玩轉C鏈表

作者: wwang 來源: 博客園發布時間: 2010-12-05 15:23 閱讀: 3338 次推薦: 3 原文鏈接 [收藏]

　　鏈表是C語言編程中常用的數據結構，比如我們要建一個整數鏈表，一般可能這么定義：

struct int_node {
        int val;
        struct int_node *next;
};

　　為了實現鏈表的插入、刪除、遍歷等功能，另外要再實現一系列函數，比如：

void insert_node(struct int_node *head, struct int_node *current);

void delete_node(struct int_node *head, struct int_node *current);

void access_node(struct int_node *head)
{
        struct int_node *node;
        for (node = head; node != NULL; node = node->next) {
                // do something here
        }
}

　　如果我們的代碼里只有這么一個數據結構的話，這樣做當然沒有問題，但是當代碼的規模足夠大，需要管理很多種鏈表，難道需要為每一種鏈表都要實現一套插入、刪除、遍歷等功能函數嗎？熟悉C++的同學可能會說，我們可以用標準模板庫啊，但是，我們這里談的是C，在C語言里有沒有比較好的方法呢？

　　Mr.Dave在他的博客里介紹了自己的實現，這個實現是個很好的方案，各位不妨可以參考一下。在本文中，我們把目光投向當今開源界最大的C項目--Linux Kernel，看看Linux內核如何解決這個問題。

　　Linux內核中一般使用雙向鏈表，聲明為struct list_head，這個結構體是在include/linux/types.h中定義的，鏈表的訪問是以宏或者內聯函數的形式在include/linux/list.h中定義。

struct list_head {
	struct list_head *next, *prev;
};

　　Linux內核為鏈表提供了一致的訪問接口。

void INIT_LIST_HEAD(struct list_head *list)；
void list_add(struct list_head *new, struct list_head *head)；
void list_add_tail(struct list_head *new, struct list_head *head)；
void list_del(struct list_head *entry);
int list_empty(const struct list_head *head)；

　　以上只是從Linux內核里摘選的幾個常用接口，更多的定義請參考Linux內核源代碼。我們先通過一個簡單的實作來對Linux內核如何處理鏈表建立一個感性的認識。

#include <stdio.h>
#include "list.h"

struct int_node {
        int val;
        struct list_head list;
};

int main()
{
        struct list_head head, *plist;
        struct int_node a, b;

        a.val = 2;
        b.val = 3;

        INIT_LIST_HEAD(&head);
        list_add(&a.list, &head);
        list_add(&b.list, &head);

        list_for_each(plist, &head) {
                struct int_node *node = list_entry(plist, struct int_node, list);
                printf("val = %d\n", node->val);
        }

        return 0;
}

　　看完這個實作，是不是覺得在C代碼里管理一個鏈表也很簡單呢？代碼中包含的頭文件list.h是我從Linux內核里抽取出來并做了一點修改的鏈表處理代碼，現附在這里給大家參考，使用的時候只要把這個頭文件包含到自己的工程里即可。

#ifndef __C_LIST_H
#define __C_LIST_H

typedef unsigned char u8;
typedef unsigned short u16;
typedef unsigned int u32;
typedef unsigned long size_t;

#define offsetof(TYPE, MEMBER) ((size_t) &((TYPE *)0)->MEMBER)

/**
* container_of - cast a member of a structure out to the containing structure
* @ptr: the pointer to the member.
* @type: the type of the container struct this is embedded in.
* @member: the name of the member within the struct.
*
*/
#define container_of(ptr, type, member) (type *)((char *)ptr -offsetof(type,member))

/*
* These are non-NULL pointers that will result in page faults
* under normal circumstances, used to verify that nobody uses
* non-initialized list entries.
*/
#define LIST_POISON1 ((void *) 0x00100100)
#define LIST_POISON2 ((void *) 0x00200200)

struct list_head {
struct list_head *next, *prev;
};

/**
* list_entry - get the struct for this entry
* @ptr: the &struct list_head pointer.
* @type: the type of the struct this is embedded in.
* @member: the name of the list_struct within the struct.
*/
#define list_entry(ptr, type, member) \
container_of(ptr, type, member)

