[3] MM之伙伴系统的初始化

在前文介绍了zone_list初始化完之后，即将迎来真正的内存管理机制buddy system
大体流程为：

mm_init
--->mem_init
---|--->free_all_bootmem                                            ---1
---|---|--->free_low_memory_core_early                              ---2
---|---|---|--->__free_memory_core(start, end)                      ---3            /*memblock.memory到memblock.reserved的地址，是按每一个段来吗？*/
---|---|---|---|--->__free_pages_memory(start_pfn, end_pfn)         ---4            /*以页帧入参*/
---|---|---|---|---|--->__free_pages_bootmem(pfn_to_page(start), start, order)  ---5 /*第一参数为该页帧对应的页，此处计算了该页帧对应的order*/
---|---|---|---|---|---|--->__free_pages_boot_core(page, order)                 ---6
---|---|---|---|---|---|---|--->__free_pages(page, order)                       ---7
---|---|---|---|---|---|---|---|--->free_the_page(page, order)                  ---8
---|---|---|---|---|---|---|---|---|--->free_unref_page(page)                   ---9    /*order等于0*/
---|---|---|---|---|---|---|---|---|--->__free_pages_ok(page, order)            ---10   /*order不等于0*/

上述1~10步为系统启动阶段物理内存从memblock回归到buddy system的大体流程。

页帧与页的转换：
在不同的内存模型中页与页帧的转换方式是不同的，此处仅关注CONFIG_SPARSEMEM

/*
 * Note: section's mem_map is encoded to reflect its start_pfn.
 * section[i].section_mem_map == mem_map's address - start_pfn;
 */
#define __page_to_pfn(pg)					\
({	const struct page *__pg = (pg);				\
	int __sec = page_to_section(__pg);			\
	(unsigned long)(__pg - __section_mem_map_addr(__nr_to_section(__sec)));	\
})

#define __pfn_to_page(pfn)				\
({	unsigned long __pfn = (pfn);			\
	struct mem_section *__sec = __pfn_to_section(__pfn);	\
	__section_mem_map_addr(__sec) + __pfn;		\
})

static inline struct mem_section *__pfn_to_section(unsigned long pfn)
{
	return __nr_to_section(pfn_to_section_nr(pfn));
}

static inline unsigned long pfn_to_section_nr(unsigned long pfn)
{
	return pfn >> PFN_SECTION_SHIFT;   /*PFN_SECTION_SHIFT = 2^14个页*/
}

static inline struct mem_section *__nr_to_section(unsigned long nr)
{
#ifdef CONFIG_SPARSEMEM_EXTREME             
	if (!mem_section)
		return NULL;
#endif
	if (!mem_section[SECTION_NR_TO_ROOT(nr)])
		return NULL;
	return &mem_section[SECTION_NR_TO_ROOT(nr)][nr & SECTION_ROOT_MASK];
}

#ifdef CONFIG_SPARSEMEM_EXTREME              
#define SECTIONS_PER_ROOT       (PAGE_SIZE / sizeof (struct mem_section))  /*256*/
#else
#define SECTIONS_PER_ROOT	1
#endif

static inline struct page *__section_mem_map_addr(struct mem_section *section)
{
	unsigned long map = section->section_mem_map;   
	map &= SECTION_MAP_MASK;
	return (struct page *)map;
}

可以看到两者转换的中间桥梁是section，在SPARSEMEM稀疏内存模型中mem_section使用的是静态二维数组；
静态的数据越大对内存的消耗越大，若是依据实际物理内存来分配，可能消耗会小点；因为稀疏中会有空洞；
在定义了CONFIG_SPARSEMEM_EXTREME后，mem_setcion为二级指针类型

static unsigned long __init free_low_memory_core_early(void)
{
	unsigned long count = 0;
	phys_addr_t start, end;
	u64 i;

	memblock_clear_hotplug(0, -1);

	for_each_reserved_mem_region(i, &start, &end)
		reserve_bootmem_region(start, end);

	/*
	 * We need to use NUMA_NO_NODE instead of NODE_DATA(0)->node_id
	 *  because in some case like Node0 doesn't have RAM installed
	 *  low ram will be on Node1
	 */
	for_each_free_mem_range(i, NUMA_NO_NODE, MEMBLOCK_NONE, &start, &end,
				NULL)
		count += __free_memory_core(start, end);

	return count;
}


static unsigned long __init __free_memory_core(phys_addr_t start,
				 phys_addr_t end)
{
	unsigned long start_pfn = PFN_UP(start);
	unsigned long end_pfn = min_t(unsigned long,
				      PFN_DOWN(end), max_low_pfn);

	if (start_pfn >= end_pfn)
		return 0;

	__free_pages_memory(start_pfn, end_pfn);

	return end_pfn - start_pfn;
}

order的统计算法：

static void __init __free_pages_memory(unsigned long start, unsigned long end)
{
	int order;

	while (start < end) 
    {
		order = min(MAX_ORDER - 1UL, __ffs(start));     /*__ffs计算该页帧对应的order大小*/
		while (start + (1UL << order) > end)           
			order--;

