思考题
-
请简述Linux内核在理想情况下页面分配器(page allocator)是如何分配出连续物理页面的。
答:linux内核分配连续物理页面调用alloc_pages函数,alloc_pages函数包含两个参数,1. 分配掩码,2. 伙伴系统的order。分配掩码又分为zone的修饰符和action修饰符,前者确定可以优先从哪个zone开始扫描,后者确定物理页面的迁移类型。根据得到的zone的序号/action/order,三个值,确定了分配的路径。如果在指定的zone/迁移类型/order上分配不到连续的物理页面,则会考虑从不同的zone,不同的迁移类型 和不同的order去分配物理页面。
-
在页面分配器中,如何从分配掩码(gfp_mask)中确定可以从哪些zone中分配内存?
答:gfp_mask的低4位用于确定分配的zone,但是在build zone的时候已经确定好了zone的顺序,一般优先从high -> normal->DMA32->DMA 这个顺序分配
-
页面分配器是按照什么方向来扫描zone的?
答:一般优先从high -> normal->DMA32->DMA 这个顺序分配
-
为用户进程分配物理内存,分配掩码应该选用GFP_KERNEL,还是GFP_HIGHUSER_MOVABLE呢?
答:应该选择GFP_HIGHUSER_MOVABLE,因为此宏分配的内存是可迁移的,而GFP_KERNEL,分配的是不可迁移的内存类型。
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,分配的页面个数只能是2的整数次幂。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()函数的参数有两个,一个是分配掩码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 /* 表示分配内存的请求可以中断,也就是说,调度器在请求期间可以随意选择另一个过程执行,
或者该请求可以被另一个更重要的事件中断。分配器还可以在返回内存之前,在队列上等待一个事件*/
#define ___GFP_HIGH 0x20u /*如果请求非常重要,则设置此标志,即内核急切地需要内存时,在分配内存失败可能给内存带来
严重后果时(比如威胁到系统稳定性或者系统崩溃),总是会使用该标志*/
#define ___GFP_IO 0x40u /*说明在查找空闲内存期间内核可以进行I/O操作,实际上,这意味着如果内核在内存分配期间换出页
那么仅当设置该标志时,才能将选择的页写入硬盘*/
#define ___GFP_FS 0x80u /*允许内核执行VFS操作,在与VFS层有联系的内核子系统中必须禁用,因为这可能引起递归调用。*/
#define ___GFP_COLD 0x100u /*如果需要分配不在CPU高速缓存中的冷页时,则设置此标志*/
#define ___GFP_NOWARN 0x200u /*在分配失败时禁止内核故障警告。在极少数场合该标志有用*/
#define ___GFP_REPEAT 0x400u /*在分配失败后自动重试,但在尝试若干次之后停止*/
#define ___GFP_NOFAIL 0x800u /*在分配失败后一直重试,直到成功*/
#define ___GFP_NORETRY 0x1000u
#define ___GFP_MEMALLOC 0x2000u
#define ___GFP_COMP 0x4000u
#define ___GFP_ZERO 0x8000u /*在分配成功时,将返回填充字节0的页面*/
#define ___GFP_NOMEMALLOC 0x10000u
#define ___GFP_HARDWALL 0x20000u /*只在NUMA系统上有意义。它限制只在分配当前进程的各个CPU所关联的结点分配内存。*/
#define ___GFP_THISNODE 0x40000u /*只有在NUMA系统上有意义。如果设置该比特位,则内存分配失败的情况下不允许使用其他结点作为备用*/
#define ___GFP_RECLAIMABLE 0x80000u
#define ___GFP_NOTRACK 0x200000u
#define ___GFP_NO_KSWAPD 0x400000u
#define ___GFP_OTHER_NODE 0x800000u
#define ___GFP_WRITE 0x1000000u
分配掩码在内核代码中分成两类,一类叫zone modifiers,另一类叫action modifiers。zone modifiers指定从哪个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__GFP_DMA __GFP_HIGHMEM __GFP_DMA32 __GFP_MOVABLE。
/*
* 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 */
下面以GFP_KERNEL为例,来看在理想情况下alloc_pages()函数是如何分配出物理内存的。
page = alloc_pages(GFP_KERNEL, order)
GFP_KERNEL分配掩码定义在gfp.h头文件中,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3个标志 即0x10 | 0x40 | 0x80 = 0xd0
alloc_pages()最终调用__alloc_pages_nodemask()函数,它是伙伴系统的核心函数。
alloc_pages()->alloc_pages_node()->__alloc_pages()->__alloc_pages_nodemask()
#define alloc_pages(gfp_mask, order) \
alloc_pages_node(numa_node_id(), gfp_mask, order)
static inline struct page *alloc_pages_node(int nid, gfp_t gfp_mask,
unsigned int order)
{
/* Unknown node is current node */
if (nid < 0)
nid = numa_node_id();
return __alloc_pages(gfp_mask, order, node_zonelist(nid, gfp_mask));
}
static inline struct page *
__alloc_pages(gfp_t gfp_mask, unsigned int order,
struct zonelist *zonelist)
{
return __alloc_pages_nodemask(gfp_mask, order, zonelist, NULL);
}
/*
* 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()数据从分配掩码中计算出zone的zoneidx,并存放在high_zoneidx成员中。
* 一般分配原则是从低成本内存到高成本内存,计算方法很奇怪,看不懂
*/
struct alloc_context ac = {
.high_zoneidx = gfp_zone(gfp_mask),
.nodemask = nodemask,
.migratetype = gfpflags_to_migratetype(gfp_mask),/*把gfp_mask分配掩码转换成MIGRATE_TYPES类型,
例如分配掩码为GFP_KERNEL,那么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.
