内核:arm64 kernel-5.0
梳理代码流程要先明白输入和输出,输入一般有参数,输出一般有return 返回的内容以及一些输出的参数,内存回收是在内存分配的过程中产生的,所以先简单看下内存分配的流程。
alloc_pages_nodemask
函数原型
struct page *
__alloc_pages_nodemask(gfp_t gfp_mask, unsigned int order, int preferred_nid,
nodemask_t *nodemask)
参数
其参数来源于驱动层,比如块设备驱动层调用blk_alloc_queue_node(GFP_KERNEL, set->numa_node)分配一个request_queue。blk_alloc_queue_node–>kmem_cache_alloc_node–>slab_alloc_node–>____cache_alloc–>cache_alloc_refill–>cache_grow_begin–>kmem_getpages–>__alloc_pages_node–>__alloc_pages–>alloc_pages_nodemask
此时参数中的gfp_mask为GFP_KERNEL,nodemask为NULL。
#define GFP_KERNEL (__GFP_RECLAIM | __GFP_IO | __GFP_FS)
#define __GFP_RECLAIM ((__force gfp_t)(___GFP_DIRECT_RECLAIM|___GFP_KSWAPD_RECLAIM))
#define ___GFP_DIRECT_RECLAIM 0x200000u
#define ___GFP_KSWAPD_RECLAIM 0x400000u
#define ___GFP_IO 0x40u
#define ___GFP_FS 0x80u
可知GFP_KERNEL 为 0x6000C0
流程
{
struct page *page;
unsigned int alloc_flags = ALLOC_WMARK_LOW;
gfp_t alloc_mask; /* The gfp_t that was actually used for allocation */
struct alloc_context ac = { };
if (unlikely(order >= MAX_ORDER)) {
WARN_ON_ONCE(!(gfp_mask & __GFP_NOWARN));
return NULL;
}
gfp_mask &= gfp_allowed_mask;
alloc_mask = gfp_mask;
if (!prepare_alloc_pages(gfp_mask, order, preferred_nid, nodemask, &ac, &alloc_mask, &alloc_flags))
return NULL;
finalise_ac(gfp_mask, &ac);
alloc_flags |= alloc_flags_nofragment(ac.preferred_zoneref->zone, gfp_mask);/*gfs_mask中___GFP_KSWAPD_RECLAIM被置位的情况下,
alloc_flags中ALLOC_KSWAPD会被置位,表示运行唤醒kswapd,用于防止内存碎片化。*/
page = get_page_from_freelist(alloc_mask, order, alloc_flags, &ac);
if (likely(page))
goto out;
alloc_mask = current_gfp_context(gfp_mask);
ac.spread_dirty_pages = false;
if (unlikely(ac.nodemask != nodemask))
ac.nodemask = nodemask;
page = __alloc_pages_slowpath(alloc_mask, order, &ac);
out:
if (memcg_kmem_enabled() && (gfp_mask & __GFP_ACCOUNT) && page &&
unlikely(memcg_kmem_charge(page, gfp_mask, order) != 0)) {
__free_pages(page, order);
page = NULL;
}
trace_mm_page_alloc(page, order, alloc_mask, ac.migratetype);
return page;
}
整体流程比较简单,将alloc_flags初始化为ALLOC_WMARK_LOW,在prepare_alloc_pages和finalise_ac中填充ac。先尝试快速分配,分配不成功则进入慢速路径。
prepare_alloc_pages
prepare_alloc_pages(gfp_mask, order, preferred_nid, nodemask, &ac, &alloc_mask, &alloc_flags)
{
ac->high_zoneidx = gfp_zone(gfp_mask);
ac->zonelist = node_zonelist(preferred_nid, gfp_mask);
ac->nodemask = nodemask;
ac->migratetype = gfpflags_to_migratetype(gfp_mask);
if (cpusets_enabled()) {
*alloc_mask |= __GFP_HARDWALL;
if (!ac->nodemask)
ac->nodemask = &cpuset_current_mems_allowed;
else
*alloc_flags |= ALLOC_CPUSET;
}
fs_reclaim_acquire(gfp_mask);
fs_reclaim_release(gfp_mask);
might_sleep_if(gfp_mask & __GFP_DIRECT_RECLAIM);
if (should_fail_alloc_page(gfp_mask, order))
return false;
if (IS_ENABLED(CONFIG_CMA) && ac->migratetype == MIGRATE_MOVABLE)
*alloc_flags |= ALLOC_CMA;
return true;
}
ac->high_zoneidx = gfp_zone(gfp_mask);
/*根据gfp_mask低4位的情况确定high_zoneidx,GFP_KERNEL获取到的为1,
//具体计算方式参考 https://blog.csdn.net/qqqqqq999999/article/details/90045500*/
ac->zonelist = node_zonelist(preferred_nid, gfp_mask);
//获取节点的zonelist,这里再numa的情况下区分ZONELIST_NOFALLBACK和ZONELIST_FALLBACK,本文的讨论都以没有定义CONFIG_NUMA进行说明。
//zonelist在系统初始化时通过build_zonelists完成,将各个zone按zone_type反向排列起来,假设有DMA32、NORMAL二个zone,那么在zonelist中就表示为:zonerefs[0]->zone_idx=1(ZONE_NORMAL) zonerefs[1]->zone_idx=0(ZONE_DMA32)
ac->nodemask = nodemask; //NULL
ac->migratetype = gfpflags_to_migratetype(gfp_mask);
//获取gfp_mask的3、4位(从0开始),GFP_KERNEL的情况得到的结果是0,即迁移类型为MIGRATE_UNMOVABLE
finalise_ac
finalise_ac(gfp_mask, &ac);
{
ac->spread_dirty_pages = (gfp_mask & __GFP_WRITE); //false
ac->preferred_zoneref = first_zones_zonelist(ac->zonelist,
ac->high_zoneidx, ac->nodemask);
}
first_zones_zonelist返回zone->idx小于等于high_zoneidx的第一个zoneref,本情况下即zoneref[0] (zone_normal)。
get_page_from_freelist
函数原型
static struct page *
get_page_from_freelist(gfp_t gfp_mask, unsigned int order, int alloc_flags,
const struct alloc_context *ac)
此时参数中gfp_mask为GFP_KERNEL(0x6000C0), alloc_flags为0x201(低水位,运行唤醒kswapd)
{
struct zoneref *z;
struct zone *zone;
struct pglist_data *last_pgdat_dirty_limit = NULL;
bool no_fallback;
retry:
no_fallback = alloc_flags & ALLOC_NOFRAGMENT; //0
z = ac->preferred_zoneref; //zone_normal
for_next_zone_zonelist_nodemask(zone, z, ac->zonelist, ac->high_zoneidx,
ac->nodemask) { //遍历zonelist
struct page *page;
unsigned long mark;
if (cpusets_enabled() &&
(alloc_flags & ALLOC_CPUSET) &&
!__cpuset_zone_allowed(zone, gfp_mask))
continue;
if (ac->spread_dirty_pages) { //为false,跳过
if (last_pgdat_dirty_limit == zone->zone_pgdat)
continue;
if (!node_dirty_ok(zone->zone_pgdat)) {
last_pgdat_dirty_limit = zone->zone_pgdat;
continue;
}
}
if (no_fallback && nr_online_nodes > 1 && //no_fallback为0,跳过
zone != ac->preferred_zoneref->zone) {
int local_nid;
local_nid = zone_to_nid(ac->preferred_zoneref->zone);
if (zone_to_nid(zone) != local_nid) {
alloc_flags &= ~ALLOC_NOFRAGMENT;
goto retry;
}
}
//当前mark为low水位
mark = wmark_pages(zone, alloc_flags & ALLOC_WMARK_MASK);
if (!zone_watermark_fast(zone, order, mark,
ac_classzone_idx(ac), alloc_flags)) {
int ret;
#ifdef CONFIG_DEFERRED_STRUCT_PAGE_INIT
/*
* Watermark failed for this zone, but see if we can
* grow this zone if it contains deferred pages.
