Thanks,

Can you try this?

diff --git a/lib/iommu-helper.c b/lib/iommu-helper.c
index e7d8544..495575a 100644
--- a/lib/iommu-helper.c
+++ b/lib/iommu-helper.c

@@ -8,15 +8,20 @@
 static unsigned long find_next_zero_area(unsigned long *map,
 					 unsigned long size,
 					 unsigned long start,
-					 unsigned int nr)
+					 unsigned int nr,
+					 unsigned long align_mask)
 {
 	unsigned long index, end, i;
 again:
 	index = find_next_zero_bit(map, size, start);
+
+	/* Align allocation */
+	index = (index + align_mask) & ~align_mask;
+
 	end = index + nr;
-	if (end > size)
+	if (end >= size)
 		return -1;
-	for (i = index + 1; i < end; i++) {
+	for (i = index; i < end; i++) {
 		if (test_bit(i, map)) {
 			start = i+1;
 			goto again;

@@ -50,9 +55,8 @@ unsigned long iommu_area_alloc(unsigned long *map, unsigned long size,
 {
 	unsigned long index;
 again:
-	index = find_next_zero_area(map, size, start, nr);
+	index = find_next_zero_area(map, size, start, nr, align_mask);
 	if (index != -1) {
-		index = (index + align_mask) & ~align_mask;
 		if (is_span_boundary(index, nr, shift, boundary_size)) {
 			/* we could do more effectively */
 			start = index + 1;