mm, memory_hotplug: do not associate hotadded memory to zones until online

The current memory hotplug implementation relies on having all the
struct pages associate with a zone/node during the physical hotplug
phase (arch_add_memory->__add_pages->__add_section->__add_zone).  In the
vast majority of cases this means that they are added to ZONE_NORMAL.
This has been so since 9d99aaa3 ("[PATCH] x86_64: Support memory
hotadd without sparsemem") and it wasn't a big deal back then because
movable onlining didn't exist yet.

Much later memory hotplug wanted to (ab)use ZONE_MOVABLE for movable
onlining 511c2aba ("mm, memory-hotplug: dynamic configure movable
memory and portion memory") and then things got more complicated.
Rather than reconsidering the zone association which was no longer
needed (because the memory hotplug already depended on SPARSEMEM) a
convoluted semantic of zone shifting has been developed.  Only the
currently last memblock or the one adjacent to the zone_movable can be
onlined movabl...

arch/ia64/mm/init.c

@@ -648,18 +648,11 @@ mem_init (void)
 #ifdef CONFIG_MEMORY_HOTPLUG
 int arch_add_memory(int nid, u64 start, u64 size, bool for_device)
 {
-	pg_data_t *pgdat;
-	struct zone *zone;
 	unsigned long start_pfn = start >> PAGE_SHIFT;
 	unsigned long nr_pages = size >> PAGE_SHIFT;
 	int ret;
 
-	pgdat = NODE_DATA(nid);
-
-	zone = pgdat->node_zones +
-		zone_for_memory(nid, start, size, ZONE_NORMAL, for_device);
-	ret = __add_pages(nid, zone, start_pfn, nr_pages, !for_device);
-
+	ret = __add_pages(nid, start_pfn, nr_pages, !for_device);
 	if (ret)
 		printk("%s: Problem encountered in __add_pages() as ret=%d\n",
 		       __func__,  ret);

arch/powerpc/mm/mem.c

@@ -128,16 +128,12 @@ int __weak remove_section_mapping(unsigned long start, unsigned long end)
 
 int arch_add_memory(int nid, u64 start, u64 size, bool for_device)
 {
-	struct pglist_data *pgdata;
-	struct zone *zone;
 	unsigned long start_pfn = start >> PAGE_SHIFT;
 	unsigned long nr_pages = size >> PAGE_SHIFT;
 	int rc;
 
 	resize_hpt_for_hotplug(memblock_phys_mem_size());
 
-	pgdata = NODE_DATA(nid);
-
 	start = (unsigned long)__va(start);
 	rc = create_section_mapping(start, start + size);
 	if (rc) {
@@ -147,11 +143,7 @@ int arch_add_memory(int nid, u64 start, u64 size, bool for_device)
 		return -EFAULT;
 	}
 
-	/* this should work for most non-highmem platforms */
-	zone = pgdata->node_zones +
-		zone_for_memory(nid, start, size, 0, for_device);
-
-	return __add_pages(nid, zone, start_pfn, nr_pages, !for_device);
+	return __add_pages(nid, start_pfn, nr_pages, !for_device);
 }
 
 #ifdef CONFIG_MEMORY_HOTREMOVE

arch/s390/mm/init.c

@@ -168,41 +168,15 @@ unsigned long memory_block_size_bytes(void)
 #ifdef CONFIG_MEMORY_HOTPLUG
 int arch_add_memory(int nid, u64 start, u64 size, bool for_device)
 {
-	unsigned long zone_start_pfn, zone_end_pfn, nr_pages;
 	unsigned long start_pfn = PFN_DOWN(start);
 	unsigned long size_pages = PFN_DOWN(size);
-	pg_data_t *pgdat = NODE_DATA(nid);
-	struct zone *zone;
-	int rc, i;
+	int rc;
 
 	rc = vmem_add_mapping(start, size);
 	if (rc)
 		return rc;
 
