Merge master.kernel.org:/home/davem/BK/net-2.5

into home.transmeta.com:/home/torvalds/v2.5/linux

include/linux/netdevice.h

@@ -206,7 +206,8 @@ enum netdev_state_t
 	__LINK_STATE_START,
 	__LINK_STATE_PRESENT,
 	__LINK_STATE_SCHED,
-	__LINK_STATE_NOCARRIER
+	__LINK_STATE_NOCARRIER,
+	__LINK_STATE_RX_SCHED
 };
 
 
@@ -330,6 +331,10 @@ struct net_device
 	void                    *ip6_ptr;       /* IPv6 specific data */
 	void			*ec_ptr;	/* Econet specific data	*/
 
+	struct list_head	poll_list;	/* Link to poll list	*/
+	int			quota;
+	int			weight;
+
 	struct Qdisc		*qdisc;
 	struct Qdisc		*qdisc_sleeping;
 	struct Qdisc		*qdisc_list;
@@ -373,6 +378,7 @@ struct net_device
 	int			(*stop)(struct net_device *dev);
 	int			(*hard_start_xmit) (struct sk_buff *skb,
 						    struct net_device *dev);
+	int			(*poll) (struct net_device *dev, int *quota);
 	int			(*hard_header) (struct sk_buff *skb,
 						struct net_device *dev,
 						unsigned short type,
@@ -492,8 +498,11 @@ struct softnet_data
 	int			cng_level;
 	int			avg_blog;
 	struct sk_buff_head	input_pkt_queue;
+	struct list_head	poll_list;
 	struct net_device	*output_queue;
 	struct sk_buff		*completion_queue;
+
+	struct net_device	backlog_dev;	/* Sorry. 8) */
 } __attribute__((__aligned__(SMP_CACHE_BYTES)));
 
 
@@ -547,6 +556,7 @@ static inline int netif_running(struct net_device *dev)
 	return test_bit(__LINK_STATE_START, &dev->state);
 }
 
+
 /* Use this variant when it is known for sure that it
  * is executing from interrupt context.
  */
@@ -578,6 +588,8 @@ static inline void dev_kfree_skb_any(struct sk_buff *skb)
 extern void		net_call_rx_atomic(void (*fn)(void));
 #define HAVE_NETIF_RX 1
 extern int		netif_rx(struct sk_buff *skb);
+#define HAVE_NETIF_RECEIVE_SKB 1
+extern int		netif_receive_skb(struct sk_buff *skb);
 extern int		dev_ioctl(unsigned int cmd, void *);
 extern int		dev_change_flags(struct net_device *, unsigned);
 extern void		dev_queue_xmit_nit(struct sk_buff *skb, struct net_device *dev);
@@ -695,6 +707,78 @@ enum {
 #define netif_msg_rx_status(p)	((p)->msg_enable & NETIF_MSG_RX_STATUS)
 #define netif_msg_pktdata(p)	((p)->msg_enable & NETIF_MSG_PKTDATA)
 
+/* Schedule rx intr now? */
+
+static inline int netif_rx_schedule_prep(struct net_device *dev)
+{
+	return netif_running(dev) &&
+		!test_and_set_bit(__LINK_STATE_RX_SCHED, &dev->state);
+}
+
+/* Add interface to tail of rx poll list. This assumes that _prep has
+ * already been called and returned 1.
+ */
+
+static inline void __netif_rx_schedule(struct net_device *dev)
+{
+	unsigned long flags;
+	int cpu = smp_processor_id();
+
+	local_irq_save(flags);
+	dev_hold(dev);
+	list_add_tail(&dev->poll_list, &softnet_data[cpu].poll_list);
+	if (dev->quota < 0)
+		dev->quota += dev->weight;
+	else
+		dev->quota = dev->weight;
+	__cpu_raise_softirq(cpu, NET_RX_SOFTIRQ);
+	local_irq_restore(flags);
+}
+
+/* Try to reschedule poll. Called by irq handler. */
+
+static inline void netif_rx_schedule(struct net_device *dev)
+{
+	if (netif_rx_schedule_prep(dev))
+		__netif_rx_schedule(dev);
+}
+
+/* Try to reschedule poll. Called by dev->poll() after netif_rx_complete().
+ * Do not inline this?
+ */
+static inline int netif_rx_reschedule(struct net_device *dev, int undo)
+{
+	if (netif_rx_schedule_prep(dev)) {
+		unsigned long flags;
+		int cpu = smp_processor_id();
+
+		dev->quota += undo;
+
+		local_irq_save(flags);
+		list_add_tail(&dev->poll_list, &softnet_data[cpu].poll_list);
+		__cpu_raise_softirq(cpu, NET_RX_SOFTIRQ);
+		local_irq_restore(flags);
+		return 1;
+	}
+	return 0;
+}
+
+/* Remove interface from poll list: it must be in the poll list
+ * on current cpu. This primitive is called by dev->poll(), when
+ * it completes the work. The device cannot be out of poll list at this
+ * moment, it is BUG().
+ */
+static inline void netif_rx_complete(struct net_device *dev)
+{
+	unsigned long flags;
+
+	local_irq_save(flags);
+	if (!test_bit(__LINK_STATE_RX_SCHED, &dev->state)) BUG();
+	list_del(&dev->poll_list);
+	clear_bit(__LINK_STATE_RX_SCHED, &dev->state);
+	local_irq_restore(flags);
+}
+
 /* These functions live elsewhere (drivers/net/net_init.c, but related) */
 
 extern void		ether_setup(struct net_device *dev);
@@ -719,6 +803,7 @@ extern void		dev_mcast_init(void);
 extern int		netdev_register_fc(struct net_device *dev, void (*stimul)(struct net_device *dev));
 extern void		netdev_unregister_fc(int bit);
 extern int		netdev_max_backlog;
+extern int		weight_p;
 extern unsigned long	netdev_fc_xoff;
 extern atomic_t netdev_dropping;
 extern int		netdev_set_master(struct net_device *dev, struct net_device *master);

include/linux/netfilter_arp.h

+#ifndef __LINUX_ARP_NETFILTER_H
+#define __LINUX_ARP_NETFILTER_H
+
+/* ARP-specific defines for netfilter.
+ * (C)2002 Rusty Russell IBM -- This code is GPL.
+ */
+
+#include <linux/config.h>
+#include <linux/netfilter.h>
+
+/* There is no PF_ARP. */
+#define NF_ARP		0
+
+/* ARP Hooks */
+#define NF_ARP_IN	0
+#define NF_ARP_OUT	1
+#define NF_ARP_NUMHOOKS	2
+
+#endif /* __LINUX_ARP_NETFILTER_H */

