mm: move most file-based accounting to the node

There are now a number of accounting oddities such as mapped file pages
being accounted for on the node while the total number of file pages are
accounted on the zone.  This can be coped with to some extent but it's
confusing so this patch moves the relevant file-based accounted.  Due to
throttling logic in the page allocator for reliable OOM detection, it is
still necessary to track dirty and writeback pages on a per-zone basis.

[mgorman@techsingularity.net: fix NR_ZONE_WRITE_PENDING accounting]
  Link: http://lkml.kernel.org/r/1468404004-5085-5-git-send-email-mgorman@techsingularity.net
Link: http://lkml.kernel.org/r/1467970510-21195-20-git-send-email-mgorman@techsingularity.net
Signed-off-by: Mel Gorman <mgorman@techsingularity.net>
Acked-by: Vlastimil Babka <vbabka@suse.cz>
Acked-by: Michal Hocko <mhocko@suse.com>
Cc: Hillf Danton <hillf.zj@alibaba-inc.com>
Acked-by: Johannes Weiner <hannes@cmpxchg.org>
Cc: Joonsoo Kim <iamjoonsoo.kim@lge.com>
Cc: Minchan Kim <minchan@kernel.org>
Cc: Rik van Riel <riel@surriel.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

1 files changed, 32 insertions, 42 deletions

diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index c11935bf37cb..0f92e04b58db 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -3492,14 +3492,12 @@ should_reclaim_retry(gfp_t gfp_mask, unsigned order,
 			 * prevent from pre mature OOM
 			 */
 			if (!did_some_progress) {
-				unsigned long writeback;
-				unsigned long dirty;
+				unsigned long write_pending;
 
-				writeback = zone_page_state_snapshot(zone,
-								     NR_WRITEBACK);
-				dirty = zone_page_state_snapshot(zone, NR_FILE_DIRTY);
+				write_pending = zone_page_state_snapshot(zone,
+							NR_ZONE_WRITE_PENDING);
 
-				if (2*(writeback + dirty) > reclaimable) {
+				if (2 * write_pending > reclaimable) {
 					congestion_wait(BLK_RW_ASYNC, HZ/10);
 					return true;
 				}
@@ -4175,7 +4173,7 @@ EXPORT_SYMBOL_GPL(si_mem_available);
 void si_meminfo(struct sysinfo *val)
 {
 	val->totalram = totalram_pages;
-	val->sharedram = global_page_state(NR_SHMEM);
+	val->sharedram = global_node_page_state(NR_SHMEM);
 	val->freeram = global_page_state(NR_FREE_PAGES);
 	val->bufferram = nr_blockdev_pages();
 	val->totalhigh = totalhigh_pages;
@@ -4197,7 +4195,7 @@ void si_meminfo_node(struct sysinfo *val, int nid)
 	for (zone_type = 0; zone_type < MAX_NR_ZONES; zone_type++)
 		managed_pages += pgdat->node_zones[zone_type].managed_pages;
 	val->totalram = managed_pages;
-	val->sharedram = sum_zone_node_page_state(nid, NR_SHMEM);
+	val->sharedram = node_page_state(pgdat, NR_SHMEM);
 	val->freeram = sum_zone_node_page_state(nid, NR_FREE_PAGES);
 #ifdef CONFIG_HIGHMEM
 	for (zone_type = 0; zone_type < MAX_NR_ZONES; zone_type++) {
@@ -4296,9 +4294,6 @@ void show_free_areas(unsigned int filter)
 		" unevictable:%lu dirty:%lu writeback:%lu unstable:%lu\n"
 		" slab_reclaimable:%lu slab_unreclaimable:%lu\n"
 		" mapped:%lu shmem:%lu pagetables:%lu bounce:%lu\n"
-#ifdef CONFIG_TRANSPARENT_HUGEPAGE
-		" anon_thp: %lu shmem_thp: %lu shmem_pmdmapped: %lu\n"
-#endif
 		" free:%lu free_pcp:%lu free_cma:%lu\n",
 		global_node_page_state(NR_ACTIVE_ANON),
 		global_node_page_state(NR_INACTIVE_ANON),
@@ -4307,20 +4302,15 @@ void show_free_areas(unsigned int filter)
 		global_node_page_state(NR_INACTIVE_FILE),
 		global_node_page_state(NR_ISOLATED_FILE),
 		global_node_page_state(NR_UNEVICTABLE),
-		global_page_state(NR_FILE_DIRTY),
-		global_page_state(NR_WRITEBACK),
-		global_page_state(NR_UNSTABLE_NFS),
+		global_node_page_state(NR_FILE_DIRTY),
+		global_node_page_state(NR_WRITEBACK),
+		global_node_page_state(NR_UNSTABLE_NFS),
 		global_page_state(NR_SLAB_RECLAIMABLE),
 		global_page_state(NR_SLAB_UNRECLAIMABLE),
 		global_node_page_state(NR_FILE_MAPPED),
-		global_page_state(NR_SHMEM),
+		global_node_page_state(NR_SHMEM),
 		global_page_state(NR_PAGETABLE),
 		global_page_state(NR_BOUNCE),
-#ifdef CONFIG_TRANSPARENT_HUGEPAGE
-		global_page_state(NR_ANON_THPS) * HPAGE_PMD_NR,
-		global_page_state(NR_SHMEM_THPS) * HPAGE_PMD_NR,
-		global_page_state(NR_SHMEM_PMDMAPPED) * HPAGE_PMD_NR,
-#endif
 		global_page_state(NR_FREE_PAGES),
 		free_pcp,
 		global_page_state(NR_FREE_CMA_PAGES));
@@ -4335,6 +4325,16 @@ void show_free_areas(unsigned int filter)
 			" isolated(anon):%lukB"
 			" isolated(file):%lukB"
 			" mapped:%lukB"
+			" dirty:%lukB"
+			" writeback:%lukB"
+			" shmem:%lukB"
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+			" shmem_thp: %lukB"
+			" shmem_pmdmapped: %lukB"
+			" anon_thp: %lukB"
+#endif
+			" writeback_tmp:%lukB"
+			" unstable:%lukB"
 			" all_unreclaimable? %s"
 			"\n",
 			pgdat->node_id,
@@ -4346,6 +4346,17 @@ void show_free_areas(unsigned int filter)
 			K(node_page_state(pgdat, NR_ISOLATED_ANON)),
 			K(node_page_state(pgdat, NR_ISOLATED_FILE)),
 			K(node_page_state(pgdat, NR_FILE_MAPPED)),
+			K(node_page_state(pgdat, NR_FILE_DIRTY)),
+			K(node_page_state(pgdat, NR_WRITEBACK)),
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+			K(node_page_state(pgdat, NR_SHMEM_THPS) * HPAGE_PMD_NR),
+			K(node_page_state(pgdat, NR_SHMEM_PMDMAPPED)
+					* HPAGE_PMD_NR),
+			K(node_page_state(pgdat, NR_ANON_THPS) * HPAGE_PMD_NR),
+#endif
+			K(node_page_state(pgdat, NR_SHMEM)),
+			K(node_page_state(pgdat, NR_WRITEBACK_TEMP)),
+			K(node_page_state(pgdat, NR_UNSTABLE_NFS)),
 			!pgdat_reclaimable(pgdat) ? "yes" : "no");
 	}
 
