mm: page allocator: calculate a better estimate of NR_FREE_PAGES when memory is low and kswapd is awake

Ordinarily watermark checks are based on the vmstat NR_FREE_PAGES as it is
cheaper than scanning a number of lists.  To avoid synchronization
overhead, counter deltas are maintained on a per-cpu basis and drained
both periodically and when the delta is above a threshold.  On large CPU
systems, the difference between the estimated and real value of
NR_FREE_PAGES can be very high.  If NR_FREE_PAGES is much higher than
number of real free page in buddy, the VM can allocate pages below min
watermark, at worst reducing the real number of pages to zero.  Even if
the OOM killer kills some victim for freeing memory, it may not free
memory if the exit path requires a new page resulting in livelock.

This patch introduces a zone_page_state_snapshot() function (courtesy of
Christoph) that takes a slightly more accurate view of an arbitrary vmstat
counter.  It is used to read NR_FREE_PAGES while kswapd is awake to avoid
the watermark being accidentally broken.  The estimate is not perfect and
may result in cache line bounces but is expected to be lighter than the
IPI calls necessary to continually drain the per-cpu counters while kswapd
is awake.

Signed-off-by: Christoph Lameter <cl@linux.com>
Signed-off-by: Mel Gorman <mel@csn.ul.ie>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

3 files changed, 37 insertions, 3 deletions

diff --git a/mm/mmzone.c b/mm/mmzone.c
index f5b7d1760213..e35bfb82c855 100644
--- a/mm/mmzone.c
+++ b/mm/mmzone.c
@@ -87,3 +87,24 @@ int memmap_valid_within(unsigned long pfn,
         return 1;
 }
 #endif /* CONFIG_ARCH_HAS_HOLES_MEMORYMODEL */
+
+#ifdef CONFIG_SMP
+/* Called when a more accurate view of NR_FREE_PAGES is needed */
+unsigned long zone_nr_free_pages(struct zone *zone)
+{
+        unsigned long nr_free_pages = zone_page_state(zone, NR_FREE_PAGES);
+
+        /*
+         * While kswapd is awake, it is considered the zone is under some
+         * memory pressure. Under pressure, there is a risk that
+         * per-cpu-counter-drift will allow the min watermark to be breached
+         * potentially causing a live-lock. While kswapd is awake and
+         * free pages are low, get a better estimate for free pages
+         */
+        if (nr_free_pages < zone->percpu_drift_mark &&
+                        !waitqueue_active(&zone->zone_pgdat->kswapd_wait))
+                return zone_page_state_snapshot(zone, NR_FREE_PAGES);
+
+        return nr_free_pages;
+}
+#endif /* CONFIG_SMP */
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 452e2ba06c7c..b2d21e06d45d 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -1462,7 +1462,7 @@ int zone_watermark_ok(struct zone *z, int order, unsigned long mark,
 {
         /* free_pages my go negative - that's OK */
         long min = mark;
-        long free_pages = zone_page_state(z, NR_FREE_PAGES) - (1 << order) + 1;
+        long free_pages = zone_nr_free_pages(z) - (1 << order) + 1;
         int o;
 
         if (alloc_flags & ALLOC_HIGH)
@@ -2424,7 +2424,7 @@ void show_free_areas(void)
                         " all_unreclaimable? %s"
                         "\n",
                         zone->name,
-                        K(zone_page_state(zone, NR_FREE_PAGES)),
+                        K(zone_nr_free_pages(zone)),
                         K(min_wmark_pages(zone)),
                         K(low_wmark_pages(zone)),
                         K(high_wmark_pages(zone)),
diff --git a/mm/vmstat.c b/mm/vmstat.c
index a8d6b59e609a..355a9e669aaa 100644
--- a/mm/vmstat.c
+++ b/mm/vmstat.c
@@ -138,11 +138,24 @@ static void refresh_zone_stat_thresholds(void)
         int threshold;
 
         for_each_populated_zone(zone) {
+                unsigned long max_drift, tolerate_drift;
+
                 threshold = calculate_threshold(zone);
 
                 for_each_online_cpu(cpu)
                         per_cpu_ptr(zone->pageset, cpu)->stat_threshold
                                                         = threshold;
+
+                /*
+                 * Only set percpu_drift_mark if there is a danger that
+                 * NR_FREE_PAGES reports the low watermark is ok when in fact
+                 * the min watermark could be breached by an allocation
+                 */
+                tolerate_drift = low_wmark_pages(zone) - min_wmark_pages(zone);
+                max_drift = num_online_cpus() * threshold;
+                if (max_drift > tolerate_drift)
+                        zone->percpu_drift_mark = high_wmark_pages(zone) +
+                                        max_drift;
         }
 }
 
@@ -813,7 +826,7 @@ static void zoneinfo_show_print(struct seq_file *m, pg_data_t *pgdat,
                    "\n        scanned  %lu"
                    "\n        spanned  %lu"
                    "\n        present  %lu",
-                   zone_page_state(zone, NR_FREE_PAGES),
+                   zone_nr_free_pages(zone),
                    min_wmark_pages(zone),
                    low_wmark_pages(zone),
                    high_wmark_pages(zone),