[prev in list] [next in list] [prev in thread] [next in thread] 

List:       linux-kernel
Subject:    Re: [PATCH v9 3/3] mm: Maintain randomization of page free lists
From:       Andrew Morton <akpm () linux-foundation ! org>
Date:       2019-01-31 22:14:51
Message-ID: 20190131141451.f60cdc434f97a31e3136ade4 () linux-foundation ! org
[Download RAW message or body]

On Tue, 29 Jan 2019 21:02:26 -0800 Dan Williams <dan.j.williams@intel.com> wrote:

> When freeing a page with an order >= shuffle_page_order randomly select
> the front or back of the list for insertion.
> 
> While the mm tries to defragment physical pages into huge pages this can
> tend to make the page allocator more predictable over time. Inject the
> front-back randomness to preserve the initial randomness established by
> shuffle_free_memory() when the kernel was booted.
> 
> The overhead of this manipulation is constrained by only being applied
> for MAX_ORDER sized pages by default.
> 
> 
> ...
>
> --- a/include/linux/mmzone.h
> +++ b/include/linux/mmzone.h
> @@ -98,6 +98,10 @@ extern int page_group_by_mobility_disabled;
>  struct free_area {
>  	struct list_head	free_list[MIGRATE_TYPES];
>  	unsigned long		nr_free;
> +#ifdef CONFIG_SHUFFLE_PAGE_ALLOCATOR
> +	u64			rand;
> +	u8			rand_bits;
> +#endif
>  };
>  
>  /* Used for pages not on another list */
> @@ -116,6 +120,14 @@ static inline void add_to_free_area_tail(struct page *page, struct free_area *ar
>  	area->nr_free++;
>  }
>  
> +#ifdef CONFIG_SHUFFLE_PAGE_ALLOCATOR
> +/* Used to preserve page allocation order entropy */
> +void add_to_free_area_random(struct page *page, struct free_area *area,
> +		int migratetype);
> +#else
> +#define add_to_free_area_random add_to_free_area

A static inline would be nicer.

> +#endif
> +
>  /* Used for pages which are on another list */
>  static inline void move_to_free_area(struct page *page, struct free_area *area,
>  			     int migratetype)
> 
> ...
>
> --- a/mm/shuffle.c
> +++ b/mm/shuffle.c
> @@ -186,3 +186,19 @@ void __meminit __shuffle_free_memory(pg_data_t *pgdat)
>  	for (z = pgdat->node_zones; z < pgdat->node_zones + MAX_NR_ZONES; z++)
>  		shuffle_zone(z);
>  }
> +
> +void add_to_free_area_random(struct page *page, struct free_area *area,
> +		int migratetype)
> +{
> +	if (area->rand_bits == 0) {
> +		area->rand_bits = 64;
> +		area->rand = get_random_u64();
> +	}
> +
> +	if (area->rand & 1)
> +		add_to_free_area(page, area, migratetype);
> +	else
> +		add_to_free_area_tail(page, area, migratetype);
> +	area->rand_bits--;
> +	area->rand >>= 1;
> +}

Well that's nice and simple.
[prev in list] [next in list] [prev in thread] [next in thread]