伙伴系统分配内存

内核中常用的分配物理内存页面的接口函数是alloc_pages()，用于分配一个或者多个连续的物理页面，分配页面个数只能是2个整数次幂。相比于多次分配离散的物理页面，分配连续的物理页面有利于提高系统内存的碎片化，内存碎片化是一个很让人头疼的问题。alloc_pages()函数有两个，一个是分配gfp_mask，另一个是分配阶数order。

[include/linux/gfp.h]
#define alloc_pages(gfp_mask, order)	\
	alloc_pages_node(numa_node_id(), gfp_mask, order)

分配掩码是非常重要的参数，它同样定义在gfp.h头文件中。

/* Plain integer GFP bitmasks. Do not use this directly. */
#define ___GFP_DMA		0x01u
#define ___GFP_HIGHMEM		0x02u
#define ___GFP_DMA32		0x04u
#define ___GFP_MOVABLE		0x08u
#define ___GFP_WAIT		0x10u
#define ___GFP_HIGH		0x20u
#define ___GFP_IO		0x40u
#define ___GFP_FS		0x80u
#define ___GFP_COLD		0x100u
#define ___GFP_NOWARN		0x200u
#define ___GFP_REPEAT		0x400u
#define ___GFP_NOFAIL		0x800u
#define ___GFP_NORETRY		0x1000u
#define ___GFP_MEMALLOC		0x2000u
#define ___GFP_COMP		0x4000u
#define ___GFP_ZERO		0x8000u
#define ___GFP_NOMEMALLOC	0x10000u
#define ___GFP_HARDWALL		0x20000u
#define ___GFP_THISNODE		0x40000u
#define ___GFP_RECLAIMABLE	0x80000u
#define ___GFP_NOTRACK		0x200000u
#define ___GFP_NO_KSWAPD	0x400000u
#define ___GFP_OTHER_NODE	0x800000u
#define ___GFP_WRITE		0x1000000u

分配掩码是在内核代码中分成两类，一类叫zone modifiers，另一类是action modifiers。zone modifiers指定从哪一个zone中分配所需的页面。zone modifiers由分配掩码的最低4位来定义，分别是___GFP_DMA、___GFP_HIGHMEM、___GFP_DMA32和___GFP_MOVABLE。

/* If the above are modified, __GFP_BITS_SHIFT may need updating */

/*
 * GFP bitmasks..
 *
 * Zone modifiers (see linux/mmzone.h - low three bits)
 *
 * Do not put any conditional on these. If necessary modify the definitions
 * without the underscores and use them consistently. The definitions here may
 * be used in bit comparisons.
 */
#define __GFP_DMA	((__force gfp_t)___GFP_DMA)
#define __GFP_HIGHMEM	((__force gfp_t)___GFP_HIGHMEM)
#define __GFP_DMA32	((__force gfp_t)___GFP_DMA32)
#define __GFP_MOVABLE	((__force gfp_t)___GFP_MOVABLE)  /* Page is movable */
#define GFP_ZONEMASK	(__GFP_DMA|__GFP_HIGHMEM|__GFP_DMA32|__GFP_MOVABLE)

action modifiers并不限制从哪个内存域中分配内存，但会改变分配行为，其定义如下：

/*
 * Action modifiers - doesn't change the zoning
 *
 * __GFP_REPEAT: Try hard to allocate the memory, but the allocation attempt
 * _might_ fail.  This depends upon the particular VM implementation.
 *
 * __GFP_NOFAIL: The VM implementation _must_ retry infinitely: the caller
 * cannot handle allocation failures.  This modifier is deprecated and no new
 * users should be added.
 *
 * __GFP_NORETRY: The VM implementation must not retry indefinitely.
 *
 * __GFP_MOVABLE: Flag that this page will be movable by the page migration
 * mechanism or reclaimed
 */
#define __GFP_WAIT	((__force gfp_t)___GFP_WAIT)	/* Can wait and reschedule? */
#define __GFP_HIGH	((__force gfp_t)___GFP_HIGH)	/* Should access emergency pools? */
#define __GFP_IO	((__force gfp_t)___GFP_IO)	/* Can start physical IO? */
#define __GFP_FS	((__force gfp_t)___GFP_FS)	/* Can call down to low-level FS? */
#define __GFP_COLD	((__force gfp_t)___GFP_COLD)	/* Cache-cold page required */
#define __GFP_NOWARN	((__force gfp_t)___GFP_NOWARN)	/* Suppress page allocation failure warning */
#define __GFP_REPEAT	((__force gfp_t)___GFP_REPEAT)	/* See above */
#define __GFP_NOFAIL	((__force gfp_t)___GFP_NOFAIL)	/* See above */
#define __GFP_NORETRY	((__force gfp_t)___GFP_NORETRY) /* See above */
#define __GFP_MEMALLOC	((__force gfp_t)___GFP_MEMALLOC)/* Allow access to emergency reserves */
#define __GFP_COMP	((__force gfp_t)___GFP_COMP)	/* Add compound page metadata */
#define __GFP_ZERO	((__force gfp_t)___GFP_ZERO)	/* Return zeroed page on success */
#define __GFP_NOMEMALLOC ((__force gfp_t)___GFP_NOMEMALLOC) /* Don't use emergency reserves.
							 * This takes precedence over the
							 * __GFP_MEMALLOC flag if both are
							 * set
							 */
#define __GFP_HARDWALL   ((__force gfp_t)___GFP_HARDWALL) /* Enforce hardwall cpuset memory allocs */
#define __GFP_THISNODE	((__force gfp_t)___GFP_THISNODE)/* No fallback, no policies */
#define __GFP_RECLAIMABLE ((__force gfp_t)___GFP_RECLAIMABLE) /* Page is reclaimable */
#define __GFP_NOTRACK	((__force gfp_t)___GFP_NOTRACK)  /* Don't track with kmemcheck */