-	for (i = 0; i < MAX_NR_ZONES; i++) {
-		zone = pgdat->node_zones + i;
-		if (zone_idx(zone) != ZONE_MOVABLE) {
-			/* Add range within existing zone limits, if possible */
-			zone_start_pfn = zone->zone_start_pfn;
-			zone_end_pfn = zone->zone_start_pfn +
-				       zone->spanned_pages;
-		} else {
-			/* Add remaining range to ZONE_MOVABLE */
-			zone_start_pfn = start_pfn;
-			zone_end_pfn = start_pfn + size_pages;
-		}
-		if (start_pfn < zone_start_pfn || start_pfn >= zone_end_pfn)
-			continue;
-		nr_pages = (start_pfn + size_pages > zone_end_pfn) ?
-			   zone_end_pfn - start_pfn : size_pages;
-		rc = __add_pages(nid, zone, start_pfn, nr_pages, !for_device);
-		if (rc)
-			break;
-		start_pfn += nr_pages;
-		size_pages -= nr_pages;
-		if (!size_pages)
-			break;
-	}
+	rc = __add_pages(nid, start_pfn, size_pages, !for_device);
 	if (rc)
 		vmem_remove_mapping(start, size);
 	return rc;

arch/sh/mm/init.c

@@ -487,18 +487,12 @@ void free_initrd_mem(unsigned long start, unsigned long end)
 #ifdef CONFIG_MEMORY_HOTPLUG
 int arch_add_memory(int nid, u64 start, u64 size, bool for_device)
 {
-	pg_data_t *pgdat;
 	unsigned long start_pfn = PFN_DOWN(start);
 	unsigned long nr_pages = size >> PAGE_SHIFT;
 	int ret;
 
-	pgdat = NODE_DATA(nid);
-
 	/* We only have ZONE_NORMAL, so this is easy.. */
-	ret = __add_pages(nid, pgdat->node_zones +
-			zone_for_memory(nid, start, size, ZONE_NORMAL,
-			for_device),
-			start_pfn, nr_pages, !for_device);
+	ret = __add_pages(nid, start_pfn, nr_pages, !for_device);
 	if (unlikely(ret))
 		printk("%s: Failed, __add_pages() == %d\n", __func__, ret);
 

arch/x86/mm/init_32.c

@@ -825,13 +825,10 @@ void __init mem_init(void)
 #ifdef CONFIG_MEMORY_HOTPLUG
 int arch_add_memory(int nid, u64 start, u64 size, bool for_device)
 {
-	struct pglist_data *pgdata = NODE_DATA(nid);
-	struct zone *zone = pgdata->node_zones +
-		zone_for_memory(nid, start, size, ZONE_HIGHMEM, for_device);
 	unsigned long start_pfn = start >> PAGE_SHIFT;
 	unsigned long nr_pages = size >> PAGE_SHIFT;
 
-	return __add_pages(nid, zone, start_pfn, nr_pages, !for_device);
+	return __add_pages(nid, start_pfn, nr_pages, !for_device);
 }
 
 #ifdef CONFIG_MEMORY_HOTREMOVE

arch/x86/mm/init_64.c

@@ -772,22 +772,15 @@ static void  update_end_of_memory_vars(u64 start, u64 size)
 	}
 }
 
-/*
- * Memory is added always to NORMAL zone. This means you will never get
- * additional DMA/DMA32 memory.
- */
 int arch_add_memory(int nid, u64 start, u64 size, bool for_device)
 {
-	struct pglist_data *pgdat = NODE_DATA(nid);
-	struct zone *zone = pgdat->node_zones +
-		zone_for_memory(nid, start, size, ZONE_NORMAL, for_device);
 	unsigned long start_pfn = start >> PAGE_SHIFT;
 	unsigned long nr_pages = size >> PAGE_SHIFT;
 	int ret;
 
 	init_memory_mapping(start, start + size);
 
