Linux netfilter源碼分析(1)
- IP報文的接收到hook函數的調用
1.1 ip_input.c ip_rcv()函數
以接收到的報文為例,類似的還有ip_forward(ip_forward.c)和ip_output(ip_output.c)
int ip_rcv(struct sk_buff *skb, struct net_device *dev, struct packet_type *pt, struct net_device *orig_dev)
{
struct iphdr *iph; //定義一個ip報文的數據報頭
u32 len;
if (skb->pkt_type == PACKET_OTHERHOST)
goto drop; //數據包不是發給我們的
IP_INC_STATS_BH(IPSTATS_MIB_INRECEIVES); //收到數據包統計量加1
if ((skb = skb_share_check(skb, GFP_ATOMIC)) == NULL)
{
/* 如果數據報是共享的,則複製一個出來,此時複製而出的已經和socket脫離了關係 */
IP_INC_STATS_BH(IPSTATS_MIB_INDISCARDS);
goto out;
}
if (!pskb_may_pull(skb, sizeof(struct iphdr)))
goto inhdr_error; //對數據報的頭長度進行檢查,
iph = skb->nh.iph; //取得數據報的頭部位置
if (iph->ihl < 5 || iph->version != 4) //版本號或者頭長度不對,
goto inhdr_error; //頭長度是以4字節為單位的,所以5表示的是20字節
if (!pskb_may_pull(skb, iph->ihl*4))
goto inhdr_error;
if (unlikely(ip_fast_csum((u8 *)iph, iph->ihl)))
goto inhdr_error; //檢查報文的檢驗和字段
len = ntohs(iph->tot_len);
if (skb->len < len || len < (iph->ihl*4))
goto inhdr_error; //整個報文長度不可能比報頭長度小
if (pskb_trim_rcsum(skb, len))
{ //對數據報進行裁減,這樣可以分片發送過來的數據報不會有重複數據
IP_INC_STATS_BH(IPSTATS_MIB_INDISCARDS);
goto drop;
}
return NF_HOOK(PF_INET, NF_IP_PRE_ROUTING, skb, dev, NULL,
ip_rcv_finish); //通過回調函數調用ip_rcv_finish
inhdr_error:
IP_INC_STATS_BH(IPSTATS_MIB_INHDRERRORS);
drop:
kfree_skb(skb); //丟掉數據報
out:
return NET_RX_DROP;
}
1.2 include/linux/netfilter.h NF_HOOK
#ifdef CONFIG_NETFILTER_DEBUG
#define NF_HOOK(pf, hook, skb, indev, outdev, okfn) \
nf_hook_slow((pf), (hook), (skb), (indev), (outdev), (okfn), INT_MIN)
#define NF_HOOK_THRESH nf_hook_slow
#else
#define NF_HOOK(pf, hook, skb, indev, outdev, okfn) \
(list_empty(&nf_hooks[(pf)][(hook)]) \
? (okfn)(skb) \
: nf_hook_slow((pf), (hook), (skb), (indev), (outdev), (okfn), INT_MIN))
#define NF_HOOK_THRESH(pf, hook, skb, indev, outdev, okfn, thresh) \
(list_empty(&nf_hooks[(pf)][(hook)]) \
? (okfn)(skb) \
: nf_hook_slow((pf), (hook), (skb), (indev), (outdev), (okfn), (thresh)))
#endif
/* 如果nf_hooks[PF_INET][NF_IP_FORWARD]所指向的鏈表為空(即該鉤子上沒有掛處理函數),則直接調用okfn;否則,則調用net/core/netfilter.c::nf_hook_slow()轉入Netfilter的處理。 */
1.3 net/core/netfilter.c nf_kook_slow()函數
int nf_hook_slow(int pf, unsigned int hook, struct sk_buff **pskb,
struct net_device *indev,
struct net_device *outdev,
int (*okfn)(struct sk_buff *),
int hook_thresh)
{
struct list_head *elem;
unsigned int verdict;
int ret = 0;
rcu_read_lock();
/*取得對應的鏈表首部*/
elem = &nf_hooks[pf][hook];
next_hook:
/*調用對應的鉤子函數*/
verdict = nf_iterate(&nf_hooks[pf][hook], pskb, hook, indev,
outdev, &elem, okfn, hook_thresh);
/*判斷返回值,做相應的處理*/
if (verdict == NF_ACCEPT || verdict == NF_STOP) {
ret = 1; /*前面提到過,返回1,則表示裝繼續調用okfn函數指針*/
goto unlock;
} else if (verdict == NF_DROP) {
kfree_skb(*pskb); /*刪除數據包,需要釋放skb*/
ret = -EPERM;
} else if (verdict == NF_QUEUE) {
NFDEBUG("nf_hook: Verdict = QUEUE.\n");
if (!nf_queue(*pskb, elem, pf, hook, indev, outdev, okfn))
goto next_hook;
}
unlock:
rcu_read_unlock();
return ret;
}
1.4 net/core/netfilter.c nf_iterate()函數
static unsigned int nf_iterate(struct list_head *head,
struct sk_buff **skb,
int hook,
const struct net_device *indev,
const struct net_device *outdev,
struct list_head **i,
int (*okfn)(struct sk_buff *),
int hook_thresh)
{
/*
* The caller must not block between calls to this
* function because of risk of continuing from deleted element.
*/
/* 依次調用指定hook點下的所有nf_hook_ops->(*hook)函數,這些nf_hook_ops裡有filter表註冊的,有mangle表註冊的,等等。
list_for_each_continue_rcu函數是一個for循環的宏,當調用結點中的hook函數後,根據返回值進行相應處理。如果hook函數的返回值是NF_QUEUE,NF_STOLEN,NF_DROP時,函數返回該值;如果返回值是NF_REPEAT時,則跳到前一個結點繼續處理;如果是其他值,由下一個結點繼續處理。如果整條鏈表處理完畢,返回值不是上面四個值,則返回NF_ACCEPT。*/
list_for_each_continue_rcu(*i, head) {
struct nf_hook_ops *elem = (struct nf_hook_ops *)*i;
if (hook_thresh > elem->priority)
continue;
switch (elem->hook(hook, skb, indev, outdev, okfn)) {
case NF_QUEUE:
return NF_QUEUE;
case NF_STOLEN:
return NF_STOLEN;
case NF_DROP:
return NF_DROP;
case NF_REPEAT:
*i = (*i)->prev;
break;
}
}
return NF_ACCEPT;
}