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: Mel Gorman <mgorman@techsingularity.net>
Acked-by: Vlastimil Babka <vbabka@suse.cz>
Acked-by: Michal 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: Andrew Morton <akpm@linux-foundation.org>

2 files changed, 24 insertions, 6 deletions

diff --git a/mm/internal.h b/mm/internal.h
index 99eb544fbded..62428467d7cf 100644
--- a/mm/internal.h
+++ b/mm/internal.h
@@ -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;
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 4f5c2e83cb7b..8a7e1cfa8353 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -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;
@@ -4041,8 +4051,10 @@ 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|ALLOC_OOM)) &&
+		    !free_area_empty(area, MIGRATE_HIGHATOMIC)) {
 			return true;
+		}
 	}
 	return false;
 }
@@ -4304,7 +4316,7 @@ try_this_zone:
 			 * 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 @@ restart:
 	 * 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