mm, page_alloc: cache pageset high and batch in struct zone

All per-cpu pagesets for a zone use the same high and batch values, that
are duplicated there just for performance (locality) reasons.  This patch
adds the same variables also to struct zone as a shared copy.

This will be useful later for making possible to disable pcplists
temporarily by setting high value to 0, while remembering the values for
restoring them later.  But we can also immediately benefit from not
updating pagesets of all possible cpus in case the newly recalculated
values (after sysctl change or memory online/offline) are actually
unchanged from the previous ones.

Link: https://lkml.kernel.org/r/20201111092812.11329-6-vbabka@suse.cz
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
Reviewed-by: Oscar Salvador <osalvador@suse.de>
Acked-by: Michal Hocko <mhocko@suse.com>
Reviewed-by: David Hildenbrand <david@redhat.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h
index 6e0025b5a88f1410054b398797590e781847377d..4eee08b0062ba64705e31f9efd0795472c835c1c 100644 (file)
--- a/include/linux/mmzone.h
+++ b/include/linux/mmzone.h
@@ -470,6 +470,12 @@ struct zone {
 #endif
        struct pglist_data      *zone_pgdat;
        struct per_cpu_pageset __percpu *pageset;
+       /*
+        * the high and batch values are copied to individual pagesets for
+        * faster access
+        */
+       int pageset_high;
+       int pageset_batch;
 
 #ifndef CONFIG_SPARSEMEM
        /*

diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 0c47af9e97c6e65358474f313a6dd8aa6408d86c..c3d1752b57dc012cd2b2a2d38e784e91b6388878 100644 (file)
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -5920,6 +5920,9 @@ static void build_zonelists(pg_data_t *pgdat)
  * Other parts of the kernel may not check if the zone is available.
  */
 static void pageset_init(struct per_cpu_pageset *p);
+/* These effectively disable the pcplists in the boot pageset completely */
+#define BOOT_PAGESET_HIGH      0
+#define BOOT_PAGESET_BATCH     1
 static DEFINE_PER_CPU(struct per_cpu_pageset, boot_pageset);
 static DEFINE_PER_CPU(struct per_cpu_nodestat, boot_nodestats);
 
@@ -6309,8 +6312,8 @@ static void pageset_init(struct per_cpu_pageset *p)
         * need to be as careful as pageset_update() as nobody can access the
         * pageset yet.
         */
-       pcp->high = 0;
-       pcp->batch = 1;
+       pcp->high = BOOT_PAGESET_HIGH;
+       pcp->batch = BOOT_PAGESET_BATCH;
 }
 
 /*
@@ -6334,6 +6337,13 @@ static void zone_set_pageset_high_and_batch(struct zone *zone)
                new_batch = max(1UL, 1 * new_batch);
        }
 
+       if (zone->pageset_high == new_high &&
+           zone->pageset_batch == new_batch)
+               return;
+
+       zone->pageset_high = new_high;
+       zone->pageset_batch = new_batch;
+
        for_each_possible_cpu(cpu) {
                p = per_cpu_ptr(zone->pageset, cpu);
                pageset_update(&p->pcp, new_high, new_batch);
@@ -6394,6 +6404,8 @@ static __meminit void zone_pcp_init(struct zone *zone)
         * offset of a (static) per cpu variable into the per cpu area.
         */
        zone->pageset = &boot_pageset;
+       zone->pageset_high = BOOT_PAGESET_HIGH;
+       zone->pageset_batch = BOOT_PAGESET_BATCH;
 
        if (populated_zone(zone))
                printk(KERN_DEBUG "  %s zone: %lu pages, LIFO batch:%u\n",