br-nf-bds/patches/bridge-nf-0.0.8-3-dev-bds-vs-2.5.32.diff

bridge-nf-0.0.8-3-dev-bds vs 2.5.32 - 29 August

this is a patch against 2.5.32 that needs to be applied AFTER
the ebtables patch for 2.5.32

--- linux-2.5.32/include/linux/netfilter.h	Tue Aug 27 21:26:43 2002
+++ linux-2.5.32-ebt+br-nf-0.0.3/include/linux/netfilter.h	Thu Aug 29 22:08:46 2002
@@ -117,17 +117,23 @@
 /* This is gross, but inline doesn't cut it for avoiding the function
    call in fast path: gcc doesn't inline (needs value tracking?). --RR */
 #ifdef CONFIG_NETFILTER_DEBUG
-#define NF_HOOK nf_hook_slow
+#define NF_HOOK(pf, hook, skb, indev, outdev, okfn)			\
+ nf_hook_slow((pf), (hook), (skb), (indev), (outdev), (okfn), INT_MIN)
+#define NF_HOOK_THRESH nf_hook_slow
 #else
 #define NF_HOOK(pf, hook, skb, indev, outdev, okfn)			\
 (list_empty(&nf_hooks[(pf)][(hook)])					\
  ? (okfn)(skb)								\
- : nf_hook_slow((pf), (hook), (skb), (indev), (outdev), (okfn)))
+ : nf_hook_slow((pf), (hook), (skb), (indev), (outdev), (okfn), INT_MIN))
+#define NF_HOOK_THRESH(pf, hook, skb, indev, outdev, okfn, thresh)	\
+(list_empty(&nf_hooks[(pf)][(hook)])					\
+ ? (okfn)(skb)								\
+ : nf_hook_slow((pf), (hook), (skb), (indev), (outdev), (okfn), (thresh)))
 #endif
 
 int nf_hook_slow(int pf, unsigned int hook, struct sk_buff *skb,
 		 struct net_device *indev, struct net_device *outdev,
-		 int (*okfn)(struct sk_buff *));
+		 int (*okfn)(struct sk_buff *), int thresh);
 
 /* Call setsockopt() */
 int nf_setsockopt(struct sock *sk, int pf, int optval, char *opt, 
--- linux-2.5.32/include/linux/netfilter_ipv4.h	Tue Aug 27 21:27:11 2002
+++ linux-2.5.32-ebt+br-nf-0.0.3/include/linux/netfilter_ipv4.h	Thu Aug 29 22:08:46 2002
@@ -52,8 +52,10 @@
 enum nf_ip_hook_priorities {
 	NF_IP_PRI_FIRST = INT_MIN,
 	NF_IP_PRI_CONNTRACK = -200,
+	NF_IP_PRI_BRIDGE_SABOTAGE_FORWARD = -175,
 	NF_IP_PRI_MANGLE = -150,
 	NF_IP_PRI_NAT_DST = -100,
+	NF_IP_PRI_BRIDGE_SABOTAGE = -50,
 	NF_IP_PRI_FILTER = 0,
 	NF_IP_PRI_NAT_SRC = 100,
 	NF_IP_PRI_LAST = INT_MAX,
--- linux-2.5.32/include/linux/skbuff.h	Tue Aug 27 21:26:32 2002
+++ linux-2.5.32-ebt+br-nf-0.0.3/include/linux/skbuff.h	Thu Aug 29 22:08:46 2002
@@ -137,6 +137,8 @@
  *	@sk: Socket we are owned by
  *	@stamp: Time we arrived
  *	@dev: Device we arrived on/are leaving by
+ *	@physindev: Phsical device we arrived on (see bridge-nf)
+ *	@physoutdev: Phsical device we will leave by (see bridge-nf)
  *	@h: Transport layer header
  *	@nh: Network layer header
  *	@mac: Link layer header
@@ -175,6 +177,10 @@
 	struct sock		*sk;
 	struct timeval		stamp;
 	struct net_device	*dev;
+#ifdef CONFIG_BRIDGE_NF
+	struct net_device	*physindev;
+	struct net_device	*physoutdev;
+#endif
 
 	union {
 		struct tcphdr	*th;
--- linux-2.5.32/net/bridge/br.c	Thu Aug 29 21:58:05 2002
+++ linux-2.5.32-ebt+br-nf-0.0.3/net/bridge/br.c	Thu Aug 29 22:08:46 2002
@@ -50,6 +50,11 @@
 {
 	printk(KERN_INFO "NET4: Ethernet Bridge 008 for NET4.0\n");
 
+#ifdef CONFIG_BRIDGE_NF
+	if (br_netfilter_init())
+		return 1;
+#endif
+
 	br_handle_frame_hook = br_handle_frame;
 	br_ioctl_hook = br_ioctl_deviceless_stub;
 #if defined(CONFIG_ATM_LANE) || defined(CONFIG_ATM_LANE_MODULE)
@@ -73,6 +78,9 @@
 
 static void __exit br_deinit(void)
 {
+#ifdef CONFIG_BRIDGE_NF
+	br_netfilter_fini();
+#endif
 	unregister_netdevice_notifier(&br_device_notifier);
 	br_call_ioctl_atomic(__br_clear_ioctl_hook);
 	net_call_rx_atomic(__br_clear_frame_hook);
--- linux-2.5.32/net/bridge/br_forward.c	Tue Aug 27 21:26:39 2002
+++ linux-2.5.32-ebt+br-nf-0.0.3/net/bridge/br_forward.c	Thu Aug 29 22:08:46 2002
@@ -30,7 +30,7 @@
 	return 1;
 }
 
