net: Introduce L3 Master device abstraction

L3 master devices allow users of the abstraction to influence FIB lookups
for enslaved devices. Current API provides a means for the master device
to return a specific FIB table for an enslaved device, to return an
rtable/custom dst and influence the OIF used for fib lookups.

Signed-off-by: David Ahern <dsa@cumulusnetworks.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

8 files changed, 246 insertions, 0 deletions

diff --git a/MAINTAINERS b/MAINTAINERS
index bcd263de4827..3f2d7a9d0bbf 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -6095,6 +6095,13 @@ F:	Documentation/auxdisplay/ks0108
 F:      drivers/auxdisplay/ks0108.c
 F:      include/linux/ks0108.h
 
+L3MDEV
+M:      David Ahern <dsa@cumulusnetworks.com>
+L:      netdev@vger.kernel.org
+S:      Maintained
+F:      net/l3mdev
+F:      include/net/l3mdev.h
+
 LAPB module
 L:      linux-x25@vger.kernel.org
 S:      Orphan
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 99c33e83822f..c7f14794fe14 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -1587,6 +1587,9 @@ struct net_device {
 #ifdef CONFIG_NET_SWITCHDEV
         const struct switchdev_ops *switchdev_ops;
 #endif
+#ifdef CONFIG_NET_L3_MASTER_DEV
+        const struct l3mdev_ops *l3mdev_ops;
+#endif
 
         const struct header_ops *header_ops;
 
diff --git a/include/net/l3mdev.h b/include/net/l3mdev.h
new file mode 100644
index 000000000000..e382c777bab8
--- /dev/null
+++ b/include/net/l3mdev.h
@@ -0,0 +1,125 @@
+/*
+ * include/net/l3mdev.h - L3 master device API
+ * Copyright (c) 2015 Cumulus Networks
+ * Copyright (c) 2015 David Ahern <dsa@cumulusnetworks.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ */
+#ifndef _NET_L3MDEV_H_
+#define _NET_L3MDEV_H_
+
+/**
+ * struct l3mdev_ops - l3mdev operations
+ *
+ * @l3mdev_fib_table: Get FIB table id to use for lookups
+ *
+ * @l3mdev_get_rtable: Get cached IPv4 rtable (dst_entry) for device
+ */
+
+struct l3mdev_ops {
+        u32             (*l3mdev_fib_table)(const struct net_device *dev);
+        struct rtable * (*l3mdev_get_rtable)(const struct net_device *dev,
+                                             const struct flowi4 *fl4);
+};
+
+#ifdef CONFIG_NET_L3_MASTER_DEV
+
+int l3mdev_master_ifindex_rcu(struct net_device *dev);
+static inline int l3mdev_master_ifindex(struct net_device *dev)
+{
+        int ifindex;
+
+        rcu_read_lock();
+        ifindex = l3mdev_master_ifindex_rcu(dev);
+        rcu_read_unlock();
+
+        return ifindex;
+}
+
+/* get index of an interface to use for FIB lookups. For devices
+ * enslaved to an L3 master device FIB lookups are based on the
+ * master index
+ */
+static inline int l3mdev_fib_oif_rcu(struct net_device *dev)
+{
+        return l3mdev_master_ifindex_rcu(dev) ? : dev->ifindex;
+}
+
+static inline int l3mdev_fib_oif(struct net_device *dev)
+{
+        int oif;
+
+        rcu_read_lock();
+        oif = l3mdev_fib_oif_rcu(dev);
+        rcu_read_unlock();
+
+        return oif;
+}
+
+u32 l3mdev_fib_table_rcu(const struct net_device *dev);
+u32 l3mdev_fib_table_by_index(struct net *net, int ifindex);
+static inline u32 l3mdev_fib_table(const struct net_device *dev)
+{
+        u32 tb_id;
+
+        rcu_read_lock();
+        tb_id = l3mdev_fib_table_rcu(dev);
+        rcu_read_unlock();
+
+        return tb_id;
+}
+
+static inline struct rtable *l3mdev_get_rtable(const struct net_device *dev,
+                                               const struct flowi4 *fl4)
+{
+        if (netif_is_l3_master(dev) && dev->l3mdev_ops->l3mdev_get_rtable)
+                return dev->l3mdev_ops->l3mdev_get_rtable(dev, fl4);
+
+        return NULL;
+}
+
+#else
+
+static inline int l3mdev_master_ifindex_rcu(struct net_device *dev)
+{
+        return 0;
+}
+static inline int l3mdev_master_ifindex(struct net_device *dev)
+{
+        return 0;
+}
+
+static inline int l3mdev_fib_oif_rcu(struct net_device *dev)
+{
+        return dev ? dev->ifindex : 0;
+}
+static inline int l3mdev_fib_oif(struct net_device *dev)
+{
+        return dev ? dev->ifindex : 0;
+}
+
+static inline u32 l3mdev_fib_table_rcu(const struct net_device *dev)
+{
+        return 0;
+}
+static inline u32 l3mdev_fib_table(const struct net_device *dev)
+{
+        return 0;
+}
+static inline u32 l3mdev_fib_table_by_index(struct net *net, int ifindex)
+{
+        return 0;
+}
+
+static inline struct rtable *l3mdev_get_rtable(const struct net_device *dev,
+                                               const struct flowi4 *fl4)
+{
+        return NULL;
+}
+
+#endif
+
+#endif /* _NET_L3MDEV_H_ */
diff --git a/net/Kconfig b/net/Kconfig
index 7021c1bf44d6..127da94ae25e 100644
--- a/net/Kconfig
+++ b/net/Kconfig
@@ -232,6 +232,7 @@ source "net/netlink/Kconfig"
 source "net/mpls/Kconfig"
 source "net/hsr/Kconfig"
 source "net/switchdev/Kconfig"
+source "net/l3mdev/Kconfig"
 
