延續Linux Modules（12）- netfilter我們由nf_register_hooks()來看看netfilter這個framework是如何運作的。
struct list_head nf_hooks[NFPROTO_NUMPROTO][NF_MAX_HOOKS] __read_mostly;
int nf_register_hook(struct nf_hook_ops *reg)
{
struct nf_hook_ops *elem;
int err;
err = mutex_lock_interruptible(&nf_hook_mutex);
if (err < 0)
return err;
list_for_each_entry(elem, &nf_hooks[reg->pf][reg->hooknum], list) {
if (reg->priority < elem->priority)
break;
}
list_add_rcu(®->list, elem->list.prev);
mutex_unlock(&nf_hook_mutex);
return 0;
}
void nf_unregister_hook(struct nf_hook_ops *reg)
{
mutex_lock(&nf_hook_mutex);
list_del_rcu(®->list);
mutex_unlock(&nf_hook_mutex);
synchronize_net();
}
nf_hook_register_hook()其實就是在將要註冊的callback function依照所屬的protocol family以及hooknum插入struct list_head nf_hooks[NFPROTO_NUMPROTO][NF_MAX_HOOKS]，並且會依照priority由小到大，而nf_unregister_hook()就是很簡單的reg由nf_hooks中移除。接著我們再來看看nf_iterate()，程式碼中以//為註解方式，且為粗體字型就是我的註解。
unsigned int
nf_iterate(struct list_head *head, struct sk_buff *skb,
unsigned int hook, const struct net_device *indev,
const struct net_device *outdev, struct list_head **i,
int (*okfn)(struct sk_buff *), int hook_thresh)
{
unsigned int verdict;
/*
* The caller must not block between calls to this
* function because of risk of continuing from deleted element.
*/
list_for_each_continue_rcu(*i, head) {
struct nf_hook_ops *elem = (struct nf_hook_ops *)*i;
// 註冊的priority必須小於等於hook_thresh才會被執行
if (hook_thresh > elem->priority)
continue;
/* Optimization: we don't need to hold module
reference here, since function can't sleep. --RR */
//丟進註冊的hook function執行
verdict = elem->hook(hook, skb, indev, outdev, okfn);
if (verdict != NF_ACCEPT) {
#ifdef CONFIG_NETFILTER_DEBUG
if (unlikely((verdict & NF_VERDICT_MASK) > NF_MAX_VERDICT)) {
NFDEBUG("Evil return from %p(%u).\n", elem->hook, hook);
continue;
}
#endif
//如果不是NF_ACCEPT而且也不是NF_REPEAT就回傳verdict
// (NF_DROP/NF_STOLEN/NF_QUEUE)
if (verdict != NF_REPEAT)
return verdict;
//會執行到這邊就是NF_REPEAT啦
*i = (*i)->prev;
}
// 如果verdict是NF_ACCEPT就會繼續往下一個hook function執行
}
//如果沒有任何的hook function或者所有的hook function都是NF_ACCEPT
return NF_ACCEPT;
}
/* Returns 1 if okfn() needs to be executed by the caller,
* -EPERM for NF_DROP, 0 otherwise. */
int
nf_hook_slow(u_int8_t pf, unsigned int hook, struct sk_buff *skb,
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;
/* We may already have this, but read-locks nest anyway */
rcu_read_lock();
elem = &nf_hooks[pf][hook];
next_hook:
// 將nf_hooks[pf][hook]這個linked list丟進nf_iterate()中執行
verdict = nf_iterate(&nf_hooks[pf][hook], skb, hook, indev,
outdev, &elem, okfn, hook_thresh);
if (verdict == NF_ACCEPT || verdict == NF_STOP) {
// 如果是NF_ACCEPT或NF_STOP就回傳1, 到時候NF_HOOK()/NF_HOOK_COND()
// 等macro就會執行okfn, 前面的註解也有說明
ret = 1;
} else if (verdict == NF_DROP) {
// 如果是NF_DROP就會free resource並且回傳！1, 就是不會呼叫okfn()了
kfree_skb(skb);
ret = -EPERM;
} else if ((verdict & NF_VERDICT_MASK) == NF_QUEUE) {
// 如果是QUEUE就會將他nf_queue()將資訊暫時存起來, 等候處理
if (!nf_queue(skb, elem, pf, hook, indev, outdev, okfn,
verdict >> NF_VERDICT_BITS))
goto next_hook;
}
rcu_read_unlock();
// 執行到這邊有可能是NF_STOLEN, 但ret = 0, 所以不會執行okfn,
// NF_STOLEN會改變packet原本要走的路徑
return ret;
}
#iddef CONFIG_NETFILTER
int
nf_hook_slow(u_int8_t pf, unsigned int hook, struct sk_buff *skb,
struct net_device *indev, struct net_device *outdev,
int (*okfn)(struct sk_buff *), int thresh);
/**
* nf_hook_thresh - call a netfilter hook
*
* Returns 1 if the hook has allowed the packet to pass. The function
* okfn must be invoked by the caller in this case. Any other return
* value indicates the packet has been consumed by the hook.
