Merge tag 'v2.6.38' of git://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux-2.6

[mv-sheeva.git] / mm / vmstat.c

diff --git a/mm/vmstat.c b/mm/vmstat.c
index 312d728976f1661c4fa335a1ead46356b3bf091b..0c3b5048773e6d486f43343a859ebf785161036e 100644 (file)
--- a/mm/vmstat.c
+++ b/mm/vmstat.c
@@ -83,7 +83,31 @@ EXPORT_SYMBOL(vm_stat);
 
 #ifdef CONFIG_SMP
 
-static int calculate_threshold(struct zone *zone)
+int calculate_pressure_threshold(struct zone *zone)
+{
+       int threshold;
+       int watermark_distance;
+
+       /*
+        * As vmstats are not up to date, there is drift between the estimated
+        * and real values. For high thresholds and a high number of CPUs, it
+        * is possible for the min watermark to be breached while the estimated
+        * value looks fine. The pressure threshold is a reduced value such
+        * that even the maximum amount of drift will not accidentally breach
+        * the min watermark
+        */
+       watermark_distance = low_wmark_pages(zone) - min_wmark_pages(zone);
+       threshold = max(1, (int)(watermark_distance / num_online_cpus()));
+
+       /*
+        * Maximum threshold is 125
+        */
+       threshold = min(125, threshold);
+
+       return threshold;
+}
+
+int calculate_normal_threshold(struct zone *zone)
 {
        int threshold;
        int mem;        /* memory in 128 MB units */
@@ -142,7 +166,7 @@ static void refresh_zone_stat_thresholds(void)
        for_each_populated_zone(zone) {
                unsigned long max_drift, tolerate_drift;
 
-               threshold = calculate_threshold(zone);
+               threshold = calculate_normal_threshold(zone);
 
                for_each_online_cpu(cpu)
                        per_cpu_ptr(zone->pageset, cpu)->stat_threshold
@@ -161,6 +185,26 @@ static void refresh_zone_stat_thresholds(void)
        }
 }
 
+void set_pgdat_percpu_threshold(pg_data_t *pgdat,
+                               int (*calculate_pressure)(struct zone *))
+{
+       struct zone *zone;
+       int cpu;
+       int threshold;
+       int i;
+
+       for (i = 0; i < pgdat->nr_zones; i++) {
+               zone = &pgdat->node_zones[i];
+               if (!zone->percpu_drift_mark)
+                       continue;
+
+               threshold = (*calculate_pressure)(zone);
+               for_each_possible_cpu(cpu)
+                       per_cpu_ptr(zone->pageset, cpu)->stat_threshold
+                                                       = threshold;
+       }
+}
+
 /*
  * For use when we know that interrupts are disabled.
  */
@@ -836,6 +880,7 @@ static const char * const vmstat_text[] = {
        "numa_local",
        "numa_other",
 #endif
+       "nr_anon_transparent_hugepages",
        "nr_dirty_threshold",
        "nr_dirty_background_threshold",
 
@@ -911,7 +956,7 @@ static void zoneinfo_show_print(struct seq_file *m, pg_data_t *pgdat,
                   "\n        scanned  %lu"
                   "\n        spanned  %lu"
                   "\n        present  %lu",
-                  zone_nr_free_pages(zone),
+                  zone_page_state(zone, NR_FREE_PAGES),
                   min_wmark_pages(zone),
                   low_wmark_pages(zone),
                   high_wmark_pages(zone),