netdev.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
* [patch 02/11] bridge: send correct MTU value in PMTU
@ 2008-07-30 19:37 akpm
  2008-07-30 20:32 ` [PATCH] bridge: send correct MTU value in PMTU (revised) Stephen Hemminger
  0 siblings, 1 reply; 5+ messages in thread
From: akpm @ 2008-07-30 19:37 UTC (permalink / raw)
  To: davem; +Cc: netdev, akpm, simon.wunderlich, shemminger, siwu

From: Simon Wunderlich <simon.wunderlich@s2003.tu-chemnitz.de>

When bridging interfaces with different MTUs, the bridge correctly chooses
the minimum of the MTUs of the physical devices as the bridges MTU.  But
when a frame is passed which fits through the incoming, but not through
the outgoing interface, a "Fragmentation Needed" packet is generated.

However, the propagated MTU is hardcoded to 1500, which is wrong in this
situation.  The sender will repeat the packet again with the same frame
size, and the same problem will occur again.

Instead of sending 1500, the (correct) MTU value of the bridge is now sent
via PMTU.  To achieve this, the corresponding rtable structure is stored
in its net_bridge structure.

[akpm@linux-foundation.org: coding-style fixes]
Signed-off-by: Simon Wunderlich <siwu@hrz.tu-chemnitz.de>
Cc: Stephen Hemminger <shemminger@linux-foundation.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---

 net/bridge/br_device.c    |    9 +++++-
 net/bridge/br_if.c        |   27 +++++++++++++++++++
 net/bridge/br_netfilter.c |   51 +++++++++++++-----------------------
 net/bridge/br_private.h   |    5 +++
 4 files changed, 59 insertions(+), 33 deletions(-)

diff -puN net/bridge/br_device.c~bridge-send-correct-mtu-value-in-pmtu net/bridge/br_device.c
--- a/net/bridge/br_device.c~bridge-send-correct-mtu-value-in-pmtu
+++ a/net/bridge/br_device.c
@@ -68,10 +68,17 @@ static int br_dev_stop(struct net_device
 
 static int br_change_mtu(struct net_device *dev, int new_mtu)
 {
-	if (new_mtu < 68 || new_mtu > br_min_mtu(netdev_priv(dev)))
+	struct net_bridge *br = netdev_priv(dev);
+	if (new_mtu < 68 || new_mtu > br_min_mtu(br))
 		return -EINVAL;
 
 	dev->mtu = new_mtu;
+
+#ifdef CONFIG_BRIDGE_NETFILTER
+	/* remember the MTU in the rtable for PMTU */
+	br->fake_rtable.u.dst.metrics[RTAX_MTU - 1] = new_mtu;
+#endif
+
 	return 0;
 }
 
diff -puN net/bridge/br_if.c~bridge-send-correct-mtu-value-in-pmtu net/bridge/br_if.c
--- a/net/bridge/br_if.c~bridge-send-correct-mtu-value-in-pmtu
+++ a/net/bridge/br_if.c
@@ -168,6 +168,23 @@ static void del_br(struct net_bridge *br
 	unregister_netdevice(br->dev);
 }
 
+#ifdef CONFIG_BRIDGE_NETFILTER
+/* We need these fake structures to make netfilter happy --
+ * lots of places assume that skb->dst != NULL, which isn't
+ * all that unreasonable.
+ *
+ * Currently, we fill in the PMTU entry because netfilter
+ * refragmentation needs it, and the rt_flags entry because
+ * ipt_REJECT needs it.  Future netfilter modules might
+ * require us to fill additional fields. */
+struct net_device __fake_net_device = {
+	.hard_header_len	= ETH_HLEN,
+#ifdef CONFIG_NET_NS
+	.nd_net			= &init_net,
+#endif
+};
+#endif
+
 static struct net_device *new_bridge_dev(const char *name)
 {
 	struct net_bridge *br;
@@ -202,6 +219,16 @@ static struct net_device *new_bridge_dev
 	br->topology_change = 0;
 	br->topology_change_detected = 0;
 	br->ageing_time = 300 * HZ;
+
+#ifdef CONFIG_BRIDGE_NETFILTER
+	atomic_set(&br->fake_rtable.u.dst.__refcnt, 1);
+	br->fake_rtable.u.dst.dev = &__fake_net_device;
+	br->fake_rtable.u.dst.path = &br->fake_rtable.u.dst;
+	br->fake_rtable.u.dst.metrics[RTAX_MTU - 1] = 1500;
+	br->fake_rtable.u.dst.flags	= DST_NOXFRM;
+	br->fake_rtable.rt_flags = 0;
+#endif
+
 	INIT_LIST_HEAD(&br->age_list);
 
 	br_stp_timer_init(br);
diff -puN net/bridge/br_netfilter.c~bridge-send-correct-mtu-value-in-pmtu net/bridge/br_netfilter.c
--- a/net/bridge/br_netfilter.c~bridge-send-correct-mtu-value-in-pmtu
+++ a/net/bridge/br_netfilter.c
@@ -101,33 +101,12 @@ static inline __be16 pppoe_proto(const s
 	 pppoe_proto(skb) == htons(PPP_IPV6) && \
 	 brnf_filter_pppoe_tagged)
 