include/linux/netfilter_arp/arp_tables.h

+/*
+ * 	Format of an ARP firewall descriptor
+ *
+ * 	src, tgt, src_mask, tgt_mask, arpop, arpop_mask are always stored in
+ *	network byte order.
+ * 	flags are stored in host byte order (of course).
+ */
+
+#ifndef _ARPTABLES_H
+#define _ARPTABLES_H
+
+#ifdef __KERNEL__
+#include <linux/if.h>
+#include <linux/types.h>
+#include <linux/in.h>
+#include <linux/if_arp.h>
+#include <linux/skbuff.h>
+#endif
+
+#include <linux/netfilter_arp.h>
+
+#define ARPT_FUNCTION_MAXNAMELEN 30
+#define ARPT_TABLE_MAXNAMELEN 32
+
+#define ARPT_DEV_ADDR_LEN_MAX 16
+
+struct arpt_devaddr_info {
+	char addr[ARPT_DEV_ADDR_LEN_MAX];
+	char mask[ARPT_DEV_ADDR_LEN_MAX];
+};
+
+/* Yes, Virginia, you have to zero the padding. */
+struct arpt_arp {
+	/* Source and target IP addr */
+	struct in_addr src, tgt;
+	/* Mask for src and target IP addr */
+	struct in_addr smsk, tmsk;
+
+	/* Device hw address length, src+target device addresses */
+	u_int8_t arhln, arhln_mask;
+	struct arpt_devaddr_info src_devaddr;
+	struct arpt_devaddr_info tgt_devaddr;
+
+	/* ARP operation code. */
+	u_int16_t arpop, arpop_mask;
+
+	/* ARP hardware address and protocol address format. */
+	u_int16_t arhrd, arhrd_mask;
+	u_int16_t arpro, arpro_mask;
+
+	/* The protocol address length is only accepted if it is 4
+	 * so there is no use in offering a way to do filtering on it.
+	 */
+
+	char iniface[IFNAMSIZ], outiface[IFNAMSIZ];
+	unsigned char iniface_mask[IFNAMSIZ], outiface_mask[IFNAMSIZ];
+
+	/* Flags word */
+	u_int8_t flags;
+	/* Inverse flags */
+	u_int16_t invflags;
+};
+
+struct arpt_entry_target
+{
+	union {
+		struct {
+			u_int16_t target_size;
+
+			/* Used by userspace */
+			char name[ARPT_FUNCTION_MAXNAMELEN];
+		} user;
+		struct {
+			u_int16_t target_size;
+
+			/* Used inside the kernel */
+			struct arpt_target *target;
+		} kernel;
+
+		/* Total length */
+		u_int16_t target_size;
+	} u;
+
+	unsigned char data[0];
+};
+
+struct arpt_standard_target
+{
+	struct arpt_entry_target target;
+	int verdict;
+};
+
+struct arpt_counters
+{
+	u_int64_t pcnt, bcnt;			/* Packet and byte counters */
+};
+
+/* Values for "flag" field in struct arpt_ip (general arp structure).
+ * No flags defined yet.
+ */
+#define ARPT_F_MASK		0x00	/* All possible flag bits mask. */
+
+/* Values for "inv" field in struct arpt_arp. */
+#define ARPT_INV_VIA_IN		0x0001	/* Invert the sense of IN IFACE. */
+#define ARPT_INV_VIA_OUT	0x0002	/* Invert the sense of OUT IFACE */
+#define ARPT_INV_SRCIP		0x0004	/* Invert the sense of SRC IP. */
+#define ARPT_INV_TGTIP		0x0008	/* Invert the sense of TGT IP. */
+#define ARPT_INV_SRCDEVADDR	0x0010	/* Invert the sense of SRC DEV ADDR. */
+#define ARPT_INV_TGTDEVADDR	0x0020	/* Invert the sense of TGT DEV ADDR. */
+#define ARPT_INV_ARPOP		0x0040	/* Invert the sense of ARP OP. */
+#define ARPT_INV_ARPHRD		0x0080	/* Invert the sense of ARP HRD. */
+#define ARPT_INV_ARPPRO		0x0100	/* Invert the sense of ARP PRO. */
+#define ARPT_INV_ARPHLN		0x0200	/* Invert the sense of ARP HLN. */
+#define ARPT_INV_MASK		0x007F	/* All possible flag bits mask. */
+
+/* This structure defines each of the firewall rules.  Consists of 3
+   parts which are 1) general ARP header stuff 2) match specific
+   stuff 3) the target to perform if the rule matches */
+struct arpt_entry
+{
+	struct arpt_arp arp;
+
+	/* Size of arpt_entry + matches */
+	u_int16_t target_offset;
+	/* Size of arpt_entry + matches + target */
+	u_int16_t next_offset;
+
+	/* Back pointer */
+	unsigned int comefrom;
+
+	/* Packet and byte counters. */
+	struct arpt_counters counters;
+
+	/* The matches (if any), then the target. */
+	unsigned char elems[0];
+};
+
+/*
+ * New IP firewall options for [gs]etsockopt at the RAW IP level.
+ * Unlike BSD Linux inherits IP options so you don't have to use a raw
+ * socket for this. Instead we check rights in the calls.
+ */
+#define ARPT_BASE_CTL		96	/* base for firewall socket options */
+
+#define ARPT_SO_SET_REPLACE		(ARPT_BASE_CTL)
+#define ARPT_SO_SET_ADD_COUNTERS	(ARPT_BASE_CTL + 1)
+#define ARPT_SO_SET_MAX			ARPT_SO_SET_ADD_COUNTERS
+
+#define ARPT_SO_GET_INFO		(ARPT_BASE_CTL)
+#define ARPT_SO_GET_ENTRIES		(ARPT_BASE_CTL + 1)
+#define ARPT_SO_GET_MAX			ARPT_SO_GET_ENTRIES
+
+/* CONTINUE verdict for targets */
+#define ARPT_CONTINUE 0xFFFFFFFF
+
+/* For standard target */
+#define ARPT_RETURN (-NF_MAX_VERDICT - 1)
+
+/* The argument to ARPT_SO_GET_INFO */
+struct arpt_getinfo
+{
+	/* Which table: caller fills this in. */
+	char name[ARPT_TABLE_MAXNAMELEN];
+
+	/* Kernel fills these in. */
+	/* Which hook entry points are valid: bitmask */
+	unsigned int valid_hooks;
+
+	/* Hook entry points: one per netfilter hook. */
+	unsigned int hook_entry[NF_ARP_NUMHOOKS];
+
+	/* Underflow points. */
+	unsigned int underflow[NF_ARP_NUMHOOKS];
+
+	/* Number of entries */
+	unsigned int num_entries;
+
+	/* Size of entries. */
+	unsigned int size;
+};
+
+/* The argument to ARPT_SO_SET_REPLACE. */
+struct arpt_replace
+{
+	/* Which table. */
+	char name[ARPT_TABLE_MAXNAMELEN];
+
+	/* Which hook entry points are valid: bitmask.  You can't
+           change this. */
+	unsigned int valid_hooks;
+
+	/* Number of entries */
+	unsigned int num_entries;
+
+	/* Total size of new entries */
+	unsigned int size;
+
+	/* Hook entry points. */
+	unsigned int hook_entry[NF_ARP_NUMHOOKS];
+
+	/* Underflow points. */
+	unsigned int underflow[NF_ARP_NUMHOOKS];
+
+	/* Information about old entries: */
+	/* Number of counters (must be equal to current number of entries). */
+	unsigned int num_counters;
+	/* The old entries' counters. */
+	struct arpt_counters *counters;
+
+	/* The entries (hang off end: not really an array). */
+	struct arpt_entry entries[0];
+};
+
+/* The argument to ARPT_SO_ADD_COUNTERS. */
+struct arpt_counters_info
+{
+	/* Which table. */
+	char name[ARPT_TABLE_MAXNAMELEN];
+
+	unsigned int num_counters;
+
+	/* The counters (actually `number' of these). */
+	struct arpt_counters counters[0];
+};
+
+/* The argument to ARPT_SO_GET_ENTRIES. */
+struct arpt_get_entries
+{
+	/* Which table: user fills this in. */
+	char name[ARPT_TABLE_MAXNAMELEN];
+
+	/* User fills this in: total entry size. */
+	unsigned int size;
+
+	/* The entries. */
+	struct arpt_entry entrytable[0];
+};
+
+/* Standard return verdict, or do jump. */
+#define ARPT_STANDARD_TARGET ""
+/* Error verdict. */
+#define ARPT_ERROR_TARGET "ERROR"
+
+/* Helper functions */
+static __inline__ struct arpt_entry_target *arpt_get_target(struct arpt_entry *e)
+{
+	return (void *)e + e->target_offset;
+}
+
+/* fn returns 0 to continue iteration */
+#define ARPT_ENTRY_ITERATE(entries, size, fn, args...)		\
+({								\
+	unsigned int __i;					\
+	int __ret = 0;						\
+	struct arpt_entry *__entry;				\
+								\
+	for (__i = 0; __i < (size); __i += __entry->next_offset) { \
+		__entry = (void *)(entries) + __i;		\
+								\
+		__ret = fn(__entry , ## args);			\
+		if (__ret != 0)					\
+			break;					\
+	}							\
+	__ret;							\
+})
+
+/*
+ *	Main firewall chains definitions and global var's definitions.
+ */
+#ifdef __KERNEL__
+
+/* Registration hooks for targets. */
+struct arpt_target
+{
+	struct list_head list;
+
+	const char name[ARPT_FUNCTION_MAXNAMELEN];
+
+	/* Returns verdict. */
+	unsigned int (*target)(struct sk_buff **pskb,
+			       unsigned int hooknum,
+			       const struct net_device *in,
+			       const struct net_device *out,
+			       const void *targinfo,
+			       void *userdata);
+
+	/* Called when user tries to insert an entry of this type:
+           hook_mask is a bitmask of hooks from which it can be
+           called. */
+	/* Should return true or false. */
+	int (*checkentry)(const char *tablename,
+			  const struct arpt_entry *e,
+			  void *targinfo,
+			  unsigned int targinfosize,
+			  unsigned int hook_mask);
+
+	/* Called when entry of this type deleted. */
+	void (*destroy)(void *targinfo, unsigned int targinfosize);
+
+	/* Set this to THIS_MODULE if you are a module, otherwise NULL */
+	struct module *me;
+};
+
+extern int arpt_register_target(struct arpt_target *target);
+extern void arpt_unregister_target(struct arpt_target *target);
+
+/* Furniture shopping... */
+struct arpt_table
+{
+	struct list_head list;
+
+	/* A unique name... */
+	char name[ARPT_TABLE_MAXNAMELEN];
+
+	/* Seed table: copied in register_table */
+	struct arpt_replace *table;
+
+	/* What hooks you will enter on */
+	unsigned int valid_hooks;
+
+	/* Lock for the curtain */
+	rwlock_t lock;
+
+	/* Man behind the curtain... */
+	struct arpt_table_info *private;
+
+	/* Set this to THIS_MODULE if you are a module, otherwise NULL */
+	struct module *me;
+};
+
+extern int arpt_register_table(struct arpt_table *table);
+extern void arpt_unregister_table(struct arpt_table *table);
+extern unsigned int arpt_do_table(struct sk_buff **pskb,
+				  unsigned int hook,
+				  const struct net_device *in,
+				  const struct net_device *out,
+				  struct arpt_table *table,
+				  void *userdata);
+
+#define ARPT_ALIGN(s) (((s) + (__alignof__(struct arpt_entry)-1)) & ~(__alignof__(struct arpt_entry)-1))
+#endif /*__KERNEL__*/
+#endif /* _ARPTABLES_H */

