Page allocator: get rid of the list of cold pages

We have repeatedly discussed if the cold pages still have a point. There is
one way to join the two lists: Use a single list and put the cold pages at the
end and the hot pages at the beginning. That way a single list can serve for
both types of allocations.

The discussion of the RFC for this and Mel's measurements indicate that
there may not be too much of a point left to having separate lists for
hot and cold pages (see http://marc.info/?t=119492914200001&r=1&w=2).

Signed-off-by: Christoph Lameter <clameter@sgi.com>
Cc: Mel Gorman <mel@csn.ul.ie>
Cc: Martin Bligh <mbligh@mbligh.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

3 files changed, 40 insertions, 49 deletions

diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h
index 4c4522a51a3b..8d8d1977736e 100644
--- a/include/linux/mmzone.h
+++ b/include/linux/mmzone.h
@@ -113,7 +113,7 @@ struct per_cpu_pages {
 };
 
 struct per_cpu_pageset {
-        struct per_cpu_pages pcp[2];    /* 0: hot.  1: cold */
+        struct per_cpu_pages pcp;
 #ifdef CONFIG_NUMA
         s8 expire;
 #endif
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 5c7de8e959fc..144c0967e702 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -901,24 +901,21 @@ static void drain_pages(unsigned int cpu)
 {
         unsigned long flags;
         struct zone *zone;
-        int i;
 
         for_each_zone(zone) {
                 struct per_cpu_pageset *pset;
+                struct per_cpu_pages *pcp;
 
                 if (!populated_zone(zone))
                         continue;
 
                 pset = zone_pcp(zone, cpu);
-                for (i = 0; i < ARRAY_SIZE(pset->pcp); i++) {
-                        struct per_cpu_pages *pcp;
-
-                        pcp = &pset->pcp[i];
-                        local_irq_save(flags);
-                        free_pages_bulk(zone, pcp->count, &pcp->list, 0);
-                        pcp->count = 0;
-                        local_irq_restore(flags);
-                }
+
+                pcp = &pset->pcp;
+                local_irq_save(flags);
+                free_pages_bulk(zone, pcp->count, &pcp->list, 0);
+                pcp->count = 0;
+                local_irq_restore(flags);
         }
 }
 
@@ -993,10 +990,13 @@ static void fastcall free_hot_cold_page(struct page *page, int cold)
         arch_free_page(page, 0);
         kernel_map_pages(page, 1, 0);
 
-        pcp = &zone_pcp(zone, get_cpu())->pcp[cold];
+        pcp = &zone_pcp(zone, get_cpu())->pcp;
         local_irq_save(flags);
         __count_vm_event(PGFREE);
-        list_add(&page->lru, &pcp->list);
+        if (cold)
+                list_add_tail(&page->lru, &pcp->list);
+        else
+                list_add(&page->lru, &pcp->list);
         set_page_private(page, get_pageblock_migratetype(page));
         pcp->count++;
         if (pcp->count >= pcp->high) {
@@ -1054,7 +1054,7 @@ again:
         if (likely(order == 0)) {
                 struct per_cpu_pages *pcp;
 
-                pcp = &zone_pcp(zone, cpu)->pcp[cold];
+                pcp = &zone_pcp(zone, cpu)->pcp;
                 local_irq_save(flags);
                 if (!pcp->count) {
                         pcp->count = rmqueue_bulk(zone, 0,
@@ -1064,9 +1064,15 @@ again:
                 }
 
                 /* Find a page of the appropriate migrate type */
-                list_for_each_entry(page, &pcp->list, lru)
-                        if (page_private(page) == migratetype)
-                                break;
+                if (cold) {
+                        list_for_each_entry_reverse(page, &pcp->list, lru)
+                                if (page_private(page) == migratetype)
+                                        break;
+                } else {
+                        list_for_each_entry(page, &pcp->list, lru)
+                                if (page_private(page) == migratetype)
+                                        break;
+                }
 
                 /* Allocate more to the pcp list if necessary */
                 if (unlikely(&page->lru == &pcp->list)) {
@@ -1793,12 +1799,9 @@ void show_free_areas(void)
 
