[PATCH v3 net-next 0/3] rtnetlink: RTNL avoidance in rtnl_getlink()

[PATCH v3 net-next 0/3] rtnetlink: RTNL avoidance in rtnl_getlink()

[Eric Dumazet]

Many shell scripts invoke iproute2 commands specifying a device by
its name.

This series improves their performance avoiding RTNL acquisition
for their (repeated) name->index conversion.

v3: insert patch 2/3 in the series (Jakub reported a KASAN splat)

Eric Dumazet (3):
  rtnetlink: use nla_nest_end_safe() in rtnl_fill_prop_list()
  net: defer netdev_name_node_alt_flush() call to netdev_run_todo()
  rtnetlink: do not acquire RTNL for RTM_GETLINK with
    RTEXT_FILTER_NAME_ONLY

 net/core/dev.c       |  4 +--
 net/core/rtnetlink.c | 86 ++++++++++++++++++++++++++++++--------------
 2 files changed, 61 insertions(+), 29 deletions(-)

-- 
2.54.0.631.ge1b05301d1-goog

[PATCH v3 net-next 1/3] rtnetlink: use nla_nest_end_safe() in rtnl_fill_prop_list()

[Eric Dumazet]

Avoid corrupting a netlink message and confuse user space in the
very unlikely case rtnl_fill_prop_list was able to produce a very big
nested element.

This is extremely unlikely, because rtnl_prop_list_size()
provisions nla_total_size(ALTIFNAMSIZ) per altname.

Signed-off-by: Eric Dumazet <edumazet@google.com>
---
 net/core/rtnetlink.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c
index 6a5e9ace55a0880d7b1e4303d12dc0a8b8b7c5ed..ae0254f19178735b2805a8189e81a960a49b2858 100644
--- a/net/core/rtnetlink.c
+++ b/net/core/rtnetlink.c
@@ -1971,7 +1971,9 @@ static int rtnl_fill_prop_list(struct sk_buff *skb,
 	if (ret <= 0)
 		goto nest_cancel;
 
-	nla_nest_end(skb, prop_list);
+	if (nla_nest_end_safe(skb, prop_list) < 0)
+		goto nest_cancel;
+
 	return 0;
 
 nest_cancel:
-- 
2.54.0.631.ge1b05301d1-goog

[PATCH v3 net-next 2/3] net: defer netdev_name_node_alt_flush() call to netdev_run_todo()

[Eric Dumazet]

In the following patch, we want to call rtnl_fill_prop_list() without
RTNL being held, but after a device reference was taken.

We need to free altnames in netdev_run_todo() instead of
unregister_netdevice_many_notify().

Freeing will only happen once all device references
have been released.

Note that dev->name_node serves as the anchor for altnames,
thus must be also freed in netdev_run_todo().

Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: Jakub Kicinski <kuba@kernel.org>
---
 net/core/dev.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/net/core/dev.c b/net/core/dev.c
index 26ac8eb9b259d489159c7ab5a2b206d425110b3b..2d795f3f569be00361809823fd3e59fb1871919c 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -11738,6 +11738,8 @@ void netdev_run_todo(void)
 		WARN_ON(rcu_access_pointer(dev->ip_ptr));
 		WARN_ON(rcu_access_pointer(dev->ip6_ptr));
 
+		netdev_name_node_alt_flush(dev);
+		netdev_name_node_free(dev->name_node);
 		netdev_do_free_pcpu_stats(dev);
 		if (dev->priv_destructor)
 			dev->priv_destructor(dev);
@@ -12451,8 +12453,6 @@ void unregister_netdevice_many_notify(struct list_head *head,
 		dev_uc_flush(dev);
 		dev_mc_flush(dev);
 
-		netdev_name_node_alt_flush(dev);
-		netdev_name_node_free(dev->name_node);
 
 		netdev_rss_contexts_free(dev);
 
-- 
2.54.0.631.ge1b05301d1-goog

[PATCH v3 net-next 3/3] rtnetlink: do not acquire RTNL for RTM_GETLINK with RTEXT_FILTER_NAME_ONLY

[Eric Dumazet]

When RTEXT_FILTER_NAME_ONLY is requested, rtnl_fill_ifinfo()
is dumping device attributes which do not need RTNL protection.

