本文的copyleft归gfree.wind@gmail.com所有,使用GPL发布,可以自由拷贝,转载。但转载请保持文档的完整性,注明原作者及原链接,严禁用于任何商业用途。
作者:gfree.wind@gmail.com
博客:linuxfocus.blog.chinaunix.net
在前面的博文中,我学习了数据包从L2到L5的流程,但是当时因为时间和水平的限制,整个儿流程并没有涉及太多的细节。前两天大致又过了这个流程,发现有不少细节还是需要注意的。所以决定,将之前略过的一些内容,详细的学习一遍。
今天主要是学习L2数据链路层的数据包的处理机制。在Linux kernel中,由网卡驱动完成L1物理层和L2数据链路层的工作。
首先看函数net_dev_init
- static int __init net_dev_init(void)
-
{
-
int i, rc = -ENOMEM;
-
-
BUG_ON(!dev_boot_phase);
/*
创建对应的/proc文件,如/proc/net/dev, /proc/net/softnet_stat等
*/
-
if (dev_proc_init())
-
goto out;
/* 初始化netdev对应的kobject*/
-
if (netdev_kobject_init())
-
goto out;
/*
初始化数据链路层的handle上层数据类型表。
回忆前文《TCP/IP学习(28)——数据包完整接受流程》中,在inet_init中注册了IP包类型到这个表中。
*/
-
INIT_LIST_HEAD(&ptype_all);
-
for (i = 0; i < PTYPE_HASH_SIZE; i++)
-
INIT_LIST_HEAD(&ptype_base[i]);
/*
注册neddev_net_ops subsystem
*/
-
if (register_pernet_subsys(&netdev_net_ops))
-
goto out;
-
-
/*
-
* Initialise the packet receive queues.
-
*/
- /*
- 为每个CPU初始化PERCPU的全局变量softnet_data,作为该CPU的接收缓存
- */
-
for_each_possible_cpu(i) {
-
struct softnet_data *sd = &per_cpu(softnet_data, i);
-
- ...... ......
-
}
-
-
dev_boot_phase = 0;
-
-
/* The loopback device is special if any other network devices
-
* is present in a network namespace the loopback device must
-
* be present. Since we now dynamically allocate and free the
-
* loopback device ensure this invariant is maintained by
-
* keeping the loopback device as the first device on the
-
* list of network devices. Ensuring the loopback devices
-
* is the first device that appears and the last network device
-
* that disappears.
-
*/
-
if (register_pernet_device(&loopback_net_ops))
-
goto out;
-
-
if (register_pernet_device(&default_device_ops))
-
goto out;
/*
enable软中断
*/
-
open_softirq(NET_TX_SOFTIRQ, net_tx_action);
-
open_softirq(NET_RX_SOFTIRQ, net_rx_action);
-
-
hotcpu_notifier(dev_cpu_callback, 0);
-
dst_init();
-
dev_mcast_init();
-
rc = 0;
-
out:
-
return rc;
-
}
net_dev_init在系统启动时,在注册网卡之前调用,主要就是初始化net device所需要的一些环境。
下面仍然以Intel PRO/1000的网卡驱动为例,e1000_init_module为该驱动的入口。通过e1000_init_module->pci_register_driver->e1000_probe进入初始化函数。
在e1000_probe中,通过下面这条语句绑定了操作函数。
netdev->netdev_ops = &e1000_netdev_ops;
- static const struct net_device_ops e1000_netdev_ops = {
-
.ndo_open = e1000_open,
- ...... ......
-
};
对于今天的主题来说,只需关心e1000_open即可。因为该函数是在激活该网卡时被调用,完成资源的申请,中断的注册,即e1000_intr。
- static irqreturn_t e1000_intr(int irq, void *data)
-
{
- ...... ......
