bridge: per vlan dst_metadata netlink support

This patch adds support to attach per vlan tunnel info dst
metadata. This enables bridge driver to map vlan to tunnel_info
at ingress and egress. It uses the kernel dst_metadata infrastructure.

The initial use case is vlan to vni bridging, but the api is generic
to extend to any tunnel_info in the future:
    - Uapi to configure/unconfigure/dump per vlan tunnel data
    - netlink functions to configure vlan and tunnel_info mapping
    - Introduces bridge port flag BR_LWT_VLAN to enable attach/detach
    dst_metadata to bridged packets on ports. off by default.
    - changes to existing code is mainly refactor some existing vlan
    handling netlink code + hooks for new vlan tunnel code
    - I have kept the vlan tunnel code isolated in separate files.
    - most of the netlink vlan tunnel code is handling of vlan-tunid
    ranges (follows the vlan range handling code). To conserve space
    vlan-tunid by default are always dumped in ranges if applicable.

Use case:
example use for this is a vxlan bridging gateway or vtep
which maps vlans to vn-segments (or vnis).

iproute2 example (patched and pruned iproute2 output to just show
relevant fdb entries):
example shows same host mac learnt on two vni's and
vlan 100 maps to vni 1000, vlan 101 maps to vni 1001

before (netdev per vni):
$bridge fdb show | grep "00:02:00:00:00:03"
00:02:00:00:00:03 dev vxlan1001 vlan 101 master bridge
00:02:00:00:00:03 dev vxlan1001 dst 12.0.0.8 self
00:02:00:00:00:03 dev vxlan1000 vlan 100 master bridge
00:02:00:00:00:03 dev vxlan1000 dst 12.0.0.8 self

after this patch with collect metdata in bridged mode (single netdev):
$bridge fdb show | grep "00:02:00:00:00:03"
00:02:00:00:00:03 dev vxlan0 vlan 101 master bridge
00:02:00:00:00:03 dev vxlan0 src_vni 1001 dst 12.0.0.8 self
00:02:00:00:00:03 dev vxlan0 vlan 100 master bridge
00:02:00:00:00:03 dev vxlan0 src_vni 1000 dst 12.0.0.8 self

CC: Nikolay Aleksandrov <nikolay@cumulusnetworks.com>
Signed-off-by: Roopa Prabhu <roopa@cumulusnetworks.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

