Merge branch 'x86-dma-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull x86 dma mapping updates from Ingo Molnar:
 "This tree, by Christoph Hellwig, switches over the x86 architecture to
  the generic dma-direct and swiotlb code, and also unifies more of the
  dma-direct code between architectures. The now unused x86-only
  primitives are removed"

* 'x86-dma-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  dma-mapping: Don't clear GFP_ZERO in dma_alloc_attrs
  swiotlb: Make swiotlb_{alloc,free}_buffer depend on CONFIG_DMA_DIRECT_OPS
  dma/swiotlb: Remove swiotlb_{alloc,free}_coherent()
  dma/direct: Handle force decryption for DMA coherent buffers in common code
  dma/direct: Handle the memory encryption bit in common code
  dma/swiotlb: Remove swiotlb_set_mem_attributes()
  set_memory.h: Provide set_memory_{en,de}crypted() stubs
  x86/dma: Remove dma_alloc_coherent_gfp_flags()
  iommu/intel-iommu: Enable CONFIG_DMA_DIRECT_OPS=y and clean up intel_{alloc,free}_coherent()
  iommu/amd_iommu: Use CONFIG_DMA_DIRECT_OPS=y and dma_direct_{alloc,free}()
  x86/dma/amd_gart: Use dma_direct_{alloc,free}()
  x86/dma/amd_gart: Look at dev->coherent_dma_mask instead of GFP_DMA
  x86/dma: Use generic swiotlb_ops
  x86/dma: Use DMA-direct (CONFIG_DMA_DIRECT_OPS=y)
  x86/dma: Remove dma_alloc_coherent_mask()

4 files changed, 46 insertions, 112 deletions

diff --git a/drivers/iommu/Kconfig b/drivers/iommu/Kconfig
index f3a21343e636..df171cb85822 100644
--- a/drivers/iommu/Kconfig
+++ b/drivers/iommu/Kconfig
@@ -107,6 +107,7 @@ config IOMMU_PGTABLES_L2
 # AMD IOMMU support
 config AMD_IOMMU
 	bool "AMD IOMMU support"
+	select DMA_DIRECT_OPS
 	select SWIOTLB
 	select PCI_MSI
 	select PCI_ATS
@@ -142,6 +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
diff --git a/drivers/iommu/amd_iommu.c b/drivers/iommu/amd_iommu.c
index 74788fdeb773..83819d0cbf90 100644
--- a/drivers/iommu/amd_iommu.c
+++ b/drivers/iommu/amd_iommu.c
@@ -28,6 +28,7 @@
 #include <linux/debugfs.h>
 #include <linux/scatterlist.h>
 #include <linux/dma-mapping.h>
+#include <linux/dma-direct.h>
 #include <linux/iommu-helper.h>
 #include <linux/iommu.h>
 #include <linux/delay.h>
@@ -2193,7 +2194,7 @@ static int amd_iommu_add_device(struct device *dev)
 				dev_name(dev));
 
 		iommu_ignore_device(dev);
-		dev->dma_ops = &nommu_dma_ops;
+		dev->dma_ops = &dma_direct_ops;
 		goto out;
 	}
 	init_iommu_group(dev);
@@ -2599,51 +2600,32 @@ static void *alloc_coherent(struct device *dev, size_t size,
 			    unsigned long attrs)
 {
 	u64 dma_mask = dev->coherent_dma_mask;
-	struct protection_domain *domain;
-	struct dma_ops_domain *dma_dom;
-	struct page *page;
-
-	domain = get_domain(dev);
-	if (PTR_ERR(domain) == -EINVAL) {
-		page = alloc_pages(flag, get_order(size));
-		*dma_addr = page_to_phys(page);
-		return page_address(page);
-	} else if (IS_ERR(domain))
-		return NULL;
+	struct protection_domain *domain = get_domain(dev);
+	bool is_direct = false;
+	void *virt_addr;
 
-	dma_dom   = to_dma_ops_domain(domain);
-	size	  = PAGE_ALIGN(size);
-	dma_mask  = dev->coherent_dma_mask;
-	flag     &= ~(__GFP_DMA | __GFP_HIGHMEM | __GFP_DMA32);
-	flag     |= __GFP_ZERO;
-
-	page = alloc_pages(flag | __GFP_NOWARN,  get_order(size));
-	if (!page) {
-		if (!gfpflags_allow_blocking(flag))
-			return NULL;
-
-		page = dma_alloc_from_contiguous(dev, size >> PAGE_SHIFT,
-						 get_order(size), flag);
-		if (!page)
+	if (IS_ERR(domain)) {
+		if (PTR_ERR(domain) != -EINVAL)
 			return NULL;
+		is_direct = true;
 	}
 
+	virt_addr = dma_direct_alloc(dev, size, dma_addr, flag, attrs);
+	if (!virt_addr || is_direct)
+		return virt_addr;
+
 	if (!dma_mask)
 		dma_mask = *dev->dma_mask;
 
-	*dma_addr = __map_single(dev, dma_dom, page_to_phys(page),
-				 size, DMA_BIDIRECTIONAL, dma_mask);
-
+	*dma_addr = __map_single(dev, to_dma_ops_domain(domain),
+			virt_to_phys(virt_addr), PAGE_ALIGN(size),
+			DMA_BIDIRECTIONAL, dma_mask);
 	if (*dma_addr == AMD_IOMMU_MAPPING_ERROR)
 		goto out_free;
-
-	return page_address(page);
+	return virt_addr;
 
 out_free:
-
-	if (!dma_release_from_contiguous(dev, page, size >> PAGE_SHIFT))
-		__free_pages(page, get_order(size));
-
+	dma_direct_free(dev, size, virt_addr, *dma_addr, attrs);
 	return NULL;
 }
 
