linux/include/net/vxlan.h

259 lines
7.0 KiB
C
Raw Normal View History

#ifndef __NET_VXLAN_H
#define __NET_VXLAN_H 1
#include <linux/ip.h>
#include <linux/ipv6.h>
#include <linux/if_vlan.h>
#include <linux/skbuff.h>
#include <linux/netdevice.h>
#include <linux/udp.h>
vxlan: Flow based tunneling Allows putting a VXLAN device into a new flow-based mode in which skbs with a ip_tunnel_info dst metadata attached will be encapsulated according to the instructions stored in there with the VXLAN device defaults taken into consideration. Similar on the receive side, if the VXLAN_F_COLLECT_METADATA flag is set, the packet processing will populate a ip_tunnel_info struct for each packet received and attach it to the skb using the new metadata dst. The metadata structure will contain the outer header and tunnel header fields which have been stripped off. Layers further up in the stack such as routing, tc or netfitler can later match on these fields and perform forwarding. It is the responsibility of upper layers to ensure that the flag is set if the metadata is needed. The flag limits the additional cost of metadata collecting based on demand. This prepares the VXLAN device to be steered by the routing and other subsystems which allows to support encapsulation for a large number of tunnel endpoints and tunnel ids through a single net_device which improves the scalability. It also allows for OVS to leverage this mode which in turn allows for the removal of the OVS specific VXLAN code. Because the skb is currently scrubed in vxlan_rcv(), the attachment of the new dst metadata is postponed until after scrubing which requires the temporary addition of a new member to vxlan_metadata. This member is removed again in a later commit after the indirect VXLAN receive API has been removed. Signed-off-by: Thomas Graf <tgraf@suug.ch> Signed-off-by: Pravin B Shelar <pshelar@nicira.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2015-07-21 16:43:58 +08:00
#include <net/dst_metadata.h>
#define VNI_HASH_BITS 10
#define VNI_HASH_SIZE (1<<VNI_HASH_BITS)
vxlan: Group Policy extension Implements supports for the Group Policy VXLAN extension [0] to provide a lightweight and simple security label mechanism across network peers based on VXLAN. The security context and associated metadata is mapped to/from skb->mark. This allows further mapping to a SELinux context using SECMARK, to implement ACLs directly with nftables, iptables, OVS, tc, etc. The group membership is defined by the lower 16 bits of skb->mark, the upper 16 bits are used for flags. SELinux allows to manage label to secure local resources. However, distributed applications require ACLs to implemented across hosts. This is typically achieved by matching on L2-L4 fields to identify the original sending host and process on the receiver. On top of that, netlabel and specifically CIPSO [1] allow to map security contexts to universal labels. However, netlabel and CIPSO are relatively complex. This patch provides a lightweight alternative for overlay network environments with a trusted underlay. No additional control protocol is required. Host 1: Host 2: Group A Group B Group B Group A +-----+ +-------------+ +-------+ +-----+ | lxc | | SELinux CTX | | httpd | | VM | +--+--+ +--+----------+ +---+---+ +--+--+ \---+---/ \----+---/ | | +---+---+ +---+---+ | vxlan | | vxlan | +---+---+ +---+---+ +------------------------------+ Backwards compatibility: A VXLAN-GBP socket can receive standard VXLAN frames and will assign the default group 0x0000 to such frames. A Linux VXLAN socket will drop VXLAN-GBP frames. The extension is therefore disabled by default and needs to be specifically enabled: ip link add [...] type vxlan [...] gbp In a mixed environment with VXLAN and VXLAN-GBP sockets, the GBP socket must run on a separate port number. Examples: iptables: host1# iptables -I OUTPUT -m owner --uid-owner 101 -j MARK --set-mark 0x200 host2# iptables -I INPUT -m mark --mark 0x200 -j DROP OVS: # ovs-ofctl add-flow br0 'in_port=1,actions=load:0x200->NXM_NX_TUN_GBP_ID[],NORMAL' # ovs-ofctl add-flow br0 'in_port=2,tun_gbp_id=0x200,actions=drop' [0] https://tools.ietf.org/html/draft-smith-vxlan-group-policy [1] http://lwn.net/Articles/204905/ Signed-off-by: Thomas Graf <tgraf@suug.ch> Signed-off-by: David S. Miller <davem@davemloft.net>
2015-01-15 10:53:55 +08:00
/*
* VXLAN Group Based Policy Extension:
* +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
* |1|-|-|-|1|-|-|-|R|D|R|R|A|R|R|R| Group Policy ID |
* +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
* | VXLAN Network Identifier (VNI) | Reserved |
* +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
*
* D = Don't Learn bit. When set, this bit indicates that the egress
* VTEP MUST NOT learn the source address of the encapsulated frame.
