+CONFIG_IP_NF_MATCH_LAYER7=m

[packages/kernel.git] / 01_linux-2.6.0-test11-esfq-imq.diff

diff -u -U 2 -r -N -d linux-2.6.0-test11.orig/drivers/net/Kconfig linux-2.6.0-test11/drivers/net/Kconfig
--- linux-2.6.0-test11.orig/drivers/net/Kconfig	2003-11-30 20:43:42.000000000 +0000
+++ linux-2.6.0-test11/drivers/net/Kconfig	2003-12-02 23:28:09.000000000 +0000
@@ -85,6 +85,20 @@
 	  To compile this driver as a module, choose M here: the module
 	  will be called eql.  If unsure, say N.
 
+config IMQ
+	tristate "IMQ (intermediate queueing device) support"
+	depends on NETDEVICES && NETFILTER
+	---help---
+	  The imq device(s) is used as placeholder for QoS queueing disciplines.
+	  Every packet entering/leaving the ip stack can be directed through
+	  the imq device where it's enqueued/dequeued to the attached qdisc.
+	  This allows you to treat network devices as classes and distribute
+	  bandwidth among them. Iptables is used to specify through which imq
+	  device, if any, packets travel.
+	  
+	  To compile this driver as a module, choose M here: the module
+	  will be called imq.  If unsure, say N.
+
 config TUN
 	tristate "Universal TUN/TAP device driver support"
 	depends on NETDEVICES
diff -u -U 2 -r -N -d linux-2.6.0-test11.orig/drivers/net/Makefile linux-2.6.0-test11/drivers/net/Makefile
--- linux-2.6.0-test11.orig/drivers/net/Makefile	2003-11-30 20:43:42.000000000 +0000
+++ linux-2.6.0-test11/drivers/net/Makefile	2003-12-02 19:54:09.000000000 +0000
@@ -109,6 +109,7 @@
 endif
 
