mm/hotplug: free zone->pageset when a zone becomes empty

When a zone becomes empty after memory offlining, free zone->pageset.
Otherwise it will cause memory leak when adding memory to the empty zone
again because build_all_zonelists() will allocate zone->pageset for an
empty zone.

Signed-off-by: Jiang Liu <liuj97@gmail.com>
Signed-off-by: Wei Wang <Bessel.Wang@huawei.com>
Cc: Mel Gorman <mgorman@suse.de>
Cc: Michal Hocko <mhocko@suse.cz>
Cc: Minchan Kim <minchan@kernel.org>
Cc: Rusty Russell <rusty@rustcorp.com.au>
Cc: Yinghai Lu <yinghai@kernel.org>
Cc: Tony Luck <tony.luck@intel.com>
Cc: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Cc: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Cc: David Rientjes <rientjes@google.com>
Cc: Keping Chen <chenkeping@huawei.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

Author: Jiang Liu

include/linux/mm.h

@@ -1331,6 +1331,7 @@ void warn_alloc_failed(gfp_t gfp_mask, int order, const char *fmt, ...);
 extern void setup_per_cpu_pageset(void);
 
 extern void zone_pcp_update(struct zone *zone);
+extern void zone_pcp_reset(struct zone *zone);
 
 /* nommu.c */
 extern atomic_long_t mmap_pages_allocated;

mm/memory_hotplug.c

@@ -966,6 +966,9 @@ static int __ref offline_pages(unsigned long start_pfn,
 
 	init_per_zone_wmark_min();
 
+	if (!populated_zone(zone))
+		zone_pcp_reset(zone);
+
 	if (!node_present_pages(node)) {
 		node_clear_state(node, N_HIGH_MEMORY);
 		kswapd_stop(node);

mm/page_alloc.c

@@ -5894,6 +5894,19 @@ void free_contig_range(unsigned long pfn, unsigned nr_pages)
 #endif
 
 #ifdef CONFIG_MEMORY_HOTREMOVE
+void zone_pcp_reset(struct zone *zone)
+{
+	unsigned long flags;
+
+	/* avoid races with drain_pages()  */
+	local_irq_save(flags);
+	if (zone->pageset != &boot_pageset) {
+		free_percpu(zone->pageset);
+		zone->pageset = &boot_pageset;
+	}
+	local_irq_restore(flags);
+}
+
 /*
  * All pages in the range must be isolated before calling this.
  */