*/
if (static_branch_unlikely(&deferred_pages)) {
if (_deferred_grow_zone(zone, order))
goto try_this_zone;
}
#endif
/* 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 (node_reclaim_mode == 0 || //默认为0,且只有config_numa的情况下有此节点
!zone_allows_reclaim(ac->preferred_zoneref->zone, zone))
continue;
//进行内存回收
ret = node_reclaim(zone->zone_pgdat, gfp_mask, order);
switch (ret) {
case NODE_RECLAIM_NOSCAN:
/* did not scan */
continue;
case NODE_RECLAIM_FULL:
/* scanned but unreclaimable */
continue;
default:
/* did we reclaim enough */
if (zone_watermark_ok(zone, order, mark,
ac_classzone_idx(ac), alloc_flags))
goto try_this_zone;
continue;
}
}
try_this_zone:
page = rmqueue(ac->preferred_zoneref->zone, zone, order,
gfp_mask, alloc_flags, ac->migratetype);
if (page) {
prep_new_page(page, order, gfp_mask, alloc_flags);
if (unlikely(order && (alloc_flags & ALLOC_HARDER)))
reserve_highatomic_pageblock(page, zone, order);
return page;
} else {
#ifdef CONFIG_DEFERRED_STRUCT_PAGE_INIT
/* Try again if zone has deferred pages */
if (static_branch_unlikely(&deferred_pages)) {
if (_deferred_grow_zone(zone, order))
goto try_this_zone;
}
#endif
}
}
if (no_fallback) {
alloc_flags &= ~ALLOC_NOFRAGMENT;
goto retry;
}
return NULL;
}
node_dirty_ok
计算脏页和正在回写的页是否小于limit
bool node_dirty_ok(struct pglist_data *pgdat)
{
unsigned long limit = node_dirty_limit(pgdat);
unsigned long nr_pages = 0;
nr_pages += node_page_state(pgdat, NR_FILE_DIRTY);
nr_pages += node_page_state(pgdat, NR_UNSTABLE_NFS);
nr_pages += node_page_state(pgdat, NR_WRITEBACK);
return nr_pages <= limit;
}
node_dirtyable_memory返回(该节点中所有zone的空闲页+节点的文件页-节点的预留内存)
static unsigned long node_dirtyable_memory(struct pglist_data *pgdat)
{
unsigned long nr_pages = 0;
int z;
for (z = 0; z < MAX_NR_ZONES; z++) {
struct zone *zone = pgdat->node_zones + z;
if (!populated_zone(zone))
continue;
nr_pages += zone_page_state(zone, NR_FREE_PAGES);
}
/*
* Pages reserved for the kernel should not be considered
* dirtyable, to prevent a situation where reclaim has to
* clean pages in order to balance the zones.
*/
/totalreserve_pages的计算方式?/
nr_pages -= min(nr_pages, pgdat->totalreserve_pages);
nr_pages += node_page_state(pgdat, NR_INACTIVE_FILE);
nr_pages += node_page_state(pgdat, NR_ACTIVE_FILE);
return nr_pages;
}
根据vm_dirty_bytes(先使用)和vm_dirty_ratio计算脏页限制,如果当前进程时实时进程dirty*1.25。
static unsigned long node_dirty_limit(struct pglist_data *pgdat)
{
unsigned long node_memory = node_dirtyable_memory(pgdat);
struct task_struct *tsk = current;
unsigned long dirty;
if (vm_dirty_bytes)
dirty = DIV_ROUND_UP(vm_dirty_bytes, PAGE_SIZE) *
node_memory / global_dirtyable_memory();
else
dirty = vm_dirty_ratio * node_memory / 100;
if (tsk->flags & PF_LESS_THROTTLE || rt_task(tsk))
dirty += dirty / 4;
return dirty;
}
zone_watermark_fast
函数原型
static inline bool zone_watermark_fast(struct zone *z, unsigned int order,
unsigned long mark, int classzone_idx, unsigned int alloc_flags)
z是当前遍历到的zone,mark此时为low对于内存,classzone_idx为首选zone对应的idx,此时为1
{
long free_pages = zone_page_state(z, NR_FREE_PAGES);
long cma_pages = 0;
#ifdef CONFIG_CMA
/* If allocation can't use CMA areas don't use free CMA pages */
if (!(alloc_flags & ALLOC_CMA)) //此时alloc_flags中ALLOC_CMA(0X80)没有置位
cma_pages = zone_page_state(z, NR_FREE_CMA_PAGES);
#endif
if (!order && (free_pages - cma_pages) > mark + z->lowmem_reserve[classzone_idx])
return true;
return __zone_watermark_ok(z, order, mark, classzone_idx, alloc_flags,
free_pages);
}
对于单个页面的情况做快速处理,如果当前zone的(空闲页-空闲cma )大于 (low水位+当前zone对于推荐zone的预留内存)则返回true。
每个zone有一个lowmem_reserve数组,用于防止高端zone过多地使用低端zone的内存。比如推荐的zone是normal,idx为1,那么当此时正在遍历的zone为dma32时,计算水位是否满足时就要保证空闲页大于low水位加dma32的lowmem_reserve1的值。
bool __zone_watermark_ok(struct zone *z, unsigned int order, unsigned long mark,
int classzone_idx, unsigned int alloc_flags,
long free_pages)
{
long min = mark;
int o;
const bool alloc_harder = (alloc_flags & (ALLOC_HARDER|ALLOC_OOM));
/* free_pages may go negative - that's OK */
free_pages -= (1 << order) - 1;
if (alloc_flags & ALLOC_HIGH) //高优先级进程
min -= min / 2;
if (likely(!alloc_harder)) {
free_pages -= z->nr_reserved_highatomic;
} else {
if (alloc_flags & ALLOC_OOM) //当前进程是oom的受害者
min -= min / 2;
else
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_pages -= zone_page_state(z, NR_FREE_CMA_PAGES);
#endif
if (free_pages <= min + z->lowmem_reserve[classzone_idx])
return false;
/* If this is an order-0 request then the watermark is fine */
if (!order)
return true;
/* For a high-order request, check at least one suitable page is free */
for (o = order; o < MAX_ORDER; o++) {
struct free_area *area = &z->free_area[o];
int mt;
if (!area->nr_free)
continue;
for (mt = 0; mt < MIGRATE_PCPTYPES; mt++) {
if (!list_empty(&area->free_list[mt]))
return true;
}
#ifdef CONFIG_CMA
if ((alloc_flags & ALLOC_CMA) &&
!list_empty(&area->free_list[MIGRATE_CMA])) {
return true;
}
#endif
if (alloc_harder &&
!list_empty(&area->free_list[MIGRATE_HIGHATOMIC]))
return true;
}
return false;
}
在wart_mark_ok函数中可以看到min水位下的内存是怎么处理的,如果是个高优先级进程可以使用min/2以上的内存,如果是当前进程是oom的受害者同样。
空闲内存满足标准的情况下,还需要判断伙伴系统中是否有满足标准的连续内存块。
如下图所示伙伴系统中zone有一个free_area数组(表示2的order次幂个连续的页面),每个成员是一个free_list数组,表示对应迁移类型的连续页面的数量。
node_reclaim
try_this_zone
从当前zone中使用rmqueue分配内存,并对得到的page进行检查
rmqueue //待补充
__alloc_pages_slowpath
快速分配路径不成功,则进入慢速路径,进入慢速路径前会根据当前进程的状态调整gfp_mask的标志位。
static inline struct page *
__alloc_pages_slowpath(gfp_t gfp_mask, unsigned int order,
struct alloc_context *ac)
{
bool can_direct_reclaim = gfp_mask & __GFP_DIRECT_RECLAIM;
const bool costly_order = order > PAGE_ALLOC_COSTLY_ORDER;
struct page *page = NULL;
unsigned int alloc_flags;
unsigned long did_some_progress;
enum compact_priority compact_priority;
enum compact_result compact_result;
int compaction_retries;
int no_progress_loops;
unsigned int cpuset_mems_cookie;
int reserve_flags;
/*
* We also sanity check to catch abuse of atomic reserves being used by
* callers that are not in atomic context.
*/
if (WARN_ON_ONCE((gfp_mask & (__GFP_ATOMIC|__GFP_DIRECT_RECLAIM)) ==
(__GFP_ATOMIC|__GFP_DIRECT_RECLAIM)))
gfp_mask &= ~__GFP_ATOMIC;
retry_cpuset:
compaction_retries = 0;
no_progress_loops = 0;
compact_priority = DEF_COMPACT_PRIORITY;
cpuset_mems_cookie = read_mems_allowed_begin();
/*
* The fast path uses conservative alloc_flags to succeed only until
* kswapd needs to be woken up, and to avoid the cost of setting up
* alloc_flags precisely. So we do that now.
*/
alloc_flags = gfp_to_alloc_flags(gfp_mask);//0x240,将内存水位调整为min,运行kswapd,
/*
* We need to recalculate the starting point for the zonelist iterator
* because we might have used different nodemask in the fast path, or
* there was a cpuset modification and we are retrying - otherwise we
* could end up iterating over non-eligible zones endlessly.
*/
ac->preferred_zoneref = first_zones_zonelist(ac->zonelist, //首选zone为normal
ac->high_zoneidx, ac->nodemask);
if (!ac->preferred_zoneref->zone)
goto nopage;
if (alloc_flags & ALLOC_KSWAPD)
wake_all_kswapds(order, gfp_mask, ac); //唤醒kswapd
/*
* The adjusted alloc_flags might result in immediate success, so try
* that first
*/
page = get_page_from_freelist(gfp_mask, order, alloc_flags, ac);
if (page)
goto got_pg;
/*
* For costly allocations, try direct compaction first, as it's likely
* that we have enough base pages and don't need to reclaim. For non-
* movable high-order allocations, do that as well, as compaction will
* try prevent permanent fragmentation by migrating from blocks of the
* same migratetype.
* Don't try this for allocations that are allowed to ignore
* watermarks, as the ALLOC_NO_WATERMARKS attempt didn't yet happen.
*/
if (can_direct_reclaim &&
(costly_order ||
(order > 0 && ac->migratetype != MIGRATE_MOVABLE))
&& !gfp_pfmemalloc_allowed(gfp_mask)) {
page = __alloc_pages_direct_compact(gfp_mask, order,
alloc_flags, ac,
INIT_COMPACT_PRIORITY,
&compact_result);
if (page)
goto got_pg;
/*
* Checks for costly allocations with __GFP_NORETRY, which
* includes THP page fault allocations
*/
if (costly_order && (gfp_mask & __GFP_NORETRY)) {
/*
* If compaction is deferred for high-order allocations,
* it is because sync compaction recently failed. If
* this is the case and the caller requested a THP
* allocation, we do not want to heavily disrupt the
* system, so we fail the allocation instead of entering
* direct reclaim.
