//======================
//snull.c
//======================
#ifdef LINUX_CONFIG_H
#define LINUX_CONFIG_H
#include
#endif
#include
#include
#include
#include
#include /* printk() */
#include /* kmalloc() */
#include /* error codes */
#include /* size_t */
#include /* mark_bh */
#include
#include /* struct device, and other headers */
#include /* eth_type_trans */
#include /* struct iphdr */
#include /* struct tcphdr */
#include
#include "snull.h"
#include
#include
MODULE_AUTHOR("Alessandro Rubini, Jonathan Corbet");
MODULE_LICENSE("Dual BSD/GPL");
/*
* Transmitter lockup simulation, normally disabled.
*/
static int lockup = 0;
module_param(lockup, int, 0);
static int timeout = SNULL_TIMEOUT;
module_param(timeout, int, 0);
/*
* Do we run in NAPI mode?
*/
static int use_napi = 0;
module_param(use_napi, int, 0);
/*
* A structure representing an in-flight packet.
*/
struct snull_packet {
struct snull_packet *next;
struct net_device *dev;
int datalen;
u8 data[ETH_DATA_LEN];
};
int pool_size = 8;
module_param(pool_size, int, 0);
/*
* This structure is private to each device. It is used to pass
* packets in and out, so there is place for a packet
*/
struct snull_priv {
struct net_device_stats stats;
int status;
struct snull_packet *ppool;
struct snull_packet *rx_queue; /* List of incoming packets */
int rx_int_enabled;
int tx_packetlen;
u8 *tx_packetdata;
struct sk_buff *skb;
spinlock_t lock;
struct napi_struct napi;
struct net_device *dev;
};
static void snull_tx_timeout(struct net_device *dev);
static void (*snull_interrupt)(int, void *, struct pt_regs *);
/*
* Set up a device's packet pool.
*/
void snull_setup_pool(struct net_device *dev)
{
struct snull_priv *priv = netdev_priv(dev);
int i;
struct snull_packet *pkt;
priv->ppool = NULL;
for (i = 0; i < pool_size; i++) {
pkt = kmalloc (sizeof (struct snull_packet), GFP_KERNEL);
if (pkt == NULL) {
printk (KERN_NOTICE "Ran out of memory allocating packet pool\n");
return;
}
pkt->dev = dev;
pkt->next = priv->ppool;
priv->ppool = pkt;
}
}
void snull_teardown_pool(struct net_device *dev)
{
struct snull_priv *priv = netdev_priv(dev);
struct snull_packet *pkt;
while ((pkt = priv->ppool)) {
priv->ppool = pkt->next;
kfree (pkt);
/* FIXME - in-flight packets ? */
}
}
/*
* Buffer/pool management.
*/
struct snull_packet *snull_get_tx_buffer(struct net_device *dev)
{
struct snull_priv *priv = netdev_priv(dev);
unsigned long flags;
struct snull_packet *pkt;
spin_lock_irqsave(&priv->lock, flags);
pkt = priv->ppool;
priv->ppool = pkt->next;
if (priv->ppool == NULL) {
printk (KERN_INFO "Pool empty\n");
netif_stop_queue(dev);
}
spin_unlock_irqrestore(&priv->lock, flags);
return pkt;
}
void snull_release_buffer(struct snull_packet *pkt)
{
unsigned long flags;
struct snull_priv *priv = netdev_priv(pkt->dev);
spin_lock_irqsave(&priv->lock, flags);
pkt->next = priv->ppool;
priv->ppool = pkt;
spin_unlock_irqrestore(&priv->lock, flags);
if (netif_queue_stopped(pkt->dev) && pkt->next == NULL)
netif_wake_queue(pkt->dev);
}
void snull_enqueue_buf(struct net_device *dev, struct snull_packet *pkt)
{
unsigned long flags;
struct snull_priv *priv = netdev_priv(dev);
spin_lock_irqsave(&priv->lock, flags);
pkt->next = priv->rx_queue; /* FIXME - misorders packets */
priv->rx_queue = pkt;
spin_unlock_irqrestore(&priv->lock, flags);
}
struct snull_packet *snull_dequeue_buf(struct net_device *dev)
{
struct snull_priv *priv = netdev_priv(dev);
struct snull_packet *pkt;
unsigned long flags;
spin_lock_irqsave(&priv->lock, flags);
pkt = priv->rx_queue;
if (pkt != NULL)
priv->rx_queue = pkt->next;
spin_unlock_irqrestore(&priv->lock, flags);
return pkt;
}
/*
* Enable and disable receive interrupts.
