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

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@gmail.com
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reviewed-by: Shakeel Butt <shakeelb@google.com>
Acked-by: David Rientjes <rientjes@google.com>
Acked-by: Mel Gorman <mgorman@techsingularity.net>
Reviewed-by: Vlastimil Babka <vbabka@suse.cz>
Cc: Michal Hocko <mhocko@kernel.org>
Cc: Wei Xu <weixugc@google.com>
Cc: Greg Thelen <gthelen@google.com>
Cc: Hugh Dickins <hughd@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 30d35f24d7a55804e69ede7fc52d465cbf8b89c2..5d126853e239c47e3af75c0c18d11188e285ef53 100644 (file)
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -3665,10 +3665,10 @@ 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
@@ -3680,15 +3680,15 @@ 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);