include/linux/netfilter_ipv4/ip_nat.h

@@ -11,8 +11,13 @@ enum ip_nat_manip_type
 	IP_NAT_MANIP_DST
 };
 
+#ifndef CONFIG_IP_NF_NAT_LOCAL
 /* SRC manip occurs only on POST_ROUTING */
 #define HOOK2MANIP(hooknum) ((hooknum) != NF_IP_POST_ROUTING)
+#else
+/* SRC manip occurs POST_ROUTING or LOCAL_IN */
+#define HOOK2MANIP(hooknum) ((hooknum) != NF_IP_POST_ROUTING && (hooknum) != NF_IP_LOCAL_IN)
+#endif
 
 /* 2.3.19 (I hope) will define this in linux/netfilter_ipv4.h. */
 #ifndef SO_ORIGINAL_DST

include/linux/sysctl.h

@@ -202,7 +202,8 @@ enum
 	NET_CORE_NO_CONG_THRESH=13,
 	NET_CORE_NO_CONG=14,
 	NET_CORE_LO_CONG=15,
-	NET_CORE_MOD_CONG=16
+	NET_CORE_MOD_CONG=16,
+	NET_CORE_DEV_WEIGHT=17
 };
 
 /* /proc/sys/net/ethernet */

net/core/dev.c

@@ -798,6 +798,19 @@ int dev_close(struct net_device *dev)
 
 	clear_bit(__LINK_STATE_START, &dev->state);
 
+	/* Synchronize to scheduled poll. We cannot touch poll list,
+	 * it can be even on different cpu. So just clear netif_running(),
+	 * and wait when poll really will happen. Actually, the best place
+	 * for this is inside dev->stop() after device stopped its irq
+	 * engine, but this requires more changes in devices. */
+
+	smp_mb__after_clear_bit(); /* Commit netif_running(). */
+	while (test_bit(__LINK_STATE_RX_SCHED, &dev->state)) {
+		/* No hurry. */
+		current->state = TASK_INTERRUPTIBLE;
+		schedule_timeout(1);
+	}
+
 	/*
 	 *	Call the device specific close. This cannot fail.
 	 *	Only if device is UP
@@ -1072,6 +1085,7 @@ int dev_queue_xmit(struct sk_buff *skb)
   =======================================================================*/
 
 int netdev_max_backlog = 300;
+int weight_p = 64;            /* old backlog weight */
 /* These numbers are selected based on intuition and some
  * experimentatiom, if you have more scientific way of doing this
  * please go ahead and fix things.
@@ -1237,13 +1251,11 @@ int netif_rx(struct sk_buff *skb)
 enqueue:
 			dev_hold(skb->dev);
 			__skb_queue_tail(&queue->input_pkt_queue,skb);
-			/* Runs from irqs or BH's, no need to wake BH */
-			cpu_raise_softirq(this_cpu, NET_RX_SOFTIRQ);
 			local_irq_restore(flags);
 #ifndef OFFLINE_SAMPLE
 			get_sample_stats(this_cpu);
 #endif
-			return softnet_data[this_cpu].cng_level;
+			return queue->cng_level;
 		}
 
 		if (queue->throttle) {
@@ -1253,6 +1265,8 @@ int netif_rx(struct sk_buff *skb)
 				netdev_wakeup();
 #endif
 		}
+
+		netif_rx_schedule(&queue->backlog_dev);
 		goto enqueue;
 	}
 
