diff --git a/lib/sort.c b/lib/sort.c
index 43c9fe73ae2e..fc20df42aa6f 100644
--- a/lib/sort.c
+++ b/lib/sort.c
@@ -8,6 +8,12 @@
 #include <linux/export.h>
 #include <linux/sort.h>
 
+static int alignment_ok(const void *base, int align)
+{
+	return IS_ENABLED(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS) ||
+		((unsigned long)base & (align - 1)) == 0;
+}
+
 static void u32_swap(void *a, void *b, int size)
 {
 	u32 t = *(u32 *)a;
@@ -15,6 +21,13 @@ static void u32_swap(void *a, void *b, int size)
 	*(u32 *)b = t;
 }
 
+static void u64_swap(void *a, void *b, int size)
+{
+	u64 t = *(u64 *)a;
+	*(u64 *)a = *(u64 *)b;
+	*(u64 *)b = t;
+}
+
 static void generic_swap(void *a, void *b, int size)
 {
 	char t;
@@ -50,8 +63,14 @@ void sort(void *base, size_t num, size_t size,
 	/* pre-scale counters for performance */
 	int i = (num/2 - 1) * size, n = num * size, c, r;
 
-	if (!swap_func)
-		swap_func = (size == 4 ? u32_swap : generic_swap);
+	if (!swap_func) {
+		if (size == 4 && alignment_ok(base, 4))
+			swap_func = u32_swap;
+		else if (size == 8 && alignment_ok(base, 8))
+			swap_func = u64_swap;
+		else
+			swap_func = generic_swap;
+	}
 
 	/* heapify */
 	for ( ; i >= 0; i -= size) {