net: ipv6: Emit notification when fib hardware flags are changed

After installing a route to the kernel, user space receives an
acknowledgment, which means the route was installed in the kernel,
but not necessarily in hardware.

The asynchronous nature of route installation in hardware can lead
to a routing daemon advertising a route before it was actually installed in
hardware. This can result in packet loss or mis-routed packets until the
route is installed in hardware.

It is also possible for a route already installed in hardware to change
its action and therefore its flags. For example, a host route that is
trapping packets can be "promoted" to perform decapsulation following
the installation of an IPinIP/VXLAN tunnel.

Emit RTM_NEWROUTE notifications whenever RTM_F_OFFLOAD/RTM_F_TRAP flags
are changed. The aim is to provide an indication to user-space
(e.g., routing daemons) about the state of the route in hardware.

Introduce a sysctl that controls this behavior.

Keep the default value at 0 (i.e., do not emit notifications) for several
reasons:
- Multiple RTM_NEWROUTE notification per-route might confuse existing
  routing daemons.
- Convergence reasons in routing daemons.
- The extra notifications will negatively impact the insertion rate.
- Not all users are interested in these notifications.

Move fib6_info_hw_flags_set() to C file because it is no longer a short
function.

Signed-off-by: Amit Cohen <amcohen@nvidia.com>
Signed-off-by: Ido Schimmel <idosch@nvidia.com>
Reviewed-by: David Ahern <dsahern@kernel.org>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>

3 files changed, 54 insertions, 0 deletions

diff --git a/net/ipv6/af_inet6.c b/net/ipv6/af_inet6.c
index 8e9c3e9ea36e..0e9994e0ecd7 100644
--- a/net/ipv6/af_inet6.c
+++ b/net/ipv6/af_inet6.c
@@ -954,6 +954,7 @@ static int __net_init inet6_net_init(struct net *net)
 	net->ipv6.sysctl.max_hbh_opts_cnt = IP6_DEFAULT_MAX_HBH_OPTS_CNT;
 	net->ipv6.sysctl.max_dst_opts_len = IP6_DEFAULT_MAX_DST_OPTS_LEN;
 	net->ipv6.sysctl.max_hbh_opts_len = IP6_DEFAULT_MAX_HBH_OPTS_LEN;
+	net->ipv6.sysctl.fib_notify_on_flag_change = 0;
 	atomic_set(&net->ipv6.fib6_sernum, 1);
 
 	err = ipv6_init_mibs(net);
diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index 41d8f801b75f..92b400eb8476 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -6064,6 +6064,50 @@ errout:
 		rtnl_set_sk_err(net, RTNLGRP_IPV6_ROUTE, err);
 }
 
+void fib6_info_hw_flags_set(struct net *net, struct fib6_info *f6i,
+			    bool offload, bool trap)
+{
+	struct sk_buff *skb;
+	int err;
+
+	if (f6i->offload == offload && f6i->trap == trap)
+		return;
+
+	f6i->offload = offload;
+	f6i->trap = trap;
+
+	if (!rcu_access_pointer(f6i->fib6_node))
+		/* The route was removed from the tree, do not send
+		 * notfication.
+		 */
+		return;
+
+	if (!net->ipv6.sysctl.fib_notify_on_flag_change)
+		return;
+
+	skb = nlmsg_new(rt6_nlmsg_size(f6i), GFP_KERNEL);
+	if (!skb) {
+		err = -ENOBUFS;
+		goto errout;
+	}
+
+	err = rt6_fill_node(net, skb, f6i, NULL, NULL, NULL, 0, RTM_NEWROUTE, 0,
+			    0, 0);
+	if (err < 0) {
+		/* -EMSGSIZE implies BUG in rt6_nlmsg_size() */
+		WARN_ON(err == -EMSGSIZE);
+		kfree_skb(skb);
+		goto errout;
+	}
+
+	rtnl_notify(skb, net, 0, RTNLGRP_IPV6_ROUTE, NULL, GFP_KERNEL);
+	return;
+
+errout:
+	rtnl_set_sk_err(net, RTNLGRP_IPV6_ROUTE, err);
+}
+EXPORT_SYMBOL(fib6_info_hw_flags_set);
+
 static int ip6_route_dev_notify(struct notifier_block *this,
 				unsigned long event, void *ptr)
 {
diff --git a/net/ipv6/sysctl_net_ipv6.c b/net/ipv6/sysctl_net_ipv6.c
index 5b60a4bdd36a..392ef01e3366 100644
--- a/net/ipv6/sysctl_net_ipv6.c
+++ b/net/ipv6/sysctl_net_ipv6.c
@@ -160,6 +160,15 @@ static struct ctl_table ipv6_table_template[] = {
 		.mode		= 0644,
 		.proc_handler	= proc_dointvec
 	},
+	{
+		.procname	= "fib_notify_on_flag_change",
+		.data		= &init_net.ipv6.sysctl.fib_notify_on_flag_change,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec_minmax,
+		.extra1         = SYSCTL_ZERO,
+		.extra2         = SYSCTL_ONE,
+	},
 	{ }
 };