http://blog.chinaunix.net/uid-20729583-id-1884604.html
/*
*下面的alloc_pages(gfp_mask,order)函數用來請求2^order個連續的頁框
*/
#define alloc_pages(gfp_mask, order) \
alloc_pages_node(numa_node_id(), gfp_mask, order)
#define numa_node_id() (cpu_to_node(raw_smp_processor_id()))
/* Returns the number of the node containing CPU 'cpu' */
static inline int cpu_to_node(int cpu)
{
return cpu_2_node[cpu];
}
int cpu_2_node[NR_CPUS] __read_mostly = { [0 ... NR_CPUS-1] = 0};//每個CPU都有互相對應的節點,__read_mostly是gcc的一個
//屬性
//配置設定頁面函數,這個函數比較複雜,所牽涉到的内容也比較多,尤其是程序方面的内容
static inline struct page *alloc_pages_node(int nid, gfp_t gfp_mask,
unsigned int order)
{
if (unlikely(order >= MAX_ORDER)) /*如果要求配置設定的頁數大于MAX_ORDER就以失敗告終,這裡的MAX_ORDER指的是最大頁面号,這裡要注意的是對于夥伴算法,所配置設定的 頁面的最大值為2^10,即1024個頁面,這一點在夥伴算法中經常會使用到,是以這裡的MAX_ORDER的值為11,也就是說如果order的值大于了10,即超出了最大值,那麼就會以失敗告終,直接以失敗傳回。*/
return NULL; /*從這個判斷可以了解到,所配置設定頁的最大的值為 2^10次方,即1KB個頁面,即最大不能超過4MB。*/
/* Unknown node is current node */
if (nid < 0)
nid = numa_node_id();/*具體實作: #define numa_node_id() (cpu_to_node(raw_smp_processor_id()))
//最後得到的值為0,因為假設現在隻有一個CPU */
/*
/* Returns the number of the node containing CPU 'cpu'
static inline int cpu_to_node(int cpu)
{
return cpu_2_node[cpu];//int cpu_2_node[NR_CPUS] __read_mostly = { [0 ... NR_CPUS-1] = 0 };/* 這又是C語言中使用的一個新的數組初始化的方法。 //read_mostly是在最後執行的時候被組織到一起,這被認為是為了提高效率,因為在多CPU系統中它改善了通路的時間。*/
}
*/
return __alloc_pages(gfp_mask, order,
NODE_DATA(nid)->node_zonelists + gfp_zone(gfp_mask)); /*這是夥伴算法的核心實作,node_zonelists是zone_list類型,gfp_zone的傳回值為ZONE_DMA或者是ZONE_NORMAL或ZONE_HIGH,這三個區分别對應着一個值,ZONE_DMA為0,ZONE_NORMAL為1,ZONE_HIGH為2,即__alloc_pages配置設定頁面的管理區由的三個參數決定,如果gfp_zone的傳回值為0,就是在ZONE_DMA管理區中配置設定,如果gfp_zone傳回值為1,就是在ZONE_NORMAL中進行配置設定,如果gfp_zone的傳回值為2,就是在ZONE_HIGH中進行配置設定。*/
//下面是NDOE_DATA的具體定義:
/*
struct pglist_data *node_data[MAX_NUMNODES] __read_mostly;這裡的MAX_NUMNODES的值為1,即就定義一個節點
*/
}
/*
* This is the 'heart' of the zoned buddy allocator.
* 這個算法是夥伴算法的核心操作
*/
struct page * fastcall __alloc_pages(gfp_t gfp_mask, unsigned int order,
struct zonelist *zonelist)
{
const gfp_t wait = gfp_mask & __GFP_WAIT; /*為了實作檢視是否允許核心對等待空閑頁框的目前程序進行阻塞*/
struct zone **z; //這裡為何要使用雙重指針???
