diff --git a/tools/perf/util/header.c b/tools/perf/util/header.c
index 2dd5edf161b731ae1be22b9530e25e59fd444f47..4f9b247fb31289582fdca95aa2a0874d69c3cf7d 100644
--- a/tools/perf/util/header.c
+++ b/tools/perf/util/header.c
@@ -1942,7 +1942,6 @@ int perf_file_header__read(struct perf_file_header *header,
 		else
 			return -1;
 	} else if (ph->needs_swap) {
-		unsigned int i;
 		/*
 		 * feature bitmap is declared as an array of unsigned longs --
 		 * not good since its size can differ between the host that
@@ -1958,14 +1957,17 @@ int perf_file_header__read(struct perf_file_header *header,
 		 * file), punt and fallback to the original behavior --
 		 * clearing all feature bits and setting buildid.
 		 */
-		for (i = 0; i < BITS_TO_LONGS(HEADER_FEAT_BITS); ++i)
-			header->adds_features[i] = bswap_64(header->adds_features[i]);
+		mem_bswap_64(&header->adds_features,
+			    BITS_TO_U64(HEADER_FEAT_BITS));
 
 		if (!test_bit(HEADER_HOSTNAME, header->adds_features)) {
-			for (i = 0; i < BITS_TO_LONGS(HEADER_FEAT_BITS); ++i) {
-				header->adds_features[i] = bswap_64(header->adds_features[i]);
-				header->adds_features[i] = bswap_32(header->adds_features[i]);
-			}
+			/* unswap as u64 */
+			mem_bswap_64(&header->adds_features,
+				    BITS_TO_U64(HEADER_FEAT_BITS));
+
+			/* unswap as u32 */
+			mem_bswap_32(&header->adds_features,
+				    BITS_TO_U32(HEADER_FEAT_BITS));
 		}
 
 		if (!test_bit(HEADER_HOSTNAME, header->adds_features)) {
diff --git a/tools/perf/util/include/linux/bitops.h b/tools/perf/util/include/linux/bitops.h
index f1584833bd2296aa2befe02950e5d49c7a93741f..587a230d2075a3ab1451cb46d34f651e20ffc486 100644
--- a/tools/perf/util/include/linux/bitops.h
+++ b/tools/perf/util/include/linux/bitops.h
@@ -8,6 +8,8 @@
 #define BITS_PER_LONG __WORDSIZE
 #define BITS_PER_BYTE           8
 #define BITS_TO_LONGS(nr)       DIV_ROUND_UP(nr, BITS_PER_BYTE * sizeof(long))
+#define BITS_TO_U64(nr)         DIV_ROUND_UP(nr, BITS_PER_BYTE * sizeof(u64))
+#define BITS_TO_U32(nr)         DIV_ROUND_UP(nr, BITS_PER_BYTE * sizeof(u32))
 
 #define for_each_set_bit(bit, addr, size) \
 	for ((bit) = find_first_bit((addr), (size));		\
diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c
index 2600916efa8334c8a7ce56f16b1d41d6c20b540c..c3e399bcf18deea25f4db0aafa69278b5b4cb570 100644
--- a/tools/perf/util/session.c
+++ b/tools/perf/util/session.c
@@ -442,6 +442,16 @@ static void perf_tool__fill_defaults(struct perf_tool *tool)
 			tool->finished_round = process_finished_round_stub;
 	}
 }
+ 
+void mem_bswap_32(void *src, int byte_size)
+{
+	u32 *m = src;
+	while (byte_size > 0) {
+		*m = bswap_32(*m);
+		byte_size -= sizeof(u32);
+		++m;
+	}
+}
 
 void mem_bswap_64(void *src, int byte_size)
 {
diff --git a/tools/perf/util/session.h b/tools/perf/util/session.h
index 7a5434c005653a4736cabdc2921ad907f74f2c4c..0c702e3f0a364272a9d979b04786403c4e079bbe 100644
--- a/tools/perf/util/session.h
+++ b/tools/perf/util/session.h
@@ -80,6 +80,7 @@ struct branch_info *machine__resolve_bstack(struct machine *self,
 bool perf_session__has_traces(struct perf_session *self, const char *msg);
 
 void mem_bswap_64(void *src, int byte_size);
+void mem_bswap_32(void *src, int byte_size);
 void perf_event__attr_swap(struct perf_event_attr *attr);
 
 int perf_session__create_kernel_maps(struct perf_session *self);