* notification if the %OVS_ACTION_ATTR_USERSPACE action specified an
* %OVS_USERSPACE_ATTR_USERDATA attribute, with the same length and content
* specified there.
+ * @OVS_PACKET_ATTR_EGRESS_TUN_KEY: Present for an %OVS_PACKET_CMD_ACTION
+ * notification if the %OVS_ACTION_ATTR_USERSPACE action specified an
+ * %OVS_USERSPACE_ATTR_EGRESS_TUN_PORT attribute, which is sent only if the
+ * output port is actually a tunnel port. Contains the output tunnel key
+ * extracted from the packet as nested %OVS_TUNNEL_KEY_ATTR_* attributes.
*
* These attributes follow the &struct ovs_header within the Generic Netlink
* payload for %OVS_PACKET_* commands.
OVS_PACKET_ATTR_KEY, /* Nested OVS_KEY_ATTR_* attributes. */
OVS_PACKET_ATTR_ACTIONS, /* Nested OVS_ACTION_ATTR_* attributes. */
OVS_PACKET_ATTR_USERDATA, /* OVS_ACTION_ATTR_USERSPACE arg. */
+ OVS_PACKET_ATTR_EGRESS_TUN_KEY, /* Nested OVS_TUNNEL_KEY_ATTR_*
+ attributes. */
__OVS_PACKET_ATTR_MAX
};
OVS_TUNNEL_KEY_ATTR_CSUM, /* No argument. CSUM packet. */
OVS_TUNNEL_KEY_ATTR_OAM, /* No argument. OAM frame. */
OVS_TUNNEL_KEY_ATTR_GENEVE_OPTS, /* Array of Geneve options. */
+ OVS_TUNNEL_KEY_ATTR_TP_SRC, /* be16 src Transport Port. */
+ OVS_TUNNEL_KEY_ATTR_TP_DST, /* be16 dst Transport Port. */
__OVS_TUNNEL_KEY_ATTR_MAX
};
* message should be sent. Required.
* @OVS_USERSPACE_ATTR_USERDATA: If present, its variable-length argument is
* copied to the %OVS_PACKET_CMD_ACTION message as %OVS_PACKET_ATTR_USERDATA.
+ * @OVS_USERSPACE_ATTR_EGRESS_TUN_PORT: If present, u32 output port to get
+ * tunnel info.
*/
enum ovs_userspace_attr {
OVS_USERSPACE_ATTR_UNSPEC,
OVS_USERSPACE_ATTR_PID, /* u32 Netlink PID to receive upcalls. */
OVS_USERSPACE_ATTR_USERDATA, /* Optional user-specified cookie. */
+ OVS_USERSPACE_ATTR_EGRESS_TUN_PORT, /* Optional, u32 output port
+ * to get tunnel info. */
__OVS_USERSPACE_ATTR_MAX
};
static int output_userspace(struct datapath *dp, struct sk_buff *skb,
struct sw_flow_key *key, const struct nlattr *attr)
{
+ struct ovs_tunnel_info info;
struct dp_upcall_info upcall;
const struct nlattr *a;
int rem;
upcall.key = key;
upcall.userdata = NULL;
upcall.portid = 0;
+ upcall.egress_tun_info = NULL;
for (a = nla_data(attr), rem = nla_len(attr); rem > 0;
a = nla_next(a, &rem)) {
case OVS_USERSPACE_ATTR_PID:
upcall.portid = nla_get_u32(a);
break;
+
+ case OVS_USERSPACE_ATTR_EGRESS_TUN_PORT: {
+ /* Get out tunnel info. */
+ struct vport *vport;
+
+ vport = ovs_vport_rcu(dp, nla_get_u32(a));
+ if (vport) {
+ int err;
+
+ err = ovs_vport_get_egress_tun_info(vport, skb,
+ &info);
+ if (!err)
+ upcall.egress_tun_info = &info;
+ }
+ break;
}
+
+ } /* End of switch. */
}
return ovs_dp_upcall(dp, skb, &upcall);
upcall.key = key;
upcall.userdata = NULL;
upcall.portid = ovs_vport_find_upcall_portid(p, skb);
+ upcall.egress_tun_info = NULL;
error = ovs_dp_upcall(dp, skb, &upcall);
if (unlikely(error))
kfree_skb(skb);
return err;
}
-static size_t upcall_msg_size(const struct nlattr *userdata,
+static size_t upcall_msg_size(const struct dp_upcall_info *upcall_info,
unsigned int hdrlen)
{
