深入浅出内存管理--内存管理区(Zone)

本文以Linux内核4.9来做介绍。

内存管理区(ZONE)结构体

每个Node节点中的内存又划分为多个ZONE来进行管理，内核中一共定义有如下几种类型的ZONE。

enum zone_type {
#ifdef CONFIG_ZONE_DMA
    /*
     * ZONE_DMA is used when there are devices that are not able
     * to do DMA to all of addressable memory (ZONE_NORMAL). Then we
     * carve out the portion of memory that is needed for these devices.
     * The range is arch specific.
     *
     * Some examples
     *
     * Architecture     Limit
     * ---------------------------
     * parisc, ia64, sparc  <4G
     * s390         <2G
     * arm          Various
     * alpha        Unlimited or 0-16MB.
     *
     * i386, x86_64 and multiple other arches
     *          <16M.
     */
    ZONE_DMA,
#endif
#ifdef CONFIG_ZONE_DMA32
    /*
     * x86_64 needs two ZONE_DMAs because it supports devices that are
     * only able to do DMA to the lower 16M but also 32 bit devices that
     * can only do DMA areas below 4G.
     */
    ZONE_DMA32,
#endif
    /*
     * Normal addressable memory is in ZONE_NORMAL. DMA operations can be
     * performed on pages in ZONE_NORMAL if the DMA devices support
     * transfers to all addressable memory.
     */
    ZONE_NORMAL,
#ifdef CONFIG_HIGHMEM
    /*
     * A memory area that is only addressable by the kernel through
     * mapping portions into its own address space. This is for example
     * used by i386 to allow the kernel to address the memory beyond
     * 900MB. The kernel will set up special mappings (page
     * table entries on i386) for each page that the kernel needs to
     * access.
     */
    ZONE_HIGHMEM,
#endif
    ZONE_MOVABLE,
#ifdef CONFIG_ZONE_DEVICE
    ZONE_DEVICE,
#endif
    __MAX_NR_ZONES

};

每个管理区（ZONE）对应着一个struct zone描述结构体，如下所示：

struct zone {
	/* Read-mostly fields */

	/* zone watermarks, access with *_wmark_pages(zone) macros */
	unsigned long watermark[NR_WMARK];

	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;
	struct per_cpu_pageset __percpu *pageset;

#ifdef CONFIG_CMA
	bool			cma_alloc;
#endif

#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.
	 *
	 * Read access to managed_pages should be safe because it's unsigned
	 * long. Write access to zone->managed_pages and totalram_pages are
	 * protected by managed_page_count_lock at runtime. Idealy only
	 * adjust_managed_page_count() should be used instead of directly
	 * touching zone->managed_pages and totalram_pages.
	 */
	unsigned long		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];

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

	/* Primarily protects free_area */
	spinlock_t		lock;

	/* 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;
	/* 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];
} ____cacheline_internodealigned_in_smp;

我们仅仅做一些关键成员的介绍，其余成员待遇到时再做解释：

• watermark[NR_WMARK]
  管理区水位，用于形容管理区内剩余内存的多少，当剩余内存达到对应的水位时将会触发不同的操作。一共设定三种水位：

enum zone_watermarks {
   WMARK_MIN,
   WMARK_LOW,
   WMARK_HIGH,
   NR_WMARK
};

WMARK_LOW/WMARK_HIGH：先来介绍这两个水位值，他们一个是低水位，一个是高水位，都是在页框回收算法中会用到的值。
WMARK_MIN：代表最小水位，此值是该管理区保留用作内存保留页使用的值。保留页在什么时候用呢？就是在当我们申请内存时无法等待的情况，比如在中断上下文或者持有自旋锁的时候，那么此时要尽量保证内存申请的正常返回，此时申请内存就需要从保留页来申请的，更通俗一点，我们使用kmalloc传入申请标志，当标志位为GFP_ATOMIC时，就是从保留页上申请。除此之外，WMARK_MIN也和其他两个WATER MARK一起在页框回收算法中使用。

• lowmem_reserve
  内核在分配内存时，可能会涉及到多个zone，首先尝试从zonelist的第一个zone分配，如果分配失败就会尝试zonelist中的下一个zone。举个例子，当我们应用进程通过内存映射申请Highmem中的内存，如果失败，会从
  Normal zone中尝试申请。基于此种情况，这个lowmem_reserve的意义就是保留给到当前zone使用，其余的可以用于其他zone申请时使用。

• name
  当前管理区的名称。

• free_area[MAX_ORDER]
  管理区中的空闲页框块，此成员是在伙伴系统中使用。该结构体如下：

struct free_area {
   struct list_head    free_list[MIGRATE_TYPES];
   unsigned long       nr_free;
};  

其中的free_list是伙伴系统中最常用到的一个列表。

• zone_start_pfn
  管理区其实的物理页框。