dma-contiguous: add dma_{alloc,free}_contiguous() helpers

Both dma_alloc_from_contiguous() and dma_release_from_contiguous() are
very simply implemented, but requiring callers to pass certain
parameters like count and align, and taking a boolean parameter to check
__GFP_NOWARN in the allocation flags. So every function call duplicates
similar work:

	unsigned long order = get_order(size);
	size_t count = size >> PAGE_SHIFT;

	page = dma_alloc_from_contiguous(dev, count, order,
			gfp & __GFP_NOWARN);

	[...]

	dma_release_from_contiguous(dev, page, size >> PAGE_SHIFT);

Additionally, as CMA can be used only in the context which permits
sleeping, most of callers do a gfpflags_allow_blocking() check and a
corresponding fallback allocation of normal pages upon any false result:

	if (gfpflags_allow_blocking(flag))
		page = dma_alloc_from_contiguous();
	if (!page)
		page = alloc_pages();

	[...]

	if (!dma_release_from_contiguous(dev, page, count))
		__free_pages(page, get_order(size));

So this patch simplifies those function calls by abstracting these
operations into the two new functions: dma_{alloc,free}_contiguous.

As some callers of dma_{alloc,release}_from_contiguous() might be
complicated, this patch just implements these two new functions to
kernel/dma/direct.c only as an initial step.

Suggested-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Nicolin Chen <nicoleotsuka@gmail.com>
Tested-by: dann frazier <dann.frazier@canonical.com>
Signed-off-by: Christoph Hellwig <hch@lst.de>

include/linux/dma-contiguous.h

@@ -111,6 +111,8 @@ struct page *dma_alloc_from_contiguous(struct device *dev, size_t count,
 				       unsigned int order, bool no_warn);
 bool dma_release_from_contiguous(struct device *dev, struct page *pages,
 				 int count);
+struct page *dma_alloc_contiguous(struct device *dev, size_t size, gfp_t gfp);
+void dma_free_contiguous(struct device *dev, struct page *page, size_t size);
 
 #else
 
@@ -153,6 +155,17 @@ bool dma_release_from_contiguous(struct device *dev, struct page *pages,
 	return false;
 }
 
+static inline struct page *dma_alloc_contiguous(struct device *dev, size_t size,
+		gfp_t gfp)
+{
+	return NULL;
+}
+
+static inline void dma_free_contiguous(struct device *dev, struct page *page,
+		size_t size)
+{
+}
+
 #endif
 
 #endif

kernel/dma/contiguous.c

@@ -214,6 +214,53 @@ bool dma_release_from_contiguous(struct device *dev, struct page *pages,
 	return cma_release(dev_get_cma_area(dev), pages, count);
 }
 
+/**
+ * dma_alloc_contiguous() - allocate contiguous pages
+ * @dev:   Pointer to device for which the allocation is performed.
+ * @size:  Requested allocation size.
+ * @gfp:   Allocation flags.
+ *
+ * This function allocates contiguous memory buffer for specified device. It
+ * first tries to use device specific contiguous memory area if available or
+ * the default global one, then tries a fallback allocation of normal pages.
+ */
+struct page *dma_alloc_contiguous(struct device *dev, size_t size, gfp_t gfp)
+{
+	int node = dev ? dev_to_node(dev) : NUMA_NO_NODE;
+	size_t count = PAGE_ALIGN(size) >> PAGE_SHIFT;
+	size_t align = get_order(PAGE_ALIGN(size));
+	struct cma *cma = dev_get_cma_area(dev);
+	struct page *page = NULL;
+
+	/* CMA can be used only in the context which permits sleeping */
+	if (cma && gfpflags_allow_blocking(gfp)) {
+		align = min_t(size_t, align, CONFIG_CMA_ALIGNMENT);
+		page = cma_alloc(cma, count, align, gfp & __GFP_NOWARN);
+	}
+
+	/* Fallback allocation of normal pages */
+	if (!page)
+		page = alloc_pages_node(node, gfp, align);
+	return page;
+}
+
+/**
+ * dma_free_contiguous() - release allocated pages
+ * @dev:   Pointer to device for which the pages were allocated.
+ * @page:  Pointer to the allocated pages.
+ * @size:  Size of allocated pages.
+ *
+ * This function releases memory allocated by dma_alloc_contiguous(). As the
+ * cma_release returns false when provided pages do not belong to contiguous
+ * area and true otherwise, this function then does a fallback __free_pages()
+ * upon a false-return.
+ */
+void dma_free_contiguous(struct device *dev, struct page *page, size_t size)
+{
+	if (!cma_release(dev_get_cma_area(dev), page, size >> PAGE_SHIFT))
+		__free_pages(page, get_order(size));
+}
+
 /*
  * Support for reserved memory regions defined in device tree
  */

kernel/dma/direct.c

@@ -96,8 +96,6 @@ static bool dma_coherent_ok(struct device *dev, phys_addr_t phys, size_t size)
 struct page *__dma_direct_alloc_pages(struct device *dev, size_t size,
 		dma_addr_t *dma_handle, gfp_t gfp, unsigned long attrs)
 {
-	unsigned int count = PAGE_ALIGN(size) >> PAGE_SHIFT;
-	int page_order = get_order(size);
 	struct page *page = NULL;
 	u64 phys_mask;
 
@@ -109,20 +107,9 @@ struct page *__dma_direct_alloc_pages(struct device *dev, size_t size,
 	gfp |= __dma_direct_optimal_gfp_mask(dev, dev->coherent_dma_mask,
 			&phys_mask);
 again:
-	/* CMA can be used only in the context which permits sleeping */
+	page = dma_alloc_contiguous(dev, size, gfp);
-	if (gfpflags_allow_blocking(gfp)) {
-		page = dma_alloc_from_contiguous(dev, count, page_order,
-						 gfp & __GFP_NOWARN);
-		if (page && !dma_coherent_ok(dev, page_to_phys(page), size)) {
-			dma_release_from_contiguous(dev, page, count);
-			page = NULL;
-		}
-	}
-	if (!page)
-		page = alloc_pages_node(dev_to_node(dev), gfp, page_order);
-
 	if (page && !dma_coherent_ok(dev, page_to_phys(page), size)) {
-		__free_pages(page, page_order);
+		dma_free_contiguous(dev, page, size);
 		page = NULL;
 
 		if (IS_ENABLED(CONFIG_ZONE_DMA32) &&
@@ -154,7 +141,7 @@ void *dma_direct_alloc_pages(struct device *dev, size_t size,
 	if (PageHighMem(page)) {
 		/*
 		 * Depending on the cma= arguments and per-arch setup
-		 * dma_alloc_from_contiguous could return highmem pages.
+		 * dma_alloc_contiguous could return highmem pages.
 		 * Without remapping there is no way to return them here,
 		 * so log an error and fail.
 		 */
@@ -176,10 +163,7 @@ void *dma_direct_alloc_pages(struct device *dev, size_t size,
 
 void __dma_direct_free_pages(struct device *dev, size_t size, struct page *page)
 {
-	unsigned int count = PAGE_ALIGN(size) >> PAGE_SHIFT;
+	dma_free_contiguous(dev, page, size);
-
-	if (!dma_release_from_contiguous(dev, page, count))
-		__free_pages(page, get_order(size));
 }
 
 void dma_direct_free_pages(struct device *dev, size_t size, void *cpu_addr,