		__free_pages_bootmem(pfn_to_page(start), start, order);

		start += (1UL << order);
	}
}

static __always_inline unsigned long __ffs(unsigned long word)
{
	int num = 0;

#if BITS_PER_LONG == 64
	if ((word & 0xffffffff) == 0) {
		num += 32;
		word >>= 32;
	}
#endif
	if ((word & 0xffff) == 0) {
		num += 16;
		word >>= 16;
	}
	if ((word & 0xff) == 0) {
		num += 8;
		word >>= 8;
	}
	if ((word & 0xf) == 0) {
		num += 4;
		word >>= 4;
	}
	if ((word & 0x3) == 0) {
		num += 2;
		word >>= 2;
	}
	if ((word & 0x1) == 0)
		num += 1;
	return num;
}

void __init __free_pages_bootmem(struct page *page, unsigned long pfn,
							unsigned int order)
{
	if (early_page_uninitialised(pfn))
		return;
	return __free_pages_boot_core(page, order);
}

static void __init __free_pages_boot_core(struct page *page, unsigned int order)
{
	unsigned int nr_pages = 1 << order; 
	struct page *p = page;
	unsigned int loop;

	prefetchw(p);
	for (loop = 0; loop < (nr_pages - 1); loop++, p++) {
		prefetchw(p + 1);
		__ClearPageReserved(p);
		set_page_count(p, 0);
	}
	__ClearPageReserved(p);
	set_page_count(p, 0);

	page_zone(page)->managed_pages += nr_pages;  /*managed_pages是伙伴系统所管理的页总和*/
	set_page_refcounted(page);  /*置page->_refcount为1*/
	__free_pages(page, order);
}

static inline void free_the_page(struct page *page, unsigned int order)
{
	if (order == 0)		/* Via pcp? */ /*在此阶段是将order为0的页挂载到pcp上面*/
		free_unref_page(page);
	else
		__free_pages_ok(page, order);
}

《free_the_page即是伙伴系统内存管理建立的接口，也是内存释放的真正行动者》
order等于0的页划入pcp

/*
 * Free a 0-order page
 */
void free_unref_page(struct page *page)
{
	unsigned long flags;
	unsigned long pfn = page_to_pfn(page);  /*在__free_pages_memory中通过pfn_to_page(start)，获取了页，此处拿pfn*/

	if (!free_unref_page_prepare(page, pfn))
		return;

	local_irq_save(flags);
	free_unref_page_commit(page, pfn);
	local_irq_restore(flags);
}

static bool free_unref_page_prepare(struct page *page, unsigned long pfn)
{
	int migratetype;

	if (!free_pcp_prepare(page))
		return false;

	migratetype = get_pfnblock_migratetype(page, pfn);
	set_pcppage_migratetype(page, migratetype);
	return true;
}

static bool free_pcp_prepare(struct page *page)
{
	return free_pages_prepare(page, 0, false);
}

static __always_inline bool free_pages_prepare(struct page *page,
					unsigned int order, bool check_free)
{
	int bad = 0;

	VM_BUG_ON_PAGE(PageTail(page), page);

	trace_mm_page_free(page, order);

	/*
	 * Check tail pages before head page information is cleared to
	 * avoid checking PageCompound for order-0 pages.
	 */
	if (unlikely(order)) {
		bool compound = PageCompound(page);
		int i;

		VM_BUG_ON_PAGE(compound && compound_order(page) != order, page);

		if (compound)
			ClearPageDoubleMap(page);
		for (i = 1; i < (1 << order); i++) {
			if (compound)
				bad += free_tail_pages_check(page, page + i);
			if (unlikely(free_pages_check(page + i))) {
				bad++;
				continue;
			}
			(page + i)->flags &= ~PAGE_FLAGS_CHECK_AT_PREP;
		}
	}

	if (PageMappingFlags(page))
		page->mapping = NULL;
	if (memcg_kmem_enabled() && PageKmemcg(page))
		memcg_kmem_uncharge(page, order);
	if (check_free)
		bad += free_pages_check(page);
	if (bad)
		return false;

	page_cpupid_reset_last(page); /*空*/
	page->flags &= ~PAGE_FLAGS_CHECK_AT_PREP;
	reset_page_owner(page, order);   /*空*/

	if (!PageHighMem(page)) {
		debug_check_no_locks_freed(page_address(page),
					   PAGE_SIZE << order);
		debug_check_no_obj_freed(page_address(page),
					   PAGE_SIZE << order);
	}
	arch_free_page(page, order);                /*空*/
	kernel_poison_pages(page, 1 << order, 0);   /*空*/
	kernel_map_pages(page, 1 << order, 0);      /*空*/
	kasan_free_nondeferred_pages(page, order);  /*空*/

	return true;
}

/*
 * Flags checked when a page is prepped for return by the page allocator.
 * Pages being prepped should not have these flags set.  It they are set,
 * there has been a kernel bug or struct page corruption.
 *
 * __PG_HWPOISON is exceptional because it needs to be kept beyond page's
 * alloc-free cycle to prevent from reusing the page.
 */
#define PAGE_FLAGS_CHECK_AT_PREP	\
	(((1UL << NR_PAGEFLAGS) - 1) & ~__PG_HWPOISON)
#define __PG_HWPOISON 0

