LINUX网卡驱动分析――Intel(R) PRO/100 Network Driver
LINUX网卡驱动分析――Intel(R) PRO/100 Network Driver
最近学习LINUX驱动开发，看的是《LINUX DEVICE DRIVER》这本书，差不多能看懂，不过说实在的，都是些理论上的东西，没有什么实践，感觉提升比较慢，所以想拿LINUX自带的E100网卡驱动来分析和学习一下，看看人家大师们怎么写驱动的。然后如果有时间再写一个关于我的开发板的S3C2410上的网卡(CS8900A)驱动。
注：以下分析的是基于2.6.14上带的e100.c驱动源代码。
网卡是一个网络设备，同时也是一个PCI设备。E100网卡驱动就是按照PCI规范来编写的，同时又设及到驱动程序的内存映射和DMA操作，所以是比较综合的一个驱动程序。
一、模块的初始化。
module_init(e100_init_module);
// 2.6
内核模块初始化注册
module_exit(e100_cleanup_module);
//
模块清除注册
接着step into -
àe100_init_module,
static int __init e100_init_module(void)
{
//
检查打印级别是否大于１
if(((1 << debug) - 1) & NETIF_MSG_DRV) {
printk(KERN_INFO PFX "%s, %s/n", DRV_DESCRIPTION, DRV_VERSION);
printk(KERN_INFO PFX "%s/n", DRV_COPYRIGHT);
}
//
调用
PCI
的模块注册函数，因为网卡是一个
PCI
设备
return pci_module_init(&e100_driver);
}
static void __exit e100_cleanup_module(void)
{
//
清除ＰＣＩ注册信息
pci_unregister_driver(&e100_driver);
}
接下来看一下，pci_module_init(&e100_driver);
e100_driver是一个struct pci_driver类型。在代码中，做如下初始化：
static struct pci_driver e100_driver = {
.name = DRV_NAME,// DRIVER
名称
.id_table = e100_id_table,//e100
驱动支持的
PCI
设备列表
.probe = e100_probe,//PCI
探测函数指针
.remove = __devexit_p(e100_remove),//
移除函数
#ifdef CONFIG_PM
.suspend = e100_suspend,//
挂起操作
.resume = e100_resume,//
恢复
#endif
.shutdown = e100_shutdown,//
关闭，注意：
LINUX DEVICE DRIVER
这本书中没有这一项。
};
pci_module_init其实是pci_register_driver的宏定义，实际执行pci模块注册过程。PCI注册过程除了初始化pci_driver 内部struct device_driver结构以外，还执行一些与linux设备模型相关的操作，可以参考drivers/pci.c中的初始化代码；下面我们还是将主要精力放在分析网卡驱动代码上。
接下来看一下探测函数：e100_probe；为了方便还是将代码贴一下：
static int __devinit e100_probe(struct pci_dev *pdev,
const struct pci_device_id *ent)
{
struct net_device *netdev;//
声明网络设备指针
struct nic *nic;//
网卡信息结构指针
int err;
//
一看就知道了，分配空间嘛，然后根据打印级别控制打印
if(!(netdev = alloc_etherdev(sizeof(struct nic)))) {
if(((1 << debug) - 1) & NETIF_MSG_PROBE)
printk(KERN_ERR PFX "Etherdev alloc failed, abort./n");
return -ENOMEM;
}
//
网络设备的初始化，相关的函数注册。
netdev->open = e100_open;
//
打开
netdev->stop = e100_close；
//
关闭
netdev->hard_start_xmit = e100_xmit_frame;//
开始传输
netdev->get_stats = e100_get_stats;//
获取状态
//
设置多播列表
netdev->set_multicast_list = e100_set_multicast_list;
//
设置物理ＭＡＣ地址
netdev->set_mac_address = e100_set_mac_address;
netdev->change_mtu = e100_change_mtu;
netdev->do_ioctl = e100_do_ioctl;
SET_ETHTOOL_OPS(netdev, &e100_ethtool_ops);
netdev->tx_timeout = e100_tx_timeout;
netdev->watchdog_timeo = E100_WATCHDOG_PERIOD;
netdev->poll = e100_poll;
netdev->weight = E100_NAPI_WEIGHT;
#ifdef CONFIG_NET_POLL_CONTROLLER
netdev->poll_controller = e100_netpoll;
#endif
strcpy(netdev->name, pci_name(pdev));
//
初始化完网络设备，然后与网卡信息进行绑定
//
netdev_priv
是取一个指针，
pointer to private data
nic = netdev_priv(netdev);
nic->netdev = netdev;
nic->pdev = pdev;
nic->msg_enable = (1 << debug) - 1;
pci_set_drvdata(pdev, netdev);
//
完成之后，激活设备
if((err = pci_enable_device(pdev))) {
DPRINTK(PROBE, ERR, "Cannot enable PCI device, aborting./n");
goto err_out_free_dev;
}
//
取得和资源相关的标志
if(!(pci_resource_flags(pdev, 0) & IORESOURCE_MEM)) {
DPRINTK(PROBE, ERR, "Cannot find proper PCI device "
"base address, aborting./n");
err = -ENODEV;
goto err_out_disable_pdev;
}
// 获取相关ＰＣＩ资源，应该是配置寄存器映射的内存区
if((err = pci_request_regions(pdev, DRV_NAME))) {
DPRINTK(PROBE, ERR, "Cannot obtain PCI resources, aborting./n");
