Kuniyuki Iwashima Date: Thu, 7 Nov 2024 16:48:23 -0800 Subject: rtnetlink: Register rtnl_dellink() and rtnl_setlink() with RTNL_FLAG_DOIT_PERNET_WIP. Currently, rtnl_setlink() and rtnl_dellink() cannot be fully converted to per-netns RTNL due to a lack of handling peer/lower/upper devices in different netns. For example, when we change a device in rtnl_setlink() and need to propagate that to its upper devices, we want to avoid acquiring all netns locks, for which we do not know the upper limit. The same situation happens when we remove a device. rtnl_dellink() could be transformed to remove a single device in the requested netns and delegate other devices to per-netns work, and rtnl_setlink() might be ? Until we come up with a better idea, let's use a new flag RTNL_FLAG_DOIT_PERNET_WIP for rtnl_dellink() and rtnl_setlink(). This will unblock converting RTNL users where such devices are not related. Signed-off-by: Kuniyuki Iwashima Reviewed-by: Nikolay Aleksandrov Reviewed-by: Eric Dumazet Link: https://patch.msgid.link/20241108004823.29419-11-kuniyu@amazon.com Signed-off-by: Jakub Kicinski --- include/net/rtnetlink.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/net/rtnetlink.h b/include/net/rtnetlink.h index bef76abcff8d..bc0069a8b6ea 100644 --- a/include/net/rtnetlink.h +++ b/include/net/rtnetlink.h @@ -13,6 +13,7 @@ typedef int (*rtnl_dumpit_func)(struct sk_buff *, struct netlink_callback *); enum rtnl_link_flags { RTNL_FLAG_DOIT_UNLOCKED = BIT(0), #define RTNL_FLAG_DOIT_PERNET RTNL_FLAG_DOIT_UNLOCKED +#define RTNL_FLAG_DOIT_PERNET_WIP RTNL_FLAG_DOIT_UNLOCKED RTNL_FLAG_BULK_DEL_SUPPORTED = BIT(1), RTNL_FLAG_DUMP_UNLOCKED = BIT(2), RTNL_FLAG_DUMP_SPLIT_NLM_DONE = BIT(3), /* legacy behavior */ -- cgit v1.2.3