static __always_inline int get_pfnblock_migratetype(struct page *page, unsigned long pfn)
{
	return __get_pfnblock_flags_mask(page, pfn, PB_migrate_end, MIGRATETYPE_MASK);
}

static __always_inline unsigned long __get_pfnblock_flags_mask(struct page *page,
					unsigned long pfn,
					unsigned long end_bitidx,
					unsigned long mask)
{
	unsigned long *bitmap;
	unsigned long bitidx, word_bitidx;
	unsigned long word;

	bitmap = get_pageblock_bitmap(page, pfn); /*从pageblock_flags中获取bitmap，进而获取迁移类型*/
	bitidx = pfn_to_bitidx(page, pfn);
	word_bitidx = bitidx / BITS_PER_LONG;
	bitidx &= (BITS_PER_LONG-1);

	word = bitmap[word_bitidx];
	bitidx += end_bitidx;
	return (word >> (BITS_PER_LONG - bitidx - 1)) & mask;
}

static inline unsigned long *get_pageblock_bitmap(struct page *page,
							unsigned long pfn)
{
	return __pfn_to_section(pfn)->pageblock_flags;
}

static inline struct mem_section *__pfn_to_section(unsigned long pfn)
{
	return __nr_to_section(pfn_to_section_nr(pfn));
}

static inline unsigned long pfn_to_section_nr(unsigned long pfn)
{
	return pfn >> PFN_SECTION_SHIFT;
}

static inline struct mem_section *__nr_to_section(unsigned long nr)
{
#ifdef CONFIG_SPARSEMEM_EXTREME
	if (!mem_section)
		return NULL;
#endif
	if (!mem_section[SECTION_NR_TO_ROOT(nr)])
		return NULL;
	return &mem_section[SECTION_NR_TO_ROOT(nr)][nr & SECTION_ROOT_MASK];
}
#define SECTION_NR_TO_ROOT(sec)	((sec) / SECTIONS_PER_ROOT)
#define SECTIONS_PER_ROOT       (PAGE_SIZE / sizeof (struct mem_section))

static inline int pfn_to_bitidx(struct page *page, unsigned long pfn)
{
	pfn &= (PAGES_PER_SECTION-1);
	return (pfn >> pageblock_order) * NR_PAGEBLOCK_BITS;
}

#define pageblock_order		(MAX_ORDER-1)

/* Bit indices that affect a whole block of pages */
enum pageblock_bits {
	PB_migrate,
	PB_migrate_end = PB_migrate + 3 - 1,
			/* 3 bits required for migrate types */
	PB_migrate_skip,/* If set the block is skipped by compaction */

	/*
	 * Assume the bits will always align on a word. If this assumption
	 * changes then get/set pageblock needs updating.
	 */
	NR_PAGEBLOCK_BITS
};

#define NR_MIGRATETYPE_BITS (PB_migrate_end - PB_migrate + 1)
#define MIGRATETYPE_MASK ((1UL << NR_MIGRATETYPE_BITS) - 1)

static inline void set_pcppage_migratetype(struct page *page, int migratetype)
{
	page->index = migratetype;
}

static void free_unref_page_commit(struct page *page, unsigned long pfn)
{
	struct zone *zone = page_zone(page); /*通过page可获取其对应的zone*/
	struct per_cpu_pages *pcp;          /*pcp正式登场*/
	int migratetype;

	migratetype = get_pcppage_migratetype(page); /*page->index*/
	__count_vm_event(PGFREE);

	/*
	 * We only track unmovable, reclaimable and movable on pcp lists.
	 * Free ISOLATE pages back to the allocator because they are being
	 * offlined but treat HIGHATOMIC as movable pages so we can get those
	 * areas back if necessary. Otherwise, we may have to free
	 * excessively into the page allocator
	 */
	if (migratetype >= MIGRATE_PCPTYPES) /*类型大于3时，类型重新赋值为MOVABLE*/
    {
		if (unlikely(is_migrate_isolate(migratetype))) 
        {
			free_one_page(zone, page, pfn, 0, migratetype);
			return;
		}
		migratetype = MIGRATE_MOVABLE;
	}

	pcp = &this_cpu_ptr(zone->pageset)->pcp;
	list_add(&page->lru, &pcp->lists[migratetype]); /*将此页添加到pcp->list链表头部*/
	pcp->count++;                                   /*pcp中管理的页数量加一*/
	if (pcp->count >= pcp->high) { /*当pcp管理的页面数量大于high值，释放batch个页面至伙伴系统中*/
		unsigned long batch = READ_ONCE(pcp->batch);
		free_pcppages_bulk(zone, batch, pcp);
	}
}

/*Frees a number of pages from the PCP lists*/
static void free_pcppages_bulk(struct zone *zone, int count,
					struct per_cpu_pages *pcp)
{
	int migratetype = 0;
	int batch_free = 0;
	int prefetch_nr = 0;
	bool isolated_pageblocks;
	struct page *page, *tmp;
	LIST_HEAD(head);