struct page *page; //指向頁描述符的指針
struct reclaim_state reclaim_state; //可回收頁面操作
/*
* current->reclaim_state points to one of these when a task is running
* memory reclaim
用于回收頁面
*/
struct task_struct *p = current; //将p設定成指向目前程序
int do_retry; //
int alloc_flags; //配置設定标志
int did_some_progress;
might_sleep_if(wait); //對可能睡眠的函數進行注釋
if (should_fail_alloc_page(gfp_mask, order)) /*檢查記憶體配置設定是否可行,如果不可行就直接傳回,即以失敗告終,否則就繼續執行記憶體配置設定*/
return NULL;
restart:
z = zonelist->zones; /* the list of zones suitable for gfp_mask *///首先讓z指向第一個管理區
if (unlikely(*z == NULL)) { /*unlikely()宏的功能很有意思的,可以自己去進行驗證。這裡要實作的如果*z==NULL,那麼就傳回NULL,否則就繼續執行。*/
/* Should this ever happen?? */
return NULL;
}
page = get_page_from_freelist(gfp_mask|__GFP_HARDWALL, order,
zonelist, ALLOC_WMARK_LOW|ALLOC_CPUSET); //從空閑連結清單中擷取2^order頁記憶體
//這是get_page_from_freelist函數的原型
// get_page_from_freelist(gfp_t gfp_mask, unsigned int order,struct zonelist *zonelist, int alloc_flags)
if (page)
goto got_pg; //如果獲得了相應的頁就退出,否則繼續執行
/*
* GFP_THISNODE (meaning __GFP_THISNODE, __GFP_NORETRY and
#define GFP_THISNODE (__GFP_THISNODE | __GFP_NOWARN | __GFP_NORETRY)
* __GFP_NOWARN set) should not cause reclaim since the subsystem
* (f.e. slab) using GFP_THISNODE may choose to trigger reclaim
* using a larger set of nodes after it has established that the
* allowed per node queues are empty and that nodes are
* over allocated.
*/
if (NUMA_BUILD && (gfp_mask & GFP_THISNODE) == GFP_THISNODE) //在不支援NUMA的情況下跳轉到nopage處
goto nopage;
for (z = zonelist->zones; *z; z++)
wakeup_kswapd(*z, order);//回收頁面操作,待解
/
*
* A zone is low on free memory, so wake its kswapd task to service it.
*
void wakeup_kswapd(struct zone *zone, int order)
{
pg_data_t *pgdat;
if (!populated_zone(zone)) /*return !!(zone->present_pages) zone->present_pages是以頁為機關的管理區的總大小,如果以頁為機關的管理區的總大小為0,那麼就直接結束退出*/
return;
pgdat = zone->zone_pgdat;
if (zone_watermark_ok(zone, order, zone->pages_low, 0, 0))
return;
if (pgdat->kswapd_max_order < order)
pgdat->kswapd_max_order = order;
if (!cpuset_zone_allowed_hardwall(zone, GFP_KERNEL))
return;
if (!waitqueue_active(&pgdat->kswapd_wait))
return;
wake_up_interruptible(&pgdat->kswapd_wait);
}
*
/*
* OK, we're below the kswapd watermark and have kicked background
* reclaim. Now things get more complex, so set up alloc_flags according
* to how we want to proceed.
*
* The caller may dip into page reserves a bit more if the caller
* cannot run direct reclaim, or if the caller has realtime scheduling
* policy or is asking for __GFP_HIGH memory. GFP_ATOMIC requests will
* set both ALLOC_HARDER (!wait) and ALLOC_HIGH (__GFP_HIGH).
*/
alloc_flags = ALLOC_WMARK_MIN; //
/
#define ALLOC_NO_WATERMARKS 0x01 /* don't check watermarks at all *
#define ALLOC_WMARK_MIN 0x02 /* use pages_min watermark *
#define ALLOC_WMARK_LOW 0x04 /* use pages_low watermark *
#define ALLOC_WMARK_HIGH 0x08 /* use pages_high watermark *
#define ALLOC_HARDER 0x10 /* try to alloc harder *
#define ALLOC_HIGH 0x20 /* __GFP_HIGH set *
#define ALLOC_CPUSET 0x40 /* check for correct cpuset *
*/
if ((unlikely(rt_task(p)) && !in_interrupt()) || !wait)
alloc_flags |= ALLOC_HARDER;
if (gfp_mask & __GFP_HIGH)
alloc_flags |= ALLOC_HIGH;
if (wait)
alloc_flags |= ALLOC_CPUSET;
/*
* Go through the zonelist again. Let __GFP_HIGH and allocations
* coming from realtime tasks go deeper into reserves.
*
* This is the last chance, in general, before the goto nopage.
* Ignore cpuset if GFP_ATOMIC (!wait) rather than fail alloc.
* See also cpuset_zone_allowed() comment in kernel/cpuset.c.
