iommu/intel-iommu: Enable CONFIG_DMA_DIRECT_OPS=y and clean up intel_{alloc,free}_coherent()

Use the dma_direct_*() helpers and clean up the code flow.
Tested-by: Tom Lendacky <thomas.lendacky@amd.com>
Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Thomas Gleixner <tglx@linutronix.de>
Cc: David Woodhouse <dwmw2@infradead.org>
Cc: Joerg Roedel <joro@8bytes.org>
Cc: Jon Mason <jdmason@kudzu.us>
Cc: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Muli Ben-Yehuda <mulix@mulix.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: iommu@lists.linux-foundation.org
Link: http://lkml.kernel.org/r/20180319103826.12853-9-hch@lst.deSigned-off-by: Ingo Molnar <mingo@kernel.org>

drivers/iommu/Kconfig

@@ -143,6 +143,7 @@ config DMAR_TABLE
 config INTEL_IOMMU
 	bool "Support for Intel IOMMU using DMA Remapping Devices"
 	depends on PCI_MSI && ACPI && (X86 || IA64_GENERIC)
+	select DMA_DIRECT_OPS
 	select IOMMU_API
 	select IOMMU_IOVA
 	select DMAR_TABLE

drivers/iommu/intel-iommu.c

@@ -31,6 +31,7 @@
 #include <linux/pci.h>
 #include <linux/dmar.h>
 #include <linux/dma-mapping.h>
+#include <linux/dma-direct.h>
 #include <linux/mempool.h>
 #include <linux/memory.h>
 #include <linux/cpu.h>
@@ -3708,61 +3709,30 @@ static void *intel_alloc_coherent(struct device *dev, size_t size,
 				  dma_addr_t *dma_handle, gfp_t flags,
 				  unsigned long attrs)
 {
-	struct page *page = NULL;
-	int order;
-
-	size = PAGE_ALIGN(size);
-	order = get_order(size);
-
-	if (!iommu_no_mapping(dev))
-		flags &= ~(GFP_DMA | GFP_DMA32);
-	else if (dev->coherent_dma_mask < dma_get_required_mask(dev)) {
-		if (dev->coherent_dma_mask < DMA_BIT_MASK(32))
-			flags |= GFP_DMA;
-		else
-			flags |= GFP_DMA32;
-	}
-
-	if (gfpflags_allow_blocking(flags)) {
-		unsigned int count = size >> PAGE_SHIFT;
-
-		page = dma_alloc_from_contiguous(dev, count, order, flags);
-		if (page && iommu_no_mapping(dev) &&
-		    page_to_phys(page) + size > dev->coherent_dma_mask) {
-			dma_release_from_contiguous(dev, page, count);
-			page = NULL;
-		}
-	}
+	void *vaddr;
 
-	if (!page)
-		page = alloc_pages(flags, order);
-	if (!page)
-		return NULL;
-	memset(page_address(page), 0, size);
+	vaddr = dma_direct_alloc(dev, size, dma_handle, flags, attrs);
+	if (iommu_no_mapping(dev) || !vaddr)
+		return vaddr;
 
-	*dma_handle = __intel_map_single(dev, page_to_phys(page), size,
-					 DMA_BIDIRECTIONAL,
+	*dma_handle = __intel_map_single(dev, virt_to_phys(vaddr),
+			PAGE_ALIGN(size), DMA_BIDIRECTIONAL,
 			dev->coherent_dma_mask);
-	if (*dma_handle)
-		return page_address(page);
-	if (!dma_release_from_contiguous(dev, page, size >> PAGE_SHIFT))
-		__free_pages(page, order);
+	if (!*dma_handle)
+		goto out_free_pages;
+	return vaddr;
 
+out_free_pages:
+	dma_direct_free(dev, size, vaddr, *dma_handle, attrs);
 	return NULL;
 }
 
 static void intel_free_coherent(struct device *dev, size_t size, void *vaddr,
 				dma_addr_t dma_handle, unsigned long attrs)
 {
-	int order;
-	struct page *page = virt_to_page(vaddr);
-
-	size = PAGE_ALIGN(size);
-	order = get_order(size);
-
-	intel_unmap(dev, dma_handle, size);
-	if (!dma_release_from_contiguous(dev, page, size >> PAGE_SHIFT))
-		__free_pages(page, order);
+	if (!iommu_no_mapping(dev))
+		intel_unmap(dev, dma_handle, PAGE_ALIGN(size));
+	dma_direct_free(dev, size, vaddr, dma_handle, attrs);
 }
 
 static void intel_unmap_sg(struct device *dev, struct scatterlist *sglist,