*
* A = Indicates that the group policy has already been applied to
* this packet. Policies MUST NOT be applied by devices when the
* A bit is set.
*
* [0] https://tools.ietf.org/html/draft-smith-vxlan-group-policy
*/
struct vxlanhdr_gbp {
__u8 vx_flags;
#ifdef __LITTLE_ENDIAN_BITFIELD
__u8 reserved_flags1:3,
policy_applied:1,
reserved_flags2:2,
dont_learn:1,
reserved_flags3:1;
#elif defined(__BIG_ENDIAN_BITFIELD)
__u8 reserved_flags1:1,
dont_learn:1,
reserved_flags2:2,
policy_applied:1,
reserved_flags3:3;
#else
#error "Please fix <asm/byteorder.h>"
#endif
__be16 policy_id;
__be32 vx_vni;
};
#define VXLAN_GBP_USED_BITS (VXLAN_HF_GBP | 0xFFFFFF)
/* skb->mark mapping
*
* +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
* |R|R|R|R|R|R|R|R|R|D|R|R|A|R|R|R| Group Policy ID |
* +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
*/
#define VXLAN_GBP_DONT_LEARN (BIT(6) << 16)
#define VXLAN_GBP_POLICY_APPLIED (BIT(3) << 16)
#define VXLAN_GBP_ID_MASK (0xFFFF)
/* VXLAN protocol header:
* +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
* |G|R|R|R|I|R|R|C| Reserved |
* +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
* | VXLAN Network Identifier (VNI) | Reserved |
* +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
*
* G = 1 Group Policy (VXLAN-GBP)
* I = 1 VXLAN Network Identifier (VNI) present
* C = 1 Remote checksum offload (RCO)
*/
struct vxlanhdr {
__be32 vx_flags;
__be32 vx_vni;
};
/* VXLAN header flags. */
#define VXLAN_HF_RCO BIT(21)
vxlan: Group Policy extension Implements supports for the Group Policy VXLAN extension [0] to provide a lightweight and simple security label mechanism across network peers based on VXLAN. The security context and associated metadata is mapped to/from skb->mark. This allows further mapping to a SELinux context using SECMARK, to implement ACLs directly with nftables, iptables, OVS, tc, etc. The group membership is defined by the lower 16 bits of skb->mark, the upper 16 bits are used for flags. SELinux allows to manage label to secure local resources. However, distributed applications require ACLs to implemented across hosts. This is typically achieved by matching on L2-L4 fields to identify the original sending host and process on the receiver. On top of that, netlabel and specifically CIPSO [1] allow to map security contexts to universal labels. However, netlabel and CIPSO are relatively complex. This patch provides a lightweight alternative for overlay network environments with a trusted underlay. No additional control protocol is required. Host 1: Host 2: Group A Group B Group B Group A +-----+ +-------------+ +-------+ +-----+ | lxc | | SELinux CTX | | httpd | | VM | +--+--+ +--+----------+ +---+---+ +--+--+ \---+---/ \----+---/ | | +---+---+ +---+---+ | vxlan | | vxlan | +---+---+ +---+---+ +------------------------------+ Backwards compatibility: A VXLAN-GBP socket can receive standard VXLAN frames and will assign the default group 0x0000 to such frames. A Linux VXLAN socket will drop VXLAN-GBP frames. The extension is therefore disabled by default and needs to be specifically enabled: ip link add [...] type vxlan [...] gbp In a mixed environment with VXLAN and VXLAN-GBP sockets, the GBP socket must run on a separate port number. Examples: iptables: host1# iptables -I OUTPUT -m owner --uid-owner 101 -j MARK --set-mark 0x200 host2# iptables -I INPUT -m mark --mark 0x200 -j DROP OVS: # ovs-ofctl add-flow br0 'in_port=1,actions=load:0x200->NXM_NX_TUN_GBP_ID[],NORMAL' # ovs-ofctl add-flow br0 'in_port=2,tun_gbp_id=0x200,actions=drop' [0] https://tools.ietf.org/html/draft-smith-vxlan-group-policy [1] http://lwn.net/Articles/204905/ Signed-off-by: Thomas Graf <tgraf@suug.ch> Signed-off-by: David S. Miller <davem@davemloft.net>
