人生的每个阶段都有些许的烦恼、厌倦与困惑，如何自我调整与拯救？
＝＝＝＝＝＝＝＝＝＝＝＝＝＝＝＝＝＝＝＝＝＝＝＝＝＝＝＝＝＝＝＝＝＝＝＝＝＝＝＝＝＝＝＝
网卡驱动接收数据相关代码：
(1) 假定网卡使用MSI中断。在MSI中断的处理函数中有如下代码：触发软中断
#ifdef CONFIG_E1000_NAPI
if (unlikely(hw->mac_type < e1000_82571)) {
/* disable interrupts, without the synchronize_irq bit */
atomic_inc(&adapter->irq_sem);
E1000_WRITE_REG(hw, IMC, ~0);
E1000_WRITE_FLUSH(hw);
}
if (likely(netif_rx_schedule_prep(netdev))) {
adapter->total_tx_bytes = 0;
adapter->total_tx_packets = 0;
adapter->total_rx_bytes = 0;
adapter->total_rx_packets = 0;
__netif_rx_schedule(netdev);
} else
/* this really should not happen! if it does it is basically a
* bug, but not a hard error, so enable ints and continue */
e1000_irq_enable(adapter);
(2)网卡接收软中断的具体实现：Dev.c (/linux-2.6.21/net/core)。轮询poll_list里面的每个网卡设备，并调用网卡设备的poll函数，对该网卡的数据进行处理。
static void net_rx_action(struct softirq_action *h)
{
struct softnet_data *queue = &__get_cpu_var(softnet_data);
unsigned long start_time = jiffies;
int budget = netdev_budget;
void *have;
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);
have = netpoll_poll_lock(dev);
if (dev->quota <= 0 || dev->poll(dev, &budget)) {
netpoll_poll_unlock(have);
local_irq_disable();
list_move_tail(&dev->poll_list, &queue->poll_list);
if (dev->quota < 0)
dev->quota += dev->weight;
else
dev->quota = dev->weight;
} else {
netpoll_poll_unlock(have);
dev_put(dev);
local_irq_disable();
}
}
out:
#ifdef CONFIG_NET_DMA
/*
* There may not be any more sk_buffs coming right now, so push
* any pending DMA copies to hardware
*/
if (net_dma_client) {
struct dma_chan *chan;
rcu_read_lock();
list_for_each_entry_rcu(chan, &net_dma_client->channels, client_node)
dma_async_memcpy_issue_pending(chan);
rcu_read_unlock();
}
#endif
local_irq_enable();
return;
softnet_break:
__get_cpu_var(netdev_rx_stat).time_squeeze++;
__raise_softirq_irqoff(NET_RX_SOFTIRQ);
goto out;
}
(3)poll的初始化，在网卡初始化的时候挂接该网卡的poll函数。
static int __devinit
e1000_sw_init(struct e1000_adapter *adapter)
{
struct e1000_hw *hw = &adapter->hw;
struct net_device *netdev = adapter->netdev;
struct pci_dev *pdev = adapter->pdev;
#ifdef CONFIG_E1000_NAPI
int i;
#endif
.............................
.............................
#ifdef CONFIG_E1000_NAPI
for (i = 0; i < adapter->num_rx_queues; i++) {
adapter->polling_netdev[i].priv = adapter;
adapter->polling_netdev[i].poll = &e1000_clean;
adapter->polling_netdev[i].weight = 64;
dev_hold(&adapter->polling_netdev[i]);
set_bit(__LINK_STATE_START, &adapter->polling_netdev[i].state);
}
spin_lock_init(&adapter->tx_queue_lock);
#endif
.............................
