[<prev] [next>] [thread-next>] [day] [month] [year] [list]
Message-Id: <1375312469-18623-1-git-send-email-pshelar@nicira.com>
Date: Wed, 31 Jul 2013 16:14:29 -0700
From: Pravin B Shelar <pshelar@...ira.com>
To: netdev@...r.kernel.org
Cc: stephen@...workplumber.org, Pravin B Shelar <pshelar@...ira.com>
Subject: [PATCH net-next v5 2/7] vxlan: Restructure vxlan receive for multiple protocols.
Once we have ovs-vxlan functionality, one UDP port can be assigned
to kernel-vxlan or ovs-vxlan port. Therefore following patch adds
vxlan demux functionality, so that vxlan or ovs module can
register for particular port.
Signed-off-by: Pravin B Shelar <pshelar@...ira.com>
---
drivers/net/vxlan.c | 113 ++++++++++++++++++++++++++++++++-------------------
1 files changed, 71 insertions(+), 42 deletions(-)
diff --git a/drivers/net/vxlan.c b/drivers/net/vxlan.c
index 279c7dc..8efee59 100644
--- a/drivers/net/vxlan.c
+++ b/drivers/net/vxlan.c
@@ -57,6 +57,7 @@
#define VXLAN_VID_MASK (VXLAN_N_VID - 1)
/* IP header + UDP + VXLAN + Ethernet header */
#define VXLAN_HEADROOM (20 + 8 + 8 + 14)
+#define VXLAN_HLEN (sizeof(struct udphdr) + sizeof(struct vxlanhdr))
#define VXLAN_FLAGS 0x08000000 /* struct vxlanhdr.vx_flags required value. */
@@ -82,8 +83,12 @@ static int vxlan_net_id;
static const u8 all_zeros_mac[ETH_ALEN];
+struct vxlan_sock;
+typedef void (vxlan_rcv_t)(struct vxlan_sock *vh, struct sk_buff *skb, __be32 key);
+
/* per UDP socket information */
struct vxlan_sock {
+ vxlan_rcv_t *rcv;
struct hlist_node hlist;
struct rcu_head rcu;
struct work_struct del_work;
@@ -211,6 +216,18 @@ static struct vxlan_dev *vxlan_find_vni(struct net *net, u32 id, __be16 port)
return NULL;
}
+static struct vxlan_dev *vxlan_find_vni_port(struct vxlan_sock *vs, u32 id)
+{
+ struct vxlan_dev *vxlan;
+
+ hlist_for_each_entry_rcu(vxlan, vni_head(vs, id), hlist) {
+ if (vxlan->default_dst.remote_vni == id)
+ return vxlan;
+ }
+
+ return NULL;
+}
+
/* Fill in neighbour message in skbuff. */
static int vxlan_fdb_info(struct sk_buff *skb, struct vxlan_dev *vxlan,
const struct vxlan_fdb *fdb,
@@ -836,23 +853,16 @@ static void vxlan_igmp_work(struct work_struct *work)
/* Callback from net/ipv4/udp.c to receive packets */
static int vxlan_udp_encap_recv(struct sock *sk, struct sk_buff *skb)
{
- struct iphdr *oip;
+ struct vxlan_sock *vs;
struct vxlanhdr *vxh;
- struct vxlan_dev *vxlan;
- struct pcpu_tstats *stats;
__be16 port;
- __u32 vni;
- int err;
-
- /* pop off outer UDP header */
- __skb_pull(skb, sizeof(struct udphdr));
/* Need Vxlan and inner Ethernet header to be present */
- if (!pskb_may_pull(skb, sizeof(struct vxlanhdr)))
+ if (!pskb_may_pull(skb, VXLAN_HLEN))
goto error;
- /* Drop packets with reserved bits set */
- vxh = (struct vxlanhdr *) skb->data;
+ /* Return packets with reserved bits set */
+ vxh = (struct vxlanhdr *)(udp_hdr(skb) + 1);
if (vxh->vx_flags != htonl(VXLAN_FLAGS) ||
(vxh->vx_vni & htonl(0xff))) {
netdev_dbg(skb->dev, "invalid vxlan flags=%#x vni=%#x\n",
@@ -860,28 +870,44 @@ static int vxlan_udp_encap_recv(struct sock *sk, struct sk_buff *skb)
goto error;
}
- __skb_pull(skb, sizeof(struct vxlanhdr));
+ if (iptunnel_pull_header(skb, VXLAN_HLEN, htons(ETH_P_TEB)))
+ goto drop;
- /* Is this VNI defined? */
- vni = ntohl(vxh->vx_vni) >> 8;
port = inet_sk(sk)->inet_sport;
- vxlan = vxlan_find_vni(sock_net(sk), vni, port);
- if (!vxlan) {
- netdev_dbg(skb->dev, "unknown vni %d port %u\n",
- vni, ntohs(port));