*/
static void snull_rx_ints(struct net_device *dev, int enable)
{
struct snull_priv *priv = netdev_priv(dev);
priv->rx_int_enabled = enable;
}
/*
* Open and close
*/
int snull_open(struct net_device *dev)
{
/* request_region(), request_irq(), .... (like fops->open) */
/*
* Assign the hardware address of the board: use "\0SNULx", where
* x is 0 or 1. The first byte is '\0' to avoid being a multicast
* address (the first byte of multicast addrs is odd).
*/
memcpy(dev->dev_addr, "\0SNUL0", ETH_ALEN);
if (dev == snull_devs[1])
dev->dev_addr[ETH_ALEN-1]++; /* \0SNUL1 */
netif_start_queue(dev);
return 0;
}
int snull_release(struct net_device *dev)
{
/* release ports, irq and such -- like fops->close */
netif_stop_queue(dev); /* can't transmit any more */
return 0;
}
/*
* Configuration changes (passed on by ifconfig)
*/
int snull_config(struct net_device *dev, struct ifmap *map)
{
if (dev->flags & IFF_UP) /* can't act on a running interface */
return -EBUSY;
/* Don't allow changing the I/O address */
if (map->base_addr != dev->base_addr) {
printk(KERN_WARNING "snull: Can't change I/O address\n");
return -EOPNOTSUPP;
}
/* Allow changing the IRQ */
if (map->irq != dev->irq) {
dev->irq = map->irq;
/* request_irq() is delayed to open-time */
}
/* ignore other fields */
return 0;
}
/*
* Receive a packet: retrieve, encapsulate and pass over to upper levels
*/
void snull_rx(struct net_device *dev, struct snull_packet *pkt)
{
struct sk_buff *skb;
struct snull_priv *priv = netdev_priv(dev);
/*
* The packet has been retrieved from the transmission
* medium. Build an skb around it, so upper layers can handle it
*/
skb = dev_alloc_skb(pkt->datalen + 2);
if (!skb) {
if (printk_ratelimit())
printk(KERN_NOTICE "snull rx: low on mem - packet dropped\n");
priv->stats.rx_dropped++;
goto out;
}
skb_reserve(skb, 2); /* align IP on 16B boundary */
memcpy(skb_put(skb, pkt->datalen), pkt->data, pkt->datalen);
/* Write metadata, and then pass to the receive level */
skb->dev = dev;
skb->protocol = eth_type_trans(skb, dev);
skb->ip_summed = CHECKSUM_UNNECESSARY; /* don't check it */
priv->stats.rx_packets++;
priv->stats.rx_bytes += pkt->datalen;
netif_rx(skb);
out:
return;
}
/*
* The poll implementation.
*/
static int snull_poll(struct napi_struct *napi, int budget)
{
int npackets = 0, quota = budget;
struct sk_buff *skb;
struct snull_priv *priv = container_of(napi,struct snull_priv,napi);
struct net_device *dev=priv->dev;
struct snull_packet *pkt;
while (npackets < quota && priv->rx_queue) {
pkt = snull_dequeue_buf(dev);
skb = dev_alloc_skb(pkt->datalen + 2);
if (! skb) {
if (printk_ratelimit())
printk(KERN_NOTICE "snull: packet dropped\n");
priv->stats.rx_dropped++;
snull_release_buffer(pkt);
continue;
}
skb_reserve(skb, 2); /* align IP on 16B boundary */
memcpy(skb_put(skb, pkt->datalen), pkt->data, pkt->datalen);
skb->dev = dev;
skb->protocol = eth_type_trans(skb, dev);
skb->ip_summed = CHECKSUM_UNNECESSARY; /* don't check it */
netif_receive_skb(skb);
/* Maintain stats */
npackets++;
priv->stats.rx_packets++;
priv->stats.rx_bytes += pkt->datalen;
snull_release_buffer(pkt);
}
/* If we processed all packets, we're done; tell the kernel and reenable ints */
if (! priv->rx_queue) {
napi_complete(&priv->napi);
snull_rx_ints(dev, 1);
return 0;
}
/* We couldn't process everything. */
return 1;
}
/*
* The typical interrupt entry point
*/
static void snull_regular_interrupt(int irq, void *dev_id, struct pt_regs *regs)
{
int statusword;
struct snull_priv *priv;
struct snull_packet *pkt = NULL;
/*
* As usual, check the "device" pointer to be sure it is
* really interrupting.
