enum zone_type {
#ifdef CONFIG_ZONE_DMA
	ZONE_DMA,		//如果设备不能对ZONE_NORMAL的地址做DMA，那么久单独挖出来这么一块，具体的范围与架构有关，我们这里先默认是16MB
#endif
#ifdef CONFIG_ZONE_DMA32
	ZONE_DMA32,		//对于X86_64机器而言，之所以需要两个DMA是因为有的设备只能做16MB的DMA，而有的设备能做32bit内存也就是4G的DMA		
#endif
	ZONE_NORMAL,	//本质来说这实际上就已经是线性区，
#ifdef CONFIG_HIGHMEM
	ZONE_HIGHMEM,	//高端内存区，这块内存如果内存想访问需要映射到自己的地址空间里，目前看起来也就X86用了(?)，也就是高于900MB的地址空间。
#endif
	ZONE_MOVABLE,	//这个内存区很有趣，是个实际上并不真正存在的内存区。
#ifdef CONFIG_ZONE_DEVICE
	ZONE_DEVICE,
#endif
	__MAX_NR_ZONES
};

typedef struct pglist_data {
	struct zone node_zones[MAX_NR_ZONES];
	struct zonelist node_zonelists[MAX_ZONELISTS];
	int nr_zones;
#ifdef CONFIG_FLAT_NODE_MEM_MAP	/* means !SPARSEMEM */
	struct page *node_mem_map;
#ifdef CONFIG_PAGE_EXTENSION
	struct page_ext *node_page_ext;
#endif
#endif
#if defined(CONFIG_MEMORY_HOTPLUG) || defined(CONFIG_DEFERRED_STRUCT_PAGE_INIT)
	/*
	 * Must be held any time you expect node_start_pfn,
	 * node_present_pages, node_spanned_pages or nr_zones to stay constant.
	 *
	 * pgdat_resize_lock() and pgdat_resize_unlock() are provided to
	 * manipulate node_size_lock without checking for CONFIG_MEMORY_HOTPLUG
	 * or CONFIG_DEFERRED_STRUCT_PAGE_INIT.
	 *
	 * Nests above zone->lock and zone->span_seqlock
	 */
	spinlock_t node_size_lock;
#endif
	unsigned long node_start_pfn;
	unsigned long node_present_pages; /* total number of physical pages */
	unsigned long node_spanned_pages; /* total size of physical page
					     range, including holes */
	int node_id;
	wait_queue_head_t kswapd_wait;  //为kswapd新添加的等待队列链表，每个节点都有一个kswapedN
	wait_queue_head_t pfmemalloc_wait;
	struct task_struct *kswapd;	/* Protected by
					   mem_hotplug_begin/end() */
	int kswapd_order;
	enum zone_type kswapd_classzone_idx;

	int kswapd_failures;		/* Number of 'reclaimed == 0' runs */

#ifdef CONFIG_COMPACTION
	int kcompactd_max_order;
	enum zone_type kcompactd_classzone_idx;
	wait_queue_head_t kcompactd_wait;
	struct task_struct *kcompactd;
#endif
	/*
	 * This is a per-node reserve of pages that are not available
	 * to userspace allocations.
	 */
	unsigned long		totalreserve_pages;

#ifdef CONFIG_NUMA
	/*
	 * zone reclaim becomes active if more unmapped pages exist.
	 */
	unsigned long		min_unmapped_pages;
	unsigned long		min_slab_pages;
#endif /* CONFIG_NUMA */

	/* Write-intensive fields used by page reclaim */
	ZONE_PADDING(_pad1_)
	spinlock_t		lru_lock;

#ifdef CONFIG_DEFERRED_STRUCT_PAGE_INIT
	/*
	 * If memory initialisation on large machines is deferred then this
	 * is the first PFN that needs to be initialised.
	 */
	unsigned long first_deferred_pfn;
#endif /* CONFIG_DEFERRED_STRUCT_PAGE_INIT */

#ifdef CONFIG_TRANSPARENT_HUGEPAGE
	spinlock_t split_queue_lock;
	struct list_head split_queue;
	unsigned long split_queue_len;
#endif

	/* Fields commonly accessed by the page reclaim scanner */
	struct lruvec		lruvec;

	unsigned long		flags;

	ZONE_PADDING(_pad2_)