+
+ vs = vxlan_find_sock(sock_net(sk), port);
+ if (!vs)
goto drop;
- }
- if (!pskb_may_pull(skb, ETH_HLEN)) {
- vxlan->dev->stats.rx_length_errors++;
- vxlan->dev->stats.rx_errors++;
+ vs->rcv(vs, skb, vxh->vx_vni);
+ return 0;
+
+drop:
+ /* Consume bad packet */
+ kfree_skb(skb);
+ return 0;
+
+error:
+ /* Return non vxlan pkt */
+ return 1;
+}
+
+static void vxlan_rcv(struct vxlan_sock *vs,
+ struct sk_buff *skb, __be32 vx_vni)
+{
+ struct iphdr *oip;
+ struct vxlan_dev *vxlan;
+ struct pcpu_tstats *stats;
+ __u32 vni;
+ int err;
+
+ vni = ntohl(vx_vni) >> 8;
+ /* Is this VNI defined? */
+ vxlan = vxlan_find_vni_port(vs, vni);
+ if (!vxlan)
goto drop;
- }
skb_reset_mac_header(skb);
-
- /* Re-examine inner Ethernet packet */
- oip = ip_hdr(skb);
skb->protocol = eth_type_trans(skb, vxlan->dev);
/* Ignore packet loops (and multicast echo) */
@@ -889,11 +915,12 @@ static int vxlan_udp_encap_recv(struct sock *sk, struct sk_buff *skb)
vxlan->dev->dev_addr) == 0)
goto drop;
+ /* Re-examine inner Ethernet packet */
+ oip = ip_hdr(skb);
if ((vxlan->flags & VXLAN_F_LEARN) &&
vxlan_snoop(skb->dev, oip->saddr, eth_hdr(skb)->h_source))
goto drop;
- __skb_tunnel_rx(skb, vxlan->dev);
skb_reset_network_header(skb);
/* If the NIC driver gave us an encapsulated packet with
@@ -927,16 +954,10 @@ static int vxlan_udp_encap_recv(struct sock *sk, struct sk_buff *skb)
netif_rx(skb);
- return 0;
-error:
- /* Put UDP header back */
- __skb_push(skb, sizeof(struct udphdr));
-
- return 1;
+ return;
drop:
/* Consume bad packet */
kfree_skb(skb);
- return 0;
}
static int arp_reduce(struct net_device *dev, struct sk_buff *skb)
@@ -1608,7 +1629,8 @@ static void vxlan_del_work(struct work_struct *work)
kfree_rcu(vs, rcu);
}
-static void vxlan_socket_create(struct net *net, __be16 port)
+static void vxlan_socket_create(struct net *net, __be16 port,
+ vxlan_rcv_t *rcv)
{
struct vxlan_net *vn = net_generic(net, vxlan_net_id);
struct vxlan_sock *vs;
@@ -1656,6 +1678,7 @@ static void vxlan_socket_create(struct net *net, __be16 port)
/* Disable multicast loopback */
inet_sk(sk)->mc_loop = 0;
+ vs->rcv = rcv;
spin_lock(&vn->sock_lock);
hlist_add_head_rcu(&vs->hlist, vs_head(net, port));
spin_unlock(&vn->sock_lock);
@@ -1668,21 +1691,27 @@ static void vxlan_socket_create(struct net *net, __be16 port)
}
/* Scheduled at device creation to bind to a socket */
-static struct vxlan_sock *vxlan_sock_add(struct net *net, __be16 port)
+static struct vxlan_sock *vxlan_sock_add(struct net *net, __be16 port,
+ vxlan_rcv_t *rcv)
{
struct vxlan_net *vn = net_generic(net, vxlan_net_id);
struct vxlan_sock *vs;
- vxlan_socket_create(net, port);
+ vxlan_socket_create(net, port, rcv);
spin_lock(&vn->sock_lock);
vs = vxlan_find_sock(net, port);
- if (vs)
- atomic_inc(&vs->refcnt);
- else
+ if (vs) {
+ if (vs->rcv == rcv)
+ atomic_inc(&vs->refcnt);
+ else
+ vs = ERR_PTR(-EBUSY);
+ }
+ spin_unlock(&vn->sock_lock);
+
+ if (!vs)
vs = ERR_PTR(-EINVAL);
- spin_unlock(&vn->sock_lock);
return vs;
}
@@ -1694,7 +1723,7 @@ static void vxlan_sock_work(struct work_struct *work)
__be16 port = vxlan->dst_port;
struct vxlan_sock *nvs;
- nvs = vxlan_sock_add(net, port);
+ nvs = vxlan_sock_add(net, port, vxlan_rcv);
spin_lock(&vn->sock_lock);
if (!IS_ERR(nvs))
vxlan_vs_add_dev(nvs, vxlan);
--
1.7.1
--
To unsubscribe from this list: send the line "unsubscribe netdev" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
Powered by blists - more mailing lists