* Then assign "struct device *dev"
*/
struct net_device *dev = (struct net_device *)dev_id;
/* ... and check with hw if it's really ours */
/* paranoid */
if (!dev)
return;
/* Lock the device */
priv = netdev_priv(dev);
spin_lock(&priv->lock);
/* retrieve statusword: real netdevices use I/O instructions */
statusword = priv->status;
priv->status = 0;
if (statusword & SNULL_RX_INTR) {
/* send it to snull_rx for handling */
pkt = priv->rx_queue;
if (pkt) {
priv->rx_queue = pkt->next;
snull_rx(dev, pkt);
}
}
if (statusword & SNULL_TX_INTR) {
/* a transmission is over: free the skb */
priv->stats.tx_packets++;
priv->stats.tx_bytes += priv->tx_packetlen;
dev_kfree_skb(priv->skb);
}
/* Unlock the device and we are done */
spin_unlock(&priv->lock);
if (pkt) snull_release_buffer(pkt); /* Do this outside the lock! */
return;
}
/*
* A NAPI interrupt handler.
*/
static void snull_napi_interrupt(int irq, void *dev_id, struct pt_regs *regs)
{
int statusword;
struct snull_priv *priv;
/*
* As usual, check the "device" pointer for shared handlers.
* Then assign "struct device *dev"
*/
struct net_device *dev = (struct net_device *)dev_id;
/* ... and check with hw if it's really ours */
/* paranoid */
if (!dev)
return;
/* Lock the device */
priv = netdev_priv(dev);
spin_lock(&priv->lock);
/* retrieve statusword: real netdevices use I/O instructions */
statusword = priv->status;
priv->status = 0;
if (statusword & SNULL_RX_INTR) {
snull_rx_ints(dev, 0); /* Disable further interrupts */
napi_schedule(&priv->napi);
}
if (statusword & SNULL_TX_INTR) {
/* a transmission is over: free the skb */
priv->stats.tx_packets++;
priv->stats.tx_bytes += priv->tx_packetlen;
dev_kfree_skb(priv->skb);
}
/* Unlock the device and we are done */
spin_unlock(&priv->lock);
return;
}
/*
* Transmit a packet (low level interface)
*/
static void snull_hw_tx(char *buf, int len, struct net_device *dev)
{
/*
* This function deals with hw details. This interface loops
* back the packet to the other snull interface (if any).