size_t size = NLMSG_ALIGN(sizeof(struct ovs_header))
+ nla_total_size(ovs_key_attr_size()); /* OVS_PACKET_ATTR_KEY */
/* OVS_PACKET_ATTR_USERDATA */
- if (userdata)
- size += NLA_ALIGN(userdata->nla_len);
+ if (upcall_info->userdata)
+ size += NLA_ALIGN(upcall_info->userdata->nla_len);
+
+ /* OVS_PACKET_ATTR_EGRESS_TUN_KEY */
+ if (upcall_info->egress_tun_info)
+ size += nla_total_size(ovs_tun_key_attr_size());
return size;
}
else
hlen = skb->len;
- len = upcall_msg_size(upcall_info->userdata, hlen);
+ len = upcall_msg_size(upcall_info, hlen);
user_skb = genlmsg_new_unicast(len, &info, GFP_ATOMIC);
if (!user_skb) {
err = -ENOMEM;
nla_len(upcall_info->userdata),
nla_data(upcall_info->userdata));
+ if (upcall_info->egress_tun_info) {
+ nla = nla_nest_start(user_skb, OVS_PACKET_ATTR_EGRESS_TUN_KEY);
+ err = ovs_nla_put_egress_tunnel_key(user_skb,
+ upcall_info->egress_tun_info);
+ BUG_ON(err);
+ nla_nest_end(user_skb, nla);
+ }
+
/* Only reserve room for attribute header, packet data is added
* in skb_zerocopy() */
if (!(nla = nla_reserve(user_skb, OVS_PACKET_ATTR_PACKET, 0))) {
* @pid: Netlink PID to which packet should be sent. If @pid is 0 then no
* packet is sent and the packet is accounted in the datapath's @n_lost
* counter.
+ * @egress_tun_info: If nonnull, becomes %OVS_PACKET_ATTR_EGRESS_TUN_KEY.
*/
struct dp_upcall_info {
u8 cmd;
const struct sw_flow_key *key;
const struct nlattr *userdata;
u32 portid;
+ const struct ovs_tunnel_info *egress_tun_info;
};
/**
/* Used to memset ovs_key_ipv4_tunnel padding. */
#define OVS_TUNNEL_KEY_SIZE \
- (offsetof(struct ovs_key_ipv4_tunnel, ipv4_ttl) + \
- FIELD_SIZEOF(struct ovs_key_ipv4_tunnel, ipv4_ttl))
+ (offsetof(struct ovs_key_ipv4_tunnel, tp_dst) + \
+ FIELD_SIZEOF(struct ovs_key_ipv4_tunnel, tp_dst))
struct ovs_key_ipv4_tunnel {
__be64 tun_id;
__be16 tun_flags;
u8 ipv4_tos;
u8 ipv4_ttl;
+ __be16 tp_src;
+ __be16 tp_dst;
} __packed __aligned(4); /* Minimize padding. */
struct ovs_tunnel_info {
FIELD_SIZEOF(struct sw_flow_key, tun_opts) - \
opt_len))
-static inline void ovs_flow_tun_info_init(struct ovs_tunnel_info *tun_info,
- const struct iphdr *iph,
- __be64 tun_id, __be16 tun_flags,
- struct geneve_opt *opts,
- u8 opts_len)
+static inline void __ovs_flow_tun_info_init(struct ovs_tunnel_info *tun_info,
+ __be32 saddr, __be32 daddr,
+ u8 tos, u8 ttl,
+ __be16 tp_src,
+ __be16 tp_dst,
+ __be64 tun_id,
+ __be16 tun_flags,
+ struct geneve_opt *opts,
+ u8 opts_len)
{
tun_info->tunnel.tun_id = tun_id;
- tun_info->tunnel.ipv4_src = iph->saddr;
- tun_info->tunnel.ipv4_dst = iph->daddr;
- tun_info->tunnel.ipv4_tos = iph->tos;
- tun_info->tunnel.ipv4_ttl = iph->ttl;
+ tun_info->tunnel.ipv4_src = saddr;
+ tun_info->tunnel.ipv4_dst = daddr;
+ tun_info->tunnel.ipv4_tos = tos;
+ tun_info->tunnel.ipv4_ttl = ttl;
tun_info->tunnel.tun_flags = tun_flags;
- /* clear struct padding. */
- memset((unsigned char *)&tun_info->tunnel + OVS_TUNNEL_KEY_SIZE, 0,
- sizeof(tun_info->tunnel) - OVS_TUNNEL_KEY_SIZE);
+ /* For the tunnel types on the top of IPsec, the tp_src and tp_dst of
+ * the upper tunnel are used.