goto err_out_disable_pdev;
}
// 设置３２位ＤＭＡ位掩码，一方面也为了测试配置
if((err = pci_set_dma_mask(pdev, DMA_32BIT_MASK))) {
DPRINTK(PROBE, ERR, "No usable DMA configuration, aborting./n");
goto err_out_free_res;
}
// 空操作
SET_MODULE_OWNER(netdev);
SET_NETDEV_DEV(netdev, &pdev->dev);
// io映射成虚拟地址，供内核使用
nic->csr = ioremap(pci_resource_start(pdev, 0), sizeof(struct csr));
if(!nic->csr) {
DPRINTK(PROBE, ERR, "Cannot map device registers, aborting./n");
err = -ENOMEM;
goto err_out_free_res;
}
if(ent->driver_data)
nic->flags |= ich;
else
nic->flags &= ~ich;
e100_get_defaults(nic);
/* locks must be initialized before calling hw_reset */
spin_lock_init(&nic->cb_lock);
spin_lock_init(&nic->cmd_lock);
/* Reset the device before pci_set_master() in case device is in some
* funky state and has an interrupt pending - hint: we don't have the
* interrupt handler registered yet. */
e100_hw_reset(nic);
pci_set_master(pdev);
init_timer(&nic->watchdog);
nic->watchdog.function = e100_watchdog;
nic->watchdog.data = (unsigned long)nic;
init_timer(&nic->blink_timer);
nic->blink_timer.function = e100_blink_led;
nic->blink_timer.data = (unsigned long)nic;
INIT_WORK(&nic->tx_timeout_task,
(void (*)(void *))e100_tx_timeout_task, netdev);
if((err = e100_alloc(nic))) {
DPRINTK(PROBE, ERR, "Cannot alloc driver memory, aborting./n");
goto err_out_iounmap;
}
if((err = e100_eeprom_load(nic)))
goto err_out_free;
e100_phy_init(nic);
memcpy(netdev->dev_addr, nic->eeprom, ETH_ALEN);
if(!is_valid_ether_addr(netdev->dev_addr)) {
DPRINTK(PROBE, ERR, "Invalid MAC address from "
"EEPROM, aborting./n");
err = -EAGAIN;
goto err_out_free;
}
/* Wol magic packet can be enabled from eeprom */
if((nic->mac >= mac_82558_D101_A4) &&
(nic->eeprom[eeprom_id] & eeprom_id_wol))
nic->flags |= wol_magic;
/* ack any pending wake events, disable PME */
pci_enable_wake(pdev, 0, 0);
strcpy(netdev->name, "eth%d");
if((err = register_netdev(netdev))) {
DPRINTK(PROBE, ERR, "Cannot register net device, aborting./n");
goto err_out_free;
}
DPRINTK(PROBE, INFO, "addr 0x%lx, irq %d, "
"MAC addr %02X:%02X:%02X:%02X:%02X:%02X/n",
pci_resource_start(pdev, 0), pdev->irq,
netdev->dev_addr[0], netdev->dev_addr[1], netdev->dev_addr[2],
netdev->dev_addr[3], netdev->dev_addr[4], netdev->dev_addr[5]);
return 0;
err_out_free:
e100_free(nic);
err_out_iounmap:
iounmap(nic->csr);
err_out_free_res:
pci_release_regions(pdev);
err_out_disable_pdev:
pci_disable_device(pdev);
err_out_free_dev:
pci_set_drvdata(pdev, NULL);
free_netdev(netdev);
return err;
｝
以上就是网卡探测的过程。
//
把ＰＣＩ总线读一下，强迫写完成。
static inline void e100_write_flush(struct nic *nic)
{
/* Flush previous PCI writes through intermediate bridges
* by doing a benign read */
(void)readb(&nic->csr->scb.status);
}
static inline void e100_enable_irq(struct nic *nic)
{
unsigned long flags;
//
自旋锁之前，禁止中断
spin_lock_irqsave(&nic->cmd_lock, flags);
writeb(irq_mask_none, &nic->csr->scb.cmd_hi);
spin_unlock_irqrestore(&nic->cmd_lock, flags);
//
刷新
e100_write_flush(nic);
}
static inline void e100_disable_irq(struct nic *nic)
{
unsigned long flags;
spin_lock_irqsave(&nic->cmd_lock, flags);
writeb(irq_mask_all, &nic->csr->scb.cmd_hi);
spin_unlock_irqrestore(&nic->cmd_lock, flags);
e100_write_flush(nic);
}
static void e100_hw_reset(struct nic *nic)