@@ -1308,19 +1322,12 @@ static int deliver_to_old_ones(struct packet_type *pt, struct sk_buff *skb, int
 	return ret;
 }
 
-/* Reparent skb to master device. This function is called
- * only from net_rx_action under BR_NETPROTO_LOCK. It is misuse
- * of BR_NETPROTO_LOCK, but it is OK for now.
- */
 static __inline__ void skb_bond(struct sk_buff *skb)
 {
 	struct net_device *dev = skb->dev;
-	
-	if (dev->master) {
-		dev_hold(dev->master);
+
+	if (dev->master)
 		skb->dev = dev->master;
-		dev_put(dev);
-	}
 }
 
 static void net_tx_action(struct softirq_action *h)
@@ -1416,121 +1423,138 @@ static inline void handle_diverter(struct sk_buff *skb)
 }
 #endif   /* CONFIG_NET_DIVERT */
 
-
-static void net_rx_action(struct softirq_action *h)
+int netif_receive_skb(struct sk_buff *skb)
 {
-	int this_cpu = smp_processor_id();
-	struct softnet_data *queue = &softnet_data[this_cpu];
-	unsigned long start_time = jiffies;
-	int bugdet = netdev_max_backlog;
-
-	br_read_lock(BR_NETPROTO_LOCK);
-
-	for (;;) {
-		struct sk_buff *skb;
-		struct net_device *rx_dev;
-
-		local_irq_disable();
-		skb = __skb_dequeue(&queue->input_pkt_queue);
-		local_irq_enable();
+	struct packet_type *ptype, *pt_prev;
+	int ret = NET_RX_DROP;
+	unsigned short type = skb->protocol;
 
-		if (skb == NULL)
-			break;
+	if (skb->stamp.tv_sec == 0)
+		do_gettimeofday(&skb->stamp);
 
-		skb_bond(skb);
+	skb_bond(skb);
 
-		rx_dev = skb->dev;
+	netdev_rx_stat[smp_processor_id()].total++;
 
 #ifdef CONFIG_NET_FASTROUTE
-		if (skb->pkt_type == PACKET_FASTROUTE) {
-			netdev_rx_stat[this_cpu].fastroute_deferred_out++;
-			dev_queue_xmit(skb);
-			dev_put(rx_dev);
-			continue;
-		}
+	if (skb->pkt_type == PACKET_FASTROUTE) {
+		netdev_rx_stat[smp_processor_id()].fastroute_deferred_out++;
+		return dev_queue_xmit(skb);
+	}
 #endif
-		skb->h.raw = skb->nh.raw = skb->data;
-		{
-			struct packet_type *ptype, *pt_prev;
-			unsigned short type = skb->protocol;
-
-			pt_prev = NULL;
-			for (ptype = ptype_all; ptype; ptype = ptype->next) {
-				if (!ptype->dev || ptype->dev == skb->dev) {
-					if (pt_prev) {
-						if (!pt_prev->data) {
-							deliver_to_old_ones(pt_prev, skb, 0);
-						} else {
-							atomic_inc(&skb->users);
-							pt_prev->func(skb,
-								      skb->dev,
-								      pt_prev);
-						}
-					}
-					pt_prev = ptype;
+
+	skb->h.raw = skb->nh.raw = skb->data;
+
+	pt_prev = NULL;
+	for (ptype = ptype_all; ptype; ptype = ptype->next) {
+		if (!ptype->dev || ptype->dev == skb->dev) {
+			if (pt_prev) {
+				if (!pt_prev->data) {
+					ret = deliver_to_old_ones(pt_prev, skb, 0);
+				} else {
+					atomic_inc(&skb->users);
+					ret = pt_prev->func(skb, skb->dev, pt_prev);
 				}
 			}
+			pt_prev = ptype;
+		}
+	}
 
 #ifdef CONFIG_NET_DIVERT
-			if (skb->dev->divert && skb->dev->divert->divert)
-				handle_diverter(skb);
+	if (skb->dev->divert && skb->dev->divert->divert)
+		ret = handle_diverter(skb);
 #endif /* CONFIG_NET_DIVERT */
-
 			
 #if defined(CONFIG_BRIDGE) || defined(CONFIG_BRIDGE_MODULE)
-			if (skb->dev->br_port != NULL &&
-			    br_handle_frame_hook != NULL) {
-				handle_bridge(skb, pt_prev);
-				dev_put(rx_dev);
-				continue;
-			}
+	if (skb->dev->br_port != NULL &&
+	    br_handle_frame_hook != NULL) {
+		return handle_bridge(skb, pt_prev);
+	}
 #endif
 
-			for (ptype=ptype_base[ntohs(type)&15];ptype;ptype=ptype->next) {
-				if (ptype->type == type &&
-				    (!ptype->dev || ptype->dev == skb->dev)) {
-					if (pt_prev) {
-						if (!pt_prev->data)
-							deliver_to_old_ones(pt_prev, skb, 0);
-						else {
-							atomic_inc(&skb->users);
-							pt_prev->func(skb,
-								      skb->dev,
-								      pt_prev);
-						}
-					}
-					pt_prev = ptype;
+	for (ptype=ptype_base[ntohs(type)&15];ptype;ptype=ptype->next) {
+		if (ptype->type == type &&
+		    (!ptype->dev || ptype->dev == skb->dev)) {
+			if (pt_prev) {
+				if (!pt_prev->data) {
+					ret = deliver_to_old_ones(pt_prev, skb, 0);
+				} else {
+					atomic_inc(&skb->users);
+					ret = pt_prev->func(skb, skb->dev, pt_prev);
 				}
 			}
+			pt_prev = ptype;
+		}
+	}
 
-			if (pt_prev) {
-				if (!pt_prev->data)
-					deliver_to_old_ones(pt_prev, skb, 1);
-				else
-					pt_prev->func(skb, skb->dev, pt_prev);
-			} else
-				kfree_skb(skb);
+	if (pt_prev) {
+		if (!pt_prev->data) {
+			ret = deliver_to_old_ones(pt_prev, skb, 1);
+		} else {
+			ret = pt_prev->func(skb, skb->dev, pt_prev);
 		}
+	} else {
+		kfree_skb(skb);
+		/* Jamal, now you will not able to escape explaining
+		 * me how you were going to use this. :-)
+		 */
+		ret = NET_RX_DROP;
+	}
 
-		dev_put(rx_dev);
+	return ret;
+}
 
-		if (bugdet-- < 0 || jiffies - start_time > 1)
-			goto softnet_break;
+static int process_backlog(struct net_device *backlog_dev, int *budget)
+{
+	int work = 0;
+	int quota = min(backlog_dev->quota, *budget);
+	int this_cpu = smp_processor_id();
+	struct softnet_data *queue = &softnet_data[this_cpu];
+	unsigned long start_time = jiffies;
+
+	for (;;) {
+		struct sk_buff *skb;
+		struct net_device *dev;
+
+		local_irq_disable();
+		skb = __skb_dequeue(&queue->input_pkt_queue);
+		if (skb == NULL)
+			goto job_done;
+		local_irq_enable();
+
+		dev = skb->dev;
+
+		netif_receive_skb(skb);
+
+		dev_put(dev);
+
+		work++;
+
+		if (work >= quota || jiffies - start_time > 1)
+			break;
 