* In other words, this function implements the snull behaviour,
* while all other procedures are rather device-independent
*/
struct iphdr *ih;
struct net_device *dest;
struct snull_priv *priv;
u32 *saddr, *daddr;
struct snull_packet *tx_buffer;
/* I am paranoid. Ain't I? */
if (len < sizeof(struct ethhdr) + sizeof(struct iphdr)) {
printk("snull: Hmm... packet too short (%i octets)\n",
len);
return;
}
if (0) { /* enable this conditional to look at the data */
int i;
PDEBUG("len is %i\n" KERN_DEBUG "data:",len);
for (i=14 ; i
printk("\n");
}
/*
* Ethhdr is 14 bytes, but the kernel arranges for iphdr
* to be aligned (i.e., ethhdr is unaligned)
*/
ih = (struct iphdr *)(buf+sizeof(struct ethhdr));
saddr = &ih->saddr;
daddr = &ih->daddr;
((u8 *)saddr)[2] ^= 1; /* change the third octet (class C) */
((u8 *)daddr)[2] ^= 1;
ih->check = 0; /* and rebuild the checksum (ip needs it) */
ih->check = ip_fast_csum((unsigned char *)ih,ih->ihl);
if (dev == snull_devs[0])
PDEBUGG("%08x:%05i --> %08x:%05i\n",
ntohl(ih->saddr),ntohs(((struct tcphdr *)(ih+1))->source),
ntohl(ih->daddr),ntohs(((struct tcphdr *)(ih+1))->dest));
else
PDEBUGG("%08x:%05i <-- %08x:%05i\n",
ntohl(ih->daddr),ntohs(((struct tcphdr *)(ih+1))->dest),
ntohl(ih->saddr),ntohs(((struct tcphdr *)(ih+1))->source));
/*
* Ok, now the packet is ready for transmission: first simulate a
* receive interrupt on the twin device, then a
* transmission-done on the transmitting device
*/
dest = snull_devs[dev == snull_devs[0] ? 1 : 0];
priv = netdev_priv(dest);
tx_buffer = snull_get_tx_buffer(dev);
tx_buffer->datalen = len;
memcpy(tx_buffer->data, buf, len);
snull_enqueue_buf(dest, tx_buffer);
if (priv->rx_int_enabled) {
priv->status |= SNULL_RX_INTR;
snull_interrupt(0, dest, NULL);
}
priv = netdev_priv(dev);
priv->tx_packetlen = len;
priv->tx_packetdata = buf;
priv->status |= SNULL_TX_INTR;
if (lockup && ((priv->stats.tx_packets + 1) % lockup) == 0) {
/* Simulate a dropped transmit interrupt */
netif_stop_queue(dev);
PDEBUG("Simulate lockup at %ld, txp %ld\n", jiffies,
(unsigned long) priv->stats.tx_packets);
}
else
snull_interrupt(0, dev, NULL);
}
/*
* Transmit a packet (called by the kernel)
*/
int snull_tx(struct sk_buff *skb, struct net_device *dev)
{
int len;
char *data, shortpkt[ETH_ZLEN];
struct snull_priv *priv = netdev_priv(dev);
data = skb->data;
len = skb->len;
if (len < ETH_ZLEN) {
memset(shortpkt, 0, ETH_ZLEN);
memcpy(shortpkt, skb->data, skb->len);
len = ETH_ZLEN;
data = shortpkt;
}
dev->trans_start = jiffies; /* save the timestamp */
/* Remember the skb, so we can free it at interrupt time */
priv->skb = skb;
/* actual deliver of data is device-specific, and not shown here */
snull_hw_tx(data, len, dev);
return 0; /* Our simple device can not fail */
}
/*
* Deal with a transmit timeout.
*/
void snull_tx_timeout (struct net_device *dev)
{
struct snull_priv *priv = netdev_priv(dev);
PDEBUG("Transmit timeout at %ld, latency %ld\n", jiffies,
jiffies - dev->trans_start);
/* Simulate a transmission interrupt to get things moving */
priv->status = SNULL_TX_INTR;
snull_interrupt(0, dev, NULL);
priv->stats.tx_errors++;
netif_wake_queue(dev);
return;
}
/*
* Ioctl commands
*/
int snull_ioctl(struct net_device *dev, struct ifreq *rq, int cmd)
{
PDEBUG("ioctl\n");
return 0;
}
/*
* Return statistics to the caller
*/
struct net_device_stats *snull_stats(struct net_device *dev)
{
struct snull_priv *priv = netdev_priv(dev);
return &priv->stats;
}
/*
* This function is called to fill up an eth header, since arp is not
* available on the interface
*/
int snull_rebuild_header(struct sk_buff *skb)
{
struct ethhdr *eth = (struct ethhdr *) skb->data;
struct net_device *dev = skb->dev;
memcpy(eth->h_source, dev->dev_addr, dev->addr_len);
memcpy(eth->h_dest, dev->dev_addr, dev->addr_len);
eth->h_dest[ETH_ALEN-1] ^= 0x01; /* dest is us xor 1 */
return 0;
}
int snull_header(struct sk_buff *skb, struct net_device *dev,
unsigned short type, const void *daddr, const void *saddr,
unsigned len)
{
struct ethhdr *eth = (struct ethhdr *)skb_push(skb,ETH_HLEN);
eth->h_proto = htons(type);
memcpy(eth->h_source, saddr ? saddr : dev->dev_addr, dev->addr_len);
memcpy(eth->h_dest, daddr ? daddr : dev->dev_addr, dev->addr_len);
eth->h_dest[ETH_ALEN-1] ^= 0x01; /* dest is us xor 1 */
return (dev->hard_header_len);
}
/*
* The "change_mtu" method is usually not needed.