{
/* Put CU and RU into idle with a selective reset to get
* device off of PCI bus */
writel(selective_reset, &nic->csr->port);
e100_write_flush(nic); udelay(20);
/* Now fully reset device */
writel(software_reset, &nic->csr->port);
e100_write_flush(nic); udelay(20);
/* Mask off our interrupt line - it's unmasked after reset */
//
关中断
e100_disable_irq(nic);
}
//硬件初始化
static int e100_hw_init(struct nic *nic)
{
int err;
e100_hw_reset(nic);
DPRINTK(HW, ERR, "e100_hw_init/n");
if(!in_interrupt() && (err = e100_self_test(nic)))
return err;
if((err = e100_phy_init(nic)))
return err;
if((err = e100_exec_cmd(nic, cuc_load_base, 0)))
return err;
if((err = e100_exec_cmd(nic, ruc_load_base, 0)))
return err;
if((err = e100_exec_cb(nic, NULL, e100_load_ucode)))
return err;
if((err = e100_exec_cb(nic, NULL, e100_configure)))
return err;
if((err = e100_exec_cb(nic, NULL, e100_setup_iaaddr)))
return err;
if((err = e100_exec_cmd(nic, cuc_dump_addr,
nic->dma_addr + offsetof(struct mem, stats))))
return err;
if((err = e100_exec_cmd(nic, cuc_dump_reset, 0)))
return err;
e100_disable_irq(nic);
return 0;
}
//多播
static void e100_multi(struct nic *nic, struct cb *cb, struct sk_buff *skb)
{
struct net_device *netdev = nic->netdev;
struct dev_mc_list *list = netdev->mc_list;
u16 i, count = min(netdev->mc_count, E100_MAX_MULTICAST_ADDRS);
cb->command = cpu_to_le16(cb_multi);
cb->u.multi.count = cpu_to_le16(count * ETH_ALEN);
for(i = 0; list && i < count; i++, list = list->next)
memcpy(&cb->u.multi.addr[i*ETH_ALEN], &list->dmi_addr,
ETH_ALEN);
}
static void e100_set_multicast_list(struct net_device *netdev)
{
struct nic *nic = netdev_priv(netdev);
DPRINTK(HW, DEBUG, "mc_count=%d, flags=0x%04X/n",
netdev->mc_count, netdev->flags);
if(netdev->flags & IFF_PROMISC)
nic->flags |= promiscuous;
else
nic->flags &= ~promiscuous;
if(netdev->flags & IFF_ALLMULTI ||
netdev->mc_count > E100_MAX_MULTICAST_ADDRS)
nic->flags |= multicast_all;
else
nic->flags &= ~multicast_all;
e100_exec_cb(nic, NULL, e100_configure);
e100_exec_cb(nic, NULL, e100_multi);
}
static void e100_update_stats(struct nic *nic)
{
struct net_device_stats *ns = &nic->net_stats;
struct stats *s = &nic->mem->stats;
u32 *complete = (nic->mac < mac_82558_D101_A4) ? &s->fc_xmt_pause :
(nic->mac < mac_82559_D101M) ? (u32 *)&s->xmt_tco_frames :
&s->complete;
/* Device's stats reporting may take several microseconds to
* complete, so where always waiting for results of the
* previous command. */
if(*complete == le32_to_cpu(cuc_dump_reset_complete)) {
*complete = 0;
nic->tx_frames = le32_to_cpu(s->tx_good_frames);
nic->tx_collisions = le32_to_cpu(s->tx_total_collisions);
ns->tx_aborted_errors += le32_to_cpu(s->tx_max_collisions);
ns->tx_window_errors += le32_to_cpu(s->tx_late_collisions);
ns->tx_carrier_errors += le32_to_cpu(s->tx_lost_crs);
ns->tx_fifo_errors += le32_to_cpu(s->tx_underruns);
ns->collisions += nic->tx_collisions;
ns->tx_errors += le32_to_cpu(s->tx_max_collisions) +
le32_to_cpu(s->tx_lost_crs);
ns->rx_length_errors += le32_to_cpu(s->rx_short_frame_errors) +
nic->rx_over_length_errors;
ns->rx_crc_errors += le32_to_cpu(s->rx_crc_errors);
ns->rx_frame_errors += le32_to_cpu(s->rx_alignment_errors);
ns->rx_over_errors += le32_to_cpu(s->rx_overrun_errors);