- /*
- 检测是否可以调度NAPI:
- 当没有disable NAPI且没有该网卡对应的NAPI在运行时(保证对应一个网卡的NAPI只有一个实例在运行),即可调度一个新的NAPI。
- NAPI是一种新的网卡数据检查处理方式。基本上是interrupt+poll。详细信息问google
- */
-
if (likely(napi_schedule_prep(&adapter->napi))) {
- /*
- 清楚单次的统计信息。
- 刚看到这里时,我也奇怪,为什么total的统计信息要被清零。
- 实际上这些统计信息只是一次NAPI运行的统计信息,并不是网卡总的统计信息。
- 网卡的统计信息为netdev->stats。NAPI运行完会将下面的值加到网卡的统计信息上的。
- */
-
adapter->total_tx_bytes = 0;
-
adapter->total_tx_packets = 0;
-
adapter->total_rx_bytes = 0;
-
adapter->total_rx_packets = 0;
- /* 要求调度对应的NAPI实例 */
-
__napi_schedule(&adapter->napi);
-
} else {
-
/* this really should not if it does it is basically a
-
* bug, but not a hard error, so enable ints and continue */
-
if (!test_bit(__E1000_DOWN, &adapter->flags))
-
e1000_irq_enable(adapter);
-
}
-
-
return IRQ_HANDLED;
-
}
上面为中断的关键流程,其中要求调度对应的NAPI实例时,实际上是引发一个软中断。
__raise_softirq_irqoff(NET_RX_SOFTIRQ)。这个中断函数的主要功能就是要求调度一个NAPI——这里跟以前理解的中断函数不太一样。按照教科书式的概念,网卡的中断函数,应该将数据包从网卡的缓冲中取出放到一个系统缓冲中,然后在引发软中断去做剩下的工作。
下面看NET_RX_SOFTIRQ软中断对应的处理函数net_rx_action。
- static void net_rx_action(struct softirq_action *h)
-
{
-
struct softnet_data *sd = &__get_cpu_var(softnet_data);
-
unsigned long time_limit = jiffies + 2;
-
int budget = netdev_budget;
-
void *have;
-
-
local_irq_disable();
/* 开始顺序poll所有需要poll的网卡 */
-
while (!list_empty(&sd->poll_list)) {
-
struct napi_struct *n;
-
int work, weight;
-
-
/* If softirq window is exhuasted then punt.
-
* Allow this to run for 2 jiffies since which will allow
-
* an average latency of 1.5/HZ.
-
*/
-
if (unlikely(budget <= 0 || time_after(jiffies, time_limit)))
-
goto softnet_break;
-
-
local_irq_enable();
-
-
/* Even though interrupts have been re-enabled, this
-
* access is safe because interrupts can only add new
-
* entries to the tail of this list, and only ->poll()
-
* calls can remove this head entry from the list.
-
*/
- /* 取得一个网卡的NAPI实例 */
-
n = list_first_entry(&sd->poll_list, struct napi_struct, poll_list);
/* 给这个实例上锁 */
-
have = netpoll_poll_lock(n);
-
-
weight = n->weight;
-
-
/* This NAPI_STATE_SCHED test is for avoiding a race
-
* with netpoll's poll_napi(). Only the entity which
-
* obtains the lock and sees NAPI_STATE_SCHED set will
-
* actually make the ->poll() call. Therefore we avoid
-
* accidently calling ->poll() when NAPI is not scheduled.
-
*/
-
work = 0;
-
if (test_bit(NAPI_STATE_SCHED, &n->state)) {
- /* poll这个网卡 */
-
work = n->poll(n, weight);
-
trace_napi_poll(n);
-
}
-
-
WARN_ON_ONCE(work > weight);
-
-
budget -= work;
-
-
local_irq_disable();
-
-
/* Drivers must not modify the NAPI state if they
-
* consume the entire weight. In such cases this code
-
* still "owns" the NAPI instance and therefore can
-
* move the instance around on the list at-will.
-
*/
-
if (unlikely(work == weight)) {
- /* 该NAPI的weight消耗完毕,需要处理下一个 */
-
if (unlikely(napi_disable_pending(n))) {
-
local_irq_enable();
-
napi_complete(n);
-
local_irq_disable();
-
} else
-
list_move_tail(&n->poll_list, &sd->poll_list);
-
}
-
-
netpoll_poll_unlock(have);
-
}
-
out:
-
net_rps_action_and_irq_enable(sd);
-
-
#ifdef CONFIG_NET_DMA
-
/*
-
* There may not be any more sk_buffs coming right now, so push
-
* any pending DMA copies to hardware
-
*/
-
dma_issue_pending_all();
-
#endif
-
-
return;
-
-
softnet_break:
-
sd->time_squeeze++;
-
__raise_softirq_irqoff(NET_RX_SOFTIRQ);
-
goto out;
-
}
通过上面这个软中断处理函数,对应每个网卡来说,又需要跳回驱动,去学习对应的poll函数。对于本文的这个驱动来说,poll函数就是e1000_clean->e1000_clean_rx_irq。这个函数是真正用于处理网卡接收数据包的工作。
- static bool e1000_clean_rx_irq(struct e1000_adapter *adapter,
-
struct e1000_rx_ring *rx_ring,
-
int *work_done, int work_to_do)
-
{
- ...... ......
/* 得到当前需要处理buffer*/
-
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;
-
-
if (*work_done >= work_to_do) //如果已经poll到足够的包,可以跳出返回
-
break;
-
(*work_done)++;
-
rmb(); /* read descriptor and rx_buffer_info after status DD */
/* 得到数据包buffer对应的skb buffer结构地址 */
-
status = rx_desc->status;
-
skb = buffer_info->skb;
-
buffer_info->skb = NULL;
/*
然后做一些网卡硬件相关,及一些sanity check
*/
...... ......