-static int __dev_queue_push_xmit(struct sk_buff *skb)
+int br_dev_queue_push_xmit(struct sk_buff *skb)
 {
 	skb_push(skb, ETH_HLEN);
 	dev_queue_xmit(skb);
@@ -38,10 +38,10 @@
 	return 0;
 }
 
-static int __br_forward_finish(struct sk_buff *skb)
+int br_forward_finish(struct sk_buff *skb)
 {
 	NF_HOOK(PF_BRIDGE, NF_BR_POST_ROUTING, skb, NULL, skb->dev,
-			__dev_queue_push_xmit);
+			br_dev_queue_push_xmit);
 
 	return 0;
 }
@@ -50,7 +50,7 @@
 {
 	skb->dev = to->dev;
 	NF_HOOK(PF_BRIDGE, NF_BR_LOCAL_OUT, skb, NULL, skb->dev,
-			__br_forward_finish);
+			br_forward_finish);
 }
 
 static void __br_forward(struct net_bridge_port *to, struct sk_buff *skb)
@@ -61,7 +61,7 @@
 	skb->dev = to->dev;
 
 	NF_HOOK(PF_BRIDGE, NF_BR_FORWARD, skb, indev, skb->dev,
-			__br_forward_finish);
+			br_forward_finish);
 }
 
 /* called under bridge lock */
--- linux-2.5.32/net/bridge/br_input.c	Thu Aug 29 21:58:05 2002
+++ linux-2.5.32-ebt+br-nf-0.0.3/net/bridge/br_input.c	Thu Aug 29 22:08:46 2002
@@ -50,7 +50,7 @@
 			br_pass_frame_up_finish);
 }
 
-static int br_handle_frame_finish(struct sk_buff *skb)
+int br_handle_frame_finish(struct sk_buff *skb)
 {
 	struct net_bridge *br;
 	unsigned char *dest;
--- linux-2.5.32/net/bridge/br_private.h	Thu Aug 29 21:58:05 2002
+++ linux-2.5.32-ebt+br-nf-0.0.3/net/bridge/br_private.h	Thu Aug 29 22:08:46 2002
@@ -144,8 +144,10 @@
 /* br_forward.c */
 extern void br_deliver(struct net_bridge_port *to,
 		struct sk_buff *skb);
+extern int br_dev_queue_push_xmit(struct sk_buff *skb);
 extern void br_forward(struct net_bridge_port *to,
 		struct sk_buff *skb);
+extern int br_forward_finish(struct sk_buff *skb);
 extern void br_flood_deliver(struct net_bridge *br,
 		      struct sk_buff *skb,
 		      int clone);
@@ -166,6 +168,7 @@
 			   int *ifindices);
 
 /* br_input.c */
+extern int br_handle_frame_finish(struct sk_buff *skb);
 extern int br_handle_frame(struct sk_buff *skb);
 
 /* br_ioctl.c */
@@ -176,6 +179,10 @@
 	     unsigned long arg1,
 	     unsigned long arg2);
 extern int br_ioctl_deviceless_stub(unsigned long arg);
+
+/* br_netfilter.c */
+extern int br_netfilter_init(void);
+extern void br_netfilter_fini(void);
 
 /* br_stp.c */
 extern int br_is_root_bridge(struct net_bridge *br);
--- linux-2.5.32/net/bridge/Makefile	Thu Aug 29 21:58:05 2002
+++ linux-2.5.32-ebt+br-nf-0.0.3/net/bridge/Makefile	Thu Aug 29 22:08:46 2002
@@ -15,4 +15,10 @@
 			br_stp_if.o br_stp_timer.o
 obj-$(CONFIG_BRIDGE_EBT) += netfilter/
 
+ifneq ($(CONFIG_BRIDGE_NF),n)
+ifneq ($(CONFIG_BRIDGE_NF),)
+bridge-objs += br_netfilter.o
+endif
+endif
+
 include $(TOPDIR)/Rules.make
--- linux-2.5.32/net/Config.in	Thu Aug 29 21:58:05 2002
+++ linux-2.5.32-ebt+br-nf-0.0.3/net/Config.in	Thu Aug 29 22:08:47 2002
@@ -66,6 +66,9 @@
    source net/bridge/netfilter/Config.in
 fi
 if [ "$CONFIG_EXPERIMENTAL" = "y" ]; then
+   if [ "$CONFIG_BRIDGE" != "n" -a "$CONFIG_NETFILTER" != "n" ]; then
+      bool '  netfilter (firewalling) support' CONFIG_BRIDGE_NF
+   fi
    tristate 'CCITT X.25 Packet Layer (EXPERIMENTAL)' CONFIG_X25
    tristate 'LAPB Data Link Driver (EXPERIMENTAL)' CONFIG_LAPB
    bool 'Frame Diverter (EXPERIMENTAL)' CONFIG_NET_DIVERT
--- linux-2.5.32/net/core/netfilter.c	Tue Aug 27 21:26:42 2002
+++ linux-2.5.32-ebt+br-nf-0.0.3/net/core/netfilter.c	Thu Aug 29 22:08:46 2002
@@ -342,10 +342,15 @@
 			       const struct net_device *indev,
 			       const struct net_device *outdev,
 			       struct list_head **i,
-			       int (*okfn)(struct sk_buff *))
+			       int (*okfn)(struct sk_buff *),
+			       int hook_thresh)
 {
 	for (*i = (*i)->next; *i != head; *i = (*i)->next) {
 		struct nf_hook_ops *elem = (struct nf_hook_ops *)*i;
+
+		if (hook_thresh > elem->priority)
+			continue;
+
 		switch (elem->hook(hook, skb, indev, outdev, okfn)) {
 		case NF_QUEUE:
 			return NF_QUEUE;
@@ -413,6 +418,10 @@
 {
 	int status;
 	struct nf_info *info;
+#ifdef CONFIG_BRIDGE_NF
+	struct net_device *physindev;
+	struct net_device *physoutdev;
+#endif
 
 	if (!queue_handler[pf].outfn) {
 		kfree_skb(skb);
@@ -435,11 +444,20 @@
 	if (indev) dev_hold(indev);
 	if (outdev) dev_hold(outdev);
 