+ * E.g: GRE over IPSEC, the tp_src and tp_port are zero.
+ */
+ tun_info->tunnel.tp_src = tp_src;
+ tun_info->tunnel.tp_dst = tp_dst;
+
+ /* Clear struct padding. */
+ if (sizeof(tun_info->tunnel) != OVS_TUNNEL_KEY_SIZE)
+ memset((unsigned char *)&tun_info->tunnel + OVS_TUNNEL_KEY_SIZE,
+ 0, sizeof(tun_info->tunnel) - OVS_TUNNEL_KEY_SIZE);
tun_info->options = opts;
tun_info->options_len = opts_len;
}
+static inline void ovs_flow_tun_info_init(struct ovs_tunnel_info *tun_info,
+ const struct iphdr *iph,
+ __be16 tp_src,
+ __be16 tp_dst,
+ __be64 tun_id,
+ __be16 tun_flags,
+ struct geneve_opt *opts,
+ u8 opts_len)
+{
+ __ovs_flow_tun_info_init(tun_info, iph->saddr, iph->daddr,
+ iph->tos, iph->ttl,
+ tp_src, tp_dst,
+ tun_id, tun_flags,
+ opts, opts_len);
+}
+
+#define OVS_SW_FLOW_KEY_METADATA_SIZE \
+ (offsetof(struct sw_flow_key, recirc_id) + \
+ FIELD_SIZEOF(struct sw_flow_key, recirc_id))
+
struct sw_flow_key {
u8 tun_opts[255];
u8 tun_opts_len;
return true;
}
+size_t ovs_tun_key_attr_size(void)
+{
+ /* Whenever adding new OVS_TUNNEL_KEY_ FIELDS, we should consider
+ * updating this function.
+ */
+ return nla_total_size(8) /* OVS_TUNNEL_KEY_ATTR_ID */
+ + nla_total_size(4) /* OVS_TUNNEL_KEY_ATTR_IPV4_SRC */
+ + nla_total_size(4) /* OVS_TUNNEL_KEY_ATTR_IPV4_DST */
+ + nla_total_size(1) /* OVS_TUNNEL_KEY_ATTR_TOS */
+ + nla_total_size(1) /* OVS_TUNNEL_KEY_ATTR_TTL */
+ + nla_total_size(0) /* OVS_TUNNEL_KEY_ATTR_DONT_FRAGMENT */
+ + nla_total_size(0) /* OVS_TUNNEL_KEY_ATTR_CSUM */
+ + nla_total_size(0) /* OVS_TUNNEL_KEY_ATTR_OAM */
+ + nla_total_size(256) /* OVS_TUNNEL_KEY_ATTR_GENEVE_OPTS */
+ + nla_total_size(2) /* OVS_TUNNEL_KEY_ATTR_TP_SRC */
+ + nla_total_size(2); /* OVS_TUNNEL_KEY_ATTR_TP_DST */
+}
+
size_t ovs_key_attr_size(void)
{
/* Whenever adding new OVS_KEY_ FIELDS, we should consider
return nla_total_size(4) /* OVS_KEY_ATTR_PRIORITY */
+ nla_total_size(0) /* OVS_KEY_ATTR_TUNNEL */
- + nla_total_size(8) /* OVS_TUNNEL_KEY_ATTR_ID */
- + nla_total_size(4) /* OVS_TUNNEL_KEY_ATTR_IPV4_SRC */
- + nla_total_size(4) /* OVS_TUNNEL_KEY_ATTR_IPV4_DST */
- + nla_total_size(1) /* OVS_TUNNEL_KEY_ATTR_TOS */
- + nla_total_size(1) /* OVS_TUNNEL_KEY_ATTR_TTL */
- + nla_total_size(0) /* OVS_TUNNEL_KEY_ATTR_DONT_FRAGMENT */
- + nla_total_size(0) /* OVS_TUNNEL_KEY_ATTR_CSUM */
- + nla_total_size(0) /* OVS_TUNNEL_KEY_ATTR_OAM */
- + nla_total_size(256) /* OVS_TUNNEL_KEY_ATTR_GENEVE_OPTS */
+ + ovs_tun_key_attr_size()
+ nla_total_size(4) /* OVS_KEY_ATTR_IN_PORT */
+ nla_total_size(4) /* OVS_KEY_ATTR_SKB_MARK */
+ nla_total_size(4) /* OVS_KEY_ATTR_DP_HASH */
[OVS_TUNNEL_KEY_ATTR_TTL] = 1,
[OVS_TUNNEL_KEY_ATTR_DONT_FRAGMENT] = 0,
