diff --git a/include/linux/bitmap.h b/include/linux/bitmap.h
index 598bc999f4c2860969771b77d67872348f1f87f1..3b77588a93602eecd5d73d30d6fd77377286f07e 100644
--- a/include/linux/bitmap.h
+++ b/include/linux/bitmap.h
@@ -339,6 +339,24 @@ static inline int bitmap_parse(const char *buf, unsigned int buflen,
 	return __bitmap_parse(buf, buflen, 0, maskp, nmaskbits);
 }
 
+/*
+ * bitmap_from_u64 - Check and swap words within u64.
+ *  @mask: source bitmap
+ *  @dst:  destination bitmap
+ *
+ * In 32-bit Big Endian kernel, when using (u32 *)(&val)[*]
+ * to read u64 mask, we will get the wrong word.
+ * That is "(u32 *)(&val)[0]" gets the upper 32 bits,
+ * but we expect the lower 32-bits of u64.
+ */
+static inline void bitmap_from_u64(unsigned long *dst, u64 mask)
+{
+	dst[0] = mask & ULONG_MAX;
+
+	if (sizeof(mask) > sizeof(unsigned long))
+		dst[1] = mask >> 32;
+}
+
 #endif /* __ASSEMBLY__ */
 
 #endif /* __LINUX_BITMAP_H */
diff --git a/kernel/events/core.c b/kernel/events/core.c
index ca4fde5ed2680054cd53f158584cf1d4a5566c33..849919c2f3d789595c596855e48c683558a1154b 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -5340,9 +5340,10 @@ perf_output_sample_regs(struct perf_output_handle *handle,
 			struct pt_regs *regs, u64 mask)
 {
 	int bit;
+	DECLARE_BITMAP(_mask, 64);
 
-	for_each_set_bit(bit, (const unsigned long *) &mask,
-			 sizeof(mask) * BITS_PER_BYTE) {
+	bitmap_from_u64(_mask, mask);
+	for_each_set_bit(bit, _mask, sizeof(mask) * BITS_PER_BYTE) {
 		u64 val;
 
 		val = perf_reg_value(regs, bit);