Many shell scripts invoke iproute2 commands specifying a device by
its name. After this patch, they will no longer add RTNL pressure.

Signed-off-by: Eric Dumazet <edumazet@google.com>
---
 net/core/rtnetlink.c | 82 ++++++++++++++++++++++++++++++--------------
 1 file changed, 56 insertions(+), 26 deletions(-)

diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c
index ae0254f19178735b2805a8189e81a960a49b2858..587bb8bbc73d0b2075ca508a5537200f65f74594 100644
--- a/net/core/rtnetlink.c
+++ b/net/core/rtnetlink.c
@@ -2068,7 +2068,6 @@ static int rtnl_fill_ifinfo(struct sk_buff *skb,
 	struct nlmsghdr *nlh;
 	struct Qdisc *qdisc;
 
-	ASSERT_RTNL();
 	nlh = nlmsg_put(skb, pid, seq, type, sizeof(*ifm), flags);
 	if (nlh == NULL)
 		return -EMSGSIZE;
@@ -2091,6 +2090,7 @@ static int rtnl_fill_ifinfo(struct sk_buff *skb,
 	if (ext_filter_mask & RTEXT_FILTER_NAME_ONLY)
 		goto end;
 
+	ASSERT_RTNL();
 	if (tgt_netnsid >= 0 &&
 	    nla_put_s32(skb, IFLA_TARGET_NETNSID, tgt_netnsid))
 		goto nla_put_failure;
@@ -3468,6 +3468,21 @@ static struct net_device *rtnl_dev_get(struct net *net,
 	return __dev_get_by_name(net, ifname);
 }
 
+static struct net_device *rtnl_dev_get_rcu(struct net *net,
+					   struct nlattr *tb[])
+{
+	char ifname[ALTIFNAMSIZ];
+
+	if (tb[IFLA_IFNAME])
+		nla_strscpy(ifname, tb[IFLA_IFNAME], IFNAMSIZ);
+	else if (tb[IFLA_ALT_IFNAME])
+		nla_strscpy(ifname, tb[IFLA_ALT_IFNAME], ALTIFNAMSIZ);
+	else
+		return NULL;
+
+	return dev_get_by_name_rcu(net, ifname);
+}
+
 static int rtnl_setlink(struct sk_buff *skb, struct nlmsghdr *nlh,
 			struct netlink_ext_ack *extack)
 {
@@ -4187,14 +4202,15 @@ static int rtnl_getlink(struct sk_buff *skb, struct nlmsghdr *nlh,
 			struct netlink_ext_ack *extack)
 {
 	struct net *net = sock_net(skb->sk);
+	struct nlattr *tb[IFLA_MAX + 1];
+	netdevice_tracker dev_tracker;
+	struct net_device *dev = NULL;
 	struct net *tgt_net = net;
+	u32 ext_filter_mask = 0;
 	struct ifinfomsg *ifm;
-	struct nlattr *tb[IFLA_MAX+1];
-	struct net_device *dev = NULL;
 	struct sk_buff *nskb;
 	int netnsid = -1;
 	int err;
-	u32 ext_filter_mask = 0;
 
 	err = rtnl_valid_getlink_req(skb, nlh, tb, extack);
 	if (err < 0)
@@ -4214,43 +4230,56 @@ static int rtnl_getlink(struct sk_buff *skb, struct nlmsghdr *nlh,
 	if (tb[IFLA_EXT_MASK])
 		ext_filter_mask = nla_get_u32(tb[IFLA_EXT_MASK]);
 
