With the removal of the special treating of OVS VXLAN vports, the
indirect call to vxlan_rcv() can be avoided and the VNI member
in vxlan_metadata can be removed.
Signed-off-by: Thomas Graf <tg...@suug.ch>
---
drivers/net/vxlan.c | 225 +++++++++++++++++++++++++---------------------------
include/net/vxlan.h | 7 --
2 files changed, 107 insertions(+), 125 deletions(-)
diff --git a/drivers/net/vxlan.c b/drivers/net/vxlan.c
index b696871..9cc7d5a 100644
--- a/drivers/net/vxlan.c
+++ b/drivers/net/vxlan.c
@@ -75,7 +75,6 @@ static struct rtnl_link_ops vxlan_link_ops;
static const u8 all_zeros_mac[ETH_ALEN];
static struct vxlan_sock *vxlan_sock_add(struct net *net, __be16 port,
- vxlan_rcv_t *rcv, void *data,
bool no_share, u32 flags);
/* per-network namespace private data for this module */
@@ -1122,6 +1121,102 @@ static struct vxlanhdr *vxlan_remcsum(struct sk_buff
*skb, struct vxlanhdr *vh,
return vh;
}
+static void vxlan_rcv(struct vxlan_sock *vs, struct sk_buff *skb,
+ struct vxlan_metadata *md, __u32 vni)
+{
+ struct ip_tunnel_info *tun_info = skb_shinfo(skb)->tun_info;
+ struct iphdr *oip = NULL;
+ struct ipv6hdr *oip6 = NULL;
+ struct vxlan_dev *vxlan;
+ struct pcpu_sw_netstats *stats;
+ union vxlan_addr saddr;
+ int err = 0;
+ union vxlan_addr *remote_ip;
+
+ /* For flow based devices, map all packets to VNI 0 */
+ if (vs->flags & VXLAN_F_FLOW_BASED)
+ vni = 0;
+
+ /* Is this VNI defined? */
+ vxlan = vxlan_vs_find_vni(vs, vni);
+ if (!vxlan)
+ goto drop;
+
+ remote_ip = &vxlan->default_dst.remote_ip;
+ skb_reset_mac_header(skb);
+ skb_scrub_packet(skb, !net_eq(vxlan->net, dev_net(vxlan->dev)));
+ skb->protocol = eth_type_trans(skb, vxlan->dev);
+ skb_postpull_rcsum(skb, eth_hdr(skb), ETH_HLEN);
+
+ /* Ignore packet loops (and multicast echo) */
+ if (ether_addr_equal(eth_hdr(skb)->h_source, vxlan->dev->dev_addr))
+ goto drop;
+
+ /* Re-examine inner Ethernet packet */
+ if (remote_ip->sa.sa_family == AF_INET) {
+ oip = ip_hdr(skb);
+ saddr.sin.sin_addr.s_addr = oip->saddr;
+ saddr.sa.sa_family = AF_INET;
+
+ if (tun_info) {
+ tun_info->key.ipv4_src = oip->saddr;
+ tun_info->key.ipv4_dst = oip->daddr;
+ tun_info->key.ipv4_tos = oip->tos;
+ tun_info->key.ipv4_ttl = oip->ttl;
+ }
+#if IS_ENABLED(CONFIG_IPV6)
+ } else {
+ oip6 = ipv6_hdr(skb);
+ saddr.sin6.sin6_addr = oip6->saddr;
+ saddr.sa.sa_family = AF_INET6;
+
+ /* TODO : Fill IPv6 tunnel info */
+#endif
+ }
+
+ if ((vxlan->flags & VXLAN_F_LEARN) &&
+ vxlan_snoop(skb->dev, &saddr, eth_hdr(skb)->h_source))
+ goto drop;
+
+ skb_reset_network_header(skb);
+ if (!(vs->flags & VXLAN_F_FLOW_BASED))
+ skb->mark = md->gbp;
+
+ if (oip6)
+ err = IP6_ECN_decapsulate(oip6, skb);
+ if (oip)
+ err = IP_ECN_decapsulate(oip, skb);
+
+ if (unlikely(err)) {