 #ifdef CONFIG_NET_HW_FLOWCONTROL
-	if (queue->throttle && queue->input_pkt_queue.qlen < no_cong_thresh ) {
-		if (atomic_dec_and_test(&netdev_dropping)) {
-			queue->throttle = 0;
-			netdev_wakeup();
-			goto softnet_break;
+		if (queue->throttle && queue->input_pkt_queue.qlen < no_cong_thresh ) {
+			if (atomic_dec_and_test(&netdev_dropping)) {
+				queue->throttle = 0;
+				netdev_wakeup();
+				break;
+			}
 		}
-	}
 #endif
-
 	}
-	br_read_unlock(BR_NETPROTO_LOCK);
 
-	local_irq_disable();
+	backlog_dev->quota -= work;
+	*budget -= work;
+	return -1;
+
+job_done:
+	backlog_dev->quota -= work;
+	*budget -= work;
+
+	list_del(&backlog_dev->poll_list);
+	clear_bit(__LINK_STATE_RX_SCHED, &backlog_dev->state);
+
 	if (queue->throttle) {
 		queue->throttle = 0;
 #ifdef CONFIG_NET_HW_FLOWCONTROL
@@ -1539,21 +1563,53 @@ static void net_rx_action(struct softirq_action *h)
 #endif
 	}
 	local_irq_enable();
+	return 0;
+}
 
-	NET_PROFILE_LEAVE(softnet_process);
-	return;
+static void net_rx_action(struct softirq_action *h)
+{
+	int this_cpu = smp_processor_id();
+	struct softnet_data *queue = &softnet_data[this_cpu];
+	unsigned long start_time = jiffies;
+	int budget = netdev_max_backlog;
 
-softnet_break:
+	br_read_lock(BR_NETPROTO_LOCK);
+	local_irq_disable();
+
+	while (!list_empty(&queue->poll_list)) {
+		struct net_device *dev;
+
+		if (budget <= 0 || jiffies - start_time > 1)
+			goto softnet_break;
+
+		local_irq_enable();
+
+		dev = list_entry(queue->poll_list.next, struct net_device, poll_list);
+
+		if (dev->quota <= 0 || dev->poll(dev, &budget)) {
+			local_irq_disable();
+			list_del(&dev->poll_list);
+			list_add_tail(&dev->poll_list, &queue->poll_list);
+			if (dev->quota < 0)
+				dev->quota += dev->weight;
+			else
+				dev->quota = dev->weight;
+		} else {
+			dev_put(dev);
+			local_irq_disable();
+		}
+	}
+
+	local_irq_enable();
 	br_read_unlock(BR_NETPROTO_LOCK);
+	return;
 
-	local_irq_disable();
+softnet_break:
 	netdev_rx_stat[this_cpu].time_squeeze++;
-	/* This already runs in BH context, no need to wake up BH's */
-	cpu_raise_softirq(this_cpu, NET_RX_SOFTIRQ);
-	local_irq_enable();
+	__cpu_raise_softirq(this_cpu, NET_RX_SOFTIRQ);
 
-	NET_PROFILE_LEAVE(softnet_process);
-	return;
+	local_irq_enable();
+	br_read_unlock(BR_NETPROTO_LOCK);
 }
 
 static gifconf_func_t * gifconf_list [NPROTO];
@@ -2626,6 +2682,7 @@ int __init net_dev_init(void)
 	if (!dev_boot_phase)
 		return 0;
 
+
 #ifdef CONFIG_NET_DIVERT
 	dv_init();
 #endif /* CONFIG_NET_DIVERT */
@@ -2643,8 +2700,13 @@ int __init net_dev_init(void)
 		queue->cng_level = 0;
 		queue->avg_blog = 10; /* arbitrary non-zero */
 		queue->completion_queue = NULL;
+		INIT_LIST_HEAD(&queue->poll_list);
+		set_bit(__LINK_STATE_START, &queue->backlog_dev.state);
+		queue->backlog_dev.weight = weight_p;
+		queue->backlog_dev.poll = process_backlog;
+		atomic_set(&queue->backlog_dev.refcnt, 1);
 	}
-	
+
 #ifdef CONFIG_NET_PROFILE
 	net_profile_init();
 	NET_PROFILE_REGISTER(dev_queue_xmit);
@@ -2744,7 +2806,6 @@ int __init net_dev_init(void)
 #ifdef CONFIG_NET_SCHED
 	pktsched_init();
 #endif
-
 	/*
 	 *	Initialise network devices
 	 */

net/core/sysctl_net_core.c

@@ -12,6 +12,7 @@
 #ifdef CONFIG_SYSCTL
 
 extern int netdev_max_backlog;
+extern int weight_p;
 extern int no_cong_thresh;
 extern int no_cong;
 extern int lo_cong;
@@ -47,6 +48,9 @@ ctl_table core_table[] = {
 	{NET_CORE_RMEM_DEFAULT, "rmem_default",
 	 &sysctl_rmem_default, sizeof(int), 0644, NULL,
 	 &proc_dointvec},
+	{NET_CORE_DEV_WEIGHT, "dev_weight",
+	 &weight_p, sizeof(int), 0644, NULL,
+	 &proc_dointvec},
 	{NET_CORE_MAX_BACKLOG, "netdev_max_backlog",
 	 &netdev_max_backlog, sizeof(int), 0644, NULL,
 	 &proc_dointvec},

net/ipv4/arp.c

@@ -112,7 +112,7 @@
 #include <asm/system.h>
 #include <asm/uaccess.h>
 
-
+#include <linux/netfilter_arp.h>
 
 /*
  *	Interface to generic neighbour cache.
@@ -561,7 +561,8 @@ void arp_send(int type, int ptype, u32 dest_ip,
 	arp_ptr+=dev->addr_len;
 	memcpy(arp_ptr, &dest_ip, 4);
 
-	dev_queue_xmit(skb);
+	/* Send it off, maybe filter it using firewalling first.  */
+	NF_HOOK(NF_ARP, NF_ARP_OUT, skb, NULL, dev, dev_queue_xmit);
 	return;
 
 out:
@@ -574,45 +575,31 @@ static void parp_redo(struct sk_buff *skb)
 }
 
 /*
- *	Receive an arp request by the device layer.
+ *	Process an arp request.
  */
 
-int arp_rcv(struct sk_buff *skb, struct net_device *dev, struct packet_type *pt)
+int arp_process(struct sk_buff *skb)
 {
-	struct arphdr *arp = skb->nh.arph;
-	unsigned char *arp_ptr= (unsigned char *)(arp+1);
+	struct net_device *dev = skb->dev;
+	struct in_device *in_dev = in_dev_get(dev);
+	struct arphdr *arp;
+	unsigned char *arp_ptr;
 	struct rtable *rt;
 	unsigned char *sha, *tha;
 	u32 sip, tip;
 	u16 dev_type = dev->type;
 	int addr_type;
-	struct in_device *in_dev = in_dev_get(dev);
 	struct neighbour *n;
 