#define __GFP_NO_KSWAPD	((__force gfp_t)___GFP_NO_KSWAPD)
#define __GFP_OTHER_NODE ((__force gfp_t)___GFP_OTHER_NODE) /* On behalf of other node */
#define __GFP_WRITE	((__force gfp_t)___GFP_WRITE)	/* Allocator intends to dirty page */

上述这些标志位，我们在后续代码中遇到时再详细介绍。

下面是GFP_KERNEL为例，为看理想情况下alloc_pages()函数是如何分配出物理内存的。

[分配物理内存的例子]
page = alloc_pages(GFP_KERNEL, order);

GFP_KERNEL分配掩码定义在gfp.h头文件上，是一个分配掩码的组合。常用的分配掩码组合如下：

/* This equals 0, but use constants in case they ever change */
#define GFP_NOWAIT	(GFP_ATOMIC & ~__GFP_HIGH)
/* GFP_ATOMIC means both !wait (__GFP_WAIT not set) and use emergency pool */
#define GFP_ATOMIC	(__GFP_HIGH)
#define GFP_NOIO	(__GFP_WAIT)
#define GFP_NOFS	(__GFP_WAIT | __GFP_IO)
#define GFP_KERNEL	(__GFP_WAIT | __GFP_IO | __GFP_FS)
#define GFP_TEMPORARY	(__GFP_WAIT | __GFP_IO | __GFP_FS | \
			 __GFP_RECLAIMABLE)
#define GFP_USER	(__GFP_WAIT | __GFP_IO | __GFP_FS | __GFP_HARDWALL)
#define GFP_HIGHUSER	(GFP_USER | __GFP_HIGHMEM)
#define GFP_HIGHUSER_MOVABLE	(GFP_HIGHUSER | __GFP_MOVABLE)
#define GFP_IOFS	(__GFP_IO | __GFP_FS)
#define GFP_TRANSHUGE	(GFP_HIGHUSER_MOVABLE | __GFP_COMP | \
			 __GFP_NOMEMALLOC | __GFP_NORETRY | __GFP_NOWARN | \
			 __GFP_NO_KSWAPD)

所以GFP_KERNEL分配掩码包含了__GFP_WAIT、__GFP_IO、__GFP_FS这三个标志位，换算成十六进制0xd0；

alloc_pages()最终调用__alloc_pages_nodemask()函数，它是伙伴系统的核心函数；

/*
 * This is the 'heart' of the zoned buddy allocator.
 */
struct page *
__alloc_pages_nodemask(gfp_t gfp_mask, unsigned int order,
			struct zonelist *zonelist, nodemask_t *nodemask)
{
	struct zoneref *preferred_zoneref;
	struct page *page = NULL;
	unsigned int cpuset_mems_cookie;
	int alloc_flags = ALLOC_WMARK_LOW|ALLOC_CPUSET|ALLOC_FAIR;
	gfp_t alloc_mask; /* The gfp_t that was actually used for allocation */
	struct alloc_context ac = {
		.high_zoneidx = gfp_zone(gfp_mask),
		.nodemask = nodemask,
		.migratetype = gfpflags_to_migratetype(gfp_mask),
	};

struct alloc_context数据结构是伙伴系统分配函数中用于保存相关参数的数据结构。gfp_zone()函数从分配掩码中计算出zone的zoneidx，并存放high_zoneidx成员中。

static inline enum zone_type gfp_zone(gfp_t flags)
{
	enum zone_type z;
	int bit = (__force int) (flags & GFP_ZONEMASK);