+ if (log_ecn_error) {
+ if (oip6)
+ net_info_ratelimited("non-ECT from %pI6\n",
+ &oip6->saddr);
+ if (oip)
+ net_info_ratelimited("non-ECT from %pI4 with
TOS=%#x\n",
+ &oip->saddr, oip->tos);
+ }
+ if (err > 1) {
+ ++vxlan->dev->stats.rx_frame_errors;
+ ++vxlan->dev->stats.rx_errors;
+ goto drop;
+ }
+ }
+
+ stats = this_cpu_ptr(vxlan->dev->tstats);
+ u64_stats_update_begin(&stats->syncp);
+ stats->rx_packets++;
+ stats->rx_bytes += skb->len;
+ u64_stats_update_end(&stats->syncp);
+
+ netif_rx(skb);
+
+ return;
+drop:
+ /* Consume bad packet */
+ kfree_skb(skb);
+}
+
/* Callback from net/ipv4/udp.c to receive packets */
static int vxlan_udp_encap_recv(struct sock *sk, struct sk_buff *skb)
{
@@ -1226,8 +1321,7 @@ static int vxlan_udp_encap_recv(struct sock *sk, struct
sk_buff *skb)
goto bad_flags;
}
- md->vni = vxh->vx_vni;
- vs->rcv(vs, skb, md);
+ vxlan_rcv(vs, skb, md, vni >> 8);
return 0;
drop:
@@ -1244,105 +1338,6 @@ error:
return 1;
}
-static void vxlan_rcv(struct vxlan_sock *vs, struct sk_buff *skb,
- struct vxlan_metadata *md)
-{
- struct ip_tunnel_info *tun_info = skb_shinfo(skb)->tun_info;
- struct iphdr *oip = NULL;
- struct ipv6hdr *oip6 = NULL;
- struct vxlan_dev *vxlan;
- struct pcpu_sw_netstats *stats;
- union vxlan_addr saddr;
- __u32 vni;
- int err = 0;
- union vxlan_addr *remote_ip;
-
- /* For flow based devices, map all packets to VNI 0 */
- if (vs->flags & VXLAN_F_FLOW_BASED)
- vni = 0;
- else
- vni = ntohl(md->vni) >> 8;
-
- /* Is this VNI defined? */
- vxlan = vxlan_vs_find_vni(vs, vni);
- if (!vxlan)
- goto drop;
-
- remote_ip = &vxlan->default_dst.remote_ip;
- skb_reset_mac_header(skb);
- skb_scrub_packet(skb, !net_eq(vxlan->net, dev_net(vxlan->dev)));
- skb->protocol = eth_type_trans(skb, vxlan->dev);
- skb_postpull_rcsum(skb, eth_hdr(skb), ETH_HLEN);
-
- /* Ignore packet loops (and multicast echo) */
- if (ether_addr_equal(eth_hdr(skb)->h_source, vxlan->dev->dev_addr))
- goto drop;
-
- /* Re-examine inner Ethernet packet */
- if (remote_ip->sa.sa_family == AF_INET) {
- oip = ip_hdr(skb);
- saddr.sin.sin_addr.s_addr = oip->saddr;
- saddr.sa.sa_family = AF_INET;
-
- if (tun_info) {
- tun_info->key.ipv4_src = oip->saddr;
- tun_info->key.ipv4_dst = oip->daddr;
- tun_info->key.ipv4_tos = oip->tos;
- tun_info->key.ipv4_ttl = oip->ttl;
- }
-#if IS_ENABLED(CONFIG_IPV6)
- } else {
- oip6 = ipv6_hdr(skb);
- saddr.sin6.sin6_addr = oip6->saddr;
- saddr.sa.sa_family = AF_INET6;
-
- /* TODO : Fill IPv6 tunnel info */
-#endif
- }
-
- if ((vxlan->flags & VXLAN_F_LEARN) &&
- vxlan_snoop(skb->dev, &saddr, eth_hdr(skb)->h_source))
- goto drop;
-
- skb_reset_network_header(skb);
- if (!(vs->flags & VXLAN_F_FLOW_BASED))
- skb->mark = md->gbp;
-
- if (oip6)
- err = IP6_ECN_decapsulate(oip6, skb);
- if (oip)