 obj-$(CONFIG_DUMMY) += dummy.o
+obj-$(CONFIG_IMQ) += imq.o
 obj-$(CONFIG_DE600) += de600.o
 obj-$(CONFIG_DE620) += de620.o
 obj-$(CONFIG_AT1500) += lance.o
diff -u -U 2 -r -N -d linux-2.6.0-test11.orig/drivers/net/imq.c linux-2.6.0-test11/drivers/net/imq.c
--- linux-2.6.0-test11.orig/drivers/net/imq.c	1970-01-01 01:00:00.000000000 +0100
+++ linux-2.6.0-test11/drivers/net/imq.c	2003-12-02 23:52:55.000000000 +0000
@@ -0,0 +1,321 @@
+/*
+ *             Pseudo-driver for the intermediate queue device.
+ *
+ *             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.
+ *
+ * Authors:    Patrick McHardy, <kaber@trash.net>
+ *
+ * 	       The first version was written by Martin Devera, <devik@cdi.cz>
+ *
+ * Credits:    Jan Rafaj <imq2t@cedric.vabo.cz>
+ *              - Update patch to 2.4.21
+ *             Sebastian Strollo <sstrollo@nortelnetworks.com>
+ *              - Fix "Dead-loop on netdevice imq"-issue
+ */
+
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/config.h>
+#include <linux/skbuff.h>
+#include <linux/netdevice.h>
+#include <linux/rtnetlink.h>
+#include <linux/if_arp.h>
+#include <linux/netfilter.h>
+#include <linux/netfilter_ipv4.h>
+#if defined(CONFIG_IPV6) || defined (CONFIG_IPV6_MODULE)
+#include <linux/netfilter_ipv6.h>
+#endif
+#include <linux/imq.h>
+#include <net/pkt_sched.h>
+
+static nf_hookfn imq_nf_hook;
+
+static struct nf_hook_ops imq_ingress_ipv4 = {
+	.hook		= imq_nf_hook,
+	.owner		= THIS_MODULE,
+	.pf		= PF_INET,
+	.hooknum	= NF_IP_PRE_ROUTING,
+	.priority	= NF_IP_PRI_MANGLE + 1
+};
+
+static struct nf_hook_ops imq_egress_ipv4 = {
+	.hook		= imq_nf_hook,
+	.owner		= THIS_MODULE,
+	.pf		= PF_INET,
+	.hooknum	= NF_IP_POST_ROUTING,
+	.priority	= NF_IP_PRI_LAST
+};
+
+#if defined(CONFIG_IPV6) || defined (CONFIG_IPV6_MODULE)
+static struct nf_hook_ops imq_ingress_ipv6 = {
+	.hook		= imq_nf_hook,
+	.owner		= THIS_MODULE,
+	.pf		= PF_INET6,
+	.hooknum	= NF_IP6_PRE_ROUTING,
+	.priority	= NF_IP6_PRI_MANGLE + 1
+};
+
+static struct nf_hook_ops imq_egress_ipv6 = {
+	.hook		= imq_nf_hook,
+	.owner		= THIS_MODULE,
+	.pf		= PF_INET6,
+	.hooknum	= NF_IP6_POST_ROUTING,
+	.priority	= NF_IP6_PRI_LAST
+};
+#endif
+
+static unsigned int numdevs = 2;
+
+MODULE_PARM(numdevs, "i");
+MODULE_PARM_DESC(numdevs, "number of imq devices");
+
+static struct net_device *imq_devs;
+
+
+static struct net_device_stats *imq_get_stats(struct net_device *dev)
+{
+	return (struct net_device_stats *)dev->priv;
+}
+
+/* called for packets kfree'd in qdiscs at places other than enqueue */
+static void imq_skb_destructor(struct sk_buff *skb)
+{
+	struct nf_info *info = skb->nf_info;
+
+	if (info) {
+		if (info->indev)
+			dev_put(info->indev);
+		if (info->outdev)
+			dev_put(info->outdev);
+		kfree(info);
+	}
+}
+
+static int imq_dev_xmit(struct sk_buff *skb, struct net_device *dev)
+{
+	struct net_device_stats *stats = (struct net_device_stats*) dev->priv;
+	
+	stats->tx_bytes += skb->len;
+	stats->tx_packets++;
+
+	skb->imq_flags = 0;
+	skb->destructor = NULL;
+	
+	dev->trans_start = jiffies;
+	nf_reinject(skb, skb->nf_info, NF_ACCEPT);
+	return 0;
+}
+
+static int imq_nf_queue(struct sk_buff *skb, struct nf_info *info,
+			void *data)
+{
+	struct net_device *dev;
+	struct net_device_stats *stats;
+	struct sk_buff *skb2 = NULL;
+	struct Qdisc *q;
+	unsigned int index = skb->imq_flags&IMQ_F_IFMASK;
+	int ret = -1;
+
+	if (index > numdevs) 
+		return -1;
+	
+	dev = imq_devs + index;
+	if (!(dev->flags & IFF_UP)) {
+		skb->imq_flags = 0;
+		nf_reinject(skb, info, NF_ACCEPT);
+		return 0;
+	}
+	dev->last_rx = jiffies;
+
+	if (skb->destructor) {
+		skb2 = skb;
+		skb = skb_clone(skb, GFP_ATOMIC);
+		if (!skb)
+			return -1;
+	}
+	skb->nf_info = info;
+
+	stats = (struct net_device_stats *)dev->priv;
+	stats->rx_bytes+= skb->len;
+	stats->rx_packets++;
+	
+	spin_lock_bh(&dev->queue_lock);
+	q = dev->qdisc;
+	if (q->enqueue) {
+		q->enqueue(skb_get(skb), q);
+		if (skb_shared(skb)) {
+			skb->destructor = imq_skb_destructor;
+			kfree_skb(skb);
+			ret = 0;
+		}
+	}
+	if (spin_is_locked(&dev->xmit_lock))
+		netif_schedule(dev);
+	else
+		qdisc_run(dev);
+	spin_unlock_bh(&dev->queue_lock);
+
+	if (skb2)
+		kfree_skb(ret ? skb : skb2);
+
+	return ret;
+}
+
+static unsigned int imq_nf_hook(unsigned int hook, struct sk_buff **pskb,
+		   const struct net_device *indev,
+		   const struct net_device *outdev,
+		   int (*okfn)(struct sk_buff *))
+{
+	if ((*pskb)->imq_flags & IMQ_F_ENQUEUE)