ns->rx_fifo_errors += le32_to_cpu(s->rx_overrun_errors);
ns->rx_missed_errors += le32_to_cpu(s->rx_resource_errors);
ns->rx_errors += le32_to_cpu(s->rx_crc_errors) +
le32_to_cpu(s->rx_alignment_errors) +
le32_to_cpu(s->rx_short_frame_errors) +
le32_to_cpu(s->rx_cdt_errors);
nic->tx_deferred += le32_to_cpu(s->tx_deferred);
nic->tx_single_collisions +=
le32_to_cpu(s->tx_single_collisions);
nic->tx_multiple_collisions +=
le32_to_cpu(s->tx_multiple_collisions);
if(nic->mac >= mac_82558_D101_A4) {
nic->tx_fc_pause += le32_to_cpu(s->fc_xmt_pause);
nic->rx_fc_pause += le32_to_cpu(s->fc_rcv_pause);
nic->rx_fc_unsupported +=
le32_to_cpu(s->fc_rcv_unsupported);
if(nic->mac >= mac_82559_D101M) {
nic->tx_tco_frames +=
le16_to_cpu(s->xmt_tco_frames);
nic->rx_tco_frames +=
le16_to_cpu(s->rcv_tco_frames);
}
}
}
if(e100_exec_cmd(nic, cuc_dump_reset, 0))
DPRINTK(TX_ERR, DEBUG, "exec cuc_dump_reset failed/n");
}
//
网卡信息监测
static void e100_watchdog(unsigned long data)
{
struct nic *nic = (struct nic *)data;
struct ethtool_cmd cmd;
DPRINTK(TIMER, DEBUG, "right now = %ld/n", jiffies);
/* mii library handles link maintenance tasks */
mii_ethtool_gset(&nic->mii, &cmd);
if(mii_link_ok(&nic->mii) && !netif_carrier_ok(nic->netdev)) {
DPRINTK(LINK, INFO, "link up, %sMbps, %s-duplex/n",
cmd.speed == SPEED_100 ? "100" : "10",
cmd.duplex == DUPLEX_FULL ? "full" : "half");
} else if(!mii_link_ok(&nic->mii) && netif_carrier_ok(nic->netdev)) {
DPRINTK(LINK, INFO, "link down/n");
}
mii_check_link(&nic->mii);
/* Software generated interrupt to recover from (rare) Rx
* allocation failure.
* Unfortunately have to use a spinlock to not re-enable interrupts
* accidentally, due to hardware that shares a register between the
* interrupt mask bit and the SW Interrupt generation bit */
spin_lock_irq(&nic->cmd_lock);
writeb(readb(&nic->csr->scb.cmd_hi) | irq_sw_gen,&nic->csr->scb.cmd_hi);
spin_unlock_irq(&nic->cmd_lock);
e100_write_flush(nic);
e100_update_stats(nic);
e100_adjust_adaptive_ifs(nic, cmd.speed, cmd.duplex);
if(nic->mac <= mac_82557_D100_C)
/* Issue a multicast command to workaround a 557 lock up */
e100_set_multicast_list(nic->netdev);
if(nic->flags & ich && cmd.speed==SPEED_10 && cmd.duplex==DUPLEX_HALF)
/* Need SW workaround for ICH[x] 10Mbps/half duplex Tx hang. */
nic->flags |= ich_10h_workaround;
else
nic->flags &= ~ich_10h_workaround;
mod_timer(&nic->watchdog, jiffies + E100_WATCHDOG_PERIOD);
}
static inline
void e100_xmit_prepare(struct nic *nic, struct cb *cb,
struct sk_buff *skb)
{
cb->command = nic->tx_command;
/* interrupt every 16 packets regardless of delay */
if((nic->cbs_avail & ~15) == nic->cbs_avail)
cb->command |= cpu_to_le16(cb_i);
cb->u.tcb.tbd_array = cb->dma_addr + offsetof(struct cb, u.tcb.tbd);
cb->u.tcb.tcb_byte_count = 0;
cb->u.tcb.threshold = nic->tx_threshold;
cb->u.tcb.tbd_count = 1;
cb->u.tcb.tbd.buf_addr = cpu_to_le32(pci_map_single(nic->pdev,
skb->data, skb->len, PCI_DMA_TODEVICE));
/* check for mapping failure? */
cb->u.tcb.tbd.size = cpu_to_le16(skb->len);
}
static int
e100_xmit_frame(struct sk_buff *skb, struct net_device *netdev)
{
struct nic *nic = netdev_priv(netdev);
int err;
if(nic->flags & ich_10h_workaround) {
/* SW workaround for ICH[x] 10Mbps/half duplex Tx hang.