- err = IP_ECN_decapsulate(oip, skb);
-
- if (unlikely(err)) {
- if (log_ecn_error) {
- if (oip6)
- net_info_ratelimited("non-ECT from %pI6\n",
- &oip6->saddr);
- if (oip)
- net_info_ratelimited("non-ECT from %pI4 with
TOS=%#x\n",
- &oip->saddr, oip->tos);
- }
- if (err > 1) {
- ++vxlan->dev->stats.rx_frame_errors;
- ++vxlan->dev->stats.rx_errors;
- goto drop;
- }
- }
-
- stats = this_cpu_ptr(vxlan->dev->tstats);
- u64_stats_update_begin(&stats->syncp);
- stats->rx_packets++;
- stats->rx_bytes += skb->len;
- u64_stats_update_end(&stats->syncp);
-
- netif_rx(skb);
-
- return;
-drop:
- /* Consume bad packet */
- kfree_skb(skb);
-}
-
static int arp_reduce(struct net_device *dev, struct sk_buff *skb)
{
struct vxlan_dev *vxlan = netdev_priv(dev);
@@ -1681,7 +1676,7 @@ static int vxlan6_xmit_skb(struct dst_entry *dst, struct
sock *sk,
struct sk_buff *skb,
struct net_device *dev, struct in6_addr *saddr,
struct in6_addr *daddr, __u8 prio, __u8 ttl,
- __be16 src_port, __be16 dst_port,
+ __be16 src_port, __be16 dst_port, __u32 vni,
struct vxlan_metadata *md, bool xnet, u32 vxflags)
{
struct vxlanhdr *vxh;
@@ -1731,7 +1726,7 @@ static int vxlan6_xmit_skb(struct dst_entry *dst, struct
sock *sk,
vxh = (struct vxlanhdr *) __skb_push(skb, sizeof(*vxh));
vxh->vx_flags = htonl(VXLAN_HF_VNI);
- vxh->vx_vni = md->vni;
+ vxh->vx_vni = vni;
if (type & SKB_GSO_TUNNEL_REMCSUM) {
u32 data = (skb_checksum_start_offset(skb) - hdrlen) >>
@@ -1766,7 +1761,7 @@ err:
static int vxlan_xmit_skb(struct rtable *rt, struct sock *sk, struct sk_buff
*skb,
__be32 src, __be32 dst, __u8 tos, __u8 ttl, __be16 df,
- __be16 src_port, __be16 dst_port,
+ __be16 src_port, __be16 dst_port, __u32 vni,
struct vxlan_metadata *md, bool xnet, u32 vxflags)
{
struct vxlanhdr *vxh;
@@ -1810,7 +1805,7 @@ static int vxlan_xmit_skb(struct rtable *rt, struct sock
*sk, struct sk_buff *sk
vxh = (struct vxlanhdr *) __skb_push(skb, sizeof(*vxh));
vxh->vx_flags = htonl(VXLAN_HF_VNI);
- vxh->vx_vni = md->vni;
+ vxh->vx_vni = vni;
if (type & SKB_GSO_TUNNEL_REMCSUM) {
u32 data = (skb_checksum_start_offset(skb) - hdrlen) >>
@@ -2002,10 +1997,9 @@ static void vxlan_xmit_one(struct sk_buff *skb, struct
net_device *dev,
tos = ip_tunnel_ecn_encap(tos, old_iph, skb);
ttl = ttl ? : ip4_dst_hoplimit(&rt->dst);
- md->vni = htonl(vni << 8);
err = vxlan_xmit_skb(rt, sk, skb, fl4.saddr,
dst->sin.sin_addr.s_addr, tos, ttl, df,
- src_port, dst_port, md,
+ src_port, dst_port, htonl(vni << 8), md,
!net_eq(vxlan->net, dev_net(vxlan->dev)),
flags);
if (err < 0) {
@@ -2060,11 +2054,10 @@ static void vxlan_xmit_one(struct sk_buff *skb, struct
net_device *dev,
}
ttl = ttl ? : ip6_dst_hoplimit(ndst);
- md->vni = htonl(vni << 8);
md->gbp = skb->mark;
err = vxlan6_xmit_skb(ndst, sk, skb, dev, &fl6.saddr,