	z = (GFP_ZONE_TABLE >> (bit * ZONES_SHIFT)) &
					 ((1 << ZONES_SHIFT) - 1);
	VM_BUG_ON((GFP_ZONE_BAD >> bit) & 1);
	return z;
}

gfp_zone()函数会用到GFP_ZONEMASK、GFP_ZONE_TABLE和ZONES_SHIFT等宏。它们的定义如下：

#define GFP_ZONEMASK	(__GFP_DMA|__GFP_HIGHMEM|__GFP_DMA32|__GFP_MOVABLE)
#define GFP_ZONE_TABLE ( \
	(ZONE_NORMAL << 0 * ZONES_SHIFT)				      \
	| (OPT_ZONE_DMA << ___GFP_DMA * ZONES_SHIFT)			      \
	| (OPT_ZONE_HIGHMEM << ___GFP_HIGHMEM * ZONES_SHIFT)		      \
	| (OPT_ZONE_DMA32 << ___GFP_DMA32 * ZONES_SHIFT)		      \
	| (ZONE_NORMAL << ___GFP_MOVABLE * ZONES_SHIFT)			      \
	| (OPT_ZONE_DMA << (___GFP_MOVABLE | ___GFP_DMA) * ZONES_SHIFT)	      \
	| (ZONE_MOVABLE << (___GFP_MOVABLE | ___GFP_HIGHMEM) * ZONES_SHIFT)   \
	| (OPT_ZONE_DMA32 << (___GFP_MOVABLE | ___GFP_DMA32) * ZONES_SHIFT)   \
)
#if MAX_NR_ZONES < 2
#define ZONES_SHIFT 0
#elif MAX_NR_ZONES <= 2
#define ZONES_SHIFT 1
#elif MAX_NR_ZONES <= 4
#define ZONES_SHIFT 2

GFP_ZONEMASK是分配掩码的低4位，在ARM Vexprss平台上，只有ZONE_NORMAL和ZONE_HIGHMEM这两个zone，但是计算__MAX_NR_ZONES需要加上ZONE_MOVABLE，所以MAX_NR_ZONES等于3，这里ZONE_SHIFT等于2，那么GFP_ZONE_TABLE计算结果等于0x200010。

在上述例子中，以GFP_KERNEL分配掩码(0xd0)为参数代入gfp_zone()函数中，最终结果为0，即high_zoneidx为0。

另外__alloc_pages_nodemask()第15行代码中的gfpflags_to_migratetype()函数把gfp_mask分配掩码转换成MIGRATE_TYPES类型是MIGRATE_UNMOVABLE；如果分配掩码为GFP_HIGHUSER_MOVABLE，那么MIGRATE_TYPES类型是MIGRATE_MOVABLE。

/* Convert GFP flags to their corresponding migrate type */
static inline int gfpflags_to_migratetype(const gfp_t gfp_flags)
{
	WARN_ON((gfp_flags & GFP_MOVABLE_MASK) == GFP_MOVABLE_MASK);

	if (unlikely(page_group_by_mobility_disabled))
		return MIGRATE_UNMOVABLE;

	/* Group based on mobility */
	return (((gfp_flags & __GFP_MOVABLE) != 0) << 1) |
		((gfp_flags & __GFP_RECLAIMABLE) != 0);
}

继续回到__alloc_pages_nodemask()函数中。

[__alloc_pages_nodemask]
retry_cpuset:
	cpuset_mems_cookie = read_mems_allowed_begin();

	/* We set it here, as __alloc_pages_slowpath might have changed it */
	ac.zonelist = zonelist;
	/* The preferred zone is used for statistics later */
	preferred_zoneref = first_zones_zonelist(ac.zonelist, ac.high_zoneidx,
				ac.nodemask ? : &cpuset_current_mems_allowed,
				&ac.preferred_zone);
	if (!ac.preferred_zone)
		goto out;
	ac.classzone_idx = zonelist_zone_idx(preferred_zoneref);

	/* First allocation attempt */
	alloc_mask = gfp_mask|__GFP_HARDWALL;
	page = get_page_from_freelist(alloc_mask, order, alloc_flags, &ac);
	if (unlikely(!page)) {
		/*
		 * Runtime PM, block IO and its error handling path
		 * can deadlock because I/O on the device might not
		 * complete.
		 */
		alloc_mask = memalloc_noio_flags(gfp_mask);

		page = __alloc_pages_slowpath(alloc_mask, order, &ac);
	}

	if (kmemcheck_enabled && page)
		kmemcheck_pagealloc_alloc(page, order, gfp_mask);

	trace_mm_page_alloc(page, order, alloc_mask, ac.migratetype);

out:
	/*
	 * When updating a task's mems_allowed, it is possible to race with
	 * parallel threads in such a way that an allocation can fail while
	 * the mask is being updated. If a page allocation is about to fail,
	 * check if the cpuset changed during allocation and if so, retry.
	 */
	if (unlikely(!page && read_mems_allowed_retry(cpuset_mems_cookie)))
		goto retry_cpuset;

	return page;

