From 9f2fd03c9bde366c928c9242fc9b2e2c5111a134 Mon Sep 17 00:00:00 2001 From: JP Kobryn Date: Mon, 22 Jun 2026 17:46:00 -0700 Subject: [PATCH] mm/page_alloc: use existing highatomic reserves on the buddy fastpath ALLOC_HIGHATOMIC currently provides both access to MIGRATE_HIGHATOMIC free pages and permission to create new highatomic pageblock reserves. This makes it unsuitable for the fastpath. However, the fastpath can reach rmqueue_buddy() while MIGRATE_HIGHATOMIC reserves have free pages available. In this situation, the allocation can fall back to other migratetypes without trying those reserves first. Allow high-priority non-blocking allocations to use existing MIGRATE_HIGHATOMIC reserves on the buddy fastpath without growing them. First tighten the criteria for reserving pageblocks so that growth may only occur in the slowpath. Then allow fastpath usage by enabling ALLOC_HIGHATOMIC when the GFP mask describes a non-blocking high-priority allocation. This logic has been factored out from gfp_to_alloc_flags() to a new function gfp_to_alloc_flags_nonblocking(). A UDP receive workload was run with free MIGRATE_HIGHATOMIC pageblocks available in the target zone. Before this patch, the workload did not consume these blocks. With this patch, eligible order-1 allocations reaching the buddy path consumed existing MIGRATE_HIGHATOMIC pageblocks, with no highatomic misses observed. The workload did not grow highatomic reserves and NAPI page-frag allocations remained healthy with no failures or order-0 fallbacks. Link: https://lore.kernel.org/20260623004600.113347-1-jp.kobryn@linux.dev Signed-off-by: JP Kobryn Reviewed-by: Vlastimil Babka (SUSE) Acked-by: Johannes Weiner Reviewed-by: Shakeel Butt Cc: Brendan Jackman Cc: David Hildenbrand Cc: Frank van der Linden Cc: Liam R. Howlett Cc: Lorenzo Stoakes Cc: Michal Hocko Cc: Mike Rapoport Cc: Suren Baghdasaryan Cc: Zi Yan Signed-off-by: Andrew Morton --- mm/page_alloc.c | 44 ++++++++++++++++++++++++++++++-------------- 1 file changed, 30 insertions(+), 14 deletions(-) diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 549fa83045eb..62f71ece7ca1 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -3249,10 +3249,11 @@ struct page *rmqueue_buddy(struct zone *preferred_zone, struct zone *zone, } while (check_new_pages(page, order)); /* - * If this is a high-order atomic allocation then check - * if the pageblock should be reserved for the future + * Slowpath (precarious) high-atomic allocations may reserve + * a pageblock for future use. */ - if (unlikely(alloc_flags & ALLOC_HIGHATOMIC)) + if (unlikely((alloc_flags & ALLOC_HIGHATOMIC) && + ((alloc_flags & ALLOC_WMARK_MASK) == ALLOC_WMARK_MIN))) reserve_highatomic_pageblock(page, order, zone); __count_zid_vm_events(PGALLOC, page_zonenum(page), 1 << order); @@ -4472,6 +4473,29 @@ static void wake_all_kswapds(unsigned int order, gfp_t gfp_mask, } } +static inline unsigned int +gfp_to_alloc_flags_nonblocking(gfp_t gfp_mask, unsigned int order) +{ + unsigned int alloc_flags = 0; + + if (gfp_mask & __GFP_DIRECT_RECLAIM) + return 0; + + /* + * Not worth trying to allocate harder for __GFP_NOMEMALLOC even + * if it can't schedule. + */ + if (gfp_mask & __GFP_NOMEMALLOC) + return 0; + + alloc_flags |= ALLOC_NON_BLOCK; + + if (order > 0 && (gfp_mask & __GFP_HIGH)) + alloc_flags |= ALLOC_HIGHATOMIC; + + return alloc_flags; +} + static inline unsigned int gfp_to_alloc_flags(gfp_t gfp_mask, unsigned int order) { @@ -4488,18 +4512,9 @@ gfp_to_alloc_flags(gfp_t gfp_mask, unsigned int order) if (gfp_mask & __GFP_KSWAPD_RECLAIM) alloc_flags |= ALLOC_KSWAPD; + alloc_flags |= gfp_to_alloc_flags_nonblocking(gfp_mask, order); + if (!(gfp_mask & __GFP_DIRECT_RECLAIM)) { - /* - * Not worth trying to allocate harder for __GFP_NOMEMALLOC even - * if it can't schedule. - */ - if (!(gfp_mask & __GFP_NOMEMALLOC)) { - alloc_flags |= ALLOC_NON_BLOCK; - - if (order > 0 && (alloc_flags & ALLOC_MIN_RESERVE)) - alloc_flags |= ALLOC_HIGHATOMIC; - } - /* * Ignore cpuset mems for non-blocking __GFP_HIGH (probably * GFP_ATOMIC) rather than fail, see the comment for @@ -5292,6 +5307,7 @@ struct page *__alloc_frozen_pages_noprof(gfp_t gfp, unsigned int order, * memory until all local zones are considered. */ alloc_flags |= alloc_flags_nofragment(zonelist_zone(ac.preferred_zoneref), gfp); + alloc_flags |= gfp_to_alloc_flags_nonblocking(gfp, order) & ALLOC_HIGHATOMIC; /* First allocation attempt */ page = get_page_from_freelist(alloc_gfp, order, alloc_flags, &ac);