[OVS_TUNNEL_KEY_ATTR_CSUM] = 0,
+ [OVS_TUNNEL_KEY_ATTR_TP_SRC] = sizeof(u16),
+ [OVS_TUNNEL_KEY_ATTR_TP_DST] = sizeof(u16),
[OVS_TUNNEL_KEY_ATTR_OAM] = 0,
[OVS_TUNNEL_KEY_ATTR_GENEVE_OPTS] = -1,
};
case OVS_TUNNEL_KEY_ATTR_CSUM:
tun_flags |= TUNNEL_CSUM;
break;
+ case OVS_TUNNEL_KEY_ATTR_TP_SRC:
+ SW_FLOW_KEY_PUT(match, tun_key.tp_src,
+ nla_get_be16(a), is_mask);
+ break;
+ case OVS_TUNNEL_KEY_ATTR_TP_DST:
+ SW_FLOW_KEY_PUT(match, tun_key.tp_dst,
+ nla_get_be16(a), is_mask);
+ break;
case OVS_TUNNEL_KEY_ATTR_OAM:
tun_flags |= TUNNEL_OAM;
break;
if ((output->tun_flags & TUNNEL_CSUM) &&
nla_put_flag(skb, OVS_TUNNEL_KEY_ATTR_CSUM))
return -EMSGSIZE;
+ if (output->tp_src &&
+ nla_put_be16(skb, OVS_TUNNEL_KEY_ATTR_TP_SRC, output->tp_src))
+ return -EMSGSIZE;
+ if (output->tp_dst &&
+ nla_put_be16(skb, OVS_TUNNEL_KEY_ATTR_TP_DST, output->tp_dst))
+ return -EMSGSIZE;
if ((output->tun_flags & TUNNEL_OAM) &&
nla_put_flag(skb, OVS_TUNNEL_KEY_ATTR_OAM))
return -EMSGSIZE;
return 0;
}
-
static int ipv4_tun_to_nlattr(struct sk_buff *skb,
const struct ovs_key_ipv4_tunnel *output,
const struct geneve_opt *tun_opts,
return 0;
}
+int ovs_nla_put_egress_tunnel_key(struct sk_buff *skb,
+ const struct ovs_tunnel_info *egress_tun_info)
+{
+ return __ipv4_tun_to_nlattr(skb, &egress_tun_info->tunnel,
+ egress_tun_info->options,
+ egress_tun_info->options_len);
+}
+
static int metadata_from_nlattrs(struct sw_flow_match *match, u64 *attrs,
const struct nlattr **a, bool is_mask)
{
static const struct nla_policy userspace_policy[OVS_USERSPACE_ATTR_MAX + 1] = {
[OVS_USERSPACE_ATTR_PID] = {.type = NLA_U32 },
[OVS_USERSPACE_ATTR_USERDATA] = {.type = NLA_UNSPEC },
+ [OVS_USERSPACE_ATTR_EGRESS_TUN_PORT] = {.type = NLA_U32 },
};
struct nlattr *a[OVS_USERSPACE_ATTR_MAX + 1];
int error;
#include "flow.h"
+size_t ovs_tun_key_attr_size(void);
size_t ovs_key_attr_size(void);
void ovs_match_init(struct sw_flow_match *match,
int ovs_nla_get_match(struct sw_flow_match *match,
const struct nlattr *,
const struct nlattr *);
+int ovs_nla_put_egress_tunnel_key(struct sk_buff *,
+ const struct ovs_tunnel_info *);
int ovs_nla_copy_actions(const struct nlattr *attr,
const struct sw_flow_key *key,
key = vni_to_tunnel_id(geneveh->vni);
- ovs_flow_tun_info_init(&tun_info, ip_hdr(skb), key, flags,
+ ovs_flow_tun_info_init(&tun_info, ip_hdr(skb),
+ udp_hdr(skb)->source, udp_hdr(skb)->dest,
+ key, flags,
geneveh->options, opts_len);
ovs_vport_receive(vport, skb, &tun_info);
return geneve_port->name;
}
+static int geneve_get_egress_tun_info(struct vport *vport, struct sk_buff *skb,
+ struct ovs_tunnel_info *egress_tun_info)
+{
+ struct geneve_port *geneve_port = geneve_vport(vport);