*/
if (compact_result == COMPACT_DEFERRED)
goto nopage;
/*
* Looks like reclaim/compaction is worth trying, but
* sync compaction could be very expensive, so keep
* using async compaction.
*/
compact_priority = INIT_COMPACT_PRIORITY;
}
}
retry:
/* Ensure kswapd doesn't accidentally go to sleep as long as we loop */
if (alloc_flags & ALLOC_KSWAPD)
wake_all_kswapds(order, gfp_mask, ac);
reserve_flags = __gfp_pfmemalloc_flags(gfp_mask);
if (reserve_flags)
alloc_flags = reserve_flags;
/*
* Reset the nodemask and zonelist iterators if memory policies can be
* ignored. These allocations are high priority and system rather than
* user oriented.
*/
if (!(alloc_flags & ALLOC_CPUSET) || reserve_flags) {
ac->nodemask = NULL;
ac->preferred_zoneref = first_zones_zonelist(ac->zonelist,
ac->high_zoneidx, ac->nodemask);
}
/* Attempt with potentially adjusted zonelist and alloc_flags */
page = get_page_from_freelist(gfp_mask, order, alloc_flags, ac);
if (page)
goto got_pg;
/* Caller is not willing to reclaim, we can't balance anything */
if (!can_direct_reclaim)
goto nopage;
/* Avoid recursion of direct reclaim */
if (current->flags & PF_MEMALLOC)
goto nopage;
/* Try direct reclaim and then allocating */
page = __alloc_pages_direct_reclaim(gfp_mask, order, alloc_flags, ac,
&did_some_progress);
if (page)
goto got_pg;
/* Try direct compaction and then allocating */
page = __alloc_pages_direct_compact(gfp_mask, order, alloc_flags, ac,
compact_priority, &compact_result);
if (page)
goto got_pg;
/* Do not loop if specifically requested */
if (gfp_mask & __GFP_NORETRY)
goto nopage;
/*
* Do not retry costly high order allocations unless they are
* __GFP_RETRY_MAYFAIL
*/
if (costly_order && !(gfp_mask & __GFP_RETRY_MAYFAIL))
goto nopage;
if (should_reclaim_retry(gfp_mask, order, ac, alloc_flags,
did_some_progress > 0, &no_progress_loops))
goto retry;
/*
* It doesn't make any sense to retry for the compaction if the order-0
* reclaim is not able to make any progress because the current
* implementation of the compaction depends on the sufficient amount
* of free memory (see __compaction_suitable)
*/
if (did_some_progress > 0 &&
should_compact_retry(ac, order, alloc_flags,
compact_result, &compact_priority,
&compaction_retries))
goto retry;
/* Deal with possible cpuset update races before we start OOM killing */
if (check_retry_cpuset(cpuset_mems_cookie, ac))
goto retry_cpuset;
/* Reclaim has failed us, start killing things */
page = __alloc_pages_may_oom(gfp_mask, order, ac, &did_some_progress);
if (page)
goto got_pg;
/* Avoid allocations with no watermarks from looping endlessly */
if (tsk_is_oom_victim(current) &&
(alloc_flags == ALLOC_OOM ||
(gfp_mask & __GFP_NOMEMALLOC)))
goto nopage;
/* Retry as long as the OOM killer is making progress */
if (did_some_progress) {
no_progress_loops = 0;
goto retry;
}
nopage:
/* Deal with possible cpuset update races before we fail */
if (check_retry_cpuset(cpuset_mems_cookie, ac))
goto retry_cpuset;
/*
* Make sure that __GFP_NOFAIL request doesn't leak out and make sure
* we always retry
*/
if (gfp_mask & __GFP_NOFAIL) {
/*
* All existing users of the __GFP_NOFAIL are blockable, so warn
* of any new users that actually require GFP_NOWAIT
*/
if (WARN_ON_ONCE(!can_direct_reclaim))
goto fail;
/*
* PF_MEMALLOC request from this context is rather bizarre
* because we cannot reclaim anything and only can loop waiting
* for somebody to do a work for us
*/
WARN_ON_ONCE(current->flags & PF_MEMALLOC);
/*
* non failing costly orders are a hard requirement which we
* are not prepared for much so let's warn about these users
* so that we can identify them and convert them to something
* else.
*/
WARN_ON_ONCE(order > PAGE_ALLOC_COSTLY_ORDER);
/*
* Help non-failing allocations by giving them access to memory
* reserves but do not use ALLOC_NO_WATERMARKS because this
* could deplete whole memory reserves which would just make
* the situation worse
*/
page = __alloc_pages_cpuset_fallback(gfp_mask, order, ALLOC_HARDER, ac);
if (page)
goto got_pg;
cond_resched();
goto retry;
}
fail:
warn_alloc(gfp_mask, ac->nodemask,
"page allocation failure: order:%u", order);
got_pg:
return page;
}
简化后的整体流程如下:
会通过kswapd异步回收、直接回收、内存规整、oom等方式分配内存,如果尝试各种方式都无法分配成功,就只能失败并打印page allocation failure了。
wake_all_kswapds
wakeup_kswapd
此时zone为normal,gfp_flags为GFP_KERNEL,classzone_idx为1。
void wakeup_kswapd(struct zone *zone, gfp_t gfp_flags, int order,
enum zone_type classzone_idx)
{
pg_data_t *pgdat;
if (!managed_zone(zone))
return;
if (!cpuset_zone_allowed(zone, gfp_flags))
return;
pgdat = zone->zone_pgdat;
pgdat->kswapd_classzone_idx = kswapd_classzone_idx(pgdat,
classzone_idx);
pgdat->kswapd_order = max(pgdat->kswapd_order, order);
if (!waitqueue_active(&pgdat->kswapd_wait))
return;
/* Hopeless node, leave it to direct reclaim if possible */
if (pgdat->kswapd_failures >= MAX_RECLAIM_RETRIES || //kswapd失败次数太多(kswapd已经救不了它了),或者是内存高于high水位且watermarkboost没有设置(不需要唤醒)
(pgdat_balanced(pgdat, order, classzone_idx) &&
!pgdat_watermark_boosted(pgdat, classzone_idx))) {
/*
* There may be plenty of free memory available, but it's too
* fragmented for high-order allocations. Wake up kcompactd
* and rely on compaction_suitable() to determine if it's
* needed. If it fails, it will defer subsequent attempts to
* ratelimit its work.
*/
if (!(gfp_flags & __GFP_DIRECT_RECLAIM))
wakeup_kcompactd(pgdat, order, classzone_idx);
return;
}
trace_mm_vmscan_wakeup_kswapd(pgdat->node_id, classzone_idx, order,
gfp_flags);
wake_up_interruptible(&pgdat->kswapd_wait);
}
kswapd
static int kswapd(void *p)
{
unsigned int alloc_order, reclaim_order;
unsigned int classzone_idx = MAX_NR_ZONES - 1;
pg_data_t *pgdat = (pg_data_t*)p;
struct task_struct *tsk = current;
struct reclaim_state reclaim_state = {
.reclaimed_slab = 0,
};
const struct cpumask *cpumask = cpumask_of_node(pgdat->node_id);
if (!cpumask_empty(cpumask))
set_cpus_allowed_ptr(tsk, cpumask); //绑核操作,一般不建议
current->reclaim_state = &reclaim_state;
/*
* Tell the memory management that we're a "memory allocator",
* and that if we need more memory we should get access to it
* regardless (see "__alloc_pages()"). "kswapd" should
* never get caught in the normal page freeing logic.
*
* (Kswapd normally doesn't need memory anyway, but sometimes
* you need a small amount of memory in order to be able to
* page out something else, and this flag essentially protects
* us from recursively trying to free more memory as we're
* trying to free the first piece of memory in the first place).