2015-01-15 10:53:55 +08:00
#define VXLAN_HF_VNI BIT(27)
#define VXLAN_HF_GBP BIT(31)
vxlan: Remote checksum offload Add support for remote checksum offload in VXLAN. This uses a reserved bit to indicate that RCO is being done, and uses the low order reserved eight bits of the VNI to hold the start and offset values in a compressed manner. Start is encoded in the low order seven bits of VNI. This is start >> 1 so that the checksum start offset is 0-254 using even values only. Checksum offset (transport checksum field) is indicated in the high order bit in the low order byte of the VNI. If the bit is set, the checksum field is for UDP (so offset = start + 6), else checksum field is for TCP (so offset = start + 16). Only TCP and UDP are supported in this implementation. Remote checksum offload for VXLAN is described in: https://tools.ietf.org/html/draft-herbert-vxlan-rco-00 Tested by running 200 TCP_STREAM connections with VXLAN (over IPv4). With UDP checksums and Remote Checksum Offload IPv4 Client 11.84% CPU utilization Server 12.96% CPU utilization 9197 Mbps IPv6 Client 12.46% CPU utilization Server 14.48% CPU utilization 8963 Mbps With UDP checksums, no remote checksum offload IPv4 Client 15.67% CPU utilization Server 14.83% CPU utilization 9094 Mbps IPv6 Client 16.21% CPU utilization Server 14.32% CPU utilization 9058 Mbps No UDP checksums IPv4 Client 15.03% CPU utilization Server 23.09% CPU utilization 9089 Mbps IPv6 Client 16.18% CPU utilization Server 26.57% CPU utilization 8954 Mbps Signed-off-by: Tom Herbert <therbert@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2015-01-13 09:00:38 +08:00
/* Remote checksum offload header option */
#define VXLAN_RCO_MASK 0x7f /* Last byte of vni field */
#define VXLAN_RCO_UDP 0x80 /* Indicate UDP RCO (TCP when not set *) */
#define VXLAN_RCO_SHIFT 1 /* Left shift of start */
#define VXLAN_RCO_SHIFT_MASK ((1 << VXLAN_RCO_SHIFT) - 1)
#define VXLAN_MAX_REMCSUM_START (VXLAN_RCO_MASK << VXLAN_RCO_SHIFT)
#define VXLAN_N_VID (1u << 24)
#define VXLAN_VID_MASK (VXLAN_N_VID - 1)
#define VXLAN_VNI_MASK (VXLAN_VID_MASK << 8)
#define VXLAN_HLEN (sizeof(struct udphdr) + sizeof(struct vxlanhdr))
#define VNI_HASH_BITS 10
#define VNI_HASH_SIZE (1<<VNI_HASH_BITS)
#define FDB_HASH_BITS 8
#define FDB_HASH_SIZE (1<<FDB_HASH_BITS)
vxlan: Group Policy extension Implements supports for the Group Policy VXLAN extension [0] to provide a lightweight and simple security label mechanism across network peers based on VXLAN. The security context and associated metadata is mapped to/from skb->mark. This allows further mapping to a SELinux context using SECMARK, to implement ACLs directly with nftables, iptables, OVS, tc, etc. The group membership is defined by the lower 16 bits of skb->mark, the upper 16 bits are used for flags. SELinux allows to manage label to secure local resources. However, distributed applications require ACLs to implemented across hosts. This is typically achieved by matching on L2-L4 fields to identify the original sending host and process on the receiver. On top of that, netlabel and specifically CIPSO [1] allow to map security contexts to universal labels. However, netlabel