diff mbox

[2/3] mpls: Per-device enabling of packet input

Message ID 1429648467-8449-3-git-send-email-rshearma@brocade.com
State Superseded, archived
Delegated to: David Miller
Headers show

Commit Message

Robert Shearman April 21, 2015, 8:34 p.m. UTC
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 (except the loopback) 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" <ebiederm@xmission.com>
Signed-off-by: Robert Shearman <rshearma@brocade.com>
---
 Documentation/networking/mpls-sysctl.txt |  9 ++++
 net/mpls/af_mpls.c                       | 75 +++++++++++++++++++++++++++++++-
 net/mpls/internal.h                      |  3 ++
 3 files changed, 85 insertions(+), 2 deletions(-)
diff mbox

Patch

diff --git a/Documentation/networking/mpls-sysctl.txt b/Documentation/networking/mpls-sysctl.txt
index 639ddf0ece9b..9ed15f86c17c 100644
--- a/Documentation/networking/mpls-sysctl.txt
+++ b/Documentation/networking/mpls-sysctl.txt
@@ -18,3 +18,12 @@  platform_labels - INTEGER
 
 	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
diff --git a/net/mpls/af_mpls.c b/net/mpls/af_mpls.c
index ad45017eed99..7ac93082e3dc 100644
--- a/net/mpls/af_mpls.c
+++ b/net/mpls/af_mpls.c
@@ -150,7 +150,7 @@  static int mpls_forward(struct sk_buff *skb, struct net_device *dev,
 	/* 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)
@@ -438,6 +438,60 @@  errout:
 	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;
@@ -449,9 +503,24 @@  static struct mpls_dev *mpls_add_dev(struct net_device *dev)
 	if (!mdev)
 		return ERR_PTR(err);
 
+	/* Enable MPLS by default on loopback devices, since this
+	 * doesn't represent a security boundary and is required for the
+	 * lookup of inner labels for LSPs terminating on this router.
+	 */
+	if (dev->flags & IFF_LOOPBACK)
+		mdev->input_enabled = 1;
+
+	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)
@@ -475,6 +544,8 @@  static void mpls_ifdown(struct net_device *dev)
 	if (!mdev)
 		return;
 
+	mpls_dev_sysctl_unregister(mdev);
+
 	RCU_INIT_POINTER(dev->mpls_ptr, NULL);
 
 	kfree(mdev);
@@ -958,7 +1029,7 @@  static int mpls_platform_labels(struct ctl_table *table, int write,
 	return ret;
 }
 
-static struct ctl_table mpls_table[] = {
+static const struct ctl_table mpls_table[] = {
 	{
 		.procname	= "platform_labels",
 		.data		= NULL,
diff --git a/net/mpls/internal.h b/net/mpls/internal.h
index 8090cb3099b4..693877d69606 100644
--- a/net/mpls/internal.h
+++ b/net/mpls/internal.h
@@ -23,6 +23,9 @@  struct mpls_entry_decoded {
 };
 
 struct mpls_dev {
+	int			input_enabled;
+
+	struct ctl_table_header *sysctl;
 };
 
 struct sk_buff;