+		return NF_QUEUE;
+
+	return NF_ACCEPT;
+}
+
+
+static int __init imq_init_hooks(void)
+{
+	int err;
+
+	if ((err = nf_register_queue_handler(PF_INET, imq_nf_queue, NULL)))
+		goto err1;
+	if ((err = nf_register_hook(&imq_ingress_ipv4)))
+		goto err2;
+	if ((err = nf_register_hook(&imq_egress_ipv4)))
+		goto err3;
+#if defined(CONFIG_IPV6) || defined (CONFIG_IPV6_MODULE)
+	if ((err = nf_register_queue_handler(PF_INET6, imq_nf_queue, NULL)))
+		goto err4;
+	if ((err = nf_register_hook(&imq_ingress_ipv6)))
+		goto err5;
+	if ((err = nf_register_hook(&imq_egress_ipv6)))
+		goto err6;
+#endif
+	
+	return 0;
+	
+#if defined(CONFIG_IPV6) || defined (CONFIG_IPV6_MODULE)
+err6:
+	nf_unregister_hook(&imq_ingress_ipv6);
+err5:
+	nf_unregister_queue_handler(PF_INET6);
+err4:
+	nf_unregister_hook(&imq_egress_ipv4);
+#endif
+err3:
+	nf_unregister_hook(&imq_ingress_ipv4);
+err2:
+	nf_unregister_queue_handler(PF_INET);
+err1:
+	return err;
+}
+
+static void __exit imq_unhook(void)
+{
+	nf_unregister_hook(&imq_ingress_ipv4);
+	nf_unregister_hook(&imq_egress_ipv4);
+	nf_unregister_queue_handler(PF_INET);
+#if defined(CONFIG_IPV6) || defined (CONFIG_IPV6_MODULE)
+	nf_unregister_hook(&imq_ingress_ipv6);
+	nf_unregister_hook(&imq_egress_ipv6);
+	nf_unregister_queue_handler(PF_INET6);
+#endif
+}
+
+static int __init imq_dev_init(struct net_device *dev)
+{
+	dev->hard_start_xmit	= imq_dev_xmit;
+	dev->type		= ARPHRD_VOID;
+	dev->mtu		= 1500;
+	dev->tx_queue_len	= 30;
+	dev->flags		= IFF_NOARP;
+	dev->priv = kmalloc(sizeof(struct net_device_stats), GFP_KERNEL);
+	if (dev->priv == NULL)
+		return -ENOMEM;
+	memset(dev->priv, 0, sizeof(struct net_device_stats));
+	dev->get_stats		= imq_get_stats;
+
+	return 0;
+}
+
+static void imq_dev_uninit(struct net_device *dev)
+{
+	kfree(dev->priv);
+}
+
+static int __init imq_init_devs(void)
+{
+	struct net_device *dev;
+	int i;
+
+	if (!numdevs || numdevs > IMQ_MAX_DEVS) {
+		printk(KERN_ERR "numdevs has to be betweed 1 and %u\n",
+		       IMQ_MAX_DEVS);
+		return -EINVAL;
+	}
+
+	imq_devs = kmalloc(sizeof(struct net_device) * numdevs, GFP_KERNEL);
+	if (!imq_devs)
+		return -ENOMEM;
+	memset(imq_devs, 0, sizeof(struct net_device) * numdevs);
+
+	/* we start counting at zero */
+	numdevs--;
+
+	for (i = 0, dev = imq_devs; i <= numdevs; i++, dev++) {
+		SET_MODULE_OWNER(dev);
+		strcpy(dev->name, "imq%d");
+		dev->init   = imq_dev_init;
+		dev->uninit = imq_dev_uninit;
+
+		if (register_netdev(dev) < 0)
+			goto err_register;
+	}
+	return 0;
+
+err_register:
+	for (; i; i--)
+		unregister_netdev(--dev);
+	kfree(imq_devs);
+	return -EIO;
+}
+
+static void imq_cleanup_devs(void)
+{
+	int i;
+	struct net_device *dev = imq_devs;
+	
+	for (i = 0; i <= numdevs; i++)
+		unregister_netdev(dev++);
+
+	kfree(imq_devs);
+}
+
+static int __init imq_init_module(void)
+{
+	int err;
+
+	if ((err = imq_init_devs()))
+		return err;
+	if ((err = imq_init_hooks())) {
+		imq_cleanup_devs();
+		return err;
+	}
+
+	printk(KERN_INFO "imq driver loaded.\n");
+
+	return 0;
+}
+
+static void __exit imq_cleanup_module(void)
+{
+	imq_unhook();
+	imq_cleanup_devs();
+}
+
+module_init(imq_init_module);
+module_exit(imq_cleanup_module);
+MODULE_LICENSE("GPL");
diff -u -U 2 -r -N -d linux-2.6.0-test11.orig/include/linux/imq.h linux-2.6.0-test11/include/linux/imq.h
--- linux-2.6.0-test11.orig/include/linux/imq.h	1970-01-01 01:00:00.000000000 +0100
+++ linux-2.6.0-test11/include/linux/imq.h	2003-12-02 19:54:09.000000000 +0000
@@ -0,0 +1,9 @@
+#ifndef _IMQ_H
+#define _IMQ_H
+
+#define IMQ_MAX_DEVS	16
+
+#define IMQ_F_IFMASK	0x7f
+#define IMQ_F_ENQUEUE	0x80
+
+#endif /* _IMQ_H */
diff -u -U 2 -r -N -d linux-2.6.0-test11.orig/include/linux/netfilter_ipv4/ipt_IMQ.h linux-2.6.0-test11/include/linux/netfilter_ipv4/ipt_IMQ.h
--- linux-2.6.0-test11.orig/include/linux/netfilter_ipv4/ipt_IMQ.h	1970-01-01 01:00:00.000000000 +0100
+++ linux-2.6.0-test11/include/linux/netfilter_ipv4/ipt_IMQ.h	2003-12-02 19:54:06.000000000 +0000
@@ -0,0 +1,8 @@
+#ifndef _IPT_IMQ_H
+#define _IPT_IMQ_H
+
+struct ipt_imq_info {
+	unsigned int todev;	/* target imq device */
+};
+
+#endif /* _IPT_IMQ_H */
diff -u -U 2 -r -N -d linux-2.6.0-test11.orig/include/linux/pkt_sched.h linux-2.6.0-test11/include/linux/pkt_sched.h
--- linux-2.6.0-test11.orig/include/linux/pkt_sched.h	2003-11-30 20:43:31.000000000 +0000
+++ linux-2.6.0-test11/include/linux/pkt_sched.h	2003-12-02 19:53:57.000000000 +0000
@@ -157,6 +157,13 @@
 