* If you need it, it must be like this.
*/
int snull_change_mtu(struct net_device *dev, int new_mtu)
{
unsigned long flags;
struct snull_priv *priv = netdev_priv(dev);
spinlock_t *lock = &priv->lock;
/* check ranges */
if ((new_mtu < 68) || (new_mtu > 1500))
return -EINVAL;
/*
* Do anything you need, and the accept the value
*/
spin_lock_irqsave(lock, flags);
dev->mtu = new_mtu;
spin_unlock_irqrestore(lock, flags);
return 0; /* success */
}
static const struct net_device_ops snull_dev_ops = {
.ndo_open =snull_open,
.ndo_stop =snull_release,
.ndo_set_config =snull_config,
.ndo_start_xmit =snull_tx,
.ndo_do_ioctl =snull_ioctl,
.ndo_get_stats =snull_stats,
.ndo_change_mtu =snull_change_mtu,
.ndo_tx_timeout =snull_tx_timeout,
};
static const struct header_ops snull_header_ops= {
.create =snull_header,
.rebuild =snull_rebuild_header,
.cache = NULL, /* Disable caching */
};
/*
* The init function (sometimes called probe).
* It is invoked by register_netdev()
*/
void snull_init(struct net_device *dev)
{
struct snull_priv *priv;
#if 0
/*
* Make the usual checks: check_region(), probe irq, ... -ENODEV
* should be returned if no device found. No resource should be
* grabbed: this is done on open().
*/
#endif
/*
* Then, assign other fields in dev, using ether_setup() and some
* hand assignments
*/
ether_setup(dev); /* assign some of the fields */
dev->netdev_ops = &snull_dev_ops;
dev->header_ops = &snull_header_ops;
dev->watchdog_timeo = timeout;
/* keep the default flags, just add NOARP */
dev->flags |= IFF_NOARP;
dev->features |= NETIF_F_NO_CSUM;
/*
* Then, initialize the priv field. This encloses the statistics
* and a few private fields.
*/
priv = netdev_priv(dev);
memset(priv, 0, sizeof(struct snull_priv));
priv->dev = dev;
spin_lock_init(&priv->lock);
snull_rx_ints(dev, 1); /* enable receive interrupts */
snull_setup_pool(dev);
if (use_napi) {
netif_napi_add(dev,&priv->napi,snull_poll,2);
}
}
/*
* The devices
*/
struct net_device *snull_devs[2];
/*
* Finally, the module stuff
*/
void snull_cleanup(void)
{
int i;
for (i = 0; i < 2; i++) {
if (snull_devs[i]) {
unregister_netdev(snull_devs[i]);
snull_teardown_pool(snull_devs[i]);
free_netdev(snull_devs[i]);
}
}
return;
}
int snull_init_module(void)
{
int result, i, ret = -ENOMEM;
snull_interrupt = use_napi ? snull_napi_interrupt : snull_regular_interrupt;
/* Allocate the devices */
snull_devs[0] = alloc_netdev(sizeof(struct snull_priv), "sn%d",
snull_init);
snull_devs[1] = alloc_netdev(sizeof(struct snull_priv), "sn%d",
snull_init);
if (snull_devs[0] == NULL || snull_devs[1] == NULL)
goto out;
ret = -ENODEV;
for (i = 0; i < 2; i++)
if ((result = register_netdev(snull_devs[i])))