*/
};
gfp_mask &= gfp_allowed_mask;
lockdep_trace_alloc(gfp_mask);
might_sleep_if(gfp_mask & __GFP_WAIT);
if (should_fail_alloc_page(gfp_mask, order))
return NULL;
/*
* Check the zones suitable for the gfp_mask contain at least one
* valid zone. It's possible to have an empty zonelist as a result
* of GFP_THISNODE and a memoryless node
*/
if (unlikely(!zonelist->_zonerefs->zone))
return NULL;
if (IS_ENABLED(CONFIG_CMA) && ac.migratetype == MIGRATE_MOVABLE)
alloc_flags |= ALLOC_CMA;
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;
/*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,
这个函数处理很多特殊场景,参见下面get_page_from_freelist实现*/
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;
}
get_page_from_freelist()是伙伴系统使用的另一个重要的辅助函数。它通过标志集和分配阶来判断是否能进行分配。如果可以,则发起实际的分配操作。
/*
* 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. cpuset用于绑定进程,提高效率
*/
/*
* 首先需要判断从哪个zone来分配内存,。for_each_zone_zonelist_nodemask 宏扫描内存结点中的zonelist去查找合适分配内存的zone。
* 扫描zonelist,寻找具有足够空闲空间的内存域。
*/
/* 首先解释ALLOC_*标志(cpuset_zone_allowed()是另外一个辅助函数,用于检查给定内存域是否属于该进程允许运行的CPU. zone_watermark_ok()接下来
** 检查所遍历到的内存域是否有足够的空闲页,并试图分配一个连续内存块。如果两个条件之一不满足,即或者没有足够的空闲页,或者没有连续内存块可满足分配请求,则
** 循环进行到备用列表中的下一个内存域,作同样的检查。
** 如果内存域适用于当前的分配请求,那么buffered_rmqueue()试图从中分配所需数目的页。
*/
for_each_zone_zonelist_nodemask(zone, z, zonelist, ac->high_zoneidx,
ac->nodemask) {
unsigned long mark;
if (IS_ENABLED(CONFIG_NUMA) && zlc_active &&
!zlc_zone_worth_trying(zonelist, z, allowednodes))
continue;
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;
mark = zone->watermark[alloc_flags & ALLOC_WMARK_MASK];
if (!zone_watermark_ok(zone, order, mark,
ac->classzone_idx, alloc_flags)) {
int ret;
/* Checked here to keep the fast path fast */
BUILD_BUG_ON(ALLOC_NO_WATERMARKS < NR_WMARK);
if (alloc_flags & ALLOC_NO_WATERMARKS)
goto try_this_zone;
if (IS_ENABLED(CONFIG_NUMA) &&
!did_zlc_setup && nr_online_nodes > 1) {
/*
* we do zlc_setup if there are multiple nodes
* and before considering the first zone allowed
* by the cpuset.
*/
allowednodes = zlc_setup(zonelist, alloc_flags);
zlc_active = 1;
did_zlc_setup = 1;
}
if (zone_reclaim_mode == 0 ||
!zone_allows_reclaim(ac->preferred_zone, zone))
goto this_zone_full;
/*
* As we may have just activated ZLC, check if the first
* eligible zone has failed zone_reclaim recently.
*/
if (IS_ENABLED(CONFIG_NUMA) && zlc_active &&
!zlc_zone_worth_trying(zonelist, z, allowednodes))
continue;
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;
}
this_zone_full:
if (IS_ENABLED(CONFIG_NUMA) && zlc_active)
zlc_mark_zone_full(zonelist, z);
}
/*
* The first pass makes sure allocations are spread fairly within the
* local node. However, the local node might have free pages left
* after the fairness batches are exhausted, and remote zones haven't
* even been considered yet. Try once more without fairness, and
* include remote zones now, before entering the slowpath and waking
* kswapd: prefer spilling to a remote zone over swapping locally.