 /* SFQ section */
 
+enum
+{
+	TCA_SFQ_HASH_CLASSIC,
+	TCA_SFQ_HASH_DST,
+	TCA_SFQ_HASH_SRC,
+};
+
 struct tc_sfq_qopt
 {
 	unsigned	quantum;	/* Bytes per round allocated to flow */
@@ -164,6 +171,7 @@
 	__u32		limit;		/* Maximal packets in queue */
 	unsigned	divisor;	/* Hash divisor  */
 	unsigned	flows;		/* Maximal number of flows  */
+	unsigned	hash_kind;	/* Hash function to use for flow identification */
 };
 
 /*
@@ -173,6 +181,8 @@
  *
  *	The only reason for this is efficiency, it is possible
  *	to change these parameters in compile time.
+ *	
+ *	If you need to play with this values use esfq.
  */
 
 /* RED section */
diff -u -U 2 -r -N -d linux-2.6.0-test11.orig/include/linux/skbuff.h linux-2.6.0-test11/include/linux/skbuff.h
--- linux-2.6.0-test11.orig/include/linux/skbuff.h	2003-11-30 20:43:31.000000000 +0000
+++ linux-2.6.0-test11/include/linux/skbuff.h	2003-12-02 19:54:09.000000000 +0000
@@ -112,6 +112,9 @@
 #endif
 
 #endif
+#if defined(CONFIG_IMQ) || defined(CONFIG_IMQ_MODULE)
+struct nf_info;
+#endif
 
 struct sk_buff_head {
 	/* These two members must be first. */
@@ -234,6 +237,7 @@
 				data_len,
 				csum;
 	unsigned char		local_df,
+				imq_flags,
 				cloned,
 				pkt_type,
 				ip_summed;
@@ -261,6 +265,9 @@
 #ifdef CONFIG_NET_SCHED
        __u32			tc_index;               /* traffic control index */
 #endif
+#if defined(CONFIG_IMQ) || defined(CONFIG_IMQ_MODULE)
+	struct nf_info		*nf_info;
+#endif
 
 	/* These elements must be at the end, see alloc_skb() for details.  */
 	unsigned int		truesize;
diff -u -U 2 -r -N -d linux-2.6.0-test11.orig/net/core/skbuff.c linux-2.6.0-test11/net/core/skbuff.c
--- linux-2.6.0-test11.orig/net/core/skbuff.c	2003-11-30 20:43:52.000000000 +0000
+++ linux-2.6.0-test11/net/core/skbuff.c	2003-12-02 19:54:09.000000000 +0000
@@ -152,6 +152,13 @@
 	skb_shinfo(skb)->tso_size = 0;
 	skb_shinfo(skb)->tso_segs = 0;
 	skb_shinfo(skb)->frag_list = NULL;
+
+/* probably doomed to failure */
+#if defined(CONFIG_IMQ) || defined (CONFIG_IMQ_MODULE)
+	skb->imq_flags = 0;
+	skb->nf_info = NULL;
+#endif
+                
 out:
 	return skb;
 nodata:
@@ -313,6 +320,10 @@
 #ifdef CONFIG_NET_SCHED
 	C(tc_index);
 #endif
+#if defined(CONFIG_IMQ) || defined(CONFIG_IMQ_MODULE)
+	C(imq_flags);
+	C(nf_info);
+#endif
 	C(truesize);
 	atomic_set(&n->users, 1);
 	C(head);
@@ -368,6 +379,10 @@
 #ifdef CONFIG_NET_SCHED
 	new->tc_index	= old->tc_index;
 #endif
+#if defined(CONFIG_IMQ) || defined(CONFIG_IMQ_MODULE)
+	new->imq_flags=old->imq_flags;
+	new->nf_info=old->nf_info;
+#endif
 	atomic_set(&new->users, 1);
 }
 