+#ifdef CONFIG_BRIDGE_NF
+	if ((physindev = skb->physindev)) dev_hold(physindev);
+	if ((physoutdev = skb->physoutdev)) dev_hold(physoutdev);
+#endif
+
 	status = queue_handler[pf].outfn(skb, info, queue_handler[pf].data);
 	if (status < 0) {
 		/* James M doesn't say fuck enough. */
 		if (indev) dev_put(indev);
 		if (outdev) dev_put(outdev);
+#ifdef CONFIG_BRIDGE_NF
+		if (physindev) dev_put(physindev);
+		if (physoutdev) dev_put(physoutdev);
+#endif
 		kfree(info);
 		kfree_skb(skb);
 		return;
@@ -449,7 +467,8 @@
 int nf_hook_slow(int pf, unsigned int hook, struct sk_buff *skb,
 		 struct net_device *indev,
 		 struct net_device *outdev,
-		 int (*okfn)(struct sk_buff *))
+		 int (*okfn)(struct sk_buff *),
+		 int hook_thresh)
 {
 	struct list_head *elem;
 	unsigned int verdict;
@@ -481,7 +500,7 @@
 
 	elem = &nf_hooks[pf][hook];
 	verdict = nf_iterate(&nf_hooks[pf][hook], &skb, hook, indev,
-			     outdev, &elem, okfn);
+			     outdev, &elem, okfn, hook_thresh);
 	if (verdict == NF_QUEUE) {
 		NFDEBUG("nf_hook: Verdict = QUEUE.\n");
 		nf_queue(skb, elem, pf, hook, indev, outdev, okfn);
@@ -530,7 +549,7 @@
 		verdict = nf_iterate(&nf_hooks[info->pf][info->hook],
 				     &skb, info->hook, 
 				     info->indev, info->outdev, &elem,
-				     info->okfn);
+				     info->okfn, INT_MIN);
 	}
 
 	switch (verdict) {
--- linux-2.5.32/net/core/skbuff.c	Tue Aug 27 21:26:36 2002
+++ linux-2.5.32-ebt+br-nf-0.0.3/net/core/skbuff.c	Thu Aug 29 22:08:46 2002
@@ -232,6 +232,10 @@
 	skb->sk		  = NULL;
 	skb->stamp.tv_sec = 0;	/* No idea about time */
 	skb->dev	  = NULL;
+#ifdef CONFIG_BRIDGE_NF
+	skb->physindev	  = NULL;
+	skb->physoutdev	  = NULL;
+#endif
 	skb->dst	  = NULL;
 	memset(skb->cb, 0, sizeof(skb->cb));
 	skb->pkt_type	  = PACKET_HOST;	/* Default type */
@@ -361,6 +365,10 @@
 	n->sk = NULL;
 	C(stamp);
 	C(dev);
+#ifdef CONFIG_BRIDGE_NF
+	C(physindev);
+	C(physoutdev);
+#endif
 	C(h);
 	C(nh);
 	C(mac);
@@ -416,6 +424,10 @@
 	new->list	= NULL;
 	new->sk		= NULL;
 	new->dev	= old->dev;
+#ifdef CONFIG_BRIDGE_NF
+	new->physindev	= old->physindev;
+	new->physoutdev	= old->physoutdev;
+#endif
 	new->priority	= old->priority;
 	new->protocol	= old->protocol;
 	new->dst	= dst_clone(old->dst);
--- linux-2.5.32/net/ipv4/ip_output.c	Tue Aug 27 21:27:33 2002
+++ linux-2.5.32-ebt+br-nf-0.0.3/net/ipv4/ip_output.c	Thu Aug 29 22:08:47 2002
@@ -835,6 +835,10 @@
 			skb_set_owner_w(skb2, skb->sk);
 		skb2->dst = dst_clone(skb->dst);
 		skb2->dev = skb->dev;
+#ifdef CONFIG_BRIDGE_NF
+		skb2->physindev = skb->physindev;
+		skb2->physoutdev = skb->physoutdev;
+#endif
 
 		/*
 		 *	Copy the packet header into the new buffer.
@@ -898,6 +902,9 @@
 		iph->tot_len = htons(len + hlen);
 
 		ip_send_check(iph);
+#ifdef CONFIG_BRIDGE_NF
+		memcpy(skb2->data - 16, skb->data - 16, 16);
+#endif
 
 		err = output(skb2);
 		if (err)
--- linux-2.5.32/net/ipv4/netfilter/ip_tables.c	Tue Aug 27 21:26:37 2002
+++ linux-2.5.32-ebt+br-nf-0.0.3/net/ipv4/netfilter/ip_tables.c	Thu Aug 29 22:08:46 2002
@@ -122,12 +122,19 @@
 static inline int
 ip_packet_match(const struct iphdr *ip,
 		const char *indev,
+#ifdef CONFIG_BRIDGE_NF
+		const char *physindev,
+#endif
 		const char *outdev,
+#ifdef CONFIG_BRIDGE_NF
+		const char *physoutdev,
+#endif
 		const struct ipt_ip *ipinfo,
 		int isfrag)
 {
 	size_t i;
 	unsigned long ret;
+	unsigned long ret2 = 1;
 
 #define FWINV(bool,invflg) ((bool) ^ !!(ipinfo->invflags & invflg))
 