and CIPSO are relatively complex. This patch provides a lightweight alternative for overlay network environments with a trusted underlay. No additional control protocol is required. Host 1: Host 2: Group A Group B Group B Group A +-----+ +-------------+ +-------+ +-----+ | lxc | | SELinux CTX | | httpd | | VM | +--+--+ +--+----------+ +---+---+ +--+--+ \---+---/ \----+---/ | | +---+---+ +---+---+ | vxlan | | vxlan | +---+---+ +---+---+ +------------------------------+ Backwards compatibility: A VXLAN-GBP socket can receive standard VXLAN frames and will assign the default group 0x0000 to such frames. A Linux VXLAN socket will drop VXLAN-GBP frames. The extension is therefore disabled by default and needs to be specifically enabled: ip link add [...] type vxlan [...] gbp In a mixed environment with VXLAN and VXLAN-GBP sockets, the GBP socket must run on a separate port number. Examples: iptables: host1# iptables -I OUTPUT -m owner --uid-owner 101 -j MARK --set-mark 0x200 host2# iptables -I INPUT -m mark --mark 0x200 -j DROP OVS: # ovs-ofctl add-flow br0 'in_port=1,actions=load:0x200->NXM_NX_TUN_GBP_ID[],NORMAL' # ovs-ofctl add-flow br0 'in_port=2,tun_gbp_id=0x200,actions=drop' [0] https://tools.ietf.org/html/draft-smith-vxlan-group-policy [1] http://lwn.net/Articles/204905/ Signed-off-by: Thomas Graf <tgraf@suug.ch> Signed-off-by: David S. Miller <davem@davemloft.net>
2015-01-15 10:53:55 +08:00
struct vxlan_metadata {
u32 gbp;
};
/* per UDP socket information */
struct vxlan_sock {
struct hlist_node hlist;
struct work_struct del_work;
struct socket *sock;
struct rcu_head rcu;
struct hlist_head vni_list[VNI_HASH_SIZE];
atomic_t refcnt;
struct udp_offload udp_offloads;
vxlan: Remote checksum offload Add support for remote checksum offload in VXLAN. This uses a reserved bit to indicate that RCO is being done, and uses the low order reserved eight bits of the VNI to hold the start and offset values in a compressed manner. Start is encoded in the low order seven bits of VNI. This is start >> 1 so that the checksum start offset is 0-254 using even values only. Checksum offset (transport checksum field) is indicated in the high order bit in the low order byte of the VNI. If the bit is set, the checksum field is for UDP (so offset = start + 6), else checksum field is for TCP (so offset = start + 16). Only TCP and UDP are supported in this implementation. Remote checksum offload for VXLAN is described in: https://tools.ietf.org/html/draft-herbert-vxlan-rco-00 Tested by running 200 TCP_STREAM connections with VXLAN (over IPv4). With UDP checksums and Remote Checksum Offload IPv4 Client 11.84% CPU utilization Server 12.96% CPU utilization 9197 Mbps IPv6 Client 12.46% CPU utilization Server 14.48% CPU utilization 8963 Mbps With UDP checksums, no remote checksum offload IPv4 Client 15.67% CPU utilization Server 14.83% CPU utilization 9094 Mbps IPv6 Client 16.21% CPU utilization Server 14.32% CPU utilization 9058 Mbps No UDP checksums IPv4 Client 15.03% CPU utilization Server 23.09% CPU utilization 9089 Mbps IPv6 Client 16.18% CPU utilization Server 26.57% CPU utilization 8954 Mbps Signed-off-by: Tom Herbert <therbert@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2015-01-13 09:00:38 +08:00
u32 flags;
};
union vxlan_addr {
struct sockaddr_in sin;
struct sockaddr_in6 sin6;
struct sockaddr sa;
};
struct vxlan_rdst {
union vxlan_addr remote_ip;
__be16 remote_port;
u32 remote_vni;
u32 remote_ifindex;
