mem-hotplug: introduce movablenode option

index b5f8218..c4cd81a 100644
@@ -157,6 +157,38 @@ static inline int save_add_info(void) {return 1;}
 static inline int save_add_info(void) {return 0;}
 #endif
 
+static nodemask_t movablenode_mask;
+
+static void __init parse_movablenode_one(char *p)
+{
+	int node;
+
+	get_option(&p, &node);
+	node_set(node, movablenode_mask);
+}
+
+/*
+ * movablenode=<movable nid>,...,<movable nid> sets which node is movable
+ * node.
+ */
+static int __init parse_movablenode_opt(char *str)
+{
+#ifdef CONFIG_MOVABLE_NODE
+	while (str) {
+		char *k = strchr(str, ',');
+
+		if (k)
+			*k++ = 0;
+		parse_movablenode_one(str);
+		str = k;
+	}
+#else
+	pr_warn("movable_node option not supported\n");
+#endif
+	return 0;
+}
+early_param("movablenode", parse_movablenode_opt);
+
 /* Callback for parsing of the Proximity Domain <-> Memory Area mappings */
 int __init
 acpi_numa_memory_affinity_init(struct acpi_srat_mem_affinity *ma)

@@ -205,6 +237,10 @@ acpi_numa_memory_affinity_init(struct acpi_srat_mem_affinity *ma)
 
 	max_possible_pfn = max(max_possible_pfn, PFN_UP(end - 1));
 
+	if (node_isset(node, movablenode_mask) && memblock_mark_hotplug(start, ma->length))
+		pr_warn("SRAT debug: Failed to mark hotplug range [mem %#010Lx-%#010Lx] in memblock\n",
+			(unsigned long long)start, (unsigned long long)end - 1);
+
 	return 0;
 out_err_bad_srat:
 	bad_srat();

index 2b258ec..e0ec3b6 100644
@@ -1399,15 +1399,18 @@ static void __init deferred_free_range(struct page *page,
 		return;
 
 	/* Free a large naturally-aligned chunk if possible */
-	if (nr_pages == MAX_ORDER_NR_PAGES &&
-	    (pfn & (MAX_ORDER_NR_PAGES-1)) == 0) {
+	if (nr_pages == pageblock_nr_pages &&
+	    (pfn & (pageblock_nr_pages - 1)) == 0) {
 		set_pageblock_migratetype(page, MIGRATE_MOVABLE);
-		__free_pages_boot_core(page, MAX_ORDER-1);
+		__free_pages_boot_core(page, pageblock_order);
 		return;
 	}
 
-	for (i = 0; i < nr_pages; i++, page++)
+	for (i = 0; i < nr_pages; i++, page++, pfn++) {
+		if ((pfn & (pageblock_nr_pages - 1)) == 0)
+			set_pageblock_migratetype(page, MIGRATE_MOVABLE);
 		__free_pages_boot_core(page, 0);
+	}
 }
 
 /* Completion tracking for deferred_init_memmap() threads */

@@ -1475,9 +1478,9 @@ static int __init deferred_init_memmap(void *data)
 
 			/*
 			 * Ensure pfn_valid is checked every
-			 * MAX_ORDER_NR_PAGES for memory holes
+			 * pageblock_nr_pages for memory holes
 			 */
-			if ((pfn & (MAX_ORDER_NR_PAGES - 1)) == 0) {
+			if ((pfn & (pageblock_nr_pages - 1)) == 0) {
 				if (!pfn_valid(pfn)) {
 					page = NULL;
 					goto free_range;

@@ -1490,7 +1493,7 @@ static int __init deferred_init_memmap(void *data)
 			}
 
 			/* Minimise pfn page lookups and scheduler checks */
-			if (page && (pfn & (MAX_ORDER_NR_PAGES - 1)) != 0) {
+			if (page && (pfn & (pageblock_nr_pages - 1)) != 0) {
 				page++;
 			} else {
 				nr_pages += nr_to_free;

@@ -1526,6 +1529,9 @@ free_range:
 			free_base_page = NULL;
 			free_base_pfn = nr_to_free = 0;
 		}
+		/* Free the last block of pages to allocator */
+		nr_pages += nr_to_free;
+		deferred_free_range(free_base_page, free_base_pfn, nr_to_free);
 
 		first_init_pfn = max(end_pfn, first_init_pfn);
 	}

index 2b258ec..e0ec3b6 100644
@@ -1399,15 +1399,18 @@ static void __init deferred_free_range(struct page *page,
 		return;
 
 	/* Free a large naturally-aligned chunk if possible */
-	if (nr_pages == MAX_ORDER_NR_PAGES &&
-	    (pfn & (MAX_ORDER_NR_PAGES-1)) == 0) {
+	if (nr_pages == pageblock_nr_pages &&
+	    (pfn & (pageblock_nr_pages - 1)) == 0) {
 		set_pageblock_migratetype(page, MIGRATE_MOVABLE);
-		__free_pages_boot_core(page, MAX_ORDER-1);
+		__free_pages_boot_core(page, pageblock_order);
 		return;
 	}
 
-	for (i = 0; i < nr_pages; i++, page++)
+	for (i = 0; i < nr_pages; i++, page++, pfn++) {
+		if ((pfn & (pageblock_nr_pages - 1)) == 0)
+			set_pageblock_migratetype(page, MIGRATE_MOVABLE);
 		__free_pages_boot_core(page, 0);
+	}
 }
 