	/*
	 * Ensure proper count is passed which otherwise would stuck in the
	 * below while (list_empty(list)) loop.
	 */
	count = min(pcp->count, count);
	while (count) {
		struct list_head *list;

		/*
		 * Remove pages from lists in a round-robin fashion. A
		 * batch_free count is maintained that is incremented when an
		 * empty list is encountered.  This is so more pages are freed
		 * off fuller lists instead of spinning excessively around empty
		 * lists
		 */
		do {
			batch_free++;
			if (++migratetype == MIGRATE_PCPTYPES)
				migratetype = 0;
			list = &pcp->lists[migratetype];
		} while (list_empty(list));

		/* This is the only non-empty list. Free them all. */
		if (batch_free == MIGRATE_PCPTYPES)
			batch_free = count;

		do {
			page = list_last_entry(list, struct page, lru);
			/* must delete to avoid corrupting pcp list */
			list_del(&page->lru);  /*从链表中删除该page的lru节点*/
			pcp->count--;           /*pcp count减一*/

			if (bulkfree_pcp_prepare(page))
				continue;

			list_add_tail(&page->lru, &head); /*将page添加到head的尾部*/

			/*
			 * We are going to put the page back to the global
			 * pool, prefetch its buddy to speed up later access
			 * under zone->lock. It is believed the overhead of
			 * an additional test and calculating buddy_pfn here
			 * can be offset by reduced memory latency later. To
			 * avoid excessive prefetching due to large count, only
			 * prefetch buddy for the first pcp->batch nr of pages.
			 */
			if (prefetch_nr++ < pcp->batch)
				prefetch_buddy(page);
		} while (--count && --batch_free && !list_empty(list));
	}

	spin_lock(&zone->lock);
	isolated_pageblocks = has_isolate_pageblock(zone);

	/*
	 * Use safe version since after __free_one_page(),
	 * page->lru.next will not point to original list.
	 */
	list_for_each_entry_safe(page, tmp, &head, lru) {
		int mt = get_pcppage_migratetype(page);
		/* MIGRATE_ISOLATE page should not go to pcplists */
		VM_BUG_ON_PAGE(is_migrate_isolate(mt), page);
		/* Pageblock could have been isolated meanwhile */
		if (unlikely(isolated_pageblocks))
			mt = get_pageblock_migratetype(page);

		__free_one_page(page, page_to_pfn(page), zone, 0, mt);
		trace_mm_page_pcpu_drain(page, 0, mt);
	}
	spin_unlock(&zone->lock);
}

static inline void prefetch_buddy(struct page *page)
{
	unsigned long pfn = page_to_pfn(page);
	unsigned long buddy_pfn = __find_buddy_pfn(pfn, 0);
	struct page *buddy = page + (buddy_pfn - pfn);

	prefetch(buddy);
}

static inline unsigned long
__find_buddy_pfn(unsigned long page_pfn, unsigned int order)
{
	return page_pfn ^ (1 << order);
}

static inline void prefetch(const void *ptr)
{
	asm volatile("prfm pldl1keep, %a0\n" : : "p" (ptr));
}

static inline bool has_isolate_pageblock(struct zone *zone)
{
	return zone->nr_isolate_pageblock;
}

static bool bulkfree_pcp_prepare(struct page *page)
{
	return free_pages_check(page);
}
static inline int free_pages_check(struct page *page)
{
	if (likely(page_expected_state(page, PAGE_FLAGS_CHECK_AT_FREE)))
		return 0;

	/* Something has gone sideways, find it */
	free_pages_check_bad(page);
	return 1;
}

/*page, page_to_pfn(page), zone, 0, MOVABLE*/
static inline void __free_one_page(struct page *page,
		unsigned long pfn,
		struct zone *zone, unsigned int order,
		int migratetype)
{
	unsigned long combined_pfn;
	unsigned long uninitialized_var(buddy_pfn);
	struct page *buddy;
	unsigned int max_order;

	max_order = min_t(unsigned int, MAX_ORDER, pageblock_order + 1); /*pageblock_order =10, 此接口返回11*/

	VM_BUG_ON(!zone_is_initialized(zone));
	VM_BUG_ON_PAGE(page->flags & PAGE_FLAGS_CHECK_AT_PREP, page);

	VM_BUG_ON(migratetype == -1);
	if (likely(!is_migrate_isolate(migratetype)))
		__mod_zone_freepage_state(zone, 1 << order, migratetype);

	VM_BUG_ON_PAGE(pfn & ((1 << order) - 1), page);
	VM_BUG_ON_PAGE(bad_range(zone, page), page);

continue_merging:
    /* 0 < 10*/
	while (order < max_order - 1) {
		buddy_pfn = __find_buddy_pfn(pfn, order); /*通过固有公式计算该pfn的伙伴*/
		buddy = page + (buddy_pfn - pfn); /*对应伙伴的页地址*/

