@@ -178,6 +178,11 @@ static inline unsigned long io_tlb_offset(unsigned long val)
 	return val & (IO_TLB_SEGSIZE - 1);
 }
 
+static inline unsigned long nr_slots(u64 val)
+{
+	return DIV_ROUND_UP(val, IO_TLB_SIZE);
+}
+
 /*
  * Early SWIOTLB allocation may be too early to allow an architecture to
  * perform the desired operations.  This function allows the architecture to

@@ -477,20 +482,20 @@ phys_addr_t swiotlb_tbl_map_single(struct device *hwdev, phys_addr_t orig_addr,
 
 	tbl_dma_addr &= mask;
 
-	offset_slots = ALIGN(tbl_dma_addr, IO_TLB_SIZE) >> IO_TLB_SHIFT;
+	offset_slots = nr_slots(tbl_dma_addr);
 
 	/*
 	 * Carefully handle integer overflow which can occur when mask == ~0UL.
 	 */
 	max_slots = mask + 1
-		    ? ALIGN(mask + 1, IO_TLB_SIZE) >> IO_TLB_SHIFT
+		    ? nr_slots(mask + 1)
 		    : 1UL << (BITS_PER_LONG - IO_TLB_SHIFT);
 
 	/*
 	 * For mappings greater than or equal to a page, we limit the stride
 	 * (and hence alignment) to a page size.
 	 */
-	nslots = ALIGN(alloc_size, IO_TLB_SIZE) >> IO_TLB_SHIFT;
+	nslots = nr_slots(alloc_size);
 	if (alloc_size >= PAGE_SIZE)
 		stride = (1 << (PAGE_SHIFT - IO_TLB_SHIFT));
 	else

@@ -586,7 +591,7 @@ void swiotlb_tbl_unmap_single(struct device *hwdev, phys_addr_t tlb_addr,
 			      enum dma_data_direction dir, unsigned long attrs)
 {
 	unsigned long flags;
-	int i, count, nslots = ALIGN(alloc_size, IO_TLB_SIZE) >> IO_TLB_SHIFT;
+	int i, count, nslots = nr_slots(alloc_size);
 	int index = (tlb_addr - io_tlb_start) >> IO_TLB_SHIFT;
 	phys_addr_t orig_addr = io_tlb_orig_addr[index];