Issue a NOP command followed by a 1us delay before
issuing the Tx command. */
if(e100_exec_cmd(nic, cuc_nop, 0))
DPRINTK(TX_ERR, DEBUG, "exec cuc_nop failed/n");
udelay(1);
}
err = e100_exec_cb(nic, skb, e100_xmit_prepare);
switch(err) {
case -ENOSPC:
/* We queued the skb, but now we're out of space. */
DPRINTK(TX_ERR, DEBUG, "No space for CB/n");
netif_stop_queue(netdev);
break;
case -ENOMEM:
/* This is a hard error - log it. */
DPRINTK(TX_ERR, DEBUG, "Out of Tx resources, returning skb/n");
netif_stop_queue(netdev);
return 1;
}
netdev->trans_start = jiffies;
return 0;
}
//
发包过程。
//
对发包对列进行清理
static inline int
e100_tx_clean(struct nic *nic)
{
struct cb *cb;
int tx_cleaned = 0;
spin_lock(&nic->cb_lock);
DPRINTK(TX_DONE, DEBUG, "cb->status = 0x%04X/n",
nic->cb_to_clean->status);
/* Clean CBs marked complete */
for(cb = nic->cb_to_clean;
cb->status & cpu_to_le16(cb_complete);//
转成无符号３２位小头数值
cb = nic->cb_to_clean = cb->next) {
if(likely(cb->skb != NULL)) {
nic->net_stats.tx_packets++;
nic->net_stats.tx_bytes += cb->skb->len;
pci_unmap_single(nic->pdev,
le32_to_cpu(cb->u.tcb.tbd.buf_addr),
le16_to_cpu(cb->u.tcb.tbd.size),
PCI_DMA_TODEVICE);//
解除
DMA
映射
dev_kfree_skb_any(cb->skb);//
释放
skb
cb->skb = NULL;
tx_cleaned = 1;
}
cb->status = 0;
nic->cbs_avail++;
}
spin_unlock(&nic->cb_lock);
/* Recover from running out of Tx resources in xmit_frame */
if(unlikely(tx_cleaned && netif_queue_stopped(nic->netdev)))
netif_wake_queue(nic->netdev);
return tx_cleaned;
}
//
控制队列操作
static void e100_clean_cbs(struct nic *nic)
{
if(nic->cbs) {
while(nic->cbs_avail != nic->params.cbs.count) {
struct cb *cb = nic->cb_to_clean;
if(cb->skb) {
pci_unmap_single(nic->pdev,
le32_to_cpu(cb->u.tcb.tbd.buf_addr),
le16_to_cpu(cb->u.tcb.tbd.size),
PCI_DMA_TODEVICE);
dev_kfree_skb(cb->skb);
}
nic->cb_to_clean = nic->cb_to_clean->next;
nic->cbs_avail++;
}
pci_free_consistent(nic->pdev,
sizeof(struct cb) * nic->params.cbs.count,
nic->cbs, nic->cbs_dma_addr);
nic->cbs = NULL;
nic->cbs_avail = 0;
}
nic->cuc_cmd = cuc_start;
nic->cb_to_use = nic->cb_to_send = nic->cb_to_clean =
nic->cbs;
}
static int e100_alloc_cbs(struct nic *nic)
{
struct cb *cb;
unsigned int i, count = nic->params.cbs.count;
nic->cuc_cmd = cuc_start;
nic->cb_to_use = nic->cb_to_send = nic->cb_to_clean = NULL;
nic->cbs_avail = 0;
nic->cbs = pci_alloc_consistent(nic->pdev,
sizeof(struct cb) * count, &nic->cbs_dma_addr);
if(!nic->cbs)
return -ENOMEM;
for(cb = nic->cbs, i = 0; i < count; cb++, i++) {
cb->next = (i + 1 < count) ? cb + 1 : nic->cbs;
cb->prev = (i == 0) ? nic->cbs + count - 1 : cb - 1;
cb->dma_addr = nic->cbs_dma_addr + i * sizeof(struct cb);
cb->link = cpu_to_le32(nic->cbs_dma_addr +
((i+1) % count) * sizeof(struct cb));
cb->skb = NULL;
}
nic->cb_to_use = nic->cb_to_send = nic->cb_to_clean = nic->cbs;
nic->cbs_avail = count;
return 0;
}
//
启动接收过程
static inline void e100_start_receiver(struct nic *nic, struct rx *rx)
{
if(!nic->rxs) return;
if(RU_SUSPENDED != nic->ru_running) return;
/* handle init time starts */
if(!rx) rx = nic->rxs;
/* (Re)start RU if suspended or idle and RFA is non-NULL */
if(rx->skb) {
e100_exec_cmd(nic, ruc_start, rx->dma_addr);
nic->ru_running = RU_RUNNING;
}
}
/*
给收包过程分配skb，这个是非常重要的过程，主要完成skb 的分配工作，如果rx 队列没有
