內核使用伙伴系統來解決內存分配引起的外部碎片問題。
一、數據結構描述
結構zone中的free_area數組描述伙伴系統該數組為free_area結構
www.2cto.com
struct zone {
……
struct free_area free_area[MAX_ORDER];
……
}；
www.2cto.com
struct free_area {/*鏈表類型為5類，對於分類為新加入的*/
struct list_head free_list[MIGRATE_TYPES];
unsigned long nr_free;
};
下圖為伙伴系統在管理區中的表示。
二、伙伴系統的初始化
在初始化物理管理區的時候初始化伙伴系統的，具體實現在下面的函數中：
Start_kernel()->setup_arch()->paging_init()->zone_sizes_init()->free_area_init_nodes()->free_area_init_node()->free_area_init_core()->init_currently_empty_zone()->zone_init_free_lists()
www.2cto.com
/*初始化對應zone中所有order和所有類型的鏈表*/
static void __meminit zone_init_free_lists(struct zone *zone)
{
int order, t;
for_each_migratetype_order(order, t) {
INIT_LIST_HEAD(&zone->free_area[order].free_list[t]);
zone->free_area[order].nr_free = 0;
}
}
三、伙伴系統中數據初始化
將bootmem分配器中的數據回收到伙伴系統中
start_kernel()->mm_init()->mem_init()
www.2cto.com
void __init mem_init(void)
{
int codesize, reservedpages, datasize, initsize;
int tmp;
/*和具體硬件相關*/
pci_iommu_alloc();
#ifdef CONFIG_FLATMEM
BUG_ON(!mem_map);
#endif
/* this will put all low memory onto the freelists */
/*釋放bootmem中的內存到伙伴系統中，包括bootmem占有的位圖
返回總共釋放的頁面數**/
totalram_pages += free_all_bootmem();
reservedpages = 0;
for (tmp = 0; tmp < max_low_pfn; tmp++)
/*
* Only count reserved RAM pages:
*/
if (page_is_ram(tmp) && PageReserved(pfn_to_page(tmp)))
reservedpages++;
/*初始化高端內存區，將高端內存區放入伙伴系統中*/
set_highmem_pages_init();
/*內核代碼段、數據段、初始化端長度*/
codesize = (unsigned long) &_etext - (unsigned long) &_text;
datasize = (unsigned long) &_edata - (unsigned long) &_etext;
initsize = (unsigned long) &__init_end - (unsigned long) &__init_begin;
/*打印輸出各種內存初始化後的信息*/
printk(KERN_INFO "Memory: %luk/%luk available (%dk kernel code, "
"%dk reserved, %dk data, %dk init, %ldk highmem)\n",
nr_free_pages() << (PAGE_SHIFT-10),
num_physpages << (PAGE_SHIFT-10),
codesize >> 10,
reservedpages << (PAGE_SHIFT-10),
datasize >> 10,
initsize >> 10,
(unsigned long) (totalhigh_pages << (PAGE_SHIFT-10))
);
printk(KERN_INFO "virtual kernel memory layout:\n"
" fixmap : 0x%08lx - 0x%08lx (%4ld kB)\n"
#ifdef CONFIG_HIGHMEM
" pkmap : 0x%08lx - 0x%08lx (%4ld kB)\n"
#endif
" vmalloc : 0x%08lx - 0x%08lx (%4ld MB)\n"
" lowmem : 0x%08lx - 0x%08lx (%4ld MB)\n"
" .init : 0x%08lx - 0x%08lx (%4ld kB)\n"
" .data : 0x%08lx - 0x%08lx (%4ld kB)\n"
" .text : 0x%08lx - 0x%08lx (%4ld kB)\n",
FIXADDR_START, FIXADDR_TOP,
(FIXADDR_TOP - FIXADDR_START) >> 10,
#ifdef CONFIG_HIGHMEM
PKMAP_BASE, PKMAP_BASE+LAST_PKMAP*PAGE_SIZE,
(LAST_PKMAP*PAGE_SIZE) >> 10,
#endif
VMALLOC_START, VMALLOC_END,
(VMALLOC_END - VMALLOC_START) >> 20,
(unsigned long)__va(0), (unsigned long)high_memory,
((unsigned long)high_memory - (unsigned long)__va(0)) >> 20,
(unsigned long)&__init_begin, (unsigned long)&__init_end,
((unsigned long)&__init_end -
(unsigned long)&__init_begin) >> 10,
(unsigned long)&_etext, (unsigned long)&_edata,
((unsigned long)&_edata - (unsigned long)&_etext) >> 10,
(unsigned long)&_text, (unsigned long)&_etext,
((unsigned long)&_etext - (unsigned long)&_text) >> 10);
/*
* Check boundaries twice: Some fundamental inconsistencies can
* be detected at build time already.