printk("snull: error %i registering device \"%s\"\n",
result, snull_devs[i]->name);
else
ret = 0;
out:
if (ret)
snull_cleanup();
return ret;
}
module_init(snull_init_module);
module_exit(snull_cleanup);
//====================================
//snull.h
//====================================
#undef PDEBUG /* undef it, just in case */
#ifdef SNULL_DEBUG
# ifdef __KERNEL__
/* This one if debugging is on, and kernel space */
# define PDEBUG(fmt, args...) printk( KERN_DEBUG "snull: " fmt, ## args)
# else
/* This one for user space */
# define PDEBUG(fmt, args...) fprintf(stderr, fmt, ## args)
# endif
#else
# define PDEBUG(fmt, args...) /* not debugging: nothing */
#endif
#undef PDEBUGG
#define PDEBUGG(fmt, args...) /* nothing: it's a placeholder */
/* These are the flags in the statusword */
#define SNULL_RX_INTR 0x0001
#define SNULL_TX_INTR 0x0002
/* Default timeout period */
#define SNULL_TIMEOUT 5 /* In jiffies */
extern struct net_device *snull_devs[];
//=================================
//Makefile
//=================================
ifeq ($(KERNELRELEASE),)
KERNELDIR ?= /home/fang/ext-disk/doc/forlinux/kernel-3.2
PWD := $(shell pwd)
modules:
$(MAKE) -C $(KERNELDIR) M=$(PWD) modules
modules_install:
$(MAKE) -C $(KERNELDIR) M=$(PWD) modules_install
clean:
rm -rf *.o *~ core .depend .*.cmd *.ko *.mod.c .tmp_versions
.PHONY: modules modules_install clean
else
obj-m := snull.o
#obj-m := lo-fang.o
endif
//=====================================
//演示过程:
//=====================================
/*
下面是网络编号的可能值. 一旦你把这些行放进 /etc/networks, 你可以使用
名子来调用你的网络. 这些值选自保留做私人用途的编号范围.
snullnet0 192.168.0.0
snullnet1 192.168.1.0
下面的是一些可能的主机编号, 可放进 /etc/hosts 里面:
192.168.0.1 local0
192.168.0.2 remote0
192.168.1.2 local1
192.168.1.1 remote1
这些编号的重要特性是 local0 的主机部分与 remote1 的主机部分相同,
local1 的主机部分和 remote0 的主机部分相同. 你可以使用完全不同的编号,
只要保持着这种关系.
但是要小心, 如果你的计算机以及连接到一个网络上. 你选择的编号可能是真
实的互联网或者内联网的编号, 把它们安排给你的接口会阻止和这些真实的主
机间的通讯. 例如, 尽管刚刚展示的这些编号不是可以路由的互联网编号, 它
们也可能被你的私有网络已经在使用.
不管你选择什么编号, 你可以正确设置这些接口来操作, 通过发出下面的命令:
ifconfig sn0 local0
ifconfig sn1 local1
你可能需要添加网络掩码 255.255.255.0 参数, 如果选择的地址范围不是 C
类范围.
在此, 接口的"远程"端点能够到达了. 下面的屏幕拷贝显示了一个主机如何到
达 remote0 和 remote1 的, 通过 snull 接口.
morgana% ping -c 2 remote0
64 bytes from 192.168.0.99: icmp_seq=0 ttl=64 time=1.6 ms
64 bytes from 192.168.0.99: icmp_seq=1 ttl=64 time=0.9 ms
2 packets transmitted, 2 packets received, 0% packet loss
morgana% ping -c 2 remote1
64 bytes from 192.168.1.88: icmp_seq=0 ttl=64 time=1.8 ms
64 bytes from 192.168.1.88: icmp_seq=1 ttl=64 time=0.9 ms
2 packets transmitted, 2 packets received, 0% packet loss
注意, 你不能到达属于这两个网络的任何其他主机, 因为报文被你的计算机丢
弃了, 在地址被修改和收到报文之后. 例如, 一个发向 192.168.0.32 的报文
将离开 sn0 并以 192.168.1.32 的目的地址出现在 sn1, 这并不是这台主机的
本地地址.
*/