-/* We need these fake structures to make netfilter happy --
- * lots of places assume that skb->dst != NULL, which isn't
- * all that unreasonable.
- *
- * Currently, we fill in the PMTU entry because netfilter
- * refragmentation needs it, and the rt_flags entry because
- * ipt_REJECT needs it.  Future netfilter modules might
- * require us to fill additional fields. */
-static struct net_device __fake_net_device = {
-	.hard_header_len	= ETH_HLEN,
-#ifdef CONFIG_NET_NS
-	.nd_net			= &init_net,
-#endif
-};
+static inline struct rtable *bridge_parent_rtable(const struct net_device *dev)
+{
+	struct net_bridge_port *port = rcu_dereference(dev->br_port);
 
-static struct rtable __fake_rtable = {
-	.u = {
-		.dst = {
-			.__refcnt		= ATOMIC_INIT(1),
-			.dev			= &__fake_net_device,
-			.path			= &__fake_rtable.u.dst,
-			.metrics		= {[RTAX_MTU - 1] = 1500},
-			.flags			= DST_NOXFRM,
-		}
-	},
-	.rt_flags	= 0,
-};
+	return port ? &port->br->fake_rtable : NULL;
+}
 
 static inline struct net_device *bridge_parent(const struct net_device *dev)
 {
@@ -226,8 +205,12 @@ static int br_nf_pre_routing_finish_ipv6
 	}
 	nf_bridge->mask ^= BRNF_NF_BRIDGE_PREROUTING;
 
-	skb->rtable = &__fake_rtable;
-	dst_hold(&__fake_rtable.u.dst);
+	skb->rtable = bridge_parent_rtable(nf_bridge->physindev);
+	if (!skb->rtable) {
+		kfree_skb(skb);
+		return 0;
+	}
+	dst_hold(&skb->rtable->u.dst);
 
 	skb->dev = nf_bridge->physindev;
 	nf_bridge_push_encap_header(skb);
@@ -391,8 +374,12 @@ bridged_dnat:
 			skb->pkt_type = PACKET_HOST;
 		}
 	} else {
-		skb->rtable = &__fake_rtable;
-		dst_hold(&__fake_rtable.u.dst);
+		skb->rtable = bridge_parent_rtable(nf_bridge->physindev);
+		if (!skb->rtable) {
+			kfree_skb(skb);
+			return 0;
+		}
+		dst_hold(&skb->rtable->u.dst);
 	}
 
 	skb->dev = nf_bridge->physindev;
@@ -611,8 +598,8 @@ static unsigned int br_nf_local_in(unsig
 				   const struct net_device *out,
 				   int (*okfn)(struct sk_buff *))
 {
-	if (skb->rtable == &__fake_rtable) {
-		dst_release(&__fake_rtable.u.dst);
+	if (skb->rtable && skb->rtable == bridge_parent_rtable(in)) {
+		dst_release(&skb->rtable->u.dst);
 		skb->rtable = NULL;
 	}
 
diff -puN net/bridge/br_private.h~bridge-send-correct-mtu-value-in-pmtu net/bridge/br_private.h
--- a/net/bridge/br_private.h~bridge-send-correct-mtu-value-in-pmtu
+++ a/net/bridge/br_private.h
@@ -15,6 +15,7 @@
 
 #include <linux/netdevice.h>
 #include <linux/if_bridge.h>
+#include <net/route.h>	/* struct rtable, RTAX_MTU */
 
 #define BR_HASH_BITS 8
 #define BR_HASH_SIZE (1 << BR_HASH_BITS)
@@ -92,6 +93,9 @@ struct net_bridge
 	struct hlist_head		hash[BR_HASH_SIZE];
 	struct list_head		age_list;
 	unsigned long			feature_mask;
+#ifdef CONFIG_BRIDGE_NETFILTER
+	struct rtable 			fake_rtable;
+#endif
 	unsigned long			flags;
 #define BR_SET_MAC_ADDR		0x00000001
 
@@ -200,6 +204,7 @@ extern void br_netfilter_fini(void);
 #else
 #define br_netfilter_init()	(0)
 #define br_netfilter_fini()	do { } while(0)
+extern struct net_device __fake_net_device;
 #endif
 
 /* br_stp.c */
_

^ permalink raw reply	[flat|nested] 5+ messages in thread

end of thread, other threads:[~2008-07-30 23:28 UTC | newest]

Thread overview: 5+ messages (download: mbox.gz follow: Atom feed
-- links below jump to the message on this page --
2008-07-30 19:37 [patch 02/11] bridge: send correct MTU value in PMTU akpm
2008-07-30 20:32 ` [PATCH] bridge: send correct MTU value in PMTU (revised) Stephen Hemminger
2008-07-30 20:50   ` Andrew Morton
2008-07-30 21:10     ` Stephen Hemminger
2008-07-30 23:28       ` David Miller

This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).