*/
#define __FIXADDR_TOP (-PAGE_SIZE)
#ifdef CONFIG_HIGHMEM
BUILD_BUG_ON(PKMAP_BASE + LAST_PKMAP*PAGE_SIZE > FIXADDR_START);
BUILD_BUG_ON(VMALLOC_END > PKMAP_BASE);
#endif
#define high_memory (-128UL << 20)
BUILD_BUG_ON(VMALLOC_START >= VMALLOC_END);
#undef high_memory
#undef __FIXADDR_TOP
#ifdef CONFIG_HIGHMEM
BUG_ON(PKMAP_BASE + LAST_PKMAP*PAGE_SIZE > FIXADDR_START);
BUG_ON(VMALLOC_END > PKMAP_BASE);
#endif
BUG_ON(VMALLOC_START >= VMALLOC_END);
BUG_ON((unsigned long)high_memory > VMALLOC_START);
if (boot_cpu_data.wp_works_ok < 0)
test_wp_bit();
save_pg_dir();
/*調用zap_low_mappings函數清low_memory的映射，內核線程只訪問內核空間是不能訪問用戶空間的
，其實low_memory的映射被設置的部分也就是當初為
8MB建立的恆等映射填充了臨時內核頁全局目錄的第0項，第1項
這裡將用戶空間的頁目錄項<3G的PGD清0；*/
zap_low_mappings(true);
}
www.2cto.com
/**
* free_all_bootmem - release free pages to the buddy allocator
*
* Returns the number of pages actually released.
*/
unsigned long __init free_all_bootmem(void)
{
return free_all_bootmem_core(NODE_DATA(0)->bdata);
}
www.2cto.com
static unsigned long __init free_all_bootmem_core(bootmem_data_t *bdata)
{
int aligned;
struct page *page;
unsigned long start, end, pages, count = 0;
if (!bdata->node_bootmem_map)
return 0;
/*節點內存開始和結束處*/
start = bdata->node_min_pfn;
end = bdata->node_low_pfn;
/*
* If the start is aligned to the machines wordsize, we might
* be able to free pages in bulks of that order.
*/
aligned = !(start & (BITS_PER_LONG - 1));
bdebug("nid=%td start=%lx end=%lx aligned=%d\n",
bdata - bootmem_node_data, start, end, aligned);
/*用於釋放整個bootmem所涉及的內存*/
while (start < end) {
unsigned long *map, idx, vec;
map = bdata->node_bootmem_map;
idx = start - bdata->node_min_pfn;/*相對於開始處的偏移*/
vec = ~map[idx / BITS_PER_LONG];/*vec值為頁面分配情況*/
/*如果開始地址以32位對其、連續的32個頁面都沒有被分配(空閒),並且
釋放起點以上的32個頁面都是合法的(不超過end值)，則釋放連續的32個
頁面，即1<<5個頁面*/
if (aligned && vec == ~0UL && start + BITS_PER_LONG < end) {
int order = ilog2(BITS_PER_LONG);/*32位下為5*/
/*釋放到伙伴系統中*/
__free_pages_bootmem(pfn_to_page(start), order);
count += BITS_PER_LONG;/*釋放的總頁面數更新*/
} else {
unsigned long off = 0;
/*vec!=0表示這個區間存在頁面空閒，off為這個區間的下標，從0開始*/
while (vec && off < BITS_PER_LONG) {
if (vec & 1) {/*如果頁面空閒*/
/*偏移轉化為具體的頁面*/
page = pfn_to_page(start + off);
/*一個頁面一個頁面的釋放*/
__free_pages_bootmem(page, 0);/*釋放單個頁面*/
count++;/*更新釋放頁面總數*/
}
vec >>= 1;/*vec向右移動一位，表示訪問下一個頁面*/
off++;/*偏移加一*/
}
}
start += BITS_PER_LONG;/*偏移向後移動*/
}
/*虛擬地址轉化為page
用於釋放bdata中的位圖所占有的內存*/
page = virt_to_page(bdata->node_bootmem_map);
pages = bdata->node_low_pfn - bdata->node_min_pfn;
/*計算bootmem分配器中所使用的頁面數,即位圖使用的頁面數*/
pages = bootmem_bootmap_pages(pages);
count += pages;/*釋放的總頁面數加*/
while (pages--)/*每次釋放一個頁面，釋放
總共的pages個頁面*/
__free_pages_bootmem(page++, 0);
bdebug("nid=%td released=%lx\n", bdata - bootmem_node_data, count);
return count;/*返回釋放的總頁面數*/
}
www.2cto.com
/*
* permit the bootmem allocator to evade page validation on high-order frees
*/
void __meminit __free_pages_bootmem(struct page *page, unsigned int order)
{
if (order == 0) {
__ClearPageReserved(page);
set_page_count(page, 0);/*設置頁面的引用位為0*/
set_page_refcounted(page);/*設置頁面的引用位為1*/
__free_page(page);/*釋放單個頁面到伙伴系統中*/
} else {
int loop;
