On 7/23/15, 7:22 AM, Nicolas Dichtel wrote:
This patch takes advantage of the newly added lwtunnel framework to
allow the user to set routes that points to a peer netns.
Packets are injected to the peer netns via the loopback device. It works
only when the output device is 'lo'.
Example:
ip route add 40.1.1.1/32 encap netns nsid 5 via dev lo
Signed-off-by: Nicolas Dichtel <nicolas.dich...@6wind.com>
---
drivers/net/loopback.c | 16 +++++++++++++
include/net/lwtunnel.h | 23 +++++++++++++++++++
include/uapi/linux/lwtunnel.h | 1 +
net/core/net_namespace.c | 52 +++++++++++++++++++++++++++++++++++++++++++
4 files changed, 92 insertions(+)
diff --git a/drivers/net/loopback.c b/drivers/net/loopback.c
index c76283c2f84a..758d02f592f9 100644
--- a/drivers/net/loopback.c
+++ b/drivers/net/loopback.c
@@ -57,6 +57,7 @@
#include <linux/percpu.h>
#include <net/net_namespace.h>
#include <linux/u64_stats_sync.h>
+#include <net/lwtunnel.h>
struct pcpu_lstats {
u64 packets;
@@ -71,9 +72,23 @@ struct pcpu_lstats {
static netdev_tx_t loopback_xmit(struct sk_buff *skb,
struct net_device *dev)
{
+ int nsid = skb_lwt_netns_info(skb);
struct pcpu_lstats *lb_stats;
int len;
+ if (nsid >= 0) {
+ struct net *peernet = get_net_ns_by_id(dev_net(dev), nsid);
+
+ if (!peernet) {
+ kfree_skb(skb);
+ goto end;
+ }
+
+ dev_forward_skb(peernet->loopback_dev, skb);
+ put_net(peernet);
+ goto end;
+ }
+
skb_orphan(skb);
/* Before queueing this packet to netif_rx(),
@@ -94,6 +109,7 @@ static netdev_tx_t loopback_xmit(struct sk_buff *skb,
u64_stats_update_end(&lb_stats->syncp);
}
+end:
return NETDEV_TX_OK;
}
diff --git a/include/net/lwtunnel.h b/include/net/lwtunnel.h
index 918e03c1dafa..cc05ce3c1aae 100644
--- a/include/net/lwtunnel.h
+++ b/include/net/lwtunnel.h
@@ -5,7 +5,9 @@
#include <linux/netdevice.h>
#include <linux/skbuff.h>
#include <linux/types.h>
+#include <linux/net_namespace.h>
#include <net/route.h>
+#include <net/ip6_fib.h>
#define LWTUNNEL_HASH_BITS 7
#define LWTUNNEL_HASH_SIZE (1 << LWTUNNEL_HASH_BITS)
@@ -141,4 +143,25 @@ static inline int lwtunnel_output6(struct sock *sk, struct
sk_buff *skb)
#endif
+static inline u32 *lwt_netns_info(struct lwtunnel_state *lwtstate)
+{
+ return (u32 *)lwtstate->data;
+}
+
+static inline int skb_lwt_netns_info(struct sk_buff *skb)
+{
+ if (skb->protocol == htons(ETH_P_IP)) {
+ struct rtable *rt = (struct rtable *)skb_dst(skb);
+
+ if (rt && rt->rt_lwtstate)
+ return *lwt_netns_info(rt->rt_lwtstate);
+ } else if (skb->protocol == htons(ETH_P_IPV6)) {
+ struct rt6_info *rt6 = (struct rt6_info *)skb_dst(skb);
+
+ if (rt6 && rt6->rt6i_lwtstate)
+ return *lwt_netns_info(rt6->rt6i_lwtstate);
+ }
+
+ return NETNSA_NSID_NOT_ASSIGNED;
+}
#endif /* __NET_LWTUNNEL_H */
since these apis' don't have to be netns specific,
Can they just be named lwtunnel_get_state_data and skb_lwtunnel_state ?
and seems like they should be declared for both CONFIG_LWTUNNEL 'y' and 'n'.
Thanks,
Roopa
--
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