- /*
- 设置skb->pkt_type:PACKET_BROADCAST等;
- 即数据链路层协议类型
- */
-
skb->protocol = eth_type_trans(skb, netdev);
/* 将数据包传递给上层,并做一些通用数据链路层的处理 */
-
e1000_receive_skb(adapter, status, rx_desc->special, skb);
-
-
next_desc:
- /* 处理下一个数据包 */
- ...... ......
- }
/* 更新统计信息等*/
- ...... ......
- return cleaned;
-
}
在这个函数中,真正的从网卡buffer中取出数据包,然后根据硬件的特性做一些特定处理,并简单的设置了数据包的一些field,完成L1的操作,设置好L2的报头。这时,数据包已经为TCP/IP协议栈所需要的skb_buff结构。
然后调用e1000_receive_skb->netif_receive_skb->__netif_receive_skb
- static int __netif_receive_skb(struct sk_buff *skb)
-
{
-
struct packet_type *ptype, *pt_prev;
-
rx_handler_func_t *rx_handler;
-
struct net_device *orig_dev;
-
struct net_device *master;
-
struct net_device *null_or_orig;
-
struct net_device *orig_or_bond;
-
int ret = NET_RX_DROP;
-
__be16 type;
/* 为skb打时间戳 */
-
if (!netdev_tstamp_prequeue)
-
net_timestamp_check(skb);
/* vlan下硬件加速处理 */
-
if (vlan_tx_tag_present(skb) && vlan_hwaccel_do_receive(skb))
-
return NET_RX_SUCCESS;
-
-
/* if we've gotten here through NAPI, check netpoll */
-
if (netpoll_receive_skb(skb))
-
return NET_RX_DROP;
/* 设置skb的iif为接收网卡的索引 */
-
if (!skb->skb_iif)
-
skb->skb_iif = skb->dev->ifindex;
-
/*
-
* bonding note: skbs received on inactive slaves should only
-
* be delivered to pkt handlers that are exact matches. Also
-
* the deliver_no_wcard flag will be set. If packet handlers
-
* are sensitive to duplicate packets these skbs will need to
-
* be dropped at the handler. The vlan accel path may have
-
* already set the deliver_no_wcard flag.
-
*/
- /*关于网卡的bond的处理, 这个feature我只是了解,所以略过 */
-
null_or_orig = NULL;
-
orig_dev = skb->dev;
-
master = ACCESS_ONCE(orig_dev->master);
-
if (skb->deliver_no_wcard)
-
null_or_orig = orig_dev;
-
else if (master) {
-
if (skb_bond_should_drop(skb, master)) {
-
skb->deliver_no_wcard = 1;
-
null_or_orig = orig_dev; /* deliver only exact match */
-
} else
-
skb->dev = master;
-
}
-
-
__this_cpu_inc(softnet_data.processed);
- /* 初始化l3 header 和 l4 header 的地址*/
-
skb_reset_network_header(skb);
-
skb_reset_transport_header(skb);
- /* 得到mac地址长度,准确来说是2层地址的长度 */
-
skb->mac_len = skb->network_header - skb->mac_header;
-
-
pt_prev = NULL;
-
-
rcu_read_lock();
-
- /*
- 省略一些不太相关的代码
- */
- ...... ......
-
- /*
- 通过2层协议类型作为key,得到相应链表。
- */
-
type = skb->protocol;
-
list_for_each_entry_rcu(ptype,
-
&ptype_base[ntohs(type) & PTYPE_HASH_MASK], list) {
-
if (ptype->type == type && (ptype->dev == null_or_orig ||
-
ptype->dev == skb->dev || ptype->dev == orig_dev ||
-
ptype->dev == orig_or_bond)) {
-
if (pt_prev) //找到匹配的协议类型,上传给L3层
-
ret = deliver_skb(skb, pt_prev, orig_dev);
-
pt_prev = ptype;
-
}
-
}
-
-
if (pt_prev) {
-
ret = pt_prev->func(skb, skb->dev, pt_prev, orig_dev);
-
} else {
-
kfree_skb(skb);
-
/* Jamal, now you will not able to escape explaining
-
* me how you were going to use this. :-)
-
*/
-
ret = NET_RX_DROP;
-
}
-
-
out:
-
rcu_read_unlock();
-
return ret;
-
}
现在基本上已经比较详细的学习了L2层的数据包处理流程。当然,还有很多很多的细节没有涉及,道路还很漫长啊。
阅读(10661) | 评论(7) | 转发(14) |