-	err = -EINVAL;
 	ifm = nlmsg_data(nlh);
-	if (ifm->ifi_index > 0)
-		dev = __dev_get_by_index(tgt_net, ifm->ifi_index);
-	else if (tb[IFLA_IFNAME] || tb[IFLA_ALT_IFNAME])
-		dev = rtnl_dev_get(tgt_net, tb);
-	else
+	rcu_read_lock();
+	if (ifm->ifi_index > 0) {
+		dev = dev_get_by_index_rcu(tgt_net, ifm->ifi_index);
+	} else if (tb[IFLA_IFNAME] || tb[IFLA_ALT_IFNAME]) {
+		dev = rtnl_dev_get_rcu(tgt_net, tb);
+	} else {
+		rcu_read_unlock();
+		err = -EINVAL;
 		goto out;
+	}
+	netdev_hold(dev, &dev_tracker, GFP_ATOMIC);
+	rcu_read_unlock();
 
 	err = -ENODEV;
 	if (dev == NULL)
 		goto out;
 
+	if (!(ext_filter_mask & RTEXT_FILTER_NAME_ONLY)) {
+		rtnl_lock();
+		/* Synchronize the carrier state so we don't report a state
+		 * that we're not actually going to honour immediately; if
+		 * the driver just did a carrier off->on transition, we can
+		 * only TX if link watch work has run, but without this we'd
+		 * already report carrier on, even if it doesn't work yet.
+		 */
+		linkwatch_sync_dev(dev);
+	}
+
 	err = -ENOBUFS;
 	nskb = nlmsg_new_large(if_nlmsg_size(dev, ext_filter_mask));
-	if (nskb == NULL)
-		goto out;
+	if (nskb)
+		err = rtnl_fill_ifinfo(nskb, dev, net,
+				       RTM_NEWLINK, NETLINK_CB(skb).portid,
+				       nlh->nlmsg_seq, 0, 0, ext_filter_mask,
+				       0, NULL, 0, netnsid, GFP_KERNEL);
 
-	/* Synchronize the carrier state so we don't report a state
-	 * that we're not actually going to honour immediately; if
-	 * the driver just did a carrier off->on transition, we can
-	 * only TX if link watch work has run, but without this we'd
-	 * already report carrier on, even if it doesn't work yet.
-	 */
-	linkwatch_sync_dev(dev);
+	if (!(ext_filter_mask & RTEXT_FILTER_NAME_ONLY))
+		rtnl_unlock();
 
-	err = rtnl_fill_ifinfo(nskb, dev, net,
-			       RTM_NEWLINK, NETLINK_CB(skb).portid,
-			       nlh->nlmsg_seq, 0, 0, ext_filter_mask,
-			       0, NULL, 0, netnsid, GFP_KERNEL);
 	if (err < 0) {
 		/* -EMSGSIZE implies BUG in if_nlmsg_size */
-		WARN_ON(err == -EMSGSIZE);
+		WARN_ON_ONCE(err == -EMSGSIZE &&
+			     !(ext_filter_mask & RTEXT_FILTER_NAME_ONLY));
 		kfree_skb(nskb);
-	} else
+	} else {
 		err = rtnl_unicast(nskb, net, NETLINK_CB(skb).portid);
+	}
 out:
+	netdev_put(dev, &dev_tracker);
 	if (netnsid >= 0)
 		put_net(tgt_net);
 
@@ -7116,7 +7145,8 @@ static const struct rtnl_msg_handler rtnetlink_rtnl_msg_handlers[] __initconst =
 	{.msgtype = RTM_DELLINK, .doit = rtnl_dellink,
 	 .flags = RTNL_FLAG_DOIT_PERNET_WIP},
 	{.msgtype = RTM_GETLINK, .doit = rtnl_getlink,
-	 .dumpit = rtnl_dump_ifinfo, .flags = RTNL_FLAG_DUMP_SPLIT_NLM_DONE},
+	 .dumpit = rtnl_dump_ifinfo,
+	 .flags = RTNL_FLAG_DUMP_SPLIT_NLM_DONE | RTNL_FLAG_DOIT_UNLOCKED},
 	{.msgtype = RTM_SETLINK, .doit = rtnl_setlink,
 	 .flags = RTNL_FLAG_DOIT_PERNET_WIP},
 	{.msgtype = RTM_GETADDR, .dumpit = rtnl_dump_all},
-- 
2.54.0.631.ge1b05301d1-goog