首先get_page_from_freelist()会去尝试分配物理页面，如果这里分配失败，就会调用到__alloc_pages_slowpath()函数，这个函数会处理许多特殊的场景。这里假设在理想情况下，get_page_from_freelist()能分配成功；

/*
 * get_page_from_freelist goes through the zonelist trying to allocate
 * a page.
 */
static struct page *
get_page_from_freelist(gfp_t gfp_mask, unsigned int order, int alloc_flags,
						const struct alloc_context *ac)
{
	struct zonelist *zonelist = ac->zonelist;
	struct zoneref *z;
	struct page *page = NULL;
	struct zone *zone;
	nodemask_t *allowednodes = NULL;/* zonelist_cache approximation */
	int zlc_active = 0;		/* set if using zonelist_cache */
	int did_zlc_setup = 0;		/* just call zlc_setup() one time */
	bool consider_zone_dirty = (alloc_flags & ALLOC_WMARK_LOW) &&
				(gfp_mask & __GFP_WRITE);
	int nr_fair_skipped = 0;
	bool zonelist_rescan;

zonelist_scan:
	zonelist_rescan = false;

	/*
	 * Scan zonelist, looking for a zone with enough free.
	 * See also __cpuset_node_allowed() comment in kernel/cpuset.c.
	 */
	for_each_zone_zonelist_nodemask(zone, z, zonelist, ac->high_zoneidx,
								ac->nodemask) {

get_page_from_freelist()函数首先需要先判断可以从哪一个zone来分配内存。for_each_zone_zonelist_nodemask宏扫描内存节点中的zonelist去查找合适分配内存的zone。

/**
 * for_each_zone_zonelist_nodemask - helper macro to iterate over valid zones in a zonelist at or below a given zone index and within a nodemask
 * @zone - The current zone in the iterator
 * @z - The current pointer within zonelist->zones being iterated
 * @zlist - The zonelist being iterated
 * @highidx - The zone index of the highest zone to return
 * @nodemask - Nodemask allowed by the allocator
 *
 * This iterator iterates though all zones at or below a given zone index and
 * within a given nodemask
 */
#define for_each_zone_zonelist_nodemask(zone, z, zlist, highidx, nodemask) \
	for (z = first_zones_zonelist(zlist, highidx, nodemask, &zone);	\
		zone;							\
		z = next_zones_zonelist(++z, highidx, nodemask),	\
			zone = zonelist_zone(z))			\

for_each_zone_zonelist_nodemask首先通过first_zones_zonelist()从给定的zoneidx开始查找，这个给定的zoneidx就是highidx，之前通过gfp_zone()函数转换得来的。

/**
 * first_zones_zonelist - Returns the first zone at or below highest_zoneidx within the allowed nodemask in a zonelist
 * @zonelist - The zonelist to search for a suitable zone
 * @highest_zoneidx - The zone index of the highest zone to return
 * @nodes - An optional nodemask to filter the zonelist with
 * @zone - The first suitable zone found is returned via this parameter
 *
 * This function returns the first zone at or below a given zone index that is
 * within the allowed nodemask. The zoneref returned is a cursor that can be
 * used to iterate the zonelist with next_zones_zonelist by advancing it by
 * one before calling.
 */
static inline struct zoneref *first_zones_zonelist(struct zonelist *zonelist,
					enum zone_type highest_zoneidx,
					nodemask_t *nodes,
					struct zone **zone)
{
	struct zoneref *z = next_zones_zonelist(zonelist->_zonerefs,
							highest_zoneidx, nodes);
	*zone = zonelist_zone(z);
	return z;
}

first_zones_zonelist()函数会调用next_zones_zonelist()函数来计算zoneref，最后返回zone数据结构；

struct zoneref *next_zones_zonelist(struct zoneref *z,
					enum zone_type highest_zoneidx,
					nodemask_t *nodes)
{
	/*
	 * Find the next suitable zone to use for the allocation.
	 * Only filter based on nodemask if it's set
	 */
	if (likely(nodes == NULL))
		while (zonelist_zone_idx(z) > highest_zoneidx)
			z++;
	else
		while (zonelist_zone_idx(z) > highest_zoneidx ||
				(z->zone && !zref_in_nodemask(z, nodes)))
			z++;

	return z;
}

计算zone的核心函数在next_zones_zonelist()函数中，这里highest_zoneidx是gfp_zone()函数计算分配掩码得来。zonelist有一个zoneref数组，zoneref数据结构里有一个成员zone指针会指向zone数据结构，还有一个zone_index成员指向zone的编号。zone在系统处理时会初始化这个数组，具体函数在build_zonelists_node()中。在ARM Vexpress平台中，zone类型、zoneref[]数组和zoneidx的关系如下：

