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 <mgorman@techsingularity.net>
Tested-by: Minchan Kim <minchan@kernel.org>
Acked-by: Minchan Kim <minchan@kernel.org>
Acked-by: Vlastimil Babka <vbabka@suse.cz>
Tested-by: Yu Zhao <yuzhao@google.com>
Cc: Hugh Dickins <hughd@google.com>
Cc: Marcelo Tosatti <mtosatti@redhat.com>
Cc: Marek Szyprowski <m.szyprowski@samsung.com>
Cc: Michal Hocko <mhocko@kernel.org>
Cc: Nicolas Saenz Julienne <nsaenzju@redhat.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>

diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h
index 5da1135..041136b 100644 (file)
--- a/include/linux/mmzone.h
+++ b/include/linux/mmzone.h
@@ -355,15 +355,18 @@ 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
@@ -389,7 +392,7 @@ 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 78ba5ba..b5c340d 100644 (file)
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -653,7 +653,7 @@ 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);
@@ -667,7 +667,7 @@ 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;
 #else
        VM_BUG_ON(order > PAGE_ALLOC_COSTLY_ORDER);