-	ret = __add_pages(nid, zone, start_pfn, nr_pages, !for_device);
+	ret = __add_pages(nid, start_pfn, nr_pages, !for_device);
 	WARN_ON_ONCE(ret);
 
 	/* update max_pfn, max_low_pfn and high_memory */

drivers/base/memory.c

@@ -392,39 +392,43 @@ static ssize_t show_valid_zones(struct device *dev,
 				struct device_attribute *attr, char *buf)
 {
 	struct memory_block *mem = to_memory_block(dev);
-	unsigned long start_pfn, end_pfn;
-	unsigned long valid_start, valid_end, valid_pages;
+	unsigned long start_pfn = section_nr_to_pfn(mem->start_section_nr);
 	unsigned long nr_pages = PAGES_PER_SECTION * sections_per_block;
-	struct zone *zone;
-	int zone_shift = 0;
+	unsigned long valid_start_pfn, valid_end_pfn;
+	bool append = false;
+	int nid;
 
-	start_pfn = section_nr_to_pfn(mem->start_section_nr);
-	end_pfn = start_pfn + nr_pages;
-
-	/* The block contains more than one zone can not be offlined. */
-	if (!test_pages_in_a_zone(start_pfn, end_pfn, &valid_start, &valid_end))
+	/*
+	 * The block contains more than one zone can not be offlined.
+	 * This can happen e.g. for ZONE_DMA and ZONE_DMA32
+	 */
+	if (!test_pages_in_a_zone(start_pfn, start_pfn + nr_pages, &valid_start_pfn, &valid_end_pfn))
 		return sprintf(buf, "none\n");
 
-	zone = page_zone(pfn_to_page(valid_start));
-	valid_pages = valid_end - valid_start;
-
-	/* MMOP_ONLINE_KEEP */
-	sprintf(buf, "%s", zone->name);
+	start_pfn = valid_start_pfn;
+	nr_pages = valid_end_pfn - start_pfn;
 
-	/* MMOP_ONLINE_KERNEL */
-	zone_can_shift(valid_start, valid_pages, ZONE_NORMAL, &zone_shift);
-	if (zone_shift) {
-		strcat(buf, " ");
-		strcat(buf, (zone + zone_shift)->name);
+	/*
+	 * Check the existing zone. Make sure that we do that only on the
+	 * online nodes otherwise the page_zone is not reliable
+	 */
+	if (mem->state == MEM_ONLINE) {
+		strcat(buf, page_zone(pfn_to_page(start_pfn))->name);
+		goto out;
 	}
 
-	/* MMOP_ONLINE_MOVABLE */
-	zone_can_shift(valid_start, valid_pages, ZONE_MOVABLE, &zone_shift);
-	if (zone_shift) {
-		strcat(buf, " ");
-		strcat(buf, (zone + zone_shift)->name);
+	nid = pfn_to_nid(start_pfn);
+	if (allow_online_pfn_range(nid, start_pfn, nr_pages, MMOP_ONLINE_KERNEL)) {
+		strcat(buf, NODE_DATA(nid)->node_zones[ZONE_NORMAL].name);
+		append = true;
 	}
 
+	if (allow_online_pfn_range(nid, start_pfn, nr_pages, MMOP_ONLINE_MOVABLE)) {
+		if (append)
+			strcat(buf, " ");
+		strcat(buf, NODE_DATA(nid)->node_zones[ZONE_MOVABLE].name);
+	}
+out:
 	strcat(buf, "\n");
 
 	return strlen(buf);

include/linux/memory_hotplug.h

@@ -123,8 +123,8 @@ extern int __remove_pages(struct zone *zone, unsigned long start_pfn,
 	unsigned long nr_pages);
 #endif /* CONFIG_MEMORY_HOTREMOVE */
 
-/* reasonably generic interface to expand the physical pages in a zone  */
-extern int __add_pages(int nid, struct zone *zone, unsigned long start_pfn,
+/* reasonably generic interface to expand the physical pages */
+extern int __add_pages(int nid, unsigned long start_pfn,
 	unsigned long nr_pages, bool want_memblock);
 
