[NET]: Add IFB (Intermediate Functional Block) network device.

A new device to do intermidiate functional block in a system shared
manner.  To use the new functionality, you need to turn on
qos/classifier actions.

The new functionality can be grouped as:

1) qdiscs/policies that are per device as opposed to system wide.  ifb
allows for a device which can be redirected to thus providing an
impression of sharing.

2) Allows for queueing incoming traffic for shaping instead of
dropping.

Packets are redirected to this device using tc/action mirred redirect
construct. If they are sent to it by plain routing instead then they
will merely be dropped and the stats would indicate that.

Signed-off-by: Jamal Hadi Salim <hadi@cyberus.ca>
Signed-off-by: David S. Miller <davem@davemloft.net>

3 files changed, 308 insertions, 0 deletions

diff --git a/drivers/net/Kconfig b/drivers/net/Kconfig
index 733bc25b2bf..4959800a18d 100644
--- a/drivers/net/Kconfig
+++ b/drivers/net/Kconfig
@@ -27,6 +27,19 @@ config NETDEVICES
 # that for each of the symbols.
 if NETDEVICES
 
+config IFB
+	tristate "Intermediate Functional Block support"
+	depends on NET_CLS_ACT
+	---help---
+	  This is an intermidiate driver that allows sharing of
+	  resources.
+	  To compile this driver as a module, choose M here: the module
+	  will be called ifb.  If you want to use more than one ifb
+	  device at a time, you need to compile this driver as a module.
+	  Instead of 'ifb', the devices will then be called 'ifb0',
+	  'ifb1' etc.
+	  Look at the iproute2 documentation directory for usage etc
+
 config DUMMY
 	tristate "Dummy net driver support"
 	---help---
diff --git a/drivers/net/Makefile b/drivers/net/Makefile
index b74a7cb5bae..00e72b12fb9 100644
--- a/drivers/net/Makefile
+++ b/drivers/net/Makefile
@@ -125,6 +125,7 @@ ifeq ($(CONFIG_SLIP_COMPRESSED),y)
 endif
 