@@ -157,7 +164,15 @@
 			& ((const unsigned long *)ipinfo->iniface_mask)[i];
 	}
 
-	if (FWINV(ret != 0, IPT_INV_VIA_IN)) {
+#ifdef CONFIG_BRIDGE_NF
+	for (i = 0, ret2 = 0; i < IFNAMSIZ/sizeof(unsigned long); i++) {
+		ret2 |= (((const unsigned long *)physindev)[i]
+			^ ((const unsigned long *)ipinfo->iniface)[i])
+			& ((const unsigned long *)ipinfo->iniface_mask)[i];
+	}
+#endif
+
+	if (FWINV(ret != 0 && ret2 != 0, IPT_INV_VIA_IN)) {
 		dprintf("VIA in mismatch (%s vs %s).%s\n",
 			indev, ipinfo->iniface,
 			ipinfo->invflags&IPT_INV_VIA_IN ?" (INV)":"");
@@ -170,7 +185,15 @@
 			& ((const unsigned long *)ipinfo->outiface_mask)[i];
 	}
 
-	if (FWINV(ret != 0, IPT_INV_VIA_OUT)) {
+#ifdef CONFIG_BRIDGE_NF
+	for (i = 0, ret2 = 0; i < IFNAMSIZ/sizeof(unsigned long); i++) {
+		ret2 |= (((const unsigned long *)physoutdev)[i]
+			^ ((const unsigned long *)ipinfo->outiface)[i])
+			& ((const unsigned long *)ipinfo->outiface_mask)[i];
+	}
+#endif
+
+	if (FWINV(ret != 0 && ret2 != 0, IPT_INV_VIA_OUT)) {
 		dprintf("VIA out mismatch (%s vs %s).%s\n",
 			outdev, ipinfo->outiface,
 			ipinfo->invflags&IPT_INV_VIA_OUT ?" (INV)":"");
@@ -269,6 +292,9 @@
 	/* Initializing verdict to NF_DROP keeps gcc happy. */
 	unsigned int verdict = NF_DROP;
 	const char *indev, *outdev;
+#ifdef CONFIG_BRIDGE_NF
+	const char *physindev, *physoutdev;
+#endif
 	void *table_base;
 	struct ipt_entry *e, *back;
 
@@ -278,6 +304,11 @@
 	datalen = (*pskb)->len - ip->ihl * 4;
 	indev = in ? in->name : nulldevname;
 	outdev = out ? out->name : nulldevname;
+#ifdef CONFIG_BRIDGE_NF
+	physindev = (*pskb)->physindev ? (*pskb)->physindev->name : nulldevname;
+	physoutdev = (*pskb)->physoutdev ? (*pskb)->physoutdev->name : nulldevname;
+#endif
+
 	/* We handle fragments by dealing with the first fragment as
 	 * if it was a normal packet.  All other fragments are treated
 	 * normally, except that they will NEVER match rules that ask
@@ -312,7 +343,15 @@
 		IP_NF_ASSERT(e);
 		IP_NF_ASSERT(back);
 		(*pskb)->nfcache |= e->nfcache;
-		if (ip_packet_match(ip, indev, outdev, &e->ip, offset)) {
+		if (ip_packet_match(ip, indev,
+#ifdef CONFIG_BRIDGE_NF
+		    physindev,
+#endif
+		    outdev,
+#ifdef CONFIG_BRIDGE_NF
+		    physoutdev,
+#endif
+		    &e->ip, offset)) {
 			struct ipt_entry_target *t;
 
