Commit eb2e2b42 authored by Mel Gorman's avatar Mel Gorman Committed by Andrew Morton
Browse files

mm/page_alloc: explicitly record high-order atomic allocations in alloc_flags 

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().

Link: https://lkml.kernel.org/r/20230113111217.14134-4-mgorman@techsingularity.net


Signed-off-by: default avatarMel Gorman <mgorman@techsingularity.net>
Acked-by: default avatarVlastimil Babka <vbabka@suse.cz>
Acked-by: default avatarMichal Hocko <mhocko@suse.com>
Cc: Matthew Wilcox <willy@infradead.org>
Cc: NeilBrown <neilb@suse.de>
Cc: Thierry Reding <thierry.reding@gmail.com>
Signed-off-by: default avatarAndrew Morton <akpm@linux-foundation.org>
parent c988dcbe

mm/internal.h

+1 −0
Original line number Diff line number Diff line
@@ -789,6 +789,7 @@ 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;

mm/page_alloc.c

+23 −6
Original line number Diff line number Diff line
@@ -3724,10 +3724,20 @@ 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);



			/*

			 * If the allocation fails, allow OOM handling access

			 * to HIGHATOMIC reserves as failing now is worse than

			 * failing a high-order atomic allocation in the

			 * future.

			 */

			if (!page && (alloc_flags & ALLOC_OOM))

				page = __rmqueue_smallest(zone, order, MIGRATE_HIGHATOMIC);



			if (!page) {

				spin_unlock_irqrestore(&zone->lock, flags);

				return NULL;
@@ -4041,9 +4051,11 @@ 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|ALLOC_OOM)) &&

		    !free_area_empty(area, MIGRATE_HIGHATOMIC)) {

			return true;

		}

	}

	return false;

}
@@ -4304,7 +4316,7 @@ 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;
@@ -4831,7 +4843,7 @@ 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;
@@ -4857,8 +4869,13 @@ 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().
@@ -5066,7 +5083,7 @@ __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