	/* Per-node vmstats */
	struct per_cpu_nodestat __percpu *per_cpu_nodestats;
	atomic_long_t		vm_stat[NR_VM_NODE_STAT_ITEMS];
} pg_data_t;

struct zone {
	/* Read-mostly fields */

	/* zone watermarks, access with *_wmark_pages(zone) macros */
	unsigned long _watermark[NR_WMARK];//管理区极值，分别对应WMARK_MIN,WMARK_LOW,WMARK_HIGH,
	unsigned long watermark_boost;

	unsigned long nr_reserved_highatomic;

	/*
	 * We don't know if the memory that we're going to allocate will be
	 * freeable or/and it will be released eventually, so to avoid totally
	 * wasting several GB of ram we must reserve some of the lower zone
	 * memory (otherwise we risk to run OOM on the lower zones despite
	 * there being tons of freeable ram on the higher zones).  This array is
	 * recalculated at runtime if the sysctl_lowmem_reserve_ratio sysctl
	 * changes.
	 */
	long lowmem_reserve[MAX_NR_ZONES];

#ifdef CONFIG_NUMA
	int node;
#endif
	struct pglist_data	*zone_pgdat;//反指回具体的节点
	struct per_cpu_pageset __percpu *pageset;

#ifndef CONFIG_SPARSEMEM
	/*
	 * Flags for a pageblock_nr_pages block. See pageblock-flags.h.
	 * In SPARSEMEM, this map is stored in struct mem_section
	 */
	unsigned long		*pageblock_flags;
#endif /* CONFIG_SPARSEMEM */

	/* zone_start_pfn == zone_start_paddr >> PAGE_SHIFT */
	unsigned long		zone_start_pfn;

	/*
	 * spanned_pages is the total pages spanned by the zone, including
	 * holes, which is calculated as:
	 * 	spanned_pages = zone_end_pfn - zone_start_pfn;
	 *
	 * present_pages is physical pages existing within the zone, which
	 * is calculated as:
	 *	present_pages = spanned_pages - absent_pages(pages in holes);
	 *
	 * managed_pages is present pages managed by the buddy system, which
	 * is calculated as (reserved_pages includes pages allocated by the
	 * bootmem allocator):
	 *	managed_pages = present_pages - reserved_pages;
	 *
	 * So present_pages may be used by memory hotplug or memory power
	 * management logic to figure out unmanaged pages by checking
	 * (present_pages - managed_pages). And managed_pages should be used
	 * by page allocator and vm scanner to calculate all kinds of watermarks
	 * and thresholds.
	 *
	 * Locking rules:
	 *
	 * zone_start_pfn and spanned_pages are protected by span_seqlock.
	 * It is a seqlock because it has to be read outside of zone->lock,
	 * and it is done in the main allocator path.  But, it is written
	 * quite infrequently.
	 *
	 * The span_seq lock is declared along with zone->lock because it is
	 * frequently read in proximity to zone->lock.  It's good to
	 * give them a chance of being in the same cacheline.
	 *
	 * Write access to present_pages at runtime should be protected by
	 * mem_hotplug_begin/end(). Any reader who can't tolerant drift of
	 * present_pages should get_online_mems() to get a stable value.
	 */
	atomic_long_t		managed_pages;
	unsigned long		spanned_pages;
	unsigned long		present_pages;

	const char		*name;

#ifdef CONFIG_MEMORY_ISOLATION
	/*
	 * Number of isolated pageblock. It is used to solve incorrect
	 * freepage counting problem due to racy retrieving migratetype
	 * of pageblock. Protected by zone->lock.
	 */
	unsigned long		nr_isolate_pageblock;
#endif

#ifdef CONFIG_MEMORY_HOTPLUG
	/* see spanned/present_pages for more description */
	seqlock_t		span_seqlock;
#endif

	int initialized;

	/* Write-intensive fields used from the page allocator */
	ZONE_PADDING(_pad1_)

	/* free areas of different sizes */
	struct free_area	free_area[MAX_ORDER]; //空闲区域位图，三种类型:可移动，可回收，不可移动。ORDER为具体的阶

	/* zone flags, see below */
	unsigned long		flags;

	/* Primarily protects free_area */
	spinlock_t		lock;	//保护锁

	/* Write-intensive fields used by compaction and vmstats. */
	ZONE_PADDING(_pad2_)

	/*
	 * When free pages are below this point, additional steps are taken
	 * when reading the number of free pages to avoid per-cpu counter
	 * drift allowing watermarks to be breached
	 */
	unsigned long percpu_drift_mark;