*/
/*
a. PF_KSWAPD主要⽤于标记该线程是个kswapd线程,在后续运⾏中,与其他业务线程进行区别,例如在 get_scan_count中⽤于调节swappiness等。
b. PF_MEMALLOC 标记该线程是个关键线程,即在紧急情况下能在低于Min Watermark 的情况下继续分配内存,说明该线程分配内存时不受Watermark的限制。这是因为kswapd在运⾏的时候说明系统已经低内存,⽽kswapd有时为了回收更多内存需要临时分配内存用作周转,例如在把Anon page压缩到zram的过程中,⾸先需要分配内存来保存压缩后的内存,如果分配不成功,则可能⽆法完成内存回收工作。
c. PF_SWAPWRITE 表⽰可以写swap,说明kswapd可以回收匿名⻚
————————————————
版权声明:本文为CSDN博主「内核工匠」的原创文章,遵循CC 4.0 BY-SA版权协议,转载请附上原文出处链接及本声明。
原文链接:https://blog.csdn.net/feelabclihu/article/details/124054410
*/
tsk->flags |= PF_MEMALLOC | PF_SWAPWRITE | PF_KSWAPD; //设置kswapd的进程标志位
set_freezable();
pgdat->kswapd_order = 0;
pgdat->kswapd_classzone_idx = MAX_NR_ZONES;
for ( ; ; ) {
bool ret;
alloc_order = reclaim_order = pgdat->kswapd_order;
classzone_idx = kswapd_classzone_idx(pgdat, classzone_idx);
kswapd_try_sleep:
kswapd_try_to_sleep(pgdat, alloc_order, reclaim_order, //尝试睡眠,并把自己放入pgdat→kswapd_wait等待队列中,直到kswapd被唤醒。
classzone_idx);
/* Read the new order and classzone_idx */
alloc_order = reclaim_order = pgdat->kswapd_order;
classzone_idx = kswapd_classzone_idx(pgdat, 0);
pgdat->kswapd_order = 0;
pgdat->kswapd_classzone_idx = MAX_NR_ZONES;
ret = try_to_freeze();
if (kthread_should_stop())
break;
/*
* We can speed up thawing tasks if we don't call balance_pgdat
* after returning from the refrigerator
*/
if (ret)
continue;
/*
* Reclaim begins at the requested order but if a high-order
* reclaim fails then kswapd falls back to reclaiming for
* order-0. If that happens, kswapd will consider sleeping
* for the order it finished reclaiming at (reclaim_order)
* but kcompactd is woken to compact for the original
* request (alloc_order).
*/
trace_mm_vmscan_kswapd_wake(pgdat->node_id, classzone_idx,
alloc_order);
reclaim_order = balance_pgdat(pgdat, alloc_order, classzone_idx);
if (reclaim_order < alloc_order)
goto kswapd_try_sleep;
}
tsk->flags &= ~(PF_MEMALLOC | PF_SWAPWRITE | PF_KSWAPD);
current->reclaim_state = NULL;
return 0;
}
代码流程大致如下
balance_pgdat
static int balance_pgdat(pg_data_t *pgdat, int order, int classzone_idx)
{
int i;
unsigned long nr_soft_reclaimed;
unsigned long nr_soft_scanned;
unsigned long pflags;
unsigned long nr_boost_reclaim;
unsigned long zone_boosts[MAX_NR_ZONES] = { 0, };
bool boosted;
struct zone *zone;
struct scan_control sc = {
.gfp_mask = GFP_KERNEL,
.order = order,
.may_unmap = 1,
};
psi_memstall_enter(&pflags);
__fs_reclaim_acquire();
count_vm_event(PAGEOUTRUN);
/*
* Account for the reclaim boost. Note that the zone boost is left in
* place so that parallel allocations that are near the watermark will
* stall or direct reclaim until kswapd is finished.
*/
nr_boost_reclaim = 0;
for (i = 0; i <= classzone_idx; i++) {
zone = pgdat->node_zones + i;
if (!managed_zone(zone))
continue;
nr_boost_reclaim += zone->watermark_boost;
zone_boosts[i] = zone->watermark_boost;
}
boosted = nr_boost_reclaim;
restart:
sc.priority = DEF_PRIORITY;
do {
unsigned long nr_reclaimed = sc.nr_reclaimed;
bool raise_priority = true;
bool balanced;
bool ret;
sc.reclaim_idx = classzone_idx;
/*
* If the number of buffer_heads exceeds the maximum allowed
* then consider reclaiming from all zones. This has a dual
* purpose -- on 64-bit systems it is expected that
* buffer_heads are stripped during active rotation. On 32-bit
* systems, highmem pages can pin lowmem memory and shrinking
* buffers can relieve lowmem pressure. Reclaim may still not
* go ahead if all eligible zones for the original allocation
* request are balanced to avoid excessive reclaim from kswapd.
*/
if (buffer_heads_over_limit) {
for (i = MAX_NR_ZONES - 1; i >= 0; i--) {
zone = pgdat->node_zones + i;
if (!managed_zone(zone))
continue;
sc.reclaim_idx = i;
break;
}
}
/*
* If the pgdat is imbalanced then ignore boosting and preserve
* the watermarks for a later time and restart. Note that the
* zone watermarks will be still reset at the end of balancing
* on the grounds that the normal reclaim should be enough to
* re-evaluate if boosting is required when kswapd next wakes.
*/
balanced = pgdat_balanced(pgdat, sc.order, classzone_idx); //是否有空闲内存高于high的zone。
if (!balanced && nr_boost_reclaim) {
nr_boost_reclaim = 0;
goto restart;
}
/*
* If boosting is not active then only reclaim if there are no
* eligible zones. Note that sc.reclaim_idx is not used as
* buffer_heads_over_limit may have adjusted it.
*/
if (!nr_boost_reclaim && balanced) //有空闲内存高于high的zone,直接退出kswapd内存回收
goto out;
/* Limit the priority of boosting to avoid reclaim writeback */
if (nr_boost_reclaim && sc.priority == DEF_PRIORITY - 2)
raise_priority = false;
/*
* Do not writeback or swap pages for boosted reclaim. The
* intent is to relieve pressure not issue sub-optimal IO
* from reclaim context. If no pages are reclaimed, the
* reclaim will be aborted.
*/
sc.may_writepage = !laptop_mode && !nr_boost_reclaim;
sc.may_swap = !nr_boost_reclaim;
sc.may_shrinkslab = !nr_boost_reclaim;
/*
* Do some background aging of the anon list, to give
* pages a chance to be referenced before reclaiming. All
* pages are rotated regardless of classzone as this is
* about consistent aging.
*/
age_active_anon(pgdat, &sc); //完成匿名页的老化处理,以4g的机器来说,开机后总内存3.x,对应的比例计算的5,即inactive*5<active时,需要把active 中的页面迁移到inactive中。在迁移的时候一次性选择32页,先把这32页从lru中剥离出来,对其进行单独处理,这也可以尽量短地持有lru链表的锁。剥离出来的这部分会被加入到ISOLATED类型的页面中。
/*
* If we're getting trouble reclaiming, start doing writepage
* even in laptop mode.
*/
if (sc.priority < DEF_PRIORITY - 2)
sc.may_writepage = 1;
/* Call soft limit reclaim before calling shrink_node. */
sc.nr_scanned = 0;
nr_soft_scanned = 0;
nr_soft_reclaimed = mem_cgroup_soft_limit_reclaim(pgdat, sc.order,
sc.gfp_mask, &nr_soft_scanned);
sc.nr_reclaimed += nr_soft_reclaimed;
/*
* There should be no need to raise the scanning priority if
* enough pages are already being scanned that that high
* watermark would be met at 100% efficiency.
*/
if (kswapd_shrink_node(pgdat, &sc))
raise_priority = false;
/*
* If the low watermark is met there is no need for processes
* to be throttled on pfmemalloc_wait as they should not be
* able to safely make forward progress. Wake them
*/
if (waitqueue_active(&pgdat->pfmemalloc_wait) &&
allow_direct_reclaim(pgdat))
wake_up_all(&pgdat->pfmemalloc_wait);
/* Check if kswapd should be suspending */
__fs_reclaim_release();
ret = try_to_freeze();
__fs_reclaim_acquire();
if (ret || kthread_should_stop())
break;
/*
* Raise priority if scanning rate is too low or there was no
* progress in reclaiming pages
*/
nr_reclaimed = sc.nr_reclaimed - nr_reclaimed;
nr_boost_reclaim -= min(nr_boost_reclaim, nr_reclaimed);
/*
* If reclaim made no progress for a boost, stop reclaim as
* IO cannot be queued and it could be an infinite loop in
* extreme circumstances.
*/
if (nr_boost_reclaim && !nr_reclaimed)
break;
if (raise_priority || !nr_reclaimed)
sc.priority--;
} while (sc.priority >= 1);
if (!sc.nr_reclaimed)
pgdat->kswapd_failures++;
out:
/* If reclaim was boosted, account for the reclaim done in this pass */
if (boosted) {
unsigned long flags;
for (i = 0; i <= classzone_idx; i++) {
if (!zone_boosts[i])
continue;
/* Increments are under the zone lock */
zone = pgdat->node_zones + i;
spin_lock_irqsave(&zone->lock, flags);
zone->watermark_boost -= min(zone->watermark_boost, zone_boosts[i]);
spin_unlock_irqrestore(&zone->lock, flags);
}
/*
* As there is now likely space, wakeup kcompact to defragment
* pageblocks.
*/
wakeup_kcompactd(pgdat, pageblock_order, classzone_idx);
}
snapshot_refaults(NULL, pgdat);
__fs_reclaim_release();
psi_memstall_leave(&pflags);
/*
* Return the order kswapd stopped reclaiming at as
* prepare_kswapd_sleep() takes it into account. If another caller
* entered the allocator slow path while kswapd was awake, order will
* remain at the higher level.
*/
return sc.order;
}
kswapd_shrink_node
static bool kswapd_shrink_node(pg_data_t *pgdat,
struct scan_control *sc)
{
struct zone *zone;
int z;
/* Reclaim a number of pages proportional to the number of zones */
sc->nr_to_reclaim = 0;
for (z = 0; z <= sc->reclaim_idx; z++) {
zone = pgdat->node_zones + z;
if (!managed_zone(zone))
continue;
sc->nr_to_reclaim += max(high_wmark_pages(zone), SWAP_CLUSTER_MAX);
}
/*
* Historically care was taken to put equal pressure on all zones but
* now pressure is applied based on node LRU order.
