Re: [PATCH 28/28] mm, page_alloc: Defer debugging checks of pages allocated from the PCP

[Naoya Horiguchi]

> @@ -2579,20 +2612,22 @@ struct page *buffered_rmqueue(struct zone *preferred_zone,
>  		struct list_head *list;
>  
>  		local_irq_save(flags);
> -		pcp = &this_cpu_ptr(zone->pageset)->pcp;
> -		list = &pcp->lists[migratetype];
> -		if (list_empty(list)) {
> -			pcp->count += rmqueue_bulk(zone, 0,
> -					pcp->batch, list,
> -					migratetype, cold);
> -			if (unlikely(list_empty(list)))
> -				goto failed;
> -		}
> +		do {
> +			pcp = &this_cpu_ptr(zone->pageset)->pcp;
> +			list = &pcp->lists[migratetype];
> +			if (list_empty(list)) {
> +				pcp->count += rmqueue_bulk(zone, 0,
> +						pcp->batch, list,
> +						migratetype, cold);
> +				if (unlikely(list_empty(list)))
> +					goto failed;
> +			}
>  
> -		if (cold)
> -			page = list_last_entry(list, struct page, lru);
> -		else
> -			page = list_first_entry(list, struct page, lru);
> +			if (cold)
> +				page = list_last_entry(list, struct page, lru);
> +			else
> +				page = list_first_entry(list, struct page, lru);
> +		} while (page && check_new_pcp(page));

This causes infinite loop when check_new_pcp() returns 1, because the bad
page is still in the list (I assume that a bad page never disappears).
The original kernel is free from this problem because we do retry after
list_del(). So moving the following 3 lines into this do-while block solves
the problem?

    __dec_zone_state(zone, NR_ALLOC_BATCH);
    list_del(&page->lru);                  
    pcp->count--;                          

There seems no infinit loop issue in order > 0 block below, because bad pages
are deleted from free list in __rmqueue_smallest().

Thanks,
Naoya Horiguchi

>  
>  		__dec_zone_state(zone, NR_ALLOC_BATCH);
>  		list_del(&page->lru);
> @@ -2605,14 +2640,16 @@ struct page *buffered_rmqueue(struct zone *preferred_zone,
>  		WARN_ON_ONCE((gfp_flags & __GFP_NOFAIL) && (order > 1));
>  		spin_lock_irqsave(&zone->lock, flags);
>  
> -		page = NULL;
> -		if (alloc_flags & ALLOC_HARDER) {
> -			page = __rmqueue_smallest(zone, order, MIGRATE_HIGHATOMIC);
> -			if (page)
> -				trace_mm_page_alloc_zone_locked(page, order, migratetype);
> -		}
> -		if (!page)
> -			page = __rmqueue(zone, order, migratetype);
> +		do {
> +			page = NULL;
> +			if (alloc_flags & ALLOC_HARDER) {
> +				page = __rmqueue_smallest(zone, order, MIGRATE_HIGHATOMIC);
> +				if (page)
> +					trace_mm_page_alloc_zone_locked(page, order, migratetype);
> +			}
> +			if (!page)
> +				page = __rmqueue(zone, order, migratetype);
> +		} while (page && check_new_pages(page, order));
>  		spin_unlock(&zone->lock);
>  		if (!page)
>  			goto failed;
> @@ -2979,8 +3016,7 @@ get_page_from_freelist(gfp_t gfp_mask, unsigned int order, int alloc_flags,
>  		page = buffered_rmqueue(ac->preferred_zoneref->zone, zone, order,
>  				gfp_mask, alloc_flags, ac->migratetype);
>  		if (page) {
> -			if (prep_new_page(page, order, gfp_mask, alloc_flags))
> -				goto try_this_zone;
> +			prep_new_page(page, order, gfp_mask, alloc_flags);
>  
>  			/*
>  			 * If this is a high-order atomic allocation then check
> -- 
> 2.6.4
> 
> --
> To unsubscribe, send a message with 'unsubscribe linux-mm' in
> the body to majordomo@xxxxxxxxxx  For more info on Linux MM,
> see: http://www.linux-mm.org/ .
> Don't email: <a href=mailto:"dont@xxxxxxxxx";> email@xxxxxxxxx </a>