diff --git a/mm/percpu-internal.h b/mm/percpu-internal.h
index c876b5b5bc18..f02f31cea0e6 100644
--- a/mm/percpu-internal.h
+++ b/mm/percpu-internal.h
@@ -26,6 +26,9 @@ struct pcpu_chunk {
 	int			start_offset;	/* the overlap with the previous
 						   region to have a page aligned
 						   base_addr */
+	int			end_offset;	/* additional area required to
+						   have the region end page
+						   aligned */
 	int			nr_populated;	/* # of populated pages */
 	unsigned long		populated[];	/* populated bitmap */
 };
diff --git a/mm/percpu-stats.c b/mm/percpu-stats.c
index 32f3550ea099..ffbdb96cdbeb 100644
--- a/mm/percpu-stats.c
+++ b/mm/percpu-stats.c
@@ -51,7 +51,7 @@ static int find_max_map_used(void)
 static void chunk_map_stats(struct seq_file *m, struct pcpu_chunk *chunk,
 			    int *buffer)
 {
-	int i, s_index, last_alloc, alloc_sign, as_len;
+	int i, s_index, e_index, last_alloc, alloc_sign, as_len;
 	int *alloc_sizes, *p;
 	/* statistics */
 	int sum_frag = 0, max_frag = 0;
@@ -59,10 +59,11 @@ static void chunk_map_stats(struct seq_file *m, struct pcpu_chunk *chunk,
 
 	alloc_sizes = buffer;
 	s_index = (chunk->start_offset) ? 1 : 0;
+	e_index = chunk->map_used - ((chunk->end_offset) ? 1 : 0);
 
 	/* find last allocation */
 	last_alloc = -1;
-	for (i = chunk->map_used - 1; i >= s_index; i--) {
+	for (i = e_index - 1; i >= s_index; i--) {
 		if (chunk->map[i] & 1) {
 			last_alloc = i;
 			break;
diff --git a/mm/percpu.c b/mm/percpu.c
index 2e785a77ce14..1d2c980fde3f 100644
--- a/mm/percpu.c
+++ b/mm/percpu.c
@@ -715,12 +715,16 @@ static struct pcpu_chunk * __init pcpu_alloc_first_chunk(void *base_addr,
 							 int init_map_size)
 {
 	struct pcpu_chunk *chunk;
+	int region_size;
+
+	region_size = PFN_ALIGN(start_offset + map_size);
 
 	chunk = memblock_virt_alloc(pcpu_chunk_struct_size, 0);
 	INIT_LIST_HEAD(&chunk->list);
 	INIT_LIST_HEAD(&chunk->map_extend_list);
 	chunk->base_addr = base_addr;
 	chunk->start_offset = start_offset;
+	chunk->end_offset = region_size - chunk->start_offset - map_size;
 	chunk->map = map;
 	chunk->map_alloc = init_map_size;
 
@@ -735,6 +739,11 @@ static struct pcpu_chunk * __init pcpu_alloc_first_chunk(void *base_addr,
 	chunk->map[2] = (chunk->start_offset + chunk->free_size) | 1;
 	chunk->map_used = 2;
 
+	if (chunk->end_offset) {
+		/* hide the end of the bitmap */
+		chunk->map[++chunk->map_used] = region_size | 1;
+	}
+
 	return chunk;
 }