1 files changed, 84 insertions, 15 deletions

diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c
index 9ca1d604f7c..6e7d8b21dbf 100644
--- a/mm/memory_hotplug.c
+++ b/mm/memory_hotplug.c
@@ -34,6 +34,17 @@
 
 #include "internal.h"
 
+/*
+ * online_page_callback contains pointer to current page onlining function.
+ * Initially it is generic_online_page(). If it is required it could be
+ * changed by calling set_online_page_callback() for callback registration
+ * and restore_online_page_callback() for generic callback restore.
+ */
+
+static void generic_online_page(struct page *page);
+
+static online_page_callback_t online_page_callback = generic_online_page;
+
 DEFINE_MUTEX(mem_hotplug_mutex);
 
 void lock_memory_hotplug(void)
@@ -361,27 +372,74 @@ int __remove_pages(struct zone *zone, unsigned long phys_start_pfn,
 }
 EXPORT_SYMBOL_GPL(__remove_pages);
 
-void online_page(struct page *page)
+int set_online_page_callback(online_page_callback_t callback)
+{
+	int rc = -EINVAL;
+
+	lock_memory_hotplug();
+
+	if (online_page_callback == generic_online_page) {
+		online_page_callback = callback;
+		rc = 0;
+	}
+
+	unlock_memory_hotplug();
+
+	return rc;
+}
+EXPORT_SYMBOL_GPL(set_online_page_callback);
+
+int restore_online_page_callback(online_page_callback_t callback)
+{
+	int rc = -EINVAL;
+
+	lock_memory_hotplug();
+
+	if (online_page_callback == callback) {
+		online_page_callback = generic_online_page;
+		rc = 0;
+	}
+
+	unlock_memory_hotplug();
+
+	return rc;
+}
+EXPORT_SYMBOL_GPL(restore_online_page_callback);
+
+void __online_page_set_limits(struct page *page)
 {
 	unsigned long pfn = page_to_pfn(page);
 
-	totalram_pages++;
 	if (pfn >= num_physpages)
 		num_physpages = pfn + 1;
+}
+EXPORT_SYMBOL_GPL(__online_page_set_limits);
+
+void __online_page_increment_counters(struct page *page)
+{
+	totalram_pages++;
 
 #ifdef CONFIG_HIGHMEM
 	if (PageHighMem(page))
 		totalhigh_pages++;
 #endif
+}
+EXPORT_SYMBOL_GPL(__online_page_increment_counters);
 
-#ifdef CONFIG_FLATMEM
-	max_mapnr = max(pfn, max_mapnr);
-#endif
-
+void __online_page_free(struct page *page)
+{
 	ClearPageReserved(page);
 	init_page_count(page);
 	__free_page(page);
 }
+EXPORT_SYMBOL_GPL(__online_page_free);
+
+static void generic_online_page(struct page *page)
+{
+	__online_page_set_limits(page);
+	__online_page_increment_counters(page);
+	__online_page_free(page);
+}
 
 static int online_pages_range(unsigned long start_pfn, unsigned long nr_pages,
 			void *arg)
@@ -392,7 +450,7 @@ static int online_pages_range(unsigned long start_pfn, unsigned long nr_pages,
 	if (PageReserved(pfn_to_page(start_pfn)))
 		for (i = 0; i < nr_pages; i++) {
 			page = pfn_to_page(start_pfn + i);
-			online_page(page);
+			(*online_page_callback)(page);
 			onlined_pages++;
 		}
 	*(unsigned long *)arg = onlined_pages;
@@ -400,7 +458,7 @@ static int online_pages_range(unsigned long start_pfn, unsigned long nr_pages,
 }
 
 
-int online_pages(unsigned long pfn, unsigned long nr_pages)
+int __ref online_pages(unsigned long pfn, unsigned long nr_pages)
 {
 	unsigned long onlined_pages = 0;
 	struct zone *zone;
@@ -459,8 +517,9 @@ int online_pages(unsigned long pfn, unsigned long nr_pages)
 		zone_pcp_update(zone);
 
 	mutex_unlock(&zonelists_mutex);
-	setup_per_zone_wmarks();
-	calculate_zone_inactive_ratio(zone);
+
+	init_per_zone_wmark_min();
+
 	if (onlined_pages) {
 		kswapd_run(zone_to_nid(zone));
 		node_set_state(zone_to_nid(zone), N_HIGH_MEMORY);
@@ -497,6 +556,14 @@ static pg_data_t __ref *hotadd_new_pgdat(int nid, u64 start)
 	/* init node's zones as empty zones, we don't have any present pages.*/
 	free_area_init_node(nid, zones_size, start_pfn, zholes_size);
 
+	/*
+	 * The node we allocated has no zone fallback lists. For avoiding
+	 * to access not-initialized zonelist, build here.
+	 */
+	mutex_lock(&zonelists_mutex);
+	build_all_zonelists(NULL);
+	mutex_unlock(&zonelists_mutex);
+
 	return pgdat;
 }
 
@@ -518,7 +585,7 @@ int mem_online_node(int nid)
 
 	lock_memory_hotplug();
 	pgdat = hotadd_new_pgdat(nid, 0);
-	if (pgdat) {
+	if (!pgdat) {
 		ret = -ENOMEM;
 		goto out;
 	}
@@ -705,7 +772,7 @@ do_migrate_range(unsigned long start_pfn, unsigned long end_pfn)
 		if (!pfn_valid(pfn))
 			continue;
 		page = pfn_to_page(pfn);
-		if (!page_count(page))
+		if (!get_page_unless_zero(page))
 			continue;
 		/*
 		 * We can skip free pages. And we can only deal with pages on
@@ -713,6 +780,7 @@ do_migrate_range(unsigned long start_pfn, unsigned long end_pfn)
 		 */
 		ret = isolate_lru_page(page);
 		if (!ret) { /* Success */
+			put_page(page);
 			list_add_tail(&page->lru, &source);
 			move_pages--;
 			inc_zone_page_state(page, NR_ISOLATED_ANON +
@@ -724,6 +792,7 @@ do_migrate_range(unsigned long start_pfn, unsigned long end_pfn)
 			       pfn);
 			dump_page(page);
 #endif
+			put_page(page);
 			/* Because we don't have big zone->lock. we should
 			   check this again here. */
 			if (page_count(page)) {
@@ -795,7 +864,7 @@ check_pages_isolated(unsigned long start_pfn, unsigned long end_pfn)
 	return offlined;
 }
 
-static int offline_pages(unsigned long start_pfn,
+static int __ref offline_pages(unsigned long start_pfn,
 		  unsigned long end_pfn, unsigned long timeout)
 {
 	unsigned long pfn, nr_pages, expire;
@@ -893,8 +962,8 @@ repeat:
 	zone->zone_pgdat->node_present_pages -= offlined_pages;
 	totalram_pages -= offlined_pages;
 
-	setup_per_zone_wmarks();
-	calculate_zone_inactive_ratio(zone);
+	init_per_zone_wmark_min();
+
 	if (!node_present_pages(node)) {
 		node_clear_state(node, N_HIGH_MEMORY);
 		kswapd_stop(node);