+ struct net *net = ovs_dp_get_net(vport->dp);
+ __be16 dport = inet_sk(geneve_port->gs->sock->sk)->inet_sport;
+ __be16 sport = udp_flow_src_port(net, skb, 1, USHRT_MAX, true);
+
+ /* Get tp_src and tp_dst, refert to geneve_build_header().
+ */
+ return ovs_tunnel_get_egress_info(egress_tun_info,
+ ovs_dp_get_net(vport->dp),
+ OVS_CB(skb)->egress_tun_info,
+ IPPROTO_UDP, skb->mark, sport, dport);
+}
+
static struct vport_ops ovs_geneve_vport_ops = {
.type = OVS_VPORT_TYPE_GENEVE,
.create = geneve_tnl_create,
.get_options = geneve_get_options,
.send = geneve_tnl_send,
.owner = THIS_MODULE,
+ .get_egress_tun_info = geneve_get_egress_tun_info,
};
static int __init ovs_geneve_tnl_init(void)
return PACKET_REJECT;
key = key_to_tunnel_id(tpi->key, tpi->seq);
- ovs_flow_tun_info_init(&tun_info, ip_hdr(skb), key,
+ ovs_flow_tun_info_init(&tun_info, ip_hdr(skb), 0, 0, key,
filter_tnl_flags(tpi->flags), NULL, 0);
ovs_vport_receive(vport, skb, &tun_info);
gre_exit();
}
+static int gre_get_egress_tun_info(struct vport *vport, struct sk_buff *skb,
+ struct ovs_tunnel_info *egress_tun_info)
+{
+ return ovs_tunnel_get_egress_info(egress_tun_info,
+ ovs_dp_get_net(vport->dp),
+ OVS_CB(skb)->egress_tun_info,
+ IPPROTO_GRE, skb->mark, 0, 0);
+}
+
static struct vport_ops ovs_gre_vport_ops = {
.type = OVS_VPORT_TYPE_GRE,
.create = gre_create,
.destroy = gre_tnl_destroy,
.get_name = gre_get_name,
.send = gre_tnl_send,
+ .get_egress_tun_info = gre_get_egress_tun_info,
.owner = THIS_MODULE,
};
/* Save outer tunnel values */
iph = ip_hdr(skb);
key = cpu_to_be64(ntohl(vx_vni) >> 8);
- ovs_flow_tun_info_init(&tun_info, iph, key, TUNNEL_KEY, NULL, 0);
+ ovs_flow_tun_info_init(&tun_info, iph,
+ udp_hdr(skb)->source, udp_hdr(skb)->dest,
+ key, TUNNEL_KEY, NULL, 0);
ovs_vport_receive(vport, skb, &tun_info);
}
return err;
}
+static int vxlan_get_egress_tun_info(struct vport *vport, struct sk_buff *skb,
+ struct ovs_tunnel_info *egress_tun_info)
+{
+ struct net *net = ovs_dp_get_net(vport->dp);
+ struct vxlan_port *vxlan_port = vxlan_vport(vport);
+ __be16 dst_port = inet_sk(vxlan_port->vs->sock->sk)->inet_sport;
+ __be16 src_port;
+ int port_min;
+ int port_max;
+
+ inet_get_local_port_range(net, &port_min, &port_max);
+ src_port = udp_flow_src_port(net, skb, 0, 0, true);
+
+ return ovs_tunnel_get_egress_info(egress_tun_info, net,
+ OVS_CB(skb)->egress_tun_info,
+ IPPROTO_UDP, skb->mark,
+ src_port, dst_port);
+}
+
static const char *vxlan_get_name(const struct vport *vport)
{
struct vxlan_port *vxlan_port = vxlan_vport(vport);
.get_name = vxlan_get_name,
.get_options = vxlan_get_options,
.send = vxlan_tnl_send,
+ .get_egress_tun_info = vxlan_get_egress_tun_info,
