iommu/dma: Finish optimising higher-order allocations

Now that we know exactly which page sizes our caller wants to use in the
given domain, we can restrict higher-order allocation attempts to just
those sizes, if any, and avoid wasting any time or effort on other sizes
which offer no benefit. In the same vein, this also lets us accommodate
a minimum order greater than 0 for special cases.

Signed-off-by: Robin Murphy <robin.murphy@arm.com>
Acked-by: Will Deacon <will.deacon@arm.com>
Tested-by: Yong Wu <yong.wu@mediatek.com>
Signed-off-by: Joerg Roedel <jroedel@suse.de>

drivers/iommu/dma-iommu.c

@@ -190,11 +190,15 @@ static void __iommu_dma_free_pages(struct page **pages, int count)
 	kvfree(pages);
 }
 
-static struct page **__iommu_dma_alloc_pages(unsigned int count, gfp_t gfp)
+static struct page **__iommu_dma_alloc_pages(unsigned int count,
+		unsigned long order_mask, gfp_t gfp)
 {
 	struct page **pages;
 	unsigned int i = 0, array_size = count * sizeof(*pages);
-	unsigned int order = MAX_ORDER;
+
+	order_mask &= (2U << MAX_ORDER) - 1;
+	if (!order_mask)
+		return NULL;
 
 	if (array_size <= PAGE_SIZE)
 		pages = kzalloc(array_size, GFP_KERNEL);
@@ -208,36 +212,38 @@ static struct page **__iommu_dma_alloc_pages(unsigned int count, gfp_t gfp)
 
 	while (count) {
 		struct page *page = NULL;
-		int j;
+		unsigned int order_size;
 
 		/*
 		 * Higher-order allocations are a convenience rather
 		 * than a necessity, hence using __GFP_NORETRY until
-		 * falling back to single-page allocations.
+		 * falling back to minimum-order allocations.
 		 */
-		for (order = min_t(unsigned int, order, __fls(count));
-		     order > 0; order--) {
-			page = alloc_pages(gfp | __GFP_NORETRY, order);
+		for (order_mask &= (2U << __fls(count)) - 1;
+		     order_mask; order_mask &= ~order_size) {
+			unsigned int order = __fls(order_mask);
+
+			order_size = 1U << order;
+			page = alloc_pages((order_mask - order_size) ?
+					   gfp | __GFP_NORETRY : gfp, order);
 			if (!page)
 				continue;
-			if (PageCompound(page)) {
-				if (!split_huge_page(page))
-					break;
-				__free_pages(page, order);
-			} else {
+			if (!order)
+				break;
+			if (!PageCompound(page)) {
 				split_page(page, order);
 				break;
+			} else if (!split_huge_page(page)) {
+				break;
 			}
+			__free_pages(page, order);
 		}
-		if (!page)
-			page = alloc_page(gfp);
 		if (!page) {
 			__iommu_dma_free_pages(pages, i);
 			return NULL;
 		}
-		j = 1 << order;
-		count -= j;
-		while (j--)
+		count -= order_size;
+		while (order_size--)
 			pages[i++] = page++;
 	}
 	return pages;
@@ -267,6 +273,7 @@ void iommu_dma_free(struct device *dev, struct page **pages, size_t size,
  *	 attached to an iommu_dma_domain
  * @size: Size of buffer in bytes
  * @gfp: Allocation flags
+ * @attrs: DMA attributes for this allocation
  * @prot: IOMMU mapping flags
  * @handle: Out argument for allocated DMA handle
  * @flush_page: Arch callback which must ensure PAGE_SIZE bytes from the
@@ -278,8 +285,8 @@ void iommu_dma_free(struct device *dev, struct page **pages, size_t size,
  * Return: Array of struct page pointers describing the buffer,
  *	   or NULL on failure.
  */
-struct page **iommu_dma_alloc(struct device *dev, size_t size,
-		gfp_t gfp, int prot, dma_addr_t *handle,
+struct page **iommu_dma_alloc(struct device *dev, size_t size, gfp_t gfp,
+		struct dma_attrs *attrs, int prot, dma_addr_t *handle,
 		void (*flush_page)(struct device *, const void *, phys_addr_t))
 {
 	struct iommu_domain *domain = iommu_get_domain_for_dev(dev);
@@ -288,11 +295,22 @@ struct page **iommu_dma_alloc(struct device *dev, size_t size,
 	struct page **pages;
 	struct sg_table sgt;
 	dma_addr_t dma_addr;
-	unsigned int count = PAGE_ALIGN(size) >> PAGE_SHIFT;
+	unsigned int count, min_size, alloc_sizes = domain->pgsize_bitmap;
 
 	*handle = DMA_ERROR_CODE;
 
-	pages = __iommu_dma_alloc_pages(count, gfp);
+	min_size = alloc_sizes & -alloc_sizes;
+	if (min_size < PAGE_SIZE) {
+		min_size = PAGE_SIZE;
+		alloc_sizes |= PAGE_SIZE;
+	} else {
+		size = ALIGN(size, min_size);
+	}
+	if (dma_get_attr(DMA_ATTR_ALLOC_SINGLE_PAGES, attrs))
+		alloc_sizes = min_size;
+
+	count = PAGE_ALIGN(size) >> PAGE_SHIFT;
+	pages = __iommu_dma_alloc_pages(count, alloc_sizes >> PAGE_SHIFT, gfp);
 	if (!pages)
 		return NULL;