-/*
- *	The hardware length of the packet should match the hardware length
- *	of the device.  Similarly, the hardware types should match.  The
- *	device should be ARP-able.  Also, if pln is not 4, then the lookup
- *	is not from an IP number.  We can't currently handle this, so toss
- *	it. 
- */  
-	if (in_dev == NULL ||
-	    arp->ar_hln != dev->addr_len    || 
-	    dev->flags & IFF_NOARP ||
-	    skb->pkt_type == PACKET_OTHERHOST ||
-	    skb->pkt_type == PACKET_LOOPBACK ||
-	    arp->ar_pln != 4)
+	/* arp_rcv below verifies the ARP header, verifies the device
+	 * is ARP'able, and linearizes the SKB (if needed).
+	 */
+
+	if (in_dev == NULL)
 		goto out;
 
-	if ((skb = skb_share_check(skb, GFP_ATOMIC)) == NULL)
-		goto out_of_mem;
-
-	if (skb_is_nonlinear(skb)) {
-		if (skb_linearize(skb, GFP_ATOMIC) != 0)
-			goto freeskb;
-		arp = skb->nh.arph;
-		arp_ptr= (unsigned char *)(arp+1);
-	}
+	arp = skb->nh.arph;
+	arp_ptr= (unsigned char *)(arp+1);
 
 	switch (dev_type) {
 	default:	
@@ -827,13 +814,41 @@ int arp_rcv(struct sk_buff *skb, struct net_device *dev, struct packet_type *pt)
 out:
 	if (in_dev)
 		in_dev_put(in_dev);
-freeskb:
 	kfree_skb(skb);
-out_of_mem:
 	return 0;
 }
 
 
+/*
+ *	Receive an arp request from the device layer.
+ */
+
+int arp_rcv(struct sk_buff *skb, struct net_device *dev, struct packet_type *pt)
+{
+	struct arphdr *arp = skb->nh.arph;
+
+	if (arp->ar_hln != dev->addr_len ||
+	    dev->flags & IFF_NOARP ||
+	    skb->pkt_type == PACKET_OTHERHOST ||
+	    skb->pkt_type == PACKET_LOOPBACK ||
+	    arp->ar_pln != 4)
+		goto freeskb;
+
+	if ((skb = skb_share_check(skb, GFP_ATOMIC)) == NULL)
+		goto out_of_mem;
+
+	if (skb_is_nonlinear(skb)) {
+		if (skb_linearize(skb, GFP_ATOMIC) != 0)
+			goto freeskb;
+	}
+
+	return NF_HOOK(NF_ARP, NF_ARP_IN, skb, dev, NULL, arp_process);
+
+freeskb:
+	kfree_skb(skb);
+out_of_mem:
+	return 0;
+}
 
 /*
  *	User level interface (ioctl, /proc)

net/ipv4/netfilter/Config.in

@@ -47,6 +47,7 @@ if [ "$CONFIG_IP_NF_IPTABLES" != "n" ]; then
       define_bool CONFIG_IP_NF_NAT_NEEDED y
       dep_tristate '    MASQUERADE target support' CONFIG_IP_NF_TARGET_MASQUERADE $CONFIG_IP_NF_NAT
       dep_tristate '    REDIRECT target support' CONFIG_IP_NF_TARGET_REDIRECT $CONFIG_IP_NF_NAT
+      bool '    NAT of local connections' CONFIG_IP_NF_NAT_LOCAL
       if [ "$CONFIG_EXPERIMENTAL" = "y" ]; then
         dep_tristate '    Basic SNMP-ALG support (EXPERIMENTAL)' CONFIG_IP_NF_NAT_SNMP_BASIC $CONFIG_IP_NF_NAT
       fi
@@ -79,6 +80,11 @@ if [ "$CONFIG_IP_NF_IPTABLES" != "n" ]; then
   dep_tristate '  TCPMSS target support' CONFIG_IP_NF_TARGET_TCPMSS $CONFIG_IP_NF_IPTABLES
 fi
 
+tristate 'ARP tables support' CONFIG_IP_NF_ARPTABLES
+if [ "$CONFIG_IP_NF_ARPTABLES" != "n" ]; then
+  dep_tristate '  ARP packet filtering' CONFIG_IP_NF_ARPFILTER $CONFIG_IP_NF_ARPTABLES 
+fi
+
 # Backwards compatibility modules: only if you don't build in the others.
 if [ "$CONFIG_IP_NF_CONNTRACK" != "y" ]; then
   if [ "$CONFIG_IP_NF_IPTABLES" != "y" ]; then

net/ipv4/netfilter/Makefile

@@ -9,7 +9,7 @@
 
 O_TARGET := netfilter.o
 
-export-objs = ip_conntrack_standalone.o ip_conntrack_ftp.o ip_fw_compat.o ip_nat_standalone.o ip_tables.o
+export-objs = ip_conntrack_standalone.o ip_conntrack_ftp.o ip_fw_compat.o ip_nat_standalone.o ip_tables.o arp_tables.o
 
 # Multipart objects.
 list-multi		:= ip_conntrack.o iptable_nat.o ipfwadm.o ipchains.o
@@ -75,6 +75,12 @@ obj-$(CONFIG_IP_NF_TARGET_LOG) += ipt_LOG.o
 obj-$(CONFIG_IP_NF_TARGET_ULOG) += ipt_ULOG.o
 obj-$(CONFIG_IP_NF_TARGET_TCPMSS) += ipt_TCPMSS.o
 
+# generic ARP tables
+obj-$(CONFIG_IP_NF_ARPTABLES) += arp_tables.o
+
+# just filtering instance of ARP tables for now
+obj-$(CONFIG_IP_NF_ARPFILTER) += arptable_filter.o
+
 # backwards compatibility 
 obj-$(CONFIG_IP_NF_COMPAT_IPCHAINS) += ipchains.o
 obj-$(CONFIG_IP_NF_COMPAT_IPFWADM) += ipfwadm.o