 #ifdef CONFIG_NUMA
@@ -299,15 +299,16 @@ extern int add_memory_resource(int nid, struct resource *resource, bool online);
 extern int zone_for_memory(int nid, u64 start, u64 size, int zone_default,
 		bool for_device);
 extern int arch_add_memory(int nid, u64 start, u64 size, bool for_device);
+extern void move_pfn_range_to_zone(struct zone *zone, unsigned long start_pfn,
+		unsigned long nr_pages);
 extern int offline_pages(unsigned long start_pfn, unsigned long nr_pages);
 extern bool is_memblock_offlined(struct memory_block *mem);
 extern void remove_memory(int nid, u64 start, u64 size);
-extern int sparse_add_one_section(struct zone *zone, unsigned long start_pfn);
+extern int sparse_add_one_section(struct pglist_data *pgdat, unsigned long start_pfn);
 extern void sparse_remove_one_section(struct zone *zone, struct mem_section *ms,
 		unsigned long map_offset);
 extern struct page *sparse_decode_mem_map(unsigned long coded_mem_map,
 					  unsigned long pnum);
-extern bool zone_can_shift(unsigned long pfn, unsigned long nr_pages,
-			  enum zone_type target, int *zone_shift);
-
+extern bool allow_online_pfn_range(int nid, unsigned long pfn, unsigned long nr_pages,
+		int online_type);
 #endif /* __LINUX_MEMORY_HOTPLUG_H */

include/linux/mmzone.h

@@ -532,6 +532,22 @@ static inline bool zone_is_empty(struct zone *zone)
 	return zone->spanned_pages == 0;
 }
 
+/*
+ * Return true if [start_pfn, start_pfn + nr_pages) range has a non-empty
+ * intersection with the given zone
+ */
+static inline bool zone_intersects(struct zone *zone,
+		unsigned long start_pfn, unsigned long nr_pages)
+{
+	if (zone_is_empty(zone))
+		return false;
+	if (start_pfn >= zone_end_pfn(zone) ||
+	    start_pfn + nr_pages <= zone->zone_start_pfn)
+		return false;
+
+	return true;
+}
+
 /*
  * The "priority" of VM scanning is how much of the queues we will scan in one
  * go. A value of 12 for DEF_PRIORITY implies that we will scan 1/4096th of the

kernel/memremap.c

@@ -359,6 +359,10 @@ void *devm_memremap_pages(struct device *dev, struct resource *res,
 
 	mem_hotplug_begin();
 	error = arch_add_memory(nid, align_start, align_size, true);
+	if (!error)
+		move_pfn_range_to_zone(&NODE_DATA(nid)->node_zones[ZONE_DEVICE],
+					align_start >> PAGE_SHIFT,
+					align_size >> PAGE_SHIFT);
 	mem_hotplug_done();
 	if (error)
 		goto err_add_memory;

mm/memory_hotplug.c

@@ -433,25 +433,6 @@ out_fail:
 	return -1;
 }
 
-static struct zone * __meminit move_pfn_range(int zone_shift,
-		unsigned long start_pfn, unsigned long end_pfn)
-{
-	struct zone *zone = page_zone(pfn_to_page(start_pfn));
-	int ret = 0;
-
-	if (zone_shift < 0)
-		ret = move_pfn_range_left(zone + zone_shift, zone,
-					  start_pfn, end_pfn);
-	else if (zone_shift)
-		ret = move_pfn_range_right(zone, zone + zone_shift,
-					   start_pfn, end_pfn);
-
-	if (ret)
-		return NULL;
-
-	return zone + zone_shift;
-}
-
 static void __meminit grow_pgdat_span(struct pglist_data *pgdat, unsigned long start_pfn,
 				      unsigned long end_pfn)
 {
@@ -493,23 +474,35 @@ static int __meminit __add_zone(struct zone *zone, unsigned long phys_start_pfn)
 	return 0;
 }
 
