Merge branch 'vxlan-vnifiltering'

Roopa Prabhu says:

====================
vxlan metadata device vnifiltering support

This series adds vnifiltering support to vxlan 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.

This series adds vnifiltering support to collect metadata devices to
terminate 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    │
                                     └────────────┘

v2:
  - remove stale xstats declarations pointed out by Nikolay Aleksandrov
  - squash selinux patch with the tunnel api patch as pointed out by
    benjamin poirier
  - Fix various build issues:
	Reported-by: kernel test robot <lkp@intel.com>

v3:
  - incorporate review feedback from Jakub
	- move rhashtable declarations to c file
	- define and use netlink policy for top level vxlan filter api
	- fix unused stats function warning
	- pass vninode from vnifilter lookup into stats count function
		to avoid another lookup (only applicable to vxlan_rcv)
	- fix missing vxlan vni delete notifications in vnifilter uninit
	  function
	- misc cleanups
  - remote dev check for multicast groups added via vnifiltering api
====================

Signed-off-by: David S. Miller <davem@davemloft.net>

3 files changed, 110 insertions, 2 deletions

diff --git a/include/net/vxlan.h b/include/net/vxlan.h
index 5a934bebe630..bca5b01af247 100644
--- a/include/net/vxlan.h
+++ b/include/net/vxlan.h
@@ -227,11 +227,56 @@ struct vxlan_config {
 	enum ifla_vxlan_df	df;
 };
 
+enum {
+	VXLAN_VNI_STATS_RX,
+	VXLAN_VNI_STATS_RX_DROPS,
+	VXLAN_VNI_STATS_RX_ERRORS,
+	VXLAN_VNI_STATS_TX,
+	VXLAN_VNI_STATS_TX_DROPS,
+	VXLAN_VNI_STATS_TX_ERRORS,
+};
+
+struct vxlan_vni_stats {
+	u64 rx_packets;
+	u64 rx_bytes;
+	u64 rx_drops;
+	u64 rx_errors;
+	u64 tx_packets;
+	u64 tx_bytes;
+	u64 tx_drops;
+	u64 tx_errors;
+};
+
+struct vxlan_vni_stats_pcpu {
+	struct vxlan_vni_stats stats;
+	struct u64_stats_sync syncp;
+};
+
 struct vxlan_dev_node {
 	struct hlist_node hlist;
 	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 vxlan_vni_stats_pcpu __percpu *stats;
+
+	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 +299,8 @@ struct vxlan_dev {
 
 	struct vxlan_config	cfg;
 
+	struct vxlan_vni_group  __rcu *vnigrp;
+
 	struct hlist_head fdb_head[FDB_HASH_SIZE];
 };
 
@@ -274,6 +321,7 @@ 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 +331,8 @@ 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 +341,8 @@ 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);
diff --git a/include/uapi/linux/if_link.h b/include/uapi/linux/if_link.h
index be09d2ad4b5d..e315e53125f4 100644
--- a/include/uapi/linux/if_link.h
+++ b/include/uapi/linux/if_link.h
@@ -713,7 +713,55 @@ enum ipvlan_mode {
 #define IPVLAN_F_PRIVATE	0x01
 #define IPVLAN_F_VEPA		0x02
 