		if (!pfn_valid_within(buddy_pfn)) /*判断不可再继续合并，执行合并的动作*/
			goto done_merging;
		if (!page_is_buddy(page, buddy, order)) /*判断不可再继续合并，执行合并的动作*/
			goto done_merging;
		/*
		 * Our buddy is free or it is CONFIG_DEBUG_PAGEALLOC guard page,
		 * merge with it and move up one order.
		 */
		if (page_is_guard(buddy)) {
			clear_page_guard(zone, buddy, order, migratetype);
		} else {
			list_del(&buddy->lru);
			zone->free_area[order].nr_free--;
			rmv_page_order(buddy);
		}
		combined_pfn = buddy_pfn & pfn;
		page = page + (combined_pfn - pfn);
		pfn = combined_pfn;
		order++;
	}
	if (max_order < MAX_ORDER) {
		/* If we are here, it means order is >= pageblock_order.
		 * We want to prevent merge between freepages on isolate
		 * pageblock and normal pageblock. Without this, pageblock
		 * isolation could cause incorrect freepage or CMA accounting.
		 *
		 * We don't want to hit this code for the more frequent
		 * low-order merging.
		 */
		if (unlikely(has_isolate_pageblock(zone))) {
			int buddy_mt;

			buddy_pfn = __find_buddy_pfn(pfn, order);
			buddy = page + (buddy_pfn - pfn);
			buddy_mt = get_pageblock_migratetype(buddy);

			if (migratetype != buddy_mt
					&& (is_migrate_isolate(migratetype) ||
						is_migrate_isolate(buddy_mt)))
				goto done_merging;
		}
		max_order++;
		goto continue_merging;
	}

done_merging:
	set_page_order(page, order);

	/*
	 * If this is not the largest possible page, check if the buddy
	 * of the next-highest order is free. If it is, it's possible
	 * that pages are being freed that will coalesce soon. In case,
	 * that is happening, add the free page to the tail of the list
	 * so it's less likely to be used soon and more likely to be merged
	 * as a higher order page
	 */
	if ((order < MAX_ORDER-2) && pfn_valid_within(buddy_pfn)) {
		struct page *higher_page, *higher_buddy;
		combined_pfn = buddy_pfn & pfn;
		higher_page = page + (combined_pfn - pfn);
		buddy_pfn = __find_buddy_pfn(combined_pfn, order + 1);
		higher_buddy = higher_page + (buddy_pfn - combined_pfn);
		if (pfn_valid_within(buddy_pfn) &&
		    page_is_buddy(higher_page, higher_buddy, order + 1)) {
			list_add_tail(&page->lru,
				&zone->free_area[order].free_list[migratetype]);
			goto out;
		}
	}

	list_add(&page->lru, &zone->free_area[order].free_list[migratetype]);
out:
	zone->free_area[order].nr_free++;
}

/* 检查该页是否空闲且是buddy，我们可以将该页和其buddy进行合并，如果
 * buddy 不在空洞中 &&
 * buddy 在伙伴系统中 &&
 * 页和它的伙伴有相同的order&&
 * 页和它的伙伴在同一个zone中
 * This function checks whether a page is free && is the buddy
 * we can coalesce a page and its buddy if
 * (a) the buddy is not in a hole (check before calling!) &&
 * (b) the buddy is in the buddy system &&
 * (c) a page and its buddy have the same order &&
 * (d) a page and its buddy are in the same zone.
 *
 * For recording whether a page is in the buddy system, we set PageBuddy.
 * Setting, clearing, and testing PageBuddy is serialized by zone->lock.
 *
 * For recording page's order, we use page_private(page).
 */
static inline int page_is_buddy(struct page *page, struct page *buddy,
							unsigned int order)
{
	/*page_is_guard为false*/
	if (page_is_guard(buddy) && page_order(buddy) == order) {
		if (page_zone_id(page) != page_zone_id(buddy))
			return 0;

		VM_BUG_ON_PAGE(page_count(buddy) != 0, buddy);

		return 1;
	}

	if (PageBuddy(buddy) && page_order(buddy) == order) {
		/*
		 * zone check is done late to avoid uselessly
		 * calculating zone/node ids for pages that could
		 * never merge.
		 */
		if (page_zone_id(page) != page_zone_id(buddy))
			return 0;

		VM_BUG_ON_PAGE(page_count(buddy) != 0, buddy);

		return 1;
	}
	return 0;
}

/*
 * PageBuddy() indicates that the page is free and in the buddy system
 * (see mm/page_alloc.c).
 */
PAGE_TYPE_OPS(Buddy, buddy)

/*
 * For pages that are never mapped to userspace (and aren't PageSlab),
 * page_type may be used.  Because it is initialised to -1, we invert the
 * sense of the bit, so __SetPageFoo *clears* the bit used for PageFoo, and
 * __ClearPageFoo *sets* the bit used for PageFoo.  We reserve a few high and
 * low bits so that an underflow or overflow of page_mapcount() won't be
 * mistaken for a page type value.
 */

#define PAGE_TYPE_BASE	0xf0000000
/* Reserve		0x0000007f to catch underflows of page_mapcount */
#define PG_buddy	0x00000080
#define PG_balloon	0x00000100
#define PG_kmemcg	0x00000200
#define PG_table	0x00000400

#define PageType(page, flag)						\
	((page->page_type & (PAGE_TYPE_BASE | flag)) == PAGE_TYPE_BASE)