 obj-$(CONFIG_DUMMY) += dummy.o
+obj-$(CONFIG_IFB) += ifb.o
 obj-$(CONFIG_DE600) += de600.o
 obj-$(CONFIG_DE620) += de620.o
 obj-$(CONFIG_LANCE) += lance.o
diff --git a/drivers/net/ifb.c b/drivers/net/ifb.c
new file mode 100644
index 00000000000..1b699259b4e
--- /dev/null
+++ b/drivers/net/ifb.c
@@ -0,0 +1,294 @@
+/* drivers/net/ifb.c: 
+
+	The purpose of this driver is to provide a device that allows
+	for sharing of resources:
+
+	1) qdiscs/policies that are per device as opposed to system wide.
+	ifb allows for a device which can be redirected to thus providing
+	an impression of sharing.
+
+	2) Allows for queueing incoming traffic for shaping instead of
+	dropping. 
+	
+	The original concept is based on what is known as the IMQ
+	driver initially written by Martin Devera, later rewritten
+	by Patrick McHardy and then maintained by Andre Correa.
+
+	You need the tc action  mirror or redirect to feed this device
+       	packets.
+
+	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:	Jamal Hadi Salim (2005)
+ 
+*/
+
+
+#include <linux/config.h>
+#include <linux/module.h>
+#include <linux/kernel.h>
+#include <linux/netdevice.h>
+#include <linux/etherdevice.h>
+#include <linux/init.h>
+#include <linux/moduleparam.h>
+#include <net/pkt_sched.h> 
+
+#define TX_TIMEOUT  (2*HZ)
+                                                                                
+#define TX_Q_LIMIT    32
+struct ifb_private {
+	struct net_device_stats stats;
+	struct tasklet_struct   ifb_tasklet;
+	int     tasklet_pending;
+	/* mostly debug stats leave in for now */
+	unsigned long   st_task_enter; /* tasklet entered */
+	unsigned long   st_txq_refl_try; /* transmit queue refill attempt */
+	unsigned long   st_rxq_enter; /* receive queue entered */
+	unsigned long   st_rx2tx_tran; /* receive to trasmit transfers */
+	unsigned long   st_rxq_notenter; /*receiveQ not entered, resched */
+	unsigned long   st_rx_frm_egr; /* received from egress path */
+	unsigned long   st_rx_frm_ing; /* received from ingress path */
+	unsigned long   st_rxq_check;
+	unsigned long   st_rxq_rsch;
+	struct sk_buff_head     rq;
+	struct sk_buff_head     tq;
+};
+
+static int numifbs = 1;
+
+static void ri_tasklet(unsigned long dev);
+static int ifb_xmit(struct sk_buff *skb, struct net_device *dev);
+static struct net_device_stats *ifb_get_stats(struct net_device *dev);
+static int ifb_open(struct net_device *dev);
+static int ifb_close(struct net_device *dev);
+
+static void ri_tasklet(unsigned long dev) 
+{
+
+	struct net_device *_dev = (struct net_device *)dev;
+	struct ifb_private *dp = netdev_priv(_dev);
+	struct net_device_stats *stats = &dp->stats;
+	struct sk_buff *skb;
+
+	dp->st_task_enter++;
+	if ((skb = skb_peek(&dp->tq)) == NULL) {
+		dp->st_txq_refl_try++;
+		if (spin_trylock(&_dev->xmit_lock)) {
+			dp->st_rxq_enter++;
+			while ((skb = skb_dequeue(&dp->rq)) != NULL) {
+				skb_queue_tail(&dp->tq, skb);
+				dp->st_rx2tx_tran++;
+			}
+			spin_unlock(&_dev->xmit_lock);
+		} else {
+			/* reschedule */
+			dp->st_rxq_notenter++;
+			goto resched;
+		}
+	}
+
+	while ((skb = skb_dequeue(&dp->tq)) != NULL) {
+		u32 from = G_TC_FROM(skb->tc_verd);
+
+		skb->tc_verd = 0;
+		skb->tc_verd = SET_TC_NCLS(skb->tc_verd);
+		stats->tx_packets++;
+		stats->tx_bytes +=skb->len;
+		if (from & AT_EGRESS) {
+			dp->st_rx_frm_egr++;
+			dev_queue_xmit(skb);
+		} else if (from & AT_INGRESS) {
+
+			dp->st_rx_frm_ing++;
+			netif_rx(skb);
+		} else {
+			dev_kfree_skb(skb);
+			stats->tx_dropped++;
+		}
+	}
+
+	if (spin_trylock(&_dev->xmit_lock)) {
+		dp->st_rxq_check++;
+		if ((skb = skb_peek(&dp->rq)) == NULL) {
+			dp->tasklet_pending = 0;
+			if (netif_queue_stopped(_dev))
+				netif_wake_queue(_dev);
+		} else {
+			dp->st_rxq_rsch++;
+			spin_unlock(&_dev->xmit_lock);