-static int __meminit __add_section(int nid, struct zone *zone,
-		unsigned long phys_start_pfn, bool want_memblock)
+static int __meminit __add_section(int nid, unsigned long phys_start_pfn,
+		bool want_memblock)
 {
 	int ret;
+	int i;
 
 	if (pfn_valid(phys_start_pfn))
 		return -EEXIST;
 
-	ret = sparse_add_one_section(zone, phys_start_pfn);
-
+	ret = sparse_add_one_section(NODE_DATA(nid), phys_start_pfn);
 	if (ret < 0)
 		return ret;
 
-	ret = __add_zone(zone, phys_start_pfn);
+	/*
+	 * Make all the pages reserved so that nobody will stumble over half
+	 * initialized state.
+	 * FIXME: We also have to associate it with a node because pfn_to_node
+	 * relies on having page with the proper node.
+	 */
+	for (i = 0; i < PAGES_PER_SECTION; i++) {
+		unsigned long pfn = phys_start_pfn + i;
+		struct page *page;
+		if (!pfn_valid(pfn))
+			continue;
 
-	if (ret < 0)
-		return ret;
+		page = pfn_to_page(pfn);
+		set_page_node(page, nid);
+		SetPageReserved(page);
+	}
 
 	if (!want_memblock)
 		return 0;
@@ -523,7 +516,7 @@ static int __meminit __add_section(int nid, struct zone *zone,
  * call this function after deciding the zone to which to
  * add the new pages.
  */
-int __ref __add_pages(int nid, struct zone *zone, unsigned long phys_start_pfn,
+int __ref __add_pages(int nid, unsigned long phys_start_pfn,
 			unsigned long nr_pages, bool want_memblock)
 {
 	unsigned long i;
@@ -531,8 +524,6 @@ int __ref __add_pages(int nid, struct zone *zone, unsigned long phys_start_pfn,
 	int start_sec, end_sec;
 	struct vmem_altmap *altmap;
 
-	clear_zone_contiguous(zone);
-
 	/* during initialize mem_map, align hot-added range to section */
 	start_sec = pfn_to_section_nr(phys_start_pfn);
 	end_sec = pfn_to_section_nr(phys_start_pfn + nr_pages - 1);
@@ -552,7 +543,7 @@ int __ref __add_pages(int nid, struct zone *zone, unsigned long phys_start_pfn,
 	}
 
 	for (i = start_sec; i <= end_sec; i++) {
-		err = __add_section(nid, zone, section_nr_to_pfn(i), want_memblock);
+		err = __add_section(nid, section_nr_to_pfn(i), want_memblock);
 
 		/*
 		 * EEXIST is finally dealt with by ioresource collision
@@ -565,7 +556,6 @@ int __ref __add_pages(int nid, struct zone *zone, unsigned long phys_start_pfn,
 	}
 	vmemmap_populate_print_last();
 out:
-	set_zone_contiguous(zone);
 	return err;
 }
 EXPORT_SYMBOL_GPL(__add_pages);
@@ -1034,39 +1024,109 @@ static void node_states_set_node(int node, struct memory_notify *arg)
 	node_set_state(node, N_MEMORY);
 }
 
-bool zone_can_shift(unsigned long pfn, unsigned long nr_pages,
-		   enum zone_type target, int *zone_shift)
+bool allow_online_pfn_range(int nid, unsigned long pfn, unsigned long nr_pages, int online_type)
 {
-	struct zone *zone = page_zone(pfn_to_page(pfn));
-	enum zone_type idx = zone_idx(zone);
-	int i;
+	struct pglist_data *pgdat = NODE_DATA(nid);
+	struct zone *movable_zone = &pgdat->node_zones[ZONE_MOVABLE];
+	struct zone *normal_zone =  &pgdat->node_zones[ZONE_NORMAL];
 