ZONE_HIGHMEM	__zonerefs[0]->zone_index=1
ZONE_NORMAL		__zonerefs[1]->zone_index=0

zonerefs[0]表示ZONE_HIGHMEM，其zone编号zone_index的值为1；zonerefs[1]表示ZONE_NORMAL，其zone的编号zone_index为0。也就是说，基于zone的设计思想是：分配物理页面时会优先考虑ZONE_HIGHMEM，因为ZONE_HIGHMEM在zonelist中排在ZONE_NORMAL前面；

回到我们之前的例子，gfp_zone(GFP_KERNEL)函数返回0，即highest_zoneidx为0，而这个内存节点的第一个zone是ZONE_HIGHMEM，其zone编号zone_index的值为1.因此在next_zones_zonelist()中，z++，最终first_zones_zonelist()函数会返回ZONE_NORMAL。在for_each_zone_zonelist_nodemask()遍历过程中也只能遍历ZONE_NORMAL这一个zone了。

再举一个例子，分配掩码GFP_HIGHUSER_MOVABLE，GFP_HIGHUSER_MOVEABLE包含了__GFP_HIGHMEM，那么next_zones_zonelist()函数返回哪个zone呢？

GFP_HIGHUSER_MOVABLE的值为0x200da，那么gfp_zone(GFP_HIGHUSER_MOVABLE)函数等于2，即highest_zoneidx为2，而这个内存节点的第一个ZONE_HIGHME，其zone编号zone_index的值为1；

• 在first_zones_zonelist()函数中，由于第一个zone的zone_index值小于highest_zoneidx，因此会返回ZONE_HIGHMEM。
• 在for_each_zone_zonelist_nodemask()函数中，next_zones_zonelist(++z, highidx, nodemask)依然会返回ZONE_NORMAL；
• 因此这里会遍历ZONE_HIGHMEM和ZONE_NORMAL，这两个zone，但是会先遍历ZONE_HIGHMEM，然后才是ZONE_NORMAL。 要正确理解for_each_zone_zonelist_nodemask()这个宏的行为，需要理解如下两个方面：
  • highest_zoneidx是怎么计算得来的，即如何解析分配掩码，这是gfp_zone()函数的职责。
  • 每个内存节点都有一个struct pglist_data数据结构，其成员node_zonelists是一个struct zonelist数据结构，zonelist中包含了struct zoneref __zonerefs[]数组来描述这些zone。其中ZONE_HIGHMEM排在前面，并且 _zonerefs[0]->zone_index=1，ZONE_NORMAL排在后面，且 _zonerefs[1]->zone_index=0；