#define PAGE_TYPE_OPS(uname, lname)					\
static __always_inline int Page##uname(struct page *page)		\
{									\
	return PageType(page, PG_##lname);				\
}									\
static __always_inline void __SetPage##uname(struct page *page)		\
{									\
	VM_BUG_ON_PAGE(!PageType(page, 0), page);			\
	page->page_type &= ~PG_##lname;					\
}									\
static __always_inline void __ClearPage##uname(struct page *page)	\
{									\
	VM_BUG_ON_PAGE(!Page##uname(page), page);			\
	page->page_type |= PG_##lname;					\
}

static inline bool page_is_guard(struct page *page) { return false; }
static inline unsigned int page_order(struct page *page)
{
	/* PageBuddy() must be checked by the caller */
	return page_private(page);
}
#define page_private(page)		((page)->private)


#define pfn_valid_within(pfn) pfn_valid(pfn)
int pfn_valid(unsigned long pfn)
{
	phys_addr_t addr = pfn << PAGE_SHIFT;

	if ((addr >> PAGE_SHIFT) != pfn)
		return 0;

#ifdef CONFIG_SPARSEMEM
	if (pfn_to_section_nr(pfn) >= NR_MEM_SECTIONS)
		return 0;

	if (!valid_section(__nr_to_section(pfn_to_section_nr(pfn))))
		return 0;
#endif
	return memblock_is_map_memory(addr);
}
/*zone, 1<<0, MOVABLE*/
static inline void __mod_zone_freepage_state(struct zone *zone, int nr_pages,
					     int migratetype)
{
	__mod_zone_page_state(zone, NR_FREE_PAGES, nr_pages);
	if (is_migrate_cma(migratetype))
		__mod_zone_page_state(zone, NR_FREE_CMA_PAGES, nr_pages);
}
/*
 * For use when we know that interrupts are disabled,
 * or when we know that preemption is disabled and that
 * particular counter cannot be updated from interrupt context.
 */
void __mod_zone_page_state(struct zone *zone, enum zone_stat_item item,
			   long delta)
{
	struct per_cpu_pageset __percpu *pcp = zone->pageset;
	s8 __percpu *p = pcp->vm_stat_diff + item;
	long x;
	long t;

	x = delta + __this_cpu_read(*p);

	t = __this_cpu_read(pcp->stat_threshold);

	if (unlikely(x > t || x < -t)) {
		zone_page_state_add(x, zone, item);
		x = 0;
	}
	__this_cpu_write(*p, x);
}

struct per_cpu_pages {
	int count;		/* number of pages in the list */
	int high;		/* high watermark, emptying needed */
	int batch;		/* chunk size for buddy add/remove */

	/* Lists of pages, one per migrate type stored on the pcp-lists */
	struct list_head lists[MIGRATE_PCPTYPES];
};

struct per_cpu_pageset {
	struct per_cpu_pages pcp;
#ifdef CONFIG_NUMA
	s8 expire;
	u16 vm_numa_stat_diff[NR_VM_NUMA_STAT_ITEMS];
#endif
#ifdef CONFIG_SMP
	s8 stat_threshold;
	s8 vm_stat_diff[NR_VM_ZONE_STAT_ITEMS];
#endif
};

struct per_cpu_nodestat {
	s8 stat_threshold;
	s8 vm_node_stat_diff[NR_VM_NODE_STAT_ITEMS];
};

#define this_cpu_ptr(ptr) raw_cpu_ptr(ptr)

#define raw_cpu_ptr(ptr)						\
({									\
	__verify_pcpu_ptr(ptr);						\
	arch_raw_cpu_ptr(ptr);						\
})

#define arch_raw_cpu_ptr(ptr) SHIFT_PERCPU_PTR(ptr, __my_cpu_offset)

#define SHIFT_PERCPU_PTR(__p, __offset)					\
	RELOC_HIDE((typeof(*(__p)) __kernel __force *)(__p), (__offset))


static inline unsigned long __my_cpu_offset(void)
{
	unsigned long off;

	/*
	 * We want to allow caching the value, so avoid using volatile and
	 * instead use a fake stack read to hazard against barrier().
	 */
	asm(ALTERNATIVE("mrs %0, tpidr_el1",
			"mrs %0, tpidr_el2",
			ARM64_HAS_VIRT_HOST_EXTN)
		: "=r" (off) :
		"Q" (*(const unsigned long *)current_stack_pointer));

	return off;
}

/*
 * __verify_pcpu_ptr() verifies @ptr is a percpu pointer without evaluating
 * @ptr and is invoked once before a percpu area is accessed by all
 * accessors and operations.  This is performed in the generic part of
 * percpu and arch overrides don't need to worry about it; however, if an
 * arch wants to implement an arch-specific percpu accessor or operation,
 * it may use __verify_pcpu_ptr() to verify the parameters.
 *
 * + 0 is required in order to convert the pointer type from a
 * potential array type to a pointer to a single item of the array.
 */
#define __verify_pcpu_ptr(ptr)						\
do {									\
	const void __percpu *__vpp_verify = (typeof((ptr) + 0))NULL;	\
	(void)__vpp_verify;						\
} while (0)