+			goto resched;
+		}
+		spin_unlock(&_dev->xmit_lock);
+	} else {
+resched:
+		dp->tasklet_pending = 1;
+		tasklet_schedule(&dp->ifb_tasklet);
+	}
+
+}
+
+static void __init ifb_setup(struct net_device *dev)
+{
+	/* Initialize the device structure. */
+	dev->get_stats = ifb_get_stats;
+	dev->hard_start_xmit = ifb_xmit;
+	dev->open = &ifb_open;
+	dev->stop = &ifb_close;
+
+	/* Fill in device structure with ethernet-generic values. */
+	ether_setup(dev);
+	dev->tx_queue_len = TX_Q_LIMIT;
+	dev->change_mtu = NULL;
+	dev->flags |= IFF_NOARP;
+	dev->flags &= ~IFF_MULTICAST;
+	SET_MODULE_OWNER(dev);
+	random_ether_addr(dev->dev_addr);
+}
+
+static int ifb_xmit(struct sk_buff *skb, struct net_device *dev)
+{
+	struct ifb_private *dp = netdev_priv(dev);
+	struct net_device_stats *stats = &dp->stats;
+	int ret = 0;
+	u32 from = G_TC_FROM(skb->tc_verd);
+
+	stats->tx_packets++;
+	stats->tx_bytes+=skb->len;
+
+	if (!from || !skb->input_dev) {
+dropped:
+		dev_kfree_skb(skb);
+		stats->rx_dropped++;
+		return ret;
+	} else {
+		/* 
+		 * note we could be going
+		 * ingress -> egress or
+		 * egress -> ingress
+		*/
+		skb->dev = skb->input_dev;
+		skb->input_dev = dev;
+		if (from & AT_INGRESS) {
+			skb_pull(skb, skb->dev->hard_header_len);
+		} else {
+			if (!(from & AT_EGRESS)) {
+				goto dropped;
+			}
+		}
+	}
+
+	if (skb_queue_len(&dp->rq) >= dev->tx_queue_len) {
+		netif_stop_queue(dev);
+	}
+
+	dev->trans_start = jiffies;
+	skb_queue_tail(&dp->rq, skb);
+	if (!dp->tasklet_pending) {
+		dp->tasklet_pending = 1;
+		tasklet_schedule(&dp->ifb_tasklet);
+	}
+
+	return ret;
+}
+
+static struct net_device_stats *ifb_get_stats(struct net_device *dev)
+{
+	struct ifb_private *dp = netdev_priv(dev);
+	struct net_device_stats *stats = &dp->stats;
+
+	pr_debug("tasklets stats %ld:%ld:%ld:%ld:%ld:%ld:%ld:%ld:%ld \n",
+		dp->st_task_enter, dp->st_txq_refl_try, dp->st_rxq_enter, 
+		dp->st_rx2tx_tran dp->st_rxq_notenter, dp->st_rx_frm_egr,
+		dp->st_rx_frm_ing, dp->st_rxq_check, dp->st_rxq_rsch );
+
+	return stats;
+}
+
+static struct net_device **ifbs;
+
+/* Number of ifb devices to be set up by this module. */
+module_param(numifbs, int, 0);
+MODULE_PARM_DESC(numifbs, "Number of ifb devices");
+
+static int ifb_close(struct net_device *dev)
+{
+	struct ifb_private *dp = netdev_priv(dev);
+
+	tasklet_kill(&dp->ifb_tasklet);
+	netif_stop_queue(dev);
+	skb_queue_purge(&dp->rq);
+	skb_queue_purge(&dp->tq);
+	return 0;
+}
+
+static int ifb_open(struct net_device *dev)
+{
+	struct ifb_private *dp = netdev_priv(dev);
+
+	tasklet_init(&dp->ifb_tasklet, ri_tasklet, (unsigned long)dev);
+	skb_queue_head_init(&dp->rq);
+	skb_queue_head_init(&dp->tq);
+	netif_start_queue(dev);
+
+	return 0;
+}
+
+static int __init ifb_init_one(int index)
+{
+	struct net_device *dev_ifb;
+	int err;
+
+	dev_ifb = alloc_netdev(sizeof(struct ifb_private),
+				 "ifb%d", ifb_setup);
+
+	if (!dev_ifb)
+		return -ENOMEM;
+
+	if ((err = register_netdev(dev_ifb))) {
+		free_netdev(dev_ifb);
+		dev_ifb = NULL;
+	} else {
+		ifbs[index] = dev_ifb; 
+	}
+
+	return err;
+}
+
+static void ifb_free_one(int index)
+{
+	unregister_netdev(ifbs[index]);
+	free_netdev(ifbs[index]);
+} 
+
+static int __init ifb_init_module(void)
+{ 
+	int i, err = 0;
+	ifbs = kmalloc(numifbs * sizeof(void *), GFP_KERNEL); 
+	if (!ifbs)
+		return -ENOMEM; 
+	for (i = 0; i < numifbs && !err; i++)
+		err = ifb_init_one(i); 
+	if (err) { 
+		while (--i >= 0)
+			ifb_free_one(i);
+	}
+
+	return err;
+} 
+
+static void __exit ifb_cleanup_module(void)
+{
+	int i;
+
+	for (i = 0; i < numifbs; i++) 
+		ifb_free_one(i); 
+	kfree(ifbs);	
+}
+
+module_init(ifb_init_module);
+module_exit(ifb_cleanup_module);
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Jamal Hadi Salim");