mem-hotplug: reset node managed pages when hot-adding a new pgdat

commit f784a3f1 upstream.

In free_area_init_core(), zone->managed_pages is set to an approximate
value for lowmem, and will be adjusted when the bootmem allocator frees
pages into the buddy system.

But free_area_init_core() is also called by hotadd_new_pgdat() when
hot-adding memory.  As a result, zone->managed_pages of the newly added
node's pgdat is set to an approximate value in the very beginning.

Even if the memory on that node has node been onlined,
/sys/device/system/node/nodeXXX/meminfo has wrong value:

  hot-add node2 (memory not onlined)
  cat /sys/device/system/node/node2/meminfo
  Node 2 MemTotal:       33554432 kB
  Node 2 MemFree:               0 kB
  Node 2 MemUsed:        33554432 kB
  Node 2 Active:                0 kB

This patch fixes this problem by reset node managed pages to 0 after
hot-adding a new node.

1. Move reset_managed_pages_done from reset_node_managed_pages() to
   reset_all_zones_managed_pages()
2. Make reset_node_managed_pages() non-static
3. Call reset_node_managed_pages() in hotadd_new_pgdat() after pgdat
   is initialized
Signed-off-by: Tang Chen <tangchen@cn.fujitsu.com>
Signed-off-by: Yasuaki Ishimatsu <isimatu.yasuaki@jp.fujitsu.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Luis Henriques <luis.henriques@canonical.com>

include/linux/bootmem.h

@@ -46,6 +46,7 @@ extern unsigned long init_bootmem_node(pg_data_t *pgdat,
 extern unsigned long init_bootmem(unsigned long addr, unsigned long memend);
 
 extern unsigned long free_all_bootmem(void);
+extern void reset_node_managed_pages(pg_data_t *pgdat);
 extern void reset_all_zones_managed_pages(void);
 
 extern void free_bootmem_node(pg_data_t *pgdat,

mm/bootmem.c

@@ -243,13 +243,10 @@ static unsigned long __init free_all_bootmem_core(bootmem_data_t *bdata)
 
 static int reset_managed_pages_done __initdata;
 
-static inline void __init reset_node_managed_pages(pg_data_t *pgdat)
+void reset_node_managed_pages(pg_data_t *pgdat)
 {
 	struct zone *z;
 
-	if (reset_managed_pages_done)
-		return;
-
 	for (z = pgdat->node_zones; z < pgdat->node_zones + MAX_NR_ZONES; z++)
 		z->managed_pages = 0;
 }
@@ -258,8 +255,12 @@ void __init reset_all_zones_managed_pages(void)
 {
 	struct pglist_data *pgdat;
 
+	if (reset_managed_pages_done)
+		return;
+
 	for_each_online_pgdat(pgdat)
 		reset_node_managed_pages(pgdat);
+
 	reset_managed_pages_done = 1;
 }
 

mm/memory_hotplug.c

@@ -31,6 +31,7 @@
 #include <linux/stop_machine.h>
 #include <linux/hugetlb.h>
 #include <linux/memblock.h>
+#include <linux/bootmem.h>
 
 #include <asm/tlbflush.h>
 
@@ -1093,6 +1094,14 @@ static pg_data_t __ref *hotadd_new_pgdat(int nid, u64 start)
 	build_all_zonelists(pgdat, NULL);
 	mutex_unlock(&zonelists_mutex);
 
+	/*
+	 * zone->managed_pages is set to an approximate value in
+	 * free_area_init_core(), which will cause
+	 * /sys/device/system/node/nodeX/meminfo has wrong data.
+	 * So reset it to 0 before any memory is onlined.
+	 */
+	reset_node_managed_pages(pgdat);
+
 	return pgdat;
 }
 

mm/nobootmem.c

@@ -143,12 +143,10 @@ static unsigned long __init free_low_memory_core_early(void)
 
 static int reset_managed_pages_done __initdata;
 
-static inline void __init reset_node_managed_pages(pg_data_t *pgdat)
+void reset_node_managed_pages(pg_data_t *pgdat)
 {
 	struct zone *z;
 
-	if (reset_managed_pages_done)
-		return;
 	for (z = pgdat->node_zones; z < pgdat->node_zones + MAX_NR_ZONES; z++)
 		z->managed_pages = 0;
 }
@@ -157,8 +155,12 @@ void __init reset_all_zones_managed_pages(void)
 {
 	struct pglist_data *pgdat;
 
+	if (reset_managed_pages_done)
+		return;
+
 	for_each_online_pgdat(pgdat)
 		reset_node_managed_pages(pgdat);
+
 	reset_managed_pages_done = 1;
 }