diff -u -U 2 -r -N -d linux-2.6.0-test11.orig/net/ipv4/netfilter/Kconfig linux-2.6.0-test11/net/ipv4/netfilter/Kconfig
--- linux-2.6.0-test11.orig/net/ipv4/netfilter/Kconfig	2003-11-30 20:43:52.000000000 +0000
+++ linux-2.6.0-test11/net/ipv4/netfilter/Kconfig	2003-12-02 19:54:06.000000000 +0000
@@ -501,6 +501,15 @@
 
 	  To compile it as a module, choose M here.  If unsure, say N.
 
+config IP_NF_TARGET_IMQ
+	tristate "IMQ target support"
+	depends on IP_NF_IPTABLES
+	---help---
+	  This option adds a `IMQ' target which is used to specify if and
+	  to which imq device packets should get enqueued/dequeued.
+
+	  To compile it as a module, choose M here.  If unsure, say N.
+
 config IP_NF_TARGET_TCPMSS
 	tristate "TCPMSS target support"
 	depends on IP_NF_IPTABLES
diff -u -U 2 -r -N -d linux-2.6.0-test11.orig/net/ipv4/netfilter/Makefile linux-2.6.0-test11/net/ipv4/netfilter/Makefile
--- linux-2.6.0-test11.orig/net/ipv4/netfilter/Makefile	2003-11-30 20:43:52.000000000 +0000
+++ linux-2.6.0-test11/net/ipv4/netfilter/Makefile	2003-12-02 19:54:06.000000000 +0000
@@ -72,6 +72,7 @@
 obj-$(CONFIG_IP_NF_TARGET_ECN) += ipt_ECN.o
 obj-$(CONFIG_IP_NF_TARGET_DSCP) += ipt_DSCP.o
 obj-$(CONFIG_IP_NF_TARGET_MARK) += ipt_MARK.o
+obj-$(CONFIG_IP_NF_TARGET_IMQ) += ipt_IMQ.o
 obj-$(CONFIG_IP_NF_TARGET_MASQUERADE) += ipt_MASQUERADE.o
 obj-$(CONFIG_IP_NF_TARGET_REDIRECT) += ipt_REDIRECT.o
 obj-$(CONFIG_IP_NF_TARGET_NETMAP) += ipt_NETMAP.o
diff -u -U 2 -r -N -d linux-2.6.0-test11.orig/net/ipv4/netfilter/ipt_IMQ.c linux-2.6.0-test11/net/ipv4/netfilter/ipt_IMQ.c
--- linux-2.6.0-test11.orig/net/ipv4/netfilter/ipt_IMQ.c	1970-01-01 01:00:00.000000000 +0100
+++ linux-2.6.0-test11/net/ipv4/netfilter/ipt_IMQ.c	2003-12-03 00:01:18.000000000 +0000
@@ -0,0 +1,76 @@
+/* This target marks packets to be enqueued to an imq device */
+#include <linux/module.h>
+#include <linux/skbuff.h>
+#include <linux/netfilter_ipv4/ip_tables.h>
+#include <linux/netfilter_ipv4/ipt_IMQ.h>
+#include <linux/imq.h>
+
+static unsigned int imq_target(struct sk_buff **pskb,
+			       const struct net_device *in,
+			       const struct net_device *out,
+			       unsigned int hooknum,
+			       const void *targinfo,
+			       void *userinfo)
+{
+	struct ipt_imq_info *mr = (struct ipt_imq_info*)targinfo;
+
+	(*pskb)->imq_flags = mr->todev | IMQ_F_ENQUEUE;
+	(*pskb)->nfcache |= NFC_ALTERED;
+
+	return IPT_CONTINUE;
+}
+
+static int imq_checkentry(const char *tablename,
+			  const struct ipt_entry *e,
+			  void *targinfo,
+			  unsigned int targinfosize,
+			  unsigned int hook_mask)
+{
+	struct ipt_imq_info *mr;
+
+	if (targinfosize != IPT_ALIGN(sizeof(struct ipt_imq_info))) {
+		printk(KERN_WARNING "IMQ: invalid targinfosize\n");
+		return 0;
+	}
+	mr = (struct ipt_imq_info*)targinfo;
+
+	if (strcmp(tablename, "mangle") != 0) {
+		printk(KERN_WARNING
+		       "IMQ: IMQ can only be called from \"mangle\" table, not \"%s\"\n",
+		       tablename);
+		return 0;
+	}
+	
+	if (mr->todev > IMQ_MAX_DEVS) {
+		printk(KERN_WARNING
+		       "IMQ: invalid device specified, highest is %u\n",
+		       IMQ_MAX_DEVS);
+		return 0;
+	}
+	
+	return 1;
+}
+
+static struct ipt_target ipt_imq_reg = {
+	.name		= "IMQ",
+	.target		= imq_target,
+	.checkentry	= imq_checkentry,
+	.me		= THIS_MODULE
+};
+
+static int __init init(void)
+{
+	if (ipt_register_target(&ipt_imq_reg))
+		return -EINVAL;
+
+	return 0;
+}
+
+static void __exit fini(void)
+{
+	ipt_unregister_target(&ipt_imq_reg);
+}
+
+module_init(init);
+module_exit(fini);
+MODULE_LICENSE("GPL");
diff -u -U 2 -r -N -d linux-2.6.0-test11.orig/net/sched/Kconfig linux-2.6.0-test11/net/sched/Kconfig
--- linux-2.6.0-test11.orig/net/sched/Kconfig	2003-11-30 20:43:54.000000000 +0000
+++ linux-2.6.0-test11/net/sched/Kconfig	2003-12-02 19:53:57.000000000 +0000
@@ -105,6 +105,24 @@
 	  To compile this code as a module, choose M here: the
 	  module will be called sch_sfq.
 
