OpenCloudOS-Kernel/include/net/dst_metadata.h

160 lines
3.6 KiB
C
Raw Normal View History

#ifndef __NET_DST_METADATA_H
#define __NET_DST_METADATA_H 1
#include <linux/skbuff.h>
#include <net/ip_tunnels.h>
#include <net/dst.h>
struct metadata_dst {
struct dst_entry dst;
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
union {
struct ip_tunnel_info tun_info;
} u;
};
static inline struct metadata_dst *skb_metadata_dst(struct sk_buff *skb)
{
struct metadata_dst *md_dst = (struct metadata_dst *) skb_dst(skb);
if (md_dst && md_dst->dst.flags & DST_METADATA)
return md_dst;
return NULL;
}
static inline struct ip_tunnel_info *skb_tunnel_info(struct sk_buff *skb)
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
{
struct metadata_dst *md_dst = skb_metadata_dst(skb);
struct dst_entry *dst;
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
if (md_dst)
return &md_dst->u.tun_info;
dst = skb_dst(skb);
if (dst && dst->lwtstate)
return lwt_tun_info(dst->lwtstate);
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
return NULL;
}
static inline bool skb_valid_dst(const struct sk_buff *skb)
{
struct dst_entry *dst = skb_dst(skb);
return dst && !(dst->flags & DST_METADATA);
}
static inline int skb_metadata_dst_cmp(const struct sk_buff *skb_a,
const struct sk_buff *skb_b)
{
const struct metadata_dst *a, *b;
if (!(skb_a->_skb_refdst | skb_b->_skb_refdst))
return 0;
a = (const struct metadata_dst *) skb_dst(skb_a);
b = (const struct metadata_dst *) skb_dst(skb_b);
if (!a != !b || a->u.tun_info.options_len != b->u.tun_info.options_len)
return 1;
return memcmp(&a->u.tun_info, &b->u.tun_info,
sizeof(a->u.tun_info) + a->u.tun_info.options_len);
}
struct metadata_dst *metadata_dst_alloc(u8 optslen, gfp_t flags);
struct metadata_dst __percpu *metadata_dst_alloc_percpu(u8 optslen, gfp_t flags);
static inline struct metadata_dst *tun_rx_dst(int md_size)
{
struct metadata_dst *tun_dst;
tun_dst = metadata_dst_alloc(md_size, GFP_ATOMIC);
if (!tun_dst)
return NULL;
tun_dst->u.tun_info.options_len = 0;
tun_dst->u.tun_info.mode = 0;
return tun_dst;
}
static inline struct metadata_dst *tun_dst_unclone(struct sk_buff *skb)
{
struct metadata_dst *md_dst = skb_metadata_dst(skb);
int md_size;
struct metadata_dst *new_md;
if (!md_dst)
return ERR_PTR(-EINVAL);
md_size = md_dst->u.tun_info.options_len;
new_md = metadata_dst_alloc(md_size, GFP_ATOMIC);
if (!new_md)
return ERR_PTR(-ENOMEM);
memcpy(&new_md->u.tun_info, &md_dst->u.tun_info,
sizeof(struct ip_tunnel_info) + md_size);
skb_dst_drop(skb);
dst_hold(&new_md->dst);
skb_dst_set(skb, &new_md->dst);
return new_md;
}
static inline struct ip_tunnel_info *skb_tunnel_info_unclone(struct sk_buff *skb)
{
struct metadata_dst *dst;
dst = tun_dst_unclone(skb);
if (IS_ERR(dst))
return NULL;
return &dst->u.tun_info;
}
static inline struct metadata_dst *ip_tun_rx_dst(struct sk_buff *skb,
__be16 flags,
__be64 tunnel_id,
int md_size)
{
const struct iphdr *iph = ip_hdr(skb);
struct metadata_dst *tun_dst;
tun_dst = tun_rx_dst(md_size);
if (!tun_dst)
return NULL;
ip_tunnel_key_init(&tun_dst->u.tun_info.key,
iph->saddr, iph->daddr, iph->tos, iph->ttl,
0, 0, tunnel_id, flags);
return tun_dst;
}
static inline struct metadata_dst *ipv6_tun_rx_dst(struct sk_buff *skb,
__be16 flags,
__be64 tunnel_id,
int md_size)
{
const struct ipv6hdr *ip6h = ipv6_hdr(skb);
struct metadata_dst *tun_dst;
struct ip_tunnel_info *info;
tun_dst = tun_rx_dst(md_size);
if (!tun_dst)
return NULL;
info = &tun_dst->u.tun_info;
info->mode = IP_TUNNEL_INFO_IPV6;
info->key.tun_flags = flags;
info->key.tun_id = tunnel_id;
info->key.tp_src = 0;
info->key.tp_dst = 0;
info->key.u.ipv6.src = ip6h->saddr;
info->key.u.ipv6.dst = ip6h->daddr;
info->key.tos = ipv6_get_dsfield(ip6h);
info->key.ttl = ip6h->hop_limit;
return tun_dst;
}
#endif /* __NET_DST_METADATA_H */