Re: [PATCH 3/6] mm/page_alloc: Explicitly record high-order atomic allocations in alloc_flags

[Vlastimil Babka]

On 11/29/22 16:16, Mel Gorman wrote:
> A high-order ALLOC_HARDER allocation is assumed to be atomic. While that
> is accurate, it changes later in the series. In preparation, explicitly
> record high-order atomic allocations in gfp_to_alloc_flags().
> 
> Signed-off-by: Mel Gorman <mgorman@xxxxxxxxxxxxxxxxxxx>
> ---
>  mm/internal.h   |  1 +
>  mm/page_alloc.c | 19 +++++++++++++------
>  2 files changed, 14 insertions(+), 6 deletions(-)
> 
> diff --git a/mm/internal.h b/mm/internal.h
> index d503e57a57a1..9a9d9b5ee87f 100644
> --- a/mm/internal.h
> +++ b/mm/internal.h
> @@ -754,6 +754,7 @@ unsigned int reclaim_clean_pages_from_list(struct zone *zone,
>  #else
>  #define ALLOC_NOFRAGMENT	  0x0
>  #endif
> +#define ALLOC_HIGHATOMIC	0x200 /* Allows access to MIGRATE_HIGHATOMIC */
>  #define ALLOC_KSWAPD		0x800 /* allow waking of kswapd, __GFP_KSWAPD_RECLAIM set */
>  
>  enum ttu_flags;
> diff --git a/mm/page_alloc.c b/mm/page_alloc.c
> index da746e9eb2cf..e2b65767dda0 100644
> --- a/mm/page_alloc.c
> +++ b/mm/page_alloc.c
> @@ -3710,7 +3710,7 @@ struct page *rmqueue_buddy(struct zone *preferred_zone, struct zone *zone,
>  		 * reserved for high-order atomic allocation, so order-0
>  		 * request should skip it.
>  		 */
> -		if (order > 0 && alloc_flags & ALLOC_HARDER)
> +		if (alloc_flags & ALLOC_HIGHATOMIC)
>  			page = __rmqueue_smallest(zone, order, MIGRATE_HIGHATOMIC);
>  		if (!page) {
>  			page = __rmqueue(zone, order, migratetype, alloc_flags);
> @@ -4028,8 +4028,10 @@ bool __zone_watermark_ok(struct zone *z, unsigned int order, unsigned long mark,
>  			return true;
>  		}
>  #endif
> -		if (alloc_harder && !free_area_empty(area, MIGRATE_HIGHATOMIC))
> +		if ((alloc_flags & ALLOC_HIGHATOMIC) &&
> +		    !free_area_empty(area, MIGRATE_HIGHATOMIC)) {
>  			return true;

alloc_harder is defined as
	(alloc_flags & (ALLOC_HARDER|ALLOC_OOM));
AFAICS this means we no longer allow ALLOC_OOM to use the highatomic
reserve. Isn't that a risk?

> +		}
>  	}
>  	return false;
>  }
> @@ -4291,7 +4293,7 @@ get_page_from_freelist(gfp_t gfp_mask, unsigned int order, int alloc_flags,
>  			 * If this is a high-order atomic allocation then check
>  			 * if the pageblock should be reserved for the future
>  			 */
> -			if (unlikely(order && (alloc_flags & ALLOC_HARDER)))
> +			if (unlikely(alloc_flags & ALLOC_HIGHATOMIC))
>  				reserve_highatomic_pageblock(page, zone, order);
>  
>  			return page;
> @@ -4818,7 +4820,7 @@ static void wake_all_kswapds(unsigned int order, gfp_t gfp_mask,
>  }
>  
>  static inline unsigned int
> -gfp_to_alloc_flags(gfp_t gfp_mask)
> +gfp_to_alloc_flags(gfp_t gfp_mask, unsigned int order)
>  {
>  	unsigned int alloc_flags = ALLOC_WMARK_MIN | ALLOC_CPUSET;
>  
> @@ -4844,8 +4846,13 @@ gfp_to_alloc_flags(gfp_t gfp_mask)
>  		 * Not worth trying to allocate harder for __GFP_NOMEMALLOC even
>  		 * if it can't schedule.
>  		 */
> -		if (!(gfp_mask & __GFP_NOMEMALLOC))
> +		if (!(gfp_mask & __GFP_NOMEMALLOC)) {
>  			alloc_flags |= ALLOC_HARDER;
> +
> +			if (order > 0)
> +				alloc_flags |= ALLOC_HIGHATOMIC;
> +		}
> +
>  		/*
>  		 * Ignore cpuset mems for GFP_ATOMIC rather than fail, see the
>  		 * comment for __cpuset_node_allowed().
> @@ -5053,7 +5060,7 @@ __alloc_pages_slowpath(gfp_t gfp_mask, unsigned int order,
>  	 * 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);
> +	alloc_flags = gfp_to_alloc_flags(gfp_mask, order);
>  
>  	/*
>  	 * We need to recalculate the starting point for the zonelist iterator