-	*zone_shift = 0;
+	/*
+	 * TODO there shouldn't be any inherent reason to have ZONE_NORMAL
+	 * physically before ZONE_MOVABLE. All we need is they do not
+	 * overlap. Historically we didn't allow ZONE_NORMAL after ZONE_MOVABLE
+	 * though so let's stick with it for simplicity for now.
+	 * TODO make sure we do not overlap with ZONE_DEVICE
+	 */
+	if (online_type == MMOP_ONLINE_KERNEL) {
+		if (zone_is_empty(movable_zone))
+			return true;
+		return movable_zone->zone_start_pfn >= pfn + nr_pages;
+	} else if (online_type == MMOP_ONLINE_MOVABLE) {
+		return zone_end_pfn(normal_zone) <= pfn;
+	}
 
-	if (idx < target) {
-		/* pages must be at end of current zone */
-		if (pfn + nr_pages != zone_end_pfn(zone))
-			return false;
+	/* MMOP_ONLINE_KEEP will always succeed and inherits the current zone */
+	return online_type == MMOP_ONLINE_KEEP;
+}
 
-		/* no zones in use between current zone and target */
-		for (i = idx + 1; i < target; i++)
-			if (zone_is_initialized(zone - idx + i))
-				return false;
-	}
+static void __meminit resize_zone_range(struct zone *zone, unsigned long start_pfn,
+		unsigned long nr_pages)
+{
+	unsigned long old_end_pfn = zone_end_pfn(zone);
 
-	if (target < idx) {
-		/* pages must be at beginning of current zone */
-		if (pfn != zone->zone_start_pfn)
-			return false;
+	if (zone_is_empty(zone) || start_pfn < zone->zone_start_pfn)
+		zone->zone_start_pfn = start_pfn;
+
+	zone->spanned_pages = max(start_pfn + nr_pages, old_end_pfn) - zone->zone_start_pfn;
+}
+
+static void __meminit resize_pgdat_range(struct pglist_data *pgdat, unsigned long start_pfn,
+                                     unsigned long nr_pages)
+{
+	unsigned long old_end_pfn = pgdat_end_pfn(pgdat);
 
-		/* no zones in use between current zone and target */
-		for (i = target + 1; i < idx; i++)
-			if (zone_is_initialized(zone - idx + i))
-				return false;
+	if (!pgdat->node_spanned_pages || start_pfn < pgdat->node_start_pfn)
+		pgdat->node_start_pfn = start_pfn;
+
+	pgdat->node_spanned_pages = max(start_pfn + nr_pages, old_end_pfn) - pgdat->node_start_pfn;
+}
+
+void move_pfn_range_to_zone(struct zone *zone,
+		unsigned long start_pfn, unsigned long nr_pages)
+{
+	struct pglist_data *pgdat = zone->zone_pgdat;
+	int nid = pgdat->node_id;
+	unsigned long flags;
+
+	if (zone_is_empty(zone))
+		init_currently_empty_zone(zone, start_pfn, nr_pages);
+
+	clear_zone_contiguous(zone);
+
+	/* TODO Huh pgdat is irqsave while zone is not. It used to be like that before */
+	pgdat_resize_lock(pgdat, &flags);
+	zone_span_writelock(zone);
+	resize_zone_range(zone, start_pfn, nr_pages);
+	zone_span_writeunlock(zone);
+	resize_pgdat_range(pgdat, start_pfn, nr_pages);
+	pgdat_resize_unlock(pgdat, &flags);
+
+	/*
+	 * TODO now we have a visible range of pages which are not associated
+	 * with their zone properly. Not nice but set_pfnblock_flags_mask
+	 * expects the zone spans the pfn range. All the pages in the range
+	 * are reserved so nobody should be touching them so we should be safe
+	 */
+	memmap_init_zone(nr_pages, nid, zone_idx(zone), start_pfn, MEMMAP_HOTPLUG);
+
+	set_zone_contiguous(zone);
+}
+
+/*
+ * Associates the given pfn range with the given node and the zone appropriate
+ * for the given online type.
+ */
+static struct zone * __meminit move_pfn_range(int online_type, int nid,
+		unsigned long start_pfn, unsigned long nr_pages)
+{
+	struct pglist_data *pgdat = NODE_DATA(nid);
+	struct zone *zone = &pgdat->node_zones[ZONE_NORMAL];
+
+	if (online_type == MMOP_ONLINE_KEEP) {
+		struct zone *movable_zone = &pgdat->node_zones[ZONE_MOVABLE];
+		/*
+		 * MMOP_ONLINE_KEEP inherits the current zone which is
+		 * ZONE_NORMAL by default but we might be within ZONE_MOVABLE
+		 * already.
+		 */
+		if (zone_intersects(movable_zone, start_pfn, nr_pages))
+			zone = movable_zone;
+	} else if (online_type == MMOP_ONLINE_MOVABLE) {
+		zone = &pgdat->node_zones[ZONE_MOVABLE];
 	}
 