#if defined CONFIG_COMPACTION || defined CONFIG_CMA
	/* pfn where compaction free scanner should start */
	unsigned long		compact_cached_free_pfn;  //内存平整用
	/* pfn where async and sync compaction migration scanner should start */
	unsigned long		compact_cached_migrate_pfn[2];
#endif

#ifdef CONFIG_COMPACTION
	/*
	 * On compaction failure, 1<<compact_defer_shift compactions
	 * are skipped before trying again. The number attempted since
	 * last failure is tracked with compact_considered.
	 */
	unsigned int		compact_considered;
	unsigned int		compact_defer_shift;
	int			compact_order_failed;
#endif

#if defined CONFIG_COMPACTION || defined CONFIG_CMA
	/* Set to true when the PG_migrate_skip bits should be cleared */
	bool			compact_blockskip_flush;
#endif

	bool			contiguous;

	ZONE_PADDING(_pad3_)
	/* Zone statistics */
	atomic_long_t		vm_stat[NR_VM_ZONE_STAT_ITEMS];   //原子数据的统计。
	atomic_long_t		vm_numa_stat[NR_VM_NUMA_STAT_ITEMS];
} ___c

struct page {
	unsigned long flags;		/* Atomic flags, some possibly    应该还是用flag来反向映射管理区吧，不过似乎没必要了
					 * updated asynchronously */
	/*
	 * Five words (20/40 bytes) are available in this union.
	 * WARNING: bit 0 of the first word is used for PageTail(). That
	 * means the other users of this union MUST NOT use the bit to
	 * avoid collision and false-positive PageTail().
	 */
	union {
		struct {	/* Page cache and anonymous pages */
			/**
			 * @lru: Pageout list, eg. active_list protected by
			 * zone_lru_lock.  Sometimes used as a generic list
			 * by the page owner.
			 */
			struct list_head lru;
			/* See page-flags.h for PAGE_MAPPING_FLAGS */
			struct address_space *mapping;
			pgoff_t index;		/* Our offset within mapping. */
			/**
			 * @private: Mapping-private opaque data.
			 * Usually used for buffer_heads if PagePrivate.
			 * Used for swp_entry_t if PageSwapCache.
			 * Indicates order in the buddy system if PageBuddy.
			 */
			unsigned long private;
		};
		struct {	/* slab, slob and slub */
			union {
				struct list_head slab_list;	/* uses lru */
				struct {	/* Partial pages */
					struct page *next;
#ifdef CONFIG_64BIT
					int pages;	/* Nr of pages left */
					int pobjects;	/* Approximate count */
#else
					short int pages;
					short int pobjects;
#endif
				};
			};
			struct kmem_cache *slab_cache; /* not slob */
			/* Double-word boundary */
			void *freelist;		/* first free object */
			union {
				void *s_mem;	/* slab: first object */
				unsigned long counters;		/* SLUB */
				struct {			/* SLUB */
					unsigned inuse:16;
					unsigned objects:15;
					unsigned frozen:1;
				};
			};
		};
		struct {	/* Tail pages of compound page */
			unsigned long compound_head;	/* Bit zero is set */

			/* First tail page only */
			unsigned char compound_dtor;
			unsigned char compound_order;
			atomic_t compound_mapcount;
		};
		struct {	/* Second tail page of compound page */
			unsigned long _compound_pad_1;	/* compound_head */
			unsigned long _compound_pad_2;
			struct list_head deferred_list;
		};
		struct {	/* Page table pages */
			unsigned long _pt_pad_1;	/* compound_head */
			pgtable_t pmd_huge_pte; /* protected by page->ptl */
			unsigned long _pt_pad_2;	/* mapping */
			union {
				struct mm_struct *pt_mm; /* x86 pgds only */
				atomic_t pt_frag_refcount; /* powerpc */
			};
#if ALLOC_SPLIT_PTLOCKS
			spinlock_t *ptl;
#else
			spinlock_t ptl;
#endif
		};
		struct {	/* ZONE_DEVICE pages */
			/** @pgmap: Points to the hosting device page map. */
			struct dev_pagemap *pgmap;
			unsigned long hmm_data;
			unsigned long _zd_pad_1;	/* uses mapping */
		};

		/** @rcu_head: You can use this to free a page by RCU. */
		struct rcu_head rcu_head;
	};

	union {		/* This union is 4 bytes in size. */
		/*
		 * If the page can be mapped to userspace, encodes the number
		 * of times this page is referenced by a page table.
		 */
		atomic_t _mapcount;