skb，则new 一个，否则把状态同步一下，然后直接使用旧的skb，用于提高效率。分配好的
skb要作pci_map动作，就是把内存挂在网卡的DMA通道，等有中断发生，内存就是网络数据
包了，效验的动作在后面会作*/
#define RFD_BUF_LEN (sizeof(struct rfd) + VLAN_ETH_FRAME_LEN)
static inline int e100_rx_alloc_skb(struct nic *nic, struct rx *rx)
{
if(!(rx->skb = dev_alloc_skb(RFD_BUF_LEN + NET_IP_ALIGN)))
return -ENOMEM;
/* Align, init, and map the RFD. */
rx->skb->dev = nic->netdev;
skb_reserve(rx->skb, NET_IP_ALIGN);//ＩＰ对齐
memcpy(rx->skb->data, &nic->blank_rfd, sizeof(struct rfd));
// 映射到DMA通道
rx->dma_addr = pci_map_single(nic->pdev, rx->skb->data,
RFD_BUF_LEN, PCI_DMA_BIDIRECTIONAL);
if(pci_dma_mapping_error(rx->dma_addr)) {
dev_kfree_skb_any(rx->skb);
rx->skb = 0;
rx->dma_addr = 0;
return -ENOMEM;
}
/* Link the RFD to end of RFA by linking previous RFD to
* this one, and clearing EL bit of previous. */
if(rx->prev->skb) {
struct rfd *prev_rfd = (struct rfd *)rx->prev->skb->data;
put_unaligned(cpu_to_le32(rx->dma_addr),
(u32 *)&prev_rfd->link);
wmb();
prev_rfd->command &= ~cpu_to_le16(cb_el);
pci_dma_sync_single_for_device(nic->pdev, rx->prev->dma_addr,
sizeof(struct rfd), PCI_DMA_TODEVICE);
}
return 0;
}
以下为主要的收包过程。
static inline int e100_rx_indicate(struct nic *nic, struct rx *rx,
unsigned int *work_done, unsigned int work_to_do)
{
struct sk_buff *skb = rx->skb;
struct rfd *rfd = (struct rfd *)skb->data;
u16 rfd_status, actual_size;
if(unlikely(work_done && *work_done >= work_to_do))
return -EAGAIN;
/* Need to sync before taking a peek at cb_complete bit */
pci_dma_sync_single_for_cpu(nic->pdev, rx->dma_addr,
sizeof(struct rfd), PCI_DMA_FROMDEVICE);
rfd_status = le16_to_cpu(rfd->status);
DPRINTK(RX_STATUS, DEBUG, "status=0x%04X/n", rfd_status);
/* If data isn't ready, nothing to indicate */
if(unlikely(!(rfd_status & cb_complete)))
return -ENODATA;
/* Get actual data size */
actual_size = le16_to_cpu(rfd->actual_size) & 0x3FFF;
if(unlikely(actual_size > RFD_BUF_LEN - sizeof(struct rfd)))
actual_size = RFD_BUF_LEN - sizeof(struct rfd);
/* Get data */
pci_unmap_single(nic->pdev, rx->dma_addr,
RFD_BUF_LEN, PCI_DMA_FROMDEVICE);
/* this allows for a fast restart without re-enabling interrupts */
if(le16_to_cpu(rfd->command) & cb_el)
nic->ru_running = RU_SUSPENDED;
/* Pull off the RFD and put the actual data (minus eth hdr) */
skb_reserve(skb, sizeof(struct rfd));
skb_put(skb, actual_size);
skb->protocol = eth_type_trans(skb, nic->netdev);
if(unlikely(!(rfd_status & cb_ok))) {
/* Don't indicate if hardware indicates errors */
dev_kfree_skb_any(skb);
} else if(actual_size > ETH_DATA_LEN + VLAN_ETH_HLEN) {
/* Don't indicate oversized frames */
nic->rx_over_length_errors++;
dev_kfree_skb_any(skb);
} else {
nic->net_stats.rx_packets++;
nic->net_stats.rx_bytes += actual_size;
nic->netdev->last_rx = jiffies;
netif_receive_skb(skb);
if(work_done)
(*work_done)++;
}
rx->skb = NULL;
return 0;
}
收包清除
static inline void e100_rx_clean(struct nic *nic, unsigned int *work_done,
unsigned int work_to_do)
{
struct rx *rx;
int restart_required = 0;
struct rx *rx_to_start = NULL;
/* are we already rnr? then pay attention!!! this ensures that
* the state machine progression never allows a start with a
* partially cleaned list, avoiding a race between hardware
