diff --git a/include/asm-generic/percpu.h b/include/asm-generic/percpu.h
index 0504ef8..976f8ac 100644
--- a/include/asm-generic/percpu.h
+++ b/include/asm-generic/percpu.h
@@ -115,15 +115,35 @@ do {									\
 	(__ret);							\
 })
 
-#define this_cpu_generic_read(pcp)					\
+#define __this_cpu_generic_read_nopreempt(pcp)				\
 ({									\
 	typeof(pcp) __ret;						\
 	preempt_disable_notrace();					\
-	__ret = raw_cpu_generic_read(pcp);				\
+	__ret = READ_ONCE(*raw_cpu_ptr(&(pcp)));			\
 	preempt_enable_notrace();					\
 	__ret;								\
 })
 
+#define __this_cpu_generic_read_noirq(pcp)				\
+({									\
+	typeof(pcp) __ret;						\
+	unsigned long __flags;						\
+	raw_local_irq_save(__flags);					\
+	__ret = raw_cpu_generic_read(pcp);				\
+	raw_local_irq_restore(__flags);					\
+	__ret;								\
+})
+
+#define this_cpu_generic_read(pcp)					\
+({									\
+	typeof(pcp) __ret;						\
+	if (__native_word(pcp))						\
+		__ret = __this_cpu_generic_read_nopreempt(pcp);		\
+	else								\
+		__ret = __this_cpu_generic_read_noirq(pcp);		\
+	__ret;								\
+})
+
 #define this_cpu_generic_to_op(pcp, val, op)				\
 do {									\
 	unsigned long __flags;						\
diff --git a/mm/percpu-stats.c b/mm/percpu-stats.c
index 6142484..7a58460 100644
--- a/mm/percpu-stats.c
+++ b/mm/percpu-stats.c
@@ -73,7 +73,7 @@ static void chunk_map_stats(struct seq_file *m, struct pcpu_chunk *chunk,
 		     last_alloc + 1 : 0;
 
 	as_len = 0;
-	start = chunk->start_offset;
+	start = chunk->start_offset / PCPU_MIN_ALLOC_SIZE;
 
 	/*
 	 * If a bit is set in the allocation map, the bound_map identifies
diff --git a/mm/percpu.c b/mm/percpu.c
index 59d44d6..aa121ce 100644
--- a/mm/percpu.c
+++ b/mm/percpu.c
@@ -353,6 +353,8 @@ static void pcpu_next_md_free_region(struct pcpu_chunk *chunk, int *bit_off,
 					block->contig_hint_start);
 			return;
 		}
+		/* reset to satisfy the second predicate above */
+		block_off = 0;
 
 		*bits = block->right_free;
 		*bit_off = (i + 1) * PCPU_BITMAP_BLOCK_BITS - block->right_free;
@@ -407,6 +409,8 @@ static void pcpu_next_fit_region(struct pcpu_chunk *chunk, int alloc_bits,
 			*bit_off = pcpu_block_off_to_off(i, block->first_free);
 			return;
 		}
+		/* reset to satisfy the second predicate above */
+		block_off = 0;
 
 		*bit_off = ALIGN(PCPU_BITMAP_BLOCK_BITS - block->right_free,
 				 align);