*/
static inline int
nf_hook_thresh(u_int8_t pf, unsigned int hook, struct sk_buff *skb,
struct net_device *indev, struct net_device *outdev,
int (*okfn)(struct sk_buff *), int thresh)
{
#ifndef CONFIG_NETFILTER_DEBUG
if (list_empty(&nf_hooks[pf][hook]))
return 1;
#endif
return nf_hook_slow(pf, hook, skb, indev, outdev, okfn, thresh);
}
static inline int
nf_hook(u_int8_t pf, unsigned int hook, struct sk_buff *skb,
struct net_device *indev, struct net_device *outdev,
int (*okfn)(struct sk_buff *))
{
return nf_hook_thresh(pf, hook, skb, indev, outdev, okfn, INT_MIN);
}
/* Activate hook; either okfn or kfree_skb called, unless a hook
returns NF_STOLEN (in which case, it's up to the hook to deal with
the consequences).
Returns -ERRNO if packet dropped. Zero means queued, stolen or
accepted.
*/
/* RR:
> I don't want nf_hook to return anything because people might forget
> about async and trust the return value to mean "packet was ok".
AK:
Just document it clearly, then you can expect some sense from kernel
coders :)
*/
static inline int
NF_HOOK_THRESH(uint8_t pf, unsigned int hook, struct sk_buff *skb,
struct net_device *in, struct net_device *out,
int (*okfn)(struct sk_buff *), int thresh)
{
int ret = nf_hook_thresh(pf, hook, skb, in, out, okfn, thresh);
if (ret == 1)
ret = okfn(skb);
return ret;
}
static inline int
NF_HOOK_COND(uint8_t pf, unsigned int hook, struct sk_buff *skb,
struct net_device *in, struct net_device *out,
int (*okfn)(struct sk_buff *), bool cond)
{
int ret;
if (!cond ||
(ret = nf_hook_thresh(pf, hook, skb, in, out, okfn, INT_MIN) == 1))
ret = okfn(skb);
return ret;
}
static inline int
NF_HOOK(uint8_t pf, unsigned int hook, struct sk_buff *skb,
struct net_device *in, struct net_device *out,
int (*okfn)(struct sk_buff *))
{
return NF_HOOK_THRESH(pf, hook, skb, in, out, okfn, INT_MIN);
}
#else /* !CONFIG_NETFILTER */
#define NF_HOOK(pf, hook, skb, indev, outdev, okfn) (okfn)(skb)
#define NF_HOOK_COND(pf, hook, skb, indev, outdev, okfn, cond) (okfn)(skb)
static inline int
nf_hook_thresh(u_int8_t pf, unsigned int hook, struct sk_buff *skb,
struct net_device *indev, struct net_device *outdev,
int (*okfn)(struct sk_buff *), int thresh)
{
return okfn(skb);
}
static inline int
nf_hook(u_int8_t pf, unsigned int hook, struct sk_buff *skb,
struct net_device *indev, struct net_device *outdev,
int (*okfn)(struct sk_buff *))
{
return 1;
}
#endif /*CONFIG_NETFILTER*/
如果沒有defined CONFIG_NETFILTER，NF_HOOK()其實就是直接呼叫okfn了。到這邊對於netfilter的運作就有基本的認識了，有機會hack其他關於netfilter的心得再和大家分享。Kernel version：2.6.36