* and rx_to_clean when in NAPI mode */
if(RU_SUSPENDED == nic->ru_running)
restart_required = 1;
/* Indicate newly arrived packets */
for(rx = nic->rx_to_clean; rx->skb; rx = nic->rx_to_clean = rx->next) {
int err = e100_rx_indicate(nic, rx, work_done, work_to_do);
if(-EAGAIN == err) {
/* hit quota so have more work to do, restart once
* cleanup is complete */
restart_required = 0;
break;
} else if(-ENODATA == err)
break; /* No more to clean */
}
/* save our starting point as the place we'll restart the receiver */
if(restart_required)
rx_to_start = nic->rx_to_clean;
/* Alloc new skbs to refill list */
for(rx = nic->rx_to_use; !rx->skb; rx = nic->rx_to_use = rx->next) {
if(unlikely(e100_rx_alloc_skb(nic, rx)))
break; /* Better luck next time (see watchdog) */
}
if(restart_required) {
// ack the rnr?
writeb(stat_ack_rnr, &nic->csr->scb.stat_ack);
e100_start_receiver(nic, rx_to_start);
if(work_done)
(*work_done)++;
}
}
static void e100_rx_clean_list(struct nic *nic)
{
struct rx *rx;
unsigned int i, count = nic->params.rfds.count;
nic->ru_running = RU_UNINITIALIZED;
if(nic->rxs) {
for(rx = nic->rxs, i = 0; i < count; rx++, i++) {
if(rx->skb) {
pci_unmap_single(nic->pdev, rx->dma_addr,
RFD_BUF_LEN, PCI_DMA_FROMDEVICE);
dev_kfree_skb(rx->skb);
}
}
kfree(nic->rxs);
nic->rxs = NULL;
}
nic->rx_to_use = nic->rx_to_clean = NULL;
}
static int e100_rx_alloc_list(struct nic *nic)
{
struct rx *rx;
unsigned int i, count = nic->params.rfds.count;
nic->rx_to_use = nic->rx_to_clean = NULL;
nic->ru_running = RU_UNINITIALIZED;
if(!(nic->rxs = kmalloc(sizeof(struct rx) * count, GFP_ATOMIC)))
return -ENOMEM;
memset(nic->rxs, 0, sizeof(struct rx) * count);
for(rx = nic->rxs, i = 0; i < count; rx++, i++) {
rx->next = (i + 1 < count) ? rx + 1 : nic->rxs;
rx->prev = (i == 0) ? nic->rxs + count - 1 : rx - 1;
if(e100_rx_alloc_skb(nic, rx)) {
e100_rx_clean_list(nic);
return -ENOMEM;
}
}
nic->rx_to_use = nic->rx_to_clean = nic->rxs;
nic->ru_running = RU_SUSPENDED;
return 0;
}
static int e100_poll(struct net_device *netdev, int *budget)
{
struct nic *nic = netdev_priv(netdev);
unsigned int work_to_do = min(netdev->quota, *budget);
unsigned int work_done = 0;
int tx_cleaned;
e100_rx_clean(nic, &work_done, work_to_do);
tx_cleaned = e100_tx_clean(nic);
/* If no Rx and Tx cleanup work was done, exit polling mode. */
if((!tx_cleaned && (work_done == 0)) || !netif_running(netdev)) {
netif_rx_complete(netdev);
e100_enable_irq(nic);
return 0;
}
*budget -= work_done;
netdev->quota -= work_done;
return 1;
}
#ifdef CONFIG_NET_POLL_CONTROLLER
static void e100_netpoll(struct net_device *netdev)
{
struct nic *nic = netdev_priv(netdev);
e100_disable_irq(nic);
e100_intr(nic->pdev->irq, netdev, NULL);
e100_tx_clean(nic);
e100_enable_irq(nic);
}
#endif
static struct net_device_stats *e100_get_stats(struct net_device *netdev)
{
struct nic *nic = netdev_priv(netdev);
return &nic->net_stats;
}
static int e100_set_mac_address(struct net_device *netdev, void *p)
{
struct nic *nic = netdev_priv(netdev);
struct sockaddr *addr = p;
if (!is_valid_ether_addr(addr->sa_data))
return -EADDRNOTAVAIL;
memcpy(netdev->dev_addr, addr->sa_data, netdev->addr_len);
e100_exec_cb(nic, NULL, e100_setup_iaaddr);
return 0;
}
