Linux物理内存概述

Linux可以支持大量的架构，所以需要用一种与架构无关的方式去描述内存。在linux的内存管理中，我们首先要明确的一个概念就是NUMA(Non-Uniform Memory Access,关于NUMA的介绍可以参考我前面的文章)。很多大型机器都采用NUMA架构，将内存和CPU分为很多组，每一组称为一个节点(node)。节点与节点之间的互相访问，会因为“距离”的不同导致不同的开销。Linux通过struct pglist_data这个结构体来描述节点，对于UMA架构，Linux同样会保留节点的概念，只是整个系统就是一个节点，只需要一个struct pglist_data来描述，它叫作contig_page_data.

struct pglist_data结构描述如下,现在只需了解其中的关键项即可

typedef struct pglist_data {
	struct zone node_zones[MAX_NR_ZONES];          /*节点中的管理区*/
	struct zonelist node_zonelists[MAX_ZONELISTS]; /*list中zone的顺序代表了分配内存的顺序，前者分配内存失败将会到后者的区域中分配内存*/
	int nr_zones;    				 /*节点中管理区的数目，不一定为3个，有的节点中可能不存在ZONE_DMA*/
#ifdef CONFIG_FLAT_NODE_MEM_MAP			 /* means !SPARSEMEM */
	struct page *node_mem_map;
#ifdef CONFIG_CGROUP_MEM_RES_CTLR
	struct page_cgroup *node_page_cgroup;
#endif
#endif
	struct bootmem_data *bdata;
#ifdef CONFIG_MEMORY_HOTPLUG
	/*
	 * Must be held any time you expect node_start_pfn, node_present_pages
	 * or node_spanned_pages stay constant.  Holding this will also
	 * guarantee that any pfn_valid() stays that way.
	 *
	 * Nests above zone->lock and zone->size_seqlock.
	 */
	spinlock_t node_size_lock;
#endif
	unsigned long node_start_pfn;     /*该节点的起始页框编号*/
	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;                      /*节点标识符，代表当前节点是系统中的第几个节点*/
	wait_queue_head_t kswapd_wait;    /*页换出进程使用的等待队列*/
	struct task_struct *kswapd;       /*指向页换出进程的进程描述符*/
	int kswapd_max_order;             /*kswapd将要创建的空闲块的大小取对数的值*/

每个节点的内存会被分为几个块，我们称之为管理区(zone),对于一个管理区，我们使用struct zone结构体来描述。管理区的类型可以分为ZONE_NORMAL,ZONE_DMA,ZONE_HIGHMEM三种。这三个管理区在物理内存上的布局为

ZONE_DMA: 0~16MB

ZONE_NORMAL: 16MB~896MB

ZONE_HIGHMEM:896MB~end

struct zone结构描述如下：

struct zone {
	/* Fields commonly accessed by the page allocator */

	/* zone watermarks, access with *_wmark_pages(zone) macros */
	unsigned long watermark[NR_WMARK];/*该管理区的三个水平线值，min,low,high*/

	/*
	 * 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;

	/*
	 * 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's tons of freeable ram
	 * on the higher zones). This array is recalculated at runtime if the
	 * sysctl_lowmem_reserve_ratio sysctl changes.
	 */
	unsigned long		lowmem_reserve[MAX_NR_ZONES];  /*每个管理区必须保留的页框数*/

#ifdef CONFIG_NUMA           /*如果定义了NUMA*/
	int node;           /*该管理区所属节点的节点号*/
	/*
	 * zone reclaim becomes active if more unmapped pages exist.
	 */
	unsigned long		min_unmapped_pages;  /*当可回收的页面数大于该变量时，管理区将回收页面*/
	unsigned long		min_slab_pages;      /*同上，只不过该标准用于slab回收页面中*/
	struct per_cpu_pageset	*pageset[NR_CPUS];   /*每个CPU使用的页面缓存*/
#else
	struct per_cpu_pageset	pageset[NR_CPUS];
#endif
	/*
	 * free areas of different sizes
	 */
	spinlock_t		lock;       /*保护该管理区的自旋锁*/
#ifdef CONFIG_MEMORY_HOTPLUG
	/* see spanned/present_pages for more description */
	seqlock_t		span_seqlock;
#endif
	struct free_area	free_area[MAX_ORDER];/*标识出管理区中的空闲页框块*/

#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_PADDING(_pad1_)

	/* Fields commonly accessed by the page reclaim scanner */
	spinlock_t		lru_lock;	
	struct zone_lru {
		struct list_head list;
	} lru[NR_LRU_LISTS];
    
	struct zone_reclaim_stat reclaim_stat; /*页面回收的状态*/

	/*管理区回收页框时使用的计数器，记录到上一次回收，一共扫过的页框数*/
	unsigned long		pages_scanned;	   /* since last reclaim */
	unsigned long		flags;		   /* zone flags, see below */

	/* Zone statistics */
	atomic_long_t		vm_stat[NR_VM_ZONE_STAT_ITEMS];