                         pageset = zone_pcp(zone, cpu);
 
-                        printk("CPU %4d: Hot: hi:%5d, btch:%4d usd:%4d   "
-                               "Cold: hi:%5d, btch:%4d usd:%4d\n",
-                               cpu, pageset->pcp[0].high,
-                               pageset->pcp[0].batch, pageset->pcp[0].count,
-                               pageset->pcp[1].high, pageset->pcp[1].batch,
-                               pageset->pcp[1].count);
+                        printk("CPU %4d: hi:%5d, btch:%4d usd:%4d\n",
+                               cpu, pageset->pcp.high,
+                               pageset->pcp.batch, pageset->pcp.count);
                 }
         }
 
@@ -2596,17 +2599,11 @@ inline void setup_pageset(struct per_cpu_pageset *p, unsigned long batch)
 
         memset(p, 0, sizeof(*p));
 
-        pcp = &p->pcp[0];               /* hot */
+        pcp = &p->pcp;
         pcp->count = 0;
         pcp->high = 6 * batch;
         pcp->batch = max(1UL, 1 * batch);
         INIT_LIST_HEAD(&pcp->list);
-
-        pcp = &p->pcp[1];               /* cold*/
-        pcp->count = 0;
-        pcp->high = 2 * batch;
-        pcp->batch = max(1UL, batch/2);
-        INIT_LIST_HEAD(&pcp->list);
 }
 
 /*
@@ -2619,7 +2616,7 @@ static void setup_pagelist_highmark(struct per_cpu_pageset *p,
 {
         struct per_cpu_pages *pcp;
 
-        pcp = &p->pcp[0]; /* hot list */
+        pcp = &p->pcp;
         pcp->high = high;
         pcp->batch = max(1UL, high/4);
         if ((high/4) > (PAGE_SHIFT * 8))
diff --git a/mm/vmstat.c b/mm/vmstat.c
index 9ffc573ceb6e..888668e0b7db 100644
--- a/mm/vmstat.c
+++ b/mm/vmstat.c
@@ -337,7 +337,7 @@ void refresh_cpu_vm_stats(int cpu)
                  * Check if there are pages remaining in this pageset
                  * if not then there is nothing to expire.
                  */
-                if (!p->expire || (!p->pcp[0].count && !p->pcp[1].count))
+                if (!p->expire || !p->pcp.count)
                         continue;
 
                 /*
@@ -352,11 +352,8 @@ void refresh_cpu_vm_stats(int cpu)
                 if (p->expire)
                         continue;
 
-                if (p->pcp[0].count)
-                        drain_zone_pages(zone, p->pcp + 0);
-
-                if (p->pcp[1].count)
-                        drain_zone_pages(zone, p->pcp + 1);
+                if (p->pcp.count)
+                        drain_zone_pages(zone, &p->pcp);
 #endif
         }
 
@@ -693,20 +690,17 @@ static void zoneinfo_show_print(struct seq_file *m, pg_data_t *pgdat,
                    "\n  pagesets");
         for_each_online_cpu(i) {
                 struct per_cpu_pageset *pageset;
-                int j;
 
                 pageset = zone_pcp(zone, i);
-                for (j = 0; j < ARRAY_SIZE(pageset->pcp); j++) {
-                        seq_printf(m,
-                                   "\n    cpu: %i pcp: %i"
-                                   "\n              count: %i"
-                                   "\n              high:  %i"
-                                   "\n              batch: %i",
-                                   i, j,
-                                   pageset->pcp[j].count,
-                                   pageset->pcp[j].high,
-                                   pageset->pcp[j].batch);
-                        }
+                seq_printf(m,
+                           "\n    cpu: %i"
+                           "\n              count: %i"
+                           "\n              high:  %i"
+                           "\n              batch: %i",
+                           i,
+                           pageset->pcp.count,
+                           pageset->pcp.high,
+                           pageset->pcp.batch);
 #ifdef CONFIG_SMP
                 seq_printf(m, "\n  vm stats threshold: %d",
                                 pageset->stat_threshold);