&fl6.daddr,
- 0, ttl, src_port, dst_port, md,
+ 0, ttl, src_port, dst_port, htonl(vni <<
8), md,
!net_eq(vxlan->net, dev_net(vxlan->dev)),
vxlan->flags);
#endif
@@ -2257,8 +2250,8 @@ static int vxlan_open(struct net_device *dev)
struct vxlan_sock *vs;
int ret = 0;
- vs = vxlan_sock_add(vxlan->net, vxlan->cfg.dst_port, vxlan_rcv,
- NULL, vxlan->cfg.no_share, vxlan->flags);
+ vs = vxlan_sock_add(vxlan->net, vxlan->cfg.dst_port,
+ vxlan->cfg.no_share, vxlan->flags);
if (IS_ERR(vs))
return PTR_ERR(vs);
@@ -2557,7 +2550,6 @@ static struct socket *vxlan_create_sock(struct net *net,
bool ipv6,
/* Create new listen socket if needed */
static struct vxlan_sock *vxlan_socket_create(struct net *net, __be16 port,
- vxlan_rcv_t *rcv, void *data,
u32 flags)
{
struct vxlan_net *vn = net_generic(net, vxlan_net_id);
@@ -2586,8 +2578,6 @@ static struct vxlan_sock *vxlan_socket_create(struct net
*net, __be16 port,
vs->sock = sock;
atomic_set(&vs->refcnt, 1);
- vs->rcv = rcv;
- vs->data = data;
vs->flags = (flags & VXLAN_F_RCV_FLAGS);
/* Initialize the vxlan udp offloads structure */
@@ -2612,7 +2602,6 @@ static struct vxlan_sock *vxlan_socket_create(struct net
*net, __be16 port,
}
static struct vxlan_sock *vxlan_sock_add(struct net *net, __be16 port,
- vxlan_rcv_t *rcv, void *data,
bool no_share, u32 flags)
{
struct vxlan_net *vn = net_generic(net, vxlan_net_id);
@@ -2623,7 +2612,7 @@ static struct vxlan_sock *vxlan_sock_add(struct net *net,
__be16 port,
spin_lock(&vn->sock_lock);
vs = vxlan_find_sock(net, ipv6 ? AF_INET6 : AF_INET, port,
flags);
- if (vs && vs->rcv == rcv) {
+ if (vs) {
if (!atomic_add_unless(&vs->refcnt, 1, 0))
vs = ERR_PTR(-EBUSY);
spin_unlock(&vn->sock_lock);
@@ -2632,7 +2621,7 @@ static struct vxlan_sock *vxlan_sock_add(struct net *net,
__be16 port,
spin_unlock(&vn->sock_lock);
}
- return vxlan_socket_create(net, port, rcv, data, flags);
+ return vxlan_socket_create(net, port, flags);
}
static int vxlan_dev_configure(struct net *src_net, struct net_device *dev,
diff --git a/include/net/vxlan.h b/include/net/vxlan.h
index d3ce81f..c157c5d 100644
--- a/include/net/vxlan.h
+++ b/include/net/vxlan.h
@@ -100,19 +100,12 @@ struct vxlanhdr {
#define FDB_HASH_SIZE (1<<FDB_HASH_BITS)
struct vxlan_metadata {
- __be32 vni;
u32 gbp;
};
-struct vxlan_sock;
-typedef void (vxlan_rcv_t)(struct vxlan_sock *vh, struct sk_buff *skb,
- struct vxlan_metadata *md);
-
/* per UDP socket information */
struct vxlan_sock {
struct hlist_node hlist;
- vxlan_rcv_t *rcv;
- void *data;
struct work_struct del_work;
struct socket *sock;
struct rcu_head rcu;
--
2.3.5
--
To unsubscribe from this list: send the line "unsubscribe netdev" in
the body of a message to majord...@vger.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