+config NET_SCH_ESFQ
+	tristate "ESFQ queue"
+	depends on NET_SCHED
+	---help---
+	  Say Y here if you want to use the Enhanced Stochastic Fairness
+	  Queueing (ESFQ) packet scheduling algorithm for some of your network
+	  devices or as a leaf discipline for the CBQ scheduling algorithm (see
+	  the top of <file:net/sched/sch_esfq.c> for details and references
+	  about the SFQ algorithm).
+	  
+	  This is an enchanced SFQ version which allows you to control the
+	  hardcoded values in the SFQ scheduler: queue depth, hash table size,
+	  queues limit. Also adds control to the hash function used to identify
+	  packet flows. Hash by src or dst ip and original sfq hash.
+	  
+	  To compile this code as a module, choose M here: the
+	  module will be called sch_esfq.
+
 config NET_SCH_TEQL
 	tristate "TEQL queue"
 	depends on NET_SCHED
diff -u -U 2 -r -N -d linux-2.6.0-test11.orig/net/sched/Makefile linux-2.6.0-test11/net/sched/Makefile
--- linux-2.6.0-test11.orig/net/sched/Makefile	2003-11-30 20:43:54.000000000 +0000
+++ linux-2.6.0-test11/net/sched/Makefile	2003-12-02 19:53:57.000000000 +0000
@@ -15,6 +15,7 @@
 obj-$(CONFIG_NET_SCH_HFSC)	+= sch_hfsc.o
 obj-$(CONFIG_NET_SCH_HTB)	+= sch_htb.o
 obj-$(CONFIG_NET_SCH_SFQ)	+= sch_sfq.o
+obj-$(CONFIG_NET_SCH_ESFQ)	+= sch_esfq.o
 obj-$(CONFIG_NET_SCH_RED)	+= sch_red.o
 obj-$(CONFIG_NET_SCH_TBF)	+= sch_tbf.o
 obj-$(CONFIG_NET_SCH_PRIO)	+= sch_prio.o
diff -u -U 2 -r -N -d linux-2.6.0-test11.orig/net/sched/sch_api.c linux-2.6.0-test11/net/sched/sch_api.c
--- linux-2.6.0-test11.orig/net/sched/sch_api.c	2003-11-30 20:43:54.000000000 +0000
+++ linux-2.6.0-test11/net/sched/sch_api.c	2003-12-02 19:53:57.000000000 +0000
@@ -1235,6 +1235,9 @@
 #ifdef CONFIG_NET_SCH_SFQ
 	INIT_QDISC(sfq);
 #endif
+#ifdef CONFIG_NET_SCH_ESFQ
+	INIT_QDISC(esfq);
+#endif
 #ifdef CONFIG_NET_SCH_TBF
 	INIT_QDISC(tbf);
 #endif
diff -u -U 2 -r -N -d linux-2.6.0-test11.orig/net/sched/sch_esfq.c linux-2.6.0-test11/net/sched/sch_esfq.c
--- linux-2.6.0-test11.orig/net/sched/sch_esfq.c	1970-01-01 01:00:00.000000000 +0100
+++ linux-2.6.0-test11/net/sched/sch_esfq.c	2003-12-03 00:18:29.000000000 +0000
@@ -0,0 +1,588 @@
+/*
+ * net/sched/sch_esfq.c	Extended Stochastic Fairness Queueing discipline.
+ *
+ *		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.
+ *
+ * Authors:	Alexey Kuznetsov, <kuznet@ms2.inr.ac.ru>
+ *
+ * Changes:	Alexander Atanasov, <alex@ssi.bg>
+ *		Added dynamic depth,limit,divisor,hash_kind options.
+ *		Added dst and src hashes.
+ */
+
+#include <linux/config.h>
+#include <linux/module.h>
+#include <asm/uaccess.h>
+#include <asm/system.h>
+#include <asm/bitops.h>
+#include <linux/types.h>
+#include <linux/kernel.h>
+#include <linux/sched.h>
+#include <linux/string.h>
+#include <linux/mm.h>
+#include <linux/socket.h>
+#include <linux/sockios.h>
+#include <linux/in.h>
+#include <linux/errno.h>
+#include <linux/interrupt.h>
+#include <linux/if_ether.h>
+#include <linux/inet.h>
+#include <linux/netdevice.h>
+#include <linux/etherdevice.h>
+#include <linux/notifier.h>
+#include <linux/init.h>
+#include <net/ip.h>
+#include <linux/ipv6.h>
+#include <net/route.h>
+#include <linux/skbuff.h>
+#include <net/sock.h>
+#include <net/pkt_sched.h>
+
+
+/*	Stochastic Fairness Queuing algorithm.
+	For more comments look at sch_sfq.c.
+	The difference is that you can change limit, depth,
+	hash table size and choose 3 hash types.
+	
+	classic:	same as in sch_sfq.c
+	dst:		destination IP address
+	src:		source IP address
+	
+	TODO: 
+		make sfq_change work.
+*/
+
+
+/* This type should contain at least SFQ_DEPTH*2 values */
+typedef unsigned int esfq_index;
+
+struct esfq_head
+{
+	esfq_index	next;
+	esfq_index	prev;
+};
+
+struct esfq_sched_data
+{
+/* Parameters */
+	int		perturb_period;
+	unsigned	quantum;	/* Allotment per round: MUST BE >= MTU */
+	int		limit;
+	unsigned	depth;
+	unsigned	hash_divisor;
+	unsigned	hash_kind;
+/* Variables */
+	struct timer_list perturb_timer;
+	int		perturbation;
+	esfq_index	tail;		/* Index of current slot in round */
+	esfq_index	max_depth;	/* Maximal depth */
+
+	esfq_index	*ht;			/* Hash table */
+	esfq_index	*next;			/* Active slots link */
+	short		*allot;			/* Current allotment per slot */
+	unsigned short	*hash;			/* Hash value indexed by slots */
+	struct sk_buff_head	*qs;		/* Slot queue */
+	struct esfq_head	*dep;		/* Linked list of slots, indexed by depth */
+};
+
+static __inline__ unsigned esfq_hash_u32(struct esfq_sched_data *q,u32 h)
+{
+	int pert = q->perturbation;
+
+	if (pert)
+		h = (h<<pert) ^ (h>>(0x1F - pert));
+
+	h = ntohl(h) * 2654435761UL;
+	return h & (q->hash_divisor-1);
+}
+
+static __inline__ unsigned esfq_fold_hash_classic(struct esfq_sched_data *q, u32 h, u32 h1)
+{
+	int pert = q->perturbation;
+
+	/* Have we any rotation primitives? If not, WHY? */
+	h ^= (h1<<pert) ^ (h1>>(0x1F - pert));
+	h ^= h>>10;
+	return h & (q->hash_divisor-1);
+}
+
+#ifndef IPPROTO_ESP
+#define IPPROTO_ESP 50
+#endif
+
+static unsigned esfq_hash(struct esfq_sched_data *q, struct sk_buff *skb)
+{
+	u32 h, h2;
+	u32 hs;
+
+	switch (skb->protocol) {
+	case __constant_htons(ETH_P_IP):
+	{
+		struct iphdr *iph = skb->nh.iph;
+		h = iph->daddr;
+		hs = iph->saddr;
+		h2 = hs^iph->protocol;
+		if (!(iph->frag_off&htons(IP_MF|IP_OFFSET)) &&
+		    (iph->protocol == IPPROTO_TCP ||
+		     iph->protocol == IPPROTO_UDP ||
+		     iph->protocol == IPPROTO_ESP))
+			h2 ^= *(((u32*)iph) + iph->ihl);
+		break;
+	}