 			if (IPT_MATCH_ITERATE(e, do_match,
--- linux-2.5.32/net/ipv4/netfilter/ipt_LOG.c	Tue Aug 27 21:26:39 2002
+++ linux-2.5.32-ebt+br-nf-0.0.3/net/ipv4/netfilter/ipt_LOG.c	Thu Aug 29 22:08:46 2002
@@ -285,10 +285,17 @@
 	level_string[1] = '0' + (loginfo->level % 8);
 	spin_lock_bh(&log_lock);
 	printk(level_string);
-	printk("%sIN=%s OUT=%s ",
-	       loginfo->prefix,
-	       in ? in->name : "",
-	       out ? out->name : "");
+	printk("%sIN=%s ", loginfo->prefix, in ? in->name : "");
+#ifdef CONFIG_BRIDGE_NF
+	if ((*pskb)->physindev && in != (*pskb)->physindev)
+		printk("PHYSIN=%s ", (*pskb)->physindev->name);
+#endif
+	printk("OUT=%s ", out ? out->name : "");
+#ifdef CONFIG_BRIDGE_NF
+	if ((*pskb)->physoutdev && out != (*pskb)->physoutdev)
+		printk("PHYSOUT=%s ", (*pskb)->physoutdev->name);
+#endif
+
 	if (in && !out) {
 		/* MAC logging for input chain only. */
 		printk("MAC=");
--- /dev/null	Thu Aug 24 11:00:32 2000
+++ linux-2.5.32-ebt+br-nf-0.0.3/net/bridge/br_netfilter.c	Thu Aug 29 22:08:46 2002
@@ -0,0 +1,567 @@
+/*
+ *	Handle firewalling
+ *	Linux ethernet bridge
+ *
+ *	Authors:
+ *	Lennert Buytenhek               <buytenh@gnu.org>
+ *	Bart De Schuymer		<bart.de.schuymer@pandora.be>
+ *
+ *	$Id: bridge-nf-0.0.8-3-dev-bds-vs-2.5.32.diff,v 1.1 2002/08/30 19:01:07 bdschuym Exp $
+ *
+ *	This program is free software; you can redistribute it and/or
+ *	modify it under the terms of the GNU General Public License
+ *	as published by the Free Software Foundation; either version
+ *	2 of the License, or (at your option) any later version.
+ *
+ *	Lennert dedicates this file to Kerstin Wurdinger.
+ */
+
+#include <linux/module.h>
+#include <linux/kernel.h>
+#include <linux/ip.h>
+#include <linux/netdevice.h>
+#include <linux/skbuff.h>
+#include <linux/if_ether.h>
+#include <linux/netfilter_bridge.h>
+#include <linux/netfilter_ipv4.h>
+#include <linux/in_route.h>
+#include <net/ip.h>
+#include <net/tcp.h>
+#include <asm/uaccess.h>
+#include <asm/checksum.h>
+#include "br_private.h"
+
+
+#ifndef WE_REALLY_INSIST_ON_NOT_HAVING_NAT_SUPPORT
+/* As the original source/destination addresses are variables private to this
+ * file, we store them in unused space at the end of the control buffer.
+ * On 64-bit platforms the TCP control buffer size still leaves us 8 bytes
+ * of space at the end, so that fits.  Usage of the original source address
+ * and the original destination address never overlaps (daddr is needed
+ * around PRE_ROUTING, and saddr around POST_ROUTING), so that's okay as
+ * well.
+ */
+#define skb_origaddr(skb)		(*((u32 *)((skb)->cb + sizeof((skb)->cb) - 4)))
+
+#define store_orig_dstaddr(skb)		(skb_origaddr(skb) = (skb)->nh.iph->daddr)
+#define store_orig_srcaddr(skb)		(skb_origaddr(skb) = (skb)->nh.iph->saddr)
+#define dnat_took_place(skb)		(skb_origaddr(skb) != (skb)->nh.iph->daddr)
+#define snat_took_place(skb)		(skb_origaddr(skb) != (skb)->nh.iph->saddr)
+#else
+#define store_orig_dstaddr(skb)
+#define store_orig_srcaddr(skb)
+#define dnat_took_place(skb)		(0)
+#define snat_took_place(skb)		(0)
+#endif
+
+
+#define has_bridge_parent(device)	((device)->br_port != NULL)
+#define bridge_parent(device)		(&((device)->br_port->br->dev))
+
+
+/* As opposed to the DNAT case, for the SNAT case it's not quite
+ * clear what we should do with ethernet addresses in NAT'ed
+ * packets.  Use this heuristic for now.
+ */
+static inline void __maybe_fixup_src_address(struct sk_buff *skb)
+{
+	if (snat_took_place(skb) &&
+	    inet_addr_type(skb->nh.iph->saddr) == RTN_LOCAL) {
+		memcpy(skb->mac.ethernet->h_source,
+			bridge_parent(skb->dev)->dev_addr,
+			ETH_ALEN);
+	}
+}
+
+
+/* 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
+};
+
+static struct rtable __fake_rtable = {
+	u: {
+		dst: {
+			__refcnt:		ATOMIC_INIT(1),
+			dev:			&__fake_net_device,
+			pmtu:			1500
+		}
+	},
+
+	rt_flags:	0
+};
+
+
+/* PF_BRIDGE/PRE_ROUTING *********************************************/
+static void __br_dnat_complain(void)
+{
+	static unsigned long last_complaint = 0;
+
+	if (jiffies - last_complaint >= 5 * HZ) {
+		printk(KERN_WARNING "Performing cross-bridge DNAT requires IP "
+			"forwarding to be enabled\n");
+		last_complaint = jiffies;
+	}
+}
+
+
+static int br_nf_pre_routing_finish_bridge(struct sk_buff *skb)
+{
+	skb->dev = bridge_parent(skb->dev);
+	skb->dst->output(skb);
+	return 0;
+}
+
+/* This requires some explaining.  If DNAT has taken place,
+ * we will need to fix up the destination ethernet address,
+ * and this is a tricky process.
+ *
+ * There are two cases to consider:
+ * 1. The packet was DNAT'ed to a device in the same bridge
+ *    port group as it was received on.  We can still bridge
+ *    the packet.
+ * 2. The packet was DNAT'ed to a different device, either