.owner = THIS_MODULE,
};
call_rcu(&vport->rcu, free_vport_rcu);
}
EXPORT_SYMBOL_GPL(ovs_vport_deferred_free);
+
+int ovs_tunnel_get_egress_info(struct ovs_tunnel_info *egress_tun_info,
+ struct net *net,
+ const struct ovs_tunnel_info *tun_info,
+ u8 ipproto,
+ u32 skb_mark,
+ __be16 tp_src,
+ __be16 tp_dst)
+{
+ const struct ovs_key_ipv4_tunnel *tun_key;
+ struct rtable *rt;
+ struct flowi4 fl;
+
+ if (unlikely(!tun_info))
+ return -EINVAL;
+
+ tun_key = &tun_info->tunnel;
+
+ /* Route lookup to get srouce IP address.
+ * The process may need to be changed if the corresponding process
+ * in vports ops changed.
+ */
+ memset(&fl, 0, sizeof(fl));
+ fl.daddr = tun_key->ipv4_dst;
+ fl.saddr = tun_key->ipv4_src;
+ fl.flowi4_tos = RT_TOS(tun_key->ipv4_tos);
+ fl.flowi4_mark = skb_mark;
+ fl.flowi4_proto = IPPROTO_GRE;
+
+ rt = ip_route_output_key(net, &fl);
+ if (IS_ERR(rt))
+ return PTR_ERR(rt);
+
+ ip_rt_put(rt);
+
+ /* Generate egress_tun_info based on tun_info,
+ * saddr, tp_src and tp_dst
+ */
+ __ovs_flow_tun_info_init(egress_tun_info,
+ fl.saddr, tun_key->ipv4_dst,
+ tun_key->ipv4_tos,
+ tun_key->ipv4_ttl,
+ tp_src, tp_dst,
+ tun_key->tun_id,
+ tun_key->tun_flags,
+ tun_info->options,
+ tun_info->options_len);
+
+ return 0;
+}
+EXPORT_SYMBOL_GPL(ovs_tunnel_get_egress_info);
+
+int ovs_vport_get_egress_tun_info(struct vport *vport, struct sk_buff *skb,
+ struct ovs_tunnel_info *info)
+{
+ /* get_egress_tun_info() is only implemented on tunnel ports. */
+ if (unlikely(!vport->ops->get_egress_tun_info))
+ return -EINVAL;
+
+ return vport->ops->get_egress_tun_info(vport, skb, info);
+}
int ovs_vport_send(struct vport *, struct sk_buff *);
+int ovs_tunnel_get_egress_info(struct ovs_tunnel_info *egress_tun_info,
+ struct net *net,
+ const struct ovs_tunnel_info *tun_info,
+ u8 ipproto,
+ u32 skb_mark,
+ __be16 tp_src,
+ __be16 tp_dst);
+int ovs_vport_get_egress_tun_info(struct vport *vport, struct sk_buff *skb,
+ struct ovs_tunnel_info *info);
+
/* The following definitions are for implementers of vport devices: */
struct vport_err_stats {
* @get_name: Get the device's name.
* @send: Send a packet on the device. Returns the length of the packet sent,
* zero for dropped packets or negative for error.
+ * @get_egress_tun_info: Get the egress tunnel 5-tuple and other info for
+ * a packet.
*/
struct vport_ops {
enum ovs_vport_type type;
const char *(*get_name)(const struct vport *);
int (*send)(struct vport *, struct sk_buff *);
+ int (*get_egress_tun_info)(struct vport *, struct sk_buff *,
+ struct ovs_tunnel_info *);
struct module *owner;
struct list_head list;
projects / users / willy / pagecache.git / commitdiff