  上述这些设计让人感觉复杂，但是这是正确理解以zone为基础的物理页面分配机制的基石。（说实话zone的分配实在是奇妙~） 在__alloc_page_nodemask()的第24行代码调用first_zones_zonelist()，计算出preferred_zoneref并且保存到ac.classzone_idx变量中，该变量在kswapd内核线程中还会用到。例如以GFP_KERNEL为分配掩码，preferred_zone指的是ZONE_NORMAL，ac.classzone_idx的值为0； 回到get_page_from_freelist()函数中，for_each_zone_zonelist_nodemask()找到了接下来可以从哪些zone中分配内存，下面做一些必要的检查； [get_page_from_freelist()] .... if (cpusets_enabled() && (alloc_flags & ALLOC_CPUSET) && !cpuset_zone_allowed(zone, gfp_mask)) continue; /* * Distribute pages in proportion to the individual * zone size to ensure fair page aging. The zone a * page was allocated in should have no effect on the * time the page has in memory before being reclaimed. */ if (alloc_flags & ALLOC_FAIR) { if (!zone_local(ac->preferred_zone, zone)) break; if (test_bit(ZONE_FAIR_DEPLETED, &zone->flags)) { nr_fair_skipped++; continue; } } /* * When allocating a page cache page for writing, we * want to get it from a zone that is within its dirty * limit, such that no single zone holds more than its * proportional share of globally allowed dirty pages. * The dirty limits take into account the zone's * lowmem reserves and high watermark so that kswapd * should be able to balance it without having to * write pages from its LRU list. * * This may look like it could increase pressure on * lower zones by failing allocations in higher zones * before they are full. But the pages that do spill * over are limited as the lower zones are protected * by this very same mechanism. It should not become * a practical burden to them. * * XXX: For now, allow allocations to potentially * exceed the per-zone dirty limit in the slowpath * (ALLOC_WMARK_LOW unset) before going into reclaim, * which is important when on a NUMA setup the allowed * zones are together not big enough to reach the * global limit. The proper fix for these situations * will require awareness of zones in the * dirty-throttling and the flusher threads. */ if (consider_zone_dirty && !zone_dirty_ok(zone)) continue; ..... 下面代码用于检测当前zone的watermark水位是否充足。 [get_page_from_freelist()] ... mark = zone->watermark[alloc_flags & ALLOC_WMARK_MASK]; if (!zone_watermark_ok(zone, order, mark, ac->classzone_idx, alloc_flags)) { ... ret = zone_reclaim(zone, gfp_mask, order); switch (ret) { case ZONE_RECLAIM_NOSCAN: /* did not scan */ continue; case ZONE_RECLAIM_FULL: /* scanned but unreclaimable */ continue; default: /* did we reclaim enough */ if (zone_watermark_ok(zone, order, mark, ac->classzone_idx, alloc_flags)) goto try_this_zone; /* * Failed to reclaim enough to meet watermark. * Only mark the zone full if checking the min * watermark or if we failed to reclaim just * 1<<order pages or else the page allocator * fastpath will prematurely mark zones full * when the watermark is between the low and * min watermarks. */ if (((alloc_flags & ALLOC_WMARK_MASK) == ALLOC_WMARK_MIN) || ret == ZONE_RECLAIM_SOME) goto this_zone_full; continue; } } try_this_zone: page = buffered_rmqueue(ac->preferred_zone, zone, order, gfp_mask, ac->migratetype); if (page) { if (prep_new_page(page, order, gfp_mask, alloc_flags)) goto try_this_zone; return page; } ... zone数据结构中有一个成员watermark记录各种水位的情况。系统定义了3种水位，分别是WMARK_MIN、WMARK_LOW和WMARK_HIGH。watermark水位的计算在__setup_per_zone_wmarks()函数中。 [mm/page_alloc.c] static void __setup_per_zone_wmarks(void) { unsigned long pages_min = min_free_kbytes >> (PAGE_SHIFT - 10); unsigned long lowmem_pages = 0; struct zone *zone; unsigned long flags; /* Calculate total number of !ZONE_HIGHMEM pages */ for_each_zone(zone) { if (!is_highmem(zone)) lowmem_pages += zone->managed_pages; } for_each_zone(zone) { u64 tmp; spin_lock_irqsave(&zone->lock, flags); tmp = (u64)pages_min * zone->managed_pages; do_div(tmp, lowmem_pages); if (is_highmem(zone)) { /* * __GFP_HIGH and PF_MEMALLOC allocations usually don't * need highmem pages, so cap pages_min to a small * value here. * * The WMARK_HIGH-WMARK_LOW and (WMARK_LOW-WMARK_MIN) * deltas controls asynch page reclaim, and so should * not be capped for highmem. */ unsigned long min_pages; min_pages = zone->managed_pages / 1024; min_pages = clamp(min_pages, SWAP_CLUSTER_MAX, 128UL); zone->watermark[WMARK_MIN] = min_pages; } else { /* * If it's a lowmem zone, reserve a number of pages * proportionate to the zone's size. */ zone->watermark[WMARK_MIN] = tmp; } zone->watermark[WMARK_LOW] = min_wmark_pages(zone) + (tmp >> 2); zone->watermark[WMARK_HIGH] = min_wmark_pages(zone) + (tmp >> 1); __mod_zone_page_state(zone, NR_ALLOC_BATCH, high_wmark_pages(zone) - low_wmark_pages(zone) - atomic_long_read(&zone->vm_stat[NR_ALLOC_BATCH])); setup_zone_migrate_reserve(zone); spin_unlock_irqrestore(&zone->lock, flags); } /* update totalreserve_pages */ calculate_totalreserve_pages(); } 计算watermark水位用到min_free_kbytes这个值，它是在系统启动时通过系统空闲页面的数量计算的，具体计算在init_per_zone_wmark_min()这个函数中。