net/ipv4/netfilter/arptable_filter.c

+/*
+ * Filtering ARP tables module.
+ *
+ * Copyright (C) 2002 David S. Miller (davem@redhat.com)
+ *
+ */
+
+#include <linux/module.h>
+#include <linux/netfilter_arp/arp_tables.h>
+
+#define FILTER_VALID_HOOKS ((1 << NF_ARP_IN) | (1 << NF_ARP_OUT))
+
+/* Standard entry. */
+struct arpt_standard
+{
+	struct arpt_entry entry;
+	struct arpt_standard_target target;
+};
+
+struct arpt_error_target
+{
+	struct arpt_entry_target target;
+	char errorname[ARPT_FUNCTION_MAXNAMELEN];
+};
+
+struct arpt_error
+{
+	struct arpt_entry entry;
+	struct arpt_error_target target;
+};
+
+static struct
+{
+	struct arpt_replace repl;
+	struct arpt_standard entries[2];
+	struct arpt_error term;
+} initial_table __initdata
+= { { "filter", FILTER_VALID_HOOKS, 3,
+      sizeof(struct arpt_standard) * 2 + sizeof(struct arpt_error),
+      { [NF_ARP_IN] 0,
+	[NF_ARP_OUT] sizeof(struct arpt_standard) },
+      { [NF_ARP_IN] 0,
+	[NF_ARP_OUT] sizeof(struct arpt_standard), },
+      0, NULL, { } },
+    {
+	    /* ARP_IN */
+	    {
+		    {
+			    {
+				    { 0 }, { 0 }, { 0 }, { 0 },
+				    0, 0,
+				    { { 0, }, { 0, } },
+				    { { 0, }, { 0, } },
+				    0, 0,
+				    0, 0,
+				    0, 0,
+				    "", "", { 0 }, { 0 },
+				    0, 0
+			    },
+			    sizeof(struct arpt_entry),
+			    sizeof(struct arpt_standard),
+			    0,
+			    { 0, 0 }, { } },
+		    { { { { ARPT_ALIGN(sizeof(struct arpt_standard_target)), "" } }, { } },
+		      -NF_ACCEPT - 1 }
+	    },
+	    /* ARP_OUT */
+	    {
+		    {
+			    {
+				    { 0 }, { 0 }, { 0 }, { 0 },
+				    0, 0,
+				    { { 0, }, { 0, } },
+				    { { 0, }, { 0, } },
+				    0, 0,
+				    0, 0,
+				    0, 0,
+				    "", "", { 0 }, { 0 },
+				    0, 0
+			    },
+			    sizeof(struct arpt_entry),
+			    sizeof(struct arpt_standard),
+			    0,
+			    { 0, 0 }, { } },
+		    { { { { ARPT_ALIGN(sizeof(struct arpt_standard_target)), "" } }, { } },
+		      -NF_ACCEPT - 1 }
+	    }
+    },
+    /* ERROR */
+    {
+	    {
+		    {
+			    { 0 }, { 0 }, { 0 }, { 0 },
+			    0, 0,
+			    { { 0, }, { 0, } },
+			    { { 0, }, { 0, } },
+			    0, 0,
+			    0, 0,
+			    0, 0,
+			    "", "", { 0 }, { 0 },
+			    0, 0
+		    },
+		    sizeof(struct arpt_entry),
+		    sizeof(struct arpt_error),
+		    0,
+		    { 0, 0 }, { } },
+	    { { { { ARPT_ALIGN(sizeof(struct arpt_error_target)), ARPT_ERROR_TARGET } },
+		{ } },
+	      "ERROR"
+	    }
+    }
+};
+
+static struct arpt_table packet_filter
+= { { NULL, NULL }, "filter", &initial_table.repl,
+    FILTER_VALID_HOOKS, RW_LOCK_UNLOCKED, NULL, THIS_MODULE };
+
+/* The work comes in here from netfilter.c */
+static unsigned int arpt_hook(unsigned int hook,
+			      struct sk_buff **pskb,
+			      const struct net_device *in,
+			      const struct net_device *out,
+			      int (*okfn)(struct sk_buff *))
+{
+	return arpt_do_table(pskb, hook, in, out, &packet_filter, NULL);
+}
+
+static struct nf_hook_ops arpt_ops[]
+= { { { NULL, NULL }, arpt_hook, NF_ARP, NF_ARP_IN, 0 },
+    { { NULL, NULL }, arpt_hook, NF_ARP, NF_ARP_OUT, 0 }
+};
+
+static int __init init(void)
+{
+	int ret;
+
+	/* Register table */
+	ret = arpt_register_table(&packet_filter);
+	if (ret < 0)
+		return ret;
+
+	/* Register hooks */
+	ret = nf_register_hook(&arpt_ops[0]);
+	if (ret < 0)
+		goto cleanup_table;
+
+	ret = nf_register_hook(&arpt_ops[1]);
+	if (ret < 0)
+		goto cleanup_hook0;
+
+	return ret;
+
+cleanup_hook0:
+	nf_unregister_hook(&arpt_ops[0]);
+
+cleanup_table:
+	arpt_unregister_table(&packet_filter);
+
+	return ret;
+}
+
+static void __exit fini(void)
+{
+	unsigned int i;
+
+	for (i = 0; i < sizeof(arpt_ops)/sizeof(struct nf_hook_ops); i++)
+		nf_unregister_hook(&arpt_ops[i]);
+
+	arpt_unregister_table(&packet_filter);
+}
+
+module_init(init);
+module_exit(fini);
+MODULE_LICENSE("GPL");

net/ipv4/netfilter/ip_conntrack_standalone.c

@@ -15,6 +15,7 @@
 #include <linux/skbuff.h>
 #include <linux/proc_fs.h>
 #include <linux/version.h>
+#include <linux/brlock.h>
 #include <net/checksum.h>
 
 #define ASSERT_READ_LOCK(x) MUST_BE_READ_LOCKED(&ip_conntrack_lock)
@@ -35,6 +36,11 @@
 struct module *ip_conntrack_module = THIS_MODULE;
 MODULE_LICENSE("GPL");
 
+static int kill_proto(const struct ip_conntrack *i, void *data)
+{
+	return (i->tuplehash[IP_CT_DIR_ORIGINAL].dst.protonum == 
+			*((u_int8_t *) data));
+}
 
 static unsigned int
 print_tuple(char *buffer, const struct ip_conntrack_tuple *tuple,
@@ -304,12 +310,24 @@ int ip_conntrack_protocol_register(struct ip_conntrack_protocol *proto)
 	return ret;
 }
 
-/* FIXME: Implement this --RR */
-#if 0
 void ip_conntrack_protocol_unregister(struct ip_conntrack_protocol *proto)
 {
+	WRITE_LOCK(&ip_conntrack_lock);
+
+	/* find_proto() returns proto_generic in case there is no protocol 
+	 * helper. So this should be enough - HW */
+	LIST_DELETE(&protocol_list, proto);
+	WRITE_UNLOCK(&ip_conntrack_lock);
+	
+	/* Somebody could be still looking at the proto in bh. */
+	br_write_lock_bh(BR_NETPROTO_LOCK);
+	br_write_unlock_bh(BR_NETPROTO_LOCK);
+
+	/* Remove all contrack entries for this protocol */
+	ip_ct_selective_cleanup(kill_proto, &proto->proto);
+
+	MOD_DEC_USE_COUNT;
 }
-#endif
 
 static int __init init(void)
 {
@@ -325,6 +343,7 @@ module_init(init);
 module_exit(fini);
 
 EXPORT_SYMBOL(ip_conntrack_protocol_register);
+EXPORT_SYMBOL(ip_conntrack_protocol_unregister);
 EXPORT_SYMBOL(invert_tuplepr);
 EXPORT_SYMBOL(ip_conntrack_alter_reply);
 EXPORT_SYMBOL(ip_conntrack_destroyed);
@@ -335,6 +354,7 @@ EXPORT_SYMBOL(ip_conntrack_helper_unregister);
 EXPORT_SYMBOL(ip_ct_selective_cleanup);
 EXPORT_SYMBOL(ip_ct_refresh);
 EXPORT_SYMBOL(ip_conntrack_expect_related);
+EXPORT_SYMBOL(ip_conntrack_unexpect_related);
 EXPORT_SYMBOL(ip_conntrack_tuple_taken);
 EXPORT_SYMBOL(ip_ct_gather_frags);
 EXPORT_SYMBOL(ip_conntrack_htable_size);

net/ipv4/netfilter/ip_nat_core.c

@@ -314,6 +314,7 @@ find_best_ips_proto(struct ip_conntrack_tuple *tuple,
 			 * do_extra_mangle last time. */
 			*other_ipp = saved_ip;
 