enum migratetype {
	MIGRATE_UNMOVABLE,
	MIGRATE_MOVABLE,
	MIGRATE_RECLAIMABLE,
	MIGRATE_PCPTYPES,	/* the number of types on the pcp lists */
	MIGRATE_HIGHATOMIC = MIGRATE_PCPTYPES,
#ifdef CONFIG_CMA
	/*
	 * MIGRATE_CMA migration type is designed to mimic the way
	 * ZONE_MOVABLE works.  Only movable pages can be allocated
	 * from MIGRATE_CMA pageblocks and page allocator never
	 * implicitly change migration type of MIGRATE_CMA pageblock.
	 *
	 * The way to use it is to change migratetype of a range of
	 * pageblocks to MIGRATE_CMA which can be done by
	 * __free_pageblock_cma() function.  What is important though
	 * is that a range of pageblocks must be aligned to
	 * MAX_ORDER_NR_PAGES should biggest page be bigger then
	 * a single pageblock.
	 */
	MIGRATE_CMA,
#endif
#ifdef CONFIG_MEMORY_ISOLATION
	MIGRATE_ISOLATE,	/* can't allocate from here */
#endif
	MIGRATE_TYPES
};

static inline struct zone *page_zone(const struct page *page)
{
	return &NODE_DATA(page_to_nid(page))->node_zones[page_zonenum(page)];
}

static inline enum zone_type page_zonenum(const struct page *page)
{
	return (page->flags >> ZONES_PGSHIFT) & ZONES_MASK;
}
#define ZONES_PGSHIFT		(ZONES_PGOFF * (ZONES_WIDTH != 0))
/* Page flags: | [SECTION] | [NODE] | ZONE | [LAST_CPUPID] | ... | FLAGS | */
#define SECTIONS_PGOFF		((sizeof(unsigned long)*8) - SECTIONS_WIDTH)
#define NODES_PGOFF		(SECTIONS_PGOFF - NODES_WIDTH)
#define ZONES_PGOFF		(NODES_PGOFF - ZONES_WIDTH)
#define LAST_CPUPID_PGOFF	(ZONES_PGOFF - LAST_CPUPID_WIDTH)

/*
 * Define the bit shifts to access each section.  For non-existent
 * sections we define the shift as 0; that plus a 0 mask ensures
 * the compiler will optimise away reference to them.
 */
#define SECTIONS_PGSHIFT	(SECTIONS_PGOFF * (SECTIONS_WIDTH != 0))
#define NODES_PGSHIFT		(NODES_PGOFF * (NODES_WIDTH != 0))
#define ZONES_PGSHIFT		(ZONES_PGOFF * (ZONES_WIDTH != 0))
#define LAST_CPUPID_PGSHIFT	(LAST_CPUPID_PGOFF * (LAST_CPUPID_WIDTH != 0))

order不等于0的页的常规处理，假设当前order为10
static void __free_pages_ok(struct page *page, unsigned int order)
{
	unsigned long flags;
	int migratetype;
	unsigned long pfn = page_to_pfn(page);

	if (!free_pages_prepare(page, order, true))
		return;

	migratetype = get_pfnblock_migratetype(page, pfn);
	local_irq_save(flags);
	__count_vm_events(PGFREE, 1 << order);
	free_one_page(page_zone(page), page, pfn, order, migratetype);
	local_irq_restore(flags);
}

NOTE：order不论是不是0，其最终的处理核心都是由free_one_page来实现

static void free_one_page(struct zone *zone,
				struct page *page, unsigned long pfn,
				unsigned int order,
				int migratetype)
{
	spin_lock(&zone->lock);
	if (unlikely(has_isolate_pageblock(zone) ||
		is_migrate_isolate(migratetype))) {
		migratetype = get_pfnblock_migratetype(page, pfn);
	}
	__free_one_page(page, pfn, zone, order, migratetype);
	spin_unlock(&zone->lock);
}

/*eg: pfn=0, order=10, zone=ZONE_DMA32,ZONE_MOVABLE*/
static inline void __free_one_page(struct page *page,
		unsigned long pfn,
		struct zone *zone, unsigned int order,
		int migratetype)
{
	unsigned long combined_pfn;
	unsigned long uninitialized_var(buddy_pfn);
	struct page *buddy;
	unsigned int max_order;
    static int r_count = 0;
    
	max_order = min_t(unsigned int, MAX_ORDER, pageblock_order + 1); /*最小是11*/

	VM_BUG_ON(!zone_is_initialized(zone));
	VM_BUG_ON_PAGE(page->flags & PAGE_FLAGS_CHECK_AT_PREP, page);

	VM_BUG_ON(migratetype == -1);
	if (likely(!is_migrate_isolate(migratetype)))
		__mod_zone_freepage_state(zone, 1 << order, migratetype);

	VM_BUG_ON_PAGE(pfn & ((1 << order) - 1), page);
	VM_BUG_ON_PAGE(bad_range(zone, page), page);

continue_merging:
	while (order < max_order - 1) {

		buddy_pfn = __find_buddy_pfn(pfn, order); /*通过固有公式计算该pfn的伙伴:pfn ^ (1 << order)*/
		buddy = page + (buddy_pfn - pfn); /*对应伙伴的页地址*/
    
		if (!pfn_valid_within(buddy_pfn))/*如果buddy_pfn不再合法section内，则说明该buddy_pfn异常特殊，不能继续合并*/
		{
            goto done_merging;
        }
			
		if (!page_is_buddy(page, buddy, order))
		{
            goto done_merging;
        }
			