..............................
return 0;
}
(4) poll implement:调用接口处理该网卡环行队列中的数据帧，每次最多处理poll_dev->quota个数据帧。
/**
* e1000_clean - NAPI Rx polling callback
* @adapter: board private structure
**/
static int
e1000_clean(struct net_device *poll_dev, int *budget)
{
struct e1000_adapter *adapter;
int work_to_do = min(*budget, poll_dev->quota);
int tx_cleaned = 0, work_done = 0;
/* Must NOT use netdev_priv macro here. */
adapter = poll_dev->priv;
/* Keep link state information with original netdev */
if (!netif_carrier_ok(poll_dev))
goto quit_polling;
/* e1000_clean is called per-cpu. This lock protects
* tx_ring[0] from being cleaned by multiple cpus
* simultaneously. A failure obtaining the lock means
* tx_ring[0] is currently being cleaned anyway. */
if (spin_trylock(&adapter->tx_queue_lock)) {
tx_cleaned = e1000_clean_tx_irq(adapter,
&adapter->tx_ring[0]);
spin_unlock(&adapter->tx_queue_lock);
}
adapter->clean_rx(adapter, &adapter->rx_ring[0],
&work_done, work_to_do);
*budget -= work_done;
poll_dev->quota -= work_done;
/* If no Tx and not enough Rx work done, exit the polling mode */
if ((!tx_cleaned && (work_done == 0)) ||
!netif_running(poll_dev)) {
quit_polling:
if (likely(adapter->itr_setting & 3))
e1000_set_itr(adapter);
netif_rx_complete(poll_dev);
e1000_irq_enable(adapter);
return 0;
}
return 1;
}
(5) 对数据帧进行处理接口的初始化：e1000_open->e1000_up->e1000_configure_rx(struct e1000_adapter *adapter)
if (adapter->rx_ps_pages) {
/* this is a 32 byte descriptor */
rdlen = adapter->rx_ring[0].count *
sizeof(union e1000_rx_desc_packet_split);
adapter->clean_rx = e1000_clean_rx_irq_ps;
adapter->alloc_rx_buf = e1000_alloc_rx_buffers_ps;
} else {
rdlen = adapter->rx_ring[0].count *
sizeof(struct e1000_rx_desc);
adapter->clean_rx = e1000_clean_rx_irq;
adapter->alloc_rx_buf = e1000_alloc_rx_buffers;
}(6)对数据帧处理的具体函数实现，将处理后的数据包发送到L3：
/**
* e1000_clean_rx_irq - Send received data up the network stack; legacy
* @adapter: board private structure
**/
static boolean_t
#ifdef CONFIG_E1000_NAPI
e1000_clean_rx_irq(struct e1000_adapter *adapter,
struct e1000_rx_ring *rx_ring,
int *work_done, int work_to_do)
#else
e1000_clean_rx_irq(struct e1000_adapter *adapter,
struct e1000_rx_ring *rx_ring)
#endif
{
struct net_device *netdev = adapter->netdev;
struct pci_dev *pdev = adapter->pdev;
struct e1000_rx_desc *rx_desc, *next_rxd;
struct e1000_buffer *buffer_info, *next_buffer;
unsigned long flags;
uint32_t length;
uint8_t last_byte;
unsigned int i;
int cleaned_count = 0;
boolean_t cleaned = FALSE;
unsigned int total_rx_bytes=0, total_rx_packets=0;
i = rx_ring->next_to_clean;
rx_desc = E1000_RX_DESC(*rx_ring, i);
buffer_info = &rx_ring->buffer_info[i];
while (rx_desc->status & E1000_RXD_STAT_DD) {
struct sk_buff *skb;
u8 status;
#ifdef CONFIG_E1000_NAPI
if (*work_done >= work_to_do)
break;
(*work_done)++;
#endif
status = rx_desc->status;
skb = buffer_info->skb;
buffer_info->skb = NULL;
prefetch(skb->data - NET_IP_ALIGN);
if (++i == rx_ring->count) i = 0;