+ *    a non-bridged device or another bridge port group.
+ *    The packet will need to be routed.
+ *
+ * The way to distinguish between the two is by calling ip_route_input()
+ * and looking at skb->dst->dev, which it changed to the destination device
+ * if ip_route_input() succeeds.
+ *
+ * Let us first consider ip_route_input() succeeds:
+ *
+ * If skb->dst->dev equals the logical bridge device the packet came in on,
+ * we can consider this bridging. We then call skb->dst->output() which will
+ * make the packet enter br_nf_local_out() not much later. In that function
+ * it is assured that the iptables FORWARD chain is traversed for the packet.
+ *
+ * Else, the packet is considered to be routed and we just change the
+ * destination MAC address so that the packet will later be passed up to the ip
+ * stack to be routed.
+ *
+ * Let us now consider ip_route_input() fails:
+ *
+ * After a "echo '0' > /proc/sys/net/ipv4/ip_forward" ip_route_input() will
+ * fail, while ip_route_output() will return success. The source address for
+ * for ip_route_output() is set to zero, so ip_route_output()
+ * thinks we're handling a locally generated packet and won't care if
+ * ip forwarding is allowed. We send a warning message to the users's log
+ * telling her to put ip forwarding on.
+ *
+ * ip_route_input() will also fail if there is no route available. Then we just
+ * drop the packet.
+ *
+ * The other special thing happening here is putting skb->physoutdev on
+ * &__fake_net_device (resp. NULL) for bridged (resp. routed) packets. This is
+ * needed so that br_nf_local_out() can know that it has to give the packets to
+ * the BR_NF_FORWARD (resp. BR_NF_LOCAL_OUT) bridge hook. See that function.
+ * --Lennert, 20020411
+ * --Bart, 20020416 (updated)
+ */
+
+static int br_nf_pre_routing_finish(struct sk_buff *skb)
+{
+	struct net_device *dev = skb->dev;
+	struct iphdr *iph = skb->nh.iph;
+
+	if (dnat_took_place(skb)) {
+		if (ip_route_input(skb, iph->daddr, iph->saddr, iph->tos, dev)) {
+			struct rtable *rt;
+
+			if (!ip_route_output(&rt, iph->daddr, 0, iph->tos, 0)) {
+				// bridged dnated traffic isn't dependent on
+				// disabled ip_forwarding
+				if (((struct dst_entry *)rt)->dev == dev) {
+					skb->dst = (struct dst_entry *)rt;
+					goto bridged_dnat;
+				}
+				__br_dnat_complain();
+				dst_release((struct dst_entry *)rt);
+			}
+			kfree_skb(skb);
+			return 0;
+		} else {
+			if (skb->dst->dev == dev) {
+bridged_dnat:
+				// tell br_nf_local_out this is a bridged frame
+				skb->physoutdev = &__fake_net_device;
+				skb->dev = skb->physindev;
+				NF_HOOK_THRESH(PF_BRIDGE, NF_BR_PRE_ROUTING, skb, skb->dev, NULL,
+						br_nf_pre_routing_finish_bridge, 1);
+				return 0;
+			}
+			// tell br_nf_local_out this is a routed frame
+			skb->physoutdev = NULL;
+			memcpy(skb->mac.ethernet->h_dest, dev->dev_addr, ETH_ALEN);
+		}
+	} else {
+		skb->dst = (struct dst_entry *)&__fake_rtable;
+		dst_hold(skb->dst);
+	}
+
+	skb->dev = skb->physindev;
+	NF_HOOK_THRESH(PF_BRIDGE, NF_BR_PRE_ROUTING, skb, skb->dev, NULL,
+			br_handle_frame_finish, 1);
+
+	return 0;
+}
+
+/* Replicate the checks that IPv4 does on packet reception.
+ * Set skb->dev to the bridge device (i.e. parent of the
+ * receiving device) to make netfilter happy, the REDIRECT
+ * target in particular.  Save the original destination IP
+ * address to be able to detect DNAT afterwards.
+ */
+static unsigned int br_nf_pre_routing(unsigned int hook, struct sk_buff **pskb, const struct net_device *in, const struct net_device *out, int (*okfn)(struct sk_buff *))
+{
+	struct iphdr *iph;
+	__u32 len;
+	struct sk_buff *skb;
+
+	if ((*pskb)->protocol != __constant_htons(ETH_P_IP))
+		return NF_ACCEPT;
+
+	if ((skb = skb_share_check(*pskb, GFP_ATOMIC)) == NULL)
+		goto out;
+
+	if (!pskb_may_pull(skb, sizeof(struct iphdr)))
+		goto inhdr_error;
+
+	iph = skb->nh.iph;
+	if (iph->ihl < 5 || iph->version != 4)
+		goto inhdr_error;
+
+	if (!pskb_may_pull(skb, 4*iph->ihl))
+		goto inhdr_error;
+
+	iph = skb->nh.iph;
+	if (ip_fast_csum((__u8 *)iph, iph->ihl) != 0)
+		goto inhdr_error;
+
+	len = ntohs(iph->tot_len);
+	if (skb->len < len || len < 4*iph->ihl)
+		goto inhdr_error;
+
+	if (skb->len > len) {
+		__pskb_trim(skb, len);
+		if (skb->ip_summed == CHECKSUM_HW)
+			skb->ip_summed = CHECKSUM_NONE;
+	}
+
+	skb->physindev = skb->dev;
+	skb->dev = bridge_parent(skb->dev);
+	if (skb->pkt_type == PACKET_OTHERHOST)
+		skb->pkt_type = PACKET_HOST;
+	store_orig_dstaddr(skb);
+	NF_HOOK(PF_INET, NF_IP_PRE_ROUTING, skb, skb->dev, NULL,
+		br_nf_pre_routing_finish);
+
+	return NF_STOLEN;
+
+inhdr_error:
+//	IP_INC_STATS_BH(IpInHdrErrors);
+out:
+	return NF_DROP;
+}
+
+
+/* PF_BRIDGE/LOCAL_IN ************************************************/
+/* The packet is locally destined, which requires a real