/*這個不是很明白，可能和特定的體系相關???*/
prefetchw(page);
for (loop = 0; loop < BITS_PER_LONG; loop++) {
struct page *p = &page[loop];
if (loop + 1 < BITS_PER_LONG)
prefetchw(p + 1);
__ClearPageReserved(p);
set_page_count(p, 0);
}
set_page_refcounted(page);/*設置頁面的引用計數為1*/
/*這裡具體釋放到那個類型裡面，
要看page的裡面具體的東西，也就是
可以用相關函數來獲取他所屬的類型*/
__free_pages(page, order);/*釋放order個頁面*/
}
}
www.2cto.com
void __init set_highmem_pages_init(void)
{
struct zone *zone;
int nid;
for_each_zone(zone) {
unsigned long zone_start_pfn, zone_end_pfn;
if (!is_highmem(zone))/*驗證是否屬於高端內存區域中*/
/*如果不屬於，將不執行下面的操作*/
continue;
zone_start_pfn = zone->zone_start_pfn;
zone_end_pfn = zone_start_pfn + zone->spanned_pages;
/*返回zone中的node的id*/
nid = zone_to_nid(zone);
printk(KERN_INFO "Initializing %s for node %d (%08lx:%08lx)\n",
zone->name, nid, zone_start_pfn, zone_end_pfn);
/*將區間中的內存放到伙伴系統中*/
add_highpages_with_active_regions(nid, zone_start_pfn,
zone_end_pfn);
}
totalram_pages += totalhigh_pages;
｝
www.2cto.com
void __init add_highpages_with_active_regions(int nid, unsigned long start_pfn,
unsigned long end_pfn)
{
struct add_highpages_data data;
data.start_pfn = start_pfn;
data.end_pfn = end_pfn;
/*對節點中的每個區域進行頁面的回收到伙伴系統中*/
work_with_active_regions(nid, add_highpages_work_fn, &data);
}
www.2cto.com
/*用指定函數來操作活動區，在高端內存初始化時用了*/
void __init work_with_active_regions(int nid, work_fn_t work_fn, void *data)
{
int i;
int ret;
for_each_active_range_index_in_nid(i, nid) {
ret = work_fn(early_node_map[i].start_pfn,
early_node_map[i].end_pfn, data);
if (ret)
break;
}
}
www.2cto.com
static int __init add_highpages_work_fn(unsigned long start_pfn,
unsigned long end_pfn, void *datax)
{
int node_pfn;
struct page *page;
unsigned long final_start_pfn, final_end_pfn;
struct add_highpages_data *data;
data = (struct add_highpages_data *)datax;
/*活動內存區間與指定考慮區間交集*/
final_start_pfn = max(start_pfn, data->start_pfn);
final_end_pfn = min(end_pfn, data->end_pfn);
if (final_start_pfn >= final_end_pfn)
return 0;
for (node_pfn = final_start_pfn; node_pfn < final_end_pfn;
node_pfn++) {
if (!pfn_valid(node_pfn))/*驗證頁面是否有效*/
continue;
page = pfn_to_page(node_pfn);/*將下標轉換為具體的頁面*/
/*初始化頁面的count值，將頁面釋放到伙伴系統中*/
add_one_highpage_init(page, node_pfn);
}
return 0;
}
www.2cto.com
static void __init add_one_highpage_init(struct page *page, int pfn)
{
/*ClearPageReserved清除了該頁面flag中的reserved標志，表示該頁面屬於動態內存*/
ClearPageReserved(page);
init_page_count(page);/*設置page的count值為1*/
__free_page(page); /*釋放頁面到伙伴系統*/
totalhigh_pages++;/*更新高端頁面總數*/
}
www.2cto.com
void zap_low_mappings(bool early)
{
int i;
/*
* Zap initial low-memory mappings.
*
* Note that "pgd_clear()" doesn't do it for
* us, because pgd_clear() is a no-op on i386.
*/
/*這個函數很簡單，就是把前面我們在arch/x86/kernel/head_32.S中設置的頁全局目錄的前若干項清零
。這若干項到底是多少
不錯，0xc0000000>>22 & 1023= 768，這些也全局目錄項代表虛擬地址前3G的頁面，也就是所謂的用戶區
，我們在這裡把它全清零了。*/
for (i = 0; i < KERNEL_PGD_BOUNDARY; i++) {
#ifdef CONFIG_X86_PAE
set_pgd(swapper_pg_dir+i, __pgd(1 + __pa(empty_zero_page)));
#else
set_pgd(swapper_pg_dir+i, __pgd(0));
#endif
}
if (early)
__flush_tlb();
else
flush_tlb_all();
}
到此，伙伴系統已經建立並且裡面存放了應有的內存數據。要從伙伴系統中分配內存，必須要有分配和釋放機制。後面總結具體的分配和釋放工作