		/*
		 * Our buddy is free or it is CONFIG_DEBUG_PAGEALLOC guard page,
		 * merge with it and move up one order.
		 */
		if (page_is_guard(buddy)) {
			clear_page_guard(zone, buddy, order, migratetype);
		} else {
			list_del(&buddy->lru);
			zone->free_area[order].nr_free--;
			rmv_page_order(buddy);
		}
		combined_pfn = buddy_pfn & pfn;
		page = page + (combined_pfn - pfn);
		pfn = combined_pfn;
		order++;
	}
	if (max_order < MAX_ORDER) {
		/* If we are here, it means order is >= pageblock_order.
		 * We want to prevent merge between freepages on isolate
		 * pageblock and normal pageblock. Without this, pageblock
		 * isolation could cause incorrect freepage or CMA accounting.
		 *
		 * We don't want to hit this code for the more frequent
		 * low-order merging.
		 */
		if (unlikely(has_isolate_pageblock(zone))) {
			int buddy_mt;

			buddy_pfn = __find_buddy_pfn(pfn, order);
			buddy = page + (buddy_pfn - pfn);
			buddy_mt = get_pageblock_migratetype(buddy);

			if (migratetype != buddy_mt
					&& (is_migrate_isolate(migratetype) ||
						is_migrate_isolate(buddy_mt)))
				goto done_merging;
		}
		max_order++;
		goto continue_merging;
	}

done_merging:
	set_page_order(page, order);

	/*
	 * If this is not the largest possible page, check if the buddy
	 * of the next-highest order is free. If it is, it's possible
	 * that pages are being freed that will coalesce soon. In case,
	 * that is happening, add the free page to the tail of the list
	 * so it's less likely to be used soon and more likely to be merged
	 * as a higher order page
	 */
	if ((order < MAX_ORDER-2) && pfn_valid_within(buddy_pfn)) {
		struct page *higher_page, *higher_buddy;
		combined_pfn = buddy_pfn & pfn;
		higher_page = page + (combined_pfn - pfn);
		buddy_pfn = __find_buddy_pfn(combined_pfn, order + 1);
		higher_buddy = higher_page + (buddy_pfn - combined_pfn);
		if (pfn_valid_within(buddy_pfn) &&
		    page_is_buddy(higher_page, higher_buddy, order + 1)) {
			list_add_tail(&page->lru,
				&zone->free_area[order].free_list[migratetype]);
			goto out;
		}
	}

	/*将连续1024个页添加到具体order=10对应的free_area数组的具体type的free_list中*/
	list_add(&page->lru, &zone->free_area[order].free_list[migratetype]);
out:
	zone->free_area[order].nr_free++; /*free_area的下标为10的nr_free空闲页自加*/
	/*至此该page被放到了buddy system中了！！！*/
}

static inline void set_page_order(struct page *page, unsigned int order)
{
	set_page_private(page, order);
	__SetPageBuddy(page);  /*page->page_type &= ~PG_buddy;*/
}
#define set_page_private(page, v)	((page)->private = (v))


PAGE_TYPE_OPS(Buddy, buddy)

#define PageType(page, flag)						\
	((page->page_type & (PAGE_TYPE_BASE | flag)) == PAGE_TYPE_BASE)

#define PAGE_TYPE_OPS(uname, lname)					\
static __always_inline int Page##uname(struct page *page)		\
{									\
	return PageType(page, PG_##lname);				\
}									\
static __always_inline void __SetPage##uname(struct page *page)		\
{									\
	VM_BUG_ON_PAGE(!PageType(page, 0), page);			\
	page->page_type &= ~PG_##lname;					\
}									\
static __always_inline void __ClearPage##uname(struct page *page)	\
{									\
	VM_BUG_ON_PAGE(!Page##uname(page), page);			\
	page->page_type |= PG_##lname;					\
}

#define PAGE_TYPE_BASE	0xf0000000
/* Reserve		0x0000007f to catch underflows of page_mapcount */
#define PG_buddy	0x00000080
#define PG_balloon	0x00000100
#define PG_kmemcg	0x00000200
#define PG_table	0x00000400

Summary:
1、先是有memblock.memory和memblock.reserved的初始化
2、section的初始化、section->section_mem_map是一个关键
3、zone、zone_list的初始化、order、迁移类型以及pageflag
4、free_area的初始化，order=0的，先往pcp上挂载，若超出量 则返回给buddy system；
order不为0的，直接往buddy system中挂载；其中根据page查找其page_buddy，判断page_buddy是否合法，
合法则合并，删除page_budd->lru，以page为起始地址，将order++，add到free_area[order]->free_list[type]
5、page的order是记录在其private字段中；
6、pfn、page是通过section中间量转换的；

此内容仅为buddy system 学习过程中的笔记记录，有问题请及时指出，谢谢。