+ * dst_entry, so detach the fake one.  On the way up, the
+ * packet would pass through PRE_ROUTING again (which already
+ * took place when the packet entered the bridge), but we
+ * register an IPv4 PRE_ROUTING 'sabotage' hook that will
+ * prevent this from happening.
+ */
+static unsigned int br_nf_local_in(unsigned int hook, struct sk_buff **pskb, const struct net_device *in, const struct net_device *out, int (*okfn)(struct sk_buff *))
+{
+	struct sk_buff *skb = *pskb;
+
+	if (skb->protocol != __constant_htons(ETH_P_IP))
+		return NF_ACCEPT;
+
+	if (skb->dst == (struct dst_entry *)&__fake_rtable) {
+		dst_release(skb->dst);
+		skb->dst = NULL;
+	}
+
+	return NF_ACCEPT;
+}
+
+
+/* PF_BRIDGE/FORWARD *************************************************/
+static int br_nf_forward_finish(struct sk_buff *skb)
+{
+	NF_HOOK_THRESH(PF_BRIDGE, NF_BR_FORWARD, skb, skb->physindev,
+			skb->dev, br_forward_finish, 1);
+
+	return 0;
+}
+
+/* This is the 'purely bridged' case.  We pass the packet to
+ * netfilter with indev and outdev set to the bridge device,
+ * but we are still able to filter on the 'real' indev/outdev
+ * because another bit of the bridge-nf patch overloads the
+ * '-i' and '-o' iptables interface checks to take
+ * skb->phys{in,out}dev into account as well (so both the real
+ * device and the bridge device will match).
+ */
+static unsigned int br_nf_forward(unsigned int hook, struct sk_buff **pskb, const struct net_device *in, const struct net_device *out, int (*okfn)(struct sk_buff *))
+{
+	struct sk_buff *skb = *pskb;
+
+	// don't mess with non-ip frames, also don't mess with the ip-packets
+	// when br_nf_local_out_finish explicitly says so.
+	if (skb->protocol != __constant_htons(ETH_P_IP) || skb->physindev == NULL)
+		return NF_ACCEPT;
+
+	skb->physoutdev = skb->dev;
+	NF_HOOK(PF_INET, NF_IP_FORWARD, skb, bridge_parent(skb->physindev),
+			bridge_parent(skb->dev), br_nf_forward_finish);
+
+	return NF_STOLEN;
+}
+
+
+/* PF_BRIDGE/LOCAL_OUT ***********************************************/
+static int br_nf_local_out_finish_forward(struct sk_buff *skb)
+{
+	struct net_device *dev;
+
+	dev = skb->physindev;
+	// tell br_nf_forward to stay away
+	skb->physindev = NULL;
+	NF_HOOK(PF_BRIDGE, NF_BR_FORWARD, skb, dev, skb->dev,
+		br_forward_finish);
+
+	return 0;
+}
+
+static int br_nf_local_out_finish(struct sk_buff *skb)
+{
+	NF_HOOK_THRESH(PF_BRIDGE, NF_BR_LOCAL_OUT, skb, NULL, skb->dev,
+			br_forward_finish, INT_MIN + 1);
+
+	return 0;
+}
+
+
+/* This hook sees both locally originated IP packets and forwarded
+ * IP packets (in both cases the destination device is a bridge
+ * device).  For the sake of interface transparency (i.e. properly
+ * overloading the '-o' option), we steal packets destined to
+ * a bridge device away from the IPv4 FORWARD and OUTPUT hooks,
+ * and reinject them later, when we have determined the real
+ * output device.  This reinjecting happens here.
+ *
+ * If skb->physindev is NULL, the bridge-nf code never touched
+ * this packet before, and so the packet was locally originated.
+ * We call the IPv4 LOCAL_OUT hook.
+ *
+ * If skb->physindev isn't NULL, there are two cases:
+ * 1. The packet was IP routed.
+ * 2. The packet was cross-bridge DNAT'ed (see the comment near
+ *    PF_BRIDGE/PRE_ROUTING).
+ * In both cases, we call the IPv4 FORWARD hook.  In case 1,
+ * if the packet originally came from a bridge device, and in
+ * case 2, skb->physindev will have a bridge device as parent,
+ * so we use that parent device as indev.  Otherwise, we just
+ * use physindev.
+ *
+ * If skb->physoutdev == NULL the bridge code never touched the
+ * packet or the packet was routed in br_nf_pre_routing_finish().
+ * We give the packet to the bridge NF_BR_LOCAL_OUT hook.
+ * If not, the packet is actually a bridged one so we give it to
+ * the NF_BR_FORWARD hook.
+ */
+
+static unsigned int br_nf_local_out(unsigned int hook, struct sk_buff **pskb, const struct net_device *in, const struct net_device *out, int (*_okfn)(struct sk_buff *))
+{
+	int hookno, prio;
+	int (*okfn)(struct sk_buff *skb);
+	struct net_device *realindev;
+	struct sk_buff *skb = *pskb;
+
+	if (skb->protocol != __constant_htons(ETH_P_IP))
+		return NF_ACCEPT;
+
+	/* Sometimes we get packets with NULL ->dst here (for example,
+	 * running a dhcp client daemon triggers this).
+	 */
+	if (skb->dst == NULL)
+		return NF_ACCEPT;
+
+	// bridged, take forward
+	// (see big note in front of br_nf_pre_routing_finish)
+	if (skb->physoutdev == &__fake_net_device) {
+		okfn = br_nf_local_out_finish_forward;
+	} else if (skb->physoutdev == NULL) {
+		// non-bridged: routed or locally generated traffic, take local_out
+		// (see big note in front of br_nf_pre_routing_finish)
+		okfn = br_nf_local_out_finish;