	/*
	 * prev_priority holds the scanning priority for this zone.  It is
	 * defined as the scanning priority at which we achieved our reclaim
	 * target at the previous try_to_free_pages() or balance_pgdat()
	 * invokation.
	 *
	 * We use prev_priority as a measure of how much stress page reclaim is
	 * under - it drives the swappiness decision: whether to unmap mapped
	 * pages.
	 *
	 * Access to both this field is quite racy even on uniprocessor.  But
	 * it is expected to average out OK.
	 */
	int prev_priority;

	/*
	 * The target ratio of ACTIVE_ANON to INACTIVE_ANON pages on
	 * this zone's LRU.  Maintained by the pageout code.
	 */
	unsigned int inactive_ratio;


	ZONE_PADDING(_pad2_)
	/* Rarely used or read-mostly fields */

	/*
	 * wait_table		-- the array holding the hash table
	 * wait_table_hash_nr_entries	-- the size of the hash table array
	 * wait_table_bits	-- wait_table_size == (1 << wait_table_bits)
	 *
	 * The purpose of all these is to keep track of the people
	 * waiting for a page to become available and make them
	 * runnable again when possible. The trouble is that this
	 * consumes a lot of space, especially when so few things
	 * wait on pages at a given time. So instead of using
	 * per-page waitqueues, we use a waitqueue hash table.
	 *
	 * The bucket discipline is to sleep on the same queue when
	 * colliding and wake all in that wait queue when removing.
	 * When something wakes, it must check to be sure its page is
	 * truly available, a la thundering herd. The cost of a
	 * collision is great, but given the expected load of the
	 * table, they should be so rare as to be outweighed by the
	 * benefits from the saved space.
	 *
	 * __wait_on_page_locked() and unlock_page() in mm/filemap.c, are the
	 * primary users of these fields, and in mm/page_alloc.c
	 * free_area_init_core() performs the initialization of them.
	 */
	wait_queue_head_t	* wait_table;   /*进程等待队列的散列表，这些进程正在等待管理区中的某页*/
	unsigned long		wait_table_hash_nr_entries;   /*散列表数组的大小*/
	unsigned long		wait_table_bits;              /*散列表数组的大小对2取log的结果*/

	/*
	 * Discontig memory support fields.
	 */
	struct pglist_data	*zone_pgdat;              /*管理区所属节点*/
	/* zone_start_pfn == zone_start_paddr >> PAGE_SHIFT */
	unsigned long		zone_start_pfn; /*管理区的起始页框号*/

	/*
	 * zone_start_pfn, spanned_pages and present_pages are all
	 * 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 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.
	 */
	unsigned long		spanned_pages;	/*管理区的大小,包括洞*/
	unsigned long		present_pages;	/*管理区的大小，不包括洞*/

	/*
	 * rarely used fields:
	 */
	const char		*name; /*指向管理区的名称，为"DMA","NORMAL"或"HighMem"*/
}

物理内存中的每个页都会有一个与之关联的struct page结构来对其进行描述和跟踪，其结构描述如下

struct page {
	unsigned long flags;		/* Atomic flags, some possibly
					 * updated asynchronously */
	atomic_t _count;		/* Usage count, see below. */
	union {
		atomic_t _mapcount;	/* Count of ptes mapped in mms,
					 * to show when page is mapped
					 * & limit reverse map searches.
					 */
		struct {		/* SLUB */
			u16 inuse;
			u16 objects;
		};
	};
	union {
	    struct {
		unsigned long private;		/* Mapping-private opaque data:
					 	 * usually used for buffer_heads
						 * if PagePrivate set; used for
						 * swp_entry_t if PageSwapCache;
						 * indicates order in the buddy
						 * system if PG_buddy is set.
						 */
		struct address_space *mapping;	/* If low bit clear, points to
						 * inode address_space, or NULL.
						 * If page mapped as anonymous
						 * memory, low bit is set, and
						 * it points to anon_vma object:
						 * see PAGE_MAPPING_ANON below.
						 */
	    };
#if USE_SPLIT_PTLOCKS
	    spinlock_t ptl;
#endif
	    struct kmem_cache *slab;	/* SLUB: Pointer to slab */
	    struct page *first_page;	/* Compound tail pages */
	};
	union {
		pgoff_t index;		/* Our offset within mapping. */
		void *freelist;		/* SLUB: freelist req. slab lock */
	};
	struct list_head lru;		/* Pageout list, eg. active_list
					 * protected by zone->lru_lock !
					 */
	/*
	 * 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 CONFIG_WANT_PAGE_DEBUG_FLAGS
	unsigned long debug_flags;	/* Use atomic bitops on this */
#endif

#ifdef CONFIG_KMEMCHECK
	/*
	 * kmemcheck wants to track the status of each byte in a page; this
	 * is a pointer to such a status block. NULL if not tracked.
	 */
	void *shadow;
#endif
};

Node,Zone和Page的关系可以用下图来描述

至此，已经对内存管理中的这三个关键数据结构有了一个感性的认识，在后面将会结合具体的代码来逐步深入，选择的代码版本为2.6.32.59~