*/
shrink_node(pgdat, sc);
/*
* Fragmentation may mean that the system cannot be rebalanced for
* high-order allocations. If twice the allocation size has been
* reclaimed then recheck watermarks only at order-0 to prevent
* excessive reclaim. Assume that a process requested a high-order
* can direct reclaim/compact.
*/
if (sc->order && sc->nr_reclaimed >= compact_gap(sc->order))
sc->order = 0;
return sc->nr_scanned >= sc->nr_to_reclaim;
}
shrink_node
static bool shrink_node(pg_data_t *pgdat, struct scan_control *sc)
{
struct reclaim_state *reclaim_state = current->reclaim_state;
unsigned long nr_reclaimed, nr_scanned;
bool reclaimable = false;
do {
struct mem_cgroup *root = sc->target_mem_cgroup;
struct mem_cgroup_reclaim_cookie reclaim = {
.pgdat = pgdat,
.priority = sc->priority,
};
unsigned long node_lru_pages = 0;
struct mem_cgroup *memcg;
memset(&sc->nr, 0, sizeof(sc->nr));
nr_reclaimed = sc->nr_reclaimed;
nr_scanned = sc->nr_scanned;
memcg = mem_cgroup_iter(root, NULL, &reclaim);
do {
unsigned long lru_pages;
unsigned long reclaimed;
unsigned long scanned;
switch (mem_cgroup_protected(root, memcg)) {
case MEMCG_PROT_MIN:
/*
* Hard protection.
* If there is no reclaimable memory, OOM.
*/
continue;
case MEMCG_PROT_LOW:
/*
* Soft protection.
* Respect the protection only as long as
* there is an unprotected supply
* of reclaimable memory from other cgroups.
*/
if (!sc->memcg_low_reclaim) {
sc->memcg_low_skipped = 1;
continue;
}
memcg_memory_event(memcg, MEMCG_LOW);
break;
case MEMCG_PROT_NONE:
break;
}
reclaimed = sc->nr_reclaimed;
scanned = sc->nr_scanned;
shrink_node_memcg(pgdat, memcg, sc, &lru_pages);
node_lru_pages += lru_pages;
if (sc->may_shrinkslab) {
shrink_slab(sc->gfp_mask, pgdat->node_id,
memcg, sc->priority);
}
/* Record the group's reclaim efficiency */
vmpressure(sc->gfp_mask, memcg, false,
sc->nr_scanned - scanned,
sc->nr_reclaimed - reclaimed);
/*
* Direct reclaim and kswapd have to scan all memory
* cgroups to fulfill the overall scan target for the
* node.
*
* Limit reclaim, on the other hand, only cares about
* nr_to_reclaim pages to be reclaimed and it will
* retry with decreasing priority if one round over the
* whole hierarchy is not sufficient.
*/
if (!global_reclaim(sc) &&
sc->nr_reclaimed >= sc->nr_to_reclaim) {
mem_cgroup_iter_break(root, memcg);
break;
}
} while ((memcg = mem_cgroup_iter(root, memcg, &reclaim)));
if (reclaim_state) {
sc->nr_reclaimed += reclaim_state->reclaimed_slab;
reclaim_state->reclaimed_slab = 0;
}
/* Record the subtree's reclaim efficiency */
vmpressure(sc->gfp_mask, sc->target_mem_cgroup, true,
sc->nr_scanned - nr_scanned,
sc->nr_reclaimed - nr_reclaimed);
if (sc->nr_reclaimed - nr_reclaimed)
reclaimable = true;
if (current_is_kswapd()) {
/*
* If reclaim is isolating dirty pages under writeback,
* it implies that the long-lived page allocation rate
* is exceeding the page laundering rate. Either the
* global limits are not being effective at throttling
* processes due to the page distribution throughout
* zones or there is heavy usage of a slow backing
* device. The only option is to throttle from reclaim
* context which is not ideal as there is no guarantee
* the dirtying process is throttled in the same way
* balance_dirty_pages() manages.
*
* Once a node is flagged PGDAT_WRITEBACK, kswapd will
* count the number of pages under pages flagged for
* immediate reclaim and stall if any are encountered
* in the nr_immediate check below.
*/
if (sc->nr.writeback && sc->nr.writeback == sc->nr.taken)
set_bit(PGDAT_WRITEBACK, &pgdat->flags);
/*
* Tag a node as congested if all the dirty pages
* scanned were backed by a congested BDI and
* wait_iff_congested will stall.
*/
if (sc->nr.dirty && sc->nr.dirty == sc->nr.congested)
set_bit(PGDAT_CONGESTED, &pgdat->flags);
/* Allow kswapd to start writing pages during reclaim.*/
if (sc->nr.unqueued_dirty == sc->nr.file_taken)
set_bit(PGDAT_DIRTY, &pgdat->flags);
/*
* If kswapd scans pages marked marked for immediate
* reclaim and under writeback (nr_immediate), it
* implies that pages are cycling through the LRU
* faster than they are written so also forcibly stall.
*/
if (sc->nr.immediate)
congestion_wait(BLK_RW_ASYNC, HZ/10);
}
/*
* Legacy memcg will stall in page writeback so avoid forcibly
* stalling in wait_iff_congested().
*/
if (!global_reclaim(sc) && sane_reclaim(sc) &&
sc->nr.dirty && sc->nr.dirty == sc->nr.congested)
set_memcg_congestion(pgdat, root, true);
/*
* Stall direct reclaim for IO completions if underlying BDIs
* and node is congested. Allow kswapd to continue until it
* starts encountering unqueued dirty pages or cycling through
* the LRU too quickly.
*/
if (!sc->hibernation_mode && !current_is_kswapd() &&
current_may_throttle() && pgdat_memcg_congested(pgdat, root))
wait_iff_congested(BLK_RW_ASYNC, HZ/10);
} while (should_continue_reclaim(pgdat, sc->nr_reclaimed - nr_reclaimed,
sc->nr_scanned - nr_scanned, sc));
/*
* Kswapd gives up on balancing particular nodes after too
* many failures to reclaim anything from them and goes to
* sleep. On reclaim progress, reset the failure counter. A
* successful direct reclaim run will revive a dormant kswapd.
*/
if (reclaimable)
pgdat->kswapd_failures = 0;
return reclaimable;
}
shrink_node_memcg
/*
* This is a basic per-node page freer. Used by both kswapd and direct reclaim.
*/
static void shrink_node_memcg(struct pglist_data *pgdat, struct mem_cgroup *memcg,
struct scan_control *sc, unsigned long *lru_pages)
{
struct lruvec *lruvec = mem_cgroup_lruvec(pgdat, memcg);
unsigned long nr[NR_LRU_LISTS];
unsigned long targets[NR_LRU_LISTS];
unsigned long nr_to_scan;
enum lru_list lru;
unsigned long nr_reclaimed = 0;
unsigned long nr_to_reclaim = sc->nr_to_reclaim;
struct blk_plug plug;
bool scan_adjusted;
get_scan_count(lruvec, memcg, sc, nr, lru_pages); //根据swappiness的值计算需要回收的匿名页和文件页的数量
/* Record the original scan target for proportional adjustments later */
memcpy(targets, nr, sizeof(nr));
/*
* Global reclaiming within direct reclaim at DEF_PRIORITY is a normal
* event that can occur when there is little memory pressure e.g.
* multiple streaming readers/writers. Hence, we do not abort scanning
* when the requested number of pages are reclaimed when scanning at
* DEF_PRIORITY on the assumption that the fact we are direct
* reclaiming implies that kswapd is not keeping up and it is best to
* do a batch of work at once. For memcg reclaim one check is made to
* abort proportional reclaim if either the file or anon lru has already
* dropped to zero at the first pass.
*/
scan_adjusted = (global_reclaim(sc) && !current_is_kswapd() &&
sc->priority == DEF_PRIORITY);
blk_start_plug(&plug); //块设备层接口,因为内存回收过程中涉及io操作,在这里对io进行蓄洪。
while (nr[LRU_INACTIVE_ANON] || nr[LRU_ACTIVE_FILE] ||
nr[LRU_INACTIVE_FILE]) {
unsigned long nr_anon, nr_file, percentage;
unsigned long nr_scanned;
for_each_evictable_lru(lru) {
if (nr[lru]) {
nr_to_scan = min(nr[lru], SWAP_CLUSTER_MAX);
nr[lru] -= nr_to_scan;
nr_reclaimed += shrink_list(lru, nr_to_scan,
lruvec, memcg, sc);
}
}
cond_resched();
if (nr_reclaimed < nr_to_reclaim || scan_adjusted)
continue;
/*
* For kswapd and memcg, reclaim at least the number of pages
* requested. Ensure that the anon and file LRUs are scanned
* proportionally what was requested by get_scan_count(). We
* stop reclaiming one LRU and reduce the amount scanning
* proportional to the original scan target.
*/
nr_file = nr[LRU_INACTIVE_FILE] + nr[LRU_ACTIVE_FILE];
nr_anon = nr[LRU_INACTIVE_ANON] + nr[LRU_ACTIVE_ANON];
/*
* It's just vindictive to attack the larger once the smaller
* has gone to zero. And given the way we stop scanning the
* smaller below, this makes sure that we only make one nudge
* towards proportionality once we've got nr_to_reclaim.
