iommu/dma: Refactor iommu_dma_free

The freeing logic was made particularly horrible by part of it being
opaque to the arch wrapper, which led to a lot of convoluted repetition
to ensure each path did everything in the right order. Now that it's
all private, we can pick apart and consolidate the logically-distinct
steps of freeing the IOMMU mapping, the underlying pages, and the CPU
remap (if necessary) into something much more manageable.
Signed-off-by: Robin Murphy <robin.murphy@arm.com>
[various cosmetic changes to the code flow]
Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Joerg Roedel <jroedel@suse.de>

drivers/iommu/dma-iommu.c

@@ -935,6 +935,39 @@ static void iommu_dma_unmap_resource(struct device *dev, dma_addr_t handle,
 	__iommu_dma_unmap(dev, handle, size);
 }
 
+static void iommu_dma_free(struct device *dev, size_t size, void *cpu_addr,
+		dma_addr_t handle, unsigned long attrs)
+{
+	size_t alloc_size = PAGE_ALIGN(size);
+	int count = alloc_size >> PAGE_SHIFT;
+	struct page *page = NULL, **pages = NULL;
+
+	__iommu_dma_unmap(dev, handle, size);
+
+	/* Non-coherent atomic allocation? Easy */
+	if (dma_free_from_pool(cpu_addr, alloc_size))
+		return;
+
+	if (is_vmalloc_addr(cpu_addr)) {
+		/*
+		 * If it the address is remapped, then it's either non-coherent
+		 * or highmem CMA, or an iommu_dma_alloc_remap() construction.
+		 */
+		pages = __iommu_dma_get_pages(cpu_addr);
+		if (!pages)
+			page = vmalloc_to_page(cpu_addr);
+		dma_common_free_remap(cpu_addr, alloc_size, VM_USERMAP);
+	} else {
+		/* Lowmem means a coherent atomic or CMA allocation */
+		page = virt_to_page(cpu_addr);
+	}
+
+	if (pages)
+		__iommu_dma_free_pages(pages, count);
+	if (page && !dma_release_from_contiguous(dev, page, count))
+		__free_pages(page, get_order(alloc_size));
+}
+
 static void *iommu_dma_alloc(struct device *dev, size_t size,
 		dma_addr_t *handle, gfp_t gfp, unsigned long attrs)
 {
@@ -1004,46 +1037,6 @@ static void *iommu_dma_alloc(struct device *dev, size_t size,
 	return addr;
 }
 
-static void iommu_dma_free(struct device *dev, size_t size, void *cpu_addr,
-		dma_addr_t handle, unsigned long attrs)
-{
-	size_t iosize = size;
-
-	size = PAGE_ALIGN(size);
-	/*
-	 * @cpu_addr will be one of 4 things depending on how it was allocated:
-	 * - A remapped array of pages for contiguous allocations.
-	 * - A remapped array of pages from iommu_dma_alloc_remap(), for all
-	 *   non-atomic allocations.
-	 * - A non-cacheable alias from the atomic pool, for atomic
-	 *   allocations by non-coherent devices.
-	 * - A normal lowmem address, for atomic allocations by
-	 *   coherent devices.
-	 * Hence how dodgy the below logic looks...
-	 */
-	if (dma_in_atomic_pool(cpu_addr, size)) {
-		__iommu_dma_unmap(dev, handle, iosize);
-		dma_free_from_pool(cpu_addr, size);
-	} else if (attrs & DMA_ATTR_FORCE_CONTIGUOUS) {
-		struct page *page = vmalloc_to_page(cpu_addr);
-
-		__iommu_dma_unmap(dev, handle, iosize);
-		dma_release_from_contiguous(dev, page, size >> PAGE_SHIFT);
-		dma_common_free_remap(cpu_addr, size, VM_USERMAP);
-	} else if (is_vmalloc_addr(cpu_addr)){
-		struct page **pages = __iommu_dma_get_pages(cpu_addr);
-
-		if (!pages)
-			return;
-		__iommu_dma_unmap(dev, handle, iosize);
-		__iommu_dma_free_pages(pages, size >> PAGE_SHIFT);
-		dma_common_free_remap(cpu_addr, size, VM_USERMAP);
-	} else {
-		__iommu_dma_unmap(dev, handle, iosize);
-		__free_pages(virt_to_page(cpu_addr), get_order(size));
-	}
-}
-
 static int __iommu_dma_mmap_pfn(struct vm_area_struct *vma,
 			      unsigned long pfn, size_t size)
 {