Patch "mm/page_alloc: call check_new_pages() while zone spinlock is not held" has been added to the 5.15-stable tree

[Sasha Levin <sashal@xxxxxxxxxx>]

This is a note to let you know that I've just added the patch titled

    mm/page_alloc: call check_new_pages() while zone spinlock is not held

to the 5.15-stable tree which can be found at:
    http://www.kernel.org/git/?p=linux/kernel/git/stable/stable-queue.git;a=summary

The filename of the patch is:
     mm-page_alloc-call-check_new_pages-while-zone-spinlo.patch
and it can be found in the queue-5.15 subdirectory.

If you, or anyone else, feels it should not be added to the stable tree,
please let <stable@xxxxxxxxxxxxxxx> know about it.



commit 8a6a5f3d06c606cfc62400eac84532a110cd2844
Author: Eric Dumazet <edumazet@xxxxxxxxxx>
Date:   Tue Mar 22 14:43:57 2022 -0700

    mm/page_alloc: call check_new_pages() while zone spinlock is not held
    
    [ Upstream commit 3313204c8ad553cf93f1ee8cc89456c73a7df938 ]
    
    For high order pages not using pcp, rmqueue() is currently calling the
    costly check_new_pages() while zone spinlock is held, and hard irqs
    masked.
    
    This is not needed, we can release the spinlock sooner to reduce zone
    spinlock contention.
    
    Note that after this patch, we call __mod_zone_freepage_state() before
    deciding to leak the page because it is in bad state.
    
    Link: https://lkml.kernel.org/r/20220304170215.1868106-1-eric.dumazet@xxxxxxxxx
    Signed-off-by: Eric Dumazet <edumazet@xxxxxxxxxx>
    Reviewed-by: Shakeel Butt <shakeelb@xxxxxxxxxx>
    Acked-by: David Rientjes <rientjes@xxxxxxxxxx>
    Acked-by: Mel Gorman <mgorman@xxxxxxxxxxxxxxxxxxx>
    Reviewed-by: Vlastimil Babka <vbabka@xxxxxxx>
    Cc: Michal Hocko <mhocko@xxxxxxxxxx>
    Cc: Wei Xu <weixugc@xxxxxxxxxx>
    Cc: Greg Thelen <gthelen@xxxxxxxxxx>
    Cc: Hugh Dickins <hughd@xxxxxxxxxx>
    Signed-off-by: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx>
    Signed-off-by: Linus Torvalds <torvalds@xxxxxxxxxxxxxxxxxxxx>
    Stable-dep-of: 281dd25c1a01 ("mm/page_alloc: let GFP_ATOMIC order-0 allocs access highatomic reserves")
    Signed-off-by: Sasha Levin <sashal@xxxxxxxxxx>

diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 264efa022fa96..474150584ba48 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -3698,10 +3698,10 @@ struct page *rmqueue(struct zone *preferred_zone,
 	 * allocate greater than order-1 page units with __GFP_NOFAIL.
 	 */
 	WARN_ON_ONCE((gfp_flags & __GFP_NOFAIL) && (order > 1));
-	spin_lock_irqsave(&zone->lock, flags);
 
 	do {
 		page = NULL;
+		spin_lock_irqsave(&zone->lock, flags);
 		/*
 		 * order-0 request can reach here when the pcplist is skipped
 		 * due to non-CMA allocation context. HIGHATOMIC area is
@@ -3713,15 +3713,15 @@ struct page *rmqueue(struct zone *preferred_zone,
 			if (page)
 				trace_mm_page_alloc_zone_locked(page, order, migratetype);
 		}
-		if (!page)
+		if (!page) {
 			page = __rmqueue(zone, order, migratetype, alloc_flags);
-	} while (page && check_new_pages(page, order));
-	if (!page)
-		goto failed;
-
-	__mod_zone_freepage_state(zone, -(1 << order),
-				  get_pcppage_migratetype(page));
-	spin_unlock_irqrestore(&zone->lock, flags);
+			if (!page)
+				goto failed;
+		}
+		__mod_zone_freepage_state(zone, -(1 << order),
+					  get_pcppage_migratetype(page));
+		spin_unlock_irqrestore(&zone->lock, flags);
+	} while (check_new_pages(page, order));
 
 	__count_zid_vm_events(PGALLOC, page_zonenum(page), 1 << order);
 	zone_statistics(preferred_zone, zone, 1);