struct list_head list;
struct rcu_head rcu;
};
struct vxlan_config {
union vxlan_addr remote_ip;
union vxlan_addr saddr;
u32 vni;
int remote_ifindex;
int mtu;
__be16 dst_port;
__u16 port_min;
__u16 port_max;
__u8 tos;
__u8 ttl;
u32 flags;
unsigned long age_interval;
unsigned int addrmax;
bool no_share;
};
/* Pseudo network device */
struct vxlan_dev {
struct hlist_node hlist; /* vni hash table */
struct list_head next; /* vxlan's per namespace list */
struct vxlan_sock *vn4_sock; /* listening socket for IPv4 */
#if IS_ENABLED(CONFIG_IPV6)
struct vxlan_sock *vn6_sock; /* listening socket for IPv6 */
#endif
struct net_device *dev;
struct net *net; /* netns for packet i/o */
struct vxlan_rdst default_dst; /* default destination */
u32 flags; /* VXLAN_F_* in vxlan.h */
struct timer_list age_timer;
spinlock_t hash_lock;
unsigned int addrcnt;
struct gro_cells gro_cells;
struct vxlan_config cfg;
struct hlist_head fdb_head[FDB_HASH_SIZE];
};
#define VXLAN_F_LEARN 0x01
#define VXLAN_F_PROXY 0x02
#define VXLAN_F_RSC 0x04
#define VXLAN_F_L2MISS 0x08
#define VXLAN_F_L3MISS 0x10
#define VXLAN_F_IPV6 0x20
#define VXLAN_F_UDP_CSUM 0x40
#define VXLAN_F_UDP_ZERO_CSUM6_TX 0x80
#define VXLAN_F_UDP_ZERO_CSUM6_RX 0x100
vxlan: Remote checksum offload Add support for remote checksum offload in VXLAN. This uses a reserved bit to indicate that RCO is being done, and uses the low order reserved eight bits of the VNI to hold the start and offset values in a compressed manner. Start is encoded in the low order seven bits of VNI. This is start >> 1 so that the checksum start offset is 0-254 using even values only. Checksum offset (transport checksum field) is indicated in the high order bit in the low order byte of the VNI. If the bit is set, the checksum field is for UDP (so offset = start + 6), else checksum field is for TCP (so offset = start + 16). Only TCP and UDP are supported in this implementation. Remote checksum offload for VXLAN is described in: https://tools.ietf.org/html/draft-herbert-vxlan-rco-00 Tested by running 200 TCP_STREAM connections with VXLAN (over IPv4). With UDP checksums and Remote Checksum Offload IPv4 Client 11.84% CPU utilization Server 12.96% CPU utilization 9197 Mbps IPv6 Client 12.46% CPU utilization Server 14.48% CPU utilization 8963 Mbps With UDP checksums, no remote checksum offload IPv4 Client 15.67% CPU utilization Server 14.83% CPU utilization 9094 Mbps IPv6 Client 16.21% CPU utilization Server 14.32% CPU utilization 9058 Mbps No UDP checksums IPv4 Client 15.03% CPU utilization Server 23.09% CPU utilization 9089 Mbps IPv6 Client 16.18% CPU utilization Server 26.57% CPU utilization 8954 Mbps Signed-off-by: Tom Herbert <therbert@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2015-01-13 09:00:38 +08:00
#define VXLAN_F_REMCSUM_TX 0x200
#define VXLAN_F_REMCSUM_RX 0x400
vxlan: Group Policy extension Implements supports for the Group Policy VXLAN extension [0] to provide a lightweight and simple security label mechanism across network peers based on VXLAN. The security context and associated metadata is mapped to/from skb->mark. This allows further mapping to a SELinux context using SECMARK, to implement ACLs directly with nftables, iptables, OVS, tc, etc. The group membership is defined by the lower 16 bits of skb->mark, the upper 16 bits are used for flags. SELinux allows to manage label to secure local resources. However, distributed applications require ACLs to implemented across hosts. This