+	case __constant_htons(ETH_P_IPV6):
+	{
+		struct ipv6hdr *iph = skb->nh.ipv6h;
+		h = iph->daddr.s6_addr32[3];
+		hs = iph->saddr.s6_addr32[3];
+		h2 = hs^iph->nexthdr;
+		if (iph->nexthdr == IPPROTO_TCP ||
+		    iph->nexthdr == IPPROTO_UDP ||
+		    iph->nexthdr == IPPROTO_ESP)
+			h2 ^= *(u32*)&iph[1];
+		break;
+	}
+	default:
+		h = (u32)(unsigned long)skb->dst;
+		hs = (u32)(unsigned long)skb->sk;
+		h2 = hs^skb->protocol;
+	}
+	switch(q->hash_kind)
+	{
+	case TCA_SFQ_HASH_CLASSIC:
+		return esfq_fold_hash_classic(q, h, h2);
+	case TCA_SFQ_HASH_DST:
+		return esfq_hash_u32(q,h);
+	case TCA_SFQ_HASH_SRC:
+		return esfq_hash_u32(q,hs);
+	default:
+		if (net_ratelimit())
+			printk(KERN_DEBUG "esfq unknown hash method, fallback to classic\n");
+	}
+	return esfq_fold_hash_classic(q, h, h2);
+}
+
+extern __inline__ void esfq_link(struct esfq_sched_data *q, esfq_index x)
+{
+	esfq_index p, n;
+	int d = q->qs[x].qlen + q->depth;
+
+	p = d;
+	n = q->dep[d].next;
+	q->dep[x].next = n;
+	q->dep[x].prev = p;
+	q->dep[p].next = q->dep[n].prev = x;
+}
+
+extern __inline__ void esfq_dec(struct esfq_sched_data *q, esfq_index x)
+{
+	esfq_index p, n;
+
+	n = q->dep[x].next;
+	p = q->dep[x].prev;
+	q->dep[p].next = n;
+	q->dep[n].prev = p;
+
+	if (n == p && q->max_depth == q->qs[x].qlen + 1)
+		q->max_depth--;
+
+	esfq_link(q, x);
+}
+
+extern __inline__ void esfq_inc(struct esfq_sched_data *q, esfq_index x)
+{
+	esfq_index p, n;
+	int d;
+
+	n = q->dep[x].next;
+	p = q->dep[x].prev;
+	q->dep[p].next = n;
+	q->dep[n].prev = p;
+	d = q->qs[x].qlen;
+	if (q->max_depth < d)
+		q->max_depth = d;
+
+	esfq_link(q, x);
+}
+
+static unsigned int esfq_drop(struct Qdisc *sch)
+{
+	struct esfq_sched_data *q = (struct esfq_sched_data *)sch->data;
+	esfq_index d = q->max_depth;
+	struct sk_buff *skb;
+
+	/* Queue is full! Find the longest slot and
+	   drop a packet from it */
+
+	if (d > 1) {
+		esfq_index x = q->dep[d+q->depth].next;
+		skb = q->qs[x].prev;
+		__skb_unlink(skb, &q->qs[x]);
+		kfree_skb(skb);
+		esfq_dec(q, x);
+		sch->q.qlen--;
+		sch->stats.drops++;
+		return 1;
+	}
+
+	if (d == 1) {
+		/* It is difficult to believe, but ALL THE SLOTS HAVE LENGTH 1. */
+		d = q->next[q->tail];
+		q->next[q->tail] = q->next[d];
+		q->allot[q->next[d]] += q->quantum;
+		skb = q->qs[d].prev;
+		__skb_unlink(skb, &q->qs[d]);
+		kfree_skb(skb);
+		esfq_dec(q, d);
+		sch->q.qlen--;
+		q->ht[q->hash[d]] = q->depth;
+		sch->stats.drops++;
+		return 1;
+	}
+
+	return 0;
+}
+
+static int
+esfq_enqueue(struct sk_buff *skb, struct Qdisc* sch)
+{
+	struct esfq_sched_data *q = (struct esfq_sched_data *)sch->data;
+	unsigned hash = esfq_hash(q, skb);
+	unsigned depth = q->depth;
+	esfq_index x;
+
+	x = q->ht[hash];
+	if (x == depth) {
+		q->ht[hash] = x = q->dep[depth].next;
+		q->hash[x] = hash;
+	}
+	__skb_queue_tail(&q->qs[x], skb);
+	esfq_inc(q, x);
+	if (q->qs[x].qlen == 1) {		/* The flow is new */
+		if (q->tail == depth) {	/* It is the first flow */
+			q->tail = x;
+			q->next[x] = x;
+			q->allot[x] = q->quantum;
+		} else {
+			q->next[x] = q->next[q->tail];
+			q->next[q->tail] = x;
+			q->tail = x;
+		}
+	}
+	if (++sch->q.qlen < q->limit-1) {
+		sch->stats.bytes += skb->len;
+		sch->stats.packets++;
+		return 0;
+	}
+
+	esfq_drop(sch);
+	return NET_XMIT_CN;
+}
+
+static int
+esfq_requeue(struct sk_buff *skb, struct Qdisc* sch)
+{
+	struct esfq_sched_data *q = (struct esfq_sched_data *)sch->data;
+	unsigned hash = esfq_hash(q, skb);
+	unsigned depth = q->depth;
+	esfq_index x;
+
+	x = q->ht[hash];
+	if (x == depth) {
+		q->ht[hash] = x = q->dep[depth].next;
+		q->hash[x] = hash;
+	}
+	__skb_queue_head(&q->qs[x], skb);
+	esfq_inc(q, x);
+	if (q->qs[x].qlen == 1) {		/* The flow is new */
+		if (q->tail == depth) {	/* It is the first flow */
+			q->tail = x;
+			q->next[x] = x;
+			q->allot[x] = q->quantum;
+		} else {
+			q->next[x] = q->next[q->tail];
+			q->next[q->tail] = x;
+			q->tail = x;
+		}
+	}
+	if (++sch->q.qlen < q->limit - 1)
+		return 0;
+
+	sch->stats.drops++;
+	esfq_drop(sch);
+	return NET_XMIT_CN;
+}
+
+
+
+
+static struct sk_buff *
+esfq_dequeue(struct Qdisc* sch)
+{
+	struct esfq_sched_data *q = (struct esfq_sched_data *)sch->data;
+	struct sk_buff *skb;
+	unsigned depth = q->depth;
+	esfq_index a, old_a;
+
+	/* No active slots */
+	if (q->tail == depth)
+		return NULL;
+	
+	a = old_a = q->next[q->tail];
+	
+	/* Grab packet */
+	skb = __skb_dequeue(&q->qs[a]);
+	esfq_dec(q, a);
+	sch->q.qlen--;
+	
+	/* Is the slot empty? */
+	if (q->qs[a].qlen == 0) {
+		a = q->next[a];
+		if (a == old_a) {
+			q->tail = depth;
+			return skb;
+		}
+		q->next[q->tail] = a;
+		q->allot[a] += q->quantum;
+	} else if ((q->allot[a] -= skb->len) <= 0) {
+		q->tail = a;
+		a = q->next[a];
+		q->allot[a] += q->quantum;
+	}
+	
+	return skb;
+}
+
+static void
+esfq_reset(struct Qdisc* sch)
+{
+	struct sk_buff *skb;
+
+	while ((skb = esfq_dequeue(sch)) != NULL)
+		kfree_skb(skb);
+}
+
+static void esfq_perturbation(unsigned long arg)
+{
+	struct Qdisc *sch = (struct Qdisc*)arg;
+	struct esfq_sched_data *q = (struct esfq_sched_data *)sch->data;
+
+	q->perturbation = net_random()&0x1F;
+	q->perturb_timer.expires = jiffies + q->perturb_period;
+
+	if (q->perturb_period) {
+		q->perturb_timer.expires = jiffies + q->perturb_period;
+		add_timer(&q->perturb_timer);
+	}
+}
+
+static int esfq_change(struct Qdisc *sch, struct rtattr *opt)
+{
+	struct esfq_sched_data *q = (struct esfq_sched_data *)sch->data;
