arm64: Enable CMA

arm64 bit targets need the features CMA provides. Add the appropriate
hooks, header files, and Kconfig to allow this to happen.

Cc: Will Deacon <will.deacon@arm.com>
Cc: Marek Szyprowski <m.szyprowski@samsung.com>
Signed-off-by: Laura Abbott <lauraa@codeaurora.org>
Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
(cherry picked from commit 6ac2104debc235b745265b64d610237a6833fd53)
Signed-off-by: Alex Shi <alex.shi@linaro.org>

Conflicts:
	arch/arm64/Kconfig

(cherry picked from commit 0a4b0f00f4c9cb80a0fb11b9e0f898f82745e370)
Signed-off-by: Alex Shi <alex.shi@linaro.org>

Conflicts:
	arch/arm64/mm/dma-mapping.c

2 files changed, 31 insertions, 2 deletions

diff --git a/arch/arm64/mm/dma-mapping.c b/arch/arm64/mm/dma-mapping.c
index 4bd7579ec9e6..c4c005cc2ed2 100644
--- a/arch/arm64/mm/dma-mapping.c
+++ b/arch/arm64/mm/dma-mapping.c
@@ -21,6 +21,7 @@
 #include <linux/export.h>
 #include <linux/slab.h>
 #include <linux/dma-mapping.h>
+#include <linux/dma-contiguous.h>
 #include <linux/vmalloc.h>
 #include <linux/swiotlb.h>
 
@@ -36,14 +37,39 @@ static void *arm64_swiotlb_alloc_coherent(struct device *dev, size_t size,
 	if (IS_ENABLED(CONFIG_ZONE_DMA32) &&
 	    dev->coherent_dma_mask <= DMA_BIT_MASK(32))
 		flags |= GFP_DMA32;
-	return swiotlb_alloc_coherent(dev, size, dma_handle, flags);
+	if (IS_ENABLED(CONFIG_DMA_CMA)) {
+		struct page *page;
+
+		page = dma_alloc_from_contiguous(dev, size >> PAGE_SHIFT,
+							get_order(size));
+		if (!page)
+			return NULL;
+
+		*dma_handle = phys_to_dma(dev, page_to_phys(page));
+		return page_address(page);
+	} else {
+		return swiotlb_alloc_coherent(dev, size, dma_handle, flags);
+	}
 }
 
 static void arm64_swiotlb_free_coherent(struct device *dev, size_t size,
 					void *vaddr, dma_addr_t dma_handle,
 					struct dma_attrs *attrs)
 {
-	swiotlb_free_coherent(dev, size, vaddr, dma_handle);
+	if (dev == NULL) {
+		WARN_ONCE(1, "Use an actual device structure for DMA allocation\n");
+		return;
+	}
+
+	if (IS_ENABLED(CONFIG_DMA_CMA)) {
+		phys_addr_t paddr = dma_to_phys(dev, dma_handle);
+
+		dma_release_from_contiguous(dev,
+					phys_to_page(paddr),
+					size >> PAGE_SHIFT);
+	} else {
+		swiotlb_free_coherent(dev, size, vaddr, dma_handle);
+	}
 }
 
 static struct dma_map_ops arm64_swiotlb_dma_ops = {
diff --git a/arch/arm64/mm/init.c b/arch/arm64/mm/init.c
index f497ca77925a..851d3c137e03 100644
--- a/arch/arm64/mm/init.c
+++ b/arch/arm64/mm/init.c
@@ -30,6 +30,7 @@
 #include <linux/memblock.h>
 #include <linux/sort.h>
 #include <linux/of_fdt.h>
+#include <linux/dma-contiguous.h>
 
 #include <asm/prom.h>
 #include <asm/sections.h>
@@ -173,6 +174,8 @@ void __init arm64_memblock_init(void)
 		memblock_reserve(base, size);
 	}
 
+	dma_contiguous_reserve(0);
+
 	memblock_allow_resize();
 	memblock_dump_all();
 }