*/
if (alloc_flags & ALLOC_FAIR) {
alloc_flags &= ~ALLOC_FAIR;
if (nr_fair_skipped) {
zonelist_rescan = true;
reset_alloc_batches(ac->preferred_zone);
}
if (nr_online_nodes > 1)
zonelist_rescan = true;
}
if (unlikely(IS_ENABLED(CONFIG_NUMA) && zlc_active)) {
/* Disable zlc cache for second zonelist scan */
zlc_active = 0;
zonelist_rescan = true;
}
if (zonelist_rescan)
goto zonelist_scan;
return NULL;
}
/**
* 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)) \
/* 此宏首先通过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()函数会调用next_zones_zonelist()函数来计算zoneref,最后返回 zone 数据结构。
/**
* 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;
}
/* Returns the next zone at or below highest_zoneidx in a zonelist */
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;
}
static inline int zonelist_zone_idx(struct zoneref *zoneref)
{
return zoneref->zone_idx;
}
计算zone的核心函数在next_zones_zonelist()函数中,这里zonelist_zone_idx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的编号zone_index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。因为Vexpress平台只有HIGHMEM和NORMAL.
再举一个例子,分配掩码为GFP_HIGHUSER_MOVABLE, GFP_HIGHUSER_MOVABLE包含了__GFP_HIGHMEM, 那么next_zones_zonelist函数会返回哪个zone呢?
GFP_HIGHUSER_MOVABLE值为0x200da, 那么gfp_zone(GFP_HIGHUSER_MOVABLE) 函数等于2,即highest_zoneidx为2, 而这个内存结点的第一个ZONE_HIGHME, 其zhone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有些复杂,但是这是正确理解以zone为基础的物理页面的分配机制的基石。
在__alloc_pages_nodemask()中调用first_zones_zonelist(),计算出preferred_zoneref并且保存到ac.classzone_idx 变量中,该变量在kswapd内存线程中还会用到。例如以GFP_KERNEL为分配掩码,preferred_zone指的是ZONE_NORMAL, ac.classzone_idx值为0.
理解上面的函数,需要理解一些辅助函数
首先我们需要定义一些函数使用的标志,用于控制到达各个水位指定的临界状态时的行为。
enum zone_watermarks {
WMARK_MIN,
WMARK_LOW,
WMARK_HIGH,
NR_WMARK
};
/* The ALLOC_WMARK bits are used as an index to zone->watermark */
#define ALLOC_WMARK_MIN WMARK_MIN /*使用pages_min 水位*/
#define ALLOC_WMARK_LOW WMARK_LOW /*使用pages_low 水位*/
#define ALLOC_WMARK_HIGH WMARK_HIGH /*使用pages_high 水位*/
#define ALLOC_NO_WATERMARKS 0x04 /* don't check watermarks at all 完全不检查水位*/
/* Mask to get the watermark bits */
#define ALLOC_WMARK_MASK (ALLOC_NO_WATERMARKS-1)
#define ALLOC_HARDER 0x10 /* try to alloc harder 试图更努力地分配,即放宽限制*/
#define ALLOC_HIGH 0x20 /* __GFP_HIGH set 设置了__GFP_HIGH*/
#define ALLOC_CPUSET 0x40 /* check for correct cpuset */
#define ALLOC_CMA 0x80 /* allow allocations from CMA areas */
#define ALLOC_FAIR 0x100 /* fair zone allocation 检查内存结点是否对应着指定的CPU集合*/
前几个标志表示在判断页是否可分配时,需要考虑哪些水位。默认情况下(即没有因其他因素带来的压力而需要更多的内存),只有内存域包含页的数目至少为zone->watermark[WMARK_HIGH]时,才能分配页。这对应于ALLOC_WMARK_HIGH标志。如果要使用较低(zone->watermark[WMARK_LOW])或最低(zone->watermark[WMARK_MIN])设置,则必须相应地设置ALLOC_WMARK_LOW或者ALLOC_WMARK_MIN。ALLOC_HARDER进一步放宽限制,最后,ALLOC_CPUSET告知内核,内存只能从当前进程允许的CPU相关联的内存结点分配,当然该选项只对NUMA系统有意义。
设置的标志在zone_watermark_ok()函数中检查,该函数根据设置的标志判断是否能从给定的内存域分配内存。
bool zone_watermark_ok(struct zone *z, unsigned int order, unsigned long mark,
int classzone_idx, int alloc_flags)
{
return __zone_watermark_ok(z, order, mark, classzone_idx, alloc_flags,
zone_page_state(z, NR_FREE_PAGES));
}
/*
* Return true if free pages are above 'mark'. This takes into account the order
* of the allocation.
