+#ifdef CONFIG_SWIOTLB
+	if (unlikely(dev->dma_io_tlb_mem))
+		return swiotlb_alloc(dev, size, dma_handle, attrs);
+#endif

Another place where the dma_io_tlb_mem is useful to avoid the ifdef.

-phys_addr_t swiotlb_tbl_map_single(struct device *hwdev, phys_addr_t orig_addr,
-		size_t mapping_size, size_t alloc_size,
-		enum dma_data_direction dir, unsigned long attrs)
+static int swiotlb_tbl_find_free_region(struct device *hwdev,
+					dma_addr_t tbl_dma_addr,
+					size_t alloc_size,
+					unsigned long attrs)

+static void swiotlb_tbl_release_region(struct device *hwdev, int index,
+				       size_t size)

This refactoring should be another prep patch.

+void *swiotlb_alloc(struct device *dev, size_t size, dma_addr_t *dma_handle,
+		    unsigned long attrs)

I'd rather have the names convey there are for the per-device bounce
buffer in some form.

+	struct io_tlb_mem *mem = dev->dma_io_tlb_mem;

While we're at it I wonder if the io_tlb is something we could change
while we're at it.  Maybe replace io_tlb_mem with struct swiotlb
and rename the field in struct device to dev_swiotlb?

+	int index;
+	void *vaddr;
+	phys_addr_t tlb_addr;
+
+	size = PAGE_ALIGN(size);
+	index = swiotlb_tbl_find_free_region(dev, mem->start, size, attrs);
+	if (index < 0)
+		return NULL;
+
+	tlb_addr = mem->start + (index << IO_TLB_SHIFT);
+	*dma_handle = phys_to_dma_unencrypted(dev, tlb_addr);
+
+	if (!dev_is_dma_coherent(dev)) {
+		unsigned long pfn = PFN_DOWN(tlb_addr);
+
+		/* remove any dirty cache lines on the kernel alias */
+		arch_dma_prep_coherent(pfn_to_page(pfn), size);

Can we hook in somewhat lower level in the dma-direct code so that all
the remapping in dma-direct can be reused instead of duplicated?  That
also becomes important if we want to use non-remapping uncached support,
e.g. on mips or x86, or the direct changing of the attributes that Will
planned to look into for arm64.