*/
if (!nr_file || !nr_anon)
break;
if (nr_file > nr_anon) {
unsigned long scan_target = targets[LRU_INACTIVE_ANON] +
targets[LRU_ACTIVE_ANON] + 1;
lru = LRU_BASE;
percentage = nr_anon * 100 / scan_target;
} else {
unsigned long scan_target = targets[LRU_INACTIVE_FILE] +
targets[LRU_ACTIVE_FILE] + 1;
lru = LRU_FILE;
percentage = nr_file * 100 / scan_target;
}
/* Stop scanning the smaller of the LRU */
nr[lru] = 0;
nr[lru + LRU_ACTIVE] = 0;
/*
* Recalculate the other LRU scan count based on its original
* scan target and the percentage scanning already complete
*/
lru = (lru == LRU_FILE) ? LRU_BASE : LRU_FILE;
nr_scanned = targets[lru] - nr[lru];
nr[lru] = targets[lru] * (100 - percentage) / 100;
nr[lru] -= min(nr[lru], nr_scanned);
lru += LRU_ACTIVE;
nr_scanned = targets[lru] - nr[lru];
nr[lru] = targets[lru] * (100 - percentage) / 100;
nr[lru] -= min(nr[lru], nr_scanned);
scan_adjusted = true;
}
blk_finish_plug(&plug); //完成蓄洪,将io一次性下发。
sc->nr_reclaimed += nr_reclaimed;
/*
* Even if we did not try to evict anon pages at all, we want to
* rebalance the anon lru active/inactive ratio.
*/
if (inactive_list_is_low(lruvec, false, memcg, sc, true)) //对active 和inactive类型的LRU链表进行调整,保证inactive list不会太低。
shrink_active_list(SWAP_CLUSTER_MAX, lruvec,
sc, LRU_ACTIVE_ANON);
}
get_scan_acount
static void get_scan_count(struct lruvec *lruvec, struct mem_cgroup *memcg,
struct scan_control *sc, unsigned long *nr,
unsigned long *lru_pages)
{
int swappiness = mem_cgroup_swappiness(memcg);
struct zone_reclaim_stat *reclaim_stat = &lruvec->reclaim_stat;
u64 fraction[2];
u64 denominator = 0; /* gcc */
struct pglist_data *pgdat = lruvec_pgdat(lruvec);
unsigned long anon_prio, file_prio;
enum scan_balance scan_balance;
unsigned long anon, file;
unsigned long ap, fp;
enum lru_list lru;
/* If we have no swap space, do not bother scanning anon pages. */
if (!sc->may_swap || mem_cgroup_get_nr_swap_pages(memcg) <= 0) {
scan_balance = SCAN_FILE;
goto out;
}
/*
* Global reclaim will swap to prevent OOM even with no
* swappiness, but memcg users want to use this knob to
* disable swapping for individual groups completely when
* using the memory controller's swap limit feature would be
* too expensive.
*/
if (!global_reclaim(sc) && !swappiness) {
scan_balance = SCAN_FILE;
goto out;
}
/*
* Do not apply any pressure balancing cleverness when the
* system is close to OOM, scan both anon and file equally
* (unless the swappiness setting disagrees with swapping).
*/
if (!sc->priority && swappiness) {
scan_balance = SCAN_EQUAL;
goto out;
}
/*
* Prevent the reclaimer from falling into the cache trap: as
* cache pages start out inactive, every cache fault will tip
* the scan balance towards the file LRU. And as the file LRU
* shrinks, so does the window for rotation from references.
* This means we have a runaway feedback loop where a tiny
* thrashing file LRU becomes infinitely more attractive than
* anon pages. Try to detect this based on file LRU size.
*/
if (global_reclaim(sc)) {
unsigned long pgdatfile;
unsigned long pgdatfree;
int z;
unsigned long total_high_wmark = 0;
pgdatfree = sum_zone_node_page_state(pgdat->node_id, NR_FREE_PAGES);
pgdatfile = node_page_state(pgdat, NR_ACTIVE_FILE) +
node_page_state(pgdat, NR_INACTIVE_FILE);
for (z = 0; z < MAX_NR_ZONES; z++) {
struct zone *zone = &pgdat->node_zones[z];
if (!managed_zone(zone))
continue;
total_high_wmark += high_wmark_pages(zone);
}
if (unlikely(pgdatfile + pgdatfree <= total_high_wmark)) {
/*
* Force SCAN_ANON if there are enough inactive
* anonymous pages on the LRU in eligible zones.
* Otherwise, the small LRU gets thrashed.
*/
if (!inactive_list_is_low(lruvec, false, memcg, sc, false) &&
lruvec_lru_size(lruvec, LRU_INACTIVE_ANON, sc->reclaim_idx)
>> sc->priority) {
scan_balance = SCAN_ANON;
goto out;
}
}
}
/*
* If there is enough inactive page cache, i.e. if the size of the
* inactive list is greater than that of the active list *and* the
* inactive list actually has some pages to scan on this priority, we
* do not reclaim anything from the anonymous working set right now.
* Without the second condition we could end up never scanning an
* lruvec even if it has plenty of old anonymous pages unless the
* system is under heavy pressure.
*/
if (!inactive_list_is_low(lruvec, true, memcg, sc, false) &&
lruvec_lru_size(lruvec, LRU_INACTIVE_FILE, sc->reclaim_idx) >> sc->priority) {
scan_balance = SCAN_FILE;
goto out;
}
scan_balance = SCAN_FRACT;
/*
* With swappiness at 100, anonymous and file have the same priority.
* This scanning priority is essentially the inverse of IO cost.
*/
anon_prio = swappiness;
file_prio = 200 - anon_prio;
/*
* OK, so we have swap space and a fair amount of page cache
* pages. We use the recently rotated / recently scanned
* ratios to determine how valuable each cache is.
*
* Because workloads change over time (and to avoid overflow)
* we keep these statistics as a floating average, which ends
* up weighing recent references more than old ones.
*
* anon in [0], file in [1]
*/
anon = lruvec_lru_size(lruvec, LRU_ACTIVE_ANON, MAX_NR_ZONES) +
lruvec_lru_size(lruvec, LRU_INACTIVE_ANON, MAX_NR_ZONES);
file = lruvec_lru_size(lruvec, LRU_ACTIVE_FILE, MAX_NR_ZONES) +
lruvec_lru_size(lruvec, LRU_INACTIVE_FILE, MAX_NR_ZONES);
spin_lock_irq(&pgdat->lru_lock);
if (unlikely(reclaim_stat->recent_scanned[0] > anon / 4)) {
reclaim_stat->recent_scanned[0] /= 2;
reclaim_stat->recent_rotated[0] /= 2;
}
if (unlikely(reclaim_stat->recent_scanned[1] > file / 4)) {
reclaim_stat->recent_scanned[1] /= 2;
reclaim_stat->recent_rotated[1] /= 2;
}
/*
* The amount of pressure on anon vs file pages is inversely
* proportional to the fraction of recently scanned pages on
* each list that were recently referenced and in active use.
*/
ap = anon_prio * (reclaim_stat->recent_scanned[0] + 1);
ap /= reclaim_stat->recent_rotated[0] + 1;
fp = file_prio * (reclaim_stat->recent_scanned[1] + 1);
fp /= reclaim_stat->recent_rotated[1] + 1;
spin_unlock_irq(&pgdat->lru_lock);
fraction[0] = ap;
fraction[1] = fp;
denominator = ap + fp + 1;
out:
*lru_pages = 0;
for_each_evictable_lru(lru) {
int file = is_file_lru(lru);
unsigned long size;
unsigned long scan;
size = lruvec_lru_size(lruvec, lru, sc->reclaim_idx);
scan = size >> sc->priority;
/*
* If the cgroup's already been deleted, make sure to
* scrape out the remaining cache.
*/
if (!scan && !mem_cgroup_online(memcg))
scan = min(size, SWAP_CLUSTER_MAX);
switch (scan_balance) {
case SCAN_EQUAL:
/* Scan lists relative to size */
break;
case SCAN_FRACT:
/*
* Scan types proportional to swappiness and
* their relative recent reclaim efficiency.
* Make sure we don't miss the last page
* because of a round-off error.