static int e100_change_mtu(struct net_device *netdev, int new_mtu)
{
if(new_mtu < ETH_ZLEN || new_mtu > ETH_DATA_LEN)
return -EINVAL;
netdev->mtu = new_mtu;
return 0;
}
#ifdef CONFIG_PM
static int e100_asf(struct nic *nic)；
#endif
static int e100_up(struct nic *nic)
{
int err;
if((err = e100_rx_alloc_list(nic)))
return err;
if((err = e100_alloc_cbs(nic)))
goto err_rx_clean_list;
if((err = e100_hw_init(nic)))
goto err_clean_cbs;
e100_set_multicast_list(nic->netdev);
e100_start_receiver(nic, 0);
mod_timer(&nic->watchdog, jiffies);
if((err = request_irq(nic->pdev->irq, e100_intr, SA_SHIRQ,
nic->netdev->name, nic->netdev)))
goto err_no_irq;
netif_wake_queue(nic->netdev);
netif_poll_enable(nic->netdev);
/* enable ints _after_ enabling poll, preventing a race between
* disable ints+schedule */
e100_enable_irq(nic);
return 0;
err_no_irq:
del_timer_sync(&nic->watchdog);
err_clean_cbs:
e100_clean_cbs(nic);
err_rx_clean_list:
e100_rx_clean_list(nic);
return err;
}
static void e100_down(struct nic *nic)
{
/* wait here for poll to complete */
netif_poll_disable(nic->netdev);
netif_stop_queue(nic->netdev);
e100_hw_reset(nic);
free_irq(nic->pdev->irq, nic->netdev);
del_timer_sync(&nic->watchdog);
netif_carrier_off(nic->netdev);
e100_clean_cbs(nic);
e100_rx_clean_list(nic);
}
static void e100_tx_timeout(struct net_device *netdev)
{
struct nic *nic = netdev_priv(netdev);
/* Reset outside of interrupt context, to avoid request_irq
* in interrupt context */
schedule_work(&nic->tx_timeout_task);
}
#define MII_LED_CONTROL
0x1B
static void e100_blink_led(unsigned long data)
{
struct nic *nic = (struct nic *)data;
enum led_state {
led_on = 0x01,
led_off = 0x04,
led_on_559 = 0x05,
led_on_557 = 0x07,
};
nic->leds = (nic->leds & led_on) ? led_off :
(nic->mac < mac_82559_D101M) ? led_on_557 : led_on_559;
mdio_write(nic->netdev, nic->mii.phy_id, MII_LED_CONTROL, nic->leds);
mod_timer(&nic->blink_timer, jiffies + HZ / 4);
}
static int e100_get_settings(struct net_device *netdev, struct ethtool_cmd *cmd)
{
struct nic *nic = netdev_priv(netdev);
return mii_ethtool_gset(&nic->mii, cmd);
}
static int e100_set_settings(struct net_device *netdev, struct ethtool_cmd *cmd)
{
struct nic *nic = netdev_priv(netdev);
int err;
mdio_write(netdev, nic->mii.phy_id, MII_BMCR, BMCR_RESET);
err = mii_ethtool_sset(&nic->mii, cmd);
e100_exec_cb(nic, NULL, e100_configure);
return err;
}
。。。。。
// 对应标准网卡驱动程序的一些封装函数
static int e100_do_ioctl(struct net_device *netdev, struct ifreq *ifr, int cmd)
{
struct nic *nic = netdev_priv(netdev);
return generic_mii_ioctl(&nic->mii, if_mii(ifr), cmd, NULL);
}
static int e100_alloc(struct nic *nic)
{
nic->mem = pci_alloc_consistent(nic->pdev, sizeof(struct mem),
&nic->dma_addr);
return nic->mem ? 0 : -ENOMEM;
}
static void e100_free(struct nic *nic)
{
if(nic->mem) {
pci_free_consistent(nic->pdev, sizeof(struct mem),
nic->mem, nic->dma_addr);
nic->mem = NULL;
}
}
static int e100_open(struct net_device *netdev)
{
struct nic *nic = netdev_priv(netdev);
int err = 0;
netif_carrier_off(netdev);
if((err = e100_up(nic)))
DPRINTK(IFUP, ERR, "Cannot open interface, aborting./n");
return err;
}
static int e100_close(struct net_device *netdev)
{
e100_down(netdev_priv(netdev));
return 0;
}