mpls: Per-device enabling of packet input

An MPLS network is a single trust domain where the edges must be in
control of what labels make their way into the core. The simplest way
of ensuring this is for the edge device to always impose the labels,
and not allow forward labeled traffic from untrusted neighbours. This
is achieved by allowing a per-device configuration of whether MPLS
traffic input from that interface should be processed or not.

To be secure by default, the default state is changed to MPLS being
disabled on all interfaces unless explicitly enabled and no global
option is provided to change the default. Whilst this differs from
other protocols (e.g. IPv6), network operators are used to explicitly
enabling MPLS forwarding on interfaces, and with the number of links
to the MPLS core typically fairly low this doesn't present too much of
a burden on operators.

Cc: "Eric W. Biederman" <[e-mail]>
Signed-off-by: Robert Shearman <[e-mail]>
Reviewed-by: "Eric W. Biederman" <[e-mail]>
Signed-off-by: David S. Miller <[e-mail]>

Documentation/networking/mpls-sysctl.txt

···
 
 	Possible values: 0 - 1048575
 	Default: 0
+
+conf/<interface>/input - BOOL
+	Control whether packets can be input on this interface.
+
+	If disabled, packets will be discarded without further
+	processing.
+
+	0 - disabled (default)
+	not 0 - enabled

net/mpls/af_mpls.c

···
 	/* Careful this entire function runs inside of an rcu critical section */
 
 	mdev = mpls_dev_get(dev);
-	if (!mdev)
+	if (!mdev || !mdev->input_enabled)
 		goto drop;
 
 	if (skb->pkt_type != PACKET_HOST)
···
 	return err;
 }
 
+#define MPLS_PERDEV_SYSCTL_OFFSET(field)	\
+	(&((struct mpls_dev *)0)->field)
+
+static const struct ctl_table mpls_dev_table[] = {
+	{
+		.procname	= "input",
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec,
+		.data		= MPLS_PERDEV_SYSCTL_OFFSET(input_enabled),
+	},
+	{ }
+};
+
+static int mpls_dev_sysctl_register(struct net_device *dev,
+				    struct mpls_dev *mdev)
+{
+	char path[sizeof("net/mpls/conf/") + IFNAMSIZ];
+	struct ctl_table *table;
+	int i;
+
+	table = kmemdup(&mpls_dev_table, sizeof(mpls_dev_table), GFP_KERNEL);
+	if (!table)
+		goto out;
+
+	/* Table data contains only offsets relative to the base of
+	 * the mdev at this point, so make them absolute.
+	 */
+	for (i = 0; i < ARRAY_SIZE(mpls_dev_table); i++)
+		table[i].data = (char *)mdev + (uintptr_t)table[i].data;
+
+	snprintf(path, sizeof(path), "net/mpls/conf/%s", dev->name);
+
+	mdev->sysctl = register_net_sysctl(dev_net(dev), path, table);
+	if (!mdev->sysctl)
+		goto free;
+
+	return 0;
+
+free:
+	kfree(table);
+out:
+	return -ENOBUFS;
+}
+
+static void mpls_dev_sysctl_unregister(struct mpls_dev *mdev)
+{
+	struct ctl_table *table;
+
+	table = mdev->sysctl->ctl_table_arg;
+	unregister_net_sysctl_table(mdev->sysctl);
+	kfree(table);
+}
+
 static struct mpls_dev *mpls_add_dev(struct net_device *dev)
 {
 	struct mpls_dev *mdev;
···
 	if (!mdev)
 		return ERR_PTR(err);
 
+	err = mpls_dev_sysctl_register(dev, mdev);
+	if (err)
+		goto free;
+
 	rcu_assign_pointer(dev->mpls_ptr, mdev);
 
 	return mdev;
+
+free:
+	kfree(mdev);
+	return ERR_PTR(err);
 }
 
 static void mpls_ifdown(struct net_device *dev)
···
 	mdev = mpls_dev_get(dev);
 	if (!mdev)
 		return;
+
+	mpls_dev_sysctl_unregister(mdev);
 
 	RCU_INIT_POINTER(dev->mpls_ptr, NULL);
 
···
 	return ret;
 }
 
-static struct ctl_table mpls_table[] = {
+static const struct ctl_table mpls_table[] = {
 	{
 		.procname	= "platform_labels",
 		.data		= NULL,

net/mpls/internal.h

···
 };
 
 struct mpls_dev {
+	int			input_enabled;
+
+	struct ctl_table_header *sysctl;
 };
 
 struct sk_buff;