*/
scan = DIV64_U64_ROUND_UP(scan * fraction[file],
denominator);
break;
case SCAN_FILE:
case SCAN_ANON:
/* Scan one type exclusively */
if ((scan_balance == SCAN_FILE) != file) {
size = 0;
scan = 0;
}
break;
default:
/* Look ma, no brain */
BUG();
}
*lru_pages += size;
nr[lru] = scan;
}
}
shrink_list shrink_inactive_list
static unsigned long shrink_list(enum lru_list lru, unsigned long nr_to_scan,
struct lruvec *lruvec, struct mem_cgroup *memcg,
struct scan_control *sc)
{
if (is_active_lru(lru)) {
if (inactive_list_is_low(lruvec, is_file_lru(lru),
memcg, sc, true))
shrink_active_list(nr_to_scan, lruvec, sc, lru);
return 0;
}
return shrink_inactive_list(nr_to_scan, lruvec, sc, lru);
}
static noinline_for_stack unsigned long
shrink_inactive_list(unsigned long nr_to_scan, struct lruvec *lruvec,
struct scan_control *sc, enum lru_list lru)
{
LIST_HEAD(page_list);
unsigned long nr_scanned;
unsigned long nr_reclaimed = 0;
unsigned long nr_taken;
struct reclaim_stat stat = {};
isolate_mode_t isolate_mode = 0;
int file = is_file_lru(lru);
struct pglist_data *pgdat = lruvec_pgdat(lruvec);
struct zone_reclaim_stat *reclaim_stat = &lruvec->reclaim_stat;
bool stalled = false;
while (unlikely(too_many_isolated(pgdat, file, sc))) {
if (stalled)
return 0;
/* wait a bit for the reclaimer. */
msleep(100);
stalled = true;
/* We are about to die and free our memory. Return now. */
if (fatal_signal_pending(current))
return SWAP_CLUSTER_MAX;
}
lru_add_drain();
if (!sc->may_unmap)
isolate_mode |= ISOLATE_UNMAPPED;
spin_lock_irq(&pgdat->lru_lock);
nr_taken = isolate_lru_pages(nr_to_scan, lruvec, &page_list,
&nr_scanned, sc, isolate_mode, lru);
__mod_node_page_state(pgdat, NR_ISOLATED_ANON + file, nr_taken);
reclaim_stat->recent_scanned[file] += nr_taken;
if (current_is_kswapd()) {
if (global_reclaim(sc))
__count_vm_events(PGSCAN_KSWAPD, nr_scanned);
count_memcg_events(lruvec_memcg(lruvec), PGSCAN_KSWAPD,
nr_scanned);
} else {
if (global_reclaim(sc))
__count_vm_events(PGSCAN_DIRECT, nr_scanned);
count_memcg_events(lruvec_memcg(lruvec), PGSCAN_DIRECT,
nr_scanned);
}
spin_unlock_irq(&pgdat->lru_lock);
if (nr_taken == 0)
return 0;
nr_reclaimed = shrink_page_list(&page_list, pgdat, sc, 0,
&stat, false);
spin_lock_irq(&pgdat->lru_lock);
if (current_is_kswapd()) {
if (global_reclaim(sc))
__count_vm_events(PGSTEAL_KSWAPD, nr_reclaimed);
count_memcg_events(lruvec_memcg(lruvec), PGSTEAL_KSWAPD,
nr_reclaimed);
} else {
if (global_reclaim(sc))
__count_vm_events(PGSTEAL_DIRECT, nr_reclaimed);
count_memcg_events(lruvec_memcg(lruvec), PGSTEAL_DIRECT,
nr_reclaimed);
}
putback_inactive_pages(lruvec, &page_list);
__mod_node_page_state(pgdat, NR_ISOLATED_ANON + file, -nr_taken);
spin_unlock_irq(&pgdat->lru_lock);
mem_cgroup_uncharge_list(&page_list);
free_unref_page_list(&page_list);
/*
* If dirty pages are scanned that are not queued for IO, it
* implies that flushers are not doing their job. This can
* happen when memory pressure pushes dirty pages to the end of
* the LRU before the dirty limits are breached and the dirty
* data has expired. It can also happen when the proportion of
* dirty pages grows not through writes but through memory
* pressure reclaiming all the clean cache. And in some cases,
* the flushers simply cannot keep up with the allocation
* rate. Nudge the flusher threads in case they are asleep.
*/
if (stat.nr_unqueued_dirty == nr_taken)
wakeup_flusher_threads(WB_REASON_VMSCAN);
sc->nr.dirty += stat.nr_dirty;
sc->nr.congested += stat.nr_congested;
sc->nr.unqueued_dirty += stat.nr_unqueued_dirty;
sc->nr.writeback += stat.nr_writeback;
sc->nr.immediate += stat.nr_immediate;
sc->nr.taken += nr_taken;
if (file)
sc->nr.file_taken += nr_taken;
trace_mm_vmscan_lru_shrink_inactive(pgdat->node_id,
nr_scanned, nr_reclaimed, &stat, sc->priority, file);
return nr_reclaimed;
}
shrink_page_list
/*
* shrink_page_list() returns the number of reclaimed pages
*/
static unsigned long shrink_page_list(struct list_head *page_list,
struct pglist_data *pgdat,
struct scan_control *sc,
enum ttu_flags ttu_flags,
struct reclaim_stat *stat,
bool force_reclaim)
{
LIST_HEAD(ret_pages);
LIST_HEAD(free_pages);
int pgactivate = 0;
unsigned nr_unqueued_dirty = 0;
unsigned nr_dirty = 0;
unsigned nr_congested = 0;
unsigned nr_reclaimed = 0;
unsigned nr_writeback = 0;
unsigned nr_immediate = 0;
unsigned nr_ref_keep = 0;
unsigned nr_unmap_fail = 0;
cond_resched();
while (!list_empty(page_list)) {
struct address_space *mapping;
struct page *page;
int may_enter_fs;
enum page_references references = PAGEREF_RECLAIM_CLEAN;
bool dirty, writeback;
cond_resched();
page = lru_to_page(page_list);
list_del(&page->lru);
if (!trylock_page(page))
goto keep;
VM_BUG_ON_PAGE(PageActive(page), page);
sc->nr_scanned++;
if (unlikely(!page_evictable(page)))
goto activate_locked;
if (!sc->may_unmap && page_mapped(page))
goto keep_locked;
/* Double the slab pressure for mapped and swapcache pages */
if ((page_mapped(page) || PageSwapCache(page)) &&
!(PageAnon(page) && !PageSwapBacked(page)))
sc->nr_scanned++;
may_enter_fs = (sc->gfp_mask & __GFP_FS) ||
(PageSwapCache(page) && (sc->gfp_mask & __GFP_IO));
/*
* The number of dirty pages determines if a node is marked
* reclaim_congested which affects wait_iff_congested. kswapd
* will stall and start writing pages if the tail of the LRU
* is all dirty unqueued pages.
*/
page_check_dirty_writeback(page, &dirty, &writeback);
if (dirty || writeback)
nr_dirty++;
if (dirty && !writeback)
nr_unqueued_dirty++;
/*
* Treat this page as congested if the underlying BDI is or if
* pages are cycling through the LRU so quickly that the
* pages marked for immediate reclaim are making it to the
* end of the LRU a second time.
*/
mapping = page_mapping(page);
if (((dirty || writeback) && mapping &&
inode_write_congested(mapping->host)) ||
(writeback && PageReclaim(page)))
nr_congested++;
/*
* If a page at the tail of the LRU is under writeback, there
* are three cases to consider.
*
* 1) If reclaim is encountering an excessive number of pages
* under writeback and this page is both under writeback and
* PageReclaim then it indicates that pages are being queued
* for IO but are being recycled through the LRU before the
* IO can complete. Waiting on the page itself risks an
* indefinite stall if it is impossible to writeback the
* page due to IO error or disconnected storage so instead
* note that the LRU is being scanned too quickly and the
* caller can stall after page list has been processed.
*
* 2) Global or new memcg reclaim encounters a page that is
* not marked for immediate reclaim, or the caller does not
* have __GFP_FS (or __GFP_IO if it's simply going to swap,
* not to fs). In this case mark the page for immediate
* reclaim and continue scanning.
*
* Require may_enter_fs because we would wait on fs, which
* may not have submitted IO yet. And the loop driver might
* enter reclaim, and deadlock if it waits on a page for
* which it is needed to do the write (loop masks off
* __GFP_IO|__GFP_FS for this reason); but more thought
* would probably show more reasons.
*
* 3) Legacy memcg encounters a page that is already marked
* PageReclaim. memcg does not have any dirty pages
* throttling so we could easily OOM just because too many
* pages are in writeback and there is nothing else to
* reclaim. Wait for the writeback to complete.
*
* In cases 1) and 2) we activate the pages to get them out of
* the way while we continue scanning for clean pages on the
* inactive list and refilling from the active list. The
* observation here is that waiting for disk writes is more
* expensive than potentially causing reloads down the line.
* Since they're marked for immediate reclaim, they won't put
* memory pressure on the cache working set any longer than it
* takes to write them to disk.
*/
if (PageWriteback(page)) {
/* Case 1 above */
if (current_is_kswapd() &&
PageReclaim(page) &&
test_bit(PGDAT_WRITEBACK, &pgdat->flags)) {
nr_immediate++;
goto activate_locked;
/* Case 2 above */
} else if (sane_reclaim(sc) ||
!PageReclaim(page) || !may_enter_fs) {
/*
* This is slightly racy - end_page_writeback()
* might have just cleared PageReclaim, then
* setting PageReclaim here end up interpreted
* as PageReadahead - but that does not matter
* enough to care. What we do want is for this
* page to have PageReclaim set next time memcg
* reclaim reaches the tests above, so it will
* then wait_on_page_writeback() to avoid OOM;
* and it's also appropriate in global reclaim.
*/
SetPageReclaim(page);
nr_writeback++;
goto activate_locked;
/* Case 3 above */
} else {
unlock_page(page);
wait_on_page_writeback(page);//the disk sleep state occur!