is typically achieved by matching on L2-L4 fields to identify the original sending host and process on the receiver. On top of that, netlabel and specifically CIPSO [1] allow to map security contexts to universal labels. However, netlabel and CIPSO are relatively complex. This patch provides a lightweight alternative for overlay network environments with a trusted underlay. No additional control protocol is required. Host 1: Host 2: Group A Group B Group B Group A +-----+ +-------------+ +-------+ +-----+ | lxc | | SELinux CTX | | httpd | | VM | +--+--+ +--+----------+ +---+---+ +--+--+ \---+---/ \----+---/ | | +---+---+ +---+---+ | vxlan | | vxlan | +---+---+ +---+---+ +------------------------------+ Backwards compatibility: A VXLAN-GBP socket can receive standard VXLAN frames and will assign the default group 0x0000 to such frames. A Linux VXLAN socket will drop VXLAN-GBP frames. The extension is therefore disabled by default and needs to be specifically enabled: ip link add [...] type vxlan [...] gbp In a mixed environment with VXLAN and VXLAN-GBP sockets, the GBP socket must run on a separate port number. Examples: iptables: host1# iptables -I OUTPUT -m owner --uid-owner 101 -j MARK --set-mark 0x200 host2# iptables -I INPUT -m mark --mark 0x200 -j DROP OVS: # ovs-ofctl add-flow br0 'in_port=1,actions=load:0x200->NXM_NX_TUN_GBP_ID[],NORMAL' # ovs-ofctl add-flow br0 'in_port=2,tun_gbp_id=0x200,actions=drop' [0] https://tools.ietf.org/html/draft-smith-vxlan-group-policy [1] http://lwn.net/Articles/204905/ Signed-off-by: Thomas Graf <tgraf@suug.ch> Signed-off-by: David S. Miller <davem@davemloft.net>
2015-01-15 10:53:55 +08:00
#define VXLAN_F_GBP 0x800
#define VXLAN_F_REMCSUM_NOPARTIAL 0x1000
vxlan: Flow based tunneling Allows putting a VXLAN device into a new flow-based mode in which skbs with a ip_tunnel_info dst metadata attached will be encapsulated according to the instructions stored in there with the VXLAN device defaults taken into consideration. Similar on the receive side, if the VXLAN_F_COLLECT_METADATA flag is set, the packet processing will populate a ip_tunnel_info struct for each packet received and attach it to the skb using the new metadata dst. The metadata structure will contain the outer header and tunnel header fields which have been stripped off. Layers further up in the stack such as routing, tc or netfitler can later match on these fields and perform forwarding. It is the responsibility of upper layers to ensure that the flag is set if the metadata is needed. The flag limits the additional cost of metadata collecting based on demand. This prepares the VXLAN device to be steered by the routing and other subsystems which allows to support encapsulation for a large number of tunnel endpoints and tunnel ids through a single net_device which improves the scalability. It also allows for OVS to leverage this mode which in turn allows for the removal of the OVS specific VXLAN code. Because the skb is currently scrubed in vxlan_rcv(), the attachment of the new dst metadata is postponed until after scrubing which requires the temporary addition of a new member to vxlan_metadata. This member is removed again in a later commit after the indirect VXLAN receive API has been removed. Signed-off-by: Thomas Graf <tgraf@suug.ch> Signed-off-by: Pravin B Shelar <pshelar@nicira.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2015-07-21 16:43:58 +08:00
#define VXLAN_F_COLLECT_METADATA 0x2000