#define LIST_HEAD_INIT(name) { &(name), &(name) }

#define LIST_HEAD(name) \
struct list_head name = LIST_HEAD_INIT(name)

static inline void INIT_LIST_HEAD(struct list_head *list)
{
list->next = list;
list->prev = list;
}

/**
* list_for_each - iterate over a list
* @pos: the &struct list_head to use as a loop counter.
* @head: the head for your list.
*/
#define list_for_each(pos, head) \
for (pos = (head)->next; pos != (head); pos = pos->next)

/**
* list_for_each_r - iterate over a list reversely
* @pos: the &struct list_head to use as a loop counter.
* @head: the head for your list.
*/
#define list_for_each_r(pos, head) \
for (pos = (head)->prev; pos != (head); pos = pos->prev)

/*
* Insert a new entry between two known consecutive entries.
*
* This is only for internal list manipulation where we know
* the prev/next entries already!
*/
static inline void __list_add(struct list_head *new,
struct list_head *prev,
struct list_head *next)
{
next->prev = new;
new->next = next;
new->prev = prev;
prev->next = new;
}

/**
* list_add - add a new entry
* @new: new entry to be added
* @head: list head to add it after
*
* Insert a new entry after the specified head.
* This is good for implementing stacks.
*/
static inline void list_add(struct list_head *new, struct list_head *head)
{
__list_add(new, head, head->next);
}

/**
* list_add_tail - add a new entry
* @new: new entry to be added
* @head: list head to add it before
*
* Insert a new entry before the specified head.
* This is useful for implementing queues.
*/
static inline void list_add_tail(struct list_head *new, struct list_head *head)
{
__list_add(new, head->prev, head);
}

/*
* Delete a list entry by making the prev/next entries
* point to each other.
*
* This is only for internal list manipulation where we know
* the prev/next entries already!
*/
static inline void __list_del(struct list_head * prev, struct list_head * next)
{
next->prev = prev;
prev->next = next;
}

/**
* list_del - deletes entry from list.
* @entry: the element to delete from the list.
* Note: list_empty on entry does not return true after this, the entry is
* in an undefined state.
*/
static inline void list_del(struct list_head *entry)
{
__list_del(entry->prev, entry->next);
entry->next = LIST_POISON1;
entry->prev = LIST_POISON2;
}

/**
* list_empty - tests whether a list is empty
* @head: the list to test.
*/
static inline int list_empty(const struct list_head *head)
{
return head->next == head;
}

static inline void __list_splice(struct list_head *list,
struct list_head *head)
{
struct list_head *first = list->next;
struct list_head *last = list->prev;
struct list_head *at = head->next;

first->prev = head;
head->next = first;

last->next = at;
at->prev = last;
}

/**
* list_splice - join two lists
* @list: the new list to add.
* @head: the place to add it in the first list.
*/
static inline void list_splice(struct list_head *list, struct list_head *head)
{
if (!list_empty(list))
__list_splice(list, head);
}

#endif // __C_LIST_H

　　list_head通常是嵌在數據結構內使用，在上文的實作中我們還是以整數鏈表為例，int_node的定義如下：

struct int_node {
        int val;
        struct list_head list;
};

　　使用list_head組織的鏈表的結構如下圖所示：

　　遍歷鏈表是用宏list_for_each來完成。

#define list_for_each(pos, head) \
	for (pos = (head)->next; prefetch(pos->next), pos != (head); \
        	pos = pos->next)

　　在這里，pos和head均是struct list_head。在遍歷的過程中如果需要訪問節點，可以用list_entry來取得這個節點的基址。

#define list_entry(ptr, type, member) \
	container_of(ptr, type, member)

　　我們來看看container_of是如何實現的。如下圖所示，我們已經知道TYPE結構中MEMBER的地址，如果要得到這個結構體的地址，只需要知道MEMBER在結構體中的偏移量就可以了。如何得到這個偏移量地址呢？這里用到C語言的一個小技巧，我們不妨把結構體投影到地址為0的地方，那么成員的絕對地址就是偏移量。得到偏移量之后，再根據ptr指針指向的地址，就可以很容易的計算出結構體的地址。