/* then go back and try same page again */
list_add_tail(&page->lru, page_list);
continue;
}
}
if (!force_reclaim)
references = page_check_references(page, sc);
switch (references) {
case PAGEREF_ACTIVATE:
goto activate_locked;
case PAGEREF_KEEP:
nr_ref_keep++;
goto keep_locked;
case PAGEREF_RECLAIM:
case PAGEREF_RECLAIM_CLEAN:
; /* try to reclaim the page below */
}
/*
* Anonymous process memory has backing store?
* Try to allocate it some swap space here.
* Lazyfree page could be freed directly
*/
if (PageAnon(page) && PageSwapBacked(page)) {
if (!PageSwapCache(page)) {
if (!(sc->gfp_mask & __GFP_IO))
goto keep_locked;
if (PageTransHuge(page)) {
/* cannot split THP, skip it */
if (!can_split_huge_page(page, NULL))
goto activate_locked;
/*
* Split pages without a PMD map right
* away. Chances are some or all of the
* tail pages can be freed without IO.
*/
if (!compound_mapcount(page) &&
split_huge_page_to_list(page,
page_list))
goto activate_locked;
}
if (!add_to_swap(page)) {
if (!PageTransHuge(page))
goto activate_locked;
/* Fallback to swap normal pages */
if (split_huge_page_to_list(page,
page_list))
goto activate_locked;
#ifdef CONFIG_TRANSPARENT_HUGEPAGE
count_vm_event(THP_SWPOUT_FALLBACK);
#endif
if (!add_to_swap(page))
goto activate_locked;
}
may_enter_fs = 1;
/* Adding to swap updated mapping */
mapping = page_mapping(page);
}
} else if (unlikely(PageTransHuge(page))) {
/* Split file THP */
if (split_huge_page_to_list(page, page_list))
goto keep_locked;
}
/*
* The page is mapped into the page tables of one or more
* processes. Try to unmap it here.
*/
if (page_mapped(page)) {
enum ttu_flags flags = ttu_flags | TTU_BATCH_FLUSH;
if (unlikely(PageTransHuge(page)))
flags |= TTU_SPLIT_HUGE_PMD;
if (!try_to_unmap(page, flags)) {
nr_unmap_fail++;
goto activate_locked;
}
}
if (PageDirty(page)) {
/*
* Only kswapd can writeback filesystem pages
* to avoid risk of stack overflow. But avoid
* injecting inefficient single-page IO into
* flusher writeback as much as possible: only
* write pages when we've encountered many
* dirty pages, and when we've already scanned
* the rest of the LRU for clean pages and see
* the same dirty pages again (PageReclaim).
*/
if (page_is_file_cache(page) &&
(!current_is_kswapd() || !PageReclaim(page) ||
!test_bit(PGDAT_DIRTY, &pgdat->flags))) {
/*
* Immediately reclaim when written back.
* Similar in principal to deactivate_page()
* except we already have the page isolated
* and know it's dirty
*/
inc_node_page_state(page, NR_VMSCAN_IMMEDIATE);
SetPageReclaim(page);
goto activate_locked;
}
if (references == PAGEREF_RECLAIM_CLEAN)
goto keep_locked;
if (!may_enter_fs)
goto keep_locked;
if (!sc->may_writepage)
goto keep_locked;
/*
* Page is dirty. Flush the TLB if a writable entry
* potentially exists to avoid CPU writes after IO
* starts and then write it out here.
*/
try_to_unmap_flush_dirty();
switch (pageout(page, mapping, sc)) {
case PAGE_KEEP:
goto keep_locked;
case PAGE_ACTIVATE:
goto activate_locked;
case PAGE_SUCCESS:
if (PageWriteback(page))
goto keep;
if (PageDirty(page))
goto keep;
/*
* A synchronous write - probably a ramdisk. Go
* ahead and try to reclaim the page.
*/
if (!trylock_page(page))
goto keep;
if (PageDirty(page) || PageWriteback(page))
goto keep_locked;
mapping = page_mapping(page);
case PAGE_CLEAN:
; /* try to free the page below */
}
}
/*
* If the page has buffers, try to free the buffer mappings
* associated with this page. If we succeed we try to free
* the page as well.
*
* We do this even if the page is PageDirty().
* try_to_release_page() does not perform I/O, but it is
* possible for a page to have PageDirty set, but it is actually
* clean (all its buffers are clean). This happens if the
* buffers were written out directly, with submit_bh(). ext3
* will do this, as well as the blockdev mapping.
* try_to_release_page() will discover that cleanness and will
* drop the buffers and mark the page clean - it can be freed.
*
* Rarely, pages can have buffers and no ->mapping. These are
* the pages which were not successfully invalidated in
* truncate_complete_page(). We try to drop those buffers here
* and if that worked, and the page is no longer mapped into
* process address space (page_count == 1) it can be freed.
* Otherwise, leave the page on the LRU so it is swappable.
*/
if (page_has_private(page)) {
if (!try_to_release_page(page, sc->gfp_mask))
goto activate_locked;
if (!mapping && page_count(page) == 1) {
unlock_page(page);
if (put_page_testzero(page))
goto free_it;
else {
/*
* rare race with speculative reference.
* the speculative reference will free
* this page shortly, so we may
* increment nr_reclaimed here (and
* leave it off the LRU).
*/
nr_reclaimed++;
continue;
}
}
}
if (PageAnon(page) && !PageSwapBacked(page)) {
/* follow __remove_mapping for reference */
if (!page_ref_freeze(page, 1))
goto keep_locked;
if (PageDirty(page)) {
page_ref_unfreeze(page, 1);
goto keep_locked;
}
count_vm_event(PGLAZYFREED);
count_memcg_page_event(page, PGLAZYFREED);
} else if (!mapping || !__remove_mapping(mapping, page, true))
goto keep_locked;
unlock_page(page);
free_it:
nr_reclaimed++;
/*
* Is there need to periodically free_page_list? It would
* appear not as the counts should be low
*/
if (unlikely(PageTransHuge(page))) {
mem_cgroup_uncharge(page);
(*get_compound_page_dtor(page))(page);
} else
list_add(&page->lru, &free_pages);
continue;
activate_locked:
/* Not a candidate for swapping, so reclaim swap space. */
if (PageSwapCache(page) && (mem_cgroup_swap_full(page) ||
PageMlocked(page)))
try_to_free_swap(page);
VM_BUG_ON_PAGE(PageActive(page), page);
if (!PageMlocked(page)) {
SetPageActive(page);
pgactivate++;
count_memcg_page_event(page, PGACTIVATE);
}
keep_locked:
unlock_page(page);
keep:
list_add(&page->lru, &ret_pages);
VM_BUG_ON_PAGE(PageLRU(page) || PageUnevictable(page), page);
}
mem_cgroup_uncharge_list(&free_pages);
try_to_unmap_flush();
free_unref_page_list(&free_pages);
list_splice(&ret_pages, page_list);
count_vm_events(PGACTIVATE, pgactivate);
if (stat) {
stat->nr_dirty = nr_dirty;
stat->nr_congested = nr_congested;
stat->nr_unqueued_dirty = nr_unqueued_dirty;
stat->nr_writeback = nr_writeback;
stat->nr_immediate = nr_immediate;
stat->nr_activate = pgactivate;
stat->nr_ref_keep = nr_ref_keep;
stat->nr_unmap_fail = nr_unmap_fail;
}
return nr_reclaimed;
}
shrink_slab
遍历全局变量shrinker_list上注册的shrinker,调用对应的scan_object函数进行回收。
static unsigned long shrink_slab(gfp_t gfp_mask, int nid,
struct mem_cgroup *memcg,
int priority)
{
unsigned long ret, freed = 0;
struct shrinker *shrinker;
if (!mem_cgroup_is_root(memcg))
return shrink_slab_memcg(gfp_mask, nid, memcg, priority);
if (!down_read_trylock(&shrinker_rwsem))
goto out;
list_for_each_entry(shrinker, &shrinker_list, list) {
struct shrink_control sc = {
.gfp_mask = gfp_mask,
.nid = nid,
.memcg = memcg,
};
ret = do_shrink_slab(&sc, shrinker, priority);
if (ret == SHRINK_EMPTY)
ret = 0;
freed += ret;
/*
* Bail out if someone want to register a new shrinker to
* prevent the regsitration from being stalled for long periods
* by parallel ongoing shrinking.
*/
if (rwsem_is_contended(&shrinker_rwsem)) {
freed = freed ? : 1;
break;
}
}
up_read(&shrinker_rwsem);
out:
cond_resched();
return freed;
}
__alloc_pages_direct_reclaim
static inline struct page *
__alloc_pages_direct_reclaim(gfp_t gfp_mask, unsigned int order,
unsigned int alloc_flags, const struct alloc_context *ac,
unsigned long *did_some_progress)
struct page *page = NULL;
bool drained = false;
*did_some_progress = __perform_reclaim(gfp_mask, order, ac);
if (unlikely(!(*did_some_progress)))
return NULL;
retry:
page = get_page_from_freelist(gfp_mask, order, alloc_flags, ac);
/*
* If an allocation failed after direct reclaim, it could be because
* pages are pinned on the per-cpu lists or in high alloc reserves.
* Shrink them them and try again
*/
if (!page && !drained) {
unreserve_highatomic_pageblock(ac, false);
drain_all_pages(NULL);
drained = true;
goto retry;
}
return page;
代码流程如下