/*
* This is the 'heart' of the zoned buddy allocator.
*/
struct page * fastcall
__alloc_pages(gfp_t gfp_mask, unsigned int order,
struct zonelist *zonelist)
{
const gfp_t wait = gfp_mask & __GFP_WAIT;
struct zone **z;
struct page *page;
struct reclaim_state reclaim_state;
struct task_struct *p = current;
int do_retry;
int alloc_flags;
int did_some_progress;
might_sleep_if(wait);
/*一系列宏定义，最后调用cond_resched()
might_sleep_if-> might_sleep->might_resched->cond_resched
如果在gfp_mask中设置了__GFP_WAIT位，表明内核可以阻塞当前进程，来等待空闲页面。在分配开始之前即阻塞，目的是为了等待其它进程释放更多的页面？？
*/
if (should_fail_alloc_page(gfp_mask, order))
/*通过简单算法在真正分配前检查分配是否会失败，避免进入真正的分配程序后浪费系统时间*/
return NULL;
restart:
z = zonelist->zones; /* the list of zones suitable for gfp_mask */
if (unlikely(*z == NULL)) {
/* Should this ever happen?? */
return NULL;
}
page = get_page_from_freelist(gfp_mask|__GFP_HARDWALL, order,
zonelist, ALLOC_WMARK_LOW|ALLOC_CPUSET);
/*get_page_from_freelist以指定的watermark来分配页面
每个zone struct中定义了三个watermark：pages_min, pages_low, pages_high，表示zone中应保持的空闲页面的阈值。
get_page_from_freelist函数通过设置Alloc flags来选择watermark。
#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 */
*/
/*首先以pages_low watermark分配页面，如果分配成功，则跳转到got_pg*/
if (page)
goto got_pg;
/*
* GFP_THISNODE (meaning __GFP_THISNODE, __GFP_NORETRY and
* __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.
*/
/*如果pages_low watermark分配失败的话，检查gfp_mask，如果GFP_THISNODE标志被设置，表明不能重试，因此跳转到nopage，返回失败!*/
if (NUMA_BUILD && (gfp_mask & GFP_THISNODE) == GFP_THISNODE)
goto nopage;
/*否则调用kswapd对zonelist中的所有zone进行页面回首，期待能将一些闲置
页面交换到文件系统中*/
for (z = zonelist->zones; *z; z++)
wakeup_kswapd(*z, order);
/*
* 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;
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.
*/
/*降低对zone中空闲页面得要求，以pages_min再次分配页面*/
page = get_page_from_freelist(gfp_mask, order, zonelist, alloc_flags);
if (page)
goto got_pg;
/* This allocation should allow future memory freeing. */
rebalance:
if (((p->flags & PF_MEMALLOC) || unlikely(test_thread_flag(TIF_MEMDIE)))
&& !in_interrupt()) {
if (!(gfp_mask & __GFP_NOMEMALLOC)) {
nofail_alloc:
/*如果gfp_mask设置不需要保留紧急内存区域，
以不设water_mark再次分配页面*/
/* 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;
/*如果gfp_mask设置了__GFP_NOFAIL，则不断重试，直到分配成功*/
if (gfp_mask & __GFP_NOFAIL) {
congestion_wait(WRITE, HZ/50);
goto nofail_alloc;
}
}
goto nopage;
}
/* Atomic allocations - we can't balance anything */
if (!wait)
goto nopage;
/*重新调度之后，试图释放一些不常用的页面*/
cond_resched();
/* We now go into synchronous reclaim */
cpuset_memory_divssure_bump();
p->flags |= PF_MEMALLOC;
reclaim_state.reclaimed_slab = 0;
p->reclaim_state = &reclaim_state;
did_some_progress = try_to_free_pages(zonelist->zones, gfp_mask);
p->reclaim_state = NULL;
p->flags &= ~PF_MEMALLOC;
cond_resched();
/*调度之后，如果确实释放了一部分页面，则重新分配页面*/
if (likely(did_some_progress)) {
page = get_page_from_freelist(gfp_mask, order,
zonelist, alloc_flags);
if (page)
goto got_pg;
/*如果没有释放页面，并且允许重试，则以pages_high watermark分配页面，因为以pages_high分配，所以除非此时其它的cpu杀死了某个进程，释放了一部分页面，这次分配肯定会失败，失败之后内核通过调用out_of_momery函数杀死某个经过选择的进程，获得一部分空闲页面。采用pages_high watermark可以避免两个cpu都选择某个进程来杀死，从而造成不必要的损失。*/
} else if ((gfp_mask & __GFP_FS) && !(gfp_mask & __GFP_NORETRY)) {
/*
* 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 divssure.
*/
page = get_page_from_freelist(gfp_mask|__GFP_HARDWALL, order,
zonelist, ALLOC_WMARK_HIGH|ALLOC_CPUSET);
if (page)
goto got_pg;
/*在这里选择某个进程杀死，释放部分空闲页面*/
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 <= 3) || (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();
show_mem();
}
got_pg:
return page;
}