+/* Tunnel RTM header */
+struct tunnel_msg {
+	__u8 family;
+	__u8 flags;
+	__u16 reserved2;
+	__u32 ifindex;
+};
+
 /* VXLAN section */
+
+/* include statistics in the dump */
+#define TUNNEL_MSG_FLAG_STATS	0x01
+
+#define TUNNEL_MSG_VALID_USER_FLAGS TUNNEL_MSG_FLAG_STATS
+
+/* Embedded inside VXLAN_VNIFILTER_ENTRY_STATS */
+enum {
+	VNIFILTER_ENTRY_STATS_UNSPEC,
+	VNIFILTER_ENTRY_STATS_RX_BYTES,
+	VNIFILTER_ENTRY_STATS_RX_PKTS,
+	VNIFILTER_ENTRY_STATS_RX_DROPS,
+	VNIFILTER_ENTRY_STATS_RX_ERRORS,
+	VNIFILTER_ENTRY_STATS_TX_BYTES,
+	VNIFILTER_ENTRY_STATS_TX_PKTS,
+	VNIFILTER_ENTRY_STATS_TX_DROPS,
+	VNIFILTER_ENTRY_STATS_TX_ERRORS,
+	VNIFILTER_ENTRY_STATS_PAD,
+	__VNIFILTER_ENTRY_STATS_MAX
+};
+#define VNIFILTER_ENTRY_STATS_MAX (__VNIFILTER_ENTRY_STATS_MAX - 1)
+
+enum {
+	VXLAN_VNIFILTER_ENTRY_UNSPEC,
+	VXLAN_VNIFILTER_ENTRY_START,
+	VXLAN_VNIFILTER_ENTRY_END,
+	VXLAN_VNIFILTER_ENTRY_GROUP,
+	VXLAN_VNIFILTER_ENTRY_GROUP6,
+	VXLAN_VNIFILTER_ENTRY_STATS,
+	__VXLAN_VNIFILTER_ENTRY_MAX
+};
+#define VXLAN_VNIFILTER_ENTRY_MAX	(__VXLAN_VNIFILTER_ENTRY_MAX - 1)
+
+enum {
+	VXLAN_VNIFILTER_UNSPEC,
+	VXLAN_VNIFILTER_ENTRY,
+	__VXLAN_VNIFILTER_MAX
+};
+#define VXLAN_VNIFILTER_MAX	(__VXLAN_VNIFILTER_MAX - 1)
+
 enum {
 	IFLA_VXLAN_UNSPEC,
 	IFLA_VXLAN_ID,
@@ -745,6 +793,7 @@ enum {
 	IFLA_VXLAN_GPE,
 	IFLA_VXLAN_TTL_INHERIT,
 	IFLA_VXLAN_DF,
+	IFLA_VXLAN_VNIFILTER, /* only applicable with COLLECT_METADATA mode */
 	__IFLA_VXLAN_MAX
 };
 #define IFLA_VXLAN_MAX	(__IFLA_VXLAN_MAX - 1)
diff --git a/include/uapi/linux/rtnetlink.h b/include/uapi/linux/rtnetlink.h
index 93d934cc4613..0970cb4b1b88 100644
--- a/include/uapi/linux/rtnetlink.h
+++ b/include/uapi/linux/rtnetlink.h
@@ -185,6 +185,13 @@ enum {
 	RTM_GETNEXTHOPBUCKET,
 #define RTM_GETNEXTHOPBUCKET	RTM_GETNEXTHOPBUCKET
 
+	RTM_NEWTUNNEL = 120,
+#define RTM_NEWTUNNEL	RTM_NEWTUNNEL
+	RTM_DELTUNNEL,
+#define RTM_DELTUNNEL	RTM_DELTUNNEL
+	RTM_GETTUNNEL,
+#define RTM_GETTUNNEL	RTM_GETTUNNEL
+
 	__RTM_MAX,
 #define RTM_MAX		(((__RTM_MAX + 3) & ~3) - 1)
 };
@@ -756,6 +763,8 @@ enum rtnetlink_groups {
 #define RTNLGRP_BRVLAN		RTNLGRP_BRVLAN
 	RTNLGRP_MCTP_IFADDR,
 #define RTNLGRP_MCTP_IFADDR	RTNLGRP_MCTP_IFADDR
+	RTNLGRP_TUNNEL,
+#define RTNLGRP_TUNNEL		RTNLGRP_TUNNEL
 	__RTNLGRP_MAX
 };
 #define RTNLGRP_MAX	(__RTNLGRP_MAX - 1)