@@ -4368,24 +4379,14 @@ void show_free_areas(unsigned int filter)
 			" present:%lukB"
 			" managed:%lukB"
 			" mlocked:%lukB"
-			" dirty:%lukB"
-			" writeback:%lukB"
-			" shmem:%lukB"
-#ifdef CONFIG_TRANSPARENT_HUGEPAGE
-			" shmem_thp: %lukB"
-			" shmem_pmdmapped: %lukB"
-			" anon_thp: %lukB"
-#endif
 			" slab_reclaimable:%lukB"
 			" slab_unreclaimable:%lukB"
 			" kernel_stack:%lukB"
 			" pagetables:%lukB"
-			" unstable:%lukB"
 			" bounce:%lukB"
 			" free_pcp:%lukB"
 			" local_pcp:%ukB"
 			" free_cma:%lukB"
-			" writeback_tmp:%lukB"
 			" node_pages_scanned:%lu"
 			"\n",
 			zone->name,
@@ -4396,26 +4397,15 @@ void show_free_areas(unsigned int filter)
 			K(zone->present_pages),
 			K(zone->managed_pages),
 			K(zone_page_state(zone, NR_MLOCK)),
-			K(zone_page_state(zone, NR_FILE_DIRTY)),
-			K(zone_page_state(zone, NR_WRITEBACK)),
-			K(zone_page_state(zone, NR_SHMEM)),
-#ifdef CONFIG_TRANSPARENT_HUGEPAGE
-			K(zone_page_state(zone, NR_SHMEM_THPS) * HPAGE_PMD_NR),
-			K(zone_page_state(zone, NR_SHMEM_PMDMAPPED)
-					* HPAGE_PMD_NR),
-			K(zone_page_state(zone, NR_ANON_THPS) * HPAGE_PMD_NR),
-#endif
 			K(zone_page_state(zone, NR_SLAB_RECLAIMABLE)),
 			K(zone_page_state(zone, NR_SLAB_UNRECLAIMABLE)),
 			zone_page_state(zone, NR_KERNEL_STACK) *
 				THREAD_SIZE / 1024,
 			K(zone_page_state(zone, NR_PAGETABLE)),
-			K(zone_page_state(zone, NR_UNSTABLE_NFS)),
 			K(zone_page_state(zone, NR_BOUNCE)),
 			K(free_pcp),
 			K(this_cpu_read(zone->pageset->pcp.count)),
 			K(zone_page_state(zone, NR_FREE_CMA_PAGES)),
-			K(zone_page_state(zone, NR_WRITEBACK_TEMP)),
 			K(node_page_state(zone->zone_pgdat, NR_PAGES_SCANNED)));
 		printk("lowmem_reserve[]:");
 		for (i = 0; i < MAX_NR_ZONES; i++)
@@ -4458,7 +4448,7 @@ void show_free_areas(unsigned int filter)
 
 	hugetlb_show_meminfo();
 
-	printk("%ld total pagecache pages\n", global_page_state(NR_FILE_PAGES));
+	printk("%ld total pagecache pages\n", global_node_page_state(NR_FILE_PAGES));
 
 	show_swap_cache_info();
 }