1 files changed, 149 insertions, 0 deletions

diff --git a/net/bridge/br_vlan_tunnel.c b/net/bridge/br_vlan_tunnel.c
new file mode 100644
index 000000000000..b3fd29d20a3c
--- /dev/null
+++ b/net/bridge/br_vlan_tunnel.c
@@ -0,0 +1,149 @@
+/*
+ *	Bridge per vlan tunnel port dst_metadata handling code
+ *
+ *	Authors:
+ *	Roopa Prabhu		<roopa@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/kernel.h>
+#include <linux/netdevice.h>
+#include <linux/rtnetlink.h>
+#include <linux/slab.h>
+#include <net/switchdev.h>
+#include <net/dst_metadata.h>
+
+#include "br_private.h"
+#include "br_private_tunnel.h"
+
+static inline int br_vlan_tunid_cmp(struct rhashtable_compare_arg *arg,
+				    const void *ptr)
+{
+	const struct net_bridge_vlan *vle = ptr;
+	__be64 tunid = *(__be64 *)arg->key;
+
+	return vle->tinfo.tunnel_id != tunid;
+}
+
+static const struct rhashtable_params br_vlan_tunnel_rht_params = {
+	.head_offset = offsetof(struct net_bridge_vlan, tnode),
+	.key_offset = offsetof(struct net_bridge_vlan, tinfo.tunnel_id),
+	.key_len = sizeof(__be64),
+	.nelem_hint = 3,
+	.locks_mul = 1,
+	.obj_cmpfn = br_vlan_tunid_cmp,
+	.automatic_shrinking = true,
+};
+
+void vlan_tunnel_info_del(struct net_bridge_vlan_group *vg,
+			  struct net_bridge_vlan *vlan)
+{
+	if (!vlan->tinfo.tunnel_dst)
+		return;
+	rhashtable_remove_fast(&vg->tunnel_hash, &vlan->tnode,
+			       br_vlan_tunnel_rht_params);
+	vlan->tinfo.tunnel_id = 0;
+	dst_release(&vlan->tinfo.tunnel_dst->dst);
+	vlan->tinfo.tunnel_dst = NULL;
+}
+
+static int __vlan_tunnel_info_add(struct net_bridge_vlan_group *vg,
+				  struct net_bridge_vlan *vlan, u32 tun_id)
+{
+	struct metadata_dst *metadata = NULL;
+	__be64 key = key32_to_tunnel_id(cpu_to_be32(tun_id));
+	int err;
+
+	if (vlan->tinfo.tunnel_dst)
+		return -EEXIST;
+
+	metadata = __ip_tun_set_dst(0, 0, 0, 0, 0, TUNNEL_KEY,
+				    key, 0);
+	if (!metadata)
+		return -EINVAL;
+
+	metadata->u.tun_info.mode |= IP_TUNNEL_INFO_TX | IP_TUNNEL_INFO_BRIDGE;
+	vlan->tinfo.tunnel_dst = metadata;
+	vlan->tinfo.tunnel_id = key;
+
+	err = rhashtable_lookup_insert_fast(&vg->tunnel_hash, &vlan->tnode,
+					    br_vlan_tunnel_rht_params);
+	if (err)
+		goto out;
+
+	return 0;
+out:
+	dst_release(&vlan->tinfo.tunnel_dst->dst);
+
+	return err;
+}
+
+/* Must be protected by RTNL.
+ * Must be called with vid in range from 1 to 4094 inclusive.
+ */
+int nbp_vlan_tunnel_info_add(struct net_bridge_port *port, u16 vid, u32 tun_id)
+{
+	struct net_bridge_vlan_group *vg;
+	struct net_bridge_vlan *vlan;
+
+	ASSERT_RTNL();
+
+	vg = nbp_vlan_group(port);
+	vlan = br_vlan_find(vg, vid);
+	if (!vlan)
+		return -EINVAL;
+
+	return __vlan_tunnel_info_add(vg, vlan, tun_id);
+}
+
+/* Must be protected by RTNL.
+ * Must be called with vid in range from 1 to 4094 inclusive.
+ */
+int nbp_vlan_tunnel_info_delete(struct net_bridge_port *port, u16 vid)
+{
+	struct net_bridge_vlan_group *vg;
+	struct net_bridge_vlan *v;
+
+	ASSERT_RTNL();
+
+	vg = nbp_vlan_group(port);
+	v = br_vlan_find(vg, vid);
+	if (!v)
+		return -ENOENT;
+
+	vlan_tunnel_info_del(vg, v);
+
+	return 0;
+}
+
+static void __vlan_tunnel_info_flush(struct net_bridge_vlan_group *vg)
+{
+	struct net_bridge_vlan *vlan, *tmp;
+
+	list_for_each_entry_safe(vlan, tmp, &vg->vlan_list, vlist)
+		vlan_tunnel_info_del(vg, vlan);
+}
+
+void nbp_vlan_tunnel_info_flush(struct net_bridge_port *port)
+{
+	struct net_bridge_vlan_group *vg;
+
+	ASSERT_RTNL();
+
+	vg = nbp_vlan_group(port);
+	__vlan_tunnel_info_flush(vg);
+}
+
+int vlan_tunnel_init(struct net_bridge_vlan_group *vg)
+{
+	return rhashtable_init(&vg->tunnel_hash, &br_vlan_tunnel_rht_params);
+}
+
+void vlan_tunnel_deinit(struct net_bridge_vlan_group *vg)
+{
+	rhashtable_destroy(&vg->tunnel_hash);
+}