@@ -2654,24 +2636,17 @@ static void free_coherent(struct device *dev, size_t size,
 			  void *virt_addr, dma_addr_t dma_addr,
 			  unsigned long attrs)
 {
-	struct protection_domain *domain;
-	struct dma_ops_domain *dma_dom;
-	struct page *page;
+	struct protection_domain *domain = get_domain(dev);
 
-	page = virt_to_page(virt_addr);
 	size = PAGE_ALIGN(size);
 
-	domain = get_domain(dev);
-	if (IS_ERR(domain))
-		goto free_mem;
+	if (!IS_ERR(domain)) {
+		struct dma_ops_domain *dma_dom = to_dma_ops_domain(domain);
 
-	dma_dom = to_dma_ops_domain(domain);
-
-	__unmap_single(dma_dom, dma_addr, size, DMA_BIDIRECTIONAL);
+		__unmap_single(dma_dom, dma_addr, size, DMA_BIDIRECTIONAL);
+	}
 
-free_mem:
-	if (!dma_release_from_contiguous(dev, page, size >> PAGE_SHIFT))
-		__free_pages(page, get_order(size));
+	dma_direct_free(dev, size, virt_addr, dma_addr, attrs);
 }
 
 /*
@@ -2680,7 +2655,7 @@ free_mem:
  */
 static int amd_iommu_dma_supported(struct device *dev, u64 mask)
 {
-	if (!x86_dma_supported(dev, mask))
+	if (!dma_direct_supported(dev, mask))
 		return 0;
 	return check_device(dev);
 }
@@ -2794,7 +2769,7 @@ int __init amd_iommu_init_dma_ops(void)
 	 * continue to be SWIOTLB.
 	 */
 	if (!swiotlb)
-		dma_ops = &nommu_dma_ops;
+		dma_ops = &dma_direct_ops;
 
 	if (amd_iommu_unmap_flush)
 		pr_info("AMD-Vi: IO/TLB flush on unmap enabled\n");
diff --git a/drivers/iommu/intel-iommu.c b/drivers/iommu/intel-iommu.c
index 582fd01cb7d1..24d1b1b42013 100644
--- a/drivers/iommu/intel-iommu.c
+++ b/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>
@@ -45,6 +46,7 @@
 #include <linux/pci-ats.h>
 #include <linux/memblock.h>
 #include <linux/dma-contiguous.h>
+#include <linux/dma-direct.h>
 #include <linux/crash_dump.h>
 #include <asm/irq_remapping.h>
 #include <asm/cacheflush.h>
@@ -3707,61 +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;
+	void *vaddr;
 
-	size = PAGE_ALIGN(size);
-	order = get_order(size);
+	vaddr = dma_direct_alloc(dev, size, dma_handle, flags, attrs);
+	if (iommu_no_mapping(dev) || !vaddr)
+		return vaddr;
 
-	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;
-		}
-	}
-
-	if (!page)
-		page = alloc_pages(flags, order);
-	if (!page)
-		return NULL;
-	memset(page_address(page), 0, size);
-
-	*dma_handle = __intel_map_single(dev, page_to_phys(page), 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);
+	*dma_handle = __intel_map_single(dev, virt_to_phys(vaddr),
+			PAGE_ALIGN(size), DMA_BIDIRECTIONAL,
+			dev->coherent_dma_mask);
+	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,
@@ -3871,7 +3842,7 @@ const struct dma_map_ops intel_dma_ops = {
 	.unmap_page = intel_unmap_page,
 	.mapping_error = intel_mapping_error,
 #ifdef CONFIG_X86
-	.dma_supported = x86_dma_supported,
+	.dma_supported = dma_direct_supported,
 #endif
 };
 
diff --git a/drivers/xen/swiotlb-xen.c b/drivers/xen/swiotlb-xen.c
index 5bb72d3f8337..e1c60899fdbc 100644
--- a/drivers/xen/swiotlb-xen.c
+++ b/drivers/xen/swiotlb-xen.c
@@ -53,20 +53,6 @@
  * API.
  */
 
-#ifndef CONFIG_X86
-static unsigned long dma_alloc_coherent_mask(struct device *dev,
-					    gfp_t gfp)
-{
-	unsigned long dma_mask = 0;
-
-	dma_mask = dev->coherent_dma_mask;
-	if (!dma_mask)
-		dma_mask = (gfp & GFP_DMA) ? DMA_BIT_MASK(24) : DMA_BIT_MASK(32);
-
-	return dma_mask;
-}
-#endif
-
 #define XEN_SWIOTLB_ERROR_CODE	(~(dma_addr_t)0x0)
 
 static char *xen_io_tlb_start, *xen_io_tlb_end;
@@ -328,7 +314,7 @@ xen_swiotlb_alloc_coherent(struct device *hwdev, size_t size,
 		return ret;
 
 	if (hwdev && hwdev->coherent_dma_mask)
-		dma_mask = dma_alloc_coherent_mask(hwdev, flags);
+		dma_mask = hwdev->coherent_dma_mask;
 
 	/* At this point dma_handle is the physical address, next we are
 	 * going to set it to the machine address.