next_rxd = E1000_RX_DESC(*rx_ring, i);
prefetch(next_rxd);
next_buffer = &rx_ring->buffer_info[i];
cleaned = TRUE;
cleaned_count++;
pci_unmap_single(pdev,
buffer_info->dma,
buffer_info->length,
PCI_DMA_FROMDEVICE);
length = le16_to_cpu(rx_desc->length);
if (unlikely(!(status & E1000_RXD_STAT_EOP))) {
/* All receives must fit into a single buffer */
E1000_DBG("%s: Receive packet consumed multiple"
" buffers/n", netdev->name);
/* recycle */
buffer_info->skb = skb;
goto next_desc;
}
if (unlikely(rx_desc->errors & E1000_RXD_ERR_FRAME_ERR_MASK)) {
last_byte = *(skb->data + length - 1);
if (TBI_ACCEPT(&adapter->hw, status,
rx_desc->errors, length, last_byte)) {
spin_lock_irqsave(&adapter->stats_lock, flags);
e1000_tbi_adjust_stats(&adapter->hw,
&adapter->stats,
length, skb->data);
spin_unlock_irqrestore(&adapter->stats_lock,
flags);
length--;
} else {
/* recycle */
buffer_info->skb = skb;
goto next_desc;
}
}
/* adjust length to remove Ethernet CRC, this must be
* done after the TBI_ACCEPT workaround above */
length -= 4;
/* probably a little skewed due to removing CRC */
total_rx_bytes += length;
total_rx_packets++;
/* code added for copybreak, this should improve
* performance for small packets with large amounts
* of reassembly being done in the stack */
if (length < copybreak) {
struct sk_buff *new_skb =
netdev_alloc_skb(netdev, length + NET_IP_ALIGN);
if (new_skb) {
skb_reserve(new_skb, NET_IP_ALIGN);
memcpy(new_skb->data - NET_IP_ALIGN,
skb->data - NET_IP_ALIGN,
length + NET_IP_ALIGN);
/* save the skb in buffer_info as good */
buffer_info->skb = skb;
skb = new_skb;
}
/* else just continue with the old one */
}
/* end copybreak code */
skb_put(skb, length);
/* Receive Checksum Offload */
e1000_rx_checksum(adapter,
(uint32_t)(status) |
((uint32_t)(rx_desc->errors) << 24),
le16_to_cpu(rx_desc->csum), skb);
skb->protocol = eth_type_trans(skb, netdev);
#ifdef CONFIG_E1000_NAPI
if (unlikely(adapter->vlgrp &&
(status & E1000_RXD_STAT_VP))) {
vlan_hwaccel_receive_skb(skb, adapter->vlgrp,
le16_to_cpu(rx_desc->special) &
E1000_RXD_SPC_VLAN_MASK);
} else {
netif_receive_skb(skb);
}
#else /* CONFIG_E1000_NAPI */
if (unlikely(adapter->vlgrp &&
(status & E1000_RXD_STAT_VP))) {
vlan_hwaccel_rx(skb, adapter->vlgrp,
le16_to_cpu(rx_desc->special) &
E1000_RXD_SPC_VLAN_MASK);
} else {
netif_rx(skb);
}
#endif /* CONFIG_E1000_NAPI */
netdev->last_rx = jiffies;
next_desc:
rx_desc->status = 0;
/* return some buffers to hardware, one at a time is too slow */
if (unlikely(cleaned_count >= E1000_RX_BUFFER_WRITE)) {
adapter->alloc_rx_buf(adapter, rx_ring, cleaned_count);
cleaned_count = 0;
}
/* use prefetched values */
rx_desc = next_rxd;
buffer_info = next_buffer;
}
rx_ring->next_to_clean = i;
cleaned_count = E1000_DESC_UNUSED(rx_ring);
if (cleaned_count)
adapter->alloc_rx_buf(adapter, rx_ring, cleaned_count);
adapter->total_rx_packets += total_rx_packets;
adapter->total_rx_bytes += total_rx_bytes;
return cleaned;
}