+	struct tc_sfq_qopt *ctl = RTA_DATA(opt);
+	int old_perturb = q->perturb_period;
+	
+	if (opt->rta_len < RTA_LENGTH(sizeof(*ctl)))
+		return -EINVAL;
+	
+	sch_tree_lock(sch);
+	q->quantum = ctl->quantum ? : psched_mtu(sch->dev);
+	q->perturb_period = ctl->perturb_period*HZ;
+//	q->hash_divisor = ctl->divisor;
+//	q->tail = q->limit = q->depth = ctl->flows;
+	
+	if (ctl->limit)
+		q->limit = min_t(u32, ctl->limit, q->depth);
+	
+	if (ctl->hash_kind) {
+		q->hash_kind = ctl->hash_kind;
+		if (q->hash_kind !=  TCA_SFQ_HASH_CLASSIC)
+			q->perturb_period = 0;
+	}
+	
+	// is sch_tree_lock enough to do this ?
+	while (sch->q.qlen >= q->limit-1)
+		esfq_drop(sch);
+	
+	if (old_perturb)
+		del_timer(&q->perturb_timer);
+	if (q->perturb_period) {
+		q->perturb_timer.expires = jiffies + q->perturb_period;
+		add_timer(&q->perturb_timer);
+	} else {
+		q->perturbation = 0;
+	}
+	sch_tree_unlock(sch);
+	return 0;
+}
+
+static int esfq_init(struct Qdisc *sch, struct rtattr *opt)
+{
+	struct esfq_sched_data *q = (struct esfq_sched_data *)sch->data;
+	struct tc_sfq_qopt *ctl;
+	esfq_index p = ~0UL/2;
+	int i;
+	
+	if (opt && opt->rta_len < RTA_LENGTH(sizeof(*ctl)))
+		return -EINVAL;
+
+	q->perturb_timer.data = (unsigned long)sch;
+	q->perturb_timer.function = esfq_perturbation;
+	init_timer(&q->perturb_timer);
+	q->perturbation = 0;
+	q->hash_kind = TCA_SFQ_HASH_CLASSIC;
+	q->max_depth = 0;
+	if (opt == NULL) {
+		q->quantum = psched_mtu(sch->dev);
+		q->perturb_period = 0;
+		q->hash_divisor = 1024;
+		q->tail = q->limit = q->depth = 128;
+		
+	} else {
+		ctl = RTA_DATA(opt);
+		q->quantum = ctl->quantum ? : psched_mtu(sch->dev);
+		q->perturb_period = ctl->perturb_period*HZ;
+		q->hash_divisor = ctl->divisor ? : 1024;
+		q->tail = q->limit = q->depth = ctl->flows ? : 128;
+		
+		if ( q->depth > p - 1 )
+			return -EINVAL;
+		
+		if (ctl->limit)
+			q->limit = min_t(u32, ctl->limit, q->depth);
+		
+		if (ctl->hash_kind) {
+			q->hash_kind = ctl->hash_kind;
+		}
+		
+		if (q->perturb_period) {
+			q->perturb_timer.expires = jiffies + q->perturb_period;
+			add_timer(&q->perturb_timer);
+		}
+	}
+	
+	q->ht = kmalloc(q->hash_divisor*sizeof(esfq_index), GFP_KERNEL);
+	if (!q->ht)
+		goto err_case;
+		
+	q->dep = kmalloc((1+q->depth*2)*sizeof(struct esfq_head), GFP_KERNEL);
+	if (!q->dep)
+		goto err_case;
+	q->next = kmalloc(q->depth*sizeof(esfq_index), GFP_KERNEL);
+	if (!q->next)
+		goto err_case;
+	
+	q->allot = kmalloc(q->depth*sizeof(short), GFP_KERNEL);
+	if (!q->allot)
+		goto err_case;
+	q->hash = kmalloc(q->depth*sizeof(unsigned short), GFP_KERNEL);
+	if (!q->hash)
+		goto err_case;
+	q->qs = kmalloc(q->depth*sizeof(struct sk_buff_head), GFP_KERNEL);
+	if (!q->qs)
+		goto err_case;
+	
+	for (i=0; i< q->hash_divisor; i++)
+		q->ht[i] = q->depth;
+	for (i=0; i<q->depth; i++) {
+		skb_queue_head_init(&q->qs[i]);
+		q->dep[i+q->depth].next = i+q->depth;
+		q->dep[i+q->depth].prev = i+q->depth;
+	}
+	
+	for (i=0; i<q->depth; i++)
+		esfq_link(q, i);
+	MOD_INC_USE_COUNT;
+	return 0;
+err_case:
+	if (q->ht)
+		kfree(q->ht);
+	if (q->dep)
+		kfree(q->dep);
+	if (q->next)
+		kfree(q->next);
+	if (q->allot)
+		kfree(q->allot);
+	if (q->hash)
+		kfree(q->hash);
+	if (q->qs)
+		kfree(q->qs);
+	return -ENOBUFS;
+}
+
+static void esfq_destroy(struct Qdisc *sch)
+{
+	struct esfq_sched_data *q = (struct esfq_sched_data *)sch->data;
+	del_timer(&q->perturb_timer);
+	if(q->ht)
+		kfree(q->ht);
+	if(q->dep)
+		kfree(q->dep);
+	if(q->next)
+		kfree(q->next);
+	if(q->allot)
+		kfree(q->allot);
+	if(q->hash)
+		kfree(q->hash);
+	if(q->qs)
+		kfree(q->qs);
+	MOD_DEC_USE_COUNT;
+}
+
+static int esfq_dump(struct Qdisc *sch, struct sk_buff *skb)
+{
+	struct esfq_sched_data *q = (struct esfq_sched_data *)sch->data;
+	unsigned char	 *b = skb->tail;
+	struct tc_sfq_qopt opt;
+
+	opt.quantum = q->quantum;
+	opt.perturb_period = q->perturb_period/HZ;
+
+	opt.limit = q->limit;
+	opt.divisor = q->hash_divisor;
+	opt.flows = q->depth;
+	opt.hash_kind = q->hash_kind;
+
+	RTA_PUT(skb, TCA_OPTIONS, sizeof(opt), &opt);
+
+	return skb->len;
+
+rtattr_failure:
+	skb_trim(skb, b - skb->data);
+	return -1;
+}
+
+struct Qdisc_ops esfq_qdisc_ops =
+{
+	NULL,
+	NULL,
+	"esfq",
+	sizeof(struct esfq_sched_data),
+
+	esfq_enqueue,
+	esfq_dequeue,
+	esfq_requeue,
+	esfq_drop,
+
+	esfq_init,
+	esfq_reset,
+	esfq_destroy,
+	NULL, /* esfq_change - needs more work */
+
+	esfq_dump,
+};
+
+#ifdef MODULE
+int init_module(void)
+{
+	return register_qdisc(&esfq_qdisc_ops);
+}
+
+void cleanup_module(void) 
+{
+	unregister_qdisc(&esfq_qdisc_ops);
+}
+#endif
+MODULE_LICENSE("GPL");
diff -u -U 2 -r -N -d linux-2.6.0-test11.orig/net/sched/sch_generic.c linux-2.6.0-test11/net/sched/sch_generic.c
--- linux-2.6.0-test11.orig/net/sched/sch_generic.c	2003-11-30 20:43:54.000000000 +0000
+++ linux-2.6.0-test11/net/sched/sch_generic.c	2003-12-02 19:54:09.000000000 +0000
@@ -30,6 +30,9 @@
 #include <linux/skbuff.h>
 #include <linux/rtnetlink.h>
 #include <linux/init.h>
+#if defined(CONFIG_IMQ) || defined(CONFIG_IMQ_MODULE)
+#include <linux/imq.h>
+#endif
 #include <net/sock.h>
 #include <net/pkt_sched.h>
 
@@ -90,7 +93,11 @@
 			spin_unlock(&dev->queue_lock);
 
 			if (!netif_queue_stopped(dev)) {
+#if defined(CONFIG_IMQ) || defined(CONFIG_IMQ_MODULE)
+				if (netdev_nit && !(skb->imq_flags & IMQ_F_ENQUEUE))
+#else
 				if (netdev_nit)
+#endif
 					dev_queue_xmit_nit(skb, dev);
 
 				if (dev->hard_start_xmit(skb, dev) == 0) {