 config RPS
         bool
diff --git a/net/Makefile b/net/Makefile
index 3995613e5510..a5d04098dfce 100644
--- a/net/Makefile
+++ b/net/Makefile
@@ -74,3 +74,6 @@ obj-$(CONFIG_HSR)		+= hsr/
 ifneq ($(CONFIG_NET_SWITCHDEV),)
 obj-y                           += switchdev/
 endif
+ifneq ($(CONFIG_NET_L3_MASTER_DEV),)
+obj-y                           += l3mdev/
+endif
diff --git a/net/l3mdev/Kconfig b/net/l3mdev/Kconfig
new file mode 100644
index 000000000000..5d47325037bc
--- /dev/null
+++ b/net/l3mdev/Kconfig
@@ -0,0 +1,10 @@
+#
+# Configuration for L3 master device support
+#
+
+config NET_L3_MASTER_DEV
+        bool "L3 Master device support"
+        depends on INET || IPV6
+        ---help---
+          This module provides glue between core networking code and device
+          drivers to support L3 master devices like VRF.
diff --git a/net/l3mdev/Makefile b/net/l3mdev/Makefile
new file mode 100644
index 000000000000..84a53a6f609a
--- /dev/null
+++ b/net/l3mdev/Makefile
@@ -0,0 +1,5 @@
+#
+# Makefile for the L3 device API
+#
+
+obj-$(CONFIG_NET_L3_MASTER_DEV) += l3mdev.o
diff --git a/net/l3mdev/l3mdev.c b/net/l3mdev/l3mdev.c
new file mode 100644
index 000000000000..ddf75ad41713
--- /dev/null
+++ b/net/l3mdev/l3mdev.c
@@ -0,0 +1,92 @@
+/*
+ * net/l3mdev/l3mdev.c - L3 master device implementation
+ * Copyright (c) 2015 Cumulus Networks
+ * Copyright (c) 2015 David Ahern <dsa@cumulusnetworks.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ */
+
+#include <linux/netdevice.h>
+#include <net/l3mdev.h>
+
+/**
+ *      l3mdev_master_ifindex - get index of L3 master device
+ *      @dev: targeted interface
+ */
+
+int l3mdev_master_ifindex_rcu(struct net_device *dev)
+{
+        int ifindex = 0;
+
+        if (!dev)
+                return 0;
+
+        if (netif_is_l3_master(dev)) {
+                ifindex = dev->ifindex;
+        } else if (dev->flags & IFF_SLAVE) {
+                struct net_device *master;
+
+                master = netdev_master_upper_dev_get_rcu(dev);
+                if (master && netif_is_l3_master(master))
+                        ifindex = master->ifindex;
+        }
+
+        return ifindex;
+}
+EXPORT_SYMBOL_GPL(l3mdev_master_ifindex_rcu);
+
+/**
+ *      l3mdev_fib_table - get FIB table id associated with an L3
+ *                             master interface
+ *      @dev: targeted interface
+ */
+
+u32 l3mdev_fib_table_rcu(const struct net_device *dev)
+{
+        u32 tb_id = 0;
+
+        if (!dev)
+                return 0;
+
+        if (netif_is_l3_master(dev)) {
+                if (dev->l3mdev_ops->l3mdev_fib_table)
+                        tb_id = dev->l3mdev_ops->l3mdev_fib_table(dev);
+        } else if (dev->flags & IFF_SLAVE) {
+                /* Users of netdev_master_upper_dev_get_rcu need non-const,
+                 * but current inet_*type functions take a const
+                 */
+                struct net_device *_dev = (struct net_device *) dev;
+                const struct net_device *master;
+
+                master = netdev_master_upper_dev_get_rcu(_dev);
+                if (master && netif_is_l3_master(master) &&
+                    master->l3mdev_ops->l3mdev_fib_table)
+                        tb_id = master->l3mdev_ops->l3mdev_fib_table(master);
+        }
+
+        return tb_id;
+}
+EXPORT_SYMBOL_GPL(l3mdev_fib_table_rcu);
+
+u32 l3mdev_fib_table_by_index(struct net *net, int ifindex)
+{
+        struct net_device *dev;
+        u32 tb_id = 0;
+
+        if (!ifindex)
+                return 0;
+
+        rcu_read_lock();
+
+        dev = dev_get_by_index_rcu(net, ifindex);
+        if (dev)
+                tb_id = l3mdev_fib_table_rcu(dev);
+
+        rcu_read_unlock();
+
+        return tb_id;
+}
+EXPORT_SYMBOL_GPL(l3mdev_fib_table_by_index);