From 233075bea4efb193907f37b72c1ca77d9d432b40 Mon Sep 17 00:00:00 2001 From: Mel Gorman Date: Fri, 24 Jun 2022 13:54:18 +0100 Subject: [PATCH] BACKPORT: mm/page_alloc: use only one PCP list for THP-sized allocations The per_cpu_pages is cache-aligned on a standard x86-64 distribution configuration but a later patch will add a new field which would push the structure into the next cache line. Use only one list to store THP-sized pages on the per-cpu list. This assumes that the vast majority of THP-sized allocations are GFP_MOVABLE but even if it was another type, it would not contribute to serious fragmentation that potentially causes a later THP allocation failure. Align per_cpu_pages on the cacheline boundary to ensure there is no false cache sharing. After this patch, the structure sizing is; struct per_cpu_pages { int count; /* 0 4 */ int high; /* 4 4 */ int batch; /* 8 4 */ short int free_factor; /* 12 2 */ short int expire; /* 14 2 */ struct list_head lists[13]; /* 16 208 */ /* size: 256, cachelines: 4, members: 6 */ /* padding: 32 */ } __attribute__((__aligned__(64))); Link: https://lkml.kernel.org/r/20220624125423.6126-3-mgorman@techsingularity.net Signed-off-by: Mel Gorman Tested-by: Minchan Kim Acked-by: Minchan Kim Acked-by: Vlastimil Babka Tested-by: Yu Zhao Cc: Hugh Dickins Cc: Marcelo Tosatti Cc: Marek Szyprowski Cc: Michal Hocko Cc: Nicolas Saenz Julienne Signed-off-by: Andrew Morton Bug: 230899966 (cherry picked from commit 5d0a661d808fc8ddc26940b1a12b82ae356f3ae2) [surenb: fixed trivial merge conflicts] Change-Id: Id4e625a0400aaba24961a221d23926bb6d2712ce Signed-off-by: Suren Baghdasaryan --- include/linux/mmzone.h | 11 +++++++---- mm/page_alloc.c | 4 ++-- 2 files changed, 9 insertions(+), 6 deletions(-) diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index 0ea89cd365d4..92521d0eecfb 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -657,15 +657,18 @@ enum zone_watermarks { }; /* - * One per migratetype for each PAGE_ALLOC_COSTLY_ORDER plus one additional - * for pageblock size for THP if configured. + * One per migratetype for each PAGE_ALLOC_COSTLY_ORDER. One additional list + * for THP which will usually be GFP_MOVABLE. Even if it is another type, + * it should not contribute to serious fragmentation causing THP allocation + * failures. */ #ifdef CONFIG_TRANSPARENT_HUGEPAGE #define NR_PCP_THP 1 #else #define NR_PCP_THP 0 #endif -#define NR_PCP_LISTS (MIGRATE_PCPTYPES * (PAGE_ALLOC_COSTLY_ORDER + 1 + NR_PCP_THP)) +#define NR_LOWORDER_PCP_LISTS (MIGRATE_PCPTYPES * (PAGE_ALLOC_COSTLY_ORDER + 1)) +#define NR_PCP_LISTS (NR_LOWORDER_PCP_LISTS + NR_PCP_THP) /* * Shift to encode migratetype and order in the same integer, with order @@ -691,7 +694,7 @@ struct per_cpu_pages { /* Lists of pages, one per migrate type stored on the pcp-lists */ struct list_head lists[NR_PCP_LISTS]; -}; +} ____cacheline_aligned_in_smp; struct per_cpu_zonestat { #ifdef CONFIG_SMP diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 73143b079418..f2f35919b564 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -669,7 +669,7 @@ static inline unsigned int order_to_pindex(int migratetype, int order) #ifdef CONFIG_TRANSPARENT_HUGEPAGE if (order > PAGE_ALLOC_COSTLY_ORDER) { VM_BUG_ON(order != pageblock_order); - base = PAGE_ALLOC_COSTLY_ORDER + 1; + return NR_LOWORDER_PCP_LISTS; } #else VM_BUG_ON(order > PAGE_ALLOC_COSTLY_ORDER); @@ -683,7 +683,7 @@ static inline int pindex_to_order(unsigned int pindex) int order = pindex / MIGRATE_PCPTYPES; #ifdef CONFIG_TRANSPARENT_HUGEPAGE - if (order > PAGE_ALLOC_COSTLY_ORDER) { + if (pindex == NR_LOWORDER_PCP_LISTS) { order = pageblock_order; VM_BUG_ON(order != pageblock_order); }