vxlan: vni filtering support on collect metadata device

This patch adds vnifiltering support to collect metadata device.

Motivation:
You can only use a single vxlan collect metadata device for a given
vxlan udp port in the system today. The vxlan collect metadata device
terminates all received vxlan packets. As shown in the below diagram,
there are use-cases where you need to support multiple such vxlan devices in
independent bridge domains. Each vxlan device must terminate the vni's
it is configured for.
Example usecase: In a service provider network a service provider
typically supports multiple bridge domains with overlapping vlans.
One bridge domain per customer. Vlans in each bridge domain are
mapped to globally unique vxlan ranges assigned to each customer.

vnifiltering support in collect metadata devices terminates only configured
vnis. This is similar to vlan filtering in bridge driver. The vni filtering
capability is provided by a new flag on collect metadata device.

In the below pic:
	- customer1 is mapped to br1 bridge domain
	- customer2 is mapped to br2 bridge domain
	- customer1 vlan 10-11 is mapped to vni 1001-1002
	- customer2 vlan 10-11 is mapped to vni 2001-2002
	- br1 and br2 are vlan filtering bridges
	- vxlan1 and vxlan2 are collect metadata devices with
	  vnifiltering enabled

┌──────────────────────────────────────────────────────────────────┐
│  switch                                                          │
│                                                                  │
│         ┌───────────┐                 ┌───────────┐              │
│         │           │                 │           │              │
│         │   br1     │                 │   br2     │              │
│         └┬─────────┬┘                 └──┬───────┬┘              │
│     vlans│         │               vlans │       │               │
│     10,11│         │                10,11│       │               │
│          │     vlanvnimap:               │    vlanvnimap:        │
│          │       10-1001,11-1002         │      10-2001,11-2002  │
│          │         │                     │       │               │
│   ┌──────┴┐     ┌──┴─────────┐       ┌───┴────┐  │               │
│   │ swp1  │     │vxlan1      │       │ swp2   │ ┌┴─────────────┐ │
│   │       │     │  vnifilter:│       │        │ │vxlan2        │ │
│   └───┬───┘     │   1001,1002│       └───┬────┘ │ vnifilter:   │ │
│       │         └────────────┘           │      │  2001,2002   │ │
│       │                                  │      └──────────────┘ │
│       │                                  │                       │
└───────┼──────────────────────────────────┼───────────────────────┘
        │                                  │
        │                                  │
  ┌─────┴───────┐                          │
  │  customer1  │                    ┌─────┴──────┐
  │ host/VM     │                    │customer2   │
  └─────────────┘                    │ host/VM    │
                                     └────────────┘

With this implementation, vxlan dst metadata device can
be associated with range of vnis.
struct vxlan_vni_node is introduced to represent
a configured vni. We start with vni and its
associated remote_ip in this structure. This
structure can be extended to bring in other
per vni attributes if there are usecases for it.
A vni inherits an attribute from the base vxlan device
if there is no per vni attributes defined.

struct vxlan_dev gets a new rhashtable for
vnis called vxlan_vni_group. vxlan_vnifilter.c
implements the necessary netlink api, notifications
and helper functions to process and manage lifecycle
of vxlan_vni_node.

This patch also adds new helper functions in vxlan_multicast.c
to handle per vni remote_ip multicast groups which are part
of vxlan_vni_group.

Fix build problems:
Reported-by: kernel test robot <lkp@intel.com>
Signed-off-by: Roopa Prabhu <roopa@nvidia.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

1 files changed, 26 insertions, 2 deletions

diff --git a/include/net/vxlan.h b/include/net/vxlan.h
index 5a934bebe630..8eb961bb9589 100644
--- a/include/net/vxlan.h
+++ b/include/net/vxlan.h
@@ -232,6 +232,25 @@ struct vxlan_dev_node {
 	struct vxlan_dev *vxlan;
 };
 
+struct vxlan_vni_node {
+	struct rhash_head vnode;
+	struct vxlan_dev_node hlist4; /* vni hash table for IPv4 socket */
+#if IS_ENABLED(CONFIG_IPV6)
+	struct vxlan_dev_node hlist6; /* vni hash table for IPv6 socket */
+#endif
+	struct list_head vlist;
+	__be32 vni;
+	union vxlan_addr remote_ip; /* default remote ip for this vni */
+
+	struct rcu_head rcu;
+};
+
+struct vxlan_vni_group {
+	struct rhashtable	vni_hash;
+	struct list_head	vni_list;
+	u32			num_vnis;
+};
+
 /* Pseudo network device */
 struct vxlan_dev {
 	struct vxlan_dev_node hlist4;	/* vni hash table for IPv4 socket */
@@ -254,6 +273,8 @@ struct vxlan_dev {
 
 	struct vxlan_config	cfg;
 
+	struct vxlan_vni_group  __rcu *vnigrp;
+
 	struct hlist_head fdb_head[FDB_HASH_SIZE];
 };
 
@@ -274,6 +295,7 @@ struct vxlan_dev {
 #define VXLAN_F_GPE			0x4000
 #define VXLAN_F_IPV6_LINKLOCAL		0x8000
 #define VXLAN_F_TTL_INHERIT		0x10000
+#define VXLAN_F_VNIFILTER               0x20000
 
 /* Flags that are used in the receive path. These flags must match in
  * order for a socket to be shareable
@@ -283,7 +305,8 @@ struct vxlan_dev {
 					 VXLAN_F_UDP_ZERO_CSUM6_RX |	\
 					 VXLAN_F_REMCSUM_RX |		\
 					 VXLAN_F_REMCSUM_NOPARTIAL |	\
-					 VXLAN_F_COLLECT_METADATA)
+					 VXLAN_F_COLLECT_METADATA |	\
+					 VXLAN_F_VNIFILTER)
 
 /* Flags that can be set together with VXLAN_F_GPE. */
 #define VXLAN_F_ALLOWED_GPE		(VXLAN_F_GPE |			\
@@ -292,7 +315,8 @@ struct vxlan_dev {
 					 VXLAN_F_UDP_ZERO_CSUM_TX |	\
 					 VXLAN_F_UDP_ZERO_CSUM6_TX |	\
 					 VXLAN_F_UDP_ZERO_CSUM6_RX |	\
-					 VXLAN_F_COLLECT_METADATA)
+					 VXLAN_F_COLLECT_METADATA  |	\
+					 VXLAN_F_VNIFILTER)
 
 struct net_device *vxlan_dev_create(struct net *net, const char *name,
 				    u8 name_assign_type, struct vxlan_config *conf);