 /* Completion tracking for deferred_init_memmap() threads */

@@ -1475,9 +1478,9 @@ static int __init deferred_init_memmap(void *data)
 
 			/*
 			 * Ensure pfn_valid is checked every
-			 * MAX_ORDER_NR_PAGES for memory holes
+			 * pageblock_nr_pages for memory holes
 			 */
-			if ((pfn & (MAX_ORDER_NR_PAGES - 1)) == 0) {
+			if ((pfn & (pageblock_nr_pages - 1)) == 0) {
 				if (!pfn_valid(pfn)) {
 					page = NULL;
 					goto free_range;

@@ -1490,7 +1493,7 @@ static int __init deferred_init_memmap(void *data)
 			}
 
 			/* Minimise pfn page lookups and scheduler checks */
-			if (page && (pfn & (MAX_ORDER_NR_PAGES - 1)) != 0) {
+			if (page && (pfn & (pageblock_nr_pages - 1)) != 0) {
 				page++;
 			} else {
 				nr_pages += nr_to_free;

@@ -1526,6 +1529,9 @@ free_range:
 			free_base_page = NULL;
 			free_base_pfn = nr_to_free = 0;
 		}
+		/* Free the last block of pages to allocator */
+		nr_pages += nr_to_free;
+		deferred_free_range(free_base_page, free_base_pfn, nr_to_free);
 
 		first_init_pfn = max(end_pfn, first_init_pfn);
 	}

index 6903b69..2b258ec 100644
@@ -5173,15 +5173,6 @@ void __meminit memmap_init_zone(unsigned long size, int nid, unsigned long zone,
 
 #ifdef CONFIG_HAVE_MEMBLOCK_NODE_MAP
 		/*
-		 * If not mirrored_kernelcore and ZONE_MOVABLE exists, range
-		 * from zone_movable_pfn[nid] to end of each node should be
-		 * ZONE_MOVABLE not ZONE_NORMAL. skip it.
-		 */
-		if (!mirrored_kernelcore && zone_movable_pfn[nid])
-			if (zone == ZONE_NORMAL && pfn >= zone_movable_pfn[nid])
-				continue;
-
-		/*
 		 * Check given memblock attribute by firmware which can affect
 		 * kernel memory layout.  If zone==ZONE_MOVABLE but memory is
 		 * mirrored, it's an overlapped memmap init. skip it.

@@ -5619,6 +5610,12 @@ static void __meminit adjust_zone_range_for_zone_movable(int nid,
 			*zone_end_pfn = min(node_end_pfn,
 				arch_zone_highest_possible_pfn[movable_zone]);
 
+		/* Adjust for ZONE_MOVABLE starting within this range */
+		} else if (!mirrored_kernelcore &&
+			*zone_start_pfn < zone_movable_pfn[nid] &&
+			*zone_end_pfn > zone_movable_pfn[nid]) {
+			*zone_end_pfn = zone_movable_pfn[nid];
+
 		/* Check if this whole range is within ZONE_MOVABLE */
 		} else if (*zone_start_pfn >= zone_movable_pfn[nid])
 			*zone_start_pfn = *zone_end_pfn;

@@ -5722,28 +5719,23 @@ static unsigned long __meminit zone_absent_pages_in_node(int nid,
 	 * Treat pages to be ZONE_MOVABLE in ZONE_NORMAL as absent pages
 	 * and vice versa.
 	 */
-	if (zone_movable_pfn[nid]) {
-		if (mirrored_kernelcore) {
-			unsigned long start_pfn, end_pfn;
-			struct memblock_region *r;
-
-			for_each_memblock(memory, r) {
-				start_pfn = clamp(memblock_region_memory_base_pfn(r),
-						  zone_start_pfn, zone_end_pfn);
-				end_pfn = clamp(memblock_region_memory_end_pfn(r),
-						zone_start_pfn, zone_end_pfn);
-
-				if (zone_type == ZONE_MOVABLE &&
-				    memblock_is_mirror(r))
-					nr_absent += end_pfn - start_pfn;
-
-				if (zone_type == ZONE_NORMAL &&
-				    !memblock_is_mirror(r))
-					nr_absent += end_pfn - start_pfn;
-			}
-		} else {
-			if (zone_type == ZONE_NORMAL)
-				nr_absent += node_end_pfn - zone_movable_pfn[nid];
+	if (mirrored_kernelcore && zone_movable_pfn[nid]) {
+		unsigned long start_pfn, end_pfn;
+		struct memblock_region *r;
+
+		for_each_memblock(memory, r) {
+			start_pfn = clamp(memblock_region_memory_base_pfn(r),
+					  zone_start_pfn, zone_end_pfn);
+			end_pfn = clamp(memblock_region_memory_end_pfn(r),
+					zone_start_pfn, zone_end_pfn);
+
+			if (zone_type == ZONE_MOVABLE &&
+			    memblock_is_mirror(r))
+				nr_absent += end_pfn - start_pfn;
+
+			if (zone_type == ZONE_NORMAL &&
+			    !memblock_is_mirror(r))
+				nr_absent += end_pfn - start_pfn;
 		}
 	}