-	*zone_shift = target - idx;
-	return true;
+	move_pfn_range_to_zone(zone, start_pfn, nr_pages);
+	return zone;
 }
 
 /* Must be protected by mem_hotplug_begin() */
@@ -1079,38 +1139,21 @@ int __ref online_pages(unsigned long pfn, unsigned long nr_pages, int online_typ
 	int nid;
 	int ret;
 	struct memory_notify arg;
-	int zone_shift = 0;
 
-	/*
-	 * This doesn't need a lock to do pfn_to_page().
-	 * The section can't be removed here because of the
-	 * memory_block->state_mutex.
-	 */
-	zone = page_zone(pfn_to_page(pfn));
-
-	if ((zone_idx(zone) > ZONE_NORMAL ||
-	    online_type == MMOP_ONLINE_MOVABLE) &&
-	    !can_online_high_movable(pfn_to_nid(pfn)))
+	nid = pfn_to_nid(pfn);
+	if (!allow_online_pfn_range(nid, pfn, nr_pages, online_type))
 		return -EINVAL;
 
-	if (online_type == MMOP_ONLINE_KERNEL) {
-		if (!zone_can_shift(pfn, nr_pages, ZONE_NORMAL, &zone_shift))
-			return -EINVAL;
-	} else if (online_type == MMOP_ONLINE_MOVABLE) {
-		if (!zone_can_shift(pfn, nr_pages, ZONE_MOVABLE, &zone_shift))
-			return -EINVAL;
-	}
-
-	zone = move_pfn_range(zone_shift, pfn, pfn + nr_pages);
-	if (!zone)
+	if (online_type == MMOP_ONLINE_MOVABLE && !can_online_high_movable(nid))
 		return -EINVAL;
 
+	/* associate pfn range with the zone */
+	zone = move_pfn_range(online_type, nid, pfn, nr_pages);
+
 	arg.start_pfn = pfn;
 	arg.nr_pages = nr_pages;
 	node_states_check_changes_online(nr_pages, zone, &arg);
 
-	nid = zone_to_nid(zone);
-
 	ret = memory_notify(MEM_GOING_ONLINE, &arg);
 	ret = notifier_to_errno(ret);
 	if (ret)

mm/sparse.c

@@ -761,10 +761,9 @@ static void free_map_bootmem(struct page *memmap)
  * set.  If this is <=0, then that means that the passed-in
  * map was not consumed and must be freed.
  */
-int __meminit sparse_add_one_section(struct zone *zone, unsigned long start_pfn)
+int __meminit sparse_add_one_section(struct pglist_data *pgdat, unsigned long start_pfn)
 {
 	unsigned long section_nr = pfn_to_section_nr(start_pfn);
-	struct pglist_data *pgdat = zone->zone_pgdat;
 	struct mem_section *ms;
 	struct page *memmap;
 	unsigned long *usemap;