另外系统起来之后也可以通过sysfs来设置，节点在/proc/sys/vm/min_free_kbytes。计算watermark水位的公式不算复杂，最后结果保存在每个zone的watermark数组中，后续伙伴系统和kswapd内核线程中用到； 回到get_page_from_freelist()函数，这里会读取WMARK_LOW水位的值到变量mark中，这里zone_watermark_ok()函数判断当前zone的空闲页面是否满足WMARK_LOW水位。 [get_page_from_freelist->zone_watermark_ok->__zone_watermark_ok] /* * Return true if free pages are above 'mark'. This takes into account the order * of the allocation. */ static bool __zone_watermark_ok(struct zone *z, unsigned int order, unsigned long mark, int classzone_idx, int alloc_flags, long free_pages) { /* free_pages may go negative - that's OK */ long min = mark; int o; long free_cma = 0; free_pages -= (1 << order) - 1; if (alloc_flags & ALLOC_HIGH) min -= min / 2; if (alloc_flags & ALLOC_HARDER) min -= min / 4; #ifdef CONFIG_CMA /* If allocation can't use CMA areas don't use free CMA pages */ if (!(alloc_flags & ALLOC_CMA)) free_cma = zone_page_state(z, NR_FREE_CMA_PAGES); #endif if (free_pages - free_cma <= min + z->lowmem_reserve[classzone_idx]) return false; for (o = 0; o < order; o++) { /* At the next order, this order's pages become unavailable */ free_pages -= z->free_area[o].nr_free << o; /* Require fewer higher order pages to be free */ min >>= 1; if (free_pages <= min) return false; } return true; } 参数z表示要判断的zone，order是要分配的内存的阶数，mark是要检查的水位。通常分配物理内存页面的内核路径是检查WMARK_LOW水位，而页面回收kswapd内核线程则是检查WMARK_HIGH水位，这会导致一个内存节点各个zone的页面老化速度不一致的问题，为了解决这个问题，内核提出了许多的诡异的补丁，这个问题可以参见之后的内容。 __zone_watermark_ok()函数首先判断zone的空闲页面是否小于某个水位值和zone的最低保留值（lowmem_reserve）之和。返回true表示空闲页面在某个水位在上，否则返回false； 回到get_page_from_freelist()函数中，当判断当前zone的空闲页面低于WMARK_LOW水位，会调用zone_reclaim()函数来回收页面。我们这里假设zone_watermark_ok()判断空闲页面充沛，接下来就会调用buffered_rmqueue()函数从伙伴系统中分配物理页面。 [__alloc_pages_nodemask()->get_page_from_freelist()->buffered_rmqueue()] /* * Allocate a page from the given zone. Use pcplists for order-0 allocations. */ static inline struct page *buffered_rmqueue(struct zone *preferred_zone, struct zone *zone, unsigned int order, gfp_t gfp_flags, int migratetype) { unsigned long flags; struct page *page; bool cold = ((gfp_flags & __GFP_COLD) != 0); if (likely(order == 0)) { struct per_cpu_pages *pcp; struct list_head *list; local_irq_save(flags); pcp = &this_cpu_ptr(zone->pageset)->pcp; list = &pcp->lists[migratetype]; if (list_empty(list)) { pcp->count += rmqueue_bulk(zone, 0, pcp->batch, list, migratetype, cold); if (unlikely(list_empty(list))) goto failed; } if (cold) page = list_entry(list->prev, struct page, lru); else page = list_entry(list->next, struct page, lru); list_del(&page->lru); pcp->count--; } else { if (unlikely(gfp_flags & __GFP_NOFAIL)) { /* * __GFP_NOFAIL is not to be used in new code. * * All __GFP_NOFAIL callers should be fixed so that they * properly detect and handle allocation failures. * * We most definitely don't want callers attempting to * allocate greater than order-1 page units with * __GFP_NOFAIL. */ WARN_ON_ONCE(order > 1); } spin_lock_irqsave(&zone->lock, flags); page = __rmqueue(zone, order, migratetype); spin_unlock(&zone->lock); if (!page) goto failed; __mod_zone_freepage_state(zone, -(1 << order), get_freepage_migratetype(page)); } __mod_zone_page_state(zone, NR_ALLOC_BATCH, -(1 << order)); if (atomic_long_read(&zone->vm_stat[NR_ALLOC_BATCH]) <= 0 && !test_bit(ZONE_FAIR_DEPLETED, &zone->flags)) set_bit(ZONE_FAIR_DEPLETED, &zone->flags); __count_zone_vm_events(PGALLOC, zone, 1 << order); zone_statistics(preferred_zone, zone, gfp_flags); local_irq_restore(flags); VM_BUG_ON_PAGE(bad_range(zone, page), page); return page; failed: local_irq_restore(flags); return NULL; } 这里根据order数值兵分两路：一路是order等于0 的情况，也就是分配一个物理页面时，从zone->per_cpu_pageset列表中分配；另一路order大于0的情况，就从伙伴系统中分配。我们只关注order大于0 的情况，它最终会调用到__rmqueue_smallest()函数。 [get_page_from_freelist()->buffered_rmqueue()->buffered_rmqueue->__rmqueue()->__rmqueue_smallest()] /* * Go through the free lists for the given migratetype and remove * the smallest available page from the freelists */ static inline struct page *__rmqueue_smallest(struct zone *zone, unsigned int order, int migratetype) { unsigned int current_order; struct free_area *area; struct page *page; /* Find a page of the appropriate size in the preferred list */ for (current_order = order; current_order < MAX_ORDER; ++current_order) { area = &(zone->free_area[current_order]); if (list_empty(&area->free_list[migratetype])) continue; page = list_entry(area->free_list[migratetype].next, struct page, lru); list_del(&page->lru); rmv_page_order(page); area->nr_free--; expand(zone, page, order, current_order, area, migratetype); set_freepage_migratetype(page, migratetype); return page; } return NULL; } 在__rmqueue_smallest()函数中，首先从order开始查找zone中的空闲链表。如果zone的当前order对应的空闲区free_area中相应的migratetype类型的链表里没有空闲链表，那么就会查找下一级order。 为什么会这样？因为在系统启动时，空闲页面会尽可能分配到MAX_ORDER-1的链表中，这个可以在系统刚起来之后，通过'cat /proc/pagetypeinfo'命令可以看出端倪。当找到某个order的空闲区中对应的mirgratetype类型的空闲链表中有空闲内存块时，就会从一个内存块摘下来，然后摘用expand()函数来切“蛋糕”。因为通常摘下来的内存块会比需要的内存大，切完之后需要把剩下来的内存块重新放回伙伴系统中。 expand()函数就是实现“切蛋糕”的功能。这里的参数high就是current_order，通常是current_order要比需求的order要大。每比较一次，area减一，相当于退了一级order，最后通过list_add把剩下的内存块添加到低一级的空闲链表中。 [get_page_from_freelist()->buffered_rmqueue()->buffered_rmqueue->__rmqueue()->__rmqueue_smallest()->expand()] /* * The order of subdivision here is critical for the IO subsystem. * Please do not alter this order without good reasons and regression * testing. Specifically, as large blocks of memory are subdivided, * the order in which smaller blocks are delivered depends on the order * they're subdivided in this function. This is the primary factor * influencing the order in which pages are delivered to the IO * subsystem according to empirical testing, and this is also justified * by considering the behavior of a buddy system containing a single * large block of memory acted on by a series of small allocations. * This behavior is a critical factor in sglist merging's success. * * -- nyc */ static inline void expand(struct zone *zone, struct page *page, int low, int high, struct free_area *area, int migratetype) { unsigned long size = 1 << high; while (high > low) { area--; high--; size >>= 1; VM_BUG_ON_PAGE(bad_range(zone, &page[size]), &page[size]); if (IS_ENABLED(CONFIG_DEBUG_PAGEALLOC) && debug_guardpage_enabled() && high < debug_guardpage_minorder()) { /* * Mark as guard pages (or page), that will allow to * merge back to allocator when buddy will be freed. * Corresponding page table entries will not be touched, * pages will stay not present in virtual address space */ set_page_guard(zone, &page[size], high, migratetype); continue; } list_add(&page[size].lru, &area->free_list[migratetype]); area->nr_free++; set_page_order(&page[size], high); } } 所需要的页面分配成功之后，__rmqueue()函数返回到这个内存块的起始页面struct page数据结构。回到buffered_rmqueue()函数，最后还需要利用zone_statistics()函数做一些统计数据的计算。 回到get_page_from_freelist()函数，最后还要通过prep_new_page()函数做一些有趣的检查，才能最终出厂。 [__alloc_page_nodemask()->get_page_from_freelist()->prep_new_page()->check_new_page()] /* * This page is about to be returned from the page allocator */ static inline int check_new_page(struct page *page) { const char *bad_reason = NULL; unsigned long bad_flags = 0; if (unlikely(page_mapcount(page))) bad_reason = "nonzero mapcount"; if (unlikely(page->mapping != NULL)) bad_reason = "non-NULL mapping"; if (unlikely(atomic_read(&page->_count) != 0)) bad_reason = "nonzero _count"; if (unlikely(page->flags & PAGE_FLAGS_CHECK_AT_PREP)) { bad_reason = "PAGE_FLAGS_CHECK_AT_PREP flag set"; bad_flags = PAGE_FLAGS_CHECK_AT_PREP; } #ifdef CONFIG_MEMCG if (unlikely(page->mem_cgroup)) bad_reason = "page still charged to cgroup"; #endif if (unlikely(bad_reason)) { bad_page(page, bad_reason, bad_flags); return 1; } return 0; } check_new_page()函数主要做如下的检查：

  • 刚分配的页面struct page的_macpcount计数应该为0。
  • 这是page->mapping为NULL。
  • 判断这是page的_count是否为0。注意alloc_page()分配的 _count为1，但这里为0，因为这个函数之后还调用set_page_refcounted()->set_page_count()，把 _count设置为1；
  • 检查PAGE_FLAGS_CHECK_AT_PREP标志位，这个flag在free_page时已经清除了，而这时该flag被设置，说明分配过程中有问题。

  上述检查都通过后，我们分配的页面就合格了，可以出厂了，页面page便开启了属于它的精彩生命周期。