[patch 08/12] net namespace : find namespace by addr

[dlezcano@fr.ibm.com]

[-- Attachment #1: net-namespace-l3-switch-to-net_ns-from-dst-addr.patch --]
[-- Type: text/plain, Size: 3573 bytes --]

From: Daniel Lezcano <dlezcano@fr.ibm.com>

Switch to the the l3 namespace using the destination address.

Signed-off-by: Daniel Lezcano <dlezcano@fr.ibm.com>

---
 include/linux/net_namespace.h |    7 +++++++
 net/core/net_namespace.c      |   35 +++++++++++++++++++++++++++++++++++
 net/ipv4/ip_input.c           |   16 +++++++++++++++-
 3 files changed, 57 insertions(+), 1 deletion(-)

Index: 2.6.20-rc4-mm1/net/ipv4/ip_input.c
===================================================================
--- 2.6.20-rc4-mm1.orig/net/ipv4/ip_input.c
+++ 2.6.20-rc4-mm1/net/ipv4/ip_input.c
@@ -374,6 +374,9 @@
 {
 	struct iphdr *iph;
 	u32 len;
+	int err;
+	struct net_namespace *net_ns = current_net_ns;
+	struct net_namespace *dst_net_ns = NULL;
 
 	/* When the interface is in promisc. mode, drop all the crap
 	 * that it receives, do not try to analyse it.
@@ -393,6 +396,9 @@
 
 	iph = skb->nh.iph;
 
+	dst_net_ns = net_ns_find_from_dest_addr(iph->daddr);
+	if (dst_net_ns && !net_ns_match(net_ns, dst_net_ns))
+		push_net_ns(dst_net_ns);
 	/*
 	 *	RFC1122: 3.1.2.2 MUST silently discard any IP frame that fails the checksum.
 	 *
@@ -431,10 +437,18 @@
 	/* Remove any debris in the socket control block */
 	memset(IPCB(skb), 0, sizeof(struct inet_skb_parm));
 
-	return NF_HOOK(PF_INET, NF_IP_PRE_ROUTING, skb, dev, NULL,
+	err =  NF_HOOK(PF_INET, NF_IP_PRE_ROUTING, skb, dev, NULL,
 		       ip_rcv_finish);
 
+	if (dst_net_ns && !net_ns_match(net_ns, dst_net_ns))
+		pop_net_ns(net_ns);
+
+	return err;
+
 inhdr_error:
+	if (dst_net_ns && !net_ns_match(net_ns, dst_net_ns))
+		pop_net_ns(net_ns);
+
 	IP_INC_STATS_BH(IPSTATS_MIB_INHDRERRORS);
 drop:
         kfree_skb(skb);
Index: 2.6.20-rc4-mm1/include/linux/net_namespace.h
===================================================================
--- 2.6.20-rc4-mm1.orig/include/linux/net_namespace.h
+++ 2.6.20-rc4-mm1/include/linux/net_namespace.h
@@ -99,6 +99,8 @@
 extern __be32 net_ns_select_source_address(const struct net_device *dev,
 					   u32 dst, int scope);
 
+extern struct net_namespace *net_ns_find_from_dest_addr(u32 daddr);
+
 #define SELECT_SRC_ADDR net_ns_select_source_address
 
 #else /* CONFIG_NET_NS */
@@ -167,6 +169,11 @@
 	return 0;
 }
 
+static inline struct net_namespace *net_ns_find_from_dest_addr(u32 daddr)
+{
+	return NULL;
+}
+
 #define SELECT_SRC_ADDR inet_select_addr
 
 #endif /* !CONFIG_NET_NS */
Index: 2.6.20-rc4-mm1/net/core/net_namespace.c
===================================================================
--- 2.6.20-rc4-mm1.orig/net/core/net_namespace.c
+++ 2.6.20-rc4-mm1/net/core/net_namespace.c
@@ -385,4 +385,39 @@
 out:
 	return addr;
 }
+
+/*
+ * This function finds the network namespace destination deduced from
+ * the destination address. The network namespace is retrieved from
+ * the ifaddr owned by a network namespace
+ * @daddr  : destination
+ * Returns : the network namespace destination or NULL if not found
+ */
+struct net_namespace *net_ns_find_from_dest_addr(u32 daddr)
+{
+	struct net_namespace *net_ns = NULL;
+	struct net_device *dev;
+	struct in_device *in_dev;
+
+	if (LOOPBACK(daddr))
+		return current_net_ns;
+
+	read_lock(&dev_base_lock);
+	rcu_read_lock();
+	for (dev = dev_base; dev; dev = dev->next) {
+		if ((in_dev = __in_dev_get_rcu(dev)) == NULL)
+			continue;
+		for_ifa(in_dev) {
+			if (ifa->ifa_local == daddr) {
+				net_ns = ifa->ifa_net_ns;
+				goto out_unlock_both;
+			}
+		} endfor_ifa(in_dev);
+	}
+out_unlock_both:
+	read_unlock(&dev_base_lock);
+	rcu_read_unlock();
+
+	return net_ns;
+}
 #endif /* CONFIG_NET_NS */

--