如果可用页面超出标记(mark),这考虑了分配顺序
*/
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 free_pages可能变为负数,没有关系*/
long min = mark;/*mark表示水水位值*/
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 在下一阶,当前阶的页是不可用的*/
free_pages -= z->free_area[o].nr_free << o;
/* Require fewer higher order pages to be free 所需高阶空闲页的数目相对较少 */
min >>= 1;
if (free_pages <= min)
return false;
/*此循环的目的可以总结为:
依次循环,检查内存中是否有足够多的大块(即order比较高)空闲内存。
每次循环处理中,先把当前order的free page从总的free pages中减去,因为我们是看是否有足够多
的大块内存。既然已经把free pages中的一部分已经划掉了,比较标准也应该相应放宽。
放宽多少,就是对应min右移多少来决定。
例子:如果请求分配的order 是1, 还有100个free pages,其中order 0的有96 pages,order 1 的有 4 pages,处理后的min是16
这样在第一轮循环中,free_pages即变为4,min 假设右移了1位则为8,这样判断下来不满足watermark要求。
如果将要求放宽,即将min右移4位,这样第一轮循环中min变为1,free pages满足watermark要求。
*/
}
return true;
}
zone_page_state(z, NR_FREE_PAGES)用来得到空闲页的数目。
在解释了ALLOC_HIGH和ALLOC_HARDER标志后(将最小值标记降低到当前值的1/2或1/4,使分配过程努力或更加努力),该函数会检查空闲页的数目是否小于最小值与lowmem_reserve中指定的紧急分配值之和。如果不小于,则代码遍历所有小于当前阶的分配阶,从frea_pages减去当前分配阶的所有空闲页(左移o位是必要的,因为nr_free记载的时当前分配阶的空闲页块数目,而非单页的数目)。同时,每升高一阶,所需空闲页的最小值折半。如果内核遍历所有低端内存域之后,发现内存不足,则不进行内存分配。
系统中定义的三个水位(WMARK_MIN/WMARK_LOW/WMARK_HIGH)。watermark水位的计算在__setup_per_zone_wmarks()函数中.
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,它是系统启动时通过系统空闲页面的数量来计算的,具体计算在init_per_zone_wmark_min()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",后续伙伴系统和kswapd内核线程会用到。
我们假设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。
如果内存找到适当的内存域,具有足够的空闲页可供分配,那么还有两件事情需要完成。首先它必须检查这些页是否是连续的(到目前为止,只知道有许多空闲页)。其次,必须按伙伴系统的方式从free_lists移除这些页,这可能需要分解并重排内存区。
内核将该工作委托给buffered_rmqueue()函数. 改函数必需各个步骤如下:
__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);/*是否指定冷页*/
if (likely(order == 0)) {/*分配单页*/
struct per_cpu_pages *pcp;
struct list_head *list;
local_irq_save(flags);/*禁止本地CPU中断,禁止前保存中断状态*/
pcp = &this_cpu_ptr(zone->pageset)->pcp;/*获取到cpu高速缓存*/
list = &pcp->lists[migratetype];/*根据迁移类型,得到高速缓存的freelist*/
if (list_empty(list)) {/*空的,高速缓存没有数据,这可能是上次获取的cpu高速缓存迁移类型和这次不一样*/
/*下面查看rmqueue_bulk()函数实现*/
pcp->count += rmqueue_bulk(zone, 0,
pcp->batch, list,
migratetype, cold);/*该函数向高速缓存添加内存页,从伙伴系统中得到页,然后填充到cpu高速缓存中, batch:批量*/
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;
}
如果只分配一页,内核会进行优化,即分配为0的情况,2^0 = 1。该页不是从伙伴系统直接取得,而是取自per-CPU的页缓存((深入Linux内核架构 184页)回想一下,可知该缓存提供了CPU本地的热页和冷页的列表,zone->pageset是一个数组,用于实现每个CPU的热/冷页帧列表,内核使用这些列表来保存可用于满足实现的"新鲜"页。但冷热页帧对应的高速缓存状态不同:有些页帧也很可能仍然在高速缓存中,因此可以快速访问,故称为热的;未缓存的页帧与此相对,故称之为冷的)。
分配1页的情况:
如果分配标志设置了GFP_COLD,那么必须从per-CPU缓存取得冷页,前提是有的话。
rmqueue_bulk()函数实现
[__alloc_pages_nodemask()->get_page_from_freelist()->buffered_rmqueue()->rmqueue_bulk()]
/*
* Obtain a specified number of elements from the buddy allocator, all under
* a single hold of the lock, for efficiency. Add them to the supplied list.