/* Flags that are used in the receive path. These flags must match in
* order for a socket to be shareable
*/
#define VXLAN_F_RCV_FLAGS (VXLAN_F_GBP | \
VXLAN_F_UDP_ZERO_CSUM6_RX | \
VXLAN_F_REMCSUM_RX | \
vxlan: Flow based tunneling Allows putting a VXLAN device into a new flow-based mode in which skbs with a ip_tunnel_info dst metadata attached will be encapsulated according to the instructions stored in there with the VXLAN device defaults taken into consideration. Similar on the receive side, if the VXLAN_F_COLLECT_METADATA flag is set, the packet processing will populate a ip_tunnel_info struct for each packet received and attach it to the skb using the new metadata dst. The metadata structure will contain the outer header and tunnel header fields which have been stripped off. Layers further up in the stack such as routing, tc or netfitler can later match on these fields and perform forwarding. It is the responsibility of upper layers to ensure that the flag is set if the metadata is needed. The flag limits the additional cost of metadata collecting based on demand. This prepares the VXLAN device to be steered by the routing and other subsystems which allows to support encapsulation for a large number of tunnel endpoints and tunnel ids through a single net_device which improves the scalability. It also allows for OVS to leverage this mode which in turn allows for the removal of the OVS specific VXLAN code. Because the skb is currently scrubed in vxlan_rcv(), the attachment of the new dst metadata is postponed until after scrubing which requires the temporary addition of a new member to vxlan_metadata. This member is removed again in a later commit after the indirect VXLAN receive API has been removed. Signed-off-by: Thomas Graf <tgraf@suug.ch> Signed-off-by: Pravin B Shelar <pshelar@nicira.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2015-07-21 16:43:58 +08:00
VXLAN_F_REMCSUM_NOPARTIAL | \
VXLAN_F_COLLECT_METADATA)
struct net_device *vxlan_dev_create(struct net *net, const char *name,
u8 name_assign_type, struct vxlan_config *conf);
static inline __be16 vxlan_dev_dst_port(struct vxlan_dev *vxlan,
unsigned short family)
{
#if IS_ENABLED(CONFIG_IPV6)
if (family == AF_INET6)
return inet_sk(vxlan->vn6_sock->sock->sk)->inet_sport;
#endif
return inet_sk(vxlan->vn4_sock->sock->sk)->inet_sport;
}
static inline netdev_features_t vxlan_features_check(struct sk_buff *skb,
netdev_features_t features)
{
u8 l4_hdr = 0;
if (!skb->encapsulation)
return features;
switch (vlan_get_protocol(skb)) {
case htons(ETH_P_IP):
l4_hdr = ip_hdr(skb)->protocol;
break;
case htons(ETH_P_IPV6):
l4_hdr = ipv6_hdr(skb)->nexthdr;
break;
default:
return features;;
}
if ((l4_hdr == IPPROTO_UDP) &&
(skb->inner_protocol_type != ENCAP_TYPE_ETHER ||
skb->inner_protocol != htons(ETH_P_TEB) ||
(skb_inner_mac_header(skb) - skb_transport_header(skb) !=
sizeof(struct udphdr) + sizeof(struct vxlanhdr))))
return features & ~(NETIF_F_CSUM_MASK | NETIF_F_GSO_MASK);
return features;
}
/* IP header + UDP + VXLAN + Ethernet header */
#define VXLAN_HEADROOM (20 + 8 + 8 + 14)
/* IPv6 header + UDP + VXLAN + Ethernet header */
#define VXLAN6_HEADROOM (40 + 8 + 8 + 14)
#if IS_ENABLED(CONFIG_VXLAN)
void vxlan_get_rx_port(struct net_device *netdev);
#else
static inline void vxlan_get_rx_port(struct net_device *netdev)
{
}
#endif
static inline unsigned short vxlan_get_sk_family(struct vxlan_sock *vs)
{
return vs->sock->sk->sk_family;
}
#endif