+#ifdef CONFIG_IP_NF_NAT_LOCAL
 			if (hooknum == NF_IP_LOCAL_OUT
 			    && *var_ipp != orig_dstip
 			    && !do_extra_mangle(*var_ipp, other_ipp)) {
@@ -324,6 +325,7 @@ find_best_ips_proto(struct ip_conntrack_tuple *tuple,
 				 * anyway. */
 				continue;
 			}
+#endif
 
 			/* Count how many others map onto this. */
 			score = count_maps(tuple->src.ip, tuple->dst.ip,
@@ -367,11 +369,13 @@ find_best_ips_proto_fast(struct ip_conntrack_tuple *tuple,
 		else {
 			/* Only do extra mangle when required (breaks
                            socket binding) */
+#ifdef CONFIG_IP_NF_NAT_LOCAL
 			if (tuple->dst.ip != mr->range[0].min_ip
 			    && hooknum == NF_IP_LOCAL_OUT
 			    && !do_extra_mangle(mr->range[0].min_ip,
 						&tuple->src.ip))
 				return NULL;
+#endif
 			tuple->dst.ip = mr->range[0].min_ip;
 		}
 	}
@@ -494,7 +498,10 @@ helper_cmp(const struct ip_nat_helper *helper,
 static unsigned int opposite_hook[NF_IP_NUMHOOKS]
 = { [NF_IP_PRE_ROUTING] = NF_IP_POST_ROUTING,
     [NF_IP_POST_ROUTING] = NF_IP_PRE_ROUTING,
-    [NF_IP_LOCAL_OUT] = NF_IP_POST_ROUTING
+#ifdef CONFIG_IP_NF_NAT_LOCAL
+    [NF_IP_LOCAL_OUT] = NF_IP_LOCAL_IN,
+    [NF_IP_LOCAL_IN] = NF_IP_LOCAL_OUT,
+#endif
 };
 
 unsigned int

net/ipv4/netfilter/ip_nat_rule.c

@@ -140,8 +140,12 @@ static unsigned int ipt_dnat_target(struct sk_buff **pskb,
 	struct ip_conntrack *ct;
 	enum ip_conntrack_info ctinfo;
 
+#ifdef CONFIG_IP_NF_NAT_LOCAL
 	IP_NF_ASSERT(hooknum == NF_IP_PRE_ROUTING
 		     || hooknum == NF_IP_LOCAL_OUT);
+#else
+	IP_NF_ASSERT(hooknum == NF_IP_PRE_ROUTING);
+#endif
 
 	ct = ip_conntrack_get(*pskb, &ctinfo);
 
@@ -210,7 +214,7 @@ static int ipt_dnat_checkentry(const char *tablename,
 
 	/* Only allow these for NAT. */
 	if (strcmp(tablename, "nat") != 0) {
-		DEBUGP("SNAT: wrong table %s\n", tablename);
+		DEBUGP("DNAT: wrong table %s\n", tablename);
 		return 0;
 	}
 
@@ -218,6 +222,14 @@ static int ipt_dnat_checkentry(const char *tablename,
 		DEBUGP("DNAT: hook mask 0x%x bad\n", hook_mask);
 		return 0;
 	}
+	
+#ifndef CONFIG_IP_NF_NAT_LOCAL
+	if (hook_mask & (1 << NF_IP_LOCAL_OUT)) {
+		DEBUGP("DNAT: CONFIG_IP_NF_NAT_LOCAL not enabled\n");
+		return 0;
+	}
+#endif
+
 	return 1;
 }
 

net/ipv4/netfilter/ip_nat_standalone.c

@@ -42,7 +42,8 @@
 #define HOOKNAME(hooknum) ((hooknum) == NF_IP_POST_ROUTING ? "POST_ROUTING"  \
 			   : ((hooknum) == NF_IP_PRE_ROUTING ? "PRE_ROUTING" \
 			      : ((hooknum) == NF_IP_LOCAL_OUT ? "LOCAL_OUT"  \
-				 : "*ERROR*")))
+			         : ((hooknum) == NF_IP_LOCAL_IN ? "LOCAL_IN"  \
+				    : "*ERROR*")))
 
 static unsigned int
 ip_nat_fn(unsigned int hooknum,
@@ -95,6 +96,12 @@ ip_nat_fn(unsigned int hooknum,
 		}
 		/* Fall thru... (Only ICMPs can be IP_CT_IS_REPLY) */
 	case IP_CT_NEW:
+#ifdef CONFIG_IP_NF_NAT_LOCAL
+		/* LOCAL_IN hook doesn't have a chain and thus doesn't care
+		 * about new packets -HW */
+		if (hooknum == NF_IP_LOCAL_IN)
+			return NF_ACCEPT;
+#endif
 		info = &ct->nat.info;
 
 		WRITE_LOCK(&ip_nat_lock);
@@ -205,6 +212,11 @@ static struct nf_hook_ops ip_nat_out_ops
 static struct nf_hook_ops ip_nat_local_out_ops
 = { { NULL, NULL }, ip_nat_local_fn, PF_INET, NF_IP_LOCAL_OUT, NF_IP_PRI_NAT_DST };
 
+#ifdef CONFIG_IP_NF_NAT_LOCAL
+static struct nf_hook_ops ip_nat_local_in_ops
+= { { NULL, NULL }, ip_nat_fn, PF_INET, NF_IP_LOCAL_IN, NF_IP_PRI_NAT_SRC };
+#endif
+
 /* Protocol registration. */
 int ip_nat_protocol_register(struct ip_nat_protocol *proto)
 {
@@ -273,6 +285,13 @@ static int init_or_cleanup(int init)
 		printk("ip_nat_init: can't register local out hook.\n");
 		goto cleanup_outops;
 	}
+#ifdef CONFIG_IP_NF_NAT_LOCAL
+	ret = nf_register_hook(&ip_nat_local_in_ops);
+	if (ret < 0) {
+		printk("ip_nat_init: can't register local in hook.\n");
+		goto cleanup_localoutops;
+	}
+#endif
 	if (ip_conntrack_module)
 		__MOD_INC_USE_COUNT(ip_conntrack_module);
 	return ret;
@@ -280,6 +299,10 @@ static int init_or_cleanup(int init)
  cleanup:
 	if (ip_conntrack_module)
 		__MOD_DEC_USE_COUNT(ip_conntrack_module);
+#ifdef CONFIG_IP_NF_NAT_LOCAL
+	nf_unregister_hook(&ip_nat_local_in_ops);
+ cleanup_localoutops:
+#endif
 	nf_unregister_hook(&ip_nat_local_out_ops);
  cleanup_outops:
 	nf_unregister_hook(&ip_nat_out_ops);

net/netsyms.c

@@ -490,6 +490,7 @@ EXPORT_SYMBOL(__kfree_skb);
 EXPORT_SYMBOL(skb_clone);
 EXPORT_SYMBOL(skb_copy);
 EXPORT_SYMBOL(netif_rx);
+EXPORT_SYMBOL(netif_receive_skb);
 EXPORT_SYMBOL(dev_add_pack);
 EXPORT_SYMBOL(dev_remove_pack);
 EXPORT_SYMBOL(dev_get);