* Returns the number of new pages which were placed at *list.
*/
static int rmqueue_bulk(struct zone *zone, unsigned int order,
unsigned long count, struct list_head *list,
int migratetype, bool cold)
{
int i;
spin_lock(&zone->lock);
for (i = 0; i < count; ++i) {/*一个页面一个页面处理*/
/*下面查看__rmqueue()函数实现*/
struct page *page = __rmqueue(zone, order, migratetype);/*分配到指定迁移类型的内存页*/
if (unlikely(page == NULL))
break;
/*
* Split buddy pages returned by expand() are received here
* in physical page order. The page is added to the callers and
* list and the list head then moves forward. From the callers
* perspective, the linked list is ordered by page number in
* some conditions. This is useful for IO devices that can
* merge IO requests if the physical pages are ordered
* properly.
*/
if (likely(!cold))
list_add(&page->lru, list);/*如果是冷页,则添加到链表头*/
else
list_add_tail(&page->lru, list);/*否则添加到链表尾部*/
list = &page->lru;
if (is_migrate_cma(get_freepage_migratetype(page)))
__mod_zone_page_state(zone, NR_FREE_CMA_PAGES,
-(1 << order));
}
__mod_zone_page_state(zone, NR_FREE_PAGES, -(i << order));/*修改空闲页面的计数*/
spin_unlock(&zone->lock);
return i;/*返回添加到cpu高速缓存链表的页面个数*/
}
当分配多页情况时,下面函数和分配一页的情况都是调用的函数:
__rmqueue()函数实现
[__alloc_pages_nodemask()->get_page_from_freelist()->buffered_rmqueue()->rmqueue_bulk()->__rmqueue()]
/*
* Do the hard work of removing an element from the buddy allocator.
* Call me with the zone->lock already held.
分配指定迁移类型的内存页
*/
static struct page *__rmqueue(struct zone *zone, unsigned int order,
int migratetype)
{
struct page *page;
retry_reserve:
/*下面查看此函数实现*/
page = __rmqueue_smallest(zone, order, migratetype);/*常规情况下,从zone上分配指定的迁移类型的内存页,根据传递进来
的分配阶、用于获取页的内存域、迁移类型,来扫描页的列表,直到找到适当的连续内存块。*/
if (unlikely(!page) && migratetype != MIGRATE_RESERVE) {/*上面没有分配的内存页,并且不是紧急的迁移类型*/
page = __rmqueue_fallback(zone, order, migratetype);/*尝试其他的迁移列表,作为应急措施*/
/*
* Use MIGRATE_RESERVE rather than fail an allocation. goto
* is used because __rmqueue_smallest is an inline function
* and we want just one call site
*/
if (!page) {/*没有成功,则把迁移类型调整为MIGRATE_RESERVE表示是紧急分配*/
migratetype = MIGRATE_RESERVE;
goto retry_reserve;
}
}
trace_mm_page_alloc_zone_locked(page, order, migratetype);
return page;
}
__rmqueue_smallest()函数实现
[__alloc_pages_nodemask()->get_page_from_freelist()->buffered_rmqueue()->rmqueue_bulk()->__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 在首选的列表中找到适当大小的页,
小的内存区无用,因为分配的页必须是连续的。我们知道给定分配阶的所有页又再分成对应于不同迁移类型的列表,
在其中需要选择正确的一项。
检查适当大小的内存块非常简单。如果检查的列表中有一个元素,那么它就是可用的,因为其中包含了所需数目的连续页。否则
内核将选择下一个更高分配阶,并进行类似的搜索。
*/
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);/*设置属性,清除buddy标识,也就是设置page->_mapcount = -1*/