*/
page = get_page_from_freelist(gfp_mask, order, zonelist, alloc_flags);//在進行了頁面回收後再次進行頁面的配置設定操作
if (page)
goto got_pg; //如果配置設定成功,就成功傳回
/* This allocation should allow future memory freeing. */
rebalance:
if (((p->flags & PF_MEMALLOC) || unlikely(test_thread_flag(TIF_MEMDIE)))//#define PF_MEMALLOC 0x00000800 /* Allocating memory */ TIF_MEMDIE=16
/
6define test_thread_flag(flag) \
test_ti_thread_flag(current_thread_info(), flag)
static inline int test_ti_thread_flag(struct thread_info *ti, int flag)
{
return test_bit(flag,&ti->flags);
}
*
&& !in_interrupt()) {
if (!(gfp_mask & __GFP_NOMEMALLOC)) {
nofail_alloc:
/* go through the zonelist yet again, ignoring mins */
page = get_page_from_freelist(gfp_mask, order,
zonelist, ALLOC_NO_WATERMARKS);
if (page)
goto got_pg;
if (gfp_mask & __GFP_NOFAIL) {
congestion_wait(WRITE, HZ/50);
goto nofail_alloc;
}
}
goto nopage;
}
/* Atomic allocations - we can't balance anything */
if (!wait) //原子配置設定,就跳轉到nopage,即沒有空閑頁
goto nopage;
cond_resched();
/* We now go into synchronous reclaim 現在進入異步回收*/
cpuset_memory_pressure_bump();
p->flags |= PF_MEMALLOC;
reclaim_state.reclaimed_slab = 0;
p->reclaim_state = &reclaim_state;
did_some_progress = try_to_free_pages(zonelist->zones, order, gfp_mask);
p->reclaim_state = NULL;
p->flags &= ~PF_MEMALLOC;
cond_resched();
if (likely(did_some_progress)) {
page = get_page_from_freelist(gfp_mask, order,
zonelist, alloc_flags);
if (page)
goto got_pg;
} else if ((gfp_mask & __GFP_FS) && !(gfp_mask & __GFP_NORETRY)) {//If set the mark of the __GFP_FS zero,Then it doesn't allow the kernel execute the operation depending the filesystem .The mark of __Gfp_NORETRY means that you can allocate the page only once.Here allows allocate many times
/*
* Go through the zonelist yet one more time, keep
* very high watermark here, this is only to catch
* a parallel oom killing, we must fail if we're still
* under heavy pressure.
*/
page = get_page_from_freelist(gfp_mask|__GFP_HARDWALL, order,
zonelist, ALLOC_WMARK_HIGH|ALLOC_CPUSET);
if (page)
goto got_pg;
/* The OOM killer will not help higher order allocs so fail */
if (order > PAGE_ALLOC_COSTLY_ORDER)
goto nopage;
/*
*PAGE_ALLOC_COSTLY_ORDER是那些配置設定行為被認為是一項花費較大的服務所對應的定值,
* PAGE_ALLOC_COSTLY_ORDER is the order at which allocations are deemed
* costly to service. That is between allocation orders which should
* coelesce naturally under reasonable reclaim pressure and those which
* will not.
*
#define PAGE_ALLOC_COSTLY_ORDER 3
*
out_of_memory(zonelist, gfp_mask, order);
goto restart;
}
/*
* Don't let big-order allocations loop unless the caller explicitly
* requests that. Wait for some write requests to complete then retry.
*
* In this implementation, __GFP_REPEAT means __GFP_NOFAIL for order
* <= 3, but that may not be true in other implementations.
*/
do_retry = 0;
if (!(gfp_mask & __GFP_NORETRY)) {
if ((order <= PAGE_ALLOC_COSTLY_ORDER) ||
(gfp_mask & __GFP_REPEAT))
do_retry = 1;
if (gfp_mask & __GFP_NOFAIL)
do_retry = 1;
}
if (do_retry) {
congestion_wait(WRITE, HZ/50);
goto rebalance;
}
nopage:
if (!(gfp_mask & __GFP_NOWARN) && printk_ratelimit()) {
printk(KERN_WARNING "%s: page allocation failure."
" order:%d, mode:0x%x\n",
p->comm, order, gfp_mask);
dump_stack();
/
*
* The architecture-independent dump_stack generator
*
void dump_stack(void)
{
unsigned long stack;
show_trace(current, NULL, &stack);
}
2void show_trace(struct task_struct *task, struct pt_regs *regs,
unsigned long * stack)
{
show_trace_log_lvl(task, regs, stack, "");
}
*
show_mem();//如果沒有空閑的頁就顯示記憶體具體分布,即羅列出相應的資訊
}
got_pg:
return page;
}
EXPORT_SYMBOL(__alloc_pages);
需要的小夥伴私信回複核心免費領取
原文位址:Linux核心記憶體管理alloc_pages()函數分析 - 圈點 - 核心技術中文網 - 建構全國最權威的核心技術交流分享論壇(版權歸原文作者所有,侵權聯系删除)