+	} else {
+		printk("ARGH: bridge_or_routed hack doesn't work\n");
+		okfn = br_nf_local_out_finish;
+	}
+
+	skb->physoutdev = skb->dev;
+
+	hookno = NF_IP_LOCAL_OUT;
+	prio = NF_IP_PRI_BRIDGE_SABOTAGE;
+	if ((realindev = skb->physindev) != NULL) {
+		hookno = NF_IP_FORWARD;
+		// there is an iptables mangle table FORWARD chain with
+		// priority -150. This chain should see the physical out-dev.
+		prio = NF_IP_PRI_BRIDGE_SABOTAGE_FORWARD;
+		if (has_bridge_parent(realindev))
+			realindev = bridge_parent(realindev);
+	}
+
+	NF_HOOK_THRESH(PF_INET, hookno, skb, realindev,
+			bridge_parent(skb->dev), okfn, prio + 1);
+
+	return NF_STOLEN;
+}
+
+
+/* PF_BRIDGE/POST_ROUTING ********************************************/
+static int br_nf_post_routing_finish(struct sk_buff *skb)
+{
+	__maybe_fixup_src_address(skb);
+	NF_HOOK_THRESH(PF_BRIDGE, NF_BR_POST_ROUTING, skb, NULL,
+			bridge_parent(skb->dev), br_dev_queue_push_xmit, 1);
+
+	return 0;
+}
+
+static unsigned int br_nf_post_routing(unsigned int hook, struct sk_buff **pskb, const struct net_device *in, const struct net_device *out, int (*okfn)(struct sk_buff *))
+{
+	struct sk_buff *skb = *pskb;
+
+	/* Be very paranoid.  */
+	if (skb->mac.raw < skb->head || skb->mac.raw + ETH_HLEN > skb->data) {
+		printk(KERN_CRIT "Argh!! Fuck me harder with a chainsaw. ");
+		if (skb->dev != NULL) {
+			printk("[%s]", skb->dev->name);
+			if (has_bridge_parent(skb->dev))
+				printk("[%s]", bridge_parent(skb->dev)->name);
+		}
+		printk("\n");
+		return NF_ACCEPT;
+	}
+
+	if (skb->protocol != __constant_htons(ETH_P_IP))
+		return NF_ACCEPT;
+
+	/* Sometimes we get packets with NULL ->dst here (for example,
+	 * running a dhcp client daemon triggers this).
+	 */
+	if (skb->dst == NULL)
+		return NF_ACCEPT;
+
+	store_orig_srcaddr(skb);
+	NF_HOOK(PF_INET, NF_IP_POST_ROUTING, skb, NULL,
+		bridge_parent(skb->dev), br_nf_post_routing_finish);
+
+	return NF_STOLEN;
+}
+
+
+/* IPv4/SABOTAGE *****************************************************/
+/* Don't hand locally destined packets to PF_INET/PRE_ROUTING
+ * for the second time.  */
+static unsigned int ipv4_sabotage_in(unsigned int hook, struct sk_buff **pskb, const struct net_device *in, const struct net_device *out, int (*okfn)(struct sk_buff *))
+{
+	if (in->hard_start_xmit == br_dev_xmit &&
+	    okfn != br_nf_pre_routing_finish) {
+		okfn(*pskb);
+		return NF_STOLEN;
+	}
+
+	return NF_ACCEPT;
+}
+
+/* Postpone execution of PF_INET/FORWARD, PF_INET/LOCAL_OUT
+ * and PF_INET/POST_ROUTING until we have done the forwarding
+ * decision in the bridge code and have determined skb->physoutdev.
+ */
+static unsigned int ipv4_sabotage_out(unsigned int hook, struct sk_buff **pskb, const struct net_device *in, const struct net_device *out, int (*okfn)(struct sk_buff *))
+{
+	if (out->hard_start_xmit == br_dev_xmit &&
+	    okfn != br_nf_forward_finish &&
+	    okfn != br_nf_local_out_finish &&
+	    okfn != br_nf_post_routing_finish) {
+		struct sk_buff *skb = *pskb;
+
+		if (hook == NF_IP_FORWARD && skb->physindev == NULL)
+			skb->physindev = (struct net_device *)in;
+		okfn(skb);
+		return NF_STOLEN;
+	}
+
+	return NF_ACCEPT;
+}
+
+
+static struct nf_hook_ops br_nf_ops[] = {
+	{ { NULL, NULL }, br_nf_pre_routing, PF_BRIDGE, NF_BR_PRE_ROUTING, 0 },
+	{ { NULL, NULL }, br_nf_local_in, PF_BRIDGE, NF_BR_LOCAL_IN, 0 },
+	{ { NULL, NULL }, br_nf_forward, PF_BRIDGE, NF_BR_FORWARD, 0 },
+	// we need INT_MIN, so innocent NF_BR_LOCAL_OUT functions don't
+	// get bridged traffic as input
+	{ { NULL, NULL }, br_nf_local_out, PF_BRIDGE, NF_BR_LOCAL_OUT, INT_MIN },
+	{ { NULL, NULL }, br_nf_post_routing, PF_BRIDGE, NF_BR_POST_ROUTING, 0 },
+
+	{ { NULL, NULL }, ipv4_sabotage_in, PF_INET, NF_IP_PRE_ROUTING, NF_IP_PRI_FIRST },
+
+	{ { NULL, NULL }, ipv4_sabotage_out, PF_INET, NF_IP_FORWARD, NF_IP_PRI_BRIDGE_SABOTAGE_FORWARD },
+	{ { NULL, NULL }, ipv4_sabotage_out, PF_INET, NF_IP_LOCAL_OUT, NF_IP_PRI_BRIDGE_SABOTAGE },
+	{ { NULL, NULL }, ipv4_sabotage_out, PF_INET, NF_IP_POST_ROUTING, NF_IP_PRI_FIRST },
+};
+
+#define NUMHOOKS (sizeof(br_nf_ops)/sizeof(br_nf_ops[0]))
+
+
+int br_netfilter_init(void)
+{
+	int i;
+
+#ifndef WE_REALLY_INSIST_ON_NOT_HAVING_NAT_SUPPORT
+	if (sizeof(struct tcp_skb_cb) + 4 >= sizeof(((struct sk_buff *)NULL)->cb)) {
+		extern int __too_little_space_in_control_buffer(void);
+		__too_little_space_in_control_buffer();
+	}
+#endif
+
+	for (i=0;i<NUMHOOKS;i++) {
+		int ret;
+
+		if ((ret = nf_register_hook(&br_nf_ops[i])) >= 0)
+			continue;
+
+		while (i--)
+			nf_unregister_hook(&br_nf_ops[i]);
+
+		return ret;
+	}
+
+	printk(KERN_NOTICE "Bridge firewalling registered\n");
+
+	return 0;
+}
+
+void br_netfilter_fini(void)
+{
+	int i;
+
+	for (i=NUMHOOKS-1;i>=0;i--)
+		nf_unregister_hook(&br_nf_ops[i]);
+}