area->nr_free--;/*在用list_del从链表移除一个内存块之后,要注意,必须将struct free_area的nr_free成员减1*/
/*下面查看expand()函数实现*/
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中空闲链表,如果zone的当前order对应的空闲区free_area中相应migratetype类型的链表没有空闲对象,那么就会查找下一级order。
为什么会这样?因为在系统启动时,空闲页面会尽可能地都分配到MAX_ORDER-1的链表中,这个可以在系统刚起来之后,通过"cat /proc/pagetypeinfo"命令看出端倪。当找到某一个order的空闲区中对应的migratetype类型的空闲链表中有空闲内存块时,就会从中把一个内存块摘取下来,然后调用expand()函数来"切蛋糕"。因为通常摘下来的内存块要比需要的内存大,切完之后需要把剩下的内存块重新放回伙伴系统中。
get_page_from_freelist()->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
*/
/* 该函数使用了一组桉树,page、zone、area的语义都很显然。index指定了该伙伴对在分配位图中的索引位置,low是预期的分配阶,
high表示内存取自哪个分配阶。migratetype表示迁移类型。*/
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);
}
}
最好逐步看一下代码,理解其工作方式。我们假定一下情况:将要分配一个阶为3的块。内存中没有该长度的块,因此内核选择了一个阶为5的块。因此调用该函数的参数如下:
expand(zone, page, low = 3, high = 5, area, migratetype)
如果在特定的迁移类型列表上没有连续内存区可用,则__rmqueue_smallest()返回NULL指针。内核接下来根据备用次序,尝试使用其他迁移类型的列表满足分配请求。该任务委托给__rmqueue_fallback。迁移类型的备用次序在fallbacks数组定义。fallbacks:后备
内核总是使用特定于迁移类型的free_area列表,在处理期间不会改变页的迁移类型。(上图有些错误,最下面mem_map,应该是page指向的是8页,所以最后两格应该是白色,最前面一格应该是浅灰色,然后再分割成两格(每格8页))
-
size的值初始化为2^5 = 32.分配的内存区已经在__rmqueue中从free_area列表移除,因此在上图虚线部分已经画出。
-
在第一遍循环中,内核切换到低一个分配阶、迁移类型相同的free_area列表,即阶为4。类似地,内存区长度降低到16(通过size>>1 计算)。初始内存区的后一半插入到阶为4的free_area列表中。伙伴系统只要内存区第一个page实例,用作管理用途。内存区的长度可根据页所在的列表自动推导而得
-
后一半内存区的地址可以通过&page[size]计算。而page指针一直指向最初分配内存区的起始地址,并不改变。page指针指向的位置如上图中用箭头表示。
-
下一遍循环将剩余16页的后一半放置到对应于size = 8 的free_area列表上,page指针仍然不动。现在剩余的内存区已经是预期长度,可以将page指针作为结果返回。从上图可见,显然使用了初始页内存的起始8页。所有其余各页都进入到伙伴系统中适当的free_area列表里。
内核总是使用特定于迁移类型的free_area列表,在处理期间不会改变页的迁移类型。(上图有些错误,最下面mem_map,应该是page指向的是8页,所以最后两格应该是白色,最前面一格应该是浅灰色,然后再分割成两格(每格8页))
如果在特定的迁移类型列表上没有连续内存区可用,则__rmqueue_smallest()返回NULL指针。内核接下来根据备用次序,尝试使用其他迁移类型的列表满足分配请求。该任务委托给__rmqueue_fallback。迁移类型的备用次序在fallbacks数组定义。fallbacks:后备
/*
* This array describes the order lists are fallen back to when
* the free lists for the desirable migrate type are depleted
*/
static int fallbacks[MIGRATE_TYPES][4] = {
[MIGRATE_UNMOVABLE] = { MIGRATE_RECLAIMABLE, MIGRATE_MOVABLE, MIGRATE_RESERVE },
[MIGRATE_RECLAIMABLE] = { MIGRATE_UNMOVABLE, MIGRATE_MOVABLE, MIGRATE_RESERVE },
#ifdef CONFIG_CMA
[MIGRATE_MOVABLE] = { MIGRATE_CMA, MIGRATE_RECLAIMABLE, MIGRATE_UNMOVABLE, MIGRATE_RESERVE },
[MIGRATE_CMA] = { MIGRATE_RESERVE }, /* Never used */
#else
[MIGRATE_MOVABLE] = { MIGRATE_RECLAIMABLE, MIGRATE_UNMOVABLE, MIGRATE_RESERVE },
#endif
[MIGRATE_RESERVE] = { MIGRATE_RESERVE }, /* Never used */
#ifdef CONFIG_MEMORY_ISOLATION
[MIGRATE_ISOLATE] = { MIGRATE_RESERVE }, /* Never used */
#endif
};
首先,函数再一次遍历各个分配阶的列表:
/* Remove an element from the buddy allocator from the fallback list
*/
/*但不只是相同的迁移类型,还要考虑备用列表中指定的不同迁移类型。请注意:该函数会按照分配阶从大到小遍历!