		/*
		 * If the page is neither PageSlab nor mappable to userspace,
		 * the value stored here may help determine what this page
		 * is used for.  See page-flags.h for a list of page types
		 * which are currently stored here.
		 */
		unsigned int page_type;

		unsigned int active;		/* SLAB */
		int units;			/* SLOB */
	};

	/* Usage count. *DO NOT USE DIRECTLY*. See page_ref.h */
	atomic_t _refcount;

#ifdef CONFIG_MEMCG
	struct mem_cgroup *mem_cgroup;
#endif

	/*
	 * On machines where all RAM is mapped into kernel address space,
	 * we can simply calculate the virtual address. On machines with
	 * highmem some memory is mapped into kernel virtual memory
	 * dynamically, so we need a place to store that address.
	 * Note that this field could be 16 bits on x86 ... ;)
	 *
	 * Architectures with slow multiplication can define
	 * WANT_PAGE_VIRTUAL in asm/page.h
	 */
#if defined(WANT_PAGE_VIRTUAL)
	void *virtual;			/* Kernel virtual address (NULL if
					   not kmapped, ie. highmem) */
#endif /* WANT_PAGE_VIRTUAL */

#ifdef LAST_CPUPID_NOT_IN_PAGE_FLAGS
	int _last_cpupid;
#endif
} _struct_p

struct swap_info_struct {
	unsigned long	flags;		/* SWP_USED etc: see above 是否使用等标志位*/
	signed short	prio;		/* swap priority of this type 优先级*/   //交换区优先级
	struct plist_node list;		/* entry in swap_active_head */
	signed char	type;		/* strange name for an index */
	unsigned int	max;		/* extent of the swap_map 交换区当前包含的页数，不仅计算可用的槽数，也包括因为块设备故障损坏或用于管理目的的槽位*/ 
	unsigned char *swap_map;	/* vmalloc'ed array of usage counts 包含的项数和交换区槽位数目相同，访问计数*/
	struct swap_cluster_info *cluster_info; /* cluster info. Only for SSD */
	struct swap_cluster_list free_clusters; /* free clusters list */
	unsigned int lowest_bit;	/* index of first free in swap_map 这个和下面这个都是用来提高交换区访问速度，直接知道可以用哪个的*/
	unsigned int highest_bit;	/* index of last free in swap_map */
	unsigned int pages;		/* total of usable pages of swap 交换区可用槽位的个数 */
	unsigned int inuse_pages;	/* number of those currently in use 已经使用的交换区*/
	unsigned int cluster_next;	/* likely index for next allocation */
	unsigned int cluster_nr;	/* countdown to next cluster search */
	struct percpu_cluster __percpu *percpu_cluster; /* per cpu's swap location per cpu的交换位置*/
	struct swap_extent *curr_swap_extent; /* 这个对应当前正在操作的缓存文件的list的位置，因为可能有多个相连，直接找到 */
	struct swap_extent first_swap_extent; /* 这个对应于间隔的缓存文件，因为文件形式的缓存在地址上未必是连续的 */
	struct block_device *bdev;	/* swap device or bdev of swap file 交换设备，指向文件或分区所在底层快设备的block_device */
	struct file *swap_file;		/* seldom referenced */
	unsigned int old_block_size;	/* seldom referenced */
#ifdef CONFIG_FRONTSWAP
	unsigned long *frontswap_map;	/* frontswap in-use, one bit per page */
	atomic_t frontswap_pages;	/* frontswap pages in-use counter */
#endif
	spinlock_t lock;		/*
					 * protect map scan related fields like
					 * swap_map, lowest_bit, highest_bit,
					 * inuse_pages, cluster_next,
					 * cluster_nr, lowest_alloc,
					 * highest_alloc, free/discard cluster
					 * list. other fields are only changed
					 * at swapon/swapoff, so are protected
					 * by swap_lock. changing flags need
					 * hold this lock and swap_lock. If
					 * both locks need hold, hold swap_lock
					 * first.
					 */
	spinlock_t cont_lock;		/*
					 * protect swap count continuation page
					 * list.
					 */
	struct work_struct discard_work; /* discard worker */
	struct swap_cluster_list discard_clusters; /* discard clusters list */
	struct plist_node avail_lists[0]; /*
					   * entries in swap_avail_heads, one
					   * entry per node.
					   * Must be last as the number of the
					   * array is nr_node_ids, which is not
					   * a fixed value so have to allocate
					   * dynamically.
					   * And it has to be an array so that
					   * plist_for_each_* can work.
					   */
};

typedef struct {
	unsigned long val;
} swp_entry_t;