这与通常的策略相反(除了MIGRATE_RESERVER),内核的策略是,如果无法避免分配迁移类型不同的内存块,那么就分配一个尽可能大的内存块。
如果优先选择更小的内存块,则会向其他列表引入碎片,因为不同迁移类型的内存块将会混合起来,这显然不是我们想要的。
特别列表MIGRATE_RESERVE包含了用于紧急分配的内存,需要特殊处理。如果当前考虑的迁移类型对应的空闲列表包含空闲内存块,则从该列表分配内存*/
static inline struct page *
__rmqueue_fallback(struct zone *zone, unsigned int order, int start_migratetype)
{
struct free_area *area;
unsigned int current_order;
struct page *page;
/* Find the largest possible block of pages in the other list
在其他类型列表中找到最大可能的内存块
*/
for (current_order = MAX_ORDER-1;
current_order >= order && current_order <= MAX_ORDER-1;
--current_order) {/*这是和指定迁移类型的遍历不一样,这里从最大阶开始比遍历,就是为了防止内存碎片*/
int i;
for (i = 0;; i++) {
int migratetype = fallbacks[start_migratetype][i];
int buddy_type = start_migratetype;
/* MIGRATE_RESERVE handled later if necessary */
if (migratetype == MIGRATE_RESERVE)
break;
area = &(zone->free_area[current_order]);/*得到高阶空闲数组元素*/
if (list_empty(&area->free_list[migratetype])) /*如果对应阶上的对应迁移类型的空闲页链表是空的,则循环找备用迁移类型的空闲链表*/
continue;
page = list_entry(area->free_list[migratetype].next,
struct page, lru);/*如果找到了空闲页块,则当前阶上的空闲页块递减*/
area->nr_free--;
if (!is_migrate_cma(migratetype)) {/*不是CMA区域*/
try_to_steal_freepages(zone, page,
start_migratetype,
migratetype);
} else {
/*
* When borrowing from MIGRATE_CMA, we need to
* release the excess buddy pages to CMA
* itself, and we do not try to steal extra
* free pages.
*/
buddy_type = migratetype;
}
/* Remove the page from the freelists */
list_del(&page->lru);
rmv_page_order(page);/*清楚buddy的标识,标识该page将不是buddy系统的了*/
expand(zone, page, order, current_order, area,
buddy_type);
/*
* The freepage_migratetype may differ from pageblock's
* migratetype depending on the decisions in
* try_to_steal_freepages(). This is OK as long as it
* does not differ for MIGRATE_CMA pageblocks. For CMA
* we need to make sure unallocated pages flushed from
* pcp lists are returned to the correct freelist.
*/
set_freepage_migratetype(page, buddy_type);
trace_mm_page_alloc_extfrag(page, order, current_order,
start_migratetype, migratetype);
return page;
}
}
return NULL;
}
/*
* When we are falling back to another migratetype during allocation, try to
* steal extra free pages from the same pageblocks to satisfy further
* allocations, instead of polluting multiple pageblocks.
*
* If we are stealing a relatively large buddy page, it is likely there will
* be more free pages in the pageblock, so try to steal them all. For
* reclaimable and unmovable allocations, we steal regardless of page size,
* as fragmentation caused by those allocations polluting movable pageblocks
* is worse than movable allocations stealing from unmovable and reclaimable
* pageblocks.
*
* If we claim more than half of the pageblock, change pageblock's migratetype
* as well.
*/
static void try_to_steal_freepages(struct zone *zone, struct page *page,
int start_type, int fallback_type)
{
int current_order = page_order(page);
/* Take ownership for orders >= pageblock_order 较大内存块有多大的概念由全局变量pageblock_order给出
该变量定义了大内存块分配阶,如果需要分解来自其他迁移列表的空闲内存块,那么内核必须决定如何处理剩余的页。
如果剩余部分也是一个比较大的内存块,那么将整个内存块都转到当前分配类型对应的迁移列表是有意义的,这样可以减少碎片。
如果是在分配可回收内存,那么内核在将空闲页从一个迁移列表移动另一个时,会更加积极。
此类分配经常猝发涌现,导致许多小的可回收内存块散布到所有的迁移列表。为了避免此类情况,分配MIGRATE_RECLAIMABLE内存块时,
剩余的页总是转移到可回收迁移列表。*/
if (current_order >= pageblock_order) { //pageblock_order = (MAX_ODRER-1)
change_pageblock_range(page, current_order, start_type);
return;
}
if (current_order >= pageblock_order / 2 || /*大内存块,则全部转到start_migratetype类型下*/
start_type == MIGRATE_RECLAIMABLE || /*可回收内存页,就迁移类型转换时,会更加积极*/
start_type == MIGRATE_UNMOVABLE ||
page_group_by_mobility_disabled) {
int pages;
pages = move_freepages_block(zone, page, start_type);/*把这些页面转换到start_migratetype迁移类型下面去*/
/* Claim the whole block if over half of it is free */
if (pages >= (1 << (pageblock_order-1)) ||
page_group_by_mobility_disabled)
set_pageblock_migratetype(page, start_type);/*这里是设置整个页面的迁移类型,上面move_freepages_block函数是设置每个页的迁移类型*/
}
}
/*就是将一堆(pageblock大小)的page移动到migratetype类型的链表中*/
int move_freepages_block(struct zone *zone, struct page *page,
int migratetype)
{
unsigned long start_pfn, end_pfn;
struct page *start_page, *end_page;
start_pfn = page_to_pfn(page);/*页帧号*/
/*pageblock_nr_pages是迁移类型认为大阶所对应的页数, pageblock_nr_pages = (1UL << pageblock_order) = 1024*/
start_pfn = start_pfn & ~(pageblock_nr_pages-1);
start_page = pfn_to_page(start_pfn);
/*准备迁移pageblock_nr_pages个页面,一般要转换迁移类型的话,就转换pageblock_br_pages个连续页面,这样会减少内存碎片*/
end_page = start_page + pageblock_nr_pages - 1;
end_pfn = start_pfn + pageblock_nr_pages - 1;
/* Do not cross zone boundaries */
if (!zone_spans_pfn(zone, start_pfn))
start_page = page;
if (!zone_spans_pfn(zone, end_pfn))/*判断要迁移的内存区是否在一个zone上,不能交错zone*/
return 0;
return move_freepages(zone, start_page, end_page, migratetype);/*把要转换迁移类型的内存页面地址范围给move_freepages()进行转换*/
}
/*
* Move the free pages in a range to the free lists of the requested type.
* Note that start_page and end_pages are not aligned on a pageblock
* boundary. If alignment is required, use move_freepages_block()
*/
int move_freepages(struct zone *zone,
struct page *start_page, struct page *end_page,
int migratetype)
{
struct page *page;
unsigned long order;
int pages_moved = 0;
#ifndef CONFIG_HOLES_IN_ZONE
/*
* page_zone is not safe to call in this context when
* CONFIG_HOLES_IN_ZONE is set. This bug check is probably redundant
* anyway as we check zone boundaries in move_freepages_block().
* Remove at a later date when no bug reports exist related to
* grouping pages by mobility
*/
VM_BUG_ON(page_zone(start_page) != page_zone(end_page));
#endif
for (page = start_page; page <= end_page;) {
/* Make sure we are not inadvertently changing nodes */
VM_BUG_ON_PAGE(page_to_nid(page) != zone_to_nid(zone), page);
if (!pfn_valid_within(page_to_pfn(page))) {
page++;
continue;
}
if (!PageBuddy(page)) {/*现在页还是伙伴系统的*/
page++;
continue;
}
order = page_order(page);//得到阶
list_move(&page->lru,
&zone->free_area[order].free_list[migratetype]);//把这些页搬迁到指定迁移类型对应的链表上
set_freepage_migratetype(page, migratetype);/*设置这些页的迁移类型 page->index = migratetype*/
page += 1 << order;/*一下子就转换了2^order个页面*/
pages_moved += 1 << order;
}
return pages_moved;/*把范围内的页都迁移完,返回实际迁移了多少页*/
}
所需求的页面分配成功后,__rmqueue()函数返回这个内存块的起始页面的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()函数中,最后还要通过prep_new_page()函数做一些有趣的检查,才能出厂。
static int prep_new_page(struct page *page, unsigned int order, gfp_t gfp_flags,
int alloc_flags)
{
int i;
for (i = 0; i < (1 << order); i++) {
struct page *p = page + i;
if (unlikely(check_new_page(p)))
return 1;
}
set_page_private(page, 0);
set_page_refcounted(page);
arch_alloc_page(page, order);
kernel_map_pages(page, 1 << order, 1);
kasan_alloc_pages(page, order);
if (gfp_flags & __GFP_ZERO)
prep_zero_page(page, order, gfp_flags);
if (order && (gfp_flags & __GFP_COMP))
prep_compound_page(page, order);
set_page_owner(page, order, gfp_flags);
/*
* page->pfmemalloc is set when ALLOC_NO_WATERMARKS was necessary to
* allocate the page. The expectation is that the caller is taking
* steps that will free more memory. The caller should avoid the page
* being used for !PFMEMALLOC purposes.
*/
page->pfmemalloc = !!(alloc_flags & ALLOC_NO_WATERMARKS);
return 0;
}
/*
* 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))) /*刚分配页面的struct page的_mapcount计数应该为0*/
bad_reason = "nonzero mapcount";
if (unlikely(page->mapping != NULL)) /*这时page->mapping 为NULL*/
bad_reason = "non-NULL mapping";
if (unlikely(atomic_read(&page->_count) != 0)) /*判断这时page的_count是否为0.注意alloc_pages()分配的page的_count应该为1,但是这里为0,因为这个函数之后还调用了
set_page_refcounted()->set_page_count(),把_count设置为1*/
bad_reason = "nonzero _count";
if (unlikely(page->flags & PAGE_FLAGS_CHECK_AT_PREP)) { /*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。*/
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;
}